diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 44f52a4f5903..cbbd3e069945 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -60,3 +60,62 @@ Description:
 		Indicates whether the block layer should automatically
 		generate checksums for write requests bound for
 		devices that support receiving integrity metadata.
+
+What:		/sys/block/<disk>/alignment_offset
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a physical block size that is
+		bigger than the logical block size (for instance a drive
+		with 4KB physical sectors exposing 512-byte logical
+		blocks to the operating system).  This parameter
+		indicates how many bytes the beginning of the device is
+		offset from the disk's natural alignment.
+
+What:		/sys/block/<disk>/<partition>/alignment_offset
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a physical block size that is
+		bigger than the logical block size (for instance a drive
+		with 4KB physical sectors exposing 512-byte logical
+		blocks to the operating system).  This parameter
+		indicates how many bytes the beginning of the partition
+		is offset from the disk's natural alignment.
+
+What:		/sys/block/<disk>/queue/logical_block_size
+Date:		May 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		This is the smallest unit the storage device can
+		address.  It is typically 512 bytes.
+
+What:		/sys/block/<disk>/queue/physical_block_size
+Date:		May 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		This is the smallest unit the storage device can write
+		without resorting to read-modify-write operation.  It is
+		usually the same as the logical block size but may be
+		bigger.  One example is SATA drives with 4KB sectors
+		that expose a 512-byte logical block size to the
+		operating system.
+
+What:		/sys/block/<disk>/queue/minimum_io_size
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a preferred minimum I/O size,
+		which is the smallest request the device can perform
+		without incurring a read-modify-write penalty.  For disk
+		drives this is often the physical block size.  For RAID
+		arrays it is often the stripe chunk size.
+
+What:		/sys/block/<disk>/queue/optimal_io_size
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report an optimal I/O size, which is
+		the device's preferred unit of receiving I/O.  This is
+		rarely reported for disk drives.  For RAID devices it is
+		usually the stripe width or the internal block size.
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
new file mode 100644
index 000000000000..0a92a7c93a62
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
@@ -0,0 +1,33 @@
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/model
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 0 model for logical drive
+		Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/rev
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 0 revision for logical
+		drive Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/unique_id
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 83 serial number for logical
+		drive Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/vendor
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	Displays the SCSI INQUIRY page 0 vendor for logical drive
+		Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/block:cciss!cXdY
+Date:		March 2009
+Kernel Version: 2.6.30
+Contact:	iss_storagedev@hp.com
+Description:	A symbolic link to /sys/block/cciss!cXdY
diff --git a/Documentation/ABI/testing/sysfs-devices-cache_disable b/Documentation/ABI/testing/sysfs-devices-cache_disable
new file mode 100644
index 000000000000..175bb4f70512
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-cache_disable
@@ -0,0 +1,18 @@
+What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
+Date:      August 2008
+KernelVersion:	2.6.27
+Contact:	mark.langsdorf@amd.com
+Description:	These files exist in every cpu's cache index directories.
+		There are currently 2 cache_disable_# files in each
+		directory.  Reading from these files on a supported
+		processor will return that cache disable index value
+		for that processor and node.  Writing to one of these
+		files will cause the specificed cache index to be disabled.
+
+		Currently, only AMD Family 10h Processors support cache index
+		disable, and only for their L3 caches.  See the BIOS and
+		Kernel Developer's Guide at
+		http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
+		for formatting information and other details on the
+		cache index disable.
+Users:    joachim.deguara@amd.com
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index d9aa43d78bcc..25fb8bcf32a2 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -704,12 +704,24 @@ this directory the following files can currently be found:
 				The current number of free dma_debug_entries
 				in the allocator.
 
+	dma-api/driver-filter
+				You can write a name of a driver into this file
+				to limit the debug output to requests from that
+				particular driver. Write an empty string to
+				that file to disable the filter and see
+				all errors again.
+
 If you have this code compiled into your kernel it will be enabled by default.
 If you want to boot without the bookkeeping anyway you can provide
 'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
 Notice that you can not enable it again at runtime. You have to reboot to do
 so.
 
+If you want to see debug messages only for a special device driver you can
+specify the dma_debug_driver=<drivername> parameter. This will enable the
+driver filter at boot time. The debug code will only print errors for that
+driver afterwards. This filter can be disabled or changed later using debugfs.
+
 When the code disables itself at runtime this is most likely because it ran
 out of dma_debug_entries. These entries are preallocated at boot. The number
 of preallocated entries is defined per architecture. If it is too low for you
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index b1eb661e6302..9632444f6c62 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -13,7 +13,8 @@ DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
 	    mac80211.xml debugobjects.xml sh.xml regulator.xml \
-	    alsa-driver-api.xml writing-an-alsa-driver.xml
+	    alsa-driver-api.xml writing-an-alsa-driver.xml \
+	    tracepoint.xml
 
 ###
 # The build process is as follows (targets):
diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl
new file mode 100644
index 000000000000..b0756d0fd579
--- /dev/null
+++ b/Documentation/DocBook/tracepoint.tmpl
@@ -0,0 +1,89 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
+	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
+
+<book id="Tracepoints">
+ <bookinfo>
+  <title>The Linux Kernel Tracepoint API</title>
+
+  <authorgroup>
+   <author>
+    <firstname>Jason</firstname>
+    <surname>Baron</surname>
+    <affiliation>
+     <address>
+      <email>jbaron@redhat.com</email>
+     </address>
+    </affiliation>
+   </author>
+  </authorgroup>
+
+  <legalnotice>
+   <para>
+     This documentation is free software; you can redistribute
+     it and/or modify it under the terms of the GNU General Public
+     License as published by the Free Software Foundation; either
+     version 2 of the License, or (at your option) any later
+     version.
+   </para>
+
+   <para>
+     This program is distributed in the hope that it will be
+     useful, but WITHOUT ANY WARRANTY; without even the implied
+     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+     See the GNU General Public License for more details.
+   </para>
+
+   <para>
+     You should have received a copy of the GNU General Public
+     License along with this program; if not, write to the Free
+     Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+     MA 02111-1307 USA
+   </para>
+
+   <para>
+     For more details see the file COPYING in the source
+     distribution of Linux.
+   </para>
+  </legalnotice>
+ </bookinfo>
+
+ <toc></toc>
+  <chapter id="intro">
+   <title>Introduction</title>
+   <para>
+     Tracepoints are static probe points that are located in strategic points
+     throughout the kernel. 'Probes' register/unregister with tracepoints
+     via a callback mechanism. The 'probes' are strictly typed functions that
+     are passed a unique set of parameters defined by each tracepoint.
+   </para>
+
+   <para>
+     From this simple callback mechanism, 'probes' can be used to profile, debug,
+     and understand kernel behavior. There are a number of tools that provide a
+     framework for using 'probes'. These tools include Systemtap, ftrace, and
+     LTTng.
+   </para>
+
+   <para>
+     Tracepoints are defined in a number of header files via various macros. Thus,
+     the purpose of this document is to provide a clear accounting of the available
+     tracepoints. The intention is to understand not only what tracepoints are
+     available but also to understand where future tracepoints might be added.
+   </para>
+
+   <para>
+     The API presented has functions of the form:
+     <function>trace_tracepointname(function parameters)</function>. These are the
+     tracepoints callbacks that are found throughout the code. Registering and
+     unregistering probes with these callback sites is covered in the
+     <filename>Documentation/trace/*</filename> directory.
+   </para>
+  </chapter>
+
+  <chapter id="irq">
+   <title>IRQ</title>
+!Iinclude/trace/events/irq.h
+  </chapter>
+
+</book>
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 068848240a8b..02cced183b2d 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -192,23 +192,24 @@ rcu/rcuhier (which displays the struct rcu_node hierarchy).
 The output of "cat rcu/rcudata" looks as follows:
 
 rcu:
-  0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10
-  1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10
-  2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10
-  3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10
-  4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10
-  5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10
-  6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10
-  7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10
+rcu:
+  0 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=10951/1 dn=0 df=1101 of=0 ri=36 ql=0 b=10
+  1 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=16117/1 dn=0 df=1015 of=0 ri=0 ql=0 b=10
+  2 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1445/1 dn=0 df=1839 of=0 ri=0 ql=0 b=10
+  3 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=6681/1 dn=0 df=1545 of=0 ri=0 ql=0 b=10
+  4 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1003/1 dn=0 df=1992 of=0 ri=0 ql=0 b=10
+  5 c=17829 g=17830 pq=1 pqc=17829 qp=1 dt=3887/1 dn=0 df=3331 of=0 ri=4 ql=2 b=10
+  6 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=859/1 dn=0 df=3224 of=0 ri=0 ql=0 b=10
+  7 c=17829 g=17830 pq=0 pqc=17829 qp=1 dt=3761/1 dn=0 df=1818 of=0 ri=0 ql=2 b=10
 rcu_bh:
-  0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10
-  1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10
-  2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10
-  3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10
-  4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
-  5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
-  6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
-  7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
+  0 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=10951/1 dn=0 df=0 of=0 ri=0 ql=0 b=10
+  1 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=16117/1 dn=0 df=13 of=0 ri=0 ql=0 b=10
+  2 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1445/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  3 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=6681/1 dn=0 df=9 of=0 ri=0 ql=0 b=10
+  4 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1003/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  5 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3887/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
+  7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
 
 The first section lists the rcu_data structures for rcu, the second for
 rcu_bh.  Each section has one line per CPU, or eight for this 8-CPU system.
@@ -253,12 +254,6 @@ o	"pqc" indicates which grace period the last-observed quiescent
 o	"qp" indicates that RCU still expects a quiescent state from
 	this CPU.
 
-o	"rpfq" is the number of rcu_pending() calls on this CPU required
-	to induce this CPU to invoke force_quiescent_state().
-
-o	"rp" is low-order four hex digits of the count of how many times
-	rcu_pending() has been invoked on this CPU.
-
 o	"dt" is the current value of the dyntick counter that is incremented
 	when entering or leaving dynticks idle state, either by the
 	scheduler or by irq.  The number after the "/" is the interrupt
@@ -305,6 +300,9 @@ o	"b" is the batch limit for this CPU.  If more than this number
 	of RCU callbacks is ready to invoke, then the remainder will
 	be deferred.
 
+There is also an rcu/rcudata.csv file with the same information in
+comma-separated-variable spreadsheet format.
+
 
 The output of "cat rcu/rcugp" looks as follows:
 
@@ -411,3 +409,63 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 		For example, the first entry at the lowest level shows
 		"^0", indicating that it corresponds to bit zero in
 		the first entry at the middle level.
+
+
+The output of "cat rcu/rcu_pending" looks as follows:
+
+rcu:
+  0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+  1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+  2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+  3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+  4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+  5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+  6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+  7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+rcu_bh:
+  0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+  1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+  2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+  3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+  4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+  5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+  6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+  7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+
+As always, this is once again split into "rcu" and "rcu_bh" portions.
+The fields are as follows:
+
+o	"np" is the number of times that __rcu_pending() has been invoked
+	for the corresponding flavor of RCU.
+
+o	"qsp" is the number of times that the RCU was waiting for a
+	quiescent state from this CPU.
+
+o	"cbr" is the number of times that this CPU had RCU callbacks
+	that had passed through a grace period, and were thus ready
+	to be invoked.
+
+o	"cng" is the number of times that this CPU needed another
+	grace period while RCU was idle.
+
+o	"gpc" is the number of times that an old grace period had
+	completed, but this CPU was not yet aware of it.
+
+o	"gps" is the number of times that a new grace period had started,
+	but this CPU was not yet aware of it.
+
+o	"nf" is the number of times that this CPU suspected that the
+	current grace period had run for too long, and thus needed to
+	be forced.
+
+	Please note that "forcing" consists of sending resched IPIs
+	to holdout CPUs.  If that CPU really still is in an old RCU
+	read-side critical section, then we really do have to wait for it.
+	The assumption behing "forcing" is that the CPU is not still in
+	an old RCU read-side critical section, but has not yet responded
+	for some other reason.
+
+o	"nn" is the number of times that this CPU needed nothing.  Alert
+	readers will note that the rcu "nn" number for a given CPU very
+	closely matches the rcu_bh "np" number for that same CPU.  This
+	is due to short-circuit evaluation in rcu_pending().
diff --git a/Documentation/Smack.txt b/Documentation/Smack.txt
index 629c92e99783..34614b4c708e 100644
--- a/Documentation/Smack.txt
+++ b/Documentation/Smack.txt
@@ -184,8 +184,9 @@ length. Single character labels using special characters, that being anything
 other than a letter or digit, are reserved for use by the Smack development
 team. Smack labels are unstructured, case sensitive, and the only operation
 ever performed on them is comparison for equality. Smack labels cannot
-contain unprintable characters or the "/" (slash) character. Smack labels
-cannot begin with a '-', which is reserved for special options.
+contain unprintable characters, the "/" (slash), the "\" (backslash), the "'"
+(quote) and '"' (double-quote) characters.
+Smack labels cannot begin with a '-', which is reserved for special options.
 
 There are some predefined labels:
 
@@ -523,3 +524,18 @@ Smack supports some mount options:
 
 These mount options apply to all file system types.
 
+Smack auditing
+
+If you want Smack auditing of security events, you need to set CONFIG_AUDIT
+in your kernel configuration.
+By default, all denied events will be audited. You can change this behavior by
+writing a single character to the /smack/logging file :
+0 : no logging
+1 : log denied (default)
+2 : log accepted
+3 : log denied & accepted
+
+Events are logged as 'key=value' pairs, for each event you at least will get
+the subjet, the object, the rights requested, the action, the kernel function
+that triggered the event, plus other pairs depending on the type of event
+audited.
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 6fab97ea7e6b..8d2158a1c6aa 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
+Note: Please refer to Documentation/DMA-mapping.txt for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 
diff --git a/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt
index 4dae9a3840bf..0494f78d87e4 100644
--- a/Documentation/filesystems/gfs2-glocks.txt
+++ b/Documentation/filesystems/gfs2-glocks.txt
@@ -60,7 +60,7 @@ go_lock          | Called for the first local holder of a lock
 go_unlock        | Called on the final local unlock of a lock
 go_dump          | Called to print content of object for debugfs file, or on
                  | error to dump glock to the log.
-go_type;         | The type of the glock, LM_TYPE_.....
+go_type          | The type of the glock, LM_TYPE_.....
 go_min_hold_time | The minimum hold time
 
 The minimum hold time for each lock is the time after a remote lock
diff --git a/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.txt
index 593004b6bbab..5e3ab8f3beff 100644
--- a/Documentation/filesystems/gfs2.txt
+++ b/Documentation/filesystems/gfs2.txt
@@ -11,18 +11,15 @@ their I/O so file system consistency is maintained.  One of the nifty
 features of GFS is perfect consistency -- changes made to the file system
 on one machine show up immediately on all other machines in the cluster.
 
-GFS uses interchangable inter-node locking mechanisms.  Different lock
-modules can plug into GFS and each file system selects the appropriate
-lock module at mount time.  Lock modules include:
+GFS uses interchangable inter-node locking mechanisms, the currently
+supported mechanisms are:
 
   lock_nolock -- allows gfs to be used as a local file system
 
   lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking
   The dlm is found at linux/fs/dlm/
 
-In addition to interfacing with an external locking manager, a gfs lock
-module is responsible for interacting with external cluster management
-systems.  Lock_dlm depends on user space cluster management systems found
+Lock_dlm depends on user space cluster management systems found
 at the URL above.
 
 To use gfs as a local file system, no external clustering systems are
@@ -31,13 +28,19 @@ needed, simply:
   $ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device
   $ mount -t gfs2 /dev/block_device /dir
 
-GFS2 is not on-disk compatible with previous versions of GFS.
+If you are using Fedora, you need to install the gfs2-utils package
+and, for lock_dlm, you will also need to install the cman package
+and write a cluster.conf as per the documentation.
+
+GFS2 is not on-disk compatible with previous versions of GFS, but it
+is pretty close.
 
 The following man pages can be found at the URL above:
-  gfs2_fsck	to repair a filesystem
+  fsck.gfs2	to repair a filesystem
   gfs2_grow	to expand a filesystem online
   gfs2_jadd	to add journals to a filesystem online
   gfs2_tool	to manipulate, examine and tune a filesystem
   gfs2_quota	to examine and change quota values in a filesystem
+  gfs2_convert	to convert a gfs filesystem to gfs2 in-place
   mount.gfs2	to help mount(8) mount a filesystem
   mkfs.gfs2	to make a filesystem
diff --git a/Documentation/futex-requeue-pi.txt b/Documentation/futex-requeue-pi.txt
new file mode 100644
index 000000000000..9dc1ff4fd536
--- /dev/null
+++ b/Documentation/futex-requeue-pi.txt
@@ -0,0 +1,131 @@
+Futex Requeue PI
+----------------
+
+Requeueing of tasks from a non-PI futex to a PI futex requires
+special handling in order to ensure the underlying rt_mutex is never
+left without an owner if it has waiters; doing so would break the PI
+boosting logic [see rt-mutex-desgin.txt] For the purposes of
+brevity, this action will be referred to as "requeue_pi" throughout
+this document.  Priority inheritance is abbreviated throughout as
+"PI".
+
+Motivation
+----------
+
+Without requeue_pi, the glibc implementation of
+pthread_cond_broadcast() must resort to waking all the tasks waiting
+on a pthread_condvar and letting them try to sort out which task
+gets to run first in classic thundering-herd formation.  An ideal
+implementation would wake the highest-priority waiter, and leave the
+rest to the natural wakeup inherent in unlocking the mutex
+associated with the condvar.
+
+Consider the simplified glibc calls:
+
+/* caller must lock mutex */
+pthread_cond_wait(cond, mutex)
+{
+	lock(cond->__data.__lock);
+	unlock(mutex);
+	do {
+	   unlock(cond->__data.__lock);
+	   futex_wait(cond->__data.__futex);
+	   lock(cond->__data.__lock);
+	} while(...)
+	unlock(cond->__data.__lock);
+	lock(mutex);
+}
+
+pthread_cond_broadcast(cond)
+{
+	lock(cond->__data.__lock);
+	unlock(cond->__data.__lock);
+	futex_requeue(cond->data.__futex, cond->mutex);
+}
+
+Once pthread_cond_broadcast() requeues the tasks, the cond->mutex
+has waiters. Note that pthread_cond_wait() attempts to lock the
+mutex only after it has returned to user space.  This will leave the
+underlying rt_mutex with waiters, and no owner, breaking the
+previously mentioned PI-boosting algorithms.
+
+In order to support PI-aware pthread_condvar's, the kernel needs to
+be able to requeue tasks to PI futexes.  This support implies that
+upon a successful futex_wait system call, the caller would return to
+user space already holding the PI futex.  The glibc implementation
+would be modified as follows:
+
+
+/* caller must lock mutex */
+pthread_cond_wait_pi(cond, mutex)
+{
+	lock(cond->__data.__lock);
+	unlock(mutex);
+	do {
+	   unlock(cond->__data.__lock);
+	   futex_wait_requeue_pi(cond->__data.__futex);
+	   lock(cond->__data.__lock);
+	} while(...)
+	unlock(cond->__data.__lock);
+        /* the kernel acquired the the mutex for us */
+}
+
+pthread_cond_broadcast_pi(cond)
+{
+	lock(cond->__data.__lock);
+	unlock(cond->__data.__lock);
+	futex_requeue_pi(cond->data.__futex, cond->mutex);
+}
+
+The actual glibc implementation will likely test for PI and make the
+necessary changes inside the existing calls rather than creating new
+calls for the PI cases.  Similar changes are needed for
+pthread_cond_timedwait() and pthread_cond_signal().
+
+Implementation
+--------------
+
+In order to ensure the rt_mutex has an owner if it has waiters, it
+is necessary for both the requeue code, as well as the waiting code,
+to be able to acquire the rt_mutex before returning to user space.
+The requeue code cannot simply wake the waiter and leave it to
+acquire the rt_mutex as it would open a race window between the
+requeue call returning to user space and the waiter waking and
+starting to run.  This is especially true in the uncontended case.
+
+The solution involves two new rt_mutex helper routines,
+rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which
+allow the requeue code to acquire an uncontended rt_mutex on behalf
+of the waiter and to enqueue the waiter on a contended rt_mutex.
+Two new system calls provide the kernel<->user interface to
+requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_REQUEUE_CMP_PI.
+
+FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait()
+and pthread_cond_timedwait()) to block on the initial futex and wait
+to be requeued to a PI-aware futex.  The implementation is the
+result of a high-speed collision between futex_wait() and
+futex_lock_pi(), with some extra logic to check for the additional
+wake-up scenarios.
+
+FUTEX_REQUEUE_CMP_PI is called by the waker
+(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and
+possibly wake the waiting tasks. Internally, this system call is
+still handled by futex_requeue (by passing requeue_pi=1).  Before
+requeueing, futex_requeue() attempts to acquire the requeue target
+PI futex on behalf of the top waiter.  If it can, this waiter is
+woken.  futex_requeue() then proceeds to requeue the remaining
+nr_wake+nr_requeue tasks to the PI futex, calling
+rt_mutex_start_proxy_lock() prior to each requeue to prepare the
+task as a waiter on the underlying rt_mutex.  It is possible that
+the lock can be acquired at this stage as well, if so, the next
+waiter is woken to finish the acquisition of the lock.
+
+FUTEX_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but
+their sum is all that really matters.  futex_requeue() will wake or
+requeue up to nr_wake + nr_requeue tasks.  It will wake only as many
+tasks as it can acquire the lock for, which in the majority of cases
+should be 0 as good programming practice dictates that the caller of
+either pthread_cond_broadcast() or pthread_cond_signal() acquire the
+mutex prior to making the call. FUTEX_REQUEUE_PI requires that
+nr_wake=1.  nr_requeue should be INT_MAX for broadcast and 0 for
+signal.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index fd5cac013037..7bcdebffdab3 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -56,7 +56,6 @@ parameter is applicable:
 	ISAPNP	ISA PnP code is enabled.
 	ISDN	Appropriate ISDN support is enabled.
 	JOY	Appropriate joystick support is enabled.
-	KMEMTRACE kmemtrace is enabled.
 	LIBATA  Libata driver is enabled
 	LP	Printer support is enabled.
 	LOOP	Loopback device support is enabled.
@@ -329,11 +328,6 @@ and is between 256 and 4096 characters. It is defined in the file
 				    flushed before they will be reused, which
 				    is a lot of faster
 
-	amd_iommu_size= [HW,X86-64]
-			Define the size of the aperture for the AMD IOMMU
-			driver. Possible values are:
-			'32M', '64M' (default), '128M', '256M', '512M', '1G'
-
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
@@ -646,6 +640,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			DMA-API debugging code disables itself because the
 			architectural default is too low.
 
+	dma_debug_driver=<driver_name>
+			With this option the DMA-API debugging driver
+			filter feature can be enabled at boot time. Just
+			pass the driver to filter for as the parameter.
+			The filter can be disabled or changed to another
+			driver later using sysfs.
+
 	dscc4.setup=	[NET]
 
 	dtc3181e=	[HW,SCSI]
@@ -752,12 +753,25 @@ and is between 256 and 4096 characters. It is defined in the file
 			ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
 
 	ftrace=[tracer]
-			[ftrace] will set and start the specified tracer
+			[FTRACE] will set and start the specified tracer
 			as early as possible in order to facilitate early
 			boot debugging.
 
 	ftrace_dump_on_oops
-			[ftrace] will dump the trace buffers on oops.
+			[FTRACE] will dump the trace buffers on oops.
+
+	ftrace_filter=[function-list]
+			[FTRACE] Limit the functions traced by the function
+			tracer at boot up. function-list is a comma separated
+			list of functions. This list can be changed at run
+			time by the set_ftrace_filter file in the debugfs
+			tracing directory. 
+
+	ftrace_notrace=[function-list]
+			[FTRACE] Do not trace the functions specified in
+			function-list. This list can be changed at run time
+			by the set_ftrace_notrace file in the debugfs
+			tracing directory.
 
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
@@ -914,6 +928,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			Formt: { "sha1" | "md5" }
 			default: "sha1"
 
+	ima_tcb		[IMA]
+			Load a policy which meets the needs of the Trusted
+			Computing Base.  This means IMA will measure all
+			programs exec'd, files mmap'd for exec, and all files
+			opened for read by uid=0.
+
 	in2000=		[HW,SCSI]
 			See header of drivers/scsi/in2000.c.
 
@@ -1054,15 +1074,6 @@ and is between 256 and 4096 characters. It is defined in the file
 			use the HighMem zone if it exists, and the Normal
 			zone if it does not.
 
-	kmemtrace.enable=	[KNL,KMEMTRACE] Format: { yes | no }
-				Controls whether kmemtrace is enabled
-				at boot-time.
-
-	kmemtrace.subbufs=n	[KNL,KMEMTRACE] Overrides the number of
-			subbufs kmemtrace's relay channel has. Set this
-			higher than default (KMEMTRACE_N_SUBBUFS in code) if
-			you experience buffer overruns.
-
 	kgdboc=		[HW] kgdb over consoles.
 			Requires a tty driver that supports console polling.
 			(only serial suported for now)
@@ -1072,6 +1083,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			Configure the RouterBoard 532 series on-chip
 			Ethernet adapter MAC address.
 
+	kmemleak=	[KNL] Boot-time kmemleak enable/disable
+			Valid arguments: on, off
+			Default: on
+
 	kstack=N	[X86] Print N words from the kernel stack
 			in oops dumps.
 
@@ -1575,6 +1590,9 @@ and is between 256 and 4096 characters. It is defined in the file
 	noinitrd	[RAM] Tells the kernel not to load any configured
 			initial RAM disk.
 
+	nointremap	[X86-64, Intel-IOMMU] Do not enable interrupt
+			remapping.
+
 	nointroute	[IA-64]
 
 	nojitter	[IA64] Disables jitter checking for ITC timers.
@@ -1660,6 +1678,14 @@ and is between 256 and 4096 characters. It is defined in the file
 	oprofile.timer=	[HW]
 			Use timer interrupt instead of performance counters
 
+	oprofile.cpu_type=	Force an oprofile cpu type
+			This might be useful if you have an older oprofile
+			userland or if you want common events.
+			Format: { archperfmon }
+			archperfmon: [X86] Force use of architectural
+				perfmon on Intel CPUs instead of the
+				CPU specific event set.
+
 	osst=		[HW,SCSI] SCSI Tape Driver
 			Format: <buffer_size>,<write_threshold>
 			See also Documentation/scsi/st.txt.
diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt
new file mode 100644
index 000000000000..0112da3b9ab8
--- /dev/null
+++ b/Documentation/kmemleak.txt
@@ -0,0 +1,142 @@
+Kernel Memory Leak Detector
+===========================
+
+Introduction
+------------
+
+Kmemleak provides a way of detecting possible kernel memory leaks in a
+way similar to a tracing garbage collector
+(http://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors),
+with the difference that the orphan objects are not freed but only
+reported via /sys/kernel/debug/kmemleak. A similar method is used by the
+Valgrind tool (memcheck --leak-check) to detect the memory leaks in
+user-space applications.
+
+Usage
+-----
+
+CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel
+thread scans the memory every 10 minutes (by default) and prints any new
+unreferenced objects found. To trigger an intermediate scan and display
+all the possible memory leaks:
+
+  # mount -t debugfs nodev /sys/kernel/debug/
+  # cat /sys/kernel/debug/kmemleak
+
+Note that the orphan objects are listed in the order they were allocated
+and one object at the beginning of the list may cause other subsequent
+objects to be reported as orphan.
+
+Memory scanning parameters can be modified at run-time by writing to the
+/sys/kernel/debug/kmemleak file. The following parameters are supported:
+
+  off		- disable kmemleak (irreversible)
+  stack=on	- enable the task stacks scanning
+  stack=off	- disable the tasks stacks scanning
+  scan=on	- start the automatic memory scanning thread
+  scan=off	- stop the automatic memory scanning thread
+  scan=<secs>	- set the automatic memory scanning period in seconds (0
+		  to disable it)
+
+Kmemleak can also be disabled at boot-time by passing "kmemleak=off" on
+the kernel command line.
+
+Basic Algorithm
+---------------
+
+The memory allocations via kmalloc, vmalloc, kmem_cache_alloc and
+friends are traced and the pointers, together with additional
+information like size and stack trace, are stored in a prio search tree.
+The corresponding freeing function calls are tracked and the pointers
+removed from the kmemleak data structures.
+
+An allocated block of memory is considered orphan if no pointer to its
+start address or to any location inside the block can be found by
+scanning the memory (including saved registers). This means that there
+might be no way for the kernel to pass the address of the allocated
+block to a freeing function and therefore the block is considered a
+memory leak.
+
+The scanning algorithm steps:
+
+  1. mark all objects as white (remaining white objects will later be
+     considered orphan)
+  2. scan the memory starting with the data section and stacks, checking
+     the values against the addresses stored in the prio search tree. If
+     a pointer to a white object is found, the object is added to the
+     gray list
+  3. scan the gray objects for matching addresses (some white objects
+     can become gray and added at the end of the gray list) until the
+     gray set is finished
+  4. the remaining white objects are considered orphan and reported via
+     /sys/kernel/debug/kmemleak
+
+Some allocated memory blocks have pointers stored in the kernel's
+internal data structures and they cannot be detected as orphans. To
+avoid this, kmemleak can also store the number of values pointing to an
+address inside the block address range that need to be found so that the
+block is not considered a leak. One example is __vmalloc().
+
+Kmemleak API
+------------
+
+See the include/linux/kmemleak.h header for the functions prototype.
+
+kmemleak_init		 - initialize kmemleak
+kmemleak_alloc		 - notify of a memory block allocation
+kmemleak_free		 - notify of a memory block freeing
+kmemleak_not_leak	 - mark an object as not a leak
+kmemleak_ignore		 - do not scan or report an object as leak
+kmemleak_scan_area	 - add scan areas inside a memory block
+kmemleak_no_scan	 - do not scan a memory block
+kmemleak_erase		 - erase an old value in a pointer variable
+kmemleak_alloc_recursive - as kmemleak_alloc but checks the recursiveness
+kmemleak_free_recursive	 - as kmemleak_free but checks the recursiveness
+
+Dealing with false positives/negatives
+--------------------------------------
+
+The false negatives are real memory leaks (orphan objects) but not
+reported by kmemleak because values found during the memory scanning
+point to such objects. To reduce the number of false negatives, kmemleak
+provides the kmemleak_ignore, kmemleak_scan_area, kmemleak_no_scan and
+kmemleak_erase functions (see above). The task stacks also increase the
+amount of false negatives and their scanning is not enabled by default.
+
+The false positives are objects wrongly reported as being memory leaks
+(orphan). For objects known not to be leaks, kmemleak provides the
+kmemleak_not_leak function. The kmemleak_ignore could also be used if
+the memory block is known not to contain other pointers and it will no
+longer be scanned.
+
+Some of the reported leaks are only transient, especially on SMP
+systems, because of pointers temporarily stored in CPU registers or
+stacks. Kmemleak defines MSECS_MIN_AGE (defaulting to 1000) representing
+the minimum age of an object to be reported as a memory leak.
+
+Limitations and Drawbacks
+-------------------------
+
+The main drawback is the reduced performance of memory allocation and
+freeing. To avoid other penalties, the memory scanning is only performed
+when the /sys/kernel/debug/kmemleak file is read. Anyway, this tool is
+intended for debugging purposes where the performance might not be the
+most important requirement.
+
+To keep the algorithm simple, kmemleak scans for values pointing to any
+address inside a block's address range. This may lead to an increased
+number of false negatives. However, it is likely that a real memory leak
+will eventually become visible.
+
+Another source of false negatives is the data stored in non-pointer
+values. In a future version, kmemleak could only scan the pointer
+members in the allocated structures. This feature would solve many of
+the false negative cases described above.
+
+The tool can report false positives. These are cases where an allocated
+block doesn't need to be freed (some cases in the init_call functions),
+the pointer is calculated by other methods than the usual container_of
+macro or the pointer is stored in a location not scanned by kmemleak.
+
+Page allocations and ioremap are not tracked. Only the ARM and x86
+architectures are currently supported.
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f5b7127f54ac..7f5809eddee6 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -31,6 +31,7 @@ Contents:
 
      - Locking functions.
      - Interrupt disabling functions.
+     - Sleep and wake-up functions.
      - Miscellaneous functions.
 
  (*) Inter-CPU locking barrier effects.
@@ -1217,6 +1218,132 @@ barriers are required in such a situation, they must be provided from some
 other means.
 
 
+SLEEP AND WAKE-UP FUNCTIONS
+---------------------------
+
+Sleeping and waking on an event flagged in global data can be viewed as an
+interaction between two pieces of data: the task state of the task waiting for
+the event and the global data used to indicate the event.  To make sure that
+these appear to happen in the right order, the primitives to begin the process
+of going to sleep, and the primitives to initiate a wake up imply certain
+barriers.
+
+Firstly, the sleeper normally follows something like this sequence of events:
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (event_indicated)
+			break;
+		schedule();
+	}
+
+A general memory barrier is interpolated automatically by set_current_state()
+after it has altered the task state:
+
+	CPU 1
+	===============================
+	set_current_state();
+	  set_mb();
+	    STORE current->state
+	    <general barrier>
+	LOAD event_indicated
+
+set_current_state() may be wrapped by:
+
+	prepare_to_wait();
+	prepare_to_wait_exclusive();
+
+which therefore also imply a general memory barrier after setting the state.
+The whole sequence above is available in various canned forms, all of which
+interpolate the memory barrier in the right place:
+
+	wait_event();
+	wait_event_interruptible();
+	wait_event_interruptible_exclusive();
+	wait_event_interruptible_timeout();
+	wait_event_killable();
+	wait_event_timeout();
+	wait_on_bit();
+	wait_on_bit_lock();
+
+
+Secondly, code that performs a wake up normally follows something like this:
+
+	event_indicated = 1;
+	wake_up(&event_wait_queue);
+
+or:
+
+	event_indicated = 1;
+	wake_up_process(event_daemon);
+
+A write memory barrier is implied by wake_up() and co. if and only if they wake
+something up.  The barrier occurs before the task state is cleared, and so sits
+between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+
+	CPU 1				CPU 2
+	===============================	===============================
+	set_current_state();		STORE event_indicated
+	  set_mb();			wake_up();
+	    STORE current->state	  <write barrier>
+	    <general barrier>		  STORE current->state
+	LOAD event_indicated
+
+The available waker functions include:
+
+	complete();
+	wake_up();
+	wake_up_all();
+	wake_up_bit();
+	wake_up_interruptible();
+	wake_up_interruptible_all();
+	wake_up_interruptible_nr();
+	wake_up_interruptible_poll();
+	wake_up_interruptible_sync();
+	wake_up_interruptible_sync_poll();
+	wake_up_locked();
+	wake_up_locked_poll();
+	wake_up_nr();
+	wake_up_poll();
+	wake_up_process();
+
+
+[!] Note that the memory barriers implied by the sleeper and the waker do _not_
+order multiple stores before the wake-up with respect to loads of those stored
+values after the sleeper has called set_current_state().  For instance, if the
+sleeper does:
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (event_indicated)
+		break;
+	__set_current_state(TASK_RUNNING);
+	do_something(my_data);
+
+and the waker does:
+
+	my_data = value;
+	event_indicated = 1;
+	wake_up(&event_wait_queue);
+
+there's no guarantee that the change to event_indicated will be perceived by
+the sleeper as coming after the change to my_data.  In such a circumstance, the
+code on both sides must interpolate its own memory barriers between the
+separate data accesses.  Thus the above sleeper ought to do:
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (event_indicated) {
+		smp_rmb();
+		do_something(my_data);
+	}
+
+and the waker should do:
+
+	my_data = value;
+	smp_wmb();
+	event_indicated = 1;
+	wake_up(&event_wait_queue);
+
+
 MISCELLANEOUS FUNCTIONS
 -----------------------
 
@@ -1366,7 +1493,7 @@ WHERE ARE MEMORY BARRIERS NEEDED?
 
 Under normal operation, memory operation reordering is generally not going to
 be a problem as a single-threaded linear piece of code will still appear to
-work correctly, even if it's in an SMP kernel.  There are, however, three
+work correctly, even if it's in an SMP kernel.  There are, however, four
 circumstances in which reordering definitely _could_ be a problem:
 
  (*) Interprocessor interaction.
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 5ba4d3fc625a..1df7f9cdab05 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -4,6 +4,7 @@
 CONTENTS
 ========
 
+0. WARNING
 1. Overview
   1.1 The problem
   1.2 The solution
@@ -14,6 +15,23 @@ CONTENTS
 3. Future plans
 
 
+0. WARNING
+==========
+
+ Fiddling with these settings can result in an unstable system, the knobs are
+ root only and assumes root knows what he is doing.
+
+Most notable:
+
+ * very small values in sched_rt_period_us can result in an unstable
+   system when the period is smaller than either the available hrtimer
+   resolution, or the time it takes to handle the budget refresh itself.
+
+ * very small values in sched_rt_runtime_us can result in an unstable
+   system when the runtime is so small the system has difficulty making
+   forward progress (NOTE: the migration thread and kstopmachine both
+   are real-time processes).
+
 1. Overview
 ===========
 
@@ -169,7 +187,7 @@ get their allocated time.
 
 Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
 the biggest challenge as the current linux PI infrastructure is geared towards
-the limited static priority levels 0-139. With deadline scheduling you need to
+the limited static priority levels 0-99. With deadline scheduling you need to
 do deadline inheritance (since priority is inversely proportional to the
 deadline delta (deadline - now).
 
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index f11ca7979fa6..322a00bb99d9 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -32,6 +32,7 @@ show up in /proc/sys/kernel:
 - kstack_depth_to_print       [ X86 only ]
 - l2cr                        [ PPC only ]
 - modprobe                    ==> Documentation/debugging-modules.txt
+- modules_disabled
 - msgmax
 - msgmnb
 - msgmni
@@ -184,6 +185,16 @@ kernel stack.
 
 ==============================================================
 
+modules_disabled:
+
+A toggle value indicating if modules are allowed to be loaded
+in an otherwise modular kernel.  This toggle defaults to off
+(0), but can be set true (1).  Once true, modules can be
+neither loaded nor unloaded, and the toggle cannot be set back
+to false.
+
+==============================================================
+
 osrelease, ostype & version:
 
 # cat osrelease
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
new file mode 100644
index 000000000000..f157d7594ea7
--- /dev/null
+++ b/Documentation/trace/events.txt
@@ -0,0 +1,90 @@
+			     Event Tracing
+
+		Documentation written by Theodore Ts'o
+			Updated by Li Zefan
+
+1. Introduction
+===============
+
+Tracepoints (see Documentation/trace/tracepoints.txt) can be used
+without creating custom kernel modules to register probe functions
+using the event tracing infrastructure.
+
+Not all tracepoints can be traced using the event tracing system;
+the kernel developer must provide code snippets which define how the
+tracing information is saved into the tracing buffer, and how the
+tracing information should be printed.
+
+2. Using Event Tracing
+======================
+
+2.1 Via the 'set_event' interface
+---------------------------------
+
+The events which are available for tracing can be found in the file
+/debug/tracing/available_events.
+
+To enable a particular event, such as 'sched_wakeup', simply echo it
+to /debug/tracing/set_event. For example:
+
+	# echo sched_wakeup >> /debug/tracing/set_event
+
+[ Note: '>>' is necessary, otherwise it will firstly disable
+  all the events. ]
+
+To disable an event, echo the event name to the set_event file prefixed
+with an exclamation point:
+
+	# echo '!sched_wakeup' >> /debug/tracing/set_event
+
+To disable all events, echo an empty line to the set_event file:
+
+	# echo > /debug/tracing/set_event
+
+To enable all events, echo '*:*' or '*:' to the set_event file:
+
+	# echo *:* > /debug/tracing/set_event
+
+The events are organized into subsystems, such as ext4, irq, sched,
+etc., and a full event name looks like this: <subsystem>:<event>.  The
+subsystem name is optional, but it is displayed in the available_events
+file.  All of the events in a subsystem can be specified via the syntax
+"<subsystem>:*"; for example, to enable all irq events, you can use the
+command:
+
+	# echo 'irq:*' > /debug/tracing/set_event
+
+2.2 Via the 'enable' toggle
+---------------------------
+
+The events available are also listed in /debug/tracing/events/ hierarchy
+of directories.
+
+To enable event 'sched_wakeup':
+
+	# echo 1 > /debug/tracing/events/sched/sched_wakeup/enable
+
+To disable it:
+
+	# echo 0 > /debug/tracing/events/sched/sched_wakeup/enable
+
+To enable all events in sched subsystem:
+
+	# echo 1 > /debug/tracing/events/sched/enable
+
+To eanble all events:
+
+	# echo 1 > /debug/tracing/events/enable
+
+When reading one of these enable files, there are four results:
+
+ 0 - all events this file affects are disabled
+ 1 - all events this file affects are enabled
+ X - there is a mixture of events enabled and disabled
+ ? - this file does not affect any event
+
+3. Defining an event-enabled tracepoint
+=======================================
+
+See The example provided in samples/trace_events
+
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index fd9a3e693813..2a82d8602944 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -179,7 +179,7 @@ Here is the list of current tracers that may be configured.
 
 	Function call tracer to trace all kernel functions.
 
-  "function_graph_tracer"
+  "function_graph"
 
 	Similar to the function tracer except that the
 	function tracer probes the functions on their entry
@@ -518,9 +518,18 @@ priority with zero (0) being the highest priority and the nice
 values starting at 100 (nice -20). Below is a quick chart to map
 the kernel priority to user land priorities.
 
-  Kernel priority: 0 to 99    ==> user RT priority 99 to 0
-  Kernel priority: 100 to 139 ==> user nice -20 to 19
-  Kernel priority: 140        ==> idle task priority
+   Kernel Space                     User Space
+ ===============================================================
+   0(high) to  98(low)     user RT priority 99(high) to 1(low)
+                           with SCHED_RR or SCHED_FIFO
+ ---------------------------------------------------------------
+  99                       sched_priority is not used in scheduling
+                           decisions(it must be specified as 0)
+ ---------------------------------------------------------------
+ 100(high) to 139(low)     user nice -20(high) to 19(low)
+ ---------------------------------------------------------------
+ 140                       idle task priority
+ ---------------------------------------------------------------
 
 The task states are:
 
diff --git a/Documentation/trace/power.txt b/Documentation/trace/power.txt
new file mode 100644
index 000000000000..cd805e16dc27
--- /dev/null
+++ b/Documentation/trace/power.txt
@@ -0,0 +1,17 @@
+The power tracer collects detailed information about C-state and P-state
+transitions, instead of just looking at the high-level "average"
+information.
+
+There is a helper script found in scrips/tracing/power.pl in the kernel
+sources which can be used to parse this information and create a
+Scalable Vector Graphics (SVG) picture from the trace data.
+
+To use this tracer:
+
+	echo 0 > /sys/kernel/debug/tracing/tracing_enabled
+	echo power > /sys/kernel/debug/tracing/current_tracer
+	echo 1 > /sys/kernel/debug/tracing/tracing_enabled
+	sleep 1
+	echo 0 > /sys/kernel/debug/tracing/tracing_enabled
+	cat /sys/kernel/debug/tracing/trace | \
+		perl scripts/tracing/power.pl > out.sv
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index e0203662f9e9..8da3a795083f 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -50,6 +50,10 @@ Protocol 2.08:	(Kernel 2.6.26) Added crc32 checksum and ELF format
 Protocol 2.09:	(Kernel 2.6.26) Added a field of 64-bit physical
 		pointer to single linked list of struct	setup_data.
 
+Protocol 2.10:	(Kernel 2.6.31) Added a protocol for relaxed alignment
+		beyond the kernel_alignment added, new init_size and
+		pref_address fields.  Added extended boot loader IDs.
+
 **** MEMORY LAYOUT
 
 The traditional memory map for the kernel loader, used for Image or
@@ -168,12 +172,13 @@ Offset	Proto	Name		Meaning
 021C/4	2.00+	ramdisk_size	initrd size (set by boot loader)
 0220/4	2.00+	bootsect_kludge	DO NOT USE - for bootsect.S use only
 0224/2	2.01+	heap_end_ptr	Free memory after setup end
-0226/2	N/A	pad1		Unused
+0226/1	2.02+(3 ext_loader_ver	Extended boot loader version
+0227/1	2.02+(3	ext_loader_type	Extended boot loader ID
 0228/4	2.02+	cmd_line_ptr	32-bit pointer to the kernel command line
 022C/4	2.03+	ramdisk_max	Highest legal initrd address
 0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
 0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
-0235/1	N/A	pad2		Unused
+0235/1	2.10+	min_alignment	Minimum alignment, as a power of two
 0236/2	N/A	pad3		Unused
 0238/4	2.06+	cmdline_size	Maximum size of the kernel command line
 023C/4	2.07+	hardware_subarch Hardware subarchitecture
@@ -182,6 +187,8 @@ Offset	Proto	Name		Meaning
 024C/4	2.08+	payload_length	Length of kernel payload
 0250/8	2.09+	setup_data	64-bit physical pointer to linked list
 				of struct setup_data
+0258/8	2.10+	pref_address	Preferred loading address
+0260/4	2.10+	init_size	Linear memory required during initialization
 
 (1) For backwards compatibility, if the setup_sects field contains 0, the
     real value is 4.
@@ -190,6 +197,8 @@ Offset	Proto	Name		Meaning
     field are unusable, which means the size of a bzImage kernel
     cannot be determined.
 
+(3) Ignored, but safe to set, for boot protocols 2.02-2.09.
+
 If the "HdrS" (0x53726448) magic number is not found at offset 0x202,
 the boot protocol version is "old".  Loading an old kernel, the
 following parameters should be assumed:
@@ -343,18 +352,32 @@ Protocol:	2.00+
   0xTV here, where T is an identifier for the boot loader and V is
   a version number.  Otherwise, enter 0xFF here.
 
+  For boot loader IDs above T = 0xD, write T = 0xE to this field and
+  write the extended ID minus 0x10 to the ext_loader_type field.
+  Similarly, the ext_loader_ver field can be used to provide more than
+  four bits for the bootloader version.
+
+  For example, for T = 0x15, V = 0x234, write:
+
+  type_of_loader  <- 0xE4
+  ext_loader_type <- 0x05
+  ext_loader_ver  <- 0x23
+
   Assigned boot loader ids:
 	0  LILO			(0x00 reserved for pre-2.00 bootloader)
 	1  Loadlin
 	2  bootsect-loader	(0x20, all other values reserved)
-	3  SYSLINUX
-	4  EtherBoot
+	3  Syslinux
+	4  Etherboot/gPXE
 	5  ELILO
 	7  GRUB
-	8  U-BOOT
+	8  U-Boot
 	9  Xen
 	A  Gujin
 	B  Qemu
+	C  Arcturus Networks uCbootloader
+	E  Extended		(see ext_loader_type)
+	F  Special		(0xFF = undefined)
 
   Please contact <hpa@zytor.com> if you need a bootloader ID
   value assigned.
@@ -453,6 +476,35 @@ Protocol:	2.01+
   Set this field to the offset (from the beginning of the real-mode
   code) of the end of the setup stack/heap, minus 0x0200.
 
+Field name:	ext_loader_ver
+Type:		write (optional)
+Offset/size:	0x226/1
+Protocol:	2.02+
+
+  This field is used as an extension of the version number in the
+  type_of_loader field.  The total version number is considered to be
+  (type_of_loader & 0x0f) + (ext_loader_ver << 4).
+
+  The use of this field is boot loader specific.  If not written, it
+  is zero.
+
+  Kernels prior to 2.6.31 did not recognize this field, but it is safe
+  to write for protocol version 2.02 or higher.
+
+Field name:	ext_loader_type
+Type:		write (obligatory if (type_of_loader & 0xf0) == 0xe0)
+Offset/size:	0x227/1
+Protocol:	2.02+
+
+  This field is used as an extension of the type number in
+  type_of_loader field.  If the type in type_of_loader is 0xE, then
+  the actual type is (ext_loader_type + 0x10).
+
+  This field is ignored if the type in type_of_loader is not 0xE.
+
+  Kernels prior to 2.6.31 did not recognize this field, but it is safe
+  to write for protocol version 2.02 or higher.
+
 Field name:	cmd_line_ptr
 Type:		write (obligatory)
 Offset/size:	0x228/4
@@ -482,11 +534,19 @@ Protocol:	2.03+
   0x37FFFFFF, you can start your ramdisk at 0x37FE0000.)
 
 Field name:	kernel_alignment
-Type:		read (reloc)
+Type:		read/modify (reloc)
 Offset/size:	0x230/4
-Protocol:	2.05+
+Protocol:	2.05+ (read), 2.10+ (modify)
 
-  Alignment unit required by the kernel (if relocatable_kernel is true.)
+  Alignment unit required by the kernel (if relocatable_kernel is
+  true.)  A relocatable kernel that is loaded at an alignment
+  incompatible with the value in this field will be realigned during
+  kernel initialization.
+
+  Starting with protocol version 2.10, this reflects the kernel
+  alignment preferred for optimal performance; it is possible for the
+  loader to modify this field to permit a lesser alignment.  See the
+  min_alignment and pref_address field below.
 
 Field name:	relocatable_kernel
 Type:		read (reloc)
@@ -498,6 +558,22 @@ Protocol:	2.05+
   After loading, the boot loader must set the code32_start field to
   point to the loaded code, or to a boot loader hook.
 
+Field name:	min_alignment
+Type:		read (reloc)
+Offset/size:	0x235/1
+Protocol:	2.10+
+
+  This field, if nonzero, indicates as a power of two the minimum
+  alignment required, as opposed to preferred, by the kernel to boot.
+  If a boot loader makes use of this field, it should update the
+  kernel_alignment field with the alignment unit desired; typically:
+
+	kernel_alignment = 1 << min_alignment
+
+  There may be a considerable performance cost with an excessively
+  misaligned kernel.  Therefore, a loader should typically try each
+  power-of-two alignment from kernel_alignment down to this alignment.
+
 Field name:	cmdline_size
 Type:		read
 Offset/size:	0x238/4
@@ -582,6 +658,36 @@ Protocol:	2.09+
   sure to consider the case where the linked list already contains
   entries.
 
+Field name:	pref_address
+Type:		read (reloc)
+Offset/size:	0x258/8
+Protocol:	2.10+
+
+  This field, if nonzero, represents a preferred load address for the
+  kernel.  A relocating bootloader should attempt to load at this
+  address if possible.
+
+  A non-relocatable kernel will unconditionally move itself and to run
+  at this address.
+
+Field name:	init_size
+Type:		read
+Offset/size:	0x25c/4
+
+  This field indicates the amount of linear contiguous memory starting
+  at the kernel runtime start address that the kernel needs before it
+  is capable of examining its memory map.  This is not the same thing
+  as the total amount of memory the kernel needs to boot, but it can
+  be used by a relocating boot loader to help select a safe load
+  address for the kernel.
+
+  The kernel runtime start address is determined by the following algorithm:
+
+  if (relocatable_kernel)
+	runtime_start = align_up(load_address, kernel_alignment)
+  else
+	runtime_start = pref_address
+
 
 **** THE IMAGE CHECKSUM
 
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 34c13040a718..2db5893d6c97 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -150,11 +150,6 @@ NUMA
 		Otherwise, the remaining system RAM is allocated to an
 		additional node.
 
-  numa=hotadd=percent
-		Only allow hotadd memory to preallocate page structures upto
-		percent of already available memory.
-		numa=hotadd=0 will disable hotadd memory.
-
 ACPI
 
   acpi=off	Don't enable ACPI
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 29b52b14d0b4..d6498e3cd713 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -6,10 +6,11 @@ Virtual memory map with 4 level page tables:
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
 ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
-ffff880000000000 - ffffc0ffffffffff (=57 TB) direct mapping of all phys. memory
-ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
-ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
-ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)
+ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
+ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
+ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
+ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
+ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space
diff --git a/MAINTAINERS b/MAINTAINERS
index cf4abddfc8a4..c944d618dc83 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -71,7 +71,7 @@ P: Person
 M: Mail patches to
 L: Mailing list that is relevant to this area
 W: Web-page with status/info
-T: SCM tree type and location.  Type is one of: git, hg, quilt.
+T: SCM tree type and location.  Type is one of: git, hg, quilt, stgit.
 S: Status, one of the following:
 
 	Supported:	Someone is actually paid to look after this.
@@ -159,7 +159,8 @@ F:	drivers/net/r8169.c
 8250/16?50 (AND CLONE UARTS) SERIAL DRIVER
 L:	linux-serial@vger.kernel.org
 W:	http://serial.sourceforge.net
-S:	Orphan
+M:	alan@lxorguk.ukuu.org.uk
+S:	Odd Fixes
 F:	drivers/serial/8250*
 F:	include/linux/serial_8250.h
 
@@ -1801,10 +1802,10 @@ F:	drivers/char/epca*
 F:	drivers/char/digi*
 
 DIRECTORY NOTIFICATION (DNOTIFY)
-P:	Stephen Rothwell
-M:	sfr@canb.auug.org.au
+P:	Eric Paris
+M:	eparis@parisplace.org
 L:	linux-kernel@vger.kernel.org
-S:	Supported
+S:	Maintained
 F:	Documentation/filesystems/dnotify.txt
 F:	fs/notify/dnotify/
 F:	include/linux/dnotify.h
@@ -1978,6 +1979,16 @@ F:	Documentation/edac.txt
 F:	drivers/edac/edac_*
 F:	include/linux/edac.h
 
+EDAC-AMD64
+P:	Doug Thompson
+M:	dougthompson@xmission.com
+P:	Borislav Petkov
+M:	borislav.petkov@amd.com
+L:	bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers)
+W:	bluesmoke.sourceforge.net
+S:	Supported
+F:	drivers/edac/amd64_edac*
+
 EDAC-E752X
 P:	Mark Gross
 M:	mark.gross@intel.com
@@ -2847,6 +2858,8 @@ P:	John McCutchan
 M:	john@johnmccutchan.com
 P:	Robert Love
 M:	rlove@rlove.org
+P:	Eric Paris
+M:	eparis@parisplace.org
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	Documentation/filesystems/inotify.txt
@@ -3359,6 +3372,12 @@ F:	Documentation/trace/kmemtrace.txt
 F:	include/trace/kmemtrace.h
 F:	kernel/trace/kmemtrace.c
 
+KMEMLEAK
+P:	Catalin Marinas
+M:	catalin.marinas@arm.com
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+
 KPROBES
 P:	Ananth N Mavinakayanahalli
 M:	ananth@in.ibm.com
@@ -4392,6 +4411,16 @@ S:	Maintained
 F:	include/linux/delayacct.h
 F:	kernel/delayacct.c
 
+PERFORMANCE COUNTER SUBSYSTEM
+P:	Peter Zijlstra
+M:	a.p.zijlstra@chello.nl
+P:	Paul Mackerras
+M:	paulus@samba.org
+P:	Ingo Molnar
+M:	mingo@elte.hu
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+
 PERSONALITY HANDLING
 P:	Christoph Hellwig
 M:	hch@infradead.org
@@ -5629,6 +5658,7 @@ P:	Alan Cox
 M:	alan@lxorguk.ukuu.org.uk
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
+T:	stgit http://zeniv.linux.org.uk/~alan/ttydev/
 
 TULIP NETWORK DRIVERS
 P:	Grant Grundler
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 42ee05981e71..9a3334ae282e 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -371,8 +371,6 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path,
 	int retval = -EINVAL;
 	char *name;
 
-	lock_kernel();
-
 	name = getname(path);
 	retval = PTR_ERR(name);
 	if (IS_ERR(name))
@@ -392,7 +390,6 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path,
 	}
 	putname(name);
  out:
-	unlock_kernel();
 	return retval;
 }
 
diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index 9c9d1fd4155f..5bd5259324b7 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -176,22 +176,26 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
 	}
 }
 
-static void
+static int
 dp264_set_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
 	spin_lock(&dp264_irq_lock);
 	cpu_set_irq_affinity(irq, *affinity);
 	tsunami_update_irq_hw(cached_irq_mask);
 	spin_unlock(&dp264_irq_lock);
+
+	return 0;
 }
 
-static void
+static int
 clipper_set_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
 	spin_lock(&dp264_irq_lock);
 	cpu_set_irq_affinity(irq - 16, *affinity);
 	tsunami_update_irq_hw(cached_irq_mask);
 	spin_unlock(&dp264_irq_lock);
+
+	return 0;
 }
 
 static struct hw_interrupt_type dp264_irq_type = {
diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c
index 27f840a4ad3d..8dd239ebdb9e 100644
--- a/arch/alpha/kernel/sys_titan.c
+++ b/arch/alpha/kernel/sys_titan.c
@@ -157,13 +157,15 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
 
 }
 
-static void
+static int
 titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
 	spin_lock(&titan_irq_lock);
 	titan_cpu_set_irq_affinity(irq - 16, *affinity);
 	titan_update_irq_hw(titan_cached_irq_mask);
 	spin_unlock(&titan_irq_lock);
+
+	return 0;
 }
 
 static void
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 3e1714c6523f..664c7b8b1ba8 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -109,7 +109,7 @@ static void gic_unmask_irq(unsigned int irq)
 }
 
 #ifdef CONFIG_SMP
-static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
+static int gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
 {
 	void __iomem *reg = gic_dist_base(irq) + GIC_DIST_TARGET + (gic_irq(irq) & ~3);
 	unsigned int shift = (irq % 4) * 8;
@@ -122,6 +122,8 @@ static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
 	val |= 1 << (cpu + shift);
 	writel(val, reg);
 	spin_unlock(&irq_controller_lock);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/arm/plat-mxc/include/mach/imx-uart.h b/arch/arm/plat-mxc/include/mach/imx-uart.h
index 599217b2e13f..f9bd17dd8dd7 100644
--- a/arch/arm/plat-mxc/include/mach/imx-uart.h
+++ b/arch/arm/plat-mxc/include/mach/imx-uart.h
@@ -20,11 +20,16 @@
 #define ASMARM_ARCH_UART_H
 
 #define IMXUART_HAVE_RTSCTS (1<<0)
+#define IMXUART_IRDA        (1<<1)
 
 struct imxuart_platform_data {
 	int (*init)(struct platform_device *pdev);
 	int (*exit)(struct platform_device *pdev);
 	unsigned int flags;
+	void (*irda_enable)(int enable);
+	unsigned int irda_inv_rx:1;
+	unsigned int irda_inv_tx:1;
+	unsigned short transceiver_delay;
 };
 
 #endif
diff --git a/arch/arm/plat-omap/mailbox.c b/arch/arm/plat-omap/mailbox.c
index 0abfbaa59871..40424edae939 100644
--- a/arch/arm/plat-omap/mailbox.c
+++ b/arch/arm/plat-omap/mailbox.c
@@ -147,24 +147,40 @@ static int __mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void *arg)
 	return ret;
 }
 
+struct omap_msg_tx_data {
+	mbox_msg_t	msg;
+	void		*arg;
+};
+
+static void omap_msg_tx_end_io(struct request *rq, int error)
+{
+	kfree(rq->special);
+	__blk_put_request(rq->q, rq);
+}
+
 int omap_mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void* arg)
 {
+	struct omap_msg_tx_data *tx_data;
 	struct request *rq;
 	struct request_queue *q = mbox->txq->queue;
-	int ret = 0;
+
+	tx_data = kmalloc(sizeof(*tx_data), GFP_ATOMIC);
+	if (unlikely(!tx_data))
+		return -ENOMEM;
 
 	rq = blk_get_request(q, WRITE, GFP_ATOMIC);
 	if (unlikely(!rq)) {
-		ret = -ENOMEM;
-		goto fail;
+		kfree(tx_data);
+		return -ENOMEM;
 	}
 
-	rq->data = (void *)msg;
-	blk_insert_request(q, rq, 0, arg);
+	tx_data->msg = msg;
+	tx_data->arg = arg;
+	rq->end_io = omap_msg_tx_end_io;
+	blk_insert_request(q, rq, 0, tx_data);
 
 	schedule_work(&mbox->txq->work);
- fail:
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(omap_mbox_msg_send);
 
@@ -178,22 +194,28 @@ static void mbox_tx_work(struct work_struct *work)
 	struct request_queue *q = mbox->txq->queue;
 
 	while (1) {
+		struct omap_msg_tx_data *tx_data;
+
 		spin_lock(q->queue_lock);
-		rq = elv_next_request(q);
+		rq = blk_fetch_request(q);
 		spin_unlock(q->queue_lock);
 
 		if (!rq)
 			break;
 
-		ret = __mbox_msg_send(mbox, (mbox_msg_t) rq->data, rq->special);
+		tx_data = rq->special;
+
+		ret = __mbox_msg_send(mbox, tx_data->msg, tx_data->arg);
 		if (ret) {
 			enable_mbox_irq(mbox, IRQ_TX);
+			spin_lock(q->queue_lock);
+			blk_requeue_request(q, rq);
+			spin_unlock(q->queue_lock);
 			return;
 		}
 
 		spin_lock(q->queue_lock);
-		if (__blk_end_request(rq, 0, 0))
-			BUG();
+		__blk_end_request_all(rq, 0);
 		spin_unlock(q->queue_lock);
 	}
 }
@@ -218,16 +240,13 @@ static void mbox_rx_work(struct work_struct *work)
 
 	while (1) {
 		spin_lock_irqsave(q->queue_lock, flags);
-		rq = elv_next_request(q);
+		rq = blk_fetch_request(q);
 		spin_unlock_irqrestore(q->queue_lock, flags);
 		if (!rq)
 			break;
 
-		msg = (mbox_msg_t) rq->data;
-
-		if (blk_end_request(rq, 0, 0))
-			BUG();
-
+		msg = (mbox_msg_t)rq->special;
+		blk_end_request_all(rq, 0);
 		mbox->rxq->callback((void *)msg);
 	}
 }
@@ -264,7 +283,6 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox)
 			goto nomem;
 
 		msg = mbox_fifo_read(mbox);
-		rq->data = (void *)msg;
 
 		if (unlikely(mbox_seq_test(mbox, msg))) {
 			pr_info("mbox: Illegal seq bit!(%08x)\n", msg);
@@ -272,7 +290,7 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox)
 				mbox->err_notify();
 		}
 
-		blk_insert_request(q, rq, 0, NULL);
+		blk_insert_request(q, rq, 0, (void *)msg);
 		if (mbox->ops->type == OMAP_MBOX_TYPE1)
 			break;
 	}
@@ -329,16 +347,15 @@ omap_mbox_read(struct device *dev, struct device_attribute *attr, char *buf)
 
 	while (1) {
 		spin_lock_irqsave(q->queue_lock, flags);
-		rq = elv_next_request(q);
+		rq = blk_fetch_request(q);
 		spin_unlock_irqrestore(q->queue_lock, flags);
 
 		if (!rq)
 			break;
 
-		*p = (mbox_msg_t) rq->data;
+		*p = (mbox_msg_t)rq->special;
 
-		if (blk_end_request(rq, 0, 0))
-			BUG();
+		blk_end_request_all(rq, 0);
 
 		if (unlikely(mbox_seq_test(mbox, *p))) {
 			pr_info("mbox: Illegal seq bit!(%08x) ignored\n", *p);
diff --git a/arch/cris/arch-v32/kernel/irq.c b/arch/cris/arch-v32/kernel/irq.c
index df3925cb1c7f..d70b445f4a8f 100644
--- a/arch/cris/arch-v32/kernel/irq.c
+++ b/arch/cris/arch-v32/kernel/irq.c
@@ -325,12 +325,14 @@ static void end_crisv32_irq(unsigned int irq)
 {
 }
 
-void set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest)
+int set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest)
 {
 	unsigned long flags;
 	spin_lock_irqsave(&irq_lock, flags);
 	irq_allocations[irq - FIRST_IRQ].mask = *dest;
 	spin_unlock_irqrestore(&irq_lock, flags);
+
+	return 0;
 }
 
 static struct irq_chip crisv32_irq_type = {
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index 9d1552a9ee2c..8a5bd7a9c6f5 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -6,6 +6,7 @@ config FRV
 	bool
 	default y
 	select HAVE_IDE
+	select HAVE_ARCH_TRACEHOOK
 
 config ZONE_DMA
 	bool
diff --git a/arch/frv/include/asm/bitops.h b/arch/frv/include/asm/bitops.h
index 287f6f697ce2..50ae91b29674 100644
--- a/arch/frv/include/asm/bitops.h
+++ b/arch/frv/include/asm/bitops.h
@@ -112,7 +112,7 @@ extern unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsig
 #define atomic_clear_mask(mask, v)	atomic_test_and_ANDNOT_mask((mask), (v))
 #define atomic_set_mask(mask, v)	atomic_test_and_OR_mask((mask), (v))
 
-static inline int test_and_clear_bit(int nr, volatile void *addr)
+static inline int test_and_clear_bit(unsigned long nr, volatile void *addr)
 {
 	volatile unsigned long *ptr = addr;
 	unsigned long mask = 1UL << (nr & 31);
@@ -120,7 +120,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
 	return (atomic_test_and_ANDNOT_mask(mask, ptr) & mask) != 0;
 }
 
-static inline int test_and_set_bit(int nr, volatile void *addr)
+static inline int test_and_set_bit(unsigned long nr, volatile void *addr)
 {
 	volatile unsigned long *ptr = addr;
 	unsigned long mask = 1UL << (nr & 31);
@@ -128,7 +128,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
 	return (atomic_test_and_OR_mask(mask, ptr) & mask) != 0;
 }
 
-static inline int test_and_change_bit(int nr, volatile void *addr)
+static inline int test_and_change_bit(unsigned long nr, volatile void *addr)
 {
 	volatile unsigned long *ptr = addr;
 	unsigned long mask = 1UL << (nr & 31);
@@ -136,22 +136,22 @@ static inline int test_and_change_bit(int nr, volatile void *addr)
 	return (atomic_test_and_XOR_mask(mask, ptr) & mask) != 0;
 }
 
-static inline void clear_bit(int nr, volatile void *addr)
+static inline void clear_bit(unsigned long nr, volatile void *addr)
 {
 	test_and_clear_bit(nr, addr);
 }
 
-static inline void set_bit(int nr, volatile void *addr)
+static inline void set_bit(unsigned long nr, volatile void *addr)
 {
 	test_and_set_bit(nr, addr);
 }
 
-static inline void change_bit(int nr, volatile void * addr)
+static inline void change_bit(unsigned long nr, volatile void *addr)
 {
 	test_and_change_bit(nr, addr);
 }
 
-static inline void __clear_bit(int nr, volatile void * addr)
+static inline void __clear_bit(unsigned long nr, volatile void *addr)
 {
 	volatile unsigned long *a = addr;
 	int mask;
@@ -161,7 +161,7 @@ static inline void __clear_bit(int nr, volatile void * addr)
 	*a &= ~mask;
 }
 
-static inline void __set_bit(int nr, volatile void * addr)
+static inline void __set_bit(unsigned long nr, volatile void *addr)
 {
 	volatile unsigned long *a = addr;
 	int mask;
@@ -171,7 +171,7 @@ static inline void __set_bit(int nr, volatile void * addr)
 	*a |= mask;
 }
 
-static inline void __change_bit(int nr, volatile void *addr)
+static inline void __change_bit(unsigned long nr, volatile void *addr)
 {
 	volatile unsigned long *a = addr;
 	int mask;
@@ -181,7 +181,7 @@ static inline void __change_bit(int nr, volatile void *addr)
 	*a ^= mask;
 }
 
-static inline int __test_and_clear_bit(int nr, volatile void * addr)
+static inline int __test_and_clear_bit(unsigned long nr, volatile void *addr)
 {
 	volatile unsigned long *a = addr;
 	int mask, retval;
@@ -193,7 +193,7 @@ static inline int __test_and_clear_bit(int nr, volatile void * addr)
 	return retval;
 }
 
-static inline int __test_and_set_bit(int nr, volatile void * addr)
+static inline int __test_and_set_bit(unsigned long nr, volatile void *addr)
 {
 	volatile unsigned long *a = addr;
 	int mask, retval;
@@ -205,7 +205,7 @@ static inline int __test_and_set_bit(int nr, volatile void * addr)
 	return retval;
 }
 
-static inline int __test_and_change_bit(int nr, volatile void * addr)
+static inline int __test_and_change_bit(unsigned long nr, volatile void *addr)
 {
 	volatile unsigned long *a = addr;
 	int mask, retval;
@@ -220,12 +220,13 @@ static inline int __test_and_change_bit(int nr, volatile void * addr)
 /*
  * This routine doesn't need to be atomic.
  */
-static inline int __constant_test_bit(int nr, const volatile void * addr)
+static inline int
+__constant_test_bit(unsigned long nr, const volatile void *addr)
 {
 	return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
 }
 
-static inline int __test_bit(int nr, const volatile void * addr)
+static inline int __test_bit(unsigned long nr, const volatile void *addr)
 {
 	int 	* a = (int *) addr;
 	int	mask;
diff --git a/arch/frv/include/asm/elf.h b/arch/frv/include/asm/elf.h
index 7279ec07d62e..7bbf6e47f8c8 100644
--- a/arch/frv/include/asm/elf.h
+++ b/arch/frv/include/asm/elf.h
@@ -116,6 +116,7 @@ do {											\
 } while(0)
 
 #define USE_ELF_CORE_DUMP
+#define CORE_DUMP_USE_REGSET
 #define ELF_FDPIC_CORE_EFLAGS	EF_FRV_FDPIC
 #define ELF_EXEC_PAGESIZE	16384
 
diff --git a/arch/frv/include/asm/pci.h b/arch/frv/include/asm/pci.h
index 3ce227ba7744..492b5c4dfed6 100644
--- a/arch/frv/include/asm/pci.h
+++ b/arch/frv/include/asm/pci.h
@@ -81,8 +81,7 @@ static inline void pci_dma_sync_single(struct pci_dev *hwdev,
 				       dma_addr_t dma_handle,
 				       size_t size, int direction)
 {
-	if (direction == PCI_DMA_NONE)
-                BUG();
+	BUG_ON(direction == PCI_DMA_NONE);
 
 	frv_cache_wback_inv((unsigned long)bus_to_virt(dma_handle),
 			    (unsigned long)bus_to_virt(dma_handle) + size);
@@ -99,9 +98,7 @@ static inline void pci_dma_sync_sg(struct pci_dev *hwdev,
 				   int nelems, int direction)
 {
 	int i;
-
-	if (direction == PCI_DMA_NONE)
-                BUG();
+	BUG_ON(direction == PCI_DMA_NONE);
 
 	for (i = 0; i < nelems; i++)
 		frv_cache_wback_inv(sg_dma_address(&sg[i]),
diff --git a/arch/frv/include/asm/ptrace.h b/arch/frv/include/asm/ptrace.h
index cf6934012b64..a54b535c9e49 100644
--- a/arch/frv/include/asm/ptrace.h
+++ b/arch/frv/include/asm/ptrace.h
@@ -65,6 +65,8 @@
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
 
+struct task_struct;
+
 /*
  * we dedicate GR28 to keeping a pointer to the current exception frame
  * - gr28 is destroyed on entry to the kernel from userspace
@@ -73,11 +75,18 @@ register struct pt_regs *__frame asm("gr28");
 
 #define user_mode(regs)			(!((regs)->psr & PSR_S))
 #define instruction_pointer(regs)	((regs)->pc)
+#define user_stack_pointer(regs)	((regs)->sp)
 
 extern unsigned long user_stack(const struct pt_regs *);
 extern void show_regs(struct pt_regs *);
 #define profile_pc(regs) ((regs)->pc)
-#endif
+
+#define task_pt_regs(task) ((task)->thread.frame0)
+
+#define arch_has_single_step()	(1)
+extern void user_enable_single_step(struct task_struct *);
+extern void user_disable_single_step(struct task_struct *);
 
 #endif /* !__ASSEMBLY__ */
+#endif /* __KERNEL__ */
 #endif /* _ASM_PTRACE_H */
diff --git a/arch/frv/include/asm/syscall.h b/arch/frv/include/asm/syscall.h
new file mode 100644
index 000000000000..70689eb29b98
--- /dev/null
+++ b/arch/frv/include/asm/syscall.h
@@ -0,0 +1,123 @@
+/* syscall parameter access functions
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _ASM_SYSCALL_H
+#define _ASM_SYSCALL_H
+
+#include <linux/err.h>
+#include <asm/ptrace.h>
+
+/*
+ * Get the system call number or -1
+ */
+static inline long syscall_get_nr(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	return regs->syscallno;
+}
+
+/*
+ * Restore the clobbered GR8 register
+ * (1st syscall arg was overwritten with syscall return or error)
+ */
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	regs->gr8 = regs->orig_gr8;
+}
+
+/*
+ * See if the syscall return value is an error, returning it if it is and 0 if
+ * not
+ */
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	return IS_ERR_VALUE(regs->gr8) ? regs->gr8 : 0;
+}
+
+/*
+ * Get the syscall return value
+ */
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->gr8;
+}
+
+/*
+ * Set the syscall return value
+ */
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	if (error)
+		regs->gr8 = -error;
+	else
+		regs->gr8 = val;
+}
+
+/*
+ * Retrieve the system call arguments
+ */
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	/*
+	 * Do this simply for now. If we need to start supporting
+	 * fetching arguments from arbitrary indices, this will need some
+	 * extra logic. Presently there are no in-tree users that depend
+	 * on this behaviour.
+	 */
+	BUG_ON(i);
+
+	/* Argument pattern is: GR8, GR9, GR10, GR11, GR12, GR13 */
+	switch (n) {
+	case 6: args[5] = regs->gr13;
+	case 5: args[4] = regs->gr12;
+	case 4: args[3] = regs->gr11;
+	case 3: args[2] = regs->gr10;
+	case 2: args[1] = regs->gr9;
+	case 1:	args[0] = regs->gr8;
+		break;
+	default:
+		BUG();
+	}
+}
+
+/*
+ * Alter the system call arguments
+ */
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	/* Same note as above applies */
+	BUG_ON(i);
+
+	switch (n) {
+	case 6: regs->gr13 = args[5];
+	case 5: regs->gr12 = args[4];
+	case 4: regs->gr11 = args[3];
+	case 3: regs->gr10 = args[2];
+	case 2: regs->gr9  = args[1];
+	case 1: regs->gr8  = args[0];
+		break;
+	default:
+		BUG();
+	}
+}
+
+#endif /* _ASM_SYSCALL_H */
diff --git a/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h
index bb53ab753ffb..e8a5ed7be021 100644
--- a/arch/frv/include/asm/thread_info.h
+++ b/arch/frv/include/asm/thread_info.h
@@ -109,20 +109,20 @@ register struct thread_info *__current_thread_info asm("gr15");
  * - other flags in MSW
  */
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
-#define TIF_SIGPENDING		1	/* signal pending */
-#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_SINGLESTEP		3	/* restore singlestep on return to user mode */
-#define TIF_IRET		4	/* return with iret */
+#define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
+#define TIF_SIGPENDING		2	/* signal pending */
+#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
+#define TIF_SINGLESTEP		4	/* restore singlestep on return to user mode */
 #define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		17	/* OOM killer killed process */
 #define TIF_FREEZE		18	/* freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
-#define _TIF_IRET		(1 << TIF_IRET)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_FREEZE		(1 << TIF_FREEZE)
diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S
index 1da523b3298e..356e0e327a89 100644
--- a/arch/frv/kernel/entry.S
+++ b/arch/frv/kernel/entry.S
@@ -886,7 +886,6 @@ system_call:
 	bnc		icc0,#0,__syscall_badsys
 
 	ldi		@(gr15,#TI_FLAGS),gr4
-	ori		gr4,#_TIF_SYSCALL_TRACE,gr4
 	andicc		gr4,#_TIF_SYSCALL_TRACE,gr0,icc0
 	bne		icc0,#0,__syscall_trace_entry
 
@@ -1150,11 +1149,10 @@ __entry_work_notifysig:
 	# perform syscall entry tracing
 __syscall_trace_entry:
 	LEDS		0x6320
-	setlos.p	#0,gr8
-	call		do_syscall_trace
+	call		syscall_trace_entry
 
-	ldi		@(gr28,#REG_SYSCALLNO),gr7
-	lddi		@(gr28,#REG_GR(8)) ,gr8
+	lddi.p		@(gr28,#REG_GR(8)) ,gr8
+	ori		gr8,#0,gr7		; syscall_trace_entry() returned new syscallno
 	lddi		@(gr28,#REG_GR(10)),gr10
 	lddi.p		@(gr28,#REG_GR(12)),gr12
 
@@ -1169,11 +1167,10 @@ __syscall_exit_work:
 	beq		icc0,#1,__entry_work_pending
 
 	movsg		psr,gr23
-	andi		gr23,#~PSR_PIL,gr23	; could let do_syscall_trace() call schedule()
+	andi		gr23,#~PSR_PIL,gr23	; could let syscall_trace_exit() call schedule()
 	movgs		gr23,psr
 
-	setlos.p	#1,gr8
-	call		do_syscall_trace
+	call		syscall_trace_exit
 	bra		__entry_resume_userspace
 
 __syscall_badsys:
diff --git a/arch/frv/kernel/ptrace.c b/arch/frv/kernel/ptrace.c
index 5e7d401d21e7..60eeed3694c0 100644
--- a/arch/frv/kernel/ptrace.c
+++ b/arch/frv/kernel/ptrace.c
@@ -19,6 +19,9 @@
 #include <linux/user.h>
 #include <linux/security.h>
 #include <linux/signal.h>
+#include <linux/regset.h>
+#include <linux/elf.h>
+#include <linux/tracehook.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -32,6 +35,169 @@
  * in exit.c or in signal.c.
  */
 
+/*
+ * retrieve the contents of FRV userspace general registers
+ */
+static int genregs_get(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       void *kbuf, void __user *ubuf)
+{
+	const struct user_int_regs *iregs = &target->thread.user->i;
+	int ret;
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  iregs, 0, sizeof(*iregs));
+	if (ret < 0)
+		return ret;
+
+	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					sizeof(*iregs), -1);
+}
+
+/*
+ * update the contents of the FRV userspace general registers
+ */
+static int genregs_set(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       const void *kbuf, const void __user *ubuf)
+{
+	struct user_int_regs *iregs = &target->thread.user->i;
+	unsigned int offs_gr0, offs_gr1;
+	int ret;
+
+	/* not allowed to set PSR or __status */
+	if (pos < offsetof(struct user_int_regs, psr) + sizeof(long) &&
+	    pos + count > offsetof(struct user_int_regs, psr))
+		return -EIO;
+
+	if (pos < offsetof(struct user_int_regs, __status) + sizeof(long) &&
+	    pos + count > offsetof(struct user_int_regs, __status))
+		return -EIO;
+
+	/* set the control regs */
+	offs_gr0 = offsetof(struct user_int_regs, gr[0]);
+	offs_gr1 = offsetof(struct user_int_regs, gr[1]);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 iregs, 0, offs_gr0);
+	if (ret < 0)
+		return ret;
+
+	/* skip GR0/TBR */
+	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+					offs_gr0, offs_gr1);
+	if (ret < 0)
+		return ret;
+
+	/* set the general regs */
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &iregs->gr[1], offs_gr1, sizeof(*iregs));
+	if (ret < 0)
+		return ret;
+
+	return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+					sizeof(*iregs), -1);
+}
+
+/*
+ * retrieve the contents of FRV userspace FP/Media registers
+ */
+static int fpmregs_get(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       void *kbuf, void __user *ubuf)
+{
+	const struct user_fpmedia_regs *fpregs = &target->thread.user->f;
+	int ret;
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  fpregs, 0, sizeof(*fpregs));
+	if (ret < 0)
+		return ret;
+
+	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					sizeof(*fpregs), -1);
+}
+
+/*
+ * update the contents of the FRV userspace FP/Media registers
+ */
+static int fpmregs_set(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       const void *kbuf, const void __user *ubuf)
+{
+	struct user_fpmedia_regs *fpregs = &target->thread.user->f;
+	int ret;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 fpregs, 0, sizeof(*fpregs));
+	if (ret < 0)
+		return ret;
+
+	return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+					sizeof(*fpregs), -1);
+}
+
+/*
+ * determine if the FP/Media registers have actually been used
+ */
+static int fpmregs_active(struct task_struct *target,
+			  const struct user_regset *regset)
+{
+	return tsk_used_math(target) ? regset->n : 0;
+}
+
+/*
+ * Define the register sets available on the FRV under Linux
+ */
+enum frv_regset {
+	REGSET_GENERAL,
+	REGSET_FPMEDIA,
+};
+
+static const struct user_regset frv_regsets[] = {
+	/*
+	 * General register format is:
+	 *	PSR, ISR, CCR, CCCR, LR, LCR, PC, (STATUS), SYSCALLNO, ORIG_G8
+	 *	GNER0-1, IACC0, TBR, GR1-63
+	 */
+	[REGSET_GENERAL] = {
+		.core_note_type	= NT_PRSTATUS,
+		.n		= ELF_NGREG,
+		.size		= sizeof(long),
+		.align		= sizeof(long),
+		.get		= genregs_get,
+		.set		= genregs_set,
+	},
+	/*
+	 * FPU/Media register format is:
+	 *	FR0-63, FNER0-1, MSR0-1, ACC0-7, ACCG0-8, FSR
+	 */
+	[REGSET_FPMEDIA] = {
+		.core_note_type	= NT_PRFPREG,
+		.n		= sizeof(struct user_fpmedia_regs) / sizeof(long),
+		.size		= sizeof(long),
+		.align		= sizeof(long),
+		.get		= fpmregs_get,
+		.set		= fpmregs_set,
+		.active		= fpmregs_active,
+	},
+};
+
+static const struct user_regset_view user_frv_native_view = {
+	.name		= "frv",
+	.e_machine	= EM_FRV,
+	.regsets	= frv_regsets,
+	.n		= ARRAY_SIZE(frv_regsets),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+	return &user_frv_native_view;
+}
+
 /*
  * Get contents of register REGNO in task TASK.
  */
@@ -68,41 +234,24 @@ static inline int put_reg(struct task_struct *task, int regno,
 	}
 }
 
-/*
- * check that an address falls within the bounds of the target process's memory
- * mappings
- */
-static inline int is_user_addr_valid(struct task_struct *child,
-				     unsigned long start, unsigned long len)
-{
-#ifdef CONFIG_MMU
-	if (start >= PAGE_OFFSET || len > PAGE_OFFSET - start)
-		return -EIO;
-	return 0;
-#else
-	struct vm_area_struct *vma;
-
-	vma = find_vma(child->mm, start);
-	if (vma && start >= vma->vm_start && start + len <= vma->vm_end)
-		return 0;
-
-	return -EIO;
-#endif
-}
-
 /*
  * Called by kernel/ptrace.c when detaching..
  *
  * Control h/w single stepping
  */
-void ptrace_disable(struct task_struct *child)
+void user_enable_single_step(struct task_struct *child)
+{
+	child->thread.frame0->__status |= REG__STATUS_STEP;
+}
+
+void user_disable_single_step(struct task_struct *child)
 {
 	child->thread.frame0->__status &= ~REG__STATUS_STEP;
 }
 
-void ptrace_enable(struct task_struct *child)
+void ptrace_disable(struct task_struct *child)
 {
-	child->thread.frame0->__status |= REG__STATUS_STEP;
+	user_disable_single_step(child);
 }
 
 long arch_ptrace(struct task_struct *child, long request, long addr, long data)
@@ -111,15 +260,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 	int ret;
 
 	switch (request) {
-		/* when I and D space are separate, these will need to be fixed. */
-	case PTRACE_PEEKTEXT: /* read word at location addr. */
-	case PTRACE_PEEKDATA:
-		ret = -EIO;
-		if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0)
-			break;
-		ret = generic_ptrace_peekdata(child, addr, data);
-		break;
-
 		/* read the word at location addr in the USER area. */
 	case PTRACE_PEEKUSR: {
 		tmp = 0;
@@ -163,15 +303,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		break;
 	}
 
-		/* when I and D space are separate, this will have to be fixed. */
-	case PTRACE_POKETEXT: /* write the word at location addr. */
-	case PTRACE_POKEDATA:
-		ret = -EIO;
-		if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0)
-			break;
-		ret = generic_ptrace_pokedata(child, addr, data);
-		break;
-
 	case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
 		ret = -EIO;
 		if ((addr & 3) || addr < 0)
@@ -179,7 +310,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 
 		ret = 0;
 		switch (addr >> 2) {
-		case 0 ... PT__END-1:
+		case 0 ... PT__END - 1:
 			ret = put_reg(child, addr >> 2, data);
 			break;
 
@@ -189,95 +320,29 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		}
 		break;
 
-	case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
-	case PTRACE_CONT: /* restart after signal. */
-		ret = -EIO;
-		if (!valid_signal(data))
-			break;
-		if (request == PTRACE_SYSCALL)
-			set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
-		else
-			clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
-		child->exit_code = data;
-		ptrace_disable(child);
-		wake_up_process(child);
-		ret = 0;
-		break;
+	case PTRACE_GETREGS:	/* Get all integer regs from the child. */
+		return copy_regset_to_user(child, &user_frv_native_view,
+					   REGSET_GENERAL,
+					   0, sizeof(child->thread.user->i),
+					   (void __user *)data);
 
-		/* make the child exit.  Best I can do is send it a sigkill.
-		 * perhaps it should be put in the status that it wants to
-		 * exit.
-		 */
-	case PTRACE_KILL:
-		ret = 0;
-		if (child->exit_state == EXIT_ZOMBIE)	/* already dead */
-			break;
-		child->exit_code = SIGKILL;
-		clear_tsk_thread_flag(child, TIF_SINGLESTEP);
-		ptrace_disable(child);
-		wake_up_process(child);
-		break;
+	case PTRACE_SETREGS:	/* Set all integer regs in the child. */
+		return copy_regset_from_user(child, &user_frv_native_view,
+					     REGSET_GENERAL,
+					     0, sizeof(child->thread.user->i),
+					     (const void __user *)data);
 
-	case PTRACE_SINGLESTEP:  /* set the trap flag. */
-		ret = -EIO;
-		if (!valid_signal(data))
-			break;
-		clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
-		ptrace_enable(child);
-		child->exit_code = data;
-		wake_up_process(child);
-		ret = 0;
-		break;
+	case PTRACE_GETFPREGS:	/* Get the child FP/Media state. */
+		return copy_regset_to_user(child, &user_frv_native_view,
+					   REGSET_FPMEDIA,
+					   0, sizeof(child->thread.user->f),
+					   (void __user *)data);
 
-	case PTRACE_DETACH:	/* detach a process that was attached. */
-		ret = ptrace_detach(child, data);
-		break;
-
-	case PTRACE_GETREGS: { /* Get all integer regs from the child. */
-		int i;
-		for (i = 0; i < PT__GPEND; i++) {
-			tmp = get_reg(child, i);
-			if (put_user(tmp, (unsigned long *) data)) {
-				ret = -EFAULT;
-				break;
-			}
-			data += sizeof(long);
-		}
-		ret = 0;
-		break;
-	}
-
-	case PTRACE_SETREGS: { /* Set all integer regs in the child. */
-		int i;
-		for (i = 0; i < PT__GPEND; i++) {
-			if (get_user(tmp, (unsigned long *) data)) {
-				ret = -EFAULT;
-				break;
-			}
-			put_reg(child, i, tmp);
-			data += sizeof(long);
-		}
-		ret = 0;
-		break;
-	}
-
-	case PTRACE_GETFPREGS: { /* Get the child FP/Media state. */
-		ret = 0;
-		if (copy_to_user((void *) data,
-				 &child->thread.user->f,
-				 sizeof(child->thread.user->f)))
-			ret = -EFAULT;
-		break;
-	}
-
-	case PTRACE_SETFPREGS: { /* Set the child FP/Media state. */
-		ret = 0;
-		if (copy_from_user(&child->thread.user->f,
-				   (void *) data,
-				   sizeof(child->thread.user->f)))
-			ret = -EFAULT;
-		break;
-	}
+	case PTRACE_SETFPREGS:	/* Set the child FP/Media state. */
+		return copy_regset_from_user(child, &user_frv_native_view,
+					     REGSET_FPMEDIA,
+					     0, sizeof(child->thread.user->f),
+					     (const void __user *)data);
 
 	case PTRACE_GETFDPIC:
 		tmp = 0;
@@ -300,414 +365,36 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		break;
 
 	default:
-		ret = -EIO;
+		ret = ptrace_request(child, request, addr, data);
 		break;
 	}
 	return ret;
 }
 
-int __nongprelbss kstrace;
-
-static const struct {
-	const char	*name;
-	unsigned	argmask;
-} __syscall_name_table[NR_syscalls] = {
-	[0]	= { "restart_syscall"			},
-	[1]	= { "exit",		0x000001	},
-	[2]	= { "fork",		0xffffff	},
-	[3]	= { "read",		0x000141	},
-	[4]	= { "write",		0x000141	},
-	[5]	= { "open",		0x000235	},
-	[6]	= { "close",		0x000001	},
-	[7]	= { "waitpid",		0x000141	},
-	[8]	= { "creat",		0x000025	},
-	[9]	= { "link",		0x000055	},
-	[10]	= { "unlink",		0x000005	},
-	[11]	= { "execve",		0x000445	},
-	[12]	= { "chdir",		0x000005	},
-	[13]	= { "time",		0x000004	},
-	[14]	= { "mknod",		0x000325	},
-	[15]	= { "chmod",		0x000025	},
-	[16]	= { "lchown",		0x000025	},
-	[17]	= { "break" },
-	[18]	= { "oldstat",		0x000045	},
-	[19]	= { "lseek",		0x000131	},
-	[20]	= { "getpid",		0xffffff	},
-	[21]	= { "mount",		0x043555	},
-	[22]	= { "umount",		0x000005	},
-	[23]	= { "setuid",		0x000001	},
-	[24]	= { "getuid",		0xffffff	},
-	[25]	= { "stime",		0x000004	},
-	[26]	= { "ptrace",		0x004413	},
-	[27]	= { "alarm",		0x000001	},
-	[28]	= { "oldfstat",		0x000041	},
-	[29]	= { "pause",		0xffffff	},
-	[30]	= { "utime",		0x000045	},
-	[31]	= { "stty" },
-	[32]	= { "gtty" },
-	[33]	= { "access",		0x000025	},
-	[34]	= { "nice",		0x000001	},
-	[35]	= { "ftime" },
-	[36]	= { "sync",		0xffffff	},
-	[37]	= { "kill",		0x000011	},
-	[38]	= { "rename",		0x000055	},
-	[39]	= { "mkdir",		0x000025	},
-	[40]	= { "rmdir",		0x000005	},
-	[41]	= { "dup",		0x000001	},
-	[42]	= { "pipe",		0x000004	},
-	[43]	= { "times",		0x000004	},
-	[44]	= { "prof" },
-	[45]	= { "brk",		0x000004	},
-	[46]	= { "setgid",		0x000001	},
-	[47]	= { "getgid",		0xffffff	},
-	[48]	= { "signal",		0x000041	},
-	[49]	= { "geteuid",		0xffffff	},
-	[50]	= { "getegid",		0xffffff	},
-	[51]	= { "acct",		0x000005	},
-	[52]	= { "umount2",		0x000035	},
-	[53]	= { "lock" },
-	[54]	= { "ioctl",		0x000331	},
-	[55]	= { "fcntl",		0x000331	},
-	[56]	= { "mpx" },
-	[57]	= { "setpgid",		0x000011	},
-	[58]	= { "ulimit" },
-	[60]	= { "umask",		0x000002	},
-	[61]	= { "chroot",		0x000005	},
-	[62]	= { "ustat",		0x000043	},
-	[63]	= { "dup2",		0x000011	},
-	[64]	= { "getppid",		0xffffff	},
-	[65]	= { "getpgrp",		0xffffff	},
-	[66]	= { "setsid",		0xffffff	},
-	[67]	= { "sigaction" },
-	[68]	= { "sgetmask" },
-	[69]	= { "ssetmask" },
-	[70]	= { "setreuid" },
-	[71]	= { "setregid" },
-	[72]	= { "sigsuspend" },
-	[73]	= { "sigpending" },
-	[74]	= { "sethostname" },
-	[75]	= { "setrlimit" },
-	[76]	= { "getrlimit" },
-	[77]	= { "getrusage" },
-	[78]	= { "gettimeofday" },
-	[79]	= { "settimeofday" },
-	[80]	= { "getgroups" },
-	[81]	= { "setgroups" },
-	[82]	= { "select" },
-	[83]	= { "symlink" },
-	[84]	= { "oldlstat" },
-	[85]	= { "readlink" },
-	[86]	= { "uselib" },
-	[87]	= { "swapon" },
-	[88]	= { "reboot" },
-	[89]	= { "readdir" },
-	[91]	= { "munmap",		0x000034	},
-	[92]	= { "truncate" },
-	[93]	= { "ftruncate" },
-	[94]	= { "fchmod" },
-	[95]	= { "fchown" },
-	[96]	= { "getpriority" },
-	[97]	= { "setpriority" },
-	[99]	= { "statfs" },
-	[100]	= { "fstatfs" },
-	[102]	= { "socketcall" },
-	[103]	= { "syslog" },
-	[104]	= { "setitimer" },
-	[105]	= { "getitimer" },
-	[106]	= { "stat" },
-	[107]	= { "lstat" },
-	[108]	= { "fstat" },
-	[111]	= { "vhangup" },
-	[114]	= { "wait4" },
-	[115]	= { "swapoff" },
-	[116]	= { "sysinfo" },
-	[117]	= { "ipc" },
-	[118]	= { "fsync" },
-	[119]	= { "sigreturn" },
-	[120]	= { "clone" },
-	[121]	= { "setdomainname" },
-	[122]	= { "uname" },
-	[123]	= { "modify_ldt" },
-	[123]	= { "cacheflush" },
-	[124]	= { "adjtimex" },
-	[125]	= { "mprotect" },
-	[126]	= { "sigprocmask" },
-	[127]	= { "create_module" },
-	[128]	= { "init_module" },
-	[129]	= { "delete_module" },
-	[130]	= { "get_kernel_syms" },
-	[131]	= { "quotactl" },
-	[132]	= { "getpgid" },
-	[133]	= { "fchdir" },
-	[134]	= { "bdflush" },
-	[135]	= { "sysfs" },
-	[136]	= { "personality" },
-	[137]	= { "afs_syscall" },
-	[138]	= { "setfsuid" },
-	[139]	= { "setfsgid" },
-	[140]	= { "_llseek",			0x014331	},
-	[141]	= { "getdents" },
-	[142]	= { "_newselect",		0x000141	},
-	[143]	= { "flock" },
-	[144]	= { "msync" },
-	[145]	= { "readv" },
-	[146]	= { "writev" },
-	[147]	= { "getsid",			0x000001	},
-	[148]	= { "fdatasync",		0x000001	},
-	[149]	= { "_sysctl",			0x000004	},
-	[150]	= { "mlock" },
-	[151]	= { "munlock" },
-	[152]	= { "mlockall" },
-	[153]	= { "munlockall" },
-	[154]	= { "sched_setparam" },
-	[155]	= { "sched_getparam" },
-	[156]	= { "sched_setscheduler" },
-	[157]	= { "sched_getscheduler" },
-	[158]	= { "sched_yield" },
-	[159]	= { "sched_get_priority_max" },
-	[160]	= { "sched_get_priority_min" },
-	[161]	= { "sched_rr_get_interval" },
-	[162]	= { "nanosleep",		0x000044	},
-	[163]	= { "mremap" },
-	[164]	= { "setresuid" },
-	[165]	= { "getresuid" },
-	[166]	= { "vm86" },
-	[167]	= { "query_module" },
-	[168]	= { "poll" },
-	[169]	= { "nfsservctl" },
-	[170]	= { "setresgid" },
-	[171]	= { "getresgid" },
-	[172]	= { "prctl",			0x333331	},
-	[173]	= { "rt_sigreturn",		0xffffff	},
-	[174]	= { "rt_sigaction",		0x001441	},
-	[175]	= { "rt_sigprocmask",		0x001441	},
-	[176]	= { "rt_sigpending",		0x000014	},
-	[177]	= { "rt_sigtimedwait",		0x001444	},
-	[178]	= { "rt_sigqueueinfo",		0x000411	},
-	[179]	= { "rt_sigsuspend",		0x000014	},
-	[180]	= { "pread",			0x003341	},
-	[181]	= { "pwrite",			0x003341	},
-	[182]	= { "chown",			0x000115	},
-	[183]	= { "getcwd" },
-	[184]	= { "capget" },
-	[185]	= { "capset" },
-	[186]	= { "sigaltstack" },
-	[187]	= { "sendfile" },
-	[188]	= { "getpmsg" },
-	[189]	= { "putpmsg" },
-	[190]	= { "vfork",			0xffffff	},
-	[191]	= { "ugetrlimit" },
-	[192]	= { "mmap2",			0x313314	},
-	[193]	= { "truncate64" },
-	[194]	= { "ftruncate64" },
-	[195]	= { "stat64",			0x000045	},
-	[196]	= { "lstat64",			0x000045	},
-	[197]	= { "fstat64",			0x000041	},
-	[198]	= { "lchown32" },
-	[199]	= { "getuid32",			0xffffff	},
-	[200]	= { "getgid32",			0xffffff	},
-	[201]	= { "geteuid32",		0xffffff	},
-	[202]	= { "getegid32",		0xffffff	},
-	[203]	= { "setreuid32" },
-	[204]	= { "setregid32" },
-	[205]	= { "getgroups32" },
-	[206]	= { "setgroups32" },
-	[207]	= { "fchown32" },
-	[208]	= { "setresuid32" },
-	[209]	= { "getresuid32" },
-	[210]	= { "setresgid32" },
-	[211]	= { "getresgid32" },
-	[212]	= { "chown32" },
-	[213]	= { "setuid32" },
-	[214]	= { "setgid32" },
-	[215]	= { "setfsuid32" },
-	[216]	= { "setfsgid32" },
-	[217]	= { "pivot_root" },
-	[218]	= { "mincore" },
-	[219]	= { "madvise" },
-	[220]	= { "getdents64" },
-	[221]	= { "fcntl64" },
-	[223]	= { "security" },
-	[224]	= { "gettid" },
-	[225]	= { "readahead" },
-	[226]	= { "setxattr" },
-	[227]	= { "lsetxattr" },
-	[228]	= { "fsetxattr" },
-	[229]	= { "getxattr" },
-	[230]	= { "lgetxattr" },
-	[231]	= { "fgetxattr" },
-	[232]	= { "listxattr" },
-	[233]	= { "llistxattr" },
-	[234]	= { "flistxattr" },
-	[235]	= { "removexattr" },
-	[236]	= { "lremovexattr" },
-	[237]	= { "fremovexattr" },
-	[238]	= { "tkill" },
-	[239]	= { "sendfile64" },
-	[240]	= { "futex" },
-	[241]	= { "sched_setaffinity" },
-	[242]	= { "sched_getaffinity" },
-	[243]	= { "set_thread_area" },
-	[244]	= { "get_thread_area" },
-	[245]	= { "io_setup" },
-	[246]	= { "io_destroy" },
-	[247]	= { "io_getevents" },
-	[248]	= { "io_submit" },
-	[249]	= { "io_cancel" },
-	[250]	= { "fadvise64" },
-	[252]	= { "exit_group",		0x000001	},
-	[253]	= { "lookup_dcookie" },
-	[254]	= { "epoll_create" },
-	[255]	= { "epoll_ctl" },
-	[256]	= { "epoll_wait" },
-	[257]	= { "remap_file_pages" },
-	[258]	= { "set_tid_address" },
-	[259]	= { "timer_create" },
-	[260]	= { "timer_settime" },
-	[261]	= { "timer_gettime" },
-	[262]	= { "timer_getoverrun" },
-	[263]	= { "timer_delete" },
-	[264]	= { "clock_settime" },
-	[265]	= { "clock_gettime" },
-	[266]	= { "clock_getres" },
-	[267]	= { "clock_nanosleep" },
-	[268]	= { "statfs64" },
-	[269]	= { "fstatfs64" },
-	[270]	= { "tgkill" },
-	[271]	= { "utimes" },
-	[272]	= { "fadvise64_64" },
-	[273]	= { "vserver" },
-	[274]	= { "mbind" },
-	[275]	= { "get_mempolicy" },
-	[276]	= { "set_mempolicy" },
-	[277]	= { "mq_open" },
-	[278]	= { "mq_unlink" },
-	[279]	= { "mq_timedsend" },
-	[280]	= { "mq_timedreceive" },
-	[281]	= { "mq_notify" },
-	[282]	= { "mq_getsetattr" },
-	[283]	= { "sys_kexec_load" },
-};
-
-asmlinkage void do_syscall_trace(int leaving)
+/*
+ * handle tracing of system call entry
+ * - return the revised system call number or ULONG_MAX to cause ENOSYS
+ */
+asmlinkage unsigned long syscall_trace_entry(void)
 {
-#if 0
-	unsigned long *argp;
-	const char *name;
-	unsigned argmask;
-	char buffer[16];
-
-	if (!kstrace)
-		return;
-
-	if (!current->mm)
-		return;
-
-	if (__frame->gr7 == __NR_close)
-		return;
-
-#if 0
-	if (__frame->gr7 != __NR_mmap2 &&
-	    __frame->gr7 != __NR_vfork &&
-	    __frame->gr7 != __NR_execve &&
-	    __frame->gr7 != __NR_exit)
-		return;
-#endif
-
-	argmask = 0;
-	name = NULL;
-	if (__frame->gr7 < NR_syscalls) {
-		name = __syscall_name_table[__frame->gr7].name;
-		argmask = __syscall_name_table[__frame->gr7].argmask;
-	}
-	if (!name) {
-		sprintf(buffer, "sys_%lx", __frame->gr7);
-		name = buffer;
+	__frame->__status |= REG__STATUS_SYSC_ENTRY;
+	if (tracehook_report_syscall_entry(__frame)) {
+		/* tracing decided this syscall should not happen, so
+		 * We'll return a bogus call number to get an ENOSYS
+		 * error, but leave the original number in
+		 * __frame->syscallno
+		 */
+		return ULONG_MAX;
 	}
 
-	if (!leaving) {
-		if (!argmask) {
-			printk(KERN_CRIT "[%d] %s(%lx,%lx,%lx,%lx,%lx,%lx)\n",
-			       current->pid,
-			       name,
-			       __frame->gr8,
-			       __frame->gr9,
-			       __frame->gr10,
-			       __frame->gr11,
-			       __frame->gr12,
-			       __frame->gr13);
-		}
-		else if (argmask == 0xffffff) {
-			printk(KERN_CRIT "[%d] %s()\n",
-			       current->pid,
-			       name);
-		}
-		else {
-			printk(KERN_CRIT "[%d] %s(",
-			       current->pid,
-			       name);
-
-			argp = &__frame->gr8;
-
-			do {
-				switch (argmask & 0xf) {
-				case 1:
-					printk("%ld", (long) *argp);
-					break;
-				case 2:
-					printk("%lo", *argp);
-					break;
-				case 3:
-					printk("%lx", *argp);
-					break;
-				case 4:
-					printk("%p", (void *) *argp);
-					break;
-				case 5:
-					printk("\"%s\"", (char *) *argp);
-					break;
-				}
-
-				argp++;
-				argmask >>= 4;
-				if (argmask)
-					printk(",");
-
-			} while (argmask);
-
-			printk(")\n");
-		}
-	}
-	else {
-		if ((int)__frame->gr8 > -4096 && (int)__frame->gr8 < 4096)
-			printk(KERN_CRIT "[%d] %s() = %ld\n", current->pid, name, __frame->gr8);
-		else
-			printk(KERN_CRIT "[%d] %s() = %lx\n", current->pid, name, __frame->gr8);
-	}
-	return;
-#endif
-
-	if (!test_thread_flag(TIF_SYSCALL_TRACE))
-		return;
-
-	if (!(current->ptrace & PT_PTRACED))
-		return;
-
-	/* we need to indicate entry or exit to strace */
-	if (leaving)
-		__frame->__status |= REG__STATUS_SYSC_EXIT;
-	else
-		__frame->__status |= REG__STATUS_SYSC_ENTRY;
-
-	ptrace_notify(SIGTRAP);
-
-	/*
-	 * this isn't the same as continuing with a signal, but it will do
-	 * for normal use.  strace only continues with a signal if the
-	 * stopping signal is not SIGTRAP.  -brl
-	 */
-	if (current->exit_code) {
-		send_sig(current->exit_code, current, 1);
-		current->exit_code = 0;
-	}
+	return __frame->syscallno;
+}
+
+/*
+ * handle tracing of system call exit
+ */
+asmlinkage void syscall_trace_exit(void)
+{
+	__frame->__status |= REG__STATUS_SYSC_EXIT;
+	tracehook_report_syscall_exit(__frame, 0);
 }
diff --git a/arch/frv/kernel/signal.c b/arch/frv/kernel/signal.c
index 3bdb368292a8..4a7a62c6e783 100644
--- a/arch/frv/kernel/signal.c
+++ b/arch/frv/kernel/signal.c
@@ -21,6 +21,7 @@
 #include <linux/unistd.h>
 #include <linux/personality.h>
 #include <linux/freezer.h>
+#include <linux/tracehook.h>
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -516,6 +517,9 @@ static void do_signal(void)
 			 * clear the TIF_RESTORE_SIGMASK flag */
 			if (test_thread_flag(TIF_RESTORE_SIGMASK))
 				clear_thread_flag(TIF_RESTORE_SIGMASK);
+
+			tracehook_signal_handler(signr, &info, &ka, __frame,
+						 test_thread_flag(TIF_SINGLESTEP));
 		}
 
 		return;
@@ -564,4 +568,10 @@ asmlinkage void do_notify_resume(__u32 thread_info_flags)
 	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK))
 		do_signal();
 
+	/* deal with notification on about to resume userspace execution */
+	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+		clear_thread_flag(TIF_NOTIFY_RESUME);
+		tracehook_notify_resume(__frame);
+	}
+
 } /* end do_notify_resume() */
diff --git a/arch/frv/kernel/uaccess.c b/arch/frv/kernel/uaccess.c
index 9fb771a20df3..374f88d6cc00 100644
--- a/arch/frv/kernel/uaccess.c
+++ b/arch/frv/kernel/uaccess.c
@@ -23,8 +23,7 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
 	char *p, ch;
 	long err = -EFAULT;
 
-	if (count < 0)
-		BUG();
+	BUG_ON(count < 0);
 
 	p = dst;
 
@@ -76,8 +75,7 @@ long strnlen_user(const char __user *src, long count)
 	long err = 0;
 	char ch;
 
-	if (count < 0)
-		BUG();
+	BUG_ON(count < 0);
 
 #ifndef CONFIG_MMU
 	if ((unsigned long) src < memory_start)
diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c
index 52ff9aec799d..4e1ba0b15443 100644
--- a/arch/frv/mb93090-mb00/pci-dma-nommu.c
+++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c
@@ -116,8 +116,7 @@ EXPORT_SYMBOL(dma_free_coherent);
 dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
 			  enum dma_data_direction direction)
 {
-	if (direction == DMA_NONE)
-                BUG();
+	BUG_ON(direction == DMA_NONE);
 
 	frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size);
 
@@ -151,8 +150,7 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		frv_cache_wback_inv(sg_dma_address(&sg[i]),
 				    sg_dma_address(&sg[i]) + sg_dma_len(&sg[i]));
 
-	if (direction == DMA_NONE)
-                BUG();
+	BUG_ON(direction == DMA_NONE);
 
 	return nents;
 }
diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c
index 3ddedebc4eb3..45954f0813dc 100644
--- a/arch/frv/mb93090-mb00/pci-dma.c
+++ b/arch/frv/mb93090-mb00/pci-dma.c
@@ -48,8 +48,7 @@ EXPORT_SYMBOL(dma_free_coherent);
 dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
 			  enum dma_data_direction direction)
 {
-	if (direction == DMA_NONE)
-                BUG();
+	BUG_ON(direction == DMA_NONE);
 
 	frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size);
 
@@ -81,8 +80,7 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	void *vaddr;
 	int i;
 
-	if (direction == DMA_NONE)
-                BUG();
+	BUG_ON(direction == DMA_NONE);
 
 	dampr2 = __get_DAMPR(2);
 
diff --git a/arch/ia64/hp/sim/hpsim_irq.c b/arch/ia64/hp/sim/hpsim_irq.c
index cc0a3182db3c..acb5047ab573 100644
--- a/arch/ia64/hp/sim/hpsim_irq.c
+++ b/arch/ia64/hp/sim/hpsim_irq.c
@@ -21,9 +21,10 @@ hpsim_irq_noop (unsigned int irq)
 {
 }
 
-static void
+static int
 hpsim_set_affinity_noop(unsigned int a, const struct cpumask *b)
 {
+	return 0;
 }
 
 static struct hw_interrupt_type irq_type_hp_sim = {
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 4542651e6acb..5f43697aed30 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -371,6 +371,7 @@ struct kvm_vcpu_arch {
 	int last_run_cpu;
 	int vmm_tr_slot;
 	int vm_tr_slot;
+	int sn_rtc_tr_slot;
 
 #define KVM_MP_STATE_RUNNABLE          0
 #define KVM_MP_STATE_UNINITIALIZED     1
@@ -465,6 +466,7 @@ struct kvm_arch {
 	unsigned long	vmm_init_rr;
 
 	int		online_vcpus;
+	int		is_sn2;
 
 	struct kvm_ioapic *vioapic;
 	struct kvm_vm_stat stat;
@@ -472,6 +474,7 @@ struct kvm_arch {
 
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
+	int iommu_flags;
 	struct hlist_head irq_ack_notifier_list;
 
 	unsigned long irq_sources_bitmap;
@@ -578,6 +581,8 @@ struct kvm_vmm_info{
 	kvm_vmm_entry 	*vmm_entry;
 	kvm_tramp_entry *tramp_entry;
 	unsigned long 	vmm_ivt;
+	unsigned long	patch_mov_ar;
+	unsigned long	patch_mov_ar_sn2;
 };
 
 int kvm_highest_pending_irq(struct kvm_vcpu *vcpu);
@@ -585,7 +590,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
 void kvm_sal_emul(struct kvm_vcpu *vcpu);
 
-static inline void kvm_inject_nmi(struct kvm_vcpu *vcpu) {}
 #endif /* __ASSEMBLY__*/
 
 #endif
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 7a9bff47564f..0a9cc73d35c7 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -146,6 +146,8 @@
 #define PAGE_GATE	__pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_X_RX)
 #define PAGE_KERNEL	__pgprot(__DIRTY_BITS  | _PAGE_PL_0 | _PAGE_AR_RWX)
 #define PAGE_KERNELRX	__pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_RX)
+#define PAGE_KERNEL_UC	__pgprot(__DIRTY_BITS  | _PAGE_PL_0 | _PAGE_AR_RWX | \
+				 _PAGE_MA_UC)
 
 # ifndef __ASSEMBLY__
 
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 5510317db37b..baec6f00f7f3 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -636,7 +636,7 @@ void __init acpi_numa_arch_fixup(void)
  * success: return IRQ number (>=0)
  * failure: return < 0
  */
-int acpi_register_gsi(u32 gsi, int triggering, int polarity)
+int acpi_register_gsi(struct device *dev, u32 gsi, int triggering, int polarity)
 {
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PLATFORM)
 		return gsi;
@@ -678,7 +678,8 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
 
 	fadt = (struct acpi_table_fadt *)fadt_header;
 
-	acpi_register_gsi(fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW);
+	acpi_register_gsi(NULL, fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE,
+				 ACPI_ACTIVE_LOW);
 	return 0;
 }
 
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index 166e0d839fa0..f92cef47bf86 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -329,7 +329,7 @@ unmask_irq (unsigned int irq)
 }
 
 
-static void
+static int
 iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 #ifdef CONFIG_SMP
@@ -343,15 +343,15 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	cpu = cpumask_first_and(cpu_online_mask, mask);
 	if (cpu >= nr_cpu_ids)
-		return;
+		return -1;
 
 	if (irq_prepare_move(irq, cpu))
-		return;
+		return -1;
 
 	dest = cpu_physical_id(cpu);
 
 	if (!iosapic_intr_info[irq].count)
-		return;			/* not an IOSAPIC interrupt */
+		return -1;			/* not an IOSAPIC interrupt */
 
 	set_irq_affinity_info(irq, dest, redir);
 
@@ -376,7 +376,9 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
 		iosapic_write(iosapic, IOSAPIC_RTE_HIGH(rte_index), high32);
 		iosapic_write(iosapic, IOSAPIC_RTE_LOW(rte_index), low32);
 	}
+
 #endif
+	return 0;
 }
 
 /*
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index acc4d19ae62a..b448197728be 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -610,6 +610,9 @@ static struct irqaction ipi_irqaction = {
 	.name =		"IPI"
 };
 
+/*
+ * KVM uses this interrupt to force a cpu out of guest mode
+ */
 static struct irqaction resched_irqaction = {
 	.handler =	dummy_handler,
 	.flags =	IRQF_DISABLED,
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 2b15e233f7fe..0f8ade9331ba 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -12,7 +12,7 @@
 static struct irq_chip	ia64_msi_chip;
 
 #ifdef CONFIG_SMP
-static void ia64_set_msi_irq_affinity(unsigned int irq,
+static int ia64_set_msi_irq_affinity(unsigned int irq,
 				      const cpumask_t *cpu_mask)
 {
 	struct msi_msg msg;
@@ -20,10 +20,10 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
 	int cpu = first_cpu(*cpu_mask);
 
 	if (!cpu_online(cpu))
-		return;
+		return -1;
 
 	if (irq_prepare_move(irq, cpu))
-		return;
+		return -1;
 
 	read_msi_msg(irq, &msg);
 
@@ -39,6 +39,8 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
 
 	write_msi_msg(irq, &msg);
 	cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
+
+	return 0;
 }
 #endif /* CONFIG_SMP */
 
@@ -130,17 +132,17 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 #ifdef CONFIG_DMAR
 #ifdef CONFIG_SMP
-static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_cfg *cfg = irq_cfg + irq;
 	struct msi_msg msg;
 	int cpu = cpumask_first(mask);
 
 	if (!cpu_online(cpu))
-		return;
+		return -1;
 
 	if (irq_prepare_move(irq, cpu))
-		return;
+		return -1;
 
 	dmar_msi_read(irq, &msg);
 
@@ -151,6 +153,8 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dmar_msi_write(irq, &msg);
 	cpumask_copy(irq_desc[irq].affinity, mask);
+
+	return 0;
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
index 0a2d6b86075a..64d520937874 100644
--- a/arch/ia64/kvm/Kconfig
+++ b/arch/ia64/kvm/Kconfig
@@ -23,7 +23,7 @@ if VIRTUALIZATION
 
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
-	depends on HAVE_KVM && EXPERIMENTAL
+	depends on HAVE_KVM && MODULES && EXPERIMENTAL
 	# for device assignment:
 	depends on PCI
 	select PREEMPT_NOTIFIERS
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index d20a5db4c4dd..80c57b0a21c4 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -41,6 +41,9 @@
 #include <asm/div64.h>
 #include <asm/tlb.h>
 #include <asm/elf.h>
+#include <asm/sn/addrs.h>
+#include <asm/sn/clksupport.h>
+#include <asm/sn/shub_mmr.h>
 
 #include "misc.h"
 #include "vti.h"
@@ -65,6 +68,16 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
+static unsigned long kvm_get_itc(struct kvm_vcpu *vcpu)
+{
+#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
+	if (vcpu->kvm->arch.is_sn2)
+		return rtc_time();
+	else
+#endif
+		return ia64_getreg(_IA64_REG_AR_ITC);
+}
+
 static void kvm_flush_icache(unsigned long start, unsigned long len)
 {
 	int l;
@@ -119,8 +132,7 @@ void kvm_arch_hardware_enable(void *garbage)
 	unsigned long saved_psr;
 	int slot;
 
-	pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base),
-				PAGE_KERNEL));
+	pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base), PAGE_KERNEL));
 	local_irq_save(saved_psr);
 	slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
 	local_irq_restore(saved_psr);
@@ -283,6 +295,18 @@ static int handle_sal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 }
 
+static int __apic_accept_irq(struct kvm_vcpu *vcpu, uint64_t vector)
+{
+	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+	if (!test_and_set_bit(vector, &vpd->irr[0])) {
+		vcpu->arch.irq_new_pending = 1;
+		kvm_vcpu_kick(vcpu);
+		return 1;
+	}
+	return 0;
+}
+
 /*
  *  offset: address offset to IPI space.
  *  value:  deliver value.
@@ -292,20 +316,20 @@ static void vcpu_deliver_ipi(struct kvm_vcpu *vcpu, uint64_t dm,
 {
 	switch (dm) {
 	case SAPIC_FIXED:
-		kvm_apic_set_irq(vcpu, vector, 0);
 		break;
 	case SAPIC_NMI:
-		kvm_apic_set_irq(vcpu, 2, 0);
+		vector = 2;
 		break;
 	case SAPIC_EXTINT:
-		kvm_apic_set_irq(vcpu, 0, 0);
+		vector = 0;
 		break;
 	case SAPIC_INIT:
 	case SAPIC_PMI:
 	default:
 		printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n");
-		break;
+		return;
 	}
+	__apic_accept_irq(vcpu, vector);
 }
 
 static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id,
@@ -413,6 +437,23 @@ static int handle_switch_rr6(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return 1;
 }
 
+static int kvm_sn2_setup_mappings(struct kvm_vcpu *vcpu)
+{
+	unsigned long pte, rtc_phys_addr, map_addr;
+	int slot;
+
+	map_addr = KVM_VMM_BASE + (1UL << KVM_VMM_SHIFT);
+	rtc_phys_addr = LOCAL_MMR_OFFSET | SH_RTC;
+	pte = pte_val(mk_pte_phys(rtc_phys_addr, PAGE_KERNEL_UC));
+	slot = ia64_itr_entry(0x3, map_addr, pte, PAGE_SHIFT);
+	vcpu->arch.sn_rtc_tr_slot = slot;
+	if (slot < 0) {
+		printk(KERN_ERR "Mayday mayday! RTC mapping failed!\n");
+		slot = 0;
+	}
+	return slot;
+}
+
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 {
 
@@ -426,7 +467,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
 
-		vcpu_now_itc = ia64_getreg(_IA64_REG_AR_ITC) + vcpu->arch.itc_offset;
+		vcpu_now_itc = kvm_get_itc(vcpu) + vcpu->arch.itc_offset;
 
 		if (time_after(vcpu_now_itc, vpd->itm)) {
 			vcpu->arch.timer_check = 1;
@@ -447,10 +488,10 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 		hrtimer_cancel(p_ht);
 		vcpu->arch.ht_active = 0;
 
-		if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
+		if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests) ||
+				kvm_cpu_has_pending_timer(vcpu))
 			if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
-				vcpu->arch.mp_state =
-					KVM_MP_STATE_RUNNABLE;
+				vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 		if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
 			return -EINTR;
@@ -551,22 +592,35 @@ static int kvm_insert_vmm_mapping(struct kvm_vcpu *vcpu)
 	if (r < 0)
 		goto out;
 	vcpu->arch.vm_tr_slot = r;
+
+#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
+	if (kvm->arch.is_sn2) {
+		r = kvm_sn2_setup_mappings(vcpu);
+		if (r < 0)
+			goto out;
+	}
+#endif
+
 	r = 0;
 out:
 	return r;
-
 }
 
 static void kvm_purge_vmm_mapping(struct kvm_vcpu *vcpu)
 {
-
+	struct kvm *kvm = vcpu->kvm;
 	ia64_ptr_entry(0x3, vcpu->arch.vmm_tr_slot);
 	ia64_ptr_entry(0x3, vcpu->arch.vm_tr_slot);
-
+#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
+	if (kvm->arch.is_sn2)
+		ia64_ptr_entry(0x3, vcpu->arch.sn_rtc_tr_slot);
+#endif
 }
 
 static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
 {
+	unsigned long psr;
+	int r;
 	int cpu = smp_processor_id();
 
 	if (vcpu->arch.last_run_cpu != cpu ||
@@ -578,36 +632,27 @@ static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.host_rr6 = ia64_get_rr(RR6);
 	vti_set_rr6(vcpu->arch.vmm_rr);
-	return kvm_insert_vmm_mapping(vcpu);
+	local_irq_save(psr);
+	r = kvm_insert_vmm_mapping(vcpu);
+	local_irq_restore(psr);
+	return r;
 }
+
 static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu)
 {
 	kvm_purge_vmm_mapping(vcpu);
 	vti_set_rr6(vcpu->arch.host_rr6);
 }
 
-static int  vti_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	union context *host_ctx, *guest_ctx;
 	int r;
 
-	/*Get host and guest context with guest address space.*/
-	host_ctx = kvm_get_host_context(vcpu);
-	guest_ctx = kvm_get_guest_context(vcpu);
-
-	r = kvm_vcpu_pre_transition(vcpu);
-	if (r < 0)
-		goto out;
-	kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
-	kvm_vcpu_post_transition(vcpu);
-	r = 0;
-out:
-	return r;
-}
-
-static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
-{
-	int r;
+	/*
+	 * down_read() may sleep and return with interrupts enabled
+	 */
+	down_read(&vcpu->kvm->slots_lock);
 
 again:
 	if (signal_pending(current)) {
@@ -616,26 +661,31 @@ again:
 		goto out;
 	}
 
-	/*
-	 * down_read() may sleep and return with interrupts enabled
-	 */
-	down_read(&vcpu->kvm->slots_lock);
-
 	preempt_disable();
 	local_irq_disable();
 
-	vcpu->guest_mode = 1;
+	/*Get host and guest context with guest address space.*/
+	host_ctx = kvm_get_host_context(vcpu);
+	guest_ctx = kvm_get_guest_context(vcpu);
+
+	clear_bit(KVM_REQ_KICK, &vcpu->requests);
+
+	r = kvm_vcpu_pre_transition(vcpu);
+	if (r < 0)
+		goto vcpu_run_fail;
+
+	up_read(&vcpu->kvm->slots_lock);
 	kvm_guest_enter();
-	r = vti_vcpu_run(vcpu, kvm_run);
-	if (r < 0) {
-		local_irq_enable();
-		preempt_enable();
-		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
-		goto out;
-	}
+
+	/*
+	 * Transition to the guest
+	 */
+	kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
+
+	kvm_vcpu_post_transition(vcpu);
 
 	vcpu->arch.launched = 1;
-	vcpu->guest_mode = 0;
+	set_bit(KVM_REQ_KICK, &vcpu->requests);
 	local_irq_enable();
 
 	/*
@@ -646,9 +696,10 @@ again:
 	 */
 	barrier();
 	kvm_guest_exit();
-	up_read(&vcpu->kvm->slots_lock);
 	preempt_enable();
 
+	down_read(&vcpu->kvm->slots_lock);
+
 	r = kvm_handle_exit(kvm_run, vcpu);
 
 	if (r > 0) {
@@ -657,12 +708,20 @@ again:
 	}
 
 out:
+	up_read(&vcpu->kvm->slots_lock);
 	if (r > 0) {
 		kvm_resched(vcpu);
+		down_read(&vcpu->kvm->slots_lock);
 		goto again;
 	}
 
 	return r;
+
+vcpu_run_fail:
+	local_irq_enable();
+	preempt_enable();
+	kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+	goto out;
 }
 
 static void kvm_set_mmio_data(struct kvm_vcpu *vcpu)
@@ -788,6 +847,9 @@ struct  kvm *kvm_arch_create_vm(void)
 
 	if (IS_ERR(kvm))
 		return ERR_PTR(-ENOMEM);
+
+	kvm->arch.is_sn2 = ia64_platform_is("sn2");
+
 	kvm_init_vm(kvm);
 
 	kvm->arch.online_vcpus = 0;
@@ -884,7 +946,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	RESTORE_REGS(saved_gp);
 
 	vcpu->arch.irq_new_pending = 1;
-	vcpu->arch.itc_offset = regs->saved_itc - ia64_getreg(_IA64_REG_AR_ITC);
+	vcpu->arch.itc_offset = regs->saved_itc - kvm_get_itc(vcpu);
 	set_bit(KVM_REQ_RESUME, &vcpu->requests);
 
 	vcpu_put(vcpu);
@@ -1043,10 +1105,6 @@ static void kvm_free_vmm_area(void)
 	}
 }
 
-static void vti_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
-{
-}
-
 static int vti_init_vpd(struct kvm_vcpu *vcpu)
 {
 	int i;
@@ -1165,7 +1223,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		regs->cr_iip = PALE_RESET_ENTRY;
 
 		/*Initialize itc offset for vcpus*/
-		itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC);
+		itc_offset = 0UL - kvm_get_itc(vcpu);
 		for (i = 0; i < kvm->arch.online_vcpus; i++) {
 			v = (struct kvm_vcpu *)((char *)vcpu +
 					sizeof(struct kvm_vcpu_data) * i);
@@ -1237,6 +1295,7 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
 
 	local_irq_save(psr);
 	r = kvm_insert_vmm_mapping(vcpu);
+	local_irq_restore(psr);
 	if (r)
 		goto fail;
 	r = kvm_vcpu_init(vcpu, vcpu->kvm, id);
@@ -1254,13 +1313,11 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
 		goto uninit;
 
 	kvm_purge_vmm_mapping(vcpu);
-	local_irq_restore(psr);
 
 	return 0;
 uninit:
 	kvm_vcpu_uninit(vcpu);
 fail:
-	local_irq_restore(psr);
 	return r;
 }
 
@@ -1291,7 +1348,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->kvm = kvm;
 
 	cpu = get_cpu();
-	vti_vcpu_load(vcpu, cpu);
 	r = vti_vcpu_setup(vcpu, id);
 	put_cpu();
 
@@ -1427,7 +1483,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	}
 	for (i = 0; i < 4; i++)
 		regs->insvc[i] = vcpu->arch.insvc[i];
-	regs->saved_itc = vcpu->arch.itc_offset + ia64_getreg(_IA64_REG_AR_ITC);
+	regs->saved_itc = vcpu->arch.itc_offset + kvm_get_itc(vcpu);
 	SAVE_REGS(xtp);
 	SAVE_REGS(metaphysical_rr0);
 	SAVE_REGS(metaphysical_rr4);
@@ -1574,6 +1630,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 
 void kvm_arch_flush_shadow(struct kvm *kvm)
 {
+	kvm_flush_remote_tlbs(kvm);
 }
 
 long kvm_arch_dev_ioctl(struct file *filp,
@@ -1616,8 +1673,37 @@ out:
 	return 0;
 }
 
+
+/*
+ * On SN2, the ITC isn't stable, so copy in fast path code to use the
+ * SN2 RTC, replacing the ITC based default verion.
+ */
+static void kvm_patch_vmm(struct kvm_vmm_info *vmm_info,
+			  struct module *module)
+{
+	unsigned long new_ar, new_ar_sn2;
+	unsigned long module_base;
+
+	if (!ia64_platform_is("sn2"))
+		return;
+
+	module_base = (unsigned long)module->module_core;
+
+	new_ar = kvm_vmm_base + vmm_info->patch_mov_ar - module_base;
+	new_ar_sn2 = kvm_vmm_base + vmm_info->patch_mov_ar_sn2 - module_base;
+
+	printk(KERN_INFO "kvm: Patching ITC emulation to use SGI SN2 RTC "
+	       "as source\n");
+
+	/*
+	 * Copy the SN2 version of mov_ar into place. They are both
+	 * the same size, so 6 bundles is sufficient (6 * 0x10).
+	 */
+	memcpy((void *)new_ar, (void *)new_ar_sn2, 0x60);
+}
+
 static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
-						struct module *module)
+			    struct module *module)
 {
 	unsigned long module_base;
 	unsigned long vmm_size;
@@ -1639,6 +1725,7 @@ static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
 		return -EFAULT;
 
 	memcpy((void *)kvm_vmm_base, (void *)module_base, vmm_size);
+	kvm_patch_vmm(vmm_info, module);
 	kvm_flush_icache(kvm_vmm_base, vmm_size);
 
 	/*Recalculate kvm_vmm_info based on new VMM*/
@@ -1792,38 +1879,24 @@ void kvm_arch_hardware_unsetup(void)
 {
 }
 
-static void vcpu_kick_intr(void *info)
-{
-#ifdef DEBUG
-	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info;
-	printk(KERN_DEBUG"vcpu_kick_intr %p \n", vcpu);
-#endif
-}
-
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 {
-	int ipi_pcpu = vcpu->cpu;
-	int cpu = get_cpu();
+	int me;
+	int cpu = vcpu->cpu;
 
 	if (waitqueue_active(&vcpu->wq))
 		wake_up_interruptible(&vcpu->wq);
 
-	if (vcpu->guest_mode && cpu != ipi_pcpu)
-		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0);
+	me = get_cpu();
+	if (cpu != me && (unsigned) cpu < nr_cpu_ids && cpu_online(cpu))
+		if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests))
+			smp_send_reschedule(cpu);
 	put_cpu();
 }
 
-int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig)
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
 {
-
-	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
-
-	if (!test_and_set_bit(vec, &vpd->irr[0])) {
-		vcpu->arch.irq_new_pending = 1;
-		kvm_vcpu_kick(vcpu);
-		return 1;
-	}
-	return 0;
+	return __apic_accept_irq(vcpu, irq->vector);
 }
 
 int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
@@ -1836,20 +1909,18 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
 	return 0;
 }
 
-struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
-				       unsigned long bitmap)
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 {
-	struct kvm_vcpu *lvcpu = kvm->vcpus[0];
-	int i;
+	return vcpu1->arch.xtp - vcpu2->arch.xtp;
+}
 
-	for (i = 1; i < kvm->arch.online_vcpus; i++) {
-		if (!kvm->vcpus[i])
-			continue;
-		if (lvcpu->arch.xtp > kvm->vcpus[i]->arch.xtp)
-			lvcpu = kvm->vcpus[i];
-	}
-
-	return lvcpu;
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+		int short_hand, int dest, int dest_mode)
+{
+	struct kvm_lapic *target = vcpu->arch.apic;
+	return (dest_mode == 0) ?
+		kvm_apic_match_physical_addr(target, dest) :
+		kvm_apic_match_logical_addr(target, dest);
 }
 
 static int find_highest_bits(int *dat)
@@ -1888,6 +1959,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
+{
+	/* do real check here */
+	return 1;
+}
+
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.timer_fired;
@@ -1918,6 +1995,7 @@ static int vcpu_reset(struct kvm_vcpu *vcpu)
 	long psr;
 	local_irq_save(psr);
 	r = kvm_insert_vmm_mapping(vcpu);
+	local_irq_restore(psr);
 	if (r)
 		goto fail;
 
@@ -1930,7 +2008,6 @@ static int vcpu_reset(struct kvm_vcpu *vcpu)
 	kvm_purge_vmm_mapping(vcpu);
 	r = 0;
 fail:
-	local_irq_restore(psr);
 	return r;
 }
 
diff --git a/arch/ia64/kvm/kvm_fw.c b/arch/ia64/kvm/kvm_fw.c
index a8ae52ed5635..e4b82319881d 100644
--- a/arch/ia64/kvm/kvm_fw.c
+++ b/arch/ia64/kvm/kvm_fw.c
@@ -21,6 +21,9 @@
 
 #include <linux/kvm_host.h>
 #include <linux/smp.h>
+#include <asm/sn/addrs.h>
+#include <asm/sn/clksupport.h>
+#include <asm/sn/shub_mmr.h>
 
 #include "vti.h"
 #include "misc.h"
@@ -188,12 +191,35 @@ static struct ia64_pal_retval pal_freq_base(struct kvm_vcpu *vcpu)
 	return result;
 }
 
+/*
+ * On the SGI SN2, the ITC isn't stable. Emulation backed by the SN2
+ * RTC is used instead. This function patches the ratios from SAL
+ * to match the RTC before providing them to the guest.
+ */
+static void sn2_patch_itc_freq_ratios(struct ia64_pal_retval *result)
+{
+	struct pal_freq_ratio *ratio;
+	unsigned long sal_freq, sal_drift, factor;
+
+	result->status = ia64_sal_freq_base(SAL_FREQ_BASE_PLATFORM,
+					    &sal_freq, &sal_drift);
+	ratio = (struct pal_freq_ratio *)&result->v2;
+	factor = ((sal_freq * 3) + (sn_rtc_cycles_per_second / 2)) /
+		sn_rtc_cycles_per_second;
+
+	ratio->num = 3;
+	ratio->den = factor;
+}
+
 static struct ia64_pal_retval pal_freq_ratios(struct kvm_vcpu *vcpu)
 {
-
 	struct ia64_pal_retval result;
 
 	PAL_CALL(result, PAL_FREQ_RATIOS, 0, 0, 0);
+
+	if (vcpu->kvm->arch.is_sn2)
+		sn2_patch_itc_freq_ratios(&result);
+
 	return result;
 }
 
diff --git a/arch/ia64/kvm/lapic.h b/arch/ia64/kvm/lapic.h
index 6d6cbcb14893..ee541cebcd78 100644
--- a/arch/ia64/kvm/lapic.h
+++ b/arch/ia64/kvm/lapic.h
@@ -20,6 +20,10 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu);
 
 int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
 int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
-int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig);
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+		int short_hand, int dest, int dest_mode);
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq);
+#define kvm_apic_present(x) (true)
 
 #endif
diff --git a/arch/ia64/kvm/optvfault.S b/arch/ia64/kvm/optvfault.S
index 32254ce9a1bd..f793be3effff 100644
--- a/arch/ia64/kvm/optvfault.S
+++ b/arch/ia64/kvm/optvfault.S
@@ -11,6 +11,7 @@
 
 #include <asm/asmmacro.h>
 #include <asm/processor.h>
+#include <asm/kvm_host.h>
 
 #include "vti.h"
 #include "asm-offsets.h"
@@ -140,6 +141,35 @@ GLOBAL_ENTRY(kvm_asm_mov_from_ar)
 	;;
 END(kvm_asm_mov_from_ar)
 
+/*
+ * Special SGI SN2 optimized version of mov_from_ar using the SN2 RTC
+ * clock as it's source for emulating the ITC. This version will be
+ * copied on top of the original version if the host is determined to
+ * be an SN2.
+ */
+GLOBAL_ENTRY(kvm_asm_mov_from_ar_sn2)
+	add r18=VMM_VCPU_ITC_OFS_OFFSET, r21
+	movl r19 = (KVM_VMM_BASE+(1<<KVM_VMM_SHIFT))
+
+	add r16=VMM_VCPU_LAST_ITC_OFFSET,r21
+	extr.u r17=r25,6,7
+	mov r24=b0
+	;;
+	ld8 r18=[r18]
+	ld8 r19=[r19]
+	addl r20=@gprel(asm_mov_to_reg),gp
+	;;
+	add r19=r19,r18
+	shladd r17=r17,4,r20
+	;;
+	adds r30=kvm_resume_to_guest-asm_mov_to_reg,r20
+	st8 [r16] = r19
+	mov b0=r17
+	br.sptk.few b0
+	;;
+END(kvm_asm_mov_from_ar_sn2)
+
+
 
 // mov r1=rr[r3]
 GLOBAL_ENTRY(kvm_asm_mov_from_rr)
diff --git a/arch/ia64/kvm/process.c b/arch/ia64/kvm/process.c
index b1dc80952d91..a8f84da04b49 100644
--- a/arch/ia64/kvm/process.c
+++ b/arch/ia64/kvm/process.c
@@ -652,20 +652,25 @@ void  kvm_ia64_handle_break(unsigned long ifa, struct kvm_pt_regs *regs,
 		unsigned long isr, unsigned long iim)
 {
 	struct kvm_vcpu *v = current_vcpu;
+	long psr;
 
 	if (ia64_psr(regs)->cpl == 0) {
 		/* Allow hypercalls only when cpl = 0.  */
 		if (iim == DOMN_PAL_REQUEST) {
+			local_irq_save(psr);
 			set_pal_call_data(v);
 			vmm_transition(v);
 			get_pal_call_result(v);
 			vcpu_increment_iip(v);
+			local_irq_restore(psr);
 			return;
 		} else if (iim == DOMN_SAL_REQUEST) {
+			local_irq_save(psr);
 			set_sal_call_data(v);
 			vmm_transition(v);
 			get_sal_call_result(v);
 			vcpu_increment_iip(v);
+			local_irq_restore(psr);
 			return;
 		}
 	}
diff --git a/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c
index a18ee17b9192..a2c6c15e4761 100644
--- a/arch/ia64/kvm/vcpu.c
+++ b/arch/ia64/kvm/vcpu.c
@@ -788,13 +788,29 @@ void vcpu_set_fpreg(struct kvm_vcpu *vcpu, unsigned long reg,
 		setfpreg(reg, val, regs);   /* FIXME: handle NATs later*/
 }
 
+/*
+ * The Altix RTC is mapped specially here for the vmm module
+ */
+#define SN_RTC_BASE	(u64 *)(KVM_VMM_BASE+(1UL<<KVM_VMM_SHIFT))
+static long kvm_get_itc(struct kvm_vcpu *vcpu)
+{
+#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
+	struct kvm *kvm = (struct kvm *)KVM_VM_BASE;
+
+	if (kvm->arch.is_sn2)
+		return (*SN_RTC_BASE);
+	else
+#endif
+		return ia64_getreg(_IA64_REG_AR_ITC);
+}
+
 /************************************************************************
  * lsapic timer
  ***********************************************************************/
 u64 vcpu_get_itc(struct kvm_vcpu *vcpu)
 {
 	unsigned long guest_itc;
-	guest_itc = VMX(vcpu, itc_offset) + ia64_getreg(_IA64_REG_AR_ITC);
+	guest_itc = VMX(vcpu, itc_offset) + kvm_get_itc(vcpu);
 
 	if (guest_itc >= VMX(vcpu, last_itc)) {
 		VMX(vcpu, last_itc) = guest_itc;
@@ -809,7 +825,7 @@ static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val)
 	struct kvm_vcpu *v;
 	struct kvm *kvm;
 	int i;
-	long itc_offset = val - ia64_getreg(_IA64_REG_AR_ITC);
+	long itc_offset = val - kvm_get_itc(vcpu);
 	unsigned long vitv = VCPU(vcpu, itv);
 
 	kvm = (struct kvm *)KVM_VM_BASE;
diff --git a/arch/ia64/kvm/vmm.c b/arch/ia64/kvm/vmm.c
index 9eee5c04bacc..f4b4c899bb6c 100644
--- a/arch/ia64/kvm/vmm.c
+++ b/arch/ia64/kvm/vmm.c
@@ -30,15 +30,19 @@ MODULE_AUTHOR("Intel");
 MODULE_LICENSE("GPL");
 
 extern char kvm_ia64_ivt;
+extern char kvm_asm_mov_from_ar;
+extern char kvm_asm_mov_from_ar_sn2;
 extern fpswa_interface_t *vmm_fpswa_interface;
 
 long vmm_sanity = 1;
 
 struct kvm_vmm_info vmm_info = {
-	.module	     = THIS_MODULE,
-	.vmm_entry   = vmm_entry,
-	.tramp_entry = vmm_trampoline,
-	.vmm_ivt     = (unsigned long)&kvm_ia64_ivt,
+	.module			= THIS_MODULE,
+	.vmm_entry		= vmm_entry,
+	.tramp_entry		= vmm_trampoline,
+	.vmm_ivt		= (unsigned long)&kvm_ia64_ivt,
+	.patch_mov_ar		= (unsigned long)&kvm_asm_mov_from_ar,
+	.patch_mov_ar_sn2	= (unsigned long)&kvm_asm_mov_from_ar_sn2,
 };
 
 static int __init  kvm_vmm_init(void)
diff --git a/arch/ia64/kvm/vmm_ivt.S b/arch/ia64/kvm/vmm_ivt.S
index 3ef1a017a318..40920c630649 100644
--- a/arch/ia64/kvm/vmm_ivt.S
+++ b/arch/ia64/kvm/vmm_ivt.S
@@ -95,7 +95,7 @@ GLOBAL_ENTRY(kvm_vmm_panic)
 	;;
 	srlz.i    // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -249,7 +249,7 @@ ENTRY(kvm_break_fault)
 	;;
 	srlz.i         // guarantee that interruption collection is on
 	;;
-	//(p15)ssm psr.i               // restore psr.i
+	(p15)ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -439,7 +439,7 @@ kvm_dispatch_vexirq:
 	;;
 	srlz.i // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	adds r3=8,r2                // set up second base pointer
 	;;
 	KVM_SAVE_REST
@@ -819,7 +819,7 @@ ENTRY(kvm_dtlb_miss_dispatch)
 	;;
 	srlz.i     // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
 	;;
 	KVM_SAVE_REST
@@ -842,7 +842,7 @@ ENTRY(kvm_itlb_miss_dispatch)
 	;;
 	srlz.i   // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -871,7 +871,7 @@ ENTRY(kvm_dispatch_reflection)
 	;;
 	srlz.i   // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -898,7 +898,7 @@ ENTRY(kvm_dispatch_virtualization_fault)
 	;;
 	srlz.i    // guarantee that interruption collection is on
 	;;
-	//(p15) ssm psr.i               // restore psr.i
+	(p15) ssm psr.i               // restore psr.i
 	addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
 	;;
 	KVM_SAVE_REST
@@ -920,7 +920,7 @@ ENTRY(kvm_dispatch_interrupt)
 	;;
 	srlz.i
 	;;
-	//(p15) ssm psr.i
+	(p15) ssm psr.i
 	addl r14=@gprel(ia64_leave_hypervisor),gp
 	;;
 	KVM_SAVE_REST
@@ -1333,7 +1333,7 @@ hostret =   r24
 	;;
 (p7)    srlz.i
 	;;
-//(p6)    ssm psr.i
+(p6)    ssm psr.i
 	;;
 	mov rp=rpsave
 	mov ar.pfs=pfssave
diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
index 2c2501f13159..4290a429bf7c 100644
--- a/arch/ia64/kvm/vtlb.c
+++ b/arch/ia64/kvm/vtlb.c
@@ -254,7 +254,8 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte)
 			"(p7) st8 [%2]=r9;;"
 			"ssm psr.ic;;"
 			"srlz.d;;"
-			/* "ssm psr.i;;" Once interrupts in vmm open, need fix*/
+			"ssm psr.i;;"
+			"srlz.d;;"
 			: "=r"(ret) : "r"(iha), "r"(pte):"memory");
 
 	return ret;
diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c
index 66fd705e82c0..764f26abac05 100644
--- a/arch/ia64/sn/kernel/irq.c
+++ b/arch/ia64/sn/kernel/irq.c
@@ -227,7 +227,7 @@ finish_up:
 	return new_irq_info;
 }
 
-static void sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
+static int sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
 {
 	struct sn_irq_info *sn_irq_info, *sn_irq_info_safe;
 	nasid_t nasid;
@@ -239,6 +239,8 @@ static void sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
 	list_for_each_entry_safe(sn_irq_info, sn_irq_info_safe,
 				 sn_irq_lh[irq], list)
 		(void)sn_retarget_vector(sn_irq_info, nasid, slice);
+
+	return 0;
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index 81e428943d73..fbbfb9701201 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -151,7 +151,7 @@ int sn_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *entry)
 }
 
 #ifdef CONFIG_SMP
-static void sn_set_msi_irq_affinity(unsigned int irq,
+static int sn_set_msi_irq_affinity(unsigned int irq,
 				    const struct cpumask *cpu_mask)
 {
 	struct msi_msg msg;
@@ -168,7 +168,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
 	cpu = cpumask_first(cpu_mask);
 	sn_irq_info = sn_msi_info[irq].sn_irq_info;
 	if (sn_irq_info == NULL || sn_irq_info->irq_int_bit >= 0)
-		return;
+		return -1;
 
 	/*
 	 * Release XIO resources for the old MSI PCI address
@@ -189,7 +189,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
 	new_irq_info = sn_retarget_vector(sn_irq_info, nasid, slice);
 	sn_msi_info[irq].sn_irq_info = new_irq_info;
 	if (new_irq_info == NULL)
-		return;
+		return -1;
 
 	/*
 	 * Map the xio address into bus space
@@ -206,6 +206,8 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
 
 	write_msi_msg(irq, &msg);
 	cpumask_copy(irq_desc[irq].affinity, cpu_mask);
+
+	return 0;
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/m68k/include/asm/m520xsim.h b/arch/m68k/include/asm/m520xsim.h
index 49d016e6391a..83bbcfd6e8f2 100644
--- a/arch/m68k/include/asm/m520xsim.h
+++ b/arch/m68k/include/asm/m520xsim.h
@@ -59,5 +59,14 @@
 #define MCFPIT_IMR		MCFINTC_IMRL
 #define MCFPIT_IMR_IBIT		(1 << MCFINT_PIT1)
 
+/*
+ *  Reset Controll Unit.
+ */
+#define	MCF_RCR			0xFC0A0000
+#define	MCF_RSR			0xFC0A0001
+
+#define	MCF_RCR_SWRESET		0x80		/* Software reset bit */
+#define	MCF_RCR_FRCSTOUT	0x40		/* Force external reset */
+
 /****************************************************************************/
 #endif  /* m520xsim_h */
diff --git a/arch/m68k/include/asm/m523xsim.h b/arch/m68k/include/asm/m523xsim.h
index bf397313e93f..55183b5df1b8 100644
--- a/arch/m68k/include/asm/m523xsim.h
+++ b/arch/m68k/include/asm/m523xsim.h
@@ -41,5 +41,14 @@
 #define	MCFSIM_DACR1		0x50		/* SDRAM base address 1 */
 #define	MCFSIM_DMR1		0x54		/* SDRAM address mask 1 */
 
+/*
+ *  Reset Controll Unit (relative to IPSBAR).
+ */
+#define	MCF_RCR			0x110000
+#define	MCF_RSR			0x110001
+
+#define	MCF_RCR_SWRESET		0x80		/* Software reset bit */
+#define	MCF_RCR_FRCSTOUT	0x40		/* Force external reset */
+
 /****************************************************************************/
 #endif	/* m523xsim_h */
diff --git a/arch/m68k/include/asm/m527xsim.h b/arch/m68k/include/asm/m527xsim.h
index 1f63ab3fb3e6..95f4f8ee8f7c 100644
--- a/arch/m68k/include/asm/m527xsim.h
+++ b/arch/m68k/include/asm/m527xsim.h
@@ -70,5 +70,14 @@
 #define UART2_ENABLE_MASK	0x3f00 
 #endif
 
+/*
+ *  Reset Controll Unit (relative to IPSBAR).
+ */
+#define	MCF_RCR			0x110000
+#define	MCF_RSR			0x110001
+
+#define	MCF_RCR_SWRESET		0x80		/* Software reset bit */
+#define	MCF_RCR_FRCSTOUT	0x40		/* Force external reset */
+
 /****************************************************************************/
 #endif	/* m527xsim_h */
diff --git a/arch/m68k/include/asm/m528xsim.h b/arch/m68k/include/asm/m528xsim.h
index 28bf783a5d6d..d79c49f8134a 100644
--- a/arch/m68k/include/asm/m528xsim.h
+++ b/arch/m68k/include/asm/m528xsim.h
@@ -56,6 +56,14 @@
 #define MCF5282_INTC0_ICR17     (volatile u8 *) (MCF_IPSBAR + 0x0C51)
 
 
+/*
+ *  Reset Control Unit (relative to IPSBAR).
+ */
+#define	MCF_RCR			0x110000
+#define	MCF_RSR			0x110001
+
+#define	MCF_RCR_SWRESET		0x80		/* Software reset bit */
+#define	MCF_RCR_FRCSTOUT	0x40		/* Force external reset */
 
 /*********************************************************************
 *
diff --git a/arch/m68k/include/asm/m532xsim.h b/arch/m68k/include/asm/m532xsim.h
index ce603451b55e..eb7fd4448947 100644
--- a/arch/m68k/include/asm/m532xsim.h
+++ b/arch/m68k/include/asm/m532xsim.h
@@ -125,6 +125,18 @@
 #define	ACR_CM_OFF_IMP		(3<<5)
 #define	ACR_WPROTECT		(1<<2)
 
+/*********************************************************************
+ *
+ * Reset Controller Module
+ *
+ *********************************************************************/
+
+#define	MCF_RCR			0xFC0A0000
+#define	MCF_RSR			0xFC0A0001
+
+#define	MCF_RCR_SWRESET		0x80		/* Software reset bit */
+#define	MCF_RCR_FRCSTOUT	0x40		/* Force external reset */
+
 /*********************************************************************
  *
  * Inter-IC (I2C) Module
diff --git a/arch/m68k/include/asm/processor_no.h b/arch/m68k/include/asm/processor_no.h
index 91cba18acdd3..7a1e0ba35f5a 100644
--- a/arch/m68k/include/asm/processor_no.h
+++ b/arch/m68k/include/asm/processor_no.h
@@ -72,10 +72,10 @@ struct thread_struct {
 	unsigned char  fpstate[FPSTATESIZE];  /* floating point state */
 };
 
-#define INIT_THREAD  { \
-	sizeof(init_stack) + (unsigned long) init_stack, 0, \
-	PS_S, __KERNEL_DS, \
-	{0, 0}, 0, {0,}, {0, 0, 0}, {0,}, \
+#define INIT_THREAD  {							\
+	.ksp	= sizeof(init_stack) + (unsigned long) init_stack,	\
+	.sr	= PS_S,							\
+	.fs	= __KERNEL_DS,						\
 }
 
 /*
diff --git a/arch/m68k/include/asm/swab.h b/arch/m68k/include/asm/swab.h
index 9e3054ea59e9..5b754aace744 100644
--- a/arch/m68k/include/asm/swab.h
+++ b/arch/m68k/include/asm/swab.h
@@ -1,7 +1,7 @@
 #ifndef _M68K_SWAB_H
 #define _M68K_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/compiler.h>
 
 #define __SWAB_64_THRU_32__
diff --git a/arch/m68k/include/asm/system_no.h b/arch/m68k/include/asm/system_no.h
index 4496c0aa8379..3c0718d74398 100644
--- a/arch/m68k/include/asm/system_no.h
+++ b/arch/m68k/include/asm/system_no.h
@@ -203,113 +203,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 #include <asm-generic/cmpxchg.h>
 #endif
 
-#if defined( CONFIG_M68328 ) || defined( CONFIG_M68EZ328 ) || \
-	defined (CONFIG_M68360) || defined( CONFIG_M68VZ328 )
-#define HARD_RESET_NOW() ({		\
-        local_irq_disable();		\
-        asm("				\
-        moveal #0x10c00000, %a0;	\
-        moveb #0, 0xFFFFF300;		\
-        moveal 0(%a0), %sp;		\
-        moveal 4(%a0), %a0;		\
-        jmp (%a0);			\
-        ");				\
-})
-#endif
-
-#ifdef CONFIG_COLDFIRE
-#if defined(CONFIG_M5272) && defined(CONFIG_NETtel)
-/*
- * Need to account for broken early mask of 5272 silicon. So don't
- * jump through the original start address. Jump strait into the
- * known start of the FLASH code.
- */
-#define HARD_RESET_NOW() ({		\
-        asm("				\
-	movew #0x2700, %sr;		\
-        jmp 0xf0000400;			\
-        ");				\
-})
-#elif defined(CONFIG_NETtel) || \
-      defined(CONFIG_SECUREEDGEMP3) || defined(CONFIG_CLEOPATRA)
-#define HARD_RESET_NOW() ({		\
-        asm("				\
-	movew #0x2700, %sr;		\
-	moveal #0x10000044, %a0;	\
-	movel #0xffffffff, (%a0);	\
-	moveal #0x10000001, %a0;	\
-	moveb #0x00, (%a0);		\
-        moveal #0xf0000004, %a0;	\
-        moveal (%a0), %a0;		\
-        jmp (%a0);			\
-        ");				\
-})
-#elif defined(CONFIG_M5272)
-/*
- * Retrieve the boot address in flash using CSBR0 and CSOR0
- * find the reset vector at flash_address + 4 (e.g. 0x400)
- * remap it in the flash's current location (e.g. 0xf0000400)
- * and jump there.
- */ 
-#define HARD_RESET_NOW() ({		\
-	asm("				\
-	movew #0x2700, %%sr;		\
-	move.l	%0+0x40,%%d0;		\
-	and.l	%0+0x44,%%d0;		\
-	andi.l	#0xfffff000,%%d0;	\
-	mov.l	%%d0,%%a0;		\
-	or.l	4(%%a0),%%d0;		\
-	mov.l	%%d0,%%a0;		\
-	jmp (%%a0);"			\
-	: /* No output */		\
-	: "o" (*(char *)MCF_MBAR) );	\
-})
-#elif defined(CONFIG_M528x)
-/*
- * The MCF528x has a bit (SOFTRST) in memory (Reset Control Register RCR),
- * that when set, resets the MCF528x.
- */
-#define HARD_RESET_NOW() \
-({						\
-	unsigned char volatile *reset;		\
-	asm("move.w	#0x2700, %sr");		\
-	reset = ((volatile unsigned char *)(MCF_IPSBAR + 0x110000));	\
-	while(1)				\
-	*reset |= (0x01 << 7);\
-})
-#elif defined(CONFIG_M523x)
-#define HARD_RESET_NOW() ({		\
-	asm("				\
-	movew #0x2700, %sr;		\
-	movel #0x01000000, %sp;		\
-	moveal #0x40110000, %a0;	\
-	moveb #0x80, (%a0);		\
-	");				\
-})
-#elif defined(CONFIG_M520x)
-	/*
-	 * The MCF5208 has a bit (SOFTRST) in memory (Reset Control Register 
-	 * RCR), that when set, resets the MCF5208.
-	 */
-#define HARD_RESET_NOW() 		\
-({					\
-	unsigned char volatile *reset;	\
-	asm("move.w     #0x2700, %sr");	\
-	reset = ((volatile unsigned char *)(MCF_IPSBAR + 0xA0000));	\
-	while(1)			\
-		*reset |= 0x80;		\
-})
-#else
-#define HARD_RESET_NOW() ({		\
-        asm("				\
-	movew #0x2700, %sr;		\
-        moveal #0x4, %a0;		\
-        moveal (%a0), %a0;		\
-        jmp (%a0);			\
-        ");				\
-})
-#endif
-#endif
 #define arch_align_stack(x) (x)
 
 
diff --git a/arch/m68knommu/kernel/entry.S b/arch/m68knommu/kernel/entry.S
index f4782d2dce8f..f56faa5c9cd9 100644
--- a/arch/m68knommu/kernel/entry.S
+++ b/arch/m68knommu/kernel/entry.S
@@ -26,7 +26,6 @@
 
 #include <linux/sys.h>
 #include <linux/linkage.h>
-#include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/setup.h>
 #include <asm/segment.h>
diff --git a/arch/m68knommu/kernel/setup.c b/arch/m68knommu/kernel/setup.c
index 5985f1989021..5c2bb3eeaaa2 100644
--- a/arch/m68knommu/kernel/setup.c
+++ b/arch/m68knommu/kernel/setup.c
@@ -166,15 +166,13 @@ void __init setup_arch(char **cmdline_p)
 	printk(KERN_INFO "Motorola M5235EVB support (C)2005 Syn-tech Systems, Inc. (Jate Sujjavanich)\n");
 #endif
 
-#ifdef DEBUG
-	printk(KERN_DEBUG "KERNEL -> TEXT=0x%06x-0x%06x DATA=0x%06x-0x%06x "
-		"BSS=0x%06x-0x%06x\n", (int) &_stext, (int) &_etext,
-		(int) &_sdata, (int) &_edata,
-		(int) &_sbss, (int) &_ebss);
-	printk(KERN_DEBUG "MEMORY -> ROMFS=0x%06x-0x%06x MEM=0x%06x-0x%06x\n ",
-		(int) &_ebss, (int) memory_start,
-		(int) memory_start, (int) memory_end);
-#endif
+	pr_debug("KERNEL -> TEXT=0x%06x-0x%06x DATA=0x%06x-0x%06x "
+		 "BSS=0x%06x-0x%06x\n", (int) &_stext, (int) &_etext,
+		 (int) &_sdata, (int) &_edata,
+		 (int) &_sbss, (int) &_ebss);
+	pr_debug("MEMORY -> ROMFS=0x%06x-0x%06x MEM=0x%06x-0x%06x\n ",
+		 (int) &_ebss, (int) memory_start,
+		 (int) memory_start, (int) memory_end);
 
 	/* Keep a copy of command line */
 	*cmdline_p = &command_line[0];
diff --git a/arch/m68knommu/mm/init.c b/arch/m68knommu/mm/init.c
index 7befc0c357e0..b1703c67a4f1 100644
--- a/arch/m68knommu/mm/init.c
+++ b/arch/m68knommu/mm/init.c
@@ -126,9 +126,7 @@ void __init mem_init(void)
 	unsigned long start_mem = memory_start; /* DAVIDM - these must start at end of kernel */
 	unsigned long end_mem   = memory_end; /* DAVIDM - this must not include kernel stack at top */
 
-#ifdef DEBUG
-	printk(KERN_DEBUG "Mem_init: start=%lx, end=%lx\n", start_mem, end_mem);
-#endif
+	pr_debug("Mem_init: start=%lx, end=%lx\n", start_mem, end_mem);
 
 	end_mem &= PAGE_MASK;
 	high_memory = (void *) end_mem;
diff --git a/arch/m68knommu/platform/5206/config.c b/arch/m68knommu/platform/5206/config.c
index 53a5920c2b71..f6f79874e9af 100644
--- a/arch/m68knommu/platform/5206/config.c
+++ b/arch/m68knommu/platform/5206/config.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
@@ -21,10 +20,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
-/***************************************************************************/
-
 static struct mcf_platform_uart m5206_uart_platform[] = {
 	{
 		.mapbase	= MCF_MBAR + MCFUART_BASE1,
@@ -109,10 +104,21 @@ void mcf_settimericr(unsigned int timer, unsigned int level)
 
 /***************************************************************************/
 
+void m5206_cpu_reset(void)
+{
+	local_irq_disable();
+	/* Set watchdog to soft reset, and enabled */
+	__raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR);
+	for (;;)
+		/* wait for watchdog to timeout */;
+}
+
+/***************************************************************************/
+
 void __init config_BSP(char *commandp, int size)
 {
 	mcf_setimr(MCFSIM_IMR_MASKALL);
-	mach_reset = coldfire_reset;
+	mach_reset = m5206_cpu_reset;
 }
 
 /***************************************************************************/
diff --git a/arch/m68knommu/platform/5206e/config.c b/arch/m68knommu/platform/5206e/config.c
index db902540bf2c..65887799db81 100644
--- a/arch/m68knommu/platform/5206e/config.c
+++ b/arch/m68knommu/platform/5206e/config.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
@@ -21,10 +20,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
-/***************************************************************************/
-
 static struct mcf_platform_uart m5206e_uart_platform[] = {
 	{
 		.mapbase	= MCF_MBAR + MCFUART_BASE1,
@@ -109,6 +104,17 @@ void mcf_settimericr(unsigned int timer, unsigned int level)
 
 /***************************************************************************/
 
+void m5206e_cpu_reset(void)
+{
+	local_irq_disable();
+	/* Set watchdog to soft reset, and enabled */
+	__raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR);
+	for (;;)
+		/* wait for watchdog to timeout */;
+}
+
+/***************************************************************************/
+
 void __init config_BSP(char *commandp, int size)
 {
 	mcf_setimr(MCFSIM_IMR_MASKALL);
@@ -119,7 +125,7 @@ void __init config_BSP(char *commandp, int size)
 	commandp[size-1] = 0;
 #endif /* CONFIG_NETtel */
 
-	mach_reset = coldfire_reset;
+	mach_reset = m5206e_cpu_reset;
 }
 
 /***************************************************************************/
diff --git a/arch/m68knommu/platform/520x/config.c b/arch/m68knommu/platform/520x/config.c
index 855fc6a79d72..1c43a8aec69b 100644
--- a/arch/m68knommu/platform/520x/config.c
+++ b/arch/m68knommu/platform/520x/config.c
@@ -14,7 +14,6 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
@@ -23,10 +22,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
-/***************************************************************************/
-
 static struct mcf_platform_uart m520x_uart_platform[] = {
 	{
 		.mapbase	= MCF_MBAR + MCFUART_BASE1,
@@ -169,9 +164,17 @@ void mcf_autovector(unsigned int vec)
 
 /***************************************************************************/
 
+static void m520x_cpu_reset(void)
+{
+	local_irq_disable();
+	__raw_writeb(MCF_RCR_SWRESET, MCF_RCR);
+}
+
+/***************************************************************************/
+
 void __init config_BSP(char *commandp, int size)
 {
-	mach_reset = coldfire_reset;
+	mach_reset = m520x_cpu_reset;
 	m520x_uarts_init();
 	m520x_fec_init();
 }
diff --git a/arch/m68knommu/platform/523x/config.c b/arch/m68knommu/platform/523x/config.c
index 74133f27b30c..961fefebca14 100644
--- a/arch/m68knommu/platform/523x/config.c
+++ b/arch/m68knommu/platform/523x/config.c
@@ -15,7 +15,6 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
@@ -24,10 +23,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
-/***************************************************************************/
-
 static struct mcf_platform_uart m523x_uart_platform[] = {
 	{
 		.mapbase	= MCF_MBAR + MCFUART_BASE1,
@@ -145,13 +140,20 @@ void mcf_autovector(unsigned int vec)
 {
 	/* Everything is auto-vectored on the 523x */
 }
+/***************************************************************************/
+
+static void m523x_cpu_reset(void)
+{
+	local_irq_disable();
+	__raw_writeb(MCF_RCR_SWRESET, MCF_IPSBAR + MCF_RCR);
+}
 
 /***************************************************************************/
 
 void __init config_BSP(char *commandp, int size)
 {
 	mcf_disableall();
-	mach_reset = coldfire_reset;
+	mach_reset = m523x_cpu_reset;
 	m523x_uarts_init();
 	m523x_fec_init();
 }
diff --git a/arch/m68knommu/platform/5249/config.c b/arch/m68knommu/platform/5249/config.c
index 9eab19d01eb1..93d998825925 100644
--- a/arch/m68knommu/platform/5249/config.c
+++ b/arch/m68knommu/platform/5249/config.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
@@ -20,10 +19,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
-/***************************************************************************/
-
 static struct mcf_platform_uart m5249_uart_platform[] = {
 	{
 		.mapbase	= MCF_MBAR + MCFUART_BASE1,
@@ -106,10 +101,21 @@ void mcf_settimericr(unsigned int timer, unsigned int level)
 
 /***************************************************************************/
 
+void m5249_cpu_reset(void)
+{
+	local_irq_disable();
+	/* Set watchdog to soft reset, and enabled */
+	__raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR);
+	for (;;)
+		/* wait for watchdog to timeout */;
+}
+
+/***************************************************************************/
+
 void __init config_BSP(char *commandp, int size)
 {
 	mcf_setimr(MCFSIM_IMR_MASKALL);
-	mach_reset = coldfire_reset;
+	mach_reset = m5249_cpu_reset;
 }
 
 /***************************************************************************/
diff --git a/arch/m68knommu/platform/5272/config.c b/arch/m68knommu/platform/5272/config.c
index e049245f4092..5f95fcde05fd 100644
--- a/arch/m68knommu/platform/5272/config.c
+++ b/arch/m68knommu/platform/5272/config.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
@@ -21,8 +20,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
 extern unsigned int mcf_timervector;
 extern unsigned int mcf_profilevector;
 extern unsigned int mcf_timerlevel;
@@ -170,6 +167,19 @@ void mcf_settimericr(int timer, int level)
 
 /***************************************************************************/
 
+static void m5272_cpu_reset(void)
+{
+	local_irq_disable();
+	/* Set watchdog to reset, and enabled */
+	__raw_writew(0, MCF_MBAR + MCFSIM_WIRR);
+	__raw_writew(1, MCF_MBAR + MCFSIM_WRRR);
+	__raw_writew(0, MCF_MBAR + MCFSIM_WCR);
+	for (;;)
+		/* wait for watchdog to timeout */;
+}
+
+/***************************************************************************/
+
 void __init config_BSP(char *commandp, int size)
 {
 #if defined (CONFIG_MOD5272)
@@ -194,7 +204,7 @@ void __init config_BSP(char *commandp, int size)
 
 	mcf_timervector = 69;
 	mcf_profilevector = 70;
-	mach_reset = coldfire_reset;
+	mach_reset = m5272_cpu_reset;
 }
 
 /***************************************************************************/
diff --git a/arch/m68knommu/platform/527x/config.c b/arch/m68knommu/platform/527x/config.c
index 428b15922ef5..f746439cfd3e 100644
--- a/arch/m68knommu/platform/527x/config.c
+++ b/arch/m68knommu/platform/527x/config.c
@@ -15,7 +15,6 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
@@ -24,10 +23,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
-/***************************************************************************/
-
 static struct mcf_platform_uart m527x_uart_platform[] = {
 	{
 		.mapbase	= MCF_MBAR + MCFUART_BASE1,
@@ -227,10 +222,18 @@ void mcf_autovector(unsigned int vec)
 
 /***************************************************************************/
 
+static void m527x_cpu_reset(void)
+{
+	local_irq_disable();
+	__raw_writeb(MCF_RCR_SWRESET, MCF_IPSBAR + MCF_RCR);
+}
+
+/***************************************************************************/
+
 void __init config_BSP(char *commandp, int size)
 {
 	mcf_disableall();
-	mach_reset = coldfire_reset;
+	mach_reset = m527x_cpu_reset;
 	m527x_uarts_init();
 	m527x_fec_init();
 }
diff --git a/arch/m68knommu/platform/528x/config.c b/arch/m68knommu/platform/528x/config.c
index bee526f4d1af..a1d1a61c4fe6 100644
--- a/arch/m68knommu/platform/528x/config.c
+++ b/arch/m68knommu/platform/528x/config.c
@@ -31,10 +31,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
-/***************************************************************************/
-
 static struct mcf_platform_uart m528x_uart_platform[] = {
 	{
 		.mapbase	= MCF_MBAR + MCFUART_BASE1,
@@ -171,6 +167,14 @@ void mcf_autovector(unsigned int vec)
 
 /***************************************************************************/
 
+static void m528x_cpu_reset(void)
+{
+	local_irq_disable();
+	__raw_writeb(MCF_RCR_SWRESET, MCF_IPSBAR + MCF_RCR);
+}
+
+/***************************************************************************/
+
 #ifdef CONFIG_WILDFIRE
 void wildfire_halt(void)
 {
@@ -214,6 +218,7 @@ void __init config_BSP(char *commandp, int size)
 
 static int __init init_BSP(void)
 {
+	mach_reset = m528x_cpu_reset;
 	m528x_uarts_init();
 	m528x_fec_init();
 	platform_add_devices(m528x_devices, ARRAY_SIZE(m528x_devices));
diff --git a/arch/m68knommu/platform/5307/config.c b/arch/m68knommu/platform/5307/config.c
index 44803bf70a6e..39da9e9ff674 100644
--- a/arch/m68knommu/platform/5307/config.c
+++ b/arch/m68knommu/platform/5307/config.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
@@ -22,8 +21,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
 extern unsigned int mcf_timervector;
 extern unsigned int mcf_profilevector;
 extern unsigned int mcf_timerlevel;
@@ -119,6 +116,17 @@ void mcf_settimericr(unsigned int timer, unsigned int level)
 
 /***************************************************************************/
 
+void m5307_cpu_reset(void)
+{
+	local_irq_disable();
+	/* Set watchdog to soft reset, and enabled */
+	__raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR);
+	for (;;)
+		/* wait for watchdog to timeout */;
+}
+
+/***************************************************************************/
+
 void __init config_BSP(char *commandp, int size)
 {
 	mcf_setimr(MCFSIM_IMR_MASKALL);
@@ -134,7 +142,7 @@ void __init config_BSP(char *commandp, int size)
 	mcf_timerlevel = 6;
 #endif
 
-	mach_reset = coldfire_reset;
+	mach_reset = m5307_cpu_reset;
 
 #ifdef CONFIG_BDM_DISABLE
 	/*
diff --git a/arch/m68knommu/platform/532x/config.c b/arch/m68knommu/platform/532x/config.c
index 591f2f801134..cdb761971f7a 100644
--- a/arch/m68knommu/platform/532x/config.c
+++ b/arch/m68knommu/platform/532x/config.c
@@ -31,8 +31,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
 extern unsigned int mcf_timervector;
 extern unsigned int mcf_profilevector;
 extern unsigned int mcf_timerlevel;
@@ -164,6 +162,14 @@ void mcf_settimericr(unsigned int timer, unsigned int level)
 
 /***************************************************************************/
 
+static void m532x_cpu_reset(void)
+{
+	local_irq_disable();
+	__raw_writeb(MCF_RCR_SWRESET, MCF_RCR);
+}
+
+/***************************************************************************/
+
 void __init config_BSP(char *commandp, int size)
 {
 	mcf_setimr(MCFSIM_IMR_MASKALL);
@@ -181,7 +187,7 @@ void __init config_BSP(char *commandp, int size)
 
 	mcf_timervector = 64+32;
 	mcf_profilevector = 64+33;
-	mach_reset = coldfire_reset;
+	mach_reset = m532x_cpu_reset;
 
 #ifdef CONFIG_BDM_DISABLE
 	/*
diff --git a/arch/m68knommu/platform/5407/config.c b/arch/m68knommu/platform/5407/config.c
index 0ee8c1a200c8..b41d942bf8d0 100644
--- a/arch/m68knommu/platform/5407/config.c
+++ b/arch/m68knommu/platform/5407/config.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <asm/machdep.h>
 #include <asm/coldfire.h>
@@ -21,8 +20,6 @@
 
 /***************************************************************************/
 
-void coldfire_reset(void);
-
 extern unsigned int mcf_timervector;
 extern unsigned int mcf_profilevector;
 extern unsigned int mcf_timerlevel;
@@ -110,6 +107,17 @@ void mcf_settimericr(unsigned int timer, unsigned int level)
 
 /***************************************************************************/
 
+void m5407_cpu_reset(void)
+{
+	local_irq_disable();
+	/* set watchdog to soft reset, and enabled */
+	__raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR);
+	for (;;)
+		/* wait for watchdog to timeout */;
+}
+
+/***************************************************************************/
+
 void __init config_BSP(char *commandp, int size)
 {
 	mcf_setimr(MCFSIM_IMR_MASKALL);
@@ -121,7 +129,7 @@ void __init config_BSP(char *commandp, int size)
 	mcf_timerlevel = 6;
 #endif
 
-	mach_reset = coldfire_reset;
+	mach_reset = m5407_cpu_reset;
 }
 
 /***************************************************************************/
diff --git a/arch/m68knommu/platform/coldfire/vectors.c b/arch/m68knommu/platform/coldfire/vectors.c
index 6cf894620234..bdca0297fa9a 100644
--- a/arch/m68knommu/platform/coldfire/vectors.c
+++ b/arch/m68knommu/platform/coldfire/vectors.c
@@ -96,10 +96,3 @@ void ack_vector(unsigned int irq)
 }
 
 /***************************************************************************/
-
-void coldfire_reset(void)
-{
-	HARD_RESET_NOW();
-}
-
-/***************************************************************************/
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 1c19af8daa62..d3a0c8154bec 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -177,7 +177,7 @@ static void octeon_irq_ciu0_disable(unsigned int irq)
 }
 
 #ifdef CONFIG_SMP
-static void octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask *dest)
+static int octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask *dest)
 {
 	int cpu;
 	int bit = irq - OCTEON_IRQ_WORKQ0;	/* Bit 0-63 of EN0 */
@@ -199,6 +199,8 @@ static void octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask
 	 */
 	cvmx_read_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2));
 	write_unlock(&octeon_irq_ciu0_rwlock);
+
+	return 0;
 }
 #endif
 
@@ -292,7 +294,7 @@ static void octeon_irq_ciu1_disable(unsigned int irq)
 }
 
 #ifdef CONFIG_SMP
-static void octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask *dest)
+static int octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask *dest)
 {
 	int cpu;
 	int bit = irq - OCTEON_IRQ_WDOG0;	/* Bit 0-63 of EN1 */
@@ -315,6 +317,8 @@ static void octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask
 	 */
 	cvmx_read_csr(CVMX_CIU_INTX_EN1(cvmx_get_core_num() * 2 + 1));
 	write_unlock(&octeon_irq_ciu1_rwlock);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 3214ade02d10..4f1eed107b08 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -49,7 +49,7 @@ static inline void smtc_im_ack_irq(unsigned int irq)
 #ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
 #include <linux/cpumask.h>
 
-extern void plat_set_irq_affinity(unsigned int irq,
+extern int plat_set_irq_affinity(unsigned int irq,
 				  const struct cpumask *affinity);
 extern void smtc_forward_irq(unsigned int irq);
 
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index 87deb8f6c458..3f43c2e3aa5a 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -155,7 +155,7 @@ static void gic_unmask_irq(unsigned int irq)
 
 static DEFINE_SPINLOCK(gic_lock);
 
-static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
 	cpumask_t	tmp = CPU_MASK_NONE;
 	unsigned long	flags;
@@ -166,7 +166,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 
 	cpumask_and(&tmp, cpumask, cpu_online_mask);
 	if (cpus_empty(tmp))
-		return;
+		return -1;
 
 	/* Assumption : cpumask refers to a single CPU */
 	spin_lock_irqsave(&gic_lock, flags);
@@ -190,6 +190,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	cpumask_copy(irq_desc[irq].affinity, cpumask);
 	spin_unlock_irqrestore(&gic_lock, flags);
 
+	return 0;
 }
 #endif
 
diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c
index 5ba31888fefb..499ffe5475df 100644
--- a/arch/mips/mti-malta/malta-smtc.c
+++ b/arch/mips/mti-malta/malta-smtc.c
@@ -114,7 +114,7 @@ struct plat_smp_ops msmtc_smp_ops = {
  */
 
 
-void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
+int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 {
 	cpumask_t tmask;
 	int cpu = 0;
@@ -156,5 +156,7 @@ void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 
 	/* Do any generic SMTC IRQ affinity setup */
 	smtc_set_irq_affinity(irq, tmask);
+
+	return 0;
 }
 #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
diff --git a/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c
index c147c4b35d3f..690de06bde90 100644
--- a/arch/mips/sibyte/bcm1480/irq.c
+++ b/arch/mips/sibyte/bcm1480/irq.c
@@ -50,7 +50,7 @@ static void enable_bcm1480_irq(unsigned int irq);
 static void disable_bcm1480_irq(unsigned int irq);
 static void ack_bcm1480_irq(unsigned int irq);
 #ifdef CONFIG_SMP
-static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask);
+static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask);
 #endif
 
 #ifdef CONFIG_PCI
@@ -109,7 +109,7 @@ void bcm1480_unmask_irq(int cpu, int irq)
 }
 
 #ifdef CONFIG_SMP
-static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	int i = 0, old_cpu, cpu, int_on, k;
 	u64 cur_ints;
@@ -118,7 +118,7 @@ static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	if (cpumask_weight(mask) != 1) {
 		printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq);
-		return;
+		return -1;
 	}
 	i = cpumask_first(mask);
 
@@ -152,6 +152,8 @@ static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
 		}
 	}
 	spin_unlock_irqrestore(&bcm1480_imr_lock, flags);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/mips/sibyte/sb1250/irq.c b/arch/mips/sibyte/sb1250/irq.c
index 38cb998ade22..409dec798863 100644
--- a/arch/mips/sibyte/sb1250/irq.c
+++ b/arch/mips/sibyte/sb1250/irq.c
@@ -50,7 +50,7 @@ static void enable_sb1250_irq(unsigned int irq);
 static void disable_sb1250_irq(unsigned int irq);
 static void ack_sb1250_irq(unsigned int irq);
 #ifdef CONFIG_SMP
-static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask);
+static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask);
 #endif
 
 #ifdef CONFIG_SIBYTE_HAS_LDT
@@ -103,7 +103,7 @@ void sb1250_unmask_irq(int cpu, int irq)
 }
 
 #ifdef CONFIG_SMP
-static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	int i = 0, old_cpu, cpu, int_on;
 	u64 cur_ints;
@@ -113,7 +113,7 @@ static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	if (cpumask_weight(mask) > 1) {
 		printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq);
-		return;
+		return -1;
 	}
 
 	/* Convert logical CPU to physical CPU */
@@ -143,6 +143,8 @@ static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
 					R_IMR_INTERRUPT_MASK));
 	}
 	spin_unlock_irqrestore(&sb1250_imr_lock, flags);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 355926730e8d..89faacad5d17 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -8,6 +8,7 @@ mainmenu "Linux Kernel Configuration"
 config MN10300
 	def_bool y
 	select HAVE_OPROFILE
+	select HAVE_ARCH_TRACEHOOK
 
 config AM33
 	def_bool y
diff --git a/arch/mn10300/include/asm/elf.h b/arch/mn10300/include/asm/elf.h
index bf09f8bb392e..49105462e6fc 100644
--- a/arch/mn10300/include/asm/elf.h
+++ b/arch/mn10300/include/asm/elf.h
@@ -34,7 +34,7 @@
  */
 typedef unsigned long elf_greg_t;
 
-#define ELF_NGREG (sizeof (struct pt_regs) / sizeof(elf_greg_t))
+#define ELF_NGREG ((sizeof(struct pt_regs) / sizeof(elf_greg_t)) - 1)
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
 #define ELF_NFPREG 32
@@ -76,6 +76,7 @@ do {									\
 } while (0)
 
 #define USE_ELF_CORE_DUMP
+#define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	4096
 
 /*
diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h
index 73239271873d..f7d4b0d285e8 100644
--- a/arch/mn10300/include/asm/processor.h
+++ b/arch/mn10300/include/asm/processor.h
@@ -143,13 +143,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 
 unsigned long get_wchan(struct task_struct *p);
 
-#define task_pt_regs(task)						\
-({									\
-       struct pt_regs *__regs__;					\
-       __regs__ = (struct pt_regs *) (KSTK_TOP(task_stack_page(task)) - 8); \
-       __regs__ - 1;							\
-})
-
+#define task_pt_regs(task) ((task)->thread.uregs)
 #define KSTK_EIP(task) (task_pt_regs(task)->pc)
 #define KSTK_ESP(task) (task_pt_regs(task)->sp)
 
diff --git a/arch/mn10300/include/asm/ptrace.h b/arch/mn10300/include/asm/ptrace.h
index 7b06cc623d8b..921942ed1b03 100644
--- a/arch/mn10300/include/asm/ptrace.h
+++ b/arch/mn10300/include/asm/ptrace.h
@@ -91,9 +91,17 @@ extern struct pt_regs *__frame; /* current frame pointer */
 #if defined(__KERNEL__)
 
 #if !defined(__ASSEMBLY__)
+struct task_struct;
+
 #define user_mode(regs)			(((regs)->epsw & EPSW_nSL) == EPSW_nSL)
 #define instruction_pointer(regs)	((regs)->pc)
+#define user_stack_pointer(regs)	((regs)->sp)
 extern void show_regs(struct pt_regs *);
+
+#define arch_has_single_step()	(1)
+extern void user_enable_single_step(struct task_struct *);
+extern void user_disable_single_step(struct task_struct *);
+
 #endif  /*  !__ASSEMBLY  */
 
 #define profile_pc(regs) ((regs)->pc)
diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S
index 3dc3e462f92a..7408a27199f3 100644
--- a/arch/mn10300/kernel/entry.S
+++ b/arch/mn10300/kernel/entry.S
@@ -76,7 +76,7 @@ ENTRY(system_call)
 	cmp	nr_syscalls,d0
 	bcc	syscall_badsys
 	btst	_TIF_SYSCALL_TRACE,(TI_flags,a2)
-	bne	syscall_trace_entry
+	bne	syscall_entry_trace
 syscall_call:
 	add	d0,d0,a1
 	add	a1,a1
@@ -104,11 +104,10 @@ restore_all:
 syscall_exit_work:
 	btst	_TIF_SYSCALL_TRACE,d2
 	beq	work_pending
-	__sti				# could let do_syscall_trace() call
+	__sti				# could let syscall_trace_exit() call
 					# schedule() instead
 	mov	fp,d0
-	mov	1,d1
-	call	do_syscall_trace[],0	# do_syscall_trace(regs,entryexit)
+	call	syscall_trace_exit[],0	# do_syscall_trace(regs)
 	jmp	resume_userspace
 
 	ALIGN
@@ -138,13 +137,11 @@ work_notifysig:
 	jmp	resume_userspace
 
 	# perform syscall entry tracing
-syscall_trace_entry:
+syscall_entry_trace:
 	mov	-ENOSYS,d0
 	mov	d0,(REG_D0,fp)
 	mov	fp,d0
-	clr	d1
-	call	do_syscall_trace[],0
-	mov	(REG_ORIG_D0,fp),d0
+	call	syscall_trace_entry[],0	# returns the syscall number to actually use
 	mov	(REG_D1,fp),d1
 	cmp	nr_syscalls,d0
 	bcs	syscall_call
diff --git a/arch/mn10300/kernel/ptrace.c b/arch/mn10300/kernel/ptrace.c
index d6d6cdc75c52..e143339ad28e 100644
--- a/arch/mn10300/kernel/ptrace.c
+++ b/arch/mn10300/kernel/ptrace.c
@@ -17,6 +17,9 @@
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
+#include <linux/regset.h>
+#include <linux/elf.h>
+#include <linux/tracehook.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/system.h>
@@ -64,12 +67,6 @@ static inline int get_stack_long(struct task_struct *task, int offset)
 		((unsigned long) task->thread.uregs + offset);
 }
 
-/*
- * this routine will put a word on the processes privileged stack.
- * the offset is how far from the base addr as stored in the TSS.
- * this routine assumes that all the privileged stacks are in our
- * data space.
- */
 static inline
 int put_stack_long(struct task_struct *task, int offset, unsigned long data)
 {
@@ -80,44 +77,191 @@ int put_stack_long(struct task_struct *task, int offset, unsigned long data)
 	return 0;
 }
 
-static inline unsigned long get_fpregs(struct fpu_state_struct *buf,
-				       struct task_struct *tsk)
+/*
+ * retrieve the contents of MN10300 userspace general registers
+ */
+static int genregs_get(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       void *kbuf, void __user *ubuf)
 {
-	return __copy_to_user(buf, &tsk->thread.fpu_state,
-			      sizeof(struct fpu_state_struct));
-}
+	const struct pt_regs *regs = task_pt_regs(target);
+	int ret;
 
-static inline unsigned long set_fpregs(struct task_struct *tsk,
-				       struct fpu_state_struct *buf)
-{
-	return __copy_from_user(&tsk->thread.fpu_state, buf,
-				sizeof(struct fpu_state_struct));
-}
+	/* we need to skip regs->next */
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  regs, 0, PT_ORIG_D0 * sizeof(long));
+	if (ret < 0)
+		return ret;
 
-static inline void fpsave_init(struct task_struct *task)
-{
-	memset(&task->thread.fpu_state, 0, sizeof(struct fpu_state_struct));
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &regs->orig_d0, PT_ORIG_D0 * sizeof(long),
+				  NR_PTREGS * sizeof(long));
+	if (ret < 0)
+		return ret;
+
+	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					NR_PTREGS * sizeof(long), -1);
 }
 
 /*
- * make sure the single step bit is not set
+ * update the contents of the MN10300 userspace general registers
  */
-void ptrace_disable(struct task_struct *child)
+static int genregs_set(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       const void *kbuf, const void __user *ubuf)
 {
-#ifndef CONFIG_MN10300_USING_JTAG
-	struct user *dummy = NULL;
-	long tmp;
+	struct pt_regs *regs = task_pt_regs(target);
+	unsigned long tmp;
+	int ret;
 
-	tmp = get_stack_long(child, (unsigned long) &dummy->regs.epsw);
-	tmp &= ~EPSW_T;
-	put_stack_long(child, (unsigned long) &dummy->regs.epsw, tmp);
-#endif
+	/* we need to skip regs->next */
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 regs, 0, PT_ORIG_D0 * sizeof(long));
+	if (ret < 0)
+		return ret;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->orig_d0, PT_ORIG_D0 * sizeof(long),
+				 PT_EPSW * sizeof(long));
+	if (ret < 0)
+		return ret;
+
+	/* we need to mask off changes to EPSW */
+	tmp = regs->epsw;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &tmp, PT_EPSW * sizeof(long),
+				 PT_PC * sizeof(long));
+	tmp &= EPSW_FLAG_V | EPSW_FLAG_C | EPSW_FLAG_N | EPSW_FLAG_Z;
+	tmp |= regs->epsw & ~(EPSW_FLAG_V | EPSW_FLAG_C | EPSW_FLAG_N |
+			      EPSW_FLAG_Z);
+	regs->epsw = tmp;
+
+	if (ret < 0)
+		return ret;
+
+	/* and finally load the PC */
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->pc, PT_PC * sizeof(long),
+				 NR_PTREGS * sizeof(long));
+
+	if (ret < 0)
+		return ret;
+
+	return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+					 NR_PTREGS * sizeof(long), -1);
 }
 
 /*
- * set the single step bit
+ * retrieve the contents of MN10300 userspace FPU registers
  */
-void ptrace_enable(struct task_struct *child)
+static int fpuregs_get(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       void *kbuf, void __user *ubuf)
+{
+	const struct fpu_state_struct *fpregs = &target->thread.fpu_state;
+	int ret;
+
+	unlazy_fpu(target);
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  fpregs, 0, sizeof(*fpregs));
+	if (ret < 0)
+		return ret;
+
+	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					sizeof(*fpregs), -1);
+}
+
+/*
+ * update the contents of the MN10300 userspace FPU registers
+ */
+static int fpuregs_set(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       const void *kbuf, const void __user *ubuf)
+{
+	struct fpu_state_struct fpu_state = target->thread.fpu_state;
+	int ret;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &fpu_state, 0, sizeof(fpu_state));
+	if (ret < 0)
+		return ret;
+
+	fpu_kill_state(target);
+	target->thread.fpu_state = fpu_state;
+	set_using_fpu(target);
+
+	return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+					 sizeof(fpu_state), -1);
+}
+
+/*
+ * determine if the FPU registers have actually been used
+ */
+static int fpuregs_active(struct task_struct *target,
+			  const struct user_regset *regset)
+{
+	return is_using_fpu(target) ? regset->n : 0;
+}
+
+/*
+ * Define the register sets available on the MN10300 under Linux
+ */
+enum mn10300_regset {
+	REGSET_GENERAL,
+	REGSET_FPU,
+};
+
+static const struct user_regset mn10300_regsets[] = {
+	/*
+	 * General register format is:
+	 *	A3, A2, D3, D2, MCVF, MCRL, MCRH, MDRQ
+	 *	E1, E0, E7...E2, SP, LAR, LIR, MDR
+	 *	A1, A0, D1, D0, ORIG_D0, EPSW, PC
+	 */
+	[REGSET_GENERAL] = {
+		.core_note_type	= NT_PRSTATUS,
+		.n		= ELF_NGREG,
+		.size		= sizeof(long),
+		.align		= sizeof(long),
+		.get		= genregs_get,
+		.set		= genregs_set,
+	},
+	/*
+	 * FPU register format is:
+	 *	FS0-31, FPCR
+	 */
+	[REGSET_FPU] = {
+		.core_note_type	= NT_PRFPREG,
+		.n		= sizeof(struct fpu_state_struct) / sizeof(long),
+		.size		= sizeof(long),
+		.align		= sizeof(long),
+		.get		= fpuregs_get,
+		.set		= fpuregs_set,
+		.active		= fpuregs_active,
+	},
+};
+
+static const struct user_regset_view user_mn10300_native_view = {
+	.name		= "mn10300",
+	.e_machine	= EM_MN10300,
+	.regsets	= mn10300_regsets,
+	.n		= ARRAY_SIZE(mn10300_regsets),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+	return &user_mn10300_native_view;
+}
+
+/*
+ * set the single-step bit
+ */
+void user_enable_single_step(struct task_struct *child)
 {
 #ifndef CONFIG_MN10300_USING_JTAG
 	struct user *dummy = NULL;
@@ -129,45 +273,37 @@ void ptrace_enable(struct task_struct *child)
 #endif
 }
 
+/*
+ * make sure the single-step bit is not set
+ */
+void user_disable_single_step(struct task_struct *child)
+{
+#ifndef CONFIG_MN10300_USING_JTAG
+	struct user *dummy = NULL;
+	long tmp;
+
+	tmp = get_stack_long(child, (unsigned long) &dummy->regs.epsw);
+	tmp &= ~EPSW_T;
+	put_stack_long(child, (unsigned long) &dummy->regs.epsw, tmp);
+#endif
+}
+
+void ptrace_disable(struct task_struct *child)
+{
+	user_disable_single_step(child);
+}
+
 /*
  * handle the arch-specific side of process tracing
  */
 long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 {
-	struct fpu_state_struct fpu_state;
-	int i, ret;
+	unsigned long tmp;
+	int ret;
 
 	switch (request) {
-	/* read the word at location addr. */
-	case PTRACE_PEEKTEXT: {
-		unsigned long tmp;
-		int copied;
-
-		copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
-		ret = -EIO;
-		if (copied != sizeof(tmp))
-			break;
-		ret = put_user(tmp, (unsigned long *) data);
-		break;
-	}
-
-	/* read the word at location addr. */
-	case PTRACE_PEEKDATA: {
-		unsigned long tmp;
-		int copied;
-
-		copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
-		ret = -EIO;
-		if (copied != sizeof(tmp))
-			break;
-		ret = put_user(tmp, (unsigned long *) data);
-		break;
-	}
-
 	/* read the word at location addr in the USER area. */
-	case PTRACE_PEEKUSR: {
-		unsigned long tmp;
-
+	case PTRACE_PEEKUSR:
 		ret = -EIO;
 		if ((addr & 3) || addr < 0 ||
 		    addr > sizeof(struct user) - 3)
@@ -179,17 +315,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 					     ptrace_regid_to_frame[addr]);
 		ret = put_user(tmp, (unsigned long *) data);
 		break;
-	}
-
-	/* write the word at location addr. */
-	case PTRACE_POKETEXT:
-	case PTRACE_POKEDATA:
-		if (access_process_vm(child, addr, &data, sizeof(data), 1) ==
-		    sizeof(data))
-			ret = 0;
-		else
-			ret = -EIO;
-		break;
 
 		/* write the word at location addr in the USER area */
 	case PTRACE_POKEUSR:
@@ -204,132 +329,32 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 					     data);
 		break;
 
-		/* continue and stop at next (return from) syscall */
-	case PTRACE_SYSCALL:
-		/* restart after signal. */
-	case PTRACE_CONT:
-		ret = -EIO;
-		if ((unsigned long) data > _NSIG)
-			break;
-		if (request == PTRACE_SYSCALL)
-			set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
-		else
-			clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
-		child->exit_code = data;
-		ptrace_disable(child);
-		wake_up_process(child);
-		ret = 0;
-		break;
+	case PTRACE_GETREGS:	/* Get all integer regs from the child. */
+		return copy_regset_to_user(child, &user_mn10300_native_view,
+					   REGSET_GENERAL,
+					   0, NR_PTREGS * sizeof(long),
+					   (void __user *)data);
 
-		/*
-		 * make the child exit
-		 * - the best I can do is send it a sigkill
-		 * - perhaps it should be put in the status that it wants to
-		 *   exit
-		 */
-	case PTRACE_KILL:
-		ret = 0;
-		if (child->exit_state == EXIT_ZOMBIE)	/* already dead */
-			break;
-		child->exit_code = SIGKILL;
-		clear_tsk_thread_flag(child, TIF_SINGLESTEP);
-		ptrace_disable(child);
-		wake_up_process(child);
-		break;
+	case PTRACE_SETREGS:	/* Set all integer regs in the child. */
+		return copy_regset_from_user(child, &user_mn10300_native_view,
+					     REGSET_GENERAL,
+					     0, NR_PTREGS * sizeof(long),
+					     (const void __user *)data);
 
-	case PTRACE_SINGLESTEP: /* set the trap flag. */
-#ifndef CONFIG_MN10300_USING_JTAG
-		ret = -EIO;
-		if ((unsigned long) data > _NSIG)
-			break;
-		clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
-		ptrace_enable(child);
-		child->exit_code = data;
-		wake_up_process(child);
-		ret = 0;
-#else
-		ret = -EINVAL;
-#endif
-		break;
+	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
+		return copy_regset_to_user(child, &user_mn10300_native_view,
+					   REGSET_FPU,
+					   0, sizeof(struct fpu_state_struct),
+					   (void __user *)data);
 
-	case PTRACE_DETACH:	/* detach a process that was attached. */
-		ret = ptrace_detach(child, data);
-		break;
-
-		/* Get all gp regs from the child. */
-	case PTRACE_GETREGS: {
-		unsigned long tmp;
-
-		if (!access_ok(VERIFY_WRITE, (unsigned *) data, NR_PTREGS << 2)) {
-			ret = -EIO;
-			break;
-		}
-
-		for (i = 0; i < NR_PTREGS << 2; i += 4) {
-			tmp = get_stack_long(child, ptrace_regid_to_frame[i]);
-			__put_user(tmp, (unsigned long *) data);
-			data += sizeof(tmp);
-		}
-		ret = 0;
-		break;
-	}
-
-	case PTRACE_SETREGS: { /* Set all gp regs in the child. */
-		unsigned long tmp;
-
-		if (!access_ok(VERIFY_READ, (unsigned long *)data,
-			       sizeof(struct pt_regs))) {
-			ret = -EIO;
-			break;
-		}
-
-		for (i = 0; i < NR_PTREGS << 2; i += 4) {
-			__get_user(tmp, (unsigned long *) data);
-			put_stack_long(child, ptrace_regid_to_frame[i], tmp);
-			data += sizeof(tmp);
-		}
-		ret = 0;
-		break;
-	}
-
-	case PTRACE_GETFPREGS: { /* Get the child FPU state. */
-		if (is_using_fpu(child)) {
-			unlazy_fpu(child);
-			fpu_state = child->thread.fpu_state;
-		} else {
-			memset(&fpu_state, 0, sizeof(fpu_state));
-		}
-
-		ret = -EIO;
-		if (copy_to_user((void *) data, &fpu_state,
-				 sizeof(fpu_state)) == 0)
-			ret = 0;
-		break;
-	}
-
-	case PTRACE_SETFPREGS: { /* Set the child FPU state. */
-		ret = -EFAULT;
-		if (copy_from_user(&fpu_state, (const void *) data,
-				   sizeof(fpu_state)) == 0) {
-			fpu_kill_state(child);
-			child->thread.fpu_state = fpu_state;
-			set_using_fpu(child);
-			ret = 0;
-		}
-		break;
-	}
-
-	case PTRACE_SETOPTIONS: {
-		if (data & PTRACE_O_TRACESYSGOOD)
-			child->ptrace |= PT_TRACESYSGOOD;
-		else
-			child->ptrace &= ~PT_TRACESYSGOOD;
-		ret = 0;
-		break;
-	}
+	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
+		return copy_regset_from_user(child, &user_mn10300_native_view,
+					     REGSET_FPU,
+					     0, sizeof(struct fpu_state_struct),
+					     (const void __user *)data);
 
 	default:
-		ret = -EIO;
+		ret = ptrace_request(child, request, addr, data);
 		break;
 	}
 
@@ -337,43 +362,26 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 }
 
 /*
- * notification of system call entry/exit
- * - triggered by current->work.syscall_trace
+ * handle tracing of system call entry
+ * - return the revised system call number or ULONG_MAX to cause ENOSYS
  */
-asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit)
+asmlinkage unsigned long syscall_trace_entry(struct pt_regs *regs)
 {
-#if 0
-	/* just in case... */
-	printk(KERN_DEBUG "[%d] syscall_%lu(%lx,%lx,%lx,%lx) = %lx\n",
-	       current->pid,
-	       regs->orig_d0,
-	       regs->a0,
-	       regs->d1,
-	       regs->a3,
-	       regs->a2,
-	       regs->d0);
-	return;
-#endif
+	if (tracehook_report_syscall_entry(regs))
+		/* tracing decided this syscall should not happen, so
+		 * We'll return a bogus call number to get an ENOSYS
+		 * error, but leave the original number in
+		 * regs->orig_d0
+		 */
+		return ULONG_MAX;
 
-	if (!test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    !test_thread_flag(TIF_SINGLESTEP))
-		return;
-	if (!(current->ptrace & PT_PTRACED))
-		return;
-
-	/* the 0x80 provides a way for the tracing parent to distinguish
-	   between a syscall stop and SIGTRAP delivery */
-	ptrace_notify(SIGTRAP |
-		      ((current->ptrace & PT_TRACESYSGOOD) &&
-		       !test_thread_flag(TIF_SINGLESTEP) ? 0x80 : 0));
-
-	/*
-	 * this isn't the same as continuing with a signal, but it will do
-	 * for normal use.  strace only continues with a signal if the
-	 * stopping signal is not SIGTRAP.  -brl
-	 */
-	if (current->exit_code) {
-		send_sig(current->exit_code, current, 1);
-		current->exit_code = 0;
-	}
+	return regs->orig_d0;
+}
+
+/*
+ * handle tracing of system call exit
+ */
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+	tracehook_report_syscall_exit(regs, 0);
 }
diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c
index 841ca9955a18..9f7572a0f578 100644
--- a/arch/mn10300/kernel/signal.c
+++ b/arch/mn10300/kernel/signal.c
@@ -23,6 +23,7 @@
 #include <linux/tty.h>
 #include <linux/personality.h>
 #include <linux/suspend.h>
+#include <linux/tracehook.h>
 #include <asm/cacheflush.h>
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
@@ -511,6 +512,9 @@ static void do_signal(struct pt_regs *regs)
 			 * clear the TIF_RESTORE_SIGMASK flag */
 			if (test_thread_flag(TIF_RESTORE_SIGMASK))
 				clear_thread_flag(TIF_RESTORE_SIGMASK);
+
+			tracehook_signal_handler(signr, &info, &ka, regs,
+						 test_thread_flag(TIF_SINGLESTEP));
 		}
 
 		return;
@@ -561,4 +565,9 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags)
 	/* deal with pending signal delivery */
 	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK))
 		do_signal(regs);
+
+	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+		clear_thread_flag(TIF_NOTIFY_RESUME);
+		tracehook_notify_resume(__frame);
+	}
 }
diff --git a/arch/mn10300/mm/tlb-mn10300.S b/arch/mn10300/mm/tlb-mn10300.S
index 789208094e98..7095147dcb8b 100644
--- a/arch/mn10300/mm/tlb-mn10300.S
+++ b/arch/mn10300/mm/tlb-mn10300.S
@@ -165,24 +165,6 @@ ENTRY(itlb_aerror)
 ENTRY(dtlb_aerror)
 	and	~EPSW_NMID,epsw
 	add	-4,sp
-	mov	d1,(sp)
-
-	movhu	(MMUFCR_DFC),d1			# is it the initial valid write
-						# to this page?
-	and	MMUFCR_xFC_INITWR,d1
- 	beq	dtlb_pagefault			# jump if not
-
-	mov	(DPTEL),d1			# set the dirty bit
-						# (don't replace with BSET!)
-	or	_PAGE_DIRTY,d1
-	mov	d1,(DPTEL)
-	mov	(sp),d1
-	add	4,sp
- 	rti
-
-	ALIGN
-dtlb_pagefault:
-	mov	(sp),d1
 	SAVE_ALL
 	add	-4,sp				# need to pass three params
 
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 4ea4229d765c..8007f1e65729 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -130,15 +130,17 @@ int cpu_check_affinity(unsigned int irq, const struct cpumask *dest)
 	return cpu_dest;
 }
 
-static void cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest)
+static int cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest)
 {
 	int cpu_dest;
 
 	cpu_dest = cpu_check_affinity(irq, dest);
 	if (cpu_dest < 0)
-		return;
+		return -1;
 
 	cpumask_copy(&irq_desc[irq].affinity, dest);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index b7e034b0a6dd..53512374e1c9 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -131,5 +131,41 @@ static inline int irqs_disabled_flags(unsigned long flags)
  */
 struct irq_chip;
 
+#ifdef CONFIG_PERF_COUNTERS
+static inline unsigned long test_perf_counter_pending(void)
+{
+	unsigned long x;
+
+	asm volatile("lbz %0,%1(13)"
+		: "=r" (x)
+		: "i" (offsetof(struct paca_struct, perf_counter_pending)));
+	return x;
+}
+
+static inline void set_perf_counter_pending(void)
+{
+	asm volatile("stb %0,%1(13)" : :
+		"r" (1),
+		"i" (offsetof(struct paca_struct, perf_counter_pending)));
+}
+
+static inline void clear_perf_counter_pending(void)
+{
+	asm volatile("stb %0,%1(13)" : :
+		"r" (0),
+		"i" (offsetof(struct paca_struct, perf_counter_pending)));
+}
+
+#else
+
+static inline unsigned long test_perf_counter_pending(void)
+{
+	return 0;
+}
+
+static inline void set_perf_counter_pending(void) {}
+static inline void clear_perf_counter_pending(void) {}
+#endif /* CONFIG_PERF_COUNTERS */
+
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_HW_IRQ_H */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 082b3aedf145..6ef055723019 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -99,6 +99,7 @@ struct paca_struct {
 	u8 soft_enabled;		/* irq soft-enable flag */
 	u8 hard_enabled;		/* set if irqs are enabled in MSR */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
+	u8 perf_counter_pending;	/* PM interrupt while soft-disabled */
 
 	/* Stuff for accurate time accounting */
 	u64 user_time;			/* accumulated usermode TB ticks */
diff --git a/arch/powerpc/include/asm/perf_counter.h b/arch/powerpc/include/asm/perf_counter.h
new file mode 100644
index 000000000000..cc7c887705b8
--- /dev/null
+++ b/arch/powerpc/include/asm/perf_counter.h
@@ -0,0 +1,98 @@
+/*
+ * Performance counter support - PowerPC-specific definitions.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/types.h>
+
+#define MAX_HWCOUNTERS		8
+#define MAX_EVENT_ALTERNATIVES	8
+#define MAX_LIMITED_HWCOUNTERS	2
+
+/*
+ * This struct provides the constants and functions needed to
+ * describe the PMU on a particular POWER-family CPU.
+ */
+struct power_pmu {
+	int	n_counter;
+	int	max_alternatives;
+	u64	add_fields;
+	u64	test_adder;
+	int	(*compute_mmcr)(u64 events[], int n_ev,
+				unsigned int hwc[], u64 mmcr[]);
+	int	(*get_constraint)(u64 event, u64 *mskp, u64 *valp);
+	int	(*get_alternatives)(u64 event, unsigned int flags,
+				    u64 alt[]);
+	void	(*disable_pmc)(unsigned int pmc, u64 mmcr[]);
+	int	(*limited_pmc_event)(u64 event);
+	u32	flags;
+	int	n_generic;
+	int	*generic_events;
+	int	(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+			       [PERF_COUNT_HW_CACHE_OP_MAX]
+			       [PERF_COUNT_HW_CACHE_RESULT_MAX];
+};
+
+extern struct power_pmu *ppmu;
+
+/*
+ * Values for power_pmu.flags
+ */
+#define PPMU_LIMITED_PMC5_6	1	/* PMC5/6 have limited function */
+#define PPMU_ALT_SIPR		2	/* uses alternate posn for SIPR/HV */
+
+/*
+ * Values for flags to get_alternatives()
+ */
+#define PPMU_LIMITED_PMC_OK	1	/* can put this on a limited PMC */
+#define PPMU_LIMITED_PMC_REQD	2	/* have to put this on a limited PMC */
+#define PPMU_ONLY_COUNT_RUN	4	/* only counting in run state */
+
+struct pt_regs;
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs)	perf_misc_flags(regs)
+
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+
+/*
+ * The power_pmu.get_constraint function returns a 64-bit value and
+ * a 64-bit mask that express the constraints between this event and
+ * other events.
+ *
+ * The value and mask are divided up into (non-overlapping) bitfields
+ * of three different types:
+ *
+ * Select field: this expresses the constraint that some set of bits
+ * in MMCR* needs to be set to a specific value for this event.  For a
+ * select field, the mask contains 1s in every bit of the field, and
+ * the value contains a unique value for each possible setting of the
+ * MMCR* bits.  The constraint checking code will ensure that two events
+ * that set the same field in their masks have the same value in their
+ * value dwords.
+ *
+ * Add field: this expresses the constraint that there can be at most
+ * N events in a particular class.  A field of k bits can be used for
+ * N <= 2^(k-1) - 1.  The mask has the most significant bit of the field
+ * set (and the other bits 0), and the value has only the least significant
+ * bit of the field set.  In addition, the 'add_fields' and 'test_adder'
+ * in the struct power_pmu for this processor come into play.  The
+ * add_fields value contains 1 in the LSB of the field, and the
+ * test_adder contains 2^(k-1) - 1 - N in the field.
+ *
+ * NAND field: this expresses the constraint that you may not have events
+ * in all of a set of classes.  (For example, on PPC970, you can't select
+ * events from the FPU, ISU and IDU simultaneously, although any two are
+ * possible.)  For N classes, the field is N+1 bits wide, and each class
+ * is assigned one bit from the least-significant N bits.  The mask has
+ * only the most-significant bit set, and the value has only the bit
+ * for the event's class set.  The test_adder has the least significant
+ * bit set in the field.
+ *
+ * If an event is not subject to the constraint expressed by a particular
+ * field, then it will have 0 in both the mask and value for that field.
+ */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index e8018d540e87..fb359b0a6937 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -492,11 +492,13 @@
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
 #define SPRN_MMCRA	0x312
+#define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SIHV	0x10000000UL /* state of MSR HV when SIAR set */
 #define   MMCRA_SIPR	0x08000000UL /* state of MSR PR when SIAR set */
 #define   MMCRA_SLOT	0x07000000UL /* SLOT bits (37-39) */
 #define   MMCRA_SLOT_SHIFT	24
 #define   MMCRA_SAMPLE_ENABLE 0x00000001UL /* enable sampling */
+#define   POWER6_MMCRA_SDSYNC 0x0000080000000000ULL	/* SDAR/SIAR synced */
 #define   POWER6_MMCRA_SIHV   0x0000040000000000ULL
 #define   POWER6_MMCRA_SIPR   0x0000020000000000ULL
 #define   POWER6_MMCRA_THRM	0x00000020UL
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index d98a30dfd41c..a0b92de51c7e 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -322,6 +322,6 @@ SYSCALL_SPU(epoll_create1)
 SYSCALL_SPU(dup3)
 SYSCALL_SPU(pipe2)
 SYSCALL(inotify_init1)
-SYSCALL(ni_syscall)
+SYSCALL_SPU(perf_counter_open)
 COMPAT_SYS_SPU(preadv)
 COMPAT_SYS_SPU(pwritev)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 3f06f8ec81c5..4badac2d11d1 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -341,6 +341,7 @@
 #define __NR_dup3		316
 #define __NR_pipe2		317
 #define __NR_inotify_init1	318
+#define __NR_perf_counter_open	319
 #define __NR_preadv		320
 #define __NR_pwritev		321
 
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 71901fbda4a5..a2c683403c2b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -94,6 +94,9 @@ obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_PERF_COUNTERS)	+= perf_counter.o power4-pmu.o ppc970-pmu.o \
+				   power5-pmu.o power5+-pmu.o power6-pmu.o \
+				   power7-pmu.o
 
 obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 1e40bc053946..e981d1ce1914 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -131,6 +131,7 @@ int main(void)
 	DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
+	DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_counter_pending));
 	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
 	DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
 	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index abfc32330479..43e073477c34 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -526,6 +526,15 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
 2:
 	TRACE_AND_RESTORE_IRQ(r5);
 
+#ifdef CONFIG_PERF_COUNTERS
+	/* check paca->perf_counter_pending if we're enabling ints */
+	lbz	r3,PACAPERFPEND(r13)
+	and.	r3,r3,r5
+	beq	27f
+	bl	.perf_counter_do_pending
+27:
+#endif /* CONFIG_PERF_COUNTERS */
+
 	/* extract EE bit and use it to restore paca->hard_enabled */
 	ld	r3,_MSR(r1)
 	rldicl	r4,r3,49,63		/* r0 = (r3 >> 15) & 1 */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 8c1a4966867e..844d3f882a15 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -53,6 +53,7 @@
 #include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/debugfs.h>
+#include <linux/perf_counter.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -135,6 +136,11 @@ notrace void raw_local_irq_restore(unsigned long en)
 			iseries_handle_interrupts();
 	}
 
+	if (test_perf_counter_pending()) {
+		clear_perf_counter_pending();
+		perf_counter_do_pending();
+	}
+
 	/*
 	 * if (get_paca()->hard_enabled) return;
 	 * But again we need to take care that gcc gets hard_enabled directly
diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c
new file mode 100644
index 000000000000..bb202388170e
--- /dev/null
+++ b/arch/powerpc/kernel/perf_counter.c
@@ -0,0 +1,1263 @@
+/*
+ * Performance counter support - powerpc architecture code
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_counter.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <asm/reg.h>
+#include <asm/pmc.h>
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/ptrace.h>
+
+struct cpu_hw_counters {
+	int n_counters;
+	int n_percpu;
+	int disabled;
+	int n_added;
+	int n_limited;
+	u8  pmcs_enabled;
+	struct perf_counter *counter[MAX_HWCOUNTERS];
+	u64 events[MAX_HWCOUNTERS];
+	unsigned int flags[MAX_HWCOUNTERS];
+	u64 mmcr[3];
+	struct perf_counter *limited_counter[MAX_LIMITED_HWCOUNTERS];
+	u8  limited_hwidx[MAX_LIMITED_HWCOUNTERS];
+};
+DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters);
+
+struct power_pmu *ppmu;
+
+/*
+ * Normally, to ignore kernel events we set the FCS (freeze counters
+ * in supervisor mode) bit in MMCR0, but if the kernel runs with the
+ * hypervisor bit set in the MSR, or if we are running on a processor
+ * where the hypervisor bit is forced to 1 (as on Apple G5 processors),
+ * then we need to use the FCHV bit to ignore kernel events.
+ */
+static unsigned int freeze_counters_kernel = MMCR0_FCS;
+
+static void perf_counter_interrupt(struct pt_regs *regs);
+
+void perf_counter_print_debug(void)
+{
+}
+
+/*
+ * Read one performance monitor counter (PMC).
+ */
+static unsigned long read_pmc(int idx)
+{
+	unsigned long val;
+
+	switch (idx) {
+	case 1:
+		val = mfspr(SPRN_PMC1);
+		break;
+	case 2:
+		val = mfspr(SPRN_PMC2);
+		break;
+	case 3:
+		val = mfspr(SPRN_PMC3);
+		break;
+	case 4:
+		val = mfspr(SPRN_PMC4);
+		break;
+	case 5:
+		val = mfspr(SPRN_PMC5);
+		break;
+	case 6:
+		val = mfspr(SPRN_PMC6);
+		break;
+	case 7:
+		val = mfspr(SPRN_PMC7);
+		break;
+	case 8:
+		val = mfspr(SPRN_PMC8);
+		break;
+	default:
+		printk(KERN_ERR "oops trying to read PMC%d\n", idx);
+		val = 0;
+	}
+	return val;
+}
+
+/*
+ * Write one PMC.
+ */
+static void write_pmc(int idx, unsigned long val)
+{
+	switch (idx) {
+	case 1:
+		mtspr(SPRN_PMC1, val);
+		break;
+	case 2:
+		mtspr(SPRN_PMC2, val);
+		break;
+	case 3:
+		mtspr(SPRN_PMC3, val);
+		break;
+	case 4:
+		mtspr(SPRN_PMC4, val);
+		break;
+	case 5:
+		mtspr(SPRN_PMC5, val);
+		break;
+	case 6:
+		mtspr(SPRN_PMC6, val);
+		break;
+	case 7:
+		mtspr(SPRN_PMC7, val);
+		break;
+	case 8:
+		mtspr(SPRN_PMC8, val);
+		break;
+	default:
+		printk(KERN_ERR "oops trying to write PMC%d\n", idx);
+	}
+}
+
+/*
+ * Check if a set of events can all go on the PMU at once.
+ * If they can't, this will look at alternative codes for the events
+ * and see if any combination of alternative codes is feasible.
+ * The feasible set is returned in event[].
+ */
+static int power_check_constraints(u64 event[], unsigned int cflags[],
+				   int n_ev)
+{
+	u64 mask, value, nv;
+	u64 alternatives[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
+	u64 amasks[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
+	u64 avalues[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
+	u64 smasks[MAX_HWCOUNTERS], svalues[MAX_HWCOUNTERS];
+	int n_alt[MAX_HWCOUNTERS], choice[MAX_HWCOUNTERS];
+	int i, j;
+	u64 addf = ppmu->add_fields;
+	u64 tadd = ppmu->test_adder;
+
+	if (n_ev > ppmu->n_counter)
+		return -1;
+
+	/* First see if the events will go on as-is */
+	for (i = 0; i < n_ev; ++i) {
+		if ((cflags[i] & PPMU_LIMITED_PMC_REQD)
+		    && !ppmu->limited_pmc_event(event[i])) {
+			ppmu->get_alternatives(event[i], cflags[i],
+					       alternatives[i]);
+			event[i] = alternatives[i][0];
+		}
+		if (ppmu->get_constraint(event[i], &amasks[i][0],
+					 &avalues[i][0]))
+			return -1;
+	}
+	value = mask = 0;
+	for (i = 0; i < n_ev; ++i) {
+		nv = (value | avalues[i][0]) + (value & avalues[i][0] & addf);
+		if ((((nv + tadd) ^ value) & mask) != 0 ||
+		    (((nv + tadd) ^ avalues[i][0]) & amasks[i][0]) != 0)
+			break;
+		value = nv;
+		mask |= amasks[i][0];
+	}
+	if (i == n_ev)
+		return 0;	/* all OK */
+
+	/* doesn't work, gather alternatives... */
+	if (!ppmu->get_alternatives)
+		return -1;
+	for (i = 0; i < n_ev; ++i) {
+		choice[i] = 0;
+		n_alt[i] = ppmu->get_alternatives(event[i], cflags[i],
+						  alternatives[i]);
+		for (j = 1; j < n_alt[i]; ++j)
+			ppmu->get_constraint(alternatives[i][j],
+					     &amasks[i][j], &avalues[i][j]);
+	}
+
+	/* enumerate all possibilities and see if any will work */
+	i = 0;
+	j = -1;
+	value = mask = nv = 0;
+	while (i < n_ev) {
+		if (j >= 0) {
+			/* we're backtracking, restore context */
+			value = svalues[i];
+			mask = smasks[i];
+			j = choice[i];
+		}
+		/*
+		 * See if any alternative k for event i,
+		 * where k > j, will satisfy the constraints.
+		 */
+		while (++j < n_alt[i]) {
+			nv = (value | avalues[i][j]) +
+				(value & avalues[i][j] & addf);
+			if ((((nv + tadd) ^ value) & mask) == 0 &&
+			    (((nv + tadd) ^ avalues[i][j])
+			     & amasks[i][j]) == 0)
+				break;
+		}
+		if (j >= n_alt[i]) {
+			/*
+			 * No feasible alternative, backtrack
+			 * to event i-1 and continue enumerating its
+			 * alternatives from where we got up to.
+			 */
+			if (--i < 0)
+				return -1;
+		} else {
+			/*
+			 * Found a feasible alternative for event i,
+			 * remember where we got up to with this event,
+			 * go on to the next event, and start with
+			 * the first alternative for it.
+			 */
+			choice[i] = j;
+			svalues[i] = value;
+			smasks[i] = mask;
+			value = nv;
+			mask |= amasks[i][j];
+			++i;
+			j = -1;
+		}
+	}
+
+	/* OK, we have a feasible combination, tell the caller the solution */
+	for (i = 0; i < n_ev; ++i)
+		event[i] = alternatives[i][choice[i]];
+	return 0;
+}
+
+/*
+ * Check if newly-added counters have consistent settings for
+ * exclude_{user,kernel,hv} with each other and any previously
+ * added counters.
+ */
+static int check_excludes(struct perf_counter **ctrs, unsigned int cflags[],
+			  int n_prev, int n_new)
+{
+	int eu = 0, ek = 0, eh = 0;
+	int i, n, first;
+	struct perf_counter *counter;
+
+	n = n_prev + n_new;
+	if (n <= 1)
+		return 0;
+
+	first = 1;
+	for (i = 0; i < n; ++i) {
+		if (cflags[i] & PPMU_LIMITED_PMC_OK) {
+			cflags[i] &= ~PPMU_LIMITED_PMC_REQD;
+			continue;
+		}
+		counter = ctrs[i];
+		if (first) {
+			eu = counter->attr.exclude_user;
+			ek = counter->attr.exclude_kernel;
+			eh = counter->attr.exclude_hv;
+			first = 0;
+		} else if (counter->attr.exclude_user != eu ||
+			   counter->attr.exclude_kernel != ek ||
+			   counter->attr.exclude_hv != eh) {
+			return -EAGAIN;
+		}
+	}
+
+	if (eu || ek || eh)
+		for (i = 0; i < n; ++i)
+			if (cflags[i] & PPMU_LIMITED_PMC_OK)
+				cflags[i] |= PPMU_LIMITED_PMC_REQD;
+
+	return 0;
+}
+
+static void power_pmu_read(struct perf_counter *counter)
+{
+	long val, delta, prev;
+
+	if (!counter->hw.idx)
+		return;
+	/*
+	 * Performance monitor interrupts come even when interrupts
+	 * are soft-disabled, as long as interrupts are hard-enabled.
+	 * Therefore we treat them like NMIs.
+	 */
+	do {
+		prev = atomic64_read(&counter->hw.prev_count);
+		barrier();
+		val = read_pmc(counter->hw.idx);
+	} while (atomic64_cmpxchg(&counter->hw.prev_count, prev, val) != prev);
+
+	/* The counters are only 32 bits wide */
+	delta = (val - prev) & 0xfffffffful;
+	atomic64_add(delta, &counter->count);
+	atomic64_sub(delta, &counter->hw.period_left);
+}
+
+/*
+ * On some machines, PMC5 and PMC6 can't be written, don't respect
+ * the freeze conditions, and don't generate interrupts.  This tells
+ * us if `counter' is using such a PMC.
+ */
+static int is_limited_pmc(int pmcnum)
+{
+	return (ppmu->flags & PPMU_LIMITED_PMC5_6)
+		&& (pmcnum == 5 || pmcnum == 6);
+}
+
+static void freeze_limited_counters(struct cpu_hw_counters *cpuhw,
+				    unsigned long pmc5, unsigned long pmc6)
+{
+	struct perf_counter *counter;
+	u64 val, prev, delta;
+	int i;
+
+	for (i = 0; i < cpuhw->n_limited; ++i) {
+		counter = cpuhw->limited_counter[i];
+		if (!counter->hw.idx)
+			continue;
+		val = (counter->hw.idx == 5) ? pmc5 : pmc6;
+		prev = atomic64_read(&counter->hw.prev_count);
+		counter->hw.idx = 0;
+		delta = (val - prev) & 0xfffffffful;
+		atomic64_add(delta, &counter->count);
+	}
+}
+
+static void thaw_limited_counters(struct cpu_hw_counters *cpuhw,
+				  unsigned long pmc5, unsigned long pmc6)
+{
+	struct perf_counter *counter;
+	u64 val;
+	int i;
+
+	for (i = 0; i < cpuhw->n_limited; ++i) {
+		counter = cpuhw->limited_counter[i];
+		counter->hw.idx = cpuhw->limited_hwidx[i];
+		val = (counter->hw.idx == 5) ? pmc5 : pmc6;
+		atomic64_set(&counter->hw.prev_count, val);
+		perf_counter_update_userpage(counter);
+	}
+}
+
+/*
+ * Since limited counters don't respect the freeze conditions, we
+ * have to read them immediately after freezing or unfreezing the
+ * other counters.  We try to keep the values from the limited
+ * counters as consistent as possible by keeping the delay (in
+ * cycles and instructions) between freezing/unfreezing and reading
+ * the limited counters as small and consistent as possible.
+ * Therefore, if any limited counters are in use, we read them
+ * both, and always in the same order, to minimize variability,
+ * and do it inside the same asm that writes MMCR0.
+ */
+static void write_mmcr0(struct cpu_hw_counters *cpuhw, unsigned long mmcr0)
+{
+	unsigned long pmc5, pmc6;
+
+	if (!cpuhw->n_limited) {
+		mtspr(SPRN_MMCR0, mmcr0);
+		return;
+	}
+
+	/*
+	 * Write MMCR0, then read PMC5 and PMC6 immediately.
+	 * To ensure we don't get a performance monitor interrupt
+	 * between writing MMCR0 and freezing/thawing the limited
+	 * counters, we first write MMCR0 with the counter overflow
+	 * interrupt enable bits turned off.
+	 */
+	asm volatile("mtspr %3,%2; mfspr %0,%4; mfspr %1,%5"
+		     : "=&r" (pmc5), "=&r" (pmc6)
+		     : "r" (mmcr0 & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)),
+		       "i" (SPRN_MMCR0),
+		       "i" (SPRN_PMC5), "i" (SPRN_PMC6));
+
+	if (mmcr0 & MMCR0_FC)
+		freeze_limited_counters(cpuhw, pmc5, pmc6);
+	else
+		thaw_limited_counters(cpuhw, pmc5, pmc6);
+
+	/*
+	 * Write the full MMCR0 including the counter overflow interrupt
+	 * enable bits, if necessary.
+	 */
+	if (mmcr0 & (MMCR0_PMC1CE | MMCR0_PMCjCE))
+		mtspr(SPRN_MMCR0, mmcr0);
+}
+
+/*
+ * Disable all counters to prevent PMU interrupts and to allow
+ * counters to be added or removed.
+ */
+void hw_perf_disable(void)
+{
+	struct cpu_hw_counters *cpuhw;
+	unsigned long ret;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+
+	ret = cpuhw->disabled;
+	if (!ret) {
+		cpuhw->disabled = 1;
+		cpuhw->n_added = 0;
+
+		/*
+		 * Check if we ever enabled the PMU on this cpu.
+		 */
+		if (!cpuhw->pmcs_enabled) {
+			if (ppc_md.enable_pmcs)
+				ppc_md.enable_pmcs();
+			cpuhw->pmcs_enabled = 1;
+		}
+
+		/*
+		 * Disable instruction sampling if it was enabled
+		 */
+		if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) {
+			mtspr(SPRN_MMCRA,
+			      cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
+			mb();
+		}
+
+		/*
+		 * Set the 'freeze counters' bit.
+		 * The barrier is to make sure the mtspr has been
+		 * executed and the PMU has frozen the counters
+		 * before we return.
+		 */
+		write_mmcr0(cpuhw, mfspr(SPRN_MMCR0) | MMCR0_FC);
+		mb();
+	}
+	local_irq_restore(flags);
+}
+
+/*
+ * Re-enable all counters if disable == 0.
+ * If we were previously disabled and counters were added, then
+ * put the new config on the PMU.
+ */
+void hw_perf_enable(void)
+{
+	struct perf_counter *counter;
+	struct cpu_hw_counters *cpuhw;
+	unsigned long flags;
+	long i;
+	unsigned long val;
+	s64 left;
+	unsigned int hwc_index[MAX_HWCOUNTERS];
+	int n_lim;
+	int idx;
+
+	local_irq_save(flags);
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+	if (!cpuhw->disabled) {
+		local_irq_restore(flags);
+		return;
+	}
+	cpuhw->disabled = 0;
+
+	/*
+	 * If we didn't change anything, or only removed counters,
+	 * no need to recalculate MMCR* settings and reset the PMCs.
+	 * Just reenable the PMU with the current MMCR* settings
+	 * (possibly updated for removal of counters).
+	 */
+	if (!cpuhw->n_added) {
+		mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
+		mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
+		if (cpuhw->n_counters == 0)
+			get_lppaca()->pmcregs_in_use = 0;
+		goto out_enable;
+	}
+
+	/*
+	 * Compute MMCR* values for the new set of counters
+	 */
+	if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_counters, hwc_index,
+			       cpuhw->mmcr)) {
+		/* shouldn't ever get here */
+		printk(KERN_ERR "oops compute_mmcr failed\n");
+		goto out;
+	}
+
+	/*
+	 * Add in MMCR0 freeze bits corresponding to the
+	 * attr.exclude_* bits for the first counter.
+	 * We have already checked that all counters have the
+	 * same values for these bits as the first counter.
+	 */
+	counter = cpuhw->counter[0];
+	if (counter->attr.exclude_user)
+		cpuhw->mmcr[0] |= MMCR0_FCP;
+	if (counter->attr.exclude_kernel)
+		cpuhw->mmcr[0] |= freeze_counters_kernel;
+	if (counter->attr.exclude_hv)
+		cpuhw->mmcr[0] |= MMCR0_FCHV;
+
+	/*
+	 * Write the new configuration to MMCR* with the freeze
+	 * bit set and set the hardware counters to their initial values.
+	 * Then unfreeze the counters.
+	 */
+	get_lppaca()->pmcregs_in_use = 1;
+	mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
+	mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
+	mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE))
+				| MMCR0_FC);
+
+	/*
+	 * Read off any pre-existing counters that need to move
+	 * to another PMC.
+	 */
+	for (i = 0; i < cpuhw->n_counters; ++i) {
+		counter = cpuhw->counter[i];
+		if (counter->hw.idx && counter->hw.idx != hwc_index[i] + 1) {
+			power_pmu_read(counter);
+			write_pmc(counter->hw.idx, 0);
+			counter->hw.idx = 0;
+		}
+	}
+
+	/*
+	 * Initialize the PMCs for all the new and moved counters.
+	 */
+	cpuhw->n_limited = n_lim = 0;
+	for (i = 0; i < cpuhw->n_counters; ++i) {
+		counter = cpuhw->counter[i];
+		if (counter->hw.idx)
+			continue;
+		idx = hwc_index[i] + 1;
+		if (is_limited_pmc(idx)) {
+			cpuhw->limited_counter[n_lim] = counter;
+			cpuhw->limited_hwidx[n_lim] = idx;
+			++n_lim;
+			continue;
+		}
+		val = 0;
+		if (counter->hw.sample_period) {
+			left = atomic64_read(&counter->hw.period_left);
+			if (left < 0x80000000L)
+				val = 0x80000000L - left;
+		}
+		atomic64_set(&counter->hw.prev_count, val);
+		counter->hw.idx = idx;
+		write_pmc(idx, val);
+		perf_counter_update_userpage(counter);
+	}
+	cpuhw->n_limited = n_lim;
+	cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE;
+
+ out_enable:
+	mb();
+	write_mmcr0(cpuhw, cpuhw->mmcr[0]);
+
+	/*
+	 * Enable instruction sampling if necessary
+	 */
+	if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) {
+		mb();
+		mtspr(SPRN_MMCRA, cpuhw->mmcr[2]);
+	}
+
+ out:
+	local_irq_restore(flags);
+}
+
+static int collect_events(struct perf_counter *group, int max_count,
+			  struct perf_counter *ctrs[], u64 *events,
+			  unsigned int *flags)
+{
+	int n = 0;
+	struct perf_counter *counter;
+
+	if (!is_software_counter(group)) {
+		if (n >= max_count)
+			return -1;
+		ctrs[n] = group;
+		flags[n] = group->hw.counter_base;
+		events[n++] = group->hw.config;
+	}
+	list_for_each_entry(counter, &group->sibling_list, list_entry) {
+		if (!is_software_counter(counter) &&
+		    counter->state != PERF_COUNTER_STATE_OFF) {
+			if (n >= max_count)
+				return -1;
+			ctrs[n] = counter;
+			flags[n] = counter->hw.counter_base;
+			events[n++] = counter->hw.config;
+		}
+	}
+	return n;
+}
+
+static void counter_sched_in(struct perf_counter *counter, int cpu)
+{
+	counter->state = PERF_COUNTER_STATE_ACTIVE;
+	counter->oncpu = cpu;
+	counter->tstamp_running += counter->ctx->time - counter->tstamp_stopped;
+	if (is_software_counter(counter))
+		counter->pmu->enable(counter);
+}
+
+/*
+ * Called to enable a whole group of counters.
+ * Returns 1 if the group was enabled, or -EAGAIN if it could not be.
+ * Assumes the caller has disabled interrupts and has
+ * frozen the PMU with hw_perf_save_disable.
+ */
+int hw_perf_group_sched_in(struct perf_counter *group_leader,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_counter_context *ctx, int cpu)
+{
+	struct cpu_hw_counters *cpuhw;
+	long i, n, n0;
+	struct perf_counter *sub;
+
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+	n0 = cpuhw->n_counters;
+	n = collect_events(group_leader, ppmu->n_counter - n0,
+			   &cpuhw->counter[n0], &cpuhw->events[n0],
+			   &cpuhw->flags[n0]);
+	if (n < 0)
+		return -EAGAIN;
+	if (check_excludes(cpuhw->counter, cpuhw->flags, n0, n))
+		return -EAGAIN;
+	i = power_check_constraints(cpuhw->events, cpuhw->flags, n + n0);
+	if (i < 0)
+		return -EAGAIN;
+	cpuhw->n_counters = n0 + n;
+	cpuhw->n_added += n;
+
+	/*
+	 * OK, this group can go on; update counter states etc.,
+	 * and enable any software counters
+	 */
+	for (i = n0; i < n0 + n; ++i)
+		cpuhw->counter[i]->hw.config = cpuhw->events[i];
+	cpuctx->active_oncpu += n;
+	n = 1;
+	counter_sched_in(group_leader, cpu);
+	list_for_each_entry(sub, &group_leader->sibling_list, list_entry) {
+		if (sub->state != PERF_COUNTER_STATE_OFF) {
+			counter_sched_in(sub, cpu);
+			++n;
+		}
+	}
+	ctx->nr_active += n;
+
+	return 1;
+}
+
+/*
+ * Add a counter to the PMU.
+ * If all counters are not already frozen, then we disable and
+ * re-enable the PMU in order to get hw_perf_enable to do the
+ * actual work of reconfiguring the PMU.
+ */
+static int power_pmu_enable(struct perf_counter *counter)
+{
+	struct cpu_hw_counters *cpuhw;
+	unsigned long flags;
+	int n0;
+	int ret = -EAGAIN;
+
+	local_irq_save(flags);
+	perf_disable();
+
+	/*
+	 * Add the counter to the list (if there is room)
+	 * and check whether the total set is still feasible.
+	 */
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+	n0 = cpuhw->n_counters;
+	if (n0 >= ppmu->n_counter)
+		goto out;
+	cpuhw->counter[n0] = counter;
+	cpuhw->events[n0] = counter->hw.config;
+	cpuhw->flags[n0] = counter->hw.counter_base;
+	if (check_excludes(cpuhw->counter, cpuhw->flags, n0, 1))
+		goto out;
+	if (power_check_constraints(cpuhw->events, cpuhw->flags, n0 + 1))
+		goto out;
+
+	counter->hw.config = cpuhw->events[n0];
+	++cpuhw->n_counters;
+	++cpuhw->n_added;
+
+	ret = 0;
+ out:
+	perf_enable();
+	local_irq_restore(flags);
+	return ret;
+}
+
+/*
+ * Remove a counter from the PMU.
+ */
+static void power_pmu_disable(struct perf_counter *counter)
+{
+	struct cpu_hw_counters *cpuhw;
+	long i;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	perf_disable();
+
+	power_pmu_read(counter);
+
+	cpuhw = &__get_cpu_var(cpu_hw_counters);
+	for (i = 0; i < cpuhw->n_counters; ++i) {
+		if (counter == cpuhw->counter[i]) {
+			while (++i < cpuhw->n_counters)
+				cpuhw->counter[i-1] = cpuhw->counter[i];
+			--cpuhw->n_counters;
+			ppmu->disable_pmc(counter->hw.idx - 1, cpuhw->mmcr);
+			if (counter->hw.idx) {
+				write_pmc(counter->hw.idx, 0);
+				counter->hw.idx = 0;
+			}
+			perf_counter_update_userpage(counter);
+			break;
+		}
+	}
+	for (i = 0; i < cpuhw->n_limited; ++i)
+		if (counter == cpuhw->limited_counter[i])
+			break;
+	if (i < cpuhw->n_limited) {
+		while (++i < cpuhw->n_limited) {
+			cpuhw->limited_counter[i-1] = cpuhw->limited_counter[i];
+			cpuhw->limited_hwidx[i-1] = cpuhw->limited_hwidx[i];
+		}
+		--cpuhw->n_limited;
+	}
+	if (cpuhw->n_counters == 0) {
+		/* disable exceptions if no counters are running */
+		cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE);
+	}
+
+	perf_enable();
+	local_irq_restore(flags);
+}
+
+/*
+ * Re-enable interrupts on a counter after they were throttled
+ * because they were coming too fast.
+ */
+static void power_pmu_unthrottle(struct perf_counter *counter)
+{
+	s64 val, left;
+	unsigned long flags;
+
+	if (!counter->hw.idx || !counter->hw.sample_period)
+		return;
+	local_irq_save(flags);
+	perf_disable();
+	power_pmu_read(counter);
+	left = counter->hw.sample_period;
+	counter->hw.last_period = left;
+	val = 0;
+	if (left < 0x80000000L)
+		val = 0x80000000L - left;
+	write_pmc(counter->hw.idx, val);
+	atomic64_set(&counter->hw.prev_count, val);
+	atomic64_set(&counter->hw.period_left, left);
+	perf_counter_update_userpage(counter);
+	perf_enable();
+	local_irq_restore(flags);
+}
+
+struct pmu power_pmu = {
+	.enable		= power_pmu_enable,
+	.disable	= power_pmu_disable,
+	.read		= power_pmu_read,
+	.unthrottle	= power_pmu_unthrottle,
+};
+
+/*
+ * Return 1 if we might be able to put counter on a limited PMC,
+ * or 0 if not.
+ * A counter can only go on a limited PMC if it counts something
+ * that a limited PMC can count, doesn't require interrupts, and
+ * doesn't exclude any processor mode.
+ */
+static int can_go_on_limited_pmc(struct perf_counter *counter, u64 ev,
+				 unsigned int flags)
+{
+	int n;
+	u64 alt[MAX_EVENT_ALTERNATIVES];
+
+	if (counter->attr.exclude_user
+	    || counter->attr.exclude_kernel
+	    || counter->attr.exclude_hv
+	    || counter->attr.sample_period)
+		return 0;
+
+	if (ppmu->limited_pmc_event(ev))
+		return 1;
+
+	/*
+	 * The requested event isn't on a limited PMC already;
+	 * see if any alternative code goes on a limited PMC.
+	 */
+	if (!ppmu->get_alternatives)
+		return 0;
+
+	flags |= PPMU_LIMITED_PMC_OK | PPMU_LIMITED_PMC_REQD;
+	n = ppmu->get_alternatives(ev, flags, alt);
+
+	return n > 0;
+}
+
+/*
+ * Find an alternative event that goes on a normal PMC, if possible,
+ * and return the event code, or 0 if there is no such alternative.
+ * (Note: event code 0 is "don't count" on all machines.)
+ */
+static u64 normal_pmc_alternative(u64 ev, unsigned long flags)
+{
+	u64 alt[MAX_EVENT_ALTERNATIVES];
+	int n;
+
+	flags &= ~(PPMU_LIMITED_PMC_OK | PPMU_LIMITED_PMC_REQD);
+	n = ppmu->get_alternatives(ev, flags, alt);
+	if (!n)
+		return 0;
+	return alt[0];
+}
+
+/* Number of perf_counters counting hardware events */
+static atomic_t num_counters;
+/* Used to avoid races in calling reserve/release_pmc_hardware */
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+/*
+ * Release the PMU if this is the last perf_counter.
+ */
+static void hw_perf_counter_destroy(struct perf_counter *counter)
+{
+	if (!atomic_add_unless(&num_counters, -1, 1)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_dec_return(&num_counters) == 0)
+			release_pmc_hardware();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
+/*
+ * Translate a generic cache event config to a raw event code.
+ */
+static int hw_perf_cache_event(u64 config, u64 *eventp)
+{
+	unsigned long type, op, result;
+	int ev;
+
+	if (!ppmu->cache_events)
+		return -EINVAL;
+
+	/* unpack config */
+	type = config & 0xff;
+	op = (config >> 8) & 0xff;
+	result = (config >> 16) & 0xff;
+
+	if (type >= PERF_COUNT_HW_CACHE_MAX ||
+	    op >= PERF_COUNT_HW_CACHE_OP_MAX ||
+	    result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+		return -EINVAL;
+
+	ev = (*ppmu->cache_events)[type][op][result];
+	if (ev == 0)
+		return -EOPNOTSUPP;
+	if (ev == -1)
+		return -EINVAL;
+	*eventp = ev;
+	return 0;
+}
+
+const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
+{
+	u64 ev;
+	unsigned long flags;
+	struct perf_counter *ctrs[MAX_HWCOUNTERS];
+	u64 events[MAX_HWCOUNTERS];
+	unsigned int cflags[MAX_HWCOUNTERS];
+	int n;
+	int err;
+
+	if (!ppmu)
+		return ERR_PTR(-ENXIO);
+	switch (counter->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		ev = counter->attr.config;
+		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
+			return ERR_PTR(-EOPNOTSUPP);
+		ev = ppmu->generic_events[ev];
+		break;
+	case PERF_TYPE_HW_CACHE:
+		err = hw_perf_cache_event(counter->attr.config, &ev);
+		if (err)
+			return ERR_PTR(err);
+		break;
+	case PERF_TYPE_RAW:
+		ev = counter->attr.config;
+		break;
+	}
+	counter->hw.config_base = ev;
+	counter->hw.idx = 0;
+
+	/*
+	 * If we are not running on a hypervisor, force the
+	 * exclude_hv bit to 0 so that we don't care what
+	 * the user set it to.
+	 */
+	if (!firmware_has_feature(FW_FEATURE_LPAR))
+		counter->attr.exclude_hv = 0;
+
+	/*
+	 * If this is a per-task counter, then we can use
+	 * PM_RUN_* events interchangeably with their non RUN_*
+	 * equivalents, e.g. PM_RUN_CYC instead of PM_CYC.
+	 * XXX we should check if the task is an idle task.
+	 */
+	flags = 0;
+	if (counter->ctx->task)
+		flags |= PPMU_ONLY_COUNT_RUN;
+
+	/*
+	 * If this machine has limited counters, check whether this
+	 * event could go on a limited counter.
+	 */
+	if (ppmu->flags & PPMU_LIMITED_PMC5_6) {
+		if (can_go_on_limited_pmc(counter, ev, flags)) {
+			flags |= PPMU_LIMITED_PMC_OK;
+		} else if (ppmu->limited_pmc_event(ev)) {
+			/*
+			 * The requested event is on a limited PMC,
+			 * but we can't use a limited PMC; see if any
+			 * alternative goes on a normal PMC.
+			 */
+			ev = normal_pmc_alternative(ev, flags);
+			if (!ev)
+				return ERR_PTR(-EINVAL);
+		}
+	}
+
+	/*
+	 * If this is in a group, check if it can go on with all the
+	 * other hardware counters in the group.  We assume the counter
+	 * hasn't been linked into its leader's sibling list at this point.
+	 */
+	n = 0;
+	if (counter->group_leader != counter) {
+		n = collect_events(counter->group_leader, ppmu->n_counter - 1,
+				   ctrs, events, cflags);
+		if (n < 0)
+			return ERR_PTR(-EINVAL);
+	}
+	events[n] = ev;
+	ctrs[n] = counter;
+	cflags[n] = flags;
+	if (check_excludes(ctrs, cflags, n, 1))
+		return ERR_PTR(-EINVAL);
+	if (power_check_constraints(events, cflags, n + 1))
+		return ERR_PTR(-EINVAL);
+
+	counter->hw.config = events[n];
+	counter->hw.counter_base = cflags[n];
+	counter->hw.last_period = counter->hw.sample_period;
+	atomic64_set(&counter->hw.period_left, counter->hw.last_period);
+
+	/*
+	 * See if we need to reserve the PMU.
+	 * If no counters are currently in use, then we have to take a
+	 * mutex to ensure that we don't race with another task doing
+	 * reserve_pmc_hardware or release_pmc_hardware.
+	 */
+	err = 0;
+	if (!atomic_inc_not_zero(&num_counters)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&num_counters) == 0 &&
+		    reserve_pmc_hardware(perf_counter_interrupt))
+			err = -EBUSY;
+		else
+			atomic_inc(&num_counters);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+	counter->destroy = hw_perf_counter_destroy;
+
+	if (err)
+		return ERR_PTR(err);
+	return &power_pmu;
+}
+
+/*
+ * A counter has overflowed; update its count and record
+ * things if requested.  Note that interrupts are hard-disabled
+ * here so there is no possibility of being interrupted.
+ */
+static void record_and_restart(struct perf_counter *counter, long val,
+			       struct pt_regs *regs, int nmi)
+{
+	u64 period = counter->hw.sample_period;
+	s64 prev, delta, left;
+	int record = 0;
+	u64 addr, mmcra, sdsync;
+
+	/* we don't have to worry about interrupts here */
+	prev = atomic64_read(&counter->hw.prev_count);
+	delta = (val - prev) & 0xfffffffful;
+	atomic64_add(delta, &counter->count);
+
+	/*
+	 * See if the total period for this counter has expired,
+	 * and update for the next period.
+	 */
+	val = 0;
+	left = atomic64_read(&counter->hw.period_left) - delta;
+	if (period) {
+		if (left <= 0) {
+			left += period;
+			if (left <= 0)
+				left = period;
+			record = 1;
+		}
+		if (left < 0x80000000L)
+			val = 0x80000000L - left;
+	}
+
+	/*
+	 * Finally record data if requested.
+	 */
+	if (record) {
+		struct perf_sample_data data = {
+			.regs	= regs,
+			.addr	= 0,
+			.period	= counter->hw.last_period,
+		};
+
+		if (counter->attr.sample_type & PERF_SAMPLE_ADDR) {
+			/*
+			 * The user wants a data address recorded.
+			 * If we're not doing instruction sampling,
+			 * give them the SDAR (sampled data address).
+			 * If we are doing instruction sampling, then only
+			 * give them the SDAR if it corresponds to the
+			 * instruction pointed to by SIAR; this is indicated
+			 * by the [POWER6_]MMCRA_SDSYNC bit in MMCRA.
+			 */
+			mmcra = regs->dsisr;
+			sdsync = (ppmu->flags & PPMU_ALT_SIPR) ?
+				POWER6_MMCRA_SDSYNC : MMCRA_SDSYNC;
+			if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync))
+				data.addr = mfspr(SPRN_SDAR);
+		}
+		if (perf_counter_overflow(counter, nmi, &data)) {
+			/*
+			 * Interrupts are coming too fast - throttle them
+			 * by setting the counter to 0, so it will be
+			 * at least 2^30 cycles until the next interrupt
+			 * (assuming each counter counts at most 2 counts
+			 * per cycle).
+			 */
+			val = 0;
+			left = ~0ULL >> 1;
+		}
+	}
+
+	write_pmc(counter->hw.idx, val);
+	atomic64_set(&counter->hw.prev_count, val);
+	atomic64_set(&counter->hw.period_left, left);
+	perf_counter_update_userpage(counter);
+}
+
+/*
+ * Called from generic code to get the misc flags (i.e. processor mode)
+ * for an event.
+ */
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+	unsigned long mmcra;
+
+	if (TRAP(regs) != 0xf00) {
+		/* not a PMU interrupt */
+		return user_mode(regs) ? PERF_EVENT_MISC_USER :
+			PERF_EVENT_MISC_KERNEL;
+	}
+
+	mmcra = regs->dsisr;
+	if (ppmu->flags & PPMU_ALT_SIPR) {
+		if (mmcra & POWER6_MMCRA_SIHV)
+			return PERF_EVENT_MISC_HYPERVISOR;
+		return (mmcra & POWER6_MMCRA_SIPR) ? PERF_EVENT_MISC_USER :
+			PERF_EVENT_MISC_KERNEL;
+	}
+	if (mmcra & MMCRA_SIHV)
+		return PERF_EVENT_MISC_HYPERVISOR;
+	return (mmcra & MMCRA_SIPR) ? PERF_EVENT_MISC_USER :
+			PERF_EVENT_MISC_KERNEL;
+}
+
+/*
+ * Called from generic code to get the instruction pointer
+ * for an event.
+ */
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+	unsigned long mmcra;
+	unsigned long ip;
+	unsigned long slot;
+
+	if (TRAP(regs) != 0xf00)
+		return regs->nip;	/* not a PMU interrupt */
+
+	ip = mfspr(SPRN_SIAR);
+	mmcra = regs->dsisr;
+	if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) {
+		slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT;
+		if (slot > 1)
+			ip += 4 * (slot - 1);
+	}
+	return ip;
+}
+
+/*
+ * Performance monitor interrupt stuff
+ */
+static void perf_counter_interrupt(struct pt_regs *regs)
+{
+	int i;
+	struct cpu_hw_counters *cpuhw = &__get_cpu_var(cpu_hw_counters);
+	struct perf_counter *counter;
+	long val;
+	int found = 0;
+	int nmi;
+
+	if (cpuhw->n_limited)
+		freeze_limited_counters(cpuhw, mfspr(SPRN_PMC5),
+					mfspr(SPRN_PMC6));
+
+	/*
+	 * Overload regs->dsisr to store MMCRA so we only need to read it once.
+	 */
+	regs->dsisr = mfspr(SPRN_MMCRA);
+
+	/*
+	 * If interrupts were soft-disabled when this PMU interrupt
+	 * occurred, treat it as an NMI.
+	 */
+	nmi = !regs->softe;
+	if (nmi)
+		nmi_enter();
+	else
+		irq_enter();
+
+	for (i = 0; i < cpuhw->n_counters; ++i) {
+		counter = cpuhw->counter[i];
+		if (!counter->hw.idx || is_limited_pmc(counter->hw.idx))
+			continue;
+		val = read_pmc(counter->hw.idx);
+		if ((int)val < 0) {
+			/* counter has overflowed */
+			found = 1;
+			record_and_restart(counter, val, regs, nmi);
+		}
+	}
+
+	/*
+	 * In case we didn't find and reset the counter that caused
+	 * the interrupt, scan all counters and reset any that are
+	 * negative, to avoid getting continual interrupts.
+	 * Any that we processed in the previous loop will not be negative.
+	 */
+	if (!found) {
+		for (i = 0; i < ppmu->n_counter; ++i) {
+			if (is_limited_pmc(i + 1))
+				continue;
+			val = read_pmc(i + 1);
+			if ((int)val < 0)
+				write_pmc(i + 1, 0);
+		}
+	}
+
+	/*
+	 * Reset MMCR0 to its normal value.  This will set PMXE and
+	 * clear FC (freeze counters) and PMAO (perf mon alert occurred)
+	 * and thus allow interrupts to occur again.
+	 * XXX might want to use MSR.PM to keep the counters frozen until
+	 * we get back out of this interrupt.
+	 */
+	write_mmcr0(cpuhw, cpuhw->mmcr[0]);
+
+	if (nmi)
+		nmi_exit();
+	else
+		irq_exit();
+}
+
+void hw_perf_counter_setup(int cpu)
+{
+	struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu);
+
+	memset(cpuhw, 0, sizeof(*cpuhw));
+	cpuhw->mmcr[0] = MMCR0_FC;
+}
+
+extern struct power_pmu power4_pmu;
+extern struct power_pmu ppc970_pmu;
+extern struct power_pmu power5_pmu;
+extern struct power_pmu power5p_pmu;
+extern struct power_pmu power6_pmu;
+extern struct power_pmu power7_pmu;
+
+static int init_perf_counters(void)
+{
+	unsigned long pvr;
+
+	/* XXX should get this from cputable */
+	pvr = mfspr(SPRN_PVR);
+	switch (PVR_VER(pvr)) {
+	case PV_POWER4:
+	case PV_POWER4p:
+		ppmu = &power4_pmu;
+		break;
+	case PV_970:
+	case PV_970FX:
+	case PV_970MP:
+		ppmu = &ppc970_pmu;
+		break;
+	case PV_POWER5:
+		ppmu = &power5_pmu;
+		break;
+	case PV_POWER5p:
+		ppmu = &power5p_pmu;
+		break;
+	case 0x3e:
+		ppmu = &power6_pmu;
+		break;
+	case 0x3f:
+		ppmu = &power7_pmu;
+		break;
+	}
+
+	/*
+	 * Use FCHV to ignore kernel events if MSR.HV is set.
+	 */
+	if (mfmsr() & MSR_HV)
+		freeze_counters_kernel = MMCR0_FCHV;
+
+	return 0;
+}
+
+arch_initcall(init_perf_counters);
diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c
new file mode 100644
index 000000000000..07bd308a5fa7
--- /dev/null
+++ b/arch/powerpc/kernel/power4-pmu.c
@@ -0,0 +1,598 @@
+/*
+ * Performance counter support for POWER4 (GP) and POWER4+ (GQ) processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <asm/reg.h>
+
+/*
+ * Bits in event code for POWER4
+ */
+#define PM_PMC_SH	12	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_UNIT_SH	8	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_LOWER_SH	6
+#define PM_LOWER_MSK	1
+#define PM_LOWER_MSKS	0x40
+#define PM_BYTE_SH	4	/* Byte number of event bus to use */
+#define PM_BYTE_MSK	3
+#define PM_PMCSEL_MSK	7
+
+/*
+ * Unit code values
+ */
+#define PM_FPU		1
+#define PM_ISU1		2
+#define PM_IFU		3
+#define PM_IDU0		4
+#define PM_ISU1_ALT	6
+#define PM_ISU2		7
+#define PM_IFU_ALT	8
+#define PM_LSU0		9
+#define PM_LSU1		0xc
+#define PM_GPS		0xf
+
+/*
+ * Bits in MMCR0 for POWER4
+ */
+#define MMCR0_PMC1SEL_SH	8
+#define MMCR0_PMC2SEL_SH	1
+#define MMCR_PMCSEL_MSK		0x1f
+
+/*
+ * Bits in MMCR1 for POWER4
+ */
+#define MMCR1_TTM0SEL_SH	62
+#define MMCR1_TTC0SEL_SH	61
+#define MMCR1_TTM1SEL_SH	59
+#define MMCR1_TTC1SEL_SH	58
+#define MMCR1_TTM2SEL_SH	56
+#define MMCR1_TTC2SEL_SH	55
+#define MMCR1_TTM3SEL_SH	53
+#define MMCR1_TTC3SEL_SH	52
+#define MMCR1_TTMSEL_MSK	3
+#define MMCR1_TD_CP_DBG0SEL_SH	50
+#define MMCR1_TD_CP_DBG1SEL_SH	48
+#define MMCR1_TD_CP_DBG2SEL_SH	46
+#define MMCR1_TD_CP_DBG3SEL_SH	44
+#define MMCR1_DEBUG0SEL_SH	43
+#define MMCR1_DEBUG1SEL_SH	42
+#define MMCR1_DEBUG2SEL_SH	41
+#define MMCR1_DEBUG3SEL_SH	40
+#define MMCR1_PMC1_ADDER_SEL_SH	39
+#define MMCR1_PMC2_ADDER_SEL_SH	38
+#define MMCR1_PMC6_ADDER_SEL_SH	37
+#define MMCR1_PMC5_ADDER_SEL_SH	36
+#define MMCR1_PMC8_ADDER_SEL_SH	35
+#define MMCR1_PMC7_ADDER_SEL_SH	34
+#define MMCR1_PMC3_ADDER_SEL_SH	33
+#define MMCR1_PMC4_ADDER_SEL_SH	32
+#define MMCR1_PMC3SEL_SH	27
+#define MMCR1_PMC4SEL_SH	22
+#define MMCR1_PMC5SEL_SH	17
+#define MMCR1_PMC6SEL_SH	12
+#define MMCR1_PMC7SEL_SH	7
+#define MMCR1_PMC8SEL_SH	2	/* note bit 0 is in MMCRA for GP */
+
+static short mmcr1_adder_bits[8] = {
+	MMCR1_PMC1_ADDER_SEL_SH,
+	MMCR1_PMC2_ADDER_SEL_SH,
+	MMCR1_PMC3_ADDER_SEL_SH,
+	MMCR1_PMC4_ADDER_SEL_SH,
+	MMCR1_PMC5_ADDER_SEL_SH,
+	MMCR1_PMC6_ADDER_SEL_SH,
+	MMCR1_PMC7_ADDER_SEL_SH,
+	MMCR1_PMC8_ADDER_SEL_SH
+};
+
+/*
+ * Bits in MMCRA
+ */
+#define MMCRA_PMC8SEL0_SH	17	/* PMC8SEL bit 0 for GP */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *        |[  >[  >[   >|||[  >[  ><  ><  ><  ><  ><><><><><><><><>
+ *        | UC1 UC2 UC3 ||| PS1 PS2 B0  B1  B2  B3 P1P2P3P4P5P6P7P8
+ * 	  \SMPL	        ||\TTC3SEL
+ * 		        |\TTC_IFU_SEL
+ * 		        \TTM2SEL0
+ *
+ * SMPL - SAMPLE_ENABLE constraint
+ *     56: SAMPLE_ENABLE value 0x0100_0000_0000_0000
+ *
+ * UC1 - unit constraint 1: can't have all three of FPU/ISU1/IDU0|ISU2
+ *     55: UC1 error 0x0080_0000_0000_0000
+ *     54: FPU events needed 0x0040_0000_0000_0000
+ *     53: ISU1 events needed 0x0020_0000_0000_0000
+ *     52: IDU0|ISU2 events needed 0x0010_0000_0000_0000
+ *
+ * UC2 - unit constraint 2: can't have all three of FPU/IFU/LSU0
+ *     51: UC2 error 0x0008_0000_0000_0000
+ *     50: FPU events needed 0x0004_0000_0000_0000
+ *     49: IFU events needed 0x0002_0000_0000_0000
+ *     48: LSU0 events needed 0x0001_0000_0000_0000
+ *
+ * UC3 - unit constraint 3: can't have all four of LSU0/IFU/IDU0|ISU2/ISU1
+ *     47: UC3 error 0x8000_0000_0000
+ *     46: LSU0 events needed 0x4000_0000_0000
+ *     45: IFU events needed 0x2000_0000_0000
+ *     44: IDU0|ISU2 events needed 0x1000_0000_0000
+ *     43: ISU1 events needed 0x0800_0000_0000
+ *
+ * TTM2SEL0
+ *     42: 0 = IDU0 events needed
+ *     	   1 = ISU2 events needed 0x0400_0000_0000
+ *
+ * TTC_IFU_SEL
+ *     41: 0 = IFU.U events needed
+ *     	   1 = IFU.L events needed 0x0200_0000_0000
+ *
+ * TTC3SEL
+ *     40: 0 = LSU1.U events needed
+ *     	   1 = LSU1.L events needed 0x0100_0000_0000
+ *
+ * PS1
+ *     39: PS1 error 0x0080_0000_0000
+ *     36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000
+ *
+ * PS2
+ *     35: PS2 error 0x0008_0000_0000
+ *     32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000
+ *
+ * B0
+ *     28-31: Byte 0 event source 0xf000_0000
+ *     	   1 = FPU
+ * 	   2 = ISU1
+ * 	   3 = IFU
+ * 	   4 = IDU0
+ * 	   7 = ISU2
+ * 	   9 = LSU0
+ * 	   c = LSU1
+ * 	   f = GPS
+ *
+ * B1, B2, B3
+ *     24-27, 20-23, 16-19: Byte 1, 2, 3 event sources
+ *
+ * P8
+ *     15: P8 error 0x8000
+ *     14-15: Count of events needing PMC8
+ *
+ * P1..P7
+ *     0-13: Count of events needing PMC1..PMC7
+ *
+ * Note: this doesn't allow events using IFU.U to be combined with events
+ * using IFU.L, though that is feasible (using TTM0 and TTM2).  However
+ * there are no listed events for IFU.L (they are debug events not
+ * verified for performance monitoring) so this shouldn't cause a
+ * problem.
+ */
+
+static struct unitinfo {
+	u64	value, mask;
+	int	unit;
+	int	lowerbit;
+} p4_unitinfo[16] = {
+	[PM_FPU]  = { 0x44000000000000ull, 0x88000000000000ull, PM_FPU, 0 },
+	[PM_ISU1] = { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 },
+	[PM_ISU1_ALT] =
+		    { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 },
+	[PM_IFU]  = { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 },
+	[PM_IFU_ALT] =
+		    { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 },
+	[PM_IDU0] = { 0x10100000000000ull, 0x80840000000000ull, PM_IDU0, 1 },
+	[PM_ISU2] = { 0x10140000000000ull, 0x80840000000000ull, PM_ISU2, 0 },
+	[PM_LSU0] = { 0x01400000000000ull, 0x08800000000000ull, PM_LSU0, 0 },
+	[PM_LSU1] = { 0x00000000000000ull, 0x00010000000000ull, PM_LSU1, 40 },
+	[PM_GPS]  = { 0x00000000000000ull, 0x00000000000000ull, PM_GPS, 0 }
+};
+
+static unsigned char direct_marked_event[8] = {
+	(1<<2) | (1<<3),	/* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */
+	(1<<3) | (1<<5),	/* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */
+	(1<<3),			/* PMC3: PM_MRK_ST_CMPL_INT */
+	(1<<4) | (1<<5),	/* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */
+	(1<<4) | (1<<5),	/* PMC5: PM_MRK_GRP_TIMEO */
+	(1<<3) | (1<<4) | (1<<5),
+		/* PMC6: PM_MRK_ST_GPS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */
+	(1<<4) | (1<<5),	/* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */
+	(1<<4),			/* PMC8: PM_MRK_LSU_FIN */
+};
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int p4_marked_instr_event(u64 event)
+{
+	int pmc, psel, unit, byte, bit;
+	unsigned int mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if (pmc) {
+		if (direct_marked_event[pmc - 1] & (1 << psel))
+			return 1;
+		if (psel == 0)		/* add events */
+			bit = (pmc <= 4)? pmc - 1: 8 - pmc;
+		else if (psel == 6)	/* decode events */
+			bit = 4;
+		else
+			return 0;
+	} else
+		bit = psel;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	mask = 0;
+	switch (unit) {
+	case PM_LSU1:
+		if (event & PM_LOWER_MSKS)
+			mask = 1 << 28;		/* byte 7 bit 4 */
+		else
+			mask = 6 << 24;		/* byte 3 bits 1 and 2 */
+		break;
+	case PM_LSU0:
+		/* byte 3, bit 3; byte 2 bits 0,2,3,4,5; byte 1 */
+		mask = 0x083dff00;
+	}
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+static int p4_get_constraint(u64 event, u64 *maskp, u64 *valp)
+{
+	int pmc, byte, unit, lower, sh;
+	u64 mask = 0, value = 0;
+	int grp = -1;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 8)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		grp = ((pmc - 1) >> 1) & 1;
+	}
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	if (unit) {
+		lower = (event >> PM_LOWER_SH) & PM_LOWER_MSK;
+
+		/*
+		 * Bus events on bytes 0 and 2 can be counted
+		 * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8.
+		 */
+		if (!pmc)
+			grp = byte & 1;
+
+		if (!p4_unitinfo[unit].unit)
+			return -1;
+		mask  |= p4_unitinfo[unit].mask;
+		value |= p4_unitinfo[unit].value;
+		sh = p4_unitinfo[unit].lowerbit;
+		if (sh > 1)
+			value |= (u64)lower << sh;
+		else if (lower != sh)
+			return -1;
+		unit = p4_unitinfo[unit].unit;
+
+		/* Set byte lane select field */
+		mask  |= 0xfULL << (28 - 4 * byte);
+		value |= (u64)unit << (28 - 4 * byte);
+	}
+	if (grp == 0) {
+		/* increment PMC1/2/5/6 field */
+		mask  |= 0x8000000000ull;
+		value |= 0x1000000000ull;
+	} else {
+		/* increment PMC3/4/7/8 field */
+		mask  |= 0x800000000ull;
+		value |= 0x100000000ull;
+	}
+
+	/* Marked instruction events need sample_enable set */
+	if (p4_marked_instr_event(event)) {
+		mask  |= 1ull << 56;
+		value |= 1ull << 56;
+	}
+
+	/* PMCSEL=6 decode events on byte 2 need sample_enable clear */
+	if (pmc && (event & PM_PMCSEL_MSK) == 6 && byte == 2)
+		mask  |= 1ull << 56;
+
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static unsigned int ppc_inst_cmpl[] = {
+	0x1001, 0x4001, 0x6001, 0x7001, 0x8001
+};
+
+static int p4_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, na;
+
+	alt[0] = event;
+	na = 1;
+
+	/* 2 possibilities for PM_GRP_DISP_REJECT */
+	if (event == 0x8003 || event == 0x0224) {
+		alt[1] = event ^ (0x8003 ^ 0x0224);
+		return 2;
+	}
+
+	/* 2 possibilities for PM_ST_MISS_L1 */
+	if (event == 0x0c13 || event == 0x0c23) {
+		alt[1] = event ^ (0x0c13 ^ 0x0c23);
+		return 2;
+	}
+
+	/* several possibilities for PM_INST_CMPL */
+	for (i = 0; i < ARRAY_SIZE(ppc_inst_cmpl); ++i) {
+		if (event == ppc_inst_cmpl[i]) {
+			for (j = 0; j < ARRAY_SIZE(ppc_inst_cmpl); ++j)
+				if (j != i)
+					alt[na++] = ppc_inst_cmpl[j];
+			break;
+		}
+	}
+
+	return na;
+}
+
+static int p4_compute_mmcr(u64 event[], int n_ev,
+			   unsigned int hwc[], u64 mmcr[])
+{
+	u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0;
+	unsigned int pmc, unit, byte, psel, lower;
+	unsigned int ttm, grp;
+	unsigned int pmc_inuse = 0;
+	unsigned int pmc_grp_use[2];
+	unsigned char busbyte[4];
+	unsigned char unituse[16];
+	unsigned int unitlower = 0;
+	int i;
+
+	if (n_ev > 8)
+		return -1;
+
+	/* First pass to count resource use */
+	pmc_grp_use[0] = pmc_grp_use[1] = 0;
+	memset(busbyte, 0, sizeof(busbyte));
+	memset(unituse, 0, sizeof(unituse));
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+			/* count 1/2/5/6 vs 3/4/7/8 use */
+			++pmc_grp_use[((pmc - 1) >> 1) & 1];
+		}
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		lower = (event[i] >> PM_LOWER_SH) & PM_LOWER_MSK;
+		if (unit) {
+			if (!pmc)
+				++pmc_grp_use[byte & 1];
+			if (unit == 6 || unit == 8)
+				/* map alt ISU1/IFU codes: 6->2, 8->3 */
+				unit = (unit >> 1) - 1;
+			if (busbyte[byte] && busbyte[byte] != unit)
+				return -1;
+			busbyte[byte] = unit;
+			lower <<= unit;
+			if (unituse[unit] && lower != (unitlower & lower))
+				return -1;
+			unituse[unit] = 1;
+			unitlower |= lower;
+		}
+	}
+	if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4)
+		return -1;
+
+	/*
+	 * Assign resources and set multiplexer selects.
+	 *
+	 * Units 1,2,3 are on TTM0, 4,6,7 on TTM1, 8,10 on TTM2.
+	 * Each TTMx can only select one unit, but since
+	 * units 2 and 6 are both ISU1, and 3 and 8 are both IFU,
+	 * we have some choices.
+	 */
+	if (unituse[2] & (unituse[1] | (unituse[3] & unituse[9]))) {
+		unituse[6] = 1;		/* Move 2 to 6 */
+		unituse[2] = 0;
+	}
+	if (unituse[3] & (unituse[1] | unituse[2])) {
+		unituse[8] = 1;		/* Move 3 to 8 */
+		unituse[3] = 0;
+		unitlower = (unitlower & ~8) | ((unitlower & 8) << 5);
+	}
+	/* Check only one unit per TTMx */
+	if (unituse[1] + unituse[2] + unituse[3] > 1 ||
+	    unituse[4] + unituse[6] + unituse[7] > 1 ||
+	    unituse[8] + unituse[9] > 1 ||
+	    (unituse[5] | unituse[10] | unituse[11] |
+	     unituse[13] | unituse[14]))
+		return -1;
+
+	/* Set TTMxSEL fields.  Note, units 1-3 => TTM0SEL codes 0-2 */
+	mmcr1 |= (u64)(unituse[3] * 2 + unituse[2]) << MMCR1_TTM0SEL_SH;
+	mmcr1 |= (u64)(unituse[7] * 3 + unituse[6] * 2) << MMCR1_TTM1SEL_SH;
+	mmcr1 |= (u64)unituse[9] << MMCR1_TTM2SEL_SH;
+
+	/* Set TTCxSEL fields. */
+	if (unitlower & 0xe)
+		mmcr1 |= 1ull << MMCR1_TTC0SEL_SH;
+	if (unitlower & 0xf0)
+		mmcr1 |= 1ull << MMCR1_TTC1SEL_SH;
+	if (unitlower & 0xf00)
+		mmcr1 |= 1ull << MMCR1_TTC2SEL_SH;
+	if (unitlower & 0x7000)
+		mmcr1 |= 1ull << MMCR1_TTC3SEL_SH;
+
+	/* Set byte lane select fields. */
+	for (byte = 0; byte < 4; ++byte) {
+		unit = busbyte[byte];
+		if (!unit)
+			continue;
+		if (unit == 0xf) {
+			/* special case for GPS */
+			mmcr1 |= 1ull << (MMCR1_DEBUG0SEL_SH - byte);
+		} else {
+			if (!unituse[unit])
+				ttm = unit - 1;		/* 2->1, 3->2 */
+			else
+				ttm = unit >> 2;
+			mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2*byte);
+		}
+	}
+
+	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		if (!pmc) {
+			/* Bus event or 00xxx direct event (off or cycles) */
+			if (unit)
+				psel |= 0x10 | ((byte & 2) << 2);
+			for (pmc = 0; pmc < 8; ++pmc) {
+				if (pmc_inuse & (1 << pmc))
+					continue;
+				grp = (pmc >> 1) & 1;
+				if (unit) {
+					if (grp == (byte & 1))
+						break;
+				} else if (pmc_grp_use[grp] < 4) {
+					++pmc_grp_use[grp];
+					break;
+				}
+			}
+			pmc_inuse |= 1 << pmc;
+		} else {
+			/* Direct event */
+			--pmc;
+			if (psel == 0 && (byte & 2))
+				/* add events on higher-numbered bus */
+				mmcr1 |= 1ull << mmcr1_adder_bits[pmc];
+			else if (psel == 6 && byte == 3)
+				/* seem to need to set sample_enable here */
+				mmcra |= MMCRA_SAMPLE_ENABLE;
+			psel |= 8;
+		}
+		if (pmc <= 1)
+			mmcr0 |= psel << (MMCR0_PMC1SEL_SH - 7 * pmc);
+		else
+			mmcr1 |= psel << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
+		if (pmc == 7)	/* PMC8 */
+			mmcra |= (psel & 1) << MMCRA_PMC8SEL0_SH;
+		hwc[i] = pmc;
+		if (p4_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+	}
+
+	if (pmc_inuse & 1)
+		mmcr0 |= MMCR0_PMC1CE;
+	if (pmc_inuse & 0xfe)
+		mmcr0 |= MMCR0_PMCjCE;
+
+	mmcra |= 0x2000;	/* mark only one IOP per PPC instruction */
+
+	/* Return MMCRx values */
+	mmcr[0] = mmcr0;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void p4_disable_pmc(unsigned int pmc, u64 mmcr[])
+{
+	/*
+	 * Setting the PMCxSEL field to 0 disables PMC x.
+	 * (Note that pmc is 0-based here, not 1-based.)
+	 */
+	if (pmc <= 1) {
+		mmcr[0] &= ~(0x1fUL << (MMCR0_PMC1SEL_SH - 7 * pmc));
+	} else {
+		mmcr[1] &= ~(0x1fUL << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)));
+		if (pmc == 7)
+			mmcr[2] &= ~(1UL << MMCRA_PMC8SEL0_SH);
+	}
+}
+
+static int p4_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 7,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x1001,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x8c10, /* PM_LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x3c10, /* PM_LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x330,  /* PM_BR_ISSUED */
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x331,  /* PM_BR_MPRED_CR */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x8c10,		0x3c10	},
+		[C(OP_WRITE)] = {	0x7c10,		0xc13	},
+		[C(OP_PREFETCH)] = {	0xc35,		0	},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	0,		0	},
+		[C(OP_PREFETCH)] = {	0xc34,		0	},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x904	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x900	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x330,		0x331	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+struct power_pmu power4_pmu = {
+	.n_counter = 8,
+	.max_alternatives = 5,
+	.add_fields = 0x0000001100005555ull,
+	.test_adder = 0x0011083300000000ull,
+	.compute_mmcr = p4_compute_mmcr,
+	.get_constraint = p4_get_constraint,
+	.get_alternatives = p4_get_alternatives,
+	.disable_pmc = p4_disable_pmc,
+	.n_generic = ARRAY_SIZE(p4_generic_events),
+	.generic_events = p4_generic_events,
+	.cache_events = &power4_cache_events,
+};
diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c
new file mode 100644
index 000000000000..41e5d2d958d4
--- /dev/null
+++ b/arch/powerpc/kernel/power5+-pmu.c
@@ -0,0 +1,671 @@
+/*
+ * Performance counter support for POWER5+/++ (not POWER5) processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <asm/reg.h>
+
+/*
+ * Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3)
+ */
+#define PM_PMC_SH	20	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_PMC_MSKS	(PM_PMC_MSK << PM_PMC_SH)
+#define PM_UNIT_SH	16	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_BYTE_SH	12	/* Byte number of event bus to use */
+#define PM_BYTE_MSK	7
+#define PM_GRS_SH	8	/* Storage subsystem mux select */
+#define PM_GRS_MSK	7
+#define PM_BUSEVENT_MSK	0x80	/* Set if event uses event bus */
+#define PM_PMCSEL_MSK	0x7f
+
+/* Values in PM_UNIT field */
+#define PM_FPU		0
+#define PM_ISU0		1
+#define PM_IFU		2
+#define PM_ISU1		3
+#define PM_IDU		4
+#define PM_ISU0_ALT	6
+#define PM_GRS		7
+#define PM_LSU0		8
+#define PM_LSU1		0xc
+#define PM_LASTUNIT	0xc
+
+/*
+ * Bits in MMCR1 for POWER5+
+ */
+#define MMCR1_TTM0SEL_SH	62
+#define MMCR1_TTM1SEL_SH	60
+#define MMCR1_TTM2SEL_SH	58
+#define MMCR1_TTM3SEL_SH	56
+#define MMCR1_TTMSEL_MSK	3
+#define MMCR1_TD_CP_DBG0SEL_SH	54
+#define MMCR1_TD_CP_DBG1SEL_SH	52
+#define MMCR1_TD_CP_DBG2SEL_SH	50
+#define MMCR1_TD_CP_DBG3SEL_SH	48
+#define MMCR1_GRS_L2SEL_SH	46
+#define MMCR1_GRS_L2SEL_MSK	3
+#define MMCR1_GRS_L3SEL_SH	44
+#define MMCR1_GRS_L3SEL_MSK	3
+#define MMCR1_GRS_MCSEL_SH	41
+#define MMCR1_GRS_MCSEL_MSK	7
+#define MMCR1_GRS_FABSEL_SH	39
+#define MMCR1_GRS_FABSEL_MSK	3
+#define MMCR1_PMC1_ADDER_SEL_SH	35
+#define MMCR1_PMC2_ADDER_SEL_SH	34
+#define MMCR1_PMC3_ADDER_SEL_SH	33
+#define MMCR1_PMC4_ADDER_SEL_SH	32
+#define MMCR1_PMC1SEL_SH	25
+#define MMCR1_PMC2SEL_SH	17
+#define MMCR1_PMC3SEL_SH	9
+#define MMCR1_PMC4SEL_SH	1
+#define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
+#define MMCR1_PMCSEL_MSK	0x7f
+
+/*
+ * Bits in MMCRA
+ */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *             [  ><><>< ><> <><>[  >  <  ><  ><  ><  ><><><><><><>
+ *             NC  G0G1G2 G3 T0T1 UC    B0  B1  B2  B3 P6P5P4P3P2P1
+ *
+ * NC - number of counters
+ *     51: NC error 0x0008_0000_0000_0000
+ *     48-50: number of events needing PMC1-4 0x0007_0000_0000_0000
+ *
+ * G0..G3 - GRS mux constraints
+ *     46-47: GRS_L2SEL value
+ *     44-45: GRS_L3SEL value
+ *     41-44: GRS_MCSEL value
+ *     39-40: GRS_FABSEL value
+ *	Note that these match up with their bit positions in MMCR1
+ *
+ * T0 - TTM0 constraint
+ *     36-37: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0x30_0000_0000
+ *
+ * T1 - TTM1 constraint
+ *     34-35: TTM1SEL value (0=IDU, 3=GRS) 0x0c_0000_0000
+ *
+ * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS
+ *     33: UC3 error 0x02_0000_0000
+ *     32: FPU|IFU|ISU1 events needed 0x01_0000_0000
+ *     31: ISU0 events needed 0x01_8000_0000
+ *     30: IDU|GRS events needed 0x00_4000_0000
+ *
+ * B0
+ *     24-27: Byte 0 event source 0x0f00_0000
+ *	      Encoding as for the event code
+ *
+ * B1, B2, B3
+ *     20-23, 16-19, 12-15: Byte 1, 2, 3 event sources
+ *
+ * P6
+ *     11: P6 error 0x800
+ *     10-11: Count of events needing PMC6
+ *
+ * P1..P5
+ *     0-9: Count of events needing PMC1..PMC5
+ */
+
+static const int grsel_shift[8] = {
+	MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH,
+	MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH,
+	MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH
+};
+
+/* Masks and values for using events from the various units */
+static u64 unit_cons[PM_LASTUNIT+1][2] = {
+	[PM_FPU] =   { 0x3200000000ull, 0x0100000000ull },
+	[PM_ISU0] =  { 0x0200000000ull, 0x0080000000ull },
+	[PM_ISU1] =  { 0x3200000000ull, 0x3100000000ull },
+	[PM_IFU] =   { 0x3200000000ull, 0x2100000000ull },
+	[PM_IDU] =   { 0x0e00000000ull, 0x0040000000ull },
+	[PM_GRS] =   { 0x0e00000000ull, 0x0c40000000ull },
+};
+
+static int power5p_get_constraint(u64 event, u64 *maskp, u64 *valp)
+{
+	int pmc, byte, unit, sh;
+	int bit, fmask;
+	u64 mask = 0, value = 0;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 6)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		if (pmc >= 5 && !(event == 0x500009 || event == 0x600005))
+			return -1;
+	}
+	if (event & PM_BUSEVENT_MSK) {
+		unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+		if (unit > PM_LASTUNIT)
+			return -1;
+		if (unit == PM_ISU0_ALT)
+			unit = PM_ISU0;
+		mask |= unit_cons[unit][0];
+		value |= unit_cons[unit][1];
+		byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+		if (byte >= 4) {
+			if (unit != PM_LSU1)
+				return -1;
+			/* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */
+			++unit;
+			byte &= 3;
+		}
+		if (unit == PM_GRS) {
+			bit = event & 7;
+			fmask = (bit == 6)? 7: 3;
+			sh = grsel_shift[bit];
+			mask |= (u64)fmask << sh;
+			value |= (u64)((event >> PM_GRS_SH) & fmask) << sh;
+		}
+		/* Set byte lane select field */
+		mask  |= 0xfULL << (24 - 4 * byte);
+		value |= (u64)unit << (24 - 4 * byte);
+	}
+	if (pmc < 5) {
+		/* need a counter from PMC1-4 set */
+		mask  |= 0x8000000000000ull;
+		value |= 0x1000000000000ull;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static int power5p_limited_pmc_event(u64 event)
+{
+	int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+
+	return pmc == 5 || pmc == 6;
+}
+
+#define MAX_ALT	3	/* at most 3 alternatives for any event */
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x100c0,  0x40001f },			/* PM_GCT_FULL_CYC */
+	{ 0x120e4,  0x400002 },			/* PM_GRP_DISP_REJECT */
+	{ 0x230e2,  0x323087 },			/* PM_BR_PRED_CR */
+	{ 0x230e3,  0x223087, 0x3230a0 },	/* PM_BR_PRED_TA */
+	{ 0x410c7,  0x441084 },			/* PM_THRD_L2MISS_BOTH_CYC */
+	{ 0x800c4,  0xc20e0 },			/* PM_DTLB_MISS */
+	{ 0xc50c6,  0xc60e0 },			/* PM_MRK_DTLB_MISS */
+	{ 0x100005, 0x600005 },			/* PM_RUN_CYC */
+	{ 0x100009, 0x200009 },			/* PM_INST_CMPL */
+	{ 0x200015, 0x300015 },			/* PM_LSU_LMQ_SRQ_EMPTY_CYC */
+	{ 0x300009, 0x400009 },			/* PM_INST_DISP */
+};
+
+/*
+ * Scan the alternatives table for a match and return the
+ * index into the alternatives table if found, else -1.
+ */
+static int find_alternative(unsigned int event)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			break;
+		for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
+			if (event == event_alternatives[i][j])
+				return i;
+	}
+	return -1;
+}
+
+static const unsigned char bytedecode_alternatives[4][4] = {
+	/* PMC 1 */	{ 0x21, 0x23, 0x25, 0x27 },
+	/* PMC 2 */	{ 0x07, 0x17, 0x0e, 0x1e },
+	/* PMC 3 */	{ 0x20, 0x22, 0x24, 0x26 },
+	/* PMC 4 */	{ 0x07, 0x17, 0x0e, 0x1e }
+};
+
+/*
+ * Some direct events for decodes of event bus byte 3 have alternative
+ * PMCSEL values on other counters.  This returns the alternative
+ * event code for those that do, or -1 otherwise.  This also handles
+ * alternative PCMSEL values for add events.
+ */
+static s64 find_alternative_bdecode(u64 event)
+{
+	int pmc, altpmc, pp, j;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc == 0 || pmc > 4)
+		return -1;
+	altpmc = 5 - pmc;	/* 1 <-> 4, 2 <-> 3 */
+	pp = event & PM_PMCSEL_MSK;
+	for (j = 0; j < 4; ++j) {
+		if (bytedecode_alternatives[pmc - 1][j] == pp) {
+			return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) |
+				(altpmc << PM_PMC_SH) |
+				bytedecode_alternatives[altpmc - 1][j];
+		}
+	}
+
+	/* new decode alternatives for power5+ */
+	if (pmc == 1 && (pp == 0x0d || pp == 0x0e))
+		return event + (2 << PM_PMC_SH) + (0x2e - 0x0d);
+	if (pmc == 3 && (pp == 0x2e || pp == 0x2f))
+		return event - (2 << PM_PMC_SH) - (0x2e - 0x0d);
+
+	/* alternative add event encodings */
+	if (pp == 0x10 || pp == 0x28)
+		return ((event ^ (0x10 ^ 0x28)) & ~PM_PMC_MSKS) |
+			(altpmc << PM_PMC_SH);
+
+	return -1;
+}
+
+static int power5p_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nalt = 1;
+	int nlim;
+	s64 ae;
+
+	alt[0] = event;
+	nalt = 1;
+	nlim = power5p_limited_pmc_event(event);
+	i = find_alternative(event);
+	if (i >= 0) {
+		for (j = 0; j < MAX_ALT; ++j) {
+			ae = event_alternatives[i][j];
+			if (ae && ae != event)
+				alt[nalt++] = ae;
+			nlim += power5p_limited_pmc_event(ae);
+		}
+	} else {
+		ae = find_alternative_bdecode(event);
+		if (ae > 0)
+			alt[nalt++] = ae;
+	}
+
+	if (flags & PPMU_ONLY_COUNT_RUN) {
+		/*
+		 * We're only counting in RUN state,
+		 * so PM_CYC is equivalent to PM_RUN_CYC
+		 * and PM_INST_CMPL === PM_RUN_INST_CMPL.
+		 * This doesn't include alternatives that don't provide
+		 * any extra flexibility in assigning PMCs (e.g.
+		 * 0x100005 for PM_RUN_CYC vs. 0xf for PM_CYC).
+		 * Note that even with these additional alternatives
+		 * we never end up with more than 3 alternatives for any event.
+		 */
+		j = nalt;
+		for (i = 0; i < nalt; ++i) {
+			switch (alt[i]) {
+			case 0xf:	/* PM_CYC */
+				alt[j++] = 0x600005;	/* PM_RUN_CYC */
+				++nlim;
+				break;
+			case 0x600005:	/* PM_RUN_CYC */
+				alt[j++] = 0xf;
+				break;
+			case 0x100009:	/* PM_INST_CMPL */
+				alt[j++] = 0x500009;	/* PM_RUN_INST_CMPL */
+				++nlim;
+				break;
+			case 0x500009:	/* PM_RUN_INST_CMPL */
+				alt[j++] = 0x100009;	/* PM_INST_CMPL */
+				alt[j++] = 0x200009;
+				break;
+			}
+		}
+		nalt = j;
+	}
+
+	if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) {
+		/* remove the limited PMC events */
+		j = 0;
+		for (i = 0; i < nalt; ++i) {
+			if (!power5p_limited_pmc_event(alt[i])) {
+				alt[j] = alt[i];
+				++j;
+			}
+		}
+		nalt = j;
+	} else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) {
+		/* remove all but the limited PMC events */
+		j = 0;
+		for (i = 0; i < nalt; ++i) {
+			if (power5p_limited_pmc_event(alt[i])) {
+				alt[j] = alt[i];
+				++j;
+			}
+		}
+		nalt = j;
+	}
+
+	return nalt;
+}
+
+/*
+ * Map of which direct events on which PMCs are marked instruction events.
+ * Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event.
+ * Bit 0 is set if it is marked for all PMCs.
+ * The 0x80 bit indicates a byte decode PMCSEL value.
+ */
+static unsigned char direct_event_is_marked[0x28] = {
+	0,	/* 00 */
+	0x1f,	/* 01 PM_IOPS_CMPL */
+	0x2,	/* 02 PM_MRK_GRP_DISP */
+	0xe,	/* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */
+	0,	/* 04 */
+	0x1c,	/* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */
+	0x80,	/* 06 */
+	0x80,	/* 07 */
+	0, 0, 0,/* 08 - 0a */
+	0x18,	/* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */
+	0,	/* 0c */
+	0x80,	/* 0d */
+	0x80,	/* 0e */
+	0,	/* 0f */
+	0,	/* 10 */
+	0x14,	/* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */
+	0,	/* 12 */
+	0x10,	/* 13 PM_MRK_GRP_CMPL */
+	0x1f,	/* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */
+	0x2,	/* 15 PM_MRK_GRP_ISSUED */
+	0x80,	/* 16 */
+	0x80,	/* 17 */
+	0, 0, 0, 0, 0,
+	0x80,	/* 1d */
+	0x80,	/* 1e */
+	0,	/* 1f */
+	0x80,	/* 20 */
+	0x80,	/* 21 */
+	0x80,	/* 22 */
+	0x80,	/* 23 */
+	0x80,	/* 24 */
+	0x80,	/* 25 */
+	0x80,	/* 26 */
+	0x80,	/* 27 */
+};
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int power5p_marked_instr_event(u64 event)
+{
+	int pmc, psel;
+	int bit, byte, unit;
+	u32 mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if (pmc >= 5)
+		return 0;
+
+	bit = -1;
+	if (psel < sizeof(direct_event_is_marked)) {
+		if (direct_event_is_marked[psel] & (1 << pmc))
+			return 1;
+		if (direct_event_is_marked[psel] & 0x80)
+			bit = 4;
+		else if (psel == 0x08)
+			bit = pmc - 1;
+		else if (psel == 0x10)
+			bit = 4 - pmc;
+		else if (psel == 0x1b && (pmc == 1 || pmc == 3))
+			bit = 4;
+	} else if ((psel & 0x48) == 0x40) {
+		bit = psel & 7;
+	} else if (psel == 0x28) {
+		bit = pmc - 1;
+	} else if (pmc == 3 && (psel == 0x2e || psel == 0x2f)) {
+		bit = 4;
+	}
+
+	if (!(event & PM_BUSEVENT_MSK) || bit == -1)
+		return 0;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	if (unit == PM_LSU0) {
+		/* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */
+		mask = 0x5dff00;
+	} else if (unit == PM_LSU1 && byte >= 4) {
+		byte -= 4;
+		/* byte 5 bits 6-7, byte 6 bits 0,4, byte 7 bits 0-4,6 */
+		mask = 0x5f11c000;
+	} else
+		return 0;
+
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+static int power5p_compute_mmcr(u64 event[], int n_ev,
+				unsigned int hwc[], u64 mmcr[])
+{
+	u64 mmcr1 = 0;
+	u64 mmcra = 0;
+	unsigned int pmc, unit, byte, psel;
+	unsigned int ttm;
+	int i, isbus, bit, grsel;
+	unsigned int pmc_inuse = 0;
+	unsigned char busbyte[4];
+	unsigned char unituse[16];
+	int ttmuse;
+
+	if (n_ev > 6)
+		return -1;
+
+	/* First pass to count resource use */
+	memset(busbyte, 0, sizeof(busbyte));
+	memset(unituse, 0, sizeof(unituse));
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc > 6)
+				return -1;
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+		}
+		if (event[i] & PM_BUSEVENT_MSK) {
+			unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+			byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+			if (unit > PM_LASTUNIT)
+				return -1;
+			if (unit == PM_ISU0_ALT)
+				unit = PM_ISU0;
+			if (byte >= 4) {
+				if (unit != PM_LSU1)
+					return -1;
+				++unit;
+				byte &= 3;
+			}
+			if (busbyte[byte] && busbyte[byte] != unit)
+				return -1;
+			busbyte[byte] = unit;
+			unituse[unit] = 1;
+		}
+	}
+
+	/*
+	 * Assign resources and set multiplexer selects.
+	 *
+	 * PM_ISU0 can go either on TTM0 or TTM1, but that's the only
+	 * choice we have to deal with.
+	 */
+	if (unituse[PM_ISU0] &
+	    (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) {
+		unituse[PM_ISU0_ALT] = 1;	/* move ISU to TTM1 */
+		unituse[PM_ISU0] = 0;
+	}
+	/* Set TTM[01]SEL fields. */
+	ttmuse = 0;
+	for (i = PM_FPU; i <= PM_ISU1; ++i) {
+		if (!unituse[i])
+			continue;
+		if (ttmuse++)
+			return -1;
+		mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH;
+	}
+	ttmuse = 0;
+	for (; i <= PM_GRS; ++i) {
+		if (!unituse[i])
+			continue;
+		if (ttmuse++)
+			return -1;
+		mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH;
+	}
+	if (ttmuse > 1)
+		return -1;
+
+	/* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */
+	for (byte = 0; byte < 4; ++byte) {
+		unit = busbyte[byte];
+		if (!unit)
+			continue;
+		if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) {
+			/* get ISU0 through TTM1 rather than TTM0 */
+			unit = PM_ISU0_ALT;
+		} else if (unit == PM_LSU1 + 1) {
+			/* select lower word of LSU1 for this byte */
+			mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
+		}
+		ttm = unit >> 2;
+		mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+	}
+
+	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		isbus = event[i] & PM_BUSEVENT_MSK;
+		if (!pmc) {
+			/* Bus event or any-PMC direct event */
+			for (pmc = 0; pmc < 4; ++pmc) {
+				if (!(pmc_inuse & (1 << pmc)))
+					break;
+			}
+			if (pmc >= 4)
+				return -1;
+			pmc_inuse |= 1 << pmc;
+		} else if (pmc <= 4) {
+			/* Direct event */
+			--pmc;
+			if (isbus && (byte & 2) &&
+			    (psel == 8 || psel == 0x10 || psel == 0x28))
+				/* add events on higher-numbered bus */
+				mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
+		} else {
+			/* Instructions or run cycles on PMC5/6 */
+			--pmc;
+		}
+		if (isbus && unit == PM_GRS) {
+			bit = psel & 7;
+			grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK;
+			mmcr1 |= (u64)grsel << grsel_shift[bit];
+		}
+		if (power5p_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+		if ((psel & 0x58) == 0x40 && (byte & 1) != ((pmc >> 1) & 1))
+			/* select alternate byte lane */
+			psel |= 0x10;
+		if (pmc <= 3)
+			mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
+		hwc[i] = pmc;
+	}
+
+	/* Return MMCRx values */
+	mmcr[0] = 0;
+	if (pmc_inuse & 1)
+		mmcr[0] = MMCR0_PMC1CE;
+	if (pmc_inuse & 0x3e)
+		mmcr[0] |= MMCR0_PMCjCE;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void power5p_disable_pmc(unsigned int pmc, u64 mmcr[])
+{
+	if (pmc <= 3)
+		mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
+}
+
+static int power5p_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0xf,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x100009,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x1c10a8, /* LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x3c1088, /* LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x230e4,  /* BR_ISSUED */
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x230e5,  /* BR_MPRED_CR */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x1c10a8,	0x3c1088	},
+		[C(OP_WRITE)] = {	0x2c10a8,	0xc10c3		},
+		[C(OP_PREFETCH)] = {	0xc70e7,	-1		},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	0,		0		},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0		},
+		[C(OP_WRITE)] = {	0,		0		},
+		[C(OP_PREFETCH)] = {	0xc50c3,	0		},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0xc20e4,	0x800c4		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x800c0		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x230e4,	0x230e5		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+};
+
+struct power_pmu power5p_pmu = {
+	.n_counter = 6,
+	.max_alternatives = MAX_ALT,
+	.add_fields = 0x7000000000055ull,
+	.test_adder = 0x3000040000000ull,
+	.compute_mmcr = power5p_compute_mmcr,
+	.get_constraint = power5p_get_constraint,
+	.get_alternatives = power5p_get_alternatives,
+	.disable_pmc = power5p_disable_pmc,
+	.limited_pmc_event = power5p_limited_pmc_event,
+	.flags = PPMU_LIMITED_PMC5_6,
+	.n_generic = ARRAY_SIZE(power5p_generic_events),
+	.generic_events = power5p_generic_events,
+	.cache_events = &power5p_cache_events,
+};
diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c
new file mode 100644
index 000000000000..05600b66221a
--- /dev/null
+++ b/arch/powerpc/kernel/power5-pmu.c
@@ -0,0 +1,611 @@
+/*
+ * Performance counter support for POWER5 (not POWER5++) processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <asm/reg.h>
+
+/*
+ * Bits in event code for POWER5 (not POWER5++)
+ */
+#define PM_PMC_SH	20	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_PMC_MSKS	(PM_PMC_MSK << PM_PMC_SH)
+#define PM_UNIT_SH	16	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_BYTE_SH	12	/* Byte number of event bus to use */
+#define PM_BYTE_MSK	7
+#define PM_GRS_SH	8	/* Storage subsystem mux select */
+#define PM_GRS_MSK	7
+#define PM_BUSEVENT_MSK	0x80	/* Set if event uses event bus */
+#define PM_PMCSEL_MSK	0x7f
+
+/* Values in PM_UNIT field */
+#define PM_FPU		0
+#define PM_ISU0		1
+#define PM_IFU		2
+#define PM_ISU1		3
+#define PM_IDU		4
+#define PM_ISU0_ALT	6
+#define PM_GRS		7
+#define PM_LSU0		8
+#define PM_LSU1		0xc
+#define PM_LASTUNIT	0xc
+
+/*
+ * Bits in MMCR1 for POWER5
+ */
+#define MMCR1_TTM0SEL_SH	62
+#define MMCR1_TTM1SEL_SH	60
+#define MMCR1_TTM2SEL_SH	58
+#define MMCR1_TTM3SEL_SH	56
+#define MMCR1_TTMSEL_MSK	3
+#define MMCR1_TD_CP_DBG0SEL_SH	54
+#define MMCR1_TD_CP_DBG1SEL_SH	52
+#define MMCR1_TD_CP_DBG2SEL_SH	50
+#define MMCR1_TD_CP_DBG3SEL_SH	48
+#define MMCR1_GRS_L2SEL_SH	46
+#define MMCR1_GRS_L2SEL_MSK	3
+#define MMCR1_GRS_L3SEL_SH	44
+#define MMCR1_GRS_L3SEL_MSK	3
+#define MMCR1_GRS_MCSEL_SH	41
+#define MMCR1_GRS_MCSEL_MSK	7
+#define MMCR1_GRS_FABSEL_SH	39
+#define MMCR1_GRS_FABSEL_MSK	3
+#define MMCR1_PMC1_ADDER_SEL_SH	35
+#define MMCR1_PMC2_ADDER_SEL_SH	34
+#define MMCR1_PMC3_ADDER_SEL_SH	33
+#define MMCR1_PMC4_ADDER_SEL_SH	32
+#define MMCR1_PMC1SEL_SH	25
+#define MMCR1_PMC2SEL_SH	17
+#define MMCR1_PMC3SEL_SH	9
+#define MMCR1_PMC4SEL_SH	1
+#define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
+#define MMCR1_PMCSEL_MSK	0x7f
+
+/*
+ * Bits in MMCRA
+ */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *         <><>[  ><><>< ><> [  >[ >[ ><  ><  ><  ><  ><><><><><><>
+ *         T0T1 NC G0G1G2 G3  UC PS1PS2 B0  B1  B2  B3 P6P5P4P3P2P1
+ *
+ * T0 - TTM0 constraint
+ *     54-55: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0xc0_0000_0000_0000
+ *
+ * T1 - TTM1 constraint
+ *     52-53: TTM1SEL value (0=IDU, 3=GRS) 0x30_0000_0000_0000
+ *
+ * NC - number of counters
+ *     51: NC error 0x0008_0000_0000_0000
+ *     48-50: number of events needing PMC1-4 0x0007_0000_0000_0000
+ *
+ * G0..G3 - GRS mux constraints
+ *     46-47: GRS_L2SEL value
+ *     44-45: GRS_L3SEL value
+ *     41-44: GRS_MCSEL value
+ *     39-40: GRS_FABSEL value
+ *	Note that these match up with their bit positions in MMCR1
+ *
+ * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS
+ *     37: UC3 error 0x20_0000_0000
+ *     36: FPU|IFU|ISU1 events needed 0x10_0000_0000
+ *     35: ISU0 events needed 0x08_0000_0000
+ *     34: IDU|GRS events needed 0x04_0000_0000
+ *
+ * PS1
+ *     33: PS1 error 0x2_0000_0000
+ *     31-32: count of events needing PMC1/2 0x1_8000_0000
+ *
+ * PS2
+ *     30: PS2 error 0x4000_0000
+ *     28-29: count of events needing PMC3/4 0x3000_0000
+ *
+ * B0
+ *     24-27: Byte 0 event source 0x0f00_0000
+ *	      Encoding as for the event code
+ *
+ * B1, B2, B3
+ *     20-23, 16-19, 12-15: Byte 1, 2, 3 event sources
+ *
+ * P1..P6
+ *     0-11: Count of events needing PMC1..PMC6
+ */
+
+static const int grsel_shift[8] = {
+	MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH,
+	MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH,
+	MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH
+};
+
+/* Masks and values for using events from the various units */
+static u64 unit_cons[PM_LASTUNIT+1][2] = {
+	[PM_FPU] =   { 0xc0002000000000ull, 0x00001000000000ull },
+	[PM_ISU0] =  { 0x00002000000000ull, 0x00000800000000ull },
+	[PM_ISU1] =  { 0xc0002000000000ull, 0xc0001000000000ull },
+	[PM_IFU] =   { 0xc0002000000000ull, 0x80001000000000ull },
+	[PM_IDU] =   { 0x30002000000000ull, 0x00000400000000ull },
+	[PM_GRS] =   { 0x30002000000000ull, 0x30000400000000ull },
+};
+
+static int power5_get_constraint(u64 event, u64 *maskp, u64 *valp)
+{
+	int pmc, byte, unit, sh;
+	int bit, fmask;
+	u64 mask = 0, value = 0;
+	int grp = -1;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 6)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		if (pmc <= 4)
+			grp = (pmc - 1) >> 1;
+		else if (event != 0x500009 && event != 0x600005)
+			return -1;
+	}
+	if (event & PM_BUSEVENT_MSK) {
+		unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+		if (unit > PM_LASTUNIT)
+			return -1;
+		if (unit == PM_ISU0_ALT)
+			unit = PM_ISU0;
+		mask |= unit_cons[unit][0];
+		value |= unit_cons[unit][1];
+		byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+		if (byte >= 4) {
+			if (unit != PM_LSU1)
+				return -1;
+			/* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */
+			++unit;
+			byte &= 3;
+		}
+		if (unit == PM_GRS) {
+			bit = event & 7;
+			fmask = (bit == 6)? 7: 3;
+			sh = grsel_shift[bit];
+			mask |= (u64)fmask << sh;
+			value |= (u64)((event >> PM_GRS_SH) & fmask) << sh;
+		}
+		/*
+		 * Bus events on bytes 0 and 2 can be counted
+		 * on PMC1/2; bytes 1 and 3 on PMC3/4.
+		 */
+		if (!pmc)
+			grp = byte & 1;
+		/* Set byte lane select field */
+		mask  |= 0xfULL << (24 - 4 * byte);
+		value |= (u64)unit << (24 - 4 * byte);
+	}
+	if (grp == 0) {
+		/* increment PMC1/2 field */
+		mask  |= 0x200000000ull;
+		value |= 0x080000000ull;
+	} else if (grp == 1) {
+		/* increment PMC3/4 field */
+		mask  |= 0x40000000ull;
+		value |= 0x10000000ull;
+	}
+	if (pmc < 5) {
+		/* need a counter from PMC1-4 set */
+		mask  |= 0x8000000000000ull;
+		value |= 0x1000000000000ull;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+#define MAX_ALT	3	/* at most 3 alternatives for any event */
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x120e4,  0x400002 },			/* PM_GRP_DISP_REJECT */
+	{ 0x410c7,  0x441084 },			/* PM_THRD_L2MISS_BOTH_CYC */
+	{ 0x100005, 0x600005 },			/* PM_RUN_CYC */
+	{ 0x100009, 0x200009, 0x500009 },	/* PM_INST_CMPL */
+	{ 0x300009, 0x400009 },			/* PM_INST_DISP */
+};
+
+/*
+ * Scan the alternatives table for a match and return the
+ * index into the alternatives table if found, else -1.
+ */
+static int find_alternative(u64 event)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			break;
+		for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
+			if (event == event_alternatives[i][j])
+				return i;
+	}
+	return -1;
+}
+
+static const unsigned char bytedecode_alternatives[4][4] = {
+	/* PMC 1 */	{ 0x21, 0x23, 0x25, 0x27 },
+	/* PMC 2 */	{ 0x07, 0x17, 0x0e, 0x1e },
+	/* PMC 3 */	{ 0x20, 0x22, 0x24, 0x26 },
+	/* PMC 4 */	{ 0x07, 0x17, 0x0e, 0x1e }
+};
+
+/*
+ * Some direct events for decodes of event bus byte 3 have alternative
+ * PMCSEL values on other counters.  This returns the alternative
+ * event code for those that do, or -1 otherwise.
+ */
+static s64 find_alternative_bdecode(u64 event)
+{
+	int pmc, altpmc, pp, j;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc == 0 || pmc > 4)
+		return -1;
+	altpmc = 5 - pmc;	/* 1 <-> 4, 2 <-> 3 */
+	pp = event & PM_PMCSEL_MSK;
+	for (j = 0; j < 4; ++j) {
+		if (bytedecode_alternatives[pmc - 1][j] == pp) {
+			return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) |
+				(altpmc << PM_PMC_SH) |
+				bytedecode_alternatives[altpmc - 1][j];
+		}
+	}
+	return -1;
+}
+
+static int power5_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nalt = 1;
+	s64 ae;
+
+	alt[0] = event;
+	nalt = 1;
+	i = find_alternative(event);
+	if (i >= 0) {
+		for (j = 0; j < MAX_ALT; ++j) {
+			ae = event_alternatives[i][j];
+			if (ae && ae != event)
+				alt[nalt++] = ae;
+		}
+	} else {
+		ae = find_alternative_bdecode(event);
+		if (ae > 0)
+			alt[nalt++] = ae;
+	}
+	return nalt;
+}
+
+/*
+ * Map of which direct events on which PMCs are marked instruction events.
+ * Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event.
+ * Bit 0 is set if it is marked for all PMCs.
+ * The 0x80 bit indicates a byte decode PMCSEL value.
+ */
+static unsigned char direct_event_is_marked[0x28] = {
+	0,	/* 00 */
+	0x1f,	/* 01 PM_IOPS_CMPL */
+	0x2,	/* 02 PM_MRK_GRP_DISP */
+	0xe,	/* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */
+	0,	/* 04 */
+	0x1c,	/* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */
+	0x80,	/* 06 */
+	0x80,	/* 07 */
+	0, 0, 0,/* 08 - 0a */
+	0x18,	/* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */
+	0,	/* 0c */
+	0x80,	/* 0d */
+	0x80,	/* 0e */
+	0,	/* 0f */
+	0,	/* 10 */
+	0x14,	/* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */
+	0,	/* 12 */
+	0x10,	/* 13 PM_MRK_GRP_CMPL */
+	0x1f,	/* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */
+	0x2,	/* 15 PM_MRK_GRP_ISSUED */
+	0x80,	/* 16 */
+	0x80,	/* 17 */
+	0, 0, 0, 0, 0,
+	0x80,	/* 1d */
+	0x80,	/* 1e */
+	0,	/* 1f */
+	0x80,	/* 20 */
+	0x80,	/* 21 */
+	0x80,	/* 22 */
+	0x80,	/* 23 */
+	0x80,	/* 24 */
+	0x80,	/* 25 */
+	0x80,	/* 26 */
+	0x80,	/* 27 */
+};
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int power5_marked_instr_event(u64 event)
+{
+	int pmc, psel;
+	int bit, byte, unit;
+	u32 mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if (pmc >= 5)
+		return 0;
+
+	bit = -1;
+	if (psel < sizeof(direct_event_is_marked)) {
+		if (direct_event_is_marked[psel] & (1 << pmc))
+			return 1;
+		if (direct_event_is_marked[psel] & 0x80)
+			bit = 4;
+		else if (psel == 0x08)
+			bit = pmc - 1;
+		else if (psel == 0x10)
+			bit = 4 - pmc;
+		else if (psel == 0x1b && (pmc == 1 || pmc == 3))
+			bit = 4;
+	} else if ((psel & 0x58) == 0x40)
+		bit = psel & 7;
+
+	if (!(event & PM_BUSEVENT_MSK))
+		return 0;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	if (unit == PM_LSU0) {
+		/* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */
+		mask = 0x5dff00;
+	} else if (unit == PM_LSU1 && byte >= 4) {
+		byte -= 4;
+		/* byte 4 bits 1,3,5,7, byte 5 bits 6-7, byte 7 bits 0-4,6 */
+		mask = 0x5f00c0aa;
+	} else
+		return 0;
+
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+static int power5_compute_mmcr(u64 event[], int n_ev,
+			       unsigned int hwc[], u64 mmcr[])
+{
+	u64 mmcr1 = 0;
+	u64 mmcra = 0;
+	unsigned int pmc, unit, byte, psel;
+	unsigned int ttm, grp;
+	int i, isbus, bit, grsel;
+	unsigned int pmc_inuse = 0;
+	unsigned int pmc_grp_use[2];
+	unsigned char busbyte[4];
+	unsigned char unituse[16];
+	int ttmuse;
+
+	if (n_ev > 6)
+		return -1;
+
+	/* First pass to count resource use */
+	pmc_grp_use[0] = pmc_grp_use[1] = 0;
+	memset(busbyte, 0, sizeof(busbyte));
+	memset(unituse, 0, sizeof(unituse));
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc > 6)
+				return -1;
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+			/* count 1/2 vs 3/4 use */
+			if (pmc <= 4)
+				++pmc_grp_use[(pmc - 1) >> 1];
+		}
+		if (event[i] & PM_BUSEVENT_MSK) {
+			unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+			byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+			if (unit > PM_LASTUNIT)
+				return -1;
+			if (unit == PM_ISU0_ALT)
+				unit = PM_ISU0;
+			if (byte >= 4) {
+				if (unit != PM_LSU1)
+					return -1;
+				++unit;
+				byte &= 3;
+			}
+			if (!pmc)
+				++pmc_grp_use[byte & 1];
+			if (busbyte[byte] && busbyte[byte] != unit)
+				return -1;
+			busbyte[byte] = unit;
+			unituse[unit] = 1;
+		}
+	}
+	if (pmc_grp_use[0] > 2 || pmc_grp_use[1] > 2)
+		return -1;
+
+	/*
+	 * Assign resources and set multiplexer selects.
+	 *
+	 * PM_ISU0 can go either on TTM0 or TTM1, but that's the only
+	 * choice we have to deal with.
+	 */
+	if (unituse[PM_ISU0] &
+	    (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) {
+		unituse[PM_ISU0_ALT] = 1;	/* move ISU to TTM1 */
+		unituse[PM_ISU0] = 0;
+	}
+	/* Set TTM[01]SEL fields. */
+	ttmuse = 0;
+	for (i = PM_FPU; i <= PM_ISU1; ++i) {
+		if (!unituse[i])
+			continue;
+		if (ttmuse++)
+			return -1;
+		mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH;
+	}
+	ttmuse = 0;
+	for (; i <= PM_GRS; ++i) {
+		if (!unituse[i])
+			continue;
+		if (ttmuse++)
+			return -1;
+		mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH;
+	}
+	if (ttmuse > 1)
+		return -1;
+
+	/* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */
+	for (byte = 0; byte < 4; ++byte) {
+		unit = busbyte[byte];
+		if (!unit)
+			continue;
+		if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) {
+			/* get ISU0 through TTM1 rather than TTM0 */
+			unit = PM_ISU0_ALT;
+		} else if (unit == PM_LSU1 + 1) {
+			/* select lower word of LSU1 for this byte */
+			mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
+		}
+		ttm = unit >> 2;
+		mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+	}
+
+	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		isbus = event[i] & PM_BUSEVENT_MSK;
+		if (!pmc) {
+			/* Bus event or any-PMC direct event */
+			for (pmc = 0; pmc < 4; ++pmc) {
+				if (pmc_inuse & (1 << pmc))
+					continue;
+				grp = (pmc >> 1) & 1;
+				if (isbus) {
+					if (grp == (byte & 1))
+						break;
+				} else if (pmc_grp_use[grp] < 2) {
+					++pmc_grp_use[grp];
+					break;
+				}
+			}
+			pmc_inuse |= 1 << pmc;
+		} else if (pmc <= 4) {
+			/* Direct event */
+			--pmc;
+			if ((psel == 8 || psel == 0x10) && isbus && (byte & 2))
+				/* add events on higher-numbered bus */
+				mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
+		} else {
+			/* Instructions or run cycles on PMC5/6 */
+			--pmc;
+		}
+		if (isbus && unit == PM_GRS) {
+			bit = psel & 7;
+			grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK;
+			mmcr1 |= (u64)grsel << grsel_shift[bit];
+		}
+		if (power5_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+		if (pmc <= 3)
+			mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
+		hwc[i] = pmc;
+	}
+
+	/* Return MMCRx values */
+	mmcr[0] = 0;
+	if (pmc_inuse & 1)
+		mmcr[0] = MMCR0_PMC1CE;
+	if (pmc_inuse & 0x3e)
+		mmcr[0] |= MMCR0_PMCjCE;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void power5_disable_pmc(unsigned int pmc, u64 mmcr[])
+{
+	if (pmc <= 3)
+		mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
+}
+
+static int power5_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0xf,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x100009,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x4c1090, /* LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x3c1088, /* LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x230e4,  /* BR_ISSUED */
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x230e5,  /* BR_MPRED_CR */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x4c1090,	0x3c1088	},
+		[C(OP_WRITE)] = {	0x3c1090,	0xc10c3		},
+		[C(OP_PREFETCH)] = {	0xc70e7,	0		},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	0,		0		},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x3c309b	},
+		[C(OP_WRITE)] = {	0,		0		},
+		[C(OP_PREFETCH)] = {	0xc50c3,	0		},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x2c4090,	0x800c4		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x800c0		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x230e4,	0x230e5		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+};
+
+struct power_pmu power5_pmu = {
+	.n_counter = 6,
+	.max_alternatives = MAX_ALT,
+	.add_fields = 0x7000090000555ull,
+	.test_adder = 0x3000490000000ull,
+	.compute_mmcr = power5_compute_mmcr,
+	.get_constraint = power5_get_constraint,
+	.get_alternatives = power5_get_alternatives,
+	.disable_pmc = power5_disable_pmc,
+	.n_generic = ARRAY_SIZE(power5_generic_events),
+	.generic_events = power5_generic_events,
+	.cache_events = &power5_cache_events,
+};
diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c
new file mode 100644
index 000000000000..46f74bebcfd9
--- /dev/null
+++ b/arch/powerpc/kernel/power6-pmu.c
@@ -0,0 +1,532 @@
+/*
+ * Performance counter support for POWER6 processors.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <asm/reg.h>
+
+/*
+ * Bits in event code for POWER6
+ */
+#define PM_PMC_SH	20	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0x7
+#define PM_PMC_MSKS	(PM_PMC_MSK << PM_PMC_SH)
+#define PM_UNIT_SH	16	/* Unit event comes (TTMxSEL encoding) */
+#define PM_UNIT_MSK	0xf
+#define PM_UNIT_MSKS	(PM_UNIT_MSK << PM_UNIT_SH)
+#define PM_LLAV		0x8000	/* Load lookahead match value */
+#define PM_LLA		0x4000	/* Load lookahead match enable */
+#define PM_BYTE_SH	12	/* Byte of event bus to use */
+#define PM_BYTE_MSK	3
+#define PM_SUBUNIT_SH	8	/* Subunit event comes from (NEST_SEL enc.) */
+#define PM_SUBUNIT_MSK	7
+#define PM_SUBUNIT_MSKS	(PM_SUBUNIT_MSK << PM_SUBUNIT_SH)
+#define PM_PMCSEL_MSK	0xff	/* PMCxSEL value */
+#define PM_BUSEVENT_MSK	0xf3700
+
+/*
+ * Bits in MMCR1 for POWER6
+ */
+#define MMCR1_TTM0SEL_SH	60
+#define MMCR1_TTMSEL_SH(n)	(MMCR1_TTM0SEL_SH - (n) * 4)
+#define MMCR1_TTMSEL_MSK	0xf
+#define MMCR1_TTMSEL(m, n)	(((m) >> MMCR1_TTMSEL_SH(n)) & MMCR1_TTMSEL_MSK)
+#define MMCR1_NESTSEL_SH	45
+#define MMCR1_NESTSEL_MSK	0x7
+#define MMCR1_NESTSEL(m)	(((m) >> MMCR1_NESTSEL_SH) & MMCR1_NESTSEL_MSK)
+#define MMCR1_PMC1_LLA		((u64)1 << 44)
+#define MMCR1_PMC1_LLA_VALUE	((u64)1 << 39)
+#define MMCR1_PMC1_ADDR_SEL	((u64)1 << 35)
+#define MMCR1_PMC1SEL_SH	24
+#define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
+#define MMCR1_PMCSEL_MSK	0xff
+
+/*
+ * Map of which direct events on which PMCs are marked instruction events.
+ * Indexed by PMCSEL value >> 1.
+ * Bottom 4 bits are a map of which PMCs are interesting,
+ * top 4 bits say what sort of event:
+ *   0 = direct marked event,
+ *   1 = byte decode event,
+ *   4 = add/and event (PMC1 -> bits 0 & 4),
+ *   5 = add/and event (PMC1 -> bits 1 & 5),
+ *   6 = add/and event (PMC1 -> bits 2 & 6),
+ *   7 = add/and event (PMC1 -> bits 3 & 7).
+ */
+static unsigned char direct_event_is_marked[0x60 >> 1] = {
+	0,	/* 00 */
+	0,	/* 02 */
+	0,	/* 04 */
+	0x07,	/* 06 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */
+	0x04,	/* 08 PM_MRK_DFU_FIN */
+	0x06,	/* 0a PM_MRK_IFU_FIN, PM_MRK_INST_FIN */
+	0,	/* 0c */
+	0,	/* 0e */
+	0x02,	/* 10 PM_MRK_INST_DISP */
+	0x08,	/* 12 PM_MRK_LSU_DERAT_MISS */
+	0,	/* 14 */
+	0,	/* 16 */
+	0x0c,	/* 18 PM_THRESH_TIMEO, PM_MRK_INST_FIN */
+	0x0f,	/* 1a PM_MRK_INST_DISP, PM_MRK_{FXU,FPU,LSU}_FIN */
+	0x01,	/* 1c PM_MRK_INST_ISSUED */
+	0,	/* 1e */
+	0,	/* 20 */
+	0,	/* 22 */
+	0,	/* 24 */
+	0,	/* 26 */
+	0x15,	/* 28 PM_MRK_DATA_FROM_L2MISS, PM_MRK_DATA_FROM_L3MISS */
+	0,	/* 2a */
+	0,	/* 2c */
+	0,	/* 2e */
+	0x4f,	/* 30 */
+	0x7f,	/* 32 */
+	0x4f,	/* 34 */
+	0x5f,	/* 36 */
+	0x6f,	/* 38 */
+	0x4f,	/* 3a */
+	0,	/* 3c */
+	0x08,	/* 3e PM_MRK_INST_TIMEO */
+	0x1f,	/* 40 */
+	0x1f,	/* 42 */
+	0x1f,	/* 44 */
+	0x1f,	/* 46 */
+	0x1f,	/* 48 */
+	0x1f,	/* 4a */
+	0x1f,	/* 4c */
+	0x1f,	/* 4e */
+	0,	/* 50 */
+	0x05,	/* 52 PM_MRK_BR_TAKEN, PM_MRK_BR_MPRED */
+	0x1c,	/* 54 PM_MRK_PTEG_FROM_L3MISS, PM_MRK_PTEG_FROM_L2MISS */
+	0x02,	/* 56 PM_MRK_LD_MISS_L1 */
+	0,	/* 58 */
+	0,	/* 5a */
+	0,	/* 5c */
+	0,	/* 5e */
+};
+
+/*
+ * Masks showing for each unit which bits are marked events.
+ * These masks are in LE order, i.e. 0x00000001 is byte 0, bit 0.
+ */
+static u32 marked_bus_events[16] = {
+	0x01000000,	/* direct events set 1: byte 3 bit 0 */
+	0x00010000,	/* direct events set 2: byte 2 bit 0 */
+	0, 0, 0, 0,	/* IDU, IFU, nest: nothing */
+	0x00000088,	/* VMX set 1: byte 0 bits 3, 7 */
+	0x000000c0,	/* VMX set 2: byte 0 bits 4-7 */
+	0x04010000,	/* LSU set 1: byte 2 bit 0, byte 3 bit 2 */
+	0xff010000u,	/* LSU set 2: byte 2 bit 0, all of byte 3 */
+	0,		/* LSU set 3 */
+	0x00000010,	/* VMX set 3: byte 0 bit 4 */
+	0,		/* BFP set 1 */
+	0x00000022,	/* BFP set 2: byte 0 bits 1, 5 */
+	0, 0
+};
+	
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int power6_marked_instr_event(u64 event)
+{
+	int pmc, psel, ptype;
+	int bit, byte, unit;
+	u32 mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = (event & PM_PMCSEL_MSK) >> 1;	/* drop edge/level bit */
+	if (pmc >= 5)
+		return 0;
+
+	bit = -1;
+	if (psel < sizeof(direct_event_is_marked)) {
+		ptype = direct_event_is_marked[psel];
+		if (pmc == 0 || !(ptype & (1 << (pmc - 1))))
+			return 0;
+		ptype >>= 4;
+		if (ptype == 0)
+			return 1;
+		if (ptype == 1)
+			bit = 0;
+		else
+			bit = ptype ^ (pmc - 1);
+	} else if ((psel & 0x48) == 0x40)
+		bit = psel & 7;
+
+	if (!(event & PM_BUSEVENT_MSK) || bit == -1)
+		return 0;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	mask = marked_bus_events[unit];
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+/*
+ * Assign PMC numbers and compute MMCR1 value for a set of events
+ */
+static int p6_compute_mmcr(u64 event[], int n_ev,
+			   unsigned int hwc[], u64 mmcr[])
+{
+	u64 mmcr1 = 0;
+	u64 mmcra = 0;
+	int i;
+	unsigned int pmc, ev, b, u, s, psel;
+	unsigned int ttmset = 0;
+	unsigned int pmc_inuse = 0;
+
+	if (n_ev > 6)
+		return -1;
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;	/* collision! */
+			pmc_inuse |= 1 << (pmc - 1);
+		}
+	}
+	for (i = 0; i < n_ev; ++i) {
+		ev = event[i];
+		pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			--pmc;
+		} else {
+			/* can go on any PMC; find a free one */
+			for (pmc = 0; pmc < 4; ++pmc)
+				if (!(pmc_inuse & (1 << pmc)))
+					break;
+			if (pmc >= 4)
+				return -1;
+			pmc_inuse |= 1 << pmc;
+		}
+		hwc[i] = pmc;
+		psel = ev & PM_PMCSEL_MSK;
+		if (ev & PM_BUSEVENT_MSK) {
+			/* this event uses the event bus */
+			b = (ev >> PM_BYTE_SH) & PM_BYTE_MSK;
+			u = (ev >> PM_UNIT_SH) & PM_UNIT_MSK;
+			/* check for conflict on this byte of event bus */
+			if ((ttmset & (1 << b)) && MMCR1_TTMSEL(mmcr1, b) != u)
+				return -1;
+			mmcr1 |= (u64)u << MMCR1_TTMSEL_SH(b);
+			ttmset |= 1 << b;
+			if (u == 5) {
+				/* Nest events have a further mux */
+				s = (ev >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK;
+				if ((ttmset & 0x10) &&
+				    MMCR1_NESTSEL(mmcr1) != s)
+					return -1;
+				ttmset |= 0x10;
+				mmcr1 |= (u64)s << MMCR1_NESTSEL_SH;
+			}
+			if (0x30 <= psel && psel <= 0x3d) {
+				/* these need the PMCx_ADDR_SEL bits */
+				if (b >= 2)
+					mmcr1 |= MMCR1_PMC1_ADDR_SEL >> pmc;
+			}
+			/* bus select values are different for PMC3/4 */
+			if (pmc >= 2 && (psel & 0x90) == 0x80)
+				psel ^= 0x20;
+		}
+		if (ev & PM_LLA) {
+			mmcr1 |= MMCR1_PMC1_LLA >> pmc;
+			if (ev & PM_LLAV)
+				mmcr1 |= MMCR1_PMC1_LLA_VALUE >> pmc;
+		}
+		if (power6_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+		if (pmc < 4)
+			mmcr1 |= (u64)psel << MMCR1_PMCSEL_SH(pmc);
+	}
+	mmcr[0] = 0;
+	if (pmc_inuse & 1)
+		mmcr[0] = MMCR0_PMC1CE;
+	if (pmc_inuse & 0xe)
+		mmcr[0] |= MMCR0_PMCjCE;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+/*
+ * Layout of constraint bits:
+ *
+ *	0-1	add field: number of uses of PMC1 (max 1)
+ *	2-3, 4-5, 6-7, 8-9, 10-11: ditto for PMC2, 3, 4, 5, 6
+ *	12-15	add field: number of uses of PMC1-4 (max 4)
+ *	16-19	select field: unit on byte 0 of event bus
+ *	20-23, 24-27, 28-31 ditto for bytes 1, 2, 3
+ *	32-34	select field: nest (subunit) event selector
+ */
+static int p6_get_constraint(u64 event, u64 *maskp, u64 *valp)
+{
+	int pmc, byte, sh, subunit;
+	u64 mask = 0, value = 0;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 4 && !(event == 0x500009 || event == 0x600005))
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+	}
+	if (event & PM_BUSEVENT_MSK) {
+		byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+		sh = byte * 4 + (16 - PM_UNIT_SH);
+		mask |= PM_UNIT_MSKS << sh;
+		value |= (u64)(event & PM_UNIT_MSKS) << sh;
+		if ((event & PM_UNIT_MSKS) == (5 << PM_UNIT_SH)) {
+			subunit = (event >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK;
+			mask  |= (u64)PM_SUBUNIT_MSK << 32;
+			value |= (u64)subunit << 32;
+		}
+	}
+	if (pmc <= 4) {
+		mask  |= 0x8000;	/* add field for count of PMC1-4 uses */
+		value |= 0x1000;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static int p6_limited_pmc_event(u64 event)
+{
+	int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+
+	return pmc == 5 || pmc == 6;
+}
+
+#define MAX_ALT	4	/* at most 4 alternatives for any event */
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x0130e8, 0x2000f6, 0x3000fc },	/* PM_PTEG_RELOAD_VALID */
+	{ 0x080080, 0x10000d, 0x30000c, 0x4000f0 }, /* PM_LD_MISS_L1 */
+	{ 0x080088, 0x200054, 0x3000f0 },	/* PM_ST_MISS_L1 */
+	{ 0x10000a, 0x2000f4, 0x600005 },	/* PM_RUN_CYC */
+	{ 0x10000b, 0x2000f5 },			/* PM_RUN_COUNT */
+	{ 0x10000e, 0x400010 },			/* PM_PURR */
+	{ 0x100010, 0x4000f8 },			/* PM_FLUSH */
+	{ 0x10001a, 0x200010 },			/* PM_MRK_INST_DISP */
+	{ 0x100026, 0x3000f8 },			/* PM_TB_BIT_TRANS */
+	{ 0x100054, 0x2000f0 },			/* PM_ST_FIN */
+	{ 0x100056, 0x2000fc },			/* PM_L1_ICACHE_MISS */
+	{ 0x1000f0, 0x40000a },			/* PM_INST_IMC_MATCH_CMPL */
+	{ 0x1000f8, 0x200008 },			/* PM_GCT_EMPTY_CYC */
+	{ 0x1000fc, 0x400006 },			/* PM_LSU_DERAT_MISS_CYC */
+	{ 0x20000e, 0x400007 },			/* PM_LSU_DERAT_MISS */
+	{ 0x200012, 0x300012 },			/* PM_INST_DISP */
+	{ 0x2000f2, 0x3000f2 },			/* PM_INST_DISP */
+	{ 0x2000f8, 0x300010 },			/* PM_EXT_INT */
+	{ 0x2000fe, 0x300056 },			/* PM_DATA_FROM_L2MISS */
+	{ 0x2d0030, 0x30001a },			/* PM_MRK_FPU_FIN */
+	{ 0x30000a, 0x400018 },			/* PM_MRK_INST_FIN */
+	{ 0x3000f6, 0x40000e },			/* PM_L1_DCACHE_RELOAD_VALID */
+	{ 0x3000fe, 0x400056 },			/* PM_DATA_FROM_L3MISS */
+};
+
+/*
+ * This could be made more efficient with a binary search on
+ * a presorted list, if necessary
+ */
+static int find_alternatives_list(u64 event)
+{
+	int i, j;
+	unsigned int alt;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			return -1;
+		for (j = 0; j < MAX_ALT; ++j) {
+			alt = event_alternatives[i][j];
+			if (!alt || event < alt)
+				break;
+			if (event == alt)
+				return i;
+		}
+	}
+	return -1;
+}
+
+static int p6_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nlim;
+	unsigned int psel, pmc;
+	unsigned int nalt = 1;
+	u64 aevent;
+
+	alt[0] = event;
+	nlim = p6_limited_pmc_event(event);
+
+	/* check the alternatives table */
+	i = find_alternatives_list(event);
+	if (i >= 0) {
+		/* copy out alternatives from list */
+		for (j = 0; j < MAX_ALT; ++j) {
+			aevent = event_alternatives[i][j];
+			if (!aevent)
+				break;
+			if (aevent != event)
+				alt[nalt++] = aevent;
+			nlim += p6_limited_pmc_event(aevent);
+		}
+
+	} else {
+		/* Check for alternative ways of computing sum events */
+		/* PMCSEL 0x32 counter N == PMCSEL 0x34 counter 5-N */
+		psel = event & (PM_PMCSEL_MSK & ~1);	/* ignore edge bit */
+		pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc && (psel == 0x32 || psel == 0x34))
+			alt[nalt++] = ((event ^ 0x6) & ~PM_PMC_MSKS) |
+				((5 - pmc) << PM_PMC_SH);
+
+		/* PMCSEL 0x38 counter N == PMCSEL 0x3a counter N+/-2 */
+		if (pmc && (psel == 0x38 || psel == 0x3a))
+			alt[nalt++] = ((event ^ 0x2) & ~PM_PMC_MSKS) |
+				((pmc > 2? pmc - 2: pmc + 2) << PM_PMC_SH);
+	}
+
+	if (flags & PPMU_ONLY_COUNT_RUN) {
+		/*
+		 * We're only counting in RUN state,
+		 * so PM_CYC is equivalent to PM_RUN_CYC,
+		 * PM_INST_CMPL === PM_RUN_INST_CMPL, PM_PURR === PM_RUN_PURR.
+		 * This doesn't include alternatives that don't provide
+		 * any extra flexibility in assigning PMCs (e.g.
+		 * 0x10000a for PM_RUN_CYC vs. 0x1e for PM_CYC).
+		 * Note that even with these additional alternatives
+		 * we never end up with more than 4 alternatives for any event.
+		 */
+		j = nalt;
+		for (i = 0; i < nalt; ++i) {
+			switch (alt[i]) {
+			case 0x1e:	/* PM_CYC */
+				alt[j++] = 0x600005;	/* PM_RUN_CYC */
+				++nlim;
+				break;
+			case 0x10000a:	/* PM_RUN_CYC */
+				alt[j++] = 0x1e;	/* PM_CYC */
+				break;
+			case 2:		/* PM_INST_CMPL */
+				alt[j++] = 0x500009;	/* PM_RUN_INST_CMPL */
+				++nlim;
+				break;
+			case 0x500009:	/* PM_RUN_INST_CMPL */
+				alt[j++] = 2;		/* PM_INST_CMPL */
+				break;
+			case 0x10000e:	/* PM_PURR */
+				alt[j++] = 0x4000f4;	/* PM_RUN_PURR */
+				break;
+			case 0x4000f4:	/* PM_RUN_PURR */
+				alt[j++] = 0x10000e;	/* PM_PURR */
+				break;
+			}
+		}
+		nalt = j;
+	}
+
+	if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) {
+		/* remove the limited PMC events */
+		j = 0;
+		for (i = 0; i < nalt; ++i) {
+			if (!p6_limited_pmc_event(alt[i])) {
+				alt[j] = alt[i];
+				++j;
+			}
+		}
+		nalt = j;
+	} else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) {
+		/* remove all but the limited PMC events */
+		j = 0;
+		for (i = 0; i < nalt; ++i) {
+			if (p6_limited_pmc_event(alt[i])) {
+				alt[j] = alt[i];
+				++j;
+			}
+		}
+		nalt = j;
+	}
+
+	return nalt;
+}
+
+static void p6_disable_pmc(unsigned int pmc, u64 mmcr[])
+{
+	/* Set PMCxSEL to 0 to disable PMCx */
+	if (pmc <= 3)
+		mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc));
+}
+
+static int power6_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x1e,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 2,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x280030, /* LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x30000c, /* LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x410a0,  /* BR_PRED */
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x400052, /* BR_MPRED */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ * The "DTLB" and "ITLB" events relate to the DERAT and IERAT.
+ */
+static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x80082,	0x80080		},
+		[C(OP_WRITE)] = {	0x80086,	0x80088		},
+		[C(OP_PREFETCH)] = {	0x810a4,	0		},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x100056 	},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	0x4008c,	0		},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x150730,	0x250532	},
+		[C(OP_WRITE)] = {	0x250432,	0x150432	},
+		[C(OP_PREFETCH)] = {	0x810a6,	0		},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x20000e	},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x420ce		},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x430e6,	0x400052	},
+		[C(OP_WRITE)] = {	-1,		-1		},
+		[C(OP_PREFETCH)] = {	-1,		-1		},
+	},
+};
+
+struct power_pmu power6_pmu = {
+	.n_counter = 6,
+	.max_alternatives = MAX_ALT,
+	.add_fields = 0x1555,
+	.test_adder = 0x3000,
+	.compute_mmcr = p6_compute_mmcr,
+	.get_constraint = p6_get_constraint,
+	.get_alternatives = p6_get_alternatives,
+	.disable_pmc = p6_disable_pmc,
+	.limited_pmc_event = p6_limited_pmc_event,
+	.flags = PPMU_LIMITED_PMC5_6 | PPMU_ALT_SIPR,
+	.n_generic = ARRAY_SIZE(power6_generic_events),
+	.generic_events = power6_generic_events,
+	.cache_events = &power6_cache_events,
+};
diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c
new file mode 100644
index 000000000000..b3f7d1216bae
--- /dev/null
+++ b/arch/powerpc/kernel/power7-pmu.c
@@ -0,0 +1,357 @@
+/*
+ * Performance counter support for POWER7 processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/perf_counter.h>
+#include <asm/reg.h>
+
+/*
+ * Bits in event code for POWER7
+ */
+#define PM_PMC_SH	16	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_PMC_MSKS	(PM_PMC_MSK << PM_PMC_SH)
+#define PM_UNIT_SH	12	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_COMBINE_SH	11	/* Combined event bit */
+#define PM_COMBINE_MSK	1
+#define PM_COMBINE_MSKS	0x800
+#define PM_L2SEL_SH	8	/* L2 event select */
+#define PM_L2SEL_MSK	7
+#define PM_PMCSEL_MSK	0xff
+
+/*
+ * Bits in MMCR1 for POWER7
+ */
+#define MMCR1_TTM0SEL_SH	60
+#define MMCR1_TTM1SEL_SH	56
+#define MMCR1_TTM2SEL_SH	52
+#define MMCR1_TTM3SEL_SH	48
+#define MMCR1_TTMSEL_MSK	0xf
+#define MMCR1_L2SEL_SH		45
+#define MMCR1_L2SEL_MSK		7
+#define MMCR1_PMC1_COMBINE_SH	35
+#define MMCR1_PMC2_COMBINE_SH	34
+#define MMCR1_PMC3_COMBINE_SH	33
+#define MMCR1_PMC4_COMBINE_SH	32
+#define MMCR1_PMC1SEL_SH	24
+#define MMCR1_PMC2SEL_SH	16
+#define MMCR1_PMC3SEL_SH	8
+#define MMCR1_PMC4SEL_SH	0
+#define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
+#define MMCR1_PMCSEL_MSK	0xff
+
+/*
+ * Bits in MMCRA
+ */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *                                                 [  ><><><><><><>
+ *                                                  NC P6P5P4P3P2P1
+ *
+ * NC - number of counters
+ *     15: NC error 0x8000
+ *     12-14: number of events needing PMC1-4 0x7000
+ *
+ * P6
+ *     11: P6 error 0x800
+ *     10-11: Count of events needing PMC6
+ *
+ * P1..P5
+ *     0-9: Count of events needing PMC1..PMC5
+ */
+
+static int power7_get_constraint(u64 event, u64 *maskp, u64 *valp)
+{
+	int pmc, sh;
+	u64 mask = 0, value = 0;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 6)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		if (pmc >= 5 && !(event == 0x500fa || event == 0x600f4))
+			return -1;
+	}
+	if (pmc < 5) {
+		/* need a counter from PMC1-4 set */
+		mask  |= 0x8000;
+		value |= 0x1000;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+#define MAX_ALT	2	/* at most 2 alternatives for any event */
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x200f2, 0x300f2 },		/* PM_INST_DISP */
+	{ 0x200f4, 0x600f4 },		/* PM_RUN_CYC */
+	{ 0x400fa, 0x500fa },		/* PM_RUN_INST_CMPL */
+};
+
+/*
+ * Scan the alternatives table for a match and return the
+ * index into the alternatives table if found, else -1.
+ */
+static int find_alternative(u64 event)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			break;
+		for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
+			if (event == event_alternatives[i][j])
+				return i;
+	}
+	return -1;
+}
+
+static s64 find_alternative_decode(u64 event)
+{
+	int pmc, psel;
+
+	/* this only handles the 4x decode events */
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if ((pmc == 2 || pmc == 4) && (psel & ~7) == 0x40)
+		return event - (1 << PM_PMC_SH) + 8;
+	if ((pmc == 1 || pmc == 3) && (psel & ~7) == 0x48)
+		return event + (1 << PM_PMC_SH) - 8;
+	return -1;
+}
+
+static int power7_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nalt = 1;
+	s64 ae;
+
+	alt[0] = event;
+	nalt = 1;
+	i = find_alternative(event);
+	if (i >= 0) {
+		for (j = 0; j < MAX_ALT; ++j) {
+			ae = event_alternatives[i][j];
+			if (ae && ae != event)
+				alt[nalt++] = ae;
+		}
+	} else {
+		ae = find_alternative_decode(event);
+		if (ae > 0)
+			alt[nalt++] = ae;
+	}
+
+	if (flags & PPMU_ONLY_COUNT_RUN) {
+		/*
+		 * We're only counting in RUN state,
+		 * so PM_CYC is equivalent to PM_RUN_CYC
+		 * and PM_INST_CMPL === PM_RUN_INST_CMPL.
+		 * This doesn't include alternatives that don't provide
+		 * any extra flexibility in assigning PMCs.
+		 */
+		j = nalt;
+		for (i = 0; i < nalt; ++i) {
+			switch (alt[i]) {
+			case 0x1e:	/* PM_CYC */
+				alt[j++] = 0x600f4;	/* PM_RUN_CYC */
+				break;
+			case 0x600f4:	/* PM_RUN_CYC */
+				alt[j++] = 0x1e;
+				break;
+			case 0x2:	/* PM_PPC_CMPL */
+				alt[j++] = 0x500fa;	/* PM_RUN_INST_CMPL */
+				break;
+			case 0x500fa:	/* PM_RUN_INST_CMPL */
+				alt[j++] = 0x2;	/* PM_PPC_CMPL */
+				break;
+			}
+		}
+		nalt = j;
+	}
+
+	return nalt;
+}
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int power7_marked_instr_event(u64 event)
+{
+	int pmc, psel;
+	int unit;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	psel = event & PM_PMCSEL_MSK & ~1;	/* trim off edge/level bit */
+	if (pmc >= 5)
+		return 0;
+
+	switch (psel >> 4) {
+	case 2:
+		return pmc == 2 || pmc == 4;
+	case 3:
+		if (psel == 0x3c)
+			return pmc == 1;
+		if (psel == 0x3e)
+			return pmc != 2;
+		return 1;
+	case 4:
+	case 5:
+		return unit == 0xd;
+	case 6:
+		if (psel == 0x64)
+			return pmc >= 3;
+	case 8:
+		return unit == 0xd;
+	}
+	return 0;
+}
+
+static int power7_compute_mmcr(u64 event[], int n_ev,
+			       unsigned int hwc[], u64 mmcr[])
+{
+	u64 mmcr1 = 0;
+	u64 mmcra = 0;
+	unsigned int pmc, unit, combine, l2sel, psel;
+	unsigned int pmc_inuse = 0;
+	int i;
+
+	/* First pass to count resource use */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc > 6)
+				return -1;
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+		}
+	}
+
+	/* Second pass: assign PMCs, set all MMCR1 fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		combine = (event[i] >> PM_COMBINE_SH) & PM_COMBINE_MSK;
+		l2sel = (event[i] >> PM_L2SEL_SH) & PM_L2SEL_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		if (!pmc) {
+			/* Bus event or any-PMC direct event */
+			for (pmc = 0; pmc < 4; ++pmc) {
+				if (!(pmc_inuse & (1 << pmc)))
+					break;
+			}
+			if (pmc >= 4)
+				return -1;
+			pmc_inuse |= 1 << pmc;
+		} else {
+			/* Direct or decoded event */
+			--pmc;
+		}
+		if (pmc <= 3) {
+			mmcr1 |= (u64) unit << (MMCR1_TTM0SEL_SH - 4 * pmc);
+			mmcr1 |= (u64) combine << (MMCR1_PMC1_COMBINE_SH - pmc);
+			mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
+			if (unit == 6)	/* L2 events */
+				mmcr1 |= (u64) l2sel << MMCR1_L2SEL_SH;
+		}
+		if (power7_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+		hwc[i] = pmc;
+	}
+
+	/* Return MMCRx values */
+	mmcr[0] = 0;
+	if (pmc_inuse & 1)
+		mmcr[0] = MMCR0_PMC1CE;
+	if (pmc_inuse & 0x3e)
+		mmcr[0] |= MMCR0_PMCjCE;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void power7_disable_pmc(unsigned int pmc, u64 mmcr[])
+{
+	if (pmc <= 3)
+		mmcr[1] &= ~(0xffULL << MMCR1_PMCSEL_SH(pmc));
+}
+
+static int power7_generic_events[] = {
+	[PERF_COUNT_CPU_CYCLES] = 0x1e,
+	[PERF_COUNT_INSTRUCTIONS] = 2,
+	[PERF_COUNT_CACHE_REFERENCES] = 0xc880,		/* LD_REF_L1_LSU */
+	[PERF_COUNT_CACHE_MISSES] = 0x400f0,		/* LD_MISS_L1 */
+	[PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x10068,	/* BRU_FIN */
+	[PERF_COUNT_BRANCH_MISSES] = 0x400f6,		/* BR_MPRED */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x400f0,	0xc880	},
+		[C(OP_WRITE)] = {	0,		0x300f0	},
+		[C(OP_PREFETCH)] = {	0xd8b8,		0	},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x200fc	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	0x408a,		0	},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x6080,		0x6084	},
+		[C(OP_WRITE)] = {	0x6082,		0x6086	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x300fc	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x400fc	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x10068,	0x400f6	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+struct power_pmu power7_pmu = {
+	.n_counter = 6,
+	.max_alternatives = MAX_ALT + 1,
+	.add_fields = 0x1555ull,
+	.test_adder = 0x3000ull,
+	.compute_mmcr = power7_compute_mmcr,
+	.get_constraint = power7_get_constraint,
+	.get_alternatives = power7_get_alternatives,
+	.disable_pmc = power7_disable_pmc,
+	.n_generic = ARRAY_SIZE(power7_generic_events),
+	.generic_events = power7_generic_events,
+	.cache_events = &power7_cache_events,
+};
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c
new file mode 100644
index 000000000000..ba0a357a89f4
--- /dev/null
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -0,0 +1,482 @@
+/*
+ * Performance counter support for PPC970-family processors.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/string.h>
+#include <linux/perf_counter.h>
+#include <asm/reg.h>
+
+/*
+ * Bits in event code for PPC970
+ */
+#define PM_PMC_SH	12	/* PMC number (1-based) for direct events */
+#define PM_PMC_MSK	0xf
+#define PM_UNIT_SH	8	/* TTMMUX number and setting - unit select */
+#define PM_UNIT_MSK	0xf
+#define PM_SPCSEL_SH	6
+#define PM_SPCSEL_MSK	3
+#define PM_BYTE_SH	4	/* Byte number of event bus to use */
+#define PM_BYTE_MSK	3
+#define PM_PMCSEL_MSK	0xf
+
+/* Values in PM_UNIT field */
+#define PM_NONE		0
+#define PM_FPU		1
+#define PM_VPU		2
+#define PM_ISU		3
+#define PM_IFU		4
+#define PM_IDU		5
+#define PM_STS		6
+#define PM_LSU0		7
+#define PM_LSU1U	8
+#define PM_LSU1L	9
+#define PM_LASTUNIT	9
+
+/*
+ * Bits in MMCR0 for PPC970
+ */
+#define MMCR0_PMC1SEL_SH	8
+#define MMCR0_PMC2SEL_SH	1
+#define MMCR_PMCSEL_MSK		0x1f
+
+/*
+ * Bits in MMCR1 for PPC970
+ */
+#define MMCR1_TTM0SEL_SH	62
+#define MMCR1_TTM1SEL_SH	59
+#define MMCR1_TTM3SEL_SH	53
+#define MMCR1_TTMSEL_MSK	3
+#define MMCR1_TD_CP_DBG0SEL_SH	50
+#define MMCR1_TD_CP_DBG1SEL_SH	48
+#define MMCR1_TD_CP_DBG2SEL_SH	46
+#define MMCR1_TD_CP_DBG3SEL_SH	44
+#define MMCR1_PMC1_ADDER_SEL_SH	39
+#define MMCR1_PMC2_ADDER_SEL_SH	38
+#define MMCR1_PMC6_ADDER_SEL_SH	37
+#define MMCR1_PMC5_ADDER_SEL_SH	36
+#define MMCR1_PMC8_ADDER_SEL_SH	35
+#define MMCR1_PMC7_ADDER_SEL_SH	34
+#define MMCR1_PMC3_ADDER_SEL_SH	33
+#define MMCR1_PMC4_ADDER_SEL_SH	32
+#define MMCR1_PMC3SEL_SH	27
+#define MMCR1_PMC4SEL_SH	22
+#define MMCR1_PMC5SEL_SH	17
+#define MMCR1_PMC6SEL_SH	12
+#define MMCR1_PMC7SEL_SH	7
+#define MMCR1_PMC8SEL_SH	2
+
+static short mmcr1_adder_bits[8] = {
+	MMCR1_PMC1_ADDER_SEL_SH,
+	MMCR1_PMC2_ADDER_SEL_SH,
+	MMCR1_PMC3_ADDER_SEL_SH,
+	MMCR1_PMC4_ADDER_SEL_SH,
+	MMCR1_PMC5_ADDER_SEL_SH,
+	MMCR1_PMC6_ADDER_SEL_SH,
+	MMCR1_PMC7_ADDER_SEL_SH,
+	MMCR1_PMC8_ADDER_SEL_SH
+};
+
+/*
+ * Bits in MMCRA
+ */
+
+/*
+ * Layout of constraint bits:
+ * 6666555555555544444444443333333333222222222211111111110000000000
+ * 3210987654321098765432109876543210987654321098765432109876543210
+ *               <><><>[  >[  >[  ><  ><  ><  ><  ><><><><><><><><>
+ *               SPT0T1 UC  PS1 PS2 B0  B1  B2  B3 P1P2P3P4P5P6P7P8
+ *
+ * SP - SPCSEL constraint
+ *     48-49: SPCSEL value 0x3_0000_0000_0000
+ *
+ * T0 - TTM0 constraint
+ *     46-47: TTM0SEL value (0=FPU, 2=IFU, 3=VPU) 0xC000_0000_0000
+ *
+ * T1 - TTM1 constraint
+ *     44-45: TTM1SEL value (0=IDU, 3=STS) 0x3000_0000_0000
+ *
+ * UC - unit constraint: can't have all three of FPU|IFU|VPU, ISU, IDU|STS
+ *     43: UC3 error 0x0800_0000_0000
+ *     42: FPU|IFU|VPU events needed 0x0400_0000_0000
+ *     41: ISU events needed 0x0200_0000_0000
+ *     40: IDU|STS events needed 0x0100_0000_0000
+ *
+ * PS1
+ *     39: PS1 error 0x0080_0000_0000
+ *     36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000
+ *
+ * PS2
+ *     35: PS2 error 0x0008_0000_0000
+ *     32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000
+ *
+ * B0
+ *     28-31: Byte 0 event source 0xf000_0000
+ *	      Encoding as for the event code
+ *
+ * B1, B2, B3
+ *     24-27, 20-23, 16-19: Byte 1, 2, 3 event sources
+ *
+ * P1
+ *     15: P1 error 0x8000
+ *     14-15: Count of events needing PMC1
+ *
+ * P2..P8
+ *     0-13: Count of events needing PMC2..PMC8
+ */
+
+static unsigned char direct_marked_event[8] = {
+	(1<<2) | (1<<3),	/* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */
+	(1<<3) | (1<<5),	/* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */
+	(1<<3) | (1<<5),	/* PMC3: PM_MRK_ST_CMPL_INT, PM_MRK_VMX_FIN */
+	(1<<4) | (1<<5),	/* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */
+	(1<<4) | (1<<5),	/* PMC5: PM_GRP_MRK, PM_MRK_GRP_TIMEO */
+	(1<<3) | (1<<4) | (1<<5),
+		/* PMC6: PM_MRK_ST_STS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */
+	(1<<4) | (1<<5),	/* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */
+	(1<<4)			/* PMC8: PM_MRK_LSU_FIN */
+};
+
+/*
+ * Returns 1 if event counts things relating to marked instructions
+ * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
+ */
+static int p970_marked_instr_event(u64 event)
+{
+	int pmc, psel, unit, byte, bit;
+	unsigned int mask;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	psel = event & PM_PMCSEL_MSK;
+	if (pmc) {
+		if (direct_marked_event[pmc - 1] & (1 << psel))
+			return 1;
+		if (psel == 0)		/* add events */
+			bit = (pmc <= 4)? pmc - 1: 8 - pmc;
+		else if (psel == 7 || psel == 13)	/* decode events */
+			bit = 4;
+		else
+			return 0;
+	} else
+		bit = psel;
+
+	byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	mask = 0;
+	switch (unit) {
+	case PM_VPU:
+		mask = 0x4c;		/* byte 0 bits 2,3,6 */
+	case PM_LSU0:
+		/* byte 2 bits 0,2,3,4,6; all of byte 1 */
+		mask = 0x085dff00;
+	case PM_LSU1L:
+		mask = 0x50 << 24;	/* byte 3 bits 4,6 */
+		break;
+	}
+	return (mask >> (byte * 8 + bit)) & 1;
+}
+
+/* Masks and values for using events from the various units */
+static u64 unit_cons[PM_LASTUNIT+1][2] = {
+	[PM_FPU] =   { 0xc80000000000ull, 0x040000000000ull },
+	[PM_VPU] =   { 0xc80000000000ull, 0xc40000000000ull },
+	[PM_ISU] =   { 0x080000000000ull, 0x020000000000ull },
+	[PM_IFU] =   { 0xc80000000000ull, 0x840000000000ull },
+	[PM_IDU] =   { 0x380000000000ull, 0x010000000000ull },
+	[PM_STS] =   { 0x380000000000ull, 0x310000000000ull },
+};
+
+static int p970_get_constraint(u64 event, u64 *maskp, u64 *valp)
+{
+	int pmc, byte, unit, sh, spcsel;
+	u64 mask = 0, value = 0;
+	int grp = -1;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > 8)
+			return -1;
+		sh = (pmc - 1) * 2;
+		mask |= 2 << sh;
+		value |= 1 << sh;
+		grp = ((pmc - 1) >> 1) & 1;
+	}
+	unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK;
+	if (unit) {
+		if (unit > PM_LASTUNIT)
+			return -1;
+		mask |= unit_cons[unit][0];
+		value |= unit_cons[unit][1];
+		byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
+		/*
+		 * Bus events on bytes 0 and 2 can be counted
+		 * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8.
+		 */
+		if (!pmc)
+			grp = byte & 1;
+		/* Set byte lane select field */
+		mask  |= 0xfULL << (28 - 4 * byte);
+		value |= (u64)unit << (28 - 4 * byte);
+	}
+	if (grp == 0) {
+		/* increment PMC1/2/5/6 field */
+		mask  |= 0x8000000000ull;
+		value |= 0x1000000000ull;
+	} else if (grp == 1) {
+		/* increment PMC3/4/7/8 field */
+		mask  |= 0x800000000ull;
+		value |= 0x100000000ull;
+	}
+	spcsel = (event >> PM_SPCSEL_SH) & PM_SPCSEL_MSK;
+	if (spcsel) {
+		mask  |= 3ull << 48;
+		value |= (u64)spcsel << 48;
+	}
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	alt[0] = event;
+
+	/* 2 alternatives for LSU empty */
+	if (event == 0x2002 || event == 0x3002) {
+		alt[1] = event ^ 0x1000;
+		return 2;
+	}
+		
+	return 1;
+}
+
+static int p970_compute_mmcr(u64 event[], int n_ev,
+			     unsigned int hwc[], u64 mmcr[])
+{
+	u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0;
+	unsigned int pmc, unit, byte, psel;
+	unsigned int ttm, grp;
+	unsigned int pmc_inuse = 0;
+	unsigned int pmc_grp_use[2];
+	unsigned char busbyte[4];
+	unsigned char unituse[16];
+	unsigned char unitmap[] = { 0, 0<<3, 3<<3, 1<<3, 2<<3, 0|4, 3|4 };
+	unsigned char ttmuse[2];
+	unsigned char pmcsel[8];
+	int i;
+	int spcsel;
+
+	if (n_ev > 8)
+		return -1;
+
+	/* First pass to count resource use */
+	pmc_grp_use[0] = pmc_grp_use[1] = 0;
+	memset(busbyte, 0, sizeof(busbyte));
+	memset(unituse, 0, sizeof(unituse));
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		if (pmc) {
+			if (pmc_inuse & (1 << (pmc - 1)))
+				return -1;
+			pmc_inuse |= 1 << (pmc - 1);
+			/* count 1/2/5/6 vs 3/4/7/8 use */
+			++pmc_grp_use[((pmc - 1) >> 1) & 1];
+		}
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		if (unit) {
+			if (unit > PM_LASTUNIT)
+				return -1;
+			if (!pmc)
+				++pmc_grp_use[byte & 1];
+			if (busbyte[byte] && busbyte[byte] != unit)
+				return -1;
+			busbyte[byte] = unit;
+			unituse[unit] = 1;
+		}
+	}
+	if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4)
+		return -1;
+
+	/*
+	 * Assign resources and set multiplexer selects.
+	 *
+	 * PM_ISU can go either on TTM0 or TTM1, but that's the only
+	 * choice we have to deal with.
+	 */
+	if (unituse[PM_ISU] &
+	    (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_VPU]))
+		unitmap[PM_ISU] = 2 | 4;	/* move ISU to TTM1 */
+	/* Set TTM[01]SEL fields. */
+	ttmuse[0] = ttmuse[1] = 0;
+	for (i = PM_FPU; i <= PM_STS; ++i) {
+		if (!unituse[i])
+			continue;
+		ttm = unitmap[i];
+		++ttmuse[(ttm >> 2) & 1];
+		mmcr1 |= (u64)(ttm & ~4) << MMCR1_TTM1SEL_SH;
+	}
+	/* Check only one unit per TTMx */
+	if (ttmuse[0] > 1 || ttmuse[1] > 1)
+		return -1;
+
+	/* Set byte lane select fields and TTM3SEL. */
+	for (byte = 0; byte < 4; ++byte) {
+		unit = busbyte[byte];
+		if (!unit)
+			continue;
+		if (unit <= PM_STS)
+			ttm = (unitmap[unit] >> 2) & 1;
+		else if (unit == PM_LSU0)
+			ttm = 2;
+		else {
+			ttm = 3;
+			if (unit == PM_LSU1L && byte >= 2)
+				mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
+		}
+		mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+	}
+
+	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
+	memset(pmcsel, 0x8, sizeof(pmcsel));	/* 8 means don't count */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK;
+		unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK;
+		byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK;
+		psel = event[i] & PM_PMCSEL_MSK;
+		if (!pmc) {
+			/* Bus event or any-PMC direct event */
+			if (unit)
+				psel |= 0x10 | ((byte & 2) << 2);
+			else
+				psel |= 8;
+			for (pmc = 0; pmc < 8; ++pmc) {
+				if (pmc_inuse & (1 << pmc))
+					continue;
+				grp = (pmc >> 1) & 1;
+				if (unit) {
+					if (grp == (byte & 1))
+						break;
+				} else if (pmc_grp_use[grp] < 4) {
+					++pmc_grp_use[grp];
+					break;
+				}
+			}
+			pmc_inuse |= 1 << pmc;
+		} else {
+			/* Direct event */
+			--pmc;
+			if (psel == 0 && (byte & 2))
+				/* add events on higher-numbered bus */
+				mmcr1 |= 1ull << mmcr1_adder_bits[pmc];
+		}
+		pmcsel[pmc] = psel;
+		hwc[i] = pmc;
+		spcsel = (event[i] >> PM_SPCSEL_SH) & PM_SPCSEL_MSK;
+		mmcr1 |= spcsel;
+		if (p970_marked_instr_event(event[i]))
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+	}
+	for (pmc = 0; pmc < 2; ++pmc)
+		mmcr0 |= pmcsel[pmc] << (MMCR0_PMC1SEL_SH - 7 * pmc);
+	for (; pmc < 8; ++pmc)
+		mmcr1 |= (u64)pmcsel[pmc] << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
+	if (pmc_inuse & 1)
+		mmcr0 |= MMCR0_PMC1CE;
+	if (pmc_inuse & 0xfe)
+		mmcr0 |= MMCR0_PMCjCE;
+
+	mmcra |= 0x2000;	/* mark only one IOP per PPC instruction */
+
+	/* Return MMCRx values */
+	mmcr[0] = mmcr0;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	return 0;
+}
+
+static void p970_disable_pmc(unsigned int pmc, u64 mmcr[])
+{
+	int shift, i;
+
+	if (pmc <= 1) {
+		shift = MMCR0_PMC1SEL_SH - 7 * pmc;
+		i = 0;
+	} else {
+		shift = MMCR1_PMC3SEL_SH - 5 * (pmc - 2);
+		i = 1;
+	}
+	/*
+	 * Setting the PMCxSEL field to 0x08 disables PMC x.
+	 */
+	mmcr[i] = (mmcr[i] & ~(0x1fUL << shift)) | (0x08UL << shift);
+}
+
+static int ppc970_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 7,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 1,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x8810, /* PM_LD_REF_L1 */
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x3810, /* PM_LD_MISS_L1 */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x431,  /* PM_BR_ISSUED */
+	[PERF_COUNT_HW_BRANCH_MISSES] 		= 0x327,  /* PM_GRP_BR_MPRED */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x8810,		0x3810	},
+		[C(OP_WRITE)] = {	0x7810,		0x813	},
+		[C(OP_PREFETCH)] = {	0x731,		0	},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	0,		0	},
+		[C(OP_PREFETCH)] = {	0x733,		0	},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x704	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x700	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x431,		0x327	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+struct power_pmu ppc970_pmu = {
+	.n_counter = 8,
+	.max_alternatives = 2,
+	.add_fields = 0x001100005555ull,
+	.test_adder = 0x013300000000ull,
+	.compute_mmcr = p970_compute_mmcr,
+	.get_constraint = p970_get_constraint,
+	.get_alternatives = p970_get_alternatives,
+	.disable_pmc = p970_disable_pmc,
+	.n_generic = ARRAY_SIZE(ppc970_generic_events),
+	.generic_events = ppc970_generic_events,
+	.cache_events = &ppc970_cache_events,
+};
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 9057335fdc61..2cf915e51e7e 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -41,6 +41,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 	return !!(v->arch.pending_exceptions);
 }
 
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
+{
+	/* do real check here */
+	return 1;
+}
+
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
 	return !(v->arch.msr & MSR_WE);
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 76993941cac9..5beffc8f481e 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
+#include <linux/perf_counter.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
@@ -170,6 +171,8 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		die("Weird page fault", regs, SIGSEGV);
 	}
 
+	perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -309,6 +312,8 @@ good_area:
 	}
 	if (ret & VM_FAULT_MAJOR) {
 		current->maj_flt++;
+		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+				     regs, address);
 #ifdef CONFIG_PPC_SMLPAR
 		if (firmware_has_feature(FW_FEATURE_CMO)) {
 			preempt_disable();
@@ -316,8 +321,11 @@ good_area:
 			preempt_enable();
 		}
 #endif
-	} else
+	} else {
 		current->min_flt++;
+		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+				     regs, address);
+	}
 	up_read(&mm->mmap_sem);
 	return 0;
 
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 9da795e49337..732ee93a8e98 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -1,6 +1,7 @@
 config PPC64
 	bool "64-bit kernel"
 	default n
+	select HAVE_PERF_COUNTERS
 	help
 	  This option selects whether a 32-bit or a 64-bit kernel
 	  will be built.
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 80b513449f4c..be3581a8c294 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -333,7 +333,7 @@ static void xics_eoi_lpar(unsigned int virq)
 	lpar_xirr_info_set((0xff << 24) | irq);
 }
 
-static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
+static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 {
 	unsigned int irq;
 	int status;
@@ -342,14 +342,14 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 
 	irq = (unsigned int)irq_map[virq].hwirq;
 	if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS)
-		return;
+		return -1;
 
 	status = rtas_call(ibm_get_xive, 1, 3, xics_status, irq);
 
 	if (status) {
 		printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n",
 			__func__, irq, status);
-		return;
+		return -1;
 	}
 
 	/*
@@ -363,7 +363,7 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 		printk(KERN_WARNING
 			"%s: No online cpus in the mask %s for irq %d\n",
 			__func__, cpulist, virq);
-		return;
+		return -1;
 	}
 
 	status = rtas_call(ibm_set_xive, 3, 1, NULL,
@@ -372,8 +372,10 @@ static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 	if (status) {
 		printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n",
 			__func__, irq, status);
-		return;
+		return -1;
 	}
+
+	return 0;
 }
 
 static struct irq_chip xics_pic_direct = {
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index 9e105cbc5e5f..a4779912a5ca 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -250,7 +250,7 @@ axon_ram_probe(struct of_device *device, const struct of_device_id *device_id)
 
 	set_capacity(bank->disk, bank->size >> AXON_RAM_SECTOR_SHIFT);
 	blk_queue_make_request(bank->disk->queue, axon_ram_make_request);
-	blk_queue_hardsect_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE);
+	blk_queue_logical_block_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE);
 	add_disk(bank->disk);
 
 	bank->irq_id = irq_of_parse_and_map(device->node, 0);
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0efc12d1a3d7..352d8c3ef526 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -807,7 +807,7 @@ static void mpic_end_ipi(unsigned int irq)
 
 #endif /* CONFIG_SMP */
 
-void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
 	struct mpic *mpic = mpic_from_irq(irq);
 	unsigned int src = mpic_irq_to_hw(irq);
@@ -824,6 +824,8 @@ void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 		mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION),
 			       mpic_physmask(cpus_addr(tmp)[0]));
 	}
+
+	return 0;
 }
 
 static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type)
diff --git a/arch/powerpc/sysdev/mpic.h b/arch/powerpc/sysdev/mpic.h
index 3cef2af10f42..eff433c322a0 100644
--- a/arch/powerpc/sysdev/mpic.h
+++ b/arch/powerpc/sysdev/mpic.h
@@ -36,6 +36,6 @@ static inline int mpic_pasemi_msi_init(struct mpic *mpic)
 
 extern int mpic_set_irq_type(unsigned int virq, unsigned int flow_type);
 extern void mpic_set_vector(unsigned int virq, unsigned int vector);
-extern void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask);
+extern int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask);
 
 #endif /* _POWERPC_SYSDEV_MPIC_H */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 54ea39f96ecd..a27d0d5a6f86 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -13,6 +13,8 @@
 
 #ifndef ASM_KVM_HOST_H
 #define ASM_KVM_HOST_H
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
 #include <linux/kvm_host.h>
 #include <asm/debug.h>
 #include <asm/cpuid.h>
@@ -210,7 +212,8 @@ struct kvm_vcpu_arch {
 	s390_fp_regs      guest_fpregs;
 	unsigned int      guest_acrs[NUM_ACRS];
 	struct kvm_s390_local_interrupt local_int;
-	struct timer_list ckc_timer;
+	struct hrtimer    ckc_timer;
+	struct tasklet_struct tasklet;
 	union  {
 		cpuid_t	  cpu_id;
 		u64	  stidp_data;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 9d19803111ba..98997ccba501 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -154,17 +154,25 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 static int handle_validity(struct kvm_vcpu *vcpu)
 {
 	int viwhy = vcpu->arch.sie_block->ipb >> 16;
+	int rc;
+
 	vcpu->stat.exit_validity++;
-	if (viwhy == 0x37) {
-		fault_in_pages_writeable((char __user *)
-					 vcpu->kvm->arch.guest_origin +
-					 vcpu->arch.sie_block->prefix,
-					 PAGE_SIZE);
-		return 0;
-	}
-	VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d",
-		   viwhy);
-	return -ENOTSUPP;
+	if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix
+		<= vcpu->kvm->arch.guest_memsize - 2*PAGE_SIZE)){
+		rc = fault_in_pages_writeable((char __user *)
+			 vcpu->kvm->arch.guest_origin +
+			 vcpu->arch.sie_block->prefix,
+			 2*PAGE_SIZE);
+		if (rc)
+			/* user will receive sigsegv, exit to user */
+			rc = -ENOTSUPP;
+	} else
+		rc = -ENOTSUPP;
+
+	if (rc)
+		VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d",
+			   viwhy);
+	return rc;
 }
 
 static int handle_instruction(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 0189356fe209..f04f5301b1b4 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -12,6 +12,8 @@
 
 #include <asm/lowcore.h>
 #include <asm/uaccess.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
 #include <linux/kvm_host.h>
 #include <linux/signal.h>
 #include "kvm-s390.h"
@@ -299,13 +301,13 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 	}
 
 	if ((!rc) && atomic_read(&fi->active)) {
-		spin_lock_bh(&fi->lock);
+		spin_lock(&fi->lock);
 		list_for_each_entry(inti, &fi->list, list)
 			if (__interrupt_is_deliverable(vcpu, inti)) {
 				rc = 1;
 				break;
 			}
-		spin_unlock_bh(&fi->lock);
+		spin_unlock(&fi->lock);
 	}
 
 	if ((!rc) && (vcpu->arch.sie_block->ckc <
@@ -318,6 +320,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 	return rc;
 }
 
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
+{
+	/* do real check here */
+	return 1;
+}
+
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	return 0;
@@ -355,14 +363,12 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
-	sltime = (vcpu->arch.sie_block->ckc - now) / (0xf4240000ul / HZ) + 1;
+	sltime = ((vcpu->arch.sie_block->ckc - now)*125)>>9;
 
-	vcpu->arch.ckc_timer.expires = jiffies + sltime;
-
-	add_timer(&vcpu->arch.ckc_timer);
-	VCPU_EVENT(vcpu, 5, "enabled wait timer:%llx jiffies", sltime);
+	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
+	VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);
 no_timer:
-	spin_lock_bh(&vcpu->arch.local_int.float_int->lock);
+	spin_lock(&vcpu->arch.local_int.float_int->lock);
 	spin_lock_bh(&vcpu->arch.local_int.lock);
 	add_wait_queue(&vcpu->arch.local_int.wq, &wait);
 	while (list_empty(&vcpu->arch.local_int.list) &&
@@ -371,33 +377,46 @@ no_timer:
 		!signal_pending(current)) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		spin_unlock_bh(&vcpu->arch.local_int.lock);
-		spin_unlock_bh(&vcpu->arch.local_int.float_int->lock);
+		spin_unlock(&vcpu->arch.local_int.float_int->lock);
 		vcpu_put(vcpu);
 		schedule();
 		vcpu_load(vcpu);
-		spin_lock_bh(&vcpu->arch.local_int.float_int->lock);
+		spin_lock(&vcpu->arch.local_int.float_int->lock);
 		spin_lock_bh(&vcpu->arch.local_int.lock);
 	}
 	__unset_cpu_idle(vcpu);
 	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(&vcpu->wq, &wait);
 	spin_unlock_bh(&vcpu->arch.local_int.lock);
-	spin_unlock_bh(&vcpu->arch.local_int.float_int->lock);
-	del_timer(&vcpu->arch.ckc_timer);
+	spin_unlock(&vcpu->arch.local_int.float_int->lock);
+	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
 	return 0;
 }
 
-void kvm_s390_idle_wakeup(unsigned long data)
+void kvm_s390_tasklet(unsigned long parm)
 {
-	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm;
 
-	spin_lock_bh(&vcpu->arch.local_int.lock);
+	spin_lock(&vcpu->arch.local_int.lock);
 	vcpu->arch.local_int.timer_due = 1;
 	if (waitqueue_active(&vcpu->arch.local_int.wq))
 		wake_up_interruptible(&vcpu->arch.local_int.wq);
-	spin_unlock_bh(&vcpu->arch.local_int.lock);
+	spin_unlock(&vcpu->arch.local_int.lock);
 }
 
+/*
+ * low level hrtimer wake routine. Because this runs in hardirq context
+ * we schedule a tasklet to do the real work.
+ */
+enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
+	tasklet_schedule(&vcpu->arch.tasklet);
+
+	return HRTIMER_NORESTART;
+}
 
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 {
@@ -436,7 +455,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 	if (atomic_read(&fi->active)) {
 		do {
 			deliver = 0;
-			spin_lock_bh(&fi->lock);
+			spin_lock(&fi->lock);
 			list_for_each_entry_safe(inti, n, &fi->list, list) {
 				if (__interrupt_is_deliverable(vcpu, inti)) {
 					list_del(&inti->list);
@@ -447,7 +466,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 			}
 			if (list_empty(&fi->list))
 				atomic_set(&fi->active, 0);
-			spin_unlock_bh(&fi->lock);
+			spin_unlock(&fi->lock);
 			if (deliver) {
 				__do_deliver_interrupt(vcpu, inti);
 				kfree(inti);
@@ -512,7 +531,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 
 	mutex_lock(&kvm->lock);
 	fi = &kvm->arch.float_int;
-	spin_lock_bh(&fi->lock);
+	spin_lock(&fi->lock);
 	list_add_tail(&inti->list, &fi->list);
 	atomic_set(&fi->active, 1);
 	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
@@ -529,7 +548,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	if (waitqueue_active(&li->wq))
 		wake_up_interruptible(&li->wq);
 	spin_unlock_bh(&li->lock);
-	spin_unlock_bh(&fi->lock);
+	spin_unlock(&fi->lock);
 	mutex_unlock(&kvm->lock);
 	return 0;
 }
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f4d56e9939c9..10bccd1f8aee 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -15,6 +15,7 @@
 #include <linux/compiler.h>
 #include <linux/err.h>
 #include <linux/fs.h>
+#include <linux/hrtimer.h>
 #include <linux/init.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
@@ -195,6 +196,10 @@ out_nokvm:
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
+	if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
+		(__u64) vcpu->arch.sie_block)
+		vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
+	smp_mb();
 	free_page((unsigned long)(vcpu->arch.sie_block));
 	kvm_vcpu_uninit(vcpu);
 	kfree(vcpu);
@@ -283,8 +288,10 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->gmsor = vcpu->kvm->arch.guest_origin;
 	vcpu->arch.sie_block->ecb   = 2;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
-	setup_timer(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup,
-		 (unsigned long) vcpu);
+	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+	tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
+		     (unsigned long) vcpu);
+	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
 	get_cpu_id(&vcpu->arch.cpu_id);
 	vcpu->arch.cpu_id.version = 0xff;
 	return 0;
@@ -307,19 +314,21 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 	vcpu->arch.sie_block->icpua = id;
 	BUG_ON(!kvm->arch.sca);
-	BUG_ON(kvm->arch.sca->cpu[id].sda);
-	kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+	if (!kvm->arch.sca->cpu[id].sda)
+		kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+	else
+		BUG_ON(!kvm->vcpus[id]); /* vcpu does already exist */
 	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
 	vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
 
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
-	spin_lock_bh(&kvm->arch.float_int.lock);
+	spin_lock(&kvm->arch.float_int.lock);
 	kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
 	init_waitqueue_head(&vcpu->arch.local_int.wq);
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
-	spin_unlock_bh(&kvm->arch.float_int.lock);
+	spin_unlock(&kvm->arch.float_int.lock);
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
@@ -478,6 +487,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	vcpu_load(vcpu);
 
+	/* verify, that memory has been registered */
+	if (!vcpu->kvm->arch.guest_memsize) {
+		vcpu_put(vcpu);
+		return -EINVAL;
+	}
+
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
@@ -657,6 +672,8 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot old,
 				int user_alloc)
 {
+	int i;
+
 	/* A few sanity checks. We can have exactly one memory slot which has
 	   to start at guest virtual zero and which has to be located at a
 	   page boundary in userland and which has to end at a page boundary.
@@ -664,7 +681,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	   vmas. It is okay to mmap() and munmap() stuff in this slot after
 	   doing this call at any time */
 
-	if (mem->slot)
+	if (mem->slot || kvm->arch.guest_memsize)
 		return -EINVAL;
 
 	if (mem->guest_phys_addr)
@@ -676,15 +693,39 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	if (mem->memory_size & (PAGE_SIZE - 1))
 		return -EINVAL;
 
+	if (!user_alloc)
+		return -EINVAL;
+
+	/* lock all vcpus */
+	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+		if (!kvm->vcpus[i])
+			continue;
+		if (!mutex_trylock(&kvm->vcpus[i]->mutex))
+			goto fail_out;
+	}
+
 	kvm->arch.guest_origin = mem->userspace_addr;
 	kvm->arch.guest_memsize = mem->memory_size;
 
-	/* FIXME: we do want to interrupt running CPUs and update their memory
-	   configuration now to avoid race conditions. But hey, changing the
-	   memory layout while virtual CPUs are running is usually bad
-	   programming practice. */
+	/* update sie control blocks, and unlock all vcpus */
+	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+		if (kvm->vcpus[i]) {
+			kvm->vcpus[i]->arch.sie_block->gmsor =
+				kvm->arch.guest_origin;
+			kvm->vcpus[i]->arch.sie_block->gmslm =
+				kvm->arch.guest_memsize +
+				kvm->arch.guest_origin +
+				VIRTIODESCSPACE - 1ul;
+			mutex_unlock(&kvm->vcpus[i]->mutex);
+		}
+	}
 
 	return 0;
+
+fail_out:
+	for (; i >= 0; i--)
+		mutex_unlock(&kvm->vcpus[i]->mutex);
+	return -EINVAL;
 }
 
 void kvm_arch_flush_shadow(struct kvm *kvm)
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 00bbe69b78da..748fee872323 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -14,6 +14,7 @@
 #ifndef ARCH_S390_KVM_S390_H
 #define ARCH_S390_KVM_S390_H
 
+#include <linux/hrtimer.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
@@ -41,7 +42,8 @@ static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
 }
 
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
-void kvm_s390_idle_wakeup(unsigned long data);
+enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
+void kvm_s390_tasklet(unsigned long parm);
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
 int kvm_s390_inject_vm(struct kvm *kvm,
 		struct kvm_s390_interrupt *s390int);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 4b88834b8dd8..93ecd06e1a74 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -204,11 +204,11 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 	int cpus = 0;
 	int n;
 
-	spin_lock_bh(&fi->lock);
+	spin_lock(&fi->lock);
 	for (n = 0; n < KVM_MAX_VCPUS; n++)
 		if (fi->local_int[n])
 			cpus++;
-	spin_unlock_bh(&fi->lock);
+	spin_unlock(&fi->lock);
 
 	/* deal with other level 3 hypervisors */
 	if (stsi(mem, 3, 2, 2) == -ENOSYS)
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index f27dbedf0866..36678835034d 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -52,7 +52,7 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
 	if (cpu_addr >= KVM_MAX_VCPUS)
 		return 3; /* not operational */
 
-	spin_lock_bh(&fi->lock);
+	spin_lock(&fi->lock);
 	if (fi->local_int[cpu_addr] == NULL)
 		rc = 3; /* not operational */
 	else if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
@@ -64,7 +64,7 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
 		*reg |= SIGP_STAT_STOPPED;
 		rc = 1; /* status stored */
 	}
-	spin_unlock_bh(&fi->lock);
+	spin_unlock(&fi->lock);
 
 	VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc);
 	return rc;
@@ -86,7 +86,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
 
 	inti->type = KVM_S390_INT_EMERGENCY;
 
-	spin_lock_bh(&fi->lock);
+	spin_lock(&fi->lock);
 	li = fi->local_int[cpu_addr];
 	if (li == NULL) {
 		rc = 3; /* not operational */
@@ -102,7 +102,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
 	spin_unlock_bh(&li->lock);
 	rc = 0; /* order accepted */
 unlock:
-	spin_unlock_bh(&fi->lock);
+	spin_unlock(&fi->lock);
 	VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr);
 	return rc;
 }
@@ -123,7 +123,7 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store)
 
 	inti->type = KVM_S390_SIGP_STOP;
 
-	spin_lock_bh(&fi->lock);
+	spin_lock(&fi->lock);
 	li = fi->local_int[cpu_addr];
 	if (li == NULL) {
 		rc = 3; /* not operational */
@@ -142,7 +142,7 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store)
 	spin_unlock_bh(&li->lock);
 	rc = 0; /* order accepted */
 unlock:
-	spin_unlock_bh(&fi->lock);
+	spin_unlock(&fi->lock);
 	VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr);
 	return rc;
 }
@@ -188,7 +188,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 	if (!inti)
 		return 2; /* busy */
 
-	spin_lock_bh(&fi->lock);
+	spin_lock(&fi->lock);
 	li = fi->local_int[cpu_addr];
 
 	if ((cpu_addr >= KVM_MAX_VCPUS) || (li == NULL)) {
@@ -220,7 +220,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 out_li:
 	spin_unlock_bh(&li->lock);
 out_fi:
-	spin_unlock_bh(&fi->lock);
+	spin_unlock(&fi->lock);
 	return rc;
 }
 
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index e7390dd0283d..586cd045e2db 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -15,6 +15,7 @@ config SUPERH
 	select HAVE_IOREMAP_PROT if MMU
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
+	select RTC_LIB
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
 	  and consumer electronics; it was also used in the Sega Dreamcast
@@ -74,14 +75,18 @@ config GENERIC_IOMAP
 	bool
 
 config GENERIC_TIME
-	def_bool n
+	def_bool y
 
 config GENERIC_CLOCKEVENTS
-	def_bool n
+	def_bool y
 
 config GENERIC_CLOCKEVENTS_BROADCAST
 	bool
 
+config GENERIC_CMOS_UPDATE
+	def_bool y
+	depends on SH_SH03 || SH_DREAMCAST
+
 config GENERIC_LOCKBREAK
 	def_bool y
 	depends on SMP && PREEMPT
@@ -112,6 +117,12 @@ config SYS_SUPPORTS_PCI
 config SYS_SUPPORTS_CMT
 	bool
 
+config SYS_SUPPORTS_MTU2
+	bool
+
+config SYS_SUPPORTS_TMU
+	bool
+
 config STACKTRACE_SUPPORT
 	def_bool y
 
@@ -157,13 +168,14 @@ config CPU_SH3
 	bool
 	select CPU_HAS_INTEVT
 	select CPU_HAS_SR_RB
+	select SYS_SUPPORTS_TMU
 
 config CPU_SH4
 	bool
 	select CPU_HAS_INTEVT
 	select CPU_HAS_SR_RB
-	select CPU_HAS_PTEA if !CPU_SH4A || CPU_SHX2
 	select CPU_HAS_FPU if !CPU_SH4AL_DSP
+	select SYS_SUPPORTS_TMU
 
 config CPU_SH4A
 	bool
@@ -177,6 +189,7 @@ config CPU_SH4AL_DSP
 config CPU_SH5
 	bool
 	select CPU_HAS_FPU
+	select SYS_SUPPORTS_TMU
 
 config CPU_SHX2
 	bool
@@ -210,27 +223,32 @@ config CPU_SUBTYPE_SH7201
 	bool "Support SH7201 processor"
 	select CPU_SH2A
 	select CPU_HAS_FPU
+	select SYS_SUPPORTS_MTU2
  
 config CPU_SUBTYPE_SH7203
 	bool "Support SH7203 processor"
 	select CPU_SH2A
 	select CPU_HAS_FPU
 	select SYS_SUPPORTS_CMT
+	select SYS_SUPPORTS_MTU2
 
 config CPU_SUBTYPE_SH7206
 	bool "Support SH7206 processor"
 	select CPU_SH2A
 	select SYS_SUPPORTS_CMT
+	select SYS_SUPPORTS_MTU2
 
 config CPU_SUBTYPE_SH7263
 	bool "Support SH7263 processor"
 	select CPU_SH2A
 	select CPU_HAS_FPU
 	select SYS_SUPPORTS_CMT
+	select SYS_SUPPORTS_MTU2
 
 config CPU_SUBTYPE_MXG
 	bool "Support MX-G processor"
 	select CPU_SH2A
+	select SYS_SUPPORTS_MTU2
 	help
 	  Select MX-G if running on an R8A03022BG part.
 
@@ -283,6 +301,7 @@ config CPU_SUBTYPE_SH7720
 	bool "Support SH7720 processor"
 	select CPU_SH3
 	select CPU_HAS_DSP
+	select SYS_SUPPORTS_CMT
 	help
 	  Select SH7720 if you have a SH3-DSP SH7720 CPU.
 
@@ -290,6 +309,7 @@ config CPU_SUBTYPE_SH7721
 	bool "Support SH7721 processor"
 	select CPU_SH3
 	select CPU_HAS_DSP
+	select SYS_SUPPORTS_CMT
 	help
 	  Select SH7721 if you have a SH3-DSP SH7721 CPU.
 
@@ -347,6 +367,16 @@ config CPU_SUBTYPE_SH7723
 	help
 	  Select SH7723 if you have an SH-MobileR2 CPU.
 
+config CPU_SUBTYPE_SH7724
+	bool "Support SH7724 processor"
+	select CPU_SH4A
+	select CPU_SHX2
+	select ARCH_SHMOBILE
+	select ARCH_SPARSEMEM_ENABLE
+	select SYS_SUPPORTS_CMT
+	help
+	  Select SH7724 if you have an SH-MobileR2R CPU.
+
 config CPU_SUBTYPE_SH7763
 	bool "Support SH7763 processor"
 	select CPU_SH4A
@@ -442,48 +472,26 @@ source "arch/sh/boards/Kconfig"
 
 menu "Timer and clock configuration"
 
-config SH_TMU
-	bool "TMU timer support"
-	depends on CPU_SH3 || CPU_SH4
-	default y
-	select GENERIC_TIME
-	select GENERIC_CLOCKEVENTS
-	help
-	  This enables the use of the TMU as the system timer.
-
-config SH_CMT
-	bool "CMT timer support"
-	depends on SYS_SUPPORTS_CMT && CPU_SH2
+config SH_TIMER_TMU
+	bool "TMU timer driver"
+	depends on SYS_SUPPORTS_TMU
 	default y
 	help
-	  This enables the use of the CMT as the system timer.
+	  This enables the build of the TMU timer driver.
 
-#
-# Support for the new-style CMT driver. This will replace SH_CMT
-# once its other dependencies are merged.
-#
 config SH_TIMER_CMT
-	bool "CMT clockevents driver"
-	depends on SYS_SUPPORTS_CMT && !SH_CMT
-	select GENERIC_CLOCKEVENTS
-
-config SH_MTU2
-	bool "MTU2 timer support"
-	depends on CPU_SH2A
+	bool "CMT timer driver"
+	depends on SYS_SUPPORTS_CMT
 	default y
 	help
-	  This enables the use of the MTU2 as the system timer.
+	  This enables build of the CMT timer driver.
 
-config SH_TIMER_IRQ
-	int
-	default "28" if CPU_SUBTYPE_SH7780 || CPU_SUBTYPE_SH7785 || \
-			CPU_SUBTYPE_SH7763
-	default "86" if CPU_SUBTYPE_SH7619
-	default "140" if CPU_SUBTYPE_SH7206
-	default "142" if CPU_SUBTYPE_SH7203 && SH_CMT
-	default "153" if CPU_SUBTYPE_SH7203 && SH_MTU2
-	default "238" if CPU_SUBTYPE_MXG
-	default "16"
+config SH_TIMER_MTU2
+	bool "MTU2 timer driver"
+	depends on SYS_SUPPORTS_MTU2
+	default y
+	help
+	  This enables build of the MTU2 timer driver.
 
 config SH_PCLK_FREQ
 	int "Peripheral clock frequency (in Hz)"
@@ -494,7 +502,7 @@ config SH_PCLK_FREQ
 			      CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7705 || \
 			      CPU_SUBTYPE_SH7203 || CPU_SUBTYPE_SH7206 || \
 			      CPU_SUBTYPE_SH7263 || CPU_SUBTYPE_MXG    || \
-			      CPU_SUBTYPE_SH7786
+			      CPU_SUBTYPE_SH7786 || CPU_SUBTYPE_SH7724
 	default "60000000" if CPU_SUBTYPE_SH7751 || CPU_SUBTYPE_SH7751R
 	default "66000000" if CPU_SUBTYPE_SH4_202
 	default "50000000"
@@ -503,6 +511,13 @@ config SH_PCLK_FREQ
 	  This is necessary for determining the reference clock value on
 	  platforms lacking an RTC.
 
+config SH_CLK_CPG
+	def_bool y
+
+config SH_CLK_CPG_LEGACY
+	depends on SH_CLK_CPG
+	def_bool y if !CPU_SUBTYPE_SH7785 && !ARCH_SHMOBILE
+
 config SH_CLK_MD
 	int "CPU Mode Pin Setting"
 	depends on CPU_SH2
@@ -663,27 +678,54 @@ config GUSA_RB
 	  LLSC, this should be more efficient than the other alternative of
 	  disabling interrupts around the atomic sequence.
 
+config SPARSE_IRQ
+	bool "Support sparse irq numbering"
+	depends on EXPERIMENTAL
+	help
+	  This enables support for sparse irqs. This is useful in general
+	  as most CPUs have a fairly sparse array of IRQ vectors, which
+	  the irq_desc then maps directly on to. Systems with a high
+	  number of off-chip IRQs will want to treat this as
+	  experimental until they have been independently verified.
+
+	  If you don't know what to do here, say N.
+
 endmenu
 
 menu "Boot options"
 
 config ZERO_PAGE_OFFSET
-	hex "Zero page offset"
-	default "0x00004000" if SH_SH03
-	default "0x00010000" if PAGE_SIZE_64KB
+	hex
+	default "0x00010000" if PAGE_SIZE_64KB || SH_RTS7751R2D || \
+				SH_7751_SOLUTION_ENGINE
+	default "0x00004000" if PAGE_SIZE_16KB || SH_SH03
 	default "0x00002000" if PAGE_SIZE_8KB
 	default "0x00001000"
 	help
 	  This sets the default offset of zero page.
 
 config BOOT_LINK_OFFSET
-	hex "Link address offset for booting"
+	hex
+	default "0x00210000" if SH_SHMIN
+	default "0x00400000" if SH_CAYMAN
+	default "0x00810000" if SH_7780_SOLUTION_ENGINE
+	default "0x009e0000" if SH_TITAN
+	default "0x01800000" if SH_SDK7780
+	default "0x02000000" if SH_EDOSK7760
 	default "0x00800000"
 	help
 	  This option allows you to set the link address offset of the zImage.
 	  This can be useful if you are on a board which has a small amount of
 	  memory.
 
+config ENTRY_OFFSET
+	hex
+	default "0x00001000" if PAGE_SIZE_4KB
+	default "0x00002000" if PAGE_SIZE_8KB
+	default "0x00004000" if PAGE_SIZE_16KB
+	default "0x00010000" if PAGE_SIZE_64KB
+	default "0x00000000"
+
 config UBC_WAKEUP
 	bool "Wakeup UBC on startup"
 	depends on CPU_SH4 && !CPU_SH4A
diff --git a/arch/sh/Kconfig.cpu b/arch/sh/Kconfig.cpu
index c7d704381a6d..cd6e3ea598d5 100644
--- a/arch/sh/Kconfig.cpu
+++ b/arch/sh/Kconfig.cpu
@@ -76,11 +76,6 @@ config SPECULATIVE_EXECUTION
 
 	  If unsure, say N.
 
-config SH64_USER_MISALIGNED_FIXUP
-	def_bool y
-	prompt "Fixup misaligned loads/stores occurring in user mode"
-	depends on SUPERH64
-
 config SH64_ID2815_WORKAROUND
 	bool "Include workaround for SH5-101 cut2 silicon defect ID2815"
 	depends on CPU_SUBTYPE_SH5_101
@@ -101,9 +96,6 @@ config CPU_HAS_SR_RB
 	  See <file:Documentation/sh/register-banks.txt> for further
 	  information on SR.RB and register banking in the kernel in general.
 
-config CPU_HAS_PTEA
-	bool
-
 config CPU_HAS_PTEAEX
 	bool
 
diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug
index 0d62681f72a0..8179cc9be9a4 100644
--- a/arch/sh/Kconfig.debug
+++ b/arch/sh/Kconfig.debug
@@ -38,10 +38,10 @@ config EARLY_SCIF_CONSOLE_PORT
 	default "0xffe00000" if CPU_SUBTYPE_SH7780 || CPU_SUBTYPE_SH7763 || \
 				CPU_SUBTYPE_SH7722 || CPU_SUBTYPE_SH7366 || \
 				CPU_SUBTYPE_SH7343
-	default "0xffe80000" if CPU_SH4
 	default "0xffea0000" if CPU_SUBTYPE_SH7785
 	default "0xfffe8000" if CPU_SUBTYPE_SH7203
 	default "0xfffe9800" if CPU_SUBTYPE_SH7206 || CPU_SUBTYPE_SH7263
+	default "0xffe80000" if CPU_SH4
 	default "0x00000000"
 
 config EARLY_PRINTK
@@ -92,7 +92,7 @@ config 4KSTACKS
 
 config IRQSTACKS
 	bool "Use separate kernel stacks when processing interrupts"
-	depends on DEBUG_KERNEL && SUPERH32
+	depends on DEBUG_KERNEL && SUPERH32 && BROKEN
 	help
 	  If you say Y here the kernel will use separate kernel stacks
 	  for handling hard and soft interrupts.  This can help avoid
@@ -122,27 +122,8 @@ config SH_NO_BSS_INIT
 	  For all other cases, say N. If this option seems perplexing, or
 	  you aren't sure, say N.
 
-config MORE_COMPILE_OPTIONS
-	bool "Add any additional compile options"
-	help
-	  If you want to add additional CFLAGS to the kernel build, enable this
-	  option and then enter what you would like to add in the next question.
-	  Note however that -g is already appended with the selection of KGDB.
-
-config COMPILE_OPTIONS
-	string "Additional compile arguments"
-	depends on MORE_COMPILE_OPTIONS
-
 config SH64_SR_WATCH
 	bool "Debug: set SR.WATCH to enable hardware watchpoints and trace"
 	depends on SUPERH64
 
-config POOR_MANS_STRACE
-	bool "Debug: enable rudimentary strace facility"
-	depends on SUPERH64
-	help
-	  This option allows system calls to be traced to the console.  It also
-	  aids in detecting kernel stack underflow.  It is useful for debugging
-	  early-userland problems (e.g. init incurring fatal exceptions.)
-
 endmenu
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index bece1f7535f2..75d049b03f7e 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -70,9 +70,6 @@ cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -ml
 cflags-y	+= $(call cc-option,-mno-fdpic)
 cflags-y	+= $(isaflags-y) -ffreestanding
 
-cflags-$(CONFIG_MORE_COMPILE_OPTIONS)	+= \
-	$(shell echo $(CONFIG_COMPILE_OPTIONS) | sed -e 's/"//g')
-
 OBJCOPYFLAGS	:= -O binary -R .note -R .note.gnu.build-id -R .comment \
 		   -R .stab -R .stabstr -S
 
@@ -85,7 +82,6 @@ defaultimage-$(CONFIG_SH_7206_SOLUTION_ENGINE)	:= vmlinux
 defaultimage-$(CONFIG_SH_7619_SOLUTION_ENGINE)	:= vmlinux
 
 # Set some sensible Kbuild defaults
-KBUILD_DEFCONFIG	:= shx3_defconfig
 KBUILD_IMAGE		:= $(defaultimage-y)
 
 #
@@ -93,26 +89,38 @@ KBUILD_IMAGE		:= $(defaultimage-y)
 # error messages during linking.
 #
 ifdef CONFIG_SUPERH32
-UTS_MACHINE	:= sh
-LDFLAGS_vmlinux	+= -e _stext
+UTS_MACHINE		:= sh
+BITS			:= 32
+LDFLAGS_vmlinux		+= -e _stext
+KBUILD_DEFCONFIG	:= shx3_defconfig
 else
-UTS_MACHINE	:= sh64
-LDFLAGS_vmlinux	+= --defsym phys_stext=_stext-$(CONFIG_PAGE_OFFSET) \
-		   --defsym phys_stext_shmedia=phys_stext+1 \
-		   -e phys_stext_shmedia
+UTS_MACHINE		:= sh64
+BITS			:= 64
+LDFLAGS_vmlinux		+= --defsym phys_stext=_stext-$(CONFIG_PAGE_OFFSET) \
+			   --defsym phys_stext_shmedia=phys_stext+1 \
+			   -e phys_stext_shmedia
+KBUILD_DEFCONFIG	:= cayman_defconfig
+endif
+
+ifneq ($(SUBARCH),$(ARCH))
+  ifeq ($(CROSS_COMPILE),)
+    CROSS_COMPILE := $(call cc-cross-prefix, $(UTS_MACHINE)-linux-  $(UTS_MACHINE)-linux-gnu-  $(UTS_MACHINE)-unknown-linux-gnu-)
+  endif
 endif
 
 ifdef CONFIG_CPU_LITTLE_ENDIAN
-LDFLAGS_vmlinux		+= --defsym 'jiffies=jiffies_64'
+ld-bfd			:= elf32-$(UTS_MACHINE)-linux
+LDFLAGS_vmlinux		+= --defsym 'jiffies=jiffies_64' --oformat $(ld-bfd)
 LDFLAGS			+= -EL
 else
-LDFLAGS_vmlinux		+= --defsym 'jiffies=jiffies_64+4'
+ld-bfd			:= elf32-$(UTS_MACHINE)big-linux
+LDFLAGS_vmlinux		+= --defsym 'jiffies=jiffies_64+4' --oformat $(ld-bfd)
 LDFLAGS			+= -EB
 endif
 
-head-y			:= arch/sh/kernel/init_task.o
-head-$(CONFIG_SUPERH32)	+= arch/sh/kernel/head_32.o
-head-$(CONFIG_SUPERH64)	+= arch/sh/kernel/head_64.o
+export ld-bfd BITS
+
+head-y	:= arch/sh/kernel/init_task.o arch/sh/kernel/head_$(BITS).o
 
 core-y				+= arch/sh/kernel/ arch/sh/mm/ arch/sh/boards/
 core-$(CONFIG_SH_FPU_EMU)	+= arch/sh/math-emu/
@@ -193,10 +201,11 @@ zImage uImage uImage.srec vmlinux.srec: vmlinux
 
 compressed: zImage
 
-archprepare: maketools arch/sh/lib64/syscalltab.h
+archprepare: maketools
 
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
+	$(Q)$(MAKE) $(clean)=arch/sh/kernel/vsyscall
 
 define archhelp
 	@echo '* zImage 	           - Compressed kernel image'
@@ -205,34 +214,4 @@ define archhelp
 	@echo '  uImage.srec  	           - Create an S-record for U-Boot'
 endef
 
-define filechk_gen-syscalltab
-       (set -e; \
-	echo "/*"; \
-	echo " * DO NOT MODIFY."; \
-	echo " *"; \
-	echo " * This file was generated by arch/sh/Makefile"; \
-	echo " * Any changes will be reverted at build time."; \
-	echo " */"; \
-	echo ""; \
-	echo "#ifndef __SYSCALLTAB_H"; \
-	echo "#define __SYSCALLTAB_H"; \
-	echo ""; \
-	echo "#include <linux/kernel.h>"; \
-	echo ""; \
-	echo "struct syscall_info {"; \
-	echo "	const char *name;"; \
-	echo "} syscall_info_table[] = {"; \
-	sed -e '/^.*\.long /!d;s//	{ "/;s/\(\([^/]*\)\/\)\{1\}.*/\2/; \
-		s/[ \t]*$$//g;s/$$/" },/;s/\("\)sys_/\1/g'; \
-	echo "};"; \
-	echo ""; \
-	echo "#define NUM_SYSCALL_INFO_ENTRIES ARRAY_SIZE(syscall_info_table)";\
-	echo ""; \
-	echo "#endif /* __SYSCALLTAB_H */" )
-endef
-
-arch/sh/lib64/syscalltab.h: arch/sh/kernel/syscalls_64.S
-	$(call filechk,gen-syscalltab)
-
-CLEAN_FILES += arch/sh/lib64/syscalltab.h \
-	       include/asm-sh/machtypes.h
+CLEAN_FILES += include/asm-sh/machtypes.h
diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig
index dcc1af8a2cfe..1c91b1f565d5 100644
--- a/arch/sh/boards/Kconfig
+++ b/arch/sh/boards/Kconfig
@@ -46,6 +46,15 @@ config SH_7722_SOLUTION_ENGINE
 	  Select 7722 SolutionEngine if configuring for a Hitachi SH772
 	  evaluation board.
 
+config SH_7724_SOLUTION_ENGINE
+	bool "SolutionEngine7724"
+	select SOLUTION_ENGINE
+	depends on CPU_SUBTYPE_SH7724
+	select ARCH_REQUIRE_GPIOLIB
+	help
+	  Select 7724 SolutionEngine if configuring for a Hitachi SH7724
+	  evaluation board.
+
 config SH_7751_SOLUTION_ENGINE
 	bool "SolutionEngine7751"
 	select SOLUTION_ENGINE
@@ -121,7 +130,7 @@ config SH_RTS7751R2D
 	bool "RTS7751R2D"
 	depends on CPU_SUBTYPE_SH7751R
 	select SYS_SUPPORTS_PCI
-	select IO_TRAPPED
+	select IO_TRAPPED if MMU
 	help
 	  Select RTS7751R2D if configuring for a Renesas Technology
 	  Sales SH-Graphics board.
@@ -145,13 +154,13 @@ config SH_HIGHLANDER
 	bool "Highlander"
 	depends on CPU_SUBTYPE_SH7780 || CPU_SUBTYPE_SH7785
 	select SYS_SUPPORTS_PCI
-	select IO_TRAPPED
+	select IO_TRAPPED if MMU
 
 config SH_SH7785LCR
 	bool "SH7785LCR"
 	depends on CPU_SUBTYPE_SH7785
 	select SYS_SUPPORTS_PCI
-	select IO_TRAPPED
+	select IO_TRAPPED if MMU
 
 config SH_SH7785LCR_29BIT_PHYSMAPS
 	bool "SH7785LCR 29bit physmaps"
diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c
index f2a29641b6a3..1c4d83ef2a47 100644
--- a/arch/sh/boards/board-ap325rxa.c
+++ b/arch/sh/boards/board-ap325rxa.c
@@ -535,6 +535,18 @@ static int __init ap325rxa_devices_setup(void)
 }
 device_initcall(ap325rxa_devices_setup);
 
+/* Return the board specific boot mode pin configuration */
+static int ap325rxa_mode_pins(void)
+{
+	/* MD0=0, MD1=0, MD2=0: Clock Mode 0
+	 * MD3=0: 16-bit Area0 Bus Width
+	 * MD5=1: Little Endian
+	 * TSTMD=1, MD8=1: Test Mode Disabled
+	 */
+	return MODE_PIN5 | MODE_PIN8;
+}
+
 static struct sh_machine_vector mv_ap325rxa __initmv = {
 	.mv_name = "AP-325RXA",
+	.mv_mode_pins = ap325rxa_mode_pins,
 };
diff --git a/arch/sh/boards/board-sh7785lcr.c b/arch/sh/boards/board-sh7785lcr.c
index 6f94f17adc46..7be56fb06c1f 100644
--- a/arch/sh/boards/board-sh7785lcr.c
+++ b/arch/sh/boards/board-sh7785lcr.c
@@ -2,12 +2,12 @@
  * Renesas Technology Corp. R0P7785LC0011RL Support.
  *
  * Copyright (C) 2008  Yoshihiro Shimoda
+ * Copyright (C) 2009  Paul Mundt
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  */
-
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/sm501.h>
@@ -19,8 +19,12 @@
 #include <linux/i2c-pca-platform.h>
 #include <linux/i2c-algo-pca.h>
 #include <linux/irq.h>
-#include <asm/heartbeat.h>
+#include <linux/clk.h>
+#include <linux/errno.h>
 #include <mach/sh7785lcr.h>
+#include <asm/heartbeat.h>
+#include <asm/clock.h>
+#include <cpu/sh7785.h>
 
 /*
  * NOTE: This board has 2 physical memory maps.
@@ -273,6 +277,20 @@ void __init init_sh7785lcr_IRQ(void)
 	plat_irq_setup_pins(IRQ_MODE_IRQ3210);
 }
 
+static int sh7785lcr_clk_init(void)
+{
+	struct clk *clk;
+	int ret;
+
+	clk = clk_get(NULL, "extal");
+	if (!clk || IS_ERR(clk))
+		return PTR_ERR(clk);
+	ret = clk_set_rate(clk, 33333333);
+	clk_put(clk);
+
+	return ret;
+}
+
 static void sh7785lcr_power_off(void)
 {
 	unsigned char *p;
@@ -303,12 +321,34 @@ static void __init sh7785lcr_setup(char **cmdline_p)
 	writel(0x000307c2, sm501_reg);
 }
 
+/* Return the board specific boot mode pin configuration */
+static int sh7785lcr_mode_pins(void)
+{
+	int value = 0;
+
+	/* These are the factory default settings of S1 and S2.
+	 * If you change these dip switches then you will need to
+	 * adjust the values below as well.
+	 */
+	value |= MODE_PIN4; /* Clock Mode 16 */
+	value |= MODE_PIN5; /* 32-bit Area0 bus width */
+	value |= MODE_PIN6; /* 32-bit Area0 bus width */
+	value |= MODE_PIN7; /* Area 0 SRAM interface [fixed] */
+	value |= MODE_PIN8; /* Little Endian */
+	value |= MODE_PIN9; /* Master Mode */
+	value |= MODE_PIN14; /* No PLL step-up */
+
+	return value;
+}
+
 /*
  * The Machine Vector
  */
 static struct sh_machine_vector mv_sh7785lcr __initmv = {
 	.mv_name		= "SH7785LCR",
 	.mv_setup		= sh7785lcr_setup,
+	.mv_clk_init		= sh7785lcr_clk_init,
 	.mv_init_irq		= init_sh7785lcr_IRQ,
+	.mv_mode_pins		= sh7785lcr_mode_pins,
 };
 
diff --git a/arch/sh/boards/mach-cayman/Makefile b/arch/sh/boards/mach-cayman/Makefile
index cafe1ac3b29c..00fa3eaecb1b 100644
--- a/arch/sh/boards/mach-cayman/Makefile
+++ b/arch/sh/boards/mach-cayman/Makefile
@@ -1,4 +1,4 @@
 #
 # Makefile for the Hitachi Cayman specific parts of the kernel
 #
-obj-y := setup.o irq.o
+obj-y := setup.o irq.o panic.o
diff --git a/arch/sh/boards/mach-cayman/irq.c b/arch/sh/boards/mach-cayman/irq.c
index da62ad516994..33f770856319 100644
--- a/arch/sh/boards/mach-cayman/irq.c
+++ b/arch/sh/boards/mach-cayman/irq.c
@@ -142,26 +142,11 @@ int cayman_irq_demux(int evt)
 	return irq;
 }
 
-#if defined(CONFIG_PROC_FS) && defined(CONFIG_SYSCTL)
-int cayman_irq_describe(char* p, int irq)
-{
-	if (irq < NR_INTC_IRQS) {
-		return intc_irq_describe(p, irq);
-	} else if (irq < NR_INTC_IRQS + 8) {
-		return sprintf(p, "(SMSC %d)", irq - NR_INTC_IRQS);
-	} else if ((irq >= NR_INTC_IRQS + 24) && (irq < NR_INTC_IRQS + 32)) {
-		return sprintf(p, "(PCI2 %d)", irq - (NR_INTC_IRQS + 24));
-	}
-
-	return 0;
-}
-#endif
-
 void init_cayman_irq(void)
 {
 	int i;
 
-	epld_virt = onchip_remap(EPLD_BASE, 1024, "EPLD");
+	epld_virt = (unsigned long)ioremap_nocache(EPLD_BASE, 1024);
 	if (!epld_virt) {
 		printk(KERN_ERR "Cayman IRQ: Unable to remap EPLD\n");
 		return;
diff --git a/arch/sh/boards/mach-cayman/panic.c b/arch/sh/boards/mach-cayman/panic.c
new file mode 100644
index 000000000000..d1e67306d07c
--- /dev/null
+++ b/arch/sh/boards/mach-cayman/panic.c
@@ -0,0 +1,49 @@
+/*
+ * Copyright (C) 2003  Richard Curnow, SuperH UK Limited
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <cpu/registers.h>
+
+/* THIS IS A PHYSICAL ADDRESS */
+#define HDSP2534_ADDR (0x04002100)
+
+static void poor_mans_delay(void)
+{
+	int i;
+
+	for (i = 0; i < 2500000; i++)
+		cpu_relax();
+}
+
+static void show_value(unsigned long x)
+{
+	int i;
+	unsigned nibble;
+	for (i = 0; i < 8; i++) {
+		nibble = ((x >> (i * 4)) & 0xf);
+
+		__raw_writeb(nibble + ((nibble > 9) ? 55 : 48),
+			  HDSP2534_ADDR + 0xe0 + ((7 - i) << 2));
+	}
+}
+
+void
+panic_handler(unsigned long panicPC, unsigned long panicSSR,
+	      unsigned long panicEXPEVT)
+{
+	while (1) {
+		/* This piece of code displays the PC on the LED display */
+		show_value(panicPC);
+		poor_mans_delay();
+		show_value(panicSSR);
+		poor_mans_delay();
+		show_value(panicEXPEVT);
+		poor_mans_delay();
+	}
+}
diff --git a/arch/sh/boards/mach-cayman/setup.c b/arch/sh/boards/mach-cayman/setup.c
index e7f9cc5f2ff1..7e8216ac31bd 100644
--- a/arch/sh/boards/mach-cayman/setup.c
+++ b/arch/sh/boards/mach-cayman/setup.c
@@ -102,7 +102,7 @@ static int __init smsc_superio_setup(void)
 {
 	unsigned char devid, devrev;
 
-	smsc_superio_virt = onchip_remap(SMSC_SUPERIO_BASE, 1024, "SMSC SuperIO");
+	smsc_superio_virt = (unsigned long)ioremap_nocache(SMSC_SUPERIO_BASE, 1024);
 	if (!smsc_superio_virt) {
 		panic("Unable to remap SMSC SuperIO\n");
 	}
diff --git a/arch/sh/boards/mach-dreamcast/setup.c b/arch/sh/boards/mach-dreamcast/setup.c
index d1bee4884cd6..ebe99227d4e6 100644
--- a/arch/sh/boards/mach-dreamcast/setup.c
+++ b/arch/sh/boards/mach-dreamcast/setup.c
@@ -30,7 +30,6 @@
 
 extern struct irq_chip systemasic_int;
 extern void aica_time_init(void);
-extern int gapspci_init(void);
 extern int systemasic_irq_demux(int);
 
 static void __init dreamcast_setup(char **cmdline_p)
@@ -51,11 +50,6 @@ static void __init dreamcast_setup(char **cmdline_p)
 					 handle_level_irq);
 
 	board_time_init = aica_time_init;
-
-#ifdef CONFIG_PCI
-	if (gapspci_init() < 0)
-		printk(KERN_WARNING "GAPSPCI was not detected.\n");
-#endif
 }
 
 static struct sh_machine_vector mv_dreamcast __initmv = {
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 1ee1de0bc1c3..6ed401cd3156 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -584,3 +584,22 @@ static int __init migor_devices_setup(void)
 	return platform_add_devices(migor_devices, ARRAY_SIZE(migor_devices));
 }
 __initcall(migor_devices_setup);
+
+/* Return the board specific boot mode pin configuration */
+static int migor_mode_pins(void)
+{
+	/* MD0=1, MD1=1, MD2=0: Clock Mode 3
+	 * MD3=0: 16-bit Area0 Bus Width
+	 * MD5=1: Little Endian
+	 * TSTMD=1, MD8=0: Test Mode Disabled
+	 */
+	return MODE_PIN0 | MODE_PIN1 | MODE_PIN5;
+}
+
+/*
+ * The Machine Vector
+ */
+static struct sh_machine_vector mv_migor __initmv = {
+	.mv_name		= "Migo-R",
+	.mv_mode_pins		= migor_mode_pins,
+};
diff --git a/arch/sh/boards/mach-r2d/setup.c b/arch/sh/boards/mach-r2d/setup.c
index c585be00956e..a625ecb93e47 100644
--- a/arch/sh/boards/mach-r2d/setup.c
+++ b/arch/sh/boards/mach-r2d/setup.c
@@ -10,6 +10,9 @@
  */
 #include <linux/init.h>
 #include <linux/platform_device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
 #include <linux/ata_platform.h>
 #include <linux/sm501.h>
 #include <linux/sm501-regs.h>
@@ -181,6 +184,50 @@ static struct platform_device sm501_device = {
 	.resource	= sm501_resources,
 };
 
+static struct mtd_partition r2d_partitions[] = {
+	{
+		.name		= "U-Boot",
+		.offset		= 0x00000000,
+		.size		= 0x00040000,
+		.mask_flags	= MTD_WRITEABLE,
+	}, {
+		.name		= "Environment",
+		.offset		= MTDPART_OFS_NXTBLK,
+		.size		= 0x00040000,
+		.mask_flags	= MTD_WRITEABLE,
+	}, {
+		.name		= "Kernel",
+		.offset		= MTDPART_OFS_NXTBLK,
+		.size		= 0x001c0000,
+	}, {
+		.name		= "Flash_FS",
+		.offset		= MTDPART_OFS_NXTBLK,
+		.size		= MTDPART_SIZ_FULL,
+	}
+};
+
+static struct physmap_flash_data flash_data = {
+	.width		= 2,
+	.nr_parts	= ARRAY_SIZE(r2d_partitions),
+	.parts		= r2d_partitions,
+};
+
+static struct resource flash_resource = {
+	.start		= 0x00000000,
+	.end		= 0x02000000,
+	.flags		= IORESOURCE_MEM,
+};
+
+static struct platform_device flash_device = {
+	.name		= "physmap-flash",
+	.id		= -1,
+	.resource	= &flash_resource,
+	.num_resources	= 1,
+	.dev		= {
+		.platform_data = &flash_data,
+	},
+};
+
 static struct platform_device *rts7751r2d_devices[] __initdata = {
 	&sm501_device,
 	&heartbeat_device,
@@ -203,6 +250,9 @@ static int __init rts7751r2d_devices_setup(void)
 	if (register_trapped_io(&cf_trapped_io) == 0)
 		platform_device_register(&cf_ide_device);
 
+	if (mach_is_r2d_plus())
+		platform_device_register(&flash_device);
+
 	spi_register_board_info(spi_bus, ARRAY_SIZE(spi_bus));
 
 	return platform_add_devices(rts7751r2d_devices,
diff --git a/arch/sh/boards/mach-se/7724/Makefile b/arch/sh/boards/mach-se/7724/Makefile
new file mode 100644
index 000000000000..349cbd6ce82d
--- /dev/null
+++ b/arch/sh/boards/mach-se/7724/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the HITACHI UL SolutionEngine 7724 specific parts of the kernel
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+#
+
+obj-y	 := setup.o irq.o
\ No newline at end of file
diff --git a/arch/sh/boards/mach-se/7724/irq.c b/arch/sh/boards/mach-se/7724/irq.c
new file mode 100644
index 000000000000..f76cf3b49f23
--- /dev/null
+++ b/arch/sh/boards/mach-se/7724/irq.c
@@ -0,0 +1,139 @@
+/*
+ * linux/arch/sh/boards/se/7724/irq.c
+ *
+ * Copyright (C) 2009 Renesas Solutions Corp.
+ *
+ * Kuninori Morimoto <morimoto.kuninori@renesas.com>
+ *
+ * Based on  linux/arch/sh/boards/se/7722/irq.c
+ * Copyright (C) 2007  Nobuhiro Iwamatsu
+ *
+ * Hitachi UL SolutionEngine 7724 Support.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <asm/irq.h>
+#include <asm/io.h>
+#include <mach-se/mach/se7724.h>
+
+struct fpga_irq {
+	unsigned long  sraddr;
+	unsigned long  mraddr;
+	unsigned short mask;
+	unsigned int   base;
+};
+
+static unsigned int fpga2irq(unsigned int irq)
+{
+	if (irq >= IRQ0_BASE &&
+	    irq <= IRQ0_END)
+		return IRQ0_IRQ;
+	else if (irq >= IRQ1_BASE &&
+		 irq <= IRQ1_END)
+		return IRQ1_IRQ;
+	else
+		return IRQ2_IRQ;
+}
+
+static struct fpga_irq get_fpga_irq(unsigned int irq)
+{
+	struct fpga_irq set;
+
+	switch (irq) {
+	case IRQ0_IRQ:
+		set.sraddr = IRQ0_SR;
+		set.mraddr = IRQ0_MR;
+		set.mask   = IRQ0_MASK;
+		set.base   = IRQ0_BASE;
+		break;
+	case IRQ1_IRQ:
+		set.sraddr = IRQ1_SR;
+		set.mraddr = IRQ1_MR;
+		set.mask   = IRQ1_MASK;
+		set.base   = IRQ1_BASE;
+		break;
+	default:
+		set.sraddr = IRQ2_SR;
+		set.mraddr = IRQ2_MR;
+		set.mask   = IRQ2_MASK;
+		set.base   = IRQ2_BASE;
+		break;
+	}
+
+	return set;
+}
+
+static void disable_se7724_irq(unsigned int irq)
+{
+	struct fpga_irq set = get_fpga_irq(fpga2irq(irq));
+	unsigned int bit = irq - set.base;
+	ctrl_outw(ctrl_inw(set.mraddr) | 0x0001 << bit, set.mraddr);
+}
+
+static void enable_se7724_irq(unsigned int irq)
+{
+	struct fpga_irq set = get_fpga_irq(fpga2irq(irq));
+	unsigned int bit = irq - set.base;
+	ctrl_outw(ctrl_inw(set.mraddr) & ~(0x0001 << bit), set.mraddr);
+}
+
+static struct irq_chip se7724_irq_chip __read_mostly = {
+	.name           = "SE7724-FPGA",
+	.mask           = disable_se7724_irq,
+	.unmask         = enable_se7724_irq,
+	.mask_ack       = disable_se7724_irq,
+};
+
+static void se7724_irq_demux(unsigned int irq, struct irq_desc *desc)
+{
+	struct fpga_irq set = get_fpga_irq(irq);
+	unsigned short intv = ctrl_inw(set.sraddr);
+	struct irq_desc *ext_desc;
+	unsigned int ext_irq = set.base;
+
+	intv &= set.mask;
+
+	while (intv) {
+		if (intv & 0x0001) {
+			ext_desc = irq_desc + ext_irq;
+			handle_level_irq(ext_irq, ext_desc);
+		}
+		intv >>= 1;
+		ext_irq++;
+	}
+}
+
+/*
+ * Initialize IRQ setting
+ */
+void __init init_se7724_IRQ(void)
+{
+	int i;
+
+	ctrl_outw(0xffff, IRQ0_MR);  /* mask all */
+	ctrl_outw(0xffff, IRQ1_MR);  /* mask all */
+	ctrl_outw(0xffff, IRQ2_MR);  /* mask all */
+	ctrl_outw(0x0000, IRQ0_SR);  /* clear irq */
+	ctrl_outw(0x0000, IRQ1_SR);  /* clear irq */
+	ctrl_outw(0x0000, IRQ2_SR);  /* clear irq */
+	ctrl_outw(0x002a, IRQ_MODE); /* set irq type */
+
+	for (i = 0; i < SE7724_FPGA_IRQ_NR; i++)
+		set_irq_chip_and_handler_name(SE7724_FPGA_IRQ_BASE + i,
+					      &se7724_irq_chip,
+					      handle_level_irq, "level");
+
+	set_irq_chained_handler(IRQ0_IRQ, se7724_irq_demux);
+	set_irq_type(IRQ0_IRQ, IRQ_TYPE_LEVEL_LOW);
+
+	set_irq_chained_handler(IRQ1_IRQ, se7724_irq_demux);
+	set_irq_type(IRQ1_IRQ, IRQ_TYPE_LEVEL_LOW);
+
+	set_irq_chained_handler(IRQ2_IRQ, se7724_irq_demux);
+	set_irq_type(IRQ2_IRQ, IRQ_TYPE_LEVEL_LOW);
+}
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
new file mode 100644
index 000000000000..9cd04bd558b8
--- /dev/null
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -0,0 +1,448 @@
+/*
+ * linux/arch/sh/boards/se/7724/setup.c
+ *
+ * Copyright (C) 2009 Renesas Solutions Corp.
+ *
+ * Kuninori Morimoto <morimoto.kuninori@renesas.com>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/physmap.h>
+#include <linux/delay.h>
+#include <linux/smc91x.h>
+#include <linux/gpio.h>
+#include <linux/input.h>
+#include <video/sh_mobile_lcdc.h>
+#include <media/sh_mobile_ceu.h>
+#include <asm/io.h>
+#include <asm/heartbeat.h>
+#include <asm/sh_keysc.h>
+#include <cpu/sh7724.h>
+#include <mach-se/mach/se7724.h>
+
+/*
+ * SWx    1234 5678
+ * ------------------------------------
+ * SW31 : 1001 1100    : default
+ * SW32 : 0111 1111    : use on board flash
+ *
+ * SW41 : abxx xxxx  -> a = 0 : Analog  monitor
+ *                          1 : Digital monitor
+ *                      b = 0 : VGA
+ *                          1 : SVGA
+ */
+
+/* Heartbeat */
+static struct heartbeat_data heartbeat_data = {
+	.regsize = 16,
+};
+
+static struct resource heartbeat_resources[] = {
+	[0] = {
+		.start  = PA_LED,
+		.end    = PA_LED,
+		.flags  = IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device heartbeat_device = {
+	.name           = "heartbeat",
+	.id             = -1,
+	.dev = {
+		.platform_data = &heartbeat_data,
+	},
+	.num_resources  = ARRAY_SIZE(heartbeat_resources),
+	.resource       = heartbeat_resources,
+};
+
+/* LAN91C111 */
+static struct smc91x_platdata smc91x_info = {
+	.flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+};
+
+static struct resource smc91x_eth_resources[] = {
+	[0] = {
+		.name   = "SMC91C111" ,
+		.start  = 0x1a300300,
+		.end    = 0x1a30030f,
+		.flags  = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = IRQ0_SMC,
+		.flags  = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
+	},
+};
+
+static struct platform_device smc91x_eth_device = {
+	.name	= "smc91x",
+	.num_resources  = ARRAY_SIZE(smc91x_eth_resources),
+	.resource       = smc91x_eth_resources,
+	.dev	= {
+		.platform_data	= &smc91x_info,
+	},
+};
+
+/* MTD */
+static struct mtd_partition nor_flash_partitions[] = {
+	{
+		.name = "uboot",
+		.offset = 0,
+		.size = (1 * 1024 * 1024),
+		.mask_flags = MTD_WRITEABLE,	/* Read-only */
+	}, {
+		.name = "kernel",
+		.offset = MTDPART_OFS_APPEND,
+		.size = (2 * 1024 * 1024),
+	}, {
+		.name = "free-area",
+		.offset = MTDPART_OFS_APPEND,
+		.size = MTDPART_SIZ_FULL,
+	},
+};
+
+static struct physmap_flash_data nor_flash_data = {
+	.width		= 2,
+	.parts		= nor_flash_partitions,
+	.nr_parts	= ARRAY_SIZE(nor_flash_partitions),
+};
+
+static struct resource nor_flash_resources[] = {
+	[0] = {
+		.name	= "NOR Flash",
+		.start	= 0x00000000,
+		.end	= 0x01ffffff,
+		.flags	= IORESOURCE_MEM,
+	}
+};
+
+static struct platform_device nor_flash_device = {
+	.name		= "physmap-flash",
+	.resource	= nor_flash_resources,
+	.num_resources	= ARRAY_SIZE(nor_flash_resources),
+	.dev		= {
+		.platform_data = &nor_flash_data,
+	},
+};
+
+/* LCDC */
+static struct sh_mobile_lcdc_info lcdc_info = {
+	.clock_source = LCDC_CLK_EXTERNAL,
+	.ch[0] = {
+		.chan = LCDC_CHAN_MAINLCD,
+		.bpp = 16,
+		.clock_divider = 1,
+		.lcd_cfg = {
+			.name = "LB070WV1",
+			.sync = 0, /* hsync and vsync are active low */
+		},
+		.lcd_size_cfg = { /* 7.0 inch */
+			.width = 152,
+			.height = 91,
+		},
+		.board_cfg = {
+		},
+	}
+};
+
+static struct resource lcdc_resources[] = {
+	[0] = {
+		.name	= "LCDC",
+		.start	= 0xfe940000,
+		.end	= 0xfe941fff,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 106,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device lcdc_device = {
+	.name		= "sh_mobile_lcdc_fb",
+	.num_resources	= ARRAY_SIZE(lcdc_resources),
+	.resource	= lcdc_resources,
+	.dev		= {
+		.platform_data	= &lcdc_info,
+	},
+};
+
+/* CEU0 */
+static struct sh_mobile_ceu_info sh_mobile_ceu0_info = {
+	.flags = SH_CEU_FLAG_USE_8BIT_BUS,
+};
+
+static struct resource ceu0_resources[] = {
+	[0] = {
+		.name	= "CEU0",
+		.start	= 0xfe910000,
+		.end	= 0xfe91009f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = 52,
+		.flags  = IORESOURCE_IRQ,
+	},
+	[2] = {
+		/* place holder for contiguous memory */
+	},
+};
+
+static struct platform_device ceu0_device = {
+	.name		= "sh_mobile_ceu",
+	.id             = 0, /* "ceu0" clock */
+	.num_resources	= ARRAY_SIZE(ceu0_resources),
+	.resource	= ceu0_resources,
+	.dev	= {
+		.platform_data	= &sh_mobile_ceu0_info,
+	},
+};
+
+/* CEU1 */
+static struct sh_mobile_ceu_info sh_mobile_ceu1_info = {
+	.flags = SH_CEU_FLAG_USE_8BIT_BUS,
+};
+
+static struct resource ceu1_resources[] = {
+	[0] = {
+		.name	= "CEU1",
+		.start	= 0xfe914000,
+		.end	= 0xfe91409f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = 63,
+		.flags  = IORESOURCE_IRQ,
+	},
+	[2] = {
+		/* place holder for contiguous memory */
+	},
+};
+
+static struct platform_device ceu1_device = {
+	.name		= "sh_mobile_ceu",
+	.id             = 1, /* "ceu1" clock */
+	.num_resources	= ARRAY_SIZE(ceu1_resources),
+	.resource	= ceu1_resources,
+	.dev	= {
+		.platform_data	= &sh_mobile_ceu1_info,
+	},
+};
+
+/* KEYSC */
+static struct sh_keysc_info keysc_info = {
+	.mode = SH_KEYSC_MODE_1,
+	.scan_timing = 10,
+	.delay = 50,
+	.keycodes = {
+		KEY_1, KEY_2, KEY_3, KEY_4, KEY_5,
+		KEY_6, KEY_7, KEY_8, KEY_9, KEY_A,
+		KEY_B, KEY_C, KEY_D, KEY_E, KEY_F,
+		KEY_G, KEY_H, KEY_I, KEY_K, KEY_L,
+		KEY_M, KEY_N, KEY_O, KEY_P, KEY_Q,
+		KEY_R, KEY_S, KEY_T, KEY_U, KEY_V,
+	},
+};
+
+static struct resource keysc_resources[] = {
+	[0] = {
+		.start  = 0x1a204000,
+		.end    = 0x1a20400f,
+		.flags  = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = IRQ0_KEY,
+		.flags  = IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device keysc_device = {
+	.name           = "sh_keysc",
+	.id             = 0, /* "keysc0" clock */
+	.num_resources  = ARRAY_SIZE(keysc_resources),
+	.resource       = keysc_resources,
+	.dev	= {
+		.platform_data	= &keysc_info,
+	},
+};
+
+static struct platform_device *ms7724se_devices[] __initdata = {
+	&heartbeat_device,
+	&smc91x_eth_device,
+	&lcdc_device,
+	&nor_flash_device,
+	&ceu0_device,
+	&ceu1_device,
+	&keysc_device,
+};
+
+#define SW4140    0xBA201000
+#define FPGA_OUT  0xBA200400
+#define PORT_HIZA 0xA4050158
+
+#define SW41_A    0x0100
+#define SW41_B    0x0200
+#define SW41_C    0x0400
+#define SW41_D    0x0800
+#define SW41_E    0x1000
+#define SW41_F    0x2000
+#define SW41_G    0x4000
+#define SW41_H    0x8000
+static int __init devices_setup(void)
+{
+	u16 sw = ctrl_inw(SW4140); /* select camera, monitor */
+
+	/* Reset Release */
+	ctrl_outw(ctrl_inw(FPGA_OUT) &
+		  ~((1 << 1)  | /* LAN */
+		    (1 << 6)  | /* VIDEO DAC */
+		    (1 << 12)), /* USB0 */
+		  FPGA_OUT);
+
+	/* enable IRQ 0,1,2 */
+	gpio_request(GPIO_FN_INTC_IRQ0, NULL);
+	gpio_request(GPIO_FN_INTC_IRQ1, NULL);
+	gpio_request(GPIO_FN_INTC_IRQ2, NULL);
+
+	/* enable SCIFA3 */
+	gpio_request(GPIO_FN_SCIF3_I_SCK, NULL);
+	gpio_request(GPIO_FN_SCIF3_I_RXD, NULL);
+	gpio_request(GPIO_FN_SCIF3_I_TXD, NULL);
+	gpio_request(GPIO_FN_SCIF3_I_CTS, NULL);
+	gpio_request(GPIO_FN_SCIF3_I_RTS, NULL);
+
+	/* enable LCDC */
+	gpio_request(GPIO_FN_LCDD23,   NULL);
+	gpio_request(GPIO_FN_LCDD22,   NULL);
+	gpio_request(GPIO_FN_LCDD21,   NULL);
+	gpio_request(GPIO_FN_LCDD20,   NULL);
+	gpio_request(GPIO_FN_LCDD19,   NULL);
+	gpio_request(GPIO_FN_LCDD18,   NULL);
+	gpio_request(GPIO_FN_LCDD17,   NULL);
+	gpio_request(GPIO_FN_LCDD16,   NULL);
+	gpio_request(GPIO_FN_LCDD15,   NULL);
+	gpio_request(GPIO_FN_LCDD14,   NULL);
+	gpio_request(GPIO_FN_LCDD13,   NULL);
+	gpio_request(GPIO_FN_LCDD12,   NULL);
+	gpio_request(GPIO_FN_LCDD11,   NULL);
+	gpio_request(GPIO_FN_LCDD10,   NULL);
+	gpio_request(GPIO_FN_LCDD9,    NULL);
+	gpio_request(GPIO_FN_LCDD8,    NULL);
+	gpio_request(GPIO_FN_LCDD7,    NULL);
+	gpio_request(GPIO_FN_LCDD6,    NULL);
+	gpio_request(GPIO_FN_LCDD5,    NULL);
+	gpio_request(GPIO_FN_LCDD4,    NULL);
+	gpio_request(GPIO_FN_LCDD3,    NULL);
+	gpio_request(GPIO_FN_LCDD2,    NULL);
+	gpio_request(GPIO_FN_LCDD1,    NULL);
+	gpio_request(GPIO_FN_LCDD0,    NULL);
+	gpio_request(GPIO_FN_LCDDISP,  NULL);
+	gpio_request(GPIO_FN_LCDHSYN,  NULL);
+	gpio_request(GPIO_FN_LCDDCK,   NULL);
+	gpio_request(GPIO_FN_LCDVSYN,  NULL);
+	gpio_request(GPIO_FN_LCDDON,   NULL);
+	gpio_request(GPIO_FN_LCDVEPWC, NULL);
+	gpio_request(GPIO_FN_LCDVCPWC, NULL);
+	gpio_request(GPIO_FN_LCDRD,    NULL);
+	gpio_request(GPIO_FN_LCDLCLK,  NULL);
+	ctrl_outw((ctrl_inw(PORT_HIZA) & ~0x0001), PORT_HIZA);
+
+	/* enable CEU0 */
+	gpio_request(GPIO_FN_VIO0_D15, NULL);
+	gpio_request(GPIO_FN_VIO0_D14, NULL);
+	gpio_request(GPIO_FN_VIO0_D13, NULL);
+	gpio_request(GPIO_FN_VIO0_D12, NULL);
+	gpio_request(GPIO_FN_VIO0_D11, NULL);
+	gpio_request(GPIO_FN_VIO0_D10, NULL);
+	gpio_request(GPIO_FN_VIO0_D9,  NULL);
+	gpio_request(GPIO_FN_VIO0_D8,  NULL);
+	gpio_request(GPIO_FN_VIO0_D7,  NULL);
+	gpio_request(GPIO_FN_VIO0_D6,  NULL);
+	gpio_request(GPIO_FN_VIO0_D5,  NULL);
+	gpio_request(GPIO_FN_VIO0_D4,  NULL);
+	gpio_request(GPIO_FN_VIO0_D3,  NULL);
+	gpio_request(GPIO_FN_VIO0_D2,  NULL);
+	gpio_request(GPIO_FN_VIO0_D1,  NULL);
+	gpio_request(GPIO_FN_VIO0_D0,  NULL);
+	gpio_request(GPIO_FN_VIO0_VD,  NULL);
+	gpio_request(GPIO_FN_VIO0_CLK, NULL);
+	gpio_request(GPIO_FN_VIO0_FLD, NULL);
+	gpio_request(GPIO_FN_VIO0_HD,  NULL);
+	platform_resource_setup_memory(&ceu0_device, "ceu", 4 << 20);
+
+	/* enable CEU1 */
+	gpio_request(GPIO_FN_VIO1_D7,  NULL);
+	gpio_request(GPIO_FN_VIO1_D6,  NULL);
+	gpio_request(GPIO_FN_VIO1_D5,  NULL);
+	gpio_request(GPIO_FN_VIO1_D4,  NULL);
+	gpio_request(GPIO_FN_VIO1_D3,  NULL);
+	gpio_request(GPIO_FN_VIO1_D2,  NULL);
+	gpio_request(GPIO_FN_VIO1_D1,  NULL);
+	gpio_request(GPIO_FN_VIO1_D0,  NULL);
+	gpio_request(GPIO_FN_VIO1_FLD, NULL);
+	gpio_request(GPIO_FN_VIO1_HD,  NULL);
+	gpio_request(GPIO_FN_VIO1_VD,  NULL);
+	gpio_request(GPIO_FN_VIO1_CLK, NULL);
+	platform_resource_setup_memory(&ceu1_device, "ceu", 4 << 20);
+
+	/* KEYSC */
+	gpio_request(GPIO_FN_KEYOUT5_IN5, NULL);
+	gpio_request(GPIO_FN_KEYOUT4_IN6, NULL);
+	gpio_request(GPIO_FN_KEYIN4,      NULL);
+	gpio_request(GPIO_FN_KEYIN3,      NULL);
+	gpio_request(GPIO_FN_KEYIN2,      NULL);
+	gpio_request(GPIO_FN_KEYIN1,      NULL);
+	gpio_request(GPIO_FN_KEYIN0,      NULL);
+	gpio_request(GPIO_FN_KEYOUT3,     NULL);
+	gpio_request(GPIO_FN_KEYOUT2,     NULL);
+	gpio_request(GPIO_FN_KEYOUT1,     NULL);
+	gpio_request(GPIO_FN_KEYOUT0,     NULL);
+
+	if (sw & SW41_B) {
+		/* SVGA */
+		lcdc_info.ch[0].lcd_cfg.xres         = 800;
+		lcdc_info.ch[0].lcd_cfg.yres         = 600;
+		lcdc_info.ch[0].lcd_cfg.left_margin  = 142;
+		lcdc_info.ch[0].lcd_cfg.right_margin = 52;
+		lcdc_info.ch[0].lcd_cfg.hsync_len    = 96;
+		lcdc_info.ch[0].lcd_cfg.upper_margin = 24;
+		lcdc_info.ch[0].lcd_cfg.lower_margin = 2;
+		lcdc_info.ch[0].lcd_cfg.vsync_len    = 2;
+	} else {
+		/* VGA */
+		lcdc_info.ch[0].lcd_cfg.xres         = 640;
+		lcdc_info.ch[0].lcd_cfg.yres         = 480;
+		lcdc_info.ch[0].lcd_cfg.left_margin  = 105;
+		lcdc_info.ch[0].lcd_cfg.right_margin = 50;
+		lcdc_info.ch[0].lcd_cfg.hsync_len    = 96;
+		lcdc_info.ch[0].lcd_cfg.upper_margin = 33;
+		lcdc_info.ch[0].lcd_cfg.lower_margin = 10;
+		lcdc_info.ch[0].lcd_cfg.vsync_len    = 2;
+	}
+
+	if (sw & SW41_A) {
+		/* Digital monitor */
+		lcdc_info.ch[0].interface_type = RGB18;
+		lcdc_info.ch[0].flags          = 0;
+	} else {
+		/* Analog monitor */
+		lcdc_info.ch[0].interface_type = RGB24;
+		lcdc_info.ch[0].flags          = LCDC_FLAGS_DWPOL;
+	}
+
+	return platform_add_devices(ms7724se_devices,
+				ARRAY_SIZE(ms7724se_devices));
+}
+device_initcall(devices_setup);
+
+static struct sh_machine_vector mv_ms7724se __initmv = {
+	.mv_name	= "ms7724se",
+	.mv_init_irq	= init_se7724_IRQ,
+	.mv_nr_irqs	= SE7724_FPGA_IRQ_BASE + SE7724_FPGA_IRQ_NR,
+};
diff --git a/arch/sh/boards/mach-se/7751/Makefile b/arch/sh/boards/mach-se/7751/Makefile
index dbc29f3a9de5..e6f4341bfe6e 100644
--- a/arch/sh/boards/mach-se/7751/Makefile
+++ b/arch/sh/boards/mach-se/7751/Makefile
@@ -3,5 +3,3 @@
 #
 
 obj-y	 := setup.o io.o irq.o
-
-obj-$(CONFIG_PCI) += pci.o
diff --git a/arch/sh/boards/mach-se/7751/io.c b/arch/sh/boards/mach-se/7751/io.c
index 6287ae570319..6e75bd4459e5 100644
--- a/arch/sh/boards/mach-se/7751/io.c
+++ b/arch/sh/boards/mach-se/7751/io.c
@@ -34,8 +34,6 @@ unsigned char sh7751se_inb(unsigned long port)
 {
 	if (PXSEG(port))
 		return *(volatile unsigned char *)port;
-	else if (is_pci_ioaddr(port))
-		return *(volatile unsigned char *)pci_ioaddr(port);
 	else
 		return (*port2adr(port)) & 0xff;
 }
@@ -46,8 +44,6 @@ unsigned char sh7751se_inb_p(unsigned long port)
 
         if (PXSEG(port))
                 v = *(volatile unsigned char *)port;
-	else if (is_pci_ioaddr(port))
-                v = *(volatile unsigned char *)pci_ioaddr(port);
 	else
 		v = (*port2adr(port)) & 0xff;
 	ctrl_delay();
@@ -58,8 +54,6 @@ unsigned short sh7751se_inw(unsigned long port)
 {
         if (PXSEG(port))
                 return *(volatile unsigned short *)port;
-	else if (is_pci_ioaddr(port))
-                return *(volatile unsigned short *)pci_ioaddr(port);
 	else if (port >= 0x2000)
 		return *port2adr(port);
 	else
@@ -71,8 +65,6 @@ unsigned int sh7751se_inl(unsigned long port)
 {
         if (PXSEG(port))
                 return *(volatile unsigned long *)port;
-	else if (is_pci_ioaddr(port))
-                return *(volatile unsigned int *)pci_ioaddr(port);
 	else if (port >= 0x2000)
 		return *port2adr(port);
 	else
@@ -85,8 +77,6 @@ void sh7751se_outb(unsigned char value, unsigned long port)
 
         if (PXSEG(port))
                 *(volatile unsigned char *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned char*)pci_ioaddr(port)) = value;
 	else
 		*(port2adr(port)) = value;
 }
@@ -95,8 +85,6 @@ void sh7751se_outb_p(unsigned char value, unsigned long port)
 {
         if (PXSEG(port))
                 *(volatile unsigned char *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned char*)pci_ioaddr(port)) = value;
 	else
 		*(port2adr(port)) = value;
 	ctrl_delay();
@@ -106,8 +94,6 @@ void sh7751se_outw(unsigned short value, unsigned long port)
 {
         if (PXSEG(port))
                 *(volatile unsigned short *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned short *)pci_ioaddr(port)) = value;
 	else if (port >= 0x2000)
 		*port2adr(port) = value;
 	else
@@ -118,8 +104,6 @@ void sh7751se_outl(unsigned int value, unsigned long port)
 {
         if (PXSEG(port))
                 *(volatile unsigned long *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned long*)pci_ioaddr(port)) = value;
 	else
 		maybebadio(port);
 }
diff --git a/arch/sh/boards/mach-se/7751/pci.c b/arch/sh/boards/mach-se/7751/pci.c
deleted file mode 100644
index 203b2923fe7f..000000000000
--- a/arch/sh/boards/mach-se/7751/pci.c
+++ /dev/null
@@ -1,147 +0,0 @@
-/*
- * linux/arch/sh/boards/se/7751/pci.c
- *
- * Author:  Ian DaSilva (idasilva@mvista.com)
- *
- * Highly leveraged from pci-bigsur.c, written by Dustin McIntire.
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * PCI initialization for the Hitachi SH7751 Solution Engine board (MS7751SE01)
- */
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-
-#include <asm/io.h>
-#include "../../../drivers/pci/pci-sh7751.h"
-
-#define PCIMCR_MRSET_OFF	0xBFFFFFFF
-#define PCIMCR_RFSH_OFF		0xFFFFFFFB
-
-/*
- * Only long word accesses of the PCIC's internal local registers and the
- * configuration registers from the CPU is supported.
- */
-#define PCIC_WRITE(x,v) writel((v), PCI_REG(x))
-#define PCIC_READ(x) readl(PCI_REG(x))
-
-/*
- * Description:  This function sets up and initializes the pcic, sets
- * up the BARS, maps the DRAM into the address space etc, etc.
- */
-int __init pcibios_init_platform(void)
-{
-   unsigned long bcr1, wcr1, wcr2, wcr3, mcr;
-   unsigned short bcr2;
-
-   /*
-    * Initialize the slave bus controller on the pcic.  The values used
-    * here should not be hardcoded, but they should be taken from the bsc
-    * on the processor, to make this function as generic as possible.
-    * (i.e. Another sbc may usr different SDRAM timing settings -- in order
-    * for the pcic to work, its settings need to be exactly the same.)
-    */
-   bcr1 = (*(volatile unsigned long*)(SH7751_BCR1));
-   bcr2 = (*(volatile unsigned short*)(SH7751_BCR2));
-   wcr1 = (*(volatile unsigned long*)(SH7751_WCR1));
-   wcr2 = (*(volatile unsigned long*)(SH7751_WCR2));
-   wcr3 = (*(volatile unsigned long*)(SH7751_WCR3));
-   mcr = (*(volatile unsigned long*)(SH7751_MCR));
-
-   bcr1 = bcr1 | 0x00080000;  /* Enable Bit 19, BREQEN */
-   (*(volatile unsigned long*)(SH7751_BCR1)) = bcr1;   
-
-   bcr1 = bcr1 | 0x40080000;  /* Enable Bit 19 BREQEN, set PCIC to slave */
-   PCIC_WRITE(SH7751_PCIBCR1, bcr1);	 /* PCIC BCR1 */
-   PCIC_WRITE(SH7751_PCIBCR2, bcr2);     /* PCIC BCR2 */
-   PCIC_WRITE(SH7751_PCIWCR1, wcr1);     /* PCIC WCR1 */
-   PCIC_WRITE(SH7751_PCIWCR2, wcr2);     /* PCIC WCR2 */
-   PCIC_WRITE(SH7751_PCIWCR3, wcr3);     /* PCIC WCR3 */
-   mcr = (mcr & PCIMCR_MRSET_OFF) & PCIMCR_RFSH_OFF;
-   PCIC_WRITE(SH7751_PCIMCR, mcr);      /* PCIC MCR */
-
-
-   /* Enable all interrupts, so we know what to fix */
-   PCIC_WRITE(SH7751_PCIINTM, 0x0000c3ff);
-   PCIC_WRITE(SH7751_PCIAINTM, 0x0000380f);
-
-   /* Set up standard PCI config registers */
-   PCIC_WRITE(SH7751_PCICONF1, 	0xF39000C7); /* Bus Master, Mem & I/O access */
-   PCIC_WRITE(SH7751_PCICONF2, 	0x00000000); /* PCI Class code & Revision ID */
-   PCIC_WRITE(SH7751_PCICONF4, 	0xab000001); /* PCI I/O address (local regs) */
-   PCIC_WRITE(SH7751_PCICONF5, 	0x0c000000); /* PCI MEM address (local RAM)  */
-   PCIC_WRITE(SH7751_PCICONF6, 	0xd0000000); /* PCI MEM address (unused)     */
-   PCIC_WRITE(SH7751_PCICONF11, 0x35051054); /* PCI Subsystem ID & Vendor ID */
-   PCIC_WRITE(SH7751_PCILSR0, 0x03f00000);   /* MEM (full 64M exposed)       */
-   PCIC_WRITE(SH7751_PCILSR1, 0x00000000);   /* MEM (unused)                 */
-   PCIC_WRITE(SH7751_PCILAR0, 0x0c000000);   /* MEM (direct map from PCI)    */
-   PCIC_WRITE(SH7751_PCILAR1, 0x00000000);   /* MEM (unused)                 */
-
-   /* Now turn it on... */
-   PCIC_WRITE(SH7751_PCICR, 0xa5000001);
-
-   /*
-    * Set PCIMBR and PCIIOBR here, assuming a single window
-    * (16M MEM, 256K IO) is enough.  If a larger space is
-    * needed, the readx/writex and inx/outx functions will
-    * have to do more (e.g. setting registers for each call).
-    */
-
-   /*
-    * Set the MBR so PCI address is one-to-one with window,
-    * meaning all calls go straight through... use BUG_ON to
-    * catch erroneous assumption.
-    */
-   BUG_ON(PCIBIOS_MIN_MEM != SH7751_PCI_MEMORY_BASE);
-
-   PCIC_WRITE(SH7751_PCIMBR, PCIBIOS_MIN_MEM);
-
-   /* Set IOBR for window containing area specified in pci.h */
-   PCIC_WRITE(SH7751_PCIIOBR, (PCIBIOS_MIN_IO & SH7751_PCIIOBR_MASK));
-
-   /* All done, may as well say so... */
-   printk("SH7751 PCI: Finished initialization of the PCI controller\n");
-
-   return 1;
-}
-
-int __init pcibios_map_platform_irq(u8 slot, u8 pin)
-{
-        switch (slot) {
-        case 0: return 13;
-        case 1: return 13; 	/* AMD Ethernet controller */
-        case 2: return -1;
-        case 3: return -1;
-        case 4: return -1;
-        default:
-                printk("PCI: Bad IRQ mapping request for slot %d\n", slot);
-                return -1;
-        }
-}
-
-static struct resource sh7751_io_resource = {
-	.name   = "SH7751 IO",
-	.start  = SH7751_PCI_IO_BASE,
-	.end    = SH7751_PCI_IO_BASE + SH7751_PCI_IO_SIZE - 1,
-	.flags  = IORESOURCE_IO
-};
-
-static struct resource sh7751_mem_resource = {
-	.name   = "SH7751 mem",
-	.start  = SH7751_PCI_MEMORY_BASE,
-	.end    = SH7751_PCI_MEMORY_BASE + SH7751_PCI_MEM_SIZE - 1,
-	.flags  = IORESOURCE_MEM
-};
-
-extern struct pci_ops sh7751_pci_ops;
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh7751_pci_ops, &sh7751_io_resource, &sh7751_mem_resource, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-
diff --git a/arch/sh/boards/mach-se/7780/irq.c b/arch/sh/boards/mach-se/7780/irq.c
index 66ad292c9fc3..b8d43b638fcf 100644
--- a/arch/sh/boards/mach-se/7780/irq.c
+++ b/arch/sh/boards/mach-se/7780/irq.c
@@ -12,10 +12,13 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
-#include <asm/irq.h>
-#include <asm/io.h>
+#include <linux/irq.h>
+#include <linux/io.h>
 #include <mach-se/mach/se7780.h>
 
+#define INTC_BASE	0xffd00000
+#define INTC_ICR1	(INTC_BASE+0x1c)
+
 /*
  * Initialize IRQ setting
  */
@@ -43,4 +46,24 @@ void __init init_se7780_IRQ(void)
 	ctrl_outw((IRQPIN_PCCPW << IRQPOS_PCCPW), FPGA_INTSEL3);
 
 	plat_irq_setup_pins(IRQ_MODE_IRQ); /* install handlers for IRQ0-7 */
+
+	/* ICR1: detect low level(for 2ndcut) */
+	ctrl_outl(0xAAAA0000, INTC_ICR1);
+
+	/*
+	 * FPGA PCISEL register initialize
+	 *
+	 *  CPU  || SLOT1 | SLOT2 | S-ATA | USB
+	 *  -------------------------------------
+	 *  INTA || INTA  | INTD  |  --   | INTB
+	 *  -------------------------------------
+	 *  INTB || INTB  | INTA  |  --   | INTC
+	 *  -------------------------------------
+	 *  INTC || INTC  | INTB  | INTA  |  --
+	 *  -------------------------------------
+	 *  INTD || INTD  | INTC  |  --   | INTA
+	 *  -------------------------------------
+	 */
+	ctrl_outw(0x0013, FPGA_PCI_INTSEL1);
+	ctrl_outw(0xE402, FPGA_PCI_INTSEL2);
 }
diff --git a/arch/sh/boards/mach-se/Makefile b/arch/sh/boards/mach-se/Makefile
index 2de42bae4b4f..b537e238c6bc 100644
--- a/arch/sh/boards/mach-se/Makefile
+++ b/arch/sh/boards/mach-se/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_SH_7751_SOLUTION_ENGINE)	+= 7751/
 obj-$(CONFIG_SH_7780_SOLUTION_ENGINE)	+= 7780/
 obj-$(CONFIG_SH_7343_SOLUTION_ENGINE)	+= 7343/
 obj-$(CONFIG_SH_7721_SOLUTION_ENGINE)	+= 7721/
+obj-$(CONFIG_SH_7724_SOLUTION_ENGINE)	+= 7724/
diff --git a/arch/sh/boards/mach-sh03/rtc.c b/arch/sh/boards/mach-sh03/rtc.c
index 0a9266bb51c5..a8b9f844ab5b 100644
--- a/arch/sh/boards/mach-sh03/rtc.c
+++ b/arch/sh/boards/mach-sh03/rtc.c
@@ -35,13 +35,13 @@
 #define RTC_BUSY	1
 #define RTC_STOP	2
 
-extern spinlock_t rtc_lock;
+static DEFINE_SPINLOCK(sh03_rtc_lock);
 
 unsigned long get_cmos_time(void)
 {
 	unsigned int year, mon, day, hour, min, sec;
 
-	spin_lock(&rtc_lock);
+	spin_lock(&sh03_rtc_lock);
  again:
 	do {
 		sec  = (ctrl_inb(RTC_SEC1) & 0xf) + (ctrl_inb(RTC_SEC10) & 0x7) * 10;
@@ -73,7 +73,7 @@ unsigned long get_cmos_time(void)
 		goto again;
 	}
 
-	spin_unlock(&rtc_lock);
+	spin_unlock(&sh03_rtc_lock);
 	return mktime(year, mon, day, hour, min, sec);
 }
 
@@ -91,7 +91,7 @@ static int set_rtc_mmss(unsigned long nowtime)
 	int i;
 
 	/* gets recalled with irq locally disabled */
-	spin_lock(&rtc_lock);
+	spin_lock(&sh03_rtc_lock);
 	for (i = 0 ; i < 1000000 ; i++)	/* may take up to 1 second... */
 		if (!(ctrl_inb(RTC_CTL) & RTC_BUSY))
 			break;
@@ -113,7 +113,7 @@ static int set_rtc_mmss(unsigned long nowtime)
 		       cmos_minutes, real_minutes);
 		retval = -1;
 	}
-	spin_unlock(&rtc_lock);
+	spin_unlock(&sh03_rtc_lock);
 
 	return retval;
 }
diff --git a/arch/sh/boards/mach-snapgear/io.c b/arch/sh/boards/mach-snapgear/io.c
index 0f4824264557..476650e42dbc 100644
--- a/arch/sh/boards/mach-snapgear/io.c
+++ b/arch/sh/boards/mach-snapgear/io.c
@@ -36,8 +36,6 @@ unsigned char snapgear_inb(unsigned long port)
 {
 	if (PXSEG(port))
 		return *(volatile unsigned char *)port;
-	else if (is_pci_ioaddr(port))
-		return *(volatile unsigned char *)pci_ioaddr(port);
 	else
 		return (*port2adr(port)) & 0xff;
 }
@@ -48,8 +46,6 @@ unsigned char snapgear_inb_p(unsigned long port)
 
 	if (PXSEG(port))
 		v = *(volatile unsigned char *)port;
-	else if (is_pci_ioaddr(port))
-		v = *(volatile unsigned char *)pci_ioaddr(port);
 	else
 		v = (*port2adr(port))&0xff;
 	ctrl_delay();
@@ -60,8 +56,6 @@ unsigned short snapgear_inw(unsigned long port)
 {
 	if (PXSEG(port))
 		return *(volatile unsigned short *)port;
-	else if (is_pci_ioaddr(port))
-		return *(volatile unsigned short *)pci_ioaddr(port);
 	else if (port >= 0x2000)
 		return *port2adr(port);
 	else
@@ -73,8 +67,6 @@ unsigned int snapgear_inl(unsigned long port)
 {
 	if (PXSEG(port))
 		return *(volatile unsigned long *)port;
-	else if (is_pci_ioaddr(port))
-		return *(volatile unsigned int *)pci_ioaddr(port);
 	else if (port >= 0x2000)
 		return *port2adr(port);
 	else
@@ -87,8 +79,6 @@ void snapgear_outb(unsigned char value, unsigned long port)
 
 	if (PXSEG(port))
 		*(volatile unsigned char *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned char*)pci_ioaddr(port)) = value;
 	else
 		*(port2adr(port)) = value;
 }
@@ -97,8 +87,6 @@ void snapgear_outb_p(unsigned char value, unsigned long port)
 {
 	if (PXSEG(port))
 		*(volatile unsigned char *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned char*)pci_ioaddr(port)) = value;
 	else
 		*(port2adr(port)) = value;
 	ctrl_delay();
@@ -108,8 +96,6 @@ void snapgear_outw(unsigned short value, unsigned long port)
 {
 	if (PXSEG(port))
 		*(volatile unsigned short *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned short *)pci_ioaddr(port)) = value;
 	else if (port >= 0x2000)
 		*port2adr(port) = value;
 	else
@@ -120,8 +106,6 @@ void snapgear_outl(unsigned int value, unsigned long port)
 {
 	if (PXSEG(port))
 		*(volatile unsigned long *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned long*)pci_ioaddr(port)) = value;
 	else
 		maybebadio(port);
 }
diff --git a/arch/sh/boards/mach-systemh/io.c b/arch/sh/boards/mach-systemh/io.c
index dec3db0ee933..15577ff1f715 100644
--- a/arch/sh/boards/mach-systemh/io.c
+++ b/arch/sh/boards/mach-systemh/io.c
@@ -35,8 +35,6 @@ unsigned char sh7751systemh_inb(unsigned long port)
 {
 	if (PXSEG(port))
 		return *(volatile unsigned char *)port;
-	else if (is_pci_ioaddr(port))
-		return *(volatile unsigned char *)pci_ioaddr(port);
 	else if (port <= 0x3F1)
 		return *(volatile unsigned char *)ETHER_IOMAP(port);
 	else
@@ -49,8 +47,6 @@ unsigned char sh7751systemh_inb_p(unsigned long port)
 
         if (PXSEG(port))
                 v = *(volatile unsigned char *)port;
-	else if (is_pci_ioaddr(port))
-                v = *(volatile unsigned char *)pci_ioaddr(port);
 	else if (port <= 0x3F1)
 		v = *(volatile unsigned char *)ETHER_IOMAP(port);
 	else
@@ -63,8 +59,6 @@ unsigned short sh7751systemh_inw(unsigned long port)
 {
         if (PXSEG(port))
                 return *(volatile unsigned short *)port;
-	else if (is_pci_ioaddr(port))
-                return *(volatile unsigned short *)pci_ioaddr(port);
 	else if (port >= 0x2000)
 		return *port2adr(port);
 	else if (port <= 0x3F1)
@@ -78,8 +72,6 @@ unsigned int sh7751systemh_inl(unsigned long port)
 {
         if (PXSEG(port))
                 return *(volatile unsigned long *)port;
-	else if (is_pci_ioaddr(port))
-                return *(volatile unsigned int *)pci_ioaddr(port);
 	else if (port >= 0x2000)
 		return *port2adr(port);
 	else if (port <= 0x3F1)
@@ -94,8 +86,6 @@ void sh7751systemh_outb(unsigned char value, unsigned long port)
 
         if (PXSEG(port))
                 *(volatile unsigned char *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned char*)pci_ioaddr(port)) = value;
 	else if (port <= 0x3F1)
 		*(volatile unsigned char *)ETHER_IOMAP(port) = value;
 	else
@@ -106,8 +96,6 @@ void sh7751systemh_outb_p(unsigned char value, unsigned long port)
 {
         if (PXSEG(port))
                 *(volatile unsigned char *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned char*)pci_ioaddr(port)) = value;
 	else if (port <= 0x3F1)
 		*(volatile unsigned char *)ETHER_IOMAP(port) = value;
 	else
@@ -119,8 +107,6 @@ void sh7751systemh_outw(unsigned short value, unsigned long port)
 {
         if (PXSEG(port))
                 *(volatile unsigned short *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned short *)pci_ioaddr(port)) = value;
 	else if (port >= 0x2000)
 		*port2adr(port) = value;
 	else if (port <= 0x3F1)
@@ -133,8 +119,6 @@ void sh7751systemh_outl(unsigned int value, unsigned long port)
 {
         if (PXSEG(port))
                 *(volatile unsigned long *)port = value;
-	else if (is_pci_ioaddr(port))
-		*((unsigned long*)pci_ioaddr(port)) = value;
 	else
 		maybebadio(port);
 }
diff --git a/arch/sh/boards/mach-titan/io.c b/arch/sh/boards/mach-titan/io.c
index 4badad4c6f30..0130e9826aca 100644
--- a/arch/sh/boards/mach-titan/io.c
+++ b/arch/sh/boards/mach-titan/io.c
@@ -17,8 +17,6 @@ u8 titan_inb(unsigned long port)
 {
         if (PXSEG(port))
                 return ctrl_inb(port);
-        else if (is_pci_ioaddr(port))
-                return ctrl_inb(pci_ioaddr(port));
         return ctrl_inw(port2adr(port)) & 0xff;
 }
 
@@ -28,8 +26,6 @@ u8 titan_inb_p(unsigned long port)
 
         if (PXSEG(port))
                 v = ctrl_inb(port);
-        else if (is_pci_ioaddr(port))
-                v = ctrl_inb(pci_ioaddr(port));
         else
                 v = ctrl_inw(port2adr(port)) & 0xff;
         ctrl_delay();
@@ -40,8 +36,6 @@ u16 titan_inw(unsigned long port)
 {
         if (PXSEG(port))
                 return ctrl_inw(port);
-        else if (is_pci_ioaddr(port))
-                return ctrl_inw(pci_ioaddr(port));
         else if (port >= 0x2000)
                 return ctrl_inw(port2adr(port));
         else
@@ -53,8 +47,6 @@ u32 titan_inl(unsigned long port)
 {
         if (PXSEG(port))
                 return ctrl_inl(port);
-        else if (is_pci_ioaddr(port))
-                return ctrl_inl(pci_ioaddr(port));
         else if (port >= 0x2000)
                 return ctrl_inw(port2adr(port));
         else
@@ -66,8 +58,6 @@ void titan_outb(u8 value, unsigned long port)
 {
         if (PXSEG(port))
                 ctrl_outb(value, port);
-        else if (is_pci_ioaddr(port))
-                ctrl_outb(value, pci_ioaddr(port));
         else
                 ctrl_outw(value, port2adr(port));
 }
@@ -76,8 +66,6 @@ void titan_outb_p(u8 value, unsigned long port)
 {
         if (PXSEG(port))
                 ctrl_outb(value, port);
-        else if (is_pci_ioaddr(port))
-                ctrl_outb(value, pci_ioaddr(port));
         else
                 ctrl_outw(value, port2adr(port));
         ctrl_delay();
@@ -87,8 +75,6 @@ void titan_outw(u16 value, unsigned long port)
 {
         if (PXSEG(port))
                 ctrl_outw(value, port);
-        else if (is_pci_ioaddr(port))
-                ctrl_outw(value, pci_ioaddr(port));
         else if (port >= 0x2000)
                 ctrl_outw(value, port2adr(port));
         else
@@ -99,8 +85,6 @@ void titan_outl(u32 value, unsigned long port)
 {
         if (PXSEG(port))
                 ctrl_outl(value, port);
-        else if (is_pci_ioaddr(port))
-                ctrl_outl(value, pci_ioaddr(port));
         else
                 maybebadio(port);
 }
@@ -117,10 +101,8 @@ void titan_outsl(unsigned long port, const void *src, unsigned long count)
 
 void __iomem *titan_ioport_map(unsigned long port, unsigned int size)
 {
-	if (PXSEG(port) || is_pci_memaddr(port))
+	if (PXSEG(port))
 		return (void __iomem *)port;
-	else if (is_pci_ioaddr(port))
-		return (void __iomem *)pci_ioaddr(port);
 
 	return (void __iomem *)port2adr(port);
 }
diff --git a/arch/sh/boot/Makefile b/arch/sh/boot/Makefile
index 95483d161258..78efb04c28f3 100644
--- a/arch/sh/boot/Makefile
+++ b/arch/sh/boot/Makefile
@@ -20,9 +20,6 @@ CONFIG_BOOT_LINK_OFFSET	?= 0x00800000
 CONFIG_ZERO_PAGE_OFFSET	?= 0x00001000
 CONFIG_ENTRY_OFFSET	?= 0x00001000
 
-export CONFIG_PAGE_OFFSET CONFIG_MEMORY_START CONFIG_BOOT_LINK_OFFSET \
-       CONFIG_ZERO_PAGE_OFFSET CONFIG_ENTRY_OFFSET
-
 targets := zImage vmlinux.srec uImage uImage.srec
 subdir- := compressed
 
@@ -43,6 +40,9 @@ KERNEL_MEMORY := $(shell /bin/bash -c 'printf "0x%08x" \
 		     $$[$(CONFIG_MEMORY_START)]')
 endif
 
+export CONFIG_PAGE_OFFSET CONFIG_MEMORY_START CONFIG_BOOT_LINK_OFFSET \
+       CONFIG_ZERO_PAGE_OFFSET CONFIG_ENTRY_OFFSET KERNEL_MEMORY
+
 KERNEL_LOAD	:= $(shell /bin/bash -c 'printf "0x%08x" \
 		     $$[$(CONFIG_PAGE_OFFSET)  + \
 			$(KERNEL_MEMORY) + \
diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile
index efb01dc3c8c3..9531bf1b7c2f 100644
--- a/arch/sh/boot/compressed/Makefile
+++ b/arch/sh/boot/compressed/Makefile
@@ -1,5 +1,47 @@
-ifeq ($(CONFIG_SUPERH32),y)
-include ${srctree}/arch/sh/boot/compressed/Makefile_32
-else
-include ${srctree}/arch/sh/boot/compressed/Makefile_64
+#
+# linux/arch/sh/boot/compressed/Makefile
+#
+# create a compressed vmlinux image from the original vmlinux
+#
+
+targets		:= vmlinux vmlinux.bin vmlinux.bin.gz \
+		   head_$(BITS).o misc_$(BITS).o piggy.o
+
+OBJECTS = $(obj)/head_$(BITS).o $(obj)/misc_$(BITS).o $(obj)/cache.o
+
+ifdef CONFIG_SH_STANDARD_BIOS
+OBJECTS += $(obj)/../../kernel/sh_bios.o
 endif
+
+#
+# IMAGE_OFFSET is the load offset of the compression loader
+#
+IMAGE_OFFSET	:= $(shell /bin/bash -c 'printf "0x%08x" \
+		     $$[$(CONFIG_PAGE_OFFSET)  + \
+			$(KERNEL_MEMORY) + \
+			$(CONFIG_BOOT_LINK_OFFSET)]')
+
+LIBGCC	:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
+
+ifeq ($(CONFIG_FUNCTION_TRACER),y)
+ORIG_CFLAGS := $(KBUILD_CFLAGS)
+KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
+endif
+
+LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \
+		   -T $(obj)/../../kernel/vmlinux.lds
+
+$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(LIBGCC) FORCE
+	$(call if_changed,ld)
+	@:
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,gzip)
+
+OBJCOPYFLAGS += -R .empty_zero_page
+
+$(obj)/piggy.o: $(obj)/piggy.S $(obj)/vmlinux.bin.gz FORCE
+	$(call if_changed,as_o_S)
diff --git a/arch/sh/boot/compressed/Makefile_32 b/arch/sh/boot/compressed/Makefile_32
deleted file mode 100644
index b96a055b053e..000000000000
--- a/arch/sh/boot/compressed/Makefile_32
+++ /dev/null
@@ -1,46 +0,0 @@
-#
-# linux/arch/sh/boot/compressed/Makefile
-#
-# create a compressed vmlinux image from the original vmlinux
-#
-
-targets		:= vmlinux vmlinux.bin vmlinux.bin.gz \
-		   head_32.o misc_32.o piggy.o
-
-OBJECTS = $(obj)/head_32.o $(obj)/misc_32.o
-
-ifdef CONFIG_SH_STANDARD_BIOS
-OBJECTS += $(obj)/../../kernel/sh_bios.o
-endif
-
-#
-# IMAGE_OFFSET is the load offset of the compression loader
-#
-IMAGE_OFFSET	:= $(shell /bin/bash -c 'printf "0x%08x" \
-		     $$[$(CONFIG_PAGE_OFFSET)  + \
-			$(CONFIG_MEMORY_START) + \
-			$(CONFIG_BOOT_LINK_OFFSET)]')
-
-LIBGCC	:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
-
-ifeq ($(CONFIG_FUNCTION_TRACER),y)
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
-endif
-
-LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -e startup -T $(obj)/../../kernel/vmlinux.lds
-
-$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(LIBGCC) FORCE
-	$(call if_changed,ld)
-	@:
-
-$(obj)/vmlinux.bin: vmlinux FORCE
-	$(call if_changed,objcopy)
-
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,gzip)
-
-OBJCOPYFLAGS += -R .empty_zero_page
-
-$(obj)/piggy.o: $(obj)/piggy.S $(obj)/vmlinux.bin.gz FORCE
-	$(call if_changed,as_o_S)
diff --git a/arch/sh/boot/compressed/Makefile_64 b/arch/sh/boot/compressed/Makefile_64
deleted file mode 100644
index 658d4f915556..000000000000
--- a/arch/sh/boot/compressed/Makefile_64
+++ /dev/null
@@ -1,43 +0,0 @@
-#
-# arch/sh/boot/compressed/Makefile_64
-#
-# create a compressed vmlinux image from the original vmlinux
-#
-# Copyright (C) 2002 Stuart Menefy
-# Copyright (C) 2004 Paul Mundt
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-
-targets		:= vmlinux vmlinux.bin vmlinux.bin.gz \
-		   head_64.o misc_64.o cache.o piggy.o
-
-OBJECTS		:= $(obj)/vmlinux_64.lds $(obj)/head_64.o $(obj)/misc_64.o \
-		   $(obj)/cache.o
-
-#
-# ZIMAGE_OFFSET is the load offset of the compression loader
-# (4M for the kernel plus 64K for this loader)
-#
-ZIMAGE_OFFSET	:= $(shell /bin/bash -c 'printf "0x%08x" \
-		     $$[$(CONFIG_PAGE_OFFSET)+0x400000+0x10000]')
-
-LDFLAGS_vmlinux := -Ttext $(ZIMAGE_OFFSET) -e startup \
-		    -T $(obj)/../../kernel/vmlinux.lds
-
-$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o FORCE
-	$(call if_changed,ld)
-	@:
-
-$(obj)/vmlinux.bin: vmlinux FORCE
-	$(call if_changed,objcopy)
-
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,gzip)
-
-OBJCOPYFLAGS += -R .empty_zero_page
-
-$(obj)/piggy.o: $(obj)/piggy.S $(obj)/vmlinux.bin.gz FORCE
-	$(call if_changed,as_o_S)
diff --git a/arch/sh/boot/compressed/head_64.S b/arch/sh/boot/compressed/head_64.S
index 622eac3cf556..9993113c6713 100644
--- a/arch/sh/boot/compressed/head_64.S
+++ b/arch/sh/boot/compressed/head_64.S
@@ -14,6 +14,7 @@
  *   Copyright (C) 2002 Stuart Menefy (stuart.menefy@st.com)
  */
 #include <asm/cache.h>
+#include <asm/tlb.h>
 #include <cpu/mmu_context.h>
 #include <cpu/registers.h>
 
@@ -33,11 +34,7 @@
 #define	ICCR0_INIT_VAL	ICCR0_ON | ICCR0_ICI		/* ICE + ICI */
 #define	ICCR1_INIT_VAL	ICCR1_NOLOCK			/* No locking */
 
-#if 1
 #define	OCCR0_INIT_VAL	OCCR0_ON | OCCR0_OCI | OCCR0_WB	/* OCE + OCI + WB */
-#else
-#define	OCCR0_INIT_VAL	OCCR0_OFF
-#endif
 #define	OCCR1_INIT_VAL	OCCR1_NOLOCK			/* No locking */
 
 	.text
diff --git a/arch/sh/boot/compressed/vmlinux_64.lds b/arch/sh/boot/compressed/vmlinux_64.lds
deleted file mode 100644
index 59c2ef4aeda5..000000000000
--- a/arch/sh/boot/compressed/vmlinux_64.lds
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * ld script to make compressed SuperH/shmedia Linux kernel+decompression
- *		bootstrap
- * Modified by Stuart Menefy from arch/sh/vmlinux.lds.S written by Niibe Yutaka
- */
-
-
-#ifdef CONFIG_LITTLE_ENDIAN
-/* OUTPUT_FORMAT("elf32-sh64l-linux", "elf32-sh64l-linux", "elf32-sh64l-linux") */
-#define NOP 0x6ff0fff0
-#else
-/* OUTPUT_FORMAT("elf32-sh64", "elf32-sh64", "elf32-sh64") */
-#define NOP 0xf0fff06f
-#endif
-
-OUTPUT_FORMAT("elf32-sh64-linux")
-OUTPUT_ARCH(sh)
-ENTRY(_start)
-
-#define ALIGNED_GAP(section, align) (((ADDR(section)+SIZEOF(section)+(align)-1) & ~((align)-1))-ADDR(section))
-#define FOLLOWING(section, align) AT (LOADADDR(section) + ALIGNED_GAP(section,align))
-
-SECTIONS
-{
-  _text = .;			/* Text and read-only data */
-
-  .text : {
-	*(.text)
-	*(.text64)
-	*(.text..SHmedia32)
-	*(.fixup)
-	*(.gnu.warning)
-	} = NOP
-  . = ALIGN(4);
-  .rodata : { *(.rodata) }
-
-  /* There is no 'real' reason for eight byte alignment, four would work
-   * as well, but gdb downloads much (*4) faster with this.
-   */
-  . = ALIGN(8);
-  .image : { *(.image) }
-  . = ALIGN(4);
-  _etext = .;			/* End of text section */
-
-  .data :			/* Data */
-	FOLLOWING(.image, 4)
-	{
-	_data = .;
-	*(.data)
-	}
-  _data_image = LOADADDR(.data);/* Address of data section in ROM */
-
-  _edata = .;			/* End of data section */
-
-  .stack : { stack = .;  _stack = .; }
-
-  . = ALIGN(4);
-  __bss_start = .;		/* BSS */
-  .bss : {
-	*(.bss)
-	}
-  . = ALIGN(4);
-  _end = . ;
-}
diff --git a/arch/sh/cchips/Kconfig b/arch/sh/cchips/Kconfig
index f43d18373f22..a5ab2eccdaa6 100644
--- a/arch/sh/cchips/Kconfig
+++ b/arch/sh/cchips/Kconfig
@@ -34,11 +34,6 @@ config HD64461_IRQ
 
 	  Do not change this unless you know what you are doing.
 
-config HD64461_IOBASE
-	hex "HD64461 start address"
-	depends on HD64461
-	default "0xb0000000"
-
 config HD64461_ENABLER
 	bool "HD64461 PCMCIA enabler"
 	depends on HD64461
diff --git a/arch/sh/cchips/hd6446x/hd64461.c b/arch/sh/cchips/hd6446x/hd64461.c
index 25ef91061521..50aa0c1f76ea 100644
--- a/arch/sh/cchips/hd6446x/hd64461.c
+++ b/arch/sh/cchips/hd6446x/hd64461.c
@@ -80,7 +80,7 @@ int __init setup_hd64461(void)
 
 	printk(KERN_INFO
 	       "HD64461 configured at 0x%x on irq %d(mapped into %d to %d)\n",
-	       CONFIG_HD64461_IOBASE, CONFIG_HD64461_IRQ, HD64461_IRQBASE,
+	       HD64461_IOBASE, CONFIG_HD64461_IRQ, HD64461_IRQBASE,
 	       HD64461_IRQBASE + 15);
 
 /* Should be at processor specific part.. */
diff --git a/arch/sh/configs/ap325rxa_defconfig b/arch/sh/configs/ap325rxa_defconfig
index c8d982a8a2e6..022f70e0ea03 100644
--- a/arch/sh/configs/ap325rxa_defconfig
+++ b/arch/sh/configs/ap325rxa_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 17:46:53 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:42:06 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -74,6 +75,7 @@ CONFIG_EMBEDDED=y
 CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 # CONFIG_KALLSYMS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -92,12 +94,15 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -110,7 +115,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -159,6 +163,7 @@ CONFIG_ARCH_SHMOBILE=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 CONFIG_CPU_SUBTYPE_SH7723=y
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -168,8 +173,6 @@ CONFIG_CPU_SUBTYPE_SH7723=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -573,6 +576,7 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_DH is not set
 # CONFIG_SCSI_OSD_INITIATOR is not set
@@ -695,6 +699,7 @@ CONFIG_DEVKMEM=y
 #
 # Non-8250 serial port support
 #
+# CONFIG_SERIAL_MAX3100 is not set
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=6
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
@@ -1030,6 +1035,7 @@ CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
@@ -1051,6 +1057,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1100,6 +1111,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1191,10 +1203,24 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1303,6 +1329,7 @@ CONFIG_CRYPTO_CBC=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/cayman_defconfig b/arch/sh/configs/cayman_defconfig
index fa5fc1e1e980..40301f86a45c 100644
--- a/arch/sh/configs/cayman_defconfig
+++ b/arch/sh/configs/cayman_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 17:49:14 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:42:53 2009
 #
 CONFIG_SUPERH=y
 # CONFIG_SUPERH32 is not set
@@ -40,6 +40,7 @@ CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SWAP=y
 # CONFIG_SYSVIPC is not set
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
 # CONFIG_AUDIT is not set
@@ -70,6 +71,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -89,10 +91,13 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -105,7 +110,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -127,39 +131,6 @@ CONFIG_DEFAULT_IOSCHED="cfq"
 # System type
 #
 CONFIG_CPU_SH5=y
-# CONFIG_CPU_SUBTYPE_SH7619 is not set
-# CONFIG_CPU_SUBTYPE_SH7201 is not set
-# CONFIG_CPU_SUBTYPE_SH7203 is not set
-# CONFIG_CPU_SUBTYPE_SH7206 is not set
-# CONFIG_CPU_SUBTYPE_SH7263 is not set
-# CONFIG_CPU_SUBTYPE_MXG is not set
-# CONFIG_CPU_SUBTYPE_SH7705 is not set
-# CONFIG_CPU_SUBTYPE_SH7706 is not set
-# CONFIG_CPU_SUBTYPE_SH7707 is not set
-# CONFIG_CPU_SUBTYPE_SH7708 is not set
-# CONFIG_CPU_SUBTYPE_SH7709 is not set
-# CONFIG_CPU_SUBTYPE_SH7710 is not set
-# CONFIG_CPU_SUBTYPE_SH7712 is not set
-# CONFIG_CPU_SUBTYPE_SH7720 is not set
-# CONFIG_CPU_SUBTYPE_SH7721 is not set
-# CONFIG_CPU_SUBTYPE_SH7750 is not set
-# CONFIG_CPU_SUBTYPE_SH7091 is not set
-# CONFIG_CPU_SUBTYPE_SH7750R is not set
-# CONFIG_CPU_SUBTYPE_SH7750S is not set
-# CONFIG_CPU_SUBTYPE_SH7751 is not set
-# CONFIG_CPU_SUBTYPE_SH7751R is not set
-# CONFIG_CPU_SUBTYPE_SH7760 is not set
-# CONFIG_CPU_SUBTYPE_SH4_202 is not set
-# CONFIG_CPU_SUBTYPE_SH7723 is not set
-# CONFIG_CPU_SUBTYPE_SH7763 is not set
-# CONFIG_CPU_SUBTYPE_SH7770 is not set
-# CONFIG_CPU_SUBTYPE_SH7780 is not set
-# CONFIG_CPU_SUBTYPE_SH7785 is not set
-# CONFIG_CPU_SUBTYPE_SH7786 is not set
-# CONFIG_CPU_SUBTYPE_SHX3 is not set
-# CONFIG_CPU_SUBTYPE_SH7343 is not set
-# CONFIG_CPU_SUBTYPE_SH7722 is not set
-# CONFIG_CPU_SUBTYPE_SH7366 is not set
 CONFIG_CPU_SUBTYPE_SH5_101=y
 # CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
@@ -279,8 +250,6 @@ CONFIG_BOOT_LINK_OFFSET=0x00800000
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -492,6 +461,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -568,6 +538,7 @@ CONFIG_NETDEV_1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -591,6 +562,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -779,6 +751,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_F71805F is not set
 # CONFIG_SENSORS_F71882FG is not set
 # CONFIG_SENSORS_F75375S is not set
+# CONFIG_SENSORS_G760A is not set
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_IT87 is not set
@@ -1042,7 +1015,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
@@ -1082,6 +1054,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1104,6 +1077,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1146,8 +1124,13 @@ CONFIG_MINIX_FS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1208,6 +1191,9 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 CONFIG_SCHED_DEBUG=y
 CONFIG_SCHEDSTATS=y
 # CONFIG_TIMER_STATS is not set
@@ -1241,15 +1227,21 @@ CONFIG_FRAME_POINTER=y
 # CONFIG_LATENCYTOP is not set
 # CONFIG_SYSCTL_SYSCALL_CHECK is not set
 # CONFIG_PAGE_POISONING is not set
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 # CONFIG_EARLY_SCIF_CONSOLE is not set
 # CONFIG_DEBUG_BOOTMEM is not set
@@ -1354,6 +1346,7 @@ CONFIG_CRYPTO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/dreamcast_defconfig b/arch/sh/configs/dreamcast_defconfig
index 5c1123640142..1f3cc98330bf 100644
--- a/arch/sh/configs/dreamcast_defconfig
+++ b/arch/sh/configs/dreamcast_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 17:51:48 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:44:27 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -71,6 +72,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -90,6 +92,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 CONFIG_PROFILING=y
+# CONFIG_MARKERS is not set
 # CONFIG_OPROFILE is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
@@ -98,6 +101,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -110,7 +115,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -156,6 +160,7 @@ CONFIG_CPU_SUBTYPE_SH7091=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -165,8 +170,6 @@ CONFIG_CPU_SUBTYPE_SH7091=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -271,7 +274,7 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_SH_DMA_API=y
 CONFIG_SH_DMA=y
 CONFIG_SH_DMA_IRQ_MULTI=y
-CONFIG_NR_ONCHIP_DMA_CHANNELS=6
+CONFIG_NR_ONCHIP_DMA_CHANNELS=4
 CONFIG_NR_DMA_CHANNELS_BOOL=y
 CONFIG_NR_DMA_CHANNELS=9
 # CONFIG_PVR2_DMA is not set
@@ -320,7 +323,6 @@ CONFIG_CMDLINE="console=ttySC1,115200 panic=3"
 CONFIG_MAPLE=y
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -602,6 +604,7 @@ CONFIG_INPUT_MOUSE=y
 # CONFIG_MOUSE_APPLETOUCH is not set
 # CONFIG_MOUSE_BCM5974 is not set
 # CONFIG_MOUSE_VSXXXAA is not set
+# CONFIG_MOUSE_MAPLE is not set
 # CONFIG_INPUT_JOYSTICK is not set
 # CONFIG_INPUT_TABLET is not set
 # CONFIG_INPUT_TOUCHSCREEN is not set
@@ -812,7 +815,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
@@ -866,6 +868,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -910,6 +917,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
@@ -947,10 +955,24 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1051,6 +1073,7 @@ CONFIG_CRYPTO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/edosk7705_defconfig b/arch/sh/configs/edosk7705_defconfig
index f4c34b039312..d7092457ddc7 100644
--- a/arch/sh/configs/edosk7705_defconfig
+++ b/arch/sh/configs/edosk7705_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 17:54:02 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:45:04 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
@@ -56,6 +57,7 @@ CONFIG_EMBEDDED=y
 # CONFIG_UID16 is not set
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_HOTPLUG is not set
 # CONFIG_PRINTK is not set
 # CONFIG_BUG is not set
@@ -74,12 +76,15 @@ CONFIG_SHMEM=y
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_BASE_SMALL=1
 # CONFIG_MODULES is not set
@@ -114,6 +119,7 @@ CONFIG_CPU_SUBTYPE_SH7705=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -123,8 +129,6 @@ CONFIG_CPU_SUBTYPE_SH7705=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -381,6 +385,10 @@ CONFIG_SSB_POSSIBLE=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+
 #
 # Pseudo filesystems
 #
@@ -409,10 +417,22 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -426,6 +446,7 @@ CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SECURITYFS is not set
 # CONFIG_SECURITY_FILE_CAPABILITIES is not set
 # CONFIG_CRYPTO is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/edosk7760_defconfig b/arch/sh/configs/edosk7760_defconfig
index 7825c2699f18..a822b1d8c116 100644
--- a/arch/sh/configs/edosk7760_defconfig
+++ b/arch/sh/configs/edosk7760_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 17:54:57 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:45:25 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -40,6 +41,7 @@ CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
@@ -67,7 +69,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -77,6 +78,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -96,6 +98,7 @@ CONFIG_COMPAT_BRK=y
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -103,6 +106,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -115,7 +120,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -161,6 +165,7 @@ CONFIG_CPU_SH4=y
 CONFIG_CPU_SUBTYPE_SH7760=y
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -170,8 +175,6 @@ CONFIG_CPU_SUBTYPE_SH7760=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -815,6 +818,7 @@ CONFIG_EXT2_FS_XATTR=y
 # CONFIG_EXT2_FS_SECURITY is not set
 CONFIG_EXT2_FS_XIP=y
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -838,6 +842,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_FUSE_FS is not set
 CONFIG_GENERIC_ACL=y
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -883,6 +892,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 # CONFIG_NFS_V3 is not set
@@ -964,6 +974,9 @@ CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
 CONFIG_TIMER_STATS=y
@@ -1001,6 +1014,7 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1010,9 +1024,14 @@ CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 # CONFIG_PREEMPT_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1126,6 +1145,7 @@ CONFIG_CRYPTO_DES=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/espt_defconfig b/arch/sh/configs/espt_defconfig
index ebb4c37abaa6..c5b50077913d 100644
--- a/arch/sh/configs/espt_defconfig
+++ b/arch/sh/configs/espt_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 17:58:18 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:46:26 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -78,6 +79,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -106,6 +108,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -117,7 +121,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -164,6 +167,7 @@ CONFIG_CPU_SH4A=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 CONFIG_CPU_SUBTYPE_SH7763=y
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -173,8 +177,6 @@ CONFIG_CPU_SUBTYPE_SH7763=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -548,6 +550,7 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_DH is not set
 # CONFIG_SCSI_OSD_INITIATOR is not set
@@ -919,6 +922,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -942,6 +946,11 @@ CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
 CONFIG_GENERIC_ACL=y
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -985,8 +994,13 @@ CONFIG_CRAMFS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 # CONFIG_NFS_V3 is not set
@@ -1075,11 +1089,25 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1179,6 +1207,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig
index 82b113af08d3..8e13027eecc3 100644
--- a/arch/sh/configs/hp6xx_defconfig
+++ b/arch/sh/configs/hp6xx_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:01:05 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:47:15 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -67,6 +68,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -85,12 +87,15 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -98,7 +103,6 @@ CONFIG_BASE_SMALL=0
 # CONFIG_MODULES is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -144,6 +148,7 @@ CONFIG_CPU_SUBTYPE_SH7709=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -153,8 +158,6 @@ CONFIG_CPU_SUBTYPE_SH7709=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -385,6 +388,7 @@ CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_SRP_ATTRS is not set
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
 # CONFIG_SCSI_DH is not set
@@ -431,6 +435,7 @@ CONFIG_KEYBOARD_HP6XX=y
 # CONFIG_INPUT_JOYSTICK is not set
 # CONFIG_INPUT_TABLET is not set
 CONFIG_INPUT_TOUCHSCREEN=y
+# CONFIG_TOUCHSCREEN_AD7879 is not set
 # CONFIG_TOUCHSCREEN_FUJITSU is not set
 # CONFIG_TOUCHSCREEN_GUNZE is not set
 # CONFIG_TOUCHSCREEN_ELO is not set
@@ -673,6 +678,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -719,6 +729,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 
 #
 # Partition Types
@@ -786,10 +797,23 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -898,6 +922,7 @@ CONFIG_CRYPTO_MD5=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig
index b6fa4a7599d0..7f549aef0dfd 100644
--- a/arch/sh/configs/landisk_defconfig
+++ b/arch/sh/configs/landisk_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:02:54 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:47:48 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -69,6 +70,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_EXTRA_PASS=y
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -88,6 +90,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -95,6 +98,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -107,7 +112,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -153,6 +157,7 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -162,8 +167,6 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -292,8 +295,6 @@ CONFIG_BOOT_LINK_OFFSET=0x00800000
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -602,6 +603,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -706,6 +708,7 @@ CONFIG_NETDEV_1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -729,6 +732,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -922,6 +926,7 @@ CONFIG_VIDEO_HELPER_CHIPS_AUTO=y
 # CONFIG_SOC_CAMERA is not set
 CONFIG_V4L_USB_DRIVERS=y
 # CONFIG_USB_VIDEO_CLASS is not set
+CONFIG_USB_VIDEO_CLASS_INPUT_EVDEV=y
 # CONFIG_USB_GSPCA is not set
 # CONFIG_VIDEO_HDPVR is not set
 CONFIG_VIDEO_USBVIDEO=m
@@ -994,15 +999,17 @@ CONFIG_USB_HID=m
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=m
 CONFIG_HID_APPLE=m
 CONFIG_HID_BELKIN=m
 CONFIG_HID_CHERRY=m
 CONFIG_HID_CHICONY=m
 CONFIG_HID_CYPRESS=m
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=m
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=m
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=m
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1197,6 +1204,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1221,6 +1229,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1270,10 +1283,15 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 CONFIG_UFS_FS=m
 # CONFIG_UFS_FS_WRITE is not set
 # CONFIG_UFS_DEBUG is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=m
 CONFIG_NFS_V3=y
@@ -1364,10 +1382,23 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_SH_STANDARD_BIOS=y
@@ -1469,6 +1500,7 @@ CONFIG_CRYPTO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig
index 92c515c4199f..a7db539f2800 100644
--- a/arch/sh/configs/lboxre2_defconfig
+++ b/arch/sh/configs/lboxre2_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:06:51 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:48:54 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -69,6 +70,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_EXTRA_PASS=y
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -88,6 +90,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -95,6 +98,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -107,7 +112,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -153,6 +157,7 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -162,8 +167,6 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -293,8 +296,6 @@ CONFIG_CMDLINE="console=ttySC1,115200 root=/dev/sda1"
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -542,6 +543,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -702,6 +704,7 @@ CONFIG_NETDEV_1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -725,6 +728,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -931,7 +935,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
@@ -1007,6 +1010,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1028,6 +1032,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1073,8 +1082,13 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
@@ -1151,10 +1165,23 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_SH_STANDARD_BIOS=y
@@ -1256,6 +1283,7 @@ CONFIG_CRYPTO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/magicpanelr2_defconfig b/arch/sh/configs/magicpanelr2_defconfig
index 26586c2d64ca..58bec61506fa 100644
--- a/arch/sh/configs/magicpanelr2_defconfig
+++ b/arch/sh/configs/magicpanelr2_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:07:39 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:49:32 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -39,6 +40,7 @@ CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 # CONFIG_TASKSTATS is not set
@@ -66,7 +68,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -76,6 +77,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -94,6 +96,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -101,6 +104,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -113,7 +118,6 @@ CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -159,6 +163,7 @@ CONFIG_CPU_SUBTYPE_SH7720=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -168,8 +173,6 @@ CONFIG_CPU_SUBTYPE_SH7720=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -813,6 +816,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_EXT3_FS_XATTR is not set
 # CONFIG_EXT4_FS is not set
 CONFIG_JBD=y
@@ -830,6 +834,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -884,6 +893,7 @@ CONFIG_JFFS2_RTIME=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -965,6 +975,7 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 # CONFIG_DETECT_SOFTLOCKUP is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -1000,6 +1011,7 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1008,9 +1020,14 @@ CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 # CONFIG_IRQSOFF_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1035,6 +1052,7 @@ CONFIG_DUMP_CODE=y
 # CONFIG_SECURITYFS is not set
 # CONFIG_SECURITY_FILE_CAPABILITIES is not set
 # CONFIG_CRYPTO is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/microdev_defconfig b/arch/sh/configs/microdev_defconfig
index 75178355d69a..2886fc84bc1c 100644
--- a/arch/sh/configs/microdev_defconfig
+++ b/arch/sh/configs/microdev_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:11:13 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:50:51 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -65,7 +66,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -74,6 +74,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -92,12 +93,15 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -105,7 +109,6 @@ CONFIG_BASE_SMALL=0
 # CONFIG_MODULES is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -151,6 +154,7 @@ CONFIG_CPU_SH4=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 CONFIG_CPU_SUBTYPE_SH4_202=y
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -160,8 +164,6 @@ CONFIG_CPU_SUBTYPE_SH4_202=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -647,6 +649,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -668,6 +671,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -715,6 +723,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -802,10 +811,24 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -914,6 +937,7 @@ CONFIG_CRYPTO_DES=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/migor_defconfig b/arch/sh/configs/migor_defconfig
index a8720f9c6047..8ecceb4bf27e 100644
--- a/arch/sh/configs/migor_defconfig
+++ b/arch/sh/configs/migor_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:14:03 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:51:34 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -67,7 +68,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -76,6 +76,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -104,6 +105,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -115,7 +118,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -165,6 +167,7 @@ CONFIG_ARCH_SHMOBILE=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -174,8 +177,6 @@ CONFIG_ARCH_SHMOBILE=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 CONFIG_CPU_SUBTYPE_SH7722=y
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -577,6 +578,7 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_DH is not set
 # CONFIG_SCSI_OSD_INITIATOR is not set
@@ -873,7 +875,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 # CONFIG_USB_ARCH_HAS_OHCI is not set
@@ -1011,6 +1012,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1056,6 +1062,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 # CONFIG_NFS_V3 is not set
@@ -1105,11 +1112,25 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1218,6 +1239,7 @@ CONFIG_CRYPTO_WORKQUEUE=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/polaris_defconfig b/arch/sh/configs/polaris_defconfig
index df2d177d5346..2b9507286182 100644
--- a/arch/sh/configs/polaris_defconfig
+++ b/arch/sh/configs/polaris_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:16:48 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:52:19 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -40,6 +41,7 @@ CONFIG_LOCALVERSION=""
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 # CONFIG_TASKSTATS is not set
@@ -76,6 +78,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -94,6 +97,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -101,6 +105,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -113,7 +119,6 @@ CONFIG_MODVERSIONS=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -159,6 +164,7 @@ CONFIG_CPU_SUBTYPE_SH7709=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -168,8 +174,6 @@ CONFIG_CPU_SUBTYPE_SH7709=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -777,6 +781,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -831,6 +840,7 @@ CONFIG_JFFS2_RTIME=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -874,6 +884,9 @@ CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -914,6 +927,7 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -923,9 +937,14 @@ CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 # CONFIG_PREEMPT_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -950,6 +969,7 @@ CONFIG_DUMP_CODE=y
 # CONFIG_SECURITYFS is not set
 # CONFIG_SECURITY_FILE_CAPABILITIES is not set
 # CONFIG_CRYPTO is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig
index 7def4df46ddb..943da63a3852 100644
--- a/arch/sh/configs/r7780mp_defconfig
+++ b/arch/sh/configs/r7780mp_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:20:17 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:53:28 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -78,6 +79,7 @@ CONFIG_UID16=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -107,6 +109,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_BASE_SMALL=0
@@ -118,7 +122,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -165,6 +168,7 @@ CONFIG_CPU_SH4A=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 CONFIG_CPU_SUBTYPE_SH7780=y
@@ -174,8 +178,6 @@ CONFIG_CPU_SUBTYPE_SH7780=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -258,7 +260,7 @@ CONFIG_SH_R7780MP=y
 #
 CONFIG_SH_TMU=y
 CONFIG_SH_TIMER_IRQ=28
-CONFIG_SH_PCLK_FREQ=32000000
+CONFIG_SH_PCLK_FREQ=33333333
 # CONFIG_NO_HZ is not set
 # CONFIG_HIGH_RES_TIMERS is not set
 CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
@@ -313,8 +315,6 @@ CONFIG_CMDLINE="console=ttySC0,115200 root=/dev/sda1"
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -536,6 +536,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -696,6 +697,7 @@ CONFIG_E1000=m
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -719,6 +721,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -920,6 +923,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_F71805F is not set
 # CONFIG_SENSORS_F71882FG is not set
 # CONFIG_SENSORS_F75375S is not set
+# CONFIG_SENSORS_G760A is not set
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_IT87 is not set
@@ -1027,7 +1031,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
@@ -1120,6 +1123,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1142,6 +1146,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 CONFIG_FUSE_FS=m
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1191,6 +1200,7 @@ CONFIG_MINIX_FS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1279,6 +1289,9 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -1316,6 +1329,7 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1325,11 +1339,16 @@ CONFIG_TRACING=y
 # CONFIG_PREEMPT_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1449,6 +1468,7 @@ CONFIG_CRYPTO_DES=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/r7785rp_defconfig b/arch/sh/configs/r7785rp_defconfig
index cb134ffc2118..82658f672398 100644
--- a/arch/sh/configs/r7785rp_defconfig
+++ b/arch/sh/configs/r7785rp_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:24:35 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:55:10 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -43,6 +44,7 @@ CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
@@ -78,6 +80,7 @@ CONFIG_UID16=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -108,6 +111,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -120,7 +125,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -168,6 +172,7 @@ CONFIG_CPU_SHX2=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -177,8 +182,6 @@ CONFIG_CPU_SUBTYPE_SH7785=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -266,7 +269,7 @@ CONFIG_SH_R7785RP=y
 #
 CONFIG_SH_TMU=y
 CONFIG_SH_TIMER_IRQ=28
-CONFIG_SH_PCLK_FREQ=50000000
+CONFIG_SH_PCLK_FREQ=33333333
 CONFIG_TICK_ONESHOT=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -337,8 +340,6 @@ CONFIG_CMDLINE="console=ttySC0,115200 root=/dev/sda1"
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 # CONFIG_PCI_LEGACY is not set
@@ -561,6 +562,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -698,6 +700,7 @@ CONFIG_NETDEV_1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -721,6 +724,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -948,6 +952,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_F71805F is not set
 # CONFIG_SENSORS_F71882FG is not set
 # CONFIG_SENSORS_F75375S is not set
+# CONFIG_SENSORS_G760A is not set
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_IT87 is not set
@@ -970,6 +975,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_PC87360 is not set
 # CONFIG_SENSORS_PC87427 is not set
 # CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_SENSORS_SHT15 is not set
 # CONFIG_SENSORS_SIS5595 is not set
 # CONFIG_SENSORS_DME1737 is not set
 # CONFIG_SENSORS_SMSC47M1 is not set
@@ -1109,7 +1115,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
@@ -1202,6 +1207,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1224,6 +1230,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 CONFIG_FUSE_FS=m
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1273,6 +1284,7 @@ CONFIG_MINIX_FS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1359,6 +1371,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 # CONFIG_DETECT_SOFTLOCKUP is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -1401,6 +1414,7 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1410,11 +1424,16 @@ CONFIG_TRACING=y
 # CONFIG_PREEMPT_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1534,6 +1553,7 @@ CONFIG_CRYPTO_DES=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/rsk7201_defconfig b/arch/sh/configs/rsk7201_defconfig
index a037c744b798..fa4395768d19 100644
--- a/arch/sh/configs/rsk7201_defconfig
+++ b/arch/sh/configs/rsk7201_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:29:08 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:56:29 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -65,7 +66,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -74,6 +74,7 @@ CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -100,6 +101,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_RT_MUTEXES=y
 CONFIG_BASE_SMALL=0
@@ -110,7 +113,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -157,6 +159,7 @@ CONFIG_CPU_SUBTYPE_SH7201=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -166,8 +169,6 @@ CONFIG_CPU_SUBTYPE_SH7201=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -602,6 +603,11 @@ CONFIG_EXT2_FS=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -651,8 +657,13 @@ CONFIG_JFFS2_RTIME=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 
 #
 # Partition Types
@@ -686,11 +697,24 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -705,6 +729,7 @@ CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SECURITYFS is not set
 # CONFIG_SECURITY_FILE_CAPABILITIES is not set
 # CONFIG_CRYPTO is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/rsk7203_defconfig b/arch/sh/configs/rsk7203_defconfig
index 9ae28e88426c..e3a65f819f0a 100644
--- a/arch/sh/configs/rsk7203_defconfig
+++ b/arch/sh/configs/rsk7203_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:30:34 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:57:06 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -39,6 +40,7 @@ CONFIG_LOCALVERSION=""
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
@@ -70,7 +72,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -80,6 +81,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -106,6 +108,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_RT_MUTEXES=y
 CONFIG_BASE_SMALL=0
@@ -116,7 +120,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -163,6 +166,7 @@ CONFIG_CPU_SUBTYPE_SH7203=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -172,8 +176,6 @@ CONFIG_CPU_SUBTYPE_SH7203=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -750,15 +752,17 @@ CONFIG_USB_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=y
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=y
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -874,6 +878,7 @@ CONFIG_LEDS_CLASS=y
 # LED drivers
 #
 CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_GPIO_PLATFORM=y
 
 #
 # LED Triggers
@@ -882,6 +887,7 @@ CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_BACKLIGHT=y
+# CONFIG_LEDS_TRIGGER_GPIO is not set
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 
 #
@@ -950,6 +956,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -989,8 +1000,13 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 # CONFIG_NFS_V3 is not set
@@ -1033,6 +1049,9 @@ CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -1076,6 +1095,7 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1083,11 +1103,16 @@ CONFIG_TRACING=y
 # CONFIG_FUNCTION_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1111,6 +1136,7 @@ CONFIG_DUMP_CODE=y
 # CONFIG_SECURITYFS is not set
 # CONFIG_SECURITY_FILE_CAPABILITIES is not set
 # CONFIG_CRYPTO is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/rts7751r2d1_defconfig b/arch/sh/configs/rts7751r2d1_defconfig
index c0f741af6da8..a4a59f6205ab 100644
--- a/arch/sh/configs/rts7751r2d1_defconfig
+++ b/arch/sh/configs/rts7751r2d1_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:33:25 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:58:13 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -70,6 +71,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -99,6 +101,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -110,7 +114,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -156,6 +159,7 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -165,8 +169,6 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -302,8 +304,6 @@ CONFIG_CMDLINE="console=tty0 console=ttySC0,115200 root=/dev/sda1 earlyprintk=se
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -513,6 +513,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -672,6 +673,7 @@ CONFIG_NETDEV_1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -695,6 +697,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -793,6 +796,7 @@ CONFIG_SERIAL_8250_RUNTIME_UARTS=4
 #
 # Non-8250 serial port support
 #
+# CONFIG_SERIAL_MAX3100 is not set
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=1
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
@@ -1079,15 +1083,17 @@ CONFIG_USB_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=y
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=y
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1290,6 +1296,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1337,6 +1348,7 @@ CONFIG_MINIX_FS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
@@ -1417,11 +1429,25 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1524,6 +1550,7 @@ CONFIG_CRYPTO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/rts7751r2dplus_defconfig b/arch/sh/configs/rts7751r2dplus_defconfig
index 8feef629e49c..a860435b8847 100644
--- a/arch/sh/configs/rts7751r2dplus_defconfig
+++ b/arch/sh/configs/rts7751r2dplus_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:34:12 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:59:01 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -70,6 +71,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -99,6 +101,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -110,7 +114,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -156,6 +159,7 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -165,8 +169,6 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -302,8 +304,6 @@ CONFIG_CMDLINE="console=tty0 console=ttySC0,115200 root=/dev/sda1 earlyprintk=se
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -424,7 +424,92 @@ CONFIG_FIRMWARE_IN_KERNEL=y
 CONFIG_EXTRA_FIRMWARE=""
 # CONFIG_SYS_HYPERVISOR is not set
 # CONFIG_CONNECTOR is not set
-# CONFIG_MTD is not set
+CONFIG_MTD=y
+# CONFIG_MTD_DEBUG is not set
+CONFIG_MTD_CONCAT=y
+CONFIG_MTD_PARTITIONS=y
+# CONFIG_MTD_TESTS is not set
+# CONFIG_MTD_REDBOOT_PARTS is not set
+CONFIG_MTD_CMDLINE_PARTS=y
+# CONFIG_MTD_AR7_PARTS is not set
+
+#
+# User Modules And Translation Layers
+#
+CONFIG_MTD_CHAR=y
+# CONFIG_MTD_BLKDEVS is not set
+# CONFIG_MTD_BLOCK is not set
+# CONFIG_MTD_BLOCK_RO is not set
+# CONFIG_FTL is not set
+# CONFIG_NFTL is not set
+# CONFIG_INFTL is not set
+# CONFIG_RFD_FTL is not set
+# CONFIG_SSFDC is not set
+# CONFIG_MTD_OOPS is not set
+
+#
+# RAM/ROM/Flash chip drivers
+#
+CONFIG_MTD_CFI=y
+# CONFIG_MTD_JEDECPROBE is not set
+CONFIG_MTD_GEN_PROBE=y
+# CONFIG_MTD_CFI_ADV_OPTIONS is not set
+CONFIG_MTD_MAP_BANK_WIDTH_1=y
+CONFIG_MTD_MAP_BANK_WIDTH_2=y
+CONFIG_MTD_MAP_BANK_WIDTH_4=y
+# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
+CONFIG_MTD_CFI_I1=y
+CONFIG_MTD_CFI_I2=y
+# CONFIG_MTD_CFI_I4 is not set
+# CONFIG_MTD_CFI_I8 is not set
+# CONFIG_MTD_CFI_INTELEXT is not set
+CONFIG_MTD_CFI_AMDSTD=y
+# CONFIG_MTD_CFI_STAA is not set
+CONFIG_MTD_CFI_UTIL=y
+# CONFIG_MTD_RAM is not set
+# CONFIG_MTD_ROM is not set
+# CONFIG_MTD_ABSENT is not set
+
+#
+# Mapping drivers for chip access
+#
+# CONFIG_MTD_COMPLEX_MAPPINGS is not set
+CONFIG_MTD_PHYSMAP=y
+# CONFIG_MTD_PHYSMAP_COMPAT is not set
+# CONFIG_MTD_INTEL_VR_NOR is not set
+# CONFIG_MTD_PLATRAM is not set
+
+#
+# Self-contained MTD device drivers
+#
+# CONFIG_MTD_PMC551 is not set
+# CONFIG_MTD_DATAFLASH is not set
+# CONFIG_MTD_M25P80 is not set
+# CONFIG_MTD_SLRAM is not set
+# CONFIG_MTD_PHRAM is not set
+# CONFIG_MTD_MTDRAM is not set
+# CONFIG_MTD_BLOCK2MTD is not set
+
+#
+# Disk-On-Chip Device Drivers
+#
+# CONFIG_MTD_DOC2000 is not set
+# CONFIG_MTD_DOC2001 is not set
+# CONFIG_MTD_DOC2001PLUS is not set
+# CONFIG_MTD_NAND is not set
+# CONFIG_MTD_ONENAND is not set
+
+#
+# LPDDR flash memory drivers
+#
+# CONFIG_MTD_LPDDR is not set
+
+#
+# UBI - Unsorted block images
+#
+# CONFIG_MTD_UBI is not set
 # CONFIG_PARPORT is not set
 CONFIG_BLK_DEV=y
 # CONFIG_BLK_CPQ_CISS_DA is not set
@@ -513,6 +598,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -672,6 +758,7 @@ CONFIG_NETDEV_1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -695,6 +782,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -793,6 +881,7 @@ CONFIG_SERIAL_8250_RUNTIME_UARTS=4
 #
 # Non-8250 serial port support
 #
+# CONFIG_SERIAL_MAX3100 is not set
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=1
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
@@ -1079,15 +1168,17 @@ CONFIG_USB_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=y
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=y
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1290,6 +1381,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1337,6 +1433,7 @@ CONFIG_MINIX_FS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
@@ -1417,11 +1514,25 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1524,6 +1635,7 @@ CONFIG_CRYPTO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig
index 739e2299ae80..a629b79a1844 100644
--- a/arch/sh/configs/sdk7780_defconfig
+++ b/arch/sh/configs/sdk7780_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:34:43 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 12:59:32 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -41,6 +42,7 @@ CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
@@ -73,6 +75,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -93,6 +96,7 @@ CONFIG_COMPAT_BRK=y
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -100,6 +104,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -112,7 +118,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 CONFIG_LBD=y
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -159,6 +164,7 @@ CONFIG_CPU_SH4A=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 CONFIG_CPU_SUBTYPE_SH7780=y
@@ -168,8 +174,6 @@ CONFIG_CPU_SUBTYPE_SH7780=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -310,8 +314,6 @@ CONFIG_CMDLINE="mem=128M console=tty0 console=ttySC0,115200 ip=bootp root=/dev/n
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 # CONFIG_PCI_LEGACY is not set
@@ -646,6 +648,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -1091,15 +1094,17 @@ CONFIG_USB_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=y
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=y
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1257,6 +1262,7 @@ CONFIG_EXT2_FS_POSIX_ACL=y
 # CONFIG_EXT2_FS_SECURITY is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1280,6 +1286,11 @@ CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
 CONFIG_GENERIC_ACL=y
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1331,6 +1342,7 @@ CONFIG_MINIX_FS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1418,6 +1430,9 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
 CONFIG_TIMER_STATS=y
@@ -1455,6 +1470,7 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1464,9 +1480,14 @@ CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 # CONFIG_PREEMPT_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1580,6 +1601,7 @@ CONFIG_CRYPTO_DES=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig
index d30e0a7ad9f1..5caf85a3312d 100644
--- a/arch/sh/configs/se7206_defconfig
+++ b/arch/sh/configs/se7206_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:39:37 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:01:02 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -40,6 +41,7 @@ CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
@@ -63,6 +65,7 @@ CONFIG_CGROUP_DEBUG=y
 CONFIG_CGROUP_NS=y
 # CONFIG_CGROUP_FREEZER is not set
 CONFIG_CGROUP_DEVICE=y
+# CONFIG_CPUSETS is not set
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
 CONFIG_CGROUP_MEM_RES_CTLR=y
@@ -80,7 +83,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -90,6 +92,7 @@ CONFIG_EMBEDDED=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -116,6 +119,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_RT_MUTEXES=y
 CONFIG_BASE_SMALL=0
@@ -127,7 +132,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -174,6 +178,7 @@ CONFIG_CPU_SUBTYPE_SH7206=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -183,8 +188,6 @@ CONFIG_CPU_SUBTYPE_SH7206=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -745,6 +748,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -785,8 +793,13 @@ CONFIG_CRAMFS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -831,6 +844,9 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -869,6 +885,7 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -876,11 +893,16 @@ CONFIG_TRACING=y
 # CONFIG_FUNCTION_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -991,6 +1013,7 @@ CONFIG_CRYPTO_LZO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7343_defconfig b/arch/sh/configs/se7343_defconfig
index fbb72d029e68..004d531716dc 100644
--- a/arch/sh/configs/se7343_defconfig
+++ b/arch/sh/configs/se7343_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:42:00 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:01:44 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -40,6 +41,7 @@ CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
 # CONFIG_AUDIT is not set
@@ -73,6 +75,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -91,6 +94,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -98,6 +102,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_BASE_SMALL=0
@@ -109,7 +115,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -158,6 +163,7 @@ CONFIG_ARCH_SHMOBILE=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -167,8 +173,6 @@ CONFIG_ARCH_SHMOBILE=y
 CONFIG_CPU_SUBTYPE_SH7343=y
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -769,6 +773,7 @@ CONFIG_VIDEO_HELPER_CHIPS_AUTO=y
 # CONFIG_SOC_CAMERA is not set
 CONFIG_V4L_USB_DRIVERS=y
 # CONFIG_USB_VIDEO_CLASS is not set
+CONFIG_USB_VIDEO_CLASS_INPUT_EVDEV=y
 CONFIG_USB_GSPCA=m
 # CONFIG_USB_M5602 is not set
 # CONFIG_USB_STV06XX is not set
@@ -800,6 +805,7 @@ CONFIG_USB_GSPCA=m
 # CONFIG_VIDEO_PVRUSB2 is not set
 # CONFIG_VIDEO_HDPVR is not set
 # CONFIG_VIDEO_EM28XX is not set
+# CONFIG_VIDEO_CX231XX is not set
 # CONFIG_VIDEO_USBVISION is not set
 # CONFIG_USB_VICAM is not set
 # CONFIG_USB_IBMCAM is not set
@@ -813,6 +819,7 @@ CONFIG_USB_GSPCA=m
 # CONFIG_USB_STV680 is not set
 # CONFIG_USB_ZC0301 is not set
 # CONFIG_USB_PWC is not set
+CONFIG_USB_PWC_INPUT_EVDEV=y
 # CONFIG_USB_ZR364XX is not set
 # CONFIG_USB_STKWEBCAM is not set
 # CONFIG_USB_S2255 is not set
@@ -914,15 +921,17 @@ CONFIG_USB_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=y
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=y
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1050,6 +1059,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1070,6 +1080,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1125,6 +1140,7 @@ CONFIG_CRAMFS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1174,10 +1190,23 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1279,6 +1308,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7619_defconfig b/arch/sh/configs/se7619_defconfig
index 125304e80f57..edbece52afc1 100644
--- a/arch/sh/configs/se7619_defconfig
+++ b/arch/sh/configs/se7619_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:44:53 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:02:32 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -61,6 +62,7 @@ CONFIG_EMBEDDED=y
 # CONFIG_UID16 is not set
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -78,11 +80,14 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_BASE_SMALL=1
@@ -134,6 +139,7 @@ CONFIG_CPU_SUBTYPE_SH7619=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -143,8 +149,6 @@ CONFIG_CPU_SUBTYPE_SH7619=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -513,7 +517,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 # CONFIG_USB_ARCH_HAS_OHCI is not set
@@ -563,6 +566,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -601,8 +609,13 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 
 #
 # Partition Types
@@ -630,10 +643,21 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -647,6 +671,7 @@ CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SECURITYFS is not set
 # CONFIG_SECURITY_FILE_CAPABILITIES is not set
 # CONFIG_CRYPTO is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7705_defconfig b/arch/sh/configs/se7705_defconfig
index 0308abf52384..bae161c66835 100644
--- a/arch/sh/configs/se7705_defconfig
+++ b/arch/sh/configs/se7705_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:45:56 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:02:52 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -62,7 +63,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -70,6 +70,7 @@ CONFIG_EMBEDDED=y
 CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -88,12 +89,15 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -150,6 +154,7 @@ CONFIG_CPU_SUBTYPE_SH7705=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -159,8 +164,6 @@ CONFIG_CPU_SUBTYPE_SH7705=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -698,7 +701,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 # CONFIG_USB_ARCH_HAS_OHCI is not set
@@ -751,6 +753,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -804,6 +811,7 @@ CONFIG_JFFS2_RTIME=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 # CONFIG_NFS_V3 is not set
@@ -847,10 +855,23 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -949,6 +970,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7712_defconfig b/arch/sh/configs/se7712_defconfig
index a8c24b703489..330043f3c316 100644
--- a/arch/sh/configs/se7712_defconfig
+++ b/arch/sh/configs/se7712_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:48:18 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:03:27 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
@@ -38,6 +39,7 @@ CONFIG_LOCALVERSION=""
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
@@ -69,6 +71,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 # CONFIG_BUG is not set
@@ -87,6 +90,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -94,6 +98,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -105,7 +111,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -151,6 +156,7 @@ CONFIG_CPU_SUBTYPE_SH7712=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -160,8 +166,6 @@ CONFIG_CPU_SUBTYPE_SH7712=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -585,6 +589,7 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_DH is not set
 # CONFIG_SCSI_OSD_INITIATOR is not set
@@ -812,6 +817,7 @@ CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -832,6 +838,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -887,6 +898,7 @@ CONFIG_CRAMFS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 # CONFIG_NFS_V3 is not set
@@ -927,6 +939,7 @@ CONFIG_FRAME_WARN=1024
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 # CONFIG_DETECT_SOFTLOCKUP is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -961,6 +974,7 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -969,9 +983,14 @@ CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 # CONFIG_IRQSOFF_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1090,6 +1109,7 @@ CONFIG_CRYPTO_DEFLATE=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7721_defconfig b/arch/sh/configs/se7721_defconfig
index 4b79c2567dc8..56478918440d 100644
--- a/arch/sh/configs/se7721_defconfig
+++ b/arch/sh/configs/se7721_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:51:44 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:04:19 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
@@ -38,6 +39,7 @@ CONFIG_LOCALVERSION=""
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
@@ -73,6 +75,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 # CONFIG_BUG is not set
@@ -91,6 +94,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -98,6 +102,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -109,7 +115,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -155,6 +160,7 @@ CONFIG_CPU_SUBTYPE_SH7721=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -164,8 +170,6 @@ CONFIG_CPU_SUBTYPE_SH7721=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -776,15 +780,17 @@ CONFIG_USB_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=y
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=y
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -943,6 +949,7 @@ CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -963,6 +970,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1021,6 +1033,7 @@ CONFIG_CRAMFS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 
 #
@@ -1085,6 +1098,7 @@ CONFIG_FRAME_WARN=1024
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 # CONFIG_DETECT_SOFTLOCKUP is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -1119,6 +1133,7 @@ CONFIG_FRAME_POINTER=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1127,9 +1142,14 @@ CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 # CONFIG_IRQSOFF_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1248,6 +1268,7 @@ CONFIG_CRYPTO_DEFLATE=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7722_defconfig b/arch/sh/configs/se7722_defconfig
index 82bdaac45fb5..726fdbdb2807 100644
--- a/arch/sh/configs/se7722_defconfig
+++ b/arch/sh/configs/se7722_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:55:10 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:05:29 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -69,7 +70,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -78,6 +78,7 @@ CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -97,6 +98,7 @@ CONFIG_COMPAT_BRK=y
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 CONFIG_PROFILING=y
+# CONFIG_MARKERS is not set
 # CONFIG_OPROFILE is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
@@ -105,6 +107,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -117,7 +121,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -167,6 +170,7 @@ CONFIG_ARCH_SHMOBILE=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -176,8 +180,6 @@ CONFIG_ARCH_SHMOBILE=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 CONFIG_CPU_SUBTYPE_SH7722=y
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -486,6 +488,7 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_DH is not set
 # CONFIG_SCSI_OSD_INITIATOR is not set
@@ -692,7 +695,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 # CONFIG_USB_ARCH_HAS_OHCI is not set
@@ -766,6 +768,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -788,6 +791,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -832,6 +840,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
@@ -872,11 +881,25 @@ CONFIG_DEBUG_FS=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_SH_STANDARD_BIOS=y
@@ -977,6 +1000,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7724_defconfig b/arch/sh/configs/se7724_defconfig
new file mode 100644
index 000000000000..96d2587467e6
--- /dev/null
+++ b/arch/sh/configs/se7724_defconfig
@@ -0,0 +1,1552 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.30-rc6
+# Tue May 26 13:18:09 2009
+#
+CONFIG_SUPERH=y
+CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
+CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+CONFIG_GENERIC_BUG=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_GENERIC_GPIO=y
+CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
+CONFIG_ARCH_HIBERNATION_POSSIBLE=y
+CONFIG_SYS_SUPPORTS_CMT=y
+CONFIG_SYS_SUPPORTS_TMU=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_ARCH_NO_VIRT_TO_BUS=y
+CONFIG_ARCH_HAS_DEFAULT_IDLE=y
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# General setup
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_BROKEN_ON_SMP=y
+CONFIG_LOCK_KERNEL=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_LOCALVERSION=""
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+# CONFIG_POSIX_MQUEUE is not set
+CONFIG_BSD_PROCESS_ACCT=y
+# CONFIG_BSD_PROCESS_ACCT_V3 is not set
+# CONFIG_TASKSTATS is not set
+# CONFIG_AUDIT is not set
+
+#
+# RCU Subsystem
+#
+CONFIG_CLASSIC_RCU=y
+# CONFIG_TREE_RCU is not set
+# CONFIG_PREEMPT_RCU is not set
+# CONFIG_TREE_RCU_TRACE is not set
+# CONFIG_PREEMPT_RCU_TRACE is not set
+# CONFIG_IKCONFIG is not set
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_GROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+# CONFIG_RT_GROUP_SCHED is not set
+CONFIG_USER_SCHED=y
+# CONFIG_CGROUP_SCHED is not set
+# CONFIG_CGROUPS is not set
+CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+# CONFIG_RELAY is not set
+# CONFIG_NAMESPACES is not set
+# CONFIG_BLK_DEV_INITRD is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
+CONFIG_EMBEDDED=y
+CONFIG_UID16=y
+CONFIG_SYSCTL_SYSCALL=y
+# CONFIG_KALLSYMS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
+CONFIG_HOTPLUG=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_SHMEM=y
+CONFIG_AIO=y
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_COMPAT_BRK=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
+# CONFIG_SLOB is not set
+# CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
+CONFIG_HAVE_OPROFILE=y
+CONFIG_HAVE_IOREMAP_PROT=y
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_SLABINFO=y
+CONFIG_RT_MUTEXES=y
+CONFIG_BASE_SMALL=0
+CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+# CONFIG_DEFAULT_AS is not set
+# CONFIG_DEFAULT_DEADLINE is not set
+CONFIG_DEFAULT_CFQ=y
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="cfq"
+# CONFIG_FREEZER is not set
+
+#
+# System type
+#
+CONFIG_CPU_SH4=y
+CONFIG_CPU_SH4A=y
+CONFIG_CPU_SHX2=y
+CONFIG_ARCH_SHMOBILE=y
+# CONFIG_CPU_SUBTYPE_SH7619 is not set
+# CONFIG_CPU_SUBTYPE_SH7201 is not set
+# CONFIG_CPU_SUBTYPE_SH7203 is not set
+# CONFIG_CPU_SUBTYPE_SH7206 is not set
+# CONFIG_CPU_SUBTYPE_SH7263 is not set
+# CONFIG_CPU_SUBTYPE_MXG is not set
+# CONFIG_CPU_SUBTYPE_SH7705 is not set
+# CONFIG_CPU_SUBTYPE_SH7706 is not set
+# CONFIG_CPU_SUBTYPE_SH7707 is not set
+# CONFIG_CPU_SUBTYPE_SH7708 is not set
+# CONFIG_CPU_SUBTYPE_SH7709 is not set
+# CONFIG_CPU_SUBTYPE_SH7710 is not set
+# CONFIG_CPU_SUBTYPE_SH7712 is not set
+# CONFIG_CPU_SUBTYPE_SH7720 is not set
+# CONFIG_CPU_SUBTYPE_SH7721 is not set
+# CONFIG_CPU_SUBTYPE_SH7750 is not set
+# CONFIG_CPU_SUBTYPE_SH7091 is not set
+# CONFIG_CPU_SUBTYPE_SH7750R is not set
+# CONFIG_CPU_SUBTYPE_SH7750S is not set
+# CONFIG_CPU_SUBTYPE_SH7751 is not set
+# CONFIG_CPU_SUBTYPE_SH7751R is not set
+# CONFIG_CPU_SUBTYPE_SH7760 is not set
+# CONFIG_CPU_SUBTYPE_SH4_202 is not set
+# CONFIG_CPU_SUBTYPE_SH7723 is not set
+CONFIG_CPU_SUBTYPE_SH7724=y
+# CONFIG_CPU_SUBTYPE_SH7763 is not set
+# CONFIG_CPU_SUBTYPE_SH7770 is not set
+# CONFIG_CPU_SUBTYPE_SH7780 is not set
+# CONFIG_CPU_SUBTYPE_SH7785 is not set
+# CONFIG_CPU_SUBTYPE_SH7786 is not set
+# CONFIG_CPU_SUBTYPE_SHX3 is not set
+# CONFIG_CPU_SUBTYPE_SH7343 is not set
+# CONFIG_CPU_SUBTYPE_SH7722 is not set
+# CONFIG_CPU_SUBTYPE_SH7366 is not set
+
+#
+# Memory management options
+#
+CONFIG_QUICKLIST=y
+CONFIG_MMU=y
+CONFIG_PAGE_OFFSET=0x80000000
+CONFIG_FORCE_MAX_ZONEORDER=11
+CONFIG_MEMORY_START=0x08000000
+CONFIG_MEMORY_SIZE=0x08000000
+CONFIG_29BIT=y
+# CONFIG_X2TLB is not set
+CONFIG_VSYSCALL=y
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_DEFAULT=y
+CONFIG_MAX_ACTIVE_REGIONS=1
+CONFIG_ARCH_POPULATES_NODE_MAP=y
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
+CONFIG_PAGE_SIZE_4KB=y
+# CONFIG_PAGE_SIZE_8KB is not set
+# CONFIG_PAGE_SIZE_16KB is not set
+# CONFIG_PAGE_SIZE_64KB is not set
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_FLATMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+CONFIG_SPARSEMEM_STATIC=y
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4
+# CONFIG_PHYS_ADDR_T_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=0
+CONFIG_NR_QUICK=2
+CONFIG_UNEVICTABLE_LRU=y
+CONFIG_HAVE_MLOCK=y
+CONFIG_HAVE_MLOCKED_PAGE_BIT=y
+
+#
+# Cache configuration
+#
+CONFIG_CACHE_WRITEBACK=y
+# CONFIG_CACHE_WRITETHROUGH is not set
+# CONFIG_CACHE_OFF is not set
+
+#
+# Processor features
+#
+CONFIG_CPU_LITTLE_ENDIAN=y
+# CONFIG_CPU_BIG_ENDIAN is not set
+CONFIG_SH_FPU=y
+# CONFIG_SH_STORE_QUEUES is not set
+CONFIG_CPU_HAS_INTEVT=y
+CONFIG_CPU_HAS_SR_RB=y
+CONFIG_CPU_HAS_PTEA=y
+CONFIG_CPU_HAS_FPU=y
+
+#
+# Board support
+#
+CONFIG_SOLUTION_ENGINE=y
+CONFIG_SH_7724_SOLUTION_ENGINE=y
+
+#
+# Timer and clock configuration
+#
+CONFIG_SH_TIMER_TMU=y
+# CONFIG_SH_TIMER_CMT is not set
+CONFIG_SH_PCLK_FREQ=33333333
+# CONFIG_NO_HZ is not set
+# CONFIG_HIGH_RES_TIMERS is not set
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+
+#
+# CPU Frequency scaling
+#
+# CONFIG_CPU_FREQ is not set
+
+#
+# DMA support
+#
+# CONFIG_SH_DMA is not set
+
+#
+# Companion Chips
+#
+
+#
+# Additional SuperH Device Drivers
+#
+CONFIG_HEARTBEAT=y
+# CONFIG_PUSH_SWITCH is not set
+
+#
+# Kernel features
+#
+# CONFIG_HZ_100 is not set
+CONFIG_HZ_250=y
+# CONFIG_HZ_300 is not set
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=250
+# CONFIG_SCHED_HRTICK is not set
+# CONFIG_KEXEC is not set
+# CONFIG_CRASH_DUMP is not set
+CONFIG_SECCOMP=y
+# CONFIG_PREEMPT_NONE is not set
+# CONFIG_PREEMPT_VOLUNTARY is not set
+CONFIG_PREEMPT=y
+CONFIG_GUSA=y
+
+#
+# Boot options
+#
+CONFIG_ZERO_PAGE_OFFSET=0x00001000
+CONFIG_BOOT_LINK_OFFSET=0x00800000
+CONFIG_ENTRY_OFFSET=0x00001000
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="console=tty1 console=ttySC3,115200 root=/dev/nfs ip=dhcp memchunk.vpu=4m"
+
+#
+# Bus options
+#
+# CONFIG_ARCH_SUPPORTS_MSI is not set
+# CONFIG_PCCARD is not set
+
+#
+# Executable file formats
+#
+CONFIG_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_HAVE_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+
+#
+# Power management options (EXPERIMENTAL)
+#
+# CONFIG_PM is not set
+# CONFIG_CPU_IDLE is not set
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+# CONFIG_PACKET_MMAP is not set
+CONFIG_UNIX=y
+# CONFIG_NET_KEY is not set
+CONFIG_INET=y
+# CONFIG_IP_MULTICAST is not set
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_ASK_IP_FIB_HASH=y
+# CONFIG_IP_FIB_TRIE is not set
+CONFIG_IP_FIB_HASH=y
+# CONFIG_IP_MULTIPLE_TABLES is not set
+# CONFIG_IP_ROUTE_MULTIPATH is not set
+# CONFIG_IP_ROUTE_VERBOSE is not set
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+# CONFIG_IP_PNP_BOOTP is not set
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_ARPD is not set
+# CONFIG_SYN_COOKIES is not set
+# CONFIG_INET_AH is not set
+# CONFIG_INET_ESP is not set
+# CONFIG_INET_IPCOMP is not set
+# CONFIG_INET_XFRM_TUNNEL is not set
+# CONFIG_INET_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+CONFIG_INET_DIAG=y
+CONFIG_INET_TCP_DIAG=y
+# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_TCP_MD5SIG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_NETWORK_SECMARK is not set
+# CONFIG_NETFILTER is not set
+# CONFIG_IP_DCCP is not set
+# CONFIG_IP_SCTP is not set
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
+# CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_DECNET is not set
+# CONFIG_LLC2 is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+# CONFIG_PHONET is not set
+# CONFIG_NET_SCHED is not set
+# CONFIG_DCB is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+CONFIG_WIRELESS=y
+# CONFIG_CFG80211 is not set
+# CONFIG_WIRELESS_OLD_REGULATORY is not set
+# CONFIG_WIRELESS_EXT is not set
+# CONFIG_LIB80211 is not set
+# CONFIG_MAC80211 is not set
+# CONFIG_WIMAX is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_CONNECTOR is not set
+CONFIG_MTD=y
+# CONFIG_MTD_DEBUG is not set
+CONFIG_MTD_CONCAT=y
+CONFIG_MTD_PARTITIONS=y
+# CONFIG_MTD_TESTS is not set
+# CONFIG_MTD_REDBOOT_PARTS is not set
+CONFIG_MTD_CMDLINE_PARTS=y
+# CONFIG_MTD_AR7_PARTS is not set
+
+#
+# User Modules And Translation Layers
+#
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLKDEVS=y
+CONFIG_MTD_BLOCK=y
+# CONFIG_FTL is not set
+# CONFIG_NFTL is not set
+# CONFIG_INFTL is not set
+# CONFIG_RFD_FTL is not set
+# CONFIG_SSFDC is not set
+# CONFIG_MTD_OOPS is not set
+
+#
+# RAM/ROM/Flash chip drivers
+#
+CONFIG_MTD_CFI=y
+# CONFIG_MTD_JEDECPROBE is not set
+CONFIG_MTD_GEN_PROBE=y
+# CONFIG_MTD_CFI_ADV_OPTIONS is not set
+CONFIG_MTD_MAP_BANK_WIDTH_1=y
+CONFIG_MTD_MAP_BANK_WIDTH_2=y
+CONFIG_MTD_MAP_BANK_WIDTH_4=y
+# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
+CONFIG_MTD_CFI_I1=y
+CONFIG_MTD_CFI_I2=y
+# CONFIG_MTD_CFI_I4 is not set
+# CONFIG_MTD_CFI_I8 is not set
+# CONFIG_MTD_CFI_INTELEXT is not set
+CONFIG_MTD_CFI_AMDSTD=y
+# CONFIG_MTD_CFI_STAA is not set
+CONFIG_MTD_CFI_UTIL=y
+# CONFIG_MTD_RAM is not set
+# CONFIG_MTD_ROM is not set
+# CONFIG_MTD_ABSENT is not set
+
+#
+# Mapping drivers for chip access
+#
+# CONFIG_MTD_COMPLEX_MAPPINGS is not set
+CONFIG_MTD_PHYSMAP=y
+# CONFIG_MTD_PHYSMAP_COMPAT is not set
+# CONFIG_MTD_PLATRAM is not set
+
+#
+# Self-contained MTD device drivers
+#
+# CONFIG_MTD_DATAFLASH is not set
+# CONFIG_MTD_M25P80 is not set
+# CONFIG_MTD_SLRAM is not set
+# CONFIG_MTD_PHRAM is not set
+# CONFIG_MTD_MTDRAM is not set
+# CONFIG_MTD_BLOCK2MTD is not set
+
+#
+# Disk-On-Chip Device Drivers
+#
+# CONFIG_MTD_DOC2000 is not set
+# CONFIG_MTD_DOC2001 is not set
+# CONFIG_MTD_DOC2001PLUS is not set
+CONFIG_MTD_NAND=y
+# CONFIG_MTD_NAND_VERIFY_WRITE is not set
+# CONFIG_MTD_NAND_ECC_SMC is not set
+# CONFIG_MTD_NAND_MUSEUM_IDS is not set
+CONFIG_MTD_NAND_IDS=y
+# CONFIG_MTD_NAND_DISKONCHIP is not set
+# CONFIG_MTD_NAND_NANDSIM is not set
+# CONFIG_MTD_NAND_PLATFORM is not set
+# CONFIG_MTD_ALAUDA is not set
+# CONFIG_MTD_ONENAND is not set
+
+#
+# LPDDR flash memory drivers
+#
+# CONFIG_MTD_LPDDR is not set
+
+#
+# UBI - Unsorted block images
+#
+CONFIG_MTD_UBI=y
+CONFIG_MTD_UBI_WL_THRESHOLD=4096
+CONFIG_MTD_UBI_BEB_RESERVE=1
+# CONFIG_MTD_UBI_GLUEBI is not set
+
+#
+# UBI debugging options
+#
+# CONFIG_MTD_UBI_DEBUG is not set
+# CONFIG_PARPORT is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_DEV_COW_COMMON is not set
+# CONFIG_BLK_DEV_LOOP is not set
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_UB is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=4
+CONFIG_BLK_DEV_RAM_SIZE=4096
+# CONFIG_BLK_DEV_XIP is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+# CONFIG_BLK_DEV_HD is not set
+CONFIG_MISC_DEVICES=y
+# CONFIG_ICS932S401 is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+# CONFIG_ISL29003 is not set
+# CONFIG_C2PORT is not set
+
+#
+# EEPROM support
+#
+# CONFIG_EEPROM_AT24 is not set
+# CONFIG_EEPROM_AT25 is not set
+# CONFIG_EEPROM_LEGACY is not set
+# CONFIG_EEPROM_93CX6 is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
+# CONFIG_SCSI_TGT is not set
+# CONFIG_SCSI_NETLINK is not set
+CONFIG_SCSI_PROC_FS=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+CONFIG_BLK_DEV_SD=y
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+# CONFIG_BLK_DEV_SR is not set
+# CONFIG_CHR_DEV_SG is not set
+# CONFIG_CHR_DEV_SCH is not set
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+# CONFIG_SCSI_MULTI_LUN is not set
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+# CONFIG_SCSI_SCAN_ASYNC is not set
+CONFIG_SCSI_WAIT_SCAN=m
+
+#
+# SCSI Transports
+#
+# CONFIG_SCSI_SPI_ATTRS is not set
+# CONFIG_SCSI_FC_ATTRS is not set
+# CONFIG_SCSI_ISCSI_ATTRS is not set
+# CONFIG_SCSI_SAS_LIBSAS is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
+CONFIG_SCSI_LOWLEVEL=y
+# CONFIG_ISCSI_TCP is not set
+# CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
+# CONFIG_SCSI_DEBUG is not set
+# CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
+# CONFIG_ATA is not set
+# CONFIG_MD is not set
+CONFIG_NETDEVICES=y
+CONFIG_COMPAT_NET_DEV_OPS=y
+# CONFIG_DUMMY is not set
+# CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
+# CONFIG_EQUALIZER is not set
+# CONFIG_TUN is not set
+# CONFIG_VETH is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+CONFIG_SMSC_PHY=y
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
+# CONFIG_FIXED_PHY is not set
+CONFIG_MDIO_BITBANG=y
+# CONFIG_MDIO_GPIO is not set
+CONFIG_NET_ETHERNET=y
+CONFIG_MII=y
+# CONFIG_AX88796 is not set
+# CONFIG_STNIC is not set
+CONFIG_SMC91X=y
+# CONFIG_ENC28J60 is not set
+# CONFIG_ETHOC is not set
+# CONFIG_SMC911X is not set
+# CONFIG_SMSC911X is not set
+# CONFIG_DNET is not set
+# CONFIG_IBM_NEW_EMAC_ZMII is not set
+# CONFIG_IBM_NEW_EMAC_RGMII is not set
+# CONFIG_IBM_NEW_EMAC_TAH is not set
+# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
+# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
+# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
+# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
+# CONFIG_B44 is not set
+# CONFIG_NETDEV_1000 is not set
+# CONFIG_NETDEV_10000 is not set
+
+#
+# Wireless LAN
+#
+# CONFIG_WLAN_PRE80211 is not set
+# CONFIG_WLAN_80211 is not set
+
+#
+# Enable WiMAX (Networking options) to see the WiMAX drivers
+#
+
+#
+# USB Network Adapters
+#
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET is not set
+# CONFIG_WAN is not set
+# CONFIG_PPP is not set
+# CONFIG_SLIP is not set
+# CONFIG_NETCONSOLE is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+# CONFIG_ISDN is not set
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
+
+#
+# Userland interfaces
+#
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_JOYDEV is not set
+CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_EVBUG is not set
+
+#
+# Input Device Drivers
+#
+CONFIG_INPUT_KEYBOARD=y
+# CONFIG_KEYBOARD_ATKBD is not set
+# CONFIG_KEYBOARD_SUNKBD is not set
+# CONFIG_KEYBOARD_LKKBD is not set
+# CONFIG_KEYBOARD_XTKBD is not set
+# CONFIG_KEYBOARD_NEWTON is not set
+# CONFIG_KEYBOARD_STOWAWAY is not set
+# CONFIG_KEYBOARD_GPIO is not set
+CONFIG_KEYBOARD_SH_KEYSC=y
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
+# CONFIG_INPUT_TOUCHSCREEN is not set
+# CONFIG_INPUT_MISC is not set
+
+#
+# Hardware I/O ports
+#
+# CONFIG_SERIO is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_DEVKMEM=y
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+# CONFIG_SERIAL_MAX3100 is not set
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_SH_SCI_NR_UARTS=6
+CONFIG_SERIAL_SH_SCI_CONSOLE=y
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+CONFIG_UNIX98_PTYS=y
+# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=256
+# CONFIG_IPMI_HANDLER is not set
+CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_TIMERIOMEM is not set
+# CONFIG_R3964 is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_TCG_TPM is not set
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_HELPER_AUTO=y
+
+#
+# I2C Hardware Bus support
+#
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_GPIO is not set
+# CONFIG_I2C_OCORES is not set
+CONFIG_I2C_SH_MOBILE=y
+# CONFIG_I2C_SIMTEC is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+# CONFIG_I2C_TINY_USB is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_PCA_PLATFORM is not set
+# CONFIG_I2C_STUB is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_DS1682 is not set
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_PCF8575 is not set
+# CONFIG_SENSORS_PCA9539 is not set
+# CONFIG_SENSORS_MAX6875 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
+CONFIG_SPI=y
+CONFIG_SPI_MASTER=y
+
+#
+# SPI Master Controller Drivers
+#
+CONFIG_SPI_BITBANG=y
+# CONFIG_SPI_GPIO is not set
+# CONFIG_SPI_SH_SCI is not set
+
+#
+# SPI Protocol Masters
+#
+# CONFIG_SPI_SPIDEV is not set
+# CONFIG_SPI_TLE62X0 is not set
+CONFIG_ARCH_REQUIRE_GPIOLIB=y
+CONFIG_GPIOLIB=y
+# CONFIG_GPIO_SYSFS is not set
+
+#
+# Memory mapped GPIO expanders:
+#
+
+#
+# I2C GPIO expanders:
+#
+# CONFIG_GPIO_MAX732X is not set
+# CONFIG_GPIO_PCA953X is not set
+# CONFIG_GPIO_PCF857X is not set
+
+#
+# PCI GPIO expanders:
+#
+
+#
+# SPI GPIO expanders:
+#
+# CONFIG_GPIO_MAX7301 is not set
+# CONFIG_GPIO_MCP23S08 is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+# CONFIG_THERMAL is not set
+# CONFIG_THERMAL_HWMON is not set
+# CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
+
+#
+# Multifunction device drivers
+#
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_TPS65010 is not set
+# CONFIG_TWL4030_CORE is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_PMIC_DA903X is not set
+# CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_PCF50633 is not set
+# CONFIG_REGULATOR is not set
+
+#
+# Multimedia devices
+#
+
+#
+# Multimedia core support
+#
+CONFIG_VIDEO_DEV=y
+CONFIG_VIDEO_V4L2_COMMON=y
+# CONFIG_VIDEO_ALLOW_V4L1 is not set
+CONFIG_VIDEO_V4L1_COMPAT=y
+# CONFIG_DVB_CORE is not set
+CONFIG_VIDEO_MEDIA=y
+
+#
+# Multimedia drivers
+#
+# CONFIG_MEDIA_ATTACH is not set
+CONFIG_MEDIA_TUNER=y
+# CONFIG_MEDIA_TUNER_CUSTOMISE is not set
+CONFIG_MEDIA_TUNER_SIMPLE=y
+CONFIG_MEDIA_TUNER_TDA8290=y
+CONFIG_MEDIA_TUNER_TDA9887=y
+CONFIG_MEDIA_TUNER_TEA5761=y
+CONFIG_MEDIA_TUNER_TEA5767=y
+CONFIG_MEDIA_TUNER_MT20XX=y
+CONFIG_MEDIA_TUNER_XC2028=y
+CONFIG_MEDIA_TUNER_XC5000=y
+CONFIG_MEDIA_TUNER_MC44S803=y
+CONFIG_VIDEO_V4L2=y
+CONFIG_VIDEOBUF_GEN=y
+CONFIG_VIDEOBUF_DMA_CONTIG=y
+CONFIG_VIDEO_CAPTURE_DRIVERS=y
+# CONFIG_VIDEO_ADV_DEBUG is not set
+# CONFIG_VIDEO_FIXED_MINOR_RANGES is not set
+CONFIG_VIDEO_HELPER_CHIPS_AUTO=y
+# CONFIG_VIDEO_VIVI is not set
+# CONFIG_VIDEO_SAA5246A is not set
+# CONFIG_VIDEO_SAA5249 is not set
+CONFIG_SOC_CAMERA=y
+# CONFIG_SOC_CAMERA_MT9M001 is not set
+# CONFIG_SOC_CAMERA_MT9M111 is not set
+# CONFIG_SOC_CAMERA_MT9T031 is not set
+# CONFIG_SOC_CAMERA_MT9V022 is not set
+# CONFIG_SOC_CAMERA_TW9910 is not set
+# CONFIG_SOC_CAMERA_PLATFORM is not set
+CONFIG_SOC_CAMERA_OV772X=y
+CONFIG_VIDEO_SH_MOBILE_CEU=y
+CONFIG_V4L_USB_DRIVERS=y
+# CONFIG_USB_VIDEO_CLASS is not set
+CONFIG_USB_VIDEO_CLASS_INPUT_EVDEV=y
+CONFIG_USB_GSPCA=m
+# CONFIG_USB_M5602 is not set
+# CONFIG_USB_STV06XX is not set
+# CONFIG_USB_GSPCA_CONEX is not set
+# CONFIG_USB_GSPCA_ETOMS is not set
+# CONFIG_USB_GSPCA_FINEPIX is not set
+# CONFIG_USB_GSPCA_MARS is not set
+# CONFIG_USB_GSPCA_MR97310A is not set
+# CONFIG_USB_GSPCA_OV519 is not set
+# CONFIG_USB_GSPCA_OV534 is not set
+# CONFIG_USB_GSPCA_PAC207 is not set
+# CONFIG_USB_GSPCA_PAC7311 is not set
+# CONFIG_USB_GSPCA_SONIXB is not set
+# CONFIG_USB_GSPCA_SONIXJ is not set
+# CONFIG_USB_GSPCA_SPCA500 is not set
+# CONFIG_USB_GSPCA_SPCA501 is not set
+# CONFIG_USB_GSPCA_SPCA505 is not set
+# CONFIG_USB_GSPCA_SPCA506 is not set
+# CONFIG_USB_GSPCA_SPCA508 is not set
+# CONFIG_USB_GSPCA_SPCA561 is not set
+# CONFIG_USB_GSPCA_SQ905 is not set
+# CONFIG_USB_GSPCA_SQ905C is not set
+# CONFIG_USB_GSPCA_STK014 is not set
+# CONFIG_USB_GSPCA_SUNPLUS is not set
+# CONFIG_USB_GSPCA_T613 is not set
+# CONFIG_USB_GSPCA_TV8532 is not set
+# CONFIG_USB_GSPCA_VC032X is not set
+# CONFIG_USB_GSPCA_ZC3XX is not set
+# CONFIG_VIDEO_PVRUSB2 is not set
+# CONFIG_VIDEO_HDPVR is not set
+# CONFIG_VIDEO_EM28XX is not set
+# CONFIG_VIDEO_CX231XX is not set
+# CONFIG_VIDEO_USBVISION is not set
+# CONFIG_USB_ET61X251 is not set
+# CONFIG_USB_SN9C102 is not set
+# CONFIG_USB_ZC0301 is not set
+CONFIG_USB_PWC_INPUT_EVDEV=y
+# CONFIG_USB_ZR364XX is not set
+# CONFIG_USB_STKWEBCAM is not set
+# CONFIG_USB_S2255 is not set
+# CONFIG_RADIO_ADAPTERS is not set
+# CONFIG_DAB is not set
+
+#
+# Graphics support
+#
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+CONFIG_FB=y
+# CONFIG_FIRMWARE_EDID is not set
+# CONFIG_FB_DDC is not set
+# CONFIG_FB_BOOT_VESA_SUPPORT is not set
+# CONFIG_FB_CFB_FILLRECT is not set
+# CONFIG_FB_CFB_COPYAREA is not set
+# CONFIG_FB_CFB_IMAGEBLIT is not set
+# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
+CONFIG_FB_SYS_FILLRECT=y
+CONFIG_FB_SYS_COPYAREA=y
+CONFIG_FB_SYS_IMAGEBLIT=y
+# CONFIG_FB_FOREIGN_ENDIAN is not set
+CONFIG_FB_SYS_FOPS=y
+CONFIG_FB_DEFERRED_IO=y
+# CONFIG_FB_SVGALIB is not set
+# CONFIG_FB_MACMODES is not set
+# CONFIG_FB_BACKLIGHT is not set
+# CONFIG_FB_MODE_HELPERS is not set
+# CONFIG_FB_TILEBLITTING is not set
+
+#
+# Frame buffer hardware drivers
+#
+# CONFIG_FB_S1D13XXX is not set
+CONFIG_FB_SH_MOBILE_LCDC=y
+# CONFIG_FB_VIRTUAL is not set
+# CONFIG_FB_METRONOME is not set
+# CONFIG_FB_MB862XX is not set
+# CONFIG_FB_BROADSHEET is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+
+#
+# Console display driver support
+#
+CONFIG_DUMMY_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY is not set
+# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
+# CONFIG_FONTS is not set
+CONFIG_FONT_8x8=y
+CONFIG_FONT_8x16=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+# CONFIG_LOGO_SUPERH_MONO is not set
+# CONFIG_LOGO_SUPERH_VGA16 is not set
+CONFIG_LOGO_SUPERH_CLUT224=y
+# CONFIG_SOUND is not set
+CONFIG_HID_SUPPORT=y
+CONFIG_HID=y
+# CONFIG_HID_DEBUG is not set
+# CONFIG_HIDRAW is not set
+
+#
+# USB Input Devices
+#
+CONFIG_USB_HID=y
+# CONFIG_HID_PID is not set
+# CONFIG_USB_HIDDEV is not set
+
+#
+# Special HID drivers
+#
+# CONFIG_HID_A4TECH is not set
+# CONFIG_HID_APPLE is not set
+# CONFIG_HID_BELKIN is not set
+# CONFIG_HID_CHERRY is not set
+# CONFIG_HID_CHICONY is not set
+# CONFIG_HID_CYPRESS is not set
+# CONFIG_DRAGONRISE_FF is not set
+# CONFIG_HID_EZKEY is not set
+# CONFIG_HID_KYE is not set
+# CONFIG_HID_GYRATION is not set
+# CONFIG_HID_KENSINGTON is not set
+# CONFIG_HID_LOGITECH is not set
+# CONFIG_HID_MICROSOFT is not set
+# CONFIG_HID_MONTEREY is not set
+# CONFIG_HID_NTRIG is not set
+# CONFIG_HID_PANTHERLORD is not set
+# CONFIG_HID_PETALYNX is not set
+# CONFIG_HID_SAMSUNG is not set
+# CONFIG_HID_SONY is not set
+# CONFIG_HID_SUNPLUS is not set
+# CONFIG_GREENASIA_FF is not set
+# CONFIG_HID_TOPSEED is not set
+# CONFIG_THRUSTMASTER_FF is not set
+# CONFIG_ZEROPLUS_FF is not set
+CONFIG_USB_SUPPORT=y
+CONFIG_USB_ARCH_HAS_HCD=y
+# CONFIG_USB_ARCH_HAS_OHCI is not set
+# CONFIG_USB_ARCH_HAS_EHCI is not set
+CONFIG_USB=y
+# CONFIG_USB_DEBUG is not set
+# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set
+
+#
+# Miscellaneous USB options
+#
+# CONFIG_USB_DEVICEFS is not set
+CONFIG_USB_DEVICE_CLASS=y
+# CONFIG_USB_DYNAMIC_MINORS is not set
+# CONFIG_USB_OTG is not set
+# CONFIG_USB_OTG_WHITELIST is not set
+# CONFIG_USB_OTG_BLACKLIST_HUB is not set
+CONFIG_USB_MON=y
+# CONFIG_USB_WUSB is not set
+# CONFIG_USB_WUSB_CBAF is not set
+
+#
+# USB Host Controller Drivers
+#
+# CONFIG_USB_C67X00_HCD is not set
+# CONFIG_USB_OXU210HP_HCD is not set
+# CONFIG_USB_ISP116X_HCD is not set
+# CONFIG_USB_ISP1760_HCD is not set
+# CONFIG_USB_SL811_HCD is not set
+CONFIG_USB_R8A66597_HCD=y
+# CONFIG_USB_HWA_HCD is not set
+
+#
+# USB Device Class drivers
+#
+# CONFIG_USB_ACM is not set
+# CONFIG_USB_PRINTER is not set
+# CONFIG_USB_WDM is not set
+# CONFIG_USB_TMC is not set
+
+#
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
+#
+
+#
+# also be needed; see USB_STORAGE Help for more info
+#
+CONFIG_USB_STORAGE=y
+# CONFIG_USB_STORAGE_DEBUG is not set
+# CONFIG_USB_STORAGE_DATAFAB is not set
+# CONFIG_USB_STORAGE_FREECOM is not set
+# CONFIG_USB_STORAGE_ISD200 is not set
+# CONFIG_USB_STORAGE_USBAT is not set
+# CONFIG_USB_STORAGE_SDDR09 is not set
+# CONFIG_USB_STORAGE_SDDR55 is not set
+# CONFIG_USB_STORAGE_JUMPSHOT is not set
+# CONFIG_USB_STORAGE_ALAUDA is not set
+# CONFIG_USB_STORAGE_ONETOUCH is not set
+# CONFIG_USB_STORAGE_KARMA is not set
+# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set
+# CONFIG_USB_LIBUSUAL is not set
+
+#
+# USB Imaging devices
+#
+# CONFIG_USB_MDC800 is not set
+# CONFIG_USB_MICROTEK is not set
+
+#
+# USB port drivers
+#
+# CONFIG_USB_SERIAL is not set
+
+#
+# USB Miscellaneous drivers
+#
+# CONFIG_USB_EMI62 is not set
+# CONFIG_USB_EMI26 is not set
+# CONFIG_USB_ADUTUX is not set
+# CONFIG_USB_SEVSEG is not set
+# CONFIG_USB_RIO500 is not set
+# CONFIG_USB_LEGOTOWER is not set
+# CONFIG_USB_LCD is not set
+# CONFIG_USB_BERRY_CHARGE is not set
+# CONFIG_USB_LED is not set
+# CONFIG_USB_CYPRESS_CY7C63 is not set
+# CONFIG_USB_CYTHERM is not set
+# CONFIG_USB_IDMOUSE is not set
+# CONFIG_USB_FTDI_ELAN is not set
+# CONFIG_USB_APPLEDISPLAY is not set
+# CONFIG_USB_LD is not set
+# CONFIG_USB_TRANCEVIBRATOR is not set
+# CONFIG_USB_IOWARRIOR is not set
+# CONFIG_USB_ISIGHTFW is not set
+# CONFIG_USB_VST is not set
+# CONFIG_USB_GADGET is not set
+
+#
+# OTG and related infrastructure
+#
+# CONFIG_USB_GPIO_VBUS is not set
+# CONFIG_NOP_USB_XCEIV is not set
+CONFIG_MMC=y
+# CONFIG_MMC_DEBUG is not set
+# CONFIG_MMC_UNSAFE_RESUME is not set
+
+#
+# MMC/SD/SDIO Card Drivers
+#
+CONFIG_MMC_BLOCK=y
+CONFIG_MMC_BLOCK_BOUNCE=y
+# CONFIG_SDIO_UART is not set
+# CONFIG_MMC_TEST is not set
+
+#
+# MMC/SD/SDIO Host Controller Drivers
+#
+# CONFIG_MMC_SDHCI is not set
+CONFIG_MMC_SPI=y
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_ACCESSIBILITY is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
+
+#
+# RTC interfaces
+#
+CONFIG_RTC_INTF_SYSFS=y
+CONFIG_RTC_INTF_PROC=y
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
+
+#
+# I2C RTC drivers
+#
+# CONFIG_RTC_DRV_DS1307 is not set
+# CONFIG_RTC_DRV_DS1374 is not set
+# CONFIG_RTC_DRV_DS1672 is not set
+# CONFIG_RTC_DRV_MAX6900 is not set
+# CONFIG_RTC_DRV_RS5C372 is not set
+# CONFIG_RTC_DRV_ISL1208 is not set
+# CONFIG_RTC_DRV_X1205 is not set
+CONFIG_RTC_DRV_PCF8563=y
+# CONFIG_RTC_DRV_PCF8583 is not set
+# CONFIG_RTC_DRV_M41T80 is not set
+# CONFIG_RTC_DRV_S35390A is not set
+# CONFIG_RTC_DRV_FM3130 is not set
+# CONFIG_RTC_DRV_RX8581 is not set
+
+#
+# SPI RTC drivers
+#
+# CONFIG_RTC_DRV_M41T94 is not set
+# CONFIG_RTC_DRV_DS1305 is not set
+# CONFIG_RTC_DRV_DS1390 is not set
+# CONFIG_RTC_DRV_MAX6902 is not set
+# CONFIG_RTC_DRV_R9701 is not set
+# CONFIG_RTC_DRV_RS5C348 is not set
+# CONFIG_RTC_DRV_DS3234 is not set
+
+#
+# Platform RTC drivers
+#
+# CONFIG_RTC_DRV_DS1286 is not set
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
+# CONFIG_RTC_DRV_V3020 is not set
+
+#
+# on-CPU RTC drivers
+#
+# CONFIG_RTC_DRV_SH is not set
+# CONFIG_RTC_DRV_GENERIC is not set
+# CONFIG_DMADEVICES is not set
+# CONFIG_AUXDISPLAY is not set
+CONFIG_UIO=y
+# CONFIG_UIO_PDRV is not set
+CONFIG_UIO_PDRV_GENIRQ=y
+# CONFIG_UIO_SMX is not set
+# CONFIG_UIO_SERCOS3 is not set
+# CONFIG_STAGING is not set
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_EXT2_FS_POSIX_ACL=y
+CONFIG_EXT2_FS_SECURITY=y
+# CONFIG_EXT2_FS_XIP is not set
+CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT3_FS_XATTR=y
+CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT3_FS_SECURITY=y
+# CONFIG_EXT4_FS is not set
+CONFIG_JBD=y
+CONFIG_FS_MBCACHE=y
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+CONFIG_FS_POSIX_ACL=y
+CONFIG_FILE_LOCKING=y
+# CONFIG_XFS_FS is not set
+# CONFIG_OCFS2_FS is not set
+# CONFIG_BTRFS_FS is not set
+CONFIG_DNOTIFY=y
+CONFIG_INOTIFY=y
+CONFIG_INOTIFY_USER=y
+# CONFIG_QUOTA is not set
+# CONFIG_AUTOFS_FS is not set
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=y
+# CONFIG_MSDOS_FS is not set
+CONFIG_VFAT_FS=y
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
+# CONFIG_HUGETLBFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+# CONFIG_CONFIGFS_FS is not set
+CONFIG_MISC_FILESYSTEMS=y
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+# CONFIG_JFFS2_FS is not set
+# CONFIG_UBIFS_FS is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_SQUASHFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+# CONFIG_NFS_V3_ACL is not set
+# CONFIG_NFS_V4 is not set
+CONFIG_ROOT_NFS=y
+CONFIG_NFSD=y
+CONFIG_NFSD_V3=y
+# CONFIG_NFSD_V3_ACL is not set
+# CONFIG_NFSD_V4 is not set
+CONFIG_LOCKD=y
+CONFIG_LOCKD_V4=y
+CONFIG_EXPORTFS=y
+CONFIG_NFS_COMMON=y
+CONFIG_SUNRPC=y
+# CONFIG_RPCSEC_GSS_KRB5 is not set
+# CONFIG_RPCSEC_GSS_SPKM3 is not set
+# CONFIG_SMB_FS is not set
+# CONFIG_CIFS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="iso8859-1"
+CONFIG_NLS_CODEPAGE_437=y
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+# CONFIG_NLS_CODEPAGE_850 is not set
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+CONFIG_NLS_CODEPAGE_932=y
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+# CONFIG_NLS_ASCII is not set
+CONFIG_NLS_ISO8859_1=y
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_UTF8 is not set
+# CONFIG_DLM is not set
+
+#
+# Kernel hacking
+#
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+# CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_WARN_DEPRECATED=y
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+# CONFIG_DEBUG_FS is not set
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_DEBUG_KERNEL is not set
+# CONFIG_DEBUG_BUGVERBOSE is not set
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_LATENCYTOP is not set
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
+
+#
+# Tracers
+#
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_SH_STANDARD_BIOS is not set
+# CONFIG_EARLY_SCIF_CONSOLE is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+# CONFIG_CRYPTO_FIPS is not set
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_ALGAPI2=y
+CONFIG_CRYPTO_AEAD2=y
+CONFIG_CRYPTO_BLKCIPHER=y
+CONFIG_CRYPTO_BLKCIPHER2=y
+CONFIG_CRYPTO_HASH2=y
+CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP=y
+CONFIG_CRYPTO_MANAGER=y
+CONFIG_CRYPTO_MANAGER2=y
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+CONFIG_CRYPTO_WORKQUEUE=y
+# CONFIG_CRYPTO_CRYPTD is not set
+# CONFIG_CRYPTO_AUTHENC is not set
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+CONFIG_CRYPTO_CBC=y
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+# CONFIG_CRYPTO_ECB is not set
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+# CONFIG_CRYPTO_HMAC is not set
+# CONFIG_CRYPTO_XCBC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_MD4 is not set
+# CONFIG_CRYPTO_MD5 is not set
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+# CONFIG_CRYPTO_SHA1 is not set
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+# CONFIG_CRYPTO_AES is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+# CONFIG_CRYPTO_DES is not set
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+
+#
+# Compression
+#
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
+# CONFIG_CRYPTO_LZO is not set
+
+#
+# Random Number Generation
+#
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
+
+#
+# Library routines
+#
+CONFIG_BITREVERSE=y
+CONFIG_GENERIC_FIND_LAST_BIT=y
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+CONFIG_CRC_T10DIF=y
+CONFIG_CRC_ITU_T=y
+CONFIG_CRC32=y
+CONFIG_CRC7=y
+# CONFIG_LIBCRC32C is not set
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
+CONFIG_NLATTR=y
diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig
index ceef6d9138ee..ed1a1230f636 100644
--- a/arch/sh/configs/se7750_defconfig
+++ b/arch/sh/configs/se7750_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:57:31 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:06:02 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -70,6 +71,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -88,6 +90,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -95,6 +98,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -106,7 +111,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -152,6 +156,7 @@ CONFIG_CPU_SUBTYPE_SH7750=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -161,8 +166,6 @@ CONFIG_CPU_SUBTYPE_SH7750=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -553,6 +556,7 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_DH is not set
 # CONFIG_SCSI_OSD_INITIATOR is not set
@@ -774,6 +778,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -829,6 +838,7 @@ CONFIG_JFFS2_RTIME=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 # CONFIG_NFS_V3 is not set
@@ -886,10 +896,23 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -989,6 +1012,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7751_defconfig b/arch/sh/configs/se7751_defconfig
index 67fc26b3a7d0..55f3b788e0cb 100644
--- a/arch/sh/configs/se7751_defconfig
+++ b/arch/sh/configs/se7751_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 18:59:59 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:06:44 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -65,7 +66,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -74,6 +74,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -92,6 +93,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -99,6 +101,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -110,7 +114,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -156,6 +159,7 @@ CONFIG_CPU_SUBTYPE_SH7751=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -165,8 +169,6 @@ CONFIG_CPU_SUBTYPE_SH7751=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -741,6 +743,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -796,6 +803,7 @@ CONFIG_JFFS2_RTIME=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
@@ -833,10 +841,23 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -936,6 +957,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/se7780_defconfig b/arch/sh/configs/se7780_defconfig
index ebce23cc2ad8..c4f0af32efa9 100644
--- a/arch/sh/configs/se7780_defconfig
+++ b/arch/sh/configs/se7780_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:02:05 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:07:14 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -67,6 +68,7 @@ CONFIG_EMBEDDED=y
 CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 # CONFIG_KALLSYMS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -86,12 +88,15 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -103,7 +108,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
 #
@@ -149,6 +153,7 @@ CONFIG_CPU_SH4A=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 CONFIG_CPU_SUBTYPE_SH7780=y
@@ -158,8 +163,6 @@ CONFIG_CPU_SUBTYPE_SH7780=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -285,8 +288,6 @@ CONFIG_CMDLINE="console=ttySC0.115200 root=/dev/sda1"
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -558,6 +559,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -957,15 +959,17 @@ CONFIG_USB_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=y
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=y
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1121,6 +1125,10 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1245,11 +1253,24 @@ CONFIG_DEBUG_FS=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1345,6 +1366,7 @@ CONFIG_CRYPTO=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig
index 6fcdb090cf32..f9c6e51dc0b0 100644
--- a/arch/sh/configs/sh03_defconfig
+++ b/arch/sh/configs/sh03_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:04:59 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:07:56 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -41,6 +42,7 @@ CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
@@ -67,7 +69,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -76,6 +77,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -105,6 +107,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -117,7 +121,6 @@ CONFIG_MODVERSIONS=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -163,6 +166,7 @@ CONFIG_CPU_SUBTYPE_SH7751=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -172,8 +176,6 @@ CONFIG_CPU_SUBTYPE_SH7751=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -300,8 +302,6 @@ CONFIG_CMDLINE="console=ttySC1,115200 mem=64M root=/dev/nfs"
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -562,6 +562,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -656,6 +657,7 @@ CONFIG_NETDEV_1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -679,6 +681,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -887,7 +890,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
@@ -929,6 +931,7 @@ CONFIG_EXT2_FS_XATTR=y
 # CONFIG_EXT2_FS_SECURITY is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -951,6 +954,11 @@ CONFIG_AUTOFS_FS=y
 CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1001,6 +1009,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1112,11 +1121,26 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_SH_STANDARD_BIOS=y
@@ -1228,6 +1252,7 @@ CONFIG_CRYPTO_DEFLATE=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/sh7710voipgw_defconfig b/arch/sh/configs/sh7710voipgw_defconfig
index 1ab37c01da6e..48b58098cf84 100644
--- a/arch/sh/configs/sh7710voipgw_defconfig
+++ b/arch/sh/configs/sh7710voipgw_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:09:01 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:09:16 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -39,6 +40,7 @@ CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
 # CONFIG_AUDIT is not set
@@ -72,6 +74,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -90,6 +93,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -97,6 +101,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_BASE_SMALL=0
@@ -108,7 +114,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -154,6 +159,7 @@ CONFIG_CPU_SUBTYPE_SH7710=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -163,8 +169,6 @@ CONFIG_CPU_SUBTYPE_SH7710=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -728,7 +732,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 # CONFIG_USB_ARCH_HAS_OHCI is not set
@@ -779,6 +782,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -834,6 +842,7 @@ CONFIG_JFFS2_RTIME=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
@@ -871,11 +880,24 @@ CONFIG_DEBUG_FS=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -975,6 +997,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/sh7724_generic_defconfig b/arch/sh/configs/sh7724_generic_defconfig
new file mode 100644
index 000000000000..ec8f18c7684c
--- /dev/null
+++ b/arch/sh/configs/sh7724_generic_defconfig
@@ -0,0 +1,707 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:09:47 2009
+#
+CONFIG_SUPERH=y
+CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
+CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+CONFIG_GENERIC_BUG=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
+CONFIG_GENERIC_IRQ_PROBE=y
+# CONFIG_GENERIC_GPIO is not set
+CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
+CONFIG_ARCH_HIBERNATION_POSSIBLE=y
+CONFIG_SYS_SUPPORTS_CMT=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_ARCH_NO_VIRT_TO_BUS=y
+CONFIG_ARCH_HAS_DEFAULT_IDLE=y
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# General setup
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_BROKEN_ON_SMP=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_LOCALVERSION=""
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+
+#
+# RCU Subsystem
+#
+# CONFIG_CLASSIC_RCU is not set
+CONFIG_TREE_RCU=y
+# CONFIG_PREEMPT_RCU is not set
+# CONFIG_RCU_TRACE is not set
+CONFIG_RCU_FANOUT=32
+# CONFIG_RCU_FANOUT_EXACT is not set
+# CONFIG_TREE_RCU_TRACE is not set
+# CONFIG_PREEMPT_RCU_TRACE is not set
+# CONFIG_IKCONFIG is not set
+CONFIG_LOG_BUF_SHIFT=17
+CONFIG_GROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_USER_SCHED=y
+# CONFIG_CGROUP_SCHED is not set
+CONFIG_CGROUPS=y
+# CONFIG_CGROUP_DEBUG is not set
+# CONFIG_CGROUP_NS is not set
+# CONFIG_CGROUP_FREEZER is not set
+# CONFIG_CGROUP_DEVICE is not set
+# CONFIG_CPUSETS is not set
+# CONFIG_CGROUP_CPUACCT is not set
+# CONFIG_RESOURCE_COUNTERS is not set
+# CONFIG_RELAY is not set
+# CONFIG_NAMESPACES is not set
+# CONFIG_BLK_DEV_INITRD is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
+CONFIG_EMBEDDED=y
+# CONFIG_UID16 is not set
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
+CONFIG_HOTPLUG=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_SHMEM=y
+CONFIG_AIO=y
+CONFIG_VM_EVENT_COUNTERS=y
+# CONFIG_COMPAT_BRK is not set
+# CONFIG_SLAB is not set
+CONFIG_SLUB=y
+# CONFIG_SLOB is not set
+CONFIG_PROFILING=y
+CONFIG_TRACEPOINTS=y
+# CONFIG_MARKERS is not set
+CONFIG_OPROFILE=y
+CONFIG_HAVE_OPROFILE=y
+CONFIG_HAVE_IOREMAP_PROT=y
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_RT_MUTEXES=y
+CONFIG_BASE_SMALL=0
+# CONFIG_MODULES is not set
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
+CONFIG_FREEZER=y
+
+#
+# System type
+#
+CONFIG_CPU_SH4=y
+CONFIG_CPU_SH4A=y
+CONFIG_CPU_SHX2=y
+CONFIG_ARCH_SHMOBILE=y
+# CONFIG_CPU_SUBTYPE_SH7619 is not set
+# CONFIG_CPU_SUBTYPE_SH7201 is not set
+# CONFIG_CPU_SUBTYPE_SH7203 is not set
+# CONFIG_CPU_SUBTYPE_SH7206 is not set
+# CONFIG_CPU_SUBTYPE_SH7263 is not set
+# CONFIG_CPU_SUBTYPE_MXG is not set
+# CONFIG_CPU_SUBTYPE_SH7705 is not set
+# CONFIG_CPU_SUBTYPE_SH7706 is not set
+# CONFIG_CPU_SUBTYPE_SH7707 is not set
+# CONFIG_CPU_SUBTYPE_SH7708 is not set
+# CONFIG_CPU_SUBTYPE_SH7709 is not set
+# CONFIG_CPU_SUBTYPE_SH7710 is not set
+# CONFIG_CPU_SUBTYPE_SH7712 is not set
+# CONFIG_CPU_SUBTYPE_SH7720 is not set
+# CONFIG_CPU_SUBTYPE_SH7721 is not set
+# CONFIG_CPU_SUBTYPE_SH7750 is not set
+# CONFIG_CPU_SUBTYPE_SH7091 is not set
+# CONFIG_CPU_SUBTYPE_SH7750R is not set
+# CONFIG_CPU_SUBTYPE_SH7750S is not set
+# CONFIG_CPU_SUBTYPE_SH7751 is not set
+# CONFIG_CPU_SUBTYPE_SH7751R is not set
+# CONFIG_CPU_SUBTYPE_SH7760 is not set
+# CONFIG_CPU_SUBTYPE_SH4_202 is not set
+# CONFIG_CPU_SUBTYPE_SH7723 is not set
+CONFIG_CPU_SUBTYPE_SH7724=y
+# CONFIG_CPU_SUBTYPE_SH7763 is not set
+# CONFIG_CPU_SUBTYPE_SH7770 is not set
+# CONFIG_CPU_SUBTYPE_SH7780 is not set
+# CONFIG_CPU_SUBTYPE_SH7785 is not set
+# CONFIG_CPU_SUBTYPE_SH7786 is not set
+# CONFIG_CPU_SUBTYPE_SHX3 is not set
+# CONFIG_CPU_SUBTYPE_SH7343 is not set
+# CONFIG_CPU_SUBTYPE_SH7722 is not set
+# CONFIG_CPU_SUBTYPE_SH7366 is not set
+
+#
+# Memory management options
+#
+CONFIG_QUICKLIST=y
+CONFIG_MMU=y
+CONFIG_PAGE_OFFSET=0x80000000
+CONFIG_MEMORY_START=0x08000000
+CONFIG_MEMORY_SIZE=0x04000000
+CONFIG_29BIT=y
+# CONFIG_X2TLB is not set
+CONFIG_VSYSCALL=y
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_DEFAULT=y
+CONFIG_MAX_ACTIVE_REGIONS=1
+CONFIG_ARCH_POPULATES_NODE_MAP=y
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
+CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
+CONFIG_PAGE_SIZE_4KB=y
+# CONFIG_PAGE_SIZE_8KB is not set
+# CONFIG_PAGE_SIZE_16KB is not set
+# CONFIG_PAGE_SIZE_64KB is not set
+CONFIG_ENTRY_OFFSET=0x00001000
+CONFIG_SELECT_MEMORY_MODEL=y
+# CONFIG_FLATMEM_MANUAL is not set
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+CONFIG_SPARSEMEM_MANUAL=y
+CONFIG_SPARSEMEM=y
+CONFIG_HAVE_MEMORY_PRESENT=y
+CONFIG_SPARSEMEM_STATIC=y
+
+#
+# Memory hotplug is currently incompatible with Software Suspend
+#
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4
+CONFIG_MIGRATION=y
+# CONFIG_PHYS_ADDR_T_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=0
+CONFIG_NR_QUICK=2
+CONFIG_UNEVICTABLE_LRU=y
+CONFIG_HAVE_MLOCK=y
+CONFIG_HAVE_MLOCKED_PAGE_BIT=y
+
+#
+# Cache configuration
+#
+CONFIG_CACHE_WRITEBACK=y
+# CONFIG_CACHE_WRITETHROUGH is not set
+# CONFIG_CACHE_OFF is not set
+
+#
+# Processor features
+#
+CONFIG_CPU_LITTLE_ENDIAN=y
+# CONFIG_CPU_BIG_ENDIAN is not set
+CONFIG_SH_FPU=y
+# CONFIG_SH_STORE_QUEUES is not set
+CONFIG_CPU_HAS_INTEVT=y
+CONFIG_CPU_HAS_SR_RB=y
+CONFIG_CPU_HAS_PTEA=y
+CONFIG_CPU_HAS_FPU=y
+
+#
+# Board support
+#
+
+#
+# Timer and clock configuration
+#
+CONFIG_SH_TMU=y
+CONFIG_SH_TIMER_CMT=y
+CONFIG_SH_TIMER_IRQ=16
+CONFIG_SH_PCLK_FREQ=41666666
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+
+#
+# CPU Frequency scaling
+#
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_TABLE=y
+# CONFIG_CPU_FREQ_DEBUG is not set
+CONFIG_CPU_FREQ_STAT=y
+# CONFIG_CPU_FREQ_STAT_DETAILS is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+# CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
+# CONFIG_CPU_FREQ_GOV_USERSPACE is not set
+# CONFIG_CPU_FREQ_GOV_ONDEMAND is not set
+# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set
+CONFIG_SH_CPU_FREQ=y
+
+#
+# DMA support
+#
+# CONFIG_SH_DMA is not set
+
+#
+# Companion Chips
+#
+
+#
+# Additional SuperH Device Drivers
+#
+# CONFIG_HEARTBEAT is not set
+# CONFIG_PUSH_SWITCH is not set
+
+#
+# Kernel features
+#
+# CONFIG_HZ_100 is not set
+CONFIG_HZ_250=y
+# CONFIG_HZ_300 is not set
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=250
+CONFIG_SCHED_HRTICK=y
+CONFIG_KEXEC=y
+# CONFIG_CRASH_DUMP is not set
+CONFIG_KEXEC_JUMP=y
+CONFIG_PREEMPT_NONE=y
+# CONFIG_PREEMPT_VOLUNTARY is not set
+# CONFIG_PREEMPT is not set
+CONFIG_GUSA=y
+
+#
+# Boot options
+#
+CONFIG_ZERO_PAGE_OFFSET=0x00001000
+CONFIG_BOOT_LINK_OFFSET=0x00800000
+# CONFIG_CMDLINE_BOOL is not set
+
+#
+# Bus options
+#
+# CONFIG_ARCH_SUPPORTS_MSI is not set
+# CONFIG_PCCARD is not set
+
+#
+# Executable file formats
+#
+CONFIG_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_HAVE_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+
+#
+# Power management options (EXPERIMENTAL)
+#
+CONFIG_PM=y
+# CONFIG_PM_DEBUG is not set
+CONFIG_PM_SLEEP=y
+CONFIG_SUSPEND=y
+CONFIG_SUSPEND_FREEZER=y
+CONFIG_HIBERNATION=y
+CONFIG_PM_STD_PARTITION=""
+CONFIG_CPU_IDLE=y
+CONFIG_CPU_IDLE_GOV_LADDER=y
+CONFIG_CPU_IDLE_GOV_MENU=y
+# CONFIG_NET is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_STANDALONE=y
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_MTD is not set
+# CONFIG_PARPORT is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_DEV_COW_COMMON is not set
+# CONFIG_BLK_DEV_LOOP is not set
+# CONFIG_BLK_DEV_RAM is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_BLK_DEV_HD is not set
+# CONFIG_MISC_DEVICES is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+# CONFIG_SCSI is not set
+# CONFIG_SCSI_DMA is not set
+# CONFIG_SCSI_NETLINK is not set
+# CONFIG_ATA is not set
+# CONFIG_MD is not set
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+# CONFIG_INPUT is not set
+
+#
+# Hardware I/O ports
+#
+# CONFIG_SERIO is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+# CONFIG_VT is not set
+# CONFIG_DEVKMEM is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_SH_SCI_NR_UARTS=6
+CONFIG_SERIAL_SH_SCI_CONSOLE=y
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+# CONFIG_UNIX98_PTYS is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_R3964 is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_TCG_TPM is not set
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_HELPER_AUTO=y
+
+#
+# I2C Hardware Bus support
+#
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_OCORES is not set
+CONFIG_I2C_SH_MOBILE=y
+# CONFIG_I2C_SIMTEC is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_PCA_PLATFORM is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_DS1682 is not set
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_PCF8575 is not set
+# CONFIG_SENSORS_PCA9539 is not set
+# CONFIG_SENSORS_MAX6875 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
+# CONFIG_SPI is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+# CONFIG_THERMAL is not set
+# CONFIG_THERMAL_HWMON is not set
+# CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
+
+#
+# Multifunction device drivers
+#
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_TWL4030_CORE is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_PMIC_DA903X is not set
+# CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_PCF50633 is not set
+# CONFIG_REGULATOR is not set
+
+#
+# Multimedia devices
+#
+
+#
+# Multimedia core support
+#
+# CONFIG_VIDEO_DEV is not set
+# CONFIG_VIDEO_MEDIA is not set
+
+#
+# Multimedia drivers
+#
+# CONFIG_DAB is not set
+
+#
+# Graphics support
+#
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_SOUND is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_ACCESSIBILITY is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
+
+#
+# RTC interfaces
+#
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
+
+#
+# I2C RTC drivers
+#
+# CONFIG_RTC_DRV_DS1307 is not set
+# CONFIG_RTC_DRV_DS1374 is not set
+# CONFIG_RTC_DRV_DS1672 is not set
+# CONFIG_RTC_DRV_MAX6900 is not set
+# CONFIG_RTC_DRV_RS5C372 is not set
+# CONFIG_RTC_DRV_ISL1208 is not set
+# CONFIG_RTC_DRV_X1205 is not set
+# CONFIG_RTC_DRV_PCF8563 is not set
+# CONFIG_RTC_DRV_PCF8583 is not set
+# CONFIG_RTC_DRV_M41T80 is not set
+# CONFIG_RTC_DRV_S35390A is not set
+# CONFIG_RTC_DRV_FM3130 is not set
+# CONFIG_RTC_DRV_RX8581 is not set
+
+#
+# SPI RTC drivers
+#
+
+#
+# Platform RTC drivers
+#
+# CONFIG_RTC_DRV_DS1286 is not set
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
+# CONFIG_RTC_DRV_V3020 is not set
+
+#
+# on-CPU RTC drivers
+#
+CONFIG_RTC_DRV_SH=y
+# CONFIG_DMADEVICES is not set
+# CONFIG_AUXDISPLAY is not set
+CONFIG_UIO=y
+# CONFIG_UIO_PDRV is not set
+CONFIG_UIO_PDRV_GENIRQ=y
+# CONFIG_UIO_SMX is not set
+# CONFIG_UIO_SERCOS3 is not set
+# CONFIG_STAGING is not set
+
+#
+# File systems
+#
+# CONFIG_EXT2_FS is not set
+# CONFIG_EXT3_FS is not set
+# CONFIG_EXT4_FS is not set
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+CONFIG_FILE_LOCKING=y
+# CONFIG_XFS_FS is not set
+# CONFIG_BTRFS_FS is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY is not set
+# CONFIG_QUOTA is not set
+# CONFIG_AUTOFS_FS is not set
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+# CONFIG_MSDOS_FS is not set
+# CONFIG_VFAT_FS is not set
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+# CONFIG_PROC_FS is not set
+# CONFIG_SYSFS is not set
+# CONFIG_TMPFS is not set
+# CONFIG_HUGETLBFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_NLS is not set
+
+#
+# Kernel hacking
+#
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+# CONFIG_PRINTK_TIME is not set
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_FS=y
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_DEBUG_KERNEL is not set
+CONFIG_STACKTRACE=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_LATENCYTOP is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+CONFIG_NOP_TRACER=y
+CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_RING_BUFFER=y
+CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
+
+#
+# Tracers
+#
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_FTRACE_STARTUP_TEST is not set
+# CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_SH_STANDARD_BIOS is not set
+# CONFIG_EARLY_SCIF_CONSOLE is not set
+# CONFIG_MORE_COMPILE_OPTIONS is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITYFS is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+# CONFIG_CRYPTO is not set
+CONFIG_BINARY_PRINTF=y
+
+#
+# Library routines
+#
+CONFIG_GENERIC_FIND_LAST_BIT=y
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
+# CONFIG_CRC_ITU_T is not set
+# CONFIG_CRC32 is not set
+# CONFIG_CRC7 is not set
+# CONFIG_LIBCRC32C is not set
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
diff --git a/arch/sh/configs/sh7763rdp_defconfig b/arch/sh/configs/sh7763rdp_defconfig
index c79bb84ec305..f77bc7998d2f 100644
--- a/arch/sh/configs/sh7763rdp_defconfig
+++ b/arch/sh/configs/sh7763rdp_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:10:57 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:10:12 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -78,6 +79,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -106,6 +108,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -117,7 +121,6 @@ CONFIG_MODULES=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -164,6 +167,7 @@ CONFIG_CPU_SH4A=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 CONFIG_CPU_SUBTYPE_SH7763=y
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -173,8 +177,6 @@ CONFIG_CPU_SUBTYPE_SH7763=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -555,6 +557,7 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_DH is not set
 # CONFIG_SCSI_OSD_INITIATOR is not set
@@ -941,6 +944,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -964,6 +968,11 @@ CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
 CONFIG_GENERIC_ACL=y
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1012,6 +1021,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 # CONFIG_NFS_V3 is not set
@@ -1100,11 +1110,25 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1204,6 +1228,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/sh7770_generic_defconfig b/arch/sh/configs/sh7770_generic_defconfig
new file mode 100644
index 000000000000..d6489b46ca5b
--- /dev/null
+++ b/arch/sh/configs/sh7770_generic_defconfig
@@ -0,0 +1,700 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.30-rc4
+# Tue May 12 14:48:21 2009
+#
+CONFIG_SUPERH=y
+CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
+CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+CONFIG_GENERIC_BUG=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
+CONFIG_GENERIC_IRQ_PROBE=y
+# CONFIG_GENERIC_GPIO is not set
+CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+# CONFIG_ARCH_SUSPEND_POSSIBLE is not set
+CONFIG_ARCH_HIBERNATION_POSSIBLE=y
+CONFIG_SYS_SUPPORTS_TMU=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_ARCH_NO_VIRT_TO_BUS=y
+CONFIG_ARCH_HAS_DEFAULT_IDLE=y
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# General setup
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_BROKEN_ON_SMP=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_LOCALVERSION=""
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+# CONFIG_BSD_PROCESS_ACCT is not set
+
+#
+# RCU Subsystem
+#
+# CONFIG_CLASSIC_RCU is not set
+CONFIG_TREE_RCU=y
+# CONFIG_PREEMPT_RCU is not set
+# CONFIG_RCU_TRACE is not set
+CONFIG_RCU_FANOUT=32
+# CONFIG_RCU_FANOUT_EXACT is not set
+# CONFIG_TREE_RCU_TRACE is not set
+# CONFIG_PREEMPT_RCU_TRACE is not set
+# CONFIG_IKCONFIG is not set
+CONFIG_LOG_BUF_SHIFT=17
+CONFIG_GROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_USER_SCHED=y
+# CONFIG_CGROUP_SCHED is not set
+CONFIG_CGROUPS=y
+# CONFIG_CGROUP_DEBUG is not set
+# CONFIG_CGROUP_NS is not set
+# CONFIG_CGROUP_FREEZER is not set
+# CONFIG_CGROUP_DEVICE is not set
+# CONFIG_CPUSETS is not set
+# CONFIG_CGROUP_CPUACCT is not set
+# CONFIG_RESOURCE_COUNTERS is not set
+# CONFIG_RELAY is not set
+# CONFIG_NAMESPACES is not set
+# CONFIG_BLK_DEV_INITRD is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
+CONFIG_EMBEDDED=y
+# CONFIG_UID16 is not set
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
+CONFIG_HOTPLUG=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_SHMEM=y
+CONFIG_AIO=y
+CONFIG_VM_EVENT_COUNTERS=y
+# CONFIG_COMPAT_BRK is not set
+# CONFIG_SLAB is not set
+CONFIG_SLUB=y
+# CONFIG_SLOB is not set
+CONFIG_PROFILING=y
+CONFIG_TRACEPOINTS=y
+# CONFIG_MARKERS is not set
+CONFIG_OPROFILE=y
+CONFIG_HAVE_OPROFILE=y
+CONFIG_HAVE_IOREMAP_PROT=y
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_RT_MUTEXES=y
+CONFIG_BASE_SMALL=0
+# CONFIG_MODULES is not set
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+CONFIG_IOSCHED_CFQ=y
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
+CONFIG_FREEZER=y
+
+#
+# System type
+#
+CONFIG_CPU_SH4=y
+CONFIG_CPU_SH4A=y
+# CONFIG_CPU_SUBTYPE_SH7619 is not set
+# CONFIG_CPU_SUBTYPE_SH7201 is not set
+# CONFIG_CPU_SUBTYPE_SH7203 is not set
+# CONFIG_CPU_SUBTYPE_SH7206 is not set
+# CONFIG_CPU_SUBTYPE_SH7263 is not set
+# CONFIG_CPU_SUBTYPE_MXG is not set
+# CONFIG_CPU_SUBTYPE_SH7705 is not set
+# CONFIG_CPU_SUBTYPE_SH7706 is not set
+# CONFIG_CPU_SUBTYPE_SH7707 is not set
+# CONFIG_CPU_SUBTYPE_SH7708 is not set
+# CONFIG_CPU_SUBTYPE_SH7709 is not set
+# CONFIG_CPU_SUBTYPE_SH7710 is not set
+# CONFIG_CPU_SUBTYPE_SH7712 is not set
+# CONFIG_CPU_SUBTYPE_SH7720 is not set
+# CONFIG_CPU_SUBTYPE_SH7721 is not set
+# CONFIG_CPU_SUBTYPE_SH7750 is not set
+# CONFIG_CPU_SUBTYPE_SH7091 is not set
+# CONFIG_CPU_SUBTYPE_SH7750R is not set
+# CONFIG_CPU_SUBTYPE_SH7750S is not set
+# CONFIG_CPU_SUBTYPE_SH7751 is not set
+# CONFIG_CPU_SUBTYPE_SH7751R is not set
+# CONFIG_CPU_SUBTYPE_SH7760 is not set
+# CONFIG_CPU_SUBTYPE_SH4_202 is not set
+# CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
+# CONFIG_CPU_SUBTYPE_SH7763 is not set
+CONFIG_CPU_SUBTYPE_SH7770=y
+# CONFIG_CPU_SUBTYPE_SH7780 is not set
+# CONFIG_CPU_SUBTYPE_SH7785 is not set
+# CONFIG_CPU_SUBTYPE_SH7786 is not set
+# CONFIG_CPU_SUBTYPE_SHX3 is not set
+# CONFIG_CPU_SUBTYPE_SH7343 is not set
+# CONFIG_CPU_SUBTYPE_SH7722 is not set
+# CONFIG_CPU_SUBTYPE_SH7366 is not set
+
+#
+# Memory management options
+#
+CONFIG_QUICKLIST=y
+CONFIG_MMU=y
+CONFIG_PAGE_OFFSET=0x80000000
+CONFIG_MEMORY_START=0x08000000
+CONFIG_MEMORY_SIZE=0x04000000
+CONFIG_29BIT=y
+CONFIG_VSYSCALL=y
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_DEFAULT=y
+CONFIG_MAX_ACTIVE_REGIONS=1
+CONFIG_ARCH_POPULATES_NODE_MAP=y
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
+CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
+CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
+CONFIG_PAGE_SIZE_4KB=y
+# CONFIG_PAGE_SIZE_8KB is not set
+# CONFIG_PAGE_SIZE_16KB is not set
+# CONFIG_PAGE_SIZE_64KB is not set
+CONFIG_SELECT_MEMORY_MODEL=y
+# CONFIG_FLATMEM_MANUAL is not set
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+CONFIG_SPARSEMEM_MANUAL=y
+CONFIG_SPARSEMEM=y
+CONFIG_HAVE_MEMORY_PRESENT=y
+CONFIG_SPARSEMEM_STATIC=y
+
+#
+# Memory hotplug is currently incompatible with Software Suspend
+#
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4
+CONFIG_MIGRATION=y
+# CONFIG_PHYS_ADDR_T_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=0
+CONFIG_NR_QUICK=2
+CONFIG_UNEVICTABLE_LRU=y
+CONFIG_HAVE_MLOCK=y
+CONFIG_HAVE_MLOCKED_PAGE_BIT=y
+
+#
+# Cache configuration
+#
+CONFIG_CACHE_WRITEBACK=y
+# CONFIG_CACHE_WRITETHROUGH is not set
+# CONFIG_CACHE_OFF is not set
+
+#
+# Processor features
+#
+CONFIG_CPU_LITTLE_ENDIAN=y
+# CONFIG_CPU_BIG_ENDIAN is not set
+CONFIG_SH_FPU=y
+# CONFIG_SH_STORE_QUEUES is not set
+CONFIG_CPU_HAS_INTEVT=y
+CONFIG_CPU_HAS_SR_RB=y
+CONFIG_CPU_HAS_FPU=y
+
+#
+# Board support
+#
+
+#
+# Timer and clock configuration
+#
+CONFIG_SH_TMU=y
+CONFIG_SH_TIMER_IRQ=16
+CONFIG_SH_PCLK_FREQ=41666666
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+
+#
+# CPU Frequency scaling
+#
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_TABLE=y
+# CONFIG_CPU_FREQ_DEBUG is not set
+CONFIG_CPU_FREQ_STAT=y
+# CONFIG_CPU_FREQ_STAT_DETAILS is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
+# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+# CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
+# CONFIG_CPU_FREQ_GOV_USERSPACE is not set
+# CONFIG_CPU_FREQ_GOV_ONDEMAND is not set
+# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set
+CONFIG_SH_CPU_FREQ=y
+
+#
+# DMA support
+#
+# CONFIG_SH_DMA is not set
+
+#
+# Companion Chips
+#
+
+#
+# Additional SuperH Device Drivers
+#
+# CONFIG_HEARTBEAT is not set
+# CONFIG_PUSH_SWITCH is not set
+
+#
+# Kernel features
+#
+# CONFIG_HZ_100 is not set
+CONFIG_HZ_250=y
+# CONFIG_HZ_300 is not set
+# CONFIG_HZ_1000 is not set
+CONFIG_HZ=250
+CONFIG_SCHED_HRTICK=y
+CONFIG_KEXEC=y
+# CONFIG_CRASH_DUMP is not set
+CONFIG_KEXEC_JUMP=y
+CONFIG_PREEMPT_NONE=y
+# CONFIG_PREEMPT_VOLUNTARY is not set
+# CONFIG_PREEMPT is not set
+CONFIG_GUSA=y
+
+#
+# Boot options
+#
+CONFIG_ZERO_PAGE_OFFSET=0x00001000
+CONFIG_BOOT_LINK_OFFSET=0x00800000
+CONFIG_ENTRY_OFFSET=0x00001000
+# CONFIG_CMDLINE_BOOL is not set
+
+#
+# Bus options
+#
+# CONFIG_ARCH_SUPPORTS_MSI is not set
+# CONFIG_PCCARD is not set
+
+#
+# Executable file formats
+#
+CONFIG_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_HAVE_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+
+#
+# Power management options (EXPERIMENTAL)
+#
+CONFIG_PM=y
+# CONFIG_PM_DEBUG is not set
+CONFIG_PM_SLEEP=y
+CONFIG_HIBERNATION=y
+CONFIG_PM_STD_PARTITION=""
+CONFIG_CPU_IDLE=y
+CONFIG_CPU_IDLE_GOV_LADDER=y
+CONFIG_CPU_IDLE_GOV_MENU=y
+# CONFIG_NET is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_STANDALONE=y
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_MTD is not set
+# CONFIG_PARPORT is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_DEV_COW_COMMON is not set
+# CONFIG_BLK_DEV_LOOP is not set
+# CONFIG_BLK_DEV_RAM is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_BLK_DEV_HD is not set
+# CONFIG_MISC_DEVICES is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+# CONFIG_SCSI is not set
+# CONFIG_SCSI_DMA is not set
+# CONFIG_SCSI_NETLINK is not set
+# CONFIG_ATA is not set
+# CONFIG_MD is not set
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+# CONFIG_INPUT is not set
+
+#
+# Hardware I/O ports
+#
+# CONFIG_SERIO is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+# CONFIG_VT is not set
+# CONFIG_DEVKMEM is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_SH_SCI_NR_UARTS=6
+CONFIG_SERIAL_SH_SCI_CONSOLE=y
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+# CONFIG_UNIX98_PTYS is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_R3964 is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_TCG_TPM is not set
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_HELPER_AUTO=y
+
+#
+# I2C Hardware Bus support
+#
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_OCORES is not set
+CONFIG_I2C_SH_MOBILE=y
+# CONFIG_I2C_SIMTEC is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_PCA_PLATFORM is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_DS1682 is not set
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_PCF8575 is not set
+# CONFIG_SENSORS_PCA9539 is not set
+# CONFIG_SENSORS_MAX6875 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
+# CONFIG_SPI is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+# CONFIG_THERMAL is not set
+# CONFIG_THERMAL_HWMON is not set
+# CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
+
+#
+# Multifunction device drivers
+#
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_TWL4030_CORE is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_PMIC_DA903X is not set
+# CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_PCF50633 is not set
+# CONFIG_REGULATOR is not set
+
+#
+# Multimedia devices
+#
+
+#
+# Multimedia core support
+#
+# CONFIG_VIDEO_DEV is not set
+# CONFIG_VIDEO_MEDIA is not set
+
+#
+# Multimedia drivers
+#
+# CONFIG_DAB is not set
+
+#
+# Graphics support
+#
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_SOUND is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_ACCESSIBILITY is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
+
+#
+# RTC interfaces
+#
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
+
+#
+# I2C RTC drivers
+#
+# CONFIG_RTC_DRV_DS1307 is not set
+# CONFIG_RTC_DRV_DS1374 is not set
+# CONFIG_RTC_DRV_DS1672 is not set
+# CONFIG_RTC_DRV_MAX6900 is not set
+# CONFIG_RTC_DRV_RS5C372 is not set
+# CONFIG_RTC_DRV_ISL1208 is not set
+# CONFIG_RTC_DRV_X1205 is not set
+# CONFIG_RTC_DRV_PCF8563 is not set
+# CONFIG_RTC_DRV_PCF8583 is not set
+# CONFIG_RTC_DRV_M41T80 is not set
+# CONFIG_RTC_DRV_S35390A is not set
+# CONFIG_RTC_DRV_FM3130 is not set
+# CONFIG_RTC_DRV_RX8581 is not set
+
+#
+# SPI RTC drivers
+#
+
+#
+# Platform RTC drivers
+#
+# CONFIG_RTC_DRV_DS1286 is not set
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
+# CONFIG_RTC_DRV_V3020 is not set
+
+#
+# on-CPU RTC drivers
+#
+CONFIG_RTC_DRV_SH=y
+# CONFIG_RTC_DRV_GENERIC is not set
+# CONFIG_DMADEVICES is not set
+# CONFIG_AUXDISPLAY is not set
+CONFIG_UIO=y
+# CONFIG_UIO_PDRV is not set
+CONFIG_UIO_PDRV_GENIRQ=y
+# CONFIG_UIO_SMX is not set
+# CONFIG_UIO_SERCOS3 is not set
+# CONFIG_STAGING is not set
+
+#
+# File systems
+#
+# CONFIG_EXT2_FS is not set
+# CONFIG_EXT3_FS is not set
+# CONFIG_EXT4_FS is not set
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+CONFIG_FILE_LOCKING=y
+# CONFIG_XFS_FS is not set
+# CONFIG_BTRFS_FS is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY is not set
+# CONFIG_QUOTA is not set
+# CONFIG_AUTOFS_FS is not set
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+# CONFIG_MSDOS_FS is not set
+# CONFIG_VFAT_FS is not set
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+# CONFIG_PROC_FS is not set
+# CONFIG_SYSFS is not set
+# CONFIG_TMPFS is not set
+# CONFIG_HUGETLBFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_NLS is not set
+
+#
+# Kernel hacking
+#
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+# CONFIG_PRINTK_TIME is not set
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_FS=y
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_DEBUG_KERNEL is not set
+CONFIG_STACKTRACE=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_LATENCYTOP is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+CONFIG_NOP_TRACER=y
+CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_RING_BUFFER=y
+CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
+
+#
+# Tracers
+#
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_FTRACE_STARTUP_TEST is not set
+# CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_SH_STANDARD_BIOS is not set
+# CONFIG_EARLY_SCIF_CONSOLE is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITYFS is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+# CONFIG_CRYPTO is not set
+CONFIG_BINARY_PRINTF=y
+
+#
+# Library routines
+#
+CONFIG_GENERIC_FIND_LAST_BIT=y
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
+# CONFIG_CRC_ITU_T is not set
+# CONFIG_CRC32 is not set
+# CONFIG_CRC7 is not set
+# CONFIG_LIBCRC32C is not set
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig
index a6cf4505741c..1c55b800d124 100644
--- a/arch/sh/configs/sh7785lcr_32bit_defconfig
+++ b/arch/sh/configs/sh7785lcr_32bit_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:12:18 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:10:53 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -79,6 +80,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -98,6 +100,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 CONFIG_PROFILING=y
+# CONFIG_MARKERS is not set
 # CONFIG_OPROFILE is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
@@ -106,6 +109,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -118,7 +123,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -166,6 +170,7 @@ CONFIG_CPU_SHX2=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -175,8 +180,6 @@ CONFIG_CPU_SUBTYPE_SH7785=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -310,8 +313,6 @@ CONFIG_BOOT_LINK_OFFSET=0x00800000
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -672,6 +673,7 @@ CONFIG_NETDEV_1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -1009,15 +1011,17 @@ CONFIG_USB_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=y
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=y
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1218,6 +1222,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1239,6 +1244,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1289,6 +1299,7 @@ CONFIG_MINIX_FS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1377,6 +1388,9 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -1413,6 +1427,7 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1422,9 +1437,14 @@ CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 # CONFIG_PREEMPT_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1542,6 +1562,7 @@ CONFIG_CRYPTO_DES=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/sh7785lcr_defconfig b/arch/sh/configs/sh7785lcr_defconfig
index e4fac2efc055..4385fe97a780 100644
--- a/arch/sh/configs/sh7785lcr_defconfig
+++ b/arch/sh/configs/sh7785lcr_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.30-rc2
-# Wed Apr 22 19:17:56 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:11:48 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
@@ -307,8 +307,6 @@ CONFIG_BOOT_LINK_OFFSET=0x00800000
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
diff --git a/arch/sh/configs/shmin_defconfig b/arch/sh/configs/shmin_defconfig
index d695e9061874..4e120256ec63 100644
--- a/arch/sh/configs/shmin_defconfig
+++ b/arch/sh/configs/shmin_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:19:03 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:12:41 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
@@ -63,6 +64,7 @@ CONFIG_EMBEDDED=y
 # CONFIG_UID16 is not set
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_PRINTK=y
 # CONFIG_BUG is not set
@@ -81,12 +83,15 @@ CONFIG_COMPAT_BRK=y
 # CONFIG_SLUB is not set
 CONFIG_SLOB=y
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_BASE_SMALL=1
 # CONFIG_MODULES is not set
@@ -137,6 +142,7 @@ CONFIG_CPU_SUBTYPE_SH7706=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -146,8 +152,6 @@ CONFIG_CPU_SUBTYPE_SH7706=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -674,6 +678,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -718,6 +727,7 @@ CONFIG_CRAMFS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -762,10 +772,22 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_SH_STANDARD_BIOS=y
@@ -864,6 +886,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/shx3_defconfig b/arch/sh/configs/shx3_defconfig
index e3651f574399..c088144925fa 100644
--- a/arch/sh/configs/shx3_defconfig
+++ b/arch/sh/configs/shx3_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:20:54 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:13:12 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -42,6 +43,7 @@ CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
@@ -96,6 +98,7 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -126,6 +129,8 @@ CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_USE_GENERIC_SMP_HELPERS=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_RT_MUTEXES=y
 CONFIG_BASE_SMALL=0
@@ -138,7 +143,6 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -186,6 +190,7 @@ CONFIG_CPU_SHX3=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -195,8 +200,6 @@ CONFIG_CPU_SUBTYPE_SHX3=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -553,6 +556,7 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_DH is not set
 # CONFIG_SCSI_OSD_INITIATOR is not set
@@ -646,6 +650,7 @@ CONFIG_DEVKMEM=y
 #
 # Non-8250 serial port support
 #
+# CONFIG_SERIAL_MAX3100 is not set
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=2
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
@@ -985,6 +990,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1007,6 +1013,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1051,6 +1062,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
@@ -1085,6 +1097,9 @@ CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -1124,6 +1139,7 @@ CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1133,11 +1149,16 @@ CONFIG_TRACING=y
 # CONFIG_PREEMPT_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_FTRACE_STARTUP_TEST is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1245,6 +1266,7 @@ CONFIG_CRYPTO=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
diff --git a/arch/sh/configs/snapgear_defconfig b/arch/sh/configs/snapgear_defconfig
index 6960f60bf52e..54a7a3c41f34 100644
--- a/arch/sh/configs/snapgear_defconfig
+++ b/arch/sh/configs/snapgear_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:21:39 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:14:00 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -64,7 +65,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -73,6 +73,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -92,12 +93,15 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -105,7 +109,6 @@ CONFIG_BASE_SMALL=0
 # CONFIG_MODULES is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -151,6 +154,7 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -160,8 +164,6 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -295,8 +297,6 @@ CONFIG_BOOT_LINK_OFFSET=0x00800000
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -762,6 +762,11 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -805,8 +810,13 @@ CONFIG_CRAMFS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 # CONFIG_NFS_FS is not set
 # CONFIG_NFSD is not set
@@ -844,10 +854,23 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -862,6 +885,7 @@ CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SECURITYFS is not set
 # CONFIG_SECURITY_FILE_CAPABILITIES is not set
 # CONFIG_CRYPTO is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/systemh_defconfig b/arch/sh/configs/systemh_defconfig
index 7ea639bc5936..dbe7e546f0bb 100644
--- a/arch/sh/configs/systemh_defconfig
+++ b/arch/sh/configs/systemh_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:23:31 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:14:33 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -61,7 +62,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -70,6 +70,7 @@ CONFIG_UID16=y
 # CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_HOTPLUG is not set
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -88,6 +89,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -95,6 +97,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -107,7 +111,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -153,6 +156,7 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -162,8 +166,6 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -505,6 +507,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -547,8 +554,13 @@ CONFIG_CRAMFS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 
 #
 # Partition Types
@@ -577,10 +589,24 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -595,6 +621,7 @@ CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SECURITYFS is not set
 # CONFIG_SECURITY_FILE_CAPABILITIES is not set
 # CONFIG_CRYPTO is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index bbeb4c6ebb95..8ca94ef74278 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:24:55 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:14:55 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -40,6 +41,7 @@ CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
 # CONFIG_AUDIT is not set
@@ -66,7 +68,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -76,6 +77,7 @@ CONFIG_UID16=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -95,6 +97,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
 CONFIG_HAVE_IOREMAP_PROT=y
@@ -102,6 +105,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -114,7 +119,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -160,6 +164,7 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -169,8 +174,6 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -305,8 +308,6 @@ CONFIG_CMDLINE="console=ttySC1,38400N81 root=/dev/nfs ip=:::::eth1:autoconf rw"
 #
 CONFIG_PCI=y
 CONFIG_SH_PCIDMA_NONCOHERENT=y
-CONFIG_PCI_AUTO=y
-CONFIG_PCI_AUTO_UPDATE_RESOURCES=y
 # CONFIG_PCIEPORTBUS is not set
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 CONFIG_PCI_LEGACY=y
@@ -789,6 +790,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -906,6 +908,7 @@ CONFIG_NETDEV_1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -929,6 +932,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -1182,7 +1186,6 @@ CONFIG_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
@@ -1393,6 +1396,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_EXT3_FS_XATTR is not set
 # CONFIG_EXT4_FS is not set
 CONFIG_JBD=y
@@ -1418,6 +1422,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 CONFIG_FUSE_FS=m
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1467,8 +1476,13 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 CONFIG_ROMFS_FS=y
+CONFIG_ROMFS_BACKED_BY_BLOCK=y
+# CONFIG_ROMFS_BACKED_BY_MTD is not set
+# CONFIG_ROMFS_BACKED_BY_BOTH is not set
+CONFIG_ROMFS_ON_BLOCK=y
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1576,6 +1590,7 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 # CONFIG_DETECT_SOFTLOCKUP is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 CONFIG_SCHED_DEBUG=y
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
@@ -1610,6 +1625,7 @@ CONFIG_SCHED_DEBUG=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -1618,9 +1634,14 @@ CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 # CONFIG_IRQSOFF_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -1741,6 +1762,7 @@ CONFIG_CRYPTO_DEFLATE=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/ul2_defconfig b/arch/sh/configs/ul2_defconfig
index 34f5192a3241..bfb4d9806892 100644
--- a/arch/sh/configs/ul2_defconfig
+++ b/arch/sh/configs/ul2_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:30:27 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 13:17:05 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -69,7 +70,6 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 # CONFIG_RD_BZIP2 is not set
 # CONFIG_RD_LZMA is not set
-CONFIG_INITRAMFS_COMPRESSION_NONE=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -78,6 +78,7 @@ CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -97,6 +98,7 @@ CONFIG_COMPAT_BRK=y
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 CONFIG_PROFILING=y
+# CONFIG_MARKERS is not set
 # CONFIG_OPROFILE is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
@@ -105,6 +107,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -117,7 +121,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -167,6 +170,7 @@ CONFIG_ARCH_SHMOBILE=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -176,8 +180,6 @@ CONFIG_ARCH_SHMOBILE=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 CONFIG_CPU_SUBTYPE_SH7366=y
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -584,6 +586,7 @@ CONFIG_SCSI_WAIT_SCAN=m
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_DH is not set
 # CONFIG_SCSI_OSD_INITIATOR is not set
@@ -936,6 +939,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -957,6 +961,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1005,6 +1014,7 @@ CONFIG_CRAMFS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 # CONFIG_NFS_V3 is not set
@@ -1095,10 +1105,24 @@ CONFIG_FRAME_WARN=1024
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1208,6 +1232,7 @@ CONFIG_CRYPTO_ARC4=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/configs/urquell_defconfig b/arch/sh/configs/urquell_defconfig
index d174b1a4d802..512664fed66c 100644
--- a/arch/sh/configs/urquell_defconfig
+++ b/arch/sh/configs/urquell_defconfig
@@ -1,10 +1,11 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29
-# Thu Apr  2 19:33:39 2009
+# Linux kernel version: 2.6.30-rc3
+# Mon Apr 27 14:02:55 2009
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
+# CONFIG_SUPERH64 is not set
 CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 CONFIG_GENERIC_BUG=y
@@ -76,6 +77,7 @@ CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -94,6 +96,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 CONFIG_PROFILING=y
+# CONFIG_MARKERS is not set
 # CONFIG_OPROFILE is not set
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
@@ -102,6 +105,8 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_HAVE_CLK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -114,7 +119,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -162,6 +166,7 @@ CONFIG_CPU_SHX3=y
 # CONFIG_CPU_SUBTYPE_SH7760 is not set
 # CONFIG_CPU_SUBTYPE_SH4_202 is not set
 # CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7724 is not set
 # CONFIG_CPU_SUBTYPE_SH7763 is not set
 # CONFIG_CPU_SUBTYPE_SH7770 is not set
 # CONFIG_CPU_SUBTYPE_SH7780 is not set
@@ -171,8 +176,6 @@ CONFIG_CPU_SUBTYPE_SH7786=y
 # CONFIG_CPU_SUBTYPE_SH7343 is not set
 # CONFIG_CPU_SUBTYPE_SH7722 is not set
 # CONFIG_CPU_SUBTYPE_SH7366 is not set
-# CONFIG_CPU_SUBTYPE_SH5_101 is not set
-# CONFIG_CPU_SUBTYPE_SH5_103 is not set
 
 #
 # Memory management options
@@ -900,15 +903,17 @@ CONFIG_USB_HID=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+# CONFIG_HID_KYE is not set
 CONFIG_HID_GYRATION=y
+# CONFIG_HID_KENSINGTON is not set
 CONFIG_HID_LOGITECH=y
 # CONFIG_LOGITECH_FF is not set
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1046,6 +1051,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
@@ -1067,6 +1073,11 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1117,6 +1128,7 @@ CONFIG_MINIX_FS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -1209,10 +1221,24 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
 #
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_SH_STANDARD_BIOS is not set
@@ -1322,6 +1348,7 @@ CONFIG_CRYPTO_DES=y
 #
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
+# CONFIG_BINARY_PRINTF is not set
 
 #
 # Library routines
diff --git a/arch/sh/drivers/dma/Kconfig b/arch/sh/drivers/dma/Kconfig
index 666713ac5fcf..63e9dd30b41c 100644
--- a/arch/sh/drivers/dma/Kconfig
+++ b/arch/sh/drivers/dma/Kconfig
@@ -16,7 +16,8 @@ config SH_DMA_IRQ_MULTI
 		     CPU_SUBTYPE_SH7750S || CPU_SUBTYPE_SH7750R || \
 		     CPU_SUBTYPE_SH7751R || CPU_SUBTYPE_SH7091  || \
 		     CPU_SUBTYPE_SH7763  || CPU_SUBTYPE_SH7764  || \
-		     CPU_SUBTYPE_SH7780  || CPU_SUBTYPE_SH7785
+		     CPU_SUBTYPE_SH7780  || CPU_SUBTYPE_SH7785  || \
+		     CPU_SUBTYPE_SH7760
 
 config NR_ONCHIP_DMA_CHANNELS
 	int
diff --git a/arch/sh/drivers/pci/Kconfig b/arch/sh/drivers/pci/Kconfig
index 7e816ededed7..e8db585a6638 100644
--- a/arch/sh/drivers/pci/Kconfig
+++ b/arch/sh/drivers/pci/Kconfig
@@ -17,21 +17,3 @@ config SH_PCIDMA_NONCOHERENT
 	  code will not have to flush the CPU's caches. If you have a PCI host
 	  bridge integrated with your SH CPU, refer carefully to the chip specs
 	  to see if you can say 'N' here. Otherwise, leave it as 'Y'.
-
-# This is also board-specific
-config PCI_AUTO
-	bool
-	depends on PCI
-	default y
-
-config PCI_AUTO_UPDATE_RESOURCES
-	bool
-	depends on PCI_AUTO
-	default y if !SH_DREAMCAST
-	help
-	  Selecting this option will cause the PCI auto code to leave your
-	  BAR values alone. Otherwise they will be updated automatically. If
-	  for some reason, you have a board that simply refuses to work
-	  with its resources updated beyond what they are when the device
-	  is powered up, set this to N. Everyone else will want this as Y.
-
diff --git a/arch/sh/drivers/pci/Makefile b/arch/sh/drivers/pci/Makefile
index 847e90894d1b..d2ffc477549a 100644
--- a/arch/sh/drivers/pci/Makefile
+++ b/arch/sh/drivers/pci/Makefile
@@ -1,9 +1,7 @@
 #
 # Makefile for the PCI specific kernel interface routines under Linux.
 #
-
 obj-y					+= pci.o
-obj-$(CONFIG_PCI_AUTO)			+= pci-auto.o
 
 obj-$(CONFIG_CPU_SUBTYPE_SH7751)	+= pci-sh7751.o ops-sh4.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7751R)	+= pci-sh7751.o ops-sh4.o
@@ -12,15 +10,17 @@ obj-$(CONFIG_CPU_SUBTYPE_SH7780)	+= pci-sh7780.o ops-sh4.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7785)	+= pci-sh7780.o ops-sh4.o
 obj-$(CONFIG_CPU_SH5)			+= pci-sh5.o ops-sh5.o
 
-obj-$(CONFIG_SH_DREAMCAST)		+= ops-dreamcast.o fixups-dreamcast.o
-obj-$(CONFIG_SH_SECUREEDGE5410)		+= ops-snapgear.o
-obj-$(CONFIG_SH_RTS7751R2D)		+= ops-rts7751r2d.o fixups-rts7751r2d.o
-obj-$(CONFIG_SH_SH03)			+= ops-sh03.o fixups-sh03.o
-obj-$(CONFIG_SH_HIGHLANDER)		+= ops-r7780rp.o fixups-r7780rp.o
-obj-$(CONFIG_SH_SDK7780)		+= ops-sdk7780.o fixups-sdk7780.o
-obj-$(CONFIG_SH_TITAN)			+= ops-titan.o
-obj-$(CONFIG_SH_LANDISK)		+= ops-landisk.o
-obj-$(CONFIG_SH_LBOX_RE2)		+= ops-lboxre2.o fixups-lboxre2.o
-obj-$(CONFIG_SH_7780_SOLUTION_ENGINE)	+= ops-se7780.o fixups-se7780.o
-obj-$(CONFIG_SH_CAYMAN)			+= ops-cayman.o
-obj-$(CONFIG_SH_SH7785LCR)		+= ops-sh7785lcr.o fixups-sh7785lcr.o
+obj-$(CONFIG_SH_DREAMCAST)		+= ops-dreamcast.o fixups-dreamcast.o \
+					   pci-dreamcast.o
+obj-$(CONFIG_SH_SECUREEDGE5410)		+= fixups-snapgear.o
+obj-$(CONFIG_SH_7751_SOLUTION_ENGINE)	+= fixups-se7751.o
+obj-$(CONFIG_SH_RTS7751R2D)		+= fixups-rts7751r2d.o
+obj-$(CONFIG_SH_SH03)			+= fixups-sh03.o
+obj-$(CONFIG_SH_HIGHLANDER)		+= fixups-r7780rp.o
+obj-$(CONFIG_SH_SH7785LCR)		+= fixups-r7780rp.o
+obj-$(CONFIG_SH_SDK7780)		+= fixups-sdk7780.o
+obj-$(CONFIG_SH_7780_SOLUTION_ENGINE)	+= fixups-sdk7780.o
+obj-$(CONFIG_SH_TITAN)			+= fixups-titan.o
+obj-$(CONFIG_SH_LANDISK)		+= fixups-landisk.o
+obj-$(CONFIG_SH_LBOX_RE2)		+= fixups-rts7751r2d.o
+obj-$(CONFIG_SH_CAYMAN)			+= fixups-cayman.o
diff --git a/arch/sh/drivers/pci/ops-cayman.c b/arch/sh/drivers/pci/fixups-cayman.c
similarity index 88%
rename from arch/sh/drivers/pci/ops-cayman.c
rename to arch/sh/drivers/pci/fixups-cayman.c
index 38ef76207af6..b68b61d22c6c 100644
--- a/arch/sh/drivers/pci/ops-cayman.c
+++ b/arch/sh/drivers/pci/fixups-cayman.c
@@ -75,15 +75,3 @@ int __init pcibios_map_platform_irq(struct pci_dev *dev, u8 slot, u8 pin)
 
 	return result;
 }
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh5_pci_ops, NULL, NULL, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-EXPORT_SYMBOL(board_pci_channels);
-
-int __init pcibios_init_platform(void)
-{
-	return sh5pci_init(__pa(memory_start),
-			   __pa(memory_end) - __pa(memory_start));
-}
diff --git a/arch/sh/drivers/pci/fixups-dreamcast.c b/arch/sh/drivers/pci/fixups-dreamcast.c
index 2bf85cf091e1..ed7f489936f1 100644
--- a/arch/sh/drivers/pci/fixups-dreamcast.c
+++ b/arch/sh/drivers/pci/fixups-dreamcast.c
@@ -30,7 +30,7 @@
 
 static void __init gapspci_fixup_resources(struct pci_dev *dev)
 {
-	struct pci_channel *p = board_pci_channels;
+	struct pci_channel *p = dev->sysdata;
 
 	printk(KERN_NOTICE "PCI: Fixing up device %s\n", pci_name(dev));
 
@@ -41,6 +41,13 @@ static void __init gapspci_fixup_resources(struct pci_dev *dev)
 		 */
 		dev->resource[1].start	= p->io_resource->start  + 0x100;
 		dev->resource[1].end	= dev->resource[1].start + 0x200 - 1;
+
+		/*
+		 * This is not a normal BAR, prevent any attempts to move
+		 * the BAR, as this will result in a bus lock.
+		 */
+		dev->resource[1].flags |= IORESOURCE_PCI_FIXED;
+
 		/*
 		 * Redirect dma memory allocations to special memory window.
 		 */
diff --git a/arch/sh/drivers/pci/ops-landisk.c b/arch/sh/drivers/pci/fixups-landisk.c
similarity index 51%
rename from arch/sh/drivers/pci/ops-landisk.c
rename to arch/sh/drivers/pci/fixups-landisk.c
index bff09ecf3419..bb1a6bb5149e 100644
--- a/arch/sh/drivers/pci/ops-landisk.c
+++ b/arch/sh/drivers/pci/fixups-landisk.c
@@ -15,39 +15,6 @@
 #include <linux/pci.h>
 #include "pci-sh4.h"
 
-static struct resource sh7751_io_resource = {
-	.name = "SH7751 IO",
-	.start = SH7751_PCI_IO_BASE,
-	.end = SH7751_PCI_IO_BASE + SH7751_PCI_IO_SIZE - 1,
-	.flags = IORESOURCE_IO
-};
-
-static struct resource sh7751_mem_resource = {
-	.name = "SH7751 mem",
-	.start = SH7751_PCI_MEMORY_BASE,
-	.end = SH7751_PCI_MEMORY_BASE + SH7751_PCI_MEM_SIZE - 1,
-	.flags = IORESOURCE_MEM
-};
-
-struct pci_channel board_pci_channels[] = {
-	{&sh4_pci_ops, &sh7751_io_resource, &sh7751_mem_resource, 0, 0x3ff},
-	{NULL, NULL, NULL, 0, 0},
-};
-
-static struct sh4_pci_address_map sh7751_pci_map = {
-	.window0 = {
-		.base	= SH7751_CS3_BASE_ADDR,
-		.size	= (64 << 20),	/* 64MB */
-	},
-
-	.flags = SH4_PCIC_NO_RESET,
-};
-
-int __init pcibios_init_platform(void)
-{
-	return sh7751_pcic_init(&sh7751_pci_map);
-}
-
 int pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
 {
 	/*
diff --git a/arch/sh/drivers/pci/fixups-lboxre2.c b/arch/sh/drivers/pci/fixups-lboxre2.c
deleted file mode 100644
index 1c1d41255ec0..000000000000
--- a/arch/sh/drivers/pci/fixups-lboxre2.c
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * arch/sh/drivers/pci/fixups-lboxre2.c
- *
- * L-BOX RE2 PCI fixups
- *
- * Copyright (C) 2007 Nobuhiro Iwamatsu
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include "pci-sh4.h"
-
-#define PCIMCR_MRSET_OFF	0xBFFFFFFF
-#define PCIMCR_RFSH_OFF		0xFFFFFFFB
-
-int pci_fixup_pcic(void)
-{
-	unsigned long bcr1, mcr;
-
-	bcr1 = ctrl_inl(SH7751_BCR1);
-	bcr1 |= 0x40080000;	/* Enable Bit 19 BREQEN, set PCIC to slave */
-	pci_write_reg(bcr1, SH4_PCIBCR1);
-
-	/* Enable all interrupts, so we known what to fix */
-	pci_write_reg(0x0000c3ff, SH4_PCIINTM);
-	pci_write_reg(0x0000380f, SH4_PCIAINTM);
-	pci_write_reg(0xfb900047, SH7751_PCICONF1);
-	pci_write_reg(0xab000001, SH7751_PCICONF4);
-
-	mcr = ctrl_inl(SH7751_MCR);
-	mcr = (mcr & PCIMCR_MRSET_OFF) & PCIMCR_RFSH_OFF;
-	pci_write_reg(mcr, SH4_PCIMCR);
-
-	pci_write_reg(0x0c000000, SH7751_PCICONF5);
-	pci_write_reg(0xd0000000, SH7751_PCICONF6);
-	pci_write_reg(0x0c000000, SH4_PCILAR0);
-	pci_write_reg(0x00000000, SH4_PCILAR1);
-
-	return 0;
-}
diff --git a/arch/sh/drivers/pci/fixups-r7780rp.c b/arch/sh/drivers/pci/fixups-r7780rp.c
index 3e321df65d22..15ca65cb667e 100644
--- a/arch/sh/drivers/pci/fixups-r7780rp.c
+++ b/arch/sh/drivers/pci/fixups-r7780rp.c
@@ -11,35 +11,26 @@
  * for more details.
  */
 #include <linux/pci.h>
+#include <linux/io.h>
 #include "pci-sh4.h"
-#include <asm/io.h>
 
-int pci_fixup_pcic(void)
+static char irq_tab[] __initdata = {
+	65, 66, 67, 68,
+};
+
+int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
 {
-	pci_write_reg(0x000043ff, SH4_PCIINTM);
-	pci_write_reg(0x0000380f, SH4_PCIAINTM);
+	return irq_tab[slot];
+}
 
-	pci_write_reg(0xfbb00047, SH7780_PCICMD);
-	pci_write_reg(0x00000000, SH7780_PCIIBAR);
-
-	pci_write_reg(0x00011912, SH7780_PCISVID);
-	pci_write_reg(0x08000000, SH7780_PCICSCR0);
-	pci_write_reg(0x0000001b, SH7780_PCICSAR0);
-	pci_write_reg(0xfd000000, SH7780_PCICSCR1);
-	pci_write_reg(0x0000000f, SH7780_PCICSAR1);
-
-	pci_write_reg(0xfd000000, SH7780_PCIMBR0);
-	pci_write_reg(0x00fc0000, SH7780_PCIMBMR0);
-
-#ifdef CONFIG_32BIT
-	pci_write_reg(0xc0000000, SH7780_PCIMBR2);
-	pci_write_reg(0x20000000 - SH7780_PCI_IO_SIZE, SH7780_PCIMBMR2);
-#endif
-
-	/* Set IOBR for windows containing area specified in pci.h */
-	pci_write_reg((PCIBIOS_MIN_IO & ~(SH7780_PCI_IO_SIZE - 1)),
-		      SH7780_PCIIOBR);
-	pci_write_reg(((SH7780_PCI_IO_SIZE-1) & (7<<18)), SH7780_PCIIOBMR);
+int pci_fixup_pcic(struct pci_channel *chan)
+{
+	pci_write_reg(chan, 0x000043ff, SH4_PCIINTM);
+	pci_write_reg(chan, 0x00000000, SH7780_PCIIBAR);
+	pci_write_reg(chan, 0x08000000, SH7780_PCICSCR0);
+	pci_write_reg(chan, 0x0000001b, SH7780_PCICSAR0);
+	pci_write_reg(chan, 0xfd000000, SH7780_PCICSCR1);
+	pci_write_reg(chan, 0x0000000f, SH7780_PCICSAR1);
 
 	return 0;
 }
diff --git a/arch/sh/drivers/pci/fixups-rts7751r2d.c b/arch/sh/drivers/pci/fixups-rts7751r2d.c
index 904bce8768d3..052b354236dc 100644
--- a/arch/sh/drivers/pci/fixups-rts7751r2d.c
+++ b/arch/sh/drivers/pci/fixups-rts7751r2d.c
@@ -1,43 +1,67 @@
 /*
  * arch/sh/drivers/pci/fixups-rts7751r2d.c
  *
- * RTS7751R2D PCI fixups
+ * RTS7751R2D / LBOXRE2 PCI fixups
  *
  * Copyright (C) 2003  Lineo uSolutions, Inc.
  * Copyright (C) 2004  Paul Mundt
+ * Copyright (C) 2007  Nobuhiro Iwamatsu
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  */
+#include <linux/pci.h>
+#include <mach/lboxre2.h>
+#include <mach/r2d.h>
 #include "pci-sh4.h"
+#include <asm/machtypes.h>
 
 #define PCIMCR_MRSET_OFF	0xBFFFFFFF
 #define PCIMCR_RFSH_OFF		0xFFFFFFFB
 
-int pci_fixup_pcic(void)
+static u8 rts7751r2d_irq_tab[] __initdata = {
+	IRQ_PCI_INTA,
+	IRQ_PCI_INTB,
+	IRQ_PCI_INTC,
+	IRQ_PCI_INTD,
+};
+
+static char lboxre2_irq_tab[] __initdata = {
+	IRQ_ETH0, IRQ_ETH1, IRQ_INTA, IRQ_INTD,
+};
+
+int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
+{
+	if (mach_is_lboxre2())
+		return lboxre2_irq_tab[slot];
+	else
+		return rts7751r2d_irq_tab[slot];
+}
+
+int pci_fixup_pcic(struct pci_channel *chan)
 {
 	unsigned long bcr1, mcr;
 
 	bcr1 = ctrl_inl(SH7751_BCR1);
 	bcr1 |= 0x40080000;	/* Enable Bit 19 BREQEN, set PCIC to slave */
-	pci_write_reg(bcr1, SH4_PCIBCR1);
+	pci_write_reg(chan, bcr1, SH4_PCIBCR1);
 
 	/* Enable all interrupts, so we known what to fix */
-	pci_write_reg(0x0000c3ff, SH4_PCIINTM);
-	pci_write_reg(0x0000380f, SH4_PCIAINTM);
+	pci_write_reg(chan, 0x0000c3ff, SH4_PCIINTM);
+	pci_write_reg(chan, 0x0000380f, SH4_PCIAINTM);
 
-	pci_write_reg(0xfb900047, SH7751_PCICONF1);
-	pci_write_reg(0xab000001, SH7751_PCICONF4);
+	pci_write_reg(chan, 0xfb900047, SH7751_PCICONF1);
+	pci_write_reg(chan, 0xab000001, SH7751_PCICONF4);
 
 	mcr = ctrl_inl(SH7751_MCR);
 	mcr = (mcr & PCIMCR_MRSET_OFF) & PCIMCR_RFSH_OFF;
-	pci_write_reg(mcr, SH4_PCIMCR);
+	pci_write_reg(chan, mcr, SH4_PCIMCR);
 
-	pci_write_reg(0x0c000000, SH7751_PCICONF5);
-	pci_write_reg(0xd0000000, SH7751_PCICONF6);
-	pci_write_reg(0x0c000000, SH4_PCILAR0);
-	pci_write_reg(0x00000000, SH4_PCILAR1);
+	pci_write_reg(chan, 0x0c000000, SH7751_PCICONF5);
+	pci_write_reg(chan, 0xd0000000, SH7751_PCICONF6);
+	pci_write_reg(chan, 0x0c000000, SH4_PCILAR0);
+	pci_write_reg(chan, 0x00000000, SH4_PCILAR1);
 
 	return 0;
 }
diff --git a/arch/sh/drivers/pci/fixups-sdk7780.c b/arch/sh/drivers/pci/fixups-sdk7780.c
index 2f8863099dd1..250b0edd7365 100644
--- a/arch/sh/drivers/pci/fixups-sdk7780.c
+++ b/arch/sh/drivers/pci/fixups-sdk7780.c
@@ -5,55 +5,48 @@
  *
  * Copyright (C) 2003  Lineo uSolutions, Inc.
  * Copyright (C) 2004 - 2006  Paul Mundt
+ * Copyright (C) 2006  Nobuhiro Iwamatsu
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  */
 #include <linux/pci.h>
+#include <linux/io.h>
 #include "pci-sh4.h"
-#include <asm/io.h>
 
-int pci_fixup_pcic(void)
+/* IDSEL [16][17][18][19][20][21][22][23][24][25][26][27][28][29][30][31] */
+static char sdk7780_irq_tab[4][16] __initdata = {
+	/* INTA */
+	{ 65, 68, 67, 68, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
+	/* INTB */
+	{ 66, 65, -1, 65, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
+	/* INTC */
+	{ 67, 66, -1, 66, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
+	/* INTD */
+	{ 68, 67, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
+};
+
+int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
+{
+       return sdk7780_irq_tab[pin-1][slot];
+}
+int pci_fixup_pcic(struct pci_channel *chan)
 {
-	ctrl_outl(0x00000001, SH7780_PCI_VCR2);
-
 	/* Enable all interrupts, so we know what to fix */
-	pci_write_reg(0x0000C3FF, SH7780_PCIIMR);
-	pci_write_reg(0x0000380F, SH7780_PCIAINTM);
+	pci_write_reg(chan, 0x0000C3FF, SH7780_PCIIMR);
 
 	/* Set up standard PCI config registers */
-	pci_write_reg(0xFB00, SH7780_PCISTATUS);
-	pci_write_reg(0x0047, SH7780_PCICMD);
-	pci_write_reg(0x00, SH7780_PCIPIF);
-	pci_write_reg(0x00, SH7780_PCISUB);
-	pci_write_reg(0x06, SH7780_PCIBCC);
-	pci_write_reg(0x1912, SH7780_PCISVID);
-	pci_write_reg(0x0001, SH7780_PCISID);
+	pci_write_reg(chan, 0x08000000, SH7780_PCIMBAR0);	/* PCI */
+	pci_write_reg(chan, 0x08000000, SH4_PCILAR0);	/* SHwy */
+	pci_write_reg(chan, 0x07F00001, SH4_PCILSR0);	/* size 128M w/ MBAR */
 
-	pci_write_reg(0x08000000, SH7780_PCIMBAR0);	/* PCI */
-	pci_write_reg(0x08000000, SH7780_PCILAR0);	/* SHwy */
-	pci_write_reg(0x07F00001, SH7780_PCILSR);	/* size 128M w/ MBAR */
+	pci_write_reg(chan, 0x00000000, SH7780_PCIMBAR1);
+	pci_write_reg(chan, 0x00000000, SH4_PCILAR1);
+	pci_write_reg(chan, 0x00000000, SH4_PCILSR1);
 
-	pci_write_reg(0x00000000, SH7780_PCIMBAR1);
-	pci_write_reg(0x00000000, SH7780_PCILAR1);
-	pci_write_reg(0x00000000, SH7780_PCILSR1);
-
-	pci_write_reg(0xAB000801, SH7780_PCIIBAR);
-
-	/*
-	 * Set the MBR so PCI address is one-to-one with window,
-	 * meaning all calls go straight through... use ifdef to
-	 * catch erroneous assumption.
-	 */
-	pci_write_reg(0xFD000000 , SH7780_PCIMBR0);
-	pci_write_reg(0x00FC0000 , SH7780_PCIMBMR0);	/* 16M */
-
-	/* Set IOBR for window containing area specified in pci.h */
-	pci_write_reg(PCIBIOS_MIN_IO & ~(SH7780_PCI_IO_SIZE-1), SH7780_PCIIOBR);
-	pci_write_reg((SH7780_PCI_IO_SIZE-1) & (7 << 18), SH7780_PCIIOBMR);
-
-	pci_write_reg(0xA5000C01, SH7780_PCICR);
+	pci_write_reg(chan, 0xAB000801, SH7780_PCIIBAR);
+	pci_write_reg(chan, 0xA5000C01, SH4_PCICR);
 
 	return 0;
 }
diff --git a/arch/sh/drivers/pci/fixups-se7751.c b/arch/sh/drivers/pci/fixups-se7751.c
new file mode 100644
index 000000000000..475fa9f0fe2c
--- /dev/null
+++ b/arch/sh/drivers/pci/fixups-se7751.c
@@ -0,0 +1,111 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/io.h>
+#include "pci-sh4.h"
+
+int __init pcibios_map_platform_irq(u8 slot, u8 pin)
+{
+        switch (slot) {
+        case 0: return 13;
+        case 1: return 13;	/* AMD Ethernet controller */
+        case 2: return -1;
+        case 3: return -1;
+        case 4: return -1;
+        default:
+                printk("PCI: Bad IRQ mapping request for slot %d\n", slot);
+                return -1;
+        }
+}
+
+#define PCIMCR_MRSET_OFF	0xBFFFFFFF
+#define PCIMCR_RFSH_OFF		0xFFFFFFFB
+
+/*
+ * Only long word accesses of the PCIC's internal local registers and the
+ * configuration registers from the CPU is supported.
+ */
+#define PCIC_WRITE(x,v) writel((v), PCI_REG(x))
+#define PCIC_READ(x) readl(PCI_REG(x))
+
+/*
+ * Description:  This function sets up and initializes the pcic, sets
+ * up the BARS, maps the DRAM into the address space etc, etc.
+ */
+int pci_fixup_pcic(struct pci_channel *chan)
+{
+	unsigned long bcr1, wcr1, wcr2, wcr3, mcr;
+	unsigned short bcr2;
+
+	/*
+	* Initialize the slave bus controller on the pcic.  The values used
+	* here should not be hardcoded, but they should be taken from the bsc
+	* on the processor, to make this function as generic as possible.
+	* (i.e. Another sbc may usr different SDRAM timing settings -- in order
+	* for the pcic to work, its settings need to be exactly the same.)
+	*/
+	bcr1 = (*(volatile unsigned long*)(SH7751_BCR1));
+	bcr2 = (*(volatile unsigned short*)(SH7751_BCR2));
+	wcr1 = (*(volatile unsigned long*)(SH7751_WCR1));
+	wcr2 = (*(volatile unsigned long*)(SH7751_WCR2));
+	wcr3 = (*(volatile unsigned long*)(SH7751_WCR3));
+	mcr = (*(volatile unsigned long*)(SH7751_MCR));
+
+	bcr1 = bcr1 | 0x00080000;  /* Enable Bit 19, BREQEN */
+	(*(volatile unsigned long*)(SH7751_BCR1)) = bcr1;
+
+	bcr1 = bcr1 | 0x40080000;  /* Enable Bit 19 BREQEN, set PCIC to slave */
+	PCIC_WRITE(SH7751_PCIBCR1, bcr1);	 /* PCIC BCR1 */
+	PCIC_WRITE(SH7751_PCIBCR2, bcr2);     /* PCIC BCR2 */
+	PCIC_WRITE(SH7751_PCIWCR1, wcr1);     /* PCIC WCR1 */
+	PCIC_WRITE(SH7751_PCIWCR2, wcr2);     /* PCIC WCR2 */
+	PCIC_WRITE(SH7751_PCIWCR3, wcr3);     /* PCIC WCR3 */
+	mcr = (mcr & PCIMCR_MRSET_OFF) & PCIMCR_RFSH_OFF;
+	PCIC_WRITE(SH7751_PCIMCR, mcr);      /* PCIC MCR */
+
+
+	/* Enable all interrupts, so we know what to fix */
+	PCIC_WRITE(SH7751_PCIINTM, 0x0000c3ff);
+	PCIC_WRITE(SH7751_PCIAINTM, 0x0000380f);
+
+	/* Set up standard PCI config registers */
+	PCIC_WRITE(SH7751_PCICONF1,	0xF39000C7); /* Bus Master, Mem & I/O access */
+	PCIC_WRITE(SH7751_PCICONF2,	0x00000000); /* PCI Class code & Revision ID */
+	PCIC_WRITE(SH7751_PCICONF4,	0xab000001); /* PCI I/O address (local regs) */
+	PCIC_WRITE(SH7751_PCICONF5,	0x0c000000); /* PCI MEM address (local RAM)  */
+	PCIC_WRITE(SH7751_PCICONF6,	0xd0000000); /* PCI MEM address (unused)     */
+	PCIC_WRITE(SH7751_PCICONF11, 0x35051054); /* PCI Subsystem ID & Vendor ID */
+	PCIC_WRITE(SH7751_PCILSR0, 0x03f00000);   /* MEM (full 64M exposed)       */
+	PCIC_WRITE(SH7751_PCILSR1, 0x00000000);   /* MEM (unused)                 */
+	PCIC_WRITE(SH7751_PCILAR0, 0x0c000000);   /* MEM (direct map from PCI)    */
+	PCIC_WRITE(SH7751_PCILAR1, 0x00000000);   /* MEM (unused)                 */
+
+	/* Now turn it on... */
+	PCIC_WRITE(SH7751_PCICR, 0xa5000001);
+
+	/*
+	* Set PCIMBR and PCIIOBR here, assuming a single window
+	* (16M MEM, 256K IO) is enough.  If a larger space is
+	* needed, the readx/writex and inx/outx functions will
+	* have to do more (e.g. setting registers for each call).
+	*/
+
+	/*
+	* Set the MBR so PCI address is one-to-one with window,
+	* meaning all calls go straight through... use BUG_ON to
+	* catch erroneous assumption.
+	*/
+	BUG_ON(chan->mem_resource->start != SH7751_PCI_MEMORY_BASE);
+
+	PCIC_WRITE(SH7751_PCIMBR, chan->mem_resource->start);
+
+	/* Set IOBR for window containing area specified in pci.h */
+	PCIC_WRITE(SH7751_PCIIOBR, (chan->io_resource->start & SH7751_PCIIOBR_MASK));
+
+	/* All done, may as well say so... */
+	printk("SH7751 PCI: Finished initialization of the PCI controller\n");
+
+	return 1;
+}
diff --git a/arch/sh/drivers/pci/fixups-se7780.c b/arch/sh/drivers/pci/fixups-se7780.c
deleted file mode 100644
index 880cea1c0d89..000000000000
--- a/arch/sh/drivers/pci/fixups-se7780.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * arch/sh/drivers/pci/fixups-se7780.c
- *
- * HITACHI UL Solution Engine 7780  PCI fixups
- *
- * Copyright (C) 2003  Lineo uSolutions, Inc.
- * Copyright (C) 2004 - 2006  Paul Mundt
- * Copyright (C) 2006  Nobuhiro Iwamatsu
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/pci.h>
-#include "pci-sh4.h"
-#include <asm/io.h>
-
-int pci_fixup_pcic(void)
-{
-	ctrl_outl(0x00000001, SH7780_PCI_VCR2);
-
-	/* Enable all interrupts, so we know what to fix */
-	pci_write_reg(0x0000C3FF, SH7780_PCIIMR);
-	pci_write_reg(0x0000380F, SH7780_PCIAINTM);
-
-	/* Set up standard PCI config registers */
-	ctrl_outw(0xFB00, PCI_REG(SH7780_PCISTATUS));
-	ctrl_outw(0x0047, PCI_REG(SH7780_PCICMD));
-	ctrl_outb(  0x00, PCI_REG(SH7780_PCIPIF));
-	ctrl_outb(  0x00, PCI_REG(SH7780_PCISUB));
-	ctrl_outb(  0x06, PCI_REG(SH7780_PCIBCC));
-	ctrl_outw(0x1912, PCI_REG(SH7780_PCISVID));
-	ctrl_outw(0x0001, PCI_REG(SH7780_PCISID));
-
-	pci_write_reg(0x08000000, SH7780_PCIMBAR0);     /* PCI */
-	pci_write_reg(0x08000000, SH7780_PCILAR0);     /* SHwy */
-	pci_write_reg(0x07F00001, SH7780_PCILSR);      /* size 128M w/ MBAR */
-
-	pci_write_reg(0x00000000, SH7780_PCIMBAR1);
-	pci_write_reg(0x00000000, SH7780_PCILAR1);
-	pci_write_reg(0x00000000, SH7780_PCILSR1);
-
-	pci_write_reg(0xAB000801, SH7780_PCIIBAR);
-
-	/*
-	 * Set the MBR so PCI address is one-to-one with window,
-	 * meaning all calls go straight through... use ifdef to
-	 * catch erroneous assumption.
-	 */
-	pci_write_reg(0xFD000000 , SH7780_PCIMBR0);
-	pci_write_reg(0x00FC0000 , SH7780_PCIMBMR0);    /* 16M */
-
-	/* Set IOBR for window containing area specified in pci.h */
-	pci_write_reg(PCIBIOS_MIN_IO & ~(SH7780_PCI_IO_SIZE-1), SH7780_PCIIOBR);
-	pci_write_reg((SH7780_PCI_IO_SIZE-1) & (7 << 18), SH7780_PCIIOBMR);
-
-	pci_write_reg(0xA5000C01, SH7780_PCICR);
-
-	return 0;
-}
diff --git a/arch/sh/drivers/pci/fixups-sh7785lcr.c b/arch/sh/drivers/pci/fixups-sh7785lcr.c
deleted file mode 100644
index 4949e601387a..000000000000
--- a/arch/sh/drivers/pci/fixups-sh7785lcr.c
+++ /dev/null
@@ -1,46 +0,0 @@
-/*
- * arch/sh/drivers/pci/fixups-sh7785lcr.c
- *
- * R0P7785LC0011RL PCI fixups
- * Copyright (C) 2008  Yoshihiro Shimoda
- *
- * Based on arch/sh/drivers/pci/fixups-r7780rp.c
- * Copyright (C) 2003  Lineo uSolutions, Inc.
- * Copyright (C) 2004 - 2006  Paul Mundt
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/pci.h>
-#include "pci-sh4.h"
-
-int pci_fixup_pcic(void)
-{
-	pci_write_reg(0x000043ff, SH4_PCIINTM);
-	pci_write_reg(0x0000380f, SH4_PCIAINTM);
-
-	pci_write_reg(0xfbb00047, SH7780_PCICMD);
-	pci_write_reg(0x00000000, SH7780_PCIIBAR);
-
-	pci_write_reg(0x00011912, SH7780_PCISVID);
-	pci_write_reg(0x08000000, SH7780_PCICSCR0);
-	pci_write_reg(0x0000001b, SH7780_PCICSAR0);
-	pci_write_reg(0xfd000000, SH7780_PCICSCR1);
-	pci_write_reg(0x0000000f, SH7780_PCICSAR1);
-
-	pci_write_reg(0xfd000000, SH7780_PCIMBR0);
-	pci_write_reg(0x00fc0000, SH7780_PCIMBMR0);
-
-#ifdef CONFIG_32BIT
-	pci_write_reg(0xc0000000, SH7780_PCIMBR2);
-	pci_write_reg(0x20000000 - SH7780_PCI_IO_SIZE, SH7780_PCIMBMR2);
-#endif
-
-	/* Set IOBR for windows containing area specified in pci.h */
-	pci_write_reg((PCIBIOS_MIN_IO & ~(SH7780_PCI_IO_SIZE - 1)),
-		      SH7780_PCIIOBR);
-	pci_write_reg(((SH7780_PCI_IO_SIZE - 1) & (7 << 18)), SH7780_PCIIOBMR);
-
-	return 0;
-}
diff --git a/arch/sh/drivers/pci/fixups-snapgear.c b/arch/sh/drivers/pci/fixups-snapgear.c
new file mode 100644
index 000000000000..5a39ecc1adb8
--- /dev/null
+++ b/arch/sh/drivers/pci/fixups-snapgear.c
@@ -0,0 +1,38 @@
+/*
+ * arch/sh/drivers/pci/ops-snapgear.c
+ *
+ * Author:  David McCullough <davidm@snapgear.com>
+ *
+ * Ported to new API by Paul Mundt <lethal@linux-sh.org>
+ *
+ * Highly leveraged from pci-bigsur.c, written by Dustin McIntire.
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License.  See linux/COPYING for more information.
+ *
+ * PCI initialization for the SnapGear boards
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include "pci-sh4.h"
+
+int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
+{
+	int irq = -1;
+
+	switch (slot) {
+	case 8:  /* the PCI bridge */ break;
+	case 11: irq = 8;  break; /* USB    */
+	case 12: irq = 11; break; /* PCMCIA */
+	case 13: irq = 5;  break; /* eth0   */
+	case 14: irq = 8;  break; /* eth1   */
+	case 15: irq = 11; break; /* safenet (unused) */
+	}
+
+	printk("PCI: Mapping SnapGear IRQ for slot %d, pin %c to irq %d\n",
+	       slot, pin - 1 + 'A', irq);
+
+	return irq;
+}
diff --git a/arch/sh/drivers/pci/ops-titan.c b/arch/sh/drivers/pci/fixups-titan.c
similarity index 50%
rename from arch/sh/drivers/pci/ops-titan.c
rename to arch/sh/drivers/pci/fixups-titan.c
index a8f7801a34af..3a79fa8254a6 100644
--- a/arch/sh/drivers/pci/ops-titan.c
+++ b/arch/sh/drivers/pci/fixups-titan.c
@@ -36,42 +36,3 @@ int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
 
 	return irq;
 }
-
-static struct resource sh7751_io_resource = {
-	.name	= "SH7751_IO",
-	.start	= SH7751_PCI_IO_BASE,
-	.end	= SH7751_PCI_IO_BASE + SH7751_PCI_IO_SIZE - 1,
-	.flags	= IORESOURCE_IO
-};
-
-static struct resource sh7751_mem_resource = {
-	.name	= "SH7751_mem",
-	.start	= SH7751_PCI_MEMORY_BASE,
-	.end	= SH7751_PCI_MEMORY_BASE + SH7751_PCI_MEM_SIZE - 1,
-	.flags	= IORESOURCE_MEM
-};
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh4_pci_ops, &sh7751_io_resource, &sh7751_mem_resource, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-EXPORT_SYMBOL(board_pci_channels);
-
-static struct sh4_pci_address_map sh7751_pci_map = {
-	.window0	= {
-		.base	= SH7751_CS2_BASE_ADDR,
-		.size	= SH7751_MEM_REGION_SIZE*2,	/* cs2 and cs3 */
-	},
-
-	.window1	= {
-		.base	= SH7751_CS2_BASE_ADDR,
-		.size	= SH7751_MEM_REGION_SIZE*2,
-	},
-
-	.flags	= SH4_PCIC_NO_RESET,
-};
-
-int __init pcibios_init_platform(void)
-{
-	return sh7751_pcic_init(&sh7751_pci_map);
-}
diff --git a/arch/sh/drivers/pci/ops-dreamcast.c b/arch/sh/drivers/pci/ops-dreamcast.c
index f5d2a2aa6f3f..e83d0d3aabe2 100644
--- a/arch/sh/drivers/pci/ops-dreamcast.c
+++ b/arch/sh/drivers/pci/ops-dreamcast.c
@@ -1,15 +1,9 @@
 /*
- * arch/sh/drivers/pci/ops-dreamcast.c
- *
  * PCI operations for the Sega Dreamcast
  *
  * Copyright (C) 2001, 2002  M. R. Brown
  * Copyright (C) 2002, 2003  Paul Mundt
  *
- * This file originally bore the message (with enclosed-$):
- *	Id: pci.c,v 1.3 2003/05/04 19:29:46 lethal Exp
- *	Dreamcast PCI: Supports SEGA Broadband Adaptor only.
- *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
@@ -23,34 +17,10 @@
 #include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/module.h>
-
-#include <asm/io.h>
-#include <asm/irq.h>
+#include <linux/io.h>
+#include <linux/irq.h>
 #include <mach/pci.h>
 
-static struct resource gapspci_io_resource = {
-	.name	= "GAPSPCI IO",
-	.start	= GAPSPCI_BBA_CONFIG,
-	.end	= GAPSPCI_BBA_CONFIG + GAPSPCI_BBA_CONFIG_SIZE - 1,
-	.flags	= IORESOURCE_IO,
-};
-
-static struct resource gapspci_mem_resource = {
-	.name	= "GAPSPCI mem",
-	.start	= GAPSPCI_DMA_BASE,
-	.end	= GAPSPCI_DMA_BASE + GAPSPCI_DMA_SIZE - 1,
-	.flags	= IORESOURCE_MEM,
-};
-
-static struct pci_ops gapspci_pci_ops;
-
-struct pci_channel board_pci_channels[] = {
-	{ &gapspci_pci_ops, &gapspci_io_resource,
-	  &gapspci_mem_resource, 0, 1 },
-	{ 0, }
-};
-EXPORT_SYMBOL(board_pci_channels);
-
 /*
  * The !gapspci_config_access case really shouldn't happen, ever, unless
  * someone implicitly messes around with the last devfn value.. otherwise we
@@ -85,10 +55,10 @@ static int gapspci_read(struct pci_bus *bus, unsigned int devfn, int where, int
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	switch (size) {
-		case 1: *val = inb(GAPSPCI_BBA_CONFIG+where); break;
-		case 2: *val = inw(GAPSPCI_BBA_CONFIG+where); break;
-		case 4: *val = inl(GAPSPCI_BBA_CONFIG+where); break;
-	}	
+	case 1: *val = inb(GAPSPCI_BBA_CONFIG+where); break;
+	case 2: *val = inw(GAPSPCI_BBA_CONFIG+where); break;
+	case 4: *val = inl(GAPSPCI_BBA_CONFIG+where); break;
+	}
 
         return PCIBIOS_SUCCESSFUL;
 }
@@ -99,72 +69,15 @@ static int gapspci_write(struct pci_bus *bus, unsigned int devfn, int where, int
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	switch (size) {
-		case 1: outb(( u8)val, GAPSPCI_BBA_CONFIG+where); break;
-		case 2: outw((u16)val, GAPSPCI_BBA_CONFIG+where); break;
-		case 4: outl((u32)val, GAPSPCI_BBA_CONFIG+where); break;
+	case 1: outb(( u8)val, GAPSPCI_BBA_CONFIG+where); break;
+	case 2: outw((u16)val, GAPSPCI_BBA_CONFIG+where); break;
+	case 4: outl((u32)val, GAPSPCI_BBA_CONFIG+where); break;
 	}
 
         return PCIBIOS_SUCCESSFUL;
 }
 
-static struct pci_ops gapspci_pci_ops = {
+struct pci_ops gapspci_pci_ops = {
 	.read	= gapspci_read,
 	.write	= gapspci_write,
 };
-
-/*
- * gapspci init
- */
-
-int __init gapspci_init(void)
-{
-	char idbuf[16];
-	int i;
-
-	/*
-	 * FIXME: All of this wants documenting to some degree,
-	 * even some basic register definitions would be nice.
-	 *
-	 * I haven't seen anything this ugly since.. maple.
-	 */
-
-	for (i=0; i<16; i++)
-		idbuf[i] = inb(GAPSPCI_REGS+i);
-
-	if (strncmp(idbuf, "GAPSPCI_BRIDGE_2", 16))
-		return -ENODEV;
-
-	outl(0x5a14a501, GAPSPCI_REGS+0x18);
-
-	for (i=0; i<1000000; i++)
-		;
-
-	if (inl(GAPSPCI_REGS+0x18) != 1)
-		return -EINVAL;
-
-	outl(0x01000000, GAPSPCI_REGS+0x20);
-	outl(0x01000000, GAPSPCI_REGS+0x24);
-
-	outl(GAPSPCI_DMA_BASE, GAPSPCI_REGS+0x28);
-	outl(GAPSPCI_DMA_BASE+GAPSPCI_DMA_SIZE, GAPSPCI_REGS+0x2c);
-
-	outl(1, GAPSPCI_REGS+0x14);
-	outl(1, GAPSPCI_REGS+0x34);
-
-	/* Setting Broadband Adapter */
-	outw(0xf900, GAPSPCI_BBA_CONFIG+0x06);
-	outl(0x00000000, GAPSPCI_BBA_CONFIG+0x30);
-	outb(0x00, GAPSPCI_BBA_CONFIG+0x3c);
-	outb(0xf0, GAPSPCI_BBA_CONFIG+0x0d);
-	outw(0x0006, GAPSPCI_BBA_CONFIG+0x04);
-	outl(0x00002001, GAPSPCI_BBA_CONFIG+0x10);
-	outl(0x01000000, GAPSPCI_BBA_CONFIG+0x14);
-
-	return 0;
-}
-
-/* Haven't done anything here as yet */
-char * __devinit pcibios_setup(char *str)
-{
-	return str;
-}
diff --git a/arch/sh/drivers/pci/ops-lboxre2.c b/arch/sh/drivers/pci/ops-lboxre2.c
deleted file mode 100644
index 86c0b6fb7375..000000000000
--- a/arch/sh/drivers/pci/ops-lboxre2.c
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * linux/arch/sh/drivers/pci/ops-lboxre2.c
- *
- * Copyright (C) 2007 Nobuhiro Iwamatsu
- *
- * PCI initialization for the NTT COMWARE L-BOX RE2
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/io.h>
-#include <mach/lboxre2.h>
-#include "pci-sh4.h"
-
-static char lboxre2_irq_tab[] __initdata = {
-	IRQ_ETH0, IRQ_ETH1, IRQ_INTA, IRQ_INTD,
-};
-
-int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
-{
-	return lboxre2_irq_tab[slot];
-}
-
-static struct resource sh7751_io_resource = {
-	.name	= "SH7751_IO",
-	.start	= SH7751_PCI_IO_BASE ,
-	.end	= SH7751_PCI_IO_BASE + SH7751_PCI_IO_SIZE - 1,
-	.flags	= IORESOURCE_IO
-};
-
-static struct resource sh7751_mem_resource = {
-	.name	= "SH7751_mem",
-	.start	= SH7751_PCI_MEMORY_BASE,
-	.end	= SH7751_PCI_MEMORY_BASE + SH7751_PCI_MEM_SIZE - 1,
-	.flags	= IORESOURCE_MEM
-};
-
-extern struct pci_ops sh7751_pci_ops;
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh4_pci_ops, &sh7751_io_resource, &sh7751_mem_resource, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-
-EXPORT_SYMBOL(board_pci_channels);
-
-static struct sh4_pci_address_map sh7751_pci_map = {
-	.window0	= {
-		.base	= SH7751_CS3_BASE_ADDR,
-		.size	= 0x04000000,
-	},
-	.window1	= {
-		.base	= 0x00000000,	/* Unused */
-		.size	= 0x00000000,	/* Unused */
-	},
-	.flags	= SH4_PCIC_NO_RESET,
-};
-
-int __init pcibios_init_platform(void)
-{
-	return sh7751_pcic_init(&sh7751_pci_map);
-}
diff --git a/arch/sh/drivers/pci/ops-r7780rp.c b/arch/sh/drivers/pci/ops-r7780rp.c
deleted file mode 100644
index 8555238e63eb..000000000000
--- a/arch/sh/drivers/pci/ops-r7780rp.c
+++ /dev/null
@@ -1,68 +0,0 @@
-/*
- * Author:  Ian DaSilva (idasilva@mvista.com)
- *
- * Highly leveraged from pci-bigsur.c, written by Dustin McIntire.
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * PCI initialization for the Renesas SH7780 Highlander R7780RP-1 board
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include <mach/highlander.h>
-#include <asm/io.h>
-#include "pci-sh4.h"
-
-static char irq_tab[] __initdata = {
-	65, 66, 67, 68,
-};
-
-int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
-{
-	return irq_tab[slot];
-}
-
-static struct resource sh7780_io_resource = {
-	.name	= "SH7780_IO",
-	.start	= SH7780_PCI_IO_BASE,
-	.end	= SH7780_PCI_IO_BASE + SH7780_PCI_IO_SIZE - 1,
-	.flags	= IORESOURCE_IO
-};
-
-static struct resource sh7780_mem_resource = {
-	.name	= "SH7780_mem",
-	.start	= SH7780_PCI_MEMORY_BASE,
-	.end	= SH7780_PCI_MEMORY_BASE + SH7780_PCI_MEM_SIZE - 1,
-	.flags	= IORESOURCE_MEM
-};
-
-extern struct pci_ops sh7780_pci_ops;
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh4_pci_ops, &sh7780_io_resource, &sh7780_mem_resource, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-EXPORT_SYMBOL(board_pci_channels);
-
-static struct sh4_pci_address_map sh7780_pci_map = {
-	.window0	= {
-		.base	= SH7780_CS2_BASE_ADDR,
-		.size	= 0x04000000,
-	},
-
-	.window1	= {
-		.base	= SH7780_CS3_BASE_ADDR,
-		.size	= 0x04000000,
-	},
-
-	.flags	= SH4_PCIC_NO_RESET,
-};
-
-int __init pcibios_init_platform(void)
-{
-	return sh7780_pcic_init(&sh7780_pci_map);
-}
diff --git a/arch/sh/drivers/pci/ops-rts7751r2d.c b/arch/sh/drivers/pci/ops-rts7751r2d.c
deleted file mode 100644
index d6ca74b25d5f..000000000000
--- a/arch/sh/drivers/pci/ops-rts7751r2d.c
+++ /dev/null
@@ -1,74 +0,0 @@
-/*
- * linux/arch/sh/drivers/pci/ops-rts7751r2d.c
- *
- * Author:  Ian DaSilva (idasilva@mvista.com)
- *
- * Highly leveraged from pci-bigsur.c, written by Dustin McIntire.
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * PCI initialization for the Renesas SH7751R RTS7751R2D board
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/io.h>
-#include <mach/r2d.h>
-#include "pci-sh4.h"
-
-static u8 rts7751r2d_irq_tab[] __initdata = {
-	IRQ_PCI_INTA,
-	IRQ_PCI_INTB,
-	IRQ_PCI_INTC,
-	IRQ_PCI_INTD,
-};
-
-int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
-{
-	return rts7751r2d_irq_tab[slot];
-}
-
-static struct resource sh7751_io_resource = {
-	.name	= "SH7751_IO",
-	.start	= 0x4000,
-	.end	= SH7751_PCI_IO_SIZE - 1,
-	.flags	= IORESOURCE_IO
-};
-
-static struct resource sh7751_mem_resource = {
-	.name	= "SH7751_mem",
-	.start	= SH7751_PCI_MEMORY_BASE,
-	.end	= SH7751_PCI_MEMORY_BASE + SH7751_PCI_MEM_SIZE - 1,
-	.flags	= IORESOURCE_MEM
-};
-
-extern struct pci_ops sh7751_pci_ops;
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh4_pci_ops, &sh7751_io_resource, &sh7751_mem_resource, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-EXPORT_SYMBOL(board_pci_channels);
-
-static struct sh4_pci_address_map sh7751_pci_map = {
-	.window0	= {
-		.base	= SH7751_CS3_BASE_ADDR,
-		.size	= 0x04000000,
-	},
-
-	.window1	= {
-		.base	= 0x00000000,	/* Unused */
-		.size	= 0x00000000,	/* Unused */
-	},
-
-	.flags	= SH4_PCIC_NO_RESET,
-};
-
-int __init pcibios_init_platform(void)
-{
-	__set_io_port_base(SH7751_PCI_IO_BASE);
-	return sh7751_pcic_init(&sh7751_pci_map);
-}
-
diff --git a/arch/sh/drivers/pci/ops-sdk7780.c b/arch/sh/drivers/pci/ops-sdk7780.c
deleted file mode 100644
index 4dcc64184b23..000000000000
--- a/arch/sh/drivers/pci/ops-sdk7780.c
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * linux/arch/sh/drivers/pci/ops-sdk7780.c
- *
- * Copyright (C) 2006  Nobuhiro Iwamatsu
- *
- * PCI initialization for the SDK7780SE03
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include <mach/sdk7780.h>
-#include <asm/io.h>
-#include "pci-sh4.h"
-
-/* IDSEL [16][17][18][19][20][21][22][23][24][25][26][27][28][29][30][31] */
-static char sdk7780_irq_tab[4][16] __initdata = {
-	/* INTA */
-	{ 65, 68, 67, 68, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
-	/* INTB */
-	{ 66, 65, -1, 65, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
-	/* INTC */
-	{ 67, 66, -1, 66, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
-	/* INTD */
-	{ 68, 67, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
-};
-
-int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
-{
-       return sdk7780_irq_tab[pin-1][slot];
-}
-
-static struct resource sdk7780_io_resource = {
-	.name	= "SH7780_IO",
-	.start	= SH7780_PCI_IO_BASE,
-	.end	= SH7780_PCI_IO_BASE + SH7780_PCI_IO_SIZE - 1,
-	.flags	= IORESOURCE_IO
-};
-
-static struct resource sdk7780_mem_resource = {
-	.name	= "SH7780_mem",
-	.start	= SH7780_PCI_MEMORY_BASE,
-	.end	= SH7780_PCI_MEMORY_BASE + SH7780_PCI_MEM_SIZE - 1,
-	.flags	= IORESOURCE_MEM
-};
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh4_pci_ops, &sdk7780_io_resource, &sdk7780_mem_resource, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-EXPORT_SYMBOL(board_pci_channels);
-
-static struct sh4_pci_address_map sdk7780_pci_map = {
-	.window0	= {
-		.base	= SH7780_CS2_BASE_ADDR,
-		.size	= 0x04000000,
-	},
-	.window1	= {
-		.base	= SH7780_CS3_BASE_ADDR,
-		.size	= 0x04000000,
-	},
-	.flags	= SH4_PCIC_NO_RESET,
-};
-
-int __init pcibios_init_platform(void)
-{
-	printk(KERN_INFO "SH7780 PCI: Finished initializing PCI controller\n");
-	return sh7780_pcic_init(&sdk7780_pci_map);
-}
diff --git a/arch/sh/drivers/pci/ops-se7780.c b/arch/sh/drivers/pci/ops-se7780.c
deleted file mode 100644
index 3145c62484d6..000000000000
--- a/arch/sh/drivers/pci/ops-se7780.c
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * linux/arch/sh/drivers/pci/ops-se7780.c
- *
- * Copyright (C) 2006  Nobuhiro Iwamatsu
- *
- * PCI initialization for the Hitachi UL Solution Engine 7780SE03
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include <mach-se/mach/se7780.h>
-#include <asm/io.h>
-#include "pci-sh4.h"
-
-/*
- * IDSEL = AD16  PCI slot
- * IDSEL = AD17  PCI slot
- * IDSEL = AD18  Serial ATA Controller (Silicon Image SiL3512A)
- * IDSEL = AD19  USB Host Controller (NEC uPD7210100A)
- */
-
-/* IDSEL [16][17][18][19][20][21][22][23][24][25][26][27][28][29][30][31] */
-static char se7780_irq_tab[4][16] __initdata = {
-	/* INTA */
-	{ 65, 68, 67, 68, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
-	/* INTB */
-	{ 66, 65, -1, 65, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
-	/* INTC */
-	{ 67, 66, -1, 66, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
-	/* INTD */
-	{ 68, 67, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 },
-};
-
-int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
-{
-       return se7780_irq_tab[pin-1][slot];
-}
-
-static struct resource se7780_io_resource = {
-	.name	= "SH7780_IO",
-	.start	= SH7780_PCI_IO_BASE,
-	.end	= SH7780_PCI_IO_BASE + SH7780_PCI_IO_SIZE - 1,
-	.flags	= IORESOURCE_IO
-};
-
-static struct resource se7780_mem_resource = {
-	.name	= "SH7780_mem",
-	.start	= SH7780_PCI_MEMORY_BASE,
-	.end	= SH7780_PCI_MEMORY_BASE + SH7780_PCI_MEM_SIZE - 1,
-	.flags	= IORESOURCE_MEM
-};
-
-extern struct pci_ops se7780_pci_ops;
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh4_pci_ops, &se7780_io_resource, &se7780_mem_resource, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-EXPORT_SYMBOL(board_pci_channels);
-
-static struct sh4_pci_address_map se7780_pci_map = {
-	.window0	= {
-		.base	= SH7780_CS2_BASE_ADDR,
-		.size	= 0x04000000,
-	},
-	.flags  = SH4_PCIC_NO_RESET,
-};
-
-int __init pcibios_init_platform(void)
-{
-	printk("SH7780 PCI: Finished initialization of the PCI controller\n");
-
-	/*
-	 * FPGA PCISEL register initialize
-	 *
-	 *  CPU  || SLOT1 | SLOT2 | S-ATA | USB
-	 *  -------------------------------------
-	 *  INTA || INTA  | INTD  |  --   | INTB
-	 *  -------------------------------------
-	 *  INTB || INTB  | INTA  |  --   | INTC
-	 *  -------------------------------------
-	 *  INTC || INTC  | INTB  | INTA  |  --
-	 *  -------------------------------------
-	 *  INTD || INTD  | INTC  |  --   | INTA
-	 *  -------------------------------------
-	 */
-	ctrl_outw(0x0013, FPGA_PCI_INTSEL1);
-	ctrl_outw(0xE402, FPGA_PCI_INTSEL2);
-
-	return sh7780_pcic_init(&se7780_pci_map);
-}
diff --git a/arch/sh/drivers/pci/ops-sh03.c b/arch/sh/drivers/pci/ops-sh03.c
deleted file mode 100644
index e1703ff5a4d2..000000000000
--- a/arch/sh/drivers/pci/ops-sh03.c
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- * linux/arch/sh/drivers/pci/ops-sh03.c
- *
- * PCI initialization for the Interface CTP/PCI-SH03 board
- */
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include <asm/io.h>
-#include "pci-sh7751.h"
-
-/*
- * Description:  This function sets up and initializes the pcic, sets
- * up the BARS, maps the DRAM into the address space etc, etc.
- */
-int __init pcibios_init_platform(void)
-{
-	__set_io_port_base(SH7751_PCI_IO_BASE);
-	return 1;
-}
-
-static struct resource sh7751_io_resource = {
-	.name   = "SH03 IO",
-	.start  = SH7751_PCI_IO_BASE,
-	.end    = SH7751_PCI_IO_BASE + SH7751_PCI_IO_SIZE - 1,
-	.flags  = IORESOURCE_IO
-};
-
-static struct resource sh7751_mem_resource = {
-	.name   = "SH03 mem",
-	.start  = SH7751_PCI_MEMORY_BASE,
-	.end    = SH7751_PCI_MEMORY_BASE + SH7751_PCI_MEM_SIZE - 1,
-	.flags  = IORESOURCE_MEM
-};
-
-extern struct pci_ops sh4_pci_ops;
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh4_pci_ops, &sh7751_io_resource, &sh7751_mem_resource, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-
diff --git a/arch/sh/drivers/pci/ops-sh4.c b/arch/sh/drivers/pci/ops-sh4.c
index 710a3b0306e5..78bebebdc99c 100644
--- a/arch/sh/drivers/pci/ops-sh4.c
+++ b/arch/sh/drivers/pci/ops-sh4.c
@@ -1,22 +1,22 @@
 /*
  * Generic SH-4 / SH-4A PCIC operations (SH7751, SH7780).
  *
- * Copyright (C) 2002 - 2006  Paul Mundt
+ * Copyright (C) 2002 - 2009  Paul Mundt
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License v2. See the file "COPYING" in the main directory of this archive
  * for more details.
  */
 #include <linux/pci.h>
+#include <linux/io.h>
 #include <asm/addrspace.h>
-#include <asm/io.h>
 #include "pci-sh4.h"
 
 /*
  * Direct access to PCI hardware...
  */
 #define CONFIG_CMD(bus, devfn, where) \
-	P1SEGADDR((bus->number << 16) | (devfn << 8) | (where & ~3))
+	(P1SEG | (bus->number << 16) | (devfn << 8) | (where & ~3))
 
 static DEFINE_SPINLOCK(sh4_pci_lock);
 
@@ -26,6 +26,7 @@ static DEFINE_SPINLOCK(sh4_pci_lock);
 static int sh4_pci_read(struct pci_bus *bus, unsigned int devfn,
 			   int where, int size, u32 *val)
 {
+	struct pci_channel *chan = bus->sysdata;
 	unsigned long flags;
 	u32 data;
 
@@ -34,8 +35,8 @@ static int sh4_pci_read(struct pci_bus *bus, unsigned int devfn,
 	 * so we must do byte alignment by hand
 	 */
 	spin_lock_irqsave(&sh4_pci_lock, flags);
-	pci_write_reg(CONFIG_CMD(bus, devfn, where), SH4_PCIPAR);
-	data = pci_read_reg(SH4_PCIPDR);
+	pci_write_reg(chan, CONFIG_CMD(bus, devfn, where), SH4_PCIPAR);
+	data = pci_read_reg(chan, SH4_PCIPDR);
 	spin_unlock_irqrestore(&sh4_pci_lock, flags);
 
 	switch (size) {
@@ -63,13 +64,14 @@ static int sh4_pci_read(struct pci_bus *bus, unsigned int devfn,
 static int sh4_pci_write(struct pci_bus *bus, unsigned int devfn,
 			 int where, int size, u32 val)
 {
+	struct pci_channel *chan = bus->sysdata;
 	unsigned long flags;
 	int shift;
 	u32 data;
 
 	spin_lock_irqsave(&sh4_pci_lock, flags);
-	pci_write_reg(CONFIG_CMD(bus, devfn, where), SH4_PCIPAR);
-	data = pci_read_reg(SH4_PCIPDR);
+	pci_write_reg(chan, CONFIG_CMD(bus, devfn, where), SH4_PCIPAR);
+	data = pci_read_reg(chan, SH4_PCIPDR);
 	spin_unlock_irqrestore(&sh4_pci_lock, flags);
 
 	switch (size) {
@@ -90,7 +92,7 @@ static int sh4_pci_write(struct pci_bus *bus, unsigned int devfn,
 		return PCIBIOS_FUNC_NOT_SUPPORTED;
 	}
 
-	pci_write_reg(data, SH4_PCIPDR);
+	pci_write_reg(chan, data, SH4_PCIPDR);
 
 	return PCIBIOS_SUCCESSFUL;
 }
@@ -104,66 +106,31 @@ struct pci_ops sh4_pci_ops = {
  * Not really related to pci_ops, but it's common and not worth shoving
  * somewhere else for now..
  */
-static unsigned int pci_probe = PCI_PROBE_CONF1;
-
-int __init sh4_pci_check_direct(void)
+int __init sh4_pci_check_direct(struct pci_channel *chan)
 {
 	/*
 	 * Check if configuration works.
 	 */
-	if (pci_probe & PCI_PROBE_CONF1) {
-		unsigned int tmp = pci_read_reg(SH4_PCIPAR);
+	unsigned int tmp = pci_read_reg(chan, SH4_PCIPAR);
 
-		pci_write_reg(P1SEG, SH4_PCIPAR);
+	pci_write_reg(chan, P1SEG, SH4_PCIPAR);
 
-		if (pci_read_reg(SH4_PCIPAR) == P1SEG) {
-			pci_write_reg(tmp, SH4_PCIPAR);
-			printk(KERN_INFO "PCI: Using configuration type 1\n");
-			request_region(PCI_REG(SH4_PCIPAR), 8, "PCI conf1");
-
-			return 0;
-		}
-
-		pci_write_reg(tmp, SH4_PCIPAR);
+	if (pci_read_reg(chan, SH4_PCIPAR) == P1SEG) {
+		pci_write_reg(chan, tmp, SH4_PCIPAR);
+		printk(KERN_INFO "PCI: Using configuration type 1\n");
+		request_region(chan->reg_base + SH4_PCIPAR, 8,
+			       "PCI conf1");
+		return 0;
 	}
 
-	pr_debug("PCI: pci_check_direct failed\n");
+	pci_write_reg(chan, tmp, SH4_PCIPAR);
+
+	printk(KERN_ERR "PCI: %s failed\n", __func__);
+
 	return -EINVAL;
 }
 
-/* Handle generic fixups */
-static void __init pci_fixup_ide_bases(struct pci_dev *d)
-{
-	int i;
-
-	/*
-	 * PCI IDE controllers use non-standard I/O port decoding, respect it.
-	 */
-	if ((d->class >> 8) != PCI_CLASS_STORAGE_IDE)
-		return;
-	pr_debug("PCI: IDE base address fixup for %s\n", pci_name(d));
-	for(i = 0; i < 4; i++) {
-		struct resource *r = &d->resource[i];
-
-		if ((r->start & ~0x80) == 0x374) {
-			r->start |= 2;
-			r->end = r->start;
-		}
-	}
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_ide_bases);
-
-char * __devinit pcibios_setup(char *str)
-{
-	if (!strcmp(str, "off")) {
-		pci_probe = 0;
-		return NULL;
-	}
-
-	return str;
-}
-
-int __attribute__((weak)) pci_fixup_pcic(void)
+int __attribute__((weak)) pci_fixup_pcic(struct pci_channel *chan)
 {
 	/* Nothing to do. */
 	return 0;
diff --git a/arch/sh/drivers/pci/ops-sh5.c b/arch/sh/drivers/pci/ops-sh5.c
index 729e38a6fe07..4ce95a001b80 100644
--- a/arch/sh/drivers/pci/ops-sh5.c
+++ b/arch/sh/drivers/pci/ops-sh5.c
@@ -22,31 +22,6 @@
 #include <asm/io.h>
 #include "pci-sh5.h"
 
-static void __init pci_fixup_ide_bases(struct pci_dev *d)
-{
-	int i;
-
-	/*
-	 * PCI IDE controllers use non-standard I/O port decoding, respect it.
-	 */
-	if ((d->class >> 8) != PCI_CLASS_STORAGE_IDE)
-		return;
-	printk("PCI: IDE base address fixup for %s\n", pci_name(d));
-	for(i=0; i<4; i++) {
-		struct resource *r = &d->resource[i];
-		if ((r->start & ~0x80) == 0x374) {
-			r->start |= 2;
-			r->end = r->start;
-		}
-	}
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_ide_bases);
-
-char * __devinit pcibios_setup(char *str)
-{
-	return str;
-}
-
 static int sh5pci_read(struct pci_bus *bus, unsigned int devfn, int where,
 			int size, u32 *val)
 {
diff --git a/arch/sh/drivers/pci/ops-sh7785lcr.c b/arch/sh/drivers/pci/ops-sh7785lcr.c
deleted file mode 100644
index fb0869f0bef8..000000000000
--- a/arch/sh/drivers/pci/ops-sh7785lcr.c
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- * Author:  Ian DaSilva (idasilva@mvista.com)
- *
- * Highly leveraged from pci-bigsur.c, written by Dustin McIntire.
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * PCI initialization for the Renesas R0P7785LC0011RL board
- * Based on arch/sh/drivers/pci/ops-r7780rp.c
- *
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/pci.h>
-#include "pci-sh4.h"
-
-static char irq_tab[] __initdata = {
-	65, 66, 67, 68,
-};
-
-int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
-{
-	return irq_tab[slot];
-}
-
-static struct resource sh7785_io_resource = {
-	.name	= "SH7785_IO",
-	.start	= SH7780_PCI_IO_BASE,
-	.end	= SH7780_PCI_IO_BASE + SH7780_PCI_IO_SIZE - 1,
-	.flags	= IORESOURCE_IO
-};
-
-static struct resource sh7785_mem_resource = {
-	.name	= "SH7785_mem",
-	.start	= SH7780_PCI_MEMORY_BASE,
-	.end	= SH7780_PCI_MEMORY_BASE + SH7780_PCI_MEM_SIZE - 1,
-	.flags	= IORESOURCE_MEM
-};
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh4_pci_ops, &sh7785_io_resource, &sh7785_mem_resource, 0, 0xff },
-	{ NULL, NULL, NULL, 0, 0 },
-};
-EXPORT_SYMBOL(board_pci_channels);
-
-static struct sh4_pci_address_map sh7785_pci_map = {
-	.window0	= {
-#if defined(CONFIG_32BIT)
-		.base	= SH7780_32BIT_DDR_BASE_ADDR,
-		.size	= 0x40000000,
-#else
-		.base	= SH7780_CS0_BASE_ADDR,
-		.size	= 0x20000000,
-#endif
-	},
-
-	.flags	= SH4_PCIC_NO_RESET,
-};
-
-int __init pcibios_init_platform(void)
-{
-	return sh7780_pcic_init(&sh7785_pci_map);
-}
diff --git a/arch/sh/drivers/pci/ops-snapgear.c b/arch/sh/drivers/pci/ops-snapgear.c
deleted file mode 100644
index 53dd893d4e54..000000000000
--- a/arch/sh/drivers/pci/ops-snapgear.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * arch/sh/drivers/pci/ops-snapgear.c
- *
- * Author:  David McCullough <davidm@snapgear.com>
- *
- * Ported to new API by Paul Mundt <lethal@linux-sh.org>
- *
- * Highly leveraged from pci-bigsur.c, written by Dustin McIntire.
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * PCI initialization for the SnapGear boards
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include "pci-sh4.h"
-
-#define SNAPGEAR_PCI_IO		0x4000
-#define SNAPGEAR_PCI_MEM	0xfd000000
-
-/* PCI: default LOCAL memory window sizes (seen from PCI bus) */
-#define SNAPGEAR_LSR0_SIZE    (64*(1<<20)) //64MB
-#define SNAPGEAR_LSR1_SIZE    (64*(1<<20)) //64MB
-
-static struct resource sh7751_io_resource = {
-	.name		= "SH7751 IO",
-	.start		= SNAPGEAR_PCI_IO,
-	.end		= SNAPGEAR_PCI_IO + (64*1024) - 1, /* 64KiB I/O */
-	.flags		= IORESOURCE_IO,
-};
-
-static struct resource sh7751_mem_resource = {
-	.name		= "SH7751 mem",
-	.start		= SNAPGEAR_PCI_MEM,
-	.end		= SNAPGEAR_PCI_MEM + (64*1024*1024) - 1, /* 64MiB mem */
-	.flags		= IORESOURCE_MEM,
-};
-
-struct pci_channel board_pci_channels[] = {
-	{ &sh4_pci_ops, &sh7751_io_resource, &sh7751_mem_resource, 0, 0xff },
-	{ 0, }
-};
-
-static struct sh4_pci_address_map sh7751_pci_map = {
-	.window0	= {
-		.base	= SH7751_CS2_BASE_ADDR,
-		.size	= SNAPGEAR_LSR0_SIZE,
-	},
-
-	.window1	= {
-		.base	= SH7751_CS2_BASE_ADDR,
-		.size	= SNAPGEAR_LSR1_SIZE,
-	},
-
-	.flags	= SH4_PCIC_NO_RESET,
-};
-
-/*
- * Initialize the SnapGear PCI interface
- * Setup hardware to be Central Funtion
- * Copy the BSR regs to the PCI interface
- * Setup PCI windows into local RAM
- */
-int __init pcibios_init_platform(void)
-{
-	return sh7751_pcic_init(&sh7751_pci_map);
-}
-
-int __init pcibios_map_platform_irq(struct pci_dev *pdev, u8 slot, u8 pin)
-{
-	int irq = -1;
-
-	switch (slot) {
-	case 8:  /* the PCI bridge */ break;
-	case 11: irq = 8;  break; /* USB    */
-	case 12: irq = 11; break; /* PCMCIA */
-	case 13: irq = 5;  break; /* eth0   */
-	case 14: irq = 8;  break; /* eth1   */
-	case 15: irq = 11; break; /* safenet (unused) */
-	}
-
-	printk("PCI: Mapping SnapGear IRQ for slot %d, pin %c to irq %d\n",
-	       slot, pin - 1 + 'A', irq);
-
-	return irq;
-}
-
-void __init pcibios_fixup(void)
-{
-	/* Nothing to fixup .. */
-}
diff --git a/arch/sh/drivers/pci/pci-auto.c b/arch/sh/drivers/pci/pci-auto.c
deleted file mode 100644
index cf48b12ee58c..000000000000
--- a/arch/sh/drivers/pci/pci-auto.c
+++ /dev/null
@@ -1,545 +0,0 @@
-/*
- * PCI autoconfiguration library
- *
- * Author: Matt Porter <mporter@mvista.com>
- *
- * Copyright 2000, 2001 MontaVista Software Inc.
- * Copyright 2001 Bradley D. LaRonde <brad@ltc.com>
- * Copyright 2003 Paul Mundt <lethal@linux-sh.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-/*
- * Modified for MIPS by Jun Sun, jsun@mvista.com
- *
- * . Simplify the interface between pci_auto and the rest: a single function.
- * . Assign resources from low address to upper address.
- * . change most int to u32.
- *
- * Further modified to include it as mips generic code, ppopov@mvista.com.
- *
- * 2001-10-26  Bradley D. LaRonde <brad@ltc.com>
- * - Add a top_bus argument to the "early config" functions so that
- *   they can set a fake parent bus pointer to convince the underlying
- *   pci ops to use type 1 configuration for sub busses.
- * - Set bridge base and limit registers correctly.
- * - Align io and memory base properly before and after bridge setup.
- * - Don't fall through to pci_setup_bars for bridge.
- * - Reformat the debug output to look more like lspci's output.
- *
- * Cloned for SuperH by M. R. Brown, mrbrown@0xd6.org
- *
- * 2003-08-05  Paul Mundt <lethal@linux-sh.org>
- * - Don't update the BAR values on systems that already have valid addresses
- *   and don't want these updated for whatever reason, by way of a new config
- *   option check. However, we still read in the old BAR values so that they
- *   can still be reported through the debug output.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/pci.h>
-
-#define	DEBUG
-#ifdef	DEBUG
-#define	DBG(x...)	printk(x)
-#else
-#define	DBG(x...)
-#endif
-
-/*
- * These functions are used early on before PCI scanning is done
- * and all of the pci_dev and pci_bus structures have been created.
- */
-static struct pci_dev *fake_pci_dev(struct pci_channel *hose,
-	int top_bus, int busnr, int devfn)
-{
-	static struct pci_dev dev;
-	static struct pci_bus bus;
-
-	dev.bus = &bus;
-	dev.sysdata = hose;
-	dev.devfn = devfn;
-	bus.number = busnr;
-	bus.ops = hose->pci_ops;
-
-	if(busnr != top_bus)
-		/* Fake a parent bus structure. */
-		bus.parent = &bus;
-	else
-		bus.parent = NULL;
-
-	return &dev;
-}
-
-#define EARLY_PCI_OP(rw, size, type)					\
-static int early_##rw##_config_##size(struct pci_channel *hose,		\
-	int top_bus, int bus, int devfn, int offset, type value)	\
-{									\
-	return pci_##rw##_config_##size(				\
-		fake_pci_dev(hose, top_bus, bus, devfn),		\
-		offset, value);						\
-}
-
-EARLY_PCI_OP(read, byte, u8 *)
-EARLY_PCI_OP(read, word, u16 *)
-EARLY_PCI_OP(read, dword, u32 *)
-EARLY_PCI_OP(write, byte, u8)
-EARLY_PCI_OP(write, word, u16)
-EARLY_PCI_OP(write, dword, u32)
-
-static struct resource *io_resource_inuse;
-static struct resource *mem_resource_inuse;
-
-static u32 pciauto_lower_iospc;
-static u32 pciauto_upper_iospc;
-
-static u32 pciauto_lower_memspc;
-static u32 pciauto_upper_memspc;
-
-static void __init
-pciauto_setup_bars(struct pci_channel *hose,
-		   int top_bus,
-		   int current_bus,
-		   int pci_devfn,
-		   int bar_limit)
-{
-	u32 bar_response, bar_size, bar_value;
-	u32 bar, addr_mask, bar_nr = 0;
-	u32 * upper_limit;
-	u32 * lower_limit;
-	int found_mem64 = 0;
-
-	for (bar = PCI_BASE_ADDRESS_0; bar <= bar_limit; bar+=4) {
-		u32 bar_addr;
-
-		/* Read the old BAR value */
-		early_read_config_dword(hose, top_bus,
-					current_bus,
-					pci_devfn,
-					bar,
-					&bar_addr);
-
-		/* Tickle the BAR and get the response */
-		early_write_config_dword(hose, top_bus,
-					 current_bus,
-					 pci_devfn,
-					 bar,
-					 0xffffffff);
-
-		early_read_config_dword(hose, top_bus,
-					current_bus,
-					pci_devfn,
-					bar,
-					&bar_response);
-
-		/*
-		 * Write the old BAR value back out, only update the BAR
-		 * if we implicitly want resources to be updated, which
-		 * is done by the generic code further down. -- PFM.
-		 */
-		early_write_config_dword(hose, top_bus,
-					 current_bus,
-					 pci_devfn,
-					 bar,
-					 bar_addr);
-
-		/* If BAR is not implemented go to the next BAR */
-		if (!bar_response)
-			continue;
-
-		/*
-		 * Workaround for a BAR that doesn't use its upper word,
-		 * like the ALi 1535D+ PCI DC-97 Controller Modem (M5457).
-		 * bdl <brad@ltc.com>
-		 */
-		if (!(bar_response & 0xffff0000))
-			bar_response |= 0xffff0000;
-
-retry:
-		/* Check the BAR type and set our address mask */
-		if (bar_response & PCI_BASE_ADDRESS_SPACE) {
-			addr_mask = PCI_BASE_ADDRESS_IO_MASK;
-			upper_limit = &pciauto_upper_iospc;
-			lower_limit = &pciauto_lower_iospc;
-			DBG("        I/O");
-		} else {
-			if ((bar_response & PCI_BASE_ADDRESS_MEM_TYPE_MASK) ==
-			    PCI_BASE_ADDRESS_MEM_TYPE_64)
-				found_mem64 = 1;
-
-			addr_mask = PCI_BASE_ADDRESS_MEM_MASK;
-			upper_limit = &pciauto_upper_memspc;
-			lower_limit = &pciauto_lower_memspc;
-			DBG("        Mem");
-		}
-
-
-		/* Calculate requested size */
-		bar_size = ~(bar_response & addr_mask) + 1;
-
-		/* Allocate a base address */
-		bar_value = ((*lower_limit - 1) & ~(bar_size - 1)) + bar_size;
-
-		if ((bar_value + bar_size) > *upper_limit) {
-			if (bar_response & PCI_BASE_ADDRESS_SPACE) {
-				if (io_resource_inuse->child) {
-					io_resource_inuse =
-						io_resource_inuse->child;
-					pciauto_lower_iospc =
-						io_resource_inuse->start;
-					pciauto_upper_iospc =
-						io_resource_inuse->end + 1;
-					goto retry;
-				}
-
-			} else {
-				if (mem_resource_inuse->child) {
-					mem_resource_inuse =
-						mem_resource_inuse->child;
-					pciauto_lower_memspc =
-						mem_resource_inuse->start;
-					pciauto_upper_memspc =
-						mem_resource_inuse->end + 1;
-					goto retry;
-				}
-			}
-			DBG(" unavailable -- skipping, value %x size %x\n",
-					bar_value, bar_size);
-			continue;
-		}
-
-		if (bar_value < *lower_limit || (bar_value + bar_size) >= *upper_limit) {
-			DBG(" unavailable -- skipping, value %x size %x\n",
-					bar_value, bar_size);
-			continue;
-		}
-
-#ifdef CONFIG_PCI_AUTO_UPDATE_RESOURCES
-		/* Write it out and update our limit */
-		early_write_config_dword(hose, top_bus, current_bus, pci_devfn,
-					 bar, bar_value);
-#endif
-
-		*lower_limit = bar_value + bar_size;
-
-		/*
-		 * If we are a 64-bit decoder then increment to the
-		 * upper 32 bits of the bar and force it to locate
-		 * in the lower 4GB of memory.
-		 */
-		if (found_mem64) {
-			bar += 4;
-			early_write_config_dword(hose, top_bus,
-						 current_bus,
-						 pci_devfn,
-						 bar,
-						 0x00000000);
-		}
-
-		DBG(" at 0x%.8x [size=0x%x]\n", bar_value, bar_size);
-
-		bar_nr++;
-	}
-
-}
-
-static void __init
-pciauto_prescan_setup_bridge(struct pci_channel *hose,
-			     int top_bus,
-			     int current_bus,
-			     int pci_devfn,
-			     int sub_bus)
-{
-	/* Configure bus number registers */
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-	                        PCI_PRIMARY_BUS, current_bus);
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-				PCI_SECONDARY_BUS, sub_bus + 1);
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-				PCI_SUBORDINATE_BUS, 0xff);
-
-	/* Align memory and I/O to 1MB and 4KB boundaries. */
-	pciauto_lower_memspc = (pciauto_lower_memspc + (0x100000 - 1))
-		& ~(0x100000 - 1);
-	pciauto_lower_iospc = (pciauto_lower_iospc + (0x1000 - 1))
-		& ~(0x1000 - 1);
-
-	/* Set base (lower limit) of address range behind bridge. */
-	early_write_config_word(hose, top_bus, current_bus, pci_devfn,
-		PCI_MEMORY_BASE, pciauto_lower_memspc >> 16);
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-		PCI_IO_BASE, (pciauto_lower_iospc & 0x0000f000) >> 8);
-	early_write_config_word(hose, top_bus, current_bus, pci_devfn,
-		PCI_IO_BASE_UPPER16, pciauto_lower_iospc >> 16);
-
-	/* We don't support prefetchable memory for now, so disable */
-	early_write_config_word(hose, top_bus, current_bus, pci_devfn,
-				PCI_PREF_MEMORY_BASE, 0);
-	early_write_config_word(hose, top_bus, current_bus, pci_devfn,
-				PCI_PREF_MEMORY_LIMIT, 0);
-}
-
-static void __init
-pciauto_postscan_setup_bridge(struct pci_channel *hose,
-			      int top_bus,
-			      int current_bus,
-			      int pci_devfn,
-			      int sub_bus)
-{
-	u32 temp;
-
-	/*
-	 * [jsun] we always bump up baselines a little, so that if there
-	 * nothing behind P2P bridge, we don't wind up overlapping IO/MEM
-	 * spaces.
-	 */
-	pciauto_lower_memspc += 1;
-	pciauto_lower_iospc += 1;
-
-	/* Configure bus number registers */
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-				PCI_SUBORDINATE_BUS, sub_bus);
-
-	/* Set upper limit of address range behind bridge. */
-	early_write_config_word(hose, top_bus, current_bus, pci_devfn,
-		PCI_MEMORY_LIMIT, pciauto_lower_memspc >> 16);
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-		PCI_IO_LIMIT, (pciauto_lower_iospc & 0x0000f000) >> 8);
-	early_write_config_word(hose, top_bus, current_bus, pci_devfn,
-		PCI_IO_LIMIT_UPPER16, pciauto_lower_iospc >> 16);
-
-	/* Align memory and I/O to 1MB and 4KB boundaries. */
-	pciauto_lower_memspc = (pciauto_lower_memspc + (0x100000 - 1))
-		& ~(0x100000 - 1);
-	pciauto_lower_iospc = (pciauto_lower_iospc + (0x1000 - 1))
-		& ~(0x1000 - 1);
-
-	/* Enable memory and I/O accesses, enable bus master */
-	early_read_config_dword(hose, top_bus, current_bus, pci_devfn,
-		PCI_COMMAND, &temp);
-	early_write_config_dword(hose, top_bus, current_bus, pci_devfn,
-		PCI_COMMAND, temp | PCI_COMMAND_IO | PCI_COMMAND_MEMORY
-		| PCI_COMMAND_MASTER);
-}
-
-static void __init
-pciauto_prescan_setup_cardbus_bridge(struct pci_channel *hose,
-			int top_bus,
-			int current_bus,
-			int pci_devfn,
-			int sub_bus)
-{
-	/* Configure bus number registers */
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-				PCI_PRIMARY_BUS, current_bus);
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-				PCI_SECONDARY_BUS, sub_bus + 1);
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-				PCI_SUBORDINATE_BUS, 0xff);
-
-	/* Align memory and I/O to 4KB and 4 byte boundaries. */
-	pciauto_lower_memspc = (pciauto_lower_memspc + (0x1000 - 1))
-		& ~(0x1000 - 1);
-	pciauto_lower_iospc = (pciauto_lower_iospc + (0x4 - 1))
-		& ~(0x4 - 1);
-
-	early_write_config_dword(hose, top_bus, current_bus, pci_devfn,
-		PCI_CB_MEMORY_BASE_0, pciauto_lower_memspc);
-	early_write_config_dword(hose, top_bus, current_bus, pci_devfn,
-		PCI_CB_IO_BASE_0, pciauto_lower_iospc);
-}
-
-static void __init
-pciauto_postscan_setup_cardbus_bridge(struct pci_channel *hose,
-			int top_bus,
-			int current_bus,
-			int pci_devfn,
-			int sub_bus)
-{
-	u32 temp;
-
-	/*
-	 * [jsun] we always bump up baselines a little, so that if there
-	 * nothing behind P2P bridge, we don't wind up overlapping IO/MEM
-	 * spaces.
-	 */
-	pciauto_lower_memspc += 1;
-	pciauto_lower_iospc += 1;
-
-	/*
-	 * Configure subordinate bus number.  The PCI subsystem
-	 * bus scan will renumber buses (reserving three additional
-	 * for this PCI<->CardBus bridge for the case where a CardBus
-	 * adapter contains a P2P or CB2CB bridge.
-	 */
-
-	early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-				PCI_SUBORDINATE_BUS, sub_bus);
-
-	/*
-	 * Reserve an additional 4MB for mem space and 16KB for
-	 * I/O space.  This should cover any additional space
-	 * requirement of unusual CardBus devices with
-	 * additional bridges that can consume more address space.
-	 *
-	 * Although pcmcia-cs currently will reprogram bridge
-	 * windows, the goal is to add an option to leave them
-	 * alone and use the bridge window ranges as the regions
-	 * that are searched for free resources upon hot-insertion
-	 * of a device.  This will allow a PCI<->CardBus bridge
-	 * configured by this routine to happily live behind a
-	 * P2P bridge in a system.
-	 */
-	/* Align memory and I/O to 4KB and 4 byte boundaries. */
-	pciauto_lower_memspc = (pciauto_lower_memspc + (0x1000 - 1))
-		& ~(0x1000 - 1);
-	pciauto_lower_iospc = (pciauto_lower_iospc + (0x4 - 1))
-		& ~(0x4 - 1);
-	/* Set up memory and I/O filter limits, assume 32-bit I/O space */
-	early_write_config_dword(hose, top_bus, current_bus, pci_devfn,
-		PCI_CB_MEMORY_LIMIT_0, pciauto_lower_memspc - 1);
-	early_write_config_dword(hose, top_bus, current_bus, pci_devfn,
-		PCI_CB_IO_LIMIT_0, pciauto_lower_iospc - 1);
-
-	/* Enable memory and I/O accesses, enable bus master */
-	early_read_config_dword(hose, top_bus, current_bus, pci_devfn,
-		PCI_COMMAND, &temp);
-	early_write_config_dword(hose, top_bus, current_bus, pci_devfn,
-		PCI_COMMAND, temp | PCI_COMMAND_IO | PCI_COMMAND_MEMORY |
-		PCI_COMMAND_MASTER);
-}
-
-#define	PCIAUTO_IDE_MODE_MASK		0x05
-
-static int __init
-pciauto_bus_scan(struct pci_channel *hose, int top_bus, int current_bus)
-{
-	int sub_bus;
-	u32 pci_devfn, pci_class, cmdstat, found_multi=0;
-	unsigned short vid, did;
-	unsigned char header_type;
-	int devfn_start = 0;
-	int devfn_stop = 0xff;
-
-	sub_bus = current_bus;
-
-	if (hose->first_devfn)
-		devfn_start = hose->first_devfn;
-	if (hose->last_devfn)
-		devfn_stop = hose->last_devfn;
-
-	for (pci_devfn=devfn_start; pci_devfn<devfn_stop; pci_devfn++) {
-
-		if (PCI_FUNC(pci_devfn) && !found_multi)
-			continue;
-
-		early_read_config_word(hose, top_bus, current_bus, pci_devfn,
-				       PCI_VENDOR_ID, &vid);
-
-		if (vid == 0xffff) continue;
-
-		early_read_config_byte(hose, top_bus, current_bus, pci_devfn,
-				       PCI_HEADER_TYPE, &header_type);
-
-		if (!PCI_FUNC(pci_devfn))
-			found_multi = header_type & 0x80;
-
-		early_read_config_word(hose, top_bus, current_bus, pci_devfn,
-				       PCI_DEVICE_ID, &did);
-
-		early_read_config_dword(hose, top_bus, current_bus, pci_devfn,
-					PCI_CLASS_REVISION, &pci_class);
-
-		DBG("%.2x:%.2x.%x Class %.4x: %.4x:%.4x",
-			current_bus, PCI_SLOT(pci_devfn), PCI_FUNC(pci_devfn),
-			pci_class >> 16, vid, did);
-		if (pci_class & 0xff)
-			DBG(" (rev %.2x)", pci_class & 0xff);
-		DBG("\n");
-
-		if ((pci_class >> 16) == PCI_CLASS_BRIDGE_PCI) {
-			DBG("        Bridge: primary=%.2x, secondary=%.2x\n",
-				current_bus, sub_bus + 1);
-			pciauto_prescan_setup_bridge(hose, top_bus, current_bus,
-						     pci_devfn, sub_bus);
-			DBG("Scanning sub bus %.2x, I/O 0x%.8x, Mem 0x%.8x\n",
-				sub_bus + 1,
-				pciauto_lower_iospc, pciauto_lower_memspc);
-			sub_bus = pciauto_bus_scan(hose, top_bus, sub_bus+1);
-			DBG("Back to bus %.2x\n", current_bus);
-			pciauto_postscan_setup_bridge(hose, top_bus, current_bus,
-							pci_devfn, sub_bus);
-			continue;
-		} else if ((pci_class >> 16) == PCI_CLASS_BRIDGE_CARDBUS) {
-			DBG("  CARDBUS  Bridge: primary=%.2x, secondary=%.2x\n",
-				current_bus, sub_bus + 1);
-			DBG("PCI Autoconfig: Found CardBus bridge, device %d function %d\n", PCI_SLOT(pci_devfn), PCI_FUNC(pci_devfn));
-			/* Place CardBus Socket/ExCA registers */
-			pciauto_setup_bars(hose, top_bus, current_bus, pci_devfn, PCI_BASE_ADDRESS_0);
-
-			pciauto_prescan_setup_cardbus_bridge(hose, top_bus,
-					current_bus, pci_devfn, sub_bus);
-
-			DBG("Scanning sub bus %.2x, I/O 0x%.8x, Mem 0x%.8x\n",
-				sub_bus + 1,
-				pciauto_lower_iospc, pciauto_lower_memspc);
-			sub_bus = pciauto_bus_scan(hose, top_bus, sub_bus+1);
-			DBG("Back to bus %.2x, sub_bus is %x\n", current_bus, sub_bus);
-			pciauto_postscan_setup_cardbus_bridge(hose, top_bus,
-					current_bus, pci_devfn, sub_bus);
-			continue;
-		} else if ((pci_class >> 16) == PCI_CLASS_STORAGE_IDE) {
-
-			unsigned char prg_iface;
-
-			early_read_config_byte(hose, top_bus, current_bus,
-				pci_devfn, PCI_CLASS_PROG, &prg_iface);
-			if (!(prg_iface & PCIAUTO_IDE_MODE_MASK)) {
-				DBG("Skipping legacy mode IDE controller\n");
-				continue;
-			}
-		}
-
-		/*
-		 * Found a peripheral, enable some standard
-		 * settings
-		 */
-		early_read_config_dword(hose, top_bus, current_bus, pci_devfn,
-					PCI_COMMAND, &cmdstat);
-		early_write_config_dword(hose, top_bus, current_bus, pci_devfn,
-					 PCI_COMMAND, cmdstat | PCI_COMMAND_IO |
-					 PCI_COMMAND_MEMORY |
-					 PCI_COMMAND_MASTER);
-		early_write_config_byte(hose, top_bus, current_bus, pci_devfn,
-					PCI_LATENCY_TIMER, 0x80);
-
-		/* Allocate PCI I/O and/or memory space */
-		pciauto_setup_bars(hose, top_bus, current_bus, pci_devfn, PCI_BASE_ADDRESS_5);
-	}
-	return sub_bus;
-}
-
-int __init
-pciauto_assign_resources(int busno, struct pci_channel *hose)
-{
-	/* setup resource limits */
-	io_resource_inuse = hose->io_resource;
-	mem_resource_inuse = hose->mem_resource;
-
-	pciauto_lower_iospc = io_resource_inuse->start;
-	pciauto_upper_iospc = io_resource_inuse->end + 1;
-	pciauto_lower_memspc = mem_resource_inuse->start;
-	pciauto_upper_memspc = mem_resource_inuse->end + 1;
-	DBG("Autoconfig PCI channel 0x%p\n", hose);
-	DBG("Scanning bus %.2x, I/O 0x%.8x:0x%.8x, Mem 0x%.8x:0x%.8x\n",
-		busno, pciauto_lower_iospc, pciauto_upper_iospc, 
-		pciauto_lower_memspc, pciauto_upper_memspc);
-
-	return pciauto_bus_scan(hose, busno, busno);
-}
diff --git a/arch/sh/drivers/pci/pci-dreamcast.c b/arch/sh/drivers/pci/pci-dreamcast.c
new file mode 100644
index 000000000000..210f9d4af141
--- /dev/null
+++ b/arch/sh/drivers/pci/pci-dreamcast.c
@@ -0,0 +1,102 @@
+/*
+ * PCI support for the Sega Dreamcast
+ *
+ * Copyright (C) 2001, 2002  M. R. Brown
+ * Copyright (C) 2002, 2003  Paul Mundt
+ *
+ * This file originally bore the message (with enclosed-$):
+ *	Id: pci.c,v 1.3 2003/05/04 19:29:46 lethal Exp
+ *	Dreamcast PCI: Supports SEGA Broadband Adaptor only.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <mach/pci.h>
+
+static struct resource gapspci_io_resource = {
+	.name	= "GAPSPCI IO",
+	.start	= GAPSPCI_BBA_CONFIG,
+	.end	= GAPSPCI_BBA_CONFIG + GAPSPCI_BBA_CONFIG_SIZE - 1,
+	.flags	= IORESOURCE_IO,
+};
+
+static struct resource gapspci_mem_resource = {
+	.name	= "GAPSPCI mem",
+	.start	= GAPSPCI_DMA_BASE,
+	.end	= GAPSPCI_DMA_BASE + GAPSPCI_DMA_SIZE - 1,
+	.flags	= IORESOURCE_MEM,
+};
+
+static struct pci_channel dreamcast_pci_controller = {
+	.pci_ops	= &gapspci_pci_ops,
+	.io_resource	= &gapspci_io_resource,
+	.io_offset	= 0x00000000,
+	.mem_resource	= &gapspci_mem_resource,
+	.mem_offset	= 0x00000000,
+};
+
+/*
+ * gapspci init
+ */
+
+static int __init gapspci_init(void)
+{
+	char idbuf[16];
+	int i;
+
+	/*
+	 * FIXME: All of this wants documenting to some degree,
+	 * even some basic register definitions would be nice.
+	 *
+	 * I haven't seen anything this ugly since.. maple.
+	 */
+
+	for (i=0; i<16; i++)
+		idbuf[i] = inb(GAPSPCI_REGS+i);
+
+	if (strncmp(idbuf, "GAPSPCI_BRIDGE_2", 16))
+		return -ENODEV;
+
+	outl(0x5a14a501, GAPSPCI_REGS+0x18);
+
+	for (i=0; i<1000000; i++)
+		cpu_relax();
+
+	if (inl(GAPSPCI_REGS+0x18) != 1)
+		return -EINVAL;
+
+	outl(0x01000000, GAPSPCI_REGS+0x20);
+	outl(0x01000000, GAPSPCI_REGS+0x24);
+
+	outl(GAPSPCI_DMA_BASE, GAPSPCI_REGS+0x28);
+	outl(GAPSPCI_DMA_BASE+GAPSPCI_DMA_SIZE, GAPSPCI_REGS+0x2c);
+
+	outl(1, GAPSPCI_REGS+0x14);
+	outl(1, GAPSPCI_REGS+0x34);
+
+	/* Setting Broadband Adapter */
+	outw(0xf900, GAPSPCI_BBA_CONFIG+0x06);
+	outl(0x00000000, GAPSPCI_BBA_CONFIG+0x30);
+	outb(0x00, GAPSPCI_BBA_CONFIG+0x3c);
+	outb(0xf0, GAPSPCI_BBA_CONFIG+0x0d);
+	outw(0x0006, GAPSPCI_BBA_CONFIG+0x04);
+	outl(0x00002001, GAPSPCI_BBA_CONFIG+0x10);
+	outl(0x01000000, GAPSPCI_BBA_CONFIG+0x14);
+
+	register_pci_controller(&dreamcast_pci_controller);
+
+	return 0;
+}
+arch_initcall(gapspci_init);
diff --git a/arch/sh/drivers/pci/pci-sh4.h b/arch/sh/drivers/pci/pci-sh4.h
index a83dcf70c13b..3d5296cde622 100644
--- a/arch/sh/drivers/pci/pci-sh4.h
+++ b/arch/sh/drivers/pci/pci-sh4.h
@@ -149,13 +149,10 @@
   #define SH4_PCIPDTR_PB0	  0x000000001	/* Port 0 Enable */
 #define SH4_PCIPDR		0x220		/* Port IO Data Register */
 
-/* Flags */
-#define SH4_PCIC_NO_RESET	0x0001
-
 /* arch/sh/kernel/drivers/pci/ops-sh4.c */
 extern struct pci_ops sh4_pci_ops;
-int sh4_pci_check_direct(void);
-int pci_fixup_pcic(void);
+int sh4_pci_check_direct(struct pci_channel *chan);
+int pci_fixup_pcic(struct pci_channel *chan);
 
 struct sh4_pci_address_space {
 	unsigned long base;
@@ -165,16 +162,18 @@ struct sh4_pci_address_space {
 struct sh4_pci_address_map {
 	struct sh4_pci_address_space window0;
 	struct sh4_pci_address_space window1;
-	unsigned long flags;
 };
 
-static inline void pci_write_reg(unsigned long val, unsigned long reg)
+static inline void pci_write_reg(struct pci_channel *chan,
+				 unsigned long val, unsigned long reg)
 {
-	ctrl_outl(val, PCI_REG(reg));
+	ctrl_outl(val, chan->reg_base + reg);
 }
 
-static inline unsigned long pci_read_reg(unsigned long reg)
+static inline unsigned long pci_read_reg(struct pci_channel *chan,
+					 unsigned long reg)
 {
-	return ctrl_inl(PCI_REG(reg));
+	return ctrl_inl(chan->reg_base + reg);
 }
+
 #endif /* __PCI_SH4_H */
diff --git a/arch/sh/drivers/pci/pci-sh5.c b/arch/sh/drivers/pci/pci-sh5.c
index 7a97438762c8..873ed2b44055 100644
--- a/arch/sh/drivers/pci/pci-sh5.c
+++ b/arch/sh/drivers/pci/pci-sh5.c
@@ -89,8 +89,21 @@ static irqreturn_t pcish5_serr_irq(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
-int __init sh5pci_init(unsigned long memStart, unsigned long memSize)
+static struct resource sh5_io_resource = { /* place holder */ };
+static struct resource sh5_mem_resource = { /* place holder */ };
+
+static struct pci_channel sh5pci_controller = {
+	.pci_ops		= &sh5_pci_ops,
+	.mem_resource		= &sh5_mem_resource,
+	.mem_offset		= 0x00000000,
+	.io_resource		= &sh5_io_resource,
+	.io_offset		= 0x00000000,
+};
+
+static int __init sh5pci_init(void)
 {
+	unsigned long memStart = __pa(memory_start);
+	unsigned long memSize = __pa(memory_end) - memStart;
 	u32 lsr0;
 	u32 uval;
 
@@ -106,12 +119,12 @@ int __init sh5pci_init(unsigned long memStart, unsigned long memSize)
                 return -EINVAL;
         }
 
-	pcicr_virt = onchip_remap(SH5PCI_ICR_BASE, 1024, "PCICR");
+	pcicr_virt = (unsigned long)ioremap_nocache(SH5PCI_ICR_BASE, 1024);
 	if (!pcicr_virt) {
 		panic("Unable to remap PCICR\n");
 	}
 
-	PCI_IO_AREA = onchip_remap(SH5PCI_IO_BASE, 0x10000, "PCIIO");
+	PCI_IO_AREA = (unsigned long)ioremap_nocache(SH5PCI_IO_BASE, 0x10000);
 	if (!PCI_IO_AREA) {
 		panic("Unable to remap PCIIO\n");
 	}
@@ -197,32 +210,14 @@ int __init sh5pci_init(unsigned long memStart, unsigned long memSize)
         SH5PCI_WRITE(AINTM, ~0);
         SH5PCI_WRITE(PINTM, ~0);
 
+	sh5_io_resource.start = PCI_IO_AREA;
+	sh5_io_resource.end = PCI_IO_AREA + 0x10000;
+
+	sh5_mem_resource.start = memStart;
+	sh5_mem_resource.end = memStart + memSize;
+
+	register_pci_controller(&sh5pci_controller);
+
 	return 0;
 }
-
-void __devinit pcibios_fixup_bus(struct pci_bus *bus)
-{
-	struct pci_dev *dev = bus->self;
-	int i;
-
-	if (dev) {
-		for (i= 0; i < 3; i++) {
-			bus->resource[i] =
-				&dev->resource[PCI_BRIDGE_RESOURCES+i];
-			bus->resource[i]->name = bus->name;
-		}
-		bus->resource[0]->flags |= IORESOURCE_IO;
-		bus->resource[1]->flags |= IORESOURCE_MEM;
-
-		/* For now, propagate host limits to the bus;
-		 * we'll adjust them later. */
-		bus->resource[0]->end = 64*1024 - 1 ;
-		bus->resource[1]->end = PCIBIOS_MIN_MEM+(256*1024*1024)-1;
-		bus->resource[0]->start = PCIBIOS_MIN_IO;
-		bus->resource[1]->start = PCIBIOS_MIN_MEM;
-
-		/* Turn off downstream PF memory address range by default */
-		bus->resource[2]->start = 1024*1024;
-		bus->resource[2]->end = bus->resource[2]->start - 1;
-	}
-}
+arch_initcall(sh5pci_init);
diff --git a/arch/sh/drivers/pci/pci-sh5.h b/arch/sh/drivers/pci/pci-sh5.h
index 7cff3fc04d30..f277628221f3 100644
--- a/arch/sh/drivers/pci/pci-sh5.h
+++ b/arch/sh/drivers/pci/pci-sh5.h
@@ -107,7 +107,4 @@ extern unsigned long pcicr_virt;
 
 extern struct pci_ops sh5_pci_ops;
 
-/* arch/sh/drivers/pci/pci-sh5.c */
-int sh5pci_init(unsigned long memStart, unsigned long memSize);
-
 #endif /* __PCI_SH5_H */
diff --git a/arch/sh/drivers/pci/pci-sh7751.c b/arch/sh/drivers/pci/pci-sh7751.c
index 3065eb184f01..70c1999a0ec4 100644
--- a/arch/sh/drivers/pci/pci-sh7751.c
+++ b/arch/sh/drivers/pci/pci-sh7751.c
@@ -1,114 +1,111 @@
 /*
- *	Low-Level PCI Support for the SH7751
+ * Low-Level PCI Support for the SH7751
  *
- *  Dustin McIntire (dustin@sensoria.com)
- *	Derived from arch/i386/kernel/pci-*.c which bore the message:
- *	(c) 1999--2000 Martin Mares <mj@ucw.cz>
+ *  Copyright (C) 2003 - 2009  Paul Mundt
+ *  Copyright (C) 2001  Dustin McIntire
  *
- *  Ported to the new API by Paul Mundt <lethal@linux-sh.org>
- *  With cleanup by Paul van Gool <pvangool@mimotech.com>
- *
- *  May be copied or modified under the terms of the GNU General Public
- *  License.  See linux/COPYING for more information.
+ *  With cleanup by Paul van Gool <pvangool@mimotech.com>, 2003.
  *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
  */
-#undef DEBUG
-
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <linux/delay.h>
+#include <linux/io.h>
 #include "pci-sh4.h"
 #include <asm/addrspace.h>
-#include <asm/io.h>
 
-/*
- * Initialization. Try all known PCI access methods. Note that we support
- * using both PCI BIOS and direct access: in such cases, we use I/O ports
- * to access config space.
- *
- * Note that the platform specific initialization (BSC registers, and memory
- * space mapping) will be called via the platform defined function
- * pcibios_init_platform().
- */
+static int __init __area_sdram_check(struct pci_channel *chan,
+				     unsigned int area)
+{
+	unsigned long word;
+
+	word = __raw_readl(SH7751_BCR1);
+	/* check BCR for SDRAM in area */
+	if (((word >> area) & 1) == 0) {
+		printk("PCI: Area %d is not configured for SDRAM. BCR1=0x%lx\n",
+		       area, word);
+		return 0;
+	}
+	pci_write_reg(chan, word, SH4_PCIBCR1);
+
+	word = __raw_readw(SH7751_BCR2);
+	/* check BCR2 for 32bit SDRAM interface*/
+	if (((word >> (area << 1)) & 0x3) != 0x3) {
+		printk("PCI: Area %d is not 32 bit SDRAM. BCR2=0x%lx\n",
+		       area, word);
+		return 0;
+	}
+	pci_write_reg(chan, word, SH4_PCIBCR2);
+
+	return 1;
+}
+
+static struct resource sh7751_io_resource = {
+	.name	= "SH7751_IO",
+	.start	= SH7751_PCI_IO_BASE,
+	.end	= SH7751_PCI_IO_BASE + SH7751_PCI_IO_SIZE - 1,
+	.flags	= IORESOURCE_IO
+};
+
+static struct resource sh7751_mem_resource = {
+	.name	= "SH7751_mem",
+	.start	= SH7751_PCI_MEMORY_BASE,
+	.end	= SH7751_PCI_MEMORY_BASE + SH7751_PCI_MEM_SIZE - 1,
+	.flags	= IORESOURCE_MEM
+};
+
+static struct pci_channel sh7751_pci_controller = {
+	.pci_ops	= &sh4_pci_ops,
+	.mem_resource	= &sh7751_mem_resource,
+	.mem_offset	= 0x00000000,
+	.io_resource	= &sh7751_io_resource,
+	.io_offset	= 0x00000000,
+	.io_map_base	= SH7751_PCI_IO_BASE,
+};
+
+static struct sh4_pci_address_map sh7751_pci_map = {
+	.window0	= {
+		.base	= SH7751_CS3_BASE_ADDR,
+		.size	= 0x04000000,
+	},
+};
+
 static int __init sh7751_pci_init(void)
 {
+	struct pci_channel *chan = &sh7751_pci_controller;
 	unsigned int id;
+	u32 word, reg;
 	int ret;
 
-	pr_debug("PCI: Starting intialization.\n");
+	printk(KERN_NOTICE "PCI: Starting intialization.\n");
+
+	chan->reg_base = 0xfe200000;
 
 	/* check for SH7751/SH7751R hardware */
-	id = pci_read_reg(SH7751_PCICONF0);
+	id = pci_read_reg(chan, SH7751_PCICONF0);
 	if (id != ((SH7751_DEVICE_ID << 16) | SH7751_VENDOR_ID) &&
 	    id != ((SH7751R_DEVICE_ID << 16) | SH7751_VENDOR_ID)) {
 		pr_debug("PCI: This is not an SH7751(R) (%x)\n", id);
 		return -ENODEV;
 	}
 
-	if ((ret = sh4_pci_check_direct()) != 0)
+	if ((ret = sh4_pci_check_direct(chan)) != 0)
 		return ret;
 
-	return pcibios_init_platform();
-}
-subsys_initcall(sh7751_pci_init);
-
-static int __init __area_sdram_check(unsigned int area)
-{
-	u32 word;
-
-	word = ctrl_inl(SH7751_BCR1);
-	/* check BCR for SDRAM in area */
-	if (((word >> area) & 1) == 0) {
-		printk("PCI: Area %d is not configured for SDRAM. BCR1=0x%x\n",
-		       area, word);
-		return 0;
-	}
-	pci_write_reg(word, SH4_PCIBCR1);
-
-	word = (u16)ctrl_inw(SH7751_BCR2);
-	/* check BCR2 for 32bit SDRAM interface*/
-	if (((word >> (area << 1)) & 0x3) != 0x3) {
-		printk("PCI: Area %d is not 32 bit SDRAM. BCR2=0x%x\n",
-		       area, word);
-		return 0;
-	}
-	pci_write_reg(word, SH4_PCIBCR2);
-
-	return 1;
-}
-
-int __init sh7751_pcic_init(struct sh4_pci_address_map *map)
-{
-	u32 reg;
-	u32 word;
-
 	/* Set the BCR's to enable PCI access */
 	reg = ctrl_inl(SH7751_BCR1);
 	reg |= 0x80000;
 	ctrl_outl(reg, SH7751_BCR1);
 
 	/* Turn the clocks back on (not done in reset)*/
-	pci_write_reg(0, SH4_PCICLKR);
+	pci_write_reg(chan, 0, SH4_PCICLKR);
 	/* Clear Powerdown IRQ's (not done in reset) */
 	word = SH4_PCIPINT_D3 | SH4_PCIPINT_D0;
-	pci_write_reg(word, SH4_PCIPINT);
-
-	/*
-	 * This code is unused for some boards as it is done in the
-	 * bootloader and doing it here means the MAC addresses loaded
-	 * by the bootloader get lost.
-	 */
-	if (!(map->flags & SH4_PCIC_NO_RESET)) {
-		/* toggle PCI reset pin */
-		word = SH4_PCICR_PREFIX | SH4_PCICR_PRST;
-		pci_write_reg(word, SH4_PCICR);
-		/* Wait for a long time... not 1 sec. but long enough */
-		mdelay(100);
-		word = SH4_PCICR_PREFIX;
-		pci_write_reg(word, SH4_PCICR);
-	}
+	pci_write_reg(chan, word, SH4_PCIPINT);
 
 	/* set the command/status bits to:
 	 * Wait Cycle Control + Parity Enable + Bus Master +
@@ -116,89 +113,75 @@ int __init sh7751_pcic_init(struct sh4_pci_address_map *map)
 	 */
 	word = SH7751_PCICONF1_WCC | SH7751_PCICONF1_PER |
 	       SH7751_PCICONF1_BUM | SH7751_PCICONF1_MES;
-	pci_write_reg(word, SH7751_PCICONF1);
+	pci_write_reg(chan, word, SH7751_PCICONF1);
 
 	/* define this host as the host bridge */
 	word = PCI_BASE_CLASS_BRIDGE << 24;
-	pci_write_reg(word, SH7751_PCICONF2);
+	pci_write_reg(chan, word, SH7751_PCICONF2);
 
 	/* Set IO and Mem windows to local address
 	 * Make PCI and local address the same for easy 1 to 1 mapping
-	 * Window0 = map->window0.size @ non-cached area base = SDRAM
-	 * Window1 = map->window1.size @ cached area base = SDRAM
 	 */
-	word = map->window0.size - 1;
-	pci_write_reg(word, SH4_PCILSR0);
-	word = map->window1.size - 1;
-	pci_write_reg(word, SH4_PCILSR1);
+	word = sh7751_pci_map.window0.size - 1;
+	pci_write_reg(chan, word, SH4_PCILSR0);
 	/* Set the values on window 0 PCI config registers */
-	word = P2SEGADDR(map->window0.base);
-	pci_write_reg(word, SH4_PCILAR0);
-	pci_write_reg(word, SH7751_PCICONF5);
-	/* Set the values on window 1 PCI config registers */
-	word =  PHYSADDR(map->window1.base);
-	pci_write_reg(word, SH4_PCILAR1);
-	pci_write_reg(word, SH7751_PCICONF6);
+	word = P2SEGADDR(sh7751_pci_map.window0.base);
+	pci_write_reg(chan, word, SH4_PCILAR0);
+	pci_write_reg(chan, word, SH7751_PCICONF5);
 
 	/* Set the local 16MB PCI memory space window to
 	 * the lowest PCI mapped address
 	 */
-	word = PCIBIOS_MIN_MEM & SH4_PCIMBR_MASK;
+	word = chan->mem_resource->start & SH4_PCIMBR_MASK;
 	pr_debug("PCI: Setting upper bits of Memory window to 0x%x\n", word);
-	pci_write_reg(word , SH4_PCIMBR);
-
-	/* Map IO space into PCI IO window
-	 * The IO window is 64K-PCIBIOS_MIN_IO in size
-	 * IO addresses will be translated to the
-	 * PCI IO window base address
-	 */
-	pr_debug("PCI: Mapping IO address 0x%x - 0x%x to base 0x%x\n",
-		 PCIBIOS_MIN_IO, (64 << 10),
-		 SH7751_PCI_IO_BASE + PCIBIOS_MIN_IO);
+	pci_write_reg(chan, word , SH4_PCIMBR);
 
 	/* Make sure the MSB's of IO window are set to access PCI space
 	 * correctly */
-	word = PCIBIOS_MIN_IO & SH4_PCIIOBR_MASK;
+	word = chan->io_resource->start & SH4_PCIIOBR_MASK;
 	pr_debug("PCI: Setting upper bits of IO window to 0x%x\n", word);
-	pci_write_reg(word, SH4_PCIIOBR);
+	pci_write_reg(chan, word, SH4_PCIIOBR);
 
 	/* Set PCI WCRx, BCRx's, copy from BSC locations */
 
 	/* check BCR for SDRAM in specified area */
-	switch (map->window0.base) {
-	case SH7751_CS0_BASE_ADDR: word = __area_sdram_check(0); break;
-	case SH7751_CS1_BASE_ADDR: word = __area_sdram_check(1); break;
-	case SH7751_CS2_BASE_ADDR: word = __area_sdram_check(2); break;
-	case SH7751_CS3_BASE_ADDR: word = __area_sdram_check(3); break;
-	case SH7751_CS4_BASE_ADDR: word = __area_sdram_check(4); break;
-	case SH7751_CS5_BASE_ADDR: word = __area_sdram_check(5); break;
-	case SH7751_CS6_BASE_ADDR: word = __area_sdram_check(6); break;
+	switch (sh7751_pci_map.window0.base) {
+	case SH7751_CS0_BASE_ADDR: word = __area_sdram_check(chan, 0); break;
+	case SH7751_CS1_BASE_ADDR: word = __area_sdram_check(chan, 1); break;
+	case SH7751_CS2_BASE_ADDR: word = __area_sdram_check(chan, 2); break;
+	case SH7751_CS3_BASE_ADDR: word = __area_sdram_check(chan, 3); break;
+	case SH7751_CS4_BASE_ADDR: word = __area_sdram_check(chan, 4); break;
+	case SH7751_CS5_BASE_ADDR: word = __area_sdram_check(chan, 5); break;
+	case SH7751_CS6_BASE_ADDR: word = __area_sdram_check(chan, 6); break;
 	}
 
 	if (!word)
-		return 0;
+		return -1;
 
 	/* configure the wait control registers */
 	word = ctrl_inl(SH7751_WCR1);
-	pci_write_reg(word, SH4_PCIWCR1);
+	pci_write_reg(chan, word, SH4_PCIWCR1);
 	word = ctrl_inl(SH7751_WCR2);
-	pci_write_reg(word, SH4_PCIWCR2);
+	pci_write_reg(chan, word, SH4_PCIWCR2);
 	word = ctrl_inl(SH7751_WCR3);
-	pci_write_reg(word, SH4_PCIWCR3);
+	pci_write_reg(chan, word, SH4_PCIWCR3);
 	word = ctrl_inl(SH7751_MCR);
-	pci_write_reg(word, SH4_PCIMCR);
+	pci_write_reg(chan, word, SH4_PCIMCR);
 
 	/* NOTE: I'm ignoring the PCI error IRQs for now..
 	 * TODO: add support for the internal error interrupts and
 	 * DMA interrupts...
 	 */
 
-	pci_fixup_pcic();
+	pci_fixup_pcic(chan);
 
 	/* SH7751 init done, set central function init complete */
 	/* use round robin mode to stop a device starving/overruning */
 	word = SH4_PCICR_PREFIX | SH4_PCICR_CFIN | SH4_PCICR_ARBM;
-	pci_write_reg(word, SH4_PCICR);
+	pci_write_reg(chan, word, SH4_PCICR);
 
-	return 1;
+	register_pci_controller(chan);
+
+	return 0;
 }
+arch_initcall(sh7751_pci_init);
diff --git a/arch/sh/drivers/pci/pci-sh7751.h b/arch/sh/drivers/pci/pci-sh7751.h
index 68e3cb5e6bec..4983a4d20355 100644
--- a/arch/sh/drivers/pci/pci-sh7751.h
+++ b/arch/sh/drivers/pci/pci-sh7751.h
@@ -26,7 +26,6 @@
 #define SH7751_PCI_IO_SIZE           0x40000     /* Size of IO window */
 
 #define SH7751_PCIREG_BASE           0xFE200000  /* PCI regs base address */
-#define PCI_REG(n)                  (SH7751_PCIREG_BASE+ n)
 
 #define SH7751_PCICONF0            0x0           /* PCI Config Reg 0 */
   #define SH7751_PCICONF0_DEVID      0xFFFF0000  /* Device ID */
@@ -58,7 +57,7 @@
   #define SH7751_PCICONF2_SCC        0x00FF0000  /* Sub-Class Code */
   #define SH7751_PCICONF2_RLPI       0x0000FF00  /* Programming Interface */
   #define SH7751_PCICONF2_REV        0x000000FF  /* Revision ID */
-#define SH7751_PCICONF3            0xC           /* PCI Config Reg 3 */ 
+#define SH7751_PCICONF3            0xC           /* PCI Config Reg 3 */
   #define SH7751_PCICONF3_BIST7      0x80000000  /* Bist Supported */
   #define SH7751_PCICONF3_BIST6      0x40000000  /* Bist Executing */
   #define SH7751_PCICONF3_BIST3_0    0x0F000000  /* Bist Passed */
@@ -73,12 +72,12 @@
   #define SH7751_PCICONF5_BASE       0xFFFFFFF0  /* Mem Space Base Addr */
   #define SH7751_PCICONF5_LAP        0x00000008  /* Prefetch Enabled */
   #define SH7751_PCICONF5_LAT        0x00000006  /* Local Memory type */
-  #define SH7751_PCICONF5_ASI        0x00000001  /* Address Space Type */  
+  #define SH7751_PCICONF5_ASI        0x00000001  /* Address Space Type */
 #define SH7751_PCICONF6            0x18          /* PCI Config Reg 6 */
   #define SH7751_PCICONF6_BASE       0xFFFFFFF0  /* Mem Space Base Addr */
   #define SH7751_PCICONF6_LAP        0x00000008  /* Prefetch Enabled */
   #define SH7751_PCICONF6_LAT        0x00000006  /* Local Memory type */
-  #define SH7751_PCICONF6_ASI        0x00000001  /* Address Space Type */  
+  #define SH7751_PCICONF6_ASI        0x00000001  /* Address Space Type */
 /* PCICONF7 - PCICONF10 are undefined */
 #define SH7751_PCICONF11           0x2C          /* PCI Config Reg 11 */
   #define SH7751_PCICONF11_SSID      0xFFFF0000  /* Subsystem ID */
@@ -127,9 +126,4 @@
 #define SH7751_CS5_BASE_ADDR       (SH7751_CS4_BASE_ADDR + SH7751_MEM_REGION_SIZE)
 #define SH7751_CS6_BASE_ADDR       (SH7751_CS5_BASE_ADDR + SH7751_MEM_REGION_SIZE)
 
-struct sh4_pci_address_map;
-
-/* arch/sh/drivers/pci/pci-sh7751.c */
-int sh7751_pcic_init(struct sh4_pci_address_map *map);
-
 #endif /* _PCI_SH7751_H_ */
diff --git a/arch/sh/drivers/pci/pci-sh7780.c b/arch/sh/drivers/pci/pci-sh7780.c
index bae6a2cf047d..323b92d565fe 100644
--- a/arch/sh/drivers/pci/pci-sh7780.c
+++ b/arch/sh/drivers/pci/pci-sh7780.c
@@ -1,19 +1,12 @@
 /*
- *	Low-Level PCI Support for the SH7780
+ * Low-Level PCI Support for the SH7780
  *
- *  Dustin McIntire (dustin@sensoria.com)
- *	Derived from arch/i386/kernel/pci-*.c which bore the message:
- *	(c) 1999--2000 Martin Mares <mj@ucw.cz>
- *
- *  Ported to the new API by Paul Mundt <lethal@linux-sh.org>
- *  With cleanup by Paul van Gool <pvangool@mimotech.com>
- *
- *  May be copied or modified under the terms of the GNU General Public
- *  License.  See linux/COPYING for more information.
+ *  Copyright (C) 2005 - 2009  Paul Mundt
  *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
  */
-#undef DEBUG
-
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -22,135 +15,132 @@
 #include <linux/delay.h>
 #include "pci-sh4.h"
 
-#define INTC_BASE	0xffd00000
-#define INTC_ICR0	(INTC_BASE+0x0)
-#define INTC_ICR1	(INTC_BASE+0x1c)
-#define INTC_INTPRI	(INTC_BASE+0x10)
-#define INTC_INTREQ	(INTC_BASE+0x24)
-#define INTC_INTMSK0	(INTC_BASE+0x44)
-#define INTC_INTMSK1	(INTC_BASE+0x48)
-#define INTC_INTMSK2	(INTC_BASE+0x40080)
-#define INTC_INTMSKCLR0	(INTC_BASE+0x64)
-#define INTC_INTMSKCLR1	(INTC_BASE+0x68)
-#define INTC_INTMSKCLR2	(INTC_BASE+0x40084)
-#define INTC_INT2MSKR	(INTC_BASE+0x40038)
-#define INTC_INT2MSKCR	(INTC_BASE+0x4003c)
+static struct resource sh7785_io_resource = {
+	.name	= "SH7785_IO",
+	.start	= SH7780_PCI_IO_BASE,
+	.end	= SH7780_PCI_IO_BASE + SH7780_PCI_IO_SIZE - 1,
+	.flags	= IORESOURCE_IO
+};
+
+static struct resource sh7785_mem_resource = {
+	.name	= "SH7785_mem",
+	.start	= SH7780_PCI_MEMORY_BASE,
+	.end	= SH7780_PCI_MEMORY_BASE + SH7780_PCI_MEM_SIZE - 1,
+	.flags	= IORESOURCE_MEM
+};
+
+static struct pci_channel sh7780_pci_controller = {
+	.pci_ops	= &sh4_pci_ops,
+	.mem_resource	= &sh7785_mem_resource,
+	.mem_offset	= 0x00000000,
+	.io_resource	= &sh7785_io_resource,
+	.io_offset	= 0x00000000,
+	.io_map_base	= SH7780_PCI_IO_BASE,
+};
+
+static struct sh4_pci_address_map sh7780_pci_map = {
+	.window0	= {
+#if defined(CONFIG_32BIT)
+		.base	= SH7780_32BIT_DDR_BASE_ADDR,
+		.size	= 0x40000000,
+#else
+		.base	= SH7780_CS0_BASE_ADDR,
+		.size	= 0x20000000,
+#endif
+	},
+};
 
-/*
- * Initialization. Try all known PCI access methods. Note that we support
- * using both PCI BIOS and direct access: in such cases, we use I/O ports
- * to access config space.
- *
- * Note that the platform specific initialization (BSC registers, and memory
- * space mapping) will be called via the platform defined function
- * pcibios_init_platform().
- */
 static int __init sh7780_pci_init(void)
 {
+	struct pci_channel *chan = &sh7780_pci_controller;
 	unsigned int id;
-	int ret, match = 0;
+	const char *type = NULL;
+	int ret;
+	u32 word;
 
-	pr_debug("PCI: Starting intialization.\n");
+	printk(KERN_NOTICE "PCI: Starting intialization.\n");
 
-	ctrl_outl(0x00000001, SH7780_PCI_VCR2); /* Enable PCIC */
+	chan->reg_base = 0xfe040000;
 
-	/* check for SH7780/SH7780R hardware */
-	id = pci_read_reg(SH7780_PCIVID);
-	if ((id & 0xffff) == SH7780_VENDOR_ID) {
-		switch ((id >> 16) & 0xffff) {
-		case SH7763_DEVICE_ID:
-		case SH7780_DEVICE_ID:
-		case SH7781_DEVICE_ID:
-		case SH7785_DEVICE_ID:
-			match = 1;
-			break;
-		}
-	}
+	/* Enable CPU access to the PCIC registers. */
+	__raw_writel(PCIECR_ENBL, PCIECR);
 
-	if (unlikely(!match)) {
-		printk(KERN_ERR "PCI: This is not an SH7780 (%x)\n", id);
+	id = __raw_readw(chan->reg_base + SH7780_PCIVID);
+	if (id != SH7780_VENDOR_ID) {
+		printk(KERN_ERR "PCI: Unknown vendor ID 0x%04x.\n", id);
 		return -ENODEV;
 	}
 
-	/* Setup the INTC */
-	if (mach_is_7780se()) {
-		/* ICR0: IRL=use separately */
-		ctrl_outl(0x00C00020, INTC_ICR0);
-		/* ICR1: detect low level(for 2ndcut) */
-		ctrl_outl(0xAAAA0000, INTC_ICR1);
-		/* INTPRI: priority=3(all) */
-		ctrl_outl(0x33333333, INTC_INTPRI);
+	id = __raw_readw(chan->reg_base + SH7780_PCIDID);
+	type = (id == SH7763_DEVICE_ID)	? "SH7763" :
+	       (id == SH7780_DEVICE_ID) ? "SH7780" :
+	       (id == SH7781_DEVICE_ID) ? "SH7781" :
+	       (id == SH7785_DEVICE_ID) ? "SH7785" :
+					  NULL;
+	if (unlikely(!type)) {
+		printk(KERN_ERR "PCI: Found an unsupported Renesas host "
+		       "controller, device id 0x%04x.\n", id);
+		return -EINVAL;
 	}
 
-	if ((ret = sh4_pci_check_direct()) != 0)
+	printk(KERN_NOTICE "PCI: Found a Renesas %s host "
+	       "controller, revision %d.\n", type,
+	       __raw_readb(chan->reg_base + SH7780_PCIRID));
+
+	if ((ret = sh4_pci_check_direct(chan)) != 0)
 		return ret;
 
-	return pcibios_init_platform();
-}
-core_initcall(sh7780_pci_init);
-
-int __init sh7780_pcic_init(struct sh4_pci_address_map *map)
-{
-	u32 word;
+	/*
+	 * Set the class and sub-class codes.
+	 */
+	__raw_writeb(PCI_CLASS_BRIDGE_HOST >> 8,
+		     chan->reg_base + SH7780_PCIBCC);
+	__raw_writeb(PCI_CLASS_BRIDGE_HOST & 0xff,
+		     chan->reg_base + SH7780_PCISUB);
 
 	/*
-	 * This code is unused for some boards as it is done in the
-	 * bootloader and doing it here means the MAC addresses loaded
-	 * by the bootloader get lost.
-	 */
-	if (!(map->flags & SH4_PCIC_NO_RESET)) {
-		/* toggle PCI reset pin */
-		word = SH4_PCICR_PREFIX | SH4_PCICR_PRST;
-		pci_write_reg(word, SH4_PCICR);
-		/* Wait for a long time... not 1 sec. but long enough */
-		mdelay(100);
-		word = SH4_PCICR_PREFIX;
-		pci_write_reg(word, SH4_PCICR);
-	}
-
-	/* set the command/status bits to:
-	 * Wait Cycle Control + Parity Enable + Bus Master +
-	 * Mem space enable
-	 */
-	pci_write_reg(0x00000046, SH7780_PCICMD);
-
-	/* define this host as the host bridge */
-	word = PCI_BASE_CLASS_BRIDGE << 24;
-	pci_write_reg(word, SH7780_PCIRID);
-
-	/* Set IO and Mem windows to local address
+	 * Set IO and Mem windows to local address
 	 * Make PCI and local address the same for easy 1 to 1 mapping
 	 */
-	pci_write_reg(map->window0.size - 0xfffff, SH4_PCILSR0);
-	pci_write_reg(map->window1.size - 0xfffff, SH4_PCILSR1);
+	pci_write_reg(chan, sh7780_pci_map.window0.size - 0xfffff, SH4_PCILSR0);
 	/* Set the values on window 0 PCI config registers */
-	pci_write_reg(map->window0.base, SH4_PCILAR0);
-	pci_write_reg(map->window0.base, SH7780_PCIMBAR0);
-	/* Set the values on window 1 PCI config registers */
-	pci_write_reg(map->window1.base, SH4_PCILAR1);
-	pci_write_reg(map->window1.base, SH7780_PCIMBAR1);
+	pci_write_reg(chan, sh7780_pci_map.window0.base, SH4_PCILAR0);
+	pci_write_reg(chan, sh7780_pci_map.window0.base, SH7780_PCIMBAR0);
 
-	/* Map IO space into PCI IO window
-	 * The IO window is 64K-PCIBIOS_MIN_IO in size
-	 * IO addresses will be translated to the
-	 * PCI IO window base address
-	 */
-	pr_debug("PCI: Mapping IO address 0x%x - 0x%x to base 0x%x\n",
-		 PCIBIOS_MIN_IO, (64 << 10),
-		 SH7780_PCI_IO_BASE + PCIBIOS_MIN_IO);
+	pci_write_reg(chan, 0x0000380f, SH4_PCIAINTM);
 
-	/* NOTE: I'm ignoring the PCI error IRQs for now..
-	 * TODO: add support for the internal error interrupts and
-	 * DMA interrupts...
-	 */
+	/* Set up standard PCI config registers */
+	__raw_writew(0xFB00, chan->reg_base + SH7780_PCISTATUS);
+	__raw_writew(0x0047, chan->reg_base + SH7780_PCICMD);
+	__raw_writew(0x1912, chan->reg_base + SH7780_PCISVID);
+	__raw_writew(0x0001, chan->reg_base + SH7780_PCISID);
+
+	__raw_writeb(0x00, chan->reg_base + SH7780_PCIPIF);
 
 	/* Apply any last-minute PCIC fixups */
-	pci_fixup_pcic();
+	pci_fixup_pcic(chan);
+
+	pci_write_reg(chan, 0xfd000000, SH7780_PCIMBR0);
+	pci_write_reg(chan, 0x00fc0000, SH7780_PCIMBMR0);
+
+#ifdef CONFIG_32BIT
+	pci_write_reg(chan, 0xc0000000, SH7780_PCIMBR2);
+	pci_write_reg(chan, 0x20000000 - SH7780_PCI_IO_SIZE, SH7780_PCIMBMR2);
+#endif
+
+	/* Set IOBR for windows containing area specified in pci.h */
+	pci_write_reg(chan, chan->io_resource->start & ~(SH7780_PCI_IO_SIZE-1),
+		      SH7780_PCIIOBR);
+	pci_write_reg(chan, ((SH7780_PCI_IO_SIZE-1) & (7<<18)),
+		      SH7780_PCIIOBMR);
 
 	/* SH7780 init done, set central function init complete */
 	/* use round robin mode to stop a device starving/overruning */
 	word = SH4_PCICR_PREFIX | SH4_PCICR_CFIN | SH4_PCICR_FTO;
-	pci_write_reg(word, SH4_PCICR);
+	pci_write_reg(chan, word, SH4_PCICR);
 
-	return 1;
+	register_pci_controller(chan);
+
+	return 0;
 }
+arch_initcall(sh7780_pci_init);
diff --git a/arch/sh/drivers/pci/pci-sh7780.h b/arch/sh/drivers/pci/pci-sh7780.h
index 93adc7119b79..4a52478c97cf 100644
--- a/arch/sh/drivers/pci/pci-sh7780.h
+++ b/arch/sh/drivers/pci/pci-sh7780.h
@@ -20,9 +20,8 @@
 #define SH7785_DEVICE_ID	0x0007
 
 /* SH7780 Control Registers */
-#define	SH7780_PCI_VCR0		0xFE000000
-#define	SH7780_PCI_VCR1		0xFE000004
-#define	SH7780_PCI_VCR2		0xFE000008
+#define	PCIECR			0xFE000008
+#define PCIECR_ENBL		0x01
 
 /* SH7780 Specific Values */
 #define SH7780_PCI_CONFIG_BASE	0xFD000000	/* Config space base addr */
@@ -35,7 +34,6 @@
 #define SH7780_PCI_IO_SIZE	0x00400000	/* Size of IO window */
 
 #define SH7780_PCIREG_BASE	0xFE040000	/* PCI regs base address */
-#define PCI_REG(n)		(SH7780_PCIREG_BASE+n)
 
 /* SH7780 PCI Config Registers */
 #define SH7780_PCIVID		0x000		/* Vendor ID */
@@ -67,11 +65,6 @@
 #define SH7780_PCIPMCSR_BSE	0x046
 #define SH7780_PCICDD		0x047
 
-#define SH7780_PCICR		0x100		/* PCI Control Register */
-#define SH7780_PCILSR		0x104		/* PCI Local Space Register0 */
-#define SH7780_PCILSR1		0x108		/* PCI Local Space Register1 */
-#define SH7780_PCILAR0		0x10C		/* PCI Local Address Register1 */
-#define SH7780_PCILAR1		0x110		/* PCI Local Address Register1 */
 #define SH7780_PCIIR		0x114		/* PCI Interrupt Register */
 #define SH7780_PCIIMR		0x118		/* PCI Interrupt Mask Register */
 #define SH7780_PCIAIR		0x11C		/* Error Address Register */
@@ -106,9 +99,4 @@
 
 #define SH7780_32BIT_DDR_BASE_ADDR	0x40000000
 
-struct sh4_pci_address_map;
-
-/* arch/sh/drivers/pci/pci-sh7780.c */
-int sh7780_pcic_init(struct sh4_pci_address_map *map);
-
 #endif /* _PCI_SH7780_H_ */
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index 0d6ac7a1db49..54d77cbb8b39 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -1,67 +1,156 @@
 /*
- * arch/sh/drivers/pci/pci.c
+ * New-style PCI core.
  *
- * Copyright (c) 2002 M. R. Brown  <mrbrown@linux-sh.org>
- * Copyright (c) 2004 - 2006 Paul Mundt  <lethal@linux-sh.org>
+ * Copyright (c) 2004 - 2009  Paul Mundt
+ * Copyright (c) 2002  M. R. Brown
  *
- * These functions are collected here to reduce duplication of common
- * code amongst the many platform-specific PCI support code files.
- *
- * These routines require the following board-specific routines:
- * void pcibios_fixup_irqs();
- *
- * See include/asm-sh/pci.h for more information.
+ * Modelled after arch/mips/pci/pci.c:
+ *  Copyright (C) 2003, 04 Ralf Baechle (ralf@linux-mips.org)
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  */
 #include <linux/kernel.h>
+#include <linux/mm.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/types.h>
 #include <linux/dma-debug.h>
-#include <asm/io.h>
+#include <linux/io.h>
+#include <linux/mutex.h>
+
+unsigned long PCIBIOS_MIN_IO = 0x0000;
+unsigned long PCIBIOS_MIN_MEM = 0;
+
+/*
+ * The PCI controller list.
+ */
+static struct pci_channel *hose_head, **hose_tail = &hose_head;
+
+static int pci_initialized;
+
+static void __devinit pcibios_scanbus(struct pci_channel *hose)
+{
+	static int next_busno;
+	struct pci_bus *bus;
+
+	bus = pci_scan_bus(next_busno, hose->pci_ops, hose);
+	if (bus) {
+		next_busno = bus->subordinate + 1;
+		/* Don't allow 8-bit bus number overflow inside the hose -
+		   reserve some space for bridges. */
+		if (next_busno > 224)
+			next_busno = 0;
+
+		pci_bus_size_bridges(bus);
+		pci_bus_assign_resources(bus);
+		pci_enable_bridges(bus);
+	}
+}
+
+static DEFINE_MUTEX(pci_scan_mutex);
+
+void __devinit register_pci_controller(struct pci_channel *hose)
+{
+	if (request_resource(&iomem_resource, hose->mem_resource) < 0)
+		goto out;
+	if (request_resource(&ioport_resource, hose->io_resource) < 0) {
+		release_resource(hose->mem_resource);
+		goto out;
+	}
+
+	*hose_tail = hose;
+	hose_tail = &hose->next;
+
+	/*
+	 * Do not panic here but later - this might hapen before console init.
+	 */
+	if (!hose->io_map_base) {
+		printk(KERN_WARNING
+		       "registering PCI controller with io_map_base unset\n");
+	}
+
+	/*
+	 * Scan the bus if it is register after the PCI subsystem
+	 * initialization.
+	 */
+	if (pci_initialized) {
+		mutex_lock(&pci_scan_mutex);
+		pcibios_scanbus(hose);
+		mutex_unlock(&pci_scan_mutex);
+	}
+
+	return;
+
+out:
+	printk(KERN_WARNING
+	       "Skipping PCI bus scan due to resource conflict\n");
+}
 
 static int __init pcibios_init(void)
 {
-	struct pci_channel *p;
-	struct pci_bus *bus;
-	int busno;
+	struct pci_channel *hose;
 
-#ifdef CONFIG_PCI_AUTO
-	/* assign resources */
-	busno = 0;
-	for (p = board_pci_channels; p->pci_ops != NULL; p++)
-		busno = pciauto_assign_resources(busno, p) + 1;
-#endif
-
-	/* scan the buses */
-	busno = 0;
-	for (p = board_pci_channels; p->pci_ops != NULL; p++) {
-		bus = pci_scan_bus(busno, p->pci_ops, p);
-		busno = bus->subordinate + 1;
-	}
+	/* Scan all of the recorded PCI controllers.  */
+	for (hose = hose_head; hose; hose = hose->next)
+		pcibios_scanbus(hose);
 
 	pci_fixup_irqs(pci_common_swizzle, pcibios_map_platform_irq);
 
 	dma_debug_add_bus(&pci_bus_type);
 
+	pci_initialized = 1;
+
 	return 0;
 }
 subsys_initcall(pcibios_init);
 
+static void pcibios_fixup_device_resources(struct pci_dev *dev,
+	struct pci_bus *bus)
+{
+	/* Update device resources.  */
+	struct pci_channel *hose = bus->sysdata;
+	unsigned long offset = 0;
+	int i;
+
+	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+		if (!dev->resource[i].start)
+			continue;
+		if (dev->resource[i].flags & IORESOURCE_PCI_FIXED)
+			continue;
+		if (dev->resource[i].flags & IORESOURCE_IO)
+			offset = hose->io_offset;
+		else if (dev->resource[i].flags & IORESOURCE_MEM)
+			offset = hose->mem_offset;
+
+		dev->resource[i].start += offset;
+		dev->resource[i].end += offset;
+	}
+}
+
 /*
  *  Called after each bus is probed, but before its children
  *  are examined.
  */
-void __devinit __weak pcibios_fixup_bus(struct pci_bus *bus)
+void __devinit pcibios_fixup_bus(struct pci_bus *bus)
 {
-	pci_read_bridge_bases(bus);
-}
+	struct pci_dev *dev = bus->self;
+	struct list_head *ln;
+	struct pci_channel *chan = bus->sysdata;
 
-void pcibios_align_resource(void *data, struct resource *res,
-			    resource_size_t size, resource_size_t align)
-			    __attribute__ ((weak));
+	if (!dev) {
+		bus->resource[0] = chan->io_resource;
+		bus->resource[1] = chan->mem_resource;
+	}
+
+	for (ln = bus->devices.next; ln != &bus->devices; ln = ln->next) {
+		dev = pci_dev_b(ln);
+
+		if ((dev->class >> 8) != PCI_CLASS_BRIDGE_PCI)
+			pcibios_fixup_device_resources(dev, bus);
+	}
+}
 
 /*
  * We need to avoid collisions with `mirrored' VGA ports
@@ -72,14 +161,58 @@ void pcibios_align_resource(void *data, struct resource *res,
 void pcibios_align_resource(void *data, struct resource *res,
 			    resource_size_t size, resource_size_t align)
 {
-	if (res->flags & IORESOURCE_IO) {
-		resource_size_t start = res->start;
+	struct pci_dev *dev = data;
+	struct pci_channel *chan = dev->sysdata;
+	resource_size_t start = res->start;
 
+	if (res->flags & IORESOURCE_IO) {
+		if (start < PCIBIOS_MIN_IO + chan->io_resource->start)
+			start = PCIBIOS_MIN_IO + chan->io_resource->start;
+
+		/*
+                 * Put everything into 0x00-0xff region modulo 0x400.
+		 */
 		if (start & 0x300) {
 			start = (start + 0x3ff) & ~0x3ff;
 			res->start = start;
 		}
+	} else if (res->flags & IORESOURCE_MEM) {
+		if (start < PCIBIOS_MIN_MEM + chan->mem_resource->start)
+			start = PCIBIOS_MIN_MEM + chan->mem_resource->start;
 	}
+
+	res->start = start;
+}
+
+void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
+			 struct resource *res)
+{
+	struct pci_channel *hose = dev->sysdata;
+	unsigned long offset = 0;
+
+	if (res->flags & IORESOURCE_IO)
+		offset = hose->io_offset;
+	else if (res->flags & IORESOURCE_MEM)
+		offset = hose->mem_offset;
+
+	region->start = res->start - offset;
+	region->end = res->end - offset;
+}
+
+void __devinit
+pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
+			struct pci_bus_region *region)
+{
+	struct pci_channel *hose = dev->sysdata;
+	unsigned long offset = 0;
+
+	if (res->flags & IORESOURCE_IO)
+		offset = hose->io_offset;
+	else if (res->flags & IORESOURCE_MEM)
+		offset = hose->mem_offset;
+
+	res->start = region->start + offset;
+	res->end = region->end + offset;
 }
 
 int pcibios_enable_device(struct pci_dev *dev, int mask)
@@ -90,13 +223,21 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 
 	pci_read_config_word(dev, PCI_COMMAND, &cmd);
 	old_cmd = cmd;
-	for(idx=0; idx<6; idx++) {
-		if (!(mask & (1 << idx)))
+	for (idx=0; idx < PCI_NUM_RESOURCES; idx++) {
+		/* Only set up the requested stuff */
+		if (!(mask & (1<<idx)))
 			continue;
+
 		r = &dev->resource[idx];
+		if (!(r->flags & (IORESOURCE_IO | IORESOURCE_MEM)))
+			continue;
+		if ((idx == PCI_ROM_RESOURCE) &&
+				(!(r->flags & IORESOURCE_ROM_ENABLE)))
+			continue;
 		if (!r->start && r->end) {
-			printk(KERN_ERR "PCI: Device %s not available because "
-			       "of resource collisions\n", pci_name(dev));
+			printk(KERN_ERR "PCI: Device %s not available "
+			       "because of resource collisions\n",
+			       pci_name(dev));
 			return -EINVAL;
 		}
 		if (r->flags & IORESOURCE_IO)
@@ -104,10 +245,8 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 		if (r->flags & IORESOURCE_MEM)
 			cmd |= PCI_COMMAND_MEMORY;
 	}
-	if (dev->resource[PCI_ROM_RESOURCE].start)
-		cmd |= PCI_COMMAND_MEMORY;
 	if (cmd != old_cmd) {
-		printk(KERN_INFO "PCI: Enabling device %s (%04x -> %04x)\n",
+		printk("PCI: Enabling device %s (%04x -> %04x)\n",
 		       pci_name(dev), old_cmd, cmd);
 		pci_write_config_word(dev, PCI_COMMAND, cmd);
 	}
@@ -140,6 +279,43 @@ void __init pcibios_update_irq(struct pci_dev *dev, int irq)
 	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
 }
 
+char * __devinit pcibios_setup(char *str)
+{
+	return str;
+}
+
+int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+			enum pci_mmap_state mmap_state, int write_combine)
+{
+	/*
+	 * I/O space can be accessed via normal processor loads and stores on
+	 * this platform but for now we elect not to do this and portable
+	 * drivers should not do this anyway.
+	 */
+	if (mmap_state == pci_mmap_io)
+		return -EINVAL;
+
+	/*
+	 * Ignore write-combine; for now only return uncached mappings.
+	 */
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+			       vma->vm_end - vma->vm_start,
+			       vma->vm_page_prot);
+}
+
+static void __iomem *ioport_map_pci(struct pci_dev *dev,
+				    unsigned long port, unsigned int nr)
+{
+	struct pci_channel *chan = dev->sysdata;
+
+	if (!chan->io_map_base)
+		chan->io_map_base = generic_io_base;
+
+	return (void __iomem *)(chan->io_map_base + port);
+}
+
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
 	resource_size_t start = pci_resource_start(dev, bar);
@@ -151,20 +327,24 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 	if (maxlen && len > maxlen)
 		len = maxlen;
 
+	if (flags & IORESOURCE_IO)
+		return ioport_map_pci(dev, start, len);
+
 	/*
 	 * Presently the IORESOURCE_MEM case is a bit special, most
 	 * SH7751 style PCI controllers have PCI memory at a fixed
-	 * location in the address space where no remapping is desired
-	 * (typically at 0xfd000000, but is_pci_memaddr() will know
-	 * best). With the IORESOURCE_MEM case more care has to be taken
+	 * location in the address space where no remapping is desired.
+	 * With the IORESOURCE_MEM case more care has to be taken
 	 * to inhibit page table mapping for legacy cores, but this is
 	 * punted off to __ioremap().
 	 *					-- PFM.
 	 */
-	if (flags & IORESOURCE_IO)
-		return ioport_map(start, len);
-	if (flags & IORESOURCE_MEM)
-		return ioremap(start, len);
+	if (flags & IORESOURCE_MEM) {
+		if (flags & IORESOURCE_CACHEABLE)
+			return ioremap(start, len);
+
+		return ioremap_nocache(start, len);
+	}
 
 	return NULL;
 }
@@ -175,3 +355,10 @@ void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
 	iounmap(addr);
 }
 EXPORT_SYMBOL(pci_iounmap);
+
+#ifdef CONFIG_HOTPLUG
+EXPORT_SYMBOL(pcibios_resource_to_bus);
+EXPORT_SYMBOL(pcibios_bus_to_resource);
+EXPORT_SYMBOL(PCIBIOS_MIN_IO);
+EXPORT_SYMBOL(PCIBIOS_MIN_MEM);
+#endif
diff --git a/arch/sh/include/asm/atomic-llsc.h b/arch/sh/include/asm/atomic-llsc.h
index 4b00b78e3f4f..b040e1e08610 100644
--- a/arch/sh/include/asm/atomic-llsc.h
+++ b/arch/sh/include/asm/atomic-llsc.h
@@ -104,4 +104,31 @@ static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
 	: "t");
 }
 
+#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
+
+/**
+ * atomic_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static inline int atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int c, old;
+	c = atomic_read(v);
+	for (;;) {
+		if (unlikely(c == (u)))
+			break;
+		old = atomic_cmpxchg((v), c, c + (a));
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+
+	return c != (u);
+}
+
 #endif /* __ASM_SH_ATOMIC_LLSC_H */
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index a5647d0cd179..157c320272cb 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -45,7 +45,7 @@
 #define atomic_inc(v) atomic_add(1,(v))
 #define atomic_dec(v) atomic_sub(1,(v))
 
-#ifndef CONFIG_GUSA_RB
+#if !defined(CONFIG_GUSA_RB) && !defined(CONFIG_CPU_SH4A)
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -73,7 +73,7 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 
 	return ret != u;
 }
-#endif
+#endif /* !CONFIG_GUSA_RB && !CONFIG_CPU_SH4A */
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index 09acbc32d6c7..4c5462daa74c 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -75,7 +75,5 @@ extern void copy_from_user_page(struct vm_area_struct *vma,
 #define flush_cache_vmap(start, end)		flush_cache_all()
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
-#define HAVE_ARCH_UNMAPPED_AREA
-
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_CACHEFLUSH_H */
diff --git a/arch/sh/include/asm/clock.h b/arch/sh/include/asm/clock.h
index 2f6c9627bc1f..9fe7d7f8af40 100644
--- a/arch/sh/include/asm/clock.h
+++ b/arch/sh/include/asm/clock.h
@@ -1,9 +1,9 @@
 #ifndef __ASM_SH_CLOCK_H
 #define __ASM_SH_CLOCK_H
 
-#include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/seq_file.h>
+#include <linux/cpufreq.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 
@@ -11,9 +11,9 @@ struct clk;
 
 struct clk_ops {
 	void (*init)(struct clk *clk);
-	void (*enable)(struct clk *clk);
+	int (*enable)(struct clk *clk);
 	void (*disable)(struct clk *clk);
-	void (*recalc)(struct clk *clk);
+	unsigned long (*recalc)(struct clk *clk);
 	int (*set_rate)(struct clk *clk, unsigned long rate, int algo_id);
 	int (*set_parent)(struct clk *clk, struct clk *parent);
 	long (*round_rate)(struct clk *clk, unsigned long rate);
@@ -28,43 +28,47 @@ struct clk {
 	struct clk		*parent;
 	struct clk_ops		*ops;
 
-	struct kref		kref;
+	struct list_head	children;
+	struct list_head	sibling;	/* node for children */
+
+	int			usecount;
 
 	unsigned long		rate;
 	unsigned long		flags;
+
+	void __iomem		*enable_reg;
+	unsigned int		enable_bit;
+
 	unsigned long		arch_flags;
+	void			*priv;
+	struct dentry		*dentry;
+	struct cpufreq_frequency_table *freq_table;
 };
 
-#define CLK_ALWAYS_ENABLED	(1 << 0)
-#define CLK_RATE_PROPAGATES	(1 << 1)
+struct clk_lookup {
+	struct list_head	node;
+	const char		*dev_id;
+	const char		*con_id;
+	struct clk		*clk;
+};
+
+#define CLK_ENABLE_ON_INIT	(1 << 0)
 
 /* Should be defined by processor-specific code */
-void arch_init_clk_ops(struct clk_ops **, int type);
+void __deprecated arch_init_clk_ops(struct clk_ops **, int type);
 int __init arch_clk_init(void);
 
 /* arch/sh/kernel/cpu/clock.c */
 int clk_init(void);
-
-void clk_recalc_rate(struct clk *);
-
+unsigned long followparent_recalc(struct clk *);
+void recalculate_root_clocks(void);
+void propagate_rate(struct clk *);
+int clk_reparent(struct clk *child, struct clk *parent);
 int clk_register(struct clk *);
 void clk_unregister(struct clk *);
 
-static inline int clk_always_enable(const char *id)
-{
-	struct clk *clk;
-	int ret;
-
-	clk = clk_get(NULL, id);
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
-
-	ret = clk_enable(clk);
-	if (ret)
-		clk_put(clk);
-
-	return ret;
-}
+/* arch/sh/kernel/cpu/clock-cpg.c */
+int __init __deprecated cpg_clk_init(void);
 
 /* the exported API, in addition to clk_set_rate */
 /**
@@ -96,4 +100,63 @@ enum clk_sh_algo_id {
 
 	IP_N1,
 };
+
+struct clk_div_mult_table {
+	unsigned int *divisors;
+	unsigned int nr_divisors;
+	unsigned int *multipliers;
+	unsigned int nr_multipliers;
+};
+
+struct cpufreq_frequency_table;
+void clk_rate_table_build(struct clk *clk,
+			  struct cpufreq_frequency_table *freq_table,
+			  int nr_freqs,
+			  struct clk_div_mult_table *src_table,
+			  unsigned long *bitmap);
+
+long clk_rate_table_round(struct clk *clk,
+			  struct cpufreq_frequency_table *freq_table,
+			  unsigned long rate);
+
+int clk_rate_table_find(struct clk *clk,
+			struct cpufreq_frequency_table *freq_table,
+			unsigned long rate);
+
+#define SH_CLK_MSTP32(_name, _id, _parent, _enable_reg,	\
+	    _enable_bit, _flags)			\
+{							\
+	.name		= _name,			\
+	.id		= _id,				\
+	.parent		= _parent,			\
+	.enable_reg	= (void __iomem *)_enable_reg,	\
+	.enable_bit	= _enable_bit,			\
+	.flags		= _flags,			\
+}
+
+int sh_clk_mstp32_register(struct clk *clks, int nr);
+
+#define SH_CLK_DIV4(_name, _parent, _reg, _shift, _div_bitmap, _flags)	\
+{									\
+	.name = _name,							\
+	.parent = _parent,						\
+	.enable_reg = (void __iomem *)_reg,				\
+	.enable_bit = _shift,						\
+	.arch_flags = _div_bitmap,					\
+	.flags = _flags,						\
+}
+
+int sh_clk_div4_register(struct clk *clks, int nr,
+			 struct clk_div_mult_table *table);
+
+#define SH_CLK_DIV6(_name, _parent, _reg, _flags)	\
+{							\
+	.name = _name,					\
+	.parent = _parent,				\
+	.enable_reg = (void __iomem *)_reg,		\
+	.flags = _flags,				\
+}
+
+int sh_clk_div6_register(struct clk *clks, int nr);
+
 #endif /* __ASM_SH_CLOCK_H */
diff --git a/arch/sh/include/asm/cmpxchg-llsc.h b/arch/sh/include/asm/cmpxchg-llsc.h
index 0fac3da536ca..47136661a203 100644
--- a/arch/sh/include/asm/cmpxchg-llsc.h
+++ b/arch/sh/include/asm/cmpxchg-llsc.h
@@ -55,7 +55,7 @@ __cmpxchg_u32(volatile int *m, unsigned long old, unsigned long new)
 		"mov		%0, %1				\n\t"
 		"cmp/eq		%1, %3				\n\t"
 		"bf		2f				\n\t"
-		"mov		%3, %0				\n\t"
+		"mov		%4, %0				\n\t"
 		"2:						\n\t"
 		"movco.l	%0, @%2				\n\t"
 		"bf		1b				\n\t"
diff --git a/arch/sh/include/asm/device.h b/arch/sh/include/asm/device.h
index efd511d0803a..8688a88303ee 100644
--- a/arch/sh/include/asm/device.h
+++ b/arch/sh/include/asm/device.h
@@ -10,3 +10,5 @@ struct platform_device;
 int platform_resource_setup_memory(struct platform_device *pdev,
 				   char *name, unsigned long memsize);
 
+void plat_early_device_setup(void);
+
diff --git a/arch/sh/include/asm/hd64461.h b/arch/sh/include/asm/hd64461.h
index 52b4b6238277..977355f0a483 100644
--- a/arch/sh/include/asm/hd64461.h
+++ b/arch/sh/include/asm/hd64461.h
@@ -13,18 +13,20 @@
 #define	HD64461_PCC_WINDOW	0x01000000
 
 /* Area 6 - Slot 0 - memory and/or IO card */
-#define	HD64461_PCC0_BASE	(CONFIG_HD64461_IOBASE + 0x8000000)
+#define HD64461_IOBASE		0xb0000000
+#define HD64461_IO_OFFSET(x)	(HD64461_IOBASE + (x))
+#define	HD64461_PCC0_BASE	HD64461_IO_OFFSET(0x8000000)
 #define	HD64461_PCC0_ATTR	(HD64461_PCC0_BASE)				/* 0xb80000000 */
 #define	HD64461_PCC0_COMM	(HD64461_PCC0_BASE+HD64461_PCC_WINDOW)		/* 0xb90000000 */
 #define	HD64461_PCC0_IO		(HD64461_PCC0_BASE+2*HD64461_PCC_WINDOW)	/* 0xba0000000 */
 
 /* Area 5 - Slot 1 - memory card only */
-#define	HD64461_PCC1_BASE	(CONFIG_HD64461_IOBASE + 0x4000000)
+#define	HD64461_PCC1_BASE	HD64461_IO_OFFSET(0x4000000)
 #define	HD64461_PCC1_ATTR	(HD64461_PCC1_BASE)				/* 0xb4000000 */
 #define	HD64461_PCC1_COMM	(HD64461_PCC1_BASE+HD64461_PCC_WINDOW)		/* 0xb5000000 */
 
 /* Standby Control Register for HD64461 */
-#define	HD64461_STBCR			CONFIG_HD64461_IOBASE
+#define	HD64461_STBCR			HD64461_IO_OFFSET(0x00000000)
 #define	HD64461_STBCR_CKIO_STBY		0x2000
 #define	HD64461_STBCR_SAFECKE_IST	0x1000
 #define	HD64461_STBCR_SLCKE_IST		0x0800
@@ -41,19 +43,19 @@
 #define	HD64461_STBCR_SURTST		0x0001
 
 /* System Configuration Register */
-#define	HD64461_SYSCR		(CONFIG_HD64461_IOBASE + 0x02)
+#define	HD64461_SYSCR		HD64461_IO_OFFSET(0x02)
 
 /* CPU Data Bus Control Register */
-#define	HD64461_SCPUCR		(CONFIG_HD64461_IOBASE + 0x04)
+#define	HD64461_SCPUCR		HD64461_IO_OFFSET(0x04)
 
 /* Base Address Register */
-#define	HD64461_LCDCBAR		(CONFIG_HD64461_IOBASE + 0x1000)
+#define	HD64461_LCDCBAR		HD64461_IO_OFFSET(0x1000)
 
 /* Line increment address */
-#define	HD64461_LCDCLOR		(CONFIG_HD64461_IOBASE + 0x1002)
+#define	HD64461_LCDCLOR		HD64461_IO_OFFSET(0x1002)
 
 /* Controls LCD controller */
-#define	HD64461_LCDCCR		(CONFIG_HD64461_IOBASE + 0x1004)
+#define	HD64461_LCDCCR		HD64461_IO_OFFSET(0x1004)
 
 /* LCCDR control bits */
 #define	HD64461_LCDCCR_STBACK	0x0400	/* Standby Back */
@@ -64,30 +66,30 @@
 #define	HD64461_LCDCCR_SPON	0x0010	/* Start Power On */
 
 /* Controls LCD (1) */
-#define	HD64461_LDR1		(CONFIG_HD64461_IOBASE + 0x1010)
+#define	HD64461_LDR1		HD64461_IO_OFFSET(0x1010)
 #define	HD64461_LDR1_DON	0x01	/* Display On */
 #define	HD64461_LDR1_DINV	0x80	/* Display Invert */
 
 /* Controls LCD (2) */
-#define	HD64461_LDR2		(CONFIG_HD64461_IOBASE + 0x1012)
-#define	HD64461_LDHNCR		(CONFIG_HD64461_IOBASE + 0x1014)	/* Number of horizontal characters */
-#define	HD64461_LDHNSR		(CONFIG_HD64461_IOBASE + 0x1016)	/* Specify output start position + width of CL1 */
-#define	HD64461_LDVNTR		(CONFIG_HD64461_IOBASE + 0x1018)	/* Specify total vertical lines */
-#define	HD64461_LDVNDR		(CONFIG_HD64461_IOBASE + 0x101a)	/* specify number of display vertical lines */
-#define	HD64461_LDVSPR		(CONFIG_HD64461_IOBASE + 0x101c)	/* specify vertical synchronization pos and AC nr */
+#define	HD64461_LDR2		HD64461_IO_OFFSET(0x1012)
+#define	HD64461_LDHNCR		HD64461_IO_OFFSET(0x1014)	/* Number of horizontal characters */
+#define	HD64461_LDHNSR		HD64461_IO_OFFSET(0x1016)	/* Specify output start position + width of CL1 */
+#define	HD64461_LDVNTR		HD64461_IO_OFFSET(0x1018)	/* Specify total vertical lines */
+#define	HD64461_LDVNDR		HD64461_IO_OFFSET(0x101a)	/* specify number of display vertical lines */
+#define	HD64461_LDVSPR		HD64461_IO_OFFSET(0x101c)	/* specify vertical synchronization pos and AC nr */
 
 /* Controls LCD (3) */
-#define	HD64461_LDR3		(CONFIG_HD64461_IOBASE + 0x101e)
+#define	HD64461_LDR3		HD64461_IO_OFFSET(0x101e)
 
 /* Palette Registers */
-#define	HD64461_CPTWAR		(CONFIG_HD64461_IOBASE + 0x1030)	/* Color Palette Write Address Register */
-#define	HD64461_CPTWDR		(CONFIG_HD64461_IOBASE + 0x1032)	/* Color Palette Write Data Register */
-#define	HD64461_CPTRAR		(CONFIG_HD64461_IOBASE + 0x1034)	/* Color Palette Read Address Register */
-#define	HD64461_CPTRDR		(CONFIG_HD64461_IOBASE + 0x1036)	/* Color Palette Read Data Register */
+#define	HD64461_CPTWAR		HD64461_IO_OFFSET(0x1030)	/* Color Palette Write Address Register */
+#define	HD64461_CPTWDR		HD64461_IO_OFFSET(0x1032)	/* Color Palette Write Data Register */
+#define	HD64461_CPTRAR		HD64461_IO_OFFSET(0x1034)	/* Color Palette Read Address Register */
+#define	HD64461_CPTRDR		HD64461_IO_OFFSET(0x1036)	/* Color Palette Read Data Register */
 
-#define	HD64461_GRDOR		(CONFIG_HD64461_IOBASE + 0x1040)	/* Display Resolution Offset Register */
-#define	HD64461_GRSCR		(CONFIG_HD64461_IOBASE + 0x1042)	/* Solid Color Register */
-#define	HD64461_GRCFGR		(CONFIG_HD64461_IOBASE + 0x1044)	/* Accelerator Configuration Register */
+#define	HD64461_GRDOR		HD64461_IO_OFFSET(0x1040)	/* Display Resolution Offset Register */
+#define	HD64461_GRSCR		HD64461_IO_OFFSET(0x1042)	/* Solid Color Register */
+#define	HD64461_GRCFGR		HD64461_IO_OFFSET(0x1044)	/* Accelerator Configuration Register */
 
 #define	HD64461_GRCFGR_ACCSTATUS	0x10	/* Accelerator Status */
 #define	HD64461_GRCFGR_ACCRESET		0x08	/* Accelerator Reset */
@@ -97,41 +99,41 @@
 #define	HD64461_GRCFGR_COLORDEPTH8	0x01	/* Sets Colordepth 8 for Accelerator */
 
 /* Line Drawing Registers */
-#define	HD64461_LNSARH		(CONFIG_HD64461_IOBASE + 0x1046)	/* Line Start Address Register (H) */
-#define	HD64461_LNSARL		(CONFIG_HD64461_IOBASE + 0x1048)	/* Line Start Address Register (L) */
-#define	HD64461_LNAXLR		(CONFIG_HD64461_IOBASE + 0x104a)	/* Axis Pixel Length Register */
-#define	HD64461_LNDGR		(CONFIG_HD64461_IOBASE + 0x104c)	/* Diagonal Register */
-#define	HD64461_LNAXR		(CONFIG_HD64461_IOBASE + 0x104e)	/* Axial Register */
-#define	HD64461_LNERTR		(CONFIG_HD64461_IOBASE + 0x1050)	/* Start Error Term Register */
-#define	HD64461_LNMDR		(CONFIG_HD64461_IOBASE + 0x1052)	/* Line Mode Register */
+#define	HD64461_LNSARH		HD64461_IO_OFFSET(0x1046)	/* Line Start Address Register (H) */
+#define	HD64461_LNSARL		HD64461_IO_OFFSET(0x1048)	/* Line Start Address Register (L) */
+#define	HD64461_LNAXLR		HD64461_IO_OFFSET(0x104a)	/* Axis Pixel Length Register */
+#define	HD64461_LNDGR		HD64461_IO_OFFSET(0x104c)	/* Diagonal Register */
+#define	HD64461_LNAXR		HD64461_IO_OFFSET(0x104e)	/* Axial Register */
+#define	HD64461_LNERTR		HD64461_IO_OFFSET(0x1050)	/* Start Error Term Register */
+#define	HD64461_LNMDR		HD64461_IO_OFFSET(0x1052)	/* Line Mode Register */
 
 /* BitBLT Registers */
-#define	HD64461_BBTSSARH	(CONFIG_HD64461_IOBASE + 0x1054)	/* Source Start Address Register (H) */
-#define	HD64461_BBTSSARL	(CONFIG_HD64461_IOBASE + 0x1056)	/* Source Start Address Register (L) */
-#define	HD64461_BBTDSARH	(CONFIG_HD64461_IOBASE + 0x1058)	/* Destination Start Address Register (H) */
-#define	HD64461_BBTDSARL	(CONFIG_HD64461_IOBASE + 0x105a)	/* Destination Start Address Register (L) */
-#define	HD64461_BBTDWR		(CONFIG_HD64461_IOBASE + 0x105c)	/* Destination Block Width Register */
-#define	HD64461_BBTDHR		(CONFIG_HD64461_IOBASE + 0x105e)	/* Destination Block Height Register */
-#define	HD64461_BBTPARH		(CONFIG_HD64461_IOBASE + 0x1060)	/* Pattern Start Address Register (H) */
-#define	HD64461_BBTPARL		(CONFIG_HD64461_IOBASE + 0x1062)	/* Pattern Start Address Register (L) */
-#define	HD64461_BBTMARH		(CONFIG_HD64461_IOBASE + 0x1064)	/* Mask Start Address Register (H) */
-#define	HD64461_BBTMARL		(CONFIG_HD64461_IOBASE + 0x1066)	/* Mask Start Address Register (L) */
-#define	HD64461_BBTROPR		(CONFIG_HD64461_IOBASE + 0x1068)	/* ROP Register */
-#define	HD64461_BBTMDR		(CONFIG_HD64461_IOBASE + 0x106a)	/* BitBLT Mode Register */
+#define	HD64461_BBTSSARH	HD64461_IO_OFFSET(0x1054)	/* Source Start Address Register (H) */
+#define	HD64461_BBTSSARL	HD64461_IO_OFFSET(0x1056)	/* Source Start Address Register (L) */
+#define	HD64461_BBTDSARH	HD64461_IO_OFFSET(0x1058)	/* Destination Start Address Register (H) */
+#define	HD64461_BBTDSARL	HD64461_IO_OFFSET(0x105a)	/* Destination Start Address Register (L) */
+#define	HD64461_BBTDWR		HD64461_IO_OFFSET(0x105c)	/* Destination Block Width Register */
+#define	HD64461_BBTDHR		HD64461_IO_OFFSET(0x105e)	/* Destination Block Height Register */
+#define	HD64461_BBTPARH		HD64461_IO_OFFSET(0x1060)	/* Pattern Start Address Register (H) */
+#define	HD64461_BBTPARL		HD64461_IO_OFFSET(0x1062)	/* Pattern Start Address Register (L) */
+#define	HD64461_BBTMARH		HD64461_IO_OFFSET(0x1064)	/* Mask Start Address Register (H) */
+#define	HD64461_BBTMARL		HD64461_IO_OFFSET(0x1066)	/* Mask Start Address Register (L) */
+#define	HD64461_BBTROPR		HD64461_IO_OFFSET(0x1068)	/* ROP Register */
+#define	HD64461_BBTMDR		HD64461_IO_OFFSET(0x106a)	/* BitBLT Mode Register */
 
 /* PC Card Controller Registers */
 /* Maps to Physical Area 6 */
-#define	HD64461_PCC0ISR		(CONFIG_HD64461_IOBASE + 0x2000)	/* socket 0 interface status */
-#define	HD64461_PCC0GCR		(CONFIG_HD64461_IOBASE + 0x2002)	/* socket 0 general control */
-#define	HD64461_PCC0CSCR	(CONFIG_HD64461_IOBASE + 0x2004)	/* socket 0 card status change */
-#define	HD64461_PCC0CSCIER	(CONFIG_HD64461_IOBASE + 0x2006)	/* socket 0 card status change interrupt enable */
-#define	HD64461_PCC0SCR		(CONFIG_HD64461_IOBASE + 0x2008)	/* socket 0 software control */
+#define	HD64461_PCC0ISR		HD64461_IO_OFFSET(0x2000)	/* socket 0 interface status */
+#define	HD64461_PCC0GCR		HD64461_IO_OFFSET(0x2002)	/* socket 0 general control */
+#define	HD64461_PCC0CSCR	HD64461_IO_OFFSET(0x2004)	/* socket 0 card status change */
+#define	HD64461_PCC0CSCIER	HD64461_IO_OFFSET(0x2006)	/* socket 0 card status change interrupt enable */
+#define	HD64461_PCC0SCR		HD64461_IO_OFFSET(0x2008)	/* socket 0 software control */
 /* Maps to Physical Area 5 */
-#define	HD64461_PCC1ISR		(CONFIG_HD64461_IOBASE + 0x2010)	/* socket 1 interface status */
-#define	HD64461_PCC1GCR		(CONFIG_HD64461_IOBASE + 0x2012)	/* socket 1 general control */
-#define	HD64461_PCC1CSCR	(CONFIG_HD64461_IOBASE + 0x2014)	/* socket 1 card status change */
-#define	HD64461_PCC1CSCIER	(CONFIG_HD64461_IOBASE + 0x2016)	/* socket 1 card status change interrupt enable */
-#define	HD64461_PCC1SCR		(CONFIG_HD64461_IOBASE + 0x2018)	/* socket 1 software control */
+#define	HD64461_PCC1ISR		HD64461_IO_OFFSET(0x2010)	/* socket 1 interface status */
+#define	HD64461_PCC1GCR		HD64461_IO_OFFSET(0x2012)	/* socket 1 general control */
+#define	HD64461_PCC1CSCR	HD64461_IO_OFFSET(0x2014)	/* socket 1 card status change */
+#define	HD64461_PCC1CSCIER	HD64461_IO_OFFSET(0x2016)	/* socket 1 card status change interrupt enable */
+#define	HD64461_PCC1SCR		HD64461_IO_OFFSET(0x2018)	/* socket 1 software control */
 
 /* PCC Interface Status Register */
 #define	HD64461_PCCISR_READY		0x80	/* card ready */
@@ -189,41 +191,41 @@
 #define	HD64461_PCCSCR_SWP		0x01	/* write protect */
 
 /* PCC0 Output Pins Control Register */
-#define	HD64461_P0OCR		(CONFIG_HD64461_IOBASE + 0x202a)
+#define	HD64461_P0OCR		HD64461_IO_OFFSET(0x202a)
 
 /* PCC1 Output Pins Control Register */
-#define	HD64461_P1OCR		(CONFIG_HD64461_IOBASE + 0x202c)
+#define	HD64461_P1OCR		HD64461_IO_OFFSET(0x202c)
 
 /* PC Card General Control Register */
-#define	HD64461_PGCR		(CONFIG_HD64461_IOBASE + 0x202e)
+#define	HD64461_PGCR		HD64461_IO_OFFSET(0x202e)
 
 /* Port Control Registers */
-#define	HD64461_GPACR		(CONFIG_HD64461_IOBASE + 0x4000)	/* Port A - Handles IRDA/TIMER */
-#define	HD64461_GPBCR		(CONFIG_HD64461_IOBASE + 0x4002)	/* Port B - Handles UART */
-#define	HD64461_GPCCR		(CONFIG_HD64461_IOBASE + 0x4004)	/* Port C - Handles PCMCIA 1 */
-#define	HD64461_GPDCR		(CONFIG_HD64461_IOBASE + 0x4006)	/* Port D - Handles PCMCIA 1 */
+#define	HD64461_GPACR		HD64461_IO_OFFSET(0x4000)	/* Port A - Handles IRDA/TIMER */
+#define	HD64461_GPBCR		HD64461_IO_OFFSET(0x4002)	/* Port B - Handles UART */
+#define	HD64461_GPCCR		HD64461_IO_OFFSET(0x4004)	/* Port C - Handles PCMCIA 1 */
+#define	HD64461_GPDCR		HD64461_IO_OFFSET(0x4006)	/* Port D - Handles PCMCIA 1 */
 
 /* Port Control Data Registers */
-#define	HD64461_GPADR		(CONFIG_HD64461_IOBASE + 0x4010)	/* A */
-#define	HD64461_GPBDR		(CONFIG_HD64461_IOBASE + 0x4012)	/* B */
-#define	HD64461_GPCDR		(CONFIG_HD64461_IOBASE + 0x4014)	/* C */
-#define	HD64461_GPDDR		(CONFIG_HD64461_IOBASE + 0x4016)	/* D */
+#define	HD64461_GPADR		HD64461_IO_OFFSET(0x4010)	/* A */
+#define	HD64461_GPBDR		HD64461_IO_OFFSET(0x4012)	/* B */
+#define	HD64461_GPCDR		HD64461_IO_OFFSET(0x4014)	/* C */
+#define	HD64461_GPDDR		HD64461_IO_OFFSET(0x4016)	/* D */
 
 /* Interrupt Control Registers */
-#define	HD64461_GPAICR		(CONFIG_HD64461_IOBASE + 0x4020)	/* A */
-#define	HD64461_GPBICR		(CONFIG_HD64461_IOBASE + 0x4022)	/* B */
-#define	HD64461_GPCICR		(CONFIG_HD64461_IOBASE + 0x4024)	/* C */
-#define	HD64461_GPDICR		(CONFIG_HD64461_IOBASE + 0x4026)	/* D */
+#define	HD64461_GPAICR		HD64461_IO_OFFSET(0x4020)	/* A */
+#define	HD64461_GPBICR		HD64461_IO_OFFSET(0x4022)	/* B */
+#define	HD64461_GPCICR		HD64461_IO_OFFSET(0x4024)	/* C */
+#define	HD64461_GPDICR		HD64461_IO_OFFSET(0x4026)	/* D */
 
 /* Interrupt Status Registers */
-#define	HD64461_GPAISR		(CONFIG_HD64461_IOBASE + 0x4040)	/* A */
-#define	HD64461_GPBISR		(CONFIG_HD64461_IOBASE + 0x4042)	/* B */
-#define	HD64461_GPCISR		(CONFIG_HD64461_IOBASE + 0x4044)	/* C */
-#define	HD64461_GPDISR		(CONFIG_HD64461_IOBASE + 0x4046)	/* D */
+#define	HD64461_GPAISR		HD64461_IO_OFFSET(0x4040)	/* A */
+#define	HD64461_GPBISR		HD64461_IO_OFFSET(0x4042)	/* B */
+#define	HD64461_GPCISR		HD64461_IO_OFFSET(0x4044)	/* C */
+#define	HD64461_GPDISR		HD64461_IO_OFFSET(0x4046)	/* D */
 
 /* Interrupt Request Register & Interrupt Mask Register */
-#define	HD64461_NIRR		(CONFIG_HD64461_IOBASE + 0x5000)
-#define	HD64461_NIMR		(CONFIG_HD64461_IOBASE + 0x5002)
+#define	HD64461_NIRR		HD64461_IO_OFFSET(0x5000)
+#define	HD64461_NIMR		HD64461_IO_OFFSET(0x5002)
 
 #define	HD64461_IRQBASE		OFFCHIP_IRQ_BASE
 #define	OFFCHIP_IRQ_BASE	64
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 0454f8d68059..25348141674b 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -123,10 +123,15 @@ static inline void __raw_reads##bwlq(volatile void __iomem *mem,	\
 
 __BUILD_MEMORY_STRING(b, u8)
 __BUILD_MEMORY_STRING(w, u16)
-__BUILD_MEMORY_STRING(q, u64)
 
+#ifdef CONFIG_SUPERH32
 void __raw_writesl(void __iomem *addr, const void *data, int longlen);
 void __raw_readsl(const void __iomem *addr, void *data, int longlen);
+#else
+__BUILD_MEMORY_STRING(l, u32)
+#endif
+
+__BUILD_MEMORY_STRING(q, u64)
 
 #define writesb			__raw_writesb
 #define writesw			__raw_writesw
@@ -224,17 +229,6 @@ void __iomem *__ioremap(unsigned long offset, unsigned long size,
 			unsigned long flags);
 void __iounmap(void __iomem *addr);
 
-/* arch/sh/mm/ioremap_64.c */
-unsigned long onchip_remap(unsigned long addr, unsigned long size,
-			   const char *name);
-extern void onchip_unmap(unsigned long vaddr);
-#else
-#define __ioremap(offset, size, flags)	((void __iomem *)(offset))
-#define __iounmap(addr)			do { } while (0)
-#define onchip_remap(addr, size, name)	(addr)
-#define onchip_unmap(addr)		do { } while (0)
-#endif /* CONFIG_MMU */
-
 static inline void __iomem *
 __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags)
 {
@@ -268,6 +262,10 @@ __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags)
 
 	return __ioremap(offset, size, flags);
 }
+#else
+#define __ioremap_mode(offset, size, flags)	((void __iomem *)(offset))
+#define __iounmap(addr)				do { } while (0)
+#endif /* CONFIG_MMU */
 
 #define ioremap(offset, size)				\
 	__ioremap_mode((offset), (size), 0)
diff --git a/arch/sh/include/asm/irq.h b/arch/sh/include/asm/irq.h
index d319baaf4fbd..a2b8c99cc06f 100644
--- a/arch/sh/include/asm/irq.h
+++ b/arch/sh/include/asm/irq.h
@@ -8,7 +8,8 @@
  * advised to cap this at the hard limit that they're interested in
  * through the machvec.
  */
-#define NR_IRQS 256
+#define NR_IRQS			256
+#define NR_IRQS_LEGACY		8	/* Legacy external IRQ0-7 */
 
 /*
  * Convert back and forth between INTEVT and IRQ values.
diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h
index 613644a758e8..036c3311233c 100644
--- a/arch/sh/include/asm/kprobes.h
+++ b/arch/sh/include/asm/kprobes.h
@@ -6,7 +6,7 @@
 #include <linux/types.h>
 #include <linux/ptrace.h>
 
-typedef u16 kprobe_opcode_t;
+typedef insn_size_t kprobe_opcode_t;
 #define BREAKPOINT_INSTRUCTION	0xc33a
 
 #define MAX_INSN_SIZE 16
diff --git a/arch/sh/include/asm/machvec.h b/arch/sh/include/asm/machvec.h
index 64b1c16a0f03..84dd37761f56 100644
--- a/arch/sh/include/asm/machvec.h
+++ b/arch/sh/include/asm/machvec.h
@@ -46,6 +46,9 @@ struct sh_machine_vector {
 
 	void __iomem *(*mv_ioport_map)(unsigned long port, unsigned int size);
 	void (*mv_ioport_unmap)(void __iomem *);
+
+	int (*mv_clk_init)(void);
+	int (*mv_mode_pins)(void);
 };
 
 extern struct sh_machine_vector sh_mv;
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index df1d383e18a5..ae0da6f48b6d 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -17,54 +17,29 @@
  * external) PCI controllers.
  */
 struct pci_channel {
-	struct pci_ops *pci_ops;
-	struct resource *io_resource;
-	struct resource *mem_resource;
-	int first_devfn;
-	int last_devfn;
+	struct pci_channel	*next;
+
+	struct pci_ops		*pci_ops;
+	struct resource		*io_resource;
+	struct resource		*mem_resource;
+
+	unsigned long		io_offset;
+	unsigned long		mem_offset;
+
+	unsigned long		reg_base;
+
+	unsigned long		io_map_base;
 };
 
-/*
- * Each board initializes this array and terminates it with a NULL entry.
- */
-extern struct pci_channel board_pci_channels[];
+extern void register_pci_controller(struct pci_channel *hose);
 
-#define PCIBIOS_MIN_IO		board_pci_channels->io_resource->start
-#define PCIBIOS_MIN_MEM		board_pci_channels->mem_resource->start
-
-/*
- * I/O routine helpers
- */
-#if defined(CONFIG_CPU_SUBTYPE_SH7780) || defined(CONFIG_CPU_SUBTYPE_SH7785)
-#define PCI_IO_AREA		0xFE400000
-#define PCI_IO_SIZE		0x00400000
-#elif defined(CONFIG_CPU_SH5)
-extern unsigned long PCI_IO_AREA;
-#define PCI_IO_SIZE		0x00010000
-#else
-#define PCI_IO_AREA		0xFE240000
-#define PCI_IO_SIZE		0x00040000
-#endif
-
-#define PCI_MEM_SIZE		0x01000000
-
-#define SH4_PCIIOBR_MASK	0xFFFC0000
-#define pci_ioaddr(addr)	(PCI_IO_AREA + (addr & ~SH4_PCIIOBR_MASK))
-
-#if defined(CONFIG_PCI)
-#define is_pci_ioaddr(port)		\
-	(((port) >= PCIBIOS_MIN_IO) &&	\
-	 ((port) < (PCIBIOS_MIN_IO + PCI_IO_SIZE)))
-#define is_pci_memaddr(port)		\
-	(((port) >= PCIBIOS_MIN_MEM) &&	\
-	 ((port) < (PCIBIOS_MIN_MEM + PCI_MEM_SIZE)))
-#else
-#define is_pci_ioaddr(port)	(0)
-#define is_pci_memaddr(port)	(0)
-#endif
+extern unsigned long PCIBIOS_MIN_IO, PCIBIOS_MIN_MEM;
 
 struct pci_dev;
 
+#define HAVE_PCI_MMAP
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+	enum pci_mmap_state mmap_state, int write_combine);
 extern void pcibios_set_master(struct pci_dev *dev);
 
 static inline void pcibios_penalize_isa_irq(int irq, int active)
@@ -114,31 +89,76 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
 #endif
 
 #ifdef CONFIG_PCI
+/*
+ * None of the SH PCI controllers support MWI, it is always treated as a
+ * direct memory write.
+ */
+#define PCI_DISABLE_MWI
+
 static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 					enum pci_dma_burst_strategy *strat,
 					unsigned long *strategy_parameter)
 {
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
+	unsigned long cacheline_size;
+	u8 byte;
+
+	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
+
+	if (byte == 0)
+		cacheline_size = L1_CACHE_BYTES;
+	else
+		cacheline_size = byte << 2;
+
+	*strat = PCI_DMA_BURST_MULTIPLE;
+	*strategy_parameter = cacheline_size;
 }
 #endif
 
-/* Board-specific fixup routines. */
-void pcibios_fixup(void);
-int pcibios_init_platform(void);
-int pcibios_map_platform_irq(struct pci_dev *dev, u8 slot, u8 pin);
+#ifdef CONFIG_SUPERH32
+/*
+ * If we're on an SH7751 or SH7780 PCI controller, PCI memory is mapped
+ * at the end of the address space in a special non-translatable area.
+ */
+#define PCI_MEM_FIXED_START	0xfd000000
+#define PCI_MEM_FIXED_END	(PCI_MEM_FIXED_START + 0x01000000)
 
-#ifdef CONFIG_PCI_AUTO
-int pciauto_assign_resources(int busno, struct pci_channel *hose);
+#define is_pci_memory_fixed_range(s, e)	\
+	((s) >= PCI_MEM_FIXED_START && (e) < PCI_MEM_FIXED_END)
+#else
+#define is_pci_memory_fixed_range(s, e)	(0)
 #endif
 
-#endif /* __KERNEL__ */
+/* Board-specific fixup routines. */
+int pcibios_map_platform_irq(struct pci_dev *dev, u8 slot, u8 pin);
 
-/* generic pci stuff */
-#include <asm-generic/pci.h>
+extern void pcibios_resource_to_bus(struct pci_dev *dev,
+	struct pci_bus_region *region, struct resource *res);
+
+extern void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
+				    struct pci_bus_region *region);
+
+static inline struct resource *
+pcibios_select_root(struct pci_dev *pdev, struct resource *res)
+{
+	struct resource *root = NULL;
+
+	if (res->flags & IORESOURCE_IO)
+		root = &ioport_resource;
+	if (res->flags & IORESOURCE_MEM)
+		root = &iomem_resource;
+
+	return root;
+}
+
+/* Chances are this interrupt is wired PC-style ...  */
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+	return channel ? 15 : 14;
+}
 
 /* generic DMA-mapping stuff */
 #include <asm-generic/pci-dma-compat.h>
 
+#endif /* __KERNEL__ */
 #endif /* __ASM_SH_PCI_H */
 
diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h
index b517ae08b9c0..2a011b18090b 100644
--- a/arch/sh/include/asm/pgtable.h
+++ b/arch/sh/include/asm/pgtable.h
@@ -154,6 +154,10 @@ extern void kmap_coherent_init(void);
 #define kmap_coherent_init()	do { } while (0)
 #endif
 
+/* arch/sh/mm/mmap.c */
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+
 #include <asm-generic/pgtable.h>
 
 #endif /* __ASM_SH_PGTABLE_H */
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index 1fd58b421438..ff7daaf9a620 100644
--- a/arch/sh/include/asm/processor.h
+++ b/arch/sh/include/asm/processor.h
@@ -32,7 +32,7 @@ enum cpu_type {
 
 	/* SH-4A types */
 	CPU_SH7763, CPU_SH7770, CPU_SH7780, CPU_SH7781, CPU_SH7785, CPU_SH7786,
-	CPU_SH7723, CPU_SHX3,
+	CPU_SH7723, CPU_SH7724, CPU_SHX3,
 
 	/* SH4AL-DSP types */
 	CPU_SH7343, CPU_SH7722, CPU_SH7366,
@@ -94,6 +94,27 @@ extern struct pt_regs fake_swapper_regs;
 const char *get_cpu_subtype(struct sh_cpuinfo *c);
 extern const struct seq_operations cpuinfo_op;
 
+/* processor boot mode configuration */
+#define MODE_PIN0 (1 << 0)
+#define MODE_PIN1 (1 << 1)
+#define MODE_PIN2 (1 << 2)
+#define MODE_PIN3 (1 << 3)
+#define MODE_PIN4 (1 << 4)
+#define MODE_PIN5 (1 << 5)
+#define MODE_PIN6 (1 << 6)
+#define MODE_PIN7 (1 << 7)
+#define MODE_PIN8 (1 << 8)
+#define MODE_PIN9 (1 << 9)
+#define MODE_PIN10 (1 << 10)
+#define MODE_PIN11 (1 << 11)
+#define MODE_PIN12 (1 << 12)
+#define MODE_PIN13 (1 << 13)
+#define MODE_PIN14 (1 << 14)
+#define MODE_PIN15 (1 << 15)
+
+int generic_mode_pins(void);
+int test_mode_pin(int pin);
+
 #ifdef CONFIG_VSYSCALL
 int vsyscall_init(void);
 #else
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index 68e20ff9aa9b..1dc12cb44a2d 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -102,6 +102,11 @@ struct pt_dspregs {
 #define	PTRACE_GETDSPREGS	55	/* DSP registers */
 #define	PTRACE_SETDSPREGS	56
 
+#define PT_TEXT_END_ADDR 	240
+#define PT_TEXT_ADDR 		244	/* &(struct user)->start_code */
+#define PT_DATA_ADDR 		248	/* &(struct user)->start_data */
+#define PT_TEXT_LEN		252
+
 #ifdef __KERNEL__
 #include <asm/addrspace.h>
 
diff --git a/arch/sh/include/asm/rtc.h b/arch/sh/include/asm/rtc.h
index f7b010d48af7..52b0c2dba979 100644
--- a/arch/sh/include/asm/rtc.h
+++ b/arch/sh/include/asm/rtc.h
@@ -6,6 +6,17 @@ extern void (*board_time_init)(void);
 extern void (*rtc_sh_get_time)(struct timespec *);
 extern int (*rtc_sh_set_time)(const time_t);
 
+/* some dummy definitions */
+#define RTC_BATT_BAD 0x100	/* battery bad */
+#define RTC_SQWE 0x08		/* enable square-wave output */
+#define RTC_DM_BINARY 0x04	/* all time/date values are BCD if clear */
+#define RTC_24H 0x02		/* 24 hour mode - else hours bit 7 means pm */
+#define RTC_DST_EN 0x01	        /* auto switch DST - works f. USA only */
+
+struct rtc_time;
+unsigned int get_rtc_time(struct rtc_time *);
+int set_rtc_time(struct rtc_time *);
+
 #define RTC_CAP_4_DIGIT_YEAR	(1 << 0)
 
 struct sh_rtc_platform_info {
diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h
index 60283565f89b..a28c9f0053fd 100644
--- a/arch/sh/include/asm/spinlock.h
+++ b/arch/sh/include/asm/spinlock.h
@@ -26,7 +26,7 @@
 #define __raw_spin_is_locked(x)		((x)->lock <= 0)
 #define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
 #define __raw_spin_unlock_wait(x) \
-	do { cpu_relax(); } while ((x)->lock)
+	do { while (__raw_spin_is_locked(x)) cpu_relax(); } while (0)
 
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
diff --git a/arch/sh/include/asm/swab.h b/arch/sh/include/asm/swab.h
index e69315935107..0e08fe54ad71 100644
--- a/arch/sh/include/asm/swab.h
+++ b/arch/sh/include/asm/swab.h
@@ -14,15 +14,15 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {
 	__asm__(
 #ifdef __SH5__
-		"byterev	%0, %0\n\t"
+		"byterev	%1, %0\n\t"
 		"shari		%0, 32, %0"
 #else
-		"swap.b		%0, %0\n\t"
+		"swap.b		%1, %0\n\t"
 		"swap.w		%0, %0\n\t"
 		"swap.b		%0, %0"
 #endif
 		: "=r" (x)
-		: "0" (x));
+		: "r" (x));
 
 	return x;
 }
@@ -32,13 +32,13 @@ static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 {
 	__asm__(
 #ifdef __SH5__
-		"byterev	%0, %0\n\t"
+		"byterev	%1, %0\n\t"
 		"shari		%0, 32, %0"
 #else
-		"swap.b		%0, %0"
+		"swap.b		%1, %0"
 #endif
 		: "=r" (x)
-		:  "0" (x));
+		:  "r" (x));
 
 	return x;
 }
diff --git a/arch/sh/include/asm/system_32.h b/arch/sh/include/asm/system_32.h
index 240b31e1142c..6c68a51f1cc5 100644
--- a/arch/sh/include/asm/system_32.h
+++ b/arch/sh/include/asm/system_32.h
@@ -198,7 +198,7 @@ do {							\
 })
 #endif
 
-int handle_unaligned_access(opcode_t instruction, struct pt_regs *regs,
+int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
 			    struct mem_access *ma);
 
 asmlinkage void do_address_error(struct pt_regs *regs,
diff --git a/arch/sh/include/asm/timer.h b/arch/sh/include/asm/timer.h
deleted file mode 100644
index 4c3b66e30af2..000000000000
--- a/arch/sh/include/asm/timer.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef __ASM_SH_TIMER_H
-#define __ASM_SH_TIMER_H
-
-#include <linux/sysdev.h>
-#include <linux/clocksource.h>
-#include <cpu/timer.h>
-
-struct sys_timer_ops {
-	int (*init)(void);
-	int (*start)(void);
-	int (*stop)(void);
-#ifndef CONFIG_GENERIC_TIME
-	unsigned long (*get_offset)(void);
-#endif
-};
-
-struct sys_timer {
-	const char		*name;
-
-	struct sys_device	dev;
-	struct sys_timer_ops	*ops;
-};
-
-#define TICK_SIZE (tick_nsec / 1000)
-
-extern struct sys_timer tmu_timer, cmt_timer, mtu2_timer;
-extern struct sys_timer *sys_timer;
-
-#ifndef CONFIG_GENERIC_TIME
-static inline unsigned long get_timer_offset(void)
-{
-	return sys_timer->ops->get_offset();
-}
-#endif
-
-/* arch/sh/kernel/timers/timer.c */
-struct sys_timer *get_sys_timer(void);
-
-/* arch/sh/kernel/time.c */
-void handle_timer_tick(void);
-
-extern struct clocksource clocksource_sh;
-
-#endif /* __ASM_SH_TIMER_H */
diff --git a/arch/sh/include/asm/types.h b/arch/sh/include/asm/types.h
index beea4e6f8dfd..b13caca62a76 100644
--- a/arch/sh/include/asm/types.h
+++ b/arch/sh/include/asm/types.h
@@ -23,9 +23,9 @@ typedef unsigned short umode_t;
 typedef u32 dma_addr_t;
 
 #ifdef CONFIG_SUPERH32
-typedef u16 opcode_t;
+typedef u16 insn_size_t;
 #else
-typedef u32 opcode_t;
+typedef u32 insn_size_t;
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/sh/include/asm/ubc.h b/arch/sh/include/asm/ubc.h
index a7b9028bbfbb..4ca4b7717371 100644
--- a/arch/sh/include/asm/ubc.h
+++ b/arch/sh/include/asm/ubc.h
@@ -42,12 +42,23 @@
 
 #define BRCR_CMFA		(1 << 15)
 #define BRCR_CMFB		(1 << 14)
+
+#if defined CONFIG_CPU_SH2A
+#define BRCR_CMFCA		(1 << 15)
+#define BRCR_CMFCB		(1 << 14)
+#define BRCR_CMFDA		(1 << 13)
+#define BRCR_CMFDB		(1 << 12)
+#define BRCR_PCBB		(1 << 6)	/* 1: after execution */
+#define BRCR_PCBA		(1 << 5)	/* 1: after execution */
+#define BRCR_PCTE		0
+#else
 #define BRCR_PCTE		(1 << 11)
 #define BRCR_PCBA		(1 << 10)	/* 1: after execution */
 #define BRCR_DBEB		(1 << 7)
 #define BRCR_PCBB		(1 << 6)
 #define BRCR_SEQ		(1 << 3)
 #define BRCR_UBDE		(1 << 0)
+#endif
 
 #ifndef __ASSEMBLY__
 /* arch/sh/kernel/cpu/ubc.S */
diff --git a/arch/sh/include/asm/unaligned-sh4a.h b/arch/sh/include/asm/unaligned-sh4a.h
index d8f89770275b..9f4dd252c981 100644
--- a/arch/sh/include/asm/unaligned-sh4a.h
+++ b/arch/sh/include/asm/unaligned-sh4a.h
@@ -3,9 +3,9 @@
 
 /*
  * SH-4A has support for unaligned 32-bit loads, and 32-bit loads only.
- * Support for 16 and 64-bit accesses are done through shifting and
- * masking relative to the endianness. Unaligned stores are not supported
- * by the instruction encoding, so these continue to use the packed
+ * Support for 64-bit accesses are done through shifting and masking
+ * relative to the endianness. Unaligned stores are not supported by the
+ * instruction encoding, so these continue to use the packed
  * struct.
  *
  * The same note as with the movli.l/movco.l pair applies here, as long
@@ -41,9 +41,9 @@ struct __una_u64 { u64 x __attribute__((packed)); };
 static inline u16 __get_unaligned_cpu16(const u8 *p)
 {
 #ifdef __LITTLE_ENDIAN
-	return __get_unaligned_cpu32(p) & 0xffff;
+	return p[0] | p[1] << 8;
 #else
-	return __get_unaligned_cpu32(p) >> 16;
+	return p[0] << 8 | p[1];
 #endif
 }
 
diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h
index 2efb819e2db3..65197086a1c5 100644
--- a/arch/sh/include/asm/unistd_32.h
+++ b/arch/sh/include/asm/unistd_32.h
@@ -343,8 +343,9 @@
 #define __NR_inotify_init1	332
 #define __NR_preadv		333
 #define __NR_pwritev		334
+#define __NR_rt_tgsigqueueinfo	335
 
-#define NR_syscalls 335
+#define NR_syscalls 336
 
 #ifdef __KERNEL__
 
diff --git a/arch/sh/include/asm/unistd_64.h b/arch/sh/include/asm/unistd_64.h
index 6eb9d2934c0f..8014aea88ec3 100644
--- a/arch/sh/include/asm/unistd_64.h
+++ b/arch/sh/include/asm/unistd_64.h
@@ -383,10 +383,11 @@
 #define __NR_inotify_init1	360
 #define __NR_preadv		361
 #define __NR_pwritev		362
+#define __NR_rt_tgsigqueueinfo	363
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 363
+#define NR_syscalls 364
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/sh/include/cpu-sh2a/cpu/ubc.h b/arch/sh/include/cpu-sh2a/cpu/ubc.h
index 8ce2fc1cf625..1192e1c761a7 100644
--- a/arch/sh/include/cpu-sh2a/cpu/ubc.h
+++ b/arch/sh/include/cpu-sh2a/cpu/ubc.h
@@ -1 +1,28 @@
-#include <cpu-sh2/cpu/ubc.h>
+/*
+ * SH-2A UBC definitions
+ *
+ * Copyright (C) 2008 Kieran Bingham
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef __ASM_CPU_SH2A_UBC_H
+#define __ASM_CPU_SH2A_UBC_H
+
+#define UBC_BARA                0xfffc0400
+#define UBC_BAMRA               0xfffc0404
+#define UBC_BBRA                0xfffc04a0	/* 16 bit access */
+#define UBC_BDRA                0xfffc0408
+#define UBC_BDMRA               0xfffc040c
+
+#define UBC_BARB                0xfffc0410
+#define UBC_BAMRB               0xfffc0414
+#define UBC_BBRB                0xfffc04b0	/* 16 bit access */
+#define UBC_BDRB                0xfffc0418
+#define UBC_BDMRB               0xfffc041c
+
+#define UBC_BRCR                0xfffc04c0
+
+#endif /* __ASM_CPU_SH2A_UBC_H */
diff --git a/arch/sh/include/cpu-sh3/cpu/timer.h b/arch/sh/include/cpu-sh3/cpu/timer.h
deleted file mode 100644
index 793acf12aa08..000000000000
--- a/arch/sh/include/cpu-sh3/cpu/timer.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * include/asm-sh/cpu-sh3/timer.h
- *
- * Copyright (C) 2004 Lineo Solutions, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#ifndef __ASM_CPU_SH3_TIMER_H
-#define __ASM_CPU_SH3_TIMER_H
-
-/*
- * ---------------------------------------------------------------------------
- * TMU Common definitions for SH3 processors
- *	SH7706
- *	SH7709S
- *	SH7727
- *	SH7729R
- *	SH7710
- *	SH7720
- *	SH7710
- * ---------------------------------------------------------------------------
- */
-
-#if  !defined(CONFIG_CPU_SUBTYPE_SH7720) && !defined(CONFIG_CPU_SUBTYPE_SH7721)
-#define TMU_TOCR	0xfffffe90	/* Byte access */
-#endif
-
-#if defined(CONFIG_CPU_SUBTYPE_SH7710) || \
-    defined(CONFIG_CPU_SUBTYPE_SH7720) || \
-    defined(CONFIG_CPU_SUBTYPE_SH7721)
-#define TMU_012_TSTR	0xa412fe92	/* Byte access */
-
-#define TMU0_TCOR	0xa412fe94	/* Long access */
-#define TMU0_TCNT	0xa412fe98	/* Long access */
-#define TMU0_TCR	0xa412fe9c	/* Word access */
-
-#define TMU1_TCOR	0xa412fea0	/* Long access */
-#define TMU1_TCNT	0xa412fea4	/* Long access */
-#define TMU1_TCR	0xa412fea8	/* Word access */
-
-#define TMU2_TCOR	0xa412feac	/* Long access */
-#define TMU2_TCNT	0xa412feb0	/* Long access */
-#define TMU2_TCR	0xa412feb4	/* Word access */
-
-#else
-#define TMU_012_TSTR	0xfffffe92	/* Byte access */
-
-#define TMU0_TCOR	0xfffffe94	/* Long access */
-#define TMU0_TCNT	0xfffffe98	/* Long access */
-#define TMU0_TCR	0xfffffe9c	/* Word access */
-
-#define TMU1_TCOR	0xfffffea0	/* Long access */
-#define TMU1_TCNT	0xfffffea4	/* Long access */
-#define TMU1_TCR	0xfffffea8	/* Word access */
-
-#define TMU2_TCOR	0xfffffeac	/* Long access */
-#define TMU2_TCNT	0xfffffeb0	/* Long access */
-#define TMU2_TCR	0xfffffeb4	/* Word access */
-#if !defined(CONFIG_CPU_SUBTYPE_SH7720) && !defined(CONFIG_CPU_SUBTYPE_SH7721)
-#define TMU2_TCPR2	0xfffffeb8	/* Long access */
-#endif
-#endif
-
-#endif /* __ASM_CPU_SH3_TIMER_H */
-
diff --git a/arch/sh/include/cpu-sh4/cpu/cache.h b/arch/sh/include/cpu-sh4/cpu/cache.h
index 1c61ebf5c8e3..7bfb9e8b069c 100644
--- a/arch/sh/include/cpu-sh4/cpu/cache.h
+++ b/arch/sh/include/cpu-sh4/cpu/cache.h
@@ -38,5 +38,7 @@
 #define CACHE_IC_ADDRESS_ARRAY	0xf0000000
 #define CACHE_OC_ADDRESS_ARRAY	0xf4000000
 
+#define RAMCR			0xFF000074
+
 #endif /* __ASM_CPU_SH4_CACHE_H */
 
diff --git a/arch/sh/include/cpu-sh4/cpu/freq.h b/arch/sh/include/cpu-sh4/cpu/freq.h
index 749d1c434337..ccf1d999db6d 100644
--- a/arch/sh/include/cpu-sh4/cpu/freq.h
+++ b/arch/sh/include/cpu-sh4/cpu/freq.h
@@ -25,6 +25,24 @@
 #elif defined(CONFIG_CPU_SUBTYPE_SH7763) || \
       defined(CONFIG_CPU_SUBTYPE_SH7780)
 #define	FRQCR			0xffc80000
+#elif defined(CONFIG_CPU_SUBTYPE_SH7724)
+#define FRQCRA			0xa4150000
+#define FRQCRB			0xa4150004
+#define VCLKCR			0xa4150048
+
+#define FCLKACR			0xa4150008
+#define FCLKBCR			0xa415000c
+#define FRQCR			FRQCRA
+#define SCLKACR			FCLKACR
+#define SCLKBCR			FCLKBCR
+#define FCLKACR			0xa4150008
+#define FCLKBCR			0xa415000c
+#define IrDACLKCR		0xa4150018
+
+#define MSTPCR0			0xa4150030
+#define MSTPCR1			0xa4150034
+#define MSTPCR2			0xa4150038
+
 #elif defined(CONFIG_CPU_SUBTYPE_SH7785)
 #define FRQCR0			0xffc80000
 #define FRQCR1			0xffc80004
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7722.h b/arch/sh/include/cpu-sh4/cpu/sh7722.h
index 4b3096f5307b..738ea43c5038 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7722.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7722.h
@@ -1,6 +1,20 @@
 #ifndef __ASM_SH7722_H__
 #define __ASM_SH7722_H__
 
+/* Boot Mode Pins:
+ *
+ * MD0: CPG - Clock Mode 0->3
+ * MD1: CPG - Clock Mode 0->3
+ * MD2: CPG - Reserved (L: Normal operation)
+ * MD3: BSC - Area0 Bus Width (16/32-bit) [CS0BCR.9,10]
+ * MD5: BSC - Endian Mode (L: Big, H: Little) [CMNCR.3]
+ * MD8: Test Mode
+ */
+
+/* Pin Function Controller:
+ * GPIO_FN_xx - GPIO used to select pin function
+ * GPIO_Pxx - GPIO mapped to real I/O pin on CPU
+ */
 enum {
 	/* PTA */
 	GPIO_PTA7, GPIO_PTA6, GPIO_PTA5, GPIO_PTA4,
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7723.h b/arch/sh/include/cpu-sh4/cpu/sh7723.h
index 9d2f6d7aa938..14c8ca936781 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7723.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7723.h
@@ -1,6 +1,20 @@
 #ifndef __ASM_SH7723_H__
 #define __ASM_SH7723_H__
 
+/* Boot Mode Pins:
+ *
+ * MD0: CPG - Clock Mode 0->3
+ * MD1: CPG - Clock Mode 0->3
+ * MD2: CPG - Reserved (L: Normal operation)
+ * MD3: BSC - Area0 Bus Width (16/32-bit) [CS0BCR.9,10]
+ * MD5: BSC - Endian Mode (L: Big, H: Little) [CMNCR.3]
+ * MD8: Test Mode
+ */
+
+/* Pin Function Controller:
+ * GPIO_FN_xx - GPIO used to select pin function
+ * GPIO_Pxx - GPIO mapped to real I/O pin on CPU
+ */
 enum {
 	/* PTA */
 	GPIO_PTA7, GPIO_PTA6, GPIO_PTA5, GPIO_PTA4,
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7724.h b/arch/sh/include/cpu-sh4/cpu/sh7724.h
new file mode 100644
index 000000000000..66fd1184359e
--- /dev/null
+++ b/arch/sh/include/cpu-sh4/cpu/sh7724.h
@@ -0,0 +1,269 @@
+#ifndef __ASM_SH7724_H__
+#define __ASM_SH7724_H__
+
+/* Boot Mode Pins:
+ *
+ * MD0: CPG - Clock Mode 0->7
+ * MD1: CPG - Clock Mode 0->7
+ * MD2: CPG - Clock Mode 0->7
+ * MD3: BSC - Area0 Bus Width (16/32-bit) [CS0BCR.9,10]
+ * MD5: BSC - Endian Mode (L: Big, H: Little) [CMNCR.3]
+ * MD8: Test Mode
+ */
+
+/* Pin Function Controller:
+ * GPIO_FN_xx - GPIO used to select pin function
+ * GPIO_Pxx - GPIO mapped to real I/O pin on CPU
+ */
+enum {
+	/* PTA */
+	GPIO_PTA7, GPIO_PTA6, GPIO_PTA5, GPIO_PTA4,
+	GPIO_PTA3, GPIO_PTA2, GPIO_PTA1, GPIO_PTA0,
+
+	/* PTB */
+	GPIO_PTB7, GPIO_PTB6, GPIO_PTB5, GPIO_PTB4,
+	GPIO_PTB3, GPIO_PTB2, GPIO_PTB1, GPIO_PTB0,
+
+	/* PTC */
+	GPIO_PTC7, GPIO_PTC6, GPIO_PTC5, GPIO_PTC4,
+	GPIO_PTC3, GPIO_PTC2, GPIO_PTC1, GPIO_PTC0,
+
+	/* PTD */
+	GPIO_PTD7, GPIO_PTD6, GPIO_PTD5, GPIO_PTD4,
+	GPIO_PTD3, GPIO_PTD2, GPIO_PTD1, GPIO_PTD0,
+
+	/* PTE */
+	GPIO_PTE7, GPIO_PTE6, GPIO_PTE5, GPIO_PTE4,
+	GPIO_PTE3, GPIO_PTE2, GPIO_PTE1, GPIO_PTE0,
+
+	/* PTF */
+	GPIO_PTF7, GPIO_PTF6, GPIO_PTF5, GPIO_PTF4,
+	GPIO_PTF3, GPIO_PTF2, GPIO_PTF1, GPIO_PTF0,
+
+	/* PTG */
+			      GPIO_PTG5, GPIO_PTG4,
+	GPIO_PTG3, GPIO_PTG2, GPIO_PTG1, GPIO_PTG0,
+
+	/* PTH */
+	GPIO_PTH7, GPIO_PTH6, GPIO_PTH5, GPIO_PTH4,
+	GPIO_PTH3, GPIO_PTH2, GPIO_PTH1, GPIO_PTH0,
+
+	/* PTJ */
+	GPIO_PTJ7, GPIO_PTJ6, GPIO_PTJ5,
+	GPIO_PTJ3, GPIO_PTJ2, GPIO_PTJ1, GPIO_PTJ0,
+
+	/* PTK */
+	GPIO_PTK7, GPIO_PTK6, GPIO_PTK5, GPIO_PTK4,
+	GPIO_PTK3, GPIO_PTK2, GPIO_PTK1, GPIO_PTK0,
+
+	/* PTL */
+	GPIO_PTL7, GPIO_PTL6, GPIO_PTL5, GPIO_PTL4,
+	GPIO_PTL3, GPIO_PTL2, GPIO_PTL1, GPIO_PTL0,
+
+	/* PTM */
+	GPIO_PTM7, GPIO_PTM6, GPIO_PTM5, GPIO_PTM4,
+	GPIO_PTM3, GPIO_PTM2, GPIO_PTM1, GPIO_PTM0,
+
+	/* PTN */
+	GPIO_PTN7, GPIO_PTN6, GPIO_PTN5, GPIO_PTN4,
+	GPIO_PTN3, GPIO_PTN2, GPIO_PTN1, GPIO_PTN0,
+
+	/* PTQ */
+	GPIO_PTQ7, GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4,
+	GPIO_PTQ3, GPIO_PTQ2, GPIO_PTQ1, GPIO_PTQ0,
+
+	/* PTR */
+	GPIO_PTR7, GPIO_PTR6, GPIO_PTR5, GPIO_PTR4,
+	GPIO_PTR3, GPIO_PTR2, GPIO_PTR1, GPIO_PTR0,
+
+	/* PTS */
+		   GPIO_PTS6, GPIO_PTS5, GPIO_PTS4,
+	GPIO_PTS3, GPIO_PTS2, GPIO_PTS1, GPIO_PTS0,
+
+	/* PTT */
+	GPIO_PTT7, GPIO_PTT6, GPIO_PTT5, GPIO_PTT4,
+	GPIO_PTT3, GPIO_PTT2, GPIO_PTT1, GPIO_PTT0,
+
+	/* PTU */
+	GPIO_PTU7, GPIO_PTU6, GPIO_PTU5, GPIO_PTU4,
+	GPIO_PTU3, GPIO_PTU2, GPIO_PTU1, GPIO_PTU0,
+
+	/* PTV */
+	GPIO_PTV7, GPIO_PTV6, GPIO_PTV5, GPIO_PTV4,
+	GPIO_PTV3, GPIO_PTV2, GPIO_PTV1, GPIO_PTV0,
+
+	/* PTW */
+	GPIO_PTW7, GPIO_PTW6, GPIO_PTW5, GPIO_PTW4,
+	GPIO_PTW3, GPIO_PTW2, GPIO_PTW1, GPIO_PTW0,
+
+	/* PTX */
+	GPIO_PTX7, GPIO_PTX6, GPIO_PTX5, GPIO_PTX4,
+	GPIO_PTX3, GPIO_PTX2, GPIO_PTX1, GPIO_PTX0,
+
+	/* PTY */
+	GPIO_PTY7, GPIO_PTY6, GPIO_PTY5, GPIO_PTY4,
+	GPIO_PTY3, GPIO_PTY2, GPIO_PTY1, GPIO_PTY0,
+
+	/* PTZ */
+	GPIO_PTZ7, GPIO_PTZ6, GPIO_PTZ5, GPIO_PTZ4,
+	GPIO_PTZ3, GPIO_PTZ2, GPIO_PTZ1, GPIO_PTZ0,
+
+	/* BSC (PTA/PTB/PTJ/PTQ/PTR/PTT) */
+	GPIO_FN_D31, GPIO_FN_D30, GPIO_FN_D29, GPIO_FN_D28,
+	GPIO_FN_D27, GPIO_FN_D26, GPIO_FN_D25, GPIO_FN_D24,
+	GPIO_FN_D23, GPIO_FN_D22, GPIO_FN_D21, GPIO_FN_D20,
+	GPIO_FN_D19, GPIO_FN_D18, GPIO_FN_D17, GPIO_FN_D16,
+	GPIO_FN_D15, GPIO_FN_D14, GPIO_FN_D13, GPIO_FN_D12,
+	GPIO_FN_D11, GPIO_FN_D10, GPIO_FN_D9,  GPIO_FN_D8,
+	GPIO_FN_D7,  GPIO_FN_D6,  GPIO_FN_D5,  GPIO_FN_D4,
+	GPIO_FN_D3,  GPIO_FN_D2,  GPIO_FN_D1,  GPIO_FN_D0,
+	GPIO_FN_A25, GPIO_FN_A24, GPIO_FN_A23, GPIO_FN_A22,
+	GPIO_FN_CS6B_CE1B,  GPIO_FN_CS6A_CE2B,
+	GPIO_FN_CS5B_CE1A,  GPIO_FN_CS5A_CE2A,
+	GPIO_FN_WE3_ICIOWR, GPIO_FN_WE2_ICIORD,
+	GPIO_FN_IOIS16,     GPIO_FN_WAIT,
+	GPIO_FN_BS,
+
+	/* KEYSC (PTA/PTB)*/
+	GPIO_FN_KEYOUT5_IN5, GPIO_FN_KEYOUT4_IN6, GPIO_FN_KEYIN4,
+	GPIO_FN_KEYIN3,  GPIO_FN_KEYIN2,  GPIO_FN_KEYIN1,  GPIO_FN_KEYIN0,
+	GPIO_FN_KEYOUT3, GPIO_FN_KEYOUT2, GPIO_FN_KEYOUT1, GPIO_FN_KEYOUT0,
+
+	/* ATAPI (PTA/PTB/PTK/PTR/PTS/PTW) */
+	GPIO_FN_IDED15, GPIO_FN_IDED14, GPIO_FN_IDED13, GPIO_FN_IDED12,
+	GPIO_FN_IDED11, GPIO_FN_IDED10, GPIO_FN_IDED9,  GPIO_FN_IDED8,
+	GPIO_FN_IDED7,  GPIO_FN_IDED6,  GPIO_FN_IDED5,  GPIO_FN_IDED4,
+	GPIO_FN_IDED3,  GPIO_FN_IDED2,  GPIO_FN_IDED1,  GPIO_FN_IDED0,
+	GPIO_FN_IDEA2,     GPIO_FN_IDEA1,     GPIO_FN_IDEA0,  GPIO_FN_IDEIOWR,
+	GPIO_FN_IODREQ,    GPIO_FN_IDECS0,    GPIO_FN_IDECS1, GPIO_FN_IDEIORD,
+	GPIO_FN_DIRECTION, GPIO_FN_EXBUF_ENB, GPIO_FN_IDERST, GPIO_FN_IODACK,
+	GPIO_FN_IDEINT,    GPIO_FN_IDEIORDY,
+
+	/* TPU (PTB/PTR/PTS) */
+	GPIO_FN_TPUTO3, GPIO_FN_TPUTO2, GPIO_FN_TPUTO1, GPIO_FN_TPUTO0,
+	GPIO_FN_TPUTI3, GPIO_FN_TPUTI2,
+
+	/* LCDC (PTC/PTD/PTE/PTF/PTM/PTR) */
+	GPIO_FN_LCDD23, GPIO_FN_LCDD22, GPIO_FN_LCDD21, GPIO_FN_LCDD20,
+	GPIO_FN_LCDD19, GPIO_FN_LCDD18, GPIO_FN_LCDD17, GPIO_FN_LCDD16,
+	GPIO_FN_LCDD15, GPIO_FN_LCDD14, GPIO_FN_LCDD13, GPIO_FN_LCDD12,
+	GPIO_FN_LCDD11, GPIO_FN_LCDD10, GPIO_FN_LCDD9,  GPIO_FN_LCDD8,
+	GPIO_FN_LCDD7,  GPIO_FN_LCDD6,  GPIO_FN_LCDD5,  GPIO_FN_LCDD4,
+	GPIO_FN_LCDD3,  GPIO_FN_LCDD2,  GPIO_FN_LCDD1,  GPIO_FN_LCDD0,
+	GPIO_FN_LCDVSYN,  GPIO_FN_LCDDISP,  GPIO_FN_LCDRS,  GPIO_FN_LCDHSYN,
+	GPIO_FN_LCDCS,    GPIO_FN_LCDDON,   GPIO_FN_LCDDCK, GPIO_FN_LCDWR,
+	GPIO_FN_LCDVEPWC, GPIO_FN_LCDVCPWC, GPIO_FN_LCDRD,  GPIO_FN_LCDLCLK,
+
+	/* SCIF0 (PTF/PTM) */
+	GPIO_FN_SCIF0_TXD, GPIO_FN_SCIF0_RXD, GPIO_FN_SCIF0_SCK,
+
+	/* SCIF1 (PTL) */
+	GPIO_FN_SCIF1_SCK, GPIO_FN_SCIF1_RXD, GPIO_FN_SCIF1_TXD,
+
+	/* SCIF2 (PTE/PTF/PTN) with LCDC, VOU */
+	GPIO_FN_SCIF2_L_TXD, GPIO_FN_SCIF2_L_SCK, GPIO_FN_SCIF2_L_RXD,
+	GPIO_FN_SCIF2_V_TXD, GPIO_FN_SCIF2_V_SCK, GPIO_FN_SCIF2_V_RXD,
+
+	/* SCIF3 (PTL/PTN/PTZ) with VOU, IRQ */
+	GPIO_FN_SCIF3_V_SCK, GPIO_FN_SCIF3_V_RXD, GPIO_FN_SCIF3_V_TXD,
+	GPIO_FN_SCIF3_V_CTS, GPIO_FN_SCIF3_V_RTS,
+	GPIO_FN_SCIF3_I_SCK, GPIO_FN_SCIF3_I_RXD, GPIO_FN_SCIF3_I_TXD,
+	GPIO_FN_SCIF3_I_CTS, GPIO_FN_SCIF3_I_RTS,
+
+	/* SCIF4 (PTE) */
+	GPIO_FN_SCIF4_SCK, GPIO_FN_SCIF4_RXD, GPIO_FN_SCIF4_TXD,
+
+	/* SCIF5 (PTS) */
+	GPIO_FN_SCIF5_SCK, GPIO_FN_SCIF5_RXD, GPIO_FN_SCIF5_TXD,
+
+	/* FSI (PTE/PTU/PTV) */
+	GPIO_FN_FSIMCKB,   GPIO_FN_FSIMCKA,    GPIO_FN_FSIOASD,
+	GPIO_FN_FSIIABCK,  GPIO_FN_FSIIALRCK,  GPIO_FN_FSIOABCK,
+	GPIO_FN_FSIOALRCK, GPIO_FN_CLKAUDIOAO, GPIO_FN_FSIIBSD,
+	GPIO_FN_FSIOBSD,   GPIO_FN_FSIIBBCK,   GPIO_FN_FSIIBLRCK,
+	GPIO_FN_FSIOBBCK,  GPIO_FN_FSIOBLRCK,  GPIO_FN_CLKAUDIOBO,
+	GPIO_FN_FSIIASD,
+
+	/* AUD (PTG) */
+	GPIO_FN_AUDCK,   GPIO_FN_AUDSYNC, GPIO_FN_AUDATA3,
+	GPIO_FN_AUDATA2, GPIO_FN_AUDATA1, GPIO_FN_AUDATA0,
+
+	/* VIO (PTS) (common?) */
+	GPIO_FN_VIO_CKO,
+
+	/* VIO0 (PTH/PTK) */
+	GPIO_FN_VIO0_D15, GPIO_FN_VIO0_D14, GPIO_FN_VIO0_D13, GPIO_FN_VIO0_D12,
+	GPIO_FN_VIO0_D11, GPIO_FN_VIO0_D10, GPIO_FN_VIO0_D9,  GPIO_FN_VIO0_D8,
+	GPIO_FN_VIO0_D7,  GPIO_FN_VIO0_D6,  GPIO_FN_VIO0_D5,  GPIO_FN_VIO0_D4,
+	GPIO_FN_VIO0_D3,  GPIO_FN_VIO0_D2,  GPIO_FN_VIO0_D1,  GPIO_FN_VIO0_D0,
+	GPIO_FN_VIO0_VD,  GPIO_FN_VIO0_CLK,
+	GPIO_FN_VIO0_FLD, GPIO_FN_VIO0_HD,
+
+	/* VIO1 (PTK/PTS) */
+	GPIO_FN_VIO1_D7,  GPIO_FN_VIO1_D6, GPIO_FN_VIO1_D5, GPIO_FN_VIO1_D4,
+	GPIO_FN_VIO1_D3,  GPIO_FN_VIO1_D2, GPIO_FN_VIO1_D1, GPIO_FN_VIO1_D0,
+	GPIO_FN_VIO1_FLD, GPIO_FN_VIO1_HD, GPIO_FN_VIO1_VD, GPIO_FN_VIO1_CLK,
+
+	/* Eth  (PTL/PTN/PTX) */
+	GPIO_FN_RMII_RXD0,    GPIO_FN_RMII_RXD1,
+	GPIO_FN_RMII_TXD0,    GPIO_FN_RMII_TXD1,
+	GPIO_FN_RMII_REF_CLK, GPIO_FN_RMII_TX_EN,
+	GPIO_FN_RMII_RX_ER,   GPIO_FN_RMII_CRS_DV,
+	GPIO_FN_LNKSTA,       GPIO_FN_MDIO,
+	GPIO_FN_MDC,
+
+	/* System (PTJ) */
+	GPIO_FN_PDSTATUS, GPIO_FN_STATUS2, GPIO_FN_STATUS0,
+
+	/* VOU (PTL/PTM/PTN*/
+	GPIO_FN_DV_D15,  GPIO_FN_DV_D14, GPIO_FN_DV_D13,   GPIO_FN_DV_D12,
+	GPIO_FN_DV_D11,  GPIO_FN_DV_D10, GPIO_FN_DV_D9,    GPIO_FN_DV_D8,
+	GPIO_FN_DV_D7,   GPIO_FN_DV_D6,  GPIO_FN_DV_D5,    GPIO_FN_DV_D4,
+	GPIO_FN_DV_D3,   GPIO_FN_DV_D2,  GPIO_FN_DV_D1,    GPIO_FN_DV_D0,
+	GPIO_FN_DV_CLKI, GPIO_FN_DV_CLK, GPIO_FN_DV_VSYNC, GPIO_FN_DV_HSYNC,
+
+	/* MSIOF0 (PTL/PTM) */
+	GPIO_FN_MSIOF0_RXD,   GPIO_FN_MSIOF0_TXD,
+	GPIO_FN_MSIOF0_MCK,   GPIO_FN_MSIOF0_TSCK,
+	GPIO_FN_MSIOF0_SS1,   GPIO_FN_MSIOF0_SS2,
+	GPIO_FN_MSIOF0_TSYNC, GPIO_FN_MSIOF0_RSCK,
+	GPIO_FN_MSIOF0_RSYNC,
+
+	/* MSIOF1 (PTV) */
+	GPIO_FN_MSIOF1_RXD,   GPIO_FN_MSIOF1_TXD,
+	GPIO_FN_MSIOF1_MCK,   GPIO_FN_MSIOF1_TSCK,
+	GPIO_FN_MSIOF1_SS1,   GPIO_FN_MSIOF1_SS2,
+	GPIO_FN_MSIOF1_TSYNC, GPIO_FN_MSIOF1_RSCK,
+	GPIO_FN_MSIOF1_RSYNC,
+
+	/* DMAC (PTU/PTX) */
+	GPIO_FN_DMAC_DACK0, GPIO_FN_DMAC_DREQ0,
+	GPIO_FN_DMAC_DACK1, GPIO_FN_DMAC_DREQ1,
+
+	/* SDHI0 (PTY) */
+	GPIO_FN_SDHI0CD, GPIO_FN_SDHI0WP, GPIO_FN_SDHI0CMD, GPIO_FN_SDHI0CLK,
+	GPIO_FN_SDHI0D3, GPIO_FN_SDHI0D2, GPIO_FN_SDHI0D1,  GPIO_FN_SDHI0D0,
+
+	/* SDHI1 (PTW) */
+	GPIO_FN_SDHI1CD, GPIO_FN_SDHI1WP, GPIO_FN_SDHI1CMD, GPIO_FN_SDHI1CLK,
+	GPIO_FN_SDHI1D3, GPIO_FN_SDHI1D2, GPIO_FN_SDHI1D1,  GPIO_FN_SDHI1D0,
+
+	/* MMC (PTW/PTX)*/
+	GPIO_FN_MMC_D7,  GPIO_FN_MMC_D6,  GPIO_FN_MMC_D5, GPIO_FN_MMC_D4,
+	GPIO_FN_MMC_D3,  GPIO_FN_MMC_D2,  GPIO_FN_MMC_D1, GPIO_FN_MMC_D0,
+	GPIO_FN_MMC_CLK, GPIO_FN_MMC_CMD,
+
+	/* IrDA (PTX) */
+	GPIO_FN_IRDA_OUT, GPIO_FN_IRDA_IN,
+
+	/* TSIF (PTX) */
+	GPIO_FN_TSIF_TS0_SDAT, GPIO_FN_TSIF_TS0_SCK,
+	GPIO_FN_TSIF_TS0_SDEN, GPIO_FN_TSIF_TS0_SPSYNC,
+
+	/* IRQ (PTZ) */
+	GPIO_FN_INTC_IRQ7, GPIO_FN_INTC_IRQ6, GPIO_FN_INTC_IRQ5,
+	GPIO_FN_INTC_IRQ4, GPIO_FN_INTC_IRQ3, GPIO_FN_INTC_IRQ2,
+	GPIO_FN_INTC_IRQ1, GPIO_FN_INTC_IRQ0,
+};
+
+#endif /* __ASM_SH7724_H__ */
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7785.h b/arch/sh/include/cpu-sh4/cpu/sh7785.h
index e4006afb735e..9dc9d91e0a8e 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7785.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7785.h
@@ -1,6 +1,31 @@
 #ifndef __ASM_SH7785_H__
 #define __ASM_SH7785_H__
 
+/* Boot Mode Pins:
+ *
+ * MODE0: CPG - Initial Pck/Bck Frequency [FRQMR1]
+ * MODE1: CPG - Initial Uck/SHck/DDRck Frequency [FRQMR1]
+ * MODE2: CPG - Reserved (L: Normal operation)
+ * MODE3: CPG - Reserved (L: Normal operation)
+ * MODE4: CPG - Initial PLL setting (72x/36x)
+ * MODE5: LBSC - Area0 Memory Type / Bus Width [CS0BCR.8]
+ * MODE6: LBSC - Area0 Memory Type / Bus Width [CS0BCR.9]
+ * MODE7: LBSC - Area0 Memory Type / Bus Width [CS0BCR.3]
+ * MODE8: LBSC - Endian Mode (L: Big, H: Little) [BCR.31]
+ * MODE9: LBSC - Master/Slave Mode (L: Slave) [BCR.30]
+ * MODE10: CPG - Clock Input (L: Ext Clk, H: Crystal)
+ * MODE11: PCI - Pin Mode (LL: PCI host, LH: PCI slave)
+ * MODE12: PCI - Pin Mode (HL: Local bus, HH: DU)
+ * MODE13: Boot Address Mode (L: 29-bit, H: 32-bit)
+ * MODE14: Reserved (H: Normal operation)
+ *
+ * More information in sh7785 manual Rev.1.00, page 1628.
+ */
+
+/* Pin Function Controller:
+ * GPIO_FN_xx - GPIO used to select pin function
+ * GPIO_Pxx - GPIO mapped to real I/O pin on CPU
+ */
 enum {
 	/* PA */
 	GPIO_PA7, GPIO_PA6, GPIO_PA5, GPIO_PA4,
diff --git a/arch/sh/include/cpu-sh4/cpu/timer.h b/arch/sh/include/cpu-sh4/cpu/timer.h
deleted file mode 100644
index d1e796b96888..000000000000
--- a/arch/sh/include/cpu-sh4/cpu/timer.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * include/asm-sh/cpu-sh4/timer.h
- *
- * Copyright (C) 2004 Lineo Solutions, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#ifndef __ASM_CPU_SH4_TIMER_H
-#define __ASM_CPU_SH4_TIMER_H
-
-/*
- * ---------------------------------------------------------------------------
- * TMU Common definitions for SH4 processors
- *	SH7750S/SH7750R
- *	SH7751/SH7751R
- *	SH7760
- *	SH-X3
- * ---------------------------------------------------------------------------
- */
-#ifdef CONFIG_CPU_SUBTYPE_SHX3
-#define TMU_012_BASE	0xffc10000
-#define TMU_345_BASE	0xffc20000
-#else
-#define TMU_012_BASE	0xffd80000
-#define TMU_345_BASE	0xfe100000
-#endif
-
-#define TMU_TOCR	TMU_012_BASE	/* Not supported on all CPUs */
-
-#define TMU_012_TSTR	(TMU_012_BASE + 0x04)
-#define TMU_345_TSTR	(TMU_345_BASE + 0x04)
-
-#define TMU0_TCOR	(TMU_012_BASE + 0x08)
-#define TMU0_TCNT	(TMU_012_BASE + 0x0c)
-#define TMU0_TCR	(TMU_012_BASE + 0x10)
-
-#define TMU1_TCOR       (TMU_012_BASE + 0x14)
-#define TMU1_TCNT       (TMU_012_BASE + 0x18)
-#define TMU1_TCR        (TMU_012_BASE + 0x1c)
-
-#define TMU2_TCOR       (TMU_012_BASE + 0x20)
-#define TMU2_TCNT       (TMU_012_BASE + 0x24)
-#define TMU2_TCR	(TMU_012_BASE + 0x28)
-#define TMU2_TCPR	(TMU_012_BASE + 0x2c)
-
-#define TMU3_TCOR	(TMU_345_BASE + 0x08)
-#define TMU3_TCNT	(TMU_345_BASE + 0x0c)
-#define TMU3_TCR	(TMU_345_BASE + 0x10)
-
-#define TMU4_TCOR	(TMU_345_BASE + 0x14)
-#define TMU4_TCNT	(TMU_345_BASE + 0x18)
-#define TMU4_TCR	(TMU_345_BASE + 0x1c)
-
-#define TMU5_TCOR	(TMU_345_BASE + 0x20)
-#define TMU5_TCNT	(TMU_345_BASE + 0x24)
-#define TMU5_TCR	(TMU_345_BASE + 0x28)
-
-#endif /* __ASM_CPU_SH4_TIMER_H */
diff --git a/arch/sh/include/cpu-sh5/cpu/irq.h b/arch/sh/include/cpu-sh5/cpu/irq.h
index f0f0756e6e84..0ccf257a72d1 100644
--- a/arch/sh/include/cpu-sh5/cpu/irq.h
+++ b/arch/sh/include/cpu-sh5/cpu/irq.h
@@ -111,7 +111,6 @@
 #define TOP_PRIORITY	15
 
 extern int intc_evt_to_irq[(0xE20/0x20)+1];
-int intc_irq_describe(char* p, int irq);
 extern int platform_int_priority[NR_INTC_IRQS];
 
 #endif /* __ASM_SH_CPU_SH5_IRQ_H */
diff --git a/arch/sh/include/mach-common/mach/sh7785lcr.h b/arch/sh/include/mach-common/mach/sh7785lcr.h
index 1ce27d5c7491..90011d435f30 100644
--- a/arch/sh/include/mach-common/mach/sh7785lcr.h
+++ b/arch/sh/include/mach-common/mach/sh7785lcr.h
@@ -9,11 +9,11 @@
  * -----------------------------+---------------+---------------
  * 0x00000000 - 0x03ffffff(CS0)	| NOR Flash	| NOR Flash
  * 0x04000000 - 0x05ffffff(CS1)	| PLD		| PLD
- * 0x06000000 - 0x07ffffff(CS1)	| reserved	| I2C
+ * 0x06000000 - 0x07ffffff(CS1)	| I2C		| I2C
  * 0x08000000 - 0x0bffffff(CS2)	| USB		| DDR SDRAM
  * 0x0c000000 - 0x0fffffff(CS3)	| SD		| DDR SDRAM
  * 0x10000000 - 0x13ffffff(CS4)	| SM107		| SM107
- * 0x14000000 - 0x17ffffff(CS5)	| I2C		| USB
+ * 0x14000000 - 0x17ffffff(CS5)	| reserved	| USB
  * 0x18000000 - 0x1bffffff(CS6)	| reserved	| SD
  * 0x40000000 - 0x5fffffff	| DDR SDRAM	| (cannot use)
  *
@@ -32,6 +32,9 @@
 #define PLD_VERSR		(PLD_BASE_ADDR + 0x0c)
 #define PLD_MMSR		(PLD_BASE_ADDR + 0x0e)
 
+#define PCA9564_ADDR		0x06000000	/* I2C */
+#define PCA9564_SIZE		0x00000100
+
 #define SM107_MEM_ADDR		0x10000000
 #define SM107_MEM_SIZE		0x00e00000
 #define SM107_REG_ADDR		0x13e00000
@@ -40,16 +43,13 @@
 #if defined(CONFIG_SH_SH7785LCR_29BIT_PHYSMAPS)
 #define R8A66597_ADDR		0x14000000	/* USB */
 #define CG200_ADDR		0x18000000	/* SD */
-#define PCA9564_ADDR		0x06000000	/* I2C */
 #else
 #define R8A66597_ADDR		0x08000000
 #define CG200_ADDR		0x0c000000
-#define PCA9564_ADDR		0x14000000
 #endif
 
 #define R8A66597_SIZE		0x00000100
 #define CG200_SIZE		0x00010000
-#define PCA9564_SIZE		0x00000100
 
 #endif  /* __ASM_SH_RENESAS_SH7785LCR_H */
 
diff --git a/arch/sh/include/mach-dreamcast/mach/pci.h b/arch/sh/include/mach-dreamcast/mach/pci.h
index 75fc9009e092..0314d975e626 100644
--- a/arch/sh/include/mach-dreamcast/mach/pci.h
+++ b/arch/sh/include/mach-dreamcast/mach/pci.h
@@ -21,5 +21,7 @@
 
 #define	GAPSPCI_IRQ		HW_EVENT_EXTERNAL
 
+extern struct pci_ops gapspci_pci_ops;
+
 #endif /* __ASM_SH_DREAMCAST_PCI_H */
 
diff --git a/arch/sh/include/mach-se/mach/se7724.h b/arch/sh/include/mach-se/mach/se7724.h
new file mode 100644
index 000000000000..74164b60d0db
--- /dev/null
+++ b/arch/sh/include/mach-se/mach/se7724.h
@@ -0,0 +1,67 @@
+#ifndef __ASM_SH_SE7724_H
+#define __ASM_SH_SE7724_H
+
+/*
+ * linux/include/asm-sh/se7724.h
+ *
+ * Copyright (C) 2009 Renesas Solutions Corp.
+ *
+ * Kuninori Morimoto <morimoto.kuninori@renesas.com>
+ *
+ * Hitachi UL SolutionEngine 7724 Support.
+ *
+ * Based on se7722.h
+ * Copyright (C) 2007  Nobuhiro Iwamatsu
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ */
+#include <asm/addrspace.h>
+
+#define PA_LED		(0xba203000)	/* 8bit LED */
+#define IRQ_MODE	(0xba200010)
+#define IRQ0_SR		(0xba200014)
+#define IRQ1_SR		(0xba200018)
+#define IRQ2_SR		(0xba20001c)
+#define IRQ0_MR		(0xba200020)
+#define IRQ1_MR		(0xba200024)
+#define IRQ2_MR		(0xba200028)
+
+/* IRQ */
+#define IRQ0_IRQ        32
+#define IRQ1_IRQ        33
+#define IRQ2_IRQ        34
+
+/* Bits in IRQ012 registers */
+#define SE7724_FPGA_IRQ_BASE	220
+
+/* IRQ0 */
+#define IRQ0_BASE	SE7724_FPGA_IRQ_BASE
+#define IRQ0_KEY	(IRQ0_BASE + 12)
+#define IRQ0_RMII	(IRQ0_BASE + 13)
+#define IRQ0_SMC	(IRQ0_BASE + 14)
+#define IRQ0_MASK	0x7fff
+#define IRQ0_END	IRQ0_SMC
+/* IRQ1 */
+#define IRQ1_BASE	(IRQ0_END + 1)
+#define IRQ1_TS		(IRQ1_BASE + 0)
+#define IRQ1_MASK	0x0001
+#define IRQ1_END	IRQ1_TS
+/* IRQ2 */
+#define IRQ2_BASE	(IRQ1_END + 1)
+#define IRQ2_USB0	(IRQ1_BASE + 0)
+#define IRQ2_USB1	(IRQ1_BASE + 1)
+#define IRQ2_MASK	0x0003
+#define IRQ2_END	IRQ2_USB1
+
+#define SE7724_FPGA_IRQ_NR	(IRQ2_END - IRQ0_BASE)
+
+/* arch/sh/boards/se/7724/irq.c */
+void init_se7724_IRQ(void);
+
+#define __IO_PREFIX		se7724
+#include <asm/io_generic.h>
+
+#endif  /* __ASM_SH_SE7724_H */
diff --git a/arch/sh/kernel/Makefile_32 b/arch/sh/kernel/Makefile_32
index 82a3a150c00d..9411e3e31e68 100644
--- a/arch/sh/kernel/Makefile_32
+++ b/arch/sh/kernel/Makefile_32
@@ -11,10 +11,10 @@ endif
 
 obj-y	:= debugtraps.o idle.o io.o io_generic.o irq.o			\
 	   machvec.o process_32.o ptrace_32.o setup.o signal_32.o	\
-	   sys_sh.o sys_sh32.o syscalls_32.o time_32.o topology.o	\
+	   sys_sh.o sys_sh32.o syscalls_32.o time.o topology.o	\
 	   traps.o traps_32.o
 
-obj-y				+= cpu/ timers/
+obj-y				+= cpu/
 obj-$(CONFIG_VSYSCALL)		+= vsyscall/
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SH_STANDARD_BIOS)	+= sh_bios.o
@@ -32,4 +32,6 @@ obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_DUMP_CODE)		+= disassemble.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o
 
+obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= localtimer.o
+
 EXTRA_CFLAGS += -Werror
diff --git a/arch/sh/kernel/Makefile_64 b/arch/sh/kernel/Makefile_64
index fe425d7f6871..67b9f6c6326b 100644
--- a/arch/sh/kernel/Makefile_64
+++ b/arch/sh/kernel/Makefile_64
@@ -2,19 +2,18 @@ extra-y	:= head_64.o init_task.o vmlinux.lds
 
 obj-y	:= debugtraps.o idle.o io.o io_generic.o irq.o machvec.o process_64.o \
 	   ptrace_64.o setup.o signal_64.o sys_sh.o sys_sh64.o \
-	   syscalls_64.o time_64.o topology.o traps.o traps_64.o
+	   syscalls_64.o time.o topology.o traps.o traps_64.o
 
-obj-y				+= cpu/ timers/
-obj-$(CONFIG_VSYSCALL)		+= vsyscall/
+obj-y				+= cpu/
 obj-$(CONFIG_SMP)		+= smp.o
-obj-$(CONFIG_SH_STANDARD_BIOS)	+= sh_bios.o
 obj-$(CONFIG_SH_CPU_FREQ)	+= cpufreq.o
 obj-$(CONFIG_MODULES)		+= sh_ksyms_64.o module.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_IO_TRAPPED)	+= io_trapped.o
 obj-$(CONFIG_GENERIC_GPIO)	+= gpio.o
 
+obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= localtimer.o
+
 EXTRA_CFLAGS += -Werror
diff --git a/arch/sh/kernel/cpu/Makefile b/arch/sh/kernel/cpu/Makefile
index 2600641a483f..eecad7cbd61e 100644
--- a/arch/sh/kernel/cpu/Makefile
+++ b/arch/sh/kernel/cpu/Makefile
@@ -17,5 +17,6 @@ obj-$(CONFIG_ARCH_SHMOBILE)	+= shmobile/
 
 obj-$(CONFIG_UBC_WAKEUP)	+= ubc.o
 obj-$(CONFIG_SH_ADC)		+= adc.o
+obj-$(CONFIG_SH_CLK_CPG)	+= clock-cpg.o
 
 obj-y	+= irq/ init.o clock.o
diff --git a/arch/sh/kernel/cpu/clock-cpg.c b/arch/sh/kernel/cpu/clock-cpg.c
new file mode 100644
index 000000000000..275942e58e4f
--- /dev/null
+++ b/arch/sh/kernel/cpu/clock-cpg.c
@@ -0,0 +1,256 @@
+#include <linux/clk.h>
+#include <linux/compiler.h>
+#include <linux/bootmem.h>
+#include <linux/io.h>
+#include <asm/clock.h>
+
+static int sh_clk_mstp32_enable(struct clk *clk)
+{
+	__raw_writel(__raw_readl(clk->enable_reg) & ~(1 << clk->enable_bit),
+		     clk->enable_reg);
+	return 0;
+}
+
+static void sh_clk_mstp32_disable(struct clk *clk)
+{
+	__raw_writel(__raw_readl(clk->enable_reg) | (1 << clk->enable_bit),
+		     clk->enable_reg);
+}
+
+static struct clk_ops sh_clk_mstp32_clk_ops = {
+	.enable		= sh_clk_mstp32_enable,
+	.disable	= sh_clk_mstp32_disable,
+	.recalc		= followparent_recalc,
+};
+
+int __init sh_clk_mstp32_register(struct clk *clks, int nr)
+{
+	struct clk *clkp;
+	int ret = 0;
+	int k;
+
+	for (k = 0; !ret && (k < nr); k++) {
+		clkp = clks + k;
+		clkp->ops = &sh_clk_mstp32_clk_ops;
+		ret |= clk_register(clkp);
+	}
+
+	return ret;
+}
+
+static long sh_clk_div_round_rate(struct clk *clk, unsigned long rate)
+{
+	return clk_rate_table_round(clk, clk->freq_table, rate);
+}
+
+static int sh_clk_div6_divisors[64] = {
+	1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
+	17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32,
+	33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48,
+	49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64
+};
+
+static struct clk_div_mult_table sh_clk_div6_table = {
+	.divisors = sh_clk_div6_divisors,
+	.nr_divisors = ARRAY_SIZE(sh_clk_div6_divisors),
+};
+
+static unsigned long sh_clk_div6_recalc(struct clk *clk)
+{
+	struct clk_div_mult_table *table = &sh_clk_div6_table;
+	unsigned int idx;
+
+	clk_rate_table_build(clk, clk->freq_table, table->nr_divisors,
+			     table, NULL);
+
+	idx = __raw_readl(clk->enable_reg) & 0x003f;
+
+	return clk->freq_table[idx].frequency;
+}
+
+static int sh_clk_div6_set_rate(struct clk *clk,
+				unsigned long rate, int algo_id)
+{
+	unsigned long value;
+	int idx;
+
+	idx = clk_rate_table_find(clk, clk->freq_table, rate);
+	if (idx < 0)
+		return idx;
+
+	value = __raw_readl(clk->enable_reg);
+	value &= ~0x3f;
+	value |= idx;
+	__raw_writel(value, clk->enable_reg);
+	return 0;
+}
+
+static int sh_clk_div6_enable(struct clk *clk)
+{
+	unsigned long value;
+	int ret;
+
+	ret = sh_clk_div6_set_rate(clk, clk->rate, 0);
+	if (ret == 0) {
+		value = __raw_readl(clk->enable_reg);
+		value &= ~0x100; /* clear stop bit to enable clock */
+		__raw_writel(value, clk->enable_reg);
+	}
+	return ret;
+}
+
+static void sh_clk_div6_disable(struct clk *clk)
+{
+	unsigned long value;
+
+	value = __raw_readl(clk->enable_reg);
+	value |= 0x100; /* stop clock */
+	value |= 0x3f; /* VDIV bits must be non-zero, overwrite divider */
+	__raw_writel(value, clk->enable_reg);
+}
+
+static struct clk_ops sh_clk_div6_clk_ops = {
+	.recalc		= sh_clk_div6_recalc,
+	.round_rate	= sh_clk_div_round_rate,
+	.set_rate	= sh_clk_div6_set_rate,
+	.enable		= sh_clk_div6_enable,
+	.disable	= sh_clk_div6_disable,
+};
+
+int __init sh_clk_div6_register(struct clk *clks, int nr)
+{
+	struct clk *clkp;
+	void *freq_table;
+	int nr_divs = sh_clk_div6_table.nr_divisors;
+	int freq_table_size = sizeof(struct cpufreq_frequency_table);
+	int ret = 0;
+	int k;
+
+	freq_table_size *= (nr_divs + 1);
+
+	freq_table = alloc_bootmem(freq_table_size * nr);
+	if (!freq_table)
+		return -ENOMEM;
+
+	for (k = 0; !ret && (k < nr); k++) {
+		clkp = clks + k;
+
+		clkp->ops = &sh_clk_div6_clk_ops;
+		clkp->id = -1;
+		clkp->freq_table = freq_table + (k * freq_table_size);
+		clkp->freq_table[nr_divs].frequency = CPUFREQ_TABLE_END;
+
+		ret = clk_register(clkp);
+	}
+
+	return ret;
+}
+
+static unsigned long sh_clk_div4_recalc(struct clk *clk)
+{
+	struct clk_div_mult_table *table = clk->priv;
+	unsigned int idx;
+
+	clk_rate_table_build(clk, clk->freq_table, table->nr_divisors,
+			     table, &clk->arch_flags);
+
+	idx = (__raw_readl(clk->enable_reg) >> clk->enable_bit) & 0x000f;
+
+	return clk->freq_table[idx].frequency;
+}
+
+static struct clk_ops sh_clk_div4_clk_ops = {
+	.recalc		= sh_clk_div4_recalc,
+	.round_rate	= sh_clk_div_round_rate,
+};
+
+int __init sh_clk_div4_register(struct clk *clks, int nr,
+				struct clk_div_mult_table *table)
+{
+	struct clk *clkp;
+	void *freq_table;
+	int nr_divs = table->nr_divisors;
+	int freq_table_size = sizeof(struct cpufreq_frequency_table);
+	int ret = 0;
+	int k;
+
+	freq_table_size *= (nr_divs + 1);
+
+	freq_table = alloc_bootmem(freq_table_size * nr);
+	if (!freq_table)
+		return -ENOMEM;
+
+	for (k = 0; !ret && (k < nr); k++) {
+		clkp = clks + k;
+
+		clkp->ops = &sh_clk_div4_clk_ops;
+		clkp->id = -1;
+		clkp->priv = table;
+
+		clkp->freq_table = freq_table + (k * freq_table_size);
+		clkp->freq_table[nr_divs].frequency = CPUFREQ_TABLE_END;
+
+		ret = clk_register(clkp);
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_SH_CLK_CPG_LEGACY
+static struct clk master_clk = {
+	.name		= "master_clk",
+	.flags		= CLK_ENABLE_ON_INIT,
+	.rate		= CONFIG_SH_PCLK_FREQ,
+};
+
+static struct clk peripheral_clk = {
+	.name		= "peripheral_clk",
+	.parent		= &master_clk,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+static struct clk bus_clk = {
+	.name		= "bus_clk",
+	.parent		= &master_clk,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+static struct clk cpu_clk = {
+	.name		= "cpu_clk",
+	.parent		= &master_clk,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+/*
+ * The ordering of these clocks matters, do not change it.
+ */
+static struct clk *onchip_clocks[] = {
+	&master_clk,
+	&peripheral_clk,
+	&bus_clk,
+	&cpu_clk,
+};
+
+int __init __deprecated cpg_clk_init(void)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < ARRAY_SIZE(onchip_clocks); i++) {
+		struct clk *clk = onchip_clocks[i];
+		arch_init_clk_ops(&clk->ops, i);
+		if (clk->ops)
+			ret |= clk_register(clk);
+	}
+
+	return ret;
+}
+
+/*
+ * Placeholder for compatability, until the lazy CPUs do this
+ * on their own.
+ */
+int __init __weak arch_clk_init(void)
+{
+	return cpg_clk_init();
+}
+#endif /* CONFIG_SH_CPG_CLK_LEGACY */
diff --git a/arch/sh/kernel/cpu/clock.c b/arch/sh/kernel/cpu/clock.c
index 1dc896483b59..f3a46be2ae81 100644
--- a/arch/sh/kernel/cpu/clock.c
+++ b/arch/sh/kernel/cpu/clock.c
@@ -1,15 +1,19 @@
 /*
  * arch/sh/kernel/cpu/clock.c - SuperH clock framework
  *
- *  Copyright (C) 2005, 2006, 2007  Paul Mundt
+ *  Copyright (C) 2005 - 2009  Paul Mundt
  *
  * This clock framework is derived from the OMAP version by:
  *
- *	Copyright (C) 2004 - 2005 Nokia Corporation
+ *	Copyright (C) 2004 - 2008 Nokia Corporation
  *	Written by Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com>
  *
  *  Modified for omap shared clock framework by Tony Lindgren <tony@atomide.com>
  *
+ *  With clkdev bits:
+ *
+ *	Copyright (C) 2008 Russell King.
+ *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
@@ -19,134 +23,159 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
-#include <linux/kref.h>
 #include <linux/kobject.h>
 #include <linux/sysdev.h>
 #include <linux/seq_file.h>
 #include <linux/err.h>
 #include <linux/platform_device.h>
-#include <linux/proc_fs.h>
+#include <linux/debugfs.h>
+#include <linux/cpufreq.h>
 #include <asm/clock.h>
-#include <asm/timer.h>
+#include <asm/machvec.h>
 
 static LIST_HEAD(clock_list);
 static DEFINE_SPINLOCK(clock_lock);
 static DEFINE_MUTEX(clock_list_sem);
 
-/*
- * Each subtype is expected to define the init routines for these clocks,
- * as each subtype (or processor family) will have these clocks at the
- * very least. These are all provided through the CPG, which even some of
- * the more quirky parts (such as ST40, SH4-202, etc.) still have.
- *
- * The processor-specific code is expected to register any additional
- * clock sources that are of interest.
- */
-static struct clk master_clk = {
-	.name		= "master_clk",
-	.flags		= CLK_ALWAYS_ENABLED | CLK_RATE_PROPAGATES,
-	.rate		= CONFIG_SH_PCLK_FREQ,
-};
-
-static struct clk module_clk = {
-	.name		= "module_clk",
-	.parent		= &master_clk,
-	.flags		= CLK_ALWAYS_ENABLED | CLK_RATE_PROPAGATES,
-};
-
-static struct clk bus_clk = {
-	.name		= "bus_clk",
-	.parent		= &master_clk,
-	.flags		= CLK_ALWAYS_ENABLED | CLK_RATE_PROPAGATES,
-};
-
-static struct clk cpu_clk = {
-	.name		= "cpu_clk",
-	.parent		= &master_clk,
-	.flags		= CLK_ALWAYS_ENABLED,
-};
-
-/*
- * The ordering of these clocks matters, do not change it.
- */
-static struct clk *onchip_clocks[] = {
-	&master_clk,
-	&module_clk,
-	&bus_clk,
-	&cpu_clk,
-};
-
-static void propagate_rate(struct clk *clk)
+void clk_rate_table_build(struct clk *clk,
+			  struct cpufreq_frequency_table *freq_table,
+			  int nr_freqs,
+			  struct clk_div_mult_table *src_table,
+			  unsigned long *bitmap)
 {
-	struct clk *clkp;
+	unsigned long mult, div;
+	unsigned long freq;
+	int i;
 
-	list_for_each_entry(clkp, &clock_list, node) {
-		if (likely(clkp->parent != clk))
-			continue;
-		if (likely(clkp->ops && clkp->ops->recalc))
-			clkp->ops->recalc(clkp);
-		if (unlikely(clkp->flags & CLK_RATE_PROPAGATES))
-			propagate_rate(clkp);
+	for (i = 0; i < nr_freqs; i++) {
+		div = 1;
+		mult = 1;
+
+		if (src_table->divisors && i < src_table->nr_divisors)
+			div = src_table->divisors[i];
+
+		if (src_table->multipliers && i < src_table->nr_multipliers)
+			mult = src_table->multipliers[i];
+
+		if (!div || !mult || (bitmap && !test_bit(i, bitmap)))
+			freq = CPUFREQ_ENTRY_INVALID;
+		else
+			freq = clk->parent->rate * mult / div;
+
+		freq_table[i].index = i;
+		freq_table[i].frequency = freq;
 	}
+
+	/* Termination entry */
+	freq_table[i].index = i;
+	freq_table[i].frequency = CPUFREQ_TABLE_END;
 }
 
-static int __clk_enable(struct clk *clk)
+long clk_rate_table_round(struct clk *clk,
+			  struct cpufreq_frequency_table *freq_table,
+			  unsigned long rate)
 {
-	/*
-	 * See if this is the first time we're enabling the clock, some
-	 * clocks that are always enabled still require "special"
-	 * initialization. This is especially true if the clock mode
-	 * changes and the clock needs to hunt for the proper set of
-	 * divisors to use before it can effectively recalc.
-	 */
-	if (unlikely(atomic_read(&clk->kref.refcount) == 1))
-		if (clk->ops && clk->ops->init)
-			clk->ops->init(clk);
+	unsigned long rate_error, rate_error_prev = ~0UL;
+	unsigned long rate_best_fit = rate;
+	unsigned long highest, lowest;
+	int i;
 
-	kref_get(&clk->kref);
+	highest = lowest = 0;
 
-	if (clk->flags & CLK_ALWAYS_ENABLED)
-		return 0;
+	for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		unsigned long freq = freq_table[i].frequency;
 
-	if (likely(clk->ops && clk->ops->enable))
-		clk->ops->enable(clk);
+		if (freq == CPUFREQ_ENTRY_INVALID)
+			continue;
+
+		if (freq > highest)
+			highest = freq;
+		if (freq < lowest)
+			lowest = freq;
+
+		rate_error = abs(freq - rate);
+		if (rate_error < rate_error_prev) {
+			rate_best_fit = freq;
+			rate_error_prev = rate_error;
+		}
+
+		if (rate_error == 0)
+			break;
+	}
+
+	if (rate >= highest)
+		rate_best_fit = highest;
+	if (rate <= lowest)
+		rate_best_fit = lowest;
+
+	return rate_best_fit;
+}
+
+int clk_rate_table_find(struct clk *clk,
+			struct cpufreq_frequency_table *freq_table,
+			unsigned long rate)
+{
+	int i;
+
+	for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		unsigned long freq = freq_table[i].frequency;
+
+		if (freq == CPUFREQ_ENTRY_INVALID)
+			continue;
+
+		if (freq == rate)
+			return i;
+	}
+
+	return -ENOENT;
+}
+
+/* Used for clocks that always have same value as the parent clock */
+unsigned long followparent_recalc(struct clk *clk)
+{
+	return clk->parent ? clk->parent->rate : 0;
+}
+
+int clk_reparent(struct clk *child, struct clk *parent)
+{
+	list_del_init(&child->sibling);
+	if (parent)
+		list_add(&child->sibling, &parent->children);
+	child->parent = parent;
+
+	/* now do the debugfs renaming to reattach the child
+	   to the proper parent */
 
 	return 0;
 }
 
-int clk_enable(struct clk *clk)
+/* Propagate rate to children */
+void propagate_rate(struct clk *tclk)
 {
-	unsigned long flags;
-	int ret;
+	struct clk *clkp;
 
-	if (!clk)
-		return -EINVAL;
+	list_for_each_entry(clkp, &tclk->children, sibling) {
+		if (clkp->ops && clkp->ops->recalc)
+			clkp->rate = clkp->ops->recalc(clkp);
 
-	clk_enable(clk->parent);
-
-	spin_lock_irqsave(&clock_lock, flags);
-	ret = __clk_enable(clk);
-	spin_unlock_irqrestore(&clock_lock, flags);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(clk_enable);
-
-static void clk_kref_release(struct kref *kref)
-{
-	/* Nothing to do */
+		propagate_rate(clkp);
+	}
 }
 
 static void __clk_disable(struct clk *clk)
 {
-	int count = kref_put(&clk->kref, clk_kref_release);
-
-	if (clk->flags & CLK_ALWAYS_ENABLED)
+	if (clk->usecount == 0) {
+		printk(KERN_ERR "Trying disable clock %s with 0 usecount\n",
+		       clk->name);
+		WARN_ON(1);
 		return;
+	}
 
-	if (!count) {	/* count reaches zero, disable the clock */
+	if (!(--clk->usecount)) {
 		if (likely(clk->ops && clk->ops->disable))
 			clk->ops->disable(clk);
+		if (likely(clk->parent))
+			__clk_disable(clk->parent);
 	}
 }
 
@@ -160,29 +189,98 @@ void clk_disable(struct clk *clk)
 	spin_lock_irqsave(&clock_lock, flags);
 	__clk_disable(clk);
 	spin_unlock_irqrestore(&clock_lock, flags);
-
-	clk_disable(clk->parent);
 }
 EXPORT_SYMBOL_GPL(clk_disable);
 
+static int __clk_enable(struct clk *clk)
+{
+	int ret = 0;
+
+	if (clk->usecount++ == 0) {
+		if (clk->parent) {
+			ret = __clk_enable(clk->parent);
+			if (unlikely(ret))
+				goto err;
+		}
+
+		if (clk->ops && clk->ops->enable) {
+			ret = clk->ops->enable(clk);
+			if (ret) {
+				if (clk->parent)
+					__clk_disable(clk->parent);
+				goto err;
+			}
+		}
+	}
+
+	return ret;
+err:
+	clk->usecount--;
+	return ret;
+}
+
+int clk_enable(struct clk *clk)
+{
+	unsigned long flags;
+	int ret;
+
+	if (!clk)
+		return -EINVAL;
+
+	spin_lock_irqsave(&clock_lock, flags);
+	ret = __clk_enable(clk);
+	spin_unlock_irqrestore(&clock_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_enable);
+
+static LIST_HEAD(root_clks);
+
+/**
+ * recalculate_root_clocks - recalculate and propagate all root clocks
+ *
+ * Recalculates all root clocks (clocks with no parent), which if the
+ * clock's .recalc is set correctly, should also propagate their rates.
+ * Called at init.
+ */
+void recalculate_root_clocks(void)
+{
+	struct clk *clkp;
+
+	list_for_each_entry(clkp, &root_clks, sibling) {
+		if (clkp->ops && clkp->ops->recalc)
+			clkp->rate = clkp->ops->recalc(clkp);
+		propagate_rate(clkp);
+	}
+}
+
 int clk_register(struct clk *clk)
 {
+	if (clk == NULL || IS_ERR(clk))
+		return -EINVAL;
+
+	/*
+	 * trap out already registered clocks
+	 */
+	if (clk->node.next || clk->node.prev)
+		return 0;
+
 	mutex_lock(&clock_list_sem);
 
+	INIT_LIST_HEAD(&clk->children);
+	clk->usecount = 0;
+
+	if (clk->parent)
+		list_add(&clk->sibling, &clk->parent->children);
+	else
+		list_add(&clk->sibling, &root_clks);
+
 	list_add(&clk->node, &clock_list);
-	kref_init(&clk->kref);
-
+	if (clk->ops && clk->ops->init)
+		clk->ops->init(clk);
 	mutex_unlock(&clock_list_sem);
 
-	if (clk->flags & CLK_ALWAYS_ENABLED) {
-		pr_debug( "Clock '%s' is ALWAYS_ENABLED\n", clk->name);
-		if (clk->ops && clk->ops->init)
-			clk->ops->init(clk);
-		if (clk->ops && clk->ops->enable)
-			clk->ops->enable(clk);
-		pr_debug( "Enabled.");
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(clk_register);
@@ -190,11 +288,21 @@ EXPORT_SYMBOL_GPL(clk_register);
 void clk_unregister(struct clk *clk)
 {
 	mutex_lock(&clock_list_sem);
+	list_del(&clk->sibling);
 	list_del(&clk->node);
 	mutex_unlock(&clock_list_sem);
 }
 EXPORT_SYMBOL_GPL(clk_unregister);
 
+static void clk_enable_init_clocks(void)
+{
+	struct clk *clkp;
+
+	list_for_each_entry(clkp, &clock_list, node)
+		if (clkp->flags & CLK_ENABLE_ON_INIT)
+			clk_enable(clkp);
+}
+
 unsigned long clk_get_rate(struct clk *clk)
 {
 	return clk->rate;
@@ -210,56 +318,59 @@ EXPORT_SYMBOL_GPL(clk_set_rate);
 int clk_set_rate_ex(struct clk *clk, unsigned long rate, int algo_id)
 {
 	int ret = -EOPNOTSUPP;
+	unsigned long flags;
+
+	spin_lock_irqsave(&clock_lock, flags);
 
 	if (likely(clk->ops && clk->ops->set_rate)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&clock_lock, flags);
 		ret = clk->ops->set_rate(clk, rate, algo_id);
-		spin_unlock_irqrestore(&clock_lock, flags);
+		if (ret != 0)
+			goto out_unlock;
+	} else {
+		clk->rate = rate;
+		ret = 0;
 	}
 
-	if (unlikely(clk->flags & CLK_RATE_PROPAGATES))
-		propagate_rate(clk);
+	if (clk->ops && clk->ops->recalc)
+		clk->rate = clk->ops->recalc(clk);
+
+	propagate_rate(clk);
+
+out_unlock:
+	spin_unlock_irqrestore(&clock_lock, flags);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(clk_set_rate_ex);
 
-void clk_recalc_rate(struct clk *clk)
-{
-	if (likely(clk->ops && clk->ops->recalc)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&clock_lock, flags);
-		clk->ops->recalc(clk);
-		spin_unlock_irqrestore(&clock_lock, flags);
-	}
-
-	if (unlikely(clk->flags & CLK_RATE_PROPAGATES))
-		propagate_rate(clk);
-}
-EXPORT_SYMBOL_GPL(clk_recalc_rate);
-
 int clk_set_parent(struct clk *clk, struct clk *parent)
 {
+	unsigned long flags;
 	int ret = -EINVAL;
-	struct clk *old;
 
 	if (!parent || !clk)
 		return ret;
+	if (clk->parent == parent)
+		return 0;
 
-	old = clk->parent;
-	if (likely(clk->ops && clk->ops->set_parent)) {
-		unsigned long flags;
-		spin_lock_irqsave(&clock_lock, flags);
-		ret = clk->ops->set_parent(clk, parent);
-		spin_unlock_irqrestore(&clock_lock, flags);
-		clk->parent = (ret ? old : parent);
-	}
+	spin_lock_irqsave(&clock_lock, flags);
+	if (clk->usecount == 0) {
+		if (clk->ops->set_parent)
+			ret = clk->ops->set_parent(clk, parent);
+		else
+			ret = clk_reparent(clk, parent);
+
+		if (ret == 0) {
+			pr_debug("clock: set parent of %s to %s (new rate %ld)\n",
+				 clk->name, clk->parent->name, clk->rate);
+			if (clk->ops->recalc)
+				clk->rate = clk->ops->recalc(clk);
+			propagate_rate(clk);
+		}
+	} else
+		ret = -EBUSY;
+	spin_unlock_irqrestore(&clock_lock, flags);
 
-	if (unlikely(clk->flags & CLK_RATE_PROPAGATES))
-		propagate_rate(clk);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(clk_set_parent);
@@ -286,15 +397,70 @@ long clk_round_rate(struct clk *clk, unsigned long rate)
 }
 EXPORT_SYMBOL_GPL(clk_round_rate);
 
+/*
+ * Find the correct struct clk for the device and connection ID.
+ * We do slightly fuzzy matching here:
+ *  An entry with a NULL ID is assumed to be a wildcard.
+ *  If an entry has a device ID, it must match
+ *  If an entry has a connection ID, it must match
+ * Then we take the most specific entry - with the following
+ * order of precidence: dev+con > dev only > con only.
+ */
+static struct clk *clk_find(const char *dev_id, const char *con_id)
+{
+	struct clk_lookup *p;
+	struct clk *clk = NULL;
+	int match, best = 0;
+
+	list_for_each_entry(p, &clock_list, node) {
+		match = 0;
+		if (p->dev_id) {
+			if (!dev_id || strcmp(p->dev_id, dev_id))
+				continue;
+			match += 2;
+		}
+		if (p->con_id) {
+			if (!con_id || strcmp(p->con_id, con_id))
+				continue;
+			match += 1;
+		}
+		if (match == 0)
+			continue;
+
+		if (match > best) {
+			clk = p->clk;
+			best = match;
+		}
+	}
+	return clk;
+}
+
+struct clk *clk_get_sys(const char *dev_id, const char *con_id)
+{
+	struct clk *clk;
+
+	mutex_lock(&clock_list_sem);
+	clk = clk_find(dev_id, con_id);
+	mutex_unlock(&clock_list_sem);
+
+	return clk ? clk : ERR_PTR(-ENOENT);
+}
+EXPORT_SYMBOL_GPL(clk_get_sys);
+
 /*
  * Returns a clock. Note that we first try to use device id on the bus
  * and clock name. If this fails, we try to use clock name only.
  */
 struct clk *clk_get(struct device *dev, const char *id)
 {
+	const char *dev_id = dev ? dev_name(dev) : NULL;
 	struct clk *p, *clk = ERR_PTR(-ENOENT);
 	int idno;
 
+	clk = clk_get_sys(dev_id, id);
+	if (clk && !IS_ERR(clk))
+		return clk;
+
 	if (dev == NULL || dev->bus != &platform_bus_type)
 		idno = -1;
 	else
@@ -330,36 +496,6 @@ void clk_put(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(clk_put);
 
-void __init __attribute__ ((weak))
-arch_init_clk_ops(struct clk_ops **ops, int type)
-{
-}
-
-int __init __attribute__ ((weak))
-arch_clk_init(void)
-{
-	return 0;
-}
-
-static int show_clocks(char *buf, char **start, off_t off,
-		       int len, int *eof, void *data)
-{
-	struct clk *clk;
-	char *p = buf;
-
-	list_for_each_entry_reverse(clk, &clock_list, node) {
-		unsigned long rate = clk_get_rate(clk);
-
-		p += sprintf(p, "%-12s\t: %ld.%02ldMHz\t%s\n", clk->name,
-			     rate / 1000000, (rate % 1000000) / 10000,
-			     ((clk->flags & CLK_ALWAYS_ENABLED) ||
-			      (atomic_read(&clk->kref.refcount) != 1)) ?
-			     "enabled" : "disabled");
-	}
-
-	return p - buf;
-}
-
 #ifdef CONFIG_PM
 static int clks_sysdev_suspend(struct sys_device *dev, pm_message_t state)
 {
@@ -369,20 +505,22 @@ static int clks_sysdev_suspend(struct sys_device *dev, pm_message_t state)
 	switch (state.event) {
 	case PM_EVENT_ON:
 		/* Resumeing from hibernation */
-		if (prev_state.event == PM_EVENT_FREEZE) {
-			list_for_each_entry(clkp, &clock_list, node)
-				if (likely(clkp->ops)) {
-					unsigned long rate = clkp->rate;
+		if (prev_state.event != PM_EVENT_FREEZE)
+			break;
 
-					if (likely(clkp->ops->set_parent))
-						clkp->ops->set_parent(clkp,
-							clkp->parent);
-					if (likely(clkp->ops->set_rate))
-						clkp->ops->set_rate(clkp,
-							rate, NO_CHANGE);
-					else if (likely(clkp->ops->recalc))
-						clkp->ops->recalc(clkp);
-					}
+		list_for_each_entry(clkp, &clock_list, node) {
+			if (likely(clkp->ops)) {
+				unsigned long rate = clkp->rate;
+
+				if (likely(clkp->ops->set_parent))
+					clkp->ops->set_parent(clkp,
+						clkp->parent);
+				if (likely(clkp->ops->set_rate))
+					clkp->ops->set_rate(clkp,
+						rate, NO_CHANGE);
+				else if (likely(clkp->ops->recalc))
+					clkp->rate = clkp->ops->recalc(clkp);
+			}
 		}
 		break;
 	case PM_EVENT_FREEZE:
@@ -426,34 +564,116 @@ subsys_initcall(clk_sysdev_init);
 
 int __init clk_init(void)
 {
-	int i, ret = 0;
+	int ret;
 
-	BUG_ON(!master_clk.rate);
-
-	for (i = 0; i < ARRAY_SIZE(onchip_clocks); i++) {
-		struct clk *clk = onchip_clocks[i];
-
-		arch_init_clk_ops(&clk->ops, i);
-		ret |= clk_register(clk);
+	ret = arch_clk_init();
+	if (unlikely(ret)) {
+		pr_err("%s: CPU clock registration failed.\n", __func__);
+		return ret;
 	}
 
-	ret |= arch_clk_init();
+	if (sh_mv.mv_clk_init) {
+		ret = sh_mv.mv_clk_init();
+		if (unlikely(ret)) {
+			pr_err("%s: machvec clock initialization failed.\n",
+			       __func__);
+			return ret;
+		}
+	}
 
 	/* Kick the child clocks.. */
-	propagate_rate(&master_clk);
-	propagate_rate(&bus_clk);
+	recalculate_root_clocks();
+
+	/* Enable the necessary init clocks */
+	clk_enable_init_clocks();
 
 	return ret;
 }
 
-static int __init clk_proc_init(void)
-{
-	struct proc_dir_entry *p;
-	p = create_proc_read_entry("clocks", S_IRUSR, NULL,
-				   show_clocks, NULL);
-	if (unlikely(!p))
-		return -EINVAL;
+/*
+ *	debugfs support to trace clock tree hierarchy and attributes
+ */
+static struct dentry *clk_debugfs_root;
 
+static int clk_debugfs_register_one(struct clk *c)
+{
+	int err;
+	struct dentry *d, *child;
+	struct clk *pa = c->parent;
+	char s[255];
+	char *p = s;
+
+	p += sprintf(p, "%s", c->name);
+	if (c->id >= 0)
+		sprintf(p, ":%d", c->id);
+	d = debugfs_create_dir(s, pa ? pa->dentry : clk_debugfs_root);
+	if (!d)
+		return -ENOMEM;
+	c->dentry = d;
+
+	d = debugfs_create_u8("usecount", S_IRUGO, c->dentry, (u8 *)&c->usecount);
+	if (!d) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	d = debugfs_create_u32("rate", S_IRUGO, c->dentry, (u32 *)&c->rate);
+	if (!d) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	d = debugfs_create_x32("flags", S_IRUGO, c->dentry, (u32 *)&c->flags);
+	if (!d) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	return 0;
+
+err_out:
+	d = c->dentry;
+	list_for_each_entry(child, &d->d_subdirs, d_u.d_child)
+		debugfs_remove(child);
+	debugfs_remove(c->dentry);
+	return err;
+}
+
+static int clk_debugfs_register(struct clk *c)
+{
+	int err;
+	struct clk *pa = c->parent;
+
+	if (pa && !pa->dentry) {
+		err = clk_debugfs_register(pa);
+		if (err)
+			return err;
+	}
+
+	if (!c->dentry) {
+		err = clk_debugfs_register_one(c);
+		if (err)
+			return err;
+	}
 	return 0;
 }
-subsys_initcall(clk_proc_init);
+
+static int __init clk_debugfs_init(void)
+{
+	struct clk *c;
+	struct dentry *d;
+	int err;
+
+	d = debugfs_create_dir("clock", NULL);
+	if (!d)
+		return -ENOMEM;
+	clk_debugfs_root = d;
+
+	list_for_each_entry(c, &clock_list, node) {
+		err = clk_debugfs_register(c);
+		if (err)
+			goto err_out;
+	}
+	return 0;
+err_out:
+	debugfs_remove(clk_debugfs_root); /* REVISIT: Cleanup correctly */
+	return err;
+}
+late_initcall(clk_debugfs_init);
diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c
index d29e69c156f0..ad85421099cd 100644
--- a/arch/sh/kernel/cpu/init.c
+++ b/arch/sh/kernel/cpu/init.c
@@ -62,6 +62,11 @@ static void __init speculative_execution_init(void)
 #define speculative_execution_init()	do { } while (0)
 #endif
 
+/* 2nd-level cache init */
+void __uses_jump_to_uncached __attribute__ ((weak)) l2_cache_init(void)
+{
+}
+
 /*
  * Generic first-level cache init
  */
@@ -146,6 +151,8 @@ static void __uses_jump_to_uncached cache_init(void)
 	flags &= ~CCR_CACHE_ENABLE;
 #endif
 
+	l2_cache_init();
+
 	ctrl_outl(flags, CCR);
 	back_to_cached();
 }
diff --git a/arch/sh/kernel/cpu/irq/imask.c b/arch/sh/kernel/cpu/irq/imask.c
index 301b505c4278..6b5d191eec3a 100644
--- a/arch/sh/kernel/cpu/irq/imask.c
+++ b/arch/sh/kernel/cpu/irq/imask.c
@@ -18,38 +18,17 @@
 #include <linux/spinlock.h>
 #include <linux/cache.h>
 #include <linux/irq.h>
+#include <linux/bitmap.h>
 #include <asm/system.h>
 #include <asm/irq.h>
 
 /* Bitmap of IRQ masked */
-static unsigned long imask_mask = 0x7fff;
-static int interrupt_priority = 0;
-
-static void enable_imask_irq(unsigned int irq);
-static void disable_imask_irq(unsigned int irq);
-static void shutdown_imask_irq(unsigned int irq);
-static void mask_and_ack_imask(unsigned int);
-static void end_imask_irq(unsigned int irq);
-
 #define IMASK_PRIORITY	15
 
-static unsigned int startup_imask_irq(unsigned int irq)
-{
-	/* Nothing to do */
-	return 0; /* never anything pending */
-}
+static DECLARE_BITMAP(imask_mask, IMASK_PRIORITY);
+static int interrupt_priority;
 
-static struct hw_interrupt_type imask_irq_type = {
-	.typename = "SR.IMASK",
-	.startup = startup_imask_irq,
-	.shutdown = shutdown_imask_irq,
-	.enable = enable_imask_irq,
-	.disable = disable_imask_irq,
-	.ack = mask_and_ack_imask,
-	.end = end_imask_irq
-};
-
-void static inline set_interrupt_registers(int ip)
+static inline void set_interrupt_registers(int ip)
 {
 	unsigned long __dummy;
 
@@ -72,42 +51,31 @@ void static inline set_interrupt_registers(int ip)
 		     : "t");
 }
 
-static void disable_imask_irq(unsigned int irq)
+static void mask_imask_irq(unsigned int irq)
 {
-	clear_bit(irq, &imask_mask);
+	clear_bit(irq, imask_mask);
 	if (interrupt_priority < IMASK_PRIORITY - irq)
 		interrupt_priority = IMASK_PRIORITY - irq;
-
 	set_interrupt_registers(interrupt_priority);
 }
 
-static void enable_imask_irq(unsigned int irq)
+static void unmask_imask_irq(unsigned int irq)
 {
-	set_bit(irq, &imask_mask);
-	interrupt_priority = IMASK_PRIORITY - ffz(imask_mask);
-
+	set_bit(irq, imask_mask);
+	interrupt_priority = IMASK_PRIORITY -
+		find_first_zero_bit(imask_mask, IMASK_PRIORITY);
 	set_interrupt_registers(interrupt_priority);
 }
 
-static void mask_and_ack_imask(unsigned int irq)
-{
-	disable_imask_irq(irq);
-}
-
-static void end_imask_irq(unsigned int irq)
-{
-	if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS)))
-		enable_imask_irq(irq);
-}
-
-static void shutdown_imask_irq(unsigned int irq)
-{
-	/* Nothing to do */
-}
+static struct irq_chip imask_irq_chip = {
+	.typename	= "SR.IMASK",
+	.mask		= mask_imask_irq,
+	.unmask		= unmask_imask_irq,
+	.mask_ack	= mask_imask_irq,
+};
 
 void make_imask_irq(unsigned int irq)
 {
-	disable_irq_nosync(irq);
-	irq_desc[irq].chip = &imask_irq_type;
-	enable_irq(irq);
+	set_irq_chip_and_handler_name(irq, &imask_irq_chip,
+				      handle_level_irq, "level");
 }
diff --git a/arch/sh/kernel/cpu/irq/intc-sh5.c b/arch/sh/kernel/cpu/irq/intc-sh5.c
index 726f0335da76..6c092f1f5557 100644
--- a/arch/sh/kernel/cpu/irq/intc-sh5.c
+++ b/arch/sh/kernel/cpu/irq/intc-sh5.c
@@ -84,7 +84,7 @@ static void disable_intc_irq(unsigned int irq);
 static void mask_and_ack_intc(unsigned int);
 static void end_intc_irq(unsigned int irq);
 
-static struct hw_interrupt_type intc_irq_type = {
+static struct irq_chip intc_irq_type = {
 	.typename = "INTC",
 	.startup = startup_intc_irq,
 	.shutdown = shutdown_intc_irq,
@@ -152,43 +152,13 @@ static void end_intc_irq(unsigned int irq)
 	enable_intc_irq(irq);
 }
 
-/* For future use, if we ever support IRLM=0) */
-void make_intc_irq(unsigned int irq)
-{
-	disable_irq_nosync(irq);
-	irq_desc[irq].chip = &intc_irq_type;
-	disable_intc_irq(irq);
-}
-
-#if defined(CONFIG_PROC_FS) && defined(CONFIG_SYSCTL)
-static int IRQ_to_vectorN[NR_INTC_IRQS] = {
-	0x12, 0x15, 0x18, 0x1B, 0x40, 0x41, 0x42, 0x43, /*  0- 7 */
-	  -1,   -1,   -1,   -1, 0x50, 0x51, 0x52, 0x53,	/*  8-15 */
-	0x54, 0x55, 0x32, 0x33, 0x34, 0x35, 0x36,   -1, /* 16-23 */
-	  -1,   -1,   -1,   -1,   -1,   -1,   -1,   -1, /* 24-31 */
-	0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x38,	/* 32-39 */
-        0x39, 0x3A, 0x3B,   -1,   -1,   -1,   -1,   -1, /* 40-47 */
-	  -1,   -1,   -1,   -1,   -1,   -1,   -1,   -1, /* 48-55 */
-	  -1,   -1,   -1,   -1,   -1,   -1,   -1, 0x2B, /* 56-63 */
-
-};
-
-int intc_irq_describe(char* p, int irq)
-{
-	if (irq < NR_INTC_IRQS)
-		return sprintf(p, "(0x%3x)", IRQ_to_vectorN[irq]*0x20);
-	else
-		return 0;
-}
-#endif
-
 void __init plat_irq_setup(void)
 {
 	unsigned long long __dummy0, __dummy1=~0x00000000100000f0;
 	unsigned long reg;
 	int i;
 
-	intc_virt = onchip_remap(INTC_BASE, 1024, "INTC");
+	intc_virt = (unsigned long)ioremap_nocache(INTC_BASE, 1024);
 	if (!intc_virt) {
 		panic("Unable to remap INTC\n");
 	}
@@ -196,7 +166,7 @@ void __init plat_irq_setup(void)
 
 	/* Set default: per-line enable/disable, priority driven ack/eoi */
 	for (i = 0; i < NR_INTC_IRQS; i++)
-		irq_desc[i].chip = &intc_irq_type;
+		set_irq_chip_and_handler(i, &intc_irq_type, handle_level_irq);
 
 
 	/* Disable all interrupts and set all priorities to 0 to avoid trouble */
diff --git a/arch/sh/kernel/cpu/irq/ipr.c b/arch/sh/kernel/cpu/irq/ipr.c
index 3eb17ee5540e..808d99a48efb 100644
--- a/arch/sh/kernel/cpu/irq/ipr.c
+++ b/arch/sh/kernel/cpu/irq/ipr.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
+#include <linux/topology.h>
 
 static inline struct ipr_desc *get_ipr_desc(unsigned int irq)
 {
@@ -59,10 +60,18 @@ void register_ipr_controller(struct ipr_desc *desc)
 
 	for (i = 0; i < desc->nr_irqs; i++) {
 		struct ipr_data *p = desc->ipr_data + i;
+		struct irq_desc *irq_desc;
 
 		BUG_ON(p->ipr_idx >= desc->nr_offsets);
 		BUG_ON(!desc->ipr_offsets[p->ipr_idx]);
 
+		irq_desc = irq_to_desc_alloc_node(p->irq, numa_node_id());
+		if (unlikely(!irq_desc)) {
+			printk(KERN_INFO "can not get irq_desc for %d\n",
+			       p->irq);
+			continue;
+		}
+
 		disable_irq_nosync(p->irq);
 		set_irq_chip_and_handler_name(p->irq, &desc->chip,
 				      handle_level_irq, "level");
diff --git a/arch/sh/kernel/cpu/sh2/clock-sh7619.c b/arch/sh/kernel/cpu/sh2/clock-sh7619.c
index d2c157917999..4fe863170e31 100644
--- a/arch/sh/kernel/cpu/sh2/clock-sh7619.c
+++ b/arch/sh/kernel/cpu/sh2/clock-sh7619.c
@@ -38,32 +38,27 @@ static struct clk_ops sh7619_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FREQCR) & 0x0007);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7619_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
-	clk->rate = clk->parent->rate / pll1rate[(ctrl_inw(FREQCR) >> 8) & 7];
+	return clk->parent->rate / pll1rate[(ctrl_inw(FREQCR) >> 8) & 7];
 }
 
 static struct clk_ops sh7619_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
-{
-	clk->rate = clk->parent->rate;
-}
-
 static struct clk_ops sh7619_cpu_clk_ops = {
-	.recalc		= cpu_clk_recalc,
+	.recalc		= followparent_recalc,
 };
 
 static struct clk_ops *sh7619_clk_ops[] = {
@@ -78,4 +73,3 @@ void __init arch_init_clk_ops(struct clk_ops **ops, int idx)
 	if (idx < ARRAY_SIZE(sh7619_clk_ops))
 		*ops = sh7619_clk_ops[idx];
 }
-
diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
index 0e32d8e448ca..13798733f2db 100644
--- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c
+++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
@@ -12,6 +12,8 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
+#include <linux/io.h>
 
 enum {
 	UNUSED = 0,
@@ -109,9 +111,75 @@ static struct platform_device eth_device = {
 	.resource = eth_resources,
 };
 
+static struct sh_timer_config cmt0_platform_data = {
+	.name = "CMT0",
+	.channel_offset = 0x02,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 125,
+	.clocksource_rating = 0, /* disabled due to code generation issues */
+};
+
+static struct resource cmt0_resources[] = {
+	[0] = {
+		.name	= "CMT0",
+		.start	= 0xf84a0072,
+		.end	= 0xf84a0077,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 86,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt0_device = {
+	.name		= "sh_cmt",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &cmt0_platform_data,
+	},
+	.resource	= cmt0_resources,
+	.num_resources	= ARRAY_SIZE(cmt0_resources),
+};
+
+static struct sh_timer_config cmt1_platform_data = {
+	.name = "CMT1",
+	.channel_offset = 0x08,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 125,
+	.clocksource_rating = 0, /* disabled due to code generation issues */
+};
+
+static struct resource cmt1_resources[] = {
+	[0] = {
+		.name	= "CMT1",
+		.start	= 0xf84a0078,
+		.end	= 0xf84a007d,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 87,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt1_device = {
+	.name		= "sh_cmt",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &cmt1_platform_data,
+	},
+	.resource	= cmt1_resources,
+	.num_resources	= ARRAY_SIZE(cmt1_resources),
+};
+
 static struct platform_device *sh7619_devices[] __initdata = {
 	&sci_device,
 	&eth_device,
+	&cmt0_device,
+	&cmt1_device,
 };
 
 static int __init sh7619_devices_setup(void)
@@ -125,3 +193,19 @@ void __init plat_irq_setup(void)
 {
 	register_intc_controller(&intc_desc);
 }
+
+static struct platform_device *sh7619_early_devices[] __initdata = {
+	&cmt0_device,
+	&cmt1_device,
+};
+
+#define STBCR3 0xf80a0000
+
+void __init plat_early_device_setup(void)
+{
+	/* enable CMT clock */
+	__raw_writeb(__raw_readb(STBCR3) & ~0x10, STBCR3);
+
+	early_platform_add_devices(sh7619_early_devices,
+				   ARRAY_SIZE(sh7619_early_devices));
+}
diff --git a/arch/sh/kernel/cpu/sh2a/clock-sh7201.c b/arch/sh/kernel/cpu/sh2a/clock-sh7201.c
index 4a5e59732334..7814c76159a7 100644
--- a/arch/sh/kernel/cpu/sh2a/clock-sh7201.c
+++ b/arch/sh/kernel/cpu/sh2a/clock-sh7201.c
@@ -34,37 +34,37 @@ static const int pfc_divisors[]={1,2,3,4,6,8,12};
 
 static void master_clk_init(struct clk *clk)
 {
-	clk->rate = 10000000 * PLL2 * pll1rate[(ctrl_inw(FREQCR) >> 8) & 0x0007];
+	return 10000000 * PLL2 * pll1rate[(ctrl_inw(FREQCR) >> 8) & 0x0007];
 }
 
 static struct clk_ops sh7201_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FREQCR) & 0x0007);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7201_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FREQCR) & 0x0007);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7201_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inw(FREQCR) >> 4) & 0x0007);
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh7201_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh2a/clock-sh7203.c b/arch/sh/kernel/cpu/sh2a/clock-sh7203.c
index fb781329848a..940986965102 100644
--- a/arch/sh/kernel/cpu/sh2a/clock-sh7203.c
+++ b/arch/sh/kernel/cpu/sh2a/clock-sh7203.c
@@ -46,33 +46,28 @@ static struct clk_ops sh7203_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FREQCR) & 0x0007);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7203_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FREQCR) & 0x0007);
-	clk->rate = clk->parent->rate / pfc_divisors[idx-2];
+	return clk->parent->rate / pfc_divisors[idx-2];
 }
 
 static struct clk_ops sh7203_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
-{
-	clk->rate = clk->parent->rate;
-}
-
 static struct clk_ops sh7203_cpu_clk_ops = {
-	.recalc		= cpu_clk_recalc,
+	.recalc		= followparent_recalc,
 };
 
 static struct clk_ops *sh7203_clk_ops[] = {
diff --git a/arch/sh/kernel/cpu/sh2a/clock-sh7206.c b/arch/sh/kernel/cpu/sh2a/clock-sh7206.c
index 82d7f991ef6b..c2268bdeceeb 100644
--- a/arch/sh/kernel/cpu/sh2a/clock-sh7206.c
+++ b/arch/sh/kernel/cpu/sh2a/clock-sh7206.c
@@ -41,29 +41,29 @@ static struct clk_ops sh7206_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FREQCR) & 0x0007);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7206_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
-	clk->rate = clk->parent->rate / pll1rate[(ctrl_inw(FREQCR) >> 8) & 0x0007];
+	return clk->parent->rate / pll1rate[(ctrl_inw(FREQCR) >> 8) & 0x0007];
 }
 
 static struct clk_ops sh7206_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FREQCR) & 0x0007);
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh7206_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh2a/setup-mxg.c b/arch/sh/kernel/cpu/sh2a/setup-mxg.c
index 844293723cfc..869c2da4820b 100644
--- a/arch/sh/kernel/cpu/sh2a/setup-mxg.c
+++ b/arch/sh/kernel/cpu/sh2a/setup-mxg.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
 
 enum {
 	UNUSED = 0,
@@ -24,7 +25,7 @@ enum {
 
 	SCIF0, SCIF1,
 
-	MTU2_GROUP1, MTU2_GROUP2, MTU2_GROUP3, MTU2_GROUP4, MTU2_GROUP5
+	MTU2_GROUP1, MTU2_GROUP2, MTU2_GROUP3, MTU2_GROUP4, MTU2_GROUP5,
 	MTU2_TGI3B, MTU2_TGI3C,
 
 	/* interrupt groups */
@@ -113,6 +114,99 @@ static struct intc_mask_reg mask_registers[] __initdata = {
 static DECLARE_INTC_DESC(intc_desc, "mxg", vectors, groups,
 			 mask_registers, prio_registers, NULL);
 
+static struct sh_timer_config mtu2_0_platform_data = {
+	.name = "MTU2_0",
+	.channel_offset = -0x80,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_0_resources[] = {
+	[0] = {
+		.name	= "MTU2_0",
+		.start	= 0xff801300,
+		.end	= 0xff801326,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 228,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_0_device = {
+	.name		= "sh_mtu2",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &mtu2_0_platform_data,
+	},
+	.resource	= mtu2_0_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_0_resources),
+};
+
+static struct sh_timer_config mtu2_1_platform_data = {
+	.name = "MTU2_1",
+	.channel_offset = -0x100,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_1_resources[] = {
+	[0] = {
+		.name	= "MTU2_1",
+		.start	= 0xff801380,
+		.end	= 0xff801390,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 234,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_1_device = {
+	.name		= "sh_mtu2",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &mtu2_1_platform_data,
+	},
+	.resource	= mtu2_1_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_1_resources),
+};
+
+static struct sh_timer_config mtu2_2_platform_data = {
+	.name = "MTU2_2",
+	.channel_offset = 0x80,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_2_resources[] = {
+	[0] = {
+		.name	= "MTU2_2",
+		.start	= 0xff801000,
+		.end	= 0xff80100a,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 240,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_2_device = {
+	.name		= "sh_mtu2",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &mtu2_2_platform_data,
+	},
+	.resource	= mtu2_2_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_2_resources),
+};
+
 static struct plat_sci_port sci_platform_data[] = {
 	{
 		.mapbase	= 0xff804000,
@@ -134,6 +228,9 @@ static struct platform_device sci_device = {
 
 static struct platform_device *mxg_devices[] __initdata = {
 	&sci_device,
+	&mtu2_0_device,
+	&mtu2_1_device,
+	&mtu2_2_device,
 };
 
 static int __init mxg_devices_setup(void)
@@ -147,3 +244,15 @@ void __init plat_irq_setup(void)
 {
 	register_intc_controller(&intc_desc);
 }
+
+static struct platform_device *mxg_early_devices[] __initdata = {
+	&mtu2_0_device,
+	&mtu2_1_device,
+	&mtu2_2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(mxg_early_devices,
+				   ARRAY_SIZE(mxg_early_devices));
+}
diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c
index 00f42f9e3f5c..d8febe128066 100644
--- a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c
+++ b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c
@@ -12,6 +12,8 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
+#include <linux/io.h>
 
 enum {
 	UNUSED = 0,
@@ -249,9 +251,105 @@ static struct platform_device rtc_device = {
 	.resource	= rtc_resources,
 };
 
+static struct sh_timer_config mtu2_0_platform_data = {
+	.name = "MTU2_0",
+	.channel_offset = -0x80,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_0_resources[] = {
+	[0] = {
+		.name	= "MTU2_0",
+		.start	= 0xfffe4300,
+		.end	= 0xfffe4326,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 108,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_0_device = {
+	.name		= "sh_mtu2",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &mtu2_0_platform_data,
+	},
+	.resource	= mtu2_0_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_0_resources),
+};
+
+static struct sh_timer_config mtu2_1_platform_data = {
+	.name = "MTU2_1",
+	.channel_offset = -0x100,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_1_resources[] = {
+	[0] = {
+		.name	= "MTU2_1",
+		.start	= 0xfffe4380,
+		.end	= 0xfffe4390,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 116,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_1_device = {
+	.name		= "sh_mtu2",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &mtu2_1_platform_data,
+	},
+	.resource	= mtu2_1_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_1_resources),
+};
+
+static struct sh_timer_config mtu2_2_platform_data = {
+	.name = "MTU2_2",
+	.channel_offset = 0x80,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_2_resources[] = {
+	[0] = {
+		.name	= "MTU2_2",
+		.start	= 0xfffe4000,
+		.end	= 0xfffe400a,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 124,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_2_device = {
+	.name		= "sh_mtu2",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &mtu2_2_platform_data,
+	},
+	.resource	= mtu2_2_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_2_resources),
+};
+
 static struct platform_device *sh7201_devices[] __initdata = {
 	&sci_device,
 	&rtc_device,
+	&mtu2_0_device,
+	&mtu2_1_device,
+	&mtu2_2_device,
 };
 
 static int __init sh7201_devices_setup(void)
@@ -265,3 +363,20 @@ void __init plat_irq_setup(void)
 {
 	register_intc_controller(&intc_desc);
 }
+
+static struct platform_device *sh7201_early_devices[] __initdata = {
+	&mtu2_0_device,
+	&mtu2_1_device,
+	&mtu2_2_device,
+};
+
+#define STBCR3 0xfffe0408
+
+void __init plat_early_device_setup(void)
+{
+	/* enable MTU2 clock */
+	__raw_writeb(__raw_readb(STBCR3) & ~0x20, STBCR3);
+
+	early_platform_add_devices(sh7201_early_devices,
+				   ARRAY_SIZE(sh7201_early_devices));
+}
diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c
index 820dfb2e8656..62e3039d2398 100644
--- a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c
+++ b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c
@@ -11,6 +11,8 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
+#include <linux/io.h>
 
 enum {
 	UNUSED = 0,
@@ -205,6 +207,132 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config cmt0_platform_data = {
+	.name = "CMT0",
+	.channel_offset = 0x02,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 125,
+	.clocksource_rating = 0, /* disabled due to code generation issues */
+};
+
+static struct resource cmt0_resources[] = {
+	[0] = {
+		.name	= "CMT0",
+		.start	= 0xfffec002,
+		.end	= 0xfffec007,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 142,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt0_device = {
+	.name		= "sh_cmt",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &cmt0_platform_data,
+	},
+	.resource	= cmt0_resources,
+	.num_resources	= ARRAY_SIZE(cmt0_resources),
+};
+
+static struct sh_timer_config cmt1_platform_data = {
+	.name = "CMT1",
+	.channel_offset = 0x08,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 125,
+	.clocksource_rating = 0, /* disabled due to code generation issues */
+};
+
+static struct resource cmt1_resources[] = {
+	[0] = {
+		.name	= "CMT1",
+		.start	= 0xfffec008,
+		.end	= 0xfffec00d,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 143,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt1_device = {
+	.name		= "sh_cmt",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &cmt1_platform_data,
+	},
+	.resource	= cmt1_resources,
+	.num_resources	= ARRAY_SIZE(cmt1_resources),
+};
+
+static struct sh_timer_config mtu2_0_platform_data = {
+	.name = "MTU2_0",
+	.channel_offset = -0x80,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_0_resources[] = {
+	[0] = {
+		.name	= "MTU2_0",
+		.start	= 0xfffe4300,
+		.end	= 0xfffe4326,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 146,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_0_device = {
+	.name		= "sh_mtu2",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &mtu2_0_platform_data,
+	},
+	.resource	= mtu2_0_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_0_resources),
+};
+
+static struct sh_timer_config mtu2_1_platform_data = {
+	.name = "MTU2_1",
+	.channel_offset = -0x100,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_1_resources[] = {
+	[0] = {
+		.name	= "MTU2_1",
+		.start	= 0xfffe4380,
+		.end	= 0xfffe4390,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 153,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_1_device = {
+	.name		= "sh_mtu2",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &mtu2_1_platform_data,
+	},
+	.resource	= mtu2_1_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_1_resources),
+};
+
 static struct resource rtc_resources[] = {
 	[0] = {
 		.start	= 0xffff2000,
@@ -227,6 +355,10 @@ static struct platform_device rtc_device = {
 
 static struct platform_device *sh7203_devices[] __initdata = {
 	&sci_device,
+	&cmt0_device,
+	&cmt1_device,
+	&mtu2_0_device,
+	&mtu2_1_device,
 	&rtc_device,
 };
 
@@ -241,3 +373,25 @@ void __init plat_irq_setup(void)
 {
 	register_intc_controller(&intc_desc);
 }
+
+static struct platform_device *sh7203_early_devices[] __initdata = {
+	&cmt0_device,
+	&cmt1_device,
+	&mtu2_0_device,
+	&mtu2_1_device,
+};
+
+#define STBCR3 0xfffe0408
+#define STBCR4 0xfffe040c
+
+void __init plat_early_device_setup(void)
+{
+	/* enable CMT clock */
+	__raw_writeb(__raw_readb(STBCR4) & ~0x04, STBCR4);
+
+	/* enable MTU2 clock */
+	__raw_writeb(__raw_readb(STBCR3) & ~0x20, STBCR3);
+
+	early_platform_add_devices(sh7203_early_devices,
+				   ARRAY_SIZE(sh7203_early_devices));
+}
diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c
index c46a8355726d..3e6f3d7a58be 100644
--- a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c
+++ b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c
@@ -12,6 +12,8 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
+#include <linux/io.h>
 
 enum {
 	UNUSED = 0,
@@ -165,8 +167,170 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config cmt0_platform_data = {
+	.name = "CMT0",
+	.channel_offset = 0x02,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 125,
+	.clocksource_rating = 0, /* disabled due to code generation issues */
+};
+
+static struct resource cmt0_resources[] = {
+	[0] = {
+		.name	= "CMT0",
+		.start	= 0xfffec002,
+		.end	= 0xfffec007,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 140,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt0_device = {
+	.name		= "sh_cmt",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &cmt0_platform_data,
+	},
+	.resource	= cmt0_resources,
+	.num_resources	= ARRAY_SIZE(cmt0_resources),
+};
+
+static struct sh_timer_config cmt1_platform_data = {
+	.name = "CMT1",
+	.channel_offset = 0x08,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 125,
+	.clocksource_rating = 0, /* disabled due to code generation issues */
+};
+
+static struct resource cmt1_resources[] = {
+	[0] = {
+		.name	= "CMT1",
+		.start	= 0xfffec008,
+		.end	= 0xfffec00d,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 144,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt1_device = {
+	.name		= "sh_cmt",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &cmt1_platform_data,
+	},
+	.resource	= cmt1_resources,
+	.num_resources	= ARRAY_SIZE(cmt1_resources),
+};
+
+static struct sh_timer_config mtu2_0_platform_data = {
+	.name = "MTU2_0",
+	.channel_offset = -0x80,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_0_resources[] = {
+	[0] = {
+		.name	= "MTU2_0",
+		.start	= 0xfffe4300,
+		.end	= 0xfffe4326,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 156,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_0_device = {
+	.name		= "sh_mtu2",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &mtu2_0_platform_data,
+	},
+	.resource	= mtu2_0_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_0_resources),
+};
+
+static struct sh_timer_config mtu2_1_platform_data = {
+	.name = "MTU2_1",
+	.channel_offset = -0x100,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_1_resources[] = {
+	[0] = {
+		.name	= "MTU2_1",
+		.start	= 0xfffe4380,
+		.end	= 0xfffe4390,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 164,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_1_device = {
+	.name		= "sh_mtu2",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &mtu2_1_platform_data,
+	},
+	.resource	= mtu2_1_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_1_resources),
+};
+
+static struct sh_timer_config mtu2_2_platform_data = {
+	.name = "MTU2_2",
+	.channel_offset = 0x80,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource mtu2_2_resources[] = {
+	[0] = {
+		.name	= "MTU2_2",
+		.start	= 0xfffe4000,
+		.end	= 0xfffe400a,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 180,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mtu2_2_device = {
+	.name		= "sh_mtu2",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &mtu2_2_platform_data,
+	},
+	.resource	= mtu2_2_resources,
+	.num_resources	= ARRAY_SIZE(mtu2_2_resources),
+};
+
 static struct platform_device *sh7206_devices[] __initdata = {
 	&sci_device,
+	&cmt0_device,
+	&cmt1_device,
+	&mtu2_0_device,
+	&mtu2_1_device,
+	&mtu2_2_device,
 };
 
 static int __init sh7206_devices_setup(void)
@@ -180,3 +344,26 @@ void __init plat_irq_setup(void)
 {
 	register_intc_controller(&intc_desc);
 }
+
+static struct platform_device *sh7206_early_devices[] __initdata = {
+	&cmt0_device,
+	&cmt1_device,
+	&mtu2_0_device,
+	&mtu2_1_device,
+	&mtu2_2_device,
+};
+
+#define STBCR3 0xfffe0408
+#define STBCR4 0xfffe040c
+
+void __init plat_early_device_setup(void)
+{
+	/* enable CMT clock */
+	__raw_writeb(__raw_readb(STBCR4) & ~0x04, STBCR4);
+
+	/* enable MTU2 clock */
+	__raw_writeb(__raw_readb(STBCR3) & ~0x20, STBCR3);
+
+	early_platform_add_devices(sh7206_early_devices,
+				   ARRAY_SIZE(sh7206_early_devices));
+}
diff --git a/arch/sh/kernel/cpu/sh3/clock-sh3.c b/arch/sh/kernel/cpu/sh3/clock-sh3.c
index c3c945958baf..27b8738f0b09 100644
--- a/arch/sh/kernel/cpu/sh3/clock-sh3.c
+++ b/arch/sh/kernel/cpu/sh3/clock-sh3.c
@@ -38,36 +38,36 @@ static struct clk_ops sh3_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = ((frqcr & 0x2000) >> 11) | (frqcr & 0x0003);
 
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh3_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = ((frqcr & 0x8000) >> 13) | ((frqcr & 0x0030) >> 4);
 
-	clk->rate = clk->parent->rate / stc_multipliers[idx];
+	return clk->parent->rate / stc_multipliers[idx];
 }
 
 static struct clk_ops sh3_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = ((frqcr & 0x4000) >> 12) | ((frqcr & 0x000c) >> 2);
 
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh3_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh3/clock-sh7705.c b/arch/sh/kernel/cpu/sh3/clock-sh7705.c
index dfdbf3277fd7..0ca8f2c3646c 100644
--- a/arch/sh/kernel/cpu/sh3/clock-sh7705.c
+++ b/arch/sh/kernel/cpu/sh3/clock-sh7705.c
@@ -39,30 +39,30 @@ static struct clk_ops sh7705_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = ctrl_inw(FRQCR) & 0x0003;
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7705_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FRQCR) & 0x0300) >> 8;
-	clk->rate = clk->parent->rate / stc_multipliers[idx];
+	return clk->parent->rate / stc_multipliers[idx];
 }
 
 static struct clk_ops sh7705_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FRQCR) & 0x0030) >> 4;
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh7705_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh3/clock-sh7706.c b/arch/sh/kernel/cpu/sh3/clock-sh7706.c
index 0cf96f9833bc..4bf7887d310a 100644
--- a/arch/sh/kernel/cpu/sh3/clock-sh7706.c
+++ b/arch/sh/kernel/cpu/sh3/clock-sh7706.c
@@ -34,36 +34,36 @@ static struct clk_ops sh7706_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = ((frqcr & 0x2000) >> 11) | (frqcr & 0x0003);
 
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7706_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = ((frqcr & 0x8000) >> 13) | ((frqcr & 0x0030) >> 4);
 
-	clk->rate = clk->parent->rate / stc_multipliers[idx];
+	return clk->parent->rate / stc_multipliers[idx];
 }
 
 static struct clk_ops sh7706_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = ((frqcr & 0x4000) >> 12) | ((frqcr & 0x000c) >> 2);
 
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh7706_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh3/clock-sh7709.c b/arch/sh/kernel/cpu/sh3/clock-sh7709.c
index b791a29fdb62..fa30b6017730 100644
--- a/arch/sh/kernel/cpu/sh3/clock-sh7709.c
+++ b/arch/sh/kernel/cpu/sh3/clock-sh7709.c
@@ -41,12 +41,12 @@ static struct clk_ops sh7709_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = ((frqcr & 0x2000) >> 11) | (frqcr & 0x0003);
 
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7709_module_clk_ops = {
@@ -56,25 +56,25 @@ static struct clk_ops sh7709_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = (frqcr & 0x0080) ?
 		((frqcr & 0x8000) >> 13) | ((frqcr & 0x0030) >> 4) : 1;
 
-	clk->rate = clk->parent->rate * stc_multipliers[idx];
+	return clk->parent->rate * stc_multipliers[idx];
 }
 
 static struct clk_ops sh7709_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = ((frqcr & 0x4000) >> 12) | ((frqcr & 0x000c) >> 2);
 
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh7709_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh3/clock-sh7710.c b/arch/sh/kernel/cpu/sh3/clock-sh7710.c
index 4744c50ec449..030a58ba18a5 100644
--- a/arch/sh/kernel/cpu/sh3/clock-sh7710.c
+++ b/arch/sh/kernel/cpu/sh3/clock-sh7710.c
@@ -33,30 +33,30 @@ static struct clk_ops sh7710_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FRQCR) & 0x0007);
-	clk->rate = clk->parent->rate / md_table[idx];
+	return clk->parent->rate / md_table[idx];
 }
 
 static struct clk_ops sh7710_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FRQCR) & 0x0700) >> 8;
-	clk->rate = clk->parent->rate / md_table[idx];
+	return clk->parent->rate / md_table[idx];
 }
 
 static struct clk_ops sh7710_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FRQCR) & 0x0070) >> 4;
-	clk->rate = clk->parent->rate / md_table[idx];
+	return clk->parent->rate / md_table[idx];
 }
 
 static struct clk_ops sh7710_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh3/clock-sh7712.c b/arch/sh/kernel/cpu/sh3/clock-sh7712.c
index 54f54df51ef0..6428ee6c77ed 100644
--- a/arch/sh/kernel/cpu/sh3/clock-sh7712.c
+++ b/arch/sh/kernel/cpu/sh3/clock-sh7712.c
@@ -33,24 +33,24 @@ static struct clk_ops sh7712_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = frqcr & 0x0007;
 
-	clk->rate = clk->parent->rate / divisors[idx];
+	return clk->parent->rate / divisors[idx];
 }
 
 static struct clk_ops sh7712_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int frqcr = ctrl_inw(FRQCR);
 	int idx = (frqcr & 0x0030) >> 4;
 
-	clk->rate = clk->parent->rate / divisors[idx];
+	return clk->parent->rate / divisors[idx];
 }
 
 static struct clk_ops sh7712_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7705.c b/arch/sh/kernel/cpu/sh3/setup-sh7705.c
index 63b67badd67e..88f742fed9ed 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh7705.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh7705.c
@@ -13,6 +13,7 @@
 #include <linux/irq.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
 #include <asm/rtc.h>
 
 enum {
@@ -116,7 +117,102 @@ static struct platform_device rtc_device = {
 	},
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x02,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xfffffe94,
+		.end	= 0xfffffe9f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0xe,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xfffffea0,
+		.end	= 0xfffffeab,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1a,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xfffffeac,
+		.end	= 0xfffffebb,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
 static struct platform_device *sh7705_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
 	&sci_device,
 	&rtc_device,
 };
@@ -128,6 +224,18 @@ static int __init sh7705_devices_setup(void)
 }
 __initcall(sh7705_devices_setup);
 
+static struct platform_device *sh7705_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7705_early_devices,
+				   ARRAY_SIZE(sh7705_early_devices));
+}
+
 void __init plat_irq_setup(void)
 {
 	register_intc_controller(&intc_desc);
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
index a74f960b5e79..c56306798584 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
@@ -18,6 +18,7 @@
 #include <linux/platform_device.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
 
 enum {
 	UNUSED = 0,
@@ -144,7 +145,102 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x02,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xfffffe94,
+		.end	= 0xfffffe9f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0xe,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xfffffea0,
+		.end	= 0xfffffeab,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1a,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xfffffeac,
+		.end	= 0xfffffebb,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
 static struct platform_device *sh770x_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
 	&sci_device,
 	&rtc_device,
 };
@@ -156,6 +252,18 @@ static int __init sh770x_devices_setup(void)
 }
 __initcall(sh770x_devices_setup);
 
+static struct platform_device *sh770x_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh770x_early_devices,
+				   ARRAY_SIZE(sh770x_early_devices));
+}
+
 void __init plat_irq_setup(void)
 {
 	register_intc_controller(&intc_desc);
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7710.c b/arch/sh/kernel/cpu/sh3/setup-sh7710.c
index 335098b66e2f..efa76c8148f4 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh7710.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh7710.c
@@ -13,6 +13,7 @@
 #include <linux/irq.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
 #include <asm/rtc.h>
 
 enum {
@@ -120,7 +121,102 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x02,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xa412fe94,
+		.end	= 0xa412fe9f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0xe,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xa412fea0,
+		.end	= 0xa412feab,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1a,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xa412feac,
+		.end	= 0xa412feb5,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
 static struct platform_device *sh7710_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
 	&sci_device,
 	&rtc_device,
 };
@@ -132,6 +228,18 @@ static int __init sh7710_devices_setup(void)
 }
 __initcall(sh7710_devices_setup);
 
+static struct platform_device *sh7710_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7710_early_devices,
+				   ARRAY_SIZE(sh7710_early_devices));
+}
+
 void __init plat_irq_setup(void)
 {
 	register_intc_controller(&intc_desc);
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7720.c b/arch/sh/kernel/cpu/sh3/setup-sh7720.c
index 003874a2fd2a..5b2107798edb 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh7720.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh7720.c
@@ -18,6 +18,7 @@
 #include <linux/serial.h>
 #include <linux/io.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
 #include <asm/rtc.h>
 
 static struct resource rtc_resources[] = {
@@ -123,7 +124,259 @@ static struct platform_device usbf_device = {
 	.resource	= usbf_resources,
 };
 
+static struct sh_timer_config cmt0_platform_data = {
+	.name = "CMT0",
+	.channel_offset = 0x10,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 125,
+	.clocksource_rating = 125,
+};
+
+static struct resource cmt0_resources[] = {
+	[0] = {
+		.name	= "CMT0",
+		.start	= 0x044a0010,
+		.end	= 0x044a001b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 104,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt0_device = {
+	.name		= "sh_cmt",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &cmt0_platform_data,
+	},
+	.resource	= cmt0_resources,
+	.num_resources	= ARRAY_SIZE(cmt0_resources),
+};
+
+static struct sh_timer_config cmt1_platform_data = {
+	.name = "CMT1",
+	.channel_offset = 0x20,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource cmt1_resources[] = {
+	[0] = {
+		.name	= "CMT1",
+		.start	= 0x044a0020,
+		.end	= 0x044a002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 104,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt1_device = {
+	.name		= "sh_cmt",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &cmt1_platform_data,
+	},
+	.resource	= cmt1_resources,
+	.num_resources	= ARRAY_SIZE(cmt1_resources),
+};
+
+static struct sh_timer_config cmt2_platform_data = {
+	.name = "CMT2",
+	.channel_offset = 0x30,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource cmt2_resources[] = {
+	[0] = {
+		.name	= "CMT2",
+		.start	= 0x044a0030,
+		.end	= 0x044a003b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 104,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt2_device = {
+	.name		= "sh_cmt",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &cmt2_platform_data,
+	},
+	.resource	= cmt2_resources,
+	.num_resources	= ARRAY_SIZE(cmt2_resources),
+};
+
+static struct sh_timer_config cmt3_platform_data = {
+	.name = "CMT3",
+	.channel_offset = 0x40,
+	.timer_bit = 3,
+	.clk = "peripheral_clk",
+};
+
+static struct resource cmt3_resources[] = {
+	[0] = {
+		.name	= "CMT3",
+		.start	= 0x044a0040,
+		.end	= 0x044a004b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 104,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt3_device = {
+	.name		= "sh_cmt",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &cmt3_platform_data,
+	},
+	.resource	= cmt3_resources,
+	.num_resources	= ARRAY_SIZE(cmt3_resources),
+};
+
+static struct sh_timer_config cmt4_platform_data = {
+	.name = "CMT4",
+	.channel_offset = 0x50,
+	.timer_bit = 4,
+	.clk = "peripheral_clk",
+};
+
+static struct resource cmt4_resources[] = {
+	[0] = {
+		.name	= "CMT4",
+		.start	= 0x044a0050,
+		.end	= 0x044a005b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 104,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt4_device = {
+	.name		= "sh_cmt",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &cmt4_platform_data,
+	},
+	.resource	= cmt4_resources,
+	.num_resources	= ARRAY_SIZE(cmt4_resources),
+};
+
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x02,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xa412fe94,
+		.end	= 0xa412fe9f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0xe,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xa412fea0,
+		.end	= 0xa412feab,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1a,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xa412feac,
+		.end	= 0xa412feb5,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
 static struct platform_device *sh7720_devices[] __initdata = {
+	&cmt0_device,
+	&cmt1_device,
+	&cmt2_device,
+	&cmt3_device,
+	&cmt4_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
 	&rtc_device,
 	&sci_device,
 	&usb_ohci_device,
@@ -137,6 +390,23 @@ static int __init sh7720_devices_setup(void)
 }
 __initcall(sh7720_devices_setup);
 
+static struct platform_device *sh7720_early_devices[] __initdata = {
+	&cmt0_device,
+	&cmt1_device,
+	&cmt2_device,
+	&cmt3_device,
+	&cmt4_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7720_early_devices,
+				   ARRAY_SIZE(sh7720_early_devices));
+}
+
 enum {
 	UNUSED = 0,
 
diff --git a/arch/sh/kernel/cpu/sh4/clock-sh4-202.c b/arch/sh/kernel/cpu/sh4/clock-sh4-202.c
index a33429463e96..21421e34e7d5 100644
--- a/arch/sh/kernel/cpu/sh4/clock-sh4-202.c
+++ b/arch/sh/kernel/cpu/sh4/clock-sh4-202.c
@@ -21,10 +21,10 @@
 static int frqcr3_divisors[] = { 1, 2, 3, 4, 6, 8, 16 };
 static int frqcr3_values[]   = { 0, 1, 2, 3, 4, 5, 6  };
 
-static void emi_clk_recalc(struct clk *clk)
+static unsigned long emi_clk_recalc(struct clk *clk)
 {
 	int idx = ctrl_inl(CPG2_FRQCR3) & 0x0007;
-	clk->rate = clk->parent->rate / frqcr3_divisors[idx];
+	return clk->parent->rate / frqcr3_divisors[idx];
 }
 
 static inline int frqcr3_lookup(struct clk *clk, unsigned long rate)
@@ -46,14 +46,14 @@ static struct clk_ops sh4202_emi_clk_ops = {
 
 static struct clk sh4202_emi_clk = {
 	.name		= "emi_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
+	.flags		= CLK_ENABLE_ON_INIT,
 	.ops		= &sh4202_emi_clk_ops,
 };
 
-static void femi_clk_recalc(struct clk *clk)
+static unsigned long femi_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inl(CPG2_FRQCR3) >> 3) & 0x0007;
-	clk->rate = clk->parent->rate / frqcr3_divisors[idx];
+	return clk->parent->rate / frqcr3_divisors[idx];
 }
 
 static struct clk_ops sh4202_femi_clk_ops = {
@@ -62,7 +62,7 @@ static struct clk_ops sh4202_femi_clk_ops = {
 
 static struct clk sh4202_femi_clk = {
 	.name		= "femi_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
+	.flags		= CLK_ENABLE_ON_INIT,
 	.ops		= &sh4202_femi_clk_ops,
 };
 
@@ -90,10 +90,10 @@ static void shoc_clk_init(struct clk *clk)
 	WARN_ON(i == ARRAY_SIZE(frqcr3_divisors));	/* Undefined clock */
 }
 
-static void shoc_clk_recalc(struct clk *clk)
+static unsigned long shoc_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inl(CPG2_FRQCR3) >> 6) & 0x0007;
-	clk->rate = clk->parent->rate / frqcr3_divisors[idx];
+	return clk->parent->rate / frqcr3_divisors[idx];
 }
 
 static int shoc_clk_verify_rate(struct clk *clk, unsigned long rate)
@@ -140,7 +140,7 @@ static struct clk_ops sh4202_shoc_clk_ops = {
 
 static struct clk sh4202_shoc_clk = {
 	.name		= "shoc_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
+	.flags		= CLK_ENABLE_ON_INIT,
 	.ops		= &sh4202_shoc_clk_ops,
 };
 
@@ -150,31 +150,22 @@ static struct clk *sh4202_onchip_clocks[] = {
 	&sh4202_shoc_clk,
 };
 
-static int __init sh4202_clk_init(void)
+int __init arch_clk_init(void)
 {
-	struct clk *clk = clk_get(NULL, "master_clk");
-	int i;
+	struct clk *clk;
+	int i, ret = 0;
 
+	cpg_clk_init();
+
+	clk = clk_get(NULL, "master_clk");
 	for (i = 0; i < ARRAY_SIZE(sh4202_onchip_clocks); i++) {
 		struct clk *clkp = sh4202_onchip_clocks[i];
 
 		clkp->parent = clk;
-		clk_register(clkp);
-		clk_enable(clkp);
+		ret |= clk_register(clkp);
 	}
 
-	/*
-	 * Now that we have the rest of the clocks registered, we need to
-	 * force the parent clock to propagate so that these clocks will
-	 * automatically figure out their rate. We cheat by handing the
-	 * parent clock its current rate and forcing child propagation.
-	 */
-	clk_set_rate(clk, clk_get_rate(clk));
-
 	clk_put(clk);
 
-	return 0;
+	return ret;
 }
-
-arch_initcall(sh4202_clk_init);
-
diff --git a/arch/sh/kernel/cpu/sh4/clock-sh4.c b/arch/sh/kernel/cpu/sh4/clock-sh4.c
index dca9f87a12d6..73294d9cd049 100644
--- a/arch/sh/kernel/cpu/sh4/clock-sh4.c
+++ b/arch/sh/kernel/cpu/sh4/clock-sh4.c
@@ -35,30 +35,30 @@ static struct clk_ops sh4_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FRQCR) & 0x0007);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh4_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FRQCR) >> 3) & 0x0007;
-	clk->rate = clk->parent->rate / bfc_divisors[idx];
+	return clk->parent->rate / bfc_divisors[idx];
 }
 
 static struct clk_ops sh4_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(FRQCR) >> 6) & 0x0007;
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh4_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh4/probe.c b/arch/sh/kernel/cpu/sh4/probe.c
index 91e3677ae09d..6c78d0a9c857 100644
--- a/arch/sh/kernel/cpu/sh4/probe.c
+++ b/arch/sh/kernel/cpu/sh4/probe.c
@@ -60,12 +60,18 @@ int __init detect_cpu_and_cache_system(void)
 		if ((cvr & 0x10000000) == 0)
 			boot_cpu_data.flags |= CPU_HAS_DSP;
 
-		boot_cpu_data.flags |= CPU_HAS_LLSC;
+		boot_cpu_data.flags |= CPU_HAS_LLSC | CPU_HAS_PERF_COUNTER;
 		boot_cpu_data.cut_major = pvr & 0x7f;
+
+		boot_cpu_data.icache.ways = 4;
+		boot_cpu_data.dcache.ways = 4;
+	} else {
+		/* And some SH-4 defaults.. */
+		boot_cpu_data.flags |= CPU_HAS_PTEA;
 	}
 
 	/* FPU detection works for everyone */
-	if ((cvr & 0x20000000) == 1)
+	if ((cvr & 0x20000000))
 		boot_cpu_data.flags |= CPU_HAS_FPU;
 
 	/* Mask off the upper chip ID */
@@ -78,25 +84,20 @@ int __init detect_cpu_and_cache_system(void)
 	switch (pvr) {
 	case 0x205:
 		boot_cpu_data.type = CPU_SH7750;
-		boot_cpu_data.flags |= CPU_HAS_P2_FLUSH_BUG | CPU_HAS_FPU |
-				   CPU_HAS_PERF_COUNTER;
+		boot_cpu_data.flags |= CPU_HAS_P2_FLUSH_BUG |
+				       CPU_HAS_PERF_COUNTER;
 		break;
 	case 0x206:
 		boot_cpu_data.type = CPU_SH7750S;
-		boot_cpu_data.flags |= CPU_HAS_P2_FLUSH_BUG | CPU_HAS_FPU |
-				   CPU_HAS_PERF_COUNTER;
+		boot_cpu_data.flags |= CPU_HAS_P2_FLUSH_BUG |
+				       CPU_HAS_PERF_COUNTER;
 		break;
 	case 0x1100:
 		boot_cpu_data.type = CPU_SH7751;
-		boot_cpu_data.flags |= CPU_HAS_FPU;
 		break;
 	case 0x2001:
 	case 0x2004:
 		boot_cpu_data.type = CPU_SH7770;
-		boot_cpu_data.icache.ways = 4;
-		boot_cpu_data.dcache.ways = 4;
-
-		boot_cpu_data.flags |= CPU_HAS_FPU | CPU_HAS_LLSC;
 		break;
 	case 0x2006:
 	case 0x200A:
@@ -107,45 +108,26 @@ int __init detect_cpu_and_cache_system(void)
 		else
 			boot_cpu_data.type = CPU_SH7780;
 
-		boot_cpu_data.icache.ways = 4;
-		boot_cpu_data.dcache.ways = 4;
-
-		boot_cpu_data.flags |= CPU_HAS_FPU | CPU_HAS_PERF_COUNTER |
-				   CPU_HAS_LLSC;
 		break;
 	case 0x3000:
 	case 0x3003:
 	case 0x3009:
 		boot_cpu_data.type = CPU_SH7343;
-		boot_cpu_data.icache.ways = 4;
-		boot_cpu_data.dcache.ways = 4;
-		boot_cpu_data.flags |= CPU_HAS_LLSC;
 		break;
 	case 0x3004:
 	case 0x3007:
 		boot_cpu_data.type = CPU_SH7785;
-		boot_cpu_data.icache.ways = 4;
-		boot_cpu_data.dcache.ways = 4;
-		boot_cpu_data.flags |= CPU_HAS_FPU | CPU_HAS_PERF_COUNTER |
-					  CPU_HAS_LLSC;
 		break;
 	case 0x4004:
 		boot_cpu_data.type = CPU_SH7786;
-		boot_cpu_data.icache.ways = 4;
-		boot_cpu_data.dcache.ways = 4;
-		boot_cpu_data.flags |= CPU_HAS_FPU | CPU_HAS_PERF_COUNTER |
-			CPU_HAS_LLSC | CPU_HAS_PTEAEX;
+		boot_cpu_data.flags |= CPU_HAS_PTEAEX | CPU_HAS_L2_CACHE;
 		break;
 	case 0x3008:
-		boot_cpu_data.icache.ways = 4;
-		boot_cpu_data.dcache.ways = 4;
-		boot_cpu_data.flags |= CPU_HAS_LLSC;
-
 		switch (prr) {
 		case 0x50:
 		case 0x51:
 			boot_cpu_data.type = CPU_SH7723;
-			boot_cpu_data.flags |= CPU_HAS_FPU | CPU_HAS_L2_CACHE;
+			boot_cpu_data.flags |= CPU_HAS_L2_CACHE;
 			break;
 		case 0x70:
 			boot_cpu_data.type = CPU_SH7366;
@@ -156,13 +138,13 @@ int __init detect_cpu_and_cache_system(void)
 			break;
 		}
 		break;
+	case 0x300b:
+		boot_cpu_data.type = CPU_SH7724;
+		boot_cpu_data.flags |= CPU_HAS_L2_CACHE;
+		break;
 	case 0x4000:	/* 1st cut */
 	case 0x4001:	/* 2nd cut */
 		boot_cpu_data.type = CPU_SHX3;
-		boot_cpu_data.icache.ways = 4;
-		boot_cpu_data.dcache.ways = 4;
-		boot_cpu_data.flags |= CPU_HAS_FPU | CPU_HAS_PERF_COUNTER |
-					  CPU_HAS_LLSC;
 		break;
 	case 0x700:
 		boot_cpu_data.type = CPU_SH4_501;
@@ -173,7 +155,6 @@ int __init detect_cpu_and_cache_system(void)
 		boot_cpu_data.type = CPU_SH4_202;
 		boot_cpu_data.icache.ways = 2;
 		boot_cpu_data.dcache.ways = 2;
-		boot_cpu_data.flags |= CPU_HAS_FPU;
 		break;
 	case 0x500 ... 0x501:
 		switch (prr) {
@@ -191,18 +172,12 @@ int __init detect_cpu_and_cache_system(void)
 		boot_cpu_data.icache.ways = 2;
 		boot_cpu_data.dcache.ways = 2;
 
-		boot_cpu_data.flags |= CPU_HAS_FPU;
-
 		break;
 	default:
 		boot_cpu_data.type = CPU_SH_NONE;
 		break;
 	}
 
-#ifdef CONFIG_CPU_HAS_PTEA
-	boot_cpu_data.flags |= CPU_HAS_PTEA;
-#endif
-
 	/*
 	 * On anything that's not a direct-mapped cache, look to the CVR
 	 * for I/D-cache specifics.
@@ -222,43 +197,48 @@ int __init detect_cpu_and_cache_system(void)
 	}
 
 	/*
-	 * Setup the L2 cache desc
-	 *
 	 * SH-4A's have an optional PIPT L2.
 	 */
 	if (boot_cpu_data.flags & CPU_HAS_L2_CACHE) {
-		/* Bug if we can't decode the L2 info */
-		BUG_ON(!(cvr & 0xf));
-
-		/* Silicon and specifications have clearly never met.. */
-		cvr ^= 0xf;
-
 		/*
-		 * Size calculation is much more sensible
-		 * than it is for the L1.
-		 *
-		 * Sizes are 128KB, 258KB, 512KB, and 1MB.
+		 * Verify that it really has something hooked up, this
+		 * is the safety net for CPUs that have optional L2
+		 * support yet do not implement it.
 		 */
-		size = (cvr & 0xf) << 17;
+		if ((cvr & 0xf) == 0)
+			boot_cpu_data.flags &= ~CPU_HAS_L2_CACHE;
+		else {
+			/*
+			 * Silicon and specifications have clearly never
+			 * met..
+			 */
+			cvr ^= 0xf;
 
-		BUG_ON(!size);
+			/*
+			 * Size calculation is much more sensible
+			 * than it is for the L1.
+			 *
+			 * Sizes are 128KB, 258KB, 512KB, and 1MB.
+			 */
+			size = (cvr & 0xf) << 17;
 
-		boot_cpu_data.scache.way_incr		= (1 << 16);
-		boot_cpu_data.scache.entry_shift	= 5;
-		boot_cpu_data.scache.ways		= 4;
-		boot_cpu_data.scache.linesz		= L1_CACHE_BYTES;
+			boot_cpu_data.scache.way_incr		= (1 << 16);
+			boot_cpu_data.scache.entry_shift	= 5;
+			boot_cpu_data.scache.ways		= 4;
+			boot_cpu_data.scache.linesz		= L1_CACHE_BYTES;
 
-		boot_cpu_data.scache.entry_mask	=
-			(boot_cpu_data.scache.way_incr -
-			 boot_cpu_data.scache.linesz);
+			boot_cpu_data.scache.entry_mask	=
+				(boot_cpu_data.scache.way_incr -
+				 boot_cpu_data.scache.linesz);
 
-		boot_cpu_data.scache.sets	= size /
-			(boot_cpu_data.scache.linesz *
-			 boot_cpu_data.scache.ways);
+			boot_cpu_data.scache.sets	= size /
+				(boot_cpu_data.scache.linesz *
+				 boot_cpu_data.scache.ways);
 
-		boot_cpu_data.scache.way_size	=
-			(boot_cpu_data.scache.sets *
-			 boot_cpu_data.scache.linesz);
+			boot_cpu_data.scache.way_size	=
+				(boot_cpu_data.scache.sets *
+				 boot_cpu_data.scache.linesz);
+		}
 	}
 
 	return 0;
diff --git a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c
index 7371abf64f80..6d088d123591 100644
--- a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c
+++ b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c
@@ -2,6 +2,7 @@
  * SH4-202 Setup
  *
  *  Copyright (C) 2006  Paul Mundt
+ *  Copyright (C) 2009  Magnus Damm
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
@@ -11,6 +12,8 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
+#include <linux/io.h>
 
 static struct plat_sci_port sci_platform_data[] = {
 	{
@@ -31,8 +34,103 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
 static struct platform_device *sh4202_devices[] __initdata = {
 	&sci_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
 };
 
 static int __init sh4202_devices_setup(void)
@@ -42,7 +140,71 @@ static int __init sh4202_devices_setup(void)
 }
 __initcall(sh4202_devices_setup);
 
+static struct platform_device *sh4202_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh4202_early_devices,
+				   ARRAY_SIZE(sh4202_early_devices));
+}
+
+enum {
+	UNUSED = 0,
+
+	/* interrupt sources */
+	IRL0, IRL1, IRL2, IRL3, /* only IRLM mode supported */
+	HUDI, TMU0, TMU1, TMU2, RTC, SCIF, WDT,
+};
+
+static struct intc_vect vectors[] __initdata = {
+	INTC_VECT(HUDI, 0x600),
+	INTC_VECT(TMU0, 0x400), INTC_VECT(TMU1, 0x420),
+	INTC_VECT(TMU2, 0x440), INTC_VECT(TMU2, 0x460),
+	INTC_VECT(RTC, 0x480), INTC_VECT(RTC, 0x4a0),
+	INTC_VECT(RTC, 0x4c0),
+	INTC_VECT(SCIF, 0x700), INTC_VECT(SCIF, 0x720),
+	INTC_VECT(SCIF, 0x740), INTC_VECT(SCIF, 0x760),
+	INTC_VECT(WDT, 0x560),
+};
+
+static struct intc_prio_reg prio_registers[] __initdata = {
+	{ 0xffd00004, 0, 16, 4, /* IPRA */ { TMU0, TMU1, TMU2, RTC } },
+	{ 0xffd00008, 0, 16, 4, /* IPRB */ { WDT, 0, 0, 0 } },
+	{ 0xffd0000c, 0, 16, 4, /* IPRC */ { 0, 0, SCIF, HUDI } },
+	{ 0xffd00010, 0, 16, 4, /* IPRD */ { IRL0, IRL1, IRL2, IRL3 } },
+};
+
+static DECLARE_INTC_DESC(intc_desc, "sh4-202", vectors, NULL,
+			 NULL, prio_registers, NULL);
+
+static struct intc_vect vectors_irlm[] __initdata = {
+	INTC_VECT(IRL0, 0x240), INTC_VECT(IRL1, 0x2a0),
+	INTC_VECT(IRL2, 0x300), INTC_VECT(IRL3, 0x360),
+};
+
+static DECLARE_INTC_DESC(intc_desc_irlm, "sh4-202_irlm", vectors_irlm, NULL,
+			 NULL, prio_registers, NULL);
+
 void __init plat_irq_setup(void)
 {
-	/* do nothing - all IRL interrupts are handled by the board code */
+	register_intc_controller(&intc_desc);
+}
+
+#define INTC_ICR	0xffd00000UL
+#define INTC_ICR_IRLM   (1<<7)
+
+void __init plat_irq_setup_pins(int mode)
+{
+	switch (mode) {
+	case IRQ_MODE_IRQ: /* individual interrupt mode for IRL3-0 */
+		ctrl_outw(ctrl_inw(INTC_ICR) | INTC_ICR_IRLM, INTC_ICR);
+		register_intc_controller(&intc_desc_irlm);
+		break;
+	default:
+		BUG();
+	}
 }
diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c
index a1c80d909cd6..851672d15cf4 100644
--- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c
+++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/io.h>
+#include <linux/sh_timer.h>
 #include <linux/serial_sci.h>
 
 static struct resource rtc_resources[] = {
@@ -60,9 +61,177 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+/* SH7750R, SH7751 and SH7751R all have two extra timer channels */
+#if defined(CONFIG_CPU_SUBTYPE_SH7750R) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7751) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7751R)
+
+static struct sh_timer_config tmu3_platform_data = {
+	.name = "TMU3",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu3_resources[] = {
+	[0] = {
+		.name	= "TMU3",
+		.start	= 0xfe100008,
+		.end	= 0xfe100013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 72,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu3_device = {
+	.name		= "sh_tmu",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &tmu3_platform_data,
+	},
+	.resource	= tmu3_resources,
+	.num_resources	= ARRAY_SIZE(tmu3_resources),
+};
+
+static struct sh_timer_config tmu4_platform_data = {
+	.name = "TMU4",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu4_resources[] = {
+	[0] = {
+		.name	= "TMU4",
+		.start	= 0xfe100014,
+		.end	= 0xfe10001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 76,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu4_device = {
+	.name		= "sh_tmu",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &tmu4_platform_data,
+	},
+	.resource	= tmu4_resources,
+	.num_resources	= ARRAY_SIZE(tmu4_resources),
+};
+
+#endif
+
 static struct platform_device *sh7750_devices[] __initdata = {
 	&rtc_device,
 	&sci_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+#if defined(CONFIG_CPU_SUBTYPE_SH7750R) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7751) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7751R)
+	&tmu3_device,
+	&tmu4_device,
+#endif
 };
 
 static int __init sh7750_devices_setup(void)
@@ -72,6 +241,24 @@ static int __init sh7750_devices_setup(void)
 }
 __initcall(sh7750_devices_setup);
 
+static struct platform_device *sh7750_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+#if defined(CONFIG_CPU_SUBTYPE_SH7750R) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7751) || \
+	defined(CONFIG_CPU_SUBTYPE_SH7751R)
+	&tmu3_device,
+	&tmu4_device,
+#endif
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7750_early_devices,
+				   ARRAY_SIZE(sh7750_early_devices));
+}
+
 enum {
 	UNUSED = 0,
 
diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7760.c b/arch/sh/kernel/cpu/sh4/setup-sh7760.c
index d9bdc931ac09..5b822519bd90 100644
--- a/arch/sh/kernel/cpu/sh4/setup-sh7760.c
+++ b/arch/sh/kernel/cpu/sh4/setup-sh7760.c
@@ -10,6 +10,7 @@
 #include <linux/platform_device.h>
 #include <linux/init.h>
 #include <linux/serial.h>
+#include <linux/sh_timer.h>
 #include <linux/serial_sci.h>
 #include <linux/io.h>
 
@@ -18,10 +19,7 @@ enum {
 
 	/* interrupt sources */
 	IRL0, IRL1, IRL2, IRL3,
-	HUDI, GPIOI,
-	DMAC_DMTE0, DMAC_DMTE1, DMAC_DMTE2, DMAC_DMTE3,
-	DMAC_DMTE4, DMAC_DMTE5, DMAC_DMTE6, DMAC_DMTE7,
-	DMAC_DMAE,
+	HUDI, GPIOI, DMAC,
 	IRQ4, IRQ5, IRQ6, IRQ7,
 	HCAN20, HCAN21,
 	SSI0, SSI1,
@@ -36,21 +34,20 @@ enum {
 	HSPI,
 	MMCIF0, MMCIF1, MMCIF2, MMCIF3,
 	MFI, ADC, CMT,
-	TMU0, TMU1, TMU2_TUNI, TMU2_TICPI,
-	WDT,
-	REF_RCMI, REF_ROVI,
+	TMU0, TMU1, TMU2,
+	WDT, REF,
 
 	/* interrupt groups */
-	DMAC, DMABRG, SCIF0, SCIF1, SCIF2, SIM, MMCIF, TMU2, REF,
+	DMABRG, SCIF0, SCIF1, SCIF2, SIM, MMCIF,
 };
 
 static struct intc_vect vectors[] __initdata = {
 	INTC_VECT(HUDI, 0x600), INTC_VECT(GPIOI, 0x620),
-	INTC_VECT(DMAC_DMTE0, 0x640), INTC_VECT(DMAC_DMTE1, 0x660),
-	INTC_VECT(DMAC_DMTE2, 0x680), INTC_VECT(DMAC_DMTE3, 0x6a0),
-	INTC_VECT(DMAC_DMTE4, 0x780), INTC_VECT(DMAC_DMTE5, 0x7a0),
-	INTC_VECT(DMAC_DMTE6, 0x7c0), INTC_VECT(DMAC_DMTE7, 0x7e0),
-	INTC_VECT(DMAC_DMAE, 0x6c0),
+	INTC_VECT(DMAC, 0x640), INTC_VECT(DMAC, 0x660),
+	INTC_VECT(DMAC, 0x680), INTC_VECT(DMAC, 0x6a0),
+	INTC_VECT(DMAC, 0x780), INTC_VECT(DMAC, 0x7a0),
+	INTC_VECT(DMAC, 0x7c0), INTC_VECT(DMAC, 0x7e0),
+	INTC_VECT(DMAC, 0x6c0),
 	INTC_VECT(IRQ4, 0x800), INTC_VECT(IRQ5, 0x820),
 	INTC_VECT(IRQ6, 0x840), INTC_VECT(IRQ6, 0x860),
 	INTC_VECT(HCAN20, 0x900), INTC_VECT(HCAN21, 0x920),
@@ -74,23 +71,18 @@ static struct intc_vect vectors[] __initdata = {
 	INTC_VECT(MFI, 0xe80), /* 0xf80 according to data sheet */
 	INTC_VECT(ADC, 0xf80), INTC_VECT(CMT, 0xfa0),
 	INTC_VECT(TMU0, 0x400), INTC_VECT(TMU1, 0x420),
-	INTC_VECT(TMU2_TUNI, 0x440), INTC_VECT(TMU2_TICPI, 0x460),
+	INTC_VECT(TMU2, 0x440), INTC_VECT(TMU2, 0x460),
 	INTC_VECT(WDT, 0x560),
-	INTC_VECT(REF_RCMI, 0x580), INTC_VECT(REF_ROVI, 0x5a0),
+	INTC_VECT(REF, 0x580), INTC_VECT(REF, 0x5a0),
 };
 
 static struct intc_group groups[] __initdata = {
-	INTC_GROUP(DMAC, DMAC_DMTE0, DMAC_DMTE1, DMAC_DMTE2,
-		   DMAC_DMTE3, DMAC_DMTE4, DMAC_DMTE5,
-		   DMAC_DMTE6, DMAC_DMTE7, DMAC_DMAE),
 	INTC_GROUP(DMABRG, DMABRG0, DMABRG1, DMABRG2),
 	INTC_GROUP(SCIF0, SCIF0_ERI, SCIF0_RXI, SCIF0_BRI, SCIF0_TXI),
 	INTC_GROUP(SCIF1, SCIF1_ERI, SCIF1_RXI, SCIF1_BRI, SCIF1_TXI),
 	INTC_GROUP(SCIF2, SCIF2_ERI, SCIF2_RXI, SCIF2_BRI, SCIF2_TXI),
 	INTC_GROUP(SIM, SIM_ERI, SIM_RXI, SIM_TXI, SIM_TEI),
 	INTC_GROUP(MMCIF, MMCIF0, MMCIF1, MMCIF2, MMCIF3),
-	INTC_GROUP(TMU2, TMU2_TUNI, TMU2_TICPI),
-	INTC_GROUP(REF, REF_RCMI, REF_ROVI),
 };
 
 static struct intc_mask_reg mask_registers[] __initdata = {
@@ -168,8 +160,104 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+
 static struct platform_device *sh7760_devices[] __initdata = {
 	&sci_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
 };
 
 static int __init sh7760_devices_setup(void)
@@ -179,6 +267,18 @@ static int __init sh7760_devices_setup(void)
 }
 __initcall(sh7760_devices_setup);
 
+static struct platform_device *sh7760_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7760_early_devices,
+				   ARRAY_SIZE(sh7760_early_devices));
+}
+
 #define INTC_ICR	0xffd00000UL
 #define INTC_ICR_IRLM	(1 << 7)
 
diff --git a/arch/sh/kernel/cpu/sh4a/Makefile b/arch/sh/kernel/cpu/sh4a/Makefile
index 1a92361feeb9..96ea09ca8cc1 100644
--- a/arch/sh/kernel/cpu/sh4a/Makefile
+++ b/arch/sh/kernel/cpu/sh4a/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_CPU_SUBTYPE_SH7786)	+= setup-sh7786.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7343)	+= setup-sh7343.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7722)	+= setup-sh7722.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7723)	+= setup-sh7723.o
+obj-$(CONFIG_CPU_SUBTYPE_SH7724)	+= setup-sh7724.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7366)	+= setup-sh7366.o
 obj-$(CONFIG_CPU_SUBTYPE_SHX3)		+= setup-shx3.o
 
@@ -23,15 +24,17 @@ clock-$(CONFIG_CPU_SUBTYPE_SH7770)	:= clock-sh7770.o
 clock-$(CONFIG_CPU_SUBTYPE_SH7780)	:= clock-sh7780.o
 clock-$(CONFIG_CPU_SUBTYPE_SH7785)	:= clock-sh7785.o
 clock-$(CONFIG_CPU_SUBTYPE_SH7786)	:= clock-sh7786.o
-clock-$(CONFIG_CPU_SUBTYPE_SH7343)	:= clock-sh7722.o
+clock-$(CONFIG_CPU_SUBTYPE_SH7343)	:= clock-sh7343.o
 clock-$(CONFIG_CPU_SUBTYPE_SH7722)	:= clock-sh7722.o
-clock-$(CONFIG_CPU_SUBTYPE_SH7723)	:= clock-sh7722.o
-clock-$(CONFIG_CPU_SUBTYPE_SH7366)	:= clock-sh7722.o
+clock-$(CONFIG_CPU_SUBTYPE_SH7723)	:= clock-sh7723.o
+clock-$(CONFIG_CPU_SUBTYPE_SH7724)	:= clock-sh7724.o
+clock-$(CONFIG_CPU_SUBTYPE_SH7366)	:= clock-sh7366.o
 clock-$(CONFIG_CPU_SUBTYPE_SHX3)	:= clock-shx3.o
 
 # Pinmux setup
 pinmux-$(CONFIG_CPU_SUBTYPE_SH7722)	:= pinmux-sh7722.o
 pinmux-$(CONFIG_CPU_SUBTYPE_SH7723)	:= pinmux-sh7723.o
+pinmux-$(CONFIG_CPU_SUBTYPE_SH7724)	:= pinmux-sh7724.o
 pinmux-$(CONFIG_CPU_SUBTYPE_SH7785)	:= pinmux-sh7785.o
 pinmux-$(CONFIG_CPU_SUBTYPE_SH7786)	:= pinmux-sh7786.o
 
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7343.c b/arch/sh/kernel/cpu/sh4a/clock-sh7343.c
new file mode 100644
index 000000000000..0ee3ee861252
--- /dev/null
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7343.c
@@ -0,0 +1,211 @@
+/*
+ * arch/sh/kernel/cpu/sh4a/clock-sh7343.c
+ *
+ * SH7343 clock framework support
+ *
+ * Copyright (C) 2009 Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <asm/clock.h>
+
+/* SH7343 registers */
+#define FRQCR		0xa4150000
+#define VCLKCR		0xa4150004
+#define SCLKACR		0xa4150008
+#define SCLKBCR		0xa415000c
+#define PLLCR		0xa4150024
+#define MSTPCR0		0xa4150030
+#define MSTPCR1		0xa4150034
+#define MSTPCR2		0xa4150038
+#define DLLFRQ		0xa4150050
+
+/* Fixed 32 KHz root clock for RTC and Power Management purposes */
+static struct clk r_clk = {
+	.name           = "rclk",
+	.id             = -1,
+	.rate           = 32768,
+};
+
+/*
+ * Default rate for the root input clock, reset this with clk_set_rate()
+ * from the platform code.
+ */
+struct clk extal_clk = {
+	.name		= "extal",
+	.id		= -1,
+	.rate		= 33333333,
+};
+
+/* The dll block multiplies the 32khz r_clk, may be used instead of extal */
+static unsigned long dll_recalc(struct clk *clk)
+{
+	unsigned long mult;
+
+	if (__raw_readl(PLLCR) & 0x1000)
+		mult = __raw_readl(DLLFRQ);
+	else
+		mult = 0;
+
+	return clk->parent->rate * mult;
+}
+
+static struct clk_ops dll_clk_ops = {
+	.recalc		= dll_recalc,
+};
+
+static struct clk dll_clk = {
+	.name           = "dll_clk",
+	.id             = -1,
+	.ops		= &dll_clk_ops,
+	.parent		= &r_clk,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+static unsigned long pll_recalc(struct clk *clk)
+{
+	unsigned long mult = 1;
+
+	if (__raw_readl(PLLCR) & 0x4000)
+		mult = (((__raw_readl(FRQCR) >> 24) & 0x1f) + 1);
+
+	return clk->parent->rate * mult;
+}
+
+static struct clk_ops pll_clk_ops = {
+	.recalc		= pll_recalc,
+};
+
+static struct clk pll_clk = {
+	.name		= "pll_clk",
+	.id		= -1,
+	.ops		= &pll_clk_ops,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+struct clk *main_clks[] = {
+	&r_clk,
+	&extal_clk,
+	&dll_clk,
+	&pll_clk,
+};
+
+static int multipliers[] = { 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1 };
+static int divisors[] = { 1, 3, 2, 5, 3, 4, 5, 6, 8, 10, 12, 16, 20 };
+
+static struct clk_div_mult_table div4_table = {
+	.divisors = divisors,
+	.nr_divisors = ARRAY_SIZE(divisors),
+	.multipliers = multipliers,
+	.nr_multipliers = ARRAY_SIZE(multipliers),
+};
+
+enum { DIV4_I, DIV4_U, DIV4_SH, DIV4_B, DIV4_B3, DIV4_P,
+       DIV4_SIUA, DIV4_SIUB, DIV4_NR };
+
+#define DIV4(_str, _reg, _bit, _mask, _flags) \
+  SH_CLK_DIV4(_str, &pll_clk, _reg, _bit, _mask, _flags)
+
+struct clk div4_clks[DIV4_NR] = {
+	[DIV4_I] = DIV4("cpu_clk", FRQCR, 20, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_U] = DIV4("umem_clk", FRQCR, 16, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_SH] = DIV4("shyway_clk", FRQCR, 12, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_B] = DIV4("bus_clk", FRQCR, 8, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_B3] = DIV4("b3_clk", FRQCR, 4, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_P] = DIV4("peripheral_clk", FRQCR, 0, 0x1fff, 0),
+	[DIV4_SIUA] = DIV4("siua_clk", SCLKACR, 0, 0x1fff, 0),
+	[DIV4_SIUB] = DIV4("siub_clk", SCLKBCR, 0, 0x1fff, 0),
+};
+
+struct clk div6_clks[] = {
+	SH_CLK_DIV6("video_clk", &pll_clk, VCLKCR, 0),
+};
+
+#define MSTP(_str, _parent, _reg, _bit, _flags) \
+  SH_CLK_MSTP32(_str, -1, _parent, _reg, _bit, _flags)
+
+static struct clk mstp_clks[] = {
+	MSTP("tlb0", &div4_clks[DIV4_I], MSTPCR0, 31, CLK_ENABLE_ON_INIT),
+	MSTP("ic0", &div4_clks[DIV4_I], MSTPCR0, 30, CLK_ENABLE_ON_INIT),
+	MSTP("oc0", &div4_clks[DIV4_I], MSTPCR0, 29, CLK_ENABLE_ON_INIT),
+	MSTP("uram0", &div4_clks[DIV4_U], MSTPCR0, 28, CLK_ENABLE_ON_INIT),
+	MSTP("xymem0", &div4_clks[DIV4_B], MSTPCR0, 26, CLK_ENABLE_ON_INIT),
+	MSTP("intc3", &div4_clks[DIV4_P], MSTPCR0, 23, 0),
+	MSTP("intc0", &div4_clks[DIV4_P], MSTPCR0, 22, 0),
+	MSTP("dmac0", &div4_clks[DIV4_P], MSTPCR0, 21, 0),
+	MSTP("sh0", &div4_clks[DIV4_P], MSTPCR0, 20, 0),
+	MSTP("hudi0", &div4_clks[DIV4_P], MSTPCR0, 19, 0),
+	MSTP("ubc0", &div4_clks[DIV4_P], MSTPCR0, 17, 0),
+	MSTP("tmu0", &div4_clks[DIV4_P], MSTPCR0, 15, 0),
+	MSTP("cmt0", &r_clk, MSTPCR0, 14, 0),
+	MSTP("rwdt0", &r_clk, MSTPCR0, 13, 0),
+	MSTP("mfi0", &div4_clks[DIV4_P], MSTPCR0, 11, 0),
+	MSTP("flctl0", &div4_clks[DIV4_P], MSTPCR0, 10, 0),
+	MSTP("scif0", &div4_clks[DIV4_P], MSTPCR0, 7, 0),
+	MSTP("scif1", &div4_clks[DIV4_P], MSTPCR0, 6, 0),
+	MSTP("scif2", &div4_clks[DIV4_P], MSTPCR0, 5, 0),
+	MSTP("scif3", &div4_clks[DIV4_P], MSTPCR0, 4, 0),
+	MSTP("sio0", &div4_clks[DIV4_P], MSTPCR0, 3, 0),
+	MSTP("siof0", &div4_clks[DIV4_P], MSTPCR0, 2, 0),
+	MSTP("siof1", &div4_clks[DIV4_P], MSTPCR0, 1, 0),
+
+	MSTP("i2c0", &div4_clks[DIV4_P], MSTPCR1, 9, 0),
+	MSTP("i2c1", &div4_clks[DIV4_P], MSTPCR1, 8, 0),
+
+	MSTP("tpu0", &div4_clks[DIV4_P], MSTPCR2, 25, 0),
+	MSTP("irda0", &div4_clks[DIV4_P], MSTPCR2, 24, 0),
+	MSTP("sdhi0", &div4_clks[DIV4_P], MSTPCR2, 18, 0),
+	MSTP("mmcif0", &div4_clks[DIV4_P], MSTPCR2, 17, 0),
+	MSTP("sim0", &div4_clks[DIV4_P], MSTPCR2, 16, 0),
+	MSTP("keysc0", &r_clk, MSTPCR2, 14, 0),
+	MSTP("tsif0", &div4_clks[DIV4_P], MSTPCR2, 13, 0),
+	MSTP("s3d40", &div4_clks[DIV4_P], MSTPCR2, 12, 0),
+	MSTP("usbf0", &div4_clks[DIV4_P], MSTPCR2, 11, 0),
+	MSTP("siu0", &div4_clks[DIV4_B], MSTPCR2, 8, 0),
+	MSTP("jpu0", &div4_clks[DIV4_B], MSTPCR2, 6, CLK_ENABLE_ON_INIT),
+	MSTP("vou0", &div4_clks[DIV4_B], MSTPCR2, 5, 0),
+	MSTP("beu0", &div4_clks[DIV4_B], MSTPCR2, 4, 0),
+	MSTP("ceu0", &div4_clks[DIV4_B], MSTPCR2, 3, 0),
+	MSTP("veu0", &div4_clks[DIV4_B], MSTPCR2, 2, CLK_ENABLE_ON_INIT),
+	MSTP("vpu0", &div4_clks[DIV4_B], MSTPCR2, 1, CLK_ENABLE_ON_INIT),
+	MSTP("lcdc0", &div4_clks[DIV4_B], MSTPCR2, 0, 0),
+};
+
+int __init arch_clk_init(void)
+{
+	int k, ret = 0;
+
+	/* autodetect extal or dll configuration */
+	if (__raw_readl(PLLCR) & 0x1000)
+		pll_clk.parent = &dll_clk;
+	else
+		pll_clk.parent = &extal_clk;
+
+	for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
+		ret = clk_register(main_clks[k]);
+
+	if (!ret)
+		ret = sh_clk_div4_register(div4_clks, DIV4_NR, &div4_table);
+
+	if (!ret)
+		ret = sh_clk_div6_register(div6_clks, ARRAY_SIZE(div6_clks));
+
+	if (!ret)
+		ret = sh_clk_mstp32_register(mstp_clks, ARRAY_SIZE(mstp_clks));
+
+	return ret;
+}
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7366.c b/arch/sh/kernel/cpu/sh4a/clock-sh7366.c
new file mode 100644
index 000000000000..a95ebaba095c
--- /dev/null
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7366.c
@@ -0,0 +1,211 @@
+/*
+ * arch/sh/kernel/cpu/sh4a/clock-sh7366.c
+ *
+ * SH7366 clock framework support
+ *
+ * Copyright (C) 2009 Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <asm/clock.h>
+
+/* SH7366 registers */
+#define FRQCR		0xa4150000
+#define VCLKCR		0xa4150004
+#define SCLKACR		0xa4150008
+#define SCLKBCR		0xa415000c
+#define PLLCR		0xa4150024
+#define MSTPCR0		0xa4150030
+#define MSTPCR1		0xa4150034
+#define MSTPCR2		0xa4150038
+#define DLLFRQ		0xa4150050
+
+/* Fixed 32 KHz root clock for RTC and Power Management purposes */
+static struct clk r_clk = {
+	.name           = "rclk",
+	.id             = -1,
+	.rate           = 32768,
+};
+
+/*
+ * Default rate for the root input clock, reset this with clk_set_rate()
+ * from the platform code.
+ */
+struct clk extal_clk = {
+	.name		= "extal",
+	.id		= -1,
+	.rate		= 33333333,
+};
+
+/* The dll block multiplies the 32khz r_clk, may be used instead of extal */
+static unsigned long dll_recalc(struct clk *clk)
+{
+	unsigned long mult;
+
+	if (__raw_readl(PLLCR) & 0x1000)
+		mult = __raw_readl(DLLFRQ);
+	else
+		mult = 0;
+
+	return clk->parent->rate * mult;
+}
+
+static struct clk_ops dll_clk_ops = {
+	.recalc		= dll_recalc,
+};
+
+static struct clk dll_clk = {
+	.name           = "dll_clk",
+	.id             = -1,
+	.ops		= &dll_clk_ops,
+	.parent		= &r_clk,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+static unsigned long pll_recalc(struct clk *clk)
+{
+	unsigned long mult = 1;
+	unsigned long div = 1;
+
+	if (__raw_readl(PLLCR) & 0x4000)
+		mult = (((__raw_readl(FRQCR) >> 24) & 0x1f) + 1);
+	else
+		div = 2;
+
+	return (clk->parent->rate * mult) / div;
+}
+
+static struct clk_ops pll_clk_ops = {
+	.recalc		= pll_recalc,
+};
+
+static struct clk pll_clk = {
+	.name		= "pll_clk",
+	.id		= -1,
+	.ops		= &pll_clk_ops,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+struct clk *main_clks[] = {
+	&r_clk,
+	&extal_clk,
+	&dll_clk,
+	&pll_clk,
+};
+
+static int multipliers[] = { 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1 };
+static int divisors[] = { 1, 3, 2, 5, 3, 4, 5, 6, 8, 10, 12, 16, 20 };
+
+static struct clk_div_mult_table div4_table = {
+	.divisors = divisors,
+	.nr_divisors = ARRAY_SIZE(divisors),
+	.multipliers = multipliers,
+	.nr_multipliers = ARRAY_SIZE(multipliers),
+};
+
+enum { DIV4_I, DIV4_U, DIV4_SH, DIV4_B, DIV4_B3, DIV4_P,
+       DIV4_SIUA, DIV4_SIUB, DIV4_NR };
+
+#define DIV4(_str, _reg, _bit, _mask, _flags) \
+  SH_CLK_DIV4(_str, &pll_clk, _reg, _bit, _mask, _flags)
+
+struct clk div4_clks[DIV4_NR] = {
+	[DIV4_I] = DIV4("cpu_clk", FRQCR, 20, 0x1fef, CLK_ENABLE_ON_INIT),
+	[DIV4_U] = DIV4("umem_clk", FRQCR, 16, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_SH] = DIV4("shyway_clk", FRQCR, 12, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_B] = DIV4("bus_clk", FRQCR, 8, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_B3] = DIV4("b3_clk", FRQCR, 4, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_P] = DIV4("peripheral_clk", FRQCR, 0, 0x1fff, 0),
+	[DIV4_SIUA] = DIV4("siua_clk", SCLKACR, 0, 0x1fff, 0),
+	[DIV4_SIUB] = DIV4("siub_clk", SCLKBCR, 0, 0x1fff, 0),
+};
+
+struct clk div6_clks[] = {
+	SH_CLK_DIV6("video_clk", &pll_clk, VCLKCR, 0),
+};
+
+#define MSTP(_str, _parent, _reg, _bit, _flags) \
+  SH_CLK_MSTP32(_str, -1, _parent, _reg, _bit, _flags)
+
+static struct clk mstp_clks[] = {
+	/* See page 52 of Datasheet V0.40: Overview -> Block Diagram */
+	MSTP("tlb0", &div4_clks[DIV4_I], MSTPCR0, 31, CLK_ENABLE_ON_INIT),
+	MSTP("ic0", &div4_clks[DIV4_I], MSTPCR0, 30, CLK_ENABLE_ON_INIT),
+	MSTP("oc0", &div4_clks[DIV4_I], MSTPCR0, 29, CLK_ENABLE_ON_INIT),
+	MSTP("rsmem0", &div4_clks[DIV4_SH], MSTPCR0, 28, CLK_ENABLE_ON_INIT),
+	MSTP("xymem0", &div4_clks[DIV4_B], MSTPCR0, 26, CLK_ENABLE_ON_INIT),
+	MSTP("intc3", &div4_clks[DIV4_P], MSTPCR0, 23, 0),
+	MSTP("intc0", &div4_clks[DIV4_P], MSTPCR0, 22, 0),
+	MSTP("dmac0", &div4_clks[DIV4_P], MSTPCR0, 21, 0),
+	MSTP("sh0", &div4_clks[DIV4_P], MSTPCR0, 20, 0),
+	MSTP("hudi0", &div4_clks[DIV4_P], MSTPCR0, 19, 0),
+	MSTP("ubc0", &div4_clks[DIV4_P], MSTPCR0, 17, 0),
+	MSTP("tmu0", &div4_clks[DIV4_P], MSTPCR0, 15, 0),
+	MSTP("cmt0", &r_clk, MSTPCR0, 14, 0),
+	MSTP("rwdt0", &r_clk, MSTPCR0, 13, 0),
+	MSTP("mfi0", &div4_clks[DIV4_P], MSTPCR0, 11, 0),
+	MSTP("flctl0", &div4_clks[DIV4_P], MSTPCR0, 10, 0),
+	MSTP("scif0", &div4_clks[DIV4_P], MSTPCR0, 7, 0),
+	MSTP("scif1", &div4_clks[DIV4_P], MSTPCR0, 6, 0),
+	MSTP("scif2", &div4_clks[DIV4_P], MSTPCR0, 5, 0),
+	MSTP("msiof0", &div4_clks[DIV4_P], MSTPCR0, 2, 0),
+	MSTP("sbr0", &div4_clks[DIV4_P], MSTPCR0, 1, 0),
+
+	MSTP("i2c0", &div4_clks[DIV4_P], MSTPCR1, 9, 0),
+
+	MSTP("icb0", &div4_clks[DIV4_P], MSTPCR2, 27, 0),
+	MSTP("meram0", &div4_clks[DIV4_P], MSTPCR2, 26, 0),
+	MSTP("dacy1", &div4_clks[DIV4_P], MSTPCR2, 24, 0),
+	MSTP("dacy0", &div4_clks[DIV4_P], MSTPCR2, 23, 0),
+	MSTP("tsif0", &div4_clks[DIV4_P], MSTPCR2, 22, 0),
+	MSTP("sdhi0", &div4_clks[DIV4_P], MSTPCR2, 18, 0),
+	MSTP("mmcif0", &div4_clks[DIV4_P], MSTPCR2, 17, 0),
+	MSTP("usbf0", &div4_clks[DIV4_P], MSTPCR2, 11, 0),
+	MSTP("siu0", &div4_clks[DIV4_B], MSTPCR2, 9, 0),
+	MSTP("veu1", &div4_clks[DIV4_B], MSTPCR2, 7, CLK_ENABLE_ON_INIT),
+	MSTP("vou0", &div4_clks[DIV4_B], MSTPCR2, 5, 0),
+	MSTP("beu0", &div4_clks[DIV4_B], MSTPCR2, 4, 0),
+	MSTP("ceu0", &div4_clks[DIV4_B], MSTPCR2, 3, 0),
+	MSTP("veu0", &div4_clks[DIV4_B], MSTPCR2, 2, CLK_ENABLE_ON_INIT),
+	MSTP("vpu0", &div4_clks[DIV4_B], MSTPCR2, 1, CLK_ENABLE_ON_INIT),
+	MSTP("lcdc0", &div4_clks[DIV4_B], MSTPCR2, 0, 0),
+};
+
+int __init arch_clk_init(void)
+{
+	int k, ret = 0;
+
+	/* autodetect extal or dll configuration */
+	if (__raw_readl(PLLCR) & 0x1000)
+		pll_clk.parent = &dll_clk;
+	else
+		pll_clk.parent = &extal_clk;
+
+	for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
+		ret = clk_register(main_clks[k]);
+
+	if (!ret)
+		ret = sh_clk_div4_register(div4_clks, DIV4_NR, &div4_table);
+
+	if (!ret)
+		ret = sh_clk_div6_register(div6_clks, ARRAY_SIZE(div6_clks));
+
+	if (!ret)
+		ret = sh_clk_mstp32_register(mstp_clks, ARRAY_SIZE(mstp_clks));
+
+	return ret;
+}
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c
index 0e174af21874..40f859354f79 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c
@@ -1,844 +1,197 @@
 /*
  * arch/sh/kernel/cpu/sh4a/clock-sh7722.c
  *
- * SH7343, SH7722, SH7723 & SH7366 support for the clock framework
+ * SH7722 clock framework support
  *
- * Copyright (c) 2006-2007 Nomad Global Solutions Inc
- * Based on code for sh7343 by Paul Mundt
+ * Copyright (C) 2009 Magnus Damm
  *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
-#include <linux/errno.h>
-#include <linux/stringify.h>
 #include <asm/clock.h>
-#include <asm/freq.h>
 
-#define N  (-1)
-#define NM (-2)
-#define ROUND_NEAREST 0
-#define ROUND_DOWN -1
-#define ROUND_UP   +1
+/* SH7722 registers */
+#define FRQCR		0xa4150000
+#define VCLKCR		0xa4150004
+#define SCLKACR		0xa4150008
+#define SCLKBCR		0xa415000c
+#define IRDACLKCR	0xa4150018
+#define PLLCR		0xa4150024
+#define MSTPCR0		0xa4150030
+#define MSTPCR1		0xa4150034
+#define MSTPCR2		0xa4150038
+#define DLLFRQ		0xa4150050
 
-static int adjust_algos[][3] = {
-	{},	/* NO_CHANGE */
-	{ NM, N, 1 },   /* N:1, N:1 */
-	{ 3, 2, 2 },	/* 3:2:2 */
-	{ 5, 2, 2 },    /* 5:2:2 */
-	{ N, 1, 1 },	/* N:1:1 */
-
-	{ N, 1 },	/* N:1 */
-
-	{ N, 1 },	/* N:1 */
-	{ 3, 2 },
-	{ 4, 3 },
-	{ 5, 4 },
-
-	{ N, 1 }
-};
-
-static unsigned long adjust_pair_of_clocks(unsigned long r1, unsigned long r2,
-			int m1, int m2, int round_flag)
-{
-	unsigned long rem, div;
-	int the_one = 0;
-
-	pr_debug( "Actual values: r1 = %ld\n", r1);
-	pr_debug( "...............r2 = %ld\n", r2);
-
-	if (m1 == m2) {
-		r2 = r1;
-		pr_debug( "setting equal rates: r2 now %ld\n", r2);
-	} else if ((m2 == N  && m1 == 1) ||
-		   (m2 == NM && m1 == N)) { /* N:1 or NM:N */
-		pr_debug( "Setting rates as 1:N (N:N*M)\n");
-		rem = r2 % r1;
-		pr_debug( "...remainder = %ld\n", rem);
-		if (rem) {
-			div = r2 / r1;
-			pr_debug( "...div = %ld\n", div);
-			switch (round_flag) {
-			case ROUND_NEAREST:
-				the_one = rem >= r1/2 ? 1 : 0; break;
-			case ROUND_UP:
-				the_one = 1; break;
-			case ROUND_DOWN:
-				the_one = 0; break;
-			}
-
-			r2 = r1 * (div + the_one);
-			pr_debug( "...setting r2 to %ld\n", r2);
-		}
-	} else if ((m2 == 1  && m1 == N) ||
-		   (m2 == N && m1 == NM)) { /* 1:N or N:NM */
-		pr_debug( "Setting rates as N:1 (N*M:N)\n");
-		rem = r1 % r2;
-		pr_debug( "...remainder = %ld\n", rem);
-		if (rem) {
-			div = r1 / r2;
-			pr_debug( "...div = %ld\n", div);
-			switch (round_flag) {
-			case ROUND_NEAREST:
-				the_one = rem > r2/2 ? 1 : 0; break;
-			case ROUND_UP:
-				the_one = 0; break;
-			case ROUND_DOWN:
-				the_one = 1; break;
-			}
-
-			r2 = r1 / (div + the_one);
-			pr_debug( "...setting r2 to %ld\n", r2);
-		}
-	} else { /* value:value */
-		pr_debug( "Setting rates as %d:%d\n", m1, m2);
-		div = r1 / m1;
-		r2 = div * m2;
-		pr_debug( "...div = %ld\n", div);
-		pr_debug( "...setting r2 to %ld\n", r2);
-	}
-
-	return r2;
-}
-
-static void adjust_clocks(int originate, int *l, unsigned long v[],
-			  int n_in_line)
-{
-	int x;
-
-	pr_debug( "Go down from %d...\n", originate);
-	/* go up recalculation clocks */
-	for (x = originate; x>0; x -- )
-		v[x-1] = adjust_pair_of_clocks(v[x], v[x-1],
-					l[x], l[x-1],
-					ROUND_UP);
-
-	pr_debug( "Go up from %d...\n", originate);
-	/* go down recalculation clocks */
-	for (x = originate; x<n_in_line - 1; x ++ )
-		v[x+1] = adjust_pair_of_clocks(v[x], v[x+1],
-					l[x], l[x+1],
-					ROUND_UP);
-}
-
-
-/*
- * SH7722 uses a common set of multipliers and divisors, so this
- * is quite simple..
- */
-
-/*
- * Instead of having two separate multipliers/divisors set, like this:
- *
- * static int multipliers[] = { 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1 };
- * static int divisors[] = { 1, 3, 2, 5, 3, 4, 5, 6, 8, 10, 12, 16, 20 };
- *
- * I created the divisors2 array, which is used to calculate rate like
- *   rate = parent * 2 / divisors2[ divisor ];
-*/
-static int divisors2[] = { 2, 3, 4, 5, 6, 8, 10, 12, 16, 20, 24, 32, 40 };
-
-static void master_clk_recalc(struct clk *clk)
-{
-	unsigned frqcr = ctrl_inl(FRQCR);
-
-	clk->rate = CONFIG_SH_PCLK_FREQ * (((frqcr >> 24) & 0x1f) + 1);
-}
-
-static void master_clk_init(struct clk *clk)
-{
-	clk->parent = NULL;
-	clk->flags |= CLK_RATE_PROPAGATES;
-	clk->rate = CONFIG_SH_PCLK_FREQ;
-	master_clk_recalc(clk);
-}
-
-
-static void module_clk_recalc(struct clk *clk)
-{
-	unsigned long frqcr = ctrl_inl(FRQCR);
-
-	clk->rate = clk->parent->rate / (((frqcr >> 24) & 0x1f) + 1);
-}
-
-static int master_clk_setrate(struct clk *clk, unsigned long rate, int id)
-{
-	int div = rate / clk->rate;
-	int master_divs[] = { 2, 3, 4, 6, 8, 16 };
-	int index;
-	unsigned long frqcr;
-
-	for (index = 1; index < ARRAY_SIZE(master_divs); index++)
-		if (div >= master_divs[index - 1] && div < master_divs[index])
-			break;
-
-	if (index >= ARRAY_SIZE(master_divs))
-		index = ARRAY_SIZE(master_divs);
-	div = master_divs[index - 1];
-
-	frqcr = ctrl_inl(FRQCR);
-	frqcr &= ~(0xF << 24);
-	frqcr |= ( (div-1) << 24);
-	ctrl_outl(frqcr, FRQCR);
-
-	return 0;
-}
-
-static struct clk_ops sh7722_master_clk_ops = {
-	.init = master_clk_init,
-	.recalc = master_clk_recalc,
-	.set_rate = master_clk_setrate,
-};
-
-static struct clk_ops sh7722_module_clk_ops = {
-       .recalc = module_clk_recalc,
-};
-
-struct frqcr_context {
-	unsigned mask;
-	unsigned shift;
-};
-
-struct frqcr_context sh7722_get_clk_context(const char *name)
-{
-	struct frqcr_context ctx = { 0, };
-
-	if (!strcmp(name, "peripheral_clk")) {
-		ctx.shift = 0;
-		ctx.mask = 0xF;
-	} else if (!strcmp(name, "sdram_clk")) {
-		ctx.shift = 4;
-		ctx.mask = 0xF;
-	} else if (!strcmp(name, "bus_clk")) {
-		ctx.shift = 8;
-		ctx.mask = 0xF;
-	} else if (!strcmp(name, "sh_clk")) {
-		ctx.shift = 12;
-		ctx.mask = 0xF;
-	} else if (!strcmp(name, "umem_clk")) {
-		ctx.shift = 16;
-		ctx.mask = 0xF;
-	} else if (!strcmp(name, "cpu_clk")) {
-		ctx.shift = 20;
-		ctx.mask = 7;
-	}
-	return ctx;
-}
-
-/**
- * sh7722_find_div_index - find divisor for setting rate
- *
- * All sh7722 clocks use the same set of multipliers/divisors. This function
- * chooses correct divisor to set the rate of clock with parent clock that
- * generates frequency of 'parent_rate'
- *
- * @parent_rate: rate of parent clock
- * @rate: requested rate to be set
- */
-static int sh7722_find_div_index(unsigned long parent_rate, unsigned rate)
-{
-	unsigned div2 = parent_rate * 2 / rate;
-	int index;
-
-	if (rate > parent_rate)
-		return -EINVAL;
-
-	for (index = 1; index < ARRAY_SIZE(divisors2); index++) {
-		if (div2 > divisors2[index - 1] && div2 <= divisors2[index])
-			break;
-	}
-	if (index >= ARRAY_SIZE(divisors2))
-		index = ARRAY_SIZE(divisors2) - 1;
-	return index;
-}
-
-static void sh7722_frqcr_recalc(struct clk *clk)
-{
-	struct frqcr_context ctx = sh7722_get_clk_context(clk->name);
-	unsigned long frqcr = ctrl_inl(FRQCR);
-	int index;
-
-	index = (frqcr >> ctx.shift) & ctx.mask;
-	clk->rate = clk->parent->rate * 2 / divisors2[index];
-}
-
-static int sh7722_frqcr_set_rate(struct clk *clk, unsigned long rate,
-				 int algo_id)
-{
-	struct frqcr_context ctx = sh7722_get_clk_context(clk->name);
-	unsigned long parent_rate = clk->parent->rate;
-	int div;
-	unsigned long frqcr;
-	int err = 0;
-
-	/* pretty invalid */
-	if (parent_rate < rate)
-		return -EINVAL;
-
-	/* look for multiplier/divisor pair */
-	div = sh7722_find_div_index(parent_rate, rate);
-	if (div<0)
-		return div;
-
-	/* calculate new value of clock rate */
-	clk->rate = parent_rate * 2 / divisors2[div];
-	frqcr = ctrl_inl(FRQCR);
-
-	/* FIXME: adjust as algo_id specifies */
-	if (algo_id != NO_CHANGE) {
-		int originator;
-		char *algo_group_1[] = { "cpu_clk", "umem_clk", "sh_clk" };
-		char *algo_group_2[] = { "sh_clk", "bus_clk" };
-		char *algo_group_3[] = { "sh_clk", "sdram_clk" };
-		char *algo_group_4[] = { "bus_clk", "peripheral_clk" };
-		char *algo_group_5[] = { "cpu_clk", "peripheral_clk" };
-		char **algo_current = NULL;
-		/* 3 is the maximum number of clocks in relation */
-		struct clk *ck[3];
-		unsigned long values[3]; /* the same comment as above */
-		int part_length = -1;
-		int i;
-
-		/*
-		 * all the steps below only required if adjustion was
-		 * requested
-		 */
-		if (algo_id == IUS_N1_N1 ||
-		    algo_id == IUS_322 ||
-		    algo_id == IUS_522 ||
-		    algo_id == IUS_N11) {
-			algo_current = algo_group_1;
-			part_length = 3;
-		}
-		if (algo_id == SB_N1) {
-			algo_current = algo_group_2;
-			part_length = 2;
-		}
-		if (algo_id == SB3_N1 ||
-		    algo_id == SB3_32 ||
-		    algo_id == SB3_43 ||
-		    algo_id == SB3_54) {
-			algo_current = algo_group_3;
-			part_length = 2;
-		}
-		if (algo_id == BP_N1) {
-			algo_current = algo_group_4;
-			part_length = 2;
-		}
-		if (algo_id == IP_N1) {
-			algo_current = algo_group_5;
-			part_length = 2;
-		}
-		if (!algo_current)
-			goto incorrect_algo_id;
-
-		originator = -1;
-		for (i = 0; i < part_length; i ++ ) {
-			if (originator >= 0 && !strcmp(clk->name,
-						       algo_current[i]))
-				originator = i;
-			ck[i] = clk_get(NULL, algo_current[i]);
-			values[i] = clk_get_rate(ck[i]);
-		}
-
-		if (originator >= 0)
-			adjust_clocks(originator, adjust_algos[algo_id],
-				      values, part_length);
-
-		for (i = 0; i < part_length; i ++ ) {
-			struct frqcr_context part_ctx;
-			int part_div;
-
-			if (likely(!err)) {
-				part_div = sh7722_find_div_index(parent_rate,
-								rate);
-				if (part_div > 0) {
-					part_ctx = sh7722_get_clk_context(
-								ck[i]->name);
-					frqcr &= ~(part_ctx.mask <<
-						   part_ctx.shift);
-					frqcr |= part_div << part_ctx.shift;
-				} else
-					err = part_div;
-			}
-
-			ck[i]->ops->recalc(ck[i]);
-			clk_put(ck[i]);
-		}
-	}
-
-	/* was there any error during recalculation ? If so, bail out.. */
-	if (unlikely(err!=0))
-		goto out_err;
-
-	/* clear FRQCR bits */
-	frqcr &= ~(ctx.mask << ctx.shift);
-	frqcr |= div << ctx.shift;
-
-	/* ...and perform actual change */
-	ctrl_outl(frqcr, FRQCR);
-	return 0;
-
-incorrect_algo_id:
-	return -EINVAL;
-out_err:
-	return err;
-}
-
-static long sh7722_frqcr_round_rate(struct clk *clk, unsigned long rate)
-{
-	unsigned long parent_rate = clk->parent->rate;
-	int div;
-
-	/* look for multiplier/divisor pair */
-	div = sh7722_find_div_index(parent_rate, rate);
-	if (div < 0)
-		return clk->rate;
-
-	/* calculate new value of clock rate */
-	return parent_rate * 2 / divisors2[div];
-}
-
-static struct clk_ops sh7722_frqcr_clk_ops = {
-	.recalc = sh7722_frqcr_recalc,
-	.set_rate = sh7722_frqcr_set_rate,
-	.round_rate = sh7722_frqcr_round_rate,
+/* Fixed 32 KHz root clock for RTC and Power Management purposes */
+static struct clk r_clk = {
+	.name           = "rclk",
+	.id             = -1,
+	.rate           = 32768,
 };
 
 /*
- * clock ops methods for SIU A/B and IrDA clock
- *
+ * Default rate for the root input clock, reset this with clk_set_rate()
+ * from the platform code.
  */
+struct clk extal_clk = {
+	.name		= "extal",
+	.id		= -1,
+	.rate		= 33333333,
+};
 
-#ifndef CONFIG_CPU_SUBTYPE_SH7343
-
-static int sh7722_siu_set_rate(struct clk *clk, unsigned long rate, int algo_id)
+/* The dll block multiplies the 32khz r_clk, may be used instead of extal */
+static unsigned long dll_recalc(struct clk *clk)
 {
-	unsigned long r;
-	int div;
+	unsigned long mult;
 
-	r = ctrl_inl(clk->arch_flags);
-	div = sh7722_find_div_index(clk->parent->rate, rate);
-	if (div < 0)
-		return div;
-	r = (r & ~0xF) | div;
-	ctrl_outl(r, clk->arch_flags);
-	return 0;
-}
-
-static void sh7722_siu_recalc(struct clk *clk)
-{
-	unsigned long r;
-
-	r = ctrl_inl(clk->arch_flags);
-	clk->rate = clk->parent->rate * 2 / divisors2[r & 0xF];
-}
-
-static int sh7722_siu_start_stop(struct clk *clk, int enable)
-{
-	unsigned long r;
-
-	r = ctrl_inl(clk->arch_flags);
-	if (enable)
-		ctrl_outl(r & ~(1 << 8), clk->arch_flags);
+	if (__raw_readl(PLLCR) & 0x1000)
+		mult = __raw_readl(DLLFRQ);
 	else
-		ctrl_outl(r | (1 << 8), clk->arch_flags);
-	return 0;
+		mult = 0;
+
+	return clk->parent->rate * mult;
 }
 
-static void sh7722_siu_enable(struct clk *clk)
+static struct clk_ops dll_clk_ops = {
+	.recalc		= dll_recalc,
+};
+
+static struct clk dll_clk = {
+	.name           = "dll_clk",
+	.id             = -1,
+	.ops		= &dll_clk_ops,
+	.parent		= &r_clk,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+static unsigned long pll_recalc(struct clk *clk)
 {
-	sh7722_siu_start_stop(clk, 1);
-}
+	unsigned long mult = 1;
+	unsigned long div = 1;
 
-static void sh7722_siu_disable(struct clk *clk)
-{
-	sh7722_siu_start_stop(clk, 0);
-}
-
-static struct clk_ops sh7722_siu_clk_ops = {
-	.recalc = sh7722_siu_recalc,
-	.set_rate = sh7722_siu_set_rate,
-	.enable = sh7722_siu_enable,
-	.disable = sh7722_siu_disable,
-};
-
-#endif /* CONFIG_CPU_SUBTYPE_SH7343 */
-
-static void sh7722_video_enable(struct clk *clk)
-{
-	unsigned long r;
-
-	r = ctrl_inl(VCLKCR);
-	ctrl_outl( r & ~(1<<8), VCLKCR);
-}
-
-static void sh7722_video_disable(struct clk *clk)
-{
-	unsigned long r;
-
-	r = ctrl_inl(VCLKCR);
-	ctrl_outl( r | (1<<8), VCLKCR);
-}
-
-static int sh7722_video_set_rate(struct clk *clk, unsigned long rate,
-				 int algo_id)
-{
-	unsigned long r;
-
-	r = ctrl_inl(VCLKCR);
-	r &= ~0x3F;
-	r |= ((clk->parent->rate / rate - 1) & 0x3F);
-	ctrl_outl(r, VCLKCR);
-	return 0;
-}
-
-static void sh7722_video_recalc(struct clk *clk)
-{
-	unsigned long r;
-
-	r = ctrl_inl(VCLKCR);
-	clk->rate = clk->parent->rate / ((r & 0x3F) + 1);
-}
-
-static struct clk_ops sh7722_video_clk_ops = {
-	.recalc = sh7722_video_recalc,
-	.set_rate = sh7722_video_set_rate,
-	.enable = sh7722_video_enable,
-	.disable = sh7722_video_disable,
-};
-/*
- * and at last, clock definitions themselves
- */
-static struct clk sh7722_umem_clock = {
-	.name = "umem_clk",
-	.ops = &sh7722_frqcr_clk_ops,
-	.flags = CLK_RATE_PROPAGATES,
-};
-
-static struct clk sh7722_sh_clock = {
-	.name = "sh_clk",
-	.ops = &sh7722_frqcr_clk_ops,
-	.flags = CLK_RATE_PROPAGATES,
-};
-
-static struct clk sh7722_peripheral_clock = {
-	.name = "peripheral_clk",
-	.ops = &sh7722_frqcr_clk_ops,
-	.flags = CLK_RATE_PROPAGATES,
-};
-
-static struct clk sh7722_sdram_clock = {
-	.name = "sdram_clk",
-	.ops = &sh7722_frqcr_clk_ops,
-};
-
-static struct clk sh7722_r_clock = {
-	.name = "r_clk",
-	.rate = 32768,
-	.flags = CLK_RATE_PROPAGATES,
-};
-
-#ifndef CONFIG_CPU_SUBTYPE_SH7343
-
-/*
- * these three clocks - SIU A, SIU B, IrDA - share the same clk_ops
- * methods of clk_ops determine which register they should access by
- * examining clk->name field
- */
-static struct clk sh7722_siu_a_clock = {
-	.name = "siu_a_clk",
-	.arch_flags = SCLKACR,
-	.ops = &sh7722_siu_clk_ops,
-};
-
-static struct clk sh7722_siu_b_clock = {
-	.name = "siu_b_clk",
-	.arch_flags = SCLKBCR,
-	.ops = &sh7722_siu_clk_ops,
-};
-
-#if defined(CONFIG_CPU_SUBTYPE_SH7722)
-static struct clk sh7722_irda_clock = {
-	.name = "irda_clk",
-	.arch_flags = IrDACLKCR,
-	.ops = &sh7722_siu_clk_ops,
-};
-#endif
-#endif /* CONFIG_CPU_SUBTYPE_SH7343 */
-
-static struct clk sh7722_video_clock = {
-	.name = "video_clk",
-	.ops = &sh7722_video_clk_ops,
-};
-
-#define MSTPCR_ARCH_FLAGS(reg, bit) (((reg) << 8) | (bit))
-#define MSTPCR_ARCH_FLAGS_REG(value) ((value) >> 8)
-#define MSTPCR_ARCH_FLAGS_BIT(value) ((value) & 0xff)
-
-static int sh7722_mstpcr_start_stop(struct clk *clk, int enable)
-{
-	unsigned long bit = MSTPCR_ARCH_FLAGS_BIT(clk->arch_flags);
-	unsigned long reg;
-	unsigned long r;
-
-	switch(MSTPCR_ARCH_FLAGS_REG(clk->arch_flags)) {
-	case 0:
-		reg = MSTPCR0;
-		break;
-	case 1:
-		reg = MSTPCR1;
-		break;
-	case 2:
-		reg = MSTPCR2;
-		break;
-	default:
-		return -EINVAL;
-	}  
-
-	r = ctrl_inl(reg);
-
-	if (enable)
-		r &= ~(1 << bit);
+	if (__raw_readl(PLLCR) & 0x4000)
+		mult = (((__raw_readl(FRQCR) >> 24) & 0x1f) + 1);
 	else
-		r |= (1 << bit);
+		div = 2;
 
-	ctrl_outl(r, reg);
-	return 0;
+	return (clk->parent->rate * mult) / div;
 }
 
-static void sh7722_mstpcr_enable(struct clk *clk)
-{
-	sh7722_mstpcr_start_stop(clk, 1);
-}
-
-static void sh7722_mstpcr_disable(struct clk *clk)
-{
-	sh7722_mstpcr_start_stop(clk, 0);
-}
-
-static void sh7722_mstpcr_recalc(struct clk *clk)
-{
-	if (clk->parent)
-		clk->rate = clk->parent->rate;
-}
-
-static struct clk_ops sh7722_mstpcr_clk_ops = {
-	.enable = sh7722_mstpcr_enable,
-	.disable = sh7722_mstpcr_disable,
-	.recalc = sh7722_mstpcr_recalc,
+static struct clk_ops pll_clk_ops = {
+	.recalc		= pll_recalc,
 };
 
-#define MSTPCR(_name, _parent, regnr, bitnr) \
-{						\
-	.name = _name,				\
-	.arch_flags = MSTPCR_ARCH_FLAGS(regnr, bitnr),	\
-	.ops = (void *)_parent,		\
-}
-
-static struct clk sh7722_mstpcr_clocks[] = {
-#if defined(CONFIG_CPU_SUBTYPE_SH7722)
-	MSTPCR("uram0", "umem_clk", 0, 28),
-	MSTPCR("xymem0", "bus_clk", 0, 26),
-	MSTPCR("tmu0", "peripheral_clk", 0, 15),
-	MSTPCR("cmt0", "r_clk", 0, 14),
-	MSTPCR("rwdt0", "r_clk", 0, 13),
-	MSTPCR("flctl0", "peripheral_clk", 0, 10),
-	MSTPCR("scif0", "peripheral_clk", 0, 7),
-	MSTPCR("scif1", "peripheral_clk", 0, 6),
-	MSTPCR("scif2", "peripheral_clk", 0, 5),
-	MSTPCR("i2c0", "peripheral_clk", 1, 9),
-	MSTPCR("rtc0", "r_clk", 1, 8),
-	MSTPCR("sdhi0", "peripheral_clk", 2, 18),
-	MSTPCR("keysc0", "r_clk", 2, 14),
-	MSTPCR("usbf0", "peripheral_clk", 2, 11),
-	MSTPCR("2dg0", "bus_clk", 2, 9),
-	MSTPCR("siu0", "bus_clk", 2, 8),
-	MSTPCR("vou0", "bus_clk", 2, 5),
-	MSTPCR("jpu0", "bus_clk", 2, 6),
-	MSTPCR("beu0", "bus_clk", 2, 4),
-	MSTPCR("ceu0", "bus_clk", 2, 3),
-	MSTPCR("veu0", "bus_clk", 2, 2),
-	MSTPCR("vpu0", "bus_clk", 2, 1),
-	MSTPCR("lcdc0", "bus_clk", 2, 0),
-#endif
-#if defined(CONFIG_CPU_SUBTYPE_SH7723)
-	/* See page 60 of Datasheet V1.0: Overview -> Block Diagram */
-	MSTPCR("tlb0", "cpu_clk", 0, 31),
-	MSTPCR("ic0", "cpu_clk", 0, 30),
-	MSTPCR("oc0", "cpu_clk", 0, 29),
-	MSTPCR("l2c0", "sh_clk", 0, 28),
-	MSTPCR("ilmem0", "cpu_clk", 0, 27),
-	MSTPCR("fpu0", "cpu_clk", 0, 24),
-	MSTPCR("intc0", "cpu_clk", 0, 22),
-	MSTPCR("dmac0", "bus_clk", 0, 21),
-	MSTPCR("sh0", "sh_clk", 0, 20),
-	MSTPCR("hudi0", "peripheral_clk", 0, 19),
-	MSTPCR("ubc0", "cpu_clk", 0, 17),
-	MSTPCR("tmu0", "peripheral_clk", 0, 15),
-	MSTPCR("cmt0", "r_clk", 0, 14),
-	MSTPCR("rwdt0", "r_clk", 0, 13),
-	MSTPCR("dmac1", "bus_clk", 0, 12),
-	MSTPCR("tmu1", "peripheral_clk", 0, 11),
-	MSTPCR("flctl0", "peripheral_clk", 0, 10),
-	MSTPCR("scif0", "peripheral_clk", 0, 9),
-	MSTPCR("scif1", "peripheral_clk", 0, 8),
-	MSTPCR("scif2", "peripheral_clk", 0, 7),
-	MSTPCR("scif3", "bus_clk", 0, 6),
-	MSTPCR("scif4", "bus_clk", 0, 5),
-	MSTPCR("scif5", "bus_clk", 0, 4),
-	MSTPCR("msiof0", "bus_clk", 0, 2),
-	MSTPCR("msiof1", "bus_clk", 0, 1),
-	MSTPCR("meram0", "sh_clk", 0, 0),
-	MSTPCR("i2c0", "peripheral_clk", 1, 9),
-	MSTPCR("rtc0", "r_clk", 1, 8),
-	MSTPCR("atapi0", "sh_clk", 2, 28),
-	MSTPCR("adc0", "peripheral_clk", 2, 28),
-	MSTPCR("tpu0", "bus_clk", 2, 25),
-	MSTPCR("irda0", "peripheral_clk", 2, 24),
-	MSTPCR("tsif0", "bus_clk", 2, 22),
-	MSTPCR("icb0", "bus_clk", 2, 21),
-	MSTPCR("sdhi0", "bus_clk", 2, 18),
-	MSTPCR("sdhi1", "bus_clk", 2, 17),
-	MSTPCR("keysc0", "r_clk", 2, 14),
-	MSTPCR("usb0", "bus_clk", 2, 11),
-	MSTPCR("2dg0", "bus_clk", 2, 10),
-	MSTPCR("siu0", "bus_clk", 2, 8),
-	MSTPCR("veu1", "bus_clk", 2, 6),
-	MSTPCR("vou0", "bus_clk", 2, 5),
-	MSTPCR("beu0", "bus_clk", 2, 4),
-	MSTPCR("ceu0", "bus_clk", 2, 3),
-	MSTPCR("veu0", "bus_clk", 2, 2),
-	MSTPCR("vpu0", "bus_clk", 2, 1),
-	MSTPCR("lcdc0", "bus_clk", 2, 0),
-#endif
-#if defined(CONFIG_CPU_SUBTYPE_SH7343)
-	MSTPCR("uram0", "umem_clk", 0, 28),
-	MSTPCR("xymem0", "bus_clk", 0, 26),
-	MSTPCR("tmu0", "peripheral_clk", 0, 15),
-	MSTPCR("cmt0", "r_clk", 0, 14),
-	MSTPCR("rwdt0", "r_clk", 0, 13),
-	MSTPCR("scif0", "peripheral_clk", 0, 7),
-	MSTPCR("scif1", "peripheral_clk", 0, 6),
-	MSTPCR("scif2", "peripheral_clk", 0, 5),
-	MSTPCR("scif3", "peripheral_clk", 0, 4),
-	MSTPCR("i2c0", "peripheral_clk", 1, 9),
-	MSTPCR("i2c1", "peripheral_clk", 1, 8),
-	MSTPCR("sdhi0", "peripheral_clk", 2, 18),
-	MSTPCR("keysc0", "r_clk", 2, 14),
-	MSTPCR("usbf0", "peripheral_clk", 2, 11),
-	MSTPCR("siu0", "bus_clk", 2, 8),
-	MSTPCR("jpu0", "bus_clk", 2, 6),
-	MSTPCR("vou0", "bus_clk", 2, 5),
-	MSTPCR("beu0", "bus_clk", 2, 4),
-	MSTPCR("ceu0", "bus_clk", 2, 3),
-	MSTPCR("veu0", "bus_clk", 2, 2),
-	MSTPCR("vpu0", "bus_clk", 2, 1),
-	MSTPCR("lcdc0", "bus_clk", 2, 0),
-#endif
-#if defined(CONFIG_CPU_SUBTYPE_SH7366)
-	/* See page 52 of Datasheet V0.40: Overview -> Block Diagram */
-	MSTPCR("tlb0", "cpu_clk", 0, 31),
-	MSTPCR("ic0", "cpu_clk", 0, 30),
-	MSTPCR("oc0", "cpu_clk", 0, 29),
-	MSTPCR("rsmem0", "sh_clk", 0, 28),
-	MSTPCR("xymem0", "cpu_clk", 0, 26),
-	MSTPCR("intc30", "peripheral_clk", 0, 23),
-	MSTPCR("intc0", "peripheral_clk", 0, 22),
-	MSTPCR("dmac0", "bus_clk", 0, 21),
-	MSTPCR("sh0", "sh_clk", 0, 20),
-	MSTPCR("hudi0", "peripheral_clk", 0, 19),
-	MSTPCR("ubc0", "cpu_clk", 0, 17),
-	MSTPCR("tmu0", "peripheral_clk", 0, 15),
-	MSTPCR("cmt0", "r_clk", 0, 14),
-	MSTPCR("rwdt0", "r_clk", 0, 13),
-	MSTPCR("flctl0", "peripheral_clk", 0, 10),
-	MSTPCR("scif0", "peripheral_clk", 0, 7),
-	MSTPCR("scif1", "bus_clk", 0, 6),
-	MSTPCR("scif2", "bus_clk", 0, 5),
-	MSTPCR("msiof0", "peripheral_clk", 0, 2),
-	MSTPCR("sbr0", "peripheral_clk", 0, 1),
-	MSTPCR("i2c0", "peripheral_clk", 1, 9),
-	MSTPCR("icb0", "bus_clk", 2, 27),
-	MSTPCR("meram0", "sh_clk", 2, 26),
-	MSTPCR("dacc0", "peripheral_clk", 2, 24),
-	MSTPCR("dacy0", "peripheral_clk", 2, 23),
-	MSTPCR("tsif0", "bus_clk", 2, 22),
-	MSTPCR("sdhi0", "bus_clk", 2, 18),
-	MSTPCR("mmcif0", "bus_clk", 2, 17),
-	MSTPCR("usb0", "bus_clk", 2, 11),
-	MSTPCR("siu0", "bus_clk", 2, 8),
-	MSTPCR("veu1", "bus_clk", 2, 7),
-	MSTPCR("vou0", "bus_clk", 2, 5),
-	MSTPCR("beu0", "bus_clk", 2, 4),
-	MSTPCR("ceu0", "bus_clk", 2, 3),
-	MSTPCR("veu0", "bus_clk", 2, 2),
-	MSTPCR("vpu0", "bus_clk", 2, 1),
-	MSTPCR("lcdc0", "bus_clk", 2, 0),
-#endif
+static struct clk pll_clk = {
+	.name		= "pll_clk",
+	.id		= -1,
+	.ops		= &pll_clk_ops,
+	.flags		= CLK_ENABLE_ON_INIT,
 };
 
-static struct clk *sh7722_clocks[] = {
-	&sh7722_umem_clock,
-	&sh7722_sh_clock,
-	&sh7722_peripheral_clock,
-	&sh7722_sdram_clock,
-#ifndef CONFIG_CPU_SUBTYPE_SH7343
-	&sh7722_siu_a_clock,
-	&sh7722_siu_b_clock,
-#if defined(CONFIG_CPU_SUBTYPE_SH7722)
-	&sh7722_irda_clock,
-#endif
-#endif
-	&sh7722_video_clock,
+struct clk *main_clks[] = {
+	&r_clk,
+	&extal_clk,
+	&dll_clk,
+	&pll_clk,
 };
 
-/*
- * init in order: master, module, bus, cpu
- */
-struct clk_ops *onchip_ops[] = {
-	&sh7722_master_clk_ops,
-	&sh7722_module_clk_ops,
-	&sh7722_frqcr_clk_ops,
-	&sh7722_frqcr_clk_ops,
+static int multipliers[] = { 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1 };
+static int divisors[] = { 1, 3, 2, 5, 3, 4, 5, 6, 8, 10, 12, 16, 20 };
+
+static struct clk_div_mult_table div4_table = {
+	.divisors = divisors,
+	.nr_divisors = ARRAY_SIZE(divisors),
+	.multipliers = multipliers,
+	.nr_multipliers = ARRAY_SIZE(multipliers),
 };
 
-void __init
-arch_init_clk_ops(struct clk_ops **ops, int type)
-{
-	BUG_ON(type < 0 || type > ARRAY_SIZE(onchip_ops));
-	*ops = onchip_ops[type];
-}
+enum { DIV4_I, DIV4_U, DIV4_SH, DIV4_B, DIV4_B3, DIV4_P,
+       DIV4_SIUA, DIV4_SIUB, DIV4_IRDA, DIV4_NR };
+
+#define DIV4(_str, _reg, _bit, _mask, _flags) \
+  SH_CLK_DIV4(_str, &pll_clk, _reg, _bit, _mask, _flags)
+
+struct clk div4_clks[DIV4_NR] = {
+	[DIV4_I] = DIV4("cpu_clk", FRQCR, 20, 0x1fef, CLK_ENABLE_ON_INIT),
+	[DIV4_U] = DIV4("umem_clk", FRQCR, 16, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_SH] = DIV4("shyway_clk", FRQCR, 12, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_B] = DIV4("bus_clk", FRQCR, 8, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_B3] = DIV4("b3_clk", FRQCR, 4, 0x1fff, CLK_ENABLE_ON_INIT),
+	[DIV4_P] = DIV4("peripheral_clk", FRQCR, 0, 0x1fff, 0),
+	[DIV4_SIUA] = DIV4("siua_clk", SCLKACR, 0, 0x1fff, 0),
+	[DIV4_SIUB] = DIV4("siub_clk", SCLKBCR, 0, 0x1fff, 0),
+	[DIV4_IRDA] = DIV4("irda_clk", IRDACLKCR, 0, 0x1fff, 0),
+};
+
+struct clk div6_clks[] = {
+	SH_CLK_DIV6("video_clk", &pll_clk, VCLKCR, 0),
+};
+
+#define MSTP(_str, _parent, _reg, _bit, _flags) \
+  SH_CLK_MSTP32(_str, -1, _parent, _reg, _bit, _flags)
+
+static struct clk mstp_clks[] = {
+	MSTP("uram0", &div4_clks[DIV4_U], MSTPCR0, 28, CLK_ENABLE_ON_INIT),
+	MSTP("xymem0", &div4_clks[DIV4_B], MSTPCR0, 26, CLK_ENABLE_ON_INIT),
+	MSTP("tmu0", &div4_clks[DIV4_P], MSTPCR0, 15, 0),
+	MSTP("cmt0", &r_clk, MSTPCR0, 14, 0),
+	MSTP("rwdt0", &r_clk, MSTPCR0, 13, 0),
+	MSTP("flctl0", &div4_clks[DIV4_P], MSTPCR0, 10, 0),
+	MSTP("scif0", &div4_clks[DIV4_P], MSTPCR0, 7, 0),
+	MSTP("scif1", &div4_clks[DIV4_P], MSTPCR0, 6, 0),
+	MSTP("scif2", &div4_clks[DIV4_P], MSTPCR0, 5, 0),
+
+	MSTP("i2c0", &div4_clks[DIV4_P], MSTPCR1, 9, 0),
+	MSTP("rtc0", &r_clk, MSTPCR1, 8, 0),
+
+	MSTP("sdhi0", &div4_clks[DIV4_P], MSTPCR2, 18, 0),
+	MSTP("keysc0", &r_clk, MSTPCR2, 14, 0),
+	MSTP("usbf0", &div4_clks[DIV4_P], MSTPCR2, 11, 0),
+	MSTP("2dg0", &div4_clks[DIV4_B], MSTPCR2, 9, 0),
+	MSTP("siu0", &div4_clks[DIV4_B], MSTPCR2, 8, 0),
+	MSTP("vou0", &div4_clks[DIV4_B], MSTPCR2, 5, 0),
+	MSTP("jpu0", &div4_clks[DIV4_B], MSTPCR2, 6, CLK_ENABLE_ON_INIT),
+	MSTP("beu0", &div4_clks[DIV4_B], MSTPCR2, 4, 0),
+	MSTP("ceu0", &div4_clks[DIV4_B], MSTPCR2, 3, 0),
+	MSTP("veu0", &div4_clks[DIV4_B], MSTPCR2, 2, CLK_ENABLE_ON_INIT),
+	MSTP("vpu0", &div4_clks[DIV4_B], MSTPCR2, 1, CLK_ENABLE_ON_INIT),
+	MSTP("lcdc0", &div4_clks[DIV4_B], MSTPCR2, 0, 0),
+};
 
 int __init arch_clk_init(void)
 {
-	struct clk *clk;
-	int i;
+	int k, ret = 0;
 
-	clk = clk_get(NULL, "master_clk");
-	for (i = 0; i < ARRAY_SIZE(sh7722_clocks); i++) {
-		pr_debug( "Registering clock '%s'\n", sh7722_clocks[i]->name);
-		sh7722_clocks[i]->parent = clk;
-		clk_register(sh7722_clocks[i]);
-	}
-	clk_put(clk);
+	/* autodetect extal or dll configuration */
+	if (__raw_readl(PLLCR) & 0x1000)
+		pll_clk.parent = &dll_clk;
+	else
+		pll_clk.parent = &extal_clk;
 
-	clk_register(&sh7722_r_clock);
+	for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
+		ret = clk_register(main_clks[k]);
 
-	for (i = 0; i < ARRAY_SIZE(sh7722_mstpcr_clocks); i++) {
-		pr_debug( "Registering mstpcr clock '%s'\n",
-			  sh7722_mstpcr_clocks[i].name);
-		clk = clk_get(NULL, (void *) sh7722_mstpcr_clocks[i].ops);
-		sh7722_mstpcr_clocks[i].parent = clk;
-		sh7722_mstpcr_clocks[i].ops = &sh7722_mstpcr_clk_ops;
-		clk_register(&sh7722_mstpcr_clocks[i]);
-		clk_put(clk);
-	}
+	if (!ret)
+		ret = sh_clk_div4_register(div4_clks, DIV4_NR, &div4_table);
 
-	clk_recalc_rate(&sh7722_r_clock); /* make sure rate gets propagated */
+	if (!ret)
+		ret = sh_clk_div6_register(div6_clks, ARRAY_SIZE(div6_clks));
 
-	return 0;
+	if (!ret)
+		ret = sh_clk_mstp32_register(mstp_clks, ARRAY_SIZE(mstp_clks));
+
+	return ret;
 }
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7723.c b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c
new file mode 100644
index 000000000000..e67c2678b8ae
--- /dev/null
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c
@@ -0,0 +1,222 @@
+/*
+ * arch/sh/kernel/cpu/sh4a/clock-sh7723.c
+ *
+ * SH7723 clock framework support
+ *
+ * Copyright (C) 2009 Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <asm/clock.h>
+
+/* SH7723 registers */
+#define FRQCR		0xa4150000
+#define VCLKCR		0xa4150004
+#define SCLKACR		0xa4150008
+#define SCLKBCR		0xa415000c
+#define IRDACLKCR	0xa4150018
+#define PLLCR		0xa4150024
+#define MSTPCR0		0xa4150030
+#define MSTPCR1		0xa4150034
+#define MSTPCR2		0xa4150038
+#define DLLFRQ		0xa4150050
+
+/* Fixed 32 KHz root clock for RTC and Power Management purposes */
+static struct clk r_clk = {
+	.name           = "rclk",
+	.id             = -1,
+	.rate           = 32768,
+};
+
+/*
+ * Default rate for the root input clock, reset this with clk_set_rate()
+ * from the platform code.
+ */
+struct clk extal_clk = {
+	.name		= "extal",
+	.id		= -1,
+	.rate		= 33333333,
+};
+
+/* The dll multiplies the 32khz r_clk, may be used instead of extal */
+static unsigned long dll_recalc(struct clk *clk)
+{
+	unsigned long mult;
+
+	if (__raw_readl(PLLCR) & 0x1000)
+		mult = __raw_readl(DLLFRQ);
+	else
+		mult = 0;
+
+	return clk->parent->rate * mult;
+}
+
+static struct clk_ops dll_clk_ops = {
+	.recalc		= dll_recalc,
+};
+
+static struct clk dll_clk = {
+	.name           = "dll_clk",
+	.id             = -1,
+	.ops		= &dll_clk_ops,
+	.parent		= &r_clk,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+static unsigned long pll_recalc(struct clk *clk)
+{
+	unsigned long mult = 1;
+	unsigned long div = 1;
+
+	if (__raw_readl(PLLCR) & 0x4000)
+		mult = (((__raw_readl(FRQCR) >> 24) & 0x1f) + 1);
+	else
+		div = 2;
+
+	return (clk->parent->rate * mult) / div;
+}
+
+static struct clk_ops pll_clk_ops = {
+	.recalc		= pll_recalc,
+};
+
+static struct clk pll_clk = {
+	.name		= "pll_clk",
+	.id		= -1,
+	.ops		= &pll_clk_ops,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+struct clk *main_clks[] = {
+	&r_clk,
+	&extal_clk,
+	&dll_clk,
+	&pll_clk,
+};
+
+static int multipliers[] = { 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1 };
+static int divisors[] = { 1, 3, 2, 5, 3, 4, 5, 6, 8, 10, 12, 16, 20 };
+
+static struct clk_div_mult_table div4_table = {
+	.divisors = divisors,
+	.nr_divisors = ARRAY_SIZE(divisors),
+	.multipliers = multipliers,
+	.nr_multipliers = ARRAY_SIZE(multipliers),
+};
+
+enum { DIV4_I, DIV4_U, DIV4_SH, DIV4_B, DIV4_B3, DIV4_P,
+       DIV4_SIUA, DIV4_SIUB, DIV4_IRDA, DIV4_NR };
+
+#define DIV4(_str, _reg, _bit, _mask, _flags) \
+  SH_CLK_DIV4(_str, &pll_clk, _reg, _bit, _mask, _flags)
+
+struct clk div4_clks[DIV4_NR] = {
+	[DIV4_I] = DIV4("cpu_clk", FRQCR, 20, 0x0dbf, CLK_ENABLE_ON_INIT),
+	[DIV4_U] = DIV4("umem_clk", FRQCR, 16, 0x0dbf, CLK_ENABLE_ON_INIT),
+	[DIV4_SH] = DIV4("shyway_clk", FRQCR, 12, 0x0dbf, CLK_ENABLE_ON_INIT),
+	[DIV4_B] = DIV4("bus_clk", FRQCR, 8, 0x0dbf, CLK_ENABLE_ON_INIT),
+	[DIV4_B3] = DIV4("b3_clk", FRQCR, 4, 0x0db4, CLK_ENABLE_ON_INIT),
+	[DIV4_P] = DIV4("peripheral_clk", FRQCR, 0, 0x0dbf, 0),
+	[DIV4_SIUA] = DIV4("siua_clk", SCLKACR, 0, 0x0dbf, 0),
+	[DIV4_SIUB] = DIV4("siub_clk", SCLKBCR, 0, 0x0dbf, 0),
+	[DIV4_IRDA] = DIV4("irda_clk", IRDACLKCR, 0, 0x0dbf, 0),
+};
+
+struct clk div6_clks[] = {
+	SH_CLK_DIV6("video_clk", &pll_clk, VCLKCR, 0),
+};
+
+#define MSTP(_str, _parent, _reg, _bit, _force_on, _need_cpg, _need_ram) \
+  SH_CLK_MSTP32(_str, -1, _parent, _reg, _bit, _force_on * CLK_ENABLE_ON_INIT)
+
+static struct clk mstp_clks[] = {
+	/* See page 60 of Datasheet V1.0: Overview -> Block Diagram */
+	MSTP("tlb0", &div4_clks[DIV4_I], MSTPCR0, 31, 1, 1, 0),
+	MSTP("ic0", &div4_clks[DIV4_I], MSTPCR0, 30, 1, 1, 0),
+	MSTP("oc0", &div4_clks[DIV4_I], MSTPCR0, 29, 1, 1, 0),
+	MSTP("l2c0", &div4_clks[DIV4_SH], MSTPCR0, 28, 1, 1, 0),
+	MSTP("ilmem0", &div4_clks[DIV4_I], MSTPCR0, 27, 1, 1, 0),
+	MSTP("fpu0", &div4_clks[DIV4_I], MSTPCR0, 24, 1, 1, 0),
+	MSTP("intc0", &div4_clks[DIV4_I], MSTPCR0, 22, 1, 1, 0),
+	MSTP("dmac0", &div4_clks[DIV4_B], MSTPCR0, 21, 0, 1, 1),
+	MSTP("sh0", &div4_clks[DIV4_SH], MSTPCR0, 20, 0, 1, 0),
+	MSTP("hudi0", &div4_clks[DIV4_P], MSTPCR0, 19, 0, 1, 0),
+	MSTP("ubc0", &div4_clks[DIV4_I], MSTPCR0, 17, 0, 1, 0),
+	MSTP("tmu0", &div4_clks[DIV4_P], MSTPCR0, 15, 0, 1, 0),
+	MSTP("cmt0", &r_clk, MSTPCR0, 14, 0, 0, 0),
+	MSTP("rwdt0", &r_clk, MSTPCR0, 13, 0, 0, 0),
+	MSTP("dmac1", &div4_clks[DIV4_B], MSTPCR0, 12, 0, 1, 1),
+	MSTP("tmu1", &div4_clks[DIV4_P], MSTPCR0, 11, 0, 1, 0),
+	MSTP("flctl0", &div4_clks[DIV4_P], MSTPCR0, 10, 0, 1, 0),
+	MSTP("scif0", &div4_clks[DIV4_P], MSTPCR0, 9, 0, 1, 0),
+	MSTP("scif1", &div4_clks[DIV4_P], MSTPCR0, 8, 0, 1, 0),
+	MSTP("scif2", &div4_clks[DIV4_P], MSTPCR0, 7, 0, 1, 0),
+	MSTP("scif3", &div4_clks[DIV4_B], MSTPCR0, 6, 0, 1, 0),
+	MSTP("scif4", &div4_clks[DIV4_B], MSTPCR0, 5, 0, 1, 0),
+	MSTP("scif5", &div4_clks[DIV4_B], MSTPCR0, 4, 0, 1, 0),
+	MSTP("msiof0", &div4_clks[DIV4_B], MSTPCR0, 2, 0, 1, 0),
+	MSTP("msiof1", &div4_clks[DIV4_B], MSTPCR0, 1, 0, 1, 0),
+	MSTP("meram0", &div4_clks[DIV4_SH], MSTPCR0, 0, 1, 1, 0),
+
+	MSTP("i2c0", &div4_clks[DIV4_P], MSTPCR1, 9, 0, 1, 0),
+	MSTP("rtc0", &r_clk, MSTPCR1, 8, 0, 0, 0),
+
+	MSTP("atapi0", &div4_clks[DIV4_SH], MSTPCR2, 28, 0, 1, 0),
+	MSTP("adc0", &div4_clks[DIV4_P], MSTPCR2, 27, 0, 1, 0),
+	MSTP("tpu0", &div4_clks[DIV4_B], MSTPCR2, 25, 0, 1, 0),
+	MSTP("irda0", &div4_clks[DIV4_P], MSTPCR2, 24, 0, 1, 0),
+	MSTP("tsif0", &div4_clks[DIV4_B], MSTPCR2, 22, 0, 1, 0),
+	MSTP("icb0", &div4_clks[DIV4_B], MSTPCR2, 21, 0, 1, 1),
+	MSTP("sdhi0", &div4_clks[DIV4_B], MSTPCR2, 18, 0, 1, 0),
+	MSTP("sdhi1", &div4_clks[DIV4_B], MSTPCR2, 17, 0, 1, 0),
+	MSTP("keysc0", &r_clk, MSTPCR2, 14, 0, 0, 0),
+	MSTP("usb0", &div4_clks[DIV4_B], MSTPCR2, 11, 0, 1, 0),
+	MSTP("2dg0", &div4_clks[DIV4_B], MSTPCR2, 10, 0, 1, 1),
+	MSTP("siu0", &div4_clks[DIV4_B], MSTPCR2, 8, 0, 1, 0),
+	MSTP("veu1", &div4_clks[DIV4_B], MSTPCR2, 6, 1, 1, 1),
+	MSTP("vou0", &div4_clks[DIV4_B], MSTPCR2, 5, 0, 1, 1),
+	MSTP("beu0", &div4_clks[DIV4_B], MSTPCR2, 4, 0, 1, 1),
+	MSTP("ceu0", &div4_clks[DIV4_B], MSTPCR2, 3, 0, 1, 1),
+	MSTP("veu0", &div4_clks[DIV4_B], MSTPCR2, 2, 1, 1, 1),
+	MSTP("vpu0", &div4_clks[DIV4_B], MSTPCR2, 1, 1, 1, 1),
+	MSTP("lcdc0", &div4_clks[DIV4_B], MSTPCR2, 0, 0, 1, 1),
+};
+
+int __init arch_clk_init(void)
+{
+	int k, ret = 0;
+
+	/* autodetect extal or dll configuration */
+	if (__raw_readl(PLLCR) & 0x1000)
+		pll_clk.parent = &dll_clk;
+	else
+		pll_clk.parent = &extal_clk;
+
+	for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
+		ret = clk_register(main_clks[k]);
+
+	if (!ret)
+		ret = sh_clk_div4_register(div4_clks, DIV4_NR, &div4_table);
+
+	if (!ret)
+		ret = sh_clk_div6_register(div6_clks, ARRAY_SIZE(div6_clks));
+
+	if (!ret)
+		ret = sh_clk_mstp32_register(mstp_clks, ARRAY_SIZE(mstp_clks));
+
+	return ret;
+}
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7724.c b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c
new file mode 100644
index 000000000000..5d5c9b952883
--- /dev/null
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7724.c
@@ -0,0 +1,242 @@
+/*
+ * arch/sh/kernel/cpu/sh4a/clock-sh7724.c
+ *
+ * SH7724 clock framework support
+ *
+ * Copyright (C) 2009 Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <asm/clock.h>
+
+/* SH7724 registers */
+#define FRQCRA		0xa4150000
+#define FRQCRB		0xa4150004
+#define VCLKCR		0xa4150048
+#define FCLKACR		0xa4150008
+#define FCLKBCR		0xa415000c
+#define IRDACLKCR	0xa4150018
+#define PLLCR		0xa4150024
+#define MSTPCR0		0xa4150030
+#define MSTPCR1		0xa4150034
+#define MSTPCR2		0xa4150038
+#define SPUCLKCR	0xa415003c
+#define FLLFRQ		0xa4150050
+#define LSTATS		0xa4150060
+
+/* Fixed 32 KHz root clock for RTC and Power Management purposes */
+static struct clk r_clk = {
+	.name           = "rclk",
+	.id             = -1,
+	.rate           = 32768,
+};
+
+/*
+ * Default rate for the root input clock, reset this with clk_set_rate()
+ * from the platform code.
+ */
+struct clk extal_clk = {
+	.name		= "extal",
+	.id		= -1,
+	.rate		= 33333333,
+};
+
+/* The fll multiplies the 32khz r_clk, may be used instead of extal */
+static unsigned long fll_recalc(struct clk *clk)
+{
+	unsigned long mult = 0;
+	unsigned long div = 1;
+
+	if (__raw_readl(PLLCR) & 0x1000)
+		mult = __raw_readl(FLLFRQ) & 0x3ff;
+
+	if (__raw_readl(FLLFRQ) & 0x4000)
+		div = 2;
+
+	return (clk->parent->rate * mult) / div;
+}
+
+static struct clk_ops fll_clk_ops = {
+	.recalc		= fll_recalc,
+};
+
+static struct clk fll_clk = {
+	.name           = "fll_clk",
+	.id             = -1,
+	.ops		= &fll_clk_ops,
+	.parent		= &r_clk,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+static unsigned long pll_recalc(struct clk *clk)
+{
+	unsigned long mult = 1;
+
+	if (__raw_readl(PLLCR) & 0x4000)
+		mult = (((__raw_readl(FRQCRA) >> 24) & 0x3f) + 1) * 2;
+
+	return clk->parent->rate * mult;
+}
+
+static struct clk_ops pll_clk_ops = {
+	.recalc		= pll_recalc,
+};
+
+static struct clk pll_clk = {
+	.name		= "pll_clk",
+	.id		= -1,
+	.ops		= &pll_clk_ops,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+/* A fixed divide-by-3 block use by the div6 clocks */
+static unsigned long div3_recalc(struct clk *clk)
+{
+	return clk->parent->rate / 3;
+}
+
+static struct clk_ops div3_clk_ops = {
+	.recalc		= div3_recalc,
+};
+
+static struct clk div3_clk = {
+	.name		= "div3_clk",
+	.id		= -1,
+	.ops		= &div3_clk_ops,
+	.parent		= &pll_clk,
+};
+
+struct clk *main_clks[] = {
+	&r_clk,
+	&extal_clk,
+	&fll_clk,
+	&pll_clk,
+	&div3_clk,
+};
+
+static int divisors[] = { 2, 0, 4, 6, 8, 12, 16, 0, 24, 32, 36, 48, 0, 72 };
+
+static struct clk_div_mult_table div4_table = {
+	.divisors = divisors,
+	.nr_divisors = ARRAY_SIZE(divisors),
+};
+
+enum { DIV4_I, DIV4_SH, DIV4_B, DIV4_P, DIV4_M1, DIV4_NR };
+
+#define DIV4(_str, _reg, _bit, _mask, _flags) \
+  SH_CLK_DIV4(_str, &pll_clk, _reg, _bit, _mask, _flags)
+
+struct clk div4_clks[DIV4_NR] = {
+	[DIV4_I] = DIV4("cpu_clk", FRQCRA, 20, 0x2f7d, CLK_ENABLE_ON_INIT),
+	[DIV4_SH] = DIV4("shyway_clk", FRQCRA, 12, 0x2f7c, CLK_ENABLE_ON_INIT),
+	[DIV4_B] = DIV4("bus_clk", FRQCRA, 8, 0x2f7c, CLK_ENABLE_ON_INIT),
+	[DIV4_P] = DIV4("peripheral_clk", FRQCRA, 0, 0x2f7c, 0),
+	[DIV4_M1] = DIV4("vpu_clk", FRQCRB, 4, 0x2f7c, 0),
+};
+
+struct clk div6_clks[] = {
+	SH_CLK_DIV6("video_clk", &div3_clk, VCLKCR, 0),
+	SH_CLK_DIV6("fsia_clk", &div3_clk, FCLKACR, 0),
+	SH_CLK_DIV6("fsib_clk", &div3_clk, FCLKBCR, 0),
+	SH_CLK_DIV6("irda_clk", &div3_clk, IRDACLKCR, 0),
+	SH_CLK_DIV6("spu_clk", &div3_clk, SPUCLKCR, 0),
+};
+
+#define MSTP(_str, _parent, _reg, _bit, _force_on, _need_cpg, _need_ram) \
+  SH_CLK_MSTP32(_str, -1, _parent, _reg, _bit, _force_on * CLK_ENABLE_ON_INIT)
+
+static struct clk mstp_clks[] = {
+	MSTP("tlb0", &div4_clks[DIV4_I], MSTPCR0, 31, 1, 1, 0),
+	MSTP("ic0", &div4_clks[DIV4_I], MSTPCR0, 30, 1, 1, 0),
+	MSTP("oc0", &div4_clks[DIV4_I], MSTPCR0, 29, 1, 1, 0),
+	MSTP("rs0", &div4_clks[DIV4_B], MSTPCR0, 28, 1, 1, 0),
+	MSTP("ilmem0", &div4_clks[DIV4_I], MSTPCR0, 27, 1, 1, 0),
+	MSTP("l2c0", &div4_clks[DIV4_SH], MSTPCR0, 26, 1, 1, 0),
+	MSTP("fpu0", &div4_clks[DIV4_I], MSTPCR0, 24, 1, 1, 0),
+	MSTP("intc0", &div4_clks[DIV4_P], MSTPCR0, 22, 1, 1, 0),
+	MSTP("dmac0", &div4_clks[DIV4_B], MSTPCR0, 21, 0, 1, 1),
+	MSTP("sh0", &div4_clks[DIV4_SH], MSTPCR0, 20, 0, 1, 0),
+	MSTP("hudi0", &div4_clks[DIV4_P], MSTPCR0, 19, 0, 1, 0),
+	MSTP("ubc0", &div4_clks[DIV4_I], MSTPCR0, 17, 0, 1, 0),
+	MSTP("tmu0", &div4_clks[DIV4_P], MSTPCR0, 15, 0, 1, 0),
+	MSTP("cmt0", &r_clk, MSTPCR0, 14, 0, 0, 0),
+	MSTP("rwdt0", &r_clk, MSTPCR0, 13, 0, 0, 0),
+	MSTP("dmac1", &div4_clks[DIV4_B], MSTPCR0, 12, 0, 1, 1),
+	MSTP("tmu1", &div4_clks[DIV4_P], MSTPCR0, 10, 0, 1, 0),
+	MSTP("scif0", &div4_clks[DIV4_P], MSTPCR0, 9, 0, 1, 0),
+	MSTP("scif1", &div4_clks[DIV4_P], MSTPCR0, 8, 0, 1, 0),
+	MSTP("scif2", &div4_clks[DIV4_P], MSTPCR0, 7, 0, 1, 0),
+	MSTP("scif3", &div4_clks[DIV4_B], MSTPCR0, 6, 0, 1, 0),
+	MSTP("scif4", &div4_clks[DIV4_B], MSTPCR0, 5, 0, 1, 0),
+	MSTP("scif5", &div4_clks[DIV4_B], MSTPCR0, 4, 0, 1, 0),
+	MSTP("msiof0", &div4_clks[DIV4_B], MSTPCR0, 2, 0, 1, 0),
+	MSTP("msiof1", &div4_clks[DIV4_B], MSTPCR0, 1, 0, 1, 0),
+
+	MSTP("keysc0", &r_clk, MSTPCR1, 12, 0, 0, 0),
+	MSTP("rtc0", &r_clk, MSTPCR1, 11, 0, 0, 0),
+	MSTP("i2c0", &div4_clks[DIV4_P], MSTPCR1, 9, 0, 1, 0),
+	MSTP("i2c1", &div4_clks[DIV4_P], MSTPCR1, 8, 0, 1, 0),
+
+	MSTP("mmc0", &div4_clks[DIV4_B], MSTPCR2, 29, 0, 1, 0),
+	MSTP("eth0", &div4_clks[DIV4_B], MSTPCR2, 28, 0, 1, 0),
+	MSTP("atapi0", &div4_clks[DIV4_B], MSTPCR2, 26, 0, 1, 0),
+	MSTP("tpu0", &div4_clks[DIV4_B], MSTPCR2, 25, 0, 1, 0),
+	MSTP("irda0", &div4_clks[DIV4_P], MSTPCR2, 24, 0, 1, 0),
+	MSTP("tsif0", &div4_clks[DIV4_B], MSTPCR2, 22, 0, 1, 0),
+	MSTP("usb1", &div4_clks[DIV4_B], MSTPCR2, 21, 0, 1, 1),
+	MSTP("usb0", &div4_clks[DIV4_B], MSTPCR2, 20, 0, 1, 1),
+	MSTP("2dg0", &div4_clks[DIV4_B], MSTPCR2, 19, 0, 1, 1),
+	MSTP("sdhi0", &div4_clks[DIV4_B], MSTPCR2, 18, 0, 1, 0),
+	MSTP("sdhi1", &div4_clks[DIV4_B], MSTPCR2, 17, 0, 1, 0),
+	MSTP("veu1", &div4_clks[DIV4_B], MSTPCR2, 15, 1, 1, 1),
+	MSTP("ceu1", &div4_clks[DIV4_B], MSTPCR2, 13, 0, 1, 1),
+	MSTP("beu1", &div4_clks[DIV4_B], MSTPCR2, 12, 0, 1, 1),
+	MSTP("2ddmac0", &div4_clks[DIV4_SH], MSTPCR2, 10, 0, 1, 1),
+	MSTP("spu0", &div4_clks[DIV4_B], MSTPCR2, 9, 0, 1, 0),
+	MSTP("jpu0", &div4_clks[DIV4_B], MSTPCR2, 6, 1, 1, 1),
+	MSTP("vou0", &div4_clks[DIV4_B], MSTPCR2, 5, 0, 1, 1),
+	MSTP("beu0", &div4_clks[DIV4_B], MSTPCR2, 4, 0, 1, 1),
+	MSTP("ceu0", &div4_clks[DIV4_B], MSTPCR2, 3, 0, 1, 1),
+	MSTP("veu0", &div4_clks[DIV4_B], MSTPCR2, 2, 1, 1, 1),
+	MSTP("vpu0", &div4_clks[DIV4_B], MSTPCR2, 1, 1, 1, 1),
+	MSTP("lcdc0", &div4_clks[DIV4_B], MSTPCR2, 0, 0, 1, 1),
+};
+
+int __init arch_clk_init(void)
+{
+	int k, ret = 0;
+
+	/* autodetect extal or fll configuration */
+	if (__raw_readl(PLLCR) & 0x1000)
+		pll_clk.parent = &fll_clk;
+	else
+		pll_clk.parent = &extal_clk;
+
+	for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
+		ret = clk_register(main_clks[k]);
+
+	if (!ret)
+		ret = sh_clk_div4_register(div4_clks, DIV4_NR, &div4_table);
+
+	if (!ret)
+		ret = sh_clk_div6_register(div6_clks, ARRAY_SIZE(div6_clks));
+
+	if (!ret)
+		ret = sh_clk_mstp32_register(mstp_clks, ARRAY_SIZE(mstp_clks));
+
+	return ret;
+}
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7763.c b/arch/sh/kernel/cpu/sh4a/clock-sh7763.c
index 3177d0d1e06d..370cd47642ef 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7763.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7763.c
@@ -29,33 +29,28 @@ static struct clk_ops sh7763_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> 4) & 0x07);
-	clk->rate = clk->parent->rate / p0fc_divisors[idx];
+	return clk->parent->rate / p0fc_divisors[idx];
 }
 
 static struct clk_ops sh7763_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> 16) & 0x07);
-	clk->rate = clk->parent->rate / bfc_divisors[idx];
+	return clk->parent->rate / bfc_divisors[idx];
 }
 
 static struct clk_ops sh7763_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
-{
-	clk->rate = clk->parent->rate;
-}
-
 static struct clk_ops sh7763_cpu_clk_ops = {
-	.recalc		= cpu_clk_recalc,
+	.recalc		= followparent_recalc,
 };
 
 static struct clk_ops *sh7763_clk_ops[] = {
@@ -71,10 +66,10 @@ void __init arch_init_clk_ops(struct clk_ops **ops, int idx)
 		*ops = sh7763_clk_ops[idx];
 }
 
-static void shyway_clk_recalc(struct clk *clk)
+static unsigned long shyway_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> 20) & 0x07);
-	clk->rate = clk->parent->rate / cfc_divisors[idx];
+	return clk->parent->rate / cfc_divisors[idx];
 }
 
 static struct clk_ops sh7763_shyway_clk_ops = {
@@ -83,7 +78,7 @@ static struct clk_ops sh7763_shyway_clk_ops = {
 
 static struct clk sh7763_shyway_clk = {
 	.name		= "shyway_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
+	.flags		= CLK_ENABLE_ON_INIT,
 	.ops		= &sh7763_shyway_clk_ops,
 };
 
@@ -95,31 +90,22 @@ static struct clk *sh7763_onchip_clocks[] = {
 	&sh7763_shyway_clk,
 };
 
-static int __init sh7763_clk_init(void)
+int __init arch_clk_init(void)
 {
-	struct clk *clk = clk_get(NULL, "master_clk");
-	int i;
+	struct clk *clk;
+	int i, ret = 0;
 
+	cpg_clk_init();
+
+	clk = clk_get(NULL, "master_clk");
 	for (i = 0; i < ARRAY_SIZE(sh7763_onchip_clocks); i++) {
 		struct clk *clkp = sh7763_onchip_clocks[i];
 
 		clkp->parent = clk;
-		clk_register(clkp);
-		clk_enable(clkp);
+		ret |= clk_register(clkp);
 	}
 
-	/*
-	 * Now that we have the rest of the clocks registered, we need to
-	 * force the parent clock to propagate so that these clocks will
-	 * automatically figure out their rate. We cheat by handing the
-	 * parent clock its current rate and forcing child propagation.
-	 */
-	clk_set_rate(clk, clk_get_rate(clk));
-
 	clk_put(clk);
 
-	return 0;
+	return ret;
 }
-
-arch_initcall(sh7763_clk_init);
-
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7770.c b/arch/sh/kernel/cpu/sh4a/clock-sh7770.c
index 8e236062c721..e0b896769205 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7770.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7770.c
@@ -28,30 +28,30 @@ static struct clk_ops sh7770_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> 28) & 0x000f);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7770_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inl(FRQCR) & 0x000f);
-	clk->rate = clk->parent->rate / bfc_divisors[idx];
+	return clk->parent->rate / bfc_divisors[idx];
 }
 
 static struct clk_ops sh7770_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> 24) & 0x000f);
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh7770_cpu_clk_ops = {
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7780.c b/arch/sh/kernel/cpu/sh4a/clock-sh7780.c
index 01f3da619d3d..a249d823578e 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7780.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7780.c
@@ -29,30 +29,30 @@ static struct clk_ops sh7780_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inl(FRQCR) & 0x0003);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7780_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> 16) & 0x0007);
-	clk->rate = clk->parent->rate / bfc_divisors[idx];
+	return clk->parent->rate / bfc_divisors[idx];
 }
 
 static struct clk_ops sh7780_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> 24) & 0x0001);
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh7780_cpu_clk_ops = {
@@ -72,10 +72,10 @@ void __init arch_init_clk_ops(struct clk_ops **ops, int idx)
 		*ops = sh7780_clk_ops[idx];
 }
 
-static void shyway_clk_recalc(struct clk *clk)
+static unsigned long shyway_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> 20) & 0x0007);
-	clk->rate = clk->parent->rate / cfc_divisors[idx];
+	return clk->parent->rate / cfc_divisors[idx];
 }
 
 static struct clk_ops sh7780_shyway_clk_ops = {
@@ -84,7 +84,7 @@ static struct clk_ops sh7780_shyway_clk_ops = {
 
 static struct clk sh7780_shyway_clk = {
 	.name		= "shyway_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
+	.flags		= CLK_ENABLE_ON_INIT,
 	.ops		= &sh7780_shyway_clk_ops,
 };
 
@@ -96,31 +96,22 @@ static struct clk *sh7780_onchip_clocks[] = {
 	&sh7780_shyway_clk,
 };
 
-static int __init sh7780_clk_init(void)
+int __init arch_clk_init(void)
 {
-	struct clk *clk = clk_get(NULL, "master_clk");
-	int i;
+	struct clk *clk;
+	int i, ret = 0;
 
+	cpg_clk_init();
+
+	clk = clk_get(NULL, "master_clk");
 	for (i = 0; i < ARRAY_SIZE(sh7780_onchip_clocks); i++) {
 		struct clk *clkp = sh7780_onchip_clocks[i];
 
 		clkp->parent = clk;
-		clk_register(clkp);
-		clk_enable(clkp);
+		ret |= clk_register(clkp);
 	}
 
-	/*
-	 * Now that we have the rest of the clocks registered, we need to
-	 * force the parent clock to propagate so that these clocks will
-	 * automatically figure out their rate. We cheat by handing the
-	 * parent clock its current rate and forcing child propagation.
-	 */
-	clk_set_rate(clk, clk_get_rate(clk));
-
 	clk_put(clk);
 
-	return 0;
+	return ret;
 }
-
-arch_initcall(sh7780_clk_init);
-
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
index 27fa81bef6a0..73abfbf2f16d 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
@@ -3,7 +3,7 @@
  *
  * SH7785 support for the clock framework
  *
- *  Copyright (C) 2007  Paul Mundt
+ *  Copyright (C) 2007 - 2009  Paul Mundt
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
@@ -11,152 +11,116 @@
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/cpufreq.h>
 #include <asm/clock.h>
 #include <asm/freq.h>
-#include <asm/io.h>
-
-static int ifc_divisors[] = { 1, 2, 4, 6 };
-static int ufc_divisors[] = { 1, 1, 4, 6 };
-static int sfc_divisors[] = { 1, 1, 4, 6 };
-static int bfc_divisors[] = { 1, 1, 1, 1, 1, 12, 16, 18,
-			     24, 32, 36, 48, 1, 1, 1, 1 };
-static int mfc_divisors[] = { 1, 1, 4, 6 };
-static int pfc_divisors[] = { 1, 1, 1, 1, 1, 1, 1, 18,
-			      24, 32, 36, 48, 1, 1, 1, 1 };
-
-static void master_clk_init(struct clk *clk)
-{
-	clk->rate *= pfc_divisors[ctrl_inl(FRQMR1) & 0x000f];
-}
-
-static struct clk_ops sh7785_master_clk_ops = {
-	.init		= master_clk_init,
-};
-
-static void module_clk_recalc(struct clk *clk)
-{
-	int idx = (ctrl_inl(FRQMR1) & 0x000f);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
-}
-
-static struct clk_ops sh7785_module_clk_ops = {
-	.recalc		= module_clk_recalc,
-};
-
-static void bus_clk_recalc(struct clk *clk)
-{
-	int idx = ((ctrl_inl(FRQMR1) >> 16) & 0x000f);
-	clk->rate = clk->parent->rate / bfc_divisors[idx];
-}
-
-static struct clk_ops sh7785_bus_clk_ops = {
-	.recalc		= bus_clk_recalc,
-};
-
-static void cpu_clk_recalc(struct clk *clk)
-{
-	int idx = ((ctrl_inl(FRQMR1) >> 28) & 0x0003);
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
-}
-
-static struct clk_ops sh7785_cpu_clk_ops = {
-	.recalc		= cpu_clk_recalc,
-};
-
-static struct clk_ops *sh7785_clk_ops[] = {
-	&sh7785_master_clk_ops,
-	&sh7785_module_clk_ops,
-	&sh7785_bus_clk_ops,
-	&sh7785_cpu_clk_ops,
-};
-
-void __init arch_init_clk_ops(struct clk_ops **ops, int idx)
-{
-	if (idx < ARRAY_SIZE(sh7785_clk_ops))
-		*ops = sh7785_clk_ops[idx];
-}
-
-static void shyway_clk_recalc(struct clk *clk)
-{
-	int idx = ((ctrl_inl(FRQMR1) >> 20) & 0x0003);
-	clk->rate = clk->parent->rate / sfc_divisors[idx];
-}
-
-static struct clk_ops sh7785_shyway_clk_ops = {
-	.recalc		= shyway_clk_recalc,
-};
-
-static struct clk sh7785_shyway_clk = {
-	.name		= "shyway_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
-	.ops		= &sh7785_shyway_clk_ops,
-};
-
-static void ddr_clk_recalc(struct clk *clk)
-{
-	int idx = ((ctrl_inl(FRQMR1) >> 12) & 0x0003);
-	clk->rate = clk->parent->rate / mfc_divisors[idx];
-}
-
-static struct clk_ops sh7785_ddr_clk_ops = {
-	.recalc		= ddr_clk_recalc,
-};
-
-static struct clk sh7785_ddr_clk = {
-	.name		= "ddr_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
-	.ops		= &sh7785_ddr_clk_ops,
-};
-
-static void ram_clk_recalc(struct clk *clk)
-{
-	int idx = ((ctrl_inl(FRQMR1) >> 24) & 0x0003);
-	clk->rate = clk->parent->rate / ufc_divisors[idx];
-}
-
-static struct clk_ops sh7785_ram_clk_ops = {
-	.recalc		= ram_clk_recalc,
-};
-
-static struct clk sh7785_ram_clk = {
-	.name		= "ram_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
-	.ops		= &sh7785_ram_clk_ops,
-};
+#include <cpu/sh7785.h>
 
 /*
- * Additional SH7785-specific on-chip clocks that aren't already part of the
- * clock framework
+ * Default rate for the root input clock, reset this with clk_set_rate()
+ * from the platform code.
  */
-static struct clk *sh7785_onchip_clocks[] = {
-	&sh7785_shyway_clk,
-	&sh7785_ddr_clk,
-	&sh7785_ram_clk,
+static struct clk extal_clk = {
+	.name		= "extal",
+	.id		= -1,
+	.rate		= 33333333,
 };
 
-static int __init sh7785_clk_init(void)
+static unsigned long pll_recalc(struct clk *clk)
 {
-	struct clk *clk = clk_get(NULL, "master_clk");
-	int i;
+	int multiplier;
 
-	for (i = 0; i < ARRAY_SIZE(sh7785_onchip_clocks); i++) {
-		struct clk *clkp = sh7785_onchip_clocks[i];
+	multiplier = test_mode_pin(MODE_PIN4) ? 36 : 72;
 
-		clkp->parent = clk;
-		clk_register(clkp);
-		clk_enable(clkp);
-	}
-
-	/*
-	 * Now that we have the rest of the clocks registered, we need to
-	 * force the parent clock to propagate so that these clocks will
-	 * automatically figure out their rate. We cheat by handing the
-	 * parent clock its current rate and forcing child propagation.
-	 */
-	clk_set_rate(clk, clk_get_rate(clk));
-
-	clk_put(clk);
-
-	return 0;
+	return clk->parent->rate * multiplier;
+}
+
+static struct clk_ops pll_clk_ops = {
+	.recalc		= pll_recalc,
+};
+
+static struct clk pll_clk = {
+	.name		= "pll_clk",
+	.id		= -1,
+	.ops		= &pll_clk_ops,
+	.parent		= &extal_clk,
+	.flags		= CLK_ENABLE_ON_INIT,
+};
+
+static struct clk *clks[] = {
+	&extal_clk,
+	&pll_clk,
+};
+
+static unsigned int div2[] = { 1, 2, 4, 6, 8, 12, 16, 18,
+			       24, 32, 36, 48 };
+
+static struct clk_div_mult_table div4_table = {
+	.divisors = div2,
+	.nr_divisors = ARRAY_SIZE(div2),
+};
+
+enum { DIV4_I, DIV4_U, DIV4_SH, DIV4_B, DIV4_DDR, DIV4_GA,
+	DIV4_DU, DIV4_P, DIV4_NR };
+
+#define DIV4(_str, _bit, _mask, _flags) \
+  SH_CLK_DIV4(_str, &pll_clk, FRQMR1, _bit, _mask, _flags)
+
+struct clk div4_clks[DIV4_NR] = {
+	[DIV4_P] = DIV4("peripheral_clk", 0, 0x0f80, 0),
+	[DIV4_DU] = DIV4("du_clk", 4, 0x0ff0, 0),
+	[DIV4_GA] = DIV4("ga_clk", 8, 0x0030, 0),
+	[DIV4_DDR] = DIV4("ddr_clk", 12, 0x000c, CLK_ENABLE_ON_INIT),
+	[DIV4_B] = DIV4("bus_clk", 16, 0x0fe0, CLK_ENABLE_ON_INIT),
+	[DIV4_SH] = DIV4("shyway_clk", 20, 0x000c, CLK_ENABLE_ON_INIT),
+	[DIV4_U] = DIV4("umem_clk", 24, 0x000c, CLK_ENABLE_ON_INIT),
+	[DIV4_I] = DIV4("cpu_clk", 28, 0x000e, CLK_ENABLE_ON_INIT),
+};
+
+#define MSTPCR0		0xffc80030
+#define MSTPCR1		0xffc80034
+
+static struct clk mstp_clks[] = {
+	/* MSTPCR0 */
+	SH_CLK_MSTP32("scif_fck", 5, &div4_clks[DIV4_P], MSTPCR0, 29, 0),
+	SH_CLK_MSTP32("scif_fck", 4, &div4_clks[DIV4_P], MSTPCR0, 28, 0),
+	SH_CLK_MSTP32("scif_fck", 3, &div4_clks[DIV4_P], MSTPCR0, 27, 0),
+	SH_CLK_MSTP32("scif_fck", 2, &div4_clks[DIV4_P], MSTPCR0, 26, 0),
+	SH_CLK_MSTP32("scif_fck", 1, &div4_clks[DIV4_P], MSTPCR0, 25, 0),
+	SH_CLK_MSTP32("scif_fck", 0, &div4_clks[DIV4_P], MSTPCR0, 24, 0),
+	SH_CLK_MSTP32("ssi_fck", 1, &div4_clks[DIV4_P], MSTPCR0, 21, 0),
+	SH_CLK_MSTP32("ssi_fck", 0, &div4_clks[DIV4_P], MSTPCR0, 20, 0),
+	SH_CLK_MSTP32("hac_fck", 1, &div4_clks[DIV4_P], MSTPCR0, 17, 0),
+	SH_CLK_MSTP32("hac_fck", 0, &div4_clks[DIV4_P], MSTPCR0, 16, 0),
+	SH_CLK_MSTP32("mmcif_fck", -1, &div4_clks[DIV4_P], MSTPCR0, 13, 0),
+	SH_CLK_MSTP32("flctl_fck", -1, &div4_clks[DIV4_P], MSTPCR0, 12, 0),
+	SH_CLK_MSTP32("tmu345_fck", -1, &div4_clks[DIV4_P], MSTPCR0, 9, 0),
+	SH_CLK_MSTP32("tmu012_fck", -1, &div4_clks[DIV4_P], MSTPCR0, 8, 0),
+	SH_CLK_MSTP32("siof_fck", -1, &div4_clks[DIV4_P], MSTPCR0, 3, 0),
+	SH_CLK_MSTP32("hspi_fck", -1, &div4_clks[DIV4_P], MSTPCR0, 2, 0),
+
+	/* MSTPCR1 */
+	SH_CLK_MSTP32("hudi_fck", -1, NULL, MSTPCR1, 19, 0),
+	SH_CLK_MSTP32("ubc_fck", -1, NULL, MSTPCR1, 17, 0),
+	SH_CLK_MSTP32("dmac_11_6_fck", -1, NULL, MSTPCR1, 5, 0),
+	SH_CLK_MSTP32("dmac_5_0_fck", -1, NULL, MSTPCR1, 4, 0),
+	SH_CLK_MSTP32("gdta_fck", -1, NULL, MSTPCR1, 0, 0),
+};
+
+int __init arch_clk_init(void)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < ARRAY_SIZE(clks); i++)
+		ret |= clk_register(clks[i]);
+
+	if (!ret)
+		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
+					   &div4_table);
+	if (!ret)
+		ret = sh_clk_mstp32_register(mstp_clks, ARRAY_SIZE(mstp_clks));
+
+	return ret;
 }
-arch_initcall(sh7785_clk_init);
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
index f84a9c134471..a0e8869071ac 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
@@ -36,30 +36,30 @@ static struct clk_ops sh7786_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inl(FRQMR1) & 0x000f);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops sh7786_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQMR1) >> 16) & 0x000f);
-	clk->rate = clk->parent->rate / bfc_divisors[idx];
+	return clk->parent->rate / bfc_divisors[idx];
 }
 
 static struct clk_ops sh7786_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQMR1) >> 28) & 0x0003);
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops sh7786_cpu_clk_ops = {
@@ -79,10 +79,10 @@ void __init arch_init_clk_ops(struct clk_ops **ops, int idx)
 		*ops = sh7786_clk_ops[idx];
 }
 
-static void shyway_clk_recalc(struct clk *clk)
+static unsigned long shyway_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQMR1) >> 20) & 0x0003);
-	clk->rate = clk->parent->rate / sfc_divisors[idx];
+	return clk->parent->rate / sfc_divisors[idx];
 }
 
 static struct clk_ops sh7786_shyway_clk_ops = {
@@ -91,14 +91,14 @@ static struct clk_ops sh7786_shyway_clk_ops = {
 
 static struct clk sh7786_shyway_clk = {
 	.name		= "shyway_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
+	.flags		= CLK_ENABLE_ON_INIT,
 	.ops		= &sh7786_shyway_clk_ops,
 };
 
-static void ddr_clk_recalc(struct clk *clk)
+static unsigned long ddr_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQMR1) >> 12) & 0x0003);
-	clk->rate = clk->parent->rate / mfc_divisors[idx];
+	return clk->parent->rate / mfc_divisors[idx];
 }
 
 static struct clk_ops sh7786_ddr_clk_ops = {
@@ -107,7 +107,7 @@ static struct clk_ops sh7786_ddr_clk_ops = {
 
 static struct clk sh7786_ddr_clk = {
 	.name		= "ddr_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
+	.flags		= CLK_ENABLE_ON_INIT,
 	.ops		= &sh7786_ddr_clk_ops,
 };
 
@@ -120,29 +120,22 @@ static struct clk *sh7786_onchip_clocks[] = {
 	&sh7786_ddr_clk,
 };
 
-static int __init sh7786_clk_init(void)
+int __init arch_clk_init(void)
 {
-	struct clk *clk = clk_get(NULL, "master_clk");
-	int i;
+	struct clk *clk;
+	int i, ret = 0;
 
+	cpg_clk_init();
+
+	clk = clk_get(NULL, "master_clk");
 	for (i = 0; i < ARRAY_SIZE(sh7786_onchip_clocks); i++) {
 		struct clk *clkp = sh7786_onchip_clocks[i];
 
 		clkp->parent = clk;
-		clk_register(clkp);
-		clk_enable(clkp);
+		ret |= clk_register(clkp);
 	}
 
-	/*
-	 * Now that we have the rest of the clocks registered, we need to
-	 * force the parent clock to propagate so that these clocks will
-	 * automatically figure out their rate. We cheat by handing the
-	 * parent clock its current rate and forcing child propagation.
-	 */
-	clk_set_rate(clk, clk_get_rate(clk));
-
 	clk_put(clk);
 
-	return 0;
+	return ret;
 }
-arch_initcall(sh7786_clk_init);
diff --git a/arch/sh/kernel/cpu/sh4a/clock-shx3.c b/arch/sh/kernel/cpu/sh4a/clock-shx3.c
index c630b29e06a8..23c27d32d982 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-shx3.c
@@ -40,30 +40,30 @@ static struct clk_ops shx3_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> PFC_POS) & PFC_MSK);
-	clk->rate = clk->parent->rate / pfc_divisors[idx];
+	return clk->parent->rate / pfc_divisors[idx];
 }
 
 static struct clk_ops shx3_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> BFC_POS) & BFC_MSK);
-	clk->rate = clk->parent->rate / bfc_divisors[idx];
+	return clk->parent->rate / bfc_divisors[idx];
 }
 
 static struct clk_ops shx3_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> IFC_POS) & IFC_MSK);
-	clk->rate = clk->parent->rate / ifc_divisors[idx];
+	return clk->parent->rate / ifc_divisors[idx];
 }
 
 static struct clk_ops shx3_cpu_clk_ops = {
@@ -83,10 +83,10 @@ void __init arch_init_clk_ops(struct clk_ops **ops, int idx)
 		*ops = shx3_clk_ops[idx];
 }
 
-static void shyway_clk_recalc(struct clk *clk)
+static unsigned long shyway_clk_recalc(struct clk *clk)
 {
 	int idx = ((ctrl_inl(FRQCR) >> CFC_POS) & CFC_MSK);
-	clk->rate = clk->parent->rate / cfc_divisors[idx];
+	return clk->parent->rate / cfc_divisors[idx];
 }
 
 static struct clk_ops shx3_shyway_clk_ops = {
@@ -95,7 +95,7 @@ static struct clk_ops shx3_shyway_clk_ops = {
 
 static struct clk shx3_shyway_clk = {
 	.name		= "shyway_clk",
-	.flags		= CLK_ALWAYS_ENABLED,
+	.flags		= CLK_ENABLE_ON_INIT,
 	.ops		= &shx3_shyway_clk_ops,
 };
 
@@ -107,29 +107,22 @@ static struct clk *shx3_onchip_clocks[] = {
 	&shx3_shyway_clk,
 };
 
-static int __init shx3_clk_init(void)
+int __init arch_clk_init(void)
 {
-	struct clk *clk = clk_get(NULL, "master_clk");
-	int i;
+	struct clk *clk;
+	int i, ret = 0;
 
+	cpg_clk_init();
+
+	clk = clk_get(NULL, "master_clk");
 	for (i = 0; i < ARRAY_SIZE(shx3_onchip_clocks); i++) {
 		struct clk *clkp = shx3_onchip_clocks[i];
 
 		clkp->parent = clk;
-		clk_register(clkp);
-		clk_enable(clkp);
+		ret |= clk_register(clkp);
 	}
 
-	/*
-	 * Now that we have the rest of the clocks registered, we need to
-	 * force the parent clock to propagate so that these clocks will
-	 * automatically figure out their rate. We cheat by handing the
-	 * parent clock its current rate and forcing child propagation.
-	 */
-	clk_set_rate(clk, clk_get_rate(clk));
-
 	clk_put(clk);
 
-	return 0;
+	return ret;
 }
-arch_initcall(shx3_clk_init);
diff --git a/arch/sh/kernel/cpu/sh4a/pinmux-sh7724.c b/arch/sh/kernel/cpu/sh4a/pinmux-sh7724.c
new file mode 100644
index 000000000000..1af0f9586379
--- /dev/null
+++ b/arch/sh/kernel/cpu/sh4a/pinmux-sh7724.c
@@ -0,0 +1,2230 @@
+/*
+ * SH7724 Pinmux
+ *
+ * Copyright (C) 2009 Renesas Solutions Corp.
+ *
+ * Kuninori Morimoto <morimoto.kuninori@renesas.com>
+ *
+ * Based on SH7723 Pinmux
+ *  Copyright (C) 2008  Magnus Damm
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <cpu/sh7724.h>
+
+enum {
+	PINMUX_RESERVED = 0,
+
+	PINMUX_DATA_BEGIN,
+	PTA7_DATA, PTA6_DATA, PTA5_DATA, PTA4_DATA,
+	PTA3_DATA, PTA2_DATA, PTA1_DATA, PTA0_DATA,
+	PTB7_DATA, PTB6_DATA, PTB5_DATA, PTB4_DATA,
+	PTB3_DATA, PTB2_DATA, PTB1_DATA, PTB0_DATA,
+	PTC7_DATA, PTC6_DATA, PTC5_DATA, PTC4_DATA,
+	PTC3_DATA, PTC2_DATA, PTC1_DATA, PTC0_DATA,
+	PTD7_DATA, PTD6_DATA, PTD5_DATA, PTD4_DATA,
+	PTD3_DATA, PTD2_DATA, PTD1_DATA, PTD0_DATA,
+	PTE7_DATA, PTE6_DATA, PTE5_DATA, PTE4_DATA,
+	PTE3_DATA, PTE2_DATA, PTE1_DATA, PTE0_DATA,
+	PTF7_DATA, PTF6_DATA, PTF5_DATA, PTF4_DATA,
+	PTF3_DATA, PTF2_DATA, PTF1_DATA, PTF0_DATA,
+			      PTG5_DATA, PTG4_DATA,
+	PTG3_DATA, PTG2_DATA, PTG1_DATA, PTG0_DATA,
+	PTH7_DATA, PTH6_DATA, PTH5_DATA, PTH4_DATA,
+	PTH3_DATA, PTH2_DATA, PTH1_DATA, PTH0_DATA,
+	PTJ7_DATA, PTJ6_DATA, PTJ5_DATA,
+	PTJ3_DATA, PTJ2_DATA, PTJ1_DATA, PTJ0_DATA,
+	PTK7_DATA, PTK6_DATA, PTK5_DATA, PTK4_DATA,
+	PTK3_DATA, PTK2_DATA, PTK1_DATA, PTK0_DATA,
+	PTL7_DATA, PTL6_DATA, PTL5_DATA, PTL4_DATA,
+	PTL3_DATA, PTL2_DATA, PTL1_DATA, PTL0_DATA,
+	PTM7_DATA, PTM6_DATA, PTM5_DATA, PTM4_DATA,
+	PTM3_DATA, PTM2_DATA, PTM1_DATA, PTM0_DATA,
+	PTN7_DATA, PTN6_DATA, PTN5_DATA, PTN4_DATA,
+	PTN3_DATA, PTN2_DATA, PTN1_DATA, PTN0_DATA,
+	PTQ7_DATA, PTQ6_DATA, PTQ5_DATA, PTQ4_DATA,
+	PTQ3_DATA, PTQ2_DATA, PTQ1_DATA, PTQ0_DATA,
+	PTR7_DATA, PTR6_DATA, PTR5_DATA, PTR4_DATA,
+	PTR3_DATA, PTR2_DATA, PTR1_DATA, PTR0_DATA,
+		   PTS6_DATA, PTS5_DATA, PTS4_DATA,
+	PTS3_DATA, PTS2_DATA, PTS1_DATA, PTS0_DATA,
+	PTT7_DATA, PTT6_DATA, PTT5_DATA, PTT4_DATA,
+	PTT3_DATA, PTT2_DATA, PTT1_DATA, PTT0_DATA,
+	PTU7_DATA, PTU6_DATA, PTU5_DATA, PTU4_DATA,
+	PTU3_DATA, PTU2_DATA, PTU1_DATA, PTU0_DATA,
+	PTV7_DATA, PTV6_DATA, PTV5_DATA, PTV4_DATA,
+	PTV3_DATA, PTV2_DATA, PTV1_DATA, PTV0_DATA,
+	PTW7_DATA, PTW6_DATA, PTW5_DATA, PTW4_DATA,
+	PTW3_DATA, PTW2_DATA, PTW1_DATA, PTW0_DATA,
+	PTX7_DATA, PTX6_DATA, PTX5_DATA, PTX4_DATA,
+	PTX3_DATA, PTX2_DATA, PTX1_DATA, PTX0_DATA,
+	PTY7_DATA, PTY6_DATA, PTY5_DATA, PTY4_DATA,
+	PTY3_DATA, PTY2_DATA, PTY1_DATA, PTY0_DATA,
+	PTZ7_DATA, PTZ6_DATA, PTZ5_DATA, PTZ4_DATA,
+	PTZ3_DATA, PTZ2_DATA, PTZ1_DATA, PTZ0_DATA,
+	PINMUX_DATA_END,
+
+	PINMUX_INPUT_BEGIN,
+	PTA7_IN, PTA6_IN, PTA5_IN, PTA4_IN,
+	PTA3_IN, PTA2_IN, PTA1_IN, PTA0_IN,
+	PTB7_IN, PTB6_IN, PTB5_IN, PTB4_IN,
+	PTB3_IN, PTB2_IN, PTB1_IN, PTB0_IN,
+	PTC7_IN, PTC6_IN, PTC5_IN, PTC4_IN,
+	PTC3_IN, PTC2_IN, PTC1_IN, PTC0_IN,
+	PTD7_IN, PTD6_IN, PTD5_IN, PTD4_IN,
+	PTD3_IN, PTD2_IN, PTD1_IN, PTD0_IN,
+	PTE7_IN, PTE6_IN, PTE5_IN, PTE4_IN,
+	PTE3_IN, PTE2_IN, PTE1_IN, PTE0_IN,
+	PTF7_IN, PTF6_IN, PTF5_IN, PTF4_IN,
+	PTF3_IN, PTF2_IN, PTF1_IN, PTF0_IN,
+	PTH7_IN, PTH6_IN, PTH5_IN, PTH4_IN,
+	PTH3_IN, PTH2_IN, PTH1_IN, PTH0_IN,
+	PTJ3_IN, PTJ2_IN, PTJ1_IN, PTJ0_IN,
+	PTK7_IN, PTK6_IN, PTK5_IN, PTK4_IN,
+	PTK3_IN, PTK2_IN, PTK1_IN, PTK0_IN,
+	PTL7_IN, PTL6_IN, PTL5_IN, PTL4_IN,
+	PTL3_IN, PTL2_IN, PTL1_IN, PTL0_IN,
+	PTM7_IN, PTM6_IN, PTM5_IN, PTM4_IN,
+	PTM3_IN, PTM2_IN, PTM1_IN, PTM0_IN,
+	PTN7_IN, PTN6_IN, PTN5_IN, PTN4_IN,
+	PTN3_IN, PTN2_IN, PTN1_IN, PTN0_IN,
+	PTQ7_IN, PTQ6_IN, PTQ5_IN, PTQ4_IN,
+	PTQ3_IN, PTQ2_IN, PTQ1_IN, PTQ0_IN,
+	PTR7_IN, PTR6_IN, PTR5_IN, PTR4_IN,
+	PTR3_IN, PTR2_IN, PTR1_IN, PTR0_IN,
+		 PTS6_IN, PTS5_IN, PTS4_IN,
+	PTS3_IN, PTS2_IN, PTS1_IN, PTS0_IN,
+	PTT7_IN, PTT6_IN, PTT5_IN, PTT4_IN,
+	PTT3_IN, PTT2_IN, PTT1_IN, PTT0_IN,
+	PTU7_IN, PTU6_IN, PTU5_IN, PTU4_IN,
+	PTU3_IN, PTU2_IN, PTU1_IN, PTU0_IN,
+	PTV7_IN, PTV6_IN, PTV5_IN, PTV4_IN,
+	PTV3_IN, PTV2_IN, PTV1_IN, PTV0_IN,
+	PTW7_IN, PTW6_IN, PTW5_IN, PTW4_IN,
+	PTW3_IN, PTW2_IN, PTW1_IN, PTW0_IN,
+	PTX7_IN, PTX6_IN, PTX5_IN, PTX4_IN,
+	PTX3_IN, PTX2_IN, PTX1_IN, PTX0_IN,
+	PTY7_IN, PTY6_IN, PTY5_IN, PTY4_IN,
+	PTY3_IN, PTY2_IN, PTY1_IN, PTY0_IN,
+	PTZ7_IN, PTZ6_IN, PTZ5_IN, PTZ4_IN,
+	PTZ3_IN, PTZ2_IN, PTZ1_IN, PTZ0_IN,
+	PINMUX_INPUT_END,
+
+	PINMUX_INPUT_PULLUP_BEGIN,
+	PTA7_IN_PU, PTA6_IN_PU, PTA5_IN_PU, PTA4_IN_PU,
+	PTA3_IN_PU, PTA2_IN_PU, PTA1_IN_PU, PTA0_IN_PU,
+	PTB7_IN_PU, PTB6_IN_PU, PTB5_IN_PU, PTB4_IN_PU,
+	PTB3_IN_PU, PTB2_IN_PU, PTB1_IN_PU, PTB0_IN_PU,
+	PTC7_IN_PU, PTC6_IN_PU, PTC5_IN_PU, PTC4_IN_PU,
+	PTC3_IN_PU, PTC2_IN_PU, PTC1_IN_PU, PTC0_IN_PU,
+	PTD7_IN_PU, PTD6_IN_PU, PTD5_IN_PU, PTD4_IN_PU,
+	PTD3_IN_PU, PTD2_IN_PU, PTD1_IN_PU, PTD0_IN_PU,
+	PTE7_IN_PU, PTE6_IN_PU, PTE5_IN_PU, PTE4_IN_PU,
+	PTE3_IN_PU, PTE2_IN_PU, PTE1_IN_PU, PTE0_IN_PU,
+	PTF7_IN_PU, PTF6_IN_PU, PTF5_IN_PU, PTF4_IN_PU,
+	PTF3_IN_PU, PTF2_IN_PU, PTF1_IN_PU, PTF0_IN_PU,
+	PTH7_IN_PU, PTH6_IN_PU, PTH5_IN_PU, PTH4_IN_PU,
+	PTH3_IN_PU, PTH2_IN_PU, PTH1_IN_PU, PTH0_IN_PU,
+	PTJ3_IN_PU, PTJ2_IN_PU, PTJ1_IN_PU, PTJ0_IN_PU,
+	PTK7_IN_PU, PTK6_IN_PU, PTK5_IN_PU, PTK4_IN_PU,
+	PTK3_IN_PU, PTK2_IN_PU, PTK1_IN_PU, PTK0_IN_PU,
+	PTL7_IN_PU, PTL6_IN_PU, PTL5_IN_PU, PTL4_IN_PU,
+	PTL3_IN_PU, PTL2_IN_PU, PTL1_IN_PU, PTL0_IN_PU,
+	PTM7_IN_PU, PTM6_IN_PU, PTM5_IN_PU, PTM4_IN_PU,
+	PTM3_IN_PU, PTM2_IN_PU, PTM1_IN_PU, PTM0_IN_PU,
+	PTN7_IN_PU, PTN6_IN_PU, PTN5_IN_PU, PTN4_IN_PU,
+	PTN3_IN_PU, PTN2_IN_PU, PTN1_IN_PU, PTN0_IN_PU,
+	PTQ7_IN_PU, PTQ6_IN_PU, PTQ5_IN_PU, PTQ4_IN_PU,
+	PTQ3_IN_PU, PTQ2_IN_PU, PTQ1_IN_PU, PTQ0_IN_PU,
+	PTR7_IN_PU, PTR6_IN_PU, PTR5_IN_PU, PTR4_IN_PU,
+	PTR3_IN_PU, PTR2_IN_PU, PTR1_IN_PU, PTR0_IN_PU,
+		    PTS6_IN_PU, PTS5_IN_PU, PTS4_IN_PU,
+	PTS3_IN_PU, PTS2_IN_PU, PTS1_IN_PU, PTS0_IN_PU,
+	PTT7_IN_PU, PTT6_IN_PU, PTT5_IN_PU, PTT4_IN_PU,
+	PTT3_IN_PU, PTT2_IN_PU, PTT1_IN_PU, PTT0_IN_PU,
+	PTU7_IN_PU, PTU6_IN_PU, PTU5_IN_PU, PTU4_IN_PU,
+	PTU3_IN_PU, PTU2_IN_PU, PTU1_IN_PU, PTU0_IN_PU,
+	PTV7_IN_PU, PTV6_IN_PU, PTV5_IN_PU, PTV4_IN_PU,
+	PTV3_IN_PU, PTV2_IN_PU, PTV1_IN_PU, PTV0_IN_PU,
+	PTW7_IN_PU, PTW6_IN_PU, PTW5_IN_PU, PTW4_IN_PU,
+	PTW3_IN_PU, PTW2_IN_PU, PTW1_IN_PU, PTW0_IN_PU,
+	PTX7_IN_PU, PTX6_IN_PU, PTX5_IN_PU, PTX4_IN_PU,
+	PTX3_IN_PU, PTX2_IN_PU, PTX1_IN_PU, PTX0_IN_PU,
+	PTY7_IN_PU, PTY6_IN_PU, PTY5_IN_PU, PTY4_IN_PU,
+	PTY3_IN_PU, PTY2_IN_PU, PTY1_IN_PU, PTY0_IN_PU,
+	PTZ7_IN_PU, PTZ6_IN_PU, PTZ5_IN_PU, PTZ4_IN_PU,
+	PTZ3_IN_PU, PTZ2_IN_PU, PTZ1_IN_PU, PTZ0_IN_PU,
+	PINMUX_INPUT_PULLUP_END,
+
+	PINMUX_OUTPUT_BEGIN,
+	PTA7_OUT, PTA6_OUT, PTA5_OUT, PTA4_OUT,
+	PTA3_OUT, PTA2_OUT, PTA1_OUT, PTA0_OUT,
+	PTB7_OUT, PTB6_OUT, PTB5_OUT, PTB4_OUT,
+	PTB3_OUT, PTB2_OUT, PTB1_OUT, PTB0_OUT,
+	PTC7_OUT, PTC6_OUT, PTC5_OUT, PTC4_OUT,
+	PTC3_OUT, PTC2_OUT, PTC1_OUT, PTC0_OUT,
+	PTD7_OUT, PTD6_OUT, PTD5_OUT, PTD4_OUT,
+	PTD3_OUT, PTD2_OUT, PTD1_OUT, PTD0_OUT,
+	PTE7_OUT, PTE6_OUT, PTE5_OUT, PTE4_OUT,
+	PTE3_OUT, PTE2_OUT, PTE1_OUT, PTE0_OUT,
+	PTF7_OUT, PTF6_OUT, PTF5_OUT, PTF4_OUT,
+	PTF3_OUT, PTF2_OUT, PTF1_OUT, PTF0_OUT,
+			    PTG5_OUT, PTG4_OUT,
+	PTG3_OUT, PTG2_OUT, PTG1_OUT, PTG0_OUT,
+	PTH7_OUT, PTH6_OUT, PTH5_OUT, PTH4_OUT,
+	PTH3_OUT, PTH2_OUT, PTH1_OUT, PTH0_OUT,
+	PTJ7_OUT, PTJ6_OUT, PTJ5_OUT,
+	PTJ3_OUT, PTJ2_OUT, PTJ1_OUT, PTJ0_OUT,
+	PTK7_OUT, PTK6_OUT, PTK5_OUT, PTK4_OUT,
+	PTK3_OUT, PTK2_OUT, PTK1_OUT, PTK0_OUT,
+	PTL7_OUT, PTL6_OUT, PTL5_OUT, PTL4_OUT,
+	PTL3_OUT, PTL2_OUT, PTL1_OUT, PTL0_OUT,
+	PTM7_OUT, PTM6_OUT, PTM5_OUT, PTM4_OUT,
+	PTM3_OUT, PTM2_OUT, PTM1_OUT, PTM0_OUT,
+	PTN7_OUT, PTN6_OUT, PTN5_OUT, PTN4_OUT,
+	PTN3_OUT, PTN2_OUT, PTN1_OUT, PTN0_OUT,
+	PTQ7_OUT, PTQ6_OUT, PTQ5_OUT, PTQ4_OUT,
+	PTQ3_OUT, PTQ2_OUT, PTQ1_OUT, PTQ0_OUT,
+	PTR7_OUT, PTR6_OUT, PTR5_OUT, PTR4_OUT,
+			    PTR1_OUT, PTR0_OUT,
+		  PTS6_OUT, PTS5_OUT, PTS4_OUT,
+	PTS3_OUT, PTS2_OUT, PTS1_OUT, PTS0_OUT,
+	PTT7_OUT, PTT6_OUT, PTT5_OUT, PTT4_OUT,
+	PTT3_OUT, PTT2_OUT, PTT1_OUT, PTT0_OUT,
+	PTU7_OUT, PTU6_OUT, PTU5_OUT, PTU4_OUT,
+	PTU3_OUT, PTU2_OUT, PTU1_OUT, PTU0_OUT,
+	PTV7_OUT, PTV6_OUT, PTV5_OUT, PTV4_OUT,
+	PTV3_OUT, PTV2_OUT, PTV1_OUT, PTV0_OUT,
+	PTW7_OUT, PTW6_OUT, PTW5_OUT, PTW4_OUT,
+	PTW3_OUT, PTW2_OUT, PTW1_OUT, PTW0_OUT,
+	PTX7_OUT, PTX6_OUT, PTX5_OUT, PTX4_OUT,
+	PTX3_OUT, PTX2_OUT, PTX1_OUT, PTX0_OUT,
+	PTY7_OUT, PTY6_OUT, PTY5_OUT, PTY4_OUT,
+	PTY3_OUT, PTY2_OUT, PTY1_OUT, PTY0_OUT,
+	PTZ7_OUT, PTZ6_OUT, PTZ5_OUT, PTZ4_OUT,
+	PTZ3_OUT, PTZ2_OUT, PTZ1_OUT, PTZ0_OUT,
+	PINMUX_OUTPUT_END,
+
+	PINMUX_FUNCTION_BEGIN,
+	PTA7_FN, PTA6_FN, PTA5_FN, PTA4_FN,
+	PTA3_FN, PTA2_FN, PTA1_FN, PTA0_FN,
+	PTB7_FN, PTB6_FN, PTB5_FN, PTB4_FN,
+	PTB3_FN, PTB2_FN, PTB1_FN, PTB0_FN,
+	PTC7_FN, PTC6_FN, PTC5_FN, PTC4_FN,
+	PTC3_FN, PTC2_FN, PTC1_FN, PTC0_FN,
+	PTD7_FN, PTD6_FN, PTD5_FN, PTD4_FN,
+	PTD3_FN, PTD2_FN, PTD1_FN, PTD0_FN,
+	PTE7_FN, PTE6_FN, PTE5_FN, PTE4_FN,
+	PTE3_FN, PTE2_FN, PTE1_FN, PTE0_FN,
+	PTF7_FN, PTF6_FN, PTF5_FN, PTF4_FN,
+	PTF3_FN, PTF2_FN, PTF1_FN, PTF0_FN,
+			  PTG5_FN, PTG4_FN,
+	PTG3_FN, PTG2_FN, PTG1_FN, PTG0_FN,
+	PTH7_FN, PTH6_FN, PTH5_FN, PTH4_FN,
+	PTH3_FN, PTH2_FN, PTH1_FN, PTH0_FN,
+	PTJ7_FN, PTJ6_FN, PTJ5_FN,
+	PTJ3_FN, PTJ2_FN, PTJ1_FN, PTJ0_FN,
+	PTK7_FN, PTK6_FN, PTK5_FN, PTK4_FN,
+	PTK3_FN, PTK2_FN, PTK1_FN, PTK0_FN,
+	PTL7_FN, PTL6_FN, PTL5_FN, PTL4_FN,
+	PTL3_FN, PTL2_FN, PTL1_FN, PTL0_FN,
+	PTM7_FN, PTM6_FN, PTM5_FN, PTM4_FN,
+	PTM3_FN, PTM2_FN, PTM1_FN, PTM0_FN,
+	PTN7_FN, PTN6_FN, PTN5_FN, PTN4_FN,
+	PTN3_FN, PTN2_FN, PTN1_FN, PTN0_FN,
+	PTQ7_FN, PTQ6_FN, PTQ5_FN, PTQ4_FN,
+	PTQ3_FN, PTQ2_FN, PTQ1_FN, PTQ0_FN,
+	PTR7_FN, PTR6_FN, PTR5_FN, PTR4_FN,
+	PTR3_FN, PTR2_FN, PTR1_FN, PTR0_FN,
+		 PTS6_FN, PTS5_FN, PTS4_FN,
+	PTS3_FN, PTS2_FN, PTS1_FN, PTS0_FN,
+	PTT7_FN, PTT6_FN, PTT5_FN, PTT4_FN,
+	PTT3_FN, PTT2_FN, PTT1_FN, PTT0_FN,
+	PTU7_FN, PTU6_FN, PTU5_FN, PTU4_FN,
+	PTU3_FN, PTU2_FN, PTU1_FN, PTU0_FN,
+	PTV7_FN, PTV6_FN, PTV5_FN, PTV4_FN,
+	PTV3_FN, PTV2_FN, PTV1_FN, PTV0_FN,
+	PTW7_FN, PTW6_FN, PTW5_FN, PTW4_FN,
+	PTW3_FN, PTW2_FN, PTW1_FN, PTW0_FN,
+	PTX7_FN, PTX6_FN, PTX5_FN, PTX4_FN,
+	PTX3_FN, PTX2_FN, PTX1_FN, PTX0_FN,
+	PTY7_FN, PTY6_FN, PTY5_FN, PTY4_FN,
+	PTY3_FN, PTY2_FN, PTY1_FN, PTY0_FN,
+	PTZ7_FN, PTZ6_FN, PTZ5_FN, PTZ4_FN,
+	PTZ3_FN, PTZ2_FN, PTZ1_FN, PTZ0_FN,
+
+
+	PSA15_0, PSA15_1,
+	PSA14_0, PSA14_1,
+	PSA13_0, PSA13_1,
+	PSA12_0, PSA12_1,
+	PSA10_0, PSA10_1,
+	PSA9_0,  PSA9_1,
+	PSA8_0,  PSA8_1,
+	PSA7_0,  PSA7_1,
+	PSA6_0,  PSA6_1,
+	PSA5_0,  PSA5_1,
+	PSA3_0,  PSA3_1,
+	PSA2_0,  PSA2_1,
+	PSA1_0,  PSA1_1,
+	PSA0_0,  PSA0_1,
+
+	PSB14_0, PSB14_1,
+	PSB13_0, PSB13_1,
+	PSB12_0, PSB12_1,
+	PSB11_0, PSB11_1,
+	PSB10_0, PSB10_1,
+	PSB9_0,  PSB9_1,
+	PSB8_0,  PSB8_1,
+	PSB7_0,  PSB7_1,
+	PSB6_0,  PSB6_1,
+	PSB5_0,  PSB5_1,
+	PSB4_0,  PSB4_1,
+	PSB3_0,  PSB3_1,
+	PSB2_0,  PSB2_1,
+	PSB1_0,  PSB1_1,
+	PSB0_0,  PSB0_1,
+
+	PSC15_0, PSC15_1,
+	PSC14_0, PSC14_1,
+	PSC13_0, PSC13_1,
+	PSC12_0, PSC12_1,
+	PSC11_0, PSC11_1,
+	PSC10_0, PSC10_1,
+	PSC9_0,  PSC9_1,
+	PSC8_0,  PSC8_1,
+	PSC7_0,  PSC7_1,
+	PSC6_0,  PSC6_1,
+	PSC5_0,  PSC5_1,
+	PSC4_0,  PSC4_1,
+	PSC2_0,  PSC2_1,
+	PSC1_0,  PSC1_1,
+	PSC0_0,  PSC0_1,
+
+	PSD15_0, PSD15_1,
+	PSD14_0, PSD14_1,
+	PSD13_0, PSD13_1,
+	PSD12_0, PSD12_1,
+	PSD11_0, PSD11_1,
+	PSD10_0, PSD10_1,
+	PSD9_0,  PSD9_1,
+	PSD8_0,  PSD8_1,
+	PSD7_0,  PSD7_1,
+	PSD6_0,  PSD6_1,
+	PSD5_0,  PSD5_1,
+	PSD4_0,  PSD4_1,
+	PSD3_0,  PSD3_1,
+	PSD2_0,  PSD2_1,
+	PSD1_0,  PSD1_1,
+	PSD0_0,  PSD0_1,
+
+	PSE15_0, PSE15_1,
+	PSE14_0, PSE14_1,
+	PSE13_0, PSE13_1,
+	PSE12_0, PSE12_1,
+	PSE11_0, PSE11_1,
+	PSE10_0, PSE10_1,
+	PSE9_0,  PSE9_1,
+	PSE8_0,  PSE8_1,
+	PSE7_0,  PSE7_1,
+	PSE6_0,  PSE6_1,
+	PSE5_0,  PSE5_1,
+	PSE4_0,  PSE4_1,
+	PSE3_0,  PSE3_1,
+	PSE2_0,  PSE2_1,
+	PSE1_0,  PSE1_1,
+	PSE0_0,  PSE0_1,
+	PINMUX_FUNCTION_END,
+
+	PINMUX_MARK_BEGIN,
+	/*PTA*/
+	D23_MARK,	KEYOUT2_MARK,		IDED15_MARK,
+	D22_MARK,	KEYOUT1_MARK,		IDED14_MARK,
+	D21_MARK,	KEYOUT0_MARK,		IDED13_MARK,
+	D20_MARK,	KEYIN4_MARK,		IDED12_MARK,
+	D19_MARK,	KEYIN3_MARK,		IDED11_MARK,
+	D18_MARK,	KEYIN2_MARK,		IDED10_MARK,
+	D17_MARK,	KEYIN1_MARK,		IDED9_MARK,
+	D16_MARK,	KEYIN0_MARK,		IDED8_MARK,
+
+	/*PTB*/
+	D31_MARK,	TPUTO1_MARK,		IDEA1_MARK,
+	D30_MARK,	TPUTO0_MARK,		IDEA0_MARK,
+	D29_MARK,				IODREQ_MARK,
+	D28_MARK,				IDECS0_MARK,
+	D27_MARK,				IDECS1_MARK,
+	D26_MARK,	KEYOUT5_IN5_MARK,	IDEIORD_MARK,
+	D25_MARK,	KEYOUT4_IN6_MARK,	IDEIOWR_MARK,
+	D24_MARK,	KEYOUT3_MARK,		IDEINT_MARK,
+
+	/*PTC*/
+	LCDD7_MARK,
+	LCDD6_MARK,
+	LCDD5_MARK,
+	LCDD4_MARK,
+	LCDD3_MARK,
+	LCDD2_MARK,
+	LCDD1_MARK,
+	LCDD0_MARK,
+
+	/*PTD*/
+	LCDD15_MARK,
+	LCDD14_MARK,
+	LCDD13_MARK,
+	LCDD12_MARK,
+	LCDD11_MARK,
+	LCDD10_MARK,
+	LCDD9_MARK,
+	LCDD8_MARK,
+
+	/*PTE*/
+	FSIMCKB_MARK,
+	FSIMCKA_MARK,
+	LCDD21_MARK,	SCIF2_L_TXD_MARK,
+	LCDD20_MARK,	SCIF4_SCK_MARK,
+	LCDD19_MARK,	SCIF4_RXD_MARK,
+	LCDD18_MARK,	SCIF4_TXD_MARK,
+	LCDD17_MARK,
+	LCDD16_MARK,
+
+	/*PTF*/
+	LCDVSYN_MARK,
+	LCDDISP_MARK,	LCDRS_MARK,
+	LCDHSYN_MARK,	LCDCS_MARK,
+	LCDDON_MARK,
+	LCDDCK_MARK,	LCDWR_MARK,
+	LCDVEPWC_MARK,	SCIF0_TXD_MARK,
+	LCDD23_MARK,	SCIF2_L_SCK_MARK,
+	LCDD22_MARK,	SCIF2_L_RXD_MARK,
+
+	/*PTG*/
+	AUDCK_MARK,
+	AUDSYNC_MARK,
+	AUDATA3_MARK,
+	AUDATA2_MARK,
+	AUDATA1_MARK,
+	AUDATA0_MARK,
+
+	/*PTH*/
+	VIO0_VD_MARK,
+	VIO0_CLK_MARK,
+	VIO0_D7_MARK,
+	VIO0_D6_MARK,
+	VIO0_D5_MARK,
+	VIO0_D4_MARK,
+	VIO0_D3_MARK,
+	VIO0_D2_MARK,
+
+	/*PTJ*/
+	PDSTATUS_MARK,
+	STATUS2_MARK,
+	STATUS0_MARK,
+	A25_MARK,		BS_MARK,
+	A24_MARK,
+	A23_MARK,
+	A22_MARK,
+
+	/*PTK*/
+	VIO1_D5_MARK,	VIO0_D13_MARK,	IDED5_MARK,
+	VIO1_D4_MARK,	VIO0_D12_MARK,	IDED4_MARK,
+	VIO1_D3_MARK,	VIO0_D11_MARK,	IDED3_MARK,
+	VIO1_D2_MARK,	VIO0_D10_MARK,	IDED2_MARK,
+	VIO1_D1_MARK,	VIO0_D9_MARK,	IDED1_MARK,
+	VIO1_D0_MARK,	VIO0_D8_MARK,	IDED0_MARK,
+	VIO0_FLD_MARK,
+	VIO0_HD_MARK,
+
+	/*PTL*/
+	DV_D5_MARK,	SCIF3_V_SCK_MARK,	RMII_RXD0_MARK,
+	DV_D4_MARK,	SCIF3_V_RXD_MARK,	RMII_RXD1_MARK,
+	DV_D3_MARK,	SCIF3_V_TXD_MARK,	RMII_REF_CLK_MARK,
+	DV_D2_MARK,	SCIF1_SCK_MARK,		RMII_TX_EN_MARK,
+	DV_D1_MARK,	SCIF1_RXD_MARK,		RMII_TXD0_MARK,
+	DV_D0_MARK,	SCIF1_TXD_MARK,		RMII_TXD1_MARK,
+	DV_D15_MARK,
+	DV_D14_MARK,	MSIOF0_MCK_MARK,
+
+	/*PTM*/
+	DV_D13_MARK,	MSIOF0_TSCK_MARK,
+	DV_D12_MARK,	MSIOF0_RXD_MARK,
+	DV_D11_MARK,	MSIOF0_TXD_MARK,
+	DV_D10_MARK,	MSIOF0_TSYNC_MARK,
+	DV_D9_MARK,	MSIOF0_SS1_MARK,	MSIOF0_RSCK_MARK,
+	DV_D8_MARK,	MSIOF0_SS2_MARK,	MSIOF0_RSYNC_MARK,
+	LCDVCPWC_MARK,	SCIF0_RXD_MARK,
+	LCDRD_MARK,	SCIF0_SCK_MARK,
+
+	/*PTN*/
+	VIO0_D1_MARK,
+	VIO0_D0_MARK,
+	DV_CLKI_MARK,
+	DV_CLK_MARK,	SCIF2_V_SCK_MARK,
+	DV_VSYNC_MARK,	SCIF2_V_RXD_MARK,
+	DV_HSYNC_MARK,	SCIF2_V_TXD_MARK,
+	DV_D7_MARK,	SCIF3_V_CTS_MARK,	RMII_RX_ER_MARK,
+	DV_D6_MARK,	SCIF3_V_RTS_MARK,	RMII_CRS_DV_MARK,
+
+	/*PTQ*/
+	D7_MARK,
+	D6_MARK,
+	D5_MARK,
+	D4_MARK,
+	D3_MARK,
+	D2_MARK,
+	D1_MARK,
+	D0_MARK,
+
+	/*PTR*/
+	CS6B_CE1B_MARK,
+	CS6A_CE2B_MARK,
+	CS5B_CE1A_MARK,
+	CS5A_CE2A_MARK,
+	IOIS16_MARK,		LCDLCLK_MARK,
+	WAIT_MARK,
+	WE3_ICIOWR_MARK,	TPUTO3_MARK,	TPUTI3_MARK,
+	WE2_ICIORD_MARK,	TPUTO2_MARK,	IDEA2_MARK,
+
+	/*PTS*/
+	VIO_CKO_MARK,
+	VIO1_FLD_MARK,	TPUTI2_MARK,		IDEIORDY_MARK,
+	VIO1_HD_MARK,	SCIF5_SCK_MARK,
+	VIO1_VD_MARK,	SCIF5_RXD_MARK,
+	VIO1_CLK_MARK,	SCIF5_TXD_MARK,
+	VIO1_D7_MARK,	VIO0_D15_MARK,		IDED7_MARK,
+	VIO1_D6_MARK,	VIO0_D14_MARK,		IDED6_MARK,
+
+	/*PTT*/
+	D15_MARK,
+	D14_MARK,
+	D13_MARK,
+	D12_MARK,
+	D11_MARK,
+	D10_MARK,
+	D9_MARK,
+	D8_MARK,
+
+	/*PTU*/
+	DMAC_DACK0_MARK,
+	DMAC_DREQ0_MARK,
+	FSIOASD_MARK,
+	FSIIABCK_MARK,
+	FSIIALRCK_MARK,
+	FSIOABCK_MARK,
+	FSIOALRCK_MARK,
+	CLKAUDIOAO_MARK,
+
+	/*PTV*/
+	FSIIBSD_MARK,		MSIOF1_SS2_MARK,	MSIOF1_RSYNC_MARK,
+	FSIOBSD_MARK,		MSIOF1_SS1_MARK,	MSIOF1_RSCK_MARK,
+	FSIIBBCK_MARK,		MSIOF1_RXD_MARK,
+	FSIIBLRCK_MARK,		MSIOF1_TSYNC_MARK,
+	FSIOBBCK_MARK,		MSIOF1_TSCK_MARK,
+	FSIOBLRCK_MARK,		MSIOF1_TXD_MARK,
+	CLKAUDIOBO_MARK,	MSIOF1_MCK_MARK,
+	FSIIASD_MARK,
+
+	/*PTW*/
+	MMC_D7_MARK,		SDHI1CD_MARK,		IODACK_MARK,
+	MMC_D6_MARK,		SDHI1WP_MARK,		IDERST_MARK,
+	MMC_D5_MARK,		SDHI1D3_MARK,		EXBUF_ENB_MARK,
+	MMC_D4_MARK,		SDHI1D2_MARK,		DIRECTION_MARK,
+	MMC_D3_MARK,		SDHI1D1_MARK,
+	MMC_D2_MARK,		SDHI1D0_MARK,
+	MMC_D1_MARK,		SDHI1CMD_MARK,
+	MMC_D0_MARK,		SDHI1CLK_MARK,
+
+	/*PTX*/
+	DMAC_DACK1_MARK,	IRDA_OUT_MARK,
+	DMAC_DREQ1_MARK,	IRDA_IN_MARK,
+	TSIF_TS0_SDAT_MARK,				LNKSTA_MARK,
+	TSIF_TS0_SCK_MARK,				MDIO_MARK,
+	TSIF_TS0_SDEN_MARK,				MDC_MARK,
+	TSIF_TS0_SPSYNC_MARK,
+	MMC_CLK_MARK,
+	MMC_CMD_MARK,
+
+	/*PTY*/
+	SDHI0CD_MARK,
+	SDHI0WP_MARK,
+	SDHI0D3_MARK,
+	SDHI0D2_MARK,
+	SDHI0D1_MARK,
+	SDHI0D0_MARK,
+	SDHI0CMD_MARK,
+	SDHI0CLK_MARK,
+
+	/*PTZ*/
+	INTC_IRQ7_MARK,		SCIF3_I_CTS_MARK,
+	INTC_IRQ6_MARK,		SCIF3_I_RTS_MARK,
+	INTC_IRQ5_MARK,		SCIF3_I_SCK_MARK,
+	INTC_IRQ4_MARK,		SCIF3_I_RXD_MARK,
+	INTC_IRQ3_MARK,		SCIF3_I_TXD_MARK,
+	INTC_IRQ2_MARK,
+	INTC_IRQ1_MARK,
+	INTC_IRQ0_MARK,
+	PINMUX_MARK_END,
+};
+
+static pinmux_enum_t pinmux_data[] = {
+	/* PTA GPIO */
+	PINMUX_DATA(PTA7_DATA, PTA7_IN, PTA7_OUT, PTA7_IN_PU),
+	PINMUX_DATA(PTA6_DATA, PTA6_IN, PTA6_OUT, PTA6_IN_PU),
+	PINMUX_DATA(PTA5_DATA, PTA5_IN, PTA5_OUT, PTA5_IN_PU),
+	PINMUX_DATA(PTA4_DATA, PTA4_IN, PTA4_OUT, PTA4_IN_PU),
+	PINMUX_DATA(PTA3_DATA, PTA3_IN, PTA3_OUT, PTA3_IN_PU),
+	PINMUX_DATA(PTA2_DATA, PTA2_IN, PTA2_OUT, PTA2_IN_PU),
+	PINMUX_DATA(PTA1_DATA, PTA1_IN, PTA1_OUT, PTA1_IN_PU),
+	PINMUX_DATA(PTA0_DATA, PTA0_IN, PTA0_OUT, PTA0_IN_PU),
+
+	/* PTB GPIO */
+	PINMUX_DATA(PTB7_DATA, PTB7_IN, PTB7_OUT, PTB7_IN_PU),
+	PINMUX_DATA(PTB6_DATA, PTB6_IN, PTB6_OUT, PTB6_IN_PU),
+	PINMUX_DATA(PTB5_DATA, PTB5_IN, PTB5_OUT, PTB5_IN_PU),
+	PINMUX_DATA(PTB4_DATA, PTB4_IN, PTB4_OUT, PTB4_IN_PU),
+	PINMUX_DATA(PTB3_DATA, PTB3_IN, PTB3_OUT, PTB3_IN_PU),
+	PINMUX_DATA(PTB2_DATA, PTB2_IN, PTB2_OUT, PTB2_IN_PU),
+	PINMUX_DATA(PTB1_DATA, PTB1_IN, PTB1_OUT, PTB1_IN_PU),
+	PINMUX_DATA(PTB0_DATA, PTB0_IN, PTB0_OUT, PTB0_IN_PU),
+
+	/* PTC GPIO */
+	PINMUX_DATA(PTC7_DATA, PTC7_IN, PTC7_OUT, PTC7_IN_PU),
+	PINMUX_DATA(PTC6_DATA, PTC6_IN, PTC6_OUT, PTC6_IN_PU),
+	PINMUX_DATA(PTC5_DATA, PTC5_IN, PTC5_OUT, PTC5_IN_PU),
+	PINMUX_DATA(PTC4_DATA, PTC4_IN, PTC4_OUT, PTC4_IN_PU),
+	PINMUX_DATA(PTC3_DATA, PTC3_IN, PTC3_OUT, PTC3_IN_PU),
+	PINMUX_DATA(PTC2_DATA, PTC2_IN, PTC2_OUT, PTC2_IN_PU),
+	PINMUX_DATA(PTC1_DATA, PTC1_IN, PTC1_OUT, PTC1_IN_PU),
+	PINMUX_DATA(PTC0_DATA, PTC0_IN, PTC0_OUT, PTC0_IN_PU),
+
+	/* PTD GPIO */
+	PINMUX_DATA(PTD7_DATA, PTD7_IN, PTD7_OUT, PTD7_IN_PU),
+	PINMUX_DATA(PTD6_DATA, PTD6_IN, PTD6_OUT, PTD6_IN_PU),
+	PINMUX_DATA(PTD5_DATA, PTD5_IN, PTD5_OUT, PTD5_IN_PU),
+	PINMUX_DATA(PTD4_DATA, PTD4_IN, PTD4_OUT, PTD4_IN_PU),
+	PINMUX_DATA(PTD3_DATA, PTD3_IN, PTD3_OUT, PTD3_IN_PU),
+	PINMUX_DATA(PTD2_DATA, PTD2_IN, PTD2_OUT, PTD2_IN_PU),
+	PINMUX_DATA(PTD1_DATA, PTD1_IN, PTD1_OUT, PTD1_IN_PU),
+	PINMUX_DATA(PTD0_DATA, PTD0_IN, PTD0_OUT, PTD0_IN_PU),
+
+	/* PTE GPIO */
+	PINMUX_DATA(PTE7_DATA, PTE7_IN, PTE7_OUT, PTE7_IN_PU),
+	PINMUX_DATA(PTE6_DATA, PTE6_IN, PTE6_OUT, PTE6_IN_PU),
+	PINMUX_DATA(PTE5_DATA, PTE5_IN, PTE5_OUT, PTE5_IN_PU),
+	PINMUX_DATA(PTE4_DATA, PTE4_IN, PTE4_OUT, PTE4_IN_PU),
+	PINMUX_DATA(PTE3_DATA, PTE3_IN, PTE3_OUT, PTE3_IN_PU),
+	PINMUX_DATA(PTE2_DATA, PTE2_IN, PTE2_OUT, PTE2_IN_PU),
+	PINMUX_DATA(PTE1_DATA, PTE1_IN, PTE1_OUT, PTE1_IN_PU),
+	PINMUX_DATA(PTE0_DATA, PTE0_IN, PTE0_OUT, PTE0_IN_PU),
+
+	/* PTF GPIO */
+	PINMUX_DATA(PTF7_DATA, PTF7_IN, PTF7_OUT, PTF7_IN_PU),
+	PINMUX_DATA(PTF6_DATA, PTF6_IN, PTF6_OUT, PTF6_IN_PU),
+	PINMUX_DATA(PTF5_DATA, PTF5_IN, PTF5_OUT, PTF5_IN_PU),
+	PINMUX_DATA(PTF4_DATA, PTF4_IN, PTF4_OUT, PTF4_IN_PU),
+	PINMUX_DATA(PTF3_DATA, PTF3_IN, PTF3_OUT, PTF3_IN_PU),
+	PINMUX_DATA(PTF2_DATA, PTF2_IN, PTF2_OUT, PTF2_IN_PU),
+	PINMUX_DATA(PTF1_DATA, PTF1_IN, PTF1_OUT, PTF1_IN_PU),
+	PINMUX_DATA(PTF0_DATA, PTF0_IN, PTF0_OUT, PTF0_IN_PU),
+
+	/* PTG GPIO */
+	PINMUX_DATA(PTG5_DATA, PTG5_OUT),
+	PINMUX_DATA(PTG4_DATA, PTG4_OUT),
+	PINMUX_DATA(PTG3_DATA, PTG3_OUT),
+	PINMUX_DATA(PTG2_DATA, PTG2_OUT),
+	PINMUX_DATA(PTG1_DATA, PTG1_OUT),
+	PINMUX_DATA(PTG0_DATA, PTG0_OUT),
+
+	/* PTH GPIO */
+	PINMUX_DATA(PTH7_DATA, PTH7_IN, PTH7_OUT, PTH7_IN_PU),
+	PINMUX_DATA(PTH6_DATA, PTH6_IN, PTH6_OUT, PTH6_IN_PU),
+	PINMUX_DATA(PTH5_DATA, PTH5_IN, PTH5_OUT, PTH5_IN_PU),
+	PINMUX_DATA(PTH4_DATA, PTH4_IN, PTH4_OUT, PTH4_IN_PU),
+	PINMUX_DATA(PTH3_DATA, PTH3_IN, PTH3_OUT, PTH3_IN_PU),
+	PINMUX_DATA(PTH2_DATA, PTH2_IN, PTH2_OUT, PTH2_IN_PU),
+	PINMUX_DATA(PTH1_DATA, PTH1_IN, PTH1_OUT, PTH1_IN_PU),
+	PINMUX_DATA(PTH0_DATA, PTH0_IN, PTH0_OUT, PTH0_IN_PU),
+
+	/* PTJ GPIO */
+	PINMUX_DATA(PTJ7_DATA, PTJ7_OUT),
+	PINMUX_DATA(PTJ6_DATA, PTJ6_OUT),
+	PINMUX_DATA(PTJ5_DATA, PTJ5_OUT),
+	PINMUX_DATA(PTJ3_DATA, PTJ3_IN, PTJ3_OUT, PTJ3_IN_PU),
+	PINMUX_DATA(PTJ2_DATA, PTJ2_IN, PTJ2_OUT, PTJ2_IN_PU),
+	PINMUX_DATA(PTJ1_DATA, PTJ1_IN, PTJ1_OUT, PTJ1_IN_PU),
+	PINMUX_DATA(PTJ0_DATA, PTJ0_IN, PTJ0_OUT, PTJ0_IN_PU),
+
+	/* PTK GPIO */
+	PINMUX_DATA(PTK7_DATA, PTK7_IN, PTK7_OUT, PTK7_IN_PU),
+	PINMUX_DATA(PTK6_DATA, PTK6_IN, PTK6_OUT, PTK6_IN_PU),
+	PINMUX_DATA(PTK5_DATA, PTK5_IN, PTK5_OUT, PTK5_IN_PU),
+	PINMUX_DATA(PTK4_DATA, PTK4_IN, PTK4_OUT, PTK4_IN_PU),
+	PINMUX_DATA(PTK3_DATA, PTK3_IN, PTK3_OUT, PTK3_IN_PU),
+	PINMUX_DATA(PTK2_DATA, PTK2_IN, PTK2_OUT, PTK2_IN_PU),
+	PINMUX_DATA(PTK1_DATA, PTK1_IN, PTK1_OUT, PTK1_IN_PU),
+	PINMUX_DATA(PTK0_DATA, PTK0_IN, PTK0_OUT, PTK0_IN_PU),
+
+	/* PTL GPIO */
+	PINMUX_DATA(PTL7_DATA, PTL7_IN, PTL7_OUT, PTL7_IN_PU),
+	PINMUX_DATA(PTL6_DATA, PTL6_IN, PTL6_OUT, PTL6_IN_PU),
+	PINMUX_DATA(PTL5_DATA, PTL5_IN, PTL5_OUT, PTL5_IN_PU),
+	PINMUX_DATA(PTL4_DATA, PTL4_IN, PTL4_OUT, PTL4_IN_PU),
+	PINMUX_DATA(PTL3_DATA, PTL3_IN, PTL3_OUT, PTL3_IN_PU),
+	PINMUX_DATA(PTL2_DATA, PTL2_IN, PTL2_OUT, PTL2_IN_PU),
+	PINMUX_DATA(PTL1_DATA, PTL1_IN, PTL1_OUT, PTL1_IN_PU),
+	PINMUX_DATA(PTL0_DATA, PTL0_IN, PTL0_OUT, PTL0_IN_PU),
+
+	/* PTM GPIO */
+	PINMUX_DATA(PTM7_DATA, PTM7_IN, PTM7_OUT, PTM7_IN_PU),
+	PINMUX_DATA(PTM6_DATA, PTM6_IN, PTM6_OUT, PTM6_IN_PU),
+	PINMUX_DATA(PTM5_DATA, PTM5_IN, PTM5_OUT, PTM5_IN_PU),
+	PINMUX_DATA(PTM4_DATA, PTM4_IN, PTM4_OUT, PTM4_IN_PU),
+	PINMUX_DATA(PTM3_DATA, PTM3_IN, PTM3_OUT, PTM3_IN_PU),
+	PINMUX_DATA(PTM2_DATA, PTM2_IN, PTM2_OUT, PTM2_IN_PU),
+	PINMUX_DATA(PTM1_DATA, PTM1_IN, PTM1_OUT, PTM1_IN_PU),
+	PINMUX_DATA(PTM0_DATA, PTM0_IN, PTM0_OUT, PTM0_IN_PU),
+
+	/* PTN GPIO */
+	PINMUX_DATA(PTN7_DATA, PTN7_IN, PTN7_OUT, PTN7_IN_PU),
+	PINMUX_DATA(PTN6_DATA, PTN6_IN, PTN6_OUT, PTN6_IN_PU),
+	PINMUX_DATA(PTN5_DATA, PTN5_IN, PTN5_OUT, PTN5_IN_PU),
+	PINMUX_DATA(PTN4_DATA, PTN4_IN, PTN4_OUT, PTN4_IN_PU),
+	PINMUX_DATA(PTN3_DATA, PTN3_IN, PTN3_OUT, PTN3_IN_PU),
+	PINMUX_DATA(PTN2_DATA, PTN2_IN, PTN2_OUT, PTN2_IN_PU),
+	PINMUX_DATA(PTN1_DATA, PTN1_IN, PTN1_OUT, PTN1_IN_PU),
+	PINMUX_DATA(PTN0_DATA, PTN0_IN, PTN0_OUT, PTN0_IN_PU),
+
+	/* PTQ GPIO */
+	PINMUX_DATA(PTQ7_DATA, PTQ7_IN, PTQ7_OUT, PTQ7_IN_PU),
+	PINMUX_DATA(PTQ6_DATA, PTQ6_IN, PTQ6_OUT, PTQ6_IN_PU),
+	PINMUX_DATA(PTQ5_DATA, PTQ5_IN, PTQ5_OUT, PTQ5_IN_PU),
+	PINMUX_DATA(PTQ4_DATA, PTQ4_IN, PTQ4_OUT, PTQ4_IN_PU),
+	PINMUX_DATA(PTQ3_DATA, PTQ3_IN, PTQ3_OUT, PTQ3_IN_PU),
+	PINMUX_DATA(PTQ2_DATA, PTQ2_IN, PTQ2_OUT, PTQ2_IN_PU),
+	PINMUX_DATA(PTQ1_DATA, PTQ1_IN, PTQ1_OUT, PTQ1_IN_PU),
+	PINMUX_DATA(PTQ0_DATA, PTQ0_IN, PTQ0_OUT, PTQ0_IN_PU),
+
+	/* PTR GPIO */
+	PINMUX_DATA(PTR7_DATA, PTR7_IN, PTR7_OUT, PTR7_IN_PU),
+	PINMUX_DATA(PTR6_DATA, PTR6_IN, PTR6_OUT, PTR6_IN_PU),
+	PINMUX_DATA(PTR5_DATA, PTR5_IN, PTR5_OUT, PTR5_IN_PU),
+	PINMUX_DATA(PTR4_DATA, PTR4_IN, PTR4_OUT, PTR4_IN_PU),
+	PINMUX_DATA(PTR3_DATA, PTR3_IN,           PTR3_IN_PU),
+	PINMUX_DATA(PTR2_DATA, PTR2_IN,           PTR2_IN_PU),
+	PINMUX_DATA(PTR1_DATA, PTR1_IN, PTR1_OUT, PTR1_IN_PU),
+	PINMUX_DATA(PTR0_DATA, PTR0_IN, PTR0_OUT, PTR0_IN_PU),
+
+	/* PTS GPIO */
+	PINMUX_DATA(PTS6_DATA, PTS6_IN, PTS6_OUT, PTS6_IN_PU),
+	PINMUX_DATA(PTS5_DATA, PTS5_IN, PTS5_OUT, PTS5_IN_PU),
+	PINMUX_DATA(PTS4_DATA, PTS4_IN, PTS4_OUT, PTS4_IN_PU),
+	PINMUX_DATA(PTS3_DATA, PTS3_IN, PTS3_OUT, PTS3_IN_PU),
+	PINMUX_DATA(PTS2_DATA, PTS2_IN, PTS2_OUT, PTS2_IN_PU),
+	PINMUX_DATA(PTS1_DATA, PTS1_IN, PTS1_OUT, PTS1_IN_PU),
+	PINMUX_DATA(PTS0_DATA, PTS0_IN, PTS0_OUT, PTS0_IN_PU),
+
+	/* PTT GPIO */
+	PINMUX_DATA(PTT7_DATA, PTT7_IN, PTT7_OUT, PTT7_IN_PU),
+	PINMUX_DATA(PTT6_DATA, PTT6_IN, PTT6_OUT, PTT6_IN_PU),
+	PINMUX_DATA(PTT5_DATA, PTT5_IN, PTT5_OUT, PTT5_IN_PU),
+	PINMUX_DATA(PTT4_DATA, PTT4_IN, PTT4_OUT, PTT4_IN_PU),
+	PINMUX_DATA(PTT3_DATA, PTT3_IN, PTT3_OUT, PTT3_IN_PU),
+	PINMUX_DATA(PTT2_DATA, PTT2_IN, PTT2_OUT, PTT2_IN_PU),
+	PINMUX_DATA(PTT1_DATA, PTT1_IN, PTT1_OUT, PTT1_IN_PU),
+	PINMUX_DATA(PTT0_DATA, PTT0_IN, PTT0_OUT, PTT0_IN_PU),
+
+	/* PTU GPIO */
+	PINMUX_DATA(PTU7_DATA, PTU7_IN, PTU7_OUT, PTU7_IN_PU),
+	PINMUX_DATA(PTU6_DATA, PTU6_IN, PTU6_OUT, PTU6_IN_PU),
+	PINMUX_DATA(PTU5_DATA, PTU5_IN, PTU5_OUT, PTU5_IN_PU),
+	PINMUX_DATA(PTU4_DATA, PTU4_IN, PTU4_OUT, PTU4_IN_PU),
+	PINMUX_DATA(PTU3_DATA, PTU3_IN, PTU3_OUT, PTU3_IN_PU),
+	PINMUX_DATA(PTU2_DATA, PTU2_IN, PTU2_OUT, PTU2_IN_PU),
+	PINMUX_DATA(PTU1_DATA, PTU1_IN, PTU1_OUT, PTU1_IN_PU),
+	PINMUX_DATA(PTU0_DATA, PTU0_IN, PTU0_OUT, PTU0_IN_PU),
+
+	/* PTV GPIO */
+	PINMUX_DATA(PTV7_DATA, PTV7_IN, PTV7_OUT, PTV7_IN_PU),
+	PINMUX_DATA(PTV6_DATA, PTV6_IN, PTV6_OUT, PTV6_IN_PU),
+	PINMUX_DATA(PTV5_DATA, PTV5_IN, PTV5_OUT, PTV5_IN_PU),
+	PINMUX_DATA(PTV4_DATA, PTV4_IN, PTV4_OUT, PTV4_IN_PU),
+	PINMUX_DATA(PTV3_DATA, PTV3_IN, PTV3_OUT, PTV3_IN_PU),
+	PINMUX_DATA(PTV2_DATA, PTV2_IN, PTV2_OUT, PTV2_IN_PU),
+	PINMUX_DATA(PTV1_DATA, PTV1_IN, PTV1_OUT, PTV1_IN_PU),
+	PINMUX_DATA(PTV0_DATA, PTV0_IN, PTV0_OUT, PTV0_IN_PU),
+
+	/* PTW GPIO */
+	PINMUX_DATA(PTW7_DATA, PTW7_IN, PTW7_OUT, PTW7_IN_PU),
+	PINMUX_DATA(PTW6_DATA, PTW6_IN, PTW6_OUT, PTW6_IN_PU),
+	PINMUX_DATA(PTW5_DATA, PTW5_IN, PTW5_OUT, PTW5_IN_PU),
+	PINMUX_DATA(PTW4_DATA, PTW4_IN, PTW4_OUT, PTW4_IN_PU),
+	PINMUX_DATA(PTW3_DATA, PTW3_IN, PTW3_OUT, PTW3_IN_PU),
+	PINMUX_DATA(PTW2_DATA, PTW2_IN, PTW2_OUT, PTW2_IN_PU),
+	PINMUX_DATA(PTW1_DATA, PTW1_IN, PTW1_OUT, PTW1_IN_PU),
+	PINMUX_DATA(PTW0_DATA, PTW0_IN, PTW0_OUT, PTW0_IN_PU),
+
+	/* PTX GPIO */
+	PINMUX_DATA(PTX7_DATA, PTX7_IN, PTX7_OUT, PTX7_IN_PU),
+	PINMUX_DATA(PTX6_DATA, PTX6_IN, PTX6_OUT, PTX6_IN_PU),
+	PINMUX_DATA(PTX5_DATA, PTX5_IN, PTX5_OUT, PTX5_IN_PU),
+	PINMUX_DATA(PTX4_DATA, PTX4_IN, PTX4_OUT, PTX4_IN_PU),
+	PINMUX_DATA(PTX3_DATA, PTX3_IN, PTX3_OUT, PTX3_IN_PU),
+	PINMUX_DATA(PTX2_DATA, PTX2_IN, PTX2_OUT, PTX2_IN_PU),
+	PINMUX_DATA(PTX1_DATA, PTX1_IN, PTX1_OUT, PTX1_IN_PU),
+	PINMUX_DATA(PTX0_DATA, PTX0_IN, PTX0_OUT, PTX0_IN_PU),
+
+	/* PTY GPIO */
+	PINMUX_DATA(PTY7_DATA, PTY7_IN, PTY7_OUT, PTY7_IN_PU),
+	PINMUX_DATA(PTY6_DATA, PTY6_IN, PTY6_OUT, PTY6_IN_PU),
+	PINMUX_DATA(PTY5_DATA, PTY5_IN, PTY5_OUT, PTY5_IN_PU),
+	PINMUX_DATA(PTY4_DATA, PTY4_IN, PTY4_OUT, PTY4_IN_PU),
+	PINMUX_DATA(PTY3_DATA, PTY3_IN, PTY3_OUT, PTY3_IN_PU),
+	PINMUX_DATA(PTY2_DATA, PTY2_IN, PTY2_OUT, PTY2_IN_PU),
+	PINMUX_DATA(PTY1_DATA, PTY1_IN, PTY1_OUT, PTY1_IN_PU),
+	PINMUX_DATA(PTY0_DATA, PTY0_IN, PTY0_OUT, PTY0_IN_PU),
+
+	/* PTZ GPIO */
+	PINMUX_DATA(PTZ7_DATA, PTZ7_IN, PTZ7_OUT, PTZ7_IN_PU),
+	PINMUX_DATA(PTZ6_DATA, PTZ6_IN, PTZ6_OUT, PTZ6_IN_PU),
+	PINMUX_DATA(PTZ5_DATA, PTZ5_IN, PTZ5_OUT, PTZ5_IN_PU),
+	PINMUX_DATA(PTZ4_DATA, PTZ4_IN, PTZ4_OUT, PTZ4_IN_PU),
+	PINMUX_DATA(PTZ3_DATA, PTZ3_IN, PTZ3_OUT, PTZ3_IN_PU),
+	PINMUX_DATA(PTZ2_DATA, PTZ2_IN, PTZ2_OUT, PTZ2_IN_PU),
+	PINMUX_DATA(PTZ1_DATA, PTZ1_IN, PTZ1_OUT, PTZ1_IN_PU),
+	PINMUX_DATA(PTZ0_DATA, PTZ0_IN, PTZ0_OUT, PTZ0_IN_PU),
+
+	/* PTA FN */
+	PINMUX_DATA(D23_MARK,	PSA15_0, PSA14_0, PTA7_FN),
+	PINMUX_DATA(D22_MARK,	PSA15_0, PSA14_0, PTA6_FN),
+	PINMUX_DATA(D21_MARK,	PSA15_0, PSA14_0, PTA5_FN),
+	PINMUX_DATA(D20_MARK,	PSA15_0, PSA14_0, PTA4_FN),
+	PINMUX_DATA(D19_MARK,	PSA15_0, PSA14_0, PTA3_FN),
+	PINMUX_DATA(D18_MARK,	PSA15_0, PSA14_0, PTA2_FN),
+	PINMUX_DATA(D17_MARK,	PSA15_0, PSA14_0, PTA1_FN),
+	PINMUX_DATA(D16_MARK,	PSA15_0, PSA14_0, PTA0_FN),
+
+	PINMUX_DATA(KEYOUT2_MARK,	PSA15_0, PSA14_1, PTA7_FN),
+	PINMUX_DATA(KEYOUT1_MARK,	PSA15_0, PSA14_1, PTA6_FN),
+	PINMUX_DATA(KEYOUT0_MARK,	PSA15_0, PSA14_1, PTA5_FN),
+	PINMUX_DATA(KEYIN4_MARK,	PSA15_0, PSA14_1, PTA4_FN),
+	PINMUX_DATA(KEYIN3_MARK,	PSA15_0, PSA14_1, PTA3_FN),
+	PINMUX_DATA(KEYIN2_MARK,	PSA15_0, PSA14_1, PTA2_FN),
+	PINMUX_DATA(KEYIN1_MARK,	PSA15_0, PSA14_1, PTA1_FN),
+	PINMUX_DATA(KEYIN0_MARK,	PSA15_0, PSA14_1, PTA0_FN),
+
+	PINMUX_DATA(IDED15_MARK,	PSA15_1, PSA14_0, PTA7_FN),
+	PINMUX_DATA(IDED14_MARK,	PSA15_1, PSA14_0, PTA6_FN),
+	PINMUX_DATA(IDED13_MARK,	PSA15_1, PSA14_0, PTA5_FN),
+	PINMUX_DATA(IDED12_MARK,	PSA15_1, PSA14_0, PTA4_FN),
+	PINMUX_DATA(IDED11_MARK,	PSA15_1, PSA14_0, PTA3_FN),
+	PINMUX_DATA(IDED10_MARK,	PSA15_1, PSA14_0, PTA2_FN),
+	PINMUX_DATA(IDED9_MARK,		PSA15_1, PSA14_0, PTA1_FN),
+	PINMUX_DATA(IDED8_MARK,		PSA15_1, PSA14_0, PTA0_FN),
+
+	/* PTB FN */
+	PINMUX_DATA(D31_MARK,		PSE15_0, PSE14_0, PTB7_FN),
+	PINMUX_DATA(D30_MARK,		PSE15_0, PSE14_0, PTB6_FN),
+	PINMUX_DATA(D29_MARK,		PSE11_0,          PTB5_FN),
+	PINMUX_DATA(D28_MARK,		PSE11_0,          PTB4_FN),
+	PINMUX_DATA(D27_MARK,		PSE11_0,          PTB3_FN),
+	PINMUX_DATA(D26_MARK,		PSA15_0, PSA14_0, PTB2_FN),
+	PINMUX_DATA(D25_MARK,		PSA15_0, PSA14_0, PTB1_FN),
+	PINMUX_DATA(D24_MARK,		PSA15_0, PSA14_0, PTB0_FN),
+
+	PINMUX_DATA(IDEA1_MARK,		PSE15_1, PSE14_0, PTB7_FN),
+	PINMUX_DATA(IDEA0_MARK,		PSE15_1, PSE14_0, PTB6_FN),
+	PINMUX_DATA(IODREQ_MARK,	PSE11_1,          PTB5_FN),
+	PINMUX_DATA(IDECS0_MARK,	PSE11_1,          PTB4_FN),
+	PINMUX_DATA(IDECS1_MARK,	PSE11_1,          PTB3_FN),
+	PINMUX_DATA(IDEIORD_MARK,	PSA15_1, PSA14_0, PTB2_FN),
+	PINMUX_DATA(IDEIOWR_MARK,	PSA15_1, PSA14_0, PTB1_FN),
+	PINMUX_DATA(IDEINT_MARK,	PSA15_1, PSA14_0, PTB0_FN),
+
+	PINMUX_DATA(TPUTO1_MARK,	PSE15_0, PSE14_1, PTB7_FN),
+	PINMUX_DATA(TPUTO0_MARK,	PSE15_0, PSE14_1, PTB6_FN),
+
+	PINMUX_DATA(KEYOUT5_IN5_MARK,	PSA15_0, PSA14_1, PTB2_FN),
+	PINMUX_DATA(KEYOUT4_IN6_MARK,	PSA15_0, PSA14_1, PTB1_FN),
+	PINMUX_DATA(KEYOUT3_MARK,	PSA15_0, PSA14_1, PTB0_FN),
+
+	/* PTC FN */
+	PINMUX_DATA(LCDD7_MARK, PSD5_0, PTC7_FN),
+	PINMUX_DATA(LCDD6_MARK, PSD5_0, PTC6_FN),
+	PINMUX_DATA(LCDD5_MARK, PSD5_0, PTC5_FN),
+	PINMUX_DATA(LCDD4_MARK, PSD5_0, PTC4_FN),
+	PINMUX_DATA(LCDD3_MARK, PSD5_0, PTC3_FN),
+	PINMUX_DATA(LCDD2_MARK, PSD5_0, PTC2_FN),
+	PINMUX_DATA(LCDD1_MARK, PSD5_0, PTC1_FN),
+	PINMUX_DATA(LCDD0_MARK, PSD5_0, PTC0_FN),
+
+	/* PTD FN */
+	PINMUX_DATA(LCDD15_MARK, PSD5_0, PTD7_FN),
+	PINMUX_DATA(LCDD14_MARK, PSD5_0, PTD6_FN),
+	PINMUX_DATA(LCDD13_MARK, PSD5_0, PTD5_FN),
+	PINMUX_DATA(LCDD12_MARK, PSD5_0, PTD4_FN),
+	PINMUX_DATA(LCDD11_MARK, PSD5_0, PTD3_FN),
+	PINMUX_DATA(LCDD10_MARK, PSD5_0, PTD2_FN),
+	PINMUX_DATA(LCDD9_MARK,  PSD5_0, PTD1_FN),
+	PINMUX_DATA(LCDD8_MARK,  PSD5_0, PTD0_FN),
+
+	/* PTE FN */
+	PINMUX_DATA(FSIMCKB_MARK, PTE7_FN),
+	PINMUX_DATA(FSIMCKA_MARK, PTE6_FN),
+
+	PINMUX_DATA(LCDD21_MARK,	PSC5_0, PSC4_0, PTE5_FN),
+	PINMUX_DATA(LCDD20_MARK,	PSD3_0, PSD2_0, PTE4_FN),
+	PINMUX_DATA(LCDD19_MARK,	PSA3_0, PSA2_0, PTE3_FN),
+	PINMUX_DATA(LCDD18_MARK,	PSA3_0, PSA2_0, PTE2_FN),
+	PINMUX_DATA(LCDD17_MARK,	PSD5_0,         PTE1_FN),
+	PINMUX_DATA(LCDD16_MARK,	PSD5_0,         PTE0_FN),
+
+	PINMUX_DATA(SCIF2_L_TXD_MARK,	PSC5_0, PSC4_1, PTE5_FN),
+	PINMUX_DATA(SCIF4_SCK_MARK,	PSD3_0, PSD2_1, PTE4_FN),
+	PINMUX_DATA(SCIF4_RXD_MARK,	PSA3_0, PSA2_1, PTE3_FN),
+	PINMUX_DATA(SCIF4_TXD_MARK,	PSA3_0, PSA2_1, PTE2_FN),
+
+	/* PTF FN */
+	PINMUX_DATA(LCDVSYN_MARK,	PSD8_0,          PTF7_FN),
+	PINMUX_DATA(LCDDISP_MARK,	PSD10_0, PSD9_0, PTF6_FN),
+	PINMUX_DATA(LCDHSYN_MARK,	PSD10_0, PSD9_0, PTF5_FN),
+	PINMUX_DATA(LCDDON_MARK,	PSD8_0,          PTF4_FN),
+	PINMUX_DATA(LCDDCK_MARK,	PSD10_0, PSD9_0, PTF3_FN),
+	PINMUX_DATA(LCDVEPWC_MARK,	PSA6_0,          PTF2_FN),
+	PINMUX_DATA(LCDD23_MARK,	PSC7_0,  PSC6_0, PTF1_FN),
+	PINMUX_DATA(LCDD22_MARK,	PSC5_0,  PSC4_0, PTF0_FN),
+
+	PINMUX_DATA(LCDRS_MARK,		PSD10_0, PSD9_1, PTF6_FN),
+	PINMUX_DATA(LCDCS_MARK,		PSD10_0, PSD9_1, PTF5_FN),
+	PINMUX_DATA(LCDWR_MARK,		PSD10_0, PSD9_1, PTF3_FN),
+
+	PINMUX_DATA(SCIF0_TXD_MARK,	PSA6_1,          PTF2_FN),
+	PINMUX_DATA(SCIF2_L_SCK_MARK,	PSC7_0,  PSC6_1, PTF1_FN),
+	PINMUX_DATA(SCIF2_L_RXD_MARK,	PSC5_0,  PSC4_1, PTF0_FN),
+
+	/* PTG FN */
+	PINMUX_DATA(AUDCK_MARK,   PTG5_FN),
+	PINMUX_DATA(AUDSYNC_MARK, PTG4_FN),
+	PINMUX_DATA(AUDATA3_MARK, PTG3_FN),
+	PINMUX_DATA(AUDATA2_MARK, PTG2_FN),
+	PINMUX_DATA(AUDATA1_MARK, PTG1_FN),
+	PINMUX_DATA(AUDATA0_MARK, PTG0_FN),
+
+	/* PTH FN */
+	PINMUX_DATA(VIO0_VD_MARK,  PTH7_FN),
+	PINMUX_DATA(VIO0_CLK_MARK, PTH6_FN),
+	PINMUX_DATA(VIO0_D7_MARK,  PTH5_FN),
+	PINMUX_DATA(VIO0_D6_MARK,  PTH4_FN),
+	PINMUX_DATA(VIO0_D5_MARK,  PTH3_FN),
+	PINMUX_DATA(VIO0_D4_MARK,  PTH2_FN),
+	PINMUX_DATA(VIO0_D3_MARK,  PTH1_FN),
+	PINMUX_DATA(VIO0_D2_MARK,  PTH0_FN),
+
+	/* PTJ FN */
+	PINMUX_DATA(PDSTATUS_MARK,	PTJ7_FN),
+	PINMUX_DATA(STATUS2_MARK,	PTJ6_FN),
+	PINMUX_DATA(STATUS0_MARK,	PTJ5_FN),
+	PINMUX_DATA(A25_MARK,		PSA8_0, PTJ3_FN),
+	PINMUX_DATA(BS_MARK,		PSA8_1, PTJ3_FN),
+	PINMUX_DATA(A24_MARK,		PTJ2_FN),
+	PINMUX_DATA(A23_MARK,		PTJ1_FN),
+	PINMUX_DATA(A22_MARK,		PTJ0_FN),
+
+	/* PTK FN */
+	PINMUX_DATA(VIO1_D5_MARK,	PSB7_0, PSB6_0, PTK7_FN),
+	PINMUX_DATA(VIO1_D4_MARK,	PSB7_0, PSB6_0, PTK6_FN),
+	PINMUX_DATA(VIO1_D3_MARK,	PSB7_0, PSB6_0, PTK5_FN),
+	PINMUX_DATA(VIO1_D2_MARK,	PSB7_0, PSB6_0, PTK4_FN),
+	PINMUX_DATA(VIO1_D1_MARK,	PSB7_0, PSB6_0, PTK3_FN),
+	PINMUX_DATA(VIO1_D0_MARK,	PSB7_0, PSB6_0, PTK2_FN),
+
+	PINMUX_DATA(VIO0_D13_MARK,	PSB7_0, PSB6_1, PTK7_FN),
+	PINMUX_DATA(VIO0_D12_MARK,	PSB7_0, PSB6_1, PTK6_FN),
+	PINMUX_DATA(VIO0_D11_MARK,	PSB7_0, PSB6_1, PTK5_FN),
+	PINMUX_DATA(VIO0_D10_MARK,	PSB7_0, PSB6_1, PTK4_FN),
+	PINMUX_DATA(VIO0_D9_MARK,	PSB7_0, PSB6_1, PTK3_FN),
+	PINMUX_DATA(VIO0_D8_MARK,	PSB7_0, PSB6_1, PTK2_FN),
+
+	PINMUX_DATA(IDED5_MARK,		PSB7_1, PSB6_0, PTK7_FN),
+	PINMUX_DATA(IDED4_MARK,		PSB7_1, PSB6_0, PTK6_FN),
+	PINMUX_DATA(IDED3_MARK,		PSB7_1, PSB6_0, PTK5_FN),
+	PINMUX_DATA(IDED2_MARK,		PSB7_1, PSB6_0, PTK4_FN),
+	PINMUX_DATA(IDED1_MARK,		PSB7_1, PSB6_0, PTK3_FN),
+	PINMUX_DATA(IDED0_MARK,		PSB7_1, PSB6_0, PTK2_FN),
+
+	PINMUX_DATA(VIO0_FLD_MARK,	PTK1_FN),
+	PINMUX_DATA(VIO0_HD_MARK,	PTK0_FN),
+
+	/* PTL FN */
+	PINMUX_DATA(DV_D5_MARK,		PSB9_0, PSB8_0, PTL7_FN),
+	PINMUX_DATA(DV_D4_MARK,		PSB9_0, PSB8_0, PTL6_FN),
+	PINMUX_DATA(DV_D3_MARK,		PSE7_0, PSE6_0, PTL5_FN),
+	PINMUX_DATA(DV_D2_MARK,		PSC9_0, PSC8_0, PTL4_FN),
+	PINMUX_DATA(DV_D1_MARK,		PSC9_0, PSC8_0, PTL3_FN),
+	PINMUX_DATA(DV_D0_MARK,		PSC9_0, PSC8_0, PTL2_FN),
+	PINMUX_DATA(DV_D15_MARK,	PSD4_0,         PTL1_FN),
+	PINMUX_DATA(DV_D14_MARK,	PSE5_0, PSE4_0, PTL0_FN),
+
+	PINMUX_DATA(SCIF3_V_SCK_MARK,	PSB9_0, PSB8_1, PTL7_FN),
+	PINMUX_DATA(SCIF3_V_RXD_MARK,	PSB9_0, PSB8_1, PTL6_FN),
+	PINMUX_DATA(SCIF3_V_TXD_MARK,	PSE7_0, PSE6_1, PTL5_FN),
+	PINMUX_DATA(SCIF1_SCK_MARK,	PSC9_0, PSC8_1, PTL4_FN),
+	PINMUX_DATA(SCIF1_RXD_MARK,	PSC9_0, PSC8_1, PTL3_FN),
+	PINMUX_DATA(SCIF1_TXD_MARK,	PSC9_0, PSC8_1, PTL2_FN),
+
+	PINMUX_DATA(RMII_RXD0_MARK,	PSB9_1, PSB8_0, PTL7_FN),
+	PINMUX_DATA(RMII_RXD1_MARK,	PSB9_1, PSB8_0, PTL6_FN),
+	PINMUX_DATA(RMII_REF_CLK_MARK,	PSE7_1, PSE6_0, PTL5_FN),
+	PINMUX_DATA(RMII_TX_EN_MARK,	PSC9_1, PSC8_0, PTL4_FN),
+	PINMUX_DATA(RMII_TXD0_MARK,	PSC9_1, PSC8_0, PTL3_FN),
+	PINMUX_DATA(RMII_TXD1_MARK,	PSC9_1, PSC8_0, PTL2_FN),
+
+	PINMUX_DATA(MSIOF0_MCK_MARK,	PSE5_0, PSE4_1, PTL0_FN),
+
+	/* PTM FN */
+	PINMUX_DATA(DV_D13_MARK,	PSC13_0, PSC12_0, PTM7_FN),
+	PINMUX_DATA(DV_D12_MARK,	PSC13_0, PSC12_0, PTM6_FN),
+	PINMUX_DATA(DV_D11_MARK,	PSC13_0, PSC12_0, PTM5_FN),
+	PINMUX_DATA(DV_D10_MARK,	PSC13_0, PSC12_0, PTM4_FN),
+	PINMUX_DATA(DV_D9_MARK,		PSC11_0, PSC10_0, PTM3_FN),
+	PINMUX_DATA(DV_D8_MARK,		PSC11_0, PSC10_0, PTM2_FN),
+
+	PINMUX_DATA(MSIOF0_TSCK_MARK,	PSC13_0, PSC12_1, PTM7_FN),
+	PINMUX_DATA(MSIOF0_RXD_MARK,	PSC13_0, PSC12_1, PTM6_FN),
+	PINMUX_DATA(MSIOF0_TXD_MARK,	PSC13_0, PSC12_1, PTM5_FN),
+	PINMUX_DATA(MSIOF0_TSYNC_MARK,	PSC13_0, PSC12_1, PTM4_FN),
+	PINMUX_DATA(MSIOF0_SS1_MARK,	PSC11_0, PSC10_1, PTM3_FN),
+	PINMUX_DATA(MSIOF0_RSCK_MARK,	PSC11_1, PSC10_0, PTM3_FN),
+	PINMUX_DATA(MSIOF0_SS2_MARK,	PSC11_0, PSC10_1, PTM2_FN),
+	PINMUX_DATA(MSIOF0_RSYNC_MARK,	PSC11_1, PSC10_0, PTM2_FN),
+
+	PINMUX_DATA(LCDVCPWC_MARK,	PSA6_0, PTM1_FN),
+	PINMUX_DATA(LCDRD_MARK,		PSA7_0, PTM0_FN),
+
+	PINMUX_DATA(SCIF0_RXD_MARK,	PSA6_1, PTM1_FN),
+	PINMUX_DATA(SCIF0_SCK_MARK,	PSA7_1, PTM0_FN),
+
+	/* PTN FN */
+	PINMUX_DATA(VIO0_D1_MARK,	PTN7_FN),
+	PINMUX_DATA(VIO0_D0_MARK,	PTN6_FN),
+
+	PINMUX_DATA(DV_CLKI_MARK,	PSD11_0,          PTN5_FN),
+	PINMUX_DATA(DV_CLK_MARK,	PSD13_0, PSD12_0, PTN4_FN),
+	PINMUX_DATA(DV_VSYNC_MARK,	PSD15_0, PSD14_0, PTN3_FN),
+	PINMUX_DATA(DV_HSYNC_MARK,	PSB5_0,  PSB4_0,  PTN2_FN),
+	PINMUX_DATA(DV_D7_MARK,		PSB3_0,  PSB2_0,  PTN1_FN),
+	PINMUX_DATA(DV_D6_MARK,		PSB1_0,  PSB0_0,  PTN0_FN),
+
+	PINMUX_DATA(SCIF2_V_SCK_MARK,	PSD13_0, PSD12_1, PTN4_FN),
+	PINMUX_DATA(SCIF2_V_RXD_MARK,	PSD15_0, PSD14_1, PTN3_FN),
+	PINMUX_DATA(SCIF2_V_TXD_MARK,	PSB5_0,  PSB4_1,  PTN2_FN),
+	PINMUX_DATA(SCIF3_V_CTS_MARK,	PSB3_0,  PSB2_1,  PTN1_FN),
+	PINMUX_DATA(SCIF3_V_RTS_MARK,	PSB1_0,  PSB0_1,  PTN0_FN),
+
+	PINMUX_DATA(RMII_RX_ER_MARK,	PSB3_1, PSB2_0, PTN1_FN),
+	PINMUX_DATA(RMII_CRS_DV_MARK,	PSB1_1, PSB0_0, PTN0_FN),
+
+	/* PTQ FN */
+	PINMUX_DATA(D7_MARK, PTQ7_FN),
+	PINMUX_DATA(D6_MARK, PTQ6_FN),
+	PINMUX_DATA(D5_MARK, PTQ5_FN),
+	PINMUX_DATA(D4_MARK, PTQ4_FN),
+	PINMUX_DATA(D3_MARK, PTQ3_FN),
+	PINMUX_DATA(D2_MARK, PTQ2_FN),
+	PINMUX_DATA(D1_MARK, PTQ1_FN),
+	PINMUX_DATA(D0_MARK, PTQ0_FN),
+
+	/* PTR FN */
+	PINMUX_DATA(CS6B_CE1B_MARK,	                PTR7_FN),
+	PINMUX_DATA(CS6A_CE2B_MARK,	                PTR6_FN),
+	PINMUX_DATA(CS5B_CE1A_MARK,	                PTR5_FN),
+	PINMUX_DATA(CS5A_CE2A_MARK,	                PTR4_FN),
+	PINMUX_DATA(IOIS16_MARK,	PSA5_0,         PTR3_FN),
+	PINMUX_DATA(WAIT_MARK,		                PTR2_FN),
+	PINMUX_DATA(WE3_ICIOWR_MARK,	PSA1_0, PSA0_0, PTR1_FN),
+	PINMUX_DATA(WE2_ICIORD_MARK,	PSD1_0, PSD0_0, PTR0_FN),
+
+	PINMUX_DATA(LCDLCLK_MARK,	PSA5_1,         PTR3_FN),
+
+	PINMUX_DATA(IDEA2_MARK,		PSD1_1, PSD0_0, PTR0_FN),
+
+	PINMUX_DATA(TPUTO3_MARK,	PSA1_0, PSA0_1, PTR1_FN),
+	PINMUX_DATA(TPUTI3_MARK,	PSA1_1, PSA0_0, PTR1_FN),
+	PINMUX_DATA(TPUTO2_MARK,	PSD1_0, PSD0_1, PTR0_FN),
+
+	/* PTS FN */
+	PINMUX_DATA(VIO_CKO_MARK,	PTS6_FN),
+
+	PINMUX_DATA(TPUTI2_MARK,	PSE9_0, PSE8_1, PTS5_FN),
+
+	PINMUX_DATA(IDEIORDY_MARK,	PSE9_1, PSE8_0, PTS5_FN),
+
+	PINMUX_DATA(VIO1_FLD_MARK,	PSE9_0, PSE8_0, PTS5_FN),
+	PINMUX_DATA(VIO1_HD_MARK,	PSA10_0,        PTS4_FN),
+	PINMUX_DATA(VIO1_VD_MARK,	PSA9_0,         PTS3_FN),
+	PINMUX_DATA(VIO1_CLK_MARK,	PSA9_0,         PTS2_FN),
+	PINMUX_DATA(VIO1_D7_MARK,	PSB7_0, PSB6_0, PTS1_FN),
+	PINMUX_DATA(VIO1_D6_MARK,	PSB7_0, PSB6_0, PTS0_FN),
+
+	PINMUX_DATA(SCIF5_SCK_MARK,	PSA10_1, PTS4_FN),
+	PINMUX_DATA(SCIF5_RXD_MARK,	PSA9_1,  PTS3_FN),
+	PINMUX_DATA(SCIF5_TXD_MARK,	PSA9_1,  PTS2_FN),
+
+	PINMUX_DATA(VIO0_D15_MARK,	PSB7_0, PSB6_1, PTS1_FN),
+	PINMUX_DATA(VIO0_D14_MARK,	PSB7_0, PSB6_1, PTS0_FN),
+
+	PINMUX_DATA(IDED7_MARK,		PSB7_1, PSB6_0, PTS1_FN),
+	PINMUX_DATA(IDED6_MARK,		PSB7_1, PSB6_0, PTS0_FN),
+
+	/* PTT FN */
+	PINMUX_DATA(D15_MARK, PTT7_FN),
+	PINMUX_DATA(D14_MARK, PTT6_FN),
+	PINMUX_DATA(D13_MARK, PTT5_FN),
+	PINMUX_DATA(D12_MARK, PTT4_FN),
+	PINMUX_DATA(D11_MARK, PTT3_FN),
+	PINMUX_DATA(D10_MARK, PTT2_FN),
+	PINMUX_DATA(D9_MARK,  PTT1_FN),
+	PINMUX_DATA(D8_MARK,  PTT0_FN),
+
+	/* PTU FN */
+	PINMUX_DATA(DMAC_DACK0_MARK, PTU7_FN),
+	PINMUX_DATA(DMAC_DREQ0_MARK, PTU6_FN),
+
+	PINMUX_DATA(FSIOASD_MARK,	PSE1_0, PTU5_FN),
+	PINMUX_DATA(FSIIABCK_MARK,	PSE1_0, PTU4_FN),
+	PINMUX_DATA(FSIIALRCK_MARK,	PSE1_0, PTU3_FN),
+	PINMUX_DATA(FSIOABCK_MARK,	PSE1_0, PTU2_FN),
+	PINMUX_DATA(FSIOALRCK_MARK,	PSE1_0, PTU1_FN),
+	PINMUX_DATA(CLKAUDIOAO_MARK,	PSE0_0, PTU0_FN),
+
+	/* PTV FN */
+	PINMUX_DATA(FSIIBSD_MARK,	PSD7_0,  PSD6_0,  PTV7_FN),
+	PINMUX_DATA(FSIOBSD_MARK,	PSD7_0,  PSD6_0,  PTV6_FN),
+	PINMUX_DATA(FSIIBBCK_MARK,	PSC15_0, PSC14_0, PTV5_FN),
+	PINMUX_DATA(FSIIBLRCK_MARK,	PSC15_0, PSC14_0, PTV4_FN),
+	PINMUX_DATA(FSIOBBCK_MARK,	PSC15_0, PSC14_0, PTV3_FN),
+	PINMUX_DATA(FSIOBLRCK_MARK,	PSC15_0, PSC14_0, PTV2_FN),
+	PINMUX_DATA(CLKAUDIOBO_MARK,	PSE3_0,  PSE2_0,  PTV1_FN),
+	PINMUX_DATA(FSIIASD_MARK,	PSE10_0,          PTV0_FN),
+
+	PINMUX_DATA(MSIOF1_SS2_MARK,	PSD7_0,  PSD6_1,  PTV7_FN),
+	PINMUX_DATA(MSIOF1_RSYNC_MARK,	PSD7_1,  PSD6_0,  PTV7_FN),
+	PINMUX_DATA(MSIOF1_SS1_MARK,	PSD7_0,  PSD6_1,  PTV6_FN),
+	PINMUX_DATA(MSIOF1_RSCK_MARK,	PSD7_1,  PSD6_0,  PTV6_FN),
+	PINMUX_DATA(MSIOF1_RXD_MARK,	PSC15_0, PSC14_1, PTV5_FN),
+	PINMUX_DATA(MSIOF1_TSYNC_MARK,	PSC15_0, PSC14_1, PTV4_FN),
+	PINMUX_DATA(MSIOF1_TSCK_MARK,	PSC15_0, PSC14_1, PTV3_FN),
+	PINMUX_DATA(MSIOF1_TXD_MARK,	PSC15_0, PSC14_1, PTV2_FN),
+	PINMUX_DATA(MSIOF1_MCK_MARK,	PSE3_0,  PSE2_1,  PTV1_FN),
+
+	/* PTW FN */
+	PINMUX_DATA(MMC_D7_MARK,	PSE13_0, PSE12_0, PTW7_FN),
+	PINMUX_DATA(MMC_D6_MARK,	PSE13_0, PSE12_0, PTW6_FN),
+	PINMUX_DATA(MMC_D5_MARK,	PSE13_0, PSE12_0, PTW5_FN),
+	PINMUX_DATA(MMC_D4_MARK,	PSE13_0, PSE12_0, PTW4_FN),
+	PINMUX_DATA(MMC_D3_MARK,	PSA13_0,          PTW3_FN),
+	PINMUX_DATA(MMC_D2_MARK,	PSA13_0,          PTW2_FN),
+	PINMUX_DATA(MMC_D1_MARK,	PSA13_0,          PTW1_FN),
+	PINMUX_DATA(MMC_D0_MARK,	PSA13_0,          PTW0_FN),
+
+	PINMUX_DATA(SDHI1CD_MARK,	PSE13_0, PSE12_1, PTW7_FN),
+	PINMUX_DATA(SDHI1WP_MARK,	PSE13_0, PSE12_1, PTW6_FN),
+	PINMUX_DATA(SDHI1D3_MARK,	PSE13_0, PSE12_1, PTW5_FN),
+	PINMUX_DATA(SDHI1D2_MARK,	PSE13_0, PSE12_1, PTW4_FN),
+	PINMUX_DATA(SDHI1D1_MARK,	PSA13_1,          PTW3_FN),
+	PINMUX_DATA(SDHI1D0_MARK,	PSA13_1,          PTW2_FN),
+	PINMUX_DATA(SDHI1CMD_MARK,	PSA13_1,          PTW1_FN),
+	PINMUX_DATA(SDHI1CLK_MARK,	PSA13_1,          PTW0_FN),
+
+	PINMUX_DATA(IODACK_MARK,	PSE13_1, PSE12_0, PTW7_FN),
+	PINMUX_DATA(IDERST_MARK,	PSE13_1, PSE12_0, PTW6_FN),
+	PINMUX_DATA(EXBUF_ENB_MARK,	PSE13_1, PSE12_0, PTW5_FN),
+	PINMUX_DATA(DIRECTION_MARK,	PSE13_1, PSE12_0, PTW4_FN),
+
+	/* PTX FN */
+	PINMUX_DATA(DMAC_DACK1_MARK,	PSA12_0, PTX7_FN),
+	PINMUX_DATA(DMAC_DREQ1_MARK,	PSA12_0, PTX6_FN),
+
+	PINMUX_DATA(IRDA_OUT_MARK,	PSA12_1, PTX7_FN),
+	PINMUX_DATA(IRDA_IN_MARK,	PSA12_1, PTX6_FN),
+
+	PINMUX_DATA(TSIF_TS0_SDAT_MARK,	PSC0_0, PTX5_FN),
+	PINMUX_DATA(TSIF_TS0_SCK_MARK,	PSC1_0, PTX4_FN),
+	PINMUX_DATA(TSIF_TS0_SDEN_MARK,	PSC2_0, PTX3_FN),
+	PINMUX_DATA(TSIF_TS0_SPSYNC_MARK,       PTX2_FN),
+
+	PINMUX_DATA(LNKSTA_MARK,	PSC0_1, PTX5_FN),
+	PINMUX_DATA(MDIO_MARK,		PSC1_1, PTX4_FN),
+	PINMUX_DATA(MDC_MARK,		PSC2_1, PTX3_FN),
+
+	PINMUX_DATA(MMC_CLK_MARK, PTX1_FN),
+	PINMUX_DATA(MMC_CMD_MARK, PTX0_FN),
+
+	/* PTY FN */
+	PINMUX_DATA(SDHI0CD_MARK,  PTY7_FN),
+	PINMUX_DATA(SDHI0WP_MARK,  PTY6_FN),
+	PINMUX_DATA(SDHI0D3_MARK,  PTY5_FN),
+	PINMUX_DATA(SDHI0D2_MARK,  PTY4_FN),
+	PINMUX_DATA(SDHI0D1_MARK,  PTY3_FN),
+	PINMUX_DATA(SDHI0D0_MARK,  PTY2_FN),
+	PINMUX_DATA(SDHI0CMD_MARK, PTY1_FN),
+	PINMUX_DATA(SDHI0CLK_MARK, PTY0_FN),
+
+	/* PTZ FN */
+	PINMUX_DATA(INTC_IRQ7_MARK,	PSB10_0, PTZ7_FN),
+	PINMUX_DATA(INTC_IRQ6_MARK,	PSB11_0, PTZ6_FN),
+	PINMUX_DATA(INTC_IRQ5_MARK,	PSB12_0, PTZ5_FN),
+	PINMUX_DATA(INTC_IRQ4_MARK,	PSB13_0, PTZ4_FN),
+	PINMUX_DATA(INTC_IRQ3_MARK,	PSB14_0, PTZ3_FN),
+	PINMUX_DATA(INTC_IRQ2_MARK,	         PTZ2_FN),
+	PINMUX_DATA(INTC_IRQ1_MARK,	         PTZ1_FN),
+	PINMUX_DATA(INTC_IRQ0_MARK,	         PTZ0_FN),
+
+	PINMUX_DATA(SCIF3_I_CTS_MARK,	PSB10_1, PTZ7_FN),
+	PINMUX_DATA(SCIF3_I_RTS_MARK,	PSB11_1, PTZ6_FN),
+	PINMUX_DATA(SCIF3_I_SCK_MARK,	PSB12_1, PTZ5_FN),
+	PINMUX_DATA(SCIF3_I_RXD_MARK,	PSB13_1, PTZ4_FN),
+	PINMUX_DATA(SCIF3_I_TXD_MARK,	PSB14_1, PTZ3_FN),
+};
+
+static struct pinmux_gpio pinmux_gpios[] = {
+	/* PTA */
+	PINMUX_GPIO(GPIO_PTA7, PTA7_DATA),
+	PINMUX_GPIO(GPIO_PTA6, PTA6_DATA),
+	PINMUX_GPIO(GPIO_PTA5, PTA5_DATA),
+	PINMUX_GPIO(GPIO_PTA4, PTA4_DATA),
+	PINMUX_GPIO(GPIO_PTA3, PTA3_DATA),
+	PINMUX_GPIO(GPIO_PTA2, PTA2_DATA),
+	PINMUX_GPIO(GPIO_PTA1, PTA1_DATA),
+	PINMUX_GPIO(GPIO_PTA0, PTA0_DATA),
+
+	/* PTB */
+	PINMUX_GPIO(GPIO_PTB7, PTB7_DATA),
+	PINMUX_GPIO(GPIO_PTB6, PTB6_DATA),
+	PINMUX_GPIO(GPIO_PTB5, PTB5_DATA),
+	PINMUX_GPIO(GPIO_PTB4, PTB4_DATA),
+	PINMUX_GPIO(GPIO_PTB3, PTB3_DATA),
+	PINMUX_GPIO(GPIO_PTB2, PTB2_DATA),
+	PINMUX_GPIO(GPIO_PTB1, PTB1_DATA),
+	PINMUX_GPIO(GPIO_PTB0, PTB0_DATA),
+
+	/* PTC */
+	PINMUX_GPIO(GPIO_PTC7, PTC7_DATA),
+	PINMUX_GPIO(GPIO_PTC6, PTC6_DATA),
+	PINMUX_GPIO(GPIO_PTC5, PTC5_DATA),
+	PINMUX_GPIO(GPIO_PTC4, PTC4_DATA),
+	PINMUX_GPIO(GPIO_PTC3, PTC3_DATA),
+	PINMUX_GPIO(GPIO_PTC2, PTC2_DATA),
+	PINMUX_GPIO(GPIO_PTC1, PTC1_DATA),
+	PINMUX_GPIO(GPIO_PTC0, PTC0_DATA),
+
+	/* PTD */
+	PINMUX_GPIO(GPIO_PTD7, PTD7_DATA),
+	PINMUX_GPIO(GPIO_PTD6, PTD6_DATA),
+	PINMUX_GPIO(GPIO_PTD5, PTD5_DATA),
+	PINMUX_GPIO(GPIO_PTD4, PTD4_DATA),
+	PINMUX_GPIO(GPIO_PTD3, PTD3_DATA),
+	PINMUX_GPIO(GPIO_PTD2, PTD2_DATA),
+	PINMUX_GPIO(GPIO_PTD1, PTD1_DATA),
+	PINMUX_GPIO(GPIO_PTD0, PTD0_DATA),
+
+	/* PTE */
+	PINMUX_GPIO(GPIO_PTE7, PTE7_DATA),
+	PINMUX_GPIO(GPIO_PTE6, PTE6_DATA),
+	PINMUX_GPIO(GPIO_PTE5, PTE5_DATA),
+	PINMUX_GPIO(GPIO_PTE4, PTE4_DATA),
+	PINMUX_GPIO(GPIO_PTE3, PTE3_DATA),
+	PINMUX_GPIO(GPIO_PTE2, PTE2_DATA),
+	PINMUX_GPIO(GPIO_PTE1, PTE1_DATA),
+	PINMUX_GPIO(GPIO_PTE0, PTE0_DATA),
+
+	/* PTF */
+	PINMUX_GPIO(GPIO_PTF7, PTF7_DATA),
+	PINMUX_GPIO(GPIO_PTF6, PTF6_DATA),
+	PINMUX_GPIO(GPIO_PTF5, PTF5_DATA),
+	PINMUX_GPIO(GPIO_PTF4, PTF4_DATA),
+	PINMUX_GPIO(GPIO_PTF3, PTF3_DATA),
+	PINMUX_GPIO(GPIO_PTF2, PTF2_DATA),
+	PINMUX_GPIO(GPIO_PTF1, PTF1_DATA),
+	PINMUX_GPIO(GPIO_PTF0, PTF0_DATA),
+
+	/* PTG */
+	PINMUX_GPIO(GPIO_PTG5, PTG5_DATA),
+	PINMUX_GPIO(GPIO_PTG4, PTG4_DATA),
+	PINMUX_GPIO(GPIO_PTG3, PTG3_DATA),
+	PINMUX_GPIO(GPIO_PTG2, PTG2_DATA),
+	PINMUX_GPIO(GPIO_PTG1, PTG1_DATA),
+	PINMUX_GPIO(GPIO_PTG0, PTG0_DATA),
+
+	/* PTH */
+	PINMUX_GPIO(GPIO_PTH7, PTH7_DATA),
+	PINMUX_GPIO(GPIO_PTH6, PTH6_DATA),
+	PINMUX_GPIO(GPIO_PTH5, PTH5_DATA),
+	PINMUX_GPIO(GPIO_PTH4, PTH4_DATA),
+	PINMUX_GPIO(GPIO_PTH3, PTH3_DATA),
+	PINMUX_GPIO(GPIO_PTH2, PTH2_DATA),
+	PINMUX_GPIO(GPIO_PTH1, PTH1_DATA),
+	PINMUX_GPIO(GPIO_PTH0, PTH0_DATA),
+
+	/* PTJ */
+	PINMUX_GPIO(GPIO_PTJ7, PTJ7_DATA),
+	PINMUX_GPIO(GPIO_PTJ6, PTJ6_DATA),
+	PINMUX_GPIO(GPIO_PTJ5, PTJ5_DATA),
+	PINMUX_GPIO(GPIO_PTJ3, PTJ3_DATA),
+	PINMUX_GPIO(GPIO_PTJ2, PTJ2_DATA),
+	PINMUX_GPIO(GPIO_PTJ1, PTJ1_DATA),
+	PINMUX_GPIO(GPIO_PTJ0, PTJ0_DATA),
+
+	/* PTK */
+	PINMUX_GPIO(GPIO_PTK7, PTK7_DATA),
+	PINMUX_GPIO(GPIO_PTK6, PTK6_DATA),
+	PINMUX_GPIO(GPIO_PTK5, PTK5_DATA),
+	PINMUX_GPIO(GPIO_PTK4, PTK4_DATA),
+	PINMUX_GPIO(GPIO_PTK3, PTK3_DATA),
+	PINMUX_GPIO(GPIO_PTK2, PTK2_DATA),
+	PINMUX_GPIO(GPIO_PTK1, PTK1_DATA),
+	PINMUX_GPIO(GPIO_PTK0, PTK0_DATA),
+
+	/* PTL */
+	PINMUX_GPIO(GPIO_PTL7, PTL7_DATA),
+	PINMUX_GPIO(GPIO_PTL6, PTL6_DATA),
+	PINMUX_GPIO(GPIO_PTL5, PTL5_DATA),
+	PINMUX_GPIO(GPIO_PTL4, PTL4_DATA),
+	PINMUX_GPIO(GPIO_PTL3, PTL3_DATA),
+	PINMUX_GPIO(GPIO_PTL2, PTL2_DATA),
+	PINMUX_GPIO(GPIO_PTL1, PTL1_DATA),
+	PINMUX_GPIO(GPIO_PTL0, PTL0_DATA),
+
+	/* PTM */
+	PINMUX_GPIO(GPIO_PTM7, PTM7_DATA),
+	PINMUX_GPIO(GPIO_PTM6, PTM6_DATA),
+	PINMUX_GPIO(GPIO_PTM5, PTM5_DATA),
+	PINMUX_GPIO(GPIO_PTM4, PTM4_DATA),
+	PINMUX_GPIO(GPIO_PTM3, PTM3_DATA),
+	PINMUX_GPIO(GPIO_PTM2, PTM2_DATA),
+	PINMUX_GPIO(GPIO_PTM1, PTM1_DATA),
+	PINMUX_GPIO(GPIO_PTM0, PTM0_DATA),
+
+	/* PTN */
+	PINMUX_GPIO(GPIO_PTN7, PTN7_DATA),
+	PINMUX_GPIO(GPIO_PTN6, PTN6_DATA),
+	PINMUX_GPIO(GPIO_PTN5, PTN5_DATA),
+	PINMUX_GPIO(GPIO_PTN4, PTN4_DATA),
+	PINMUX_GPIO(GPIO_PTN3, PTN3_DATA),
+	PINMUX_GPIO(GPIO_PTN2, PTN2_DATA),
+	PINMUX_GPIO(GPIO_PTN1, PTN1_DATA),
+	PINMUX_GPIO(GPIO_PTN0, PTN0_DATA),
+
+	/* PTQ */
+	PINMUX_GPIO(GPIO_PTQ7, PTQ7_DATA),
+	PINMUX_GPIO(GPIO_PTQ6, PTQ6_DATA),
+	PINMUX_GPIO(GPIO_PTQ5, PTQ5_DATA),
+	PINMUX_GPIO(GPIO_PTQ4, PTQ4_DATA),
+	PINMUX_GPIO(GPIO_PTQ3, PTQ3_DATA),
+	PINMUX_GPIO(GPIO_PTQ2, PTQ2_DATA),
+	PINMUX_GPIO(GPIO_PTQ1, PTQ1_DATA),
+	PINMUX_GPIO(GPIO_PTQ0, PTQ0_DATA),
+
+	/* PTR */
+	PINMUX_GPIO(GPIO_PTR7, PTR7_DATA),
+	PINMUX_GPIO(GPIO_PTR6, PTR6_DATA),
+	PINMUX_GPIO(GPIO_PTR5, PTR5_DATA),
+	PINMUX_GPIO(GPIO_PTR4, PTR4_DATA),
+	PINMUX_GPIO(GPIO_PTR3, PTR3_DATA),
+	PINMUX_GPIO(GPIO_PTR2, PTR2_DATA),
+	PINMUX_GPIO(GPIO_PTR1, PTR1_DATA),
+	PINMUX_GPIO(GPIO_PTR0, PTR0_DATA),
+
+	/* PTS */
+	PINMUX_GPIO(GPIO_PTS6, PTS6_DATA),
+	PINMUX_GPIO(GPIO_PTS5, PTS5_DATA),
+	PINMUX_GPIO(GPIO_PTS4, PTS4_DATA),
+	PINMUX_GPIO(GPIO_PTS3, PTS3_DATA),
+	PINMUX_GPIO(GPIO_PTS2, PTS2_DATA),
+	PINMUX_GPIO(GPIO_PTS1, PTS1_DATA),
+	PINMUX_GPIO(GPIO_PTS0, PTS0_DATA),
+
+	/* PTT */
+	PINMUX_GPIO(GPIO_PTT7, PTT7_DATA),
+	PINMUX_GPIO(GPIO_PTT6, PTT6_DATA),
+	PINMUX_GPIO(GPIO_PTT5, PTT5_DATA),
+	PINMUX_GPIO(GPIO_PTT4, PTT4_DATA),
+	PINMUX_GPIO(GPIO_PTT3, PTT3_DATA),
+	PINMUX_GPIO(GPIO_PTT2, PTT2_DATA),
+	PINMUX_GPIO(GPIO_PTT1, PTT1_DATA),
+	PINMUX_GPIO(GPIO_PTT0, PTT0_DATA),
+
+	/* PTU */
+	PINMUX_GPIO(GPIO_PTU7, PTU7_DATA),
+	PINMUX_GPIO(GPIO_PTU6, PTU6_DATA),
+	PINMUX_GPIO(GPIO_PTU5, PTU5_DATA),
+	PINMUX_GPIO(GPIO_PTU4, PTU4_DATA),
+	PINMUX_GPIO(GPIO_PTU3, PTU3_DATA),
+	PINMUX_GPIO(GPIO_PTU2, PTU2_DATA),
+	PINMUX_GPIO(GPIO_PTU1, PTU1_DATA),
+	PINMUX_GPIO(GPIO_PTU0, PTU0_DATA),
+
+	/* PTV */
+	PINMUX_GPIO(GPIO_PTV7, PTV7_DATA),
+	PINMUX_GPIO(GPIO_PTV6, PTV6_DATA),
+	PINMUX_GPIO(GPIO_PTV5, PTV5_DATA),
+	PINMUX_GPIO(GPIO_PTV4, PTV4_DATA),
+	PINMUX_GPIO(GPIO_PTV3, PTV3_DATA),
+	PINMUX_GPIO(GPIO_PTV2, PTV2_DATA),
+	PINMUX_GPIO(GPIO_PTV1, PTV1_DATA),
+	PINMUX_GPIO(GPIO_PTV0, PTV0_DATA),
+
+	/* PTW */
+	PINMUX_GPIO(GPIO_PTW7, PTW7_DATA),
+	PINMUX_GPIO(GPIO_PTW6, PTW6_DATA),
+	PINMUX_GPIO(GPIO_PTW5, PTW5_DATA),
+	PINMUX_GPIO(GPIO_PTW4, PTW4_DATA),
+	PINMUX_GPIO(GPIO_PTW3, PTW3_DATA),
+	PINMUX_GPIO(GPIO_PTW2, PTW2_DATA),
+	PINMUX_GPIO(GPIO_PTW1, PTW1_DATA),
+	PINMUX_GPIO(GPIO_PTW0, PTW0_DATA),
+
+	/* PTX */
+	PINMUX_GPIO(GPIO_PTX7, PTX7_DATA),
+	PINMUX_GPIO(GPIO_PTX6, PTX6_DATA),
+	PINMUX_GPIO(GPIO_PTX5, PTX5_DATA),
+	PINMUX_GPIO(GPIO_PTX4, PTX4_DATA),
+	PINMUX_GPIO(GPIO_PTX3, PTX3_DATA),
+	PINMUX_GPIO(GPIO_PTX2, PTX2_DATA),
+	PINMUX_GPIO(GPIO_PTX1, PTX1_DATA),
+	PINMUX_GPIO(GPIO_PTX0, PTX0_DATA),
+
+	/* PTY */
+	PINMUX_GPIO(GPIO_PTY7, PTY7_DATA),
+	PINMUX_GPIO(GPIO_PTY6, PTY6_DATA),
+	PINMUX_GPIO(GPIO_PTY5, PTY5_DATA),
+	PINMUX_GPIO(GPIO_PTY4, PTY4_DATA),
+	PINMUX_GPIO(GPIO_PTY3, PTY3_DATA),
+	PINMUX_GPIO(GPIO_PTY2, PTY2_DATA),
+	PINMUX_GPIO(GPIO_PTY1, PTY1_DATA),
+	PINMUX_GPIO(GPIO_PTY0, PTY0_DATA),
+
+	/* PTZ */
+	PINMUX_GPIO(GPIO_PTZ7, PTZ7_DATA),
+	PINMUX_GPIO(GPIO_PTZ6, PTZ6_DATA),
+	PINMUX_GPIO(GPIO_PTZ5, PTZ5_DATA),
+	PINMUX_GPIO(GPIO_PTZ4, PTZ4_DATA),
+	PINMUX_GPIO(GPIO_PTZ3, PTZ3_DATA),
+	PINMUX_GPIO(GPIO_PTZ2, PTZ2_DATA),
+	PINMUX_GPIO(GPIO_PTZ1, PTZ1_DATA),
+	PINMUX_GPIO(GPIO_PTZ0, PTZ0_DATA),
+
+	/* BSC */
+	PINMUX_GPIO(GPIO_FN_D31,	D31_MARK),
+	PINMUX_GPIO(GPIO_FN_D30,	D30_MARK),
+	PINMUX_GPIO(GPIO_FN_D29,	D29_MARK),
+	PINMUX_GPIO(GPIO_FN_D28,	D28_MARK),
+	PINMUX_GPIO(GPIO_FN_D27,	D27_MARK),
+	PINMUX_GPIO(GPIO_FN_D26,	D26_MARK),
+	PINMUX_GPIO(GPIO_FN_D25,	D25_MARK),
+	PINMUX_GPIO(GPIO_FN_D24,	D24_MARK),
+	PINMUX_GPIO(GPIO_FN_D23,	D23_MARK),
+	PINMUX_GPIO(GPIO_FN_D22,	D22_MARK),
+	PINMUX_GPIO(GPIO_FN_D21,	D21_MARK),
+	PINMUX_GPIO(GPIO_FN_D20,	D20_MARK),
+	PINMUX_GPIO(GPIO_FN_D19,	D19_MARK),
+	PINMUX_GPIO(GPIO_FN_D18,	D18_MARK),
+	PINMUX_GPIO(GPIO_FN_D17,	D17_MARK),
+	PINMUX_GPIO(GPIO_FN_D16,	D16_MARK),
+	PINMUX_GPIO(GPIO_FN_D15,	D15_MARK),
+	PINMUX_GPIO(GPIO_FN_D14,	D14_MARK),
+	PINMUX_GPIO(GPIO_FN_D13,	D13_MARK),
+	PINMUX_GPIO(GPIO_FN_D12,	D12_MARK),
+	PINMUX_GPIO(GPIO_FN_D11,	D11_MARK),
+	PINMUX_GPIO(GPIO_FN_D10,	D10_MARK),
+	PINMUX_GPIO(GPIO_FN_D9,		D9_MARK),
+	PINMUX_GPIO(GPIO_FN_D8,		D8_MARK),
+	PINMUX_GPIO(GPIO_FN_D7,		D7_MARK),
+	PINMUX_GPIO(GPIO_FN_D6,		D6_MARK),
+	PINMUX_GPIO(GPIO_FN_D5,		D5_MARK),
+	PINMUX_GPIO(GPIO_FN_D4,		D4_MARK),
+	PINMUX_GPIO(GPIO_FN_D3,		D3_MARK),
+	PINMUX_GPIO(GPIO_FN_D2,		D2_MARK),
+	PINMUX_GPIO(GPIO_FN_D1,		D1_MARK),
+	PINMUX_GPIO(GPIO_FN_D0,		D0_MARK),
+	PINMUX_GPIO(GPIO_FN_A25,	A25_MARK),
+	PINMUX_GPIO(GPIO_FN_A24,	A24_MARK),
+	PINMUX_GPIO(GPIO_FN_A23,	A23_MARK),
+	PINMUX_GPIO(GPIO_FN_A22,	A22_MARK),
+	PINMUX_GPIO(GPIO_FN_CS6B_CE1B,	CS6B_CE1B_MARK),
+	PINMUX_GPIO(GPIO_FN_CS6A_CE2B,	CS6A_CE2B_MARK),
+	PINMUX_GPIO(GPIO_FN_CS5B_CE1A,	CS5B_CE1A_MARK),
+	PINMUX_GPIO(GPIO_FN_CS5A_CE2A,	CS5A_CE2A_MARK),
+	PINMUX_GPIO(GPIO_FN_WE3_ICIOWR,	WE3_ICIOWR_MARK),
+	PINMUX_GPIO(GPIO_FN_WE2_ICIORD,	WE2_ICIORD_MARK),
+	PINMUX_GPIO(GPIO_FN_IOIS16,	IOIS16_MARK),
+	PINMUX_GPIO(GPIO_FN_WAIT,	WAIT_MARK),
+	PINMUX_GPIO(GPIO_FN_BS,		BS_MARK),
+
+	/* KEYSC */
+	PINMUX_GPIO(GPIO_FN_KEYOUT5_IN5,	KEYOUT5_IN5_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYOUT4_IN6,	KEYOUT4_IN6_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYIN4,		KEYIN4_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYIN3,		KEYIN3_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYIN2,		KEYIN2_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYIN1,		KEYIN1_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYIN0,		KEYIN0_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYOUT3,		KEYOUT3_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYOUT2,		KEYOUT2_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYOUT1,		KEYOUT1_MARK),
+	PINMUX_GPIO(GPIO_FN_KEYOUT0,		KEYOUT0_MARK),
+
+	/* ATAPI */
+	PINMUX_GPIO(GPIO_FN_IDED15,	IDED15_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED14,	IDED14_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED13,	IDED13_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED12,	IDED12_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED11,	IDED11_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED10,	IDED10_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED9,	IDED9_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED8,	IDED8_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED7,	IDED7_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED6,	IDED6_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED5,	IDED5_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED4,	IDED4_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED3,	IDED3_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED2,	IDED2_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED1,	IDED1_MARK),
+	PINMUX_GPIO(GPIO_FN_IDED0,	IDED0_MARK),
+	PINMUX_GPIO(GPIO_FN_IDEA2,	IDEA2_MARK),
+	PINMUX_GPIO(GPIO_FN_IDEA1,	IDEA1_MARK),
+	PINMUX_GPIO(GPIO_FN_IDEA0,	IDEA0_MARK),
+	PINMUX_GPIO(GPIO_FN_IDEIOWR,	IDEIOWR_MARK),
+	PINMUX_GPIO(GPIO_FN_IODREQ,	IODREQ_MARK),
+	PINMUX_GPIO(GPIO_FN_IDECS0,	IDECS0_MARK),
+	PINMUX_GPIO(GPIO_FN_IDECS1,	IDECS1_MARK),
+	PINMUX_GPIO(GPIO_FN_IDEIORD,	IDEIORD_MARK),
+	PINMUX_GPIO(GPIO_FN_DIRECTION,	DIRECTION_MARK),
+	PINMUX_GPIO(GPIO_FN_EXBUF_ENB,	EXBUF_ENB_MARK),
+	PINMUX_GPIO(GPIO_FN_IDERST,	IDERST_MARK),
+	PINMUX_GPIO(GPIO_FN_IODACK,	IODACK_MARK),
+	PINMUX_GPIO(GPIO_FN_IDEINT,	IDEINT_MARK),
+	PINMUX_GPIO(GPIO_FN_IDEIORDY,	IDEIORDY_MARK),
+
+	/* TPU */
+	PINMUX_GPIO(GPIO_FN_TPUTO3,	TPUTO3_MARK),
+	PINMUX_GPIO(GPIO_FN_TPUTO2,	TPUTO2_MARK),
+	PINMUX_GPIO(GPIO_FN_TPUTO1,	TPUTO1_MARK),
+	PINMUX_GPIO(GPIO_FN_TPUTO0,	TPUTO0_MARK),
+	PINMUX_GPIO(GPIO_FN_TPUTI3,	TPUTI3_MARK),
+	PINMUX_GPIO(GPIO_FN_TPUTI2,	TPUTI2_MARK),
+
+	/* LCDC */
+	PINMUX_GPIO(GPIO_FN_LCDD23,	LCDD23_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD22,	LCDD22_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD21,	LCDD21_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD20,	LCDD20_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD19,	LCDD19_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD18,	LCDD18_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD17,	LCDD17_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD16,	LCDD16_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD15,	LCDD15_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD14,	LCDD14_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD13,	LCDD13_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD12,	LCDD12_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD11,	LCDD11_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD10,	LCDD10_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD9,	LCDD9_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD8,	LCDD8_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD7,	LCDD7_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD6,	LCDD6_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD5,	LCDD5_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD4,	LCDD4_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD3,	LCDD3_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD2,	LCDD2_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD1,	LCDD1_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDD0,	LCDD0_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDVSYN,	LCDVSYN_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDDISP,	LCDDISP_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDRS,	LCDRS_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDHSYN,	LCDHSYN_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDCS,	LCDCS_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDDON,	LCDDON_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDDCK,	LCDDCK_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDWR,	LCDWR_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDVEPWC,	LCDVEPWC_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDVCPWC,	LCDVCPWC_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDRD,	LCDRD_MARK),
+	PINMUX_GPIO(GPIO_FN_LCDLCLK,	LCDLCLK_MARK),
+
+	/* SCIF0 */
+	PINMUX_GPIO(GPIO_FN_SCIF0_TXD,	SCIF0_TXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF0_RXD,	SCIF0_RXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF0_SCK,	SCIF0_SCK_MARK),
+
+	/* SCIF1 */
+	PINMUX_GPIO(GPIO_FN_SCIF1_SCK,	SCIF1_SCK_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF1_RXD,	SCIF1_RXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF1_TXD,	SCIF1_TXD_MARK),
+
+	/* SCIF2 */
+	PINMUX_GPIO(GPIO_FN_SCIF2_L_TXD,	SCIF2_L_TXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF2_L_SCK,	SCIF2_L_SCK_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF2_L_RXD,	SCIF2_L_RXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF2_V_TXD,	SCIF2_V_TXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF2_V_SCK,	SCIF2_V_SCK_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF2_V_RXD,	SCIF2_V_RXD_MARK),
+
+	/* SCIF3 */
+	PINMUX_GPIO(GPIO_FN_SCIF3_V_SCK,	SCIF3_V_SCK_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF3_V_RXD,	SCIF3_V_RXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF3_V_TXD,	SCIF3_V_TXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF3_V_CTS,	SCIF3_V_CTS_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF3_V_RTS,	SCIF3_V_RTS_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF3_I_SCK,	SCIF3_I_SCK_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF3_I_RXD,	SCIF3_I_RXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF3_I_TXD,	SCIF3_I_TXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF3_I_CTS,	SCIF3_I_CTS_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF3_I_RTS,	SCIF3_I_RTS_MARK),
+
+	/* SCIF4 */
+	PINMUX_GPIO(GPIO_FN_SCIF4_SCK,	SCIF4_SCK_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF4_RXD,	SCIF4_RXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF4_TXD,	SCIF4_TXD_MARK),
+
+	/* SCIF5 */
+	PINMUX_GPIO(GPIO_FN_SCIF5_SCK,	SCIF5_SCK_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF5_RXD,	SCIF5_RXD_MARK),
+	PINMUX_GPIO(GPIO_FN_SCIF5_TXD,	SCIF5_TXD_MARK),
+
+	/* FSI */
+	PINMUX_GPIO(GPIO_FN_FSIMCKB,	FSIMCKB_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIMCKA,	FSIMCKA_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIOASD,	FSIOASD_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIIABCK,	FSIIABCK_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIIALRCK,	FSIIALRCK_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIOABCK,	FSIOABCK_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIOALRCK,	FSIOALRCK_MARK),
+	PINMUX_GPIO(GPIO_FN_CLKAUDIOAO,	CLKAUDIOAO_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIIBSD,	FSIIBSD_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIOBSD,	FSIOBSD_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIIBBCK,	FSIIBBCK_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIIBLRCK,	FSIIBLRCK_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIOBBCK,	FSIOBBCK_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIOBLRCK,	FSIOBLRCK_MARK),
+	PINMUX_GPIO(GPIO_FN_CLKAUDIOBO,	CLKAUDIOBO_MARK),
+	PINMUX_GPIO(GPIO_FN_FSIIASD,	FSIIASD_MARK),
+
+	/* AUD */
+	PINMUX_GPIO(GPIO_FN_AUDCK,	AUDCK_MARK),
+	PINMUX_GPIO(GPIO_FN_AUDSYNC,	AUDSYNC_MARK),
+	PINMUX_GPIO(GPIO_FN_AUDATA3,	AUDATA3_MARK),
+	PINMUX_GPIO(GPIO_FN_AUDATA2,	AUDATA2_MARK),
+	PINMUX_GPIO(GPIO_FN_AUDATA1,	AUDATA1_MARK),
+	PINMUX_GPIO(GPIO_FN_AUDATA0,	AUDATA0_MARK),
+
+	/* VIO */
+	PINMUX_GPIO(GPIO_FN_VIO_CKO,	VIO_CKO_MARK),
+
+	/* VIO0 */
+	PINMUX_GPIO(GPIO_FN_VIO0_D15,	VIO0_D15_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D14,	VIO0_D14_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D13,	VIO0_D13_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D12,	VIO0_D12_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D11,	VIO0_D11_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D10,	VIO0_D10_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D9,	VIO0_D9_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D8,	VIO0_D8_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D7,	VIO0_D7_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D6,	VIO0_D6_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D5,	VIO0_D5_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D4,	VIO0_D4_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D3,	VIO0_D3_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D2,	VIO0_D2_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D1,	VIO0_D1_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_D0,	VIO0_D0_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_VD,	VIO0_VD_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_CLK,	VIO0_CLK_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_FLD,	VIO0_FLD_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO0_HD,	VIO0_HD_MARK),
+
+	/* VIO1 */
+	PINMUX_GPIO(GPIO_FN_VIO1_D7,	VIO1_D7_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_D6,	VIO1_D6_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_D5,	VIO1_D5_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_D4,	VIO1_D4_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_D3,	VIO1_D3_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_D2,	VIO1_D2_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_D1,	VIO1_D1_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_D0,	VIO1_D0_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_FLD,	VIO1_FLD_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_HD,	VIO1_HD_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_VD,	VIO1_VD_MARK),
+	PINMUX_GPIO(GPIO_FN_VIO1_CLK,	VIO1_CLK_MARK),
+
+	/* Eth */
+	PINMUX_GPIO(GPIO_FN_RMII_RXD0,		RMII_RXD0_MARK),
+	PINMUX_GPIO(GPIO_FN_RMII_RXD1,		RMII_RXD1_MARK),
+	PINMUX_GPIO(GPIO_FN_RMII_TXD0,		RMII_TXD0_MARK),
+	PINMUX_GPIO(GPIO_FN_RMII_TXD1,		RMII_TXD1_MARK),
+	PINMUX_GPIO(GPIO_FN_RMII_REF_CLK,	RMII_REF_CLK_MARK),
+	PINMUX_GPIO(GPIO_FN_RMII_TX_EN,		RMII_TX_EN_MARK),
+	PINMUX_GPIO(GPIO_FN_RMII_RX_ER,		RMII_RX_ER_MARK),
+	PINMUX_GPIO(GPIO_FN_RMII_CRS_DV,	RMII_CRS_DV_MARK),
+	PINMUX_GPIO(GPIO_FN_LNKSTA,		LNKSTA_MARK),
+	PINMUX_GPIO(GPIO_FN_MDIO,		MDIO_MARK),
+	PINMUX_GPIO(GPIO_FN_MDC,		MDC_MARK),
+
+	/* System */
+	PINMUX_GPIO(GPIO_FN_PDSTATUS,	PDSTATUS_MARK),
+	PINMUX_GPIO(GPIO_FN_STATUS2,	STATUS2_MARK),
+	PINMUX_GPIO(GPIO_FN_STATUS0,	STATUS0_MARK),
+
+	/* VOU */
+	PINMUX_GPIO(GPIO_FN_DV_D15,	DV_D15_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D14,	DV_D14_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D13,	DV_D13_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D12,	DV_D12_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D11,	DV_D11_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D10,	DV_D10_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D9,	DV_D9_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D8,	DV_D8_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D7,	DV_D7_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D6,	DV_D6_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D5,	DV_D5_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D4,	DV_D4_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D3,	DV_D3_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D2,	DV_D2_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D1,	DV_D1_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_D0,	DV_D0_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_CLKI,	DV_CLKI_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_CLK,	DV_CLK_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_VSYNC,	DV_VSYNC_MARK),
+	PINMUX_GPIO(GPIO_FN_DV_HSYNC,	DV_HSYNC_MARK),
+
+	/* MSIOF0 */
+	PINMUX_GPIO(GPIO_FN_MSIOF0_RXD,		MSIOF0_RXD_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF0_TXD,		MSIOF0_TXD_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF0_MCK,		MSIOF0_MCK_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF0_TSCK,	MSIOF0_TSCK_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF0_SS1,		MSIOF0_SS1_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF0_SS2,		MSIOF0_SS2_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF0_TSYNC,	MSIOF0_TSYNC_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF0_RSCK,	MSIOF0_RSCK_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF0_RSYNC,	MSIOF0_RSYNC_MARK),
+
+	/* MSIOF1 */
+	PINMUX_GPIO(GPIO_FN_MSIOF1_RXD,		MSIOF1_RXD_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF1_TXD,		MSIOF1_TXD_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF1_MCK,		MSIOF1_MCK_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF1_TSCK,	MSIOF1_TSCK_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF1_SS1,		MSIOF1_SS1_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF1_SS2,		MSIOF1_SS2_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF1_TSYNC,	MSIOF1_TSYNC_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF1_RSCK,	MSIOF1_RSCK_MARK),
+	PINMUX_GPIO(GPIO_FN_MSIOF1_RSYNC,	MSIOF1_RSYNC_MARK),
+
+	/* DMAC */
+	PINMUX_GPIO(GPIO_FN_DMAC_DACK0,	DMAC_DACK0_MARK),
+	PINMUX_GPIO(GPIO_FN_DMAC_DREQ0,	DMAC_DREQ0_MARK),
+	PINMUX_GPIO(GPIO_FN_DMAC_DACK1,	DMAC_DACK1_MARK),
+	PINMUX_GPIO(GPIO_FN_DMAC_DREQ1,	DMAC_DREQ1_MARK),
+
+	/* SDHI0 */
+	PINMUX_GPIO(GPIO_FN_SDHI0CD,	SDHI0CD_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI0WP,	SDHI0WP_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI0CMD,	SDHI0CMD_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI0CLK,	SDHI0CLK_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI0D3,	SDHI0D3_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI0D2,	SDHI0D2_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI0D1,	SDHI0D1_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI0D0,	SDHI0D0_MARK),
+
+	/* SDHI1 */
+	PINMUX_GPIO(GPIO_FN_SDHI1CD,	SDHI1CD_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI1WP,	SDHI1WP_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI1CMD,	SDHI1CMD_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI1CLK,	SDHI1CLK_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI1D3,	SDHI1D3_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI1D2,	SDHI1D2_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI1D1,	SDHI1D1_MARK),
+	PINMUX_GPIO(GPIO_FN_SDHI1D0,	SDHI1D0_MARK),
+
+	/* MMC */
+	PINMUX_GPIO(GPIO_FN_MMC_D7,	MMC_D7_MARK),
+	PINMUX_GPIO(GPIO_FN_MMC_D6,	MMC_D6_MARK),
+	PINMUX_GPIO(GPIO_FN_MMC_D5,	MMC_D5_MARK),
+	PINMUX_GPIO(GPIO_FN_MMC_D4,	MMC_D4_MARK),
+	PINMUX_GPIO(GPIO_FN_MMC_D3,	MMC_D3_MARK),
+	PINMUX_GPIO(GPIO_FN_MMC_D2,	MMC_D2_MARK),
+	PINMUX_GPIO(GPIO_FN_MMC_D1,	MMC_D1_MARK),
+	PINMUX_GPIO(GPIO_FN_MMC_D0,	MMC_D0_MARK),
+	PINMUX_GPIO(GPIO_FN_MMC_CLK,	MMC_CLK_MARK),
+	PINMUX_GPIO(GPIO_FN_MMC_CMD,	MMC_CMD_MARK),
+
+	/* IrDA */
+	PINMUX_GPIO(GPIO_FN_IRDA_OUT,	IRDA_OUT_MARK),
+	PINMUX_GPIO(GPIO_FN_IRDA_IN,	IRDA_IN_MARK),
+
+	/* TSIF */
+	PINMUX_GPIO(GPIO_FN_TSIF_TS0_SDAT,	TSIF_TS0_SDAT_MARK),
+	PINMUX_GPIO(GPIO_FN_TSIF_TS0_SCK,	TSIF_TS0_SCK_MARK),
+	PINMUX_GPIO(GPIO_FN_TSIF_TS0_SDEN,	TSIF_TS0_SDEN_MARK),
+	PINMUX_GPIO(GPIO_FN_TSIF_TS0_SPSYNC,	TSIF_TS0_SPSYNC_MARK),
+
+	/* IRQ */
+	PINMUX_GPIO(GPIO_FN_INTC_IRQ7,	INTC_IRQ7_MARK),
+	PINMUX_GPIO(GPIO_FN_INTC_IRQ6,	INTC_IRQ6_MARK),
+	PINMUX_GPIO(GPIO_FN_INTC_IRQ5,	INTC_IRQ5_MARK),
+	PINMUX_GPIO(GPIO_FN_INTC_IRQ4,	INTC_IRQ4_MARK),
+	PINMUX_GPIO(GPIO_FN_INTC_IRQ3,	INTC_IRQ3_MARK),
+	PINMUX_GPIO(GPIO_FN_INTC_IRQ2,	INTC_IRQ2_MARK),
+	PINMUX_GPIO(GPIO_FN_INTC_IRQ1,	INTC_IRQ1_MARK),
+	PINMUX_GPIO(GPIO_FN_INTC_IRQ0,	INTC_IRQ0_MARK),
+ };
+
+static struct pinmux_cfg_reg pinmux_config_regs[] = {
+	{ PINMUX_CFG_REG("PACR", 0xa4050100, 16, 2) {
+		PTA7_FN, PTA7_OUT, PTA7_IN_PU, PTA7_IN,
+		PTA6_FN, PTA6_OUT, PTA6_IN_PU, PTA6_IN,
+		PTA5_FN, PTA5_OUT, PTA5_IN_PU, PTA5_IN,
+		PTA4_FN, PTA4_OUT, PTA4_IN_PU, PTA4_IN,
+		PTA3_FN, PTA3_OUT, PTA3_IN_PU, PTA3_IN,
+		PTA2_FN, PTA2_OUT, PTA2_IN_PU, PTA2_IN,
+		PTA1_FN, PTA1_OUT, PTA1_IN_PU, PTA1_IN,
+		PTA0_FN, PTA0_OUT, PTA0_IN_PU, PTA0_IN }
+	},
+	{ PINMUX_CFG_REG("PBCR", 0xa4050102, 16, 2) {
+		PTB7_FN, PTB7_OUT, PTB7_IN_PU, PTB7_IN,
+		PTB6_FN, PTB6_OUT, PTB6_IN_PU, PTB6_IN,
+		PTB5_FN, PTB5_OUT, PTB5_IN_PU, PTB5_IN,
+		PTB4_FN, PTB4_OUT, PTB4_IN_PU, PTB4_IN,
+		PTB3_FN, PTB3_OUT, PTB3_IN_PU, PTB3_IN,
+		PTB2_FN, PTB2_OUT, PTB2_IN_PU, PTB2_IN,
+		PTB1_FN, PTB1_OUT, PTB1_IN_PU, PTB1_IN,
+		PTB0_FN, PTB0_OUT, PTB0_IN_PU, PTB0_IN }
+	},
+	{ PINMUX_CFG_REG("PCCR", 0xa4050104, 16, 2) {
+		PTC7_FN, PTC7_OUT, PTC7_IN_PU, PTC7_IN,
+		PTC6_FN, PTC6_OUT, PTC6_IN_PU, PTC6_IN,
+		PTC5_FN, PTC5_OUT, PTC5_IN_PU, PTC5_IN,
+		PTC4_FN, PTC4_OUT, PTC4_IN_PU, PTC4_IN,
+		PTC3_FN, PTC3_OUT, PTC3_IN_PU, PTC3_IN,
+		PTC2_FN, PTC2_OUT, PTC2_IN_PU, PTC2_IN,
+		PTC1_FN, PTC1_OUT, PTC1_IN_PU, PTC1_IN,
+		PTC0_FN, PTC0_OUT, PTC0_IN_PU, PTC0_IN }
+	},
+	{ PINMUX_CFG_REG("PDCR", 0xa4050106, 16, 2) {
+		PTD7_FN, PTD7_OUT, PTD7_IN_PU, PTD7_IN,
+		PTD6_FN, PTD6_OUT, PTD6_IN_PU, PTD6_IN,
+		PTD5_FN, PTD5_OUT, PTD5_IN_PU, PTD5_IN,
+		PTD4_FN, PTD4_OUT, PTD4_IN_PU, PTD4_IN,
+		PTD3_FN, PTD3_OUT, PTD3_IN_PU, PTD3_IN,
+		PTD2_FN, PTD2_OUT, PTD2_IN_PU, PTD2_IN,
+		PTD1_FN, PTD1_OUT, PTD1_IN_PU, PTD1_IN,
+		PTD0_FN, PTD0_OUT, PTD0_IN_PU, PTD0_IN }
+	},
+	{ PINMUX_CFG_REG("PECR", 0xa4050108, 16, 2) {
+		PTE7_FN, PTE7_OUT, PTE7_IN_PU, PTE7_IN,
+		PTE6_FN, PTE6_OUT, PTE6_IN_PU, PTE6_IN,
+		PTE5_FN, PTE5_OUT, PTE5_IN_PU, PTE5_IN,
+		PTE4_FN, PTE4_OUT, PTE4_IN_PU, PTE4_IN,
+		PTE3_FN, PTE3_OUT, PTE3_IN_PU, PTE3_IN,
+		PTE2_FN, PTE2_OUT, PTE2_IN_PU, PTE2_IN,
+		PTE1_FN, PTE1_OUT, PTE1_IN_PU, PTE1_IN,
+		PTE0_FN, PTE0_OUT, PTE0_IN_PU, PTE0_IN }
+	},
+	{ PINMUX_CFG_REG("PFCR", 0xa405010a, 16, 2) {
+		PTF7_FN, PTF7_OUT, PTF7_IN_PU, PTF7_IN,
+		PTF6_FN, PTF6_OUT, PTF6_IN_PU, PTF6_IN,
+		PTF5_FN, PTF5_OUT, PTF5_IN_PU, PTF5_IN,
+		PTF4_FN, PTF4_OUT, PTF4_IN_PU, PTF4_IN,
+		PTF3_FN, PTF3_OUT, PTF3_IN_PU, PTF3_IN,
+		PTF2_FN, PTF2_OUT, PTF2_IN_PU, PTF2_IN,
+		PTF1_FN, PTF1_OUT, PTF1_IN_PU, PTF1_IN,
+		PTF0_FN, PTF0_OUT, PTF0_IN_PU, PTF0_IN }
+	},
+	{ PINMUX_CFG_REG("PGCR", 0xa405010c, 16, 2) {
+		0, 0, 0, 0,
+		0, 0, 0, 0,
+		PTG5_FN, PTG5_OUT, 0, 0,
+		PTG4_FN, PTG4_OUT, 0, 0,
+		PTG3_FN, PTG3_OUT, 0, 0,
+		PTG2_FN, PTG2_OUT, 0, 0,
+		PTG1_FN, PTG1_OUT, 0, 0,
+		PTG0_FN, PTG0_OUT, 0, 0 }
+	},
+	{ PINMUX_CFG_REG("PHCR", 0xa405010e, 16, 2) {
+		PTH7_FN, PTH7_OUT, PTH7_IN_PU, PTH7_IN,
+		PTH6_FN, PTH6_OUT, PTH6_IN_PU, PTH6_IN,
+		PTH5_FN, PTH5_OUT, PTH5_IN_PU, PTH5_IN,
+		PTH4_FN, PTH4_OUT, PTH4_IN_PU, PTH4_IN,
+		PTH3_FN, PTH3_OUT, PTH3_IN_PU, PTH3_IN,
+		PTH2_FN, PTH2_OUT, PTH2_IN_PU, PTH2_IN,
+		PTH1_FN, PTH1_OUT, PTH1_IN_PU, PTH1_IN,
+		PTH0_FN, PTH0_OUT, PTH0_IN_PU, PTH0_IN }
+	},
+	{ PINMUX_CFG_REG("PJCR", 0xa4050110, 16, 2) {
+		PTJ7_FN, PTJ7_OUT, 0, 0,
+		PTJ6_FN, PTJ6_OUT, 0, 0,
+		PTJ5_FN, PTJ5_OUT, 0, 0,
+		0, 0, 0, 0,
+		PTJ3_FN, PTJ3_OUT, PTJ3_IN_PU, PTJ3_IN,
+		PTJ2_FN, PTJ2_OUT, PTJ2_IN_PU, PTJ2_IN,
+		PTJ1_FN, PTJ1_OUT, PTJ1_IN_PU, PTJ1_IN,
+		PTJ0_FN, PTJ0_OUT, PTJ0_IN_PU, PTJ0_IN }
+	},
+	{ PINMUX_CFG_REG("PKCR", 0xa4050112, 16, 2) {
+		PTK7_FN, PTK7_OUT, PTK7_IN_PU, PTK7_IN,
+		PTK6_FN, PTK6_OUT, PTK6_IN_PU, PTK6_IN,
+		PTK5_FN, PTK5_OUT, PTK5_IN_PU, PTK5_IN,
+		PTK4_FN, PTK4_OUT, PTK4_IN_PU, PTK4_IN,
+		PTK3_FN, PTK3_OUT, PTK3_IN_PU, PTK3_IN,
+		PTK2_FN, PTK2_OUT, PTK2_IN_PU, PTK2_IN,
+		PTK1_FN, PTK1_OUT, PTK1_IN_PU, PTK1_IN,
+		PTK0_FN, PTK0_OUT, PTK0_IN_PU, PTK0_IN }
+	},
+	{ PINMUX_CFG_REG("PLCR", 0xa4050114, 16, 2) {
+		PTL7_FN, PTL7_OUT, PTL7_IN_PU, PTL7_IN,
+		PTL6_FN, PTL6_OUT, PTL6_IN_PU, PTL6_IN,
+		PTL5_FN, PTL5_OUT, PTL5_IN_PU, PTL5_IN,
+		PTL4_FN, PTL4_OUT, PTL4_IN_PU, PTL4_IN,
+		PTL3_FN, PTL3_OUT, PTL3_IN_PU, PTL3_IN,
+		PTL2_FN, PTL2_OUT, PTL2_IN_PU, PTL2_IN,
+		PTL1_FN, PTL1_OUT, PTL1_IN_PU, PTL1_IN,
+		PTL0_FN, PTL0_OUT, PTL0_IN_PU, PTL0_IN }
+	},
+	{ PINMUX_CFG_REG("PMCR", 0xa4050116, 16, 2) {
+		PTM7_FN, PTM7_OUT, PTM7_IN_PU, PTM7_IN,
+		PTM6_FN, PTM6_OUT, PTM6_IN_PU, PTM6_IN,
+		PTM5_FN, PTM5_OUT, PTM5_IN_PU, PTM5_IN,
+		PTM4_FN, PTM4_OUT, PTM4_IN_PU, PTM4_IN,
+		PTM3_FN, PTM3_OUT, PTM3_IN_PU, PTM3_IN,
+		PTM2_FN, PTM2_OUT, PTM2_IN_PU, PTM2_IN,
+		PTM1_FN, PTM1_OUT, PTM1_IN_PU, PTM1_IN,
+		PTM0_FN, PTM0_OUT, PTM0_IN_PU, PTM0_IN }
+	},
+	{ PINMUX_CFG_REG("PNCR", 0xa4050118, 16, 2) {
+		PTN7_FN, PTN7_OUT, PTN7_IN_PU, PTN7_IN,
+		PTN6_FN, PTN6_OUT, PTN6_IN_PU, PTN6_IN,
+		PTN5_FN, PTN5_OUT, PTN5_IN_PU, PTN5_IN,
+		PTN4_FN, PTN4_OUT, PTN4_IN_PU, PTN4_IN,
+		PTN3_FN, PTN3_OUT, PTN3_IN_PU, PTN3_IN,
+		PTN2_FN, PTN2_OUT, PTN2_IN_PU, PTN2_IN,
+		PTN1_FN, PTN1_OUT, PTN1_IN_PU, PTN1_IN,
+		PTN0_FN, PTN0_OUT, PTN0_IN_PU, PTN0_IN }
+	},
+	{ PINMUX_CFG_REG("PQCR", 0xa405011a, 16, 2) {
+		PTQ7_FN, PTQ7_OUT, PTQ7_IN_PU, PTQ7_IN,
+		PTQ6_FN, PTQ6_OUT, PTQ6_IN_PU, PTQ6_IN,
+		PTQ5_FN, PTQ5_OUT, PTQ5_IN_PU, PTQ5_IN,
+		PTQ4_FN, PTQ4_OUT, PTQ4_IN_PU, PTQ4_IN,
+		PTQ3_FN, PTQ3_OUT, PTQ3_IN_PU, PTQ3_IN,
+		PTQ2_FN, PTQ2_OUT, PTQ2_IN_PU, PTQ2_IN,
+		PTQ1_FN, PTQ1_OUT, PTQ1_IN_PU, PTQ1_IN,
+		PTQ0_FN, PTQ0_OUT, PTQ0_IN_PU, PTQ0_IN }
+	},
+	{ PINMUX_CFG_REG("PRCR", 0xa405011c, 16, 2) {
+		PTR7_FN, PTR7_OUT, PTR7_IN_PU, PTR7_IN,
+		PTR6_FN, PTR6_OUT, PTR6_IN_PU, PTR6_IN,
+		PTR5_FN, PTR5_OUT, PTR5_IN_PU, PTR5_IN,
+		PTR4_FN, PTR4_OUT, PTR4_IN_PU, PTR4_IN,
+		PTR3_FN, 0,        PTR3_IN_PU, PTR3_IN,
+		PTR2_FN, 0,        PTR2_IN_PU, PTR2_IN,
+		PTR1_FN, PTR1_OUT, PTR1_IN_PU, PTR1_IN,
+		PTR0_FN, PTR0_OUT, PTR0_IN_PU, PTR0_IN }
+	},
+	{ PINMUX_CFG_REG("PSCR", 0xa405011e, 16, 2) {
+		0, 0, 0, 0,
+		PTS6_FN, PTS6_OUT, PTS6_IN_PU, PTS6_IN,
+		PTS5_FN, PTS5_OUT, PTS5_IN_PU, PTS5_IN,
+		PTS4_FN, PTS4_OUT, PTS4_IN_PU, PTS4_IN,
+		PTS3_FN, PTS3_OUT, PTS3_IN_PU, PTS3_IN,
+		PTS2_FN, PTS2_OUT, PTS2_IN_PU, PTS2_IN,
+		PTS1_FN, PTS1_OUT, PTS1_IN_PU, PTS1_IN,
+		PTS0_FN, PTS0_OUT, PTS0_IN_PU, PTS0_IN }
+	},
+	{ PINMUX_CFG_REG("PTCR", 0xa4050140, 16, 2) {
+		PTT7_FN, PTT7_OUT, PTT7_IN_PU, PTT7_IN,
+		PTT6_FN, PTT6_OUT, PTT6_IN_PU, PTT6_IN,
+		PTT5_FN, PTT5_OUT, PTT5_IN_PU, PTT5_IN,
+		PTT4_FN, PTT4_OUT, PTT4_IN_PU, PTT4_IN,
+		PTT3_FN, PTT3_OUT, PTT3_IN_PU, PTT3_IN,
+		PTT2_FN, PTT2_OUT, PTT2_IN_PU, PTT2_IN,
+		PTT1_FN, PTT1_OUT, PTT1_IN_PU, PTT1_IN,
+		PTT0_FN, PTT0_OUT, PTT0_IN_PU, PTT0_IN }
+	},
+	{ PINMUX_CFG_REG("PUCR", 0xa4050142, 16, 2) {
+		PTU7_FN, PTU7_OUT, PTU7_IN_PU, PTU7_IN,
+		PTU6_FN, PTU6_OUT, PTU6_IN_PU, PTU6_IN,
+		PTU5_FN, PTU5_OUT, PTU5_IN_PU, PTU5_IN,
+		PTU4_FN, PTU4_OUT, PTU4_IN_PU, PTU4_IN,
+		PTU3_FN, PTU3_OUT, PTU3_IN_PU, PTU3_IN,
+		PTU2_FN, PTU2_OUT, PTU2_IN_PU, PTU2_IN,
+		PTU1_FN, PTU1_OUT, PTU1_IN_PU, PTU1_IN,
+		PTU0_FN, PTU0_OUT, PTU0_IN_PU, PTU0_IN }
+	},
+	{ PINMUX_CFG_REG("PVCR", 0xa4050144, 16, 2) {
+		PTV7_FN, PTV7_OUT, PTV7_IN_PU, PTV7_IN,
+		PTV6_FN, PTV6_OUT, PTV6_IN_PU, PTV6_IN,
+		PTV5_FN, PTV5_OUT, PTV5_IN_PU, PTV5_IN,
+		PTV4_FN, PTV4_OUT, PTV4_IN_PU, PTV4_IN,
+		PTV3_FN, PTV3_OUT, PTV3_IN_PU, PTV3_IN,
+		PTV2_FN, PTV2_OUT, PTV2_IN_PU, PTV2_IN,
+		PTV1_FN, PTV1_OUT, PTV1_IN_PU, PTV1_IN,
+		PTV0_FN, PTV0_OUT, PTV0_IN_PU, PTV0_IN }
+	},
+	{ PINMUX_CFG_REG("PWCR", 0xa4050146, 16, 2) {
+		PTW7_FN, PTW7_OUT, PTW7_IN_PU, PTW7_IN,
+		PTW6_FN, PTW6_OUT, PTW6_IN_PU, PTW6_IN,
+		PTW5_FN, PTW5_OUT, PTW5_IN_PU, PTW5_IN,
+		PTW4_FN, PTW4_OUT, PTW4_IN_PU, PTW4_IN,
+		PTW3_FN, PTW3_OUT, PTW3_IN_PU, PTW3_IN,
+		PTW2_FN, PTW2_OUT, PTW2_IN_PU, PTW2_IN,
+		PTW1_FN, PTW1_OUT, PTW1_IN_PU, PTW1_IN,
+		PTW0_FN, PTW0_OUT, PTW0_IN_PU, PTW0_IN }
+	},
+	{ PINMUX_CFG_REG("PXCR", 0xa4050148, 16, 2) {
+		PTX7_FN, PTX7_OUT, PTX7_IN_PU, PTX7_IN,
+		PTX6_FN, PTX6_OUT, PTX6_IN_PU, PTX6_IN,
+		PTX5_FN, PTX5_OUT, PTX5_IN_PU, PTX5_IN,
+		PTX4_FN, PTX4_OUT, PTX4_IN_PU, PTX4_IN,
+		PTX3_FN, PTX3_OUT, PTX3_IN_PU, PTX3_IN,
+		PTX2_FN, PTX2_OUT, PTX2_IN_PU, PTX2_IN,
+		PTX1_FN, PTX1_OUT, PTX1_IN_PU, PTX1_IN,
+		PTX0_FN, PTX0_OUT, PTX0_IN_PU, PTX0_IN }
+	},
+	{ PINMUX_CFG_REG("PYCR", 0xa405014a, 16, 2) {
+		PTY7_FN, PTY7_OUT, PTY7_IN_PU, PTY7_IN,
+		PTY6_FN, PTY6_OUT, PTY6_IN_PU, PTY6_IN,
+		PTY5_FN, PTY5_OUT, PTY5_IN_PU, PTY5_IN,
+		PTY4_FN, PTY4_OUT, PTY4_IN_PU, PTY4_IN,
+		PTY3_FN, PTY3_OUT, PTY3_IN_PU, PTY3_IN,
+		PTY2_FN, PTY2_OUT, PTY2_IN_PU, PTY2_IN,
+		PTY1_FN, PTY1_OUT, PTY1_IN_PU, PTY1_IN,
+		PTY0_FN, PTY0_OUT, PTY0_IN_PU, PTY0_IN }
+	},
+	{ PINMUX_CFG_REG("PZCR", 0xa405014c, 16, 2) {
+		PTZ7_FN, PTZ7_OUT, PTZ7_IN_PU, PTZ7_IN,
+		PTZ6_FN, PTZ6_OUT, PTZ6_IN_PU, PTZ6_IN,
+		PTZ5_FN, PTZ5_OUT, PTZ5_IN_PU, PTZ5_IN,
+		PTZ4_FN, PTZ4_OUT, PTZ4_IN_PU, PTZ4_IN,
+		PTZ3_FN, PTZ3_OUT, PTZ3_IN_PU, PTZ3_IN,
+		PTZ2_FN, PTZ2_OUT, PTZ2_IN_PU, PTZ2_IN,
+		PTZ1_FN, PTZ1_OUT, PTZ1_IN_PU, PTZ1_IN,
+		PTZ0_FN, PTZ0_OUT, PTZ0_IN_PU, PTZ0_IN }
+	},
+	{ PINMUX_CFG_REG("PSELA", 0xa405014e, 16, 1) {
+		PSA15_0, PSA15_1,
+		PSA14_0, PSA14_1,
+		PSA13_0, PSA13_1,
+		PSA12_0, PSA12_1,
+		0, 0,
+		PSA10_0, PSA10_1,
+		PSA9_0,  PSA9_1,
+		PSA8_0,  PSA8_1,
+		PSA7_0,  PSA7_1,
+		PSA6_0,  PSA6_1,
+		PSA5_0,  PSA5_1,
+		0, 0,
+		PSA3_0,  PSA3_1,
+		PSA2_0,  PSA2_1,
+		PSA1_0,  PSA1_1,
+		PSA0_0,  PSA0_1}
+	},
+	{ PINMUX_CFG_REG("PSELB", 0xa4050150, 16, 1) {
+		0, 0,
+		PSB14_0, PSB14_1,
+		PSB13_0, PSB13_1,
+		PSB12_0, PSB12_1,
+		PSB11_0, PSB11_1,
+		PSB10_0, PSB10_1,
+		PSB9_0,  PSB9_1,
+		PSB8_0,  PSB8_1,
+		PSB7_0,  PSB7_1,
+		PSB6_0,  PSB6_1,
+		PSB5_0,  PSB5_1,
+		PSB4_0,  PSB4_1,
+		PSB3_0,  PSB3_1,
+		PSB2_0,  PSB2_1,
+		PSB1_0,  PSB1_1,
+		PSB0_0,  PSB0_1}
+	},
+	{ PINMUX_CFG_REG("PSELC", 0xa4050152, 16, 1) {
+		PSC15_0, PSC15_1,
+		PSC14_0, PSC14_1,
+		PSC13_0, PSC13_1,
+		PSC12_0, PSC12_1,
+		PSC11_0, PSC11_1,
+		PSC10_0, PSC10_1,
+		PSC9_0,  PSC9_1,
+		PSC8_0,  PSC8_1,
+		PSC7_0,  PSC7_1,
+		PSC6_0,  PSC6_1,
+		PSC5_0,  PSC5_1,
+		PSC4_0,  PSC4_1,
+		0, 0,
+		PSC2_0,  PSC2_1,
+		PSC1_0,  PSC1_1,
+		PSC0_0,  PSC0_1}
+	},
+	{ PINMUX_CFG_REG("PSELD", 0xa4050154, 16, 1) {
+		PSD15_0, PSD15_1,
+		PSD14_0, PSD14_1,
+		PSD13_0, PSD13_1,
+		PSD12_0, PSD12_1,
+		PSD11_0, PSD11_1,
+		PSD10_0, PSD10_1,
+		PSD9_0,  PSD9_1,
+		PSD8_0,  PSD8_1,
+		PSD7_0,  PSD7_1,
+		PSD6_0,  PSD6_1,
+		PSD5_0,  PSD5_1,
+		PSD4_0,  PSD4_1,
+		PSD3_0,  PSD3_1,
+		PSD2_0,  PSD2_1,
+		PSD1_0,  PSD1_1,
+		PSD0_0,  PSD0_1}
+	},
+	{ PINMUX_CFG_REG("PSELE", 0xa4050156, 16, 1) {
+		PSE15_0, PSE15_1,
+		PSE14_0, PSE14_1,
+		PSE13_0, PSE13_1,
+		PSE12_0, PSE12_1,
+		PSE11_0, PSE11_1,
+		PSE10_0, PSE10_1,
+		PSE9_0,  PSE9_1,
+		PSE8_0,  PSE8_1,
+		PSE7_0,  PSE7_1,
+		PSE6_0,  PSE6_1,
+		PSE5_0,  PSE5_1,
+		PSE4_0,  PSE4_1,
+		PSE3_0,  PSE3_1,
+		PSE2_0,  PSE2_1,
+		PSE1_0,  PSE1_1,
+		PSE0_0,  PSE0_1}
+	},
+	{}
+};
+
+static struct pinmux_data_reg pinmux_data_regs[] = {
+	{ PINMUX_DATA_REG("PADR", 0xa4050120, 8) {
+		PTA7_DATA, PTA6_DATA, PTA5_DATA, PTA4_DATA,
+		PTA3_DATA, PTA2_DATA, PTA1_DATA, PTA0_DATA }
+	},
+	{ PINMUX_DATA_REG("PBDR", 0xa4050122, 8) {
+		PTB7_DATA, PTB6_DATA, PTB5_DATA, PTB4_DATA,
+		PTB3_DATA, PTB2_DATA, PTB1_DATA, PTB0_DATA }
+	},
+	{ PINMUX_DATA_REG("PCDR", 0xa4050124, 8) {
+		PTC7_DATA, PTC6_DATA, PTC5_DATA, PTC4_DATA,
+		PTC3_DATA, PTC2_DATA, PTC1_DATA, PTC0_DATA }
+	},
+	{ PINMUX_DATA_REG("PDDR", 0xa4050126, 8) {
+		PTD7_DATA, PTD6_DATA, PTD5_DATA, PTD4_DATA,
+		PTD3_DATA, PTD2_DATA, PTD1_DATA, PTD0_DATA }
+	},
+	{ PINMUX_DATA_REG("PEDR", 0xa4050128, 8) {
+		PTE7_DATA, PTE6_DATA, PTE5_DATA, PTE4_DATA,
+		PTE3_DATA, PTE2_DATA, PTE1_DATA, PTE0_DATA }
+	},
+	{ PINMUX_DATA_REG("PFDR", 0xa405012a, 8) {
+		PTF7_DATA, PTF6_DATA, PTF5_DATA, PTF4_DATA,
+		PTF3_DATA, PTF2_DATA, PTF1_DATA, PTF0_DATA }
+	},
+	{ PINMUX_DATA_REG("PGDR", 0xa405012c, 8) {
+		0,         0,         PTG5_DATA, PTG4_DATA,
+		PTG3_DATA, PTG2_DATA, PTG1_DATA, PTG0_DATA }
+	},
+	{ PINMUX_DATA_REG("PHDR", 0xa405012e, 8) {
+		PTH7_DATA, PTH6_DATA, PTH5_DATA, PTH4_DATA,
+		PTH3_DATA, PTH2_DATA, PTH1_DATA, PTH0_DATA }
+	},
+	{ PINMUX_DATA_REG("PJDR", 0xa4050130, 8) {
+		PTJ7_DATA, PTJ6_DATA, PTJ5_DATA, 0,
+		PTJ3_DATA, PTJ2_DATA, PTJ1_DATA, PTJ0_DATA }
+	},
+	{ PINMUX_DATA_REG("PKDR", 0xa4050132, 8) {
+		PTK7_DATA, PTK6_DATA, PTK5_DATA, PTK4_DATA,
+		PTK3_DATA, PTK2_DATA, PTK1_DATA, PTK0_DATA }
+	},
+	{ PINMUX_DATA_REG("PLDR", 0xa4050134, 8) {
+		PTL7_DATA, PTL6_DATA, PTL5_DATA, PTL4_DATA,
+		PTL3_DATA, PTL2_DATA, PTL1_DATA, PTL0_DATA }
+	},
+	{ PINMUX_DATA_REG("PMDR", 0xa4050136, 8) {
+		PTM7_DATA, PTM6_DATA, PTM5_DATA, PTM4_DATA,
+		PTM3_DATA, PTM2_DATA, PTM1_DATA, PTM0_DATA }
+	},
+	{ PINMUX_DATA_REG("PNDR", 0xa4050138, 8) {
+		PTN7_DATA, PTN6_DATA, PTN5_DATA, PTN4_DATA,
+		PTN3_DATA, PTN2_DATA, PTN1_DATA, PTN0_DATA }
+	},
+	{ PINMUX_DATA_REG("PQDR", 0xa405013a, 8) {
+		PTQ7_DATA, PTQ6_DATA, PTQ5_DATA, PTQ4_DATA,
+		PTQ3_DATA, PTQ2_DATA, PTQ1_DATA, PTQ0_DATA }
+	},
+	{ PINMUX_DATA_REG("PRDR", 0xa405013c, 8) {
+		PTR7_DATA, PTR6_DATA, PTR5_DATA, PTR4_DATA,
+		PTR3_DATA, PTR2_DATA, PTR1_DATA, PTR0_DATA }
+	},
+	{ PINMUX_DATA_REG("PSDR", 0xa405013e, 8) {
+		0,         PTS6_DATA, PTS5_DATA, PTS4_DATA,
+		PTS3_DATA, PTS2_DATA, PTS1_DATA, PTS0_DATA }
+	},
+	{ PINMUX_DATA_REG("PTDR", 0xa4050160, 8) {
+		PTT7_DATA, PTT6_DATA, PTT5_DATA, PTT4_DATA,
+		PTT3_DATA, PTT2_DATA, PTT1_DATA, PTT0_DATA }
+	},
+	{ PINMUX_DATA_REG("PUDR", 0xa4050162, 8) {
+		PTU7_DATA, PTU6_DATA, PTU5_DATA, PTU4_DATA,
+		PTU3_DATA, PTU2_DATA, PTU1_DATA, PTU0_DATA }
+	},
+	{ PINMUX_DATA_REG("PVDR", 0xa4050164, 8) {
+		PTV7_DATA, PTV6_DATA, PTV5_DATA, PTV4_DATA,
+		PTV3_DATA, PTV2_DATA, PTV1_DATA, PTV0_DATA }
+	},
+	{ PINMUX_DATA_REG("PWDR", 0xa4050166, 8) {
+		PTW7_DATA, PTW6_DATA, PTW5_DATA, PTW4_DATA,
+		PTW3_DATA, PTW2_DATA, PTW1_DATA, PTW0_DATA }
+	},
+	{ PINMUX_DATA_REG("PXDR", 0xa4050168, 8) {
+		PTX7_DATA, PTX6_DATA, PTX5_DATA, PTX4_DATA,
+		PTX3_DATA, PTX2_DATA, PTX1_DATA, PTX0_DATA }
+	},
+	{ PINMUX_DATA_REG("PYDR", 0xa405016a, 8) {
+		PTY7_DATA, PTY6_DATA, PTY5_DATA, PTY4_DATA,
+		PTY3_DATA, PTY2_DATA, PTY1_DATA, PTY0_DATA }
+	},
+	{ PINMUX_DATA_REG("PZDR", 0xa405016c, 8) {
+		PTZ7_DATA, PTZ6_DATA, PTZ5_DATA, PTZ4_DATA,
+		PTZ3_DATA, PTZ2_DATA, PTZ1_DATA, PTZ0_DATA }
+	},
+	{ },
+};
+
+static struct pinmux_info sh7724_pinmux_info = {
+	.name = "sh7724_pfc",
+	.reserved_id = PINMUX_RESERVED,
+	.data = { PINMUX_DATA_BEGIN, PINMUX_DATA_END },
+	.input = { PINMUX_INPUT_BEGIN, PINMUX_INPUT_END },
+	.input_pu = { PINMUX_INPUT_PULLUP_BEGIN, PINMUX_INPUT_PULLUP_END },
+	.output = { PINMUX_OUTPUT_BEGIN, PINMUX_OUTPUT_END },
+	.mark = { PINMUX_MARK_BEGIN, PINMUX_MARK_END },
+	.function = { PINMUX_FUNCTION_BEGIN, PINMUX_FUNCTION_END },
+
+	.first_gpio = GPIO_PTA7,
+	.last_gpio = GPIO_FN_INTC_IRQ0,
+
+	.gpios = pinmux_gpios,
+	.cfg_regs = pinmux_config_regs,
+	.data_regs = pinmux_data_regs,
+
+	.gpio_data = pinmux_data,
+	.gpio_data_size = ARRAY_SIZE(pinmux_data),
+};
+
+static int __init plat_pinmux_setup(void)
+{
+	return register_pinmux(&sh7724_pinmux_info);
+}
+arch_initcall(plat_pinmux_setup);
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c
index c1549382c87c..6307e087c864 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c
@@ -12,7 +12,7 @@
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
 #include <linux/uio_driver.h>
-#include <linux/sh_cmt.h>
+#include <linux/sh_timer.h>
 #include <asm/clock.h>
 
 static struct resource iic0_resources[] = {
@@ -141,7 +141,7 @@ static struct platform_device jpu_device = {
 	.num_resources	= ARRAY_SIZE(jpu_resources),
 };
 
-static struct sh_cmt_config cmt_platform_data = {
+static struct sh_timer_config cmt_platform_data = {
 	.name = "CMT",
 	.channel_offset = 0x60,
 	.timer_bit = 5,
@@ -173,27 +173,123 @@ static struct platform_device cmt_device = {
 	.num_resources	= ARRAY_SIZE(cmt_resources),
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "tmu0",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "tmu0",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "tmu0",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
 static struct plat_sci_port sci_platform_data[] = {
 	{
 		.mapbase	= 0xffe00000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 80, 80, 80, 80 },
+		.clk		= "scif0",
 	}, {
 		.mapbase	= 0xffe10000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 81, 81, 81, 81 },
+		.clk		= "scif1",
 	}, {
 		.mapbase	= 0xffe20000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 82, 82, 82, 82 },
+		.clk		= "scif2",
 	}, {
 		.mapbase	= 0xffe30000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 83, 83, 83, 83 },
+		.clk		= "scif3",
 	}, {
 		.flags = 0,
 	}
@@ -209,6 +305,9 @@ static struct platform_device sci_device = {
 
 static struct platform_device *sh7343_devices[] __initdata = {
 	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
 	&iic0_device,
 	&iic1_device,
 	&sci_device,
@@ -219,12 +318,6 @@ static struct platform_device *sh7343_devices[] __initdata = {
 
 static int __init sh7343_devices_setup(void)
 {
-	clk_always_enable("uram0"); /* URAM */
-	clk_always_enable("xymem0"); /* XYMEM */
-	clk_always_enable("veu0"); /* VEU */
-	clk_always_enable("vpu0"); /* VPU */
-	clk_always_enable("jpu0"); /* JPU */
-
 	platform_resource_setup_memory(&vpu_device, "vpu", 1 << 20);
 	platform_resource_setup_memory(&veu_device, "veu", 2 << 20);
 	platform_resource_setup_memory(&jpu_device, "jpu", 2 << 20);
@@ -234,6 +327,19 @@ static int __init sh7343_devices_setup(void)
 }
 __initcall(sh7343_devices_setup);
 
+static struct platform_device *sh7343_early_devices[] __initdata = {
+	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7343_early_devices,
+				   ARRAY_SIZE(sh7343_early_devices));
+}
+
 enum {
 	UNUSED = 0,
 
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c
index 93ecf8ed5c6c..318516f6bfad 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c
@@ -14,7 +14,7 @@
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
 #include <linux/uio_driver.h>
-#include <linux/sh_cmt.h>
+#include <linux/sh_timer.h>
 #include <asm/clock.h>
 
 static struct resource iic_resources[] = {
@@ -148,7 +148,7 @@ static struct platform_device veu1_device = {
 	.num_resources	= ARRAY_SIZE(veu1_resources),
 };
 
-static struct sh_cmt_config cmt_platform_data = {
+static struct sh_timer_config cmt_platform_data = {
 	.name = "CMT",
 	.channel_offset = 0x60,
 	.timer_bit = 5,
@@ -180,12 +180,105 @@ static struct platform_device cmt_device = {
 	.num_resources	= ARRAY_SIZE(cmt_resources),
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "tmu0",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "tmu0",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "tmu0",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
 static struct plat_sci_port sci_platform_data[] = {
 	{
 		.mapbase	= 0xffe00000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 80, 80, 80, 80 },
+		.clk		= "scif0",
 	}, {
 		.flags = 0,
 	}
@@ -201,6 +294,9 @@ static struct platform_device sci_device = {
 
 static struct platform_device *sh7366_devices[] __initdata = {
 	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
 	&iic_device,
 	&sci_device,
 	&usb_host_device,
@@ -211,12 +307,6 @@ static struct platform_device *sh7366_devices[] __initdata = {
 
 static int __init sh7366_devices_setup(void)
 {
-	clk_always_enable("rsmem0"); /* RSMEM */
-	clk_always_enable("xymem0"); /* XYMEM */
-	clk_always_enable("veu1"); /* VEU-2 */
-	clk_always_enable("veu0"); /* VEU-1 */
-	clk_always_enable("vpu0"); /* VPU */
-
 	platform_resource_setup_memory(&vpu_device, "vpu", 2 << 20);
 	platform_resource_setup_memory(&veu0_device, "veu0", 2 << 20);
 	platform_resource_setup_memory(&veu1_device, "veu1", 2 << 20);
@@ -226,6 +316,19 @@ static int __init sh7366_devices_setup(void)
 }
 __initcall(sh7366_devices_setup);
 
+static struct platform_device *sh7366_early_devices[] __initdata = {
+	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7366_early_devices,
+				   ARRAY_SIZE(sh7366_early_devices));
+}
+
 enum {
 	UNUSED=0,
 
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
index 406747f07dc0..ea524a2da3e4 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
@@ -13,7 +13,7 @@
 #include <linux/serial_sci.h>
 #include <linux/mm.h>
 #include <linux/uio_driver.h>
-#include <linux/sh_cmt.h>
+#include <linux/sh_timer.h>
 #include <asm/clock.h>
 #include <asm/mmzone.h>
 
@@ -177,13 +177,13 @@ static struct platform_device jpu_device = {
 	.num_resources	= ARRAY_SIZE(jpu_resources),
 };
 
-static struct sh_cmt_config cmt_platform_data = {
+static struct sh_timer_config cmt_platform_data = {
 	.name = "CMT",
 	.channel_offset = 0x60,
 	.timer_bit = 5,
 	.clk = "cmt0",
 	.clockevent_rating = 125,
-	.clocksource_rating = 200,
+	.clocksource_rating = 125,
 };
 
 static struct resource cmt_resources[] = {
@@ -209,24 +209,119 @@ static struct platform_device cmt_device = {
 	.num_resources	= ARRAY_SIZE(cmt_resources),
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "tmu0",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "tmu0",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "tmu0",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
 static struct plat_sci_port sci_platform_data[] = {
 	{
 		.mapbase	= 0xffe00000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 80, 80, 80, 80 },
+		.clk		= "scif0",
 	},
 	{
 		.mapbase	= 0xffe10000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 81, 81, 81, 81 },
+		.clk		= "scif1",
 	},
 	{
 		.mapbase	= 0xffe20000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 82, 82, 82, 82 },
+		.clk		= "scif2",
 	},
 	{
 		.flags = 0,
@@ -243,6 +338,9 @@ static struct platform_device sci_device = {
 
 static struct platform_device *sh7722_devices[] __initdata = {
 	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
 	&rtc_device,
 	&usbf_device,
 	&iic_device,
@@ -254,12 +352,6 @@ static struct platform_device *sh7722_devices[] __initdata = {
 
 static int __init sh7722_devices_setup(void)
 {
-	clk_always_enable("uram0"); /* URAM */
-	clk_always_enable("xymem0"); /* XYMEM */
-	clk_always_enable("veu0"); /* VEU */
-	clk_always_enable("vpu0"); /* VPU */
-	clk_always_enable("jpu0"); /* JPU */
-
 	platform_resource_setup_memory(&vpu_device, "vpu", 1 << 20);
 	platform_resource_setup_memory(&veu_device, "veu", 2 << 20);
 	platform_resource_setup_memory(&jpu_device, "jpu", 2 << 20);
@@ -269,6 +361,19 @@ static int __init sh7722_devices_setup(void)
 }
 __initcall(sh7722_devices_setup);
 
+static struct platform_device *sh7722_early_devices[] __initdata = {
+	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7722_early_devices,
+				   ARRAY_SIZE(sh7722_early_devices));
+}
+
 enum {
 	UNUSED=0,
 
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c
index a800466b938c..d8f4a13aeff9 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c
@@ -13,7 +13,8 @@
 #include <linux/mm.h>
 #include <linux/serial_sci.h>
 #include <linux/uio_driver.h>
-#include <linux/sh_cmt.h>
+#include <linux/sh_timer.h>
+#include <linux/io.h>
 #include <asm/clock.h>
 #include <asm/mmzone.h>
 
@@ -101,13 +102,13 @@ static struct platform_device veu1_device = {
 	.num_resources	= ARRAY_SIZE(veu1_resources),
 };
 
-static struct sh_cmt_config cmt_platform_data = {
+static struct sh_timer_config cmt_platform_data = {
 	.name = "CMT",
 	.channel_offset = 0x60,
 	.timer_bit = 5,
 	.clk = "cmt0",
 	.clockevent_rating = 125,
-	.clocksource_rating = 200,
+	.clocksource_rating = 125,
 };
 
 static struct resource cmt_resources[] = {
@@ -133,37 +134,225 @@ static struct platform_device cmt_device = {
 	.num_resources	= ARRAY_SIZE(cmt_resources),
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "tmu0",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "tmu0",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "tmu0",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+static struct sh_timer_config tmu3_platform_data = {
+	.name = "TMU3",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "tmu1",
+};
+
+static struct resource tmu3_resources[] = {
+	[0] = {
+		.name	= "TMU3",
+		.start	= 0xffd90008,
+		.end	= 0xffd90013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 57,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu3_device = {
+	.name		= "sh_tmu",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &tmu3_platform_data,
+	},
+	.resource	= tmu3_resources,
+	.num_resources	= ARRAY_SIZE(tmu3_resources),
+};
+
+static struct sh_timer_config tmu4_platform_data = {
+	.name = "TMU4",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "tmu1",
+};
+
+static struct resource tmu4_resources[] = {
+	[0] = {
+		.name	= "TMU4",
+		.start	= 0xffd90014,
+		.end	= 0xffd9001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 58,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu4_device = {
+	.name		= "sh_tmu",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &tmu4_platform_data,
+	},
+	.resource	= tmu4_resources,
+	.num_resources	= ARRAY_SIZE(tmu4_resources),
+};
+
+static struct sh_timer_config tmu5_platform_data = {
+	.name = "TMU5",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "tmu1",
+};
+
+static struct resource tmu5_resources[] = {
+	[0] = {
+		.name	= "TMU5",
+		.start	= 0xffd90020,
+		.end	= 0xffd9002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 57,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu5_device = {
+	.name		= "sh_tmu",
+	.id		= 5,
+	.dev = {
+		.platform_data	= &tmu5_platform_data,
+	},
+	.resource	= tmu5_resources,
+	.num_resources	= ARRAY_SIZE(tmu5_resources),
+};
+
 static struct plat_sci_port sci_platform_data[] = {
 	{
 		.mapbase        = 0xffe00000,
 		.flags          = UPF_BOOT_AUTOCONF,
 		.type           = PORT_SCIF,
 		.irqs           = { 80, 80, 80, 80 },
+		.clk		= "scif0",
 	},{
 		.mapbase        = 0xffe10000,
 		.flags          = UPF_BOOT_AUTOCONF,
 		.type           = PORT_SCIF,
 		.irqs           = { 81, 81, 81, 81 },
+		.clk		= "scif1",
 	},{
 		.mapbase        = 0xffe20000,
 		.flags          = UPF_BOOT_AUTOCONF,
 		.type           = PORT_SCIF,
 		.irqs           = { 82, 82, 82, 82 },
+		.clk		= "scif2",
 	},{
 		.mapbase	= 0xa4e30000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIFA,
 		.irqs		= { 56, 56, 56, 56 },
+		.clk		= "scif3",
 	},{
 		.mapbase	= 0xa4e40000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIFA,
 		.irqs		= { 88, 88, 88, 88 },
+		.clk		= "scif4",
 	},{
 		.mapbase	= 0xa4e50000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIFA,
 		.irqs		= { 109, 109, 109, 109 },
+		.clk		= "scif5",
 	}, {
 		.flags = 0,
 	}
@@ -255,6 +444,12 @@ static struct platform_device iic_device = {
 
 static struct platform_device *sh7723_devices[] __initdata = {
 	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
 	&sci_device,
 	&rtc_device,
 	&iic_device,
@@ -266,11 +461,6 @@ static struct platform_device *sh7723_devices[] __initdata = {
 
 static int __init sh7723_devices_setup(void)
 {
-	clk_always_enable("meram0"); /* MERAM */
-	clk_always_enable("veu1"); /* VEU2H1 */
-	clk_always_enable("veu0"); /* VEU2H0 */
-	clk_always_enable("vpu0"); /* VPU */
-
 	platform_resource_setup_memory(&vpu_device, "vpu", 2 << 20);
 	platform_resource_setup_memory(&veu0_device, "veu0", 2 << 20);
 	platform_resource_setup_memory(&veu1_device, "veu1", 2 << 20);
@@ -280,6 +470,31 @@ static int __init sh7723_devices_setup(void)
 }
 __initcall(sh7723_devices_setup);
 
+static struct platform_device *sh7723_early_devices[] __initdata = {
+	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7723_early_devices,
+				   ARRAY_SIZE(sh7723_early_devices));
+}
+
+#define RAMCR_CACHE_L2FC	0x0002
+#define RAMCR_CACHE_L2E		0x0001
+#define L2_CACHE_ENABLE		(RAMCR_CACHE_L2E|RAMCR_CACHE_L2FC)
+void __uses_jump_to_uncached l2_cache_init(void)
+{
+	/* Enable L2 cache */
+	ctrl_outl(L2_CACHE_ENABLE, RAMCR);
+}
+
 enum {
 	UNUSED=0,
 
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c
new file mode 100644
index 000000000000..e5ac9eb11c63
--- /dev/null
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c
@@ -0,0 +1,786 @@
+/*
+ * SH7724 Setup
+ *
+ * Copyright (C) 2009 Renesas Solutions Corp.
+ *
+ * Kuninori Morimoto <morimoto.kuninori@renesas.com>
+ *
+ * Based on SH7723 Setup
+ * Copyright (C) 2008  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/platform_device.h>
+#include <linux/init.h>
+#include <linux/serial.h>
+#include <linux/mm.h>
+#include <linux/serial_sci.h>
+#include <linux/uio_driver.h>
+#include <linux/sh_timer.h>
+#include <linux/io.h>
+#include <asm/clock.h>
+#include <asm/mmzone.h>
+
+/* Serial */
+static struct plat_sci_port sci_platform_data[] = {
+	{
+		.mapbase        = 0xffe00000,
+		.flags          = UPF_BOOT_AUTOCONF,
+		.type           = PORT_SCIF,
+		.irqs           = { 80, 80, 80, 80 },
+		.clk		= "scif0",
+	}, {
+		.mapbase        = 0xffe10000,
+		.flags          = UPF_BOOT_AUTOCONF,
+		.type           = PORT_SCIF,
+		.irqs           = { 81, 81, 81, 81 },
+		.clk		= "scif1",
+	}, {
+		.mapbase        = 0xffe20000,
+		.flags          = UPF_BOOT_AUTOCONF,
+		.type           = PORT_SCIF,
+		.irqs           = { 82, 82, 82, 82 },
+		.clk		= "scif2",
+	}, {
+		.mapbase	= 0xa4e30000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIFA,
+		.irqs		= { 56, 56, 56, 56 },
+		.clk		= "scif3",
+	}, {
+		.mapbase	= 0xa4e40000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIFA,
+		.irqs		= { 88, 88, 88, 88 },
+		.clk		= "scif4",
+	}, {
+		.mapbase	= 0xa4e50000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIFA,
+		.irqs		= { 109, 109, 109, 109 },
+		.clk		= "scif5",
+	}, {
+		.flags = 0,
+	}
+};
+
+static struct platform_device sci_device = {
+	.name		= "sh-sci",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= sci_platform_data,
+	},
+};
+
+/* RTC */
+static struct resource rtc_resources[] = {
+	[0] = {
+		.start	= 0xa465fec0,
+		.end	= 0xa465fec0 + 0x58 - 1,
+		.flags	= IORESOURCE_IO,
+	},
+	[1] = {
+		/* Period IRQ */
+		.start	= 69,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[2] = {
+		/* Carry IRQ */
+		.start	= 70,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[3] = {
+		/* Alarm IRQ */
+		.start	= 68,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device rtc_device = {
+	.name		= "sh-rtc",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(rtc_resources),
+	.resource	= rtc_resources,
+};
+
+/* I2C0 */
+static struct resource iic0_resources[] = {
+	[0] = {
+		.name	= "IIC0",
+		.start  = 0x04470000,
+		.end    = 0x04470018 - 1,
+		.flags  = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = 96,
+		.end    = 99,
+		.flags  = IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device iic0_device = {
+	.name           = "i2c-sh_mobile",
+	.id             = 0, /* "i2c0" clock */
+	.num_resources  = ARRAY_SIZE(iic0_resources),
+	.resource       = iic0_resources,
+};
+
+/* I2C1 */
+static struct resource iic1_resources[] = {
+	[0] = {
+		.name	= "IIC1",
+		.start  = 0x04750000,
+		.end    = 0x04750018 - 1,
+		.flags  = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = 92,
+		.end    = 95,
+		.flags  = IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device iic1_device = {
+	.name           = "i2c-sh_mobile",
+	.id             = 1, /* "i2c1" clock */
+	.num_resources  = ARRAY_SIZE(iic1_resources),
+	.resource       = iic1_resources,
+};
+
+/* VPU */
+static struct uio_info vpu_platform_data = {
+	.name = "VPU5F",
+	.version = "0",
+	.irq = 60,
+};
+
+static struct resource vpu_resources[] = {
+	[0] = {
+		.name	= "VPU",
+		.start	= 0xfe900000,
+		.end	= 0xfe902807,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		/* place holder for contiguous memory */
+	},
+};
+
+static struct platform_device vpu_device = {
+	.name		= "uio_pdrv_genirq",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &vpu_platform_data,
+	},
+	.resource	= vpu_resources,
+	.num_resources	= ARRAY_SIZE(vpu_resources),
+};
+
+/* VEU0 */
+static struct uio_info veu0_platform_data = {
+	.name = "VEU3F0",
+	.version = "0",
+	.irq = 83,
+};
+
+static struct resource veu0_resources[] = {
+	[0] = {
+		.name	= "VEU3F0",
+		.start	= 0xfe920000,
+		.end	= 0xfe9200cb - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		/* place holder for contiguous memory */
+	},
+};
+
+static struct platform_device veu0_device = {
+	.name		= "uio_pdrv_genirq",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &veu0_platform_data,
+	},
+	.resource	= veu0_resources,
+	.num_resources	= ARRAY_SIZE(veu0_resources),
+};
+
+/* VEU1 */
+static struct uio_info veu1_platform_data = {
+	.name = "VEU3F1",
+	.version = "0",
+	.irq = 54,
+};
+
+static struct resource veu1_resources[] = {
+	[0] = {
+		.name	= "VEU3F1",
+		.start	= 0xfe924000,
+		.end	= 0xfe9240cb - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		/* place holder for contiguous memory */
+	},
+};
+
+static struct platform_device veu1_device = {
+	.name		= "uio_pdrv_genirq",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &veu1_platform_data,
+	},
+	.resource	= veu1_resources,
+	.num_resources	= ARRAY_SIZE(veu1_resources),
+};
+
+static struct sh_timer_config cmt_platform_data = {
+	.name = "CMT",
+	.channel_offset = 0x60,
+	.timer_bit = 5,
+	.clk = "cmt0",
+	.clockevent_rating = 125,
+	.clocksource_rating = 200,
+};
+
+static struct resource cmt_resources[] = {
+	[0] = {
+		.name	= "CMT",
+		.start	= 0x044a0060,
+		.end	= 0x044a006b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 104,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device cmt_device = {
+	.name		= "sh_cmt",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &cmt_platform_data,
+	},
+	.resource	= cmt_resources,
+	.num_resources	= ARRAY_SIZE(cmt_resources),
+};
+
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "tmu0",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "tmu0",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "tmu0",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+
+static struct sh_timer_config tmu3_platform_data = {
+	.name = "TMU3",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "tmu1",
+};
+
+static struct resource tmu3_resources[] = {
+	[0] = {
+		.name	= "TMU3",
+		.start	= 0xffd90008,
+		.end	= 0xffd90013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 57,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu3_device = {
+	.name		= "sh_tmu",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &tmu3_platform_data,
+	},
+	.resource	= tmu3_resources,
+	.num_resources	= ARRAY_SIZE(tmu3_resources),
+};
+
+static struct sh_timer_config tmu4_platform_data = {
+	.name = "TMU4",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "tmu1",
+};
+
+static struct resource tmu4_resources[] = {
+	[0] = {
+		.name	= "TMU4",
+		.start	= 0xffd90014,
+		.end	= 0xffd9001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 58,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu4_device = {
+	.name		= "sh_tmu",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &tmu4_platform_data,
+	},
+	.resource	= tmu4_resources,
+	.num_resources	= ARRAY_SIZE(tmu4_resources),
+};
+
+static struct sh_timer_config tmu5_platform_data = {
+	.name = "TMU5",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "tmu1",
+};
+
+static struct resource tmu5_resources[] = {
+	[0] = {
+		.name	= "TMU5",
+		.start	= 0xffd90020,
+		.end	= 0xffd9002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 57,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu5_device = {
+	.name		= "sh_tmu",
+	.id		= 5,
+	.dev = {
+		.platform_data	= &tmu5_platform_data,
+	},
+	.resource	= tmu5_resources,
+	.num_resources	= ARRAY_SIZE(tmu5_resources),
+};
+
+/* JPU */
+static struct uio_info jpu_platform_data = {
+	.name = "JPU",
+	.version = "0",
+	.irq = 27,
+};
+
+static struct resource jpu_resources[] = {
+	[0] = {
+		.name	= "JPU",
+		.start	= 0xfe980000,
+		.end	= 0xfe9902d3,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		/* place holder for contiguous memory */
+	},
+};
+
+static struct platform_device jpu_device = {
+	.name		= "uio_pdrv_genirq",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &jpu_platform_data,
+	},
+	.resource	= jpu_resources,
+	.num_resources	= ARRAY_SIZE(jpu_resources),
+};
+
+static struct platform_device *sh7724_devices[] __initdata = {
+	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+	&sci_device,
+	&rtc_device,
+	&iic0_device,
+	&iic1_device,
+	&vpu_device,
+	&veu0_device,
+	&veu1_device,
+	&jpu_device,
+};
+
+static int __init sh7724_devices_setup(void)
+{
+	platform_resource_setup_memory(&vpu_device, "vpu", 2 << 20);
+	platform_resource_setup_memory(&veu0_device, "veu0", 2 << 20);
+	platform_resource_setup_memory(&veu1_device, "veu1", 2 << 20);
+	platform_resource_setup_memory(&jpu_device,  "jpu",  2 << 20);
+
+	return platform_add_devices(sh7724_devices,
+				    ARRAY_SIZE(sh7724_devices));
+}
+device_initcall(sh7724_devices_setup);
+
+static struct platform_device *sh7724_early_devices[] __initdata = {
+	&cmt_device,
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7724_early_devices,
+				   ARRAY_SIZE(sh7724_early_devices));
+}
+
+#define RAMCR_CACHE_L2FC	0x0002
+#define RAMCR_CACHE_L2E		0x0001
+#define L2_CACHE_ENABLE		(RAMCR_CACHE_L2E|RAMCR_CACHE_L2FC)
+void __uses_jump_to_uncached l2_cache_init(void)
+{
+	/* Enable L2 cache */
+	ctrl_outl(L2_CACHE_ENABLE, RAMCR);
+}
+
+enum {
+	UNUSED = 0,
+
+	/* interrupt sources */
+	IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7,
+	HUDI,
+	DMAC1A_DEI0, DMAC1A_DEI1, DMAC1A_DEI2, DMAC1A_DEI3,
+	_2DG_TRI, _2DG_INI, _2DG_CEI,
+	DMAC0A_DEI0, DMAC0A_DEI1, DMAC0A_DEI2, DMAC0A_DEI3,
+	VIO_CEU0, VIO_BEU0, VIO_VEU1, VIO_VOU,
+	SCIFA3,
+	VPU,
+	TPU,
+	CEU1,
+	BEU1,
+	USB0, USB1,
+	ATAPI,
+	RTC_ATI, RTC_PRI, RTC_CUI,
+	DMAC1B_DEI4, DMAC1B_DEI5, DMAC1B_DADERR,
+	DMAC0B_DEI4, DMAC0B_DEI5, DMAC0B_DADERR,
+	KEYSC,
+	SCIF_SCIF0, SCIF_SCIF1, SCIF_SCIF2,
+	VEU0,
+	MSIOF_MSIOFI0, MSIOF_MSIOFI1,
+	SPU_SPUI0, SPU_SPUI1,
+	SCIFA4,
+	ICB,
+	ETHI,
+	I2C1_ALI, I2C1_TACKI, I2C1_WAITI, I2C1_DTEI,
+	I2C0_ALI, I2C0_TACKI, I2C0_WAITI, I2C0_DTEI,
+	SDHI0_SDHII0, SDHI0_SDHII1, SDHI0_SDHII2, SDHI0_SDHII3,
+	CMT,
+	TSIF,
+	FSI,
+	SCIFA5,
+	TMU0_TUNI0, TMU0_TUNI1, TMU0_TUNI2,
+	IRDA,
+	SDHI1_SDHII0, SDHI1_SDHII1, SDHI1_SDHII2,
+	JPU,
+	_2DDMAC,
+	MMC_MMC2I, MMC_MMC3I,
+	LCDC,
+	TMU1_TUNI0, TMU1_TUNI1, TMU1_TUNI2,
+
+	/* interrupt groups */
+	DMAC1A, _2DG, DMAC0A, VIO, USB, RTC,
+	DMAC1B, DMAC0B, I2C0, I2C1, SDHI0, SDHI1, SPU, MMCIF,
+};
+
+static struct intc_vect vectors[] __initdata = {
+	INTC_VECT(IRQ0, 0x600), INTC_VECT(IRQ1, 0x620),
+	INTC_VECT(IRQ2, 0x640), INTC_VECT(IRQ3, 0x660),
+	INTC_VECT(IRQ4, 0x680), INTC_VECT(IRQ5, 0x6a0),
+	INTC_VECT(IRQ6, 0x6c0), INTC_VECT(IRQ7, 0x6e0),
+
+	INTC_VECT(DMAC1A_DEI0, 0x700),
+	INTC_VECT(DMAC1A_DEI1, 0x720),
+	INTC_VECT(DMAC1A_DEI2, 0x740),
+	INTC_VECT(DMAC1A_DEI3, 0x760),
+
+	INTC_VECT(_2DG_TRI, 0x780),
+	INTC_VECT(_2DG_INI, 0x7A0),
+	INTC_VECT(_2DG_CEI, 0x7C0),
+
+	INTC_VECT(DMAC0A_DEI0, 0x800),
+	INTC_VECT(DMAC0A_DEI1, 0x820),
+	INTC_VECT(DMAC0A_DEI2, 0x840),
+	INTC_VECT(DMAC0A_DEI3, 0x860),
+
+	INTC_VECT(VIO_CEU0, 0x880),
+	INTC_VECT(VIO_BEU0, 0x8A0),
+	INTC_VECT(VIO_VEU1, 0x8C0),
+	INTC_VECT(VIO_VOU,  0x8E0),
+
+	INTC_VECT(SCIFA3, 0x900),
+	INTC_VECT(VPU,    0x980),
+	INTC_VECT(TPU,    0x9A0),
+	INTC_VECT(CEU1,   0x9E0),
+	INTC_VECT(BEU1,   0xA00),
+	INTC_VECT(USB0,   0xA20),
+	INTC_VECT(USB1,   0xA40),
+	INTC_VECT(ATAPI,  0xA60),
+
+	INTC_VECT(RTC_ATI, 0xA80),
+	INTC_VECT(RTC_PRI, 0xAA0),
+	INTC_VECT(RTC_CUI, 0xAC0),
+
+	INTC_VECT(DMAC1B_DEI4, 0xB00),
+	INTC_VECT(DMAC1B_DEI5, 0xB20),
+	INTC_VECT(DMAC1B_DADERR, 0xB40),
+
+	INTC_VECT(DMAC0B_DEI4, 0xB80),
+	INTC_VECT(DMAC0B_DEI5, 0xBA0),
+	INTC_VECT(DMAC0B_DADERR, 0xBC0),
+
+	INTC_VECT(KEYSC,      0xBE0),
+	INTC_VECT(SCIF_SCIF0, 0xC00),
+	INTC_VECT(SCIF_SCIF1, 0xC20),
+	INTC_VECT(SCIF_SCIF2, 0xC40),
+	INTC_VECT(VEU0,       0xC60),
+	INTC_VECT(MSIOF_MSIOFI0, 0xC80),
+	INTC_VECT(MSIOF_MSIOFI1, 0xCA0),
+	INTC_VECT(SPU_SPUI0, 0xCC0),
+	INTC_VECT(SPU_SPUI1, 0xCE0),
+	INTC_VECT(SCIFA4,    0xD00),
+
+	INTC_VECT(ICB,  0xD20),
+	INTC_VECT(ETHI, 0xD60),
+
+	INTC_VECT(I2C1_ALI, 0xD80),
+	INTC_VECT(I2C1_TACKI, 0xDA0),
+	INTC_VECT(I2C1_WAITI, 0xDC0),
+	INTC_VECT(I2C1_DTEI, 0xDE0),
+
+	INTC_VECT(I2C0_ALI, 0xE00),
+	INTC_VECT(I2C0_TACKI, 0xE20),
+	INTC_VECT(I2C0_WAITI, 0xE40),
+	INTC_VECT(I2C0_DTEI, 0xE60),
+
+	INTC_VECT(SDHI0_SDHII0, 0xE80),
+	INTC_VECT(SDHI0_SDHII1, 0xEA0),
+	INTC_VECT(SDHI0_SDHII2, 0xEC0),
+	INTC_VECT(SDHI0_SDHII3, 0xEE0),
+
+	INTC_VECT(CMT,    0xF00),
+	INTC_VECT(TSIF,   0xF20),
+	INTC_VECT(FSI,    0xF80),
+	INTC_VECT(SCIFA5, 0xFA0),
+
+	INTC_VECT(TMU0_TUNI0, 0x400),
+	INTC_VECT(TMU0_TUNI1, 0x420),
+	INTC_VECT(TMU0_TUNI2, 0x440),
+
+	INTC_VECT(IRDA,    0x480),
+
+	INTC_VECT(SDHI1_SDHII0, 0x4E0),
+	INTC_VECT(SDHI1_SDHII1, 0x500),
+	INTC_VECT(SDHI1_SDHII2, 0x520),
+
+	INTC_VECT(JPU, 0x560),
+	INTC_VECT(_2DDMAC, 0x4A0),
+
+	INTC_VECT(MMC_MMC2I, 0x5A0),
+	INTC_VECT(MMC_MMC3I, 0x5C0),
+
+	INTC_VECT(LCDC, 0xF40),
+
+	INTC_VECT(TMU1_TUNI0, 0x920),
+	INTC_VECT(TMU1_TUNI1, 0x940),
+	INTC_VECT(TMU1_TUNI2, 0x960),
+};
+
+static struct intc_group groups[] __initdata = {
+	INTC_GROUP(DMAC1A, DMAC1A_DEI0, DMAC1A_DEI1, DMAC1A_DEI2, DMAC1A_DEI3),
+	INTC_GROUP(_2DG, _2DG_TRI, _2DG_INI, _2DG_CEI),
+	INTC_GROUP(DMAC0A, DMAC0A_DEI0, DMAC0A_DEI1, DMAC0A_DEI2, DMAC0A_DEI3),
+	INTC_GROUP(VIO, VIO_CEU0, VIO_BEU0, VIO_VEU1, VIO_VOU),
+	INTC_GROUP(USB, USB0, USB1),
+	INTC_GROUP(RTC, RTC_ATI, RTC_PRI, RTC_CUI),
+	INTC_GROUP(DMAC1B, DMAC1B_DEI4, DMAC1B_DEI5, DMAC1B_DADERR),
+	INTC_GROUP(DMAC0B, DMAC0B_DEI4, DMAC0B_DEI5, DMAC0B_DADERR),
+	INTC_GROUP(I2C0, I2C0_ALI, I2C0_TACKI, I2C0_WAITI, I2C0_DTEI),
+	INTC_GROUP(I2C1, I2C1_ALI, I2C1_TACKI, I2C1_WAITI, I2C1_DTEI),
+	INTC_GROUP(SDHI0, SDHI0_SDHII0, SDHI0_SDHII1, SDHI0_SDHII2, SDHI0_SDHII3),
+	INTC_GROUP(SDHI1, SDHI1_SDHII0, SDHI1_SDHII1, SDHI1_SDHII2),
+	INTC_GROUP(SPU, SPU_SPUI0, SPU_SPUI1),
+	INTC_GROUP(MMCIF, MMC_MMC2I, MMC_MMC3I),
+};
+
+static struct intc_mask_reg mask_registers[] __initdata = {
+	{ 0xa4080080, 0xa40800c0, 8, /* IMR0 / IMCR0 */
+	  { 0, TMU1_TUNI2, TMU1_TUNI1, TMU1_TUNI0,
+	    0, SDHI1_SDHII2, SDHI1_SDHII1, SDHI1_SDHII0 } },
+	{ 0xa4080084, 0xa40800c4, 8, /* IMR1 / IMCR1 */
+	  { VIO_VOU, VIO_VEU1, VIO_BEU0, VIO_CEU0,
+	    DMAC0A_DEI3, DMAC0A_DEI2, DMAC0A_DEI1, DMAC0A_DEI0 } },
+	{ 0xa4080088, 0xa40800c8, 8, /* IMR2 / IMCR2 */
+	  { 0, 0, 0, VPU, ATAPI, ETHI, 0, SCIFA3 } },
+	{ 0xa408008c, 0xa40800cc, 8, /* IMR3 / IMCR3 */
+	  { DMAC1A_DEI3, DMAC1A_DEI2, DMAC1A_DEI1, DMAC1A_DEI0,
+	    SPU_SPUI1, SPU_SPUI0, BEU1, IRDA } },
+	{ 0xa4080090, 0xa40800d0, 8, /* IMR4 / IMCR4 */
+	  { 0, TMU0_TUNI2, TMU0_TUNI1, TMU0_TUNI0,
+	    JPU, 0, 0, LCDC } },
+	{ 0xa4080094, 0xa40800d4, 8, /* IMR5 / IMCR5 */
+	  { KEYSC, DMAC0B_DADERR, DMAC0B_DEI5, DMAC0B_DEI4,
+	    VEU0, SCIF_SCIF2, SCIF_SCIF1, SCIF_SCIF0 } },
+	{ 0xa4080098, 0xa40800d8, 8, /* IMR6 / IMCR6 */
+	  { 0, 0, ICB, SCIFA4,
+	    CEU1, 0, MSIOF_MSIOFI1, MSIOF_MSIOFI0 } },
+	{ 0xa408009c, 0xa40800dc, 8, /* IMR7 / IMCR7 */
+	  { I2C0_DTEI, I2C0_WAITI, I2C0_TACKI, I2C0_ALI,
+	    I2C1_DTEI, I2C1_WAITI, I2C1_TACKI, I2C1_ALI } },
+	{ 0xa40800a0, 0xa40800e0, 8, /* IMR8 / IMCR8 */
+	  { SDHI0_SDHII3, SDHI0_SDHII2, SDHI0_SDHII1, SDHI0_SDHII0,
+	    0, 0, SCIFA5, FSI } },
+	{ 0xa40800a4, 0xa40800e4, 8, /* IMR9 / IMCR9 */
+	  { 0, 0, 0, CMT, 0, USB1, USB0, 0 } },
+	{ 0xa40800a8, 0xa40800e8, 8, /* IMR10 / IMCR10 */
+	  { 0, DMAC1B_DADERR, DMAC1B_DEI5, DMAC1B_DEI4,
+	    0, RTC_CUI, RTC_PRI, RTC_ATI } },
+	{ 0xa40800ac, 0xa40800ec, 8, /* IMR11 / IMCR11 */
+	  { 0, _2DG_CEI, _2DG_INI, _2DG_TRI,
+	    0, TPU, 0, TSIF } },
+	{ 0xa40800b0, 0xa40800f0, 8, /* IMR12 / IMCR12 */
+	  { 0, 0, MMC_MMC3I, MMC_MMC2I, 0, 0, 0, _2DDMAC } },
+	{ 0xa4140044, 0xa4140064, 8, /* INTMSK00 / INTMSKCLR00 */
+	  { IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7 } },
+};
+
+static struct intc_prio_reg prio_registers[] __initdata = {
+	{ 0xa4080000, 0, 16, 4, /* IPRA */ { TMU0_TUNI0, TMU0_TUNI1,
+					     TMU0_TUNI2, IRDA } },
+	{ 0xa4080004, 0, 16, 4, /* IPRB */ { JPU, LCDC, DMAC1A, BEU1 } },
+	{ 0xa4080008, 0, 16, 4, /* IPRC */ { TMU1_TUNI0, TMU1_TUNI1,
+					     TMU1_TUNI2, SPU } },
+	{ 0xa408000c, 0, 16, 4, /* IPRD */ { 0, MMCIF, 0, ATAPI } },
+	{ 0xa4080010, 0, 16, 4, /* IPRE */ { DMAC0A, VIO, SCIFA3, VPU } },
+	{ 0xa4080014, 0, 16, 4, /* IPRF */ { KEYSC, DMAC0B, USB, CMT } },
+	{ 0xa4080018, 0, 16, 4, /* IPRG */ { SCIF_SCIF0, SCIF_SCIF1,
+					     SCIF_SCIF2, VEU0 } },
+	{ 0xa408001c, 0, 16, 4, /* IPRH */ { MSIOF_MSIOFI0, MSIOF_MSIOFI1,
+					     I2C1, I2C0 } },
+	{ 0xa4080020, 0, 16, 4, /* IPRI */ { SCIFA4, ICB, TSIF, _2DG } },
+	{ 0xa4080024, 0, 16, 4, /* IPRJ */ { CEU1, ETHI, FSI, SDHI1 } },
+	{ 0xa4080028, 0, 16, 4, /* IPRK */ { RTC, DMAC1B, 0, SDHI0 } },
+	{ 0xa408002c, 0, 16, 4, /* IPRL */ { SCIFA5, 0, TPU, _2DDMAC } },
+	{ 0xa4140010, 0, 32, 4, /* INTPRI00 */
+	  { IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7 } },
+};
+
+static struct intc_sense_reg sense_registers[] __initdata = {
+	{ 0xa414001c, 16, 2, /* ICR1 */
+	  { IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7 } },
+};
+
+static struct intc_mask_reg ack_registers[] __initdata = {
+	{ 0xa4140024, 0, 8, /* INTREQ00 */
+	  { IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7 } },
+};
+
+static DECLARE_INTC_DESC_ACK(intc_desc, "sh7724", vectors, groups,
+			     mask_registers, prio_registers, sense_registers,
+			     ack_registers);
+
+void __init plat_irq_setup(void)
+{
+	register_intc_controller(&intc_desc);
+}
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c
index bdf0f61ae1ed..f1e0c0d36da7 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c
@@ -12,6 +12,7 @@
 #include <linux/platform_device.h>
 #include <linux/init.h>
 #include <linux/serial.h>
+#include <linux/sh_timer.h>
 #include <linux/io.h>
 #include <linux/serial_sci.h>
 
@@ -113,7 +114,195 @@ static struct platform_device usbf_device = {
 	.resource	= usbf_resources,
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 28,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 29,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 30,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+static struct sh_timer_config tmu3_platform_data = {
+	.name = "TMU3",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu3_resources[] = {
+	[0] = {
+		.name	= "TMU3",
+		.start	= 0xffd88008,
+		.end	= 0xffd88013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 96,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu3_device = {
+	.name		= "sh_tmu",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &tmu3_platform_data,
+	},
+	.resource	= tmu3_resources,
+	.num_resources	= ARRAY_SIZE(tmu3_resources),
+};
+
+static struct sh_timer_config tmu4_platform_data = {
+	.name = "TMU4",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu4_resources[] = {
+	[0] = {
+		.name	= "TMU4",
+		.start	= 0xffd88014,
+		.end	= 0xffd8801f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 97,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu4_device = {
+	.name		= "sh_tmu",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &tmu4_platform_data,
+	},
+	.resource	= tmu4_resources,
+	.num_resources	= ARRAY_SIZE(tmu4_resources),
+};
+
+static struct sh_timer_config tmu5_platform_data = {
+	.name = "TMU5",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu5_resources[] = {
+	[0] = {
+		.name	= "TMU5",
+		.start	= 0xffd88020,
+		.end	= 0xffd8802b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 98,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu5_device = {
+	.name		= "sh_tmu",
+	.id		= 5,
+	.dev = {
+		.platform_data	= &tmu5_platform_data,
+	},
+	.resource	= tmu5_resources,
+	.num_resources	= ARRAY_SIZE(tmu5_resources),
+};
+
 static struct platform_device *sh7763_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
 	&rtc_device,
 	&sci_device,
 	&usb_ohci_device,
@@ -127,6 +316,21 @@ static int __init sh7763_devices_setup(void)
 }
 __initcall(sh7763_devices_setup);
 
+static struct platform_device *sh7763_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7763_early_devices,
+				   ARRAY_SIZE(sh7763_early_devices));
+}
+
 enum {
 	UNUSED = 0,
 
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c
index b73578ee295d..1e86209db284 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c
@@ -11,6 +11,8 @@
 #include <linux/init.h>
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
+#include <linux/io.h>
 
 static struct plat_sci_port sci_platform_data[] = {
 	{
@@ -76,7 +78,288 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+static struct sh_timer_config tmu3_platform_data = {
+	.name = "TMU3",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu3_resources[] = {
+	[0] = {
+		.name	= "TMU3",
+		.start	= 0xffd81008,
+		.end	= 0xffd81013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 19,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu3_device = {
+	.name		= "sh_tmu",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &tmu3_platform_data,
+	},
+	.resource	= tmu3_resources,
+	.num_resources	= ARRAY_SIZE(tmu3_resources),
+};
+
+static struct sh_timer_config tmu4_platform_data = {
+	.name = "TMU4",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu4_resources[] = {
+	[0] = {
+		.name	= "TMU4",
+		.start	= 0xffd81014,
+		.end	= 0xffd8101f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 20,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu4_device = {
+	.name		= "sh_tmu",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &tmu4_platform_data,
+	},
+	.resource	= tmu4_resources,
+	.num_resources	= ARRAY_SIZE(tmu4_resources),
+};
+
+static struct sh_timer_config tmu5_platform_data = {
+	.name = "TMU5",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu5_resources[] = {
+	[0] = {
+		.name	= "TMU5",
+		.start	= 0xffd81020,
+		.end	= 0xffd8102f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 21,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu5_device = {
+	.name		= "sh_tmu",
+	.id		= 5,
+	.dev = {
+		.platform_data	= &tmu5_platform_data,
+	},
+	.resource	= tmu5_resources,
+	.num_resources	= ARRAY_SIZE(tmu5_resources),
+};
+
+static struct sh_timer_config tmu6_platform_data = {
+	.name = "TMU6",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu6_resources[] = {
+	[0] = {
+		.name	= "TMU6",
+		.start	= 0xffd82008,
+		.end	= 0xffd82013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 22,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu6_device = {
+	.name		= "sh_tmu",
+	.id		= 6,
+	.dev = {
+		.platform_data	= &tmu6_platform_data,
+	},
+	.resource	= tmu6_resources,
+	.num_resources	= ARRAY_SIZE(tmu6_resources),
+};
+
+static struct sh_timer_config tmu7_platform_data = {
+	.name = "TMU7",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu7_resources[] = {
+	[0] = {
+		.name	= "TMU7",
+		.start	= 0xffd82014,
+		.end	= 0xffd8201f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 23,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu7_device = {
+	.name		= "sh_tmu",
+	.id		= 7,
+	.dev = {
+		.platform_data	= &tmu7_platform_data,
+	},
+	.resource	= tmu7_resources,
+	.num_resources	= ARRAY_SIZE(tmu7_resources),
+};
+
+static struct sh_timer_config tmu8_platform_data = {
+	.name = "TMU8",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu8_resources[] = {
+	[0] = {
+		.name	= "TMU8",
+		.start	= 0xffd82020,
+		.end	= 0xffd8202b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 24,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu8_device = {
+	.name		= "sh_tmu",
+	.id		= 8,
+	.dev = {
+		.platform_data	= &tmu8_platform_data,
+	},
+	.resource	= tmu8_resources,
+	.num_resources	= ARRAY_SIZE(tmu8_resources),
+};
+
 static struct platform_device *sh7770_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+	&tmu6_device,
+	&tmu7_device,
+	&tmu8_device,
 	&sci_device,
 };
 
@@ -87,6 +370,269 @@ static int __init sh7770_devices_setup(void)
 }
 __initcall(sh7770_devices_setup);
 
+static struct platform_device *sh7770_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+	&tmu6_device,
+	&tmu7_device,
+	&tmu8_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7770_early_devices,
+				   ARRAY_SIZE(sh7770_early_devices));
+}
+
+enum {
+	UNUSED = 0,
+
+	/* interrupt sources */
+	IRL_LLLL, IRL_LLLH, IRL_LLHL, IRL_LLHH,
+	IRL_LHLL, IRL_LHLH, IRL_LHHL, IRL_LHHH,
+	IRL_HLLL, IRL_HLLH, IRL_HLHL, IRL_HLHH,
+	IRL_HHLL, IRL_HHLH, IRL_HHHL,
+
+	IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5,
+
+	GPIO,
+	TMU0, TMU1, TMU2, TMU2_TICPI,
+	TMU3, TMU4, TMU5, TMU5_TICPI,
+	TMU6, TMU7, TMU8,
+	HAC, IPI, SPDIF, HUDI, I2C,
+	DMAC0_DMINT0, DMAC0_DMINT1, DMAC0_DMINT2,
+	I2S0, I2S1, I2S2, I2S3,
+	SRC_RX, SRC_TX, SRC_SPDIF,
+	DU, VIDEO_IN, REMOTE, YUV, USB, ATAPI, CAN, GPS, GFX2D,
+	GFX3D_MBX, GFX3D_DMAC,
+	EXBUS_ATA,
+	SPI0, SPI1,
+	SCIF089, SCIF1234, SCIF567,
+	ADC,
+	BBDMAC_0_3, BBDMAC_4_7, BBDMAC_8_10, BBDMAC_11_14,
+	BBDMAC_15_18, BBDMAC_19_22, BBDMAC_23_26, BBDMAC_27,
+	BBDMAC_28, BBDMAC_29, BBDMAC_30, BBDMAC_31,
+
+	/* interrupt groups */
+	TMU, DMAC, I2S, SRC, GFX3D, SPI, SCIF, BBDMAC,
+};
+
+static struct intc_vect vectors[] __initdata = {
+	INTC_VECT(GPIO, 0x3e0),
+	INTC_VECT(TMU0, 0x400), INTC_VECT(TMU1, 0x420),
+	INTC_VECT(TMU2, 0x440), INTC_VECT(TMU2_TICPI, 0x460),
+	INTC_VECT(TMU3, 0x480), INTC_VECT(TMU4, 0x4a0),
+	INTC_VECT(TMU5, 0x4c0), INTC_VECT(TMU5_TICPI, 0x4e0),
+	INTC_VECT(TMU6, 0x500), INTC_VECT(TMU7, 0x520),
+	INTC_VECT(TMU8, 0x540),
+	INTC_VECT(HAC, 0x580), INTC_VECT(IPI, 0x5c0),
+	INTC_VECT(SPDIF, 0x5e0),
+	INTC_VECT(HUDI, 0x600), INTC_VECT(I2C, 0x620),
+	INTC_VECT(DMAC0_DMINT0, 0x640), INTC_VECT(DMAC0_DMINT1, 0x660),
+	INTC_VECT(DMAC0_DMINT2, 0x680),
+	INTC_VECT(I2S0, 0x6a0), INTC_VECT(I2S1, 0x6c0),
+	INTC_VECT(I2S2, 0x6e0), INTC_VECT(I2S3, 0x700),
+	INTC_VECT(SRC_RX, 0x720), INTC_VECT(SRC_TX, 0x740),
+	INTC_VECT(SRC_SPDIF, 0x760),
+	INTC_VECT(DU, 0x780), INTC_VECT(VIDEO_IN, 0x7a0),
+	INTC_VECT(REMOTE, 0x7c0), INTC_VECT(YUV, 0x7e0),
+	INTC_VECT(USB, 0x840), INTC_VECT(ATAPI, 0x860),
+	INTC_VECT(CAN, 0x880), INTC_VECT(GPS, 0x8a0),
+	INTC_VECT(GFX2D, 0x8c0),
+	INTC_VECT(GFX3D_MBX, 0x900), INTC_VECT(GFX3D_DMAC, 0x920),
+	INTC_VECT(EXBUS_ATA, 0x940),
+	INTC_VECT(SPI0, 0x960), INTC_VECT(SPI1, 0x980),
+	INTC_VECT(SCIF089, 0x9a0), INTC_VECT(SCIF1234, 0x9c0),
+	INTC_VECT(SCIF1234, 0x9e0), INTC_VECT(SCIF1234, 0xa00),
+	INTC_VECT(SCIF1234, 0xa20), INTC_VECT(SCIF567, 0xa40),
+	INTC_VECT(SCIF567, 0xa60), INTC_VECT(SCIF567, 0xa80),
+	INTC_VECT(SCIF089, 0xaa0), INTC_VECT(SCIF089, 0xac0),
+	INTC_VECT(ADC, 0xb20),
+	INTC_VECT(BBDMAC_0_3, 0xba0), INTC_VECT(BBDMAC_0_3, 0xbc0),
+	INTC_VECT(BBDMAC_0_3, 0xbe0), INTC_VECT(BBDMAC_0_3, 0xc00),
+	INTC_VECT(BBDMAC_4_7, 0xc20), INTC_VECT(BBDMAC_4_7, 0xc40),
+	INTC_VECT(BBDMAC_4_7, 0xc60), INTC_VECT(BBDMAC_4_7, 0xc80),
+	INTC_VECT(BBDMAC_8_10, 0xca0), INTC_VECT(BBDMAC_8_10, 0xcc0),
+	INTC_VECT(BBDMAC_8_10, 0xce0), INTC_VECT(BBDMAC_11_14, 0xd00),
+	INTC_VECT(BBDMAC_11_14, 0xd20), INTC_VECT(BBDMAC_11_14, 0xd40),
+	INTC_VECT(BBDMAC_11_14, 0xd60), INTC_VECT(BBDMAC_15_18, 0xd80),
+	INTC_VECT(BBDMAC_15_18, 0xda0), INTC_VECT(BBDMAC_15_18, 0xdc0),
+	INTC_VECT(BBDMAC_15_18, 0xde0), INTC_VECT(BBDMAC_19_22, 0xe00),
+	INTC_VECT(BBDMAC_19_22, 0xe20), INTC_VECT(BBDMAC_19_22, 0xe40),
+	INTC_VECT(BBDMAC_19_22, 0xe60), INTC_VECT(BBDMAC_23_26, 0xe80),
+	INTC_VECT(BBDMAC_23_26, 0xea0), INTC_VECT(BBDMAC_23_26, 0xec0),
+	INTC_VECT(BBDMAC_23_26, 0xee0), INTC_VECT(BBDMAC_27, 0xf00),
+	INTC_VECT(BBDMAC_28, 0xf20), INTC_VECT(BBDMAC_29, 0xf40),
+	INTC_VECT(BBDMAC_30, 0xf60), INTC_VECT(BBDMAC_31, 0xf80),
+};
+
+static struct intc_group groups[] __initdata = {
+	INTC_GROUP(TMU, TMU0, TMU1, TMU2, TMU2_TICPI, TMU3, TMU4, TMU5,
+		   TMU5_TICPI, TMU6, TMU7, TMU8),
+	INTC_GROUP(DMAC, DMAC0_DMINT0, DMAC0_DMINT1, DMAC0_DMINT2),
+	INTC_GROUP(I2S, I2S0, I2S1, I2S2, I2S3),
+	INTC_GROUP(SRC, SRC_RX, SRC_TX, SRC_SPDIF),
+	INTC_GROUP(GFX3D, GFX3D_MBX, GFX3D_DMAC),
+	INTC_GROUP(SPI, SPI0, SPI1),
+	INTC_GROUP(SCIF, SCIF089, SCIF1234, SCIF567),
+	INTC_GROUP(BBDMAC,
+		   BBDMAC_0_3, BBDMAC_4_7, BBDMAC_8_10, BBDMAC_11_14,
+		   BBDMAC_15_18, BBDMAC_19_22, BBDMAC_23_26, BBDMAC_27,
+		   BBDMAC_28, BBDMAC_29, BBDMAC_30, BBDMAC_31),
+};
+
+static struct intc_mask_reg mask_registers[] __initdata = {
+	{ 0xffe00040, 0xffe00044, 32, /* INT2MSKR / INT2MSKCR */
+	  { 0, BBDMAC, ADC, SCIF, SPI, EXBUS_ATA, GFX3D, GFX2D,
+	    GPS, CAN, ATAPI, USB, YUV, REMOTE, VIDEO_IN, DU, SRC, I2S,
+	    DMAC, I2C, HUDI, SPDIF, IPI, HAC, TMU, GPIO } },
+};
+
+static struct intc_prio_reg prio_registers[] __initdata = {
+	{ 0xffe00000, 0, 32, 8, /* INT2PRI0 */ { GPIO, TMU0, 0, HAC } },
+	{ 0xffe00004, 0, 32, 8, /* INT2PRI1 */ { IPI, SPDIF, HUDI, I2C } },
+	{ 0xffe00008, 0, 32, 8, /* INT2PRI2 */ { DMAC, I2S, SRC, DU } },
+	{ 0xffe0000c, 0, 32, 8, /* INT2PRI3 */ { VIDEO_IN, REMOTE, YUV, USB } },
+	{ 0xffe00010, 0, 32, 8, /* INT2PRI4 */ { ATAPI, CAN, GPS, GFX2D } },
+	{ 0xffe00014, 0, 32, 8, /* INT2PRI5 */ { 0, GFX3D, EXBUS_ATA, SPI } },
+	{ 0xffe00018, 0, 32, 8, /* INT2PRI6 */ { SCIF1234, SCIF567, SCIF089 } },
+	{ 0xffe0001c, 0, 32, 8, /* INT2PRI7 */ { ADC, 0, 0, BBDMAC_0_3 } },
+	{ 0xffe00020, 0, 32, 8, /* INT2PRI8 */
+	  { BBDMAC_4_7, BBDMAC_8_10, BBDMAC_11_14, BBDMAC_15_18 } },
+	{ 0xffe00024, 0, 32, 8, /* INT2PRI9 */
+	  { BBDMAC_19_22, BBDMAC_23_26, BBDMAC_27, BBDMAC_28 } },
+	{ 0xffe00028, 0, 32, 8, /* INT2PRI10 */
+	  { BBDMAC_29, BBDMAC_30, BBDMAC_31 } },
+	{ 0xffe0002c, 0, 32, 8, /* INT2PRI11 */
+	  { TMU1, TMU2, TMU2_TICPI, TMU3 } },
+	{ 0xffe00030, 0, 32, 8, /* INT2PRI12 */
+	  { TMU4, TMU5, TMU5_TICPI, TMU6 } },
+	{ 0xffe00034, 0, 32, 8, /* INT2PRI13 */
+	  { TMU7, TMU8 } },
+};
+
+static DECLARE_INTC_DESC(intc_desc, "sh7770", vectors, groups,
+			 mask_registers, prio_registers, NULL);
+
+/* Support for external interrupt pins in IRQ mode */
+static struct intc_vect irq_vectors[] __initdata = {
+	INTC_VECT(IRQ0, 0x240), INTC_VECT(IRQ1, 0x280),
+	INTC_VECT(IRQ2, 0x2c0), INTC_VECT(IRQ3, 0x300),
+	INTC_VECT(IRQ4, 0x340), INTC_VECT(IRQ5, 0x380),
+};
+
+static struct intc_mask_reg irq_mask_registers[] __initdata = {
+	{ 0xffd00044, 0xffd00064, 32, /* INTMSK0 / INTMSKCLR0 */
+	  { IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, } },
+};
+
+static struct intc_prio_reg irq_prio_registers[] __initdata = {
+	{ 0xffd00010, 0, 32, 4, /* INTPRI */ { IRQ0, IRQ1, IRQ2, IRQ3,
+					       IRQ4, IRQ5, } },
+};
+
+static struct intc_sense_reg irq_sense_registers[] __initdata = {
+	{ 0xffd0001c, 32, 2, /* ICR1 */   { IRQ0, IRQ1, IRQ2, IRQ3,
+					    IRQ4, IRQ5, } },
+};
+
+static DECLARE_INTC_DESC(intc_irq_desc, "sh7770-irq", irq_vectors,
+			 NULL, irq_mask_registers, irq_prio_registers,
+			 irq_sense_registers);
+
+/* External interrupt pins in IRL mode */
+static struct intc_vect irl_vectors[] __initdata = {
+	INTC_VECT(IRL_LLLL, 0x200), INTC_VECT(IRL_LLLH, 0x220),
+	INTC_VECT(IRL_LLHL, 0x240), INTC_VECT(IRL_LLHH, 0x260),
+	INTC_VECT(IRL_LHLL, 0x280), INTC_VECT(IRL_LHLH, 0x2a0),
+	INTC_VECT(IRL_LHHL, 0x2c0), INTC_VECT(IRL_LHHH, 0x2e0),
+	INTC_VECT(IRL_HLLL, 0x300), INTC_VECT(IRL_HLLH, 0x320),
+	INTC_VECT(IRL_HLHL, 0x340), INTC_VECT(IRL_HLHH, 0x360),
+	INTC_VECT(IRL_HHLL, 0x380), INTC_VECT(IRL_HHLH, 0x3a0),
+	INTC_VECT(IRL_HHHL, 0x3c0),
+};
+
+static struct intc_mask_reg irl3210_mask_registers[] __initdata = {
+	{ 0xffd40080, 0xffd40084, 32, /* INTMSK2 / INTMSKCLR2 */
+	  { IRL_LLLL, IRL_LLLH, IRL_LLHL, IRL_LLHH,
+	    IRL_LHLL, IRL_LHLH, IRL_LHHL, IRL_LHHH,
+	    IRL_HLLL, IRL_HLLH, IRL_HLHL, IRL_HLHH,
+	    IRL_HHLL, IRL_HHLH, IRL_HHHL, } },
+};
+
+static struct intc_mask_reg irl7654_mask_registers[] __initdata = {
+	{ 0xffd40080, 0xffd40084, 32, /* INTMSK2 / INTMSKCLR2 */
+	  { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	    IRL_LLLL, IRL_LLLH, IRL_LLHL, IRL_LLHH,
+	    IRL_LHLL, IRL_LHLH, IRL_LHHL, IRL_LHHH,
+	    IRL_HLLL, IRL_HLLH, IRL_HLHL, IRL_HLHH,
+	    IRL_HHLL, IRL_HHLH, IRL_HHHL, } },
+};
+
+static DECLARE_INTC_DESC(intc_irl7654_desc, "sh7780-irl7654", irl_vectors,
+			 NULL, irl7654_mask_registers, NULL, NULL);
+
+static DECLARE_INTC_DESC(intc_irl3210_desc, "sh7780-irl3210", irl_vectors,
+			 NULL, irl3210_mask_registers, NULL, NULL);
+
+#define INTC_ICR0	0xffd00000
+#define INTC_INTMSK0	0xffd00044
+#define INTC_INTMSK1	0xffd00048
+#define INTC_INTMSK2	0xffd40080
+#define INTC_INTMSKCLR1	0xffd00068
+#define INTC_INTMSKCLR2	0xffd40084
+
 void __init plat_irq_setup(void)
 {
+	/* disable IRQ7-0 */
+	ctrl_outl(0xff000000, INTC_INTMSK0);
+
+	/* disable IRL3-0 + IRL7-4 */
+	ctrl_outl(0xc0000000, INTC_INTMSK1);
+	ctrl_outl(0xfffefffe, INTC_INTMSK2);
+
+	/* select IRL mode for IRL3-0 + IRL7-4 */
+	ctrl_outl(ctrl_inl(INTC_ICR0) & ~0x00c00000, INTC_ICR0);
+
+	/* disable holding function, ie enable "SH-4 Mode" */
+	ctrl_outl(ctrl_inl(INTC_ICR0) | 0x00200000, INTC_ICR0);
+
+	register_intc_controller(&intc_desc);
+}
+
+void __init plat_irq_setup_pins(int mode)
+{
+	switch (mode) {
+	case IRQ_MODE_IRQ:
+		/* select IRQ mode for IRL3-0 + IRL7-4 */
+		ctrl_outl(ctrl_inl(INTC_ICR0) | 0x00c00000, INTC_ICR0);
+		register_intc_controller(&intc_irq_desc);
+		break;
+	case IRQ_MODE_IRL7654:
+		/* enable IRL7-4 but don't provide any masking */
+		ctrl_outl(0x40000000, INTC_INTMSKCLR1);
+		ctrl_outl(0x0000fffe, INTC_INTMSKCLR2);
+		break;
+	case IRQ_MODE_IRL3210:
+		/* enable IRL0-3 but don't provide any masking */
+		ctrl_outl(0x80000000, INTC_INTMSKCLR1);
+		ctrl_outl(0xfffe0000, INTC_INTMSKCLR2);
+		break;
+	case IRQ_MODE_IRL7654_MASK:
+		/* enable IRL7-4 and mask using cpu intc controller */
+		ctrl_outl(0x40000000, INTC_INTMSKCLR1);
+		register_intc_controller(&intc_irl7654_desc);
+		break;
+	case IRQ_MODE_IRL3210_MASK:
+		/* enable IRL0-3 and mask using cpu intc controller */
+		ctrl_outl(0x80000000, INTC_INTMSKCLR1);
+		register_intc_controller(&intc_irl3210_desc);
+		break;
+	default:
+		BUG();
+	}
 }
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c
index 6f7227cd65bf..715e05b431e5 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c
@@ -12,6 +12,189 @@
 #include <linux/serial.h>
 #include <linux/io.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_timer.h>
+
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 28,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 29,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 30,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+static struct sh_timer_config tmu3_platform_data = {
+	.name = "TMU3",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu3_resources[] = {
+	[0] = {
+		.name	= "TMU3",
+		.start	= 0xffdc0008,
+		.end	= 0xffdc0013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 96,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu3_device = {
+	.name		= "sh_tmu",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &tmu3_platform_data,
+	},
+	.resource	= tmu3_resources,
+	.num_resources	= ARRAY_SIZE(tmu3_resources),
+};
+
+static struct sh_timer_config tmu4_platform_data = {
+	.name = "TMU4",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu4_resources[] = {
+	[0] = {
+		.name	= "TMU4",
+		.start	= 0xffdc0014,
+		.end	= 0xffdc001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 97,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu4_device = {
+	.name		= "sh_tmu",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &tmu4_platform_data,
+	},
+	.resource	= tmu4_resources,
+	.num_resources	= ARRAY_SIZE(tmu4_resources),
+};
+
+static struct sh_timer_config tmu5_platform_data = {
+	.name = "TMU5",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu5_resources[] = {
+	[0] = {
+		.name	= "TMU5",
+		.start	= 0xffdc0020,
+		.end	= 0xffdc002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 98,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu5_device = {
+	.name		= "sh_tmu",
+	.id		= 5,
+	.dev = {
+		.platform_data	= &tmu5_platform_data,
+	},
+	.resource	= tmu5_resources,
+	.num_resources	= ARRAY_SIZE(tmu5_resources),
+};
 
 static struct resource rtc_resources[] = {
 	[0] = {
@@ -58,6 +241,12 @@ static struct platform_device sci_device = {
 };
 
 static struct platform_device *sh7780_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
 	&rtc_device,
 	&sci_device,
 };
@@ -69,6 +258,21 @@ static int __init sh7780_devices_setup(void)
 }
 __initcall(sh7780_devices_setup);
 
+static struct platform_device *sh7780_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7780_early_devices,
+				   ARRAY_SIZE(sh7780_early_devices));
+}
+
 enum {
 	UNUSED = 0,
 
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c
index d80802a49dbd..af561402570b 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c
@@ -13,39 +13,228 @@
 #include <linux/serial_sci.h>
 #include <linux/io.h>
 #include <linux/mm.h>
+#include <linux/sh_timer.h>
 #include <asm/mmzone.h>
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "tmu012_fck",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 28,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "tmu012_fck",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 29,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "tmu012_fck",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 30,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+static struct sh_timer_config tmu3_platform_data = {
+	.name = "TMU3",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "tmu345_fck",
+};
+
+static struct resource tmu3_resources[] = {
+	[0] = {
+		.name	= "TMU3",
+		.start	= 0xffdc0008,
+		.end	= 0xffdc0013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 96,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu3_device = {
+	.name		= "sh_tmu",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &tmu3_platform_data,
+	},
+	.resource	= tmu3_resources,
+	.num_resources	= ARRAY_SIZE(tmu3_resources),
+};
+
+static struct sh_timer_config tmu4_platform_data = {
+	.name = "TMU4",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "tmu345_fck",
+};
+
+static struct resource tmu4_resources[] = {
+	[0] = {
+		.name	= "TMU4",
+		.start	= 0xffdc0014,
+		.end	= 0xffdc001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 97,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu4_device = {
+	.name		= "sh_tmu",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &tmu4_platform_data,
+	},
+	.resource	= tmu4_resources,
+	.num_resources	= ARRAY_SIZE(tmu4_resources),
+};
+
+static struct sh_timer_config tmu5_platform_data = {
+	.name = "TMU5",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "tmu345_fck",
+};
+
+static struct resource tmu5_resources[] = {
+	[0] = {
+		.name	= "TMU5",
+		.start	= 0xffdc0020,
+		.end	= 0xffdc002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 98,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu5_device = {
+	.name		= "sh_tmu",
+	.id		= 5,
+	.dev = {
+		.platform_data	= &tmu5_platform_data,
+	},
+	.resource	= tmu5_resources,
+	.num_resources	= ARRAY_SIZE(tmu5_resources),
+};
+
 static struct plat_sci_port sci_platform_data[] = {
 	{
 		.mapbase	= 0xffea0000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 40, 40, 40, 40 },
+		.clk		= "scif_fck",
 	}, {
 		.mapbase	= 0xffeb0000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 44, 44, 44, 44 },
+		.clk		= "scif_fck",
 	}, {
 		.mapbase	= 0xffec0000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 60, 60, 60, 60 },
+		.clk		= "scif_fck",
 	}, {
 		.mapbase	= 0xffed0000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 61, 61, 61, 61 },
+		.clk		= "scif_fck",
 	}, {
 		.mapbase	= 0xffee0000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 62, 62, 62, 62 },
+		.clk		= "scif_fck",
 	}, {
 		.mapbase	= 0xffef0000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
 		.irqs		= { 63, 63, 63, 63 },
+		.clk		= "scif_fck",
 	}, {
 		.flags = 0,
 	}
@@ -60,6 +249,12 @@ static struct platform_device sci_device = {
 };
 
 static struct platform_device *sh7785_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
 	&sci_device,
 };
 
@@ -70,6 +265,21 @@ static int __init sh7785_devices_setup(void)
 }
 __initcall(sh7785_devices_setup);
 
+static struct platform_device *sh7785_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+};
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7785_early_devices,
+				   ARRAY_SIZE(sh7785_early_devices));
+}
+
 enum {
 	UNUSED = 0,
 
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c
index 90e8cfff55fd..93e0d2c017e8 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c
@@ -3,6 +3,7 @@
  *
  * Copyright (C) 2009  Renesas Solutions Corp.
  * Kuninori Morimoto <morimoto.kuninori@renesas.com>
+ * Paul Mundt <paul.mundt@renesas.com>
  *
  * Based on SH7785 Setup
  *
@@ -19,6 +20,7 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
+#include <linux/sh_timer.h>
 #include <asm/mmzone.h>
 
 static struct plat_sci_port sci_platform_data[] = {
@@ -69,6 +71,368 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffd80008,
+		.end	= 0xffd80013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffd80014,
+		.end	= 0xffd8001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffd80020,
+		.end	= 0xffd8002f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+static struct sh_timer_config tmu3_platform_data = {
+	.name = "TMU3",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu3_resources[] = {
+	[0] = {
+		.name	= "TMU3",
+		.start	= 0xffda0008,
+		.end	= 0xffda0013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 20,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu3_device = {
+	.name		= "sh_tmu",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &tmu3_platform_data,
+	},
+	.resource	= tmu3_resources,
+	.num_resources	= ARRAY_SIZE(tmu3_resources),
+};
+
+static struct sh_timer_config tmu4_platform_data = {
+	.name = "TMU4",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu4_resources[] = {
+	[0] = {
+		.name	= "TMU4",
+		.start	= 0xffda0014,
+		.end	= 0xffda001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 21,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu4_device = {
+	.name		= "sh_tmu",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &tmu4_platform_data,
+	},
+	.resource	= tmu4_resources,
+	.num_resources	= ARRAY_SIZE(tmu4_resources),
+};
+
+static struct sh_timer_config tmu5_platform_data = {
+	.name = "TMU5",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu5_resources[] = {
+	[0] = {
+		.name	= "TMU5",
+		.start	= 0xffda0020,
+		.end	= 0xffda002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 22,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu5_device = {
+	.name		= "sh_tmu",
+	.id		= 5,
+	.dev = {
+		.platform_data	= &tmu5_platform_data,
+	},
+	.resource	= tmu5_resources,
+	.num_resources	= ARRAY_SIZE(tmu5_resources),
+};
+
+static struct sh_timer_config tmu6_platform_data = {
+	.name = "TMU6",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu6_resources[] = {
+	[0] = {
+		.name	= "TMU6",
+		.start	= 0xffdc0008,
+		.end	= 0xffdc0013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 45,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu6_device = {
+	.name		= "sh_tmu",
+	.id		= 6,
+	.dev = {
+		.platform_data	= &tmu6_platform_data,
+	},
+	.resource	= tmu6_resources,
+	.num_resources	= ARRAY_SIZE(tmu6_resources),
+};
+
+static struct sh_timer_config tmu7_platform_data = {
+	.name = "TMU7",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu7_resources[] = {
+	[0] = {
+		.name	= "TMU7",
+		.start	= 0xffdc0014,
+		.end	= 0xffdc001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 45,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu7_device = {
+	.name		= "sh_tmu",
+	.id		= 7,
+	.dev = {
+		.platform_data	= &tmu7_platform_data,
+	},
+	.resource	= tmu7_resources,
+	.num_resources	= ARRAY_SIZE(tmu7_resources),
+};
+
+static struct sh_timer_config tmu8_platform_data = {
+	.name = "TMU8",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu8_resources[] = {
+	[0] = {
+		.name	= "TMU8",
+		.start	= 0xffdc0020,
+		.end	= 0xffdc002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 45,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu8_device = {
+	.name		= "sh_tmu",
+	.id		= 8,
+	.dev = {
+		.platform_data	= &tmu8_platform_data,
+	},
+	.resource	= tmu8_resources,
+	.num_resources	= ARRAY_SIZE(tmu8_resources),
+};
+
+static struct sh_timer_config tmu9_platform_data = {
+	.name = "TMU9",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu9_resources[] = {
+	[0] = {
+		.name	= "TMU9",
+		.start	= 0xffde0008,
+		.end	= 0xffde0013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 46,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu9_device = {
+	.name		= "sh_tmu",
+	.id		= 9,
+	.dev = {
+		.platform_data	= &tmu9_platform_data,
+	},
+	.resource	= tmu9_resources,
+	.num_resources	= ARRAY_SIZE(tmu9_resources),
+};
+
+static struct sh_timer_config tmu10_platform_data = {
+	.name = "TMU10",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu10_resources[] = {
+	[0] = {
+		.name	= "TMU10",
+		.start	= 0xffde0014,
+		.end	= 0xffde001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 46,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu10_device = {
+	.name		= "sh_tmu",
+	.id		= 10,
+	.dev = {
+		.platform_data	= &tmu10_platform_data,
+	},
+	.resource	= tmu10_resources,
+	.num_resources	= ARRAY_SIZE(tmu10_resources),
+};
+
+static struct sh_timer_config tmu11_platform_data = {
+	.name = "TMU11",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu11_resources[] = {
+	[0] = {
+		.name	= "TMU11",
+		.start	= 0xffde0020,
+		.end	= 0xffde002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 46,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu11_device = {
+	.name		= "sh_tmu",
+	.id		= 11,
+	.dev = {
+		.platform_data	= &tmu11_platform_data,
+	},
+	.resource	= tmu11_resources,
+	.num_resources	= ARRAY_SIZE(tmu11_resources),
+};
+
 static struct resource usb_ohci_resources[] = {
 	[0] = {
 		.start	= 0xffe70400,
@@ -94,6 +458,21 @@ static struct platform_device usb_ohci_device = {
 	.resource	= usb_ohci_resources,
 };
 
+static struct platform_device *sh7786_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+	&tmu6_device,
+	&tmu7_device,
+	&tmu8_device,
+	&tmu9_device,
+	&tmu10_device,
+	&tmu11_device,
+};
+
 static struct platform_device *sh7786_devices[] __initdata = {
 	&sci_device,
 	&usb_ohci_device,
@@ -156,12 +535,26 @@ static void __init sh7786_usb_setup(void)
 
 static int __init sh7786_devices_setup(void)
 {
+	int ret;
+
 	sh7786_usb_setup();
+
+	ret = platform_add_devices(sh7786_early_devices,
+				   ARRAY_SIZE(sh7786_early_devices));
+	if (unlikely(ret != 0))
+		return ret;
+
 	return platform_add_devices(sh7786_devices,
 				    ARRAY_SIZE(sh7786_devices));
 }
 device_initcall(sh7786_devices_setup);
 
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh7786_early_devices,
+				   ARRAY_SIZE(sh7786_early_devices));
+}
+
 enum {
 	UNUSED = 0,
 
diff --git a/arch/sh/kernel/cpu/sh4a/setup-shx3.c b/arch/sh/kernel/cpu/sh4a/setup-shx3.c
index bd35f32534b9..53c65fd9ccef 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-shx3.c
@@ -1,7 +1,7 @@
 /*
- * SH-X3 Setup
+ * SH-X3 Prototype Setup
  *
- *  Copyright (C) 2007  Paul Mundt
+ *  Copyright (C) 2007 - 2009  Paul Mundt
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
@@ -12,6 +12,7 @@
 #include <linux/serial.h>
 #include <linux/serial_sci.h>
 #include <linux/io.h>
+#include <linux/sh_timer.h>
 #include <asm/mmzone.h>
 
 static struct plat_sci_port sci_platform_data[] = {
@@ -48,17 +49,221 @@ static struct platform_device sci_device = {
 	},
 };
 
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= 0xffc10008,
+		.end	= 0xffc10013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 16,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= 0xffc10014,
+		.end	= 0xffc1001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 17,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= 0xffc10020,
+		.end	= 0xffc1002f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 18,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+static struct sh_timer_config tmu3_platform_data = {
+	.name = "TMU3",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu3_resources[] = {
+	[0] = {
+		.name	= "TMU3",
+		.start	= 0xffc20008,
+		.end	= 0xffc20013,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 19,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu3_device = {
+	.name		= "sh_tmu",
+	.id		= 3,
+	.dev = {
+		.platform_data	= &tmu3_platform_data,
+	},
+	.resource	= tmu3_resources,
+	.num_resources	= ARRAY_SIZE(tmu3_resources),
+};
+
+static struct sh_timer_config tmu4_platform_data = {
+	.name = "TMU4",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu4_resources[] = {
+	[0] = {
+		.name	= "TMU4",
+		.start	= 0xffc20014,
+		.end	= 0xffc2001f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 20,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu4_device = {
+	.name		= "sh_tmu",
+	.id		= 4,
+	.dev = {
+		.platform_data	= &tmu4_platform_data,
+	},
+	.resource	= tmu4_resources,
+	.num_resources	= ARRAY_SIZE(tmu4_resources),
+};
+
+static struct sh_timer_config tmu5_platform_data = {
+	.name = "TMU5",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu5_resources[] = {
+	[0] = {
+		.name	= "TMU5",
+		.start	= 0xffc20020,
+		.end	= 0xffc2002b,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= 21,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu5_device = {
+	.name		= "sh_tmu",
+	.id		= 5,
+	.dev = {
+		.platform_data	= &tmu5_platform_data,
+	},
+	.resource	= tmu5_resources,
+	.num_resources	= ARRAY_SIZE(tmu5_resources),
+};
+
+static struct platform_device *shx3_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+	&tmu3_device,
+	&tmu4_device,
+	&tmu5_device,
+};
+
 static struct platform_device *shx3_devices[] __initdata = {
 	&sci_device,
 };
 
 static int __init shx3_devices_setup(void)
 {
+	int ret;
+
+	ret = platform_add_devices(shx3_early_devices,
+				   ARRAY_SIZE(shx3_early_devices));
+	if (unlikely(ret != 0))
+		return ret;
+
 	return platform_add_devices(shx3_devices,
 				    ARRAY_SIZE(shx3_devices));
 }
 __initcall(shx3_devices_setup);
 
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(shx3_early_devices,
+				   ARRAY_SIZE(shx3_early_devices));
+}
+
 enum {
 	UNUSED = 0,
 
diff --git a/arch/sh/kernel/cpu/sh5/Makefile b/arch/sh/kernel/cpu/sh5/Makefile
index ce4602ea23a8..a184a31e686e 100644
--- a/arch/sh/kernel/cpu/sh5/Makefile
+++ b/arch/sh/kernel/cpu/sh5/Makefile
@@ -6,6 +6,9 @@ obj-y := entry.o probe.o switchto.o
 obj-$(CONFIG_SH_FPU)		+= fpu.o
 obj-$(CONFIG_KALLSYMS)		+= unwind.o
 
+# CPU subtype setup
+obj-$(CONFIG_CPU_SH5)		+= setup-sh5.o
+
 # Primary on-chip clocks (common)
 clock-$(CONFIG_CPU_SH5)		:= clock-sh5.o
 
diff --git a/arch/sh/kernel/cpu/sh5/clock-sh5.c b/arch/sh/kernel/cpu/sh5/clock-sh5.c
index 52c49248833a..7f864ebc51d3 100644
--- a/arch/sh/kernel/cpu/sh5/clock-sh5.c
+++ b/arch/sh/kernel/cpu/sh5/clock-sh5.c
@@ -32,30 +32,30 @@ static struct clk_ops sh5_master_clk_ops = {
 	.init		= master_clk_init,
 };
 
-static void module_clk_recalc(struct clk *clk)
+static unsigned long module_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(cprc_base) >> 12) & 0x0007;
-	clk->rate = clk->parent->rate / ifc_table[idx];
+	return clk->parent->rate / ifc_table[idx];
 }
 
 static struct clk_ops sh5_module_clk_ops = {
 	.recalc		= module_clk_recalc,
 };
 
-static void bus_clk_recalc(struct clk *clk)
+static unsigned long bus_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(cprc_base) >> 3) & 0x0007;
-	clk->rate = clk->parent->rate / ifc_table[idx];
+	return clk->parent->rate / ifc_table[idx];
 }
 
 static struct clk_ops sh5_bus_clk_ops = {
 	.recalc		= bus_clk_recalc,
 };
 
-static void cpu_clk_recalc(struct clk *clk)
+static unsigned long cpu_clk_recalc(struct clk *clk)
 {
 	int idx = (ctrl_inw(cprc_base) & 0x0007);
-	clk->rate = clk->parent->rate / ifc_table[idx];
+	return clk->parent->rate / ifc_table[idx];
 }
 
 static struct clk_ops sh5_cpu_clk_ops = {
@@ -71,7 +71,7 @@ static struct clk_ops *sh5_clk_ops[] = {
 
 void __init arch_init_clk_ops(struct clk_ops **ops, int idx)
 {
-	cprc_base = onchip_remap(CPRC_BASE, 1024, "CPRC");
+	cprc_base = (unsigned long)ioremap_nocache(CPRC_BASE, 1024);
 	BUG_ON(!cprc_base);
 
 	if (idx < ARRAY_SIZE(sh5_clk_ops))
diff --git a/arch/sh/kernel/cpu/sh5/entry.S b/arch/sh/kernel/cpu/sh5/entry.S
index 7e49cb812f8b..b0aacf675258 100644
--- a/arch/sh/kernel/cpu/sh5/entry.S
+++ b/arch/sh/kernel/cpu/sh5/entry.S
@@ -812,27 +812,6 @@ no_underflow:
 	! exceptions
 	add	SP, ZERO, r14
 
-#ifdef CONFIG_POOR_MANS_STRACE
-	/* We've pushed all the registers now, so only r2-r4 hold anything
-	 * useful. Move them into callee save registers */
-	or	r2, ZERO, r28
-	or	r3, ZERO, r29
-	or	r4, ZERO, r30
-
-	/* Preserve r2 as the event code */
-	movi	evt_debug, r3
-	ori	r3, 1, r3
-	ptabs	r3, tr0
-
-	or	SP, ZERO, r6
-	getcon	TRA, r5
-	blink	tr0, LINK
-
-	or	r28, ZERO, r2
-	or	r29, ZERO, r3
-	or	r30, ZERO, r4
-#endif
-
 	/* For syscall and debug race condition, get TRA now */
 	getcon	TRA, r5
 
@@ -887,11 +866,6 @@ no_underflow:
  */
 	.global ret_from_irq
 ret_from_irq:
-#ifdef CONFIG_POOR_MANS_STRACE
-	pta	evt_debug_ret_from_irq, tr0
-	ori	SP, 0, r2
-	blink	tr0, LINK
-#endif
 	ld.q	SP, FRAME_S(FSSR), r6
 	shlri	r6, 30, r6
 	andi	r6, 1, r6
@@ -905,12 +879,6 @@ ret_from_irq:
 ret_from_exception:
 	preempt_stop()
 
-#ifdef CONFIG_POOR_MANS_STRACE
-	pta	evt_debug_ret_from_exc, tr0
-	ori	SP, 0, r2
-	blink	tr0, LINK
-#endif
-
 	ld.q	SP, FRAME_S(FSSR), r6
 	shlri	r6, 30, r6
 	andi	r6, 1, r6
@@ -1236,18 +1204,6 @@ syscall_bad:
 	.global syscall_ret
 syscall_ret:
 	st.q	SP, FRAME_R(9), r2	/* Expecting SP back to BASIC frame */
-
-#ifdef CONFIG_POOR_MANS_STRACE
-	/* nothing useful in registers at this point */
-
-	movi	evt_debug2, r5
-	ori	r5, 1, r5
-	ptabs	r5, tr0
-	ld.q	SP, FRAME_R(9), r2
-	or	SP, ZERO, r3
-	blink	tr0, LINK
-#endif
-
 	ld.q	SP, FRAME_S(FSPC), r2
 	addi	r2, 4, r2		/* Move PC, being pre-execution event */
 	st.q	SP, FRAME_S(FSPC), r2
@@ -1268,25 +1224,12 @@ ret_from_fork:
 	ptabs	r5, tr0
 	blink	tr0, LINK
 
-#ifdef CONFIG_POOR_MANS_STRACE
-	/* nothing useful in registers at this point */
-
-	movi	evt_debug2, r5
-	ori	r5, 1, r5
-	ptabs	r5, tr0
-	ld.q	SP, FRAME_R(9), r2
-	or	SP, ZERO, r3
-	blink	tr0, LINK
-#endif
-
 	ld.q	SP, FRAME_S(FSPC), r2
 	addi	r2, 4, r2		/* Move PC, being pre-execution event */
 	st.q	SP, FRAME_S(FSPC), r2
 	pta	ret_from_syscall, tr0
 	blink	tr0, ZERO
 
-
-
 syscall_allowed:
 	/* Use LINK to deflect the exit point, default is syscall_ret */
 	pta	syscall_ret, tr0
@@ -1410,8 +1353,8 @@ peek_real_address_q:
 	   r2(out) : result quadword
 
 	   This is provided as a cheapskate way of manipulating device
-	   registers for debugging (to avoid the need to onchip_remap the debug
-	   module, and to avoid the need to onchip_remap the watchpoint
+	   registers for debugging (to avoid the need to ioremap the debug
+	   module, and to avoid the need to ioremap the watchpoint
 	   controller in a way that identity maps sufficient bits to avoid the
 	   SH5-101 cut2 silicon defect).
 
@@ -1459,8 +1402,8 @@ poke_real_address_q:
 	   r3 : quadword value to write.
 
 	   This is provided as a cheapskate way of manipulating device
-	   registers for debugging (to avoid the need to onchip_remap the debug
-	   module, and to avoid the need to onchip_remap the watchpoint
+	   registers for debugging (to avoid the need to ioremap the debug
+	   module, and to avoid the need to ioremap the watchpoint
 	   controller in a way that identity maps sufficient bits to avoid the
 	   SH5-101 cut2 silicon defect).
 
diff --git a/arch/sh/kernel/cpu/sh5/setup-sh5.c b/arch/sh/kernel/cpu/sh5/setup-sh5.c
new file mode 100644
index 000000000000..f5ff1ac57fc2
--- /dev/null
+++ b/arch/sh/kernel/cpu/sh5/setup-sh5.c
@@ -0,0 +1,195 @@
+/*
+ * SH5-101/SH5-103 CPU Setup
+ *
+ *  Copyright (C) 2009  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/platform_device.h>
+#include <linux/init.h>
+#include <linux/serial.h>
+#include <linux/serial_sci.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/sh_timer.h>
+#include <asm/addrspace.h>
+
+static struct plat_sci_port sci_platform_data[] = {
+	{
+		.mapbase	= PHYS_PERIPHERAL_BLOCK + 0x01030000,
+		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP,
+		.type		= PORT_SCIF,
+		.irqs		= { 39, 40, 42, 0 },
+	}, {
+		.flags = 0,
+	}
+};
+
+static struct platform_device sci_device = {
+	.name		= "sh-sci",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= sci_platform_data,
+	},
+};
+
+static struct resource rtc_resources[] = {
+	[0] = {
+		.start	= PHYS_PERIPHERAL_BLOCK + 0x01040000,
+		.end	= PHYS_PERIPHERAL_BLOCK + 0x01040000 + 0x58 - 1,
+		.flags	= IORESOURCE_IO,
+	},
+	[1] = {
+		/* Period IRQ */
+		.start	= IRQ_PRI,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[2] = {
+		/* Carry IRQ */
+		.start	= IRQ_CUI,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[3] = {
+		/* Alarm IRQ */
+		.start	= IRQ_ATI,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device rtc_device = {
+	.name		= "sh-rtc",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(rtc_resources),
+	.resource	= rtc_resources,
+};
+
+#define	TMU_BLOCK_OFF	0x01020000
+#define TMU_BASE	PHYS_PERIPHERAL_BLOCK + TMU_BLOCK_OFF
+#define TMU0_BASE	(TMU_BASE + 0x8 + (0xc * 0x0))
+#define TMU1_BASE	(TMU_BASE + 0x8 + (0xc * 0x1))
+#define TMU2_BASE	(TMU_BASE + 0x8 + (0xc * 0x2))
+
+static struct sh_timer_config tmu0_platform_data = {
+	.name = "TMU0",
+	.channel_offset = 0x04,
+	.timer_bit = 0,
+	.clk = "peripheral_clk",
+	.clockevent_rating = 200,
+};
+
+static struct resource tmu0_resources[] = {
+	[0] = {
+		.name	= "TMU0",
+		.start	= TMU0_BASE,
+		.end	= TMU0_BASE + 0xc - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= IRQ_TUNI0,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu0_device = {
+	.name		= "sh_tmu",
+	.id		= 0,
+	.dev = {
+		.platform_data	= &tmu0_platform_data,
+	},
+	.resource	= tmu0_resources,
+	.num_resources	= ARRAY_SIZE(tmu0_resources),
+};
+
+static struct sh_timer_config tmu1_platform_data = {
+	.name = "TMU1",
+	.channel_offset = 0x10,
+	.timer_bit = 1,
+	.clk = "peripheral_clk",
+	.clocksource_rating = 200,
+};
+
+static struct resource tmu1_resources[] = {
+	[0] = {
+		.name	= "TMU1",
+		.start	= TMU1_BASE,
+		.end	= TMU1_BASE + 0xc - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= IRQ_TUNI1,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu1_device = {
+	.name		= "sh_tmu",
+	.id		= 1,
+	.dev = {
+		.platform_data	= &tmu1_platform_data,
+	},
+	.resource	= tmu1_resources,
+	.num_resources	= ARRAY_SIZE(tmu1_resources),
+};
+
+static struct sh_timer_config tmu2_platform_data = {
+	.name = "TMU2",
+	.channel_offset = 0x1c,
+	.timer_bit = 2,
+	.clk = "peripheral_clk",
+};
+
+static struct resource tmu2_resources[] = {
+	[0] = {
+		.name	= "TMU2",
+		.start	= TMU2_BASE,
+		.end	= TMU2_BASE + 0xc - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= IRQ_TUNI2,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tmu2_device = {
+	.name		= "sh_tmu",
+	.id		= 2,
+	.dev = {
+		.platform_data	= &tmu2_platform_data,
+	},
+	.resource	= tmu2_resources,
+	.num_resources	= ARRAY_SIZE(tmu2_resources),
+};
+
+static struct platform_device *sh5_early_devices[] __initdata = {
+	&tmu0_device,
+	&tmu1_device,
+	&tmu2_device,
+};
+
+static struct platform_device *sh5_devices[] __initdata = {
+	&sci_device,
+	&rtc_device,
+};
+
+static int __init sh5_devices_setup(void)
+{
+	int ret;
+
+	ret = platform_add_devices(sh5_early_devices,
+				   ARRAY_SIZE(sh5_early_devices));
+	if (unlikely(ret != 0))
+		return ret;
+
+	return platform_add_devices(sh5_devices,
+				    ARRAY_SIZE(sh5_devices));
+}
+__initcall(sh5_devices_setup);
+
+void __init plat_early_device_setup(void)
+{
+	early_platform_add_devices(sh5_early_devices,
+				   ARRAY_SIZE(sh5_early_devices));
+}
diff --git a/arch/sh/kernel/io.c b/arch/sh/kernel/io.c
index 29cf4588fc05..4f85fffaa557 100644
--- a/arch/sh/kernel/io.c
+++ b/arch/sh/kernel/io.c
@@ -12,6 +12,7 @@
  * for more details.
  */
 #include <linux/module.h>
+#include <linux/pci.h>
 #include <asm/machvec.h>
 #include <asm/io.h>
 
diff --git a/arch/sh/kernel/io_trapped.c b/arch/sh/kernel/io_trapped.c
index c22853b059ef..77dfecb64373 100644
--- a/arch/sh/kernel/io_trapped.c
+++ b/arch/sh/kernel/io_trapped.c
@@ -267,7 +267,7 @@ static struct mem_access trapped_io_access = {
 int handle_trapped_io(struct pt_regs *regs, unsigned long address)
 {
 	mm_segment_t oldfs;
-	opcode_t instruction;
+	insn_size_t instruction;
 	int tmp;
 
 	if (!lookup_tiop(address))
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 3f1372eb0091..3d09062f4682 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -31,39 +31,64 @@ void ack_bad_irq(unsigned int irq)
 }
 
 #if defined(CONFIG_PROC_FS)
+/*
+ * /proc/interrupts printing:
+ */
+static int show_other_interrupts(struct seq_file *p, int prec)
+{
+	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
+	return 0;
+}
+
 int show_interrupts(struct seq_file *p, void *v)
 {
-	int i = *(loff_t *) v, j;
-	struct irqaction * action;
-	unsigned long flags;
+	unsigned long flags, any_count = 0;
+	int i = *(loff_t *)v, j, prec;
+	struct irqaction *action;
+	struct irq_desc *desc;
+
+	if (i > nr_irqs)
+		return 0;
+
+	for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
+		j *= 10;
+
+	if (i == nr_irqs)
+		return show_other_interrupts(p, prec);
 
 	if (i == 0) {
-		seq_puts(p, "           ");
+		seq_printf(p, "%*s", prec + 8, "");
 		for_each_online_cpu(j)
-			seq_printf(p, "CPU%d       ",j);
+			seq_printf(p, "CPU%-8d", j);
 		seq_putc(p, '\n');
 	}
 
-	if (i < sh_mv.mv_nr_irqs) {
-		spin_lock_irqsave(&irq_desc[i].lock, flags);
-		action = irq_desc[i].action;
-		if (!action)
-			goto unlock;
-		seq_printf(p, "%3d: ",i);
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-		seq_printf(p, " %14s", irq_desc[i].chip->name);
-		seq_printf(p, "-%-8s", irq_desc[i].name);
+	desc = irq_to_desc(i);
+	if (!desc)
+		return 0;
+
+	spin_lock_irqsave(&desc->lock, flags);
+	for_each_online_cpu(j)
+		any_count |= kstat_irqs_cpu(i, j);
+	action = desc->action;
+	if (!action && !any_count)
+		goto out;
+
+	seq_printf(p, "%*d: ", prec, i);
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+	seq_printf(p, " %14s", desc->chip->name);
+	seq_printf(p, "-%-8s", desc->name);
+
+	if (action) {
 		seq_printf(p, "  %s", action->name);
-
-		for (action=action->next; action; action = action->next)
+		while ((action = action->next) != NULL)
 			seq_printf(p, ", %s", action->name);
-		seq_putc(p, '\n');
-unlock:
-		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
-	} else if (i == sh_mv.mv_nr_irqs)
-		seq_printf(p, "Err: %10u\n", atomic_read(&irq_err_count));
+	}
 
+	seq_putc(p, '\n');
+out:
+	spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
 }
 #endif
@@ -254,3 +279,11 @@ void __init init_IRQ(void)
 
 	irq_ctx_init(smp_processor_id());
 }
+
+#ifdef CONFIG_SPARSE_IRQ
+int __init arch_probe_nr_irqs(void)
+{
+	nr_irqs = sh_mv.mv_nr_irqs;
+	return 0;
+}
+#endif
diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c
index 7c747e7d71b8..305aad742aec 100644
--- a/arch/sh/kernel/kgdb.c
+++ b/arch/sh/kernel/kgdb.c
@@ -47,7 +47,7 @@ char in_nmi = 0;	/* Set during NMI to prevent re-entry */
 /* Calculate the new address for after a step */
 static short *get_step_address(struct pt_regs *linux_regs)
 {
-	opcode_t op = __raw_readw(linux_regs->pc);
+	insn_size_t op = __raw_readw(linux_regs->pc);
 	long addr;
 
 	/* BT */
@@ -134,7 +134,7 @@ static short *get_step_address(struct pt_regs *linux_regs)
  */
 
 static unsigned long stepped_address;
-static opcode_t stepped_opcode;
+static insn_size_t stepped_opcode;
 
 static void do_single_step(struct pt_regs *linux_regs)
 {
diff --git a/arch/sh/kernel/timers/timer-broadcast.c b/arch/sh/kernel/localtimer.c
similarity index 100%
rename from arch/sh/kernel/timers/timer-broadcast.c
rename to arch/sh/kernel/localtimer.c
diff --git a/arch/sh/kernel/machvec.c b/arch/sh/kernel/machvec.c
index c1ea41e5812a..548f6607fd0f 100644
--- a/arch/sh/kernel/machvec.c
+++ b/arch/sh/kernel/machvec.c
@@ -129,6 +129,7 @@ void __init sh_mv_setup(void)
 	mv_set(ioport_map);
 	mv_set(ioport_unmap);
 	mv_set(irq_demux);
+	mv_set(mode_pins);
 
 	if (!sh_mv.mv_nr_irqs)
 		sh_mv.mv_nr_irqs = NR_IRQS;
diff --git a/arch/sh/kernel/module.c b/arch/sh/kernel/module.c
index c43081039dd5..c19b0f7d2cc1 100644
--- a/arch/sh/kernel/module.c
+++ b/arch/sh/kernel/module.c
@@ -90,7 +90,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 		 * SHmedia, the LSB of the symbol needs to be asserted
 		 * for the CPU to be in SHmedia mode when it starts executing
 		 * the branch target. */
-		relocation |= (sym->st_other & 4);
+		relocation |= !!(sym->st_other & 4);
 #endif
 
 		switch (ELF32_R_TYPE(rel[i].r_info)) {
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 6d94725d22f2..9289ede29c7b 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -251,7 +251,8 @@ static void ubc_set_tracing(int asid, unsigned long pc)
 
 	if (current_cpu_data.type == CPU_SH7729 ||
 	    current_cpu_data.type == CPU_SH7710 ||
-	    current_cpu_data.type == CPU_SH7712) {
+	    current_cpu_data.type == CPU_SH7712 ||
+	    current_cpu_data.type == CPU_SH7203){
 		ctrl_outw(BBR_INST | BBR_READ | BBR_CPU, UBC_BBRA);
 		ctrl_outl(BRCR_PCBA | BRCR_PCTE, UBC_BRCR);
 	} else {
@@ -407,6 +408,7 @@ asmlinkage void break_point_trap(void)
 #else
 	ctrl_outw(0, UBC_BBRA);
 	ctrl_outw(0, UBC_BBRB);
+	ctrl_outl(0, UBC_BRCR);
 #endif
 	current->thread.ubc_pc = 0;
 	ubc_usercnt -= 1;
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index f7b22dd83b0c..3392e835a374 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -334,6 +334,14 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 					[(addr - (long)&dummy->fpu) >> 2];
 		} else if (addr == (long) &dummy->u_fpvalid)
 			tmp = !!tsk_used_math(child);
+		else if (addr == PT_TEXT_ADDR)
+			tmp = child->mm->start_code;
+		else if (addr == PT_DATA_ADDR)
+			tmp = child->mm->start_data;
+		else if (addr == PT_TEXT_END_ADDR)
+			tmp = child->mm->end_code;
+		else if (addr == PT_TEXT_LEN)
+			tmp = child->mm->end_code - child->mm->start_code;
 		else
 			tmp = 0;
 		ret = put_user(tmp, datap);
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 04a6004fccc4..dd38338553ef 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -29,6 +29,7 @@
 #include <linux/mmzone.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/platform_device.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/page.h>
@@ -155,7 +156,7 @@ static void __init reserve_crashkernel(void)
 			&crash_size, &crash_base);
 	if (ret == 0 && crash_size) {
 		if (crash_base <= 0) {
-			vp = alloc_bootmem_nopanic(crash_size); 
+			vp = alloc_bootmem_nopanic(crash_size);
 			if (!vp) {
 				printk(KERN_INFO "crashkernel allocation "
 				       "failed\n");
@@ -184,7 +185,6 @@ static inline void __init reserve_crashkernel(void)
 {}
 #endif
 
-#ifndef CONFIG_GENERIC_CALIBRATE_DELAY
 void __cpuinit calibrate_delay(void)
 {
 	struct clk *clk = clk_get(NULL, "cpu_clk");
@@ -200,7 +200,6 @@ void __cpuinit calibrate_delay(void)
 			 (loops_per_jiffy/(5000/HZ)) % 100,
 			 loops_per_jiffy);
 }
-#endif
 
 void __init __add_active_range(unsigned int nid, unsigned long start_pfn,
 						unsigned long end_pfn)
@@ -328,6 +327,10 @@ static int __init parse_elfcorehdr(char *arg)
 early_param("elfcorehdr", parse_elfcorehdr);
 #endif
 
+void __init __attribute__ ((weak)) plat_early_device_setup(void)
+{
+}
+
 void __init setup_arch(char **cmdline_p)
 {
 	enable_mmu();
@@ -381,6 +384,8 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
+	plat_early_device_setup();
+
 	sh_mv_setup();
 
 	/*
@@ -415,6 +420,18 @@ void __init setup_arch(char **cmdline_p)
 #endif
 }
 
+/* processor boot mode configuration */
+int generic_mode_pins(void)
+{
+	pr_warning("generic_mode_pins(): missing mode pin configuration\n");
+	return 0;
+}
+
+int test_mode_pin(int pin)
+{
+	return sh_mv.mv_mode_pins() & pin;
+}
+
 static const char *cpu_name[] = {
 	[CPU_SH7201]	= "SH7201",
 	[CPU_SH7203]	= "SH7203",	[CPU_SH7263]	= "SH7263",
@@ -435,7 +452,8 @@ static const char *cpu_name[] = {
 	[CPU_SH7722]	= "SH7722",	[CPU_SHX3]	= "SH-X3",
 	[CPU_SH5_101]	= "SH5-101",	[CPU_SH5_103]	= "SH5-103",
 	[CPU_MXG]	= "MX-G",	[CPU_SH7723]	= "SH7723",
-	[CPU_SH7366]	= "SH7366",	[CPU_SH_NONE]	= "Unknown"
+	[CPU_SH7366]	= "SH7366",	[CPU_SH7724]	= "SH7724",
+	[CPU_SH_NONE]	= "Unknown"
 };
 
 const char *get_cpu_subtype(struct sh_cpuinfo *c)
diff --git a/arch/sh/kernel/sh_ksyms_32.c b/arch/sh/kernel/sh_ksyms_32.c
index 528de2955c81..fcc5de31f83b 100644
--- a/arch/sh/kernel/sh_ksyms_32.c
+++ b/arch/sh/kernel/sh_ksyms_32.c
@@ -19,14 +19,10 @@
 #include <asm/ftrace.h>
 
 extern int dump_fpu(struct pt_regs *, elf_fpregset_t *);
-extern struct hw_interrupt_type no_irq_type;
 
 /* platform dependent support */
 EXPORT_SYMBOL(dump_fpu);
 EXPORT_SYMBOL(kernel_thread);
-EXPORT_SYMBOL(irq_desc);
-EXPORT_SYMBOL(no_irq_type);
-
 EXPORT_SYMBOL(strlen);
 
 /* PCI exports */
@@ -41,11 +37,6 @@ EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(__copy_user);
-
-#ifdef CONFIG_MMU
-EXPORT_SYMBOL(get_vm_area);
-#endif
-
 EXPORT_SYMBOL(__udelay);
 EXPORT_SYMBOL(__ndelay);
 EXPORT_SYMBOL(__const_udelay);
diff --git a/arch/sh/kernel/sh_ksyms_64.c b/arch/sh/kernel/sh_ksyms_64.c
index 0d74d6b8774e..8f54ef0cfbca 100644
--- a/arch/sh/kernel/sh_ksyms_64.c
+++ b/arch/sh/kernel/sh_ksyms_64.c
@@ -76,5 +76,7 @@ EXPORT_SYMBOL(strcpy);
 #define DECLARE_EXPORT(name) extern void name(void);EXPORT_SYMBOL(name)
 
 DECLARE_EXPORT(__sdivsi3);
+DECLARE_EXPORT(__sdivsi3_1);
+DECLARE_EXPORT(__sdivsi3_2);
 DECLARE_EXPORT(__udivsi3);
 DECLARE_EXPORT(__div_table);
diff --git a/arch/sh/kernel/syscalls_32.S b/arch/sh/kernel/syscalls_32.S
index 05202edd8e21..a9fff9f731ec 100644
--- a/arch/sh/kernel/syscalls_32.S
+++ b/arch/sh/kernel/syscalls_32.S
@@ -350,4 +350,5 @@ ENTRY(sys_call_table)
 	.long sys_pipe2
 	.long sys_inotify_init1
 	.long sys_preadv
-	.long sys_writev
+	.long sys_pwritev
+	.long sys_rt_tgsigqueueinfo	/* 335 */
diff --git a/arch/sh/kernel/syscalls_64.S b/arch/sh/kernel/syscalls_64.S
index a083609f9284..75c1889af1ed 100644
--- a/arch/sh/kernel/syscalls_64.S
+++ b/arch/sh/kernel/syscalls_64.S
@@ -389,3 +389,4 @@ sys_call_table:
 	.long sys_inotify_init1		/* 360 */
 	.long sys_preadv
 	.long sys_pwritev
+	.long sys_rt_tgsigqueueinfo
diff --git a/arch/sh/kernel/time.c b/arch/sh/kernel/time.c
new file mode 100644
index 000000000000..2edde32c764b
--- /dev/null
+++ b/arch/sh/kernel/time.c
@@ -0,0 +1,125 @@
+/*
+ *  arch/sh/kernel/time.c
+ *
+ *  Copyright (C) 1999  Tetsuya Okada & Niibe Yutaka
+ *  Copyright (C) 2000  Philipp Rumpf <prumpf@tux.org>
+ *  Copyright (C) 2002 - 2009  Paul Mundt
+ *  Copyright (C) 2002  M. R. Brown  <mrbrown@linux-sh.org>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/profile.h>
+#include <linux/timex.h>
+#include <linux/sched.h>
+#include <linux/clockchips.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+#include <linux/rtc.h>
+#include <asm/clock.h>
+#include <asm/rtc.h>
+
+/* Dummy RTC ops */
+static void null_rtc_get_time(struct timespec *tv)
+{
+	tv->tv_sec = mktime(2000, 1, 1, 0, 0, 0);
+	tv->tv_nsec = 0;
+}
+
+static int null_rtc_set_time(const time_t secs)
+{
+	return 0;
+}
+
+void (*rtc_sh_get_time)(struct timespec *) = null_rtc_get_time;
+int (*rtc_sh_set_time)(const time_t) = null_rtc_set_time;
+
+#ifdef CONFIG_GENERIC_CMOS_UPDATE
+unsigned long read_persistent_clock(void)
+{
+	struct timespec tv;
+	rtc_sh_get_time(&tv);
+	return tv.tv_sec;
+}
+
+int update_persistent_clock(struct timespec now)
+{
+	return rtc_sh_set_time(now.tv_sec);
+}
+#endif
+
+unsigned int get_rtc_time(struct rtc_time *tm)
+{
+	if (rtc_sh_get_time != null_rtc_get_time) {
+		struct timespec tv;
+
+		rtc_sh_get_time(&tv);
+		rtc_time_to_tm(tv.tv_sec, tm);
+	}
+
+	return RTC_24H;
+}
+EXPORT_SYMBOL(get_rtc_time);
+
+int set_rtc_time(struct rtc_time *tm)
+{
+	unsigned long secs;
+
+	rtc_tm_to_time(tm, &secs);
+	return rtc_sh_set_time(secs);
+}
+EXPORT_SYMBOL(set_rtc_time);
+
+static int __init rtc_generic_init(void)
+{
+	struct platform_device *pdev;
+
+	if (rtc_sh_get_time == null_rtc_get_time)
+		return -ENODEV;
+
+	pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	return 0;
+}
+module_init(rtc_generic_init);
+
+void (*board_time_init)(void);
+
+unsigned long long sched_clock(void)
+{
+	return (jiffies_64 - INITIAL_JIFFIES) * (NSEC_PER_SEC / HZ);
+}
+
+static void __init sh_late_time_init(void)
+{
+	/*
+	 * Make sure all compiled-in early timers register themselves.
+	 * Run probe() for one "earlytimer" device.
+	 */
+	early_platform_driver_register_all("earlytimer");
+	early_platform_driver_probe("earlytimer", 1, 0);
+}
+
+void __init time_init(void)
+{
+	if (board_time_init)
+		board_time_init();
+
+	clk_init();
+
+	rtc_sh_get_time(&xtime);
+	set_normalized_timespec(&wall_to_monotonic,
+				-xtime.tv_sec, -xtime.tv_nsec);
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+	local_timer_setup(smp_processor_id());
+#endif
+
+	late_time_init = sh_late_time_init;
+}
diff --git a/arch/sh/kernel/time_32.c b/arch/sh/kernel/time_32.c
deleted file mode 100644
index 1700d2465f6c..000000000000
--- a/arch/sh/kernel/time_32.c
+++ /dev/null
@@ -1,240 +0,0 @@
-/*
- *  arch/sh/kernel/time_32.c
- *
- *  Copyright (C) 1999  Tetsuya Okada & Niibe Yutaka
- *  Copyright (C) 2000  Philipp Rumpf <prumpf@tux.org>
- *  Copyright (C) 2002 - 2008  Paul Mundt
- *  Copyright (C) 2002  M. R. Brown  <mrbrown@linux-sh.org>
- *
- *  Some code taken from i386 version.
- *    Copyright (C) 1991, 1992, 1995  Linus Torvalds
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/profile.h>
-#include <linux/timex.h>
-#include <linux/sched.h>
-#include <linux/clockchips.h>
-#include <linux/mc146818rtc.h>	/* for rtc_lock */
-#include <linux/smp.h>
-#include <asm/clock.h>
-#include <asm/rtc.h>
-#include <asm/timer.h>
-#include <asm/kgdb.h>
-
-struct sys_timer *sys_timer;
-
-/* Move this somewhere more sensible.. */
-DEFINE_SPINLOCK(rtc_lock);
-EXPORT_SYMBOL(rtc_lock);
-
-/* Dummy RTC ops */
-static void null_rtc_get_time(struct timespec *tv)
-{
-	tv->tv_sec = mktime(2000, 1, 1, 0, 0, 0);
-	tv->tv_nsec = 0;
-}
-
-static int null_rtc_set_time(const time_t secs)
-{
-	return 0;
-}
-
-void (*rtc_sh_get_time)(struct timespec *) = null_rtc_get_time;
-int (*rtc_sh_set_time)(const time_t) = null_rtc_set_time;
-
-#ifndef CONFIG_GENERIC_TIME
-void do_gettimeofday(struct timeval *tv)
-{
-	unsigned long flags;
-	unsigned long seq;
-	unsigned long usec, sec;
-
-	do {
-		/*
-		 * Turn off IRQs when grabbing xtime_lock, so that
-		 * the sys_timer get_offset code doesn't have to handle it.
-		 */
-		seq = read_seqbegin_irqsave(&xtime_lock, flags);
-		usec = get_timer_offset();
-		sec = xtime.tv_sec;
-		usec += xtime.tv_nsec / NSEC_PER_USEC;
-	} while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
-
-	while (usec >= 1000000) {
-		usec -= 1000000;
-		sec++;
-	}
-
-	tv->tv_sec = sec;
-	tv->tv_usec = usec;
-}
-EXPORT_SYMBOL(do_gettimeofday);
-
-int do_settimeofday(struct timespec *tv)
-{
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
-
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
-		return -EINVAL;
-
-	write_seqlock_irq(&xtime_lock);
-	/*
-	 * This is revolting. We need to set "xtime" correctly. However, the
-	 * value in this location is the value at the most recent update of
-	 * wall time.  Discover what correction gettimeofday() would have
-	 * made, and then undo it!
-	 */
-	nsec -= get_timer_offset() * NSEC_PER_USEC;
-
-	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
-
-	set_normalized_timespec(&xtime, sec, nsec);
-	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
-
-	ntp_clear();
-	write_sequnlock_irq(&xtime_lock);
-	clock_was_set();
-
-	return 0;
-}
-EXPORT_SYMBOL(do_settimeofday);
-#endif /* !CONFIG_GENERIC_TIME */
-
-/* last time the RTC clock got updated */
-static long last_rtc_update;
-
-/*
- * handle_timer_tick() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
- */
-void handle_timer_tick(void)
-{
-	if (current->pid)
-		profile_tick(CPU_PROFILING);
-
-	/*
-	 * Here we are in the timer irq handler. We just have irqs locally
-	 * disabled but we don't know if the timer_bh is running on the other
-	 * CPU. We need to avoid to SMP race with it. NOTE: we don' t need
-	 * the irq version of write_lock because as just said we have irq
-	 * locally disabled. -arca
-	 */
-	write_seqlock(&xtime_lock);
-	do_timer(1);
-
-	/*
-	 * If we have an externally synchronized Linux clock, then update
-	 * RTC clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-	 * called as close as possible to 500 ms before the new second starts.
-	 */
-	if (ntp_synced() &&
-	    xtime.tv_sec > last_rtc_update + 660 &&
-	    (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 &&
-	    (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) {
-		if (rtc_sh_set_time(xtime.tv_sec) == 0)
-			last_rtc_update = xtime.tv_sec;
-		else
-			/* do it again in 60s */
-			last_rtc_update = xtime.tv_sec - 600;
-	}
-	write_sequnlock(&xtime_lock);
-
-#ifndef CONFIG_SMP
-	update_process_times(user_mode(get_irq_regs()));
-#endif
-}
-
-#ifdef CONFIG_PM
-int timer_suspend(struct sys_device *dev, pm_message_t state)
-{
-	struct sys_timer *sys_timer = container_of(dev, struct sys_timer, dev);
-
-	sys_timer->ops->stop();
-
-	return 0;
-}
-
-int timer_resume(struct sys_device *dev)
-{
-	struct sys_timer *sys_timer = container_of(dev, struct sys_timer, dev);
-
-	sys_timer->ops->start();
-
-	return 0;
-}
-#else
-#define timer_suspend NULL
-#define timer_resume NULL
-#endif
-
-static struct sysdev_class timer_sysclass = {
-	.name	 = "timer",
-	.suspend = timer_suspend,
-	.resume	 = timer_resume,
-};
-
-static int __init timer_init_sysfs(void)
-{
-	int ret;
-
-	if (!sys_timer)
-		return 0;
-
-	ret = sysdev_class_register(&timer_sysclass);
-	if (ret != 0)
-		return ret;
-
-	sys_timer->dev.cls = &timer_sysclass;
-	return sysdev_register(&sys_timer->dev);
-}
-device_initcall(timer_init_sysfs);
-
-void (*board_time_init)(void);
-
-struct clocksource clocksource_sh = {
-	.name		= "SuperH",
-};
-
-#ifdef CONFIG_GENERIC_TIME
-unsigned long long sched_clock(void)
-{
-	unsigned long long cycles;
-
-	/* jiffies based sched_clock if no clocksource is installed */
-	if (!clocksource_sh.rating)
-		return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
-
-	cycles = clocksource_sh.read(&clocksource_sh);
-	return cyc2ns(&clocksource_sh, cycles);
-}
-#endif
-
-void __init time_init(void)
-{
-	if (board_time_init)
-		board_time_init();
-
-	clk_init();
-
-	rtc_sh_get_time(&xtime);
-	set_normalized_timespec(&wall_to_monotonic,
-				-xtime.tv_sec, -xtime.tv_nsec);
-
-#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
-	local_timer_setup(smp_processor_id());
-#endif
-
-	/*
-	 * Find the timer to use as the system timer, it will be
-	 * initialized for us.
-	 */
-	sys_timer = get_sys_timer();
-	if (unlikely(!sys_timer))
-		panic("System timer missing.\n");
-
-	printk(KERN_INFO "Using %s for system timer\n", sys_timer->name);
-}
diff --git a/arch/sh/kernel/time_64.c b/arch/sh/kernel/time_64.c
deleted file mode 100644
index 988c77c37231..000000000000
--- a/arch/sh/kernel/time_64.c
+++ /dev/null
@@ -1,363 +0,0 @@
-/*
- * arch/sh/kernel/time_64.c
- *
- * Copyright (C) 2000, 2001  Paolo Alberelli
- * Copyright (C) 2003 - 2007  Paul Mundt
- * Copyright (C) 2003  Richard Curnow
- *
- *    Original TMU/RTC code taken from sh version.
- *    Copyright (C) 1999  Tetsuya Okada & Niibe Yutaka
- *      Some code taken from i386 version.
- *      Copyright (C) 1991, 1992, 1995  Linus Torvalds
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/errno.h>
-#include <linux/rwsem.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/time.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/profile.h>
-#include <linux/smp.h>
-#include <linux/module.h>
-#include <linux/bcd.h>
-#include <linux/timex.h>
-#include <linux/irq.h>
-#include <linux/io.h>
-#include <linux/platform_device.h>
-#include <cpu/registers.h>	 /* required by inline __asm__ stmt. */
-#include <cpu/irq.h>
-#include <asm/addrspace.h>
-#include <asm/processor.h>
-#include <asm/uaccess.h>
-#include <asm/delay.h>
-#include <asm/clock.h>
-
-#define TMU_TOCR_INIT	0x00
-#define TMU0_TCR_INIT	0x0020
-#define TMU_TSTR_INIT	1
-#define TMU_TSTR_OFF	0
-
-/* Real Time Clock */
-#define	RTC_BLOCK_OFF	0x01040000
-#define RTC_BASE	PHYS_PERIPHERAL_BLOCK + RTC_BLOCK_OFF
-#define RTC_RCR1_CIE	0x10	/* Carry Interrupt Enable */
-#define RTC_RCR1	(rtc_base + 0x38)
-
-/* Time Management Unit */
-#define	TMU_BLOCK_OFF	0x01020000
-#define TMU_BASE	PHYS_PERIPHERAL_BLOCK + TMU_BLOCK_OFF
-#define TMU0_BASE	tmu_base + 0x8 + (0xc * 0x0)
-#define TMU1_BASE	tmu_base + 0x8 + (0xc * 0x1)
-#define TMU2_BASE	tmu_base + 0x8 + (0xc * 0x2)
-
-#define TMU_TOCR	tmu_base+0x0	/* Byte access */
-#define TMU_TSTR	tmu_base+0x4	/* Byte access */
-
-#define TMU0_TCOR	TMU0_BASE+0x0	/* Long access */
-#define TMU0_TCNT	TMU0_BASE+0x4	/* Long access */
-#define TMU0_TCR	TMU0_BASE+0x8	/* Word access */
-
-#define TICK_SIZE (tick_nsec / 1000)
-
-static unsigned long tmu_base, rtc_base;
-unsigned long cprc_base;
-
-/* Variables to allow interpolation of time of day to resolution better than a
- * jiffy. */
-
-/* This is effectively protected by xtime_lock */
-static unsigned long ctc_last_interrupt;
-static unsigned long long usecs_per_jiffy = 1000000/HZ; /* Approximation */
-
-#define CTC_JIFFY_SCALE_SHIFT 40
-
-/* 2**CTC_JIFFY_SCALE_SHIFT / ctc_ticks_per_jiffy */
-static unsigned long long scaled_recip_ctc_ticks_per_jiffy;
-
-/* Estimate number of microseconds that have elapsed since the last timer tick,
-   by scaling the delta that has occurred in the CTC register.
-
-   WARNING WARNING WARNING : This algorithm relies on the CTC decrementing at
-   the CPU clock rate.  If the CPU sleeps, the CTC stops counting.  Bear this
-   in mind if enabling SLEEP_WORKS in process.c.  In that case, this algorithm
-   probably needs to use TMU.TCNT0 instead.  This will work even if the CPU is
-   sleeping, though will be coarser.
-
-   FIXME : What if usecs_per_tick is moving around too much, e.g. if an adjtime
-   is running or if the freq or tick arguments of adjtimex are modified after
-   we have calibrated the scaling factor?  This will result in either a jump at
-   the end of a tick period, or a wrap backwards at the start of the next one,
-   if the application is reading the time of day often enough.  I think we
-   ought to do better than this.  For this reason, usecs_per_jiffy is left
-   separated out in the calculation below.  This allows some future hook into
-   the adjtime-related stuff in kernel/timer.c to remove this hazard.
-
-*/
-
-static unsigned long usecs_since_tick(void)
-{
-	unsigned long long current_ctc;
-	long ctc_ticks_since_interrupt;
-	unsigned long long ull_ctc_ticks_since_interrupt;
-	unsigned long result;
-
-	unsigned long long mul1_out;
-	unsigned long long mul1_out_high;
-	unsigned long long mul2_out_low, mul2_out_high;
-
-	/* Read CTC register */
-	asm ("getcon cr62, %0" : "=r" (current_ctc));
-	/* Note, the CTC counts down on each CPU clock, not up.
-	   Note(2), use long type to get correct wraparound arithmetic when
-	   the counter crosses zero. */
-	ctc_ticks_since_interrupt = (long) ctc_last_interrupt - (long) current_ctc;
-	ull_ctc_ticks_since_interrupt = (unsigned long long) ctc_ticks_since_interrupt;
-
-	/* Inline assembly to do 32x32x32->64 multiplier */
-	asm volatile ("mulu.l %1, %2, %0" :
-	     "=r" (mul1_out) :
-	     "r" (ull_ctc_ticks_since_interrupt), "r" (usecs_per_jiffy));
-
-	mul1_out_high = mul1_out >> 32;
-
-	asm volatile ("mulu.l %1, %2, %0" :
-	     "=r" (mul2_out_low) :
-	     "r" (mul1_out), "r" (scaled_recip_ctc_ticks_per_jiffy));
-
-#if 1
-	asm volatile ("mulu.l %1, %2, %0" :
-	     "=r" (mul2_out_high) :
-	     "r" (mul1_out_high), "r" (scaled_recip_ctc_ticks_per_jiffy));
-#endif
-
-	result = (unsigned long) (((mul2_out_high << 32) + mul2_out_low) >> CTC_JIFFY_SCALE_SHIFT);
-
-	return result;
-}
-
-void do_gettimeofday(struct timeval *tv)
-{
-	unsigned long flags;
-	unsigned long seq;
-	unsigned long usec, sec;
-
-	do {
-		seq = read_seqbegin_irqsave(&xtime_lock, flags);
-		usec = usecs_since_tick();
-		sec = xtime.tv_sec;
-		usec += xtime.tv_nsec / 1000;
-	} while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
-
-	while (usec >= 1000000) {
-		usec -= 1000000;
-		sec++;
-	}
-
-	tv->tv_sec = sec;
-	tv->tv_usec = usec;
-}
-EXPORT_SYMBOL(do_gettimeofday);
-
-int do_settimeofday(struct timespec *tv)
-{
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
-
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
-		return -EINVAL;
-
-	write_seqlock_irq(&xtime_lock);
-	/*
-	 * This is revolting. We need to set "xtime" correctly. However, the
-	 * value in this location is the value at the most recent update of
-	 * wall time.  Discover what correction gettimeofday() would have
-	 * made, and then undo it!
-	 */
-	nsec -= 1000 * usecs_since_tick();
-
-	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
-
-	set_normalized_timespec(&xtime, sec, nsec);
-	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
-
-	ntp_clear();
-	write_sequnlock_irq(&xtime_lock);
-	clock_was_set();
-
-	return 0;
-}
-EXPORT_SYMBOL(do_settimeofday);
-
-/* Dummy RTC ops */
-static void null_rtc_get_time(struct timespec *tv)
-{
-	tv->tv_sec = mktime(2000, 1, 1, 0, 0, 0);
-	tv->tv_nsec = 0;
-}
-
-static int null_rtc_set_time(const time_t secs)
-{
-	return 0;
-}
-
-void (*rtc_sh_get_time)(struct timespec *) = null_rtc_get_time;
-int (*rtc_sh_set_time)(const time_t) = null_rtc_set_time;
-
-/* last time the RTC clock got updated */
-static long last_rtc_update;
-
-/*
- * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "do_timer()" routine every clocktick
- */
-static inline void do_timer_interrupt(void)
-{
-	unsigned long long current_ctc;
-
-	if (current->pid)
-		profile_tick(CPU_PROFILING);
-
-	/*
-	 * Here we are in the timer irq handler. We just have irqs locally
-	 * disabled but we don't know if the timer_bh is running on the other
-	 * CPU. We need to avoid to SMP race with it. NOTE: we don' t need
-	 * the irq version of write_lock because as just said we have irq
-	 * locally disabled. -arca
-	 */
-	write_seqlock(&xtime_lock);
-	asm ("getcon cr62, %0" : "=r" (current_ctc));
-	ctc_last_interrupt = (unsigned long) current_ctc;
-
-	do_timer(1);
-
-	/*
-	 * If we have an externally synchronized Linux clock, then update
-	 * RTC clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
-	 * called as close as possible to 500 ms before the new second starts.
-	 */
-	if (ntp_synced() &&
-	    xtime.tv_sec > last_rtc_update + 660 &&
-	    (xtime.tv_nsec / 1000) >= 500000 - ((unsigned) TICK_SIZE) / 2 &&
-	    (xtime.tv_nsec / 1000) <= 500000 + ((unsigned) TICK_SIZE) / 2) {
-		if (rtc_sh_set_time(xtime.tv_sec) == 0)
-			last_rtc_update = xtime.tv_sec;
-		else
-			/* do it again in 60 s */
-			last_rtc_update = xtime.tv_sec - 600;
-	}
-	write_sequnlock(&xtime_lock);
-
-#ifndef CONFIG_SMP
-	update_process_times(user_mode(get_irq_regs()));
-#endif
-}
-
-/*
- * This is the same as the above, except we _also_ save the current
- * Time Stamp Counter value at the time of the timer interrupt, so that
- * we later on can estimate the time of day more exactly.
- */
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	unsigned long timer_status;
-
-	/* Clear UNF bit */
-	timer_status = ctrl_inw(TMU0_TCR);
-	timer_status &= ~0x100;
-	ctrl_outw(timer_status, TMU0_TCR);
-
-	do_timer_interrupt();
-
-	return IRQ_HANDLED;
-}
-
-static struct irqaction irq0  = {
-	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED,
-	.name = "timer",
-};
-
-void __init time_init(void)
-{
-	unsigned long interval;
-	struct clk *clk;
-
-	tmu_base = onchip_remap(TMU_BASE, 1024, "TMU");
-	if (!tmu_base) {
-		panic("Unable to remap TMU\n");
-	}
-
-	rtc_base = onchip_remap(RTC_BASE, 1024, "RTC");
-	if (!rtc_base) {
-		panic("Unable to remap RTC\n");
-	}
-
-	clk = clk_get(NULL, "cpu_clk");
-	scaled_recip_ctc_ticks_per_jiffy = ((1ULL << CTC_JIFFY_SCALE_SHIFT) /
-			(unsigned long long)(clk_get_rate(clk) / HZ));
-
-	rtc_sh_get_time(&xtime);
-
-	setup_irq(TIMER_IRQ, &irq0);
-
-	clk = clk_get(NULL, "module_clk");
-	interval = (clk_get_rate(clk)/(HZ*4));
-
-	printk("Interval = %ld\n", interval);
-
-	/* Start TMU0 */
-	ctrl_outb(TMU_TSTR_OFF, TMU_TSTR);
-	ctrl_outb(TMU_TOCR_INIT, TMU_TOCR);
-	ctrl_outw(TMU0_TCR_INIT, TMU0_TCR);
-	ctrl_outl(interval, TMU0_TCOR);
-	ctrl_outl(interval, TMU0_TCNT);
-	ctrl_outb(TMU_TSTR_INIT, TMU_TSTR);
-}
-
-static struct resource rtc_resources[] = {
-	[0] = {
-		/* RTC base, filled in by rtc_init */
-		.flags	= IORESOURCE_IO,
-	},
-	[1] = {
-		/* Period IRQ */
-		.start	= IRQ_PRI,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = {
-		/* Carry IRQ */
-		.start	= IRQ_CUI,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[3] = {
-		/* Alarm IRQ */
-		.start	= IRQ_ATI,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device rtc_device = {
-	.name		= "sh-rtc",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(rtc_resources),
-	.resource	= rtc_resources,
-};
-
-static int __init rtc_init(void)
-{
-	rtc_resources[0].start	= rtc_base;
-	rtc_resources[0].end	= rtc_resources[0].start + 0x58 - 1;
-
-	return platform_device_register(&rtc_device);
-}
-device_initcall(rtc_init);
diff --git a/arch/sh/kernel/timers/Makefile b/arch/sh/kernel/timers/Makefile
deleted file mode 100644
index 0b7f8577193f..000000000000
--- a/arch/sh/kernel/timers/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-#
-# Makefile for the various Linux/SuperH timers
-#
-
-obj-y	:= timer.o
-
-obj-$(CONFIG_SH_TMU)		+= timer-tmu.o
-obj-$(CONFIG_SH_MTU2)		+= timer-mtu2.o
-obj-$(CONFIG_SH_CMT)		+= timer-cmt.o
-
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= timer-broadcast.o
diff --git a/arch/sh/kernel/timers/timer-cmt.c b/arch/sh/kernel/timers/timer-cmt.c
deleted file mode 100644
index 9aa348658ae3..000000000000
--- a/arch/sh/kernel/timers/timer-cmt.c
+++ /dev/null
@@ -1,188 +0,0 @@
-/*
- * arch/sh/kernel/timers/timer-cmt.c - CMT Timer Support
- *
- *  Copyright (C) 2005  Yoshinori Sato
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/seqlock.h>
-#include <asm/timer.h>
-#include <asm/rtc.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/clock.h>
-
-#if defined(CONFIG_CPU_SUBTYPE_SH7619)
-#define CMT_CMSTR	0xf84a0070
-#define CMT_CMCSR_0	0xf84a0072
-#define CMT_CMCNT_0	0xf84a0074
-#define CMT_CMCOR_0	0xf84a0076
-#define CMT_CMCSR_1	0xf84a0078
-#define CMT_CMCNT_1	0xf84a007a
-#define CMT_CMCOR_1	0xf84a007c
-
-#define STBCR3		0xf80a0000
-#define cmt_clock_enable() do {	ctrl_outb(ctrl_inb(STBCR3) & ~0x10, STBCR3); } while(0)
-#define CMT_CMCSR_INIT	0x0040
-#define CMT_CMCSR_CALIB	0x0000
-#elif defined(CONFIG_CPU_SUBTYPE_SH7203) || \
-      defined(CONFIG_CPU_SUBTYPE_SH7206) || \
-      defined(CONFIG_CPU_SUBTYPE_SH7263)
-#define CMT_CMSTR	0xfffec000
-#define CMT_CMCSR_0	0xfffec002
-#define CMT_CMCNT_0	0xfffec004
-#define CMT_CMCOR_0	0xfffec006
-
-#define STBCR4		0xfffe040c
-#define cmt_clock_enable() do {	ctrl_outb(ctrl_inb(STBCR4) & ~0x04, STBCR4); } while(0)
-#define CMT_CMCSR_INIT	0x0040
-#define CMT_CMCSR_CALIB	0x0000
-#else
-#error "Unknown CPU SUBTYPE"
-#endif
-
-static unsigned long cmt_timer_get_offset(void)
-{
-	int count;
-	static unsigned short count_p = 0xffff;    /* for the first call after boot */
-	static unsigned long jiffies_p = 0;
-
-	/*
-	 * cache volatile jiffies temporarily; we have IRQs turned off.
-	 */
-	unsigned long jiffies_t;
-
-	/* timer count may underflow right here */
-	count =  ctrl_inw(CMT_CMCOR_0);
-	count -= ctrl_inw(CMT_CMCNT_0);
-
-	jiffies_t = jiffies;
-
-	/*
-	 * avoiding timer inconsistencies (they are rare, but they happen)...
-	 * there is one kind of problem that must be avoided here:
-	 *  1. the timer counter underflows
-	 */
-
-	if (jiffies_t == jiffies_p) {
-		if (count > count_p) {
-			/* the nutcase */
-			if (ctrl_inw(CMT_CMCSR_0) & 0x80) { /* Check CMF bit */
-				count -= LATCH;
-			} else {
-				printk("%s (): hardware timer problem?\n",
-				       __func__);
-			}
-		}
-	} else
-		jiffies_p = jiffies_t;
-
-	count_p = count;
-
-	count = ((LATCH-1) - count) * TICK_SIZE;
-	count = (count + LATCH/2) / LATCH;
-
-	return count;
-}
-
-static irqreturn_t cmt_timer_interrupt(int irq, void *dev_id)
-{
-	unsigned long timer_status;
-
-	/* Clear CMF bit */
-	timer_status = ctrl_inw(CMT_CMCSR_0);
-	timer_status &= ~0x80;
-	ctrl_outw(timer_status, CMT_CMCSR_0);
-
-	handle_timer_tick();
-
-	return IRQ_HANDLED;
-}
-
-static struct irqaction cmt_irq = {
-	.name		= "timer",
-	.handler	= cmt_timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
-};
-
-static void cmt_clk_init(struct clk *clk)
-{
-	u8 divisor = CMT_CMCSR_INIT & 0x3;
-	ctrl_inw(CMT_CMCSR_0);
-	ctrl_outw(CMT_CMCSR_INIT, CMT_CMCSR_0);
-	clk->parent = clk_get(NULL, "module_clk");
-	clk->rate = clk->parent->rate / (8 << (divisor << 1));
-}
-
-static void cmt_clk_recalc(struct clk *clk)
-{
-	u8 divisor = ctrl_inw(CMT_CMCSR_0) & 0x3;
-	clk->rate = clk->parent->rate / (8 << (divisor << 1));
-}
-
-static struct clk_ops cmt_clk_ops = {
-	.init		= cmt_clk_init,
-	.recalc		= cmt_clk_recalc,
-};
-
-static struct clk cmt0_clk = {
-	.name		= "cmt0_clk",
-	.ops		= &cmt_clk_ops,
-};
-
-static int cmt_timer_start(void)
-{
-	ctrl_outw(ctrl_inw(CMT_CMSTR) | 0x01, CMT_CMSTR);
-	return 0;
-}
-
-static int cmt_timer_stop(void)
-{
-	ctrl_outw(ctrl_inw(CMT_CMSTR) & ~0x01, CMT_CMSTR);
-	return 0;
-}
-
-static int cmt_timer_init(void)
-{
-	unsigned long interval;
-
-	cmt_clock_enable();
-
-	setup_irq(CONFIG_SH_TIMER_IRQ, &cmt_irq);
-
-	cmt0_clk.parent = clk_get(NULL, "module_clk");
-
-	cmt_timer_stop();
-
-	interval = cmt0_clk.parent->rate / 8 / HZ;
-	printk(KERN_INFO "Interval = %ld\n", interval);
-
-	ctrl_outw(interval, CMT_CMCOR_0);
-
-	clk_register(&cmt0_clk);
-	clk_enable(&cmt0_clk);
-
-	cmt_timer_start();
-
-	return 0;
-}
-
-static struct sys_timer_ops cmt_timer_ops = {
-	.init		= cmt_timer_init,
-	.start		= cmt_timer_start,
-	.stop		= cmt_timer_stop,
-#ifndef CONFIG_GENERIC_TIME
-	.get_offset	= cmt_timer_get_offset,
-#endif
-};
-
-struct sys_timer cmt_timer = {
-	.name	= "cmt",
-	.ops	= &cmt_timer_ops,
-};
diff --git a/arch/sh/kernel/timers/timer-mtu2.c b/arch/sh/kernel/timers/timer-mtu2.c
deleted file mode 100644
index 9b0ef0126479..000000000000
--- a/arch/sh/kernel/timers/timer-mtu2.c
+++ /dev/null
@@ -1,202 +0,0 @@
-/*
- * arch/sh/kernel/timers/timer-mtu2.c - MTU2 Timer Support
- *
- *  Copyright (C) 2005  Paul Mundt
- *
- * Based off of arch/sh/kernel/timers/timer-tmu.c
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/seqlock.h>
-#include <asm/timer.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/clock.h>
-
-/*
- * We use channel 1 for our lowly system timer. Channel 2 would be the other
- * likely candidate, but we leave it alone as it has higher divisors that
- * would be of more use to other more interesting applications.
- *
- * TODO: Presently we only implement a 16-bit single-channel system timer.
- * However, we can implement channel cascade if we go the overflow route and
- * get away with using 2 MTU2 channels as a 32-bit timer.
- */
-#define MTU2_TSTR	0xfffe4280
-#define MTU2_TCR_1	0xfffe4380
-#define MTU2_TMDR_1	0xfffe4381
-#define MTU2_TIOR_1	0xfffe4382
-#define MTU2_TIER_1	0xfffe4384
-#define MTU2_TSR_1	0xfffe4385
-#define MTU2_TCNT_1	0xfffe4386	/* 16-bit counter */
-
-#if defined(CONFIG_CPU_SUBTYPE_SH7201) || \
-    defined(CONFIG_CPU_SUBTYPE_SH7203)
-#define MTU2_TGRA_1	0xfffe4388
-#else
-#define MTU2_TGRA_1	0xfffe438a
-#endif
-
-#define STBCR3		0xfffe0408
-
-#define MTU2_TSTR_CST1	(1 << 1)	/* Counter Start 1 */
-
-#define MTU2_TSR_TGFA	(1 << 0)	/* GRA compare match */
-
-#define MTU2_TIER_TGIEA	(1 << 0)	/* GRA compare match  interrupt enable */
-
-#define MTU2_TCR_INIT	0x22
-
-#define MTU2_TCR_CALIB  0x00
-
-static unsigned long mtu2_timer_get_offset(void)
-{
-	int count;
-	static int count_p = 0x7fff;	/* for the first call after boot */
-	static unsigned long jiffies_p = 0;
-
-	/*
-	 * cache volatile jiffies temporarily; we have IRQs turned off.
-	 */
-	unsigned long jiffies_t;
-
-	/* timer count may underflow right here */
-	count = ctrl_inw(MTU2_TCNT_1);	/* read the latched count */
-
-	jiffies_t = jiffies;
-
-	/*
-	 * avoiding timer inconsistencies (they are rare, but they happen)...
-	 * there is one kind of problem that must be avoided here:
-	 *  1. the timer counter underflows
-	 */
-
-	if (jiffies_t == jiffies_p) {
-		if (count > count_p) {
-			if (ctrl_inb(MTU2_TSR_1) & MTU2_TSR_TGFA) {
-				count -= LATCH;
-			} else {
-				printk("%s (): hardware timer problem?\n",
-				       __func__);
-			}
-		}
-	} else
-		jiffies_p = jiffies_t;
-
-	count_p = count;
-
-	count = ((LATCH-1) - count) * TICK_SIZE;
-	count = (count + LATCH/2) / LATCH;
-
-	return count;
-}
-
-static irqreturn_t mtu2_timer_interrupt(int irq, void *dev_id)
-{
-	unsigned long timer_status;
-
-	/* Clear TGFA bit */
-	timer_status = ctrl_inb(MTU2_TSR_1);
-	timer_status &= ~MTU2_TSR_TGFA;
-	ctrl_outb(timer_status, MTU2_TSR_1);
-
-	/* Do timer tick */
-	handle_timer_tick();
-
-	return IRQ_HANDLED;
-}
-
-static struct irqaction mtu2_irq = {
-	.name		= "timer",
-	.handler	= mtu2_timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
-};
-
-static unsigned int divisors[] = { 1, 4, 16, 64, 1, 1, 256 };
-
-static void mtu2_clk_init(struct clk *clk)
-{
-	u8 idx = MTU2_TCR_INIT & 0x7;
-
-	clk->rate = clk->parent->rate / divisors[idx];
-	/* Start TCNT counting */
-	ctrl_outb(ctrl_inb(MTU2_TSTR) | MTU2_TSTR_CST1, MTU2_TSTR);
-
-}
-
-static void mtu2_clk_recalc(struct clk *clk)
-{
-	u8 idx = ctrl_inb(MTU2_TCR_1) & 0x7;
-	clk->rate = clk->parent->rate / divisors[idx];
-}
-
-static struct clk_ops mtu2_clk_ops = {
-	.init		= mtu2_clk_init,
-	.recalc		= mtu2_clk_recalc,
-};
-
-static struct clk mtu2_clk1 = {
-	.name		= "mtu2_clk1",
-	.ops		= &mtu2_clk_ops,
-};
-
-static int mtu2_timer_start(void)
-{
-	ctrl_outb(ctrl_inb(MTU2_TSTR) | MTU2_TSTR_CST1, MTU2_TSTR);
-	return 0;
-}
-
-static int mtu2_timer_stop(void)
-{
-	ctrl_outb(ctrl_inb(MTU2_TSTR) & ~MTU2_TSTR_CST1, MTU2_TSTR);
-	return 0;
-}
-
-static int mtu2_timer_init(void)
-{
-	unsigned long interval;
-
-	setup_irq(CONFIG_SH_TIMER_IRQ, &mtu2_irq);
-
-	mtu2_clk1.parent = clk_get(NULL, "module_clk");
-
-	ctrl_outb(ctrl_inb(STBCR3) & (~0x20), STBCR3);
-
-	/* Normal operation */
-	ctrl_outb(0, MTU2_TMDR_1);
-	ctrl_outb(MTU2_TCR_INIT, MTU2_TCR_1);
-	ctrl_outb(0x01, MTU2_TIOR_1);
-
-	/* Enable underflow interrupt */
-	ctrl_outb(ctrl_inb(MTU2_TIER_1) | MTU2_TIER_TGIEA, MTU2_TIER_1);
-
-	interval = CONFIG_SH_PCLK_FREQ / 16 / HZ;
-	printk(KERN_INFO "Interval = %ld\n", interval);
-
-	ctrl_outw(interval, MTU2_TGRA_1);
-	ctrl_outw(0, MTU2_TCNT_1);
-
-	clk_register(&mtu2_clk1);
-	clk_enable(&mtu2_clk1);
-
-	return 0;
-}
-
-struct sys_timer_ops mtu2_timer_ops = {
-	.init		= mtu2_timer_init,
-	.start		= mtu2_timer_start,
-	.stop		= mtu2_timer_stop,
-#ifndef CONFIG_GENERIC_TIME
-	.get_offset	= mtu2_timer_get_offset,
-#endif
-};
-
-struct sys_timer mtu2_timer = {
-	.name	= "mtu2",
-	.ops	= &mtu2_timer_ops,
-};
diff --git a/arch/sh/kernel/timers/timer-tmu.c b/arch/sh/kernel/timers/timer-tmu.c
deleted file mode 100644
index fe8d8930ccb6..000000000000
--- a/arch/sh/kernel/timers/timer-tmu.c
+++ /dev/null
@@ -1,297 +0,0 @@
-/*
- * arch/sh/kernel/timers/timer-tmu.c - TMU Timer Support
- *
- *  Copyright (C) 2005 - 2007  Paul Mundt
- *
- * TMU handling code hacked out of arch/sh/kernel/time.c
- *
- *  Copyright (C) 1999  Tetsuya Okada & Niibe Yutaka
- *  Copyright (C) 2000  Philipp Rumpf <prumpf@tux.org>
- *  Copyright (C) 2002, 2003, 2004  Paul Mundt
- *  Copyright (C) 2002  M. R. Brown  <mrbrown@linux-sh.org>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/seqlock.h>
-#include <linux/clockchips.h>
-#include <asm/timer.h>
-#include <asm/rtc.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/clock.h>
-
-#define TMU_TOCR_INIT	0x00
-#define TMU_TCR_INIT	0x0020
-
-#define TMU0		(0)
-#define TMU1		(1)
-
-static inline void _tmu_start(int tmu_num)
-{
-	ctrl_outb(ctrl_inb(TMU_012_TSTR) | (0x1<<tmu_num), TMU_012_TSTR);
-}
-
-static inline void _tmu_set_irq(int tmu_num, int enabled)
-{
-	register unsigned long tmu_tcr = TMU0_TCR + (0xc*tmu_num);
-	ctrl_outw( (enabled ? ctrl_inw(tmu_tcr) | (1<<5) : ctrl_inw(tmu_tcr) & ~(1<<5)), tmu_tcr);
-}
-
-static inline void _tmu_stop(int tmu_num)
-{
-	ctrl_outb(ctrl_inb(TMU_012_TSTR) & ~(0x1<<tmu_num), TMU_012_TSTR);
-}
-
-static inline void _tmu_clear_status(int tmu_num)
-{
-	register unsigned long tmu_tcr = TMU0_TCR + (0xc*tmu_num);
-	/* Clear UNF bit */
-	ctrl_outw(ctrl_inw(tmu_tcr) & ~0x100, tmu_tcr);
-}
-
-static inline unsigned long _tmu_read(int tmu_num)
-{
-        return ctrl_inl(TMU0_TCNT+0xC*tmu_num);
-}
-
-static int tmu_timer_start(void)
-{
-	_tmu_start(TMU0);
-	_tmu_start(TMU1);
-	_tmu_set_irq(TMU0,1);
-	return 0;
-}
-
-static int tmu_timer_stop(void)
-{
-	_tmu_stop(TMU0);
-	_tmu_stop(TMU1);
-	_tmu_clear_status(TMU0);
-	return 0;
-}
-
-/*
- * also when the module_clk is scaled the TMU1
- * will show the same frequency
- */
-static int tmus_are_scaled;
-
-static cycle_t tmu_timer_read(struct clocksource *cs)
-{
-	return ((cycle_t)(~_tmu_read(TMU1)))<<tmus_are_scaled;
-}
-
-
-static unsigned long tmu_latest_interval[3];
-static void tmu_timer_set_interval(int tmu_num, unsigned long interval, unsigned int reload)
-{
-	unsigned long tmu_tcnt = TMU0_TCNT + tmu_num*0xC;
-	unsigned long tmu_tcor = TMU0_TCOR + tmu_num*0xC;
-
-	_tmu_stop(tmu_num);
-
-	ctrl_outl(interval, tmu_tcnt);
-	tmu_latest_interval[tmu_num] = interval;
-
-	/*
-	 * TCNT reloads from TCOR on underflow, clear it if we don't
-	 * intend to auto-reload
-	 */
-	ctrl_outl( reload ? interval : 0 , tmu_tcor);
-
-	_tmu_start(tmu_num);
-}
-
-static int tmu_set_next_event(unsigned long cycles,
-			      struct clock_event_device *evt)
-{
-	tmu_timer_set_interval(TMU0,cycles, evt->mode == CLOCK_EVT_MODE_PERIODIC);
-	_tmu_set_irq(TMU0,1);
-	return 0;
-}
-
-static void tmu_set_mode(enum clock_event_mode mode,
-			 struct clock_event_device *evt)
-{
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		ctrl_outl(tmu_latest_interval[TMU0], TMU0_TCOR);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		ctrl_outl(0, TMU0_TCOR);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	}
-}
-
-static struct clock_event_device tmu0_clockevent = {
-	.name		= "tmu0",
-	.shift		= 32,
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= tmu_set_mode,
-	.set_next_event	= tmu_set_next_event,
-};
-
-static irqreturn_t tmu_timer_interrupt(int irq, void *dummy)
-{
-	struct clock_event_device *evt = &tmu0_clockevent;
-	_tmu_clear_status(TMU0);
-	_tmu_set_irq(TMU0,tmu0_clockevent.mode != CLOCK_EVT_MODE_ONESHOT);
-
-	switch (tmu0_clockevent.mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_PERIODIC:
-		evt->event_handler(evt);
-		break;
-	default:
-		break;
-	}
-
-	return IRQ_HANDLED;
-}
-
-static struct irqaction tmu0_irq = {
-	.name		= "periodic/oneshot timer",
-	.handler	= tmu_timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
-};
-
-static void __init tmu_clk_init(struct clk *clk)
-{
-	u8 divisor  = TMU_TCR_INIT & 0x7;
-	int tmu_num = clk->name[3]-'0';
-	ctrl_outw(TMU_TCR_INIT, TMU0_TCR+(tmu_num*0xC));
-	clk->rate = clk_get_rate(clk->parent) / (4 << (divisor << 1));
-}
-
-static void tmu_clk_recalc(struct clk *clk)
-{
-	int tmu_num = clk->name[3]-'0';
-	unsigned long prev_rate = clk_get_rate(clk);
-	unsigned long flags;
-	u8 divisor = ctrl_inw(TMU0_TCR+tmu_num*0xC) & 0x7;
-	clk->rate  = clk_get_rate(clk->parent) / (4 << (divisor << 1));
-
-	if(prev_rate==clk_get_rate(clk))
-		return;
-
-	if(tmu_num)
-		return; /* No more work on TMU1 */
-
-	local_irq_save(flags);
-	tmus_are_scaled = (prev_rate > clk->rate);
-
-	_tmu_stop(TMU0);
-
-	tmu0_clockevent.mult = div_sc(clk->rate, NSEC_PER_SEC,
-				tmu0_clockevent.shift);
-	tmu0_clockevent.max_delta_ns =
-			clockevent_delta2ns(-1, &tmu0_clockevent);
-	tmu0_clockevent.min_delta_ns =
-			clockevent_delta2ns(1, &tmu0_clockevent);
-
-	if (tmus_are_scaled)
-		tmu_latest_interval[TMU0] >>= 1;
-	else
-		tmu_latest_interval[TMU0] <<= 1;
-
-	tmu_timer_set_interval(TMU0,
-		tmu_latest_interval[TMU0],
-		tmu0_clockevent.mode == CLOCK_EVT_MODE_PERIODIC);
-
-	_tmu_start(TMU0);
-
-	local_irq_restore(flags);
-}
-
-static struct clk_ops tmu_clk_ops = {
-	.init		= tmu_clk_init,
-	.recalc		= tmu_clk_recalc,
-};
-
-static struct clk tmu0_clk = {
-	.name		= "tmu0_clk",
-	.ops		= &tmu_clk_ops,
-};
-
-static struct clk tmu1_clk = {
-	.name		= "tmu1_clk",
-	.ops		= &tmu_clk_ops,
-};
-
-static int tmu_timer_init(void)
-{
-	unsigned long interval;
-	unsigned long frequency;
-
-	setup_irq(CONFIG_SH_TIMER_IRQ, &tmu0_irq);
-
-	tmu0_clk.parent = clk_get(NULL, "module_clk");
-	tmu1_clk.parent = clk_get(NULL, "module_clk");
-
-	tmu_timer_stop();
-
-#if !defined(CONFIG_CPU_SUBTYPE_SH7720) && \
-    !defined(CONFIG_CPU_SUBTYPE_SH7721) && \
-    !defined(CONFIG_CPU_SUBTYPE_SH7760) && \
-    !defined(CONFIG_CPU_SUBTYPE_SH7785) && \
-    !defined(CONFIG_CPU_SUBTYPE_SH7786) && \
-    !defined(CONFIG_CPU_SUBTYPE_SHX3)
-	ctrl_outb(TMU_TOCR_INIT, TMU_TOCR);
-#endif
-
-	clk_register(&tmu0_clk);
-	clk_register(&tmu1_clk);
-	clk_enable(&tmu0_clk);
-	clk_enable(&tmu1_clk);
-
-	frequency = clk_get_rate(&tmu0_clk);
-	interval = (frequency + HZ / 2) / HZ;
-
-	tmu_timer_set_interval(TMU0,interval, 1);
-	tmu_timer_set_interval(TMU1,~0,1);
-
-	_tmu_start(TMU1);
-
-	clocksource_sh.rating = 200;
-	clocksource_sh.mask = CLOCKSOURCE_MASK(32);
-	clocksource_sh.read = tmu_timer_read;
-	clocksource_sh.shift = 10;
-	clocksource_sh.mult = clocksource_hz2mult(clk_get_rate(&tmu1_clk),
-						  clocksource_sh.shift);
-	clocksource_sh.flags = CLOCK_SOURCE_IS_CONTINUOUS;
-	clocksource_register(&clocksource_sh);
-
-	tmu0_clockevent.mult = div_sc(frequency, NSEC_PER_SEC,
-				      tmu0_clockevent.shift);
-	tmu0_clockevent.max_delta_ns =
-			clockevent_delta2ns(-1, &tmu0_clockevent);
-	tmu0_clockevent.min_delta_ns =
-			clockevent_delta2ns(1, &tmu0_clockevent);
-
-	tmu0_clockevent.cpumask = cpumask_of(0);
-	tmu0_clockevent.rating = 100;
-
-	clockevents_register_device(&tmu0_clockevent);
-
-	return 0;
-}
-
-static struct sys_timer_ops tmu_timer_ops = {
-	.init		= tmu_timer_init,
-	.start		= tmu_timer_start,
-	.stop		= tmu_timer_stop,
-};
-
-struct sys_timer tmu_timer = {
-	.name	= "tmu",
-	.ops	= &tmu_timer_ops,
-};
diff --git a/arch/sh/kernel/timers/timer.c b/arch/sh/kernel/timers/timer.c
deleted file mode 100644
index 4e7e747d1b69..000000000000
--- a/arch/sh/kernel/timers/timer.c
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * arch/sh/kernel/timers/timer.c - Common timer code
- *
- *  Copyright (C) 2005  Paul Mundt
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/timer.h>
-#include <linux/string.h>
-#include <asm/timer.h>
-
-static struct sys_timer *sys_timers[] = {
-#ifdef CONFIG_SH_TMU
-	&tmu_timer,
-#endif
-#ifdef CONFIG_SH_MTU2
-	&mtu2_timer,
-#endif
-#ifdef CONFIG_SH_CMT
-	&cmt_timer,
-#endif
-	NULL,
-};
-
-static char timer_override[10];
-static int __init timer_setup(char *str)
-{
-	if (str)
-		strlcpy(timer_override, str, sizeof(timer_override));
-	return 1;
-}
-__setup("timer=", timer_setup);
-
-struct sys_timer *get_sys_timer(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(sys_timers); i++) {
-		struct sys_timer *t = sys_timers[i];
-
-		if (unlikely(!t))
-			break;
-		if (unlikely(timer_override[0]))
-			if ((strcmp(timer_override, t->name) != 0))
-				continue;
-		if (likely(t->ops->init() == 0))
-			return t;
-	}
-
-	return NULL;
-}
diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index 438f1ebcc453..46348ed07cc3 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -22,11 +22,11 @@ static void handle_BUG(struct pt_regs *regs)
 
 int is_valid_bugaddr(unsigned long addr)
 {
-	unsigned short opcode;
+	insn_size_t opcode;
 
 	if (addr < PAGE_OFFSET)
 		return 0;
-	if (probe_kernel_address((u16 *)addr, opcode))
+	if (probe_kernel_address((insn_size_t *)addr, opcode))
 		return 0;
 
 	return opcode == TRAPA_BUG_OPCODE;
@@ -66,7 +66,7 @@ BUILD_TRAP_HANDLER(bug)
 
 #ifdef CONFIG_BUG
 	if (__kernel_text_address(instruction_pointer(regs))) {
-		opcode_t insn = *(opcode_t *)instruction_pointer(regs);
+		insn_size_t insn = *(insn_size_t *)instruction_pointer(regs);
 		if (insn == TRAPA_BUG_OPCODE)
 			handle_BUG(regs);
 	}
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 30ca9c51e52d..2b772776fcda 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -34,6 +34,7 @@
 # define TRAP_ILLEGAL_SLOT_INST	6
 # define TRAP_ADDRESS_ERROR	9
 # ifdef CONFIG_CPU_SH2A
+#  define TRAP_UBC		12
 #  define TRAP_FPU_ERROR	13
 #  define TRAP_DIVZERO_ERROR	17
 #  define TRAP_DIVOVF_ERROR	18
@@ -176,7 +177,7 @@ static struct mem_access user_mem_access = {
  *   (if that instruction is in a branch delay slot)
  * - return 0 if emulation okay, -EFAULT on existential error
  */
-static int handle_unaligned_ins(opcode_t instruction, struct pt_regs *regs,
+static int handle_unaligned_ins(insn_size_t instruction, struct pt_regs *regs,
 				struct mem_access *ma)
 {
 	int ret, index, count;
@@ -321,10 +322,10 @@ static int handle_unaligned_ins(opcode_t instruction, struct pt_regs *regs,
  * - fetches the instruction from PC+2
  */
 static inline int handle_delayslot(struct pt_regs *regs,
-				   opcode_t old_instruction,
+				   insn_size_t old_instruction,
 				   struct mem_access *ma)
 {
-	opcode_t instruction;
+	insn_size_t instruction;
 	void __user *addr = (void __user *)(regs->pc +
 		instruction_size(old_instruction));
 
@@ -364,7 +365,7 @@ static inline int handle_delayslot(struct pt_regs *regs,
 
 static int handle_unaligned_notify_count = 10;
 
-int handle_unaligned_access(opcode_t instruction, struct pt_regs *regs,
+int handle_unaligned_access(insn_size_t instruction, struct pt_regs *regs,
 			    struct mem_access *ma)
 {
 	u_int rm;
@@ -522,7 +523,7 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 	unsigned long error_code = 0;
 	mm_segment_t oldfs;
 	siginfo_t info;
-	opcode_t instruction;
+	insn_size_t instruction;
 	int tmp;
 
 	/* Intentional ifdef */
@@ -849,6 +850,10 @@ void __init trap_init(void)
 #endif
 #endif
 
+#ifdef TRAP_UBC
+	set_exception_table_vec(TRAP_UBC, break_point_trap);
+#endif
+
 	/* Setup VBR for boot cpu */
 	per_cpu_trap_init();
 }
diff --git a/arch/sh/kernel/traps_64.c b/arch/sh/kernel/traps_64.c
index a85831cbf18b..267e5ebbb475 100644
--- a/arch/sh/kernel/traps_64.c
+++ b/arch/sh/kernel/traps_64.c
@@ -370,7 +370,6 @@ static int generate_and_check_address(struct pt_regs *regs,
 		return -1;
 	}
 
-#if defined(CONFIG_SH64_USER_MISALIGNED_FIXUP)
 	/* Check accessible.  For misaligned access in the kernel, assume the
 	   address is always accessible (and if not, just fault when the
 	   load/store gets done.) */
@@ -380,18 +379,13 @@ static int generate_and_check_address(struct pt_regs *regs,
 		}
 		/* Do access_ok check later - it depends on whether it's a load or a store. */
 	}
-#endif
 
 	*address = addr;
 	return 0;
 }
 
-/* Default value as for sh */
-#if defined(CONFIG_SH64_USER_MISALIGNED_FIXUP)
 static int user_mode_unaligned_fixup_count = 10;
 static int user_mode_unaligned_fixup_enable = 1;
-#endif
-
 static int kernel_mode_unaligned_fixup_count = 32;
 
 static void misaligned_kernel_word_load(__u64 address, int do_sign_extend, __u64 *result)
@@ -440,7 +434,6 @@ static int misaligned_load(struct pt_regs *regs,
 	}
 
 	destreg = (opcode >> 4) & 0x3f;
-#if defined(CONFIG_SH64_USER_MISALIGNED_FIXUP)
 	if (user_mode(regs)) {
 		__u64 buffer;
 
@@ -470,9 +463,7 @@ static int misaligned_load(struct pt_regs *regs,
 				width_shift, (unsigned long) regs->pc);
 			break;
 		}
-	} else
-#endif
-	{
+	} else {
 		/* kernel mode - we can take short cuts since if we fault, it's a genuine bug */
 		__u64 lo, hi;
 
@@ -519,7 +510,6 @@ static int misaligned_store(struct pt_regs *regs,
 	}
 
 	srcreg = (opcode >> 4) & 0x3f;
-#if defined(CONFIG_SH64_USER_MISALIGNED_FIXUP)
 	if (user_mode(regs)) {
 		__u64 buffer;
 
@@ -546,9 +536,7 @@ static int misaligned_store(struct pt_regs *regs,
 		if (__copy_user((void *)(int)address, &buffer, (1 << width_shift)) > 0) {
 			return -1; /* fault */
 		}
-	} else
-#endif
-	{
+	} else {
 		/* kernel mode - we can take short cuts since if we fault, it's a genuine bug */
 		__u64 val = regs->regs[srcreg];
 
@@ -576,7 +564,6 @@ static int misaligned_store(struct pt_regs *regs,
 
 }
 
-#if defined(CONFIG_SH64_USER_MISALIGNED_FIXUP)
 /* Never need to fix up misaligned FPU accesses within the kernel since that's a real
    error. */
 static int misaligned_fpu_load(struct pt_regs *regs,
@@ -727,7 +714,6 @@ static int misaligned_fpu_store(struct pt_regs *regs,
 		return -1;
 	}
 }
-#endif
 
 static int misaligned_fixup(struct pt_regs *regs)
 {
@@ -735,12 +721,8 @@ static int misaligned_fixup(struct pt_regs *regs)
 	int error;
 	int major, minor;
 
-#if !defined(CONFIG_SH64_USER_MISALIGNED_FIXUP)
-	/* Never fixup user mode misaligned accesses without this option enabled. */
-	return -1;
-#else
-	if (!user_mode_unaligned_fixup_enable) return -1;
-#endif
+	if (!user_mode_unaligned_fixup_enable)
+		return -1;
 
 	error = read_opcode(regs->pc, &opcode, user_mode(regs));
 	if (error < 0) {
@@ -749,15 +731,12 @@ static int misaligned_fixup(struct pt_regs *regs)
 	major = (opcode >> 26) & 0x3f;
 	minor = (opcode >> 16) & 0xf;
 
-#if defined(CONFIG_SH64_USER_MISALIGNED_FIXUP)
 	if (user_mode(regs) && (user_mode_unaligned_fixup_count > 0)) {
 		--user_mode_unaligned_fixup_count;
 		/* Only do 'count' worth of these reports, to remove a potential DoS against syslog */
 		printk("Fixing up unaligned userspace access in \"%s\" pid=%d pc=0x%08x ins=0x%08lx\n",
 		       current->comm, task_pid_nr(current), (__u32)regs->pc, opcode);
-	} else
-#endif
-	if (!user_mode(regs) && (kernel_mode_unaligned_fixup_count > 0)) {
+	} else if (!user_mode(regs) && (kernel_mode_unaligned_fixup_count > 0)) {
 		--kernel_mode_unaligned_fixup_count;
 		if (in_interrupt()) {
 			printk("Fixing up unaligned kernelspace access in interrupt pc=0x%08x ins=0x%08lx\n",
@@ -830,7 +809,6 @@ static int misaligned_fixup(struct pt_regs *regs)
 			}
 			break;
 
-#if defined(CONFIG_SH64_USER_MISALIGNED_FIXUP)
 		case (0x94>>2): /* FLD.S */
 			error = misaligned_fpu_load(regs, opcode, 1, 2, 0);
 			break;
@@ -881,7 +859,6 @@ static int misaligned_fixup(struct pt_regs *regs)
 				break;
 			}
 			break;
-#endif
 
 		default:
 			/* Fault */
@@ -907,7 +884,6 @@ static ctl_table unaligned_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec
 	},
-#if defined(CONFIG_SH64_USER_MISALIGNED_FIXUP)
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "user_reports",
@@ -923,7 +899,6 @@ static ctl_table unaligned_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec},
-#endif
 	{}
 };
 
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index d7d4991f32af..f53c76acaede 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -1,5 +1,178 @@
-#ifdef CONFIG_SUPERH32
-# include "vmlinux_32.lds.S"
+/*
+ * ld script to make SuperH Linux kernel
+ * Written by Niibe Yutaka and Paul Mundt
+ */
+#ifdef CONFIG_SUPERH64
+#define LOAD_OFFSET	CONFIG_PAGE_OFFSET
+OUTPUT_ARCH(sh:sh5)
 #else
-# include "vmlinux_64.lds.S"
+#define LOAD_OFFSET	0
+OUTPUT_ARCH(sh)
 #endif
+
+#include <asm/thread_info.h>
+#include <asm/cache.h>
+#include <asm-generic/vmlinux.lds.h>
+
+ENTRY(_start)
+SECTIONS
+{
+#ifdef CONFIG_PMB_FIXED
+	. = CONFIG_PAGE_OFFSET + (CONFIG_MEMORY_START & 0x1fffffff) +
+	    CONFIG_ZERO_PAGE_OFFSET;
+#elif defined(CONFIG_32BIT)
+	. = CONFIG_PAGE_OFFSET + CONFIG_ZERO_PAGE_OFFSET;
+#else
+	. = CONFIG_PAGE_OFFSET + CONFIG_MEMORY_START + CONFIG_ZERO_PAGE_OFFSET;
+#endif
+
+	_text = .;		/* Text and read-only data */
+
+	.empty_zero_page : AT(ADDR(.empty_zero_page) - LOAD_OFFSET) {
+		*(.empty_zero_page)
+	} = 0
+
+	.text : AT(ADDR(.text) - LOAD_OFFSET) {
+		HEAD_TEXT
+		TEXT_TEXT
+
+#ifdef CONFIG_SUPERH64
+		*(.text64)
+		*(.text..SHmedia32)
+#endif
+
+		SCHED_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		IRQENTRY_TEXT
+		*(.fixup)
+		*(.gnu.warning)
+		_etext = .;		/* End of text section */
+	} = 0x0009
+
+	. = ALIGN(16);		/* Exception table */
+	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
+		__start___ex_table = .;
+		*(__ex_table)
+		__stop___ex_table = .;
+	}
+
+	NOTES
+	RO_DATA(PAGE_SIZE)
+
+	/*
+	 * Code which must be executed uncached and the associated data
+	 */
+	. = ALIGN(PAGE_SIZE);
+	.uncached : AT(ADDR(.uncached) - LOAD_OFFSET) {
+		__uncached_start = .;
+		*(.uncached.text)
+		*(.uncached.data)
+		__uncached_end = .;
+	}
+
+	. = ALIGN(THREAD_SIZE);
+	.data : AT(ADDR(.data) - LOAD_OFFSET) {		/* Data */
+		*(.data.init_task)
+
+		. = ALIGN(L1_CACHE_BYTES);
+		*(.data.cacheline_aligned)
+
+		. = ALIGN(L1_CACHE_BYTES);
+		*(.data.read_mostly)
+
+		. = ALIGN(PAGE_SIZE);
+		*(.data.page_aligned)
+
+		__nosave_begin = .;
+		*(.data.nosave)
+		. = ALIGN(PAGE_SIZE);
+		__nosave_end = .;
+
+		DATA_DATA
+		CONSTRUCTORS
+	}
+
+	_edata = .;			/* End of data section */
+
+	. = ALIGN(PAGE_SIZE);		/* Init code and data */
+	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+		__init_begin = .;
+		_sinittext = .;
+		INIT_TEXT
+		_einittext = .;
+	}
+
+	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) { INIT_DATA }
+
+	. = ALIGN(16);
+	.init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
+		__setup_start = .;
+		*(.init.setup)
+		__setup_end = .;
+	}
+
+	.initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
+		__initcall_start = .;
+		INITCALLS
+		__initcall_end = .;
+	}
+
+	.con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
+		__con_initcall_start = .;
+		*(.con_initcall.init)
+		__con_initcall_end = .;
+	}
+
+	SECURITY_INIT
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	. = ALIGN(PAGE_SIZE);
+	.init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
+		__initramfs_start = .;
+		*(.init.ramfs)
+		__initramfs_end = .;
+	}
+#endif
+
+	. = ALIGN(4);
+	.machvec.init : AT(ADDR(.machvec.init) - LOAD_OFFSET) {
+		__machvec_start = .;
+		*(.machvec.init)
+		__machvec_end = .;
+	}
+
+	PERCPU(PAGE_SIZE)
+
+	/*
+	 * .exit.text is discarded at runtime, not link time, to deal with
+	 * references from __bug_table
+	 */
+	.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) { EXIT_TEXT }
+	.exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) { EXIT_DATA }
+
+	. = ALIGN(PAGE_SIZE);
+	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
+		__init_end = .;
+		__bss_start = .;		/* BSS */
+		*(.bss.page_aligned)
+		*(.bss)
+		*(COMMON)
+		. = ALIGN(4);
+		_ebss = .;			/* uClinux MTD sucks */
+		_end = . ;
+	}
+
+	/*
+	 * When something in the kernel is NOT compiled as a module, the
+	 * module cleanup code and data are put into these segments. Both
+	 * can then be thrown away, as cleanup code is never called unless
+	 * it's a module.
+	 */
+	/DISCARD/ : {
+		*(.exitcall.exit)
+	}
+
+	STABS_DEBUG
+	DWARF_DEBUG
+}
diff --git a/arch/sh/kernel/vmlinux_32.lds.S b/arch/sh/kernel/vmlinux_32.lds.S
deleted file mode 100644
index dd9b2ee1312d..000000000000
--- a/arch/sh/kernel/vmlinux_32.lds.S
+++ /dev/null
@@ -1,154 +0,0 @@
-/*
- * ld script to make SuperH Linux kernel
- * Written by Niibe Yutaka
- */
-#include <asm/thread_info.h>
-#include <asm/cache.h>
-#include <asm-generic/vmlinux.lds.h>
-
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-OUTPUT_FORMAT("elf32-sh-linux", "elf32-sh-linux", "elf32-sh-linux")
-#else
-OUTPUT_FORMAT("elf32-shbig-linux", "elf32-shbig-linux", "elf32-shbig-linux")
-#endif
-OUTPUT_ARCH(sh)
-ENTRY(_start)
-SECTIONS
-{
-#ifdef CONFIG_PMB_FIXED
-	. = CONFIG_PAGE_OFFSET + (CONFIG_MEMORY_START & 0x1fffffff) +
-	    CONFIG_ZERO_PAGE_OFFSET;
-#elif defined(CONFIG_32BIT)
-	. = CONFIG_PAGE_OFFSET + CONFIG_ZERO_PAGE_OFFSET;
-#else
-	. = CONFIG_PAGE_OFFSET + CONFIG_MEMORY_START + CONFIG_ZERO_PAGE_OFFSET;
-#endif
-
-	_text = .;			/* Text and read-only data */
-
-	.empty_zero_page : {
-		*(.empty_zero_page)
-	} = 0
-
-	.text : {
-		HEAD_TEXT
-		TEXT_TEXT
-		SCHED_TEXT
-		LOCK_TEXT
-		KPROBES_TEXT
-		*(.fixup)
-		*(.gnu.warning)
-	} = 0x0009
-
-	. = ALIGN(16);		/* Exception table */
-	__start___ex_table = .;
-	__ex_table : { *(__ex_table) }
-	__stop___ex_table = .;
-
-	_etext = .;			/* End of text section */
-
-	NOTES
-	RO_DATA(PAGE_SIZE)
-
-	/*
-	 * Code which must be executed uncached and the associated data
-	 */
-	. = ALIGN(PAGE_SIZE);
-	__uncached_start = .;
-	.uncached.text : { *(.uncached.text) }
-	.uncached.data : { *(.uncached.data) }
-	__uncached_end = .;
-
-	. = ALIGN(THREAD_SIZE);
-	.data : {			/* Data */
-		*(.data.init_task)
-
-		. = ALIGN(L1_CACHE_BYTES);
-		*(.data.cacheline_aligned)
-
-		. = ALIGN(L1_CACHE_BYTES);
-		*(.data.read_mostly)
-
-		. = ALIGN(PAGE_SIZE);
-		*(.data.page_aligned)
-
-		__nosave_begin = .;
-		*(.data.nosave)
-		. = ALIGN(PAGE_SIZE);
-		__nosave_end = .;
-
-		DATA_DATA
-		CONSTRUCTORS
-	}
-
-	_edata = .;			/* End of data section */
-
-	. = ALIGN(PAGE_SIZE);		/* Init code and data */
-	__init_begin = .;
-	_sinittext = .;
-	.init.text : { INIT_TEXT }
-	_einittext = .;
-	.init.data : { INIT_DATA }
-
-	. = ALIGN(16);
-	__setup_start = .;
-	.init.setup : { *(.init.setup) }
-	__setup_end = .;
-
-	__initcall_start = .;
-	.initcall.init : {
-		INITCALLS
-	}
-	__initcall_end = .;
-	__con_initcall_start = .;
-	.con_initcall.init : { *(.con_initcall.init) }
-	__con_initcall_end = .;
-
-	SECURITY_INIT
-
-#ifdef CONFIG_BLK_DEV_INITRD
-	. = ALIGN(PAGE_SIZE);
-	__initramfs_start = .;
-	.init.ramfs : { *(.init.ramfs) }
-	__initramfs_end = .;
-#endif
-
-	. = ALIGN(4);
-	__machvec_start = .;
-	.machvec.init : { *(.machvec.init) }
-	__machvec_end = .;
-
-	PERCPU(PAGE_SIZE)
-
-	/*
-	 * .exit.text is discarded at runtime, not link time, to deal with
-	 * references from __bug_table
-	 */
-	.exit.text : { EXIT_TEXT }
-	.exit.data : { EXIT_DATA }
-
-	. = ALIGN(PAGE_SIZE);
-	.bss : {
-		__init_end = .;
-		__bss_start = .;		/* BSS */
-		*(.bss.page_aligned)
-		*(.bss)
-		*(COMMON)
-		. = ALIGN(4);
-		_ebss = .;			/* uClinux MTD sucks */
-		_end = . ;
-	}
-
-	/*
-	 * When something in the kernel is NOT compiled as a module, the
-	 * module cleanup code and data are put into these segments. Both
-	 * can then be thrown away, as cleanup code is never called unless
-	 * it's a module.
-	 */
-	/DISCARD/ : {
-		*(.exitcall.exit)
-	}
-
-	STABS_DEBUG
-	DWARF_DEBUG
-}
diff --git a/arch/sh/kernel/vmlinux_64.lds.S b/arch/sh/kernel/vmlinux_64.lds.S
deleted file mode 100644
index 69664460c688..000000000000
--- a/arch/sh/kernel/vmlinux_64.lds.S
+++ /dev/null
@@ -1,163 +0,0 @@
-/*
- * ld script to make SH64 Linux kernel
- *
- * Copyright (C) 2000, 2001  Paolo Alberelli
- *
- * benedict.gaster@superh.com:	 2nd May 2002
- *    Add definition of empty_zero_page to be the first page of kernel image.
- *
- * benedict.gaster@superh.com:	 3rd May 2002
- *    Added support for ramdisk, removing statically linked romfs at the
- *    same time.
- *
- * lethal@linux-sh.org:          9th May 2003
- *    Kill off GLOBAL_NAME() usage and other CDC-isms.
- *
- * lethal@linux-sh.org:         19th May 2003
- *    Remove support for ancient toolchains.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <asm/page.h>
-#include <asm/cache.h>
-#include <asm/thread_info.h>
-
-#define LOAD_OFFSET	CONFIG_PAGE_OFFSET
-#include <asm-generic/vmlinux.lds.h>
-
-OUTPUT_ARCH(sh:sh5)
-
-#define C_PHYS(x) AT (ADDR(x) - LOAD_OFFSET)
-
-ENTRY(__start)
-SECTIONS
-{
-	. = CONFIG_PAGE_OFFSET + CONFIG_MEMORY_START + PAGE_SIZE;
-	_text = .;			/* Text and read-only data */
-
-	.empty_zero_page : C_PHYS(.empty_zero_page) {
-		*(.empty_zero_page)
-	} = 0
-
-	.text : C_PHYS(.text) {
-		HEAD_TEXT
-		TEXT_TEXT
-		*(.text64)
-		*(.text..SHmedia32)
-		SCHED_TEXT
-		LOCK_TEXT
-		KPROBES_TEXT
-		*(.fixup)
-		*(.gnu.warning)
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-	} = 0x6ff0fff0
-#else
-	} = 0xf0fff06f
-#endif
-
-	/* We likely want __ex_table to be Cache Line aligned */
-	. = ALIGN(L1_CACHE_BYTES);		/* Exception table */
-	__start___ex_table = .;
-	__ex_table : C_PHYS(__ex_table) { *(__ex_table) }
-	__stop___ex_table = .;
-
-	_etext = .;			/* End of text section */
-
-	NOTES 
-	RO_DATA(PAGE_SIZE)
-
-	. = ALIGN(THREAD_SIZE);
-	.data : C_PHYS(.data) {			/* Data */
-		*(.data.init_task)
-
-		. = ALIGN(L1_CACHE_BYTES);
-		*(.data.cacheline_aligned)
-
-		. = ALIGN(L1_CACHE_BYTES);
-		*(.data.read_mostly)
-
-		. = ALIGN(PAGE_SIZE);
-		*(.data.page_aligned)
-
-		__nosave_begin = .;
-		*(.data.nosave)
-		. = ALIGN(PAGE_SIZE);
-		__nosave_end = .;
-
-		DATA_DATA
-		CONSTRUCTORS
-	}
-
-	_edata = .;			/* End of data section */
-
-	. = ALIGN(PAGE_SIZE);		/* Init code and data */
-	__init_begin = .;
-	_sinittext = .;
-	.init.text : C_PHYS(.init.text) { INIT_TEXT }
-	_einittext = .;
-	.init.data : C_PHYS(.init.data) { INIT_DATA }
-	. = ALIGN(L1_CACHE_BYTES);	/* Better if Cache Line aligned */
-	__setup_start = .;
-	.init.setup : C_PHYS(.init.setup) { *(.init.setup) }
-	__setup_end = .;
-	__initcall_start = .;
-	.initcall.init : C_PHYS(.initcall.init) {
-		INITCALLS
-	}
-	__initcall_end = .;
-	__con_initcall_start = .;
-	.con_initcall.init : C_PHYS(.con_initcall.init) {
-		*(.con_initcall.init)
-	}
-	__con_initcall_end = .;
-
-	SECURITY_INIT
-
-#ifdef CONFIG_BLK_DEV_INITRD
-	. = ALIGN(PAGE_SIZE);
-	__initramfs_start = .;
-	.init.ramfs : C_PHYS(.init.ramfs) { *(.init.ramfs) }
-	__initramfs_end = .;
-#endif
-
-	. = ALIGN(8);
-	__machvec_start = .;
-	.machvec.init : C_PHYS(.machvec.init) { *(.machvec.init) }
-	__machvec_end = .;
-
-	PERCPU(PAGE_SIZE)
-
-	/*
-	 * .exit.text is discarded at runtime, not link time, to deal with
-	 * references from __bug_table
-	 */
-	.exit.text : C_PHYS(.exit.text) { EXIT_TEXT }
-	.exit.data : C_PHYS(.exit.data) { EXIT_DATA }
-
-	. = ALIGN(PAGE_SIZE);
-	.bss : C_PHYS(.bss) {
-		__init_end = .;
-		__bss_start = .;		/* BSS */
-		*(.bss.page_aligned)
-		*(.bss)
-		*(COMMON)
-		. = ALIGN(4);
-		_ebss = .;			/* uClinux MTD sucks */
-		_end = . ;
-	}
-
-	/*
-	 * When something in the kernel is NOT compiled as a module, the
-	 * module cleanup code and data are put into these segments. Both
-	 * can then be thrown away, as cleanup code is never called unless
-	 * it's a module.
-	 */
-	/DISCARD/ : {
-		*(.exitcall.exit)
-	}
-
-	STABS_DEBUG
-	DWARF_DEBUG
-}
diff --git a/arch/sh/lib64/.gitignore b/arch/sh/lib64/.gitignore
deleted file mode 100644
index 3508c2cb23c4..000000000000
--- a/arch/sh/lib64/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-syscalltab.h
diff --git a/arch/sh/lib64/dbg.c b/arch/sh/lib64/dbg.c
index 2fb8eaf6de60..6152a6a6d9c6 100644
--- a/arch/sh/lib64/dbg.c
+++ b/arch/sh/lib64/dbg.c
@@ -135,140 +135,6 @@ void print_itlb(void)
 	    (" =============================================================\n");
 }
 
-/* ======================================================================= */
-
-#ifdef CONFIG_POOR_MANS_STRACE
-
-#include "syscalltab.h"
-
-struct ring_node {
-	int evt;
-	int ret_addr;
-	int event;
-	int tra;
-	int pid;
-	unsigned long sp;
-	unsigned long pc;
-};
-
-static struct ring_node event_ring[16];
-static int event_ptr = 0;
-
-struct stored_syscall_data {
-	int pid;
-	int syscall_number;
-};
-
-#define N_STORED_SYSCALLS 16
-
-static struct stored_syscall_data stored_syscalls[N_STORED_SYSCALLS];
-static int syscall_next=0;
-static int syscall_next_print=0;
-
-void evt_debug(int evt, int ret_addr, int event, int tra, struct pt_regs *regs)
-{
-	int syscallno = tra & 0xff;
-	unsigned long sp;
-	unsigned long stack_bottom;
-	int pid;
-	struct ring_node *rr;
-
-	pid = current->pid;
-	stack_bottom = (unsigned long) task_stack_page(current);
-	asm volatile("ori r15, 0, %0" : "=r" (sp));
-	rr = event_ring + event_ptr;
-	rr->evt = evt;
-	rr->ret_addr = ret_addr;
-	rr->event = event;
-	rr->tra = tra;
-	rr->pid = pid;
-	rr->sp = sp;
-	rr->pc = regs->pc;
-
-	if (sp < stack_bottom + 3092) {
-		int i, j;
-		printk("evt_debug : stack underflow report\n");
-		for (j=0, i = event_ptr; j<16; j++) {
-			rr = event_ring + i;
-			printk("evt=%08x event=%08x tra=%08x pid=%5d sp=%08lx pc=%08lx\n",
-				rr->evt, rr->event, rr->tra, rr->pid, rr->sp, rr->pc);
-			i--;
-			i &= 15;
-		}
-		panic("STACK UNDERFLOW\n");
-	}
-
-	event_ptr = (event_ptr + 1) & 15;
-
-	if ((event == 2) && (evt == 0x160)) {
-		if (syscallno < NUM_SYSCALL_INFO_ENTRIES) {
-			/* Store the syscall information to print later.  We
-			 * can't print this now - currently we're running with
-			 * SR.BL=1, so we can't take a tlbmiss (which could occur
-			 * in the console drivers under printk).
-			 *
-			 * Just overwrite old entries on ring overflow - this
-			 * is only for last-hope debugging. */
-			stored_syscalls[syscall_next].pid = current->pid;
-			stored_syscalls[syscall_next].syscall_number = syscallno;
-			syscall_next++;
-			syscall_next &= (N_STORED_SYSCALLS - 1);
-		}
-	}
-}
-
-static void drain_syscalls(void) {
-	while (syscall_next_print != syscall_next) {
-		printk("Task %d: %s()\n",
-			stored_syscalls[syscall_next_print].pid,
-			syscall_info_table[stored_syscalls[syscall_next_print].syscall_number].name);
-			syscall_next_print++;
-			syscall_next_print &= (N_STORED_SYSCALLS - 1);
-	}
-}
-
-void evt_debug2(unsigned int ret)
-{
-	drain_syscalls();
-	printk("Task %d: syscall returns %08x\n", current->pid, ret);
-}
-
-void evt_debug_ret_from_irq(struct pt_regs *regs)
-{
-	int pid;
-	struct ring_node *rr;
-
-	pid = current->pid;
-	rr = event_ring + event_ptr;
-	rr->evt = 0xffff;
-	rr->ret_addr = 0;
-	rr->event = 0;
-	rr->tra = 0;
-	rr->pid = pid;
-	rr->pc = regs->pc;
-	event_ptr = (event_ptr + 1) & 15;
-}
-
-void evt_debug_ret_from_exc(struct pt_regs *regs)
-{
-	int pid;
-	struct ring_node *rr;
-
-	pid = current->pid;
-	rr = event_ring + event_ptr;
-	rr->evt = 0xfffe;
-	rr->ret_addr = 0;
-	rr->event = 0;
-	rr->tra = 0;
-	rr->pid = pid;
-	rr->pc = regs->pc;
-	event_ptr = (event_ptr + 1) & 15;
-}
-
-#endif /* CONFIG_POOR_MANS_STRACE */
-
-/* ======================================================================= */
-
 void show_excp_regs(char *from, int trapnr, int signr, struct pt_regs *regs)
 {
 
@@ -380,51 +246,3 @@ void show_excp_regs(char *from, int trapnr, int signr, struct pt_regs *regs)
 	print_dtlb();
 	print_itlb();
 }
-
-/* ======================================================================= */
-
-/*
-** Depending on <base> scan the MMU, Data or Instruction side
-** looking for a valid mapping matching Eaddr & asid.
-** Return -1 if not found or the TLB id entry otherwise.
-** Note: it works only for 4k pages!
-*/
-static unsigned long
-lookup_mmu_side(unsigned long base, unsigned long Eaddr, unsigned long asid)
-{
-	regType_t pteH;
-	unsigned long epn;
-	int count;
-
-	epn = Eaddr & 0xfffff000;
-
-	for (count = 0; count < MAX_TLBs; count++, base += TLB_STEP) {
-		pteH = getConfigReg(base);
-		if (GET_VALID(pteH))
-			if ((unsigned long) GET_EPN(pteH) == epn)
-				if ((unsigned long) GET_ASID(pteH) == asid)
-					break;
-	}
-	return ((unsigned long) ((count < MAX_TLBs) ? base : -1));
-}
-
-unsigned long lookup_dtlb(unsigned long Eaddr)
-{
-	unsigned long asid = get_asid();
-	return (lookup_mmu_side((u64) DTLB_BASE, Eaddr, asid));
-}
-
-unsigned long lookup_itlb(unsigned long Eaddr)
-{
-	unsigned long asid = get_asid();
-	return (lookup_mmu_side((u64) ITLB_BASE, Eaddr, asid));
-}
-
-void print_page(struct page *page)
-{
-	printk("  page[%p] -> index 0x%lx,  count 0x%x,  flags 0x%lx\n",
-	       page, page->index, page_count(page), page->flags);
-	printk("       address_space = %p, pages =%ld\n", page->mapping,
-	       page->mapping->nrpages);
-
-}
diff --git a/arch/sh/lib64/panic.c b/arch/sh/lib64/panic.c
index da32ba7b5fcc..38c954e04f6a 100644
--- a/arch/sh/lib64/panic.c
+++ b/arch/sh/lib64/panic.c
@@ -6,53 +6,10 @@
  * for more details.
  */
 
-#include <linux/kernel.h>
-#include <asm/io.h>
-#include <cpu/registers.h>
-
-/* THIS IS A PHYSICAL ADDRESS */
-#define HDSP2534_ADDR (0x04002100)
-
-#ifdef CONFIG_SH_CAYMAN
-
-static void poor_mans_delay(void)
-{
-	int i;
-	for (i = 0; i < 2500000; i++) {
-	}		/* poor man's delay */
-}
-
-static void show_value(unsigned long x)
-{
-	int i;
-	unsigned nibble;
-	for (i = 0; i < 8; i++) {
-		nibble = ((x >> (i * 4)) & 0xf);
-
-		ctrl_outb(nibble + ((nibble > 9) ? 55 : 48),
-			  HDSP2534_ADDR + 0xe0 + ((7 - i) << 2));
-	}
-}
-
-#endif
-
 void
 panic_handler(unsigned long panicPC, unsigned long panicSSR,
 	      unsigned long panicEXPEVT)
 {
-#ifdef CONFIG_SH_CAYMAN
-	while (1) {
-		/* This piece of code displays the PC on the LED display */
-		show_value(panicPC);
-		poor_mans_delay();
-		show_value(panicSSR);
-		poor_mans_delay();
-		show_value(panicEXPEVT);
-		poor_mans_delay();
-	}
-#endif
-
 	/* Never return from the panic handler */
 	for (;;) ;
-
 }
diff --git a/arch/sh/lib64/sdivsi3.S b/arch/sh/lib64/sdivsi3.S
index 6a800c6a4904..1963bbd42288 100644
--- a/arch/sh/lib64/sdivsi3.S
+++ b/arch/sh/lib64/sdivsi3.S
@@ -1,4 +1,6 @@
 	.global	__sdivsi3
+	.global	__sdivsi3_1
+	.global	__sdivsi3_2
 	.section	.text..SHmedia32,"ax"
 	.align	2
 
@@ -6,13 +8,15 @@
 	/* clobbered: r1,r18,r19,r20,r21,r25,tr0 */
 	/* result in r0 */
 __sdivsi3:
+__sdivsi3_1:
 	ptb __div_table,tr0
+	gettr tr0,r20
 
+__sdivsi3_2:
 	nsb r5, r1
 	shlld r5, r1, r25    /* normalize; [-2 ..1, 1..2) in s2.62 */
 	shari r25, 58, r21   /* extract 5(6) bit index (s2.4 with hole -1..1) */
 	/* bubble */
-	gettr tr0,r20
 	ldx.ub r20, r21, r19 /* u0.8 */
 	shari r25, 32, r25   /* normalize to s2.30 */
 	shlli r21, 1, r21
diff --git a/arch/sh/lib64/udelay.c b/arch/sh/lib64/udelay.c
index d76bd801194f..f215b063da70 100644
--- a/arch/sh/lib64/udelay.c
+++ b/arch/sh/lib64/udelay.c
@@ -33,7 +33,7 @@ void __delay(unsigned long loops)
 			     :"0"(loops));
 }
 
-inline void __const_udelay(unsigned long xloops)
+void __const_udelay(unsigned long xloops)
 {
 	__delay(xloops * (HZ * cpu_data[raw_smp_processor_id()].loops_per_jiffy));
 }
diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
index d4079cab2d58..2795618e4f07 100644
--- a/arch/sh/mm/Kconfig
+++ b/arch/sh/mm/Kconfig
@@ -21,6 +21,29 @@ config PAGE_OFFSET
 	default "0x20000000" if MMU && SUPERH64
 	default "0x00000000"
 
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	range 9 64 if PAGE_SIZE_16KB
+	default "9" if PAGE_SIZE_16KB
+	range 7 64 if PAGE_SIZE_64KB
+	default "7" if PAGE_SIZE_64KB
+	range 11 64
+	default "14" if !MMU
+	default "11"
+	help
+	  The kernel memory allocator divides physically contiguous memory
+	  blocks into "zones", where each zone is a power of two number of
+	  pages.  This option selects the largest power of two that the kernel
+	  keeps in the memory allocator.  If you need to allocate very large
+	  blocks of physically contiguous memory, then you may need to
+	  increase this value.
+
+	  This config option is actually maximum order plus one. For example,
+	  a value of 11 means that the largest free memory block is 2^10 pages.
+
+	  The page size is not necessarily 4KB. Keep this in mind when
+	  choosing a value for this option.
+
 config MEMORY_START
 	hex "Physical memory start address"
 	default "0x08000000"
@@ -201,14 +224,6 @@ config PAGE_SIZE_64KB
 
 endchoice
 
-config ENTRY_OFFSET
-	hex
-	default "0x00001000" if PAGE_SIZE_4KB
-	default "0x00002000" if PAGE_SIZE_8KB
-	default "0x00004000" if PAGE_SIZE_16KB
-	default "0x00010000" if PAGE_SIZE_64KB
-	default "0x00000000"
-
 choice
 	prompt "HugeTLB page size"
 	depends on HUGETLB_PAGE && (CPU_SH4 || CPU_SH5) && MMU
diff --git a/arch/sh/mm/cache-sh5.c b/arch/sh/mm/cache-sh5.c
index 9e277ec7d536..86762092508c 100644
--- a/arch/sh/mm/cache-sh5.c
+++ b/arch/sh/mm/cache-sh5.c
@@ -60,7 +60,7 @@ static inline void sh64_teardown_dtlb_cache_slot(void)
 static inline void sh64_icache_inv_all(void)
 {
 	unsigned long long addr, flag, data;
-	unsigned int flags;
+	unsigned long flags;
 
 	addr = ICCR0;
 	flag = ICCR0_ICI;
@@ -172,7 +172,7 @@ static void sh64_icache_inv_user_page_range(struct mm_struct *mm,
 		unsigned long eaddr;
 		unsigned long after_last_page_start;
 		unsigned long mm_asid, current_asid;
-		unsigned long long flags = 0ULL;
+		unsigned long flags = 0;
 
 		mm_asid = cpu_asid(smp_processor_id(), mm);
 		current_asid = get_asid();
@@ -236,7 +236,7 @@ static void sh64_icache_inv_user_small_range(struct mm_struct *mm,
 	unsigned long long eaddr = start;
 	unsigned long long eaddr_end = start + len;
 	unsigned long current_asid, mm_asid;
-	unsigned long long flags;
+	unsigned long flags;
 	unsigned long long epage_start;
 
 	/*
@@ -342,7 +342,7 @@ static void inline sh64_dcache_purge_sets(int sets_to_purge_base, int n_sets)
 			 * alloco is a NOP if the cache is write-through.
 			 */
 			if (test_bit(SH_CACHE_MODE_WT, &(cpu_data->dcache.flags)))
-				ctrl_inb(eaddr);
+				__raw_readb((unsigned long)eaddr);
 		}
 	}
 
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 3edf297c829b..ee8e6bbe882c 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -184,7 +184,6 @@ void __init paging_init(void)
 }
 
 static struct kcore_list kcore_mem, kcore_vmalloc;
-int after_bootmem = 0;
 
 void __init mem_init(void)
 {
@@ -217,8 +216,6 @@ void __init mem_init(void)
 	memset(empty_zero_page, 0, PAGE_SIZE);
 	__flush_wback_region(empty_zero_page, PAGE_SIZE);
 
-	after_bootmem = 1;
-
 	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
 	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
 	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;
diff --git a/arch/sh/mm/ioremap_32.c b/arch/sh/mm/ioremap_32.c
index 60cc486d2c2c..da2f4186f2cd 100644
--- a/arch/sh/mm/ioremap_32.c
+++ b/arch/sh/mm/ioremap_32.c
@@ -46,17 +46,15 @@ void __iomem *__ioremap(unsigned long phys_addr, unsigned long size,
 		return NULL;
 
 	/*
-	 * If we're on an SH7751 or SH7780 PCI controller, PCI memory is
-	 * mapped at the end of the address space (typically 0xfd000000)
-	 * in a non-translatable area, so mapping through page tables for
-	 * this area is not only pointless, but also fundamentally
-	 * broken. Just return the physical address instead.
+	 * If we're in the fixed PCI memory range, mapping through page
+	 * tables is not only pointless, but also fundamentally broken.
+	 * Just return the physical address instead.
 	 *
 	 * For boards that map a small PCI memory aperture somewhere in
 	 * P1/P2 space, ioremap() will already do the right thing,
 	 * and we'll never get this far.
 	 */
-	if (is_pci_memaddr(phys_addr) && is_pci_memaddr(last_addr))
+	if (is_pci_memory_fixed_range(phys_addr, size))
 		return (void __iomem *)phys_addr;
 
 #if !defined(CONFIG_PMB_FIXED)
@@ -121,7 +119,9 @@ void __iounmap(void __iomem *addr)
 	unsigned long seg = PXSEG(vaddr);
 	struct vm_struct *p;
 
-	if (seg < P3SEG || vaddr >= P3_ADDR_MAX || is_pci_memaddr(vaddr))
+	if (seg < P3SEG || vaddr >= P3_ADDR_MAX)
+		return;
+	if (is_pci_memory_fixed_range(vaddr, 0))
 		return;
 
 #ifdef CONFIG_PMB
diff --git a/arch/sh/mm/ioremap_64.c b/arch/sh/mm/ioremap_64.c
index 31e1bb5effbe..828c8597219d 100644
--- a/arch/sh/mm/ioremap_64.c
+++ b/arch/sh/mm/ioremap_64.c
@@ -20,6 +20,7 @@
 #include <linux/io.h>
 #include <linux/bootmem.h>
 #include <linux/proc_fs.h>
+#include <linux/slab.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/addrspace.h>
@@ -27,88 +28,17 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu.h>
 
-static void shmedia_mapioaddr(unsigned long, unsigned long);
-static unsigned long shmedia_ioremap(struct resource *, u32, int);
-
-/*
- * Generic mapping function (not visible outside):
- */
-
-/*
- * Remap an arbitrary physical address space into the kernel virtual
- * address space. Needed when the kernel wants to access high addresses
- * directly.
- *
- * NOTE! We need to allow non-page-aligned mappings too: we will obviously
- * have to convert them into an offset in a page-aligned mapping, but the
- * caller shouldn't need to know that small detail.
- */
-void *__ioremap(unsigned long phys_addr, unsigned long size,
-		unsigned long flags)
-{
-	void * addr;
-	struct vm_struct * area;
-	unsigned long offset, last_addr;
-	pgprot_t pgprot;
-
-	/* Don't allow wraparound or zero size */
-	last_addr = phys_addr + size - 1;
-	if (!size || last_addr < phys_addr)
-		return NULL;
-
-	pgprot = __pgprot(_PAGE_PRESENT  | _PAGE_READ   |
-			  _PAGE_WRITE    | _PAGE_DIRTY  |
-			  _PAGE_ACCESSED | _PAGE_SHARED | flags);
-
-	/*
-	 * Mappings have to be page-aligned
-	 */
-	offset = phys_addr & ~PAGE_MASK;
-	phys_addr &= PAGE_MASK;
-	size = PAGE_ALIGN(last_addr + 1) - phys_addr;
-
-	/*
-	 * Ok, go for it..
-	 */
-	area = get_vm_area(size, VM_IOREMAP);
-	if (!area)
-		return NULL;
-	pr_debug("Get vm_area returns %p addr %p\n", area, area->addr);
-	area->phys_addr = phys_addr;
-	addr = area->addr;
-	if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size,
-			       phys_addr, pgprot)) {
-		vunmap(addr);
-		return NULL;
-	}
-	return (void *) (offset + (char *)addr);
-}
-EXPORT_SYMBOL(__ioremap);
-
-void __iounmap(void *addr)
-{
-	struct vm_struct *area;
-
-	vfree((void *) (PAGE_MASK & (unsigned long) addr));
-	area = remove_vm_area((void *) (PAGE_MASK & (unsigned long) addr));
-	if (!area) {
-		printk(KERN_ERR "iounmap: bad address %p\n", addr);
-		return;
-	}
-
-	kfree(area);
-}
-EXPORT_SYMBOL(__iounmap);
-
 static struct resource shmedia_iomap = {
 	.name	= "shmedia_iomap",
 	.start	= IOBASE_VADDR + PAGE_SIZE,
 	.end	= IOBASE_END - 1,
 };
 
-static void shmedia_mapioaddr(unsigned long pa, unsigned long va);
+static void shmedia_mapioaddr(unsigned long pa, unsigned long va,
+			      unsigned long flags);
 static void shmedia_unmapioaddr(unsigned long vaddr);
-static unsigned long shmedia_ioremap(struct resource *res, u32 pa, int sz);
+static void __iomem *shmedia_ioremap(struct resource *res, u32 pa,
+				     int sz, unsigned long flags);
 
 /*
  * We have the same problem as the SPARC, so lets have the same comment:
@@ -130,18 +60,18 @@ static struct xresource xresv[XNRES];
 
 static struct xresource *xres_alloc(void)
 {
-        struct xresource *xrp;
-        int n;
+	struct xresource *xrp;
+	int n;
 
-        xrp = xresv;
-        for (n = 0; n < XNRES; n++) {
-                if (xrp->xflag == 0) {
-                        xrp->xflag = 1;
-                        return xrp;
-                }
-                xrp++;
-        }
-        return NULL;
+	xrp = xresv;
+	for (n = 0; n < XNRES; n++) {
+		if (xrp->xflag == 0) {
+			xrp->xflag = 1;
+			return xrp;
+		}
+		xrp++;
+	}
+	return NULL;
 }
 
 static void xres_free(struct xresource *xrp)
@@ -161,76 +91,71 @@ static struct resource *shmedia_find_resource(struct resource *root,
 	return NULL;
 }
 
-static unsigned long shmedia_alloc_io(unsigned long phys, unsigned long size,
-				      const char *name)
+static void __iomem *shmedia_alloc_io(unsigned long phys, unsigned long size,
+				      const char *name, unsigned long flags)
 {
-        static int printed_full = 0;
-        struct xresource *xres;
-        struct resource *res;
-        char *tack;
-        int tlen;
+	static int printed_full;
+	struct xresource *xres;
+	struct resource *res;
+	char *tack;
+	int tlen;
 
-        if (name == NULL) name = "???";
+	if (name == NULL)
+		name = "???";
 
-        if ((xres = xres_alloc()) != 0) {
-                tack = xres->xname;
-                res = &xres->xres;
-        } else {
-                if (!printed_full) {
-                        printk("%s: done with statics, switching to kmalloc\n",
-			       __func__);
-                        printed_full = 1;
-                }
-                tlen = strlen(name);
-                tack = kmalloc(sizeof (struct resource) + tlen + 1, GFP_KERNEL);
-                if (!tack)
-			return -ENOMEM;
-                memset(tack, 0, sizeof(struct resource));
-                res = (struct resource *) tack;
-                tack += sizeof (struct resource);
-        }
+	xres = xres_alloc();
+	if (xres != 0) {
+		tack = xres->xname;
+		res = &xres->xres;
+	} else {
+		if (!printed_full) {
+			printk(KERN_NOTICE "%s: done with statics, "
+			       "switching to kmalloc\n", __func__);
+			printed_full = 1;
+		}
+		tlen = strlen(name);
+		tack = kmalloc(sizeof(struct resource) + tlen + 1, GFP_KERNEL);
+		if (!tack)
+			return NULL;
+		memset(tack, 0, sizeof(struct resource));
+		res = (struct resource *) tack;
+		tack += sizeof(struct resource);
+	}
 
-        strncpy(tack, name, XNMLN);
-        tack[XNMLN] = 0;
-        res->name = tack;
+	strncpy(tack, name, XNMLN);
+	tack[XNMLN] = 0;
+	res->name = tack;
 
-        return shmedia_ioremap(res, phys, size);
+	return shmedia_ioremap(res, phys, size, flags);
 }
 
-static unsigned long shmedia_ioremap(struct resource *res, u32 pa, int sz)
+static void __iomem *shmedia_ioremap(struct resource *res, u32 pa, int sz,
+				     unsigned long flags)
 {
-        unsigned long offset = ((unsigned long) pa) & (~PAGE_MASK);
+	unsigned long offset = ((unsigned long) pa) & (~PAGE_MASK);
 	unsigned long round_sz = (offset + sz + PAGE_SIZE-1) & PAGE_MASK;
-        unsigned long va;
-        unsigned int psz;
+	unsigned long va;
+	unsigned int psz;
 
-        if (allocate_resource(&shmedia_iomap, res, round_sz,
+	if (allocate_resource(&shmedia_iomap, res, round_sz,
 			      shmedia_iomap.start, shmedia_iomap.end,
 			      PAGE_SIZE, NULL, NULL) != 0) {
-                panic("alloc_io_res(%s): cannot occupy\n",
-                    (res->name != NULL)? res->name: "???");
-        }
+		panic("alloc_io_res(%s): cannot occupy\n",
+		      (res->name != NULL) ? res->name : "???");
+	}
 
-        va = res->start;
-        pa &= PAGE_MASK;
+	va = res->start;
+	pa &= PAGE_MASK;
 
 	psz = (res->end - res->start + (PAGE_SIZE - 1)) / PAGE_SIZE;
 
-	/* log at boot time ... */
-	printk("mapioaddr: %6s  [%2d page%s]  va 0x%08lx   pa 0x%08x\n",
-	       ((res->name != NULL) ? res->name : "???"),
-	       psz, psz == 1 ? " " : "s", va, pa);
+	for (psz = res->end - res->start + 1; psz != 0; psz -= PAGE_SIZE) {
+		shmedia_mapioaddr(pa, va, flags);
+		va += PAGE_SIZE;
+		pa += PAGE_SIZE;
+	}
 
-        for (psz = res->end - res->start + 1; psz != 0; psz -= PAGE_SIZE) {
-                shmedia_mapioaddr(pa, va);
-                va += PAGE_SIZE;
-                pa += PAGE_SIZE;
-        }
-
-        res->start += offset;
-        res->end = res->start + sz - 1;         /* not strictly necessary.. */
-
-        return res->start;
+	return (void __iomem *)(unsigned long)(res->start + offset);
 }
 
 static void shmedia_free_io(struct resource *res)
@@ -249,14 +174,12 @@ static void shmedia_free_io(struct resource *res)
 
 static __init_refok void *sh64_get_page(void)
 {
-	extern int after_bootmem;
 	void *page;
 
-	if (after_bootmem) {
-		page = (void *)get_zeroed_page(GFP_ATOMIC);
-	} else {
+	if (slab_is_available())
+		page = (void *)get_zeroed_page(GFP_KERNEL);
+	else
 		page = alloc_bootmem_pages(PAGE_SIZE);
-	}
 
 	if (!page || ((unsigned long)page & ~PAGE_MASK))
 		panic("sh64_get_page: Out of memory already?\n");
@@ -264,17 +187,20 @@ static __init_refok void *sh64_get_page(void)
 	return page;
 }
 
-static void shmedia_mapioaddr(unsigned long pa, unsigned long va)
+static void shmedia_mapioaddr(unsigned long pa, unsigned long va,
+			      unsigned long flags)
 {
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep, pte;
 	pgprot_t prot;
-	unsigned long flags = 1; /* 1 = CB0-1 device */
 
 	pr_debug("shmedia_mapiopage pa %08lx va %08lx\n",  pa, va);
 
+	if (!flags)
+		flags = 1; /* 1 = CB0-1 device */
+
 	pgdp = pgd_offset_k(va);
 	if (pgd_none(*pgdp) || !pgd_present(*pgdp)) {
 		pudp = (pud_t *)sh64_get_page();
@@ -288,7 +214,7 @@ static void shmedia_mapioaddr(unsigned long pa, unsigned long va)
 	}
 
 	pmdp = pmd_offset(pudp, va);
-	if (pmd_none(*pmdp) || !pmd_present(*pmdp) ) {
+	if (pmd_none(*pmdp) || !pmd_present(*pmdp)) {
 		ptep = (pte_t *)sh64_get_page();
 		set_pmd(pmdp, __pmd((unsigned long)ptep + _PAGE_TABLE));
 	}
@@ -336,17 +262,19 @@ static void shmedia_unmapioaddr(unsigned long vaddr)
 	pte_clear(&init_mm, vaddr, ptep);
 }
 
-unsigned long onchip_remap(unsigned long phys, unsigned long size, const char *name)
+void __iomem *__ioremap(unsigned long offset, unsigned long size,
+			unsigned long flags)
 {
-	if (size < PAGE_SIZE)
-		size = PAGE_SIZE;
+	char name[14];
 
-	return shmedia_alloc_io(phys, size, name);
+	sprintf(name, "phys_%08x", (u32)offset);
+	return shmedia_alloc_io(offset, size, name, flags);
 }
-EXPORT_SYMBOL(onchip_remap);
+EXPORT_SYMBOL(__ioremap);
 
-void onchip_unmap(unsigned long vaddr)
+void __iounmap(void __iomem *virtual)
 {
+	unsigned long vaddr = (unsigned long)virtual & PAGE_MASK;
 	struct resource *res;
 	unsigned int psz;
 
@@ -357,10 +285,7 @@ void onchip_unmap(unsigned long vaddr)
 		return;
 	}
 
-        psz = (res->end - res->start + (PAGE_SIZE - 1)) / PAGE_SIZE;
-
-        printk(KERN_DEBUG "unmapioaddr: %6s  [%2d page%s] freed\n",
-	       res->name, psz, psz == 1 ? " " : "s");
+	psz = (res->end - res->start + (PAGE_SIZE - 1)) / PAGE_SIZE;
 
 	shmedia_free_io(res);
 
@@ -371,9 +296,8 @@ void onchip_unmap(unsigned long vaddr)
 		kfree(res);
 	}
 }
-EXPORT_SYMBOL(onchip_unmap);
+EXPORT_SYMBOL(__iounmap);
 
-#ifdef CONFIG_PROC_FS
 static int
 ioremap_proc_info(char *buf, char **start, off_t fpos, int length, int *eof,
 		  void *data)
@@ -385,7 +309,10 @@ ioremap_proc_info(char *buf, char **start, off_t fpos, int length, int *eof,
 	for (r = ((struct resource *)data)->child; r != NULL; r = r->sibling) {
 		if (p + 32 >= e)        /* Better than nothing */
 			break;
-		if ((nm = r->name) == 0) nm = "???";
+		nm = r->name;
+		if (nm == NULL)
+			nm = "???";
+
 		p += sprintf(p, "%08lx-%08lx: %s\n",
 			     (unsigned long)r->start,
 			     (unsigned long)r->end, nm);
@@ -393,14 +320,11 @@ ioremap_proc_info(char *buf, char **start, off_t fpos, int length, int *eof,
 
 	return p-buf;
 }
-#endif /* CONFIG_PROC_FS */
 
 static int __init register_proc_onchip(void)
 {
-#ifdef CONFIG_PROC_FS
-	create_proc_read_entry("io_map",0,0, ioremap_proc_info, &shmedia_iomap);
-#endif
+	create_proc_read_entry("io_map", 0, 0, ioremap_proc_info,
+			       &shmedia_iomap);
 	return 0;
 }
-
-__initcall(register_proc_onchip);
+late_initcall(register_proc_onchip);
diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c
index 931f4d003fa0..1b5fdfb4e0c2 100644
--- a/arch/sh/mm/mmap.c
+++ b/arch/sh/mm/mmap.c
@@ -1,7 +1,7 @@
 /*
  * arch/sh/mm/mmap.c
  *
- * Copyright (C) 2008  Paul Mundt
+ * Copyright (C) 2008 - 2009  Paul Mundt
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
@@ -21,9 +21,26 @@ EXPORT_SYMBOL(shm_align_mask);
 /*
  * To avoid cache aliases, we map the shared page with same color.
  */
-#define COLOUR_ALIGN(addr, pgoff)				\
-	((((addr) + shm_align_mask) & ~shm_align_mask) +	\
-	 (((pgoff) << PAGE_SHIFT) & shm_align_mask))
+static inline unsigned long COLOUR_ALIGN(unsigned long addr,
+					 unsigned long pgoff)
+{
+	unsigned long base = (addr + shm_align_mask) & ~shm_align_mask;
+	unsigned long off = (pgoff << PAGE_SHIFT) & shm_align_mask;
+
+	return base + off;
+}
+
+static inline unsigned long COLOUR_ALIGN_DOWN(unsigned long addr,
+					      unsigned long pgoff)
+{
+	unsigned long base = addr & ~shm_align_mask;
+	unsigned long off = (pgoff << PAGE_SHIFT) & shm_align_mask;
+
+	if (base + off <= addr)
+		return base + off;
+
+	return base - off;
+}
 
 unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	unsigned long len, unsigned long pgoff, unsigned long flags)
@@ -103,6 +120,117 @@ full_search:
 			addr = COLOUR_ALIGN(addr, pgoff);
 	}
 }
+
+unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
+			  const unsigned long len, const unsigned long pgoff,
+			  const unsigned long flags)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm = current->mm;
+	unsigned long addr = addr0;
+	int do_colour_align;
+
+	if (flags & MAP_FIXED) {
+		/* We do not accept a shared mapping if it would violate
+		 * cache aliasing constraints.
+		 */
+		if ((flags & MAP_SHARED) &&
+		    ((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask))
+			return -EINVAL;
+		return addr;
+	}
+
+	if (unlikely(len > TASK_SIZE))
+		return -ENOMEM;
+
+	do_colour_align = 0;
+	if (filp || (flags & MAP_SHARED))
+		do_colour_align = 1;
+
+	/* requesting a specific address */
+	if (addr) {
+		if (do_colour_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vma || addr + len <= vma->vm_start))
+			return addr;
+	}
+
+	/* check if free_area_cache is useful for us */
+	if (len <= mm->cached_hole_size) {
+	        mm->cached_hole_size = 0;
+		mm->free_area_cache = mm->mmap_base;
+	}
+
+	/* either no address requested or can't fit in requested address hole */
+	addr = mm->free_area_cache;
+	if (do_colour_align) {
+		unsigned long base = COLOUR_ALIGN_DOWN(addr-len, pgoff);
+
+		addr = base + len;
+	}
+
+	/* make sure it can fit in the remaining address space */
+	if (likely(addr > len)) {
+		vma = find_vma(mm, addr-len);
+		if (!vma || addr <= vma->vm_start) {
+			/* remember the address as a hint for next time */
+			return (mm->free_area_cache = addr-len);
+		}
+	}
+
+	if (unlikely(mm->mmap_base < len))
+		goto bottomup;
+
+	addr = mm->mmap_base-len;
+	if (do_colour_align)
+		addr = COLOUR_ALIGN_DOWN(addr, pgoff);
+
+	do {
+		/*
+		 * Lookup failure means no vma is above this address,
+		 * else if new region fits below vma->vm_start,
+		 * return with success:
+		 */
+		vma = find_vma(mm, addr);
+		if (likely(!vma || addr+len <= vma->vm_start)) {
+			/* remember the address as a hint for next time */
+			return (mm->free_area_cache = addr);
+		}
+
+		/* remember the largest hole we saw so far */
+		if (addr + mm->cached_hole_size < vma->vm_start)
+		        mm->cached_hole_size = vma->vm_start - addr;
+
+		/* try just below the current vma->vm_start */
+		addr = vma->vm_start-len;
+		if (do_colour_align)
+			addr = COLOUR_ALIGN_DOWN(addr, pgoff);
+	} while (likely(len < vma->vm_start));
+
+bottomup:
+	/*
+	 * A failed mmap() very likely causes application failure,
+	 * so fall back to the bottom-up function here. This scenario
+	 * can happen with large stack limits and large mmap()
+	 * allocations.
+	 */
+	mm->cached_hole_size = ~0UL;
+	mm->free_area_cache = TASK_UNMAPPED_BASE;
+	addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
+	/*
+	 * Restore the topdown base:
+	 */
+	mm->free_area_cache = mm->mmap_base;
+	mm->cached_hole_size = ~0UL;
+
+	return addr;
+}
 #endif /* CONFIG_MMU */
 
 /*
diff --git a/arch/sh/oprofile/common.c b/arch/sh/oprofile/common.c
index 1b9d4304b3bf..44f4e31c6d63 100644
--- a/arch/sh/oprofile/common.c
+++ b/arch/sh/oprofile/common.c
@@ -109,6 +109,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	case CPU_SH7785:
 	case CPU_SH7786:
 	case CPU_SH7723:
+	case CPU_SH7724:
 	case CPU_SHX3:
 		lmodel = &op_model_sh4a_ops;
 		break;
diff --git a/arch/sh/tools/mach-types b/arch/sh/tools/mach-types
index 8477b5d884fd..fec3a53b8650 100644
--- a/arch/sh/tools/mach-types
+++ b/arch/sh/tools/mach-types
@@ -23,6 +23,7 @@ HD64461			HD64461
 7619SE			SH_7619_SOLUTION_ENGINE
 7721SE			SH_7721_SOLUTION_ENGINE
 7722SE			SH_7722_SOLUTION_ENGINE
+7724SE			SH_7724_SOLUTION_ENGINE
 7751SE			SH_7751_SOLUTION_ENGINE
 7780SE			SH_7780_SOLUTION_ENGINE
 7751SYSTEMH		SH_7751_SYSTEMH
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 639ac805448a..65865726b283 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -102,8 +102,8 @@ struct thread_info {
 #define TI_KERN_CNTD1	0x00000488
 #define TI_PCR		0x00000490
 #define TI_RESTART_BLOCK 0x00000498
-#define TI_KUNA_REGS	0x000004c0
-#define TI_KUNA_INSN	0x000004c8
+#define TI_KUNA_REGS	0x000004c8
+#define TI_KUNA_INSN	0x000004d0
 #define TI_FPREGS	0x00000500
 
 /* We embed this in the uppermost byte of thread_info->flags */
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 5deabe921a47..e5e78f9cfc95 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -318,10 +318,12 @@ static void sun4u_irq_enable(unsigned int virt_irq)
 	}
 }
 
-static void sun4u_set_affinity(unsigned int virt_irq,
+static int sun4u_set_affinity(unsigned int virt_irq,
 			       const struct cpumask *mask)
 {
 	sun4u_irq_enable(virt_irq);
+
+	return 0;
 }
 
 /* Don't do anything.  The desc->status check for IRQ_DISABLED in
@@ -377,7 +379,7 @@ static void sun4v_irq_enable(unsigned int virt_irq)
 		       ino, err);
 }
 
-static void sun4v_set_affinity(unsigned int virt_irq,
+static int sun4v_set_affinity(unsigned int virt_irq,
 			       const struct cpumask *mask)
 {
 	unsigned int ino = virt_irq_table[virt_irq].dev_ino;
@@ -388,6 +390,8 @@ static void sun4v_set_affinity(unsigned int virt_irq,
 	if (err != HV_EOK)
 		printk(KERN_ERR "sun4v_intr_settarget(%x,%lu): "
 		       "err(%d)\n", ino, cpuid, err);
+
+	return 0;
 }
 
 static void sun4v_irq_disable(unsigned int virt_irq)
@@ -445,7 +449,7 @@ static void sun4v_virq_enable(unsigned int virt_irq)
 		       dev_handle, dev_ino, err);
 }
 
-static void sun4v_virt_set_affinity(unsigned int virt_irq,
+static int sun4v_virt_set_affinity(unsigned int virt_irq,
 				    const struct cpumask *mask)
 {
 	unsigned long cpuid, dev_handle, dev_ino;
@@ -461,6 +465,8 @@ static void sun4v_virt_set_affinity(unsigned int virt_irq,
 		printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
 		       "err(%d)\n",
 		       dev_handle, dev_ino, cpuid, err);
+
+	return 0;
 }
 
 static void sun4v_virq_disable(unsigned int virt_irq)
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index f934225fd8ef..aa9e926e13d7 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -451,23 +451,6 @@ static void do_ubd_request(struct request_queue * q);
 
 /* Only changed by ubd_init, which is an initcall. */
 static int thread_fd = -1;
-
-static void ubd_end_request(struct request *req, int bytes, int error)
-{
-	blk_end_request(req, error, bytes);
-}
-
-/* Callable only from interrupt context - otherwise you need to do
- * spin_lock_irq()/spin_lock_irqsave() */
-static inline void ubd_finish(struct request *req, int bytes)
-{
-	if(bytes < 0){
-		ubd_end_request(req, 0, -EIO);
-		return;
-	}
-	ubd_end_request(req, bytes, 0);
-}
-
 static LIST_HEAD(restart);
 
 /* XXX - move this inside ubd_intr. */
@@ -475,7 +458,6 @@ static LIST_HEAD(restart);
 static void ubd_handler(void)
 {
 	struct io_thread_req *req;
-	struct request *rq;
 	struct ubd *ubd;
 	struct list_head *list, *next_ele;
 	unsigned long flags;
@@ -492,10 +474,7 @@ static void ubd_handler(void)
 			return;
 		}
 
-		rq = req->req;
-		rq->nr_sectors -= req->length >> 9;
-		if(rq->nr_sectors == 0)
-			ubd_finish(rq, rq->hard_nr_sectors << 9);
+		blk_end_request(req->req, 0, req->length);
 		kfree(req);
 	}
 	reactivate_fd(thread_fd, UBD_IRQ);
@@ -1243,27 +1222,26 @@ static void do_ubd_request(struct request_queue *q)
 {
 	struct io_thread_req *io_req;
 	struct request *req;
-	int n, last_sectors;
+	sector_t sector;
+	int n;
 
 	while(1){
 		struct ubd *dev = q->queuedata;
 		if(dev->end_sg == 0){
-			struct request *req = elv_next_request(q);
+			struct request *req = blk_fetch_request(q);
 			if(req == NULL)
 				return;
 
 			dev->request = req;
-			blkdev_dequeue_request(req);
 			dev->start_sg = 0;
 			dev->end_sg = blk_rq_map_sg(q, req, dev->sg);
 		}
 
 		req = dev->request;
-		last_sectors = 0;
+		sector = blk_rq_pos(req);
 		while(dev->start_sg < dev->end_sg){
 			struct scatterlist *sg = &dev->sg[dev->start_sg];
 
-			req->sector += last_sectors;
 			io_req = kmalloc(sizeof(struct io_thread_req),
 					 GFP_ATOMIC);
 			if(io_req == NULL){
@@ -1272,10 +1250,10 @@ static void do_ubd_request(struct request_queue *q)
 				return;
 			}
 			prepare_request(req, io_req,
-					(unsigned long long) req->sector << 9,
+					(unsigned long long)sector << 9,
 					sg->offset, sg->length, sg_page(sg));
 
-			last_sectors = sg->length >> 9;
+			sector += sg->length >> 9;
 			n = os_write_file(thread_fd, &io_req,
 					  sizeof(struct io_thread_req *));
 			if(n != sizeof(struct io_thread_req *)){
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
new file mode 100644
index 000000000000..ad8ec356fb36
--- /dev/null
+++ b/arch/x86/Kbuild
@@ -0,0 +1,16 @@
+
+obj-$(CONFIG_KVM) += kvm/
+
+# Xen paravirtualization support
+obj-$(CONFIG_XEN) += xen/
+
+# lguest paravirtualization support
+obj-$(CONFIG_LGUEST_GUEST) += lguest/
+
+obj-y += kernel/
+obj-y += mm/
+
+obj-y += crypto/
+obj-y += vdso/
+obj-$(CONFIG_IA32_EMULATION) += ia32/
+
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a6efe0a2e9ae..68f5578fe38e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -47,6 +47,11 @@ config X86
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
 
+config OUTPUT_FORMAT
+	string
+	default "elf32-i386" if X86_32
+	default "elf64-x86-64" if X86_64
+
 config ARCH_DEFCONFIG
 	string
 	default "arch/x86/configs/i386_defconfig" if X86_32
@@ -274,15 +279,9 @@ config SPARSE_IRQ
 
 	  If you don't know what to do here, say N.
 
-config NUMA_MIGRATE_IRQ_DESC
-	bool "Move irq desc when changing irq smp_affinity"
+config NUMA_IRQ_DESC
+	def_bool y
 	depends on SPARSE_IRQ && NUMA
-	depends on BROKEN
-	default n
-	---help---
-	  This enables moving irq_desc to cpu/node that irq will use handled.
-
-	  If you don't know what to do here, say N.
 
 config X86_MPPARSE
 	bool "Enable MPS table" if ACPI
@@ -355,7 +354,7 @@ config X86_UV
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
-	select X86_X2APIC
+	depends on X86_X2APIC
 	---help---
 	  This option is needed in order to support SGI Ultraviolet systems.
 	  If you don't have one of these, you should say N here.
@@ -740,6 +739,7 @@ config X86_UP_IOAPIC
 config X86_LOCAL_APIC
 	def_bool y
 	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
+	select HAVE_PERF_COUNTERS if (!M386 && !M486)
 
 config X86_IO_APIC
 	def_bool y
@@ -1466,9 +1466,7 @@ config KEXEC_JUMP
 
 config PHYSICAL_START
 	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)
-	default "0x1000000" if X86_NUMAQ
-	default "0x200000" if X86_64
-	default "0x100000"
+	default "0x1000000"
 	---help---
 	  This gives the physical address where the kernel is loaded.
 
@@ -1487,15 +1485,15 @@ config PHYSICAL_START
 	  to be specifically compiled to run from a specific memory area
 	  (normally a reserved region) and this option comes handy.
 
-	  So if you are using bzImage for capturing the crash dump, leave
-	  the value here unchanged to 0x100000 and set CONFIG_RELOCATABLE=y.
-	  Otherwise if you plan to use vmlinux for capturing the crash dump
-	  change this value to start of the reserved region (Typically 16MB
-	  0x1000000). In other words, it can be set based on the "X" value as
-	  specified in the "crashkernel=YM@XM" command line boot parameter
-	  passed to the panic-ed kernel. Typically this parameter is set as
-	  crashkernel=64M@16M. Please take a look at
-	  Documentation/kdump/kdump.txt for more details about crash dumps.
+	  So if you are using bzImage for capturing the crash dump,
+	  leave the value here unchanged to 0x1000000 and set
+	  CONFIG_RELOCATABLE=y.  Otherwise if you plan to use vmlinux
+	  for capturing the crash dump change this value to start of
+	  the reserved region.  In other words, it can be set based on
+	  the "X" value as specified in the "crashkernel=YM@XM"
+	  command line boot parameter passed to the panic-ed
+	  kernel. Please take a look at Documentation/kdump/kdump.txt
+	  for more details about crash dumps.
 
 	  Usage of bzImage for capturing the crash dump is recommended as
 	  one does not have to build two kernels. Same kernel can be used
@@ -1508,8 +1506,8 @@ config PHYSICAL_START
 	  Don't change this unless you know what you are doing.
 
 config RELOCATABLE
-	bool "Build a relocatable kernel (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	bool "Build a relocatable kernel"
+	default y
 	---help---
 	  This builds a kernel image that retains relocation information
 	  so it can be loaded someplace besides the default 1MB.
@@ -1524,12 +1522,16 @@ config RELOCATABLE
 	  it has been loaded at and the compile time physical address
 	  (CONFIG_PHYSICAL_START) is ignored.
 
+# Relocation on x86-32 needs some additional build support
+config X86_NEED_RELOCS
+	def_bool y
+	depends on X86_32 && RELOCATABLE
+
 config PHYSICAL_ALIGN
 	hex
 	prompt "Alignment value to which kernel should be aligned" if X86_32
-	default "0x100000" if X86_32
-	default "0x200000" if X86_64
-	range 0x2000 0x400000
+	default "0x1000000"
+	range 0x2000 0x1000000
 	---help---
 	  This value puts the alignment restrictions on physical address
 	  where kernel is loaded and run from. Kernel is compiled for an
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index d8359e73317f..d105f29bb6bb 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -159,14 +159,30 @@ config IOMMU_DEBUG
 	  options. See Documentation/x86_64/boot-options.txt for more
 	  details.
 
+config IOMMU_STRESS
+	bool "Enable IOMMU stress-test mode"
+	---help---
+	  This option disables various optimizations in IOMMU related
+	  code to do real stress testing of the IOMMU code. This option
+	  will cause a performance drop and should only be enabled for
+	  testing.
+
 config IOMMU_LEAK
 	bool "IOMMU leak tracing"
-	depends on DEBUG_KERNEL
-	depends on IOMMU_DEBUG
+	depends on IOMMU_DEBUG && DMA_API_DEBUG
 	---help---
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
+config X86_DS_SELFTEST
+    bool "DS selftest"
+    default y
+    depends on DEBUG_KERNEL
+    depends on X86_DS
+	---help---
+	  Perform Debug Store selftests at boot time.
+	  If in doubt, say "N".
+
 config HAVE_MMIOTRACE_SUPPORT
 	def_bool y
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8c86b72afdc2..edbd0ca62067 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -7,8 +7,6 @@ else
         KBUILD_DEFCONFIG := $(ARCH)_defconfig
 endif
 
-core-$(CONFIG_KVM) += arch/x86/kvm/
-
 # BITS is used as extension for files which are available in a 32 bit
 # and a 64 bit version to simplify shared Makefiles.
 # e.g.: obj-y += foo_$(BITS).o
@@ -118,21 +116,8 @@ head-y += arch/x86/kernel/init_task.o
 
 libs-y  += arch/x86/lib/
 
-# Sub architecture files that needs linking first
-core-y += $(fcore-y)
-
-# Xen paravirtualization support
-core-$(CONFIG_XEN) += arch/x86/xen/
-
-# lguest paravirtualization support
-core-$(CONFIG_LGUEST_GUEST) += arch/x86/lguest/
-
-core-y += arch/x86/kernel/
-core-y += arch/x86/mm/
-
-core-y += arch/x86/crypto/
-core-y += arch/x86/vdso/
-core-$(CONFIG_IA32_EMULATION) += arch/x86/ia32/
+# See arch/x86/Kbuild for content of core part of the kernel
+core-y += arch/x86/
 
 # drivers-y are linked after core-y
 drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
diff --git a/arch/x86/boot/.gitignore b/arch/x86/boot/.gitignore
index 172cf8a98bdd..851fe936d242 100644
--- a/arch/x86/boot/.gitignore
+++ b/arch/x86/boot/.gitignore
@@ -3,6 +3,8 @@ bzImage
 cpustr.h
 mkcpustr
 offsets.h
+voffset.h
+zoffset.h
 setup
 setup.bin
 setup.elf
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 6633b6e7505a..8d16ada25048 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -26,9 +26,10 @@ targets		:= vmlinux.bin setup.bin setup.elf bzImage
 targets		+= fdimage fdimage144 fdimage288 image.iso mtools.conf
 subdir-		:= compressed
 
-setup-y		+= a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o
+setup-y		+= a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o edd.o
 setup-y		+= header.o main.o mca.o memory.o pm.o pmjump.o
-setup-y		+= printf.o string.o tty.o video.o video-mode.o version.o
+setup-y		+= printf.o regs.o string.o tty.o video.o video-mode.o
+setup-y		+= version.o
 setup-$(CONFIG_X86_APM_BOOT) += apm.o
 
 # The link order of the video-*.o modules can matter.  In particular,
@@ -86,19 +87,27 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-offsets := -e 's/^00*/0/' \
-        -e 's/^\([0-9a-fA-F]*\) . \(input_data\|input_data_end\)$$/\#define \2 0x\1/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) . \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
 
-quiet_cmd_offsets = OFFSETS $@
-      cmd_offsets = $(NM) $< | sed -n $(sed-offsets) > $@
+quiet_cmd_voffset = VOFFSET $@
+      cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
 
-$(obj)/offsets.h: $(obj)/compressed/vmlinux FORCE
-	$(call if_changed,offsets)
+targets += voffset.h
+$(obj)/voffset.h: vmlinux FORCE
+	$(call if_changed,voffset)
+
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+
+quiet_cmd_zoffset = ZOFFSET $@
+      cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
+
+targets += zoffset.h
+$(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE
+	$(call if_changed,zoffset)
 
-targets += offsets.h
 
 AFLAGS_header.o += -I$(obj)
-$(obj)/header.o: $(obj)/offsets.h
+$(obj)/header.o: $(obj)/voffset.h $(obj)/zoffset.h
 
 LDFLAGS_setup.elf	:= -T
 $(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE
diff --git a/arch/x86/boot/a20.c b/arch/x86/boot/a20.c
index 7c19ce8c2442..64a31a6d751a 100644
--- a/arch/x86/boot/a20.c
+++ b/arch/x86/boot/a20.c
@@ -2,7 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
- *   Copyright 2009 Intel Corporation
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -90,8 +90,11 @@ static int a20_test_long(void)
 
 static void enable_a20_bios(void)
 {
-	asm volatile("pushfl; int $0x15; popfl"
-		     : : "a" ((u16)0x2401));
+	struct biosregs ireg;
+
+	initregs(&ireg);
+	ireg.ax = 0x2401;
+	intcall(0x15, &ireg, NULL);
 }
 
 static void enable_a20_kbc(void)
diff --git a/arch/x86/boot/apm.c b/arch/x86/boot/apm.c
index 7aa6033001f9..ee274834ea8b 100644
--- a/arch/x86/boot/apm.c
+++ b/arch/x86/boot/apm.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   Original APM BIOS checking by Stephen Rothwell, May 1994
  *   (sfr@canb.auug.org.au)
@@ -19,75 +20,56 @@
 
 int query_apm_bios(void)
 {
-	u16 ax, bx, cx, dx, di;
-	u32 ebx, esi;
-	u8 err;
+	struct biosregs ireg, oreg;
 
 	/* APM BIOS installation check */
-	ax = 0x5300;
-	bx = cx = 0;
-	asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp ; setc %0"
-		     : "=d" (err), "+a" (ax), "+b" (bx), "+c" (cx)
-		     : : "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x53;
+	intcall(0x15, &ireg, &oreg);
 
-	if (err)
+	if (oreg.flags & X86_EFLAGS_CF)
 		return -1;		/* No APM BIOS */
 
-	if (bx != 0x504d)	/* "PM" signature */
+	if (oreg.bx != 0x504d)		/* "PM" signature */
 		return -1;
 
-	if (!(cx & 0x02))		/* 32 bits supported? */
+	if (!(oreg.cx & 0x02))		/* 32 bits supported? */
 		return -1;
 
 	/* Disconnect first, just in case */
-	ax = 0x5304;
-	bx = 0;
-	asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp"
-		     : "+a" (ax), "+b" (bx)
-		     : : "ecx", "edx", "esi", "edi");
-
-	/* Paranoia */
-	ebx = esi = 0;
-	cx = dx = di = 0;
+	ireg.al = 0x04;
+	intcall(0x15, &ireg, NULL);
 
 	/* 32-bit connect */
-	asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp ; setc %6"
-		     : "=a" (ax), "+b" (ebx), "+c" (cx), "+d" (dx),
-		       "+S" (esi), "+D" (di), "=m" (err)
-		     : "a" (0x5303));
+	ireg.al = 0x03;
+	intcall(0x15, &ireg, &oreg);
 
-	boot_params.apm_bios_info.cseg = ax;
-	boot_params.apm_bios_info.offset = ebx;
-	boot_params.apm_bios_info.cseg_16 = cx;
-	boot_params.apm_bios_info.dseg = dx;
-	boot_params.apm_bios_info.cseg_len = (u16)esi;
-	boot_params.apm_bios_info.cseg_16_len = esi >> 16;
-	boot_params.apm_bios_info.dseg_len = di;
+	boot_params.apm_bios_info.cseg        = oreg.ax;
+	boot_params.apm_bios_info.offset      = oreg.ebx;
+	boot_params.apm_bios_info.cseg_16     = oreg.cx;
+	boot_params.apm_bios_info.dseg        = oreg.dx;
+	boot_params.apm_bios_info.cseg_len    = oreg.si;
+	boot_params.apm_bios_info.cseg_16_len = oreg.hsi;
+	boot_params.apm_bios_info.dseg_len    = oreg.di;
 
-	if (err)
+	if (oreg.flags & X86_EFLAGS_CF)
 		return -1;
 
 	/* Redo the installation check as the 32-bit connect;
 	   some BIOSes return different flags this way... */
 
-	ax = 0x5300;
-	bx = cx = 0;
-	asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp ; setc %0"
-		     : "=d" (err), "+a" (ax), "+b" (bx), "+c" (cx)
-		     : : "esi", "edi");
+	ireg.al = 0x00;
+	intcall(0x15, &ireg, &oreg);
 
-	if (err || bx != 0x504d) {
+	if ((oreg.eflags & X86_EFLAGS_CF) || oreg.bx != 0x504d) {
 		/* Failure with 32-bit connect, try to disconect and ignore */
-		ax = 0x5304;
-		bx = 0;
-		asm volatile("pushl %%ebp ; int $0x15 ; popl %%ebp"
-			     : "+a" (ax), "+b" (bx)
-			     : : "ecx", "edx", "esi", "edi");
+		ireg.al = 0x04;
+		intcall(0x15, &ireg, NULL);
 		return -1;
 	}
 
-	boot_params.apm_bios_info.version = ax;
-	boot_params.apm_bios_info.flags = cx;
+	boot_params.apm_bios_info.version = oreg.ax;
+	boot_params.apm_bios_info.flags   = oreg.cx;
 	return 0;
 }
 
diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
new file mode 100644
index 000000000000..507793739ea5
--- /dev/null
+++ b/arch/x86/boot/bioscall.S
@@ -0,0 +1,82 @@
+/* -----------------------------------------------------------------------
+ *
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * "Glove box" for BIOS calls.  Avoids the constant problems with BIOSes
+ * touching registers they shouldn't be.
+ */
+
+	.code16
+	.text
+	.globl	intcall
+	.type	intcall, @function
+intcall:
+	/* Self-modify the INT instruction.  Ugly, but works. */
+	cmpb	%al, 3f
+	je	1f
+	movb	%al, 3f
+	jmp	1f		/* Synchronize pipeline */
+1:
+	/* Save state */
+	pushfl
+	pushw	%fs
+	pushw	%gs
+	pushal
+
+	/* Copy input state to stack frame */
+	subw	$44, %sp
+	movw	%dx, %si
+	movw	%sp, %di
+	movw	$11, %cx
+	rep; movsd
+
+	/* Pop full state from the stack */
+	popal
+	popw	%gs
+	popw	%fs
+	popw	%es
+	popw	%ds
+	popfl
+
+	/* Actual INT */
+	.byte	0xcd		/* INT opcode */
+3:	.byte	0
+
+	/* Push full state to the stack */
+	pushfl
+	pushw	%ds
+	pushw	%es
+	pushw	%fs
+	pushw	%gs
+	pushal
+
+	/* Re-establish C environment invariants */
+	cld
+	movzwl	%sp, %esp
+	movw	%cs, %ax
+	movw	%ax, %ds
+	movw	%ax, %es
+
+	/* Copy output state from stack frame */
+	movw	68(%esp), %di	/* Original %cx == 3rd argument */
+	andw	%di, %di
+	jz	4f
+	movw	%sp, %si
+	movw	$11, %cx
+	rep; movsd
+4:	addw	$44, %sp
+
+	/* Restore state and return */
+	popal
+	popw	%gs
+	popw	%fs
+	popfl
+	retl
+	.size	intcall, .-intcall
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 7b2692e897e5..98239d2658f2 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -26,6 +27,7 @@
 #include <asm/setup.h>
 #include "bitops.h"
 #include <asm/cpufeature.h>
+#include <asm/processor-flags.h>
 
 /* Useful macros */
 #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
@@ -241,6 +243,49 @@ int enable_a20(void);
 /* apm.c */
 int query_apm_bios(void);
 
+/* bioscall.c */
+struct biosregs {
+	union {
+		struct {
+			u32 edi;
+			u32 esi;
+			u32 ebp;
+			u32 _esp;
+			u32 ebx;
+			u32 edx;
+			u32 ecx;
+			u32 eax;
+			u32 _fsgs;
+			u32 _dses;
+			u32 eflags;
+		};
+		struct {
+			u16 di, hdi;
+			u16 si, hsi;
+			u16 bp, hbp;
+			u16 _sp, _hsp;
+			u16 bx, hbx;
+			u16 dx, hdx;
+			u16 cx, hcx;
+			u16 ax, hax;
+			u16 gs, fs;
+			u16 es, ds;
+			u16 flags, hflags;
+		};
+		struct {
+			u8 dil, dih, edi2, edi3;
+			u8 sil, sih, esi2, esi3;
+			u8 bpl, bph, ebp2, ebp3;
+			u8 _spl, _sph, _esp2, _esp3;
+			u8 bl, bh, ebx2, ebx3;
+			u8 dl, dh, edx2, edx3;
+			u8 cl, ch, ecx2, ecx3;
+			u8 al, ah, eax2, eax3;
+		};
+	};
+};
+void intcall(u8 int_no, const struct biosregs *ireg, struct biosregs *oreg);
+
 /* cmdline.c */
 int cmdline_find_option(const char *option, char *buffer, int bufsize);
 int cmdline_find_option_bool(const char *option);
@@ -279,6 +324,9 @@ int sprintf(char *buf, const char *fmt, ...);
 int vsprintf(char *buf, const char *fmt, va_list args);
 int printf(const char *fmt, ...);
 
+/* regs.c */
+void initregs(struct biosregs *regs);
+
 /* string.c */
 int strcmp(const char *str1, const char *str2);
 size_t strnlen(const char *s, size_t maxlen);
diff --git a/arch/x86/boot/compressed/.gitignore b/arch/x86/boot/compressed/.gitignore
index 63eff3b04d01..4a46fab7162e 100644
--- a/arch/x86/boot/compressed/.gitignore
+++ b/arch/x86/boot/compressed/.gitignore
@@ -1,3 +1,6 @@
 relocs
 vmlinux.bin.all
 vmlinux.relocs
+vmlinux.lds
+mkpiggy
+piggy.S
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 65551c9f8571..49c8a4c37d7c 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -19,7 +19,9 @@ KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 LDFLAGS := -m elf_$(UTS_MACHINE)
 LDFLAGS_vmlinux := -T
 
-$(obj)/vmlinux: $(src)/vmlinux_$(BITS).lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE
+hostprogs-y	:= mkpiggy
+
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE
 	$(call if_changed,ld)
 	@:
 
@@ -29,7 +31,7 @@ $(obj)/vmlinux.bin: vmlinux FORCE
 
 
 targets += vmlinux.bin.all vmlinux.relocs relocs
-hostprogs-$(CONFIG_X86_32) += relocs
+hostprogs-$(CONFIG_X86_NEED_RELOCS) += relocs
 
 quiet_cmd_relocs = RELOCS  $@
       cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
@@ -37,46 +39,22 @@ $(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE
 	$(call if_changed,relocs)
 
 vmlinux.bin.all-y := $(obj)/vmlinux.bin
-vmlinux.bin.all-$(CONFIG_RELOCATABLE) += $(obj)/vmlinux.relocs
-quiet_cmd_relocbin = BUILD   $@
-      cmd_relocbin = cat $(filter-out FORCE,$^) > $@
-$(obj)/vmlinux.bin.all: $(vmlinux.bin.all-y) FORCE
-	$(call if_changed,relocbin)
+vmlinux.bin.all-$(CONFIG_X86_NEED_RELOCS) += $(obj)/vmlinux.relocs
 
-ifeq ($(CONFIG_X86_32),y)
-
-ifdef CONFIG_RELOCATABLE
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
+$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin.all FORCE
+$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin.all FORCE
-	$(call if_changed,lzma)
-else
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,lzma)
-endif
-LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
-
-else
-
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzma)
 
-LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
-endif
+suffix-$(CONFIG_KERNEL_GZIP)	:= gz
+suffix-$(CONFIG_KERNEL_BZIP2)	:= bz2
+suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
 
-suffix_$(CONFIG_KERNEL_GZIP)  = gz
-suffix_$(CONFIG_KERNEL_BZIP2) = bz2
-suffix_$(CONFIG_KERNEL_LZMA)  = lzma
+quiet_cmd_mkpiggy = MKPIGGY $@
+      cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
 
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE
-	$(call if_changed,ld)
+targets += piggy.S
+$(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
+	$(call if_changed,mkpiggy)
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 3a8a866fb2e2..75e4f001e706 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -12,16 +12,16 @@
  * the page directory. [According to comments etc elsewhere on a compressed
  * kernel it will end up at 0x1000 + 1Mb I hope so as I assume this. - AC]
  *
- * Page 0 is deliberately kept safe, since System Management Mode code in 
+ * Page 0 is deliberately kept safe, since System Management Mode code in
  * laptops may need to access the BIOS data stored there.  This is also
- * useful for future device drivers that either access the BIOS via VM86 
+ * useful for future device drivers that either access the BIOS via VM86
  * mode.
  */
 
 /*
  * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
  */
-.text
+	.text
 
 #include <linux/linkage.h>
 #include <asm/segment.h>
@@ -29,161 +29,151 @@
 #include <asm/boot.h>
 #include <asm/asm-offsets.h>
 
-.section ".text.head","ax",@progbits
+	.section ".text.head","ax",@progbits
 ENTRY(startup_32)
 	cld
-	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
-	 * us to not reload segments */
-	testb $(1<<6), BP_loadflags(%esi)
-	jnz 1f
+	/*
+	 * Test KEEP_SEGMENTS flag to see if the bootloader is asking
+	 * us to not reload segments
+	 */
+	testb	$(1<<6), BP_loadflags(%esi)
+	jnz	1f
 
 	cli
-	movl $(__BOOT_DS),%eax
-	movl %eax,%ds
-	movl %eax,%es
-	movl %eax,%fs
-	movl %eax,%gs
-	movl %eax,%ss
+	movl	$__BOOT_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %fs
+	movl	%eax, %gs
+	movl	%eax, %ss
 1:
 
-/* Calculate the delta between where we were compiled to run
+/*
+ * Calculate the delta between where we were compiled to run
  * at and where we were actually loaded at.  This can only be done
  * with a short local call on x86.  Nothing  else will tell us what
  * address we are running at.  The reserved chunk of the real-mode
  * data at 0x1e4 (defined as a scratch field) are used as the stack
  * for this calculation. Only 4 bytes are needed.
  */
-	leal (0x1e4+4)(%esi), %esp
-	call 1f
-1:	popl %ebp
-	subl $1b, %ebp
+	leal	(BP_scratch+4)(%esi), %esp
+	call	1f
+1:	popl	%ebp
+	subl	$1b, %ebp
 
-/* %ebp contains the address we are loaded at by the boot loader and %ebx
+/*
+ * %ebp contains the address we are loaded at by the boot loader and %ebx
  * contains the address where we should move the kernel image temporarily
  * for safe in-place decompression.
  */
 
 #ifdef CONFIG_RELOCATABLE
-	movl 	%ebp, %ebx
-	addl    $(CONFIG_PHYSICAL_ALIGN - 1), %ebx
-	andl    $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebx
+	movl	%ebp, %ebx
+	movl	BP_kernel_alignment(%esi), %eax
+	decl	%eax
+	addl    %eax, %ebx
+	notl	%eax
+	andl    %eax, %ebx
 #else
-	movl $LOAD_PHYSICAL_ADDR, %ebx
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
 #endif
 
-	/* Replace the compressed data size with the uncompressed size */
-	subl input_len(%ebp), %ebx
-	movl output_len(%ebp), %eax
-	addl %eax, %ebx
-	/* Add 8 bytes for every 32K input block */
-	shrl $12, %eax
-	addl %eax, %ebx
-	/* Add 32K + 18 bytes of extra slack */
-	addl $(32768 + 18), %ebx
-	/* Align on a 4K boundary */
-	addl $4095, %ebx
-	andl $~4095, %ebx
+	/* Target address to relocate to for decompression */
+	addl	$z_extract_offset, %ebx
 
-/* Copy the compressed kernel to the end of our buffer
+	/* Set up the stack */
+	leal	boot_stack_end(%ebx), %esp
+
+	/* Zero EFLAGS */
+	pushl	$0
+	popfl
+
+/*
+ * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
-	pushl %esi
-	leal _end(%ebp), %esi
-	leal _end(%ebx), %edi
-	movl $(_end - startup_32), %ecx
+	pushl	%esi
+	leal	(_bss-4)(%ebp), %esi
+	leal	(_bss-4)(%ebx), %edi
+	movl	$(_bss - startup_32), %ecx
+	shrl	$2, %ecx
 	std
-	rep
-	movsb
+	rep	movsl
 	cld
-	popl %esi
-
-/* Compute the kernel start address.
- */
-#ifdef CONFIG_RELOCATABLE
-	addl    $(CONFIG_PHYSICAL_ALIGN - 1), %ebp
-	andl    $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebp
-#else
-	movl	$LOAD_PHYSICAL_ADDR, %ebp
-#endif
+	popl	%esi
 
 /*
  * Jump to the relocated address.
  */
-	leal relocated(%ebx), %eax
-	jmp *%eax
+	leal	relocated(%ebx), %eax
+	jmp	*%eax
 ENDPROC(startup_32)
 
-.section ".text"
+	.text
 relocated:
 
 /*
- * Clear BSS
+ * Clear BSS (stack is currently empty)
  */
-	xorl %eax,%eax
-	leal _edata(%ebx),%edi
-	leal _end(%ebx), %ecx
-	subl %edi,%ecx
-	cld
-	rep
-	stosb
-
-/*
- * Setup the stack for the decompressor
- */
-	leal boot_stack_end(%ebx), %esp
+	xorl	%eax, %eax
+	leal	_bss(%ebx), %edi
+	leal	_ebss(%ebx), %ecx
+	subl	%edi, %ecx
+	shrl	$2, %ecx
+	rep	stosl
 
 /*
  * Do the decompression, and jump to the new kernel..
  */
-	movl output_len(%ebx), %eax
-	pushl %eax
-			# push arguments for decompress_kernel:
-	pushl %ebp	# output address
-	movl input_len(%ebx), %eax
-	pushl %eax	# input_len
-	leal input_data(%ebx), %eax
-	pushl %eax	# input_data
-	leal boot_heap(%ebx), %eax
-	pushl %eax	# heap area
-	pushl %esi	# real mode pointer
-	call decompress_kernel
-	addl $20, %esp
-	popl %ecx
+	leal	z_extract_offset_negative(%ebx), %ebp
+				/* push arguments for decompress_kernel: */
+	pushl	%ebp		/* output address */
+	pushl	$z_input_len	/* input_len */
+	leal	input_data(%ebx), %eax
+	pushl	%eax		/* input_data */
+	leal	boot_heap(%ebx), %eax
+	pushl	%eax		/* heap area */
+	pushl	%esi		/* real mode pointer */
+	call	decompress_kernel
+	addl	$20, %esp
 
 #if CONFIG_RELOCATABLE
-/* Find the address of the relocations.
+/*
+ * Find the address of the relocations.
  */
-	movl %ebp, %edi
-	addl %ecx, %edi
+	leal	z_output_len(%ebp), %edi
 
-/* Calculate the delta between where vmlinux was compiled to run
+/*
+ * Calculate the delta between where vmlinux was compiled to run
  * and where it was actually loaded.
  */
-	movl %ebp, %ebx
-	subl $LOAD_PHYSICAL_ADDR, %ebx
-	jz   2f		/* Nothing to be done if loaded at compiled addr. */
+	movl	%ebp, %ebx
+	subl	$LOAD_PHYSICAL_ADDR, %ebx
+	jz	2f	/* Nothing to be done if loaded at compiled addr. */
 /*
  * Process relocations.
  */
 
-1:	subl $4, %edi
-	movl 0(%edi), %ecx
-	testl %ecx, %ecx
-	jz 2f
-	addl %ebx, -__PAGE_OFFSET(%ebx, %ecx)
-	jmp 1b
+1:	subl	$4, %edi
+	movl	(%edi), %ecx
+	testl	%ecx, %ecx
+	jz	2f
+	addl	%ebx, -__PAGE_OFFSET(%ebx, %ecx)
+	jmp	1b
 2:
 #endif
 
 /*
  * Jump to the decompressed kernel.
  */
-	xorl %ebx,%ebx
-	jmp *%ebp
+	xorl	%ebx, %ebx
+	jmp	*%ebp
 
-.bss
-/* Stack and heap for uncompression */
-.balign 4
+/*
+ * Stack and heap for uncompression
+ */
+	.bss
+	.balign 4
 boot_heap:
 	.fill BOOT_HEAP_SIZE, 1, 0
 boot_stack:
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index ed4a82948002..f62c284db9eb 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -21,8 +21,8 @@
 /*
  * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
  */
-.code32
-.text
+	.code32
+	.text
 
 #include <linux/linkage.h>
 #include <asm/segment.h>
@@ -33,12 +33,14 @@
 #include <asm/processor-flags.h>
 #include <asm/asm-offsets.h>
 
-.section ".text.head"
+	.section ".text.head"
 	.code32
 ENTRY(startup_32)
 	cld
-	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
-	 * us to not reload segments */
+	/*
+	 * Test KEEP_SEGMENTS flag to see if the bootloader is asking
+	 * us to not reload segments
+	 */
 	testb $(1<<6), BP_loadflags(%esi)
 	jnz 1f
 
@@ -49,14 +51,15 @@ ENTRY(startup_32)
 	movl	%eax, %ss
 1:
 
-/* Calculate the delta between where we were compiled to run
+/*
+ * Calculate the delta between where we were compiled to run
  * at and where we were actually loaded at.  This can only be done
  * with a short local call on x86.  Nothing  else will tell us what
  * address we are running at.  The reserved chunk of the real-mode
  * data at 0x1e4 (defined as a scratch field) are used as the stack
  * for this calculation. Only 4 bytes are needed.
  */
-	leal	(0x1e4+4)(%esi), %esp
+	leal	(BP_scratch+4)(%esi), %esp
 	call	1f
 1:	popl	%ebp
 	subl	$1b, %ebp
@@ -70,32 +73,28 @@ ENTRY(startup_32)
 	testl	%eax, %eax
 	jnz	no_longmode
 
-/* Compute the delta between where we were compiled to run at
+/*
+ * Compute the delta between where we were compiled to run at
  * and where the code will actually run at.
- */
-/* %ebp contains the address we are loaded at by the boot loader and %ebx
+ *
+ * %ebp contains the address we are loaded at by the boot loader and %ebx
  * contains the address where we should move the kernel image temporarily
  * for safe in-place decompression.
  */
 
 #ifdef CONFIG_RELOCATABLE
 	movl	%ebp, %ebx
-	addl	$(PMD_PAGE_SIZE -1), %ebx
-	andl	$PMD_PAGE_MASK, %ebx
+	movl	BP_kernel_alignment(%esi), %eax
+	decl	%eax
+	addl	%eax, %ebx
+	notl	%eax
+	andl	%eax, %ebx
 #else
-	movl	$CONFIG_PHYSICAL_START, %ebx
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
 #endif
 
-	/* Replace the compressed data size with the uncompressed size */
-	subl	input_len(%ebp), %ebx
-	movl	output_len(%ebp), %eax
-	addl	%eax, %ebx
-	/* Add 8 bytes for every 32K input block */
-	shrl	$12, %eax
-	addl	%eax, %ebx
-	/* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
-	addl	$(32768 + 18 + 4095), %ebx
-	andl	$~4095, %ebx
+	/* Target address to relocate to for decompression */
+	addl	$z_extract_offset, %ebx
 
 /*
  * Prepare for entering 64 bit mode
@@ -114,7 +113,7 @@ ENTRY(startup_32)
  /*
   * Build early 4G boot pagetable
   */
-	/* Initialize Page tables to 0*/
+	/* Initialize Page tables to 0 */
 	leal	pgtable(%ebx), %edi
 	xorl	%eax, %eax
 	movl	$((4096*6)/4), %ecx
@@ -155,7 +154,8 @@ ENTRY(startup_32)
 	btsl	$_EFER_LME, %eax
 	wrmsr
 
-	/* Setup for the jump to 64bit mode
+	/*
+	 * Setup for the jump to 64bit mode
 	 *
 	 * When the jump is performend we will be in long mode but
 	 * in 32bit compatibility mode with EFER.LME = 1, CS.L = 0, CS.D = 1
@@ -184,7 +184,8 @@ no_longmode:
 
 #include "../../kernel/verify_cpu_64.S"
 
-	/* Be careful here startup_64 needs to be at a predictable
+	/*
+	 * Be careful here startup_64 needs to be at a predictable
 	 * address so I can export it in an ELF header.  Bootloaders
 	 * should look at the ELF header to find this address, as
 	 * it may change in the future.
@@ -192,7 +193,8 @@ no_longmode:
 	.code64
 	.org 0x200
 ENTRY(startup_64)
-	/* We come here either from startup_32 or directly from a
+	/*
+	 * We come here either from startup_32 or directly from a
 	 * 64bit bootloader.  If we come here from a bootloader we depend on
 	 * an identity mapped page table being provied that maps our
 	 * entire text+data+bss and hopefully all of memory.
@@ -209,50 +211,54 @@ ENTRY(startup_64)
 	movl    $0x20, %eax
 	ltr	%ax
 
-	/* Compute the decompressed kernel start address.  It is where
+	/*
+	 * Compute the decompressed kernel start address.  It is where
 	 * we were loaded at aligned to a 2M boundary. %rbp contains the
 	 * decompressed kernel start address.
 	 *
 	 * If it is a relocatable kernel then decompress and run the kernel
 	 * from load address aligned to 2MB addr, otherwise decompress and
-	 * run the kernel from CONFIG_PHYSICAL_START
+	 * run the kernel from LOAD_PHYSICAL_ADDR
+	 *
+	 * We cannot rely on the calculation done in 32-bit mode, since we
+	 * may have been invoked via the 64-bit entry point.
 	 */
 
 	/* Start with the delta to where the kernel will run at. */
 #ifdef CONFIG_RELOCATABLE
 	leaq	startup_32(%rip) /* - $startup_32 */, %rbp
-	addq	$(PMD_PAGE_SIZE - 1), %rbp
-	andq	$PMD_PAGE_MASK, %rbp
-	movq	%rbp, %rbx
+	movl	BP_kernel_alignment(%rsi), %eax
+	decl	%eax
+	addq	%rax, %rbp
+	notq	%rax
+	andq	%rax, %rbp
 #else
-	movq	$CONFIG_PHYSICAL_START, %rbp
-	movq	%rbp, %rbx
+	movq	$LOAD_PHYSICAL_ADDR, %rbp
 #endif
 
-	/* Replace the compressed data size with the uncompressed size */
-	movl	input_len(%rip), %eax
-	subq	%rax, %rbx
-	movl	output_len(%rip), %eax
-	addq	%rax, %rbx
-	/* Add 8 bytes for every 32K input block */
-	shrq	$12, %rax
-	addq	%rax, %rbx
-	/* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
-	addq	$(32768 + 18 + 4095), %rbx
-	andq	$~4095, %rbx
+	/* Target address to relocate to for decompression */
+	leaq	z_extract_offset(%rbp), %rbx
 
-/* Copy the compressed kernel to the end of our buffer
+	/* Set up the stack */
+	leaq	boot_stack_end(%rbx), %rsp
+
+	/* Zero EFLAGS */
+	pushq	$0
+	popfq
+
+/*
+ * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
-	leaq	_end_before_pgt(%rip), %r8
-	leaq	_end_before_pgt(%rbx), %r9
-	movq	$_end_before_pgt /* - $startup_32 */, %rcx
-1:	subq	$8, %r8
-	subq	$8, %r9
-	movq	0(%r8), %rax
-	movq	%rax, 0(%r9)
-	subq	$8, %rcx
-	jnz	1b
+	pushq	%rsi
+	leaq	(_bss-8)(%rip), %rsi
+	leaq	(_bss-8)(%rbx), %rdi
+	movq	$_bss /* - $startup_32 */, %rcx
+	shrq	$3, %rcx
+	std
+	rep	movsq
+	cld
+	popq	%rsi
 
 /*
  * Jump to the relocated address.
@@ -260,37 +266,28 @@ ENTRY(startup_64)
 	leaq	relocated(%rbx), %rax
 	jmp	*%rax
 
-.section ".text"
+	.text
 relocated:
 
 /*
- * Clear BSS
+ * Clear BSS (stack is currently empty)
  */
-	xorq	%rax, %rax
-	leaq    _edata(%rbx), %rdi
-	leaq    _end_before_pgt(%rbx), %rcx
+	xorl	%eax, %eax
+	leaq    _bss(%rip), %rdi
+	leaq    _ebss(%rip), %rcx
 	subq	%rdi, %rcx
-	cld
-	rep
-	stosb
-
-	/* Setup the stack */
-	leaq	boot_stack_end(%rip), %rsp
-
-	/* zero EFLAGS after setting rsp */
-	pushq	$0
-	popfq
+	shrq	$3, %rcx
+	rep	stosq
 
 /*
  * Do the decompression, and jump to the new kernel..
  */
-	pushq	%rsi			# Save the real mode argument
-	movq	%rsi, %rdi		# real mode address
-	leaq	boot_heap(%rip), %rsi	# malloc area for uncompression
-	leaq	input_data(%rip), %rdx  # input_data
-	movl	input_len(%rip), %eax
-	movq	%rax, %rcx		# input_len
-	movq	%rbp, %r8		# output
+	pushq	%rsi			/* Save the real mode argument */
+	movq	%rsi, %rdi		/* real mode address */
+	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
+	leaq	input_data(%rip), %rdx  /* input_data */
+	movl	$z_input_len, %ecx	/* input_len */
+	movq	%rbp, %r8		/* output target address */
 	call	decompress_kernel
 	popq	%rsi
 
@@ -311,11 +308,21 @@ gdt:
 	.quad   0x0000000000000000	/* TS continued */
 gdt_end:
 
-.bss
-/* Stack and heap for uncompression */
-.balign 4
+/*
+ * Stack and heap for uncompression
+ */
+	.bss
+	.balign 4
 boot_heap:
 	.fill BOOT_HEAP_SIZE, 1, 0
 boot_stack:
 	.fill BOOT_STACK_SIZE, 1, 0
 boot_stack_end:
+
+/*
+ * Space for page tables (not in .bss so not zeroed)
+ */
+	.section ".pgtable","a",@nobits
+	.balign 4096
+pgtable:
+	.fill 6*4096, 1, 0
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index e45be73684ff..842b2a36174a 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -325,20 +325,18 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
+	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
+		error("Destination address inappropriately aligned");
 #ifdef CONFIG_X86_64
-	if ((unsigned long)output & (__KERNEL_ALIGN - 1))
-		error("Destination address not 2M aligned");
-	if ((unsigned long)output >= 0xffffffffffUL)
+	if (heap > 0x3fffffffffffUL)
 		error("Destination address too large");
 #else
-	if ((u32)output & (CONFIG_PHYSICAL_ALIGN - 1))
-		error("Destination address not CONFIG_PHYSICAL_ALIGN aligned");
 	if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff))
 		error("Destination address too large");
-#ifndef CONFIG_RELOCATABLE
-	if ((u32)output != LOAD_PHYSICAL_ADDR)
-		error("Wrong destination address");
 #endif
+#ifndef CONFIG_RELOCATABLE
+	if ((unsigned long)output != LOAD_PHYSICAL_ADDR)
+		error("Wrong destination address");
 #endif
 
 	if (!quiet)
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
new file mode 100644
index 000000000000..bcbd36c41432
--- /dev/null
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -0,0 +1,97 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *  Copyright (C) 2009 Intel Corporation. All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License version
+ *  2 as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ *  02110-1301, USA.
+ *
+ *  H. Peter Anvin <hpa@linux.intel.com>
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Compute the desired load offset from a compressed program; outputs
+ * a small assembly wrapper with the appropriate symbols defined.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+
+static uint32_t getle32(const void *p)
+{
+	const uint8_t *cp = p;
+
+	return (uint32_t)cp[0] + ((uint32_t)cp[1] << 8) +
+		((uint32_t)cp[2] << 16) + ((uint32_t)cp[3] << 24);
+}
+
+int main(int argc, char *argv[])
+{
+	uint32_t olen;
+	long ilen;
+	unsigned long offs;
+	FILE *f;
+
+	if (argc < 2) {
+		fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
+		return 1;
+	}
+
+	/* Get the information for the compressed kernel image first */
+
+	f = fopen(argv[1], "r");
+	if (!f) {
+		perror(argv[1]);
+		return 1;
+	}
+
+
+	if (fseek(f, -4L, SEEK_END)) {
+		perror(argv[1]);
+	}
+	fread(&olen, sizeof olen, 1, f);
+	ilen = ftell(f);
+	olen = getle32(&olen);
+	fclose(f);
+
+	/*
+	 * Now we have the input (compressed) and output (uncompressed)
+	 * sizes, compute the necessary decompression offset...
+	 */
+
+	offs = (olen > ilen) ? olen - ilen : 0;
+	offs += olen >> 12;	/* Add 8 bytes for each 32K block */
+	offs += 32*1024 + 18;	/* Add 32K + 18 bytes slack */
+	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
+
+	printf(".section \".rodata.compressed\",\"a\",@progbits\n");
+	printf(".globl z_input_len\n");
+	printf("z_input_len = %lu\n", ilen);
+	printf(".globl z_output_len\n");
+	printf("z_output_len = %lu\n", (unsigned long)olen);
+	printf(".globl z_extract_offset\n");
+	printf("z_extract_offset = 0x%lx\n", offs);
+	/* z_extract_offset_negative allows simplification of head_32.S */
+	printf(".globl z_extract_offset_negative\n");
+	printf("z_extract_offset_negative = -0x%lx\n", offs);
+
+	printf(".globl input_data, input_data_end\n");
+	printf("input_data:\n");
+	printf(".incbin \"%s\"\n", argv[1]);
+	printf("input_data_end:\n");
+
+	return 0;
+}
diff --git a/arch/x86/boot/compressed/vmlinux_64.lds b/arch/x86/boot/compressed/vmlinux.lds.S
similarity index 57%
rename from arch/x86/boot/compressed/vmlinux_64.lds
rename to arch/x86/boot/compressed/vmlinux.lds.S
index bef1ac891bce..cc353e1b3ffd 100644
--- a/arch/x86/boot/compressed/vmlinux_64.lds
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -1,6 +1,17 @@
-OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
+OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
+
+#undef i386
+
+#include <asm/page_types.h>
+
+#ifdef CONFIG_X86_64
 OUTPUT_ARCH(i386:x86-64)
 ENTRY(startup_64)
+#else
+OUTPUT_ARCH(i386)
+ENTRY(startup_32)
+#endif
+
 SECTIONS
 {
 	/* Be careful parts of head_64.S assume startup_32 is at
@@ -33,16 +44,22 @@ SECTIONS
 		*(.data.*)
 		_edata = . ;
 	}
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
 	.bss : {
 		_bss = . ;
 		*(.bss)
 		*(.bss.*)
 		*(COMMON)
-		. = ALIGN(8);
-		_end_before_pgt = . ;
-		. = ALIGN(4096);
-		pgtable = . ;
-		. = . + 4096 * 6;
+		. = ALIGN(8);	/* For convenience during zeroing */
 		_ebss = .;
 	}
+#ifdef CONFIG_X86_64
+       . = ALIGN(PAGE_SIZE);
+       .pgtable : {
+		_pgtable = . ;
+		*(.pgtable)
+		_epgtable = . ;
+	}
+#endif
+	_end = .;
 }
diff --git a/arch/x86/boot/compressed/vmlinux.scr b/arch/x86/boot/compressed/vmlinux.scr
deleted file mode 100644
index f02382ae5c48..000000000000
--- a/arch/x86/boot/compressed/vmlinux.scr
+++ /dev/null
@@ -1,10 +0,0 @@
-SECTIONS
-{
-  .rodata.compressed : {
-	input_len = .;
-	LONG(input_data_end - input_data) input_data = .;
-	*(.data)
-	output_len = . - 4;
-	input_data_end = .;
-	}
-}
diff --git a/arch/x86/boot/compressed/vmlinux_32.lds b/arch/x86/boot/compressed/vmlinux_32.lds
deleted file mode 100644
index bb3c48379c40..000000000000
--- a/arch/x86/boot/compressed/vmlinux_32.lds
+++ /dev/null
@@ -1,43 +0,0 @@
-OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
-OUTPUT_ARCH(i386)
-ENTRY(startup_32)
-SECTIONS
-{
-	/* Be careful parts of head_32.S assume startup_32 is at
-	 * address 0.
-	 */
-	. = 0;
-	.text.head : {
-		_head = . ;
-		*(.text.head)
-		_ehead = . ;
-	}
-	.rodata.compressed : {
-		*(.rodata.compressed)
-	}
-	.text :	{
-		_text = .; 	/* Text */
-		*(.text)
-		*(.text.*)
-		_etext = . ;
-	}
-	.rodata : {
-		_rodata = . ;
-		*(.rodata)	 /* read-only data */
-		*(.rodata.*)
-		_erodata = . ;
-	}
-	.data :	{
-		_data = . ;
-		*(.data)
-		*(.data.*)
-		_edata = . ;
-	}
-	.bss : {
-		_bss = . ;
-		*(.bss)
-		*(.bss.*)
-		*(COMMON)
-		_end = . ;
-	}
-}
diff --git a/arch/x86/boot/edd.c b/arch/x86/boot/edd.c
index 1aae8f3e5ca1..c501a5b466f8 100644
--- a/arch/x86/boot/edd.c
+++ b/arch/x86/boot/edd.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -22,17 +23,17 @@
  */
 static int read_mbr(u8 devno, void *buf)
 {
-	u16 ax, bx, cx, dx;
+	struct biosregs ireg, oreg;
 
-	ax = 0x0201;		/* Legacy Read, one sector */
-	cx = 0x0001;		/* Sector 0-0-1 */
-	dx = devno;
-	bx = (size_t)buf;
-	asm volatile("pushfl; stc; int $0x13; setc %%al; popfl"
-		     : "+a" (ax), "+c" (cx), "+d" (dx), "+b" (bx)
-		     : : "esi", "edi", "memory");
+	initregs(&ireg);
+	ireg.ax = 0x0201;		/* Legacy Read, one sector */
+	ireg.cx = 0x0001;		/* Sector 0-0-1 */
+	ireg.dl = devno;
+	ireg.bx = (size_t)buf;
 
-	return -(u8)ax;		/* 0 or -1 */
+	intcall(0x13, &ireg, &oreg);
+
+	return -(oreg.eflags & X86_EFLAGS_CF); /* 0 or -1 */
 }
 
 static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
@@ -72,56 +73,46 @@ static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
 
 static int get_edd_info(u8 devno, struct edd_info *ei)
 {
-	u16 ax, bx, cx, dx, di;
+	struct biosregs ireg, oreg;
 
 	memset(ei, 0, sizeof *ei);
 
 	/* Check Extensions Present */
 
-	ax = 0x4100;
-	bx = EDDMAGIC1;
-	dx = devno;
-	asm("pushfl; stc; int $0x13; setc %%al; popfl"
-	    : "+a" (ax), "+b" (bx), "=c" (cx), "+d" (dx)
-	    : : "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x41;
+	ireg.bx = EDDMAGIC1;
+	ireg.dl = devno;
+	intcall(0x13, &ireg, &oreg);
 
-	if ((u8)ax)
+	if (oreg.eflags & X86_EFLAGS_CF)
 		return -1;	/* No extended information */
 
-	if (bx != EDDMAGIC2)
+	if (oreg.bx != EDDMAGIC2)
 		return -1;
 
 	ei->device  = devno;
-	ei->version = ax >> 8;	/* EDD version number */
-	ei->interface_support = cx; /* EDD functionality subsets */
+	ei->version = oreg.ah;		 /* EDD version number */
+	ei->interface_support = oreg.cx; /* EDD functionality subsets */
 
 	/* Extended Get Device Parameters */
 
 	ei->params.length = sizeof(ei->params);
-	ax = 0x4800;
-	dx = devno;
-	asm("pushfl; int $0x13; popfl"
-	    : "+a" (ax), "+d" (dx), "=m" (ei->params)
-	    : "S" (&ei->params)
-	    : "ebx", "ecx", "edi");
+	ireg.ah = 0x48;
+	ireg.si = (size_t)&ei->params;
+	intcall(0x13, &ireg, &oreg);
 
 	/* Get legacy CHS parameters */
 
 	/* Ralf Brown recommends setting ES:DI to 0:0 */
-	ax = 0x0800;
-	dx = devno;
-	di = 0;
-	asm("pushw %%es; "
-	    "movw %%di,%%es; "
-	    "pushfl; stc; int $0x13; setc %%al; popfl; "
-	    "popw %%es"
-	    : "+a" (ax), "=b" (bx), "=c" (cx), "+d" (dx), "+D" (di)
-	    : : "esi");
+	ireg.ah = 0x08;
+	ireg.es = 0;
+	intcall(0x13, &ireg, &oreg);
 
-	if ((u8)ax == 0) {
-		ei->legacy_max_cylinder = (cx >> 8) + ((cx & 0xc0) << 2);
-		ei->legacy_max_head = dx >> 8;
-		ei->legacy_sectors_per_track = cx & 0x3f;
+	if (!(oreg.eflags & X86_EFLAGS_CF)) {
+		ei->legacy_max_cylinder = oreg.ch + ((oreg.cl & 0xc0) << 2);
+		ei->legacy_max_head = oreg.dh;
+		ei->legacy_sectors_per_track = oreg.cl & 0x3f;
 	}
 
 	return 0;
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 5d84d1c74e4c..b31cc54b4641 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -22,7 +22,8 @@
 #include <asm/page_types.h>
 #include <asm/setup.h>
 #include "boot.h"
-#include "offsets.h"
+#include "voffset.h"
+#include "zoffset.h"
 
 BOOTSEG		= 0x07C0		/* original address of boot-sector */
 SYSSEG		= 0x1000		/* historical load address >> 4 */
@@ -115,7 +116,7 @@ _start:
 	# Part 2 of the header, from the old setup.S
 
 		.ascii	"HdrS"		# header signature
-		.word	0x0209		# header version number (>= 0x0105)
+		.word	0x020a		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 		.globl realmode_swtch
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
@@ -168,7 +169,11 @@ heap_end_ptr:	.word	_end+STACK_SIZE-512
 					# end of setup code can be used by setup
 					# for local heap purposes.
 
-pad1:		.word	0
+ext_loader_ver:
+		.byte	0		# Extended boot loader version
+ext_loader_type:
+		.byte	0		# Extended boot loader type
+
 cmd_line_ptr:	.long	0		# (Header version 0x0202 or later)
 					# If nonzero, a 32-bit pointer
 					# to the kernel command line.
@@ -200,7 +205,7 @@ relocatable_kernel:    .byte 1
 #else
 relocatable_kernel:    .byte 0
 #endif
-pad2:			.byte 0
+min_alignment:		.byte MIN_KERNEL_ALIGN_LG2	# minimum alignment
 pad3:			.word 0
 
 cmdline_size:   .long   COMMAND_LINE_SIZE-1     #length of the command line,
@@ -212,16 +217,27 @@ hardware_subarch:	.long 0			# subarchitecture, added with 2.07
 
 hardware_subarch_data:	.quad 0
 
-payload_offset:		.long input_data
-payload_length:		.long input_data_end-input_data
+payload_offset:		.long ZO_input_data
+payload_length:		.long ZO_z_input_len
 
 setup_data:		.quad 0			# 64-bit physical pointer to
 						# single linked list of
 						# struct setup_data
 
+pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
+
+#define ZO_INIT_SIZE	(ZO__end - ZO_startup_32 + ZO_z_extract_offset)
+#define VO_INIT_SIZE	(VO__end - VO__text)
+#if ZO_INIT_SIZE > VO_INIT_SIZE
+#define INIT_SIZE ZO_INIT_SIZE
+#else
+#define INIT_SIZE VO_INIT_SIZE
+#endif
+init_size:		.long INIT_SIZE		# kernel initialization size
+
 # End of setup header #####################################################
 
-	.section ".inittext", "ax"
+	.section ".entrytext", "ax"
 start_of_setup:
 #ifdef SAFE_RESET_DISK_CONTROLLER
 # Reset the disk controller.
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index 58f0415d3ae0..140172b895bd 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -61,11 +62,10 @@ static void copy_boot_params(void)
  */
 static void keyboard_set_repeat(void)
 {
-	u16 ax = 0x0305;
-	u16 bx = 0;
-	asm volatile("int $0x16"
-		     : "+a" (ax), "+b" (bx)
-		     : : "ecx", "edx", "esi", "edi");
+	struct biosregs ireg;
+	initregs(&ireg);
+	ireg.ax = 0x0305;
+	intcall(0x16, &ireg, NULL);
 }
 
 /*
@@ -73,18 +73,22 @@ static void keyboard_set_repeat(void)
  */
 static void query_ist(void)
 {
+	struct biosregs ireg, oreg;
+
 	/* Some older BIOSes apparently crash on this call, so filter
 	   it from machines too old to have SpeedStep at all. */
 	if (cpu.level < 6)
 		return;
 
-	asm("int $0x15"
-	    : "=a" (boot_params.ist_info.signature),
-	      "=b" (boot_params.ist_info.command),
-	      "=c" (boot_params.ist_info.event),
-	      "=d" (boot_params.ist_info.perf_level)
-	    : "a" (0x0000e980),	 /* IST Support */
-	      "d" (0x47534943)); /* Request value */
+	initregs(&ireg);
+	ireg.ax  = 0xe980;	 /* IST Support */
+	ireg.edx = 0x47534943;	 /* Request value */
+	intcall(0x15, &ireg, &oreg);
+
+	boot_params.ist_info.signature  = oreg.eax;
+	boot_params.ist_info.command    = oreg.ebx;
+	boot_params.ist_info.event      = oreg.ecx;
+	boot_params.ist_info.perf_level = oreg.edx;
 }
 
 /*
@@ -93,13 +97,12 @@ static void query_ist(void)
 static void set_bios_mode(void)
 {
 #ifdef CONFIG_X86_64
-	u32 eax, ebx;
+	struct biosregs ireg;
 
-	eax = 0xec00;
-	ebx = 2;
-	asm volatile("int $0x15"
-		     : "+a" (eax), "+b" (ebx)
-		     : : "ecx", "edx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ax = 0xec00;
+	ireg.bx = 2;
+	intcall(0x15, &ireg, NULL);
 #endif
 }
 
diff --git a/arch/x86/boot/mca.c b/arch/x86/boot/mca.c
index 911eaae5d696..a95a531148ef 100644
--- a/arch/x86/boot/mca.c
+++ b/arch/x86/boot/mca.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -16,26 +17,22 @@
 
 int query_mca(void)
 {
-	u8 err;
-	u16 es, bx, len;
+	struct biosregs ireg, oreg;
+	u16 len;
 
-	asm("pushw %%es ; "
-	    "int $0x15 ; "
-	    "setc %0 ; "
-	    "movw %%es, %1 ; "
-	    "popw %%es"
-	    : "=acd" (err), "=acdSD" (es), "=b" (bx)
-	    : "a" (0xc000));
+	initregs(&ireg);
+	ireg.ah = 0xc0;
+	intcall(0x15, &ireg, &oreg);
 
-	if (err)
+	if (oreg.eflags & X86_EFLAGS_CF)
 		return -1;	/* No MCA present */
 
-	set_fs(es);
-	len = rdfs16(bx);
+	set_fs(oreg.es);
+	len = rdfs16(oreg.bx);
 
 	if (len > sizeof(boot_params.sys_desc_table))
 		len = sizeof(boot_params.sys_desc_table);
 
-	copy_from_fs(&boot_params.sys_desc_table, bx, len);
+	copy_from_fs(&boot_params.sys_desc_table, oreg.bx, len);
 	return 0;
 }
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index 74b3d2ba84e9..cae3feb1035e 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -20,12 +20,16 @@
 static int detect_memory_e820(void)
 {
 	int count = 0;
-	u32 next = 0;
-	u32 size, id, edi;
-	u8 err;
+	struct biosregs ireg, oreg;
 	struct e820entry *desc = boot_params.e820_map;
 	static struct e820entry buf; /* static so it is zeroed */
 
+	initregs(&ireg);
+	ireg.ax  = 0xe820;
+	ireg.cx  = sizeof buf;
+	ireg.edx = SMAP;
+	ireg.di  = (size_t)&buf;
+
 	/*
 	 * Note: at least one BIOS is known which assumes that the
 	 * buffer pointed to by one e820 call is the same one as
@@ -41,22 +45,13 @@ static int detect_memory_e820(void)
 	 */
 
 	do {
-		size = sizeof buf;
-
-		/* Important: %edx and %esi are clobbered by some BIOSes,
-		   so they must be either used for the error output
-		   or explicitly marked clobbered.  Given that, assume there
-		   is something out there clobbering %ebp and %edi, too. */
-		asm("pushl %%ebp; int $0x15; popl %%ebp; setc %0"
-		    : "=d" (err), "+b" (next), "=a" (id), "+c" (size),
-		      "=D" (edi), "+m" (buf)
-		    : "D" (&buf), "d" (SMAP), "a" (0xe820)
-		    : "esi");
+		intcall(0x15, &ireg, &oreg);
+		ireg.ebx = oreg.ebx; /* for next iteration... */
 
 		/* BIOSes which terminate the chain with CF = 1 as opposed
 		   to %ebx = 0 don't always report the SMAP signature on
 		   the final, failing, probe. */
-		if (err)
+		if (oreg.eflags & X86_EFLAGS_CF)
 			break;
 
 		/* Some BIOSes stop returning SMAP in the middle of
@@ -64,60 +59,64 @@ static int detect_memory_e820(void)
 		   screwed up the map at that point, we might have a
 		   partial map, the full map, or complete garbage, so
 		   just return failure. */
-		if (id != SMAP) {
+		if (oreg.eax != SMAP) {
 			count = 0;
 			break;
 		}
 
 		*desc++ = buf;
 		count++;
-	} while (next && count < ARRAY_SIZE(boot_params.e820_map));
+	} while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map));
 
 	return boot_params.e820_entries = count;
 }
 
 static int detect_memory_e801(void)
 {
-	u16 ax, bx, cx, dx;
-	u8 err;
+	struct biosregs ireg, oreg;
 
-	bx = cx = dx = 0;
-	ax = 0xe801;
-	asm("stc; int $0x15; setc %0"
-	    : "=m" (err), "+a" (ax), "+b" (bx), "+c" (cx), "+d" (dx));
+	initregs(&ireg);
+	ireg.ax = 0xe801;
+	intcall(0x15, &ireg, &oreg);
 
-	if (err)
+	if (oreg.eflags & X86_EFLAGS_CF)
 		return -1;
 
 	/* Do we really need to do this? */
-	if (cx || dx) {
-		ax = cx;
-		bx = dx;
+	if (oreg.cx || oreg.dx) {
+		oreg.ax = oreg.cx;
+		oreg.bx = oreg.dx;
 	}
 
-	if (ax > 15*1024)
+	if (oreg.ax > 15*1024) {
 		return -1;	/* Bogus! */
-
-	/* This ignores memory above 16MB if we have a memory hole
-	   there.  If someone actually finds a machine with a memory
-	   hole at 16MB and no support for 0E820h they should probably
-	   generate a fake e820 map. */
-	boot_params.alt_mem_k = (ax == 15*1024) ? (dx << 6)+ax : ax;
+	} else if (oreg.ax == 15*1024) {
+		boot_params.alt_mem_k = (oreg.dx << 6) + oreg.ax;
+	} else {
+		/*
+		 * This ignores memory above 16MB if we have a memory
+		 * hole there.  If someone actually finds a machine
+		 * with a memory hole at 16MB and no support for
+		 * 0E820h they should probably generate a fake e820
+		 * map.
+		 */
+		boot_params.alt_mem_k = oreg.ax;
+	}
 
 	return 0;
 }
 
 static int detect_memory_88(void)
 {
-	u16 ax;
-	u8 err;
+	struct biosregs ireg, oreg;
 
-	ax = 0x8800;
-	asm("stc; int $0x15; setc %0" : "=bcdm" (err), "+a" (ax));
+	initregs(&ireg);
+	ireg.ah = 0x88;
+	intcall(0x15, &ireg, &oreg);
 
-	boot_params.screen_info.ext_mem_k = ax;
+	boot_params.screen_info.ext_mem_k = oreg.ax;
 
-	return -err;
+	return -(oreg.eflags & X86_EFLAGS_CF); /* 0 or -1 */
 }
 
 int detect_memory(void)
diff --git a/arch/x86/boot/regs.c b/arch/x86/boot/regs.c
new file mode 100644
index 000000000000..958019b1cfa5
--- /dev/null
+++ b/arch/x86/boot/regs.c
@@ -0,0 +1,29 @@
+/* -----------------------------------------------------------------------
+ *
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Simple helper function for initializing a register set.
+ *
+ * Note that this sets EFLAGS_CF in the input register set; this
+ * makes it easier to catch functions which do nothing but don't
+ * explicitly set CF.
+ */
+
+#include "boot.h"
+
+void initregs(struct biosregs *reg)
+{
+	memset(reg, 0, sizeof *reg);
+	reg->eflags |= X86_EFLAGS_CF;
+	reg->ds = ds();
+	reg->es = ds();
+	reg->fs = fs();
+	reg->gs = gs();
+}
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index bb8dc2de7969..0f6ec455a2b1 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -15,8 +15,11 @@ SECTIONS
 
 	. = 497;
 	.header		: { *(.header) }
+	.entrytext	: { *(.entrytext) }
 	.inittext	: { *(.inittext) }
 	.initdata	: { *(.initdata) }
+	__end_init = .;
+
 	.text		: { *(.text) }
 	.text32		: { *(.text32) }
 
@@ -52,4 +55,7 @@ SECTIONS
 
 	. = ASSERT(_end <= 0x8000, "Setup too big!");
 	. = ASSERT(hdr == 0x1f1, "The setup header has the wrong offset!");
+	/* Necessary for the very-old-loader check to work... */
+	. = ASSERT(__end_init <= 5*512, "init sections too big!");
+
 }
diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c
index 7e8e8b25f5f6..01ec69c901c7 100644
--- a/arch/x86/boot/tty.c
+++ b/arch/x86/boot/tty.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -22,24 +23,23 @@
 
 void __attribute__((section(".inittext"))) putchar(int ch)
 {
-	unsigned char c = ch;
+	struct biosregs ireg;
 
-	if (c == '\n')
+	if (ch == '\n')
 		putchar('\r');	/* \n -> \r\n */
 
-	/* int $0x10 is known to have bugs involving touching registers
-	   it shouldn't.  Be extra conservative... */
-	asm volatile("pushal; pushw %%ds; int $0x10; popw %%ds; popal"
-		     : : "b" (0x0007), "c" (0x0001), "a" (0x0e00|ch));
+	initregs(&ireg);
+	ireg.bx = 0x0007;
+	ireg.cx = 0x0001;
+	ireg.ah = 0x0e;
+	ireg.al = ch;
+	intcall(0x10, &ireg, NULL);
 }
 
 void __attribute__((section(".inittext"))) puts(const char *str)
 {
-	int n = 0;
-	while (*str) {
+	while (*str)
 		putchar(*str++);
-		n++;
-	}
 }
 
 /*
@@ -49,14 +49,13 @@ void __attribute__((section(".inittext"))) puts(const char *str)
 
 static u8 gettime(void)
 {
-	u16 ax = 0x0200;
-	u16 cx, dx;
+	struct biosregs ireg, oreg;
 
-	asm volatile("int $0x1a"
-		     : "+a" (ax), "=c" (cx), "=d" (dx)
-		     : : "ebx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x02;
+	intcall(0x1a, &ireg, &oreg);
 
-	return dx >> 8;
+	return oreg.dh;
 }
 
 /*
@@ -64,19 +63,24 @@ static u8 gettime(void)
  */
 int getchar(void)
 {
-	u16 ax = 0;
-	asm volatile("int $0x16" : "+a" (ax));
+	struct biosregs ireg, oreg;
 
-	return ax & 0xff;
+	initregs(&ireg);
+	/* ireg.ah = 0x00; */
+	intcall(0x16, &ireg, &oreg);
+
+	return oreg.al;
 }
 
 static int kbd_pending(void)
 {
-	u8 pending;
-	asm volatile("int $0x16; setnz %0"
-		     : "=qm" (pending)
-		     : "a" (0x0100));
-	return pending;
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ah = 0x01;
+	intcall(0x16, &ireg, &oreg);
+
+	return !(oreg.eflags & X86_EFLAGS_ZF);
 }
 
 void kbd_flush(void)
diff --git a/arch/x86/boot/video-bios.c b/arch/x86/boot/video-bios.c
index 3fa979c9c363..d660be492363 100644
--- a/arch/x86/boot/video-bios.c
+++ b/arch/x86/boot/video-bios.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -29,21 +30,21 @@ static int bios_set_mode(struct mode_info *mi)
 
 static int set_bios_mode(u8 mode)
 {
-	u16 ax;
+	struct biosregs ireg, oreg;
 	u8 new_mode;
 
-	ax = mode;		/* AH=0x00 Set Video Mode */
-	asm volatile(INT10
-		     : "+a" (ax)
-		     : : "ebx", "ecx", "edx", "esi", "edi");
+	initregs(&ireg);
+	ireg.al = mode;		/* AH=0x00 Set Video Mode */
+	intcall(0x10, &ireg, NULL);
 
-	ax = 0x0f00;		/* Get Current Video Mode */
-	asm volatile(INT10
-		     : "+a" (ax)
-		     : : "ebx", "ecx", "edx", "esi", "edi");
+
+	ireg.ah = 0x0f;		/* Get Current Video Mode */
+	intcall(0x10, &ireg, &oreg);
 
 	do_restore = 1;		/* Assume video contents were lost */
-	new_mode = ax & 0x7f;	/* Not all BIOSes are clean with the top bit */
+
+	/* Not all BIOSes are clean with the top bit */
+	new_mode = ireg.al & 0x7f;
 
 	if (new_mode == mode)
 		return 0;	/* Mode change OK */
@@ -53,10 +54,8 @@ static int set_bios_mode(u8 mode)
 		/* Mode setting failed, but we didn't end up where we
 		   started.  That's bad.  Try to revert to the original
 		   video mode. */
-		ax = boot_params.screen_info.orig_video_mode;
-		asm volatile(INT10
-			     : "+a" (ax)
-			     : : "ebx", "ecx", "edx", "esi", "edi");
+		ireg.ax = boot_params.screen_info.orig_video_mode;
+		intcall(0x10, &ireg, NULL);
 	}
 #endif
 	return -1;
diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c
index 4a58c8ce3f69..c700147d6ffb 100644
--- a/arch/x86/boot/video-vesa.c
+++ b/arch/x86/boot/video-vesa.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -31,7 +32,7 @@ static inline void vesa_store_mode_params_graphics(void) {}
 static int vesa_probe(void)
 {
 #if defined(CONFIG_VIDEO_VESA) || defined(CONFIG_FIRMWARE_EDID)
-	u16 ax, cx, di;
+	struct biosregs ireg, oreg;
 	u16 mode;
 	addr_t mode_ptr;
 	struct mode_info *mi;
@@ -39,13 +40,12 @@ static int vesa_probe(void)
 
 	video_vesa.modes = GET_HEAP(struct mode_info, 0);
 
-	ax = 0x4f00;
-	di = (size_t)&vginfo;
-	asm(INT10
-	    : "+a" (ax), "+D" (di), "=m" (vginfo)
-	    : : "ebx", "ecx", "edx", "esi");
+	initregs(&ireg);
+	ireg.ax = 0x4f00;
+	ireg.di = (size_t)&vginfo;
+	intcall(0x10, &ireg, &oreg);
 
-	if (ax != 0x004f ||
+	if (ireg.ax != 0x004f ||
 	    vginfo.signature != VESA_MAGIC ||
 	    vginfo.version < 0x0102)
 		return 0;	/* Not present */
@@ -65,14 +65,12 @@ static int vesa_probe(void)
 
 		memset(&vminfo, 0, sizeof vminfo); /* Just in case... */
 
-		ax = 0x4f01;
-		cx = mode;
-		di = (size_t)&vminfo;
-		asm(INT10
-		    : "+a" (ax), "+c" (cx), "+D" (di), "=m" (vminfo)
-		    : : "ebx", "edx", "esi");
+		ireg.ax = 0x4f01;
+		ireg.cx = mode;
+		ireg.di = (size_t)&vminfo;
+		intcall(0x10, &ireg, &oreg);
 
-		if (ax != 0x004f)
+		if (ireg.ax != 0x004f)
 			continue;
 
 		if ((vminfo.mode_attr & 0x15) == 0x05) {
@@ -111,20 +109,19 @@ static int vesa_probe(void)
 
 static int vesa_set_mode(struct mode_info *mode)
 {
-	u16 ax, bx, cx, di;
+	struct biosregs ireg, oreg;
 	int is_graphic;
 	u16 vesa_mode = mode->mode - VIDEO_FIRST_VESA;
 
 	memset(&vminfo, 0, sizeof vminfo); /* Just in case... */
 
-	ax = 0x4f01;
-	cx = vesa_mode;
-	di = (size_t)&vminfo;
-	asm(INT10
-	    : "+a" (ax), "+c" (cx), "+D" (di), "=m" (vminfo)
-	    : : "ebx", "edx", "esi");
+	initregs(&ireg);
+	ireg.ax = 0x4f01;
+	ireg.cx = vesa_mode;
+	ireg.di = (size_t)&vminfo;
+	intcall(0x10, &ireg, &oreg);
 
-	if (ax != 0x004f)
+	if (oreg.ax != 0x004f)
 		return -1;
 
 	if ((vminfo.mode_attr & 0x15) == 0x05) {
@@ -141,14 +138,12 @@ static int vesa_set_mode(struct mode_info *mode)
 	}
 
 
-	ax = 0x4f02;
-	bx = vesa_mode;
-	di = 0;
-	asm volatile(INT10
-		     : "+a" (ax), "+b" (bx), "+D" (di)
-		     : : "ecx", "edx", "esi");
+	initregs(&ireg);
+	ireg.ax = 0x4f02;
+	ireg.bx = vesa_mode;
+	intcall(0x10, &ireg, &oreg);
 
-	if (ax != 0x004f)
+	if (oreg.ax != 0x004f)
 		return -1;
 
 	graphic_mode = is_graphic;
@@ -171,50 +166,45 @@ static int vesa_set_mode(struct mode_info *mode)
 /* Switch DAC to 8-bit mode */
 static void vesa_dac_set_8bits(void)
 {
+	struct biosregs ireg, oreg;
 	u8 dac_size = 6;
 
 	/* If possible, switch the DAC to 8-bit mode */
 	if (vginfo.capabilities & 1) {
-		u16 ax, bx;
-
-		ax = 0x4f08;
-		bx = 0x0800;
-		asm volatile(INT10
-			     : "+a" (ax), "+b" (bx)
-			     : : "ecx", "edx", "esi", "edi");
-
-		if (ax == 0x004f)
-			dac_size = bx >> 8;
+		initregs(&ireg);
+		ireg.ax = 0x4f08;
+		ireg.bh = 0x08;
+		intcall(0x10, &ireg, &oreg);
+		if (oreg.ax == 0x004f)
+			dac_size = oreg.bh;
 	}
 
 	/* Set the color sizes to the DAC size, and offsets to 0 */
-	boot_params.screen_info.red_size = dac_size;
+	boot_params.screen_info.red_size   = dac_size;
 	boot_params.screen_info.green_size = dac_size;
-	boot_params.screen_info.blue_size = dac_size;
-	boot_params.screen_info.rsvd_size = dac_size;
+	boot_params.screen_info.blue_size  = dac_size;
+	boot_params.screen_info.rsvd_size  = dac_size;
 
-	boot_params.screen_info.red_pos = 0;
-	boot_params.screen_info.green_pos = 0;
-	boot_params.screen_info.blue_pos = 0;
-	boot_params.screen_info.rsvd_pos = 0;
+	boot_params.screen_info.red_pos    = 0;
+	boot_params.screen_info.green_pos  = 0;
+	boot_params.screen_info.blue_pos   = 0;
+	boot_params.screen_info.rsvd_pos   = 0;
 }
 
 /* Save the VESA protected mode info */
 static void vesa_store_pm_info(void)
 {
-	u16 ax, bx, di, es;
+	struct biosregs ireg, oreg;
 
-	ax = 0x4f0a;
-	bx = di = 0;
-	asm("pushw %%es; "INT10"; movw %%es,%0; popw %%es"
-	    : "=d" (es), "+a" (ax), "+b" (bx), "+D" (di)
-	    : : "ecx", "esi");
+	initregs(&ireg);
+	ireg.ax = 0x4f0a;
+	intcall(0x10, &ireg, &oreg);
 
-	if (ax != 0x004f)
+	if (oreg.ax != 0x004f)
 		return;
 
-	boot_params.screen_info.vesapm_seg = es;
-	boot_params.screen_info.vesapm_off = di;
+	boot_params.screen_info.vesapm_seg = oreg.es;
+	boot_params.screen_info.vesapm_off = oreg.di;
 }
 
 /*
@@ -252,7 +242,7 @@ static void vesa_store_mode_params_graphics(void)
 void vesa_store_edid(void)
 {
 #ifdef CONFIG_FIRMWARE_EDID
-	u16 ax, bx, cx, dx, di;
+	struct biosregs ireg, oreg;
 
 	/* Apparently used as a nonsense token... */
 	memset(&boot_params.edid_info, 0x13, sizeof boot_params.edid_info);
@@ -260,33 +250,26 @@ void vesa_store_edid(void)
 	if (vginfo.version < 0x0200)
 		return;		/* EDID requires VBE 2.0+ */
 
-	ax = 0x4f15;		/* VBE DDC */
-	bx = 0x0000;		/* Report DDC capabilities */
-	cx = 0;			/* Controller 0 */
-	di = 0;			/* ES:DI must be 0 by spec */
+	initregs(&ireg);
+	ireg.ax = 0x4f15;		/* VBE DDC */
+	/* ireg.bx = 0x0000; */		/* Report DDC capabilities */
+	/* ireg.cx = 0;	*/		/* Controller 0 */
+	ireg.es = 0;			/* ES:DI must be 0 by spec */
+	intcall(0x10, &ireg, &oreg);
 
-	/* Note: The VBE DDC spec is different from the main VESA spec;
-	   we genuinely have to assume all registers are destroyed here. */
-
-	asm("pushw %%es; movw %2,%%es; "INT10"; popw %%es"
-	    : "+a" (ax), "+b" (bx), "+c" (cx), "+D" (di)
-	    : : "esi", "edx");
-
-	if (ax != 0x004f)
+	if (oreg.ax != 0x004f)
 		return;		/* No EDID */
 
 	/* BH = time in seconds to transfer EDD information */
 	/* BL = DDC level supported */
 
-	ax = 0x4f15;		/* VBE DDC */
-	bx = 0x0001;		/* Read EDID */
-	cx = 0;			/* Controller 0 */
-	dx = 0;			/* EDID block number */
-	di =(size_t) &boot_params.edid_info; /* (ES:)Pointer to block */
-	asm(INT10
-	    : "+a" (ax), "+b" (bx), "+d" (dx), "=m" (boot_params.edid_info),
-	      "+c" (cx), "+D" (di)
-	    : : "esi");
+	ireg.ax = 0x4f15;		/* VBE DDC */
+	ireg.bx = 0x0001;		/* Read EDID */
+	/* ireg.cx = 0; */		/* Controller 0 */
+	/* ireg.dx = 0;	*/		/* EDID block number */
+	ireg.es = ds();
+	ireg.di =(size_t)&boot_params.edid_info; /* (ES:)Pointer to block */
+	intcall(0x10, &ireg, &oreg);
 #endif /* CONFIG_FIRMWARE_EDID */
 }
 
diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c
index 9e0587a37768..8f8d827e254d 100644
--- a/arch/x86/boot/video-vga.c
+++ b/arch/x86/boot/video-vga.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -39,30 +40,30 @@ static __videocard video_vga;
 /* Set basic 80x25 mode */
 static u8 vga_set_basic_mode(void)
 {
+	struct biosregs ireg, oreg;
 	u16 ax;
 	u8 rows;
 	u8 mode;
 
+	initregs(&ireg);
+
 #ifdef CONFIG_VIDEO_400_HACK
 	if (adapter >= ADAPTER_VGA) {
-		asm volatile(INT10
-			     : : "a" (0x1202), "b" (0x0030)
-			     : "ecx", "edx", "esi", "edi");
+		ireg.ax = 0x1202;
+		ireg.bx = 0x0030;
+		intcall(0x10, &ireg, NULL);
 	}
 #endif
 
 	ax = 0x0f00;
-	asm volatile(INT10
-		     : "+a" (ax)
-		     : : "ebx", "ecx", "edx", "esi", "edi");
-
-	mode = (u8)ax;
+	intcall(0x10, &ireg, &oreg);
+	mode = oreg.al;
 
 	set_fs(0);
 	rows = rdfs8(0x484);	/* rows minus one */
 
 #ifndef CONFIG_VIDEO_400_HACK
-	if ((ax == 0x5003 || ax == 0x5007) &&
+	if ((oreg.ax == 0x5003 || oreg.ax == 0x5007) &&
 	    (rows == 0 || rows == 24))
 		return mode;
 #endif
@@ -71,10 +72,8 @@ static u8 vga_set_basic_mode(void)
 		mode = 3;
 
 	/* Set the mode */
-	ax = mode;
-	asm volatile(INT10
-		     : "+a" (ax)
-		     : : "ebx", "ecx", "edx", "esi", "edi");
+	ireg.ax = mode;		/* AH=0: set mode */
+	intcall(0x10, &ireg, NULL);
 	do_restore = 1;
 	return mode;
 }
@@ -82,43 +81,69 @@ static u8 vga_set_basic_mode(void)
 static void vga_set_8font(void)
 {
 	/* Set 8x8 font - 80x43 on EGA, 80x50 on VGA */
+	struct biosregs ireg;
+
+	initregs(&ireg);
 
 	/* Set 8x8 font */
-	asm volatile(INT10 : : "a" (0x1112), "b" (0));
+	ireg.ax = 0x1112;
+	/* ireg.bl = 0; */
+	intcall(0x10, &ireg, NULL);
 
 	/* Use alternate print screen */
-	asm volatile(INT10 : : "a" (0x1200), "b" (0x20));
+	ireg.ax = 0x1200;
+	ireg.bl = 0x20;
+	intcall(0x10, &ireg, NULL);
 
 	/* Turn off cursor emulation */
-	asm volatile(INT10 : : "a" (0x1201), "b" (0x34));
+	ireg.ax = 0x1201;
+	ireg.bl = 0x34;
+	intcall(0x10, &ireg, NULL);
 
 	/* Cursor is scan lines 6-7 */
-	asm volatile(INT10 : : "a" (0x0100), "c" (0x0607));
+	ireg.ax = 0x0100;
+	ireg.cx = 0x0607;
+	intcall(0x10, &ireg, NULL);
 }
 
 static void vga_set_14font(void)
 {
 	/* Set 9x14 font - 80x28 on VGA */
+	struct biosregs ireg;
+
+	initregs(&ireg);
 
 	/* Set 9x14 font */
-	asm volatile(INT10 : : "a" (0x1111), "b" (0));
+	ireg.ax = 0x1111;
+	/* ireg.bl = 0; */
+	intcall(0x10, &ireg, NULL);
 
 	/* Turn off cursor emulation */
-	asm volatile(INT10 : : "a" (0x1201), "b" (0x34));
+	ireg.ax = 0x1201;
+	ireg.bl = 0x34;
+	intcall(0x10, &ireg, NULL);
 
 	/* Cursor is scan lines 11-12 */
-	asm volatile(INT10 : : "a" (0x0100), "c" (0x0b0c));
+	ireg.ax = 0x0100;
+	ireg.cx = 0x0b0c;
+	intcall(0x10, &ireg, NULL);
 }
 
 static void vga_set_80x43(void)
 {
 	/* Set 80x43 mode on VGA (not EGA) */
+	struct biosregs ireg;
+
+	initregs(&ireg);
 
 	/* Set 350 scans */
-	asm volatile(INT10 : : "a" (0x1201), "b" (0x30));
+	ireg.ax = 0x1201;
+	ireg.bl = 0x30;
+	intcall(0x10, &ireg, NULL);
 
 	/* Reset video mode */
-	asm volatile(INT10 : : "a" (0x0003));
+	ireg.ax = 0x0003;
+	intcall(0x10, &ireg, NULL);
 
 	vga_set_8font();
 }
@@ -225,8 +250,6 @@ static int vga_set_mode(struct mode_info *mode)
  */
 static int vga_probe(void)
 {
-	u16 ega_bx;
-
 	static const char *card_name[] = {
 		"CGA/MDA/HGC", "EGA", "VGA"
 	};
@@ -240,26 +263,26 @@ static int vga_probe(void)
 		sizeof(ega_modes)/sizeof(struct mode_info),
 		sizeof(vga_modes)/sizeof(struct mode_info),
 	};
-	u8 vga_flag;
 
-	asm(INT10
-	    : "=b" (ega_bx)
-	    : "a" (0x1200), "b" (0x10) /* Check EGA/VGA */
-	    : "ecx", "edx", "esi", "edi");
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+
+	ireg.ax = 0x1200;
+	ireg.bl = 0x10;		/* Check EGA/VGA */
+	intcall(0x10, &ireg, &oreg);
 
 #ifndef _WAKEUP
-	boot_params.screen_info.orig_video_ega_bx = ega_bx;
+	boot_params.screen_info.orig_video_ega_bx = oreg.bx;
 #endif
 
 	/* If we have MDA/CGA/HGC then BL will be unchanged at 0x10 */
-	if ((u8)ega_bx != 0x10) {
+	if (oreg.bl != 0x10) {
 		/* EGA/VGA */
-		asm(INT10
-		    : "=a" (vga_flag)
-		    : "a" (0x1a00)
-		    : "ebx", "ecx", "edx", "esi", "edi");
+		ireg.ax = 0x1a00;
+		intcall(0x10, &ireg, &oreg);
 
-		if (vga_flag == 0x1a) {
+		if (oreg.al == 0x1a) {
 			adapter = ADAPTER_VGA;
 #ifndef _WAKEUP
 			boot_params.screen_info.orig_video_isVGA = 1;
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index 3bef2c1febe9..bad728b76fc2 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -18,33 +19,29 @@
 
 static void store_cursor_position(void)
 {
-	u16 curpos;
-	u16 ax, bx;
+	struct biosregs ireg, oreg;
 
-	ax = 0x0300;
-	bx = 0;
-	asm(INT10
-	    : "=d" (curpos), "+a" (ax), "+b" (bx)
-	    : : "ecx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x03;
+	intcall(0x10, &ireg, &oreg);
 
-	boot_params.screen_info.orig_x = curpos;
-	boot_params.screen_info.orig_y = curpos >> 8;
+	boot_params.screen_info.orig_x = oreg.dl;
+	boot_params.screen_info.orig_y = oreg.dh;
 }
 
 static void store_video_mode(void)
 {
-	u16 ax, page;
+	struct biosregs ireg, oreg;
 
 	/* N.B.: the saving of the video page here is a bit silly,
 	   since we pretty much assume page 0 everywhere. */
-	ax = 0x0f00;
-	asm(INT10
-	    : "+a" (ax), "=b" (page)
-	    : : "ecx", "edx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x0f;
+	intcall(0x10, &ireg, &oreg);
 
 	/* Not all BIOSes are clean with respect to the top bit */
-	boot_params.screen_info.orig_video_mode = ax & 0x7f;
-	boot_params.screen_info.orig_video_page = page >> 8;
+	boot_params.screen_info.orig_video_mode = oreg.al & 0x7f;
+	boot_params.screen_info.orig_video_page = oreg.bh;
 }
 
 /*
@@ -257,7 +254,7 @@ static void restore_screen(void)
 	int y;
 	addr_t dst = 0;
 	u16 *src = saved.data;
-	u16 ax, bx, dx;
+	struct biosregs ireg;
 
 	if (graphic_mode)
 		return;		/* Can't restore onto a graphic mode */
@@ -296,12 +293,11 @@ static void restore_screen(void)
 	}
 
 	/* Restore cursor position */
-	ax = 0x0200;		/* Set cursor position */
-	bx = 0;			/* Page number (<< 8) */
-	dx = (saved.cury << 8)+saved.curx;
-	asm volatile(INT10
-		     : "+a" (ax), "+b" (bx), "+d" (dx)
-		     : : "ecx", "esi", "edi");
+	initregs(&ireg);
+	ireg.ah = 0x02;		/* Set cursor position */
+	ireg.dh = saved.cury;
+	ireg.dl = saved.curx;
+	intcall(0x10, &ireg, NULL);
 }
 #else
 #define save_screen()		((void)0)
diff --git a/arch/x86/boot/video.h b/arch/x86/boot/video.h
index ee63f5d14461..5bb174a997fc 100644
--- a/arch/x86/boot/video.h
+++ b/arch/x86/boot/video.h
@@ -112,20 +112,6 @@ extern int force_x, force_y;	/* Don't query the BIOS for cols/rows */
 extern int do_restore;		/* Restore screen contents */
 extern int graphic_mode;	/* Graphics mode with linear frame buffer */
 
-/*
- * int $0x10 is notorious for touching registers it shouldn't.
- * gcc doesn't like %ebp being clobbered, so define it as a push/pop
- * sequence here.
- *
- * A number of systems, including the original PC can clobber %bp in
- * certain circumstances, like when scrolling.  There exists at least
- * one Trident video card which could clobber DS under a set of
- * circumstances that we are unlikely to encounter (scrolling when
- * using an extended graphics mode of more than 800x600 pixels), but
- * it's cheap insurance to deal with that here.
- */
-#define INT10 "pushl %%ebp; pushw %%ds; int $0x10; popw %%ds; popl %%ebp"
-
 /* Accessing VGA indexed registers */
 static inline u8 in_idx(u16 port, u8 index)
 {
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 235b81d0f6f2..edb992ebef92 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,12 +1,13 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29-rc4
-# Tue Feb 24 15:50:58 2009
+# Linux kernel version: 2.6.30-rc2
+# Mon May 11 16:21:55 2009
 #
 # CONFIG_64BIT is not set
 CONFIG_X86_32=y
 # CONFIG_X86_64 is not set
 CONFIG_X86=y
+CONFIG_OUTPUT_FORMAT="elf32-i386"
 CONFIG_ARCH_DEFCONFIG="arch/x86/configs/i386_defconfig"
 CONFIG_GENERIC_TIME=y
 CONFIG_GENERIC_CMOS_UPDATE=y
@@ -33,6 +34,7 @@ CONFIG_ARCH_HAS_CPU_RELAX=y
 CONFIG_ARCH_HAS_DEFAULT_IDLE=y
 CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
 CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_HAVE_DYNAMIC_PER_CPU_AREA=y
 # CONFIG_HAVE_CPUMASK_OF_CPU_MAP is not set
 CONFIG_ARCH_HIBERNATION_POSSIBLE=y
 CONFIG_ARCH_SUSPEND_POSSIBLE=y
@@ -40,15 +42,16 @@ CONFIG_ARCH_SUSPEND_POSSIBLE=y
 CONFIG_ARCH_POPULATES_NODE_MAP=y
 # CONFIG_AUDIT_ARCH is not set
 CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
 CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_GENERIC_PENDING_IRQ=y
-CONFIG_X86_SMP=y
 CONFIG_USE_GENERIC_SMP_HELPERS=y
 CONFIG_X86_32_SMP=y
 CONFIG_X86_HT=y
-CONFIG_X86_BIOS_REBOOT=y
 CONFIG_X86_TRAMPOLINE=y
+CONFIG_X86_32_LAZY_GS=y
 CONFIG_KTIME_SCALAR=y
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 
@@ -60,10 +63,17 @@ CONFIG_LOCK_KERNEL=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
 CONFIG_LOCALVERSION=""
 # CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_HAVE_KERNEL_GZIP=y
+CONFIG_HAVE_KERNEL_BZIP2=y
+CONFIG_HAVE_KERNEL_LZMA=y
+CONFIG_KERNEL_GZIP=y
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 CONFIG_TASKSTATS=y
@@ -113,23 +123,26 @@ CONFIG_PID_NS=y
 CONFIG_NET_NS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
+CONFIG_RD_GZIP=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
 # CONFIG_EMBEDDED is not set
 CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_KALLSYMS_EXTRA_PASS=y
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
 CONFIG_PCSPKR_PLATFORM=y
-# CONFIG_COMPAT_BRK is not set
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
-CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
 CONFIG_SIGNALFD=y
 CONFIG_TIMERFD=y
@@ -139,6 +152,7 @@ CONFIG_AIO=y
 CONFIG_VM_EVENT_COUNTERS=y
 CONFIG_PCI_QUIRKS=y
 CONFIG_SLUB_DEBUG=y
+# CONFIG_COMPAT_BRK is not set
 # CONFIG_SLAB is not set
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
@@ -154,6 +168,8 @@ CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 CONFIG_HAVE_GENERIC_DMA_COHERENT=y
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -167,7 +183,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
 # CONFIG_LBD is not set
-CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BLK_DEV_BSG=y
 # CONFIG_BLK_DEV_INTEGRITY is not set
 
@@ -194,12 +209,12 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 CONFIG_SMP=y
 CONFIG_SPARSE_IRQ=y
-CONFIG_X86_FIND_SMP_CONFIG=y
 CONFIG_X86_MPPARSE=y
+# CONFIG_X86_BIGSMP is not set
+CONFIG_X86_EXTENDED_PLATFORM=y
 # CONFIG_X86_ELAN is not set
-# CONFIG_X86_GENERICARCH is not set
-# CONFIG_X86_VSMP is not set
 # CONFIG_X86_RDC321X is not set
+# CONFIG_X86_32_NON_STANDARD is not set
 CONFIG_SCHED_OMIT_FRAME_POINTER=y
 # CONFIG_PARAVIRT_GUEST is not set
 # CONFIG_MEMTEST is not set
@@ -230,8 +245,10 @@ CONFIG_M686=y
 # CONFIG_GENERIC_CPU is not set
 CONFIG_X86_GENERIC=y
 CONFIG_X86_CPU=y
+CONFIG_X86_L1_CACHE_BYTES=64
+CONFIG_X86_INTERNODE_CACHE_BYTES=64
 CONFIG_X86_CMPXCHG=y
-CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_X86_L1_CACHE_SHIFT=5
 CONFIG_X86_XADD=y
 # CONFIG_X86_PPRO_FENCE is not set
 CONFIG_X86_WP_WORKS_OK=y
@@ -247,7 +264,7 @@ CONFIG_X86_DEBUGCTLMSR=y
 CONFIG_CPU_SUP_INTEL=y
 CONFIG_CPU_SUP_CYRIX_32=y
 CONFIG_CPU_SUP_AMD=y
-CONFIG_CPU_SUP_CENTAUR_32=y
+CONFIG_CPU_SUP_CENTAUR=y
 CONFIG_CPU_SUP_TRANSMETA_32=y
 CONFIG_CPU_SUP_UMC_32=y
 CONFIG_X86_DS=y
@@ -279,6 +296,7 @@ CONFIG_MICROCODE_AMD=y
 CONFIG_MICROCODE_OLD_INTERFACE=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
+# CONFIG_X86_CPU_DEBUG is not set
 # CONFIG_NOHIGHMEM is not set
 CONFIG_HIGHMEM4G=y
 # CONFIG_HIGHMEM64G is not set
@@ -302,6 +320,8 @@ CONFIG_ZONE_DMA_FLAG=1
 CONFIG_BOUNCE=y
 CONFIG_VIRT_TO_BUS=y
 CONFIG_UNEVICTABLE_LRU=y
+CONFIG_HAVE_MLOCK=y
+CONFIG_HAVE_MLOCKED_PAGE_BIT=y
 CONFIG_HIGHPTE=y
 CONFIG_X86_CHECK_BIOS_CORRUPTION=y
 CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
@@ -312,6 +332,7 @@ CONFIG_MTRR=y
 CONFIG_X86_PAT=y
 CONFIG_EFI=y
 CONFIG_SECCOMP=y
+# CONFIG_CC_STACKPROTECTOR is not set
 # CONFIG_HZ_100 is not set
 # CONFIG_HZ_250 is not set
 # CONFIG_HZ_300 is not set
@@ -322,8 +343,9 @@ CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 # CONFIG_KEXEC_JUMP is not set
 CONFIG_PHYSICAL_START=0x1000000
-# CONFIG_RELOCATABLE is not set
-CONFIG_PHYSICAL_ALIGN=0x200000
+CONFIG_RELOCATABLE=y
+CONFIG_X86_NEED_RELOCS=y
+CONFIG_PHYSICAL_ALIGN=0x1000000
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_COMPAT_VDSO is not set
 # CONFIG_CMDLINE_BOOL is not set
@@ -363,7 +385,6 @@ CONFIG_ACPI_THERMAL=y
 CONFIG_ACPI_BLACKLIST_YEAR=0
 # CONFIG_ACPI_DEBUG is not set
 # CONFIG_ACPI_PCI_SLOT is not set
-CONFIG_ACPI_SYSTEM=y
 CONFIG_X86_PM_TIMER=y
 CONFIG_ACPI_CONTAINER=y
 # CONFIG_ACPI_SBS is not set
@@ -425,6 +446,7 @@ CONFIG_PCI_BIOS=y
 CONFIG_PCI_DIRECT=y
 CONFIG_PCI_MMCONFIG=y
 CONFIG_PCI_DOMAINS=y
+# CONFIG_DMAR is not set
 CONFIG_PCIEPORTBUS=y
 # CONFIG_HOTPLUG_PCI_PCIE is not set
 CONFIG_PCIEAER=y
@@ -435,6 +457,7 @@ CONFIG_PCI_MSI=y
 # CONFIG_PCI_DEBUG is not set
 # CONFIG_PCI_STUB is not set
 CONFIG_HT_IRQ=y
+# CONFIG_PCI_IOV is not set
 CONFIG_ISA_DMA_API=y
 # CONFIG_ISA is not set
 # CONFIG_MCA is not set
@@ -481,7 +504,6 @@ CONFIG_NET=y
 #
 # Networking options
 #
-CONFIG_COMPAT_NET_DEV_OPS=y
 CONFIG_PACKET=y
 CONFIG_PACKET_MMAP=y
 CONFIG_UNIX=y
@@ -639,6 +661,7 @@ CONFIG_LLC=y
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
+# CONFIG_PHONET is not set
 CONFIG_NET_SCHED=y
 
 #
@@ -696,6 +719,7 @@ CONFIG_NET_SCH_FIFO=y
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_NET_TCPPROBE is not set
+# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_HAMRADIO=y
 
 #
@@ -706,12 +730,10 @@ CONFIG_HAMRADIO=y
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
-# CONFIG_PHONET is not set
 CONFIG_FIB_RULES=y
 CONFIG_WIRELESS=y
 CONFIG_CFG80211=y
 # CONFIG_CFG80211_REG_DEBUG is not set
-CONFIG_NL80211=y
 CONFIG_WIRELESS_OLD_REGULATORY=y
 CONFIG_WIRELESS_EXT=y
 CONFIG_WIRELESS_EXT_SYSFS=y
@@ -789,6 +811,7 @@ CONFIG_MISC_DEVICES=y
 # CONFIG_ICS932S401 is not set
 # CONFIG_ENCLOSURE_SERVICES is not set
 # CONFIG_HP_ILO is not set
+# CONFIG_ISL29003 is not set
 # CONFIG_C2PORT is not set
 
 #
@@ -842,6 +865,7 @@ CONFIG_SCSI_SPI_ATTRS=y
 # CONFIG_SCSI_LOWLEVEL is not set
 # CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
 # CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
 CONFIG_ATA=y
 # CONFIG_ATA_NONSTANDARD is not set
 CONFIG_ATA_ACPI=y
@@ -940,6 +964,7 @@ CONFIG_DM_ZERO=y
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
+CONFIG_COMPAT_NET_DEV_OPS=y
 # CONFIG_IFB is not set
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
@@ -977,6 +1002,8 @@ CONFIG_MII=y
 CONFIG_NET_VENDOR_3COM=y
 # CONFIG_VORTEX is not set
 # CONFIG_TYPHOON is not set
+# CONFIG_ETHOC is not set
+# CONFIG_DNET is not set
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
 # CONFIG_TULIP is not set
@@ -1026,6 +1053,7 @@ CONFIG_E1000=y
 CONFIG_E1000E=y
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -1040,6 +1068,7 @@ CONFIG_BNX2=y
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
 # CONFIG_ATL1E is not set
+# CONFIG_ATL1C is not set
 # CONFIG_JME is not set
 CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
@@ -1049,6 +1078,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -1058,6 +1088,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_BNX2X is not set
 # CONFIG_QLGE is not set
 # CONFIG_SFC is not set
+# CONFIG_BE2NET is not set
 CONFIG_TR=y
 # CONFIG_IBMOL is not set
 # CONFIG_IBMLS is not set
@@ -1073,8 +1104,8 @@ CONFIG_WLAN_80211=y
 # CONFIG_LIBERTAS is not set
 # CONFIG_LIBERTAS_THINFIRM is not set
 # CONFIG_AIRO is not set
-# CONFIG_HERMES is not set
 # CONFIG_ATMEL is not set
+# CONFIG_AT76C50X_USB is not set
 # CONFIG_AIRO_CS is not set
 # CONFIG_PCMCIA_WL3501 is not set
 # CONFIG_PRISM54 is not set
@@ -1084,21 +1115,21 @@ CONFIG_WLAN_80211=y
 # CONFIG_RTL8187 is not set
 # CONFIG_ADM8211 is not set
 # CONFIG_MAC80211_HWSIM is not set
+# CONFIG_MWL8K is not set
 # CONFIG_P54_COMMON is not set
 CONFIG_ATH5K=y
 # CONFIG_ATH5K_DEBUG is not set
 # CONFIG_ATH9K is not set
+# CONFIG_AR9170_USB is not set
 # CONFIG_IPW2100 is not set
 # CONFIG_IPW2200 is not set
-# CONFIG_IWLCORE is not set
-# CONFIG_IWLWIFI_LEDS is not set
-# CONFIG_IWLAGN is not set
-# CONFIG_IWL3945 is not set
+# CONFIG_IWLWIFI is not set
 # CONFIG_HOSTAP is not set
 # CONFIG_B43 is not set
 # CONFIG_B43LEGACY is not set
 # CONFIG_ZD1211RW is not set
 # CONFIG_RT2X00 is not set
+# CONFIG_HERMES is not set
 
 #
 # Enable WiMAX (Networking options) to see the WiMAX drivers
@@ -1209,6 +1240,8 @@ CONFIG_INPUT_TABLET=y
 # CONFIG_TABLET_USB_KBTAB is not set
 # CONFIG_TABLET_USB_WACOM is not set
 CONFIG_INPUT_TOUCHSCREEN=y
+# CONFIG_TOUCHSCREEN_AD7879_I2C is not set
+# CONFIG_TOUCHSCREEN_AD7879 is not set
 # CONFIG_TOUCHSCREEN_FUJITSU is not set
 # CONFIG_TOUCHSCREEN_GUNZE is not set
 # CONFIG_TOUCHSCREEN_ELO is not set
@@ -1303,6 +1336,7 @@ CONFIG_UNIX98_PTYS=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_IPMI_HANDLER is not set
 CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_TIMERIOMEM is not set
 CONFIG_HW_RANDOM_INTEL=y
 CONFIG_HW_RANDOM_AMD=y
 CONFIG_HW_RANDOM_GEODE=y
@@ -1390,7 +1424,6 @@ CONFIG_I2C_I801=y
 # CONFIG_SENSORS_PCF8574 is not set
 # CONFIG_PCF8575 is not set
 # CONFIG_SENSORS_PCA9539 is not set
-# CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_MAX6875 is not set
 # CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
@@ -1424,6 +1457,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_ADT7475 is not set
 # CONFIG_SENSORS_K8TEMP is not set
 # CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_ATK0110 is not set
 # CONFIG_SENSORS_ATXP1 is not set
 # CONFIG_SENSORS_DS1621 is not set
 # CONFIG_SENSORS_I5K_AMB is not set
@@ -1433,6 +1467,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_FSCHER is not set
 # CONFIG_SENSORS_FSCPOS is not set
 # CONFIG_SENSORS_FSCHMD is not set
+# CONFIG_SENSORS_G760A is not set
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_CORETEMP is not set
@@ -1448,11 +1483,14 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_LM90 is not set
 # CONFIG_SENSORS_LM92 is not set
 # CONFIG_SENSORS_LM93 is not set
+# CONFIG_SENSORS_LTC4215 is not set
 # CONFIG_SENSORS_LTC4245 is not set
+# CONFIG_SENSORS_LM95241 is not set
 # CONFIG_SENSORS_MAX1619 is not set
 # CONFIG_SENSORS_MAX6650 is not set
 # CONFIG_SENSORS_PC87360 is not set
 # CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_SIS5595 is not set
 # CONFIG_SENSORS_DME1737 is not set
 # CONFIG_SENSORS_SMSC47M1 is not set
@@ -1643,7 +1681,6 @@ CONFIG_FB_EFI=y
 # CONFIG_FB_3DFX is not set
 # CONFIG_FB_VOODOO1 is not set
 # CONFIG_FB_VT8623 is not set
-# CONFIG_FB_CYBLA is not set
 # CONFIG_FB_TRIDENT is not set
 # CONFIG_FB_ARK is not set
 # CONFIG_FB_PM3 is not set
@@ -1652,6 +1689,7 @@ CONFIG_FB_EFI=y
 # CONFIG_FB_VIRTUAL is not set
 # CONFIG_FB_METRONOME is not set
 # CONFIG_FB_MB862XX is not set
+# CONFIG_FB_BROADSHEET is not set
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
@@ -1738,6 +1776,8 @@ CONFIG_SND_PCI=y
 # CONFIG_SND_INDIGO is not set
 # CONFIG_SND_INDIGOIO is not set
 # CONFIG_SND_INDIGODJ is not set
+# CONFIG_SND_INDIGOIOX is not set
+# CONFIG_SND_INDIGODJX is not set
 # CONFIG_SND_EMU10K1 is not set
 # CONFIG_SND_EMU10K1X is not set
 # CONFIG_SND_ENS1370 is not set
@@ -1811,15 +1851,17 @@ CONFIG_USB_HIDDEV=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+CONFIG_HID_KYE=y
 CONFIG_HID_GYRATION=y
+CONFIG_HID_KENSINGTON=y
 CONFIG_HID_LOGITECH=y
 CONFIG_LOGITECH_FF=y
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1885,11 +1927,11 @@ CONFIG_USB_PRINTER=y
 # CONFIG_USB_TMC is not set
 
 #
-# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
 #
 
 #
-# see USB_STORAGE Help for more information
+# also be needed; see USB_STORAGE Help for more info
 #
 CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_DEBUG is not set
@@ -1931,7 +1973,6 @@ CONFIG_USB_LIBUSUAL=y
 # CONFIG_USB_LED is not set
 # CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
-# CONFIG_USB_PHIDGET is not set
 # CONFIG_USB_IDMOUSE is not set
 # CONFIG_USB_FTDI_ELAN is not set
 # CONFIG_USB_APPLEDISPLAY is not set
@@ -1947,6 +1988,7 @@ CONFIG_USB_LIBUSUAL=y
 #
 # OTG and related infrastructure
 #
+# CONFIG_NOP_USB_XCEIV is not set
 # CONFIG_UWB is not set
 # CONFIG_MMC is not set
 # CONFIG_MEMSTICK is not set
@@ -1958,8 +2000,10 @@ CONFIG_LEDS_CLASS=y
 #
 # CONFIG_LEDS_ALIX2 is not set
 # CONFIG_LEDS_PCA9532 is not set
+# CONFIG_LEDS_LP5521 is not set
 # CONFIG_LEDS_CLEVO_MAIL is not set
 # CONFIG_LEDS_PCA955X is not set
+# CONFIG_LEDS_BD2802 is not set
 
 #
 # LED Triggers
@@ -1969,6 +2013,10 @@ CONFIG_LEDS_TRIGGERS=y
 # CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
 # CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
 # CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set
+
+#
+# iptables trigger is under Netfilter config (LED target)
+#
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
 CONFIG_EDAC=y
@@ -2037,6 +2085,7 @@ CONFIG_DMADEVICES=y
 # DMA Devices
 #
 # CONFIG_INTEL_IOATDMA is not set
+# CONFIG_AUXDISPLAY is not set
 # CONFIG_UIO is not set
 # CONFIG_STAGING is not set
 CONFIG_X86_PLATFORM_DEVICES=y
@@ -2071,6 +2120,7 @@ CONFIG_DMIID=y
 #
 # CONFIG_EXT2_FS is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
@@ -2100,6 +2150,11 @@ CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
 CONFIG_GENERIC_ACL=y
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -2151,6 +2206,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -2164,7 +2220,6 @@ CONFIG_NFS_ACL_SUPPORT=y
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=y
 CONFIG_SUNRPC_GSS=y
-# CONFIG_SUNRPC_REGISTER_V4 is not set
 CONFIG_RPCSEC_GSS_KRB5=y
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
@@ -2251,6 +2306,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 # CONFIG_DETECT_SOFTLOCKUP is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
@@ -2266,6 +2322,7 @@ CONFIG_TIMER_STATS=y
 # CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
 # CONFIG_DEBUG_KOBJECT is not set
 # CONFIG_DEBUG_HIGHMEM is not set
 CONFIG_DEBUG_BUGVERBOSE=y
@@ -2289,13 +2346,19 @@ CONFIG_FRAME_POINTER=y
 # CONFIG_FAULT_INJECTION is not set
 # CONFIG_LATENCYTOP is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
+# CONFIG_DEBUG_PAGEALLOC is not set
 CONFIG_USER_STACKTRACE_SUPPORT=y
+CONFIG_NOP_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_HAVE_HW_BRANCH_TRACER=y
+CONFIG_HAVE_FTRACE_SYSCALLS=y
+CONFIG_RING_BUFFER=y
+CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -2305,13 +2368,21 @@ CONFIG_HAVE_HW_BRANCH_TRACER=y
 # CONFIG_SYSPROF_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_FTRACE_SYSCALLS is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_POWER_TRACER is not set
 # CONFIG_STACK_TRACER is not set
 # CONFIG_HW_BRANCH_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+CONFIG_BLK_DEV_IO_TRACE=y
+# CONFIG_FTRACE_STARTUP_TEST is not set
+# CONFIG_MMIOTRACE is not set
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
-# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
+# CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -2321,7 +2392,6 @@ CONFIG_EARLY_PRINTK=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DEBUG_STACK_USAGE=y
-# CONFIG_DEBUG_PAGEALLOC is not set
 # CONFIG_DEBUG_PER_CPU_MAPS is not set
 # CONFIG_X86_PTDUMP is not set
 CONFIG_DEBUG_RODATA=y
@@ -2329,7 +2399,7 @@ CONFIG_DEBUG_RODATA=y
 CONFIG_DEBUG_NX_TEST=m
 # CONFIG_4KSTACKS is not set
 CONFIG_DOUBLEFAULT=y
-# CONFIG_MMIOTRACE is not set
+CONFIG_HAVE_MMIOTRACE_SUPPORT=y
 CONFIG_IO_DELAY_TYPE_0X80=0
 CONFIG_IO_DELAY_TYPE_0XED=1
 CONFIG_IO_DELAY_TYPE_UDELAY=2
@@ -2365,6 +2435,8 @@ CONFIG_SECURITY_SELINUX_AVC_STATS=y
 CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
 # CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
 # CONFIG_SECURITY_SMACK is not set
+# CONFIG_SECURITY_TOMOYO is not set
+# CONFIG_IMA is not set
 CONFIG_CRYPTO=y
 
 #
@@ -2380,10 +2452,12 @@ CONFIG_CRYPTO_BLKCIPHER2=y
 CONFIG_CRYPTO_HASH=y
 CONFIG_CRYPTO_HASH2=y
 CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP=y
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_MANAGER2=y
 # CONFIG_CRYPTO_GF128MUL is not set
 # CONFIG_CRYPTO_NULL is not set
+CONFIG_CRYPTO_WORKQUEUE=y
 # CONFIG_CRYPTO_CRYPTD is not set
 CONFIG_CRYPTO_AUTHENC=y
 # CONFIG_CRYPTO_TEST is not set
@@ -2456,6 +2530,7 @@ CONFIG_CRYPTO_DES=y
 # Compression
 #
 # CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
 # CONFIG_CRYPTO_LZO is not set
 
 #
@@ -2467,11 +2542,13 @@ CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_GEODE is not set
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
 CONFIG_HAVE_KVM=y
+CONFIG_HAVE_KVM_IRQCHIP=y
 CONFIG_VIRTUALIZATION=y
 # CONFIG_KVM is not set
 # CONFIG_LGUEST is not set
 # CONFIG_VIRTIO_PCI is not set
 # CONFIG_VIRTIO_BALLOON is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
@@ -2489,7 +2566,10 @@ CONFIG_CRC32=y
 # CONFIG_LIBCRC32C is not set
 CONFIG_AUDIT_GENERIC=y
 CONFIG_ZLIB_INFLATE=y
-CONFIG_PLIST=y
+CONFIG_DECOMPRESS_GZIP=y
+CONFIG_DECOMPRESS_BZIP2=y
+CONFIG_DECOMPRESS_LZMA=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
 CONFIG_HAS_DMA=y
+CONFIG_NLATTR=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 9fe5d212ab4c..cee1dd2e69b2 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1,12 +1,13 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.29-rc4
-# Tue Feb 24 15:44:16 2009
+# Linux kernel version: 2.6.30-rc2
+# Mon May 11 16:22:00 2009
 #
 CONFIG_64BIT=y
 # CONFIG_X86_32 is not set
 CONFIG_X86_64=y
 CONFIG_X86=y
+CONFIG_OUTPUT_FORMAT="elf64-x86-64"
 CONFIG_ARCH_DEFCONFIG="arch/x86/configs/x86_64_defconfig"
 CONFIG_GENERIC_TIME=y
 CONFIG_GENERIC_CMOS_UPDATE=y
@@ -34,6 +35,7 @@ CONFIG_ARCH_HAS_CPU_RELAX=y
 CONFIG_ARCH_HAS_DEFAULT_IDLE=y
 CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
 CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_HAVE_DYNAMIC_PER_CPU_AREA=y
 CONFIG_HAVE_CPUMASK_OF_CPU_MAP=y
 CONFIG_ARCH_HIBERNATION_POSSIBLE=y
 CONFIG_ARCH_SUSPEND_POSSIBLE=y
@@ -41,14 +43,14 @@ CONFIG_ZONE_DMA32=y
 CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_AUDIT_ARCH=y
 CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
+CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
 CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_GENERIC_PENDING_IRQ=y
-CONFIG_X86_SMP=y
 CONFIG_USE_GENERIC_SMP_HELPERS=y
 CONFIG_X86_64_SMP=y
 CONFIG_X86_HT=y
-CONFIG_X86_BIOS_REBOOT=y
 CONFIG_X86_TRAMPOLINE=y
 # CONFIG_KTIME_SCALAR is not set
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
@@ -61,10 +63,17 @@ CONFIG_LOCK_KERNEL=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
 CONFIG_LOCALVERSION=""
 # CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_HAVE_KERNEL_GZIP=y
+CONFIG_HAVE_KERNEL_BZIP2=y
+CONFIG_HAVE_KERNEL_LZMA=y
+CONFIG_KERNEL_GZIP=y
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_POSIX_MQUEUE_SYSCTL=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 CONFIG_TASKSTATS=y
@@ -114,23 +123,26 @@ CONFIG_PID_NS=y
 CONFIG_NET_NS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
+CONFIG_RD_GZIP=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
 # CONFIG_EMBEDDED is not set
 CONFIG_UID16=y
 CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_KALLSYMS_EXTRA_PASS=y
+# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
 CONFIG_PCSPKR_PLATFORM=y
-# CONFIG_COMPAT_BRK is not set
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
-CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
 CONFIG_SIGNALFD=y
 CONFIG_TIMERFD=y
@@ -140,6 +152,7 @@ CONFIG_AIO=y
 CONFIG_VM_EVENT_COUNTERS=y
 CONFIG_PCI_QUIRKS=y
 CONFIG_SLUB_DEBUG=y
+# CONFIG_COMPAT_BRK is not set
 # CONFIG_SLAB is not set
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
@@ -155,6 +168,8 @@ CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+# CONFIG_SLOW_WORK is not set
 # CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
@@ -167,7 +182,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
-CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BLK_DEV_BSG=y
 # CONFIG_BLK_DEV_INTEGRITY is not set
 CONFIG_BLOCK_COMPAT=y
@@ -195,12 +209,10 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 CONFIG_SMP=y
 CONFIG_SPARSE_IRQ=y
-# CONFIG_NUMA_MIGRATE_IRQ_DESC is not set
-CONFIG_X86_FIND_SMP_CONFIG=y
 CONFIG_X86_MPPARSE=y
-# CONFIG_X86_ELAN is not set
-# CONFIG_X86_GENERICARCH is not set
+CONFIG_X86_EXTENDED_PLATFORM=y
 # CONFIG_X86_VSMP is not set
+# CONFIG_X86_UV is not set
 CONFIG_SCHED_OMIT_FRAME_POINTER=y
 # CONFIG_PARAVIRT_GUEST is not set
 # CONFIG_MEMTEST is not set
@@ -230,10 +242,10 @@ CONFIG_SCHED_OMIT_FRAME_POINTER=y
 # CONFIG_MCORE2 is not set
 CONFIG_GENERIC_CPU=y
 CONFIG_X86_CPU=y
-CONFIG_X86_L1_CACHE_BYTES=128
-CONFIG_X86_INTERNODE_CACHE_BYTES=128
+CONFIG_X86_L1_CACHE_BYTES=64
+CONFIG_X86_INTERNODE_CACHE_BYTES=64
 CONFIG_X86_CMPXCHG=y
-CONFIG_X86_L1_CACHE_SHIFT=7
+CONFIG_X86_L1_CACHE_SHIFT=6
 CONFIG_X86_WP_WORKS_OK=y
 CONFIG_X86_TSC=y
 CONFIG_X86_CMPXCHG64=y
@@ -242,7 +254,7 @@ CONFIG_X86_MINIMUM_CPU_FAMILY=64
 CONFIG_X86_DEBUGCTLMSR=y
 CONFIG_CPU_SUP_INTEL=y
 CONFIG_CPU_SUP_AMD=y
-CONFIG_CPU_SUP_CENTAUR_64=y
+CONFIG_CPU_SUP_CENTAUR=y
 CONFIG_X86_DS=y
 CONFIG_X86_PTRACE_BTS=y
 CONFIG_HPET_TIMER=y
@@ -269,6 +281,7 @@ CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
 CONFIG_X86_MCE=y
 CONFIG_X86_MCE_INTEL=y
 CONFIG_X86_MCE_AMD=y
+CONFIG_X86_MCE_THRESHOLD=y
 # CONFIG_I8K is not set
 CONFIG_MICROCODE=y
 CONFIG_MICROCODE_INTEL=y
@@ -276,6 +289,7 @@ CONFIG_MICROCODE_AMD=y
 CONFIG_MICROCODE_OLD_INTERFACE=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
+# CONFIG_X86_CPU_DEBUG is not set
 CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
 CONFIG_DIRECT_GBPAGES=y
 CONFIG_NUMA=y
@@ -309,6 +323,8 @@ CONFIG_ZONE_DMA_FLAG=1
 CONFIG_BOUNCE=y
 CONFIG_VIRT_TO_BUS=y
 CONFIG_UNEVICTABLE_LRU=y
+CONFIG_HAVE_MLOCK=y
+CONFIG_HAVE_MLOCKED_PAGE_BIT=y
 CONFIG_X86_CHECK_BIOS_CORRUPTION=y
 CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
 CONFIG_X86_RESERVE_LOW_64K=y
@@ -317,6 +333,7 @@ CONFIG_MTRR=y
 CONFIG_X86_PAT=y
 CONFIG_EFI=y
 CONFIG_SECCOMP=y
+# CONFIG_CC_STACKPROTECTOR is not set
 # CONFIG_HZ_100 is not set
 # CONFIG_HZ_250 is not set
 # CONFIG_HZ_300 is not set
@@ -325,9 +342,10 @@ CONFIG_HZ=1000
 CONFIG_SCHED_HRTICK=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
+# CONFIG_KEXEC_JUMP is not set
 CONFIG_PHYSICAL_START=0x1000000
-# CONFIG_RELOCATABLE is not set
-CONFIG_PHYSICAL_ALIGN=0x200000
+CONFIG_RELOCATABLE=y
+CONFIG_PHYSICAL_ALIGN=0x1000000
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_COMPAT_VDSO is not set
 # CONFIG_CMDLINE_BOOL is not set
@@ -370,7 +388,6 @@ CONFIG_ACPI_NUMA=y
 CONFIG_ACPI_BLACKLIST_YEAR=0
 # CONFIG_ACPI_DEBUG is not set
 # CONFIG_ACPI_PCI_SLOT is not set
-CONFIG_ACPI_SYSTEM=y
 CONFIG_X86_PM_TIMER=y
 CONFIG_ACPI_CONTAINER=y
 # CONFIG_ACPI_SBS is not set
@@ -436,6 +453,7 @@ CONFIG_PCI_MSI=y
 # CONFIG_PCI_DEBUG is not set
 # CONFIG_PCI_STUB is not set
 CONFIG_HT_IRQ=y
+# CONFIG_PCI_IOV is not set
 CONFIG_ISA_DMA_API=y
 CONFIG_K8_NB=y
 CONFIG_PCCARD=y
@@ -481,7 +499,6 @@ CONFIG_NET=y
 #
 # Networking options
 #
-CONFIG_COMPAT_NET_DEV_OPS=y
 CONFIG_PACKET=y
 CONFIG_PACKET_MMAP=y
 CONFIG_UNIX=y
@@ -639,6 +656,7 @@ CONFIG_LLC=y
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
+# CONFIG_PHONET is not set
 CONFIG_NET_SCHED=y
 
 #
@@ -696,6 +714,7 @@ CONFIG_NET_SCH_FIFO=y
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_NET_TCPPROBE is not set
+# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_HAMRADIO=y
 
 #
@@ -706,12 +725,10 @@ CONFIG_HAMRADIO=y
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
-# CONFIG_PHONET is not set
 CONFIG_FIB_RULES=y
 CONFIG_WIRELESS=y
 CONFIG_CFG80211=y
 # CONFIG_CFG80211_REG_DEBUG is not set
-CONFIG_NL80211=y
 CONFIG_WIRELESS_OLD_REGULATORY=y
 CONFIG_WIRELESS_EXT=y
 CONFIG_WIRELESS_EXT_SYSFS=y
@@ -788,9 +805,8 @@ CONFIG_MISC_DEVICES=y
 # CONFIG_TIFM_CORE is not set
 # CONFIG_ICS932S401 is not set
 # CONFIG_ENCLOSURE_SERVICES is not set
-# CONFIG_SGI_XP is not set
 # CONFIG_HP_ILO is not set
-# CONFIG_SGI_GRU is not set
+# CONFIG_ISL29003 is not set
 # CONFIG_C2PORT is not set
 
 #
@@ -844,6 +860,7 @@ CONFIG_SCSI_SPI_ATTRS=y
 # CONFIG_SCSI_LOWLEVEL is not set
 # CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
 # CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
 CONFIG_ATA=y
 # CONFIG_ATA_NONSTANDARD is not set
 CONFIG_ATA_ACPI=y
@@ -940,6 +957,7 @@ CONFIG_DM_ZERO=y
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
+CONFIG_COMPAT_NET_DEV_OPS=y
 # CONFIG_IFB is not set
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
@@ -977,6 +995,8 @@ CONFIG_MII=y
 CONFIG_NET_VENDOR_3COM=y
 # CONFIG_VORTEX is not set
 # CONFIG_TYPHOON is not set
+# CONFIG_ETHOC is not set
+# CONFIG_DNET is not set
 CONFIG_NET_TULIP=y
 # CONFIG_DE2104X is not set
 # CONFIG_TULIP is not set
@@ -1026,6 +1046,7 @@ CONFIG_E1000=y
 # CONFIG_E1000E is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -1040,6 +1061,7 @@ CONFIG_TIGON3=y
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
 # CONFIG_ATL1E is not set
+# CONFIG_ATL1C is not set
 # CONFIG_JME is not set
 CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
@@ -1049,6 +1071,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
@@ -1058,6 +1081,7 @@ CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_BNX2X is not set
 # CONFIG_QLGE is not set
 # CONFIG_SFC is not set
+# CONFIG_BE2NET is not set
 CONFIG_TR=y
 # CONFIG_IBMOL is not set
 # CONFIG_3C359 is not set
@@ -1072,8 +1096,8 @@ CONFIG_WLAN_80211=y
 # CONFIG_LIBERTAS is not set
 # CONFIG_LIBERTAS_THINFIRM is not set
 # CONFIG_AIRO is not set
-# CONFIG_HERMES is not set
 # CONFIG_ATMEL is not set
+# CONFIG_AT76C50X_USB is not set
 # CONFIG_AIRO_CS is not set
 # CONFIG_PCMCIA_WL3501 is not set
 # CONFIG_PRISM54 is not set
@@ -1083,21 +1107,21 @@ CONFIG_WLAN_80211=y
 # CONFIG_RTL8187 is not set
 # CONFIG_ADM8211 is not set
 # CONFIG_MAC80211_HWSIM is not set
+# CONFIG_MWL8K is not set
 # CONFIG_P54_COMMON is not set
 CONFIG_ATH5K=y
 # CONFIG_ATH5K_DEBUG is not set
 # CONFIG_ATH9K is not set
+# CONFIG_AR9170_USB is not set
 # CONFIG_IPW2100 is not set
 # CONFIG_IPW2200 is not set
-# CONFIG_IWLCORE is not set
-# CONFIG_IWLWIFI_LEDS is not set
-# CONFIG_IWLAGN is not set
-# CONFIG_IWL3945 is not set
+# CONFIG_IWLWIFI is not set
 # CONFIG_HOSTAP is not set
 # CONFIG_B43 is not set
 # CONFIG_B43LEGACY is not set
 # CONFIG_ZD1211RW is not set
 # CONFIG_RT2X00 is not set
+# CONFIG_HERMES is not set
 
 #
 # Enable WiMAX (Networking options) to see the WiMAX drivers
@@ -1208,6 +1232,8 @@ CONFIG_INPUT_TABLET=y
 # CONFIG_TABLET_USB_KBTAB is not set
 # CONFIG_TABLET_USB_WACOM is not set
 CONFIG_INPUT_TOUCHSCREEN=y
+# CONFIG_TOUCHSCREEN_AD7879_I2C is not set
+# CONFIG_TOUCHSCREEN_AD7879 is not set
 # CONFIG_TOUCHSCREEN_FUJITSU is not set
 # CONFIG_TOUCHSCREEN_GUNZE is not set
 # CONFIG_TOUCHSCREEN_ELO is not set
@@ -1301,6 +1327,7 @@ CONFIG_UNIX98_PTYS=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_IPMI_HANDLER is not set
 CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_TIMERIOMEM is not set
 # CONFIG_HW_RANDOM_INTEL is not set
 # CONFIG_HW_RANDOM_AMD is not set
 CONFIG_NVRAM=y
@@ -1382,7 +1409,6 @@ CONFIG_I2C_I801=y
 # CONFIG_SENSORS_PCF8574 is not set
 # CONFIG_PCF8575 is not set
 # CONFIG_SENSORS_PCA9539 is not set
-# CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_MAX6875 is not set
 # CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
@@ -1416,6 +1442,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_ADT7475 is not set
 # CONFIG_SENSORS_K8TEMP is not set
 # CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_ATK0110 is not set
 # CONFIG_SENSORS_ATXP1 is not set
 # CONFIG_SENSORS_DS1621 is not set
 # CONFIG_SENSORS_I5K_AMB is not set
@@ -1425,6 +1452,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_FSCHER is not set
 # CONFIG_SENSORS_FSCPOS is not set
 # CONFIG_SENSORS_FSCHMD is not set
+# CONFIG_SENSORS_G760A is not set
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_CORETEMP is not set
@@ -1440,11 +1468,14 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_LM90 is not set
 # CONFIG_SENSORS_LM92 is not set
 # CONFIG_SENSORS_LM93 is not set
+# CONFIG_SENSORS_LTC4215 is not set
 # CONFIG_SENSORS_LTC4245 is not set
+# CONFIG_SENSORS_LM95241 is not set
 # CONFIG_SENSORS_MAX1619 is not set
 # CONFIG_SENSORS_MAX6650 is not set
 # CONFIG_SENSORS_PC87360 is not set
 # CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_SIS5595 is not set
 # CONFIG_SENSORS_DME1737 is not set
 # CONFIG_SENSORS_SMSC47M1 is not set
@@ -1635,6 +1666,7 @@ CONFIG_FB_EFI=y
 # CONFIG_FB_VIRTUAL is not set
 # CONFIG_FB_METRONOME is not set
 # CONFIG_FB_MB862XX is not set
+# CONFIG_FB_BROADSHEET is not set
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
@@ -1720,6 +1752,8 @@ CONFIG_SND_PCI=y
 # CONFIG_SND_INDIGO is not set
 # CONFIG_SND_INDIGOIO is not set
 # CONFIG_SND_INDIGODJ is not set
+# CONFIG_SND_INDIGOIOX is not set
+# CONFIG_SND_INDIGODJX is not set
 # CONFIG_SND_EMU10K1 is not set
 # CONFIG_SND_EMU10K1X is not set
 # CONFIG_SND_ENS1370 is not set
@@ -1792,15 +1826,17 @@ CONFIG_USB_HIDDEV=y
 #
 # Special HID drivers
 #
-CONFIG_HID_COMPAT=y
 CONFIG_HID_A4TECH=y
 CONFIG_HID_APPLE=y
 CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+# CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
+CONFIG_HID_KYE=y
 CONFIG_HID_GYRATION=y
+CONFIG_HID_KENSINGTON=y
 CONFIG_HID_LOGITECH=y
 CONFIG_LOGITECH_FF=y
 # CONFIG_LOGIRUMBLEPAD2_FF is not set
@@ -1866,11 +1902,11 @@ CONFIG_USB_PRINTER=y
 # CONFIG_USB_TMC is not set
 
 #
-# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
 #
 
 #
-# see USB_STORAGE Help for more information
+# also be needed; see USB_STORAGE Help for more info
 #
 CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_DEBUG is not set
@@ -1912,7 +1948,6 @@ CONFIG_USB_LIBUSUAL=y
 # CONFIG_USB_LED is not set
 # CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
-# CONFIG_USB_PHIDGET is not set
 # CONFIG_USB_IDMOUSE is not set
 # CONFIG_USB_FTDI_ELAN is not set
 # CONFIG_USB_APPLEDISPLAY is not set
@@ -1928,6 +1963,7 @@ CONFIG_USB_LIBUSUAL=y
 #
 # OTG and related infrastructure
 #
+# CONFIG_NOP_USB_XCEIV is not set
 # CONFIG_UWB is not set
 # CONFIG_MMC is not set
 # CONFIG_MEMSTICK is not set
@@ -1939,8 +1975,10 @@ CONFIG_LEDS_CLASS=y
 #
 # CONFIG_LEDS_ALIX2 is not set
 # CONFIG_LEDS_PCA9532 is not set
+# CONFIG_LEDS_LP5521 is not set
 # CONFIG_LEDS_CLEVO_MAIL is not set
 # CONFIG_LEDS_PCA955X is not set
+# CONFIG_LEDS_BD2802 is not set
 
 #
 # LED Triggers
@@ -1950,6 +1988,10 @@ CONFIG_LEDS_TRIGGERS=y
 # CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
 # CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
 # CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set
+
+#
+# iptables trigger is under Netfilter config (LED target)
+#
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
 CONFIG_EDAC=y
@@ -2018,6 +2060,7 @@ CONFIG_DMADEVICES=y
 # DMA Devices
 #
 # CONFIG_INTEL_IOATDMA is not set
+# CONFIG_AUXDISPLAY is not set
 # CONFIG_UIO is not set
 # CONFIG_STAGING is not set
 CONFIG_X86_PLATFORM_DEVICES=y
@@ -2051,6 +2094,7 @@ CONFIG_DMIID=y
 #
 # CONFIG_EXT2_FS is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
@@ -2081,6 +2125,11 @@ CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
 CONFIG_GENERIC_ACL=y
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -2132,6 +2181,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
+# CONFIG_NILFS2_FS is not set
 CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -2145,7 +2195,6 @@ CONFIG_NFS_ACL_SUPPORT=y
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=y
 CONFIG_SUNRPC_GSS=y
-# CONFIG_SUNRPC_REGISTER_V4 is not set
 CONFIG_RPCSEC_GSS_KRB5=y
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
@@ -2232,6 +2281,7 @@ CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 # CONFIG_DETECT_SOFTLOCKUP is not set
+# CONFIG_DETECT_HUNG_TASK is not set
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
@@ -2247,6 +2297,7 @@ CONFIG_TIMER_STATS=y
 # CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
 # CONFIG_DEBUG_KOBJECT is not set
 CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_INFO is not set
@@ -2269,13 +2320,19 @@ CONFIG_FRAME_POINTER=y
 # CONFIG_FAULT_INJECTION is not set
 # CONFIG_LATENCYTOP is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
+# CONFIG_DEBUG_PAGEALLOC is not set
 CONFIG_USER_STACKTRACE_SUPPORT=y
+CONFIG_NOP_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_HAVE_HW_BRANCH_TRACER=y
+CONFIG_HAVE_FTRACE_SYSCALLS=y
+CONFIG_RING_BUFFER=y
+CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
 
 #
 # Tracers
@@ -2285,13 +2342,21 @@ CONFIG_HAVE_HW_BRANCH_TRACER=y
 # CONFIG_SYSPROF_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
 # CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_EVENT_TRACER is not set
+# CONFIG_FTRACE_SYSCALLS is not set
 # CONFIG_BOOT_TRACER is not set
 # CONFIG_TRACE_BRANCH_PROFILING is not set
 # CONFIG_POWER_TRACER is not set
 # CONFIG_STACK_TRACER is not set
 # CONFIG_HW_BRANCH_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+CONFIG_BLK_DEV_IO_TRACE=y
+# CONFIG_FTRACE_STARTUP_TEST is not set
+# CONFIG_MMIOTRACE is not set
 CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
-# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
+# CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
 # CONFIG_KGDB is not set
@@ -2301,14 +2366,13 @@ CONFIG_EARLY_PRINTK=y
 CONFIG_EARLY_PRINTK_DBGP=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DEBUG_STACK_USAGE=y
-# CONFIG_DEBUG_PAGEALLOC is not set
 # CONFIG_DEBUG_PER_CPU_MAPS is not set
 # CONFIG_X86_PTDUMP is not set
 CONFIG_DEBUG_RODATA=y
 # CONFIG_DEBUG_RODATA_TEST is not set
 CONFIG_DEBUG_NX_TEST=m
 # CONFIG_IOMMU_DEBUG is not set
-# CONFIG_MMIOTRACE is not set
+CONFIG_HAVE_MMIOTRACE_SUPPORT=y
 CONFIG_IO_DELAY_TYPE_0X80=0
 CONFIG_IO_DELAY_TYPE_0XED=1
 CONFIG_IO_DELAY_TYPE_UDELAY=2
@@ -2344,6 +2408,8 @@ CONFIG_SECURITY_SELINUX_AVC_STATS=y
 CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
 # CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
 # CONFIG_SECURITY_SMACK is not set
+# CONFIG_SECURITY_TOMOYO is not set
+# CONFIG_IMA is not set
 CONFIG_CRYPTO=y
 
 #
@@ -2359,10 +2425,12 @@ CONFIG_CRYPTO_BLKCIPHER2=y
 CONFIG_CRYPTO_HASH=y
 CONFIG_CRYPTO_HASH2=y
 CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP=y
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_MANAGER2=y
 # CONFIG_CRYPTO_GF128MUL is not set
 # CONFIG_CRYPTO_NULL is not set
+CONFIG_CRYPTO_WORKQUEUE=y
 # CONFIG_CRYPTO_CRYPTD is not set
 CONFIG_CRYPTO_AUTHENC=y
 # CONFIG_CRYPTO_TEST is not set
@@ -2414,6 +2482,7 @@ CONFIG_CRYPTO_SHA1=y
 #
 CONFIG_CRYPTO_AES=y
 # CONFIG_CRYPTO_AES_X86_64 is not set
+# CONFIG_CRYPTO_AES_NI_INTEL is not set
 # CONFIG_CRYPTO_ANUBIS is not set
 CONFIG_CRYPTO_ARC4=y
 # CONFIG_CRYPTO_BLOWFISH is not set
@@ -2435,6 +2504,7 @@ CONFIG_CRYPTO_DES=y
 # Compression
 #
 # CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
 # CONFIG_CRYPTO_LZO is not set
 
 #
@@ -2444,10 +2514,12 @@ CONFIG_CRYPTO_DES=y
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
 CONFIG_HAVE_KVM=y
+CONFIG_HAVE_KVM_IRQCHIP=y
 CONFIG_VIRTUALIZATION=y
 # CONFIG_KVM is not set
 # CONFIG_VIRTIO_PCI is not set
 # CONFIG_VIRTIO_BALLOON is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
@@ -2464,7 +2536,10 @@ CONFIG_CRC32=y
 # CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=y
-CONFIG_PLIST=y
+CONFIG_DECOMPRESS_GZIP=y
+CONFIG_DECOMPRESS_BZIP2=y
+CONFIG_DECOMPRESS_LZMA=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
 CONFIG_HAS_DMA=y
+CONFIG_NLATTR=y
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index a505202086e8..e590261ba059 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -825,9 +825,11 @@ ia32_sys_call_table:
 	.quad compat_sys_signalfd4
 	.quad sys_eventfd2
 	.quad sys_epoll_create1
-	.quad sys_dup3			/* 330 */
+	.quad sys_dup3				/* 330 */
 	.quad sys_pipe2
 	.quad sys_inotify_init1
 	.quad compat_sys_preadv
 	.quad compat_sys_pwritev
+	.quad compat_sys_rt_tgsigqueueinfo	/* 335 */
+	.quad sys_perf_counter_open
 ia32_syscall_end:
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index f6aa18eadf71..1a37bcdc8606 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/stddef.h>
+#include <linux/stringify.h>
 #include <asm/asm.h>
 
 /*
@@ -74,6 +75,22 @@ static inline void alternatives_smp_switch(int smp) {}
 
 const unsigned char *const *find_nop_table(void);
 
+/* alternative assembly primitive: */
+#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+									\
+      "661:\n\t" oldinstr "\n662:\n"					\
+      ".section .altinstructions,\"a\"\n"				\
+      _ASM_ALIGN "\n"							\
+      _ASM_PTR "661b\n"				/* label           */	\
+      _ASM_PTR "663f\n"				/* new instruction */	\
+      "	 .byte " __stringify(feature) "\n"	/* feature bit     */	\
+      "	 .byte 662b-661b\n"			/* sourcelen       */	\
+      "	 .byte 664f-663f\n"			/* replacementlen  */	\
+      ".previous\n"							\
+      ".section .altinstr_replacement, \"ax\"\n"			\
+      "663:\n\t" newinstr "\n664:\n"		/* replacement     */	\
+      ".previous"
+
 /*
  * Alternative instructions for different CPU types or capabilities.
  *
@@ -87,18 +104,7 @@ const unsigned char *const *find_nop_table(void);
  * without volatile and memory clobber.
  */
 #define alternative(oldinstr, newinstr, feature)			\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c0\n"		/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
-		      ".previous" :: "i" (feature) : "memory")
+	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory")
 
 /*
  * Alternative inline assembly with input.
@@ -109,35 +115,16 @@ const unsigned char *const *find_nop_table(void);
  * Best is to use constraints that are fixed size (like (%1) ... "r")
  * If you use variable sized constraints like "m" or "g" in the
  * replacement make sure to pad to the worst case length.
+ * Leaving an unused argument 0 to keep API compatibility.
  */
 #define alternative_input(oldinstr, newinstr, feature, input...)	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c0\n"		/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
-		      ".previous" :: "i" (feature), ##input)
+	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\
+		: : "i" (0), ## input)
 
 /* Like alternative_input, but with a single output argument */
 #define alternative_io(oldinstr, newinstr, feature, output, input...)	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c[feat]\n"	/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */ \
-		      ".previous" : output : [feat] "i" (feature), ##input)
+	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\
+		: output : "i" (0), ## input)
 
 /*
  * use this macro(s) if you need more than one output parameter
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index f712344329bc..262e02820049 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -27,6 +27,8 @@ extern int amd_iommu_init(void);
 extern int amd_iommu_init_dma_ops(void);
 extern void amd_iommu_detect(void);
 extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
+extern void amd_iommu_flush_all_domains(void);
+extern void amd_iommu_flush_all_devices(void);
 #else
 static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 95c8cd9d22b5..0c878caaa0a2 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -194,6 +194,27 @@
 #define PD_DMA_OPS_MASK		(1UL << 0) /* domain used for dma_ops */
 #define PD_DEFAULT_MASK		(1UL << 1) /* domain is a default dma_ops
 					      domain for an IOMMU */
+extern bool amd_iommu_dump;
+#define DUMP_printk(format, arg...)					\
+	do {								\
+		if (amd_iommu_dump)						\
+			printk(KERN_INFO "AMD IOMMU: " format, ## arg);	\
+	} while(0);
+
+/*
+ * Make iterating over all IOMMUs easier
+ */
+#define for_each_iommu(iommu) \
+	list_for_each_entry((iommu), &amd_iommu_list, list)
+#define for_each_iommu_safe(iommu, next) \
+	list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list)
+
+#define APERTURE_RANGE_SHIFT	27	/* 128 MB */
+#define APERTURE_RANGE_SIZE	(1ULL << APERTURE_RANGE_SHIFT)
+#define APERTURE_RANGE_PAGES	(APERTURE_RANGE_SIZE >> PAGE_SHIFT)
+#define APERTURE_MAX_RANGES	32	/* allows 4GB of DMA address space */
+#define APERTURE_RANGE_INDEX(a)	((a) >> APERTURE_RANGE_SHIFT)
+#define APERTURE_PAGE_INDEX(a)	(((a) >> 21) & 0x3fULL)
 
 /*
  * This structure contains generic data for  IOMMU protection domains
@@ -209,6 +230,26 @@ struct protection_domain {
 	void *priv;		/* private data */
 };
 
+/*
+ * For dynamic growth the aperture size is split into ranges of 128MB of
+ * DMA address space each. This struct represents one such range.
+ */
+struct aperture_range {
+
+	/* address allocation bitmap */
+	unsigned long *bitmap;
+
+	/*
+	 * Array of PTE pages for the aperture. In this array we save all the
+	 * leaf pages of the domain page table used for the aperture. This way
+	 * we don't need to walk the page table to find a specific PTE. We can
+	 * just calculate its address in constant time.
+	 */
+	u64 *pte_pages[64];
+
+	unsigned long offset;
+};
+
 /*
  * Data container for a dma_ops specific protection domain
  */
@@ -222,18 +263,10 @@ struct dma_ops_domain {
 	unsigned long aperture_size;
 
 	/* address we start to search for free addresses */
-	unsigned long next_bit;
+	unsigned long next_address;
 
-	/* address allocation bitmap */
-	unsigned long *bitmap;
-
-	/*
-	 * Array of PTE pages for the aperture. In this array we save all the
-	 * leaf pages of the domain page table used for the aperture. This way
-	 * we don't need to walk the page table to find a specific PTE. We can
-	 * just calculate its address in constant time.
-	 */
-	u64 **pte_pages;
+	/* address space relevant data */
+	struct aperture_range *aperture[APERTURE_MAX_RANGES];
 
 	/* This will be set to true when TLB needs to be flushed */
 	bool need_flush;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 42f2f8377422..bb7d47925847 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -107,8 +107,7 @@ extern u32 native_safe_apic_wait_icr_idle(void);
 extern void native_apic_icr_write(u32 low, u32 id);
 extern u64 native_apic_icr_read(void);
 
-#define EIM_8BIT_APIC_ID	0
-#define EIM_32BIT_APIC_ID	1
+extern int x2apic_mode;
 
 #ifdef CONFIG_X86_X2APIC
 /*
@@ -166,10 +165,9 @@ static inline u64 native_x2apic_icr_read(void)
 	return val;
 }
 
-extern int x2apic, x2apic_phys;
+extern int x2apic_phys;
 extern void check_x2apic(void);
 extern void enable_x2apic(void);
-extern void enable_IR_x2apic(void);
 extern void x2apic_icr_write(u32 low, u32 id);
 static inline int x2apic_enabled(void)
 {
@@ -183,6 +181,8 @@ static inline int x2apic_enabled(void)
 		return 1;
 	return 0;
 }
+
+#define x2apic_supported()	(cpu_has_x2apic)
 #else
 static inline void check_x2apic(void)
 {
@@ -190,28 +190,20 @@ static inline void check_x2apic(void)
 static inline void enable_x2apic(void)
 {
 }
-static inline void enable_IR_x2apic(void)
-{
-}
 static inline int x2apic_enabled(void)
 {
 	return 0;
 }
 
-#define	x2apic	0
-
+#define	x2apic_preenabled 0
+#define	x2apic_supported()	0
 #endif
 
+extern void enable_IR_x2apic(void);
+
 extern int get_physical_broadcast(void);
 
-#ifdef CONFIG_X86_X2APIC
-static inline void ack_x2APIC_irq(void)
-{
-	/* Docs say use 0 for future compatibility */
-	native_apic_msr_write(APIC_EOI, 0);
-}
-#endif
-
+extern void apic_disable(void);
 extern int lapic_get_maxlvt(void);
 extern void clear_local_APIC(void);
 extern void connect_bsp_APIC(void);
@@ -252,7 +244,7 @@ static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok		1
 static inline void init_apic_mappings(void) { }
 static inline void disable_local_APIC(void) { }
-
+static inline void apic_disable(void) { }
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_64
@@ -410,7 +402,7 @@ static inline unsigned default_get_apic_id(unsigned long x)
 {
 	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
 
-	if (APIC_XAPIC(ver))
+	if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID))
 		return (x >> 24) & 0xFF;
 	else
 		return (x >> 24) & 0x0F;
@@ -478,6 +470,9 @@ static inline unsigned int read_apic_id(void)
 extern void default_setup_apic_routing(void);
 
 #ifdef CONFIG_X86_32
+
+extern struct apic apic_default;
+
 /*
  * Set up the logical destination ID.
  *
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index bc9514fb3b13..7ddb36ab933b 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -22,6 +22,7 @@
 #  define	APIC_INTEGRATED(x)	(1)
 #endif
 #define		APIC_XAPIC(x)		((x) >= 0x14)
+#define		APIC_EXT_SPACE(x)	((x) & 0x80000000)
 #define	APIC_TASKPRI	0x80
 #define		APIC_TPRI_MASK		0xFFu
 #define	APIC_ARBPRI	0x90
@@ -116,7 +117,9 @@
 #define		APIC_TDR_DIV_32		0x8
 #define		APIC_TDR_DIV_64		0x9
 #define		APIC_TDR_DIV_128	0xA
-#define	APIC_EILVT0     0x500
+#define	APIC_EFEAT	0x400
+#define	APIC_ECTRL	0x410
+#define APIC_EILVTn(n)	(0x500 + 0x10 * n)
 #define		APIC_EILVT_NR_AMD_K8	1	/* # of extended interrupts */
 #define		APIC_EILVT_NR_AMD_10H	4
 #define		APIC_EILVT_LVTOFF(x)	(((x) >> 4) & 0xF)
@@ -125,9 +128,6 @@
 #define		APIC_EILVT_MSG_NMI	0x4
 #define		APIC_EILVT_MSG_EXT	0x7
 #define		APIC_EILVT_MASKED	(1 << 16)
-#define	APIC_EILVT1     0x510
-#define	APIC_EILVT2     0x520
-#define	APIC_EILVT3     0x530
 
 #define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
 #define APIC_BASE_MSR	0x800
diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h
index c83d31486081..8cb9c814e120 100644
--- a/arch/x86/include/asm/atomic_32.h
+++ b/arch/x86/include/asm/atomic_32.h
@@ -247,5 +247,241 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 #define smp_mb__before_atomic_inc()	barrier()
 #define smp_mb__after_atomic_inc()	barrier()
 
+/* An 64bit atomic type */
+
+typedef struct {
+	unsigned long long counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(val)	{ (val) }
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically reads the value of @v.
+ * Doesn't imply a read memory barrier.
+ */
+#define __atomic64_read(ptr)		((ptr)->counter)
+
+static inline unsigned long long
+cmpxchg8b(unsigned long long *ptr, unsigned long long old, unsigned long long new)
+{
+	asm volatile(
+
+		LOCK_PREFIX "cmpxchg8b (%[ptr])\n"
+
+		     :		"=A" (old)
+
+		     : [ptr]	"D" (ptr),
+				"A" (old),
+				"b" (ll_low(new)),
+				"c" (ll_high(new))
+
+		     : "memory");
+
+	return old;
+}
+
+static inline unsigned long long
+atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val,
+		 unsigned long long new_val)
+{
+	return cmpxchg8b(&ptr->counter, old_val, new_val);
+}
+
+/**
+ * atomic64_xchg - xchg atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ * @new_val:  value to assign
+ * @old_val:  old value that was there
+ *
+ * Atomically xchgs the value of @ptr to @new_val and returns
+ * the old value.
+ */
+
+static inline unsigned long long
+atomic64_xchg(atomic64_t *ptr, unsigned long long new_val)
+{
+	unsigned long long old_val;
+
+	do {
+		old_val = atomic_read(ptr);
+	} while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
+
+	return old_val;
+}
+
+/**
+ * atomic64_set - set atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ * @new_val:  value to assign
+ *
+ * Atomically sets the value of @ptr to @new_val.
+ */
+static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val)
+{
+	atomic64_xchg(ptr, new_val);
+}
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ *
+ * Atomically reads the value of @ptr and returns it.
+ */
+static inline unsigned long long atomic64_read(atomic64_t *ptr)
+{
+	unsigned long long curr_val;
+
+	do {
+		curr_val = __atomic64_read(ptr);
+	} while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val);
+
+	return curr_val;
+}
+
+/**
+ * atomic64_add_return - add and return
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr and returns @delta + *@ptr
+ */
+static inline unsigned long long
+atomic64_add_return(unsigned long long delta, atomic64_t *ptr)
+{
+	unsigned long long old_val, new_val;
+
+	do {
+		old_val = atomic_read(ptr);
+		new_val = old_val + delta;
+
+	} while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
+
+	return new_val;
+}
+
+static inline long atomic64_sub_return(unsigned long long delta, atomic64_t *ptr)
+{
+	return atomic64_add_return(-delta, ptr);
+}
+
+static inline long atomic64_inc_return(atomic64_t *ptr)
+{
+	return atomic64_add_return(1, ptr);
+}
+
+static inline long atomic64_dec_return(atomic64_t *ptr)
+{
+	return atomic64_sub_return(1, ptr);
+}
+
+/**
+ * atomic64_add - add integer to atomic64 variable
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr.
+ */
+static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr)
+{
+	atomic64_add_return(delta, ptr);
+}
+
+/**
+ * atomic64_sub - subtract the atomic64 variable
+ * @delta: integer value to subtract
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically subtracts @delta from @ptr.
+ */
+static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr)
+{
+	atomic64_add(-delta, ptr);
+}
+
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @delta: integer value to subtract
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically subtracts @delta from @ptr and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int
+atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr)
+{
+	unsigned long long old_val = atomic64_sub_return(delta, ptr);
+
+	return old_val == 0;
+}
+
+/**
+ * atomic64_inc - increment atomic64 variable
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically increments @ptr by 1.
+ */
+static inline void atomic64_inc(atomic64_t *ptr)
+{
+	atomic64_add(1, ptr);
+}
+
+/**
+ * atomic64_dec - decrement atomic64 variable
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically decrements @ptr by 1.
+ */
+static inline void atomic64_dec(atomic64_t *ptr)
+{
+	atomic64_sub(1, ptr);
+}
+
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically decrements @ptr by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic64_dec_and_test(atomic64_t *ptr)
+{
+	return atomic64_sub_and_test(1, ptr);
+}
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically increments @ptr by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_inc_and_test(atomic64_t *ptr)
+{
+	return atomic64_sub_and_test(-1, ptr);
+}
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int
+atomic64_add_negative(unsigned long long delta, atomic64_t *ptr)
+{
+	long long old_val = atomic64_add_return(delta, ptr);
+
+	return old_val < 0;
+}
+
 #include <asm-generic/atomic-long.h>
 #endif /* _ASM_X86_ATOMIC_32_H */
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 6ba23dd9fc92..418e632d4a80 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -8,11 +8,26 @@
 
 #ifdef __KERNEL__
 
+#include <asm/page_types.h>
+
 /* Physical address where kernel should be loaded. */
 #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
 				+ (CONFIG_PHYSICAL_ALIGN - 1)) \
 				& ~(CONFIG_PHYSICAL_ALIGN - 1))
 
+/* Minimum kernel alignment, as a power of two */
+#ifdef CONFIG_x86_64
+#define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
+#else
+#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT+1)
+#endif
+#define MIN_KERNEL_ALIGN	(_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
+
+#if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \
+	(CONFIG_PHYSICAL_ALIGN < (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2))
+#error "Invalid value for CONFIG_PHYSICAL_ALIGN"
+#endif
+
 #ifdef CONFIG_KERNEL_BZIP2
 #define BOOT_HEAP_SIZE             0x400000
 #else /* !CONFIG_KERNEL_BZIP2 */
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 433adaebf9b6..1724e8de317c 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -50,7 +50,8 @@ struct setup_header {
 	__u32	ramdisk_size;
 	__u32	bootsect_kludge;
 	__u16	heap_end_ptr;
-	__u16	_pad1;
+	__u8	ext_loader_ver;
+	__u8	ext_loader_type;
 	__u32	cmd_line_ptr;
 	__u32	initrd_addr_max;
 	__u32	kernel_alignment;
diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h
index 222802029fa6..d96c1ee3a95c 100644
--- a/arch/x86/include/asm/cpu_debug.h
+++ b/arch/x86/include/asm/cpu_debug.h
@@ -86,105 +86,7 @@ enum cpu_file_bit {
 	CPU_VALUE_BIT,				/* value		*/
 };
 
-#define	CPU_FILE_VALUE			(1 << CPU_VALUE_BIT)
-
-/*
- * DisplayFamily_DisplayModel	Processor Families/Processor Number Series
- * --------------------------	------------------------------------------
- * 05_01, 05_02, 05_04		Pentium, Pentium with MMX
- *
- * 06_01			Pentium Pro
- * 06_03, 06_05			Pentium II Xeon, Pentium II
- * 06_07, 06_08, 06_0A, 06_0B	Pentium III Xeon, Pentum III
- *
- * 06_09, 060D			Pentium M
- *
- * 06_0E			Core Duo, Core Solo
- *
- * 06_0F			Xeon 3000, 3200, 5100, 5300, 7300 series,
- *				Core 2 Quad, Core 2 Extreme, Core 2 Duo,
- *				Pentium dual-core
- * 06_17			Xeon 5200, 5400 series, Core 2 Quad Q9650
- *
- * 06_1C			Atom
- *
- * 0F_00, 0F_01, 0F_02		Xeon, Xeon MP, Pentium 4
- * 0F_03, 0F_04			Xeon, Xeon MP, Pentium 4, Pentium D
- *
- * 0F_06			Xeon 7100, 5000 Series, Xeon MP,
- *				Pentium 4, Pentium D
- */
-
-/* Register processors bits */
-enum cpu_processor_bit {
-	CPU_NONE,
-/* Intel */
-	CPU_INTEL_PENTIUM_BIT,
-	CPU_INTEL_P6_BIT,
-	CPU_INTEL_PENTIUM_M_BIT,
-	CPU_INTEL_CORE_BIT,
-	CPU_INTEL_CORE2_BIT,
-	CPU_INTEL_ATOM_BIT,
-	CPU_INTEL_XEON_P4_BIT,
-	CPU_INTEL_XEON_MP_BIT,
-/* AMD */
-	CPU_AMD_K6_BIT,
-	CPU_AMD_K7_BIT,
-	CPU_AMD_K8_BIT,
-	CPU_AMD_0F_BIT,
-	CPU_AMD_10_BIT,
-	CPU_AMD_11_BIT,
-};
-
-#define	CPU_INTEL_PENTIUM	(1 << CPU_INTEL_PENTIUM_BIT)
-#define	CPU_INTEL_P6		(1 << CPU_INTEL_P6_BIT)
-#define	CPU_INTEL_PENTIUM_M	(1 << CPU_INTEL_PENTIUM_M_BIT)
-#define	CPU_INTEL_CORE		(1 << CPU_INTEL_CORE_BIT)
-#define	CPU_INTEL_CORE2		(1 << CPU_INTEL_CORE2_BIT)
-#define	CPU_INTEL_ATOM		(1 << CPU_INTEL_ATOM_BIT)
-#define	CPU_INTEL_XEON_P4	(1 << CPU_INTEL_XEON_P4_BIT)
-#define	CPU_INTEL_XEON_MP	(1 << CPU_INTEL_XEON_MP_BIT)
-
-#define	CPU_INTEL_PX		(CPU_INTEL_P6 | CPU_INTEL_PENTIUM_M)
-#define	CPU_INTEL_COREX		(CPU_INTEL_CORE | CPU_INTEL_CORE2)
-#define	CPU_INTEL_XEON		(CPU_INTEL_XEON_P4 | CPU_INTEL_XEON_MP)
-#define	CPU_CO_AT		(CPU_INTEL_CORE | CPU_INTEL_ATOM)
-#define	CPU_C2_AT		(CPU_INTEL_CORE2 | CPU_INTEL_ATOM)
-#define	CPU_CX_AT		(CPU_INTEL_COREX | CPU_INTEL_ATOM)
-#define	CPU_CX_XE		(CPU_INTEL_COREX | CPU_INTEL_XEON)
-#define	CPU_P6_XE		(CPU_INTEL_P6 | CPU_INTEL_XEON)
-#define	CPU_PM_CO_AT		(CPU_INTEL_PENTIUM_M | CPU_CO_AT)
-#define	CPU_C2_AT_XE		(CPU_C2_AT | CPU_INTEL_XEON)
-#define	CPU_CX_AT_XE		(CPU_CX_AT | CPU_INTEL_XEON)
-#define	CPU_P6_CX_AT		(CPU_INTEL_P6 | CPU_CX_AT)
-#define	CPU_P6_CX_XE		(CPU_P6_XE | CPU_INTEL_COREX)
-#define	CPU_P6_CX_AT_XE		(CPU_INTEL_P6 | CPU_CX_AT_XE)
-#define	CPU_PM_CX_AT_XE		(CPU_INTEL_PENTIUM_M | CPU_CX_AT_XE)
-#define	CPU_PM_CX_AT		(CPU_INTEL_PENTIUM_M | CPU_CX_AT)
-#define	CPU_PM_CX_XE		(CPU_INTEL_PENTIUM_M | CPU_CX_XE)
-#define	CPU_PX_CX_AT		(CPU_INTEL_PX | CPU_CX_AT)
-#define	CPU_PX_CX_AT_XE		(CPU_INTEL_PX | CPU_CX_AT_XE)
-
-/* Select all supported Intel CPUs */
-#define	CPU_INTEL_ALL		(CPU_INTEL_PENTIUM | CPU_PX_CX_AT_XE)
-
-#define	CPU_AMD_K6		(1 << CPU_AMD_K6_BIT)
-#define	CPU_AMD_K7		(1 << CPU_AMD_K7_BIT)
-#define	CPU_AMD_K8		(1 << CPU_AMD_K8_BIT)
-#define	CPU_AMD_0F		(1 << CPU_AMD_0F_BIT)
-#define	CPU_AMD_10		(1 << CPU_AMD_10_BIT)
-#define	CPU_AMD_11		(1 << CPU_AMD_11_BIT)
-
-#define	CPU_K10_PLUS		(CPU_AMD_10 | CPU_AMD_11)
-#define	CPU_K0F_PLUS		(CPU_AMD_0F | CPU_K10_PLUS)
-#define	CPU_K8_PLUS		(CPU_AMD_K8 | CPU_K0F_PLUS)
-#define	CPU_K7_PLUS		(CPU_AMD_K7 | CPU_K8_PLUS)
-
-/* Select all supported AMD CPUs */
-#define	CPU_AMD_ALL		(CPU_AMD_K6 | CPU_K7_PLUS)
-
-/* Select all supported CPUs */
-#define	CPU_ALL			(CPU_INTEL_ALL | CPU_AMD_ALL)
+#define	CPU_FILE_VALUE		(1 << CPU_VALUE_BIT)
 
 #define MAX_CPU_FILES		512
 
@@ -220,7 +122,6 @@ struct cpu_debug_range {
 	unsigned		min;		/* Register range min	*/
 	unsigned		max;		/* Register range max	*/
 	unsigned		flag;		/* Supported flags	*/
-	unsigned		model;		/* Supported models	*/
 };
 
 #endif /* _ASM_X86_CPU_DEBUG_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index bb83b1c397aa..4a28d22d4793 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -22,7 +22,7 @@
 #define X86_FEATURE_TSC		(0*32+ 4) /* Time Stamp Counter */
 #define X86_FEATURE_MSR		(0*32+ 5) /* Model-Specific Registers */
 #define X86_FEATURE_PAE		(0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Architecture */
+#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Exception */
 #define X86_FEATURE_CX8		(0*32+ 8) /* CMPXCHG8 instruction */
 #define X86_FEATURE_APIC	(0*32+ 9) /* Onboard APIC */
 #define X86_FEATURE_SEP		(0*32+11) /* SYSENTER/SYSEXIT */
@@ -94,6 +94,7 @@
 #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
 #define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
@@ -115,6 +116,8 @@
 #define X86_FEATURE_XMM4_1	(4*32+19) /* "sse4_1" SSE-4.1 */
 #define X86_FEATURE_XMM4_2	(4*32+20) /* "sse4_2" SSE-4.2 */
 #define X86_FEATURE_X2APIC	(4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE	(4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT      (4*32+23) /* POPCNT instruction */
 #define X86_FEATURE_AES		(4*32+25) /* AES instructions */
 #define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
 #define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
@@ -192,11 +195,11 @@ extern const char * const x86_power_flags[32];
 #define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
 #define setup_clear_cpu_cap(bit) do { \
 	clear_cpu_cap(&boot_cpu_data, bit);	\
-	set_bit(bit, (unsigned long *)cleared_cpu_caps); \
+	set_bit(bit, (unsigned long *)cpu_caps_cleared); \
 } while (0)
 #define setup_force_cpu_cap(bit) do { \
 	set_cpu_cap(&boot_cpu_data, bit);	\
-	clear_bit(bit, (unsigned long *)cleared_cpu_caps);	\
+	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
index a8f672ba100c..70dac199b093 100644
--- a/arch/x86/include/asm/ds.h
+++ b/arch/x86/include/asm/ds.h
@@ -15,8 +15,8 @@
  * - buffer allocation (memory accounting)
  *
  *
- * Copyright (C) 2007-2008 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
+ * Copyright (C) 2007-2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
  */
 
 #ifndef _ASM_X86_DS_H
@@ -83,8 +83,10 @@ enum ds_feature {
  * The interrupt threshold is independent from the overflow callback
  * to allow users to use their own overflow interrupt handling mechanism.
  *
- * task: the task to request recording for;
- *       NULL for per-cpu recording on the current cpu
+ * The function might sleep.
+ *
+ * task: the task to request recording for
+ * cpu:  the cpu to request recording for
  * base: the base pointer for the (non-pageable) buffer;
  * size: the size of the provided buffer in bytes
  * ovfl: pointer to a function to be called on buffer overflow;
@@ -93,19 +95,28 @@ enum ds_feature {
  *     -1 if no interrupt threshold is requested.
  * flags: a bit-mask of the above flags
  */
-extern struct bts_tracer *ds_request_bts(struct task_struct *task,
-					 void *base, size_t size,
-					 bts_ovfl_callback_t ovfl,
-					 size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs(struct task_struct *task,
-					   void *base, size_t size,
-					   pebs_ovfl_callback_t ovfl,
-					   size_t th, unsigned int flags);
+extern struct bts_tracer *ds_request_bts_task(struct task_struct *task,
+					      void *base, size_t size,
+					      bts_ovfl_callback_t ovfl,
+					      size_t th, unsigned int flags);
+extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
+					     bts_ovfl_callback_t ovfl,
+					     size_t th, unsigned int flags);
+extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
+						void *base, size_t size,
+						pebs_ovfl_callback_t ovfl,
+						size_t th, unsigned int flags);
+extern struct pebs_tracer *ds_request_pebs_cpu(int cpu,
+					       void *base, size_t size,
+					       pebs_ovfl_callback_t ovfl,
+					       size_t th, unsigned int flags);
 
 /*
  * Release BTS or PEBS resources
  * Suspend and resume BTS or PEBS tracing
  *
+ * Must be called with irq's enabled.
+ *
  * tracer: the tracer handle returned from ds_request_~()
  */
 extern void ds_release_bts(struct bts_tracer *tracer);
@@ -115,6 +126,28 @@ extern void ds_release_pebs(struct pebs_tracer *tracer);
 extern void ds_suspend_pebs(struct pebs_tracer *tracer);
 extern void ds_resume_pebs(struct pebs_tracer *tracer);
 
+/*
+ * Release BTS or PEBS resources
+ * Suspend and resume BTS or PEBS tracing
+ *
+ * Cpu tracers must call this on the traced cpu.
+ * Task tracers must call ds_release_~_noirq() for themselves.
+ *
+ * May be called with irq's disabled.
+ *
+ * Returns 0 if successful;
+ * -EPERM if the cpu tracer does not trace the current cpu.
+ * -EPERM if the task tracer does not trace itself.
+ *
+ * tracer: the tracer handle returned from ds_request_~()
+ */
+extern int ds_release_bts_noirq(struct bts_tracer *tracer);
+extern int ds_suspend_bts_noirq(struct bts_tracer *tracer);
+extern int ds_resume_bts_noirq(struct bts_tracer *tracer);
+extern int ds_release_pebs_noirq(struct pebs_tracer *tracer);
+extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer);
+extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer);
+
 
 /*
  * The raw DS buffer state as it is used for BTS and PEBS recording.
@@ -170,9 +203,9 @@ struct bts_struct {
 		} lbr;
 		/* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
 		struct {
-			__u64 jiffies;
+			__u64 clock;
 			pid_t pid;
-		} timestamp;
+		} event;
 	} variant;
 };
 
@@ -201,8 +234,12 @@ struct bts_trace {
 struct pebs_trace {
 	struct ds_trace ds;
 
-	/* the PEBS reset value */
-	unsigned long long reset_value;
+	/* the number of valid counters in the below array */
+	unsigned int counters;
+
+#define MAX_PEBS_COUNTERS 4
+	/* the counter reset value */
+	unsigned long long counter_reset[MAX_PEBS_COUNTERS];
 };
 
 
@@ -237,9 +274,11 @@ extern int ds_reset_pebs(struct pebs_tracer *tracer);
  * Returns 0 on success; -Eerrno on error
  *
  * tracer: the tracer handle returned from ds_request_pebs()
+ * counter: the index of the counter
  * value: the new counter reset value
  */
-extern int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value);
+extern int ds_set_pebs_reset(struct pebs_tracer *tracer,
+			     unsigned int counter, u64 value);
 
 /*
  * Initialization
@@ -252,21 +291,12 @@ extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
  */
 extern void ds_switch_to(struct task_struct *prev, struct task_struct *next);
 
-/*
- * Task clone/init and cleanup work
- */
-extern void ds_copy_thread(struct task_struct *tsk, struct task_struct *father);
-extern void ds_exit_thread(struct task_struct *tsk);
-
 #else /* CONFIG_X86_DS */
 
 struct cpuinfo_x86;
 static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
 static inline void ds_switch_to(struct task_struct *prev,
 				struct task_struct *next) {}
-static inline void ds_copy_thread(struct task_struct *tsk,
-				  struct task_struct *father) {}
-static inline void ds_exit_thread(struct task_struct *tsk) {}
 
 #endif /* CONFIG_X86_DS */
 #endif /* _ASM_X86_DS_H */
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index c2e6bedaf258..d750a10ccad6 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -49,7 +49,7 @@ BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
 BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 
 #ifdef CONFIG_PERF_COUNTERS
-BUILD_INTERRUPT(perf_counter_interrupt, LOCAL_PERF_VECTOR)
+BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR)
 #endif
 
 #ifdef CONFIG_X86_MCE_P4THERMAL
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 37555e52f980..9ebc5c255032 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -13,6 +13,8 @@ typedef struct {
 	unsigned int irq_spurious_count;
 #endif
 	unsigned int generic_irqs;	/* arch dependent */
+	unsigned int apic_perf_irqs;
+	unsigned int apic_pending_irqs;
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b762ea49bd70..6df45f639666 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -29,6 +29,8 @@
 extern void apic_timer_interrupt(void);
 extern void generic_interrupt(void);
 extern void error_interrupt(void);
+extern void perf_pending_interrupt(void);
+
 extern void spurious_interrupt(void);
 extern void thermal_interrupt(void);
 extern void reschedule_interrupt(void);
@@ -63,7 +65,26 @@ extern unsigned long io_apic_irqs;
 extern void init_VISWS_APIC_irqs(void);
 extern void setup_IO_APIC(void);
 extern void disable_IO_APIC(void);
-extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
+
+struct io_apic_irq_attr {
+	int ioapic;
+	int ioapic_pin;
+	int trigger;
+	int polarity;
+};
+
+static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
+					int ioapic, int ioapic_pin,
+					int trigger, int polarity)
+{
+	irq_attr->ioapic     = ioapic;
+	irq_attr->ioapic_pin = ioapic_pin;
+	irq_attr->trigger    = trigger;
+	irq_attr->polarity   = polarity;
+}
+
+extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin,
+					struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 
 extern void enable_IO_APIC(void);
@@ -78,7 +99,11 @@ extern void eisa_set_level_irq(unsigned int irq);
 /* SMP */
 extern void smp_apic_timer_interrupt(struct pt_regs *);
 extern void smp_spurious_interrupt(struct pt_regs *);
+extern void smp_generic_interrupt(struct pt_regs *);
 extern void smp_error_interrupt(struct pt_regs *);
+#ifdef CONFIG_X86_IO_APIC
+extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
+#endif
 #ifdef CONFIG_SMP
 extern void smp_reschedule_interrupt(struct pt_regs *);
 extern void smp_call_function_interrupt(struct pt_regs *);
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 71c9e5183982..175adf58dd4f 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -67,7 +67,7 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 		     ".previous\n"
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err)
-#if 0 /* See comment in __save_init_fpu() below. */
+#if 0 /* See comment in fxsave() below. */
 		     : [fx] "r" (fx), "m" (*fx), "0" (0));
 #else
 		     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
@@ -75,14 +75,6 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 	return err;
 }
 
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_XSAVE)
-		return xrstor_checking(&tsk->thread.xstate->xsave);
-	else
-		return fxrstor_checking(&tsk->thread.xstate->fxsave);
-}
-
 /* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
    is pending. Clear the x87 state here by setting it to fixed
    values. The kernel data segment can be sometimes 0 and sometimes
@@ -120,7 +112,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 		     ".previous\n"
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err), "=m" (*fx)
-#if 0 /* See comment in __fxsave_clear() below. */
+#if 0 /* See comment in fxsave() below. */
 		     : [fx] "r" (fx), "0" (0));
 #else
 		     : [fx] "cdaSDb" (fx), "0" (0));
@@ -185,12 +177,9 @@ static inline void tolerant_fwait(void)
 	asm volatile("fnclex ; fwait");
 }
 
-static inline void restore_fpu(struct task_struct *tsk)
+/* perform fxrstor iff the processor has extended states, otherwise frstor */
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
-	if (task_thread_info(tsk)->status & TS_XSAVE) {
-		xrstor_checking(&tsk->thread.xstate->xsave);
-		return;
-	}
 	/*
 	 * The "nop" is needed to make the instructions the same
 	 * length.
@@ -199,7 +188,9 @@ static inline void restore_fpu(struct task_struct *tsk)
 		"nop ; frstor %1",
 		"fxrstor %1",
 		X86_FEATURE_FXSR,
-		"m" (tsk->thread.xstate->fxsave));
+		"m" (*fx));
+
+	return 0;
 }
 
 /* We need a safe address that is cheap to find and that is already
@@ -262,6 +253,14 @@ end:
 
 #endif	/* CONFIG_X86_64 */
 
+static inline int restore_fpu_checking(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_XSAVE)
+		return xrstor_checking(&tsk->thread.xstate->xsave);
+	else
+		return fxrstor_checking(&tsk->thread.xstate->fxsave);
+}
+
 /*
  * Signal frame handlers...
  */
@@ -305,18 +304,18 @@ static inline void kernel_fpu_end(void)
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
  * DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context aswell. To prevent these kernel instructions
- * in interrupt context interact wrongly with other user/kernel fpu usage, we
+ * get used from interrupt context as well. To prevent these kernel instructions
+ * in interrupt context interacting wrongly with other user/kernel fpu usage, we
  * should use them only in the context of irq_ts_save/restore()
  */
 static inline int irq_ts_save(void)
 {
 	/*
-	 * If we are in process context, we are ok to take a spurious DNA fault.
-	 * Otherwise, doing clts() in process context require pre-emption to
-	 * be disabled or some heavy lifting like kernel_fpu_begin()
+	 * If in process context and not atomic, we can take a spurious DNA fault.
+	 * Otherwise, doing clts() in process context requires disabling preemption
+	 * or some heavy lifting like kernel_fpu_begin()
 	 */
-	if (!in_interrupt())
+	if (!in_atomic())
 		return 0;
 
 	if (read_cr0() & X86_CR0_TS) {
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 1a99e6c092af..58d7091eeb1f 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -60,8 +60,4 @@ extern struct irq_chip i8259A_chip;
 extern void mask_8259A(void);
 extern void unmask_8259A(void);
 
-#ifdef CONFIG_X86_32
-extern void init_ISA_irqs(void);
-#endif
-
 #endif /* _ASM_X86_I8259_H */
diff --git a/arch/x86/include/asm/intel_arch_perfmon.h b/arch/x86/include/asm/intel_arch_perfmon.h
deleted file mode 100644
index fa0fd068bc2e..000000000000
--- a/arch/x86/include/asm/intel_arch_perfmon.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef _ASM_X86_INTEL_ARCH_PERFMON_H
-#define _ASM_X86_INTEL_ARCH_PERFMON_H
-
-#define MSR_ARCH_PERFMON_PERFCTR0		0xc1
-#define MSR_ARCH_PERFMON_PERFCTR1		0xc2
-
-#define MSR_ARCH_PERFMON_EVENTSEL0		0x186
-#define MSR_ARCH_PERFMON_EVENTSEL1		0x187
-
-#define ARCH_PERFMON_EVENTSEL0_ENABLE	(1 << 22)
-#define ARCH_PERFMON_EVENTSEL_INT	(1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS	(1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR	(1 << 16)
-
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL	(0x3c)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK	(0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
-	(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
-
-union cpuid10_eax {
-	struct {
-		unsigned int version_id:8;
-		unsigned int num_counters:8;
-		unsigned int bit_width:8;
-		unsigned int mask_length:8;
-	} split;
-	unsigned int full;
-};
-
-#endif /* _ASM_X86_INTEL_ARCH_PERFMON_H */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 9d826e436010..daf866ed0612 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -154,22 +154,19 @@ extern int timer_through_8259;
 extern int io_apic_get_unique_id(int ioapic, int apic_id);
 extern int io_apic_get_version(int ioapic);
 extern int io_apic_get_redir_entries(int ioapic);
-extern int io_apic_set_pci_routing(int ioapic, int pin, int irq,
-				   int edge_level, int active_high_low);
 #endif /* CONFIG_ACPI */
 
+struct io_apic_irq_attr;
+extern int io_apic_set_pci_routing(struct device *dev, int irq,
+		 struct io_apic_irq_attr *irq_attr);
 extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 extern void ioapic_init_mappings(void);
 
-#ifdef CONFIG_X86_64
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
 extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
-extern void reinit_intr_remapped_IO_APIC(int intr_remapping,
-	struct IO_APIC_route_entry **ioapic_entries);
-#endif
 
 extern void probe_nr_irqs_gsi(void);
 
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index 86af26091d6c..0e9fe1d9d971 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -1,3 +1,6 @@
+#ifndef _ASM_X86_IOMAP_H
+#define _ASM_X86_IOMAP_H
+
 /*
  * Copyright © 2008 Ingo Molnar
  *
@@ -31,3 +34,5 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
 
 void
 iounmap_atomic(void *kvaddr, enum km_type type);
+
+#endif /* _ASM_X86_IOMAP_H */
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 0396760fccb8..f275e2244505 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -1,6 +1,6 @@
 #ifndef _ASM_X86_IRQ_REMAPPING_H
 #define _ASM_X86_IRQ_REMAPPING_H
 
-#define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8)
+#define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
 
 #endif	/* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 3cbd79bbb47c..e997be98c9b9 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -34,6 +34,7 @@
 
 #ifdef CONFIG_X86_32
 # define SYSCALL_VECTOR			0x80
+# define IA32_SYSCALL_VECTOR		0x80
 #else
 # define IA32_SYSCALL_VECTOR		0x80
 #endif
@@ -106,16 +107,16 @@
  */
 #define LOCAL_TIMER_VECTOR		0xef
 
-/*
- * Performance monitoring interrupt vector:
- */
-#define LOCAL_PERF_VECTOR		0xee
-
 /*
  * Generic system vector for platform specific use
  */
 #define GENERIC_INTERRUPT_VECTOR	0xed
 
+/*
+ * Performance monitoring pending work vector:
+ */
+#define LOCAL_PENDING_VECTOR		0xec
+
 /*
  * First APIC vector available to drivers: (vectors 0x30-0xee) we
  * start at 0x31(0x41) to spread out vectors evenly between priority
diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/k8.h
index 54c8cc53b24d..c2d1f3b58e5f 100644
--- a/arch/x86/include/asm/k8.h
+++ b/arch/x86/include/asm/k8.h
@@ -12,4 +12,17 @@ extern int cache_k8_northbridges(void);
 extern void k8_flush_garts(void);
 extern int k8_scan_nodes(unsigned long start, unsigned long end);
 
+#ifdef CONFIG_K8_NB
+static inline struct pci_dev *node_to_k8_nb_misc(int node)
+{
+	return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL;
+}
+#else
+static inline struct pci_dev *node_to_k8_nb_misc(int node)
+{
+	return NULL;
+}
+#endif
+
+
 #endif /* _ASM_X86_K8_H */
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index dc3f6cf11704..125be8b19568 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -16,6 +16,7 @@
 #define __KVM_HAVE_MSI
 #define __KVM_HAVE_USER_NMI
 #define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_MSIX
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f0faf58044ff..eabdc1cfab5c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -185,6 +185,7 @@ union kvm_mmu_page_role {
 		unsigned access:3;
 		unsigned invalid:1;
 		unsigned cr4_pge:1;
+		unsigned nxe:1;
 	};
 };
 
@@ -212,7 +213,6 @@ struct kvm_mmu_page {
 	int multimapped;         /* More than one parent_pte? */
 	int root_count;          /* Currently serving as active root */
 	bool unsync;
-	bool global;
 	unsigned int unsync_children;
 	union {
 		u64 *parent_pte;               /* !multimapped */
@@ -261,13 +261,11 @@ struct kvm_mmu {
 	union kvm_mmu_page_role base_role;
 
 	u64 *pae_root;
+	u64 rsvd_bits_mask[2][4];
 };
 
 struct kvm_vcpu_arch {
 	u64 host_tsc;
-	int interrupt_window_open;
-	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
-	DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
 	/*
 	 * rip and regs accesses must go through
 	 * kvm_{register,rip}_{read,write} functions.
@@ -286,6 +284,7 @@ struct kvm_vcpu_arch {
 	u64 shadow_efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
+	int32_t apic_arb_prio;
 	int mp_state;
 	int sipi_vector;
 	u64 ia32_misc_enable_msr;
@@ -320,6 +319,8 @@ struct kvm_vcpu_arch {
 	struct kvm_pio_request pio;
 	void *pio_data;
 
+	u8 event_exit_inst_len;
+
 	struct kvm_queued_exception {
 		bool pending;
 		bool has_error_code;
@@ -329,11 +330,12 @@ struct kvm_vcpu_arch {
 
 	struct kvm_queued_interrupt {
 		bool pending;
+		bool soft;
 		u8 nr;
 	} interrupt;
 
 	struct {
-		int active;
+		int vm86_active;
 		u8 save_iopl;
 		struct kvm_save_segment {
 			u16 selector;
@@ -356,9 +358,9 @@ struct kvm_vcpu_arch {
 	unsigned int time_offset;
 	struct page *time_page;
 
+	bool singlestep; /* guest is single stepped by KVM */
 	bool nmi_pending;
 	bool nmi_injected;
-	bool nmi_window_open;
 
 	struct mtrr_state_type mtrr_state;
 	u32 pat;
@@ -392,15 +394,14 @@ struct kvm_arch{
 	 */
 	struct list_head active_mmu_pages;
 	struct list_head assigned_dev_head;
-	struct list_head oos_global_pages;
 	struct iommu_domain *iommu_domain;
+	int iommu_flags;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
 	struct hlist_head irq_ack_notifier_list;
 	int vapics_in_nmi_mode;
 
-	int round_robin_prev_vcpu;
 	unsigned int tss_addr;
 	struct page *apic_access_page;
 
@@ -423,7 +424,6 @@ struct kvm_vm_stat {
 	u32 mmu_recycled;
 	u32 mmu_cache_miss;
 	u32 mmu_unsync;
-	u32 mmu_unsync_global;
 	u32 remote_tlb_flush;
 	u32 lpages;
 };
@@ -443,7 +443,6 @@ struct kvm_vcpu_stat {
 	u32 halt_exits;
 	u32 halt_wakeup;
 	u32 request_irq_exits;
-	u32 request_nmi_exits;
 	u32 irq_exits;
 	u32 host_state_reload;
 	u32 efer_reload;
@@ -511,20 +510,22 @@ struct kvm_x86_ops {
 	void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
 	int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
 	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
+	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
 	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
 				unsigned char *hypercall_addr);
-	int (*get_irq)(struct kvm_vcpu *vcpu);
-	void (*set_irq)(struct kvm_vcpu *vcpu, int vec);
+	void (*set_irq)(struct kvm_vcpu *vcpu);
+	void (*set_nmi)(struct kvm_vcpu *vcpu);
 	void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
 				bool has_error_code, u32 error_code);
-	bool (*exception_injected)(struct kvm_vcpu *vcpu);
-	void (*inject_pending_irq)(struct kvm_vcpu *vcpu);
-	void (*inject_pending_vectors)(struct kvm_vcpu *vcpu,
-				       struct kvm_run *run);
-
+	int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
+	int (*nmi_allowed)(struct kvm_vcpu *vcpu);
+	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
+	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
+	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
-	int (*get_mt_mask_shift)(void);
+	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 };
 
 extern struct kvm_x86_ops *kvm_x86_ops;
@@ -538,7 +539,7 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
 void kvm_mmu_set_base_ptes(u64 base_pte);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 mt_mask);
+		u64 dirty_mask, u64 nx_mask, u64 x_mask);
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
@@ -552,6 +553,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
 int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
 		  gpa_t addr, unsigned long *ret);
+u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 extern bool tdp_enabled;
 
@@ -563,6 +565,7 @@ enum emulation_result {
 
 #define EMULTYPE_NO_DECODE	    (1 << 0)
 #define EMULTYPE_TRAP_UD	    (1 << 1)
+#define EMULTYPE_SKIP		    (1 << 2)
 int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
 			unsigned long cr2, u16 error_code, int emulation_type);
 void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
@@ -638,7 +641,6 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-void kvm_mmu_sync_global(struct kvm_vcpu *vcpu);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
@@ -769,6 +771,8 @@ enum {
 #define HF_GIF_MASK		(1 << 0)
 #define HF_HIF_MASK		(1 << 1)
 #define HF_VINTR_MASK		(1 << 2)
+#define HF_NMI_MASK		(1 << 3)
+#define HF_IRET_MASK		(1 << 4)
 
 /*
  * Hardware virtualization extension instructions may fault if a
@@ -791,5 +795,6 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
 
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/kvm_x86_emulate.h b/arch/x86/include/asm/kvm_x86_emulate.h
index 6a159732881a..b7ed2c423116 100644
--- a/arch/x86/include/asm/kvm_x86_emulate.h
+++ b/arch/x86/include/asm/kvm_x86_emulate.h
@@ -143,6 +143,9 @@ struct decode_cache {
 	struct fetch_cache fetch;
 };
 
+#define X86_SHADOW_INT_MOV_SS  1
+#define X86_SHADOW_INT_STI     2
+
 struct x86_emulate_ctxt {
 	/* Register state before/after emulation. */
 	struct kvm_vcpu *vcpu;
@@ -152,6 +155,9 @@ struct x86_emulate_ctxt {
 	int mode;
 	u32 cs_base;
 
+	/* interruptibility state, as a result of execution of STI or MOV SS */
+	int interruptibility;
+
 	/* decode cache */
 	struct decode_cache decode;
 };
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index c882664716c1..ef51b501e22a 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -9,20 +9,31 @@ struct cpu_signature {
 
 struct device;
 
+enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
+
 struct microcode_ops {
-	int  (*request_microcode_user) (int cpu, const void __user *buf, size_t size);
-	int  (*request_microcode_fw) (int cpu, struct device *device);
+	enum ucode_state (*request_microcode_user) (int cpu,
+				const void __user *buf, size_t size);
 
-	void (*apply_microcode) (int cpu);
+	enum ucode_state (*request_microcode_fw) (int cpu,
+				struct device *device);
 
-	int  (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
 	void (*microcode_fini_cpu) (int cpu);
+
+	/*
+	 * The generic 'microcode_core' part guarantees that
+	 * the callbacks below run on a target cpu when they
+	 * are being called.
+	 * See also the "Synchronization" section in microcode_core.c.
+	 */
+	int (*apply_microcode) (int cpu);
+	int (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
 };
 
 struct ucode_cpu_info {
-	struct cpu_signature cpu_sig;
-	int valid;
-	void *mc;
+	struct cpu_signature	cpu_sig;
+	int			valid;
+	void			*mc;
 };
 extern struct ucode_cpu_info ucode_cpu_info[];
 
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 642fc7fc8cdc..e2a1bb6d71ea 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -61,9 +61,11 @@ extern void get_smp_config(void);
 #ifdef CONFIG_X86_MPPARSE
 extern void find_smp_config(void);
 extern void early_reserve_e820_mpc_new(void);
+extern int enable_update_mptable;
 #else
 static inline void find_smp_config(void) { }
 static inline void early_reserve_e820_mpc_new(void) { }
+#define enable_update_mptable 0
 #endif
 
 void __cpuinit generic_processor_info(int apicid, int version);
@@ -72,20 +74,13 @@ extern void mp_register_ioapic(int id, u32 address, u32 gsi_base);
 extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 				   u32 gsi);
 extern void mp_config_acpi_legacy_irqs(void);
-extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+struct device;
+extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level,
+				 int active_high_low);
 extern int acpi_probe_gsi(void);
 #ifdef CONFIG_X86_IO_APIC
-extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
-				u32 gsi, int triggering, int polarity);
 extern int mp_find_ioapic(int gsi);
 extern int mp_find_ioapic_pin(int ioapic, int gsi);
-#else
-static inline int
-mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
-		   u32 gsi, int triggering, int polarity)
-{
-	return 0;
-}
 #endif
 #else /* !CONFIG_ACPI: */
 static inline int acpi_probe_gsi(void)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ec41fc16c167..4d58d04fca83 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -121,7 +121,6 @@
 #define MSR_K8_TOP_MEM1			0xc001001a
 #define MSR_K8_TOP_MEM2			0xc001001d
 #define MSR_K8_SYSCFG			0xc0010010
-#define MSR_K8_HWCR			0xc0010015
 #define MSR_K8_INT_PENDING_MSG		0xc0010055
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 638bf6241807..22603764e7db 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -12,6 +12,17 @@
 
 #include <asm/asm.h>
 #include <asm/errno.h>
+#include <asm/cpumask.h>
+
+struct msr {
+	union {
+		struct {
+			u32 l;
+			u32 h;
+		};
+		u64 q;
+	};
+};
 
 static inline unsigned long long native_read_tscp(unsigned int *aux)
 {
@@ -216,6 +227,8 @@ do {                                                            \
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
+void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
 #else  /*  CONFIG_SMP  */
@@ -229,6 +242,16 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 	wrmsr(msr_no, l, h);
 	return 0;
 }
+static inline void rdmsr_on_cpus(const cpumask_t *m, u32 msr_no,
+				struct msr *msrs)
+{
+       rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h));
+}
+static inline void wrmsr_on_cpus(const cpumask_t *m, u32 msr_no,
+				struct msr *msrs)
+{
+       wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h);
+}
 static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no,
 				    u32 *l, u32 *h)
 {
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c45a0a568dff..c97264409934 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -64,7 +64,7 @@ static inline int nmi_watchdog_active(void)
 	 * but since they are power of two we could use a
 	 * cheaper way --cvg
 	 */
-	return nmi_watchdog & 0x3;
+	return nmi_watchdog & (NMI_LOCAL_APIC | NMI_IO_APIC);
 }
 #endif
 
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 064ed6df4cbe..c4ae822e415f 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -17,9 +17,6 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,
 extern void numa_init_array(void);
 extern int numa_off;
 
-extern void srat_reserve_add_area(int nodeid);
-extern int hotadd_percent;
-
 extern s16 apicid_to_node[MAX_LOCAL_APIC];
 
 extern unsigned long numa_free_all_bootmem(void);
@@ -27,6 +24,13 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
 			       unsigned long end);
 
 #ifdef CONFIG_NUMA
+/*
+ * Too small node sizes may confuse the VM badly. Usually they
+ * result from BIOS bugs. So dont recognize nodes as standalone
+ * NUMA entities that have less than this amount of RAM listed:
+ */
+#define NODE_MIN_SIZE (4*1024*1024)
+
 extern void __init init_cpu_to_node(void);
 extern void __cpuinit numa_set_node(int cpu, int node);
 extern void __cpuinit numa_clear_node(int cpu);
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 0f915ae649a7..6f1b7331313f 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -54,10 +54,6 @@ extern unsigned int __VMALLOC_RESERVE;
 extern int sysctl_legacy_va_layout;
 
 extern void find_low_pfn_range(void);
-extern unsigned long init_memory_mapping(unsigned long start,
-					 unsigned long end);
-extern void initmem_init(unsigned long, unsigned long);
-extern void free_initmem(void);
 extern void setup_bootmem_allocator(void);
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index d38c91b70248..8d382d3abf38 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -32,22 +32,14 @@
  */
 #define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
 
-#define __PHYSICAL_START	CONFIG_PHYSICAL_START
-#define __KERNEL_ALIGN		0x200000
-
-/*
- * Make sure kernel is aligned to 2MB address. Catching it at compile
- * time is better. Change your config file and compile the kernel
- * for a 2MB aligned address (CONFIG_PHYSICAL_START)
- */
-#if (CONFIG_PHYSICAL_START % __KERNEL_ALIGN) != 0
-#error "CONFIG_PHYSICAL_START must be a multiple of 2MB"
-#endif
+#define __PHYSICAL_START	((CONFIG_PHYSICAL_START +	 	\
+				  (CONFIG_PHYSICAL_ALIGN - 1)) &	\
+				 ~(CONFIG_PHYSICAL_ALIGN - 1))
 
 #define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
 #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
 
-/* See Documentation/x86_64/mm.txt for a description of the memory map. */
+/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
 #define __PHYSICAL_MASK_SHIFT	46
 #define __VIRTUAL_MASK_SHIFT	48
 
@@ -71,12 +63,6 @@ extern unsigned long __phys_addr(unsigned long);
 
 #define vmemmap ((struct page *)VMEMMAP_START)
 
-extern unsigned long init_memory_mapping(unsigned long start,
-					 unsigned long end);
-
-extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
-extern void free_initmem(void);
-
 extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
 extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
 
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 826ad37006ab..6473f5ccff85 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -46,6 +46,12 @@ extern int devmem_is_allowed(unsigned long pagenr);
 extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
+extern unsigned long init_memory_mapping(unsigned long start,
+					 unsigned long end);
+
+extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+extern void free_initmem(void);
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif	/* _ASM_X86_PAGE_DEFS_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a53da004e08e..4fb37c8a0832 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -56,6 +56,7 @@ struct desc_ptr;
 struct tss_struct;
 struct mm_struct;
 struct desc_struct;
+struct task_struct;
 
 /*
  * Wrapper type for pointers to code which uses the non-standard
@@ -203,7 +204,8 @@ struct pv_cpu_ops {
 
 	void (*swapgs)(void);
 
-	struct pv_lazy_ops lazy_mode;
+	void (*start_context_switch)(struct task_struct *prev);
+	void (*end_context_switch)(struct task_struct *next);
 };
 
 struct pv_irq_ops {
@@ -1399,25 +1401,23 @@ enum paravirt_lazy_mode {
 };
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_enter_lazy_cpu(void);
-void paravirt_leave_lazy_cpu(void);
+void paravirt_start_context_switch(struct task_struct *prev);
+void paravirt_end_context_switch(struct task_struct *next);
+
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode);
 
-#define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-static inline void arch_enter_lazy_cpu_mode(void)
+#define  __HAVE_ARCH_START_CONTEXT_SWITCH
+static inline void arch_start_context_switch(struct task_struct *prev)
 {
-	PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
+	PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
 }
 
-static inline void arch_leave_lazy_cpu_mode(void)
+static inline void arch_end_context_switch(struct task_struct *next)
 {
-	PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
+	PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
 }
 
-void arch_flush_lazy_cpu_mode(void);
-
 #define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 static inline void arch_enter_lazy_mmu_mode(void)
 {
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
new file mode 100644
index 000000000000..876ed97147b3
--- /dev/null
+++ b/arch/x86/include/asm/perf_counter.h
@@ -0,0 +1,100 @@
+#ifndef _ASM_X86_PERF_COUNTER_H
+#define _ASM_X86_PERF_COUNTER_H
+
+/*
+ * Performance counter hw details:
+ */
+
+#define X86_PMC_MAX_GENERIC					8
+#define X86_PMC_MAX_FIXED					3
+
+#define X86_PMC_IDX_GENERIC				        0
+#define X86_PMC_IDX_FIXED				       32
+#define X86_PMC_IDX_MAX					       64
+
+#define MSR_ARCH_PERFMON_PERFCTR0			      0xc1
+#define MSR_ARCH_PERFMON_PERFCTR1			      0xc2
+
+#define MSR_ARCH_PERFMON_EVENTSEL0			     0x186
+#define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
+
+#define ARCH_PERFMON_EVENTSEL0_ENABLE			  (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
+#define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
+#define ARCH_PERFMON_EVENTSEL_USR			  (1 << 16)
+
+/*
+ * Includes eventsel and unit mask as well:
+ */
+#define ARCH_PERFMON_EVENT_MASK				    0xffff
+
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 		 0
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
+		(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
+
+#define ARCH_PERFMON_BRANCH_MISSES_RETIRED			 6
+
+/*
+ * Intel "Architectural Performance Monitoring" CPUID
+ * detection/enumeration details:
+ */
+union cpuid10_eax {
+	struct {
+		unsigned int version_id:8;
+		unsigned int num_counters:8;
+		unsigned int bit_width:8;
+		unsigned int mask_length:8;
+	} split;
+	unsigned int full;
+};
+
+union cpuid10_edx {
+	struct {
+		unsigned int num_counters_fixed:4;
+		unsigned int reserved:28;
+	} split;
+	unsigned int full;
+};
+
+
+/*
+ * Fixed-purpose performance counters:
+ */
+
+/*
+ * All 3 fixed-mode PMCs are configured via this single MSR:
+ */
+#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL			0x38d
+
+/*
+ * The counts are available in three separate MSRs:
+ */
+
+/* Instr_Retired.Any: */
+#define MSR_ARCH_PERFMON_FIXED_CTR0			0x309
+#define X86_PMC_IDX_FIXED_INSTRUCTIONS			(X86_PMC_IDX_FIXED + 0)
+
+/* CPU_CLK_Unhalted.Core: */
+#define MSR_ARCH_PERFMON_FIXED_CTR1			0x30a
+#define X86_PMC_IDX_FIXED_CPU_CYCLES			(X86_PMC_IDX_FIXED + 1)
+
+/* CPU_CLK_Unhalted.Ref: */
+#define MSR_ARCH_PERFMON_FIXED_CTR2			0x30b
+#define X86_PMC_IDX_FIXED_BUS_CYCLES			(X86_PMC_IDX_FIXED + 2)
+
+extern void set_perf_counter_pending(void);
+
+#define clear_perf_counter_pending()	do { } while (0)
+#define test_perf_counter_pending()	(0)
+
+#ifdef CONFIG_PERF_COUNTERS
+extern void init_hw_perf_counters(void);
+extern void perf_counters_lapic_init(void);
+#else
+static inline void init_hw_perf_counters(void)		{ }
+static inline void perf_counters_lapic_init(void)	{ }
+#endif
+
+#endif /* _ASM_X86_PERF_COUNTER_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 29d96d168bc0..18ef7ebf2631 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -81,6 +81,8 @@ static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
 #define pte_val(x)	native_pte_val(x)
 #define __pte(x)	native_make_pte(x)
 
+#define arch_end_context_switch(prev)	do {} while(0)
+
 #endif	/* CONFIG_PARAVIRT */
 
 /*
@@ -503,6 +505,8 @@ static inline int pgd_none(pgd_t pgd)
 
 #ifndef __ASSEMBLY__
 
+extern int direct_gbpages;
+
 /* local pte updates need not use xchg for locking */
 static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
 {
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 6b87bc6d5018..abde308fdb0f 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -25,10 +25,6 @@ extern pgd_t init_level4_pgt[];
 
 extern void paging_init(void);
 
-#endif /* !__ASSEMBLY__ */
-
-#ifndef __ASSEMBLY__
-
 #define pte_ERROR(e)					\
 	printk("%s:%d: bad pte %p(%016lx).\n",		\
 	       __FILE__, __LINE__, &(e), pte_val(e))
@@ -135,8 +131,6 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 
 #define update_mmu_cache(vma, address, pte) do { } while (0)
 
-extern int direct_gbpages;
-
 /* Encode and de-code a swap entry */
 #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
 #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index fbf42b8e0383..766ea16fbbbd 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -51,11 +51,11 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_SIZE	(_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
-
+/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
 #define MAXMEM		 _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
-#define VMALLOC_START    _AC(0xffffc20000000000, UL)
-#define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
-#define VMEMMAP_START	 _AC(0xffffe20000000000, UL)
+#define VMALLOC_START    _AC(0xffffc90000000000, UL)
+#define VMALLOC_END      _AC(0xffffe8ffffffffff, UL)
+#define VMEMMAP_START	 _AC(0xffffea0000000000, UL)
 #define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b8238dc8786d..4d258ad76a0f 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -273,7 +273,6 @@ typedef struct page *pgtable_t;
 
 extern pteval_t __supported_pte_mask;
 extern int nx_enabled;
-extern void set_nx(void);
 
 #define pgprot_writecombine	pgprot_writecombine
 extern pgprot_t pgprot_writecombine(pgprot_t prot);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c2cceae709c8..c7768269b1cf 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -135,7 +135,8 @@ extern struct cpuinfo_x86	boot_cpu_data;
 extern struct cpuinfo_x86	new_cpu_data;
 
 extern struct tss_struct	doublefault_tss;
-extern __u32			cleared_cpu_caps[NCAPINTS];
+extern __u32			cpu_caps_cleared[NCAPINTS];
+extern __u32			cpu_caps_set[NCAPINTS];
 
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
@@ -409,9 +410,6 @@ DECLARE_PER_CPU(unsigned long, stack_canary);
 extern unsigned int xstate_size;
 extern void free_thread_xstate(struct task_struct *);
 extern struct kmem_cache *task_xstate_cachep;
-extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
-extern unsigned short num_cache_leaves;
 
 struct thread_struct {
 	/* Cached TLS descriptors: */
@@ -427,8 +425,12 @@ struct thread_struct {
 	unsigned short		fsindex;
 	unsigned short		gsindex;
 #endif
+#ifdef CONFIG_X86_32
 	unsigned long		ip;
+#endif
+#ifdef CONFIG_X86_64
 	unsigned long		fs;
+#endif
 	unsigned long		gs;
 	/* Hardware debugging registers: */
 	unsigned long		debugreg0;
@@ -460,14 +462,8 @@ struct thread_struct {
 	unsigned		io_bitmap_max;
 /* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
 	unsigned long	debugctlmsr;
-#ifdef CONFIG_X86_DS
-/* Debug Store context; see include/asm-x86/ds.h; goes into MSR_IA32_DS_AREA */
+	/* Debug Store context; see asm/ds.h */
 	struct ds_context	*ds_ctx;
-#endif /* CONFIG_X86_DS */
-#ifdef CONFIG_X86_PTRACE_BTS
-/* the signal to send on a bts buffer overflow */
-	unsigned int	bts_ovfl_signal;
-#endif /* CONFIG_X86_PTRACE_BTS */
 };
 
 static inline unsigned long native_get_debugreg(int regno)
@@ -795,6 +791,21 @@ static inline unsigned long get_debugctlmsr(void)
     return debugctlmsr;
 }
 
+static inline unsigned long get_debugctlmsr_on_cpu(int cpu)
+{
+	u64 debugctlmsr = 0;
+	u32 val1, val2;
+
+#ifndef CONFIG_X86_DEBUGCTLMSR
+	if (boot_cpu_data.x86 < 6)
+		return 0;
+#endif
+	rdmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &val1, &val2);
+	debugctlmsr = val1 | ((u64)val2 << 32);
+
+	return debugctlmsr;
+}
+
 static inline void update_debugctlmsr(unsigned long debugctlmsr)
 {
 #ifndef CONFIG_X86_DEBUGCTLMSR
@@ -804,6 +815,18 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
 }
 
+static inline void update_debugctlmsr_on_cpu(int cpu,
+					     unsigned long debugctlmsr)
+{
+#ifndef CONFIG_X86_DEBUGCTLMSR
+	if (boot_cpu_data.x86 < 6)
+		return;
+#endif
+	wrmsr_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR,
+		     (u32)((u64)debugctlmsr),
+		     (u32)((u64)debugctlmsr >> 32));
+}
+
 /*
  * from system description table in BIOS. Mostly for MCA use, but
  * others may find it useful:
@@ -814,6 +837,7 @@ extern unsigned int		BIOS_revision;
 
 /* Boot loader type from the setup header: */
 extern int			bootloader_type;
+extern int			bootloader_version;
 
 extern char			ignore_fpu_irq;
 
@@ -874,7 +898,6 @@ static inline void spin_lock_prefetch(const void *x)
 	.vm86_info		= NULL,					  \
 	.sysenter_cs		= __KERNEL_CS,				  \
 	.io_bitmap_ptr		= NULL,					  \
-	.fs			= __KERNEL_PERCPU,			  \
 }
 
 /*
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 624f133943ed..0f0d908349aa 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -236,12 +236,11 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info, int can_allocate);
 
-extern void x86_ptrace_untrace(struct task_struct *);
-extern void x86_ptrace_fork(struct task_struct *child,
-			    unsigned long clone_flags);
+#ifdef CONFIG_X86_PTRACE_BTS
+extern void ptrace_bts_untrace(struct task_struct *tsk);
 
-#define arch_ptrace_untrace(tsk) x86_ptrace_untrace(tsk)
-#define arch_ptrace_fork(child, flags) x86_ptrace_fork(child, flags)
+#define arch_ptrace_untrace(tsk)	ptrace_bts_untrace(tsk)
+#endif /* CONFIG_X86_PTRACE_BTS */
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index a4737dddfd58..64cf2d24fad1 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -48,9 +48,15 @@
 #endif
 
 #ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT
+/* Paravirtualized systems may not have PSE or PGE available */
 #define NEED_PSE	0
-#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
 #define NEED_PGE	0
+#else
+#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
+#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
+#endif
+#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
 #define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
 #define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
 #define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index bdc2ada05ae0..4093d1ed6db2 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -33,7 +33,6 @@ struct x86_quirks {
 	int (*setup_ioapic_ids)(void);
 };
 
-extern void x86_quirk_pre_intr_init(void);
 extern void x86_quirk_intr_init(void);
 
 extern void x86_quirk_trap_init(void);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 19e0d88b966d..6a84ed166aec 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -180,7 +180,7 @@ extern int safe_smp_processor_id(void);
 static inline int logical_smp_processor_id(void)
 {
 	/* we don't want to mark this access volatile - bad code generation */
-	return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR));
+	return GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
 }
 
 #endif
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index e3cc3c063ec5..4517d6b93188 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -27,7 +27,7 @@
 #else /* CONFIG_X86_32 */
 # define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
 # define MAX_PHYSADDR_BITS	44
-# define MAX_PHYSMEM_BITS	44 /* Can be max 45 bits */
+# define MAX_PHYSMEM_BITS	46
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 82ada75f3ebf..85574b7c1bc1 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -225,6 +225,7 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_EVTINJ_VALID_ERR (1 << 11)
 
 #define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK
+#define SVM_EXITINTINFO_TYPE_MASK SVM_EVTINJ_TYPE_MASK
 
 #define	SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR
 #define	SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 7043408f6904..372b76edd63f 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -1,7 +1,7 @@
 /*
  * syscalls.h - Linux syscall interfaces (arch-specific)
  *
- * Copyright (c) 2008 Jaswinder Singh
+ * Copyright (c) 2008 Jaswinder Singh Rajput
  *
  * This file is released under the GPLv2.
  * See the file COPYING for more details.
@@ -12,50 +12,55 @@
 
 #include <linux/compiler.h>
 #include <linux/linkage.h>
-#include <linux/types.h>
 #include <linux/signal.h>
+#include <linux/types.h>
 
 /* Common in X86_32 and X86_64 */
 /* kernel/ioport.c */
 asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
 
+/* kernel/process.c */
+int sys_fork(struct pt_regs *);
+int sys_vfork(struct pt_regs *);
+
 /* kernel/ldt.c */
 asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
 
+/* kernel/signal.c */
+long sys_rt_sigreturn(struct pt_regs *);
+
 /* kernel/tls.c */
 asmlinkage int sys_set_thread_area(struct user_desc __user *);
 asmlinkage int sys_get_thread_area(struct user_desc __user *);
 
 /* X86_32 only */
 #ifdef CONFIG_X86_32
+/* kernel/ioport.c */
+long sys_iopl(struct pt_regs *);
+
 /* kernel/process_32.c */
-int sys_fork(struct pt_regs *);
 int sys_clone(struct pt_regs *);
-int sys_vfork(struct pt_regs *);
 int sys_execve(struct pt_regs *);
 
-/* kernel/signal_32.c */
+/* kernel/signal.c */
 asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
 asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
 			     struct old_sigaction __user *);
 int sys_sigaltstack(struct pt_regs *);
 unsigned long sys_sigreturn(struct pt_regs *);
-long sys_rt_sigreturn(struct pt_regs *);
-
-/* kernel/ioport.c */
-long sys_iopl(struct pt_regs *);
 
 /* kernel/sys_i386_32.c */
+struct mmap_arg_struct;
+struct sel_arg_struct;
+struct oldold_utsname;
+struct old_utsname;
+
 asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
 			  unsigned long, unsigned long, unsigned long);
-struct mmap_arg_struct;
 asmlinkage int old_mmap(struct mmap_arg_struct __user *);
-struct sel_arg_struct;
 asmlinkage int old_select(struct sel_arg_struct __user *);
 asmlinkage int sys_ipc(uint, int, int, int, void __user *, long);
-struct old_utsname;
 asmlinkage int sys_uname(struct old_utsname __user *);
-struct oldold_utsname;
 asmlinkage int sys_olduname(struct oldold_utsname __user *);
 
 /* kernel/vm86_32.c */
@@ -65,29 +70,27 @@ int sys_vm86(struct pt_regs *);
 #else /* CONFIG_X86_32 */
 
 /* X86_64 only */
+/* kernel/ioport.c */
+asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
+
 /* kernel/process_64.c */
-asmlinkage long sys_fork(struct pt_regs *);
 asmlinkage long sys_clone(unsigned long, unsigned long,
 			  void __user *, void __user *,
 			  struct pt_regs *);
-asmlinkage long sys_vfork(struct pt_regs *);
 asmlinkage long sys_execve(char __user *, char __user * __user *,
 			   char __user * __user *,
 			   struct pt_regs *);
 long sys_arch_prctl(int, unsigned long);
 
-/* kernel/ioport.c */
-asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
-
-/* kernel/signal_64.c */
+/* kernel/signal.c */
 asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
 				struct pt_regs *);
-long sys_rt_sigreturn(struct pt_regs *);
 
 /* kernel/sys_x86_64.c */
+struct new_utsname;
+
 asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
 			 unsigned long, unsigned long, unsigned long);
-struct new_utsname;
 asmlinkage long sys_uname(struct new_utsname __user *);
 
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/termios.h b/arch/x86/include/asm/termios.h
index f72956331c49..c4ee8056baca 100644
--- a/arch/x86/include/asm/termios.h
+++ b/arch/x86/include/asm/termios.h
@@ -67,6 +67,7 @@ static inline int user_termio_to_kernel_termios(struct ktermios *termios,
 	SET_LOW_TERMIOS_BITS(termios, termio, c_oflag);
 	SET_LOW_TERMIOS_BITS(termios, termio, c_cflag);
 	SET_LOW_TERMIOS_BITS(termios, termio, c_lflag);
+	get_user(termios->c_line, &termio->c_line);
 	return copy_from_user(termios->c_cc, termio->c_cc, NCC);
 }
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8820a73ae090..602c769fc98c 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -94,7 +94,8 @@ struct thread_info {
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
 #define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
 #define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
-#define TIF_SYSCALL_FTRACE	27	/* for ftrace syscall instrumentation */
+#define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
+#define TIF_SYSCALL_FTRACE	28	/* for ftrace syscall instrumentation */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -116,6 +117,7 @@ struct thread_info {
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
 #define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
 #define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_FTRACE	(1 << TIF_SYSCALL_FTRACE)
 
 /* work to do in syscall_trace_enter() */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 16a5c84b0329..a5ecc9c33e92 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -17,7 +17,7 @@
 
 static inline void __native_flush_tlb(void)
 {
-	write_cr3(read_cr3());
+	native_write_cr3(native_read_cr3());
 }
 
 static inline void __native_flush_tlb_global(void)
@@ -32,11 +32,11 @@ static inline void __native_flush_tlb_global(void)
 	 */
 	raw_local_irq_save(flags);
 
-	cr4 = read_cr4();
+	cr4 = native_read_cr4();
 	/* clear PGE */
-	write_cr4(cr4 & ~X86_CR4_PGE);
+	native_write_cr4(cr4 & ~X86_CR4_PGE);
 	/* write old PGE again and flush TLBs */
-	write_cr4(cr4);
+	native_write_cr4(cr4);
 
 	raw_local_irq_restore(flags);
 }
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index f44b49abca49..066ef590d7e0 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -203,7 +203,8 @@ struct pci_bus;
 void x86_pci_root_bus_res_quirks(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
+#define mc_capable()	((boot_cpu_data.x86_max_cores > 1) && \
+			(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 0d5342515b86..bfd74c032fca 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_TRAPS_H
 
 #include <asm/debugreg.h>
+#include <asm/siginfo.h>			/* TRAP_TRACE, ... */
 
 #ifdef CONFIG_X86_32
 #define dotraplinkage
@@ -13,6 +14,9 @@ asmlinkage void divide_error(void);
 asmlinkage void debug(void);
 asmlinkage void nmi(void);
 asmlinkage void int3(void);
+asmlinkage void xen_debug(void);
+asmlinkage void xen_int3(void);
+asmlinkage void xen_stack_segment(void);
 asmlinkage void overflow(void);
 asmlinkage void bounds(void);
 asmlinkage void invalid_op(void);
@@ -74,7 +78,6 @@ static inline int get_si_code(unsigned long condition)
 }
 
 extern int panic_on_unrecovered_nmi;
-extern int kstack_depth_to_print;
 
 void math_error(void __user *);
 void math_emulate(struct math_emu_info *);
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index 6e72d74cf8dc..732a30706153 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -340,6 +340,8 @@
 #define __NR_inotify_init1	332
 #define __NR_preadv		333
 #define __NR_pwritev		334
+#define __NR_rt_tgsigqueueinfo	335
+#define __NR_perf_counter_open	336
 
 #ifdef __KERNEL__
 
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index f81829462325..900e1617e672 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -657,7 +657,10 @@ __SYSCALL(__NR_inotify_init1, sys_inotify_init1)
 __SYSCALL(__NR_preadv, sys_preadv)
 #define __NR_pwritev				296
 __SYSCALL(__NR_pwritev, sys_pwritev)
-
+#define __NR_rt_tgsigqueueinfo			297
+__SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo)
+#define __NR_perf_counter_open			298
+__SYSCALL(__NR_perf_counter_open, sys_perf_counter_open)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 9b0e61bf7a88..bddd44f2f0ab 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -37,7 +37,7 @@
 #define UV_CPUS_PER_ACT_STATUS		32
 #define UV_ACT_STATUS_MASK		0x3
 #define UV_ACT_STATUS_SIZE		2
-#define UV_ACTIVATION_DESCRIPTOR_SIZE	32
+#define UV_ADP_SIZE			32
 #define UV_DISTRIBUTION_SIZE		256
 #define UV_SW_ACK_NPENDING		8
 #define UV_NET_ENDPOINT_INTD		0x38
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index d3a98ea1062e..341070f7ad5c 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -133,6 +133,7 @@ struct uv_scir_s {
 struct uv_hub_info_s {
 	unsigned long		global_mmr_base;
 	unsigned long		gpa_mask;
+	unsigned int		gnode_extra;
 	unsigned long		gnode_upper;
 	unsigned long		lowmem_remap_top;
 	unsigned long		lowmem_remap_base;
@@ -159,7 +160,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
  * 		p -  PNODE (local part of nsids, right shifted 1)
  */
 #define UV_NASID_TO_PNODE(n)		(((n) >> 1) & uv_hub_info->pnode_mask)
-#define UV_PNODE_TO_NASID(p)		(((p) << 1) | uv_hub_info->gnode_upper)
+#define UV_PNODE_TO_GNODE(p)		((p) |uv_hub_info->gnode_extra)
+#define UV_PNODE_TO_NASID(p)		(UV_PNODE_TO_GNODE(p) << 1)
 
 #define UV_LOCAL_MMR_BASE		0xf4000000UL
 #define UV_GLOBAL_MMR32_BASE		0xf8000000UL
@@ -173,7 +175,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
 #define UV_GLOBAL_MMR64_PNODE_BITS(p)					\
-	((unsigned long)(p) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+	((unsigned long)(UV_PNODE_TO_GNODE(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
 
 #define UV_APIC_PNODE_SHIFT	6
 
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 498f944010b9..11be5ad2e0e9 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -247,6 +247,7 @@ enum vmcs_field {
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_MCE_DURING_VMENTRY	 41
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
 #define EXIT_REASON_EPT_VIOLATION       48
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 88d1bfc847d3..4f78bd682125 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -28,7 +28,7 @@ CFLAGS_paravirt.o	:= $(nostackp)
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o i8259.o irqinit_$(BITS).o
+obj-y			+= setup.o i8259.o irqinit.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
@@ -44,6 +44,7 @@ obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o
 obj-$(CONFIG_X86_DS)		+= ds.o
+obj-$(CONFIG_X86_DS_SELFTEST)		+= ds_selftest.o
 obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)	+= tls.o
 obj-y				+= step.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 723989d7f802..631086159c53 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -33,6 +33,7 @@
 #include <linux/irq.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
+#include <linux/pci.h>
 
 #include <asm/pgtable.h>
 #include <asm/io_apic.h>
@@ -522,7 +523,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
  * success: return IRQ number (>=0)
  * failure: return < 0
  */
-int acpi_register_gsi(u32 gsi, int triggering, int polarity)
+int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
 {
 	unsigned int irq;
 	unsigned int plat_gsi = gsi;
@@ -532,14 +533,14 @@ int acpi_register_gsi(u32 gsi, int triggering, int polarity)
 	 * Make sure all (legacy) PCI IRQs are set as level-triggered.
 	 */
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
-		if (triggering == ACPI_LEVEL_SENSITIVE)
+		if (trigger == ACPI_LEVEL_SENSITIVE)
 			eisa_set_level_irq(gsi);
 	}
 #endif
 
 #ifdef CONFIG_X86_IO_APIC
 	if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) {
-		plat_gsi = mp_register_gsi(gsi, triggering, polarity);
+		plat_gsi = mp_register_gsi(dev, gsi, trigger, polarity);
 	}
 #endif
 	acpi_gsi_to_irq(plat_gsi, &irq);
@@ -903,10 +904,8 @@ extern int es7000_plat;
 #endif
 
 static struct {
-	int apic_id;
 	int gsi_base;
 	int gsi_end;
-	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
 } mp_ioapic_routing[MAX_IO_APICS];
 
 int mp_find_ioapic(int gsi)
@@ -986,16 +985,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 
 	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
 	mp_ioapics[idx].apicid = uniq_ioapic_id(id);
-#ifdef CONFIG_X86_32
 	mp_ioapics[idx].apicver = io_apic_get_version(idx);
-#else
-	mp_ioapics[idx].apicver = 0;
-#endif
+
 	/*
 	 * Build basic GSI lookup table to facilitate gsi->io_apic lookups
 	 * and to prevent reprogramming of IOAPIC pins (PCI GSIs).
 	 */
-	mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].apicid;
 	mp_ioapic_routing[idx].gsi_base = gsi_base;
 	mp_ioapic_routing[idx].gsi_end = gsi_base +
 	    io_apic_get_redir_entries(idx);
@@ -1158,26 +1153,52 @@ void __init mp_config_acpi_legacy_irqs(void)
 	}
 }
 
-int mp_register_gsi(u32 gsi, int triggering, int polarity)
+static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
+			int polarity)
+{
+#ifdef CONFIG_X86_MPPARSE
+	struct mpc_intsrc mp_irq;
+	struct pci_dev *pdev;
+	unsigned char number;
+	unsigned int devfn;
+	int ioapic;
+	u8 pin;
+
+	if (!acpi_ioapic)
+		return 0;
+	if (!dev)
+		return 0;
+	if (dev->bus != &pci_bus_type)
+		return 0;
+
+	pdev = to_pci_dev(dev);
+	number = pdev->bus->number;
+	devfn = pdev->devfn;
+	pin = pdev->pin;
+	/* print the entry should happen on mptable identically */
+	mp_irq.type = MP_INTSRC;
+	mp_irq.irqtype = mp_INT;
+	mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
+	mp_irq.srcbus = number;
+	mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+	ioapic = mp_find_ioapic(gsi);
+	mp_irq.dstapic = mp_ioapics[ioapic].apicid;
+	mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
+
+	save_mp_irq(&mp_irq);
+#endif
+	return 0;
+}
+
+int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
 {
 	int ioapic;
 	int ioapic_pin;
-#ifdef CONFIG_X86_32
-#define MAX_GSI_NUM	4096
-#define IRQ_COMPRESSION_START	64
-
-	static int pci_irq = IRQ_COMPRESSION_START;
-	/*
-	 * Mapping between Global System Interrupts, which
-	 * represent all possible interrupts, and IRQs
-	 * assigned to actual devices.
-	 */
-	static int gsi_to_irq[MAX_GSI_NUM];
-#else
+	struct io_apic_irq_attr irq_attr;
 
 	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
 		return gsi;
-#endif
 
 	/* Don't set up the ACPI SCI because it's already set up */
 	if (acpi_gbl_FADT.sci_interrupt == gsi)
@@ -1196,95 +1217,24 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity)
 		gsi = ioapic_renumber_irq(ioapic, gsi);
 #endif
 
-	/*
-	 * Avoid pin reprogramming.  PRTs typically include entries
-	 * with redundant pin->gsi mappings (but unique PCI devices);
-	 * we only program the IOAPIC on the first.
-	 */
 	if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
 		printk(KERN_ERR "Invalid reference to IOAPIC pin "
-		       "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
+		       "%d-%d\n", mp_ioapics[ioapic].apicid,
 		       ioapic_pin);
 		return gsi;
 	}
-	if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) {
-		pr_debug("Pin %d-%d already programmed\n",
-			 mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
-#ifdef CONFIG_X86_32
-		return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]);
-#else
-		return gsi;
-#endif
-	}
 
-	set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed);
-#ifdef CONFIG_X86_32
-	/*
-	 * For GSI >= 64, use IRQ compression
-	 */
-	if ((gsi >= IRQ_COMPRESSION_START)
-	    && (triggering == ACPI_LEVEL_SENSITIVE)) {
-		/*
-		 * For PCI devices assign IRQs in order, avoiding gaps
-		 * due to unused I/O APIC pins.
-		 */
-		int irq = gsi;
-		if (gsi < MAX_GSI_NUM) {
-			/*
-			 * Retain the VIA chipset work-around (gsi > 15), but
-			 * avoid a problem where the 8254 timer (IRQ0) is setup
-			 * via an override (so it's not on pin 0 of the ioapic),
-			 * and at the same time, the pin 0 interrupt is a PCI
-			 * type.  The gsi > 15 test could cause these two pins
-			 * to be shared as IRQ0, and they are not shareable.
-			 * So test for this condition, and if necessary, avoid
-			 * the pin collision.
-			 */
-			gsi = pci_irq++;
-			/*
-			 * Don't assign IRQ used by ACPI SCI
-			 */
-			if (gsi == acpi_gbl_FADT.sci_interrupt)
-				gsi = pci_irq++;
-			gsi_to_irq[irq] = gsi;
-		} else {
-			printk(KERN_ERR "GSI %u is too high\n", gsi);
-			return gsi;
-		}
-	}
-#endif
-	io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
-				triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
-				polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+	if (enable_update_mptable)
+		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
+
+	set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
+			     trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
+			     polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+	io_apic_set_pci_routing(dev, gsi, &irq_attr);
+
 	return gsi;
 }
 
-int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
-			u32 gsi, int triggering, int polarity)
-{
-#ifdef CONFIG_X86_MPPARSE
-	struct mpc_intsrc mp_irq;
-	int ioapic;
-
-	if (!acpi_ioapic)
-		return 0;
-
-	/* print the entry should happen on mptable identically */
-	mp_irq.type = MP_INTSRC;
-	mp_irq.irqtype = mp_INT;
-	mp_irq.irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
-				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
-	mp_irq.srcbus = number;
-	mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
-	ioapic = mp_find_ioapic(gsi);
-	mp_irq.dstapic = mp_ioapic_routing[ioapic].apic_id;
-	mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
-
-	save_mp_irq(&mp_irq);
-#endif
-	return 0;
-}
-
 /*
  * Parse IOAPIC related entries in MADT
  * returns 0 on success, < 0 on error
diff --git a/arch/x86/kernel/acpi/realmode/Makefile b/arch/x86/kernel/acpi/realmode/Makefile
index 1c31cc0e9def..167bc16ce0e5 100644
--- a/arch/x86/kernel/acpi/realmode/Makefile
+++ b/arch/x86/kernel/acpi/realmode/Makefile
@@ -9,7 +9,7 @@
 always		:= wakeup.bin
 targets		:= wakeup.elf wakeup.lds
 
-wakeup-y	+= wakeup.o wakemain.o video-mode.o copy.o
+wakeup-y	+= wakeup.o wakemain.o video-mode.o copy.o bioscall.o regs.o
 
 # The link order of the video-*.o modules can matter.  In particular,
 # video-vga.o *must* be listed first, followed by video-vesa.o.
diff --git a/arch/x86/kernel/acpi/realmode/bioscall.S b/arch/x86/kernel/acpi/realmode/bioscall.S
new file mode 100644
index 000000000000..f51eb0bb56ce
--- /dev/null
+++ b/arch/x86/kernel/acpi/realmode/bioscall.S
@@ -0,0 +1 @@
+#include "../../../boot/bioscall.S"
diff --git a/arch/x86/kernel/acpi/realmode/regs.c b/arch/x86/kernel/acpi/realmode/regs.c
new file mode 100644
index 000000000000..6206033ba202
--- /dev/null
+++ b/arch/x86/kernel/acpi/realmode/regs.c
@@ -0,0 +1 @@
+#include "../../../boot/regs.c"
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index a97db99dad52..1c60554537c3 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -55,7 +55,16 @@ struct iommu_cmd {
 static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
 			     struct unity_map_entry *e);
 static struct dma_ops_domain *find_protection_domain(u16 devid);
+static u64* alloc_pte(struct protection_domain *dom,
+		      unsigned long address, u64
+		      **pte_page, gfp_t gfp);
+static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
+				      unsigned long start_page,
+				      unsigned int pages);
 
+#ifndef BUS_NOTIFY_UNBOUND_DRIVER
+#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
+#endif
 
 #ifdef CONFIG_AMD_IOMMU_STATS
 
@@ -213,7 +222,7 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
 {
 	struct amd_iommu *iommu;
 
-	list_for_each_entry(iommu, &amd_iommu_list, list)
+	for_each_iommu(iommu)
 		iommu_poll_events(iommu);
 
 	return IRQ_HANDLED;
@@ -440,7 +449,7 @@ static void iommu_flush_domain(u16 domid)
 	__iommu_build_inv_iommu_pages(&cmd, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
 				      domid, 1, 1);
 
-	list_for_each_entry(iommu, &amd_iommu_list, list) {
+	for_each_iommu(iommu) {
 		spin_lock_irqsave(&iommu->lock, flags);
 		__iommu_queue_command(iommu, &cmd);
 		__iommu_completion_wait(iommu);
@@ -449,6 +458,35 @@ static void iommu_flush_domain(u16 domid)
 	}
 }
 
+void amd_iommu_flush_all_domains(void)
+{
+	int i;
+
+	for (i = 1; i < MAX_DOMAIN_ID; ++i) {
+		if (!test_bit(i, amd_iommu_pd_alloc_bitmap))
+			continue;
+		iommu_flush_domain(i);
+	}
+}
+
+void amd_iommu_flush_all_devices(void)
+{
+	struct amd_iommu *iommu;
+	int i;
+
+	for (i = 0; i <= amd_iommu_last_bdf; ++i) {
+		if (amd_iommu_pd_table[i] == NULL)
+			continue;
+
+		iommu = amd_iommu_rlookup_table[i];
+		if (!iommu)
+			continue;
+
+		iommu_queue_inv_dev_entry(iommu, i);
+		iommu_completion_wait(iommu);
+	}
+}
+
 /****************************************************************************
  *
  * The functions below are used the create the page table mappings for
@@ -468,7 +506,7 @@ static int iommu_map_page(struct protection_domain *dom,
 			  unsigned long phys_addr,
 			  int prot)
 {
-	u64 __pte, *pte, *page;
+	u64 __pte, *pte;
 
 	bus_addr  = PAGE_ALIGN(bus_addr);
 	phys_addr = PAGE_ALIGN(phys_addr);
@@ -477,27 +515,7 @@ static int iommu_map_page(struct protection_domain *dom,
 	if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
 		return -EINVAL;
 
-	pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(bus_addr)];
-
-	if (!IOMMU_PTE_PRESENT(*pte)) {
-		page = (u64 *)get_zeroed_page(GFP_KERNEL);
-		if (!page)
-			return -ENOMEM;
-		*pte = IOMMU_L2_PDE(virt_to_phys(page));
-	}
-
-	pte = IOMMU_PTE_PAGE(*pte);
-	pte = &pte[IOMMU_PTE_L1_INDEX(bus_addr)];
-
-	if (!IOMMU_PTE_PRESENT(*pte)) {
-		page = (u64 *)get_zeroed_page(GFP_KERNEL);
-		if (!page)
-			return -ENOMEM;
-		*pte = IOMMU_L1_PDE(virt_to_phys(page));
-	}
-
-	pte = IOMMU_PTE_PAGE(*pte);
-	pte = &pte[IOMMU_PTE_L0_INDEX(bus_addr)];
+	pte = alloc_pte(dom, bus_addr, NULL, GFP_KERNEL);
 
 	if (IOMMU_PTE_PRESENT(*pte))
 		return -EBUSY;
@@ -595,7 +613,8 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
 		 * as allocated in the aperture
 		 */
 		if (addr < dma_dom->aperture_size)
-			__set_bit(addr >> PAGE_SHIFT, dma_dom->bitmap);
+			__set_bit(addr >> PAGE_SHIFT,
+				  dma_dom->aperture[0]->bitmap);
 	}
 
 	return 0;
@@ -632,42 +651,191 @@ static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom,
  ****************************************************************************/
 
 /*
- * The address allocator core function.
+ * The address allocator core functions.
  *
  * called with domain->lock held
  */
+
+/*
+ * This function checks if there is a PTE for a given dma address. If
+ * there is one, it returns the pointer to it.
+ */
+static u64* fetch_pte(struct protection_domain *domain,
+		      unsigned long address)
+{
+	u64 *pte;
+
+	pte = &domain->pt_root[IOMMU_PTE_L2_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte))
+		return NULL;
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L1_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte))
+		return NULL;
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L0_INDEX(address)];
+
+	return pte;
+}
+
+/*
+ * This function is used to add a new aperture range to an existing
+ * aperture in case of dma_ops domain allocation or address allocation
+ * failure.
+ */
+static int alloc_new_range(struct amd_iommu *iommu,
+			   struct dma_ops_domain *dma_dom,
+			   bool populate, gfp_t gfp)
+{
+	int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
+	int i;
+
+#ifdef CONFIG_IOMMU_STRESS
+	populate = false;
+#endif
+
+	if (index >= APERTURE_MAX_RANGES)
+		return -ENOMEM;
+
+	dma_dom->aperture[index] = kzalloc(sizeof(struct aperture_range), gfp);
+	if (!dma_dom->aperture[index])
+		return -ENOMEM;
+
+	dma_dom->aperture[index]->bitmap = (void *)get_zeroed_page(gfp);
+	if (!dma_dom->aperture[index]->bitmap)
+		goto out_free;
+
+	dma_dom->aperture[index]->offset = dma_dom->aperture_size;
+
+	if (populate) {
+		unsigned long address = dma_dom->aperture_size;
+		int i, num_ptes = APERTURE_RANGE_PAGES / 512;
+		u64 *pte, *pte_page;
+
+		for (i = 0; i < num_ptes; ++i) {
+			pte = alloc_pte(&dma_dom->domain, address,
+					&pte_page, gfp);
+			if (!pte)
+				goto out_free;
+
+			dma_dom->aperture[index]->pte_pages[i] = pte_page;
+
+			address += APERTURE_RANGE_SIZE / 64;
+		}
+	}
+
+	dma_dom->aperture_size += APERTURE_RANGE_SIZE;
+
+	/* Intialize the exclusion range if necessary */
+	if (iommu->exclusion_start &&
+	    iommu->exclusion_start >= dma_dom->aperture[index]->offset &&
+	    iommu->exclusion_start < dma_dom->aperture_size) {
+		unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT;
+		int pages = iommu_num_pages(iommu->exclusion_start,
+					    iommu->exclusion_length,
+					    PAGE_SIZE);
+		dma_ops_reserve_addresses(dma_dom, startpage, pages);
+	}
+
+	/*
+	 * Check for areas already mapped as present in the new aperture
+	 * range and mark those pages as reserved in the allocator. Such
+	 * mappings may already exist as a result of requested unity
+	 * mappings for devices.
+	 */
+	for (i = dma_dom->aperture[index]->offset;
+	     i < dma_dom->aperture_size;
+	     i += PAGE_SIZE) {
+		u64 *pte = fetch_pte(&dma_dom->domain, i);
+		if (!pte || !IOMMU_PTE_PRESENT(*pte))
+			continue;
+
+		dma_ops_reserve_addresses(dma_dom, i << PAGE_SHIFT, 1);
+	}
+
+	return 0;
+
+out_free:
+	free_page((unsigned long)dma_dom->aperture[index]->bitmap);
+
+	kfree(dma_dom->aperture[index]);
+	dma_dom->aperture[index] = NULL;
+
+	return -ENOMEM;
+}
+
+static unsigned long dma_ops_area_alloc(struct device *dev,
+					struct dma_ops_domain *dom,
+					unsigned int pages,
+					unsigned long align_mask,
+					u64 dma_mask,
+					unsigned long start)
+{
+	unsigned long next_bit = dom->next_address % APERTURE_RANGE_SIZE;
+	int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT;
+	int i = start >> APERTURE_RANGE_SHIFT;
+	unsigned long boundary_size;
+	unsigned long address = -1;
+	unsigned long limit;
+
+	next_bit >>= PAGE_SHIFT;
+
+	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+			PAGE_SIZE) >> PAGE_SHIFT;
+
+	for (;i < max_index; ++i) {
+		unsigned long offset = dom->aperture[i]->offset >> PAGE_SHIFT;
+
+		if (dom->aperture[i]->offset >= dma_mask)
+			break;
+
+		limit = iommu_device_max_index(APERTURE_RANGE_PAGES, offset,
+					       dma_mask >> PAGE_SHIFT);
+
+		address = iommu_area_alloc(dom->aperture[i]->bitmap,
+					   limit, next_bit, pages, 0,
+					    boundary_size, align_mask);
+		if (address != -1) {
+			address = dom->aperture[i]->offset +
+				  (address << PAGE_SHIFT);
+			dom->next_address = address + (pages << PAGE_SHIFT);
+			break;
+		}
+
+		next_bit = 0;
+	}
+
+	return address;
+}
+
 static unsigned long dma_ops_alloc_addresses(struct device *dev,
 					     struct dma_ops_domain *dom,
 					     unsigned int pages,
 					     unsigned long align_mask,
 					     u64 dma_mask)
 {
-	unsigned long limit;
 	unsigned long address;
-	unsigned long boundary_size;
 
-	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-			PAGE_SIZE) >> PAGE_SHIFT;
-	limit = iommu_device_max_index(dom->aperture_size >> PAGE_SHIFT, 0,
-				       dma_mask >> PAGE_SHIFT);
+#ifdef CONFIG_IOMMU_STRESS
+	dom->next_address = 0;
+	dom->need_flush = true;
+#endif
 
-	if (dom->next_bit >= limit) {
-		dom->next_bit = 0;
-		dom->need_flush = true;
-	}
+	address = dma_ops_area_alloc(dev, dom, pages, align_mask,
+				     dma_mask, dom->next_address);
 
-	address = iommu_area_alloc(dom->bitmap, limit, dom->next_bit, pages,
-				   0 , boundary_size, align_mask);
 	if (address == -1) {
-		address = iommu_area_alloc(dom->bitmap, limit, 0, pages,
-				0, boundary_size, align_mask);
+		dom->next_address = 0;
+		address = dma_ops_area_alloc(dev, dom, pages, align_mask,
+					     dma_mask, 0);
 		dom->need_flush = true;
 	}
 
-	if (likely(address != -1)) {
-		dom->next_bit = address + pages;
-		address <<= PAGE_SHIFT;
-	} else
+	if (unlikely(address == -1))
 		address = bad_dma_address;
 
 	WARN_ON((address + (PAGE_SIZE*pages)) > dom->aperture_size);
@@ -684,11 +852,23 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom,
 				   unsigned long address,
 				   unsigned int pages)
 {
-	address >>= PAGE_SHIFT;
-	iommu_area_free(dom->bitmap, address, pages);
+	unsigned i = address >> APERTURE_RANGE_SHIFT;
+	struct aperture_range *range = dom->aperture[i];
 
-	if (address >= dom->next_bit)
+	BUG_ON(i >= APERTURE_MAX_RANGES || range == NULL);
+
+#ifdef CONFIG_IOMMU_STRESS
+	if (i < 4)
+		return;
+#endif
+
+	if (address >= dom->next_address)
 		dom->need_flush = true;
+
+	address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT;
+
+	iommu_area_free(range->bitmap, address, pages);
+
 }
 
 /****************************************************************************
@@ -736,12 +916,16 @@ static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
 				      unsigned long start_page,
 				      unsigned int pages)
 {
-	unsigned int last_page = dom->aperture_size >> PAGE_SHIFT;
+	unsigned int i, last_page = dom->aperture_size >> PAGE_SHIFT;
 
 	if (start_page + pages > last_page)
 		pages = last_page - start_page;
 
-	iommu_area_reserve(dom->bitmap, start_page, pages);
+	for (i = start_page; i < start_page + pages; ++i) {
+		int index = i / APERTURE_RANGE_PAGES;
+		int page  = i % APERTURE_RANGE_PAGES;
+		__set_bit(page, dom->aperture[index]->bitmap);
+	}
 }
 
 static void free_pagetable(struct protection_domain *domain)
@@ -780,14 +964,19 @@ static void free_pagetable(struct protection_domain *domain)
  */
 static void dma_ops_domain_free(struct dma_ops_domain *dom)
 {
+	int i;
+
 	if (!dom)
 		return;
 
 	free_pagetable(&dom->domain);
 
-	kfree(dom->pte_pages);
-
-	kfree(dom->bitmap);
+	for (i = 0; i < APERTURE_MAX_RANGES; ++i) {
+		if (!dom->aperture[i])
+			continue;
+		free_page((unsigned long)dom->aperture[i]->bitmap);
+		kfree(dom->aperture[i]);
+	}
 
 	kfree(dom);
 }
@@ -797,19 +986,9 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom)
  * It also intializes the page table and the address allocator data
  * structures required for the dma_ops interface
  */
-static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu,
-						   unsigned order)
+static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu)
 {
 	struct dma_ops_domain *dma_dom;
-	unsigned i, num_pte_pages;
-	u64 *l2_pde;
-	u64 address;
-
-	/*
-	 * Currently the DMA aperture must be between 32 MB and 1GB in size
-	 */
-	if ((order < 25) || (order > 30))
-		return NULL;
 
 	dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL);
 	if (!dma_dom)
@@ -826,55 +1005,20 @@ static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu,
 	dma_dom->domain.priv = dma_dom;
 	if (!dma_dom->domain.pt_root)
 		goto free_dma_dom;
-	dma_dom->aperture_size = (1ULL << order);
-	dma_dom->bitmap = kzalloc(dma_dom->aperture_size / (PAGE_SIZE * 8),
-				  GFP_KERNEL);
-	if (!dma_dom->bitmap)
-		goto free_dma_dom;
-	/*
-	 * mark the first page as allocated so we never return 0 as
-	 * a valid dma-address. So we can use 0 as error value
-	 */
-	dma_dom->bitmap[0] = 1;
-	dma_dom->next_bit = 0;
 
 	dma_dom->need_flush = false;
 	dma_dom->target_dev = 0xffff;
 
-	/* Intialize the exclusion range if necessary */
-	if (iommu->exclusion_start &&
-	    iommu->exclusion_start < dma_dom->aperture_size) {
-		unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT;
-		int pages = iommu_num_pages(iommu->exclusion_start,
-					    iommu->exclusion_length,
-					    PAGE_SIZE);
-		dma_ops_reserve_addresses(dma_dom, startpage, pages);
-	}
+	if (alloc_new_range(iommu, dma_dom, true, GFP_KERNEL))
+		goto free_dma_dom;
 
 	/*
-	 * At the last step, build the page tables so we don't need to
-	 * allocate page table pages in the dma_ops mapping/unmapping
-	 * path.
+	 * mark the first page as allocated so we never return 0 as
+	 * a valid dma-address. So we can use 0 as error value
 	 */
-	num_pte_pages = dma_dom->aperture_size / (PAGE_SIZE * 512);
-	dma_dom->pte_pages = kzalloc(num_pte_pages * sizeof(void *),
-			GFP_KERNEL);
-	if (!dma_dom->pte_pages)
-		goto free_dma_dom;
+	dma_dom->aperture[0]->bitmap[0] = 1;
+	dma_dom->next_address = 0;
 
-	l2_pde = (u64 *)get_zeroed_page(GFP_KERNEL);
-	if (l2_pde == NULL)
-		goto free_dma_dom;
-
-	dma_dom->domain.pt_root[0] = IOMMU_L2_PDE(virt_to_phys(l2_pde));
-
-	for (i = 0; i < num_pte_pages; ++i) {
-		dma_dom->pte_pages[i] = (u64 *)get_zeroed_page(GFP_KERNEL);
-		if (!dma_dom->pte_pages[i])
-			goto free_dma_dom;
-		address = virt_to_phys(dma_dom->pte_pages[i]);
-		l2_pde[i] = IOMMU_L1_PDE(address);
-	}
 
 	return dma_dom;
 
@@ -983,7 +1127,6 @@ static int device_change_notifier(struct notifier_block *nb,
 	struct protection_domain *domain;
 	struct dma_ops_domain *dma_domain;
 	struct amd_iommu *iommu;
-	int order = amd_iommu_aperture_order;
 	unsigned long flags;
 
 	if (devid > amd_iommu_last_bdf)
@@ -1002,17 +1145,7 @@ static int device_change_notifier(struct notifier_block *nb,
 			  "to a non-dma-ops domain\n", dev_name(dev));
 
 	switch (action) {
-	case BUS_NOTIFY_BOUND_DRIVER:
-		if (domain)
-			goto out;
-		dma_domain = find_protection_domain(devid);
-		if (!dma_domain)
-			dma_domain = iommu->default_dom;
-		attach_device(iommu, &dma_domain->domain, devid);
-		printk(KERN_INFO "AMD IOMMU: Using protection domain %d for "
-		       "device %s\n", dma_domain->domain.id, dev_name(dev));
-		break;
-	case BUS_NOTIFY_UNBIND_DRIVER:
+	case BUS_NOTIFY_UNBOUND_DRIVER:
 		if (!domain)
 			goto out;
 		detach_device(domain, devid);
@@ -1022,7 +1155,7 @@ static int device_change_notifier(struct notifier_block *nb,
 		dma_domain = find_protection_domain(devid);
 		if (dma_domain)
 			goto out;
-		dma_domain = dma_ops_domain_alloc(iommu, order);
+		dma_domain = dma_ops_domain_alloc(iommu);
 		if (!dma_domain)
 			goto out;
 		dma_domain->target_dev = devid;
@@ -1133,8 +1266,8 @@ static int get_device_resources(struct device *dev,
 			dma_dom = (*iommu)->default_dom;
 		*domain = &dma_dom->domain;
 		attach_device(*iommu, *domain, *bdf);
-		printk(KERN_INFO "AMD IOMMU: Using protection domain %d for "
-				"device %s\n", (*domain)->id, dev_name(dev));
+		DUMP_printk("Using protection domain %d for device %s\n",
+			    (*domain)->id, dev_name(dev));
 	}
 
 	if (domain_for_device(_bdf) == NULL)
@@ -1143,6 +1276,66 @@ static int get_device_resources(struct device *dev,
 	return 1;
 }
 
+/*
+ * If the pte_page is not yet allocated this function is called
+ */
+static u64* alloc_pte(struct protection_domain *dom,
+		      unsigned long address, u64 **pte_page, gfp_t gfp)
+{
+	u64 *pte, *page;
+
+	pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte)) {
+		page = (u64 *)get_zeroed_page(gfp);
+		if (!page)
+			return NULL;
+		*pte = IOMMU_L2_PDE(virt_to_phys(page));
+	}
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L1_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte)) {
+		page = (u64 *)get_zeroed_page(gfp);
+		if (!page)
+			return NULL;
+		*pte = IOMMU_L1_PDE(virt_to_phys(page));
+	}
+
+	pte = IOMMU_PTE_PAGE(*pte);
+
+	if (pte_page)
+		*pte_page = pte;
+
+	pte = &pte[IOMMU_PTE_L0_INDEX(address)];
+
+	return pte;
+}
+
+/*
+ * This function fetches the PTE for a given address in the aperture
+ */
+static u64* dma_ops_get_pte(struct dma_ops_domain *dom,
+			    unsigned long address)
+{
+	struct aperture_range *aperture;
+	u64 *pte, *pte_page;
+
+	aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
+	if (!aperture)
+		return NULL;
+
+	pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
+	if (!pte) {
+		pte = alloc_pte(&dom->domain, address, &pte_page, GFP_ATOMIC);
+		aperture->pte_pages[APERTURE_PAGE_INDEX(address)] = pte_page;
+	} else
+		pte += IOMMU_PTE_L0_INDEX(address);
+
+	return pte;
+}
+
 /*
  * This is the generic map function. It maps one 4kb page at paddr to
  * the given address in the DMA address space for the domain.
@@ -1159,8 +1352,9 @@ static dma_addr_t dma_ops_domain_map(struct amd_iommu *iommu,
 
 	paddr &= PAGE_MASK;
 
-	pte  = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
-	pte += IOMMU_PTE_L0_INDEX(address);
+	pte  = dma_ops_get_pte(dom, address);
+	if (!pte)
+		return bad_dma_address;
 
 	__pte = paddr | IOMMU_PTE_P | IOMMU_PTE_FC;
 
@@ -1185,14 +1379,20 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
 				 struct dma_ops_domain *dom,
 				 unsigned long address)
 {
+	struct aperture_range *aperture;
 	u64 *pte;
 
 	if (address >= dom->aperture_size)
 		return;
 
-	WARN_ON(address & ~PAGE_MASK || address >= dom->aperture_size);
+	aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
+	if (!aperture)
+		return;
+
+	pte  = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
+	if (!pte)
+		return;
 
-	pte  = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
 	pte += IOMMU_PTE_L0_INDEX(address);
 
 	WARN_ON(!*pte);
@@ -1216,7 +1416,7 @@ static dma_addr_t __map_single(struct device *dev,
 			       u64 dma_mask)
 {
 	dma_addr_t offset = paddr & ~PAGE_MASK;
-	dma_addr_t address, start;
+	dma_addr_t address, start, ret;
 	unsigned int pages;
 	unsigned long align_mask = 0;
 	int i;
@@ -1232,14 +1432,33 @@ static dma_addr_t __map_single(struct device *dev,
 	if (align)
 		align_mask = (1UL << get_order(size)) - 1;
 
+retry:
 	address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask,
 					  dma_mask);
-	if (unlikely(address == bad_dma_address))
-		goto out;
+	if (unlikely(address == bad_dma_address)) {
+		/*
+		 * setting next_address here will let the address
+		 * allocator only scan the new allocated range in the
+		 * first run. This is a small optimization.
+		 */
+		dma_dom->next_address = dma_dom->aperture_size;
+
+		if (alloc_new_range(iommu, dma_dom, false, GFP_ATOMIC))
+			goto out;
+
+		/*
+		 * aperture was sucessfully enlarged by 128 MB, try
+		 * allocation again
+		 */
+		goto retry;
+	}
 
 	start = address;
 	for (i = 0; i < pages; ++i) {
-		dma_ops_domain_map(iommu, dma_dom, start, paddr, dir);
+		ret = dma_ops_domain_map(iommu, dma_dom, start, paddr, dir);
+		if (ret == bad_dma_address)
+			goto out_unmap;
+
 		paddr += PAGE_SIZE;
 		start += PAGE_SIZE;
 	}
@@ -1255,6 +1474,17 @@ static dma_addr_t __map_single(struct device *dev,
 
 out:
 	return address;
+
+out_unmap:
+
+	for (--i; i >= 0; --i) {
+		start -= PAGE_SIZE;
+		dma_ops_domain_unmap(iommu, dma_dom, start);
+	}
+
+	dma_ops_free_addresses(dma_dom, address, pages);
+
+	return bad_dma_address;
 }
 
 /*
@@ -1537,8 +1767,10 @@ static void *alloc_coherent(struct device *dev, size_t size,
 	*dma_addr = __map_single(dev, iommu, domain->priv, paddr,
 				 size, DMA_BIDIRECTIONAL, true, dma_mask);
 
-	if (*dma_addr == bad_dma_address)
+	if (*dma_addr == bad_dma_address) {
+		spin_unlock_irqrestore(&domain->lock, flags);
 		goto out_free;
+	}
 
 	iommu_completion_wait(iommu);
 
@@ -1625,7 +1857,6 @@ static void prealloc_protection_domains(void)
 	struct pci_dev *dev = NULL;
 	struct dma_ops_domain *dma_dom;
 	struct amd_iommu *iommu;
-	int order = amd_iommu_aperture_order;
 	u16 devid;
 
 	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
@@ -1638,7 +1869,7 @@ static void prealloc_protection_domains(void)
 		iommu = amd_iommu_rlookup_table[devid];
 		if (!iommu)
 			continue;
-		dma_dom = dma_ops_domain_alloc(iommu, order);
+		dma_dom = dma_ops_domain_alloc(iommu);
 		if (!dma_dom)
 			continue;
 		init_unity_mappings_for_device(dma_dom, devid);
@@ -1664,7 +1895,6 @@ static struct dma_map_ops amd_iommu_dma_ops = {
 int __init amd_iommu_init_dma_ops(void)
 {
 	struct amd_iommu *iommu;
-	int order = amd_iommu_aperture_order;
 	int ret;
 
 	/*
@@ -1672,8 +1902,8 @@ int __init amd_iommu_init_dma_ops(void)
 	 * found in the system. Devices not assigned to any other
 	 * protection domain will be assigned to the default one.
 	 */
-	list_for_each_entry(iommu, &amd_iommu_list, list) {
-		iommu->default_dom = dma_ops_domain_alloc(iommu, order);
+	for_each_iommu(iommu) {
+		iommu->default_dom = dma_ops_domain_alloc(iommu);
 		if (iommu->default_dom == NULL)
 			return -ENOMEM;
 		iommu->default_dom->domain.flags |= PD_DEFAULT_MASK;
@@ -1710,7 +1940,7 @@ int __init amd_iommu_init_dma_ops(void)
 
 free_domains:
 
-	list_for_each_entry(iommu, &amd_iommu_list, list) {
+	for_each_iommu(iommu) {
 		if (iommu->default_dom)
 			dma_ops_domain_free(iommu->default_dom);
 	}
@@ -1842,7 +2072,7 @@ static int amd_iommu_attach_device(struct iommu_domain *dom,
 
 	old_domain = domain_for_device(devid);
 	if (old_domain)
-		return -EBUSY;
+		detach_device(old_domain, devid);
 
 	attach_device(iommu, domain, devid);
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 8c0be0902dac..238989ec077d 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -115,15 +115,21 @@ struct ivmd_header {
 	u64 range_length;
 } __attribute__((packed));
 
+bool amd_iommu_dump;
+
 static int __initdata amd_iommu_detected;
 
 u16 amd_iommu_last_bdf;			/* largest PCI device id we have
 					   to handle */
 LIST_HEAD(amd_iommu_unity_map);		/* a list of required unity mappings
 					   we find in ACPI */
-unsigned amd_iommu_aperture_order = 26; /* size of aperture in power of 2 */
+#ifdef CONFIG_IOMMU_STRESS
+bool amd_iommu_isolate = false;
+#else
 bool amd_iommu_isolate = true;		/* if true, device isolation is
 					   enabled */
+#endif
+
 bool amd_iommu_unmap_flush;		/* if true, flush on every unmap */
 
 LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
@@ -175,7 +181,7 @@ static inline void update_last_devid(u16 devid)
 static inline unsigned long tbl_size(int entry_size)
 {
 	unsigned shift = PAGE_SHIFT +
-			 get_order(amd_iommu_last_bdf * entry_size);
+			 get_order(((int)amd_iommu_last_bdf + 1) * entry_size);
 
 	return 1UL << shift;
 }
@@ -193,7 +199,7 @@ static inline unsigned long tbl_size(int entry_size)
  * This function set the exclusion range in the IOMMU. DMA accesses to the
  * exclusion range are passed through untranslated
  */
-static void __init iommu_set_exclusion_range(struct amd_iommu *iommu)
+static void iommu_set_exclusion_range(struct amd_iommu *iommu)
 {
 	u64 start = iommu->exclusion_start & PAGE_MASK;
 	u64 limit = (start + iommu->exclusion_length) & PAGE_MASK;
@@ -225,7 +231,7 @@ static void __init iommu_set_device_table(struct amd_iommu *iommu)
 }
 
 /* Generic functions to enable/disable certain features of the IOMMU. */
-static void __init iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
+static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
 {
 	u32 ctrl;
 
@@ -244,7 +250,7 @@ static void __init iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
 }
 
 /* Function to enable the hardware */
-static void __init iommu_enable(struct amd_iommu *iommu)
+static void iommu_enable(struct amd_iommu *iommu)
 {
 	printk(KERN_INFO "AMD IOMMU: Enabling IOMMU at %s cap 0x%hx\n",
 	       dev_name(&iommu->dev->dev), iommu->cap_ptr);
@@ -252,11 +258,9 @@ static void __init iommu_enable(struct amd_iommu *iommu)
 	iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
 }
 
-/* Function to enable IOMMU event logging and event interrupts */
-static void __init iommu_enable_event_logging(struct amd_iommu *iommu)
+static void iommu_disable(struct amd_iommu *iommu)
 {
-	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
-	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
+	iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
 }
 
 /*
@@ -413,25 +417,36 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
 {
 	u8 *cmd_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 			get_order(CMD_BUFFER_SIZE));
-	u64 entry;
 
 	if (cmd_buf == NULL)
 		return NULL;
 
 	iommu->cmd_buf_size = CMD_BUFFER_SIZE;
 
-	entry = (u64)virt_to_phys(cmd_buf);
+	return cmd_buf;
+}
+
+/*
+ * This function writes the command buffer address to the hardware and
+ * enables it.
+ */
+static void iommu_enable_command_buffer(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	BUG_ON(iommu->cmd_buf == NULL);
+
+	entry = (u64)virt_to_phys(iommu->cmd_buf);
 	entry |= MMIO_CMD_SIZE_512;
+
 	memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
-			&entry, sizeof(entry));
+		    &entry, sizeof(entry));
 
 	/* set head and tail to zero manually */
 	writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
 	writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
 
 	iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
-
-	return cmd_buf;
 }
 
 static void __init free_command_buffer(struct amd_iommu *iommu)
@@ -443,20 +458,27 @@ static void __init free_command_buffer(struct amd_iommu *iommu)
 /* allocates the memory where the IOMMU will log its events to */
 static u8 * __init alloc_event_buffer(struct amd_iommu *iommu)
 {
-	u64 entry;
 	iommu->evt_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 						get_order(EVT_BUFFER_SIZE));
 
 	if (iommu->evt_buf == NULL)
 		return NULL;
 
+	return iommu->evt_buf;
+}
+
+static void iommu_enable_event_buffer(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	BUG_ON(iommu->evt_buf == NULL);
+
 	entry = (u64)virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;
+
 	memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET,
 		    &entry, sizeof(entry));
 
-	iommu->evt_buf_size = EVT_BUFFER_SIZE;
-
-	return iommu->evt_buf;
+	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
 }
 
 static void __init free_event_buffer(struct amd_iommu *iommu)
@@ -596,32 +618,83 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	p += sizeof(struct ivhd_header);
 	end += h->length;
 
+
 	while (p < end) {
 		e = (struct ivhd_entry *)p;
 		switch (e->type) {
 		case IVHD_DEV_ALL:
+
+			DUMP_printk("  DEV_ALL\t\t\t first devid: %02x:%02x.%x"
+				    " last device %02x:%02x.%x flags: %02x\n",
+				    PCI_BUS(iommu->first_device),
+				    PCI_SLOT(iommu->first_device),
+				    PCI_FUNC(iommu->first_device),
+				    PCI_BUS(iommu->last_device),
+				    PCI_SLOT(iommu->last_device),
+				    PCI_FUNC(iommu->last_device),
+				    e->flags);
+
 			for (dev_i = iommu->first_device;
 					dev_i <= iommu->last_device; ++dev_i)
 				set_dev_entry_from_acpi(iommu, dev_i,
 							e->flags, 0);
 			break;
 		case IVHD_DEV_SELECT:
+
+			DUMP_printk("  DEV_SELECT\t\t\t devid: %02x:%02x.%x "
+				    "flags: %02x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags);
+
 			devid = e->devid;
 			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
 			break;
 		case IVHD_DEV_SELECT_RANGE_START:
+
+			DUMP_printk("  DEV_SELECT_RANGE_START\t "
+				    "devid: %02x:%02x.%x flags: %02x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags);
+
 			devid_start = e->devid;
 			flags = e->flags;
 			ext_flags = 0;
 			alias = false;
 			break;
 		case IVHD_DEV_ALIAS:
+
+			DUMP_printk("  DEV_ALIAS\t\t\t devid: %02x:%02x.%x "
+				    "flags: %02x devid_to: %02x:%02x.%x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags,
+				    PCI_BUS(e->ext >> 8),
+				    PCI_SLOT(e->ext >> 8),
+				    PCI_FUNC(e->ext >> 8));
+
 			devid = e->devid;
 			devid_to = e->ext >> 8;
-			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
+			set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0);
 			amd_iommu_alias_table[devid] = devid_to;
 			break;
 		case IVHD_DEV_ALIAS_RANGE:
+
+			DUMP_printk("  DEV_ALIAS_RANGE\t\t "
+				    "devid: %02x:%02x.%x flags: %02x "
+				    "devid_to: %02x:%02x.%x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags,
+				    PCI_BUS(e->ext >> 8),
+				    PCI_SLOT(e->ext >> 8),
+				    PCI_FUNC(e->ext >> 8));
+
 			devid_start = e->devid;
 			flags = e->flags;
 			devid_to = e->ext >> 8;
@@ -629,17 +702,39 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 			alias = true;
 			break;
 		case IVHD_DEV_EXT_SELECT:
+
+			DUMP_printk("  DEV_EXT_SELECT\t\t devid: %02x:%02x.%x "
+				    "flags: %02x ext: %08x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags, e->ext);
+
 			devid = e->devid;
 			set_dev_entry_from_acpi(iommu, devid, e->flags,
 						e->ext);
 			break;
 		case IVHD_DEV_EXT_SELECT_RANGE:
+
+			DUMP_printk("  DEV_EXT_SELECT_RANGE\t devid: "
+				    "%02x:%02x.%x flags: %02x ext: %08x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid),
+				    e->flags, e->ext);
+
 			devid_start = e->devid;
 			flags = e->flags;
 			ext_flags = e->ext;
 			alias = false;
 			break;
 		case IVHD_DEV_RANGE_END:
+
+			DUMP_printk("  DEV_RANGE_END\t\t devid: %02x:%02x.%x\n",
+				    PCI_BUS(e->devid),
+				    PCI_SLOT(e->devid),
+				    PCI_FUNC(e->devid));
+
 			devid = e->devid;
 			for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
 				if (alias)
@@ -679,7 +774,7 @@ static void __init free_iommu_all(void)
 {
 	struct amd_iommu *iommu, *next;
 
-	list_for_each_entry_safe(iommu, next, &amd_iommu_list, list) {
+	for_each_iommu_safe(iommu, next) {
 		list_del(&iommu->list);
 		free_iommu_one(iommu);
 		kfree(iommu);
@@ -710,7 +805,6 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	if (!iommu->mmio_base)
 		return -ENOMEM;
 
-	iommu_set_device_table(iommu);
 	iommu->cmd_buf = alloc_command_buffer(iommu);
 	if (!iommu->cmd_buf)
 		return -ENOMEM;
@@ -746,6 +840,15 @@ static int __init init_iommu_all(struct acpi_table_header *table)
 		h = (struct ivhd_header *)p;
 		switch (*p) {
 		case ACPI_IVHD_TYPE:
+
+			DUMP_printk("IOMMU: device: %02x:%02x.%01x cap: %04x "
+				    "seg: %d flags: %01x info %04x\n",
+				    PCI_BUS(h->devid), PCI_SLOT(h->devid),
+				    PCI_FUNC(h->devid), h->cap_ptr,
+				    h->pci_seg, h->flags, h->info);
+			DUMP_printk("       mmio-addr: %016llx\n",
+				    h->mmio_phys);
+
 			iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL);
 			if (iommu == NULL)
 				return -ENOMEM;
@@ -773,56 +876,9 @@ static int __init init_iommu_all(struct acpi_table_header *table)
  *
  ****************************************************************************/
 
-static int __init iommu_setup_msix(struct amd_iommu *iommu)
-{
-	struct amd_iommu *curr;
-	struct msix_entry entries[32]; /* only 32 supported by AMD IOMMU */
-	int nvec = 0, i;
-
-	list_for_each_entry(curr, &amd_iommu_list, list) {
-		if (curr->dev == iommu->dev) {
-			entries[nvec].entry = curr->evt_msi_num;
-			entries[nvec].vector = 0;
-			curr->int_enabled = true;
-			nvec++;
-		}
-	}
-
-	if (pci_enable_msix(iommu->dev, entries, nvec)) {
-		pci_disable_msix(iommu->dev);
-		return 1;
-	}
-
-	for (i = 0; i < nvec; ++i) {
-		int r = request_irq(entries->vector, amd_iommu_int_handler,
-				    IRQF_SAMPLE_RANDOM,
-				    "AMD IOMMU",
-				    NULL);
-		if (r)
-			goto out_free;
-	}
-
-	return 0;
-
-out_free:
-	for (i -= 1; i >= 0; --i)
-		free_irq(entries->vector, NULL);
-
-	pci_disable_msix(iommu->dev);
-
-	return 1;
-}
-
 static int __init iommu_setup_msi(struct amd_iommu *iommu)
 {
 	int r;
-	struct amd_iommu *curr;
-
-	list_for_each_entry(curr, &amd_iommu_list, list) {
-		if (curr->dev == iommu->dev)
-			curr->int_enabled = true;
-	}
-
 
 	if (pci_enable_msi(iommu->dev))
 		return 1;
@@ -837,17 +893,18 @@ static int __init iommu_setup_msi(struct amd_iommu *iommu)
 		return 1;
 	}
 
+	iommu->int_enabled = true;
+	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
+
 	return 0;
 }
 
-static int __init iommu_init_msi(struct amd_iommu *iommu)
+static int iommu_init_msi(struct amd_iommu *iommu)
 {
 	if (iommu->int_enabled)
 		return 0;
 
-	if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSIX))
-		return iommu_setup_msix(iommu);
-	else if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI))
+	if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI))
 		return iommu_setup_msi(iommu);
 
 	return 1;
@@ -899,6 +956,7 @@ static int __init init_exclusion_range(struct ivmd_header *m)
 static int __init init_unity_map_range(struct ivmd_header *m)
 {
 	struct unity_map_entry *e = 0;
+	char *s;
 
 	e = kzalloc(sizeof(*e), GFP_KERNEL);
 	if (e == NULL)
@@ -906,14 +964,19 @@ static int __init init_unity_map_range(struct ivmd_header *m)
 
 	switch (m->type) {
 	default:
+		kfree(e);
+		return 0;
 	case ACPI_IVMD_TYPE:
+		s = "IVMD_TYPEi\t\t\t";
 		e->devid_start = e->devid_end = m->devid;
 		break;
 	case ACPI_IVMD_TYPE_ALL:
+		s = "IVMD_TYPE_ALL\t\t";
 		e->devid_start = 0;
 		e->devid_end = amd_iommu_last_bdf;
 		break;
 	case ACPI_IVMD_TYPE_RANGE:
+		s = "IVMD_TYPE_RANGE\t\t";
 		e->devid_start = m->devid;
 		e->devid_end = m->aux;
 		break;
@@ -922,6 +985,13 @@ static int __init init_unity_map_range(struct ivmd_header *m)
 	e->address_end = e->address_start + PAGE_ALIGN(m->range_length);
 	e->prot = m->flags >> 1;
 
+	DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x"
+		    " range_start: %016llx range_end: %016llx flags: %x\n", s,
+		    PCI_BUS(e->devid_start), PCI_SLOT(e->devid_start),
+		    PCI_FUNC(e->devid_start), PCI_BUS(e->devid_end),
+		    PCI_SLOT(e->devid_end), PCI_FUNC(e->devid_end),
+		    e->address_start, e->address_end, m->flags);
+
 	list_add_tail(&e->list, &amd_iommu_unity_map);
 
 	return 0;
@@ -967,18 +1037,28 @@ static void init_device_table(void)
  * This function finally enables all IOMMUs found in the system after
  * they have been initialized
  */
-static void __init enable_iommus(void)
+static void enable_iommus(void)
 {
 	struct amd_iommu *iommu;
 
-	list_for_each_entry(iommu, &amd_iommu_list, list) {
+	for_each_iommu(iommu) {
+		iommu_set_device_table(iommu);
+		iommu_enable_command_buffer(iommu);
+		iommu_enable_event_buffer(iommu);
 		iommu_set_exclusion_range(iommu);
 		iommu_init_msi(iommu);
-		iommu_enable_event_logging(iommu);
 		iommu_enable(iommu);
 	}
 }
 
+static void disable_iommus(void)
+{
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu)
+		iommu_disable(iommu);
+}
+
 /*
  * Suspend/Resume support
  * disable suspend until real resume implemented
@@ -986,12 +1066,31 @@ static void __init enable_iommus(void)
 
 static int amd_iommu_resume(struct sys_device *dev)
 {
+	/*
+	 * Disable IOMMUs before reprogramming the hardware registers.
+	 * IOMMU is still enabled from the resume kernel.
+	 */
+	disable_iommus();
+
+	/* re-load the hardware */
+	enable_iommus();
+
+	/*
+	 * we have to flush after the IOMMUs are enabled because a
+	 * disabled IOMMU will never execute the commands we send
+	 */
+	amd_iommu_flush_all_domains();
+	amd_iommu_flush_all_devices();
+
 	return 0;
 }
 
 static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
 {
-	return -EINVAL;
+	/* disable IOMMUs to go out of the way for BIOS */
+	disable_iommus();
+
+	return 0;
 }
 
 static struct sysdev_class amd_iommu_sysdev_class = {
@@ -1137,9 +1236,6 @@ int __init amd_iommu_init(void)
 
 	enable_iommus();
 
-	printk(KERN_INFO "AMD IOMMU: aperture size is %d MB\n",
-			(1 << (amd_iommu_aperture_order-20)));
-
 	printk(KERN_INFO "AMD IOMMU: device isolation ");
 	if (amd_iommu_isolate)
 		printk("enabled\n");
@@ -1211,6 +1307,13 @@ void __init amd_iommu_detect(void)
  *
  ****************************************************************************/
 
+static int __init parse_amd_iommu_dump(char *str)
+{
+	amd_iommu_dump = true;
+
+	return 1;
+}
+
 static int __init parse_amd_iommu_options(char *str)
 {
 	for (; *str; ++str) {
@@ -1225,15 +1328,5 @@ static int __init parse_amd_iommu_options(char *str)
 	return 1;
 }
 
-static int __init parse_amd_iommu_size_options(char *str)
-{
-	unsigned order = PAGE_SHIFT + get_order(memparse(str, &str));
-
-	if ((order > 24) && (order < 31))
-		amd_iommu_aperture_order = order;
-
-	return 1;
-}
-
+__setup("amd_iommu_dump", parse_amd_iommu_dump);
 __setup("amd_iommu=", parse_amd_iommu_options);
-__setup("amd_iommu_size=", parse_amd_iommu_size_options);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index f2870920f246..076d3881f3da 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -14,6 +14,7 @@
  *	Mikael Pettersson	:	PM converted to driver model.
  */
 
+#include <linux/perf_counter.h>
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/acpi_pmtmr.h>
@@ -34,6 +35,7 @@
 #include <linux/smp.h>
 #include <linux/mm.h>
 
+#include <asm/perf_counter.h>
 #include <asm/pgalloc.h>
 #include <asm/atomic.h>
 #include <asm/mpspec.h>
@@ -98,6 +100,29 @@ early_param("lapic", parse_lapic);
 /* Local APIC was disabled by the BIOS and enabled by the kernel */
 static int enabled_via_apicbase;
 
+/*
+ * Handle interrupt mode configuration register (IMCR).
+ * This register controls whether the interrupt signals
+ * that reach the BSP come from the master PIC or from the
+ * local APIC. Before entering Symmetric I/O Mode, either
+ * the BIOS or the operating system must switch out of
+ * PIC Mode by changing the IMCR.
+ */
+static inline void imcr_pic_to_apic(void)
+{
+	/* select IMCR register */
+	outb(0x70, 0x22);
+	/* NMI and 8259 INTR go through APIC */
+	outb(0x01, 0x23);
+}
+
+static inline void imcr_apic_to_pic(void)
+{
+	/* select IMCR register */
+	outb(0x70, 0x22);
+	/* NMI and 8259 INTR go directly to BSP */
+	outb(0x00, 0x23);
+}
 #endif
 
 #ifdef CONFIG_X86_64
@@ -111,13 +136,19 @@ static __init int setup_apicpmtimer(char *s)
 __setup("apicpmtimer", setup_apicpmtimer);
 #endif
 
+int x2apic_mode;
 #ifdef CONFIG_X86_X2APIC
-int x2apic;
 /* x2apic enabled before OS handover */
 static int x2apic_preenabled;
 static int disable_x2apic;
 static __init int setup_nox2apic(char *str)
 {
+	if (x2apic_enabled()) {
+		pr_warning("Bios already enabled x2apic, "
+			   "can't enforce nox2apic");
+		return 0;
+	}
+
 	disable_x2apic = 1;
 	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
 	return 0;
@@ -209,6 +240,31 @@ static int modern_apic(void)
 	return lapic_get_version() >= 0x14;
 }
 
+/*
+ * bare function to substitute write operation
+ * and it's _that_ fast :)
+ */
+static void native_apic_write_dummy(u32 reg, u32 v)
+{
+	WARN_ON_ONCE((cpu_has_apic || !disable_apic));
+}
+
+static u32 native_apic_read_dummy(u32 reg)
+{
+	WARN_ON_ONCE((cpu_has_apic && !disable_apic));
+	return 0;
+}
+
+/*
+ * right after this call apic->write/read doesn't do anything
+ * note that there is no restore operation it works one way
+ */
+void apic_disable(void)
+{
+	apic->read = native_apic_read_dummy;
+	apic->write = native_apic_write_dummy;
+}
+
 void native_apic_wait_icr_idle(void)
 {
 	while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
@@ -348,7 +404,7 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 
 static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
 {
-	unsigned long reg = (lvt_off << 4) + APIC_EILVT0;
+	unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
 	unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
 
 	apic_write(reg, v);
@@ -815,7 +871,7 @@ void clear_local_APIC(void)
 	u32 v;
 
 	/* APIC hasn't been mapped yet */
-	if (!x2apic && !apic_phys)
+	if (!x2apic_mode && !apic_phys)
 		return;
 
 	maxlvt = lapic_get_maxlvt();
@@ -1133,6 +1189,7 @@ void __cpuinit setup_local_APIC(void)
 		apic_write(APIC_ESR, 0);
 	}
 #endif
+	perf_counters_lapic_init();
 
 	preempt_disable();
 
@@ -1287,7 +1344,7 @@ void check_x2apic(void)
 {
 	if (x2apic_enabled()) {
 		pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
-		x2apic_preenabled = x2apic = 1;
+		x2apic_preenabled = x2apic_mode = 1;
 	}
 }
 
@@ -1295,7 +1352,7 @@ void enable_x2apic(void)
 {
 	int msr, msr2;
 
-	if (!x2apic)
+	if (!x2apic_mode)
 		return;
 
 	rdmsr(MSR_IA32_APICBASE, msr, msr2);
@@ -1304,6 +1361,7 @@ void enable_x2apic(void)
 		wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
 	}
 }
+#endif /* CONFIG_X86_X2APIC */
 
 void __init enable_IR_x2apic(void)
 {
@@ -1312,32 +1370,21 @@ void __init enable_IR_x2apic(void)
 	unsigned long flags;
 	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
-	if (!cpu_has_x2apic)
-		return;
-
-	if (!x2apic_preenabled && disable_x2apic) {
-		pr_info("Skipped enabling x2apic and Interrupt-remapping "
-			"because of nox2apic\n");
-		return;
-	}
-
-	if (x2apic_preenabled && disable_x2apic)
-		panic("Bios already enabled x2apic, can't enforce nox2apic");
-
-	if (!x2apic_preenabled && skip_ioapic_setup) {
-		pr_info("Skipped enabling x2apic and Interrupt-remapping "
-			"because of skipping io-apic setup\n");
-		return;
-	}
-
 	ret = dmar_table_init();
 	if (ret) {
-		pr_info("dmar_table_init() failed with %d:\n", ret);
+		pr_debug("dmar_table_init() failed with %d:\n", ret);
+		goto ir_failed;
+	}
 
-		if (x2apic_preenabled)
-			panic("x2apic enabled by bios. But IR enabling failed");
-		else
-			pr_info("Not enabling x2apic,Intr-remapping\n");
+	if (!intr_remapping_supported()) {
+		pr_debug("intr-remapping not supported\n");
+		goto ir_failed;
+	}
+
+
+	if (!x2apic_preenabled && skip_ioapic_setup) {
+		pr_info("Skipped enabling intr-remap because of skipping "
+			"io-apic setup\n");
 		return;
 	}
 
@@ -1357,19 +1404,16 @@ void __init enable_IR_x2apic(void)
 	mask_IO_APIC_setup(ioapic_entries);
 	mask_8259A();
 
-	ret = enable_intr_remapping(EIM_32BIT_APIC_ID);
-
-	if (ret && x2apic_preenabled) {
-		local_irq_restore(flags);
-		panic("x2apic enabled by bios. But IR enabling failed");
-	}
-
+	ret = enable_intr_remapping(x2apic_supported());
 	if (ret)
 		goto end_restore;
 
-	if (!x2apic) {
-		x2apic = 1;
+	pr_info("Enabled Interrupt-remapping\n");
+
+	if (x2apic_supported() && !x2apic_mode) {
+		x2apic_mode = 1;
 		enable_x2apic();
+		pr_info("Enabled x2apic\n");
 	}
 
 end_restore:
@@ -1378,37 +1422,34 @@ end_restore:
 		 * IR enabling failed
 		 */
 		restore_IO_APIC_setup(ioapic_entries);
-	else
-		reinit_intr_remapped_IO_APIC(x2apic_preenabled, ioapic_entries);
 
 	unmask_8259A();
 	local_irq_restore(flags);
 
 end:
-	if (!ret) {
-		if (!x2apic_preenabled)
-			pr_info("Enabled x2apic and interrupt-remapping\n");
-		else
-			pr_info("Enabled Interrupt-remapping\n");
-	} else
-		pr_err("Failed to enable Interrupt-remapping and x2apic\n");
 	if (ioapic_entries)
 		free_ioapic_entries(ioapic_entries);
+
+	if (!ret)
+		return;
+
+ir_failed:
+	if (x2apic_preenabled)
+		panic("x2apic enabled by bios. But IR enabling failed");
+	else if (cpu_has_x2apic)
+		pr_info("Not enabling x2apic,Intr-remapping\n");
 #else
 	if (!cpu_has_x2apic)
 		return;
 
 	if (x2apic_preenabled)
 		panic("x2apic enabled prior OS handover,"
-		      " enable CONFIG_INTR_REMAP");
-
-	pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
-		" and x2apic\n");
+		      " enable CONFIG_X86_X2APIC, CONFIG_INTR_REMAP");
 #endif
 
 	return;
 }
-#endif /* CONFIG_X86_X2APIC */
+
 
 #ifdef CONFIG_X86_64
 /*
@@ -1425,7 +1466,6 @@ static int __init detect_init_APIC(void)
 	}
 
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
-	boot_cpu_physical_apicid = 0;
 	return 0;
 }
 #else
@@ -1539,32 +1579,49 @@ void __init early_init_lapic_mapping(void)
  */
 void __init init_apic_mappings(void)
 {
-	if (x2apic) {
+	unsigned int new_apicid;
+
+	if (x2apic_mode) {
 		boot_cpu_physical_apicid = read_apic_id();
 		return;
 	}
 
-	/*
-	 * If no local APIC can be found then set up a fake all
-	 * zeroes page to simulate the local APIC and another
-	 * one for the IO-APIC.
-	 */
+	/* If no local APIC can be found return early */
 	if (!smp_found_config && detect_init_APIC()) {
-		apic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
-		apic_phys = __pa(apic_phys);
-	} else
+		/* lets NOP'ify apic operations */
+		pr_info("APIC: disable apic facility\n");
+		apic_disable();
+	} else {
 		apic_phys = mp_lapic_addr;
 
-	set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
-	apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
-				APIC_BASE, apic_phys);
+		/*
+		 * acpi lapic path already maps that address in
+		 * acpi_register_lapic_address()
+		 */
+		if (!acpi_lapic)
+			set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
+
+		apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
+					APIC_BASE, apic_phys);
+	}
 
 	/*
 	 * Fetch the APIC ID of the BSP in case we have a
 	 * default configuration (or the MP table is broken).
 	 */
-	if (boot_cpu_physical_apicid == -1U)
-		boot_cpu_physical_apicid = read_apic_id();
+	new_apicid = read_apic_id();
+	if (boot_cpu_physical_apicid != new_apicid) {
+		boot_cpu_physical_apicid = new_apicid;
+		/*
+		 * yeah -- we lie about apic_version
+		 * in case if apic was disabled via boot option
+		 * but it's not a problem for SMP compiled kernel
+		 * since smp_sanity_check is prepared for such a case
+		 * and disable smp mode
+		 */
+		apic_version[new_apicid] =
+			 GET_APIC_VERSION(apic_read(APIC_LVR));
+	}
 }
 
 /*
@@ -1733,8 +1790,7 @@ void __init connect_bsp_APIC(void)
 		 */
 		apic_printk(APIC_VERBOSE, "leaving PIC mode, "
 				"enabling APIC mode.\n");
-		outb(0x70, 0x22);
-		outb(0x01, 0x23);
+		imcr_pic_to_apic();
 	}
 #endif
 	if (apic->enable_apic_mode)
@@ -1762,8 +1818,7 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 		 */
 		apic_printk(APIC_VERBOSE, "disabling APIC mode, "
 				"entering PIC mode.\n");
-		outb(0x70, 0x22);
-		outb(0x00, 0x23);
+		imcr_apic_to_pic();
 		return;
 	}
 #endif
@@ -1969,10 +2024,10 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
 
 	local_irq_save(flags);
 	disable_local_APIC();
-#ifdef CONFIG_INTR_REMAP
+
 	if (intr_remapping_enabled)
 		disable_intr_remapping();
-#endif
+
 	local_irq_restore(flags);
 	return 0;
 }
@@ -1982,42 +2037,34 @@ static int lapic_resume(struct sys_device *dev)
 	unsigned int l, h;
 	unsigned long flags;
 	int maxlvt;
-
-#ifdef CONFIG_INTR_REMAP
-	int ret;
+	int ret = 0;
 	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
 	if (!apic_pm_state.active)
 		return 0;
 
 	local_irq_save(flags);
-	if (x2apic) {
+	if (intr_remapping_enabled) {
 		ioapic_entries = alloc_ioapic_entries();
 		if (!ioapic_entries) {
 			WARN(1, "Alloc ioapic_entries in lapic resume failed.");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto restore;
 		}
 
 		ret = save_IO_APIC_setup(ioapic_entries);
 		if (ret) {
 			WARN(1, "Saving IO-APIC state failed: %d\n", ret);
 			free_ioapic_entries(ioapic_entries);
-			return ret;
+			goto restore;
 		}
 
 		mask_IO_APIC_setup(ioapic_entries);
 		mask_8259A();
-		enable_x2apic();
 	}
-#else
-	if (!apic_pm_state.active)
-		return 0;
 
-	local_irq_save(flags);
-	if (x2apic)
+	if (x2apic_mode)
 		enable_x2apic();
-#endif
-
 	else {
 		/*
 		 * Make sure the APICBASE points to the right address
@@ -2055,21 +2102,16 @@ static int lapic_resume(struct sys_device *dev)
 	apic_write(APIC_ESR, 0);
 	apic_read(APIC_ESR);
 
-#ifdef CONFIG_INTR_REMAP
-	if (intr_remapping_enabled)
-		reenable_intr_remapping(EIM_32BIT_APIC_ID);
-
-	if (x2apic) {
+	if (intr_remapping_enabled) {
+		reenable_intr_remapping(x2apic_mode);
 		unmask_8259A();
 		restore_IO_APIC_setup(ioapic_entries);
 		free_ioapic_entries(ioapic_entries);
 	}
-#endif
-
+restore:
 	local_irq_restore(flags);
 
-
-	return 0;
+	return ret;
 }
 
 /*
@@ -2117,31 +2159,14 @@ static void apic_pm_activate(void) { }
 #endif	/* CONFIG_PM */
 
 #ifdef CONFIG_X86_64
-/*
- * apic_is_clustered_box() -- Check if we can expect good TSC
- *
- * Thus far, the major user of this is IBM's Summit2 series:
- *
- * Clustered boxes may have unsynced TSC problems if they are
- * multi-chassis. Use available data to take a good guess.
- * If in doubt, go HPET.
- */
-__cpuinit int apic_is_clustered_box(void)
+
+static int __cpuinit apic_cluster_num(void)
 {
 	int i, clusters, zeros;
 	unsigned id;
 	u16 *bios_cpu_apicid;
 	DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
 
-	/*
-	 * there is not this kind of box with AMD CPU yet.
-	 * Some AMD box with quadcore cpu and 8 sockets apicid
-	 * will be [4, 0x23] or [8, 0x27] could be thought to
-	 * vsmp box still need checking...
-	 */
-	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
-		return 0;
-
 	bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 	bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
 
@@ -2177,18 +2202,67 @@ __cpuinit int apic_is_clustered_box(void)
 			++zeros;
 	}
 
-	/* ScaleMP vSMPowered boxes have one cluster per board and TSCs are
-	 * not guaranteed to be synced between boards
-	 */
-	if (is_vsmp_box() && clusters > 1)
+	return clusters;
+}
+
+static int __cpuinitdata multi_checked;
+static int __cpuinitdata multi;
+
+static int __cpuinit set_multi(const struct dmi_system_id *d)
+{
+	if (multi)
+		return 0;
+	pr_info("APIC: %s detected, Multi Chassis\n", d->ident);
+	multi = 1;
+	return 0;
+}
+
+static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
+	{
+		.callback = set_multi,
+		.ident = "IBM System Summit2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Summit2"),
+		},
+	},
+	{}
+};
+
+static void __cpuinit dmi_check_multi(void)
+{
+	if (multi_checked)
+		return;
+
+	dmi_check_system(multi_dmi_table);
+	multi_checked = 1;
+}
+
+/*
+ * apic_is_clustered_box() -- Check if we can expect good TSC
+ *
+ * Thus far, the major user of this is IBM's Summit2 series:
+ * Clustered boxes may have unsynced TSC problems if they are
+ * multi-chassis.
+ * Use DMI to check them
+ */
+__cpuinit int apic_is_clustered_box(void)
+{
+	dmi_check_multi();
+	if (multi)
 		return 1;
 
+	if (!is_vsmp_box())
+		return 0;
+
 	/*
-	 * If clusters > 2, then should be multi-chassis.
-	 * May have to revisit this when multi-core + hyperthreaded CPUs come
-	 * out, but AFAIK this will work even for them.
+	 * ScaleMP vSMPowered boxes have one cluster per board and TSCs are
+	 * not guaranteed to be synced between boards
 	 */
-	return (clusters > 2);
+	if (apic_cluster_num() > 1)
+		return 1;
+
+	return 0;
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 306e5e88fb6f..d0c99abc26c3 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -161,7 +161,7 @@ static int flat_apic_id_registered(void)
 
 static int flat_phys_pkg_id(int initial_apic_id, int index_msb)
 {
-	return hard_smp_processor_id() >> index_msb;
+	return initial_apic_id >> index_msb;
 }
 
 struct apic apic_flat =  {
@@ -235,7 +235,7 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	 * regardless of how many processors are present (x86_64 ES7000
 	 * is an example).
 	 */
-	if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
+	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
 		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
 		printk(KERN_DEBUG "system APIC only can use physical flat");
 		return 1;
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 302947775575..69328ac8de9c 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -145,7 +145,7 @@ es7000_rename_gsi(int ioapic, int gsi)
 	return gsi;
 }
 
-static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
+static int __cpuinit wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
 {
 	unsigned long vect = 0, psaival = 0;
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 30da617d18e4..ef8d9290c7ea 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -59,6 +59,7 @@
 #include <asm/setup.h>
 #include <asm/irq_remapping.h>
 #include <asm/hpet.h>
+#include <asm/hw_irq.h>
 #include <asm/uv/uv_hub.h>
 #include <asm/uv/uv_irq.h>
 
@@ -129,12 +130,9 @@ struct irq_pin_list {
 	struct irq_pin_list *next;
 };
 
-static struct irq_pin_list *get_one_free_irq_2_pin(int cpu)
+static struct irq_pin_list *get_one_free_irq_2_pin(int node)
 {
 	struct irq_pin_list *pin;
-	int node;
-
-	node = cpu_to_node(cpu);
 
 	pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
 
@@ -148,9 +146,6 @@ struct irq_cfg {
 	unsigned move_cleanup_count;
 	u8 vector;
 	u8 move_in_progress : 1;
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-	u8 move_desc_pending : 1;
-#endif
 };
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -182,16 +177,18 @@ int __init arch_early_irq_init(void)
 	struct irq_cfg *cfg;
 	struct irq_desc *desc;
 	int count;
+	int node;
 	int i;
 
 	cfg = irq_cfgx;
 	count = ARRAY_SIZE(irq_cfgx);
+	node= cpu_to_node(boot_cpu_id);
 
 	for (i = 0; i < count; i++) {
 		desc = irq_to_desc(i);
 		desc->chip_data = &cfg[i];
-		alloc_bootmem_cpumask_var(&cfg[i].domain);
-		alloc_bootmem_cpumask_var(&cfg[i].old_domain);
+		zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
+		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
 		if (i < NR_IRQS_LEGACY)
 			cpumask_setall(cfg[i].domain);
 	}
@@ -212,12 +209,9 @@ static struct irq_cfg *irq_cfg(unsigned int irq)
 	return cfg;
 }
 
-static struct irq_cfg *get_one_free_irq_cfg(int cpu)
+static struct irq_cfg *get_one_free_irq_cfg(int node)
 {
 	struct irq_cfg *cfg;
-	int node;
-
-	node = cpu_to_node(cpu);
 
 	cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
 	if (cfg) {
@@ -238,13 +232,13 @@ static struct irq_cfg *get_one_free_irq_cfg(int cpu)
 	return cfg;
 }
 
-int arch_init_chip_data(struct irq_desc *desc, int cpu)
+int arch_init_chip_data(struct irq_desc *desc, int node)
 {
 	struct irq_cfg *cfg;
 
 	cfg = desc->chip_data;
 	if (!cfg) {
-		desc->chip_data = get_one_free_irq_cfg(cpu);
+		desc->chip_data = get_one_free_irq_cfg(node);
 		if (!desc->chip_data) {
 			printk(KERN_ERR "can not alloc irq_cfg\n");
 			BUG_ON(1);
@@ -254,10 +248,9 @@ int arch_init_chip_data(struct irq_desc *desc, int cpu)
 	return 0;
 }
 
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-
+/* for move_irq_desc */
 static void
-init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
+init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int node)
 {
 	struct irq_pin_list *old_entry, *head, *tail, *entry;
 
@@ -266,7 +259,7 @@ init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
 	if (!old_entry)
 		return;
 
-	entry = get_one_free_irq_2_pin(cpu);
+	entry = get_one_free_irq_2_pin(node);
 	if (!entry)
 		return;
 
@@ -276,7 +269,7 @@ init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
 	tail		= entry;
 	old_entry	= old_entry->next;
 	while (old_entry) {
-		entry = get_one_free_irq_2_pin(cpu);
+		entry = get_one_free_irq_2_pin(node);
 		if (!entry) {
 			entry = head;
 			while (entry) {
@@ -316,12 +309,12 @@ static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
 }
 
 void arch_init_copy_chip_data(struct irq_desc *old_desc,
-				 struct irq_desc *desc, int cpu)
+				 struct irq_desc *desc, int node)
 {
 	struct irq_cfg *cfg;
 	struct irq_cfg *old_cfg;
 
-	cfg = get_one_free_irq_cfg(cpu);
+	cfg = get_one_free_irq_cfg(node);
 
 	if (!cfg)
 		return;
@@ -332,7 +325,7 @@ void arch_init_copy_chip_data(struct irq_desc *old_desc,
 
 	memcpy(cfg, old_cfg, sizeof(struct irq_cfg));
 
-	init_copy_irq_2_pin(old_cfg, cfg, cpu);
+	init_copy_irq_2_pin(old_cfg, cfg, node);
 }
 
 static void free_irq_cfg(struct irq_cfg *old_cfg)
@@ -356,19 +349,7 @@ void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
 		old_desc->chip_data = NULL;
 	}
 }
-
-static void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg = desc->chip_data;
-
-	if (!cfg->move_in_progress) {
-		/* it means that domain is not changed */
-		if (!cpumask_intersects(desc->affinity, mask))
-			cfg->move_desc_pending = 1;
-	}
-}
-#endif
+/* end for move_irq_desc */
 
 #else
 static struct irq_cfg *irq_cfg(unsigned int irq)
@@ -378,13 +359,6 @@ static struct irq_cfg *irq_cfg(unsigned int irq)
 
 #endif
 
-#ifndef CONFIG_NUMA_MIGRATE_IRQ_DESC
-static inline void
-set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-}
-#endif
-
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -518,132 +492,18 @@ static void ioapic_mask_entry(int apic, int pin)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-#ifdef CONFIG_SMP
-static void send_cleanup_vector(struct irq_cfg *cfg)
-{
-	cpumask_var_t cleanup_mask;
-
-	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
-		unsigned int i;
-		cfg->move_cleanup_count = 0;
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
-			cfg->move_cleanup_count++;
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
-			apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
-	} else {
-		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
-		cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
-		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
-		free_cpumask_var(cleanup_mask);
-	}
-	cfg->move_in_progress = 0;
-}
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-	u8 vector = cfg->vector;
-
-	entry = cfg->irq_2_pin;
-	for (;;) {
-		unsigned int reg;
-
-		if (!entry)
-			break;
-
-		apic = entry->apic;
-		pin = entry->pin;
-		/*
-		 * With interrupt-remapping, destination information comes
-		 * from interrupt-remapping table entry.
-		 */
-		if (!irq_remapped(irq))
-			io_apic_write(apic, 0x11 + pin*2, dest);
-		reg = io_apic_read(apic, 0x10 + pin*2);
-		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
-		reg |= vector;
-		io_apic_modify(apic, 0x10 + pin*2, reg);
-		if (!entry->next)
-			break;
-		entry = entry->next;
-	}
-}
-
-static int
-assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
-
-/*
- * Either sets desc->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
- * leaves desc->affinity untouched.
- */
-static unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg;
-	unsigned int irq;
-
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return BAD_APICID;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-	if (assign_irq_vector(irq, cfg, mask))
-		return BAD_APICID;
-
-	/* check that before desc->addinity get updated */
-	set_extra_move_desc(desc, mask);
-
-	cpumask_copy(desc->affinity, mask);
-
-	return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
-}
-
-static void
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int dest;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	dest = set_desc_affinity(desc, mask);
-	if (dest != BAD_APICID) {
-		/* Only the high 8 bits are valid. */
-		dest = SET_APIC_LOGICAL_ID(dest);
-		__target_IO_APIC_irq(irq, dest, cfg);
-	}
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-static void
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	set_ioapic_affinity_irq_desc(desc, mask);
-}
-#endif /* CONFIG_SMP */
-
 /*
  * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
-static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
+static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	struct irq_pin_list *entry;
 
 	entry = cfg->irq_2_pin;
 	if (!entry) {
-		entry = get_one_free_irq_2_pin(cpu);
+		entry = get_one_free_irq_2_pin(node);
 		if (!entry) {
 			printk(KERN_ERR "can not alloc irq_2_pin to add %d - %d\n",
 					apic, pin);
@@ -663,7 +523,7 @@ static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
 		entry = entry->next;
 	}
 
-	entry->next = get_one_free_irq_2_pin(cpu);
+	entry->next = get_one_free_irq_2_pin(node);
 	entry = entry->next;
 	entry->apic = apic;
 	entry->pin = pin;
@@ -672,7 +532,7 @@ static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
 /*
  * Reroute an IRQ to a different pin.
  */
-static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
+static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
 				      int oldapic, int oldpin,
 				      int newapic, int newpin)
 {
@@ -692,7 +552,7 @@ static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
 
 	/* why? call replace before add? */
 	if (!replaced)
-		add_pin_to_irq_cpu(cfg, cpu, newapic, newpin);
+		add_pin_to_irq_node(cfg, node, newapic, newpin);
 }
 
 static inline void io_apic_modify_irq(struct irq_cfg *cfg,
@@ -850,7 +710,6 @@ static int __init ioapic_pirq_setup(char *str)
 __setup("pirq=", ioapic_pirq_setup);
 #endif /* CONFIG_X86_32 */
 
-#ifdef CONFIG_INTR_REMAP
 struct IO_APIC_route_entry **alloc_ioapic_entries(void)
 {
 	int apic;
@@ -948,20 +807,6 @@ int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries)
 	return 0;
 }
 
-void reinit_intr_remapped_IO_APIC(int intr_remapping,
-	struct IO_APIC_route_entry **ioapic_entries)
-
-{
-	/*
-	 * for now plain restore of previous settings.
-	 * TBD: In the case of OS enabling interrupt-remapping,
-	 * IO-APIC RTE's need to be setup to point to interrupt-remapping
-	 * table entries. for now, do a plain restore, and wait for
-	 * the setup_IO_APIC_irqs() to do proper initialization.
-	 */
-	restore_IO_APIC_setup(ioapic_entries);
-}
-
 void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
 {
 	int apic;
@@ -971,7 +816,6 @@ void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
 
 	kfree(ioapic_entries);
 }
-#endif
 
 /*
  * Find the IRQ entry number of a certain pin.
@@ -1032,54 +876,6 @@ static int __init find_isa_irq_apic(int irq, int type)
 	return -1;
 }
 
-/*
- * Find a specific PCI IRQ entry.
- * Not an __init, possibly needed by modules
- */
-static int pin_2_irq(int idx, int apic, int pin);
-
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
-{
-	int apic, i, best_guess = -1;
-
-	apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
-		bus, slot, pin);
-	if (test_bit(bus, mp_bus_not_pci)) {
-		apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
-		return -1;
-	}
-	for (i = 0; i < mp_irq_entries; i++) {
-		int lbus = mp_irqs[i].srcbus;
-
-		for (apic = 0; apic < nr_ioapics; apic++)
-			if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
-			    mp_irqs[i].dstapic == MP_APIC_ALL)
-				break;
-
-		if (!test_bit(lbus, mp_bus_not_pci) &&
-		    !mp_irqs[i].irqtype &&
-		    (bus == lbus) &&
-		    (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
-			int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
-
-			if (!(apic || IO_APIC_IRQ(irq)))
-				continue;
-
-			if (pin == (mp_irqs[i].srcbusirq & 3))
-				return irq;
-			/*
-			 * Use the first all-but-pin matching entry as a
-			 * best-guess fuzzy result for broken mptables.
-			 */
-			if (best_guess < 0)
-				best_guess = irq;
-		}
-	}
-	return best_guess;
-}
-
-EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
 /*
  * EISA Edge/Level control register, ELCR
@@ -1298,6 +1094,64 @@ static int pin_2_irq(int idx, int apic, int pin)
 	return irq;
 }
 
+/*
+ * Find a specific PCI IRQ entry.
+ * Not an __init, possibly needed by modules
+ */
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
+				struct io_apic_irq_attr *irq_attr)
+{
+	int apic, i, best_guess = -1;
+
+	apic_printk(APIC_DEBUG,
+		    "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
+		    bus, slot, pin);
+	if (test_bit(bus, mp_bus_not_pci)) {
+		apic_printk(APIC_VERBOSE,
+			    "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
+		return -1;
+	}
+	for (i = 0; i < mp_irq_entries; i++) {
+		int lbus = mp_irqs[i].srcbus;
+
+		for (apic = 0; apic < nr_ioapics; apic++)
+			if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
+			    mp_irqs[i].dstapic == MP_APIC_ALL)
+				break;
+
+		if (!test_bit(lbus, mp_bus_not_pci) &&
+		    !mp_irqs[i].irqtype &&
+		    (bus == lbus) &&
+		    (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
+			int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
+
+			if (!(apic || IO_APIC_IRQ(irq)))
+				continue;
+
+			if (pin == (mp_irqs[i].srcbusirq & 3)) {
+				set_io_apic_irq_attr(irq_attr, apic,
+						     mp_irqs[i].dstirq,
+						     irq_trigger(i),
+						     irq_polarity(i));
+				return irq;
+			}
+			/*
+			 * Use the first all-but-pin matching entry as a
+			 * best-guess fuzzy result for broken mptables.
+			 */
+			if (best_guess < 0) {
+				set_io_apic_irq_attr(irq_attr, apic,
+						     mp_irqs[i].dstirq,
+						     irq_trigger(i),
+						     irq_polarity(i));
+				best_guess = irq;
+			}
+		}
+	}
+	return best_guess;
+}
+EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
+
 void lock_vector_lock(void)
 {
 	/* Used to the online set of cpus does not change
@@ -1628,58 +1482,70 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
 	ioapic_write_entry(apic_id, pin, entry);
 }
 
+static struct {
+	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+} mp_ioapic_routing[MAX_IO_APICS];
+
 static void __init setup_IO_APIC_irqs(void)
 {
-	int apic_id, pin, idx, irq;
+	int apic_id = 0, pin, idx, irq;
 	int notcon = 0;
 	struct irq_desc *desc;
 	struct irq_cfg *cfg;
-	int cpu = boot_cpu_id;
+	int node = cpu_to_node(boot_cpu_id);
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
-	for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
-		for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
+#ifdef CONFIG_ACPI
+	if (!acpi_disabled && acpi_ioapic) {
+		apic_id = mp_find_ioapic(0);
+		if (apic_id < 0)
+			apic_id = 0;
+	}
+#endif
 
-			idx = find_irq_entry(apic_id, pin, mp_INT);
-			if (idx == -1) {
-				if (!notcon) {
-					notcon = 1;
-					apic_printk(APIC_VERBOSE,
-						KERN_DEBUG " %d-%d",
-						mp_ioapics[apic_id].apicid, pin);
-				} else
-					apic_printk(APIC_VERBOSE, " %d-%d",
-						mp_ioapics[apic_id].apicid, pin);
-				continue;
-			}
-			if (notcon) {
+	for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
+		idx = find_irq_entry(apic_id, pin, mp_INT);
+		if (idx == -1) {
+			if (!notcon) {
+				notcon = 1;
 				apic_printk(APIC_VERBOSE,
-					" (apicid-pin) not connected\n");
-				notcon = 0;
-			}
-
-			irq = pin_2_irq(idx, apic_id, pin);
-
-			/*
-			 * Skip the timer IRQ if there's a quirk handler
-			 * installed and if it returns 1:
-			 */
-			if (apic->multi_timer_check &&
-					apic->multi_timer_check(apic_id, irq))
-				continue;
-
-			desc = irq_to_desc_alloc_cpu(irq, cpu);
-			if (!desc) {
-				printk(KERN_INFO "can not get irq_desc for %d\n", irq);
-				continue;
-			}
-			cfg = desc->chip_data;
-			add_pin_to_irq_cpu(cfg, cpu, apic_id, pin);
-
-			setup_IO_APIC_irq(apic_id, pin, irq, desc,
-					irq_trigger(idx), irq_polarity(idx));
+					KERN_DEBUG " %d-%d",
+					mp_ioapics[apic_id].apicid, pin);
+			} else
+				apic_printk(APIC_VERBOSE, " %d-%d",
+					mp_ioapics[apic_id].apicid, pin);
+			continue;
 		}
+		if (notcon) {
+			apic_printk(APIC_VERBOSE,
+				" (apicid-pin) not connected\n");
+			notcon = 0;
+		}
+
+		irq = pin_2_irq(idx, apic_id, pin);
+
+		/*
+		 * Skip the timer IRQ if there's a quirk handler
+		 * installed and if it returns 1:
+		 */
+		if (apic->multi_timer_check &&
+				apic->multi_timer_check(apic_id, irq))
+			continue;
+
+		desc = irq_to_desc_alloc_node(irq, node);
+		if (!desc) {
+			printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+			continue;
+		}
+		cfg = desc->chip_data;
+		add_pin_to_irq_node(cfg, node, apic_id, pin);
+		/*
+		 * don't mark it in pin_programmed, so later acpi could
+		 * set it correctly when irq < 16
+		 */
+		setup_IO_APIC_irq(apic_id, pin, irq, desc,
+				irq_trigger(idx), irq_polarity(idx));
 	}
 
 	if (notcon)
@@ -1869,7 +1735,7 @@ __apicdebuginit(void) print_APIC_bitfield(int base)
 
 __apicdebuginit(void) print_local_APIC(void *dummy)
 {
-	unsigned int v, ver, maxlvt;
+	unsigned int i, v, ver, maxlvt;
 	u64 icr;
 
 	if (apic_verbosity == APIC_QUIET)
@@ -1957,6 +1823,18 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
 	printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
 	v = apic_read(APIC_TDCR);
 	printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
+
+	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+		v = apic_read(APIC_EFEAT);
+		maxlvt = (v >> 16) & 0xff;
+		printk(KERN_DEBUG "... APIC EFEAT: %08x\n", v);
+		v = apic_read(APIC_ECTRL);
+		printk(KERN_DEBUG "... APIC ECTRL: %08x\n", v);
+		for (i = 0; i < maxlvt; i++) {
+			v = apic_read(APIC_EILVTn(i));
+			printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v);
+		}
+	}
 	printk("\n");
 }
 
@@ -2005,6 +1883,11 @@ __apicdebuginit(void) print_PIC(void)
 __apicdebuginit(int) print_all_ICs(void)
 {
 	print_PIC();
+
+	/* don't print out if apic is not there */
+	if (!cpu_has_apic || disable_apic)
+		return 0;
+
 	print_all_local_APICs();
 	print_IO_APIC();
 
@@ -2360,6 +2243,118 @@ static int ioapic_retrigger_irq(unsigned int irq)
  */
 
 #ifdef CONFIG_SMP
+static void send_cleanup_vector(struct irq_cfg *cfg)
+{
+	cpumask_var_t cleanup_mask;
+
+	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
+		unsigned int i;
+		cfg->move_cleanup_count = 0;
+		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+			cfg->move_cleanup_count++;
+		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+			apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
+	} else {
+		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+		cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
+		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		free_cpumask_var(cleanup_mask);
+	}
+	cfg->move_in_progress = 0;
+}
+
+static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
+{
+	int apic, pin;
+	struct irq_pin_list *entry;
+	u8 vector = cfg->vector;
+
+	entry = cfg->irq_2_pin;
+	for (;;) {
+		unsigned int reg;
+
+		if (!entry)
+			break;
+
+		apic = entry->apic;
+		pin = entry->pin;
+		/*
+		 * With interrupt-remapping, destination information comes
+		 * from interrupt-remapping table entry.
+		 */
+		if (!irq_remapped(irq))
+			io_apic_write(apic, 0x11 + pin*2, dest);
+		reg = io_apic_read(apic, 0x10 + pin*2);
+		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
+		reg |= vector;
+		io_apic_modify(apic, 0x10 + pin*2, reg);
+		if (!entry->next)
+			break;
+		entry = entry->next;
+	}
+}
+
+static int
+assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
+
+/*
+ * Either sets desc->affinity to a valid value, and returns
+ * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
+ * leaves desc->affinity untouched.
+ */
+static unsigned int
+set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
+{
+	struct irq_cfg *cfg;
+	unsigned int irq;
+
+	if (!cpumask_intersects(mask, cpu_online_mask))
+		return BAD_APICID;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+	if (assign_irq_vector(irq, cfg, mask))
+		return BAD_APICID;
+
+	cpumask_copy(desc->affinity, mask);
+
+	return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+}
+
+static int
+set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	unsigned int dest;
+	unsigned int irq;
+	int ret = -1;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	dest = set_desc_affinity(desc, mask);
+	if (dest != BAD_APICID) {
+		/* Only the high 8 bits are valid. */
+		dest = SET_APIC_LOGICAL_ID(dest);
+		__target_IO_APIC_irq(irq, dest, cfg);
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+
+	return ret;
+}
+
+static int
+set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+
+	return set_ioapic_affinity_irq_desc(desc, mask);
+}
 
 #ifdef CONFIG_INTR_REMAP
 
@@ -2374,26 +2369,25 @@ static int ioapic_retrigger_irq(unsigned int irq)
  * Real vector that is used for interrupting cpu will be coming from
  * the interrupt-remapping table entry.
  */
-static void
+static int
 migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 {
 	struct irq_cfg *cfg;
 	struct irte irte;
 	unsigned int dest;
 	unsigned int irq;
+	int ret = -1;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
-		return;
+		return ret;
 
 	irq = desc->irq;
 	if (get_irte(irq, &irte))
-		return;
+		return ret;
 
 	cfg = desc->chip_data;
 	if (assign_irq_vector(irq, cfg, mask))
-		return;
-
-	set_extra_move_desc(desc, mask);
+		return ret;
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
 
@@ -2409,27 +2403,30 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 		send_cleanup_vector(cfg);
 
 	cpumask_copy(desc->affinity, mask);
+
+	return 0;
 }
 
 /*
  * Migrates the IRQ destination in the process context.
  */
-static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
 					    const struct cpumask *mask)
 {
-	migrate_ioapic_irq_desc(desc, mask);
+	return migrate_ioapic_irq_desc(desc, mask);
 }
-static void set_ir_ioapic_affinity_irq(unsigned int irq,
+static int set_ir_ioapic_affinity_irq(unsigned int irq,
 				       const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	set_ir_ioapic_affinity_irq_desc(desc, mask);
+	return set_ir_ioapic_affinity_irq_desc(desc, mask);
 }
 #else
-static inline void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+static inline int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
 						   const struct cpumask *mask)
 {
+	return 0;
 }
 #endif
 
@@ -2491,86 +2488,19 @@ static void irq_complete_move(struct irq_desc **descp)
 	struct irq_cfg *cfg = desc->chip_data;
 	unsigned vector, me;
 
-	if (likely(!cfg->move_in_progress)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-		if (likely(!cfg->move_desc_pending))
-			return;
-
-		/* domain has not changed, but affinity did */
-		me = smp_processor_id();
-		if (cpumask_test_cpu(me, desc->affinity)) {
-			*descp = desc = move_irq_desc(desc, me);
-			/* get the new one */
-			cfg = desc->chip_data;
-			cfg->move_desc_pending = 0;
-		}
-#endif
+	if (likely(!cfg->move_in_progress))
 		return;
-	}
 
 	vector = ~get_irq_regs()->orig_ax;
 	me = smp_processor_id();
 
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-		*descp = desc = move_irq_desc(desc, me);
-		/* get the new one */
-		cfg = desc->chip_data;
-#endif
+	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
 		send_cleanup_vector(cfg);
-	}
 }
 #else
 static inline void irq_complete_move(struct irq_desc **descp) {}
 #endif
 
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-
-	entry = cfg->irq_2_pin;
-	for (;;) {
-
-		if (!entry)
-			break;
-
-		apic = entry->apic;
-		pin = entry->pin;
-		io_apic_eoi(apic, pin);
-		entry = entry->next;
-	}
-}
-
-static void
-eoi_ioapic_irq(struct irq_desc *desc)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	__eoi_ioapic_irq(irq, cfg);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-#ifdef CONFIG_X86_X2APIC
-static void ack_x2apic_level(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	ack_x2APIC_irq();
-	eoi_ioapic_irq(desc);
-}
-
-static void ack_x2apic_edge(unsigned int irq)
-{
-	ack_x2APIC_irq();
-}
-#endif
-
 static void ack_apic_edge(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -2634,9 +2564,6 @@ static void ack_apic_level(unsigned int irq)
 	 */
 	ack_APIC_irq();
 
-	if (irq_remapped(irq))
-		eoi_ioapic_irq(desc);
-
 	/* Now we can move and renable the irq */
 	if (unlikely(do_unmask_irq)) {
 		/* Only migrate the irq if the ack has been received.
@@ -2683,22 +2610,50 @@ static void ack_apic_level(unsigned int irq)
 }
 
 #ifdef CONFIG_INTR_REMAP
+static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+{
+	int apic, pin;
+	struct irq_pin_list *entry;
+
+	entry = cfg->irq_2_pin;
+	for (;;) {
+
+		if (!entry)
+			break;
+
+		apic = entry->apic;
+		pin = entry->pin;
+		io_apic_eoi(apic, pin);
+		entry = entry->next;
+	}
+}
+
+static void
+eoi_ioapic_irq(struct irq_desc *desc)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	unsigned int irq;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	__eoi_ioapic_irq(irq, cfg);
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
 static void ir_ack_apic_edge(unsigned int irq)
 {
-#ifdef CONFIG_X86_X2APIC
-       if (x2apic_enabled())
-               return ack_x2apic_edge(irq);
-#endif
-       return ack_apic_edge(irq);
+	ack_APIC_irq();
 }
 
 static void ir_ack_apic_level(unsigned int irq)
 {
-#ifdef CONFIG_X86_X2APIC
-       if (x2apic_enabled())
-               return ack_x2apic_level(irq);
-#endif
-       return ack_apic_level(irq);
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	ack_APIC_irq();
+	eoi_ioapic_irq(desc);
 }
 #endif /* CONFIG_INTR_REMAP */
 
@@ -2903,7 +2858,7 @@ static inline void __init check_timer(void)
 {
 	struct irq_desc *desc = irq_to_desc(0);
 	struct irq_cfg *cfg = desc->chip_data;
-	int cpu = boot_cpu_id;
+	int node = cpu_to_node(boot_cpu_id);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
 	int no_pin1 = 0;
@@ -2969,7 +2924,7 @@ static inline void __init check_timer(void)
 		 * Ok, does IRQ0 through the IOAPIC work?
 		 */
 		if (no_pin1) {
-			add_pin_to_irq_cpu(cfg, cpu, apic1, pin1);
+			add_pin_to_irq_node(cfg, node, apic1, pin1);
 			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
 		} else {
 			/* for edge trigger, setup_IO_APIC_irq already
@@ -3006,7 +2961,7 @@ static inline void __init check_timer(void)
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
-		replace_pin_at_irq_cpu(cfg, cpu, apic1, pin1, apic2, pin2);
+		replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
@@ -3218,14 +3173,13 @@ static int nr_irqs_gsi = NR_IRQS_LEGACY;
 /*
  * Dynamic irq allocate and deallocation
  */
-unsigned int create_irq_nr(unsigned int irq_want)
+unsigned int create_irq_nr(unsigned int irq_want, int node)
 {
 	/* Allocate an unused irq */
 	unsigned int irq;
 	unsigned int new;
 	unsigned long flags;
 	struct irq_cfg *cfg_new = NULL;
-	int cpu = boot_cpu_id;
 	struct irq_desc *desc_new = NULL;
 
 	irq = 0;
@@ -3234,7 +3188,7 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 	spin_lock_irqsave(&vector_lock, flags);
 	for (new = irq_want; new < nr_irqs; new++) {
-		desc_new = irq_to_desc_alloc_cpu(new, cpu);
+		desc_new = irq_to_desc_alloc_node(new, node);
 		if (!desc_new) {
 			printk(KERN_INFO "can not get irq_desc for %d\n", new);
 			continue;
@@ -3243,6 +3197,9 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 		if (cfg_new->vector != 0)
 			continue;
+
+		desc_new = move_irq_desc(desc_new, node);
+
 		if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
 			irq = new;
 		break;
@@ -3260,11 +3217,12 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 int create_irq(void)
 {
+	int node = cpu_to_node(boot_cpu_id);
 	unsigned int irq_want;
 	int irq;
 
 	irq_want = nr_irqs_gsi;
-	irq = create_irq_nr(irq_want);
+	irq = create_irq_nr(irq_want, node);
 
 	if (irq == 0)
 		irq = -1;
@@ -3366,7 +3324,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 }
 
 #ifdef CONFIG_SMP
-static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3375,7 +3333,7 @@ static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
@@ -3387,13 +3345,15 @@ static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg_desc(desc, &msg);
+
+	return 0;
 }
 #ifdef CONFIG_INTR_REMAP
 /*
  * Migrate the MSI irq to another cpumask. This migration is
  * done in the process context using interrupt-remapping hardware.
  */
-static void
+static int
 ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -3402,11 +3362,11 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	struct irte irte;
 
 	if (get_irte(irq, &irte))
-		return;
+		return -1;
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	irte.vector = cfg->vector;
 	irte.dest_id = IRTE_DEST(dest);
@@ -3423,6 +3383,8 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	 */
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
+
+	return 0;
 }
 
 #endif
@@ -3518,15 +3480,17 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	unsigned int irq_want;
 	struct intel_iommu *iommu = NULL;
 	int index = 0;
+	int node;
 
 	/* x86 doesn't support multiple MSI yet */
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
+	node = dev_to_node(&dev->dev);
 	irq_want = nr_irqs_gsi;
 	sub_handle = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = create_irq_nr(irq_want);
+		irq = create_irq_nr(irq_want, node);
 		if (irq == 0)
 			return -1;
 		irq_want = irq + 1;
@@ -3576,7 +3540,7 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 #if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
 #ifdef CONFIG_SMP
-static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3585,7 +3549,7 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
@@ -3597,6 +3561,8 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	dmar_msi_write(irq, &msg);
+
+	return 0;
 }
 
 #endif /* CONFIG_SMP */
@@ -3630,7 +3596,7 @@ int arch_setup_dmar_msi(unsigned int irq)
 #ifdef CONFIG_HPET_TIMER
 
 #ifdef CONFIG_SMP
-static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3639,7 +3605,7 @@ static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
@@ -3651,6 +3617,8 @@ static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	hpet_msi_write(irq, &msg);
+
+	return 0;
 }
 
 #endif /* CONFIG_SMP */
@@ -3707,7 +3675,7 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
 	write_ht_irq_msg(irq, &msg);
 }
 
-static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg;
@@ -3715,11 +3683,13 @@ static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
 
 	dest = set_desc_affinity(desc, mask);
 	if (dest == BAD_APICID)
-		return;
+		return -1;
 
 	cfg = desc->chip_data;
 
 	target_ht_irq(irq, dest, cfg->vector);
+
+	return 0;
 }
 
 #endif
@@ -3794,6 +3764,8 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 	unsigned long flags;
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
 	cfg = irq_cfg(irq);
 
 	err = assign_irq_vector(irq, cfg, eligible_cpu);
@@ -3807,15 +3779,13 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 
 	mmr_value = 0;
 	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-	BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
-	entry->vector = cfg->vector;
-	entry->delivery_mode = apic->irq_delivery_mode;
-	entry->dest_mode = apic->irq_dest_mode;
-	entry->polarity = 0;
-	entry->trigger = 0;
-	entry->mask = 0;
-	entry->dest = apic->cpu_mask_to_apicid(eligible_cpu);
+	entry->vector		= cfg->vector;
+	entry->delivery_mode	= apic->irq_delivery_mode;
+	entry->dest_mode	= apic->irq_dest_mode;
+	entry->polarity		= 0;
+	entry->trigger		= 0;
+	entry->mask		= 0;
+	entry->dest		= apic->cpu_mask_to_apicid(eligible_cpu);
 
 	mmr_pnode = uv_blade_to_pnode(mmr_blade);
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
@@ -3833,10 +3803,10 @@ void arch_disable_uv_irq(int mmr_blade, unsigned long mmr_offset)
 	struct uv_IO_APIC_route_entry *entry;
 	int mmr_pnode;
 
+	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
 	mmr_value = 0;
 	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-	BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
-
 	entry->mask = 1;
 
 	mmr_pnode = uv_blade_to_pnode(mmr_blade);
@@ -3900,6 +3870,71 @@ int __init arch_probe_nr_irqs(void)
 }
 #endif
 
+static int __io_apic_set_pci_routing(struct device *dev, int irq,
+				struct io_apic_irq_attr *irq_attr)
+{
+	struct irq_desc *desc;
+	struct irq_cfg *cfg;
+	int node;
+	int ioapic, pin;
+	int trigger, polarity;
+
+	ioapic = irq_attr->ioapic;
+	if (!IO_APIC_IRQ(irq)) {
+		apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
+			ioapic);
+		return -EINVAL;
+	}
+
+	if (dev)
+		node = dev_to_node(dev);
+	else
+		node = cpu_to_node(boot_cpu_id);
+
+	desc = irq_to_desc_alloc_node(irq, node);
+	if (!desc) {
+		printk(KERN_INFO "can not get irq_desc %d\n", irq);
+		return 0;
+	}
+
+	pin = irq_attr->ioapic_pin;
+	trigger = irq_attr->trigger;
+	polarity = irq_attr->polarity;
+
+	/*
+	 * IRQs < 16 are already in the irq_2_pin[] map
+	 */
+	if (irq >= NR_IRQS_LEGACY) {
+		cfg = desc->chip_data;
+		add_pin_to_irq_node(cfg, node, ioapic, pin);
+	}
+
+	setup_IO_APIC_irq(ioapic, pin, irq, desc, trigger, polarity);
+
+	return 0;
+}
+
+int io_apic_set_pci_routing(struct device *dev, int irq,
+				struct io_apic_irq_attr *irq_attr)
+{
+	int ioapic, pin;
+	/*
+	 * Avoid pin reprogramming.  PRTs typically include entries
+	 * with redundant pin->gsi mappings (but unique PCI devices);
+	 * we only program the IOAPIC on the first.
+	 */
+	ioapic = irq_attr->ioapic;
+	pin = irq_attr->ioapic_pin;
+	if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) {
+		pr_debug("Pin %d-%d already programmed\n",
+			 mp_ioapics[ioapic].apicid, pin);
+		return 0;
+	}
+	set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed);
+
+	return __io_apic_set_pci_routing(dev, irq, irq_attr);
+}
+
 /* --------------------------------------------------------------------------
                           ACPI-based IOAPIC Configuration
    -------------------------------------------------------------------------- */
@@ -3980,6 +4015,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
 
 	return apic_id;
 }
+#endif
 
 int __init io_apic_get_version(int ioapic)
 {
@@ -3992,39 +4028,6 @@ int __init io_apic_get_version(int ioapic)
 
 	return reg_01.bits.version;
 }
-#endif
-
-int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int polarity)
-{
-	struct irq_desc *desc;
-	struct irq_cfg *cfg;
-	int cpu = boot_cpu_id;
-
-	if (!IO_APIC_IRQ(irq)) {
-		apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
-			ioapic);
-		return -EINVAL;
-	}
-
-	desc = irq_to_desc_alloc_cpu(irq, cpu);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc %d\n", irq);
-		return 0;
-	}
-
-	/*
-	 * IRQs < 16 are already in the irq_2_pin[] map
-	 */
-	if (irq >= NR_IRQS_LEGACY) {
-		cfg = desc->chip_data;
-		add_pin_to_irq_cpu(cfg, cpu, ioapic, pin);
-	}
-
-	setup_IO_APIC_irq(ioapic, pin, irq, desc, triggering, polarity);
-
-	return 0;
-}
-
 
 int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 {
@@ -4055,51 +4058,44 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 #ifdef CONFIG_SMP
 void __init setup_ioapic_dest(void)
 {
-	int pin, ioapic, irq, irq_entry;
+	int pin, ioapic = 0, irq, irq_entry;
 	struct irq_desc *desc;
-	struct irq_cfg *cfg;
 	const struct cpumask *mask;
 
 	if (skip_ioapic_setup == 1)
 		return;
 
-	for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
-		for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
-			irq_entry = find_irq_entry(ioapic, pin, mp_INT);
-			if (irq_entry == -1)
-				continue;
-			irq = pin_2_irq(irq_entry, ioapic, pin);
-
-			/* setup_IO_APIC_irqs could fail to get vector for some device
-			 * when you have too many devices, because at that time only boot
-			 * cpu is online.
-			 */
-			desc = irq_to_desc(irq);
-			cfg = desc->chip_data;
-			if (!cfg->vector) {
-				setup_IO_APIC_irq(ioapic, pin, irq, desc,
-						  irq_trigger(irq_entry),
-						  irq_polarity(irq_entry));
-				continue;
-
-			}
-
-			/*
-			 * Honour affinities which have been set in early boot
-			 */
-			if (desc->status &
-			    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-				mask = desc->affinity;
-			else
-				mask = apic->target_cpus();
-
-			if (intr_remapping_enabled)
-				set_ir_ioapic_affinity_irq_desc(desc, mask);
-			else
-				set_ioapic_affinity_irq_desc(desc, mask);
-		}
-
+#ifdef CONFIG_ACPI
+	if (!acpi_disabled && acpi_ioapic) {
+		ioapic = mp_find_ioapic(0);
+		if (ioapic < 0)
+			ioapic = 0;
 	}
+#endif
+
+	for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+		irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+		if (irq_entry == -1)
+			continue;
+		irq = pin_2_irq(irq_entry, ioapic, pin);
+
+		desc = irq_to_desc(irq);
+
+		/*
+		 * Honour affinities which have been set in early boot
+		 */
+		if (desc->status &
+		    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
+			mask = desc->affinity;
+		else
+			mask = apic->target_cpus();
+
+		if (intr_remapping_enabled)
+			set_ir_ioapic_affinity_irq_desc(desc, mask);
+		else
+			set_ioapic_affinity_irq_desc(desc, mask);
+	}
+
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index ce4fbfa315a1..a691302dc3ff 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -104,7 +104,7 @@ static __init void nmi_cpu_busy(void *data)
 }
 #endif
 
-static void report_broken_nmi(int cpu, int *prev_nmi_count)
+static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count)
 {
 	printk(KERN_CONT "\n");
 
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 01eda2ac65e4..440a8bccd91a 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -160,7 +160,6 @@ extern struct apic apic_summit;
 extern struct apic apic_bigsmp;
 extern struct apic apic_es7000;
 extern struct apic apic_es7000_cluster;
-extern struct apic apic_default;
 
 struct apic *apic = &apic_default;
 EXPORT_SYMBOL_GPL(apic);
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 1783652bb0e5..bc3e880f9b82 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -50,7 +50,7 @@ static struct apic *apic_probe[] __initdata = {
 void __init default_setup_apic_routing(void)
 {
 #ifdef CONFIG_X86_X2APIC
-	if (x2apic && (apic != &apic_x2apic_phys &&
+	if (x2apic_mode && (apic != &apic_x2apic_phys &&
 #ifdef CONFIG_X86_UV
 		       apic != &apic_x2apic_uv_x &&
 #endif
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 9cfe1f415d81..344eee4ac0a4 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -173,13 +173,6 @@ static inline int is_WPEG(struct rio_detail *rio){
 		rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
 }
 
-
-/* In clustered mode, the high nibble of APIC ID is a cluster number.
- * The low nibble is a 4-bit bitmap. */
-#define XAPIC_DEST_CPUS_SHIFT	4
-#define XAPIC_DEST_CPUS_MASK	((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK	(XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-
 #define SUMMIT_APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
 
 static const struct cpumask *summit_target_cpus(void)
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 4a903e2f0d17..8e4cbb255c38 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -10,7 +10,7 @@
 #include <asm/apic.h>
 #include <asm/ipi.h>
 
-DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
 
 static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 2bda69352976..ef0ae207a7c8 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -105,7 +105,7 @@ static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask)
 	cpumask_set_cpu(cpu, retmask);
 }
 
-static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 {
 #ifdef CONFIG_SMP
 	unsigned long val;
@@ -562,7 +562,7 @@ void __init uv_system_init(void)
 	union uvh_node_id_u node_id;
 	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
 	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
-	int max_pnode = 0;
+	int gnode_extra, max_pnode = 0;
 	unsigned long mmr_base, present, paddr;
 	unsigned short pnode_mask;
 
@@ -574,6 +574,13 @@ void __init uv_system_init(void)
 	mmr_base =
 	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 	    ~UV_MMR_ENABLE;
+	pnode_mask = (1 << n_val) - 1;
+	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
+	gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
+	gnode_upper = ((unsigned long)gnode_extra  << m_val);
+	printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n",
+			n_val, m_val, gnode_upper, gnode_extra);
+
 	printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
 
 	for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
@@ -583,15 +590,18 @@ void __init uv_system_init(void)
 
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
 	uv_blade_info = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!uv_blade_info);
 
 	get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
 
 	bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
 	uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!uv_node_to_blade);
 	memset(uv_node_to_blade, 255, bytes);
 
 	bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
 	uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!uv_cpu_to_blade);
 	memset(uv_cpu_to_blade, 255, bytes);
 
 	blade = 0;
@@ -607,11 +617,6 @@ void __init uv_system_init(void)
 		}
 	}
 
-	pnode_mask = (1 << n_val) - 1;
-	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
-	gnode_upper = (((unsigned long)node_id.s.node_id) &
-		       ~((1 << n_val) - 1)) << m_val;
-
 	uv_bios_init();
 	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
 			    &sn_coherency_id, &sn_region_size);
@@ -634,6 +639,7 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
 		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
+		uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
 		uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
 		uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 5a6aa1c1162f..1a830cbd7015 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -146,4 +146,5 @@ void foo(void)
 	OFFSET(BP_loadflags, boot_params, hdr.loadflags);
 	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
 	OFFSET(BP_version, boot_params, hdr.version);
+	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
 }
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index e72f062fb4b5..898ecc47e129 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -125,6 +125,7 @@ int main(void)
 	OFFSET(BP_loadflags, boot_params, hdr.loadflags);
 	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
 	OFFSET(BP_version, boot_params, hdr.version);
+	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
 
 	BLANK();
 	DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 4e242f9a06e4..3efcb2b96a15 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -1,5 +1,5 @@
 #
-# Makefile for x86-compatible CPU details and quirks
+# Makefile for x86-compatible CPU details, features and quirks
 #
 
 # Don't trace early stages of a secondary CPU boot
@@ -23,11 +23,13 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_X86_MCE)	+= mcheck/
-obj-$(CONFIG_MTRR)	+= mtrr/
-obj-$(CONFIG_CPU_FREQ)	+= cpufreq/
+obj-$(CONFIG_PERF_COUNTERS)		+= perf_counter.o
 
-obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
+obj-$(CONFIG_X86_MCE)			+= mcheck/
+obj-$(CONFIG_MTRR)			+= mtrr/
+obj-$(CONFIG_CPU_FREQ)			+= cpufreq/
+
+obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o
 
 quiet_cmd_mkcapflags = MKCAP   $@
       cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7e4a459daa64..e5b27d8f1b47 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -6,6 +6,7 @@
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
+#include <asm/pci-direct.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/numa_64.h>
@@ -272,7 +273,7 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
 	int cpu = smp_processor_id();
 	int node;
-	unsigned apicid = hard_smp_processor_id();
+	unsigned apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
 
 	node = c->phys_proc_id;
 	if (apicid_to_node[apicid] != NUMA_NO_NODE)
@@ -351,6 +352,15 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 		    (c->x86_model == 8 && c->x86_mask >= 8))
 			set_cpu_cap(c, X86_FEATURE_K6_MTRR);
 #endif
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
+	/* check CPU config space for extended APIC ID */
+	if (c->x86 >= 0xf) {
+		unsigned int val;
+		val = read_pci_config(0, 24, 0, 0x68);
+		if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
+			set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+	}
+#endif
 }
 
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 77848d9fca68..3ffdcfa9abdf 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -13,6 +13,7 @@
 #include <linux/io.h>
 
 #include <asm/stackprotector.h>
+#include <asm/perf_counter.h>
 #include <asm/mmu_context.h>
 #include <asm/hypervisor.h>
 #include <asm/processor.h>
@@ -299,7 +300,8 @@ static const char *__cpuinit table_lookup_model(struct cpuinfo_x86 *c)
 	return NULL;		/* Not found */
 }
 
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_cleared[NCAPINTS] __cpuinitdata;
+__u32 cpu_caps_set[NCAPINTS] __cpuinitdata;
 
 void load_percpu_segment(int cpu)
 {
@@ -768,6 +770,12 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 	if (this_cpu->c_identify)
 		this_cpu->c_identify(c);
 
+	/* Clear/Set all flags overriden by options, after probe */
+	for (i = 0; i < NCAPINTS; i++) {
+		c->x86_capability[i] &= ~cpu_caps_cleared[i];
+		c->x86_capability[i] |= cpu_caps_set[i];
+	}
+
 #ifdef CONFIG_X86_64
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 #endif
@@ -813,6 +821,16 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 #endif
 
 	init_hypervisor(c);
+
+	/*
+	 * Clear/Set all flags overriden by options, need do it
+	 * before following smp all cpus cap AND.
+	 */
+	for (i = 0; i < NCAPINTS; i++) {
+		c->x86_capability[i] &= ~cpu_caps_cleared[i];
+		c->x86_capability[i] |= cpu_caps_set[i];
+	}
+
 	/*
 	 * On SMP, boot_cpu_data holds the common feature set between
 	 * all CPUs; so make sure that we indicate which features are
@@ -825,10 +843,6 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 			boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
 	}
 
-	/* Clear all flags overriden by options */
-	for (i = 0; i < NCAPINTS; i++)
-		c->x86_capability[i] &= ~cleared_cpu_caps[i];
-
 #ifdef CONFIG_X86_MCE
 	/* Init Machine Check Exception if available. */
 	mcheck_init(c);
@@ -861,6 +875,7 @@ void __init identify_boot_cpu(void)
 #else
 	vgetcpu_set_mode();
 #endif
+	init_hw_perf_counters();
 }
 
 void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
index 46e29ab96c6a..6b2a52dd0403 100644
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -32,9 +32,7 @@
 
 static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]);
 static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]);
-static DEFINE_PER_CPU(unsigned, cpu_modelflag);
 static DEFINE_PER_CPU(int, cpu_priv_count);
-static DEFINE_PER_CPU(unsigned, cpu_model);
 
 static DEFINE_MUTEX(cpu_debug_lock);
 
@@ -80,302 +78,102 @@ static struct cpu_file_base cpu_file[] = {
 	{ "value",	CPU_REG_ALL,	1	},
 };
 
-/* Intel Registers Range */
-static struct cpu_debug_range cpu_intel_range[] = {
-	{ 0x00000000, 0x00000001, CPU_MC,	CPU_INTEL_ALL		},
-	{ 0x00000006, 0x00000007, CPU_MONITOR,	CPU_CX_AT_XE		},
-	{ 0x00000010, 0x00000010, CPU_TIME,	CPU_INTEL_ALL		},
-	{ 0x00000011, 0x00000013, CPU_PMC,	CPU_INTEL_PENTIUM	},
-	{ 0x00000017, 0x00000017, CPU_PLATFORM,	CPU_PX_CX_AT_XE		},
-	{ 0x0000001B, 0x0000001B, CPU_APIC,	CPU_P6_CX_AT_XE		},
+/* CPU Registers Range */
+static struct cpu_debug_range cpu_reg_range[] = {
+	{ 0x00000000, 0x00000001, CPU_MC,	},
+	{ 0x00000006, 0x00000007, CPU_MONITOR,	},
+	{ 0x00000010, 0x00000010, CPU_TIME,	},
+	{ 0x00000011, 0x00000013, CPU_PMC,	},
+	{ 0x00000017, 0x00000017, CPU_PLATFORM,	},
+	{ 0x0000001B, 0x0000001B, CPU_APIC,	},
+	{ 0x0000002A, 0x0000002B, CPU_POWERON,	},
+	{ 0x0000002C, 0x0000002C, CPU_FREQ,	},
+	{ 0x0000003A, 0x0000003A, CPU_CONTROL,	},
+	{ 0x00000040, 0x00000047, CPU_LBRANCH,	},
+	{ 0x00000060, 0x00000067, CPU_LBRANCH,	},
+	{ 0x00000079, 0x00000079, CPU_BIOS,	},
+	{ 0x00000088, 0x0000008A, CPU_CACHE,	},
+	{ 0x0000008B, 0x0000008B, CPU_BIOS,	},
+	{ 0x0000009B, 0x0000009B, CPU_MONITOR,	},
+	{ 0x000000C1, 0x000000C4, CPU_PMC,	},
+	{ 0x000000CD, 0x000000CD, CPU_FREQ,	},
+	{ 0x000000E7, 0x000000E8, CPU_PERF,	},
+	{ 0x000000FE, 0x000000FE, CPU_MTRR,	},
 
-	{ 0x0000002A, 0x0000002A, CPU_POWERON,	CPU_PX_CX_AT_XE		},
-	{ 0x0000002B, 0x0000002B, CPU_POWERON,	CPU_INTEL_XEON		},
-	{ 0x0000002C, 0x0000002C, CPU_FREQ,	CPU_INTEL_XEON		},
-	{ 0x0000003A, 0x0000003A, CPU_CONTROL,	CPU_CX_AT_XE		},
+	{ 0x00000116, 0x0000011E, CPU_CACHE,	},
+	{ 0x00000174, 0x00000176, CPU_SYSENTER,	},
+	{ 0x00000179, 0x0000017B, CPU_MC,	},
+	{ 0x00000186, 0x00000189, CPU_PMC,	},
+	{ 0x00000198, 0x00000199, CPU_PERF,	},
+	{ 0x0000019A, 0x0000019A, CPU_TIME,	},
+	{ 0x0000019B, 0x0000019D, CPU_THERM,	},
+	{ 0x000001A0, 0x000001A0, CPU_MISC,	},
+	{ 0x000001C9, 0x000001C9, CPU_LBRANCH,	},
+	{ 0x000001D7, 0x000001D8, CPU_LBRANCH,	},
+	{ 0x000001D9, 0x000001D9, CPU_DEBUG,	},
+	{ 0x000001DA, 0x000001E0, CPU_LBRANCH,	},
 
-	{ 0x00000040, 0x00000043, CPU_LBRANCH,	CPU_PM_CX_AT_XE		},
-	{ 0x00000044, 0x00000047, CPU_LBRANCH,	CPU_PM_CO_AT		},
-	{ 0x00000060, 0x00000063, CPU_LBRANCH,	CPU_C2_AT		},
-	{ 0x00000064, 0x00000067, CPU_LBRANCH,	CPU_INTEL_ATOM		},
+	{ 0x00000200, 0x0000020F, CPU_MTRR,	},
+	{ 0x00000250, 0x00000250, CPU_MTRR,	},
+	{ 0x00000258, 0x00000259, CPU_MTRR,	},
+	{ 0x00000268, 0x0000026F, CPU_MTRR,	},
+	{ 0x00000277, 0x00000277, CPU_PAT,	},
+	{ 0x000002FF, 0x000002FF, CPU_MTRR,	},
 
-	{ 0x00000079, 0x00000079, CPU_BIOS,	CPU_P6_CX_AT_XE		},
-	{ 0x00000088, 0x0000008A, CPU_CACHE,	CPU_INTEL_P6		},
-	{ 0x0000008B, 0x0000008B, CPU_BIOS,	CPU_P6_CX_AT_XE		},
-	{ 0x0000009B, 0x0000009B, CPU_MONITOR,	CPU_INTEL_XEON		},
+	{ 0x00000300, 0x00000311, CPU_PMC,	},
+	{ 0x00000345, 0x00000345, CPU_PMC,	},
+	{ 0x00000360, 0x00000371, CPU_PMC,	},
+	{ 0x0000038D, 0x00000390, CPU_PMC,	},
+	{ 0x000003A0, 0x000003BE, CPU_PMC,	},
+	{ 0x000003C0, 0x000003CD, CPU_PMC,	},
+	{ 0x000003E0, 0x000003E1, CPU_PMC,	},
+	{ 0x000003F0, 0x000003F2, CPU_PMC,	},
 
-	{ 0x000000C1, 0x000000C2, CPU_PMC,	CPU_P6_CX_AT		},
-	{ 0x000000CD, 0x000000CD, CPU_FREQ,	CPU_CX_AT		},
-	{ 0x000000E7, 0x000000E8, CPU_PERF,	CPU_CX_AT		},
-	{ 0x000000FE, 0x000000FE, CPU_MTRR,	CPU_P6_CX_XE		},
+	{ 0x00000400, 0x00000417, CPU_MC,	},
+	{ 0x00000480, 0x0000048B, CPU_VMX,	},
 
-	{ 0x00000116, 0x00000116, CPU_CACHE,	CPU_INTEL_P6		},
-	{ 0x00000118, 0x00000118, CPU_CACHE,	CPU_INTEL_P6		},
-	{ 0x00000119, 0x00000119, CPU_CACHE,	CPU_INTEL_PX		},
-	{ 0x0000011A, 0x0000011B, CPU_CACHE,	CPU_INTEL_P6		},
-	{ 0x0000011E, 0x0000011E, CPU_CACHE,	CPU_PX_CX_AT		},
+	{ 0x00000600, 0x00000600, CPU_DEBUG,	},
+	{ 0x00000680, 0x0000068F, CPU_LBRANCH,	},
+	{ 0x000006C0, 0x000006CF, CPU_LBRANCH,	},
 
-	{ 0x00000174, 0x00000176, CPU_SYSENTER,	CPU_P6_CX_AT_XE		},
-	{ 0x00000179, 0x0000017A, CPU_MC,	CPU_PX_CX_AT_XE		},
-	{ 0x0000017B, 0x0000017B, CPU_MC,	CPU_P6_XE		},
-	{ 0x00000186, 0x00000187, CPU_PMC,	CPU_P6_CX_AT		},
-	{ 0x00000198, 0x00000199, CPU_PERF,	CPU_PM_CX_AT_XE		},
-	{ 0x0000019A, 0x0000019A, CPU_TIME,	CPU_PM_CX_AT_XE		},
-	{ 0x0000019B, 0x0000019D, CPU_THERM,	CPU_PM_CX_AT_XE		},
-	{ 0x000001A0, 0x000001A0, CPU_MISC,	CPU_PM_CX_AT_XE		},
+	{ 0x000107CC, 0x000107D3, CPU_PMC,	},
 
-	{ 0x000001C9, 0x000001C9, CPU_LBRANCH,	CPU_PM_CX_AT		},
-	{ 0x000001D7, 0x000001D8, CPU_LBRANCH,	CPU_INTEL_XEON		},
-	{ 0x000001D9, 0x000001D9, CPU_DEBUG,	CPU_CX_AT_XE		},
-	{ 0x000001DA, 0x000001DA, CPU_LBRANCH,	CPU_INTEL_XEON		},
-	{ 0x000001DB, 0x000001DB, CPU_LBRANCH,	CPU_P6_XE		},
-	{ 0x000001DC, 0x000001DC, CPU_LBRANCH,	CPU_INTEL_P6		},
-	{ 0x000001DD, 0x000001DE, CPU_LBRANCH,	CPU_PX_CX_AT_XE		},
-	{ 0x000001E0, 0x000001E0, CPU_LBRANCH,	CPU_INTEL_P6		},
+	{ 0xC0000080, 0xC0000080, CPU_FEATURES,	},
+	{ 0xC0000081, 0xC0000084, CPU_CALL,	},
+	{ 0xC0000100, 0xC0000102, CPU_BASE,	},
+	{ 0xC0000103, 0xC0000103, CPU_TIME,	},
 
-	{ 0x00000200, 0x0000020F, CPU_MTRR,	CPU_P6_CX_XE		},
-	{ 0x00000250, 0x00000250, CPU_MTRR,	CPU_P6_CX_XE		},
-	{ 0x00000258, 0x00000259, CPU_MTRR,	CPU_P6_CX_XE		},
-	{ 0x00000268, 0x0000026F, CPU_MTRR,	CPU_P6_CX_XE		},
-	{ 0x00000277, 0x00000277, CPU_PAT,	CPU_C2_AT_XE		},
-	{ 0x000002FF, 0x000002FF, CPU_MTRR,	CPU_P6_CX_XE		},
-
-	{ 0x00000300, 0x00000308, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x00000309, 0x0000030B, CPU_PMC,	CPU_C2_AT_XE		},
-	{ 0x0000030C, 0x00000311, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x00000345, 0x00000345, CPU_PMC,	CPU_C2_AT		},
-	{ 0x00000360, 0x00000371, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x0000038D, 0x00000390, CPU_PMC,	CPU_C2_AT		},
-	{ 0x000003A0, 0x000003BE, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x000003C0, 0x000003CD, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x000003E0, 0x000003E1, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x000003F0, 0x000003F0, CPU_PMC,	CPU_INTEL_XEON		},
-	{ 0x000003F1, 0x000003F1, CPU_PMC,	CPU_C2_AT_XE		},
-	{ 0x000003F2, 0x000003F2, CPU_PMC,	CPU_INTEL_XEON		},
-
-	{ 0x00000400, 0x00000402, CPU_MC,	CPU_PM_CX_AT_XE		},
-	{ 0x00000403, 0x00000403, CPU_MC,	CPU_INTEL_XEON		},
-	{ 0x00000404, 0x00000406, CPU_MC,	CPU_PM_CX_AT_XE		},
-	{ 0x00000407, 0x00000407, CPU_MC,	CPU_INTEL_XEON		},
-	{ 0x00000408, 0x0000040A, CPU_MC,	CPU_PM_CX_AT_XE		},
-	{ 0x0000040B, 0x0000040B, CPU_MC,	CPU_INTEL_XEON		},
-	{ 0x0000040C, 0x0000040E, CPU_MC,	CPU_PM_CX_XE		},
-	{ 0x0000040F, 0x0000040F, CPU_MC,	CPU_INTEL_XEON		},
-	{ 0x00000410, 0x00000412, CPU_MC,	CPU_PM_CX_AT_XE		},
-	{ 0x00000413, 0x00000417, CPU_MC,	CPU_CX_AT_XE		},
-	{ 0x00000480, 0x0000048B, CPU_VMX,	CPU_CX_AT_XE		},
-
-	{ 0x00000600, 0x00000600, CPU_DEBUG,	CPU_PM_CX_AT_XE		},
-	{ 0x00000680, 0x0000068F, CPU_LBRANCH,	CPU_INTEL_XEON		},
-	{ 0x000006C0, 0x000006CF, CPU_LBRANCH,	CPU_INTEL_XEON		},
-
-	{ 0x000107CC, 0x000107D3, CPU_PMC,	CPU_INTEL_XEON_MP	},
-
-	{ 0xC0000080, 0xC0000080, CPU_FEATURES,	CPU_INTEL_XEON		},
-	{ 0xC0000081, 0xC0000082, CPU_CALL,	CPU_INTEL_XEON		},
-	{ 0xC0000084, 0xC0000084, CPU_CALL,	CPU_INTEL_XEON		},
-	{ 0xC0000100, 0xC0000102, CPU_BASE,	CPU_INTEL_XEON		},
+	{ 0xC0010000, 0xC0010007, CPU_PMC,	},
+	{ 0xC0010010, 0xC0010010, CPU_CONF,	},
+	{ 0xC0010015, 0xC0010015, CPU_CONF,	},
+	{ 0xC0010016, 0xC001001A, CPU_MTRR,	},
+	{ 0xC001001D, 0xC001001D, CPU_MTRR,	},
+	{ 0xC001001F, 0xC001001F, CPU_CONF,	},
+	{ 0xC0010030, 0xC0010035, CPU_BIOS,	},
+	{ 0xC0010044, 0xC0010048, CPU_MC,	},
+	{ 0xC0010050, 0xC0010056, CPU_SMM,	},
+	{ 0xC0010058, 0xC0010058, CPU_CONF,	},
+	{ 0xC0010060, 0xC0010060, CPU_CACHE,	},
+	{ 0xC0010061, 0xC0010068, CPU_SMM,	},
+	{ 0xC0010069, 0xC001006B, CPU_SMM,	},
+	{ 0xC0010070, 0xC0010071, CPU_SMM,	},
+	{ 0xC0010111, 0xC0010113, CPU_SMM,	},
+	{ 0xC0010114, 0xC0010118, CPU_SVM,	},
+	{ 0xC0010140, 0xC0010141, CPU_OSVM,	},
+	{ 0xC0011022, 0xC0011023, CPU_CONF,	},
 };
 
-/* AMD Registers Range */
-static struct cpu_debug_range cpu_amd_range[] = {
-	{ 0x00000000, 0x00000001, CPU_MC,	CPU_K10_PLUS,		},
-	{ 0x00000010, 0x00000010, CPU_TIME,	CPU_K8_PLUS,		},
-	{ 0x0000001B, 0x0000001B, CPU_APIC,	CPU_K8_PLUS,		},
-	{ 0x0000002A, 0x0000002A, CPU_POWERON,	CPU_K7_PLUS		},
-	{ 0x0000008B, 0x0000008B, CPU_VER,	CPU_K8_PLUS		},
-	{ 0x000000FE, 0x000000FE, CPU_MTRR,	CPU_K8_PLUS,		},
-
-	{ 0x00000174, 0x00000176, CPU_SYSENTER,	CPU_K8_PLUS,		},
-	{ 0x00000179, 0x0000017B, CPU_MC,	CPU_K8_PLUS,		},
-	{ 0x000001D9, 0x000001D9, CPU_DEBUG,	CPU_K8_PLUS,		},
-	{ 0x000001DB, 0x000001DE, CPU_LBRANCH,	CPU_K8_PLUS,		},
-
-	{ 0x00000200, 0x0000020F, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0x00000250, 0x00000250, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0x00000258, 0x00000259, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0x00000268, 0x0000026F, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0x00000277, 0x00000277, CPU_PAT,	CPU_K8_PLUS,		},
-	{ 0x000002FF, 0x000002FF, CPU_MTRR,	CPU_K8_PLUS,		},
-
-	{ 0x00000400, 0x00000413, CPU_MC,	CPU_K8_PLUS,		},
-
-	{ 0xC0000080, 0xC0000080, CPU_FEATURES,	CPU_AMD_ALL,		},
-	{ 0xC0000081, 0xC0000084, CPU_CALL,	CPU_K8_PLUS,		},
-	{ 0xC0000100, 0xC0000102, CPU_BASE,	CPU_K8_PLUS,		},
-	{ 0xC0000103, 0xC0000103, CPU_TIME,	CPU_K10_PLUS,		},
-
-	{ 0xC0010000, 0xC0010007, CPU_PMC,	CPU_K8_PLUS,		},
-	{ 0xC0010010, 0xC0010010, CPU_CONF,	CPU_K7_PLUS,		},
-	{ 0xC0010015, 0xC0010015, CPU_CONF,	CPU_K7_PLUS,		},
-	{ 0xC0010016, 0xC001001A, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0xC001001D, 0xC001001D, CPU_MTRR,	CPU_K8_PLUS,		},
-	{ 0xC001001F, 0xC001001F, CPU_CONF,	CPU_K8_PLUS,		},
-	{ 0xC0010030, 0xC0010035, CPU_BIOS,	CPU_K8_PLUS,		},
-	{ 0xC0010044, 0xC0010048, CPU_MC,	CPU_K8_PLUS,		},
-	{ 0xC0010050, 0xC0010056, CPU_SMM,	CPU_K0F_PLUS,		},
-	{ 0xC0010058, 0xC0010058, CPU_CONF,	CPU_K10_PLUS,		},
-	{ 0xC0010060, 0xC0010060, CPU_CACHE,	CPU_AMD_11,		},
-	{ 0xC0010061, 0xC0010068, CPU_SMM,	CPU_K10_PLUS,		},
-	{ 0xC0010069, 0xC001006B, CPU_SMM,	CPU_AMD_11,		},
-	{ 0xC0010070, 0xC0010071, CPU_SMM,	CPU_K10_PLUS,		},
-	{ 0xC0010111, 0xC0010113, CPU_SMM,	CPU_K8_PLUS,		},
-	{ 0xC0010114, 0xC0010118, CPU_SVM,	CPU_K10_PLUS,		},
-	{ 0xC0010140, 0xC0010141, CPU_OSVM,	CPU_K10_PLUS,		},
-	{ 0xC0011022, 0xC0011023, CPU_CONF,	CPU_K10_PLUS,		},
-};
-
-
-/* Intel */
-static int get_intel_modelflag(unsigned model)
-{
-	int flag;
-
-	switch (model) {
-	case 0x0501:
-	case 0x0502:
-	case 0x0504:
-		flag = CPU_INTEL_PENTIUM;
-		break;
-	case 0x0601:
-	case 0x0603:
-	case 0x0605:
-	case 0x0607:
-	case 0x0608:
-	case 0x060A:
-	case 0x060B:
-		flag = CPU_INTEL_P6;
-		break;
-	case 0x0609:
-	case 0x060D:
-		flag = CPU_INTEL_PENTIUM_M;
-		break;
-	case 0x060E:
-		flag = CPU_INTEL_CORE;
-		break;
-	case 0x060F:
-	case 0x0617:
-		flag = CPU_INTEL_CORE2;
-		break;
-	case 0x061C:
-		flag = CPU_INTEL_ATOM;
-		break;
-	case 0x0F00:
-	case 0x0F01:
-	case 0x0F02:
-	case 0x0F03:
-	case 0x0F04:
-		flag = CPU_INTEL_XEON_P4;
-		break;
-	case 0x0F06:
-		flag = CPU_INTEL_XEON_MP;
-		break;
-	default:
-		flag = CPU_NONE;
-		break;
-	}
-
-	return flag;
-}
-
-/* AMD */
-static int get_amd_modelflag(unsigned model)
-{
-	int flag;
-
-	switch (model >> 8) {
-	case 0x6:
-		flag = CPU_AMD_K6;
-		break;
-	case 0x7:
-		flag = CPU_AMD_K7;
-		break;
-	case 0x8:
-		flag = CPU_AMD_K8;
-		break;
-	case 0xf:
-		flag = CPU_AMD_0F;
-		break;
-	case 0x10:
-		flag = CPU_AMD_10;
-		break;
-	case 0x11:
-		flag = CPU_AMD_11;
-		break;
-	default:
-		flag = CPU_NONE;
-		break;
-	}
-
-	return flag;
-}
-
-static int get_cpu_modelflag(unsigned cpu)
-{
-	int flag;
-
-	flag = per_cpu(cpu_model, cpu);
-
-	switch (flag >> 16) {
-	case X86_VENDOR_INTEL:
-		flag = get_intel_modelflag(flag);
-		break;
-	case X86_VENDOR_AMD:
-		flag = get_amd_modelflag(flag & 0xffff);
-		break;
-	default:
-		flag = CPU_NONE;
-		break;
-	}
-
-	return flag;
-}
-
-static int get_cpu_range_count(unsigned cpu)
-{
-	int index;
-
-	switch (per_cpu(cpu_model, cpu) >> 16) {
-	case X86_VENDOR_INTEL:
-		index = ARRAY_SIZE(cpu_intel_range);
-		break;
-	case X86_VENDOR_AMD:
-		index = ARRAY_SIZE(cpu_amd_range);
-		break;
-	default:
-		index = 0;
-		break;
-	}
-
-	return index;
-}
-
 static int is_typeflag_valid(unsigned cpu, unsigned flag)
 {
-	unsigned vendor, modelflag;
-	int i, index;
+	int i;
 
 	/* Standard Registers should be always valid */
 	if (flag >= CPU_TSS)
 		return 1;
 
-	modelflag = per_cpu(cpu_modelflag, cpu);
-	vendor = per_cpu(cpu_model, cpu) >> 16;
-	index = get_cpu_range_count(cpu);
-
-	for (i = 0; i < index; i++) {
-		switch (vendor) {
-		case X86_VENDOR_INTEL:
-			if ((cpu_intel_range[i].model & modelflag) &&
-			    (cpu_intel_range[i].flag & flag))
-				return 1;
-			break;
-		case X86_VENDOR_AMD:
-			if ((cpu_amd_range[i].model & modelflag) &&
-			    (cpu_amd_range[i].flag & flag))
-				return 1;
-			break;
-		}
+	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
+		if (cpu_reg_range[i].flag == flag)
+			return 1;
 	}
 
 	/* Invalid */
@@ -385,26 +183,11 @@ static int is_typeflag_valid(unsigned cpu, unsigned flag)
 static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max,
 			      int index, unsigned flag)
 {
-	unsigned modelflag;
-
-	modelflag = per_cpu(cpu_modelflag, cpu);
-	*max = 0;
-	switch (per_cpu(cpu_model, cpu) >> 16) {
-	case X86_VENDOR_INTEL:
-		if ((cpu_intel_range[index].model & modelflag) &&
-		    (cpu_intel_range[index].flag & flag)) {
-			*min = cpu_intel_range[index].min;
-			*max = cpu_intel_range[index].max;
-		}
-		break;
-	case X86_VENDOR_AMD:
-		if ((cpu_amd_range[index].model & modelflag) &&
-		    (cpu_amd_range[index].flag & flag)) {
-			*min = cpu_amd_range[index].min;
-			*max = cpu_amd_range[index].max;
-		}
-		break;
-	}
+	if (cpu_reg_range[index].flag == flag) {
+		*min = cpu_reg_range[index].min;
+		*max = cpu_reg_range[index].max;
+	} else
+		*max = 0;
 
 	return *max;
 }
@@ -434,7 +217,7 @@ static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag)
 	unsigned msr, msr_min, msr_max;
 	struct cpu_private *priv;
 	u32 low, high;
-	int i, range;
+	int i;
 
 	if (seq) {
 		priv = seq->private;
@@ -446,9 +229,7 @@ static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag)
 		}
 	}
 
-	range = get_cpu_range_count(cpu);
-
-	for (i = 0; i < range; i++) {
+	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
 		if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag))
 			continue;
 
@@ -588,8 +369,20 @@ static void print_apic(void *arg)
 	seq_printf(seq, " TMICT\t\t: %08x\n",  apic_read(APIC_TMICT));
 	seq_printf(seq, " TMCCT\t\t: %08x\n",  apic_read(APIC_TMCCT));
 	seq_printf(seq, " TDCR\t\t: %08x\n",  apic_read(APIC_TDCR));
-#endif /* CONFIG_X86_LOCAL_APIC */
+	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+		unsigned int i, v, maxeilvt;
 
+		v = apic_read(APIC_EFEAT);
+		maxeilvt = (v >> 16) & 0xff;
+		seq_printf(seq, " EFEAT\t\t: %08x\n", v);
+		seq_printf(seq, " ECTRL\t\t: %08x\n", apic_read(APIC_ECTRL));
+
+		for (i = 0; i < maxeilvt; i++) {
+			v = apic_read(APIC_EILVTn(i));
+			seq_printf(seq, " EILVT%d\t\t: %08x\n", i, v);
+		}
+	}
+#endif /* CONFIG_X86_LOCAL_APIC */
 	seq_printf(seq, "\n MSR\t:\n");
 }
 
@@ -788,13 +581,11 @@ static int cpu_init_msr(unsigned cpu, unsigned type, struct dentry *dentry)
 {
 	struct dentry *cpu_dentry = NULL;
 	unsigned reg, reg_min, reg_max;
-	int i, range, err = 0;
+	int i, err = 0;
 	char reg_dir[12];
 	u32 low, high;
 
-	range = get_cpu_range_count(cpu);
-
-	for (i = 0; i < range; i++) {
+	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
 		if (!get_cpu_range(cpu, &reg_min, &reg_max, i,
 				   cpu_base[type].flag))
 			continue;
@@ -850,10 +641,6 @@ static int cpu_init_cpu(void)
 		cpui = &cpu_data(cpu);
 		if (!cpu_has(cpui, X86_FEATURE_MSR))
 			continue;
-		per_cpu(cpu_model, cpu) = ((cpui->x86_vendor << 16) |
-					   (cpui->x86 << 8) |
-					   (cpui->x86_model));
-		per_cpu(cpu_modelflag, cpu) = get_cpu_modelflag(cpu);
 
 		sprintf(cpu_dir, "cpu%d", cpu);
 		cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir);
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index 52c839875478..f138c6c389b9 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -220,11 +220,14 @@ config X86_LONGHAUL
 	  If in doubt, say N.
 
 config X86_E_POWERSAVER
-	tristate "VIA C7 Enhanced PowerSaver"
+	tristate "VIA C7 Enhanced PowerSaver (DANGEROUS)"
 	select CPU_FREQ_TABLE
-	depends on X86_32
+	depends on X86_32 && EXPERIMENTAL
 	help
-	  This adds the CPUFreq driver for VIA C7 processors.
+	  This adds the CPUFreq driver for VIA C7 processors.  However, this driver
+	  does not have any safeguards to prevent operating the CPU out of spec
+	  and is thus considered dangerous.  Please use the regular ACPI cpufreq
+	  driver, enabled by CONFIG_X86_ACPI_CPUFREQ.
 
 	  If in doubt, say N.
 
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 752e8c6b2c7e..ae9b503220ca 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -90,11 +90,7 @@ static int check_est_cpu(unsigned int cpuid)
 {
 	struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
 
-	if (cpu->x86_vendor != X86_VENDOR_INTEL ||
-	    !cpu_has(cpu, X86_FEATURE_EST))
-		return 0;
-
-	return 1;
+	return cpu_has(cpu, X86_FEATURE_EST);
 }
 
 static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 7437fa133c02..daed39ba2614 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -229,12 +229,12 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
 }
 #endif
 
-static void __cpuinit srat_detect_node(void)
+static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 {
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
 	unsigned node;
 	int cpu = smp_processor_id();
-	int apicid = hard_smp_processor_id();
+	int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
 
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
@@ -400,7 +400,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 	}
 
 	/* Work around errata */
-	srat_detect_node();
+	srat_detect_node(c);
 
 	if (cpu_has(c, X86_FEATURE_VMX))
 		detect_vmx_virtcap(c);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 483eda96e102..789efe217e1a 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -17,6 +17,7 @@
 
 #include <asm/processor.h>
 #include <asm/smp.h>
+#include <asm/k8.h>
 
 #define LVL_1_INST	1
 #define LVL_1_DATA	2
@@ -159,14 +160,6 @@ struct _cpuid4_info_regs {
 	unsigned long can_disable;
 };
 
-#if defined(CONFIG_PCI) && defined(CONFIG_SYSFS)
-static struct pci_device_id k8_nb_id[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
-	{}
-};
-#endif
-
 unsigned short			num_cache_leaves;
 
 /* AMD doesn't have CPUID4. Emulate it here to report the same
@@ -207,10 +200,17 @@ union l3_cache {
 };
 
 static const unsigned short __cpuinitconst assocs[] = {
-	[1] = 1, [2] = 2, [4] = 4, [6] = 8,
-	[8] = 16, [0xa] = 32, [0xb] = 48,
+	[1] = 1,
+	[2] = 2,
+	[4] = 4,
+	[6] = 8,
+	[8] = 16,
+	[0xa] = 32,
+	[0xb] = 48,
 	[0xc] = 64,
-	[0xf] = 0xffff // ??
+	[0xd] = 96,
+	[0xe] = 128,
+	[0xf] = 0xffff /* fully associative - no way to show this currently */
 };
 
 static const unsigned char __cpuinitconst levels[] = { 1, 1, 2, 3 };
@@ -271,7 +271,8 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	eax->split.type = types[leaf];
 	eax->split.level = levels[leaf];
 	if (leaf == 3)
-		eax->split.num_threads_sharing = current_cpu_data.x86_max_cores - 1;
+		eax->split.num_threads_sharing =
+			current_cpu_data.x86_max_cores - 1;
 	else
 		eax->split.num_threads_sharing = 0;
 	eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
@@ -291,6 +292,14 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
 {
 	if (index < 3)
 		return;
+
+	if (boot_cpu_data.x86 == 0x11)
+		return;
+
+	/* see erratum #382 */
+	if ((boot_cpu_data.x86 == 0x10) && (boot_cpu_data.x86_model < 0x8))
+		return;
+
 	this_leaf->can_disable = 1;
 }
 
@@ -696,98 +705,76 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
 #define to_object(k)	container_of(k, struct _index_kobject, kobj)
 #define to_attr(a)	container_of(a, struct _cache_attr, attr)
 
-#ifdef CONFIG_PCI
-static struct pci_dev *get_k8_northbridge(int node)
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
+				  unsigned int index)
 {
-	struct pci_dev *dev = NULL;
-	int i;
-
-	for (i = 0; i <= node; i++) {
-		do {
-			dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
-			if (!dev)
-				break;
-		} while (!pci_match_id(&k8_nb_id[0], dev));
-		if (!dev)
-			break;
-	}
-	return dev;
-}
-#else
-static struct pci_dev *get_k8_northbridge(int node)
-{
-	return NULL;
-}
-#endif
-
-static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
-{
-	const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
-	int node = cpu_to_node(cpumask_first(mask));
-	struct pci_dev *dev = NULL;
-	ssize_t ret = 0;
-	int i;
+	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+	int node = cpu_to_node(cpu);
+	struct pci_dev *dev = node_to_k8_nb_misc(node);
+	unsigned int reg = 0;
 
 	if (!this_leaf->can_disable)
-		return sprintf(buf, "Feature not enabled\n");
-
-	dev = get_k8_northbridge(node);
-	if (!dev) {
-		printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
 		return -EINVAL;
-	}
 
-	for (i = 0; i < 2; i++) {
-		unsigned int reg;
+	if (!dev)
+		return -EINVAL;
 
-		pci_read_config_dword(dev, 0x1BC + i * 4, &reg);
-
-		ret += sprintf(buf, "%sEntry: %d\n", buf, i);
-		ret += sprintf(buf, "%sReads:  %s\tNew Entries: %s\n",  
-			buf,
-			reg & 0x80000000 ? "Disabled" : "Allowed",
-			reg & 0x40000000 ? "Disabled" : "Allowed");
-		ret += sprintf(buf, "%sSubCache: %x\tIndex: %x\n",
-			buf, (reg & 0x30000) >> 16, reg & 0xfff);
-	}
-	return ret;
+	pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
+	return sprintf(buf, "%x\n", reg);
 }
 
-static ssize_t
-store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
-		    size_t count)
+#define SHOW_CACHE_DISABLE(index)					\
+static ssize_t								\
+show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf)  	\
+{									\
+	return show_cache_disable(this_leaf, buf, index);		\
+}
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
+
+static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
+	const char *buf, size_t count, unsigned int index)
 {
-	const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
-	int node = cpu_to_node(cpumask_first(mask));
-	struct pci_dev *dev = NULL;
-	unsigned int ret, index, val;
+	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+	int node = cpu_to_node(cpu);
+	struct pci_dev *dev = node_to_k8_nb_misc(node);
+	unsigned long val = 0;
+	unsigned int scrubber = 0;
 
 	if (!this_leaf->can_disable)
-		return 0;
-
-	if (strlen(buf) > 15)
 		return -EINVAL;
 
-	ret = sscanf(buf, "%x %x", &index, &val);
-	if (ret != 2)
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!dev)
 		return -EINVAL;
-	if (index > 1)
+
+	if (strict_strtoul(buf, 10, &val) < 0)
 		return -EINVAL;
 
 	val |= 0xc0000000;
-	dev = get_k8_northbridge(node);
-	if (!dev) {
-		printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
-		return -EINVAL;
-	}
+
+	pci_read_config_dword(dev, 0x58, &scrubber);
+	scrubber &= ~0x1f000000;
+	pci_write_config_dword(dev, 0x58, scrubber);
 
 	pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000);
 	wbinvd();
 	pci_write_config_dword(dev, 0x1BC + index * 4, val);
-
-	return 1;
+	return count;
 }
 
+#define STORE_CACHE_DISABLE(index)					\
+static ssize_t								\
+store_cache_disable_##index(struct _cpuid4_info *this_leaf,	     	\
+			    const char *buf, size_t count)		\
+{									\
+	return store_cache_disable(this_leaf, buf, count, index);	\
+}
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
+
 struct _cache_attr {
 	struct attribute attr;
 	ssize_t (*show)(struct _cpuid4_info *, char *);
@@ -808,7 +795,10 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
-static struct _cache_attr cache_disable = __ATTR(cache_disable, 0644, show_cache_disable, store_cache_disable);
+static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
+		show_cache_disable_0, store_cache_disable_0);
+static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
+		show_cache_disable_1, store_cache_disable_1);
 
 static struct attribute * default_attrs[] = {
 	&type.attr,
@@ -820,7 +810,8 @@ static struct attribute * default_attrs[] = {
 	&size.attr,
 	&shared_cpu_map.attr,
 	&shared_cpu_list.attr,
-	&cache_disable.attr,
+	&cache_disable_0.attr,
+	&cache_disable_1.attr,
 	NULL
 };
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 09dd1d414fc3..289cc4815028 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -420,6 +420,7 @@ void do_machine_check(struct pt_regs * regs, long error_code)
  out2:
 	atomic_dec(&mce_entry);
 }
+EXPORT_SYMBOL_GPL(do_machine_check);
 
 #ifdef CONFIG_X86_MCE_INTEL
 /***
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index cef3ee30744b..65a0fceedcd7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -15,7 +15,6 @@
 #include <asm/hw_irq.h>
 #include <asm/idle.h>
 #include <asm/therm_throt.h>
-#include <asm/apic.h>
 
 asmlinkage void smp_thermal_interrupt(void)
 {
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index ce0fe4b5c04f..1d584a18a50d 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -808,7 +808,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 
 	if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
 		return 0;
-	rdmsr(MTRRdefType_MSR, def, dummy);
+	rdmsr(MSR_MTRRdefType, def, dummy);
 	def &= 0xff;
 	if (def != MTRR_TYPE_UNCACHABLE)
 		return 0;
@@ -1003,7 +1003,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 	 */
 	if (!is_cpu(INTEL) || disable_mtrr_trim)
 		return 0;
-	rdmsr(MTRRdefType_MSR, def, dummy);
+	rdmsr(MSR_MTRRdefType, def, dummy);
 	def &= 0xff;
 	if (def != MTRR_TYPE_UNCACHABLE)
 		return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index d21d4fb161f7..0543f69f0b27 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -20,9 +20,9 @@ struct fixed_range_block {
 };
 
 static struct fixed_range_block fixed_range_blocks[] = {
-	{ MTRRfix64K_00000_MSR, 1 }, /* one  64k MTRR  */
-	{ MTRRfix16K_80000_MSR, 2 }, /* two  16k MTRRs */
-	{ MTRRfix4K_C0000_MSR,  8 }, /* eight 4k MTRRs */
+	{ MSR_MTRRfix64K_00000, 1 }, /* one  64k MTRR  */
+	{ MSR_MTRRfix16K_80000, 2 }, /* two  16k MTRRs */
+	{ MSR_MTRRfix4K_C0000,  8 }, /* eight 4k MTRRs */
 	{}
 };
 
@@ -194,12 +194,12 @@ get_fixed_ranges(mtrr_type * frs)
 
 	k8_check_syscfg_dram_mod_en();
 
-	rdmsr(MTRRfix64K_00000_MSR, p[0], p[1]);
+	rdmsr(MSR_MTRRfix64K_00000, p[0], p[1]);
 
 	for (i = 0; i < 2; i++)
-		rdmsr(MTRRfix16K_80000_MSR + i, p[2 + i * 2], p[3 + i * 2]);
+		rdmsr(MSR_MTRRfix16K_80000 + i, p[2 + i * 2], p[3 + i * 2]);
 	for (i = 0; i < 8; i++)
-		rdmsr(MTRRfix4K_C0000_MSR + i, p[6 + i * 2], p[7 + i * 2]);
+		rdmsr(MSR_MTRRfix4K_C0000 + i, p[6 + i * 2], p[7 + i * 2]);
 }
 
 void mtrr_save_fixed_ranges(void *info)
@@ -310,7 +310,7 @@ void __init get_mtrr_state(void)
 
 	vrs = mtrr_state.var_ranges;
 
-	rdmsr(MTRRcap_MSR, lo, dummy);
+	rdmsr(MSR_MTRRcap, lo, dummy);
 	mtrr_state.have_fixed = (lo >> 8) & 1;
 
 	for (i = 0; i < num_var_ranges; i++)
@@ -318,7 +318,7 @@ void __init get_mtrr_state(void)
 	if (mtrr_state.have_fixed)
 		get_fixed_ranges(mtrr_state.fixed_ranges);
 
-	rdmsr(MTRRdefType_MSR, lo, dummy);
+	rdmsr(MSR_MTRRdefType, lo, dummy);
 	mtrr_state.def_type = (lo & 0xff);
 	mtrr_state.enabled = (lo & 0xc00) >> 10;
 
@@ -583,10 +583,10 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	__flush_tlb();
 
 	/*  Save MTRR state */
-	rdmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
+	rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
 
 	/*  Disable MTRRs, and set the default type to uncached  */
-	mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & ~0xcff, deftype_hi);
+	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
 }
 
 static void post_set(void) __releases(set_atomicity_lock)
@@ -595,7 +595,7 @@ static void post_set(void) __releases(set_atomicity_lock)
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */
-	mtrr_wrmsr(MTRRdefType_MSR, deftype_lo, deftype_hi);
+	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
 		
 	/*  Enable caches  */
 	write_cr0(read_cr0() & 0xbfffffff);
@@ -707,7 +707,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, unsigned i
 static int generic_have_wrcomb(void)
 {
 	unsigned long config, dummy;
-	rdmsr(MTRRcap_MSR, config, dummy);
+	rdmsr(MSR_MTRRcap, config, dummy);
 	return (config & (1 << 10));
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 03cda01f57c7..8fc248b5aeaf 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -104,7 +104,7 @@ static void __init set_num_var_ranges(void)
 	unsigned long config = 0, dummy;
 
 	if (use_intel()) {
-		rdmsr(MTRRcap_MSR, config, dummy);
+		rdmsr(MSR_MTRRcap, config, dummy);
 	} else if (is_cpu(AMD))
 		config = 2;
 	else if (is_cpu(CYRIX) || is_cpu(CENTAUR))
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 77f67f7b347a..7538b767f206 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -5,21 +5,6 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 
-#define MTRRcap_MSR     0x0fe
-#define MTRRdefType_MSR 0x2ff
-
-#define MTRRfix64K_00000_MSR 0x250
-#define MTRRfix16K_80000_MSR 0x258
-#define MTRRfix16K_A0000_MSR 0x259
-#define MTRRfix4K_C0000_MSR 0x268
-#define MTRRfix4K_C8000_MSR 0x269
-#define MTRRfix4K_D0000_MSR 0x26a
-#define MTRRfix4K_D8000_MSR 0x26b
-#define MTRRfix4K_E0000_MSR 0x26c
-#define MTRRfix4K_E8000_MSR 0x26d
-#define MTRRfix4K_F0000_MSR 0x26e
-#define MTRRfix4K_F8000_MSR 0x26f
-
 #define MTRR_CHANGE_MASK_FIXED     0x01
 #define MTRR_CHANGE_MASK_VARIABLE  0x02
 #define MTRR_CHANGE_MASK_DEFTYPE   0x04
diff --git a/arch/x86/kernel/cpu/mtrr/state.c b/arch/x86/kernel/cpu/mtrr/state.c
index 7f7e2753685b..1f5fb1588d1f 100644
--- a/arch/x86/kernel/cpu/mtrr/state.c
+++ b/arch/x86/kernel/cpu/mtrr/state.c
@@ -35,7 +35,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt)
 
 		if (use_intel())
 			/*  Save MTRR state */
-			rdmsr(MTRRdefType_MSR, ctxt->deftype_lo, ctxt->deftype_hi);
+			rdmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi);
 		else
 			/* Cyrix ARRs - everything else were excluded at the top */
 			ctxt->ccr3 = getCx86(CX86_CCR3);
@@ -46,7 +46,7 @@ void set_mtrr_cache_disable(struct set_mtrr_context *ctxt)
 {
 	if (use_intel())
 		/*  Disable MTRRs, and set the default type to uncached  */
-		mtrr_wrmsr(MTRRdefType_MSR, ctxt->deftype_lo & 0xf300UL,
+		mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo & 0xf300UL,
 		      ctxt->deftype_hi);
 	else if (is_cpu(CYRIX))
 		/* Cyrix ARRs - everything else were excluded at the top */
@@ -64,7 +64,7 @@ void set_mtrr_done(struct set_mtrr_context *ctxt)
 		/*  Restore MTRRdefType  */
 		if (use_intel())
 			/* Intel (P6) standard MTRRs */
-			mtrr_wrmsr(MTRRdefType_MSR, ctxt->deftype_lo, ctxt->deftype_hi);
+			mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi);
 		else
 			/* Cyrix ARRs - everything else was excluded at the top */
 			setCx86(CX86_CCR3, ctxt->ccr3);
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
new file mode 100644
index 000000000000..895c82e78455
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -0,0 +1,1704 @@
+/*
+ * Performance counter x86 architecture code
+ *
+ *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
+ *  Copyright (C) 2009 Jaswinder Singh Rajput
+ *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+
+#include <linux/perf_counter.h>
+#include <linux/capability.h>
+#include <linux/notifier.h>
+#include <linux/hardirq.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/kdebug.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+
+#include <asm/apic.h>
+#include <asm/stacktrace.h>
+#include <asm/nmi.h>
+
+static u64 perf_counter_mask __read_mostly;
+
+struct cpu_hw_counters {
+	struct perf_counter	*counters[X86_PMC_IDX_MAX];
+	unsigned long		used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	unsigned long		interrupts;
+	int			enabled;
+};
+
+/*
+ * struct x86_pmu - generic x86 pmu
+ */
+struct x86_pmu {
+	const char	*name;
+	int		version;
+	int		(*handle_irq)(struct pt_regs *);
+	void		(*disable_all)(void);
+	void		(*enable_all)(void);
+	void		(*enable)(struct hw_perf_counter *, int);
+	void		(*disable)(struct hw_perf_counter *, int);
+	unsigned	eventsel;
+	unsigned	perfctr;
+	u64		(*event_map)(int);
+	u64		(*raw_event)(u64);
+	int		max_events;
+	int		num_counters;
+	int		num_counters_fixed;
+	int		counter_bits;
+	u64		counter_mask;
+	u64		max_period;
+	u64		intel_ctrl;
+};
+
+static struct x86_pmu x86_pmu __read_mostly;
+
+static DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters) = {
+	.enabled = 1,
+};
+
+/*
+ * Intel PerfMon v3. Used on Core2 and later.
+ */
+static const u64 intel_perfmon_event_map[] =
+{
+  [PERF_COUNT_HW_CPU_CYCLES]		= 0x003c,
+  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x4f2e,
+  [PERF_COUNT_HW_CACHE_MISSES]		= 0x412e,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
+  [PERF_COUNT_HW_BUS_CYCLES]		= 0x013c,
+};
+
+static u64 intel_pmu_event_map(int event)
+{
+	return intel_perfmon_event_map[event];
+}
+
+/*
+ * Generalized hw caching related event table, filled
+ * in on a per model basis. A value of 0 means
+ * 'not supported', -1 means 'event makes no sense on
+ * this CPU', any other value means the raw event
+ * ID.
+ */
+
+#define C(x) PERF_COUNT_HW_CACHE_##x
+
+static u64 __read_mostly hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX];
+
+static const u64 nehalem_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI            */
+		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE         */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI            */
+		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE         */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
+		[ C(RESULT_MISS)   ] = 0x024e, /* L1D_PREFETCH.MISS            */
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                    */
+		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
+		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
+		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
+		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI   (alias)  */
+		[ C(RESULT_MISS)   ] = 0x0108, /* DTLB_LOAD_MISSES.ANY         */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI   (alias)  */
+		[ C(RESULT_MISS)   ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS  */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P           */
+		[ C(RESULT_MISS)   ] = 0x20c8, /* ITLB_MISS_RETIRED            */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0x03e8, /* BPU_CLEARS.ANY               */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static const u64 core2_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI          */
+		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE       */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI          */
+		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE       */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x104e, /* L1D_PREFETCH.REQUESTS      */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080, /* L1I.READS                  */
+		[ C(RESULT_MISS)   ] = 0x0081, /* L1I.MISSES                 */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI                 */
+		[ C(RESULT_MISS)   ] = 0x4129, /* L2_LD.ISTATE               */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI                 */
+		[ C(RESULT_MISS)   ] = 0x412A, /* L2_ST.ISTATE               */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI  (alias) */
+		[ C(RESULT_MISS)   ] = 0x0208, /* DTLB_MISSES.MISS_LD        */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI  (alias) */
+		[ C(RESULT_MISS)   ] = 0x0808, /* DTLB_MISSES.MISS_ST        */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P         */
+		[ C(RESULT_MISS)   ] = 0x1282, /* ITLBMISSES                 */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY        */
+		[ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED    */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static const u64 atom_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE.LD               */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE.ST               */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                  */
+		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                 */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI                 */
+		[ C(RESULT_MISS)   ] = 0x4129, /* L2_LD.ISTATE               */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI                 */
+		[ C(RESULT_MISS)   ] = 0x412A, /* L2_ST.ISTATE               */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE_LD.MESI  (alias) */
+		[ C(RESULT_MISS)   ] = 0x0508, /* DTLB_MISSES.MISS_LD        */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE_ST.MESI  (alias) */
+		[ C(RESULT_MISS)   ] = 0x0608, /* DTLB_MISSES.MISS_ST        */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P         */
+		[ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES                */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY        */
+		[ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED    */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static u64 intel_pmu_raw_event(u64 event)
+{
+#define CORE_EVNTSEL_EVENT_MASK		0x000000FFULL
+#define CORE_EVNTSEL_UNIT_MASK		0x0000FF00ULL
+#define CORE_EVNTSEL_EDGE_MASK		0x00040000ULL
+#define CORE_EVNTSEL_INV_MASK		0x00800000ULL
+#define CORE_EVNTSEL_COUNTER_MASK	0xFF000000ULL
+
+#define CORE_EVNTSEL_MASK		\
+	(CORE_EVNTSEL_EVENT_MASK |	\
+	 CORE_EVNTSEL_UNIT_MASK  |	\
+	 CORE_EVNTSEL_EDGE_MASK  |	\
+	 CORE_EVNTSEL_INV_MASK  |	\
+	 CORE_EVNTSEL_COUNTER_MASK)
+
+	return event & CORE_EVNTSEL_MASK;
+}
+
+static const u64 amd_0f_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction cache fetches  */
+		[ C(RESULT_MISS)   ] = 0x0081, /* Instruction cache misses   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes        */
+		[ C(RESULT_MISS)   ] = 0x0085, /* Instr. fetch ITLB misses   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c2, /* Retired Branch Instr.      */
+		[ C(RESULT_MISS)   ] = 0x00c3, /* Retired Mispredicted BI    */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+/*
+ * AMD Performance Monitor K7 and later.
+ */
+static const u64 amd_perfmon_event_map[] =
+{
+  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0080,
+  [PERF_COUNT_HW_CACHE_MISSES]		= 0x0081,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
+};
+
+static u64 amd_pmu_event_map(int event)
+{
+	return amd_perfmon_event_map[event];
+}
+
+static u64 amd_pmu_raw_event(u64 event)
+{
+#define K7_EVNTSEL_EVENT_MASK	0x7000000FFULL
+#define K7_EVNTSEL_UNIT_MASK	0x00000FF00ULL
+#define K7_EVNTSEL_EDGE_MASK	0x000040000ULL
+#define K7_EVNTSEL_INV_MASK	0x000800000ULL
+#define K7_EVNTSEL_COUNTER_MASK	0x0FF000000ULL
+
+#define K7_EVNTSEL_MASK			\
+	(K7_EVNTSEL_EVENT_MASK |	\
+	 K7_EVNTSEL_UNIT_MASK  |	\
+	 K7_EVNTSEL_EDGE_MASK  |	\
+	 K7_EVNTSEL_INV_MASK   |	\
+	 K7_EVNTSEL_COUNTER_MASK)
+
+	return event & K7_EVNTSEL_MASK;
+}
+
+/*
+ * Propagate counter elapsed time into the generic counter.
+ * Can only be executed on the CPU where the counter is active.
+ * Returns the delta events processed.
+ */
+static u64
+x86_perf_counter_update(struct perf_counter *counter,
+			struct hw_perf_counter *hwc, int idx)
+{
+	int shift = 64 - x86_pmu.counter_bits;
+	u64 prev_raw_count, new_raw_count;
+	s64 delta;
+
+	/*
+	 * Careful: an NMI might modify the previous counter value.
+	 *
+	 * Our tactic to handle this is to first atomically read and
+	 * exchange a new raw count - then add that new-prev delta
+	 * count to the generic counter atomically:
+	 */
+again:
+	prev_raw_count = atomic64_read(&hwc->prev_count);
+	rdmsrl(hwc->counter_base + idx, new_raw_count);
+
+	if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+					new_raw_count) != prev_raw_count)
+		goto again;
+
+	/*
+	 * Now we have the new raw value and have updated the prev
+	 * timestamp already. We can now calculate the elapsed delta
+	 * (counter-)time and add that to the generic counter.
+	 *
+	 * Careful, not all hw sign-extends above the physical width
+	 * of the count.
+	 */
+	delta = (new_raw_count << shift) - (prev_raw_count << shift);
+	delta >>= shift;
+
+	atomic64_add(delta, &counter->count);
+	atomic64_sub(delta, &hwc->period_left);
+
+	return new_raw_count;
+}
+
+static atomic_t active_counters;
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+static bool reserve_pmc_hardware(void)
+{
+	int i;
+
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+		disable_lapic_nmi_watchdog();
+
+	for (i = 0; i < x86_pmu.num_counters; i++) {
+		if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
+			goto perfctr_fail;
+	}
+
+	for (i = 0; i < x86_pmu.num_counters; i++) {
+		if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
+			goto eventsel_fail;
+	}
+
+	return true;
+
+eventsel_fail:
+	for (i--; i >= 0; i--)
+		release_evntsel_nmi(x86_pmu.eventsel + i);
+
+	i = x86_pmu.num_counters;
+
+perfctr_fail:
+	for (i--; i >= 0; i--)
+		release_perfctr_nmi(x86_pmu.perfctr + i);
+
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+		enable_lapic_nmi_watchdog();
+
+	return false;
+}
+
+static void release_pmc_hardware(void)
+{
+	int i;
+
+	for (i = 0; i < x86_pmu.num_counters; i++) {
+		release_perfctr_nmi(x86_pmu.perfctr + i);
+		release_evntsel_nmi(x86_pmu.eventsel + i);
+	}
+
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+		enable_lapic_nmi_watchdog();
+}
+
+static void hw_perf_counter_destroy(struct perf_counter *counter)
+{
+	if (atomic_dec_and_mutex_lock(&active_counters, &pmc_reserve_mutex)) {
+		release_pmc_hardware();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
+static inline int x86_pmu_initialized(void)
+{
+	return x86_pmu.handle_irq != NULL;
+}
+
+static inline int
+set_ext_hw_attr(struct hw_perf_counter *hwc, struct perf_counter_attr *attr)
+{
+	unsigned int cache_type, cache_op, cache_result;
+	u64 config, val;
+
+	config = attr->config;
+
+	cache_type = (config >>  0) & 0xff;
+	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
+		return -EINVAL;
+
+	cache_op = (config >>  8) & 0xff;
+	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
+		return -EINVAL;
+
+	cache_result = (config >> 16) & 0xff;
+	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+		return -EINVAL;
+
+	val = hw_cache_event_ids[cache_type][cache_op][cache_result];
+
+	if (val == 0)
+		return -ENOENT;
+
+	if (val == -1)
+		return -EINVAL;
+
+	hwc->config |= val;
+
+	return 0;
+}
+
+/*
+ * Setup the hardware configuration for a given attr_type
+ */
+static int __hw_perf_counter_init(struct perf_counter *counter)
+{
+	struct perf_counter_attr *attr = &counter->attr;
+	struct hw_perf_counter *hwc = &counter->hw;
+	int err;
+
+	if (!x86_pmu_initialized())
+		return -ENODEV;
+
+	err = 0;
+	if (!atomic_inc_not_zero(&active_counters)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&active_counters) == 0 && !reserve_pmc_hardware())
+			err = -EBUSY;
+		else
+			atomic_inc(&active_counters);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+	if (err)
+		return err;
+
+	/*
+	 * Generate PMC IRQs:
+	 * (keep 'enabled' bit clear for now)
+	 */
+	hwc->config = ARCH_PERFMON_EVENTSEL_INT;
+
+	/*
+	 * Count user and OS events unless requested not to.
+	 */
+	if (!attr->exclude_user)
+		hwc->config |= ARCH_PERFMON_EVENTSEL_USR;
+	if (!attr->exclude_kernel)
+		hwc->config |= ARCH_PERFMON_EVENTSEL_OS;
+
+	if (!hwc->sample_period) {
+		hwc->sample_period = x86_pmu.max_period;
+		hwc->last_period = hwc->sample_period;
+		atomic64_set(&hwc->period_left, hwc->sample_period);
+	}
+
+	counter->destroy = hw_perf_counter_destroy;
+
+	/*
+	 * Raw event type provide the config in the event structure
+	 */
+	if (attr->type == PERF_TYPE_RAW) {
+		hwc->config |= x86_pmu.raw_event(attr->config);
+		return 0;
+	}
+
+	if (attr->type == PERF_TYPE_HW_CACHE)
+		return set_ext_hw_attr(hwc, attr);
+
+	if (attr->config >= x86_pmu.max_events)
+		return -EINVAL;
+	/*
+	 * The generic map:
+	 */
+	hwc->config |= x86_pmu.event_map(attr->config);
+
+	return 0;
+}
+
+static void intel_pmu_disable_all(void)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+}
+
+static void amd_pmu_disable_all(void)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+	int idx;
+
+	if (!cpuc->enabled)
+		return;
+
+	cpuc->enabled = 0;
+	/*
+	 * ensure we write the disable before we start disabling the
+	 * counters proper, so that amd_pmu_enable_counter() does the
+	 * right thing.
+	 */
+	barrier();
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		u64 val;
+
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+		rdmsrl(MSR_K7_EVNTSEL0 + idx, val);
+		if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE))
+			continue;
+		val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+		wrmsrl(MSR_K7_EVNTSEL0 + idx, val);
+	}
+}
+
+void hw_perf_disable(void)
+{
+	if (!x86_pmu_initialized())
+		return;
+	return x86_pmu.disable_all();
+}
+
+static void intel_pmu_enable_all(void)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+}
+
+static void amd_pmu_enable_all(void)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+	int idx;
+
+	if (cpuc->enabled)
+		return;
+
+	cpuc->enabled = 1;
+	barrier();
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		u64 val;
+
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+		rdmsrl(MSR_K7_EVNTSEL0 + idx, val);
+		if (val & ARCH_PERFMON_EVENTSEL0_ENABLE)
+			continue;
+		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+		wrmsrl(MSR_K7_EVNTSEL0 + idx, val);
+	}
+}
+
+void hw_perf_enable(void)
+{
+	if (!x86_pmu_initialized())
+		return;
+	x86_pmu.enable_all();
+}
+
+static inline u64 intel_pmu_get_status(void)
+{
+	u64 status;
+
+	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+
+	return status;
+}
+
+static inline void intel_pmu_ack_status(u64 ack)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+}
+
+static inline void x86_pmu_enable_counter(struct hw_perf_counter *hwc, int idx)
+{
+	int err;
+	err = checking_wrmsrl(hwc->config_base + idx,
+			      hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE);
+}
+
+static inline void x86_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
+{
+	int err;
+	err = checking_wrmsrl(hwc->config_base + idx,
+			      hwc->config);
+}
+
+static inline void
+intel_pmu_disable_fixed(struct hw_perf_counter *hwc, int __idx)
+{
+	int idx = __idx - X86_PMC_IDX_FIXED;
+	u64 ctrl_val, mask;
+	int err;
+
+	mask = 0xfULL << (idx * 4);
+
+	rdmsrl(hwc->config_base, ctrl_val);
+	ctrl_val &= ~mask;
+	err = checking_wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static inline void
+intel_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
+{
+	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+		intel_pmu_disable_fixed(hwc, idx);
+		return;
+	}
+
+	x86_pmu_disable_counter(hwc, idx);
+}
+
+static inline void
+amd_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
+{
+	x86_pmu_disable_counter(hwc, idx);
+}
+
+static DEFINE_PER_CPU(u64, prev_left[X86_PMC_IDX_MAX]);
+
+/*
+ * Set the next IRQ period, based on the hwc->period_left value.
+ * To be called with the counter disabled in hw:
+ */
+static int
+x86_perf_counter_set_period(struct perf_counter *counter,
+			     struct hw_perf_counter *hwc, int idx)
+{
+	s64 left = atomic64_read(&hwc->period_left);
+	s64 period = hwc->sample_period;
+	int err, ret = 0;
+
+	/*
+	 * If we are way outside a reasoable range then just skip forward:
+	 */
+	if (unlikely(left <= -period)) {
+		left = period;
+		atomic64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	}
+
+	if (unlikely(left <= 0)) {
+		left += period;
+		atomic64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	}
+	/*
+	 * Quirk: certain CPUs dont like it if just 1 event is left:
+	 */
+	if (unlikely(left < 2))
+		left = 2;
+
+	if (left > x86_pmu.max_period)
+		left = x86_pmu.max_period;
+
+	per_cpu(prev_left[idx], smp_processor_id()) = left;
+
+	/*
+	 * The hw counter starts counting from this counter offset,
+	 * mark it to be able to extra future deltas:
+	 */
+	atomic64_set(&hwc->prev_count, (u64)-left);
+
+	err = checking_wrmsrl(hwc->counter_base + idx,
+			     (u64)(-left) & x86_pmu.counter_mask);
+
+	return ret;
+}
+
+static inline void
+intel_pmu_enable_fixed(struct hw_perf_counter *hwc, int __idx)
+{
+	int idx = __idx - X86_PMC_IDX_FIXED;
+	u64 ctrl_val, bits, mask;
+	int err;
+
+	/*
+	 * Enable IRQ generation (0x8),
+	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
+	 * if requested:
+	 */
+	bits = 0x8ULL;
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
+		bits |= 0x2;
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+		bits |= 0x1;
+	bits <<= (idx * 4);
+	mask = 0xfULL << (idx * 4);
+
+	rdmsrl(hwc->config_base, ctrl_val);
+	ctrl_val &= ~mask;
+	ctrl_val |= bits;
+	err = checking_wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static void intel_pmu_enable_counter(struct hw_perf_counter *hwc, int idx)
+{
+	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+		intel_pmu_enable_fixed(hwc, idx);
+		return;
+	}
+
+	x86_pmu_enable_counter(hwc, idx);
+}
+
+static void amd_pmu_enable_counter(struct hw_perf_counter *hwc, int idx)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+
+	if (cpuc->enabled)
+		x86_pmu_enable_counter(hwc, idx);
+	else
+		x86_pmu_disable_counter(hwc, idx);
+}
+
+static int
+fixed_mode_idx(struct perf_counter *counter, struct hw_perf_counter *hwc)
+{
+	unsigned int event;
+
+	if (!x86_pmu.num_counters_fixed)
+		return -1;
+
+	event = hwc->config & ARCH_PERFMON_EVENT_MASK;
+
+	if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
+		return X86_PMC_IDX_FIXED_INSTRUCTIONS;
+	if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_CPU_CYCLES)))
+		return X86_PMC_IDX_FIXED_CPU_CYCLES;
+	if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_BUS_CYCLES)))
+		return X86_PMC_IDX_FIXED_BUS_CYCLES;
+
+	return -1;
+}
+
+/*
+ * Find a PMC slot for the freshly enabled / scheduled in counter:
+ */
+static int x86_pmu_enable(struct perf_counter *counter)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+	struct hw_perf_counter *hwc = &counter->hw;
+	int idx;
+
+	idx = fixed_mode_idx(counter, hwc);
+	if (idx >= 0) {
+		/*
+		 * Try to get the fixed counter, if that is already taken
+		 * then try to get a generic counter:
+		 */
+		if (test_and_set_bit(idx, cpuc->used_mask))
+			goto try_generic;
+
+		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
+		/*
+		 * We set it so that counter_base + idx in wrmsr/rdmsr maps to
+		 * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
+		 */
+		hwc->counter_base =
+			MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
+		hwc->idx = idx;
+	} else {
+		idx = hwc->idx;
+		/* Try to get the previous generic counter again */
+		if (test_and_set_bit(idx, cpuc->used_mask)) {
+try_generic:
+			idx = find_first_zero_bit(cpuc->used_mask,
+						  x86_pmu.num_counters);
+			if (idx == x86_pmu.num_counters)
+				return -EAGAIN;
+
+			set_bit(idx, cpuc->used_mask);
+			hwc->idx = idx;
+		}
+		hwc->config_base  = x86_pmu.eventsel;
+		hwc->counter_base = x86_pmu.perfctr;
+	}
+
+	perf_counters_lapic_init();
+
+	x86_pmu.disable(hwc, idx);
+
+	cpuc->counters[idx] = counter;
+	set_bit(idx, cpuc->active_mask);
+
+	x86_perf_counter_set_period(counter, hwc, idx);
+	x86_pmu.enable(hwc, idx);
+
+	return 0;
+}
+
+static void x86_pmu_unthrottle(struct perf_counter *counter)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+	struct hw_perf_counter *hwc = &counter->hw;
+
+	if (WARN_ON_ONCE(hwc->idx >= X86_PMC_IDX_MAX ||
+				cpuc->counters[hwc->idx] != counter))
+		return;
+
+	x86_pmu.enable(hwc, hwc->idx);
+}
+
+void perf_counter_print_debug(void)
+{
+	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
+	struct cpu_hw_counters *cpuc;
+	unsigned long flags;
+	int cpu, idx;
+
+	if (!x86_pmu.num_counters)
+		return;
+
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+	cpuc = &per_cpu(cpu_hw_counters, cpu);
+
+	if (x86_pmu.version >= 2) {
+		rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
+		rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+		rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
+		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);
+
+		pr_info("\n");
+		pr_info("CPU#%d: ctrl:       %016llx\n", cpu, ctrl);
+		pr_info("CPU#%d: status:     %016llx\n", cpu, status);
+		pr_info("CPU#%d: overflow:   %016llx\n", cpu, overflow);
+		pr_info("CPU#%d: fixed:      %016llx\n", cpu, fixed);
+	}
+	pr_info("CPU#%d: used:       %016llx\n", cpu, *(u64 *)cpuc->used_mask);
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
+		rdmsrl(x86_pmu.perfctr  + idx, pmc_count);
+
+		prev_left = per_cpu(prev_left[idx], cpu);
+
+		pr_info("CPU#%d:   gen-PMC%d ctrl:  %016llx\n",
+			cpu, idx, pmc_ctrl);
+		pr_info("CPU#%d:   gen-PMC%d count: %016llx\n",
+			cpu, idx, pmc_count);
+		pr_info("CPU#%d:   gen-PMC%d left:  %016llx\n",
+			cpu, idx, prev_left);
+	}
+	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
+		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
+
+		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
+			cpu, idx, pmc_count);
+	}
+	local_irq_restore(flags);
+}
+
+static void x86_pmu_disable(struct perf_counter *counter)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+	struct hw_perf_counter *hwc = &counter->hw;
+	int idx = hwc->idx;
+
+	/*
+	 * Must be done before we disable, otherwise the nmi handler
+	 * could reenable again:
+	 */
+	clear_bit(idx, cpuc->active_mask);
+	x86_pmu.disable(hwc, idx);
+
+	/*
+	 * Make sure the cleared pointer becomes visible before we
+	 * (potentially) free the counter:
+	 */
+	barrier();
+
+	/*
+	 * Drain the remaining delta count out of a counter
+	 * that we are disabling:
+	 */
+	x86_perf_counter_update(counter, hwc, idx);
+	cpuc->counters[idx] = NULL;
+	clear_bit(idx, cpuc->used_mask);
+}
+
+/*
+ * Save and restart an expired counter. Called by NMI contexts,
+ * so it has to be careful about preempting normal counter ops:
+ */
+static int intel_pmu_save_and_restart(struct perf_counter *counter)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+	int idx = hwc->idx;
+	int ret;
+
+	x86_perf_counter_update(counter, hwc, idx);
+	ret = x86_perf_counter_set_period(counter, hwc, idx);
+
+	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
+		intel_pmu_enable_counter(hwc, idx);
+
+	return ret;
+}
+
+static void intel_pmu_reset(void)
+{
+	unsigned long flags;
+	int idx;
+
+	if (!x86_pmu.num_counters)
+		return;
+
+	local_irq_save(flags);
+
+	printk("clearing PMU state on CPU#%d\n", smp_processor_id());
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
+		checking_wrmsrl(x86_pmu.perfctr  + idx, 0ull);
+	}
+	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
+		checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+	}
+
+	local_irq_restore(flags);
+}
+
+
+/*
+ * This handler is triggered by the local APIC, so the APIC IRQ handling
+ * rules apply:
+ */
+static int intel_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct perf_sample_data data;
+	struct cpu_hw_counters *cpuc;
+	int bit, cpu, loops;
+	u64 ack, status;
+
+	data.regs = regs;
+	data.addr = 0;
+
+	cpu = smp_processor_id();
+	cpuc = &per_cpu(cpu_hw_counters, cpu);
+
+	perf_disable();
+	status = intel_pmu_get_status();
+	if (!status) {
+		perf_enable();
+		return 0;
+	}
+
+	loops = 0;
+again:
+	if (++loops > 100) {
+		WARN_ONCE(1, "perfcounters: irq loop stuck!\n");
+		perf_counter_print_debug();
+		intel_pmu_reset();
+		perf_enable();
+		return 1;
+	}
+
+	inc_irq_stat(apic_perf_irqs);
+	ack = status;
+	for_each_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
+		struct perf_counter *counter = cpuc->counters[bit];
+
+		clear_bit(bit, (unsigned long *) &status);
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+
+		if (!intel_pmu_save_and_restart(counter))
+			continue;
+
+		if (perf_counter_overflow(counter, 1, &data))
+			intel_pmu_disable_counter(&counter->hw, bit);
+	}
+
+	intel_pmu_ack_status(ack);
+
+	/*
+	 * Repeat if there is more work to be done:
+	 */
+	status = intel_pmu_get_status();
+	if (status)
+		goto again;
+
+	perf_enable();
+
+	return 1;
+}
+
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct perf_sample_data data;
+	struct cpu_hw_counters *cpuc;
+	struct perf_counter *counter;
+	struct hw_perf_counter *hwc;
+	int cpu, idx, handled = 0;
+	u64 val;
+
+	data.regs = regs;
+	data.addr = 0;
+
+	cpu = smp_processor_id();
+	cpuc = &per_cpu(cpu_hw_counters, cpu);
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		counter = cpuc->counters[idx];
+		hwc = &counter->hw;
+
+		val = x86_perf_counter_update(counter, hwc, idx);
+		if (val & (1ULL << (x86_pmu.counter_bits - 1)))
+			continue;
+
+		/*
+		 * counter overflow
+		 */
+		handled		= 1;
+		data.period	= counter->hw.last_period;
+
+		if (!x86_perf_counter_set_period(counter, hwc, idx))
+			continue;
+
+		if (perf_counter_overflow(counter, 1, &data))
+			amd_pmu_disable_counter(hwc, idx);
+	}
+
+	if (handled)
+		inc_irq_stat(apic_perf_irqs);
+
+	return handled;
+}
+
+void smp_perf_pending_interrupt(struct pt_regs *regs)
+{
+	irq_enter();
+	ack_APIC_irq();
+	inc_irq_stat(apic_pending_irqs);
+	perf_counter_do_pending();
+	irq_exit();
+}
+
+void set_perf_counter_pending(void)
+{
+	apic->send_IPI_self(LOCAL_PENDING_VECTOR);
+}
+
+void perf_counters_lapic_init(void)
+{
+	if (!x86_pmu_initialized())
+		return;
+
+	/*
+	 * Always use NMI for PMU
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+}
+
+static int __kprobes
+perf_counter_nmi_handler(struct notifier_block *self,
+			 unsigned long cmd, void *__args)
+{
+	struct die_args *args = __args;
+	struct pt_regs *regs;
+
+	if (!atomic_read(&active_counters))
+		return NOTIFY_DONE;
+
+	switch (cmd) {
+	case DIE_NMI:
+	case DIE_NMI_IPI:
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	regs = args->regs;
+
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	/*
+	 * Can't rely on the handled return value to say it was our NMI, two
+	 * counters could trigger 'simultaneously' raising two back-to-back NMIs.
+	 *
+	 * If the first NMI handles both, the latter will be empty and daze
+	 * the CPU.
+	 */
+	x86_pmu.handle_irq(regs);
+
+	return NOTIFY_STOP;
+}
+
+static __read_mostly struct notifier_block perf_counter_nmi_notifier = {
+	.notifier_call		= perf_counter_nmi_handler,
+	.next			= NULL,
+	.priority		= 1
+};
+
+static struct x86_pmu intel_pmu = {
+	.name			= "Intel",
+	.handle_irq		= intel_pmu_handle_irq,
+	.disable_all		= intel_pmu_disable_all,
+	.enable_all		= intel_pmu_enable_all,
+	.enable			= intel_pmu_enable_counter,
+	.disable		= intel_pmu_disable_counter,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= intel_pmu_event_map,
+	.raw_event		= intel_pmu_raw_event,
+	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32 bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic counter period:
+	 */
+	.max_period		= (1ULL << 31) - 1,
+};
+
+static struct x86_pmu amd_pmu = {
+	.name			= "AMD",
+	.handle_irq		= amd_pmu_handle_irq,
+	.disable_all		= amd_pmu_disable_all,
+	.enable_all		= amd_pmu_enable_all,
+	.enable			= amd_pmu_enable_counter,
+	.disable		= amd_pmu_disable_counter,
+	.eventsel		= MSR_K7_EVNTSEL0,
+	.perfctr		= MSR_K7_PERFCTR0,
+	.event_map		= amd_pmu_event_map,
+	.raw_event		= amd_pmu_raw_event,
+	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
+	.num_counters		= 4,
+	.counter_bits		= 48,
+	.counter_mask		= (1ULL << 48) - 1,
+	/* use highest bit to detect overflow */
+	.max_period		= (1ULL << 47) - 1,
+};
+
+static int intel_pmu_init(void)
+{
+	union cpuid10_edx edx;
+	union cpuid10_eax eax;
+	unsigned int unused;
+	unsigned int ebx;
+	int version;
+
+	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
+		return -ENODEV;
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * Branch Misses Retired Event or not.
+	 */
+	cpuid(10, &eax.full, &ebx, &unused, &edx.full);
+	if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
+		return -ENODEV;
+
+	version = eax.split.version_id;
+	if (version < 2)
+		return -ENODEV;
+
+	x86_pmu				= intel_pmu;
+	x86_pmu.version			= version;
+	x86_pmu.num_counters		= eax.split.num_counters;
+	x86_pmu.counter_bits		= eax.split.bit_width;
+	x86_pmu.counter_mask		= (1ULL << eax.split.bit_width) - 1;
+
+	/*
+	 * Quirk: v2 perfmon does not report fixed-purpose counters, so
+	 * assume at least 3 counters:
+	 */
+	x86_pmu.num_counters_fixed	= max((int)edx.split.num_counters_fixed, 3);
+
+	rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+
+	/*
+	 * Install the hw-cache-events table:
+	 */
+	switch (boot_cpu_data.x86_model) {
+	case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+	case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
+	case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
+	case 29: /* six-core 45 nm xeon "Dunnington" */
+		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		pr_cont("Core2 events, ");
+		break;
+	default:
+	case 26:
+		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		pr_cont("Nehalem/Corei7 events, ");
+		break;
+	case 28:
+		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		pr_cont("Atom events, ");
+		break;
+	}
+	return 0;
+}
+
+static int amd_pmu_init(void)
+{
+	x86_pmu = amd_pmu;
+
+	switch (boot_cpu_data.x86) {
+	case 0x0f:
+	case 0x10:
+	case 0x11:
+		memcpy(hw_cache_event_ids, amd_0f_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		pr_cont("AMD Family 0f/10/11 events, ");
+		break;
+	}
+	return 0;
+}
+
+void __init init_hw_perf_counters(void)
+{
+	int err;
+
+	pr_info("Performance Counters: ");
+
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_INTEL:
+		err = intel_pmu_init();
+		break;
+	case X86_VENDOR_AMD:
+		err = amd_pmu_init();
+		break;
+	default:
+		return;
+	}
+	if (err != 0) {
+		pr_cont("no PMU driver, software counters only.\n");
+		return;
+	}
+
+	pr_cont("%s PMU driver.\n", x86_pmu.name);
+
+	if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
+		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
+		WARN(1, KERN_ERR "hw perf counters %d > max(%d), clipping!",
+		     x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
+	}
+	perf_counter_mask = (1 << x86_pmu.num_counters) - 1;
+	perf_max_counters = x86_pmu.num_counters;
+
+	if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
+		x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
+		WARN(1, KERN_ERR "hw perf counters fixed %d > max(%d), clipping!",
+		     x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
+	}
+
+	perf_counter_mask |=
+		((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
+
+	perf_counters_lapic_init();
+	register_die_notifier(&perf_counter_nmi_notifier);
+
+	pr_info("... version:                 %d\n",     x86_pmu.version);
+	pr_info("... bit width:               %d\n",     x86_pmu.counter_bits);
+	pr_info("... generic counters:        %d\n",     x86_pmu.num_counters);
+	pr_info("... value mask:              %016Lx\n", x86_pmu.counter_mask);
+	pr_info("... max period:              %016Lx\n", x86_pmu.max_period);
+	pr_info("... fixed-purpose counters:  %d\n",     x86_pmu.num_counters_fixed);
+	pr_info("... counter mask:            %016Lx\n", perf_counter_mask);
+}
+
+static inline void x86_pmu_read(struct perf_counter *counter)
+{
+	x86_perf_counter_update(counter, &counter->hw, counter->hw.idx);
+}
+
+static const struct pmu pmu = {
+	.enable		= x86_pmu_enable,
+	.disable	= x86_pmu_disable,
+	.read		= x86_pmu_read,
+	.unthrottle	= x86_pmu_unthrottle,
+};
+
+const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
+{
+	int err;
+
+	err = __hw_perf_counter_init(counter);
+	if (err)
+		return ERR_PTR(err);
+
+	return &pmu;
+}
+
+/*
+ * callchain support
+ */
+
+static inline
+void callchain_store(struct perf_callchain_entry *entry, unsigned long ip)
+{
+	if (entry->nr < MAX_STACK_DEPTH)
+		entry->ip[entry->nr++] = ip;
+}
+
+static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry);
+static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry);
+
+
+static void
+backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
+{
+	/* Ignore warnings */
+}
+
+static void backtrace_warning(void *data, char *msg)
+{
+	/* Ignore warnings */
+}
+
+static int backtrace_stack(void *data, char *name)
+{
+	/* Don't bother with IRQ stacks for now */
+	return -1;
+}
+
+static void backtrace_address(void *data, unsigned long addr, int reliable)
+{
+	struct perf_callchain_entry *entry = data;
+
+	if (reliable)
+		callchain_store(entry, addr);
+}
+
+static const struct stacktrace_ops backtrace_ops = {
+	.warning		= backtrace_warning,
+	.warning_symbol		= backtrace_warning_symbol,
+	.stack			= backtrace_stack,
+	.address		= backtrace_address,
+};
+
+static void
+perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+	unsigned long bp;
+	char *stack;
+	int nr = entry->nr;
+
+	callchain_store(entry, instruction_pointer(regs));
+
+	stack = ((char *)regs + sizeof(struct pt_regs));
+#ifdef CONFIG_FRAME_POINTER
+	bp = frame_pointer(regs);
+#else
+	bp = 0;
+#endif
+
+	dump_trace(NULL, regs, (void *)stack, bp, &backtrace_ops, entry);
+
+	entry->kernel = entry->nr - nr;
+}
+
+
+struct stack_frame {
+	const void __user	*next_fp;
+	unsigned long		return_address;
+};
+
+static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+{
+	int ret;
+
+	if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
+		return 0;
+
+	ret = 1;
+	pagefault_disable();
+	if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
+		ret = 0;
+	pagefault_enable();
+
+	return ret;
+}
+
+static void
+perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+	struct stack_frame frame;
+	const void __user *fp;
+	int nr = entry->nr;
+
+	regs = (struct pt_regs *)current->thread.sp0 - 1;
+	fp   = (void __user *)regs->bp;
+
+	callchain_store(entry, regs->ip);
+
+	while (entry->nr < MAX_STACK_DEPTH) {
+		frame.next_fp	     = NULL;
+		frame.return_address = 0;
+
+		if (!copy_stack_frame(fp, &frame))
+			break;
+
+		if ((unsigned long)fp < user_stack_pointer(regs))
+			break;
+
+		callchain_store(entry, frame.return_address);
+		fp = frame.next_fp;
+	}
+
+	entry->user = entry->nr - nr;
+}
+
+static void
+perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+	int is_user;
+
+	if (!regs)
+		return;
+
+	is_user = user_mode(regs);
+
+	if (!current || current->pid == 0)
+		return;
+
+	if (is_user && current->state != TASK_RUNNING)
+		return;
+
+	if (!is_user)
+		perf_callchain_kernel(regs, entry);
+
+	if (current->mm)
+		perf_callchain_user(regs, entry);
+}
+
+struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	struct perf_callchain_entry *entry;
+
+	if (in_nmi())
+		entry = &__get_cpu_var(nmi_entry);
+	else
+		entry = &__get_cpu_var(irq_entry);
+
+	entry->nr = 0;
+	entry->hv = 0;
+	entry->kernel = 0;
+	entry->user = 0;
+
+	perf_do_callchain(regs, entry);
+
+	return entry;
+}
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index f6c70a164e32..d6f5b9fbde32 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -19,8 +19,8 @@
 #include <linux/nmi.h>
 #include <linux/kprobes.h>
 
-#include <asm/genapic.h>
-#include <asm/intel_arch_perfmon.h>
+#include <asm/apic.h>
+#include <asm/perf_counter.h>
 
 struct nmi_watchdog_ctlblk {
 	unsigned int cccr_msr;
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index 87b67e3a765a..48bfe1386038 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -19,45 +19,61 @@
  * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
  */
 
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/trace_clock.h>
 
 #include <asm/ds.h>
 
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/slab.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/kernel.h>
-
+#include "ds_selftest.h"
 
 /*
- * The configuration for a particular DS hardware implementation.
+ * The configuration for a particular DS hardware implementation:
  */
 struct ds_configuration {
-	/* the name of the configuration */
-	const char *name;
-	/* the size of one pointer-typed field in the DS structure and
-	   in the BTS and PEBS buffers in bytes;
-	   this covers the first 8 DS fields related to buffer management. */
-	unsigned char  sizeof_field;
-	/* the size of a BTS/PEBS record in bytes */
-	unsigned char  sizeof_rec[2];
-	/* a series of bit-masks to control various features indexed
-	 * by enum ds_feature */
-	unsigned long ctl[dsf_ctl_max];
+	/* The name of the configuration: */
+	const char		*name;
+
+	/* The size of pointer-typed fields in DS, BTS, and PEBS: */
+	unsigned char		sizeof_ptr_field;
+
+	/* The size of a BTS/PEBS record in bytes: */
+	unsigned char		sizeof_rec[2];
+
+	/* The number of pebs counter reset values in the DS structure. */
+	unsigned char		nr_counter_reset;
+
+	/* Control bit-masks indexed by enum ds_feature: */
+	unsigned long		ctl[dsf_ctl_max];
 };
-static DEFINE_PER_CPU(struct ds_configuration, ds_cfg_array);
+static struct ds_configuration ds_cfg __read_mostly;
 
-#define ds_cfg per_cpu(ds_cfg_array, smp_processor_id())
 
-#define MAX_SIZEOF_DS (12 * 8)	/* maximal size of a DS configuration */
-#define MAX_SIZEOF_BTS (3 * 8)	/* maximal size of a BTS record */
-#define DS_ALIGNMENT (1 << 3)	/* BTS and PEBS buffer alignment */
+/* Maximal size of a DS configuration: */
+#define MAX_SIZEOF_DS		0x80
 
-#define BTS_CONTROL \
- (ds_cfg.ctl[dsf_bts] | ds_cfg.ctl[dsf_bts_kernel] | ds_cfg.ctl[dsf_bts_user] |\
-  ds_cfg.ctl[dsf_bts_overflow])
+/* Maximal size of a BTS record: */
+#define MAX_SIZEOF_BTS		(3 * 8)
 
+/* BTS and PEBS buffer alignment: */
+#define DS_ALIGNMENT		(1 << 3)
+
+/* Number of buffer pointers in DS: */
+#define NUM_DS_PTR_FIELDS	8
+
+/* Size of a pebs reset value in DS: */
+#define PEBS_RESET_FIELD_SIZE	8
+
+/* Mask of control bits in the DS MSR register: */
+#define BTS_CONTROL				  \
+	( ds_cfg.ctl[dsf_bts]			| \
+	  ds_cfg.ctl[dsf_bts_kernel]		| \
+	  ds_cfg.ctl[dsf_bts_user]		| \
+	  ds_cfg.ctl[dsf_bts_overflow] )
 
 /*
  * A BTS or PEBS tracer.
@@ -66,29 +82,36 @@ static DEFINE_PER_CPU(struct ds_configuration, ds_cfg_array);
  * to identify tracers.
  */
 struct ds_tracer {
-	/* the DS context (partially) owned by this tracer */
-	struct ds_context *context;
-	/* the buffer provided on ds_request() and its size in bytes */
-	void *buffer;
-	size_t size;
+	/* The DS context (partially) owned by this tracer. */
+	struct ds_context	*context;
+	/* The buffer provided on ds_request() and its size in bytes. */
+	void			*buffer;
+	size_t			size;
 };
 
 struct bts_tracer {
-	/* the common DS part */
-	struct ds_tracer ds;
-	/* the trace including the DS configuration */
-	struct bts_trace trace;
-	/* buffer overflow notification function */
-	bts_ovfl_callback_t ovfl;
+	/* The common DS part: */
+	struct ds_tracer	ds;
+
+	/* The trace including the DS configuration: */
+	struct bts_trace	trace;
+
+	/* Buffer overflow notification function: */
+	bts_ovfl_callback_t	ovfl;
+
+	/* Active flags affecting trace collection. */
+	unsigned int		flags;
 };
 
 struct pebs_tracer {
-	/* the common DS part */
-	struct ds_tracer ds;
-	/* the trace including the DS configuration */
-	struct pebs_trace trace;
-	/* buffer overflow notification function */
-	pebs_ovfl_callback_t ovfl;
+	/* The common DS part: */
+	struct ds_tracer	ds;
+
+	/* The trace including the DS configuration: */
+	struct pebs_trace	trace;
+
+	/* Buffer overflow notification function: */
+	pebs_ovfl_callback_t	ovfl;
 };
 
 /*
@@ -97,6 +120,7 @@ struct pebs_tracer {
  *
  * The DS configuration consists of the following fields; different
  * architetures vary in the size of those fields.
+ *
  * - double-word aligned base linear address of the BTS buffer
  * - write pointer into the BTS buffer
  * - end linear address of the BTS buffer (one byte beyond the end of
@@ -135,21 +159,22 @@ enum ds_field {
 };
 
 enum ds_qualifier {
-	ds_bts  = 0,
+	ds_bts = 0,
 	ds_pebs
 };
 
-static inline unsigned long ds_get(const unsigned char *base,
-				   enum ds_qualifier qual, enum ds_field field)
+static inline unsigned long
+ds_get(const unsigned char *base, enum ds_qualifier qual, enum ds_field field)
 {
-	base += (ds_cfg.sizeof_field * (field + (4 * qual)));
+	base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
 	return *(unsigned long *)base;
 }
 
-static inline void ds_set(unsigned char *base, enum ds_qualifier qual,
-			  enum ds_field field, unsigned long value)
+static inline void
+ds_set(unsigned char *base, enum ds_qualifier qual, enum ds_field field,
+       unsigned long value)
 {
-	base += (ds_cfg.sizeof_field * (field + (4 * qual)));
+	base += (ds_cfg.sizeof_ptr_field * (field + (4 * qual)));
 	(*(unsigned long *)base) = value;
 }
 
@@ -159,7 +184,6 @@ static inline void ds_set(unsigned char *base, enum ds_qualifier qual,
  */
 static DEFINE_SPINLOCK(ds_lock);
 
-
 /*
  * We either support (system-wide) per-cpu or per-thread allocation.
  * We distinguish the two based on the task_struct pointer, where a
@@ -178,12 +202,28 @@ static DEFINE_SPINLOCK(ds_lock);
  */
 static atomic_t tracers = ATOMIC_INIT(0);
 
-static inline void get_tracer(struct task_struct *task)
+static inline int get_tracer(struct task_struct *task)
 {
-	if (task)
+	int error;
+
+	spin_lock_irq(&ds_lock);
+
+	if (task) {
+		error = -EPERM;
+		if (atomic_read(&tracers) < 0)
+			goto out;
 		atomic_inc(&tracers);
-	else
+	} else {
+		error = -EPERM;
+		if (atomic_read(&tracers) > 0)
+			goto out;
 		atomic_dec(&tracers);
+	}
+
+	error = 0;
+out:
+	spin_unlock_irq(&ds_lock);
+	return error;
 }
 
 static inline void put_tracer(struct task_struct *task)
@@ -194,14 +234,6 @@ static inline void put_tracer(struct task_struct *task)
 		atomic_inc(&tracers);
 }
 
-static inline int check_tracer(struct task_struct *task)
-{
-	return task ?
-		(atomic_read(&tracers) >= 0) :
-		(atomic_read(&tracers) <= 0);
-}
-
-
 /*
  * The DS context is either attached to a thread or to a cpu:
  * - in the former case, the thread_struct contains a pointer to the
@@ -213,61 +245,58 @@ static inline int check_tracer(struct task_struct *task)
  * deallocated when the last user puts the context.
  */
 struct ds_context {
-	/* pointer to the DS configuration; goes into MSR_IA32_DS_AREA */
-	unsigned char ds[MAX_SIZEOF_DS];
-	/* the owner of the BTS and PEBS configuration, respectively */
-	struct bts_tracer *bts_master;
-	struct pebs_tracer *pebs_master;
-	/* use count */
-	unsigned long count;
-	/* a pointer to the context location inside the thread_struct
-	 * or the per_cpu context array */
-	struct ds_context **this;
-	/* a pointer to the task owning this context, or NULL, if the
-	 * context is owned by a cpu */
-	struct task_struct *task;
+	/* The DS configuration; goes into MSR_IA32_DS_AREA: */
+	unsigned char		ds[MAX_SIZEOF_DS];
+
+	/* The owner of the BTS and PEBS configuration, respectively: */
+	struct bts_tracer	*bts_master;
+	struct pebs_tracer	*pebs_master;
+
+	/* Use count: */
+	unsigned long		count;
+
+	/* Pointer to the context pointer field: */
+	struct ds_context	**this;
+
+	/* The traced task; NULL for cpu tracing: */
+	struct task_struct	*task;
+
+	/* The traced cpu; only valid if task is NULL: */
+	int			cpu;
 };
 
-static DEFINE_PER_CPU(struct ds_context *, system_context_array);
-
-#define system_context per_cpu(system_context_array, smp_processor_id())
+static DEFINE_PER_CPU(struct ds_context *, cpu_context);
 
 
-static inline struct ds_context *ds_get_context(struct task_struct *task)
+static struct ds_context *ds_get_context(struct task_struct *task, int cpu)
 {
 	struct ds_context **p_context =
-		(task ? &task->thread.ds_ctx : &system_context);
+		(task ? &task->thread.ds_ctx : &per_cpu(cpu_context, cpu));
 	struct ds_context *context = NULL;
 	struct ds_context *new_context = NULL;
-	unsigned long irq;
 
 	/* Chances are small that we already have a context. */
 	new_context = kzalloc(sizeof(*new_context), GFP_KERNEL);
 	if (!new_context)
 		return NULL;
 
-	spin_lock_irqsave(&ds_lock, irq);
+	spin_lock_irq(&ds_lock);
 
 	context = *p_context;
-	if (!context) {
+	if (likely(!context)) {
 		context = new_context;
 
 		context->this = p_context;
 		context->task = task;
+		context->cpu = cpu;
 		context->count = 0;
 
-		if (task)
-			set_tsk_thread_flag(task, TIF_DS_AREA_MSR);
-
-		if (!task || (task == current))
-			wrmsrl(MSR_IA32_DS_AREA, (unsigned long)context->ds);
-
 		*p_context = context;
 	}
 
 	context->count++;
 
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 
 	if (context != new_context)
 		kfree(new_context);
@@ -275,8 +304,9 @@ static inline struct ds_context *ds_get_context(struct task_struct *task)
 	return context;
 }
 
-static inline void ds_put_context(struct ds_context *context)
+static void ds_put_context(struct ds_context *context)
 {
+	struct task_struct *task;
 	unsigned long irq;
 
 	if (!context)
@@ -291,17 +321,55 @@ static inline void ds_put_context(struct ds_context *context)
 
 	*(context->this) = NULL;
 
-	if (context->task)
-		clear_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
+	task = context->task;
 
-	if (!context->task || (context->task == current))
-		wrmsrl(MSR_IA32_DS_AREA, 0);
+	if (task)
+		clear_tsk_thread_flag(task, TIF_DS_AREA_MSR);
+
+	/*
+	 * We leave the (now dangling) pointer to the DS configuration in
+	 * the DS_AREA msr. This is as good or as bad as replacing it with
+	 * NULL - the hardware would crash if we enabled tracing.
+	 *
+	 * This saves us some problems with having to write an msr on a
+	 * different cpu while preventing others from doing the same for the
+	 * next context for that same cpu.
+	 */
 
 	spin_unlock_irqrestore(&ds_lock, irq);
 
+	/* The context might still be in use for context switching. */
+	if (task && (task != current))
+		wait_task_context_switch(task);
+
 	kfree(context);
 }
 
+static void ds_install_ds_area(struct ds_context *context)
+{
+	unsigned long ds;
+
+	ds = (unsigned long)context->ds;
+
+	/*
+	 * There is a race between the bts master and the pebs master.
+	 *
+	 * The thread/cpu access is synchronized via get/put_cpu() for
+	 * task tracing and via wrmsr_on_cpu for cpu tracing.
+	 *
+	 * If bts and pebs are collected for the same task or same cpu,
+	 * the same confiuration is written twice.
+	 */
+	if (context->task) {
+		get_cpu();
+		if (context->task == current)
+			wrmsrl(MSR_IA32_DS_AREA, ds);
+		set_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
+		put_cpu();
+	} else
+		wrmsr_on_cpu(context->cpu, MSR_IA32_DS_AREA,
+			     (u32)((u64)ds), (u32)((u64)ds >> 32));
+}
 
 /*
  * Call the tracer's callback on a buffer overflow.
@@ -332,9 +400,9 @@ static void ds_overflow(struct ds_context *context, enum ds_qualifier qual)
  * The remainder of any partially written record is zeroed out.
  *
  * context: the DS context
- * qual: the buffer type
- * record: the data to write
- * size: the size of the data
+ * qual:    the buffer type
+ * record:  the data to write
+ * size:    the size of the data
  */
 static int ds_write(struct ds_context *context, enum ds_qualifier qual,
 		    const void *record, size_t size)
@@ -349,14 +417,14 @@ static int ds_write(struct ds_context *context, enum ds_qualifier qual,
 		unsigned long write_size, adj_write_size;
 
 		/*
-		 * write as much as possible without producing an
+		 * Write as much as possible without producing an
 		 * overflow interrupt.
 		 *
-		 * interrupt_threshold must either be
+		 * Interrupt_threshold must either be
 		 * - bigger than absolute_maximum or
 		 * - point to a record between buffer_base and absolute_maximum
 		 *
-		 * index points to a valid record.
+		 * Index points to a valid record.
 		 */
 		base   = ds_get(context->ds, qual, ds_buffer_base);
 		index  = ds_get(context->ds, qual, ds_index);
@@ -365,8 +433,10 @@ static int ds_write(struct ds_context *context, enum ds_qualifier qual,
 
 		write_end = min(end, int_th);
 
-		/* if we are already beyond the interrupt threshold,
-		 * we fill the entire buffer */
+		/*
+		 * If we are already beyond the interrupt threshold,
+		 * we fill the entire buffer.
+		 */
 		if (write_end <= index)
 			write_end = end;
 
@@ -383,7 +453,7 @@ static int ds_write(struct ds_context *context, enum ds_qualifier qual,
 		adj_write_size = write_size / ds_cfg.sizeof_rec[qual];
 		adj_write_size *= ds_cfg.sizeof_rec[qual];
 
-		/* zero out trailing bytes */
+		/* Zero out trailing bytes. */
 		memset((char *)index + write_size, 0,
 		       adj_write_size - write_size);
 		index += adj_write_size;
@@ -410,7 +480,7 @@ static int ds_write(struct ds_context *context, enum ds_qualifier qual,
  * Later architectures use 64bit pointers throughout, whereas earlier
  * architectures use 32bit pointers in 32bit mode.
  *
- * We compute the base address for the first 8 fields based on:
+ * We compute the base address for the fields based on:
  * - the field size stored in the DS configuration
  * - the relative field position
  *
@@ -431,23 +501,23 @@ enum bts_field {
 	bts_to,
 	bts_flags,
 
-	bts_qual = bts_from,
-	bts_jiffies = bts_to,
-	bts_pid = bts_flags,
+	bts_qual		= bts_from,
+	bts_clock		= bts_to,
+	bts_pid			= bts_flags,
 
-	bts_qual_mask = (bts_qual_max - 1),
-	bts_escape = ((unsigned long)-1 & ~bts_qual_mask)
+	bts_qual_mask		= (bts_qual_max - 1),
+	bts_escape		= ((unsigned long)-1 & ~bts_qual_mask)
 };
 
 static inline unsigned long bts_get(const char *base, enum bts_field field)
 {
-	base += (ds_cfg.sizeof_field * field);
+	base += (ds_cfg.sizeof_ptr_field * field);
 	return *(unsigned long *)base;
 }
 
 static inline void bts_set(char *base, enum bts_field field, unsigned long val)
 {
-	base += (ds_cfg.sizeof_field * field);;
+	base += (ds_cfg.sizeof_ptr_field * field);;
 	(*(unsigned long *)base) = val;
 }
 
@@ -463,8 +533,8 @@ static inline void bts_set(char *base, enum bts_field field, unsigned long val)
  *
  * return: bytes read/written on success; -Eerrno, otherwise
  */
-static int bts_read(struct bts_tracer *tracer, const void *at,
-		    struct bts_struct *out)
+static int
+bts_read(struct bts_tracer *tracer, const void *at, struct bts_struct *out)
 {
 	if (!tracer)
 		return -EINVAL;
@@ -478,8 +548,8 @@ static int bts_read(struct bts_tracer *tracer, const void *at,
 	memset(out, 0, sizeof(*out));
 	if ((bts_get(at, bts_qual) & ~bts_qual_mask) == bts_escape) {
 		out->qualifier = (bts_get(at, bts_qual) & bts_qual_mask);
-		out->variant.timestamp.jiffies = bts_get(at, bts_jiffies);
-		out->variant.timestamp.pid = bts_get(at, bts_pid);
+		out->variant.event.clock = bts_get(at, bts_clock);
+		out->variant.event.pid = bts_get(at, bts_pid);
 	} else {
 		out->qualifier = bts_branch;
 		out->variant.lbr.from = bts_get(at, bts_from);
@@ -516,8 +586,8 @@ static int bts_write(struct bts_tracer *tracer, const struct bts_struct *in)
 	case bts_task_arrives:
 	case bts_task_departs:
 		bts_set(raw, bts_qual, (bts_escape | in->qualifier));
-		bts_set(raw, bts_jiffies, in->variant.timestamp.jiffies);
-		bts_set(raw, bts_pid, in->variant.timestamp.pid);
+		bts_set(raw, bts_clock, in->variant.event.clock);
+		bts_set(raw, bts_pid, in->variant.event.pid);
 		break;
 	default:
 		return -EINVAL;
@@ -555,7 +625,8 @@ static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual,
 			     unsigned int flags) {
 	unsigned long buffer, adj;
 
-	/* adjust the buffer address and size to meet alignment
+	/*
+	 * Adjust the buffer address and size to meet alignment
 	 * constraints:
 	 * - buffer is double-word aligned
 	 * - size is multiple of record size
@@ -577,9 +648,11 @@ static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual,
 	trace->begin = (void *)buffer;
 	trace->top = trace->begin;
 	trace->end = (void *)(buffer + size);
-	/* The value for 'no threshold' is -1, which will set the
+	/*
+	 * The value for 'no threshold' is -1, which will set the
 	 * threshold outside of the buffer, just like we want it.
 	 */
+	ith *= ds_cfg.sizeof_rec[qual];
 	trace->ith = (void *)(buffer + size - ith);
 
 	trace->flags = flags;
@@ -588,18 +661,27 @@ static void ds_init_ds_trace(struct ds_trace *trace, enum ds_qualifier qual,
 
 static int ds_request(struct ds_tracer *tracer, struct ds_trace *trace,
 		      enum ds_qualifier qual, struct task_struct *task,
-		      void *base, size_t size, size_t th, unsigned int flags)
+		      int cpu, void *base, size_t size, size_t th)
 {
 	struct ds_context *context;
 	int error;
+	size_t req_size;
+
+	error = -EOPNOTSUPP;
+	if (!ds_cfg.sizeof_rec[qual])
+		goto out;
 
 	error = -EINVAL;
 	if (!base)
 		goto out;
 
-	/* we require some space to do alignment adjustments below */
+	req_size = ds_cfg.sizeof_rec[qual];
+	/* We might need space for alignment adjustments. */
+	if (!IS_ALIGNED((unsigned long)base, DS_ALIGNMENT))
+		req_size += DS_ALIGNMENT;
+
 	error = -EINVAL;
-	if (size < (DS_ALIGNMENT + ds_cfg.sizeof_rec[qual]))
+	if (size < req_size)
 		goto out;
 
 	if (th != (size_t)-1) {
@@ -614,182 +696,318 @@ static int ds_request(struct ds_tracer *tracer, struct ds_trace *trace,
 	tracer->size = size;
 
 	error = -ENOMEM;
-	context = ds_get_context(task);
+	context = ds_get_context(task, cpu);
 	if (!context)
 		goto out;
 	tracer->context = context;
 
-	ds_init_ds_trace(trace, qual, base, size, th, flags);
+	/*
+	 * Defer any tracer-specific initialization work for the context until
+	 * context ownership has been clarified.
+	 */
 
 	error = 0;
  out:
 	return error;
 }
 
-struct bts_tracer *ds_request_bts(struct task_struct *task,
-				  void *base, size_t size,
-				  bts_ovfl_callback_t ovfl, size_t th,
-				  unsigned int flags)
+static struct bts_tracer *ds_request_bts(struct task_struct *task, int cpu,
+					 void *base, size_t size,
+					 bts_ovfl_callback_t ovfl, size_t th,
+					 unsigned int flags)
 {
 	struct bts_tracer *tracer;
-	unsigned long irq;
 	int error;
 
-	error = -EOPNOTSUPP;
-	if (!ds_cfg.ctl[dsf_bts])
-		goto out;
-
-	/* buffer overflow notification is not yet implemented */
+	/* Buffer overflow notification is not yet implemented. */
 	error = -EOPNOTSUPP;
 	if (ovfl)
 		goto out;
 
+	error = get_tracer(task);
+	if (error < 0)
+		goto out;
+
 	error = -ENOMEM;
 	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
 	if (!tracer)
-		goto out;
+		goto out_put_tracer;
 	tracer->ovfl = ovfl;
 
+	/* Do some more error checking and acquire a tracing context. */
 	error = ds_request(&tracer->ds, &tracer->trace.ds,
-			   ds_bts, task, base, size, th, flags);
+			   ds_bts, task, cpu, base, size, th);
 	if (error < 0)
 		goto out_tracer;
 
-
-	spin_lock_irqsave(&ds_lock, irq);
-
-	error = -EPERM;
-	if (!check_tracer(task))
-		goto out_unlock;
-	get_tracer(task);
+	/* Claim the bts part of the tracing context we acquired above. */
+	spin_lock_irq(&ds_lock);
 
 	error = -EPERM;
 	if (tracer->ds.context->bts_master)
-		goto out_put_tracer;
+		goto out_unlock;
 	tracer->ds.context->bts_master = tracer;
 
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 
+	/*
+	 * Now that we own the bts part of the context, let's complete the
+	 * initialization for that part.
+	 */
+	ds_init_ds_trace(&tracer->trace.ds, ds_bts, base, size, th, flags);
+	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+	ds_install_ds_area(tracer->ds.context);
 
 	tracer->trace.read  = bts_read;
 	tracer->trace.write = bts_write;
 
-	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+	/* Start tracing. */
 	ds_resume_bts(tracer);
 
 	return tracer;
 
- out_put_tracer:
-	put_tracer(task);
  out_unlock:
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 	ds_put_context(tracer->ds.context);
  out_tracer:
 	kfree(tracer);
+ out_put_tracer:
+	put_tracer(task);
  out:
 	return ERR_PTR(error);
 }
 
-struct pebs_tracer *ds_request_pebs(struct task_struct *task,
-				    void *base, size_t size,
-				    pebs_ovfl_callback_t ovfl, size_t th,
-				    unsigned int flags)
+struct bts_tracer *ds_request_bts_task(struct task_struct *task,
+				       void *base, size_t size,
+				       bts_ovfl_callback_t ovfl,
+				       size_t th, unsigned int flags)
+{
+	return ds_request_bts(task, 0, base, size, ovfl, th, flags);
+}
+
+struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
+				      bts_ovfl_callback_t ovfl,
+				      size_t th, unsigned int flags)
+{
+	return ds_request_bts(NULL, cpu, base, size, ovfl, th, flags);
+}
+
+static struct pebs_tracer *ds_request_pebs(struct task_struct *task, int cpu,
+					   void *base, size_t size,
+					   pebs_ovfl_callback_t ovfl, size_t th,
+					   unsigned int flags)
 {
 	struct pebs_tracer *tracer;
-	unsigned long irq;
 	int error;
 
-	/* buffer overflow notification is not yet implemented */
+	/* Buffer overflow notification is not yet implemented. */
 	error = -EOPNOTSUPP;
 	if (ovfl)
 		goto out;
 
+	error = get_tracer(task);
+	if (error < 0)
+		goto out;
+
 	error = -ENOMEM;
 	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
 	if (!tracer)
-		goto out;
+		goto out_put_tracer;
 	tracer->ovfl = ovfl;
 
+	/* Do some more error checking and acquire a tracing context. */
 	error = ds_request(&tracer->ds, &tracer->trace.ds,
-			   ds_pebs, task, base, size, th, flags);
+			   ds_pebs, task, cpu, base, size, th);
 	if (error < 0)
 		goto out_tracer;
 
-	spin_lock_irqsave(&ds_lock, irq);
-
-	error = -EPERM;
-	if (!check_tracer(task))
-		goto out_unlock;
-	get_tracer(task);
+	/* Claim the pebs part of the tracing context we acquired above. */
+	spin_lock_irq(&ds_lock);
 
 	error = -EPERM;
 	if (tracer->ds.context->pebs_master)
-		goto out_put_tracer;
+		goto out_unlock;
 	tracer->ds.context->pebs_master = tracer;
 
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 
+	/*
+	 * Now that we own the pebs part of the context, let's complete the
+	 * initialization for that part.
+	 */
+	ds_init_ds_trace(&tracer->trace.ds, ds_pebs, base, size, th, flags);
 	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
+	ds_install_ds_area(tracer->ds.context);
+
+	/* Start tracing. */
 	ds_resume_pebs(tracer);
 
 	return tracer;
 
- out_put_tracer:
-	put_tracer(task);
  out_unlock:
-	spin_unlock_irqrestore(&ds_lock, irq);
+	spin_unlock_irq(&ds_lock);
 	ds_put_context(tracer->ds.context);
  out_tracer:
 	kfree(tracer);
+ out_put_tracer:
+	put_tracer(task);
  out:
 	return ERR_PTR(error);
 }
 
-void ds_release_bts(struct bts_tracer *tracer)
+struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
+					 void *base, size_t size,
+					 pebs_ovfl_callback_t ovfl,
+					 size_t th, unsigned int flags)
 {
-	if (!tracer)
-		return;
+	return ds_request_pebs(task, 0, base, size, ovfl, th, flags);
+}
 
-	ds_suspend_bts(tracer);
+struct pebs_tracer *ds_request_pebs_cpu(int cpu, void *base, size_t size,
+					pebs_ovfl_callback_t ovfl,
+					size_t th, unsigned int flags)
+{
+	return ds_request_pebs(NULL, cpu, base, size, ovfl, th, flags);
+}
+
+static void ds_free_bts(struct bts_tracer *tracer)
+{
+	struct task_struct *task;
+
+	task = tracer->ds.context->task;
 
 	WARN_ON_ONCE(tracer->ds.context->bts_master != tracer);
 	tracer->ds.context->bts_master = NULL;
 
-	put_tracer(tracer->ds.context->task);
+	/* Make sure tracing stopped and the tracer is not in use. */
+	if (task && (task != current))
+		wait_task_context_switch(task);
+
 	ds_put_context(tracer->ds.context);
+	put_tracer(task);
 
 	kfree(tracer);
 }
 
+void ds_release_bts(struct bts_tracer *tracer)
+{
+	might_sleep();
+
+	if (!tracer)
+		return;
+
+	ds_suspend_bts(tracer);
+	ds_free_bts(tracer);
+}
+
+int ds_release_bts_noirq(struct bts_tracer *tracer)
+{
+	struct task_struct *task;
+	unsigned long irq;
+	int error;
+
+	if (!tracer)
+		return 0;
+
+	task = tracer->ds.context->task;
+
+	local_irq_save(irq);
+
+	error = -EPERM;
+	if (!task &&
+	    (tracer->ds.context->cpu != smp_processor_id()))
+		goto out;
+
+	error = -EPERM;
+	if (task && (task != current))
+		goto out;
+
+	ds_suspend_bts_noirq(tracer);
+	ds_free_bts(tracer);
+
+	error = 0;
+ out:
+	local_irq_restore(irq);
+	return error;
+}
+
+static void update_task_debugctlmsr(struct task_struct *task,
+				    unsigned long debugctlmsr)
+{
+	task->thread.debugctlmsr = debugctlmsr;
+
+	get_cpu();
+	if (task == current)
+		update_debugctlmsr(debugctlmsr);
+	put_cpu();
+}
+
 void ds_suspend_bts(struct bts_tracer *tracer)
 {
 	struct task_struct *task;
+	unsigned long debugctlmsr;
+	int cpu;
 
 	if (!tracer)
 		return;
 
+	tracer->flags = 0;
+
 	task = tracer->ds.context->task;
+	cpu  = tracer->ds.context->cpu;
 
-	if (!task || (task == current))
-		update_debugctlmsr(get_debugctlmsr() & ~BTS_CONTROL);
+	WARN_ON(!task && irqs_disabled());
 
-	if (task) {
-		task->thread.debugctlmsr &= ~BTS_CONTROL;
+	debugctlmsr = (task ?
+		       task->thread.debugctlmsr :
+		       get_debugctlmsr_on_cpu(cpu));
+	debugctlmsr &= ~BTS_CONTROL;
 
-		if (!task->thread.debugctlmsr)
-			clear_tsk_thread_flag(task, TIF_DEBUGCTLMSR);
-	}
+	if (task)
+		update_task_debugctlmsr(task, debugctlmsr);
+	else
+		update_debugctlmsr_on_cpu(cpu, debugctlmsr);
 }
 
-void ds_resume_bts(struct bts_tracer *tracer)
+int ds_suspend_bts_noirq(struct bts_tracer *tracer)
 {
 	struct task_struct *task;
-	unsigned long control;
+	unsigned long debugctlmsr, irq;
+	int cpu, error = 0;
 
 	if (!tracer)
-		return;
+		return 0;
+
+	tracer->flags = 0;
 
 	task = tracer->ds.context->task;
+	cpu  = tracer->ds.context->cpu;
+
+	local_irq_save(irq);
+
+	error = -EPERM;
+	if (!task && (cpu != smp_processor_id()))
+		goto out;
+
+	debugctlmsr = (task ?
+		       task->thread.debugctlmsr :
+		       get_debugctlmsr());
+	debugctlmsr &= ~BTS_CONTROL;
+
+	if (task)
+		update_task_debugctlmsr(task, debugctlmsr);
+	else
+		update_debugctlmsr(debugctlmsr);
+
+	error = 0;
+ out:
+	local_irq_restore(irq);
+	return error;
+}
+
+static unsigned long ds_bts_control(struct bts_tracer *tracer)
+{
+	unsigned long control;
 
 	control = ds_cfg.ctl[dsf_bts];
 	if (!(tracer->trace.ds.flags & BTS_KERNEL))
@@ -797,41 +1015,149 @@ void ds_resume_bts(struct bts_tracer *tracer)
 	if (!(tracer->trace.ds.flags & BTS_USER))
 		control |= ds_cfg.ctl[dsf_bts_user];
 
-	if (task) {
-		task->thread.debugctlmsr |= control;
-		set_tsk_thread_flag(task, TIF_DEBUGCTLMSR);
-	}
-
-	if (!task || (task == current))
-		update_debugctlmsr(get_debugctlmsr() | control);
+	return control;
 }
 
-void ds_release_pebs(struct pebs_tracer *tracer)
+void ds_resume_bts(struct bts_tracer *tracer)
 {
+	struct task_struct *task;
+	unsigned long debugctlmsr;
+	int cpu;
+
 	if (!tracer)
 		return;
 
-	ds_suspend_pebs(tracer);
+	tracer->flags = tracer->trace.ds.flags;
+
+	task = tracer->ds.context->task;
+	cpu  = tracer->ds.context->cpu;
+
+	WARN_ON(!task && irqs_disabled());
+
+	debugctlmsr = (task ?
+		       task->thread.debugctlmsr :
+		       get_debugctlmsr_on_cpu(cpu));
+	debugctlmsr |= ds_bts_control(tracer);
+
+	if (task)
+		update_task_debugctlmsr(task, debugctlmsr);
+	else
+		update_debugctlmsr_on_cpu(cpu, debugctlmsr);
+}
+
+int ds_resume_bts_noirq(struct bts_tracer *tracer)
+{
+	struct task_struct *task;
+	unsigned long debugctlmsr, irq;
+	int cpu, error = 0;
+
+	if (!tracer)
+		return 0;
+
+	tracer->flags = tracer->trace.ds.flags;
+
+	task = tracer->ds.context->task;
+	cpu  = tracer->ds.context->cpu;
+
+	local_irq_save(irq);
+
+	error = -EPERM;
+	if (!task && (cpu != smp_processor_id()))
+		goto out;
+
+	debugctlmsr = (task ?
+		       task->thread.debugctlmsr :
+		       get_debugctlmsr());
+	debugctlmsr |= ds_bts_control(tracer);
+
+	if (task)
+		update_task_debugctlmsr(task, debugctlmsr);
+	else
+		update_debugctlmsr(debugctlmsr);
+
+	error = 0;
+ out:
+	local_irq_restore(irq);
+	return error;
+}
+
+static void ds_free_pebs(struct pebs_tracer *tracer)
+{
+	struct task_struct *task;
+
+	task = tracer->ds.context->task;
 
 	WARN_ON_ONCE(tracer->ds.context->pebs_master != tracer);
 	tracer->ds.context->pebs_master = NULL;
 
-	put_tracer(tracer->ds.context->task);
 	ds_put_context(tracer->ds.context);
+	put_tracer(task);
 
 	kfree(tracer);
 }
 
+void ds_release_pebs(struct pebs_tracer *tracer)
+{
+	might_sleep();
+
+	if (!tracer)
+		return;
+
+	ds_suspend_pebs(tracer);
+	ds_free_pebs(tracer);
+}
+
+int ds_release_pebs_noirq(struct pebs_tracer *tracer)
+{
+	struct task_struct *task;
+	unsigned long irq;
+	int error;
+
+	if (!tracer)
+		return 0;
+
+	task = tracer->ds.context->task;
+
+	local_irq_save(irq);
+
+	error = -EPERM;
+	if (!task &&
+	    (tracer->ds.context->cpu != smp_processor_id()))
+		goto out;
+
+	error = -EPERM;
+	if (task && (task != current))
+		goto out;
+
+	ds_suspend_pebs_noirq(tracer);
+	ds_free_pebs(tracer);
+
+	error = 0;
+ out:
+	local_irq_restore(irq);
+	return error;
+}
+
 void ds_suspend_pebs(struct pebs_tracer *tracer)
 {
 
 }
 
+int ds_suspend_pebs_noirq(struct pebs_tracer *tracer)
+{
+	return 0;
+}
+
 void ds_resume_pebs(struct pebs_tracer *tracer)
 {
 
 }
 
+int ds_resume_pebs_noirq(struct pebs_tracer *tracer)
+{
+	return 0;
+}
+
 const struct bts_trace *ds_read_bts(struct bts_tracer *tracer)
 {
 	if (!tracer)
@@ -847,8 +1173,12 @@ const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer)
 		return NULL;
 
 	ds_read_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
-	tracer->trace.reset_value =
-		*(u64 *)(tracer->ds.context->ds + (ds_cfg.sizeof_field * 8));
+
+	tracer->trace.counters = ds_cfg.nr_counter_reset;
+	memcpy(tracer->trace.counter_reset,
+	       tracer->ds.context->ds +
+	       (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field),
+	       ds_cfg.nr_counter_reset * PEBS_RESET_FIELD_SIZE);
 
 	return &tracer->trace;
 }
@@ -873,18 +1203,24 @@ int ds_reset_pebs(struct pebs_tracer *tracer)
 
 	tracer->trace.ds.top = tracer->trace.ds.begin;
 
-	ds_set(tracer->ds.context->ds, ds_bts, ds_index,
+	ds_set(tracer->ds.context->ds, ds_pebs, ds_index,
 	       (unsigned long)tracer->trace.ds.top);
 
 	return 0;
 }
 
-int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value)
+int ds_set_pebs_reset(struct pebs_tracer *tracer,
+		      unsigned int counter, u64 value)
 {
 	if (!tracer)
 		return -EINVAL;
 
-	*(u64 *)(tracer->ds.context->ds + (ds_cfg.sizeof_field * 8)) = value;
+	if (ds_cfg.nr_counter_reset < counter)
+		return -EINVAL;
+
+	*(u64 *)(tracer->ds.context->ds +
+		 (NUM_DS_PTR_FIELDS * ds_cfg.sizeof_ptr_field) +
+		 (counter * PEBS_RESET_FIELD_SIZE)) = value;
 
 	return 0;
 }
@@ -894,73 +1230,117 @@ static const struct ds_configuration ds_cfg_netburst = {
 	.ctl[dsf_bts]		= (1 << 2) | (1 << 3),
 	.ctl[dsf_bts_kernel]	= (1 << 5),
 	.ctl[dsf_bts_user]	= (1 << 6),
-
-	.sizeof_field		= sizeof(long),
-	.sizeof_rec[ds_bts]	= sizeof(long) * 3,
-#ifdef __i386__
-	.sizeof_rec[ds_pebs]	= sizeof(long) * 10,
-#else
-	.sizeof_rec[ds_pebs]	= sizeof(long) * 18,
-#endif
+	.nr_counter_reset	= 1,
 };
 static const struct ds_configuration ds_cfg_pentium_m = {
 	.name = "Pentium M",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
-
-	.sizeof_field		= sizeof(long),
-	.sizeof_rec[ds_bts]	= sizeof(long) * 3,
-#ifdef __i386__
-	.sizeof_rec[ds_pebs]	= sizeof(long) * 10,
-#else
-	.sizeof_rec[ds_pebs]	= sizeof(long) * 18,
-#endif
+	.nr_counter_reset	= 1,
 };
 static const struct ds_configuration ds_cfg_core2_atom = {
 	.name = "Core 2/Atom",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
 	.ctl[dsf_bts_kernel]	= (1 << 9),
 	.ctl[dsf_bts_user]	= (1 << 10),
-
-	.sizeof_field		= 8,
-	.sizeof_rec[ds_bts]	= 8 * 3,
-	.sizeof_rec[ds_pebs]	= 8 * 18,
+	.nr_counter_reset	= 1,
+};
+static const struct ds_configuration ds_cfg_core_i7 = {
+	.name = "Core i7",
+	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
+	.ctl[dsf_bts_kernel]	= (1 << 9),
+	.ctl[dsf_bts_user]	= (1 << 10),
+	.nr_counter_reset	= 4,
 };
 
 static void
-ds_configure(const struct ds_configuration *cfg)
+ds_configure(const struct ds_configuration *cfg,
+	     struct cpuinfo_x86 *cpu)
 {
+	unsigned long nr_pebs_fields = 0;
+
+	printk(KERN_INFO "[ds] using %s configuration\n", cfg->name);
+
+#ifdef __i386__
+	nr_pebs_fields = 10;
+#else
+	nr_pebs_fields = 18;
+#endif
+
+	/*
+	 * Starting with version 2, architectural performance
+	 * monitoring supports a format specifier.
+	 */
+	if ((cpuid_eax(0xa) & 0xff) > 1) {
+		unsigned long perf_capabilities, format;
+
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_capabilities);
+
+		format = (perf_capabilities >> 8) & 0xf;
+
+		switch (format) {
+		case 0:
+			nr_pebs_fields = 18;
+			break;
+		case 1:
+			nr_pebs_fields = 22;
+			break;
+		default:
+			printk(KERN_INFO
+			       "[ds] unknown PEBS format: %lu\n", format);
+			nr_pebs_fields = 0;
+			break;
+		}
+	}
+
 	memset(&ds_cfg, 0, sizeof(ds_cfg));
 	ds_cfg = *cfg;
 
-	printk(KERN_INFO "[ds] using %s configuration\n", ds_cfg.name);
+	ds_cfg.sizeof_ptr_field =
+		(cpu_has(cpu, X86_FEATURE_DTES64) ? 8 : 4);
 
-	if (!cpu_has_bts) {
-		ds_cfg.ctl[dsf_bts] = 0;
+	ds_cfg.sizeof_rec[ds_bts]  = ds_cfg.sizeof_ptr_field * 3;
+	ds_cfg.sizeof_rec[ds_pebs] = ds_cfg.sizeof_ptr_field * nr_pebs_fields;
+
+	if (!cpu_has(cpu, X86_FEATURE_BTS)) {
+		ds_cfg.sizeof_rec[ds_bts] = 0;
 		printk(KERN_INFO "[ds] bts not available\n");
 	}
-	if (!cpu_has_pebs)
+	if (!cpu_has(cpu, X86_FEATURE_PEBS)) {
+		ds_cfg.sizeof_rec[ds_pebs] = 0;
 		printk(KERN_INFO "[ds] pebs not available\n");
+	}
 
-	WARN_ON_ONCE(MAX_SIZEOF_DS < (12 * ds_cfg.sizeof_field));
+	printk(KERN_INFO "[ds] sizes: address: %u bit, ",
+	       8 * ds_cfg.sizeof_ptr_field);
+	printk("bts/pebs record: %u/%u bytes\n",
+	       ds_cfg.sizeof_rec[ds_bts], ds_cfg.sizeof_rec[ds_pebs]);
+
+	WARN_ON_ONCE(MAX_PEBS_COUNTERS < ds_cfg.nr_counter_reset);
 }
 
 void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
 {
+	/* Only configure the first cpu. Others are identical. */
+	if (ds_cfg.name)
+		return;
+
 	switch (c->x86) {
 	case 0x6:
 		switch (c->x86_model) {
 		case 0x9:
 		case 0xd: /* Pentium M */
-			ds_configure(&ds_cfg_pentium_m);
+			ds_configure(&ds_cfg_pentium_m, c);
 			break;
 		case 0xf:
 		case 0x17: /* Core2 */
 		case 0x1c: /* Atom */
-			ds_configure(&ds_cfg_core2_atom);
+			ds_configure(&ds_cfg_core2_atom, c);
+			break;
+		case 0x1a: /* Core i7 */
+			ds_configure(&ds_cfg_core_i7, c);
 			break;
-		case 0x1a: /* i7 */
 		default:
-			/* sorry, don't know about them */
+			/* Sorry, don't know about them. */
 			break;
 		}
 		break;
@@ -969,64 +1349,89 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
 		case 0x0:
 		case 0x1:
 		case 0x2: /* Netburst */
-			ds_configure(&ds_cfg_netburst);
+			ds_configure(&ds_cfg_netburst, c);
 			break;
 		default:
-			/* sorry, don't know about them */
+			/* Sorry, don't know about them. */
 			break;
 		}
 		break;
 	default:
-		/* sorry, don't know about them */
+		/* Sorry, don't know about them. */
 		break;
 	}
 }
 
+static inline void ds_take_timestamp(struct ds_context *context,
+				     enum bts_qualifier qualifier,
+				     struct task_struct *task)
+{
+	struct bts_tracer *tracer = context->bts_master;
+	struct bts_struct ts;
+
+	/* Prevent compilers from reading the tracer pointer twice. */
+	barrier();
+
+	if (!tracer || !(tracer->flags & BTS_TIMESTAMPS))
+		return;
+
+	memset(&ts, 0, sizeof(ts));
+	ts.qualifier		= qualifier;
+	ts.variant.event.clock	= trace_clock_global();
+	ts.variant.event.pid	= task->pid;
+
+	bts_write(tracer, &ts);
+}
+
 /*
  * Change the DS configuration from tracing prev to tracing next.
  */
 void ds_switch_to(struct task_struct *prev, struct task_struct *next)
 {
-	struct ds_context *prev_ctx = prev->thread.ds_ctx;
-	struct ds_context *next_ctx = next->thread.ds_ctx;
+	struct ds_context *prev_ctx	= prev->thread.ds_ctx;
+	struct ds_context *next_ctx	= next->thread.ds_ctx;
+	unsigned long debugctlmsr	= next->thread.debugctlmsr;
+
+	/* Make sure all data is read before we start. */
+	barrier();
 
 	if (prev_ctx) {
 		update_debugctlmsr(0);
 
-		if (prev_ctx->bts_master &&
-		    (prev_ctx->bts_master->trace.ds.flags & BTS_TIMESTAMPS)) {
-			struct bts_struct ts = {
-				.qualifier = bts_task_departs,
-				.variant.timestamp.jiffies = jiffies_64,
-				.variant.timestamp.pid = prev->pid
-			};
-			bts_write(prev_ctx->bts_master, &ts);
-		}
+		ds_take_timestamp(prev_ctx, bts_task_departs, prev);
 	}
 
 	if (next_ctx) {
-		if (next_ctx->bts_master &&
-		    (next_ctx->bts_master->trace.ds.flags & BTS_TIMESTAMPS)) {
-			struct bts_struct ts = {
-				.qualifier = bts_task_arrives,
-				.variant.timestamp.jiffies = jiffies_64,
-				.variant.timestamp.pid = next->pid
-			};
-			bts_write(next_ctx->bts_master, &ts);
-		}
+		ds_take_timestamp(next_ctx, bts_task_arrives, next);
 
 		wrmsrl(MSR_IA32_DS_AREA, (unsigned long)next_ctx->ds);
 	}
 
-	update_debugctlmsr(next->thread.debugctlmsr);
+	update_debugctlmsr(debugctlmsr);
 }
 
-void ds_copy_thread(struct task_struct *tsk, struct task_struct *father)
+static __init int ds_selftest(void)
 {
-	clear_tsk_thread_flag(tsk, TIF_DS_AREA_MSR);
-	tsk->thread.ds_ctx = NULL;
-}
+	if (ds_cfg.sizeof_rec[ds_bts]) {
+		int error;
 
-void ds_exit_thread(struct task_struct *tsk)
-{
+		error = ds_selftest_bts();
+		if (error) {
+			WARN(1, "[ds] selftest failed. disabling bts.\n");
+			ds_cfg.sizeof_rec[ds_bts] = 0;
+		}
+	}
+
+	if (ds_cfg.sizeof_rec[ds_pebs]) {
+		int error;
+
+		error = ds_selftest_pebs();
+		if (error) {
+			WARN(1, "[ds] selftest failed. disabling pebs.\n");
+			ds_cfg.sizeof_rec[ds_pebs] = 0;
+		}
+	}
+
+	return 0;
 }
+device_initcall(ds_selftest);
diff --git a/arch/x86/kernel/ds_selftest.c b/arch/x86/kernel/ds_selftest.c
new file mode 100644
index 000000000000..6bc7c199ab99
--- /dev/null
+++ b/arch/x86/kernel/ds_selftest.c
@@ -0,0 +1,408 @@
+/*
+ * Debug Store support - selftest
+ *
+ *
+ * Copyright (C) 2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2009
+ */
+
+#include "ds_selftest.h"
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/smp.h>
+#include <linux/cpu.h>
+
+#include <asm/ds.h>
+
+
+#define BUFFER_SIZE		521	/* Intentionally chose an odd size. */
+#define SMALL_BUFFER_SIZE	24	/* A single bts entry. */
+
+struct ds_selftest_bts_conf {
+	struct bts_tracer *tracer;
+	int error;
+	int (*suspend)(struct bts_tracer *);
+	int (*resume)(struct bts_tracer *);
+};
+
+static int ds_selftest_bts_consistency(const struct bts_trace *trace)
+{
+	int error = 0;
+
+	if (!trace) {
+		printk(KERN_CONT "failed to access trace...");
+		/* Bail out. Other tests are pointless. */
+		return -1;
+	}
+
+	if (!trace->read) {
+		printk(KERN_CONT "bts read not available...");
+		error = -1;
+	}
+
+	/* Do some sanity checks on the trace configuration. */
+	if (!trace->ds.n) {
+		printk(KERN_CONT "empty bts buffer...");
+		error = -1;
+	}
+	if (!trace->ds.size) {
+		printk(KERN_CONT "bad bts trace setup...");
+		error = -1;
+	}
+	if (trace->ds.end !=
+	    (char *)trace->ds.begin + (trace->ds.n * trace->ds.size)) {
+		printk(KERN_CONT "bad bts buffer setup...");
+		error = -1;
+	}
+	/*
+	 * We allow top in [begin; end], since its not clear when the
+	 * overflow adjustment happens: after the increment or before the
+	 * write.
+	 */
+	if ((trace->ds.top < trace->ds.begin) ||
+	    (trace->ds.end < trace->ds.top)) {
+		printk(KERN_CONT "bts top out of bounds...");
+		error = -1;
+	}
+
+	return error;
+}
+
+static int ds_selftest_bts_read(struct bts_tracer *tracer,
+				const struct bts_trace *trace,
+				const void *from, const void *to)
+{
+	const unsigned char *at;
+
+	/*
+	 * Check a few things which do not belong to this test.
+	 * They should be covered by other tests.
+	 */
+	if (!trace)
+		return -1;
+
+	if (!trace->read)
+		return -1;
+
+	if (to < from)
+		return -1;
+
+	if (from < trace->ds.begin)
+		return -1;
+
+	if (trace->ds.end < to)
+		return -1;
+
+	if (!trace->ds.size)
+		return -1;
+
+	/* Now to the test itself. */
+	for (at = from; (void *)at < to; at += trace->ds.size) {
+		struct bts_struct bts;
+		unsigned long index;
+		int error;
+
+		if (((void *)at - trace->ds.begin) % trace->ds.size) {
+			printk(KERN_CONT
+			       "read from non-integer index...");
+			return -1;
+		}
+		index = ((void *)at - trace->ds.begin) / trace->ds.size;
+
+		memset(&bts, 0, sizeof(bts));
+		error = trace->read(tracer, at, &bts);
+		if (error < 0) {
+			printk(KERN_CONT
+			       "error reading bts trace at [%lu] (0x%p)...",
+			       index, at);
+			return error;
+		}
+
+		switch (bts.qualifier) {
+		case BTS_BRANCH:
+			break;
+		default:
+			printk(KERN_CONT
+			       "unexpected bts entry %llu at [%lu] (0x%p)...",
+			       bts.qualifier, index, at);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static void ds_selftest_bts_cpu(void *arg)
+{
+	struct ds_selftest_bts_conf *conf = arg;
+	const struct bts_trace *trace;
+	void *top;
+
+	if (IS_ERR(conf->tracer)) {
+		conf->error = PTR_ERR(conf->tracer);
+		conf->tracer = NULL;
+
+		printk(KERN_CONT
+		       "initialization failed (err: %d)...", conf->error);
+		return;
+	}
+
+	/* We should meanwhile have enough trace. */
+	conf->error = conf->suspend(conf->tracer);
+	if (conf->error < 0)
+		return;
+
+	/* Let's see if we can access the trace. */
+	trace = ds_read_bts(conf->tracer);
+
+	conf->error = ds_selftest_bts_consistency(trace);
+	if (conf->error < 0)
+		return;
+
+	/* If everything went well, we should have a few trace entries. */
+	if (trace->ds.top == trace->ds.begin) {
+		/*
+		 * It is possible but highly unlikely that we got a
+		 * buffer overflow and end up at exactly the same
+		 * position we started from.
+		 * Let's issue a warning, but continue.
+		 */
+		printk(KERN_CONT "no trace/overflow...");
+	}
+
+	/* Let's try to read the trace we collected. */
+	conf->error =
+		ds_selftest_bts_read(conf->tracer, trace,
+				     trace->ds.begin, trace->ds.top);
+	if (conf->error < 0)
+		return;
+
+	/*
+	 * Let's read the trace again.
+	 * Since we suspended tracing, we should get the same result.
+	 */
+	top = trace->ds.top;
+
+	trace = ds_read_bts(conf->tracer);
+	conf->error = ds_selftest_bts_consistency(trace);
+	if (conf->error < 0)
+		return;
+
+	if (top != trace->ds.top) {
+		printk(KERN_CONT "suspend not working...");
+		conf->error = -1;
+		return;
+	}
+
+	/* Let's collect some more trace - see if resume is working. */
+	conf->error = conf->resume(conf->tracer);
+	if (conf->error < 0)
+		return;
+
+	conf->error = conf->suspend(conf->tracer);
+	if (conf->error < 0)
+		return;
+
+	trace = ds_read_bts(conf->tracer);
+
+	conf->error = ds_selftest_bts_consistency(trace);
+	if (conf->error < 0)
+		return;
+
+	if (trace->ds.top == top) {
+		/*
+		 * It is possible but highly unlikely that we got a
+		 * buffer overflow and end up at exactly the same
+		 * position we started from.
+		 * Let's issue a warning and check the full trace.
+		 */
+		printk(KERN_CONT
+		       "no resume progress/overflow...");
+
+		conf->error =
+			ds_selftest_bts_read(conf->tracer, trace,
+					     trace->ds.begin, trace->ds.end);
+	} else if (trace->ds.top < top) {
+		/*
+		 * We had a buffer overflow - the entire buffer should
+		 * contain trace records.
+		 */
+		conf->error =
+			ds_selftest_bts_read(conf->tracer, trace,
+					     trace->ds.begin, trace->ds.end);
+	} else {
+		/*
+		 * It is quite likely that the buffer did not overflow.
+		 * Let's just check the delta trace.
+		 */
+		conf->error =
+			ds_selftest_bts_read(conf->tracer, trace, top,
+					     trace->ds.top);
+	}
+	if (conf->error < 0)
+		return;
+
+	conf->error = 0;
+}
+
+static int ds_suspend_bts_wrap(struct bts_tracer *tracer)
+{
+	ds_suspend_bts(tracer);
+	return 0;
+}
+
+static int ds_resume_bts_wrap(struct bts_tracer *tracer)
+{
+	ds_resume_bts(tracer);
+	return 0;
+}
+
+static void ds_release_bts_noirq_wrap(void *tracer)
+{
+	(void)ds_release_bts_noirq(tracer);
+}
+
+static int ds_selftest_bts_bad_release_noirq(int cpu,
+					     struct bts_tracer *tracer)
+{
+	int error = -EPERM;
+
+	/* Try to release the tracer on the wrong cpu. */
+	get_cpu();
+	if (cpu != smp_processor_id()) {
+		error = ds_release_bts_noirq(tracer);
+		if (error != -EPERM)
+			printk(KERN_CONT "release on wrong cpu...");
+	}
+	put_cpu();
+
+	return error ? 0 : -1;
+}
+
+static int ds_selftest_bts_bad_request_cpu(int cpu, void *buffer)
+{
+	struct bts_tracer *tracer;
+	int error;
+
+	/* Try to request cpu tracing while task tracing is active. */
+	tracer = ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE, NULL,
+				    (size_t)-1, BTS_KERNEL);
+	error = PTR_ERR(tracer);
+	if (!IS_ERR(tracer)) {
+		ds_release_bts(tracer);
+		error = 0;
+	}
+
+	if (error != -EPERM)
+		printk(KERN_CONT "cpu/task tracing overlap...");
+
+	return error ? 0 : -1;
+}
+
+static int ds_selftest_bts_bad_request_task(void *buffer)
+{
+	struct bts_tracer *tracer;
+	int error;
+
+	/* Try to request cpu tracing while task tracing is active. */
+	tracer = ds_request_bts_task(current, buffer, BUFFER_SIZE, NULL,
+				    (size_t)-1, BTS_KERNEL);
+	error = PTR_ERR(tracer);
+	if (!IS_ERR(tracer)) {
+		error = 0;
+		ds_release_bts(tracer);
+	}
+
+	if (error != -EPERM)
+		printk(KERN_CONT "task/cpu tracing overlap...");
+
+	return error ? 0 : -1;
+}
+
+int ds_selftest_bts(void)
+{
+	struct ds_selftest_bts_conf conf;
+	unsigned char buffer[BUFFER_SIZE], *small_buffer;
+	unsigned long irq;
+	int cpu;
+
+	printk(KERN_INFO "[ds] bts selftest...");
+	conf.error = 0;
+
+	small_buffer = (unsigned char *)ALIGN((unsigned long)buffer, 8) + 8;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		conf.suspend = ds_suspend_bts_wrap;
+		conf.resume = ds_resume_bts_wrap;
+		conf.tracer =
+			ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
+					   NULL, (size_t)-1, BTS_KERNEL);
+		ds_selftest_bts_cpu(&conf);
+		if (conf.error >= 0)
+			conf.error = ds_selftest_bts_bad_request_task(buffer);
+		ds_release_bts(conf.tracer);
+		if (conf.error < 0)
+			goto out;
+
+		conf.suspend = ds_suspend_bts_noirq;
+		conf.resume = ds_resume_bts_noirq;
+		conf.tracer =
+			ds_request_bts_cpu(cpu, buffer, BUFFER_SIZE,
+					   NULL, (size_t)-1, BTS_KERNEL);
+		smp_call_function_single(cpu, ds_selftest_bts_cpu, &conf, 1);
+		if (conf.error >= 0) {
+			conf.error =
+				ds_selftest_bts_bad_release_noirq(cpu,
+								  conf.tracer);
+			/* We must not release the tracer twice. */
+			if (conf.error < 0)
+				conf.tracer = NULL;
+		}
+		if (conf.error >= 0)
+			conf.error = ds_selftest_bts_bad_request_task(buffer);
+		smp_call_function_single(cpu, ds_release_bts_noirq_wrap,
+					 conf.tracer, 1);
+		if (conf.error < 0)
+			goto out;
+	}
+
+	conf.suspend = ds_suspend_bts_wrap;
+	conf.resume = ds_resume_bts_wrap;
+	conf.tracer =
+		ds_request_bts_task(current, buffer, BUFFER_SIZE,
+				    NULL, (size_t)-1, BTS_KERNEL);
+	ds_selftest_bts_cpu(&conf);
+	if (conf.error >= 0)
+		conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
+	ds_release_bts(conf.tracer);
+	if (conf.error < 0)
+		goto out;
+
+	conf.suspend = ds_suspend_bts_noirq;
+	conf.resume = ds_resume_bts_noirq;
+	conf.tracer =
+		ds_request_bts_task(current, small_buffer, SMALL_BUFFER_SIZE,
+				   NULL, (size_t)-1, BTS_KERNEL);
+	local_irq_save(irq);
+	ds_selftest_bts_cpu(&conf);
+	if (conf.error >= 0)
+		conf.error = ds_selftest_bts_bad_request_cpu(0, buffer);
+	ds_release_bts_noirq(conf.tracer);
+	local_irq_restore(irq);
+	if (conf.error < 0)
+		goto out;
+
+	conf.error = 0;
+ out:
+	put_online_cpus();
+	printk(KERN_CONT "%s.\n", (conf.error ? "failed" : "passed"));
+
+	return conf.error;
+}
+
+int ds_selftest_pebs(void)
+{
+	return 0;
+}
diff --git a/arch/x86/kernel/ds_selftest.h b/arch/x86/kernel/ds_selftest.h
new file mode 100644
index 000000000000..2ba8745c6663
--- /dev/null
+++ b/arch/x86/kernel/ds_selftest.h
@@ -0,0 +1,15 @@
+/*
+ * Debug Store support - selftest
+ *
+ *
+ * Copyright (C) 2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2009
+ */
+
+#ifdef CONFIG_X86_DS_SELFTEST
+extern int ds_selftest_bts(void);
+extern int ds_selftest_pebs(void);
+#else
+static inline int ds_selftest_bts(void) { return 0; }
+static inline int ds_selftest_pebs(void) { return 0; }
+#endif
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index da87590b8698..81086c227ab7 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -29,7 +29,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *sp, unsigned long bp, char *log_lvl);
 
 extern unsigned int code_bytes;
-extern int kstack_depth_to_print;
 
 /* The form of the top of the frame on the stack */
 struct stack_frame {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 006281302925..7271fa33d791 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -617,7 +617,7 @@ __init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
  */
 __init void e820_setup_gap(void)
 {
-	unsigned long gapstart, gapsize, round;
+	unsigned long gapstart, gapsize;
 	int found;
 
 	gapstart = 0x10000000;
@@ -635,14 +635,9 @@ __init void e820_setup_gap(void)
 #endif
 
 	/*
-	 * See how much we want to round up: start off with
-	 * rounding to the next 1MB area.
+	 * e820_reserve_resources_late protect stolen RAM already
 	 */
-	round = 0x100000;
-	while ((gapsize >> 4) > round)
-		round += round;
-	/* Fun with two's complement */
-	pci_mem_start = (gapstart + round) & -round;
+	pci_mem_start = gapstart;
 
 	printk(KERN_INFO
 	       "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
@@ -1371,6 +1366,23 @@ void __init e820_reserve_resources(void)
 	}
 }
 
+/* How much should we pad RAM ending depending on where it is? */
+static unsigned long ram_alignment(resource_size_t pos)
+{
+	unsigned long mb = pos >> 20;
+
+	/* To 64kB in the first megabyte */
+	if (!mb)
+		return 64*1024;
+
+	/* To 1MB in the first 16MB */
+	if (mb < 16)
+		return 1024*1024;
+
+	/* To 32MB for anything above that */
+	return 32*1024*1024;
+}
+
 void __init e820_reserve_resources_late(void)
 {
 	int i;
@@ -1382,6 +1394,24 @@ void __init e820_reserve_resources_late(void)
 			insert_resource_expand_to_fit(&iomem_resource, res);
 		res++;
 	}
+
+	/*
+	 * Try to bump up RAM regions to reasonable boundaries to
+	 * avoid stolen RAM:
+	 */
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *entry = &e820_saved.map[i];
+		resource_size_t start, end;
+
+		if (entry->type != E820_RAM)
+			continue;
+		start = entry->addr + entry->size;
+		end = round_up(start, ram_alignment(start));
+		if (start == end)
+			continue;
+		reserve_region_with_split(&iomem_resource, start,
+						  end - 1, "RAM buffer");
+	}
 }
 
 char *__init default_machine_specific_memory_setup(void)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 76b8cd953dee..ebdb85cf2686 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -96,6 +96,7 @@ static void __init nvidia_bugs(int num, int slot, int func)
 
 }
 
+#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
 #if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
 static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 {
@@ -114,6 +115,7 @@ static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 	d &= 0xff;
 	return d;
 }
+#endif
 
 static void __init ati_bugs(int num, int slot, int func)
 {
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 38946c6e8433..a4742a340d8d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -147,27 +147,14 @@ END(ftrace_graph_caller)
 GLOBAL(return_to_handler)
 	subq  $80, %rsp
 
+	/* Save the return values */
 	movq %rax, (%rsp)
-	movq %rcx, 8(%rsp)
-	movq %rdx, 16(%rsp)
-	movq %rsi, 24(%rsp)
-	movq %rdi, 32(%rsp)
-	movq %r8, 40(%rsp)
-	movq %r9, 48(%rsp)
-	movq %r10, 56(%rsp)
-	movq %r11, 64(%rsp)
+	movq %rdx, 8(%rsp)
 
 	call ftrace_return_to_handler
 
 	movq %rax, 72(%rsp)
-	movq 64(%rsp), %r11
-	movq 56(%rsp), %r10
-	movq 48(%rsp), %r9
-	movq 40(%rsp), %r8
-	movq 32(%rsp), %rdi
-	movq 24(%rsp), %rsi
-	movq 16(%rsp), %rdx
-	movq 8(%rsp), %rcx
+	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
 	addq $72, %rsp
 	retq
@@ -1025,6 +1012,11 @@ apicinterrupt ERROR_APIC_VECTOR \
 apicinterrupt SPURIOUS_APIC_VECTOR \
 	spurious_interrupt smp_spurious_interrupt
 
+#ifdef CONFIG_PERF_COUNTERS
+apicinterrupt LOCAL_PENDING_VECTOR \
+	perf_pending_interrupt smp_perf_pending_interrupt
+#endif
+
 /*
  * Exception entry points.
  */
@@ -1379,6 +1371,11 @@ END(xen_failsafe_callback)
 paranoidzeroentry_ist debug do_debug DEBUG_STACK
 paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
 paranoiderrorentry stack_segment do_stack_segment
+#ifdef CONFIG_XEN
+zeroentry xen_debug do_debug
+zeroentry xen_int3 do_int3
+errorentry xen_stack_segment do_stack_segment
+#endif
 errorentry general_protection do_general_protection
 errorentry page_fault do_page_fault
 #ifdef CONFIG_X86_MCE
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 30683883e0cd..dc5ed4bdd88d 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -608,13 +608,6 @@ ignore_int:
 ENTRY(initial_code)
 	.long i386_start_kernel
 
-.section .text
-/*
- * Real beginning of normal "text" segment
- */
-ENTRY(stext)
-ENTRY(_stext)
-
 /*
  * BSS section
  */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index c3fe010d74c8..38287b5f116e 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -12,6 +12,7 @@
 #include <asm/io_apic.h>
 #include <asm/irq.h>
 #include <asm/idle.h>
+#include <asm/hw_irq.h>
 
 atomic_t irq_err_count;
 
@@ -24,9 +25,9 @@ void (*generic_interrupt_extension)(void) = NULL;
  */
 void ack_bad_irq(unsigned int irq)
 {
-	printk(KERN_ERR "unexpected IRQ trap at vector %02x\n", irq);
+	if (printk_ratelimit())
+		pr_err("unexpected IRQ trap at vector %02x\n", irq);
 
-#ifdef CONFIG_X86_LOCAL_APIC
 	/*
 	 * Currently unexpected vectors happen only on SMP and APIC.
 	 * We _must_ ack these because every local APIC has only N
@@ -36,9 +37,7 @@ void ack_bad_irq(unsigned int irq)
 	 * completely.
 	 * But only ack when the APIC is enabled -AK
 	 */
-	if (cpu_has_apic)
-		ack_APIC_irq();
-#endif
+	ack_APIC_irq();
 }
 
 #define irq_stats(x)		(&per_cpu(irq_stat, x))
@@ -63,6 +62,14 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
 	seq_printf(p, "  Spurious interrupts\n");
+	seq_printf(p, "%*s: ", prec, "CNT");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
+	seq_printf(p, "  Performance counter interrupts\n");
+	seq_printf(p, "%*s: ", prec, "PND");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs);
+	seq_printf(p, "  Performance pending work\n");
 #endif
 	if (generic_interrupt_extension) {
 		seq_printf(p, "%*s: ", prec, "PLT");
@@ -166,6 +173,8 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 #ifdef CONFIG_X86_LOCAL_APIC
 	sum += irq_stats(cpu)->apic_timer_irqs;
 	sum += irq_stats(cpu)->irq_spurious_count;
+	sum += irq_stats(cpu)->apic_perf_irqs;
+	sum += irq_stats(cpu)->apic_pending_irqs;
 #endif
 	if (generic_interrupt_extension)
 		sum += irq_stats(cpu)->generic_irqs;
@@ -178,7 +187,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 	sum += irq_stats(cpu)->irq_thermal_count;
 # ifdef CONFIG_X86_64
 	sum += irq_stats(cpu)->irq_threshold_count;
-#endif
+# endif
 #endif
 	return sum;
 }
@@ -213,14 +222,11 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	irq = __get_cpu_var(vector_irq)[vector];
 
 	if (!handle_irq(irq, regs)) {
-#ifdef CONFIG_X86_64
-		if (!disable_apic)
-			ack_APIC_irq();
-#endif
+		ack_APIC_irq();
 
 		if (printk_ratelimit())
-			printk(KERN_EMERG "%s: %d.%d No irq handler for vector (irq %d)\n",
-			       __func__, smp_processor_id(), vector, irq);
+			pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n",
+				__func__, smp_processor_id(), vector, irq);
 	}
 
 	irq_exit();
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit.c
similarity index 68%
rename from arch/x86/kernel/irqinit_32.c
rename to arch/x86/kernel/irqinit.c
index 368b0a8836f9..267c6624c77f 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit.c
@@ -1,20 +1,25 @@
+#include <linux/linkage.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/timex.h>
 #include <linux/slab.h>
 #include <linux/random.h>
+#include <linux/kprobes.h>
 #include <linux/init.h>
 #include <linux/kernel_stat.h>
 #include <linux/sysdev.h>
 #include <linux/bitops.h>
+#include <linux/acpi.h>
 #include <linux/io.h>
 #include <linux/delay.h>
 
 #include <asm/atomic.h>
 #include <asm/system.h>
 #include <asm/timer.h>
+#include <asm/hw_irq.h>
 #include <asm/pgtable.h>
 #include <asm/desc.h>
 #include <asm/apic.h>
@@ -22,7 +27,23 @@
 #include <asm/i8259.h>
 #include <asm/traps.h>
 
+/*
+ * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
+ * (these are usually mapped to vectors 0x30-0x3f)
+ */
 
+/*
+ * The IO-APIC gives us many more interrupt sources. Most of these
+ * are unused but an SMP system is supposed to have enough memory ...
+ * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
+ * across the spectrum, so we really want to be prepared to get all
+ * of these. Plus, more powerful systems might have more than 64
+ * IO-APIC registers.
+ *
+ * (these are usually mapped into the 0x30-0xff vector range)
+ */
+
+#ifdef CONFIG_X86_32
 /*
  * Note that on a 486, we don't want to do a SIGFPE on an irq13
  * as the irq is unreliable, and exception 16 works correctly
@@ -52,30 +73,7 @@ static struct irqaction fpu_irq = {
 	.handler = math_error_irq,
 	.name = "fpu",
 };
-
-void __init init_ISA_irqs(void)
-{
-	int i;
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	init_bsp_APIC();
 #endif
-	init_8259A(0);
-
-	/*
-	 * 16 old-style INTA-cycle interrupts:
-	 */
-	for (i = 0; i < NR_IRQS_LEGACY; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = NULL;
-		desc->depth = 1;
-
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-					      handle_level_irq, "XT");
-	}
-}
 
 /*
  * IRQ2 is cascade interrupt to second interrupt controller
@@ -118,29 +116,37 @@ int vector_used_by_percpu_irq(unsigned int vector)
 	return 0;
 }
 
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
+static void __init init_ISA_irqs(void)
 {
 	int i;
 
-	/* Execute any quirks before the call gates are initialised: */
-	x86_quirk_pre_intr_init();
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+	init_bsp_APIC();
+#endif
+	init_8259A(0);
 
 	/*
-	 * Cover the whole vector space, no vector can escape
-	 * us. (some of these will be overridden and become
-	 * 'special' SMP interrupts)
+	 * 16 old-style INTA-cycle interrupts:
 	 */
-	for (i =  FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
-		/* SYSCALL_VECTOR was reserved in trap_init. */
-		if (i != SYSCALL_VECTOR)
-			set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
+	for (i = 0; i < NR_IRQS_LEGACY; i++) {
+		struct irq_desc *desc = irq_to_desc(i);
+
+		desc->status = IRQ_DISABLED;
+		desc->action = NULL;
+		desc->depth = 1;
+
+		set_irq_chip_and_handler_name(i, &i8259A_chip,
+					      handle_level_irq, "XT");
 	}
+}
 
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
 
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_SMP)
+static void __init smp_intr_init(void)
+{
+#ifdef CONFIG_SMP
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
 	/*
 	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
 	 * IPI, driven by wakeup.
@@ -160,16 +166,32 @@ void __init native_init_IRQ(void)
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 
-	/* IPI for single call function */
+	/* IPI for generic single function call */
 	alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
-				 call_function_single_interrupt);
+			call_function_single_interrupt);
 
 	/* Low priority IPI to cleanup after moving an irq */
 	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
 	set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
 #endif
+#endif /* CONFIG_SMP */
+}
 
-#ifdef CONFIG_X86_LOCAL_APIC
+static void __init apic_intr_init(void)
+{
+	smp_intr_init();
+
+#ifdef CONFIG_X86_THERMAL_VECTOR
+	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+#endif
+#ifdef CONFIG_X86_THRESHOLD
+	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+#endif
+#if defined(CONFIG_X86_NEW_MCE) && defined(CONFIG_X86_LOCAL_APIC)
+	alloc_intr_gate(MCE_SELF_VECTOR, mce_self_interrupt);
+#endif
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
 	/* self generated IPI for local APIC timer */
 	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
 
@@ -179,16 +201,59 @@ void __init native_init_IRQ(void)
 	/* IPI vectors for APIC spurious and error interrupts */
 	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
 	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-#endif
 
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_MCE_P4THERMAL)
-	/* thermal monitor LVT interrupt */
-	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+	/* Performance monitoring interrupts: */
+# ifdef CONFIG_PERF_COUNTERS
+	alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt);
+# endif
+
 #endif
+}
+
+/**
+ * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
+ *
+ * Description:
+ *	Perform any necessary interrupt initialisation prior to setting up
+ *	the "ordinary" interrupt call gates.  For legacy reasons, the ISA
+ *	interrupts should be initialised here if the machine emulates a PC
+ *	in any way.
+ **/
+static void __init x86_quirk_pre_intr_init(void)
+{
+#ifdef CONFIG_X86_32
+	if (x86_quirks->arch_pre_intr_init) {
+		if (x86_quirks->arch_pre_intr_init())
+			return;
+	}
+#endif
+	init_ISA_irqs();
+}
+
+void __init native_init_IRQ(void)
+{
+	int i;
+
+	/* Execute any quirks before the call gates are initialised: */
+	x86_quirk_pre_intr_init();
+
+	apic_intr_init();
+
+	/*
+	 * Cover the whole vector space, no vector can escape
+	 * us. (some of these will be overridden and become
+	 * 'special' SMP interrupts)
+	 */
+	for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
+		/* IA32_SYSCALL_VECTOR could be used in trap_init already. */
+		if (!test_bit(i, used_vectors))
+			set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
+	}
 
 	if (!acpi_ioapic)
 		setup_irq(2, &irq2);
 
+#ifdef CONFIG_X86_32
 	/*
 	 * Call quirks after call gates are initialised (usually add in
 	 * the architecture specific gates):
@@ -203,4 +268,5 @@ void __init native_init_IRQ(void)
 		setup_irq(FPU_IRQ, &fpu_irq);
 
 	irq_ctx_init(smp_processor_id());
+#endif
 }
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
deleted file mode 100644
index 8cd10537fd46..000000000000
--- a/arch/x86/kernel/irqinit_64.c
+++ /dev/null
@@ -1,177 +0,0 @@
-#include <linux/linkage.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-#include <linux/acpi.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/hw_irq.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/i8259.h>
-
-/*
- * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
- * (these are usually mapped to vectors 0x30-0x3f)
- */
-
-/*
- * The IO-APIC gives us many more interrupt sources. Most of these
- * are unused but an SMP system is supposed to have enough memory ...
- * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
- * across the spectrum, so we really want to be prepared to get all
- * of these. Plus, more powerful systems might have more than 64
- * IO-APIC registers.
- *
- * (these are usually mapped into the 0x30-0xff vector range)
- */
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-
-static struct irqaction irq2 = {
-	.handler = no_action,
-	.name = "cascade",
-};
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... IRQ0_VECTOR - 1] = -1,
-	[IRQ0_VECTOR] = 0,
-	[IRQ1_VECTOR] = 1,
-	[IRQ2_VECTOR] = 2,
-	[IRQ3_VECTOR] = 3,
-	[IRQ4_VECTOR] = 4,
-	[IRQ5_VECTOR] = 5,
-	[IRQ6_VECTOR] = 6,
-	[IRQ7_VECTOR] = 7,
-	[IRQ8_VECTOR] = 8,
-	[IRQ9_VECTOR] = 9,
-	[IRQ10_VECTOR] = 10,
-	[IRQ11_VECTOR] = 11,
-	[IRQ12_VECTOR] = 12,
-	[IRQ13_VECTOR] = 13,
-	[IRQ14_VECTOR] = 14,
-	[IRQ15_VECTOR] = 15,
-	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
-};
-
-int vector_used_by_percpu_irq(unsigned int vector)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if (per_cpu(vector_irq, cpu)[vector] != -1)
-			return 1;
-	}
-
-	return 0;
-}
-
-static void __init init_ISA_irqs(void)
-{
-	int i;
-
-	init_bsp_APIC();
-	init_8259A(0);
-
-	for (i = 0; i < NR_IRQS_LEGACY; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = NULL;
-		desc->depth = 1;
-
-		/*
-		 * 16 old-style INTA-cycle interrupts:
-		 */
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-						      handle_level_irq, "XT");
-	}
-}
-
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-static void __init smp_intr_init(void)
-{
-#ifdef CONFIG_SMP
-	/*
-	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
-	 * IPI, driven by wakeup.
-	 */
-	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-
-	/* IPIs for invalidation */
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
-
-	/* IPI for generic function call */
-	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-
-	/* IPI for generic single function call */
-	alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
-			call_function_single_interrupt);
-
-	/* Low priority IPI to cleanup after moving an irq */
-	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
-	set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
-#endif
-}
-
-static void __init apic_intr_init(void)
-{
-	smp_intr_init();
-
-	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
-	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
-
-	/* self generated IPI for local APIC timer */
-	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-
-	/* generic IPI for platform specific use */
-	alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt);
-
-	/* IPI vectors for APIC spurious and error interrupts */
-	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
-	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-}
-
-void __init native_init_IRQ(void)
-{
-	int i;
-
-	init_ISA_irqs();
-	/*
-	 * Cover the whole vector space, no vector can escape
-	 * us. (some of these will be overridden and become
-	 * 'special' SMP interrupts)
-	 */
-	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
-		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (vector != IA32_SYSCALL_VECTOR)
-			set_intr_gate(vector, interrupt[i]);
-	}
-
-	apic_intr_init();
-
-	if (!acpi_ioapic)
-		setup_irq(2, &irq2);
-}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index b1f4dffb919e..8d82a77a3f3b 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -142,7 +142,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
 	gdb_regs32[GDB_PS]	= *(unsigned long *)(p->thread.sp + 8);
 	gdb_regs32[GDB_CS]	= __KERNEL_CS;
 	gdb_regs32[GDB_SS]	= __KERNEL_DS;
-	gdb_regs[GDB_PC]	= p->thread.ip;
+	gdb_regs[GDB_PC]	= 0;
 	gdb_regs[GDB_R8]	= 0;
 	gdb_regs[GDB_R9]	= 0;
 	gdb_regs[GDB_R10]	= 0;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 33019ddb56b4..a78ecad0c900 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -27,6 +27,7 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/hardirq.h>
+#include <asm/timer.h>
 
 #define MMU_QUEUE_SIZE 1024
 
@@ -195,7 +196,7 @@ static void kvm_leave_lazy_mmu(void)
 	struct kvm_para_state *state = kvm_para_state();
 
 	mmu_queue_flush(state);
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
+	paravirt_leave_lazy_mmu();
 	state->mode = paravirt_get_lazy_mode();
 }
 
@@ -230,6 +231,9 @@ static void paravirt_ops_setup(void)
 		pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
 		pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
 	}
+#ifdef CONFIG_X86_IO_APIC
+	no_timer_check = 1;
+#endif
 }
 
 void __init kvm_guest_init(void)
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 453b5795a5c6..366baa179913 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -13,25 +13,13 @@
  *  Licensed under the terms of the GNU General Public
  *  License version 2. See file COPYING for details.
  */
-#include <linux/platform_device.h>
-#include <linux/capability.h>
-#include <linux/miscdevice.h>
 #include <linux/firmware.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
 #include <linux/pci_ids.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/cpu.h>
 #include <linux/pci.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
 
 #include <asm/microcode.h>
 #include <asm/processor.h>
@@ -79,9 +67,6 @@ struct microcode_amd {
 #define UCODE_CONTAINER_SECTION_HDR	8
 #define UCODE_CONTAINER_HEADER_SIZE	12
 
-/* serialize access to the physical write */
-static DEFINE_SPINLOCK(microcode_update_lock);
-
 static struct equiv_cpu_entry *equiv_cpu_table;
 
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
@@ -144,9 +129,8 @@ static int get_matching_microcode(int cpu, void *mc, int rev)
 	return 1;
 }
 
-static void apply_microcode_amd(int cpu)
+static int apply_microcode_amd(int cpu)
 {
-	unsigned long flags;
 	u32 rev, dummy;
 	int cpu_num = raw_smp_processor_id();
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num;
@@ -156,25 +140,25 @@ static void apply_microcode_amd(int cpu)
 	BUG_ON(cpu_num != cpu);
 
 	if (mc_amd == NULL)
-		return;
+		return 0;
 
-	spin_lock_irqsave(&microcode_update_lock, flags);
 	wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
 	/* get patch id after patching */
 	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-	spin_unlock_irqrestore(&microcode_update_lock, flags);
 
 	/* check current patch id and patch's id for match */
 	if (rev != mc_amd->hdr.patch_id) {
 		printk(KERN_ERR "microcode: CPU%d: update failed "
 		       "(for patch_level=0x%x)\n", cpu, mc_amd->hdr.patch_id);
-		return;
+		return -1;
 	}
 
 	printk(KERN_INFO "microcode: CPU%d: updated (new patch_level=0x%x)\n",
 	       cpu, rev);
 
 	uci->cpu_sig.rev = rev;
+
+	return 0;
 }
 
 static int get_ucode_data(void *to, const u8 *from, size_t n)
@@ -257,13 +241,12 @@ static int install_equiv_cpu_table(const u8 *buf)
 
 static void free_equiv_cpu_table(void)
 {
-	if (equiv_cpu_table) {
-		vfree(equiv_cpu_table);
-		equiv_cpu_table = NULL;
-	}
+	vfree(equiv_cpu_table);
+	equiv_cpu_table = NULL;
 }
 
-static int generic_load_microcode(int cpu, const u8 *data, size_t size)
+static enum ucode_state
+generic_load_microcode(int cpu, const u8 *data, size_t size)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	const u8 *ucode_ptr = data;
@@ -272,12 +255,13 @@ static int generic_load_microcode(int cpu, const u8 *data, size_t size)
 	int new_rev = uci->cpu_sig.rev;
 	unsigned int leftover;
 	unsigned long offset;
+	enum ucode_state state = UCODE_OK;
 
 	offset = install_equiv_cpu_table(ucode_ptr);
 	if (!offset) {
 		printk(KERN_ERR "microcode: failed to create "
 		       "equivalent cpu table\n");
-		return -EINVAL;
+		return UCODE_ERROR;
 	}
 
 	ucode_ptr += offset;
@@ -293,8 +277,7 @@ static int generic_load_microcode(int cpu, const u8 *data, size_t size)
 
 		mc_header = (struct microcode_header_amd *)mc;
 		if (get_matching_microcode(cpu, mc, new_rev)) {
-			if (new_mc)
-				vfree(new_mc);
+			vfree(new_mc);
 			new_rev = mc_header->patch_id;
 			new_mc  = mc;
 		} else
@@ -306,34 +289,32 @@ static int generic_load_microcode(int cpu, const u8 *data, size_t size)
 
 	if (new_mc) {
 		if (!leftover) {
-			if (uci->mc)
-				vfree(uci->mc);
+			vfree(uci->mc);
 			uci->mc = new_mc;
 			pr_debug("microcode: CPU%d found a matching microcode "
 				 "update with version 0x%x (current=0x%x)\n",
 				 cpu, new_rev, uci->cpu_sig.rev);
-		} else
+		} else {
 			vfree(new_mc);
-	}
+			state = UCODE_ERROR;
+		}
+	} else
+		state = UCODE_NFOUND;
 
 	free_equiv_cpu_table();
 
-	return (int)leftover;
+	return state;
 }
 
-static int request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 {
 	const char *fw_name = "amd-ucode/microcode_amd.bin";
 	const struct firmware *firmware;
-	int ret;
+	enum ucode_state ret;
 
-	/* We should bind the task to the CPU */
-	BUG_ON(cpu != raw_smp_processor_id());
-
-	ret = request_firmware(&firmware, fw_name, device);
-	if (ret) {
+	if (request_firmware(&firmware, fw_name, device)) {
 		printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
-		return ret;
+		return UCODE_NFOUND;
 	}
 
 	ret = generic_load_microcode(cpu, firmware->data, firmware->size);
@@ -343,11 +324,12 @@ static int request_microcode_fw(int cpu, struct device *device)
 	return ret;
 }
 
-static int request_microcode_user(int cpu, const void __user *buf, size_t size)
+static enum ucode_state
+request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
 	printk(KERN_INFO "microcode: AMD microcode update via "
 	       "/dev/cpu/microcode not supported\n");
-	return -1;
+	return UCODE_ERROR;
 }
 
 static void microcode_fini_cpu_amd(int cpu)
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 98c470c069d1..9c4461501fcb 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -71,27 +71,18 @@
  *		Thanks to Stuart Swales for pointing out this bug.
  */
 #include <linux/platform_device.h>
-#include <linux/capability.h>
 #include <linux/miscdevice.h>
-#include <linux/firmware.h>
+#include <linux/capability.h>
 #include <linux/smp_lock.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 
 #include <asm/microcode.h>
 #include <asm/processor.h>
-#include <asm/msr.h>
 
 MODULE_DESCRIPTION("Microcode Update Driver");
 MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
@@ -101,36 +92,110 @@ MODULE_LICENSE("GPL");
 
 static struct microcode_ops	*microcode_ops;
 
-/* no concurrent ->write()s are allowed on /dev/cpu/microcode */
+/*
+ * Synchronization.
+ *
+ * All non cpu-hotplug-callback call sites use:
+ *
+ * - microcode_mutex to synchronize with each other;
+ * - get/put_online_cpus() to synchronize with
+ *   the cpu-hotplug-callback call sites.
+ *
+ * We guarantee that only a single cpu is being
+ * updated at any particular moment of time.
+ */
 static DEFINE_MUTEX(microcode_mutex);
 
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 EXPORT_SYMBOL_GPL(ucode_cpu_info);
 
+/*
+ * Operations that are run on a target cpu:
+ */
+
+struct cpu_info_ctx {
+	struct cpu_signature	*cpu_sig;
+	int			err;
+};
+
+static void collect_cpu_info_local(void *arg)
+{
+	struct cpu_info_ctx *ctx = arg;
+
+	ctx->err = microcode_ops->collect_cpu_info(smp_processor_id(),
+						   ctx->cpu_sig);
+}
+
+static int collect_cpu_info_on_target(int cpu, struct cpu_signature *cpu_sig)
+{
+	struct cpu_info_ctx ctx = { .cpu_sig = cpu_sig, .err = 0 };
+	int ret;
+
+	ret = smp_call_function_single(cpu, collect_cpu_info_local, &ctx, 1);
+	if (!ret)
+		ret = ctx.err;
+
+	return ret;
+}
+
+static int collect_cpu_info(int cpu)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	int ret;
+
+	memset(uci, 0, sizeof(*uci));
+
+	ret = collect_cpu_info_on_target(cpu, &uci->cpu_sig);
+	if (!ret)
+		uci->valid = 1;
+
+	return ret;
+}
+
+struct apply_microcode_ctx {
+	int err;
+};
+
+static void apply_microcode_local(void *arg)
+{
+	struct apply_microcode_ctx *ctx = arg;
+
+	ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+}
+
+static int apply_microcode_on_target(int cpu)
+{
+	struct apply_microcode_ctx ctx = { .err = 0 };
+	int ret;
+
+	ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
+	if (!ret)
+		ret = ctx.err;
+
+	return ret;
+}
+
 #ifdef CONFIG_MICROCODE_OLD_INTERFACE
 static int do_microcode_update(const void __user *buf, size_t size)
 {
-	cpumask_t old;
 	int error = 0;
 	int cpu;
 
-	old = current->cpus_allowed;
-
 	for_each_online_cpu(cpu) {
 		struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+		enum ucode_state ustate;
 
 		if (!uci->valid)
 			continue;
 
-		set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-		error = microcode_ops->request_microcode_user(cpu, buf, size);
-		if (error < 0)
-			goto out;
-		if (!error)
-			microcode_ops->apply_microcode(cpu);
+		ustate = microcode_ops->request_microcode_user(cpu, buf, size);
+		if (ustate == UCODE_ERROR) {
+			error = -1;
+			break;
+		} else if (ustate == UCODE_OK)
+			apply_microcode_on_target(cpu);
 	}
-out:
-	set_cpus_allowed_ptr(current, &old);
+
 	return error;
 }
 
@@ -143,19 +208,17 @@ static int microcode_open(struct inode *unused1, struct file *unused2)
 static ssize_t microcode_write(struct file *file, const char __user *buf,
 			       size_t len, loff_t *ppos)
 {
-	ssize_t ret;
+	ssize_t ret = -EINVAL;
 
 	if ((len >> PAGE_SHIFT) > num_physpages) {
-		printk(KERN_ERR "microcode: too much data (max %ld pages)\n",
-		       num_physpages);
-		return -EINVAL;
+		pr_err("microcode: too much data (max %ld pages)\n", num_physpages);
+		return ret;
 	}
 
 	get_online_cpus();
 	mutex_lock(&microcode_mutex);
 
-	ret = do_microcode_update(buf, len);
-	if (!ret)
+	if (do_microcode_update(buf, len) == 0)
 		ret = (ssize_t)len;
 
 	mutex_unlock(&microcode_mutex);
@@ -165,15 +228,15 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
 }
 
 static const struct file_operations microcode_fops = {
-	.owner		= THIS_MODULE,
-	.write		= microcode_write,
-	.open		= microcode_open,
+	.owner			= THIS_MODULE,
+	.write			= microcode_write,
+	.open			= microcode_open,
 };
 
 static struct miscdevice microcode_dev = {
-	.minor		= MICROCODE_MINOR,
-	.name		= "microcode",
-	.fops		= &microcode_fops,
+	.minor			= MICROCODE_MINOR,
+	.name			= "microcode",
+	.fops			= &microcode_fops,
 };
 
 static int __init microcode_dev_init(void)
@@ -182,9 +245,7 @@ static int __init microcode_dev_init(void)
 
 	error = misc_register(&microcode_dev);
 	if (error) {
-		printk(KERN_ERR
-			"microcode: can't misc_register on minor=%d\n",
-			MICROCODE_MINOR);
+		pr_err("microcode: can't misc_register on minor=%d\n", MICROCODE_MINOR);
 		return error;
 	}
 
@@ -205,42 +266,51 @@ MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
 /* fake device for request_firmware */
 static struct platform_device	*microcode_pdev;
 
-static long reload_for_cpu(void *unused)
+static int reload_for_cpu(int cpu)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	int err = 0;
 
 	mutex_lock(&microcode_mutex);
 	if (uci->valid) {
-		err = microcode_ops->request_microcode_fw(smp_processor_id(),
-							  &microcode_pdev->dev);
-		if (!err)
-			microcode_ops->apply_microcode(smp_processor_id());
+		enum ucode_state ustate;
+
+		ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev);
+		if (ustate == UCODE_OK)
+			apply_microcode_on_target(cpu);
+		else
+			if (ustate == UCODE_ERROR)
+				err = -EINVAL;
 	}
 	mutex_unlock(&microcode_mutex);
+
 	return err;
 }
 
 static ssize_t reload_store(struct sys_device *dev,
 			    struct sysdev_attribute *attr,
-			    const char *buf, size_t sz)
+			    const char *buf, size_t size)
 {
-	char *end;
-	unsigned long val = simple_strtoul(buf, &end, 0);
-	int err = 0;
+	unsigned long val;
 	int cpu = dev->id;
+	int ret = 0;
+	char *end;
 
+	val = simple_strtoul(buf, &end, 0);
 	if (end == buf)
 		return -EINVAL;
+
 	if (val == 1) {
 		get_online_cpus();
 		if (cpu_online(cpu))
-			err = work_on_cpu(cpu, reload_for_cpu, NULL);
+			ret = reload_for_cpu(cpu);
 		put_online_cpus();
 	}
-	if (err)
-		return err;
-	return sz;
+
+	if (!ret)
+		ret = size;
+
+	return ret;
 }
 
 static ssize_t version_show(struct sys_device *dev,
@@ -271,11 +341,11 @@ static struct attribute *mc_default_attrs[] = {
 };
 
 static struct attribute_group mc_attr_group = {
-	.attrs		= mc_default_attrs,
-	.name		= "microcode",
+	.attrs			= mc_default_attrs,
+	.name			= "microcode",
 };
 
-static void __microcode_fini_cpu(int cpu)
+static void microcode_fini_cpu(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
@@ -283,103 +353,68 @@ static void __microcode_fini_cpu(int cpu)
 	uci->valid = 0;
 }
 
-static void microcode_fini_cpu(int cpu)
-{
-	mutex_lock(&microcode_mutex);
-	__microcode_fini_cpu(cpu);
-	mutex_unlock(&microcode_mutex);
-}
-
-static void collect_cpu_info(int cpu)
+static enum ucode_state microcode_resume_cpu(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
-	memset(uci, 0, sizeof(*uci));
-	if (!microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig))
-		uci->valid = 1;
-}
-
-static int microcode_resume_cpu(int cpu)
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	struct cpu_signature nsig;
-
-	pr_debug("microcode: CPU%d resumed\n", cpu);
-
 	if (!uci->mc)
-		return 1;
+		return UCODE_NFOUND;
 
-	/*
-	 * Let's verify that the 'cached' ucode does belong
-	 * to this cpu (a bit of paranoia):
-	 */
-	if (microcode_ops->collect_cpu_info(cpu, &nsig)) {
-		__microcode_fini_cpu(cpu);
-		printk(KERN_ERR "failed to collect_cpu_info for resuming cpu #%d\n",
-				cpu);
-		return -1;
-	}
+	pr_debug("microcode: CPU%d updated upon resume\n", cpu);
+	apply_microcode_on_target(cpu);
 
-	if ((nsig.sig != uci->cpu_sig.sig) || (nsig.pf != uci->cpu_sig.pf)) {
-		__microcode_fini_cpu(cpu);
-		printk(KERN_ERR "cached ucode doesn't match the resuming cpu #%d\n",
-				cpu);
-		/* Should we look for a new ucode here? */
-		return 1;
-	}
-
-	return 0;
+	return UCODE_OK;
 }
 
-static long microcode_update_cpu(void *unused)
+static enum ucode_state microcode_init_cpu(int cpu)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
-	int err = 0;
+	enum ucode_state ustate;
 
-	/*
-	 * Check if the system resume is in progress (uci->valid != NULL),
-	 * otherwise just request a firmware:
-	 */
-	if (uci->valid) {
-		err = microcode_resume_cpu(smp_processor_id());
-	} else {
-		collect_cpu_info(smp_processor_id());
-		if (uci->valid && system_state == SYSTEM_RUNNING)
-			err = microcode_ops->request_microcode_fw(
-					smp_processor_id(),
-					&microcode_pdev->dev);
+	if (collect_cpu_info(cpu))
+		return UCODE_ERROR;
+
+	/* --dimm. Trigger a delayed update? */
+	if (system_state != SYSTEM_RUNNING)
+		return UCODE_NFOUND;
+
+	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev);
+
+	if (ustate == UCODE_OK) {
+		pr_debug("microcode: CPU%d updated upon init\n", cpu);
+		apply_microcode_on_target(cpu);
 	}
-	if (!err)
-		microcode_ops->apply_microcode(smp_processor_id());
-	return err;
+
+	return ustate;
 }
 
-static int microcode_init_cpu(int cpu)
+static enum ucode_state microcode_update_cpu(int cpu)
 {
-	int err;
-	mutex_lock(&microcode_mutex);
-	err = work_on_cpu(cpu, microcode_update_cpu, NULL);
-	mutex_unlock(&microcode_mutex);
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	enum ucode_state ustate;
 
-	return err;
+	if (uci->valid)
+		ustate = microcode_resume_cpu(cpu);
+	else
+		ustate = microcode_init_cpu(cpu);
+
+	return ustate;
 }
 
 static int mc_sysdev_add(struct sys_device *sys_dev)
 {
 	int err, cpu = sys_dev->id;
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
 	if (!cpu_online(cpu))
 		return 0;
 
 	pr_debug("microcode: CPU%d added\n", cpu);
-	memset(uci, 0, sizeof(*uci));
 
 	err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
 	if (err)
 		return err;
 
-	err = microcode_init_cpu(cpu);
+	if (microcode_init_cpu(cpu) == UCODE_ERROR)
+		err = -EINVAL;
 
 	return err;
 }
@@ -400,19 +435,30 @@ static int mc_sysdev_remove(struct sys_device *sys_dev)
 static int mc_sysdev_resume(struct sys_device *dev)
 {
 	int cpu = dev->id;
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
 	if (!cpu_online(cpu))
 		return 0;
 
-	/* only CPU 0 will apply ucode here */
-	microcode_update_cpu(NULL);
+	/*
+	 * All non-bootup cpus are still disabled,
+	 * so only CPU 0 will apply ucode here.
+	 *
+	 * Moreover, there can be no concurrent
+	 * updates from any other places at this point.
+	 */
+	WARN_ON(cpu != 0);
+
+	if (uci->valid && uci->mc)
+		microcode_ops->apply_microcode(cpu);
+
 	return 0;
 }
 
 static struct sysdev_driver mc_sysdev_driver = {
-	.add		= mc_sysdev_add,
-	.remove		= mc_sysdev_remove,
-	.resume		= mc_sysdev_resume,
+	.add			= mc_sysdev_add,
+	.remove			= mc_sysdev_remove,
+	.resume			= mc_sysdev_resume,
 };
 
 static __cpuinit int
@@ -425,15 +471,12 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		if (microcode_init_cpu(cpu))
-			printk(KERN_ERR "microcode: failed to init CPU%d\n",
-			       cpu);
+		microcode_update_cpu(cpu);
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
 		pr_debug("microcode: CPU%d added\n", cpu);
 		if (sysfs_create_group(&sys_dev->kobj, &mc_attr_group))
-			printk(KERN_ERR "microcode: Failed to create the sysfs "
-				"group for CPU%d\n", cpu);
+			pr_err("microcode: Failed to create group for CPU%d\n", cpu);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
@@ -465,13 +508,10 @@ static int __init microcode_init(void)
 		microcode_ops = init_amd_microcode();
 
 	if (!microcode_ops) {
-		printk(KERN_ERR "microcode: no support for this CPU vendor\n");
+		pr_err("microcode: no support for this CPU vendor\n");
 		return -ENODEV;
 	}
 
-	error = microcode_dev_init();
-	if (error)
-		return error;
 	microcode_pdev = platform_device_register_simple("microcode", -1,
 							 NULL, 0);
 	if (IS_ERR(microcode_pdev)) {
@@ -480,23 +520,31 @@ static int __init microcode_init(void)
 	}
 
 	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+
 	error = sysdev_driver_register(&cpu_sysdev_class, &mc_sysdev_driver);
+
+	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
+
 	if (error) {
-		microcode_dev_exit();
 		platform_device_unregister(microcode_pdev);
 		return error;
 	}
 
+	error = microcode_dev_init();
+	if (error)
+		return error;
+
 	register_hotcpu_notifier(&mc_cpu_notifier);
 
-	printk(KERN_INFO
-	       "Microcode Update Driver: v" MICROCODE_VERSION
+	pr_info("Microcode Update Driver: v" MICROCODE_VERSION
 	       " <tigran@aivazian.fsnet.co.uk>,"
 	       " Peter Oruba\n");
 
 	return 0;
 }
+module_init(microcode_init);
 
 static void __exit microcode_exit(void)
 {
@@ -505,16 +553,17 @@ static void __exit microcode_exit(void)
 	unregister_hotcpu_notifier(&mc_cpu_notifier);
 
 	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+
 	sysdev_driver_unregister(&cpu_sysdev_class, &mc_sysdev_driver);
+
+	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
 	platform_device_unregister(microcode_pdev);
 
 	microcode_ops = NULL;
 
-	printk(KERN_INFO
-	       "Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
+	pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
 }
-
-module_init(microcode_init);
 module_exit(microcode_exit);
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 149b9ec7c1ab..0d334ddd0a96 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -70,24 +70,11 @@
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
  *		Thanks to Stuart Swales for pointing out this bug.
  */
-#include <linux/platform_device.h>
-#include <linux/capability.h>
-#include <linux/miscdevice.h>
 #include <linux/firmware.h>
-#include <linux/smp_lock.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
 #include <linux/uaccess.h>
-#include <linux/vmalloc.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/cpu.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 #include <asm/microcode.h>
 #include <asm/processor.h>
@@ -150,13 +137,9 @@ struct extended_sigtable {
 
 #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
 
-/* serialize access to the physical write to MSR 0x79 */
-static DEFINE_SPINLOCK(microcode_update_lock);
-
 static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu_num);
-	unsigned long flags;
 	unsigned int val[2];
 
 	memset(csig, 0, sizeof(*csig));
@@ -176,18 +159,14 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 		csig->pf = 1 << ((val[1] >> 18) & 7);
 	}
 
-	/* serialize access to the physical write to MSR 0x79 */
-	spin_lock_irqsave(&microcode_update_lock, flags);
-
 	wrmsr(MSR_IA32_UCODE_REV, 0, 0);
 	/* see notes above for revision 1.07.  Apparent chip bug */
 	sync_core();
 	/* get the current revision from MSR 0x8B */
 	rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev);
-	spin_unlock_irqrestore(&microcode_update_lock, flags);
 
-	pr_debug("microcode: collect_cpu_info : sig=0x%x, pf=0x%x, rev=0x%x\n",
-			csig->sig, csig->pf, csig->rev);
+	printk(KERN_INFO "microcode: CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n",
+			cpu_num, csig->sig, csig->pf, csig->rev);
 
 	return 0;
 }
@@ -318,11 +297,10 @@ get_matching_microcode(struct cpu_signature *cpu_sig, void *mc, int rev)
 	return 0;
 }
 
-static void apply_microcode(int cpu)
+static int apply_microcode(int cpu)
 {
 	struct microcode_intel *mc_intel;
 	struct ucode_cpu_info *uci;
-	unsigned long flags;
 	unsigned int val[2];
 	int cpu_num;
 
@@ -334,10 +312,7 @@ static void apply_microcode(int cpu)
 	BUG_ON(cpu_num != cpu);
 
 	if (mc_intel == NULL)
-		return;
-
-	/* serialize access to the physical write to MSR 0x79 */
-	spin_lock_irqsave(&microcode_update_lock, flags);
+		return 0;
 
 	/* write microcode via MSR 0x79 */
 	wrmsr(MSR_IA32_UCODE_WRITE,
@@ -351,30 +326,32 @@ static void apply_microcode(int cpu)
 	/* get the current revision from MSR 0x8B */
 	rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
 
-	spin_unlock_irqrestore(&microcode_update_lock, flags);
 	if (val[1] != mc_intel->hdr.rev) {
-		printk(KERN_ERR "microcode: CPU%d update from revision "
-				"0x%x to 0x%x failed\n",
-			cpu_num, uci->cpu_sig.rev, val[1]);
-		return;
+		printk(KERN_ERR "microcode: CPU%d update "
+				"to revision 0x%x failed\n",
+			cpu_num, mc_intel->hdr.rev);
+		return -1;
 	}
-	printk(KERN_INFO "microcode: CPU%d updated from revision "
-			 "0x%x to 0x%x, date = %04x-%02x-%02x \n",
-		cpu_num, uci->cpu_sig.rev, val[1],
+	printk(KERN_INFO "microcode: CPU%d updated to revision "
+			 "0x%x, date = %04x-%02x-%02x \n",
+		cpu_num, val[1],
 		mc_intel->hdr.date & 0xffff,
 		mc_intel->hdr.date >> 24,
 		(mc_intel->hdr.date >> 16) & 0xff);
 
 	uci->cpu_sig.rev = val[1];
+
+	return 0;
 }
 
-static int generic_load_microcode(int cpu, void *data, size_t size,
-		int (*get_ucode_data)(void *, const void *, size_t))
+static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
+				int (*get_ucode_data)(void *, const void *, size_t))
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	u8 *ucode_ptr = data, *new_mc = NULL, *mc;
 	int new_rev = uci->cpu_sig.rev;
 	unsigned int leftover = size;
+	enum ucode_state state = UCODE_OK;
 
 	while (leftover) {
 		struct microcode_header_intel mc_header;
@@ -412,11 +389,15 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
 		leftover  -= mc_size;
 	}
 
-	if (!new_mc)
-		goto out;
-
 	if (leftover) {
-		vfree(new_mc);
+		if (new_mc)
+			vfree(new_mc);
+		state = UCODE_ERROR;
+		goto out;
+	}
+
+	if (!new_mc) {
+		state = UCODE_NFOUND;
 		goto out;
 	}
 
@@ -427,9 +408,8 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
 	pr_debug("microcode: CPU%d found a matching microcode update with"
 		 " version 0x%x (current=0x%x)\n",
 			cpu, new_rev, uci->cpu_sig.rev);
-
- out:
-	return (int)leftover;
+out:
+	return state;
 }
 
 static int get_ucode_fw(void *to, const void *from, size_t n)
@@ -438,21 +418,19 @@ static int get_ucode_fw(void *to, const void *from, size_t n)
 	return 0;
 }
 
-static int request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 {
 	char name[30];
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	const struct firmware *firmware;
-	int ret;
+	enum ucode_state ret;
 
-	/* We should bind the task to the CPU */
-	BUG_ON(cpu != raw_smp_processor_id());
 	sprintf(name, "intel-ucode/%02x-%02x-%02x",
 		c->x86, c->x86_model, c->x86_mask);
-	ret = request_firmware(&firmware, name, device);
-	if (ret) {
+
+	if (request_firmware(&firmware, name, device)) {
 		pr_debug("microcode: data file %s load failed\n", name);
-		return ret;
+		return UCODE_NFOUND;
 	}
 
 	ret = generic_load_microcode(cpu, (void *)firmware->data,
@@ -468,11 +446,9 @@ static int get_ucode_user(void *to, const void *from, size_t n)
 	return copy_from_user(to, from, n);
 }
 
-static int request_microcode_user(int cpu, const void __user *buf, size_t size)
+static enum ucode_state
+request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
-	/* We should bind the task to the CPU */
-	BUG_ON(cpu != raw_smp_processor_id());
-
 	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
 }
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 70fd7e414c15..651c93b28862 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -17,6 +17,7 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/smp.h>
+#include <linux/pci.h>
 
 #include <asm/mtrr.h>
 #include <asm/mpspec.h>
@@ -870,24 +871,17 @@ static
 inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
 #endif /* CONFIG_X86_IO_APIC */
 
-static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length,
-		      int count)
+static int
+check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
 {
-	if (!mpc_new_phys) {
-		pr_info("No spare slots, try to append...take your risk, "
-			"new mpc_length %x\n", count);
-	} else {
-		if (count <= mpc_new_length)
-			pr_info("No spare slots, try to append..., "
-				"new mpc_length %x\n", count);
-		else {
-			pr_err("mpc_new_length %lx is too small\n",
-				mpc_new_length);
-			return -1;
-		}
+	int ret = 0;
+
+	if (!mpc_new_phys || count <= mpc_new_length) {
+		WARN(1, "update_mptable: No spare slots (length: %x)\n", count);
+		return -1;
 	}
 
-	return 0;
+	return ret;
 }
 
 static int  __init replace_intsrc_all(struct mpc_table *mpc,
@@ -946,7 +940,7 @@ static int  __init replace_intsrc_all(struct mpc_table *mpc,
 		} else {
 			struct mpc_intsrc *m = (struct mpc_intsrc *)mpt;
 			count += sizeof(struct mpc_intsrc);
-			if (!check_slot(mpc_new_phys, mpc_new_length, count))
+			if (check_slot(mpc_new_phys, mpc_new_length, count) < 0)
 				goto out;
 			assign_to_mpc_intsrc(&mp_irqs[i], m);
 			mpc->length = count;
@@ -963,11 +957,14 @@ out:
 	return 0;
 }
 
-static int __initdata enable_update_mptable;
+int enable_update_mptable;
 
 static int __init update_mptable_setup(char *str)
 {
 	enable_update_mptable = 1;
+#ifdef CONFIG_PCI
+	pci_routeirq = 1;
+#endif
 	return 0;
 }
 early_param("update_mptable", update_mptable_setup);
@@ -980,6 +977,9 @@ static int __initdata alloc_mptable;
 static int __init parse_alloc_mptable_opt(char *p)
 {
 	enable_update_mptable = 1;
+#ifdef CONFIG_PCI
+	pci_routeirq = 1;
+#endif
 	alloc_mptable = 1;
 	if (!p)
 		return 0;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 9faf43bea336..70ec9b951d76 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -248,18 +248,16 @@ static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LA
 
 static inline void enter_lazy(enum paravirt_lazy_mode mode)
 {
-	BUG_ON(__get_cpu_var(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
-	BUG_ON(preemptible());
+	BUG_ON(percpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
 
-	__get_cpu_var(paravirt_lazy_mode) = mode;
+	percpu_write(paravirt_lazy_mode, mode);
 }
 
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode)
+static void leave_lazy(enum paravirt_lazy_mode mode)
 {
-	BUG_ON(__get_cpu_var(paravirt_lazy_mode) != mode);
-	BUG_ON(preemptible());
+	BUG_ON(percpu_read(paravirt_lazy_mode) != mode);
 
-	__get_cpu_var(paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
+	percpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
 }
 
 void paravirt_enter_lazy_mmu(void)
@@ -269,22 +267,36 @@ void paravirt_enter_lazy_mmu(void)
 
 void paravirt_leave_lazy_mmu(void)
 {
-	paravirt_leave_lazy(PARAVIRT_LAZY_MMU);
+	leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
-void paravirt_enter_lazy_cpu(void)
+void paravirt_start_context_switch(struct task_struct *prev)
 {
+	BUG_ON(preemptible());
+
+	if (percpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+	}
 	enter_lazy(PARAVIRT_LAZY_CPU);
 }
 
-void paravirt_leave_lazy_cpu(void)
+void paravirt_end_context_switch(struct task_struct *next)
 {
-	paravirt_leave_lazy(PARAVIRT_LAZY_CPU);
+	BUG_ON(preemptible());
+
+	leave_lazy(PARAVIRT_LAZY_CPU);
+
+	if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+		arch_enter_lazy_mmu_mode();
 }
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 {
-	return __get_cpu_var(paravirt_lazy_mode);
+	if (in_interrupt())
+		return PARAVIRT_LAZY_NONE;
+
+	return percpu_read(paravirt_lazy_mode);
 }
 
 void arch_flush_lazy_mmu_mode(void)
@@ -292,7 +304,6 @@ void arch_flush_lazy_mmu_mode(void)
 	preempt_disable();
 
 	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		WARN_ON(preempt_count() == 1);
 		arch_leave_lazy_mmu_mode();
 		arch_enter_lazy_mmu_mode();
 	}
@@ -300,19 +311,6 @@ void arch_flush_lazy_mmu_mode(void)
 	preempt_enable();
 }
 
-void arch_flush_lazy_cpu_mode(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
-		WARN_ON(preempt_count() == 1);
-		arch_leave_lazy_cpu_mode();
-		arch_enter_lazy_cpu_mode();
-	}
-
-	preempt_enable();
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -404,10 +402,8 @@ struct pv_cpu_ops pv_cpu_ops = {
 	.set_iopl_mask = native_set_iopl_mask,
 	.io_delay = native_io_delay,
 
-	.lazy_mode = {
-		.enter = paravirt_nop,
-		.leave = paravirt_nop,
-	},
+	.start_context_switch = paravirt_nop,
+	.end_context_switch = paravirt_nop,
 };
 
 struct pv_apic_ops pv_apic_ops = {
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 755c21e906f3..971a3bec47a8 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -186,37 +186,6 @@ static struct cal_chipset_ops calioc2_chip_ops = {
 
 static struct calgary_bus_info bus_info[MAX_PHB_BUS_NUM] = { { NULL, 0, 0 }, };
 
-/* enable this to stress test the chip's TCE cache */
-#ifdef CONFIG_IOMMU_DEBUG
-static int debugging = 1;
-
-static inline unsigned long verify_bit_range(unsigned long* bitmap,
-	int expected, unsigned long start, unsigned long end)
-{
-	unsigned long idx = start;
-
-	BUG_ON(start >= end);
-
-	while (idx < end) {
-		if (!!test_bit(idx, bitmap) != expected)
-			return idx;
-		++idx;
-	}
-
-	/* all bits have the expected value */
-	return ~0UL;
-}
-#else /* debugging is disabled */
-static int debugging;
-
-static inline unsigned long verify_bit_range(unsigned long* bitmap,
-	int expected, unsigned long start, unsigned long end)
-{
-	return ~0UL;
-}
-
-#endif /* CONFIG_IOMMU_DEBUG */
-
 static inline int translation_enabled(struct iommu_table *tbl)
 {
 	/* only PHBs with translation enabled have an IOMMU table */
@@ -228,7 +197,6 @@ static void iommu_range_reserve(struct iommu_table *tbl,
 {
 	unsigned long index;
 	unsigned long end;
-	unsigned long badbit;
 	unsigned long flags;
 
 	index = start_addr >> PAGE_SHIFT;
@@ -243,14 +211,6 @@ static void iommu_range_reserve(struct iommu_table *tbl,
 
 	spin_lock_irqsave(&tbl->it_lock, flags);
 
-	badbit = verify_bit_range(tbl->it_map, 0, index, end);
-	if (badbit != ~0UL) {
-		if (printk_ratelimit())
-			printk(KERN_ERR "Calgary: entry already allocated at "
-			       "0x%lx tbl %p dma 0x%lx npages %u\n",
-			       badbit, tbl, start_addr, npages);
-	}
-
 	iommu_area_reserve(tbl->it_map, index, npages);
 
 	spin_unlock_irqrestore(&tbl->it_lock, flags);
@@ -326,7 +286,6 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	unsigned int npages)
 {
 	unsigned long entry;
-	unsigned long badbit;
 	unsigned long badend;
 	unsigned long flags;
 
@@ -346,14 +305,6 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 
 	spin_lock_irqsave(&tbl->it_lock, flags);
 
-	badbit = verify_bit_range(tbl->it_map, 1, entry, entry + npages);
-	if (badbit != ~0UL) {
-		if (printk_ratelimit())
-			printk(KERN_ERR "Calgary: bit is off at 0x%lx "
-			       "tbl %p dma 0x%Lx entry 0x%lx npages %u\n",
-			       badbit, tbl, dma_addr, entry, npages);
-	}
-
 	iommu_area_free(tbl->it_map, entry, npages);
 
 	spin_unlock_irqrestore(&tbl->it_lock, flags);
@@ -1488,9 +1439,8 @@ void __init detect_calgary(void)
 		iommu_detected = 1;
 		calgary_detected = 1;
 		printk(KERN_INFO "PCI-DMA: Calgary IOMMU detected.\n");
-		printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d, "
-		       "CONFIG_IOMMU_DEBUG is %s.\n", specified_table_size,
-		       debugging ? "enabled" : "disabled");
+		printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d\n",
+		       specified_table_size);
 
 		/* swiotlb for devices that aren't behind the Calgary. */
 		if (max_pfn > MAX_DMA32_PFN)
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index b284b58c035c..cfd9f9063896 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -144,48 +144,21 @@ static void flush_gart(void)
 }
 
 #ifdef CONFIG_IOMMU_LEAK
-
-#define SET_LEAK(x)							\
-	do {								\
-		if (iommu_leak_tab)					\
-			iommu_leak_tab[x] = __builtin_return_address(0);\
-	} while (0)
-
-#define CLEAR_LEAK(x)							\
-	do {								\
-		if (iommu_leak_tab)					\
-			iommu_leak_tab[x] = NULL;			\
-	} while (0)
-
 /* Debugging aid for drivers that don't free their IOMMU tables */
-static void **iommu_leak_tab;
 static int leak_trace;
 static int iommu_leak_pages = 20;
 
 static void dump_leak(void)
 {
-	int i;
 	static int dump;
 
-	if (dump || !iommu_leak_tab)
+	if (dump)
 		return;
 	dump = 1;
-	show_stack(NULL, NULL);
 
-	/* Very crude. dump some from the end of the table too */
-	printk(KERN_DEBUG "Dumping %d pages from end of IOMMU:\n",
-	       iommu_leak_pages);
-	for (i = 0; i < iommu_leak_pages; i += 2) {
-		printk(KERN_DEBUG "%lu: ", iommu_pages-i);
-		printk_address((unsigned long) iommu_leak_tab[iommu_pages-i],
-				0);
-		printk(KERN_CONT "%c", (i+1)%2 == 0 ? '\n' : ' ');
-	}
-	printk(KERN_DEBUG "\n");
+	show_stack(NULL, NULL);
+	debug_dma_dump_mappings(NULL);
 }
-#else
-# define SET_LEAK(x)
-# define CLEAR_LEAK(x)
 #endif
 
 static void iommu_full(struct device *dev, size_t size, int dir)
@@ -248,7 +221,6 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 
 	for (i = 0; i < npages; i++) {
 		iommu_gatt_base[iommu_page + i] = GPTE_ENCODE(phys_mem);
-		SET_LEAK(iommu_page + i);
 		phys_mem += PAGE_SIZE;
 	}
 	return iommu_bus_base + iommu_page*PAGE_SIZE + (phys_mem & ~PAGE_MASK);
@@ -294,7 +266,6 @@ static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	npages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
 	for (i = 0; i < npages; i++) {
 		iommu_gatt_base[iommu_page + i] = gart_unmapped_entry;
-		CLEAR_LEAK(iommu_page + i);
 	}
 	free_iommu(iommu_page, npages);
 }
@@ -377,7 +348,6 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start,
 		pages = iommu_num_pages(s->offset, s->length, PAGE_SIZE);
 		while (pages--) {
 			iommu_gatt_base[iommu_page] = GPTE_ENCODE(addr);
-			SET_LEAK(iommu_page);
 			addr += PAGE_SIZE;
 			iommu_page++;
 		}
@@ -688,8 +658,6 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 	agp_gatt_table = gatt;
 
-	enable_gart_translations();
-
 	error = sysdev_class_register(&gart_sysdev_class);
 	if (!error)
 		error = sysdev_register(&device_gart);
@@ -801,11 +769,12 @@ void __init gart_iommu_init(void)
 
 #ifdef CONFIG_IOMMU_LEAK
 	if (leak_trace) {
-		iommu_leak_tab = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
-				  get_order(iommu_pages*sizeof(void *)));
-		if (!iommu_leak_tab)
+		int ret;
+
+		ret = dma_debug_resize_entries(iommu_pages);
+		if (ret)
 			printk(KERN_DEBUG
-			       "PCI-DMA: Cannot allocate leak trace area\n");
+			       "PCI-DMA: Cannot trace all the entries\n");
 	}
 #endif
 
@@ -845,6 +814,14 @@ void __init gart_iommu_init(void)
 	 * the pages as Not-Present:
 	 */
 	wbinvd();
+	
+	/*
+	 * Now all caches are flushed and we can safely enable
+	 * GART hardware.  Doing it early leaves the possibility
+	 * of stale cache entries that can lead to GART PTE
+	 * errors.
+	 */
+	enable_gart_translations();
 
 	/*
 	 * Try to workaround a bug (thanks to BenH):
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 221a3853e268..a1712f2b50f1 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -28,7 +28,7 @@ dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
 	return paddr;
 }
 
-phys_addr_t swiotlb_bus_to_phys(dma_addr_t baddr)
+phys_addr_t swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
 {
 	return baddr;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ca989158e847..3bb2be1649bd 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -8,12 +8,15 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/clockchips.h>
+#include <linux/random.h>
 #include <trace/power.h>
 #include <asm/system.h>
 #include <asm/apic.h>
+#include <asm/syscalls.h>
 #include <asm/idle.h>
 #include <asm/uaccess.h>
 #include <asm/i387.h>
+#include <asm/ds.h>
 
 unsigned long idle_halt;
 EXPORT_SYMBOL(idle_halt);
@@ -45,6 +48,8 @@ void free_thread_xstate(struct task_struct *tsk)
 		kmem_cache_free(task_xstate_cachep, tsk->thread.xstate);
 		tsk->thread.xstate = NULL;
 	}
+
+	WARN(tsk->thread.ds_ctx, "leaking DS context\n");
 }
 
 void free_thread_info(struct thread_info *ti)
@@ -83,8 +88,6 @@ void exit_thread(void)
 		put_cpu();
 		kfree(bp);
 	}
-
-	ds_exit_thread(current);
 }
 
 void flush_thread(void)
@@ -613,3 +616,16 @@ static int __init idle_setup(char *str)
 }
 early_param("idle", idle_setup);
 
+unsigned long arch_align_stack(unsigned long sp)
+{
+	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+		sp -= get_random_int() % 8192;
+	return sp & ~0xf;
+}
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+	unsigned long range_end = mm->brk + 0x02000000;
+	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
+}
+
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 76f8f84043a2..59f4524984af 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -9,8 +9,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <stdarg.h>
-
 #include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
@@ -33,7 +31,6 @@
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>
 #include <linux/personality.h>
 #include <linux/tick.h>
 #include <linux/percpu.h>
@@ -290,7 +287,8 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		p->thread.io_bitmap_max = 0;
 	}
 
-	ds_copy_thread(p, current);
+	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
+	p->thread.ds_ctx = NULL;
 
 	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
 	p->thread.debugctlmsr = 0;
@@ -407,7 +405,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * done before math_state_restore, so the TS bit is up
 	 * to date.
 	 */
-	arch_leave_lazy_cpu_mode();
+	arch_end_context_switch(next_p);
 
 	/* If the task has used fpu the last 5 timeslices, just do a full
 	 * restore of the math state immediately to avoid the trap; the
@@ -497,15 +495,3 @@ unsigned long get_wchan(struct task_struct *p)
 	return 0;
 }
 
-unsigned long arch_align_stack(unsigned long sp)
-{
-	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
-		sp -= get_random_int() % 8192;
-	return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	unsigned long range_end = mm->brk + 0x02000000;
-	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
-}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b751a41392b1..ebefb5407b9d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -14,8 +14,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <stdarg.h>
-
 #include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
@@ -32,7 +30,6 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>
 #include <linux/notifier.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
@@ -335,7 +332,8 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 			goto out;
 	}
 
-	ds_copy_thread(p, me);
+	clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
+	p->thread.ds_ctx = NULL;
 
 	clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
 	p->thread.debugctlmsr = 0;
@@ -428,7 +426,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * done before math_state_restore, so the TS bit is up
 	 * to date.
 	 */
-	arch_leave_lazy_cpu_mode();
+	arch_end_context_switch(next_p);
 
 	/*
 	 * Switch FS and GS.
@@ -660,15 +658,3 @@ long sys_arch_prctl(int code, unsigned long addr)
 	return do_arch_prctl(current, code, addr);
 }
 
-unsigned long arch_align_stack(unsigned long sp)
-{
-	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
-		sp -= get_random_int() % 8192;
-	return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	unsigned long range_end = mm->brk + 0x02000000;
-	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
-}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 23b7c8f017e2..09ecbde91c13 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
 #include <linux/audit.h>
 #include <linux/seccomp.h>
 #include <linux/signal.h>
+#include <linux/workqueue.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -578,17 +579,130 @@ static int ioperm_get(struct task_struct *target,
 }
 
 #ifdef CONFIG_X86_PTRACE_BTS
+/*
+ * A branch trace store context.
+ *
+ * Contexts may only be installed by ptrace_bts_config() and only for
+ * ptraced tasks.
+ *
+ * Contexts are destroyed when the tracee is detached from the tracer.
+ * The actual destruction work requires interrupts enabled, so the
+ * work is deferred and will be scheduled during __ptrace_unlink().
+ *
+ * Contexts hold an additional task_struct reference on the traced
+ * task, as well as a reference on the tracer's mm.
+ *
+ * Ptrace already holds a task_struct for the duration of ptrace operations,
+ * but since destruction is deferred, it may be executed after both
+ * tracer and tracee exited.
+ */
+struct bts_context {
+	/* The branch trace handle. */
+	struct bts_tracer	*tracer;
+
+	/* The buffer used to store the branch trace and its size. */
+	void			*buffer;
+	unsigned int		size;
+
+	/* The mm that paid for the above buffer. */
+	struct mm_struct	*mm;
+
+	/* The task this context belongs to. */
+	struct task_struct	*task;
+
+	/* The signal to send on a bts buffer overflow. */
+	unsigned int		bts_ovfl_signal;
+
+	/* The work struct to destroy a context. */
+	struct work_struct	work;
+};
+
+static int alloc_bts_buffer(struct bts_context *context, unsigned int size)
+{
+	void *buffer = NULL;
+	int err = -ENOMEM;
+
+	err = account_locked_memory(current->mm, current->signal->rlim, size);
+	if (err < 0)
+		return err;
+
+	buffer = kzalloc(size, GFP_KERNEL);
+	if (!buffer)
+		goto out_refund;
+
+	context->buffer = buffer;
+	context->size = size;
+	context->mm = get_task_mm(current);
+
+	return 0;
+
+ out_refund:
+	refund_locked_memory(current->mm, size);
+	return err;
+}
+
+static inline void free_bts_buffer(struct bts_context *context)
+{
+	if (!context->buffer)
+		return;
+
+	kfree(context->buffer);
+	context->buffer = NULL;
+
+	refund_locked_memory(context->mm, context->size);
+	context->size = 0;
+
+	mmput(context->mm);
+	context->mm = NULL;
+}
+
+static void free_bts_context_work(struct work_struct *w)
+{
+	struct bts_context *context;
+
+	context = container_of(w, struct bts_context, work);
+
+	ds_release_bts(context->tracer);
+	put_task_struct(context->task);
+	free_bts_buffer(context);
+	kfree(context);
+}
+
+static inline void free_bts_context(struct bts_context *context)
+{
+	INIT_WORK(&context->work, free_bts_context_work);
+	schedule_work(&context->work);
+}
+
+static inline struct bts_context *alloc_bts_context(struct task_struct *task)
+{
+	struct bts_context *context = kzalloc(sizeof(*context), GFP_KERNEL);
+	if (context) {
+		context->task = task;
+		task->bts = context;
+
+		get_task_struct(task);
+	}
+
+	return context;
+}
+
 static int ptrace_bts_read_record(struct task_struct *child, size_t index,
 				  struct bts_struct __user *out)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 	struct bts_struct bts;
 	const unsigned char *at;
 	int error;
 
-	trace = ds_read_bts(child->bts);
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	at = trace->ds.top - ((index + 1) * trace->ds.size);
 	if ((void *)at < trace->ds.begin)
@@ -597,7 +711,7 @@ static int ptrace_bts_read_record(struct task_struct *child, size_t index,
 	if (!trace->read)
 		return -EOPNOTSUPP;
 
-	error = trace->read(child->bts, at, &bts);
+	error = trace->read(context->tracer, at, &bts);
 	if (error < 0)
 		return error;
 
@@ -611,13 +725,18 @@ static int ptrace_bts_drain(struct task_struct *child,
 			    long size,
 			    struct bts_struct __user *out)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 	const unsigned char *at;
 	int error, drained = 0;
 
-	trace = ds_read_bts(child->bts);
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	if (!trace->read)
 		return -EOPNOTSUPP;
@@ -628,9 +747,8 @@ static int ptrace_bts_drain(struct task_struct *child,
 	for (at = trace->ds.begin; (void *)at < trace->ds.top;
 	     out++, drained++, at += trace->ds.size) {
 		struct bts_struct bts;
-		int error;
 
-		error = trace->read(child->bts, at, &bts);
+		error = trace->read(context->tracer, at, &bts);
 		if (error < 0)
 			return error;
 
@@ -640,35 +758,18 @@ static int ptrace_bts_drain(struct task_struct *child,
 
 	memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
 
-	error = ds_reset_bts(child->bts);
+	error = ds_reset_bts(context->tracer);
 	if (error < 0)
 		return error;
 
 	return drained;
 }
 
-static int ptrace_bts_allocate_buffer(struct task_struct *child, size_t size)
-{
-	child->bts_buffer = alloc_locked_buffer(size);
-	if (!child->bts_buffer)
-		return -ENOMEM;
-
-	child->bts_size = size;
-
-	return 0;
-}
-
-static void ptrace_bts_free_buffer(struct task_struct *child)
-{
-	free_locked_buffer(child->bts_buffer, child->bts_size);
-	child->bts_buffer = NULL;
-	child->bts_size = 0;
-}
-
 static int ptrace_bts_config(struct task_struct *child,
 			     long cfg_size,
 			     const struct ptrace_bts_config __user *ucfg)
 {
+	struct bts_context *context;
 	struct ptrace_bts_config cfg;
 	unsigned int flags = 0;
 
@@ -678,28 +779,33 @@ static int ptrace_bts_config(struct task_struct *child,
 	if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
 		return -EFAULT;
 
-	if (child->bts) {
-		ds_release_bts(child->bts);
-		child->bts = NULL;
-	}
+	context = child->bts;
+	if (!context)
+		context = alloc_bts_context(child);
+	if (!context)
+		return -ENOMEM;
 
 	if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
 		if (!cfg.signal)
 			return -EINVAL;
 
-		child->thread.bts_ovfl_signal = cfg.signal;
 		return -EOPNOTSUPP;
+		context->bts_ovfl_signal = cfg.signal;
 	}
 
-	if ((cfg.flags & PTRACE_BTS_O_ALLOC) &&
-	    (cfg.size != child->bts_size)) {
-		int error;
+	ds_release_bts(context->tracer);
+	context->tracer = NULL;
 
-		ptrace_bts_free_buffer(child);
+	if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) {
+		int err;
 
-		error = ptrace_bts_allocate_buffer(child, cfg.size);
-		if (error < 0)
-			return error;
+		free_bts_buffer(context);
+		if (!cfg.size)
+			return 0;
+
+		err = alloc_bts_buffer(context, cfg.size);
+		if (err < 0)
+			return err;
 	}
 
 	if (cfg.flags & PTRACE_BTS_O_TRACE)
@@ -708,15 +814,14 @@ static int ptrace_bts_config(struct task_struct *child,
 	if (cfg.flags & PTRACE_BTS_O_SCHED)
 		flags |= BTS_TIMESTAMPS;
 
-	child->bts = ds_request_bts(child, child->bts_buffer, child->bts_size,
-				    /* ovfl = */ NULL, /* th = */ (size_t)-1,
-				    flags);
-	if (IS_ERR(child->bts)) {
-		int error = PTR_ERR(child->bts);
-
-		ptrace_bts_free_buffer(child);
-		child->bts = NULL;
+	context->tracer =
+		ds_request_bts_task(child, context->buffer, context->size,
+				    NULL, (size_t)-1, flags);
+	if (unlikely(IS_ERR(context->tracer))) {
+		int error = PTR_ERR(context->tracer);
 
+		free_bts_buffer(context);
+		context->tracer = NULL;
 		return error;
 	}
 
@@ -727,20 +832,25 @@ static int ptrace_bts_status(struct task_struct *child,
 			     long cfg_size,
 			     struct ptrace_bts_config __user *ucfg)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 	struct ptrace_bts_config cfg;
 
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
 	if (cfg_size < sizeof(cfg))
 		return -EIO;
 
-	trace = ds_read_bts(child->bts);
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	memset(&cfg, 0, sizeof(cfg));
-	cfg.size = trace->ds.end - trace->ds.begin;
-	cfg.signal = child->thread.bts_ovfl_signal;
-	cfg.bts_size = sizeof(struct bts_struct);
+	cfg.size	= trace->ds.end - trace->ds.begin;
+	cfg.signal	= context->bts_ovfl_signal;
+	cfg.bts_size	= sizeof(struct bts_struct);
 
 	if (cfg.signal)
 		cfg.flags |= PTRACE_BTS_O_SIGNAL;
@@ -759,80 +869,51 @@ static int ptrace_bts_status(struct task_struct *child,
 
 static int ptrace_bts_clear(struct task_struct *child)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 
-	trace = ds_read_bts(child->bts);
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
 
-	return ds_reset_bts(child->bts);
+	return ds_reset_bts(context->tracer);
 }
 
 static int ptrace_bts_size(struct task_struct *child)
 {
+	struct bts_context *context;
 	const struct bts_trace *trace;
 
-	trace = ds_read_bts(child->bts);
+	context = child->bts;
+	if (!context)
+		return -ESRCH;
+
+	trace = ds_read_bts(context->tracer);
 	if (!trace)
-		return -EPERM;
+		return -ESRCH;
 
 	return (trace->ds.top - trace->ds.begin) / trace->ds.size;
 }
 
-static void ptrace_bts_fork(struct task_struct *tsk)
-{
-	tsk->bts = NULL;
-	tsk->bts_buffer = NULL;
-	tsk->bts_size = 0;
-	tsk->thread.bts_ovfl_signal = 0;
-}
-
-static void ptrace_bts_untrace(struct task_struct *child)
+/*
+ * Called from __ptrace_unlink() after the child has been moved back
+ * to its original parent.
+ */
+void ptrace_bts_untrace(struct task_struct *child)
 {
 	if (unlikely(child->bts)) {
-		ds_release_bts(child->bts);
+		free_bts_context(child->bts);
 		child->bts = NULL;
-
-		/* We cannot update total_vm and locked_vm since
-		   child's mm is already gone. But we can reclaim the
-		   memory. */
-		kfree(child->bts_buffer);
-		child->bts_buffer = NULL;
-		child->bts_size = 0;
 	}
 }
-
-static void ptrace_bts_detach(struct task_struct *child)
-{
-	/*
-	 * Ptrace_detach() races with ptrace_untrace() in case
-	 * the child dies and is reaped by another thread.
-	 *
-	 * We only do the memory accounting at this point and
-	 * leave the buffer deallocation and the bts tracer
-	 * release to ptrace_bts_untrace() which will be called
-	 * later on with tasklist_lock held.
-	 */
-	release_locked_buffer(child->bts_buffer, child->bts_size);
-}
-#else
-static inline void ptrace_bts_fork(struct task_struct *tsk) {}
-static inline void ptrace_bts_detach(struct task_struct *child) {}
-static inline void ptrace_bts_untrace(struct task_struct *child) {}
 #endif /* CONFIG_X86_PTRACE_BTS */
 
-void x86_ptrace_fork(struct task_struct *child, unsigned long clone_flags)
-{
-	ptrace_bts_fork(child);
-}
-
-void x86_ptrace_untrace(struct task_struct *child)
-{
-	ptrace_bts_untrace(child);
-}
-
 /*
  * Called by kernel/ptrace.c when detaching..
  *
@@ -844,7 +925,6 @@ void ptrace_disable(struct task_struct *child)
 #ifdef TIF_SYSCALL_EMU
 	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
 #endif
-	ptrace_bts_detach(child);
 }
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 7563b31b4f03..af71d06624bf 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -491,5 +491,42 @@ void force_hpet_resume(void)
 		break;
 	}
 }
-
+#endif
+
+#if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
+/* Set correct numa_node information for AMD NB functions */
+static void __init quirk_amd_nb_node(struct pci_dev *dev)
+{
+	struct pci_dev *nb_ht;
+	unsigned int devfn;
+	u32 val;
+
+	devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0);
+	nb_ht = pci_get_slot(dev->bus, devfn);
+	if (!nb_ht)
+		return;
+
+	pci_read_config_dword(nb_ht, 0x60, &val);
+	set_dev_node(&dev->dev, val & 7);
+	pci_dev_put(dev);
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MEMCTL,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_HT,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MAP,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_DRAM,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_LINK,
+			quirk_amd_nb_node);
 #endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 667188e0b5a0..d2d1ce8170f0 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -192,6 +192,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
 		},
 	},
+	{   /* Handle problems with rebooting on Dell Optiplex 360 with 0T656F */
+		.callback = set_bios_reboot,
+		.ident = "Dell OptiPlex 360",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 360"),
+			DMI_MATCH(DMI_BOARD_NAME, "0T656F"),
+		},
+	},
 	{	/* Handle problems with rebooting on Dell 2400's */
 		.callback = set_bios_reboot,
 		.ident = "Dell PowerEdge 2400",
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b4158439bf63..d1c636bf31a7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -112,6 +112,14 @@
 #define ARCH_SETUP
 #endif
 
+/*
+ * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
+ * The direct mapping extends to max_pfn_mapped, so that we can directly access
+ * apertures, ACPI and other tables without having to play with fixmaps.
+ */
+unsigned long max_low_pfn_mapped;
+unsigned long max_pfn_mapped;
+
 RESERVE_BRK(dmi_alloc, 65536);
 
 unsigned int boot_cpu_id __read_mostly;
@@ -214,8 +222,8 @@ unsigned long mmu_cr4_features;
 unsigned long mmu_cr4_features = X86_CR4_PAE;
 #endif
 
-/* Boot loader ID as an integer, for the benefit of proc_dointvec */
-int bootloader_type;
+/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
+int bootloader_type, bootloader_version;
 
 /*
  * Setup options
@@ -706,6 +714,12 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	saved_video_mode = boot_params.hdr.vid_mode;
 	bootloader_type = boot_params.hdr.type_of_loader;
+	if ((bootloader_type >> 4) == 0xe) {
+		bootloader_type &= 0xf;
+		bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
+	}
+	bootloader_version  = bootloader_type & 0xf;
+	bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
 
 #ifdef CONFIG_BLK_DEV_RAM
 	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
@@ -854,12 +868,16 @@ void __init setup_arch(char **cmdline_p)
 		max_low_pfn = max_pfn;
 
 	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
+	max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
 #endif
 
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
 	setup_bios_corruption_check();
 #endif
 
+	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
+			max_pfn_mapped<<PAGE_SHIFT);
+
 	reserve_brk();
 
 	/* max_pfn_mapped is updated here */
@@ -996,24 +1014,6 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_X86_32
 
-/**
- * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
- *
- * Description:
- *	Perform any necessary interrupt initialisation prior to setting up
- *	the "ordinary" interrupt call gates.  For legacy reasons, the ISA
- *	interrupts should be initialised here if the machine emulates a PC
- *	in any way.
- **/
-void __init x86_quirk_pre_intr_init(void)
-{
-	if (x86_quirks->arch_pre_intr_init) {
-		if (x86_quirks->arch_pre_intr_init())
-			return;
-	}
-	init_ISA_irqs();
-}
-
 /**
  * x86_quirk_intr_init - post gate setup interrupt initialisation
  *
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 8f0e13be36b3..9c3f0823e6aa 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -425,6 +425,14 @@ void __init setup_per_cpu_areas(void)
 	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
 #endif
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+	/*
+	 * make sure boot cpu node_number is right, when boot cpu is on the
+	 * node that doesn't have mem installed
+	 */
+	per_cpu(node_number, boot_cpu_id) = cpu_to_node(boot_cpu_id);
+#endif
+
 	/* Setup node to cpumask map */
 	setup_node_to_cpumask_map();
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 14425166b8e3..0a813b17b172 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -6,7 +6,6 @@
  *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
  *  2000-2002   x86-64 support by Andi Kleen
  */
-
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 13f33ea8ccaa..28f5fb495a66 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -172,6 +172,9 @@ void smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	inc_irq_stat(irq_resched_count);
+	/*
+	 * KVM uses this interrupt to force a cpu out of guest mode
+	 */
 }
 
 void smp_call_function_interrupt(struct pt_regs *regs)
@@ -193,19 +196,19 @@ void smp_call_function_single_interrupt(struct pt_regs *regs)
 }
 
 struct smp_ops smp_ops = {
-	.smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
-	.smp_prepare_cpus = native_smp_prepare_cpus,
-	.smp_cpus_done = native_smp_cpus_done,
+	.smp_prepare_boot_cpu	= native_smp_prepare_boot_cpu,
+	.smp_prepare_cpus	= native_smp_prepare_cpus,
+	.smp_cpus_done		= native_smp_cpus_done,
 
-	.smp_send_stop = native_smp_send_stop,
-	.smp_send_reschedule = native_smp_send_reschedule,
+	.smp_send_stop		= native_smp_send_stop,
+	.smp_send_reschedule	= native_smp_send_reschedule,
 
-	.cpu_up = native_cpu_up,
-	.cpu_die = native_cpu_die,
-	.cpu_disable = native_cpu_disable,
-	.play_dead = native_play_dead,
+	.cpu_up			= native_cpu_up,
+	.cpu_die		= native_cpu_die,
+	.cpu_disable		= native_cpu_disable,
+	.play_dead		= native_play_dead,
 
-	.send_call_func_ipi = native_send_call_func_ipi,
+	.send_call_func_ipi	= native_send_call_func_ipi,
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 58d24ef917d8..7c80007ea5f7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -504,7 +504,7 @@ void __inquire_remote_apic(int apicid)
  * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
  * won't ... remember to clear down the APIC, etc later.
  */
-int __devinit
+int __cpuinit
 wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
 {
 	unsigned long send_status, accept_status = 0;
@@ -538,7 +538,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
 	return (send_status | accept_status);
 }
 
-int __devinit
+static int __cpuinit
 wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 {
 	unsigned long send_status, accept_status = 0;
@@ -822,10 +822,12 @@ do_rest:
 	/* mark "stuck" area as not stuck */
 	*((volatile unsigned long *)trampoline_base) = 0;
 
-	/*
-	 * Cleanup possible dangling ends...
-	 */
-	smpboot_restore_warm_reset_vector();
+	if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+		/*
+		 * Cleanup possible dangling ends...
+		 */
+		smpboot_restore_warm_reset_vector();
+	}
 
 	return boot_error;
 }
@@ -990,10 +992,12 @@ static int __init smp_sanity_check(unsigned max_cpus)
 	 */
 	if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
 	    !cpu_has_apic) {
-		printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
-			boot_cpu_physical_apicid);
-		printk(KERN_ERR "... forcing use of dummy APIC emulation."
+		if (!disable_apic) {
+			pr_err("BIOS bug, local APIC #%d not detected!...\n",
+				boot_cpu_physical_apicid);
+			pr_err("... forcing use of dummy APIC emulation."
 				"(tell your hw vendor)\n");
+		}
 		smpboot_clear_io_apic();
 		arch_disable_smp_support();
 		return -1;
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index f7bddc2e37d1..4aaf7e48394f 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -20,7 +20,7 @@ save_stack_warning_symbol(void *data, char *msg, unsigned long symbol)
 
 static int save_stack_stack(void *data, char *name)
 {
-	return -1;
+	return 0;
 }
 
 static void save_stack_address(void *data, unsigned long addr, int reliable)
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index ff5c8736b491..d51321ddafda 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -334,3 +334,5 @@ ENTRY(sys_call_table)
 	.long sys_inotify_init1
 	.long sys_preadv
 	.long sys_pwritev
+	.long sys_rt_tgsigqueueinfo	/* 335 */
+	.long sys_perf_counter_open
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 8c7b03b0cfcb..124d40c575df 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -715,7 +715,12 @@ uv_activation_descriptor_init(int node, int pnode)
 	struct bau_desc *adp;
 	struct bau_desc *ad2;
 
-	adp = (struct bau_desc *)kmalloc_node(16384, GFP_KERNEL, node);
+	/*
+	 * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR)
+	 * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per blade
+	 */
+	adp = (struct bau_desc *)kmalloc_node(sizeof(struct bau_desc)*
+		UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node);
 	BUG_ON(!adp);
 
 	pa = uv_gpa(adp); /* need the real nasid*/
@@ -729,7 +734,13 @@ uv_activation_descriptor_init(int node, int pnode)
 				      (n << UV_DESC_BASE_PNODE_SHIFT | m));
 	}
 
-	for (i = 0, ad2 = adp; i < UV_ACTIVATION_DESCRIPTOR_SIZE; i++, ad2++) {
+	/*
+	 * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
+	 * cpu even though we only use the first one; one descriptor can
+	 * describe a broadcast to 256 nodes.
+	 */
+	for (i = 0, ad2 = adp; i < (UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR);
+		i++, ad2++) {
 		memset(ad2, 0, sizeof(struct bau_desc));
 		ad2->header.sw_ack_flag = 1;
 		/*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index a1d288327ff0..07d60c870ce2 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -839,9 +839,6 @@ asmlinkage void math_state_restore(void)
 	}
 
 	clts();				/* Allow maths ops (or we recurse) */
-#ifdef CONFIG_X86_32
-	restore_fpu(tsk);
-#else
 	/*
 	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
 	 */
@@ -850,7 +847,7 @@ asmlinkage void math_state_restore(void)
 		force_sig(SIGSEGV, tsk);
 		return;
 	}
-#endif
+
 	thread->status |= TS_USEDFPU;	/* So we fnsave on switch_to() */
 	tsk->fpu_counter++;
 }
@@ -945,8 +942,13 @@ void __init trap_init(void)
 #endif
 	set_intr_gate(19, &simd_coprocessor_error);
 
+	/* Reserve all the builtin and the syscall vector: */
+	for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
+		set_bit(i, used_vectors);
+
 #ifdef CONFIG_IA32_EMULATION
 	set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
+	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
 #endif
 
 #ifdef CONFIG_X86_32
@@ -963,17 +965,9 @@ void __init trap_init(void)
 	}
 
 	set_system_trap_gate(SYSCALL_VECTOR, &system_call);
-#endif
-
-	/* Reserve all the builtin and the syscall vector: */
-	for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
-		set_bit(i, used_vectors);
-
-#ifdef CONFIG_X86_64
-	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
-#else
 	set_bit(SYSCALL_VECTOR, used_vectors);
 #endif
+
 	/*
 	 * Should be a barrier for any external CPU state:
 	 */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index d57de05dc430..3e1c057e98fe 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -384,13 +384,13 @@ unsigned long native_calibrate_tsc(void)
 {
 	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags, latch, ms, fast_calibrate, tsc_khz;
+	unsigned long flags, latch, ms, fast_calibrate, hv_tsc_khz;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
-	tsc_khz = get_hypervisor_tsc_freq();
-	if (tsc_khz) {
+	hv_tsc_khz = get_hypervisor_tsc_freq();
+	if (hv_tsc_khz) {
 		printk(KERN_INFO "TSC: Frequency read from the hypervisor\n");
-		return tsc_khz;
+		return hv_tsc_khz;
 	}
 
 	local_irq_save(flags);
@@ -710,7 +710,16 @@ static cycle_t read_tsc(struct clocksource *cs)
 #ifdef CONFIG_X86_64
 static cycle_t __vsyscall_fn vread_tsc(void)
 {
-	cycle_t ret = (cycle_t)vget_cycles();
+	cycle_t ret;
+
+	/*
+	 * Surround the RDTSC by barriers, to make sure it's not
+	 * speculated to outside the seqlock critical section and
+	 * does not cause time warps:
+	 */
+	rdtsc_barrier();
+	ret = (cycle_t)vget_cycles();
+	rdtsc_barrier();
 
 	return ret >= __vsyscall_gtod_data.clock.cycle_last ?
 		ret : __vsyscall_gtod_data.clock.cycle_last;
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index bf36328f6ef9..027b5b498993 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -34,6 +34,7 @@ static __cpuinitdata atomic_t stop_count;
  * of a critical section, to be able to prove TSC time-warps:
  */
 static __cpuinitdata raw_spinlock_t sync_lock = __RAW_SPIN_LOCK_UNLOCKED;
+
 static __cpuinitdata cycles_t last_tsc;
 static __cpuinitdata cycles_t max_warp;
 static __cpuinitdata int nr_warps;
@@ -113,13 +114,12 @@ void __cpuinit check_tsc_sync_source(int cpu)
 		return;
 
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
-		printk(KERN_INFO
-		       "Skipping synchronization checks as TSC is reliable.\n");
+		pr_info("Skipping synchronization checks as TSC is reliable.\n");
 		return;
 	}
 
-	printk(KERN_INFO "checking TSC synchronization [CPU#%d -> CPU#%d]:",
-			  smp_processor_id(), cpu);
+	pr_info("checking TSC synchronization [CPU#%d -> CPU#%d]:",
+		smp_processor_id(), cpu);
 
 	/*
 	 * Reset it - in case this is a second bootup:
@@ -143,8 +143,8 @@ void __cpuinit check_tsc_sync_source(int cpu)
 
 	if (nr_warps) {
 		printk("\n");
-		printk(KERN_WARNING "Measured %Ld cycles TSC warp between CPUs,"
-				    " turning off TSC clock.\n", max_warp);
+		pr_warning("Measured %Ld cycles TSC warp between CPUs, "
+			   "turning off TSC clock.\n", max_warp);
 		mark_tsc_unstable("check_tsc_sync_source failed");
 	} else {
 		printk(" passed.\n");
@@ -195,5 +195,3 @@ void __cpuinit check_tsc_sync_target(void)
 	while (atomic_read(&stop_count) != cpus)
 		cpu_relax();
 }
-#undef NR_LOOPS
-
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index d7ac84e7fc1c..9c4e62539058 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -287,10 +287,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
 	info->regs.pt.ds = 0;
 	info->regs.pt.es = 0;
 	info->regs.pt.fs = 0;
-
-/* we are clearing gs later just before "jmp resume_userspace",
- * because it is not saved/restored.
- */
+#ifndef CONFIG_X86_32_LAZY_GS
+	info->regs.pt.gs = 0;
+#endif
 
 /*
  * The flags register is also special: we cannot trust that the user
@@ -318,9 +317,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
 	}
 
 /*
- * Save old state, set default return value (%ax) to 0
+ * Save old state, set default return value (%ax) to 0 (VM86_SIGNAL)
  */
-	info->regs32->ax = 0;
+	info->regs32->ax = VM86_SIGNAL;
 	tsk->thread.saved_sp0 = tsk->thread.sp0;
 	tsk->thread.saved_fs = info->regs32->fs;
 	tsk->thread.saved_gs = get_user_gs(info->regs32);
@@ -343,7 +342,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
 	__asm__ __volatile__(
 		"movl %0,%%esp\n\t"
 		"movl %1,%%ebp\n\t"
+#ifdef CONFIG_X86_32_LAZY_GS
 		"mov  %2, %%gs\n\t"
+#endif
 		"jmp resume_userspace"
 		: /* no outputs */
 		:"r" (&info->regs), "r" (task_thread_info(tsk)), "r" (0));
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 95deb9f2211e..b263423fbe2a 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -462,22 +462,28 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 }
 #endif
 
-static void vmi_enter_lazy_cpu(void)
+static void vmi_start_context_switch(struct task_struct *prev)
 {
-	paravirt_enter_lazy_cpu();
+	paravirt_start_context_switch(prev);
 	vmi_ops.set_lazy_mode(2);
 }
 
+static void vmi_end_context_switch(struct task_struct *next)
+{
+	vmi_ops.set_lazy_mode(0);
+	paravirt_end_context_switch(next);
+}
+
 static void vmi_enter_lazy_mmu(void)
 {
 	paravirt_enter_lazy_mmu();
 	vmi_ops.set_lazy_mode(1);
 }
 
-static void vmi_leave_lazy(void)
+static void vmi_leave_lazy_mmu(void)
 {
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
 	vmi_ops.set_lazy_mode(0);
+	paravirt_leave_lazy_mmu();
 }
 
 static inline int __init check_vmi_rom(struct vrom_header *rom)
@@ -711,14 +717,14 @@ static inline int __init activate_vmi(void)
 	para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
 	para_fill(pv_cpu_ops.io_delay, IODelay);
 
-	para_wrap(pv_cpu_ops.lazy_mode.enter, vmi_enter_lazy_cpu,
+	para_wrap(pv_cpu_ops.start_context_switch, vmi_start_context_switch,
 		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy,
+	para_wrap(pv_cpu_ops.end_context_switch, vmi_end_context_switch,
 		  set_lazy_mode, SetLazyMode);
 
 	para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
 		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy,
+	para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy_mmu,
 		  set_lazy_mode, SetLazyMode);
 
 	/* user and kernel flush are just handled with different flags to FlushTLB */
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 849ee611f013..4c85b2e2bb65 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -1,5 +1,431 @@
+/*
+ * ld script for the x86 kernel
+ *
+ * Historic 32-bit version written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *
+ * Modernisation, unification and other changes and fixes:
+ *   Copyright (C) 2007-2009  Sam Ravnborg <sam@ravnborg.org>
+ *
+ *
+ * Don't define absolute symbols until and unless you know that symbol
+ * value is should remain constant even if kernel image is relocated
+ * at run time. Absolute symbols are not relocated. If symbol value should
+ * change if kernel is relocated, make the symbol section relative and
+ * put it inside the section definition.
+ */
+
 #ifdef CONFIG_X86_32
-# include "vmlinux_32.lds.S"
+#define LOAD_OFFSET __PAGE_OFFSET
 #else
-# include "vmlinux_64.lds.S"
+#define LOAD_OFFSET __START_KERNEL_map
 #endif
+
+#include <asm-generic/vmlinux.lds.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page_types.h>
+#include <asm/cache.h>
+#include <asm/boot.h>
+
+#undef i386     /* in case the preprocessor is a 32bit one */
+
+OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
+
+#ifdef CONFIG_X86_32
+OUTPUT_ARCH(i386)
+ENTRY(phys_startup_32)
+jiffies = jiffies_64;
+#else
+OUTPUT_ARCH(i386:x86-64)
+ENTRY(phys_startup_64)
+jiffies_64 = jiffies;
+#endif
+
+PHDRS {
+	text PT_LOAD FLAGS(5);          /* R_E */
+	data PT_LOAD FLAGS(7);          /* RWE */
+#ifdef CONFIG_X86_64
+	user PT_LOAD FLAGS(7);          /* RWE */
+	data.init PT_LOAD FLAGS(7);     /* RWE */
+#ifdef CONFIG_SMP
+	percpu PT_LOAD FLAGS(7);        /* RWE */
+#endif
+	data.init2 PT_LOAD FLAGS(7);    /* RWE */
+#endif
+	note PT_NOTE FLAGS(0);          /* ___ */
+}
+
+SECTIONS
+{
+#ifdef CONFIG_X86_32
+        . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
+        phys_startup_32 = startup_32 - LOAD_OFFSET;
+#else
+        . = __START_KERNEL;
+        phys_startup_64 = startup_64 - LOAD_OFFSET;
+#endif
+
+	/* Text and read-only data */
+
+	/* bootstrapping code */
+	.text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
+		_text = .;
+		*(.text.head)
+	} :text = 0x9090
+
+	/* The rest of the text */
+	.text :  AT(ADDR(.text) - LOAD_OFFSET) {
+#ifdef CONFIG_X86_32
+		/* not really needed, already page aligned */
+		. = ALIGN(PAGE_SIZE);
+		*(.text.page_aligned)
+#endif
+		. = ALIGN(8);
+		_stext = .;
+		TEXT_TEXT
+		SCHED_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		IRQENTRY_TEXT
+		*(.fixup)
+		*(.gnu.warning)
+		/* End of text section */
+		_etext = .;
+	} :text = 0x9090
+
+	NOTES :text :note
+
+	/* Exception table */
+	. = ALIGN(16);
+	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
+		__start___ex_table = .;
+		*(__ex_table)
+		__stop___ex_table = .;
+	} :text = 0x9090
+
+	RODATA
+
+	/* Data */
+	. = ALIGN(PAGE_SIZE);
+	.data : AT(ADDR(.data) - LOAD_OFFSET) {
+		DATA_DATA
+		CONSTRUCTORS
+
+#ifdef CONFIG_X86_64
+		/* End of data section */
+		_edata = .;
+#endif
+	} :data
+
+#ifdef CONFIG_X86_32
+	/* 32 bit has nosave before _edata */
+	. = ALIGN(PAGE_SIZE);
+	.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+		__nosave_begin = .;
+		*(.data.nosave)
+		. = ALIGN(PAGE_SIZE);
+		__nosave_end = .;
+	}
+#endif
+
+	. = ALIGN(PAGE_SIZE);
+	.data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
+		*(.data.page_aligned)
+		*(.data.idt)
+	}
+
+#ifdef CONFIG_X86_32
+	. = ALIGN(32);
+#else
+	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+#endif
+	.data.cacheline_aligned :
+		AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
+		*(.data.cacheline_aligned)
+	}
+
+	/* rarely changed data like cpu maps */
+#ifdef CONFIG_X86_32
+	. = ALIGN(32);
+#else
+	. = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
+#endif
+	.data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
+		*(.data.read_mostly)
+
+#ifdef CONFIG_X86_32
+		/* End of data section */
+		_edata = .;
+#endif
+	}
+
+#ifdef CONFIG_X86_64
+
+#define VSYSCALL_ADDR (-10*1024*1024)
+#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + \
+                            SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + \
+                            SIZEOF(.data.read_mostly) + 4095) & ~(4095))
+
+#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
+#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
+
+#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
+#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
+
+	. = VSYSCALL_ADDR;
+	.vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) {
+		*(.vsyscall_0)
+	} :user
+
+	__vsyscall_0 = VSYSCALL_VIRT_ADDR;
+
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	.vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
+		*(.vsyscall_fn)
+	}
+
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	.vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) {
+		*(.vsyscall_gtod_data)
+	}
+
+	vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
+	.vsyscall_clock : AT(VLOAD(.vsyscall_clock)) {
+		*(.vsyscall_clock)
+	}
+	vsyscall_clock = VVIRT(.vsyscall_clock);
+
+
+	.vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) {
+		*(.vsyscall_1)
+	}
+	.vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2)) {
+		*(.vsyscall_2)
+	}
+
+	.vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) {
+		*(.vgetcpu_mode)
+	}
+	vgetcpu_mode = VVIRT(.vgetcpu_mode);
+
+	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	.jiffies : AT(VLOAD(.jiffies)) {
+		*(.jiffies)
+	}
+	jiffies = VVIRT(.jiffies);
+
+	.vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) {
+		*(.vsyscall_3)
+	}
+
+	. = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
+
+#undef VSYSCALL_ADDR
+#undef VSYSCALL_PHYS_ADDR
+#undef VSYSCALL_VIRT_ADDR
+#undef VLOAD_OFFSET
+#undef VLOAD
+#undef VVIRT_OFFSET
+#undef VVIRT
+
+#endif /* CONFIG_X86_64 */
+
+	/* init_task */
+	. = ALIGN(THREAD_SIZE);
+	.data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
+		*(.data.init_task)
+	}
+#ifdef CONFIG_X86_64
+	 :data.init
+#endif
+
+	/*
+	 * smp_locks might be freed after init
+	 * start/end must be page aligned
+	 */
+	. = ALIGN(PAGE_SIZE);
+	.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
+		__smp_locks = .;
+		*(.smp_locks)
+		__smp_locks_end = .;
+		. = ALIGN(PAGE_SIZE);
+	}
+
+	/* Init code and data - will be freed after init */
+	. = ALIGN(PAGE_SIZE);
+	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+		__init_begin = .; /* paired with __init_end */
+		_sinittext = .;
+		INIT_TEXT
+		_einittext = .;
+	}
+
+	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
+		INIT_DATA
+	}
+
+	. = ALIGN(16);
+	.init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
+		__setup_start = .;
+		*(.init.setup)
+		__setup_end = .;
+	}
+	.initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
+		__initcall_start = .;
+		INITCALLS
+		__initcall_end = .;
+	}
+
+	.con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
+		__con_initcall_start = .;
+		*(.con_initcall.init)
+		__con_initcall_end = .;
+	}
+
+	.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
+		__x86_cpu_dev_start = .;
+		*(.x86_cpu_dev.init)
+		__x86_cpu_dev_end = .;
+	}
+
+	SECURITY_INIT
+
+	. = ALIGN(8);
+	.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
+		__parainstructions = .;
+		*(.parainstructions)
+		__parainstructions_end = .;
+	}
+
+	. = ALIGN(8);
+	.altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
+		__alt_instructions = .;
+		*(.altinstructions)
+		__alt_instructions_end = .;
+	}
+
+	.altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
+		*(.altinstr_replacement)
+	}
+
+	/*
+	 * .exit.text is discard at runtime, not link time, to deal with
+	 *  references from .altinstructions and .eh_frame
+	 */
+	.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+		EXIT_TEXT
+	}
+
+	.exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
+		EXIT_DATA
+	}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	. = ALIGN(PAGE_SIZE);
+	.init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
+		__initramfs_start = .;
+		*(.init.ramfs)
+		__initramfs_end = .;
+	}
+#endif
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
+	/*
+	 * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
+	 * output PHDR, so the next output section - __data_nosave - should
+	 * start another section data.init2.  Also, pda should be at the head of
+	 * percpu area.  Preallocate it and define the percpu offset symbol
+	 * so that it can be accessed as a percpu variable.
+	 */
+	. = ALIGN(PAGE_SIZE);
+	PERCPU_VADDR(0, :percpu)
+#else
+	PERCPU(PAGE_SIZE)
+#endif
+
+	. = ALIGN(PAGE_SIZE);
+
+	/* freed after init ends here */
+	.init.end : AT(ADDR(.init.end) - LOAD_OFFSET) {
+		__init_end = .;
+	}
+
+#ifdef CONFIG_X86_64
+	.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+		. = ALIGN(PAGE_SIZE);
+		__nosave_begin = .;
+		*(.data.nosave)
+		. = ALIGN(PAGE_SIZE);
+		__nosave_end = .;
+	} :data.init2
+	/* use another section data.init2, see PERCPU_VADDR() above */
+#endif
+
+	/* BSS */
+	. = ALIGN(PAGE_SIZE);
+	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
+		__bss_start = .;
+		*(.bss.page_aligned)
+		*(.bss)
+		. = ALIGN(4);
+		__bss_stop = .;
+	}
+
+	. = ALIGN(PAGE_SIZE);
+	.brk : AT(ADDR(.brk) - LOAD_OFFSET) {
+		__brk_base = .;
+		. += 64 * 1024;		/* 64k alignment slop space */
+		*(.brk_reservation)	/* areas brk users have reserved */
+		__brk_limit = .;
+	}
+
+	.end : AT(ADDR(.end) - LOAD_OFFSET) {
+		_end = .;
+	}
+
+	/* Sections to be discarded */
+	/DISCARD/ : {
+		*(.exitcall.exit)
+		*(.eh_frame)
+		*(.discard)
+	}
+
+        STABS_DEBUG
+        DWARF_DEBUG
+}
+
+
+#ifdef CONFIG_X86_32
+ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
+        "kernel image bigger than KERNEL_IMAGE_SIZE")
+#else
+/*
+ * Per-cpu symbols which need to be offset from __per_cpu_load
+ * for the boot processor.
+ */
+#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
+INIT_PER_CPU(gdt_page);
+INIT_PER_CPU(irq_stack_union);
+
+/*
+ * Build-time check on the image size:
+ */
+ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
+	"kernel image bigger than KERNEL_IMAGE_SIZE")
+
+#ifdef CONFIG_SMP
+ASSERT((per_cpu__irq_stack_union == 0),
+        "irq_stack_union is not at start of per-cpu area");
+#endif
+
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_KEXEC
+#include <asm/kexec.h>
+
+ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
+       "kexec control code size is too big")
+#endif
+
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
deleted file mode 100644
index 62ad500d55f3..000000000000
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ /dev/null
@@ -1,229 +0,0 @@
-/* ld script to make i386 Linux kernel
- * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
- *
- * Don't define absolute symbols until and unless you know that symbol
- * value is should remain constant even if kernel image is relocated
- * at run time. Absolute symbols are not relocated. If symbol value should
- * change if kernel is relocated, make the symbol section relative and
- * put it inside the section definition.
- */
-
-#define LOAD_OFFSET __PAGE_OFFSET
-
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/thread_info.h>
-#include <asm/page_types.h>
-#include <asm/cache.h>
-#include <asm/boot.h>
-
-OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
-OUTPUT_ARCH(i386)
-ENTRY(phys_startup_32)
-jiffies = jiffies_64;
-
-PHDRS {
-	text PT_LOAD FLAGS(5);	/* R_E */
-	data PT_LOAD FLAGS(7);	/* RWE */
-	note PT_NOTE FLAGS(0);	/* ___ */
-}
-SECTIONS
-{
-  . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
-  phys_startup_32 = startup_32 - LOAD_OFFSET;
-
-  .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
-  	_text = .;			/* Text and read-only data */
-	*(.text.head)
-  } :text = 0x9090
-
-  /* read-only */
-  .text : AT(ADDR(.text) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE); /* not really needed, already page aligned */
-	*(.text.page_aligned)
-	TEXT_TEXT
-	SCHED_TEXT
-	LOCK_TEXT
-	KPROBES_TEXT
-	IRQENTRY_TEXT
-	*(.fixup)
-	*(.gnu.warning)
-  	_etext = .;			/* End of text section */
-  } :text = 0x9090
-
-  NOTES :text :note
-
-  . = ALIGN(16);		/* Exception table */
-  __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
-  	__start___ex_table = .;
-	 *(__ex_table)
-  	__stop___ex_table = .;
-  } :text = 0x9090
-
-  RODATA
-
-  /* writeable */
-  . = ALIGN(PAGE_SIZE);
-  .data : AT(ADDR(.data) - LOAD_OFFSET) {	/* Data */
-	DATA_DATA
-	CONSTRUCTORS
-	} :data
-
-  . = ALIGN(PAGE_SIZE);
-  .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
-  	__nosave_begin = .;
-	*(.data.nosave)
-  	. = ALIGN(PAGE_SIZE);
-  	__nosave_end = .;
-  }
-
-  . = ALIGN(PAGE_SIZE);
-  .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
-	*(.data.page_aligned)
-	*(.data.idt)
-  }
-
-  . = ALIGN(32);
-  .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
-	*(.data.cacheline_aligned)
-  }
-
-  /* rarely changed data like cpu maps */
-  . = ALIGN(32);
-  .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
-	*(.data.read_mostly)
-	_edata = .;		/* End of data section */
-  }
-
-  . = ALIGN(THREAD_SIZE);	/* init_task */
-  .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
-	*(.data.init_task)
-  }
-
-  /* might get freed after init */
-  . = ALIGN(PAGE_SIZE);
-  .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
-  	__smp_locks = .;
-	*(.smp_locks)
-	__smp_locks_end = .;
-  }
-  /* will be freed after init
-   * Following ALIGN() is required to make sure no other data falls on the
-   * same page where __smp_alt_end is pointing as that page might be freed
-   * after boot. Always make sure that ALIGN() directive is present after
-   * the section which contains __smp_alt_end.
-   */
-  . = ALIGN(PAGE_SIZE);
-
-  /* will be freed after init */
-  . = ALIGN(PAGE_SIZE);		/* Init code and data */
-  .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
-  	__init_begin = .;
-	_sinittext = .;
-	INIT_TEXT
-	_einittext = .;
-  }
-  .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
-	INIT_DATA
-  }
-  . = ALIGN(16);
-  .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
-  	__setup_start = .;
-	*(.init.setup)
-  	__setup_end = .;
-   }
-  .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
-  	__initcall_start = .;
-	INITCALLS
-  	__initcall_end = .;
-  }
-  .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
-  	__con_initcall_start = .;
-	*(.con_initcall.init)
-  	__con_initcall_end = .;
-  }
-  .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
-	__x86_cpu_dev_start = .;
-	*(.x86_cpu_dev.init)
-	__x86_cpu_dev_end = .;
-  }
-  SECURITY_INIT
-  . = ALIGN(4);
-  .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
-  	__alt_instructions = .;
-	*(.altinstructions)
-	__alt_instructions_end = .;
-  }
-  .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
-	*(.altinstr_replacement)
-  }
-  . = ALIGN(4);
-  .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
-  	__parainstructions = .;
-	*(.parainstructions)
-  	__parainstructions_end = .;
-  }
-  /* .exit.text is discard at runtime, not link time, to deal with references
-     from .altinstructions and .eh_frame */
-  .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
-	EXIT_TEXT
-  }
-  .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
-	EXIT_DATA
-  }
-#if defined(CONFIG_BLK_DEV_INITRD)
-  . = ALIGN(PAGE_SIZE);
-  .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
-	__initramfs_start = .;
-	*(.init.ramfs)
-	__initramfs_end = .;
-  }
-#endif
-  PERCPU(PAGE_SIZE)
-  . = ALIGN(PAGE_SIZE);
-  /* freed after init ends here */
-
-  .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
-	__init_end = .;
-	__bss_start = .;		/* BSS */
-	*(.bss.page_aligned)
-	*(.bss)
-	. = ALIGN(4);
-	__bss_stop = .;
-  }
-
-  .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	__brk_base = . ;
- 	. += 64 * 1024 ;	/* 64k alignment slop space */
-	*(.brk_reservation)	/* areas brk users have reserved */
-	__brk_limit = . ;
-  }
-
-  .end : AT(ADDR(.end) - LOAD_OFFSET) {
-	_end = . ;
-  }
-
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	*(.exitcall.exit)
-	*(.discard)
-	}
-
-  STABS_DEBUG
-
-  DWARF_DEBUG
-}
-
-/*
- * Build-time check on the image size:
- */
-ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
-	"kernel image bigger than KERNEL_IMAGE_SIZE")
-
-#ifdef CONFIG_KEXEC
-/* Link time checks */
-#include <asm/kexec.h>
-
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
-       "kexec control code size is too big")
-#endif
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
deleted file mode 100644
index c8742507b030..000000000000
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ /dev/null
@@ -1,298 +0,0 @@
-/* ld script to make x86-64 Linux kernel
- * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>;
- */
-
-#define LOAD_OFFSET __START_KERNEL_map
-
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/asm-offsets.h>
-#include <asm/page_types.h>
-
-#undef i386	/* in case the preprocessor is a 32bit one */
-
-OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
-OUTPUT_ARCH(i386:x86-64)
-ENTRY(phys_startup_64)
-jiffies_64 = jiffies;
-PHDRS {
-	text PT_LOAD FLAGS(5);	/* R_E */
-	data PT_LOAD FLAGS(7);	/* RWE */
-	user PT_LOAD FLAGS(7);	/* RWE */
-	data.init PT_LOAD FLAGS(7);	/* RWE */
-#ifdef CONFIG_SMP
-	percpu PT_LOAD FLAGS(7);	/* RWE */
-#endif
-	data.init2 PT_LOAD FLAGS(7);	/* RWE */
-	note PT_NOTE FLAGS(0);	/* ___ */
-}
-SECTIONS
-{
-  . = __START_KERNEL;
-  phys_startup_64 = startup_64 - LOAD_OFFSET;
-  .text :  AT(ADDR(.text) - LOAD_OFFSET) {
-	_text = .;			/* Text and read-only data */
-	/* First the code that has to be first for bootstrapping */
-	*(.text.head)
-	_stext = .;
-	/* Then the rest */
-	TEXT_TEXT
-	SCHED_TEXT
-	LOCK_TEXT
-	KPROBES_TEXT
-	IRQENTRY_TEXT
-	*(.fixup)
-	*(.gnu.warning)
-	_etext = .;		/* End of text section */
-  } :text = 0x9090
-
-  NOTES :text :note
-
-  . = ALIGN(16);		/* Exception table */
-  __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
-  	__start___ex_table = .;
-	 *(__ex_table)
-  	__stop___ex_table = .;
-  } :text = 0x9090
-
-  RODATA
-
-  . = ALIGN(PAGE_SIZE);		/* Align data segment to page size boundary */
-				/* Data */
-  .data : AT(ADDR(.data) - LOAD_OFFSET) {
-	DATA_DATA
-	CONSTRUCTORS
-	_edata = .;			/* End of data section */
-	} :data
-
-
-  .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-	*(.data.cacheline_aligned)
-  }
-  . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
-  .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
-  	*(.data.read_mostly)
-  }
-
-#define VSYSCALL_ADDR (-10*1024*1024)
-#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-
-#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
-#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
-
-#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
-#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
-
-  . = VSYSCALL_ADDR;
-  .vsyscall_0 :	 AT(VSYSCALL_PHYS_ADDR) { *(.vsyscall_0) } :user
-  __vsyscall_0 = VSYSCALL_VIRT_ADDR;
-
-  . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-  .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) }
-  . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-  .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data))
-		{ *(.vsyscall_gtod_data) }
-  vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
-  .vsyscall_clock : AT(VLOAD(.vsyscall_clock))
-		{ *(.vsyscall_clock) }
-  vsyscall_clock = VVIRT(.vsyscall_clock);
-
-
-  .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1))
-		{ *(.vsyscall_1) }
-  .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2))
-		{ *(.vsyscall_2) }
-
-  .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) }
-  vgetcpu_mode = VVIRT(.vgetcpu_mode);
-
-  . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-  .jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) }
-  jiffies = VVIRT(.jiffies);
-
-  .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3))
-		{ *(.vsyscall_3) }
-
-  . = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
-
-#undef VSYSCALL_ADDR
-#undef VSYSCALL_PHYS_ADDR
-#undef VSYSCALL_VIRT_ADDR
-#undef VLOAD_OFFSET
-#undef VLOAD
-#undef VVIRT_OFFSET
-#undef VVIRT
-
-  .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
-	. = ALIGN(THREAD_SIZE);	/* init_task */
-	*(.data.init_task)
-  }:data.init
-
-  .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	*(.data.page_aligned)
-  }
-
-  .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
-	/* might get freed after init */
-	. = ALIGN(PAGE_SIZE);
-	__smp_alt_begin = .;
-	__smp_locks = .;
-	*(.smp_locks)
-	__smp_locks_end = .;
-	. = ALIGN(PAGE_SIZE);
-	__smp_alt_end = .;
-  }
-
-  . = ALIGN(PAGE_SIZE);		/* Init code and data */
-  __init_begin = .;	/* paired with __init_end */
-  .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
-	_sinittext = .;
-	INIT_TEXT
-	_einittext = .;
-  }
-  .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
-	__initdata_begin = .;
-	INIT_DATA
-	__initdata_end = .;
-   }
-
-  .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
-	. = ALIGN(16);
-	__setup_start = .;
-	*(.init.setup)
-	__setup_end = .;
-  }
-  .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
-	__initcall_start = .;
-	INITCALLS
-	__initcall_end = .;
-  }
-  .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
-	__con_initcall_start = .;
-	*(.con_initcall.init)
-	__con_initcall_end = .;
-  }
-  .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
-	__x86_cpu_dev_start = .;
-	*(.x86_cpu_dev.init)
-	__x86_cpu_dev_end = .;
-  }
-  SECURITY_INIT
-
-  . = ALIGN(8);
-  .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
-	__parainstructions = .;
-       *(.parainstructions)
-	__parainstructions_end = .;
-  }
-
-  .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
-	. = ALIGN(8);
-	__alt_instructions = .;
-	*(.altinstructions)
-	__alt_instructions_end = .;
-  }
-  .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
-	*(.altinstr_replacement)
-  }
-  /* .exit.text is discard at runtime, not link time, to deal with references
-     from .altinstructions and .eh_frame */
-  .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
-	EXIT_TEXT
-  }
-  .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
-	EXIT_DATA
-  }
-
-#ifdef CONFIG_BLK_DEV_INITRD
-  . = ALIGN(PAGE_SIZE);
-  .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
-	__initramfs_start = .;
-	*(.init.ramfs)
-	__initramfs_end = .;
-  }
-#endif
-
-#ifdef CONFIG_SMP
-  /*
-   * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
-   * output PHDR, so the next output section - __data_nosave - should
-   * start another section data.init2.  Also, pda should be at the head of
-   * percpu area.  Preallocate it and define the percpu offset symbol
-   * so that it can be accessed as a percpu variable.
-   */
-  . = ALIGN(PAGE_SIZE);
-  PERCPU_VADDR(0, :percpu)
-#else
-  PERCPU(PAGE_SIZE)
-#endif
-
-  . = ALIGN(PAGE_SIZE);
-  __init_end = .;
-
-  .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	__nosave_begin = .;
-	*(.data.nosave)
-	. = ALIGN(PAGE_SIZE);
-	__nosave_end = .;
-  } :data.init2 /* use another section data.init2, see PERCPU_VADDR() above */
-
-  .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	__bss_start = .;		/* BSS */
-	*(.bss.page_aligned)
-	*(.bss)
-	__bss_stop = .;
-  }
-
-  .brk : AT(ADDR(.brk) - LOAD_OFFSET) {
-	. = ALIGN(PAGE_SIZE);
-	__brk_base = . ;
- 	. += 64 * 1024 ;	/* 64k alignment slop space */
-	*(.brk_reservation)	/* areas brk users have reserved */
-	__brk_limit = . ;
-  }
-
-  _end = . ;
-
-  /* Sections to be discarded */
-  /DISCARD/ : {
-	*(.exitcall.exit)
-	*(.eh_frame)
-	*(.discard)
-	}
-
-  STABS_DEBUG
-
-  DWARF_DEBUG
-}
-
- /*
-  * Per-cpu symbols which need to be offset from __per_cpu_load
-  * for the boot processor.
-  */
-#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
-INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_union);
-
-/*
- * Build-time check on the image size:
- */
-ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
-	"kernel image bigger than KERNEL_IMAGE_SIZE")
-
-#ifdef CONFIG_SMP
-ASSERT((per_cpu__irq_stack_union == 0),
-        "irq_stack_union is not at start of per-cpu area");
-#endif
-
-#ifdef CONFIG_KEXEC
-#include <asm/kexec.h>
-
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
-       "kexec control code size is too big")
-#endif
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 44153afc9067..25ee06a80aad 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -132,15 +132,7 @@ static __always_inline void do_vgettimeofday(struct timeval * tv)
 			return;
 		}
 
-		/*
-		 * Surround the RDTSC by barriers, to make sure it's not
-		 * speculated to outside the seqlock critical section and
-		 * does not cause time warps:
-		 */
-		rdtsc_barrier();
 		now = vread();
-		rdtsc_barrier();
-
 		base = __vsyscall_gtod_data.clock.cycle_last;
 		mask = __vsyscall_gtod_data.clock.mask;
 		mult = __vsyscall_gtod_data.clock.mult;
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a58504ea78cc..8600a09e0c6c 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -50,6 +50,9 @@ config KVM_INTEL
 	  Provides support for KVM on Intel processors equipped with the VT
 	  extensions.
 
+	  To compile this as a module, choose M here: the module
+	  will be called kvm-intel.
+
 config KVM_AMD
 	tristate "KVM for AMD processors support"
 	depends on KVM
@@ -57,6 +60,9 @@ config KVM_AMD
 	  Provides support for KVM on AMD processors equipped with the AMD-V
 	  (SVM) extensions.
 
+	  To compile this as a module, choose M here: the module
+	  will be called kvm-amd.
+
 config KVM_TRACE
 	bool "KVM trace support"
 	depends on KVM && SYSFS
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index d3ec292f00f2..b43c4efafe80 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -14,7 +14,7 @@ endif
 EXTRA_CFLAGS += -Ivirt/kvm -Iarch/x86/kvm
 
 kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o \
-	i8254.o
+	i8254.o timer.o
 obj-$(CONFIG_KVM) += kvm.o
 kvm-intel-objs = vmx.o
 obj-$(CONFIG_KVM_INTEL) += kvm-intel.o
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index c13bb92d3157..4d6f0d293ee2 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -98,6 +98,37 @@ static int pit_get_gate(struct kvm *kvm, int channel)
 	return kvm->arch.vpit->pit_state.channels[channel].gate;
 }
 
+static s64 __kpit_elapsed(struct kvm *kvm)
+{
+	s64 elapsed;
+	ktime_t remaining;
+	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
+
+	/*
+	 * The Counter does not stop when it reaches zero. In
+	 * Modes 0, 1, 4, and 5 the Counter ``wraps around'' to
+	 * the highest count, either FFFF hex for binary counting
+	 * or 9999 for BCD counting, and continues counting.
+	 * Modes 2 and 3 are periodic; the Counter reloads
+	 * itself with the initial count and continues counting
+	 * from there.
+	 */
+	remaining = hrtimer_expires_remaining(&ps->pit_timer.timer);
+	elapsed = ps->pit_timer.period - ktime_to_ns(remaining);
+	elapsed = mod_64(elapsed, ps->pit_timer.period);
+
+	return elapsed;
+}
+
+static s64 kpit_elapsed(struct kvm *kvm, struct kvm_kpit_channel_state *c,
+			int channel)
+{
+	if (channel == 0)
+		return __kpit_elapsed(kvm);
+
+	return ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+}
+
 static int pit_get_count(struct kvm *kvm, int channel)
 {
 	struct kvm_kpit_channel_state *c =
@@ -107,7 +138,7 @@ static int pit_get_count(struct kvm *kvm, int channel)
 
 	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
 
-	t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+	t = kpit_elapsed(kvm, c, channel);
 	d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
 
 	switch (c->mode) {
@@ -137,7 +168,7 @@ static int pit_get_out(struct kvm *kvm, int channel)
 
 	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
 
-	t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+	t = kpit_elapsed(kvm, c, channel);
 	d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
 
 	switch (c->mode) {
@@ -193,28 +224,6 @@ static void pit_latch_status(struct kvm *kvm, int channel)
 	}
 }
 
-static int __pit_timer_fn(struct kvm_kpit_state *ps)
-{
-	struct kvm_vcpu *vcpu0 = ps->pit->kvm->vcpus[0];
-	struct kvm_kpit_timer *pt = &ps->pit_timer;
-
-	if (!atomic_inc_and_test(&pt->pending))
-		set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
-
-	if (!pt->reinject)
-		atomic_set(&pt->pending, 1);
-
-	if (vcpu0 && waitqueue_active(&vcpu0->wq))
-		wake_up_interruptible(&vcpu0->wq);
-
-	hrtimer_add_expires_ns(&pt->timer, pt->period);
-	pt->scheduled = hrtimer_get_expires_ns(&pt->timer);
-	if (pt->period)
-		ps->channels[0].count_load_time = ktime_get();
-
-	return (pt->period == 0 ? 0 : 1);
-}
-
 int pit_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
@@ -235,21 +244,6 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
 	spin_unlock(&ps->inject_lock);
 }
 
-static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
-{
-	struct kvm_kpit_state *ps;
-	int restart_timer = 0;
-
-	ps = container_of(data, struct kvm_kpit_state, pit_timer.timer);
-
-	restart_timer = __pit_timer_fn(ps);
-
-	if (restart_timer)
-		return HRTIMER_RESTART;
-	else
-		return HRTIMER_NORESTART;
-}
-
 void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
@@ -263,15 +257,26 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
-static void destroy_pit_timer(struct kvm_kpit_timer *pt)
+static void destroy_pit_timer(struct kvm_timer *pt)
 {
 	pr_debug("pit: execute del timer!\n");
 	hrtimer_cancel(&pt->timer);
 }
 
+static bool kpit_is_periodic(struct kvm_timer *ktimer)
+{
+	struct kvm_kpit_state *ps = container_of(ktimer, struct kvm_kpit_state,
+						 pit_timer);
+	return ps->is_periodic;
+}
+
+static struct kvm_timer_ops kpit_ops = {
+	.is_periodic = kpit_is_periodic,
+};
+
 static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
 {
-	struct kvm_kpit_timer *pt = &ps->pit_timer;
+	struct kvm_timer *pt = &ps->pit_timer;
 	s64 interval;
 
 	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
@@ -280,8 +285,14 @@ static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
 
 	/* TODO The new value only affected after the retriggered */
 	hrtimer_cancel(&pt->timer);
-	pt->period = (is_period == 0) ? 0 : interval;
-	pt->timer.function = pit_timer_fn;
+	pt->period = interval;
+	ps->is_periodic = is_period;
+
+	pt->timer.function = kvm_timer_fn;
+	pt->t_ops = &kpit_ops;
+	pt->kvm = ps->pit->kvm;
+	pt->vcpu_id = 0;
+
 	atomic_set(&pt->pending, 0);
 	ps->irq_ack = 1;
 
@@ -298,23 +309,23 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
 	pr_debug("pit: load_count val is %d, channel is %d\n", val, channel);
 
 	/*
-	 * Though spec said the state of 8254 is undefined after power-up,
-	 * seems some tricky OS like Windows XP depends on IRQ0 interrupt
-	 * when booting up.
-	 * So here setting initialize rate for it, and not a specific number
+	 * The largest possible initial count is 0; this is equivalent
+	 * to 216 for binary counting and 104 for BCD counting.
 	 */
 	if (val == 0)
 		val = 0x10000;
 
-	ps->channels[channel].count_load_time = ktime_get();
 	ps->channels[channel].count = val;
 
-	if (channel != 0)
+	if (channel != 0) {
+		ps->channels[channel].count_load_time = ktime_get();
 		return;
+	}
 
 	/* Two types of timer
 	 * mode 1 is one shot, mode 2 is period, otherwise del timer */
 	switch (ps->channels[0].mode) {
+	case 0:
 	case 1:
         /* FIXME: enhance mode 4 precision */
 	case 4:
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index 6acbe4b505d5..bbd863ff60b7 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -3,15 +3,6 @@
 
 #include "iodev.h"
 
-struct kvm_kpit_timer {
-	struct hrtimer timer;
-	int irq;
-	s64 period; /* unit: ns */
-	s64 scheduled;
-	atomic_t pending;
-	bool reinject;
-};
-
 struct kvm_kpit_channel_state {
 	u32 count; /* can be 65536 */
 	u16 latched_count;
@@ -30,7 +21,8 @@ struct kvm_kpit_channel_state {
 
 struct kvm_kpit_state {
 	struct kvm_kpit_channel_state channels[3];
-	struct kvm_kpit_timer pit_timer;
+	struct kvm_timer pit_timer;
+	bool is_periodic;
 	u32    speaker_data_on;
 	struct mutex lock;
 	struct kvm_pit *pit;
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index cf17ed52f6fb..96dfbb6ad2a9 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -24,6 +24,7 @@
 
 #include "irq.h"
 #include "i8254.h"
+#include "x86.h"
 
 /*
  * check if there are pending timer events
@@ -48,6 +49,9 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
 	struct kvm_pic *s;
 
+	if (!irqchip_in_kernel(v->kvm))
+		return v->arch.interrupt.pending;
+
 	if (kvm_apic_has_interrupt(v) == -1) {	/* LAPIC */
 		if (kvm_apic_accept_pic_intr(v)) {
 			s = pic_irqchip(v->kvm);	/* PIC */
@@ -67,6 +71,9 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 	struct kvm_pic *s;
 	int vector;
 
+	if (!irqchip_in_kernel(v->kvm))
+		return v->arch.interrupt.nr;
+
 	vector = kvm_get_apic_interrupt(v);	/* APIC */
 	if (vector == -1) {
 		if (kvm_apic_accept_pic_intr(v)) {
diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h
new file mode 100644
index 000000000000..26bd6ba74e1c
--- /dev/null
+++ b/arch/x86/kvm/kvm_timer.h
@@ -0,0 +1,18 @@
+
+struct kvm_timer {
+	struct hrtimer timer;
+	s64 period; 				/* unit: ns */
+	atomic_t pending;			/* accumulated triggered timers */
+	bool reinject;
+	struct kvm_timer_ops *t_ops;
+	struct kvm *kvm;
+	int vcpu_id;
+};
+
+struct kvm_timer_ops {
+        bool (*is_periodic)(struct kvm_timer *);
+};
+
+
+enum hrtimer_restart kvm_timer_fn(struct hrtimer *data);
+
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index f0b67f2cdd69..ae99d83f81a3 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -196,20 +196,15 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr);
 
-int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig)
+static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
+			     int vector, int level, int trig_mode);
+
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!apic_test_and_set_irr(vec, apic)) {
-		/* a new pending irq is set in IRR */
-		if (trig)
-			apic_set_vector(vec, apic->regs + APIC_TMR);
-		else
-			apic_clear_vector(vec, apic->regs + APIC_TMR);
-		kvm_vcpu_kick(apic->vcpu);
-		return 1;
-	}
-	return 0;
+	return __apic_accept_irq(apic, irq->delivery_mode, irq->vector,
+			irq->level, irq->trig_mode);
 }
 
 static inline int apic_find_highest_isr(struct kvm_lapic *apic)
@@ -250,7 +245,7 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr)
 
 int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
 {
-	return kvm_apic_id(apic) == dest;
+	return dest == 0xff || kvm_apic_id(apic) == dest;
 }
 
 int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
@@ -279,37 +274,34 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
 	return result;
 }
 
-static int apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 			   int short_hand, int dest, int dest_mode)
 {
 	int result = 0;
 	struct kvm_lapic *target = vcpu->arch.apic;
 
 	apic_debug("target %p, source %p, dest 0x%x, "
-		   "dest_mode 0x%x, short_hand 0x%x",
+		   "dest_mode 0x%x, short_hand 0x%x\n",
 		   target, source, dest, dest_mode, short_hand);
 
 	ASSERT(!target);
 	switch (short_hand) {
 	case APIC_DEST_NOSHORT:
-		if (dest_mode == 0) {
+		if (dest_mode == 0)
 			/* Physical mode. */
-			if ((dest == 0xFF) || (dest == kvm_apic_id(target)))
-				result = 1;
-		} else
+			result = kvm_apic_match_physical_addr(target, dest);
+		else
 			/* Logical mode. */
 			result = kvm_apic_match_logical_addr(target, dest);
 		break;
 	case APIC_DEST_SELF:
-		if (target == source)
-			result = 1;
+		result = (target == source);
 		break;
 	case APIC_DEST_ALLINC:
 		result = 1;
 		break;
 	case APIC_DEST_ALLBUT:
-		if (target != source)
-			result = 1;
+		result = (target != source);
 		break;
 	default:
 		printk(KERN_WARNING "Bad dest shorthand value %x\n",
@@ -327,20 +319,22 @@ static int apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 			     int vector, int level, int trig_mode)
 {
-	int orig_irr, result = 0;
+	int result = 0;
 	struct kvm_vcpu *vcpu = apic->vcpu;
 
 	switch (delivery_mode) {
-	case APIC_DM_FIXED:
 	case APIC_DM_LOWEST:
+		vcpu->arch.apic_arb_prio++;
+	case APIC_DM_FIXED:
 		/* FIXME add logic for vcpu on reset */
 		if (unlikely(!apic_enabled(apic)))
 			break;
 
-		orig_irr = apic_test_and_set_irr(vector, apic);
-		if (orig_irr && trig_mode) {
-			apic_debug("level trig mode repeatedly for vector %d",
-				   vector);
+		result = !apic_test_and_set_irr(vector, apic);
+		if (!result) {
+			if (trig_mode)
+				apic_debug("level trig mode repeatedly for "
+						"vector %d", vector);
 			break;
 		}
 
@@ -349,10 +343,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 			apic_set_vector(vector, apic->regs + APIC_TMR);
 		} else
 			apic_clear_vector(vector, apic->regs + APIC_TMR);
-
 		kvm_vcpu_kick(vcpu);
-
-		result = (orig_irr == 0);
 		break;
 
 	case APIC_DM_REMRD:
@@ -364,12 +355,14 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		break;
 
 	case APIC_DM_NMI:
+		result = 1;
 		kvm_inject_nmi(vcpu);
 		kvm_vcpu_kick(vcpu);
 		break;
 
 	case APIC_DM_INIT:
 		if (level) {
+			result = 1;
 			if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
 				printk(KERN_DEBUG
 				       "INIT on a runnable vcpu %d\n",
@@ -386,6 +379,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		apic_debug("SIPI to vcpu %d vector 0x%02x\n",
 			   vcpu->vcpu_id, vector);
 		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
+			result = 1;
 			vcpu->arch.sipi_vector = vector;
 			vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
 			kvm_vcpu_kick(vcpu);
@@ -408,43 +402,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	return result;
 }
 
-static struct kvm_lapic *kvm_apic_round_robin(struct kvm *kvm, u8 vector,
-				       unsigned long bitmap)
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 {
-	int last;
-	int next;
-	struct kvm_lapic *apic = NULL;
-
-	last = kvm->arch.round_robin_prev_vcpu;
-	next = last;
-
-	do {
-		if (++next == KVM_MAX_VCPUS)
-			next = 0;
-		if (kvm->vcpus[next] == NULL || !test_bit(next, &bitmap))
-			continue;
-		apic = kvm->vcpus[next]->arch.apic;
-		if (apic && apic_enabled(apic))
-			break;
-		apic = NULL;
-	} while (next != last);
-	kvm->arch.round_robin_prev_vcpu = next;
-
-	if (!apic)
-		printk(KERN_DEBUG "vcpu not ready for apic_round_robin\n");
-
-	return apic;
-}
-
-struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
-		unsigned long bitmap)
-{
-	struct kvm_lapic *apic;
-
-	apic = kvm_apic_round_robin(kvm, vector, bitmap);
-	if (apic)
-		return apic->vcpu;
-	return NULL;
+	return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
 }
 
 static void apic_set_eoi(struct kvm_lapic *apic)
@@ -472,47 +432,24 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 {
 	u32 icr_low = apic_get_reg(apic, APIC_ICR);
 	u32 icr_high = apic_get_reg(apic, APIC_ICR2);
+	struct kvm_lapic_irq irq;
 
-	unsigned int dest = GET_APIC_DEST_FIELD(icr_high);
-	unsigned int short_hand = icr_low & APIC_SHORT_MASK;
-	unsigned int trig_mode = icr_low & APIC_INT_LEVELTRIG;
-	unsigned int level = icr_low & APIC_INT_ASSERT;
-	unsigned int dest_mode = icr_low & APIC_DEST_MASK;
-	unsigned int delivery_mode = icr_low & APIC_MODE_MASK;
-	unsigned int vector = icr_low & APIC_VECTOR_MASK;
-
-	struct kvm_vcpu *target;
-	struct kvm_vcpu *vcpu;
-	unsigned long lpr_map = 0;
-	int i;
+	irq.vector = icr_low & APIC_VECTOR_MASK;
+	irq.delivery_mode = icr_low & APIC_MODE_MASK;
+	irq.dest_mode = icr_low & APIC_DEST_MASK;
+	irq.level = icr_low & APIC_INT_ASSERT;
+	irq.trig_mode = icr_low & APIC_INT_LEVELTRIG;
+	irq.shorthand = icr_low & APIC_SHORT_MASK;
+	irq.dest_id = GET_APIC_DEST_FIELD(icr_high);
 
 	apic_debug("icr_high 0x%x, icr_low 0x%x, "
 		   "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, "
 		   "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n",
-		   icr_high, icr_low, short_hand, dest,
-		   trig_mode, level, dest_mode, delivery_mode, vector);
+		   icr_high, icr_low, irq.shorthand, irq.dest_id,
+		   irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
+		   irq.vector);
 
-	for (i = 0; i < KVM_MAX_VCPUS; i++) {
-		vcpu = apic->vcpu->kvm->vcpus[i];
-		if (!vcpu)
-			continue;
-
-		if (vcpu->arch.apic &&
-		    apic_match_dest(vcpu, apic, short_hand, dest, dest_mode)) {
-			if (delivery_mode == APIC_DM_LOWEST)
-				set_bit(vcpu->vcpu_id, &lpr_map);
-			else
-				__apic_accept_irq(vcpu->arch.apic, delivery_mode,
-						  vector, level, trig_mode);
-		}
-	}
-
-	if (delivery_mode == APIC_DM_LOWEST) {
-		target = kvm_get_lowest_prio_vcpu(vcpu->kvm, vector, lpr_map);
-		if (target != NULL)
-			__apic_accept_irq(target->arch.apic, delivery_mode,
-					  vector, level, trig_mode);
-	}
+	kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq);
 }
 
 static u32 apic_get_tmcct(struct kvm_lapic *apic)
@@ -527,12 +464,13 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 	if (apic_get_reg(apic, APIC_TMICT) == 0)
 		return 0;
 
-	remaining = hrtimer_expires_remaining(&apic->timer.dev);
+	remaining = hrtimer_expires_remaining(&apic->lapic_timer.timer);
 	if (ktime_to_ns(remaining) < 0)
 		remaining = ktime_set(0, 0);
 
-	ns = mod_64(ktime_to_ns(remaining), apic->timer.period);
-	tmcct = div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->timer.divide_count));
+	ns = mod_64(ktime_to_ns(remaining), apic->lapic_timer.period);
+	tmcct = div64_u64(ns,
+			 (APIC_BUS_CYCLE_NS * apic->divide_count));
 
 	return tmcct;
 }
@@ -619,25 +557,25 @@ static void update_divide_count(struct kvm_lapic *apic)
 	tdcr = apic_get_reg(apic, APIC_TDCR);
 	tmp1 = tdcr & 0xf;
 	tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1;
-	apic->timer.divide_count = 0x1 << (tmp2 & 0x7);
+	apic->divide_count = 0x1 << (tmp2 & 0x7);
 
 	apic_debug("timer divide count is 0x%x\n",
-				   apic->timer.divide_count);
+				   apic->divide_count);
 }
 
 static void start_apic_timer(struct kvm_lapic *apic)
 {
-	ktime_t now = apic->timer.dev.base->get_time();
+	ktime_t now = apic->lapic_timer.timer.base->get_time();
 
-	apic->timer.period = apic_get_reg(apic, APIC_TMICT) *
-		    APIC_BUS_CYCLE_NS * apic->timer.divide_count;
-	atomic_set(&apic->timer.pending, 0);
+	apic->lapic_timer.period = apic_get_reg(apic, APIC_TMICT) *
+		    APIC_BUS_CYCLE_NS * apic->divide_count;
+	atomic_set(&apic->lapic_timer.pending, 0);
 
-	if (!apic->timer.period)
+	if (!apic->lapic_timer.period)
 		return;
 
-	hrtimer_start(&apic->timer.dev,
-		      ktime_add_ns(now, apic->timer.period),
+	hrtimer_start(&apic->lapic_timer.timer,
+		      ktime_add_ns(now, apic->lapic_timer.period),
 		      HRTIMER_MODE_ABS);
 
 	apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
@@ -646,9 +584,9 @@ static void start_apic_timer(struct kvm_lapic *apic)
 			   "expire @ 0x%016" PRIx64 ".\n", __func__,
 			   APIC_BUS_CYCLE_NS, ktime_to_ns(now),
 			   apic_get_reg(apic, APIC_TMICT),
-			   apic->timer.period,
+			   apic->lapic_timer.period,
 			   ktime_to_ns(ktime_add_ns(now,
-					apic->timer.period)));
+					apic->lapic_timer.period)));
 }
 
 static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
@@ -730,7 +668,7 @@ static void apic_mmio_write(struct kvm_io_device *this,
 				apic_set_reg(apic, APIC_LVTT + 0x10 * i,
 					     lvt_val | APIC_LVT_MASKED);
 			}
-			atomic_set(&apic->timer.pending, 0);
+			atomic_set(&apic->lapic_timer.pending, 0);
 
 		}
 		break;
@@ -762,7 +700,7 @@ static void apic_mmio_write(struct kvm_io_device *this,
 		break;
 
 	case APIC_TMICT:
-		hrtimer_cancel(&apic->timer.dev);
+		hrtimer_cancel(&apic->lapic_timer.timer);
 		apic_set_reg(apic, APIC_TMICT, val);
 		start_apic_timer(apic);
 		return;
@@ -802,7 +740,7 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu)
 	if (!vcpu->arch.apic)
 		return;
 
-	hrtimer_cancel(&vcpu->arch.apic->timer.dev);
+	hrtimer_cancel(&vcpu->arch.apic->lapic_timer.timer);
 
 	if (vcpu->arch.apic->regs_page)
 		__free_page(vcpu->arch.apic->regs_page);
@@ -880,7 +818,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 	ASSERT(apic != NULL);
 
 	/* Stop the timer in case it's a reset to an active apic */
-	hrtimer_cancel(&apic->timer.dev);
+	hrtimer_cancel(&apic->lapic_timer.timer);
 
 	apic_set_reg(apic, APIC_ID, vcpu->vcpu_id << 24);
 	apic_set_reg(apic, APIC_LVR, APIC_VERSION);
@@ -905,11 +843,13 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
 	update_divide_count(apic);
-	atomic_set(&apic->timer.pending, 0);
+	atomic_set(&apic->lapic_timer.pending, 0);
 	if (vcpu->vcpu_id == 0)
 		vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
 	apic_update_ppr(apic);
 
+	vcpu->arch.apic_arb_prio = 0;
+
 	apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr="
 		   "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
 		   vcpu, kvm_apic_id(apic),
@@ -917,16 +857,14 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_reset);
 
+bool kvm_apic_present(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.apic && apic_hw_enabled(vcpu->arch.apic);
+}
+
 int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	int ret = 0;
-
-	if (!apic)
-		return 0;
-	ret = apic_enabled(apic);
-
-	return ret;
+	return kvm_apic_present(vcpu) && apic_sw_enabled(vcpu->arch.apic);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_enabled);
 
@@ -936,22 +874,11 @@ EXPORT_SYMBOL_GPL(kvm_lapic_enabled);
  *----------------------------------------------------------------------
  */
 
-/* TODO: make sure __apic_timer_fn runs in current pCPU */
-static int __apic_timer_fn(struct kvm_lapic *apic)
+static bool lapic_is_periodic(struct kvm_timer *ktimer)
 {
-	int result = 0;
-	wait_queue_head_t *q = &apic->vcpu->wq;
-
-	if(!atomic_inc_and_test(&apic->timer.pending))
-		set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests);
-	if (waitqueue_active(q))
-		wake_up_interruptible(q);
-
-	if (apic_lvtt_period(apic)) {
-		result = 1;
-		hrtimer_add_expires_ns(&apic->timer.dev, apic->timer.period);
-	}
-	return result;
+	struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic,
+					      lapic_timer);
+	return apic_lvtt_period(apic);
 }
 
 int apic_has_pending_timer(struct kvm_vcpu *vcpu)
@@ -959,7 +886,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *lapic = vcpu->arch.apic;
 
 	if (lapic && apic_enabled(lapic) && apic_lvt_enabled(lapic, APIC_LVTT))
-		return atomic_read(&lapic->timer.pending);
+		return atomic_read(&lapic->lapic_timer.pending);
 
 	return 0;
 }
@@ -986,20 +913,9 @@ void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu)
 		kvm_apic_local_deliver(apic, APIC_LVT0);
 }
 
-static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
-{
-	struct kvm_lapic *apic;
-	int restart_timer = 0;
-
-	apic = container_of(data, struct kvm_lapic, timer.dev);
-
-	restart_timer = __apic_timer_fn(apic);
-
-	if (restart_timer)
-		return HRTIMER_RESTART;
-	else
-		return HRTIMER_NORESTART;
-}
+static struct kvm_timer_ops lapic_timer_ops = {
+	.is_periodic = lapic_is_periodic,
+};
 
 int kvm_create_lapic(struct kvm_vcpu *vcpu)
 {
@@ -1024,8 +940,13 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	memset(apic->regs, 0, PAGE_SIZE);
 	apic->vcpu = vcpu;
 
-	hrtimer_init(&apic->timer.dev, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-	apic->timer.dev.function = apic_timer_fn;
+	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_ABS);
+	apic->lapic_timer.timer.function = kvm_timer_fn;
+	apic->lapic_timer.t_ops = &lapic_timer_ops;
+	apic->lapic_timer.kvm = vcpu->kvm;
+	apic->lapic_timer.vcpu_id = vcpu->vcpu_id;
+
 	apic->base_address = APIC_DEFAULT_PHYS_BASE;
 	vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE;
 
@@ -1078,9 +999,9 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (apic && atomic_read(&apic->timer.pending) > 0) {
+	if (apic && atomic_read(&apic->lapic_timer.pending) > 0) {
 		if (kvm_apic_local_deliver(apic, APIC_LVTT))
-			atomic_dec(&apic->timer.pending);
+			atomic_dec(&apic->lapic_timer.pending);
 	}
 }
 
@@ -1106,7 +1027,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu)
 			     MSR_IA32_APICBASE_BASE;
 	apic_set_reg(apic, APIC_LVR, APIC_VERSION);
 	apic_update_ppr(apic);
-	hrtimer_cancel(&apic->timer.dev);
+	hrtimer_cancel(&apic->lapic_timer.timer);
 	update_divide_count(apic);
 	start_apic_timer(apic);
 }
@@ -1119,7 +1040,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
 	if (!apic)
 		return;
 
-	timer = &apic->timer.dev;
+	timer = &apic->lapic_timer.timer;
 	if (hrtimer_cancel(timer))
 		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 45ab6ee71209..a587f8349c46 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -2,18 +2,15 @@
 #define __KVM_X86_LAPIC_H
 
 #include "iodev.h"
+#include "kvm_timer.h"
 
 #include <linux/kvm_host.h>
 
 struct kvm_lapic {
 	unsigned long base_address;
 	struct kvm_io_device dev;
-	struct {
-		atomic_t pending;
-		s64 period;	/* unit: ns */
-		u32 divide_count;
-		struct hrtimer dev;
-	} timer;
+	struct kvm_timer lapic_timer;
+	u32 divide_count;
 	struct kvm_vcpu *vcpu;
 	struct page *regs_page;
 	void *regs;
@@ -34,12 +31,13 @@ u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu);
 
 int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
 int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
-int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig);
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq);
 
 u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
 void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data);
 void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu);
 int kvm_lapic_enabled(struct kvm_vcpu *vcpu);
+bool kvm_apic_present(struct kvm_vcpu *vcpu);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 
 void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 32cf11e5728a..5c3d6e81a7dc 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -126,6 +126,7 @@ module_param(oos_shadow, bool, 0644);
 #define PFERR_PRESENT_MASK (1U << 0)
 #define PFERR_WRITE_MASK (1U << 1)
 #define PFERR_USER_MASK (1U << 2)
+#define PFERR_RSVD_MASK (1U << 3)
 #define PFERR_FETCH_MASK (1U << 4)
 
 #define PT_DIRECTORY_LEVEL 2
@@ -177,7 +178,11 @@ static u64 __read_mostly shadow_x_mask;	/* mutual exclusive with nx_mask */
 static u64 __read_mostly shadow_user_mask;
 static u64 __read_mostly shadow_accessed_mask;
 static u64 __read_mostly shadow_dirty_mask;
-static u64 __read_mostly shadow_mt_mask;
+
+static inline u64 rsvd_bits(int s, int e)
+{
+	return ((1ULL << (e - s + 1)) - 1) << s;
+}
 
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
 {
@@ -193,14 +198,13 @@ void kvm_mmu_set_base_ptes(u64 base_pte)
 EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes);
 
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 mt_mask)
+		u64 dirty_mask, u64 nx_mask, u64 x_mask)
 {
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
 	shadow_dirty_mask = dirty_mask;
 	shadow_nx_mask = nx_mask;
 	shadow_x_mask = x_mask;
-	shadow_mt_mask = mt_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
@@ -219,11 +223,6 @@ static int is_nx(struct kvm_vcpu *vcpu)
 	return vcpu->arch.shadow_efer & EFER_NX;
 }
 
-static int is_present_pte(unsigned long pte)
-{
-	return pte & PT_PRESENT_MASK;
-}
-
 static int is_shadow_present_pte(u64 pte)
 {
 	return pte != shadow_trap_nonpresent_pte
@@ -1074,18 +1073,10 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
 	return NULL;
 }
 
-static void kvm_unlink_unsync_global(struct kvm *kvm, struct kvm_mmu_page *sp)
-{
-	list_del(&sp->oos_link);
-	--kvm->stat.mmu_unsync_global;
-}
-
 static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	WARN_ON(!sp->unsync);
 	sp->unsync = 0;
-	if (sp->global)
-		kvm_unlink_unsync_global(kvm, sp);
 	--kvm->stat.mmu_unsync;
 }
 
@@ -1248,7 +1239,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word);
 	sp->gfn = gfn;
 	sp->role = role;
-	sp->global = 0;
 	hlist_add_head(&sp->hash_link, bucket);
 	if (!direct) {
 		if (rmap_write_protect(vcpu->kvm, gfn))
@@ -1616,7 +1606,7 @@ static int get_mtrr_type(struct mtrr_state_type *mtrr_state,
 	return mtrr_state->def_type;
 }
 
-static u8 get_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
+u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	u8 mtrr;
 
@@ -1626,6 +1616,7 @@ static u8 get_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
 		mtrr = MTRR_TYPE_WRBACK;
 	return mtrr;
 }
+EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type);
 
 static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -1646,11 +1637,7 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 	++vcpu->kvm->stat.mmu_unsync;
 	sp->unsync = 1;
 
-	if (sp->global) {
-		list_add(&sp->oos_link, &vcpu->kvm->arch.oos_global_pages);
-		++vcpu->kvm->stat.mmu_unsync_global;
-	} else
-		kvm_mmu_mark_parents_unsync(vcpu, sp);
+	kvm_mmu_mark_parents_unsync(vcpu, sp);
 
 	mmu_convert_notrap(sp);
 	return 0;
@@ -1677,21 +1664,11 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		    unsigned pte_access, int user_fault,
 		    int write_fault, int dirty, int largepage,
-		    int global, gfn_t gfn, pfn_t pfn, bool speculative,
+		    gfn_t gfn, pfn_t pfn, bool speculative,
 		    bool can_unsync)
 {
 	u64 spte;
 	int ret = 0;
-	u64 mt_mask = shadow_mt_mask;
-	struct kvm_mmu_page *sp = page_header(__pa(shadow_pte));
-
-	if (!global && sp->global) {
-		sp->global = 0;
-		if (sp->unsync) {
-			kvm_unlink_unsync_global(vcpu->kvm, sp);
-			kvm_mmu_mark_parents_unsync(vcpu, sp);
-		}
-	}
 
 	/*
 	 * We don't set the accessed bit, since we sometimes want to see
@@ -1711,16 +1688,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		spte |= shadow_user_mask;
 	if (largepage)
 		spte |= PT_PAGE_SIZE_MASK;
-	if (mt_mask) {
-		if (!kvm_is_mmio_pfn(pfn)) {
-			mt_mask = get_memory_type(vcpu, gfn) <<
-				kvm_x86_ops->get_mt_mask_shift();
-			mt_mask |= VMX_EPT_IGMT_BIT;
-		} else
-			mt_mask = MTRR_TYPE_UNCACHABLE <<
-				kvm_x86_ops->get_mt_mask_shift();
-		spte |= mt_mask;
-	}
+	if (tdp_enabled)
+		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
+			kvm_is_mmio_pfn(pfn));
 
 	spte |= (u64)pfn << PAGE_SHIFT;
 
@@ -1765,8 +1735,8 @@ set_pte:
 static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 			 unsigned pt_access, unsigned pte_access,
 			 int user_fault, int write_fault, int dirty,
-			 int *ptwrite, int largepage, int global,
-			 gfn_t gfn, pfn_t pfn, bool speculative)
+			 int *ptwrite, int largepage, gfn_t gfn,
+			 pfn_t pfn, bool speculative)
 {
 	int was_rmapped = 0;
 	int was_writeble = is_writeble_pte(*shadow_pte);
@@ -1795,7 +1765,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 			was_rmapped = 1;
 	}
 	if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault,
-		      dirty, largepage, global, gfn, pfn, speculative, true)) {
+		      dirty, largepage, gfn, pfn, speculative, true)) {
 		if (write_fault)
 			*ptwrite = 1;
 		kvm_x86_ops->tlb_flush(vcpu);
@@ -1843,7 +1813,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 		    || (largepage && iterator.level == PT_DIRECTORY_LEVEL)) {
 			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
 				     0, write, 1, &pt_write,
-				     largepage, 0, gfn, pfn, false);
+				     largepage, gfn, pfn, false);
 			++vcpu->stat.pf_fixed;
 			break;
 		}
@@ -1942,7 +1912,19 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu.root_hpa = INVALID_PAGE;
 }
 
-static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
+static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
+{
+	int ret = 0;
+
+	if (!kvm_is_visible_gfn(vcpu->kvm, root_gfn)) {
+		set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+		ret = 1;
+	}
+
+	return ret;
+}
+
+static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
 {
 	int i;
 	gfn_t root_gfn;
@@ -1957,13 +1939,15 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 		ASSERT(!VALID_PAGE(root));
 		if (tdp_enabled)
 			direct = 1;
+		if (mmu_check_root(vcpu, root_gfn))
+			return 1;
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
 				      PT64_ROOT_LEVEL, direct,
 				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
 		vcpu->arch.mmu.root_hpa = root;
-		return;
+		return 0;
 	}
 	direct = !is_paging(vcpu);
 	if (tdp_enabled)
@@ -1980,6 +1964,8 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 			root_gfn = vcpu->arch.pdptrs[i] >> PAGE_SHIFT;
 		} else if (vcpu->arch.mmu.root_level == 0)
 			root_gfn = 0;
+		if (mmu_check_root(vcpu, root_gfn))
+			return 1;
 		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
 				      PT32_ROOT_LEVEL, direct,
 				      ACC_ALL, NULL);
@@ -1988,6 +1974,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 		vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
 	}
 	vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+	return 0;
 }
 
 static void mmu_sync_roots(struct kvm_vcpu *vcpu)
@@ -2006,7 +1993,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
 	for (i = 0; i < 4; ++i) {
 		hpa_t root = vcpu->arch.mmu.pae_root[i];
 
-		if (root) {
+		if (root && VALID_PAGE(root)) {
 			root &= PT64_BASE_ADDR_MASK;
 			sp = page_header(root);
 			mmu_sync_children(vcpu, sp);
@@ -2014,15 +2001,6 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void mmu_sync_global(struct kvm_vcpu *vcpu)
-{
-	struct kvm *kvm = vcpu->kvm;
-	struct kvm_mmu_page *sp, *n;
-
-	list_for_each_entry_safe(sp, n, &kvm->arch.oos_global_pages, oos_link)
-		kvm_sync_page(vcpu, sp);
-}
-
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 {
 	spin_lock(&vcpu->kvm->mmu_lock);
@@ -2030,13 +2008,6 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
 
-void kvm_mmu_sync_global(struct kvm_vcpu *vcpu)
-{
-	spin_lock(&vcpu->kvm->mmu_lock);
-	mmu_sync_global(vcpu);
-	spin_unlock(&vcpu->kvm->mmu_lock);
-}
-
 static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr)
 {
 	return vaddr;
@@ -2151,6 +2122,14 @@ static void paging_free(struct kvm_vcpu *vcpu)
 	nonpaging_free(vcpu);
 }
 
+static bool is_rsvd_bits_set(struct kvm_vcpu *vcpu, u64 gpte, int level)
+{
+	int bit7;
+
+	bit7 = (gpte >> 7) & 1;
+	return (gpte & vcpu->arch.mmu.rsvd_bits_mask[bit7][level-1]) != 0;
+}
+
 #define PTTYPE 64
 #include "paging_tmpl.h"
 #undef PTTYPE
@@ -2159,6 +2138,59 @@ static void paging_free(struct kvm_vcpu *vcpu)
 #include "paging_tmpl.h"
 #undef PTTYPE
 
+static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
+{
+	struct kvm_mmu *context = &vcpu->arch.mmu;
+	int maxphyaddr = cpuid_maxphyaddr(vcpu);
+	u64 exb_bit_rsvd = 0;
+
+	if (!is_nx(vcpu))
+		exb_bit_rsvd = rsvd_bits(63, 63);
+	switch (level) {
+	case PT32_ROOT_LEVEL:
+		/* no rsvd bits for 2 level 4K page table entries */
+		context->rsvd_bits_mask[0][1] = 0;
+		context->rsvd_bits_mask[0][0] = 0;
+		if (is_cpuid_PSE36())
+			/* 36bits PSE 4MB page */
+			context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
+		else
+			/* 32 bits PSE 4MB page */
+			context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
+		context->rsvd_bits_mask[1][0] = ~0ull;
+		break;
+	case PT32E_ROOT_LEVEL:
+		context->rsvd_bits_mask[0][2] =
+			rsvd_bits(maxphyaddr, 63) |
+			rsvd_bits(7, 8) | rsvd_bits(1, 2);	/* PDPTE */
+		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 62);	/* PDE */
+		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 62); 	/* PTE */
+		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 62) |
+			rsvd_bits(13, 20);		/* large page */
+		context->rsvd_bits_mask[1][0] = ~0ull;
+		break;
+	case PT64_ROOT_LEVEL:
+		context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+		context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8);
+		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 51);
+		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 51);
+		context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
+		context->rsvd_bits_mask[1][2] = context->rsvd_bits_mask[0][2];
+		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
+			rsvd_bits(maxphyaddr, 51) |
+			rsvd_bits(13, 20);		/* large page */
+		context->rsvd_bits_mask[1][0] = ~0ull;
+		break;
+	}
+}
+
 static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level)
 {
 	struct kvm_mmu *context = &vcpu->arch.mmu;
@@ -2179,6 +2211,7 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level)
 
 static int paging64_init_context(struct kvm_vcpu *vcpu)
 {
+	reset_rsvds_bits_mask(vcpu, PT64_ROOT_LEVEL);
 	return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL);
 }
 
@@ -2186,6 +2219,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *context = &vcpu->arch.mmu;
 
+	reset_rsvds_bits_mask(vcpu, PT32_ROOT_LEVEL);
 	context->new_cr3 = paging_new_cr3;
 	context->page_fault = paging32_page_fault;
 	context->gva_to_gpa = paging32_gva_to_gpa;
@@ -2201,6 +2235,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu)
 
 static int paging32E_init_context(struct kvm_vcpu *vcpu)
 {
+	reset_rsvds_bits_mask(vcpu, PT32E_ROOT_LEVEL);
 	return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
 }
 
@@ -2221,12 +2256,15 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 		context->gva_to_gpa = nonpaging_gva_to_gpa;
 		context->root_level = 0;
 	} else if (is_long_mode(vcpu)) {
+		reset_rsvds_bits_mask(vcpu, PT64_ROOT_LEVEL);
 		context->gva_to_gpa = paging64_gva_to_gpa;
 		context->root_level = PT64_ROOT_LEVEL;
 	} else if (is_pae(vcpu)) {
+		reset_rsvds_bits_mask(vcpu, PT32E_ROOT_LEVEL);
 		context->gva_to_gpa = paging64_gva_to_gpa;
 		context->root_level = PT32E_ROOT_LEVEL;
 	} else {
+		reset_rsvds_bits_mask(vcpu, PT32_ROOT_LEVEL);
 		context->gva_to_gpa = paging32_gva_to_gpa;
 		context->root_level = PT32_ROOT_LEVEL;
 	}
@@ -2290,9 +2328,11 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
 		goto out;
 	spin_lock(&vcpu->kvm->mmu_lock);
 	kvm_mmu_free_some_pages(vcpu);
-	mmu_alloc_roots(vcpu);
+	r = mmu_alloc_roots(vcpu);
 	mmu_sync_roots(vcpu);
 	spin_unlock(&vcpu->kvm->mmu_lock);
+	if (r)
+		goto out;
 	kvm_x86_ops->set_cr3(vcpu, vcpu->arch.mmu.root_hpa);
 	kvm_mmu_flush_tlb(vcpu);
 out:
@@ -2638,14 +2678,6 @@ EXPORT_SYMBOL_GPL(kvm_disable_tdp);
 
 static void free_mmu_pages(struct kvm_vcpu *vcpu)
 {
-	struct kvm_mmu_page *sp;
-
-	while (!list_empty(&vcpu->kvm->arch.active_mmu_pages)) {
-		sp = container_of(vcpu->kvm->arch.active_mmu_pages.next,
-				  struct kvm_mmu_page, link);
-		kvm_mmu_zap_page(vcpu->kvm, sp);
-		cond_resched();
-	}
 	free_page((unsigned long)vcpu->arch.mmu.pae_root);
 }
 
@@ -2710,7 +2742,6 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
 {
 	struct kvm_mmu_page *sp;
 
-	spin_lock(&kvm->mmu_lock);
 	list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link) {
 		int i;
 		u64 *pt;
@@ -2725,7 +2756,6 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
 				pt[i] &= ~PT_WRITABLE_MASK;
 	}
 	kvm_flush_remote_tlbs(kvm);
-	spin_unlock(&kvm->mmu_lock);
 }
 
 void kvm_mmu_zap_all(struct kvm *kvm)
@@ -3007,11 +3037,13 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
 				       " in nonleaf level: levels %d gva %lx"
 				       " level %d pte %llx\n", audit_msg,
 				       vcpu->arch.mmu.root_level, va, level, ent);
-
-			audit_mappings_page(vcpu, ent, va, level - 1);
+			else
+				audit_mappings_page(vcpu, ent, va, level - 1);
 		} else {
 			gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va);
-			hpa_t hpa = (hpa_t)gpa_to_pfn(vcpu, gpa) << PAGE_SHIFT;
+			gfn_t gfn = gpa >> PAGE_SHIFT;
+			pfn_t pfn = gfn_to_pfn(vcpu->kvm, gfn);
+			hpa_t hpa = (hpa_t)pfn << PAGE_SHIFT;
 
 			if (is_shadow_present_pte(ent)
 			    && (ent & PT64_BASE_ADDR_MASK) != hpa)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index eaab2145f62b..3494a2fb136e 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -75,4 +75,9 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
 	return vcpu->arch.cr0 & X86_CR0_PG;
 }
 
+static inline int is_present_pte(unsigned long pte)
+{
+	return pte & PT_PRESENT_MASK;
+}
+
 #endif
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 6bd70206c561..258e4591e1ca 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -123,6 +123,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 	gfn_t table_gfn;
 	unsigned index, pt_access, pte_access;
 	gpa_t pte_gpa;
+	int rsvd_fault = 0;
 
 	pgprintk("%s: addr %lx\n", __func__, addr);
 walk:
@@ -157,6 +158,10 @@ walk:
 		if (!is_present_pte(pte))
 			goto not_present;
 
+		rsvd_fault = is_rsvd_bits_set(vcpu, pte, walker->level);
+		if (rsvd_fault)
+			goto access_error;
+
 		if (write_fault && !is_writeble_pte(pte))
 			if (user_fault || is_write_protection(vcpu))
 				goto access_error;
@@ -209,7 +214,6 @@ walk:
 		if (ret)
 			goto walk;
 		pte |= PT_DIRTY_MASK;
-		kvm_mmu_pte_write(vcpu, pte_gpa, (u8 *)&pte, sizeof(pte), 0);
 		walker->ptes[walker->level - 1] = pte;
 	}
 
@@ -233,6 +237,8 @@ err:
 		walker->error_code |= PFERR_USER_MASK;
 	if (fetch_fault)
 		walker->error_code |= PFERR_FETCH_MASK;
+	if (rsvd_fault)
+		walker->error_code |= PFERR_RSVD_MASK;
 	return 0;
 }
 
@@ -262,8 +268,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
 	kvm_get_pfn(pfn);
 	mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
 		     gpte & PT_DIRTY_MASK, NULL, largepage,
-		     gpte & PT_GLOBAL_MASK, gpte_to_gfn(gpte),
-		     pfn, true);
+		     gpte_to_gfn(gpte), pfn, true);
 }
 
 /*
@@ -297,7 +302,6 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 				     user_fault, write_fault,
 				     gw->ptes[gw->level-1] & PT_DIRTY_MASK,
 				     ptwrite, largepage,
-				     gw->ptes[gw->level-1] & PT_GLOBAL_MASK,
 				     gw->gfn, pfn, false);
 			break;
 		}
@@ -380,7 +384,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 		return r;
 
 	/*
-	 * Look up the shadow pte for the faulting address.
+	 * Look up the guest pte for the faulting address.
 	 */
 	r = FNAME(walk_addr)(&walker, vcpu, addr, write_fault, user_fault,
 			     fetch_fault);
@@ -586,7 +590,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		nr_present++;
 		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
 		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
-			 is_dirty_pte(gpte), 0, gpte & PT_GLOBAL_MASK, gfn,
+			 is_dirty_pte(gpte), 0, gfn,
 			 spte_to_pfn(sp->spt[i]), true, false);
 	}
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1f8510c51d6e..71510e07e69e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -19,6 +19,7 @@
 #include "irq.h"
 #include "mmu.h"
 #include "kvm_cache_regs.h"
+#include "x86.h"
 
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -69,7 +70,6 @@ module_param(npt, int, S_IRUGO);
 static int nested = 0;
 module_param(nested, int, S_IRUGO);
 
-static void kvm_reput_irq(struct vcpu_svm *svm);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 
 static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override);
@@ -132,24 +132,6 @@ static inline u32 svm_has(u32 feat)
 	return svm_features & feat;
 }
 
-static inline u8 pop_irq(struct kvm_vcpu *vcpu)
-{
-	int word_index = __ffs(vcpu->arch.irq_summary);
-	int bit_index = __ffs(vcpu->arch.irq_pending[word_index]);
-	int irq = word_index * BITS_PER_LONG + bit_index;
-
-	clear_bit(bit_index, &vcpu->arch.irq_pending[word_index]);
-	if (!vcpu->arch.irq_pending[word_index])
-		clear_bit(word_index, &vcpu->arch.irq_summary);
-	return irq;
-}
-
-static inline void push_irq(struct kvm_vcpu *vcpu, u8 irq)
-{
-	set_bit(irq, vcpu->arch.irq_pending);
-	set_bit(irq / BITS_PER_LONG, &vcpu->arch.irq_summary);
-}
-
 static inline void clgi(void)
 {
 	asm volatile (__ex(SVM_CLGI));
@@ -214,25 +196,41 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 	svm->vmcb->control.event_inj_err = error_code;
 }
 
-static bool svm_exception_injected(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	return !(svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID);
-}
-
 static int is_external_interrupt(u32 info)
 {
 	info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID;
 	return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR);
 }
 
+static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u32 ret = 0;
+
+	if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
+		ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS;
+	return ret & mask;
+}
+
+static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (mask == 0)
+		svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK;
+	else
+		svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK;
+
+}
+
 static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (!svm->next_rip) {
-		printk(KERN_DEBUG "%s: NOP\n", __func__);
+		if (emulate_instruction(vcpu, vcpu->run, 0, 0, EMULTYPE_SKIP) !=
+				EMULATE_DONE)
+			printk(KERN_DEBUG "%s: NOP\n", __func__);
 		return;
 	}
 	if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE)
@@ -240,9 +238,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 		       __func__, kvm_rip_read(vcpu), svm->next_rip);
 
 	kvm_rip_write(vcpu, svm->next_rip);
-	svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK;
-
-	vcpu->arch.interrupt_window_open = (svm->vcpu.arch.hflags & HF_GIF_MASK);
+	svm_set_interrupt_shadow(vcpu, 0);
 }
 
 static int has_svm(void)
@@ -830,6 +826,15 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 		if (!var->unusable)
 			var->type |= 0x1;
 		break;
+	case VCPU_SREG_SS:
+		/* On AMD CPUs sometimes the DB bit in the segment
+		 * descriptor is left as 1, although the whole segment has
+		 * been made unusable. Clear it here to pass an Intel VMX
+		 * entry check when cross vendor migrating.
+		 */
+		if (var->unusable)
+			var->db = 0;
+		break;
 	}
 }
 
@@ -960,15 +965,16 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 
 }
 
-static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
+static void update_db_intercept(struct kvm_vcpu *vcpu)
 {
-	int old_debug = vcpu->guest_debug;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	vcpu->guest_debug = dbg->control;
-
 	svm->vmcb->control.intercept_exceptions &=
 		~((1 << DB_VECTOR) | (1 << BP_VECTOR));
+
+	if (vcpu->arch.singlestep)
+		svm->vmcb->control.intercept_exceptions |= (1 << DB_VECTOR);
+
 	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
 		if (vcpu->guest_debug &
 		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
@@ -979,6 +985,16 @@ static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 				1 << BP_VECTOR;
 	} else
 		vcpu->guest_debug = 0;
+}
+
+static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
+{
+	int old_debug = vcpu->guest_debug;
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	vcpu->guest_debug = dbg->control;
+
+	update_db_intercept(vcpu);
 
 	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
 		svm->vmcb->save.dr7 = dbg->arch.debugreg[7];
@@ -993,16 +1009,6 @@ static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 	return 0;
 }
 
-static int svm_get_irq(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-	u32 exit_int_info = svm->vmcb->control.exit_int_info;
-
-	if (is_external_interrupt(exit_int_info))
-		return exit_int_info & SVM_EVTINJ_VEC_MASK;
-	return -1;
-}
-
 static void load_host_msrs(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_X86_64
@@ -1107,17 +1113,8 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value,
 
 static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
-	u32 exit_int_info = svm->vmcb->control.exit_int_info;
-	struct kvm *kvm = svm->vcpu.kvm;
 	u64 fault_address;
 	u32 error_code;
-	bool event_injection = false;
-
-	if (!irqchip_in_kernel(kvm) &&
-	    is_external_interrupt(exit_int_info)) {
-		event_injection = true;
-		push_irq(&svm->vcpu, exit_int_info & SVM_EVTINJ_VEC_MASK);
-	}
 
 	fault_address  = svm->vmcb->control.exit_info_2;
 	error_code = svm->vmcb->control.exit_info_1;
@@ -1137,23 +1134,40 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	 */
 	if (npt_enabled)
 		svm_flush_tlb(&svm->vcpu);
-
-	if (!npt_enabled && event_injection)
-		kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
+	else {
+		if (kvm_event_needs_reinjection(&svm->vcpu))
+			kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
+	}
 	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
 }
 
 static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
 	if (!(svm->vcpu.guest_debug &
-	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
+	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
+		!svm->vcpu.arch.singlestep) {
 		kvm_queue_exception(&svm->vcpu, DB_VECTOR);
 		return 1;
 	}
-	kvm_run->exit_reason = KVM_EXIT_DEBUG;
-	kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
-	kvm_run->debug.arch.exception = DB_VECTOR;
-	return 0;
+
+	if (svm->vcpu.arch.singlestep) {
+		svm->vcpu.arch.singlestep = false;
+		if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
+			svm->vmcb->save.rflags &=
+				~(X86_EFLAGS_TF | X86_EFLAGS_RF);
+		update_db_intercept(&svm->vcpu);
+	}
+
+	if (svm->vcpu.guest_debug &
+	    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)){
+		kvm_run->exit_reason = KVM_EXIT_DEBUG;
+		kvm_run->debug.arch.pc =
+			svm->vmcb->save.cs.base + svm->vmcb->save.rip;
+		kvm_run->debug.arch.exception = DB_VECTOR;
+		return 0;
+	}
+
+	return 1;
 }
 
 static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
@@ -1842,17 +1856,51 @@ static int task_switch_interception(struct vcpu_svm *svm,
 				    struct kvm_run *kvm_run)
 {
 	u16 tss_selector;
+	int reason;
+	int int_type = svm->vmcb->control.exit_int_info &
+		SVM_EXITINTINFO_TYPE_MASK;
+	int int_vec = svm->vmcb->control.exit_int_info & SVM_EVTINJ_VEC_MASK;
+	uint32_t type =
+		svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK;
+	uint32_t idt_v =
+		svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID;
 
 	tss_selector = (u16)svm->vmcb->control.exit_info_1;
+
 	if (svm->vmcb->control.exit_info_2 &
 	    (1ULL << SVM_EXITINFOSHIFT_TS_REASON_IRET))
-		return kvm_task_switch(&svm->vcpu, tss_selector,
-				       TASK_SWITCH_IRET);
-	if (svm->vmcb->control.exit_info_2 &
-	    (1ULL << SVM_EXITINFOSHIFT_TS_REASON_JMP))
-		return kvm_task_switch(&svm->vcpu, tss_selector,
-				       TASK_SWITCH_JMP);
-	return kvm_task_switch(&svm->vcpu, tss_selector, TASK_SWITCH_CALL);
+		reason = TASK_SWITCH_IRET;
+	else if (svm->vmcb->control.exit_info_2 &
+		 (1ULL << SVM_EXITINFOSHIFT_TS_REASON_JMP))
+		reason = TASK_SWITCH_JMP;
+	else if (idt_v)
+		reason = TASK_SWITCH_GATE;
+	else
+		reason = TASK_SWITCH_CALL;
+
+	if (reason == TASK_SWITCH_GATE) {
+		switch (type) {
+		case SVM_EXITINTINFO_TYPE_NMI:
+			svm->vcpu.arch.nmi_injected = false;
+			break;
+		case SVM_EXITINTINFO_TYPE_EXEPT:
+			kvm_clear_exception_queue(&svm->vcpu);
+			break;
+		case SVM_EXITINTINFO_TYPE_INTR:
+			kvm_clear_interrupt_queue(&svm->vcpu);
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (reason != TASK_SWITCH_GATE ||
+	    int_type == SVM_EXITINTINFO_TYPE_SOFT ||
+	    (int_type == SVM_EXITINTINFO_TYPE_EXEPT &&
+	     (int_vec == OF_VECTOR || int_vec == BP_VECTOR)))
+		skip_emulated_instruction(&svm->vcpu);
+
+	return kvm_task_switch(&svm->vcpu, tss_selector, reason);
 }
 
 static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
@@ -1862,6 +1910,14 @@ static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
+static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	++svm->vcpu.stat.nmi_window_exits;
+	svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+	svm->vcpu.arch.hflags |= HF_IRET_MASK;
+	return 1;
+}
+
 static int invlpg_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
 	if (emulate_instruction(&svm->vcpu, kvm_run, 0, 0, 0) != EMULATE_DONE)
@@ -1879,8 +1935,14 @@ static int emulate_on_interception(struct vcpu_svm *svm,
 
 static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
+	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
+	/* instruction emulation calls kvm_set_cr8() */
 	emulate_instruction(&svm->vcpu, NULL, 0, 0, 0);
-	if (irqchip_in_kernel(svm->vcpu.kvm))
+	if (irqchip_in_kernel(svm->vcpu.kvm)) {
+		svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
+		return 1;
+	}
+	if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
 		return 1;
 	kvm_run->exit_reason = KVM_EXIT_SET_TPR;
 	return 0;
@@ -2090,8 +2152,9 @@ static int interrupt_window_interception(struct vcpu_svm *svm,
 	 * If the user space waits to inject interrupts, exit as soon as
 	 * possible
 	 */
-	if (kvm_run->request_interrupt_window &&
-	    !svm->vcpu.arch.irq_summary) {
+	if (!irqchip_in_kernel(svm->vcpu.kvm) &&
+	    kvm_run->request_interrupt_window &&
+	    !kvm_cpu_has_interrupt(&svm->vcpu)) {
 		++svm->vcpu.stat.irq_window_exits;
 		kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
 		return 0;
@@ -2134,6 +2197,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_VINTR]			= interrupt_window_interception,
 	/* [SVM_EXIT_CR0_SEL_WRITE]		= emulate_on_interception, */
 	[SVM_EXIT_CPUID]			= cpuid_interception,
+	[SVM_EXIT_IRET]                         = iret_interception,
 	[SVM_EXIT_INVD]                         = emulate_on_interception,
 	[SVM_EXIT_HLT]				= halt_interception,
 	[SVM_EXIT_INVLPG]			= invlpg_interception,
@@ -2194,7 +2258,6 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		}
 	}
 
-	kvm_reput_irq(svm);
 
 	if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
@@ -2205,7 +2268,7 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	if (is_external_interrupt(svm->vmcb->control.exit_int_info) &&
 	    exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR &&
-	    exit_code != SVM_EXIT_NPF)
+	    exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH)
 		printk(KERN_ERR "%s: unexpected exit_ini_info 0x%x "
 		       "exit_code 0x%x\n",
 		       __func__, svm->vmcb->control.exit_int_info,
@@ -2242,6 +2305,15 @@ static void pre_svm_run(struct vcpu_svm *svm)
 		new_asid(svm, svm_data);
 }
 
+static void svm_inject_nmi(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;
+	vcpu->arch.hflags |= HF_NMI_MASK;
+	svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+	++vcpu->stat.nmi_injections;
+}
 
 static inline void svm_inject_irq(struct vcpu_svm *svm, int irq)
 {
@@ -2257,134 +2329,71 @@ static inline void svm_inject_irq(struct vcpu_svm *svm, int irq)
 		((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT);
 }
 
-static void svm_set_irq(struct kvm_vcpu *vcpu, int irq)
+static void svm_queue_irq(struct kvm_vcpu *vcpu, unsigned nr)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	svm->vmcb->control.event_inj = nr |
+		SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
+}
+
+static void svm_set_irq(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	nested_svm_intr(svm);
 
-	svm_inject_irq(svm, irq);
+	svm_queue_irq(vcpu, vcpu->arch.interrupt.nr);
 }
 
-static void update_cr8_intercept(struct kvm_vcpu *vcpu)
+static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (irr == -1)
+		return;
+
+	if (tpr >= irr)
+		svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR8_MASK;
+}
+
+static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb;
-	int max_irr, tpr;
-
-	if (!irqchip_in_kernel(vcpu->kvm) || vcpu->arch.apic->vapic_addr)
-		return;
-
-	vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
-
-	max_irr = kvm_lapic_find_highest_irr(vcpu);
-	if (max_irr == -1)
-		return;
-
-	tpr = kvm_lapic_get_cr8(vcpu) << 4;
-
-	if (tpr >= (max_irr & 0xf0))
-		vmcb->control.intercept_cr_write |= INTERCEPT_CR8_MASK;
+	return !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
+		!(svm->vcpu.arch.hflags & HF_NMI_MASK);
 }
 
-static void svm_intr_assist(struct kvm_vcpu *vcpu)
+static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb;
-	int intr_vector = -1;
-
-	if ((vmcb->control.exit_int_info & SVM_EVTINJ_VALID) &&
-	    ((vmcb->control.exit_int_info & SVM_EVTINJ_TYPE_MASK) == 0)) {
-		intr_vector = vmcb->control.exit_int_info &
-			      SVM_EVTINJ_VEC_MASK;
-		vmcb->control.exit_int_info = 0;
-		svm_inject_irq(svm, intr_vector);
-		goto out;
-	}
-
-	if (vmcb->control.int_ctl & V_IRQ_MASK)
-		goto out;
-
-	if (!kvm_cpu_has_interrupt(vcpu))
-		goto out;
-
-	if (nested_svm_intr(svm))
-		goto out;
-
-	if (!(svm->vcpu.arch.hflags & HF_GIF_MASK))
-		goto out;
-
-	if (!(vmcb->save.rflags & X86_EFLAGS_IF) ||
-	    (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) ||
-	    (vmcb->control.event_inj & SVM_EVTINJ_VALID)) {
-		/* unable to deliver irq, set pending irq */
-		svm_set_vintr(svm);
-		svm_inject_irq(svm, 0x0);
-		goto out;
-	}
-	/* Okay, we can deliver the interrupt: grab it and update PIC state. */
-	intr_vector = kvm_cpu_get_interrupt(vcpu);
-	svm_inject_irq(svm, intr_vector);
-out:
-	update_cr8_intercept(vcpu);
+	return (vmcb->save.rflags & X86_EFLAGS_IF) &&
+		!(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
+		(svm->vcpu.arch.hflags & HF_GIF_MASK);
 }
 
-static void kvm_reput_irq(struct vcpu_svm *svm)
+static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
-	struct vmcb_control_area *control = &svm->vmcb->control;
-
-	if ((control->int_ctl & V_IRQ_MASK)
-	    && !irqchip_in_kernel(svm->vcpu.kvm)) {
-		control->int_ctl &= ~V_IRQ_MASK;
-		push_irq(&svm->vcpu, control->int_vector);
-	}
-
-	svm->vcpu.arch.interrupt_window_open =
-		!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) &&
-		 (svm->vcpu.arch.hflags & HF_GIF_MASK);
+	svm_set_vintr(to_svm(vcpu));
+	svm_inject_irq(to_svm(vcpu), 0x0);
 }
 
-static void svm_do_inject_vector(struct vcpu_svm *svm)
-{
-	struct kvm_vcpu *vcpu = &svm->vcpu;
-	int word_index = __ffs(vcpu->arch.irq_summary);
-	int bit_index = __ffs(vcpu->arch.irq_pending[word_index]);
-	int irq = word_index * BITS_PER_LONG + bit_index;
-
-	clear_bit(bit_index, &vcpu->arch.irq_pending[word_index]);
-	if (!vcpu->arch.irq_pending[word_index])
-		clear_bit(word_index, &vcpu->arch.irq_summary);
-	svm_inject_irq(svm, irq);
-}
-
-static void do_interrupt_requests(struct kvm_vcpu *vcpu,
-				       struct kvm_run *kvm_run)
+static void enable_nmi_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct vmcb_control_area *control = &svm->vmcb->control;
 
-	if (nested_svm_intr(svm))
-		return;
+	if ((svm->vcpu.arch.hflags & (HF_NMI_MASK | HF_IRET_MASK))
+	    == HF_NMI_MASK)
+		return; /* IRET will cause a vm exit */
 
-	svm->vcpu.arch.interrupt_window_open =
-		(!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) &&
-		 (svm->vmcb->save.rflags & X86_EFLAGS_IF) &&
-		 (svm->vcpu.arch.hflags & HF_GIF_MASK));
-
-	if (svm->vcpu.arch.interrupt_window_open && svm->vcpu.arch.irq_summary)
-		/*
-		 * If interrupts enabled, and not blocked by sti or mov ss. Good.
-		 */
-		svm_do_inject_vector(svm);
-
-	/*
-	 * Interrupts blocked.  Wait for unblock.
-	 */
-	if (!svm->vcpu.arch.interrupt_window_open &&
-	    (svm->vcpu.arch.irq_summary || kvm_run->request_interrupt_window))
-		svm_set_vintr(svm);
-	else
-		svm_clear_vintr(svm);
+	/* Something prevents NMI from been injected. Single step over
+	   possible problem (IRET or exception injection or interrupt
+	   shadow) */
+	vcpu->arch.singlestep = true;
+	svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
+	update_db_intercept(vcpu);
 }
 
 static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
@@ -2407,7 +2416,7 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
 
 	if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) {
 		int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
-		kvm_lapic_set_tpr(vcpu, cr8);
+		kvm_set_cr8(vcpu, cr8);
 	}
 }
 
@@ -2416,14 +2425,54 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 cr8;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return;
-
 	cr8 = kvm_get_cr8(vcpu);
 	svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
 	svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
 }
 
+static void svm_complete_interrupts(struct vcpu_svm *svm)
+{
+	u8 vector;
+	int type;
+	u32 exitintinfo = svm->vmcb->control.exit_int_info;
+
+	if (svm->vcpu.arch.hflags & HF_IRET_MASK)
+		svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK);
+
+	svm->vcpu.arch.nmi_injected = false;
+	kvm_clear_exception_queue(&svm->vcpu);
+	kvm_clear_interrupt_queue(&svm->vcpu);
+
+	if (!(exitintinfo & SVM_EXITINTINFO_VALID))
+		return;
+
+	vector = exitintinfo & SVM_EXITINTINFO_VEC_MASK;
+	type = exitintinfo & SVM_EXITINTINFO_TYPE_MASK;
+
+	switch (type) {
+	case SVM_EXITINTINFO_TYPE_NMI:
+		svm->vcpu.arch.nmi_injected = true;
+		break;
+	case SVM_EXITINTINFO_TYPE_EXEPT:
+		/* In case of software exception do not reinject an exception
+		   vector, but re-execute and instruction instead */
+		if (kvm_exception_is_soft(vector))
+			break;
+		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
+			u32 err = svm->vmcb->control.exit_int_info_err;
+			kvm_queue_exception_e(&svm->vcpu, vector, err);
+
+		} else
+			kvm_queue_exception(&svm->vcpu, vector);
+		break;
+	case SVM_EXITINTINFO_TYPE_INTR:
+		kvm_queue_interrupt(&svm->vcpu, vector, false);
+		break;
+	default:
+		break;
+	}
+}
+
 #ifdef CONFIG_X86_64
 #define R "r"
 #else
@@ -2552,6 +2601,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	sync_cr8_to_lapic(vcpu);
 
 	svm->next_rip = 0;
+
+	svm_complete_interrupts(svm);
 }
 
 #undef R
@@ -2617,7 +2668,7 @@ static int get_npt_level(void)
 #endif
 }
 
-static int svm_get_mt_mask_shift(void)
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 {
 	return 0;
 }
@@ -2667,17 +2718,21 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.run = svm_vcpu_run,
 	.handle_exit = handle_exit,
 	.skip_emulated_instruction = skip_emulated_instruction,
+	.set_interrupt_shadow = svm_set_interrupt_shadow,
+	.get_interrupt_shadow = svm_get_interrupt_shadow,
 	.patch_hypercall = svm_patch_hypercall,
-	.get_irq = svm_get_irq,
 	.set_irq = svm_set_irq,
+	.set_nmi = svm_inject_nmi,
 	.queue_exception = svm_queue_exception,
-	.exception_injected = svm_exception_injected,
-	.inject_pending_irq = svm_intr_assist,
-	.inject_pending_vectors = do_interrupt_requests,
+	.interrupt_allowed = svm_interrupt_allowed,
+	.nmi_allowed = svm_nmi_allowed,
+	.enable_nmi_window = enable_nmi_window,
+	.enable_irq_window = enable_irq_window,
+	.update_cr8_intercept = update_cr8_intercept,
 
 	.set_tss_addr = svm_set_tss_addr,
 	.get_tdp_level = get_npt_level,
-	.get_mt_mask_shift = svm_get_mt_mask_shift,
+	.get_mt_mask = svm_get_mt_mask,
 };
 
 static int __init svm_init(void)
diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c
new file mode 100644
index 000000000000..86dbac072d0c
--- /dev/null
+++ b/arch/x86/kvm/timer.c
@@ -0,0 +1,46 @@
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/hrtimer.h>
+#include <asm/atomic.h>
+#include "kvm_timer.h"
+
+static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer)
+{
+	int restart_timer = 0;
+	wait_queue_head_t *q = &vcpu->wq;
+
+	/* FIXME: this code should not know anything about vcpus */
+	if (!atomic_inc_and_test(&ktimer->pending))
+		set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
+
+	if (!ktimer->reinject)
+		atomic_set(&ktimer->pending, 1);
+
+	if (waitqueue_active(q))
+		wake_up_interruptible(q);
+
+	if (ktimer->t_ops->is_periodic(ktimer)) {
+		hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
+		restart_timer = 1;
+	}
+
+	return restart_timer;
+}
+
+enum hrtimer_restart kvm_timer_fn(struct hrtimer *data)
+{
+	int restart_timer;
+	struct kvm_vcpu *vcpu;
+	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+
+	vcpu = ktimer->kvm->vcpus[ktimer->vcpu_id];
+	if (!vcpu)
+		return HRTIMER_NORESTART;
+
+	restart_timer = __kvm_timer_fn(vcpu, ktimer);
+	if (restart_timer)
+		return HRTIMER_RESTART;
+	else
+		return HRTIMER_NORESTART;
+}
+
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bb481330716f..32d6ae8fb60e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -32,26 +32,27 @@
 #include <asm/desc.h>
 #include <asm/vmx.h>
 #include <asm/virtext.h>
+#include <asm/mce.h>
 
 #define __ex(x) __kvm_handle_fault_on_reboot(x)
 
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
-static int bypass_guest_pf = 1;
-module_param(bypass_guest_pf, bool, 0);
+static int __read_mostly bypass_guest_pf = 1;
+module_param(bypass_guest_pf, bool, S_IRUGO);
 
-static int enable_vpid = 1;
-module_param(enable_vpid, bool, 0);
+static int __read_mostly enable_vpid = 1;
+module_param_named(vpid, enable_vpid, bool, 0444);
 
-static int flexpriority_enabled = 1;
-module_param(flexpriority_enabled, bool, 0);
+static int __read_mostly flexpriority_enabled = 1;
+module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO);
 
-static int enable_ept = 1;
-module_param(enable_ept, bool, 0);
+static int __read_mostly enable_ept = 1;
+module_param_named(ept, enable_ept, bool, S_IRUGO);
 
-static int emulate_invalid_guest_state = 0;
-module_param(emulate_invalid_guest_state, bool, 0);
+static int __read_mostly emulate_invalid_guest_state = 0;
+module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 
 struct vmcs {
 	u32 revision_id;
@@ -97,6 +98,7 @@ struct vcpu_vmx {
 	int soft_vnmi_blocked;
 	ktime_t entry_time;
 	s64 vnmi_blocked_time;
+	u32 exit_reason;
 };
 
 static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
@@ -111,9 +113,10 @@ static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
 static DEFINE_PER_CPU(struct list_head, vcpus_on_cpu);
 
-static struct page *vmx_io_bitmap_a;
-static struct page *vmx_io_bitmap_b;
-static struct page *vmx_msr_bitmap;
+static unsigned long *vmx_io_bitmap_a;
+static unsigned long *vmx_io_bitmap_b;
+static unsigned long *vmx_msr_bitmap_legacy;
+static unsigned long *vmx_msr_bitmap_longmode;
 
 static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
 static DEFINE_SPINLOCK(vmx_vpid_lock);
@@ -213,70 +216,78 @@ static inline int is_external_interrupt(u32 intr_info)
 		== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
 }
 
+static inline int is_machine_check(u32 intr_info)
+{
+	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
+			     INTR_INFO_VALID_MASK)) ==
+		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
+}
+
 static inline int cpu_has_vmx_msr_bitmap(void)
 {
-	return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS);
+	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
 }
 
 static inline int cpu_has_vmx_tpr_shadow(void)
 {
-	return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW);
+	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
 }
 
 static inline int vm_need_tpr_shadow(struct kvm *kvm)
 {
-	return ((cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm)));
+	return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm));
 }
 
 static inline int cpu_has_secondary_exec_ctrls(void)
 {
-	return (vmcs_config.cpu_based_exec_ctrl &
-		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS);
+	return vmcs_config.cpu_based_exec_ctrl &
+		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
 }
 
 static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
 {
-	return flexpriority_enabled
-		&& (vmcs_config.cpu_based_2nd_exec_ctrl &
-		    SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+}
+
+static inline bool cpu_has_vmx_flexpriority(void)
+{
+	return cpu_has_vmx_tpr_shadow() &&
+		cpu_has_vmx_virtualize_apic_accesses();
 }
 
 static inline int cpu_has_vmx_invept_individual_addr(void)
 {
-	return (!!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT));
+	return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
 }
 
 static inline int cpu_has_vmx_invept_context(void)
 {
-	return (!!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT));
+	return !!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT);
 }
 
 static inline int cpu_has_vmx_invept_global(void)
 {
-	return (!!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT));
+	return !!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT);
 }
 
 static inline int cpu_has_vmx_ept(void)
 {
-	return (vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_ENABLE_EPT);
-}
-
-static inline int vm_need_ept(void)
-{
-	return (cpu_has_vmx_ept() && enable_ept);
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENABLE_EPT;
 }
 
 static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
 {
-	return ((cpu_has_vmx_virtualize_apic_accesses()) &&
-		(irqchip_in_kernel(kvm)));
+	return flexpriority_enabled &&
+		(cpu_has_vmx_virtualize_apic_accesses()) &&
+		(irqchip_in_kernel(kvm));
 }
 
 static inline int cpu_has_vmx_vpid(void)
 {
-	return (vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_ENABLE_VPID);
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENABLE_VPID;
 }
 
 static inline int cpu_has_virtual_nmis(void)
@@ -284,6 +295,11 @@ static inline int cpu_has_virtual_nmis(void)
 	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
 }
 
+static inline bool report_flexpriority(void)
+{
+	return flexpriority_enabled;
+}
+
 static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
 {
 	int i;
@@ -381,7 +397,7 @@ static inline void ept_sync_global(void)
 
 static inline void ept_sync_context(u64 eptp)
 {
-	if (vm_need_ept()) {
+	if (enable_ept) {
 		if (cpu_has_vmx_invept_context())
 			__invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0);
 		else
@@ -391,7 +407,7 @@ static inline void ept_sync_context(u64 eptp)
 
 static inline void ept_sync_individual_addr(u64 eptp, gpa_t gpa)
 {
-	if (vm_need_ept()) {
+	if (enable_ept) {
 		if (cpu_has_vmx_invept_individual_addr())
 			__invept(VMX_EPT_EXTENT_INDIVIDUAL_ADDR,
 					eptp, gpa);
@@ -478,7 +494,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 {
 	u32 eb;
 
-	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR);
+	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR);
 	if (!vcpu->fpu_active)
 		eb |= 1u << NM_VECTOR;
 	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
@@ -488,9 +504,9 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
 			eb |= 1u << BP_VECTOR;
 	}
-	if (vcpu->arch.rmode.active)
+	if (vcpu->arch.rmode.vm86_active)
 		eb = ~0;
-	if (vm_need_ept())
+	if (enable_ept)
 		eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
@@ -724,29 +740,50 @@ static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 
 static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
-	if (vcpu->arch.rmode.active)
+	if (vcpu->arch.rmode.vm86_active)
 		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
 	vmcs_writel(GUEST_RFLAGS, rflags);
 }
 
+static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
+{
+	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
+	int ret = 0;
+
+	if (interruptibility & GUEST_INTR_STATE_STI)
+		ret |= X86_SHADOW_INT_STI;
+	if (interruptibility & GUEST_INTR_STATE_MOV_SS)
+		ret |= X86_SHADOW_INT_MOV_SS;
+
+	return ret & mask;
+}
+
+static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
+{
+	u32 interruptibility_old = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
+	u32 interruptibility = interruptibility_old;
+
+	interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);
+
+	if (mask & X86_SHADOW_INT_MOV_SS)
+		interruptibility |= GUEST_INTR_STATE_MOV_SS;
+	if (mask & X86_SHADOW_INT_STI)
+		interruptibility |= GUEST_INTR_STATE_STI;
+
+	if ((interruptibility != interruptibility_old))
+		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility);
+}
+
 static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	unsigned long rip;
-	u32 interruptibility;
 
 	rip = kvm_rip_read(vcpu);
 	rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
 	kvm_rip_write(vcpu, rip);
 
-	/*
-	 * We emulated an instruction, so temporary interrupt blocking
-	 * should be removed, if set.
-	 */
-	interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
-	if (interruptibility & 3)
-		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
-			     interruptibility & ~3);
-	vcpu->arch.interrupt_window_open = 1;
+	/* skipping an emulated instruction also counts */
+	vmx_set_interrupt_shadow(vcpu, 0);
 }
 
 static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
@@ -760,7 +797,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
 	}
 
-	if (vcpu->arch.rmode.active) {
+	if (vcpu->arch.rmode.vm86_active) {
 		vmx->rmode.irq.pending = true;
 		vmx->rmode.irq.vector = nr;
 		vmx->rmode.irq.rip = kvm_rip_read(vcpu);
@@ -773,8 +810,9 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 		return;
 	}
 
-	if (nr == BP_VECTOR || nr == OF_VECTOR) {
-		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
+	if (kvm_exception_is_soft(nr)) {
+		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+			     vmx->vcpu.arch.event_exit_inst_len);
 		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
 	} else
 		intr_info |= INTR_TYPE_HARD_EXCEPTION;
@@ -782,11 +820,6 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
 }
 
-static bool vmx_exception_injected(struct kvm_vcpu *vcpu)
-{
-	return false;
-}
-
 /*
  * Swap MSR entry in host/guest MSR entry array.
  */
@@ -812,6 +845,7 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
 static void setup_msrs(struct vcpu_vmx *vmx)
 {
 	int save_nmsrs;
+	unsigned long *msr_bitmap;
 
 	vmx_load_host_state(vmx);
 	save_nmsrs = 0;
@@ -847,6 +881,15 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 		__find_msr_index(vmx, MSR_KERNEL_GS_BASE);
 #endif
 	vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER);
+
+	if (cpu_has_vmx_msr_bitmap()) {
+		if (is_long_mode(&vmx->vcpu))
+			msr_bitmap = vmx_msr_bitmap_longmode;
+		else
+			msr_bitmap = vmx_msr_bitmap_legacy;
+
+		vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
+	}
 }
 
 /*
@@ -1034,13 +1077,6 @@ static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 	return 0;
 }
 
-static int vmx_get_irq(struct kvm_vcpu *vcpu)
-{
-	if (!vcpu->arch.interrupt.pending)
-		return -1;
-	return vcpu->arch.interrupt.nr;
-}
-
 static __init int cpu_has_kvm_support(void)
 {
 	return cpu_has_vmx();
@@ -1294,6 +1330,18 @@ static __init int hardware_setup(void)
 	if (boot_cpu_has(X86_FEATURE_NX))
 		kvm_enable_efer_bits(EFER_NX);
 
+	if (!cpu_has_vmx_vpid())
+		enable_vpid = 0;
+
+	if (!cpu_has_vmx_ept())
+		enable_ept = 0;
+
+	if (!cpu_has_vmx_flexpriority())
+		flexpriority_enabled = 0;
+
+	if (!cpu_has_vmx_tpr_shadow())
+		kvm_x86_ops->update_cr8_intercept = NULL;
+
 	return alloc_kvm_area();
 }
 
@@ -1324,7 +1372,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	vmx->emulation_required = 1;
-	vcpu->arch.rmode.active = 0;
+	vcpu->arch.rmode.vm86_active = 0;
 
 	vmcs_writel(GUEST_TR_BASE, vcpu->arch.rmode.tr.base);
 	vmcs_write32(GUEST_TR_LIMIT, vcpu->arch.rmode.tr.limit);
@@ -1386,7 +1434,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	vmx->emulation_required = 1;
-	vcpu->arch.rmode.active = 1;
+	vcpu->arch.rmode.vm86_active = 1;
 
 	vcpu->arch.rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
 	vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));
@@ -1485,7 +1533,7 @@ static void exit_lmode(struct kvm_vcpu *vcpu)
 static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
 {
 	vpid_sync_vcpu_all(to_vmx(vcpu));
-	if (vm_need_ept())
+	if (enable_ept)
 		ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa));
 }
 
@@ -1555,10 +1603,10 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	vmx_fpu_deactivate(vcpu);
 
-	if (vcpu->arch.rmode.active && (cr0 & X86_CR0_PE))
+	if (vcpu->arch.rmode.vm86_active && (cr0 & X86_CR0_PE))
 		enter_pmode(vcpu);
 
-	if (!vcpu->arch.rmode.active && !(cr0 & X86_CR0_PE))
+	if (!vcpu->arch.rmode.vm86_active && !(cr0 & X86_CR0_PE))
 		enter_rmode(vcpu);
 
 #ifdef CONFIG_X86_64
@@ -1570,7 +1618,7 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	}
 #endif
 
-	if (vm_need_ept())
+	if (enable_ept)
 		ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);
 
 	vmcs_writel(CR0_READ_SHADOW, cr0);
@@ -1599,7 +1647,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	u64 eptp;
 
 	guest_cr3 = cr3;
-	if (vm_need_ept()) {
+	if (enable_ept) {
 		eptp = construct_eptp(cr3);
 		vmcs_write64(EPT_POINTER, eptp);
 		ept_sync_context(eptp);
@@ -1616,11 +1664,11 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long hw_cr4 = cr4 | (vcpu->arch.rmode.active ?
+	unsigned long hw_cr4 = cr4 | (vcpu->arch.rmode.vm86_active ?
 		    KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
 
 	vcpu->arch.cr4 = cr4;
-	if (vm_need_ept())
+	if (enable_ept)
 		ept_update_paging_mode_cr4(&hw_cr4, vcpu);
 
 	vmcs_writel(CR4_READ_SHADOW, cr4);
@@ -1699,7 +1747,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 	u32 ar;
 
-	if (vcpu->arch.rmode.active && seg == VCPU_SREG_TR) {
+	if (vcpu->arch.rmode.vm86_active && seg == VCPU_SREG_TR) {
 		vcpu->arch.rmode.tr.selector = var->selector;
 		vcpu->arch.rmode.tr.base = var->base;
 		vcpu->arch.rmode.tr.limit = var->limit;
@@ -1709,7 +1757,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	vmcs_writel(sf->base, var->base);
 	vmcs_write32(sf->limit, var->limit);
 	vmcs_write16(sf->selector, var->selector);
-	if (vcpu->arch.rmode.active && var->s) {
+	if (vcpu->arch.rmode.vm86_active && var->s) {
 		/*
 		 * Hack real-mode segments into vm86 compatibility.
 		 */
@@ -1982,7 +2030,7 @@ static int init_rmode_identity_map(struct kvm *kvm)
 	pfn_t identity_map_pfn;
 	u32 tmp;
 
-	if (!vm_need_ept())
+	if (!enable_ept)
 		return 1;
 	if (unlikely(!kvm->arch.ept_identity_pagetable)) {
 		printk(KERN_ERR "EPT: identity-mapping pagetable "
@@ -2071,7 +2119,7 @@ static void allocate_vpid(struct vcpu_vmx *vmx)
 	int vpid;
 
 	vmx->vpid = 0;
-	if (!enable_vpid || !cpu_has_vmx_vpid())
+	if (!enable_vpid)
 		return;
 	spin_lock(&vmx_vpid_lock);
 	vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
@@ -2082,9 +2130,9 @@ static void allocate_vpid(struct vcpu_vmx *vmx)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-static void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr)
+static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
 {
-	void *va;
+	int f = sizeof(unsigned long);
 
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
@@ -2094,16 +2142,21 @@ static void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr)
 	 * have the write-low and read-high bitmap offsets the wrong way round.
 	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
 	 */
-	va = kmap(msr_bitmap);
 	if (msr <= 0x1fff) {
-		__clear_bit(msr, va + 0x000); /* read-low */
-		__clear_bit(msr, va + 0x800); /* write-low */
+		__clear_bit(msr, msr_bitmap + 0x000 / f); /* read-low */
+		__clear_bit(msr, msr_bitmap + 0x800 / f); /* write-low */
 	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
 		msr &= 0x1fff;
-		__clear_bit(msr, va + 0x400); /* read-high */
-		__clear_bit(msr, va + 0xc00); /* write-high */
+		__clear_bit(msr, msr_bitmap + 0x400 / f); /* read-high */
+		__clear_bit(msr, msr_bitmap + 0xc00 / f); /* write-high */
 	}
-	kunmap(msr_bitmap);
+}
+
+static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
+{
+	if (!longmode_only)
+		__vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, msr);
+	__vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, msr);
 }
 
 /*
@@ -2121,11 +2174,11 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	u32 exec_control;
 
 	/* I/O */
-	vmcs_write64(IO_BITMAP_A, page_to_phys(vmx_io_bitmap_a));
-	vmcs_write64(IO_BITMAP_B, page_to_phys(vmx_io_bitmap_b));
+	vmcs_write64(IO_BITMAP_A, __pa(vmx_io_bitmap_a));
+	vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b));
 
 	if (cpu_has_vmx_msr_bitmap())
-		vmcs_write64(MSR_BITMAP, page_to_phys(vmx_msr_bitmap));
+		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy));
 
 	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
 
@@ -2141,7 +2194,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 				CPU_BASED_CR8_LOAD_EXITING;
 #endif
 	}
-	if (!vm_need_ept())
+	if (!enable_ept)
 		exec_control |= CPU_BASED_CR3_STORE_EXITING |
 				CPU_BASED_CR3_LOAD_EXITING  |
 				CPU_BASED_INVLPG_EXITING;
@@ -2154,7 +2207,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 				~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
 		if (vmx->vpid == 0)
 			exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
-		if (!vm_need_ept())
+		if (!enable_ept)
 			exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
 	}
@@ -2273,7 +2326,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	vmx->vcpu.arch.rmode.active = 0;
+	vmx->vcpu.arch.rmode.vm86_active = 0;
 
 	vmx->soft_vnmi_blocked = 0;
 
@@ -2402,14 +2455,16 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
 	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
 }
 
-static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq)
+static void vmx_inject_irq(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	uint32_t intr;
+	int irq = vcpu->arch.interrupt.nr;
 
 	KVMTRACE_1D(INJ_VIRQ, vcpu, (u32)irq, handler);
 
 	++vcpu->stat.irq_injections;
-	if (vcpu->arch.rmode.active) {
+	if (vcpu->arch.rmode.vm86_active) {
 		vmx->rmode.irq.pending = true;
 		vmx->rmode.irq.vector = irq;
 		vmx->rmode.irq.rip = kvm_rip_read(vcpu);
@@ -2419,8 +2474,14 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq)
 		kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1);
 		return;
 	}
-	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
-			irq | INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
+	intr = irq | INTR_INFO_VALID_MASK;
+	if (vcpu->arch.interrupt.soft) {
+		intr |= INTR_TYPE_SOFT_INTR;
+		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+			     vmx->vcpu.arch.event_exit_inst_len);
+	} else
+		intr |= INTR_TYPE_EXT_INTR;
+	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr);
 }
 
 static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
@@ -2441,7 +2502,7 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
 	}
 
 	++vcpu->stat.nmi_injections;
-	if (vcpu->arch.rmode.active) {
+	if (vcpu->arch.rmode.vm86_active) {
 		vmx->rmode.irq.pending = true;
 		vmx->rmode.irq.vector = NMI_VECTOR;
 		vmx->rmode.irq.rip = kvm_rip_read(vcpu);
@@ -2456,76 +2517,21 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
 			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
 }
 
-static void vmx_update_window_states(struct kvm_vcpu *vcpu)
+static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
 {
-	u32 guest_intr = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
-
-	vcpu->arch.nmi_window_open =
-		!(guest_intr & (GUEST_INTR_STATE_STI |
-				GUEST_INTR_STATE_MOV_SS |
-				GUEST_INTR_STATE_NMI));
 	if (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked)
-		vcpu->arch.nmi_window_open = 0;
+		return 0;
 
-	vcpu->arch.interrupt_window_open =
-		((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
-		 !(guest_intr & (GUEST_INTR_STATE_STI |
-				 GUEST_INTR_STATE_MOV_SS)));
+	return	!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS |
+				GUEST_INTR_STATE_NMI));
 }
 
-static void kvm_do_inject_irq(struct kvm_vcpu *vcpu)
+static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
-	int word_index = __ffs(vcpu->arch.irq_summary);
-	int bit_index = __ffs(vcpu->arch.irq_pending[word_index]);
-	int irq = word_index * BITS_PER_LONG + bit_index;
-
-	clear_bit(bit_index, &vcpu->arch.irq_pending[word_index]);
-	if (!vcpu->arch.irq_pending[word_index])
-		clear_bit(word_index, &vcpu->arch.irq_summary);
-	kvm_queue_interrupt(vcpu, irq);
-}
-
-static void do_interrupt_requests(struct kvm_vcpu *vcpu,
-				       struct kvm_run *kvm_run)
-{
-	vmx_update_window_states(vcpu);
-
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
-				GUEST_INTR_STATE_STI |
-				GUEST_INTR_STATE_MOV_SS);
-
-	if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
-		if (vcpu->arch.interrupt.pending) {
-			enable_nmi_window(vcpu);
-		} else if (vcpu->arch.nmi_window_open) {
-			vcpu->arch.nmi_pending = false;
-			vcpu->arch.nmi_injected = true;
-		} else {
-			enable_nmi_window(vcpu);
-			return;
-		}
-	}
-	if (vcpu->arch.nmi_injected) {
-		vmx_inject_nmi(vcpu);
-		if (vcpu->arch.nmi_pending)
-			enable_nmi_window(vcpu);
-		else if (vcpu->arch.irq_summary
-			 || kvm_run->request_interrupt_window)
-			enable_irq_window(vcpu);
-		return;
-	}
-
-	if (vcpu->arch.interrupt_window_open) {
-		if (vcpu->arch.irq_summary && !vcpu->arch.interrupt.pending)
-			kvm_do_inject_irq(vcpu);
-
-		if (vcpu->arch.interrupt.pending)
-			vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr);
-	}
-	if (!vcpu->arch.interrupt_window_open &&
-	    (vcpu->arch.irq_summary || kvm_run->request_interrupt_window))
-		enable_irq_window(vcpu);
+	return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
 }
 
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
@@ -2585,6 +2591,31 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+/*
+ * Trigger machine check on the host. We assume all the MSRs are already set up
+ * by the CPU and that we still run on the same CPU as the MCE occurred on.
+ * We pass a fake environment to the machine check handler because we want
+ * the guest to be always treated like user space, no matter what context
+ * it used internally.
+ */
+static void kvm_machine_check(void)
+{
+#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
+	struct pt_regs regs = {
+		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
+		.flags = X86_EFLAGS_IF,
+	};
+
+	do_machine_check(&regs, 0);
+#endif
+}
+
+static int handle_machine_check(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	/* already handled by vcpu_run */
+	return 1;
+}
+
 static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -2596,17 +2627,14 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	vect_info = vmx->idt_vectoring_info;
 	intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 
+	if (is_machine_check(intr_info))
+		return handle_machine_check(vcpu, kvm_run);
+
 	if ((vect_info & VECTORING_INFO_VALID_MASK) &&
 						!is_page_fault(intr_info))
 		printk(KERN_ERR "%s: unexpected, vectoring info 0x%x "
 		       "intr info 0x%x\n", __func__, vect_info, intr_info);
 
-	if (!irqchip_in_kernel(vcpu->kvm) && is_external_interrupt(vect_info)) {
-		int irq = vect_info & VECTORING_INFO_VECTOR_MASK;
-		set_bit(irq, vcpu->arch.irq_pending);
-		set_bit(irq / BITS_PER_LONG, &vcpu->arch.irq_summary);
-	}
-
 	if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR)
 		return 1;  /* already handled by vmx_vcpu_run() */
 
@@ -2628,17 +2656,17 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
 	if (is_page_fault(intr_info)) {
 		/* EPT won't cause page fault directly */
-		if (vm_need_ept())
+		if (enable_ept)
 			BUG();
 		cr2 = vmcs_readl(EXIT_QUALIFICATION);
 		KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2,
 			    (u32)((u64)cr2 >> 32), handler);
-		if (vcpu->arch.interrupt.pending || vcpu->arch.exception.pending)
+		if (kvm_event_needs_reinjection(vcpu))
 			kvm_mmu_unprotect_page_virt(vcpu, cr2);
 		return kvm_mmu_page_fault(vcpu, cr2, error_code);
 	}
 
-	if (vcpu->arch.rmode.active &&
+	if (vcpu->arch.rmode.vm86_active &&
 	    handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK,
 								error_code)) {
 		if (vcpu->arch.halt_request) {
@@ -2753,13 +2781,18 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			kvm_set_cr4(vcpu, kvm_register_read(vcpu, reg));
 			skip_emulated_instruction(vcpu);
 			return 1;
-		case 8:
-			kvm_set_cr8(vcpu, kvm_register_read(vcpu, reg));
-			skip_emulated_instruction(vcpu);
-			if (irqchip_in_kernel(vcpu->kvm))
-				return 1;
-			kvm_run->exit_reason = KVM_EXIT_SET_TPR;
-			return 0;
+		case 8: {
+				u8 cr8_prev = kvm_get_cr8(vcpu);
+				u8 cr8 = kvm_register_read(vcpu, reg);
+				kvm_set_cr8(vcpu, cr8);
+				skip_emulated_instruction(vcpu);
+				if (irqchip_in_kernel(vcpu->kvm))
+					return 1;
+				if (cr8_prev <= cr8)
+					return 1;
+				kvm_run->exit_reason = KVM_EXIT_SET_TPR;
+				return 0;
+			}
 		};
 		break;
 	case 2: /* clts */
@@ -2957,8 +2990,9 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu,
 	 * If the user space waits to inject interrupts, exit as soon as
 	 * possible
 	 */
-	if (kvm_run->request_interrupt_window &&
-	    !vcpu->arch.irq_summary) {
+	if (!irqchip_in_kernel(vcpu->kvm) &&
+	    kvm_run->request_interrupt_window &&
+	    !kvm_cpu_has_interrupt(vcpu)) {
 		kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
 		return 0;
 	}
@@ -2980,7 +3014,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
-	u64 exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 
 	kvm_mmu_invlpg(vcpu, exit_qualification);
 	skip_emulated_instruction(vcpu);
@@ -2996,11 +3030,11 @@ static int handle_wbinvd(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
-	u64 exit_qualification;
+	unsigned long exit_qualification;
 	enum emulation_result er;
 	unsigned long offset;
 
-	exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	offset = exit_qualification & 0xffful;
 
 	er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
@@ -3019,22 +3053,41 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qualification;
 	u16 tss_selector;
-	int reason;
+	int reason, type, idt_v;
+
+	idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK);
+	type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK);
 
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 
 	reason = (u32)exit_qualification >> 30;
-	if (reason == TASK_SWITCH_GATE && vmx->vcpu.arch.nmi_injected &&
-	    (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
-	    (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK)
-	    == INTR_TYPE_NMI_INTR) {
-		vcpu->arch.nmi_injected = false;
-		if (cpu_has_virtual_nmis())
-			vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
-				      GUEST_INTR_STATE_NMI);
+	if (reason == TASK_SWITCH_GATE && idt_v) {
+		switch (type) {
+		case INTR_TYPE_NMI_INTR:
+			vcpu->arch.nmi_injected = false;
+			if (cpu_has_virtual_nmis())
+				vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+					      GUEST_INTR_STATE_NMI);
+			break;
+		case INTR_TYPE_EXT_INTR:
+		case INTR_TYPE_SOFT_INTR:
+			kvm_clear_interrupt_queue(vcpu);
+			break;
+		case INTR_TYPE_HARD_EXCEPTION:
+		case INTR_TYPE_SOFT_EXCEPTION:
+			kvm_clear_exception_queue(vcpu);
+			break;
+		default:
+			break;
+		}
 	}
 	tss_selector = exit_qualification;
 
+	if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION &&
+		       type != INTR_TYPE_EXT_INTR &&
+		       type != INTR_TYPE_NMI_INTR))
+		skip_emulated_instruction(vcpu);
+
 	if (!kvm_task_switch(vcpu, tss_selector, reason))
 		return 0;
 
@@ -3051,11 +3104,11 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
-	u64 exit_qualification;
+	unsigned long exit_qualification;
 	gpa_t gpa;
 	int gla_validity;
 
-	exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 
 	if (exit_qualification & (1 << 6)) {
 		printk(KERN_ERR "EPT: GPA exceeds GAW!\n");
@@ -3067,7 +3120,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		printk(KERN_ERR "EPT: Handling EPT violation failed!\n");
 		printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n",
 			(long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS),
-			(long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS));
+			vmcs_readl(GUEST_LINEAR_ADDRESS));
 		printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n",
 			(long unsigned int)exit_qualification);
 		kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
@@ -3150,6 +3203,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
 	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
 	[EXIT_REASON_TASK_SWITCH]             = handle_task_switch,
 	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
+	[EXIT_REASON_MCE_DURING_VMENTRY]      = handle_machine_check,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -3159,10 +3213,10 @@ static const int kvm_vmx_max_exit_handlers =
  * The guest has exited.  See if we can fix it or if we need userspace
  * assistance.
  */
-static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
-	u32 exit_reason = vmcs_read32(VM_EXIT_REASON);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 exit_reason = vmx->exit_reason;
 	u32 vectoring_info = vmx->idt_vectoring_info;
 
 	KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)kvm_rip_read(vcpu),
@@ -3178,7 +3232,7 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	/* Access CR3 don't cause VMExit in paging mode, so we need
 	 * to sync with guest real CR3. */
-	if (vm_need_ept() && is_paging(vcpu)) {
+	if (enable_ept && is_paging(vcpu)) {
 		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
 		ept_load_pdptrs(vcpu);
 	}
@@ -3199,9 +3253,8 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		       __func__, vectoring_info, exit_reason);
 
 	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) {
-		if (vcpu->arch.interrupt_window_open) {
+		if (vmx_interrupt_allowed(vcpu)) {
 			vmx->soft_vnmi_blocked = 0;
-			vcpu->arch.nmi_window_open = 1;
 		} else if (vmx->vnmi_blocked_time > 1000000000LL &&
 			   vcpu->arch.nmi_pending) {
 			/*
@@ -3214,7 +3267,6 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			       "state on VCPU %d after 1 s timeout\n",
 			       __func__, vcpu->vcpu_id);
 			vmx->soft_vnmi_blocked = 0;
-			vmx->vcpu.arch.nmi_window_open = 1;
 		}
 	}
 
@@ -3228,122 +3280,107 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static void update_tpr_threshold(struct kvm_vcpu *vcpu)
+static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
-	int max_irr, tpr;
-
-	if (!vm_need_tpr_shadow(vcpu->kvm))
-		return;
-
-	if (!kvm_lapic_enabled(vcpu) ||
-	    ((max_irr = kvm_lapic_find_highest_irr(vcpu)) == -1)) {
+	if (irr == -1 || tpr < irr) {
 		vmcs_write32(TPR_THRESHOLD, 0);
 		return;
 	}
 
-	tpr = (kvm_lapic_get_cr8(vcpu) & 0x0f) << 4;
-	vmcs_write32(TPR_THRESHOLD, (max_irr > tpr) ? tpr >> 4 : max_irr >> 4);
+	vmcs_write32(TPR_THRESHOLD, irr);
 }
 
 static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
-	u32 idt_vectoring_info;
+	u32 idt_vectoring_info = vmx->idt_vectoring_info;
 	bool unblock_nmi;
 	u8 vector;
 	int type;
 	bool idtv_info_valid;
-	u32 error;
 
 	exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+	vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
+
+	/* Handle machine checks before interrupts are enabled */
+	if ((vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY)
+	    || (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI
+		&& is_machine_check(exit_intr_info)))
+		kvm_machine_check();
+
+	/* We need to handle NMIs before interrupts are enabled */
+	if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
+	    (exit_intr_info & INTR_INFO_VALID_MASK)) {
+		KVMTRACE_0D(NMI, &vmx->vcpu, handler);
+		asm("int $2");
+	}
+
+	idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
+
 	if (cpu_has_virtual_nmis()) {
 		unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
 		vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
 		/*
-		 * SDM 3: 25.7.1.2
+		 * SDM 3: 27.7.1.2 (September 2008)
 		 * Re-set bit "block by NMI" before VM entry if vmexit caused by
 		 * a guest IRET fault.
+		 * SDM 3: 23.2.2 (September 2008)
+		 * Bit 12 is undefined in any of the following cases:
+		 *  If the VM exit sets the valid bit in the IDT-vectoring
+		 *   information field.
+		 *  If the VM exit is due to a double fault.
 		 */
-		if (unblock_nmi && vector != DF_VECTOR)
+		if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi &&
+		    vector != DF_VECTOR && !idtv_info_valid)
 			vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
 				      GUEST_INTR_STATE_NMI);
 	} else if (unlikely(vmx->soft_vnmi_blocked))
 		vmx->vnmi_blocked_time +=
 			ktime_to_ns(ktime_sub(ktime_get(), vmx->entry_time));
 
-	idt_vectoring_info = vmx->idt_vectoring_info;
-	idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
+	vmx->vcpu.arch.nmi_injected = false;
+	kvm_clear_exception_queue(&vmx->vcpu);
+	kvm_clear_interrupt_queue(&vmx->vcpu);
+
+	if (!idtv_info_valid)
+		return;
+
 	vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK;
 	type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK;
-	if (vmx->vcpu.arch.nmi_injected) {
+
+	switch (type) {
+	case INTR_TYPE_NMI_INTR:
+		vmx->vcpu.arch.nmi_injected = true;
 		/*
-		 * SDM 3: 25.7.1.2
-		 * Clear bit "block by NMI" before VM entry if a NMI delivery
-		 * faulted.
+		 * SDM 3: 27.7.1.2 (September 2008)
+		 * Clear bit "block by NMI" before VM entry if a NMI
+		 * delivery faulted.
 		 */
-		if (idtv_info_valid && type == INTR_TYPE_NMI_INTR)
-			vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
-					GUEST_INTR_STATE_NMI);
-		else
-			vmx->vcpu.arch.nmi_injected = false;
-	}
-	kvm_clear_exception_queue(&vmx->vcpu);
-	if (idtv_info_valid && (type == INTR_TYPE_HARD_EXCEPTION ||
-				type == INTR_TYPE_SOFT_EXCEPTION)) {
+		vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+				GUEST_INTR_STATE_NMI);
+		break;
+	case INTR_TYPE_SOFT_EXCEPTION:
+		vmx->vcpu.arch.event_exit_inst_len =
+			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		/* fall through */
+	case INTR_TYPE_HARD_EXCEPTION:
 		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
-			error = vmcs_read32(IDT_VECTORING_ERROR_CODE);
-			kvm_queue_exception_e(&vmx->vcpu, vector, error);
+			u32 err = vmcs_read32(IDT_VECTORING_ERROR_CODE);
+			kvm_queue_exception_e(&vmx->vcpu, vector, err);
 		} else
 			kvm_queue_exception(&vmx->vcpu, vector);
-		vmx->idt_vectoring_info = 0;
-	}
-	kvm_clear_interrupt_queue(&vmx->vcpu);
-	if (idtv_info_valid && type == INTR_TYPE_EXT_INTR) {
-		kvm_queue_interrupt(&vmx->vcpu, vector);
-		vmx->idt_vectoring_info = 0;
-	}
-}
-
-static void vmx_intr_assist(struct kvm_vcpu *vcpu)
-{
-	update_tpr_threshold(vcpu);
-
-	vmx_update_window_states(vcpu);
-
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
-				GUEST_INTR_STATE_STI |
-				GUEST_INTR_STATE_MOV_SS);
-
-	if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
-		if (vcpu->arch.interrupt.pending) {
-			enable_nmi_window(vcpu);
-		} else if (vcpu->arch.nmi_window_open) {
-			vcpu->arch.nmi_pending = false;
-			vcpu->arch.nmi_injected = true;
-		} else {
-			enable_nmi_window(vcpu);
-			return;
-		}
-	}
-	if (vcpu->arch.nmi_injected) {
-		vmx_inject_nmi(vcpu);
-		if (vcpu->arch.nmi_pending)
-			enable_nmi_window(vcpu);
-		else if (kvm_cpu_has_interrupt(vcpu))
-			enable_irq_window(vcpu);
-		return;
-	}
-	if (!vcpu->arch.interrupt.pending && kvm_cpu_has_interrupt(vcpu)) {
-		if (vcpu->arch.interrupt_window_open)
-			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu));
-		else
-			enable_irq_window(vcpu);
-	}
-	if (vcpu->arch.interrupt.pending) {
-		vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr);
-		if (kvm_cpu_has_interrupt(vcpu))
-			enable_irq_window(vcpu);
+		break;
+	case INTR_TYPE_SOFT_INTR:
+		vmx->vcpu.arch.event_exit_inst_len =
+			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		/* fall through */
+	case INTR_TYPE_EXT_INTR:
+		kvm_queue_interrupt(&vmx->vcpu, vector,
+			type == INTR_TYPE_SOFT_INTR);
+		break;
+	default:
+		break;
 	}
 }
 
@@ -3381,7 +3418,6 @@ static void fixup_rmode_irq(struct vcpu_vmx *vmx)
 static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 intr_info;
 
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
@@ -3505,20 +3541,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (vmx->rmode.irq.pending)
 		fixup_rmode_irq(vmx);
 
-	vmx_update_window_states(vcpu);
-
 	asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
 	vmx->launched = 1;
 
-	intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-
-	/* We need to handle NMIs before interrupts are enabled */
-	if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
-	    (intr_info & INTR_INFO_VALID_MASK)) {
-		KVMTRACE_0D(NMI, vcpu, handler);
-		asm("int $2");
-	}
-
 	vmx_complete_interrupts(vmx);
 }
 
@@ -3593,7 +3618,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 		if (alloc_apic_access_page(kvm) != 0)
 			goto free_vmcs;
 
-	if (vm_need_ept())
+	if (enable_ept)
 		if (alloc_identity_pagetable(kvm) != 0)
 			goto free_vmcs;
 
@@ -3631,9 +3656,32 @@ static int get_ept_level(void)
 	return VMX_EPT_DEFAULT_GAW + 1;
 }
 
-static int vmx_get_mt_mask_shift(void)
+static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 {
-	return VMX_EPT_MT_EPTE_SHIFT;
+	u64 ret;
+
+	/* For VT-d and EPT combination
+	 * 1. MMIO: always map as UC
+	 * 2. EPT with VT-d:
+	 *   a. VT-d without snooping control feature: can't guarantee the
+	 *	result, try to trust guest.
+	 *   b. VT-d with snooping control feature: snooping control feature of
+	 *	VT-d engine can guarantee the cache correctness. Just set it
+	 *	to WB to keep consistent with host. So the same as item 3.
+	 * 3. EPT without VT-d: always map as WB and set IGMT=1 to keep
+	 *    consistent with host MTRR
+	 */
+	if (is_mmio)
+		ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
+	else if (vcpu->kvm->arch.iommu_domain &&
+		!(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY))
+		ret = kvm_get_guest_memory_type(vcpu, gfn) <<
+		      VMX_EPT_MT_EPTE_SHIFT;
+	else
+		ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT)
+			| VMX_EPT_IGMT_BIT;
+
+	return ret;
 }
 
 static struct kvm_x86_ops vmx_x86_ops = {
@@ -3644,7 +3692,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.check_processor_compatibility = vmx_check_processor_compat,
 	.hardware_enable = hardware_enable,
 	.hardware_disable = hardware_disable,
-	.cpu_has_accelerated_tpr = cpu_has_vmx_virtualize_apic_accesses,
+	.cpu_has_accelerated_tpr = report_flexpriority,
 
 	.vcpu_create = vmx_create_vcpu,
 	.vcpu_free = vmx_free_vcpu,
@@ -3678,78 +3726,82 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.tlb_flush = vmx_flush_tlb,
 
 	.run = vmx_vcpu_run,
-	.handle_exit = kvm_handle_exit,
+	.handle_exit = vmx_handle_exit,
 	.skip_emulated_instruction = skip_emulated_instruction,
+	.set_interrupt_shadow = vmx_set_interrupt_shadow,
+	.get_interrupt_shadow = vmx_get_interrupt_shadow,
 	.patch_hypercall = vmx_patch_hypercall,
-	.get_irq = vmx_get_irq,
 	.set_irq = vmx_inject_irq,
+	.set_nmi = vmx_inject_nmi,
 	.queue_exception = vmx_queue_exception,
-	.exception_injected = vmx_exception_injected,
-	.inject_pending_irq = vmx_intr_assist,
-	.inject_pending_vectors = do_interrupt_requests,
+	.interrupt_allowed = vmx_interrupt_allowed,
+	.nmi_allowed = vmx_nmi_allowed,
+	.enable_nmi_window = enable_nmi_window,
+	.enable_irq_window = enable_irq_window,
+	.update_cr8_intercept = update_cr8_intercept,
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.get_tdp_level = get_ept_level,
-	.get_mt_mask_shift = vmx_get_mt_mask_shift,
+	.get_mt_mask = vmx_get_mt_mask,
 };
 
 static int __init vmx_init(void)
 {
-	void *va;
 	int r;
 
-	vmx_io_bitmap_a = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
+	vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_io_bitmap_a)
 		return -ENOMEM;
 
-	vmx_io_bitmap_b = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
+	vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
 	if (!vmx_io_bitmap_b) {
 		r = -ENOMEM;
 		goto out;
 	}
 
-	vmx_msr_bitmap = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
-	if (!vmx_msr_bitmap) {
+	vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL);
+	if (!vmx_msr_bitmap_legacy) {
 		r = -ENOMEM;
 		goto out1;
 	}
 
+	vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
+	if (!vmx_msr_bitmap_longmode) {
+		r = -ENOMEM;
+		goto out2;
+	}
+
 	/*
 	 * Allow direct access to the PC debug port (it is often used for I/O
 	 * delays, but the vmexits simply slow things down).
 	 */
-	va = kmap(vmx_io_bitmap_a);
-	memset(va, 0xff, PAGE_SIZE);
-	clear_bit(0x80, va);
-	kunmap(vmx_io_bitmap_a);
+	memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
+	clear_bit(0x80, vmx_io_bitmap_a);
 
-	va = kmap(vmx_io_bitmap_b);
-	memset(va, 0xff, PAGE_SIZE);
-	kunmap(vmx_io_bitmap_b);
+	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
 
-	va = kmap(vmx_msr_bitmap);
-	memset(va, 0xff, PAGE_SIZE);
-	kunmap(vmx_msr_bitmap);
+	memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
+	memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
 
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
 	if (r)
-		goto out2;
+		goto out3;
 
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_FS_BASE);
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_GS_BASE);
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_CS);
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP);
-	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP);
+	vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
+	vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
+	vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
+	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
+	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
+	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
 
-	if (vm_need_ept()) {
+	if (enable_ept) {
 		bypass_guest_pf = 0;
 		kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
 			VMX_EPT_WRITABLE_MASK);
 		kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
-				VMX_EPT_EXECUTABLE_MASK,
-				VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
+				VMX_EPT_EXECUTABLE_MASK);
 		kvm_enable_tdp();
 	} else
 		kvm_disable_tdp();
@@ -3761,20 +3813,23 @@ static int __init vmx_init(void)
 
 	return 0;
 
+out3:
+	free_page((unsigned long)vmx_msr_bitmap_longmode);
 out2:
-	__free_page(vmx_msr_bitmap);
+	free_page((unsigned long)vmx_msr_bitmap_legacy);
 out1:
-	__free_page(vmx_io_bitmap_b);
+	free_page((unsigned long)vmx_io_bitmap_b);
 out:
-	__free_page(vmx_io_bitmap_a);
+	free_page((unsigned long)vmx_io_bitmap_a);
 	return r;
 }
 
 static void __exit vmx_exit(void)
 {
-	__free_page(vmx_msr_bitmap);
-	__free_page(vmx_io_bitmap_b);
-	__free_page(vmx_io_bitmap_a);
+	free_page((unsigned long)vmx_msr_bitmap_legacy);
+	free_page((unsigned long)vmx_msr_bitmap_longmode);
+	free_page((unsigned long)vmx_io_bitmap_b);
+	free_page((unsigned long)vmx_io_bitmap_a);
 
 	kvm_exit();
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3944e917e794..249540f98513 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -91,7 +91,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "hypercalls", VCPU_STAT(hypercalls) },
 	{ "request_irq", VCPU_STAT(request_irq_exits) },
-	{ "request_nmi", VCPU_STAT(request_nmi_exits) },
 	{ "irq_exits", VCPU_STAT(irq_exits) },
 	{ "host_state_reload", VCPU_STAT(host_state_reload) },
 	{ "efer_reload", VCPU_STAT(efer_reload) },
@@ -108,7 +107,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_recycled", VM_STAT(mmu_recycled) },
 	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
-	{ "mmu_unsync_global", VM_STAT(mmu_unsync_global) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
 	{ "largepages", VM_STAT(lpages) },
 	{ NULL }
@@ -234,7 +232,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
 		goto out;
 	}
 	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
-		if ((pdpte[i] & 1) && (pdpte[i] & 0xfffffff0000001e6ull)) {
+		if (is_present_pte(pdpte[i]) &&
+		    (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) {
 			ret = 0;
 			goto out;
 		}
@@ -321,7 +320,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	kvm_x86_ops->set_cr0(vcpu, cr0);
 	vcpu->arch.cr0 = cr0;
 
-	kvm_mmu_sync_global(vcpu);
 	kvm_mmu_reset_context(vcpu);
 	return;
 }
@@ -370,7 +368,6 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	kvm_x86_ops->set_cr4(vcpu, cr4);
 	vcpu->arch.cr4 = cr4;
 	vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled;
-	kvm_mmu_sync_global(vcpu);
 	kvm_mmu_reset_context(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_set_cr4);
@@ -523,6 +520,9 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	efer |= vcpu->arch.shadow_efer & EFER_LMA;
 
 	vcpu->arch.shadow_efer = efer;
+
+	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
+	kvm_mmu_reset_context(vcpu);
 }
 
 void kvm_enable_efer_bits(u64 mask)
@@ -630,14 +630,17 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	unsigned long flags;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	void *shared_kaddr;
+	unsigned long this_tsc_khz;
 
 	if ((!vcpu->time_page))
 		return;
 
-	if (unlikely(vcpu->hv_clock_tsc_khz != __get_cpu_var(cpu_tsc_khz))) {
-		kvm_set_time_scale(__get_cpu_var(cpu_tsc_khz), &vcpu->hv_clock);
-		vcpu->hv_clock_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+	this_tsc_khz = get_cpu_var(cpu_tsc_khz);
+	if (unlikely(vcpu->hv_clock_tsc_khz != this_tsc_khz)) {
+		kvm_set_time_scale(this_tsc_khz, &vcpu->hv_clock);
+		vcpu->hv_clock_tsc_khz = this_tsc_khz;
 	}
+	put_cpu_var(cpu_tsc_khz);
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
@@ -893,6 +896,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
 	case MSR_VM_HSAVE_PA:
+	case MSR_P6_EVNTSEL0:
+	case MSR_P6_EVNTSEL1:
 		data = 0;
 		break;
 	case MSR_MTRRcap:
@@ -1024,6 +1029,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
+	case KVM_CAP_ASSIGN_DEV_IRQ:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -1241,41 +1247,53 @@ static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	entry->flags = 0;
 }
 
+#define F(x) bit(X86_FEATURE_##x)
+
 static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			 u32 index, int *nent, int maxnent)
 {
-	const u32 kvm_supported_word0_x86_features = bit(X86_FEATURE_FPU) |
-		bit(X86_FEATURE_VME) | bit(X86_FEATURE_DE) |
-		bit(X86_FEATURE_PSE) | bit(X86_FEATURE_TSC) |
-		bit(X86_FEATURE_MSR) | bit(X86_FEATURE_PAE) |
-		bit(X86_FEATURE_CX8) | bit(X86_FEATURE_APIC) |
-		bit(X86_FEATURE_SEP) | bit(X86_FEATURE_PGE) |
-		bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) |
-		bit(X86_FEATURE_CLFLSH) | bit(X86_FEATURE_MMX) |
-		bit(X86_FEATURE_FXSR) | bit(X86_FEATURE_XMM) |
-		bit(X86_FEATURE_XMM2) | bit(X86_FEATURE_SELFSNOOP);
-	const u32 kvm_supported_word1_x86_features = bit(X86_FEATURE_FPU) |
-		bit(X86_FEATURE_VME) | bit(X86_FEATURE_DE) |
-		bit(X86_FEATURE_PSE) | bit(X86_FEATURE_TSC) |
-		bit(X86_FEATURE_MSR) | bit(X86_FEATURE_PAE) |
-		bit(X86_FEATURE_CX8) | bit(X86_FEATURE_APIC) |
-		bit(X86_FEATURE_PGE) |
-		bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) |
-		bit(X86_FEATURE_MMX) | bit(X86_FEATURE_FXSR) |
-		bit(X86_FEATURE_SYSCALL) |
-		(is_efer_nx() ? bit(X86_FEATURE_NX) : 0) |
+	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
 #ifdef CONFIG_X86_64
-		bit(X86_FEATURE_LM) |
+	unsigned f_lm = F(LM);
+#else
+	unsigned f_lm = 0;
 #endif
-		bit(X86_FEATURE_FXSR_OPT) |
-		bit(X86_FEATURE_MMXEXT) |
-		bit(X86_FEATURE_3DNOWEXT) |
-		bit(X86_FEATURE_3DNOW);
-	const u32 kvm_supported_word3_x86_features =
-		bit(X86_FEATURE_XMM3) | bit(X86_FEATURE_CX16);
+
+	/* cpuid 1.edx */
+	const u32 kvm_supported_word0_x86_features =
+		F(FPU) | F(VME) | F(DE) | F(PSE) |
+		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
+		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
+		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
+		F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) |
+		0 /* Reserved, DS, ACPI */ | F(MMX) |
+		F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
+		0 /* HTT, TM, Reserved, PBE */;
+	/* cpuid 0x80000001.edx */
+	const u32 kvm_supported_word1_x86_features =
+		F(FPU) | F(VME) | F(DE) | F(PSE) |
+		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
+		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) |
+		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
+		F(PAT) | F(PSE36) | 0 /* Reserved */ |
+		f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
+		F(FXSR) | F(FXSR_OPT) | 0 /* GBPAGES */ | 0 /* RDTSCP */ |
+		0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
+	/* cpuid 1.ecx */
+	const u32 kvm_supported_word4_x86_features =
+		F(XMM3) | 0 /* Reserved, DTES64, MONITOR */ |
+		0 /* DS-CPL, VMX, SMX, EST */ |
+		0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
+		0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ |
+		0 /* Reserved, DCA */ | F(XMM4_1) |
+		F(XMM4_2) | 0 /* x2APIC */ | F(MOVBE) | F(POPCNT) |
+		0 /* Reserved, XSAVE, OSXSAVE */;
+	/* cpuid 0x80000001.ecx */
 	const u32 kvm_supported_word6_x86_features =
-		bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY) |
-		bit(X86_FEATURE_SVM);
+		F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ |
+		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
+		F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(SSE5) |
+		0 /* SKINIT */ | 0 /* WDT */;
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
@@ -1288,7 +1306,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		break;
 	case 1:
 		entry->edx &= kvm_supported_word0_x86_features;
-		entry->ecx &= kvm_supported_word3_x86_features;
+		entry->ecx &= kvm_supported_word4_x86_features;
 		break;
 	/* function 2 entries are STATEFUL. That is, repeated cpuid commands
 	 * may return different values. This forces us to get_cpu() before
@@ -1350,6 +1368,8 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	put_cpu();
 }
 
+#undef F
+
 static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 				     struct kvm_cpuid_entry2 __user *entries)
 {
@@ -1421,8 +1441,7 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 		return -ENXIO;
 	vcpu_load(vcpu);
 
-	set_bit(irq->irq, vcpu->arch.irq_pending);
-	set_bit(irq->irq / BITS_PER_LONG, &vcpu->arch.irq_summary);
+	kvm_queue_interrupt(vcpu, irq->irq, false);
 
 	vcpu_put(vcpu);
 
@@ -1584,8 +1603,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EINVAL;
 	}
 out:
-	if (lapic)
-		kfree(lapic);
+	kfree(lapic);
 	return r;
 }
 
@@ -1606,10 +1624,12 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
 		return -EINVAL;
 
 	down_write(&kvm->slots_lock);
+	spin_lock(&kvm->mmu_lock);
 
 	kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
 	kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages;
 
+	spin_unlock(&kvm->mmu_lock);
 	up_write(&kvm->slots_lock);
 	return 0;
 }
@@ -1785,7 +1805,9 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
+		spin_lock(&kvm->mmu_lock);
 		kvm_mmu_slot_remove_write_access(kvm, log->slot);
+		spin_unlock(&kvm->mmu_lock);
 		kvm_flush_remote_tlbs(kvm);
 		memslot = &kvm->memslots[log->slot];
 		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
@@ -2360,7 +2382,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 			u16 error_code,
 			int emulation_type)
 {
-	int r;
+	int r, shadow_mask;
 	struct decode_cache *c;
 
 	kvm_clear_exception_queue(vcpu);
@@ -2408,7 +2430,16 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		}
 	}
 
+	if (emulation_type & EMULTYPE_SKIP) {
+		kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.decode.eip);
+		return EMULATE_DONE;
+	}
+
 	r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
+	shadow_mask = vcpu->arch.emulate_ctxt.interruptibility;
+
+	if (r == 0)
+		kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask);
 
 	if (vcpu->arch.pio.string)
 		return EMULATE_DO_MMIO;
@@ -2761,7 +2792,7 @@ int kvm_arch_init(void *opaque)
 	kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
 	kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
-			PT_DIRTY_MASK, PT64_NX_MASK, 0, 0);
+			PT_DIRTY_MASK, PT64_NX_MASK, 0);
 
 	for_each_possible_cpu(cpu)
 		per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
@@ -3012,6 +3043,16 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 	return best;
 }
 
+int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	if (best)
+		return best->eax & 0xff;
+	return 36;
+}
+
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 {
 	u32 function, index;
@@ -3048,10 +3089,9 @@ EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
 					  struct kvm_run *kvm_run)
 {
-	return (!vcpu->arch.irq_summary &&
+	return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) &&
 		kvm_run->request_interrupt_window &&
-		vcpu->arch.interrupt_window_open &&
-		(kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF));
+		kvm_arch_interrupt_allowed(vcpu));
 }
 
 static void post_kvm_run_save(struct kvm_vcpu *vcpu,
@@ -3064,8 +3104,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu,
 		kvm_run->ready_for_interrupt_injection = 1;
 	else
 		kvm_run->ready_for_interrupt_injection =
-					(vcpu->arch.interrupt_window_open &&
-					 vcpu->arch.irq_summary == 0);
+			kvm_arch_interrupt_allowed(vcpu) &&
+			!kvm_cpu_has_interrupt(vcpu) &&
+			!kvm_event_needs_reinjection(vcpu);
 }
 
 static void vapic_enter(struct kvm_vcpu *vcpu)
@@ -3094,9 +3135,63 @@ static void vapic_exit(struct kvm_vcpu *vcpu)
 	up_read(&vcpu->kvm->slots_lock);
 }
 
+static void update_cr8_intercept(struct kvm_vcpu *vcpu)
+{
+	int max_irr, tpr;
+
+	if (!kvm_x86_ops->update_cr8_intercept)
+		return;
+
+	if (!vcpu->arch.apic->vapic_addr)
+		max_irr = kvm_lapic_find_highest_irr(vcpu);
+	else
+		max_irr = -1;
+
+	if (max_irr != -1)
+		max_irr >>= 4;
+
+	tpr = kvm_lapic_get_cr8(vcpu);
+
+	kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
+}
+
+static void inject_pending_irq(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		kvm_x86_ops->set_interrupt_shadow(vcpu, 0);
+
+	/* try to reinject previous events if any */
+	if (vcpu->arch.nmi_injected) {
+		kvm_x86_ops->set_nmi(vcpu);
+		return;
+	}
+
+	if (vcpu->arch.interrupt.pending) {
+		kvm_x86_ops->set_irq(vcpu);
+		return;
+	}
+
+	/* try to inject new event if pending */
+	if (vcpu->arch.nmi_pending) {
+		if (kvm_x86_ops->nmi_allowed(vcpu)) {
+			vcpu->arch.nmi_pending = false;
+			vcpu->arch.nmi_injected = true;
+			kvm_x86_ops->set_nmi(vcpu);
+		}
+	} else if (kvm_cpu_has_interrupt(vcpu)) {
+		if (kvm_x86_ops->interrupt_allowed(vcpu)) {
+			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
+					    false);
+			kvm_x86_ops->set_irq(vcpu);
+		}
+	}
+}
+
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	int r;
+	bool req_int_win = !irqchip_in_kernel(vcpu->kvm) &&
+		kvm_run->request_interrupt_window;
 
 	if (vcpu->requests)
 		if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
@@ -3128,9 +3223,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		}
 	}
 
-	clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
-	kvm_inject_pending_timer_irqs(vcpu);
-
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
@@ -3138,6 +3230,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	local_irq_disable();
 
+	clear_bit(KVM_REQ_KICK, &vcpu->requests);
+	smp_mb__after_clear_bit();
+
 	if (vcpu->requests || need_resched() || signal_pending(current)) {
 		local_irq_enable();
 		preempt_enable();
@@ -3145,21 +3240,21 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		goto out;
 	}
 
-	vcpu->guest_mode = 1;
-	/*
-	 * Make sure that guest_mode assignment won't happen after
-	 * testing the pending IRQ vector bitmap.
-	 */
-	smp_wmb();
-
 	if (vcpu->arch.exception.pending)
 		__queue_exception(vcpu);
-	else if (irqchip_in_kernel(vcpu->kvm))
-		kvm_x86_ops->inject_pending_irq(vcpu);
 	else
-		kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run);
+		inject_pending_irq(vcpu, kvm_run);
 
-	kvm_lapic_sync_to_vapic(vcpu);
+	/* enable NMI/IRQ window open exits if needed */
+	if (vcpu->arch.nmi_pending)
+		kvm_x86_ops->enable_nmi_window(vcpu);
+	else if (kvm_cpu_has_interrupt(vcpu) || req_int_win)
+		kvm_x86_ops->enable_irq_window(vcpu);
+
+	if (kvm_lapic_enabled(vcpu)) {
+		update_cr8_intercept(vcpu);
+		kvm_lapic_sync_to_vapic(vcpu);
+	}
 
 	up_read(&vcpu->kvm->slots_lock);
 
@@ -3193,7 +3288,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	set_debugreg(vcpu->arch.host_dr6, 6);
 	set_debugreg(vcpu->arch.host_dr7, 7);
 
-	vcpu->guest_mode = 0;
+	set_bit(KVM_REQ_KICK, &vcpu->requests);
 	local_irq_enable();
 
 	++vcpu->stat.exits;
@@ -3220,8 +3315,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		profile_hit(KVM_PROFILING, (void *)rip);
 	}
 
-	if (vcpu->arch.exception.pending && kvm_x86_ops->exception_injected(vcpu))
-		vcpu->arch.exception.pending = false;
 
 	kvm_lapic_sync_from_vapic(vcpu);
 
@@ -3230,6 +3323,7 @@ out:
 	return r;
 }
 
+
 static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	int r;
@@ -3256,29 +3350,42 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			kvm_vcpu_block(vcpu);
 			down_read(&vcpu->kvm->slots_lock);
 			if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
-				if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
+			{
+				switch(vcpu->arch.mp_state) {
+				case KVM_MP_STATE_HALTED:
 					vcpu->arch.mp_state =
-							KVM_MP_STATE_RUNNABLE;
-			if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
-				r = -EINTR;
+						KVM_MP_STATE_RUNNABLE;
+				case KVM_MP_STATE_RUNNABLE:
+					break;
+				case KVM_MP_STATE_SIPI_RECEIVED:
+				default:
+					r = -EINTR;
+					break;
+				}
+			}
 		}
 
-		if (r > 0) {
-			if (dm_request_for_irq_injection(vcpu, kvm_run)) {
-				r = -EINTR;
-				kvm_run->exit_reason = KVM_EXIT_INTR;
-				++vcpu->stat.request_irq_exits;
-			}
-			if (signal_pending(current)) {
-				r = -EINTR;
-				kvm_run->exit_reason = KVM_EXIT_INTR;
-				++vcpu->stat.signal_exits;
-			}
-			if (need_resched()) {
-				up_read(&vcpu->kvm->slots_lock);
-				kvm_resched(vcpu);
-				down_read(&vcpu->kvm->slots_lock);
-			}
+		if (r <= 0)
+			break;
+
+		clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
+		if (kvm_cpu_has_pending_timer(vcpu))
+			kvm_inject_pending_timer_irqs(vcpu);
+
+		if (dm_request_for_irq_injection(vcpu, kvm_run)) {
+			r = -EINTR;
+			kvm_run->exit_reason = KVM_EXIT_INTR;
+			++vcpu->stat.request_irq_exits;
+		}
+		if (signal_pending(current)) {
+			r = -EINTR;
+			kvm_run->exit_reason = KVM_EXIT_INTR;
+			++vcpu->stat.signal_exits;
+		}
+		if (need_resched()) {
+			up_read(&vcpu->kvm->slots_lock);
+			kvm_resched(vcpu);
+			down_read(&vcpu->kvm->slots_lock);
 		}
 	}
 
@@ -3442,7 +3549,6 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
 	struct descriptor_table dt;
-	int pending_vec;
 
 	vcpu_load(vcpu);
 
@@ -3472,16 +3578,11 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	sregs->efer = vcpu->arch.shadow_efer;
 	sregs->apic_base = kvm_get_apic_base(vcpu);
 
-	if (irqchip_in_kernel(vcpu->kvm)) {
-		memset(sregs->interrupt_bitmap, 0,
-		       sizeof sregs->interrupt_bitmap);
-		pending_vec = kvm_x86_ops->get_irq(vcpu);
-		if (pending_vec >= 0)
-			set_bit(pending_vec,
-				(unsigned long *)sregs->interrupt_bitmap);
-	} else
-		memcpy(sregs->interrupt_bitmap, vcpu->arch.irq_pending,
-		       sizeof sregs->interrupt_bitmap);
+	memset(sregs->interrupt_bitmap, 0, sizeof sregs->interrupt_bitmap);
+
+	if (vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft)
+		set_bit(vcpu->arch.interrupt.nr,
+			(unsigned long *)sregs->interrupt_bitmap);
 
 	vcpu_put(vcpu);
 
@@ -3688,7 +3789,6 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu,
 	tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS);
 	tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS);
 	tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR);
-	tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR);
 }
 
 static int load_state_from_tss32(struct kvm_vcpu *vcpu,
@@ -3785,8 +3885,8 @@ static int load_state_from_tss16(struct kvm_vcpu *vcpu,
 }
 
 static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
-		       u32 old_tss_base,
-		       struct desc_struct *nseg_desc)
+			      u16 old_tss_sel, u32 old_tss_base,
+			      struct desc_struct *nseg_desc)
 {
 	struct tss_segment_16 tss_segment_16;
 	int ret = 0;
@@ -3805,6 +3905,16 @@ static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
 			   &tss_segment_16, sizeof tss_segment_16))
 		goto out;
 
+	if (old_tss_sel != 0xffff) {
+		tss_segment_16.prev_task_link = old_tss_sel;
+
+		if (kvm_write_guest(vcpu->kvm,
+				    get_tss_base_addr(vcpu, nseg_desc),
+				    &tss_segment_16.prev_task_link,
+				    sizeof tss_segment_16.prev_task_link))
+			goto out;
+	}
+
 	if (load_state_from_tss16(vcpu, &tss_segment_16))
 		goto out;
 
@@ -3814,7 +3924,7 @@ out:
 }
 
 static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
-		       u32 old_tss_base,
+		       u16 old_tss_sel, u32 old_tss_base,
 		       struct desc_struct *nseg_desc)
 {
 	struct tss_segment_32 tss_segment_32;
@@ -3834,6 +3944,16 @@ static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
 			   &tss_segment_32, sizeof tss_segment_32))
 		goto out;
 
+	if (old_tss_sel != 0xffff) {
+		tss_segment_32.prev_task_link = old_tss_sel;
+
+		if (kvm_write_guest(vcpu->kvm,
+				    get_tss_base_addr(vcpu, nseg_desc),
+				    &tss_segment_32.prev_task_link,
+				    sizeof tss_segment_32.prev_task_link))
+			goto out;
+	}
+
 	if (load_state_from_tss32(vcpu, &tss_segment_32))
 		goto out;
 
@@ -3887,14 +4007,22 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 		kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
 	}
 
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	/* set back link to prev task only if NT bit is set in eflags
+	   note that old_tss_sel is not used afetr this point */
+	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
+		old_tss_sel = 0xffff;
+
+	/* set back link to prev task only if NT bit is set in eflags
+	   note that old_tss_sel is not used afetr this point */
+	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
+		old_tss_sel = 0xffff;
 
 	if (nseg_desc.type & 8)
-		ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_base,
-					 &nseg_desc);
+		ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel,
+					 old_tss_base, &nseg_desc);
 	else
-		ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_base,
-					 &nseg_desc);
+		ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_sel,
+					 old_tss_base, &nseg_desc);
 
 	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
 		u32 eflags = kvm_x86_ops->get_rflags(vcpu);
@@ -3920,7 +4048,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
 	int mmu_reset_needed = 0;
-	int i, pending_vec, max_bits;
+	int pending_vec, max_bits;
 	struct descriptor_table dt;
 
 	vcpu_load(vcpu);
@@ -3934,7 +4062,13 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	vcpu->arch.cr2 = sregs->cr2;
 	mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3;
-	vcpu->arch.cr3 = sregs->cr3;
+
+	down_read(&vcpu->kvm->slots_lock);
+	if (gfn_to_memslot(vcpu->kvm, sregs->cr3 >> PAGE_SHIFT))
+		vcpu->arch.cr3 = sregs->cr3;
+	else
+		set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+	up_read(&vcpu->kvm->slots_lock);
 
 	kvm_set_cr8(vcpu, sregs->cr8);
 
@@ -3956,25 +4090,14 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	if (mmu_reset_needed)
 		kvm_mmu_reset_context(vcpu);
 
-	if (!irqchip_in_kernel(vcpu->kvm)) {
-		memcpy(vcpu->arch.irq_pending, sregs->interrupt_bitmap,
-		       sizeof vcpu->arch.irq_pending);
-		vcpu->arch.irq_summary = 0;
-		for (i = 0; i < ARRAY_SIZE(vcpu->arch.irq_pending); ++i)
-			if (vcpu->arch.irq_pending[i])
-				__set_bit(i, &vcpu->arch.irq_summary);
-	} else {
-		max_bits = (sizeof sregs->interrupt_bitmap) << 3;
-		pending_vec = find_first_bit(
-			(const unsigned long *)sregs->interrupt_bitmap,
-			max_bits);
-		/* Only pending external irq is handled here */
-		if (pending_vec < max_bits) {
-			kvm_x86_ops->set_irq(vcpu, pending_vec);
-			pr_debug("Set back pending irq %d\n",
-				 pending_vec);
-		}
-		kvm_pic_clear_isr_ack(vcpu->kvm);
+	max_bits = (sizeof sregs->interrupt_bitmap) << 3;
+	pending_vec = find_first_bit(
+		(const unsigned long *)sregs->interrupt_bitmap, max_bits);
+	if (pending_vec < max_bits) {
+		kvm_queue_interrupt(vcpu, pending_vec, false);
+		pr_debug("Set back pending irq %d\n", pending_vec);
+		if (irqchip_in_kernel(vcpu->kvm))
+			kvm_pic_clear_isr_ack(vcpu->kvm);
 	}
 
 	kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
@@ -4308,7 +4431,6 @@ struct  kvm *kvm_arch_create_vm(void)
 		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
-	INIT_LIST_HEAD(&kvm->arch.oos_global_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
@@ -4411,12 +4533,14 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 		}
 	}
 
+	spin_lock(&kvm->mmu_lock);
 	if (!kvm->arch.n_requested_mmu_pages) {
 		unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
 		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
 	}
 
 	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
+	spin_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs(kvm);
 
 	return 0;
@@ -4425,6 +4549,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 void kvm_arch_flush_shadow(struct kvm *kvm)
 {
 	kvm_mmu_zap_all(kvm);
+	kvm_reload_remote_mmus(kvm);
 }
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
@@ -4434,28 +4559,24 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	       || vcpu->arch.nmi_pending;
 }
 
-static void vcpu_kick_intr(void *info)
-{
-#ifdef DEBUG
-	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info;
-	printk(KERN_DEBUG "vcpu_kick_intr %p \n", vcpu);
-#endif
-}
-
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 {
-	int ipi_pcpu = vcpu->cpu;
-	int cpu = get_cpu();
+	int me;
+	int cpu = vcpu->cpu;
 
 	if (waitqueue_active(&vcpu->wq)) {
 		wake_up_interruptible(&vcpu->wq);
 		++vcpu->stat.halt_wakeup;
 	}
-	/*
-	 * We may be called synchronously with irqs disabled in guest mode,
-	 * So need not to call smp_call_function_single() in that case.
-	 */
-	if (vcpu->guest_mode && vcpu->cpu != cpu)
-		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0);
+
+	me = get_cpu();
+	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
+		if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests))
+			smp_send_reschedule(cpu);
 	put_cpu();
 }
+
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
+{
+	return kvm_x86_ops->interrupt_allowed(vcpu);
+}
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 6a4be78a7384..4c8e10af78e8 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -8,9 +8,11 @@ static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
 	vcpu->arch.exception.pending = false;
 }
 
-static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector)
+static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector,
+	bool soft)
 {
 	vcpu->arch.interrupt.pending = true;
+	vcpu->arch.interrupt.soft = soft;
 	vcpu->arch.interrupt.nr = vector;
 }
 
@@ -19,4 +21,14 @@ static inline void kvm_clear_interrupt_queue(struct kvm_vcpu *vcpu)
 	vcpu->arch.interrupt.pending = false;
 }
 
+static inline bool kvm_event_needs_reinjection(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.exception.pending || vcpu->arch.interrupt.pending ||
+		vcpu->arch.nmi_injected;
+}
+
+static inline bool kvm_exception_is_soft(unsigned int nr)
+{
+	return (nr == BP_VECTOR) || (nr == OF_VECTOR);
+}
 #endif
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index ca91749d2083..c1b6c232e02b 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -59,13 +59,14 @@
 #define SrcImm      (5<<4)	/* Immediate operand. */
 #define SrcImmByte  (6<<4)	/* 8-bit sign-extended immediate operand. */
 #define SrcOne      (7<<4)	/* Implied '1' */
-#define SrcMask     (7<<4)
+#define SrcImmUByte (8<<4)      /* 8-bit unsigned immediate operand. */
+#define SrcMask     (0xf<<4)
 /* Generic ModRM decode. */
-#define ModRM       (1<<7)
+#define ModRM       (1<<8)
 /* Destination is only written; never read. */
-#define Mov         (1<<8)
-#define BitOp       (1<<9)
-#define MemAbs      (1<<10)      /* Memory operand is absolute displacement */
+#define Mov         (1<<9)
+#define BitOp       (1<<10)
+#define MemAbs      (1<<11)      /* Memory operand is absolute displacement */
 #define String      (1<<12)     /* String instruction (rep capable) */
 #define Stack       (1<<13)     /* Stack instruction (push/pop) */
 #define Group       (1<<14)     /* Bits 3:5 of modrm byte extend opcode */
@@ -76,6 +77,7 @@
 #define Src2CL      (1<<29)
 #define Src2ImmByte (2<<29)
 #define Src2One     (3<<29)
+#define Src2Imm16   (4<<29)
 #define Src2Mask    (7<<29)
 
 enum {
@@ -135,11 +137,11 @@ static u32 opcode_table[256] = {
 	SrcNone  | ByteOp  | ImplicitOps, SrcNone  | ImplicitOps, /* insb, insw/insd */
 	SrcNone  | ByteOp  | ImplicitOps, SrcNone  | ImplicitOps, /* outsb, outsw/outsd */
 	/* 0x70 - 0x77 */
-	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
-	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
+	SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte,
+	SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte,
 	/* 0x78 - 0x7F */
-	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
-	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
+	SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte,
+	SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte,
 	/* 0x80 - 0x87 */
 	Group | Group1_80, Group | Group1_81,
 	Group | Group1_82, Group | Group1_83,
@@ -153,7 +155,8 @@ static u32 opcode_table[256] = {
 	/* 0x90 - 0x97 */
 	DstReg, DstReg, DstReg, DstReg,	DstReg, DstReg, DstReg, DstReg,
 	/* 0x98 - 0x9F */
-	0, 0, 0, 0, ImplicitOps | Stack, ImplicitOps | Stack, 0, 0,
+	0, 0, SrcImm | Src2Imm16, 0,
+	ImplicitOps | Stack, ImplicitOps | Stack, 0, 0,
 	/* 0xA0 - 0xA7 */
 	ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs,
 	ByteOp | DstMem | SrcReg | Mov | MemAbs, DstMem | SrcReg | Mov | MemAbs,
@@ -178,7 +181,8 @@ static u32 opcode_table[256] = {
 	0, ImplicitOps | Stack, 0, 0,
 	ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov,
 	/* 0xC8 - 0xCF */
-	0, 0, 0, ImplicitOps | Stack, 0, 0, 0, 0,
+	0, 0, 0, ImplicitOps | Stack,
+	ImplicitOps, SrcImmByte, ImplicitOps, ImplicitOps,
 	/* 0xD0 - 0xD7 */
 	ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM,
 	ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM,
@@ -187,11 +191,11 @@ static u32 opcode_table[256] = {
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xE0 - 0xE7 */
 	0, 0, 0, 0,
-	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
-	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
+	ByteOp | SrcImmUByte, SrcImmUByte,
+	ByteOp | SrcImmUByte, SrcImmUByte,
 	/* 0xE8 - 0xEF */
-	ImplicitOps | Stack, SrcImm | ImplicitOps,
-	ImplicitOps, SrcImmByte | ImplicitOps,
+	SrcImm | Stack, SrcImm | ImplicitOps,
+	SrcImm | Src2Imm16, SrcImmByte | ImplicitOps,
 	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
 	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
 	/* 0xF0 - 0xF7 */
@@ -230,10 +234,8 @@ static u32 twobyte_table[256] = {
 	/* 0x70 - 0x7F */
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0x80 - 0x8F */
-	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
-	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
-	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
-	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
+	SrcImm, SrcImm, SrcImm, SrcImm, SrcImm, SrcImm, SrcImm, SrcImm,
+	SrcImm, SrcImm, SrcImm, SrcImm, SrcImm, SrcImm, SrcImm, SrcImm,
 	/* 0x90 - 0x9F */
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xA0 - 0xA7 */
@@ -1044,10 +1046,14 @@ done_prefixes:
 		}
 		break;
 	case SrcImmByte:
+	case SrcImmUByte:
 		c->src.type = OP_IMM;
 		c->src.ptr = (unsigned long *)c->eip;
 		c->src.bytes = 1;
-		c->src.val = insn_fetch(s8, 1, c->eip);
+		if ((c->d & SrcMask) == SrcImmByte)
+			c->src.val = insn_fetch(s8, 1, c->eip);
+		else
+			c->src.val = insn_fetch(u8, 1, c->eip);
 		break;
 	case SrcOne:
 		c->src.bytes = 1;
@@ -1072,6 +1078,12 @@ done_prefixes:
 		c->src2.bytes = 1;
 		c->src2.val = insn_fetch(u8, 1, c->eip);
 		break;
+	case Src2Imm16:
+		c->src2.type = OP_IMM;
+		c->src2.ptr = (unsigned long *)c->eip;
+		c->src2.bytes = 2;
+		c->src2.val = insn_fetch(u16, 2, c->eip);
+		break;
 	case Src2One:
 		c->src2.bytes = 1;
 		c->src2.val = 1;
@@ -1349,6 +1361,20 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt,
 	return 0;
 }
 
+void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask)
+{
+	u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(ctxt->vcpu, mask);
+	/*
+	 * an sti; sti; sequence only disable interrupts for the first
+	 * instruction. So, if the last instruction, be it emulated or
+	 * not, left the system with the INT_STI flag enabled, it
+	 * means that the last instruction is an sti. We should not
+	 * leave the flag on in this case. The same goes for mov ss
+	 */
+	if (!(int_shadow & mask))
+		ctxt->interruptibility = mask;
+}
+
 int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
@@ -1360,6 +1386,8 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	int io_dir_in;
 	int rc = 0;
 
+	ctxt->interruptibility = 0;
+
 	/* Shadow copy of register state. Committed on successful emulation.
 	 * NOTE: we can copy them from vcpu as x86_decode_insn() doesn't
 	 * modify them.
@@ -1531,13 +1559,10 @@ special_insn:
 			return -1;
 		}
 		return 0;
-	case 0x70 ... 0x7f: /* jcc (short) */ {
-		int rel = insn_fetch(s8, 1, c->eip);
-
+	case 0x70 ... 0x7f: /* jcc (short) */
 		if (test_cc(c->b, ctxt->eflags))
-			jmp_rel(c, rel);
+			jmp_rel(c, c->src.val);
 		break;
-	}
 	case 0x80 ... 0x83:	/* Grp1 */
 		switch (c->modrm_reg) {
 		case 0:
@@ -1609,6 +1634,9 @@ special_insn:
 		int err;
 
 		sel = c->src.val;
+		if (c->modrm_reg == VCPU_SREG_SS)
+			toggle_interruptibility(ctxt, X86_SHADOW_INT_MOV_SS);
+
 		if (c->modrm_reg <= 5) {
 			type_bits = (c->modrm_reg == 1) ? 9 : 1;
 			err = kvm_load_segment_descriptor(ctxt->vcpu, sel,
@@ -1769,59 +1797,32 @@ special_insn:
 		break;
 	case 0xe4: 	/* inb */
 	case 0xe5: 	/* in */
-		port = insn_fetch(u8, 1, c->eip);
+		port = c->src.val;
 		io_dir_in = 1;
 		goto do_io;
 	case 0xe6: /* outb */
 	case 0xe7: /* out */
-		port = insn_fetch(u8, 1, c->eip);
+		port = c->src.val;
 		io_dir_in = 0;
 		goto do_io;
 	case 0xe8: /* call (near) */ {
-		long int rel;
-		switch (c->op_bytes) {
-		case 2:
-			rel = insn_fetch(s16, 2, c->eip);
-			break;
-		case 4:
-			rel = insn_fetch(s32, 4, c->eip);
-			break;
-		default:
-			DPRINTF("Call: Invalid op_bytes\n");
-			goto cannot_emulate;
-		}
+		long int rel = c->src.val;
 		c->src.val = (unsigned long) c->eip;
 		jmp_rel(c, rel);
-		c->op_bytes = c->ad_bytes;
 		emulate_push(ctxt);
 		break;
 	}
 	case 0xe9: /* jmp rel */
 		goto jmp;
-	case 0xea: /* jmp far */ {
-		uint32_t eip;
-		uint16_t sel;
-
-		switch (c->op_bytes) {
-		case 2:
-			eip = insn_fetch(u16, 2, c->eip);
-			break;
-		case 4:
-			eip = insn_fetch(u32, 4, c->eip);
-			break;
-		default:
-			DPRINTF("jmp far: Invalid op_bytes\n");
-			goto cannot_emulate;
-		}
-		sel = insn_fetch(u16, 2, c->eip);
-		if (kvm_load_segment_descriptor(ctxt->vcpu, sel, 9, VCPU_SREG_CS) < 0) {
+	case 0xea: /* jmp far */
+		if (kvm_load_segment_descriptor(ctxt->vcpu, c->src2.val, 9,
+					VCPU_SREG_CS) < 0) {
 			DPRINTF("jmp far: Failed to load CS descriptor\n");
 			goto cannot_emulate;
 		}
 
-		c->eip = eip;
+		c->eip = c->src.val;
 		break;
-	}
 	case 0xeb:
 	      jmp:		/* jmp rel short */
 		jmp_rel(c, c->src.val);
@@ -1865,6 +1866,7 @@ special_insn:
 		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
 	case 0xfb: /* sti */
+		toggle_interruptibility(ctxt, X86_SHADOW_INT_STI);
 		ctxt->eflags |= X86_EFLAGS_IF;
 		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
@@ -2039,28 +2041,11 @@ twobyte_insn:
 		if (!test_cc(c->b, ctxt->eflags))
 			c->dst.type = OP_NONE; /* no writeback */
 		break;
-	case 0x80 ... 0x8f: /* jnz rel, etc*/ {
-		long int rel;
-
-		switch (c->op_bytes) {
-		case 2:
-			rel = insn_fetch(s16, 2, c->eip);
-			break;
-		case 4:
-			rel = insn_fetch(s32, 4, c->eip);
-			break;
-		case 8:
-			rel = insn_fetch(s64, 8, c->eip);
-			break;
-		default:
-			DPRINTF("jnz: Invalid op_bytes\n");
-			goto cannot_emulate;
-		}
+	case 0x80 ... 0x8f: /* jnz rel, etc*/
 		if (test_cc(c->b, ctxt->eflags))
-			jmp_rel(c, rel);
+			jmp_rel(c, c->src.val);
 		c->dst.type = OP_NONE;
 		break;
-	}
 	case 0xa3:
 	      bt:		/* bt */
 		c->dst.type = OP_NONE;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 33a93b417396..4e0c26559395 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -167,10 +167,16 @@ static void lazy_hcall3(unsigned long call,
 
 /* When lazy mode is turned off reset the per-cpu lazy mode variable and then
  * issue the do-nothing hypercall to flush any stored calls. */
-static void lguest_leave_lazy_mode(void)
+static void lguest_leave_lazy_mmu_mode(void)
 {
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
 	kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+	paravirt_leave_lazy_mmu();
+}
+
+static void lguest_end_context_switch(struct task_struct *next)
+{
+	kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+	paravirt_end_context_switch(next);
 }
 
 /*G:033
@@ -637,7 +643,7 @@ static void __init lguest_init_IRQ(void)
 
 void lguest_setup_irq(unsigned int irq)
 {
-	irq_to_desc_alloc_cpu(irq, 0);
+	irq_to_desc_alloc_node(irq, 0);
 	set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
 				      handle_level_irq, "level");
 }
@@ -1054,8 +1060,8 @@ __init void lguest_init(void)
 	pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
 	pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
 	pv_cpu_ops.wbinvd = lguest_wbinvd;
-	pv_cpu_ops.lazy_mode.enter = paravirt_enter_lazy_cpu;
-	pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+	pv_cpu_ops.start_context_switch = paravirt_start_context_switch;
+	pv_cpu_ops.end_context_switch = lguest_end_context_switch;
 
 	/* pagetable management */
 	pv_mmu_ops.write_cr3 = lguest_write_cr3;
@@ -1068,7 +1074,7 @@ __init void lguest_init(void)
 	pv_mmu_ops.read_cr2 = lguest_read_cr2;
 	pv_mmu_ops.read_cr3 = lguest_read_cr3;
 	pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
-	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
 	pv_mmu_ops.pte_update = lguest_pte_update;
 	pv_mmu_ops.pte_update_defer = lguest_pte_update;
 
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 55e11aa6d66c..f9d35632666b 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -2,7 +2,7 @@
 # Makefile for x86 specific library files.
 #
 
-obj-$(CONFIG_SMP) := msr-on-cpu.o
+obj-$(CONFIG_SMP) := msr.o
 
 lib-y := delay.o
 lib-y += thunk_$(BITS).o
diff --git a/arch/x86/lib/msr-on-cpu.c b/arch/x86/lib/msr-on-cpu.c
deleted file mode 100644
index 321cf720dbb6..000000000000
--- a/arch/x86/lib/msr-on-cpu.c
+++ /dev/null
@@ -1,97 +0,0 @@
-#include <linux/module.h>
-#include <linux/preempt.h>
-#include <linux/smp.h>
-#include <asm/msr.h>
-
-struct msr_info {
-	u32 msr_no;
-	u32 l, h;
-	int err;
-};
-
-static void __rdmsr_on_cpu(void *info)
-{
-	struct msr_info *rv = info;
-
-	rdmsr(rv->msr_no, rv->l, rv->h);
-}
-
-static void __wrmsr_on_cpu(void *info)
-{
-	struct msr_info *rv = info;
-
-	wrmsr(rv->msr_no, rv->l, rv->h);
-}
-
-int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
-	int err;
-	struct msr_info rv;
-
-	rv.msr_no = msr_no;
-	err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
-	*l = rv.l;
-	*h = rv.h;
-
-	return err;
-}
-
-int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
-	int err;
-	struct msr_info rv;
-
-	rv.msr_no = msr_no;
-	rv.l = l;
-	rv.h = h;
-	err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
-
-	return err;
-}
-
-/* These "safe" variants are slower and should be used when the target MSR
-   may not actually exist. */
-static void __rdmsr_safe_on_cpu(void *info)
-{
-	struct msr_info *rv = info;
-
-	rv->err = rdmsr_safe(rv->msr_no, &rv->l, &rv->h);
-}
-
-static void __wrmsr_safe_on_cpu(void *info)
-{
-	struct msr_info *rv = info;
-
-	rv->err = wrmsr_safe(rv->msr_no, rv->l, rv->h);
-}
-
-int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
-	int err;
-	struct msr_info rv;
-
-	rv.msr_no = msr_no;
-	err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
-	*l = rv.l;
-	*h = rv.h;
-
-	return err ? err : rv.err;
-}
-
-int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
-	int err;
-	struct msr_info rv;
-
-	rv.msr_no = msr_no;
-	rv.l = l;
-	rv.h = h;
-	err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
-
-	return err ? err : rv.err;
-}
-
-EXPORT_SYMBOL(rdmsr_on_cpu);
-EXPORT_SYMBOL(wrmsr_on_cpu);
-EXPORT_SYMBOL(rdmsr_safe_on_cpu);
-EXPORT_SYMBOL(wrmsr_safe_on_cpu);
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
new file mode 100644
index 000000000000..1440b9c0547e
--- /dev/null
+++ b/arch/x86/lib/msr.c
@@ -0,0 +1,183 @@
+#include <linux/module.h>
+#include <linux/preempt.h>
+#include <linux/smp.h>
+#include <asm/msr.h>
+
+struct msr_info {
+	u32 msr_no;
+	struct msr reg;
+	struct msr *msrs;
+	int off;
+	int err;
+};
+
+static void __rdmsr_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+	struct msr *reg;
+	int this_cpu = raw_smp_processor_id();
+
+	if (rv->msrs)
+		reg = &rv->msrs[this_cpu - rv->off];
+	else
+		reg = &rv->reg;
+
+	rdmsr(rv->msr_no, reg->l, reg->h);
+}
+
+static void __wrmsr_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+	struct msr *reg;
+	int this_cpu = raw_smp_processor_id();
+
+	if (rv->msrs)
+		reg = &rv->msrs[this_cpu - rv->off];
+	else
+		reg = &rv->reg;
+
+	wrmsr(rv->msr_no, reg->l, reg->h);
+}
+
+int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+	int err;
+	struct msr_info rv;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.msr_no = msr_no;
+	err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
+	*l = rv.reg.l;
+	*h = rv.reg.h;
+
+	return err;
+}
+EXPORT_SYMBOL(rdmsr_on_cpu);
+
+int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	int err;
+	struct msr_info rv;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.msr_no = msr_no;
+	rv.reg.l = l;
+	rv.reg.h = h;
+	err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
+
+	return err;
+}
+EXPORT_SYMBOL(wrmsr_on_cpu);
+
+/* rdmsr on a bunch of CPUs
+ *
+ * @mask:       which CPUs
+ * @msr_no:     which MSR
+ * @msrs:       array of MSR values
+ *
+ */
+void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs)
+{
+	struct msr_info rv;
+	int this_cpu;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.off    = cpumask_first(mask);
+	rv.msrs	  = msrs;
+	rv.msr_no = msr_no;
+
+	preempt_disable();
+	/*
+	 * FIXME: handle the CPU we're executing on separately for now until
+	 * smp_call_function_many has been fixed to not skip it.
+	 */
+	this_cpu = raw_smp_processor_id();
+	smp_call_function_single(this_cpu, __rdmsr_on_cpu, &rv, 1);
+
+	smp_call_function_many(mask, __rdmsr_on_cpu, &rv, 1);
+	preempt_enable();
+}
+EXPORT_SYMBOL(rdmsr_on_cpus);
+
+/*
+ * wrmsr on a bunch of CPUs
+ *
+ * @mask:       which CPUs
+ * @msr_no:     which MSR
+ * @msrs:       array of MSR values
+ *
+ */
+void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs)
+{
+	struct msr_info rv;
+	int this_cpu;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.off    = cpumask_first(mask);
+	rv.msrs   = msrs;
+	rv.msr_no = msr_no;
+
+	preempt_disable();
+	/*
+	 * FIXME: handle the CPU we're executing on separately for now until
+	 * smp_call_function_many has been fixed to not skip it.
+	 */
+	this_cpu = raw_smp_processor_id();
+	smp_call_function_single(this_cpu, __wrmsr_on_cpu, &rv, 1);
+
+	smp_call_function_many(mask, __wrmsr_on_cpu, &rv, 1);
+	preempt_enable();
+}
+EXPORT_SYMBOL(wrmsr_on_cpus);
+
+/* These "safe" variants are slower and should be used when the target MSR
+   may not actually exist. */
+static void __rdmsr_safe_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+
+	rv->err = rdmsr_safe(rv->msr_no, &rv->reg.l, &rv->reg.h);
+}
+
+static void __wrmsr_safe_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+
+	rv->err = wrmsr_safe(rv->msr_no, rv->reg.l, rv->reg.h);
+}
+
+int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+	int err;
+	struct msr_info rv;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.msr_no = msr_no;
+	err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
+	*l = rv.reg.l;
+	*h = rv.reg.h;
+
+	return err ? err : rv.err;
+}
+EXPORT_SYMBOL(rdmsr_safe_on_cpu);
+
+int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	int err;
+	struct msr_info rv;
+
+	memset(&rv, 0, sizeof(rv));
+
+	rv.msr_no = msr_no;
+	rv.reg.l = l;
+	rv.reg.h = h;
+	err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
+
+	return err ? err : rv.err;
+}
+EXPORT_SYMBOL(wrmsr_safe_on_cpu);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index e7277cbcfb40..a725b7f760ae 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -161,13 +161,14 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		   st->current_address >= st->marker[1].start_address) {
 		const char *unit = units;
 		unsigned long delta;
+		int width = sizeof(unsigned long) * 2;
 
 		/*
 		 * Now print the actual finished series
 		 */
-		seq_printf(m, "0x%p-0x%p   ",
-			   (void *)st->start_address,
-			   (void *)st->current_address);
+		seq_printf(m, "0x%0*lx-0x%0*lx   ",
+			   width, st->start_address,
+			   width, st->current_address);
 
 		delta = (st->current_address - st->start_address) >> 10;
 		while (!(delta & 1023) && unit[1]) {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a03b7279efa0..c6acc6326374 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -3,40 +3,17 @@
  *  Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
  *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
  */
-#include <linux/interrupt.h>
-#include <linux/mmiotrace.h>
-#include <linux/bootmem.h>
-#include <linux/compiler.h>
-#include <linux/highmem.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/vt_kern.h>
-#include <linux/signal.h>
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/module.h>
-#include <linux/kdebug.h>
-#include <linux/errno.h>
-#include <linux/magic.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/mman.h>
-#include <linux/tty.h>
-#include <linux/smp.h>
-#include <linux/mm.h>
+#include <linux/magic.h>		/* STACK_END_MAGIC		*/
+#include <linux/sched.h>		/* test_thread_flag(), ...	*/
+#include <linux/kdebug.h>		/* oops_begin/end, ...		*/
+#include <linux/module.h>		/* search_exception_table	*/
+#include <linux/bootmem.h>		/* max_low_pfn			*/
+#include <linux/kprobes.h>		/* __kprobes, ...		*/
+#include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
+#include <linux/perf_counter.h>		/* perf_swcounter_event		*/
 
-#include <asm-generic/sections.h>
-
-#include <asm/tlbflush.h>
-#include <asm/pgalloc.h>
-#include <asm/segment.h>
-#include <asm/system.h>
-#include <asm/proto.h>
-#include <asm/traps.h>
-#include <asm/desc.h>
+#include <asm/traps.h>			/* dotraplinkage, ...		*/
+#include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 
 /*
  * Page fault error code bits:
@@ -225,12 +202,10 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	if (!pmd_present(*pmd_k))
 		return NULL;
 
-	if (!pmd_present(*pmd)) {
+	if (!pmd_present(*pmd))
 		set_pmd(pmd, *pmd_k);
-		arch_flush_lazy_mmu_mode();
-	} else {
+	else
 		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
-	}
 
 	return pmd_k;
 }
@@ -538,8 +513,6 @@ bad:
 static int is_errata93(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_64
-	static int once;
-
 	if (address != regs->ip)
 		return 0;
 
@@ -549,10 +522,7 @@ static int is_errata93(struct pt_regs *regs, unsigned long address)
 	address |= 0xffffffffUL << 32;
 	if ((address >= (u64)_stext && address <= (u64)_etext) ||
 	    (address >= MODULES_VADDR && address <= MODULES_END)) {
-		if (!once) {
-			printk(errata93_warning);
-			once = 1;
-		}
+		printk_once(errata93_warning);
 		regs->ip = address;
 		return 1;
 	}
@@ -1044,6 +1014,8 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
+	perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+
 	/*
 	 * If we're in an interrupt, have no user context or are running
 	 * in an atomic region then we must not take the fault:
@@ -1137,10 +1109,15 @@ good_area:
 		return;
 	}
 
-	if (fault & VM_FAULT_MAJOR)
+	if (fault & VM_FAULT_MAJOR) {
 		tsk->maj_flt++;
-	else
+		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+				     regs, address);
+	} else {
 		tsk->min_flt++;
+		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+				     regs, address);
+	}
 
 	check_v8086_mode(regs, address, tsk);
 
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 8126e8d1a2a4..58f621e81919 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -44,7 +44,6 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
 	set_pte(kmap_pte-idx, mk_pte(page, prot));
-	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
 }
@@ -74,7 +73,6 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 #endif
 	}
 
-	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ae4f7b5d7104..34c1bfb64f1c 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,3 +1,4 @@
+#include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
 
@@ -10,6 +11,9 @@
 #include <asm/setup.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
 unsigned long __initdata e820_table_start;
 unsigned long __meminitdata e820_table_end;
@@ -23,6 +27,69 @@ int direct_gbpages
 #endif
 ;
 
+int nx_enabled;
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+static int disable_nx __cpuinitdata;
+
+/*
+ * noexec = on|off
+ *
+ * Control non-executable mappings for processes.
+ *
+ * on      Enable
+ * off     Disable
+ */
+static int __init noexec_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	if (!strncmp(str, "on", 2)) {
+		__supported_pte_mask |= _PAGE_NX;
+		disable_nx = 0;
+	} else if (!strncmp(str, "off", 3)) {
+		disable_nx = 1;
+		__supported_pte_mask &= ~_PAGE_NX;
+	}
+	return 0;
+}
+early_param("noexec", noexec_setup);
+#endif
+
+#ifdef CONFIG_X86_PAE
+static void __init set_nx(void)
+{
+	unsigned int v[4], l, h;
+
+	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
+		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
+
+		if ((v[3] & (1 << 20)) && !disable_nx) {
+			rdmsr(MSR_EFER, l, h);
+			l |= EFER_NX;
+			wrmsr(MSR_EFER, l, h);
+			nx_enabled = 1;
+			__supported_pte_mask |= _PAGE_NX;
+		}
+	}
+}
+#else
+static inline void set_nx(void)
+{
+}
+#endif
+
+#ifdef CONFIG_X86_64
+void __cpuinit check_efer(void)
+{
+	unsigned long efer;
+
+	rdmsrl(MSR_EFER, efer);
+	if (!(efer & EFER_NX) || disable_nx)
+		__supported_pte_mask &= ~_PAGE_NX;
+}
+#endif
+
 static void __init find_early_table_space(unsigned long end, int use_pse,
 					  int use_gbpages)
 {
@@ -66,12 +133,11 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 	 */
 #ifdef CONFIG_X86_32
 	start = 0x7000;
+#else
+	start = 0x8000;
+#endif
 	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
 					tables, PAGE_SIZE);
-#else /* CONFIG_X86_64 */
-	start = 0x8000;
-	e820_table_start = find_e820_area(start, end, tables, PAGE_SIZE);
-#endif
 	if (e820_table_start == -1UL)
 		panic("Cannot find space for the kernel page tables");
 
@@ -159,12 +225,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	use_gbpages = direct_gbpages;
 #endif
 
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_X86_PAE
 	set_nx();
 	if (nx_enabled)
 		printk(KERN_INFO "NX (Execute Disable) protection: active\n");
-#endif
 
 	/* Enable PSE if available */
 	if (cpu_has_pse)
@@ -175,7 +238,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 		set_in_cr4(X86_CR4_PGE);
 		__supported_pte_mask |= _PAGE_GLOBAL;
 	}
-#endif
 
 	if (use_gbpages)
 		page_size_mask |= 1 << PG_LEVEL_1G;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 749559ed80f5..949708d7a481 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,12 +49,9 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
+#include <asm/page_types.h>
 #include <asm/init.h>
 
-unsigned long max_low_pfn_mapped;
-unsigned long max_pfn_mapped;
-
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 unsigned long highstart_pfn, highend_pfn;
 
 static noinline int do_test_wp_bit(void);
@@ -587,61 +584,9 @@ void zap_low_mappings(void)
 	flush_tlb_all();
 }
 
-int nx_enabled;
-
 pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
-#ifdef CONFIG_X86_PAE
-
-static int disable_nx __initdata;
-
-/*
- * noexec = on|off
- *
- * Control non executable mappings.
- *
- * on      Enable
- * off     Disable
- */
-static int __init noexec_setup(char *str)
-{
-	if (!str || !strcmp(str, "on")) {
-		if (cpu_has_nx) {
-			__supported_pte_mask |= _PAGE_NX;
-			disable_nx = 0;
-		}
-	} else {
-		if (!strcmp(str, "off")) {
-			disable_nx = 1;
-			__supported_pte_mask &= ~_PAGE_NX;
-		} else {
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-early_param("noexec", noexec_setup);
-
-void __init set_nx(void)
-{
-	unsigned int v[4], l, h;
-
-	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
-		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
-
-		if ((v[3] & (1 << 20)) && !disable_nx) {
-			rdmsr(MSR_EFER, l, h);
-			l |= EFER_NX;
-			wrmsr(MSR_EFER, l, h);
-			nx_enabled = 1;
-			__supported_pte_mask |= _PAGE_NX;
-		}
-	}
-}
-#endif
-
 /* user-defined highmem size */
 static unsigned int highmem_pages = -1;
 
@@ -761,15 +706,15 @@ void __init initmem_init(unsigned long start_pfn,
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
 		highstart_pfn = max_low_pfn;
-	memory_present(0, 0, highend_pfn);
 	e820_register_active_regions(0, 0, highend_pfn);
+	sparse_memory_present_with_active_regions(0);
 	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
 		pages_to_mb(highend_pfn - highstart_pfn));
 	num_physpages = highend_pfn;
 	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-	memory_present(0, 0, max_low_pfn);
 	e820_register_active_regions(0, 0, max_low_pfn);
+	sparse_memory_present_with_active_regions(0);
 	num_physpages = max_low_pfn;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
 #endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 1753e8020df6..52bb9519bb86 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -50,18 +50,8 @@
 #include <asm/cacheflush.h>
 #include <asm/init.h>
 
-/*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
- */
-unsigned long max_low_pfn_mapped;
-unsigned long max_pfn_mapped;
-
 static unsigned long dma_reserve __initdata;
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -85,39 +75,6 @@ early_param("gbpages", parse_direct_gbpages_on);
 pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
-static int disable_nx __cpuinitdata;
-
-/*
- * noexec=on|off
- * Control non-executable mappings for 64-bit processes.
- *
- * on	Enable (default)
- * off	Disable
- */
-static int __init nonx_setup(char *str)
-{
-	if (!str)
-		return -EINVAL;
-	if (!strncmp(str, "on", 2)) {
-		__supported_pte_mask |= _PAGE_NX;
-		disable_nx = 0;
-	} else if (!strncmp(str, "off", 3)) {
-		disable_nx = 1;
-		__supported_pte_mask &= ~_PAGE_NX;
-	}
-	return 0;
-}
-early_param("noexec", nonx_setup);
-
-void __cpuinit check_efer(void)
-{
-	unsigned long efer;
-
-	rdmsrl(MSR_EFER, efer);
-	if (!(efer & EFER_NX) || disable_nx)
-		__supported_pte_mask &= ~_PAGE_NX;
-}
-
 int force_personality32;
 
 /*
@@ -628,6 +585,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 	early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
 	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
 }
+#endif
 
 void __init paging_init(void)
 {
@@ -638,11 +596,10 @@ void __init paging_init(void)
 	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
 	max_zone_pfns[ZONE_NORMAL] = max_pfn;
 
-	memory_present(0, 0, max_pfn);
+	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
 	free_area_init_nodes(max_zone_pfns);
 }
-#endif
 
 /*
  * Memory hotplug specific functions
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 8056545e2d39..fe6f84ca121e 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -82,7 +82,6 @@ iounmap_atomic(void *kvaddr, enum km_type type)
 	if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 
-	arch_flush_lazy_mmu_mode();
 	pagefault_enable();
 }
 EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 50dc802a1c46..16ccbd77917f 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -32,7 +32,7 @@ struct kmmio_fault_page {
 	struct list_head list;
 	struct kmmio_fault_page *release_next;
 	unsigned long page; /* location of the fault page */
-	bool old_presence; /* page presence prior to arming */
+	pteval_t old_presence; /* page presence prior to arming */
 	bool armed;
 
 	/*
@@ -97,60 +97,62 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
 static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
 {
 	struct list_head *head;
-	struct kmmio_fault_page *p;
+	struct kmmio_fault_page *f;
 
 	page &= PAGE_MASK;
 	head = kmmio_page_list(page);
-	list_for_each_entry_rcu(p, head, list) {
-		if (p->page == page)
-			return p;
+	list_for_each_entry_rcu(f, head, list) {
+		if (f->page == page)
+			return f;
 	}
 	return NULL;
 }
 
-static void set_pmd_presence(pmd_t *pmd, bool present, bool *old)
+static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old)
 {
 	pmdval_t v = pmd_val(*pmd);
-	*old = !!(v & _PAGE_PRESENT);
-	v &= ~_PAGE_PRESENT;
-	if (present)
-		v |= _PAGE_PRESENT;
+	if (clear) {
+		*old = v & _PAGE_PRESENT;
+		v &= ~_PAGE_PRESENT;
+	} else	/* presume this has been called with clear==true previously */
+		v |= *old;
 	set_pmd(pmd, __pmd(v));
 }
 
-static void set_pte_presence(pte_t *pte, bool present, bool *old)
+static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
 {
 	pteval_t v = pte_val(*pte);
-	*old = !!(v & _PAGE_PRESENT);
-	v &= ~_PAGE_PRESENT;
-	if (present)
-		v |= _PAGE_PRESENT;
+	if (clear) {
+		*old = v & _PAGE_PRESENT;
+		v &= ~_PAGE_PRESENT;
+	} else	/* presume this has been called with clear==true previously */
+		v |= *old;
 	set_pte_atomic(pte, __pte(v));
 }
 
-static int set_page_presence(unsigned long addr, bool present, bool *old)
+static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 {
 	unsigned int level;
-	pte_t *pte = lookup_address(addr, &level);
+	pte_t *pte = lookup_address(f->page, &level);
 
 	if (!pte) {
-		pr_err("kmmio: no pte for page 0x%08lx\n", addr);
+		pr_err("kmmio: no pte for page 0x%08lx\n", f->page);
 		return -1;
 	}
 
 	switch (level) {
 	case PG_LEVEL_2M:
-		set_pmd_presence((pmd_t *)pte, present, old);
+		clear_pmd_presence((pmd_t *)pte, clear, &f->old_presence);
 		break;
 	case PG_LEVEL_4K:
-		set_pte_presence(pte, present, old);
+		clear_pte_presence(pte, clear, &f->old_presence);
 		break;
 	default:
 		pr_err("kmmio: unexpected page level 0x%x.\n", level);
 		return -1;
 	}
 
-	__flush_tlb_one(addr);
+	__flush_tlb_one(f->page);
 	return 0;
 }
 
@@ -171,9 +173,9 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 	WARN_ONCE(f->armed, KERN_ERR "kmmio page already armed.\n");
 	if (f->armed) {
 		pr_warning("kmmio double-arm: page 0x%08lx, ref %d, old %d\n",
-					f->page, f->count, f->old_presence);
+					f->page, f->count, !!f->old_presence);
 	}
-	ret = set_page_presence(f->page, false, &f->old_presence);
+	ret = clear_page_presence(f, true);
 	WARN_ONCE(ret < 0, KERN_ERR "kmmio arming 0x%08lx failed.\n", f->page);
 	f->armed = true;
 	return ret;
@@ -182,8 +184,7 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 /** Restore the given page to saved presence state. */
 static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
-	bool tmp;
-	int ret = set_page_presence(f->page, f->old_presence, &tmp);
+	int ret = clear_page_presence(f, false);
 	WARN_ONCE(ret < 0,
 			KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
 	f->armed = false;
@@ -310,7 +311,12 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 	struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx);
 
 	if (!ctx->active) {
-		pr_debug("kmmio: spurious debug trap on CPU %d.\n",
+		/*
+		 * debug traps without an active context are due to either
+		 * something external causing them (f.e. using a debugger while
+		 * mmio tracing enabled), or erroneous behaviour
+		 */
+		pr_warning("kmmio: unexpected debug trap on CPU %d.\n",
 							smp_processor_id());
 		goto out;
 	}
@@ -439,12 +445,12 @@ static void rcu_free_kmmio_fault_pages(struct rcu_head *head)
 						head,
 						struct kmmio_delayed_release,
 						rcu);
-	struct kmmio_fault_page *p = dr->release_list;
-	while (p) {
-		struct kmmio_fault_page *next = p->release_next;
-		BUG_ON(p->count);
-		kfree(p);
-		p = next;
+	struct kmmio_fault_page *f = dr->release_list;
+	while (f) {
+		struct kmmio_fault_page *next = f->release_next;
+		BUG_ON(f->count);
+		kfree(f);
+		f = next;
 	}
 	kfree(dr);
 }
@@ -453,19 +459,19 @@ static void remove_kmmio_fault_pages(struct rcu_head *head)
 {
 	struct kmmio_delayed_release *dr =
 		container_of(head, struct kmmio_delayed_release, rcu);
-	struct kmmio_fault_page *p = dr->release_list;
+	struct kmmio_fault_page *f = dr->release_list;
 	struct kmmio_fault_page **prevp = &dr->release_list;
 	unsigned long flags;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
-	while (p) {
-		if (!p->count) {
-			list_del_rcu(&p->list);
-			prevp = &p->release_next;
+	while (f) {
+		if (!f->count) {
+			list_del_rcu(&f->list);
+			prevp = &f->release_next;
 		} else {
-			*prevp = p->release_next;
+			*prevp = f->release_next;
 		}
-		p = p->release_next;
+		f = f->release_next;
 	}
 	spin_unlock_irqrestore(&kmmio_lock, flags);
 
@@ -528,8 +534,8 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 }
 EXPORT_SYMBOL(unregister_kmmio_probe);
 
-static int kmmio_die_notifier(struct notifier_block *nb, unsigned long val,
-								void *args)
+static int
+kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args)
 {
 	struct die_args *arg = args;
 
@@ -544,11 +550,23 @@ static struct notifier_block nb_die = {
 	.notifier_call = kmmio_die_notifier
 };
 
-static int __init init_kmmio(void)
+int kmmio_init(void)
 {
 	int i;
+
 	for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++)
 		INIT_LIST_HEAD(&kmmio_page_table[i]);
+
 	return register_die_notifier(&nb_die);
 }
-fs_initcall(init_kmmio); /* should be before device_initcall() */
+
+void kmmio_cleanup(void)
+{
+	int i;
+
+	unregister_die_notifier(&nb_die);
+	for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++) {
+		WARN_ONCE(!list_empty(&kmmio_page_table[i]),
+			KERN_ERR "kmmio_page_table not empty at cleanup, any further tracing will leak memory.\n");
+	}
+}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 605c8be06217..18d244f70205 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -40,23 +40,22 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
 
 static void __init memtest(u64 pattern, u64 start_phys, u64 size)
 {
-	u64 i, count;
-	u64 *start;
+	u64 *p, *start, *end;
 	u64 start_bad, last_bad;
 	u64 start_phys_aligned;
-	size_t incr;
+	const size_t incr = sizeof(pattern);
 
-	incr = sizeof(pattern);
 	start_phys_aligned = ALIGN(start_phys, incr);
-	count = (size - (start_phys_aligned - start_phys))/incr;
 	start = __va(start_phys_aligned);
+	end = start + (size - (start_phys_aligned - start_phys)) / incr;
 	start_bad = 0;
 	last_bad = 0;
 
-	for (i = 0; i < count; i++)
-		start[i] = pattern;
-	for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
-		if (*start == pattern)
+	for (p = start; p < end; p++)
+		*p = pattern;
+
+	for (p = start; p < end; p++, start_phys_aligned += incr) {
+		if (*p == pattern)
 			continue;
 		if (start_phys_aligned == last_bad + incr) {
 			last_bad += incr;
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index c9342ed8b402..132772a8ec57 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -451,6 +451,7 @@ void enable_mmiotrace(void)
 
 	if (nommiotrace)
 		pr_info(NAME "MMIO tracing disabled.\n");
+	kmmio_init();
 	enter_uniprocessor();
 	spin_lock_irq(&trace_lock);
 	atomic_inc(&mmiotrace_enabled);
@@ -473,6 +474,7 @@ void disable_mmiotrace(void)
 
 	clear_trace_list(); /* guarantees: no more kmmio callbacks */
 	leave_uniprocessor();
+	kmmio_cleanup();
 	pr_info(NAME "disabled.\n");
 out:
 	mutex_unlock(&mmiotrace_mutex);
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 2d05a12029dc..459913beac71 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -179,18 +179,25 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 }
 
 /* Initialize bootmem allocator for a node */
-void __init setup_node_bootmem(int nodeid, unsigned long start,
-			       unsigned long end)
+void __init
+setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 {
 	unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
+	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	unsigned long bootmap_start, nodedata_phys;
 	void *bootmap;
-	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
 
 	if (!end)
 		return;
 
+	/*
+	 * Don't confuse VM with a node that doesn't have the
+	 * minimum amount of memory:
+	 */
+	if (end && (end - start) < NODE_MIN_SIZE)
+		return;
+
 	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
@@ -272,9 +279,6 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 		reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
 				 bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
 
-#ifdef CONFIG_ACPI_NUMA
-	srat_reserve_add_area(nodeid);
-#endif
 	node_set_online(nodeid);
 }
 
@@ -578,21 +582,6 @@ unsigned long __init numa_free_all_bootmem(void)
 	return pages;
 }
 
-void __init paging_init(void)
-{
-	unsigned long max_zone_pfns[MAX_NR_ZONES];
-
-	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
-	max_zone_pfns[ZONE_NORMAL] = max_pfn;
-
-	sparse_memory_present_with_active_regions(MAX_NUMNODES);
-	sparse_init();
-
-	free_area_init_nodes(max_zone_pfns);
-}
-
 static __init int numa_setup(char *opt)
 {
 	if (!opt)
@@ -606,8 +595,6 @@ static __init int numa_setup(char *opt)
 #ifdef CONFIG_ACPI_NUMA
 	if (!strncmp(opt, "noacpi", 6))
 		acpi_numa = -1;
-	if (!strncmp(opt, "hotadd=", 7))
-		hotadd_percent = simple_strtoul(opt+7, NULL, 10);
 #endif
 	return 0;
 }
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e17efed088c5..6ce9518fe2ac 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -839,13 +839,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	vm_unmap_aliases();
 
-	/*
-	 * If we're called with lazy mmu updates enabled, the
-	 * in-memory pte state may be stale.  Flush pending updates to
-	 * bring them up to date.
-	 */
-	arch_flush_lazy_mmu_mode();
-
 	cpa.vaddr = addr;
 	cpa.pages = pages;
 	cpa.numpages = numpages;
@@ -890,13 +883,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	} else
 		cpa_flush_all(cache);
 
-	/*
-	 * If we've been called with lazy mmu updates enabled, then
-	 * make sure that everything gets flushed out before we
-	 * return.
-	 */
-	arch_flush_lazy_mmu_mode();
-
 out:
 	return ret;
 }
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 01765955baaf..2dfcbf9df2ae 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -31,17 +31,11 @@ static nodemask_t nodes_parsed __initdata;
 static nodemask_t cpu_nodes_parsed __initdata;
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
 static struct bootnode nodes_add[MAX_NUMNODES];
-static int found_add_area __initdata;
-int hotadd_percent __initdata = 0;
 
 static int num_node_memblks __initdata;
 static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata;
 static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata;
 
-/* Too small nodes confuse the VM badly. Usually they result
-   from BIOS bugs. */
-#define NODE_MIN_SIZE (4*1024*1024)
-
 static __init int setup_node(int pxm)
 {
 	return acpi_map_pxm_to_node(pxm);
@@ -66,9 +60,6 @@ static __init void cutoff_node(int i, unsigned long start, unsigned long end)
 {
 	struct bootnode *nd = &nodes[i];
 
-	if (found_add_area)
-		return;
-
 	if (nd->start < start) {
 		nd->start = start;
 		if (nd->end < nd->start)
@@ -86,7 +77,6 @@ static __init void bad_srat(void)
 	int i;
 	printk(KERN_ERR "SRAT: SRAT not used.\n");
 	acpi_numa = -1;
-	found_add_area = 0;
 	for (i = 0; i < MAX_LOCAL_APIC; i++)
 		apicid_to_node[i] = NUMA_NO_NODE;
 	for (i = 0; i < MAX_NUMNODES; i++)
@@ -182,24 +172,21 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	       pxm, apic_id, node);
 }
 
-static int update_end_of_memory(unsigned long end) {return -1;}
-static int hotadd_enough_memory(struct bootnode *nd) {return 1;}
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 static inline int save_add_info(void) {return 1;}
 #else
 static inline int save_add_info(void) {return 0;}
 #endif
 /*
- * Update nodes_add and decide if to include add are in the zone.
- * Both SPARSE and RESERVE need nodes_add information.
- * This code supports one contiguous hot add area per node.
+ * Update nodes_add[]
+ * This code supports one contiguous hot add area per node
  */
-static int __init
-reserve_hotadd(int node, unsigned long start, unsigned long end)
+static void __init
+update_nodes_add(int node, unsigned long start, unsigned long end)
 {
 	unsigned long s_pfn = start >> PAGE_SHIFT;
 	unsigned long e_pfn = end >> PAGE_SHIFT;
-	int ret = 0, changed = 0;
+	int changed = 0;
 	struct bootnode *nd = &nodes_add[node];
 
 	/* I had some trouble with strange memory hotadd regions breaking
@@ -210,7 +197,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end)
 	   mistakes */
 	if ((signed long)(end - start) < NODE_MIN_SIZE) {
 		printk(KERN_ERR "SRAT: Hotplug area too small\n");
-		return -1;
+		return;
 	}
 
 	/* This check might be a bit too strict, but I'm keeping it for now. */
@@ -218,12 +205,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end)
 		printk(KERN_ERR
 			"SRAT: Hotplug area %lu -> %lu has existing memory\n",
 			s_pfn, e_pfn);
-		return -1;
-	}
-
-	if (!hotadd_enough_memory(&nodes_add[node]))  {
-		printk(KERN_ERR "SRAT: Hotplug area too large\n");
-		return -1;
+		return;
 	}
 
 	/* Looks good */
@@ -245,11 +227,9 @@ reserve_hotadd(int node, unsigned long start, unsigned long end)
 			printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n");
 	}
 
-	ret = update_end_of_memory(nd->end);
-
 	if (changed)
-	 	printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end);
-	return ret;
+		printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n",
+				 nd->start, nd->end);
 }
 
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
@@ -310,13 +290,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 	       start, end);
 	e820_register_active_regions(node, start >> PAGE_SHIFT,
 				     end >> PAGE_SHIFT);
-	push_node_boundaries(node, nd->start >> PAGE_SHIFT,
-						nd->end >> PAGE_SHIFT);
 
-	if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) &&
-	    (reserve_hotadd(node, start, end) < 0)) {
-		/* Ignore hotadd region. Undo damage */
-		printk(KERN_NOTICE "SRAT: Hotplug region ignored\n");
+	if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) {
+		update_nodes_add(node, start, end);
+		/* restore nodes[node] */
 		*nd = oldnode;
 		if ((nd->start | nd->end) == 0)
 			node_clear(node, nodes_parsed);
@@ -345,9 +322,9 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 			pxmram = 0;
 	}
 
-	e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
-	/* We seem to lose 3 pages somewhere. Allow a bit of slack. */
-	if ((long)(e820ram - pxmram) >= 1*1024*1024) {
+	e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
+	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
+	if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
 		printk(KERN_ERR
 	"SRAT: PXMs only cover %luMB of your %luMB e820 RAM. Not used.\n",
 			(pxmram << PAGE_SHIFT) >> 20,
@@ -357,17 +334,6 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 	return 1;
 }
 
-static void __init unparse_node(int node)
-{
-	int i;
-	node_clear(node, nodes_parsed);
-	node_clear(node, cpu_nodes_parsed);
-	for (i = 0; i < MAX_LOCAL_APIC; i++) {
-		if (apicid_to_node[i] == node)
-			apicid_to_node[i] = NUMA_NO_NODE;
-	}
-}
-
 void __init acpi_numa_arch_fixup(void) {}
 
 /* Use the information discovered above to actually set up the nodes. */
@@ -379,18 +345,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 		return -1;
 
 	/* First clean up the node list */
-	for (i = 0; i < MAX_NUMNODES; i++) {
+	for (i = 0; i < MAX_NUMNODES; i++)
 		cutoff_node(i, start, end);
-		/*
-		 * don't confuse VM with a node that doesn't have the
-		 * minimum memory.
-		 */
-		if (nodes[i].end &&
-			(nodes[i].end - nodes[i].start) < NODE_MIN_SIZE) {
-			unparse_node(i);
-			node_set_offline(i);
-		}
-	}
 
 	if (!nodes_cover_memory(nodes)) {
 		bad_srat();
@@ -423,7 +379,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 
 		if (node == NUMA_NO_NODE)
 			continue;
-		if (!node_isset(node, node_possible_map))
+		if (!node_online(node))
 			numa_clear_node(i);
 	}
 	numa_init_array();
@@ -510,26 +466,6 @@ static int null_slit_node_compare(int a, int b)
 }
 #endif /* CONFIG_NUMA_EMU */
 
-void __init srat_reserve_add_area(int nodeid)
-{
-	if (found_add_area && nodes_add[nodeid].end) {
-		u64 total_mb;
-
-		printk(KERN_INFO "SRAT: Reserving hot-add memory space "
-				"for node %d at %Lx-%Lx\n",
-			nodeid, nodes_add[nodeid].start, nodes_add[nodeid].end);
-		total_mb = (nodes_add[nodeid].end - nodes_add[nodeid].start)
-					>> PAGE_SHIFT;
-		total_mb *= sizeof(struct page);
-		total_mb >>= 20;
-		printk(KERN_INFO "SRAT: This will cost you %Lu MB of "
-				"pre-allocated memory.\n", (unsigned long long)total_mb);
-		reserve_bootmem_node(NODE_DATA(nodeid), nodes_add[nodeid].start,
-			       nodes_add[nodeid].end - nodes_add[nodeid].start,
-			       BOOTMEM_DEFAULT);
-	}
-}
-
 int __node_distance(int a, int b)
 {
 	int index;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 202864ad49a7..b07dd8d0b321 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -40,8 +40,9 @@ static int profile_exceptions_notify(struct notifier_block *self,
 
 	switch (val) {
 	case DIE_NMI:
-		if (model->check_ctrs(args->regs, &per_cpu(cpu_msrs, cpu)))
-			ret = NOTIFY_STOP;
+	case DIE_NMI_IPI:
+		model->check_ctrs(args->regs, &per_cpu(cpu_msrs, cpu));
+		ret = NOTIFY_STOP;
 		break;
 	default:
 		break;
@@ -134,7 +135,7 @@ static void nmi_cpu_setup(void *dummy)
 static struct notifier_block profile_exceptions_nb = {
 	.notifier_call = profile_exceptions_notify,
 	.next = NULL,
-	.priority = 0
+	.priority = 2
 };
 
 static int nmi_setup(void)
@@ -356,14 +357,11 @@ static void exit_sysfs(void)
 #define exit_sysfs() do { } while (0)
 #endif /* CONFIG_PM */
 
-static int p4force;
-module_param(p4force, int, 0);
-
 static int __init p4_init(char **cpu_type)
 {
 	__u8 cpu_model = boot_cpu_data.x86_model;
 
-	if (!p4force && (cpu_model > 6 || cpu_model == 5))
+	if (cpu_model > 6 || cpu_model == 5)
 		return 0;
 
 #ifndef CONFIG_SMP
@@ -389,10 +387,25 @@ static int __init p4_init(char **cpu_type)
 	return 0;
 }
 
+static int force_arch_perfmon;
+static int force_cpu_type(const char *str, struct kernel_param *kp)
+{
+	if (!strcmp(str, "archperfmon")) {
+		force_arch_perfmon = 1;
+		printk(KERN_INFO "oprofile: forcing architectural perfmon\n");
+	}
+
+	return 0;
+}
+module_param_call(cpu_type, force_cpu_type, NULL, NULL, 0);
+
 static int __init ppro_init(char **cpu_type)
 {
 	__u8 cpu_model = boot_cpu_data.x86_model;
 
+	if (force_arch_perfmon && cpu_has_arch_perfmon)
+		return 0;
+
 	switch (cpu_model) {
 	case 0 ... 2:
 		*cpu_type = "i386/ppro";
@@ -414,6 +427,13 @@ static int __init ppro_init(char **cpu_type)
 	case 15: case 23:
 		*cpu_type = "i386/core_2";
 		break;
+	case 26:
+		arch_perfmon_setup_counters();
+		*cpu_type = "i386/core_i7";
+		break;
+	case 28:
+		*cpu_type = "i386/atom";
+		break;
 	default:
 		/* Unknown */
 		return 0;
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 10131fbdaada..4da7230b3d17 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -18,7 +18,7 @@
 #include <asm/msr.h>
 #include <asm/apic.h>
 #include <asm/nmi.h>
-#include <asm/intel_arch_perfmon.h>
+#include <asm/perf_counter.h>
 
 #include "op_x86_model.h"
 #include "op_counter.h"
@@ -136,6 +136,13 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
 	u64 val;
 	int i;
 
+	/*
+	 * This can happen if perf counters are in use when
+	 * we steal the die notifier NMI.
+	 */
+	if (unlikely(!reset_value))
+		goto out;
+
 	for (i = 0 ; i < num_counters; ++i) {
 		if (!reset_value[i])
 			continue;
@@ -146,6 +153,7 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
 		}
 	}
 
+out:
 	/* Only P6 based Pentium M need to re-unmask the apic vector but it
 	 * doesn't hurt other P6 variant */
 	apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index fecbce6e7d7c..0696d506c4ad 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -889,6 +889,9 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 		return 0;
 	}
 
+	if (io_apic_assign_pci_irqs)
+		return 0;
+
 	/* Find IRQ routing entry */
 
 	if (!pirq_table)
@@ -1039,56 +1042,15 @@ static void __init pcibios_fixup_irqs(void)
 		pirq_penalty[dev->irq]++;
 	}
 
+	if (io_apic_assign_pci_irqs)
+		return;
+
 	dev = NULL;
 	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
 		pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
 		if (!pin)
 			continue;
 
-#ifdef CONFIG_X86_IO_APIC
-		/*
-		 * Recalculate IRQ numbers if we use the I/O APIC.
-		 */
-		if (io_apic_assign_pci_irqs) {
-			int irq;
-
-			/*
-			 * interrupt pins are numbered starting from 1
-			 */
-			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
-				PCI_SLOT(dev->devfn), pin - 1);
-			/*
-			 * Busses behind bridges are typically not listed in the
-			 * MP-table.  In this case we have to look up the IRQ
-			 * based on the parent bus, parent slot, and pin number.
-			 * The SMP code detects such bridged busses itself so we
-			 * should get into this branch reliably.
-			 */
-			if (irq < 0 && dev->bus->parent) {
-				/* go back to the bridge */
-				struct pci_dev *bridge = dev->bus->self;
-				int bus;
-
-				pin = pci_swizzle_interrupt_pin(dev, pin);
-				bus = bridge->bus->number;
-				irq = IO_APIC_get_PCI_irq_vector(bus,
-						PCI_SLOT(bridge->devfn), pin - 1);
-				if (irq >= 0)
-					dev_warn(&dev->dev,
-						"using bridge %s INT %c to "
-							"get IRQ %d\n",
-						 pci_name(bridge),
-						 'A' + pin - 1, irq);
-			}
-			if (irq >= 0) {
-				dev_info(&dev->dev,
-					"PCI->APIC IRQ transform: INT %c "
-						"-> IRQ %d\n",
-					'A' + pin - 1, irq);
-				dev->irq = irq;
-			}
-		}
-#endif
 		/*
 		 * Still no IRQ? Try to lookup one...
 		 */
@@ -1183,6 +1145,19 @@ int __init pcibios_irq_init(void)
 	pcibios_enable_irq = pirq_enable_irq;
 
 	pcibios_fixup_irqs();
+
+	if (io_apic_assign_pci_irqs && pci_routeirq) {
+		struct pci_dev *dev = NULL;
+		/*
+		 * PCI IRQ routing is set up by pci_enable_device(), but we
+		 * also do it here in case there are still broken drivers that
+		 * don't use pci_enable_device().
+		 */
+		printk(KERN_INFO "PCI: Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n");
+		for_each_pci_dev(dev)
+			pirq_enable_irq(dev);
+	}
+
 	return 0;
 }
 
@@ -1213,16 +1188,23 @@ void pcibios_penalize_isa_irq(int irq, int active)
 static int pirq_enable_irq(struct pci_dev *dev)
 {
 	u8 pin;
-	struct pci_dev *temp_dev;
 
 	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
-	if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) {
+	if (pin && !pcibios_lookup_irq(dev, 1)) {
 		char *msg = "";
 
-		if (io_apic_assign_pci_irqs) {
-			int irq;
+		if (!io_apic_assign_pci_irqs && dev->irq)
+			return 0;
 
-			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin - 1);
+		if (io_apic_assign_pci_irqs) {
+#ifdef CONFIG_X86_IO_APIC
+			struct pci_dev *temp_dev;
+			int irq;
+			struct io_apic_irq_attr irq_attr;
+
+			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
+						PCI_SLOT(dev->devfn),
+						pin - 1, &irq_attr);
 			/*
 			 * Busses behind bridges are typically not listed in the MP-table.
 			 * In this case we have to look up the IRQ based on the parent bus,
@@ -1235,7 +1217,8 @@ static int pirq_enable_irq(struct pci_dev *dev)
 
 				pin = pci_swizzle_interrupt_pin(dev, pin);
 				irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
-						PCI_SLOT(bridge->devfn), pin - 1);
+						PCI_SLOT(bridge->devfn),
+						pin - 1, &irq_attr);
 				if (irq >= 0)
 					dev_warn(&dev->dev, "using bridge %s "
 						 "INT %c to get IRQ %d\n",
@@ -1245,12 +1228,15 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
+				io_apic_set_pci_routing(&dev->dev, irq,
+							 &irq_attr);
+				dev->irq = irq;
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
-				dev->irq = irq;
 				return 0;
 			} else
 				msg = "; probably buggy MP table";
+#endif
 		} else if (pci_probe & PCI_BIOS_IRQ_SCAN)
 			msg = "";
 		else
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 1241f118ab56..58bc00f68b12 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -338,6 +338,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		}
 	}
 
+	current->mm->context.vdso = (void *)addr;
+
 	if (compat_uses_vma || !compat) {
 		/*
 		 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -358,11 +360,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 			goto up_fail;
 	}
 
-	current->mm->context.vdso = (void *)addr;
 	current_thread_info()->sysenter_return =
 		VDSO32_SYMBOL(addr, SYSENTER_RETURN);
 
   up_fail:
+	if (ret)
+		current->mm->context.vdso = NULL;
+
 	up_write(&mm->mmap_sem);
 
 	return ret;
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 7133cdf9098b..21e1aeb9f3ea 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/random.h>
+#include <linux/elf.h>
 #include <asm/vsyscall.h>
 #include <asm/vgtod.h>
 #include <asm/proto.h>
@@ -115,15 +116,18 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		goto up_fail;
 	}
 
+	current->mm->context.vdso = (void *)addr;
+
 	ret = install_special_mapping(mm, addr, vdso_size,
 				      VM_READ|VM_EXEC|
 				      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
 				      VM_ALWAYSDUMP,
 				      vdso_pages);
-	if (ret)
+	if (ret) {
+		current->mm->context.vdso = NULL;
 		goto up_fail;
+	}
 
-	current->mm->context.vdso = (void *)addr;
 up_fail:
 	up_write(&mm->mmap_sem);
 	return ret;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f09e8c36ee80..0a1700a2be9c 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/start_kernel.h>
 #include <linux/sched.h>
+#include <linux/kprobes.h>
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -44,6 +45,7 @@
 #include <asm/processor.h>
 #include <asm/proto.h>
 #include <asm/msr-index.h>
+#include <asm/traps.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
@@ -240,10 +242,10 @@ static unsigned long xen_get_debugreg(int reg)
 	return HYPERVISOR_get_debugreg(reg);
 }
 
-void xen_leave_lazy(void)
+static void xen_end_context_switch(struct task_struct *next)
 {
-	paravirt_leave_lazy(paravirt_get_lazy_mode());
 	xen_mc_flush();
+	paravirt_end_context_switch(next);
 }
 
 static unsigned long xen_store_tr(void)
@@ -428,11 +430,44 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 static int cvt_gate_to_trap(int vector, const gate_desc *val,
 			    struct trap_info *info)
 {
+	unsigned long addr;
+
 	if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
 		return 0;
 
 	info->vector = vector;
-	info->address = gate_offset(*val);
+
+	addr = gate_offset(*val);
+#ifdef CONFIG_X86_64
+	/*
+	 * Look for known traps using IST, and substitute them
+	 * appropriately.  The debugger ones are the only ones we care
+	 * about.  Xen will handle faults like double_fault and
+	 * machine_check, so we should never see them.  Warn if
+	 * there's an unexpected IST-using fault handler.
+	 */
+	if (addr == (unsigned long)debug)
+		addr = (unsigned long)xen_debug;
+	else if (addr == (unsigned long)int3)
+		addr = (unsigned long)xen_int3;
+	else if (addr == (unsigned long)stack_segment)
+		addr = (unsigned long)xen_stack_segment;
+	else if (addr == (unsigned long)double_fault ||
+		 addr == (unsigned long)nmi) {
+		/* Don't need to handle these */
+		return 0;
+#ifdef CONFIG_X86_MCE
+	} else if (addr == (unsigned long)machine_check) {
+		return 0;
+#endif
+	} else {
+		/* Some other trap using IST? */
+		if (WARN_ON(val->ist != 0))
+			return 0;
+	}
+#endif	/* CONFIG_X86_64 */
+	info->address = addr;
+
 	info->cs = gate_segment(*val);
 	info->flags = val->dpl;
 	/* interrupt gates clear IF */
@@ -623,10 +658,26 @@ static void xen_clts(void)
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 
+static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
+
+static unsigned long xen_read_cr0(void)
+{
+	unsigned long cr0 = percpu_read(xen_cr0_value);
+
+	if (unlikely(cr0 == 0)) {
+		cr0 = native_read_cr0();
+		percpu_write(xen_cr0_value, cr0);
+	}
+
+	return cr0;
+}
+
 static void xen_write_cr0(unsigned long cr0)
 {
 	struct multicall_space mcs;
 
+	percpu_write(xen_cr0_value, cr0);
+
 	/* Only pay attention to cr0.TS; everything else is
 	   ignored. */
 	mcs = xen_mc_entry(0);
@@ -812,7 +863,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 
 	.clts = xen_clts,
 
-	.read_cr0 = native_read_cr0,
+	.read_cr0 = xen_read_cr0,
 	.write_cr0 = xen_write_cr0,
 
 	.read_cr4 = native_read_cr4,
@@ -860,10 +911,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 	/* Xen takes care of %gs when switching to usermode for us */
 	.swapgs = paravirt_nop,
 
-	.lazy_mode = {
-		.enter = paravirt_enter_lazy_cpu,
-		.leave = xen_leave_lazy,
-	},
+	.start_context_switch = paravirt_start_context_switch,
+	.end_context_switch = xen_end_context_switch,
 };
 
 static const struct pv_apic_ops xen_apic_ops __initdata = {
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index fba55b1a4021..4ceb28581652 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -452,10 +452,6 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval)
 {
-	/* updates to init_mm may be done without lock */
-	if (mm == &init_mm)
-		preempt_disable();
-
 	ADD_STATS(set_pte_at, 1);
 //	ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
 	ADD_STATS(set_pte_at_current, mm == current->mm);
@@ -476,9 +472,7 @@ void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 	}
 	xen_set_pte(ptep, pteval);
 
-out:
-	if (mm == &init_mm)
-		preempt_enable();
+out:	return;
 }
 
 pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
@@ -1152,10 +1146,8 @@ static void drop_other_mm_ref(void *info)
 
 	/* If this cpu still has a stale cr3 reference, then make sure
 	   it has been flushed. */
-	if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) {
+	if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
 		load_cr3(swapper_pg_dir);
-		arch_flush_lazy_cpu_mode();
-	}
 }
 
 static void xen_drop_mm_ref(struct mm_struct *mm)
@@ -1168,7 +1160,6 @@ static void xen_drop_mm_ref(struct mm_struct *mm)
 			load_cr3(swapper_pg_dir);
 		else
 			leave_mm(smp_processor_id());
-		arch_flush_lazy_cpu_mode();
 	}
 
 	/* Get the "official" set of cpus referring to our pagetable. */
@@ -1876,6 +1867,14 @@ __init void xen_post_allocator_init(void)
 	xen_mark_init_mm_pinned();
 }
 
+static void xen_leave_lazy_mmu(void)
+{
+	preempt_disable();
+	xen_mc_flush();
+	paravirt_leave_lazy_mmu();
+	preempt_enable();
+}
+
 const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.pagetable_setup_start = xen_pagetable_setup_start,
 	.pagetable_setup_done = xen_pagetable_setup_done,
@@ -1949,7 +1948,7 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 	.lazy_mode = {
 		.enter = paravirt_enter_lazy_mmu,
-		.leave = xen_leave_lazy,
+		.leave = xen_leave_lazy_mmu,
 	},
 
 	.set_fixmap = xen_set_fixmap,
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 15c6c68db6a2..ad0047f47cd4 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -61,9 +61,9 @@ char * __init xen_memory_setup(void)
 	 *  - xen_start_info
 	 * See comment above "struct start_info" in <xen/interface/xen.h>
 	 */
-	e820_add_region(__pa(xen_start_info->mfn_list),
-			xen_start_info->pt_base - xen_start_info->mfn_list,
-			E820_RESERVED);
+	reserve_early(__pa(xen_start_info->mfn_list),
+		      __pa(xen_start_info->pt_base),
+			"XEN START INFO");
 
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index ca6596b05d53..22494fd4c9b5 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -30,7 +30,6 @@ pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_ident_map_ISA(void);
 void xen_reserve_top(void);
 
-void xen_leave_lazy(void);
 void xen_post_allocator_init(void);
 
 char * __init xen_memory_setup(void);
diff --git a/block/Kconfig b/block/Kconfig
index e7d12782bcfb..2c39527aa7db 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -26,6 +26,7 @@ if BLOCK
 config LBD
 	bool "Support for large block devices and files"
 	depends on !64BIT
+	default y
 	help
 	  Enable block devices or files of size 2TB and larger.
 
@@ -38,11 +39,13 @@ config LBD
 
 	  The ext4 filesystem requires that this feature be enabled in
 	  order to support filesystems that have the huge_file feature
-	  enabled.    Otherwise, it will refuse to mount any filesystems
-	  that use the huge_file feature, which is enabled by default
-	  by mke2fs.ext4.   The GFS2 filesystem also requires this feature.
+	  enabled.  Otherwise, it will refuse to mount in the read-write
+	  mode any filesystems that use the huge_file feature, which is
+	  enabled by default by mke2fs.ext4.
 
-	  If unsure, say N.
+	  The GFS2 filesystem also requires this feature.
+
+	  If unsure, say Y.
 
 config BLK_DEV_BSG
 	bool "Block layer SG support v4 (EXPERIMENTAL)"
diff --git a/block/as-iosched.c b/block/as-iosched.c
index c48fa670d221..7a12cf6ee1d3 100644
--- a/block/as-iosched.c
+++ b/block/as-iosched.c
@@ -306,8 +306,8 @@ as_choose_req(struct as_data *ad, struct request *rq1, struct request *rq2)
 	data_dir = rq_is_sync(rq1);
 
 	last = ad->last_sector[data_dir];
-	s1 = rq1->sector;
-	s2 = rq2->sector;
+	s1 = blk_rq_pos(rq1);
+	s2 = blk_rq_pos(rq2);
 
 	BUG_ON(data_dir != rq_is_sync(rq2));
 
@@ -566,13 +566,15 @@ static void as_update_iohist(struct as_data *ad, struct as_io_context *aic,
 			as_update_thinktime(ad, aic, thinktime);
 
 			/* Calculate read -> read seek distance */
-			if (aic->last_request_pos < rq->sector)
-				seek_dist = rq->sector - aic->last_request_pos;
+			if (aic->last_request_pos < blk_rq_pos(rq))
+				seek_dist = blk_rq_pos(rq) -
+					    aic->last_request_pos;
 			else
-				seek_dist = aic->last_request_pos - rq->sector;
+				seek_dist = aic->last_request_pos -
+					    blk_rq_pos(rq);
 			as_update_seekdist(ad, aic, seek_dist);
 		}
-		aic->last_request_pos = rq->sector + rq->nr_sectors;
+		aic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
 		set_bit(AS_TASK_IOSTARTED, &aic->state);
 		spin_unlock(&aic->lock);
 	}
@@ -587,7 +589,7 @@ static int as_close_req(struct as_data *ad, struct as_io_context *aic,
 {
 	unsigned long delay;	/* jiffies */
 	sector_t last = ad->last_sector[ad->batch_data_dir];
-	sector_t next = rq->sector;
+	sector_t next = blk_rq_pos(rq);
 	sector_t delta; /* acceptable close offset (in sectors) */
 	sector_t s;
 
@@ -981,7 +983,7 @@ static void as_move_to_dispatch(struct as_data *ad, struct request *rq)
 	 * This has to be set in order to be correctly updated by
 	 * as_find_next_rq
 	 */
-	ad->last_sector[data_dir] = rq->sector + rq->nr_sectors;
+	ad->last_sector[data_dir] = blk_rq_pos(rq) + blk_rq_sectors(rq);
 
 	if (data_dir == BLK_RW_SYNC) {
 		struct io_context *ioc = RQ_IOC(rq);
@@ -1312,12 +1314,8 @@ static void as_merged_requests(struct request_queue *q, struct request *req,
 static void as_work_handler(struct work_struct *work)
 {
 	struct as_data *ad = container_of(work, struct as_data, antic_work);
-	struct request_queue *q = ad->q;
-	unsigned long flags;
 
-	spin_lock_irqsave(q->queue_lock, flags);
-	blk_start_queueing(q);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	blk_run_queue(ad->q);
 }
 
 static int as_may_queue(struct request_queue *q, int rw)
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 20b4111fa050..30022b4e2f63 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -106,10 +106,7 @@ bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
 	 */
 	q->ordseq = 0;
 	rq = q->orig_bar_rq;
-
-	if (__blk_end_request(rq, q->orderr, blk_rq_bytes(rq)))
-		BUG();
-
+	__blk_end_request_all(rq, q->orderr);
 	return true;
 }
 
@@ -166,7 +163,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	 * For an empty barrier, there's no actual BAR request, which
 	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
 	 */
-	if (!rq->hard_nr_sectors) {
+	if (!blk_rq_sectors(rq)) {
 		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
 				QUEUE_ORDERED_DO_POSTFLUSH);
 		/*
@@ -183,7 +180,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	}
 
 	/* stash away the original request */
-	elv_dequeue_request(q, rq);
+	blk_dequeue_request(rq);
 	q->orig_bar_rq = rq;
 	rq = NULL;
 
@@ -221,7 +218,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	} else
 		skip |= QUEUE_ORDSEQ_PREFLUSH;
 
-	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && q->in_flight)
+	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q))
 		rq = NULL;
 	else
 		skip |= QUEUE_ORDSEQ_DRAIN;
@@ -251,10 +248,8 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp)
 			 * Queue ordering not supported.  Terminate
 			 * with prejudice.
 			 */
-			elv_dequeue_request(q, rq);
-			if (__blk_end_request(rq, -EOPNOTSUPP,
-					      blk_rq_bytes(rq)))
-				BUG();
+			blk_dequeue_request(rq);
+			__blk_end_request_all(rq, -EOPNOTSUPP);
 			*rqp = NULL;
 			return false;
 		}
@@ -329,7 +324,7 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 	/*
 	 * The driver must store the error location in ->bi_sector, if
 	 * it supports it. For non-stacked drivers, this should be copied
-	 * from rq->sector.
+	 * from blk_rq_pos(rq).
 	 */
 	if (error_sector)
 		*error_sector = bio->bi_sector;
@@ -393,10 +388,10 @@ int blkdev_issue_discard(struct block_device *bdev,
 
 		bio->bi_sector = sector;
 
-		if (nr_sects > q->max_hw_sectors) {
-			bio->bi_size = q->max_hw_sectors << 9;
-			nr_sects -= q->max_hw_sectors;
-			sector += q->max_hw_sectors;
+		if (nr_sects > queue_max_hw_sectors(q)) {
+			bio->bi_size = queue_max_hw_sectors(q) << 9;
+			nr_sects -= queue_max_hw_sectors(q);
+			sector += queue_max_hw_sectors(q);
 		} else {
 			bio->bi_size = nr_sects << 9;
 			nr_sects = 0;
diff --git a/block/blk-core.c b/block/blk-core.c
index c89883be8737..f6452f692501 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -28,22 +28,14 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/blktrace_api.h>
 #include <linux/fault-inject.h>
-#include <trace/block.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/block.h>
 
 #include "blk.h"
 
-DEFINE_TRACE(block_plug);
-DEFINE_TRACE(block_unplug_io);
-DEFINE_TRACE(block_unplug_timer);
-DEFINE_TRACE(block_getrq);
-DEFINE_TRACE(block_sleeprq);
-DEFINE_TRACE(block_rq_requeue);
-DEFINE_TRACE(block_bio_backmerge);
-DEFINE_TRACE(block_bio_frontmerge);
-DEFINE_TRACE(block_bio_queue);
-DEFINE_TRACE(block_rq_complete);
-DEFINE_TRACE(block_remap);	/* Also used in drivers/md/dm.c */
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
 
 static int __make_request(struct request_queue *q, struct bio *bio);
 
@@ -68,11 +60,11 @@ static void drive_stat_acct(struct request *rq, int new_io)
 	int rw = rq_data_dir(rq);
 	int cpu;
 
-	if (!blk_fs_request(rq) || !blk_do_io_stat(rq))
+	if (!blk_do_io_stat(rq))
 		return;
 
 	cpu = part_stat_lock();
-	part = disk_map_sector_rcu(rq->rq_disk, rq->sector);
+	part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
 
 	if (!new_io)
 		part_stat_inc(cpu, part, merges[rw]);
@@ -127,13 +119,14 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	INIT_LIST_HEAD(&rq->timeout_list);
 	rq->cpu = -1;
 	rq->q = q;
-	rq->sector = rq->hard_sector = (sector_t) -1;
+	rq->__sector = (sector_t) -1;
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->cmd = rq->__cmd;
 	rq->cmd_len = BLK_MAX_CDB;
 	rq->tag = -1;
 	rq->ref_count = 1;
+	rq->start_time = jiffies;
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -184,14 +177,11 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
 		rq->cmd_flags);
 
-	printk(KERN_INFO "  sector %llu, nr/cnr %lu/%u\n",
-						(unsigned long long)rq->sector,
-						rq->nr_sectors,
-						rq->current_nr_sectors);
-	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, data %p, len %u\n",
-						rq->bio, rq->biotail,
-						rq->buffer, rq->data,
-						rq->data_len);
+	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
+	       (unsigned long long)blk_rq_pos(rq),
+	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
+	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, len %u\n",
+	       rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
 
 	if (blk_pc_request(rq)) {
 		printk(KERN_INFO "  cdb: ");
@@ -333,24 +323,6 @@ void blk_unplug(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_unplug);
 
-static void blk_invoke_request_fn(struct request_queue *q)
-{
-	if (unlikely(blk_queue_stopped(q)))
-		return;
-
-	/*
-	 * one level of recursion is ok and is much faster than kicking
-	 * the unplug handling
-	 */
-	if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
-		q->request_fn(q);
-		queue_flag_clear(QUEUE_FLAG_REENTER, q);
-	} else {
-		queue_flag_set(QUEUE_FLAG_PLUGGED, q);
-		kblockd_schedule_work(q, &q->unplug_work);
-	}
-}
-
 /**
  * blk_start_queue - restart a previously stopped queue
  * @q:    The &struct request_queue in question
@@ -365,7 +337,7 @@ void blk_start_queue(struct request_queue *q)
 	WARN_ON(!irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
-	blk_invoke_request_fn(q);
+	__blk_run_queue(q);
 }
 EXPORT_SYMBOL(blk_start_queue);
 
@@ -425,12 +397,23 @@ void __blk_run_queue(struct request_queue *q)
 {
 	blk_remove_plug(q);
 
+	if (unlikely(blk_queue_stopped(q)))
+		return;
+
+	if (elv_queue_empty(q))
+		return;
+
 	/*
 	 * Only recurse once to avoid overrunning the stack, let the unplug
 	 * handling reinvoke the handler shortly if we already got there.
 	 */
-	if (!elv_queue_empty(q))
-		blk_invoke_request_fn(q);
+	if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
+		q->request_fn(q);
+		queue_flag_clear(QUEUE_FLAG_REENTER, q);
+	} else {
+		queue_flag_set(QUEUE_FLAG_PLUGGED, q);
+		kblockd_schedule_work(q, &q->unplug_work);
+	}
 }
 EXPORT_SYMBOL(__blk_run_queue);
 
@@ -440,9 +423,7 @@ EXPORT_SYMBOL(__blk_run_queue);
  *
  * Description:
  *    Invoke request handling on this queue, if it has pending work to do.
- *    May be used to restart queueing when a request has completed. Also
- *    See @blk_start_queueing.
- *
+ *    May be used to restart queueing when a request has completed.
  */
 void blk_run_queue(struct request_queue *q)
 {
@@ -902,26 +883,59 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 EXPORT_SYMBOL(blk_get_request);
 
 /**
- * blk_start_queueing - initiate dispatch of requests to device
- * @q:		request queue to kick into gear
+ * blk_make_request - given a bio, allocate a corresponding struct request.
+ * @q: target request queue
+ * @bio:  The bio describing the memory mappings that will be submitted for IO.
+ *        It may be a chained-bio properly constructed by block/bio layer.
+ * @gfp_mask: gfp flags to be used for memory allocation
  *
- * This is basically a helper to remove the need to know whether a queue
- * is plugged or not if someone just wants to initiate dispatch of requests
- * for this queue. Should be used to start queueing on a device outside
- * of ->request_fn() context. Also see @blk_run_queue.
+ * blk_make_request is the parallel of generic_make_request for BLOCK_PC
+ * type commands. Where the struct request needs to be farther initialized by
+ * the caller. It is passed a &struct bio, which describes the memory info of
+ * the I/O transfer.
  *
- * The queue lock must be held with interrupts disabled.
+ * The caller of blk_make_request must make sure that bi_io_vec
+ * are set to describe the memory buffers. That bio_data_dir() will return
+ * the needed direction of the request. (And all bio's in the passed bio-chain
+ * are properly set accordingly)
+ *
+ * If called under none-sleepable conditions, mapped bio buffers must not
+ * need bouncing, by calling the appropriate masked or flagged allocator,
+ * suitable for the target device. Otherwise the call to blk_queue_bounce will
+ * BUG.
+ *
+ * WARNING: When allocating/cloning a bio-chain, careful consideration should be
+ * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for
+ * anything but the first bio in the chain. Otherwise you risk waiting for IO
+ * completion of a bio that hasn't been submitted yet, thus resulting in a
+ * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
+ * of bio_alloc(), as that avoids the mempool deadlock.
+ * If possible a big IO should be split into smaller parts when allocation
+ * fails. Partial allocation should not be an error, or you risk a live-lock.
  */
-void blk_start_queueing(struct request_queue *q)
+struct request *blk_make_request(struct request_queue *q, struct bio *bio,
+				 gfp_t gfp_mask)
 {
-	if (!blk_queue_plugged(q)) {
-		if (unlikely(blk_queue_stopped(q)))
-			return;
-		q->request_fn(q);
-	} else
-		__generic_unplug_device(q);
+	struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
+
+	if (unlikely(!rq))
+		return ERR_PTR(-ENOMEM);
+
+	for_each_bio(bio) {
+		struct bio *bounce_bio = bio;
+		int ret;
+
+		blk_queue_bounce(q, &bounce_bio);
+		ret = blk_rq_append_bio(q, rq, bounce_bio);
+		if (unlikely(ret)) {
+			blk_put_request(rq);
+			return ERR_PTR(ret);
+		}
+	}
+
+	return rq;
 }
-EXPORT_SYMBOL(blk_start_queueing);
+EXPORT_SYMBOL(blk_make_request);
 
 /**
  * blk_requeue_request - put a request back on queue
@@ -942,6 +956,8 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 	if (blk_rq_tagged(rq))
 		blk_queue_end_tag(q, rq);
 
+	BUG_ON(blk_queued_rq(rq));
+
 	elv_requeue_request(q, rq);
 }
 EXPORT_SYMBOL(blk_requeue_request);
@@ -977,7 +993,6 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 	 * barrier
 	 */
 	rq->cmd_type = REQ_TYPE_SPECIAL;
-	rq->cmd_flags |= REQ_SOFTBARRIER;
 
 	rq->special = data;
 
@@ -991,7 +1006,7 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 
 	drive_stat_acct(rq, 1);
 	__elv_add_request(q, rq, where, 0);
-	blk_start_queueing(q);
+	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_insert_request);
@@ -1113,16 +1128,13 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	if (bio_failfast_driver(bio))
 		req->cmd_flags |= REQ_FAILFAST_DRIVER;
 
-	/*
-	 * REQ_BARRIER implies no merging, but lets make it explicit
-	 */
 	if (unlikely(bio_discard(bio))) {
 		req->cmd_flags |= REQ_DISCARD;
 		if (bio_barrier(bio))
 			req->cmd_flags |= REQ_SOFTBARRIER;
 		req->q->prepare_discard_fn(req->q, req);
 	} else if (unlikely(bio_barrier(bio)))
-		req->cmd_flags |= (REQ_HARDBARRIER | REQ_NOMERGE);
+		req->cmd_flags |= REQ_HARDBARRIER;
 
 	if (bio_sync(bio))
 		req->cmd_flags |= REQ_RW_SYNC;
@@ -1132,9 +1144,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 		req->cmd_flags |= REQ_NOIDLE;
 
 	req->errors = 0;
-	req->hard_sector = req->sector = bio->bi_sector;
+	req->__sector = bio->bi_sector;
 	req->ioprio = bio_prio(bio);
-	req->start_time = jiffies;
 	blk_rq_bio_prep(req->q, req, bio);
 }
 
@@ -1150,14 +1161,13 @@ static inline bool queue_should_plug(struct request_queue *q)
 static int __make_request(struct request_queue *q, struct bio *bio)
 {
 	struct request *req;
-	int el_ret, nr_sectors;
+	int el_ret;
+	unsigned int bytes = bio->bi_size;
 	const unsigned short prio = bio_prio(bio);
 	const int sync = bio_sync(bio);
 	const int unplug = bio_unplug(bio);
 	int rw_flags;
 
-	nr_sectors = bio_sectors(bio);
-
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
@@ -1182,7 +1192,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 		req->biotail->bi_next = bio;
 		req->biotail = bio;
-		req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+		req->__data_len += bytes;
 		req->ioprio = ioprio_best(req->ioprio, prio);
 		if (!blk_rq_cpu_valid(req))
 			req->cpu = bio->bi_comp_cpu;
@@ -1208,10 +1218,8 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 		 * not touch req->buffer either...
 		 */
 		req->buffer = bio_data(bio);
-		req->current_nr_sectors = bio_cur_sectors(bio);
-		req->hard_cur_sectors = req->current_nr_sectors;
-		req->sector = req->hard_sector = bio->bi_sector;
-		req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+		req->__sector = bio->bi_sector;
+		req->__data_len += bytes;
 		req->ioprio = ioprio_best(req->ioprio, prio);
 		if (!blk_rq_cpu_valid(req))
 			req->cpu = bio->bi_comp_cpu;
@@ -1277,7 +1285,7 @@ static inline void blk_partition_remap(struct bio *bio)
 		bio->bi_bdev = bdev->bd_contains;
 
 		trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
-				    bdev->bd_dev, bio->bi_sector,
+				    bdev->bd_dev,
 				    bio->bi_sector - p->start_sect);
 	}
 }
@@ -1422,11 +1430,11 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
-		if (unlikely(nr_sectors > q->max_hw_sectors)) {
+		if (unlikely(nr_sectors > queue_max_hw_sectors(q))) {
 			printk(KERN_ERR "bio too big device %s (%u > %u)\n",
-				bdevname(bio->bi_bdev, b),
-				bio_sectors(bio),
-				q->max_hw_sectors);
+			       bdevname(bio->bi_bdev, b),
+			       bio_sectors(bio),
+			       queue_max_hw_sectors(q));
 			goto end_io;
 		}
 
@@ -1446,8 +1454,7 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 
 		if (old_sector != -1)
-			trace_block_remap(q, bio, old_dev, bio->bi_sector,
-					    old_sector);
+			trace_block_remap(q, bio, old_dev, old_sector);
 
 		trace_block_bio_queue(q, bio);
 
@@ -1593,8 +1600,8 @@ EXPORT_SYMBOL(submit_bio);
  */
 int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 {
-	if (rq->nr_sectors > q->max_sectors ||
-	    rq->data_len > q->max_hw_sectors << 9) {
+	if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
+	    blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
 	}
@@ -1606,8 +1613,8 @@ int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 	 * limitation.
 	 */
 	blk_recalc_rq_segments(rq);
-	if (rq->nr_phys_segments > q->max_phys_segments ||
-	    rq->nr_phys_segments > q->max_hw_segments) {
+	if (rq->nr_phys_segments > queue_max_phys_segments(q) ||
+	    rq->nr_phys_segments > queue_max_hw_segments(q)) {
 		printk(KERN_ERR "%s: over max segments limit.\n", __func__);
 		return -EIO;
 	}
@@ -1651,40 +1658,15 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
-/**
- * blkdev_dequeue_request - dequeue request and start timeout timer
- * @req: request to dequeue
- *
- * Dequeue @req and start timeout timer on it.  This hands off the
- * request to the driver.
- *
- * Block internal functions which don't want to start timer should
- * call elv_dequeue_request().
- */
-void blkdev_dequeue_request(struct request *req)
-{
-	elv_dequeue_request(req->q, req);
-
-	/*
-	 * We are now handing the request to the hardware, add the
-	 * timeout handler.
-	 */
-	blk_add_timer(req);
-}
-EXPORT_SYMBOL(blkdev_dequeue_request);
-
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
-	if (!blk_do_io_stat(req))
-		return;
-
-	if (blk_fs_request(req)) {
+	if (blk_do_io_stat(req)) {
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
 		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
 		part_stat_unlock();
 	}
@@ -1692,22 +1674,19 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 
 static void blk_account_io_done(struct request *req)
 {
-	if (!blk_do_io_stat(req))
-		return;
-
 	/*
 	 * Account IO completion.  bar_rq isn't accounted as a normal
 	 * IO on queueing nor completion.  Accounting the containing
 	 * request is enough.
 	 */
-	if (blk_fs_request(req) && req != &req->q->bar_rq) {
+	if (blk_do_io_stat(req) && req != &req->q->bar_rq) {
 		unsigned long duration = jiffies - req->start_time;
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
 
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
@@ -1719,38 +1698,226 @@ static void blk_account_io_done(struct request *req)
 }
 
 /**
- * __end_that_request_first - end I/O on a request
- * @req:      the request being processed
- * @error:    %0 for success, < %0 for error
- * @nr_bytes: number of bytes to complete
+ * blk_peek_request - peek at the top of a request queue
+ * @q: request queue to peek at
  *
  * Description:
- *     Ends I/O on a number of bytes attached to @req, and sets it up
- *     for the next range of segments (if any) in the cluster.
+ *     Return the request at the top of @q.  The returned request
+ *     should be started using blk_start_request() before LLD starts
+ *     processing it.
  *
  * Return:
- *     %0 - we are done with this request, call end_that_request_last()
- *     %1 - still buffers pending for this request
+ *     Pointer to the request at the top of @q if available.  Null
+ *     otherwise.
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+struct request *blk_peek_request(struct request_queue *q)
+{
+	struct request *rq;
+	int ret;
+
+	while ((rq = __elv_next_request(q)) != NULL) {
+		if (!(rq->cmd_flags & REQ_STARTED)) {
+			/*
+			 * This is the first time the device driver
+			 * sees this request (possibly after
+			 * requeueing).  Notify IO scheduler.
+			 */
+			if (blk_sorted_rq(rq))
+				elv_activate_rq(q, rq);
+
+			/*
+			 * just mark as started even if we don't start
+			 * it, a request that has been delayed should
+			 * not be passed by new incoming requests
+			 */
+			rq->cmd_flags |= REQ_STARTED;
+			trace_block_rq_issue(q, rq);
+		}
+
+		if (!q->boundary_rq || q->boundary_rq == rq) {
+			q->end_sector = rq_end_sector(rq);
+			q->boundary_rq = NULL;
+		}
+
+		if (rq->cmd_flags & REQ_DONTPREP)
+			break;
+
+		if (q->dma_drain_size && blk_rq_bytes(rq)) {
+			/*
+			 * make sure space for the drain appears we
+			 * know we can do this because max_hw_segments
+			 * has been adjusted to be one fewer than the
+			 * device can handle
+			 */
+			rq->nr_phys_segments++;
+		}
+
+		if (!q->prep_rq_fn)
+			break;
+
+		ret = q->prep_rq_fn(q, rq);
+		if (ret == BLKPREP_OK) {
+			break;
+		} else if (ret == BLKPREP_DEFER) {
+			/*
+			 * the request may have been (partially) prepped.
+			 * we need to keep this request in the front to
+			 * avoid resource deadlock.  REQ_STARTED will
+			 * prevent other fs requests from passing this one.
+			 */
+			if (q->dma_drain_size && blk_rq_bytes(rq) &&
+			    !(rq->cmd_flags & REQ_DONTPREP)) {
+				/*
+				 * remove the space for the drain we added
+				 * so that we don't add it again
+				 */
+				--rq->nr_phys_segments;
+			}
+
+			rq = NULL;
+			break;
+		} else if (ret == BLKPREP_KILL) {
+			rq->cmd_flags |= REQ_QUIET;
+			/*
+			 * Mark this request as started so we don't trigger
+			 * any debug logic in the end I/O path.
+			 */
+			blk_start_request(rq);
+			__blk_end_request_all(rq, -EIO);
+		} else {
+			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
+			break;
+		}
+	}
+
+	return rq;
+}
+EXPORT_SYMBOL(blk_peek_request);
+
+void blk_dequeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	BUG_ON(list_empty(&rq->queuelist));
+	BUG_ON(ELV_ON_HASH(rq));
+
+	list_del_init(&rq->queuelist);
+
+	/*
+	 * the time frame between a request being removed from the lists
+	 * and to it is freed is accounted as io that is in progress at
+	 * the driver side.
+	 */
+	if (blk_account_rq(rq))
+		q->in_flight[rq_is_sync(rq)]++;
+}
+
+/**
+ * blk_start_request - start request processing on the driver
+ * @req: request to dequeue
+ *
+ * Description:
+ *     Dequeue @req and start timeout timer on it.  This hands off the
+ *     request to the driver.
+ *
+ *     Block internal functions which don't want to start timer should
+ *     call blk_dequeue_request().
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+void blk_start_request(struct request *req)
+{
+	blk_dequeue_request(req);
+
+	/*
+	 * We are now handing the request to the hardware, initialize
+	 * resid_len to full count and add the timeout handler.
+	 */
+	req->resid_len = blk_rq_bytes(req);
+	if (unlikely(blk_bidi_rq(req)))
+		req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
+
+	blk_add_timer(req);
+}
+EXPORT_SYMBOL(blk_start_request);
+
+/**
+ * blk_fetch_request - fetch a request from a request queue
+ * @q: request queue to fetch a request from
+ *
+ * Description:
+ *     Return the request at the top of @q.  The request is started on
+ *     return and LLD can start processing it immediately.
+ *
+ * Return:
+ *     Pointer to the request at the top of @q if available.  Null
+ *     otherwise.
+ *
+ * Context:
+ *     queue_lock must be held.
+ */
+struct request *blk_fetch_request(struct request_queue *q)
+{
+	struct request *rq;
+
+	rq = blk_peek_request(q);
+	if (rq)
+		blk_start_request(rq);
+	return rq;
+}
+EXPORT_SYMBOL(blk_fetch_request);
+
+/**
+ * blk_update_request - Special helper function for request stacking drivers
+ * @req:      the request being processed
+ * @error:    %0 for success, < %0 for error
+ * @nr_bytes: number of bytes to complete @req
+ *
+ * Description:
+ *     Ends I/O on a number of bytes attached to @req, but doesn't complete
+ *     the request structure even if @req doesn't have leftover.
+ *     If @req has leftover, sets it up for the next range of segments.
+ *
+ *     This special helper function is only for request stacking drivers
+ *     (e.g. request-based dm) so that they can handle partial completion.
+ *     Actual device drivers should use blk_end_request instead.
+ *
+ *     Passing the result of blk_rq_bytes() as @nr_bytes guarantees
+ *     %false return from this function.
+ *
+ * Return:
+ *     %false - this request doesn't have any more data
+ *     %true  - this request has more data
  **/
-static int __end_that_request_first(struct request *req, int error,
-				    int nr_bytes)
+bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 {
 	int total_bytes, bio_nbytes, next_idx = 0;
 	struct bio *bio;
 
+	if (!req->bio)
+		return false;
+
 	trace_block_rq_complete(req->q, req);
 
 	/*
-	 * for a REQ_TYPE_BLOCK_PC request, we want to carry any eventual
-	 * sense key with us all the way through
+	 * For fs requests, rq is just carrier of independent bio's
+	 * and each partial completion should be handled separately.
+	 * Reset per-request error on each partial completion.
+	 *
+	 * TODO: tj: This is too subtle.  It would be better to let
+	 * low level drivers do what they see fit.
 	 */
-	if (!blk_pc_request(req))
+	if (blk_fs_request(req))
 		req->errors = 0;
 
 	if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) {
 		printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n",
 				req->rq_disk ? req->rq_disk->disk_name : "?",
-				(unsigned long long)req->sector);
+				(unsigned long long)blk_rq_pos(req));
 	}
 
 	blk_account_io_completion(req, nr_bytes);
@@ -1810,8 +1977,15 @@ static int __end_that_request_first(struct request *req, int error,
 	/*
 	 * completely done
 	 */
-	if (!req->bio)
-		return 0;
+	if (!req->bio) {
+		/*
+		 * Reset counters so that the request stacking driver
+		 * can find how many bytes remain in the request
+		 * later.
+		 */
+		req->__data_len = 0;
+		return false;
+	}
 
 	/*
 	 * if the request wasn't completed, update state
@@ -1823,21 +1997,55 @@ static int __end_that_request_first(struct request *req, int error,
 		bio_iovec(bio)->bv_len -= nr_bytes;
 	}
 
-	blk_recalc_rq_sectors(req, total_bytes >> 9);
+	req->__data_len -= total_bytes;
+	req->buffer = bio_data(req->bio);
+
+	/* update sector only for requests with clear definition of sector */
+	if (blk_fs_request(req) || blk_discard_rq(req))
+		req->__sector += total_bytes >> 9;
+
+	/*
+	 * If total number of sectors is less than the first segment
+	 * size, something has gone terribly wrong.
+	 */
+	if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
+		printk(KERN_ERR "blk: request botched\n");
+		req->__data_len = blk_rq_cur_bytes(req);
+	}
+
+	/* recalculate the number of segments */
 	blk_recalc_rq_segments(req);
-	return 1;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(blk_update_request);
+
+static bool blk_update_bidi_request(struct request *rq, int error,
+				    unsigned int nr_bytes,
+				    unsigned int bidi_bytes)
+{
+	if (blk_update_request(rq, error, nr_bytes))
+		return true;
+
+	/* Bidi request must be completed as a whole */
+	if (unlikely(blk_bidi_rq(rq)) &&
+	    blk_update_request(rq->next_rq, error, bidi_bytes))
+		return true;
+
+	add_disk_randomness(rq->rq_disk);
+
+	return false;
 }
 
 /*
  * queue lock must be held
  */
-static void end_that_request_last(struct request *req, int error)
+static void blk_finish_request(struct request *req, int error)
 {
 	if (blk_rq_tagged(req))
 		blk_queue_end_tag(req->q, req);
 
-	if (blk_queued_rq(req))
-		elv_dequeue_request(req->q, req);
+	BUG_ON(blk_queued_rq(req));
 
 	if (unlikely(laptop_mode) && blk_fs_request(req))
 		laptop_io_completion();
@@ -1857,117 +2065,62 @@ static void end_that_request_last(struct request *req, int error)
 }
 
 /**
- * blk_rq_bytes - Returns bytes left to complete in the entire request
- * @rq: the request being processed
- **/
-unsigned int blk_rq_bytes(struct request *rq)
-{
-	if (blk_fs_request(rq))
-		return rq->hard_nr_sectors << 9;
-
-	return rq->data_len;
-}
-EXPORT_SYMBOL_GPL(blk_rq_bytes);
-
-/**
- * blk_rq_cur_bytes - Returns bytes left to complete in the current segment
- * @rq: the request being processed
- **/
-unsigned int blk_rq_cur_bytes(struct request *rq)
-{
-	if (blk_fs_request(rq))
-		return rq->current_nr_sectors << 9;
-
-	if (rq->bio)
-		return rq->bio->bi_size;
-
-	return rq->data_len;
-}
-EXPORT_SYMBOL_GPL(blk_rq_cur_bytes);
-
-/**
- * end_request - end I/O on the current segment of the request
- * @req:	the request being processed
- * @uptodate:	error value or %0/%1 uptodate flag
- *
- * Description:
- *     Ends I/O on the current segment of a request. If that is the only
- *     remaining segment, the request is also completed and freed.
- *
- *     This is a remnant of how older block drivers handled I/O completions.
- *     Modern drivers typically end I/O on the full request in one go, unless
- *     they have a residual value to account for. For that case this function
- *     isn't really useful, unless the residual just happens to be the
- *     full current segment. In other words, don't use this function in new
- *     code. Use blk_end_request() or __blk_end_request() to end a request.
- **/
-void end_request(struct request *req, int uptodate)
-{
-	int error = 0;
-
-	if (uptodate <= 0)
-		error = uptodate ? uptodate : -EIO;
-
-	__blk_end_request(req, error, req->hard_cur_sectors << 9);
-}
-EXPORT_SYMBOL(end_request);
-
-static int end_that_request_data(struct request *rq, int error,
-				 unsigned int nr_bytes, unsigned int bidi_bytes)
-{
-	if (rq->bio) {
-		if (__end_that_request_first(rq, error, nr_bytes))
-			return 1;
-
-		/* Bidi request must be completed as a whole */
-		if (blk_bidi_rq(rq) &&
-		    __end_that_request_first(rq->next_rq, error, bidi_bytes))
-			return 1;
-	}
-
-	return 0;
-}
-
-/**
- * blk_end_io - Generic end_io function to complete a request.
- * @rq:           the request being processed
- * @error:        %0 for success, < %0 for error
- * @nr_bytes:     number of bytes to complete @rq
- * @bidi_bytes:   number of bytes to complete @rq->next_rq
- * @drv_callback: function called between completion of bios in the request
- *                and completion of the request.
- *                If the callback returns non %0, this helper returns without
- *                completion of the request.
+ * blk_end_bidi_request - Complete a bidi request
+ * @rq:         the request to complete
+ * @error:      %0 for success, < %0 for error
+ * @nr_bytes:   number of bytes to complete @rq
+ * @bidi_bytes: number of bytes to complete @rq->next_rq
  *
  * Description:
  *     Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
- *     If @rq has leftover, sets it up for the next range of segments.
+ *     Drivers that supports bidi can safely call this member for any
+ *     type of request, bidi or uni.  In the later case @bidi_bytes is
+ *     just ignored.
  *
  * Return:
- *     %0 - we are done with this request
- *     %1 - this request is not freed yet, it still has pending buffers.
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
  **/
-static int blk_end_io(struct request *rq, int error, unsigned int nr_bytes,
-		      unsigned int bidi_bytes,
-		      int (drv_callback)(struct request *))
+static bool blk_end_bidi_request(struct request *rq, int error,
+				 unsigned int nr_bytes, unsigned int bidi_bytes)
 {
 	struct request_queue *q = rq->q;
-	unsigned long flags = 0UL;
+	unsigned long flags;
 
-	if (end_that_request_data(rq, error, nr_bytes, bidi_bytes))
-		return 1;
-
-	/* Special feature for tricky drivers */
-	if (drv_callback && drv_callback(rq))
-		return 1;
-
-	add_disk_randomness(rq->rq_disk);
+	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
+		return true;
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	end_that_request_last(rq, error);
+	blk_finish_request(rq, error);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
-	return 0;
+	return false;
+}
+
+/**
+ * __blk_end_bidi_request - Complete a bidi request with queue lock held
+ * @rq:         the request to complete
+ * @error:      %0 for success, < %0 for error
+ * @nr_bytes:   number of bytes to complete @rq
+ * @bidi_bytes: number of bytes to complete @rq->next_rq
+ *
+ * Description:
+ *     Identical to blk_end_bidi_request() except that queue lock is
+ *     assumed to be locked on entry and remains so on return.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ **/
+static bool __blk_end_bidi_request(struct request *rq, int error,
+				   unsigned int nr_bytes, unsigned int bidi_bytes)
+{
+	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
+		return true;
+
+	blk_finish_request(rq, error);
+
+	return false;
 }
 
 /**
@@ -1981,15 +2134,54 @@ static int blk_end_io(struct request *rq, int error, unsigned int nr_bytes,
  *     If @rq has leftover, sets it up for the next range of segments.
  *
  * Return:
- *     %0 - we are done with this request
- *     %1 - still buffers pending for this request
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
  **/
-int blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
 {
-	return blk_end_io(rq, error, nr_bytes, 0, NULL);
+	return blk_end_bidi_request(rq, error, nr_bytes, 0);
 }
 EXPORT_SYMBOL_GPL(blk_end_request);
 
+/**
+ * blk_end_request_all - Helper function for drives to finish the request.
+ * @rq: the request to finish
+ * @error: %0 for success, < %0 for error
+ *
+ * Description:
+ *     Completely finish @rq.
+ */
+void blk_end_request_all(struct request *rq, int error)
+{
+	bool pending;
+	unsigned int bidi_bytes = 0;
+
+	if (unlikely(blk_bidi_rq(rq)))
+		bidi_bytes = blk_rq_bytes(rq->next_rq);
+
+	pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
+	BUG_ON(pending);
+}
+EXPORT_SYMBOL_GPL(blk_end_request_all);
+
+/**
+ * blk_end_request_cur - Helper function to finish the current request chunk.
+ * @rq: the request to finish the current chunk for
+ * @error: %0 for success, < %0 for error
+ *
+ * Description:
+ *     Complete the current consecutively mapped chunk from @rq.
+ *
+ * Return:
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool blk_end_request_cur(struct request *rq, int error)
+{
+	return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(blk_end_request_cur);
+
 /**
  * __blk_end_request - Helper function for drivers to complete the request.
  * @rq:       the request being processed
@@ -2000,105 +2192,54 @@ EXPORT_SYMBOL_GPL(blk_end_request);
  *     Must be called with queue lock held unlike blk_end_request().
  *
  * Return:
- *     %0 - we are done with this request
- *     %1 - still buffers pending for this request
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
  **/
-int __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
 {
-	if (rq->bio && __end_that_request_first(rq, error, nr_bytes))
-		return 1;
-
-	add_disk_randomness(rq->rq_disk);
-
-	end_that_request_last(rq, error);
-
-	return 0;
+	return __blk_end_bidi_request(rq, error, nr_bytes, 0);
 }
 EXPORT_SYMBOL_GPL(__blk_end_request);
 
 /**
- * blk_end_bidi_request - Helper function for drivers to complete bidi request.
- * @rq:         the bidi request being processed
- * @error:      %0 for success, < %0 for error
- * @nr_bytes:   number of bytes to complete @rq
- * @bidi_bytes: number of bytes to complete @rq->next_rq
+ * __blk_end_request_all - Helper function for drives to finish the request.
+ * @rq: the request to finish
+ * @error: %0 for success, < %0 for error
  *
  * Description:
- *     Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
- *
- * Return:
- *     %0 - we are done with this request
- *     %1 - still buffers pending for this request
- **/
-int blk_end_bidi_request(struct request *rq, int error, unsigned int nr_bytes,
-			 unsigned int bidi_bytes)
-{
-	return blk_end_io(rq, error, nr_bytes, bidi_bytes, NULL);
-}
-EXPORT_SYMBOL_GPL(blk_end_bidi_request);
-
-/**
- * blk_update_request - Special helper function for request stacking drivers
- * @rq:           the request being processed
- * @error:        %0 for success, < %0 for error
- * @nr_bytes:     number of bytes to complete @rq
- *
- * Description:
- *     Ends I/O on a number of bytes attached to @rq, but doesn't complete
- *     the request structure even if @rq doesn't have leftover.
- *     If @rq has leftover, sets it up for the next range of segments.
- *
- *     This special helper function is only for request stacking drivers
- *     (e.g. request-based dm) so that they can handle partial completion.
- *     Actual device drivers should use blk_end_request instead.
+ *     Completely finish @rq.  Must be called with queue lock held.
  */
-void blk_update_request(struct request *rq, int error, unsigned int nr_bytes)
+void __blk_end_request_all(struct request *rq, int error)
 {
-	if (!end_that_request_data(rq, error, nr_bytes, 0)) {
-		/*
-		 * These members are not updated in end_that_request_data()
-		 * when all bios are completed.
-		 * Update them so that the request stacking driver can find
-		 * how many bytes remain in the request later.
-		 */
-		rq->nr_sectors = rq->hard_nr_sectors = 0;
-		rq->current_nr_sectors = rq->hard_cur_sectors = 0;
-	}
+	bool pending;
+	unsigned int bidi_bytes = 0;
+
+	if (unlikely(blk_bidi_rq(rq)))
+		bidi_bytes = blk_rq_bytes(rq->next_rq);
+
+	pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
+	BUG_ON(pending);
 }
-EXPORT_SYMBOL_GPL(blk_update_request);
+EXPORT_SYMBOL_GPL(__blk_end_request_all);
 
 /**
- * blk_end_request_callback - Special helper function for tricky drivers
- * @rq:           the request being processed
- * @error:        %0 for success, < %0 for error
- * @nr_bytes:     number of bytes to complete
- * @drv_callback: function called between completion of bios in the request
- *                and completion of the request.
- *                If the callback returns non %0, this helper returns without
- *                completion of the request.
+ * __blk_end_request_cur - Helper function to finish the current request chunk.
+ * @rq: the request to finish the current chunk for
+ * @error: %0 for success, < %0 for error
  *
  * Description:
- *     Ends I/O on a number of bytes attached to @rq.
- *     If @rq has leftover, sets it up for the next range of segments.
- *
- *     This special helper function is used only for existing tricky drivers.
- *     (e.g. cdrom_newpc_intr() of ide-cd)
- *     This interface will be removed when such drivers are rewritten.
- *     Don't use this interface in other places anymore.
+ *     Complete the current consecutively mapped chunk from @rq.  Must
+ *     be called with queue lock held.
  *
  * Return:
- *     %0 - we are done with this request
- *     %1 - this request is not freed yet.
- *          this request still has pending buffers or
- *          the driver doesn't want to finish this request yet.
- **/
-int blk_end_request_callback(struct request *rq, int error,
-			     unsigned int nr_bytes,
-			     int (drv_callback)(struct request *))
+ *     %false - we are done with this request
+ *     %true  - still buffers pending for this request
+ */
+bool __blk_end_request_cur(struct request *rq, int error)
 {
-	return blk_end_io(rq, error, nr_bytes, 0, drv_callback);
+	return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
 }
-EXPORT_SYMBOL_GPL(blk_end_request_callback);
+EXPORT_SYMBOL_GPL(__blk_end_request_cur);
 
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
@@ -2111,11 +2252,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
 		rq->buffer = bio_data(bio);
 	}
-	rq->current_nr_sectors = bio_cur_sectors(bio);
-	rq->hard_cur_sectors = rq->current_nr_sectors;
-	rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio);
-	rq->data_len = bio->bi_size;
-
+	rq->__data_len = bio->bi_size;
 	rq->bio = rq->biotail = bio;
 
 	if (bio->bi_bdev)
@@ -2150,6 +2287,106 @@ int blk_lld_busy(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_lld_busy);
 
+/**
+ * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
+ * @rq: the clone request to be cleaned up
+ *
+ * Description:
+ *     Free all bios in @rq for a cloned request.
+ */
+void blk_rq_unprep_clone(struct request *rq)
+{
+	struct bio *bio;
+
+	while ((bio = rq->bio) != NULL) {
+		rq->bio = bio->bi_next;
+
+		bio_put(bio);
+	}
+}
+EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
+
+/*
+ * Copy attributes of the original request to the clone request.
+ * The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied.
+ */
+static void __blk_rq_prep_clone(struct request *dst, struct request *src)
+{
+	dst->cpu = src->cpu;
+	dst->cmd_flags = (rq_data_dir(src) | REQ_NOMERGE);
+	dst->cmd_type = src->cmd_type;
+	dst->__sector = blk_rq_pos(src);
+	dst->__data_len = blk_rq_bytes(src);
+	dst->nr_phys_segments = src->nr_phys_segments;
+	dst->ioprio = src->ioprio;
+	dst->extra_len = src->extra_len;
+}
+
+/**
+ * blk_rq_prep_clone - Helper function to setup clone request
+ * @rq: the request to be setup
+ * @rq_src: original request to be cloned
+ * @bs: bio_set that bios for clone are allocated from
+ * @gfp_mask: memory allocation mask for bio
+ * @bio_ctr: setup function to be called for each clone bio.
+ *           Returns %0 for success, non %0 for failure.
+ * @data: private data to be passed to @bio_ctr
+ *
+ * Description:
+ *     Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
+ *     The actual data parts of @rq_src (e.g. ->cmd, ->buffer, ->sense)
+ *     are not copied, and copying such parts is the caller's responsibility.
+ *     Also, pages which the original bios are pointing to are not copied
+ *     and the cloned bios just point same pages.
+ *     So cloned bios must be completed before original bios, which means
+ *     the caller must complete @rq before @rq_src.
+ */
+int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
+		      struct bio_set *bs, gfp_t gfp_mask,
+		      int (*bio_ctr)(struct bio *, struct bio *, void *),
+		      void *data)
+{
+	struct bio *bio, *bio_src;
+
+	if (!bs)
+		bs = fs_bio_set;
+
+	blk_rq_init(NULL, rq);
+
+	__rq_for_each_bio(bio_src, rq_src) {
+		bio = bio_alloc_bioset(gfp_mask, bio_src->bi_max_vecs, bs);
+		if (!bio)
+			goto free_and_out;
+
+		__bio_clone(bio, bio_src);
+
+		if (bio_integrity(bio_src) &&
+		    bio_integrity_clone(bio, bio_src, gfp_mask))
+			goto free_and_out;
+
+		if (bio_ctr && bio_ctr(bio, bio_src, data))
+			goto free_and_out;
+
+		if (rq->bio) {
+			rq->biotail->bi_next = bio;
+			rq->biotail = bio;
+		} else
+			rq->bio = rq->biotail = bio;
+	}
+
+	__blk_rq_prep_clone(rq, rq_src);
+
+	return 0;
+
+free_and_out:
+	if (bio)
+		bio_free(bio, bs);
+	blk_rq_unprep_clone(rq);
+
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
+
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
 {
 	return queue_work(kblockd_workqueue, work);
@@ -2158,6 +2395,9 @@ EXPORT_SYMBOL(kblockd_schedule_work);
 
 int __init blk_dev_init(void)
 {
+	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
+			sizeof(((struct request *)0)->cmd_flags));
+
 	kblockd_workqueue = create_workqueue("kblockd");
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 6af716d1e54e..49557e91f0da 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -51,7 +51,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
 
 	rq->rq_disk = bd_disk;
-	rq->cmd_flags |= REQ_NOMERGE;
 	rq->end_io = done;
 	WARN_ON(irqs_disabled());
 	spin_lock_irq(q->queue_lock);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 91fa8e06b6a5..73e28d355688 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -340,7 +340,7 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		kobject_uevent(&bi->kobj, KOBJ_ADD);
 
 		bi->flags |= INTEGRITY_FLAG_READ | INTEGRITY_FLAG_WRITE;
-		bi->sector_size = disk->queue->hardsect_size;
+		bi->sector_size = queue_logical_block_size(disk->queue);
 		disk->integrity = bi;
 	} else
 		bi = disk->integrity;
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 012f065ac8e2..d4ed6000147d 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -35,9 +35,9 @@ int put_io_context(struct io_context *ioc)
 	if (ioc == NULL)
 		return 1;
 
-	BUG_ON(atomic_read(&ioc->refcount) == 0);
+	BUG_ON(atomic_long_read(&ioc->refcount) == 0);
 
-	if (atomic_dec_and_test(&ioc->refcount)) {
+	if (atomic_long_dec_and_test(&ioc->refcount)) {
 		rcu_read_lock();
 		if (ioc->aic && ioc->aic->dtor)
 			ioc->aic->dtor(ioc->aic);
@@ -90,7 +90,7 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 
 	ret = kmem_cache_alloc_node(iocontext_cachep, gfp_flags, node);
 	if (ret) {
-		atomic_set(&ret->refcount, 1);
+		atomic_long_set(&ret->refcount, 1);
 		atomic_set(&ret->nr_tasks, 1);
 		spin_lock_init(&ret->lock);
 		ret->ioprio_changed = 0;
@@ -151,7 +151,7 @@ struct io_context *get_io_context(gfp_t gfp_flags, int node)
 		ret = current_io_context(gfp_flags, node);
 		if (unlikely(!ret))
 			break;
-	} while (!atomic_inc_not_zero(&ret->refcount));
+	} while (!atomic_long_inc_not_zero(&ret->refcount));
 
 	return ret;
 }
@@ -163,8 +163,8 @@ void copy_io_context(struct io_context **pdst, struct io_context **psrc)
 	struct io_context *dst = *pdst;
 
 	if (src) {
-		BUG_ON(atomic_read(&src->refcount) == 0);
-		atomic_inc(&src->refcount);
+		BUG_ON(atomic_long_read(&src->refcount) == 0);
+		atomic_long_inc(&src->refcount);
 		put_io_context(dst);
 		*pdst = src;
 	}
diff --git a/block/blk-map.c b/block/blk-map.c
index f103729b462f..9083cf0180cc 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -20,11 +20,10 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
 
-		rq->data_len += bio->bi_size;
+		rq->__data_len += bio->bi_size;
 	}
 	return 0;
 }
-EXPORT_SYMBOL(blk_rq_append_bio);
 
 static int __blk_rq_unmap_user(struct bio *bio)
 {
@@ -116,7 +115,7 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 	struct bio *bio = NULL;
 	int ret;
 
-	if (len > (q->max_hw_sectors << 9))
+	if (len > (queue_max_hw_sectors(q) << 9))
 		return -EINVAL;
 	if (!len)
 		return -EINVAL;
@@ -156,7 +155,7 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 	if (!bio_flagged(bio, BIO_USER_MAPPED))
 		rq->cmd_flags |= REQ_COPY_USER;
 
-	rq->buffer = rq->data = NULL;
+	rq->buffer = NULL;
 	return 0;
 unmap_rq:
 	blk_rq_unmap_user(bio);
@@ -235,7 +234,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	blk_queue_bounce(q, &bio);
 	bio_get(bio);
 	blk_rq_bio_prep(q, rq, bio);
-	rq->buffer = rq->data = NULL;
+	rq->buffer = NULL;
 	return 0;
 }
 EXPORT_SYMBOL(blk_rq_map_user_iov);
@@ -282,7 +281,8 @@ EXPORT_SYMBOL(blk_rq_unmap_user);
  *
  * Description:
  *    Data will be mapped directly if possible. Otherwise a bounce
- *    buffer is used.
+ *    buffer is used. Can be called multple times to append multple
+ *    buffers.
  */
 int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		    unsigned int len, gfp_t gfp_mask)
@@ -290,8 +290,9 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	int reading = rq_data_dir(rq) == READ;
 	int do_copy = 0;
 	struct bio *bio;
+	int ret;
 
-	if (len > (q->max_hw_sectors << 9))
+	if (len > (queue_max_hw_sectors(q) << 9))
 		return -EINVAL;
 	if (!len || !kbuf)
 		return -EINVAL;
@@ -311,9 +312,15 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (do_copy)
 		rq->cmd_flags |= REQ_COPY_USER;
 
-	blk_rq_bio_prep(q, rq, bio);
+	ret = blk_rq_append_bio(q, rq, bio);
+	if (unlikely(ret)) {
+		/* request is too big */
+		bio_put(bio);
+		return ret;
+	}
+
 	blk_queue_bounce(q, &rq->bio);
-	rq->buffer = rq->data = NULL;
+	rq->buffer = NULL;
 	return 0;
 }
 EXPORT_SYMBOL(blk_rq_map_kern);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 23d2a6fe34a3..39ce64432ba6 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,35 +9,6 @@
 
 #include "blk.h"
 
-void blk_recalc_rq_sectors(struct request *rq, int nsect)
-{
-	if (blk_fs_request(rq) || blk_discard_rq(rq)) {
-		rq->hard_sector += nsect;
-		rq->hard_nr_sectors -= nsect;
-
-		/*
-		 * Move the I/O submission pointers ahead if required.
-		 */
-		if ((rq->nr_sectors >= rq->hard_nr_sectors) &&
-		    (rq->sector <= rq->hard_sector)) {
-			rq->sector = rq->hard_sector;
-			rq->nr_sectors = rq->hard_nr_sectors;
-			rq->hard_cur_sectors = bio_cur_sectors(rq->bio);
-			rq->current_nr_sectors = rq->hard_cur_sectors;
-			rq->buffer = bio_data(rq->bio);
-		}
-
-		/*
-		 * if total number of sectors is less than the first segment
-		 * size, something has gone terribly wrong
-		 */
-		if (rq->nr_sectors < rq->current_nr_sectors) {
-			printk(KERN_ERR "blk: request botched\n");
-			rq->nr_sectors = rq->current_nr_sectors;
-		}
-	}
-}
-
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio)
 {
@@ -61,11 +32,12 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 			 * never considered part of another segment, since that
 			 * might change with the bounce page.
 			 */
-			high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
+			high = page_to_pfn(bv->bv_page) > queue_bounce_pfn(q);
 			if (high || highprv)
 				goto new_segment;
 			if (cluster) {
-				if (seg_size + bv->bv_len > q->max_segment_size)
+				if (seg_size + bv->bv_len
+				    > queue_max_segment_size(q))
 					goto new_segment;
 				if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
 					goto new_segment;
@@ -120,7 +92,7 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 		return 0;
 
 	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
-	    q->max_segment_size)
+	    queue_max_segment_size(q))
 		return 0;
 
 	if (!bio_has_data(bio))
@@ -163,7 +135,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 		int nbytes = bvec->bv_len;
 
 		if (bvprv && cluster) {
-			if (sg->length + nbytes > q->max_segment_size)
+			if (sg->length + nbytes > queue_max_segment_size(q))
 				goto new_segment;
 
 			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
@@ -199,8 +171,9 @@ new_segment:
 
 
 	if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
-	    (rq->data_len & q->dma_pad_mask)) {
-		unsigned int pad_len = (q->dma_pad_mask & ~rq->data_len) + 1;
+	    (blk_rq_bytes(rq) & q->dma_pad_mask)) {
+		unsigned int pad_len =
+			(q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1;
 
 		sg->length += pad_len;
 		rq->extra_len += pad_len;
@@ -233,8 +206,8 @@ static inline int ll_new_hw_segment(struct request_queue *q,
 {
 	int nr_phys_segs = bio_phys_segments(q, bio);
 
-	if (req->nr_phys_segments + nr_phys_segs > q->max_hw_segments
-	    || req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
+	if (req->nr_phys_segments + nr_phys_segs > queue_max_hw_segments(q) ||
+	    req->nr_phys_segments + nr_phys_segs > queue_max_phys_segments(q)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -255,11 +228,11 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 	unsigned short max_sectors;
 
 	if (unlikely(blk_pc_request(req)))
-		max_sectors = q->max_hw_sectors;
+		max_sectors = queue_max_hw_sectors(q);
 	else
-		max_sectors = q->max_sectors;
+		max_sectors = queue_max_sectors(q);
 
-	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
+	if (blk_rq_sectors(req) + bio_sectors(bio) > max_sectors) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -279,12 +252,12 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 	unsigned short max_sectors;
 
 	if (unlikely(blk_pc_request(req)))
-		max_sectors = q->max_hw_sectors;
+		max_sectors = queue_max_hw_sectors(q);
 	else
-		max_sectors = q->max_sectors;
+		max_sectors = queue_max_sectors(q);
 
 
-	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
+	if (blk_rq_sectors(req) + bio_sectors(bio) > max_sectors) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -315,7 +288,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	/*
 	 * Will it become too large?
 	 */
-	if ((req->nr_sectors + next->nr_sectors) > q->max_sectors)
+	if ((blk_rq_sectors(req) + blk_rq_sectors(next)) > queue_max_sectors(q))
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
@@ -327,10 +300,10 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		total_phys_segments--;
 	}
 
-	if (total_phys_segments > q->max_phys_segments)
+	if (total_phys_segments > queue_max_phys_segments(q))
 		return 0;
 
-	if (total_phys_segments > q->max_hw_segments)
+	if (total_phys_segments > queue_max_hw_segments(q))
 		return 0;
 
 	/* Merge is OK... */
@@ -345,7 +318,7 @@ static void blk_account_io_merge(struct request *req)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
 
 		part_round_stats(cpu, part);
 		part_dec_in_flight(part);
@@ -366,7 +339,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	/*
 	 * not contiguous
 	 */
-	if (req->sector + req->nr_sectors != next->sector)
+	if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
 		return 0;
 
 	if (rq_data_dir(req) != rq_data_dir(next)
@@ -398,7 +371,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	req->biotail->bi_next = next->bio;
 	req->biotail = next->biotail;
 
-	req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
+	req->__data_len += blk_rq_bytes(next);
 
 	elv_merge_requests(q, req, next);
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 57af728d94bb..d71cedc09c4e 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -134,7 +134,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	q->backing_dev_info.state = 0;
 	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
 	blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
-	blk_queue_hardsect_size(q, 512);
+	blk_queue_logical_block_size(q, 512);
 	blk_queue_dma_alignment(q, 511);
 	blk_queue_congestion_threshold(q);
 	q->nr_batching = BLK_BATCH_REQ;
@@ -179,16 +179,16 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask)
 	 */
 	if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
 		dma = 1;
-	q->bounce_pfn = max_low_pfn;
+	q->limits.bounce_pfn = max_low_pfn;
 #else
 	if (b_pfn < blk_max_low_pfn)
 		dma = 1;
-	q->bounce_pfn = b_pfn;
+	q->limits.bounce_pfn = b_pfn;
 #endif
 	if (dma) {
 		init_emergency_isa_pool();
 		q->bounce_gfp = GFP_NOIO | GFP_DMA;
-		q->bounce_pfn = b_pfn;
+		q->limits.bounce_pfn = b_pfn;
 	}
 }
 EXPORT_SYMBOL(blk_queue_bounce_limit);
@@ -211,14 +211,23 @@ void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors)
 	}
 
 	if (BLK_DEF_MAX_SECTORS > max_sectors)
-		q->max_hw_sectors = q->max_sectors = max_sectors;
+		q->limits.max_hw_sectors = q->limits.max_sectors = max_sectors;
 	else {
-		q->max_sectors = BLK_DEF_MAX_SECTORS;
-		q->max_hw_sectors = max_sectors;
+		q->limits.max_sectors = BLK_DEF_MAX_SECTORS;
+		q->limits.max_hw_sectors = max_sectors;
 	}
 }
 EXPORT_SYMBOL(blk_queue_max_sectors);
 
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors)
+{
+	if (BLK_DEF_MAX_SECTORS > max_sectors)
+		q->limits.max_hw_sectors = BLK_DEF_MAX_SECTORS;
+	else
+		q->limits.max_hw_sectors = max_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_hw_sectors);
+
 /**
  * blk_queue_max_phys_segments - set max phys segments for a request for this queue
  * @q:  the request queue for the device
@@ -238,7 +247,7 @@ void blk_queue_max_phys_segments(struct request_queue *q,
 		       __func__, max_segments);
 	}
 
-	q->max_phys_segments = max_segments;
+	q->limits.max_phys_segments = max_segments;
 }
 EXPORT_SYMBOL(blk_queue_max_phys_segments);
 
@@ -262,7 +271,7 @@ void blk_queue_max_hw_segments(struct request_queue *q,
 		       __func__, max_segments);
 	}
 
-	q->max_hw_segments = max_segments;
+	q->limits.max_hw_segments = max_segments;
 }
 EXPORT_SYMBOL(blk_queue_max_hw_segments);
 
@@ -283,26 +292,110 @@ void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
 		       __func__, max_size);
 	}
 
-	q->max_segment_size = max_size;
+	q->limits.max_segment_size = max_size;
 }
 EXPORT_SYMBOL(blk_queue_max_segment_size);
 
 /**
- * blk_queue_hardsect_size - set hardware sector size for the queue
+ * blk_queue_logical_block_size - set logical block size for the queue
  * @q:  the request queue for the device
- * @size:  the hardware sector size, in bytes
+ * @size:  the logical block size, in bytes
  *
  * Description:
- *   This should typically be set to the lowest possible sector size
- *   that the hardware can operate on (possible without reverting to
- *   even internal read-modify-write operations). Usually the default
- *   of 512 covers most hardware.
+ *   This should be set to the lowest possible block size that the
+ *   storage device can address.  The default of 512 covers most
+ *   hardware.
  **/
-void blk_queue_hardsect_size(struct request_queue *q, unsigned short size)
+void blk_queue_logical_block_size(struct request_queue *q, unsigned short size)
 {
-	q->hardsect_size = size;
+	q->limits.logical_block_size = size;
+
+	if (q->limits.physical_block_size < size)
+		q->limits.physical_block_size = size;
+
+	if (q->limits.io_min < q->limits.physical_block_size)
+		q->limits.io_min = q->limits.physical_block_size;
 }
-EXPORT_SYMBOL(blk_queue_hardsect_size);
+EXPORT_SYMBOL(blk_queue_logical_block_size);
+
+/**
+ * blk_queue_physical_block_size - set physical block size for the queue
+ * @q:  the request queue for the device
+ * @size:  the physical block size, in bytes
+ *
+ * Description:
+ *   This should be set to the lowest possible sector size that the
+ *   hardware can operate on without reverting to read-modify-write
+ *   operations.
+ */
+void blk_queue_physical_block_size(struct request_queue *q, unsigned short size)
+{
+	q->limits.physical_block_size = size;
+
+	if (q->limits.physical_block_size < q->limits.logical_block_size)
+		q->limits.physical_block_size = q->limits.logical_block_size;
+
+	if (q->limits.io_min < q->limits.physical_block_size)
+		q->limits.io_min = q->limits.physical_block_size;
+}
+EXPORT_SYMBOL(blk_queue_physical_block_size);
+
+/**
+ * blk_queue_alignment_offset - set physical block alignment offset
+ * @q:	the request queue for the device
+ * @offset: alignment offset in bytes
+ *
+ * Description:
+ *   Some devices are naturally misaligned to compensate for things like
+ *   the legacy DOS partition table 63-sector offset.  Low-level drivers
+ *   should call this function for devices whose first sector is not
+ *   naturally aligned.
+ */
+void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
+{
+	q->limits.alignment_offset =
+		offset & (q->limits.physical_block_size - 1);
+	q->limits.misaligned = 0;
+}
+EXPORT_SYMBOL(blk_queue_alignment_offset);
+
+/**
+ * blk_queue_io_min - set minimum request size for the queue
+ * @q:	the request queue for the device
+ * @min:  smallest I/O size in bytes
+ *
+ * Description:
+ *   Some devices have an internal block size bigger than the reported
+ *   hardware sector size.  This function can be used to signal the
+ *   smallest I/O the device can perform without incurring a performance
+ *   penalty.
+ */
+void blk_queue_io_min(struct request_queue *q, unsigned int min)
+{
+	q->limits.io_min = min;
+
+	if (q->limits.io_min < q->limits.logical_block_size)
+		q->limits.io_min = q->limits.logical_block_size;
+
+	if (q->limits.io_min < q->limits.physical_block_size)
+		q->limits.io_min = q->limits.physical_block_size;
+}
+EXPORT_SYMBOL(blk_queue_io_min);
+
+/**
+ * blk_queue_io_opt - set optimal request size for the queue
+ * @q:	the request queue for the device
+ * @opt:  optimal request size in bytes
+ *
+ * Description:
+ *   Drivers can call this function to set the preferred I/O request
+ *   size for devices that report such a value.
+ */
+void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
+{
+	q->limits.io_opt = opt;
+}
+EXPORT_SYMBOL(blk_queue_io_opt);
 
 /*
  * Returns the minimum that is _not_ zero, unless both are zero.
@@ -317,14 +410,27 @@ EXPORT_SYMBOL(blk_queue_hardsect_size);
 void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 {
 	/* zero is "infinity" */
-	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
-	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
-	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask);
+	t->limits.max_sectors = min_not_zero(queue_max_sectors(t),
+					     queue_max_sectors(b));
+
+	t->limits.max_hw_sectors = min_not_zero(queue_max_hw_sectors(t),
+						queue_max_hw_sectors(b));
+
+	t->limits.seg_boundary_mask = min_not_zero(queue_segment_boundary(t),
+						   queue_segment_boundary(b));
+
+	t->limits.max_phys_segments = min_not_zero(queue_max_phys_segments(t),
+						   queue_max_phys_segments(b));
+
+	t->limits.max_hw_segments = min_not_zero(queue_max_hw_segments(t),
+						 queue_max_hw_segments(b));
+
+	t->limits.max_segment_size = min_not_zero(queue_max_segment_size(t),
+						  queue_max_segment_size(b));
+
+	t->limits.logical_block_size = max(queue_logical_block_size(t),
+					   queue_logical_block_size(b));
 
-	t->max_phys_segments = min_not_zero(t->max_phys_segments, b->max_phys_segments);
-	t->max_hw_segments = min_not_zero(t->max_hw_segments, b->max_hw_segments);
-	t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size);
-	t->hardsect_size = max(t->hardsect_size, b->hardsect_size);
 	if (!t->queue_lock)
 		WARN_ON_ONCE(1);
 	else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
@@ -336,6 +442,109 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
+/**
+ * blk_stack_limits - adjust queue_limits for stacked devices
+ * @t:	the stacking driver limits (top)
+ * @b:  the underlying queue limits (bottom)
+ * @offset:  offset to beginning of data within component device
+ *
+ * Description:
+ *    Merges two queue_limit structs.  Returns 0 if alignment didn't
+ *    change.  Returns -1 if adding the bottom device caused
+ *    misalignment.
+ */
+int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
+		     sector_t offset)
+{
+	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
+	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
+
+	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
+					    b->seg_boundary_mask);
+
+	t->max_phys_segments = min_not_zero(t->max_phys_segments,
+					    b->max_phys_segments);
+
+	t->max_hw_segments = min_not_zero(t->max_hw_segments,
+					  b->max_hw_segments);
+
+	t->max_segment_size = min_not_zero(t->max_segment_size,
+					   b->max_segment_size);
+
+	t->logical_block_size = max(t->logical_block_size,
+				    b->logical_block_size);
+
+	t->physical_block_size = max(t->physical_block_size,
+				     b->physical_block_size);
+
+	t->io_min = max(t->io_min, b->io_min);
+	t->no_cluster |= b->no_cluster;
+
+	/* Bottom device offset aligned? */
+	if (offset &&
+	    (offset & (b->physical_block_size - 1)) != b->alignment_offset) {
+		t->misaligned = 1;
+		return -1;
+	}
+
+	/* If top has no alignment offset, inherit from bottom */
+	if (!t->alignment_offset)
+		t->alignment_offset =
+			b->alignment_offset & (b->physical_block_size - 1);
+
+	/* Top device aligned on logical block boundary? */
+	if (t->alignment_offset & (t->logical_block_size - 1)) {
+		t->misaligned = 1;
+		return -1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(blk_stack_limits);
+
+/**
+ * disk_stack_limits - adjust queue limits for stacked drivers
+ * @disk:  MD/DM gendisk (top)
+ * @bdev:  the underlying block device (bottom)
+ * @offset:  offset to beginning of data within component device
+ *
+ * Description:
+ *    Merges the limits for two queues.  Returns 0 if alignment
+ *    didn't change.  Returns -1 if adding the bottom device caused
+ *    misalignment.
+ */
+void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
+		       sector_t offset)
+{
+	struct request_queue *t = disk->queue;
+	struct request_queue *b = bdev_get_queue(bdev);
+
+	offset += get_start_sect(bdev) << 9;
+
+	if (blk_stack_limits(&t->limits, &b->limits, offset) < 0) {
+		char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
+
+		disk_name(disk, 0, top);
+		bdevname(bdev, bottom);
+
+		printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
+		       top, bottom);
+	}
+
+	if (!t->queue_lock)
+		WARN_ON_ONCE(1);
+	else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(t->queue_lock, flags);
+		if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
+			queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
+		spin_unlock_irqrestore(t->queue_lock, flags);
+	}
+}
+EXPORT_SYMBOL(disk_stack_limits);
+
 /**
  * blk_queue_dma_pad - set pad mask
  * @q:     the request queue for the device
@@ -396,11 +605,11 @@ int blk_queue_dma_drain(struct request_queue *q,
 			       dma_drain_needed_fn *dma_drain_needed,
 			       void *buf, unsigned int size)
 {
-	if (q->max_hw_segments < 2 || q->max_phys_segments < 2)
+	if (queue_max_hw_segments(q) < 2 || queue_max_phys_segments(q) < 2)
 		return -EINVAL;
 	/* make room for appending the drain */
-	--q->max_hw_segments;
-	--q->max_phys_segments;
+	blk_queue_max_hw_segments(q, queue_max_hw_segments(q) - 1);
+	blk_queue_max_phys_segments(q, queue_max_phys_segments(q) - 1);
 	q->dma_drain_needed = dma_drain_needed;
 	q->dma_drain_buffer = buf;
 	q->dma_drain_size = size;
@@ -422,7 +631,7 @@ void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
 		       __func__, mask);
 	}
 
-	q->seg_boundary_mask = mask;
+	q->limits.seg_boundary_mask = mask;
 }
 EXPORT_SYMBOL(blk_queue_segment_boundary);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 3ff9bba3379a..b1cd04087d6a 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -95,21 +95,36 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
 {
-	int max_sectors_kb = q->max_sectors >> 1;
+	int max_sectors_kb = queue_max_sectors(q) >> 1;
 
 	return queue_var_show(max_sectors_kb, (page));
 }
 
-static ssize_t queue_hw_sector_size_show(struct request_queue *q, char *page)
+static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(q->hardsect_size, page);
+	return queue_var_show(queue_logical_block_size(q), page);
+}
+
+static ssize_t queue_physical_block_size_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_physical_block_size(q), page);
+}
+
+static ssize_t queue_io_min_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_io_min(q), page);
+}
+
+static ssize_t queue_io_opt_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_io_opt(q), page);
 }
 
 static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {
 	unsigned long max_sectors_kb,
-			max_hw_sectors_kb = q->max_hw_sectors >> 1,
+		max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1,
 			page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
 	ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
 
@@ -117,7 +132,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 		return -EINVAL;
 
 	spin_lock_irq(q->queue_lock);
-	q->max_sectors = max_sectors_kb << 1;
+	blk_queue_max_sectors(q, max_sectors_kb << 1);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
@@ -125,7 +140,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 {
-	int max_hw_sectors_kb = q->max_hw_sectors >> 1;
+	int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1;
 
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
@@ -249,7 +264,27 @@ static struct queue_sysfs_entry queue_iosched_entry = {
 
 static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.attr = {.name = "hw_sector_size", .mode = S_IRUGO },
-	.show = queue_hw_sector_size_show,
+	.show = queue_logical_block_size_show,
+};
+
+static struct queue_sysfs_entry queue_logical_block_size_entry = {
+	.attr = {.name = "logical_block_size", .mode = S_IRUGO },
+	.show = queue_logical_block_size_show,
+};
+
+static struct queue_sysfs_entry queue_physical_block_size_entry = {
+	.attr = {.name = "physical_block_size", .mode = S_IRUGO },
+	.show = queue_physical_block_size_show,
+};
+
+static struct queue_sysfs_entry queue_io_min_entry = {
+	.attr = {.name = "minimum_io_size", .mode = S_IRUGO },
+	.show = queue_io_min_show,
+};
+
+static struct queue_sysfs_entry queue_io_opt_entry = {
+	.attr = {.name = "optimal_io_size", .mode = S_IRUGO },
+	.show = queue_io_opt_show,
 };
 
 static struct queue_sysfs_entry queue_nonrot_entry = {
@@ -283,6 +318,10 @@ static struct attribute *default_attrs[] = {
 	&queue_max_sectors_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
+	&queue_logical_block_size_entry.attr,
+	&queue_physical_block_size_entry.attr,
+	&queue_io_min_entry.attr,
+	&queue_io_opt_entry.attr,
 	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
@@ -383,22 +422,26 @@ struct kobj_type blk_queue_ktype = {
 int blk_register_queue(struct gendisk *disk)
 {
 	int ret;
+	struct device *dev = disk_to_dev(disk);
 
 	struct request_queue *q = disk->queue;
 
 	if (WARN_ON(!q))
 		return -ENXIO;
 
-	if (!q->request_fn)
-		return 0;
+	ret = blk_trace_init_sysfs(dev);
+	if (ret)
+		return ret;
 
-	ret = kobject_add(&q->kobj, kobject_get(&disk_to_dev(disk)->kobj),
-			  "%s", "queue");
+	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
 	if (ret < 0)
 		return ret;
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
+	if (!q->request_fn)
+		return 0;
+
 	ret = elv_register_queue(q);
 	if (ret) {
 		kobject_uevent(&q->kobj, KOBJ_REMOVE);
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 3c518e3303ae..2e5cfeb59333 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -336,7 +336,7 @@ EXPORT_SYMBOL(blk_queue_end_tag);
 int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 {
 	struct blk_queue_tag *bqt = q->queue_tags;
-	unsigned max_depth, offset;
+	unsigned max_depth;
 	int tag;
 
 	if (unlikely((rq->cmd_flags & REQ_QUEUED))) {
@@ -355,13 +355,16 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	 * to starve sync IO on behalf of flooding async IO.
 	 */
 	max_depth = bqt->max_depth;
-	if (rq_is_sync(rq))
-		offset = 0;
-	else
-		offset = max_depth >> 2;
+	if (!rq_is_sync(rq) && max_depth > 1) {
+		max_depth -= 2;
+		if (!max_depth)
+			max_depth = 1;
+		if (q->in_flight[0] > max_depth)
+			return 1;
+	}
 
 	do {
-		tag = find_next_zero_bit(bqt->tag_map, max_depth, offset);
+		tag = find_first_zero_bit(bqt->tag_map, max_depth);
 		if (tag >= max_depth)
 			return 1;
 
@@ -374,7 +377,7 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	rq->cmd_flags |= REQ_QUEUED;
 	rq->tag = tag;
 	bqt->tag_index[tag] = rq;
-	blkdev_dequeue_request(rq);
+	blk_start_request(rq);
 	list_add(&rq->queuelist, &q->tag_busy_list);
 	return 0;
 }
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 1ec0d503cacd..1ba7e0aca878 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -122,10 +122,8 @@ void blk_rq_timed_out_timer(unsigned long data)
 			if (blk_mark_rq_complete(rq))
 				continue;
 			blk_rq_timed_out(rq);
-		} else {
-			if (!next || time_after(next, rq->deadline))
-				next = rq->deadline;
-		}
+		} else if (!next || time_after(next, rq->deadline))
+			next = rq->deadline;
 	}
 
 	/*
@@ -176,16 +174,14 @@ void blk_add_timer(struct request *req)
 	BUG_ON(!list_empty(&req->timeout_list));
 	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
 
-	if (req->timeout)
-		req->deadline = jiffies + req->timeout;
-	else {
-		req->deadline = jiffies + q->rq_timeout;
-		/*
-		 * Some LLDs, like scsi, peek at the timeout to prevent
-		 * a command from being retried forever.
-		 */
+	/*
+	 * Some LLDs, like scsi, peek at the timeout to prevent a
+	 * command from being retried forever.
+	 */
+	if (!req->timeout)
 		req->timeout = q->rq_timeout;
-	}
+
+	req->deadline = jiffies + req->timeout;
 	list_add_tail(&req->timeout_list, &q->timeout_list);
 
 	/*
diff --git a/block/blk.h b/block/blk.h
index 79c85f7c9ff5..3fae6add5430 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -13,6 +13,9 @@ extern struct kobj_type blk_queue_ktype;
 void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
+int blk_rq_append_bio(struct request_queue *q, struct request *rq,
+		      struct bio *bio);
+void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
 
 void blk_unplug_work(struct work_struct *work);
@@ -43,6 +46,43 @@ static inline void blk_clear_rq_complete(struct request *rq)
 	clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
 }
 
+/*
+ * Internal elevator interface
+ */
+#define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
+
+static inline struct request *__elv_next_request(struct request_queue *q)
+{
+	struct request *rq;
+
+	while (1) {
+		while (!list_empty(&q->queue_head)) {
+			rq = list_entry_rq(q->queue_head.next);
+			if (blk_do_ordered(q, &rq))
+				return rq;
+		}
+
+		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
+			return NULL;
+	}
+}
+
+static inline void elv_activate_rq(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_activate_req_fn)
+		e->ops->elevator_activate_req_fn(q, rq);
+}
+
+static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->ops->elevator_deactivate_req_fn)
+		e->ops->elevator_deactivate_req_fn(q, rq);
+}
+
 #ifdef CONFIG_FAIL_IO_TIMEOUT
 int blk_should_fake_timeout(struct request_queue *);
 ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
@@ -64,7 +104,6 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 int attempt_back_merge(struct request_queue *q, struct request *rq);
 int attempt_front_merge(struct request_queue *q, struct request *rq);
 void blk_recalc_rq_segments(struct request *rq);
-void blk_recalc_rq_sectors(struct request *rq, int nsect);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
@@ -112,9 +151,17 @@ static inline int blk_cpu_to_group(int cpu)
 #endif
 }
 
+/*
+ * Contribute to IO statistics IFF:
+ *
+ *	a) it's attached to a gendisk, and
+ *	b) the queue had IO stats enabled when this request was started, and
+ *	c) it's a file system request or a discard request
+ */
 static inline int blk_do_io_stat(struct request *rq)
 {
-	return rq->rq_disk && blk_rq_io_stat(rq);
+	return rq->rq_disk && blk_rq_io_stat(rq) &&
+	       (blk_fs_request(rq) || blk_discard_rq(rq));
 }
 
 #endif
diff --git a/block/bsg.c b/block/bsg.c
index dd81be455e00..5358f9ae13c1 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -446,15 +446,15 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	}
 
 	if (rq->next_rq) {
-		hdr->dout_resid = rq->data_len;
-		hdr->din_resid = rq->next_rq->data_len;
+		hdr->dout_resid = rq->resid_len;
+		hdr->din_resid = rq->next_rq->resid_len;
 		blk_rq_unmap_user(bidi_bio);
 		rq->next_rq->bio = NULL;
 		blk_put_request(rq->next_rq);
 	} else if (rq_data_dir(rq) == READ)
-		hdr->din_resid = rq->data_len;
+		hdr->din_resid = rq->resid_len;
 	else
-		hdr->dout_resid = rq->data_len;
+		hdr->dout_resid = rq->resid_len;
 
 	/*
 	 * If the request generated a negative error number, return it
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index a55a9bd75bd1..ef2f72d42434 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -349,8 +349,8 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
 	else if (rq_is_meta(rq2) && !rq_is_meta(rq1))
 		return rq2;
 
-	s1 = rq1->sector;
-	s2 = rq2->sector;
+	s1 = blk_rq_pos(rq1);
+	s2 = blk_rq_pos(rq2);
 
 	last = cfqd->last_position;
 
@@ -579,9 +579,9 @@ cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root,
 		 * Sort strictly based on sector.  Smallest to the left,
 		 * largest to the right.
 		 */
-		if (sector > cfqq->next_rq->sector)
+		if (sector > blk_rq_pos(cfqq->next_rq))
 			n = &(*p)->rb_right;
-		else if (sector < cfqq->next_rq->sector)
+		else if (sector < blk_rq_pos(cfqq->next_rq))
 			n = &(*p)->rb_left;
 		else
 			break;
@@ -611,8 +611,8 @@ static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		return;
 
 	cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio];
-	__cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root, cfqq->next_rq->sector,
-					 &parent, &p);
+	__cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root,
+				      blk_rq_pos(cfqq->next_rq), &parent, &p);
 	if (!__cfqq) {
 		rb_link_node(&cfqq->p_node, parent, p);
 		rb_insert_color(&cfqq->p_node, cfqq->p_root);
@@ -760,7 +760,7 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq)
 	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
 						cfqd->rq_in_driver);
 
-	cfqd->last_position = rq->hard_sector + rq->hard_nr_sectors;
+	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
 }
 
 static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
@@ -949,10 +949,10 @@ static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
 static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 					  struct request *rq)
 {
-	if (rq->sector >= cfqd->last_position)
-		return rq->sector - cfqd->last_position;
+	if (blk_rq_pos(rq) >= cfqd->last_position)
+		return blk_rq_pos(rq) - cfqd->last_position;
 	else
-		return cfqd->last_position - rq->sector;
+		return cfqd->last_position - blk_rq_pos(rq);
 }
 
 #define CIC_SEEK_THR	8 * 1024
@@ -996,7 +996,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 	if (cfq_rq_close(cfqd, __cfqq->next_rq))
 		return __cfqq;
 
-	if (__cfqq->next_rq->sector < sector)
+	if (blk_rq_pos(__cfqq->next_rq) < sector)
 		node = rb_next(&__cfqq->p_node);
 	else
 		node = rb_prev(&__cfqq->p_node);
@@ -1282,7 +1282,7 @@ static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	if (!cfqd->active_cic) {
 		struct cfq_io_context *cic = RQ_CIC(rq);
 
-		atomic_inc(&cic->ioc->refcount);
+		atomic_long_inc(&cic->ioc->refcount);
 		cfqd->active_cic = cic;
 	}
 }
@@ -1918,10 +1918,10 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
 
 	if (!cic->last_request_pos)
 		sdist = 0;
-	else if (cic->last_request_pos < rq->sector)
-		sdist = rq->sector - cic->last_request_pos;
+	else if (cic->last_request_pos < blk_rq_pos(rq))
+		sdist = blk_rq_pos(rq) - cic->last_request_pos;
 	else
-		sdist = cic->last_request_pos - rq->sector;
+		sdist = cic->last_request_pos - blk_rq_pos(rq);
 
 	/*
 	 * Don't allow the seek distance to get too large from the
@@ -2071,7 +2071,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfq_update_io_seektime(cfqd, cic, rq);
 	cfq_update_idle_window(cfqd, cfqq, cic);
 
-	cic->last_request_pos = rq->sector + rq->nr_sectors;
+	cic->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
 
 	if (cfqq == cfqd->active_queue) {
 		/*
@@ -2088,7 +2088,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
 			    cfqd->busy_queues > 1) {
 				del_timer(&cfqd->idle_slice_timer);
-				blk_start_queueing(cfqd->queue);
+			__blk_run_queue(cfqd->queue);
 			}
 			cfq_mark_cfqq_must_dispatch(cfqq);
 		}
@@ -2100,7 +2100,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
-		blk_start_queueing(cfqd->queue);
+		__blk_run_queue(cfqd->queue);
 	}
 }
 
@@ -2345,7 +2345,7 @@ static void cfq_kick_queue(struct work_struct *work)
 	struct request_queue *q = cfqd->queue;
 
 	spin_lock_irq(q->queue_lock);
-	blk_start_queueing(q);
+	__blk_run_queue(cfqd->queue);
 	spin_unlock_irq(q->queue_lock);
 }
 
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index f87615dea46b..7865a34e0faa 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -568,7 +568,7 @@ static int compat_blk_trace_setup(struct block_device *bdev, char __user *arg)
 	memcpy(&buts.name, &cbuts.name, 32);
 
 	mutex_lock(&bdev->bd_mutex);
-	ret = do_blk_trace_setup(q, b, bdev->bd_dev, &buts);
+	ret = do_blk_trace_setup(q, b, bdev->bd_dev, bdev, &buts);
 	mutex_unlock(&bdev->bd_mutex);
 	if (ret)
 		return ret;
@@ -763,10 +763,10 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
 		return compat_put_int(arg, block_size(bdev));
 	case BLKSSZGET: /* get block device hardware sector size */
-		return compat_put_int(arg, bdev_hardsect_size(bdev));
+		return compat_put_int(arg, bdev_logical_block_size(bdev));
 	case BLKSECTGET:
 		return compat_put_ushort(arg,
-					 bdev_get_queue(bdev)->max_sectors);
+					 queue_max_sectors(bdev_get_queue(bdev)));
 	case BLKRASET: /* compatible, but no compat_ptr (!) */
 	case BLKFRASET:
 		if (!capable(CAP_SYS_ADMIN))
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index c4d991d4adef..b547cbca7b23 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -138,7 +138,7 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 
 		__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
 		if (__rq) {
-			BUG_ON(sector != __rq->sector);
+			BUG_ON(sector != blk_rq_pos(__rq));
 
 			if (elv_rq_merge_ok(__rq, bio)) {
 				ret = ELEVATOR_FRONT_MERGE;
diff --git a/block/elevator.c b/block/elevator.c
index 7073a9072577..ca861927ba41 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -33,17 +33,16 @@
 #include <linux/compiler.h>
 #include <linux/delay.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
 #include <linux/hash.h>
 #include <linux/uaccess.h>
 
+#include <trace/events/block.h>
+
 #include "blk.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
 
-DEFINE_TRACE(block_rq_abort);
-
 /*
  * Merge hash stuff.
  */
@@ -52,11 +51,7 @@ static const int elv_hash_shift = 6;
 #define ELV_HASH_FN(sec)	\
 		(hash_long(ELV_HASH_BLOCK((sec)), elv_hash_shift))
 #define ELV_HASH_ENTRIES	(1 << elv_hash_shift)
-#define rq_hash_key(rq)		((rq)->sector + (rq)->nr_sectors)
-#define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
-
-DEFINE_TRACE(block_rq_insert);
-DEFINE_TRACE(block_rq_issue);
+#define rq_hash_key(rq)		(blk_rq_pos(rq) + blk_rq_sectors(rq))
 
 /*
  * Query io scheduler to see if the current process issuing bio may be
@@ -120,9 +115,9 @@ static inline int elv_try_merge(struct request *__rq, struct bio *bio)
 	 * we can merge and sequence is ok, check if it's possible
 	 */
 	if (elv_rq_merge_ok(__rq, bio)) {
-		if (__rq->sector + __rq->nr_sectors == bio->bi_sector)
+		if (blk_rq_pos(__rq) + blk_rq_sectors(__rq) == bio->bi_sector)
 			ret = ELEVATOR_BACK_MERGE;
-		else if (__rq->sector - bio_sectors(bio) == bio->bi_sector)
+		else if (blk_rq_pos(__rq) - bio_sectors(bio) == bio->bi_sector)
 			ret = ELEVATOR_FRONT_MERGE;
 	}
 
@@ -310,22 +305,6 @@ void elevator_exit(struct elevator_queue *e)
 }
 EXPORT_SYMBOL(elevator_exit);
 
-static void elv_activate_rq(struct request_queue *q, struct request *rq)
-{
-	struct elevator_queue *e = q->elevator;
-
-	if (e->ops->elevator_activate_req_fn)
-		e->ops->elevator_activate_req_fn(q, rq);
-}
-
-static void elv_deactivate_rq(struct request_queue *q, struct request *rq)
-{
-	struct elevator_queue *e = q->elevator;
-
-	if (e->ops->elevator_deactivate_req_fn)
-		e->ops->elevator_deactivate_req_fn(q, rq);
-}
-
 static inline void __elv_rqhash_del(struct request *rq)
 {
 	hlist_del_init(&rq->hash);
@@ -387,9 +366,9 @@ struct request *elv_rb_add(struct rb_root *root, struct request *rq)
 		parent = *p;
 		__rq = rb_entry(parent, struct request, rb_node);
 
-		if (rq->sector < __rq->sector)
+		if (blk_rq_pos(rq) < blk_rq_pos(__rq))
 			p = &(*p)->rb_left;
-		else if (rq->sector > __rq->sector)
+		else if (blk_rq_pos(rq) > blk_rq_pos(__rq))
 			p = &(*p)->rb_right;
 		else
 			return __rq;
@@ -417,9 +396,9 @@ struct request *elv_rb_find(struct rb_root *root, sector_t sector)
 	while (n) {
 		rq = rb_entry(n, struct request, rb_node);
 
-		if (sector < rq->sector)
+		if (sector < blk_rq_pos(rq))
 			n = n->rb_left;
-		else if (sector > rq->sector)
+		else if (sector > blk_rq_pos(rq))
 			n = n->rb_right;
 		else
 			return rq;
@@ -458,14 +437,14 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 			break;
 		if (pos->cmd_flags & stop_flags)
 			break;
-		if (rq->sector >= boundary) {
-			if (pos->sector < boundary)
+		if (blk_rq_pos(rq) >= boundary) {
+			if (blk_rq_pos(pos) < boundary)
 				continue;
 		} else {
-			if (pos->sector >= boundary)
+			if (blk_rq_pos(pos) >= boundary)
 				break;
 		}
-		if (rq->sector >= pos->sector)
+		if (blk_rq_pos(rq) >= blk_rq_pos(pos))
 			break;
 	}
 
@@ -563,7 +542,7 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 	 * in_flight count again
 	 */
 	if (blk_account_rq(rq)) {
-		q->in_flight--;
+		q->in_flight[rq_is_sync(rq)]--;
 		if (blk_sorted_rq(rq))
 			elv_deactivate_rq(q, rq);
 	}
@@ -592,6 +571,9 @@ void elv_drain_elevator(struct request_queue *q)
  */
 void elv_quiesce_start(struct request_queue *q)
 {
+	if (!q->elevator)
+		return;
+
 	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
 
 	/*
@@ -599,7 +581,7 @@ void elv_quiesce_start(struct request_queue *q)
 	 */
 	elv_drain_elevator(q);
 	while (q->rq.elvpriv) {
-		blk_start_queueing(q);
+		__blk_run_queue(q);
 		spin_unlock_irq(q->queue_lock);
 		msleep(10);
 		spin_lock_irq(q->queue_lock);
@@ -643,8 +625,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		 *   with anything.  There's no point in delaying queue
 		 *   processing.
 		 */
-		blk_remove_plug(q);
-		blk_start_queueing(q);
+		__blk_run_queue(q);
 		break;
 
 	case ELEVATOR_INSERT_SORT:
@@ -703,7 +684,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 
 	if (unplug_it && blk_queue_plugged(q)) {
 		int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
-			- q->in_flight;
+				- queue_in_flight(q);
 
 		if (nrq >= q->unplug_thresh)
 			__generic_unplug_device(q);
@@ -759,117 +740,6 @@ void elv_add_request(struct request_queue *q, struct request *rq, int where,
 }
 EXPORT_SYMBOL(elv_add_request);
 
-static inline struct request *__elv_next_request(struct request_queue *q)
-{
-	struct request *rq;
-
-	while (1) {
-		while (!list_empty(&q->queue_head)) {
-			rq = list_entry_rq(q->queue_head.next);
-			if (blk_do_ordered(q, &rq))
-				return rq;
-		}
-
-		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
-			return NULL;
-	}
-}
-
-struct request *elv_next_request(struct request_queue *q)
-{
-	struct request *rq;
-	int ret;
-
-	while ((rq = __elv_next_request(q)) != NULL) {
-		if (!(rq->cmd_flags & REQ_STARTED)) {
-			/*
-			 * This is the first time the device driver
-			 * sees this request (possibly after
-			 * requeueing).  Notify IO scheduler.
-			 */
-			if (blk_sorted_rq(rq))
-				elv_activate_rq(q, rq);
-
-			/*
-			 * just mark as started even if we don't start
-			 * it, a request that has been delayed should
-			 * not be passed by new incoming requests
-			 */
-			rq->cmd_flags |= REQ_STARTED;
-			trace_block_rq_issue(q, rq);
-		}
-
-		if (!q->boundary_rq || q->boundary_rq == rq) {
-			q->end_sector = rq_end_sector(rq);
-			q->boundary_rq = NULL;
-		}
-
-		if (rq->cmd_flags & REQ_DONTPREP)
-			break;
-
-		if (q->dma_drain_size && rq->data_len) {
-			/*
-			 * make sure space for the drain appears we
-			 * know we can do this because max_hw_segments
-			 * has been adjusted to be one fewer than the
-			 * device can handle
-			 */
-			rq->nr_phys_segments++;
-		}
-
-		if (!q->prep_rq_fn)
-			break;
-
-		ret = q->prep_rq_fn(q, rq);
-		if (ret == BLKPREP_OK) {
-			break;
-		} else if (ret == BLKPREP_DEFER) {
-			/*
-			 * the request may have been (partially) prepped.
-			 * we need to keep this request in the front to
-			 * avoid resource deadlock.  REQ_STARTED will
-			 * prevent other fs requests from passing this one.
-			 */
-			if (q->dma_drain_size && rq->data_len &&
-			    !(rq->cmd_flags & REQ_DONTPREP)) {
-				/*
-				 * remove the space for the drain we added
-				 * so that we don't add it again
-				 */
-				--rq->nr_phys_segments;
-			}
-
-			rq = NULL;
-			break;
-		} else if (ret == BLKPREP_KILL) {
-			rq->cmd_flags |= REQ_QUIET;
-			__blk_end_request(rq, -EIO, blk_rq_bytes(rq));
-		} else {
-			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
-			break;
-		}
-	}
-
-	return rq;
-}
-EXPORT_SYMBOL(elv_next_request);
-
-void elv_dequeue_request(struct request_queue *q, struct request *rq)
-{
-	BUG_ON(list_empty(&rq->queuelist));
-	BUG_ON(ELV_ON_HASH(rq));
-
-	list_del_init(&rq->queuelist);
-
-	/*
-	 * the time frame between a request being removed from the lists
-	 * and to it is freed is accounted as io that is in progress at
-	 * the driver side.
-	 */
-	if (blk_account_rq(rq))
-		q->in_flight++;
-}
-
 int elv_queue_empty(struct request_queue *q)
 {
 	struct elevator_queue *e = q->elevator;
@@ -939,7 +809,12 @@ void elv_abort_queue(struct request_queue *q)
 		rq = list_entry_rq(q->queue_head.next);
 		rq->cmd_flags |= REQ_QUIET;
 		trace_block_rq_abort(q, rq);
-		__blk_end_request(rq, -EIO, blk_rq_bytes(rq));
+		/*
+		 * Mark this request as started so we don't trigger
+		 * any debug logic in the end I/O path.
+		 */
+		blk_start_request(rq);
+		__blk_end_request_all(rq, -EIO);
 	}
 }
 EXPORT_SYMBOL(elv_abort_queue);
@@ -952,7 +827,7 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 	 * request is released from the driver, io must be done
 	 */
 	if (blk_account_rq(rq)) {
-		q->in_flight--;
+		q->in_flight[rq_is_sync(rq)]--;
 		if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn)
 			e->ops->elevator_completed_req_fn(q, rq);
 	}
@@ -967,11 +842,11 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 		if (!list_empty(&q->queue_head))
 			next = list_entry_rq(q->queue_head.next);
 
-		if (!q->in_flight &&
+		if (!queue_in_flight(q) &&
 		    blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
 		    (!next || blk_ordered_req_seq(next) > QUEUE_ORDSEQ_DRAIN)) {
 			blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
-			blk_start_queueing(q);
+			__blk_run_queue(q);
 		}
 	}
 }
@@ -1179,6 +1054,9 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 	char elevator_name[ELV_NAME_MAX];
 	struct elevator_type *e;
 
+	if (!q->elevator)
+		return count;
+
 	strlcpy(elevator_name, name, sizeof(elevator_name));
 	strstrip(elevator_name);
 
@@ -1202,10 +1080,15 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 ssize_t elv_iosched_show(struct request_queue *q, char *name)
 {
 	struct elevator_queue *e = q->elevator;
-	struct elevator_type *elv = e->elevator_type;
+	struct elevator_type *elv;
 	struct elevator_type *__e;
 	int len = 0;
 
+	if (!q->elevator)
+		return sprintf(name, "none\n");
+
+	elv = e->elevator_type;
+
 	spin_lock(&elv_list_lock);
 	list_for_each_entry(__e, &elv_list, list) {
 		if (!strcmp(elv->elevator_name, __e->elevator_name))
diff --git a/block/genhd.c b/block/genhd.c
index 1a4916e01732..fe7ccc0a618f 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -852,11 +852,21 @@ static ssize_t disk_capability_show(struct device *dev,
 	return sprintf(buf, "%x\n", disk->flags);
 }
 
+static ssize_t disk_alignment_offset_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue));
+}
+
 static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
 static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
 static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
 static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
+static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -875,6 +885,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_removable.attr,
 	&dev_attr_ro.attr,
 	&dev_attr_size.attr,
+	&dev_attr_alignment_offset.attr,
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
diff --git a/block/ioctl.c b/block/ioctl.c
index ad474d4bbcce..500e4c73cc52 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -152,10 +152,10 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 		bio->bi_private = &wait;
 		bio->bi_sector = start;
 
-		if (len > q->max_hw_sectors) {
-			bio->bi_size = q->max_hw_sectors << 9;
-			len -= q->max_hw_sectors;
-			start += q->max_hw_sectors;
+		if (len > queue_max_hw_sectors(q)) {
+			bio->bi_size = queue_max_hw_sectors(q) << 9;
+			len -= queue_max_hw_sectors(q);
+			start += queue_max_hw_sectors(q);
 		} else {
 			bio->bi_size = len << 9;
 			len = 0;
@@ -311,9 +311,9 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */
 		return put_int(arg, block_size(bdev));
 	case BLKSSZGET: /* get block device hardware sector size */
-		return put_int(arg, bdev_hardsect_size(bdev));
+		return put_int(arg, bdev_logical_block_size(bdev));
 	case BLKSECTGET:
-		return put_ushort(arg, bdev_get_queue(bdev)->max_sectors);
+		return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev)));
 	case BLKRASET:
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 82a0ca2f6729..5f8e798ede4e 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -75,7 +75,7 @@ static int sg_set_timeout(struct request_queue *q, int __user *p)
 
 static int sg_get_reserved_size(struct request_queue *q, int __user *p)
 {
-	unsigned val = min(q->sg_reserved_size, q->max_sectors << 9);
+	unsigned val = min(q->sg_reserved_size, queue_max_sectors(q) << 9);
 
 	return put_user(val, p);
 }
@@ -89,8 +89,8 @@ static int sg_set_reserved_size(struct request_queue *q, int __user *p)
 
 	if (size < 0)
 		return -EINVAL;
-	if (size > (q->max_sectors << 9))
-		size = q->max_sectors << 9;
+	if (size > (queue_max_sectors(q) << 9))
+		size = queue_max_sectors(q) << 9;
 
 	q->sg_reserved_size = size;
 	return 0;
@@ -230,7 +230,7 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 	hdr->info = 0;
 	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
-	hdr->resid = rq->data_len;
+	hdr->resid = rq->resid_len;
 	hdr->sb_len_wr = 0;
 
 	if (rq->sense_len && hdr->sbp) {
@@ -264,7 +264,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	if (hdr->cmd_len > BLK_MAX_CDB)
 		return -EINVAL;
 
-	if (hdr->dxfer_len > (q->max_hw_sectors << 9))
+	if (hdr->dxfer_len > (queue_max_hw_sectors(q) << 9))
 		return -EIO;
 
 	if (hdr->dxfer_len)
@@ -500,9 +500,6 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 
 	rq = blk_get_request(q, WRITE, __GFP_WAIT);
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->data = NULL;
-	rq->data_len = 0;
-	rq->extra_len = 0;
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
 	rq->cmd[0] = cmd;
 	rq->cmd[4] = data;
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 51b9f8280f88..2faa9e2ac893 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -401,7 +401,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		/* Interrupt Line values above 0xF are forbidden */
 		if (dev->irq > 0 && (dev->irq <= 0xF)) {
 			printk(" - using IRQ %d\n", dev->irq);
-			acpi_register_gsi(dev->irq, ACPI_LEVEL_SENSITIVE,
+			acpi_register_gsi(&dev->dev, dev->irq,
+					  ACPI_LEVEL_SENSITIVE,
 					  ACPI_ACTIVE_LOW);
 			return 0;
 		} else {
@@ -410,7 +411,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		}
 	}
 
-	rc = acpi_register_gsi(gsi, triggering, polarity);
+	rc = acpi_register_gsi(&dev->dev, gsi, triggering, polarity);
 	if (rc < 0) {
 		dev_warn(&dev->dev, "PCI INT %c: failed to register GSI\n",
 			 pin_name(pin));
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 6b91c26a4635..15a23031833f 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -77,8 +77,6 @@ static ssize_t ahci_led_store(struct ata_port *ap, const char *buf,
 			      size_t size);
 static ssize_t ahci_transmit_led_message(struct ata_port *ap, u32 state,
 					ssize_t size);
-#define MAX_SLOTS 8
-#define MAX_RETRY 15
 
 enum {
 	AHCI_PCI_BAR		= 5,
@@ -231,6 +229,10 @@ enum {
 
 	ICH_MAP				= 0x90, /* ICH MAP register */
 
+	/* em constants */
+	EM_MAX_SLOTS			= 8,
+	EM_MAX_RETRY			= 5,
+
 	/* em_ctl bits */
 	EM_CTL_RST			= (1 << 9), /* Reset */
 	EM_CTL_TM			= (1 << 8), /* Transmit Message */
@@ -282,8 +284,8 @@ struct ahci_port_priv {
 	unsigned int		ncq_saw_dmas:1;
 	unsigned int		ncq_saw_sdb:1;
 	u32 			intr_mask;	/* interrupts to enable */
-	struct ahci_em_priv	em_priv[MAX_SLOTS];/* enclosure management info
-					 	 * per PM slot */
+	/* enclosure management info per PM slot */
+	struct ahci_em_priv	em_priv[EM_MAX_SLOTS];
 };
 
 static int ahci_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val);
@@ -313,7 +315,6 @@ static void ahci_error_handler(struct ata_port *ap);
 static void ahci_post_internal_cmd(struct ata_queued_cmd *qc);
 static int ahci_port_resume(struct ata_port *ap);
 static void ahci_dev_config(struct ata_device *dev);
-static unsigned int ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl);
 static void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag,
 			       u32 opts);
 #ifdef CONFIG_PM
@@ -404,14 +405,14 @@ static struct ata_port_operations ahci_sb600_ops = {
 #define AHCI_HFLAGS(flags)	.private_data	= (void *)(flags)
 
 static const struct ata_port_info ahci_port_info[] = {
-	/* board_ahci */
+	[board_ahci] =
 	{
 		.flags		= AHCI_FLAG_COMMON,
 		.pio_mask	= ATA_PIO4,
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
-	/* board_ahci_vt8251 */
+	[board_ahci_vt8251] =
 	{
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_NCQ | AHCI_HFLAG_NO_PMP),
 		.flags		= AHCI_FLAG_COMMON,
@@ -419,7 +420,7 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_vt8251_ops,
 	},
-	/* board_ahci_ign_iferr */
+	[board_ahci_ign_iferr] =
 	{
 		AHCI_HFLAGS	(AHCI_HFLAG_IGN_IRQ_IF_ERR),
 		.flags		= AHCI_FLAG_COMMON,
@@ -427,17 +428,16 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
-	/* board_ahci_sb600 */
+	[board_ahci_sb600] =
 	{
 		AHCI_HFLAGS	(AHCI_HFLAG_IGN_SERR_INTERNAL |
-				 AHCI_HFLAG_32BIT_ONLY | AHCI_HFLAG_NO_MSI |
-				 AHCI_HFLAG_SECT255),
+				 AHCI_HFLAG_NO_MSI | AHCI_HFLAG_SECT255),
 		.flags		= AHCI_FLAG_COMMON,
 		.pio_mask	= ATA_PIO4,
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_sb600_ops,
 	},
-	/* board_ahci_mv */
+	[board_ahci_mv] =
 	{
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_NCQ | AHCI_HFLAG_NO_MSI |
 				 AHCI_HFLAG_MV_PATA | AHCI_HFLAG_NO_PMP),
@@ -447,7 +447,7 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
-	/* board_ahci_sb700, for SB700 and SB800 */
+	[board_ahci_sb700] =	/* for SB700 and SB800 */
 	{
 		AHCI_HFLAGS	(AHCI_HFLAG_IGN_SERR_INTERNAL),
 		.flags		= AHCI_FLAG_COMMON,
@@ -455,7 +455,7 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_sb600_ops,
 	},
-	/* board_ahci_mcp65 */
+	[board_ahci_mcp65] =
 	{
 		AHCI_HFLAGS	(AHCI_HFLAG_YES_NCQ),
 		.flags		= AHCI_FLAG_COMMON,
@@ -463,7 +463,7 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
-	/* board_ahci_nopmp */
+	[board_ahci_nopmp] =
 	{
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_PMP),
 		.flags		= AHCI_FLAG_COMMON,
@@ -1141,12 +1141,12 @@ static void ahci_start_port(struct ata_port *ap)
 			emp = &pp->em_priv[link->pmp];
 
 			/* EM Transmit bit maybe busy during init */
-			for (i = 0; i < MAX_RETRY; i++) {
+			for (i = 0; i < EM_MAX_RETRY; i++) {
 				rc = ahci_transmit_led_message(ap,
 							       emp->led_state,
 							       4);
 				if (rc == -EBUSY)
-					udelay(100);
+					msleep(1);
 				else
 					break;
 			}
@@ -1340,7 +1340,7 @@ static ssize_t ahci_transmit_led_message(struct ata_port *ap, u32 state,
 
 	/* get the slot number from the message */
 	pmp = (state & EM_MSG_LED_PMP_SLOT) >> 8;
-	if (pmp < MAX_SLOTS)
+	if (pmp < EM_MAX_SLOTS)
 		emp = &pp->em_priv[pmp];
 	else
 		return -EINVAL;
@@ -1408,7 +1408,7 @@ static ssize_t ahci_led_store(struct ata_port *ap, const char *buf,
 
 	/* get the slot number from the message */
 	pmp = (state & EM_MSG_LED_PMP_SLOT) >> 8;
-	if (pmp < MAX_SLOTS)
+	if (pmp < EM_MAX_SLOTS)
 		emp = &pp->em_priv[pmp];
 	else
 		return -EINVAL;
@@ -2584,6 +2584,51 @@ static void ahci_p5wdh_workaround(struct ata_host *host)
 	}
 }
 
+/*
+ * SB600 ahci controller on ASUS M2A-VM can't do 64bit DMA with older
+ * BIOS.  The oldest version known to be broken is 0901 and working is
+ * 1501 which was released on 2007-10-26.  Force 32bit DMA on anything
+ * older than 1501.  Please read bko#9412 for more info.
+ */
+static bool ahci_asus_m2a_vm_32bit_only(struct pci_dev *pdev)
+{
+	static const struct dmi_system_id sysids[] = {
+		{
+			.ident = "ASUS M2A-VM",
+			.matches = {
+				DMI_MATCH(DMI_BOARD_VENDOR,
+					  "ASUSTeK Computer INC."),
+				DMI_MATCH(DMI_BOARD_NAME, "M2A-VM"),
+			},
+		},
+		{ }
+	};
+	const char *cutoff_mmdd = "10/26";
+	const char *date;
+	int year;
+
+	if (pdev->bus->number != 0 || pdev->devfn != PCI_DEVFN(0x12, 0) ||
+	    !dmi_check_system(sysids))
+		return false;
+
+	/*
+	 * Argh.... both version and date are free form strings.
+	 * Let's hope they're using the same date format across
+	 * different versions.
+	 */
+	date = dmi_get_system_info(DMI_BIOS_DATE);
+	year = dmi_get_year(DMI_BIOS_DATE);
+	if (date && strlen(date) >= 10 && date[2] == '/' && date[5] == '/' &&
+	    (year > 2007 ||
+	     (year == 2007 && strncmp(date, cutoff_mmdd, 5) >= 0)))
+		return false;
+
+	dev_printk(KERN_WARNING, &pdev->dev, "ASUS M2A-VM: BIOS too old, "
+		   "forcing 32bit DMA, update BIOS\n");
+
+	return true;
+}
+
 static bool ahci_broken_system_poweroff(struct pci_dev *pdev)
 {
 	static const struct dmi_system_id broken_systems[] = {
@@ -2744,6 +2789,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (board_id == board_ahci_sb700 && pdev->revision >= 0x40)
 		hpriv->flags &= ~AHCI_HFLAG_IGN_SERR_INTERNAL;
 
+	/* apply ASUS M2A_VM quirk */
+	if (ahci_asus_m2a_vm_32bit_only(pdev))
+		hpriv->flags |= AHCI_HFLAG_32BIT_ONLY;
+
 	if (!(hpriv->flags & AHCI_HFLAG_NO_MSI))
 		pci_enable_msi(pdev);
 
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 1aeb7082b0c4..d0a14cf2bd74 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -223,10 +223,8 @@ static const struct pci_device_id piix_pci_tbl[] = {
 	/* ICH8 Mobile PATA Controller */
 	{ 0x8086, 0x2850, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich_pata_100 },
 
-	/* NOTE: The following PCI ids must be kept in sync with the
-	 * list in drivers/pci/quirks.c.
-	 */
-
+	/* SATA ports */
+	
 	/* 82801EB (ICH5) */
 	{ 0x8086, 0x24d1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich5_sata },
 	/* 82801EB (ICH5) */
@@ -1509,8 +1507,8 @@ static int __devinit piix_init_one(struct pci_dev *pdev,
 		dev_printk(KERN_DEBUG, &pdev->dev,
 			   "version " DRV_VERSION "\n");
 
-	/* no hotplugging support (FIXME) */
-	if (!in_module_init)
+	/* no hotplugging support for later devices (FIXME) */
+	if (!in_module_init && ent->driver_data >= ich5_sata)
 		return -ENODEV;
 
 	if (piix_broken_system_poweroff(pdev)) {
@@ -1591,6 +1589,7 @@ static int __devinit piix_init_one(struct pci_dev *pdev,
 		host->ports[1]->mwdma_mask = 0;
 		host->ports[1]->udma_mask = 0;
 	}
+	host->flags |= ATA_HOST_PARALLEL_SCAN;
 
 	pci_set_master(pdev);
 	return ata_pci_sff_activate_host(host, ata_sff_interrupt, &piix_sht);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c9242301cfa1..ca4d208ddf3b 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -5031,7 +5031,6 @@ int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active)
 {
 	int nr_done = 0;
 	u32 done_mask;
-	int i;
 
 	done_mask = ap->qc_active ^ qc_active;
 
@@ -5041,16 +5040,16 @@ int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active)
 		return -EINVAL;
 	}
 
-	for (i = 0; i < ATA_MAX_QUEUE; i++) {
+	while (done_mask) {
 		struct ata_queued_cmd *qc;
+		unsigned int tag = __ffs(done_mask);
 
-		if (!(done_mask & (1 << i)))
-			continue;
-
-		if ((qc = ata_qc_from_tag(ap, i))) {
+		qc = ata_qc_from_tag(ap, tag);
+		if (qc) {
 			ata_qc_complete(qc);
 			nr_done++;
 		}
+		done_mask &= ~(1 << tag);
 	}
 
 	return nr_done;
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 342316064e9f..d0dfeef55db5 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1084,7 +1084,7 @@ static int atapi_drain_needed(struct request *rq)
 	if (likely(!blk_pc_request(rq)))
 		return 0;
 
-	if (!rq->data_len || (rq->cmd_flags & REQ_RW))
+	if (!blk_rq_bytes(rq) || (rq->cmd_flags & REQ_RW))
 		return 0;
 
 	return atapi_cmd_type(rq->cmd[0]) == ATAPI_MISC;
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index bb18415d3d63..bbbb1fab1755 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -727,17 +727,23 @@ unsigned int ata_sff_data_xfer(struct ata_device *dev, unsigned char *buf,
 	else
 		iowrite16_rep(data_addr, buf, words);
 
-	/* Transfer trailing 1 byte, if any. */
+	/* Transfer trailing byte, if any. */
 	if (unlikely(buflen & 0x01)) {
-		__le16 align_buf[1] = { 0 };
-		unsigned char *trailing_buf = buf + buflen - 1;
+		unsigned char pad[2];
 
+		/* Point buf to the tail of buffer */
+		buf += buflen - 1;
+
+		/*
+		 * Use io*16_rep() accessors here as well to avoid pointlessly
+		 * swapping bytes to and fro on the big endian machines...
+		 */
 		if (rw == READ) {
-			align_buf[0] = cpu_to_le16(ioread16(data_addr));
-			memcpy(trailing_buf, align_buf, 1);
+			ioread16_rep(data_addr, pad, 1);
+			*buf = pad[0];
 		} else {
-			memcpy(align_buf, trailing_buf, 1);
-			iowrite16(le16_to_cpu(align_buf[0]), data_addr);
+			pad[0] = *buf;
+			iowrite16_rep(data_addr, pad, 1);
 		}
 		words++;
 	}
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 6cda12ba8122..b2d11f300c39 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -305,8 +305,8 @@ static irqreturn_t nv_ck804_interrupt(int irq, void *dev_instance);
 static int nv_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val);
 static int nv_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 
-static int nv_noclassify_hardreset(struct ata_link *link, unsigned int *class,
-				   unsigned long deadline);
+static int nv_hardreset(struct ata_link *link, unsigned int *class,
+			unsigned long deadline);
 static void nv_nf2_freeze(struct ata_port *ap);
 static void nv_nf2_thaw(struct ata_port *ap);
 static void nv_ck804_freeze(struct ata_port *ap);
@@ -406,49 +406,82 @@ static struct scsi_host_template nv_swncq_sht = {
 	.slave_configure	= nv_swncq_slave_config,
 };
 
-static struct ata_port_operations nv_common_ops = {
+/*
+ * NV SATA controllers have various different problems with hardreset
+ * protocol depending on the specific controller and device.
+ *
+ * GENERIC:
+ *
+ *  bko11195 reports that link doesn't come online after hardreset on
+ *  generic nv's and there have been several other similar reports on
+ *  linux-ide.
+ *
+ *  bko12351#c23 reports that warmplug on MCP61 doesn't work with
+ *  softreset.
+ *
+ * NF2/3:
+ *
+ *  bko3352 reports nf2/3 controllers can't determine device signature
+ *  reliably after hardreset.  The following thread reports detection
+ *  failure on cold boot with the standard debouncing timing.
+ *
+ *  http://thread.gmane.org/gmane.linux.ide/34098
+ *
+ *  bko12176 reports that hardreset fails to bring up the link during
+ *  boot on nf2.
+ *
+ * CK804:
+ *
+ *  For initial probing after boot and hot plugging, hardreset mostly
+ *  works fine on CK804 but curiously, reprobing on the initial port
+ *  by rescanning or rmmod/insmod fails to acquire the initial D2H Reg
+ *  FIS in somewhat undeterministic way.
+ *
+ * SWNCQ:
+ *
+ *  bko12351 reports that when SWNCQ is enabled, for hotplug to work,
+ *  hardreset should be used and hardreset can't report proper
+ *  signature, which suggests that mcp5x is closer to nf2 as long as
+ *  reset quirkiness is concerned.
+ *
+ *  bko12703 reports that boot probing fails for intel SSD with
+ *  hardreset.  Link fails to come online.  Softreset works fine.
+ *
+ * The failures are varied but the following patterns seem true for
+ * all flavors.
+ *
+ * - Softreset during boot always works.
+ *
+ * - Hardreset during boot sometimes fails to bring up the link on
+ *   certain comibnations and device signature acquisition is
+ *   unreliable.
+ *
+ * - Hardreset is often necessary after hotplug.
+ *
+ * So, preferring softreset for boot probing and error handling (as
+ * hardreset might bring down the link) but using hardreset for
+ * post-boot probing should work around the above issues in most
+ * cases.  Define nv_hardreset() which only kicks in for post-boot
+ * probing and use it for all variants.
+ */
+static struct ata_port_operations nv_generic_ops = {
 	.inherits		= &ata_bmdma_port_ops,
 	.lost_interrupt		= ATA_OP_NULL,
 	.scr_read		= nv_scr_read,
 	.scr_write		= nv_scr_write,
+	.hardreset		= nv_hardreset,
 };
 
-/* OSDL bz11195 reports that link doesn't come online after hardreset
- * on generic nv's and there have been several other similar reports
- * on linux-ide.  Disable hardreset for generic nv's.
- */
-static struct ata_port_operations nv_generic_ops = {
-	.inherits		= &nv_common_ops,
-	.hardreset		= ATA_OP_NULL,
-};
-
-/* nf2 is ripe with hardreset related problems.
- *
- * kernel bz#3352 reports nf2/3 controllers can't determine device
- * signature reliably.  The following thread reports detection failure
- * on cold boot with the standard debouncing timing.
- *
- * http://thread.gmane.org/gmane.linux.ide/34098
- *
- * And bz#12176 reports that hardreset simply doesn't work on nf2.
- * Give up on it and just don't do hardreset.
- */
 static struct ata_port_operations nv_nf2_ops = {
 	.inherits		= &nv_generic_ops,
 	.freeze			= nv_nf2_freeze,
 	.thaw			= nv_nf2_thaw,
 };
 
-/* For initial probing after boot and hot plugging, hardreset mostly
- * works fine on CK804 but curiously, reprobing on the initial port by
- * rescanning or rmmod/insmod fails to acquire the initial D2H Reg FIS
- * in somewhat undeterministic way.  Use noclassify hardreset.
- */
 static struct ata_port_operations nv_ck804_ops = {
-	.inherits		= &nv_common_ops,
+	.inherits		= &nv_generic_ops,
 	.freeze			= nv_ck804_freeze,
 	.thaw			= nv_ck804_thaw,
-	.hardreset		= nv_noclassify_hardreset,
 	.host_stop		= nv_ck804_host_stop,
 };
 
@@ -476,19 +509,8 @@ static struct ata_port_operations nv_adma_ops = {
 	.host_stop		= nv_adma_host_stop,
 };
 
-/* Kernel bz#12351 reports that when SWNCQ is enabled, for hotplug to
- * work, hardreset should be used and hardreset can't report proper
- * signature, which suggests that mcp5x is closer to nf2 as long as
- * reset quirkiness is concerned.  Define separate ops for mcp5x with
- * nv_noclassify_hardreset().
- */
-static struct ata_port_operations nv_mcp5x_ops = {
-	.inherits		= &nv_common_ops,
-	.hardreset		= nv_noclassify_hardreset,
-};
-
 static struct ata_port_operations nv_swncq_ops = {
-	.inherits		= &nv_mcp5x_ops,
+	.inherits		= &nv_generic_ops,
 
 	.qc_defer		= ata_std_qc_defer,
 	.qc_prep		= nv_swncq_qc_prep,
@@ -557,7 +579,7 @@ static const struct ata_port_info nv_port_info[] = {
 		.pio_mask	= NV_PIO_MASK,
 		.mwdma_mask	= NV_MWDMA_MASK,
 		.udma_mask	= NV_UDMA_MASK,
-		.port_ops	= &nv_mcp5x_ops,
+		.port_ops	= &nv_generic_ops,
 		.private_data	= NV_PI_PRIV(nv_generic_interrupt, &nv_sht),
 	},
 	/* SWNCQ */
@@ -1559,15 +1581,24 @@ static int nv_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val)
 	return 0;
 }
 
-static int nv_noclassify_hardreset(struct ata_link *link, unsigned int *class,
-				   unsigned long deadline)
+static int nv_hardreset(struct ata_link *link, unsigned int *class,
+			unsigned long deadline)
 {
-	bool online;
-	int rc;
+	struct ata_eh_context *ehc = &link->eh_context;
 
-	rc = sata_link_hardreset(link, sata_deb_timing_hotplug, deadline,
-				 &online, NULL);
-	return online ? -EAGAIN : rc;
+	/* Do hardreset iff it's post-boot probing, please read the
+	 * comment above port ops for details.
+	 */
+	if (!(link->ap->pflags & ATA_PFLAG_LOADING) &&
+	    !ata_dev_enabled(link->device))
+		sata_link_hardreset(link, sata_deb_timing_hotplug, deadline,
+				    NULL, NULL);
+	else if (!(ehc->i.flags & ATA_EHI_QUIET))
+		ata_link_printk(link, KERN_INFO,
+				"nv: skipping hardreset on occupied port\n");
+
+	/* device signature acquisition is unreliable */
+	return -EAGAIN;
 }
 
 static void nv_nf2_freeze(struct ata_port *ap)
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index e67ce8e5caa5..030ec079b184 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -183,7 +183,7 @@ static struct scsi_host_template sil_sht = {
 };
 
 static struct ata_port_operations sil_ops = {
-	.inherits		= &ata_bmdma_port_ops,
+	.inherits		= &ata_bmdma32_port_ops,
 	.dev_config		= sil_dev_config,
 	.set_mode		= sil_set_mode,
 	.bmdma_setup            = sil_bmdma_setup,
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index eb05a3c82a9e..bbcf970068ad 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -193,6 +193,7 @@ enum {
 					  PDC_TIMER_MASK_INT,
 };
 
+#define ECC_ERASE_BUF_SZ (128 * 1024)
 
 struct pdc_port_priv {
 	u8			dimm_buf[(ATA_PRD_SZ * ATA_MAX_PRD) + 512];
@@ -1280,7 +1281,6 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
 {
 	int speed, size, length;
 	u32 addr, spd0, pci_status;
-	u32 tmp = 0;
 	u32 time_period = 0;
 	u32 tcount = 0;
 	u32 ticks = 0;
@@ -1395,14 +1395,17 @@ static unsigned int pdc20621_dimm_init(struct ata_host *host)
 	pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
 			  PDC_DIMM_SPD_TYPE, &spd0);
 	if (spd0 == 0x02) {
+		void *buf;
 		VPRINTK("Start ECC initialization\n");
 		addr = 0;
 		length = size * 1024 * 1024;
+		buf = kzalloc(ECC_ERASE_BUF_SZ, GFP_KERNEL);
 		while (addr < length) {
-			pdc20621_put_to_dimm(host, (void *) &tmp, addr,
-					     sizeof(u32));
-			addr += sizeof(u32);
+			pdc20621_put_to_dimm(host, buf, addr,
+					     ECC_ERASE_BUF_SZ);
+			addr += ECC_ERASE_BUF_SZ;
 		}
+		kfree(buf);
 		VPRINTK("Finish ECC initialization\n");
 	}
 	return 0;
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index f22ed6cc69f2..668dc234b8e2 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -3321,7 +3321,7 @@ static int DAC960_process_queue(DAC960_Controller_T *Controller, struct request_
 	DAC960_Command_T *Command;
 
    while(1) {
-	Request = elv_next_request(req_q);
+	Request = blk_peek_request(req_q);
 	if (!Request)
 		return 1;
 
@@ -3338,10 +3338,10 @@ static int DAC960_process_queue(DAC960_Controller_T *Controller, struct request_
 	}
 	Command->Completion = Request->end_io_data;
 	Command->LogicalDriveNumber = (long)Request->rq_disk->private_data;
-	Command->BlockNumber = Request->sector;
-	Command->BlockCount = Request->nr_sectors;
+	Command->BlockNumber = blk_rq_pos(Request);
+	Command->BlockCount = blk_rq_sectors(Request);
 	Command->Request = Request;
-	blkdev_dequeue_request(Request);
+	blk_start_request(Request);
 	Command->SegmentCount = blk_rq_map_sg(req_q,
 		  Command->Request, Command->cmd_sglist);
 	/* pci_map_sg MAY change the value of SegCount */
@@ -3431,7 +3431,7 @@ static void DAC960_queue_partial_rw(DAC960_Command_T *Command)
    * successfully as possible.
    */
   Command->SegmentCount = 1;
-  Command->BlockNumber = Request->sector;
+  Command->BlockNumber = blk_rq_pos(Request);
   Command->BlockCount = 1;
   DAC960_QueueReadWriteCommand(Command);
   return;
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index ddea8e485cc9..f42fa50d3550 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -412,7 +412,7 @@ config ATA_OVER_ETH
 
 config MG_DISK
 	tristate "mGine mflash, gflash support"
-	depends on ARM && ATA && GPIOLIB
+	depends on ARM && GPIOLIB
 	help
 	  mGine mFlash(gFlash) block device driver
 
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 8df436ff7068..9c6e5b0fe894 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -112,8 +112,6 @@ module_param(fd_def_df0, ulong, 0);
 MODULE_LICENSE("GPL");
 
 static struct request_queue *floppy_queue;
-#define QUEUE (floppy_queue)
-#define CURRENT elv_next_request(floppy_queue)
 
 /*
  *  Macros
@@ -1335,64 +1333,60 @@ static int get_track(int drive, int track)
 
 static void redo_fd_request(void)
 {
+	struct request *rq;
 	unsigned int cnt, block, track, sector;
 	int drive;
 	struct amiga_floppy_struct *floppy;
 	char *data;
 	unsigned long flags;
+	int err;
 
- repeat:
-	if (!CURRENT) {
+next_req:
+	rq = blk_fetch_request(floppy_queue);
+	if (!rq) {
 		/* Nothing left to do */
 		return;
 	}
 
-	floppy = CURRENT->rq_disk->private_data;
+	floppy = rq->rq_disk->private_data;
 	drive = floppy - unit;
 
+next_segment:
 	/* Here someone could investigate to be more efficient */
-	for (cnt = 0; cnt < CURRENT->current_nr_sectors; cnt++) { 
+	for (cnt = 0, err = 0; cnt < blk_rq_cur_sectors(rq); cnt++) {
 #ifdef DEBUG
 		printk("fd: sector %ld + %d requested for %s\n",
-		       CURRENT->sector,cnt,
-		       (rq_data_dir(CURRENT) == READ) ? "read" : "write");
+		       blk_rq_pos(rq), cnt,
+		       (rq_data_dir(rq) == READ) ? "read" : "write");
 #endif
-		block = CURRENT->sector + cnt;
+		block = blk_rq_pos(rq) + cnt;
 		if ((int)block > floppy->blocks) {
-			end_request(CURRENT, 0);
-			goto repeat;
+			err = -EIO;
+			break;
 		}
 
 		track = block / (floppy->dtype->sects * floppy->type->sect_mult);
 		sector = block % (floppy->dtype->sects * floppy->type->sect_mult);
-		data = CURRENT->buffer + 512 * cnt;
+		data = rq->buffer + 512 * cnt;
 #ifdef DEBUG
 		printk("access to track %d, sector %d, with buffer at "
 		       "0x%08lx\n", track, sector, data);
 #endif
 
-		if ((rq_data_dir(CURRENT) != READ) && (rq_data_dir(CURRENT) != WRITE)) {
-			printk(KERN_WARNING "do_fd_request: unknown command\n");
-			end_request(CURRENT, 0);
-			goto repeat;
-		}
 		if (get_track(drive, track) == -1) {
-			end_request(CURRENT, 0);
-			goto repeat;
+			err = -EIO;
+			break;
 		}
 
-		switch (rq_data_dir(CURRENT)) {
-		case READ:
+		if (rq_data_dir(rq) == READ) {
 			memcpy(data, floppy->trackbuf + sector * 512, 512);
-			break;
-
-		case WRITE:
+		} else {
 			memcpy(floppy->trackbuf + sector * 512, data, 512);
 
 			/* keep the drive spinning while writes are scheduled */
 			if (!fd_motor_on(drive)) {
-				end_request(CURRENT, 0);
-				goto repeat;
+				err = -EIO;
+				break;
 			}
 			/*
 			 * setup a callback to write the track buffer
@@ -1404,14 +1398,12 @@ static void redo_fd_request(void)
 		        /* reset the timer */
 			mod_timer (flush_track_timer + drive, jiffies + 1);
 			local_irq_restore(flags);
-			break;
 		}
 	}
-	CURRENT->nr_sectors -= CURRENT->current_nr_sectors;
-	CURRENT->sector += CURRENT->current_nr_sectors;
 
-	end_request(CURRENT, 1);
-	goto repeat;
+	if (__blk_end_request_cur(rq, err))
+		goto next_segment;
+	goto next_req;
 }
 
 static void do_fd_request(struct request_queue * q)
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 4234c11c1e4c..f5e7180d7f47 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -79,9 +79,7 @@
 #undef DEBUG
 
 static struct request_queue *floppy_queue;
-
-#define QUEUE (floppy_queue)
-#define CURRENT elv_next_request(floppy_queue)
+static struct request *fd_request;
 
 /* Disk types: DD, HD, ED */
 static struct atari_disk_type {
@@ -376,6 +374,12 @@ static DEFINE_TIMER(readtrack_timer, fd_readtrack_check, 0, 0);
 static DEFINE_TIMER(timeout_timer, fd_times_out, 0, 0);
 static DEFINE_TIMER(fd_timer, check_change, 0, 0);
 	
+static void fd_end_request_cur(int err)
+{
+	if (!__blk_end_request_cur(fd_request, err))
+		fd_request = NULL;
+}
+
 static inline void start_motor_off_timer(void)
 {
 	mod_timer(&motor_off_timer, jiffies + FD_MOTOR_OFF_DELAY);
@@ -606,15 +610,15 @@ static void fd_error( void )
 		return;
 	}
 
-	if (!CURRENT)
+	if (!fd_request)
 		return;
 
-	CURRENT->errors++;
-	if (CURRENT->errors >= MAX_ERRORS) {
+	fd_request->errors++;
+	if (fd_request->errors >= MAX_ERRORS) {
 		printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive );
-		end_request(CURRENT, 0);
+		fd_end_request_cur(-EIO);
 	}
-	else if (CURRENT->errors == RECALIBRATE_ERRORS) {
+	else if (fd_request->errors == RECALIBRATE_ERRORS) {
 		printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
 		if (SelectedDrive != -1)
 			SUD.track = -1;
@@ -725,16 +729,14 @@ static void do_fd_action( int drive )
 	    if (IS_BUFFERED( drive, ReqSide, ReqTrack )) {
 		if (ReqCmd == READ) {
 		    copy_buffer( SECTOR_BUFFER(ReqSector), ReqData );
-		    if (++ReqCnt < CURRENT->current_nr_sectors) {
+		    if (++ReqCnt < blk_rq_cur_sectors(fd_request)) {
 			/* read next sector */
 			setup_req_params( drive );
 			goto repeat;
 		    }
 		    else {
 			/* all sectors finished */
-			CURRENT->nr_sectors -= CURRENT->current_nr_sectors;
-			CURRENT->sector += CURRENT->current_nr_sectors;
-			end_request(CURRENT, 1);
+			fd_end_request_cur(0);
 			redo_fd_request();
 			return;
 		    }
@@ -1132,16 +1134,14 @@ static void fd_rwsec_done1(int status)
 		}
 	}
   
-	if (++ReqCnt < CURRENT->current_nr_sectors) {
+	if (++ReqCnt < blk_rq_cur_sectors(fd_request)) {
 		/* read next sector */
 		setup_req_params( SelectedDrive );
 		do_fd_action( SelectedDrive );
 	}
 	else {
 		/* all sectors finished */
-		CURRENT->nr_sectors -= CURRENT->current_nr_sectors;
-		CURRENT->sector += CURRENT->current_nr_sectors;
-		end_request(CURRENT, 1);
+		fd_end_request_cur(0);
 		redo_fd_request();
 	}
 	return;
@@ -1382,7 +1382,7 @@ static void setup_req_params( int drive )
 	ReqData = ReqBuffer + 512 * ReqCnt;
 
 	if (UseTrackbuffer)
-		read_track = (ReqCmd == READ && CURRENT->errors == 0);
+		read_track = (ReqCmd == READ && fd_request->errors == 0);
 	else
 		read_track = 0;
 
@@ -1396,25 +1396,27 @@ static void redo_fd_request(void)
 	int drive, type;
 	struct atari_floppy_struct *floppy;
 
-	DPRINT(("redo_fd_request: CURRENT=%p dev=%s CURRENT->sector=%ld\n",
-		CURRENT, CURRENT ? CURRENT->rq_disk->disk_name : "",
-		CURRENT ? CURRENT->sector : 0 ));
+	DPRINT(("redo_fd_request: fd_request=%p dev=%s fd_request->sector=%ld\n",
+		fd_request, fd_request ? fd_request->rq_disk->disk_name : "",
+		fd_request ? blk_rq_pos(fd_request) : 0 ));
 
 	IsFormatting = 0;
 
 repeat:
+	if (!fd_request) {
+		fd_request = blk_fetch_request(floppy_queue);
+		if (!fd_request)
+			goto the_end;
+	}
 
-	if (!CURRENT)
-		goto the_end;
-
-	floppy = CURRENT->rq_disk->private_data;
+	floppy = fd_request->rq_disk->private_data;
 	drive = floppy - unit;
 	type = floppy->type;
 	
 	if (!UD.connected) {
 		/* drive not connected */
 		printk(KERN_ERR "Unknown Device: fd%d\n", drive );
-		end_request(CURRENT, 0);
+		fd_end_request_cur(-EIO);
 		goto repeat;
 	}
 		
@@ -1430,12 +1432,12 @@ repeat:
 		/* user supplied disk type */
 		if (--type >= NUM_DISK_MINORS) {
 			printk(KERN_WARNING "fd%d: invalid disk format", drive );
-			end_request(CURRENT, 0);
+			fd_end_request_cur(-EIO);
 			goto repeat;
 		}
 		if (minor2disktype[type].drive_types > DriveType)  {
 			printk(KERN_WARNING "fd%d: unsupported disk format", drive );
-			end_request(CURRENT, 0);
+			fd_end_request_cur(-EIO);
 			goto repeat;
 		}
 		type = minor2disktype[type].index;
@@ -1444,8 +1446,8 @@ repeat:
 		UD.autoprobe = 0;
 	}
 	
-	if (CURRENT->sector + 1 > UDT->blocks) {
-		end_request(CURRENT, 0);
+	if (blk_rq_pos(fd_request) + 1 > UDT->blocks) {
+		fd_end_request_cur(-EIO);
 		goto repeat;
 	}
 
@@ -1453,9 +1455,9 @@ repeat:
 	del_timer( &motor_off_timer );
 		
 	ReqCnt = 0;
-	ReqCmd = rq_data_dir(CURRENT);
-	ReqBlock = CURRENT->sector;
-	ReqBuffer = CURRENT->buffer;
+	ReqCmd = rq_data_dir(fd_request);
+	ReqBlock = blk_rq_pos(fd_request);
+	ReqBuffer = fd_request->buffer;
 	setup_req_params( drive );
 	do_fd_action( drive );
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 5f7e64ba87e5..4bf8705b3ace 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -407,12 +407,7 @@ static int __init ramdisk_size(char *str)
 	rd_size = simple_strtol(str, NULL, 0);
 	return 1;
 }
-static int __init ramdisk_size2(char *str)
-{
-	return ramdisk_size(str);
-}
-__setup("ramdisk=", ramdisk_size);
-__setup("ramdisk_size=", ramdisk_size2);
+__setup("ramdisk_size=", ramdisk_size);
 #endif
 
 /*
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 4d4d5e0d3fa6..b22cec97ea19 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -180,11 +180,13 @@ static void __devinit cciss_interrupt_mode(ctlr_info_t *, struct pci_dev *,
 					   __u32);
 static void start_io(ctlr_info_t *h);
 static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size,
-		   unsigned int use_unit_num, unsigned int log_unit,
 		   __u8 page_code, unsigned char *scsi3addr, int cmd_type);
 static int sendcmd_withirq(__u8 cmd, int ctlr, void *buff, size_t size,
-			   unsigned int use_unit_num, unsigned int log_unit,
-			   __u8 page_code, int cmd_type);
+			__u8 page_code, unsigned char scsi3addr[],
+			int cmd_type);
+static int sendcmd_withirq_core(ctlr_info_t *h, CommandList_struct *c,
+	int attempt_retry);
+static int process_sendcmd_error(ctlr_info_t *h, CommandList_struct *c);
 
 static void fail_all_cmds(unsigned long ctlr);
 static int scan_thread(void *data);
@@ -437,6 +439,194 @@ static void __devinit cciss_procinit(int i)
 }
 #endif				/* CONFIG_PROC_FS */
 
+#define MAX_PRODUCT_NAME_LEN 19
+
+#define to_hba(n) container_of(n, struct ctlr_info, dev)
+#define to_drv(n) container_of(n, drive_info_struct, dev)
+
+static struct device_type cciss_host_type = {
+	.name		= "cciss_host",
+};
+
+static ssize_t dev_show_unique_id(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	drive_info_struct *drv = to_drv(dev);
+	struct ctlr_info *h = to_hba(drv->dev.parent);
+	__u8 sn[16];
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
+	if (h->busy_configuring)
+		ret = -EBUSY;
+	else
+		memcpy(sn, drv->serial_no, sizeof(sn));
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
+
+	if (ret)
+		return ret;
+	else
+		return snprintf(buf, 16 * 2 + 2,
+				"%02X%02X%02X%02X%02X%02X%02X%02X"
+				"%02X%02X%02X%02X%02X%02X%02X%02X\n",
+				sn[0], sn[1], sn[2], sn[3],
+				sn[4], sn[5], sn[6], sn[7],
+				sn[8], sn[9], sn[10], sn[11],
+				sn[12], sn[13], sn[14], sn[15]);
+}
+DEVICE_ATTR(unique_id, S_IRUGO, dev_show_unique_id, NULL);
+
+static ssize_t dev_show_vendor(struct device *dev,
+			       struct device_attribute *attr,
+			       char *buf)
+{
+	drive_info_struct *drv = to_drv(dev);
+	struct ctlr_info *h = to_hba(drv->dev.parent);
+	char vendor[VENDOR_LEN + 1];
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
+	if (h->busy_configuring)
+		ret = -EBUSY;
+	else
+		memcpy(vendor, drv->vendor, VENDOR_LEN + 1);
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
+
+	if (ret)
+		return ret;
+	else
+		return snprintf(buf, sizeof(vendor) + 1, "%s\n", drv->vendor);
+}
+DEVICE_ATTR(vendor, S_IRUGO, dev_show_vendor, NULL);
+
+static ssize_t dev_show_model(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	drive_info_struct *drv = to_drv(dev);
+	struct ctlr_info *h = to_hba(drv->dev.parent);
+	char model[MODEL_LEN + 1];
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
+	if (h->busy_configuring)
+		ret = -EBUSY;
+	else
+		memcpy(model, drv->model, MODEL_LEN + 1);
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
+
+	if (ret)
+		return ret;
+	else
+		return snprintf(buf, sizeof(model) + 1, "%s\n", drv->model);
+}
+DEVICE_ATTR(model, S_IRUGO, dev_show_model, NULL);
+
+static ssize_t dev_show_rev(struct device *dev,
+			    struct device_attribute *attr,
+			    char *buf)
+{
+	drive_info_struct *drv = to_drv(dev);
+	struct ctlr_info *h = to_hba(drv->dev.parent);
+	char rev[REV_LEN + 1];
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
+	if (h->busy_configuring)
+		ret = -EBUSY;
+	else
+		memcpy(rev, drv->rev, REV_LEN + 1);
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
+
+	if (ret)
+		return ret;
+	else
+		return snprintf(buf, sizeof(rev) + 1, "%s\n", drv->rev);
+}
+DEVICE_ATTR(rev, S_IRUGO, dev_show_rev, NULL);
+
+static struct attribute *cciss_dev_attrs[] = {
+	&dev_attr_unique_id.attr,
+	&dev_attr_model.attr,
+	&dev_attr_vendor.attr,
+	&dev_attr_rev.attr,
+	NULL
+};
+
+static struct attribute_group cciss_dev_attr_group = {
+	.attrs = cciss_dev_attrs,
+};
+
+static struct attribute_group *cciss_dev_attr_groups[] = {
+	&cciss_dev_attr_group,
+	NULL
+};
+
+static struct device_type cciss_dev_type = {
+	.name		= "cciss_device",
+	.groups		= cciss_dev_attr_groups,
+};
+
+static struct bus_type cciss_bus_type = {
+	.name		= "cciss",
+};
+
+
+/*
+ * Initialize sysfs entry for each controller.  This sets up and registers
+ * the 'cciss#' directory for each individual controller under
+ * /sys/bus/pci/devices/<dev>/.
+ */
+static int cciss_create_hba_sysfs_entry(struct ctlr_info *h)
+{
+	device_initialize(&h->dev);
+	h->dev.type = &cciss_host_type;
+	h->dev.bus = &cciss_bus_type;
+	dev_set_name(&h->dev, "%s", h->devname);
+	h->dev.parent = &h->pdev->dev;
+
+	return device_add(&h->dev);
+}
+
+/*
+ * Remove sysfs entries for an hba.
+ */
+static void cciss_destroy_hba_sysfs_entry(struct ctlr_info *h)
+{
+	device_del(&h->dev);
+}
+
+/*
+ * Initialize sysfs for each logical drive.  This sets up and registers
+ * the 'c#d#' directory for each individual logical drive under
+ * /sys/bus/pci/devices/<dev/ccis#/. We also create a link from
+ * /sys/block/cciss!c#d# to this entry.
+ */
+static int cciss_create_ld_sysfs_entry(struct ctlr_info *h,
+				       drive_info_struct *drv,
+				       int drv_index)
+{
+	device_initialize(&drv->dev);
+	drv->dev.type = &cciss_dev_type;
+	drv->dev.bus = &cciss_bus_type;
+	dev_set_name(&drv->dev, "c%dd%d", h->ctlr, drv_index);
+	drv->dev.parent = &h->dev;
+	return device_add(&drv->dev);
+}
+
+/*
+ * Remove sysfs entries for a logical drive.
+ */
+static void cciss_destroy_ld_sysfs_entry(drive_info_struct *drv)
+{
+	device_del(&drv->dev);
+}
+
 /*
  * For operations that cannot sleep, a command block is allocated at init,
  * and managed by cmd_alloc() and cmd_free() using a simple bitmap to track
@@ -1299,7 +1489,6 @@ static void cciss_softirq_done(struct request *rq)
 {
 	CommandList_struct *cmd = rq->completion_data;
 	ctlr_info_t *h = hba[cmd->ctlr];
-	unsigned int nr_bytes;
 	unsigned long flags;
 	u64bit temp64;
 	int i, ddir;
@@ -1321,15 +1510,11 @@ static void cciss_softirq_done(struct request *rq)
 	printk("Done with %p\n", rq);
 #endif				/* CCISS_DEBUG */
 
-	/*
-	 * Store the full size and set the residual count for pc requests
-	 */
-	nr_bytes = blk_rq_bytes(rq);
+	/* set the residual count for pc requests */
 	if (blk_pc_request(rq))
-		rq->data_len = cmd->err_info->ResidualCnt;
+		rq->resid_len = cmd->err_info->ResidualCnt;
 
-	if (blk_end_request(rq, (rq->errors == 0) ? 0 : -EIO, nr_bytes))
-		BUG();
+	blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO);
 
 	spin_lock_irqsave(&h->lock, flags);
 	cmd_free(h, cmd, 1);
@@ -1337,6 +1522,56 @@ static void cciss_softirq_done(struct request *rq)
 	spin_unlock_irqrestore(&h->lock, flags);
 }
 
+static void log_unit_to_scsi3addr(ctlr_info_t *h, unsigned char scsi3addr[],
+	uint32_t log_unit)
+{
+	log_unit = h->drv[log_unit].LunID & 0x03fff;
+	memset(&scsi3addr[4], 0, 4);
+	memcpy(&scsi3addr[0], &log_unit, 4);
+	scsi3addr[3] |= 0x40;
+}
+
+/* This function gets the SCSI vendor, model, and revision of a logical drive
+ * via the inquiry page 0.  Model, vendor, and rev are set to empty strings if
+ * they cannot be read.
+ */
+static void cciss_get_device_descr(int ctlr, int logvol, int withirq,
+				   char *vendor, char *model, char *rev)
+{
+	int rc;
+	InquiryData_struct *inq_buf;
+	unsigned char scsi3addr[8];
+
+	*vendor = '\0';
+	*model = '\0';
+	*rev = '\0';
+
+	inq_buf = kzalloc(sizeof(InquiryData_struct), GFP_KERNEL);
+	if (!inq_buf)
+		return;
+
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
+	if (withirq)
+		rc = sendcmd_withirq(CISS_INQUIRY, ctlr, inq_buf,
+			     sizeof(InquiryData_struct), 0,
+				scsi3addr, TYPE_CMD);
+	else
+		rc = sendcmd(CISS_INQUIRY, ctlr, inq_buf,
+			     sizeof(InquiryData_struct), 0,
+				scsi3addr, TYPE_CMD);
+	if (rc == IO_OK) {
+		memcpy(vendor, &inq_buf->data_byte[8], VENDOR_LEN);
+		vendor[VENDOR_LEN] = '\0';
+		memcpy(model, &inq_buf->data_byte[16], MODEL_LEN);
+		model[MODEL_LEN] = '\0';
+		memcpy(rev, &inq_buf->data_byte[32], REV_LEN);
+		rev[REV_LEN] = '\0';
+	}
+
+	kfree(inq_buf);
+	return;
+}
+
 /* This function gets the serial number of a logical drive via
  * inquiry page 0x83.  Serial no. is 16 bytes.  If the serial
  * number cannot be had, for whatever reason, 16 bytes of 0xff
@@ -1348,6 +1583,7 @@ static void cciss_get_serial_no(int ctlr, int logvol, int withirq,
 #define PAGE_83_INQ_BYTES 64
 	int rc;
 	unsigned char *buf;
+	unsigned char scsi3addr[8];
 
 	if (buflen > 16)
 		buflen = 16;
@@ -1356,12 +1592,13 @@ static void cciss_get_serial_no(int ctlr, int logvol, int withirq,
 	if (!buf)
 		return;
 	memset(serial_no, 0, buflen);
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
 	if (withirq)
 		rc = sendcmd_withirq(CISS_INQUIRY, ctlr, buf,
-			PAGE_83_INQ_BYTES, 1, logvol, 0x83, TYPE_CMD);
+			PAGE_83_INQ_BYTES, 0x83, scsi3addr, TYPE_CMD);
 	else
 		rc = sendcmd(CISS_INQUIRY, ctlr, buf,
-			PAGE_83_INQ_BYTES, 1, logvol, 0x83, NULL, TYPE_CMD);
+			PAGE_83_INQ_BYTES, 0x83, scsi3addr, TYPE_CMD);
 	if (rc == IO_OK)
 		memcpy(serial_no, &buf[8], buflen);
 	kfree(buf);
@@ -1377,7 +1614,7 @@ static void cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
 	disk->first_minor = drv_index << NWD_SHIFT;
 	disk->fops = &cciss_fops;
 	disk->private_data = &h->drv[drv_index];
-	disk->driverfs_dev = &h->pdev->dev;
+	disk->driverfs_dev = &h->drv[drv_index].dev;
 
 	/* Set up queue information */
 	blk_queue_bounce_limit(disk->queue, h->pdev->dma_mask);
@@ -1394,8 +1631,8 @@ static void cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
 
 	disk->queue->queuedata = h;
 
-	blk_queue_hardsect_size(disk->queue,
-				h->drv[drv_index].block_size);
+	blk_queue_logical_block_size(disk->queue,
+				     h->drv[drv_index].block_size);
 
 	/* Make sure all queue data is written out before */
 	/* setting h->drv[drv_index].queue, as setting this */
@@ -1468,6 +1705,8 @@ static void cciss_update_drive_info(int ctlr, int drv_index, int first_time)
 	drvinfo->block_size = block_size;
 	drvinfo->nr_blocks = total_size + 1;
 
+	cciss_get_device_descr(ctlr, drv_index, 1, drvinfo->vendor,
+				drvinfo->model, drvinfo->rev);
 	cciss_get_serial_no(ctlr, drv_index, 1, drvinfo->serial_no,
 			sizeof(drvinfo->serial_no));
 
@@ -1517,6 +1756,9 @@ static void cciss_update_drive_info(int ctlr, int drv_index, int first_time)
 	h->drv[drv_index].cylinders = drvinfo->cylinders;
 	h->drv[drv_index].raid_level = drvinfo->raid_level;
 	memcpy(h->drv[drv_index].serial_no, drvinfo->serial_no, 16);
+	memcpy(h->drv[drv_index].vendor, drvinfo->vendor, VENDOR_LEN + 1);
+	memcpy(h->drv[drv_index].model, drvinfo->model, MODEL_LEN + 1);
+	memcpy(h->drv[drv_index].rev, drvinfo->rev, REV_LEN + 1);
 
 	++h->num_luns;
 	disk = h->gendisk[drv_index];
@@ -1591,6 +1833,8 @@ static int cciss_add_gendisk(ctlr_info_t *h, __u32 lunid, int controller_node)
 		}
 	}
 	h->drv[drv_index].LunID = lunid;
+	if (cciss_create_ld_sysfs_entry(h, &h->drv[drv_index], drv_index))
+		goto err_free_disk;
 
 	/* Don't need to mark this busy because nobody */
 	/* else knows about this disk yet to contend */
@@ -1598,6 +1842,11 @@ static int cciss_add_gendisk(ctlr_info_t *h, __u32 lunid, int controller_node)
 	h->drv[drv_index].busy_configuring = 0;
 	wmb();
 	return drv_index;
+
+err_free_disk:
+	put_disk(h->gendisk[drv_index]);
+	h->gendisk[drv_index] = NULL;
+	return -1;
 }
 
 /* This is for the special case of a controller which
@@ -1668,8 +1917,8 @@ static int rebuild_lun_table(ctlr_info_t *h, int first_time)
 		goto mem_msg;
 
 	return_code = sendcmd_withirq(CISS_REPORT_LOG, ctlr, ld_buff,
-				      sizeof(ReportLunData_struct), 0,
-				      0, 0, TYPE_CMD);
+				      sizeof(ReportLunData_struct),
+				      0, CTLR_LUNID, TYPE_CMD);
 
 	if (return_code == IO_OK)
 		listlength = be32_to_cpu(*(__be32 *) ld_buff->LUNListLength);
@@ -1718,6 +1967,7 @@ static int rebuild_lun_table(ctlr_info_t *h, int first_time)
 			h->drv[i].busy_configuring = 1;
 			spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
 			return_code = deregister_disk(h, i, 1);
+			cciss_destroy_ld_sysfs_entry(&h->drv[i]);
 			h->drv[i].busy_configuring = 0;
 		}
 	}
@@ -1877,11 +2127,9 @@ static int deregister_disk(ctlr_info_t *h, int drv_index,
 	return 0;
 }
 
-static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_t size, unsigned int use_unit_num,	/* 0: address the controller,
-															   1: address logical volume log_unit,
-															   2: periph device address is scsi3addr */
-		    unsigned int log_unit, __u8 page_code,
-		    unsigned char *scsi3addr, int cmd_type)
+static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff,
+		size_t size, __u8 page_code, unsigned char *scsi3addr,
+		int cmd_type)
 {
 	ctlr_info_t *h = hba[ctlr];
 	u64bit buff_dma_handle;
@@ -1897,27 +2145,12 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 		c->Header.SGTotal = 0;
 	}
 	c->Header.Tag.lower = c->busaddr;
+	memcpy(c->Header.LUN.LunAddrBytes, scsi3addr, 8);
 
 	c->Request.Type.Type = cmd_type;
 	if (cmd_type == TYPE_CMD) {
 		switch (cmd) {
 		case CISS_INQUIRY:
-			/* If the logical unit number is 0 then, this is going
-			   to controller so It's a physical command
-			   mode = 0 target = 0.  So we have nothing to write.
-			   otherwise, if use_unit_num == 1,
-			   mode = 1(volume set addressing) target = LUNID
-			   otherwise, if use_unit_num == 2,
-			   mode = 0(periph dev addr) target = scsi3addr */
-			if (use_unit_num == 1) {
-				c->Header.LUN.LogDev.VolId =
-				    h->drv[log_unit].LunID;
-				c->Header.LUN.LogDev.Mode = 1;
-			} else if (use_unit_num == 2) {
-				memcpy(c->Header.LUN.LunAddrBytes, scsi3addr,
-				       8);
-				c->Header.LUN.LogDev.Mode = 0;
-			}
 			/* are we trying to read a vital product page */
 			if (page_code != 0) {
 				c->Request.CDB[1] = 0x01;
@@ -1947,8 +2180,6 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 			break;
 
 		case CCISS_READ_CAPACITY:
-			c->Header.LUN.LogDev.VolId = h->drv[log_unit].LunID;
-			c->Header.LUN.LogDev.Mode = 1;
 			c->Request.CDBLen = 10;
 			c->Request.Type.Attribute = ATTR_SIMPLE;
 			c->Request.Type.Direction = XFER_READ;
@@ -1956,8 +2187,6 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 			c->Request.CDB[0] = cmd;
 			break;
 		case CCISS_READ_CAPACITY_16:
-			c->Header.LUN.LogDev.VolId = h->drv[log_unit].LunID;
-			c->Header.LUN.LogDev.Mode = 1;
 			c->Request.CDBLen = 16;
 			c->Request.Type.Attribute = ATTR_SIMPLE;
 			c->Request.Type.Direction = XFER_READ;
@@ -1979,6 +2208,12 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 			c->Request.CDB[0] = BMIC_WRITE;
 			c->Request.CDB[6] = BMIC_CACHE_FLUSH;
 			break;
+		case TEST_UNIT_READY:
+			c->Request.CDBLen = 6;
+			c->Request.Type.Attribute = ATTR_SIMPLE;
+			c->Request.Type.Direction = XFER_NONE;
+			c->Request.Timeout = 0;
+			break;
 		default:
 			printk(KERN_WARNING
 			       "cciss%d:  Unknown Command 0x%c\n", ctlr, cmd);
@@ -1997,13 +2232,13 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 			memcpy(&c->Request.CDB[4], buff, 8);
 			break;
 		case 1:	/* RESET message */
-			c->Request.CDBLen = 12;
+			c->Request.CDBLen = 16;
 			c->Request.Type.Attribute = ATTR_SIMPLE;
-			c->Request.Type.Direction = XFER_WRITE;
+			c->Request.Type.Direction = XFER_NONE;
 			c->Request.Timeout = 0;
 			memset(&c->Request.CDB[0], 0, sizeof(c->Request.CDB));
 			c->Request.CDB[0] = cmd;	/* reset */
-			c->Request.CDB[1] = 0x04;	/* reset a LUN */
+			c->Request.CDB[1] = 0x03;	/* reset a target */
 			break;
 		case 3:	/* No-Op message */
 			c->Request.CDBLen = 1;
@@ -2035,114 +2270,152 @@ static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff, size_
 	return status;
 }
 
-static int sendcmd_withirq(__u8 cmd,
-			   int ctlr,
-			   void *buff,
-			   size_t size,
-			   unsigned int use_unit_num,
-			   unsigned int log_unit, __u8 page_code, int cmd_type)
+static int check_target_status(ctlr_info_t *h, CommandList_struct *c)
 {
-	ctlr_info_t *h = hba[ctlr];
-	CommandList_struct *c;
+	switch (c->err_info->ScsiStatus) {
+	case SAM_STAT_GOOD:
+		return IO_OK;
+	case SAM_STAT_CHECK_CONDITION:
+		switch (0xf & c->err_info->SenseInfo[2]) {
+		case 0: return IO_OK; /* no sense */
+		case 1: return IO_OK; /* recovered error */
+		default:
+			printk(KERN_WARNING "cciss%d: cmd 0x%02x "
+				"check condition, sense key = 0x%02x\n",
+				h->ctlr, c->Request.CDB[0],
+				c->err_info->SenseInfo[2]);
+		}
+		break;
+	default:
+		printk(KERN_WARNING "cciss%d: cmd 0x%02x"
+			"scsi status = 0x%02x\n", h->ctlr,
+			c->Request.CDB[0], c->err_info->ScsiStatus);
+		break;
+	}
+	return IO_ERROR;
+}
+
+static int process_sendcmd_error(ctlr_info_t *h, CommandList_struct *c)
+{
+	int return_status = IO_OK;
+
+	if (c->err_info->CommandStatus == CMD_SUCCESS)
+		return IO_OK;
+
+	switch (c->err_info->CommandStatus) {
+	case CMD_TARGET_STATUS:
+		return_status = check_target_status(h, c);
+		break;
+	case CMD_DATA_UNDERRUN:
+	case CMD_DATA_OVERRUN:
+		/* expected for inquiry and report lun commands */
+		break;
+	case CMD_INVALID:
+		printk(KERN_WARNING "cciss: cmd 0x%02x is "
+		       "reported invalid\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_PROTOCOL_ERR:
+		printk(KERN_WARNING "cciss: cmd 0x%02x has "
+		       "protocol error \n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_HARDWARE_ERR:
+		printk(KERN_WARNING "cciss: cmd 0x%02x had "
+		       " hardware error\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_CONNECTION_LOST:
+		printk(KERN_WARNING "cciss: cmd 0x%02x had "
+		       "connection lost\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_ABORTED:
+		printk(KERN_WARNING "cciss: cmd 0x%02x was "
+		       "aborted\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_ABORT_FAILED:
+		printk(KERN_WARNING "cciss: cmd 0x%02x reports "
+		       "abort failed\n", c->Request.CDB[0]);
+		return_status = IO_ERROR;
+		break;
+	case CMD_UNSOLICITED_ABORT:
+		printk(KERN_WARNING
+		       "cciss%d: unsolicited abort 0x%02x\n", h->ctlr,
+			c->Request.CDB[0]);
+		return_status = IO_NEEDS_RETRY;
+		break;
+	default:
+		printk(KERN_WARNING "cciss: cmd 0x%02x returned "
+		       "unknown status %x\n", c->Request.CDB[0],
+		       c->err_info->CommandStatus);
+		return_status = IO_ERROR;
+	}
+	return return_status;
+}
+
+static int sendcmd_withirq_core(ctlr_info_t *h, CommandList_struct *c,
+	int attempt_retry)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
 	u64bit buff_dma_handle;
 	unsigned long flags;
-	int return_status;
-	DECLARE_COMPLETION_ONSTACK(wait);
+	int return_status = IO_OK;
 
-	if ((c = cmd_alloc(h, 0)) == NULL)
-		return -ENOMEM;
-	return_status = fill_cmd(c, cmd, ctlr, buff, size, use_unit_num,
-				 log_unit, page_code, NULL, cmd_type);
-	if (return_status != IO_OK) {
-		cmd_free(h, c, 0);
-		return return_status;
-	}
-      resend_cmd2:
+resend_cmd2:
 	c->waiting = &wait;
-
 	/* Put the request on the tail of the queue and send it */
-	spin_lock_irqsave(CCISS_LOCK(ctlr), flags);
+	spin_lock_irqsave(CCISS_LOCK(h->ctlr), flags);
 	addQ(&h->reqQ, c);
 	h->Qdepth++;
 	start_io(h);
-	spin_unlock_irqrestore(CCISS_LOCK(ctlr), flags);
+	spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags);
 
 	wait_for_completion(&wait);
 
-	if (c->err_info->CommandStatus != 0) {	/* an error has occurred */
-		switch (c->err_info->CommandStatus) {
-		case CMD_TARGET_STATUS:
-			printk(KERN_WARNING "cciss: cmd %p has "
-			       " completed with errors\n", c);
-			if (c->err_info->ScsiStatus) {
-				printk(KERN_WARNING "cciss: cmd %p "
-				       "has SCSI Status = %x\n",
-				       c, c->err_info->ScsiStatus);
-			}
+	if (c->err_info->CommandStatus == 0 || !attempt_retry)
+		goto command_done;
 
-			break;
-		case CMD_DATA_UNDERRUN:
-		case CMD_DATA_OVERRUN:
-			/* expected for inquire and report lun commands */
-			break;
-		case CMD_INVALID:
-			printk(KERN_WARNING "cciss: Cmd %p is "
-			       "reported invalid\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_PROTOCOL_ERR:
-			printk(KERN_WARNING "cciss: cmd %p has "
-			       "protocol error \n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_HARDWARE_ERR:
-			printk(KERN_WARNING "cciss: cmd %p had "
-			       " hardware error\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_CONNECTION_LOST:
-			printk(KERN_WARNING "cciss: cmd %p had "
-			       "connection lost\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_ABORTED:
-			printk(KERN_WARNING "cciss: cmd %p was "
-			       "aborted\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_ABORT_FAILED:
-			printk(KERN_WARNING "cciss: cmd %p reports "
-			       "abort failed\n", c);
-			return_status = IO_ERROR;
-			break;
-		case CMD_UNSOLICITED_ABORT:
-			printk(KERN_WARNING
-			       "cciss%d: unsolicited abort %p\n", ctlr, c);
-			if (c->retry_count < MAX_CMD_RETRIES) {
-				printk(KERN_WARNING
-				       "cciss%d: retrying %p\n", ctlr, c);
-				c->retry_count++;
-				/* erase the old error information */
-				memset(c->err_info, 0,
-				       sizeof(ErrorInfo_struct));
-				return_status = IO_OK;
-				INIT_COMPLETION(wait);
-				goto resend_cmd2;
-			}
-			return_status = IO_ERROR;
-			break;
-		default:
-			printk(KERN_WARNING "cciss: cmd %p returned "
-			       "unknown status %x\n", c,
-			       c->err_info->CommandStatus);
-			return_status = IO_ERROR;
-		}
+	return_status = process_sendcmd_error(h, c);
+
+	if (return_status == IO_NEEDS_RETRY &&
+		c->retry_count < MAX_CMD_RETRIES) {
+		printk(KERN_WARNING "cciss%d: retrying 0x%02x\n", h->ctlr,
+			c->Request.CDB[0]);
+		c->retry_count++;
+		/* erase the old error information */
+		memset(c->err_info, 0, sizeof(ErrorInfo_struct));
+		return_status = IO_OK;
+		INIT_COMPLETION(wait);
+		goto resend_cmd2;
 	}
+
+command_done:
 	/* unlock the buffers from DMA */
 	buff_dma_handle.val32.lower = c->SG[0].Addr.lower;
 	buff_dma_handle.val32.upper = c->SG[0].Addr.upper;
 	pci_unmap_single(h->pdev, (dma_addr_t) buff_dma_handle.val,
 			 c->SG[0].Len, PCI_DMA_BIDIRECTIONAL);
+	return return_status;
+}
+
+static int sendcmd_withirq(__u8 cmd, int ctlr, void *buff, size_t size,
+			   __u8 page_code, unsigned char scsi3addr[],
+			int cmd_type)
+{
+	ctlr_info_t *h = hba[ctlr];
+	CommandList_struct *c;
+	int return_status;
+
+	c = cmd_alloc(h, 0);
+	if (!c)
+		return -ENOMEM;
+	return_status = fill_cmd(c, cmd, ctlr, buff, size, page_code,
+		scsi3addr, cmd_type);
+	if (return_status == IO_OK)
+		return_status = sendcmd_withirq_core(h, c, 1);
+
 	cmd_free(h, c, 0);
 	return return_status;
 }
@@ -2155,15 +2428,17 @@ static void cciss_geometry_inquiry(int ctlr, int logvol,
 {
 	int return_code;
 	unsigned long t;
+	unsigned char scsi3addr[8];
 
 	memset(inq_buff, 0, sizeof(InquiryData_struct));
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
 	if (withirq)
 		return_code = sendcmd_withirq(CISS_INQUIRY, ctlr,
-					      inq_buff, sizeof(*inq_buff), 1,
-					      logvol, 0xC1, TYPE_CMD);
+					      inq_buff, sizeof(*inq_buff),
+					      0xC1, scsi3addr, TYPE_CMD);
 	else
 		return_code = sendcmd(CISS_INQUIRY, ctlr, inq_buff,
-				      sizeof(*inq_buff), 1, logvol, 0xC1, NULL,
+				      sizeof(*inq_buff), 0xC1, scsi3addr,
 				      TYPE_CMD);
 	if (return_code == IO_OK) {
 		if (inq_buff->data_byte[8] == 0xFF) {
@@ -2204,6 +2479,7 @@ cciss_read_capacity(int ctlr, int logvol, int withirq, sector_t *total_size,
 {
 	ReadCapdata_struct *buf;
 	int return_code;
+	unsigned char scsi3addr[8];
 
 	buf = kzalloc(sizeof(ReadCapdata_struct), GFP_KERNEL);
 	if (!buf) {
@@ -2211,14 +2487,15 @@ cciss_read_capacity(int ctlr, int logvol, int withirq, sector_t *total_size,
 		return;
 	}
 
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
 	if (withirq)
 		return_code = sendcmd_withirq(CCISS_READ_CAPACITY,
 				ctlr, buf, sizeof(ReadCapdata_struct),
-					1, logvol, 0, TYPE_CMD);
+					0, scsi3addr, TYPE_CMD);
 	else
 		return_code = sendcmd(CCISS_READ_CAPACITY,
 				ctlr, buf, sizeof(ReadCapdata_struct),
-					1, logvol, 0, NULL, TYPE_CMD);
+					0, scsi3addr, TYPE_CMD);
 	if (return_code == IO_OK) {
 		*total_size = be32_to_cpu(*(__be32 *) buf->total_size);
 		*block_size = be32_to_cpu(*(__be32 *) buf->block_size);
@@ -2238,6 +2515,7 @@ cciss_read_capacity_16(int ctlr, int logvol, int withirq, sector_t *total_size,
 {
 	ReadCapdata_struct_16 *buf;
 	int return_code;
+	unsigned char scsi3addr[8];
 
 	buf = kzalloc(sizeof(ReadCapdata_struct_16), GFP_KERNEL);
 	if (!buf) {
@@ -2245,15 +2523,16 @@ cciss_read_capacity_16(int ctlr, int logvol, int withirq, sector_t *total_size,
 		return;
 	}
 
+	log_unit_to_scsi3addr(hba[ctlr], scsi3addr, logvol);
 	if (withirq) {
 		return_code = sendcmd_withirq(CCISS_READ_CAPACITY_16,
 			ctlr, buf, sizeof(ReadCapdata_struct_16),
-				1, logvol, 0, TYPE_CMD);
+				0, scsi3addr, TYPE_CMD);
 	}
 	else {
 		return_code = sendcmd(CCISS_READ_CAPACITY_16,
 			ctlr, buf, sizeof(ReadCapdata_struct_16),
-				1, logvol, 0, NULL, TYPE_CMD);
+				0, scsi3addr, TYPE_CMD);
 	}
 	if (return_code == IO_OK) {
 		*total_size = be64_to_cpu(*(__be64 *) buf->total_size);
@@ -2303,7 +2582,7 @@ static int cciss_revalidate(struct gendisk *disk)
 	cciss_geometry_inquiry(h->ctlr, logvol, 1, total_size, block_size,
 			       inq_buff, drv);
 
-	blk_queue_hardsect_size(drv->queue, drv->block_size);
+	blk_queue_logical_block_size(drv->queue, drv->block_size);
 	set_capacity(disk, drv->nr_blocks);
 
 	kfree(inq_buff);
@@ -2333,86 +2612,21 @@ static unsigned long pollcomplete(int ctlr)
 	return 1;
 }
 
-static int add_sendcmd_reject(__u8 cmd, int ctlr, unsigned long complete)
-{
-	/* We get in here if sendcmd() is polling for completions
-	   and gets some command back that it wasn't expecting --
-	   something other than that which it just sent down.
-	   Ordinarily, that shouldn't happen, but it can happen when
-	   the scsi tape stuff gets into error handling mode, and
-	   starts using sendcmd() to try to abort commands and
-	   reset tape drives.  In that case, sendcmd may pick up
-	   completions of commands that were sent to logical drives
-	   through the block i/o system, or cciss ioctls completing, etc.
-	   In that case, we need to save those completions for later
-	   processing by the interrupt handler.
-	 */
-
-#ifdef CONFIG_CISS_SCSI_TAPE
-	struct sendcmd_reject_list *srl = &hba[ctlr]->scsi_rejects;
-
-	/* If it's not the scsi tape stuff doing error handling, (abort */
-	/* or reset) then we don't expect anything weird. */
-	if (cmd != CCISS_RESET_MSG && cmd != CCISS_ABORT_MSG) {
-#endif
-		printk(KERN_WARNING "cciss cciss%d: SendCmd "
-		       "Invalid command list address returned! (%lx)\n",
-		       ctlr, complete);
-		/* not much we can do. */
-#ifdef CONFIG_CISS_SCSI_TAPE
-		return 1;
-	}
-
-	/* We've sent down an abort or reset, but something else
-	   has completed */
-	if (srl->ncompletions >= (hba[ctlr]->nr_cmds + 2)) {
-		/* Uh oh.  No room to save it for later... */
-		printk(KERN_WARNING "cciss%d: Sendcmd: Invalid command addr, "
-		       "reject list overflow, command lost!\n", ctlr);
-		return 1;
-	}
-	/* Save it for later */
-	srl->complete[srl->ncompletions] = complete;
-	srl->ncompletions++;
-#endif
-	return 0;
-}
-
-/*
- * Send a command to the controller, and wait for it to complete.
- * Only used at init time.
+/* Send command c to controller h and poll for it to complete.
+ * Turns interrupts off on the board.  Used at driver init time
+ * and during SCSI error recovery.
  */
-static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size, unsigned int use_unit_num,	/* 0: address the controller,
-												   1: address logical volume log_unit,
-												   2: periph device address is scsi3addr */
-		   unsigned int log_unit,
-		   __u8 page_code, unsigned char *scsi3addr, int cmd_type)
+static int sendcmd_core(ctlr_info_t *h, CommandList_struct *c)
 {
-	CommandList_struct *c;
 	int i;
 	unsigned long complete;
-	ctlr_info_t *info_p = hba[ctlr];
+	int status = IO_ERROR;
 	u64bit buff_dma_handle;
-	int status, done = 0;
 
-	if ((c = cmd_alloc(info_p, 1)) == NULL) {
-		printk(KERN_WARNING "cciss: unable to get memory");
-		return IO_ERROR;
-	}
-	status = fill_cmd(c, cmd, ctlr, buff, size, use_unit_num,
-			  log_unit, page_code, scsi3addr, cmd_type);
-	if (status != IO_OK) {
-		cmd_free(info_p, c, 1);
-		return status;
-	}
-      resend_cmd1:
-	/*
-	 * Disable interrupt
-	 */
-#ifdef CCISS_DEBUG
-	printk(KERN_DEBUG "cciss: turning intr off\n");
-#endif				/* CCISS_DEBUG */
-	info_p->access.set_intr_mask(info_p, CCISS_INTR_OFF);
+resend_cmd1:
+
+	/* Disable interrupt on the board. */
+	h->access.set_intr_mask(h, CCISS_INTR_OFF);
 
 	/* Make sure there is room in the command FIFO */
 	/* Actually it should be completely empty at this time */
@@ -2420,21 +2634,15 @@ static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size, unsigned int use
 	/* tape side of the driver. */
 	for (i = 200000; i > 0; i--) {
 		/* if fifo isn't full go */
-		if (!(info_p->access.fifo_full(info_p))) {
-
+		if (!(h->access.fifo_full(h)))
 			break;
-		}
 		udelay(10);
 		printk(KERN_WARNING "cciss cciss%d: SendCmd FIFO full,"
-		       " waiting!\n", ctlr);
+		       " waiting!\n", h->ctlr);
 	}
-	/*
-	 * Send the cmd
-	 */
-	info_p->access.submit_command(info_p, c);
-	done = 0;
+	h->access.submit_command(h, c); /* Send the cmd */
 	do {
-		complete = pollcomplete(ctlr);
+		complete = pollcomplete(h->ctlr);
 
 #ifdef CCISS_DEBUG
 		printk(KERN_DEBUG "cciss: command completed\n");
@@ -2443,97 +2651,102 @@ static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size, unsigned int use
 		if (complete == 1) {
 			printk(KERN_WARNING
 			       "cciss cciss%d: SendCmd Timeout out, "
-			       "No command list address returned!\n", ctlr);
+			       "No command list address returned!\n", h->ctlr);
 			status = IO_ERROR;
-			done = 1;
 			break;
 		}
 
-		/* This will need to change for direct lookup completions */
-		if ((complete & CISS_ERROR_BIT)
-		    && (complete & ~CISS_ERROR_BIT) == c->busaddr) {
-			/* if data overrun or underun on Report command
-			   ignore it
-			 */
-			if (((c->Request.CDB[0] == CISS_REPORT_LOG) ||
-			     (c->Request.CDB[0] == CISS_REPORT_PHYS) ||
-			     (c->Request.CDB[0] == CISS_INQUIRY)) &&
-			    ((c->err_info->CommandStatus ==
-			      CMD_DATA_OVERRUN) ||
-			     (c->err_info->CommandStatus == CMD_DATA_UNDERRUN)
-			    )) {
-				complete = c->busaddr;
-			} else {
-				if (c->err_info->CommandStatus ==
-				    CMD_UNSOLICITED_ABORT) {
-					printk(KERN_WARNING "cciss%d: "
-					       "unsolicited abort %p\n",
-					       ctlr, c);
-					if (c->retry_count < MAX_CMD_RETRIES) {
-						printk(KERN_WARNING
-						       "cciss%d: retrying %p\n",
-						       ctlr, c);
-						c->retry_count++;
-						/* erase the old error */
-						/* information */
-						memset(c->err_info, 0,
-						       sizeof
-						       (ErrorInfo_struct));
-						goto resend_cmd1;
-					} else {
-						printk(KERN_WARNING
-						       "cciss%d: retried %p too "
-						       "many times\n", ctlr, c);
-						status = IO_ERROR;
-						goto cleanup1;
-					}
-				} else if (c->err_info->CommandStatus ==
-					   CMD_UNABORTABLE) {
-					printk(KERN_WARNING
-					       "cciss%d: command could not be aborted.\n",
-					       ctlr);
-					status = IO_ERROR;
-					goto cleanup1;
-				}
-				printk(KERN_WARNING "ciss ciss%d: sendcmd"
-				       " Error %x \n", ctlr,
-				       c->err_info->CommandStatus);
-				printk(KERN_WARNING "ciss ciss%d: sendcmd"
-				       " offensive info\n"
-				       "  size %x\n   num %x   value %x\n",
-				       ctlr,
-				       c->err_info->MoreErrInfo.Invalid_Cmd.
-				       offense_size,
-				       c->err_info->MoreErrInfo.Invalid_Cmd.
-				       offense_num,
-				       c->err_info->MoreErrInfo.Invalid_Cmd.
-				       offense_value);
-				status = IO_ERROR;
-				goto cleanup1;
-			}
-		}
-		/* This will need changing for direct lookup completions */
-		if (complete != c->busaddr) {
-			if (add_sendcmd_reject(cmd, ctlr, complete) != 0) {
-				BUG();	/* we are pretty much hosed if we get here. */
-			}
+		/* Make sure it's the command we're expecting. */
+		if ((complete & ~CISS_ERROR_BIT) != c->busaddr) {
+			printk(KERN_WARNING "cciss%d: Unexpected command "
+				"completion.\n", h->ctlr);
 			continue;
-		} else
-			done = 1;
-	} while (!done);
+		}
+
+		/* It is our command.  If no error, we're done. */
+		if (!(complete & CISS_ERROR_BIT)) {
+			status = IO_OK;
+			break;
+		}
+
+		/* There is an error... */
+
+		/* if data overrun or underun on Report command ignore it */
+		if (((c->Request.CDB[0] == CISS_REPORT_LOG) ||
+		     (c->Request.CDB[0] == CISS_REPORT_PHYS) ||
+		     (c->Request.CDB[0] == CISS_INQUIRY)) &&
+			((c->err_info->CommandStatus == CMD_DATA_OVERRUN) ||
+			 (c->err_info->CommandStatus == CMD_DATA_UNDERRUN))) {
+			complete = c->busaddr;
+			status = IO_OK;
+			break;
+		}
+
+		if (c->err_info->CommandStatus == CMD_UNSOLICITED_ABORT) {
+			printk(KERN_WARNING "cciss%d: unsolicited abort %p\n",
+				h->ctlr, c);
+			if (c->retry_count < MAX_CMD_RETRIES) {
+				printk(KERN_WARNING "cciss%d: retrying %p\n",
+				   h->ctlr, c);
+				c->retry_count++;
+				/* erase the old error information */
+				memset(c->err_info, 0, sizeof(c->err_info));
+				goto resend_cmd1;
+			}
+			printk(KERN_WARNING "cciss%d: retried %p too many "
+				"times\n", h->ctlr, c);
+			status = IO_ERROR;
+			break;
+		}
+
+		if (c->err_info->CommandStatus == CMD_UNABORTABLE) {
+			printk(KERN_WARNING "cciss%d: command could not be "
+				"aborted.\n", h->ctlr);
+			status = IO_ERROR;
+			break;
+		}
+
+		if (c->err_info->CommandStatus == CMD_TARGET_STATUS) {
+			status = check_target_status(h, c);
+			break;
+		}
+
+		printk(KERN_WARNING "cciss%d: sendcmd error\n", h->ctlr);
+		printk(KERN_WARNING "cmd = 0x%02x, CommandStatus = 0x%02x\n",
+			c->Request.CDB[0], c->err_info->CommandStatus);
+		status = IO_ERROR;
+		break;
+
+	} while (1);
 
-      cleanup1:
 	/* unlock the data buffer from DMA */
 	buff_dma_handle.val32.lower = c->SG[0].Addr.lower;
 	buff_dma_handle.val32.upper = c->SG[0].Addr.upper;
-	pci_unmap_single(info_p->pdev, (dma_addr_t) buff_dma_handle.val,
+	pci_unmap_single(h->pdev, (dma_addr_t) buff_dma_handle.val,
 			 c->SG[0].Len, PCI_DMA_BIDIRECTIONAL);
-#ifdef CONFIG_CISS_SCSI_TAPE
-	/* if we saved some commands for later, process them now. */
-	if (info_p->scsi_rejects.ncompletions > 0)
-		do_cciss_intr(0, info_p);
-#endif
-	cmd_free(info_p, c, 1);
+	return status;
+}
+
+/*
+ * Send a command to the controller, and wait for it to complete.
+ * Used at init time, and during SCSI error recovery.
+ */
+static int sendcmd(__u8 cmd, int ctlr, void *buff, size_t size,
+	__u8 page_code, unsigned char *scsi3addr, int cmd_type)
+{
+	CommandList_struct *c;
+	int status;
+
+	c = cmd_alloc(hba[ctlr], 1);
+	if (!c) {
+		printk(KERN_WARNING "cciss: unable to get memory");
+		return IO_ERROR;
+	}
+	status = fill_cmd(c, cmd, ctlr, buff, size, page_code,
+		scsi3addr, cmd_type);
+	if (status == IO_OK)
+		status = sendcmd_core(hba[ctlr], c);
+	cmd_free(hba[ctlr], c, 1);
 	return status;
 }
 
@@ -2691,7 +2904,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 			printk(KERN_WARNING "cciss: cmd %p has"
 			       " completed with data underrun "
 			       "reported\n", cmd);
-			cmd->rq->data_len = cmd->err_info->ResidualCnt;
+			cmd->rq->resid_len = cmd->err_info->ResidualCnt;
 		}
 		break;
 	case CMD_DATA_OVERRUN:
@@ -2806,7 +3019,7 @@ static void do_cciss_request(struct request_queue *q)
 		goto startio;
 
       queue:
-	creq = elv_next_request(q);
+	creq = blk_peek_request(q);
 	if (!creq)
 		goto startio;
 
@@ -2815,7 +3028,7 @@ static void do_cciss_request(struct request_queue *q)
 	if ((c = cmd_alloc(h, 1)) == NULL)
 		goto full;
 
-	blkdev_dequeue_request(creq);
+	blk_start_request(creq);
 
 	spin_unlock_irq(q->queue_lock);
 
@@ -2840,10 +3053,10 @@ static void do_cciss_request(struct request_queue *q)
 	c->Request.Timeout = 0;	// Don't time out
 	c->Request.CDB[0] =
 	    (rq_data_dir(creq) == READ) ? h->cciss_read : h->cciss_write;
-	start_blk = creq->sector;
+	start_blk = blk_rq_pos(creq);
 #ifdef CCISS_DEBUG
-	printk(KERN_DEBUG "ciss: sector =%d nr_sectors=%d\n", (int)creq->sector,
-	       (int)creq->nr_sectors);
+	printk(KERN_DEBUG "ciss: sector =%d nr_sectors=%d\n",
+	       (int)blk_rq_pos(creq), (int)blk_rq_sectors(creq));
 #endif				/* CCISS_DEBUG */
 
 	sg_init_table(tmp_sg, MAXSGENTRIES);
@@ -2869,8 +3082,8 @@ static void do_cciss_request(struct request_queue *q)
 		h->maxSG = seg;
 
 #ifdef CCISS_DEBUG
-	printk(KERN_DEBUG "cciss: Submitting %lu sectors in %d segments\n",
-	       creq->nr_sectors, seg);
+	printk(KERN_DEBUG "cciss: Submitting %u sectors in %d segments\n",
+	       blk_rq_sectors(creq), seg);
 #endif				/* CCISS_DEBUG */
 
 	c->Header.SGList = c->Header.SGTotal = seg;
@@ -2882,8 +3095,8 @@ static void do_cciss_request(struct request_queue *q)
 			c->Request.CDB[4] = (start_blk >> 8) & 0xff;
 			c->Request.CDB[5] = start_blk & 0xff;
 			c->Request.CDB[6] = 0;	// (sect >> 24) & 0xff; MSB
-			c->Request.CDB[7] = (creq->nr_sectors >> 8) & 0xff;
-			c->Request.CDB[8] = creq->nr_sectors & 0xff;
+			c->Request.CDB[7] = (blk_rq_sectors(creq) >> 8) & 0xff;
+			c->Request.CDB[8] = blk_rq_sectors(creq) & 0xff;
 			c->Request.CDB[9] = c->Request.CDB[11] = c->Request.CDB[12] = 0;
 		} else {
 			u32 upper32 = upper_32_bits(start_blk);
@@ -2898,10 +3111,10 @@ static void do_cciss_request(struct request_queue *q)
 			c->Request.CDB[7]= (start_blk >> 16) & 0xff;
 			c->Request.CDB[8]= (start_blk >>  8) & 0xff;
 			c->Request.CDB[9]= start_blk & 0xff;
-			c->Request.CDB[10]= (creq->nr_sectors >>  24) & 0xff;
-			c->Request.CDB[11]= (creq->nr_sectors >>  16) & 0xff;
-			c->Request.CDB[12]= (creq->nr_sectors >>  8) & 0xff;
-			c->Request.CDB[13]= creq->nr_sectors & 0xff;
+			c->Request.CDB[10]= (blk_rq_sectors(creq) >> 24) & 0xff;
+			c->Request.CDB[11]= (blk_rq_sectors(creq) >> 16) & 0xff;
+			c->Request.CDB[12]= (blk_rq_sectors(creq) >>  8) & 0xff;
+			c->Request.CDB[13]= blk_rq_sectors(creq) & 0xff;
 			c->Request.CDB[14] = c->Request.CDB[15] = 0;
 		}
 	} else if (blk_pc_request(creq)) {
@@ -2931,44 +3144,18 @@ startio:
 
 static inline unsigned long get_next_completion(ctlr_info_t *h)
 {
-#ifdef CONFIG_CISS_SCSI_TAPE
-	/* Any rejects from sendcmd() lying around? Process them first */
-	if (h->scsi_rejects.ncompletions == 0)
-		return h->access.command_completed(h);
-	else {
-		struct sendcmd_reject_list *srl;
-		int n;
-		srl = &h->scsi_rejects;
-		n = --srl->ncompletions;
-		/* printk("cciss%d: processing saved reject\n", h->ctlr); */
-		printk("p");
-		return srl->complete[n];
-	}
-#else
 	return h->access.command_completed(h);
-#endif
 }
 
 static inline int interrupt_pending(ctlr_info_t *h)
 {
-#ifdef CONFIG_CISS_SCSI_TAPE
-	return (h->access.intr_pending(h)
-		|| (h->scsi_rejects.ncompletions > 0));
-#else
 	return h->access.intr_pending(h);
-#endif
 }
 
 static inline long interrupt_not_for_us(ctlr_info_t *h)
 {
-#ifdef CONFIG_CISS_SCSI_TAPE
-	return (((h->access.intr_pending(h) == 0) ||
-		 (h->interrupts_enabled == 0))
-		&& (h->scsi_rejects.ncompletions == 0));
-#else
 	return (((h->access.intr_pending(h) == 0) ||
 		 (h->interrupts_enabled == 0)));
-#endif
 }
 
 static irqreturn_t do_cciss_intr(int irq, void *dev_id)
@@ -3723,12 +3910,15 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 	INIT_HLIST_HEAD(&hba[i]->reqQ);
 
 	if (cciss_pci_init(hba[i], pdev) != 0)
-		goto clean1;
+		goto clean0;
 
 	sprintf(hba[i]->devname, "cciss%d", i);
 	hba[i]->ctlr = i;
 	hba[i]->pdev = pdev;
 
+	if (cciss_create_hba_sysfs_entry(hba[i]))
+		goto clean0;
+
 	/* configure PCI DMA stuff */
 	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64)))
 		dac = 1;
@@ -3787,15 +3977,6 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 		printk(KERN_ERR "cciss: out of memory");
 		goto clean4;
 	}
-#ifdef CONFIG_CISS_SCSI_TAPE
-	hba[i]->scsi_rejects.complete =
-	    kmalloc(sizeof(hba[i]->scsi_rejects.complete[0]) *
-		    (hba[i]->nr_cmds + 5), GFP_KERNEL);
-	if (hba[i]->scsi_rejects.complete == NULL) {
-		printk(KERN_ERR "cciss: out of memory");
-		goto clean4;
-	}
-#endif
 	spin_lock_init(&hba[i]->lock);
 
 	/* Initialize the pdev driver private data.
@@ -3828,7 +4009,7 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 	}
 
 	return_code = sendcmd_withirq(CISS_INQUIRY, i, inq_buff,
-		sizeof(InquiryData_struct), 0, 0 , 0, TYPE_CMD);
+		sizeof(InquiryData_struct), 0, CTLR_LUNID, TYPE_CMD);
 	if (return_code == IO_OK) {
 		hba[i]->firm_ver[0] = inq_buff->data_byte[32];
 		hba[i]->firm_ver[1] = inq_buff->data_byte[33];
@@ -3855,9 +4036,6 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 
 clean4:
 	kfree(inq_buff);
-#ifdef CONFIG_CISS_SCSI_TAPE
-	kfree(hba[i]->scsi_rejects.complete);
-#endif
 	kfree(hba[i]->cmd_pool_bits);
 	if (hba[i]->cmd_pool)
 		pci_free_consistent(hba[i]->pdev,
@@ -3872,6 +4050,8 @@ clean4:
 clean2:
 	unregister_blkdev(hba[i]->major, hba[i]->devname);
 clean1:
+	cciss_destroy_hba_sysfs_entry(hba[i]);
+clean0:
 	hba[i]->busy_initializing = 0;
 	/* cleanup any queues that may have been initialized */
 	for (j=0; j <= hba[i]->highest_lun; j++){
@@ -3907,8 +4087,8 @@ static void cciss_shutdown(struct pci_dev *pdev)
 	/* sendcmd will turn off interrupt, and send the flush...
 	 * To write all data in the battery backed cache to disks */
 	memset(flush_buf, 0, 4);
-	return_code = sendcmd(CCISS_CACHE_FLUSH, i, flush_buf, 4, 0, 0, 0, NULL,
-			      TYPE_CMD);
+	return_code = sendcmd(CCISS_CACHE_FLUSH, i, flush_buf, 4, 0,
+		CTLR_LUNID, TYPE_CMD);
 	if (return_code == IO_OK) {
 		printk(KERN_INFO "Completed flushing cache on controller %d\n", i);
 	} else {
@@ -3973,15 +4153,13 @@ static void __devexit cciss_remove_one(struct pci_dev *pdev)
 	pci_free_consistent(hba[i]->pdev, hba[i]->nr_cmds * sizeof(ErrorInfo_struct),
 			    hba[i]->errinfo_pool, hba[i]->errinfo_pool_dhandle);
 	kfree(hba[i]->cmd_pool_bits);
-#ifdef CONFIG_CISS_SCSI_TAPE
-	kfree(hba[i]->scsi_rejects.complete);
-#endif
 	/*
 	 * Deliberately omit pci_disable_device(): it does something nasty to
 	 * Smart Array controllers that pci_enable_device does not undo
 	 */
 	pci_release_regions(pdev);
 	pci_set_drvdata(pdev, NULL);
+	cciss_destroy_hba_sysfs_entry(hba[i]);
 	free_hba(i);
 }
 
@@ -3999,6 +4177,8 @@ static struct pci_driver cciss_pci_driver = {
  */
 static int __init cciss_init(void)
 {
+	int err;
+
 	/*
 	 * The hardware requires that commands are aligned on a 64-bit
 	 * boundary. Given that we use pci_alloc_consistent() to allocate an
@@ -4008,8 +4188,20 @@ static int __init cciss_init(void)
 
 	printk(KERN_INFO DRIVER_NAME "\n");
 
+	err = bus_register(&cciss_bus_type);
+	if (err)
+		return err;
+
 	/* Register for our PCI devices */
-	return pci_register_driver(&cciss_pci_driver);
+	err = pci_register_driver(&cciss_pci_driver);
+	if (err)
+		goto err_bus_register;
+
+	return 0;
+
+err_bus_register:
+	bus_unregister(&cciss_bus_type);
+	return err;
 }
 
 static void __exit cciss_cleanup(void)
@@ -4026,6 +4218,7 @@ static void __exit cciss_cleanup(void)
 		}
 	}
 	remove_proc_entry("driver/cciss", NULL);
+	bus_unregister(&cciss_bus_type);
 }
 
 static void fail_all_cmds(unsigned long ctlr)
diff --git a/drivers/block/cciss.h b/drivers/block/cciss.h
index 703e08038fb9..06a5db25b298 100644
--- a/drivers/block/cciss.h
+++ b/drivers/block/cciss.h
@@ -11,6 +11,11 @@
 
 #define IO_OK		0
 #define IO_ERROR	1
+#define IO_NEEDS_RETRY  3
+
+#define VENDOR_LEN	8
+#define MODEL_LEN	16
+#define REV_LEN		4
 
 struct ctlr_info;
 typedef struct ctlr_info ctlr_info_t;
@@ -34,23 +39,20 @@ typedef struct _drive_info_struct
 	int 	cylinders;
 	int	raid_level; /* set to -1 to indicate that
 			     * the drive is not in use/configured
-			    */
-	int	busy_configuring; /*This is set when the drive is being removed
-				   *to prevent it from being opened or it's queue
-				   *from being started.
-				  */
-	__u8 serial_no[16]; /* from inquiry page 0x83, */
-			    /* not necc. null terminated. */
+			     */
+	int	busy_configuring; /* This is set when a drive is being removed
+				   * to prevent it from being opened or it's
+				   * queue from being started.
+				   */
+	struct	device dev;
+	__u8 serial_no[16]; /* from inquiry page 0x83,
+			     * not necc. null terminated.
+			     */
+	char vendor[VENDOR_LEN + 1]; /* SCSI vendor string */
+	char model[MODEL_LEN + 1];   /* SCSI model string */
+	char rev[REV_LEN + 1];       /* SCSI revision string */
 } drive_info_struct;
 
-#ifdef CONFIG_CISS_SCSI_TAPE
-
-struct sendcmd_reject_list {
-	int ncompletions;
-	unsigned long *complete; /* array of NR_CMDS tags */
-};
-
-#endif
 struct ctlr_info 
 {
 	int	ctlr;
@@ -118,11 +120,11 @@ struct ctlr_info
 	void *scsi_ctlr; /* ptr to structure containing scsi related stuff */
 	/* list of block side commands the scsi error handling sucked up */
 	/* and saved for later processing */
-	struct sendcmd_reject_list scsi_rejects;
 #endif
 	unsigned char alive;
 	struct completion *rescan_wait;
 	struct task_struct *cciss_scan_thread;
+	struct device dev;
 };
 
 /*  Defining the diffent access_menthods */
diff --git a/drivers/block/cciss_cmd.h b/drivers/block/cciss_cmd.h
index 40b1b92dae7f..cd665b00c7c5 100644
--- a/drivers/block/cciss_cmd.h
+++ b/drivers/block/cciss_cmd.h
@@ -217,6 +217,8 @@ typedef union _LUNAddr_struct {
   LogDevAddr_struct  LogDev;
 } LUNAddr_struct;
 
+#define CTLR_LUNID "\0\0\0\0\0\0\0\0"
+
 typedef struct _CommandListHeader_struct {
   BYTE              ReplyQueue;
   BYTE              SGList;
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index a3fd87b41444..3315268b4ec7 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -44,20 +44,13 @@
 #define CCISS_ABORT_MSG 0x00
 #define CCISS_RESET_MSG 0x01
 
-/* some prototypes... */ 
-static int sendcmd(
-	__u8	cmd,
-	int	ctlr,
-	void	*buff,
-	size_t	size,
-	unsigned int use_unit_num, /* 0: address the controller,
-				      1: address logical volume log_unit, 
-				      2: address is in scsi3addr */
-	unsigned int log_unit,
-	__u8	page_code,
-	unsigned char *scsi3addr,
+static int fill_cmd(CommandList_struct *c, __u8 cmd, int ctlr, void *buff,
+	size_t size,
+	__u8 page_code, unsigned char *scsi3addr,
 	int cmd_type);
 
+static CommandList_struct *cmd_alloc(ctlr_info_t *h, int get_from_pool);
+static void cmd_free(ctlr_info_t *h, CommandList_struct *c, int got_from_pool);
 
 static int cciss_scsi_proc_info(
 		struct Scsi_Host *sh,
@@ -1575,6 +1568,75 @@ cciss_seq_tape_report(struct seq_file *seq, int ctlr)
 	CPQ_TAPE_UNLOCK(ctlr, flags);
 }
 
+static int wait_for_device_to_become_ready(ctlr_info_t *h,
+	unsigned char lunaddr[])
+{
+	int rc;
+	int count = 0;
+	int waittime = HZ;
+	CommandList_struct *c;
+
+	c = cmd_alloc(h, 1);
+	if (!c) {
+		printk(KERN_WARNING "cciss%d: out of memory in "
+			"wait_for_device_to_become_ready.\n", h->ctlr);
+		return IO_ERROR;
+	}
+
+	/* Send test unit ready until device ready, or give up. */
+	while (count < 20) {
+
+		/* Wait for a bit.  do this first, because if we send
+		 * the TUR right away, the reset will just abort it.
+		 */
+		schedule_timeout_uninterruptible(waittime);
+		count++;
+
+		/* Increase wait time with each try, up to a point. */
+		if (waittime < (HZ * 30))
+			waittime = waittime * 2;
+
+		/* Send the Test Unit Ready */
+		rc = fill_cmd(c, TEST_UNIT_READY, h->ctlr, NULL, 0, 0,
+			lunaddr, TYPE_CMD);
+		if (rc == 0)
+			rc = sendcmd_withirq_core(h, c, 0);
+
+		(void) process_sendcmd_error(h, c);
+
+		if (rc != 0)
+			goto retry_tur;
+
+		if (c->err_info->CommandStatus == CMD_SUCCESS)
+			break;
+
+		if (c->err_info->CommandStatus == CMD_TARGET_STATUS &&
+			c->err_info->ScsiStatus == SAM_STAT_CHECK_CONDITION) {
+			if (c->err_info->SenseInfo[2] == NO_SENSE)
+				break;
+			if (c->err_info->SenseInfo[2] == UNIT_ATTENTION) {
+				unsigned char asc;
+				asc = c->err_info->SenseInfo[12];
+				check_for_unit_attention(h, c);
+				if (asc == POWER_OR_RESET)
+					break;
+			}
+		}
+retry_tur:
+		printk(KERN_WARNING "cciss%d: Waiting %d secs "
+			"for device to become ready.\n",
+			h->ctlr, waittime / HZ);
+		rc = 1; /* device not ready. */
+	}
+
+	if (rc)
+		printk("cciss%d: giving up on device.\n", h->ctlr);
+	else
+		printk(KERN_WARNING "cciss%d: device is ready.\n", h->ctlr);
+
+	cmd_free(h, c, 1);
+	return rc;
+}
 
 /* Need at least one of these error handlers to keep ../scsi/hosts.c from 
  * complaining.  Doing a host- or bus-reset can't do anything good here. 
@@ -1591,6 +1653,7 @@ static int cciss_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 {
 	int rc;
 	CommandList_struct *cmd_in_trouble;
+	unsigned char lunaddr[8];
 	ctlr_info_t **c;
 	int ctlr;
 
@@ -1600,19 +1663,15 @@ static int cciss_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 		return FAILED;
 	ctlr = (*c)->ctlr;
 	printk(KERN_WARNING "cciss%d: resetting tape drive or medium changer.\n", ctlr);
-
 	/* find the command that's giving us trouble */
 	cmd_in_trouble = (CommandList_struct *) scsicmd->host_scribble;
-	if (cmd_in_trouble == NULL) { /* paranoia */
+	if (cmd_in_trouble == NULL) /* paranoia */
 		return FAILED;
-	}
+	memcpy(lunaddr, &cmd_in_trouble->Header.LUN.LunAddrBytes[0], 8);
 	/* send a reset to the SCSI LUN which the command was sent to */
-	rc = sendcmd(CCISS_RESET_MSG, ctlr, NULL, 0, 2, 0, 0, 
-		(unsigned char *) &cmd_in_trouble->Header.LUN.LunAddrBytes[0], 
+	rc = sendcmd_withirq(CCISS_RESET_MSG, ctlr, NULL, 0, 0, lunaddr,
 		TYPE_MSG);
-	/* sendcmd turned off interrupts on the board, turn 'em back on. */
-	(*c)->access.set_intr_mask(*c, CCISS_INTR_ON);
-	if (rc == 0)
+	if (rc == 0 && wait_for_device_to_become_ready(*c, lunaddr) == 0)
 		return SUCCESS;
 	printk(KERN_WARNING "cciss%d: resetting device failed.\n", ctlr);
 	return FAILED;
@@ -1622,6 +1681,7 @@ static int  cciss_eh_abort_handler(struct scsi_cmnd *scsicmd)
 {
 	int rc;
 	CommandList_struct *cmd_to_abort;
+	unsigned char lunaddr[8];
 	ctlr_info_t **c;
 	int ctlr;
 
@@ -1636,12 +1696,9 @@ static int  cciss_eh_abort_handler(struct scsi_cmnd *scsicmd)
 	cmd_to_abort = (CommandList_struct *) scsicmd->host_scribble;
 	if (cmd_to_abort == NULL) /* paranoia */
 		return FAILED;
-	rc = sendcmd(CCISS_ABORT_MSG, ctlr, &cmd_to_abort->Header.Tag, 
-		0, 2, 0, 0, 
-		(unsigned char *) &cmd_to_abort->Header.LUN.LunAddrBytes[0], 
-		TYPE_MSG);
-	/* sendcmd turned off interrupts on the board, turn 'em back on. */
-	(*c)->access.set_intr_mask(*c, CCISS_INTR_ON);
+	memcpy(lunaddr, &cmd_to_abort->Header.LUN.LunAddrBytes[0], 8);
+	rc = sendcmd_withirq(CCISS_ABORT_MSG, ctlr, &cmd_to_abort->Header.Tag,
+		0, 0, lunaddr, TYPE_MSG);
 	if (rc == 0)
 		return SUCCESS;
 	return FAILED;
diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c
index ca268ca11159..44fa2018f6b0 100644
--- a/drivers/block/cpqarray.c
+++ b/drivers/block/cpqarray.c
@@ -474,7 +474,7 @@ static int __init cpqarray_register_ctlr( int i, struct pci_dev *pdev)
 		disk->fops = &ida_fops;
 		if (j && !drv->nr_blks)
 			continue;
-		blk_queue_hardsect_size(hba[i]->queue, drv->blk_size);
+		blk_queue_logical_block_size(hba[i]->queue, drv->blk_size);
 		set_capacity(disk, drv->nr_blks);
 		disk->queue = hba[i]->queue;
 		disk->private_data = drv;
@@ -903,7 +903,7 @@ static void do_ida_request(struct request_queue *q)
 		goto startio;
 
 queue_next:
-	creq = elv_next_request(q);
+	creq = blk_peek_request(q);
 	if (!creq)
 		goto startio;
 
@@ -912,17 +912,18 @@ queue_next:
 	if ((c = cmd_alloc(h,1)) == NULL)
 		goto startio;
 
-	blkdev_dequeue_request(creq);
+	blk_start_request(creq);
 
 	c->ctlr = h->ctlr;
 	c->hdr.unit = (drv_info_t *)(creq->rq_disk->private_data) - h->drv;
 	c->hdr.size = sizeof(rblk_t) >> 2;
 	c->size += sizeof(rblk_t);
 
-	c->req.hdr.blk = creq->sector;
+	c->req.hdr.blk = blk_rq_pos(creq);
 	c->rq = creq;
 DBGPX(
-	printk("sector=%d, nr_sectors=%d\n", creq->sector, creq->nr_sectors);
+	printk("sector=%d, nr_sectors=%u\n",
+	       blk_rq_pos(creq), blk_rq_sectors(creq));
 );
 	sg_init_table(tmp_sg, SG_MAX);
 	seg = blk_rq_map_sg(q, creq, tmp_sg);
@@ -940,9 +941,9 @@ DBGPX(
 						 tmp_sg[i].offset,
 						 tmp_sg[i].length, dir);
 	}
-DBGPX(	printk("Submitting %d sectors in %d segments\n", creq->nr_sectors, seg); );
+DBGPX(	printk("Submitting %u sectors in %d segments\n", blk_rq_sectors(creq), seg); );
 	c->req.hdr.sg_cnt = seg;
-	c->req.hdr.blk_cnt = creq->nr_sectors;
+	c->req.hdr.blk_cnt = blk_rq_sectors(creq);
 	c->req.hdr.cmd = (rq_data_dir(creq) == READ) ? IDA_READ : IDA_WRITE;
 	c->type = CMD_RWREQ;
 
@@ -1024,8 +1025,7 @@ static inline void complete_command(cmdlist_t *cmd, int timeout)
 				cmd->req.sg[i].size, ddir);
 
 	DBGPX(printk("Done with %p\n", rq););
-	if (__blk_end_request(rq, error, blk_rq_bytes(rq)))
-		BUG();
+	__blk_end_request_all(rq, error);
 }
 
 /*
@@ -1546,7 +1546,7 @@ static int revalidate_allvol(ctlr_info_t *host)
 		drv_info_t *drv = &host->drv[i];
 		if (i && !drv->nr_blks)
 			continue;
-		blk_queue_hardsect_size(host->queue, drv->blk_size);
+		blk_queue_logical_block_size(host->queue, drv->blk_size);
 		set_capacity(disk, drv->nr_blks);
 		disk->queue = host->queue;
 		disk->private_data = drv;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 1300df6f1642..862b40c90181 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -931,7 +931,7 @@ static inline void unlock_fdc(void)
 	del_timer(&fd_timeout);
 	cont = NULL;
 	clear_bit(0, &fdc_busy);
-	if (elv_next_request(floppy_queue))
+	if (current_req || blk_peek_request(floppy_queue))
 		do_fd_request(floppy_queue);
 	spin_unlock_irqrestore(&floppy_lock, flags);
 	wake_up(&fdc_wait);
@@ -2303,7 +2303,7 @@ static void floppy_end_request(struct request *req, int error)
 
 	/* current_count_sectors can be zero if transfer failed */
 	if (error)
-		nr_sectors = req->current_nr_sectors;
+		nr_sectors = blk_rq_cur_sectors(req);
 	if (__blk_end_request(req, error, nr_sectors << 9))
 		return;
 
@@ -2332,7 +2332,7 @@ static void request_done(int uptodate)
 	if (uptodate) {
 		/* maintain values for invalidation on geometry
 		 * change */
-		block = current_count_sectors + req->sector;
+		block = current_count_sectors + blk_rq_pos(req);
 		INFBOUND(DRS->maxblock, block);
 		if (block > _floppy->sect)
 			DRS->maxtrack = 1;
@@ -2346,10 +2346,10 @@ static void request_done(int uptodate)
 			/* record write error information */
 			DRWE->write_errors++;
 			if (DRWE->write_errors == 1) {
-				DRWE->first_error_sector = req->sector;
+				DRWE->first_error_sector = blk_rq_pos(req);
 				DRWE->first_error_generation = DRS->generation;
 			}
-			DRWE->last_error_sector = req->sector;
+			DRWE->last_error_sector = blk_rq_pos(req);
 			DRWE->last_error_generation = DRS->generation;
 		}
 		spin_lock_irqsave(q->queue_lock, flags);
@@ -2503,24 +2503,23 @@ static void copy_buffer(int ssize, int max_sector, int max_sector_2)
 
 	max_sector = transfer_size(ssize,
 				   min(max_sector, max_sector_2),
-				   current_req->nr_sectors);
+				   blk_rq_sectors(current_req));
 
 	if (current_count_sectors <= 0 && CT(COMMAND) == FD_WRITE &&
-	    buffer_max > fsector_t + current_req->nr_sectors)
+	    buffer_max > fsector_t + blk_rq_sectors(current_req))
 		current_count_sectors = min_t(int, buffer_max - fsector_t,
-					      current_req->nr_sectors);
+					      blk_rq_sectors(current_req));
 
 	remaining = current_count_sectors << 9;
 #ifdef FLOPPY_SANITY_CHECK
-	if ((remaining >> 9) > current_req->nr_sectors &&
-	    CT(COMMAND) == FD_WRITE) {
+	if (remaining > blk_rq_bytes(current_req) && CT(COMMAND) == FD_WRITE) {
 		DPRINT("in copy buffer\n");
 		printk("current_count_sectors=%ld\n", current_count_sectors);
 		printk("remaining=%d\n", remaining >> 9);
-		printk("current_req->nr_sectors=%ld\n",
-		       current_req->nr_sectors);
+		printk("current_req->nr_sectors=%u\n",
+		       blk_rq_sectors(current_req));
 		printk("current_req->current_nr_sectors=%u\n",
-		       current_req->current_nr_sectors);
+		       blk_rq_cur_sectors(current_req));
 		printk("max_sector=%d\n", max_sector);
 		printk("ssize=%d\n", ssize);
 	}
@@ -2530,7 +2529,7 @@ static void copy_buffer(int ssize, int max_sector, int max_sector_2)
 
 	dma_buffer = floppy_track_buffer + ((fsector_t - buffer_min) << 9);
 
-	size = current_req->current_nr_sectors << 9;
+	size = blk_rq_cur_bytes(current_req);
 
 	rq_for_each_segment(bv, current_req, iter) {
 		if (!remaining)
@@ -2648,10 +2647,10 @@ static int make_raw_rw_request(void)
 
 	max_sector = _floppy->sect * _floppy->head;
 
-	TRACK = (int)current_req->sector / max_sector;
-	fsector_t = (int)current_req->sector % max_sector;
+	TRACK = (int)blk_rq_pos(current_req) / max_sector;
+	fsector_t = (int)blk_rq_pos(current_req) % max_sector;
 	if (_floppy->track && TRACK >= _floppy->track) {
-		if (current_req->current_nr_sectors & 1) {
+		if (blk_rq_cur_sectors(current_req) & 1) {
 			current_count_sectors = 1;
 			return 1;
 		} else
@@ -2669,7 +2668,7 @@ static int make_raw_rw_request(void)
 		if (fsector_t >= max_sector) {
 			current_count_sectors =
 			    min_t(int, _floppy->sect - fsector_t,
-				  current_req->nr_sectors);
+				  blk_rq_sectors(current_req));
 			return 1;
 		}
 		SIZECODE = 2;
@@ -2720,7 +2719,7 @@ static int make_raw_rw_request(void)
 
 	in_sector_offset = (fsector_t % _floppy->sect) % ssize;
 	aligned_sector_t = fsector_t - in_sector_offset;
-	max_size = current_req->nr_sectors;
+	max_size = blk_rq_sectors(current_req);
 	if ((raw_cmd->track == buffer_track) &&
 	    (current_drive == buffer_drive) &&
 	    (fsector_t >= buffer_min) && (fsector_t < buffer_max)) {
@@ -2729,10 +2728,10 @@ static int make_raw_rw_request(void)
 			copy_buffer(1, max_sector, buffer_max);
 			return 1;
 		}
-	} else if (in_sector_offset || current_req->nr_sectors < ssize) {
+	} else if (in_sector_offset || blk_rq_sectors(current_req) < ssize) {
 		if (CT(COMMAND) == FD_WRITE) {
-			if (fsector_t + current_req->nr_sectors > ssize &&
-			    fsector_t + current_req->nr_sectors < ssize + ssize)
+			if (fsector_t + blk_rq_sectors(current_req) > ssize &&
+			    fsector_t + blk_rq_sectors(current_req) < ssize + ssize)
 				max_size = ssize + ssize;
 			else
 				max_size = ssize;
@@ -2776,7 +2775,7 @@ static int make_raw_rw_request(void)
 		    (indirect * 2 > direct * 3 &&
 		     *errors < DP->max_errors.read_track && ((!probing
 		       || (DP->read_track & (1 << DRS->probed_format)))))) {
-			max_size = current_req->nr_sectors;
+			max_size = blk_rq_sectors(current_req);
 		} else {
 			raw_cmd->kernel_data = current_req->buffer;
 			raw_cmd->length = current_count_sectors << 9;
@@ -2801,7 +2800,7 @@ static int make_raw_rw_request(void)
 	    fsector_t > buffer_max ||
 	    fsector_t < buffer_min ||
 	    ((CT(COMMAND) == FD_READ ||
-	      (!in_sector_offset && current_req->nr_sectors >= ssize)) &&
+	      (!in_sector_offset && blk_rq_sectors(current_req) >= ssize)) &&
 	     max_sector > 2 * max_buffer_sectors + buffer_min &&
 	     max_size + fsector_t > 2 * max_buffer_sectors + buffer_min)
 	    /* not enough space */
@@ -2879,8 +2878,8 @@ static int make_raw_rw_request(void)
 				printk("write\n");
 			return 0;
 		}
-	} else if (raw_cmd->length > current_req->nr_sectors << 9 ||
-		   current_count_sectors > current_req->nr_sectors) {
+	} else if (raw_cmd->length > blk_rq_bytes(current_req) ||
+		   current_count_sectors > blk_rq_sectors(current_req)) {
 		DPRINT("buffer overrun in direct transfer\n");
 		return 0;
 	} else if (raw_cmd->length < current_count_sectors << 9) {
@@ -2913,7 +2912,7 @@ static void redo_fd_request(void)
 			struct request *req;
 
 			spin_lock_irq(floppy_queue->queue_lock);
-			req = elv_next_request(floppy_queue);
+			req = blk_fetch_request(floppy_queue);
 			spin_unlock_irq(floppy_queue->queue_lock);
 			if (!req) {
 				do_floppy = NULL;
@@ -2990,8 +2989,9 @@ static void do_fd_request(struct request_queue * q)
 	if (usage_count == 0) {
 		printk("warning: usage count=0, current_req=%p exiting\n",
 		       current_req);
-		printk("sect=%ld type=%x flags=%x\n", (long)current_req->sector,
-		       current_req->cmd_type, current_req->cmd_flags);
+		printk("sect=%ld type=%x flags=%x\n",
+		       (long)blk_rq_pos(current_req), current_req->cmd_type,
+		       current_req->cmd_flags);
 		return;
 	}
 	if (test_bit(0, &fdc_busy)) {
@@ -4148,6 +4148,24 @@ static void floppy_device_release(struct device *dev)
 {
 }
 
+static int floppy_resume(struct platform_device *dev)
+{
+	int fdc;
+
+	for (fdc = 0; fdc < N_FDC; fdc++)
+		if (FDCS->address != -1)
+			user_reset_fdc(-1, FD_RESET_ALWAYS, 0);
+
+	return 0;
+}
+
+static struct platform_driver floppy_driver = {
+	.resume = floppy_resume,
+	.driver = {
+		.name = "floppy",
+	},
+};
+
 static struct platform_device floppy_device[N_DRIVE];
 
 static struct kobject *floppy_find(dev_t dev, int *part, void *data)
@@ -4196,10 +4214,14 @@ static int __init floppy_init(void)
 	if (err)
 		goto out_put_disk;
 
+	err = platform_driver_register(&floppy_driver);
+	if (err)
+		goto out_unreg_blkdev;
+
 	floppy_queue = blk_init_queue(do_fd_request, &floppy_lock);
 	if (!floppy_queue) {
 		err = -ENOMEM;
-		goto out_unreg_blkdev;
+		goto out_unreg_driver;
 	}
 	blk_queue_max_sectors(floppy_queue, 64);
 
@@ -4346,6 +4368,8 @@ out_flush_work:
 out_unreg_region:
 	blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256);
 	blk_cleanup_queue(floppy_queue);
+out_unreg_driver:
+	platform_driver_unregister(&floppy_driver);
 out_unreg_blkdev:
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 out_put_disk:
@@ -4566,6 +4590,7 @@ static void __exit floppy_module_exit(void)
 
 	blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256);
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
+	platform_driver_unregister(&floppy_driver);
 
 	for (drive = 0; drive < N_DRIVE; drive++) {
 		del_timer_sync(&motor_off_timer[drive]);
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
index baaa9e486e50..f65b3f369eb0 100644
--- a/drivers/block/hd.c
+++ b/drivers/block/hd.c
@@ -98,10 +98,9 @@
 
 static DEFINE_SPINLOCK(hd_lock);
 static struct request_queue *hd_queue;
+static struct request *hd_req;
 
 #define MAJOR_NR HD_MAJOR
-#define QUEUE (hd_queue)
-#define CURRENT elv_next_request(hd_queue)
 
 #define TIMEOUT_VALUE	(6*HZ)
 #define	HD_DELAY	0
@@ -195,11 +194,24 @@ static void __init hd_setup(char *str, int *ints)
 	NR_HD = hdind+1;
 }
 
+static bool hd_end_request(int err, unsigned int bytes)
+{
+	if (__blk_end_request(hd_req, err, bytes))
+		return true;
+	hd_req = NULL;
+	return false;
+}
+
+static bool hd_end_request_cur(int err)
+{
+	return hd_end_request(err, blk_rq_cur_bytes(hd_req));
+}
+
 static void dump_status(const char *msg, unsigned int stat)
 {
 	char *name = "hd?";
-	if (CURRENT)
-		name = CURRENT->rq_disk->disk_name;
+	if (hd_req)
+		name = hd_req->rq_disk->disk_name;
 
 #ifdef VERBOSE_ERRORS
 	printk("%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
@@ -227,8 +239,8 @@ static void dump_status(const char *msg, unsigned int stat)
 		if (hd_error & (BBD_ERR|ECC_ERR|ID_ERR|MARK_ERR)) {
 			printk(", CHS=%d/%d/%d", (inb(HD_HCYL)<<8) + inb(HD_LCYL),
 				inb(HD_CURRENT) & 0xf, inb(HD_SECTOR));
-			if (CURRENT)
-				printk(", sector=%ld", CURRENT->sector);
+			if (hd_req)
+				printk(", sector=%ld", blk_rq_pos(hd_req));
 		}
 		printk("\n");
 	}
@@ -406,11 +418,12 @@ static void unexpected_hd_interrupt(void)
  */
 static void bad_rw_intr(void)
 {
-	struct request *req = CURRENT;
+	struct request *req = hd_req;
+
 	if (req != NULL) {
 		struct hd_i_struct *disk = req->rq_disk->private_data;
 		if (++req->errors >= MAX_ERRORS || (hd_error & BBD_ERR)) {
-			end_request(req, 0);
+			hd_end_request_cur(-EIO);
 			disk->special_op = disk->recalibrate = 1;
 		} else if (req->errors % RESET_FREQ == 0)
 			reset = 1;
@@ -452,37 +465,30 @@ static void read_intr(void)
 	bad_rw_intr();
 	hd_request();
 	return;
+
 ok_to_read:
-	req = CURRENT;
+	req = hd_req;
 	insw(HD_DATA, req->buffer, 256);
-	req->sector++;
-	req->buffer += 512;
-	req->errors = 0;
-	i = --req->nr_sectors;
-	--req->current_nr_sectors;
 #ifdef DEBUG
-	printk("%s: read: sector %ld, remaining = %ld, buffer=%p\n",
-		req->rq_disk->disk_name, req->sector, req->nr_sectors,
-		req->buffer+512);
+	printk("%s: read: sector %ld, remaining = %u, buffer=%p\n",
+	       req->rq_disk->disk_name, blk_rq_pos(req) + 1,
+	       blk_rq_sectors(req) - 1, req->buffer+512);
 #endif
-	if (req->current_nr_sectors <= 0)
-		end_request(req, 1);
-	if (i > 0) {
+	if (hd_end_request(0, 512)) {
 		SET_HANDLER(&read_intr);
 		return;
 	}
+
 	(void) inb_p(HD_STATUS);
 #if (HD_DELAY > 0)
 	last_req = read_timer();
 #endif
-	if (elv_next_request(QUEUE))
-		hd_request();
-	return;
+	hd_request();
 }
 
 static void write_intr(void)
 {
-	struct request *req = CURRENT;
+	struct request *req = hd_req;
 	int i;
 	int retries = 100000;
 
@@ -492,30 +498,25 @@ static void write_intr(void)
 			continue;
 		if (!OK_STATUS(i))
 			break;
-		if ((req->nr_sectors <= 1) || (i & DRQ_STAT))
+		if ((blk_rq_sectors(req) <= 1) || (i & DRQ_STAT))
 			goto ok_to_write;
 	} while (--retries > 0);
 	dump_status("write_intr", i);
 	bad_rw_intr();
 	hd_request();
 	return;
+
 ok_to_write:
-	req->sector++;
-	i = --req->nr_sectors;
-	--req->current_nr_sectors;
-	req->buffer += 512;
-	if (!i || (req->bio && req->current_nr_sectors <= 0))
-		end_request(req, 1);
-	if (i > 0) {
+	if (hd_end_request(0, 512)) {
 		SET_HANDLER(&write_intr);
 		outsw(HD_DATA, req->buffer, 256);
-	} else {
-#if (HD_DELAY > 0)
-		last_req = read_timer();
-#endif
-		hd_request();
+		return;
 	}
-	return;
+
+#if (HD_DELAY > 0)
+	last_req = read_timer();
+#endif
+	hd_request();
 }
 
 static void recal_intr(void)
@@ -537,18 +538,18 @@ static void hd_times_out(unsigned long dummy)
 
 	do_hd = NULL;
 
-	if (!CURRENT)
+	if (!hd_req)
 		return;
 
 	spin_lock_irq(hd_queue->queue_lock);
 	reset = 1;
-	name = CURRENT->rq_disk->disk_name;
+	name = hd_req->rq_disk->disk_name;
 	printk("%s: timeout\n", name);
-	if (++CURRENT->errors >= MAX_ERRORS) {
+	if (++hd_req->errors >= MAX_ERRORS) {
 #ifdef DEBUG
 		printk("%s: too many errors\n", name);
 #endif
-		end_request(CURRENT, 0);
+		hd_end_request_cur(-EIO);
 	}
 	hd_request();
 	spin_unlock_irq(hd_queue->queue_lock);
@@ -563,7 +564,7 @@ static int do_special_op(struct hd_i_struct *disk, struct request *req)
 	}
 	if (disk->head > 16) {
 		printk("%s: cannot handle device with more than 16 heads - giving up\n", req->rq_disk->disk_name);
-		end_request(req, 0);
+		hd_end_request_cur(-EIO);
 	}
 	disk->special_op = 0;
 	return 1;
@@ -590,24 +591,27 @@ static void hd_request(void)
 repeat:
 	del_timer(&device_timer);
 
-	req = CURRENT;
-	if (!req) {
-		do_hd = NULL;
-		return;
+	if (!hd_req) {
+		hd_req = blk_fetch_request(hd_queue);
+		if (!hd_req) {
+			do_hd = NULL;
+			return;
+		}
 	}
+	req = hd_req;
 
 	if (reset) {
 		reset_hd();
 		return;
 	}
 	disk = req->rq_disk->private_data;
-	block = req->sector;
-	nsect = req->nr_sectors;
+	block = blk_rq_pos(req);
+	nsect = blk_rq_sectors(req);
 	if (block >= get_capacity(req->rq_disk) ||
 	    ((block+nsect) > get_capacity(req->rq_disk))) {
 		printk("%s: bad access: block=%d, count=%d\n",
 			req->rq_disk->disk_name, block, nsect);
-		end_request(req, 0);
+		hd_end_request_cur(-EIO);
 		goto repeat;
 	}
 
@@ -647,7 +651,7 @@ repeat:
 			break;
 		default:
 			printk("unknown hd-command\n");
-			end_request(req, 0);
+			hd_end_request_cur(-EIO);
 			break;
 		}
 	}
@@ -720,7 +724,7 @@ static int __init hd_init(void)
 	blk_queue_max_sectors(hd_queue, 255);
 	init_timer(&device_timer);
 	device_timer.function = hd_times_out;
-	blk_queue_hardsect_size(hd_queue, 512);
+	blk_queue_logical_block_size(hd_queue, 512);
 
 	if (!NR_HD) {
 		/*
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index ddae80825899..801f4ab83302 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -511,11 +511,7 @@ out:
  */
 static void loop_add_bio(struct loop_device *lo, struct bio *bio)
 {
-	if (lo->lo_biotail) {
-		lo->lo_biotail->bi_next = bio;
-		lo->lo_biotail = bio;
-	} else
-		lo->lo_bio = lo->lo_biotail = bio;
+	bio_list_add(&lo->lo_bio_list, bio);
 }
 
 /*
@@ -523,16 +519,7 @@ static void loop_add_bio(struct loop_device *lo, struct bio *bio)
  */
 static struct bio *loop_get_bio(struct loop_device *lo)
 {
-	struct bio *bio;
-
-	if ((bio = lo->lo_bio)) {
-		if (bio == lo->lo_biotail)
-			lo->lo_biotail = NULL;
-		lo->lo_bio = bio->bi_next;
-		bio->bi_next = NULL;
-	}
-
-	return bio;
+	return bio_list_pop(&lo->lo_bio_list);
 }
 
 static int loop_make_request(struct request_queue *q, struct bio *old_bio)
@@ -609,12 +596,13 @@ static int loop_thread(void *data)
 
 	set_user_nice(current, -20);
 
-	while (!kthread_should_stop() || lo->lo_bio) {
+	while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) {
 
 		wait_event_interruptible(lo->lo_event,
-				lo->lo_bio || kthread_should_stop());
+				!bio_list_empty(&lo->lo_bio_list) ||
+				kthread_should_stop());
 
-		if (!lo->lo_bio)
+		if (bio_list_empty(&lo->lo_bio_list))
 			continue;
 		spin_lock_irq(&lo->lo_lock);
 		bio = loop_get_bio(lo);
@@ -721,10 +709,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
 		goto out_putf;
 
-	/* new backing store needs to support loop (eg splice_read) */
-	if (!inode->i_fop->splice_read)
-		goto out_putf;
-
 	/* size of the new backing store needs to be the same */
 	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
 		goto out_putf;
@@ -800,12 +784,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	error = -EINVAL;
 	if (S_ISREG(inode->i_mode) || S_ISBLK(inode->i_mode)) {
 		const struct address_space_operations *aops = mapping->a_ops;
-		/*
-		 * If we can't read - sorry. If we only can't write - well,
-		 * it's going to be read-only.
-		 */
-		if (!file->f_op->splice_read)
-			goto out_putf;
+
 		if (aops->write_begin)
 			lo_flags |= LO_FLAGS_USE_AOPS;
 		if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write)
@@ -841,7 +820,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
-	lo->lo_bio = lo->lo_biotail = NULL;
+	bio_list_init(&lo->lo_bio_list);
 
 	/*
 	 * set queue make_request_fn, and add limits based on lower level
diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c
index f3898353d0a8..60de5a01e71e 100644
--- a/drivers/block/mg_disk.c
+++ b/drivers/block/mg_disk.c
@@ -17,71 +17,220 @@
 #include <linux/fs.h>
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
-#include <linux/libata.h>
+#include <linux/ata.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
-#include <linux/mg_disk.h>
 
 #define MG_RES_SEC (CONFIG_MG_DISK_RES << 1)
 
+/* name for block device */
+#define MG_DISK_NAME "mgd"
+/* name for platform device */
+#define MG_DEV_NAME "mg_disk"
+
+#define MG_DISK_MAJ 0
+#define MG_DISK_MAX_PART 16
+#define MG_SECTOR_SIZE 512
+#define MG_MAX_SECTS 256
+
+/* Register offsets */
+#define MG_BUFF_OFFSET			0x8000
+#define MG_STORAGE_BUFFER_SIZE		0x200
+#define MG_REG_OFFSET			0xC000
+#define MG_REG_FEATURE			(MG_REG_OFFSET + 2)	/* write case */
+#define MG_REG_ERROR			(MG_REG_OFFSET + 2)	/* read case */
+#define MG_REG_SECT_CNT			(MG_REG_OFFSET + 4)
+#define MG_REG_SECT_NUM			(MG_REG_OFFSET + 6)
+#define MG_REG_CYL_LOW			(MG_REG_OFFSET + 8)
+#define MG_REG_CYL_HIGH			(MG_REG_OFFSET + 0xA)
+#define MG_REG_DRV_HEAD			(MG_REG_OFFSET + 0xC)
+#define MG_REG_COMMAND			(MG_REG_OFFSET + 0xE)	/* write case */
+#define MG_REG_STATUS			(MG_REG_OFFSET + 0xE)	/* read  case */
+#define MG_REG_DRV_CTRL			(MG_REG_OFFSET + 0x10)
+#define MG_REG_BURST_CTRL		(MG_REG_OFFSET + 0x12)
+
+/* handy status */
+#define MG_STAT_READY	(ATA_DRDY | ATA_DSC)
+#define MG_READY_OK(s)	(((s) & (MG_STAT_READY | (ATA_BUSY | ATA_DF | \
+				 ATA_ERR))) == MG_STAT_READY)
+
+/* error code for others */
+#define MG_ERR_NONE		0
+#define MG_ERR_TIMEOUT		0x100
+#define MG_ERR_INIT_STAT	0x101
+#define MG_ERR_TRANSLATION	0x102
+#define MG_ERR_CTRL_RST		0x103
+#define MG_ERR_INV_STAT		0x104
+#define MG_ERR_RSTOUT		0x105
+
+#define MG_MAX_ERRORS	6	/* Max read/write errors */
+
+/* command */
+#define MG_CMD_RD 0x20
+#define MG_CMD_WR 0x30
+#define MG_CMD_SLEEP 0x99
+#define MG_CMD_WAKEUP 0xC3
+#define MG_CMD_ID 0xEC
+#define MG_CMD_WR_CONF 0x3C
+#define MG_CMD_RD_CONF 0x40
+
+/* operation mode */
+#define MG_OP_CASCADE (1 << 0)
+#define MG_OP_CASCADE_SYNC_RD (1 << 1)
+#define MG_OP_CASCADE_SYNC_WR (1 << 2)
+#define MG_OP_INTERLEAVE (1 << 3)
+
+/* synchronous */
+#define MG_BURST_LAT_4 (3 << 4)
+#define MG_BURST_LAT_5 (4 << 4)
+#define MG_BURST_LAT_6 (5 << 4)
+#define MG_BURST_LAT_7 (6 << 4)
+#define MG_BURST_LAT_8 (7 << 4)
+#define MG_BURST_LEN_4 (1 << 1)
+#define MG_BURST_LEN_8 (2 << 1)
+#define MG_BURST_LEN_16 (3 << 1)
+#define MG_BURST_LEN_32 (4 << 1)
+#define MG_BURST_LEN_CONT (0 << 1)
+
+/* timeout value (unit: ms) */
+#define MG_TMAX_CONF_TO_CMD	1
+#define MG_TMAX_WAIT_RD_DRQ	10
+#define MG_TMAX_WAIT_WR_DRQ	500
+#define MG_TMAX_RST_TO_BUSY	10
+#define MG_TMAX_HDRST_TO_RDY	500
+#define MG_TMAX_SWRST_TO_RDY	500
+#define MG_TMAX_RSTOUT		3000
+
+/* device attribution */
+/* use mflash as boot device */
+#define MG_BOOT_DEV		(1 << 0)
+/* use mflash as storage device */
+#define MG_STORAGE_DEV		(1 << 1)
+/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */
+#define MG_STORAGE_DEV_SKIP_RST	(1 << 2)
+
+#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
+
+/* names of GPIO resource */
+#define MG_RST_PIN	"mg_rst"
+/* except MG_BOOT_DEV, reset-out pin should be assigned */
+#define MG_RSTOUT_PIN	"mg_rstout"
+
+/* private driver data */
+struct mg_drv_data {
+	/* disk resource */
+	u32 use_polling;
+
+	/* device attribution */
+	u32 dev_attr;
+
+	/* internally used */
+	struct mg_host *host;
+};
+
+/* main structure for mflash driver */
+struct mg_host {
+	struct device *dev;
+
+	struct request_queue *breq;
+	struct request *req;
+	spinlock_t lock;
+	struct gendisk *gd;
+
+	struct timer_list timer;
+	void (*mg_do_intr) (struct mg_host *);
+
+	u16 id[ATA_ID_WORDS];
+
+	u16 cyls;
+	u16 heads;
+	u16 sectors;
+	u32 n_sectors;
+	u32 nres_sectors;
+
+	void __iomem *dev_base;
+	unsigned int irq;
+	unsigned int rst;
+	unsigned int rstout;
+
+	u32 major;
+	u32 error;
+};
+
+/*
+ * Debugging macro and defines
+ */
+#undef DO_MG_DEBUG
+#ifdef DO_MG_DEBUG
+#  define MG_DBG(fmt, args...) \
+	printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
+#else /* CONFIG_MG_DEBUG */
+#  define MG_DBG(fmt, args...) do { } while (0)
+#endif /* CONFIG_MG_DEBUG */
+
 static void mg_request(struct request_queue *);
 
+static bool mg_end_request(struct mg_host *host, int err, unsigned int nr_bytes)
+{
+	if (__blk_end_request(host->req, err, nr_bytes))
+		return true;
+
+	host->req = NULL;
+	return false;
+}
+
+static bool mg_end_request_cur(struct mg_host *host, int err)
+{
+	return mg_end_request(host, err, blk_rq_cur_bytes(host->req));
+}
+
 static void mg_dump_status(const char *msg, unsigned int stat,
 		struct mg_host *host)
 {
 	char *name = MG_DISK_NAME;
-	struct request *req;
 
-	if (host->breq) {
-		req = elv_next_request(host->breq);
-		if (req)
-			name = req->rq_disk->disk_name;
-	}
+	if (host->req)
+		name = host->req->rq_disk->disk_name;
 
 	printk(KERN_ERR "%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
-	if (stat & MG_REG_STATUS_BIT_BUSY)
+	if (stat & ATA_BUSY)
 		printk("Busy ");
-	if (stat & MG_REG_STATUS_BIT_READY)
+	if (stat & ATA_DRDY)
 		printk("DriveReady ");
-	if (stat & MG_REG_STATUS_BIT_WRITE_FAULT)
+	if (stat & ATA_DF)
 		printk("WriteFault ");
-	if (stat & MG_REG_STATUS_BIT_SEEK_DONE)
+	if (stat & ATA_DSC)
 		printk("SeekComplete ");
-	if (stat & MG_REG_STATUS_BIT_DATA_REQ)
+	if (stat & ATA_DRQ)
 		printk("DataRequest ");
-	if (stat & MG_REG_STATUS_BIT_CORRECTED_ERROR)
+	if (stat & ATA_CORR)
 		printk("CorrectedError ");
-	if (stat & MG_REG_STATUS_BIT_ERROR)
+	if (stat & ATA_ERR)
 		printk("Error ");
 	printk("}\n");
-	if ((stat & MG_REG_STATUS_BIT_ERROR) == 0) {
+	if ((stat & ATA_ERR) == 0) {
 		host->error = 0;
 	} else {
 		host->error = inb((unsigned long)host->dev_base + MG_REG_ERROR);
 		printk(KERN_ERR "%s: %s: error=0x%02x { ", name, msg,
 				host->error & 0xff);
-		if (host->error & MG_REG_ERR_BBK)
+		if (host->error & ATA_BBK)
 			printk("BadSector ");
-		if (host->error & MG_REG_ERR_UNC)
+		if (host->error & ATA_UNC)
 			printk("UncorrectableError ");
-		if (host->error & MG_REG_ERR_IDNF)
+		if (host->error & ATA_IDNF)
 			printk("SectorIdNotFound ");
-		if (host->error & MG_REG_ERR_ABRT)
+		if (host->error & ATA_ABORTED)
 			printk("DriveStatusError ");
-		if (host->error & MG_REG_ERR_AMNF)
+		if (host->error & ATA_AMNF)
 			printk("AddrMarkNotFound ");
 		printk("}");
-		if (host->error &
-				(MG_REG_ERR_BBK | MG_REG_ERR_UNC |
-				 MG_REG_ERR_IDNF | MG_REG_ERR_AMNF)) {
-			if (host->breq) {
-				req = elv_next_request(host->breq);
-				if (req)
-					printk(", sector=%u", (u32)req->sector);
-			}
-
+		if (host->error & (ATA_BBK | ATA_UNC | ATA_IDNF | ATA_AMNF)) {
+			if (host->req)
+				printk(", sector=%u",
+				       (unsigned int)blk_rq_pos(host->req));
 		}
 		printk("\n");
 	}
@@ -100,12 +249,12 @@ static unsigned int mg_wait(struct mg_host *host, u32 expect, u32 msec)
 
 	do {
 		cur_jiffies = jiffies;
-		if (status & MG_REG_STATUS_BIT_BUSY) {
-			if (expect == MG_REG_STATUS_BIT_BUSY)
+		if (status & ATA_BUSY) {
+			if (expect == ATA_BUSY)
 				break;
 		} else {
 			/* Check the error condition! */
-			if (status & MG_REG_STATUS_BIT_ERROR) {
+			if (status & ATA_ERR) {
 				mg_dump_status("mg_wait", status, host);
 				break;
 			}
@@ -114,8 +263,8 @@ static unsigned int mg_wait(struct mg_host *host, u32 expect, u32 msec)
 				if (MG_READY_OK(status))
 					break;
 
-			if (expect == MG_REG_STATUS_BIT_DATA_REQ)
-				if (status & MG_REG_STATUS_BIT_DATA_REQ)
+			if (expect == ATA_DRQ)
+				if (status & ATA_DRQ)
 					break;
 		}
 		if (!msec) {
@@ -173,6 +322,42 @@ static irqreturn_t mg_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+/* local copy of ata_id_string() */
+static void mg_id_string(const u16 *id, unsigned char *s,
+			 unsigned int ofs, unsigned int len)
+{
+	unsigned int c;
+
+	BUG_ON(len & 1);
+
+	while (len > 0) {
+		c = id[ofs] >> 8;
+		*s = c;
+		s++;
+
+		c = id[ofs] & 0xff;
+		*s = c;
+		s++;
+
+		ofs++;
+		len -= 2;
+	}
+}
+
+/* local copy of ata_id_c_string() */
+static void mg_id_c_string(const u16 *id, unsigned char *s,
+			   unsigned int ofs, unsigned int len)
+{
+	unsigned char *p;
+
+	mg_id_string(id, s, ofs, len - 1);
+
+	p = s + strnlen(s, len - 1);
+	while (p > s && p[-1] == ' ')
+		p--;
+	*p = '\0';
+}
+
 static int mg_get_disk_id(struct mg_host *host)
 {
 	u32 i;
@@ -184,12 +369,10 @@ static int mg_get_disk_id(struct mg_host *host)
 	char serial[ATA_ID_SERNO_LEN + 1];
 
 	if (!prv_data->use_polling)
-		outb(MG_REG_CTRL_INTR_DISABLE,
-				(unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 
 	outb(MG_CMD_ID, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	err = mg_wait(host, MG_REG_STATUS_BIT_DATA_REQ, MG_TMAX_WAIT_RD_DRQ);
+	err = mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_RD_DRQ);
 	if (err)
 		return err;
 
@@ -219,9 +402,9 @@ static int mg_get_disk_id(struct mg_host *host)
 		host->n_sectors -= host->nres_sectors;
 	}
 
-	ata_id_c_string(id, fwrev, ATA_ID_FW_REV, sizeof(fwrev));
-	ata_id_c_string(id, model, ATA_ID_PROD, sizeof(model));
-	ata_id_c_string(id, serial, ATA_ID_SERNO, sizeof(serial));
+	mg_id_c_string(id, fwrev, ATA_ID_FW_REV, sizeof(fwrev));
+	mg_id_c_string(id, model, ATA_ID_PROD, sizeof(model));
+	mg_id_c_string(id, serial, ATA_ID_SERNO, sizeof(serial));
 	printk(KERN_INFO "mg_disk: model: %s\n", model);
 	printk(KERN_INFO "mg_disk: firm: %.8s\n", fwrev);
 	printk(KERN_INFO "mg_disk: serial: %s\n", serial);
@@ -229,8 +412,7 @@ static int mg_get_disk_id(struct mg_host *host)
 			host->n_sectors, host->nres_sectors);
 
 	if (!prv_data->use_polling)
-		outb(MG_REG_CTRL_INTR_ENABLE, (unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 
 	return err;
 }
@@ -244,7 +426,7 @@ static int mg_disk_init(struct mg_host *host)
 
 	/* hdd rst low */
 	gpio_set_value(host->rst, 0);
-	err = mg_wait(host, MG_REG_STATUS_BIT_BUSY, MG_TMAX_RST_TO_BUSY);
+	err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
 	if (err)
 		return err;
 
@@ -255,17 +437,14 @@ static int mg_disk_init(struct mg_host *host)
 		return err;
 
 	/* soft reset on */
-	outb(MG_REG_CTRL_RESET |
-			(prv_data->use_polling ? MG_REG_CTRL_INTR_DISABLE :
-			 MG_REG_CTRL_INTR_ENABLE),
+	outb(ATA_SRST | (prv_data->use_polling ? ATA_NIEN : 0),
 			(unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-	err = mg_wait(host, MG_REG_STATUS_BIT_BUSY, MG_TMAX_RST_TO_BUSY);
+	err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
 	if (err)
 		return err;
 
 	/* soft reset off */
-	outb(prv_data->use_polling ? MG_REG_CTRL_INTR_DISABLE :
-			MG_REG_CTRL_INTR_ENABLE,
+	outb(prv_data->use_polling ? ATA_NIEN : 0,
 			(unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 	err = mg_wait(host, MG_STAT_READY, MG_TMAX_SWRST_TO_RDY);
 	if (err)
@@ -281,11 +460,10 @@ static int mg_disk_init(struct mg_host *host)
 
 static void mg_bad_rw_intr(struct mg_host *host)
 {
-	struct request *req = elv_next_request(host->breq);
-	if (req != NULL)
-		if (++req->errors >= MG_MAX_ERRORS ||
-				host->error == MG_ERR_TIMEOUT)
-			end_request(req, 0);
+	if (host->req)
+		if (++host->req->errors >= MG_MAX_ERRORS ||
+		    host->error == MG_ERR_TIMEOUT)
+			mg_end_request_cur(host, -EIO);
 }
 
 static unsigned int mg_out(struct mg_host *host,
@@ -311,7 +489,7 @@ static unsigned int mg_out(struct mg_host *host,
 			MG_REG_CYL_LOW);
 	outb((u8)(sect_num >> 16), (unsigned long)host->dev_base +
 			MG_REG_CYL_HIGH);
-	outb((u8)((sect_num >> 24) | MG_REG_HEAD_LBA_MODE),
+	outb((u8)((sect_num >> 24) | ATA_LBA | ATA_DEVICE_OBS),
 			(unsigned long)host->dev_base + MG_REG_DRV_HEAD);
 	outb(cmd, (unsigned long)host->dev_base + MG_REG_COMMAND);
 	return MG_ERR_NONE;
@@ -319,105 +497,77 @@ static unsigned int mg_out(struct mg_host *host,
 
 static void mg_read(struct request *req)
 {
-	u32 remains, j;
+	u32 j;
 	struct mg_host *host = req->rq_disk->private_data;
 
-	remains = req->nr_sectors;
-
-	if (mg_out(host, req->sector, req->nr_sectors, MG_CMD_RD, NULL) !=
-			MG_ERR_NONE)
+	if (mg_out(host, blk_rq_pos(req), blk_rq_sectors(req),
+		   MG_CMD_RD, NULL) != MG_ERR_NONE)
 		mg_bad_rw_intr(host);
 
 	MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
-			remains, req->sector, req->buffer);
+	       blk_rq_sectors(req), blk_rq_pos(req), req->buffer);
 
-	while (remains) {
-		if (mg_wait(host, MG_REG_STATUS_BIT_DATA_REQ,
-					MG_TMAX_WAIT_RD_DRQ) != MG_ERR_NONE) {
+	do {
+		u16 *buff = (u16 *)req->buffer;
+
+		if (mg_wait(host, ATA_DRQ,
+			    MG_TMAX_WAIT_RD_DRQ) != MG_ERR_NONE) {
 			mg_bad_rw_intr(host);
 			return;
 		}
-		for (j = 0; j < MG_SECTOR_SIZE >> 1; j++) {
-			*(u16 *)req->buffer =
-				inw((unsigned long)host->dev_base +
-						MG_BUFF_OFFSET + (j << 1));
-			req->buffer += 2;
-		}
-
-		req->sector++;
-		req->errors = 0;
-		remains = --req->nr_sectors;
-		--req->current_nr_sectors;
-
-		if (req->current_nr_sectors <= 0) {
-			MG_DBG("remain : %d sects\n", remains);
-			end_request(req, 1);
-			if (remains > 0)
-				req = elv_next_request(host->breq);
-		}
+		for (j = 0; j < MG_SECTOR_SIZE >> 1; j++)
+			*buff++ = inw((unsigned long)host->dev_base +
+				      MG_BUFF_OFFSET + (j << 1));
 
 		outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base +
 				MG_REG_COMMAND);
-	}
+	} while (mg_end_request(host, 0, MG_SECTOR_SIZE));
 }
 
 static void mg_write(struct request *req)
 {
-	u32 remains, j;
+	u32 j;
 	struct mg_host *host = req->rq_disk->private_data;
 
-	remains = req->nr_sectors;
-
-	if (mg_out(host, req->sector, req->nr_sectors, MG_CMD_WR, NULL) !=
-			MG_ERR_NONE) {
+	if (mg_out(host, blk_rq_pos(req), blk_rq_sectors(req),
+		   MG_CMD_WR, NULL) != MG_ERR_NONE) {
 		mg_bad_rw_intr(host);
 		return;
 	}
 
-
 	MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
-			remains, req->sector, req->buffer);
-	while (remains) {
-		if (mg_wait(host, MG_REG_STATUS_BIT_DATA_REQ,
-					MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
+	       blk_rq_sectors(req), blk_rq_pos(req), req->buffer);
+
+	do {
+		u16 *buff = (u16 *)req->buffer;
+
+	if (mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
 			mg_bad_rw_intr(host);
 			return;
 		}
-		for (j = 0; j < MG_SECTOR_SIZE >> 1; j++) {
-			outw(*(u16 *)req->buffer,
-					(unsigned long)host->dev_base +
-					MG_BUFF_OFFSET + (j << 1));
-			req->buffer += 2;
-		}
-		req->sector++;
-		remains = --req->nr_sectors;
-		--req->current_nr_sectors;
-
-		if (req->current_nr_sectors <= 0) {
-			MG_DBG("remain : %d sects\n", remains);
-			end_request(req, 1);
-			if (remains > 0)
-				req = elv_next_request(host->breq);
-		}
+		for (j = 0; j < MG_SECTOR_SIZE >> 1; j++)
+			outw(*buff++, (unsigned long)host->dev_base +
+				      MG_BUFF_OFFSET + (j << 1));
 
 		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
 				MG_REG_COMMAND);
-	}
+	} while (mg_end_request(host, 0, MG_SECTOR_SIZE));
 }
 
 static void mg_read_intr(struct mg_host *host)
 {
+	struct request *req = host->req;
 	u32 i;
-	struct request *req;
+	u16 *buff;
 
 	/* check status */
 	do {
 		i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		if (i & MG_REG_STATUS_BIT_BUSY)
+		if (i & ATA_BUSY)
 			break;
 		if (!MG_READY_OK(i))
 			break;
-		if (i & MG_REG_STATUS_BIT_DATA_REQ)
+		if (i & ATA_DRQ)
 			goto ok_to_read;
 	} while (0);
 	mg_dump_status("mg_read_intr", i, host);
@@ -427,60 +577,42 @@ static void mg_read_intr(struct mg_host *host)
 
 ok_to_read:
 	/* get current segment of request */
-	req = elv_next_request(host->breq);
+	buff = (u16 *)req->buffer;
 
 	/* read 1 sector */
-	for (i = 0; i < MG_SECTOR_SIZE >> 1; i++) {
-		*(u16 *)req->buffer =
-			inw((unsigned long)host->dev_base + MG_BUFF_OFFSET +
-					(i << 1));
-		req->buffer += 2;
-	}
+	for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
+		*buff++ = inw((unsigned long)host->dev_base + MG_BUFF_OFFSET +
+			      (i << 1));
 
-	/* manipulate request */
 	MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
-			req->sector, req->nr_sectors - 1, req->buffer);
-
-	req->sector++;
-	req->errors = 0;
-	i = --req->nr_sectors;
-	--req->current_nr_sectors;
-
-	/* let know if current segment done */
-	if (req->current_nr_sectors <= 0)
-		end_request(req, 1);
-
-	/* set handler if read remains */
-	if (i > 0) {
-		host->mg_do_intr = mg_read_intr;
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-	}
+	       blk_rq_pos(req), blk_rq_sectors(req) - 1, req->buffer);
 
 	/* send read confirm */
 	outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
 
-	/* goto next request */
-	if (!i)
+	if (mg_end_request(host, 0, MG_SECTOR_SIZE)) {
+		/* set handler if read remains */
+		host->mg_do_intr = mg_read_intr;
+		mod_timer(&host->timer, jiffies + 3 * HZ);
+	} else /* goto next request */
 		mg_request(host->breq);
 }
 
 static void mg_write_intr(struct mg_host *host)
 {
+	struct request *req = host->req;
 	u32 i, j;
 	u16 *buff;
-	struct request *req;
-
-	/* get current segment of request */
-	req = elv_next_request(host->breq);
+	bool rem;
 
 	/* check status */
 	do {
 		i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		if (i & MG_REG_STATUS_BIT_BUSY)
+		if (i & ATA_BUSY)
 			break;
 		if (!MG_READY_OK(i))
 			break;
-		if ((req->nr_sectors <= 1) || (i & MG_REG_STATUS_BIT_DATA_REQ))
+		if ((blk_rq_sectors(req) <= 1) || (i & ATA_DRQ))
 			goto ok_to_write;
 	} while (0);
 	mg_dump_status("mg_write_intr", i, host);
@@ -489,18 +621,8 @@ static void mg_write_intr(struct mg_host *host)
 	return;
 
 ok_to_write:
-	/* manipulate request */
-	req->sector++;
-	i = --req->nr_sectors;
-	--req->current_nr_sectors;
-	req->buffer += MG_SECTOR_SIZE;
-
-	/* let know if current segment or all done */
-	if (!i || (req->bio && req->current_nr_sectors <= 0))
-		end_request(req, 1);
-
-	/* write 1 sector and set handler if remains */
-	if (i > 0) {
+	if ((rem = mg_end_request(host, 0, MG_SECTOR_SIZE))) {
+		/* write 1 sector and set handler if remains */
 		buff = (u16 *)req->buffer;
 		for (j = 0; j < MG_STORAGE_BUFFER_SIZE >> 1; j++) {
 			outw(*buff, (unsigned long)host->dev_base +
@@ -508,7 +630,7 @@ ok_to_write:
 			buff++;
 		}
 		MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
-				req->sector, req->nr_sectors, req->buffer);
+		       blk_rq_pos(req), blk_rq_sectors(req), req->buffer);
 		host->mg_do_intr = mg_write_intr;
 		mod_timer(&host->timer, jiffies + 3 * HZ);
 	}
@@ -516,7 +638,7 @@ ok_to_write:
 	/* send write confirm */
 	outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
 
-	if (!i)
+	if (!rem)
 		mg_request(host->breq);
 }
 
@@ -524,49 +646,45 @@ void mg_times_out(unsigned long data)
 {
 	struct mg_host *host = (struct mg_host *)data;
 	char *name;
-	struct request *req;
 
 	spin_lock_irq(&host->lock);
 
-	req = elv_next_request(host->breq);
-	if (!req)
+	if (!host->req)
 		goto out_unlock;
 
 	host->mg_do_intr = NULL;
 
-	name = req->rq_disk->disk_name;
+	name = host->req->rq_disk->disk_name;
 	printk(KERN_DEBUG "%s: timeout\n", name);
 
 	host->error = MG_ERR_TIMEOUT;
 	mg_bad_rw_intr(host);
 
-	mg_request(host->breq);
 out_unlock:
+	mg_request(host->breq);
 	spin_unlock_irq(&host->lock);
 }
 
 static void mg_request_poll(struct request_queue *q)
 {
-	struct request *req;
-	struct mg_host *host;
+	struct mg_host *host = q->queuedata;
 
-	while ((req = elv_next_request(q)) != NULL) {
-		host = req->rq_disk->private_data;
-		if (blk_fs_request(req)) {
-			switch (rq_data_dir(req)) {
-			case READ:
-				mg_read(req);
+	while (1) {
+		if (!host->req) {
+			host->req = blk_fetch_request(q);
+			if (!host->req)
 				break;
-			case WRITE:
-				mg_write(req);
-				break;
-			default:
-				printk(KERN_WARNING "%s:%d unknown command\n",
-						__func__, __LINE__);
-				end_request(req, 0);
-				break;
-			}
 		}
+
+		if (unlikely(!blk_fs_request(host->req))) {
+			mg_end_request_cur(host, -EIO);
+			continue;
+		}
+
+		if (rq_data_dir(host->req) == READ)
+			mg_read(host->req);
+		else
+			mg_write(host->req);
 	}
 }
 
@@ -588,18 +706,15 @@ static unsigned int mg_issue_req(struct request *req,
 		break;
 	case WRITE:
 		/* TODO : handler */
-		outb(MG_REG_CTRL_INTR_DISABLE,
-				(unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 		if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr)
 				!= MG_ERR_NONE) {
 			mg_bad_rw_intr(host);
 			return host->error;
 		}
 		del_timer(&host->timer);
-		mg_wait(host, MG_REG_STATUS_BIT_DATA_REQ, MG_TMAX_WAIT_WR_DRQ);
-		outb(MG_REG_CTRL_INTR_ENABLE, (unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_WR_DRQ);
+		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 		if (host->error) {
 			mg_bad_rw_intr(host);
 			return host->error;
@@ -614,11 +729,6 @@ static unsigned int mg_issue_req(struct request *req,
 		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
 				MG_REG_COMMAND);
 		break;
-	default:
-		printk(KERN_WARNING "%s:%d unknown command\n",
-				__func__, __LINE__);
-		end_request(req, 0);
-		break;
 	}
 	return MG_ERR_NONE;
 }
@@ -626,16 +736,17 @@ static unsigned int mg_issue_req(struct request *req,
 /* This function also called from IRQ context */
 static void mg_request(struct request_queue *q)
 {
+	struct mg_host *host = q->queuedata;
 	struct request *req;
-	struct mg_host *host;
 	u32 sect_num, sect_cnt;
 
 	while (1) {
-		req = elv_next_request(q);
-		if (!req)
-			return;
-
-		host = req->rq_disk->private_data;
+		if (!host->req) {
+			host->req = blk_fetch_request(q);
+			if (!host->req)
+				break;
+		}
+		req = host->req;
 
 		/* check unwanted request call */
 		if (host->mg_do_intr)
@@ -643,9 +754,9 @@ static void mg_request(struct request_queue *q)
 
 		del_timer(&host->timer);
 
-		sect_num = req->sector;
+		sect_num = blk_rq_pos(req);
 		/* deal whole segments */
-		sect_cnt = req->nr_sectors;
+		sect_cnt = blk_rq_sectors(req);
 
 		/* sanity check */
 		if (sect_num >= get_capacity(req->rq_disk) ||
@@ -655,12 +766,14 @@ static void mg_request(struct request_queue *q)
 					"%s: bad access: sector=%d, count=%d\n",
 					req->rq_disk->disk_name,
 					sect_num, sect_cnt);
-			end_request(req, 0);
+			mg_end_request_cur(host, -EIO);
 			continue;
 		}
 
-		if (!blk_fs_request(req))
-			return;
+		if (unlikely(!blk_fs_request(req))) {
+			mg_end_request_cur(host, -EIO);
+			continue;
+		}
 
 		if (!mg_issue_req(req, host, sect_num, sect_cnt))
 			return;
@@ -690,9 +803,7 @@ static int mg_suspend(struct platform_device *plat_dev, pm_message_t state)
 		return -EIO;
 
 	if (!prv_data->use_polling)
-		outb(MG_REG_CTRL_INTR_DISABLE,
-				(unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 
 	outb(MG_CMD_SLEEP, (unsigned long)host->dev_base + MG_REG_COMMAND);
 	/* wait until mflash deep sleep */
@@ -700,9 +811,7 @@ static int mg_suspend(struct platform_device *plat_dev, pm_message_t state)
 
 	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD)) {
 		if (!prv_data->use_polling)
-			outb(MG_REG_CTRL_INTR_ENABLE,
-					(unsigned long)host->dev_base +
-					MG_REG_DRV_CTRL);
+			outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 		return -EIO;
 	}
 
@@ -725,8 +834,7 @@ static int mg_resume(struct platform_device *plat_dev)
 		return -EIO;
 
 	if (!prv_data->use_polling)
-		outb(MG_REG_CTRL_INTR_ENABLE, (unsigned long)host->dev_base +
-				MG_REG_DRV_CTRL);
+		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 
 	return 0;
 }
@@ -877,6 +985,7 @@ static int mg_probe(struct platform_device *plat_dev)
 				__func__, __LINE__);
 		goto probe_err_5;
 	}
+	host->breq->queuedata = host;
 
 	/* mflash is random device, thanx for the noop */
 	elevator_exit(host->breq->elevator);
@@ -887,7 +996,7 @@ static int mg_probe(struct platform_device *plat_dev)
 		goto probe_err_6;
 	}
 	blk_queue_max_sectors(host->breq, MG_MAX_SECTS);
-	blk_queue_hardsect_size(host->breq, MG_SECTOR_SIZE);
+	blk_queue_logical_block_size(host->breq, MG_SECTOR_SIZE);
 
 	init_timer(&host->timer);
 	host->timer.function = mg_times_out;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4d6de4f15ccb..5d23ffad7c77 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -110,7 +110,7 @@ static void nbd_end_request(struct request *req)
 			req, error ? "failed" : "done");
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	__blk_end_request(req, error, req->nr_sectors << 9);
+	__blk_end_request_all(req, error);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
@@ -231,19 +231,19 @@ static int nbd_send_req(struct nbd_device *lo, struct request *req)
 {
 	int result, flags;
 	struct nbd_request request;
-	unsigned long size = req->nr_sectors << 9;
+	unsigned long size = blk_rq_bytes(req);
 
 	request.magic = htonl(NBD_REQUEST_MAGIC);
 	request.type = htonl(nbd_cmd(req));
-	request.from = cpu_to_be64((u64) req->sector << 9);
+	request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
 	request.len = htonl(size);
 	memcpy(request.handle, &req, sizeof(req));
 
-	dprintk(DBG_TX, "%s: request %p: sending control (%s@%llu,%luB)\n",
+	dprintk(DBG_TX, "%s: request %p: sending control (%s@%llu,%uB)\n",
 			lo->disk->disk_name, req,
 			nbdcmd_to_ascii(nbd_cmd(req)),
-			(unsigned long long)req->sector << 9,
-			req->nr_sectors << 9);
+			(unsigned long long)blk_rq_pos(req) << 9,
+			blk_rq_bytes(req));
 	result = sock_xmit(lo, 1, &request, sizeof(request),
 			(nbd_cmd(req) == NBD_CMD_WRITE) ? MSG_MORE : 0);
 	if (result <= 0) {
@@ -533,11 +533,9 @@ static void do_nbd_request(struct request_queue *q)
 {
 	struct request *req;
 	
-	while ((req = elv_next_request(q)) != NULL) {
+	while ((req = blk_fetch_request(q)) != NULL) {
 		struct nbd_device *lo;
 
-		blkdev_dequeue_request(req);
-
 		spin_unlock_irq(q->queue_lock);
 
 		dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%x)\n",
@@ -580,13 +578,6 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
 		blk_rq_init(NULL, &sreq);
 		sreq.cmd_type = REQ_TYPE_SPECIAL;
 		nbd_cmd(&sreq) = NBD_CMD_DISC;
-		/*
-		 * Set these to sane values in case server implementation
-		 * fails to check the request type first and also to keep
-		 * debugging output cleaner.
-		 */
-		sreq.sector = 0;
-		sreq.nr_sectors = 0;
 		if (!lo->sock)
 			return -EINVAL;
 		nbd_send_req(lo, &sreq);
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index e91d4b4b014f..911dfd98d813 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -719,32 +719,37 @@ static void do_pcd_request(struct request_queue * q)
 	if (pcd_busy)
 		return;
 	while (1) {
-		pcd_req = elv_next_request(q);
-		if (!pcd_req)
-			return;
+		if (!pcd_req) {
+			pcd_req = blk_fetch_request(q);
+			if (!pcd_req)
+				return;
+		}
 
 		if (rq_data_dir(pcd_req) == READ) {
 			struct pcd_unit *cd = pcd_req->rq_disk->private_data;
 			if (cd != pcd_current)
 				pcd_bufblk = -1;
 			pcd_current = cd;
-			pcd_sector = pcd_req->sector;
-			pcd_count = pcd_req->current_nr_sectors;
+			pcd_sector = blk_rq_pos(pcd_req);
+			pcd_count = blk_rq_cur_sectors(pcd_req);
 			pcd_buf = pcd_req->buffer;
 			pcd_busy = 1;
 			ps_set_intr(do_pcd_read, NULL, 0, nice);
 			return;
-		} else
-			end_request(pcd_req, 0);
+		} else {
+			__blk_end_request_all(pcd_req, -EIO);
+			pcd_req = NULL;
+		}
 	}
 }
 
-static inline void next_request(int success)
+static inline void next_request(int err)
 {
 	unsigned long saved_flags;
 
 	spin_lock_irqsave(&pcd_lock, saved_flags);
-	end_request(pcd_req, success);
+	if (!__blk_end_request_cur(pcd_req, err))
+		pcd_req = NULL;
 	pcd_busy = 0;
 	do_pcd_request(pcd_queue);
 	spin_unlock_irqrestore(&pcd_lock, saved_flags);
@@ -781,7 +786,7 @@ static void pcd_start(void)
 
 	if (pcd_command(pcd_current, rd_cmd, 2048, "read block")) {
 		pcd_bufblk = -1;
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 
@@ -796,7 +801,7 @@ static void do_pcd_read(void)
 	pcd_retries = 0;
 	pcd_transfer();
 	if (!pcd_count) {
-		next_request(1);
+		next_request(0);
 		return;
 	}
 
@@ -815,7 +820,7 @@ static void do_pcd_read_drq(void)
 			return;
 		}
 		pcd_bufblk = -1;
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 9299455b0af6..bf5955b3d873 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -410,10 +410,12 @@ static void run_fsm(void)
 				pd_claimed = 0;
 				phase = NULL;
 				spin_lock_irqsave(&pd_lock, saved_flags);
-				end_request(pd_req, res);
-				pd_req = elv_next_request(pd_queue);
-				if (!pd_req)
-					stop = 1;
+				if (!__blk_end_request_cur(pd_req,
+						res == Ok ? 0 : -EIO)) {
+					pd_req = blk_fetch_request(pd_queue);
+					if (!pd_req)
+						stop = 1;
+				}
 				spin_unlock_irqrestore(&pd_lock, saved_flags);
 				if (stop)
 					return;
@@ -443,11 +445,11 @@ static enum action do_pd_io_start(void)
 
 	pd_cmd = rq_data_dir(pd_req);
 	if (pd_cmd == READ || pd_cmd == WRITE) {
-		pd_block = pd_req->sector;
-		pd_count = pd_req->current_nr_sectors;
+		pd_block = blk_rq_pos(pd_req);
+		pd_count = blk_rq_cur_sectors(pd_req);
 		if (pd_block + pd_count > get_capacity(pd_req->rq_disk))
 			return Fail;
-		pd_run = pd_req->nr_sectors;
+		pd_run = blk_rq_sectors(pd_req);
 		pd_buf = pd_req->buffer;
 		pd_retries = 0;
 		if (pd_cmd == READ)
@@ -477,8 +479,8 @@ static int pd_next_buf(void)
 	if (pd_count)
 		return 0;
 	spin_lock_irqsave(&pd_lock, saved_flags);
-	end_request(pd_req, 1);
-	pd_count = pd_req->current_nr_sectors;
+	__blk_end_request_cur(pd_req, 0);
+	pd_count = blk_rq_cur_sectors(pd_req);
 	pd_buf = pd_req->buffer;
 	spin_unlock_irqrestore(&pd_lock, saved_flags);
 	return 0;
@@ -702,7 +704,7 @@ static void do_pd_request(struct request_queue * q)
 {
 	if (pd_req)
 		return;
-	pd_req = elv_next_request(q);
+	pd_req = blk_fetch_request(q);
 	if (!pd_req)
 		return;
 
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index bef3b997ba3e..68a90834e993 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -750,12 +750,10 @@ static int pf_ready(void)
 
 static struct request_queue *pf_queue;
 
-static void pf_end_request(int uptodate)
+static void pf_end_request(int err)
 {
-	if (pf_req) {
-		end_request(pf_req, uptodate);
+	if (pf_req && !__blk_end_request_cur(pf_req, err))
 		pf_req = NULL;
-	}
 }
 
 static void do_pf_request(struct request_queue * q)
@@ -763,17 +761,19 @@ static void do_pf_request(struct request_queue * q)
 	if (pf_busy)
 		return;
 repeat:
-	pf_req = elv_next_request(q);
-	if (!pf_req)
-		return;
+	if (!pf_req) {
+		pf_req = blk_fetch_request(q);
+		if (!pf_req)
+			return;
+	}
 
 	pf_current = pf_req->rq_disk->private_data;
-	pf_block = pf_req->sector;
-	pf_run = pf_req->nr_sectors;
-	pf_count = pf_req->current_nr_sectors;
+	pf_block = blk_rq_pos(pf_req);
+	pf_run = blk_rq_sectors(pf_req);
+	pf_count = blk_rq_cur_sectors(pf_req);
 
 	if (pf_block + pf_count > get_capacity(pf_req->rq_disk)) {
-		pf_end_request(0);
+		pf_end_request(-EIO);
 		goto repeat;
 	}
 
@@ -788,7 +788,7 @@ repeat:
 		pi_do_claimed(pf_current->pi, do_pf_write);
 	else {
 		pf_busy = 0;
-		pf_end_request(0);
+		pf_end_request(-EIO);
 		goto repeat;
 	}
 }
@@ -805,23 +805,22 @@ static int pf_next_buf(void)
 		return 1;
 	if (!pf_count) {
 		spin_lock_irqsave(&pf_spin_lock, saved_flags);
-		pf_end_request(1);
-		pf_req = elv_next_request(pf_queue);
+		pf_end_request(0);
 		spin_unlock_irqrestore(&pf_spin_lock, saved_flags);
 		if (!pf_req)
 			return 1;
-		pf_count = pf_req->current_nr_sectors;
+		pf_count = blk_rq_cur_sectors(pf_req);
 		pf_buf = pf_req->buffer;
 	}
 	return 0;
 }
 
-static inline void next_request(int success)
+static inline void next_request(int err)
 {
 	unsigned long saved_flags;
 
 	spin_lock_irqsave(&pf_spin_lock, saved_flags);
-	pf_end_request(success);
+	pf_end_request(err);
 	pf_busy = 0;
 	do_pf_request(pf_queue);
 	spin_unlock_irqrestore(&pf_spin_lock, saved_flags);
@@ -844,7 +843,7 @@ static void do_pf_read_start(void)
 			pi_do_claimed(pf_current->pi, do_pf_read_start);
 			return;
 		}
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 	pf_mask = STAT_DRQ;
@@ -863,7 +862,7 @@ static void do_pf_read_drq(void)
 				pi_do_claimed(pf_current->pi, do_pf_read_start);
 				return;
 			}
-			next_request(0);
+			next_request(-EIO);
 			return;
 		}
 		pi_read_block(pf_current->pi, pf_buf, 512);
@@ -871,7 +870,7 @@ static void do_pf_read_drq(void)
 			break;
 	}
 	pi_disconnect(pf_current->pi);
-	next_request(1);
+	next_request(0);
 }
 
 static void do_pf_write(void)
@@ -890,7 +889,7 @@ static void do_pf_write_start(void)
 			pi_do_claimed(pf_current->pi, do_pf_write_start);
 			return;
 		}
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 
@@ -903,7 +902,7 @@ static void do_pf_write_start(void)
 				pi_do_claimed(pf_current->pi, do_pf_write_start);
 				return;
 			}
-			next_request(0);
+			next_request(-EIO);
 			return;
 		}
 		pi_write_block(pf_current->pi, pf_buf, 512);
@@ -923,11 +922,11 @@ static void do_pf_write_done(void)
 			pi_do_claimed(pf_current->pi, do_pf_write_start);
 			return;
 		}
-		next_request(0);
+		next_request(-EIO);
 		return;
 	}
 	pi_disconnect(pf_current->pi);
-	next_request(1);
+	next_request(0);
 }
 
 static int __init pf_init(void)
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index dc7a8c352da2..d57f11759480 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -991,13 +991,15 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
  */
 static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
 {
-	if ((pd->settings.size << 9) / CD_FRAMESIZE <= q->max_phys_segments) {
+	if ((pd->settings.size << 9) / CD_FRAMESIZE
+	    <= queue_max_phys_segments(q)) {
 		/*
 		 * The cdrom device can handle one segment/frame
 		 */
 		clear_bit(PACKET_MERGE_SEGS, &pd->flags);
 		return 0;
-	} else if ((pd->settings.size << 9) / PAGE_SIZE <= q->max_phys_segments) {
+	} else if ((pd->settings.size << 9) / PAGE_SIZE
+		   <= queue_max_phys_segments(q)) {
 		/*
 		 * We can handle this case at the expense of some extra memory
 		 * copies during write operations
@@ -2657,7 +2659,7 @@ static void pkt_init_queue(struct pktcdvd_device *pd)
 	struct request_queue *q = pd->disk->queue;
 
 	blk_queue_make_request(q, pkt_make_request);
-	blk_queue_hardsect_size(q, CD_FRAMESIZE);
+	blk_queue_logical_block_size(q, CD_FRAMESIZE);
 	blk_queue_max_sectors(q, PACKET_MAX_SECTORS);
 	blk_queue_merge_bvec(q, pkt_merge_bvec);
 	q->queuedata = pd;
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index bccc42bb9212..aaeeb544228a 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -134,13 +134,12 @@ static int ps3disk_submit_request_sg(struct ps3_storage_device *dev,
 	rq_for_each_segment(bv, req, iter)
 		n++;
 	dev_dbg(&dev->sbd.core,
-		"%s:%u: %s req has %u bvecs for %lu sectors %lu hard sectors\n",
-		__func__, __LINE__, op, n, req->nr_sectors,
-		req->hard_nr_sectors);
+		"%s:%u: %s req has %u bvecs for %u sectors\n",
+		__func__, __LINE__, op, n, blk_rq_sectors(req));
 #endif
 
-	start_sector = req->sector * priv->blocking_factor;
-	sectors = req->nr_sectors * priv->blocking_factor;
+	start_sector = blk_rq_pos(req) * priv->blocking_factor;
+	sectors = blk_rq_sectors(req) * priv->blocking_factor;
 	dev_dbg(&dev->sbd.core, "%s:%u: %s %llu sectors starting at %llu\n",
 		__func__, __LINE__, op, sectors, start_sector);
 
@@ -158,7 +157,7 @@ static int ps3disk_submit_request_sg(struct ps3_storage_device *dev,
 	if (res) {
 		dev_err(&dev->sbd.core, "%s:%u: %s failed %d\n", __func__,
 			__LINE__, op, res);
-		end_request(req, 0);
+		__blk_end_request_all(req, -EIO);
 		return 0;
 	}
 
@@ -180,7 +179,7 @@ static int ps3disk_submit_flush_request(struct ps3_storage_device *dev,
 	if (res) {
 		dev_err(&dev->sbd.core, "%s:%u: sync cache failed 0x%llx\n",
 			__func__, __LINE__, res);
-		end_request(req, 0);
+		__blk_end_request_all(req, -EIO);
 		return 0;
 	}
 
@@ -195,7 +194,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
 
 	dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__);
 
-	while ((req = elv_next_request(q))) {
+	while ((req = blk_fetch_request(q))) {
 		if (blk_fs_request(req)) {
 			if (ps3disk_submit_request_sg(dev, req))
 				break;
@@ -205,7 +204,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
 				break;
 		} else {
 			blk_dump_rq_flags(req, DEVICE_NAME " bad request");
-			end_request(req, 0);
+			__blk_end_request_all(req, -EIO);
 			continue;
 		}
 	}
@@ -231,7 +230,6 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 	struct request *req;
 	int res, read, error;
 	u64 tag, status;
-	unsigned long num_sectors;
 	const char *op;
 
 	res = lv1_storage_get_async_status(dev->sbd.dev_id, &tag, &status);
@@ -261,11 +259,9 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 	if (req->cmd_type == REQ_TYPE_LINUX_BLOCK &&
 	    req->cmd[0] == REQ_LB_OP_FLUSH) {
 		read = 0;
-		num_sectors = req->hard_cur_sectors;
 		op = "flush";
 	} else {
 		read = !rq_data_dir(req);
-		num_sectors = req->nr_sectors;
 		op = read ? "read" : "write";
 	}
 	if (status) {
@@ -281,7 +277,7 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 	}
 
 	spin_lock(&priv->lock);
-	__blk_end_request(req, error, num_sectors << 9);
+	__blk_end_request_all(req, error);
 	priv->req = NULL;
 	ps3disk_do_request(dev, priv->queue);
 	spin_unlock(&priv->lock);
@@ -481,7 +477,7 @@ static int __devinit ps3disk_probe(struct ps3_system_bus_device *_dev)
 	blk_queue_max_sectors(queue, dev->bounce_size >> 9);
 	blk_queue_segment_boundary(queue, -1UL);
 	blk_queue_dma_alignment(queue, dev->blk_size-1);
-	blk_queue_hardsect_size(queue, dev->blk_size);
+	blk_queue_logical_block_size(queue, dev->blk_size);
 
 	blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH,
 			  ps3disk_prepare_flush);
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 5861e33efe63..cbfd9c0aef03 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -212,11 +212,6 @@ static void vdc_end_special(struct vdc_port *port, struct vio_disk_desc *desc)
 	vdc_finish(&port->vio, -err, WAITING_FOR_GEN_CMD);
 }
 
-static void vdc_end_request(struct request *req, int error, int num_sectors)
-{
-	__blk_end_request(req, error, num_sectors << 9);
-}
-
 static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
 			unsigned int index)
 {
@@ -239,7 +234,7 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
 
 	rqe->req = NULL;
 
-	vdc_end_request(req, (desc->status ? -EIO : 0), desc->size >> 9);
+	__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
 
 	if (blk_queue_stopped(port->disk->queue))
 		blk_start_queue(port->disk->queue);
@@ -421,7 +416,7 @@ static int __send_request(struct request *req)
 		desc->slice = 0;
 	}
 	desc->status = ~0;
-	desc->offset = (req->sector << 9) / port->vdisk_block_size;
+	desc->offset = (blk_rq_pos(req) << 9) / port->vdisk_block_size;
 	desc->size = len;
 	desc->ncookies = err;
 
@@ -446,14 +441,13 @@ out:
 static void do_vdc_request(struct request_queue *q)
 {
 	while (1) {
-		struct request *req = elv_next_request(q);
+		struct request *req = blk_fetch_request(q);
 
 		if (!req)
 			break;
 
-		blkdev_dequeue_request(req);
 		if (__send_request(req) < 0)
-			vdc_end_request(req, -EIO, req->hard_nr_sectors);
+			__blk_end_request_all(req, -EIO);
 	}
 }
 
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index d22cc3856937..cf7877fb8a7d 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -514,7 +514,7 @@ static int floppy_read_sectors(struct floppy_state *fs,
 			ret = swim_read_sector(fs, side, track, sector,
 						buffer);
 			if (try-- == 0)
-				return -1;
+				return -EIO;
 		} while (ret != 512);
 
 		buffer += ret;
@@ -528,45 +528,31 @@ static void redo_fd_request(struct request_queue *q)
 	struct request *req;
 	struct floppy_state *fs;
 
-	while ((req = elv_next_request(q))) {
+	req = blk_fetch_request(q);
+	while (req) {
+		int err = -EIO;
 
 		fs = req->rq_disk->private_data;
-		if (req->sector < 0 || req->sector >= fs->total_secs) {
-			end_request(req, 0);
-			continue;
-		}
-		if (req->current_nr_sectors == 0) {
-			end_request(req, 1);
-			continue;
-		}
-		if (!fs->disk_in) {
-			end_request(req, 0);
-			continue;
-		}
-		if (rq_data_dir(req) == WRITE) {
-			if (fs->write_protected) {
-				end_request(req, 0);
-				continue;
-			}
-		}
+		if (blk_rq_pos(req) >= fs->total_secs)
+			goto done;
+		if (!fs->disk_in)
+			goto done;
+		if (rq_data_dir(req) == WRITE && fs->write_protected)
+			goto done;
+
 		switch (rq_data_dir(req)) {
 		case WRITE:
 			/* NOT IMPLEMENTED */
-			end_request(req, 0);
 			break;
 		case READ:
-			if (floppy_read_sectors(fs, req->sector,
-						req->current_nr_sectors,
-						req->buffer)) {
-				end_request(req, 0);
-				continue;
-			}
-			req->nr_sectors -= req->current_nr_sectors;
-			req->sector += req->current_nr_sectors;
-			req->buffer += req->current_nr_sectors * 512;
-			end_request(req, 1);
+			err = floppy_read_sectors(fs, blk_rq_pos(req),
+						  blk_rq_cur_sectors(req),
+						  req->buffer);
 			break;
 		}
+	done:
+		if (!__blk_end_request_cur(req, err))
+			req = blk_fetch_request(q);
 	}
 }
 
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 612965307ba0..80df93e3cdd0 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -251,6 +251,20 @@ static int floppy_release(struct gendisk *disk, fmode_t mode);
 static int floppy_check_change(struct gendisk *disk);
 static int floppy_revalidate(struct gendisk *disk);
 
+static bool swim3_end_request(int err, unsigned int nr_bytes)
+{
+	if (__blk_end_request(fd_req, err, nr_bytes))
+		return true;
+
+	fd_req = NULL;
+	return false;
+}
+
+static bool swim3_end_request_cur(int err)
+{
+	return swim3_end_request(err, blk_rq_cur_bytes(fd_req));
+}
+
 static void swim3_select(struct floppy_state *fs, int sel)
 {
 	struct swim3 __iomem *sw = fs->swim3;
@@ -310,25 +324,27 @@ static void start_request(struct floppy_state *fs)
 		wake_up(&fs->wait);
 		return;
 	}
-	while (fs->state == idle && (req = elv_next_request(swim3_queue))) {
+	while (fs->state == idle) {
+		if (!fd_req) {
+			fd_req = blk_fetch_request(swim3_queue);
+			if (!fd_req)
+				break;
+		}
+		req = fd_req;
 #if 0
-		printk("do_fd_req: dev=%s cmd=%d sec=%ld nr_sec=%ld buf=%p\n",
+		printk("do_fd_req: dev=%s cmd=%d sec=%ld nr_sec=%u buf=%p\n",
 		       req->rq_disk->disk_name, req->cmd,
-		       (long)req->sector, req->nr_sectors, req->buffer);
-		printk("           errors=%d current_nr_sectors=%ld\n",
-		       req->errors, req->current_nr_sectors);
+		       (long)blk_rq_pos(req), blk_rq_sectors(req), req->buffer);
+		printk("           errors=%d current_nr_sectors=%u\n",
+		       req->errors, blk_rq_cur_sectors(req));
 #endif
 
-		if (req->sector < 0 || req->sector >= fs->total_secs) {
-			end_request(req, 0);
-			continue;
-		}
-		if (req->current_nr_sectors == 0) {
-			end_request(req, 1);
+		if (blk_rq_pos(req) >= fs->total_secs) {
+			swim3_end_request_cur(-EIO);
 			continue;
 		}
 		if (fs->ejected) {
-			end_request(req, 0);
+			swim3_end_request_cur(-EIO);
 			continue;
 		}
 
@@ -336,18 +352,19 @@ static void start_request(struct floppy_state *fs)
 			if (fs->write_prot < 0)
 				fs->write_prot = swim3_readbit(fs, WRITE_PROT);
 			if (fs->write_prot) {
-				end_request(req, 0);
+				swim3_end_request_cur(-EIO);
 				continue;
 			}
 		}
 
-		/* Do not remove the cast. req->sector is now a sector_t and
-		 * can be 64 bits, but it will never go past 32 bits for this
-		 * driver anyway, so we can safely cast it down and not have
-		 * to do a 64/32 division
+		/* Do not remove the cast. blk_rq_pos(req) is now a
+		 * sector_t and can be 64 bits, but it will never go
+		 * past 32 bits for this driver anyway, so we can
+		 * safely cast it down and not have to do a 64/32
+		 * division
 		 */
-		fs->req_cyl = ((long)req->sector) / fs->secpercyl;
-		x = ((long)req->sector) % fs->secpercyl;
+		fs->req_cyl = ((long)blk_rq_pos(req)) / fs->secpercyl;
+		x = ((long)blk_rq_pos(req)) % fs->secpercyl;
 		fs->head = x / fs->secpertrack;
 		fs->req_sector = x % fs->secpertrack + 1;
 		fd_req = req;
@@ -424,7 +441,7 @@ static inline void setup_transfer(struct floppy_state *fs)
 	struct dbdma_cmd *cp = fs->dma_cmd;
 	struct dbdma_regs __iomem *dr = fs->dma;
 
-	if (fd_req->current_nr_sectors <= 0) {
+	if (blk_rq_cur_sectors(fd_req) <= 0) {
 		printk(KERN_ERR "swim3: transfer 0 sectors?\n");
 		return;
 	}
@@ -432,8 +449,8 @@ static inline void setup_transfer(struct floppy_state *fs)
 		n = 1;
 	else {
 		n = fs->secpertrack - fs->req_sector + 1;
-		if (n > fd_req->current_nr_sectors)
-			n = fd_req->current_nr_sectors;
+		if (n > blk_rq_cur_sectors(fd_req))
+			n = blk_rq_cur_sectors(fd_req);
 	}
 	fs->scount = n;
 	swim3_select(fs, fs->head? READ_DATA_1: READ_DATA_0);
@@ -508,7 +525,7 @@ static void act(struct floppy_state *fs)
 		case do_transfer:
 			if (fs->cur_cyl != fs->req_cyl) {
 				if (fs->retries > 5) {
-					end_request(fd_req, 0);
+					swim3_end_request_cur(-EIO);
 					fs->state = idle;
 					return;
 				}
@@ -540,7 +557,7 @@ static void scan_timeout(unsigned long data)
 	out_8(&sw->intr_enable, 0);
 	fs->cur_cyl = -1;
 	if (fs->retries > 5) {
-		end_request(fd_req, 0);
+		swim3_end_request_cur(-EIO);
 		fs->state = idle;
 		start_request(fs);
 	} else {
@@ -559,7 +576,7 @@ static void seek_timeout(unsigned long data)
 	out_8(&sw->select, RELAX);
 	out_8(&sw->intr_enable, 0);
 	printk(KERN_ERR "swim3: seek timeout\n");
-	end_request(fd_req, 0);
+	swim3_end_request_cur(-EIO);
 	fs->state = idle;
 	start_request(fs);
 }
@@ -583,7 +600,7 @@ static void settle_timeout(unsigned long data)
 		return;
 	}
 	printk(KERN_ERR "swim3: seek settle timeout\n");
-	end_request(fd_req, 0);
+	swim3_end_request_cur(-EIO);
 	fs->state = idle;
 	start_request(fs);
 }
@@ -593,8 +610,6 @@ static void xfer_timeout(unsigned long data)
 	struct floppy_state *fs = (struct floppy_state *) data;
 	struct swim3 __iomem *sw = fs->swim3;
 	struct dbdma_regs __iomem *dr = fs->dma;
-	struct dbdma_cmd *cp = fs->dma_cmd;
-	unsigned long s;
 	int n;
 
 	fs->timeout_pending = 0;
@@ -605,17 +620,10 @@ static void xfer_timeout(unsigned long data)
 	out_8(&sw->intr_enable, 0);
 	out_8(&sw->control_bic, WRITE_SECTORS | DO_ACTION);
 	out_8(&sw->select, RELAX);
-	if (rq_data_dir(fd_req) == WRITE)
-		++cp;
-	if (ld_le16(&cp->xfer_status) != 0)
-		s = fs->scount - ((ld_le16(&cp->res_count) + 511) >> 9);
-	else
-		s = 0;
-	fd_req->sector += s;
-	fd_req->current_nr_sectors -= s;
 	printk(KERN_ERR "swim3: timeout %sing sector %ld\n",
-	       (rq_data_dir(fd_req)==WRITE? "writ": "read"), (long)fd_req->sector);
-	end_request(fd_req, 0);
+	       (rq_data_dir(fd_req)==WRITE? "writ": "read"),
+	       (long)blk_rq_pos(fd_req));
+	swim3_end_request_cur(-EIO);
 	fs->state = idle;
 	start_request(fs);
 }
@@ -646,7 +654,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 				printk(KERN_ERR "swim3: seen sector but cyl=ff?\n");
 				fs->cur_cyl = -1;
 				if (fs->retries > 5) {
-					end_request(fd_req, 0);
+					swim3_end_request_cur(-EIO);
 					fs->state = idle;
 					start_request(fs);
 				} else {
@@ -719,9 +727,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 		if (intr & ERROR_INTR) {
 			n = fs->scount - 1 - resid / 512;
 			if (n > 0) {
-				fd_req->sector += n;
-				fd_req->current_nr_sectors -= n;
-				fd_req->buffer += n * 512;
+				blk_update_request(fd_req, 0, n << 9);
 				fs->req_sector += n;
 			}
 			if (fs->retries < 5) {
@@ -730,8 +736,8 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 			} else {
 				printk("swim3: error %sing block %ld (err=%x)\n",
 				       rq_data_dir(fd_req) == WRITE? "writ": "read",
-				       (long)fd_req->sector, err);
-				end_request(fd_req, 0);
+				       (long)blk_rq_pos(fd_req), err);
+				swim3_end_request_cur(-EIO);
 				fs->state = idle;
 			}
 		} else {
@@ -740,18 +746,12 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 				printk(KERN_ERR "swim3: fd dma: stat=%x resid=%d\n", stat, resid);
 				printk(KERN_ERR "  state=%d, dir=%x, intr=%x, err=%x\n",
 				       fs->state, rq_data_dir(fd_req), intr, err);
-				end_request(fd_req, 0);
+				swim3_end_request_cur(-EIO);
 				fs->state = idle;
 				start_request(fs);
 				break;
 			}
-			fd_req->sector += fs->scount;
-			fd_req->current_nr_sectors -= fs->scount;
-			fd_req->buffer += fs->scount * 512;
-			if (fd_req->current_nr_sectors <= 0) {
-				end_request(fd_req, 1);
-				fs->state = idle;
-			} else {
+			if (swim3_end_request(0, fs->scount << 9)) {
 				fs->req_sector += fs->scount;
 				if (fs->req_sector > fs->secpertrack) {
 					fs->req_sector -= fs->secpertrack;
@@ -761,7 +761,8 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 					}
 				}
 				act(fs);
-			}
+			} else
+				fs->state = idle;
 		}
 		if (fs->state == idle)
 			start_request(fs);
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index ff0448e4bf03..da403b6a7f43 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -749,8 +749,7 @@ static inline void carm_end_request_queued(struct carm_host *host,
 	struct request *req = crq->rq;
 	int rc;
 
-	rc = __blk_end_request(req, error, blk_rq_bytes(req));
-	assert(rc == 0);
+	__blk_end_request_all(req, error);
 
 	rc = carm_put_request(host, crq);
 	assert(rc == 0);
@@ -811,12 +810,10 @@ static void carm_oob_rq_fn(struct request_queue *q)
 
 	while (1) {
 		DPRINTK("get req\n");
-		rq = elv_next_request(q);
+		rq = blk_fetch_request(q);
 		if (!rq)
 			break;
 
-		blkdev_dequeue_request(rq);
-
 		crq = rq->special;
 		assert(crq != NULL);
 		assert(crq->rq == rq);
@@ -847,7 +844,7 @@ static void carm_rq_fn(struct request_queue *q)
 
 queue_one_request:
 	VPRINTK("get req\n");
-	rq = elv_next_request(q);
+	rq = blk_peek_request(q);
 	if (!rq)
 		return;
 
@@ -858,7 +855,7 @@ queue_one_request:
 	}
 	crq->rq = rq;
 
-	blkdev_dequeue_request(rq);
+	blk_start_request(rq);
 
 	if (rq_data_dir(rq) == WRITE) {
 		writing = 1;
@@ -904,10 +901,10 @@ queue_one_request:
 	msg->sg_count	= n_elem;
 	msg->sg_type	= SGT_32BIT;
 	msg->handle	= cpu_to_le32(TAG_ENCODE(crq->tag));
-	msg->lba	= cpu_to_le32(rq->sector & 0xffffffff);
-	tmp		= (rq->sector >> 16) >> 16;
+	msg->lba	= cpu_to_le32(blk_rq_pos(rq) & 0xffffffff);
+	tmp		= (blk_rq_pos(rq) >> 16) >> 16;
 	msg->lba_high	= cpu_to_le16( (u16) tmp );
-	msg->lba_count	= cpu_to_le16(rq->nr_sectors);
+	msg->lba_count	= cpu_to_le16(blk_rq_sectors(rq));
 
 	msg_size = sizeof(struct carm_msg_rw) - sizeof(msg->sg);
 	for (i = 0; i < n_elem; i++) {
diff --git a/drivers/block/ub.c b/drivers/block/ub.c
index 689cd27ac890..cc54473b8e77 100644
--- a/drivers/block/ub.c
+++ b/drivers/block/ub.c
@@ -360,8 +360,7 @@ static void ub_cmd_build_block(struct ub_dev *sc, struct ub_lun *lun,
 static void ub_cmd_build_packet(struct ub_dev *sc, struct ub_lun *lun,
     struct ub_scsi_cmd *cmd, struct ub_request *urq);
 static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd);
-static void ub_end_rq(struct request *rq, unsigned int status,
-    unsigned int cmd_len);
+static void ub_end_rq(struct request *rq, unsigned int status);
 static int ub_rw_cmd_retry(struct ub_dev *sc, struct ub_lun *lun,
     struct ub_request *urq, struct ub_scsi_cmd *cmd);
 static int ub_submit_scsi(struct ub_dev *sc, struct ub_scsi_cmd *cmd);
@@ -627,7 +626,7 @@ static void ub_request_fn(struct request_queue *q)
 	struct ub_lun *lun = q->queuedata;
 	struct request *rq;
 
-	while ((rq = elv_next_request(q)) != NULL) {
+	while ((rq = blk_peek_request(q)) != NULL) {
 		if (ub_request_fn_1(lun, rq) != 0) {
 			blk_stop_queue(q);
 			break;
@@ -643,14 +642,14 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq)
 	int n_elem;
 
 	if (atomic_read(&sc->poison)) {
-		blkdev_dequeue_request(rq);
-		ub_end_rq(rq, DID_NO_CONNECT << 16, blk_rq_bytes(rq));
+		blk_start_request(rq);
+		ub_end_rq(rq, DID_NO_CONNECT << 16);
 		return 0;
 	}
 
 	if (lun->changed && !blk_pc_request(rq)) {
-		blkdev_dequeue_request(rq);
-		ub_end_rq(rq, SAM_STAT_CHECK_CONDITION, blk_rq_bytes(rq));
+		blk_start_request(rq);
+		ub_end_rq(rq, SAM_STAT_CHECK_CONDITION);
 		return 0;
 	}
 
@@ -660,7 +659,7 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq)
 		return -1;
 	memset(cmd, 0, sizeof(struct ub_scsi_cmd));
 
-	blkdev_dequeue_request(rq);
+	blk_start_request(rq);
 
 	urq = &lun->urq;
 	memset(urq, 0, sizeof(struct ub_request));
@@ -702,7 +701,7 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq)
 
 drop:
 	ub_put_cmd(lun, cmd);
-	ub_end_rq(rq, DID_ERROR << 16, blk_rq_bytes(rq));
+	ub_end_rq(rq, DID_ERROR << 16);
 	return 0;
 }
 
@@ -723,11 +722,11 @@ static void ub_cmd_build_block(struct ub_dev *sc, struct ub_lun *lun,
 	/*
 	 * build the command
 	 *
-	 * The call to blk_queue_hardsect_size() guarantees that request
+	 * The call to blk_queue_logical_block_size() guarantees that request
 	 * is aligned, but it is given in terms of 512 byte units, always.
 	 */
-	block = rq->sector >> lun->capacity.bshift;
-	nblks = rq->nr_sectors >> lun->capacity.bshift;
+	block = blk_rq_pos(rq) >> lun->capacity.bshift;
+	nblks = blk_rq_sectors(rq) >> lun->capacity.bshift;
 
 	cmd->cdb[0] = (cmd->dir == UB_DIR_READ)? READ_10: WRITE_10;
 	/* 10-byte uses 4 bytes of LBA: 2147483648KB, 2097152MB, 2048GB */
@@ -739,7 +738,7 @@ static void ub_cmd_build_block(struct ub_dev *sc, struct ub_lun *lun,
 	cmd->cdb[8] = nblks;
 	cmd->cdb_len = 10;
 
-	cmd->len = rq->nr_sectors * 512;
+	cmd->len = blk_rq_bytes(rq);
 }
 
 static void ub_cmd_build_packet(struct ub_dev *sc, struct ub_lun *lun,
@@ -747,7 +746,7 @@ static void ub_cmd_build_packet(struct ub_dev *sc, struct ub_lun *lun,
 {
 	struct request *rq = urq->rq;
 
-	if (rq->data_len == 0) {
+	if (blk_rq_bytes(rq) == 0) {
 		cmd->dir = UB_DIR_NONE;
 	} else {
 		if (rq_data_dir(rq) == WRITE)
@@ -762,7 +761,7 @@ static void ub_cmd_build_packet(struct ub_dev *sc, struct ub_lun *lun,
 	memcpy(&cmd->cdb, rq->cmd, rq->cmd_len);
 	cmd->cdb_len = rq->cmd_len;
 
-	cmd->len = rq->data_len;
+	cmd->len = blk_rq_bytes(rq);
 
 	/*
 	 * To reapply this to every URB is not as incorrect as it looks.
@@ -777,16 +776,15 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 	struct ub_request *urq = cmd->back;
 	struct request *rq;
 	unsigned int scsi_status;
-	unsigned int cmd_len;
 
 	rq = urq->rq;
 
 	if (cmd->error == 0) {
 		if (blk_pc_request(rq)) {
-			if (cmd->act_len >= rq->data_len)
-				rq->data_len = 0;
+			if (cmd->act_len >= rq->resid_len)
+				rq->resid_len = 0;
 			else
-				rq->data_len -= cmd->act_len;
+				rq->resid_len -= cmd->act_len;
 			scsi_status = 0;
 		} else {
 			if (cmd->act_len != cmd->len) {
@@ -818,17 +816,14 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 
 	urq->rq = NULL;
 
-	cmd_len = cmd->len;
 	ub_put_cmd(lun, cmd);
-	ub_end_rq(rq, scsi_status, cmd_len);
+	ub_end_rq(rq, scsi_status);
 	blk_start_queue(lun->disk->queue);
 }
 
-static void ub_end_rq(struct request *rq, unsigned int scsi_status,
-    unsigned int cmd_len)
+static void ub_end_rq(struct request *rq, unsigned int scsi_status)
 {
 	int error;
-	long rqlen;
 
 	if (scsi_status == 0) {
 		error = 0;
@@ -836,12 +831,7 @@ static void ub_end_rq(struct request *rq, unsigned int scsi_status,
 		error = -EIO;
 		rq->errors = scsi_status;
 	}
-	rqlen = blk_rq_bytes(rq);    /* Oddly enough, this is the residue. */
-	if (__blk_end_request(rq, error, cmd_len)) {
-		printk(KERN_WARNING DRV_NAME
-		    ": __blk_end_request blew, %s-cmd total %u rqlen %ld\n",
-		    blk_pc_request(rq)? "pc": "fs", cmd_len, rqlen);
-	}
+	__blk_end_request_all(rq, error);
 }
 
 static int ub_rw_cmd_retry(struct ub_dev *sc, struct ub_lun *lun,
@@ -1759,7 +1749,7 @@ static int ub_bd_revalidate(struct gendisk *disk)
 	ub_revalidate(lun->udev, lun);
 
 	/* XXX Support sector size switching like in sr.c */
-	blk_queue_hardsect_size(disk->queue, lun->capacity.bsize);
+	blk_queue_logical_block_size(disk->queue, lun->capacity.bsize);
 	set_capacity(disk, lun->capacity.nsec);
 	// set_disk_ro(sdkp->disk, lun->readonly);
 
@@ -2334,7 +2324,7 @@ static int ub_probe_lun(struct ub_dev *sc, int lnum)
 	blk_queue_max_phys_segments(q, UB_MAX_REQ_SG);
 	blk_queue_segment_boundary(q, 0xffffffff);	/* Dubious. */
 	blk_queue_max_sectors(q, UB_MAX_SECTORS);
-	blk_queue_hardsect_size(q, lun->capacity.bsize);
+	blk_queue_logical_block_size(q, lun->capacity.bsize);
 
 	lun->disk = disk;
 	q->queuedata = lun;
diff --git a/drivers/block/viodasd.c b/drivers/block/viodasd.c
index ecccf65dce2f..390d69bb7c48 100644
--- a/drivers/block/viodasd.c
+++ b/drivers/block/viodasd.c
@@ -252,7 +252,7 @@ static int send_request(struct request *req)
 	struct viodasd_device *d;
 	unsigned long flags;
 
-	start = (u64)req->sector << 9;
+	start = (u64)blk_rq_pos(req) << 9;
 
 	if (rq_data_dir(req) == READ) {
 		direction = DMA_FROM_DEVICE;
@@ -361,19 +361,17 @@ static void do_viodasd_request(struct request_queue *q)
 	 * back later.
 	 */
 	while (num_req_outstanding < VIOMAXREQ) {
-		req = elv_next_request(q);
+		req = blk_fetch_request(q);
 		if (req == NULL)
 			return;
-		/* dequeue the current request from the queue */
-		blkdev_dequeue_request(req);
 		/* check that request contains a valid command */
 		if (!blk_fs_request(req)) {
-			viodasd_end_request(req, -EIO, req->hard_nr_sectors);
+			viodasd_end_request(req, -EIO, blk_rq_sectors(req));
 			continue;
 		}
 		/* Try sending the request */
 		if (send_request(req) != 0)
-			viodasd_end_request(req, -EIO, req->hard_nr_sectors);
+			viodasd_end_request(req, -EIO, blk_rq_sectors(req));
 	}
 }
 
@@ -590,7 +588,7 @@ static int viodasd_handle_read_write(struct vioblocklpevent *bevent)
 		err = vio_lookup_rc(viodasd_err_table, bevent->sub_result);
 		printk(VIOD_KERN_WARNING "read/write error %d:0x%04x (%s)\n",
 				event->xRc, bevent->sub_result, err->msg);
-		num_sect = req->hard_nr_sectors;
+		num_sect = blk_rq_sectors(req);
 	}
 	qlock = req->q->queue_lock;
 	spin_lock_irqsave(qlock, irq_flags);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 5d34764c8a87..c0facaa55cf4 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -37,6 +37,7 @@ struct virtblk_req
 	struct list_head list;
 	struct request *req;
 	struct virtio_blk_outhdr out_hdr;
+	struct virtio_scsi_inhdr in_hdr;
 	u8 status;
 };
 
@@ -50,6 +51,7 @@ static void blk_done(struct virtqueue *vq)
 	spin_lock_irqsave(&vblk->lock, flags);
 	while ((vbr = vblk->vq->vq_ops->get_buf(vblk->vq, &len)) != NULL) {
 		int error;
+
 		switch (vbr->status) {
 		case VIRTIO_BLK_S_OK:
 			error = 0;
@@ -62,7 +64,13 @@ static void blk_done(struct virtqueue *vq)
 			break;
 		}
 
-		__blk_end_request(vbr->req, error, blk_rq_bytes(vbr->req));
+		if (blk_pc_request(vbr->req)) {
+			vbr->req->resid_len = vbr->in_hdr.residual;
+			vbr->req->sense_len = vbr->in_hdr.sense_len;
+			vbr->req->errors = vbr->in_hdr.errors;
+		}
+
+		__blk_end_request_all(vbr->req, error);
 		list_del(&vbr->list);
 		mempool_free(vbr, vblk->pool);
 	}
@@ -74,7 +82,7 @@ static void blk_done(struct virtqueue *vq)
 static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		   struct request *req)
 {
-	unsigned long num, out, in;
+	unsigned long num, out = 0, in = 0;
 	struct virtblk_req *vbr;
 
 	vbr = mempool_alloc(vblk->pool, GFP_ATOMIC);
@@ -85,7 +93,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	vbr->req = req;
 	if (blk_fs_request(vbr->req)) {
 		vbr->out_hdr.type = 0;
-		vbr->out_hdr.sector = vbr->req->sector;
+		vbr->out_hdr.sector = blk_rq_pos(vbr->req);
 		vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
 	} else if (blk_pc_request(vbr->req)) {
 		vbr->out_hdr.type = VIRTIO_BLK_T_SCSI_CMD;
@@ -99,18 +107,36 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	if (blk_barrier_rq(vbr->req))
 		vbr->out_hdr.type |= VIRTIO_BLK_T_BARRIER;
 
-	sg_set_buf(&vblk->sg[0], &vbr->out_hdr, sizeof(vbr->out_hdr));
-	num = blk_rq_map_sg(q, vbr->req, vblk->sg+1);
-	sg_set_buf(&vblk->sg[num+1], &vbr->status, sizeof(vbr->status));
+	sg_set_buf(&vblk->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr));
 
-	if (rq_data_dir(vbr->req) == WRITE) {
-		vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
-		out = 1 + num;
-		in = 1;
-	} else {
-		vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
-		out = 1;
-		in = 1 + num;
+	/*
+	 * If this is a packet command we need a couple of additional headers.
+	 * Behind the normal outhdr we put a segment with the scsi command
+	 * block, and before the normal inhdr we put the sense data and the
+	 * inhdr with additional status information before the normal inhdr.
+	 */
+	if (blk_pc_request(vbr->req))
+		sg_set_buf(&vblk->sg[out++], vbr->req->cmd, vbr->req->cmd_len);
+
+	num = blk_rq_map_sg(q, vbr->req, vblk->sg + out);
+
+	if (blk_pc_request(vbr->req)) {
+		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96);
+		sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr,
+			   sizeof(vbr->in_hdr));
+	}
+
+	sg_set_buf(&vblk->sg[num + out + in++], &vbr->status,
+		   sizeof(vbr->status));
+
+	if (num) {
+		if (rq_data_dir(vbr->req) == WRITE) {
+			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
+			out += num;
+		} else {
+			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
+			in += num;
+		}
 	}
 
 	if (vblk->vq->vq_ops->add_buf(vblk->vq, vblk->sg, out, in, vbr)) {
@@ -124,12 +150,11 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 
 static void do_virtblk_request(struct request_queue *q)
 {
-	struct virtio_blk *vblk = NULL;
+	struct virtio_blk *vblk = q->queuedata;
 	struct request *req;
 	unsigned int issued = 0;
 
-	while ((req = elv_next_request(q)) != NULL) {
-		vblk = req->rq_disk->private_data;
+	while ((req = blk_peek_request(q)) != NULL) {
 		BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
 		/* If this request fails, stop queue and wait for something to
@@ -138,7 +163,7 @@ static void do_virtblk_request(struct request_queue *q)
 			blk_stop_queue(q);
 			break;
 		}
-		blkdev_dequeue_request(req);
+		blk_start_request(req);
 		issued++;
 	}
 
@@ -146,12 +171,51 @@ static void do_virtblk_request(struct request_queue *q)
 		vblk->vq->vq_ops->kick(vblk->vq);
 }
 
+/* return ATA identify data
+ */
+static int virtblk_identify(struct gendisk *disk, void *argp)
+{
+	struct virtio_blk *vblk = disk->private_data;
+	void *opaque;
+	int err = -ENOMEM;
+
+	opaque = kmalloc(VIRTIO_BLK_ID_BYTES, GFP_KERNEL);
+	if (!opaque)
+		goto out;
+
+	err = virtio_config_buf(vblk->vdev, VIRTIO_BLK_F_IDENTIFY,
+		offsetof(struct virtio_blk_config, identify), opaque,
+		VIRTIO_BLK_ID_BYTES);
+
+	if (err)
+		goto out_kfree;
+
+	if (copy_to_user(argp, opaque, VIRTIO_BLK_ID_BYTES))
+		err = -EFAULT;
+
+out_kfree:
+	kfree(opaque);
+out:
+	return err;
+}
+
 static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
 			 unsigned cmd, unsigned long data)
 {
-	return scsi_cmd_ioctl(bdev->bd_disk->queue,
-			      bdev->bd_disk, mode, cmd,
-			      (void __user *)data);
+	struct gendisk *disk = bdev->bd_disk;
+	struct virtio_blk *vblk = disk->private_data;
+	void __user *argp = (void __user *)data;
+
+	if (cmd == HDIO_GET_IDENTITY)
+		return virtblk_identify(disk, argp);
+
+	/*
+	 * Only allow the generic SCSI ioctls if the host can support it.
+	 */
+	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
+		return -ENOIOCTLCMD;
+
+	return scsi_cmd_ioctl(disk->queue, disk, mode, cmd, argp);
 }
 
 /* We provide getgeo only to please some old bootloader/partitioning tools */
@@ -249,6 +313,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 		goto out_put_disk;
 	}
 
+	vblk->disk->queue->queuedata = vblk;
 	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, vblk->disk->queue);
 
 	if (index < 26) {
@@ -313,7 +378,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 				offsetof(struct virtio_blk_config, blk_size),
 				&blk_size);
 	if (!err)
-		blk_queue_hardsect_size(vblk->disk->queue, blk_size);
+		blk_queue_logical_block_size(vblk->disk->queue, blk_size);
 
 	add_disk(vblk->disk);
 	return 0;
@@ -356,6 +421,7 @@ static struct virtio_device_id id_table[] = {
 static unsigned int features[] = {
 	VIRTIO_BLK_F_BARRIER, VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX,
 	VIRTIO_BLK_F_GEOMETRY, VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+	VIRTIO_BLK_F_SCSI, VIRTIO_BLK_F_IDENTIFY
 };
 
 static struct virtio_driver virtio_blk = {
diff --git a/drivers/block/xd.c b/drivers/block/xd.c
index 64b496fce98b..ce2429219925 100644
--- a/drivers/block/xd.c
+++ b/drivers/block/xd.c
@@ -305,30 +305,25 @@ static void do_xd_request (struct request_queue * q)
 	if (xdc_busy)
 		return;
 
-	while ((req = elv_next_request(q)) != NULL) {
-		unsigned block = req->sector;
-		unsigned count = req->nr_sectors;
-		int rw = rq_data_dir(req);
+	req = blk_fetch_request(q);
+	while (req) {
+		unsigned block = blk_rq_pos(req);
+		unsigned count = blk_rq_cur_sectors(req);
 		XD_INFO *disk = req->rq_disk->private_data;
-		int res = 0;
+		int res = -EIO;
 		int retry;
 
-		if (!blk_fs_request(req)) {
-			end_request(req, 0);
-			continue;
-		}
-		if (block + count > get_capacity(req->rq_disk)) {
-			end_request(req, 0);
-			continue;
-		}
-		if (rw != READ && rw != WRITE) {
-			printk("do_xd_request: unknown request\n");
-			end_request(req, 0);
-			continue;
-		}
+		if (!blk_fs_request(req))
+			goto done;
+		if (block + count > get_capacity(req->rq_disk))
+			goto done;
 		for (retry = 0; (retry < XD_RETRIES) && !res; retry++)
-			res = xd_readwrite(rw, disk, req->buffer, block, count);
-		end_request(req, res);	/* wrap up, 0 = fail, 1 = success */
+			res = xd_readwrite(rq_data_dir(req), disk, req->buffer,
+					   block, count);
+	done:
+		/* wrap up, 0 = success, -errno = fail */
+		if (!__blk_end_request_cur(req, res))
+			req = blk_fetch_request(q);
 	}
 }
 
@@ -418,7 +413,7 @@ static int xd_readwrite (u_char operation,XD_INFO *p,char *buffer,u_int block,u_
 				printk("xd%c: %s timeout, recalibrating drive\n",'a'+drive,(operation == READ ? "read" : "write"));
 				xd_recalibrate(drive);
 				spin_lock_irq(&xd_lock);
-				return (0);
+				return -EIO;
 			case 2:
 				if (sense[0] & 0x30) {
 					printk("xd%c: %s - ",'a'+drive,(operation == READ ? "reading" : "writing"));
@@ -439,7 +434,7 @@ static int xd_readwrite (u_char operation,XD_INFO *p,char *buffer,u_int block,u_
 				else
 					printk(" - no valid disk address\n");
 				spin_lock_irq(&xd_lock);
-				return (0);
+				return -EIO;
 		}
 		if (xd_dma_buffer)
 			for (i=0; i < (temp * 0x200); i++)
@@ -448,7 +443,7 @@ static int xd_readwrite (u_char operation,XD_INFO *p,char *buffer,u_int block,u_
 		count -= temp, buffer += temp * 0x200, block += temp;
 	}
 	spin_lock_irq(&xd_lock);
-	return (1);
+	return 0;
 }
 
 /* xd_recalibrate: recalibrate a given drive and reset controller if necessary */
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index a6cbf7b808e6..c1996829d5ec 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -122,7 +122,7 @@ static DEFINE_SPINLOCK(blkif_io_lock);
 static int get_id_from_freelist(struct blkfront_info *info)
 {
 	unsigned long free = info->shadow_free;
-	BUG_ON(free > BLK_RING_SIZE);
+	BUG_ON(free >= BLK_RING_SIZE);
 	info->shadow_free = info->shadow[free].req.id;
 	info->shadow[free].req.id = 0x0fffffee; /* debug */
 	return free;
@@ -231,7 +231,7 @@ static int blkif_queue_request(struct request *req)
 	info->shadow[id].request = (unsigned long)req;
 
 	ring_req->id = id;
-	ring_req->sector_number = (blkif_sector_t)req->sector;
+	ring_req->sector_number = (blkif_sector_t)blk_rq_pos(req);
 	ring_req->handle = info->handle;
 
 	ring_req->operation = rq_data_dir(req) ?
@@ -299,25 +299,25 @@ static void do_blkif_request(struct request_queue *rq)
 
 	queued = 0;
 
-	while ((req = elv_next_request(rq)) != NULL) {
+	while ((req = blk_peek_request(rq)) != NULL) {
 		info = req->rq_disk->private_data;
-		if (!blk_fs_request(req)) {
-			end_request(req, 0);
-			continue;
-		}
 
 		if (RING_FULL(&info->ring))
 			goto wait;
 
+		blk_start_request(req);
+
+		if (!blk_fs_request(req)) {
+			__blk_end_request_all(req, -EIO);
+			continue;
+		}
+
 		pr_debug("do_blk_req %p: cmd %p, sec %lx, "
-			 "(%u/%li) buffer:%p [%s]\n",
-			 req, req->cmd, (unsigned long)req->sector,
-			 req->current_nr_sectors,
-			 req->nr_sectors, req->buffer,
-			 rq_data_dir(req) ? "write" : "read");
+			 "(%u/%u) buffer:%p [%s]\n",
+			 req, req->cmd, (unsigned long)blk_rq_pos(req),
+			 blk_rq_cur_sectors(req), blk_rq_sectors(req),
+			 req->buffer, rq_data_dir(req) ? "write" : "read");
 
-
-		blkdev_dequeue_request(req);
 		if (blkif_queue_request(req)) {
 			blk_requeue_request(rq, req);
 wait:
@@ -344,7 +344,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
 	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
-	blk_queue_hardsect_size(rq, sector_size);
+	blk_queue_logical_block_size(rq, sector_size);
 	blk_queue_max_sectors(rq, 512);
 
 	/* Each segment in a request is up to an aligned page in size. */
@@ -551,7 +551,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 
 	for (i = info->ring.rsp_cons; i != rp; i++) {
 		unsigned long id;
-		int ret;
 
 		bret = RING_GET_RESPONSE(&info->ring, i);
 		id   = bret->id;
@@ -578,8 +577,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
 					"request: %x\n", bret->status);
 
-			ret = __blk_end_request(req, error, blk_rq_bytes(req));
-			BUG_ON(ret);
+			__blk_end_request_all(req, error);
 			break;
 		default:
 			BUG();
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index 4aecf5dc6a93..f08491a3a813 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -463,10 +463,11 @@ struct request *ace_get_next_request(struct request_queue * q)
 {
 	struct request *req;
 
-	while ((req = elv_next_request(q)) != NULL) {
+	while ((req = blk_peek_request(q)) != NULL) {
 		if (blk_fs_request(req))
 			break;
-		end_request(req, 0);
+		blk_start_request(req);
+		__blk_end_request_all(req, -EIO);
 	}
 	return req;
 }
@@ -492,9 +493,13 @@ static void ace_fsm_dostate(struct ace_device *ace)
 		set_capacity(ace->gd, 0);
 		dev_info(ace->dev, "No CF in slot\n");
 
-		/* Drop all pending requests */
-		while ((req = elv_next_request(ace->queue)) != NULL)
-			end_request(req, 0);
+		/* Drop all in-flight and pending requests */
+		if (ace->req) {
+			__blk_end_request_all(ace->req, -EIO);
+			ace->req = NULL;
+		}
+		while ((req = blk_fetch_request(ace->queue)) != NULL)
+			__blk_end_request_all(req, -EIO);
 
 		/* Drop back to IDLE state and notify waiters */
 		ace->fsm_state = ACE_FSM_STATE_IDLE;
@@ -642,19 +647,21 @@ static void ace_fsm_dostate(struct ace_device *ace)
 			ace->fsm_state = ACE_FSM_STATE_IDLE;
 			break;
 		}
+		blk_start_request(req);
 
 		/* Okay, it's a data request, set it up for transfer */
 		dev_dbg(ace->dev,
-			"request: sec=%llx hcnt=%lx, ccnt=%x, dir=%i\n",
-			(unsigned long long) req->sector, req->hard_nr_sectors,
-			req->current_nr_sectors, rq_data_dir(req));
+			"request: sec=%llx hcnt=%x, ccnt=%x, dir=%i\n",
+			(unsigned long long)blk_rq_pos(req),
+			blk_rq_sectors(req), blk_rq_cur_sectors(req),
+			rq_data_dir(req));
 
 		ace->req = req;
 		ace->data_ptr = req->buffer;
-		ace->data_count = req->current_nr_sectors * ACE_BUF_PER_SECTOR;
-		ace_out32(ace, ACE_MPULBA, req->sector & 0x0FFFFFFF);
+		ace->data_count = blk_rq_cur_sectors(req) * ACE_BUF_PER_SECTOR;
+		ace_out32(ace, ACE_MPULBA, blk_rq_pos(req) & 0x0FFFFFFF);
 
-		count = req->hard_nr_sectors;
+		count = blk_rq_sectors(req);
 		if (rq_data_dir(req)) {
 			/* Kick off write request */
 			dev_dbg(ace->dev, "write data\n");
@@ -688,7 +695,7 @@ static void ace_fsm_dostate(struct ace_device *ace)
 			dev_dbg(ace->dev,
 				"CFBSY set; t=%i iter=%i c=%i dc=%i irq=%i\n",
 				ace->fsm_task, ace->fsm_iter_num,
-				ace->req->current_nr_sectors * 16,
+				blk_rq_cur_sectors(ace->req) * 16,
 				ace->data_count, ace->in_irq);
 			ace_fsm_yield(ace);	/* need to poll CFBSY bit */
 			break;
@@ -697,7 +704,7 @@ static void ace_fsm_dostate(struct ace_device *ace)
 			dev_dbg(ace->dev,
 				"DATABUF not set; t=%i iter=%i c=%i dc=%i irq=%i\n",
 				ace->fsm_task, ace->fsm_iter_num,
-				ace->req->current_nr_sectors * 16,
+				blk_rq_cur_sectors(ace->req) * 16,
 				ace->data_count, ace->in_irq);
 			ace_fsm_yieldirq(ace);
 			break;
@@ -717,14 +724,13 @@ static void ace_fsm_dostate(struct ace_device *ace)
 		}
 
 		/* bio finished; is there another one? */
-		if (__blk_end_request(ace->req, 0,
-					blk_rq_cur_bytes(ace->req))) {
-			/* dev_dbg(ace->dev, "next block; h=%li c=%i\n",
-			 *      ace->req->hard_nr_sectors,
-			 *      ace->req->current_nr_sectors);
+		if (__blk_end_request_cur(ace->req, 0)) {
+			/* dev_dbg(ace->dev, "next block; h=%u c=%u\n",
+			 *      blk_rq_sectors(ace->req),
+			 *      blk_rq_cur_sectors(ace->req));
 			 */
 			ace->data_ptr = ace->req->buffer;
-			ace->data_count = ace->req->current_nr_sectors * 16;
+			ace->data_count = blk_rq_cur_sectors(ace->req) * 16;
 			ace_fsm_yieldirq(ace);
 			break;
 		}
@@ -978,7 +984,7 @@ static int __devinit ace_setup(struct ace_device *ace)
 	ace->queue = blk_init_queue(ace_request, &ace->lock);
 	if (ace->queue == NULL)
 		goto err_blk_initq;
-	blk_queue_hardsect_size(ace->queue, 512);
+	blk_queue_logical_block_size(ace->queue, 512);
 
 	/*
 	 * Allocate and initialize GD structure
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index 80754cdd3119..4575171e5beb 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -70,15 +70,18 @@ static struct gendisk *z2ram_gendisk;
 static void do_z2_request(struct request_queue *q)
 {
 	struct request *req;
-	while ((req = elv_next_request(q)) != NULL) {
-		unsigned long start = req->sector << 9;
-		unsigned long len  = req->current_nr_sectors << 9;
+
+	req = blk_fetch_request(q);
+	while (req) {
+		unsigned long start = blk_rq_pos(req) << 9;
+		unsigned long len  = blk_rq_cur_bytes(req);
+		int err = 0;
 
 		if (start + len > z2ram_size) {
 			printk( KERN_ERR DEVICE_NAME ": bad access: block=%lu, count=%u\n",
-				req->sector, req->current_nr_sectors);
-			end_request(req, 0);
-			continue;
+				blk_rq_pos(req), blk_rq_cur_sectors(req));
+			err = -EIO;
+			goto done;
 		}
 		while (len) {
 			unsigned long addr = start & Z2RAM_CHUNKMASK;
@@ -93,7 +96,9 @@ static void do_z2_request(struct request_queue *q)
 			start += size;
 			len -= size;
 		}
-		end_request(req, 1);
+	done:
+		if (!__blk_end_request_cur(req, err))
+			req = blk_fetch_request(q);
 	}
 }
 
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index af761dc434f6..4895f0e05322 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -277,8 +277,8 @@ static int hci_uart_tty_open(struct tty_struct *tty)
 	/* FIXME: why is this needed. Note don't use ldisc_ref here as the
 	   open path is before the ldisc is referencable */
 
-	if (tty->ldisc.ops->flush_buffer)
-		tty->ldisc.ops->flush_buffer(tty);
+	if (tty->ldisc->ops->flush_buffer)
+		tty->ldisc->ops->flush_buffer(tty);
 	tty_driver_flush_buffer(tty);
 
 	return 0;
@@ -463,7 +463,6 @@ static int hci_uart_tty_ioctl(struct tty_struct *tty, struct file * file,
 				clear_bit(HCI_UART_PROTO_SET, &hu->flags);
 				return err;
 			}
-			tty->low_latency = 1;
 		} else
 			return -EBUSY;
 		break;
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index cceace61ef28..71d1b9bab70b 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2101,8 +2101,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		nr = nframes;
 		if (cdi->cdda_method == CDDA_BPC_SINGLE)
 			nr = 1;
-		if (nr * CD_FRAMESIZE_RAW > (q->max_sectors << 9))
-			nr = (q->max_sectors << 9) / CD_FRAMESIZE_RAW;
+		if (nr * CD_FRAMESIZE_RAW > (queue_max_sectors(q) << 9))
+			nr = (queue_max_sectors(q) << 9) / CD_FRAMESIZE_RAW;
 
 		len = nr * CD_FRAMESIZE_RAW;
 
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 2eecb779437b..b5621f27c4be 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -584,8 +584,8 @@ static void gdrom_readdisk_dma(struct work_struct *work)
 	list_for_each_safe(elem, next, &gdrom_deferred) {
 		req = list_entry(elem, struct request, queuelist);
 		spin_unlock(&gdrom_lock);
-		block = req->sector/GD_TO_BLK + GD_SESSION_OFFSET;
-		block_cnt = req->nr_sectors/GD_TO_BLK;
+		block = blk_rq_pos(req)/GD_TO_BLK + GD_SESSION_OFFSET;
+		block_cnt = blk_rq_sectors(req)/GD_TO_BLK;
 		ctrl_outl(PHYSADDR(req->buffer), GDROM_DMA_STARTADDR_REG);
 		ctrl_outl(block_cnt * GDROM_HARD_SECTOR, GDROM_DMA_LENGTH_REG);
 		ctrl_outl(1, GDROM_DMA_DIRECTION_REG);
@@ -632,39 +632,35 @@ static void gdrom_readdisk_dma(struct work_struct *work)
 		* before handling ending the request */
 		spin_lock(&gdrom_lock);
 		list_del_init(&req->queuelist);
-		__blk_end_request(req, err, blk_rq_bytes(req));
+		__blk_end_request_all(req, err);
 	}
 	spin_unlock(&gdrom_lock);
 	kfree(read_command);
 }
 
-static void gdrom_request_handler_dma(struct request *req)
-{
-	/* dequeue, add to list of deferred work
-	* and then schedule workqueue */
-	blkdev_dequeue_request(req);
-	list_add_tail(&req->queuelist, &gdrom_deferred);
-	schedule_work(&work);
-}
-
 static void gdrom_request(struct request_queue *rq)
 {
 	struct request *req;
 
-	while ((req = elv_next_request(rq)) != NULL) {
+	while ((req = blk_fetch_request(rq)) != NULL) {
 		if (!blk_fs_request(req)) {
 			printk(KERN_DEBUG "GDROM: Non-fs request ignored\n");
-			end_request(req, 0);
+			__blk_end_request_all(req, -EIO);
+			continue;
 		}
 		if (rq_data_dir(req) != READ) {
 			printk(KERN_NOTICE "GDROM: Read only device -");
 			printk(" write request ignored\n");
-			end_request(req, 0);
+			__blk_end_request_all(req, -EIO);
+			continue;
 		}
-		if (req->nr_sectors)
-			gdrom_request_handler_dma(req);
-		else
-			end_request(req, 0);
+
+		/*
+		 * Add to list of deferred work and then schedule
+		 * workqueue.
+		 */
+		list_add_tail(&req->queuelist, &gdrom_deferred);
+		schedule_work(&work);
 	}
 }
 
@@ -743,7 +739,7 @@ static void __devinit probe_gdrom_setupdisk(void)
 
 static int __devinit probe_gdrom_setupqueue(void)
 {
-	blk_queue_hardsect_size(gd.gdrom_rq, GDROM_HARD_SECTOR);
+	blk_queue_logical_block_size(gd.gdrom_rq, GDROM_HARD_SECTOR);
 	/* using DMA so memory will need to be contiguous */
 	blk_queue_max_hw_segments(gd.gdrom_rq, 1);
 	/* set a large max size to get most from DMA */
diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c
index 9b1624e0ddeb..0fff646cc2f0 100644
--- a/drivers/cdrom/viocd.c
+++ b/drivers/cdrom/viocd.c
@@ -282,7 +282,7 @@ static int send_request(struct request *req)
 			viopath_targetinst(viopath_hostLp),
 			(u64)req, VIOVERSION << 16,
 			((u64)DEVICE_NR(diskinfo) << 48) | dmaaddr,
-			(u64)req->sector * 512, len, 0);
+			(u64)blk_rq_pos(req) * 512, len, 0);
 	if (hvrc != HvLpEvent_Rc_Good) {
 		printk(VIOCD_KERN_WARNING "hv error on op %d\n", (int)hvrc);
 		return -1;
@@ -291,36 +291,19 @@ static int send_request(struct request *req)
 	return 0;
 }
 
-static void viocd_end_request(struct request *req, int error)
-{
-	int nsectors = req->hard_nr_sectors;
-
-	/*
-	 * Make sure it's fully ended, and ensure that we process
-	 * at least one sector.
-	 */
-	if (blk_pc_request(req))
-		nsectors = (req->data_len + 511) >> 9;
-	if (!nsectors)
-		nsectors = 1;
-
-	if (__blk_end_request(req, error, nsectors << 9))
-		BUG();
-}
-
 static int rwreq;
 
 static void do_viocd_request(struct request_queue *q)
 {
 	struct request *req;
 
-	while ((rwreq == 0) && ((req = elv_next_request(q)) != NULL)) {
+	while ((rwreq == 0) && ((req = blk_fetch_request(q)) != NULL)) {
 		if (!blk_fs_request(req))
-			viocd_end_request(req, -EIO);
+			__blk_end_request_all(req, -EIO);
 		else if (send_request(req) < 0) {
 			printk(VIOCD_KERN_WARNING
 					"unable to send message to OS/400!");
-			viocd_end_request(req, -EIO);
+			__blk_end_request_all(req, -EIO);
 		} else
 			rwreq++;
 	}
@@ -486,8 +469,8 @@ static void vio_handle_cd_event(struct HvLpEvent *event)
 	case viocdopen:
 		if (event->xRc == 0) {
 			di = &viocd_diskinfo[bevent->disk];
-			blk_queue_hardsect_size(di->viocd_disk->queue,
-					bevent->block_size);
+			blk_queue_logical_block_size(di->viocd_disk->queue,
+						     bevent->block_size);
 			set_capacity(di->viocd_disk,
 					bevent->media_size *
 					bevent->block_size / 512);
@@ -531,9 +514,9 @@ return_complete:
 					"with rc %d:0x%04X: %s\n",
 					req, event->xRc,
 					bevent->sub_result, err->msg);
-			viocd_end_request(req, -EIO);
+			__blk_end_request_all(req, -EIO);
 		} else
-			viocd_end_request(req, 0);
+			__blk_end_request_all(req, 0);
 
 		/* restart handling of incoming requests */
 		spin_unlock_irqrestore(&viocd_reqlock, flags);
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 735bbe2be51a..02ecfd5fa61c 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -97,6 +97,19 @@ config DEVKMEM
 	  kind of kernel debugging operations.
 	  When in doubt, say "N".
 
+config BFIN_JTAG_COMM
+	tristate "Blackfin JTAG Communication"
+	depends on BLACKFIN
+	help
+	  Add support for emulating a TTY device over the Blackfin JTAG.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called bfin_jtag_comm.
+
+config BFIN_JTAG_COMM_CONSOLE
+	bool "Console on Blackfin JTAG"
+	depends on BFIN_JTAG_COMM=y
+
 config SERIAL_NONSTANDARD
 	bool "Non-standard serial port support"
 	depends on HAS_IOMEM
diff --git a/drivers/char/Makefile b/drivers/char/Makefile
index 9caf5b5ad1c0..189efcff08ce 100644
--- a/drivers/char/Makefile
+++ b/drivers/char/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_LEGACY_PTYS)	+= pty.o
 obj-$(CONFIG_UNIX98_PTYS)	+= pty.o
 obj-y				+= misc.o
 obj-$(CONFIG_VT)		+= vt_ioctl.o vc_screen.o selection.o keyboard.o
+obj-$(CONFIG_BFIN_JTAG_COMM)	+= bfin_jtag_comm.o
 obj-$(CONFIG_CONSOLE_TRANSLATIONS) += consolemap.o consolemap_deftbl.o
 obj-$(CONFIG_HW_CONSOLE)	+= vt.o defkeymap.o
 obj-$(CONFIG_AUDIT)		+= tty_audit.o
diff --git a/drivers/char/bfin_jtag_comm.c b/drivers/char/bfin_jtag_comm.c
new file mode 100644
index 000000000000..44c113d56045
--- /dev/null
+++ b/drivers/char/bfin_jtag_comm.c
@@ -0,0 +1,365 @@
+/*
+ * TTY over Blackfin JTAG Communication
+ *
+ * Copyright 2008-2009 Analog Devices Inc.
+ *
+ * Enter bugs at http://blackfin.uclinux.org/
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/circ_buf.h>
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+#include <asm/atomic.h>
+
+/* See the Debug/Emulation chapter in the HRM */
+#define EMUDOF   0x00000001	/* EMUDAT_OUT full & valid */
+#define EMUDIF   0x00000002	/* EMUDAT_IN full & valid */
+#define EMUDOOVF 0x00000004	/* EMUDAT_OUT overflow */
+#define EMUDIOVF 0x00000008	/* EMUDAT_IN overflow */
+
+#define DRV_NAME "bfin-jtag-comm"
+#define DEV_NAME "ttyBFJC"
+
+#define pr_init(fmt, args...) ({ static const __initdata char __fmt[] = fmt; printk(__fmt, ## args); })
+#define debug(fmt, args...) pr_debug(DRV_NAME ": " fmt, ## args)
+
+static inline uint32_t bfin_write_emudat(uint32_t emudat)
+{
+	__asm__ __volatile__("emudat = %0;" : : "d"(emudat));
+	return emudat;
+}
+
+static inline uint32_t bfin_read_emudat(void)
+{
+	uint32_t emudat;
+	__asm__ __volatile__("%0 = emudat;" : "=d"(emudat));
+	return emudat;
+}
+
+static inline uint32_t bfin_write_emudat_chars(char a, char b, char c, char d)
+{
+	return bfin_write_emudat((a << 0) | (b << 8) | (c << 16) | (d << 24));
+}
+
+#define CIRC_SIZE 2048	/* see comment in tty_io.c:do_tty_write() */
+#define CIRC_MASK (CIRC_SIZE - 1)
+#define circ_empty(circ)     ((circ)->head == (circ)->tail)
+#define circ_free(circ)      CIRC_SPACE((circ)->head, (circ)->tail, CIRC_SIZE)
+#define circ_cnt(circ)       CIRC_CNT((circ)->head, (circ)->tail, CIRC_SIZE)
+#define circ_byte(circ, idx) ((circ)->buf[(idx) & CIRC_MASK])
+
+static struct tty_driver *bfin_jc_driver;
+static struct task_struct *bfin_jc_kthread;
+static struct tty_struct * volatile bfin_jc_tty;
+static unsigned long bfin_jc_count;
+static DEFINE_MUTEX(bfin_jc_tty_mutex);
+static volatile struct circ_buf bfin_jc_write_buf;
+
+static int
+bfin_jc_emudat_manager(void *arg)
+{
+	uint32_t inbound_len = 0, outbound_len = 0;
+
+	while (!kthread_should_stop()) {
+		/* no one left to give data to, so sleep */
+		if (bfin_jc_tty == NULL && circ_empty(&bfin_jc_write_buf)) {
+			debug("waiting for readers\n");
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+			schedule();
+			__set_current_state(TASK_RUNNING);
+		}
+
+		/* no data available, so just chill */
+		if (!(bfin_read_DBGSTAT() & EMUDIF) && circ_empty(&bfin_jc_write_buf)) {
+			debug("waiting for data (in_len = %i) (circ: %i %i)\n",
+				inbound_len, bfin_jc_write_buf.tail, bfin_jc_write_buf.head);
+			if (inbound_len)
+				schedule();
+			else
+				schedule_timeout_interruptible(HZ);
+			continue;
+		}
+
+		/* if incoming data is ready, eat it */
+		if (bfin_read_DBGSTAT() & EMUDIF) {
+			struct tty_struct *tty;
+			mutex_lock(&bfin_jc_tty_mutex);
+			tty = (struct tty_struct *)bfin_jc_tty;
+			if (tty != NULL) {
+				uint32_t emudat = bfin_read_emudat();
+				if (inbound_len == 0) {
+					debug("incoming length: 0x%08x\n", emudat);
+					inbound_len = emudat;
+				} else {
+					size_t num_chars = (4 <= inbound_len ? 4 : inbound_len);
+					debug("  incoming data: 0x%08x (pushing %zu)\n", emudat, num_chars);
+					inbound_len -= num_chars;
+					tty_insert_flip_string(tty, (unsigned char *)&emudat, num_chars);
+					tty_flip_buffer_push(tty);
+				}
+			}
+			mutex_unlock(&bfin_jc_tty_mutex);
+		}
+
+		/* if outgoing data is ready, post it */
+		if (!(bfin_read_DBGSTAT() & EMUDOF) && !circ_empty(&bfin_jc_write_buf)) {
+			if (outbound_len == 0) {
+				outbound_len = circ_cnt(&bfin_jc_write_buf);
+				bfin_write_emudat(outbound_len);
+				debug("outgoing length: 0x%08x\n", outbound_len);
+			} else {
+				struct tty_struct *tty;
+				int tail = bfin_jc_write_buf.tail;
+				size_t ate = (4 <= outbound_len ? 4 : outbound_len);
+				uint32_t emudat =
+				bfin_write_emudat_chars(
+					circ_byte(&bfin_jc_write_buf, tail + 0),
+					circ_byte(&bfin_jc_write_buf, tail + 1),
+					circ_byte(&bfin_jc_write_buf, tail + 2),
+					circ_byte(&bfin_jc_write_buf, tail + 3)
+				);
+				bfin_jc_write_buf.tail += ate;
+				outbound_len -= ate;
+				mutex_lock(&bfin_jc_tty_mutex);
+				tty = (struct tty_struct *)bfin_jc_tty;
+				if (tty)
+					tty_wakeup(tty);
+				mutex_unlock(&bfin_jc_tty_mutex);
+				debug("  outgoing data: 0x%08x (pushing %zu)\n", emudat, ate);
+			}
+		}
+	}
+
+	__set_current_state(TASK_RUNNING);
+	return 0;
+}
+
+static int
+bfin_jc_open(struct tty_struct *tty, struct file *filp)
+{
+	mutex_lock(&bfin_jc_tty_mutex);
+	debug("open %lu\n", bfin_jc_count);
+	++bfin_jc_count;
+	bfin_jc_tty = tty;
+	wake_up_process(bfin_jc_kthread);
+	mutex_unlock(&bfin_jc_tty_mutex);
+	return 0;
+}
+
+static void
+bfin_jc_close(struct tty_struct *tty, struct file *filp)
+{
+	mutex_lock(&bfin_jc_tty_mutex);
+	debug("close %lu\n", bfin_jc_count);
+	if (--bfin_jc_count == 0)
+		bfin_jc_tty = NULL;
+	wake_up_process(bfin_jc_kthread);
+	mutex_unlock(&bfin_jc_tty_mutex);
+}
+
+/* XXX: we dont handle the put_char() case where we must handle count = 1 */
+static int
+bfin_jc_circ_write(const unsigned char *buf, int count)
+{
+	int i;
+	count = min(count, circ_free(&bfin_jc_write_buf));
+	debug("going to write chunk of %i bytes\n", count);
+	for (i = 0; i < count; ++i)
+		circ_byte(&bfin_jc_write_buf, bfin_jc_write_buf.head + i) = buf[i];
+	bfin_jc_write_buf.head += i;
+	return i;
+}
+
+#ifndef CONFIG_BFIN_JTAG_COMM_CONSOLE
+# define acquire_console_sem()
+# define release_console_sem()
+#endif
+static int
+bfin_jc_write(struct tty_struct *tty, const unsigned char *buf, int count)
+{
+	int i;
+	acquire_console_sem();
+	i = bfin_jc_circ_write(buf, count);
+	release_console_sem();
+	wake_up_process(bfin_jc_kthread);
+	return i;
+}
+
+static void
+bfin_jc_flush_chars(struct tty_struct *tty)
+{
+	wake_up_process(bfin_jc_kthread);
+}
+
+static int
+bfin_jc_write_room(struct tty_struct *tty)
+{
+	return circ_free(&bfin_jc_write_buf);
+}
+
+static int
+bfin_jc_chars_in_buffer(struct tty_struct *tty)
+{
+	return circ_cnt(&bfin_jc_write_buf);
+}
+
+static void
+bfin_jc_wait_until_sent(struct tty_struct *tty, int timeout)
+{
+	unsigned long expire = jiffies + timeout;
+	while (!circ_empty(&bfin_jc_write_buf)) {
+		if (signal_pending(current))
+			break;
+		if (time_after(jiffies, expire))
+			break;
+	}
+}
+
+static struct tty_operations bfin_jc_ops = {
+	.open            = bfin_jc_open,
+	.close           = bfin_jc_close,
+	.write           = bfin_jc_write,
+	/*.put_char        = bfin_jc_put_char,*/
+	.flush_chars     = bfin_jc_flush_chars,
+	.write_room      = bfin_jc_write_room,
+	.chars_in_buffer = bfin_jc_chars_in_buffer,
+	.wait_until_sent = bfin_jc_wait_until_sent,
+};
+
+static int __init bfin_jc_init(void)
+{
+	int ret;
+
+	bfin_jc_kthread = kthread_create(bfin_jc_emudat_manager, NULL, DRV_NAME);
+	if (IS_ERR(bfin_jc_kthread))
+		return PTR_ERR(bfin_jc_kthread);
+
+	ret = -ENOMEM;
+
+	bfin_jc_write_buf.head = bfin_jc_write_buf.tail = 0;
+	bfin_jc_write_buf.buf = kmalloc(CIRC_SIZE, GFP_KERNEL);
+	if (!bfin_jc_write_buf.buf)
+		goto err;
+
+	bfin_jc_driver = alloc_tty_driver(1);
+	if (!bfin_jc_driver)
+		goto err;
+
+	bfin_jc_driver->owner        = THIS_MODULE;
+	bfin_jc_driver->driver_name  = DRV_NAME;
+	bfin_jc_driver->name         = DEV_NAME;
+	bfin_jc_driver->type         = TTY_DRIVER_TYPE_SERIAL;
+	bfin_jc_driver->subtype      = SERIAL_TYPE_NORMAL;
+	bfin_jc_driver->init_termios = tty_std_termios;
+	tty_set_operations(bfin_jc_driver, &bfin_jc_ops);
+
+	ret = tty_register_driver(bfin_jc_driver);
+	if (ret)
+		goto err;
+
+	pr_init(KERN_INFO DRV_NAME ": initialized\n");
+
+	return 0;
+
+ err:
+	put_tty_driver(bfin_jc_driver);
+	kfree(bfin_jc_write_buf.buf);
+	kthread_stop(bfin_jc_kthread);
+	return ret;
+}
+module_init(bfin_jc_init);
+
+static void __exit bfin_jc_exit(void)
+{
+	kthread_stop(bfin_jc_kthread);
+	kfree(bfin_jc_write_buf.buf);
+	tty_unregister_driver(bfin_jc_driver);
+	put_tty_driver(bfin_jc_driver);
+}
+module_exit(bfin_jc_exit);
+
+#if defined(CONFIG_BFIN_JTAG_COMM_CONSOLE) || defined(CONFIG_EARLY_PRINTK)
+static void
+bfin_jc_straight_buffer_write(const char *buf, unsigned count)
+{
+	unsigned ate = 0;
+	while (bfin_read_DBGSTAT() & EMUDOF)
+		continue;
+	bfin_write_emudat(count);
+	while (ate < count) {
+		while (bfin_read_DBGSTAT() & EMUDOF)
+			continue;
+		bfin_write_emudat_chars(buf[ate], buf[ate+1], buf[ate+2], buf[ate+3]);
+		ate += 4;
+	}
+}
+#endif
+
+#ifdef CONFIG_BFIN_JTAG_COMM_CONSOLE
+static void
+bfin_jc_console_write(struct console *co, const char *buf, unsigned count)
+{
+	if (bfin_jc_kthread == NULL)
+		bfin_jc_straight_buffer_write(buf, count);
+	else
+		bfin_jc_circ_write(buf, count);
+}
+
+static struct tty_driver *
+bfin_jc_console_device(struct console *co, int *index)
+{
+	*index = co->index;
+	return bfin_jc_driver;
+}
+
+static struct console bfin_jc_console = {
+	.name    = DEV_NAME,
+	.write   = bfin_jc_console_write,
+	.device  = bfin_jc_console_device,
+	.flags   = CON_ANYTIME | CON_PRINTBUFFER,
+	.index   = -1,
+};
+
+static int __init bfin_jc_console_init(void)
+{
+	register_console(&bfin_jc_console);
+	return 0;
+}
+console_initcall(bfin_jc_console_init);
+#endif
+
+#ifdef CONFIG_EARLY_PRINTK
+static void __init
+bfin_jc_early_write(struct console *co, const char *buf, unsigned int count)
+{
+	bfin_jc_straight_buffer_write(buf, count);
+}
+
+static struct __initdata console bfin_jc_early_console = {
+	.name   = "early_BFJC",
+	.write   = bfin_jc_early_write,
+	.flags   = CON_ANYTIME | CON_PRINTBUFFER,
+	.index   = -1,
+};
+
+struct console * __init
+bfin_jc_early_init(unsigned int port, unsigned int cflag)
+{
+	return &bfin_jc_early_console;
+}
+#endif
+
+MODULE_AUTHOR("Mike Frysinger <vapier@gentoo.org>");
+MODULE_DESCRIPTION("TTY over Blackfin JTAG Communication");
+MODULE_LICENSE("GPL");
diff --git a/drivers/char/cyclades.c b/drivers/char/cyclades.c
index 1fdb9f657d8f..f3366d3f06cf 100644
--- a/drivers/char/cyclades.c
+++ b/drivers/char/cyclades.c
@@ -604,7 +604,6 @@
 
 #define NR_PORTS	256
 
-#define ZE_V1_NPORTS	64
 #define ZO_V1	0
 #define ZO_V2	1
 #define ZE_V1	2
@@ -663,18 +662,6 @@
 static void cy_throttle(struct tty_struct *tty);
 static void cy_send_xchar(struct tty_struct *tty, char ch);
 
-#define IS_CYC_Z(card) ((card).num_chips == (unsigned int)-1)
-
-#define Z_FPGA_CHECK(card) \
-	((readl(&((struct RUNTIME_9060 __iomem *) \
-		((card).ctl_addr))->init_ctrl) & (1<<17)) != 0)
-
-#define ISZLOADED(card)	(((ZO_V1 == readl(&((struct RUNTIME_9060 __iomem *) \
-			((card).ctl_addr))->mail_box_0)) || \
-			Z_FPGA_CHECK(card)) && \
-			(ZFIRM_ID == readl(&((struct FIRM_ID __iomem *) \
-			((card).base_addr+ID_ADDRESS))->signature)))
-
 #ifndef SERIAL_XMIT_SIZE
 #define	SERIAL_XMIT_SIZE	(min(PAGE_SIZE, 4096))
 #endif
@@ -687,8 +674,6 @@ static void cy_send_xchar(struct tty_struct *tty, char ch);
 #define DRIVER_VERSION	0x02010203
 #define RAM_SIZE 0x80000
 
-#define Z_FPGA_LOADED(X)	((readl(&(X)->init_ctrl) & (1<<17)) != 0)
-
 enum zblock_type {
 	ZBLOCK_PRG = 0,
 	ZBLOCK_FPGA = 1
@@ -883,6 +868,29 @@ static void cyz_rx_restart(unsigned long);
 static struct timer_list cyz_rx_full_timer[NR_PORTS];
 #endif				/* CONFIG_CYZ_INTR */
 
+static inline bool cy_is_Z(struct cyclades_card *card)
+{
+	return card->num_chips == (unsigned int)-1;
+}
+
+static inline bool __cyz_fpga_loaded(struct RUNTIME_9060 __iomem *ctl_addr)
+{
+	return readl(&ctl_addr->init_ctrl) & (1 << 17);
+}
+
+static inline bool cyz_fpga_loaded(struct cyclades_card *card)
+{
+	return __cyz_fpga_loaded(card->ctl_addr.p9060);
+}
+
+static inline bool cyz_is_loaded(struct cyclades_card *card)
+{
+	struct FIRM_ID __iomem *fw_id = card->base_addr + ID_ADDRESS;
+
+	return (card->hw_ver == ZO_V1 || cyz_fpga_loaded(card)) &&
+			readl(&fw_id->signature) == ZFIRM_ID;
+}
+
 static inline int serial_paranoia_check(struct cyclades_port *info,
 		char *name, const char *routine)
 {
@@ -1395,19 +1403,15 @@ cyz_fetch_msg(struct cyclades_card *cinfo,
 	unsigned long loc_doorbell;
 
 	firm_id = cinfo->base_addr + ID_ADDRESS;
-	if (!ISZLOADED(*cinfo))
-		return -1;
 	zfw_ctrl = cinfo->base_addr + (readl(&firm_id->zfwctrl_addr) & 0xfffff);
 	board_ctrl = &zfw_ctrl->board_ctrl;
 
-	loc_doorbell = readl(&((struct RUNTIME_9060 __iomem *)
-				  (cinfo->ctl_addr))->loc_doorbell);
+	loc_doorbell = readl(&cinfo->ctl_addr.p9060->loc_doorbell);
 	if (loc_doorbell) {
 		*cmd = (char)(0xff & loc_doorbell);
 		*channel = readl(&board_ctrl->fwcmd_channel);
 		*param = (__u32) readl(&board_ctrl->fwcmd_param);
-		cy_writel(&((struct RUNTIME_9060 __iomem *)(cinfo->ctl_addr))->
-			  loc_doorbell, 0xffffffff);
+		cy_writel(&cinfo->ctl_addr.p9060->loc_doorbell, 0xffffffff);
 		return 1;
 	}
 	return 0;
@@ -1424,15 +1428,14 @@ cyz_issue_cmd(struct cyclades_card *cinfo,
 	unsigned int index;
 
 	firm_id = cinfo->base_addr + ID_ADDRESS;
-	if (!ISZLOADED(*cinfo))
+	if (!cyz_is_loaded(cinfo))
 		return -1;
 
 	zfw_ctrl = cinfo->base_addr + (readl(&firm_id->zfwctrl_addr) & 0xfffff);
 	board_ctrl = &zfw_ctrl->board_ctrl;
 
 	index = 0;
-	pci_doorbell =
-	    &((struct RUNTIME_9060 __iomem *)(cinfo->ctl_addr))->pci_doorbell;
+	pci_doorbell = &cinfo->ctl_addr.p9060->pci_doorbell;
 	while ((readl(pci_doorbell) & 0xff) != 0) {
 		if (index++ == 1000)
 			return (int)(readl(pci_doorbell) & 0xff);
@@ -1624,10 +1627,8 @@ static void cyz_handle_cmd(struct cyclades_card *cinfo)
 	static struct BOARD_CTRL __iomem *board_ctrl;
 	static struct CH_CTRL __iomem *ch_ctrl;
 	static struct BUF_CTRL __iomem *buf_ctrl;
-	__u32 channel;
+	__u32 channel, param, fw_ver;
 	__u8 cmd;
-	__u32 param;
-	__u32 hw_ver, fw_ver;
 	int special_count;
 	int delta_count;
 
@@ -1635,8 +1636,6 @@ static void cyz_handle_cmd(struct cyclades_card *cinfo)
 	zfw_ctrl = cinfo->base_addr + (readl(&firm_id->zfwctrl_addr) & 0xfffff);
 	board_ctrl = &zfw_ctrl->board_ctrl;
 	fw_ver = readl(&board_ctrl->fw_version);
-	hw_ver = readl(&((struct RUNTIME_9060 __iomem *)(cinfo->ctl_addr))->
-			mail_box_0);
 
 	while (cyz_fetch_msg(cinfo, &channel, &cmd, &param) == 1) {
 		special_count = 0;
@@ -1737,15 +1736,7 @@ static irqreturn_t cyz_interrupt(int irq, void *dev_id)
 {
 	struct cyclades_card *cinfo = dev_id;
 
-	if (unlikely(cinfo == NULL)) {
-#ifdef CY_DEBUG_INTERRUPTS
-		printk(KERN_DEBUG "cyz_interrupt: spurious interrupt %d\n",
-									irq);
-#endif
-		return IRQ_NONE;	/* spurious interrupt */
-	}
-
-	if (unlikely(!ISZLOADED(*cinfo))) {
+	if (unlikely(!cyz_is_loaded(cinfo))) {
 #ifdef CY_DEBUG_INTERRUPTS
 		printk(KERN_DEBUG "cyz_interrupt: board not yet loaded "
 				"(IRQ%d).\n", irq);
@@ -1785,7 +1776,6 @@ static void cyz_poll(unsigned long arg)
 	struct tty_struct *tty;
 	struct FIRM_ID __iomem *firm_id;
 	struct ZFW_CTRL __iomem *zfw_ctrl;
-	struct BOARD_CTRL __iomem *board_ctrl;
 	struct BUF_CTRL __iomem *buf_ctrl;
 	unsigned long expires = jiffies + HZ;
 	unsigned int port, card;
@@ -1793,19 +1783,17 @@ static void cyz_poll(unsigned long arg)
 	for (card = 0; card < NR_CARDS; card++) {
 		cinfo = &cy_card[card];
 
-		if (!IS_CYC_Z(*cinfo))
+		if (!cy_is_Z(cinfo))
 			continue;
-		if (!ISZLOADED(*cinfo))
+		if (!cyz_is_loaded(cinfo))
 			continue;
 
 		firm_id = cinfo->base_addr + ID_ADDRESS;
 		zfw_ctrl = cinfo->base_addr +
 				(readl(&firm_id->zfwctrl_addr) & 0xfffff);
-		board_ctrl = &(zfw_ctrl->board_ctrl);
 
 	/* Skip first polling cycle to avoid racing conditions with the FW */
 		if (!cinfo->intr_enabled) {
-			cinfo->nports = (int)readl(&board_ctrl->n_channel);
 			cinfo->intr_enabled = 1;
 			continue;
 		}
@@ -1874,7 +1862,7 @@ static int startup(struct cyclades_port *info)
 
 	set_line_char(info);
 
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -1931,7 +1919,7 @@ static int startup(struct cyclades_port *info)
 		base_addr = card->base_addr;
 
 		firm_id = base_addr + ID_ADDRESS;
-		if (!ISZLOADED(*card))
+		if (!cyz_is_loaded(card))
 			return -ENODEV;
 
 		zfw_ctrl = card->base_addr +
@@ -2026,7 +2014,7 @@ static void start_xmit(struct cyclades_port *info)
 
 	card = info->card;
 	channel = info->line - card->first_line;
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -2070,7 +2058,7 @@ static void shutdown(struct cyclades_port *info)
 
 	card = info->card;
 	channel = info->line - card->first_line;
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -2126,7 +2114,7 @@ static void shutdown(struct cyclades_port *info)
 #endif
 
 		firm_id = base_addr + ID_ADDRESS;
-		if (!ISZLOADED(*card))
+		if (!cyz_is_loaded(card))
 			return;
 
 		zfw_ctrl = card->base_addr +
@@ -2233,7 +2221,7 @@ block_til_ready(struct tty_struct *tty, struct file *filp,
 #endif
 	info->port.blocked_open++;
 
-	if (!IS_CYC_Z(*cinfo)) {
+	if (!cy_is_Z(cinfo)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = cinfo->bus_index;
@@ -2296,7 +2284,7 @@ block_til_ready(struct tty_struct *tty, struct file *filp,
 
 		base_addr = cinfo->base_addr;
 		firm_id = base_addr + ID_ADDRESS;
-		if (!ISZLOADED(*cinfo)) {
+		if (!cyz_is_loaded(cinfo)) {
 			__set_current_state(TASK_RUNNING);
 			remove_wait_queue(&info->port.open_wait, &wait);
 			return -EINVAL;
@@ -2397,16 +2385,14 @@ static int cy_open(struct tty_struct *tty, struct file *filp)
 	   treat it as absent from the system.  This
 	   will make the user pay attention.
 	 */
-	if (IS_CYC_Z(*info->card)) {
+	if (cy_is_Z(info->card)) {
 		struct cyclades_card *cinfo = info->card;
 		struct FIRM_ID __iomem *firm_id = cinfo->base_addr + ID_ADDRESS;
 
-		if (!ISZLOADED(*cinfo)) {
-			if (((ZE_V1 == readl(&((struct RUNTIME_9060 __iomem *)
-					 (cinfo->ctl_addr))->mail_box_0)) &&
-					Z_FPGA_CHECK(*cinfo)) &&
-					(ZFIRM_HLT == readl(
-						&firm_id->signature))) {
+		if (!cyz_is_loaded(cinfo)) {
+			if (cinfo->hw_ver == ZE_V1 && cyz_fpga_loaded(cinfo) &&
+					readl(&firm_id->signature) ==
+					ZFIRM_HLT) {
 				printk(KERN_ERR "cyc:Cyclades-Z Error: you "
 					"need an external power supply for "
 					"this number of ports.\nFirmware "
@@ -2423,18 +2409,13 @@ static int cy_open(struct tty_struct *tty, struct file *filp)
 		   interrupts should be enabled as soon as the first open
 		   happens to one of its ports. */
 			if (!cinfo->intr_enabled) {
-				struct ZFW_CTRL __iomem *zfw_ctrl;
-				struct BOARD_CTRL __iomem *board_ctrl;
-
-				zfw_ctrl = cinfo->base_addr +
-					(readl(&firm_id->zfwctrl_addr) &
-					 0xfffff);
-
-				board_ctrl = &zfw_ctrl->board_ctrl;
+				u16 intr;
 
 				/* Enable interrupts on the PLX chip */
-				cy_writew(cinfo->ctl_addr + 0x68,
-					readw(cinfo->ctl_addr + 0x68) | 0x0900);
+				intr = readw(&cinfo->ctl_addr.p9060->
+						intr_ctrl_stat) | 0x0900;
+				cy_writew(&cinfo->ctl_addr.p9060->
+						intr_ctrl_stat, intr);
 				/* Enable interrupts on the FW */
 				retval = cyz_issue_cmd(cinfo, 0,
 						C_CM_IRQ_ENBL, 0L);
@@ -2442,8 +2423,6 @@ static int cy_open(struct tty_struct *tty, struct file *filp)
 					printk(KERN_ERR "cyc:IRQ enable retval "
 						"was %x\n", retval);
 				}
-				cinfo->nports =
-					(int)readl(&board_ctrl->n_channel);
 				cinfo->intr_enabled = 1;
 			}
 		}
@@ -2556,7 +2535,7 @@ static void cy_wait_until_sent(struct tty_struct *tty, int timeout)
 #endif
 	card = info->card;
 	channel = (info->line) - (card->first_line);
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -2601,7 +2580,7 @@ static void cy_flush_buffer(struct tty_struct *tty)
 	info->xmit_cnt = info->xmit_head = info->xmit_tail = 0;
 	spin_unlock_irqrestore(&card->card_lock, flags);
 
-	if (IS_CYC_Z(*card)) {	/* If it is a Z card, flush the on-board
+	if (cy_is_Z(card)) {	/* If it is a Z card, flush the on-board
 					   buffers as well */
 		spin_lock_irqsave(&card->card_lock, flags);
 		retval = cyz_issue_cmd(card, channel, C_CM_FLUSH_TX, 0L);
@@ -2682,7 +2661,7 @@ static void cy_close(struct tty_struct *tty, struct file *filp)
 
 	spin_lock_irqsave(&card->card_lock, flags);
 
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		int channel = info->line - card->first_line;
 		int index = card->bus_index;
 		void __iomem *base_addr = card->base_addr +
@@ -2902,7 +2881,7 @@ static int cy_chars_in_buffer(struct tty_struct *tty)
 	channel = (info->line) - (card->first_line);
 
 #ifdef Z_EXT_CHARS_IN_BUFFER
-	if (!IS_CYC_Z(cy_card[card])) {
+	if (!cy_is_Z(card)) {
 #endif				/* Z_EXT_CHARS_IN_BUFFER */
 #ifdef CY_DEBUG_IO
 		printk(KERN_DEBUG "cyc:cy_chars_in_buffer ttyC%d %d\n",
@@ -2984,7 +2963,6 @@ static void set_line_char(struct cyclades_port *info)
 	void __iomem *base_addr;
 	int chip, channel, index;
 	unsigned cflag, iflag;
-	unsigned short chip_number;
 	int baud, baud_rate = 0;
 	int i;
 
@@ -3013,9 +2991,8 @@ static void set_line_char(struct cyclades_port *info)
 
 	card = info->card;
 	channel = info->line - card->first_line;
-	chip_number = channel / 4;
 
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 
 		index = card->bus_index;
 
@@ -3233,21 +3210,17 @@ static void set_line_char(struct cyclades_port *info)
 	} else {
 		struct FIRM_ID __iomem *firm_id;
 		struct ZFW_CTRL __iomem *zfw_ctrl;
-		struct BOARD_CTRL __iomem *board_ctrl;
 		struct CH_CTRL __iomem *ch_ctrl;
-		struct BUF_CTRL __iomem *buf_ctrl;
 		__u32 sw_flow;
 		int retval;
 
 		firm_id = card->base_addr + ID_ADDRESS;
-		if (!ISZLOADED(*card))
+		if (!cyz_is_loaded(card))
 			return;
 
 		zfw_ctrl = card->base_addr +
 			(readl(&firm_id->zfwctrl_addr) & 0xfffff);
-		board_ctrl = &zfw_ctrl->board_ctrl;
 		ch_ctrl = &(zfw_ctrl->ch_ctrl[channel]);
-		buf_ctrl = &zfw_ctrl->buf_ctrl[channel];
 
 		/* baud rate */
 		baud = tty_get_baud_rate(info->port.tty);
@@ -3457,7 +3430,7 @@ static int get_lsr_info(struct cyclades_port *info, unsigned int __user *value)
 
 	card = info->card;
 	channel = (info->line) - (card->first_line);
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -3497,7 +3470,7 @@ static int cy_tiocmget(struct tty_struct *tty, struct file *file)
 
 	card = info->card;
 	channel = info->line - card->first_line;
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -3523,7 +3496,7 @@ static int cy_tiocmget(struct tty_struct *tty, struct file *file)
 	} else {
 		base_addr = card->base_addr;
 		firm_id = card->base_addr + ID_ADDRESS;
-		if (ISZLOADED(*card)) {
+		if (cyz_is_loaded(card)) {
 			zfw_ctrl = card->base_addr +
 				(readl(&firm_id->zfwctrl_addr) & 0xfffff);
 			board_ctrl = &zfw_ctrl->board_ctrl;
@@ -3566,7 +3539,7 @@ cy_tiocmset(struct tty_struct *tty, struct file *file,
 
 	card = info->card;
 	channel = (info->line) - (card->first_line);
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -3641,7 +3614,7 @@ cy_tiocmset(struct tty_struct *tty, struct file *file,
 		base_addr = card->base_addr;
 
 		firm_id = card->base_addr + ID_ADDRESS;
-		if (ISZLOADED(*card)) {
+		if (cyz_is_loaded(card)) {
 			zfw_ctrl = card->base_addr +
 				(readl(&firm_id->zfwctrl_addr) & 0xfffff);
 			board_ctrl = &zfw_ctrl->board_ctrl;
@@ -3713,7 +3686,7 @@ static int cy_break(struct tty_struct *tty, int break_state)
 	card = info->card;
 
 	spin_lock_irqsave(&card->card_lock, flags);
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		/* Let the transmit ISR take care of this (since it
 		   requires stuffing characters into the output stream).
 		 */
@@ -3782,7 +3755,7 @@ static int set_threshold(struct cyclades_port *info, unsigned long value)
 
 	card = info->card;
 	channel = info->line - card->first_line;
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -3810,7 +3783,7 @@ static int get_threshold(struct cyclades_port *info,
 
 	card = info->card;
 	channel = info->line - card->first_line;
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -3844,7 +3817,7 @@ static int set_timeout(struct cyclades_port *info, unsigned long value)
 
 	card = info->card;
 	channel = info->line - card->first_line;
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -3867,7 +3840,7 @@ static int get_timeout(struct cyclades_port *info,
 
 	card = info->card;
 	channel = info->line - card->first_line;
-	if (!IS_CYC_Z(*card)) {
+	if (!cy_is_Z(card)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		index = card->bus_index;
@@ -4121,7 +4094,7 @@ static void cy_send_xchar(struct tty_struct *tty, char ch)
 	card = info->card;
 	channel = info->line - card->first_line;
 
-	if (IS_CYC_Z(*card)) {
+	if (cy_is_Z(card)) {
 		if (ch == STOP_CHAR(tty))
 			cyz_issue_cmd(card, channel, C_CM_SENDXOFF, 0L);
 		else if (ch == START_CHAR(tty))
@@ -4154,7 +4127,7 @@ static void cy_throttle(struct tty_struct *tty)
 	card = info->card;
 
 	if (I_IXOFF(tty)) {
-		if (!IS_CYC_Z(*card))
+		if (!cy_is_Z(card))
 			cy_send_xchar(tty, STOP_CHAR(tty));
 		else
 			info->throttle = 1;
@@ -4162,7 +4135,7 @@ static void cy_throttle(struct tty_struct *tty)
 
 	if (tty->termios->c_cflag & CRTSCTS) {
 		channel = info->line - card->first_line;
-		if (!IS_CYC_Z(*card)) {
+		if (!cy_is_Z(card)) {
 			chip = channel >> 2;
 			channel &= 0x03;
 			index = card->bus_index;
@@ -4219,7 +4192,7 @@ static void cy_unthrottle(struct tty_struct *tty)
 	if (tty->termios->c_cflag & CRTSCTS) {
 		card = info->card;
 		channel = info->line - card->first_line;
-		if (!IS_CYC_Z(*card)) {
+		if (!cy_is_Z(card)) {
 			chip = channel >> 2;
 			channel &= 0x03;
 			index = card->bus_index;
@@ -4263,7 +4236,7 @@ static void cy_stop(struct tty_struct *tty)
 
 	cinfo = info->card;
 	channel = info->line - cinfo->first_line;
-	if (!IS_CYC_Z(*cinfo)) {
+	if (!cy_is_Z(cinfo)) {
 		index = cinfo->bus_index;
 		chip = channel >> 2;
 		channel &= 0x03;
@@ -4296,7 +4269,7 @@ static void cy_start(struct tty_struct *tty)
 	cinfo = info->card;
 	channel = info->line - cinfo->first_line;
 	index = cinfo->bus_index;
-	if (!IS_CYC_Z(*cinfo)) {
+	if (!cy_is_Z(cinfo)) {
 		chip = channel >> 2;
 		channel &= 0x03;
 		base_addr = cinfo->base_addr + (cy_chip_offset[chip] << index);
@@ -4347,33 +4320,20 @@ static void cy_hangup(struct tty_struct *tty)
 static int __devinit cy_init_card(struct cyclades_card *cinfo)
 {
 	struct cyclades_port *info;
-	u32 uninitialized_var(mailbox);
-	unsigned int nports, port;
+	unsigned int port;
 	unsigned short chip_number;
-	int uninitialized_var(index);
 
 	spin_lock_init(&cinfo->card_lock);
+	cinfo->intr_enabled = 0;
 
-	if (IS_CYC_Z(*cinfo)) {	/* Cyclades-Z */
-		mailbox = readl(&((struct RUNTIME_9060 __iomem *)
-				     cinfo->ctl_addr)->mail_box_0);
-		nports = (mailbox == ZE_V1) ? ZE_V1_NPORTS : 8;
-		cinfo->intr_enabled = 0;
-		cinfo->nports = 0;	/* Will be correctly set later, after
-					   Z FW is loaded */
-	} else {
-		index = cinfo->bus_index;
-		nports = cinfo->nports = CyPORTS_PER_CHIP * cinfo->num_chips;
-	}
-
-	cinfo->ports = kzalloc(sizeof(*cinfo->ports) * nports, GFP_KERNEL);
+	cinfo->ports = kcalloc(cinfo->nports, sizeof(*cinfo->ports),
+			GFP_KERNEL);
 	if (cinfo->ports == NULL) {
 		printk(KERN_ERR "Cyclades: cannot allocate ports\n");
-		cinfo->nports = 0;
 		return -ENOMEM;
 	}
 
-	for (port = cinfo->first_line; port < cinfo->first_line + nports;
+	for (port = cinfo->first_line; port < cinfo->first_line + cinfo->nports;
 			port++) {
 		info = &cinfo->ports[port - cinfo->first_line];
 		tty_port_init(&info->port);
@@ -4387,9 +4347,9 @@ static int __devinit cy_init_card(struct cyclades_card *cinfo)
 		init_completion(&info->shutdown_wait);
 		init_waitqueue_head(&info->delta_msr_wait);
 
-		if (IS_CYC_Z(*cinfo)) {
+		if (cy_is_Z(cinfo)) {
 			info->type = PORT_STARTECH;
-			if (mailbox == ZO_V1)
+			if (cinfo->hw_ver == ZO_V1)
 				info->xmit_fifo_size = CYZ_FIFO_SIZE;
 			else
 				info->xmit_fifo_size = 4 * CYZ_FIFO_SIZE;
@@ -4398,6 +4358,7 @@ static int __devinit cy_init_card(struct cyclades_card *cinfo)
 				cyz_rx_restart, (unsigned long)info);
 #endif
 		} else {
+			int index = cinfo->bus_index;
 			info->type = PORT_CIRRUS;
 			info->xmit_fifo_size = CyMAX_CHAR_FIFO;
 			info->cor1 = CyPARITY_NONE | Cy_1_STOP | Cy_8_BITS;
@@ -4430,7 +4391,7 @@ static int __devinit cy_init_card(struct cyclades_card *cinfo)
 	}
 
 #ifndef CONFIG_CYZ_INTR
-	if (IS_CYC_Z(*cinfo) && !timer_pending(&cyz_timerlist)) {
+	if (cy_is_Z(cinfo) && !timer_pending(&cyz_timerlist)) {
 		mod_timer(&cyz_timerlist, jiffies + 1);
 #ifdef CY_PCI_DEBUG
 		printk(KERN_DEBUG "Cyclades-Z polling initialized\n");
@@ -4621,11 +4582,12 @@ static int __init cy_detect_isa(void)
 
 		/* set cy_card */
 		cy_card[j].base_addr = cy_isa_address;
-		cy_card[j].ctl_addr = NULL;
+		cy_card[j].ctl_addr.p9050 = NULL;
 		cy_card[j].irq = (int)cy_isa_irq;
 		cy_card[j].bus_index = 0;
 		cy_card[j].first_line = cy_next_channel;
-		cy_card[j].num_chips = cy_isa_nchan / 4;
+		cy_card[j].num_chips = cy_isa_nchan / CyPORTS_PER_CHIP;
+		cy_card[j].nports = cy_isa_nchan;
 		if (cy_init_card(&cy_card[j])) {
 			cy_card[j].base_addr = NULL;
 			free_irq(cy_isa_irq, &cy_card[j]);
@@ -4781,7 +4743,7 @@ static int __devinit cyz_load_fw(struct pci_dev *pdev, void __iomem *base_addr,
 	struct CUSTOM_REG __iomem *cust = base_addr;
 	struct ZFW_CTRL __iomem *pt_zfwctrl;
 	void __iomem *tmp;
-	u32 mailbox, status;
+	u32 mailbox, status, nchan;
 	unsigned int i;
 	int retval;
 
@@ -4793,7 +4755,7 @@ static int __devinit cyz_load_fw(struct pci_dev *pdev, void __iomem *base_addr,
 
 	/* Check whether the firmware is already loaded and running. If
 	   positive, skip this board */
-	if (Z_FPGA_LOADED(ctl_addr) && readl(&fid->signature) == ZFIRM_ID) {
+	if (__cyz_fpga_loaded(ctl_addr) && readl(&fid->signature) == ZFIRM_ID) {
 		u32 cntval = readl(base_addr + 0x190);
 
 		udelay(100);
@@ -4812,7 +4774,7 @@ static int __devinit cyz_load_fw(struct pci_dev *pdev, void __iomem *base_addr,
 
 	mailbox = readl(&ctl_addr->mail_box_0);
 
-	if (mailbox == 0 || Z_FPGA_LOADED(ctl_addr)) {
+	if (mailbox == 0 || __cyz_fpga_loaded(ctl_addr)) {
 		/* stops CPU and set window to beginning of RAM */
 		cy_writel(&ctl_addr->loc_addr_base, WIN_CREG);
 		cy_writel(&cust->cpu_stop, 0);
@@ -4828,7 +4790,7 @@ static int __devinit cyz_load_fw(struct pci_dev *pdev, void __iomem *base_addr,
 				base_addr);
 		if (retval)
 			goto err_rel;
-		if (!Z_FPGA_LOADED(ctl_addr)) {
+		if (!__cyz_fpga_loaded(ctl_addr)) {
 			dev_err(&pdev->dev, "fw upload successful, but fw is "
 					"not loaded\n");
 			goto err_rel;
@@ -4887,7 +4849,7 @@ static int __devinit cyz_load_fw(struct pci_dev *pdev, void __iomem *base_addr,
 				"system before loading the new FW to the "
 				"Cyclades-Z.\n");
 
-			if (Z_FPGA_LOADED(ctl_addr))
+			if (__cyz_fpga_loaded(ctl_addr))
 				plx_init(pdev, irq, ctl_addr);
 
 			retval = -EIO;
@@ -4902,16 +4864,16 @@ static int __devinit cyz_load_fw(struct pci_dev *pdev, void __iomem *base_addr,
 			base_addr + ID_ADDRESS, readl(&fid->zfwctrl_addr),
 			base_addr + readl(&fid->zfwctrl_addr));
 
+	nchan = readl(&pt_zfwctrl->board_ctrl.n_channel);
 	dev_info(&pdev->dev, "Cyclades-Z FW loaded: version = %x, ports = %u\n",
-		readl(&pt_zfwctrl->board_ctrl.fw_version),
-		readl(&pt_zfwctrl->board_ctrl.n_channel));
+		readl(&pt_zfwctrl->board_ctrl.fw_version), nchan);
 
-	if (readl(&pt_zfwctrl->board_ctrl.n_channel) == 0) {
+	if (nchan == 0) {
 		dev_warn(&pdev->dev, "no Cyclades-Z ports were found. Please "
 			"check the connection between the Z host card and the "
 			"serial expanders.\n");
 
-		if (Z_FPGA_LOADED(ctl_addr))
+		if (__cyz_fpga_loaded(ctl_addr))
 			plx_init(pdev, irq, ctl_addr);
 
 		dev_info(&pdev->dev, "Null number of ports detected. Board "
@@ -4932,9 +4894,7 @@ static int __devinit cyz_load_fw(struct pci_dev *pdev, void __iomem *base_addr,
 	cy_writel(&ctl_addr->intr_ctrl_stat, readl(&ctl_addr->intr_ctrl_stat) |
 			0x00030800UL);
 
-	plx_init(pdev, irq, ctl_addr);
-
-	return 0;
+	return nchan;
 err_rel:
 	release_firmware(fw);
 err:
@@ -4946,7 +4906,7 @@ static int __devinit cy_pci_probe(struct pci_dev *pdev,
 {
 	void __iomem *addr0 = NULL, *addr2 = NULL;
 	char *card_name = NULL;
-	u32 mailbox;
+	u32 uninitialized_var(mailbox);
 	unsigned int device_id, nchan = 0, card_no, i;
 	unsigned char plx_ver;
 	int retval, irq;
@@ -5023,11 +4983,12 @@ static int __devinit cy_pci_probe(struct pci_dev *pdev,
 		}
 
 		/* Disable interrupts on the PLX before resetting it */
-		cy_writew(addr0 + 0x68, readw(addr0 + 0x68) & ~0x0900);
+		cy_writew(&ctl_addr->intr_ctrl_stat,
+				readw(&ctl_addr->intr_ctrl_stat) & ~0x0900);
 
 		plx_init(pdev, irq, addr0);
 
-		mailbox = (u32)readl(&ctl_addr->mail_box_0);
+		mailbox = readl(&ctl_addr->mail_box_0);
 
 		addr2 = ioremap_nocache(pci_resource_start(pdev, 2),
 				mailbox == ZE_V1 ? CyPCI_Ze_win : CyPCI_Zwin);
@@ -5038,12 +4999,8 @@ static int __devinit cy_pci_probe(struct pci_dev *pdev,
 
 		if (mailbox == ZE_V1) {
 			card_name = "Cyclades-Ze";
-
-			readl(&ctl_addr->mail_box_0);
-			nchan = ZE_V1_NPORTS;
 		} else {
 			card_name = "Cyclades-8Zo";
-
 #ifdef CY_PCI_DEBUG
 			if (mailbox == ZO_V1) {
 				cy_writel(&ctl_addr->loc_addr_base, WIN_CREG);
@@ -5065,15 +5022,12 @@ static int __devinit cy_pci_probe(struct pci_dev *pdev,
 			 */
 			if ((mailbox == ZO_V1) || (mailbox == ZO_V2))
 				cy_writel(addr2 + ID_ADDRESS, 0L);
-
-			retval = cyz_load_fw(pdev, addr2, addr0, irq);
-			if (retval)
-				goto err_unmap;
-			/* This must be a Cyclades-8Zo/PCI.  The extendable
-			   version will have a different device_id and will
-			   be allocated its maximum number of ports. */
-			nchan = 8;
 		}
+
+		retval = cyz_load_fw(pdev, addr2, addr0, irq);
+		if (retval <= 0)
+			goto err_unmap;
+		nchan = retval;
 	}
 
 	if ((cy_next_channel + nchan) > NR_PORTS) {
@@ -5103,8 +5057,10 @@ static int __devinit cy_pci_probe(struct pci_dev *pdev,
 			dev_err(&pdev->dev, "could not allocate IRQ\n");
 			goto err_unmap;
 		}
-		cy_card[card_no].num_chips = nchan / 4;
+		cy_card[card_no].num_chips = nchan / CyPORTS_PER_CHIP;
 	} else {
+		cy_card[card_no].hw_ver = mailbox;
+		cy_card[card_no].num_chips = (unsigned int)-1;
 #ifdef CONFIG_CYZ_INTR
 		/* allocate IRQ only if board has an IRQ */
 		if (irq != 0 && irq != 255) {
@@ -5117,15 +5073,15 @@ static int __devinit cy_pci_probe(struct pci_dev *pdev,
 			}
 		}
 #endif				/* CONFIG_CYZ_INTR */
-		cy_card[card_no].num_chips = (unsigned int)-1;
 	}
 
 	/* set cy_card */
 	cy_card[card_no].base_addr = addr2;
-	cy_card[card_no].ctl_addr = addr0;
+	cy_card[card_no].ctl_addr.p9050 = addr0;
 	cy_card[card_no].irq = irq;
 	cy_card[card_no].bus_index = 1;
 	cy_card[card_no].first_line = cy_next_channel;
+	cy_card[card_no].nports = nchan;
 	retval = cy_init_card(&cy_card[card_no]);
 	if (retval)
 		goto err_null;
@@ -5138,17 +5094,20 @@ static int __devinit cy_pci_probe(struct pci_dev *pdev,
 		plx_ver = readb(addr2 + CyPLX_VER) & 0x0f;
 		switch (plx_ver) {
 		case PLX_9050:
-
 			cy_writeb(addr0 + 0x4c, 0x43);
 			break;
 
 		case PLX_9060:
 		case PLX_9080:
 		default:	/* Old boards, use PLX_9060 */
-			plx_init(pdev, irq, addr0);
-			cy_writew(addr0 + 0x68, readw(addr0 + 0x68) | 0x0900);
+		{
+			struct RUNTIME_9060 __iomem *ctl_addr = addr0;
+			plx_init(pdev, irq, ctl_addr);
+			cy_writew(&ctl_addr->intr_ctrl_stat,
+				readw(&ctl_addr->intr_ctrl_stat) | 0x0900);
 			break;
 		}
+		}
 	}
 
 	dev_info(&pdev->dev, "%s/PCI #%d found: %d channels starting from "
@@ -5179,22 +5138,23 @@ static void __devexit cy_pci_remove(struct pci_dev *pdev)
 	unsigned int i;
 
 	/* non-Z with old PLX */
-	if (!IS_CYC_Z(*cinfo) && (readb(cinfo->base_addr + CyPLX_VER) & 0x0f) ==
+	if (!cy_is_Z(cinfo) && (readb(cinfo->base_addr + CyPLX_VER) & 0x0f) ==
 			PLX_9050)
-		cy_writeb(cinfo->ctl_addr + 0x4c, 0);
+		cy_writeb(cinfo->ctl_addr.p9050 + 0x4c, 0);
 	else
 #ifndef CONFIG_CYZ_INTR
-		if (!IS_CYC_Z(*cinfo))
+		if (!cy_is_Z(cinfo))
 #endif
-		cy_writew(cinfo->ctl_addr + 0x68,
-				readw(cinfo->ctl_addr + 0x68) & ~0x0900);
+		cy_writew(&cinfo->ctl_addr.p9060->intr_ctrl_stat,
+			readw(&cinfo->ctl_addr.p9060->intr_ctrl_stat) &
+			~0x0900);
 
 	iounmap(cinfo->base_addr);
-	if (cinfo->ctl_addr)
-		iounmap(cinfo->ctl_addr);
+	if (cinfo->ctl_addr.p9050)
+		iounmap(cinfo->ctl_addr.p9050);
 	if (cinfo->irq
 #ifndef CONFIG_CYZ_INTR
-		&& !IS_CYC_Z(*cinfo)
+		&& !cy_is_Z(cinfo)
 #endif /* CONFIG_CYZ_INTR */
 		)
 		free_irq(cinfo->irq, cinfo);
@@ -5240,7 +5200,7 @@ static int cyclades_proc_show(struct seq_file *m, void *v)
 					(cur_jifs - info->idle_stats.recv_idle)/
 					HZ, info->idle_stats.overruns,
 					/* FIXME: double check locking */
-					(long)info->port.tty->ldisc.ops->num);
+					(long)info->port.tty->ldisc->ops->num);
 			else
 				seq_printf(m, "%3d %8lu %10lu %8lu "
 					"%10lu %8lu %9lu %6ld\n",
@@ -5386,11 +5346,11 @@ static void __exit cy_cleanup_module(void)
 			/* clear interrupt */
 			cy_writeb(card->base_addr + Cy_ClrIntr, 0);
 			iounmap(card->base_addr);
-			if (card->ctl_addr)
-				iounmap(card->ctl_addr);
+			if (card->ctl_addr.p9050)
+				iounmap(card->ctl_addr.p9050);
 			if (card->irq
 #ifndef CONFIG_CYZ_INTR
-				&& !IS_CYC_Z(*card)
+				&& !cy_is_Z(card)
 #endif /* CONFIG_CYZ_INTR */
 				)
 				free_irq(card->irq, card);
diff --git a/drivers/char/epca.c b/drivers/char/epca.c
index af7c13ca9493..abef1f7d84fe 100644
--- a/drivers/char/epca.c
+++ b/drivers/char/epca.c
@@ -745,7 +745,7 @@ static int epca_carrier_raised(struct tty_port *port)
 	return 0;
 }
 
-static void epca_raise_dtr_rts(struct tty_port *port)
+static void epca_dtr_rts(struct tty_port *port, int onoff)
 {
 }
 
@@ -925,7 +925,7 @@ static const struct tty_operations pc_ops = {
 
 static const struct tty_port_operations epca_port_ops = {
 	.carrier_raised = epca_carrier_raised,
-	.raise_dtr_rts = epca_raise_dtr_rts,
+	.dtr_rts = epca_dtr_rts,
 };
 
 static int info_open(struct tty_struct *tty, struct file *filp)
@@ -1518,7 +1518,7 @@ static void doevent(int crd)
 		if (event & MODEMCHG_IND) {
 			/* A modem signal change has been indicated */
 			ch->imodem = mstat;
-			if (test_bit(ASYNC_CHECK_CD, &ch->port.flags)) {
+			if (test_bit(ASYNCB_CHECK_CD, &ch->port.flags)) {
 				/* We are now receiving dcd */
 				if (mstat & ch->dcd)
 					wake_up_interruptible(&ch->port.open_wait);
@@ -1765,9 +1765,9 @@ static void epcaparam(struct tty_struct *tty, struct channel *ch)
 		 * that the driver will wait on carrier detect.
 		 */
 		if (ts->c_cflag & CLOCAL)
-			clear_bit(ASYNC_CHECK_CD, &ch->port.flags);
+			clear_bit(ASYNCB_CHECK_CD, &ch->port.flags);
 		else
-			set_bit(ASYNC_CHECK_CD, &ch->port.flags);
+			set_bit(ASYNCB_CHECK_CD, &ch->port.flags);
 		mval = ch->m_dtr | ch->m_rts;
 	} /* End CBAUD not detected */
 	iflag = termios2digi_i(ch, ts->c_iflag);
@@ -2114,8 +2114,8 @@ static int pc_ioctl(struct tty_struct *tty, struct file *file,
 			tty_wait_until_sent(tty, 0);
 		} else {
 			/* ldisc lock already held in ioctl */
-			if (tty->ldisc.ops->flush_buffer)
-				tty->ldisc.ops->flush_buffer(tty);
+			if (tty->ldisc->ops->flush_buffer)
+				tty->ldisc->ops->flush_buffer(tty);
 		}
 		unlock_kernel();
 		/* Fall Thru */
@@ -2244,7 +2244,8 @@ static void do_softint(struct work_struct *work)
 			if (test_and_clear_bit(EPCA_EVENT_HANGUP, &ch->event)) {
 				tty_hangup(tty);
 				wake_up_interruptible(&ch->port.open_wait);
-				clear_bit(ASYNC_NORMAL_ACTIVE, &ch->port.flags);
+				clear_bit(ASYNCB_NORMAL_ACTIVE,
+						&ch->port.flags);
 			}
 		}
 		tty_kref_put(tty);
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 340ba4f9dc54..4a9f3492b921 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -224,7 +224,7 @@ static void hpet_timer_set_irq(struct hpet_dev *devp)
 			break;
 		}
 
-		gsi = acpi_register_gsi(irq, ACPI_LEVEL_SENSITIVE,
+		gsi = acpi_register_gsi(NULL, irq, ACPI_LEVEL_SENSITIVE,
 					ACPI_ACTIVE_LOW);
 		if (gsi > 0)
 			break;
@@ -939,7 +939,7 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data)
 		irqp = &res->data.extended_irq;
 
 		for (i = 0; i < irqp->interrupt_count; i++) {
-			irq = acpi_register_gsi(irqp->interrupts[i],
+			irq = acpi_register_gsi(NULL, irqp->interrupts[i],
 				      irqp->triggering, irqp->polarity);
 			if (irq < 0)
 				return AE_ERROR;
diff --git a/drivers/char/ip2/i2lib.c b/drivers/char/ip2/i2lib.c
index 0061e18aff60..0d10b89218ed 100644
--- a/drivers/char/ip2/i2lib.c
+++ b/drivers/char/ip2/i2lib.c
@@ -868,11 +868,11 @@ i2Input(i2ChanStrPtr pCh)
 		amountToMove = count;
 	}
 	// Move the first block
-	pCh->pTTY->ldisc.ops->receive_buf( pCh->pTTY,
+	pCh->pTTY->ldisc->ops->receive_buf( pCh->pTTY,
 		 &(pCh->Ibuf[stripIndex]), NULL, amountToMove );
 	// If we needed to wrap, do the second data move
 	if (count > amountToMove) {
-		pCh->pTTY->ldisc.ops->receive_buf( pCh->pTTY,
+		pCh->pTTY->ldisc->ops->receive_buf( pCh->pTTY,
 		 pCh->Ibuf, NULL, count - amountToMove );
 	}
 	// Bump and wrap the stripIndex all at once by the amount of data read. This
diff --git a/drivers/char/ip2/ip2main.c b/drivers/char/ip2/ip2main.c
index afd9247cf082..517271c762e6 100644
--- a/drivers/char/ip2/ip2main.c
+++ b/drivers/char/ip2/ip2main.c
@@ -1315,8 +1315,8 @@ static inline void  isig(int sig, struct tty_struct *tty, int flush)
 	if (tty->pgrp)
 		kill_pgrp(tty->pgrp, sig, 1);
 	if (flush || !L_NOFLSH(tty)) {
-		if ( tty->ldisc.ops->flush_buffer )  
-			tty->ldisc.ops->flush_buffer(tty);
+		if ( tty->ldisc->ops->flush_buffer )  
+			tty->ldisc->ops->flush_buffer(tty);
 		i2InputFlush( tty->driver_data );
 	}
 }
diff --git a/drivers/char/isicom.c b/drivers/char/isicom.c
index a59eac584d16..4d745a89504f 100644
--- a/drivers/char/isicom.c
+++ b/drivers/char/isicom.c
@@ -329,7 +329,7 @@ static inline void drop_rts(struct isi_port *port)
 
 /* card->lock MUST NOT be held */
 
-static void isicom_raise_dtr_rts(struct tty_port *port)
+static void isicom_dtr_rts(struct tty_port *port, int on)
 {
 	struct isi_port *ip = container_of(port, struct isi_port, port);
 	struct isi_board *card = ip->card;
@@ -339,10 +339,17 @@ static void isicom_raise_dtr_rts(struct tty_port *port)
 	if (!lock_card(card))
 		return;
 
-	outw(0x8000 | (channel << card->shift_count) | 0x02, base);
-	outw(0x0f04, base);
-	InterruptTheCard(base);
-	ip->status |= (ISI_DTR | ISI_RTS);
+	if (on) {
+		outw(0x8000 | (channel << card->shift_count) | 0x02, base);
+		outw(0x0f04, base);
+		InterruptTheCard(base);
+		ip->status |= (ISI_DTR | ISI_RTS);
+	} else {
+		outw(0x8000 | (channel << card->shift_count) | 0x02, base);
+		outw(0x0C04, base);
+		InterruptTheCard(base);
+		ip->status &= ~(ISI_DTR | ISI_RTS);
+	}
 	unlock_card(card);
 }
 
@@ -1339,7 +1346,7 @@ static const struct tty_operations isicom_ops = {
 
 static const struct tty_port_operations isicom_port_ops = {
 	.carrier_raised		= isicom_carrier_raised,
-	.raise_dtr_rts		= isicom_raise_dtr_rts,
+	.dtr_rts		= isicom_dtr_rts,
 };
 
 static int __devinit reset_card(struct pci_dev *pdev,
diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c
index fff19f7e29d2..e18800c400b1 100644
--- a/drivers/char/istallion.c
+++ b/drivers/char/istallion.c
@@ -1140,14 +1140,14 @@ static int stli_carrier_raised(struct tty_port *port)
 	return (portp->sigs & TIOCM_CD) ? 1 : 0;
 }
 
-static void stli_raise_dtr_rts(struct tty_port *port)
+static void stli_dtr_rts(struct tty_port *port, int on)
 {
 	struct stliport *portp = container_of(port, struct stliport, port);
 	struct stlibrd *brdp = stli_brds[portp->brdnr];
-	stli_mkasysigs(&portp->asig, 1, 1);
+	stli_mkasysigs(&portp->asig, on, on);
 	if (stli_cmdwait(brdp, portp, A_SETSIGNALS, &portp->asig,
 		sizeof(asysigs_t), 0) < 0)
-			printk(KERN_WARNING "istallion: dtr raise failed.\n");
+			printk(KERN_WARNING "istallion: dtr set failed.\n");
 }
 
 
@@ -4417,7 +4417,7 @@ static const struct tty_operations stli_ops = {
 
 static const struct tty_port_operations stli_port_ops = {
 	.carrier_raised = stli_carrier_raised,
-	.raise_dtr_rts = stli_raise_dtr_rts,
+	.dtr_rts = stli_dtr_rts,
 };
 
 /*****************************************************************************/
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 65e12bca657c..f96d0bef855e 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -694,9 +694,8 @@ static ssize_t read_zero(struct file * file, char __user * buf,
 		written += chunk - unwritten;
 		if (unwritten)
 			break;
-		/* Consider changing this to just 'signal_pending()' with lots of testing */
-		if (fatal_signal_pending(current))
-			return written ? written : -EINTR;
+		if (signal_pending(current))
+			return written ? written : -ERESTARTSYS;
 		buf += chunk;
 		count -= chunk;
 		cond_resched();
diff --git a/drivers/char/moxa.c b/drivers/char/moxa.c
index 4a4cab73d0be..65b6ff2442c6 100644
--- a/drivers/char/moxa.c
+++ b/drivers/char/moxa.c
@@ -1184,6 +1184,11 @@ static int moxa_open(struct tty_struct *tty, struct file *filp)
 		return -ENODEV;
 	}
 
+	if (port % MAX_PORTS_PER_BOARD >= brd->numPorts) {
+		mutex_unlock(&moxa_openlock);
+		return -ENODEV;
+	}
+
 	ch = &brd->ports[port % MAX_PORTS_PER_BOARD];
 	ch->port.count++;
 	tty->driver_data = ch;
diff --git a/drivers/char/mxser.c b/drivers/char/mxser.c
index 13f8871e5b21..9533f43a30bb 100644
--- a/drivers/char/mxser.c
+++ b/drivers/char/mxser.c
@@ -547,14 +547,18 @@ static int mxser_carrier_raised(struct tty_port *port)
 	return (inb(mp->ioaddr + UART_MSR) & UART_MSR_DCD)?1:0;
 }
 
-static void mxser_raise_dtr_rts(struct tty_port *port)
+static void mxser_dtr_rts(struct tty_port *port, int on)
 {
 	struct mxser_port *mp = container_of(port, struct mxser_port, port);
 	unsigned long flags;
 
 	spin_lock_irqsave(&mp->slock, flags);
-	outb(inb(mp->ioaddr + UART_MCR) |
-		UART_MCR_DTR | UART_MCR_RTS, mp->ioaddr + UART_MCR);
+	if (on)
+		outb(inb(mp->ioaddr + UART_MCR) |
+			UART_MCR_DTR | UART_MCR_RTS, mp->ioaddr + UART_MCR);
+	else
+		outb(inb(mp->ioaddr + UART_MCR)&~(UART_MCR_DTR | UART_MCR_RTS),
+			mp->ioaddr + UART_MCR);
 	spin_unlock_irqrestore(&mp->slock, flags);
 }
 
@@ -2356,7 +2360,7 @@ static const struct tty_operations mxser_ops = {
 
 struct tty_port_operations mxser_port_ops = {
 	.carrier_raised = mxser_carrier_raised,
-	.raise_dtr_rts = mxser_raise_dtr_rts,
+	.dtr_rts = mxser_dtr_rts,
 };
 
 /*
diff --git a/drivers/char/n_hdlc.c b/drivers/char/n_hdlc.c
index bacb3e2872ae..461ece591a5b 100644
--- a/drivers/char/n_hdlc.c
+++ b/drivers/char/n_hdlc.c
@@ -342,8 +342,8 @@ static int n_hdlc_tty_open (struct tty_struct *tty)
 #endif
 	
 	/* Flush any pending characters in the driver and discipline. */
-	if (tty->ldisc.ops->flush_buffer)
-		tty->ldisc.ops->flush_buffer(tty);
+	if (tty->ldisc->ops->flush_buffer)
+		tty->ldisc->ops->flush_buffer(tty);
 
 	tty_driver_flush_buffer(tty);
 		
diff --git a/drivers/char/n_tty.c b/drivers/char/n_tty.c
index f6f0e4ec2b51..94a5d5020abc 100644
--- a/drivers/char/n_tty.c
+++ b/drivers/char/n_tty.c
@@ -73,24 +73,6 @@
 #define ECHO_OP_SET_CANON_COL 0x81
 #define ECHO_OP_ERASE_TAB 0x82
 
-static inline unsigned char *alloc_buf(void)
-{
-	gfp_t prio = in_interrupt() ? GFP_ATOMIC : GFP_KERNEL;
-
-	if (PAGE_SIZE != N_TTY_BUF_SIZE)
-		return kmalloc(N_TTY_BUF_SIZE, prio);
-	else
-		return (unsigned char *)__get_free_page(prio);
-}
-
-static inline void free_buf(unsigned char *buf)
-{
-	if (PAGE_SIZE != N_TTY_BUF_SIZE)
-		kfree(buf);
-	else
-		free_page((unsigned long) buf);
-}
-
 static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
 			       unsigned char __user *ptr)
 {
@@ -1558,11 +1540,11 @@ static void n_tty_close(struct tty_struct *tty)
 {
 	n_tty_flush_buffer(tty);
 	if (tty->read_buf) {
-		free_buf(tty->read_buf);
+		kfree(tty->read_buf);
 		tty->read_buf = NULL;
 	}
 	if (tty->echo_buf) {
-		free_buf(tty->echo_buf);
+		kfree(tty->echo_buf);
 		tty->echo_buf = NULL;
 	}
 }
@@ -1584,17 +1566,16 @@ static int n_tty_open(struct tty_struct *tty)
 
 	/* These are ugly. Currently a malloc failure here can panic */
 	if (!tty->read_buf) {
-		tty->read_buf = alloc_buf();
+		tty->read_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
 		if (!tty->read_buf)
 			return -ENOMEM;
 	}
 	if (!tty->echo_buf) {
-		tty->echo_buf = alloc_buf();
+		tty->echo_buf = kzalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
+
 		if (!tty->echo_buf)
 			return -ENOMEM;
 	}
-	memset(tty->read_buf, 0, N_TTY_BUF_SIZE);
-	memset(tty->echo_buf, 0, N_TTY_BUF_SIZE);
 	reset_buffer_flags(tty);
 	tty->column = 0;
 	n_tty_set_termios(tty, NULL);
diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c
index 19d79fc54461..77b364889224 100644
--- a/drivers/char/pcmcia/synclink_cs.c
+++ b/drivers/char/pcmcia/synclink_cs.c
@@ -383,7 +383,7 @@ static void async_mode(MGSLPC_INFO *info);
 static void tx_timeout(unsigned long context);
 
 static int carrier_raised(struct tty_port *port);
-static void raise_dtr_rts(struct tty_port *port);
+static void dtr_rts(struct tty_port *port, int onoff);
 
 #if SYNCLINK_GENERIC_HDLC
 #define dev_to_port(D) (dev_to_hdlc(D)->priv)
@@ -513,7 +513,7 @@ static void ldisc_receive_buf(struct tty_struct *tty,
 
 static const struct tty_port_operations mgslpc_port_ops = {
 	.carrier_raised = carrier_raised,
-	.raise_dtr_rts = raise_dtr_rts
+	.dtr_rts = dtr_rts
 };
 
 static int mgslpc_probe(struct pcmcia_device *link)
@@ -2528,13 +2528,16 @@ static int carrier_raised(struct tty_port *port)
 	return 0;
 }
 
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int onoff)
 {
 	MGSLPC_INFO *info = container_of(port, MGSLPC_INFO, port);
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->lock,flags);
-	info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+	if (onoff)
+		info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+	else
+		info->serial_signals &= ~SerialSignal_RTS + SerialSignal_DTR;
 	set_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 }
diff --git a/drivers/char/pty.c b/drivers/char/pty.c
index 31038a0052a2..5acd29e6e043 100644
--- a/drivers/char/pty.c
+++ b/drivers/char/pty.c
@@ -30,7 +30,6 @@
 
 #include <asm/system.h>
 
-/* These are global because they are accessed in tty_io.c */
 #ifdef CONFIG_UNIX98_PTYS
 static struct tty_driver *ptm_driver;
 static struct tty_driver *pts_driver;
@@ -111,7 +110,7 @@ static int pty_write(struct tty_struct *tty, const unsigned char *buf,
 	c = to->receive_room;
 	if (c > count)
 		c = count;
-	to->ldisc.ops->receive_buf(to, buf, NULL, c);
+	to->ldisc->ops->receive_buf(to, buf, NULL, c);
 
 	return c;
 }
@@ -149,11 +148,11 @@ static int pty_chars_in_buffer(struct tty_struct *tty)
 	int count;
 
 	/* We should get the line discipline lock for "tty->link" */
-	if (!to || !to->ldisc.ops->chars_in_buffer)
+	if (!to || !to->ldisc->ops->chars_in_buffer)
 		return 0;
 
 	/* The ldisc must report 0 if no characters available to be read */
-	count = to->ldisc.ops->chars_in_buffer(to);
+	count = to->ldisc->ops->chars_in_buffer(to);
 
 	if (tty->driver->subtype == PTY_TYPE_SLAVE)
 		return count;
@@ -187,8 +186,8 @@ static void pty_flush_buffer(struct tty_struct *tty)
 	if (!to)
 		return;
 
-	if (to->ldisc.ops->flush_buffer)
-		to->ldisc.ops->flush_buffer(to);
+	if (to->ldisc->ops->flush_buffer)
+		to->ldisc->ops->flush_buffer(to);
 
 	if (to->packet) {
 		spin_lock_irqsave(&tty->ctrl_lock, flags);
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index 20d90e6a6e50..db32f0e4c7dd 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -71,7 +71,7 @@ static int raw_open(struct inode *inode, struct file *filp)
 	err = bd_claim(bdev, raw_open);
 	if (err)
 		goto out1;
-	err = set_blocksize(bdev, bdev_hardsect_size(bdev));
+	err = set_blocksize(bdev, bdev_logical_block_size(bdev));
 	if (err)
 		goto out2;
 	filp->f_flags |= O_DIRECT;
diff --git a/drivers/char/rocket.c b/drivers/char/rocket.c
index f59fc5cea067..63d5b628477a 100644
--- a/drivers/char/rocket.c
+++ b/drivers/char/rocket.c
@@ -872,11 +872,16 @@ static int carrier_raised(struct tty_port *port)
 	return (sGetChanStatusLo(&info->channel) & CD_ACT) ? 1 : 0;
 }
 
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int on)
 {
 	struct r_port *info = container_of(port, struct r_port, port);
-	sSetDTR(&info->channel);
-	sSetRTS(&info->channel);
+	if (on) {
+		sSetDTR(&info->channel);
+		sSetRTS(&info->channel);
+	} else {
+		sClrDTR(&info->channel);
+		sClrRTS(&info->channel);
+	}
 }
 
 /*
@@ -934,7 +939,7 @@ static int rp_open(struct tty_struct *tty, struct file *filp)
 	/*
 	 * Info->count is now 1; so it's safe to sleep now.
 	 */
-	if (!test_bit(ASYNC_INITIALIZED, &port->flags)) {
+	if (!test_bit(ASYNCB_INITIALIZED, &port->flags)) {
 		cp = &info->channel;
 		sSetRxTrigger(cp, TRIG_1);
 		if (sGetChanStatus(cp) & CD_ACT)
@@ -958,7 +963,7 @@ static int rp_open(struct tty_struct *tty, struct file *filp)
 		sEnRxFIFO(cp);
 		sEnTransmit(cp);
 
-		set_bit(ASYNC_INITIALIZED, &info->port.flags);
+		set_bit(ASYNCB_INITIALIZED, &info->port.flags);
 
 		/*
 		 * Set up the tty->alt_speed kludge
@@ -1641,7 +1646,7 @@ static int rp_write(struct tty_struct *tty,
 	/*  Write remaining data into the port's xmit_buf */
 	while (1) {
 		/* Hung up ? */
-		if (!test_bit(ASYNC_NORMAL_ACTIVE, &info->port.flags))
+		if (!test_bit(ASYNCB_NORMAL_ACTIVE, &info->port.flags))
 			goto end;
 		c = min(count, XMIT_BUF_SIZE - info->xmit_cnt - 1);
 		c = min(c, XMIT_BUF_SIZE - info->xmit_head);
@@ -2250,7 +2255,7 @@ static const struct tty_operations rocket_ops = {
 
 static const struct tty_port_operations rocket_port_ops = {
 	.carrier_raised = carrier_raised,
-	.raise_dtr_rts = raise_dtr_rts,
+	.dtr_rts = dtr_rts,
 };
 
 /*
diff --git a/drivers/char/selection.c b/drivers/char/selection.c
index cb8ca5698963..f97b9e848064 100644
--- a/drivers/char/selection.c
+++ b/drivers/char/selection.c
@@ -327,7 +327,7 @@ int paste_selection(struct tty_struct *tty)
 		}
 		count = sel_buffer_lth - pasted;
 		count = min(count, tty->receive_room);
-		tty->ldisc.ops->receive_buf(tty, sel_buffer + pasted,
+		tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
 								NULL, count);
 		pasted += count;
 	}
diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c
index 2ad813a801dc..53e504f41b20 100644
--- a/drivers/char/stallion.c
+++ b/drivers/char/stallion.c
@@ -772,11 +772,11 @@ static int stl_carrier_raised(struct tty_port *port)
 	return (portp->sigs & TIOCM_CD) ? 1 : 0;
 }
 
-static void stl_raise_dtr_rts(struct tty_port *port)
+static void stl_dtr_rts(struct tty_port *port, int on)
 {
 	struct stlport *portp = container_of(port, struct stlport, port);
 	/* Takes brd_lock internally */
-	stl_setsignals(portp, 1, 1);
+	stl_setsignals(portp, on, on);
 }
 
 /*****************************************************************************/
@@ -2547,7 +2547,7 @@ static const struct tty_operations stl_ops = {
 
 static const struct tty_port_operations stl_port_ops = {
 	.carrier_raised = stl_carrier_raised,
-	.raise_dtr_rts = stl_raise_dtr_rts,
+	.dtr_rts = stl_dtr_rts,
 };
 
 /*****************************************************************************/
diff --git a/drivers/char/synclink.c b/drivers/char/synclink.c
index afd0b26ca056..afded3a2379c 100644
--- a/drivers/char/synclink.c
+++ b/drivers/char/synclink.c
@@ -3247,13 +3247,16 @@ static int carrier_raised(struct tty_port *port)
 	return (info->serial_signals & SerialSignal_DCD) ? 1 : 0;
 }
 
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int on)
 {
 	struct mgsl_struct *info = container_of(port, struct mgsl_struct, port);
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->irq_spinlock,flags);
-	info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+	if (on)
+		info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+	else
+		info->serial_signals &= ~(SerialSignal_RTS + SerialSignal_DTR);
  	usc_set_serial_signals(info);
 	spin_unlock_irqrestore(&info->irq_spinlock,flags);
 }
@@ -4258,7 +4261,7 @@ static void mgsl_add_device( struct mgsl_struct *info )
 
 static const struct tty_port_operations mgsl_port_ops = {
 	.carrier_raised = carrier_raised,
-	.raise_dtr_rts = raise_dtr_rts,
+	.dtr_rts = dtr_rts,
 };
 
 
diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c
index 5e256494686a..1386625fc4ca 100644
--- a/drivers/char/synclink_gt.c
+++ b/drivers/char/synclink_gt.c
@@ -214,6 +214,7 @@ struct slgt_desc
 #define set_desc_next(a,b) (a).next   = cpu_to_le32((unsigned int)(b))
 #define set_desc_count(a,b)(a).count  = cpu_to_le16((unsigned short)(b))
 #define set_desc_eof(a,b)  (a).status = cpu_to_le16((b) ? (le16_to_cpu((a).status) | BIT0) : (le16_to_cpu((a).status) & ~BIT0))
+#define set_desc_status(a, b) (a).status = cpu_to_le16((unsigned short)(b))
 #define desc_count(a)      (le16_to_cpu((a).count))
 #define desc_status(a)     (le16_to_cpu((a).status))
 #define desc_complete(a)   (le16_to_cpu((a).status) & BIT15)
@@ -297,6 +298,7 @@ struct slgt_info {
 	u32 max_frame_size;       /* as set by device config */
 
 	unsigned int rbuf_fill_level;
+	unsigned int rx_pio;
 	unsigned int if_mode;
 	unsigned int base_clock;
 
@@ -331,6 +333,8 @@ struct slgt_info {
 	struct slgt_desc *rbufs;
 	unsigned int rbuf_current;
 	unsigned int rbuf_index;
+	unsigned int rbuf_fill_index;
+	unsigned short rbuf_fill_count;
 
 	unsigned int tbuf_count;
 	struct slgt_desc *tbufs;
@@ -2110,6 +2114,40 @@ static void ri_change(struct slgt_info *info, unsigned short status)
 	info->pending_bh |= BH_STATUS;
 }
 
+static void isr_rxdata(struct slgt_info *info)
+{
+	unsigned int count = info->rbuf_fill_count;
+	unsigned int i = info->rbuf_fill_index;
+	unsigned short reg;
+
+	while (rd_reg16(info, SSR) & IRQ_RXDATA) {
+		reg = rd_reg16(info, RDR);
+		DBGISR(("isr_rxdata %s RDR=%04X\n", info->device_name, reg));
+		if (desc_complete(info->rbufs[i])) {
+			/* all buffers full */
+			rx_stop(info);
+			info->rx_restart = 1;
+			continue;
+		}
+		info->rbufs[i].buf[count++] = (unsigned char)reg;
+		/* async mode saves status byte to buffer for each data byte */
+		if (info->params.mode == MGSL_MODE_ASYNC)
+			info->rbufs[i].buf[count++] = (unsigned char)(reg >> 8);
+		if (count == info->rbuf_fill_level || (reg & BIT10)) {
+			/* buffer full or end of frame */
+			set_desc_count(info->rbufs[i], count);
+			set_desc_status(info->rbufs[i], BIT15 | (reg >> 8));
+			info->rbuf_fill_count = count = 0;
+			if (++i == info->rbuf_count)
+				i = 0;
+			info->pending_bh |= BH_RECEIVE;
+		}
+	}
+
+	info->rbuf_fill_index = i;
+	info->rbuf_fill_count = count;
+}
+
 static void isr_serial(struct slgt_info *info)
 {
 	unsigned short status = rd_reg16(info, SSR);
@@ -2125,6 +2163,8 @@ static void isr_serial(struct slgt_info *info)
 			if (info->tx_count)
 				isr_txeom(info, status);
 		}
+		if (info->rx_pio && (status & IRQ_RXDATA))
+			isr_rxdata(info);
 		if ((status & IRQ_RXBREAK) && (status & RXBREAK)) {
 			info->icount.brk++;
 			/* process break detection if tty control allows */
@@ -2141,7 +2181,8 @@ static void isr_serial(struct slgt_info *info)
 	} else {
 		if (status & (IRQ_TXIDLE + IRQ_TXUNDER))
 			isr_txeom(info, status);
-
+		if (info->rx_pio && (status & IRQ_RXDATA))
+			isr_rxdata(info);
 		if (status & IRQ_RXIDLE) {
 			if (status & RXIDLE)
 				info->icount.rxidle++;
@@ -2642,6 +2683,10 @@ static int rx_enable(struct slgt_info *info, int enable)
 			return -EINVAL;
 		}
 		info->rbuf_fill_level = rbuf_fill_level;
+		if (rbuf_fill_level < 128)
+			info->rx_pio = 1; /* PIO mode */
+		else
+			info->rx_pio = 0; /* DMA mode */
 		rx_stop(info); /* restart receiver to use new fill level */
 	}
 
@@ -3099,13 +3144,16 @@ static int carrier_raised(struct tty_port *port)
 	return (info->signals & SerialSignal_DCD) ? 1 : 0;
 }
 
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int on)
 {
 	unsigned long flags;
 	struct slgt_info *info = container_of(port, struct slgt_info, port);
 
 	spin_lock_irqsave(&info->lock,flags);
-	info->signals |= SerialSignal_RTS + SerialSignal_DTR;
+	if (on)
+		info->signals |= SerialSignal_RTS + SerialSignal_DTR;
+	else
+		info->signals &= ~(SerialSignal_RTS + SerialSignal_DTR);
  	set_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 }
@@ -3419,7 +3467,7 @@ static void add_device(struct slgt_info *info)
 
 static const struct tty_port_operations slgt_port_ops = {
 	.carrier_raised = carrier_raised,
-	.raise_dtr_rts = raise_dtr_rts,
+	.dtr_rts = dtr_rts,
 };
 
 /*
@@ -3841,15 +3889,27 @@ static void rx_start(struct slgt_info *info)
 	rdma_reset(info);
 	reset_rbufs(info);
 
-	/* set 1st descriptor address */
-	wr_reg32(info, RDDAR, info->rbufs[0].pdesc);
-
-	if (info->params.mode != MGSL_MODE_ASYNC) {
-		/* enable rx DMA and DMA interrupt */
-		wr_reg32(info, RDCSR, (BIT2 + BIT0));
+	if (info->rx_pio) {
+		/* rx request when rx FIFO not empty */
+		wr_reg16(info, SCR, (unsigned short)(rd_reg16(info, SCR) & ~BIT14));
+		slgt_irq_on(info, IRQ_RXDATA);
+		if (info->params.mode == MGSL_MODE_ASYNC) {
+			/* enable saving of rx status */
+			wr_reg32(info, RDCSR, BIT6);
+		}
 	} else {
-		/* enable saving of rx status, rx DMA and DMA interrupt */
-		wr_reg32(info, RDCSR, (BIT6 + BIT2 + BIT0));
+		/* rx request when rx FIFO half full */
+		wr_reg16(info, SCR, (unsigned short)(rd_reg16(info, SCR) | BIT14));
+		/* set 1st descriptor address */
+		wr_reg32(info, RDDAR, info->rbufs[0].pdesc);
+
+		if (info->params.mode != MGSL_MODE_ASYNC) {
+			/* enable rx DMA and DMA interrupt */
+			wr_reg32(info, RDCSR, (BIT2 + BIT0));
+		} else {
+			/* enable saving of rx status, rx DMA and DMA interrupt */
+			wr_reg32(info, RDCSR, (BIT6 + BIT2 + BIT0));
+		}
 	}
 
 	slgt_irq_on(info, IRQ_RXOVER);
@@ -4467,6 +4527,8 @@ static void free_rbufs(struct slgt_info *info, unsigned int i, unsigned int last
 static void reset_rbufs(struct slgt_info *info)
 {
 	free_rbufs(info, 0, info->rbuf_count - 1);
+	info->rbuf_fill_index = 0;
+	info->rbuf_fill_count = 0;
 }
 
 /*
diff --git a/drivers/char/synclinkmp.c b/drivers/char/synclinkmp.c
index 26de60efe4b2..6f727e3c53ad 100644
--- a/drivers/char/synclinkmp.c
+++ b/drivers/char/synclinkmp.c
@@ -3277,13 +3277,16 @@ static int carrier_raised(struct tty_port *port)
 	return (info->serial_signals & SerialSignal_DCD) ? 1 : 0;
 }
 
-static void raise_dtr_rts(struct tty_port *port)
+static void dtr_rts(struct tty_port *port, int on)
 {
 	SLMP_INFO *info = container_of(port, SLMP_INFO, port);
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->lock,flags);
-	info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+	if (on)
+		info->serial_signals |= SerialSignal_RTS + SerialSignal_DTR;
+	else
+		info->serial_signals &= ~(SerialSignal_RTS + SerialSignal_DTR);
  	set_signals(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 }
@@ -3746,7 +3749,7 @@ static void add_device(SLMP_INFO *info)
 
 static const struct tty_port_operations port_ops = {
 	.carrier_raised = carrier_raised,
-	.raise_dtr_rts = raise_dtr_rts,
+	.dtr_rts = dtr_rts,
 };
 
 /* Allocate and initialize a device instance structure
diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c
index d6a807f4077d..39a05b5fa9cb 100644
--- a/drivers/char/sysrq.c
+++ b/drivers/char/sysrq.c
@@ -25,6 +25,7 @@
 #include <linux/kbd_kern.h>
 #include <linux/proc_fs.h>
 #include <linux/quotaops.h>
+#include <linux/perf_counter.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/suspend.h>
@@ -243,6 +244,7 @@ static void sysrq_handle_showregs(int key, struct tty_struct *tty)
 	struct pt_regs *regs = get_irq_regs();
 	if (regs)
 		show_regs(regs);
+	perf_counter_print_debug();
 }
 static struct sysrq_key_op sysrq_showregs_op = {
 	.handler	= sysrq_handle_showregs,
diff --git a/drivers/char/tty_audit.c b/drivers/char/tty_audit.c
index 55ba6f142883..ac16fbec72d0 100644
--- a/drivers/char/tty_audit.c
+++ b/drivers/char/tty_audit.c
@@ -29,10 +29,7 @@ static struct tty_audit_buf *tty_audit_buf_alloc(int major, int minor,
 	buf = kmalloc(sizeof(*buf), GFP_KERNEL);
 	if (!buf)
 		goto err;
-	if (PAGE_SIZE != N_TTY_BUF_SIZE)
-		buf->data = kmalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
-	else
-		buf->data = (unsigned char *)__get_free_page(GFP_KERNEL);
+	buf->data = kmalloc(N_TTY_BUF_SIZE, GFP_KERNEL);
 	if (!buf->data)
 		goto err_buf;
 	atomic_set(&buf->count, 1);
@@ -52,10 +49,7 @@ err:
 static void tty_audit_buf_free(struct tty_audit_buf *buf)
 {
 	WARN_ON(buf->valid != 0);
-	if (PAGE_SIZE != N_TTY_BUF_SIZE)
-		kfree(buf->data);
-	else
-		free_page((unsigned long)buf->data);
+	kfree(buf->data);
 	kfree(buf);
 }
 
diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c
index 66b99a2049e3..939e198d7670 100644
--- a/drivers/char/tty_io.c
+++ b/drivers/char/tty_io.c
@@ -295,7 +295,7 @@ struct tty_driver *tty_find_polling_driver(char *name, int *line)
 	struct tty_driver *p, *res = NULL;
 	int tty_line = 0;
 	int len;
-	char *str;
+	char *str, *stp;
 
 	for (str = name; *str; str++)
 		if ((*str >= '0' && *str <= '9') || *str == ',')
@@ -311,13 +311,14 @@ struct tty_driver *tty_find_polling_driver(char *name, int *line)
 	list_for_each_entry(p, &tty_drivers, tty_drivers) {
 		if (strncmp(name, p->name, len) != 0)
 			continue;
-		if (*str == ',')
-			str++;
-		if (*str == '\0')
-			str = NULL;
+		stp = str;
+		if (*stp == ',')
+			stp++;
+		if (*stp == '\0')
+			stp = NULL;
 
 		if (tty_line >= 0 && tty_line <= p->num && p->ops &&
-		    p->ops->poll_init && !p->ops->poll_init(p, tty_line, str)) {
+		    p->ops->poll_init && !p->ops->poll_init(p, tty_line, stp)) {
 			res = tty_driver_kref_get(p);
 			*line = tty_line;
 			break;
@@ -469,43 +470,6 @@ void tty_wakeup(struct tty_struct *tty)
 
 EXPORT_SYMBOL_GPL(tty_wakeup);
 
-/**
- *	tty_ldisc_flush	-	flush line discipline queue
- *	@tty: tty
- *
- *	Flush the line discipline queue (if any) for this tty. If there
- *	is no line discipline active this is a no-op.
- */
-
-void tty_ldisc_flush(struct tty_struct *tty)
-{
-	struct tty_ldisc *ld = tty_ldisc_ref(tty);
-	if (ld) {
-		if (ld->ops->flush_buffer)
-			ld->ops->flush_buffer(tty);
-		tty_ldisc_deref(ld);
-	}
-	tty_buffer_flush(tty);
-}
-
-EXPORT_SYMBOL_GPL(tty_ldisc_flush);
-
-/**
- *	tty_reset_termios	-	reset terminal state
- *	@tty: tty to reset
- *
- *	Restore a terminal to the driver default state
- */
-
-static void tty_reset_termios(struct tty_struct *tty)
-{
-	mutex_lock(&tty->termios_mutex);
-	*tty->termios = tty->driver->init_termios;
-	tty->termios->c_ispeed = tty_termios_input_baud_rate(tty->termios);
-	tty->termios->c_ospeed = tty_termios_baud_rate(tty->termios);
-	mutex_unlock(&tty->termios_mutex);
-}
-
 /**
  *	do_tty_hangup		-	actual handler for hangup events
  *	@work: tty device
@@ -535,7 +499,6 @@ static void do_tty_hangup(struct work_struct *work)
 	struct file *cons_filp = NULL;
 	struct file *filp, *f = NULL;
 	struct task_struct *p;
-	struct tty_ldisc *ld;
 	int    closecount = 0, n;
 	unsigned long flags;
 	int refs = 0;
@@ -566,40 +529,8 @@ static void do_tty_hangup(struct work_struct *work)
 		filp->f_op = &hung_up_tty_fops;
 	}
 	file_list_unlock();
-	/*
-	 * FIXME! What are the locking issues here? This may me overdoing
-	 * things... This question is especially important now that we've
-	 * removed the irqlock.
-	 */
-	ld = tty_ldisc_ref(tty);
-	if (ld != NULL) {
-		/* We may have no line discipline at this point */
-		if (ld->ops->flush_buffer)
-			ld->ops->flush_buffer(tty);
-		tty_driver_flush_buffer(tty);
-		if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
-		    ld->ops->write_wakeup)
-			ld->ops->write_wakeup(tty);
-		if (ld->ops->hangup)
-			ld->ops->hangup(tty);
-	}
-	/*
-	 * FIXME: Once we trust the LDISC code better we can wait here for
-	 * ldisc completion and fix the driver call race
-	 */
-	wake_up_interruptible_poll(&tty->write_wait, POLLOUT);
-	wake_up_interruptible_poll(&tty->read_wait, POLLIN);
-	/*
-	 * Shutdown the current line discipline, and reset it to
-	 * N_TTY.
-	 */
-	if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS)
-		tty_reset_termios(tty);
-	/* Defer ldisc switch */
-	/* tty_deferred_ldisc_switch(N_TTY);
 
-	  This should get done automatically when the port closes and
-	  tty_release is called */
+	tty_ldisc_hangup(tty);
 
 	read_lock(&tasklist_lock);
 	if (tty->session) {
@@ -628,12 +559,15 @@ static void do_tty_hangup(struct work_struct *work)
 	read_unlock(&tasklist_lock);
 
 	spin_lock_irqsave(&tty->ctrl_lock, flags);
-	tty->flags = 0;
+	clear_bit(TTY_THROTTLED, &tty->flags);
+	clear_bit(TTY_PUSH, &tty->flags);
+	clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
 	put_pid(tty->session);
 	put_pid(tty->pgrp);
 	tty->session = NULL;
 	tty->pgrp = NULL;
 	tty->ctrl_status = 0;
+	set_bit(TTY_HUPPED, &tty->flags);
 	spin_unlock_irqrestore(&tty->ctrl_lock, flags);
 
 	/* Account for the p->signal references we killed */
@@ -659,10 +593,7 @@ static void do_tty_hangup(struct work_struct *work)
 	 * can't yet guarantee all that.
 	 */
 	set_bit(TTY_HUPPED, &tty->flags);
-	if (ld) {
-		tty_ldisc_enable(tty);
-		tty_ldisc_deref(ld);
-	}
+	tty_ldisc_enable(tty);
 	unlock_kernel();
 	if (f)
 		fput(f);
@@ -2480,6 +2411,24 @@ static int tty_tiocmset(struct tty_struct *tty, struct file *file, unsigned int
 	return tty->ops->tiocmset(tty, file, set, clear);
 }
 
+struct tty_struct *tty_pair_get_tty(struct tty_struct *tty)
+{
+	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
+	    tty->driver->subtype == PTY_TYPE_MASTER)
+		tty = tty->link;
+	return tty;
+}
+EXPORT_SYMBOL(tty_pair_get_tty);
+
+struct tty_struct *tty_pair_get_pty(struct tty_struct *tty)
+{
+	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
+	    tty->driver->subtype == PTY_TYPE_MASTER)
+	    return tty;
+	return tty->link;
+}
+EXPORT_SYMBOL(tty_pair_get_pty);
+
 /*
  * Split this up, as gcc can choke on it otherwise..
  */
@@ -2495,11 +2444,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	if (tty_paranoia_check(tty, inode, "tty_ioctl"))
 		return -EINVAL;
 
-	real_tty = tty;
-	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
-	    tty->driver->subtype == PTY_TYPE_MASTER)
-		real_tty = tty->link;
-
+	real_tty = tty_pair_get_tty(tty);
 
 	/*
 	 * Factor out some common prep work
@@ -2555,7 +2500,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case TIOCGSID:
 		return tiocgsid(tty, real_tty, p);
 	case TIOCGETD:
-		return put_user(tty->ldisc.ops->num, (int __user *)p);
+		return put_user(tty->ldisc->ops->num, (int __user *)p);
 	case TIOCSETD:
 		return tiocsetd(tty, p);
 	/*
@@ -2770,6 +2715,7 @@ void initialize_tty_struct(struct tty_struct *tty,
 	tty->buf.head = tty->buf.tail = NULL;
 	tty_buffer_init(tty);
 	mutex_init(&tty->termios_mutex);
+	mutex_init(&tty->ldisc_mutex);
 	init_waitqueue_head(&tty->write_wait);
 	init_waitqueue_head(&tty->read_wait);
 	INIT_WORK(&tty->hangup_work, do_tty_hangup);
diff --git a/drivers/char/tty_ioctl.c b/drivers/char/tty_ioctl.c
index 6f4c7d0a53bf..8116bb1c8f80 100644
--- a/drivers/char/tty_ioctl.c
+++ b/drivers/char/tty_ioctl.c
@@ -97,14 +97,19 @@ EXPORT_SYMBOL(tty_driver_flush_buffer);
  *	@tty: terminal
  *
  *	Indicate that a tty should stop transmitting data down the stack.
+ *	Takes the termios mutex to protect against parallel throttle/unthrottle
+ *	and also to ensure the driver can consistently reference its own
+ *	termios data at this point when implementing software flow control.
  */
 
 void tty_throttle(struct tty_struct *tty)
 {
+	mutex_lock(&tty->termios_mutex);
 	/* check TTY_THROTTLED first so it indicates our state */
 	if (!test_and_set_bit(TTY_THROTTLED, &tty->flags) &&
 	    tty->ops->throttle)
 		tty->ops->throttle(tty);
+	mutex_unlock(&tty->termios_mutex);
 }
 EXPORT_SYMBOL(tty_throttle);
 
@@ -113,13 +118,21 @@ EXPORT_SYMBOL(tty_throttle);
  *	@tty: terminal
  *
  *	Indicate that a tty may continue transmitting data down the stack.
+ *	Takes the termios mutex to protect against parallel throttle/unthrottle
+ *	and also to ensure the driver can consistently reference its own
+ *	termios data at this point when implementing software flow control.
+ *
+ *	Drivers should however remember that the stack can issue a throttle,
+ *	then change flow control method, then unthrottle.
  */
 
 void tty_unthrottle(struct tty_struct *tty)
 {
+	mutex_lock(&tty->termios_mutex);
 	if (test_and_clear_bit(TTY_THROTTLED, &tty->flags) &&
 	    tty->ops->unthrottle)
 		tty->ops->unthrottle(tty);
+	mutex_unlock(&tty->termios_mutex);
 }
 EXPORT_SYMBOL(tty_unthrottle);
 
@@ -613,9 +626,25 @@ static int set_termios(struct tty_struct *tty, void __user *arg, int opt)
 	return 0;
 }
 
+static void copy_termios(struct tty_struct *tty, struct ktermios *kterm)
+{
+	mutex_lock(&tty->termios_mutex);
+	memcpy(kterm, tty->termios, sizeof(struct ktermios));
+	mutex_unlock(&tty->termios_mutex);
+}
+
+static void copy_termios_locked(struct tty_struct *tty, struct ktermios *kterm)
+{
+	mutex_lock(&tty->termios_mutex);
+	memcpy(kterm, tty->termios_locked, sizeof(struct ktermios));
+	mutex_unlock(&tty->termios_mutex);
+}
+
 static int get_termio(struct tty_struct *tty, struct termio __user *termio)
 {
-	if (kernel_termios_to_user_termio(termio, tty->termios))
+	struct ktermios kterm;
+	copy_termios(tty, &kterm);
+	if (kernel_termios_to_user_termio(termio, &kterm))
 		return -EFAULT;
 	return 0;
 }
@@ -917,6 +946,8 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file,
 	struct tty_struct *real_tty;
 	void __user *p = (void __user *)arg;
 	int ret = 0;
+	struct ktermios kterm;
+	struct termiox ktermx;
 
 	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
 	    tty->driver->subtype == PTY_TYPE_MASTER)
@@ -952,23 +983,20 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file,
 		return set_termios(real_tty, p, TERMIOS_OLD);
 #ifndef TCGETS2
 	case TCGETS:
-		mutex_lock(&real_tty->termios_mutex);
-		if (kernel_termios_to_user_termios((struct termios __user *)arg, real_tty->termios))
+		copy_termios(real_tty, &kterm);
+		if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm))
 			ret = -EFAULT;
-		mutex_unlock(&real_tty->termios_mutex);
 		return ret;
 #else
 	case TCGETS:
-		mutex_lock(&real_tty->termios_mutex);
-		if (kernel_termios_to_user_termios_1((struct termios __user *)arg, real_tty->termios))
+		copy_termios(real_tty, &kterm);
+		if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm))
 			ret = -EFAULT;
-		mutex_unlock(&real_tty->termios_mutex);
 		return ret;
 	case TCGETS2:
-		mutex_lock(&real_tty->termios_mutex);
-		if (kernel_termios_to_user_termios((struct termios2 __user *)arg, real_tty->termios))
+		copy_termios(real_tty, &kterm);
+		if (kernel_termios_to_user_termios((struct termios2 __user *)arg, &kterm))
 			ret = -EFAULT;
-		mutex_unlock(&real_tty->termios_mutex);
 		return ret;
 	case TCSETSF2:
 		return set_termios(real_tty, p,  TERMIOS_FLUSH | TERMIOS_WAIT);
@@ -987,34 +1015,36 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file,
 		return set_termios(real_tty, p, TERMIOS_TERMIO);
 #ifndef TCGETS2
 	case TIOCGLCKTRMIOS:
-		mutex_lock(&real_tty->termios_mutex);
-		if (kernel_termios_to_user_termios((struct termios __user *)arg, real_tty->termios_locked))
+		copy_termios_locked(real_tty, &kterm);
+		if (kernel_termios_to_user_termios((struct termios __user *)arg, &kterm))
 			ret = -EFAULT;
-		mutex_unlock(&real_tty->termios_mutex);
 		return ret;
 	case TIOCSLCKTRMIOS:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		mutex_lock(&real_tty->termios_mutex);
-		if (user_termios_to_kernel_termios(real_tty->termios_locked,
+		copy_termios_locked(real_tty, &kterm);
+		if (user_termios_to_kernel_termios(&kterm,
 					       (struct termios __user *) arg))
-			ret = -EFAULT;
+			return -EFAULT;
+		mutex_lock(&real_tty->termios_mutex);
+		memcpy(real_tty->termios_locked, &kterm, sizeof(struct ktermios));
 		mutex_unlock(&real_tty->termios_mutex);
-		return ret;
+		return 0;
 #else
 	case TIOCGLCKTRMIOS:
-		mutex_lock(&real_tty->termios_mutex);
-		if (kernel_termios_to_user_termios_1((struct termios __user *)arg, real_tty->termios_locked))
+		copy_termios_locked(real_tty, &kterm);
+		if (kernel_termios_to_user_termios_1((struct termios __user *)arg, &kterm))
 			ret = -EFAULT;
-		mutex_unlock(&real_tty->termios_mutex);
 		return ret;
 	case TIOCSLCKTRMIOS:
 		if (!capable(CAP_SYS_ADMIN))
-			ret = -EPERM;
-		mutex_lock(&real_tty->termios_mutex);
-		if (user_termios_to_kernel_termios_1(real_tty->termios_locked,
+			return -EPERM;
+		copy_termios_locked(real_tty, &kterm);
+		if (user_termios_to_kernel_termios_1(&kterm,
 					       (struct termios __user *) arg))
-			ret = -EFAULT;
+			return -EFAULT;
+		mutex_lock(&real_tty->termios_mutex);
+		memcpy(real_tty->termios_locked, &kterm, sizeof(struct ktermios));
 		mutex_unlock(&real_tty->termios_mutex);
 		return ret;
 #endif
@@ -1023,9 +1053,10 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file,
 		if (real_tty->termiox == NULL)
 			return -EINVAL;
 		mutex_lock(&real_tty->termios_mutex);
-		if (copy_to_user(p, real_tty->termiox, sizeof(struct termiox)))
-			ret = -EFAULT;
+		memcpy(&ktermx, real_tty->termiox, sizeof(struct termiox));
 		mutex_unlock(&real_tty->termios_mutex);
+		if (copy_to_user(p, &ktermx, sizeof(struct termiox)))
+			ret = -EFAULT;
 		return ret;
 	case TCSETX:
 		return set_termiox(real_tty, p, 0);
@@ -1035,10 +1066,9 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file,
 		return set_termiox(real_tty, p, TERMIOS_FLUSH);
 #endif		
 	case TIOCGSOFTCAR:
-		mutex_lock(&real_tty->termios_mutex);
-		ret = put_user(C_CLOCAL(real_tty) ? 1 : 0,
+		copy_termios(real_tty, &kterm);
+		ret = put_user((kterm.c_cflag & CLOCAL) ? 1 : 0,
 						(int __user *)arg);
-		mutex_unlock(&real_tty->termios_mutex);
 		return ret;
 	case TIOCSSOFTCAR:
 		if (get_user(arg, (unsigned int __user *) arg))
diff --git a/drivers/char/tty_ldisc.c b/drivers/char/tty_ldisc.c
index f78f5b0127a8..39c8f86dedd4 100644
--- a/drivers/char/tty_ldisc.c
+++ b/drivers/char/tty_ldisc.c
@@ -115,19 +115,22 @@ EXPORT_SYMBOL(tty_unregister_ldisc);
 /**
  *	tty_ldisc_try_get	-	try and reference an ldisc
  *	@disc: ldisc number
- *	@ld: tty ldisc structure to complete
  *
  *	Attempt to open and lock a line discipline into place. Return
- *	the line discipline refcounted and assigned in ld. On an error
- *	report the error code back
+ *	the line discipline refcounted or an error.
  */
 
-static int tty_ldisc_try_get(int disc, struct tty_ldisc *ld)
+static struct tty_ldisc *tty_ldisc_try_get(int disc)
 {
 	unsigned long flags;
+	struct tty_ldisc *ld;
 	struct tty_ldisc_ops *ldops;
 	int err = -EINVAL;
-	
+
+	ld = kmalloc(sizeof(struct tty_ldisc), GFP_KERNEL);
+	if (ld == NULL)
+		return ERR_PTR(-ENOMEM);
+
 	spin_lock_irqsave(&tty_ldisc_lock, flags);
 	ld->ops = NULL;
 	ldops = tty_ldiscs[disc];
@@ -140,17 +143,19 @@ static int tty_ldisc_try_get(int disc, struct tty_ldisc *ld)
 			/* lock it */
 			ldops->refcount++;
 			ld->ops = ldops;
+			ld->refcount = 0;
 			err = 0;
 		}
 	}
 	spin_unlock_irqrestore(&tty_ldisc_lock, flags);
-	return err;
+	if (err)
+		return ERR_PTR(err);
+	return ld;
 }
 
 /**
  *	tty_ldisc_get		-	take a reference to an ldisc
  *	@disc: ldisc number
- *	@ld: tty line discipline structure to use
  *
  *	Takes a reference to a line discipline. Deals with refcounts and
  *	module locking counts. Returns NULL if the discipline is not available.
@@ -161,52 +166,54 @@ static int tty_ldisc_try_get(int disc, struct tty_ldisc *ld)
  *		takes tty_ldisc_lock to guard against ldisc races
  */
 
-static int tty_ldisc_get(int disc, struct tty_ldisc *ld)
+static struct tty_ldisc *tty_ldisc_get(int disc)
 {
-	int err;
+	struct tty_ldisc *ld;
 
 	if (disc < N_TTY || disc >= NR_LDISCS)
-		return -EINVAL;
-	err = tty_ldisc_try_get(disc, ld);
-	if (err < 0) {
+		return ERR_PTR(-EINVAL);
+	ld = tty_ldisc_try_get(disc);
+	if (IS_ERR(ld)) {
 		request_module("tty-ldisc-%d", disc);
-		err = tty_ldisc_try_get(disc, ld);
+		ld = tty_ldisc_try_get(disc);
 	}
-	return err;
+	return ld;
 }
 
 /**
  *	tty_ldisc_put		-	drop ldisc reference
- *	@disc: ldisc number
+ *	@ld: ldisc
  *
  *	Drop a reference to a line discipline. Manage refcounts and
- *	module usage counts
+ *	module usage counts. Free the ldisc once the recount hits zero.
  *
  *	Locking:
  *		takes tty_ldisc_lock to guard against ldisc races
  */
 
-static void tty_ldisc_put(struct tty_ldisc_ops *ld)
+static void tty_ldisc_put(struct tty_ldisc *ld)
 {
 	unsigned long flags;
-	int disc = ld->num;
+	int disc = ld->ops->num;
+	struct tty_ldisc_ops *ldo;
 
 	BUG_ON(disc < N_TTY || disc >= NR_LDISCS);
 
 	spin_lock_irqsave(&tty_ldisc_lock, flags);
-	ld = tty_ldiscs[disc];
-	BUG_ON(ld->refcount == 0);
-	ld->refcount--;
-	module_put(ld->owner);
+	ldo = tty_ldiscs[disc];
+	BUG_ON(ldo->refcount == 0);
+	ldo->refcount--;
+	module_put(ldo->owner);
 	spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+	kfree(ld);
 }
 
-static void * tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos)
+static void *tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos)
 {
 	return (*pos < NR_LDISCS) ? pos : NULL;
 }
 
-static void * tty_ldiscs_seq_next(struct seq_file *m, void *v, loff_t *pos)
+static void *tty_ldiscs_seq_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	(*pos)++;
 	return (*pos < NR_LDISCS) ? pos : NULL;
@@ -219,12 +226,13 @@ static void tty_ldiscs_seq_stop(struct seq_file *m, void *v)
 static int tty_ldiscs_seq_show(struct seq_file *m, void *v)
 {
 	int i = *(loff_t *)v;
-	struct tty_ldisc ld;
-	
-	if (tty_ldisc_get(i, &ld) < 0)
+	struct tty_ldisc *ld;
+
+	ld = tty_ldisc_try_get(i);
+	if (IS_ERR(ld))
 		return 0;
-	seq_printf(m, "%-10s %2d\n", ld.ops->name ? ld.ops->name : "???", i);
-	tty_ldisc_put(ld.ops);
+	seq_printf(m, "%-10s %2d\n", ld->ops->name ? ld->ops->name : "???", i);
+	tty_ldisc_put(ld);
 	return 0;
 }
 
@@ -263,8 +271,7 @@ const struct file_operations tty_ldiscs_proc_fops = {
 
 static void tty_ldisc_assign(struct tty_struct *tty, struct tty_ldisc *ld)
 {
-	ld->refcount = 0;
-	tty->ldisc = *ld;
+	tty->ldisc = ld;
 }
 
 /**
@@ -286,7 +293,7 @@ static int tty_ldisc_try(struct tty_struct *tty)
 	int ret = 0;
 
 	spin_lock_irqsave(&tty_ldisc_lock, flags);
-	ld = &tty->ldisc;
+	ld = tty->ldisc;
 	if (test_bit(TTY_LDISC, &tty->flags)) {
 		ld->refcount++;
 		ret = 1;
@@ -315,10 +322,9 @@ struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *tty)
 {
 	/* wait_event is a macro */
 	wait_event(tty_ldisc_wait, tty_ldisc_try(tty));
-	WARN_ON(tty->ldisc.refcount == 0);
-	return &tty->ldisc;
+	WARN_ON(tty->ldisc->refcount == 0);
+	return tty->ldisc;
 }
-
 EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait);
 
 /**
@@ -335,10 +341,9 @@ EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait);
 struct tty_ldisc *tty_ldisc_ref(struct tty_struct *tty)
 {
 	if (tty_ldisc_try(tty))
-		return &tty->ldisc;
+		return tty->ldisc;
 	return NULL;
 }
-
 EXPORT_SYMBOL_GPL(tty_ldisc_ref);
 
 /**
@@ -366,7 +371,6 @@ void tty_ldisc_deref(struct tty_ldisc *ld)
 		wake_up(&tty_ldisc_wait);
 	spin_unlock_irqrestore(&tty_ldisc_lock, flags);
 }
-
 EXPORT_SYMBOL_GPL(tty_ldisc_deref);
 
 /**
@@ -388,6 +392,26 @@ void tty_ldisc_enable(struct tty_struct *tty)
 	wake_up(&tty_ldisc_wait);
 }
 
+/**
+ *	tty_ldisc_flush	-	flush line discipline queue
+ *	@tty: tty
+ *
+ *	Flush the line discipline queue (if any) for this tty. If there
+ *	is no line discipline active this is a no-op.
+ */
+
+void tty_ldisc_flush(struct tty_struct *tty)
+{
+	struct tty_ldisc *ld = tty_ldisc_ref(tty);
+	if (ld) {
+		if (ld->ops->flush_buffer)
+			ld->ops->flush_buffer(tty);
+		tty_ldisc_deref(ld);
+	}
+	tty_buffer_flush(tty);
+}
+EXPORT_SYMBOL_GPL(tty_ldisc_flush);
+
 /**
  *	tty_set_termios_ldisc		-	set ldisc field
  *	@tty: tty structure
@@ -407,6 +431,39 @@ static void tty_set_termios_ldisc(struct tty_struct *tty, int num)
 	mutex_unlock(&tty->termios_mutex);
 }
 
+/**
+ *	tty_ldisc_open		-	open a line discipline
+ *	@tty: tty we are opening the ldisc on
+ *	@ld: discipline to open
+ *
+ *	A helper opening method. Also a convenient debugging and check
+ *	point.
+ */
+
+static int tty_ldisc_open(struct tty_struct *tty, struct tty_ldisc *ld)
+{
+	WARN_ON(test_and_set_bit(TTY_LDISC_OPEN, &tty->flags));
+	if (ld->ops->open)
+		return ld->ops->open(tty);
+	return 0;
+}
+
+/**
+ *	tty_ldisc_close		-	close a line discipline
+ *	@tty: tty we are opening the ldisc on
+ *	@ld: discipline to close
+ *
+ *	A helper close method. Also a convenient debugging and check
+ *	point.
+ */
+
+static void tty_ldisc_close(struct tty_struct *tty, struct tty_ldisc *ld)
+{
+	WARN_ON(!test_bit(TTY_LDISC_OPEN, &tty->flags));
+	clear_bit(TTY_LDISC_OPEN, &tty->flags);
+	if (ld->ops->close)
+		ld->ops->close(tty);
+}
 
 /**
  *	tty_ldisc_restore	-	helper for tty ldisc change
@@ -420,66 +477,136 @@ static void tty_set_termios_ldisc(struct tty_struct *tty, int num)
 static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old)
 {
 	char buf[64];
-	struct tty_ldisc new_ldisc;
+	struct tty_ldisc *new_ldisc;
+	int r;
 
 	/* There is an outstanding reference here so this is safe */
-	tty_ldisc_get(old->ops->num, old);
+	old = tty_ldisc_get(old->ops->num);
+	WARN_ON(IS_ERR(old));
 	tty_ldisc_assign(tty, old);
 	tty_set_termios_ldisc(tty, old->ops->num);
-	if (old->ops->open && (old->ops->open(tty) < 0)) {
-		tty_ldisc_put(old->ops);
+	if (tty_ldisc_open(tty, old) < 0) {
+		tty_ldisc_put(old);
 		/* This driver is always present */
-		if (tty_ldisc_get(N_TTY, &new_ldisc) < 0)
+		new_ldisc = tty_ldisc_get(N_TTY);
+		if (IS_ERR(new_ldisc))
 			panic("n_tty: get");
-		tty_ldisc_assign(tty, &new_ldisc);
+		tty_ldisc_assign(tty, new_ldisc);
 		tty_set_termios_ldisc(tty, N_TTY);
-		if (new_ldisc.ops->open) {
-			int r = new_ldisc.ops->open(tty);
-				if (r < 0)
-				panic("Couldn't open N_TTY ldisc for "
-				      "%s --- error %d.",
-				      tty_name(tty, buf), r);
-		}
+		r = tty_ldisc_open(tty, new_ldisc);
+		if (r < 0)
+			panic("Couldn't open N_TTY ldisc for "
+			      "%s --- error %d.",
+			      tty_name(tty, buf), r);
 	}
 }
 
+/**
+ *	tty_ldisc_halt		-	shut down the line discipline
+ *	@tty: tty device
+ *
+ *	Shut down the line discipline and work queue for this tty device.
+ *	The TTY_LDISC flag being cleared ensures no further references can
+ *	be obtained while the delayed work queue halt ensures that no more
+ *	data is fed to the ldisc.
+ *
+ *	In order to wait for any existing references to complete see
+ *	tty_ldisc_wait_idle.
+ */
+
+static int tty_ldisc_halt(struct tty_struct *tty)
+{
+	clear_bit(TTY_LDISC, &tty->flags);
+	return cancel_delayed_work(&tty->buf.work);
+}
+
+/**
+ *	tty_ldisc_wait_idle	-	wait for the ldisc to become idle
+ *	@tty: tty to wait for
+ *
+ *	Wait for the line discipline to become idle. The discipline must
+ *	have been halted for this to guarantee it remains idle.
+ *
+ *	tty_ldisc_lock protects the ref counts currently.
+ */
+
+static int tty_ldisc_wait_idle(struct tty_struct *tty)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&tty_ldisc_lock, flags);
+	while (tty->ldisc->refcount) {
+		spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+		if (wait_event_timeout(tty_ldisc_wait,
+				tty->ldisc->refcount == 0, 5 * HZ) == 0)
+			return -EBUSY;
+		spin_lock_irqsave(&tty_ldisc_lock, flags);
+	}
+	spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+	return 0;
+}
+
 /**
  *	tty_set_ldisc		-	set line discipline
  *	@tty: the terminal to set
  *	@ldisc: the line discipline
  *
  *	Set the discipline of a tty line. Must be called from a process
- *	context.
+ *	context. The ldisc change logic has to protect itself against any
+ *	overlapping ldisc change (including on the other end of pty pairs),
+ *	the close of one side of a tty/pty pair, and eventually hangup.
  *
- *	Locking: takes tty_ldisc_lock.
- *		 called functions take termios_mutex
+ *	Locking: takes tty_ldisc_lock, termios_mutex
  */
 
 int tty_set_ldisc(struct tty_struct *tty, int ldisc)
 {
 	int retval;
-	struct tty_ldisc o_ldisc, new_ldisc;
-	int work;
-	unsigned long flags;
+	struct tty_ldisc *o_ldisc, *new_ldisc;
+	int work, o_work = 0;
 	struct tty_struct *o_tty;
 
-restart:
-	/* This is a bit ugly for now but means we can break the 'ldisc
-	   is part of the tty struct' assumption later */
-	retval = tty_ldisc_get(ldisc, &new_ldisc);
-	if (retval)
-		return retval;
+	new_ldisc = tty_ldisc_get(ldisc);
+	if (IS_ERR(new_ldisc))
+		return PTR_ERR(new_ldisc);
+
+	/*
+	 *	We need to look at the tty locking here for pty/tty pairs
+	 *	when both sides try to change in parallel.
+	 */
+
+	o_tty = tty->link;	/* o_tty is the pty side or NULL */
+
+
+	/*
+	 *	Check the no-op case
+	 */
+
+	if (tty->ldisc->ops->num == ldisc) {
+		tty_ldisc_put(new_ldisc);
+		return 0;
+	}
 
 	/*
 	 *	Problem: What do we do if this blocks ?
+	 *	We could deadlock here
 	 */
 
 	tty_wait_until_sent(tty, 0);
 
-	if (tty->ldisc.ops->num == ldisc) {
-		tty_ldisc_put(new_ldisc.ops);
-		return 0;
+	mutex_lock(&tty->ldisc_mutex);
+
+	/*
+	 *	We could be midstream of another ldisc change which has
+	 *	dropped the lock during processing. If so we need to wait.
+	 */
+
+	while (test_bit(TTY_LDISC_CHANGING, &tty->flags)) {
+		mutex_unlock(&tty->ldisc_mutex);
+		wait_event(tty_ldisc_wait,
+			test_bit(TTY_LDISC_CHANGING, &tty->flags) == 0);
+		mutex_lock(&tty->ldisc_mutex);
 	}
+	set_bit(TTY_LDISC_CHANGING, &tty->flags);
 
 	/*
 	 *	No more input please, we are switching. The new ldisc
@@ -489,8 +616,6 @@ restart:
 	tty->receive_room = 0;
 
 	o_ldisc = tty->ldisc;
-	o_tty = tty->link;
-
 	/*
 	 *	Make sure we don't change while someone holds a
 	 *	reference to the line discipline. The TTY_LDISC bit
@@ -501,108 +626,181 @@ restart:
 	 *	with a userspace app continually trying to use the tty in
 	 *	parallel to the change and re-referencing the tty.
 	 */
-	clear_bit(TTY_LDISC, &tty->flags);
-	if (o_tty)
-		clear_bit(TTY_LDISC, &o_tty->flags);
 
-	spin_lock_irqsave(&tty_ldisc_lock, flags);
-	if (tty->ldisc.refcount || (o_tty && o_tty->ldisc.refcount)) {
-		if (tty->ldisc.refcount) {
-			/* Free the new ldisc we grabbed. Must drop the lock
-			   first. */
-			spin_unlock_irqrestore(&tty_ldisc_lock, flags);
-			tty_ldisc_put(o_ldisc.ops);
-			/*
-			 * There are several reasons we may be busy, including
-			 * random momentary I/O traffic. We must therefore
-			 * retry. We could distinguish between blocking ops
-			 * and retries if we made tty_ldisc_wait() smarter.
-			 * That is up for discussion.
-			 */
-			if (wait_event_interruptible(tty_ldisc_wait, tty->ldisc.refcount == 0) < 0)
-				return -ERESTARTSYS;
-			goto restart;
-		}
-		if (o_tty && o_tty->ldisc.refcount) {
-			spin_unlock_irqrestore(&tty_ldisc_lock, flags);
-			tty_ldisc_put(o_tty->ldisc.ops);
-			if (wait_event_interruptible(tty_ldisc_wait, o_tty->ldisc.refcount == 0) < 0)
-				return -ERESTARTSYS;
-			goto restart;
-		}
-	}
-	/*
-	 *	If the TTY_LDISC bit is set, then we are racing against
-	 *	another ldisc change
-	 */
-	if (test_bit(TTY_LDISC_CHANGING, &tty->flags)) {
-		struct tty_ldisc *ld;
-		spin_unlock_irqrestore(&tty_ldisc_lock, flags);
-		tty_ldisc_put(new_ldisc.ops);
-		ld = tty_ldisc_ref_wait(tty);
-		tty_ldisc_deref(ld);
-		goto restart;
-	}
-	/*
-	 *	This flag is used to avoid two parallel ldisc changes. Once
-	 *	open and close are fine grained locked this may work better
-	 *	as a mutex shared with the open/close/hup paths
-	 */
-	set_bit(TTY_LDISC_CHANGING, &tty->flags);
+	work = tty_ldisc_halt(tty);
 	if (o_tty)
-		set_bit(TTY_LDISC_CHANGING, &o_tty->flags);
-	spin_unlock_irqrestore(&tty_ldisc_lock, flags);
-	
+		o_work = tty_ldisc_halt(o_tty);
+
 	/*
-	 *	From this point on we know nobody has an ldisc
-	 *	usage reference, nor can they obtain one until
-	 *	we say so later on.
+	 * Wait for ->hangup_work and ->buf.work handlers to terminate.
+	 * We must drop the mutex here in case a hangup is also in process.
 	 */
 
-	work = cancel_delayed_work(&tty->buf.work);
-	/*
-	 * Wait for ->hangup_work and ->buf.work handlers to terminate
-	 * MUST NOT hold locks here.
-	 */
+	mutex_unlock(&tty->ldisc_mutex);
+
 	flush_scheduled_work();
+
+	/* Let any existing reference holders finish */
+	retval = tty_ldisc_wait_idle(tty);
+	if (retval < 0) {
+		clear_bit(TTY_LDISC_CHANGING, &tty->flags);
+		tty_ldisc_put(new_ldisc);
+		return retval;
+	}
+
+	mutex_lock(&tty->ldisc_mutex);
+	if (test_bit(TTY_HUPPED, &tty->flags)) {
+		/* We were raced by the hangup method. It will have stomped
+		   the ldisc data and closed the ldisc down */
+		clear_bit(TTY_LDISC_CHANGING, &tty->flags);
+		mutex_unlock(&tty->ldisc_mutex);
+		tty_ldisc_put(new_ldisc);
+		return -EIO;
+	}
+
 	/* Shutdown the current discipline. */
-	if (o_ldisc.ops->close)
-		(o_ldisc.ops->close)(tty);
+	tty_ldisc_close(tty, o_ldisc);
 
 	/* Now set up the new line discipline. */
-	tty_ldisc_assign(tty, &new_ldisc);
+	tty_ldisc_assign(tty, new_ldisc);
 	tty_set_termios_ldisc(tty, ldisc);
-	if (new_ldisc.ops->open)
-		retval = (new_ldisc.ops->open)(tty);
+
+	retval = tty_ldisc_open(tty, new_ldisc);
 	if (retval < 0) {
-		tty_ldisc_put(new_ldisc.ops);
-		tty_ldisc_restore(tty, &o_ldisc);
+		/* Back to the old one or N_TTY if we can't */
+		tty_ldisc_put(new_ldisc);
+		tty_ldisc_restore(tty, o_ldisc);
 	}
+
 	/* At this point we hold a reference to the new ldisc and a
 	   a reference to the old ldisc. If we ended up flipping back
 	   to the existing ldisc we have two references to it */
 
-	if (tty->ldisc.ops->num != o_ldisc.ops->num && tty->ops->set_ldisc)
+	if (tty->ldisc->ops->num != o_ldisc->ops->num && tty->ops->set_ldisc)
 		tty->ops->set_ldisc(tty);
 
-	tty_ldisc_put(o_ldisc.ops);
+	tty_ldisc_put(o_ldisc);
 
 	/*
-	 *	Allow ldisc referencing to occur as soon as the driver
-	 *	ldisc callback completes.
+	 *	Allow ldisc referencing to occur again
 	 */
 
 	tty_ldisc_enable(tty);
 	if (o_tty)
 		tty_ldisc_enable(o_tty);
 
-	/* Restart it in case no characters kick it off. Safe if
+	/* Restart the work queue in case no characters kick it off. Safe if
 	   already running */
 	if (work)
 		schedule_delayed_work(&tty->buf.work, 1);
+	if (o_work)
+		schedule_delayed_work(&o_tty->buf.work, 1);
+	mutex_unlock(&tty->ldisc_mutex);
 	return retval;
 }
 
+/**
+ *	tty_reset_termios	-	reset terminal state
+ *	@tty: tty to reset
+ *
+ *	Restore a terminal to the driver default state.
+ */
+
+static void tty_reset_termios(struct tty_struct *tty)
+{
+	mutex_lock(&tty->termios_mutex);
+	*tty->termios = tty->driver->init_termios;
+	tty->termios->c_ispeed = tty_termios_input_baud_rate(tty->termios);
+	tty->termios->c_ospeed = tty_termios_baud_rate(tty->termios);
+	mutex_unlock(&tty->termios_mutex);
+}
+
+
+/**
+ *	tty_ldisc_reinit	-	reinitialise the tty ldisc
+ *	@tty: tty to reinit
+ *
+ *	Switch the tty back to N_TTY line discipline and leave the
+ *	ldisc state closed
+ */
+
+static void tty_ldisc_reinit(struct tty_struct *tty)
+{
+	struct tty_ldisc *ld;
+
+	tty_ldisc_close(tty, tty->ldisc);
+	tty_ldisc_put(tty->ldisc);
+	tty->ldisc = NULL;
+	/*
+	 *	Switch the line discipline back
+	 */
+	ld = tty_ldisc_get(N_TTY);
+	BUG_ON(IS_ERR(ld));
+	tty_ldisc_assign(tty, ld);
+	tty_set_termios_ldisc(tty, N_TTY);
+}
+
+/**
+ *	tty_ldisc_hangup		-	hangup ldisc reset
+ *	@tty: tty being hung up
+ *
+ *	Some tty devices reset their termios when they receive a hangup
+ *	event. In that situation we must also switch back to N_TTY properly
+ *	before we reset the termios data.
+ *
+ *	Locking: We can take the ldisc mutex as the rest of the code is
+ *	careful to allow for this.
+ *
+ *	In the pty pair case this occurs in the close() path of the
+ *	tty itself so we must be careful about locking rules.
+ */
+
+void tty_ldisc_hangup(struct tty_struct *tty)
+{
+	struct tty_ldisc *ld;
+
+	/*
+	 * FIXME! What are the locking issues here? This may me overdoing
+	 * things... This question is especially important now that we've
+	 * removed the irqlock.
+	 */
+	ld = tty_ldisc_ref(tty);
+	if (ld != NULL) {
+		/* We may have no line discipline at this point */
+		if (ld->ops->flush_buffer)
+			ld->ops->flush_buffer(tty);
+		tty_driver_flush_buffer(tty);
+		if ((test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) &&
+		    ld->ops->write_wakeup)
+			ld->ops->write_wakeup(tty);
+		if (ld->ops->hangup)
+			ld->ops->hangup(tty);
+		tty_ldisc_deref(ld);
+	}
+	/*
+	 * FIXME: Once we trust the LDISC code better we can wait here for
+	 * ldisc completion and fix the driver call race
+	 */
+	wake_up_interruptible_poll(&tty->write_wait, POLLOUT);
+	wake_up_interruptible_poll(&tty->read_wait, POLLIN);
+	/*
+	 * Shutdown the current line discipline, and reset it to
+	 * N_TTY.
+	 */
+	if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS) {
+		/* Avoid racing set_ldisc */
+		mutex_lock(&tty->ldisc_mutex);
+		/* Switch back to N_TTY */
+		tty_ldisc_reinit(tty);
+		/* At this point we have a closed ldisc and we want to
+		   reopen it. We could defer this to the next open but
+		   it means auditing a lot of other paths so this is a FIXME */
+		WARN_ON(tty_ldisc_open(tty, tty->ldisc));
+		tty_ldisc_enable(tty);
+		mutex_unlock(&tty->ldisc_mutex);
+		tty_reset_termios(tty);
+	}
+}
 
 /**
  *	tty_ldisc_setup			-	open line discipline
@@ -610,24 +808,23 @@ restart:
  *	@o_tty: pair tty for pty/tty pairs
  *
  *	Called during the initial open of a tty/pty pair in order to set up the
- *	line discplines and bind them to the tty.
+ *	line disciplines and bind them to the tty. This has no locking issues
+ *	as the device isn't yet active.
  */
 
 int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty)
 {
-	struct tty_ldisc *ld = &tty->ldisc;
+	struct tty_ldisc *ld = tty->ldisc;
 	int retval;
 
-	if (ld->ops->open) {
-		retval = (ld->ops->open)(tty);
-		if (retval)
-			return retval;
-	}
-	if (o_tty && o_tty->ldisc.ops->open) {
-		retval = (o_tty->ldisc.ops->open)(o_tty);
+	retval = tty_ldisc_open(tty, ld);
+	if (retval)
+		return retval;
+
+	if (o_tty) {
+		retval = tty_ldisc_open(o_tty, o_tty->ldisc);
 		if (retval) {
-			if (ld->ops->close)
-				(ld->ops->close)(tty);
+			tty_ldisc_close(tty, ld);
 			return retval;
 		}
 		tty_ldisc_enable(o_tty);
@@ -635,32 +832,25 @@ int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty)
 	tty_ldisc_enable(tty);
 	return 0;
 }
-
 /**
  *	tty_ldisc_release		-	release line discipline
  *	@tty: tty being shut down
  *	@o_tty: pair tty for pty/tty pairs
  *
- *	Called during the final close of a tty/pty pair in order to shut down the
- *	line discpline layer.
+ *	Called during the final close of a tty/pty pair in order to shut down
+ *	the line discpline layer. On exit the ldisc assigned is N_TTY and the
+ *	ldisc has not been opened.
  */
 
 void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty)
 {
-	unsigned long flags;
-	struct tty_ldisc ld;
 	/*
 	 * Prevent flush_to_ldisc() from rescheduling the work for later.  Then
 	 * kill any delayed work. As this is the final close it does not
 	 * race with the set_ldisc code path.
 	 */
-	clear_bit(TTY_LDISC, &tty->flags);
-	cancel_delayed_work(&tty->buf.work);
-
-	/*
-	 * Wait for ->hangup_work and ->buf.work handlers to terminate
-	 */
 
+	tty_ldisc_halt(tty);
 	flush_scheduled_work();
 
 	/*
@@ -668,38 +858,19 @@ void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty)
 	 * side waiters as the file is closing so user count on the file
 	 * side is zero.
 	 */
-	spin_lock_irqsave(&tty_ldisc_lock, flags);
-	while (tty->ldisc.refcount) {
-		spin_unlock_irqrestore(&tty_ldisc_lock, flags);
-		wait_event(tty_ldisc_wait, tty->ldisc.refcount == 0);
-		spin_lock_irqsave(&tty_ldisc_lock, flags);
-	}
-	spin_unlock_irqrestore(&tty_ldisc_lock, flags);
+
+	tty_ldisc_wait_idle(tty);
+
 	/*
 	 * Shutdown the current line discipline, and reset it to N_TTY.
 	 *
 	 * FIXME: this MUST get fixed for the new reflocking
 	 */
-	if (tty->ldisc.ops->close)
-		(tty->ldisc.ops->close)(tty);
-	tty_ldisc_put(tty->ldisc.ops);
 
-	/*
-	 *	Switch the line discipline back
-	 */
-	WARN_ON(tty_ldisc_get(N_TTY, &ld));
-	tty_ldisc_assign(tty, &ld);
-	tty_set_termios_ldisc(tty, N_TTY);
-	if (o_tty) {
-		/* FIXME: could o_tty be in setldisc here ? */
-		clear_bit(TTY_LDISC, &o_tty->flags);
-		if (o_tty->ldisc.ops->close)
-			(o_tty->ldisc.ops->close)(o_tty);
-		tty_ldisc_put(o_tty->ldisc.ops);
-		WARN_ON(tty_ldisc_get(N_TTY, &ld));
-		tty_ldisc_assign(o_tty, &ld);
-		tty_set_termios_ldisc(o_tty, N_TTY);
-	}
+	tty_ldisc_reinit(tty);
+	/* This will need doing differently if we need to lock */
+	if (o_tty)
+		tty_ldisc_release(o_tty, NULL);
 }
 
 /**
@@ -712,10 +883,10 @@ void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty)
 
 void tty_ldisc_init(struct tty_struct *tty)
 {
-	struct tty_ldisc ld;
-	if (tty_ldisc_get(N_TTY, &ld) < 0)
+	struct tty_ldisc *ld = tty_ldisc_get(N_TTY);
+	if (IS_ERR(ld))
 		panic("n_tty: init_tty");
-	tty_ldisc_assign(tty, &ld);
+	tty_ldisc_assign(tty, ld);
 }
 
 void tty_ldisc_begin(void)
diff --git a/drivers/char/tty_port.c b/drivers/char/tty_port.c
index 9b8004c72686..62dadfc95e34 100644
--- a/drivers/char/tty_port.c
+++ b/drivers/char/tty_port.c
@@ -137,7 +137,7 @@ int tty_port_carrier_raised(struct tty_port *port)
 EXPORT_SYMBOL(tty_port_carrier_raised);
 
 /**
- *	tty_port_raise_dtr_rts	-	Riase DTR/RTS
+ *	tty_port_raise_dtr_rts	-	Raise DTR/RTS
  *	@port: tty port
  *
  *	Wrapper for the DTR/RTS raise logic. For the moment this is used
@@ -147,11 +147,27 @@ EXPORT_SYMBOL(tty_port_carrier_raised);
 
 void tty_port_raise_dtr_rts(struct tty_port *port)
 {
-	if (port->ops->raise_dtr_rts)
-		port->ops->raise_dtr_rts(port);
+	if (port->ops->dtr_rts)
+		port->ops->dtr_rts(port, 1);
 }
 EXPORT_SYMBOL(tty_port_raise_dtr_rts);
 
+/**
+ *	tty_port_lower_dtr_rts	-	Lower DTR/RTS
+ *	@port: tty port
+ *
+ *	Wrapper for the DTR/RTS raise logic. For the moment this is used
+ *	to hide some internal details. This will eventually become entirely
+ *	internal to the tty port.
+ */
+
+void tty_port_lower_dtr_rts(struct tty_port *port)
+{
+	if (port->ops->dtr_rts)
+		port->ops->dtr_rts(port, 0);
+}
+EXPORT_SYMBOL(tty_port_lower_dtr_rts);
+
 /**
  *	tty_port_block_til_ready	-	Waiting logic for tty open
  *	@port: the tty port being opened
@@ -167,7 +183,7 @@ EXPORT_SYMBOL(tty_port_raise_dtr_rts);
  *		- port flags and counts
  *
  *	The passed tty_port must implement the carrier_raised method if it can
- *	do carrier detect and the raise_dtr_rts method if it supports software
+ *	do carrier detect and the dtr_rts method if it supports software
  *	management of these lines. Note that the dtr/rts raise is done each
  *	iteration as a hangup may have previously dropped them while we wait.
  */
@@ -182,7 +198,8 @@ int tty_port_block_til_ready(struct tty_port *port,
 
 	/* block if port is in the process of being closed */
 	if (tty_hung_up_p(filp) || port->flags & ASYNC_CLOSING) {
-		interruptible_sleep_on(&port->close_wait);
+		wait_event_interruptible(port->close_wait,
+				!(port->flags & ASYNC_CLOSING));
 		if (port->flags & ASYNC_HUP_NOTIFY)
 			return -EAGAIN;
 		else
@@ -205,7 +222,6 @@ int tty_port_block_til_ready(struct tty_port *port,
 	   before the next open may complete */
 
 	retval = 0;
-	add_wait_queue(&port->open_wait, &wait);
 
 	/* The port lock protects the port counts */
 	spin_lock_irqsave(&port->lock, flags);
@@ -219,7 +235,7 @@ int tty_port_block_til_ready(struct tty_port *port,
 		if (tty->termios->c_cflag & CBAUD)
 			tty_port_raise_dtr_rts(port);
 
-		set_current_state(TASK_INTERRUPTIBLE);
+		prepare_to_wait(&port->open_wait, &wait, TASK_INTERRUPTIBLE);
 		/* Check for a hangup or uninitialised port. Return accordingly */
 		if (tty_hung_up_p(filp) || !(port->flags & ASYNC_INITIALIZED)) {
 			if (port->flags & ASYNC_HUP_NOTIFY)
@@ -240,8 +256,7 @@ int tty_port_block_til_ready(struct tty_port *port,
 		}
 		schedule();
 	}
-	set_current_state(TASK_RUNNING);
-	remove_wait_queue(&port->open_wait, &wait);
+	finish_wait(&port->open_wait, &wait);
 
 	/* Update counts. A parallel hangup will have set count to zero and
 	   we must not mess that up further */
@@ -292,6 +307,17 @@ int tty_port_close_start(struct tty_port *port, struct tty_struct *tty, struct f
 	if (port->flags & ASYNC_INITIALIZED &&
 			port->closing_wait != ASYNC_CLOSING_WAIT_NONE)
 		tty_wait_until_sent(tty, port->closing_wait);
+	if (port->drain_delay) {
+		unsigned int bps = tty_get_baud_rate(tty);
+		long timeout;
+
+		if (bps > 1200)
+			timeout = max_t(long, (HZ * 10 * port->drain_delay) / bps,
+								HZ / 10);
+		else
+			timeout = 2 * HZ;
+		schedule_timeout_interruptible(timeout);
+	}
 	return 1;
 }
 EXPORT_SYMBOL(tty_port_close_start);
@@ -302,6 +328,9 @@ void tty_port_close_end(struct tty_port *port, struct tty_struct *tty)
 
 	tty_ldisc_flush(tty);
 
+	if (tty->termios->c_cflag & HUPCL)
+		tty_port_lower_dtr_rts(port);
+
 	spin_lock_irqsave(&port->lock, flags);
 	tty->closing = 0;
 
diff --git a/drivers/char/vt.c b/drivers/char/vt.c
index 08151d4de489..de9ebee8657b 100644
--- a/drivers/char/vt.c
+++ b/drivers/char/vt.c
@@ -95,7 +95,6 @@
 #include <linux/timer.h>
 #include <linux/interrupt.h>
 #include <linux/workqueue.h>
-#include <linux/bootmem.h>
 #include <linux/pm.h>
 #include <linux/font.h>
 #include <linux/bitops.h>
@@ -104,6 +103,7 @@
 #include <linux/io.h>
 #include <asm/system.h>
 #include <linux/uaccess.h>
+#include <linux/kmemleak.h>
 
 #define MAX_NR_CON_DRIVER 16
 
@@ -2875,14 +2875,11 @@ static int __init con_init(void)
 		mod_timer(&console_timer, jiffies + blankinterval);
 	}
 
-	/*
-	 * kmalloc is not running yet - we use the bootmem allocator.
-	 */
 	for (currcons = 0; currcons < MIN_NR_CONSOLES; currcons++) {
-		vc_cons[currcons].d = vc = alloc_bootmem(sizeof(struct vc_data));
+		vc_cons[currcons].d = vc = kzalloc(sizeof(struct vc_data), GFP_NOWAIT);
 		INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK);
 		visual_init(vc, currcons, 1);
-		vc->vc_screenbuf = (unsigned short *)alloc_bootmem(vc->vc_screenbuf_size);
+		vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT);
 		vc->vc_kmalloced = 0;
 		vc_init(vc, vc->vc_rows, vc->vc_cols,
 			currcons || !vc->vc_sw->con_save_screen);
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 1efb2879a94f..eef216f7f61d 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -3,3 +3,5 @@ obj-$(CONFIG_X86_CYCLONE_TIMER)	+= cyclone.o
 obj-$(CONFIG_X86_PM_TIMER)	+= acpi_pm.o
 obj-$(CONFIG_SCx200HR_TIMER)	+= scx200_hrt.o
 obj-$(CONFIG_SH_TIMER_CMT)	+= sh_cmt.o
+obj-$(CONFIG_SH_TIMER_MTU2)	+= sh_mtu2.o
+obj-$(CONFIG_SH_TIMER_TMU)	+= sh_tmu.o
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 1c92c39a53aa..cf56a2af5fe1 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -18,7 +18,6 @@
  */
 
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/platform_device.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
@@ -29,7 +28,7 @@
 #include <linux/err.h>
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
-#include <linux/sh_cmt.h>
+#include <linux/sh_timer.h>
 
 struct sh_cmt_priv {
 	void __iomem *mapbase;
@@ -47,6 +46,7 @@ struct sh_cmt_priv {
 	unsigned long rate;
 	spinlock_t lock;
 	struct clock_event_device ced;
+	struct clocksource cs;
 	unsigned long total_cycles;
 };
 
@@ -59,7 +59,7 @@ static DEFINE_SPINLOCK(sh_cmt_lock);
 
 static inline unsigned long sh_cmt_read(struct sh_cmt_priv *p, int reg_nr)
 {
-	struct sh_cmt_config *cfg = p->pdev->dev.platform_data;
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
 	void __iomem *base = p->mapbase;
 	unsigned long offs;
 
@@ -83,7 +83,7 @@ static inline unsigned long sh_cmt_read(struct sh_cmt_priv *p, int reg_nr)
 static inline void sh_cmt_write(struct sh_cmt_priv *p, int reg_nr,
 				unsigned long value)
 {
-	struct sh_cmt_config *cfg = p->pdev->dev.platform_data;
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
 	void __iomem *base = p->mapbase;
 	unsigned long offs;
 
@@ -110,23 +110,28 @@ static unsigned long sh_cmt_get_counter(struct sh_cmt_priv *p,
 					int *has_wrapped)
 {
 	unsigned long v1, v2, v3;
+	int o1, o2;
+
+	o1 = sh_cmt_read(p, CMCSR) & p->overflow_bit;
 
 	/* Make sure the timer value is stable. Stolen from acpi_pm.c */
 	do {
+		o2 = o1;
 		v1 = sh_cmt_read(p, CMCNT);
 		v2 = sh_cmt_read(p, CMCNT);
 		v3 = sh_cmt_read(p, CMCNT);
-	} while (unlikely((v1 > v2 && v1 < v3) || (v2 > v3 && v2 < v1)
-			  || (v3 > v1 && v3 < v2)));
+		o1 = sh_cmt_read(p, CMCSR) & p->overflow_bit;
+	} while (unlikely((o1 != o2) || (v1 > v2 && v1 < v3)
+			  || (v2 > v3 && v2 < v1) || (v3 > v1 && v3 < v2)));
 
-	*has_wrapped = sh_cmt_read(p, CMCSR) & p->overflow_bit;
+	*has_wrapped = o1;
 	return v2;
 }
 
 
 static void sh_cmt_start_stop_ch(struct sh_cmt_priv *p, int start)
 {
-	struct sh_cmt_config *cfg = p->pdev->dev.platform_data;
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
 	unsigned long flags, value;
 
 	/* start stop register shared by multiple timer channels */
@@ -144,7 +149,7 @@ static void sh_cmt_start_stop_ch(struct sh_cmt_priv *p, int start)
 
 static int sh_cmt_enable(struct sh_cmt_priv *p, unsigned long *rate)
 {
-	struct sh_cmt_config *cfg = p->pdev->dev.platform_data;
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
 	int ret;
 
 	/* enable clock */
@@ -153,16 +158,18 @@ static int sh_cmt_enable(struct sh_cmt_priv *p, unsigned long *rate)
 		pr_err("sh_cmt: cannot enable clock \"%s\"\n", cfg->clk);
 		return ret;
 	}
-	*rate = clk_get_rate(p->clk) / 8;
 
 	/* make sure channel is disabled */
 	sh_cmt_start_stop_ch(p, 0);
 
 	/* configure channel, periodic mode and maximum timeout */
-	if (p->width == 16)
-		sh_cmt_write(p, CMCSR, 0);
-	else
+	if (p->width == 16) {
+		*rate = clk_get_rate(p->clk) / 512;
+		sh_cmt_write(p, CMCSR, 0x43);
+	} else {
+		*rate = clk_get_rate(p->clk) / 8;
 		sh_cmt_write(p, CMCSR, 0x01a4);
+	}
 
 	sh_cmt_write(p, CMCOR, 0xffffffff);
 	sh_cmt_write(p, CMCNT, 0);
@@ -376,6 +383,68 @@ static void sh_cmt_stop(struct sh_cmt_priv *p, unsigned long flag)
 	spin_unlock_irqrestore(&p->lock, flags);
 }
 
+static struct sh_cmt_priv *cs_to_sh_cmt(struct clocksource *cs)
+{
+	return container_of(cs, struct sh_cmt_priv, cs);
+}
+
+static cycle_t sh_cmt_clocksource_read(struct clocksource *cs)
+{
+	struct sh_cmt_priv *p = cs_to_sh_cmt(cs);
+	unsigned long flags, raw;
+	unsigned long value;
+	int has_wrapped;
+
+	spin_lock_irqsave(&p->lock, flags);
+	value = p->total_cycles;
+	raw = sh_cmt_get_counter(p, &has_wrapped);
+
+	if (unlikely(has_wrapped))
+		raw += p->match_value;
+	spin_unlock_irqrestore(&p->lock, flags);
+
+	return value + raw;
+}
+
+static int sh_cmt_clocksource_enable(struct clocksource *cs)
+{
+	struct sh_cmt_priv *p = cs_to_sh_cmt(cs);
+	int ret;
+
+	p->total_cycles = 0;
+
+	ret = sh_cmt_start(p, FLAG_CLOCKSOURCE);
+	if (ret)
+		return ret;
+
+	/* TODO: calculate good shift from rate and counter bit width */
+	cs->shift = 0;
+	cs->mult = clocksource_hz2mult(p->rate, cs->shift);
+	return 0;
+}
+
+static void sh_cmt_clocksource_disable(struct clocksource *cs)
+{
+	sh_cmt_stop(cs_to_sh_cmt(cs), FLAG_CLOCKSOURCE);
+}
+
+static int sh_cmt_register_clocksource(struct sh_cmt_priv *p,
+				       char *name, unsigned long rating)
+{
+	struct clocksource *cs = &p->cs;
+
+	cs->name = name;
+	cs->rating = rating;
+	cs->read = sh_cmt_clocksource_read;
+	cs->enable = sh_cmt_clocksource_enable;
+	cs->disable = sh_cmt_clocksource_disable;
+	cs->mask = CLOCKSOURCE_MASK(sizeof(unsigned long) * 8);
+	cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
+	pr_info("sh_cmt: %s used as clock source\n", cs->name);
+	clocksource_register(cs);
+	return 0;
+}
+
 static struct sh_cmt_priv *ced_to_sh_cmt(struct clock_event_device *ced)
 {
 	return container_of(ced, struct sh_cmt_priv, ced);
@@ -468,9 +537,9 @@ static void sh_cmt_register_clockevent(struct sh_cmt_priv *p,
 	clockevents_register_device(ced);
 }
 
-int sh_cmt_register(struct sh_cmt_priv *p, char *name,
-		    unsigned long clockevent_rating,
-		    unsigned long clocksource_rating)
+static int sh_cmt_register(struct sh_cmt_priv *p, char *name,
+			   unsigned long clockevent_rating,
+			   unsigned long clocksource_rating)
 {
 	if (p->width == (sizeof(p->max_match_value) * 8))
 		p->max_match_value = ~0;
@@ -483,12 +552,15 @@ int sh_cmt_register(struct sh_cmt_priv *p, char *name,
 	if (clockevent_rating)
 		sh_cmt_register_clockevent(p, name, clockevent_rating);
 
+	if (clocksource_rating)
+		sh_cmt_register_clocksource(p, name, clocksource_rating);
+
 	return 0;
 }
 
 static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 {
-	struct sh_cmt_config *cfg = pdev->dev.platform_data;
+	struct sh_timer_config *cfg = pdev->dev.platform_data;
 	struct resource *res;
 	int irq, ret;
 	ret = -ENXIO;
@@ -545,7 +617,7 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 	if (resource_size(res) == 6) {
 		p->width = 16;
 		p->overflow_bit = 0x80;
-		p->clear_bits = ~0xc0;
+		p->clear_bits = ~0x80;
 	} else {
 		p->width = 32;
 		p->overflow_bit = 0x8000;
@@ -566,8 +638,14 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 static int __devinit sh_cmt_probe(struct platform_device *pdev)
 {
 	struct sh_cmt_priv *p = platform_get_drvdata(pdev);
+	struct sh_timer_config *cfg = pdev->dev.platform_data;
 	int ret;
 
+	if (p) {
+		pr_info("sh_cmt: %s kept as earlytimer\n", cfg->name);
+		return 0;
+	}
+
 	p = kmalloc(sizeof(*p), GFP_KERNEL);
 	if (p == NULL) {
 		dev_err(&pdev->dev, "failed to allocate driver data\n");
@@ -577,7 +655,6 @@ static int __devinit sh_cmt_probe(struct platform_device *pdev)
 	ret = sh_cmt_setup(p, pdev);
 	if (ret) {
 		kfree(p);
-
 		platform_set_drvdata(pdev, NULL);
 	}
 	return ret;
@@ -606,6 +683,7 @@ static void __exit sh_cmt_exit(void)
 	platform_driver_unregister(&sh_cmt_device_driver);
 }
 
+early_platform_init("earlytimer", &sh_cmt_device_driver);
 module_init(sh_cmt_init);
 module_exit(sh_cmt_exit);
 
diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
new file mode 100644
index 000000000000..d1ae75454d10
--- /dev/null
+++ b/drivers/clocksource/sh_mtu2.c
@@ -0,0 +1,357 @@
+/*
+ * SuperH Timer Support - MTU2
+ *
+ *  Copyright (C) 2009 Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/err.h>
+#include <linux/clockchips.h>
+#include <linux/sh_timer.h>
+
+struct sh_mtu2_priv {
+	void __iomem *mapbase;
+	struct clk *clk;
+	struct irqaction irqaction;
+	struct platform_device *pdev;
+	unsigned long rate;
+	unsigned long periodic;
+	struct clock_event_device ced;
+};
+
+static DEFINE_SPINLOCK(sh_mtu2_lock);
+
+#define TSTR -1 /* shared register */
+#define TCR  0 /* channel register */
+#define TMDR 1 /* channel register */
+#define TIOR 2 /* channel register */
+#define TIER 3 /* channel register */
+#define TSR  4 /* channel register */
+#define TCNT 5 /* channel register */
+#define TGR  6 /* channel register */
+
+static unsigned long mtu2_reg_offs[] = {
+	[TCR] = 0,
+	[TMDR] = 1,
+	[TIOR] = 2,
+	[TIER] = 4,
+	[TSR] = 5,
+	[TCNT] = 6,
+	[TGR] = 8,
+};
+
+static inline unsigned long sh_mtu2_read(struct sh_mtu2_priv *p, int reg_nr)
+{
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
+	void __iomem *base = p->mapbase;
+	unsigned long offs;
+
+	if (reg_nr == TSTR)
+		return ioread8(base + cfg->channel_offset);
+
+	offs = mtu2_reg_offs[reg_nr];
+
+	if ((reg_nr == TCNT) || (reg_nr == TGR))
+		return ioread16(base + offs);
+	else
+		return ioread8(base + offs);
+}
+
+static inline void sh_mtu2_write(struct sh_mtu2_priv *p, int reg_nr,
+				unsigned long value)
+{
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
+	void __iomem *base = p->mapbase;
+	unsigned long offs;
+
+	if (reg_nr == TSTR) {
+		iowrite8(value, base + cfg->channel_offset);
+		return;
+	}
+
+	offs = mtu2_reg_offs[reg_nr];
+
+	if ((reg_nr == TCNT) || (reg_nr == TGR))
+		iowrite16(value, base + offs);
+	else
+		iowrite8(value, base + offs);
+}
+
+static void sh_mtu2_start_stop_ch(struct sh_mtu2_priv *p, int start)
+{
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
+	unsigned long flags, value;
+
+	/* start stop register shared by multiple timer channels */
+	spin_lock_irqsave(&sh_mtu2_lock, flags);
+	value = sh_mtu2_read(p, TSTR);
+
+	if (start)
+		value |= 1 << cfg->timer_bit;
+	else
+		value &= ~(1 << cfg->timer_bit);
+
+	sh_mtu2_write(p, TSTR, value);
+	spin_unlock_irqrestore(&sh_mtu2_lock, flags);
+}
+
+static int sh_mtu2_enable(struct sh_mtu2_priv *p)
+{
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
+	int ret;
+
+	/* enable clock */
+	ret = clk_enable(p->clk);
+	if (ret) {
+		pr_err("sh_mtu2: cannot enable clock \"%s\"\n", cfg->clk);
+		return ret;
+	}
+
+	/* make sure channel is disabled */
+	sh_mtu2_start_stop_ch(p, 0);
+
+	p->rate = clk_get_rate(p->clk) / 64;
+	p->periodic = (p->rate + HZ/2) / HZ;
+
+	/* "Periodic Counter Operation" */
+	sh_mtu2_write(p, TCR, 0x23); /* TGRA clear, divide clock by 64 */
+	sh_mtu2_write(p, TIOR, 0);
+	sh_mtu2_write(p, TGR, p->periodic);
+	sh_mtu2_write(p, TCNT, 0);
+	sh_mtu2_write(p, TMDR, 0);
+	sh_mtu2_write(p, TIER, 0x01);
+
+	/* enable channel */
+	sh_mtu2_start_stop_ch(p, 1);
+
+	return 0;
+}
+
+static void sh_mtu2_disable(struct sh_mtu2_priv *p)
+{
+	/* disable channel */
+	sh_mtu2_start_stop_ch(p, 0);
+
+	/* stop clock */
+	clk_disable(p->clk);
+}
+
+static irqreturn_t sh_mtu2_interrupt(int irq, void *dev_id)
+{
+	struct sh_mtu2_priv *p = dev_id;
+
+	/* acknowledge interrupt */
+	sh_mtu2_read(p, TSR);
+	sh_mtu2_write(p, TSR, 0xfe);
+
+	/* notify clockevent layer */
+	p->ced.event_handler(&p->ced);
+	return IRQ_HANDLED;
+}
+
+static struct sh_mtu2_priv *ced_to_sh_mtu2(struct clock_event_device *ced)
+{
+	return container_of(ced, struct sh_mtu2_priv, ced);
+}
+
+static void sh_mtu2_clock_event_mode(enum clock_event_mode mode,
+				    struct clock_event_device *ced)
+{
+	struct sh_mtu2_priv *p = ced_to_sh_mtu2(ced);
+	int disabled = 0;
+
+	/* deal with old setting first */
+	switch (ced->mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		sh_mtu2_disable(p);
+		disabled = 1;
+		break;
+	default:
+		break;
+	}
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		pr_info("sh_mtu2: %s used for periodic clock events\n",
+			ced->name);
+		sh_mtu2_enable(p);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+		if (!disabled)
+			sh_mtu2_disable(p);
+		break;
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	default:
+		break;
+	}
+}
+
+static void sh_mtu2_register_clockevent(struct sh_mtu2_priv *p,
+				       char *name, unsigned long rating)
+{
+	struct clock_event_device *ced = &p->ced;
+	int ret;
+
+	memset(ced, 0, sizeof(*ced));
+
+	ced->name = name;
+	ced->features = CLOCK_EVT_FEAT_PERIODIC;
+	ced->rating = rating;
+	ced->cpumask = cpumask_of(0);
+	ced->set_mode = sh_mtu2_clock_event_mode;
+
+	ret = setup_irq(p->irqaction.irq, &p->irqaction);
+	if (ret) {
+		pr_err("sh_mtu2: failed to request irq %d\n",
+		       p->irqaction.irq);
+		return;
+	}
+
+	pr_info("sh_mtu2: %s used for clock events\n", ced->name);
+	clockevents_register_device(ced);
+}
+
+static int sh_mtu2_register(struct sh_mtu2_priv *p, char *name,
+			    unsigned long clockevent_rating)
+{
+	if (clockevent_rating)
+		sh_mtu2_register_clockevent(p, name, clockevent_rating);
+
+	return 0;
+}
+
+static int sh_mtu2_setup(struct sh_mtu2_priv *p, struct platform_device *pdev)
+{
+	struct sh_timer_config *cfg = pdev->dev.platform_data;
+	struct resource *res;
+	int irq, ret;
+	ret = -ENXIO;
+
+	memset(p, 0, sizeof(*p));
+	p->pdev = pdev;
+
+	if (!cfg) {
+		dev_err(&p->pdev->dev, "missing platform data\n");
+		goto err0;
+	}
+
+	platform_set_drvdata(pdev, p);
+
+	res = platform_get_resource(p->pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&p->pdev->dev, "failed to get I/O memory\n");
+		goto err0;
+	}
+
+	irq = platform_get_irq(p->pdev, 0);
+	if (irq < 0) {
+		dev_err(&p->pdev->dev, "failed to get irq\n");
+		goto err0;
+	}
+
+	/* map memory, let mapbase point to our channel */
+	p->mapbase = ioremap_nocache(res->start, resource_size(res));
+	if (p->mapbase == NULL) {
+		pr_err("sh_mtu2: failed to remap I/O memory\n");
+		goto err0;
+	}
+
+	/* setup data for setup_irq() (too early for request_irq()) */
+	p->irqaction.name = cfg->name;
+	p->irqaction.handler = sh_mtu2_interrupt;
+	p->irqaction.dev_id = p;
+	p->irqaction.irq = irq;
+	p->irqaction.flags = IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL;
+	p->irqaction.mask = CPU_MASK_NONE;
+
+	/* get hold of clock */
+	p->clk = clk_get(&p->pdev->dev, cfg->clk);
+	if (IS_ERR(p->clk)) {
+		pr_err("sh_mtu2: cannot get clock \"%s\"\n", cfg->clk);
+		ret = PTR_ERR(p->clk);
+		goto err1;
+	}
+
+	return sh_mtu2_register(p, cfg->name, cfg->clockevent_rating);
+ err1:
+	iounmap(p->mapbase);
+ err0:
+	return ret;
+}
+
+static int __devinit sh_mtu2_probe(struct platform_device *pdev)
+{
+	struct sh_mtu2_priv *p = platform_get_drvdata(pdev);
+	struct sh_timer_config *cfg = pdev->dev.platform_data;
+	int ret;
+
+	if (p) {
+		pr_info("sh_mtu2: %s kept as earlytimer\n", cfg->name);
+		return 0;
+	}
+
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
+	if (p == NULL) {
+		dev_err(&pdev->dev, "failed to allocate driver data\n");
+		return -ENOMEM;
+	}
+
+	ret = sh_mtu2_setup(p, pdev);
+	if (ret) {
+		kfree(p);
+		platform_set_drvdata(pdev, NULL);
+	}
+	return ret;
+}
+
+static int __devexit sh_mtu2_remove(struct platform_device *pdev)
+{
+	return -EBUSY; /* cannot unregister clockevent */
+}
+
+static struct platform_driver sh_mtu2_device_driver = {
+	.probe		= sh_mtu2_probe,
+	.remove		= __devexit_p(sh_mtu2_remove),
+	.driver		= {
+		.name	= "sh_mtu2",
+	}
+};
+
+static int __init sh_mtu2_init(void)
+{
+	return platform_driver_register(&sh_mtu2_device_driver);
+}
+
+static void __exit sh_mtu2_exit(void)
+{
+	platform_driver_unregister(&sh_mtu2_device_driver);
+}
+
+early_platform_init("earlytimer", &sh_mtu2_device_driver);
+module_init(sh_mtu2_init);
+module_exit(sh_mtu2_exit);
+
+MODULE_AUTHOR("Magnus Damm");
+MODULE_DESCRIPTION("SuperH MTU2 Timer Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
new file mode 100644
index 000000000000..d6ea4398bf62
--- /dev/null
+++ b/drivers/clocksource/sh_tmu.c
@@ -0,0 +1,461 @@
+/*
+ * SuperH Timer Support - TMU
+ *
+ *  Copyright (C) 2009 Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/err.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/sh_timer.h>
+
+struct sh_tmu_priv {
+	void __iomem *mapbase;
+	struct clk *clk;
+	struct irqaction irqaction;
+	struct platform_device *pdev;
+	unsigned long rate;
+	unsigned long periodic;
+	struct clock_event_device ced;
+	struct clocksource cs;
+};
+
+static DEFINE_SPINLOCK(sh_tmu_lock);
+
+#define TSTR -1 /* shared register */
+#define TCOR  0 /* channel register */
+#define TCNT 1 /* channel register */
+#define TCR 2 /* channel register */
+
+static inline unsigned long sh_tmu_read(struct sh_tmu_priv *p, int reg_nr)
+{
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
+	void __iomem *base = p->mapbase;
+	unsigned long offs;
+
+	if (reg_nr == TSTR)
+		return ioread8(base - cfg->channel_offset);
+
+	offs = reg_nr << 2;
+
+	if (reg_nr == TCR)
+		return ioread16(base + offs);
+	else
+		return ioread32(base + offs);
+}
+
+static inline void sh_tmu_write(struct sh_tmu_priv *p, int reg_nr,
+				unsigned long value)
+{
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
+	void __iomem *base = p->mapbase;
+	unsigned long offs;
+
+	if (reg_nr == TSTR) {
+		iowrite8(value, base - cfg->channel_offset);
+		return;
+	}
+
+	offs = reg_nr << 2;
+
+	if (reg_nr == TCR)
+		iowrite16(value, base + offs);
+	else
+		iowrite32(value, base + offs);
+}
+
+static void sh_tmu_start_stop_ch(struct sh_tmu_priv *p, int start)
+{
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
+	unsigned long flags, value;
+
+	/* start stop register shared by multiple timer channels */
+	spin_lock_irqsave(&sh_tmu_lock, flags);
+	value = sh_tmu_read(p, TSTR);
+
+	if (start)
+		value |= 1 << cfg->timer_bit;
+	else
+		value &= ~(1 << cfg->timer_bit);
+
+	sh_tmu_write(p, TSTR, value);
+	spin_unlock_irqrestore(&sh_tmu_lock, flags);
+}
+
+static int sh_tmu_enable(struct sh_tmu_priv *p)
+{
+	struct sh_timer_config *cfg = p->pdev->dev.platform_data;
+	int ret;
+
+	/* enable clock */
+	ret = clk_enable(p->clk);
+	if (ret) {
+		pr_err("sh_tmu: cannot enable clock \"%s\"\n", cfg->clk);
+		return ret;
+	}
+
+	/* make sure channel is disabled */
+	sh_tmu_start_stop_ch(p, 0);
+
+	/* maximum timeout */
+	sh_tmu_write(p, TCOR, 0xffffffff);
+	sh_tmu_write(p, TCNT, 0xffffffff);
+
+	/* configure channel to parent clock / 4, irq off */
+	p->rate = clk_get_rate(p->clk) / 4;
+	sh_tmu_write(p, TCR, 0x0000);
+
+	/* enable channel */
+	sh_tmu_start_stop_ch(p, 1);
+
+	return 0;
+}
+
+static void sh_tmu_disable(struct sh_tmu_priv *p)
+{
+	/* disable channel */
+	sh_tmu_start_stop_ch(p, 0);
+
+	/* stop clock */
+	clk_disable(p->clk);
+}
+
+static void sh_tmu_set_next(struct sh_tmu_priv *p, unsigned long delta,
+			    int periodic)
+{
+	/* stop timer */
+	sh_tmu_start_stop_ch(p, 0);
+
+	/* acknowledge interrupt */
+	sh_tmu_read(p, TCR);
+
+	/* enable interrupt */
+	sh_tmu_write(p, TCR, 0x0020);
+
+	/* reload delta value in case of periodic timer */
+	if (periodic)
+		sh_tmu_write(p, TCOR, delta);
+	else
+		sh_tmu_write(p, TCOR, 0);
+
+	sh_tmu_write(p, TCNT, delta);
+
+	/* start timer */
+	sh_tmu_start_stop_ch(p, 1);
+}
+
+static irqreturn_t sh_tmu_interrupt(int irq, void *dev_id)
+{
+	struct sh_tmu_priv *p = dev_id;
+
+	/* disable or acknowledge interrupt */
+	if (p->ced.mode == CLOCK_EVT_MODE_ONESHOT)
+		sh_tmu_write(p, TCR, 0x0000);
+	else
+		sh_tmu_write(p, TCR, 0x0020);
+
+	/* notify clockevent layer */
+	p->ced.event_handler(&p->ced);
+	return IRQ_HANDLED;
+}
+
+static struct sh_tmu_priv *cs_to_sh_tmu(struct clocksource *cs)
+{
+	return container_of(cs, struct sh_tmu_priv, cs);
+}
+
+static cycle_t sh_tmu_clocksource_read(struct clocksource *cs)
+{
+	struct sh_tmu_priv *p = cs_to_sh_tmu(cs);
+
+	return sh_tmu_read(p, TCNT) ^ 0xffffffff;
+}
+
+static int sh_tmu_clocksource_enable(struct clocksource *cs)
+{
+	struct sh_tmu_priv *p = cs_to_sh_tmu(cs);
+	int ret;
+
+	ret = sh_tmu_enable(p);
+	if (ret)
+		return ret;
+
+	/* TODO: calculate good shift from rate and counter bit width */
+	cs->shift = 10;
+	cs->mult = clocksource_hz2mult(p->rate, cs->shift);
+	return 0;
+}
+
+static void sh_tmu_clocksource_disable(struct clocksource *cs)
+{
+	sh_tmu_disable(cs_to_sh_tmu(cs));
+}
+
+static int sh_tmu_register_clocksource(struct sh_tmu_priv *p,
+				       char *name, unsigned long rating)
+{
+	struct clocksource *cs = &p->cs;
+
+	cs->name = name;
+	cs->rating = rating;
+	cs->read = sh_tmu_clocksource_read;
+	cs->enable = sh_tmu_clocksource_enable;
+	cs->disable = sh_tmu_clocksource_disable;
+	cs->mask = CLOCKSOURCE_MASK(32);
+	cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
+	pr_info("sh_tmu: %s used as clock source\n", cs->name);
+	clocksource_register(cs);
+	return 0;
+}
+
+static struct sh_tmu_priv *ced_to_sh_tmu(struct clock_event_device *ced)
+{
+	return container_of(ced, struct sh_tmu_priv, ced);
+}
+
+static void sh_tmu_clock_event_start(struct sh_tmu_priv *p, int periodic)
+{
+	struct clock_event_device *ced = &p->ced;
+
+	sh_tmu_enable(p);
+
+	/* TODO: calculate good shift from rate and counter bit width */
+
+	ced->shift = 32;
+	ced->mult = div_sc(p->rate, NSEC_PER_SEC, ced->shift);
+	ced->max_delta_ns = clockevent_delta2ns(0xffffffff, ced);
+	ced->min_delta_ns = 5000;
+
+	if (periodic) {
+		p->periodic = (p->rate + HZ/2) / HZ;
+		sh_tmu_set_next(p, p->periodic, 1);
+	}
+}
+
+static void sh_tmu_clock_event_mode(enum clock_event_mode mode,
+				    struct clock_event_device *ced)
+{
+	struct sh_tmu_priv *p = ced_to_sh_tmu(ced);
+	int disabled = 0;
+
+	/* deal with old setting first */
+	switch (ced->mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+	case CLOCK_EVT_MODE_ONESHOT:
+		sh_tmu_disable(p);
+		disabled = 1;
+		break;
+	default:
+		break;
+	}
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		pr_info("sh_tmu: %s used for periodic clock events\n",
+			ced->name);
+		sh_tmu_clock_event_start(p, 1);
+		break;
+	case CLOCK_EVT_MODE_ONESHOT:
+		pr_info("sh_tmu: %s used for oneshot clock events\n",
+			ced->name);
+		sh_tmu_clock_event_start(p, 0);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+		if (!disabled)
+			sh_tmu_disable(p);
+		break;
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	default:
+		break;
+	}
+}
+
+static int sh_tmu_clock_event_next(unsigned long delta,
+				   struct clock_event_device *ced)
+{
+	struct sh_tmu_priv *p = ced_to_sh_tmu(ced);
+
+	BUG_ON(ced->mode != CLOCK_EVT_MODE_ONESHOT);
+
+	/* program new delta value */
+	sh_tmu_set_next(p, delta, 0);
+	return 0;
+}
+
+static void sh_tmu_register_clockevent(struct sh_tmu_priv *p,
+				       char *name, unsigned long rating)
+{
+	struct clock_event_device *ced = &p->ced;
+	int ret;
+
+	memset(ced, 0, sizeof(*ced));
+
+	ced->name = name;
+	ced->features = CLOCK_EVT_FEAT_PERIODIC;
+	ced->features |= CLOCK_EVT_FEAT_ONESHOT;
+	ced->rating = rating;
+	ced->cpumask = cpumask_of(0);
+	ced->set_next_event = sh_tmu_clock_event_next;
+	ced->set_mode = sh_tmu_clock_event_mode;
+
+	ret = setup_irq(p->irqaction.irq, &p->irqaction);
+	if (ret) {
+		pr_err("sh_tmu: failed to request irq %d\n",
+		       p->irqaction.irq);
+		return;
+	}
+
+	pr_info("sh_tmu: %s used for clock events\n", ced->name);
+	clockevents_register_device(ced);
+}
+
+static int sh_tmu_register(struct sh_tmu_priv *p, char *name,
+		    unsigned long clockevent_rating,
+		    unsigned long clocksource_rating)
+{
+	if (clockevent_rating)
+		sh_tmu_register_clockevent(p, name, clockevent_rating);
+	else if (clocksource_rating)
+		sh_tmu_register_clocksource(p, name, clocksource_rating);
+
+	return 0;
+}
+
+static int sh_tmu_setup(struct sh_tmu_priv *p, struct platform_device *pdev)
+{
+	struct sh_timer_config *cfg = pdev->dev.platform_data;
+	struct resource *res;
+	int irq, ret;
+	ret = -ENXIO;
+
+	memset(p, 0, sizeof(*p));
+	p->pdev = pdev;
+
+	if (!cfg) {
+		dev_err(&p->pdev->dev, "missing platform data\n");
+		goto err0;
+	}
+
+	platform_set_drvdata(pdev, p);
+
+	res = platform_get_resource(p->pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&p->pdev->dev, "failed to get I/O memory\n");
+		goto err0;
+	}
+
+	irq = platform_get_irq(p->pdev, 0);
+	if (irq < 0) {
+		dev_err(&p->pdev->dev, "failed to get irq\n");
+		goto err0;
+	}
+
+	/* map memory, let mapbase point to our channel */
+	p->mapbase = ioremap_nocache(res->start, resource_size(res));
+	if (p->mapbase == NULL) {
+		pr_err("sh_tmu: failed to remap I/O memory\n");
+		goto err0;
+	}
+
+	/* setup data for setup_irq() (too early for request_irq()) */
+	p->irqaction.name = cfg->name;
+	p->irqaction.handler = sh_tmu_interrupt;
+	p->irqaction.dev_id = p;
+	p->irqaction.irq = irq;
+	p->irqaction.flags = IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL;
+	p->irqaction.mask = CPU_MASK_NONE;
+
+	/* get hold of clock */
+	p->clk = clk_get(&p->pdev->dev, cfg->clk);
+	if (IS_ERR(p->clk)) {
+		pr_err("sh_tmu: cannot get clock \"%s\"\n", cfg->clk);
+		ret = PTR_ERR(p->clk);
+		goto err1;
+	}
+
+	return sh_tmu_register(p, cfg->name,
+			       cfg->clockevent_rating,
+			       cfg->clocksource_rating);
+ err1:
+	iounmap(p->mapbase);
+ err0:
+	return ret;
+}
+
+static int __devinit sh_tmu_probe(struct platform_device *pdev)
+{
+	struct sh_tmu_priv *p = platform_get_drvdata(pdev);
+	struct sh_timer_config *cfg = pdev->dev.platform_data;
+	int ret;
+
+	if (p) {
+		pr_info("sh_tmu: %s kept as earlytimer\n", cfg->name);
+		return 0;
+	}
+
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
+	if (p == NULL) {
+		dev_err(&pdev->dev, "failed to allocate driver data\n");
+		return -ENOMEM;
+	}
+
+	ret = sh_tmu_setup(p, pdev);
+	if (ret) {
+		kfree(p);
+		platform_set_drvdata(pdev, NULL);
+	}
+	return ret;
+}
+
+static int __devexit sh_tmu_remove(struct platform_device *pdev)
+{
+	return -EBUSY; /* cannot unregister clockevent and clocksource */
+}
+
+static struct platform_driver sh_tmu_device_driver = {
+	.probe		= sh_tmu_probe,
+	.remove		= __devexit_p(sh_tmu_remove),
+	.driver		= {
+		.name	= "sh_tmu",
+	}
+};
+
+static int __init sh_tmu_init(void)
+{
+	return platform_driver_register(&sh_tmu_device_driver);
+}
+
+static void __exit sh_tmu_exit(void)
+{
+	platform_driver_unregister(&sh_tmu_device_driver);
+}
+
+early_platform_init("earlytimer", &sh_tmu_device_driver);
+module_init(sh_tmu_init);
+module_exit(sh_tmu_exit);
+
+MODULE_AUTHOR("Magnus Damm");
+MODULE_DESCRIPTION("SuperH TMU Timer Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 956982f8739b..ab4f3592a11c 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -49,7 +49,6 @@ config EDAC_DEBUG_VERBOSE
 
 config EDAC_MM_EDAC
 	tristate "Main Memory EDAC (Error Detection And Correction) reporting"
-	default y
 	help
 	  Some systems are able to detect and correct errors in main
 	  memory.  EDAC can report statistics on memory error
@@ -58,6 +57,31 @@ config EDAC_MM_EDAC
 	  occurred so that a particular failing memory module can be
 	  replaced.  If unsure, select 'Y'.
 
+config EDAC_AMD64
+	tristate "AMD64 (Opteron, Athlon64) K8, F10h, F11h"
+	depends on EDAC_MM_EDAC && K8_NB && X86_64 && PCI
+	help
+	  Support for error detection and correction on the AMD 64
+	  Families of Memory Controllers (K8, F10h and F11h)
+
+config EDAC_AMD64_ERROR_INJECTION
+	bool "Sysfs Error Injection facilities"
+	depends on EDAC_AMD64
+	help
+	  Recent Opterons (Family 10h and later) provide for Memory Error
+	  Injection into the ECC detection circuits. The amd64_edac module
+	  allows the operator/user to inject Uncorrectable and Correctable
+	  errors into DRAM.
+
+	  When enabled, in each of the respective memory controller directories
+	  (/sys/devices/system/edac/mc/mcX), there are 3 input files:
+
+	  - inject_section (0..3, 16-byte section of 64-byte cacheline),
+	  - inject_word (0..8, 16-bit word of 16-byte section),
+	  - inject_ecc_vector (hex ecc vector: select bits of inject word)
+
+	  In addition, there are two control files, inject_read and inject_write,
+	  which trigger the DRAM ECC Read and Write respectively.
 
 config EDAC_AMD76X
 	tristate "AMD 76x (760, 762, 768)"
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 59076819135d..633dc5604ee3 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -30,6 +30,13 @@ obj-$(CONFIG_EDAC_I3000)		+= i3000_edac.o
 obj-$(CONFIG_EDAC_X38)			+= x38_edac.o
 obj-$(CONFIG_EDAC_I82860)		+= i82860_edac.o
 obj-$(CONFIG_EDAC_R82600)		+= r82600_edac.o
+
+amd64_edac_mod-y :=  amd64_edac_err_types.o amd64_edac.o
+amd64_edac_mod-$(CONFIG_EDAC_DEBUG) += amd64_edac_dbg.o
+amd64_edac_mod-$(CONFIG_EDAC_AMD64_ERROR_INJECTION) += amd64_edac_inj.o
+
+obj-$(CONFIG_EDAC_AMD64)		+= amd64_edac_mod.o
+
 obj-$(CONFIG_EDAC_PASEMI)		+= pasemi_edac.o
 obj-$(CONFIG_EDAC_MPC85XX)		+= mpc85xx_edac.o
 obj-$(CONFIG_EDAC_MV64X60)		+= mv64x60_edac.o
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
new file mode 100644
index 000000000000..c36bf40568cf
--- /dev/null
+++ b/drivers/edac/amd64_edac.c
@@ -0,0 +1,3354 @@
+#include "amd64_edac.h"
+#include <asm/k8.h>
+
+static struct edac_pci_ctl_info *amd64_ctl_pci;
+
+static int report_gart_errors;
+module_param(report_gart_errors, int, 0644);
+
+/*
+ * Set by command line parameter. If BIOS has enabled the ECC, this override is
+ * cleared to prevent re-enabling the hardware by this driver.
+ */
+static int ecc_enable_override;
+module_param(ecc_enable_override, int, 0644);
+
+/* Lookup table for all possible MC control instances */
+struct amd64_pvt;
+static struct mem_ctl_info *mci_lookup[MAX_NUMNODES];
+static struct amd64_pvt *pvt_lookup[MAX_NUMNODES];
+
+/*
+ * Memory scrubber control interface. For K8, memory scrubbing is handled by
+ * hardware and can involve L2 cache, dcache as well as the main memory. With
+ * F10, this is extended to L3 cache scrubbing on CPU models sporting that
+ * functionality.
+ *
+ * This causes the "units" for the scrubbing speed to vary from 64 byte blocks
+ * (dram) over to cache lines. This is nasty, so we will use bandwidth in
+ * bytes/sec for the setting.
+ *
+ * Currently, we only do dram scrubbing. If the scrubbing is done in software on
+ * other archs, we might not have access to the caches directly.
+ */
+
+/*
+ * scan the scrub rate mapping table for a close or matching bandwidth value to
+ * issue. If requested is too big, then use last maximum value found.
+ */
+static int amd64_search_set_scrub_rate(struct pci_dev *ctl, u32 new_bw,
+				       u32 min_scrubrate)
+{
+	u32 scrubval;
+	int i;
+
+	/*
+	 * map the configured rate (new_bw) to a value specific to the AMD64
+	 * memory controller and apply to register. Search for the first
+	 * bandwidth entry that is greater or equal than the setting requested
+	 * and program that. If at last entry, turn off DRAM scrubbing.
+	 */
+	for (i = 0; i < ARRAY_SIZE(scrubrates); i++) {
+		/*
+		 * skip scrub rates which aren't recommended
+		 * (see F10 BKDG, F3x58)
+		 */
+		if (scrubrates[i].scrubval < min_scrubrate)
+			continue;
+
+		if (scrubrates[i].bandwidth <= new_bw)
+			break;
+
+		/*
+		 * if no suitable bandwidth found, turn off DRAM scrubbing
+		 * entirely by falling back to the last element in the
+		 * scrubrates array.
+		 */
+	}
+
+	scrubval = scrubrates[i].scrubval;
+	if (scrubval)
+		edac_printk(KERN_DEBUG, EDAC_MC,
+			    "Setting scrub rate bandwidth: %u\n",
+			    scrubrates[i].bandwidth);
+	else
+		edac_printk(KERN_DEBUG, EDAC_MC, "Turning scrubbing off.\n");
+
+	pci_write_bits32(ctl, K8_SCRCTRL, scrubval, 0x001F);
+
+	return 0;
+}
+
+static int amd64_set_scrub_rate(struct mem_ctl_info *mci, u32 *bandwidth)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	u32 min_scrubrate = 0x0;
+
+	switch (boot_cpu_data.x86) {
+	case 0xf:
+		min_scrubrate = K8_MIN_SCRUB_RATE_BITS;
+		break;
+	case 0x10:
+		min_scrubrate = F10_MIN_SCRUB_RATE_BITS;
+		break;
+	case 0x11:
+		min_scrubrate = F11_MIN_SCRUB_RATE_BITS;
+		break;
+
+	default:
+		amd64_printk(KERN_ERR, "Unsupported family!\n");
+		break;
+	}
+	return amd64_search_set_scrub_rate(pvt->misc_f3_ctl, *bandwidth,
+			min_scrubrate);
+}
+
+static int amd64_get_scrub_rate(struct mem_ctl_info *mci, u32 *bw)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	u32 scrubval = 0;
+	int status = -1, i, ret = 0;
+
+	ret = pci_read_config_dword(pvt->misc_f3_ctl, K8_SCRCTRL, &scrubval);
+	if (ret)
+		debugf0("Reading K8_SCRCTRL failed\n");
+
+	scrubval = scrubval & 0x001F;
+
+	edac_printk(KERN_DEBUG, EDAC_MC,
+		    "pci-read, sdram scrub control value: %d \n", scrubval);
+
+	for (i = 0; ARRAY_SIZE(scrubrates); i++) {
+		if (scrubrates[i].scrubval == scrubval) {
+			*bw = scrubrates[i].bandwidth;
+			status = 0;
+			break;
+		}
+	}
+
+	return status;
+}
+
+/* Map from a CSROW entry to the mask entry that operates on it */
+static inline u32 amd64_map_to_dcs_mask(struct amd64_pvt *pvt, int csrow)
+{
+	return csrow >> (pvt->num_dcsm >> 3);
+}
+
+/* return the 'base' address the i'th CS entry of the 'dct' DRAM controller */
+static u32 amd64_get_dct_base(struct amd64_pvt *pvt, int dct, int csrow)
+{
+	if (dct == 0)
+		return pvt->dcsb0[csrow];
+	else
+		return pvt->dcsb1[csrow];
+}
+
+/*
+ * Return the 'mask' address the i'th CS entry. This function is needed because
+ * there number of DCSM registers on Rev E and prior vs Rev F and later is
+ * different.
+ */
+static u32 amd64_get_dct_mask(struct amd64_pvt *pvt, int dct, int csrow)
+{
+	if (dct == 0)
+		return pvt->dcsm0[amd64_map_to_dcs_mask(pvt, csrow)];
+	else
+		return pvt->dcsm1[amd64_map_to_dcs_mask(pvt, csrow)];
+}
+
+
+/*
+ * In *base and *limit, pass back the full 40-bit base and limit physical
+ * addresses for the node given by node_id.  This information is obtained from
+ * DRAM Base (section 3.4.4.1) and DRAM Limit (section 3.4.4.2) registers. The
+ * base and limit addresses are of type SysAddr, as defined at the start of
+ * section 3.4.4 (p. 70).  They are the lowest and highest physical addresses
+ * in the address range they represent.
+ */
+static void amd64_get_base_and_limit(struct amd64_pvt *pvt, int node_id,
+			       u64 *base, u64 *limit)
+{
+	*base = pvt->dram_base[node_id];
+	*limit = pvt->dram_limit[node_id];
+}
+
+/*
+ * Return 1 if the SysAddr given by sys_addr matches the base/limit associated
+ * with node_id
+ */
+static int amd64_base_limit_match(struct amd64_pvt *pvt,
+					u64 sys_addr, int node_id)
+{
+	u64 base, limit, addr;
+
+	amd64_get_base_and_limit(pvt, node_id, &base, &limit);
+
+	/* The K8 treats this as a 40-bit value.  However, bits 63-40 will be
+	 * all ones if the most significant implemented address bit is 1.
+	 * Here we discard bits 63-40.  See section 3.4.2 of AMD publication
+	 * 24592: AMD x86-64 Architecture Programmer's Manual Volume 1
+	 * Application Programming.
+	 */
+	addr = sys_addr & 0x000000ffffffffffull;
+
+	return (addr >= base) && (addr <= limit);
+}
+
+/*
+ * Attempt to map a SysAddr to a node. On success, return a pointer to the
+ * mem_ctl_info structure for the node that the SysAddr maps to.
+ *
+ * On failure, return NULL.
+ */
+static struct mem_ctl_info *find_mc_by_sys_addr(struct mem_ctl_info *mci,
+						u64 sys_addr)
+{
+	struct amd64_pvt *pvt;
+	int node_id;
+	u32 intlv_en, bits;
+
+	/*
+	 * Here we use the DRAM Base (section 3.4.4.1) and DRAM Limit (section
+	 * 3.4.4.2) registers to map the SysAddr to a node ID.
+	 */
+	pvt = mci->pvt_info;
+
+	/*
+	 * The value of this field should be the same for all DRAM Base
+	 * registers.  Therefore we arbitrarily choose to read it from the
+	 * register for node 0.
+	 */
+	intlv_en = pvt->dram_IntlvEn[0];
+
+	if (intlv_en == 0) {
+		for (node_id = 0; ; ) {
+			if (amd64_base_limit_match(pvt, sys_addr, node_id))
+				break;
+
+			if (++node_id >= DRAM_REG_COUNT)
+				goto err_no_match;
+		}
+		goto found;
+	}
+
+	if (unlikely((intlv_en != (0x01 << 8)) &&
+		     (intlv_en != (0x03 << 8)) &&
+		     (intlv_en != (0x07 << 8)))) {
+		amd64_printk(KERN_WARNING, "junk value of 0x%x extracted from "
+			     "IntlvEn field of DRAM Base Register for node 0: "
+			     "This probably indicates a BIOS bug.\n", intlv_en);
+		return NULL;
+	}
+
+	bits = (((u32) sys_addr) >> 12) & intlv_en;
+
+	for (node_id = 0; ; ) {
+		if ((pvt->dram_limit[node_id] & intlv_en) == bits)
+			break;	/* intlv_sel field matches */
+
+		if (++node_id >= DRAM_REG_COUNT)
+			goto err_no_match;
+	}
+
+	/* sanity test for sys_addr */
+	if (unlikely(!amd64_base_limit_match(pvt, sys_addr, node_id))) {
+		amd64_printk(KERN_WARNING,
+			  "%s(): sys_addr 0x%lx falls outside base/limit "
+			  "address range for node %d with node interleaving "
+			  "enabled.\n", __func__, (unsigned long)sys_addr,
+			  node_id);
+		return NULL;
+	}
+
+found:
+	return edac_mc_find(node_id);
+
+err_no_match:
+	debugf2("sys_addr 0x%lx doesn't match any node\n",
+		(unsigned long)sys_addr);
+
+	return NULL;
+}
+
+/*
+ * Extract the DRAM CS base address from selected csrow register.
+ */
+static u64 base_from_dct_base(struct amd64_pvt *pvt, int csrow)
+{
+	return ((u64) (amd64_get_dct_base(pvt, 0, csrow) & pvt->dcsb_base)) <<
+				pvt->dcs_shift;
+}
+
+/*
+ * Extract the mask from the dcsb0[csrow] entry in a CPU revision-specific way.
+ */
+static u64 mask_from_dct_mask(struct amd64_pvt *pvt, int csrow)
+{
+	u64 dcsm_bits, other_bits;
+	u64 mask;
+
+	/* Extract bits from DRAM CS Mask. */
+	dcsm_bits = amd64_get_dct_mask(pvt, 0, csrow) & pvt->dcsm_mask;
+
+	other_bits = pvt->dcsm_mask;
+	other_bits = ~(other_bits << pvt->dcs_shift);
+
+	/*
+	 * The extracted bits from DCSM belong in the spaces represented by
+	 * the cleared bits in other_bits.
+	 */
+	mask = (dcsm_bits << pvt->dcs_shift) | other_bits;
+
+	return mask;
+}
+
+/*
+ * @input_addr is an InputAddr associated with the node given by mci. Return the
+ * csrow that input_addr maps to, or -1 on failure (no csrow claims input_addr).
+ */
+static int input_addr_to_csrow(struct mem_ctl_info *mci, u64 input_addr)
+{
+	struct amd64_pvt *pvt;
+	int csrow;
+	u64 base, mask;
+
+	pvt = mci->pvt_info;
+
+	/*
+	 * Here we use the DRAM CS Base and DRAM CS Mask registers. For each CS
+	 * base/mask register pair, test the condition shown near the start of
+	 * section 3.5.4 (p. 84, BKDG #26094, K8, revA-E).
+	 */
+	for (csrow = 0; csrow < CHIPSELECT_COUNT; csrow++) {
+
+		/* This DRAM chip select is disabled on this node */
+		if ((pvt->dcsb0[csrow] & K8_DCSB_CS_ENABLE) == 0)
+			continue;
+
+		base = base_from_dct_base(pvt, csrow);
+		mask = ~mask_from_dct_mask(pvt, csrow);
+
+		if ((input_addr & mask) == (base & mask)) {
+			debugf2("InputAddr 0x%lx matches csrow %d (node %d)\n",
+				(unsigned long)input_addr, csrow,
+				pvt->mc_node_id);
+
+			return csrow;
+		}
+	}
+
+	debugf2("no matching csrow for InputAddr 0x%lx (MC node %d)\n",
+		(unsigned long)input_addr, pvt->mc_node_id);
+
+	return -1;
+}
+
+/*
+ * Return the base value defined by the DRAM Base register for the node
+ * represented by mci.  This function returns the full 40-bit value despite the
+ * fact that the register only stores bits 39-24 of the value. See section
+ * 3.4.4.1 (BKDG #26094, K8, revA-E)
+ */
+static inline u64 get_dram_base(struct mem_ctl_info *mci)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+
+	return pvt->dram_base[pvt->mc_node_id];
+}
+
+/*
+ * Obtain info from the DRAM Hole Address Register (section 3.4.8, pub #26094)
+ * for the node represented by mci. Info is passed back in *hole_base,
+ * *hole_offset, and *hole_size.  Function returns 0 if info is valid or 1 if
+ * info is invalid. Info may be invalid for either of the following reasons:
+ *
+ * - The revision of the node is not E or greater.  In this case, the DRAM Hole
+ *   Address Register does not exist.
+ *
+ * - The DramHoleValid bit is cleared in the DRAM Hole Address Register,
+ *   indicating that its contents are not valid.
+ *
+ * The values passed back in *hole_base, *hole_offset, and *hole_size are
+ * complete 32-bit values despite the fact that the bitfields in the DHAR
+ * only represent bits 31-24 of the base and offset values.
+ */
+int amd64_get_dram_hole_info(struct mem_ctl_info *mci, u64 *hole_base,
+			     u64 *hole_offset, u64 *hole_size)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	u64 base;
+
+	/* only revE and later have the DRAM Hole Address Register */
+	if (boot_cpu_data.x86 == 0xf && pvt->ext_model < OPTERON_CPU_REV_E) {
+		debugf1("  revision %d for node %d does not support DHAR\n",
+			pvt->ext_model, pvt->mc_node_id);
+		return 1;
+	}
+
+	/* only valid for Fam10h */
+	if (boot_cpu_data.x86 == 0x10 &&
+	    (pvt->dhar & F10_DRAM_MEM_HOIST_VALID) == 0) {
+		debugf1("  Dram Memory Hoisting is DISABLED on this system\n");
+		return 1;
+	}
+
+	if ((pvt->dhar & DHAR_VALID) == 0) {
+		debugf1("  Dram Memory Hoisting is DISABLED on this node %d\n",
+			pvt->mc_node_id);
+		return 1;
+	}
+
+	/* This node has Memory Hoisting */
+
+	/* +------------------+--------------------+--------------------+-----
+	 * | memory           | DRAM hole          | relocated          |
+	 * | [0, (x - 1)]     | [x, 0xffffffff]    | addresses from     |
+	 * |                  |                    | DRAM hole          |
+	 * |                  |                    | [0x100000000,      |
+	 * |                  |                    |  (0x100000000+     |
+	 * |                  |                    |   (0xffffffff-x))] |
+	 * +------------------+--------------------+--------------------+-----
+	 *
+	 * Above is a diagram of physical memory showing the DRAM hole and the
+	 * relocated addresses from the DRAM hole.  As shown, the DRAM hole
+	 * starts at address x (the base address) and extends through address
+	 * 0xffffffff.  The DRAM Hole Address Register (DHAR) relocates the
+	 * addresses in the hole so that they start at 0x100000000.
+	 */
+
+	base = dhar_base(pvt->dhar);
+
+	*hole_base = base;
+	*hole_size = (0x1ull << 32) - base;
+
+	if (boot_cpu_data.x86 > 0xf)
+		*hole_offset = f10_dhar_offset(pvt->dhar);
+	else
+		*hole_offset = k8_dhar_offset(pvt->dhar);
+
+	debugf1("  DHAR info for node %d base 0x%lx offset 0x%lx size 0x%lx\n",
+		pvt->mc_node_id, (unsigned long)*hole_base,
+		(unsigned long)*hole_offset, (unsigned long)*hole_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(amd64_get_dram_hole_info);
+
+/*
+ * Return the DramAddr that the SysAddr given by @sys_addr maps to.  It is
+ * assumed that sys_addr maps to the node given by mci.
+ *
+ * The first part of section 3.4.4 (p. 70) shows how the DRAM Base (section
+ * 3.4.4.1) and DRAM Limit (section 3.4.4.2) registers are used to translate a
+ * SysAddr to a DramAddr. If the DRAM Hole Address Register (DHAR) is enabled,
+ * then it is also involved in translating a SysAddr to a DramAddr. Sections
+ * 3.4.8 and 3.5.8.2 describe the DHAR and how it is used for memory hoisting.
+ * These parts of the documentation are unclear. I interpret them as follows:
+ *
+ * When node n receives a SysAddr, it processes the SysAddr as follows:
+ *
+ * 1. It extracts the DRAMBase and DRAMLimit values from the DRAM Base and DRAM
+ *    Limit registers for node n. If the SysAddr is not within the range
+ *    specified by the base and limit values, then node n ignores the Sysaddr
+ *    (since it does not map to node n). Otherwise continue to step 2 below.
+ *
+ * 2. If the DramHoleValid bit of the DHAR for node n is clear, the DHAR is
+ *    disabled so skip to step 3 below. Otherwise see if the SysAddr is within
+ *    the range of relocated addresses (starting at 0x100000000) from the DRAM
+ *    hole. If not, skip to step 3 below. Else get the value of the
+ *    DramHoleOffset field from the DHAR. To obtain the DramAddr, subtract the
+ *    offset defined by this value from the SysAddr.
+ *
+ * 3. Obtain the base address for node n from the DRAMBase field of the DRAM
+ *    Base register for node n. To obtain the DramAddr, subtract the base
+ *    address from the SysAddr, as shown near the start of section 3.4.4 (p.70).
+ */
+static u64 sys_addr_to_dram_addr(struct mem_ctl_info *mci, u64 sys_addr)
+{
+	u64 dram_base, hole_base, hole_offset, hole_size, dram_addr;
+	int ret = 0;
+
+	dram_base = get_dram_base(mci);
+
+	ret = amd64_get_dram_hole_info(mci, &hole_base, &hole_offset,
+				      &hole_size);
+	if (!ret) {
+		if ((sys_addr >= (1ull << 32)) &&
+		    (sys_addr < ((1ull << 32) + hole_size))) {
+			/* use DHAR to translate SysAddr to DramAddr */
+			dram_addr = sys_addr - hole_offset;
+
+			debugf2("using DHAR to translate SysAddr 0x%lx to "
+				"DramAddr 0x%lx\n",
+				(unsigned long)sys_addr,
+				(unsigned long)dram_addr);
+
+			return dram_addr;
+		}
+	}
+
+	/*
+	 * Translate the SysAddr to a DramAddr as shown near the start of
+	 * section 3.4.4 (p. 70).  Although sys_addr is a 64-bit value, the k8
+	 * only deals with 40-bit values.  Therefore we discard bits 63-40 of
+	 * sys_addr below.  If bit 39 of sys_addr is 1 then the bits we
+	 * discard are all 1s.  Otherwise the bits we discard are all 0s.  See
+	 * section 3.4.2 of AMD publication 24592: AMD x86-64 Architecture
+	 * Programmer's Manual Volume 1 Application Programming.
+	 */
+	dram_addr = (sys_addr & 0xffffffffffull) - dram_base;
+
+	debugf2("using DRAM Base register to translate SysAddr 0x%lx to "
+		"DramAddr 0x%lx\n", (unsigned long)sys_addr,
+		(unsigned long)dram_addr);
+	return dram_addr;
+}
+
+/*
+ * @intlv_en is the value of the IntlvEn field from a DRAM Base register
+ * (section 3.4.4.1).  Return the number of bits from a SysAddr that are used
+ * for node interleaving.
+ */
+static int num_node_interleave_bits(unsigned intlv_en)
+{
+	static const int intlv_shift_table[] = { 0, 1, 0, 2, 0, 0, 0, 3 };
+	int n;
+
+	BUG_ON(intlv_en > 7);
+	n = intlv_shift_table[intlv_en];
+	return n;
+}
+
+/* Translate the DramAddr given by @dram_addr to an InputAddr. */
+static u64 dram_addr_to_input_addr(struct mem_ctl_info *mci, u64 dram_addr)
+{
+	struct amd64_pvt *pvt;
+	int intlv_shift;
+	u64 input_addr;
+
+	pvt = mci->pvt_info;
+
+	/*
+	 * See the start of section 3.4.4 (p. 70, BKDG #26094, K8, revA-E)
+	 * concerning translating a DramAddr to an InputAddr.
+	 */
+	intlv_shift = num_node_interleave_bits(pvt->dram_IntlvEn[0]);
+	input_addr = ((dram_addr >> intlv_shift) & 0xffffff000ull) +
+	    (dram_addr & 0xfff);
+
+	debugf2("  Intlv Shift=%d DramAddr=0x%lx maps to InputAddr=0x%lx\n",
+		intlv_shift, (unsigned long)dram_addr,
+		(unsigned long)input_addr);
+
+	return input_addr;
+}
+
+/*
+ * Translate the SysAddr represented by @sys_addr to an InputAddr.  It is
+ * assumed that @sys_addr maps to the node given by mci.
+ */
+static u64 sys_addr_to_input_addr(struct mem_ctl_info *mci, u64 sys_addr)
+{
+	u64 input_addr;
+
+	input_addr =
+	    dram_addr_to_input_addr(mci, sys_addr_to_dram_addr(mci, sys_addr));
+
+	debugf2("SysAdddr 0x%lx translates to InputAddr 0x%lx\n",
+		(unsigned long)sys_addr, (unsigned long)input_addr);
+
+	return input_addr;
+}
+
+
+/*
+ * @input_addr is an InputAddr associated with the node represented by mci.
+ * Translate @input_addr to a DramAddr and return the result.
+ */
+static u64 input_addr_to_dram_addr(struct mem_ctl_info *mci, u64 input_addr)
+{
+	struct amd64_pvt *pvt;
+	int node_id, intlv_shift;
+	u64 bits, dram_addr;
+	u32 intlv_sel;
+
+	/*
+	 * Near the start of section 3.4.4 (p. 70, BKDG #26094, K8, revA-E)
+	 * shows how to translate a DramAddr to an InputAddr. Here we reverse
+	 * this procedure. When translating from a DramAddr to an InputAddr, the
+	 * bits used for node interleaving are discarded.  Here we recover these
+	 * bits from the IntlvSel field of the DRAM Limit register (section
+	 * 3.4.4.2) for the node that input_addr is associated with.
+	 */
+	pvt = mci->pvt_info;
+	node_id = pvt->mc_node_id;
+	BUG_ON((node_id < 0) || (node_id > 7));
+
+	intlv_shift = num_node_interleave_bits(pvt->dram_IntlvEn[0]);
+
+	if (intlv_shift == 0) {
+		debugf1("    InputAddr 0x%lx translates to DramAddr of "
+			"same value\n",	(unsigned long)input_addr);
+
+		return input_addr;
+	}
+
+	bits = ((input_addr & 0xffffff000ull) << intlv_shift) +
+	    (input_addr & 0xfff);
+
+	intlv_sel = pvt->dram_IntlvSel[node_id] & ((1 << intlv_shift) - 1);
+	dram_addr = bits + (intlv_sel << 12);
+
+	debugf1("InputAddr 0x%lx translates to DramAddr 0x%lx "
+		"(%d node interleave bits)\n", (unsigned long)input_addr,
+		(unsigned long)dram_addr, intlv_shift);
+
+	return dram_addr;
+}
+
+/*
+ * @dram_addr is a DramAddr that maps to the node represented by mci. Convert
+ * @dram_addr to a SysAddr.
+ */
+static u64 dram_addr_to_sys_addr(struct mem_ctl_info *mci, u64 dram_addr)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	u64 hole_base, hole_offset, hole_size, base, limit, sys_addr;
+	int ret = 0;
+
+	ret = amd64_get_dram_hole_info(mci, &hole_base, &hole_offset,
+				      &hole_size);
+	if (!ret) {
+		if ((dram_addr >= hole_base) &&
+		    (dram_addr < (hole_base + hole_size))) {
+			sys_addr = dram_addr + hole_offset;
+
+			debugf1("using DHAR to translate DramAddr 0x%lx to "
+				"SysAddr 0x%lx\n", (unsigned long)dram_addr,
+				(unsigned long)sys_addr);
+
+			return sys_addr;
+		}
+	}
+
+	amd64_get_base_and_limit(pvt, pvt->mc_node_id, &base, &limit);
+	sys_addr = dram_addr + base;
+
+	/*
+	 * The sys_addr we have computed up to this point is a 40-bit value
+	 * because the k8 deals with 40-bit values.  However, the value we are
+	 * supposed to return is a full 64-bit physical address.  The AMD
+	 * x86-64 architecture specifies that the most significant implemented
+	 * address bit through bit 63 of a physical address must be either all
+	 * 0s or all 1s.  Therefore we sign-extend the 40-bit sys_addr to a
+	 * 64-bit value below.  See section 3.4.2 of AMD publication 24592:
+	 * AMD x86-64 Architecture Programmer's Manual Volume 1 Application
+	 * Programming.
+	 */
+	sys_addr |= ~((sys_addr & (1ull << 39)) - 1);
+
+	debugf1("    Node %d, DramAddr 0x%lx to SysAddr 0x%lx\n",
+		pvt->mc_node_id, (unsigned long)dram_addr,
+		(unsigned long)sys_addr);
+
+	return sys_addr;
+}
+
+/*
+ * @input_addr is an InputAddr associated with the node given by mci. Translate
+ * @input_addr to a SysAddr.
+ */
+static inline u64 input_addr_to_sys_addr(struct mem_ctl_info *mci,
+					 u64 input_addr)
+{
+	return dram_addr_to_sys_addr(mci,
+				     input_addr_to_dram_addr(mci, input_addr));
+}
+
+/*
+ * Find the minimum and maximum InputAddr values that map to the given @csrow.
+ * Pass back these values in *input_addr_min and *input_addr_max.
+ */
+static void find_csrow_limits(struct mem_ctl_info *mci, int csrow,
+			      u64 *input_addr_min, u64 *input_addr_max)
+{
+	struct amd64_pvt *pvt;
+	u64 base, mask;
+
+	pvt = mci->pvt_info;
+	BUG_ON((csrow < 0) || (csrow >= CHIPSELECT_COUNT));
+
+	base = base_from_dct_base(pvt, csrow);
+	mask = mask_from_dct_mask(pvt, csrow);
+
+	*input_addr_min = base & ~mask;
+	*input_addr_max = base | mask | pvt->dcs_mask_notused;
+}
+
+/*
+ * Extract error address from MCA NB Address Low (section 3.6.4.5) and MCA NB
+ * Address High (section 3.6.4.6) register values and return the result. Address
+ * is located in the info structure (nbeah and nbeal), the encoding is device
+ * specific.
+ */
+static u64 extract_error_address(struct mem_ctl_info *mci,
+				 struct amd64_error_info_regs *info)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+
+	return pvt->ops->get_error_address(mci, info);
+}
+
+
+/* Map the Error address to a PAGE and PAGE OFFSET. */
+static inline void error_address_to_page_and_offset(u64 error_address,
+						    u32 *page, u32 *offset)
+{
+	*page = (u32) (error_address >> PAGE_SHIFT);
+	*offset = ((u32) error_address) & ~PAGE_MASK;
+}
+
+/*
+ * @sys_addr is an error address (a SysAddr) extracted from the MCA NB Address
+ * Low (section 3.6.4.5) and MCA NB Address High (section 3.6.4.6) registers
+ * of a node that detected an ECC memory error.  mci represents the node that
+ * the error address maps to (possibly different from the node that detected
+ * the error).  Return the number of the csrow that sys_addr maps to, or -1 on
+ * error.
+ */
+static int sys_addr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr)
+{
+	int csrow;
+
+	csrow = input_addr_to_csrow(mci, sys_addr_to_input_addr(mci, sys_addr));
+
+	if (csrow == -1)
+		amd64_mc_printk(mci, KERN_ERR,
+			     "Failed to translate InputAddr to csrow for "
+			     "address 0x%lx\n", (unsigned long)sys_addr);
+	return csrow;
+}
+
+static int get_channel_from_ecc_syndrome(unsigned short syndrome);
+
+static void amd64_cpu_display_info(struct amd64_pvt *pvt)
+{
+	if (boot_cpu_data.x86 == 0x11)
+		edac_printk(KERN_DEBUG, EDAC_MC, "F11h CPU detected\n");
+	else if (boot_cpu_data.x86 == 0x10)
+		edac_printk(KERN_DEBUG, EDAC_MC, "F10h CPU detected\n");
+	else if (boot_cpu_data.x86 == 0xf)
+		edac_printk(KERN_DEBUG, EDAC_MC, "%s detected\n",
+			(pvt->ext_model >= OPTERON_CPU_REV_F) ?
+			"Rev F or later" : "Rev E or earlier");
+	else
+		/* we'll hardly ever ever get here */
+		edac_printk(KERN_ERR, EDAC_MC, "Unknown cpu!\n");
+}
+
+/*
+ * Determine if the DIMMs have ECC enabled. ECC is enabled ONLY if all the DIMMs
+ * are ECC capable.
+ */
+static enum edac_type amd64_determine_edac_cap(struct amd64_pvt *pvt)
+{
+	int bit;
+	enum dev_type edac_cap = EDAC_NONE;
+
+	bit = (boot_cpu_data.x86 > 0xf || pvt->ext_model >= OPTERON_CPU_REV_F)
+		? 19
+		: 17;
+
+	if (pvt->dclr0 >> BIT(bit))
+		edac_cap = EDAC_FLAG_SECDED;
+
+	return edac_cap;
+}
+
+
+static void f10_debug_display_dimm_sizes(int ctrl, struct amd64_pvt *pvt,
+					 int ganged);
+
+/* Display and decode various NB registers for debug purposes. */
+static void amd64_dump_misc_regs(struct amd64_pvt *pvt)
+{
+	int ganged;
+
+	debugf1("  nbcap:0x%8.08x DctDualCap=%s DualNode=%s 8-Node=%s\n",
+		pvt->nbcap,
+		(pvt->nbcap & K8_NBCAP_DCT_DUAL) ? "True" : "False",
+		(pvt->nbcap & K8_NBCAP_DUAL_NODE) ? "True" : "False",
+		(pvt->nbcap & K8_NBCAP_8_NODE) ? "True" : "False");
+	debugf1("    ECC Capable=%s   ChipKill Capable=%s\n",
+		(pvt->nbcap & K8_NBCAP_SECDED) ? "True" : "False",
+		(pvt->nbcap & K8_NBCAP_CHIPKILL) ? "True" : "False");
+	debugf1("  DramCfg0-low=0x%08x DIMM-ECC=%s Parity=%s Width=%s\n",
+		pvt->dclr0,
+		(pvt->dclr0 & BIT(19)) ?  "Enabled" : "Disabled",
+		(pvt->dclr0 & BIT(8)) ?  "Enabled" : "Disabled",
+		(pvt->dclr0 & BIT(11)) ?  "128b" : "64b");
+	debugf1("    DIMM x4 Present: L0=%s L1=%s L2=%s L3=%s  DIMM Type=%s\n",
+		(pvt->dclr0 & BIT(12)) ?  "Y" : "N",
+		(pvt->dclr0 & BIT(13)) ?  "Y" : "N",
+		(pvt->dclr0 & BIT(14)) ?  "Y" : "N",
+		(pvt->dclr0 & BIT(15)) ?  "Y" : "N",
+		(pvt->dclr0 & BIT(16)) ?  "UN-Buffered" : "Buffered");
+
+
+	debugf1("  online-spare: 0x%8.08x\n", pvt->online_spare);
+
+	if (boot_cpu_data.x86 == 0xf) {
+		debugf1("  dhar: 0x%8.08x Base=0x%08x Offset=0x%08x\n",
+			pvt->dhar, dhar_base(pvt->dhar),
+			k8_dhar_offset(pvt->dhar));
+		debugf1("      DramHoleValid=%s\n",
+			(pvt->dhar & DHAR_VALID) ?  "True" : "False");
+
+		debugf1("  dbam-dkt: 0x%8.08x\n", pvt->dbam0);
+
+		/* everything below this point is Fam10h and above */
+		return;
+
+	} else {
+		debugf1("  dhar: 0x%8.08x Base=0x%08x Offset=0x%08x\n",
+			pvt->dhar, dhar_base(pvt->dhar),
+			f10_dhar_offset(pvt->dhar));
+		debugf1("    DramMemHoistValid=%s DramHoleValid=%s\n",
+			(pvt->dhar & F10_DRAM_MEM_HOIST_VALID) ?
+			"True" : "False",
+			(pvt->dhar & DHAR_VALID) ?
+			"True" : "False");
+	}
+
+	/* Only if NOT ganged does dcl1 have valid info */
+	if (!dct_ganging_enabled(pvt)) {
+		debugf1("  DramCfg1-low=0x%08x DIMM-ECC=%s Parity=%s "
+			"Width=%s\n", pvt->dclr1,
+			(pvt->dclr1 & BIT(19)) ?  "Enabled" : "Disabled",
+			(pvt->dclr1 & BIT(8)) ?  "Enabled" : "Disabled",
+			(pvt->dclr1 & BIT(11)) ?  "128b" : "64b");
+		debugf1("    DIMM x4 Present: L0=%s L1=%s L2=%s L3=%s  "
+			"DIMM Type=%s\n",
+			(pvt->dclr1 & BIT(12)) ?  "Y" : "N",
+			(pvt->dclr1 & BIT(13)) ?  "Y" : "N",
+			(pvt->dclr1 & BIT(14)) ?  "Y" : "N",
+			(pvt->dclr1 & BIT(15)) ?  "Y" : "N",
+			(pvt->dclr1 & BIT(16)) ?  "UN-Buffered" : "Buffered");
+	}
+
+	/*
+	 * Determine if ganged and then dump memory sizes for first controller,
+	 * and if NOT ganged dump info for 2nd controller.
+	 */
+	ganged = dct_ganging_enabled(pvt);
+
+	f10_debug_display_dimm_sizes(0, pvt, ganged);
+
+	if (!ganged)
+		f10_debug_display_dimm_sizes(1, pvt, ganged);
+}
+
+/* Read in both of DBAM registers */
+static void amd64_read_dbam_reg(struct amd64_pvt *pvt)
+{
+	int err = 0;
+	unsigned int reg;
+
+	reg = DBAM0;
+	err = pci_read_config_dword(pvt->dram_f2_ctl, reg, &pvt->dbam0);
+	if (err)
+		goto err_reg;
+
+	if (boot_cpu_data.x86 >= 0x10) {
+		reg = DBAM1;
+		err = pci_read_config_dword(pvt->dram_f2_ctl, reg, &pvt->dbam1);
+
+		if (err)
+			goto err_reg;
+	}
+
+err_reg:
+	debugf0("Error reading F2x%03x.\n", reg);
+}
+
+/*
+ * NOTE: CPU Revision Dependent code: Rev E and Rev F
+ *
+ * Set the DCSB and DCSM mask values depending on the CPU revision value. Also
+ * set the shift factor for the DCSB and DCSM values.
+ *
+ * ->dcs_mask_notused, RevE:
+ *
+ * To find the max InputAddr for the csrow, start with the base address and set
+ * all bits that are "don't care" bits in the test at the start of section
+ * 3.5.4 (p. 84).
+ *
+ * The "don't care" bits are all set bits in the mask and all bits in the gaps
+ * between bit ranges [35:25] and [19:13]. The value REV_E_DCS_NOTUSED_BITS
+ * represents bits [24:20] and [12:0], which are all bits in the above-mentioned
+ * gaps.
+ *
+ * ->dcs_mask_notused, RevF and later:
+ *
+ * To find the max InputAddr for the csrow, start with the base address and set
+ * all bits that are "don't care" bits in the test at the start of NPT section
+ * 4.5.4 (p. 87).
+ *
+ * The "don't care" bits are all set bits in the mask and all bits in the gaps
+ * between bit ranges [36:27] and [21:13].
+ *
+ * The value REV_F_F1Xh_DCS_NOTUSED_BITS represents bits [26:22] and [12:0],
+ * which are all bits in the above-mentioned gaps.
+ */
+static void amd64_set_dct_base_and_mask(struct amd64_pvt *pvt)
+{
+	if (pvt->ext_model >= OPTERON_CPU_REV_F) {
+		pvt->dcsb_base		= REV_F_F1Xh_DCSB_BASE_BITS;
+		pvt->dcsm_mask		= REV_F_F1Xh_DCSM_MASK_BITS;
+		pvt->dcs_mask_notused	= REV_F_F1Xh_DCS_NOTUSED_BITS;
+		pvt->dcs_shift		= REV_F_F1Xh_DCS_SHIFT;
+
+		switch (boot_cpu_data.x86) {
+		case 0xf:
+			pvt->num_dcsm = REV_F_DCSM_COUNT;
+			break;
+
+		case 0x10:
+			pvt->num_dcsm = F10_DCSM_COUNT;
+			break;
+
+		case 0x11:
+			pvt->num_dcsm = F11_DCSM_COUNT;
+			break;
+
+		default:
+			amd64_printk(KERN_ERR, "Unsupported family!\n");
+			break;
+		}
+	} else {
+		pvt->dcsb_base		= REV_E_DCSB_BASE_BITS;
+		pvt->dcsm_mask		= REV_E_DCSM_MASK_BITS;
+		pvt->dcs_mask_notused	= REV_E_DCS_NOTUSED_BITS;
+		pvt->dcs_shift		= REV_E_DCS_SHIFT;
+		pvt->num_dcsm		= REV_E_DCSM_COUNT;
+	}
+}
+
+/*
+ * Function 2 Offset F10_DCSB0; read in the DCS Base and DCS Mask hw registers
+ */
+static void amd64_read_dct_base_mask(struct amd64_pvt *pvt)
+{
+	int cs, reg, err = 0;
+
+	amd64_set_dct_base_and_mask(pvt);
+
+	for (cs = 0; cs < CHIPSELECT_COUNT; cs++) {
+		reg = K8_DCSB0 + (cs * 4);
+		err = pci_read_config_dword(pvt->dram_f2_ctl, reg,
+						&pvt->dcsb0[cs]);
+		if (unlikely(err))
+			debugf0("Reading K8_DCSB0[%d] failed\n", cs);
+		else
+			debugf0("  DCSB0[%d]=0x%08x reg: F2x%x\n",
+				cs, pvt->dcsb0[cs], reg);
+
+		/* If DCT are NOT ganged, then read in DCT1's base */
+		if (boot_cpu_data.x86 >= 0x10 && !dct_ganging_enabled(pvt)) {
+			reg = F10_DCSB1 + (cs * 4);
+			err = pci_read_config_dword(pvt->dram_f2_ctl, reg,
+							&pvt->dcsb1[cs]);
+			if (unlikely(err))
+				debugf0("Reading F10_DCSB1[%d] failed\n", cs);
+			else
+				debugf0("  DCSB1[%d]=0x%08x reg: F2x%x\n",
+					cs, pvt->dcsb1[cs], reg);
+		} else {
+			pvt->dcsb1[cs] = 0;
+		}
+	}
+
+	for (cs = 0; cs < pvt->num_dcsm; cs++) {
+		reg = K8_DCSB0 + (cs * 4);
+		err = pci_read_config_dword(pvt->dram_f2_ctl, reg,
+					&pvt->dcsm0[cs]);
+		if (unlikely(err))
+			debugf0("Reading K8_DCSM0 failed\n");
+		else
+			debugf0("    DCSM0[%d]=0x%08x reg: F2x%x\n",
+				cs, pvt->dcsm0[cs], reg);
+
+		/* If DCT are NOT ganged, then read in DCT1's mask */
+		if (boot_cpu_data.x86 >= 0x10 && !dct_ganging_enabled(pvt)) {
+			reg = F10_DCSM1 + (cs * 4);
+			err = pci_read_config_dword(pvt->dram_f2_ctl, reg,
+					&pvt->dcsm1[cs]);
+			if (unlikely(err))
+				debugf0("Reading F10_DCSM1[%d] failed\n", cs);
+			else
+				debugf0("    DCSM1[%d]=0x%08x reg: F2x%x\n",
+					cs, pvt->dcsm1[cs], reg);
+		} else
+			pvt->dcsm1[cs] = 0;
+	}
+}
+
+static enum mem_type amd64_determine_memory_type(struct amd64_pvt *pvt)
+{
+	enum mem_type type;
+
+	if (boot_cpu_data.x86 >= 0x10 || pvt->ext_model >= OPTERON_CPU_REV_F) {
+		/* Rev F and later */
+		type = (pvt->dclr0 & BIT(16)) ? MEM_DDR2 : MEM_RDDR2;
+	} else {
+		/* Rev E and earlier */
+		type = (pvt->dclr0 & BIT(18)) ? MEM_DDR : MEM_RDDR;
+	}
+
+	debugf1("  Memory type is: %s\n",
+		(type == MEM_DDR2) ? "MEM_DDR2" :
+		(type == MEM_RDDR2) ? "MEM_RDDR2" :
+		(type == MEM_DDR) ? "MEM_DDR" : "MEM_RDDR");
+
+	return type;
+}
+
+/*
+ * Read the DRAM Configuration Low register. It differs between CG, D & E revs
+ * and the later RevF memory controllers (DDR vs DDR2)
+ *
+ * Return:
+ *      number of memory channels in operation
+ * Pass back:
+ *      contents of the DCL0_LOW register
+ */
+static int k8_early_channel_count(struct amd64_pvt *pvt)
+{
+	int flag, err = 0;
+
+	err = pci_read_config_dword(pvt->dram_f2_ctl, F10_DCLR_0, &pvt->dclr0);
+	if (err)
+		return err;
+
+	if ((boot_cpu_data.x86_model >> 4) >= OPTERON_CPU_REV_F) {
+		/* RevF (NPT) and later */
+		flag = pvt->dclr0 & F10_WIDTH_128;
+	} else {
+		/* RevE and earlier */
+		flag = pvt->dclr0 & REVE_WIDTH_128;
+	}
+
+	/* not used */
+	pvt->dclr1 = 0;
+
+	return (flag) ? 2 : 1;
+}
+
+/* extract the ERROR ADDRESS for the K8 CPUs */
+static u64 k8_get_error_address(struct mem_ctl_info *mci,
+				struct amd64_error_info_regs *info)
+{
+	return (((u64) (info->nbeah & 0xff)) << 32) +
+			(info->nbeal & ~0x03);
+}
+
+/*
+ * Read the Base and Limit registers for K8 based Memory controllers; extract
+ * fields from the 'raw' reg into separate data fields
+ *
+ * Isolates: BASE, LIMIT, IntlvEn, IntlvSel, RW_EN
+ */
+static void k8_read_dram_base_limit(struct amd64_pvt *pvt, int dram)
+{
+	u32 low;
+	u32 off = dram << 3;	/* 8 bytes between DRAM entries */
+	int err;
+
+	err = pci_read_config_dword(pvt->addr_f1_ctl,
+				    K8_DRAM_BASE_LOW + off, &low);
+	if (err)
+		debugf0("Reading K8_DRAM_BASE_LOW failed\n");
+
+	/* Extract parts into separate data entries */
+	pvt->dram_base[dram] = ((u64) low & 0xFFFF0000) << 8;
+	pvt->dram_IntlvEn[dram] = (low >> 8) & 0x7;
+	pvt->dram_rw_en[dram] = (low & 0x3);
+
+	err = pci_read_config_dword(pvt->addr_f1_ctl,
+				    K8_DRAM_LIMIT_LOW + off, &low);
+	if (err)
+		debugf0("Reading K8_DRAM_LIMIT_LOW failed\n");
+
+	/*
+	 * Extract parts into separate data entries. Limit is the HIGHEST memory
+	 * location of the region, so lower 24 bits need to be all ones
+	 */
+	pvt->dram_limit[dram] = (((u64) low & 0xFFFF0000) << 8) | 0x00FFFFFF;
+	pvt->dram_IntlvSel[dram] = (low >> 8) & 0x7;
+	pvt->dram_DstNode[dram] = (low & 0x7);
+}
+
+static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci,
+					struct amd64_error_info_regs *info,
+					u64 SystemAddress)
+{
+	struct mem_ctl_info *src_mci;
+	unsigned short syndrome;
+	int channel, csrow;
+	u32 page, offset;
+
+	/* Extract the syndrome parts and form a 16-bit syndrome */
+	syndrome = EXTRACT_HIGH_SYNDROME(info->nbsl) << 8;
+	syndrome |= EXTRACT_LOW_SYNDROME(info->nbsh);
+
+	/* CHIPKILL enabled */
+	if (info->nbcfg & K8_NBCFG_CHIPKILL) {
+		channel = get_channel_from_ecc_syndrome(syndrome);
+		if (channel < 0) {
+			/*
+			 * Syndrome didn't map, so we don't know which of the
+			 * 2 DIMMs is in error. So we need to ID 'both' of them
+			 * as suspect.
+			 */
+			amd64_mc_printk(mci, KERN_WARNING,
+				       "unknown syndrome 0x%x - possible error "
+				       "reporting race\n", syndrome);
+			edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR);
+			return;
+		}
+	} else {
+		/*
+		 * non-chipkill ecc mode
+		 *
+		 * The k8 documentation is unclear about how to determine the
+		 * channel number when using non-chipkill memory.  This method
+		 * was obtained from email communication with someone at AMD.
+		 * (Wish the email was placed in this comment - norsk)
+		 */
+		channel = ((SystemAddress & BIT(3)) != 0);
+	}
+
+	/*
+	 * Find out which node the error address belongs to. This may be
+	 * different from the node that detected the error.
+	 */
+	src_mci = find_mc_by_sys_addr(mci, SystemAddress);
+	if (src_mci) {
+		amd64_mc_printk(mci, KERN_ERR,
+			     "failed to map error address 0x%lx to a node\n",
+			     (unsigned long)SystemAddress);
+		edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR);
+		return;
+	}
+
+	/* Now map the SystemAddress to a CSROW */
+	csrow = sys_addr_to_csrow(src_mci, SystemAddress);
+	if (csrow < 0) {
+		edac_mc_handle_ce_no_info(src_mci, EDAC_MOD_STR);
+	} else {
+		error_address_to_page_and_offset(SystemAddress, &page, &offset);
+
+		edac_mc_handle_ce(src_mci, page, offset, syndrome, csrow,
+				  channel, EDAC_MOD_STR);
+	}
+}
+
+/*
+ * determrine the number of PAGES in for this DIMM's size based on its DRAM
+ * Address Mapping.
+ *
+ * First step is to calc the number of bits to shift a value of 1 left to
+ * indicate show many pages. Start with the DBAM value as the starting bits,
+ * then proceed to adjust those shift bits, based on CPU rev and the table.
+ * See BKDG on the DBAM
+ */
+static int k8_dbam_map_to_pages(struct amd64_pvt *pvt, int dram_map)
+{
+	int nr_pages;
+
+	if (pvt->ext_model >= OPTERON_CPU_REV_F) {
+		nr_pages = 1 << (revf_quad_ddr2_shift[dram_map] - PAGE_SHIFT);
+	} else {
+		/*
+		 * RevE and less section; this line is tricky. It collapses the
+		 * table used by RevD and later to one that matches revisions CG
+		 * and earlier.
+		 */
+		dram_map -= (pvt->ext_model >= OPTERON_CPU_REV_D) ?
+				(dram_map > 8 ? 4 : (dram_map > 5 ?
+				3 : (dram_map > 2 ? 1 : 0))) : 0;
+
+		/* 25 shift is 32MiB minimum DIMM size in RevE and prior */
+		nr_pages = 1 << (dram_map + 25 - PAGE_SHIFT);
+	}
+
+	return nr_pages;
+}
+
+/*
+ * Get the number of DCT channels in use.
+ *
+ * Return:
+ *	number of Memory Channels in operation
+ * Pass back:
+ *	contents of the DCL0_LOW register
+ */
+static int f10_early_channel_count(struct amd64_pvt *pvt)
+{
+	int err = 0, channels = 0;
+	u32 dbam;
+
+	err = pci_read_config_dword(pvt->dram_f2_ctl, F10_DCLR_0, &pvt->dclr0);
+	if (err)
+		goto err_reg;
+
+	err = pci_read_config_dword(pvt->dram_f2_ctl, F10_DCLR_1, &pvt->dclr1);
+	if (err)
+		goto err_reg;
+
+	/* If we are in 128 bit mode, then we are using 2 channels */
+	if (pvt->dclr0 & F10_WIDTH_128) {
+		debugf0("Data WIDTH is 128 bits - 2 channels\n");
+		channels = 2;
+		return channels;
+	}
+
+	/*
+	 * Need to check if in UN-ganged mode: In such, there are 2 channels,
+	 * but they are NOT in 128 bit mode and thus the above 'dcl0' status bit
+	 * will be OFF.
+	 *
+	 * Need to check DCT0[0] and DCT1[0] to see if only one of them has
+	 * their CSEnable bit on. If so, then SINGLE DIMM case.
+	 */
+	debugf0("Data WIDTH is NOT 128 bits - need more decoding\n");
+
+	/*
+	 * Check DRAM Bank Address Mapping values for each DIMM to see if there
+	 * is more than just one DIMM present in unganged mode. Need to check
+	 * both controllers since DIMMs can be placed in either one.
+	 */
+	channels = 0;
+	err = pci_read_config_dword(pvt->dram_f2_ctl, DBAM0, &dbam);
+	if (err)
+		goto err_reg;
+
+	if (DBAM_DIMM(0, dbam) > 0)
+		channels++;
+	if (DBAM_DIMM(1, dbam) > 0)
+		channels++;
+	if (DBAM_DIMM(2, dbam) > 0)
+		channels++;
+	if (DBAM_DIMM(3, dbam) > 0)
+		channels++;
+
+	/* If more than 2 DIMMs are present, then we have 2 channels */
+	if (channels > 2)
+		channels = 2;
+	else if (channels == 0) {
+		/* No DIMMs on DCT0, so look at DCT1 */
+		err = pci_read_config_dword(pvt->dram_f2_ctl, DBAM1, &dbam);
+		if (err)
+			goto err_reg;
+
+		if (DBAM_DIMM(0, dbam) > 0)
+			channels++;
+		if (DBAM_DIMM(1, dbam) > 0)
+			channels++;
+		if (DBAM_DIMM(2, dbam) > 0)
+			channels++;
+		if (DBAM_DIMM(3, dbam) > 0)
+			channels++;
+
+		if (channels > 2)
+			channels = 2;
+	}
+
+	/* If we found ALL 0 values, then assume just ONE DIMM-ONE Channel */
+	if (channels == 0)
+		channels = 1;
+
+	debugf0("DIMM count= %d\n", channels);
+
+	return channels;
+
+err_reg:
+	return -1;
+
+}
+
+static int f10_dbam_map_to_pages(struct amd64_pvt *pvt, int dram_map)
+{
+	return 1 << (revf_quad_ddr2_shift[dram_map] - PAGE_SHIFT);
+}
+
+/* Enable extended configuration access via 0xCF8 feature */
+static void amd64_setup(struct amd64_pvt *pvt)
+{
+	u32 reg;
+
+	pci_read_config_dword(pvt->misc_f3_ctl, F10_NB_CFG_HIGH, &reg);
+
+	pvt->flags.cf8_extcfg = !!(reg & F10_NB_CFG_LOW_ENABLE_EXT_CFG);
+	reg |= F10_NB_CFG_LOW_ENABLE_EXT_CFG;
+	pci_write_config_dword(pvt->misc_f3_ctl, F10_NB_CFG_HIGH, reg);
+}
+
+/* Restore the extended configuration access via 0xCF8 feature */
+static void amd64_teardown(struct amd64_pvt *pvt)
+{
+	u32 reg;
+
+	pci_read_config_dword(pvt->misc_f3_ctl, F10_NB_CFG_HIGH, &reg);
+
+	reg &= ~F10_NB_CFG_LOW_ENABLE_EXT_CFG;
+	if (pvt->flags.cf8_extcfg)
+		reg |= F10_NB_CFG_LOW_ENABLE_EXT_CFG;
+	pci_write_config_dword(pvt->misc_f3_ctl, F10_NB_CFG_HIGH, reg);
+}
+
+static u64 f10_get_error_address(struct mem_ctl_info *mci,
+			struct amd64_error_info_regs *info)
+{
+	return (((u64) (info->nbeah & 0xffff)) << 32) +
+			(info->nbeal & ~0x01);
+}
+
+/*
+ * Read the Base and Limit registers for F10 based Memory controllers. Extract
+ * fields from the 'raw' reg into separate data fields.
+ *
+ * Isolates: BASE, LIMIT, IntlvEn, IntlvSel, RW_EN.
+ */
+static void f10_read_dram_base_limit(struct amd64_pvt *pvt, int dram)
+{
+	u32 high_offset, low_offset, high_base, low_base, high_limit, low_limit;
+
+	low_offset = K8_DRAM_BASE_LOW + (dram << 3);
+	high_offset = F10_DRAM_BASE_HIGH + (dram << 3);
+
+	/* read the 'raw' DRAM BASE Address register */
+	pci_read_config_dword(pvt->addr_f1_ctl, low_offset, &low_base);
+
+	/* Read from the ECS data register */
+	pci_read_config_dword(pvt->addr_f1_ctl, high_offset, &high_base);
+
+	/* Extract parts into separate data entries */
+	pvt->dram_rw_en[dram] = (low_base & 0x3);
+
+	if (pvt->dram_rw_en[dram] == 0)
+		return;
+
+	pvt->dram_IntlvEn[dram] = (low_base >> 8) & 0x7;
+
+	pvt->dram_base[dram] = (((((u64) high_base & 0x000000FF) << 32) |
+				((u64) low_base & 0xFFFF0000))) << 8;
+
+	low_offset = K8_DRAM_LIMIT_LOW + (dram << 3);
+	high_offset = F10_DRAM_LIMIT_HIGH + (dram << 3);
+
+	/* read the 'raw' LIMIT registers */
+	pci_read_config_dword(pvt->addr_f1_ctl, low_offset, &low_limit);
+
+	/* Read from the ECS data register for the HIGH portion */
+	pci_read_config_dword(pvt->addr_f1_ctl, high_offset, &high_limit);
+
+	debugf0("  HW Regs: BASE=0x%08x-%08x      LIMIT=  0x%08x-%08x\n",
+		high_base, low_base, high_limit, low_limit);
+
+	pvt->dram_DstNode[dram] = (low_limit & 0x7);
+	pvt->dram_IntlvSel[dram] = (low_limit >> 8) & 0x7;
+
+	/*
+	 * Extract address values and form a LIMIT address. Limit is the HIGHEST
+	 * memory location of the region, so low 24 bits need to be all ones.
+	 */
+	low_limit |= 0x0000FFFF;
+	pvt->dram_limit[dram] =
+		((((u64) high_limit << 32) + (u64) low_limit) << 8) | (0xFF);
+}
+
+static void f10_read_dram_ctl_register(struct amd64_pvt *pvt)
+{
+	int err = 0;
+
+	err = pci_read_config_dword(pvt->dram_f2_ctl, F10_DCTL_SEL_LOW,
+				    &pvt->dram_ctl_select_low);
+	if (err) {
+		debugf0("Reading F10_DCTL_SEL_LOW failed\n");
+	} else {
+		debugf0("DRAM_DCTL_SEL_LOW=0x%x  DctSelBaseAddr=0x%x\n",
+			pvt->dram_ctl_select_low, dct_sel_baseaddr(pvt));
+
+		debugf0("  DRAM DCTs are=%s DRAM Is=%s DRAM-Ctl-"
+				"sel-hi-range=%s\n",
+			(dct_ganging_enabled(pvt) ? "GANGED" : "NOT GANGED"),
+			(dct_dram_enabled(pvt) ? "Enabled"   : "Disabled"),
+			(dct_high_range_enabled(pvt) ? "Enabled" : "Disabled"));
+
+		debugf0("  DctDatIntLv=%s MemCleared=%s DctSelIntLvAddr=0x%x\n",
+			(dct_data_intlv_enabled(pvt) ? "Enabled" : "Disabled"),
+			(dct_memory_cleared(pvt) ? "True " : "False "),
+			dct_sel_interleave_addr(pvt));
+	}
+
+	err = pci_read_config_dword(pvt->dram_f2_ctl, F10_DCTL_SEL_HIGH,
+				    &pvt->dram_ctl_select_high);
+	if (err)
+		debugf0("Reading F10_DCTL_SEL_HIGH failed\n");
+}
+
+/*
+ * determine channel based on the interleaving mode: F10h BKDG, 2.8.9 Memory
+ * Interleaving Modes.
+ */
+static u32 f10_determine_channel(struct amd64_pvt *pvt, u64 sys_addr,
+				int hi_range_sel, u32 intlv_en)
+{
+	u32 cs, temp, dct_sel_high = (pvt->dram_ctl_select_low >> 1) & 1;
+
+	if (dct_ganging_enabled(pvt))
+		cs = 0;
+	else if (hi_range_sel)
+		cs = dct_sel_high;
+	else if (dct_interleave_enabled(pvt)) {
+		/*
+		 * see F2x110[DctSelIntLvAddr] - channel interleave mode
+		 */
+		if (dct_sel_interleave_addr(pvt) == 0)
+			cs = sys_addr >> 6 & 1;
+		else if ((dct_sel_interleave_addr(pvt) >> 1) & 1) {
+			temp = hweight_long((u32) ((sys_addr >> 16) & 0x1F)) % 2;
+
+			if (dct_sel_interleave_addr(pvt) & 1)
+				cs = (sys_addr >> 9 & 1) ^ temp;
+			else
+				cs = (sys_addr >> 6 & 1) ^ temp;
+		} else if (intlv_en & 4)
+			cs = sys_addr >> 15 & 1;
+		else if (intlv_en & 2)
+			cs = sys_addr >> 14 & 1;
+		else if (intlv_en & 1)
+			cs = sys_addr >> 13 & 1;
+		else
+			cs = sys_addr >> 12 & 1;
+	} else if (dct_high_range_enabled(pvt) && !dct_ganging_enabled(pvt))
+		cs = ~dct_sel_high & 1;
+	else
+		cs = 0;
+
+	return cs;
+}
+
+static inline u32 f10_map_intlv_en_to_shift(u32 intlv_en)
+{
+	if (intlv_en == 1)
+		return 1;
+	else if (intlv_en == 3)
+		return 2;
+	else if (intlv_en == 7)
+		return 3;
+
+	return 0;
+}
+
+/* See F10h BKDG, 2.8.10.2 DctSelBaseOffset Programming */
+static inline u64 f10_get_base_addr_offset(u64 sys_addr, int hi_range_sel,
+						 u32 dct_sel_base_addr,
+						 u64 dct_sel_base_off,
+						 u32 hole_valid, u32 hole_off,
+						 u64 dram_base)
+{
+	u64 chan_off;
+
+	if (hi_range_sel) {
+		if (!(dct_sel_base_addr & 0xFFFFF800) &&
+		   hole_valid && (sys_addr >= 0x100000000ULL))
+			chan_off = hole_off << 16;
+		else
+			chan_off = dct_sel_base_off;
+	} else {
+		if (hole_valid && (sys_addr >= 0x100000000ULL))
+			chan_off = hole_off << 16;
+		else
+			chan_off = dram_base & 0xFFFFF8000000ULL;
+	}
+
+	return (sys_addr & 0x0000FFFFFFFFFFC0ULL) -
+			(chan_off & 0x0000FFFFFF800000ULL);
+}
+
+/* Hack for the time being - Can we get this from BIOS?? */
+#define	CH0SPARE_RANK	0
+#define	CH1SPARE_RANK	1
+
+/*
+ * checks if the csrow passed in is marked as SPARED, if so returns the new
+ * spare row
+ */
+static inline int f10_process_possible_spare(int csrow,
+				u32 cs, struct amd64_pvt *pvt)
+{
+	u32 swap_done;
+	u32 bad_dram_cs;
+
+	/* Depending on channel, isolate respective SPARING info */
+	if (cs) {
+		swap_done = F10_ONLINE_SPARE_SWAPDONE1(pvt->online_spare);
+		bad_dram_cs = F10_ONLINE_SPARE_BADDRAM_CS1(pvt->online_spare);
+		if (swap_done && (csrow == bad_dram_cs))
+			csrow = CH1SPARE_RANK;
+	} else {
+		swap_done = F10_ONLINE_SPARE_SWAPDONE0(pvt->online_spare);
+		bad_dram_cs = F10_ONLINE_SPARE_BADDRAM_CS0(pvt->online_spare);
+		if (swap_done && (csrow == bad_dram_cs))
+			csrow = CH0SPARE_RANK;
+	}
+	return csrow;
+}
+
+/*
+ * Iterate over the DRAM DCT "base" and "mask" registers looking for a
+ * SystemAddr match on the specified 'ChannelSelect' and 'NodeID'
+ *
+ * Return:
+ *	-EINVAL:  NOT FOUND
+ *	0..csrow = Chip-Select Row
+ */
+static int f10_lookup_addr_in_dct(u32 in_addr, u32 nid, u32 cs)
+{
+	struct mem_ctl_info *mci;
+	struct amd64_pvt *pvt;
+	u32 cs_base, cs_mask;
+	int cs_found = -EINVAL;
+	int csrow;
+
+	mci = mci_lookup[nid];
+	if (!mci)
+		return cs_found;
+
+	pvt = mci->pvt_info;
+
+	debugf1("InputAddr=0x%x  channelselect=%d\n", in_addr, cs);
+
+	for (csrow = 0; csrow < CHIPSELECT_COUNT; csrow++) {
+
+		cs_base = amd64_get_dct_base(pvt, cs, csrow);
+		if (!(cs_base & K8_DCSB_CS_ENABLE))
+			continue;
+
+		/*
+		 * We have an ENABLED CSROW, Isolate just the MASK bits of the
+		 * target: [28:19] and [13:5], which map to [36:27] and [21:13]
+		 * of the actual address.
+		 */
+		cs_base &= REV_F_F1Xh_DCSB_BASE_BITS;
+
+		/*
+		 * Get the DCT Mask, and ENABLE the reserved bits: [18:16] and
+		 * [4:0] to become ON. Then mask off bits [28:0] ([36:8])
+		 */
+		cs_mask = amd64_get_dct_mask(pvt, cs, csrow);
+
+		debugf1("    CSROW=%d CSBase=0x%x RAW CSMask=0x%x\n",
+				csrow, cs_base, cs_mask);
+
+		cs_mask = (cs_mask | 0x0007C01F) & 0x1FFFFFFF;
+
+		debugf1("              Final CSMask=0x%x\n", cs_mask);
+		debugf1("    (InputAddr & ~CSMask)=0x%x "
+				"(CSBase & ~CSMask)=0x%x\n",
+				(in_addr & ~cs_mask), (cs_base & ~cs_mask));
+
+		if ((in_addr & ~cs_mask) == (cs_base & ~cs_mask)) {
+			cs_found = f10_process_possible_spare(csrow, cs, pvt);
+
+			debugf1(" MATCH csrow=%d\n", cs_found);
+			break;
+		}
+	}
+	return cs_found;
+}
+
+/* For a given @dram_range, check if @sys_addr falls within it. */
+static int f10_match_to_this_node(struct amd64_pvt *pvt, int dram_range,
+				  u64 sys_addr, int *nid, int *chan_sel)
+{
+	int node_id, cs_found = -EINVAL, high_range = 0;
+	u32 intlv_en, intlv_sel, intlv_shift, hole_off;
+	u32 hole_valid, tmp, dct_sel_base, channel;
+	u64 dram_base, chan_addr, dct_sel_base_off;
+
+	dram_base = pvt->dram_base[dram_range];
+	intlv_en = pvt->dram_IntlvEn[dram_range];
+
+	node_id = pvt->dram_DstNode[dram_range];
+	intlv_sel = pvt->dram_IntlvSel[dram_range];
+
+	debugf1("(dram=%d) Base=0x%llx SystemAddr= 0x%llx Limit=0x%llx\n",
+		dram_range, dram_base, sys_addr, pvt->dram_limit[dram_range]);
+
+	/*
+	 * This assumes that one node's DHAR is the same as all the other
+	 * nodes' DHAR.
+	 */
+	hole_off = (pvt->dhar & 0x0000FF80);
+	hole_valid = (pvt->dhar & 0x1);
+	dct_sel_base_off = (pvt->dram_ctl_select_high & 0xFFFFFC00) << 16;
+
+	debugf1("   HoleOffset=0x%x  HoleValid=0x%x IntlvSel=0x%x\n",
+			hole_off, hole_valid, intlv_sel);
+
+	if (intlv_en ||
+	    (intlv_sel != ((sys_addr >> 12) & intlv_en)))
+		return -EINVAL;
+
+	dct_sel_base = dct_sel_baseaddr(pvt);
+
+	/*
+	 * check whether addresses >= DctSelBaseAddr[47:27] are to be used to
+	 * select between DCT0 and DCT1.
+	 */
+	if (dct_high_range_enabled(pvt) &&
+	   !dct_ganging_enabled(pvt) &&
+	   ((sys_addr >> 27) >= (dct_sel_base >> 11)))
+		high_range = 1;
+
+	channel = f10_determine_channel(pvt, sys_addr, high_range, intlv_en);
+
+	chan_addr = f10_get_base_addr_offset(sys_addr, high_range, dct_sel_base,
+					     dct_sel_base_off, hole_valid,
+					     hole_off, dram_base);
+
+	intlv_shift = f10_map_intlv_en_to_shift(intlv_en);
+
+	/* remove Node ID (in case of memory interleaving) */
+	tmp = chan_addr & 0xFC0;
+
+	chan_addr = ((chan_addr >> intlv_shift) & 0xFFFFFFFFF000ULL) | tmp;
+
+	/* remove channel interleave and hash */
+	if (dct_interleave_enabled(pvt) &&
+	   !dct_high_range_enabled(pvt) &&
+	   !dct_ganging_enabled(pvt)) {
+		if (dct_sel_interleave_addr(pvt) != 1)
+			chan_addr = (chan_addr >> 1) & 0xFFFFFFFFFFFFFFC0ULL;
+		else {
+			tmp = chan_addr & 0xFC0;
+			chan_addr = ((chan_addr & 0xFFFFFFFFFFFFC000ULL) >> 1)
+					| tmp;
+		}
+	}
+
+	debugf1("   (ChannelAddrLong=0x%llx) >> 8 becomes InputAddr=0x%x\n",
+		chan_addr, (u32)(chan_addr >> 8));
+
+	cs_found = f10_lookup_addr_in_dct(chan_addr >> 8, node_id, channel);
+
+	if (cs_found >= 0) {
+		*nid = node_id;
+		*chan_sel = channel;
+	}
+	return cs_found;
+}
+
+static int f10_translate_sysaddr_to_cs(struct amd64_pvt *pvt, u64 sys_addr,
+				       int *node, int *chan_sel)
+{
+	int dram_range, cs_found = -EINVAL;
+	u64 dram_base, dram_limit;
+
+	for (dram_range = 0; dram_range < DRAM_REG_COUNT; dram_range++) {
+
+		if (!pvt->dram_rw_en[dram_range])
+			continue;
+
+		dram_base = pvt->dram_base[dram_range];
+		dram_limit = pvt->dram_limit[dram_range];
+
+		if ((dram_base <= sys_addr) && (sys_addr <= dram_limit)) {
+
+			cs_found = f10_match_to_this_node(pvt, dram_range,
+							  sys_addr, node,
+							  chan_sel);
+			if (cs_found >= 0)
+				break;
+		}
+	}
+	return cs_found;
+}
+
+/*
+ * This the F10h reference code from AMD to map a @sys_addr to NodeID,
+ * CSROW, Channel.
+ *
+ * The @sys_addr is usually an error address received from the hardware.
+ */
+static void f10_map_sysaddr_to_csrow(struct mem_ctl_info *mci,
+				     struct amd64_error_info_regs *info,
+				     u64 sys_addr)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	u32 page, offset;
+	unsigned short syndrome;
+	int nid, csrow, chan = 0;
+
+	csrow = f10_translate_sysaddr_to_cs(pvt, sys_addr, &nid, &chan);
+
+	if (csrow >= 0) {
+		error_address_to_page_and_offset(sys_addr, &page, &offset);
+
+		syndrome = EXTRACT_HIGH_SYNDROME(info->nbsl) << 8;
+		syndrome |= EXTRACT_LOW_SYNDROME(info->nbsh);
+
+		/*
+		 * Is CHIPKILL on? If so, then we can attempt to use the
+		 * syndrome to isolate which channel the error was on.
+		 */
+		if (pvt->nbcfg & K8_NBCFG_CHIPKILL)
+			chan = get_channel_from_ecc_syndrome(syndrome);
+
+		if (chan >= 0) {
+			edac_mc_handle_ce(mci, page, offset, syndrome,
+					csrow, chan, EDAC_MOD_STR);
+		} else {
+			/*
+			 * Channel unknown, report all channels on this
+			 * CSROW as failed.
+			 */
+			for (chan = 0; chan < mci->csrows[csrow].nr_channels;
+								chan++) {
+					edac_mc_handle_ce(mci, page, offset,
+							syndrome,
+							csrow, chan,
+							EDAC_MOD_STR);
+			}
+		}
+
+	} else {
+		edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR);
+	}
+}
+
+/*
+ * Input (@index) is the DBAM DIMM value (1 of 4) used as an index into a shift
+ * table (revf_quad_ddr2_shift) which starts at 128MB DIMM size. Index of 0
+ * indicates an empty DIMM slot, as reported by Hardware on empty slots.
+ *
+ * Normalize to 128MB by subracting 27 bit shift.
+ */
+static int map_dbam_to_csrow_size(int index)
+{
+	int mega_bytes = 0;
+
+	if (index > 0 && index <= DBAM_MAX_VALUE)
+		mega_bytes = ((128 << (revf_quad_ddr2_shift[index]-27)));
+
+	return mega_bytes;
+}
+
+/*
+ * debug routine to display the memory sizes of a DIMM (ganged or not) and it
+ * CSROWs as well
+ */
+static void f10_debug_display_dimm_sizes(int ctrl, struct amd64_pvt *pvt,
+					 int ganged)
+{
+	int dimm, size0, size1;
+	u32 dbam;
+	u32 *dcsb;
+
+	debugf1("  dbam%d: 0x%8.08x  CSROW is %s\n", ctrl,
+			ctrl ? pvt->dbam1 : pvt->dbam0,
+			ganged ? "GANGED - dbam1 not used" : "NON-GANGED");
+
+	dbam = ctrl ? pvt->dbam1 : pvt->dbam0;
+	dcsb = ctrl ? pvt->dcsb1 : pvt->dcsb0;
+
+	/* Dump memory sizes for DIMM and its CSROWs */
+	for (dimm = 0; dimm < 4; dimm++) {
+
+		size0 = 0;
+		if (dcsb[dimm*2] & K8_DCSB_CS_ENABLE)
+			size0 = map_dbam_to_csrow_size(DBAM_DIMM(dimm, dbam));
+
+		size1 = 0;
+		if (dcsb[dimm*2 + 1] & K8_DCSB_CS_ENABLE)
+			size1 = map_dbam_to_csrow_size(DBAM_DIMM(dimm, dbam));
+
+		debugf1("     CTRL-%d DIMM-%d=%5dMB   CSROW-%d=%5dMB "
+				"CSROW-%d=%5dMB\n",
+				ctrl,
+				dimm,
+				size0 + size1,
+				dimm * 2,
+				size0,
+				dimm * 2 + 1,
+				size1);
+	}
+}
+
+/*
+ * Very early hardware probe on pci_probe thread to determine if this module
+ * supports the hardware.
+ *
+ * Return:
+ *      0 for OK
+ *      1 for error
+ */
+static int f10_probe_valid_hardware(struct amd64_pvt *pvt)
+{
+	int ret = 0;
+
+	/*
+	 * If we are on a DDR3 machine, we don't know yet if
+	 * we support that properly at this time
+	 */
+	if ((pvt->dchr0 & F10_DCHR_Ddr3Mode) ||
+	    (pvt->dchr1 & F10_DCHR_Ddr3Mode)) {
+
+		amd64_printk(KERN_WARNING,
+			"%s() This machine is running with DDR3 memory. "
+			"This is not currently supported. "
+			"DCHR0=0x%x DCHR1=0x%x\n",
+			__func__, pvt->dchr0, pvt->dchr1);
+
+		amd64_printk(KERN_WARNING,
+			"   Contact '%s' module MAINTAINER to help add"
+			" support.\n",
+			EDAC_MOD_STR);
+
+		ret = 1;
+
+	}
+	return ret;
+}
+
+/*
+ * There currently are 3 types type of MC devices for AMD Athlon/Opterons
+ * (as per PCI DEVICE_IDs):
+ *
+ * Family K8: That is the Athlon64 and Opteron CPUs. They all have the same PCI
+ * DEVICE ID, even though there is differences between the different Revisions
+ * (CG,D,E,F).
+ *
+ * Family F10h and F11h.
+ *
+ */
+static struct amd64_family_type amd64_family_types[] = {
+	[K8_CPUS] = {
+		.ctl_name = "RevF",
+		.addr_f1_ctl = PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP,
+		.misc_f3_ctl = PCI_DEVICE_ID_AMD_K8_NB_MISC,
+		.ops = {
+			.early_channel_count = k8_early_channel_count,
+			.get_error_address = k8_get_error_address,
+			.read_dram_base_limit = k8_read_dram_base_limit,
+			.map_sysaddr_to_csrow = k8_map_sysaddr_to_csrow,
+			.dbam_map_to_pages = k8_dbam_map_to_pages,
+		}
+	},
+	[F10_CPUS] = {
+		.ctl_name = "Family 10h",
+		.addr_f1_ctl = PCI_DEVICE_ID_AMD_10H_NB_MAP,
+		.misc_f3_ctl = PCI_DEVICE_ID_AMD_10H_NB_MISC,
+		.ops = {
+			.probe_valid_hardware = f10_probe_valid_hardware,
+			.early_channel_count = f10_early_channel_count,
+			.get_error_address = f10_get_error_address,
+			.read_dram_base_limit = f10_read_dram_base_limit,
+			.read_dram_ctl_register = f10_read_dram_ctl_register,
+			.map_sysaddr_to_csrow = f10_map_sysaddr_to_csrow,
+			.dbam_map_to_pages = f10_dbam_map_to_pages,
+		}
+	},
+	[F11_CPUS] = {
+		.ctl_name = "Family 11h",
+		.addr_f1_ctl = PCI_DEVICE_ID_AMD_11H_NB_MAP,
+		.misc_f3_ctl = PCI_DEVICE_ID_AMD_11H_NB_MISC,
+		.ops = {
+			.probe_valid_hardware = f10_probe_valid_hardware,
+			.early_channel_count = f10_early_channel_count,
+			.get_error_address = f10_get_error_address,
+			.read_dram_base_limit = f10_read_dram_base_limit,
+			.read_dram_ctl_register = f10_read_dram_ctl_register,
+			.map_sysaddr_to_csrow = f10_map_sysaddr_to_csrow,
+			.dbam_map_to_pages = f10_dbam_map_to_pages,
+		}
+	},
+};
+
+static struct pci_dev *pci_get_related_function(unsigned int vendor,
+						unsigned int device,
+						struct pci_dev *related)
+{
+	struct pci_dev *dev = NULL;
+
+	dev = pci_get_device(vendor, device, dev);
+	while (dev) {
+		if ((dev->bus->number == related->bus->number) &&
+		    (PCI_SLOT(dev->devfn) == PCI_SLOT(related->devfn)))
+			break;
+		dev = pci_get_device(vendor, device, dev);
+	}
+
+	return dev;
+}
+
+/*
+ * syndrome mapping table for ECC ChipKill devices
+ *
+ * The comment in each row is the token (nibble) number that is in error.
+ * The least significant nibble of the syndrome is the mask for the bits
+ * that are in error (need to be toggled) for the particular nibble.
+ *
+ * Each row contains 16 entries.
+ * The first entry (0th) is the channel number for that row of syndromes.
+ * The remaining 15 entries are the syndromes for the respective Error
+ * bit mask index.
+ *
+ * 1st index entry is 0x0001 mask, indicating that the rightmost bit is the
+ * bit in error.
+ * The 2nd index entry is 0x0010 that the second bit is damaged.
+ * The 3rd index entry is 0x0011 indicating that the rightmost 2 bits
+ * are damaged.
+ * Thus so on until index 15, 0x1111, whose entry has the syndrome
+ * indicating that all 4 bits are damaged.
+ *
+ * A search is performed on this table looking for a given syndrome.
+ *
+ * See the AMD documentation for ECC syndromes. This ECC table is valid
+ * across all the versions of the AMD64 processors.
+ *
+ * A fast lookup is to use the LAST four bits of the 16-bit syndrome as a
+ * COLUMN index, then search all ROWS of that column, looking for a match
+ * with the input syndrome. The ROW value will be the token number.
+ *
+ * The 0'th entry on that row, can be returned as the CHANNEL (0 or 1) of this
+ * error.
+ */
+#define NUMBER_ECC_ROWS  36
+static const unsigned short ecc_chipkill_syndromes[NUMBER_ECC_ROWS][16] = {
+	/* Channel 0 syndromes */
+	{/*0*/  0, 0xe821, 0x7c32, 0x9413, 0xbb44, 0x5365, 0xc776, 0x2f57,
+	   0xdd88, 0x35a9, 0xa1ba, 0x499b, 0x66cc, 0x8eed, 0x1afe, 0xf2df },
+	{/*1*/  0, 0x5d31, 0xa612, 0xfb23, 0x9584, 0xc8b5, 0x3396, 0x6ea7,
+	   0xeac8, 0xb7f9, 0x4cda, 0x11eb, 0x7f4c, 0x227d, 0xd95e, 0x846f },
+	{/*2*/  0, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
+	   0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f },
+	{/*3*/  0, 0x2021, 0x3032, 0x1013, 0x4044, 0x6065, 0x7076, 0x5057,
+	   0x8088, 0xa0a9, 0xb0ba, 0x909b, 0xc0cc, 0xe0ed, 0xf0fe, 0xd0df },
+	{/*4*/  0, 0x5041, 0xa082, 0xf0c3, 0x9054, 0xc015, 0x30d6, 0x6097,
+	   0xe0a8, 0xb0e9, 0x402a, 0x106b, 0x70fc, 0x20bd, 0xd07e, 0x803f },
+	{/*5*/  0, 0xbe21, 0xd732, 0x6913, 0x2144, 0x9f65, 0xf676, 0x4857,
+	   0x3288, 0x8ca9, 0xe5ba, 0x5b9b, 0x13cc, 0xaded, 0xc4fe, 0x7adf },
+	{/*6*/  0, 0x4951, 0x8ea2, 0xc7f3, 0x5394, 0x1ac5, 0xdd36, 0x9467,
+	   0xa1e8, 0xe8b9, 0x2f4a, 0x661b, 0xf27c, 0xbb2d, 0x7cde, 0x358f },
+	{/*7*/  0, 0x74e1, 0x9872, 0xec93, 0xd6b4, 0xa255, 0x4ec6, 0x3a27,
+	   0x6bd8, 0x1f39, 0xf3aa, 0x874b, 0xbd6c, 0xc98d, 0x251e, 0x51ff },
+	{/*8*/  0, 0x15c1, 0x2a42, 0x3f83, 0xcef4, 0xdb35, 0xe4b6, 0xf177,
+	   0x4758, 0x5299, 0x6d1a, 0x78db, 0x89ac, 0x9c6d, 0xa3ee, 0xb62f },
+	{/*9*/  0, 0x3d01, 0x1602, 0x2b03, 0x8504, 0xb805, 0x9306, 0xae07,
+	   0xca08, 0xf709, 0xdc0a, 0xe10b, 0x4f0c, 0x720d, 0x590e, 0x640f },
+	{/*a*/  0, 0x9801, 0xec02, 0x7403, 0x6b04, 0xf305, 0x8706, 0x1f07,
+	   0xbd08, 0x2509, 0x510a, 0xc90b, 0xd60c, 0x4e0d, 0x3a0e, 0xa20f },
+	{/*b*/  0, 0xd131, 0x6212, 0xb323, 0x3884, 0xe9b5, 0x5a96, 0x8ba7,
+	   0x1cc8, 0xcdf9, 0x7eda, 0xafeb, 0x244c, 0xf57d, 0x465e, 0x976f },
+	{/*c*/  0, 0xe1d1, 0x7262, 0x93b3, 0xb834, 0x59e5, 0xca56, 0x2b87,
+	   0xdc18, 0x3dc9, 0xae7a, 0x4fab, 0x542c, 0x85fd, 0x164e, 0xf79f },
+	{/*d*/  0, 0x6051, 0xb0a2, 0xd0f3, 0x1094, 0x70c5, 0xa036, 0xc067,
+	   0x20e8, 0x40b9, 0x904a, 0x601b, 0x307c, 0x502d, 0x80de, 0xe08f },
+	{/*e*/  0, 0xa4c1, 0xf842, 0x5c83, 0xe6f4, 0x4235, 0x1eb6, 0xba77,
+	   0x7b58, 0xdf99, 0x831a, 0x27db, 0x9dac, 0x396d, 0x65ee, 0xc12f },
+	{/*f*/  0, 0x11c1, 0x2242, 0x3383, 0xc8f4, 0xd935, 0xeab6, 0xfb77,
+	   0x4c58, 0x5d99, 0x6e1a, 0x7fdb, 0x84ac, 0x956d, 0xa6ee, 0xb72f },
+
+	/* Channel 1 syndromes */
+	{/*10*/ 1, 0x45d1, 0x8a62, 0xcfb3, 0x5e34, 0x1be5, 0xd456, 0x9187,
+	   0xa718, 0xe2c9, 0x2d7a, 0x68ab, 0xf92c, 0xbcfd, 0x734e, 0x369f },
+	{/*11*/ 1, 0x63e1, 0xb172, 0xd293, 0x14b4, 0x7755, 0xa5c6, 0xc627,
+	   0x28d8, 0x4b39, 0x99aa, 0xfa4b, 0x3c6c, 0x5f8d, 0x8d1e, 0xeeff },
+	{/*12*/ 1, 0xb741, 0xd982, 0x6ec3, 0x2254, 0x9515, 0xfbd6, 0x4c97,
+	   0x33a8, 0x84e9, 0xea2a, 0x5d6b, 0x11fc, 0xa6bd, 0xc87e, 0x7f3f },
+	{/*13*/ 1, 0xdd41, 0x6682, 0xbbc3, 0x3554, 0xe815, 0x53d6, 0xce97,
+	   0x1aa8, 0xc7e9, 0x7c2a, 0xa1fb, 0x2ffc, 0xf2bd, 0x497e, 0x943f },
+	{/*14*/ 1, 0x2bd1, 0x3d62, 0x16b3, 0x4f34, 0x64e5, 0x7256, 0x5987,
+	   0x8518, 0xaec9, 0xb87a, 0x93ab, 0xca2c, 0xe1fd, 0xf74e, 0xdc9f },
+	{/*15*/ 1, 0x83c1, 0xc142, 0x4283, 0xa4f4, 0x2735, 0x65b6, 0xe677,
+	   0xf858, 0x7b99, 0x391a, 0xbadb, 0x5cac, 0xdf6d, 0x9dee, 0x1e2f },
+	{/*16*/ 1, 0x8fd1, 0xc562, 0x4ab3, 0xa934, 0x26e5, 0x6c56, 0xe387,
+	   0xfe18, 0x71c9, 0x3b7a, 0xb4ab, 0x572c, 0xd8fd, 0x924e, 0x1d9f },
+	{/*17*/ 1, 0x4791, 0x89e2, 0xce73, 0x5264, 0x15f5, 0xdb86, 0x9c17,
+	   0xa3b8, 0xe429, 0x2a5a, 0x6dcb, 0xf1dc, 0xb64d, 0x783e, 0x3faf },
+	{/*18*/ 1, 0x5781, 0xa9c2, 0xfe43, 0x92a4, 0xc525, 0x3b66, 0x6ce7,
+	   0xe3f8, 0xb479, 0x4a3a, 0x1dbb, 0x715c, 0x26dd, 0xd89e, 0x8f1f },
+	{/*19*/ 1, 0xbf41, 0xd582, 0x6ac3, 0x2954, 0x9615, 0xfcd6, 0x4397,
+	   0x3ea8, 0x81e9, 0xeb2a, 0x546b, 0x17fc, 0xa8bd, 0xc27e, 0x7d3f },
+	{/*1a*/ 1, 0x9891, 0xe1e2, 0x7273, 0x6464, 0xf7f5, 0x8586, 0x1617,
+	   0xb8b8, 0x2b29, 0x595a, 0xcacb, 0xdcdc, 0x4f4d, 0x3d3e, 0xaeaf },
+	{/*1b*/ 1, 0xcce1, 0x4472, 0x8893, 0xfdb4, 0x3f55, 0xb9c6, 0x7527,
+	   0x56d8, 0x9a39, 0x12aa, 0xde4b, 0xab6c, 0x678d, 0xef1e, 0x23ff },
+	{/*1c*/ 1, 0xa761, 0xf9b2, 0x5ed3, 0xe214, 0x4575, 0x1ba6, 0xbcc7,
+	   0x7328, 0xd449, 0x8a9a, 0x2dfb, 0x913c, 0x365d, 0x688e, 0xcfef },
+	{/*1d*/ 1, 0xff61, 0x55b2, 0xaad3, 0x7914, 0x8675, 0x2ca6, 0xd3c7,
+	   0x9e28, 0x6149, 0xcb9a, 0x34fb, 0xe73c, 0x185d, 0xb28e, 0x4def },
+	{/*1e*/ 1, 0x5451, 0xa8a2, 0xfcf3, 0x9694, 0xc2c5, 0x3e36, 0x6a67,
+	   0xebe8, 0xbfb9, 0x434a, 0x171b, 0x7d7c, 0x292d, 0xd5de, 0x818f },
+	{/*1f*/ 1, 0x6fc1, 0xb542, 0xda83, 0x19f4, 0x7635, 0xacb6, 0xc377,
+	   0x2e58, 0x4199, 0x9b1a, 0xf4db, 0x37ac, 0x586d, 0x82ee, 0xed2f },
+
+	/* ECC bits are also in the set of tokens and they too can go bad
+	 * first 2 cover channel 0, while the second 2 cover channel 1
+	 */
+	{/*20*/ 0, 0xbe01, 0xd702, 0x6903, 0x2104, 0x9f05, 0xf606, 0x4807,
+	   0x3208, 0x8c09, 0xe50a, 0x5b0b, 0x130c, 0xad0d, 0xc40e, 0x7a0f },
+	{/*21*/ 0, 0x4101, 0x8202, 0xc303, 0x5804, 0x1905, 0xda06, 0x9b07,
+	   0xac08, 0xed09, 0x2e0a, 0x6f0b, 0x640c, 0xb50d, 0x760e, 0x370f },
+	{/*22*/ 1, 0xc441, 0x4882, 0x8cc3, 0xf654, 0x3215, 0xbed6, 0x7a97,
+	   0x5ba8, 0x9fe9, 0x132a, 0xd76b, 0xadfc, 0x69bd, 0xe57e, 0x213f },
+	{/*23*/ 1, 0x7621, 0x9b32, 0xed13, 0xda44, 0xac65, 0x4176, 0x3757,
+	   0x6f88, 0x19a9, 0xf4ba, 0x829b, 0xb5cc, 0xc3ed, 0x2efe, 0x58df }
+};
+
+/*
+ * Given the syndrome argument, scan each of the channel tables for a syndrome
+ * match. Depending on which table it is found, return the channel number.
+ */
+static int get_channel_from_ecc_syndrome(unsigned short syndrome)
+{
+	int row;
+	int column;
+
+	/* Determine column to scan */
+	column = syndrome & 0xF;
+
+	/* Scan all rows, looking for syndrome, or end of table */
+	for (row = 0; row < NUMBER_ECC_ROWS; row++) {
+		if (ecc_chipkill_syndromes[row][column] == syndrome)
+			return ecc_chipkill_syndromes[row][0];
+	}
+
+	debugf0("syndrome(%x) not found\n", syndrome);
+	return -1;
+}
+
+/*
+ * Check for valid error in the NB Status High register. If so, proceed to read
+ * NB Status Low, NB Address Low and NB Address High registers and store data
+ * into error structure.
+ *
+ * Returns:
+ *	- 1: if hardware regs contains valid error info
+ *	- 0: if no valid error is indicated
+ */
+static int amd64_get_error_info_regs(struct mem_ctl_info *mci,
+				     struct amd64_error_info_regs *regs)
+{
+	struct amd64_pvt *pvt;
+	struct pci_dev *misc_f3_ctl;
+	int err = 0;
+
+	pvt = mci->pvt_info;
+	misc_f3_ctl = pvt->misc_f3_ctl;
+
+	err = pci_read_config_dword(misc_f3_ctl, K8_NBSH, &regs->nbsh);
+	if (err)
+		goto err_reg;
+
+	if (!(regs->nbsh & K8_NBSH_VALID_BIT))
+		return 0;
+
+	/* valid error, read remaining error information registers */
+	err = pci_read_config_dword(misc_f3_ctl, K8_NBSL, &regs->nbsl);
+	if (err)
+		goto err_reg;
+
+	err = pci_read_config_dword(misc_f3_ctl, K8_NBEAL, &regs->nbeal);
+	if (err)
+		goto err_reg;
+
+	err = pci_read_config_dword(misc_f3_ctl, K8_NBEAH, &regs->nbeah);
+	if (err)
+		goto err_reg;
+
+	err = pci_read_config_dword(misc_f3_ctl, K8_NBCFG, &regs->nbcfg);
+	if (err)
+		goto err_reg;
+
+	return 1;
+
+err_reg:
+	debugf0("Reading error info register failed\n");
+	return 0;
+}
+
+/*
+ * This function is called to retrieve the error data from hardware and store it
+ * in the info structure.
+ *
+ * Returns:
+ *	- 1: if a valid error is found
+ *	- 0: if no error is found
+ */
+static int amd64_get_error_info(struct mem_ctl_info *mci,
+				struct amd64_error_info_regs *info)
+{
+	struct amd64_pvt *pvt;
+	struct amd64_error_info_regs regs;
+
+	pvt = mci->pvt_info;
+
+	if (!amd64_get_error_info_regs(mci, info))
+		return 0;
+
+	/*
+	 * Here's the problem with the K8's EDAC reporting: There are four
+	 * registers which report pieces of error information. They are shared
+	 * between CEs and UEs. Furthermore, contrary to what is stated in the
+	 * BKDG, the overflow bit is never used! Every error always updates the
+	 * reporting registers.
+	 *
+	 * Can you see the race condition? All four error reporting registers
+	 * must be read before a new error updates them! There is no way to read
+	 * all four registers atomically. The best than can be done is to detect
+	 * that a race has occured and then report the error without any kind of
+	 * precision.
+	 *
+	 * What is still positive is that errors are still reported and thus
+	 * problems can still be detected - just not localized because the
+	 * syndrome and address are spread out across registers.
+	 *
+	 * Grrrrr!!!!!  Here's hoping that AMD fixes this in some future K8 rev.
+	 * UEs and CEs should have separate register sets with proper overflow
+	 * bits that are used! At very least the problem can be fixed by
+	 * honoring the ErrValid bit in 'nbsh' and not updating registers - just
+	 * set the overflow bit - unless the current error is CE and the new
+	 * error is UE which would be the only situation for overwriting the
+	 * current values.
+	 */
+
+	regs = *info;
+
+	/* Use info from the second read - most current */
+	if (unlikely(!amd64_get_error_info_regs(mci, info)))
+		return 0;
+
+	/* clear the error bits in hardware */
+	pci_write_bits32(pvt->misc_f3_ctl, K8_NBSH, 0, K8_NBSH_VALID_BIT);
+
+	/* Check for the possible race condition */
+	if ((regs.nbsh != info->nbsh) ||
+	     (regs.nbsl != info->nbsl) ||
+	     (regs.nbeah != info->nbeah) ||
+	     (regs.nbeal != info->nbeal)) {
+		amd64_mc_printk(mci, KERN_WARNING,
+				"hardware STATUS read access race condition "
+				"detected!\n");
+		return 0;
+	}
+	return 1;
+}
+
+static inline void amd64_decode_gart_tlb_error(struct mem_ctl_info *mci,
+					 struct amd64_error_info_regs *info)
+{
+	u32 err_code;
+	u32 ec_tt;		/* error code transaction type (2b) */
+	u32 ec_ll;		/* error code cache level (2b) */
+
+	err_code = EXTRACT_ERROR_CODE(info->nbsl);
+	ec_ll = EXTRACT_LL_CODE(err_code);
+	ec_tt = EXTRACT_TT_CODE(err_code);
+
+	amd64_mc_printk(mci, KERN_ERR,
+		     "GART TLB event: transaction type(%s), "
+		     "cache level(%s)\n", tt_msgs[ec_tt], ll_msgs[ec_ll]);
+}
+
+static inline void amd64_decode_mem_cache_error(struct mem_ctl_info *mci,
+				      struct amd64_error_info_regs *info)
+{
+	u32 err_code;
+	u32 ec_rrrr;		/* error code memory transaction (4b) */
+	u32 ec_tt;		/* error code transaction type (2b) */
+	u32 ec_ll;		/* error code cache level (2b) */
+
+	err_code = EXTRACT_ERROR_CODE(info->nbsl);
+	ec_ll = EXTRACT_LL_CODE(err_code);
+	ec_tt = EXTRACT_TT_CODE(err_code);
+	ec_rrrr = EXTRACT_RRRR_CODE(err_code);
+
+	amd64_mc_printk(mci, KERN_ERR,
+		     "cache hierarchy error: memory transaction type(%s), "
+		     "transaction type(%s), cache level(%s)\n",
+		     rrrr_msgs[ec_rrrr], tt_msgs[ec_tt], ll_msgs[ec_ll]);
+}
+
+
+/*
+ * Handle any Correctable Errors (CEs) that have occurred. Check for valid ERROR
+ * ADDRESS and process.
+ */
+static void amd64_handle_ce(struct mem_ctl_info *mci,
+			    struct amd64_error_info_regs *info)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	u64 SystemAddress;
+
+	/* Ensure that the Error Address is VALID */
+	if ((info->nbsh & K8_NBSH_VALID_ERROR_ADDR) == 0) {
+		amd64_mc_printk(mci, KERN_ERR,
+			"HW has no ERROR_ADDRESS available\n");
+		edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR);
+		return;
+	}
+
+	SystemAddress = extract_error_address(mci, info);
+
+	amd64_mc_printk(mci, KERN_ERR,
+		"CE ERROR_ADDRESS= 0x%llx\n", SystemAddress);
+
+	pvt->ops->map_sysaddr_to_csrow(mci, info, SystemAddress);
+}
+
+/* Handle any Un-correctable Errors (UEs) */
+static void amd64_handle_ue(struct mem_ctl_info *mci,
+			    struct amd64_error_info_regs *info)
+{
+	int csrow;
+	u64 SystemAddress;
+	u32 page, offset;
+	struct mem_ctl_info *log_mci, *src_mci = NULL;
+
+	log_mci = mci;
+
+	if ((info->nbsh & K8_NBSH_VALID_ERROR_ADDR) == 0) {
+		amd64_mc_printk(mci, KERN_CRIT,
+			"HW has no ERROR_ADDRESS available\n");
+		edac_mc_handle_ue_no_info(log_mci, EDAC_MOD_STR);
+		return;
+	}
+
+	SystemAddress = extract_error_address(mci, info);
+
+	/*
+	 * Find out which node the error address belongs to. This may be
+	 * different from the node that detected the error.
+	 */
+	src_mci = find_mc_by_sys_addr(mci, SystemAddress);
+	if (!src_mci) {
+		amd64_mc_printk(mci, KERN_CRIT,
+			"ERROR ADDRESS (0x%lx) value NOT mapped to a MC\n",
+			(unsigned long)SystemAddress);
+		edac_mc_handle_ue_no_info(log_mci, EDAC_MOD_STR);
+		return;
+	}
+
+	log_mci = src_mci;
+
+	csrow = sys_addr_to_csrow(log_mci, SystemAddress);
+	if (csrow < 0) {
+		amd64_mc_printk(mci, KERN_CRIT,
+			"ERROR_ADDRESS (0x%lx) value NOT mapped to 'csrow'\n",
+			(unsigned long)SystemAddress);
+		edac_mc_handle_ue_no_info(log_mci, EDAC_MOD_STR);
+	} else {
+		error_address_to_page_and_offset(SystemAddress, &page, &offset);
+		edac_mc_handle_ue(log_mci, page, offset, csrow, EDAC_MOD_STR);
+	}
+}
+
+static void amd64_decode_bus_error(struct mem_ctl_info *mci,
+				   struct amd64_error_info_regs *info)
+{
+	u32 err_code, ext_ec;
+	u32 ec_pp;		/* error code participating processor (2p) */
+	u32 ec_to;		/* error code timed out (1b) */
+	u32 ec_rrrr;		/* error code memory transaction (4b) */
+	u32 ec_ii;		/* error code memory or I/O (2b) */
+	u32 ec_ll;		/* error code cache level (2b) */
+
+	ext_ec = EXTRACT_EXT_ERROR_CODE(info->nbsl);
+	err_code = EXTRACT_ERROR_CODE(info->nbsl);
+
+	ec_ll = EXTRACT_LL_CODE(err_code);
+	ec_ii = EXTRACT_II_CODE(err_code);
+	ec_rrrr = EXTRACT_RRRR_CODE(err_code);
+	ec_to = EXTRACT_TO_CODE(err_code);
+	ec_pp = EXTRACT_PP_CODE(err_code);
+
+	amd64_mc_printk(mci, KERN_ERR,
+		"BUS ERROR:\n"
+		"  time-out(%s) mem or i/o(%s)\n"
+		"  participating processor(%s)\n"
+		"  memory transaction type(%s)\n"
+		"  cache level(%s) Error Found by: %s\n",
+		to_msgs[ec_to],
+		ii_msgs[ec_ii],
+		pp_msgs[ec_pp],
+		rrrr_msgs[ec_rrrr],
+		ll_msgs[ec_ll],
+		(info->nbsh & K8_NBSH_ERR_SCRUBER) ?
+			"Scrubber" : "Normal Operation");
+
+	/* If this was an 'observed' error, early out */
+	if (ec_pp == K8_NBSL_PP_OBS)
+		return;		/* We aren't the node involved */
+
+	/* Parse out the extended error code for ECC events */
+	switch (ext_ec) {
+	/* F10 changed to one Extended ECC error code */
+	case F10_NBSL_EXT_ERR_RES:		/* Reserved field */
+	case F10_NBSL_EXT_ERR_ECC:		/* F10 ECC ext err code */
+		break;
+
+	default:
+		amd64_mc_printk(mci, KERN_ERR, "NOT ECC: no special error "
+					       "handling for this error\n");
+		return;
+	}
+
+	if (info->nbsh & K8_NBSH_CECC)
+		amd64_handle_ce(mci, info);
+	else if (info->nbsh & K8_NBSH_UECC)
+		amd64_handle_ue(mci, info);
+
+	/*
+	 * If main error is CE then overflow must be CE.  If main error is UE
+	 * then overflow is unknown.  We'll call the overflow a CE - if
+	 * panic_on_ue is set then we're already panic'ed and won't arrive
+	 * here. Else, then apparently someone doesn't think that UE's are
+	 * catastrophic.
+	 */
+	if (info->nbsh & K8_NBSH_OVERFLOW)
+		edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR
+					  "Error Overflow set");
+}
+
+int amd64_process_error_info(struct mem_ctl_info *mci,
+			     struct amd64_error_info_regs *info,
+			     int handle_errors)
+{
+	struct amd64_pvt *pvt;
+	struct amd64_error_info_regs *regs;
+	u32 err_code, ext_ec;
+	int gart_tlb_error = 0;
+
+	pvt = mci->pvt_info;
+
+	/* If caller doesn't want us to process the error, return */
+	if (!handle_errors)
+		return 1;
+
+	regs = info;
+
+	debugf1("NorthBridge ERROR: mci(0x%p)\n", mci);
+	debugf1("  MC node(%d) Error-Address(0x%.8x-%.8x)\n",
+		pvt->mc_node_id, regs->nbeah, regs->nbeal);
+	debugf1("  nbsh(0x%.8x) nbsl(0x%.8x)\n",
+		regs->nbsh, regs->nbsl);
+	debugf1("  Valid Error=%s Overflow=%s\n",
+		(regs->nbsh & K8_NBSH_VALID_BIT) ? "True" : "False",
+		(regs->nbsh & K8_NBSH_OVERFLOW) ? "True" : "False");
+	debugf1("  Err Uncorrected=%s MCA Error Reporting=%s\n",
+		(regs->nbsh & K8_NBSH_UNCORRECTED_ERR) ?
+			"True" : "False",
+		(regs->nbsh & K8_NBSH_ERR_ENABLE) ?
+			"True" : "False");
+	debugf1("  MiscErr Valid=%s ErrAddr Valid=%s PCC=%s\n",
+		(regs->nbsh & K8_NBSH_MISC_ERR_VALID) ?
+			"True" : "False",
+		(regs->nbsh & K8_NBSH_VALID_ERROR_ADDR) ?
+			"True" : "False",
+		(regs->nbsh & K8_NBSH_PCC) ?
+			"True" : "False");
+	debugf1("  CECC=%s UECC=%s Found by Scruber=%s\n",
+		(regs->nbsh & K8_NBSH_CECC) ?
+			"True" : "False",
+		(regs->nbsh & K8_NBSH_UECC) ?
+			"True" : "False",
+		(regs->nbsh & K8_NBSH_ERR_SCRUBER) ?
+			"True" : "False");
+	debugf1("  CORE0=%s CORE1=%s CORE2=%s CORE3=%s\n",
+		(regs->nbsh & K8_NBSH_CORE0) ? "True" : "False",
+		(regs->nbsh & K8_NBSH_CORE1) ? "True" : "False",
+		(regs->nbsh & K8_NBSH_CORE2) ? "True" : "False",
+		(regs->nbsh & K8_NBSH_CORE3) ? "True" : "False");
+
+
+	err_code = EXTRACT_ERROR_CODE(regs->nbsl);
+
+	/* Determine which error type:
+	 *	1) GART errors - non-fatal, developmental events
+	 *	2) MEMORY errors
+	 *	3) BUS errors
+	 *	4) Unknown error
+	 */
+	if (TEST_TLB_ERROR(err_code)) {
+		/*
+		 * GART errors are intended to help graphics driver developers
+		 * to detect bad GART PTEs. It is recommended by AMD to disable
+		 * GART table walk error reporting by default[1] (currently
+		 * being disabled in mce_cpu_quirks()) and according to the
+		 * comment in mce_cpu_quirks(), such GART errors can be
+		 * incorrectly triggered. We may see these errors anyway and
+		 * unless requested by the user, they won't be reported.
+		 *
+		 * [1] section 13.10.1 on BIOS and Kernel Developers Guide for
+		 *     AMD NPT family 0Fh processors
+		 */
+		if (report_gart_errors == 0)
+			return 1;
+
+		/*
+		 * Only if GART error reporting is requested should we generate
+		 * any logs.
+		 */
+		gart_tlb_error = 1;
+
+		debugf1("GART TLB error\n");
+		amd64_decode_gart_tlb_error(mci, info);
+	} else if (TEST_MEM_ERROR(err_code)) {
+		debugf1("Memory/Cache error\n");
+		amd64_decode_mem_cache_error(mci, info);
+	} else if (TEST_BUS_ERROR(err_code)) {
+		debugf1("Bus (Link/DRAM) error\n");
+		amd64_decode_bus_error(mci, info);
+	} else {
+		/* shouldn't reach here! */
+		amd64_mc_printk(mci, KERN_WARNING,
+			     "%s(): unknown MCE error 0x%x\n", __func__,
+			     err_code);
+	}
+
+	ext_ec = EXTRACT_EXT_ERROR_CODE(regs->nbsl);
+	amd64_mc_printk(mci, KERN_ERR,
+		"ExtErr=(0x%x) %s\n", ext_ec, ext_msgs[ext_ec]);
+
+	if (((ext_ec >= F10_NBSL_EXT_ERR_CRC &&
+			ext_ec <= F10_NBSL_EXT_ERR_TGT) ||
+			(ext_ec == F10_NBSL_EXT_ERR_RMW)) &&
+			EXTRACT_LDT_LINK(info->nbsh)) {
+
+		amd64_mc_printk(mci, KERN_ERR,
+			"Error on hypertransport link: %s\n",
+			htlink_msgs[
+			EXTRACT_LDT_LINK(info->nbsh)]);
+	}
+
+	/*
+	 * Check the UE bit of the NB status high register, if set generate some
+	 * logs. If NOT a GART error, then process the event as a NO-INFO event.
+	 * If it was a GART error, skip that process.
+	 */
+	if (regs->nbsh & K8_NBSH_UNCORRECTED_ERR) {
+		amd64_mc_printk(mci, KERN_CRIT, "uncorrected error\n");
+		if (!gart_tlb_error)
+			edac_mc_handle_ue_no_info(mci, "UE bit is set\n");
+	}
+
+	if (regs->nbsh & K8_NBSH_PCC)
+		amd64_mc_printk(mci, KERN_CRIT,
+			"PCC (processor context corrupt) set\n");
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(amd64_process_error_info);
+
+/*
+ * The main polling 'check' function, called FROM the edac core to perform the
+ * error checking and if an error is encountered, error processing.
+ */
+static void amd64_check(struct mem_ctl_info *mci)
+{
+	struct amd64_error_info_regs info;
+
+	if (amd64_get_error_info(mci, &info))
+		amd64_process_error_info(mci, &info, 1);
+}
+
+/*
+ * Input:
+ *	1) struct amd64_pvt which contains pvt->dram_f2_ctl pointer
+ *	2) AMD Family index value
+ *
+ * Ouput:
+ *	Upon return of 0, the following filled in:
+ *
+ *		struct pvt->addr_f1_ctl
+ *		struct pvt->misc_f3_ctl
+ *
+ *	Filled in with related device funcitions of 'dram_f2_ctl'
+ *	These devices are "reserved" via the pci_get_device()
+ *
+ *	Upon return of 1 (error status):
+ *
+ *		Nothing reserved
+ */
+static int amd64_reserve_mc_sibling_devices(struct amd64_pvt *pvt, int mc_idx)
+{
+	const struct amd64_family_type *amd64_dev = &amd64_family_types[mc_idx];
+
+	/* Reserve the ADDRESS MAP Device */
+	pvt->addr_f1_ctl = pci_get_related_function(pvt->dram_f2_ctl->vendor,
+						    amd64_dev->addr_f1_ctl,
+						    pvt->dram_f2_ctl);
+
+	if (!pvt->addr_f1_ctl) {
+		amd64_printk(KERN_ERR, "error address map device not found: "
+			     "vendor %x device 0x%x (broken BIOS?)\n",
+			     PCI_VENDOR_ID_AMD, amd64_dev->addr_f1_ctl);
+		return 1;
+	}
+
+	/* Reserve the MISC Device */
+	pvt->misc_f3_ctl = pci_get_related_function(pvt->dram_f2_ctl->vendor,
+						    amd64_dev->misc_f3_ctl,
+						    pvt->dram_f2_ctl);
+
+	if (!pvt->misc_f3_ctl) {
+		pci_dev_put(pvt->addr_f1_ctl);
+		pvt->addr_f1_ctl = NULL;
+
+		amd64_printk(KERN_ERR, "error miscellaneous device not found: "
+			     "vendor %x device 0x%x (broken BIOS?)\n",
+			     PCI_VENDOR_ID_AMD, amd64_dev->misc_f3_ctl);
+		return 1;
+	}
+
+	debugf1("    Addr Map device PCI Bus ID:\t%s\n",
+		pci_name(pvt->addr_f1_ctl));
+	debugf1("    DRAM MEM-CTL PCI Bus ID:\t%s\n",
+		pci_name(pvt->dram_f2_ctl));
+	debugf1("    Misc device PCI Bus ID:\t%s\n",
+		pci_name(pvt->misc_f3_ctl));
+
+	return 0;
+}
+
+static void amd64_free_mc_sibling_devices(struct amd64_pvt *pvt)
+{
+	pci_dev_put(pvt->addr_f1_ctl);
+	pci_dev_put(pvt->misc_f3_ctl);
+}
+
+/*
+ * Retrieve the hardware registers of the memory controller (this includes the
+ * 'Address Map' and 'Misc' device regs)
+ */
+static void amd64_read_mc_registers(struct amd64_pvt *pvt)
+{
+	u64 msr_val;
+	int dram, err = 0;
+
+	/*
+	 * Retrieve TOP_MEM and TOP_MEM2; no masking off of reserved bits since
+	 * those are Read-As-Zero
+	 */
+	rdmsrl(MSR_K8_TOP_MEM1, msr_val);
+	pvt->top_mem = msr_val >> 23;
+	debugf0("  TOP_MEM=0x%08llx\n", pvt->top_mem);
+
+	/* check first whether TOP_MEM2 is enabled */
+	rdmsrl(MSR_K8_SYSCFG, msr_val);
+	if (msr_val & (1U << 21)) {
+		rdmsrl(MSR_K8_TOP_MEM2, msr_val);
+		pvt->top_mem2 = msr_val >> 23;
+		debugf0("  TOP_MEM2=0x%08llx\n", pvt->top_mem2);
+	} else
+		debugf0("  TOP_MEM2 disabled.\n");
+
+	amd64_cpu_display_info(pvt);
+
+	err = pci_read_config_dword(pvt->misc_f3_ctl, K8_NBCAP, &pvt->nbcap);
+	if (err)
+		goto err_reg;
+
+	if (pvt->ops->read_dram_ctl_register)
+		pvt->ops->read_dram_ctl_register(pvt);
+
+	for (dram = 0; dram < DRAM_REG_COUNT; dram++) {
+		/*
+		 * Call CPU specific READ function to get the DRAM Base and
+		 * Limit values from the DCT.
+		 */
+		pvt->ops->read_dram_base_limit(pvt, dram);
+
+		/*
+		 * Only print out debug info on rows with both R and W Enabled.
+		 * Normal processing, compiler should optimize this whole 'if'
+		 * debug output block away.
+		 */
+		if (pvt->dram_rw_en[dram] != 0) {
+			debugf1("  DRAM_BASE[%d]: 0x%8.08x-%8.08x "
+				"DRAM_LIMIT:  0x%8.08x-%8.08x\n",
+				dram,
+				(u32)(pvt->dram_base[dram] >> 32),
+				(u32)(pvt->dram_base[dram] & 0xFFFFFFFF),
+				(u32)(pvt->dram_limit[dram] >> 32),
+				(u32)(pvt->dram_limit[dram] & 0xFFFFFFFF));
+			debugf1("        IntlvEn=%s %s %s "
+				"IntlvSel=%d DstNode=%d\n",
+				pvt->dram_IntlvEn[dram] ?
+					"Enabled" : "Disabled",
+				(pvt->dram_rw_en[dram] & 0x2) ? "W" : "!W",
+				(pvt->dram_rw_en[dram] & 0x1) ? "R" : "!R",
+				pvt->dram_IntlvSel[dram],
+				pvt->dram_DstNode[dram]);
+		}
+	}
+
+	amd64_read_dct_base_mask(pvt);
+
+	err = pci_read_config_dword(pvt->addr_f1_ctl, K8_DHAR, &pvt->dhar);
+	if (err)
+		goto err_reg;
+
+	amd64_read_dbam_reg(pvt);
+
+	err = pci_read_config_dword(pvt->misc_f3_ctl,
+				F10_ONLINE_SPARE, &pvt->online_spare);
+	if (err)
+		goto err_reg;
+
+	err = pci_read_config_dword(pvt->dram_f2_ctl, F10_DCLR_0, &pvt->dclr0);
+	if (err)
+		goto err_reg;
+
+	err = pci_read_config_dword(pvt->dram_f2_ctl, F10_DCHR_0, &pvt->dchr0);
+	if (err)
+		goto err_reg;
+
+	if (!dct_ganging_enabled(pvt)) {
+		err = pci_read_config_dword(pvt->dram_f2_ctl, F10_DCLR_1,
+						&pvt->dclr1);
+		if (err)
+			goto err_reg;
+
+		err = pci_read_config_dword(pvt->dram_f2_ctl, F10_DCHR_1,
+						&pvt->dchr1);
+		if (err)
+			goto err_reg;
+	}
+
+	amd64_dump_misc_regs(pvt);
+
+err_reg:
+	debugf0("Reading an MC register failed\n");
+
+}
+
+/*
+ * NOTE: CPU Revision Dependent code
+ *
+ * Input:
+ *	@csrow_nr ChipSelect Row Number (0..CHIPSELECT_COUNT-1)
+ *	k8 private pointer to -->
+ *			DRAM Bank Address mapping register
+ *			node_id
+ *			DCL register where dual_channel_active is
+ *
+ * The DBAM register consists of 4 sets of 4 bits each definitions:
+ *
+ * Bits:	CSROWs
+ * 0-3		CSROWs 0 and 1
+ * 4-7		CSROWs 2 and 3
+ * 8-11		CSROWs 4 and 5
+ * 12-15	CSROWs 6 and 7
+ *
+ * Values range from: 0 to 15
+ * The meaning of the values depends on CPU revision and dual-channel state,
+ * see relevant BKDG more info.
+ *
+ * The memory controller provides for total of only 8 CSROWs in its current
+ * architecture. Each "pair" of CSROWs normally represents just one DIMM in
+ * single channel or two (2) DIMMs in dual channel mode.
+ *
+ * The following code logic collapses the various tables for CSROW based on CPU
+ * revision.
+ *
+ * Returns:
+ *	The number of PAGE_SIZE pages on the specified CSROW number it
+ *	encompasses
+ *
+ */
+static u32 amd64_csrow_nr_pages(int csrow_nr, struct amd64_pvt *pvt)
+{
+	u32 dram_map, nr_pages;
+
+	/*
+	 * The math on this doesn't look right on the surface because x/2*4 can
+	 * be simplified to x*2 but this expression makes use of the fact that
+	 * it is integral math where 1/2=0. This intermediate value becomes the
+	 * number of bits to shift the DBAM register to extract the proper CSROW
+	 * field.
+	 */
+	dram_map = (pvt->dbam0 >> ((csrow_nr / 2) * 4)) & 0xF;
+
+	nr_pages = pvt->ops->dbam_map_to_pages(pvt, dram_map);
+
+	/*
+	 * If dual channel then double the memory size of single channel.
+	 * Channel count is 1 or 2
+	 */
+	nr_pages <<= (pvt->channel_count - 1);
+
+	debugf0("  (csrow=%d) DBAM map index= %d\n", csrow_nr, dram_map);
+	debugf0("    nr_pages= %u  channel-count = %d\n",
+		nr_pages, pvt->channel_count);
+
+	return nr_pages;
+}
+
+/*
+ * Initialize the array of csrow attribute instances, based on the values
+ * from pci config hardware registers.
+ */
+static int amd64_init_csrows(struct mem_ctl_info *mci)
+{
+	struct csrow_info *csrow;
+	struct amd64_pvt *pvt;
+	u64 input_addr_min, input_addr_max, sys_addr;
+	int i, err = 0, empty = 1;
+
+	pvt = mci->pvt_info;
+
+	err = pci_read_config_dword(pvt->misc_f3_ctl, K8_NBCFG, &pvt->nbcfg);
+	if (err)
+		debugf0("Reading K8_NBCFG failed\n");
+
+	debugf0("NBCFG= 0x%x  CHIPKILL= %s DRAM ECC= %s\n", pvt->nbcfg,
+		(pvt->nbcfg & K8_NBCFG_CHIPKILL) ? "Enabled" : "Disabled",
+		(pvt->nbcfg & K8_NBCFG_ECC_ENABLE) ? "Enabled" : "Disabled"
+		);
+
+	for (i = 0; i < CHIPSELECT_COUNT; i++) {
+		csrow = &mci->csrows[i];
+
+		if ((pvt->dcsb0[i] & K8_DCSB_CS_ENABLE) == 0) {
+			debugf1("----CSROW %d EMPTY for node %d\n", i,
+				pvt->mc_node_id);
+			continue;
+		}
+
+		debugf1("----CSROW %d VALID for MC node %d\n",
+			i, pvt->mc_node_id);
+
+		empty = 0;
+		csrow->nr_pages = amd64_csrow_nr_pages(i, pvt);
+		find_csrow_limits(mci, i, &input_addr_min, &input_addr_max);
+		sys_addr = input_addr_to_sys_addr(mci, input_addr_min);
+		csrow->first_page = (u32) (sys_addr >> PAGE_SHIFT);
+		sys_addr = input_addr_to_sys_addr(mci, input_addr_max);
+		csrow->last_page = (u32) (sys_addr >> PAGE_SHIFT);
+		csrow->page_mask = ~mask_from_dct_mask(pvt, i);
+		/* 8 bytes of resolution */
+
+		csrow->mtype = amd64_determine_memory_type(pvt);
+
+		debugf1("  for MC node %d csrow %d:\n", pvt->mc_node_id, i);
+		debugf1("    input_addr_min: 0x%lx input_addr_max: 0x%lx\n",
+			(unsigned long)input_addr_min,
+			(unsigned long)input_addr_max);
+		debugf1("    sys_addr: 0x%lx  page_mask: 0x%lx\n",
+			(unsigned long)sys_addr, csrow->page_mask);
+		debugf1("    nr_pages: %u  first_page: 0x%lx "
+			"last_page: 0x%lx\n",
+			(unsigned)csrow->nr_pages,
+			csrow->first_page, csrow->last_page);
+
+		/*
+		 * determine whether CHIPKILL or JUST ECC or NO ECC is operating
+		 */
+		if (pvt->nbcfg & K8_NBCFG_ECC_ENABLE)
+			csrow->edac_mode =
+			    (pvt->nbcfg & K8_NBCFG_CHIPKILL) ?
+			    EDAC_S4ECD4ED : EDAC_SECDED;
+		else
+			csrow->edac_mode = EDAC_NONE;
+	}
+
+	return empty;
+}
+
+/*
+ * Only if 'ecc_enable_override' is set AND BIOS had ECC disabled, do "we"
+ * enable it.
+ */
+static void amd64_enable_ecc_error_reporting(struct mem_ctl_info *mci)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	const cpumask_t *cpumask = cpumask_of_node(pvt->mc_node_id);
+	int cpu, idx = 0, err = 0;
+	struct msr msrs[cpumask_weight(cpumask)];
+	u32 value;
+	u32 mask = K8_NBCTL_CECCEn | K8_NBCTL_UECCEn;
+
+	if (!ecc_enable_override)
+		return;
+
+	memset(msrs, 0, sizeof(msrs));
+
+	amd64_printk(KERN_WARNING,
+		"'ecc_enable_override' parameter is active, "
+		"Enabling AMD ECC hardware now: CAUTION\n");
+
+	err = pci_read_config_dword(pvt->misc_f3_ctl, K8_NBCTL, &value);
+	if (err)
+		debugf0("Reading K8_NBCTL failed\n");
+
+	/* turn on UECCn and CECCEn bits */
+	pvt->old_nbctl = value & mask;
+	pvt->nbctl_mcgctl_saved = 1;
+
+	value |= mask;
+	pci_write_config_dword(pvt->misc_f3_ctl, K8_NBCTL, value);
+
+	rdmsr_on_cpus(cpumask, K8_MSR_MCGCTL, msrs);
+
+	for_each_cpu(cpu, cpumask) {
+		if (msrs[idx].l & K8_MSR_MCGCTL_NBE)
+			set_bit(idx, &pvt->old_mcgctl);
+
+		msrs[idx].l |= K8_MSR_MCGCTL_NBE;
+		idx++;
+	}
+	wrmsr_on_cpus(cpumask, K8_MSR_MCGCTL, msrs);
+
+	err = pci_read_config_dword(pvt->misc_f3_ctl, K8_NBCFG, &value);
+	if (err)
+		debugf0("Reading K8_NBCFG failed\n");
+
+	debugf0("NBCFG(1)= 0x%x  CHIPKILL= %s ECC_ENABLE= %s\n", value,
+		(value & K8_NBCFG_CHIPKILL) ? "Enabled" : "Disabled",
+		(value & K8_NBCFG_ECC_ENABLE) ? "Enabled" : "Disabled");
+
+	if (!(value & K8_NBCFG_ECC_ENABLE)) {
+		amd64_printk(KERN_WARNING,
+			"This node reports that DRAM ECC is "
+			"currently Disabled; ENABLING now\n");
+
+		/* Attempt to turn on DRAM ECC Enable */
+		value |= K8_NBCFG_ECC_ENABLE;
+		pci_write_config_dword(pvt->misc_f3_ctl, K8_NBCFG, value);
+
+		err = pci_read_config_dword(pvt->misc_f3_ctl, K8_NBCFG, &value);
+		if (err)
+			debugf0("Reading K8_NBCFG failed\n");
+
+		if (!(value & K8_NBCFG_ECC_ENABLE)) {
+			amd64_printk(KERN_WARNING,
+				"Hardware rejects Enabling DRAM ECC checking\n"
+				"Check memory DIMM configuration\n");
+		} else {
+			amd64_printk(KERN_DEBUG,
+				"Hardware accepted DRAM ECC Enable\n");
+		}
+	}
+	debugf0("NBCFG(2)= 0x%x  CHIPKILL= %s ECC_ENABLE= %s\n", value,
+		(value & K8_NBCFG_CHIPKILL) ? "Enabled" : "Disabled",
+		(value & K8_NBCFG_ECC_ENABLE) ? "Enabled" : "Disabled");
+
+	pvt->ctl_error_info.nbcfg = value;
+}
+
+static void amd64_restore_ecc_error_reporting(struct amd64_pvt *pvt)
+{
+	const cpumask_t *cpumask = cpumask_of_node(pvt->mc_node_id);
+	int cpu, idx = 0, err = 0;
+	struct msr msrs[cpumask_weight(cpumask)];
+	u32 value;
+	u32 mask = K8_NBCTL_CECCEn | K8_NBCTL_UECCEn;
+
+	if (!pvt->nbctl_mcgctl_saved)
+		return;
+
+	memset(msrs, 0, sizeof(msrs));
+
+	err = pci_read_config_dword(pvt->misc_f3_ctl, K8_NBCTL, &value);
+	if (err)
+		debugf0("Reading K8_NBCTL failed\n");
+	value &= ~mask;
+	value |= pvt->old_nbctl;
+
+	/* restore the NB Enable MCGCTL bit */
+	pci_write_config_dword(pvt->misc_f3_ctl, K8_NBCTL, value);
+
+	rdmsr_on_cpus(cpumask, K8_MSR_MCGCTL, msrs);
+
+	for_each_cpu(cpu, cpumask) {
+		msrs[idx].l &= ~K8_MSR_MCGCTL_NBE;
+		msrs[idx].l |=
+			test_bit(idx, &pvt->old_mcgctl) << K8_MSR_MCGCTL_NBE;
+		idx++;
+	}
+
+	wrmsr_on_cpus(cpumask, K8_MSR_MCGCTL, msrs);
+}
+
+static void check_mcg_ctl(void *ret)
+{
+	u64 msr_val = 0;
+	u8 nbe;
+
+	rdmsrl(MSR_IA32_MCG_CTL, msr_val);
+	nbe = msr_val & K8_MSR_MCGCTL_NBE;
+
+	debugf0("core: %u, MCG_CTL: 0x%llx, NB MSR is %s\n",
+		raw_smp_processor_id(), msr_val,
+		(nbe ? "enabled" : "disabled"));
+
+	if (!nbe)
+		*(int *)ret = 0;
+}
+
+/* check MCG_CTL on all the cpus on this node */
+static int amd64_mcg_ctl_enabled_on_cpus(const cpumask_t *mask)
+{
+	int ret = 1;
+	preempt_disable();
+	smp_call_function_many(mask, check_mcg_ctl, &ret, 1);
+	preempt_enable();
+
+	return ret;
+}
+
+/*
+ * EDAC requires that the BIOS have ECC enabled before taking over the
+ * processing of ECC errors. This is because the BIOS can properly initialize
+ * the memory system completely. A command line option allows to force-enable
+ * hardware ECC later in amd64_enable_ecc_error_reporting().
+ */
+static int amd64_check_ecc_enabled(struct amd64_pvt *pvt)
+{
+	u32 value;
+	int err = 0, ret = 0;
+	u8 ecc_enabled = 0;
+
+	err = pci_read_config_dword(pvt->misc_f3_ctl, K8_NBCFG, &value);
+	if (err)
+		debugf0("Reading K8_NBCTL failed\n");
+
+	ecc_enabled = !!(value & K8_NBCFG_ECC_ENABLE);
+
+	ret = amd64_mcg_ctl_enabled_on_cpus(cpumask_of_node(pvt->mc_node_id));
+
+	debugf0("K8_NBCFG=0x%x,  DRAM ECC is %s\n", value,
+			(value & K8_NBCFG_ECC_ENABLE ? "enabled" : "disabled"));
+
+	if (!ecc_enabled || !ret) {
+		if (!ecc_enabled) {
+			amd64_printk(KERN_WARNING, "This node reports that "
+						   "Memory ECC is currently "
+						   "disabled.\n");
+
+			amd64_printk(KERN_WARNING, "bit 0x%lx in register "
+				"F3x%x of the MISC_CONTROL device (%s) "
+				"should be enabled\n", K8_NBCFG_ECC_ENABLE,
+				K8_NBCFG, pci_name(pvt->misc_f3_ctl));
+		}
+		if (!ret) {
+			amd64_printk(KERN_WARNING, "bit 0x%016lx in MSR 0x%08x "
+					"of node %d should be enabled\n",
+					K8_MSR_MCGCTL_NBE, MSR_IA32_MCG_CTL,
+					pvt->mc_node_id);
+		}
+		if (!ecc_enable_override) {
+			amd64_printk(KERN_WARNING, "WARNING: ECC is NOT "
+				"currently enabled by the BIOS. Module "
+				"will NOT be loaded.\n"
+				"    Either Enable ECC in the BIOS, "
+				"or use the 'ecc_enable_override' "
+				"parameter.\n"
+				"    Might be a BIOS bug, if BIOS says "
+				"ECC is enabled\n"
+				"    Use of the override can cause "
+				"unknown side effects.\n");
+			ret = -ENODEV;
+		}
+	} else {
+		amd64_printk(KERN_INFO,
+			"ECC is enabled by BIOS, Proceeding "
+			"with EDAC module initialization\n");
+
+		/* CLEAR the override, since BIOS controlled it */
+		ecc_enable_override = 0;
+	}
+
+	return ret;
+}
+
+struct mcidev_sysfs_attribute sysfs_attrs[ARRAY_SIZE(amd64_dbg_attrs) +
+					  ARRAY_SIZE(amd64_inj_attrs) +
+					  1];
+
+struct mcidev_sysfs_attribute terminator = { .attr = { .name = NULL } };
+
+static void amd64_set_mc_sysfs_attributes(struct mem_ctl_info *mci)
+{
+	unsigned int i = 0, j = 0;
+
+	for (; i < ARRAY_SIZE(amd64_dbg_attrs); i++)
+		sysfs_attrs[i] = amd64_dbg_attrs[i];
+
+	for (j = 0; j < ARRAY_SIZE(amd64_inj_attrs); j++, i++)
+		sysfs_attrs[i] = amd64_inj_attrs[j];
+
+	sysfs_attrs[i] = terminator;
+
+	mci->mc_driver_sysfs_attributes = sysfs_attrs;
+}
+
+static void amd64_setup_mci_misc_attributes(struct mem_ctl_info *mci)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+
+	mci->mtype_cap		= MEM_FLAG_DDR2 | MEM_FLAG_RDDR2;
+	mci->edac_ctl_cap	= EDAC_FLAG_NONE;
+	mci->edac_cap		= EDAC_FLAG_NONE;
+
+	if (pvt->nbcap & K8_NBCAP_SECDED)
+		mci->edac_ctl_cap |= EDAC_FLAG_SECDED;
+
+	if (pvt->nbcap & K8_NBCAP_CHIPKILL)
+		mci->edac_ctl_cap |= EDAC_FLAG_S4ECD4ED;
+
+	mci->edac_cap		= amd64_determine_edac_cap(pvt);
+	mci->mod_name		= EDAC_MOD_STR;
+	mci->mod_ver		= EDAC_AMD64_VERSION;
+	mci->ctl_name		= get_amd_family_name(pvt->mc_type_index);
+	mci->dev_name		= pci_name(pvt->dram_f2_ctl);
+	mci->ctl_page_to_phys	= NULL;
+
+	/* IMPORTANT: Set the polling 'check' function in this module */
+	mci->edac_check		= amd64_check;
+
+	/* memory scrubber interface */
+	mci->set_sdram_scrub_rate = amd64_set_scrub_rate;
+	mci->get_sdram_scrub_rate = amd64_get_scrub_rate;
+}
+
+/*
+ * Init stuff for this DRAM Controller device.
+ *
+ * Due to a hardware feature on Fam10h CPUs, the Enable Extended Configuration
+ * Space feature MUST be enabled on ALL Processors prior to actually reading
+ * from the ECS registers. Since the loading of the module can occur on any
+ * 'core', and cores don't 'see' all the other processors ECS data when the
+ * others are NOT enabled. Our solution is to first enable ECS access in this
+ * routine on all processors, gather some data in a amd64_pvt structure and
+ * later come back in a finish-setup function to perform that final
+ * initialization. See also amd64_init_2nd_stage() for that.
+ */
+static int amd64_probe_one_instance(struct pci_dev *dram_f2_ctl,
+				    int mc_type_index)
+{
+	struct amd64_pvt *pvt = NULL;
+	int err = 0, ret;
+
+	ret = -ENOMEM;
+	pvt = kzalloc(sizeof(struct amd64_pvt), GFP_KERNEL);
+	if (!pvt)
+		goto err_exit;
+
+	pvt->mc_node_id = get_mc_node_id_from_pdev(dram_f2_ctl);
+
+	pvt->dram_f2_ctl	= dram_f2_ctl;
+	pvt->ext_model		= boot_cpu_data.x86_model >> 4;
+	pvt->mc_type_index	= mc_type_index;
+	pvt->ops		= family_ops(mc_type_index);
+	pvt->old_mcgctl		= 0;
+
+	/*
+	 * We have the dram_f2_ctl device as an argument, now go reserve its
+	 * sibling devices from the PCI system.
+	 */
+	ret = -ENODEV;
+	err = amd64_reserve_mc_sibling_devices(pvt, mc_type_index);
+	if (err)
+		goto err_free;
+
+	ret = -EINVAL;
+	err = amd64_check_ecc_enabled(pvt);
+	if (err)
+		goto err_put;
+
+	/*
+	 * Key operation here: setup of HW prior to performing ops on it. Some
+	 * setup is required to access ECS data. After this is performed, the
+	 * 'teardown' function must be called upon error and normal exit paths.
+	 */
+	if (boot_cpu_data.x86 >= 0x10)
+		amd64_setup(pvt);
+
+	/*
+	 * Save the pointer to the private data for use in 2nd initialization
+	 * stage
+	 */
+	pvt_lookup[pvt->mc_node_id] = pvt;
+
+	return 0;
+
+err_put:
+	amd64_free_mc_sibling_devices(pvt);
+
+err_free:
+	kfree(pvt);
+
+err_exit:
+	return ret;
+}
+
+/*
+ * This is the finishing stage of the init code. Needs to be performed after all
+ * MCs' hardware have been prepped for accessing extended config space.
+ */
+static int amd64_init_2nd_stage(struct amd64_pvt *pvt)
+{
+	int node_id = pvt->mc_node_id;
+	struct mem_ctl_info *mci;
+	int ret, err = 0;
+
+	amd64_read_mc_registers(pvt);
+
+	ret = -ENODEV;
+	if (pvt->ops->probe_valid_hardware) {
+		err = pvt->ops->probe_valid_hardware(pvt);
+		if (err)
+			goto err_exit;
+	}
+
+	/*
+	 * We need to determine how many memory channels there are. Then use
+	 * that information for calculating the size of the dynamic instance
+	 * tables in the 'mci' structure
+	 */
+	pvt->channel_count = pvt->ops->early_channel_count(pvt);
+	if (pvt->channel_count < 0)
+		goto err_exit;
+
+	ret = -ENOMEM;
+	mci = edac_mc_alloc(0, CHIPSELECT_COUNT, pvt->channel_count, node_id);
+	if (!mci)
+		goto err_exit;
+
+	mci->pvt_info = pvt;
+
+	mci->dev = &pvt->dram_f2_ctl->dev;
+	amd64_setup_mci_misc_attributes(mci);
+
+	if (amd64_init_csrows(mci))
+		mci->edac_cap = EDAC_FLAG_NONE;
+
+	amd64_enable_ecc_error_reporting(mci);
+	amd64_set_mc_sysfs_attributes(mci);
+
+	ret = -ENODEV;
+	if (edac_mc_add_mc(mci)) {
+		debugf1("failed edac_mc_add_mc()\n");
+		goto err_add_mc;
+	}
+
+	mci_lookup[node_id] = mci;
+	pvt_lookup[node_id] = NULL;
+	return 0;
+
+err_add_mc:
+	edac_mc_free(mci);
+
+err_exit:
+	debugf0("failure to init 2nd stage: ret=%d\n", ret);
+
+	amd64_restore_ecc_error_reporting(pvt);
+
+	if (boot_cpu_data.x86 > 0xf)
+		amd64_teardown(pvt);
+
+	amd64_free_mc_sibling_devices(pvt);
+
+	kfree(pvt_lookup[pvt->mc_node_id]);
+	pvt_lookup[node_id] = NULL;
+
+	return ret;
+}
+
+
+static int __devinit amd64_init_one_instance(struct pci_dev *pdev,
+				 const struct pci_device_id *mc_type)
+{
+	int ret = 0;
+
+	debugf0("(MC node=%d,mc_type='%s')\n",
+		get_mc_node_id_from_pdev(pdev),
+		get_amd_family_name(mc_type->driver_data));
+
+	ret = pci_enable_device(pdev);
+	if (ret < 0)
+		ret = -EIO;
+	else
+		ret = amd64_probe_one_instance(pdev, mc_type->driver_data);
+
+	if (ret < 0)
+		debugf0("ret=%d\n", ret);
+
+	return ret;
+}
+
+static void __devexit amd64_remove_one_instance(struct pci_dev *pdev)
+{
+	struct mem_ctl_info *mci;
+	struct amd64_pvt *pvt;
+
+	/* Remove from EDAC CORE tracking list */
+	mci = edac_mc_del_mc(&pdev->dev);
+	if (!mci)
+		return;
+
+	pvt = mci->pvt_info;
+
+	amd64_restore_ecc_error_reporting(pvt);
+
+	if (boot_cpu_data.x86 > 0xf)
+		amd64_teardown(pvt);
+
+	amd64_free_mc_sibling_devices(pvt);
+
+	kfree(pvt);
+	mci->pvt_info = NULL;
+
+	mci_lookup[pvt->mc_node_id] = NULL;
+
+	/* Free the EDAC CORE resources */
+	edac_mc_free(mci);
+}
+
+/*
+ * This table is part of the interface for loading drivers for PCI devices. The
+ * PCI core identifies what devices are on a system during boot, and then
+ * inquiry this table to see if this driver is for a given device found.
+ */
+static const struct pci_device_id amd64_pci_table[] __devinitdata = {
+	{
+		.vendor		= PCI_VENDOR_ID_AMD,
+		.device		= PCI_DEVICE_ID_AMD_K8_NB_MEMCTL,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.class		= 0,
+		.class_mask	= 0,
+		.driver_data	= K8_CPUS
+	},
+	{
+		.vendor		= PCI_VENDOR_ID_AMD,
+		.device		= PCI_DEVICE_ID_AMD_10H_NB_DRAM,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.class		= 0,
+		.class_mask	= 0,
+		.driver_data	= F10_CPUS
+	},
+	{
+		.vendor		= PCI_VENDOR_ID_AMD,
+		.device		= PCI_DEVICE_ID_AMD_11H_NB_DRAM,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.class		= 0,
+		.class_mask	= 0,
+		.driver_data	= F11_CPUS
+	},
+	{0, }
+};
+MODULE_DEVICE_TABLE(pci, amd64_pci_table);
+
+static struct pci_driver amd64_pci_driver = {
+	.name		= EDAC_MOD_STR,
+	.probe		= amd64_init_one_instance,
+	.remove		= __devexit_p(amd64_remove_one_instance),
+	.id_table	= amd64_pci_table,
+};
+
+static void amd64_setup_pci_device(void)
+{
+	struct mem_ctl_info *mci;
+	struct amd64_pvt *pvt;
+
+	if (amd64_ctl_pci)
+		return;
+
+	mci = mci_lookup[0];
+	if (mci) {
+
+		pvt = mci->pvt_info;
+		amd64_ctl_pci =
+			edac_pci_create_generic_ctl(&pvt->dram_f2_ctl->dev,
+						    EDAC_MOD_STR);
+
+		if (!amd64_ctl_pci) {
+			pr_warning("%s(): Unable to create PCI control\n",
+				   __func__);
+
+			pr_warning("%s(): PCI error report via EDAC not set\n",
+				   __func__);
+			}
+	}
+}
+
+static int __init amd64_edac_init(void)
+{
+	int nb, err = -ENODEV;
+
+	edac_printk(KERN_INFO, EDAC_MOD_STR, EDAC_AMD64_VERSION "\n");
+
+	opstate_init();
+
+	if (cache_k8_northbridges() < 0)
+		goto err_exit;
+
+	err = pci_register_driver(&amd64_pci_driver);
+	if (err)
+		return err;
+
+	/*
+	 * At this point, the array 'pvt_lookup[]' contains pointers to alloc'd
+	 * amd64_pvt structs. These will be used in the 2nd stage init function
+	 * to finish initialization of the MC instances.
+	 */
+	for (nb = 0; nb < num_k8_northbridges; nb++) {
+		if (!pvt_lookup[nb])
+			continue;
+
+		err = amd64_init_2nd_stage(pvt_lookup[nb]);
+		if (err)
+			goto err_exit;
+	}
+
+	amd64_setup_pci_device();
+
+	return 0;
+
+err_exit:
+	debugf0("'finish_setup' stage failed\n");
+	pci_unregister_driver(&amd64_pci_driver);
+
+	return err;
+}
+
+static void __exit amd64_edac_exit(void)
+{
+	if (amd64_ctl_pci)
+		edac_pci_release_generic_ctl(amd64_ctl_pci);
+
+	pci_unregister_driver(&amd64_pci_driver);
+}
+
+module_init(amd64_edac_init);
+module_exit(amd64_edac_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("SoftwareBitMaker: Doug Thompson, "
+		"Dave Peterson, Thayne Harbaugh");
+MODULE_DESCRIPTION("MC support for AMD64 memory controllers - "
+		EDAC_AMD64_VERSION);
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
new file mode 100644
index 000000000000..a159957e167b
--- /dev/null
+++ b/drivers/edac/amd64_edac.h
@@ -0,0 +1,644 @@
+/*
+ * AMD64 class Memory Controller kernel module
+ *
+ * Copyright (c) 2009 SoftwareBitMaker.
+ * Copyright (c) 2009 Advanced Micro Devices, Inc.
+ *
+ * This file may be distributed under the terms of the
+ * GNU General Public License.
+ *
+ *	Originally Written by Thayne Harbaugh
+ *
+ *      Changes by Douglas "norsk" Thompson  <dougthompson@xmission.com>:
+ *		- K8 CPU Revision D and greater support
+ *
+ *      Changes by Dave Peterson <dsp@llnl.gov> <dave_peterson@pobox.com>:
+ *		- Module largely rewritten, with new (and hopefully correct)
+ *		code for dealing with node and chip select interleaving,
+ *		various code cleanup, and bug fixes
+ *		- Added support for memory hoisting using DRAM hole address
+ *		register
+ *
+ *	Changes by Douglas "norsk" Thompson <dougthompson@xmission.com>:
+ *		-K8 Rev (1207) revision support added, required Revision
+ *		specific mini-driver code to support Rev F as well as
+ *		prior revisions
+ *
+ *	Changes by Douglas "norsk" Thompson <dougthompson@xmission.com>:
+ *		-Family 10h revision support added. New PCI Device IDs,
+ *		indicating new changes. Actual registers modified
+ *		were slight, less than the Rev E to Rev F transition
+ *		but changing the PCI Device ID was the proper thing to
+ *		do, as it provides for almost automactic family
+ *		detection. The mods to Rev F required more family
+ *		information detection.
+ *
+ *	Changes/Fixes by Borislav Petkov <borislav.petkov@amd.com>:
+ *		- misc fixes and code cleanups
+ *
+ * This module is based on the following documents
+ * (available from http://www.amd.com/):
+ *
+ *	Title:	BIOS and Kernel Developer's Guide for AMD Athlon 64 and AMD
+ *		Opteron Processors
+ *	AMD publication #: 26094
+ *`	Revision: 3.26
+ *
+ *	Title:	BIOS and Kernel Developer's Guide for AMD NPT Family 0Fh
+ *		Processors
+ *	AMD publication #: 32559
+ *	Revision: 3.00
+ *	Issue Date: May 2006
+ *
+ *	Title:	BIOS and Kernel Developer's Guide (BKDG) For AMD Family 10h
+ *		Processors
+ *	AMD publication #: 31116
+ *	Revision: 3.00
+ *	Issue Date: September 07, 2007
+ *
+ * Sections in the first 2 documents are no longer in sync with each other.
+ * The Family 10h BKDG was totally re-written from scratch with a new
+ * presentation model.
+ * Therefore, comments that refer to a Document section might be off.
+ */
+
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/slab.h>
+#include <linux/mmzone.h>
+#include <linux/edac.h>
+#include <asm/msr.h>
+#include "edac_core.h"
+
+#define amd64_printk(level, fmt, arg...) \
+	edac_printk(level, "amd64", fmt, ##arg)
+
+#define amd64_mc_printk(mci, level, fmt, arg...) \
+	edac_mc_chipset_printk(mci, level, "amd64", fmt, ##arg)
+
+/*
+ * Throughout the comments in this code, the following terms are used:
+ *
+ *	SysAddr, DramAddr, and InputAddr
+ *
+ *  These terms come directly from the amd64 documentation
+ * (AMD publication #26094).  They are defined as follows:
+ *
+ *     SysAddr:
+ *         This is a physical address generated by a CPU core or a device
+ *         doing DMA.  If generated by a CPU core, a SysAddr is the result of
+ *         a virtual to physical address translation by the CPU core's address
+ *         translation mechanism (MMU).
+ *
+ *     DramAddr:
+ *         A DramAddr is derived from a SysAddr by subtracting an offset that
+ *         depends on which node the SysAddr maps to and whether the SysAddr
+ *         is within a range affected by memory hoisting.  The DRAM Base
+ *         (section 3.4.4.1) and DRAM Limit (section 3.4.4.2) registers
+ *         determine which node a SysAddr maps to.
+ *
+ *         If the DRAM Hole Address Register (DHAR) is enabled and the SysAddr
+ *         is within the range of addresses specified by this register, then
+ *         a value x from the DHAR is subtracted from the SysAddr to produce a
+ *         DramAddr.  Here, x represents the base address for the node that
+ *         the SysAddr maps to plus an offset due to memory hoisting.  See
+ *         section 3.4.8 and the comments in amd64_get_dram_hole_info() and
+ *         sys_addr_to_dram_addr() below for more information.
+ *
+ *         If the SysAddr is not affected by the DHAR then a value y is
+ *         subtracted from the SysAddr to produce a DramAddr.  Here, y is the
+ *         base address for the node that the SysAddr maps to.  See section
+ *         3.4.4 and the comments in sys_addr_to_dram_addr() below for more
+ *         information.
+ *
+ *     InputAddr:
+ *         A DramAddr is translated to an InputAddr before being passed to the
+ *         memory controller for the node that the DramAddr is associated
+ *         with.  The memory controller then maps the InputAddr to a csrow.
+ *         If node interleaving is not in use, then the InputAddr has the same
+ *         value as the DramAddr.  Otherwise, the InputAddr is produced by
+ *         discarding the bits used for node interleaving from the DramAddr.
+ *         See section 3.4.4 for more information.
+ *
+ *         The memory controller for a given node uses its DRAM CS Base and
+ *         DRAM CS Mask registers to map an InputAddr to a csrow.  See
+ *         sections 3.5.4 and 3.5.5 for more information.
+ */
+
+#define EDAC_AMD64_VERSION		" Ver: 3.2.0 " __DATE__
+#define EDAC_MOD_STR			"amd64_edac"
+
+/* Extended Model from CPUID, for CPU Revision numbers */
+#define OPTERON_CPU_LE_REV_C		0
+#define OPTERON_CPU_REV_D		1
+#define OPTERON_CPU_REV_E		2
+
+/* NPT processors have the following Extended Models */
+#define OPTERON_CPU_REV_F		4
+#define OPTERON_CPU_REV_FA		5
+
+/* Hardware limit on ChipSelect rows per MC and processors per system */
+#define CHIPSELECT_COUNT		8
+#define DRAM_REG_COUNT			8
+
+
+/*
+ * PCI-defined configuration space registers
+ */
+
+
+/*
+ * Function 1 - Address Map
+ */
+#define K8_DRAM_BASE_LOW		0x40
+#define K8_DRAM_LIMIT_LOW		0x44
+#define K8_DHAR				0xf0
+
+#define DHAR_VALID			BIT(0)
+#define F10_DRAM_MEM_HOIST_VALID	BIT(1)
+
+#define DHAR_BASE_MASK			0xff000000
+#define dhar_base(dhar)			(dhar & DHAR_BASE_MASK)
+
+#define K8_DHAR_OFFSET_MASK		0x0000ff00
+#define k8_dhar_offset(dhar)		((dhar & K8_DHAR_OFFSET_MASK) << 16)
+
+#define F10_DHAR_OFFSET_MASK		0x0000ff80
+					/* NOTE: Extra mask bit vs K8 */
+#define f10_dhar_offset(dhar)		((dhar & F10_DHAR_OFFSET_MASK) << 16)
+
+
+/* F10 High BASE/LIMIT registers */
+#define F10_DRAM_BASE_HIGH		0x140
+#define F10_DRAM_LIMIT_HIGH		0x144
+
+
+/*
+ * Function 2 - DRAM controller
+ */
+#define K8_DCSB0			0x40
+#define F10_DCSB1			0x140
+
+#define K8_DCSB_CS_ENABLE		BIT(0)
+#define K8_DCSB_NPT_SPARE		BIT(1)
+#define K8_DCSB_NPT_TESTFAIL		BIT(2)
+
+/*
+ * REV E: select [31:21] and [15:9] from DCSB and the shift amount to form
+ * the address
+ */
+#define REV_E_DCSB_BASE_BITS		(0xFFE0FE00ULL)
+#define REV_E_DCS_SHIFT			4
+#define REV_E_DCSM_COUNT		8
+
+#define REV_F_F1Xh_DCSB_BASE_BITS	(0x1FF83FE0ULL)
+#define REV_F_F1Xh_DCS_SHIFT		8
+
+/*
+ * REV F and later: selects [28:19] and [13:5] from DCSB and the shift amount
+ * to form the address
+ */
+#define REV_F_DCSB_BASE_BITS		(0x1FF83FE0ULL)
+#define REV_F_DCS_SHIFT			8
+#define REV_F_DCSM_COUNT		4
+#define F10_DCSM_COUNT			4
+#define F11_DCSM_COUNT			2
+
+/* DRAM CS Mask Registers */
+#define K8_DCSM0			0x60
+#define F10_DCSM1			0x160
+
+/* REV E: select [29:21] and [15:9] from DCSM */
+#define REV_E_DCSM_MASK_BITS		0x3FE0FE00
+
+/* unused bits [24:20] and [12:0] */
+#define REV_E_DCS_NOTUSED_BITS		0x01F01FFF
+
+/* REV F and later: select [28:19] and [13:5] from DCSM */
+#define REV_F_F1Xh_DCSM_MASK_BITS	0x1FF83FE0
+
+/* unused bits [26:22] and [12:0] */
+#define REV_F_F1Xh_DCS_NOTUSED_BITS	0x07C01FFF
+
+#define DBAM0				0x80
+#define DBAM1				0x180
+
+/* Extract the DIMM 'type' on the i'th DIMM from the DBAM reg value passed */
+#define DBAM_DIMM(i, reg)		((((reg) >> (4*i))) & 0xF)
+
+#define DBAM_MAX_VALUE			11
+
+
+#define F10_DCLR_0			0x90
+#define F10_DCLR_1			0x190
+#define REVE_WIDTH_128			BIT(16)
+#define F10_WIDTH_128			BIT(11)
+
+
+#define F10_DCHR_0			0x94
+#define F10_DCHR_1			0x194
+
+#define F10_DCHR_FOUR_RANK_DIMM		BIT(18)
+#define F10_DCHR_Ddr3Mode		BIT(8)
+#define F10_DCHR_MblMode		BIT(6)
+
+
+#define F10_DCTL_SEL_LOW		0x110
+
+#define dct_sel_baseaddr(pvt)    \
+	((pvt->dram_ctl_select_low) & 0xFFFFF800)
+
+#define dct_sel_interleave_addr(pvt)    \
+	(((pvt->dram_ctl_select_low) >> 6) & 0x3)
+
+enum {
+	F10_DCTL_SEL_LOW_DctSelHiRngEn	= BIT(0),
+	F10_DCTL_SEL_LOW_DctSelIntLvEn	= BIT(2),
+	F10_DCTL_SEL_LOW_DctGangEn	= BIT(4),
+	F10_DCTL_SEL_LOW_DctDatIntLv	= BIT(5),
+	F10_DCTL_SEL_LOW_DramEnable	= BIT(8),
+	F10_DCTL_SEL_LOW_MemCleared	= BIT(10),
+};
+
+#define    dct_high_range_enabled(pvt)    \
+	(pvt->dram_ctl_select_low & F10_DCTL_SEL_LOW_DctSelHiRngEn)
+
+#define dct_interleave_enabled(pvt)	   \
+	(pvt->dram_ctl_select_low & F10_DCTL_SEL_LOW_DctSelIntLvEn)
+
+#define dct_ganging_enabled(pvt)        \
+	(pvt->dram_ctl_select_low & F10_DCTL_SEL_LOW_DctGangEn)
+
+#define dct_data_intlv_enabled(pvt)    \
+	(pvt->dram_ctl_select_low & F10_DCTL_SEL_LOW_DctDatIntLv)
+
+#define dct_dram_enabled(pvt)    \
+	(pvt->dram_ctl_select_low & F10_DCTL_SEL_LOW_DramEnable)
+
+#define dct_memory_cleared(pvt)    \
+	(pvt->dram_ctl_select_low & F10_DCTL_SEL_LOW_MemCleared)
+
+
+#define F10_DCTL_SEL_HIGH		0x114
+
+
+/*
+ * Function 3 - Misc Control
+ */
+#define K8_NBCTL			0x40
+
+/* Correctable ECC error reporting enable */
+#define K8_NBCTL_CECCEn			BIT(0)
+
+/* UnCorrectable ECC error reporting enable */
+#define K8_NBCTL_UECCEn			BIT(1)
+
+#define K8_NBCFG			0x44
+#define K8_NBCFG_CHIPKILL		BIT(23)
+#define K8_NBCFG_ECC_ENABLE		BIT(22)
+
+#define K8_NBSL				0x48
+
+
+#define EXTRACT_HIGH_SYNDROME(x)	(((x) >> 24) & 0xff)
+#define EXTRACT_EXT_ERROR_CODE(x)	(((x) >> 16) & 0x1f)
+
+/* Family F10h: Normalized Extended Error Codes */
+#define F10_NBSL_EXT_ERR_RES		0x0
+#define F10_NBSL_EXT_ERR_CRC		0x1
+#define F10_NBSL_EXT_ERR_SYNC		0x2
+#define F10_NBSL_EXT_ERR_MST		0x3
+#define F10_NBSL_EXT_ERR_TGT		0x4
+#define F10_NBSL_EXT_ERR_GART		0x5
+#define F10_NBSL_EXT_ERR_RMW		0x6
+#define F10_NBSL_EXT_ERR_WDT		0x7
+#define F10_NBSL_EXT_ERR_ECC		0x8
+#define F10_NBSL_EXT_ERR_DEV		0x9
+#define F10_NBSL_EXT_ERR_LINK_DATA	0xA
+
+/* Next two are overloaded values */
+#define F10_NBSL_EXT_ERR_LINK_PROTO	0xB
+#define F10_NBSL_EXT_ERR_L3_PROTO	0xB
+
+#define F10_NBSL_EXT_ERR_NB_ARRAY	0xC
+#define F10_NBSL_EXT_ERR_DRAM_PARITY	0xD
+#define F10_NBSL_EXT_ERR_LINK_RETRY	0xE
+
+/* Next two are overloaded values */
+#define F10_NBSL_EXT_ERR_GART_WALK	0xF
+#define F10_NBSL_EXT_ERR_DEV_WALK	0xF
+
+/* 0x10 to 0x1B: Reserved */
+#define F10_NBSL_EXT_ERR_L3_DATA	0x1C
+#define F10_NBSL_EXT_ERR_L3_TAG		0x1D
+#define F10_NBSL_EXT_ERR_L3_LRU		0x1E
+
+/* K8: Normalized Extended Error Codes */
+#define K8_NBSL_EXT_ERR_ECC		0x0
+#define K8_NBSL_EXT_ERR_CRC		0x1
+#define K8_NBSL_EXT_ERR_SYNC		0x2
+#define K8_NBSL_EXT_ERR_MST		0x3
+#define K8_NBSL_EXT_ERR_TGT		0x4
+#define K8_NBSL_EXT_ERR_GART		0x5
+#define K8_NBSL_EXT_ERR_RMW		0x6
+#define K8_NBSL_EXT_ERR_WDT		0x7
+#define K8_NBSL_EXT_ERR_CHIPKILL_ECC	0x8
+#define K8_NBSL_EXT_ERR_DRAM_PARITY	0xD
+
+#define EXTRACT_ERROR_CODE(x)		((x) & 0xffff)
+#define	TEST_TLB_ERROR(x)		(((x) & 0xFFF0) == 0x0010)
+#define	TEST_MEM_ERROR(x)		(((x) & 0xFF00) == 0x0100)
+#define	TEST_BUS_ERROR(x)		(((x) & 0xF800) == 0x0800)
+#define	EXTRACT_TT_CODE(x)		(((x) >> 2) & 0x3)
+#define	EXTRACT_II_CODE(x)		(((x) >> 2) & 0x3)
+#define	EXTRACT_LL_CODE(x)		(((x) >> 0) & 0x3)
+#define	EXTRACT_RRRR_CODE(x)		(((x) >> 4) & 0xf)
+#define	EXTRACT_TO_CODE(x)		(((x) >> 8) & 0x1)
+#define	EXTRACT_PP_CODE(x)		(((x) >> 9) & 0x3)
+
+/*
+ * The following are for BUS type errors AFTER values have been normalized by
+ * shifting right
+ */
+#define K8_NBSL_PP_SRC			0x0
+#define K8_NBSL_PP_RES			0x1
+#define K8_NBSL_PP_OBS			0x2
+#define K8_NBSL_PP_GENERIC		0x3
+
+
+#define K8_NBSH				0x4C
+
+#define K8_NBSH_VALID_BIT		BIT(31)
+#define K8_NBSH_OVERFLOW		BIT(30)
+#define K8_NBSH_UNCORRECTED_ERR		BIT(29)
+#define K8_NBSH_ERR_ENABLE		BIT(28)
+#define K8_NBSH_MISC_ERR_VALID		BIT(27)
+#define K8_NBSH_VALID_ERROR_ADDR	BIT(26)
+#define K8_NBSH_PCC			BIT(25)
+#define K8_NBSH_CECC			BIT(14)
+#define K8_NBSH_UECC			BIT(13)
+#define K8_NBSH_ERR_SCRUBER		BIT(8)
+#define K8_NBSH_CORE3			BIT(3)
+#define K8_NBSH_CORE2			BIT(2)
+#define K8_NBSH_CORE1			BIT(1)
+#define K8_NBSH_CORE0			BIT(0)
+
+#define EXTRACT_LDT_LINK(x)		(((x) >> 4) & 0x7)
+#define EXTRACT_ERR_CPU_MAP(x)		((x) & 0xF)
+#define EXTRACT_LOW_SYNDROME(x)		(((x) >> 15) & 0xff)
+
+
+#define K8_NBEAL			0x50
+#define K8_NBEAH			0x54
+#define K8_SCRCTRL			0x58
+
+#define F10_NB_CFG_LOW			0x88
+#define	F10_NB_CFG_LOW_ENABLE_EXT_CFG	BIT(14)
+
+#define F10_NB_CFG_HIGH			0x8C
+
+#define F10_ONLINE_SPARE		0xB0
+#define F10_ONLINE_SPARE_SWAPDONE0(x)	((x) & BIT(1))
+#define F10_ONLINE_SPARE_SWAPDONE1(x)	((x) & BIT(3))
+#define F10_ONLINE_SPARE_BADDRAM_CS0(x) (((x) >> 4) & 0x00000007)
+#define F10_ONLINE_SPARE_BADDRAM_CS1(x) (((x) >> 8) & 0x00000007)
+
+#define F10_NB_ARRAY_ADDR		0xB8
+
+#define F10_NB_ARRAY_DRAM_ECC		0x80000000
+
+/* Bits [2:1] are used to select 16-byte section within a 64-byte cacheline  */
+#define SET_NB_ARRAY_ADDRESS(section)	(((section) & 0x3) << 1)
+
+#define F10_NB_ARRAY_DATA		0xBC
+
+#define SET_NB_DRAM_INJECTION_WRITE(word, bits)  \
+					(BIT(((word) & 0xF) + 20) | \
+					BIT(17) |  \
+					((bits) & 0xF))
+
+#define SET_NB_DRAM_INJECTION_READ(word, bits)  \
+					(BIT(((word) & 0xF) + 20) | \
+					BIT(16) |  \
+					((bits) & 0xF))
+
+#define K8_NBCAP			0xE8
+#define K8_NBCAP_CORES			(BIT(12)|BIT(13))
+#define K8_NBCAP_CHIPKILL		BIT(4)
+#define K8_NBCAP_SECDED			BIT(3)
+#define K8_NBCAP_8_NODE			BIT(2)
+#define K8_NBCAP_DUAL_NODE		BIT(1)
+#define K8_NBCAP_DCT_DUAL		BIT(0)
+
+/*
+ * MSR Regs
+ */
+#define K8_MSR_MCGCTL			0x017b
+#define K8_MSR_MCGCTL_NBE		BIT(4)
+
+#define K8_MSR_MC4CTL			0x0410
+#define K8_MSR_MC4STAT			0x0411
+#define K8_MSR_MC4ADDR			0x0412
+
+/* AMD sets the first MC device at device ID 0x18. */
+static inline int get_mc_node_id_from_pdev(struct pci_dev *pdev)
+{
+	return PCI_SLOT(pdev->devfn) - 0x18;
+}
+
+enum amd64_chipset_families {
+	K8_CPUS = 0,
+	F10_CPUS,
+	F11_CPUS,
+};
+
+/*
+ * Structure to hold:
+ *
+ * 1) dynamically read status and error address HW registers
+ * 2) sysfs entered values
+ * 3) MCE values
+ *
+ * Depends on entry into the modules
+ */
+struct amd64_error_info_regs {
+	u32 nbcfg;
+	u32 nbsh;
+	u32 nbsl;
+	u32 nbeah;
+	u32 nbeal;
+};
+
+/* Error injection control structure */
+struct error_injection {
+	u32	section;
+	u32	word;
+	u32	bit_map;
+};
+
+struct amd64_pvt {
+	/* pci_device handles which we utilize */
+	struct pci_dev *addr_f1_ctl;
+	struct pci_dev *dram_f2_ctl;
+	struct pci_dev *misc_f3_ctl;
+
+	int mc_node_id;		/* MC index of this MC node */
+	int ext_model;		/* extended model value of this node */
+
+	struct low_ops *ops;	/* pointer to per PCI Device ID func table */
+
+	int channel_count;
+
+	/* Raw registers */
+	u32 dclr0;		/* DRAM Configuration Low DCT0 reg */
+	u32 dclr1;		/* DRAM Configuration Low DCT1 reg */
+	u32 dchr0;		/* DRAM Configuration High DCT0 reg */
+	u32 dchr1;		/* DRAM Configuration High DCT1 reg */
+	u32 nbcap;		/* North Bridge Capabilities */
+	u32 nbcfg;		/* F10 North Bridge Configuration */
+	u32 ext_nbcfg;		/* Extended F10 North Bridge Configuration */
+	u32 dhar;		/* DRAM Hoist reg */
+	u32 dbam0;		/* DRAM Base Address Mapping reg for DCT0 */
+	u32 dbam1;		/* DRAM Base Address Mapping reg for DCT1 */
+
+	/* DRAM CS Base Address Registers F2x[1,0][5C:40] */
+	u32 dcsb0[CHIPSELECT_COUNT];
+	u32 dcsb1[CHIPSELECT_COUNT];
+
+	/* DRAM CS Mask Registers F2x[1,0][6C:60] */
+	u32 dcsm0[CHIPSELECT_COUNT];
+	u32 dcsm1[CHIPSELECT_COUNT];
+
+	/*
+	 * Decoded parts of DRAM BASE and LIMIT Registers
+	 * F1x[78,70,68,60,58,50,48,40]
+	 */
+	u64 dram_base[DRAM_REG_COUNT];
+	u64 dram_limit[DRAM_REG_COUNT];
+	u8  dram_IntlvSel[DRAM_REG_COUNT];
+	u8  dram_IntlvEn[DRAM_REG_COUNT];
+	u8  dram_DstNode[DRAM_REG_COUNT];
+	u8  dram_rw_en[DRAM_REG_COUNT];
+
+	/*
+	 * The following fields are set at (load) run time, after CPU revision
+	 * has been determined, since the dct_base and dct_mask registers vary
+	 * based on revision
+	 */
+	u32 dcsb_base;		/* DCSB base bits */
+	u32 dcsm_mask;		/* DCSM mask bits */
+	u32 num_dcsm;		/* Number of DCSM registers */
+	u32 dcs_mask_notused;	/* DCSM notused mask bits */
+	u32 dcs_shift;		/* DCSB and DCSM shift value */
+
+	u64 top_mem;		/* top of memory below 4GB */
+	u64 top_mem2;		/* top of memory above 4GB */
+
+	u32 dram_ctl_select_low;	/* DRAM Controller Select Low Reg */
+	u32 dram_ctl_select_high;	/* DRAM Controller Select High Reg */
+	u32 online_spare;               /* On-Line spare Reg */
+
+	/* temp storage for when input is received from sysfs */
+	struct amd64_error_info_regs ctl_error_info;
+
+	/* place to store error injection parameters prior to issue */
+	struct error_injection injection;
+
+	/* Save old hw registers' values before we modified them */
+	u32 nbctl_mcgctl_saved;		/* When true, following 2 are valid */
+	u32 old_nbctl;
+	unsigned long old_mcgctl;	/* per core on this node */
+
+	/* MC Type Index value: socket F vs Family 10h */
+	u32 mc_type_index;
+
+	/* misc settings */
+	struct flags {
+		unsigned long cf8_extcfg:1;
+	} flags;
+};
+
+struct scrubrate {
+       u32 scrubval;           /* bit pattern for scrub rate */
+       u32 bandwidth;          /* bandwidth consumed (bytes/sec) */
+};
+
+extern struct scrubrate scrubrates[23];
+extern u32 revf_quad_ddr2_shift[16];
+extern const char *tt_msgs[4];
+extern const char *ll_msgs[4];
+extern const char *rrrr_msgs[16];
+extern const char *to_msgs[2];
+extern const char *pp_msgs[4];
+extern const char *ii_msgs[4];
+extern const char *ext_msgs[32];
+extern const char *htlink_msgs[8];
+
+#ifdef CONFIG_EDAC_DEBUG
+#define NUM_DBG_ATTRS 9
+#else
+#define NUM_DBG_ATTRS 0
+#endif
+
+#ifdef CONFIG_EDAC_AMD64_ERROR_INJECTION
+#define NUM_INJ_ATTRS 5
+#else
+#define NUM_INJ_ATTRS 0
+#endif
+
+extern struct mcidev_sysfs_attribute amd64_dbg_attrs[NUM_DBG_ATTRS],
+				     amd64_inj_attrs[NUM_INJ_ATTRS];
+
+/*
+ * Each of the PCI Device IDs types have their own set of hardware accessor
+ * functions and per device encoding/decoding logic.
+ */
+struct low_ops {
+	int (*probe_valid_hardware)(struct amd64_pvt *pvt);
+	int (*early_channel_count)(struct amd64_pvt *pvt);
+
+	u64 (*get_error_address)(struct mem_ctl_info *mci,
+			struct amd64_error_info_regs *info);
+	void (*read_dram_base_limit)(struct amd64_pvt *pvt, int dram);
+	void (*read_dram_ctl_register)(struct amd64_pvt *pvt);
+	void (*map_sysaddr_to_csrow)(struct mem_ctl_info *mci,
+					struct amd64_error_info_regs *info,
+					u64 SystemAddr);
+	int (*dbam_map_to_pages)(struct amd64_pvt *pvt, int dram_map);
+};
+
+struct amd64_family_type {
+	const char *ctl_name;
+	u16 addr_f1_ctl;
+	u16 misc_f3_ctl;
+	struct low_ops ops;
+};
+
+static struct amd64_family_type amd64_family_types[];
+
+static inline const char *get_amd_family_name(int index)
+{
+	return amd64_family_types[index].ctl_name;
+}
+
+static inline struct low_ops *family_ops(int index)
+{
+	return &amd64_family_types[index].ops;
+}
+
+/*
+ * For future CPU versions, verify the following as new 'slow' rates appear and
+ * modify the necessary skip values for the supported CPU.
+ */
+#define K8_MIN_SCRUB_RATE_BITS	0x0
+#define F10_MIN_SCRUB_RATE_BITS	0x5
+#define F11_MIN_SCRUB_RATE_BITS	0x6
+
+int amd64_process_error_info(struct mem_ctl_info *mci,
+			     struct amd64_error_info_regs *info,
+			     int handle_errors);
+int amd64_get_dram_hole_info(struct mem_ctl_info *mci, u64 *hole_base,
+			     u64 *hole_offset, u64 *hole_size);
diff --git a/drivers/edac/amd64_edac_dbg.c b/drivers/edac/amd64_edac_dbg.c
new file mode 100644
index 000000000000..0a41b248a4ad
--- /dev/null
+++ b/drivers/edac/amd64_edac_dbg.c
@@ -0,0 +1,255 @@
+#include "amd64_edac.h"
+
+/*
+ * accept a hex value and store it into the virtual error register file, field:
+ * nbeal and nbeah. Assume virtual error values have already been set for: NBSL,
+ * NBSH and NBCFG. Then proceed to map the error values to a MC, CSROW and
+ * CHANNEL
+ */
+static ssize_t amd64_nbea_store(struct mem_ctl_info *mci, const char *data,
+				size_t count)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	unsigned long long value;
+	int ret = 0;
+
+	ret = strict_strtoull(data, 16, &value);
+	if (ret != -EINVAL) {
+		debugf0("received NBEA= 0x%llx\n", value);
+
+		/* place the value into the virtual error packet */
+		pvt->ctl_error_info.nbeal = (u32) value;
+		value >>= 32;
+		pvt->ctl_error_info.nbeah = (u32) value;
+
+		/* Process the Mapping request */
+		/* TODO: Add race prevention */
+		amd64_process_error_info(mci, &pvt->ctl_error_info, 1);
+
+		return count;
+	}
+	return ret;
+}
+
+/* display back what the last NBEA (MCA NB Address (MC4_ADDR)) was written */
+static ssize_t amd64_nbea_show(struct mem_ctl_info *mci, char *data)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	u64 value;
+
+	value = pvt->ctl_error_info.nbeah;
+	value <<= 32;
+	value |= pvt->ctl_error_info.nbeal;
+
+	return sprintf(data, "%llx\n", value);
+}
+
+/* store the NBSL (MCA NB Status Low (MC4_STATUS)) value user desires */
+static ssize_t amd64_nbsl_store(struct mem_ctl_info *mci, const char *data,
+				size_t count)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	unsigned long value;
+	int ret = 0;
+
+	ret = strict_strtoul(data, 16, &value);
+	if (ret != -EINVAL) {
+		debugf0("received NBSL= 0x%lx\n", value);
+
+		pvt->ctl_error_info.nbsl = (u32) value;
+
+		return count;
+	}
+	return ret;
+}
+
+/* display back what the last NBSL value written */
+static ssize_t amd64_nbsl_show(struct mem_ctl_info *mci, char *data)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	u32 value;
+
+	value = pvt->ctl_error_info.nbsl;
+
+	return sprintf(data, "%x\n", value);
+}
+
+/* store the NBSH (MCA NB Status High) value user desires */
+static ssize_t amd64_nbsh_store(struct mem_ctl_info *mci, const char *data,
+				size_t count)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	unsigned long value;
+	int ret = 0;
+
+	ret = strict_strtoul(data, 16, &value);
+	if (ret != -EINVAL) {
+		debugf0("received NBSH= 0x%lx\n", value);
+
+		pvt->ctl_error_info.nbsh = (u32) value;
+
+		return count;
+	}
+	return ret;
+}
+
+/* display back what the last NBSH value written */
+static ssize_t amd64_nbsh_show(struct mem_ctl_info *mci, char *data)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	u32 value;
+
+	value = pvt->ctl_error_info.nbsh;
+
+	return sprintf(data, "%x\n", value);
+}
+
+/* accept and store the NBCFG (MCA NB Configuration) value user desires */
+static ssize_t amd64_nbcfg_store(struct mem_ctl_info *mci,
+					const char *data, size_t count)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	unsigned long value;
+	int ret = 0;
+
+	ret = strict_strtoul(data, 16, &value);
+	if (ret != -EINVAL) {
+		debugf0("received NBCFG= 0x%lx\n", value);
+
+		pvt->ctl_error_info.nbcfg = (u32) value;
+
+		return count;
+	}
+	return ret;
+}
+
+/* various show routines for the controls of a MCI */
+static ssize_t amd64_nbcfg_show(struct mem_ctl_info *mci, char *data)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+
+	return sprintf(data, "%x\n", pvt->ctl_error_info.nbcfg);
+}
+
+
+static ssize_t amd64_dhar_show(struct mem_ctl_info *mci, char *data)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+
+	return sprintf(data, "%x\n", pvt->dhar);
+}
+
+
+static ssize_t amd64_dbam_show(struct mem_ctl_info *mci, char *data)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+
+	return sprintf(data, "%x\n", pvt->dbam0);
+}
+
+
+static ssize_t amd64_topmem_show(struct mem_ctl_info *mci, char *data)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+
+	return sprintf(data, "%llx\n", pvt->top_mem);
+}
+
+
+static ssize_t amd64_topmem2_show(struct mem_ctl_info *mci, char *data)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+
+	return sprintf(data, "%llx\n", pvt->top_mem2);
+}
+
+static ssize_t amd64_hole_show(struct mem_ctl_info *mci, char *data)
+{
+	u64 hole_base = 0;
+	u64 hole_offset = 0;
+	u64 hole_size = 0;
+
+	amd64_get_dram_hole_info(mci, &hole_base, &hole_offset, &hole_size);
+
+	return sprintf(data, "%llx %llx %llx\n", hole_base, hole_offset,
+						 hole_size);
+}
+
+/*
+ * update NUM_DBG_ATTRS in case you add new members
+ */
+struct mcidev_sysfs_attribute amd64_dbg_attrs[] = {
+
+	{
+		.attr = {
+			.name = "nbea_ctl",
+			.mode = (S_IRUGO | S_IWUSR)
+		},
+		.show = amd64_nbea_show,
+		.store = amd64_nbea_store,
+	},
+	{
+		.attr = {
+			.name = "nbsl_ctl",
+			.mode = (S_IRUGO | S_IWUSR)
+		},
+		.show = amd64_nbsl_show,
+		.store = amd64_nbsl_store,
+	},
+	{
+		.attr = {
+			.name = "nbsh_ctl",
+			.mode = (S_IRUGO | S_IWUSR)
+		},
+		.show = amd64_nbsh_show,
+		.store = amd64_nbsh_store,
+	},
+	{
+		.attr = {
+			.name = "nbcfg_ctl",
+			.mode = (S_IRUGO | S_IWUSR)
+		},
+		.show = amd64_nbcfg_show,
+		.store = amd64_nbcfg_store,
+	},
+	{
+		.attr = {
+			.name = "dhar",
+			.mode = (S_IRUGO)
+		},
+		.show = amd64_dhar_show,
+		.store = NULL,
+	},
+	{
+		.attr = {
+			.name = "dbam",
+			.mode = (S_IRUGO)
+		},
+		.show = amd64_dbam_show,
+		.store = NULL,
+	},
+	{
+		.attr = {
+			.name = "topmem",
+			.mode = (S_IRUGO)
+		},
+		.show = amd64_topmem_show,
+		.store = NULL,
+	},
+	{
+		.attr = {
+			.name = "topmem2",
+			.mode = (S_IRUGO)
+		},
+		.show = amd64_topmem2_show,
+		.store = NULL,
+	},
+	{
+		.attr = {
+			.name = "dram_hole",
+			.mode = (S_IRUGO)
+		},
+		.show = amd64_hole_show,
+		.store = NULL,
+	},
+};
diff --git a/drivers/edac/amd64_edac_err_types.c b/drivers/edac/amd64_edac_err_types.c
new file mode 100644
index 000000000000..f212ff12a9d8
--- /dev/null
+++ b/drivers/edac/amd64_edac_err_types.c
@@ -0,0 +1,161 @@
+#include "amd64_edac.h"
+
+/*
+ * See F2x80 for K8 and F2x[1,0]80 for Fam10 and later. The table below is only
+ * for DDR2 DRAM mapping.
+ */
+u32 revf_quad_ddr2_shift[] = {
+	0,	/* 0000b NULL DIMM (128mb) */
+	28,	/* 0001b 256mb */
+	29,	/* 0010b 512mb */
+	29,	/* 0011b 512mb */
+	29,	/* 0100b 512mb */
+	30,	/* 0101b 1gb */
+	30,	/* 0110b 1gb */
+	31,	/* 0111b 2gb */
+	31,	/* 1000b 2gb */
+	32,	/* 1001b 4gb */
+	32,	/* 1010b 4gb */
+	33,	/* 1011b 8gb */
+	0,	/* 1100b future */
+	0,	/* 1101b future */
+	0,	/* 1110b future */
+	0	/* 1111b future */
+};
+
+/*
+ * Valid scrub rates for the K8 hardware memory scrubber. We map the scrubbing
+ * bandwidth to a valid bit pattern. The 'set' operation finds the 'matching-
+ * or higher value'.
+ *
+ *FIXME: Produce a better mapping/linearisation.
+ */
+
+struct scrubrate scrubrates[] = {
+	{ 0x01, 1600000000UL},
+	{ 0x02, 800000000UL},
+	{ 0x03, 400000000UL},
+	{ 0x04, 200000000UL},
+	{ 0x05, 100000000UL},
+	{ 0x06, 50000000UL},
+	{ 0x07, 25000000UL},
+	{ 0x08, 12284069UL},
+	{ 0x09, 6274509UL},
+	{ 0x0A, 3121951UL},
+	{ 0x0B, 1560975UL},
+	{ 0x0C, 781440UL},
+	{ 0x0D, 390720UL},
+	{ 0x0E, 195300UL},
+	{ 0x0F, 97650UL},
+	{ 0x10, 48854UL},
+	{ 0x11, 24427UL},
+	{ 0x12, 12213UL},
+	{ 0x13, 6101UL},
+	{ 0x14, 3051UL},
+	{ 0x15, 1523UL},
+	{ 0x16, 761UL},
+	{ 0x00, 0UL},        /* scrubbing off */
+};
+
+/*
+ * string representation for the different MCA reported error types, see F3x48
+ * or MSR0000_0411.
+ */
+const char *tt_msgs[] = {        /* transaction type */
+	"instruction",
+	"data",
+	"generic",
+	"reserved"
+};
+
+const char *ll_msgs[] = {	/* cache level */
+	"L0",
+	"L1",
+	"L2",
+	"L3/generic"
+};
+
+const char *rrrr_msgs[] = {
+	"generic",
+	"generic read",
+	"generic write",
+	"data read",
+	"data write",
+	"inst fetch",
+	"prefetch",
+	"evict",
+	"snoop",
+	"reserved RRRR= 9",
+	"reserved RRRR= 10",
+	"reserved RRRR= 11",
+	"reserved RRRR= 12",
+	"reserved RRRR= 13",
+	"reserved RRRR= 14",
+	"reserved RRRR= 15"
+};
+
+const char *pp_msgs[] = {	/* participating processor */
+	"local node originated (SRC)",
+	"local node responded to request (RES)",
+	"local node observed as 3rd party (OBS)",
+	"generic"
+};
+
+const char *to_msgs[] = {
+	"no timeout",
+	"timed out"
+};
+
+const char *ii_msgs[] = {	/* memory or i/o */
+	"mem access",
+	"reserved",
+	"i/o access",
+	"generic"
+};
+
+/* Map the 5 bits of Extended Error code to the string table. */
+const char *ext_msgs[] = {	/* extended error */
+	"K8 ECC error/F10 reserved",	/* 0_0000b */
+	"CRC error",			/* 0_0001b */
+	"sync error",			/* 0_0010b */
+	"mst abort",			/* 0_0011b */
+	"tgt abort",			/* 0_0100b */
+	"GART error",			/* 0_0101b */
+	"RMW error",			/* 0_0110b */
+	"Wdog timer error",		/* 0_0111b */
+	"F10-ECC/K8-Chipkill error",	/* 0_1000b */
+	"DEV Error",			/* 0_1001b */
+	"Link Data error",		/* 0_1010b */
+	"Link or L3 Protocol error",	/* 0_1011b */
+	"NB Array error",		/* 0_1100b */
+	"DRAM Parity error",		/* 0_1101b */
+	"Link Retry/GART Table Walk/DEV Table Walk error", /* 0_1110b */
+	"Res 0x0ff error",		/* 0_1111b */
+	"Res 0x100 error",		/* 1_0000b */
+	"Res 0x101 error",		/* 1_0001b */
+	"Res 0x102 error",		/* 1_0010b */
+	"Res 0x103 error",		/* 1_0011b */
+	"Res 0x104 error",		/* 1_0100b */
+	"Res 0x105 error",		/* 1_0101b */
+	"Res 0x106 error",		/* 1_0110b */
+	"Res 0x107 error",		/* 1_0111b */
+	"Res 0x108 error",		/* 1_1000b */
+	"Res 0x109 error",		/* 1_1001b */
+	"Res 0x10A error",		/* 1_1010b */
+	"Res 0x10B error",		/* 1_1011b */
+	"L3 Cache Data error",		/* 1_1100b */
+	"L3 CacheTag error",		/* 1_1101b */
+	"L3 Cache LRU error",		/* 1_1110b */
+	"Res 0x1FF error"		/* 1_1111b */
+};
+
+const char *htlink_msgs[] = {
+	"none",
+	"1",
+	"2",
+	"1 2",
+	"3",
+	"1 3",
+	"2 3",
+	"1 2 3"
+};
diff --git a/drivers/edac/amd64_edac_inj.c b/drivers/edac/amd64_edac_inj.c
new file mode 100644
index 000000000000..d3675b76b3a7
--- /dev/null
+++ b/drivers/edac/amd64_edac_inj.c
@@ -0,0 +1,185 @@
+#include "amd64_edac.h"
+
+/*
+ * store error injection section value which refers to one of 4 16-byte sections
+ * within a 64-byte cacheline
+ *
+ * range: 0..3
+ */
+static ssize_t amd64_inject_section_store(struct mem_ctl_info *mci,
+					  const char *data, size_t count)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	unsigned long value;
+	int ret = 0;
+
+	ret = strict_strtoul(data, 10, &value);
+	if (ret != -EINVAL) {
+		pvt->injection.section = (u32) value;
+		return count;
+	}
+	return ret;
+}
+
+/*
+ * store error injection word value which refers to one of 9 16-bit word of the
+ * 16-byte (128-bit + ECC bits) section
+ *
+ * range: 0..8
+ */
+static ssize_t amd64_inject_word_store(struct mem_ctl_info *mci,
+					const char *data, size_t count)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	unsigned long value;
+	int ret = 0;
+
+	ret = strict_strtoul(data, 10, &value);
+	if (ret != -EINVAL) {
+
+		value = (value <= 8) ? value : 0;
+		pvt->injection.word = (u32) value;
+
+		return count;
+	}
+	return ret;
+}
+
+/*
+ * store 16 bit error injection vector which enables injecting errors to the
+ * corresponding bit within the error injection word above. When used during a
+ * DRAM ECC read, it holds the contents of the of the DRAM ECC bits.
+ */
+static ssize_t amd64_inject_ecc_vector_store(struct mem_ctl_info *mci,
+					     const char *data, size_t count)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	unsigned long value;
+	int ret = 0;
+
+	ret = strict_strtoul(data, 16, &value);
+	if (ret != -EINVAL) {
+
+		pvt->injection.bit_map = (u32) value & 0xFFFF;
+
+		return count;
+	}
+	return ret;
+}
+
+/*
+ * Do a DRAM ECC read. Assemble staged values in the pvt area, format into
+ * fields needed by the injection registers and read the NB Array Data Port.
+ */
+static ssize_t amd64_inject_read_store(struct mem_ctl_info *mci,
+					const char *data, size_t count)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	unsigned long value;
+	u32 section, word_bits;
+	int ret = 0;
+
+	ret = strict_strtoul(data, 10, &value);
+	if (ret != -EINVAL) {
+
+		/* Form value to choose 16-byte section of cacheline */
+		section = F10_NB_ARRAY_DRAM_ECC |
+				SET_NB_ARRAY_ADDRESS(pvt->injection.section);
+		pci_write_config_dword(pvt->misc_f3_ctl,
+					F10_NB_ARRAY_ADDR, section);
+
+		word_bits = SET_NB_DRAM_INJECTION_READ(pvt->injection.word,
+						pvt->injection.bit_map);
+
+		/* Issue 'word' and 'bit' along with the READ request */
+		pci_write_config_dword(pvt->misc_f3_ctl,
+					F10_NB_ARRAY_DATA, word_bits);
+
+		debugf0("section=0x%x word_bits=0x%x\n", section, word_bits);
+
+		return count;
+	}
+	return ret;
+}
+
+/*
+ * Do a DRAM ECC write. Assemble staged values in the pvt area and format into
+ * fields needed by the injection registers.
+ */
+static ssize_t amd64_inject_write_store(struct mem_ctl_info *mci,
+					const char *data, size_t count)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	unsigned long value;
+	u32 section, word_bits;
+	int ret = 0;
+
+	ret = strict_strtoul(data, 10, &value);
+	if (ret != -EINVAL) {
+
+		/* Form value to choose 16-byte section of cacheline */
+		section = F10_NB_ARRAY_DRAM_ECC |
+				SET_NB_ARRAY_ADDRESS(pvt->injection.section);
+		pci_write_config_dword(pvt->misc_f3_ctl,
+					F10_NB_ARRAY_ADDR, section);
+
+		word_bits = SET_NB_DRAM_INJECTION_WRITE(pvt->injection.word,
+						pvt->injection.bit_map);
+
+		/* Issue 'word' and 'bit' along with the READ request */
+		pci_write_config_dword(pvt->misc_f3_ctl,
+					F10_NB_ARRAY_DATA, word_bits);
+
+		debugf0("section=0x%x word_bits=0x%x\n", section, word_bits);
+
+		return count;
+	}
+	return ret;
+}
+
+/*
+ * update NUM_INJ_ATTRS in case you add new members
+ */
+struct mcidev_sysfs_attribute amd64_inj_attrs[] = {
+
+	{
+		.attr = {
+			.name = "inject_section",
+			.mode = (S_IRUGO | S_IWUSR)
+		},
+		.show = NULL,
+		.store = amd64_inject_section_store,
+	},
+	{
+		.attr = {
+			.name = "inject_word",
+			.mode = (S_IRUGO | S_IWUSR)
+		},
+		.show = NULL,
+		.store = amd64_inject_word_store,
+	},
+	{
+		.attr = {
+			.name = "inject_ecc_vector",
+			.mode = (S_IRUGO | S_IWUSR)
+		},
+		.show = NULL,
+		.store = amd64_inject_ecc_vector_store,
+	},
+	{
+		.attr = {
+			.name = "inject_write",
+			.mode = (S_IRUGO | S_IWUSR)
+		},
+		.show = NULL,
+		.store = amd64_inject_write_store,
+	},
+	{
+		.attr = {
+			.name = "inject_read",
+			.mode = (S_IRUGO | S_IWUSR)
+		},
+		.show = NULL,
+		.store = amd64_inject_read_store,
+	},
+};
diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h
index 6ad95c8d6363..48d3b1409834 100644
--- a/drivers/edac/edac_core.h
+++ b/drivers/edac/edac_core.h
@@ -76,10 +76,11 @@
 extern int edac_debug_level;
 
 #ifndef CONFIG_EDAC_DEBUG_VERBOSE
-#define edac_debug_printk(level, fmt, arg...)                            \
-	do {                                                             \
-		if (level <= edac_debug_level)                           \
-			edac_printk(KERN_DEBUG, EDAC_DEBUG, fmt, ##arg); \
+#define edac_debug_printk(level, fmt, arg...)                           \
+	do {                                                            \
+		if (level <= edac_debug_level)                          \
+			edac_printk(KERN_DEBUG, EDAC_DEBUG,		\
+				    "%s: " fmt, __func__, ##arg);	\
 	} while (0)
 #else  /* CONFIG_EDAC_DEBUG_VERBOSE */
 #define edac_debug_printk(level, fmt, arg...)                            \
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 5f1b5400d96a..24c84ae81527 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -596,6 +596,7 @@ int dmi_get_year(int field)
 
 	return year;
 }
+EXPORT_SYMBOL(dmi_get_year);
 
 /**
  *	dmi_walk - Walk the DMI table and get called back for every record
diff --git a/drivers/i2c/busses/i2c-sh7760.c b/drivers/i2c/busses/i2c-sh7760.c
index baa28b73ae42..b9680f50f541 100644
--- a/drivers/i2c/busses/i2c-sh7760.c
+++ b/drivers/i2c/busses/i2c-sh7760.c
@@ -396,7 +396,7 @@ static int __devinit calc_CCR(unsigned long scl_hz)
 	signed char cdf, cdfm;
 	int scgd, scgdm, scgds;
 
-	mclk = clk_get(NULL, "module_clk");
+	mclk = clk_get(NULL, "peripheral_clk");
 	if (IS_ERR(mclk)) {
 		return PTR_ERR(mclk);
 	} else {
diff --git a/drivers/ide/alim15x3.c b/drivers/ide/alim15x3.c
index 537da1cde16d..e59b6dee9ae2 100644
--- a/drivers/ide/alim15x3.c
+++ b/drivers/ide/alim15x3.c
@@ -402,27 +402,23 @@ static u8 ali_cable_detect(ide_hwif_t *hwif)
 	return cbl;
 }
 
-#if !defined(CONFIG_SPARC64) && !defined(CONFIG_PPC)
+#ifndef CONFIG_SPARC64
 /**
  *	init_hwif_ali15x3	-	Initialize the ALI IDE x86 stuff
  *	@hwif: interface to configure
  *
  *	Obtain the IRQ tables for an ALi based IDE solution on the PC
  *	class platforms. This part of the code isn't applicable to the
- *	Sparc and PowerPC systems.
+ *	Sparc systems.
  */
 
 static void __devinit init_hwif_ali15x3 (ide_hwif_t *hwif)
 {
-	struct pci_dev *dev = to_pci_dev(hwif->dev);
 	u8 ideic, inmir;
 	s8 irq_routing_table[] = { -1,  9, 3, 10, 4,  5, 7,  6,
 				      1, 11, 0, 12, 0, 14, 0, 15 };
 	int irq = -1;
 
-	if (dev->device == PCI_DEVICE_ID_AL_M5229)
-		hwif->irq = hwif->channel ? 15 : 14;
-
 	if (isa_dev) {
 		/*
 		 * read IDE interface control
@@ -455,7 +451,7 @@ static void __devinit init_hwif_ali15x3 (ide_hwif_t *hwif)
 }
 #else
 #define init_hwif_ali15x3 NULL
-#endif /* !defined(CONFIG_SPARC64) && !defined(CONFIG_PPC) */
+#endif /* CONFIG_SPARC64 */
 
 /**
  *	init_dma_ali15x3	-	set up DMA on ALi15x3
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index 7201b176d75b..757e5956b132 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -79,34 +79,6 @@ void ide_init_pc(struct ide_atapi_pc *pc)
 }
 EXPORT_SYMBOL_GPL(ide_init_pc);
 
-/*
- * Generate a new packet command request in front of the request queue, before
- * the current request, so that it will be processed immediately, on the next
- * pass through the driver.
- */
-static void ide_queue_pc_head(ide_drive_t *drive, struct gendisk *disk,
-			      struct ide_atapi_pc *pc, struct request *rq)
-{
-	blk_rq_init(NULL, rq);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
-	rq->cmd_flags |= REQ_PREEMPT;
-	rq->buffer = (char *)pc;
-	rq->rq_disk = disk;
-
-	if (pc->req_xfer) {
-		rq->data = pc->buf;
-		rq->data_len = pc->req_xfer;
-	}
-
-	memcpy(rq->cmd, pc->c, 12);
-	if (drive->media == ide_tape)
-		rq->cmd[13] = REQ_IDETAPE_PC1;
-
-	drive->hwif->rq = NULL;
-
-	elv_add_request(drive->queue, rq, ELEVATOR_INSERT_FRONT, 0);
-}
-
 /*
  * Add a special packet command request to the tail of the request queue,
  * and wait for it to be serviced.
@@ -119,19 +91,21 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
 	rq->cmd_type = REQ_TYPE_SPECIAL;
-	rq->buffer = (char *)pc;
+	rq->special = (char *)pc;
 
 	if (pc->req_xfer) {
-		rq->data = pc->buf;
-		rq->data_len = pc->req_xfer;
+		error = blk_rq_map_kern(drive->queue, rq, pc->buf, pc->req_xfer,
+					GFP_NOIO);
+		if (error)
+			goto put_req;
 	}
 
 	memcpy(rq->cmd, pc->c, 12);
 	if (drive->media == ide_tape)
 		rq->cmd[13] = REQ_IDETAPE_PC1;
 	error = blk_execute_rq(drive->queue, disk, rq, 0);
+put_req:
 	blk_put_request(rq);
-
 	return error;
 }
 EXPORT_SYMBOL_GPL(ide_queue_pc_tail);
@@ -191,20 +165,113 @@ void ide_create_request_sense_cmd(ide_drive_t *drive, struct ide_atapi_pc *pc)
 }
 EXPORT_SYMBOL_GPL(ide_create_request_sense_cmd);
 
+void ide_prep_sense(ide_drive_t *drive, struct request *rq)
+{
+	struct request_sense *sense = &drive->sense_data;
+	struct request *sense_rq = &drive->sense_rq;
+	unsigned int cmd_len, sense_len;
+	int err;
+
+	debug_log("%s: enter\n", __func__);
+
+	switch (drive->media) {
+	case ide_floppy:
+		cmd_len = 255;
+		sense_len = 18;
+		break;
+	case ide_tape:
+		cmd_len = 20;
+		sense_len = 20;
+		break;
+	default:
+		cmd_len = 18;
+		sense_len = 18;
+	}
+
+	BUG_ON(sense_len > sizeof(*sense));
+
+	if (blk_sense_request(rq) || drive->sense_rq_armed)
+		return;
+
+	memset(sense, 0, sizeof(*sense));
+
+	blk_rq_init(rq->q, sense_rq);
+
+	err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len,
+			      GFP_NOIO);
+	if (unlikely(err)) {
+		if (printk_ratelimit())
+			printk(KERN_WARNING "%s: failed to map sense buffer\n",
+			       drive->name);
+		return;
+	}
+
+	sense_rq->rq_disk = rq->rq_disk;
+	sense_rq->cmd[0] = GPCMD_REQUEST_SENSE;
+	sense_rq->cmd[4] = cmd_len;
+	sense_rq->cmd_type = REQ_TYPE_SENSE;
+	sense_rq->cmd_flags |= REQ_PREEMPT;
+
+	if (drive->media == ide_tape)
+		sense_rq->cmd[13] = REQ_IDETAPE_PC1;
+
+	drive->sense_rq_armed = true;
+}
+EXPORT_SYMBOL_GPL(ide_prep_sense);
+
+int ide_queue_sense_rq(ide_drive_t *drive, void *special)
+{
+	/* deferred failure from ide_prep_sense() */
+	if (!drive->sense_rq_armed) {
+		printk(KERN_WARNING "%s: failed queue sense request\n",
+		       drive->name);
+		return -ENOMEM;
+	}
+
+	drive->sense_rq.special = special;
+	drive->sense_rq_armed = false;
+
+	drive->hwif->rq = NULL;
+
+	elv_add_request(drive->queue, &drive->sense_rq,
+			ELEVATOR_INSERT_FRONT, 0);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
+
 /*
  * Called when an error was detected during the last packet command.
- * We queue a request sense packet command in the head of the request list.
+ * We queue a request sense packet command at the head of the request
+ * queue.
  */
-void ide_retry_pc(ide_drive_t *drive, struct gendisk *disk)
+void ide_retry_pc(ide_drive_t *drive)
 {
-	struct request *rq = &drive->request_sense_rq;
+	struct request *failed_rq = drive->hwif->rq;
+	struct request *sense_rq = &drive->sense_rq;
 	struct ide_atapi_pc *pc = &drive->request_sense_pc;
 
 	(void)ide_read_error(drive);
-	ide_create_request_sense_cmd(drive, pc);
+
+	/* init pc from sense_rq */
+	ide_init_pc(pc);
+	memcpy(pc->c, sense_rq->cmd, 12);
+	pc->buf = bio_data(sense_rq->bio);	/* pointer to mapped address */
+	pc->req_xfer = blk_rq_bytes(sense_rq);
+
 	if (drive->media == ide_tape)
 		set_bit(IDE_AFLAG_IGNORE_DSC, &drive->atapi_flags);
-	ide_queue_pc_head(drive, disk, pc, rq);
+
+	/*
+	 * Push back the failed request and put request sense on top
+	 * of it.  The failed command will be retried after sense data
+	 * is acquired.
+	 */
+	blk_requeue_request(failed_rq->q, failed_rq);
+	drive->hwif->rq = NULL;
+	if (ide_queue_sense_rq(drive, pc)) {
+		blk_start_request(failed_rq);
+		ide_complete_rq(drive, -EIO, blk_rq_bytes(failed_rq));
+	}
 }
 EXPORT_SYMBOL_GPL(ide_retry_pc);
 
@@ -246,7 +313,7 @@ int ide_cd_get_xferlen(struct request *rq)
 		return 32768;
 	else if (blk_sense_request(rq) || blk_pc_request(rq) ||
 			 rq->cmd_type == REQ_TYPE_ATA_PC)
-		return rq->data_len;
+		return blk_rq_bytes(rq);
 	else
 		return 0;
 }
@@ -276,7 +343,6 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 	struct ide_cmd *cmd = &hwif->cmd;
 	struct request *rq = hwif->rq;
 	const struct ide_tp_ops *tp_ops = hwif->tp_ops;
-	xfer_func_t *xferfunc;
 	unsigned int timeout, done;
 	u16 bcount;
 	u8 stat, ireason, dsc = 0;
@@ -303,18 +369,14 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 					drive->name, rq_data_dir(pc->rq)
 						     ? "write" : "read");
 			pc->flags |= PC_FLAG_DMA_ERROR;
-		} else {
+		} else
 			pc->xferred = pc->req_xfer;
-			if (drive->pc_update_buffers)
-				drive->pc_update_buffers(drive, pc);
-		}
 		debug_log("%s: DMA finished\n", drive->name);
 	}
 
 	/* No more interrupts */
 	if ((stat & ATA_DRQ) == 0) {
 		int uptodate, error;
-		unsigned int done;
 
 		debug_log("Packet command completed, %d bytes transferred\n",
 			  pc->xferred);
@@ -343,7 +405,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 			debug_log("[cmd %x]: check condition\n", rq->cmd[0]);
 
 			/* Retry operation */
-			ide_retry_pc(drive, rq->rq_disk);
+			ide_retry_pc(drive);
 
 			/* queued, but not started */
 			return ide_stopped;
@@ -353,6 +415,12 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		if ((pc->flags & PC_FLAG_WAIT_FOR_DSC) && (stat & ATA_DSC) == 0)
 			dsc = 1;
 
+		/*
+		 * ->pc_callback() might change rq->data_len for
+		 * residual count, cache total length.
+		 */
+		done = blk_rq_bytes(rq);
+
 		/* Command finished - Call the callback function */
 		uptodate = drive->pc_callback(drive, dsc);
 
@@ -361,7 +429,6 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 
 		if (blk_special_request(rq)) {
 			rq->errors = 0;
-			done = blk_rq_bytes(rq);
 			error = 0;
 		} else {
 
@@ -370,15 +437,10 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 					rq->errors = -EIO;
 			}
 
-			if (drive->media == ide_tape)
-				done = ide_rq_bytes(rq); /* FIXME */
-			else
-				done = blk_rq_bytes(rq);
-
 			error = uptodate ? 0 : -EIO;
 		}
 
-		ide_complete_rq(drive, error, done);
+		ide_complete_rq(drive, error, blk_rq_bytes(rq));
 		return ide_stopped;
 	}
 
@@ -407,21 +469,11 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		return ide_do_reset(drive);
 	}
 
-	xferfunc = write ? tp_ops->output_data : tp_ops->input_data;
+	done = min_t(unsigned int, bcount, cmd->nleft);
+	ide_pio_bytes(drive, cmd, write, done);
 
-	if (drive->media == ide_floppy && pc->buf == NULL) {
-		done = min_t(unsigned int, bcount, cmd->nleft);
-		ide_pio_bytes(drive, cmd, write, done);
-	} else if (drive->media == ide_tape && pc->bh) {
-		done = drive->pc_io_buffers(drive, pc, bcount, write);
-	} else {
-		done = min_t(unsigned int, bcount, pc->req_xfer - pc->xferred);
-		xferfunc(drive, NULL, pc->cur_pos, done);
-	}
-
-	/* Update the current position */
+	/* Update transferred byte count */
 	pc->xferred += done;
-	pc->cur_pos += done;
 
 	bcount -= done;
 
@@ -599,7 +651,6 @@ ide_startstop_t ide_issue_pc(ide_drive_t *drive, struct ide_cmd *cmd)
 
 		/* We haven't transferred any data yet */
 		pc->xferred = 0;
-		pc->cur_pos = pc->buf;
 
 		valid_tf = IDE_VALID_DEVICE;
 		bcount = ((drive->media == ide_tape) ?
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 925eb9e245d1..424140c6c400 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -182,7 +182,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 				 (sense->information[2] <<  8) |
 				 (sense->information[3]);
 
-			if (drive->queue->hardsect_size == 2048)
+			if (queue_logical_block_size(drive->queue) == 2048)
 				/* device sector size is 2K */
 				sector <<= 2;
 
@@ -206,54 +206,25 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 	ide_cd_log_error(drive->name, failed_command, sense);
 }
 
-static void cdrom_queue_request_sense(ide_drive_t *drive, void *sense,
-				      struct request *failed_command)
-{
-	struct cdrom_info *info		= drive->driver_data;
-	struct request *rq		= &drive->request_sense_rq;
-
-	ide_debug_log(IDE_DBG_SENSE, "enter");
-
-	if (sense == NULL)
-		sense = &info->sense_data;
-
-	/* stuff the sense request in front of our current request */
-	blk_rq_init(NULL, rq);
-	rq->cmd_type = REQ_TYPE_ATA_PC;
-	rq->rq_disk = info->disk;
-
-	rq->data = sense;
-	rq->cmd[0] = GPCMD_REQUEST_SENSE;
-	rq->cmd[4] = 18;
-	rq->data_len = 18;
-
-	rq->cmd_type = REQ_TYPE_SENSE;
-	rq->cmd_flags |= REQ_PREEMPT;
-
-	/* NOTE! Save the failed command in "rq->buffer" */
-	rq->buffer = (void *) failed_command;
-
-	if (failed_command)
-		ide_debug_log(IDE_DBG_SENSE, "failed_cmd: 0x%x",
-					     failed_command->cmd[0]);
-
-	drive->hwif->rq = NULL;
-
-	elv_add_request(drive->queue, rq, ELEVATOR_INSERT_FRONT, 0);
-}
-
 static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
 {
 	/*
-	 * For REQ_TYPE_SENSE, "rq->buffer" points to the original
-	 * failed request
+	 * For REQ_TYPE_SENSE, "rq->special" points to the original
+	 * failed request.  Also, the sense data should be read
+	 * directly from rq which might be different from the original
+	 * sense buffer if it got copied during mapping.
 	 */
-	struct request *failed = (struct request *)rq->buffer;
-	struct cdrom_info *info = drive->driver_data;
-	void *sense = &info->sense_data;
+	struct request *failed = (struct request *)rq->special;
+	void *sense = bio_data(rq->bio);
 
 	if (failed) {
 		if (failed->sense) {
+			/*
+			 * Sense is always read into drive->sense_data.
+			 * Copy back if the failed request has its
+			 * sense pointer set.
+			 */
+			memcpy(failed->sense, sense, 18);
 			sense = failed->sense;
 			failed->sense_len = rq->sense_len;
 		}
@@ -428,22 +399,13 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 
 	/* if we got a CHECK_CONDITION status, queue a request sense command */
 	if (stat & ATA_ERR)
-		cdrom_queue_request_sense(drive, NULL, NULL);
+		return ide_queue_sense_rq(drive, NULL) ? 2 : 1;
 	return 1;
 
 end_request:
 	if (stat & ATA_ERR) {
-		struct request_queue *q = drive->queue;
-		unsigned long flags;
-
-		spin_lock_irqsave(q->queue_lock, flags);
-		blkdev_dequeue_request(rq);
-		spin_unlock_irqrestore(q->queue_lock, flags);
-
 		hwif->rq = NULL;
-
-		cdrom_queue_request_sense(drive, rq->sense, rq);
-		return 1;
+		return ide_queue_sense_rq(drive, rq) ? 2 : 1;
 	} else
 		return 2;
 }
@@ -503,14 +465,8 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd)
 	 * and some drives don't send them.  Sigh.
 	 */
 	if (rq->cmd[0] == GPCMD_REQUEST_SENSE &&
-	    cmd->nleft > 0 && cmd->nleft <= 5) {
-		unsigned int ofs = cmd->nbytes - cmd->nleft;
-
-		while (cmd->nleft > 0) {
-			*((u8 *)rq->data + ofs++) = 0;
-			cmd->nleft--;
-		}
-	}
+	    cmd->nleft > 0 && cmd->nleft <= 5)
+		cmd->nleft = 0;
 }
 
 int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
@@ -543,14 +499,18 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		rq->cmd_flags |= cmd_flags;
 		rq->timeout = timeout;
 		if (buffer) {
-			rq->data = buffer;
-			rq->data_len = *bufflen;
+			error = blk_rq_map_kern(drive->queue, rq, buffer,
+						*bufflen, GFP_NOIO);
+			if (error) {
+				blk_put_request(rq);
+				return error;
+			}
 		}
 
 		error = blk_execute_rq(drive->queue, info->disk, rq, 0);
 
 		if (buffer)
-			*bufflen = rq->data_len;
+			*bufflen = rq->resid_len;
 
 		flags = rq->cmd_flags;
 		blk_put_request(rq);
@@ -608,7 +568,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	struct request *rq = hwif->rq;
 	ide_expiry_t *expiry = NULL;
 	int dma_error = 0, dma, thislen, uptodate = 0;
-	int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0, nsectors;
+	int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0;
 	int sense = blk_sense_request(rq);
 	unsigned int timeout;
 	u16 len;
@@ -738,13 +698,8 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 
 out_end:
 	if (blk_pc_request(rq) && rc == 0) {
-		unsigned int dlen = rq->data_len;
-
-		rq->data_len = 0;
-
-		if (blk_end_request(rq, 0, dlen))
-			BUG();
-
+		rq->resid_len = 0;
+		blk_end_request_all(rq, 0);
 		hwif->rq = NULL;
 	} else {
 		if (sense && uptodate)
@@ -762,21 +717,13 @@ out_end:
 			ide_cd_error_cmd(drive, cmd);
 
 		/* make sure it's fully ended */
-		if (blk_pc_request(rq))
-			nsectors = (rq->data_len + 511) >> 9;
-		else
-			nsectors = rq->hard_nr_sectors;
-
-		if (nsectors == 0)
-			nsectors = 1;
-
 		if (blk_fs_request(rq) == 0) {
-			rq->data_len -= (cmd->nbytes - cmd->nleft);
+			rq->resid_len -= cmd->nbytes - cmd->nleft;
 			if (uptodate == 0 && (cmd->tf_flags & IDE_TFLAG_WRITE))
-				rq->data_len += cmd->last_xfer_len;
+				rq->resid_len += cmd->last_xfer_len;
 		}
 
-		ide_complete_rq(drive, uptodate ? 0 : -EIO, nsectors << 9);
+		ide_complete_rq(drive, uptodate ? 0 : -EIO, blk_rq_bytes(rq));
 
 		if (sense && rc == 2)
 			ide_error(drive, "request sense failure", stat);
@@ -790,7 +737,7 @@ static ide_startstop_t cdrom_start_rw(ide_drive_t *drive, struct request *rq)
 	struct request_queue *q = drive->queue;
 	int write = rq_data_dir(rq) == WRITE;
 	unsigned short sectors_per_frame =
-		queue_hardsect_size(q) >> SECTOR_BITS;
+		queue_logical_block_size(q) >> SECTOR_BITS;
 
 	ide_debug_log(IDE_DBG_RQ, "rq->cmd[0]: 0x%x, rq->cmd_flags: 0x%x, "
 				  "secs_per_frame: %u",
@@ -809,8 +756,8 @@ static ide_startstop_t cdrom_start_rw(ide_drive_t *drive, struct request *rq)
 	}
 
 	/* fs requests *must* be hardware frame aligned */
-	if ((rq->nr_sectors & (sectors_per_frame - 1)) ||
-	    (rq->sector & (sectors_per_frame - 1)))
+	if ((blk_rq_sectors(rq) & (sectors_per_frame - 1)) ||
+	    (blk_rq_pos(rq) & (sectors_per_frame - 1)))
 		return ide_stopped;
 
 	/* use DMA, if possible */
@@ -838,15 +785,10 @@ static void cdrom_do_block_pc(ide_drive_t *drive, struct request *rq)
 	drive->dma = 0;
 
 	/* sg request */
-	if (rq->bio || ((rq->cmd_type == REQ_TYPE_ATA_PC) && rq->data_len)) {
+	if (rq->bio) {
 		struct request_queue *q = drive->queue;
+		char *buf = bio_data(rq->bio);
 		unsigned int alignment;
-		char *buf;
-
-		if (rq->bio)
-			buf = bio_data(rq->bio);
-		else
-			buf = rq->data;
 
 		drive->dma = !!(drive->dev_flags & IDE_DFLAG_USING_DMA);
 
@@ -858,7 +800,7 @@ static void cdrom_do_block_pc(ide_drive_t *drive, struct request *rq)
 		 */
 		alignment = queue_dma_alignment(q) | q->dma_pad_mask;
 		if ((unsigned long)buf & alignment
-		    || rq->data_len & q->dma_pad_mask
+		    || blk_rq_bytes(rq) & q->dma_pad_mask
 		    || object_is_on_stack(buf))
 			drive->dma = 0;
 	}
@@ -896,6 +838,9 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 		goto out_end;
 	}
 
+	/* prepare sense request for this command */
+	ide_prep_sense(drive, rq);
+
 	memset(&cmd, 0, sizeof(cmd));
 
 	if (rq_data_dir(rq))
@@ -903,15 +848,14 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 
 	cmd.rq = rq;
 
-	if (blk_fs_request(rq) || rq->data_len) {
-		ide_init_sg_cmd(&cmd, blk_fs_request(rq) ? (rq->nr_sectors << 9)
-							 : rq->data_len);
+	if (blk_fs_request(rq) || blk_rq_bytes(rq)) {
+		ide_init_sg_cmd(&cmd, blk_rq_bytes(rq));
 		ide_map_sg(drive, &cmd);
 	}
 
 	return ide_issue_pc(drive, &cmd);
 out_end:
-	nsectors = rq->hard_nr_sectors;
+	nsectors = blk_rq_sectors(rq);
 
 	if (nsectors == 0)
 		nsectors = 1;
@@ -1077,8 +1021,8 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	/* save a private copy of the TOC capacity for error handling */
 	drive->probed_capacity = toc->capacity * sectors_per_frame;
 
-	blk_queue_hardsect_size(drive->queue,
-				sectors_per_frame << SECTOR_BITS);
+	blk_queue_logical_block_size(drive->queue,
+				     sectors_per_frame << SECTOR_BITS);
 
 	/* first read just the header, so we know how long the TOC is */
 	stat = cdrom_read_tocentry(drive, 0, 1, 0, (char *) &toc->hdr,
@@ -1394,9 +1338,9 @@ static int ide_cdrom_probe_capabilities(ide_drive_t *drive)
 /* standard prep_rq_fn that builds 10 byte cmds */
 static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
 {
-	int hard_sect = queue_hardsect_size(q);
-	long block = (long)rq->hard_sector / (hard_sect >> 9);
-	unsigned long blocks = rq->hard_nr_sectors / (hard_sect >> 9);
+	int hard_sect = queue_logical_block_size(q);
+	long block = (long)blk_rq_pos(rq) / (hard_sect >> 9);
+	unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9);
 
 	memset(rq->cmd, 0, BLK_MAX_CDB);
 
@@ -1599,7 +1543,7 @@ static int ide_cdrom_setup(ide_drive_t *drive)
 
 	nslots = ide_cdrom_probe_capabilities(drive);
 
-	blk_queue_hardsect_size(q, CD_FRAMESIZE);
+	blk_queue_logical_block_size(q, CD_FRAMESIZE);
 
 	if (ide_cdrom_register(drive, nslots)) {
 		printk(KERN_ERR PFX "%s: %s failed to register device with the"
diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h
index 1d97101099ce..93a3cf1b0f3f 100644
--- a/drivers/ide/ide-cd.h
+++ b/drivers/ide/ide-cd.h
@@ -87,10 +87,6 @@ struct cdrom_info {
 
 	struct atapi_toc *toc;
 
-	/* The result of the last successful request sense command
-	   on this device. */
-	struct request_sense sense_data;
-
 	u8 max_speed;		/* Max speed of the drive. */
 	u8 current_speed;	/* Current speed of the drive. */
 
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index a9fbe2c31210..c6f7fcfb9d67 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -82,7 +82,7 @@ static ide_startstop_t __ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
 					sector_t block)
 {
 	ide_hwif_t *hwif	= drive->hwif;
-	u16 nsectors		= (u16)rq->nr_sectors;
+	u16 nsectors		= (u16)blk_rq_sectors(rq);
 	u8 lba48		= !!(drive->dev_flags & IDE_DFLAG_LBA48);
 	u8 dma			= !!(drive->dev_flags & IDE_DFLAG_USING_DMA);
 	struct ide_cmd		cmd;
@@ -90,7 +90,7 @@ static ide_startstop_t __ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
 	ide_startstop_t		rc;
 
 	if ((hwif->host_flags & IDE_HFLAG_NO_LBA48_DMA) && lba48 && dma) {
-		if (block + rq->nr_sectors > 1ULL << 28)
+		if (block + blk_rq_sectors(rq) > 1ULL << 28)
 			dma = 0;
 		else
 			lba48 = 0;
@@ -195,9 +195,9 @@ static ide_startstop_t ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
 
 	ledtrig_ide_activity();
 
-	pr_debug("%s: %sing: block=%llu, sectors=%lu, buffer=0x%08lx\n",
+	pr_debug("%s: %sing: block=%llu, sectors=%u, buffer=0x%08lx\n",
 		 drive->name, rq_data_dir(rq) == READ ? "read" : "writ",
-		 (unsigned long long)block, rq->nr_sectors,
+		 (unsigned long long)block, blk_rq_sectors(rq),
 		 (unsigned long)rq->buffer);
 
 	if (hwif->rw_disk)
@@ -411,7 +411,6 @@ static void idedisk_prepare_flush(struct request_queue *q, struct request *rq)
 	cmd->protocol = ATA_PROT_NODATA;
 
 	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
-	rq->cmd_flags |= REQ_SOFTBARRIER;
 	rq->special = cmd;
 }
 
@@ -640,7 +639,7 @@ static void ide_disk_setup(ide_drive_t *drive)
 	}
 
 	printk(KERN_INFO "%s: max request size: %dKiB\n", drive->name,
-		q->max_sectors / 2);
+	       queue_max_sectors(q) / 2);
 
 	if (ata_id_is_ssd(id))
 		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c
index a0b8cab1d9a6..001f68f0bb28 100644
--- a/drivers/ide/ide-dma.c
+++ b/drivers/ide/ide-dma.c
@@ -103,7 +103,7 @@ ide_startstop_t ide_dma_intr(ide_drive_t *drive)
 				ide_finish_cmd(drive, cmd, stat);
 			else
 				ide_complete_rq(drive, 0,
-						cmd->rq->nr_sectors << 9);
+						blk_rq_sectors(cmd->rq) << 9);
 			return ide_stopped;
 		}
 		printk(KERN_ERR "%s: %s: bad DMA status (0x%02x)\n",
@@ -510,23 +510,11 @@ ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error)
 	/*
 	 * un-busy drive etc and make sure request is sane
 	 */
-
 	rq = hwif->rq;
-	if (!rq)
-		goto out;
-
-	hwif->rq = NULL;
-
-	rq->errors = 0;
-
-	if (!rq->bio)
-		goto out;
-
-	rq->sector = rq->bio->bi_sector;
-	rq->current_nr_sectors = bio_iovec(rq->bio)->bv_len >> 9;
-	rq->hard_cur_sectors = rq->current_nr_sectors;
-	rq->buffer = bio_data(rq->bio);
-out:
+	if (rq) {
+		hwif->rq = NULL;
+		rq->errors = 0;
+	}
 	return ret;
 }
 
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 2b4868d95f8b..650981758f15 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -134,13 +134,17 @@ static ide_startstop_t ide_floppy_issue_pc(ide_drive_t *drive,
 	drive->pc = pc;
 
 	if (pc->retries > IDEFLOPPY_MAX_PC_RETRIES) {
+		unsigned int done = blk_rq_bytes(drive->hwif->rq);
+
 		if (!(pc->flags & PC_FLAG_SUPPRESS_ERROR))
 			ide_floppy_report_error(floppy, pc);
+
 		/* Giving up */
 		pc->error = IDE_DRV_ERROR_GENERAL;
 
 		drive->failed_pc = NULL;
 		drive->pc_callback(drive, 0);
+		ide_complete_rq(drive, -EIO, done);
 		return ide_stopped;
 	}
 
@@ -190,7 +194,7 @@ static void idefloppy_create_rw_cmd(ide_drive_t *drive,
 {
 	struct ide_disk_obj *floppy = drive->driver_data;
 	int block = sector / floppy->bs_factor;
-	int blocks = rq->nr_sectors / floppy->bs_factor;
+	int blocks = blk_rq_sectors(rq) / floppy->bs_factor;
 	int cmd = rq_data_dir(rq);
 
 	ide_debug_log(IDE_DBG_FUNC, "block: %d, blocks: %d", block, blocks);
@@ -216,16 +220,14 @@ static void idefloppy_blockpc_cmd(struct ide_disk_obj *floppy,
 	ide_init_pc(pc);
 	memcpy(pc->c, rq->cmd, sizeof(pc->c));
 	pc->rq = rq;
-	if (rq->data_len && rq_data_dir(rq) == WRITE)
-		pc->flags |= PC_FLAG_WRITING;
-	pc->buf = rq->data;
-	if (rq->bio)
+	if (blk_rq_bytes(rq)) {
 		pc->flags |= PC_FLAG_DMA_OK;
-	/*
-	 * possibly problematic, doesn't look like ide-floppy correctly
-	 * handled scattered requests if dma fails...
-	 */
-	pc->req_xfer = pc->buf_size = rq->data_len;
+		if (rq_data_dir(rq) == WRITE)
+			pc->flags |= PC_FLAG_WRITING;
+	}
+	/* pio will be performed by ide_pio_bytes() which handles sg fine */
+	pc->buf = NULL;
+	pc->req_xfer = pc->buf_size = blk_rq_bytes(rq);
 }
 
 static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
@@ -257,16 +259,16 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 			goto out_end;
 	}
 	if (blk_fs_request(rq)) {
-		if (((long)rq->sector % floppy->bs_factor) ||
-		    (rq->nr_sectors % floppy->bs_factor)) {
+		if (((long)blk_rq_pos(rq) % floppy->bs_factor) ||
+		    (blk_rq_sectors(rq) % floppy->bs_factor)) {
 			printk(KERN_ERR PFX "%s: unsupported r/w rq size\n",
 				drive->name);
 			goto out_end;
 		}
 		pc = &floppy->queued_pc;
 		idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block);
-	} else if (blk_special_request(rq)) {
-		pc = (struct ide_atapi_pc *) rq->buffer;
+	} else if (blk_special_request(rq) || blk_sense_request(rq)) {
+		pc = (struct ide_atapi_pc *)rq->special;
 	} else if (blk_pc_request(rq)) {
 		pc = &floppy->queued_pc;
 		idefloppy_blockpc_cmd(floppy, pc, rq);
@@ -275,6 +277,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		goto out_end;
 	}
 
+	ide_prep_sense(drive, rq);
+
 	memset(&cmd, 0, sizeof(cmd));
 
 	if (rq_data_dir(rq))
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 6415a2e2ba87..bba4297f2f03 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -116,9 +116,9 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err)
 unsigned int ide_rq_bytes(struct request *rq)
 {
 	if (blk_pc_request(rq))
-		return rq->data_len;
+		return blk_rq_bytes(rq);
 	else
-		return rq->hard_cur_sectors << 9;
+		return blk_rq_cur_sectors(rq) << 9;
 }
 EXPORT_SYMBOL_GPL(ide_rq_bytes);
 
@@ -133,7 +133,7 @@ int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes)
 	 * and complete the whole request right now
 	 */
 	if (blk_noretry_request(rq) && error <= 0)
-		nr_bytes = rq->hard_nr_sectors << 9;
+		nr_bytes = blk_rq_sectors(rq) << 9;
 
 	rc = ide_end_rq(drive, rq, error, nr_bytes);
 	if (rc == 0)
@@ -248,14 +248,7 @@ void ide_map_sg(ide_drive_t *drive, struct ide_cmd *cmd)
 	struct scatterlist *sg = hwif->sg_table;
 	struct request *rq = cmd->rq;
 
-	if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE) {
-		sg_init_one(sg, rq->buffer, rq->nr_sectors * SECTOR_SIZE);
-		cmd->sg_nents = 1;
-	} else if (!rq->bio) {
-		sg_init_one(sg, rq->data, rq->data_len);
-		cmd->sg_nents = 1;
-	} else
-		cmd->sg_nents = blk_rq_map_sg(drive->queue, rq, sg);
+	cmd->sg_nents = blk_rq_map_sg(drive->queue, rq, sg);
 }
 EXPORT_SYMBOL_GPL(ide_map_sg);
 
@@ -286,7 +279,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
 
 	if (cmd) {
 		if (cmd->protocol == ATA_PROT_PIO) {
-			ide_init_sg_cmd(cmd, rq->nr_sectors << 9);
+			ide_init_sg_cmd(cmd, blk_rq_sectors(rq) << 9);
 			ide_map_sg(drive, cmd);
 		}
 
@@ -371,7 +364,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 		if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE)
 			return execute_drive_cmd(drive, rq);
 		else if (blk_pm_request(rq)) {
-			struct request_pm_state *pm = rq->data;
+			struct request_pm_state *pm = rq->special;
 #ifdef DEBUG_PM
 			printk("%s: start_power_step(step: %d)\n",
 				drive->name, pm->pm_step);
@@ -394,7 +387,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 
 		drv = *(struct ide_driver **)rq->rq_disk->private_data;
 
-		return drv->do_request(drive, rq, rq->sector);
+		return drv->do_request(drive, rq, blk_rq_pos(rq));
 	}
 	return do_special(drive);
 kill_rq:
@@ -484,6 +477,9 @@ void do_ide_request(struct request_queue *q)
 
 	spin_unlock_irq(q->queue_lock);
 
+	/* HLD do_request() callback might sleep, make sure it's okay */
+	might_sleep();
+
 	if (ide_lock_host(host, hwif))
 		goto plug_device_2;
 
@@ -491,10 +487,10 @@ void do_ide_request(struct request_queue *q)
 
 	if (!ide_lock_port(hwif)) {
 		ide_hwif_t *prev_port;
+
+		WARN_ON_ONCE(hwif->rq);
 repeat:
 		prev_port = hwif->host->cur_port;
-		hwif->rq = NULL;
-
 		if (drive->dev_flags & IDE_DFLAG_SLEEPING &&
 		    time_after(drive->sleep, jiffies)) {
 			ide_unlock_port(hwif);
@@ -523,7 +519,9 @@ repeat:
 		 * we know that the queue isn't empty, but this can happen
 		 * if the q->prep_rq_fn() decides to kill a request
 		 */
-		rq = elv_next_request(drive->queue);
+		if (!rq)
+			rq = blk_fetch_request(drive->queue);
+
 		spin_unlock_irq(q->queue_lock);
 		spin_lock_irq(&hwif->lock);
 
@@ -535,7 +533,7 @@ repeat:
 		/*
 		 * Sanity: don't accept a request that isn't a PM request
 		 * if we are currently power managed. This is very important as
-		 * blk_stop_queue() doesn't prevent the elv_next_request()
+		 * blk_stop_queue() doesn't prevent the blk_fetch_request()
 		 * above to return us whatever is in the queue. Since we call
 		 * ide_do_request() ourselves, we end up taking requests while
 		 * the queue is blocked...
@@ -559,8 +557,11 @@ repeat:
 		startstop = start_request(drive, rq);
 		spin_lock_irq(&hwif->lock);
 
-		if (startstop == ide_stopped)
+		if (startstop == ide_stopped) {
+			rq = hwif->rq;
+			hwif->rq = NULL;
 			goto repeat;
+		}
 	} else
 		goto plug_device;
 out:
@@ -576,18 +577,24 @@ plug_device:
 plug_device_2:
 	spin_lock_irq(q->queue_lock);
 
+	if (rq)
+		blk_requeue_request(q, rq);
 	if (!elv_queue_empty(q))
 		blk_plug_device(q);
 }
 
-static void ide_plug_device(ide_drive_t *drive)
+static void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq)
 {
 	struct request_queue *q = drive->queue;
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
+
+	if (rq)
+		blk_requeue_request(q, rq);
 	if (!elv_queue_empty(q))
 		blk_plug_device(q);
+
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
@@ -636,6 +643,7 @@ void ide_timer_expiry (unsigned long data)
 	unsigned long	flags;
 	int		wait = -1;
 	int		plug_device = 0;
+	struct request	*uninitialized_var(rq_in_flight);
 
 	spin_lock_irqsave(&hwif->lock, flags);
 
@@ -697,6 +705,8 @@ void ide_timer_expiry (unsigned long data)
 		spin_lock_irq(&hwif->lock);
 		enable_irq(hwif->irq);
 		if (startstop == ide_stopped && hwif->polling == 0) {
+			rq_in_flight = hwif->rq;
+			hwif->rq = NULL;
 			ide_unlock_port(hwif);
 			plug_device = 1;
 		}
@@ -705,7 +715,7 @@ void ide_timer_expiry (unsigned long data)
 
 	if (plug_device) {
 		ide_unlock_host(hwif->host);
-		ide_plug_device(drive);
+		ide_requeue_and_plug(drive, rq_in_flight);
 	}
 }
 
@@ -791,6 +801,7 @@ irqreturn_t ide_intr (int irq, void *dev_id)
 	ide_startstop_t startstop;
 	irqreturn_t irq_ret = IRQ_NONE;
 	int plug_device = 0;
+	struct request *uninitialized_var(rq_in_flight);
 
 	if (host->host_flags & IDE_HFLAG_SERIALIZE) {
 		if (hwif != host->cur_port)
@@ -870,6 +881,8 @@ irqreturn_t ide_intr (int irq, void *dev_id)
 	 */
 	if (startstop == ide_stopped && hwif->polling == 0) {
 		BUG_ON(hwif->handler);
+		rq_in_flight = hwif->rq;
+		hwif->rq = NULL;
 		ide_unlock_port(hwif);
 		plug_device = 1;
 	}
@@ -879,7 +892,7 @@ out:
 out_early:
 	if (plug_device) {
 		ide_unlock_host(hwif->host);
-		ide_plug_device(drive);
+		ide_requeue_and_plug(drive, rq_in_flight);
 	}
 
 	return irq_ret;
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index c1c25ebbaa1f..5991b23793f2 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -231,7 +231,6 @@ static int generic_drive_reset(ide_drive_t *drive)
 	rq->cmd_type = REQ_TYPE_SPECIAL;
 	rq->cmd_len = 1;
 	rq->cmd[0] = REQ_DRIVE_RESET;
-	rq->cmd_flags |= REQ_SOFTBARRIER;
 	if (blk_execute_rq(drive->queue, NULL, rq, 1))
 		ret = rq->errors;
 	blk_put_request(rq);
diff --git a/drivers/ide/ide-lib.c b/drivers/ide/ide-lib.c
index 2148df836ce7..e386a32dc9ba 100644
--- a/drivers/ide/ide-lib.c
+++ b/drivers/ide/ide-lib.c
@@ -96,7 +96,7 @@ static void ide_dump_ata_error(ide_drive_t *drive, u8 err)
 
 		if (rq)
 			printk(KERN_CONT ", sector=%llu",
-			       (unsigned long long)rq->sector);
+			       (unsigned long long)blk_rq_pos(rq));
 	}
 	printk(KERN_CONT "\n");
 }
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index 310d03f2b5b7..a914023d6d03 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -24,11 +24,8 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 			start_queue = 1;
 		spin_unlock_irq(&hwif->lock);
 
-		if (start_queue) {
-			spin_lock_irq(q->queue_lock);
-			blk_start_queueing(q);
-			spin_unlock_irq(q->queue_lock);
-		}
+		if (start_queue)
+			blk_run_queue(q);
 		return;
 	}
 	spin_unlock_irq(&hwif->lock);
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index 0d8a151c0a01..ba1488bd8430 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -7,7 +7,6 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	ide_hwif_t *hwif = drive->hwif;
 	struct request *rq;
 	struct request_pm_state rqpm;
-	struct ide_cmd cmd;
 	int ret;
 
 	/* call ACPI _GTM only once */
@@ -15,11 +14,9 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 		ide_acpi_get_timing(hwif);
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	memset(&cmd, 0, sizeof(cmd));
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
 	rq->cmd_type = REQ_TYPE_PM_SUSPEND;
-	rq->special = &cmd;
-	rq->data = &rqpm;
+	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_SUSPEND;
 	if (mesg.event == PM_EVENT_PRETHAW)
 		mesg.event = PM_EVENT_FREEZE;
@@ -41,7 +38,6 @@ int generic_ide_resume(struct device *dev)
 	ide_hwif_t *hwif = drive->hwif;
 	struct request *rq;
 	struct request_pm_state rqpm;
-	struct ide_cmd cmd;
 	int err;
 
 	/* call ACPI _PS0 / _STM only once */
@@ -53,12 +49,10 @@ int generic_ide_resume(struct device *dev)
 	ide_acpi_exec_tfs(drive);
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	memset(&cmd, 0, sizeof(cmd));
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
 	rq->cmd_type = REQ_TYPE_PM_RESUME;
 	rq->cmd_flags |= REQ_PREEMPT;
-	rq->special = &cmd;
-	rq->data = &rqpm;
+	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_RESUME;
 	rqpm.pm_state = PM_EVENT_ON;
 
@@ -77,7 +71,7 @@ int generic_ide_resume(struct device *dev)
 
 void ide_complete_power_step(ide_drive_t *drive, struct request *rq)
 {
-	struct request_pm_state *pm = rq->data;
+	struct request_pm_state *pm = rq->special;
 
 #ifdef DEBUG_PM
 	printk(KERN_INFO "%s: complete_power_step(step: %d)\n",
@@ -107,10 +101,8 @@ void ide_complete_power_step(ide_drive_t *drive, struct request *rq)
 
 ide_startstop_t ide_start_power_step(ide_drive_t *drive, struct request *rq)
 {
-	struct request_pm_state *pm = rq->data;
-	struct ide_cmd *cmd = rq->special;
-
-	memset(cmd, 0, sizeof(*cmd));
+	struct request_pm_state *pm = rq->special;
+	struct ide_cmd cmd = { };
 
 	switch (pm->pm_step) {
 	case IDE_PM_FLUSH_CACHE:	/* Suspend step 1 (flush cache) */
@@ -123,12 +115,12 @@ ide_startstop_t ide_start_power_step(ide_drive_t *drive, struct request *rq)
 			return ide_stopped;
 		}
 		if (ata_id_flush_ext_enabled(drive->id))
-			cmd->tf.command = ATA_CMD_FLUSH_EXT;
+			cmd.tf.command = ATA_CMD_FLUSH_EXT;
 		else
-			cmd->tf.command = ATA_CMD_FLUSH;
+			cmd.tf.command = ATA_CMD_FLUSH;
 		goto out_do_tf;
 	case IDE_PM_STANDBY:		/* Suspend step 2 (standby) */
-		cmd->tf.command = ATA_CMD_STANDBYNOW1;
+		cmd.tf.command = ATA_CMD_STANDBYNOW1;
 		goto out_do_tf;
 	case IDE_PM_RESTORE_PIO:	/* Resume step 1 (restore PIO) */
 		ide_set_max_pio(drive);
@@ -141,7 +133,7 @@ ide_startstop_t ide_start_power_step(ide_drive_t *drive, struct request *rq)
 			ide_complete_power_step(drive, rq);
 		return ide_stopped;
 	case IDE_PM_IDLE:		/* Resume step 2 (idle) */
-		cmd->tf.command = ATA_CMD_IDLEIMMEDIATE;
+		cmd.tf.command = ATA_CMD_IDLEIMMEDIATE;
 		goto out_do_tf;
 	case IDE_PM_RESTORE_DMA:	/* Resume step 3 (restore DMA) */
 		/*
@@ -163,11 +155,11 @@ ide_startstop_t ide_start_power_step(ide_drive_t *drive, struct request *rq)
 	return ide_stopped;
 
 out_do_tf:
-	cmd->valid.out.tf = IDE_VALID_OUT_TF | IDE_VALID_DEVICE;
-	cmd->valid.in.tf  = IDE_VALID_IN_TF  | IDE_VALID_DEVICE;
-	cmd->protocol = ATA_PROT_NODATA;
+	cmd.valid.out.tf = IDE_VALID_OUT_TF | IDE_VALID_DEVICE;
+	cmd.valid.in.tf  = IDE_VALID_IN_TF  | IDE_VALID_DEVICE;
+	cmd.protocol = ATA_PROT_NODATA;
 
-	return do_rw_taskfile(drive, cmd);
+	return do_rw_taskfile(drive, &cmd);
 }
 
 /**
@@ -181,7 +173,7 @@ out_do_tf:
 void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 {
 	struct request_queue *q = drive->queue;
-	struct request_pm_state *pm = rq->data;
+	struct request_pm_state *pm = rq->special;
 	unsigned long flags;
 
 	ide_complete_power_step(drive, rq);
@@ -207,7 +199,7 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 
 void ide_check_pm_state(ide_drive_t *drive, struct request *rq)
 {
-	struct request_pm_state *pm = rq->data;
+	struct request_pm_state *pm = rq->special;
 
 	if (blk_pm_suspend_request(rq) &&
 	    pm->pm_step == IDE_PM_START_SUSPEND)
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 3a53e0834cf7..d9764f0bc82f 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -131,13 +131,6 @@ enum {
 	IDETAPE_DIR_WRITE = (1 << 2),
 };
 
-struct idetape_bh {
-	u32 b_size;
-	atomic_t b_count;
-	struct idetape_bh *b_reqnext;
-	char *b_data;
-};
-
 /* Tape door status */
 #define DOOR_UNLOCKED			0
 #define DOOR_LOCKED			1
@@ -219,18 +212,12 @@ typedef struct ide_tape_obj {
 
 	/* Data buffer size chosen based on the tape's recommendation */
 	int buffer_size;
-	/* merge buffer */
-	struct idetape_bh *merge_bh;
-	/* size of the merge buffer */
-	int merge_bh_size;
-	/* pointer to current buffer head within the merge buffer */
-	struct idetape_bh *bh;
-	char *b_data;
-	int b_count;
-
-	int pages_per_buffer;
-	/* Wasted space in each stage */
-	int excess_bh_size;
+	/* Staging buffer of buffer_size bytes */
+	void *buf;
+	/* The read/write cursor */
+	void *cur;
+	/* The number of valid bytes in buf */
+	size_t valid;
 
 	/* Measures average tape speed */
 	unsigned long avg_time;
@@ -297,84 +284,6 @@ static struct ide_tape_obj *ide_tape_chrdev_get(unsigned int i)
 	return tape;
 }
 
-static int idetape_input_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
-				  unsigned int bcount)
-{
-	struct idetape_bh *bh = pc->bh;
-	int count;
-
-	while (bcount) {
-		if (bh == NULL)
-			break;
-		count = min(
-			(unsigned int)(bh->b_size - atomic_read(&bh->b_count)),
-			bcount);
-		drive->hwif->tp_ops->input_data(drive, NULL, bh->b_data +
-					atomic_read(&bh->b_count), count);
-		bcount -= count;
-		atomic_add(count, &bh->b_count);
-		if (atomic_read(&bh->b_count) == bh->b_size) {
-			bh = bh->b_reqnext;
-			if (bh)
-				atomic_set(&bh->b_count, 0);
-		}
-	}
-
-	pc->bh = bh;
-
-	return bcount;
-}
-
-static int idetape_output_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
-				   unsigned int bcount)
-{
-	struct idetape_bh *bh = pc->bh;
-	int count;
-
-	while (bcount) {
-		if (bh == NULL)
-			break;
-		count = min((unsigned int)pc->b_count, (unsigned int)bcount);
-		drive->hwif->tp_ops->output_data(drive, NULL, pc->b_data, count);
-		bcount -= count;
-		pc->b_data += count;
-		pc->b_count -= count;
-		if (!pc->b_count) {
-			bh = bh->b_reqnext;
-			pc->bh = bh;
-			if (bh) {
-				pc->b_data = bh->b_data;
-				pc->b_count = atomic_read(&bh->b_count);
-			}
-		}
-	}
-
-	return bcount;
-}
-
-static void idetape_update_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc)
-{
-	struct idetape_bh *bh = pc->bh;
-	int count;
-	unsigned int bcount = pc->xferred;
-
-	if (pc->flags & PC_FLAG_WRITING)
-		return;
-	while (bcount) {
-		if (bh == NULL) {
-			printk(KERN_ERR "ide-tape: bh == NULL in %s\n",
-					__func__);
-			return;
-		}
-		count = min((unsigned int)bh->b_size, (unsigned int)bcount);
-		atomic_set(&bh->b_count, count);
-		if (atomic_read(&bh->b_count) == bh->b_size)
-			bh = bh->b_reqnext;
-		bcount -= count;
-	}
-	pc->bh = bh;
-}
-
 /*
  * called on each failed packet command retry to analyze the request sense. We
  * currently do not utilize this information.
@@ -392,12 +301,10 @@ static void idetape_analyze_error(ide_drive_t *drive, u8 *sense)
 		 pc->c[0], tape->sense_key, tape->asc, tape->ascq);
 
 	/* Correct pc->xferred by asking the tape.	 */
-	if (pc->flags & PC_FLAG_DMA_ERROR) {
+	if (pc->flags & PC_FLAG_DMA_ERROR)
 		pc->xferred = pc->req_xfer -
 			tape->blk_size *
 			get_unaligned_be32(&sense[3]);
-		idetape_update_buffers(drive, pc);
-	}
 
 	/*
 	 * If error was the result of a zero-length read or write command,
@@ -436,29 +343,6 @@ static void idetape_analyze_error(ide_drive_t *drive, u8 *sense)
 	}
 }
 
-/* Free data buffers completely. */
-static void ide_tape_kfree_buffer(idetape_tape_t *tape)
-{
-	struct idetape_bh *prev_bh, *bh = tape->merge_bh;
-
-	while (bh) {
-		u32 size = bh->b_size;
-
-		while (size) {
-			unsigned int order = fls(size >> PAGE_SHIFT)-1;
-
-			if (bh->b_data)
-				free_pages((unsigned long)bh->b_data, order);
-
-			size &= (order-1);
-			bh->b_data += (1 << order) * PAGE_SIZE;
-		}
-		prev_bh = bh;
-		bh = bh->b_reqnext;
-		kfree(prev_bh);
-	}
-}
-
 static void ide_tape_handle_dsc(ide_drive_t *);
 
 static int ide_tape_callback(ide_drive_t *drive, int dsc)
@@ -496,7 +380,7 @@ static int ide_tape_callback(ide_drive_t *drive, int dsc)
 		}
 
 		tape->first_frame += blocks;
-		rq->current_nr_sectors -= blocks;
+		rq->resid_len -= blocks * tape->blk_size;
 
 		if (pc->error) {
 			uptodate = 0;
@@ -558,19 +442,6 @@ static void ide_tape_handle_dsc(ide_drive_t *drive)
 	idetape_postpone_request(drive);
 }
 
-static int ide_tape_io_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
-				unsigned int bcount, int write)
-{
-	unsigned int bleft;
-
-	if (write)
-		bleft = idetape_output_buffers(drive, pc, bcount);
-	else
-		bleft = idetape_input_buffers(drive, pc, bcount);
-
-	return bcount - bleft;
-}
-
 /*
  * Packet Command Interface
  *
@@ -622,6 +493,8 @@ static ide_startstop_t ide_tape_issue_pc(ide_drive_t *drive,
 
 	if (pc->retries > IDETAPE_MAX_PC_RETRIES ||
 		(pc->flags & PC_FLAG_ABORT)) {
+		unsigned int done = blk_rq_bytes(drive->hwif->rq);
+
 		/*
 		 * We will "abort" retrying a packet command in case legitimate
 		 * error code was received (crossing a filemark, or end of the
@@ -641,8 +514,10 @@ static ide_startstop_t ide_tape_issue_pc(ide_drive_t *drive,
 			/* Giving up */
 			pc->error = IDE_DRV_ERROR_GENERAL;
 		}
+
 		drive->failed_pc = NULL;
 		drive->pc_callback(drive, 0);
+		ide_complete_rq(drive, -EIO, done);
 		return ide_stopped;
 	}
 	debug_log(DBG_SENSE, "Retry #%d, cmd = %02X\n", pc->retries, pc->c[0]);
@@ -695,7 +570,7 @@ static ide_startstop_t idetape_media_access_finished(ide_drive_t *drive)
 				printk(KERN_ERR "ide-tape: %s: I/O error, ",
 						tape->name);
 			/* Retry operation */
-			ide_retry_pc(drive, tape->disk);
+			ide_retry_pc(drive);
 			return ide_stopped;
 		}
 		pc->error = 0;
@@ -711,27 +586,22 @@ static void ide_tape_create_rw_cmd(idetape_tape_t *tape,
 				   struct ide_atapi_pc *pc, struct request *rq,
 				   u8 opcode)
 {
-	struct idetape_bh *bh = (struct idetape_bh *)rq->special;
-	unsigned int length = rq->current_nr_sectors;
+	unsigned int length = blk_rq_sectors(rq);
 
 	ide_init_pc(pc);
 	put_unaligned(cpu_to_be32(length), (unsigned int *) &pc->c[1]);
 	pc->c[1] = 1;
-	pc->bh = bh;
 	pc->buf = NULL;
 	pc->buf_size = length * tape->blk_size;
 	pc->req_xfer = pc->buf_size;
 	if (pc->req_xfer == tape->buffer_size)
 		pc->flags |= PC_FLAG_DMA_OK;
 
-	if (opcode == READ_6) {
+	if (opcode == READ_6)
 		pc->c[0] = READ_6;
-		atomic_set(&bh->b_count, 0);
-	} else if (opcode == WRITE_6) {
+	else if (opcode == WRITE_6) {
 		pc->c[0] = WRITE_6;
 		pc->flags |= PC_FLAG_WRITING;
-		pc->b_data = bh->b_data;
-		pc->b_count = atomic_read(&bh->b_count);
 	}
 
 	memcpy(rq->cmd, pc->c, 12);
@@ -747,12 +617,10 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 	struct ide_cmd cmd;
 	u8 stat;
 
-	debug_log(DBG_SENSE, "sector: %llu, nr_sectors: %lu,"
-			" current_nr_sectors: %u\n",
-			(unsigned long long)rq->sector, rq->nr_sectors,
-			rq->current_nr_sectors);
+	debug_log(DBG_SENSE, "sector: %llu, nr_sectors: %u\n"
+		  (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq));
 
-	if (!blk_special_request(rq)) {
+	if (!(blk_special_request(rq) || blk_sense_request(rq))) {
 		/* We do not support buffer cache originated requests. */
 		printk(KERN_NOTICE "ide-tape: %s: Unsupported request in "
 			"request queue (%d)\n", drive->name, rq->cmd_type);
@@ -828,7 +696,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		goto out;
 	}
 	if (rq->cmd[13] & REQ_IDETAPE_PC1) {
-		pc = (struct ide_atapi_pc *) rq->buffer;
+		pc = (struct ide_atapi_pc *)rq->special;
 		rq->cmd[13] &= ~(REQ_IDETAPE_PC1);
 		rq->cmd[13] |= REQ_IDETAPE_PC2;
 		goto out;
@@ -840,6 +708,9 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 	BUG();
 
 out:
+	/* prepare sense request for this command */
+	ide_prep_sense(drive, rq);
+
 	memset(&cmd, 0, sizeof(cmd));
 
 	if (rq_data_dir(rq))
@@ -847,169 +718,12 @@ out:
 
 	cmd.rq = rq;
 
+	ide_init_sg_cmd(&cmd, pc->req_xfer);
+	ide_map_sg(drive, &cmd);
+
 	return ide_tape_issue_pc(drive, &cmd, pc);
 }
 
-/*
- * The function below uses __get_free_pages to allocate a data buffer of size
- * tape->buffer_size (or a bit more). We attempt to combine sequential pages as
- * much as possible.
- *
- * It returns a pointer to the newly allocated buffer, or NULL in case of
- * failure.
- */
-static struct idetape_bh *ide_tape_kmalloc_buffer(idetape_tape_t *tape,
-						  int full, int clear)
-{
-	struct idetape_bh *prev_bh, *bh, *merge_bh;
-	int pages = tape->pages_per_buffer;
-	unsigned int order, b_allocd;
-	char *b_data = NULL;
-
-	merge_bh = kmalloc(sizeof(struct idetape_bh), GFP_KERNEL);
-	bh = merge_bh;
-	if (bh == NULL)
-		goto abort;
-
-	order = fls(pages) - 1;
-	bh->b_data = (char *) __get_free_pages(GFP_KERNEL, order);
-	if (!bh->b_data)
-		goto abort;
-	b_allocd = (1 << order) * PAGE_SIZE;
-	pages &= (order-1);
-
-	if (clear)
-		memset(bh->b_data, 0, b_allocd);
-	bh->b_reqnext = NULL;
-	bh->b_size = b_allocd;
-	atomic_set(&bh->b_count, full ? bh->b_size : 0);
-
-	while (pages) {
-		order = fls(pages) - 1;
-		b_data = (char *) __get_free_pages(GFP_KERNEL, order);
-		if (!b_data)
-			goto abort;
-		b_allocd = (1 << order) * PAGE_SIZE;
-
-		if (clear)
-			memset(b_data, 0, b_allocd);
-
-		/* newly allocated page frames below buffer header or ...*/
-		if (bh->b_data == b_data + b_allocd) {
-			bh->b_size += b_allocd;
-			bh->b_data -= b_allocd;
-			if (full)
-				atomic_add(b_allocd, &bh->b_count);
-			continue;
-		}
-		/* they are above the header */
-		if (b_data == bh->b_data + bh->b_size) {
-			bh->b_size += b_allocd;
-			if (full)
-				atomic_add(b_allocd, &bh->b_count);
-			continue;
-		}
-		prev_bh = bh;
-		bh = kmalloc(sizeof(struct idetape_bh), GFP_KERNEL);
-		if (!bh) {
-			free_pages((unsigned long) b_data, order);
-			goto abort;
-		}
-		bh->b_reqnext = NULL;
-		bh->b_data = b_data;
-		bh->b_size = b_allocd;
-		atomic_set(&bh->b_count, full ? bh->b_size : 0);
-		prev_bh->b_reqnext = bh;
-
-		pages &= (order-1);
-	}
-
-	bh->b_size -= tape->excess_bh_size;
-	if (full)
-		atomic_sub(tape->excess_bh_size, &bh->b_count);
-	return merge_bh;
-abort:
-	ide_tape_kfree_buffer(tape);
-	return NULL;
-}
-
-static int idetape_copy_stage_from_user(idetape_tape_t *tape,
-					const char __user *buf, int n)
-{
-	struct idetape_bh *bh = tape->bh;
-	int count;
-	int ret = 0;
-
-	while (n) {
-		if (bh == NULL) {
-			printk(KERN_ERR "ide-tape: bh == NULL in %s\n",
-					__func__);
-			return 1;
-		}
-		count = min((unsigned int)
-				(bh->b_size - atomic_read(&bh->b_count)),
-				(unsigned int)n);
-		if (copy_from_user(bh->b_data + atomic_read(&bh->b_count), buf,
-				count))
-			ret = 1;
-		n -= count;
-		atomic_add(count, &bh->b_count);
-		buf += count;
-		if (atomic_read(&bh->b_count) == bh->b_size) {
-			bh = bh->b_reqnext;
-			if (bh)
-				atomic_set(&bh->b_count, 0);
-		}
-	}
-	tape->bh = bh;
-	return ret;
-}
-
-static int idetape_copy_stage_to_user(idetape_tape_t *tape, char __user *buf,
-				      int n)
-{
-	struct idetape_bh *bh = tape->bh;
-	int count;
-	int ret = 0;
-
-	while (n) {
-		if (bh == NULL) {
-			printk(KERN_ERR "ide-tape: bh == NULL in %s\n",
-					__func__);
-			return 1;
-		}
-		count = min(tape->b_count, n);
-		if  (copy_to_user(buf, tape->b_data, count))
-			ret = 1;
-		n -= count;
-		tape->b_data += count;
-		tape->b_count -= count;
-		buf += count;
-		if (!tape->b_count) {
-			bh = bh->b_reqnext;
-			tape->bh = bh;
-			if (bh) {
-				tape->b_data = bh->b_data;
-				tape->b_count = atomic_read(&bh->b_count);
-			}
-		}
-	}
-	return ret;
-}
-
-static void idetape_init_merge_buffer(idetape_tape_t *tape)
-{
-	struct idetape_bh *bh = tape->merge_bh;
-	tape->bh = tape->merge_bh;
-
-	if (tape->chrdev_dir == IDETAPE_DIR_WRITE)
-		atomic_set(&bh->b_count, 0);
-	else {
-		tape->b_data = bh->b_data;
-		tape->b_count = atomic_read(&bh->b_count);
-	}
-}
-
 /*
  * Write a filemark if write_filemark=1. Flush the device buffers without
  * writing a filemark otherwise.
@@ -1107,10 +821,10 @@ static void __ide_tape_discard_merge_buffer(ide_drive_t *drive)
 		return;
 
 	clear_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags);
-	tape->merge_bh_size = 0;
-	if (tape->merge_bh != NULL) {
-		ide_tape_kfree_buffer(tape);
-		tape->merge_bh = NULL;
+	tape->valid = 0;
+	if (tape->buf != NULL) {
+		kfree(tape->buf);
+		tape->buf = NULL;
 	}
 
 	tape->chrdev_dir = IDETAPE_DIR_NONE;
@@ -1164,36 +878,44 @@ static void ide_tape_discard_merge_buffer(ide_drive_t *drive,
  * Generate a read/write request for the block device interface and wait for it
  * to be serviced.
  */
-static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int blocks,
-				 struct idetape_bh *bh)
+static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 {
 	idetape_tape_t *tape = drive->driver_data;
 	struct request *rq;
-	int ret, errors;
+	int ret;
 
 	debug_log(DBG_SENSE, "%s: cmd=%d\n", __func__, cmd);
+	BUG_ON(cmd != REQ_IDETAPE_READ && cmd != REQ_IDETAPE_WRITE);
+	BUG_ON(size < 0 || size % tape->blk_size);
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
 	rq->cmd_type = REQ_TYPE_SPECIAL;
 	rq->cmd[13] = cmd;
 	rq->rq_disk = tape->disk;
-	rq->special = (void *)bh;
-	rq->sector = tape->first_frame;
-	rq->nr_sectors = blocks;
-	rq->current_nr_sectors = blocks;
+	rq->__sector = tape->first_frame;
+
+	if (size) {
+		ret = blk_rq_map_kern(drive->queue, rq, tape->buf, size,
+				      __GFP_WAIT);
+		if (ret)
+			goto out_put;
+	}
+
 	blk_execute_rq(drive->queue, tape->disk, rq, 0);
 
-	errors = rq->errors;
-	ret = tape->blk_size * (blocks - rq->current_nr_sectors);
+	/* calculate the number of transferred bytes and update buffer state */
+	size -= rq->resid_len;
+	tape->cur = tape->buf;
+	if (cmd == REQ_IDETAPE_READ)
+		tape->valid = size;
+	else
+		tape->valid = 0;
+
+	ret = size;
+	if (rq->errors == IDE_DRV_ERROR_GENERAL)
+		ret = -EIO;
+out_put:
 	blk_put_request(rq);
-
-	if ((cmd & (REQ_IDETAPE_READ | REQ_IDETAPE_WRITE)) == 0)
-		return 0;
-
-	if (tape->merge_bh)
-		idetape_init_merge_buffer(tape);
-	if (errors == IDE_DRV_ERROR_GENERAL)
-		return -EIO;
 	return ret;
 }
 
@@ -1230,153 +952,87 @@ static void idetape_create_space_cmd(struct ide_atapi_pc *pc, int count, u8 cmd)
 	pc->flags |= PC_FLAG_WAIT_FOR_DSC;
 }
 
-/* Queue up a character device originated write request. */
-static int idetape_add_chrdev_write_request(ide_drive_t *drive, int blocks)
-{
-	idetape_tape_t *tape = drive->driver_data;
-
-	debug_log(DBG_CHRDEV, "Enter %s\n", __func__);
-
-	return idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE,
-				     blocks, tape->merge_bh);
-}
-
 static void ide_tape_flush_merge_buffer(ide_drive_t *drive)
 {
 	idetape_tape_t *tape = drive->driver_data;
-	int blocks, min;
-	struct idetape_bh *bh;
 
 	if (tape->chrdev_dir != IDETAPE_DIR_WRITE) {
 		printk(KERN_ERR "ide-tape: bug: Trying to empty merge buffer"
 				" but we are not writing.\n");
 		return;
 	}
-	if (tape->merge_bh_size > tape->buffer_size) {
-		printk(KERN_ERR "ide-tape: bug: merge_buffer too big\n");
-		tape->merge_bh_size = tape->buffer_size;
-	}
-	if (tape->merge_bh_size) {
-		blocks = tape->merge_bh_size / tape->blk_size;
-		if (tape->merge_bh_size % tape->blk_size) {
-			unsigned int i;
+	if (tape->buf) {
+		size_t aligned = roundup(tape->valid, tape->blk_size);
 
-			blocks++;
-			i = tape->blk_size - tape->merge_bh_size %
-				tape->blk_size;
-			bh = tape->bh->b_reqnext;
-			while (bh) {
-				atomic_set(&bh->b_count, 0);
-				bh = bh->b_reqnext;
-			}
-			bh = tape->bh;
-			while (i) {
-				if (bh == NULL) {
-					printk(KERN_INFO "ide-tape: bug,"
-							 " bh NULL\n");
-					break;
-				}
-				min = min(i, (unsigned int)(bh->b_size -
-						atomic_read(&bh->b_count)));
-				memset(bh->b_data + atomic_read(&bh->b_count),
-						0, min);
-				atomic_add(min, &bh->b_count);
-				i -= min;
-				bh = bh->b_reqnext;
-			}
-		}
-		(void) idetape_add_chrdev_write_request(drive, blocks);
-		tape->merge_bh_size = 0;
-	}
-	if (tape->merge_bh != NULL) {
-		ide_tape_kfree_buffer(tape);
-		tape->merge_bh = NULL;
+		memset(tape->cur, 0, aligned - tape->valid);
+		idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE, aligned);
+		kfree(tape->buf);
+		tape->buf = NULL;
 	}
 	tape->chrdev_dir = IDETAPE_DIR_NONE;
 }
 
-static int idetape_init_read(ide_drive_t *drive)
+static int idetape_init_rw(ide_drive_t *drive, int dir)
 {
 	idetape_tape_t *tape = drive->driver_data;
-	int bytes_read;
+	int rc;
 
-	/* Initialize read operation */
-	if (tape->chrdev_dir != IDETAPE_DIR_READ) {
-		if (tape->chrdev_dir == IDETAPE_DIR_WRITE) {
-			ide_tape_flush_merge_buffer(drive);
-			idetape_flush_tape_buffers(drive);
-		}
-		if (tape->merge_bh || tape->merge_bh_size) {
-			printk(KERN_ERR "ide-tape: merge_bh_size should be"
-					 " 0 now\n");
-			tape->merge_bh_size = 0;
-		}
-		tape->merge_bh = ide_tape_kmalloc_buffer(tape, 0, 0);
-		if (!tape->merge_bh)
-			return -ENOMEM;
-		tape->chrdev_dir = IDETAPE_DIR_READ;
+	BUG_ON(dir != IDETAPE_DIR_READ && dir != IDETAPE_DIR_WRITE);
 
-		/*
-		 * Issue a read 0 command to ensure that DSC handshake is
-		 * switched from completion mode to buffer available mode.
-		 * No point in issuing this if DSC overlap isn't supported, some
-		 * drives (Seagate STT3401A) will return an error.
-		 */
-		if (drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) {
-			bytes_read = idetape_queue_rw_tail(drive,
-							REQ_IDETAPE_READ, 0,
-							tape->merge_bh);
-			if (bytes_read < 0) {
-				ide_tape_kfree_buffer(tape);
-				tape->merge_bh = NULL;
-				tape->chrdev_dir = IDETAPE_DIR_NONE;
-				return bytes_read;
-			}
+	if (tape->chrdev_dir == dir)
+		return 0;
+
+	if (tape->chrdev_dir == IDETAPE_DIR_READ)
+		ide_tape_discard_merge_buffer(drive, 1);
+	else if (tape->chrdev_dir == IDETAPE_DIR_WRITE) {
+		ide_tape_flush_merge_buffer(drive);
+		idetape_flush_tape_buffers(drive);
+	}
+
+	if (tape->buf || tape->valid) {
+		printk(KERN_ERR "ide-tape: valid should be 0 now\n");
+		tape->valid = 0;
+	}
+
+	tape->buf = kmalloc(tape->buffer_size, GFP_KERNEL);
+	if (!tape->buf)
+		return -ENOMEM;
+	tape->chrdev_dir = dir;
+	tape->cur = tape->buf;
+
+	/*
+	 * Issue a 0 rw command to ensure that DSC handshake is
+	 * switched from completion mode to buffer available mode.  No
+	 * point in issuing this if DSC overlap isn't supported, some
+	 * drives (Seagate STT3401A) will return an error.
+	 */
+	if (drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) {
+		int cmd = dir == IDETAPE_DIR_READ ? REQ_IDETAPE_READ
+						  : REQ_IDETAPE_WRITE;
+
+		rc = idetape_queue_rw_tail(drive, cmd, 0);
+		if (rc < 0) {
+			kfree(tape->buf);
+			tape->buf = NULL;
+			tape->chrdev_dir = IDETAPE_DIR_NONE;
+			return rc;
 		}
 	}
 
 	return 0;
 }
 
-/* called from idetape_chrdev_read() to service a chrdev read request. */
-static int idetape_add_chrdev_read_request(ide_drive_t *drive, int blocks)
-{
-	idetape_tape_t *tape = drive->driver_data;
-
-	debug_log(DBG_PROCS, "Enter %s, %d blocks\n", __func__, blocks);
-
-	/* If we are at a filemark, return a read length of 0 */
-	if (test_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags))
-		return 0;
-
-	idetape_init_read(drive);
-
-	return idetape_queue_rw_tail(drive, REQ_IDETAPE_READ, blocks,
-				     tape->merge_bh);
-}
-
 static void idetape_pad_zeros(ide_drive_t *drive, int bcount)
 {
 	idetape_tape_t *tape = drive->driver_data;
-	struct idetape_bh *bh;
-	int blocks;
+
+	memset(tape->buf, 0, tape->buffer_size);
 
 	while (bcount) {
-		unsigned int count;
+		unsigned int count = min(tape->buffer_size, bcount);
 
-		bh = tape->merge_bh;
-		count = min(tape->buffer_size, bcount);
+		idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE, count);
 		bcount -= count;
-		blocks = count / tape->blk_size;
-		while (count) {
-			atomic_set(&bh->b_count,
-				   min(count, (unsigned int)bh->b_size));
-			memset(bh->b_data, 0, atomic_read(&bh->b_count));
-			count -= atomic_read(&bh->b_count);
-			bh = bh->b_reqnext;
-		}
-		idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE, blocks,
-				      tape->merge_bh);
 	}
 }
 
@@ -1456,7 +1112,7 @@ static int idetape_space_over_filemarks(ide_drive_t *drive, short mt_op,
 	}
 
 	if (tape->chrdev_dir == IDETAPE_DIR_READ) {
-		tape->merge_bh_size = 0;
+		tape->valid = 0;
 		if (test_and_clear_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags))
 			++count;
 		ide_tape_discard_merge_buffer(drive, 0);
@@ -1505,9 +1161,9 @@ static ssize_t idetape_chrdev_read(struct file *file, char __user *buf,
 {
 	struct ide_tape_obj *tape = file->private_data;
 	ide_drive_t *drive = tape->drive;
-	ssize_t bytes_read, temp, actually_read = 0, rc;
+	size_t done = 0;
 	ssize_t ret = 0;
-	u16 ctl = *(u16 *)&tape->caps[12];
+	int rc;
 
 	debug_log(DBG_CHRDEV, "Enter %s, count %Zd\n", __func__, count);
 
@@ -1517,49 +1173,43 @@ static ssize_t idetape_chrdev_read(struct file *file, char __user *buf,
 			    (count % tape->blk_size) == 0)
 				tape->user_bs_factor = count / tape->blk_size;
 	}
-	rc = idetape_init_read(drive);
+
+	rc = idetape_init_rw(drive, IDETAPE_DIR_READ);
 	if (rc < 0)
 		return rc;
-	if (count == 0)
-		return (0);
-	if (tape->merge_bh_size) {
-		actually_read = min((unsigned int)(tape->merge_bh_size),
-				    (unsigned int)count);
-		if (idetape_copy_stage_to_user(tape, buf, actually_read))
+
+	while (done < count) {
+		size_t todo;
+
+		/* refill if staging buffer is empty */
+		if (!tape->valid) {
+			/* If we are at a filemark, nothing more to read */
+			if (test_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags))
+				break;
+			/* read */
+			if (idetape_queue_rw_tail(drive, REQ_IDETAPE_READ,
+						  tape->buffer_size) <= 0)
+				break;
+		}
+
+		/* copy out */
+		todo = min_t(size_t, count - done, tape->valid);
+		if (copy_to_user(buf + done, tape->cur, todo))
 			ret = -EFAULT;
-		buf += actually_read;
-		tape->merge_bh_size -= actually_read;
-		count -= actually_read;
+
+		tape->cur += todo;
+		tape->valid -= todo;
+		done += todo;
 	}
-	while (count >= tape->buffer_size) {
-		bytes_read = idetape_add_chrdev_read_request(drive, ctl);
-		if (bytes_read <= 0)
-			goto finish;
-		if (idetape_copy_stage_to_user(tape, buf, bytes_read))
-			ret = -EFAULT;
-		buf += bytes_read;
-		count -= bytes_read;
-		actually_read += bytes_read;
-	}
-	if (count) {
-		bytes_read = idetape_add_chrdev_read_request(drive, ctl);
-		if (bytes_read <= 0)
-			goto finish;
-		temp = min((unsigned long)count, (unsigned long)bytes_read);
-		if (idetape_copy_stage_to_user(tape, buf, temp))
-			ret = -EFAULT;
-		actually_read += temp;
-		tape->merge_bh_size = bytes_read-temp;
-	}
-finish:
-	if (!actually_read && test_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags)) {
+
+	if (!done && test_bit(IDE_AFLAG_FILEMARK, &drive->atapi_flags)) {
 		debug_log(DBG_SENSE, "%s: spacing over filemark\n", tape->name);
 
 		idetape_space_over_filemarks(drive, MTFSF, 1);
 		return 0;
 	}
 
-	return ret ? ret : actually_read;
+	return ret ? ret : done;
 }
 
 static ssize_t idetape_chrdev_write(struct file *file, const char __user *buf,
@@ -1567,9 +1217,9 @@ static ssize_t idetape_chrdev_write(struct file *file, const char __user *buf,
 {
 	struct ide_tape_obj *tape = file->private_data;
 	ide_drive_t *drive = tape->drive;
-	ssize_t actually_written = 0;
+	size_t done = 0;
 	ssize_t ret = 0;
-	u16 ctl = *(u16 *)&tape->caps[12];
+	int rc;
 
 	/* The drive is write protected. */
 	if (tape->write_prot)
@@ -1578,80 +1228,31 @@ static ssize_t idetape_chrdev_write(struct file *file, const char __user *buf,
 	debug_log(DBG_CHRDEV, "Enter %s, count %Zd\n", __func__, count);
 
 	/* Initialize write operation */
-	if (tape->chrdev_dir != IDETAPE_DIR_WRITE) {
-		if (tape->chrdev_dir == IDETAPE_DIR_READ)
-			ide_tape_discard_merge_buffer(drive, 1);
-		if (tape->merge_bh || tape->merge_bh_size) {
-			printk(KERN_ERR "ide-tape: merge_bh_size "
-				"should be 0 now\n");
-			tape->merge_bh_size = 0;
-		}
-		tape->merge_bh = ide_tape_kmalloc_buffer(tape, 0, 0);
-		if (!tape->merge_bh)
-			return -ENOMEM;
-		tape->chrdev_dir = IDETAPE_DIR_WRITE;
-		idetape_init_merge_buffer(tape);
+	rc = idetape_init_rw(drive, IDETAPE_DIR_WRITE);
+	if (rc < 0)
+		return rc;
 
-		/*
-		 * Issue a write 0 command to ensure that DSC handshake is
-		 * switched from completion mode to buffer available mode. No
-		 * point in issuing this if DSC overlap isn't supported, some
-		 * drives (Seagate STT3401A) will return an error.
-		 */
-		if (drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) {
-			ssize_t retval = idetape_queue_rw_tail(drive,
-							REQ_IDETAPE_WRITE, 0,
-							tape->merge_bh);
-			if (retval < 0) {
-				ide_tape_kfree_buffer(tape);
-				tape->merge_bh = NULL;
-				tape->chrdev_dir = IDETAPE_DIR_NONE;
-				return retval;
-			}
-		}
-	}
-	if (count == 0)
-		return (0);
-	if (tape->merge_bh_size) {
-		if (tape->merge_bh_size >= tape->buffer_size) {
-			printk(KERN_ERR "ide-tape: bug: merge buf too big\n");
-			tape->merge_bh_size = 0;
-		}
-		actually_written = min((unsigned int)
-				(tape->buffer_size - tape->merge_bh_size),
-				(unsigned int)count);
-		if (idetape_copy_stage_from_user(tape, buf, actually_written))
-				ret = -EFAULT;
-		buf += actually_written;
-		tape->merge_bh_size += actually_written;
-		count -= actually_written;
+	while (done < count) {
+		size_t todo;
 
-		if (tape->merge_bh_size == tape->buffer_size) {
-			ssize_t retval;
-			tape->merge_bh_size = 0;
-			retval = idetape_add_chrdev_write_request(drive, ctl);
-			if (retval <= 0)
-				return (retval);
-		}
-	}
-	while (count >= tape->buffer_size) {
-		ssize_t retval;
-		if (idetape_copy_stage_from_user(tape, buf, tape->buffer_size))
+		/* flush if staging buffer is full */
+		if (tape->valid == tape->buffer_size &&
+		    idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE,
+					  tape->buffer_size) <= 0)
+			return rc;
+
+		/* copy in */
+		todo = min_t(size_t, count - done,
+			     tape->buffer_size - tape->valid);
+		if (copy_from_user(tape->cur, buf + done, todo))
 			ret = -EFAULT;
-		buf += tape->buffer_size;
-		count -= tape->buffer_size;
-		retval = idetape_add_chrdev_write_request(drive, ctl);
-		actually_written += tape->buffer_size;
-		if (retval <= 0)
-			return (retval);
+
+		tape->cur += todo;
+		tape->valid += todo;
+		done += todo;
 	}
-	if (count) {
-		actually_written += count;
-		if (idetape_copy_stage_from_user(tape, buf, count))
-			ret = -EFAULT;
-		tape->merge_bh_size += count;
-	}
-	return ret ? ret : actually_written;
+
+	return ret ? ret : done;
 }
 
 static int idetape_write_filemark(ide_drive_t *drive)
@@ -1812,7 +1413,7 @@ static int idetape_chrdev_ioctl(struct inode *inode, struct file *file,
 		idetape_flush_tape_buffers(drive);
 	}
 	if (cmd == MTIOCGET || cmd == MTIOCPOS) {
-		block_offset = tape->merge_bh_size /
+		block_offset = tape->valid /
 			(tape->blk_size * tape->user_bs_factor);
 		position = idetape_read_position(drive);
 		if (position < 0)
@@ -1960,12 +1561,12 @@ static void idetape_write_release(ide_drive_t *drive, unsigned int minor)
 	idetape_tape_t *tape = drive->driver_data;
 
 	ide_tape_flush_merge_buffer(drive);
-	tape->merge_bh = ide_tape_kmalloc_buffer(tape, 1, 0);
-	if (tape->merge_bh != NULL) {
+	tape->buf = kmalloc(tape->buffer_size, GFP_KERNEL);
+	if (tape->buf != NULL) {
 		idetape_pad_zeros(drive, tape->blk_size *
 				(tape->user_bs_factor - 1));
-		ide_tape_kfree_buffer(tape);
-		tape->merge_bh = NULL;
+		kfree(tape->buf);
+		tape->buf = NULL;
 	}
 	idetape_write_filemark(drive);
 	idetape_flush_tape_buffers(drive);
@@ -2159,8 +1760,6 @@ static void idetape_setup(ide_drive_t *drive, idetape_tape_t *tape, int minor)
 	u16 *ctl = (u16 *)&tape->caps[12];
 
 	drive->pc_callback	 = ide_tape_callback;
-	drive->pc_update_buffers = idetape_update_buffers;
-	drive->pc_io_buffers	 = ide_tape_io_buffers;
 
 	drive->dev_flags |= IDE_DFLAG_DSC_OVERLAP;
 
@@ -2191,11 +1790,6 @@ static void idetape_setup(ide_drive_t *drive, idetape_tape_t *tape, int minor)
 		tape->buffer_size = *ctl * tape->blk_size;
 	}
 	buffer_size = tape->buffer_size;
-	tape->pages_per_buffer = buffer_size / PAGE_SIZE;
-	if (buffer_size % PAGE_SIZE) {
-		tape->pages_per_buffer++;
-		tape->excess_bh_size = PAGE_SIZE - buffer_size % PAGE_SIZE;
-	}
 
 	/* select the "best" DSC read/write polling freq */
 	speed = max(*(u16 *)&tape->caps[14], *(u16 *)&tape->caps[8]);
@@ -2238,7 +1832,7 @@ static void ide_tape_release(struct device *dev)
 	ide_drive_t *drive = tape->drive;
 	struct gendisk *g = tape->disk;
 
-	BUG_ON(tape->merge_bh_size);
+	BUG_ON(tape->valid);
 
 	drive->dev_flags &= ~IDE_DFLAG_DSC_OVERLAP;
 	drive->driver_data = NULL;
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index 4aa6223c11be..a0c3e1b2f73c 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -385,7 +385,7 @@ out_end:
 	if ((cmd->tf_flags & IDE_TFLAG_FS) == 0)
 		ide_finish_cmd(drive, cmd, stat);
 	else
-		ide_complete_rq(drive, 0, cmd->rq->nr_sectors << 9);
+		ide_complete_rq(drive, 0, blk_rq_sectors(cmd->rq) << 9);
 	return ide_stopped;
 out_err:
 	ide_error_cmd(drive, cmd);
@@ -424,7 +424,9 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
 	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
-	rq->buffer = buf;
+
+	if (cmd->tf_flags & IDE_TFLAG_WRITE)
+		rq->cmd_flags |= REQ_RW;
 
 	/*
 	 * (ks) We transfer currently only whole sectors.
@@ -432,18 +434,20 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 	 * if we would find a solution to transfer any size.
 	 * To support special commands like READ LONG.
 	 */
-	rq->hard_nr_sectors = rq->nr_sectors = nsect;
-	rq->hard_cur_sectors = rq->current_nr_sectors = nsect;
-
-	if (cmd->tf_flags & IDE_TFLAG_WRITE)
-		rq->cmd_flags |= REQ_RW;
+	if (nsect) {
+		error = blk_rq_map_kern(drive->queue, rq, buf,
+					nsect * SECTOR_SIZE, __GFP_WAIT);
+		if (error)
+			goto put_req;
+	}
 
 	rq->special = cmd;
 	cmd->rq = rq;
 
 	error = blk_execute_rq(drive->queue, NULL, rq, 0);
-	blk_put_request(rq);
 
+put_req:
+	blk_put_request(rq);
 	return error;
 }
 
diff --git a/drivers/ide/pdc202xx_old.c b/drivers/ide/pdc202xx_old.c
index b3bc96f930a6..e24ecc87a9b1 100644
--- a/drivers/ide/pdc202xx_old.c
+++ b/drivers/ide/pdc202xx_old.c
@@ -177,7 +177,7 @@ static void pdc202xx_dma_start(ide_drive_t *drive)
 		u8 clock = inb(high_16 + 0x11);
 
 		outb(clock | (hwif->channel ? 0x08 : 0x02), high_16 + 0x11);
-		word_count = (rq->nr_sectors << 8);
+		word_count = (blk_rq_sectors(rq) << 8);
 		word_count = (rq_data_dir(rq) == READ) ?
 					word_count | 0x05000000 :
 					word_count | 0x06000000;
diff --git a/drivers/ide/tc86c001.c b/drivers/ide/tc86c001.c
index b4cf42dc8a6f..05a93d6baecc 100644
--- a/drivers/ide/tc86c001.c
+++ b/drivers/ide/tc86c001.c
@@ -112,7 +112,7 @@ static void tc86c001_dma_start(ide_drive_t *drive)
 	ide_hwif_t *hwif	= drive->hwif;
 	unsigned long sc_base	= hwif->config_data;
 	unsigned long twcr_port	= sc_base + (drive->dn ? 0x06 : 0x04);
-	unsigned long nsectors	= hwif->rq->nr_sectors;
+	unsigned long nsectors	= blk_rq_sectors(hwif->rq);
 
 	/*
 	 * We have to manually load the sector count and size into
diff --git a/drivers/ide/tx4939ide.c b/drivers/ide/tx4939ide.c
index 564422d23976..5ca76224f6d1 100644
--- a/drivers/ide/tx4939ide.c
+++ b/drivers/ide/tx4939ide.c
@@ -307,7 +307,7 @@ static int tx4939ide_dma_setup(ide_drive_t *drive, struct ide_cmd *cmd)
 	tx4939ide_writew(SECTOR_SIZE / 2, base, drive->dn ?
 			 TX4939IDE_Xfer_Cnt_2 : TX4939IDE_Xfer_Cnt_1);
 
-	tx4939ide_writew(cmd->rq->nr_sectors, base, TX4939IDE_Sec_Cnt);
+	tx4939ide_writew(blk_rq_sectors(cmd->rq), base, TX4939IDE_Sec_Cnt);
 
 	return 0;
 }
diff --git a/drivers/ieee1394/dv1394.c b/drivers/ieee1394/dv1394.c
index 823a6297a1af..2cd00b5b45b4 100644
--- a/drivers/ieee1394/dv1394.c
+++ b/drivers/ieee1394/dv1394.c
@@ -1789,12 +1789,13 @@ static int dv1394_open(struct inode *inode, struct file *file)
 	} else {
 		/* look up the card by ID */
 		unsigned long flags;
+		int idx = ieee1394_file_to_instance(file);
 
 		spin_lock_irqsave(&dv1394_cards_lock, flags);
 		if (!list_empty(&dv1394_cards)) {
 			struct video_card *p;
 			list_for_each_entry(p, &dv1394_cards, list) {
-				if ((p->id) == ieee1394_file_to_instance(file)) {
+				if ((p->id) == idx) {
 					video = p;
 					break;
 				}
@@ -1803,7 +1804,7 @@ static int dv1394_open(struct inode *inode, struct file *file)
 		spin_unlock_irqrestore(&dv1394_cards_lock, flags);
 
 		if (!video) {
-			debug_printk("dv1394: OHCI card %d not found", ieee1394_file_to_instance(file));
+			debug_printk("dv1394: OHCI card %d not found", idx);
 			return -ENODEV;
 		}
 
diff --git a/drivers/ieee1394/ieee1394_core.h b/drivers/ieee1394/ieee1394_core.h
index 21d50f73a210..28b9f58bafd2 100644
--- a/drivers/ieee1394/ieee1394_core.h
+++ b/drivers/ieee1394/ieee1394_core.h
@@ -5,6 +5,7 @@
 #include <linux/fs.h>
 #include <linux/list.h>
 #include <linux/types.h>
+#include <linux/cdev.h>
 #include <asm/atomic.h>
 
 #include "hosts.h"
@@ -155,7 +156,10 @@ void hpsb_packet_received(struct hpsb_host *host, quadlet_t *data, size_t size,
  */
 static inline unsigned char ieee1394_file_to_instance(struct file *file)
 {
-	return file->f_path.dentry->d_inode->i_cindex;
+	int idx = cdev_index(file->f_path.dentry->d_inode);
+	if (idx < 0)
+		idx = 0;
+	return idx;
 }
 
 extern int hpsb_disable_irm;
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 56df1cee8fb3..3319c2fec28e 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -232,7 +232,7 @@ static struct page *read_sb_page(mddev_t *mddev, long offset,
 		target = rdev->sb_start + offset + index * (PAGE_SIZE/512);
 
 		if (sync_page_io(rdev->bdev, target,
-				 roundup(size, bdev_hardsect_size(rdev->bdev)),
+				 roundup(size, bdev_logical_block_size(rdev->bdev)),
 				 page, READ)) {
 			page->index = index;
 			attach_page_buffers(page, NULL); /* so that free_buffer will
@@ -287,7 +287,7 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 			int size = PAGE_SIZE;
 			if (page->index == bitmap->file_pages-1)
 				size = roundup(bitmap->last_page_size,
-					       bdev_hardsect_size(rdev->bdev));
+					       bdev_logical_block_size(rdev->bdev));
 			/* Just make sure we aren't corrupting data or
 			 * metadata
 			 */
diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c
index a2e26c242141..75d8081a9041 100644
--- a/drivers/md/dm-exception-store.c
+++ b/drivers/md/dm-exception-store.c
@@ -178,7 +178,7 @@ static int set_chunk_size(struct dm_exception_store *store,
 	}
 
 	/* Validate the chunk size against the device block size */
-	if (chunk_size_ulong % (bdev_hardsect_size(store->cow->bdev) >> 9)) {
+	if (chunk_size_ulong % (bdev_logical_block_size(store->cow->bdev) >> 9)) {
 		*error = "Chunk size is not a multiple of device blocksize";
 		return -EINVAL;
 	}
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index be233bc4d917..6fa8ccf91c70 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -413,7 +413,8 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 		 * Buffer holds both header and bitset.
 		 */
 		buf_size = dm_round_up((LOG_OFFSET << SECTOR_SHIFT) +
-				       bitset_size, ti->limits.hardsect_size);
+				       bitset_size,
+				       ti->limits.logical_block_size);
 
 		if (buf_size > dev->bdev->bd_inode->i_size) {
 			DMWARN("log device %s too small: need %llu bytes",
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index e75c6dd76a9a..2662a41337e7 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -282,7 +282,7 @@ static int read_header(struct pstore *ps, int *new_snapshot)
 	 */
 	if (!ps->store->chunk_size) {
 		ps->store->chunk_size = max(DM_CHUNK_SIZE_DEFAULT_SECTORS,
-		    bdev_hardsect_size(ps->store->cow->bdev) >> 9);
+		    bdev_logical_block_size(ps->store->cow->bdev) >> 9);
 		ps->store->chunk_mask = ps->store->chunk_size - 1;
 		ps->store->chunk_shift = ffs(ps->store->chunk_size) - 1;
 		chunk_size_supplied = 0;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 429b50b975d5..e9a73bb242b0 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -108,7 +108,8 @@ static void combine_restrictions_low(struct io_restrictions *lhs,
 	lhs->max_hw_segments =
 		min_not_zero(lhs->max_hw_segments, rhs->max_hw_segments);
 
-	lhs->hardsect_size = max(lhs->hardsect_size, rhs->hardsect_size);
+	lhs->logical_block_size = max(lhs->logical_block_size,
+				      rhs->logical_block_size);
 
 	lhs->max_segment_size =
 		min_not_zero(lhs->max_segment_size, rhs->max_segment_size);
@@ -509,7 +510,7 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
 	 *        combine_restrictions_low()
 	 */
 	rs->max_sectors =
-		min_not_zero(rs->max_sectors, q->max_sectors);
+		min_not_zero(rs->max_sectors, queue_max_sectors(q));
 
 	/*
 	 * Check if merge fn is supported.
@@ -524,24 +525,25 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
 
 	rs->max_phys_segments =
 		min_not_zero(rs->max_phys_segments,
-			     q->max_phys_segments);
+			     queue_max_phys_segments(q));
 
 	rs->max_hw_segments =
-		min_not_zero(rs->max_hw_segments, q->max_hw_segments);
+		min_not_zero(rs->max_hw_segments, queue_max_hw_segments(q));
 
-	rs->hardsect_size = max(rs->hardsect_size, q->hardsect_size);
+	rs->logical_block_size = max(rs->logical_block_size,
+				     queue_logical_block_size(q));
 
 	rs->max_segment_size =
-		min_not_zero(rs->max_segment_size, q->max_segment_size);
+		min_not_zero(rs->max_segment_size, queue_max_segment_size(q));
 
 	rs->max_hw_sectors =
-		min_not_zero(rs->max_hw_sectors, q->max_hw_sectors);
+		min_not_zero(rs->max_hw_sectors, queue_max_hw_sectors(q));
 
 	rs->seg_boundary_mask =
 		min_not_zero(rs->seg_boundary_mask,
-			     q->seg_boundary_mask);
+			     queue_segment_boundary(q));
 
-	rs->bounce_pfn = min_not_zero(rs->bounce_pfn, q->bounce_pfn);
+	rs->bounce_pfn = min_not_zero(rs->bounce_pfn, queue_bounce_pfn(q));
 
 	rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
 }
@@ -683,8 +685,8 @@ static void check_for_valid_limits(struct io_restrictions *rs)
 		rs->max_phys_segments = MAX_PHYS_SEGMENTS;
 	if (!rs->max_hw_segments)
 		rs->max_hw_segments = MAX_HW_SEGMENTS;
-	if (!rs->hardsect_size)
-		rs->hardsect_size = 1 << SECTOR_SHIFT;
+	if (!rs->logical_block_size)
+		rs->logical_block_size = 1 << SECTOR_SHIFT;
 	if (!rs->max_segment_size)
 		rs->max_segment_size = MAX_SEGMENT_SIZE;
 	if (!rs->seg_boundary_mask)
@@ -912,13 +914,13 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q)
 	 * restrictions.
 	 */
 	blk_queue_max_sectors(q, t->limits.max_sectors);
-	q->max_phys_segments = t->limits.max_phys_segments;
-	q->max_hw_segments = t->limits.max_hw_segments;
-	q->hardsect_size = t->limits.hardsect_size;
-	q->max_segment_size = t->limits.max_segment_size;
-	q->max_hw_sectors = t->limits.max_hw_sectors;
-	q->seg_boundary_mask = t->limits.seg_boundary_mask;
-	q->bounce_pfn = t->limits.bounce_pfn;
+	blk_queue_max_phys_segments(q, t->limits.max_phys_segments);
+	blk_queue_max_hw_segments(q, t->limits.max_hw_segments);
+	blk_queue_logical_block_size(q, t->limits.logical_block_size);
+	blk_queue_max_segment_size(q, t->limits.max_segment_size);
+	blk_queue_max_hw_sectors(q, t->limits.max_hw_sectors);
+	blk_queue_segment_boundary(q, t->limits.seg_boundary_mask);
+	blk_queue_bounce_limit(q, t->limits.bounce_pfn);
 
 	if (t->limits.no_cluster)
 		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 424f7b048c30..3fd8b1e65483 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -20,7 +20,8 @@
 #include <linux/idr.h>
 #include <linux/hdreg.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
+
+#include <trace/events/block.h>
 
 #define DM_MSG_PREFIX "core"
 
@@ -53,8 +54,6 @@ struct dm_target_io {
 	union map_info info;
 };
 
-DEFINE_TRACE(block_bio_complete);
-
 /*
  * For request-based dm.
  * One of these is allocated per request.
@@ -656,8 +655,7 @@ static void __map_bio(struct dm_target *ti, struct bio *clone,
 		/* the bio has been remapped so dispatch it */
 
 		trace_block_remap(bdev_get_queue(clone->bi_bdev), clone,
-				    tio->io->bio->bi_bdev->bd_dev,
-				    clone->bi_sector, sector);
+				    tio->io->bio->bi_bdev->bd_dev, sector);
 
 		generic_make_request(clone);
 	} else if (r < 0 || r == DM_MAPIO_REQUEUE) {
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 7a36e38393a1..64f1f3e046e0 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -146,7 +146,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		 * a one page request is never in violation.
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->num_sectors = rdev->sectors;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 641b211fe3fe..20f6ac338349 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1202,7 +1202,7 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 	atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read));
 
 	rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
-	bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1;
+	bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
 	if (rdev->sb_size & bmask)
 		rdev->sb_size = (rdev->sb_size | bmask) + 1;
 
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 41ced0cbe823..4ee31aa13c40 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -303,7 +303,7 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 		 * merge_bvec_fn will be involved in multipath.)
 		 */
 			if (q->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+			    queue_max_sectors(q) > (PAGE_SIZE>>9))
 				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			conf->working_disks++;
@@ -467,7 +467,7 @@ static int multipath_run (mddev_t *mddev)
 		 * violating it, not that we ever expect a device with
 		 * a merge_bvec_fn to be involved in multipath */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		if (!test_bit(Faulty, &rdev->flags))
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index c08d7559be55..925507e7d673 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -144,7 +144,7 @@ static int create_strip_zones (mddev_t *mddev)
 		 */
 
 		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		if (!smallest || (rdev1->sectors < smallest->sectors))
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 36df9109cde1..e23758b4a34e 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1130,7 +1130,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			 * a one page request is never in violation.
 			 */
 			if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+			    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			p->head_position = 0;
@@ -1996,7 +1996,7 @@ static int run(mddev_t *mddev)
 		 * a one page request is never in violation.
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->head_position = 0;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 499620afb44b..750550c1166f 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1158,8 +1158,8 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			 * a one page request is never in violation.
 			 */
 			if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
-				mddev->queue->max_sectors = (PAGE_SIZE>>9);
+			    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
+				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
@@ -2145,8 +2145,8 @@ static int run(mddev_t *mddev)
 		 * a one page request is never in violation.
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
-			mddev->queue->max_sectors = (PAGE_SIZE>>9);
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
+			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->head_position = 0;
 	}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index bb37fb1b2d82..bef876698232 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3463,10 +3463,10 @@ static int bio_fits_rdev(struct bio *bi)
 {
 	struct request_queue *q = bdev_get_queue(bi->bi_bdev);
 
-	if ((bi->bi_size>>9) > q->max_sectors)
+	if ((bi->bi_size>>9) > queue_max_sectors(q))
 		return 0;
 	blk_recount_segments(q, bi);
-	if (bi->bi_phys_segments > q->max_phys_segments)
+	if (bi->bi_phys_segments > queue_max_phys_segments(q))
 		return 0;
 
 	if (q->merge_bvec_fn)
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index de143deb06f0..7847bbc1440d 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -672,15 +672,14 @@ try_again:
 					       msb->req_sg);
 
 		if (!msb->seg_count) {
-			chunk = __blk_end_request(msb->block_req, -ENOMEM,
-					blk_rq_cur_bytes(msb->block_req));
+			chunk = __blk_end_request_cur(msb->block_req, -ENOMEM);
 			continue;
 		}
 
-		t_sec = msb->block_req->sector << 9;
+		t_sec = blk_rq_pos(msb->block_req) << 9;
 		sector_div(t_sec, msb->page_size);
 
-		count = msb->block_req->nr_sectors << 9;
+		count = blk_rq_bytes(msb->block_req);
 		count /= msb->page_size;
 
 		param.system = msb->system;
@@ -705,8 +704,8 @@ try_again:
 		return 0;
 	}
 
-	dev_dbg(&card->dev, "elv_next\n");
-	msb->block_req = elv_next_request(msb->queue);
+	dev_dbg(&card->dev, "blk_fetch\n");
+	msb->block_req = blk_fetch_request(msb->queue);
 	if (!msb->block_req) {
 		dev_dbg(&card->dev, "issue end\n");
 		return -EAGAIN;
@@ -745,7 +744,7 @@ static int mspro_block_complete_req(struct memstick_dev *card, int error)
 					t_len *= msb->page_size;
 			}
 		} else
-			t_len = msb->block_req->nr_sectors << 9;
+			t_len = blk_rq_bytes(msb->block_req);
 
 		dev_dbg(&card->dev, "transferred %x (%d)\n", t_len, error);
 
@@ -825,8 +824,8 @@ static void mspro_block_submit_req(struct request_queue *q)
 		return;
 
 	if (msb->eject) {
-		while ((req = elv_next_request(q)) != NULL)
-			__blk_end_request(req, -ENODEV, blk_rq_bytes(req));
+		while ((req = blk_fetch_request(q)) != NULL)
+			__blk_end_request_all(req, -ENODEV);
 
 		return;
 	}
@@ -1243,7 +1242,7 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 
 	sprintf(msb->disk->disk_name, "mspblk%d", disk_id);
 
-	blk_queue_hardsect_size(msb->queue, msb->page_size);
+	blk_queue_logical_block_size(msb->queue, msb->page_size);
 
 	capacity = be16_to_cpu(sys_info->user_block_count);
 	capacity *= be16_to_cpu(sys_info->block_size);
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index a9019f081b97..79f5433359f9 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -1277,8 +1277,8 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	/* do we need to support multiple segments? */
 	if (req->bio->bi_vcnt > 1 || rsp->bio->bi_vcnt > 1) {
 		printk(MYIOC_s_ERR_FMT "%s: multiple segments req %u %u, rsp %u %u\n",
-		    ioc->name, __func__, req->bio->bi_vcnt, req->data_len,
-		    rsp->bio->bi_vcnt, rsp->data_len);
+		    ioc->name, __func__, req->bio->bi_vcnt, blk_rq_bytes(req),
+		    rsp->bio->bi_vcnt, blk_rq_bytes(rsp));
 		return -EINVAL;
 	}
 
@@ -1295,7 +1295,7 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	smpreq = (SmpPassthroughRequest_t *)mf;
 	memset(smpreq, 0, sizeof(*smpreq));
 
-	smpreq->RequestDataLength = cpu_to_le16(req->data_len - 4);
+	smpreq->RequestDataLength = cpu_to_le16(blk_rq_bytes(req) - 4);
 	smpreq->Function = MPI_FUNCTION_SMP_PASSTHROUGH;
 
 	if (rphy)
@@ -1321,10 +1321,10 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 		       MPI_SGE_FLAGS_END_OF_BUFFER |
 		       MPI_SGE_FLAGS_DIRECTION |
 		       mpt_addr_size()) << MPI_SGE_FLAGS_SHIFT;
-	flagsLength |= (req->data_len - 4);
+	flagsLength |= (blk_rq_bytes(req) - 4);
 
 	dma_addr_out = pci_map_single(ioc->pcidev, bio_data(req->bio),
-				      req->data_len, PCI_DMA_BIDIRECTIONAL);
+				      blk_rq_bytes(req), PCI_DMA_BIDIRECTIONAL);
 	if (!dma_addr_out)
 		goto put_mf;
 	mpt_add_sge(psge, flagsLength, dma_addr_out);
@@ -1332,9 +1332,9 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 
 	/* response */
 	flagsLength = MPT_SGE_FLAGS_SSIMPLE_READ;
-	flagsLength |= rsp->data_len + 4;
+	flagsLength |= blk_rq_bytes(rsp) + 4;
 	dma_addr_in =  pci_map_single(ioc->pcidev, bio_data(rsp->bio),
-				      rsp->data_len, PCI_DMA_BIDIRECTIONAL);
+				      blk_rq_bytes(rsp), PCI_DMA_BIDIRECTIONAL);
 	if (!dma_addr_in)
 		goto unmap;
 	mpt_add_sge(psge, flagsLength, dma_addr_in);
@@ -1357,8 +1357,8 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 		smprep = (SmpPassthroughReply_t *)ioc->sas_mgmt.reply;
 		memcpy(req->sense, smprep, sizeof(*smprep));
 		req->sense_len = sizeof(*smprep);
-		req->data_len = 0;
-		rsp->data_len -= smprep->ResponseDataLength;
+		req->resid_len = 0;
+		rsp->resid_len -= smprep->ResponseDataLength;
 	} else {
 		printk(MYIOC_s_ERR_FMT "%s: smp passthru reply failed to be returned\n",
 		    ioc->name, __func__);
@@ -1366,10 +1366,10 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	}
 unmap:
 	if (dma_addr_out)
-		pci_unmap_single(ioc->pcidev, dma_addr_out, req->data_len,
+		pci_unmap_single(ioc->pcidev, dma_addr_out, blk_rq_bytes(req),
 				 PCI_DMA_BIDIRECTIONAL);
 	if (dma_addr_in)
-		pci_unmap_single(ioc->pcidev, dma_addr_in, rsp->data_len,
+		pci_unmap_single(ioc->pcidev, dma_addr_in, blk_rq_bytes(rsp),
 				 PCI_DMA_BIDIRECTIONAL);
 put_mf:
 	if (mf)
diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c
index a443e136dc41..335d4c78a775 100644
--- a/drivers/message/i2o/i2o_block.c
+++ b/drivers/message/i2o/i2o_block.c
@@ -426,15 +426,9 @@ static void i2o_block_end_request(struct request *req, int error,
 	struct request_queue *q = req->q;
 	unsigned long flags;
 
-	if (blk_end_request(req, error, nr_bytes)) {
-		int leftover = (req->hard_nr_sectors << KERNEL_SECTOR_SHIFT);
-
-		if (blk_pc_request(req))
-			leftover = req->data_len;
-
+	if (blk_end_request(req, error, nr_bytes))
 		if (error)
-			blk_end_request(req, -EIO, leftover);
-	}
+			blk_end_request_all(req, -EIO);
 
 	spin_lock_irqsave(q->queue_lock, flags);
 
@@ -761,7 +755,7 @@ static int i2o_block_transfer(struct request *req)
 			break;
 
 		case CACHE_SMARTFETCH:
-			if (req->nr_sectors > 16)
+			if (blk_rq_sectors(req) > 16)
 				ctl_flags = 0x201F0008;
 			else
 				ctl_flags = 0x001F0000;
@@ -781,13 +775,13 @@ static int i2o_block_transfer(struct request *req)
 			ctl_flags = 0x001F0010;
 			break;
 		case CACHE_SMARTBACK:
-			if (req->nr_sectors > 16)
+			if (blk_rq_sectors(req) > 16)
 				ctl_flags = 0x001F0004;
 			else
 				ctl_flags = 0x001F0010;
 			break;
 		case CACHE_SMARTTHROUGH:
-			if (req->nr_sectors > 16)
+			if (blk_rq_sectors(req) > 16)
 				ctl_flags = 0x001F0004;
 			else
 				ctl_flags = 0x001F0010;
@@ -800,8 +794,9 @@ static int i2o_block_transfer(struct request *req)
 	if (c->adaptec) {
 		u8 cmd[10];
 		u32 scsi_flags;
-		u16 hwsec = queue_hardsect_size(req->q) >> KERNEL_SECTOR_SHIFT;
+		u16 hwsec;
 
+		hwsec = queue_logical_block_size(req->q) >> KERNEL_SECTOR_SHIFT;
 		memset(cmd, 0, 10);
 
 		sgl_offset = SGL_OFFSET_12;
@@ -827,22 +822,22 @@ static int i2o_block_transfer(struct request *req)
 
 		*mptr++ = cpu_to_le32(scsi_flags);
 
-		*((u32 *) & cmd[2]) = cpu_to_be32(req->sector * hwsec);
-		*((u16 *) & cmd[7]) = cpu_to_be16(req->nr_sectors * hwsec);
+		*((u32 *) & cmd[2]) = cpu_to_be32(blk_rq_pos(req) * hwsec);
+		*((u16 *) & cmd[7]) = cpu_to_be16(blk_rq_sectors(req) * hwsec);
 
 		memcpy(mptr, cmd, 10);
 		mptr += 4;
-		*mptr++ = cpu_to_le32(req->nr_sectors << KERNEL_SECTOR_SHIFT);
+		*mptr++ = cpu_to_le32(blk_rq_bytes(req));
 	} else
 #endif
 	{
 		msg->u.head[1] = cpu_to_le32(cmd | HOST_TID << 12 | tid);
 		*mptr++ = cpu_to_le32(ctl_flags);
-		*mptr++ = cpu_to_le32(req->nr_sectors << KERNEL_SECTOR_SHIFT);
+		*mptr++ = cpu_to_le32(blk_rq_bytes(req));
 		*mptr++ =
-		    cpu_to_le32((u32) (req->sector << KERNEL_SECTOR_SHIFT));
+		    cpu_to_le32((u32) (blk_rq_pos(req) << KERNEL_SECTOR_SHIFT));
 		*mptr++ =
-		    cpu_to_le32(req->sector >> (32 - KERNEL_SECTOR_SHIFT));
+		    cpu_to_le32(blk_rq_pos(req) >> (32 - KERNEL_SECTOR_SHIFT));
 	}
 
 	if (!i2o_block_sglist_alloc(c, ireq, &mptr)) {
@@ -883,7 +878,7 @@ static void i2o_block_request_fn(struct request_queue *q)
 	struct request *req;
 
 	while (!blk_queue_plugged(q)) {
-		req = elv_next_request(q);
+		req = blk_peek_request(q);
 		if (!req)
 			break;
 
@@ -896,7 +891,7 @@ static void i2o_block_request_fn(struct request_queue *q)
 
 			if (queue_depth < I2O_BLOCK_MAX_OPEN_REQUESTS) {
 				if (!i2o_block_transfer(req)) {
-					blkdev_dequeue_request(req);
+					blk_start_request(req);
 					continue;
 				} else
 					osm_info("transfer error\n");
@@ -922,8 +917,10 @@ static void i2o_block_request_fn(struct request_queue *q)
 				blk_stop_queue(q);
 				break;
 			}
-		} else
-			end_request(req, 0);
+		} else {
+			blk_start_request(req);
+			__blk_end_request_all(req, -EIO);
+		}
 	}
 };
 
@@ -1082,7 +1079,7 @@ static int i2o_block_probe(struct device *dev)
 	 */
 	if (!i2o_parm_field_get(i2o_dev, 0x0004, 1, &blocksize, 4) ||
 	    !i2o_parm_field_get(i2o_dev, 0x0000, 3, &blocksize, 4)) {
-		blk_queue_hardsect_size(queue, le32_to_cpu(blocksize));
+		blk_queue_logical_block_size(queue, le32_to_cpu(blocksize));
 	} else
 		osm_warn("unable to get blocksize of %s\n", gd->disk_name);
 
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index b25e9b6516ae..98ffc41eaf2c 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -243,7 +243,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 		brq.mrq.cmd = &brq.cmd;
 		brq.mrq.data = &brq.data;
 
-		brq.cmd.arg = req->sector;
+		brq.cmd.arg = blk_rq_pos(req);
 		if (!mmc_card_blockaddr(card))
 			brq.cmd.arg <<= 9;
 		brq.cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC;
@@ -251,7 +251,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 		brq.stop.opcode = MMC_STOP_TRANSMISSION;
 		brq.stop.arg = 0;
 		brq.stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
-		brq.data.blocks = req->nr_sectors;
+		brq.data.blocks = blk_rq_sectors(req);
 
 		/*
 		 * The block layer doesn't support all sector count
@@ -301,7 +301,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 		 * Adjust the sg list so it is the same size as the
 		 * request.
 		 */
-		if (brq.data.blocks != req->nr_sectors) {
+		if (brq.data.blocks != blk_rq_sectors(req)) {
 			int i, data_size = brq.data.blocks << 9;
 			struct scatterlist *sg;
 
@@ -352,8 +352,8 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 			printk(KERN_ERR "%s: error %d transferring data,"
 			       " sector %u, nr %u, card status %#x\n",
 			       req->rq_disk->disk_name, brq.data.error,
-			       (unsigned)req->sector,
-			       (unsigned)req->nr_sectors, status);
+			       (unsigned)blk_rq_pos(req),
+			       (unsigned)blk_rq_sectors(req), status);
 		}
 
 		if (brq.stop.error) {
@@ -521,7 +521,7 @@ static struct mmc_blk_data *mmc_blk_alloc(struct mmc_card *card)
 
 	sprintf(md->disk->disk_name, "mmcblk%d", devidx);
 
-	blk_queue_hardsect_size(md->queue.queue, 512);
+	blk_queue_logical_block_size(md->queue.queue, 512);
 
 	if (!mmc_card_sd(card) && mmc_card_blockaddr(card)) {
 		/*
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 7a72e75d5c67..49e582356c65 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -55,7 +55,7 @@ static int mmc_queue_thread(void *d)
 		spin_lock_irq(q->queue_lock);
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (!blk_queue_plugged(q))
-			req = elv_next_request(q);
+			req = blk_fetch_request(q);
 		mq->req = req;
 		spin_unlock_irq(q->queue_lock);
 
@@ -88,16 +88,11 @@ static void mmc_request(struct request_queue *q)
 {
 	struct mmc_queue *mq = q->queuedata;
 	struct request *req;
-	int ret;
 
 	if (!mq) {
 		printk(KERN_ERR "MMC: killing requests for dead queue\n");
-		while ((req = elv_next_request(q)) != NULL) {
-			do {
-				ret = __blk_end_request(req, -EIO,
-							blk_rq_cur_bytes(req));
-			} while (ret);
-		}
+		while ((req = blk_fetch_request(q)) != NULL)
+			__blk_end_request_all(req, -EIO);
 		return;
 	}
 
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index a49a9c8f2cb1..aaac3b6800b7 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -47,40 +47,41 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 	unsigned long block, nsect;
 	char *buf;
 
-	block = req->sector << 9 >> tr->blkshift;
-	nsect = req->current_nr_sectors << 9 >> tr->blkshift;
+	block = blk_rq_pos(req) << 9 >> tr->blkshift;
+	nsect = blk_rq_cur_bytes(req) >> tr->blkshift;
 
 	buf = req->buffer;
 
 	if (req->cmd_type == REQ_TYPE_LINUX_BLOCK &&
 	    req->cmd[0] == REQ_LB_OP_DISCARD)
-		return !tr->discard(dev, block, nsect);
+		return tr->discard(dev, block, nsect);
 
 	if (!blk_fs_request(req))
-		return 0;
+		return -EIO;
 
-	if (req->sector + req->current_nr_sectors > get_capacity(req->rq_disk))
-		return 0;
+	if (blk_rq_pos(req) + blk_rq_cur_sectors(req) >
+	    get_capacity(req->rq_disk))
+		return -EIO;
 
 	switch(rq_data_dir(req)) {
 	case READ:
 		for (; nsect > 0; nsect--, block++, buf += tr->blksize)
 			if (tr->readsect(dev, block, buf))
-				return 0;
-		return 1;
+				return -EIO;
+		return 0;
 
 	case WRITE:
 		if (!tr->writesect)
-			return 0;
+			return -EIO;
 
 		for (; nsect > 0; nsect--, block++, buf += tr->blksize)
 			if (tr->writesect(dev, block, buf))
-				return 0;
-		return 1;
+				return -EIO;
+		return 0;
 
 	default:
 		printk(KERN_NOTICE "Unknown request %u\n", rq_data_dir(req));
-		return 0;
+		return -EIO;
 	}
 }
 
@@ -88,19 +89,18 @@ static int mtd_blktrans_thread(void *arg)
 {
 	struct mtd_blktrans_ops *tr = arg;
 	struct request_queue *rq = tr->blkcore_priv->rq;
+	struct request *req = NULL;
 
 	/* we might get involved when memory gets low, so use PF_MEMALLOC */
 	current->flags |= PF_MEMALLOC;
 
 	spin_lock_irq(rq->queue_lock);
+
 	while (!kthread_should_stop()) {
-		struct request *req;
 		struct mtd_blktrans_dev *dev;
-		int res = 0;
+		int res;
 
-		req = elv_next_request(rq);
-
-		if (!req) {
+		if (!req && !(req = blk_fetch_request(rq))) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			spin_unlock_irq(rq->queue_lock);
 			schedule();
@@ -119,8 +119,13 @@ static int mtd_blktrans_thread(void *arg)
 
 		spin_lock_irq(rq->queue_lock);
 
-		end_request(req, res);
+		if (!__blk_end_request_cur(req, res))
+			req = NULL;
 	}
+
+	if (req)
+		__blk_end_request_all(req, -EIO);
+
 	spin_unlock_irq(rq->queue_lock);
 
 	return 0;
@@ -373,7 +378,7 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr)
 	}
 
 	tr->blkcore_priv->rq->queuedata = tr;
-	blk_queue_hardsect_size(tr->blkcore_priv->rq, tr->blksize);
+	blk_queue_logical_block_size(tr->blkcore_priv->rq, tr->blksize);
 	if (tr->discard)
 		blk_queue_set_discard(tr->blkcore_priv->rq,
 				      blktrans_discard_request);
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 73348c4047e9..4a9cc92d4d18 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -702,7 +702,7 @@ static unsigned int iosapic_startup_irq(unsigned int irq)
 }
 
 #ifdef CONFIG_SMP
-static void iosapic_set_affinity_irq(unsigned int irq,
+static int iosapic_set_affinity_irq(unsigned int irq,
 				     const struct cpumask *dest)
 {
 	struct vector_info *vi = iosapic_get_vector(irq);
@@ -712,7 +712,7 @@ static void iosapic_set_affinity_irq(unsigned int irq,
 
 	dest_cpu = cpu_check_affinity(irq, dest);
 	if (dest_cpu < 0)
-		return;
+		return -1;
 
 	cpumask_copy(irq_desc[irq].affinity, cpumask_of(dest_cpu));
 	vi->txn_addr = txn_affinity_addr(irq, dest_cpu);
@@ -724,6 +724,8 @@ static void iosapic_set_affinity_irq(unsigned int irq,
 	iosapic_set_irt_data(vi, &dummy_d0, &d1);
 	iosapic_wr_irt_entry(vi, d0, d1);
 	spin_unlock_irqrestore(&iosapic_lock, flags);
+
+	return 0;
 }
 #endif
 
diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c
index 4e63cc9e2778..151bf5bc8afe 100644
--- a/drivers/parport/parport_pc.c
+++ b/drivers/parport/parport_pc.c
@@ -1,5 +1,5 @@
 /* Low-level parallel-port routines for 8255-based PC-style hardware.
- * 
+ *
  * Authors: Phil Blundell <philb@gnu.org>
  *          Tim Waugh <tim@cyberelk.demon.co.uk>
  *	    Jose Renau <renau@acm.org>
@@ -11,7 +11,7 @@
  * Cleaned up include files - Russell King <linux@arm.uk.linux.org>
  * DMA support - Bert De Jonghe <bert@sophis.be>
  * Many ECP bugs fixed.  Fred Barnes & Jamie Lokier, 1999
- * More PCI support now conditional on CONFIG_PCI, 03/2001, Paul G. 
+ * More PCI support now conditional on CONFIG_PCI, 03/2001, Paul G.
  * Various hacks, Fred Barnes, 04/2001
  * Updated probing logic - Adam Belay <ambx1@neo.rr.com>
  */
@@ -56,10 +56,10 @@
 #include <linux/pnp.h>
 #include <linux/platform_device.h>
 #include <linux/sysctl.h>
+#include <linux/io.h>
+#include <linux/uaccess.h>
 
-#include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/uaccess.h>
 
 #include <linux/parport.h>
 #include <linux/parport_pc.h>
@@ -82,7 +82,7 @@
 #define ECR_TST 06
 #define ECR_CNF 07
 #define ECR_MODE_MASK 0xe0
-#define ECR_WRITE(p,v) frob_econtrol((p),0xff,(v))
+#define ECR_WRITE(p, v) frob_econtrol((p), 0xff, (v))
 
 #undef DEBUG
 
@@ -109,27 +109,27 @@ static int pci_registered_parport;
 static int pnp_registered_parport;
 
 /* frob_control, but for ECR */
-static void frob_econtrol (struct parport *pb, unsigned char m,
+static void frob_econtrol(struct parport *pb, unsigned char m,
 			   unsigned char v)
 {
 	unsigned char ectr = 0;
 
 	if (m != 0xff)
-		ectr = inb (ECONTROL (pb));
+		ectr = inb(ECONTROL(pb));
 
-	DPRINTK (KERN_DEBUG "frob_econtrol(%02x,%02x): %02x -> %02x\n",
+	DPRINTK(KERN_DEBUG "frob_econtrol(%02x,%02x): %02x -> %02x\n",
 		m, v, ectr, (ectr & ~m) ^ v);
 
-	outb ((ectr & ~m) ^ v, ECONTROL (pb));
+	outb((ectr & ~m) ^ v, ECONTROL(pb));
 }
 
-static __inline__ void frob_set_mode (struct parport *p, int mode)
+static inline void frob_set_mode(struct parport *p, int mode)
 {
-	frob_econtrol (p, ECR_MODE_MASK, mode << 5);
+	frob_econtrol(p, ECR_MODE_MASK, mode << 5);
 }
 
 #ifdef CONFIG_PARPORT_PC_FIFO
-/* Safely change the mode bits in the ECR 
+/* Safely change the mode bits in the ECR
    Returns:
 	    0    : Success
 	   -EBUSY: Could not drain FIFO in some finite amount of time,
@@ -141,17 +141,18 @@ static int change_mode(struct parport *p, int m)
 	unsigned char oecr;
 	int mode;
 
-	DPRINTK(KERN_INFO "parport change_mode ECP-ISA to mode 0x%02x\n",m);
+	DPRINTK(KERN_INFO "parport change_mode ECP-ISA to mode 0x%02x\n", m);
 
 	if (!priv->ecr) {
-		printk (KERN_DEBUG "change_mode: but there's no ECR!\n");
+		printk(KERN_DEBUG "change_mode: but there's no ECR!\n");
 		return 0;
 	}
 
 	/* Bits <7:5> contain the mode. */
-	oecr = inb (ECONTROL (p));
+	oecr = inb(ECONTROL(p));
 	mode = (oecr >> 5) & 0x7;
-	if (mode == m) return 0;
+	if (mode == m)
+		return 0;
 
 	if (mode >= 2 && !(priv->ctr & 0x20)) {
 		/* This mode resets the FIFO, so we may
@@ -163,19 +164,21 @@ static int change_mode(struct parport *p, int m)
 		case ECR_ECP: /* ECP Parallel Port mode */
 			/* Busy wait for 200us */
 			for (counter = 0; counter < 40; counter++) {
-				if (inb (ECONTROL (p)) & 0x01)
+				if (inb(ECONTROL(p)) & 0x01)
 					break;
-				if (signal_pending (current)) break;
-				udelay (5);
+				if (signal_pending(current))
+					break;
+				udelay(5);
 			}
 
 			/* Poll slowly. */
-			while (!(inb (ECONTROL (p)) & 0x01)) {
-				if (time_after_eq (jiffies, expire))
+			while (!(inb(ECONTROL(p)) & 0x01)) {
+				if (time_after_eq(jiffies, expire))
 					/* The FIFO is stuck. */
 					return -EBUSY;
-				schedule_timeout_interruptible(msecs_to_jiffies(10));
-				if (signal_pending (current))
+				schedule_timeout_interruptible(
+							msecs_to_jiffies(10));
+				if (signal_pending(current))
 					break;
 			}
 		}
@@ -185,20 +188,20 @@ static int change_mode(struct parport *p, int m)
 		/* We have to go through mode 001 */
 		oecr &= ~(7 << 5);
 		oecr |= ECR_PS2 << 5;
-		ECR_WRITE (p, oecr);
+		ECR_WRITE(p, oecr);
 	}
 
 	/* Set the mode. */
 	oecr &= ~(7 << 5);
 	oecr |= m << 5;
-	ECR_WRITE (p, oecr);
+	ECR_WRITE(p, oecr);
 	return 0;
 }
 
 #ifdef CONFIG_PARPORT_1284
 /* Find FIFO lossage; FIFO is reset */
 #if 0
-static int get_fifo_residue (struct parport *p)
+static int get_fifo_residue(struct parport *p)
 {
 	int residue;
 	int cnfga;
@@ -206,26 +209,26 @@ static int get_fifo_residue (struct parport *p)
 
 	/* Adjust for the contents of the FIFO. */
 	for (residue = priv->fifo_depth; ; residue--) {
-		if (inb (ECONTROL (p)) & 0x2)
+		if (inb(ECONTROL(p)) & 0x2)
 				/* Full up. */
 			break;
 
-		outb (0, FIFO (p));
+		outb(0, FIFO(p));
 	}
 
-	printk (KERN_DEBUG "%s: %d PWords were left in FIFO\n", p->name,
+	printk(KERN_DEBUG "%s: %d PWords were left in FIFO\n", p->name,
 		residue);
 
 	/* Reset the FIFO. */
-	frob_set_mode (p, ECR_PS2);
+	frob_set_mode(p, ECR_PS2);
 
 	/* Now change to config mode and clean up. FIXME */
-	frob_set_mode (p, ECR_CNF);
-	cnfga = inb (CONFIGA (p));
-	printk (KERN_DEBUG "%s: cnfgA contains 0x%02x\n", p->name, cnfga);
+	frob_set_mode(p, ECR_CNF);
+	cnfga = inb(CONFIGA(p));
+	printk(KERN_DEBUG "%s: cnfgA contains 0x%02x\n", p->name, cnfga);
 
 	if (!(cnfga & (1<<2))) {
-		printk (KERN_DEBUG "%s: Accounting for extra byte\n", p->name);
+		printk(KERN_DEBUG "%s: Accounting for extra byte\n", p->name);
 		residue++;
 	}
 
@@ -233,9 +236,11 @@ static int get_fifo_residue (struct parport *p)
 	 * PWord != 1 byte. */
 
 	/* Back to PS2 mode. */
-	frob_set_mode (p, ECR_PS2);
+	frob_set_mode(p, ECR_PS2);
 
-	DPRINTK (KERN_DEBUG "*** get_fifo_residue: done residue collecting (ecr = 0x%2.2x)\n", inb (ECONTROL (p)));
+	DPRINTK(KERN_DEBUG
+	     "*** get_fifo_residue: done residue collecting (ecr = 0x%2.2x)\n",
+							inb(ECONTROL(p)));
 	return residue;
 }
 #endif  /*  0 */
@@ -257,8 +262,8 @@ static int clear_epp_timeout(struct parport *pb)
 	/* To clear timeout some chips require double read */
 	parport_pc_read_status(pb);
 	r = parport_pc_read_status(pb);
-	outb (r | 0x01, STATUS (pb)); /* Some reset by writing 1 */
-	outb (r & 0xfe, STATUS (pb)); /* Others by writing 0 */
+	outb(r | 0x01, STATUS(pb)); /* Some reset by writing 1 */
+	outb(r & 0xfe, STATUS(pb)); /* Others by writing 0 */
 	r = parport_pc_read_status(pb);
 
 	return !(r & 0x01);
@@ -272,7 +277,8 @@ static int clear_epp_timeout(struct parport *pb)
  * of these are in parport_pc.h.
  */
 
-static void parport_pc_init_state(struct pardevice *dev, struct parport_state *s)
+static void parport_pc_init_state(struct pardevice *dev,
+						struct parport_state *s)
 {
 	s->u.pc.ctr = 0xc;
 	if (dev->irq_func &&
@@ -289,22 +295,23 @@ static void parport_pc_save_state(struct parport *p, struct parport_state *s)
 	const struct parport_pc_private *priv = p->physport->private_data;
 	s->u.pc.ctr = priv->ctr;
 	if (priv->ecr)
-		s->u.pc.ecr = inb (ECONTROL (p));
+		s->u.pc.ecr = inb(ECONTROL(p));
 }
 
-static void parport_pc_restore_state(struct parport *p, struct parport_state *s)
+static void parport_pc_restore_state(struct parport *p,
+						struct parport_state *s)
 {
 	struct parport_pc_private *priv = p->physport->private_data;
 	register unsigned char c = s->u.pc.ctr & priv->ctr_writable;
-	outb (c, CONTROL (p));
+	outb(c, CONTROL(p));
 	priv->ctr = c;
 	if (priv->ecr)
-		ECR_WRITE (p, s->u.pc.ecr);
+		ECR_WRITE(p, s->u.pc.ecr);
 }
 
 #ifdef CONFIG_PARPORT_1284
-static size_t parport_pc_epp_read_data (struct parport *port, void *buf,
-					size_t length, int flags)
+static size_t parport_pc_epp_read_data(struct parport *port, void *buf,
+				       size_t length, int flags)
 {
 	size_t got = 0;
 
@@ -316,54 +323,52 @@ static size_t parport_pc_epp_read_data (struct parport *port, void *buf,
 		 *  nFault is 0 if there is at least 1 byte in the Warp's FIFO
 		 *  pError is 1 if there are 16 bytes in the Warp's FIFO
 		 */
-		status = inb (STATUS (port));
+		status = inb(STATUS(port));
 
-		while (!(status & 0x08) && (got < length)) {
-			if ((left >= 16) && (status & 0x20) && !(status & 0x08)) {
+		while (!(status & 0x08) && got < length) {
+			if (left >= 16 && (status & 0x20) && !(status & 0x08)) {
 				/* can grab 16 bytes from warp fifo */
-				if (!((long)buf & 0x03)) {
-					insl (EPPDATA (port), buf, 4);
-				} else {
-					insb (EPPDATA (port), buf, 16);
-				}
+				if (!((long)buf & 0x03))
+					insl(EPPDATA(port), buf, 4);
+				else
+					insb(EPPDATA(port), buf, 16);
 				buf += 16;
 				got += 16;
 				left -= 16;
 			} else {
 				/* grab single byte from the warp fifo */
-				*((char *)buf) = inb (EPPDATA (port));
+				*((char *)buf) = inb(EPPDATA(port));
 				buf++;
 				got++;
 				left--;
 			}
-			status = inb (STATUS (port));
+			status = inb(STATUS(port));
 			if (status & 0x01) {
 				/* EPP timeout should never occur... */
-				printk (KERN_DEBUG "%s: EPP timeout occurred while talking to "
-					"w91284pic (should not have done)\n", port->name);
-				clear_epp_timeout (port);
+				printk(KERN_DEBUG
+"%s: EPP timeout occurred while talking to w91284pic (should not have done)\n", port->name);
+				clear_epp_timeout(port);
 			}
 		}
 		return got;
 	}
 	if ((flags & PARPORT_EPP_FAST) && (length > 1)) {
-		if (!(((long)buf | length) & 0x03)) {
-			insl (EPPDATA (port), buf, (length >> 2));
-		} else {
-			insb (EPPDATA (port), buf, length);
-		}
-		if (inb (STATUS (port)) & 0x01) {
-			clear_epp_timeout (port);
+		if (!(((long)buf | length) & 0x03))
+			insl(EPPDATA(port), buf, (length >> 2));
+		else
+			insb(EPPDATA(port), buf, length);
+		if (inb(STATUS(port)) & 0x01) {
+			clear_epp_timeout(port);
 			return -EIO;
 		}
 		return length;
 	}
 	for (; got < length; got++) {
-		*((char*)buf) = inb (EPPDATA(port));
+		*((char *)buf) = inb(EPPDATA(port));
 		buf++;
-		if (inb (STATUS (port)) & 0x01) {
+		if (inb(STATUS(port)) & 0x01) {
 			/* EPP timeout */
-			clear_epp_timeout (port);
+			clear_epp_timeout(port);
 			break;
 		}
 	}
@@ -371,28 +376,27 @@ static size_t parport_pc_epp_read_data (struct parport *port, void *buf,
 	return got;
 }
 
-static size_t parport_pc_epp_write_data (struct parport *port, const void *buf,
-					 size_t length, int flags)
+static size_t parport_pc_epp_write_data(struct parport *port, const void *buf,
+					size_t length, int flags)
 {
 	size_t written = 0;
 
 	if ((flags & PARPORT_EPP_FAST) && (length > 1)) {
-		if (!(((long)buf | length) & 0x03)) {
-			outsl (EPPDATA (port), buf, (length >> 2));
-		} else {
-			outsb (EPPDATA (port), buf, length);
-		}
-		if (inb (STATUS (port)) & 0x01) {
-			clear_epp_timeout (port);
+		if (!(((long)buf | length) & 0x03))
+			outsl(EPPDATA(port), buf, (length >> 2));
+		else
+			outsb(EPPDATA(port), buf, length);
+		if (inb(STATUS(port)) & 0x01) {
+			clear_epp_timeout(port);
 			return -EIO;
 		}
 		return length;
 	}
 	for (; written < length; written++) {
-		outb (*((char*)buf), EPPDATA(port));
+		outb(*((char *)buf), EPPDATA(port));
 		buf++;
-		if (inb (STATUS(port)) & 0x01) {
-			clear_epp_timeout (port);
+		if (inb(STATUS(port)) & 0x01) {
+			clear_epp_timeout(port);
 			break;
 		}
 	}
@@ -400,24 +404,24 @@ static size_t parport_pc_epp_write_data (struct parport *port, const void *buf,
 	return written;
 }
 
-static size_t parport_pc_epp_read_addr (struct parport *port, void *buf,
+static size_t parport_pc_epp_read_addr(struct parport *port, void *buf,
 					size_t length, int flags)
 {
 	size_t got = 0;
 
 	if ((flags & PARPORT_EPP_FAST) && (length > 1)) {
-		insb (EPPADDR (port), buf, length);
-		if (inb (STATUS (port)) & 0x01) {
-			clear_epp_timeout (port);
+		insb(EPPADDR(port), buf, length);
+		if (inb(STATUS(port)) & 0x01) {
+			clear_epp_timeout(port);
 			return -EIO;
 		}
 		return length;
 	}
 	for (; got < length; got++) {
-		*((char*)buf) = inb (EPPADDR (port));
+		*((char *)buf) = inb(EPPADDR(port));
 		buf++;
-		if (inb (STATUS (port)) & 0x01) {
-			clear_epp_timeout (port);
+		if (inb(STATUS(port)) & 0x01) {
+			clear_epp_timeout(port);
 			break;
 		}
 	}
@@ -425,25 +429,25 @@ static size_t parport_pc_epp_read_addr (struct parport *port, void *buf,
 	return got;
 }
 
-static size_t parport_pc_epp_write_addr (struct parport *port,
+static size_t parport_pc_epp_write_addr(struct parport *port,
 					 const void *buf, size_t length,
 					 int flags)
 {
 	size_t written = 0;
 
 	if ((flags & PARPORT_EPP_FAST) && (length > 1)) {
-		outsb (EPPADDR (port), buf, length);
-		if (inb (STATUS (port)) & 0x01) {
-			clear_epp_timeout (port);
+		outsb(EPPADDR(port), buf, length);
+		if (inb(STATUS(port)) & 0x01) {
+			clear_epp_timeout(port);
 			return -EIO;
 		}
 		return length;
 	}
 	for (; written < length; written++) {
-		outb (*((char*)buf), EPPADDR (port));
+		outb(*((char *)buf), EPPADDR(port));
 		buf++;
-		if (inb (STATUS (port)) & 0x01) {
-			clear_epp_timeout (port);
+		if (inb(STATUS(port)) & 0x01) {
+			clear_epp_timeout(port);
 			break;
 		}
 	}
@@ -451,74 +455,74 @@ static size_t parport_pc_epp_write_addr (struct parport *port,
 	return written;
 }
 
-static size_t parport_pc_ecpepp_read_data (struct parport *port, void *buf,
-					   size_t length, int flags)
+static size_t parport_pc_ecpepp_read_data(struct parport *port, void *buf,
+					  size_t length, int flags)
 {
 	size_t got;
 
-	frob_set_mode (port, ECR_EPP);
-	parport_pc_data_reverse (port);
-	parport_pc_write_control (port, 0x4);
-	got = parport_pc_epp_read_data (port, buf, length, flags);
-	frob_set_mode (port, ECR_PS2);
+	frob_set_mode(port, ECR_EPP);
+	parport_pc_data_reverse(port);
+	parport_pc_write_control(port, 0x4);
+	got = parport_pc_epp_read_data(port, buf, length, flags);
+	frob_set_mode(port, ECR_PS2);
 
 	return got;
 }
 
-static size_t parport_pc_ecpepp_write_data (struct parport *port,
-					    const void *buf, size_t length,
-					    int flags)
+static size_t parport_pc_ecpepp_write_data(struct parport *port,
+					   const void *buf, size_t length,
+					   int flags)
 {
 	size_t written;
 
-	frob_set_mode (port, ECR_EPP);
-	parport_pc_write_control (port, 0x4);
-	parport_pc_data_forward (port);
-	written = parport_pc_epp_write_data (port, buf, length, flags);
-	frob_set_mode (port, ECR_PS2);
+	frob_set_mode(port, ECR_EPP);
+	parport_pc_write_control(port, 0x4);
+	parport_pc_data_forward(port);
+	written = parport_pc_epp_write_data(port, buf, length, flags);
+	frob_set_mode(port, ECR_PS2);
 
 	return written;
 }
 
-static size_t parport_pc_ecpepp_read_addr (struct parport *port, void *buf,
-					   size_t length, int flags)
+static size_t parport_pc_ecpepp_read_addr(struct parport *port, void *buf,
+					  size_t length, int flags)
 {
 	size_t got;
 
-	frob_set_mode (port, ECR_EPP);
-	parport_pc_data_reverse (port);
-	parport_pc_write_control (port, 0x4);
-	got = parport_pc_epp_read_addr (port, buf, length, flags);
-	frob_set_mode (port, ECR_PS2);
+	frob_set_mode(port, ECR_EPP);
+	parport_pc_data_reverse(port);
+	parport_pc_write_control(port, 0x4);
+	got = parport_pc_epp_read_addr(port, buf, length, flags);
+	frob_set_mode(port, ECR_PS2);
 
 	return got;
 }
 
-static size_t parport_pc_ecpepp_write_addr (struct parport *port,
+static size_t parport_pc_ecpepp_write_addr(struct parport *port,
 					    const void *buf, size_t length,
 					    int flags)
 {
 	size_t written;
 
-	frob_set_mode (port, ECR_EPP);
-	parport_pc_write_control (port, 0x4);
-	parport_pc_data_forward (port);
-	written = parport_pc_epp_write_addr (port, buf, length, flags);
-	frob_set_mode (port, ECR_PS2);
+	frob_set_mode(port, ECR_EPP);
+	parport_pc_write_control(port, 0x4);
+	parport_pc_data_forward(port);
+	written = parport_pc_epp_write_addr(port, buf, length, flags);
+	frob_set_mode(port, ECR_PS2);
 
 	return written;
 }
 #endif /* IEEE 1284 support */
 
 #ifdef CONFIG_PARPORT_PC_FIFO
-static size_t parport_pc_fifo_write_block_pio (struct parport *port,
+static size_t parport_pc_fifo_write_block_pio(struct parport *port,
 					       const void *buf, size_t length)
 {
 	int ret = 0;
 	const unsigned char *bufp = buf;
 	size_t left = length;
 	unsigned long expire = jiffies + port->physport->cad->timeout;
-	const int fifo = FIFO (port);
+	const int fifo = FIFO(port);
 	int poll_for = 8; /* 80 usecs */
 	const struct parport_pc_private *priv = port->physport->private_data;
 	const int fifo_depth = priv->fifo_depth;
@@ -526,25 +530,25 @@ static size_t parport_pc_fifo_write_block_pio (struct parport *port,
 	port = port->physport;
 
 	/* We don't want to be interrupted every character. */
-	parport_pc_disable_irq (port);
+	parport_pc_disable_irq(port);
 	/* set nErrIntrEn and serviceIntr */
-	frob_econtrol (port, (1<<4) | (1<<2), (1<<4) | (1<<2));
+	frob_econtrol(port, (1<<4) | (1<<2), (1<<4) | (1<<2));
 
 	/* Forward mode. */
-	parport_pc_data_forward (port); /* Must be in PS2 mode */
+	parport_pc_data_forward(port); /* Must be in PS2 mode */
 
 	while (left) {
 		unsigned char byte;
-		unsigned char ecrval = inb (ECONTROL (port));
+		unsigned char ecrval = inb(ECONTROL(port));
 		int i = 0;
 
-		if (need_resched() && time_before (jiffies, expire))
+		if (need_resched() && time_before(jiffies, expire))
 			/* Can't yield the port. */
-			schedule ();
+			schedule();
 
 		/* Anyone else waiting for the port? */
 		if (port->waithead) {
-			printk (KERN_DEBUG "Somebody wants the port\n");
+			printk(KERN_DEBUG "Somebody wants the port\n");
 			break;
 		}
 
@@ -552,21 +556,22 @@ static size_t parport_pc_fifo_write_block_pio (struct parport *port,
 			/* FIFO is full. Wait for interrupt. */
 
 			/* Clear serviceIntr */
-			ECR_WRITE (port, ecrval & ~(1<<2));
-		false_alarm:
-			ret = parport_wait_event (port, HZ);
-			if (ret < 0) break;
+			ECR_WRITE(port, ecrval & ~(1<<2));
+false_alarm:
+			ret = parport_wait_event(port, HZ);
+			if (ret < 0)
+				break;
 			ret = 0;
-			if (!time_before (jiffies, expire)) {
+			if (!time_before(jiffies, expire)) {
 				/* Timed out. */
-				printk (KERN_DEBUG "FIFO write timed out\n");
+				printk(KERN_DEBUG "FIFO write timed out\n");
 				break;
 			}
-			ecrval = inb (ECONTROL (port));
+			ecrval = inb(ECONTROL(port));
 			if (!(ecrval & (1<<2))) {
 				if (need_resched() &&
-				    time_before (jiffies, expire))
-					schedule ();
+				    time_before(jiffies, expire))
+					schedule();
 
 				goto false_alarm;
 			}
@@ -577,38 +582,38 @@ static size_t parport_pc_fifo_write_block_pio (struct parport *port,
 		/* Can't fail now. */
 		expire = jiffies + port->cad->timeout;
 
-	poll:
-		if (signal_pending (current))
+poll:
+		if (signal_pending(current))
 			break;
 
 		if (ecrval & 0x01) {
 			/* FIFO is empty. Blast it full. */
 			const int n = left < fifo_depth ? left : fifo_depth;
-			outsb (fifo, bufp, n);
+			outsb(fifo, bufp, n);
 			bufp += n;
 			left -= n;
 
 			/* Adjust the poll time. */
-			if (i < (poll_for - 2)) poll_for--;
+			if (i < (poll_for - 2))
+				poll_for--;
 			continue;
 		} else if (i++ < poll_for) {
-			udelay (10);
-			ecrval = inb (ECONTROL (port));
+			udelay(10);
+			ecrval = inb(ECONTROL(port));
 			goto poll;
 		}
 
-		/* Half-full (call me an optimist) */
+		/* Half-full(call me an optimist) */
 		byte = *bufp++;
-		outb (byte, fifo);
+		outb(byte, fifo);
 		left--;
-        }
-
-dump_parport_state ("leave fifo_write_block_pio", port);
+	}
+	dump_parport_state("leave fifo_write_block_pio", port);
 	return length - left;
 }
 
 #ifdef HAS_DMA
-static size_t parport_pc_fifo_write_block_dma (struct parport *port,
+static size_t parport_pc_fifo_write_block_dma(struct parport *port,
 					       const void *buf, size_t length)
 {
 	int ret = 0;
@@ -621,7 +626,7 @@ static size_t parport_pc_fifo_write_block_dma (struct parport *port,
 	unsigned long start = (unsigned long) buf;
 	unsigned long end = (unsigned long) buf + length - 1;
 
-dump_parport_state ("enter fifo_write_block_dma", port);
+	dump_parport_state("enter fifo_write_block_dma", port);
 	if (end < MAX_DMA_ADDRESS) {
 		/* If it would cross a 64k boundary, cap it at the end. */
 		if ((start ^ end) & ~0xffffUL)
@@ -629,8 +634,9 @@ dump_parport_state ("enter fifo_write_block_dma", port);
 
 		dma_addr = dma_handle = dma_map_single(dev, (void *)buf, length,
 						       DMA_TO_DEVICE);
-        } else {
-		/* above 16 MB we use a bounce buffer as ISA-DMA is not possible */
+	} else {
+		/* above 16 MB we use a bounce buffer as ISA-DMA
+		   is not possible */
 		maxlen   = PAGE_SIZE;          /* sizeof(priv->dma_buf) */
 		dma_addr = priv->dma_handle;
 		dma_handle = 0;
@@ -639,12 +645,12 @@ dump_parport_state ("enter fifo_write_block_dma", port);
 	port = port->physport;
 
 	/* We don't want to be interrupted every character. */
-	parport_pc_disable_irq (port);
+	parport_pc_disable_irq(port);
 	/* set nErrIntrEn and serviceIntr */
-	frob_econtrol (port, (1<<4) | (1<<2), (1<<4) | (1<<2));
+	frob_econtrol(port, (1<<4) | (1<<2), (1<<4) | (1<<2));
 
 	/* Forward mode. */
-	parport_pc_data_forward (port); /* Must be in PS2 mode */
+	parport_pc_data_forward(port); /* Must be in PS2 mode */
 
 	while (left) {
 		unsigned long expire = jiffies + port->physport->cad->timeout;
@@ -665,10 +671,10 @@ dump_parport_state ("enter fifo_write_block_dma", port);
 		set_dma_count(port->dma, count);
 
 		/* Set DMA mode */
-		frob_econtrol (port, 1<<3, 1<<3);
+		frob_econtrol(port, 1<<3, 1<<3);
 
 		/* Clear serviceIntr */
-		frob_econtrol (port, 1<<2, 0);
+		frob_econtrol(port, 1<<2, 0);
 
 		enable_dma(port->dma);
 		release_dma_lock(dmaflag);
@@ -676,20 +682,22 @@ dump_parport_state ("enter fifo_write_block_dma", port);
 		/* assume DMA will be successful */
 		left -= count;
 		buf  += count;
-		if (dma_handle) dma_addr += count;
+		if (dma_handle)
+			dma_addr += count;
 
 		/* Wait for interrupt. */
-	false_alarm:
-		ret = parport_wait_event (port, HZ);
-		if (ret < 0) break;
+false_alarm:
+		ret = parport_wait_event(port, HZ);
+		if (ret < 0)
+			break;
 		ret = 0;
-		if (!time_before (jiffies, expire)) {
+		if (!time_before(jiffies, expire)) {
 			/* Timed out. */
-			printk (KERN_DEBUG "DMA write timed out\n");
+			printk(KERN_DEBUG "DMA write timed out\n");
 			break;
 		}
 		/* Is serviceIntr set? */
-		if (!(inb (ECONTROL (port)) & (1<<2))) {
+		if (!(inb(ECONTROL(port)) & (1<<2))) {
 			cond_resched();
 
 			goto false_alarm;
@@ -705,14 +713,15 @@ dump_parport_state ("enter fifo_write_block_dma", port);
 
 		/* Anyone else waiting for the port? */
 		if (port->waithead) {
-			printk (KERN_DEBUG "Somebody wants the port\n");
+			printk(KERN_DEBUG "Somebody wants the port\n");
 			break;
 		}
 
 		/* update for possible DMA residue ! */
 		buf  -= count;
 		left += count;
-		if (dma_handle) dma_addr -= count;
+		if (dma_handle)
+			dma_addr -= count;
 	}
 
 	/* Maybe got here through break, so adjust for DMA residue! */
@@ -723,12 +732,12 @@ dump_parport_state ("enter fifo_write_block_dma", port);
 	release_dma_lock(dmaflag);
 
 	/* Turn off DMA mode */
-	frob_econtrol (port, 1<<3, 0);
+	frob_econtrol(port, 1<<3, 0);
 
 	if (dma_handle)
 		dma_unmap_single(dev, dma_handle, length, DMA_TO_DEVICE);
 
-dump_parport_state ("leave fifo_write_block_dma", port);
+	dump_parport_state("leave fifo_write_block_dma", port);
 	return length - left;
 }
 #endif
@@ -738,13 +747,13 @@ static inline size_t parport_pc_fifo_write_block(struct parport *port,
 {
 #ifdef HAS_DMA
 	if (port->dma != PARPORT_DMA_NONE)
-		return parport_pc_fifo_write_block_dma (port, buf, length);
+		return parport_pc_fifo_write_block_dma(port, buf, length);
 #endif
-	return parport_pc_fifo_write_block_pio (port, buf, length);
+	return parport_pc_fifo_write_block_pio(port, buf, length);
 }
 
 /* Parallel Port FIFO mode (ECP chipsets) */
-static size_t parport_pc_compat_write_block_pio (struct parport *port,
+static size_t parport_pc_compat_write_block_pio(struct parport *port,
 						 const void *buf, size_t length,
 						 int flags)
 {
@@ -756,14 +765,16 @@ static size_t parport_pc_compat_write_block_pio (struct parport *port,
 	/* Special case: a timeout of zero means we cannot call schedule().
 	 * Also if O_NONBLOCK is set then use the default implementation. */
 	if (port->physport->cad->timeout <= PARPORT_INACTIVITY_O_NONBLOCK)
-		return parport_ieee1284_write_compat (port, buf,
+		return parport_ieee1284_write_compat(port, buf,
 						      length, flags);
 
 	/* Set up parallel port FIFO mode.*/
-	parport_pc_data_forward (port); /* Must be in PS2 mode */
-	parport_pc_frob_control (port, PARPORT_CONTROL_STROBE, 0);
-	r = change_mode (port, ECR_PPF); /* Parallel port FIFO */
-	if (r)  printk (KERN_DEBUG "%s: Warning change_mode ECR_PPF failed\n", port->name);
+	parport_pc_data_forward(port); /* Must be in PS2 mode */
+	parport_pc_frob_control(port, PARPORT_CONTROL_STROBE, 0);
+	r = change_mode(port, ECR_PPF); /* Parallel port FIFO */
+	if (r)
+		printk(KERN_DEBUG "%s: Warning change_mode ECR_PPF failed\n",
+								port->name);
 
 	port->physport->ieee1284.phase = IEEE1284_PH_FWD_DATA;
 
@@ -775,40 +786,39 @@ static size_t parport_pc_compat_write_block_pio (struct parport *port,
 	 * the FIFO is empty, so allow 4 seconds for each position
 	 * in the fifo.
 	 */
-        expire = jiffies + (priv->fifo_depth * HZ * 4);
+	expire = jiffies + (priv->fifo_depth * HZ * 4);
 	do {
 		/* Wait for the FIFO to empty */
-		r = change_mode (port, ECR_PS2);
-		if (r != -EBUSY) {
+		r = change_mode(port, ECR_PS2);
+		if (r != -EBUSY)
 			break;
-		}
-	} while (time_before (jiffies, expire));
+	} while (time_before(jiffies, expire));
 	if (r == -EBUSY) {
 
-		printk (KERN_DEBUG "%s: FIFO is stuck\n", port->name);
+		printk(KERN_DEBUG "%s: FIFO is stuck\n", port->name);
 
 		/* Prevent further data transfer. */
-		frob_set_mode (port, ECR_TST);
+		frob_set_mode(port, ECR_TST);
 
 		/* Adjust for the contents of the FIFO. */
 		for (written -= priv->fifo_depth; ; written++) {
-			if (inb (ECONTROL (port)) & 0x2) {
+			if (inb(ECONTROL(port)) & 0x2) {
 				/* Full up. */
 				break;
 			}
-			outb (0, FIFO (port));
+			outb(0, FIFO(port));
 		}
 
 		/* Reset the FIFO and return to PS2 mode. */
-		frob_set_mode (port, ECR_PS2);
+		frob_set_mode(port, ECR_PS2);
 	}
 
-	r = parport_wait_peripheral (port,
+	r = parport_wait_peripheral(port,
 				     PARPORT_STATUS_BUSY,
 				     PARPORT_STATUS_BUSY);
 	if (r)
-		printk (KERN_DEBUG
-			"%s: BUSY timeout (%d) in compat_write_block_pio\n", 
+		printk(KERN_DEBUG
+			"%s: BUSY timeout (%d) in compat_write_block_pio\n",
 			port->name, r);
 
 	port->physport->ieee1284.phase = IEEE1284_PH_FWD_IDLE;
@@ -818,7 +828,7 @@ static size_t parport_pc_compat_write_block_pio (struct parport *port,
 
 /* ECP */
 #ifdef CONFIG_PARPORT_1284
-static size_t parport_pc_ecp_write_block_pio (struct parport *port,
+static size_t parport_pc_ecp_write_block_pio(struct parport *port,
 					      const void *buf, size_t length,
 					      int flags)
 {
@@ -830,36 +840,38 @@ static size_t parport_pc_ecp_write_block_pio (struct parport *port,
 	/* Special case: a timeout of zero means we cannot call schedule().
 	 * Also if O_NONBLOCK is set then use the default implementation. */
 	if (port->physport->cad->timeout <= PARPORT_INACTIVITY_O_NONBLOCK)
-		return parport_ieee1284_ecp_write_data (port, buf,
+		return parport_ieee1284_ecp_write_data(port, buf,
 							length, flags);
 
 	/* Switch to forward mode if necessary. */
 	if (port->physport->ieee1284.phase != IEEE1284_PH_FWD_IDLE) {
 		/* Event 47: Set nInit high. */
-		parport_frob_control (port,
+		parport_frob_control(port,
 				      PARPORT_CONTROL_INIT
 				      | PARPORT_CONTROL_AUTOFD,
 				      PARPORT_CONTROL_INIT
 				      | PARPORT_CONTROL_AUTOFD);
 
 		/* Event 49: PError goes high. */
-		r = parport_wait_peripheral (port,
+		r = parport_wait_peripheral(port,
 					     PARPORT_STATUS_PAPEROUT,
 					     PARPORT_STATUS_PAPEROUT);
 		if (r) {
-			printk (KERN_DEBUG "%s: PError timeout (%d) "
+			printk(KERN_DEBUG "%s: PError timeout (%d) "
 				"in ecp_write_block_pio\n", port->name, r);
 		}
 	}
 
 	/* Set up ECP parallel port mode.*/
-	parport_pc_data_forward (port); /* Must be in PS2 mode */
-	parport_pc_frob_control (port,
+	parport_pc_data_forward(port); /* Must be in PS2 mode */
+	parport_pc_frob_control(port,
 				 PARPORT_CONTROL_STROBE |
 				 PARPORT_CONTROL_AUTOFD,
 				 0);
-	r = change_mode (port, ECR_ECP); /* ECP FIFO */
-	if (r) printk (KERN_DEBUG "%s: Warning change_mode ECR_ECP failed\n", port->name);
+	r = change_mode(port, ECR_ECP); /* ECP FIFO */
+	if (r)
+		printk(KERN_DEBUG "%s: Warning change_mode ECR_ECP failed\n",
+								port->name);
 	port->physport->ieee1284.phase = IEEE1284_PH_FWD_DATA;
 
 	/* Write the data to the FIFO. */
@@ -873,55 +885,54 @@ static size_t parport_pc_ecp_write_block_pio (struct parport *port,
 	expire = jiffies + (priv->fifo_depth * (HZ * 4));
 	do {
 		/* Wait for the FIFO to empty */
-		r = change_mode (port, ECR_PS2);
-		if (r != -EBUSY) {
+		r = change_mode(port, ECR_PS2);
+		if (r != -EBUSY)
 			break;
-		}
-	} while (time_before (jiffies, expire));
+	} while (time_before(jiffies, expire));
 	if (r == -EBUSY) {
 
-		printk (KERN_DEBUG "%s: FIFO is stuck\n", port->name);
+		printk(KERN_DEBUG "%s: FIFO is stuck\n", port->name);
 
 		/* Prevent further data transfer. */
-		frob_set_mode (port, ECR_TST);
+		frob_set_mode(port, ECR_TST);
 
 		/* Adjust for the contents of the FIFO. */
 		for (written -= priv->fifo_depth; ; written++) {
-			if (inb (ECONTROL (port)) & 0x2) {
+			if (inb(ECONTROL(port)) & 0x2) {
 				/* Full up. */
 				break;
 			}
-			outb (0, FIFO (port));
+			outb(0, FIFO(port));
 		}
 
 		/* Reset the FIFO and return to PS2 mode. */
-		frob_set_mode (port, ECR_PS2);
+		frob_set_mode(port, ECR_PS2);
 
 		/* Host transfer recovery. */
-		parport_pc_data_reverse (port); /* Must be in PS2 mode */
-		udelay (5);
-		parport_frob_control (port, PARPORT_CONTROL_INIT, 0);
-		r = parport_wait_peripheral (port, PARPORT_STATUS_PAPEROUT, 0);
+		parport_pc_data_reverse(port); /* Must be in PS2 mode */
+		udelay(5);
+		parport_frob_control(port, PARPORT_CONTROL_INIT, 0);
+		r = parport_wait_peripheral(port, PARPORT_STATUS_PAPEROUT, 0);
 		if (r)
-			printk (KERN_DEBUG "%s: PE,1 timeout (%d) "
+			printk(KERN_DEBUG "%s: PE,1 timeout (%d) "
 				"in ecp_write_block_pio\n", port->name, r);
 
-		parport_frob_control (port,
+		parport_frob_control(port,
 				      PARPORT_CONTROL_INIT,
 				      PARPORT_CONTROL_INIT);
-		r = parport_wait_peripheral (port,
+		r = parport_wait_peripheral(port,
 					     PARPORT_STATUS_PAPEROUT,
 					     PARPORT_STATUS_PAPEROUT);
-                if (r)
-                        printk (KERN_DEBUG "%s: PE,2 timeout (%d) "
+		if (r)
+			printk(KERN_DEBUG "%s: PE,2 timeout (%d) "
 				"in ecp_write_block_pio\n", port->name, r);
 	}
 
-	r = parport_wait_peripheral (port,
-				     PARPORT_STATUS_BUSY, 
+	r = parport_wait_peripheral(port,
+				     PARPORT_STATUS_BUSY,
 				     PARPORT_STATUS_BUSY);
-	if(r)
-		printk (KERN_DEBUG
+	if (r)
+		printk(KERN_DEBUG
 			"%s: BUSY timeout (%d) in ecp_write_block_pio\n",
 			port->name, r);
 
@@ -931,7 +942,7 @@ static size_t parport_pc_ecp_write_block_pio (struct parport *port,
 }
 
 #if 0
-static size_t parport_pc_ecp_read_block_pio (struct parport *port,
+static size_t parport_pc_ecp_read_block_pio(struct parport *port,
 					     void *buf, size_t length,
 					     int flags)
 {
@@ -944,13 +955,13 @@ static size_t parport_pc_ecp_read_block_pio (struct parport *port,
 	char *bufp = buf;
 
 	port = port->physport;
-DPRINTK (KERN_DEBUG "parport_pc: parport_pc_ecp_read_block_pio\n");
-dump_parport_state ("enter fcn", port);
+	DPRINTK(KERN_DEBUG "parport_pc: parport_pc_ecp_read_block_pio\n");
+	dump_parport_state("enter fcn", port);
 
 	/* Special case: a timeout of zero means we cannot call schedule().
 	 * Also if O_NONBLOCK is set then use the default implementation. */
 	if (port->cad->timeout <= PARPORT_INACTIVITY_O_NONBLOCK)
-		return parport_ieee1284_ecp_read_data (port, buf,
+		return parport_ieee1284_ecp_read_data(port, buf,
 						       length, flags);
 
 	if (port->ieee1284.mode == IEEE1284_MODE_ECPRLE) {
@@ -966,173 +977,178 @@ dump_parport_state ("enter fcn", port);
 	 * go through software emulation.  Otherwise we may have to throw
 	 * away data. */
 	if (length < fifofull)
-		return parport_ieee1284_ecp_read_data (port, buf,
+		return parport_ieee1284_ecp_read_data(port, buf,
 						       length, flags);
 
 	if (port->ieee1284.phase != IEEE1284_PH_REV_IDLE) {
 		/* change to reverse-idle phase (must be in forward-idle) */
 
 		/* Event 38: Set nAutoFd low (also make sure nStrobe is high) */
-		parport_frob_control (port,
+		parport_frob_control(port,
 				      PARPORT_CONTROL_AUTOFD
 				      | PARPORT_CONTROL_STROBE,
 				      PARPORT_CONTROL_AUTOFD);
-		parport_pc_data_reverse (port); /* Must be in PS2 mode */
-		udelay (5);
+		parport_pc_data_reverse(port); /* Must be in PS2 mode */
+		udelay(5);
 		/* Event 39: Set nInit low to initiate bus reversal */
-		parport_frob_control (port,
+		parport_frob_control(port,
 				      PARPORT_CONTROL_INIT,
 				      0);
 		/* Event 40: Wait for  nAckReverse (PError) to go low */
-		r = parport_wait_peripheral (port, PARPORT_STATUS_PAPEROUT, 0);
-                if (r) {
-                        printk (KERN_DEBUG "%s: PE timeout Event 40 (%d) "
+		r = parport_wait_peripheral(port, PARPORT_STATUS_PAPEROUT, 0);
+		if (r) {
+			printk(KERN_DEBUG "%s: PE timeout Event 40 (%d) "
 				"in ecp_read_block_pio\n", port->name, r);
 			return 0;
 		}
 	}
 
 	/* Set up ECP FIFO mode.*/
-/*	parport_pc_frob_control (port,
+/*	parport_pc_frob_control(port,
 				 PARPORT_CONTROL_STROBE |
 				 PARPORT_CONTROL_AUTOFD,
 				 PARPORT_CONTROL_AUTOFD); */
-	r = change_mode (port, ECR_ECP); /* ECP FIFO */
-	if (r) printk (KERN_DEBUG "%s: Warning change_mode ECR_ECP failed\n", port->name);
+	r = change_mode(port, ECR_ECP); /* ECP FIFO */
+	if (r)
+		printk(KERN_DEBUG "%s: Warning change_mode ECR_ECP failed\n",
+								port->name);
 
 	port->ieee1284.phase = IEEE1284_PH_REV_DATA;
 
 	/* the first byte must be collected manually */
-dump_parport_state ("pre 43", port);
+	dump_parport_state("pre 43", port);
 	/* Event 43: Wait for nAck to go low */
-	r = parport_wait_peripheral (port, PARPORT_STATUS_ACK, 0);
+	r = parport_wait_peripheral(port, PARPORT_STATUS_ACK, 0);
 	if (r) {
 		/* timed out while reading -- no data */
-		printk (KERN_DEBUG "PIO read timed out (initial byte)\n");
+		printk(KERN_DEBUG "PIO read timed out (initial byte)\n");
 		goto out_no_data;
 	}
 	/* read byte */
-	*bufp++ = inb (DATA (port));
+	*bufp++ = inb(DATA(port));
 	left--;
-dump_parport_state ("43-44", port);
+	dump_parport_state("43-44", port);
 	/* Event 44: nAutoFd (HostAck) goes high to acknowledge */
-	parport_pc_frob_control (port,
+	parport_pc_frob_control(port,
 				 PARPORT_CONTROL_AUTOFD,
 				 0);
-dump_parport_state ("pre 45", port);
+	dump_parport_state("pre 45", port);
 	/* Event 45: Wait for nAck to go high */
-/*	r = parport_wait_peripheral (port, PARPORT_STATUS_ACK, PARPORT_STATUS_ACK); */
-dump_parport_state ("post 45", port);
-r = 0;
+	/* r = parport_wait_peripheral(port, PARPORT_STATUS_ACK,
+						PARPORT_STATUS_ACK); */
+	dump_parport_state("post 45", port);
+	r = 0;
 	if (r) {
 		/* timed out while waiting for peripheral to respond to ack */
-		printk (KERN_DEBUG "ECP PIO read timed out (waiting for nAck)\n");
+		printk(KERN_DEBUG "ECP PIO read timed out (waiting for nAck)\n");
 
 		/* keep hold of the byte we've got already */
 		goto out_no_data;
 	}
 	/* Event 46: nAutoFd (HostAck) goes low to accept more data */
-	parport_pc_frob_control (port,
+	parport_pc_frob_control(port,
 				 PARPORT_CONTROL_AUTOFD,
 				 PARPORT_CONTROL_AUTOFD);
 
 
-dump_parport_state ("rev idle", port);
+	dump_parport_state("rev idle", port);
 	/* Do the transfer. */
 	while (left > fifofull) {
 		int ret;
 		unsigned long expire = jiffies + port->cad->timeout;
-		unsigned char ecrval = inb (ECONTROL (port));
+		unsigned char ecrval = inb(ECONTROL(port));
 
-		if (need_resched() && time_before (jiffies, expire))
+		if (need_resched() && time_before(jiffies, expire))
 			/* Can't yield the port. */
-			schedule ();
+			schedule();
 
 		/* At this point, the FIFO may already be full. In
-                 * that case ECP is already holding back the
-                 * peripheral (assuming proper design) with a delayed
-                 * handshake.  Work fast to avoid a peripheral
-                 * timeout.  */
+		 * that case ECP is already holding back the
+		 * peripheral (assuming proper design) with a delayed
+		 * handshake.  Work fast to avoid a peripheral
+		 * timeout.  */
 
 		if (ecrval & 0x01) {
 			/* FIFO is empty. Wait for interrupt. */
-dump_parport_state ("FIFO empty", port);
+			dump_parport_state("FIFO empty", port);
 
 			/* Anyone else waiting for the port? */
 			if (port->waithead) {
-				printk (KERN_DEBUG "Somebody wants the port\n");
+				printk(KERN_DEBUG "Somebody wants the port\n");
 				break;
 			}
 
 			/* Clear serviceIntr */
-			ECR_WRITE (port, ecrval & ~(1<<2));
-		false_alarm:
-dump_parport_state ("waiting", port);
-			ret = parport_wait_event (port, HZ);
-DPRINTK (KERN_DEBUG "parport_wait_event returned %d\n", ret);
+			ECR_WRITE(port, ecrval & ~(1<<2));
+false_alarm:
+			dump_parport_state("waiting", port);
+			ret = parport_wait_event(port, HZ);
+			DPRINTK(KERN_DEBUG "parport_wait_event returned %d\n",
+									ret);
 			if (ret < 0)
 				break;
 			ret = 0;
-			if (!time_before (jiffies, expire)) {
+			if (!time_before(jiffies, expire)) {
 				/* Timed out. */
-dump_parport_state ("timeout", port);
-				printk (KERN_DEBUG "PIO read timed out\n");
+				dump_parport_state("timeout", port);
+				printk(KERN_DEBUG "PIO read timed out\n");
 				break;
 			}
-			ecrval = inb (ECONTROL (port));
+			ecrval = inb(ECONTROL(port));
 			if (!(ecrval & (1<<2))) {
 				if (need_resched() &&
-				    time_before (jiffies, expire)) {
-					schedule ();
+				    time_before(jiffies, expire)) {
+					schedule();
 				}
 				goto false_alarm;
 			}
 
 			/* Depending on how the FIFO threshold was
-                         * set, how long interrupt service took, and
-                         * how fast the peripheral is, we might be
-                         * lucky and have a just filled FIFO. */
+			 * set, how long interrupt service took, and
+			 * how fast the peripheral is, we might be
+			 * lucky and have a just filled FIFO. */
 			continue;
 		}
 
 		if (ecrval & 0x02) {
 			/* FIFO is full. */
-dump_parport_state ("FIFO full", port);
-			insb (fifo, bufp, fifo_depth);
+			dump_parport_state("FIFO full", port);
+			insb(fifo, bufp, fifo_depth);
 			bufp += fifo_depth;
 			left -= fifo_depth;
 			continue;
 		}
 
-DPRINTK (KERN_DEBUG "*** ecp_read_block_pio: reading one byte from the FIFO\n");
+		DPRINTK(KERN_DEBUG
+		  "*** ecp_read_block_pio: reading one byte from the FIFO\n");
 
 		/* FIFO not filled.  We will cycle this loop for a while
-                 * and either the peripheral will fill it faster,
-                 * tripping a fast empty with insb, or we empty it. */
-		*bufp++ = inb (fifo);
+		 * and either the peripheral will fill it faster,
+		 * tripping a fast empty with insb, or we empty it. */
+		*bufp++ = inb(fifo);
 		left--;
 	}
 
 	/* scoop up anything left in the FIFO */
-	while (left && !(inb (ECONTROL (port) & 0x01))) {
-		*bufp++ = inb (fifo);
+	while (left && !(inb(ECONTROL(port) & 0x01))) {
+		*bufp++ = inb(fifo);
 		left--;
 	}
 
 	port->ieee1284.phase = IEEE1284_PH_REV_IDLE;
-dump_parport_state ("rev idle2", port);
+	dump_parport_state("rev idle2", port);
 
 out_no_data:
 
 	/* Go to forward idle mode to shut the peripheral up (event 47). */
-	parport_frob_control (port, PARPORT_CONTROL_INIT, PARPORT_CONTROL_INIT);
+	parport_frob_control(port, PARPORT_CONTROL_INIT, PARPORT_CONTROL_INIT);
 
 	/* event 49: PError goes high */
-	r = parport_wait_peripheral (port,
+	r = parport_wait_peripheral(port,
 				     PARPORT_STATUS_PAPEROUT,
 				     PARPORT_STATUS_PAPEROUT);
 	if (r) {
-		printk (KERN_DEBUG
+		printk(KERN_DEBUG
 			"%s: PE timeout FWDIDLE (%d) in ecp_read_block_pio\n",
 			port->name, r);
 	}
@@ -1141,14 +1157,14 @@ out_no_data:
 
 	/* Finish up. */
 	{
-		int lost = get_fifo_residue (port);
+		int lost = get_fifo_residue(port);
 		if (lost)
 			/* Shouldn't happen with compliant peripherals. */
-			printk (KERN_DEBUG "%s: DATA LOSS (%d bytes)!\n",
+			printk(KERN_DEBUG "%s: DATA LOSS (%d bytes)!\n",
 				port->name, lost);
 	}
 
-dump_parport_state ("fwd idle", port);
+	dump_parport_state("fwd idle", port);
 	return length - left;
 }
 #endif  /*  0  */
@@ -1164,8 +1180,7 @@ dump_parport_state ("fwd idle", port);
 
 /* GCC is not inlining extern inline function later overwriten to non-inline,
    so we use outlined_ variants here.  */
-static const struct parport_operations parport_pc_ops =
-{
+static const struct parport_operations parport_pc_ops = {
 	.write_data	= parport_pc_write_data,
 	.read_data	= parport_pc_read_data,
 
@@ -1202,88 +1217,107 @@ static const struct parport_operations parport_pc_ops =
 };
 
 #ifdef CONFIG_PARPORT_PC_SUPERIO
+
+static struct superio_struct *find_free_superio(void)
+{
+	int i;
+	for (i = 0; i < NR_SUPERIOS; i++)
+		if (superios[i].io == 0)
+			return &superios[i];
+	return NULL;
+}
+
+
 /* Super-IO chipset detection, Winbond, SMSC */
 static void __devinit show_parconfig_smsc37c669(int io, int key)
 {
-	int cr1,cr4,cra,cr23,cr26,cr27,i=0;
-	static const char *const modes[]={
+	int cr1, cr4, cra, cr23, cr26, cr27;
+	struct superio_struct *s;
+
+	static const char *const modes[] = {
 		"SPP and Bidirectional (PS/2)",
 		"EPP and SPP",
 		"ECP",
 		"ECP and EPP" };
 
-	outb(key,io);
-	outb(key,io);
-	outb(1,io);
-	cr1=inb(io+1);
-	outb(4,io);
-	cr4=inb(io+1);
-	outb(0x0a,io);
-	cra=inb(io+1);
-	outb(0x23,io);
-	cr23=inb(io+1);
-	outb(0x26,io);
-	cr26=inb(io+1);
-	outb(0x27,io);
-	cr27=inb(io+1);
-	outb(0xaa,io);
+	outb(key, io);
+	outb(key, io);
+	outb(1, io);
+	cr1 = inb(io + 1);
+	outb(4, io);
+	cr4 = inb(io + 1);
+	outb(0x0a, io);
+	cra = inb(io + 1);
+	outb(0x23, io);
+	cr23 = inb(io + 1);
+	outb(0x26, io);
+	cr26 = inb(io + 1);
+	outb(0x27, io);
+	cr27 = inb(io + 1);
+	outb(0xaa, io);
 
 	if (verbose_probing) {
-		printk (KERN_INFO "SMSC 37c669 LPT Config: cr_1=0x%02x, 4=0x%02x, "
+		printk(KERN_INFO
+			"SMSC 37c669 LPT Config: cr_1=0x%02x, 4=0x%02x, "
 			"A=0x%2x, 23=0x%02x, 26=0x%02x, 27=0x%02x\n",
-			cr1,cr4,cra,cr23,cr26,cr27);
-		
+			cr1, cr4, cra, cr23, cr26, cr27);
+
 		/* The documentation calls DMA and IRQ-Lines by letters, so
 		   the board maker can/will wire them
 		   appropriately/randomly...  G=reserved H=IDE-irq, */
-		printk (KERN_INFO "SMSC LPT Config: io=0x%04x, irq=%c, dma=%c, "
-			"fifo threshold=%d\n", cr23*4,
-			(cr27 &0x0f) ? 'A'-1+(cr27 &0x0f): '-',
-			(cr26 &0x0f) ? 'A'-1+(cr26 &0x0f): '-', cra & 0x0f);
+		printk(KERN_INFO
+	"SMSC LPT Config: io=0x%04x, irq=%c, dma=%c, fifo threshold=%d\n",
+				cr23 * 4,
+				(cr27 & 0x0f) ? 'A' - 1 + (cr27 & 0x0f) : '-',
+				(cr26 & 0x0f) ? 'A' - 1 + (cr26 & 0x0f) : '-',
+				cra & 0x0f);
 		printk(KERN_INFO "SMSC LPT Config: enabled=%s power=%s\n",
-		       (cr23*4 >=0x100) ?"yes":"no", (cr1 & 4) ? "yes" : "no");
-		printk(KERN_INFO "SMSC LPT Config: Port mode=%s, EPP version =%s\n",
-		       (cr1 & 0x08 ) ? "Standard mode only (SPP)" : modes[cr4 & 0x03], 
-		       (cr4 & 0x40) ? "1.7" : "1.9");
+		       (cr23 * 4 >= 0x100) ? "yes" : "no",
+		       (cr1 & 4) ? "yes" : "no");
+		printk(KERN_INFO
+			"SMSC LPT Config: Port mode=%s, EPP version =%s\n",
+				(cr1 & 0x08) ? "Standard mode only (SPP)"
+					      : modes[cr4 & 0x03],
+				(cr4 & 0x40) ? "1.7" : "1.9");
 	}
-		
+
 	/* Heuristics !  BIOS setup for this mainboard device limits
 	   the choices to standard settings, i.e. io-address and IRQ
 	   are related, however DMA can be 1 or 3, assume DMA_A=DMA1,
 	   DMA_C=DMA3 (this is true e.g. for TYAN 1564D Tomcat IV) */
-	if(cr23*4 >=0x100) { /* if active */
-		while((superios[i].io!= 0) && (i<NR_SUPERIOS))
-			i++;
-		if(i==NR_SUPERIOS)
+	if (cr23 * 4 >= 0x100) { /* if active */
+		s = find_free_superio();
+		if (s == NULL)
 			printk(KERN_INFO "Super-IO: too many chips!\n");
 		else {
 			int d;
-			switch (cr23*4) {
-				case 0x3bc:
-					superios[i].io = 0x3bc;
-					superios[i].irq = 7;
-					break;
-				case 0x378:
-					superios[i].io = 0x378;
-					superios[i].irq = 7;
-					break;
-				case 0x278:
-					superios[i].io = 0x278;
-					superios[i].irq = 5;
+			switch (cr23 * 4) {
+			case 0x3bc:
+				s->io = 0x3bc;
+				s->irq = 7;
+				break;
+			case 0x378:
+				s->io = 0x378;
+				s->irq = 7;
+				break;
+			case 0x278:
+				s->io = 0x278;
+				s->irq = 5;
 			}
-			d=(cr26 &0x0f);
-			if((d==1) || (d==3)) 
-				superios[i].dma= d;
+			d = (cr26 & 0x0f);
+			if (d == 1 || d == 3)
+				s->dma = d;
 			else
-				superios[i].dma= PARPORT_DMA_NONE;
+				s->dma = PARPORT_DMA_NONE;
 		}
- 	}
+	}
 }
 
 
 static void __devinit show_parconfig_winbond(int io, int key)
 {
-	int cr30,cr60,cr61,cr70,cr74,crf0,i=0;
+	int cr30, cr60, cr61, cr70, cr74, crf0;
+	struct superio_struct *s;
 	static const char *const modes[] = {
 		"Standard (SPP) and Bidirectional(PS/2)", /* 0 */
 		"EPP-1.9 and SPP",
@@ -1296,110 +1330,134 @@ static void __devinit show_parconfig_winbond(int io, int key)
 	static char *const irqtypes[] = {
 		"pulsed low, high-Z",
 		"follows nACK" };
-		
+
 	/* The registers are called compatible-PnP because the
-           register layout is modelled after ISA-PnP, the access
-           method is just another ... */
-	outb(key,io);
-	outb(key,io);
-	outb(0x07,io);   /* Register 7: Select Logical Device */
-	outb(0x01,io+1); /* LD1 is Parallel Port */
-	outb(0x30,io);
-	cr30=inb(io+1);
-	outb(0x60,io);
-	cr60=inb(io+1);
-	outb(0x61,io);
-	cr61=inb(io+1);
-	outb(0x70,io);
-	cr70=inb(io+1);
-	outb(0x74,io);
-	cr74=inb(io+1);
-	outb(0xf0,io);
-	crf0=inb(io+1);
-	outb(0xaa,io);
+	   register layout is modelled after ISA-PnP, the access
+	   method is just another ... */
+	outb(key, io);
+	outb(key, io);
+	outb(0x07, io);   /* Register 7: Select Logical Device */
+	outb(0x01, io + 1); /* LD1 is Parallel Port */
+	outb(0x30, io);
+	cr30 = inb(io + 1);
+	outb(0x60, io);
+	cr60 = inb(io + 1);
+	outb(0x61, io);
+	cr61 = inb(io + 1);
+	outb(0x70, io);
+	cr70 = inb(io + 1);
+	outb(0x74, io);
+	cr74 = inb(io + 1);
+	outb(0xf0, io);
+	crf0 = inb(io + 1);
+	outb(0xaa, io);
 
 	if (verbose_probing) {
-		printk(KERN_INFO "Winbond LPT Config: cr_30=%02x 60,61=%02x%02x "
-		       "70=%02x 74=%02x, f0=%02x\n", cr30,cr60,cr61,cr70,cr74,crf0);
-		printk(KERN_INFO "Winbond LPT Config: active=%s, io=0x%02x%02x irq=%d, ", 
-		       (cr30 & 0x01) ? "yes":"no", cr60,cr61,cr70&0x0f );
+		printk(KERN_INFO
+    "Winbond LPT Config: cr_30=%02x 60,61=%02x%02x 70=%02x 74=%02x, f0=%02x\n",
+					cr30, cr60, cr61, cr70, cr74, crf0);
+		printk(KERN_INFO "Winbond LPT Config: active=%s, io=0x%02x%02x irq=%d, ",
+		       (cr30 & 0x01) ? "yes" : "no", cr60, cr61, cr70 & 0x0f);
 		if ((cr74 & 0x07) > 3)
 			printk("dma=none\n");
 		else
-			printk("dma=%d\n",cr74 & 0x07);
-		printk(KERN_INFO "Winbond LPT Config: irqtype=%s, ECP fifo threshold=%d\n",
-		       irqtypes[crf0>>7], (crf0>>3)&0x0f);
-		printk(KERN_INFO "Winbond LPT Config: Port mode=%s\n", modes[crf0 & 0x07]);
+			printk("dma=%d\n", cr74 & 0x07);
+		printk(KERN_INFO
+		    "Winbond LPT Config: irqtype=%s, ECP fifo threshold=%d\n",
+					irqtypes[crf0>>7], (crf0>>3)&0x0f);
+		printk(KERN_INFO "Winbond LPT Config: Port mode=%s\n",
+					modes[crf0 & 0x07]);
 	}
 
-	if(cr30 & 0x01) { /* the settings can be interrogated later ... */
-		while((superios[i].io!= 0) && (i<NR_SUPERIOS))
-			i++;
-		if(i==NR_SUPERIOS) 
+	if (cr30 & 0x01) { /* the settings can be interrogated later ... */
+		s = find_free_superio();
+		if (s == NULL)
 			printk(KERN_INFO "Super-IO: too many chips!\n");
 		else {
-			superios[i].io = (cr60<<8)|cr61;
-			superios[i].irq = cr70&0x0f;
-			superios[i].dma = (((cr74 & 0x07) > 3) ?
+			s->io = (cr60 << 8) | cr61;
+			s->irq = cr70 & 0x0f;
+			s->dma = (((cr74 & 0x07) > 3) ?
 					   PARPORT_DMA_NONE : (cr74 & 0x07));
 		}
 	}
 }
 
-static void __devinit decode_winbond(int efer, int key, int devid, int devrev, int oldid)
+static void __devinit decode_winbond(int efer, int key, int devid,
+							int devrev, int oldid)
 {
 	const char *type = "unknown";
-	int id,progif=2;
+	int id, progif = 2;
 
 	if (devid == devrev)
 		/* simple heuristics, we happened to read some
-                   non-winbond register */
+		   non-winbond register */
 		return;
 
-	id=(devid<<8) | devrev;
+	id = (devid << 8) | devrev;
 
 	/* Values are from public data sheets pdf files, I can just
-           confirm 83977TF is correct :-) */
-	if      (id == 0x9771) type="83977F/AF";
-	else if (id == 0x9773) type="83977TF / SMSC 97w33x/97w34x";
-	else if (id == 0x9774) type="83977ATF";
-	else if ((id & ~0x0f) == 0x5270) type="83977CTF / SMSC 97w36x";
-	else if ((id & ~0x0f) == 0x52f0) type="83977EF / SMSC 97w35x";
-	else if ((id & ~0x0f) == 0x5210) type="83627";
-	else if ((id & ~0x0f) == 0x6010) type="83697HF";
-	else if ((oldid &0x0f ) == 0x0a) { type="83877F"; progif=1;}
-	else if ((oldid &0x0f ) == 0x0b) { type="83877AF"; progif=1;}
-	else if ((oldid &0x0f ) == 0x0c) { type="83877TF"; progif=1;}
-	else if ((oldid &0x0f ) == 0x0d) { type="83877ATF"; progif=1;}
-	else progif=0;
+	   confirm 83977TF is correct :-) */
+	if (id == 0x9771)
+		type = "83977F/AF";
+	else if (id == 0x9773)
+		type = "83977TF / SMSC 97w33x/97w34x";
+	else if (id == 0x9774)
+		type = "83977ATF";
+	else if ((id & ~0x0f) == 0x5270)
+		type = "83977CTF / SMSC 97w36x";
+	else if ((id & ~0x0f) == 0x52f0)
+		type = "83977EF / SMSC 97w35x";
+	else if ((id & ~0x0f) == 0x5210)
+		type = "83627";
+	else if ((id & ~0x0f) == 0x6010)
+		type = "83697HF";
+	else if ((oldid & 0x0f) == 0x0a) {
+		type = "83877F";
+		progif = 1;
+	} else if ((oldid & 0x0f) == 0x0b) {
+		type = "83877AF";
+		progif = 1;
+	} else if ((oldid & 0x0f) == 0x0c) {
+		type = "83877TF";
+		progif = 1;
+	} else if ((oldid & 0x0f) == 0x0d) {
+		type = "83877ATF";
+		progif = 1;
+	} else
+		progif = 0;
 
 	if (verbose_probing)
 		printk(KERN_INFO "Winbond chip at EFER=0x%x key=0x%02x "
-		       "devid=%02x devrev=%02x oldid=%02x type=%s\n", 
+		       "devid=%02x devrev=%02x oldid=%02x type=%s\n",
 		       efer, key, devid, devrev, oldid, type);
 
 	if (progif == 2)
-		show_parconfig_winbond(efer,key);
+		show_parconfig_winbond(efer, key);
 }
 
 static void __devinit decode_smsc(int efer, int key, int devid, int devrev)
 {
-        const char *type = "unknown";
+	const char *type = "unknown";
 	void (*func)(int io, int key);
-        int id;
+	int id;
 
-        if (devid == devrev)
+	if (devid == devrev)
 		/* simple heuristics, we happened to read some
-                   non-smsc register */
+		   non-smsc register */
 		return;
 
-	func=NULL;
-        id=(devid<<8) | devrev;
+	func = NULL;
+	id = (devid << 8) | devrev;
 
-	if	(id==0x0302) {type="37c669"; func=show_parconfig_smsc37c669;}
-	else if	(id==0x6582) type="37c665IR";
-	else if	(devid==0x65) type="37c665GT";
-	else if	(devid==0x66) type="37c666GT";
+	if (id == 0x0302) {
+		type = "37c669";
+		func = show_parconfig_smsc37c669;
+	} else if (id == 0x6582)
+		type = "37c665IR";
+	else if	(devid == 0x65)
+		type = "37c665GT";
+	else if	(devid == 0x66)
+		type = "37c666GT";
 
 	if (verbose_probing)
 		printk(KERN_INFO "SMSC chip at EFER=0x%x "
@@ -1407,138 +1465,138 @@ static void __devinit decode_smsc(int efer, int key, int devid, int devrev)
 		       efer, key, devid, devrev, type);
 
 	if (func)
-		func(efer,key);
+		func(efer, key);
 }
 
 
 static void __devinit winbond_check(int io, int key)
 {
-	int devid,devrev,oldid,x_devid,x_devrev,x_oldid;
+	int devid, devrev, oldid, x_devid, x_devrev, x_oldid;
 
 	if (!request_region(io, 3, __func__))
 		return;
 
 	/* First probe without key */
-	outb(0x20,io);
-	x_devid=inb(io+1);
-	outb(0x21,io);
-	x_devrev=inb(io+1);
-	outb(0x09,io);
-	x_oldid=inb(io+1);
+	outb(0x20, io);
+	x_devid = inb(io + 1);
+	outb(0x21, io);
+	x_devrev = inb(io + 1);
+	outb(0x09, io);
+	x_oldid = inb(io + 1);
 
-	outb(key,io);
-	outb(key,io);     /* Write Magic Sequence to EFER, extended
-                             funtion enable register */
-	outb(0x20,io);    /* Write EFIR, extended function index register */
-	devid=inb(io+1);  /* Read EFDR, extended function data register */
-	outb(0x21,io);
-	devrev=inb(io+1);
-	outb(0x09,io);
-	oldid=inb(io+1);
-	outb(0xaa,io);    /* Magic Seal */
+	outb(key, io);
+	outb(key, io);     /* Write Magic Sequence to EFER, extended
+			      funtion enable register */
+	outb(0x20, io);    /* Write EFIR, extended function index register */
+	devid = inb(io + 1);  /* Read EFDR, extended function data register */
+	outb(0x21, io);
+	devrev = inb(io + 1);
+	outb(0x09, io);
+	oldid = inb(io + 1);
+	outb(0xaa, io);    /* Magic Seal */
 
 	if ((x_devid == devid) && (x_devrev == devrev) && (x_oldid == oldid))
 		goto out; /* protection against false positives */
 
-	decode_winbond(io,key,devid,devrev,oldid);
+	decode_winbond(io, key, devid, devrev, oldid);
 out:
 	release_region(io, 3);
 }
 
-static void __devinit winbond_check2(int io,int key)
+static void __devinit winbond_check2(int io, int key)
 {
-        int devid,devrev,oldid,x_devid,x_devrev,x_oldid;
+	int devid, devrev, oldid, x_devid, x_devrev, x_oldid;
 
 	if (!request_region(io, 3, __func__))
 		return;
 
 	/* First probe without the key */
-	outb(0x20,io+2);
-	x_devid=inb(io+2);
-	outb(0x21,io+1);
-	x_devrev=inb(io+2);
-	outb(0x09,io+1);
-	x_oldid=inb(io+2);
+	outb(0x20, io + 2);
+	x_devid = inb(io + 2);
+	outb(0x21, io + 1);
+	x_devrev = inb(io + 2);
+	outb(0x09, io + 1);
+	x_oldid = inb(io + 2);
 
-        outb(key,io);     /* Write Magic Byte to EFER, extended
-                             funtion enable register */
-        outb(0x20,io+2);  /* Write EFIR, extended function index register */
-        devid=inb(io+2);  /* Read EFDR, extended function data register */
-        outb(0x21,io+1);
-        devrev=inb(io+2);
-        outb(0x09,io+1);
-        oldid=inb(io+2);
-        outb(0xaa,io);    /* Magic Seal */
+	outb(key, io);     /* Write Magic Byte to EFER, extended
+			      funtion enable register */
+	outb(0x20, io + 2);  /* Write EFIR, extended function index register */
+	devid = inb(io + 2);  /* Read EFDR, extended function data register */
+	outb(0x21, io + 1);
+	devrev = inb(io + 2);
+	outb(0x09, io + 1);
+	oldid = inb(io + 2);
+	outb(0xaa, io);    /* Magic Seal */
 
-	if ((x_devid == devid) && (x_devrev == devrev) && (x_oldid == oldid))
+	if (x_devid == devid && x_devrev == devrev && x_oldid == oldid)
 		goto out; /* protection against false positives */
 
-	decode_winbond(io,key,devid,devrev,oldid);
+	decode_winbond(io, key, devid, devrev, oldid);
 out:
 	release_region(io, 3);
 }
 
 static void __devinit smsc_check(int io, int key)
 {
-        int id,rev,oldid,oldrev,x_id,x_rev,x_oldid,x_oldrev;
+	int id, rev, oldid, oldrev, x_id, x_rev, x_oldid, x_oldrev;
 
 	if (!request_region(io, 3, __func__))
 		return;
 
 	/* First probe without the key */
-	outb(0x0d,io);
-	x_oldid=inb(io+1);
-	outb(0x0e,io);
-	x_oldrev=inb(io+1);
-	outb(0x20,io);
-	x_id=inb(io+1);
-	outb(0x21,io);
-	x_rev=inb(io+1);
+	outb(0x0d, io);
+	x_oldid = inb(io + 1);
+	outb(0x0e, io);
+	x_oldrev = inb(io + 1);
+	outb(0x20, io);
+	x_id = inb(io + 1);
+	outb(0x21, io);
+	x_rev = inb(io + 1);
 
-        outb(key,io);
-        outb(key,io);     /* Write Magic Sequence to EFER, extended
-                             funtion enable register */
-        outb(0x0d,io);    /* Write EFIR, extended function index register */
-        oldid=inb(io+1);  /* Read EFDR, extended function data register */
-        outb(0x0e,io);
-        oldrev=inb(io+1);
-	outb(0x20,io);
-	id=inb(io+1);
-	outb(0x21,io);
-	rev=inb(io+1);
-        outb(0xaa,io);    /* Magic Seal */
+	outb(key, io);
+	outb(key, io);     /* Write Magic Sequence to EFER, extended
+			      funtion enable register */
+	outb(0x0d, io);    /* Write EFIR, extended function index register */
+	oldid = inb(io + 1);  /* Read EFDR, extended function data register */
+	outb(0x0e, io);
+	oldrev = inb(io + 1);
+	outb(0x20, io);
+	id = inb(io + 1);
+	outb(0x21, io);
+	rev = inb(io + 1);
+	outb(0xaa, io);    /* Magic Seal */
 
-	if ((x_id == id) && (x_oldrev == oldrev) &&
-	    (x_oldid == oldid) && (x_rev == rev))
+	if (x_id == id && x_oldrev == oldrev &&
+	    x_oldid == oldid && x_rev == rev)
 		goto out; /* protection against false positives */
 
-        decode_smsc(io,key,oldid,oldrev);
+	decode_smsc(io, key, oldid, oldrev);
 out:
 	release_region(io, 3);
 }
 
 
-static void __devinit detect_and_report_winbond (void)
-{ 
+static void __devinit detect_and_report_winbond(void)
+{
 	if (verbose_probing)
 		printk(KERN_DEBUG "Winbond Super-IO detection, now testing ports 3F0,370,250,4E,2E ...\n");
-	winbond_check(0x3f0,0x87);
-	winbond_check(0x370,0x87);
-	winbond_check(0x2e ,0x87);
-	winbond_check(0x4e ,0x87);
-	winbond_check(0x3f0,0x86);
-	winbond_check2(0x250,0x88); 
-	winbond_check2(0x250,0x89);
+	winbond_check(0x3f0, 0x87);
+	winbond_check(0x370, 0x87);
+	winbond_check(0x2e , 0x87);
+	winbond_check(0x4e , 0x87);
+	winbond_check(0x3f0, 0x86);
+	winbond_check2(0x250, 0x88);
+	winbond_check2(0x250, 0x89);
 }
 
-static void __devinit detect_and_report_smsc (void)
+static void __devinit detect_and_report_smsc(void)
 {
 	if (verbose_probing)
 		printk(KERN_DEBUG "SMSC Super-IO detection, now testing Ports 2F0, 370 ...\n");
-	smsc_check(0x3f0,0x55);
-	smsc_check(0x370,0x55);
-	smsc_check(0x3f0,0x44);
-	smsc_check(0x370,0x44);
+	smsc_check(0x3f0, 0x55);
+	smsc_check(0x370, 0x55);
+	smsc_check(0x3f0, 0x44);
+	smsc_check(0x370, 0x44);
 }
 
 static void __devinit detect_and_report_it87(void)
@@ -1573,34 +1631,39 @@ static void __devinit detect_and_report_it87(void)
 }
 #endif /* CONFIG_PARPORT_PC_SUPERIO */
 
-static int get_superio_dma (struct parport *p)
+static struct superio_struct *find_superio(struct parport *p)
 {
-	int i=0;
-	while( (superios[i].io != p->base) && (i<NR_SUPERIOS))
-		i++;
-	if (i!=NR_SUPERIOS)
-		return superios[i].dma;
+	int i;
+	for (i = 0; i < NR_SUPERIOS; i++)
+		if (superios[i].io != p->base)
+			return &superios[i];
+	return NULL;
+}
+
+static int get_superio_dma(struct parport *p)
+{
+	struct superio_struct *s = find_superio(p);
+	if (s)
+		return s->dma;
 	return PARPORT_DMA_NONE;
 }
 
-static int get_superio_irq (struct parport *p)
+static int get_superio_irq(struct parport *p)
 {
-	int i=0;
-        while( (superios[i].io != p->base) && (i<NR_SUPERIOS))
-                i++;
-        if (i!=NR_SUPERIOS)
-                return superios[i].irq;
-        return PARPORT_IRQ_NONE;
+	struct superio_struct *s = find_superio(p);
+	if (s)
+		return s->irq;
+	return PARPORT_IRQ_NONE;
 }
-	
+
 
 /* --- Mode detection ------------------------------------- */
 
 /*
  * Checks for port existence, all ports support SPP MODE
- * Returns: 
+ * Returns:
  *         0           :  No parallel port at this address
- *  PARPORT_MODE_PCSPP :  SPP port detected 
+ *  PARPORT_MODE_PCSPP :  SPP port detected
  *                        (if the user specified an ioport himself,
  *                         this shall always be the case!)
  *
@@ -1610,7 +1673,7 @@ static int parport_SPP_supported(struct parport *pb)
 	unsigned char r, w;
 
 	/*
-	 * first clear an eventually pending EPP timeout 
+	 * first clear an eventually pending EPP timeout
 	 * I (sailer@ife.ee.ethz.ch) have an SMSC chipset
 	 * that does not even respond to SPP cycles if an EPP
 	 * timeout is pending
@@ -1619,19 +1682,19 @@ static int parport_SPP_supported(struct parport *pb)
 
 	/* Do a simple read-write test to make sure the port exists. */
 	w = 0xc;
-	outb (w, CONTROL (pb));
+	outb(w, CONTROL(pb));
 
 	/* Is there a control register that we can read from?  Some
 	 * ports don't allow reads, so read_control just returns a
 	 * software copy. Some ports _do_ allow reads, so bypass the
 	 * software copy here.  In addition, some bits aren't
 	 * writable. */
-	r = inb (CONTROL (pb));
+	r = inb(CONTROL(pb));
 	if ((r & 0xf) == w) {
 		w = 0xe;
-		outb (w, CONTROL (pb));
-		r = inb (CONTROL (pb));
-		outb (0xc, CONTROL (pb));
+		outb(w, CONTROL(pb));
+		r = inb(CONTROL(pb));
+		outb(0xc, CONTROL(pb));
 		if ((r & 0xf) == w)
 			return PARPORT_MODE_PCSPP;
 	}
@@ -1639,18 +1702,18 @@ static int parport_SPP_supported(struct parport *pb)
 	if (user_specified)
 		/* That didn't work, but the user thinks there's a
 		 * port here. */
-		printk (KERN_INFO "parport 0x%lx (WARNING): CTR: "
+		printk(KERN_INFO "parport 0x%lx (WARNING): CTR: "
 			"wrote 0x%02x, read 0x%02x\n", pb->base, w, r);
 
 	/* Try the data register.  The data lines aren't tri-stated at
 	 * this stage, so we expect back what we wrote. */
 	w = 0xaa;
-	parport_pc_write_data (pb, w);
-	r = parport_pc_read_data (pb);
+	parport_pc_write_data(pb, w);
+	r = parport_pc_read_data(pb);
 	if (r == w) {
 		w = 0x55;
-		parport_pc_write_data (pb, w);
-		r = parport_pc_read_data (pb);
+		parport_pc_write_data(pb, w);
+		r = parport_pc_read_data(pb);
 		if (r == w)
 			return PARPORT_MODE_PCSPP;
 	}
@@ -1658,9 +1721,9 @@ static int parport_SPP_supported(struct parport *pb)
 	if (user_specified) {
 		/* Didn't work, but the user is convinced this is the
 		 * place. */
-		printk (KERN_INFO "parport 0x%lx (WARNING): DATA: "
+		printk(KERN_INFO "parport 0x%lx (WARNING): DATA: "
 			"wrote 0x%02x, read 0x%02x\n", pb->base, w, r);
-		printk (KERN_INFO "parport 0x%lx: You gave this address, "
+		printk(KERN_INFO "parport 0x%lx: You gave this address, "
 			"but there is probably no parallel port there!\n",
 			pb->base);
 	}
@@ -1691,33 +1754,33 @@ static int parport_ECR_present(struct parport *pb)
 	struct parport_pc_private *priv = pb->private_data;
 	unsigned char r = 0xc;
 
-	outb (r, CONTROL (pb));
-	if ((inb (ECONTROL (pb)) & 0x3) == (r & 0x3)) {
-		outb (r ^ 0x2, CONTROL (pb)); /* Toggle bit 1 */
+	outb(r, CONTROL(pb));
+	if ((inb(ECONTROL(pb)) & 0x3) == (r & 0x3)) {
+		outb(r ^ 0x2, CONTROL(pb)); /* Toggle bit 1 */
 
-		r = inb (CONTROL (pb));
-		if ((inb (ECONTROL (pb)) & 0x2) == (r & 0x2))
+		r = inb(CONTROL(pb));
+		if ((inb(ECONTROL(pb)) & 0x2) == (r & 0x2))
 			goto no_reg; /* Sure that no ECR register exists */
 	}
-	
-	if ((inb (ECONTROL (pb)) & 0x3 ) != 0x1)
+
+	if ((inb(ECONTROL(pb)) & 0x3) != 0x1)
 		goto no_reg;
 
-	ECR_WRITE (pb, 0x34);
-	if (inb (ECONTROL (pb)) != 0x35)
+	ECR_WRITE(pb, 0x34);
+	if (inb(ECONTROL(pb)) != 0x35)
 		goto no_reg;
 
 	priv->ecr = 1;
-	outb (0xc, CONTROL (pb));
-	
+	outb(0xc, CONTROL(pb));
+
 	/* Go to mode 000 */
-	frob_set_mode (pb, ECR_SPP);
+	frob_set_mode(pb, ECR_SPP);
 
 	return 1;
 
  no_reg:
-	outb (0xc, CONTROL (pb));
-	return 0; 
+	outb(0xc, CONTROL(pb));
+	return 0;
 }
 
 #ifdef CONFIG_PARPORT_1284
@@ -1727,7 +1790,7 @@ static int parport_ECR_present(struct parport *pb)
  * allows us to read data from the data lines.  In theory we would get back
  * 0xff but any peripheral attached to the port may drag some or all of the
  * lines down to zero.  So if we get back anything that isn't the contents
- * of the data register we deem PS/2 support to be present. 
+ * of the data register we deem PS/2 support to be present.
  *
  * Some SPP ports have "half PS/2" ability - you can't turn off the line
  * drivers, but an external peripheral with sufficiently beefy drivers of
@@ -1735,26 +1798,28 @@ static int parport_ECR_present(struct parport *pb)
  * where they can then be read back as normal.  Ports with this property
  * and the right type of device attached are likely to fail the SPP test,
  * (as they will appear to have stuck bits) and so the fact that they might
- * be misdetected here is rather academic. 
+ * be misdetected here is rather academic.
  */
 
 static int parport_PS2_supported(struct parport *pb)
 {
 	int ok = 0;
-  
+
 	clear_epp_timeout(pb);
 
 	/* try to tri-state the buffer */
-	parport_pc_data_reverse (pb);
-	
+	parport_pc_data_reverse(pb);
+
 	parport_pc_write_data(pb, 0x55);
-	if (parport_pc_read_data(pb) != 0x55) ok++;
+	if (parport_pc_read_data(pb) != 0x55)
+		ok++;
 
 	parport_pc_write_data(pb, 0xaa);
-	if (parport_pc_read_data(pb) != 0xaa) ok++;
+	if (parport_pc_read_data(pb) != 0xaa)
+		ok++;
 
 	/* cancel input mode */
-	parport_pc_data_forward (pb);
+	parport_pc_data_forward(pb);
 
 	if (ok) {
 		pb->modes |= PARPORT_MODE_TRISTATE;
@@ -1773,68 +1838,68 @@ static int parport_ECP_supported(struct parport *pb)
 	int config, configb;
 	int pword;
 	struct parport_pc_private *priv = pb->private_data;
-	/* Translate ECP intrLine to ISA irq value */	
-	static const int intrline[]= { 0, 7, 9, 10, 11, 14, 15, 5 }; 
+	/* Translate ECP intrLine to ISA irq value */
+	static const int intrline[] = { 0, 7, 9, 10, 11, 14, 15, 5 };
 
 	/* If there is no ECR, we have no hope of supporting ECP. */
 	if (!priv->ecr)
 		return 0;
 
 	/* Find out FIFO depth */
-	ECR_WRITE (pb, ECR_SPP << 5); /* Reset FIFO */
-	ECR_WRITE (pb, ECR_TST << 5); /* TEST FIFO */
-	for (i=0; i < 1024 && !(inb (ECONTROL (pb)) & 0x02); i++)
-		outb (0xaa, FIFO (pb));
+	ECR_WRITE(pb, ECR_SPP << 5); /* Reset FIFO */
+	ECR_WRITE(pb, ECR_TST << 5); /* TEST FIFO */
+	for (i = 0; i < 1024 && !(inb(ECONTROL(pb)) & 0x02); i++)
+		outb(0xaa, FIFO(pb));
 
 	/*
 	 * Using LGS chipset it uses ECR register, but
 	 * it doesn't support ECP or FIFO MODE
 	 */
 	if (i == 1024) {
-		ECR_WRITE (pb, ECR_SPP << 5);
+		ECR_WRITE(pb, ECR_SPP << 5);
 		return 0;
 	}
 
 	priv->fifo_depth = i;
 	if (verbose_probing)
-		printk (KERN_DEBUG "0x%lx: FIFO is %d bytes\n", pb->base, i);
+		printk(KERN_DEBUG "0x%lx: FIFO is %d bytes\n", pb->base, i);
 
 	/* Find out writeIntrThreshold */
-	frob_econtrol (pb, 1<<2, 1<<2);
-	frob_econtrol (pb, 1<<2, 0);
+	frob_econtrol(pb, 1<<2, 1<<2);
+	frob_econtrol(pb, 1<<2, 0);
 	for (i = 1; i <= priv->fifo_depth; i++) {
-		inb (FIFO (pb));
-		udelay (50);
-		if (inb (ECONTROL (pb)) & (1<<2))
+		inb(FIFO(pb));
+		udelay(50);
+		if (inb(ECONTROL(pb)) & (1<<2))
 			break;
 	}
 
 	if (i <= priv->fifo_depth) {
 		if (verbose_probing)
-			printk (KERN_DEBUG "0x%lx: writeIntrThreshold is %d\n",
+			printk(KERN_DEBUG "0x%lx: writeIntrThreshold is %d\n",
 				pb->base, i);
 	} else
 		/* Number of bytes we know we can write if we get an
-                   interrupt. */
+		   interrupt. */
 		i = 0;
 
 	priv->writeIntrThreshold = i;
 
 	/* Find out readIntrThreshold */
-	frob_set_mode (pb, ECR_PS2); /* Reset FIFO and enable PS2 */
-	parport_pc_data_reverse (pb); /* Must be in PS2 mode */
-	frob_set_mode (pb, ECR_TST); /* Test FIFO */
-	frob_econtrol (pb, 1<<2, 1<<2);
-	frob_econtrol (pb, 1<<2, 0);
+	frob_set_mode(pb, ECR_PS2); /* Reset FIFO and enable PS2 */
+	parport_pc_data_reverse(pb); /* Must be in PS2 mode */
+	frob_set_mode(pb, ECR_TST); /* Test FIFO */
+	frob_econtrol(pb, 1<<2, 1<<2);
+	frob_econtrol(pb, 1<<2, 0);
 	for (i = 1; i <= priv->fifo_depth; i++) {
-		outb (0xaa, FIFO (pb));
-		if (inb (ECONTROL (pb)) & (1<<2))
+		outb(0xaa, FIFO(pb));
+		if (inb(ECONTROL(pb)) & (1<<2))
 			break;
 	}
 
 	if (i <= priv->fifo_depth) {
 		if (verbose_probing)
-			printk (KERN_INFO "0x%lx: readIntrThreshold is %d\n",
+			printk(KERN_INFO "0x%lx: readIntrThreshold is %d\n",
 				pb->base, i);
 	} else
 		/* Number of bytes we can read if we get an interrupt. */
@@ -1842,23 +1907,23 @@ static int parport_ECP_supported(struct parport *pb)
 
 	priv->readIntrThreshold = i;
 
-	ECR_WRITE (pb, ECR_SPP << 5); /* Reset FIFO */
-	ECR_WRITE (pb, 0xf4); /* Configuration mode */
-	config = inb (CONFIGA (pb));
+	ECR_WRITE(pb, ECR_SPP << 5); /* Reset FIFO */
+	ECR_WRITE(pb, 0xf4); /* Configuration mode */
+	config = inb(CONFIGA(pb));
 	pword = (config >> 4) & 0x7;
 	switch (pword) {
 	case 0:
 		pword = 2;
-		printk (KERN_WARNING "0x%lx: Unsupported pword size!\n",
+		printk(KERN_WARNING "0x%lx: Unsupported pword size!\n",
 			pb->base);
 		break;
 	case 2:
 		pword = 4;
-		printk (KERN_WARNING "0x%lx: Unsupported pword size!\n",
+		printk(KERN_WARNING "0x%lx: Unsupported pword size!\n",
 			pb->base);
 		break;
 	default:
-		printk (KERN_WARNING "0x%lx: Unknown implementation ID\n",
+		printk(KERN_WARNING "0x%lx: Unknown implementation ID\n",
 			pb->base);
 		/* Assume 1 */
 	case 1:
@@ -1867,28 +1932,29 @@ static int parport_ECP_supported(struct parport *pb)
 	priv->pword = pword;
 
 	if (verbose_probing) {
-		printk (KERN_DEBUG "0x%lx: PWord is %d bits\n", pb->base, 8 * pword);
-		
-		printk (KERN_DEBUG "0x%lx: Interrupts are ISA-%s\n", pb->base,
+		printk(KERN_DEBUG "0x%lx: PWord is %d bits\n",
+			pb->base, 8 * pword);
+
+		printk(KERN_DEBUG "0x%lx: Interrupts are ISA-%s\n", pb->base,
 			config & 0x80 ? "Level" : "Pulses");
 
-		configb = inb (CONFIGB (pb));
-		printk (KERN_DEBUG "0x%lx: ECP port cfgA=0x%02x cfgB=0x%02x\n",
+		configb = inb(CONFIGB(pb));
+		printk(KERN_DEBUG "0x%lx: ECP port cfgA=0x%02x cfgB=0x%02x\n",
 			pb->base, config, configb);
-		printk (KERN_DEBUG "0x%lx: ECP settings irq=", pb->base);
-		if ((configb >>3) & 0x07)
-			printk("%d",intrline[(configb >>3) & 0x07]);
+		printk(KERN_DEBUG "0x%lx: ECP settings irq=", pb->base);
+		if ((configb >> 3) & 0x07)
+			printk("%d", intrline[(configb >> 3) & 0x07]);
 		else
 			printk("<none or set by other means>");
-		printk (" dma=");
-		if( (configb & 0x03 ) == 0x00)
+		printk(" dma=");
+		if ((configb & 0x03) == 0x00)
 			printk("<none or set by other means>\n");
 		else
-			printk("%d\n",configb & 0x07);
+			printk("%d\n", configb & 0x07);
 	}
 
 	/* Go back to mode 000 */
-	frob_set_mode (pb, ECR_SPP);
+	frob_set_mode(pb, ECR_SPP);
 
 	return 1;
 }
@@ -1903,10 +1969,10 @@ static int parport_ECPPS2_supported(struct parport *pb)
 	if (!priv->ecr)
 		return 0;
 
-	oecr = inb (ECONTROL (pb));
-	ECR_WRITE (pb, ECR_PS2 << 5);
+	oecr = inb(ECONTROL(pb));
+	ECR_WRITE(pb, ECR_PS2 << 5);
 	result = parport_PS2_supported(pb);
-	ECR_WRITE (pb, oecr);
+	ECR_WRITE(pb, oecr);
 	return result;
 }
 
@@ -1930,16 +1996,15 @@ static int parport_EPP_supported(struct parport *pb)
 	 */
 
 	/* If EPP timeout bit clear then EPP available */
-	if (!clear_epp_timeout(pb)) {
+	if (!clear_epp_timeout(pb))
 		return 0;  /* No way to clear timeout */
-	}
 
 	/* Check for Intel bug. */
 	if (priv->ecr) {
 		unsigned char i;
 		for (i = 0x00; i < 0x80; i += 0x20) {
-			ECR_WRITE (pb, i);
-			if (clear_epp_timeout (pb)) {
+			ECR_WRITE(pb, i);
+			if (clear_epp_timeout(pb)) {
 				/* Phony EPP in ECP. */
 				return 0;
 			}
@@ -1963,17 +2028,16 @@ static int parport_ECPEPP_supported(struct parport *pb)
 	int result;
 	unsigned char oecr;
 
-	if (!priv->ecr) {
+	if (!priv->ecr)
 		return 0;
-	}
 
-	oecr = inb (ECONTROL (pb));
+	oecr = inb(ECONTROL(pb));
 	/* Search for SMC style EPP+ECP mode */
-	ECR_WRITE (pb, 0x80);
-	outb (0x04, CONTROL (pb));
+	ECR_WRITE(pb, 0x80);
+	outb(0x04, CONTROL(pb));
 	result = parport_EPP_supported(pb);
 
-	ECR_WRITE (pb, oecr);
+	ECR_WRITE(pb, oecr);
 
 	if (result) {
 		/* Set up access functions to use ECP+EPP hardware. */
@@ -1991,11 +2055,25 @@ static int parport_ECPEPP_supported(struct parport *pb)
 /* Don't bother probing for modes we know we won't use. */
 static int __devinit parport_PS2_supported(struct parport *pb) { return 0; }
 #ifdef CONFIG_PARPORT_PC_FIFO
-static int parport_ECP_supported(struct parport *pb) { return 0; }
+static int parport_ECP_supported(struct parport *pb)
+{
+	return 0;
+}
 #endif
-static int __devinit parport_EPP_supported(struct parport *pb) { return 0; }
-static int __devinit parport_ECPEPP_supported(struct parport *pb){return 0;}
-static int __devinit parport_ECPPS2_supported(struct parport *pb){return 0;}
+static int __devinit parport_EPP_supported(struct parport *pb)
+{
+	return 0;
+}
+
+static int __devinit parport_ECPEPP_supported(struct parport *pb)
+{
+	return 0;
+}
+
+static int __devinit parport_ECPPS2_supported(struct parport *pb)
+{
+	return 0;
+}
 
 #endif /* No IEEE 1284 support */
 
@@ -2005,17 +2083,17 @@ static int __devinit parport_ECPPS2_supported(struct parport *pb){return 0;}
 static int programmable_irq_support(struct parport *pb)
 {
 	int irq, intrLine;
-	unsigned char oecr = inb (ECONTROL (pb));
+	unsigned char oecr = inb(ECONTROL(pb));
 	static const int lookup[8] = {
 		PARPORT_IRQ_NONE, 7, 9, 10, 11, 14, 15, 5
 	};
 
-	ECR_WRITE (pb, ECR_CNF << 5); /* Configuration MODE */
+	ECR_WRITE(pb, ECR_CNF << 5); /* Configuration MODE */
 
-	intrLine = (inb (CONFIGB (pb)) >> 3) & 0x07;
+	intrLine = (inb(CONFIGB(pb)) >> 3) & 0x07;
 	irq = lookup[intrLine];
 
-	ECR_WRITE (pb, oecr);
+	ECR_WRITE(pb, oecr);
 	return irq;
 }
 
@@ -2025,17 +2103,17 @@ static int irq_probe_ECP(struct parport *pb)
 	unsigned long irqs;
 
 	irqs = probe_irq_on();
-		
-	ECR_WRITE (pb, ECR_SPP << 5); /* Reset FIFO */
-	ECR_WRITE (pb, (ECR_TST << 5) | 0x04);
-	ECR_WRITE (pb, ECR_TST << 5);
+
+	ECR_WRITE(pb, ECR_SPP << 5); /* Reset FIFO */
+	ECR_WRITE(pb, (ECR_TST << 5) | 0x04);
+	ECR_WRITE(pb, ECR_TST << 5);
 
 	/* If Full FIFO sure that writeIntrThreshold is generated */
-	for (i=0; i < 1024 && !(inb (ECONTROL (pb)) & 0x02) ; i++) 
-		outb (0xaa, FIFO (pb));
-		
+	for (i = 0; i < 1024 && !(inb(ECONTROL(pb)) & 0x02) ; i++)
+		outb(0xaa, FIFO(pb));
+
 	pb->irq = probe_irq_off(irqs);
-	ECR_WRITE (pb, ECR_SPP << 5);
+	ECR_WRITE(pb, ECR_SPP << 5);
 
 	if (pb->irq <= 0)
 		pb->irq = PARPORT_IRQ_NONE;
@@ -2045,7 +2123,7 @@ static int irq_probe_ECP(struct parport *pb)
 
 /*
  * This detection seems that only works in National Semiconductors
- * This doesn't work in SMC, LGS, and Winbond 
+ * This doesn't work in SMC, LGS, and Winbond
  */
 static int irq_probe_EPP(struct parport *pb)
 {
@@ -2056,16 +2134,16 @@ static int irq_probe_EPP(struct parport *pb)
 	unsigned char oecr;
 
 	if (pb->modes & PARPORT_MODE_PCECR)
-		oecr = inb (ECONTROL (pb));
+		oecr = inb(ECONTROL(pb));
 
 	irqs = probe_irq_on();
 
 	if (pb->modes & PARPORT_MODE_PCECR)
-		frob_econtrol (pb, 0x10, 0x10);
-	
+		frob_econtrol(pb, 0x10, 0x10);
+
 	clear_epp_timeout(pb);
-	parport_pc_frob_control (pb, 0x20, 0x20);
-	parport_pc_frob_control (pb, 0x10, 0x10);
+	parport_pc_frob_control(pb, 0x20, 0x20);
+	parport_pc_frob_control(pb, 0x10, 0x10);
 	clear_epp_timeout(pb);
 
 	/* Device isn't expecting an EPP read
@@ -2074,9 +2152,9 @@ static int irq_probe_EPP(struct parport *pb)
 	parport_pc_read_epp(pb);
 	udelay(20);
 
-	pb->irq = probe_irq_off (irqs);
+	pb->irq = probe_irq_off(irqs);
 	if (pb->modes & PARPORT_MODE_PCECR)
-		ECR_WRITE (pb, oecr);
+		ECR_WRITE(pb, oecr);
 	parport_pc_write_control(pb, 0xc);
 
 	if (pb->irq <= 0)
@@ -2133,28 +2211,28 @@ static int parport_irq_probe(struct parport *pb)
 /* --- DMA detection -------------------------------------- */
 
 /* Only if chipset conforms to ECP ISA Interface Standard */
-static int programmable_dma_support (struct parport *p)
+static int programmable_dma_support(struct parport *p)
 {
-	unsigned char oecr = inb (ECONTROL (p));
+	unsigned char oecr = inb(ECONTROL(p));
 	int dma;
 
-	frob_set_mode (p, ECR_CNF);
-	
-	dma = inb (CONFIGB(p)) & 0x07;
+	frob_set_mode(p, ECR_CNF);
+
+	dma = inb(CONFIGB(p)) & 0x07;
 	/* 000: Indicates jumpered 8-bit DMA if read-only.
 	   100: Indicates jumpered 16-bit DMA if read-only. */
 	if ((dma & 0x03) == 0)
 		dma = PARPORT_DMA_NONE;
 
-	ECR_WRITE (p, oecr);
+	ECR_WRITE(p, oecr);
 	return dma;
 }
 
-static int parport_dma_probe (struct parport *p)
+static int parport_dma_probe(struct parport *p)
 {
 	const struct parport_pc_private *priv = p->private_data;
-	if (priv->ecr)
-		p->dma = programmable_dma_support(p); /* ask ECP chipset first */
+	if (priv->ecr)		/* ask ECP chipset first */
+		p->dma = programmable_dma_support(p);
 	if (p->dma == PARPORT_DMA_NONE) {
 		/* ask known Super-IO chips proper, although these
 		   claim ECP compatible, some don't report their DMA
@@ -2212,7 +2290,7 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 	if (!base_res)
 		goto out4;
 
-	memcpy(ops, &parport_pc_ops, sizeof (struct parport_operations));
+	memcpy(ops, &parport_pc_ops, sizeof(struct parport_operations));
 	priv->ctr = 0xc;
 	priv->ctr_writable = ~0x10;
 	priv->ecr = 0;
@@ -2239,7 +2317,7 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 			if (!parport_EPP_supported(p))
 				parport_ECPEPP_supported(p);
 	}
-	if (!parport_SPP_supported (p))
+	if (!parport_SPP_supported(p))
 		/* No port. */
 		goto out5;
 	if (priv->ecr)
@@ -2247,7 +2325,7 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 	else
 		parport_PS2_supported(p);
 
-	p->size = (p->modes & PARPORT_MODE_EPP)?8:3;
+	p->size = (p->modes & PARPORT_MODE_EPP) ? 8 : 3;
 
 	printk(KERN_INFO "%s: PC-style at 0x%lx", p->name, p->base);
 	if (p->base_hi && priv->ecr)
@@ -2271,7 +2349,7 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 		}
 	}
 	if (p->dma == PARPORT_DMA_AUTO) /* To use DMA, giving the irq
-                                           is mandatory (see above) */
+					   is mandatory (see above) */
 		p->dma = PARPORT_DMA_NONE;
 
 #ifdef CONFIG_PARPORT_PC_FIFO
@@ -2288,16 +2366,23 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 		if (p->dma != PARPORT_DMA_NONE) {
 			printk(", dma %d", p->dma);
 			p->modes |= PARPORT_MODE_DMA;
-		}
-		else printk(", using FIFO");
-	}
-	else
+		} else
+			printk(", using FIFO");
+	} else
 		/* We can't use the DMA channel after all. */
 		p->dma = PARPORT_DMA_NONE;
 #endif /* Allowed to use FIFO/DMA */
 
 	printk(" [");
-#define printmode(x) {if(p->modes&PARPORT_MODE_##x){printk("%s%s",f?",":"",#x);f++;}}
+
+#define printmode(x) \
+	{\
+		if (p->modes & PARPORT_MODE_##x) {\
+			printk("%s%s", f ? "," : "", #x);\
+			f++;\
+		} \
+	}
+
 	{
 		int f = 0;
 		printmode(PCSPP);
@@ -2309,10 +2394,10 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 	}
 #undef printmode
 #ifndef CONFIG_PARPORT_1284
-	printk ("(,...)");
+	printk("(,...)");
 #endif /* CONFIG_PARPORT_1284 */
 	printk("]\n");
-	if (probedirq != PARPORT_IRQ_NONE) 
+	if (probedirq != PARPORT_IRQ_NONE)
 		printk(KERN_INFO "%s: irq %d detected\n", p->name, probedirq);
 
 	/* If No ECP release the ports grabbed above. */
@@ -2328,7 +2413,7 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 	if (p->irq != PARPORT_IRQ_NONE) {
 		if (request_irq(p->irq, parport_irq_handler,
 				 irqflags, p->name, p)) {
-			printk (KERN_WARNING "%s: irq %d in use, "
+			printk(KERN_WARNING "%s: irq %d in use, "
 				"resorting to polled operation\n",
 				p->name, p->irq);
 			p->irq = PARPORT_IRQ_NONE;
@@ -2338,8 +2423,8 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 #ifdef CONFIG_PARPORT_PC_FIFO
 #ifdef HAS_DMA
 		if (p->dma != PARPORT_DMA_NONE) {
-			if (request_dma (p->dma, p->name)) {
-				printk (KERN_WARNING "%s: dma %d in use, "
+			if (request_dma(p->dma, p->name)) {
+				printk(KERN_WARNING "%s: dma %d in use, "
 					"resorting to PIO operation\n",
 					p->name, p->dma);
 				p->dma = PARPORT_DMA_NONE;
@@ -2349,8 +2434,8 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 						       PAGE_SIZE,
 						       &priv->dma_handle,
 						       GFP_KERNEL);
-				if (! priv->dma_buf) {
-					printk (KERN_WARNING "%s: "
+				if (!priv->dma_buf) {
+					printk(KERN_WARNING "%s: "
 						"cannot get buffer for DMA, "
 						"resorting to PIO operation\n",
 						p->name);
@@ -2369,10 +2454,10 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 		 * Put the ECP detected port in PS2 mode.
 		 * Do this also for ports that have ECR but don't do ECP.
 		 */
-		ECR_WRITE (p, 0x34);
+		ECR_WRITE(p, 0x34);
 
 	parport_pc_write_data(p, 0);
-	parport_pc_data_forward (p);
+	parport_pc_data_forward(p);
 
 	/* Now that we've told the sharing engine about the port, and
 	   found out its characteristics, let the high-level drivers
@@ -2380,7 +2465,7 @@ struct parport *parport_pc_probe_port(unsigned long int base,
 	spin_lock(&ports_lock);
 	list_add(&priv->list, &ports_list);
 	spin_unlock(&ports_lock);
-	parport_announce_port (p);
+	parport_announce_port(p);
 
 	return p;
 
@@ -2393,18 +2478,17 @@ out5:
 out4:
 	parport_put_port(p);
 out3:
-	kfree (priv);
+	kfree(priv);
 out2:
-	kfree (ops);
+	kfree(ops);
 out1:
 	if (pdev)
 		platform_device_unregister(pdev);
 	return NULL;
 }
+EXPORT_SYMBOL(parport_pc_probe_port);
 
-EXPORT_SYMBOL (parport_pc_probe_port);
-
-void parport_pc_unregister_port (struct parport *p)
+void parport_pc_unregister_port(struct parport *p)
 {
 	struct parport_pc_private *priv = p->private_data;
 	struct parport_operations *ops = p->ops;
@@ -2430,17 +2514,16 @@ void parport_pc_unregister_port (struct parport *p)
 				    priv->dma_buf,
 				    priv->dma_handle);
 #endif
-	kfree (p->private_data);
+	kfree(p->private_data);
 	parport_put_port(p);
-	kfree (ops); /* hope no-one cached it */
+	kfree(ops); /* hope no-one cached it */
 }
-
-EXPORT_SYMBOL (parport_pc_unregister_port);
+EXPORT_SYMBOL(parport_pc_unregister_port);
 
 #ifdef CONFIG_PCI
 
 /* ITE support maintained by Rich Liu <richliu@poorman.org> */
-static int __devinit sio_ite_8872_probe (struct pci_dev *pdev, int autoirq,
+static int __devinit sio_ite_8872_probe(struct pci_dev *pdev, int autoirq,
 					 int autodma,
 					 const struct parport_pc_via_data *via)
 {
@@ -2452,73 +2535,74 @@ static int __devinit sio_ite_8872_probe (struct pci_dev *pdev, int autoirq,
 	int irq;
 	int i;
 
-	DPRINTK (KERN_DEBUG "sio_ite_8872_probe()\n");
-	
-	// make sure which one chip
-	for(i = 0; i < 5; i++) {
+	DPRINTK(KERN_DEBUG "sio_ite_8872_probe()\n");
+
+	/* make sure which one chip */
+	for (i = 0; i < 5; i++) {
 		base_res = request_region(inta_addr[i], 32, "it887x");
 		if (base_res) {
 			int test;
-			pci_write_config_dword (pdev, 0x60,
+			pci_write_config_dword(pdev, 0x60,
 						0xe5000000 | inta_addr[i]);
-			pci_write_config_dword (pdev, 0x78,
+			pci_write_config_dword(pdev, 0x78,
 						0x00000000 | inta_addr[i]);
-			test = inb (inta_addr[i]);
-			if (test != 0xff) break;
+			test = inb(inta_addr[i]);
+			if (test != 0xff)
+				break;
 			release_region(inta_addr[i], 0x8);
 		}
 	}
-	if(i >= 5) {
-		printk (KERN_INFO "parport_pc: cannot find ITE8872 INTA\n");
+	if (i >= 5) {
+		printk(KERN_INFO "parport_pc: cannot find ITE8872 INTA\n");
 		return 0;
 	}
 
-	type = inb (inta_addr[i] + 0x18);
+	type = inb(inta_addr[i] + 0x18);
 	type &= 0x0f;
 
 	switch (type) {
 	case 0x2:
-		printk (KERN_INFO "parport_pc: ITE8871 found (1P)\n");
+		printk(KERN_INFO "parport_pc: ITE8871 found (1P)\n");
 		ite8872set = 0x64200000;
 		break;
 	case 0xa:
-		printk (KERN_INFO "parport_pc: ITE8875 found (1P)\n");
+		printk(KERN_INFO "parport_pc: ITE8875 found (1P)\n");
 		ite8872set = 0x64200000;
 		break;
 	case 0xe:
-		printk (KERN_INFO "parport_pc: ITE8872 found (2S1P)\n");
+		printk(KERN_INFO "parport_pc: ITE8872 found (2S1P)\n");
 		ite8872set = 0x64e00000;
 		break;
 	case 0x6:
-		printk (KERN_INFO "parport_pc: ITE8873 found (1S)\n");
+		printk(KERN_INFO "parport_pc: ITE8873 found (1S)\n");
 		return 0;
 	case 0x8:
-		DPRINTK (KERN_DEBUG "parport_pc: ITE8874 found (2S)\n");
+		DPRINTK(KERN_DEBUG "parport_pc: ITE8874 found (2S)\n");
 		return 0;
 	default:
-		printk (KERN_INFO "parport_pc: unknown ITE887x\n");
-		printk (KERN_INFO "parport_pc: please mail 'lspci -nvv' "
+		printk(KERN_INFO "parport_pc: unknown ITE887x\n");
+		printk(KERN_INFO "parport_pc: please mail 'lspci -nvv' "
 			"output to Rich.Liu@ite.com.tw\n");
 		return 0;
 	}
 
-	pci_read_config_byte (pdev, 0x3c, &ite8872_irq);
-	pci_read_config_dword (pdev, 0x1c, &ite8872_lpt);
+	pci_read_config_byte(pdev, 0x3c, &ite8872_irq);
+	pci_read_config_dword(pdev, 0x1c, &ite8872_lpt);
 	ite8872_lpt &= 0x0000ff00;
-	pci_read_config_dword (pdev, 0x20, &ite8872_lpthi);
+	pci_read_config_dword(pdev, 0x20, &ite8872_lpthi);
 	ite8872_lpthi &= 0x0000ff00;
-	pci_write_config_dword (pdev, 0x6c, 0xe3000000 | ite8872_lpt);
-	pci_write_config_dword (pdev, 0x70, 0xe3000000 | ite8872_lpthi);
-	pci_write_config_dword (pdev, 0x80, (ite8872_lpthi<<16) | ite8872_lpt);
-	// SET SPP&EPP , Parallel Port NO DMA , Enable All Function
-	// SET Parallel IRQ
-	pci_write_config_dword (pdev, 0x9c,
+	pci_write_config_dword(pdev, 0x6c, 0xe3000000 | ite8872_lpt);
+	pci_write_config_dword(pdev, 0x70, 0xe3000000 | ite8872_lpthi);
+	pci_write_config_dword(pdev, 0x80, (ite8872_lpthi<<16) | ite8872_lpt);
+	/* SET SPP&EPP , Parallel Port NO DMA , Enable All Function */
+	/* SET Parallel IRQ */
+	pci_write_config_dword(pdev, 0x9c,
 				ite8872set | (ite8872_irq * 0x11111));
 
-	DPRINTK (KERN_DEBUG "ITE887x: The IRQ is %d.\n", ite8872_irq);
-	DPRINTK (KERN_DEBUG "ITE887x: The PARALLEL I/O port is 0x%x.\n",
+	DPRINTK(KERN_DEBUG "ITE887x: The IRQ is %d.\n", ite8872_irq);
+	DPRINTK(KERN_DEBUG "ITE887x: The PARALLEL I/O port is 0x%x.\n",
 		 ite8872_lpt);
-	DPRINTK (KERN_DEBUG "ITE887x: The PARALLEL I/O porthi is 0x%x.\n",
+	DPRINTK(KERN_DEBUG "ITE887x: The PARALLEL I/O porthi is 0x%x.\n",
 		 ite8872_lpthi);
 
 	/* Let the user (or defaults) steer us away from interrupts */
@@ -2530,14 +2614,14 @@ static int __devinit sio_ite_8872_probe (struct pci_dev *pdev, int autoirq,
 	 * Release the resource so that parport_pc_probe_port can get it.
 	 */
 	release_resource(base_res);
-	if (parport_pc_probe_port (ite8872_lpt, ite8872_lpthi,
+	if (parport_pc_probe_port(ite8872_lpt, ite8872_lpthi,
 				   irq, PARPORT_DMA_NONE, &pdev->dev, 0)) {
-		printk (KERN_INFO
+		printk(KERN_INFO
 			"parport_pc: ITE 8872 parallel port: io=0x%X",
-			ite8872_lpt);
+								ite8872_lpt);
 		if (irq != PARPORT_IRQ_NONE)
-			printk (", irq=%d", irq);
-		printk ("\n");
+			printk(", irq=%d", irq);
+		printk("\n");
 		return 1;
 	}
 
@@ -2546,7 +2630,7 @@ static int __devinit sio_ite_8872_probe (struct pci_dev *pdev, int autoirq,
 
 /* VIA 8231 support by Pavel Fedin <sonic_amiga@rambler.ru>
    based on VIA 686a support code by Jeff Garzik <jgarzik@pobox.com> */
-static int __devinitdata parport_init_mode = 0;
+static int __devinitdata parport_init_mode;
 
 /* Data for two known VIA chips */
 static struct parport_pc_via_data via_686a_data __devinitdata = {
@@ -2568,7 +2652,7 @@ static struct parport_pc_via_data via_8231_data __devinitdata = {
 	0xF6
 };
 
-static int __devinit sio_via_probe (struct pci_dev *pdev, int autoirq,
+static int __devinit sio_via_probe(struct pci_dev *pdev, int autoirq,
 				    int autodma,
 				    const struct parport_pc_via_data *via)
 {
@@ -2580,38 +2664,38 @@ static int __devinit sio_via_probe (struct pci_dev *pdev, int autoirq,
 
 	printk(KERN_DEBUG "parport_pc: VIA 686A/8231 detected\n");
 
-	switch(parport_init_mode)
-	{
+	switch (parport_init_mode) {
 	case 1:
-	    printk(KERN_DEBUG "parport_pc: setting SPP mode\n");
-	    siofunc = VIA_FUNCTION_PARPORT_SPP;
-	    break;
+		printk(KERN_DEBUG "parport_pc: setting SPP mode\n");
+		siofunc = VIA_FUNCTION_PARPORT_SPP;
+		break;
 	case 2:
-	    printk(KERN_DEBUG "parport_pc: setting PS/2 mode\n");
-	    siofunc = VIA_FUNCTION_PARPORT_SPP;
-	    ppcontrol = VIA_PARPORT_BIDIR;
-	    break;
+		printk(KERN_DEBUG "parport_pc: setting PS/2 mode\n");
+		siofunc = VIA_FUNCTION_PARPORT_SPP;
+		ppcontrol = VIA_PARPORT_BIDIR;
+		break;
 	case 3:
-	    printk(KERN_DEBUG "parport_pc: setting EPP mode\n");
-	    siofunc = VIA_FUNCTION_PARPORT_EPP;
-	    ppcontrol = VIA_PARPORT_BIDIR;
-	    have_epp = 1;
-	    break;
+		printk(KERN_DEBUG "parport_pc: setting EPP mode\n");
+		siofunc = VIA_FUNCTION_PARPORT_EPP;
+		ppcontrol = VIA_PARPORT_BIDIR;
+		have_epp = 1;
+		break;
 	case 4:
-	    printk(KERN_DEBUG "parport_pc: setting ECP mode\n");
-	    siofunc = VIA_FUNCTION_PARPORT_ECP;
-	    ppcontrol = VIA_PARPORT_BIDIR;
-	    break;
+		printk(KERN_DEBUG "parport_pc: setting ECP mode\n");
+		siofunc = VIA_FUNCTION_PARPORT_ECP;
+		ppcontrol = VIA_PARPORT_BIDIR;
+		break;
 	case 5:
-	    printk(KERN_DEBUG "parport_pc: setting EPP+ECP mode\n");
-	    siofunc = VIA_FUNCTION_PARPORT_ECP;
-	    ppcontrol = VIA_PARPORT_BIDIR|VIA_PARPORT_ECPEPP;
-	    have_epp = 1;
-	    break;
-	 default:
-	    printk(KERN_DEBUG "parport_pc: probing current configuration\n");
-	    siofunc = VIA_FUNCTION_PROBE;
-	    break;
+		printk(KERN_DEBUG "parport_pc: setting EPP+ECP mode\n");
+		siofunc = VIA_FUNCTION_PARPORT_ECP;
+		ppcontrol = VIA_PARPORT_BIDIR|VIA_PARPORT_ECPEPP;
+		have_epp = 1;
+		break;
+	default:
+		printk(KERN_DEBUG
+			"parport_pc: probing current configuration\n");
+		siofunc = VIA_FUNCTION_PROBE;
+		break;
 	}
 	/*
 	 * unlock super i/o configuration
@@ -2622,38 +2706,36 @@ static int __devinit sio_via_probe (struct pci_dev *pdev, int autoirq,
 
 	/* Bits 1-0: Parallel Port Mode / Enable */
 	outb(via->viacfg_function, VIA_CONFIG_INDEX);
-	tmp = inb (VIA_CONFIG_DATA);
+	tmp = inb(VIA_CONFIG_DATA);
 	/* Bit 5: EPP+ECP enable; bit 7: PS/2 bidirectional port enable */
 	outb(via->viacfg_parport_control, VIA_CONFIG_INDEX);
-	tmp2 = inb (VIA_CONFIG_DATA);
-	if (siofunc == VIA_FUNCTION_PROBE)
-	{
-	    siofunc = tmp & VIA_FUNCTION_PARPORT_DISABLE;
-	    ppcontrol = tmp2;
+	tmp2 = inb(VIA_CONFIG_DATA);
+	if (siofunc == VIA_FUNCTION_PROBE) {
+		siofunc = tmp & VIA_FUNCTION_PARPORT_DISABLE;
+		ppcontrol = tmp2;
+	} else {
+		tmp &= ~VIA_FUNCTION_PARPORT_DISABLE;
+		tmp |= siofunc;
+		outb(via->viacfg_function, VIA_CONFIG_INDEX);
+		outb(tmp, VIA_CONFIG_DATA);
+		tmp2 &= ~(VIA_PARPORT_BIDIR|VIA_PARPORT_ECPEPP);
+		tmp2 |= ppcontrol;
+		outb(via->viacfg_parport_control, VIA_CONFIG_INDEX);
+		outb(tmp2, VIA_CONFIG_DATA);
 	}
-	else
-	{
-	    tmp &= ~VIA_FUNCTION_PARPORT_DISABLE;
-	    tmp |= siofunc;
-	    outb(via->viacfg_function, VIA_CONFIG_INDEX);
-	    outb(tmp, VIA_CONFIG_DATA);
-	    tmp2 &= ~(VIA_PARPORT_BIDIR|VIA_PARPORT_ECPEPP);
-	    tmp2 |= ppcontrol;
-	    outb(via->viacfg_parport_control, VIA_CONFIG_INDEX);
-	    outb(tmp2, VIA_CONFIG_DATA);
-	}
-	
+
 	/* Parallel Port I/O Base Address, bits 9-2 */
 	outb(via->viacfg_parport_base, VIA_CONFIG_INDEX);
 	port1 = inb(VIA_CONFIG_DATA) << 2;
-	
-	printk (KERN_DEBUG "parport_pc: Current parallel port base: 0x%X\n",port1);
-	if ((port1 == 0x3BC) && have_epp)
-	{
-	    outb(via->viacfg_parport_base, VIA_CONFIG_INDEX);
-	    outb((0x378 >> 2), VIA_CONFIG_DATA);
-	    printk(KERN_DEBUG "parport_pc: Parallel port base changed to 0x378\n");
-	    port1 = 0x378;
+
+	printk(KERN_DEBUG "parport_pc: Current parallel port base: 0x%X\n",
+									port1);
+	if (port1 == 0x3BC && have_epp) {
+		outb(via->viacfg_parport_base, VIA_CONFIG_INDEX);
+		outb((0x378 >> 2), VIA_CONFIG_DATA);
+		printk(KERN_DEBUG
+			"parport_pc: Parallel port base changed to 0x378\n");
+		port1 = 0x378;
 	}
 
 	/*
@@ -2667,36 +2749,39 @@ static int __devinit sio_via_probe (struct pci_dev *pdev, int autoirq,
 		printk(KERN_INFO "parport_pc: VIA parallel port disabled in BIOS\n");
 		return 0;
 	}
-	
+
 	/* Bits 7-4: PnP Routing for Parallel Port IRQ */
 	pci_read_config_byte(pdev, via->via_pci_parport_irq_reg, &tmp);
 	irq = ((tmp & VIA_IRQCONTROL_PARALLEL) >> 4);
 
-	if (siofunc == VIA_FUNCTION_PARPORT_ECP)
-	{
-	    /* Bits 3-2: PnP Routing for Parallel Port DMA */
-	    pci_read_config_byte(pdev, via->via_pci_parport_dma_reg, &tmp);
-	    dma = ((tmp & VIA_DMACONTROL_PARALLEL) >> 2);
-	}
-	else
-	    /* if ECP not enabled, DMA is not enabled, assumed bogus 'dma' value */
-	    dma = PARPORT_DMA_NONE;
+	if (siofunc == VIA_FUNCTION_PARPORT_ECP) {
+		/* Bits 3-2: PnP Routing for Parallel Port DMA */
+		pci_read_config_byte(pdev, via->via_pci_parport_dma_reg, &tmp);
+		dma = ((tmp & VIA_DMACONTROL_PARALLEL) >> 2);
+	} else
+		/* if ECP not enabled, DMA is not enabled, assumed
+		   bogus 'dma' value */
+		dma = PARPORT_DMA_NONE;
 
 	/* Let the user (or defaults) steer us away from interrupts and DMA */
 	if (autoirq == PARPORT_IRQ_NONE) {
-	    irq = PARPORT_IRQ_NONE;
-	    dma = PARPORT_DMA_NONE;
+		irq = PARPORT_IRQ_NONE;
+		dma = PARPORT_DMA_NONE;
 	}
 	if (autodma == PARPORT_DMA_NONE)
-	    dma = PARPORT_DMA_NONE;
+		dma = PARPORT_DMA_NONE;
 
 	switch (port1) {
-	case 0x3bc: port2 = 0x7bc; break;
-	case 0x378: port2 = 0x778; break;
-	case 0x278: port2 = 0x678; break;
+	case 0x3bc:
+		port2 = 0x7bc; break;
+	case 0x378:
+		port2 = 0x778; break;
+	case 0x278:
+		port2 = 0x678; break;
 	default:
-		printk(KERN_INFO "parport_pc: Weird VIA parport base 0x%X, ignoring\n",
-			port1);
+		printk(KERN_INFO
+			"parport_pc: Weird VIA parport base 0x%X, ignoring\n",
+									port1);
 		return 0;
 	}
 
@@ -2714,17 +2799,17 @@ static int __devinit sio_via_probe (struct pci_dev *pdev, int autoirq,
 	}
 
 	/* finally, do the probe with values obtained */
-	if (parport_pc_probe_port (port1, port2, irq, dma, &pdev->dev, 0)) {
-		printk (KERN_INFO
+	if (parport_pc_probe_port(port1, port2, irq, dma, &pdev->dev, 0)) {
+		printk(KERN_INFO
 			"parport_pc: VIA parallel port: io=0x%X", port1);
 		if (irq != PARPORT_IRQ_NONE)
-			printk (", irq=%d", irq);
+			printk(", irq=%d", irq);
 		if (dma != PARPORT_DMA_NONE)
-			printk (", dma=%d", dma);
-		printk ("\n");
+			printk(", dma=%d", dma);
+		printk("\n");
 		return 1;
 	}
-	
+
 	printk(KERN_WARNING "parport_pc: Strange, can't probe VIA parallel port: io=0x%X, irq=%d, dma=%d\n",
 		port1, irq, dma);
 	return 0;
@@ -2732,8 +2817,8 @@ static int __devinit sio_via_probe (struct pci_dev *pdev, int autoirq,
 
 
 enum parport_pc_sio_types {
-	sio_via_686a = 0,	/* Via VT82C686A motherboard Super I/O */
-	sio_via_8231,		/* Via VT8231 south bridge integrated Super IO */
+	sio_via_686a = 0,   /* Via VT82C686A motherboard Super I/O */
+	sio_via_8231,	    /* Via VT8231 south bridge integrated Super IO */
 	sio_ite_8872,
 	last_sio
 };
@@ -2804,15 +2889,15 @@ enum parport_pc_pci_cards {
 };
 
 
-/* each element directly indexed from enum list, above 
+/* each element directly indexed from enum list, above
  * (but offset by last_sio) */
 static struct parport_pc_pci {
 	int numports;
 	struct { /* BAR (base address registers) numbers in the config
-                    space header */
+		    space header */
 		int lo;
-		int hi; /* -1 if not there, >6 for offset-method (max
-                           BAR is 6) */
+		int hi;
+		/* -1 if not there, >6 for offset-method (max BAR is 6) */
 	} addr[4];
 
 	/* If set, this is called immediately after pci_enable_device.
@@ -2857,7 +2942,7 @@ static struct parport_pc_pci {
 	/* timedia_4018  */             { 2, { { 0, 1 }, { 2, 3 }, } },
 	/* timedia_9018a */             { 2, { { 0, 1 }, { 2, 3 }, } },
 					/* SYBA uses fixed offsets in
-                                           a 1K io window */
+					   a 1K io window */
 	/* syba_2p_epp AP138B */	{ 2, { { 0, 0x078 }, { 0, 0x178 }, } },
 	/* syba_1p_ecp W83787 */	{ 1, { { 0, 0x078 }, } },
 	/* titan_010l */		{ 1, { { 3, -1 }, } },
@@ -2873,11 +2958,14 @@ static struct parport_pc_pci {
 	/* oxsemi_pcie_pport */		{ 1, { { 0, 1 }, } },
 	/* aks_0100 */                  { 1, { { 0, -1 }, } },
 	/* mobility_pp */		{ 1, { { 0, 1 }, } },
-	/* netmos_9705 */               { 1, { { 0, -1 }, } }, /* untested */
-        /* netmos_9715 */               { 2, { { 0, 1 }, { 2, 3 },} }, /* untested */
-        /* netmos_9755 */               { 2, { { 0, 1 }, { 2, 3 },} }, /* untested */
-	/* netmos_9805 */               { 1, { { 0, -1 }, } }, /* untested */
-	/* netmos_9815 */               { 2, { { 0, -1 }, { 2, -1 }, } }, /* untested */
+
+	/* The netmos entries below are untested */
+	/* netmos_9705 */               { 1, { { 0, -1 }, } },
+	/* netmos_9715 */               { 2, { { 0, 1 }, { 2, 3 },} },
+	/* netmos_9755 */               { 2, { { 0, 1 }, { 2, 3 },} },
+	/* netmos_9805 */               { 1, { { 0, -1 }, } },
+	/* netmos_9815 */               { 2, { { 0, -1 }, { 2, -1 }, } },
+
 	/* quatech_sppxp100 */		{ 1, { { 0, 1 }, } },
 };
 
@@ -2906,7 +2994,7 @@ static const struct pci_device_id parport_pc_pci_tbl[] = {
 	{ PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_BOCA_IOPPAR,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, boca_ioppar },
 	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050,
-	  PCI_SUBVENDOR_ID_EXSYS, PCI_SUBDEVICE_ID_EXSYS_4014, 0,0, plx_9050 },
+	  PCI_SUBVENDOR_ID_EXSYS, PCI_SUBDEVICE_ID_EXSYS_4014, 0, 0, plx_9050 },
 	/* PCI_VENDOR_ID_TIMEDIA/SUNIX has many differing cards ...*/
 	{ 0x1409, 0x7168, 0x1409, 0x4078, 0, 0, timedia_4078a },
 	{ 0x1409, 0x7168, 0x1409, 0x4079, 0, 0, timedia_4079h },
@@ -2940,7 +3028,8 @@ static const struct pci_device_id parport_pc_pci_tbl[] = {
 	{ 0x9710, 0x9805, 0x1000, 0x0010, 0, 0, titan_1284p1 },
 	{ 0x9710, 0x9815, 0x1000, 0x0020, 0, 0, titan_1284p2 },
 	/* PCI_VENDOR_ID_AVLAB/Intek21 has another bunch of cards ...*/
-	{ 0x14db, 0x2120, PCI_ANY_ID, PCI_ANY_ID, 0, 0, avlab_1p}, /* AFAVLAB_TK9902 */
+	/* AFAVLAB_TK9902 */
+	{ 0x14db, 0x2120, PCI_ANY_ID, PCI_ANY_ID, 0, 0, avlab_1p},
 	{ 0x14db, 0x2121, PCI_ANY_ID, PCI_ANY_ID, 0, 0, avlab_2p},
 	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_16PCI952PP,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_952 },
@@ -2983,14 +3072,14 @@ static const struct pci_device_id parport_pc_pci_tbl[] = {
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, quatech_sppxp100 },
 	{ 0, } /* terminate list */
 };
-MODULE_DEVICE_TABLE(pci,parport_pc_pci_tbl);
+MODULE_DEVICE_TABLE(pci, parport_pc_pci_tbl);
 
 struct pci_parport_data {
 	int num;
 	struct parport *ports[2];
 };
 
-static int parport_pc_pci_probe (struct pci_dev *dev,
+static int parport_pc_pci_probe(struct pci_dev *dev,
 					   const struct pci_device_id *id)
 {
 	int err, count, n, i = id->driver_data;
@@ -3003,7 +3092,8 @@ static int parport_pc_pci_probe (struct pci_dev *dev,
 	/* This is a PCI card */
 	i -= last_sio;
 	count = 0;
-	if ((err = pci_enable_device (dev)) != 0)
+	err = pci_enable_device(dev);
+	if (err)
 		return err;
 
 	data = kmalloc(sizeof(struct pci_parport_data), GFP_KERNEL);
@@ -3011,7 +3101,7 @@ static int parport_pc_pci_probe (struct pci_dev *dev,
 		return -ENOMEM;
 
 	if (cards[i].preinit_hook &&
-	    cards[i].preinit_hook (dev, PARPORT_IRQ_NONE, PARPORT_DMA_NONE)) {
+	    cards[i].preinit_hook(dev, PARPORT_IRQ_NONE, PARPORT_DMA_NONE)) {
 		kfree(data);
 		return -ENODEV;
 	}
@@ -3021,25 +3111,25 @@ static int parport_pc_pci_probe (struct pci_dev *dev,
 		int hi = cards[i].addr[n].hi;
 		int irq;
 		unsigned long io_lo, io_hi;
-		io_lo = pci_resource_start (dev, lo);
+		io_lo = pci_resource_start(dev, lo);
 		io_hi = 0;
 		if ((hi >= 0) && (hi <= 6))
-			io_hi = pci_resource_start (dev, hi);
+			io_hi = pci_resource_start(dev, hi);
 		else if (hi > 6)
 			io_lo += hi; /* Reinterpret the meaning of
-                                        "hi" as an offset (see SYBA
-                                        def.) */
+					"hi" as an offset (see SYBA
+					def.) */
 		/* TODO: test if sharing interrupts works */
 		irq = dev->irq;
 		if (irq == IRQ_NONE) {
-			printk (KERN_DEBUG
+			printk(KERN_DEBUG
 	"PCI parallel port detected: %04x:%04x, I/O at %#lx(%#lx)\n",
 				parport_pc_pci_tbl[i + last_sio].vendor,
 				parport_pc_pci_tbl[i + last_sio].device,
 				io_lo, io_hi);
 			irq = PARPORT_IRQ_NONE;
 		} else {
-			printk (KERN_DEBUG
+			printk(KERN_DEBUG
 	"PCI parallel port detected: %04x:%04x, I/O at %#lx(%#lx), IRQ %d\n",
 				parport_pc_pci_tbl[i + last_sio].vendor,
 				parport_pc_pci_tbl[i + last_sio].device,
@@ -3056,7 +3146,7 @@ static int parport_pc_pci_probe (struct pci_dev *dev,
 	data->num = count;
 
 	if (cards[i].postinit_hook)
-		cards[i].postinit_hook (dev, count == 0);
+		cards[i].postinit_hook(dev, count == 0);
 
 	if (count) {
 		pci_set_drvdata(dev, data);
@@ -3090,7 +3180,7 @@ static struct pci_driver parport_pc_pci_driver = {
 	.remove		= __devexit_p(parport_pc_pci_remove),
 };
 
-static int __init parport_pc_init_superio (int autoirq, int autodma)
+static int __init parport_pc_init_superio(int autoirq, int autodma)
 {
 	const struct pci_device_id *id;
 	struct pci_dev *pdev = NULL;
@@ -3101,8 +3191,9 @@ static int __init parport_pc_init_superio (int autoirq, int autodma)
 		if (id == NULL || id->driver_data >= last_sio)
 			continue;
 
-		if (parport_pc_superio_info[id->driver_data].probe
-			(pdev, autoirq, autodma,parport_pc_superio_info[id->driver_data].via)) {
+		if (parport_pc_superio_info[id->driver_data].probe(
+			pdev, autoirq, autodma,
+			parport_pc_superio_info[id->driver_data].via)) {
 			ret++;
 		}
 	}
@@ -3111,7 +3202,10 @@ static int __init parport_pc_init_superio (int autoirq, int autodma)
 }
 #else
 static struct pci_driver parport_pc_pci_driver;
-static int __init parport_pc_init_superio(int autoirq, int autodma) {return 0;}
+static int __init parport_pc_init_superio(int autoirq, int autodma)
+{
+	return 0;
+}
 #endif /* CONFIG_PCI */
 
 #ifdef CONFIG_PNP
@@ -3124,44 +3218,45 @@ static const struct pnp_device_id parport_pc_pnp_tbl[] = {
 	{ }
 };
 
-MODULE_DEVICE_TABLE(pnp,parport_pc_pnp_tbl);
+MODULE_DEVICE_TABLE(pnp, parport_pc_pnp_tbl);
 
-static int parport_pc_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *id)
+static int parport_pc_pnp_probe(struct pnp_dev *dev,
+						const struct pnp_device_id *id)
 {
 	struct parport *pdata;
 	unsigned long io_lo, io_hi;
 	int dma, irq;
 
-	if (pnp_port_valid(dev,0) &&
-		!(pnp_port_flags(dev,0) & IORESOURCE_DISABLED)) {
-		io_lo = pnp_port_start(dev,0);
+	if (pnp_port_valid(dev, 0) &&
+		!(pnp_port_flags(dev, 0) & IORESOURCE_DISABLED)) {
+		io_lo = pnp_port_start(dev, 0);
 	} else
 		return -EINVAL;
 
-	if (pnp_port_valid(dev,1) &&
-		!(pnp_port_flags(dev,1) & IORESOURCE_DISABLED)) {
-		io_hi = pnp_port_start(dev,1);
+	if (pnp_port_valid(dev, 1) &&
+		!(pnp_port_flags(dev, 1) & IORESOURCE_DISABLED)) {
+		io_hi = pnp_port_start(dev, 1);
 	} else
 		io_hi = 0;
 
-	if (pnp_irq_valid(dev,0) &&
-		!(pnp_irq_flags(dev,0) & IORESOURCE_DISABLED)) {
-		irq = pnp_irq(dev,0);
+	if (pnp_irq_valid(dev, 0) &&
+		!(pnp_irq_flags(dev, 0) & IORESOURCE_DISABLED)) {
+		irq = pnp_irq(dev, 0);
 	} else
 		irq = PARPORT_IRQ_NONE;
 
-	if (pnp_dma_valid(dev,0) &&
-		!(pnp_dma_flags(dev,0) & IORESOURCE_DISABLED)) {
-		dma = pnp_dma(dev,0);
+	if (pnp_dma_valid(dev, 0) &&
+		!(pnp_dma_flags(dev, 0) & IORESOURCE_DISABLED)) {
+		dma = pnp_dma(dev, 0);
 	} else
 		dma = PARPORT_DMA_NONE;
 
 	dev_info(&dev->dev, "reported by %s\n", dev->protocol->name);
-	if (!(pdata = parport_pc_probe_port(io_lo, io_hi,
-					irq, dma, &dev->dev, 0)))
+	pdata = parport_pc_probe_port(io_lo, io_hi, irq, dma, &dev->dev, 0);
+	if (pdata == NULL)
 		return -ENODEV;
 
-	pnp_set_drvdata(dev,pdata);
+	pnp_set_drvdata(dev, pdata);
 	return 0;
 }
 
@@ -3203,7 +3298,7 @@ static struct platform_driver parport_pc_platform_driver = {
 
 /* This is called by parport_pc_find_nonpci_ports (in asm/parport.h) */
 static int __devinit __attribute__((unused))
-parport_pc_find_isa_ports (int autoirq, int autodma)
+parport_pc_find_isa_ports(int autoirq, int autodma)
 {
 	int count = 0;
 
@@ -3227,7 +3322,7 @@ parport_pc_find_isa_ports (int autoirq, int autodma)
  * autoirq is PARPORT_IRQ_NONE, PARPORT_IRQ_AUTO, or PARPORT_IRQ_PROBEONLY
  * autodma is PARPORT_DMA_NONE or PARPORT_DMA_AUTO
  */
-static void __init parport_pc_find_ports (int autoirq, int autodma)
+static void __init parport_pc_find_ports(int autoirq, int autodma)
 {
 	int count = 0, err;
 
@@ -3261,11 +3356,18 @@ static void __init parport_pc_find_ports (int autoirq, int autodma)
  *	syntax and keep in mind that code below is a cleaned up version.
  */
 
-static int __initdata io[PARPORT_PC_MAX_PORTS+1] = { [0 ... PARPORT_PC_MAX_PORTS] = 0 };
-static int __initdata io_hi[PARPORT_PC_MAX_PORTS+1] =
-	{ [0 ... PARPORT_PC_MAX_PORTS] = PARPORT_IOHI_AUTO };
-static int __initdata dmaval[PARPORT_PC_MAX_PORTS] = { [0 ... PARPORT_PC_MAX_PORTS-1] = PARPORT_DMA_NONE };
-static int __initdata irqval[PARPORT_PC_MAX_PORTS] = { [0 ... PARPORT_PC_MAX_PORTS-1] = PARPORT_IRQ_PROBEONLY };
+static int __initdata io[PARPORT_PC_MAX_PORTS+1] = {
+	[0 ... PARPORT_PC_MAX_PORTS] = 0
+};
+static int __initdata io_hi[PARPORT_PC_MAX_PORTS+1] = {
+	[0 ... PARPORT_PC_MAX_PORTS] = PARPORT_IOHI_AUTO
+};
+static int __initdata dmaval[PARPORT_PC_MAX_PORTS] = {
+	[0 ... PARPORT_PC_MAX_PORTS-1] = PARPORT_DMA_NONE
+};
+static int __initdata irqval[PARPORT_PC_MAX_PORTS] = {
+	[0 ... PARPORT_PC_MAX_PORTS-1] = PARPORT_IRQ_PROBEONLY
+};
 
 static int __init parport_parse_param(const char *s, int *val,
 				int automatic, int none, int nofifo)
@@ -3306,18 +3408,19 @@ static int __init parport_parse_dma(const char *dmastr, int *val)
 #ifdef CONFIG_PCI
 static int __init parport_init_mode_setup(char *str)
 {
-	printk(KERN_DEBUG "parport_pc.c: Specified parameter parport_init_mode=%s\n", str);
+	printk(KERN_DEBUG
+	     "parport_pc.c: Specified parameter parport_init_mode=%s\n", str);
 
-	if (!strcmp (str, "spp"))
-		parport_init_mode=1;
-	if (!strcmp (str, "ps2"))
-		parport_init_mode=2;
-	if (!strcmp (str, "epp"))
-		parport_init_mode=3;
-	if (!strcmp (str, "ecp"))
-		parport_init_mode=4;
-	if (!strcmp (str, "ecpepp"))
-		parport_init_mode=5;
+	if (!strcmp(str, "spp"))
+		parport_init_mode = 1;
+	if (!strcmp(str, "ps2"))
+		parport_init_mode = 2;
+	if (!strcmp(str, "epp"))
+		parport_init_mode = 3;
+	if (!strcmp(str, "ecp"))
+		parport_init_mode = 4;
+	if (!strcmp(str, "ecpepp"))
+		parport_init_mode = 5;
 	return 1;
 }
 #endif
@@ -3341,7 +3444,8 @@ module_param(verbose_probing, int, 0644);
 #endif
 #ifdef CONFIG_PCI
 static char *init_mode;
-MODULE_PARM_DESC(init_mode, "Initialise mode for VIA VT8231 port (spp, ps2, epp, ecp or ecpepp)");
+MODULE_PARM_DESC(init_mode,
+	"Initialise mode for VIA VT8231 port (spp, ps2, epp, ecp or ecpepp)");
 module_param(init_mode, charp, 0);
 #endif
 
@@ -3372,7 +3476,7 @@ static int __init parse_parport_params(void)
 				irqval[0] = val;
 				break;
 			default:
-				printk (KERN_WARNING
+				printk(KERN_WARNING
 					"parport_pc: irq specified "
 					"without base address.  Use 'io=' "
 					"to specify one\n");
@@ -3385,7 +3489,7 @@ static int __init parse_parport_params(void)
 				dmaval[0] = val;
 				break;
 			default:
-				printk (KERN_WARNING
+				printk(KERN_WARNING
 					"parport_pc: dma specified "
 					"without base address.  Use 'io=' "
 					"to specify one\n");
@@ -3396,7 +3500,7 @@ static int __init parse_parport_params(void)
 
 #else
 
-static int parport_setup_ptr __initdata = 0;
+static int parport_setup_ptr __initdata;
 
 /*
  * Acceptable parameters:
@@ -3407,7 +3511,7 @@ static int parport_setup_ptr __initdata = 0;
  *
  * IRQ/DMA may be numeric or 'auto' or 'none'
  */
-static int __init parport_setup (char *str)
+static int __init parport_setup(char *str)
 {
 	char *endptr;
 	char *sep;
@@ -3419,15 +3523,15 @@ static int __init parport_setup (char *str)
 		return 1;
 	}
 
-	if (!strncmp (str, "auto", 4)) {
+	if (!strncmp(str, "auto", 4)) {
 		irqval[0] = PARPORT_IRQ_AUTO;
 		dmaval[0] = PARPORT_DMA_AUTO;
 		return 1;
 	}
 
-	val = simple_strtoul (str, &endptr, 0);
+	val = simple_strtoul(str, &endptr, 0);
 	if (endptr == str) {
-		printk (KERN_WARNING "parport=%s not understood\n", str);
+		printk(KERN_WARNING "parport=%s not understood\n", str);
 		return 1;
 	}
 
@@ -3461,7 +3565,7 @@ static int __init parse_parport_params(void)
 	return io[0] == PARPORT_DISABLE;
 }
 
-__setup ("parport=", parport_setup);
+__setup("parport=", parport_setup);
 
 /*
  * Acceptable parameters:
@@ -3469,7 +3573,7 @@ __setup ("parport=", parport_setup);
  * parport_init_mode=[spp|ps2|epp|ecp|ecpepp]
  */
 #ifdef CONFIG_PCI
-__setup("parport_init_mode=",parport_init_mode_setup);
+__setup("parport_init_mode=", parport_init_mode_setup);
 #endif
 #endif
 
@@ -3493,13 +3597,13 @@ static int __init parport_pc_init(void)
 		for (i = 0; i < PARPORT_PC_MAX_PORTS; i++) {
 			if (!io[i])
 				break;
-			if ((io_hi[i]) == PARPORT_IOHI_AUTO)
-			       io_hi[i] = 0x400 + io[i];
+			if (io_hi[i] == PARPORT_IOHI_AUTO)
+				io_hi[i] = 0x400 + io[i];
 			parport_pc_probe_port(io[i], io_hi[i],
-					  irqval[i], dmaval[i], NULL, 0);
+					irqval[i], dmaval[i], NULL, 0);
 		}
 	} else
-		parport_pc_find_ports (irqval[0], dmaval[0]);
+		parport_pc_find_ports(irqval[0], dmaval[0]);
 
 	return 0;
 }
@@ -3507,9 +3611,9 @@ static int __init parport_pc_init(void)
 static void __exit parport_pc_exit(void)
 {
 	if (pci_registered_parport)
-		pci_unregister_driver (&parport_pc_pci_driver);
+		pci_unregister_driver(&parport_pc_pci_driver);
 	if (pnp_registered_parport)
-		pnp_unregister_driver (&parport_pc_pnp_driver);
+		pnp_unregister_driver(&parport_pc_pnp_driver);
 	platform_driver_unregister(&parport_pc_platform_driver);
 
 	while (!list_empty(&ports_list)) {
diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c
index dd18f857dfb0..42e4260c3b12 100644
--- a/drivers/pci/hotplug/ibmphp_core.c
+++ b/drivers/pci/hotplug/ibmphp_core.c
@@ -153,45 +153,47 @@ int ibmphp_init_devno(struct slot **cur_slot)
 		return -1;
 	}
 	for (loop = 0; loop < len; loop++) {
-		if ((*cur_slot)->number == rtable->slots[loop].slot) {
-		if ((*cur_slot)->bus == rtable->slots[loop].bus) {
+		if ((*cur_slot)->number == rtable->slots[loop].slot &&
+		    (*cur_slot)->bus == rtable->slots[loop].bus) {
+			struct io_apic_irq_attr irq_attr;
+
 			(*cur_slot)->device = PCI_SLOT(rtable->slots[loop].devfn);
 			for (i = 0; i < 4; i++)
 				(*cur_slot)->irq[i] = IO_APIC_get_PCI_irq_vector((int) (*cur_slot)->bus,
-						(int) (*cur_slot)->device, i);
+						(int) (*cur_slot)->device, i,
+						&irq_attr);
 
-				debug("(*cur_slot)->irq[0] = %x\n",
-						(*cur_slot)->irq[0]);
-				debug("(*cur_slot)->irq[1] = %x\n",
-						(*cur_slot)->irq[1]);
-				debug("(*cur_slot)->irq[2] = %x\n",
-						(*cur_slot)->irq[2]);
-				debug("(*cur_slot)->irq[3] = %x\n",
-						(*cur_slot)->irq[3]);
+			debug("(*cur_slot)->irq[0] = %x\n",
+					(*cur_slot)->irq[0]);
+			debug("(*cur_slot)->irq[1] = %x\n",
+					(*cur_slot)->irq[1]);
+			debug("(*cur_slot)->irq[2] = %x\n",
+					(*cur_slot)->irq[2]);
+			debug("(*cur_slot)->irq[3] = %x\n",
+					(*cur_slot)->irq[3]);
 
-				debug("rtable->exlusive_irqs = %x\n",
+			debug("rtable->exlusive_irqs = %x\n",
 					rtable->exclusive_irqs);
-				debug("rtable->slots[loop].irq[0].bitmap = %x\n",
+			debug("rtable->slots[loop].irq[0].bitmap = %x\n",
 					rtable->slots[loop].irq[0].bitmap);
-				debug("rtable->slots[loop].irq[1].bitmap = %x\n",
+			debug("rtable->slots[loop].irq[1].bitmap = %x\n",
 					rtable->slots[loop].irq[1].bitmap);
-				debug("rtable->slots[loop].irq[2].bitmap = %x\n",
+			debug("rtable->slots[loop].irq[2].bitmap = %x\n",
 					rtable->slots[loop].irq[2].bitmap);
-				debug("rtable->slots[loop].irq[3].bitmap = %x\n",
+			debug("rtable->slots[loop].irq[3].bitmap = %x\n",
 					rtable->slots[loop].irq[3].bitmap);
 
-				debug("rtable->slots[loop].irq[0].link = %x\n",
+			debug("rtable->slots[loop].irq[0].link = %x\n",
 					rtable->slots[loop].irq[0].link);
-				debug("rtable->slots[loop].irq[1].link = %x\n",
+			debug("rtable->slots[loop].irq[1].link = %x\n",
 					rtable->slots[loop].irq[1].link);
-				debug("rtable->slots[loop].irq[2].link = %x\n",
+			debug("rtable->slots[loop].irq[2].link = %x\n",
 					rtable->slots[loop].irq[2].link);
-				debug("rtable->slots[loop].irq[3].link = %x\n",
+			debug("rtable->slots[loop].irq[3].link = %x\n",
 					rtable->slots[loop].irq[3].link);
-				debug("end of init_devno\n");
-				kfree(rtable);
-				return 0;
-			}
+			debug("end of init_devno\n");
+			kfree(rtable);
+			return 0;
 		}
 	}
 
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index 6808d8333ecc..737a1c44b07a 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -98,6 +98,7 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	int max_irq;
 	int pos;
 	int irq;
+	int node;
 
 	pos = pci_find_ht_capability(dev, HT_CAPTYPE_IRQ);
 	if (!pos)
@@ -125,7 +126,8 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	cfg->msg.address_lo = 0xffffffff;
 	cfg->msg.address_hi = 0xffffffff;
 
-	irq = create_irq();
+	node = dev_to_node(&dev->dev);
+	irq = create_irq_nr(0, node);
 
 	if (irq <= 0) {
 		kfree(cfg);
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index a563fbe559d0..cd389162735f 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -1972,15 +1972,6 @@ static int __init init_dmars(void)
 		}
 	}
 
-#ifdef CONFIG_INTR_REMAP
-	if (!intr_remapping_enabled) {
-		ret = enable_intr_remapping(0);
-		if (ret)
-			printk(KERN_ERR
-			       "IOMMU: enable interrupt remapping failed\n");
-	}
-#endif
-
 	/*
 	 * For each rmrr
 	 *   for each dev attached to rmrr
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index f5e0ea724a6f..3a0cb0bb0593 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -15,6 +15,14 @@ static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
 static int ir_ioapic_num;
 int intr_remapping_enabled;
 
+static int disable_intremap;
+static __init int setup_nointremap(char *str)
+{
+	disable_intremap = 1;
+	return 0;
+}
+early_param("nointremap", setup_nointremap);
+
 struct irq_2_iommu {
 	struct intel_iommu *iommu;
 	u16 irte_index;
@@ -23,15 +31,12 @@ struct irq_2_iommu {
 };
 
 #ifdef CONFIG_GENERIC_HARDIRQS
-static struct irq_2_iommu *get_one_free_irq_2_iommu(int cpu)
+static struct irq_2_iommu *get_one_free_irq_2_iommu(int node)
 {
 	struct irq_2_iommu *iommu;
-	int node;
-
-	node = cpu_to_node(cpu);
 
 	iommu = kzalloc_node(sizeof(*iommu), GFP_ATOMIC, node);
-	printk(KERN_DEBUG "alloc irq_2_iommu on cpu %d node %d\n", cpu, node);
+	printk(KERN_DEBUG "alloc irq_2_iommu on node %d\n", node);
 
 	return iommu;
 }
@@ -48,7 +53,7 @@ static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
 	return desc->irq_2_iommu;
 }
 
-static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
+static struct irq_2_iommu *irq_2_iommu_alloc_node(unsigned int irq, int node)
 {
 	struct irq_desc *desc;
 	struct irq_2_iommu *irq_iommu;
@@ -56,7 +61,7 @@ static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
 	/*
 	 * alloc irq desc if not allocated already.
 	 */
-	desc = irq_to_desc_alloc_cpu(irq, cpu);
+	desc = irq_to_desc_alloc_node(irq, node);
 	if (!desc) {
 		printk(KERN_INFO "can not get irq_desc for %d\n", irq);
 		return NULL;
@@ -65,14 +70,14 @@ static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
 	irq_iommu = desc->irq_2_iommu;
 
 	if (!irq_iommu)
-		desc->irq_2_iommu = get_one_free_irq_2_iommu(cpu);
+		desc->irq_2_iommu = get_one_free_irq_2_iommu(node);
 
 	return desc->irq_2_iommu;
 }
 
 static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
 {
-	return irq_2_iommu_alloc_cpu(irq, boot_cpu_id);
+	return irq_2_iommu_alloc_node(irq, cpu_to_node(boot_cpu_id));
 }
 
 #else /* !CONFIG_SPARSE_IRQ */
@@ -423,20 +428,6 @@ static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
 		      readl, (sts & DMA_GSTS_IRTPS), sts);
 	spin_unlock_irqrestore(&iommu->register_lock, flags);
 
-	if (mode == 0) {
-		spin_lock_irqsave(&iommu->register_lock, flags);
-
-		/* enable comaptiblity format interrupt pass through */
-		cmd = iommu->gcmd | DMA_GCMD_CFI;
-		iommu->gcmd |= DMA_GCMD_CFI;
-		writel(cmd, iommu->reg + DMAR_GCMD_REG);
-
-		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
-			      readl, (sts & DMA_GSTS_CFIS), sts);
-
-		spin_unlock_irqrestore(&iommu->register_lock, flags);
-	}
-
 	/*
 	 * global invalidation of interrupt entry cache before enabling
 	 * interrupt-remapping.
@@ -516,6 +507,23 @@ end:
 	spin_unlock_irqrestore(&iommu->register_lock, flags);
 }
 
+int __init intr_remapping_supported(void)
+{
+	struct dmar_drhd_unit *drhd;
+
+	if (disable_intremap)
+		return 0;
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			return 0;
+	}
+
+	return 1;
+}
+
 int __init enable_intr_remapping(int eim)
 {
 	struct dmar_drhd_unit *drhd;
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index adf17856bacc..7f207f335bec 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -123,7 +123,7 @@ static void pnpacpi_parse_allocated_irqresource(struct pnp_dev *dev,
 	}
 
 	flags = irq_flags(triggering, polarity, shareable);
-	irq = acpi_register_gsi(gsi, triggering, polarity);
+	irq = acpi_register_gsi(&dev->dev, gsi, triggering, polarity);
 	if (irq >= 0)
 		pcibios_penalize_isa_irq(irq, 1);
 	else
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 4e9851fc1746..277d35d232fa 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -692,7 +692,7 @@ config RTC_DRV_GENERIC
 	tristate "Generic RTC support"
 	# Please consider writing a new RTC driver instead of using the generic
 	# RTC abstraction
-	depends on PARISC || M68K || PPC
+	depends on PARISC || M68K || PPC || SUPERH32
 	help
 	  Say Y or M here to enable RTC support on systems using the generic
 	  RTC abstraction. If you do not know what you are doing, you should
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index d1815272c435..27a1be0cd4d4 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -603,7 +603,7 @@ static void dasd_profile_end(struct dasd_block *block,
 	if (dasd_profile_level != DASD_PROFILE_ON)
 		return;
 
-	sectors = req->nr_sectors;
+	sectors = blk_rq_sectors(req);
 	if (!cqr->buildclk || !cqr->startclk ||
 	    !cqr->stopclk || !cqr->endclk ||
 	    !sectors)
@@ -1613,15 +1613,6 @@ void dasd_block_clear_timer(struct dasd_block *block)
 	del_timer(&block->timer);
 }
 
-/*
- * posts the buffer_cache about a finalized request
- */
-static inline void dasd_end_request(struct request *req, int error)
-{
-	if (__blk_end_request(req, error, blk_rq_bytes(req)))
-		BUG();
-}
-
 /*
  * Process finished error recovery ccw.
  */
@@ -1665,18 +1656,14 @@ static void __dasd_process_request_queue(struct dasd_block *block)
 	if (basedev->state < DASD_STATE_READY)
 		return;
 	/* Now we try to fetch requests from the request queue */
-	while (!blk_queue_plugged(queue) &&
-	       elv_next_request(queue)) {
-
-		req = elv_next_request(queue);
-
+	while (!blk_queue_plugged(queue) && (req = blk_peek_request(queue))) {
 		if (basedev->features & DASD_FEATURE_READONLY &&
 		    rq_data_dir(req) == WRITE) {
 			DBF_DEV_EVENT(DBF_ERR, basedev,
 				      "Rejecting write request %p",
 				      req);
-			blkdev_dequeue_request(req);
-			dasd_end_request(req, -EIO);
+			blk_start_request(req);
+			__blk_end_request_all(req, -EIO);
 			continue;
 		}
 		cqr = basedev->discipline->build_cp(basedev, block, req);
@@ -1704,8 +1691,8 @@ static void __dasd_process_request_queue(struct dasd_block *block)
 				      "CCW creation failed (rc=%ld) "
 				      "on request %p",
 				      PTR_ERR(cqr), req);
-			blkdev_dequeue_request(req);
-			dasd_end_request(req, -EIO);
+			blk_start_request(req);
+			__blk_end_request_all(req, -EIO);
 			continue;
 		}
 		/*
@@ -1714,7 +1701,7 @@ static void __dasd_process_request_queue(struct dasd_block *block)
 		 */
 		cqr->callback_data = (void *) req;
 		cqr->status = DASD_CQR_FILLED;
-		blkdev_dequeue_request(req);
+		blk_start_request(req);
 		list_add_tail(&cqr->blocklist, &block->ccw_queue);
 		dasd_profile_start(block, cqr, req);
 	}
@@ -1731,7 +1718,7 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr)
 	status = cqr->block->base->discipline->free_cp(cqr, req);
 	if (status <= 0)
 		error = status ? status : -EIO;
-	dasd_end_request(req, error);
+	__blk_end_request_all(req, error);
 }
 
 /*
@@ -2003,7 +1990,7 @@ static void dasd_setup_queue(struct dasd_block *block)
 {
 	int max;
 
-	blk_queue_hardsect_size(block->request_queue, block->bp_block);
+	blk_queue_logical_block_size(block->request_queue, block->bp_block);
 	max = block->base->discipline->max_blocks << block->s2b_shift;
 	blk_queue_max_sectors(block->request_queue, max);
 	blk_queue_max_phys_segments(block->request_queue, -1L);
@@ -2038,10 +2025,8 @@ static void dasd_flush_request_queue(struct dasd_block *block)
 		return;
 
 	spin_lock_irq(&block->request_queue_lock);
-	while ((req = elv_next_request(block->request_queue))) {
-		blkdev_dequeue_request(req);
-		dasd_end_request(req, -EIO);
-	}
+	while ((req = blk_fetch_request(block->request_queue)))
+		__blk_end_request_all(req, -EIO);
 	spin_unlock_irq(&block->request_queue_lock);
 }
 
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index b9a7f7733446..2efaddfae560 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -505,8 +505,9 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
 		return ERR_PTR(-EINVAL);
 	blksize = block->bp_block;
 	/* Calculate record id of first and last block. */
-	first_rec = req->sector >> block->s2b_shift;
-	last_rec = (req->sector + req->nr_sectors - 1) >> block->s2b_shift;
+	first_rec = blk_rq_pos(req) >> block->s2b_shift;
+	last_rec =
+		(blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift;
 	/* Check struct bio and count the number of blocks for the request. */
 	count = 0;
 	rq_for_each_segment(bv, req, iter) {
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index cb52da033f06..a41c94053e64 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -2354,10 +2354,10 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev,
 	blksize = block->bp_block;
 	blk_per_trk = recs_per_track(&private->rdc_data, 0, blksize);
 	/* Calculate record id of first and last block. */
-	first_rec = first_trk = req->sector >> block->s2b_shift;
+	first_rec = first_trk = blk_rq_pos(req) >> block->s2b_shift;
 	first_offs = sector_div(first_trk, blk_per_trk);
 	last_rec = last_trk =
-		(req->sector + req->nr_sectors - 1) >> block->s2b_shift;
+		(blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift;
 	last_offs = sector_div(last_trk, blk_per_trk);
 	cdlspecial = (private->uses_cdl && first_rec < 2*blk_per_trk);
 
@@ -2420,7 +2420,7 @@ dasd_eckd_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 	private = (struct dasd_eckd_private *) cqr->block->base->private;
 	blksize = cqr->block->bp_block;
 	blk_per_trk = recs_per_track(&private->rdc_data, 0, blksize);
-	recid = req->sector >> cqr->block->s2b_shift;
+	recid = blk_rq_pos(req) >> cqr->block->s2b_shift;
 	ccw = cqr->cpaddr;
 	/* Skip over define extent & locate record. */
 	ccw++;
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index a3eb6fd14673..8912358daa2f 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -270,8 +270,9 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 		return ERR_PTR(-EINVAL);
 	blksize = block->bp_block;
 	/* Calculate record id of first and last block. */
-	first_rec = req->sector >> block->s2b_shift;
-	last_rec = (req->sector + req->nr_sectors - 1) >> block->s2b_shift;
+	first_rec = blk_rq_pos(req) >> block->s2b_shift;
+	last_rec =
+		(blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift;
 	/* Check struct bio and count the number of blocks for the request. */
 	count = 0;
 	cidaw = 0;
@@ -309,7 +310,7 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 	ccw = cqr->cpaddr;
 	/* First ccw is define extent. */
 	define_extent(ccw++, cqr->data, rq_data_dir(req),
-		      block->bp_block, req->sector, req->nr_sectors);
+		      block->bp_block, blk_rq_pos(req), blk_rq_sectors(req));
 	/* Build locate_record + read/write ccws. */
 	idaws = (unsigned long *) (cqr->data + sizeof(struct DE_fba_data));
 	LO_data = (struct LO_fba_data *) (idaws + cidaw);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index cfdcf1aed33c..a4c7ffcd9987 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -602,7 +602,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->gd->private_data = dev_info;
 	dev_info->gd->driverfs_dev = &dev_info->dev;
 	blk_queue_make_request(dev_info->dcssblk_queue, dcssblk_make_request);
-	blk_queue_hardsect_size(dev_info->dcssblk_queue, 4096);
+	blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096);
 
 	seg_byte_size = (dev_info->end - dev_info->start + 1);
 	set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 76814f3e898a..0ae0c83ef879 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -343,7 +343,7 @@ static int __init xpram_setup_blkdev(void)
 			goto out;
 		}
 		blk_queue_make_request(xpram_queues[i], xpram_make_request);
-		blk_queue_hardsect_size(xpram_queues[i], 4096);
+		blk_queue_logical_block_size(xpram_queues[i], 4096);
 	}
 
 	/*
diff --git a/drivers/s390/char/tape_34xx.c b/drivers/s390/char/tape_34xx.c
index 5f8e8ef43dd3..2d00a383a475 100644
--- a/drivers/s390/char/tape_34xx.c
+++ b/drivers/s390/char/tape_34xx.c
@@ -1134,7 +1134,7 @@ tape_34xx_bread(struct tape_device *device, struct request *req)
 	/* Setup ccws. */
 	request->op = TO_BLOCK;
 	start_block = (struct tape_34xx_block_id *) request->cpdata;
-	start_block->block = req->sector >> TAPEBLOCK_HSEC_S2B;
+	start_block->block = blk_rq_pos(req) >> TAPEBLOCK_HSEC_S2B;
 	DBF_EVENT(6, "start_block = %i\n", start_block->block);
 
 	ccw = request->cpaddr;
diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c
index 823b05bd0dd7..c453b2f3e9f4 100644
--- a/drivers/s390/char/tape_3590.c
+++ b/drivers/s390/char/tape_3590.c
@@ -633,7 +633,7 @@ tape_3590_bread(struct tape_device *device, struct request *req)
 	struct req_iterator iter;
 
 	DBF_EVENT(6, "xBREDid:");
-	start_block = req->sector >> TAPEBLOCK_HSEC_S2B;
+	start_block = blk_rq_pos(req) >> TAPEBLOCK_HSEC_S2B;
 	DBF_EVENT(6, "start_block = %i\n", start_block);
 
 	rq_for_each_segment(bv, req, iter)
diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c
index f32e89e7c4f2..47ff695255ea 100644
--- a/drivers/s390/char/tape_block.c
+++ b/drivers/s390/char/tape_block.c
@@ -73,13 +73,6 @@ tapeblock_trigger_requeue(struct tape_device *device)
 /*
  * Post finished request.
  */
-static void
-tapeblock_end_request(struct request *req, int error)
-{
-	if (blk_end_request(req, error, blk_rq_bytes(req)))
-		BUG();
-}
-
 static void
 __tapeblock_end_request(struct tape_request *ccw_req, void *data)
 {
@@ -90,17 +83,17 @@ __tapeblock_end_request(struct tape_request *ccw_req, void *data)
 
 	device = ccw_req->device;
 	req = (struct request *) data;
-	tapeblock_end_request(req, (ccw_req->rc == 0) ? 0 : -EIO);
+	blk_end_request_all(req, (ccw_req->rc == 0) ? 0 : -EIO);
 	if (ccw_req->rc == 0)
 		/* Update position. */
 		device->blk_data.block_position =
-			(req->sector + req->nr_sectors) >> TAPEBLOCK_HSEC_S2B;
+		  (blk_rq_pos(req) + blk_rq_sectors(req)) >> TAPEBLOCK_HSEC_S2B;
 	else
 		/* We lost the position information due to an error. */
 		device->blk_data.block_position = -1;
 	device->discipline->free_bread(ccw_req);
 	if (!list_empty(&device->req_queue) ||
-	    elv_next_request(device->blk_data.request_queue))
+	    blk_peek_request(device->blk_data.request_queue))
 		tapeblock_trigger_requeue(device);
 }
 
@@ -118,7 +111,7 @@ tapeblock_start_request(struct tape_device *device, struct request *req)
 	ccw_req = device->discipline->bread(device, req);
 	if (IS_ERR(ccw_req)) {
 		DBF_EVENT(1, "TBLOCK: bread failed\n");
-		tapeblock_end_request(req, -EIO);
+		blk_end_request_all(req, -EIO);
 		return PTR_ERR(ccw_req);
 	}
 	ccw_req->callback = __tapeblock_end_request;
@@ -131,7 +124,7 @@ tapeblock_start_request(struct tape_device *device, struct request *req)
 		 * Start/enqueueing failed. No retries in
 		 * this case.
 		 */
-		tapeblock_end_request(req, -EIO);
+		blk_end_request_all(req, -EIO);
 		device->discipline->free_bread(ccw_req);
 	}
 
@@ -169,19 +162,16 @@ tapeblock_requeue(struct work_struct *work) {
 	spin_lock_irq(&device->blk_data.request_queue_lock);
 	while (
 		!blk_queue_plugged(queue) &&
-		elv_next_request(queue)   &&
+		(req = blk_fetch_request(queue)) &&
 		nr_queued < TAPEBLOCK_MIN_REQUEUE
 	) {
-		req = elv_next_request(queue);
 		if (rq_data_dir(req) == WRITE) {
 			DBF_EVENT(1, "TBLOCK: Rejecting write request\n");
-			blkdev_dequeue_request(req);
 			spin_unlock_irq(&device->blk_data.request_queue_lock);
-			tapeblock_end_request(req, -EIO);
+			blk_end_request_all(req, -EIO);
 			spin_lock_irq(&device->blk_data.request_queue_lock);
 			continue;
 		}
-		blkdev_dequeue_request(req);
 		nr_queued++;
 		spin_unlock_irq(&device->blk_data.request_queue_lock);
 		rc = tapeblock_start_request(device, req);
@@ -232,7 +222,7 @@ tapeblock_setup_device(struct tape_device * device)
 	if (rc)
 		goto cleanup_queue;
 
-	blk_queue_hardsect_size(blkdat->request_queue, TAPEBLOCK_HSEC_SIZE);
+	blk_queue_logical_block_size(blkdat->request_queue, TAPEBLOCK_HSEC_SIZE);
 	blk_queue_max_sectors(blkdat->request_queue, TAPEBLOCK_MAX_SEC);
 	blk_queue_max_phys_segments(blkdat->request_queue, -1L);
 	blk_queue_max_hw_segments(blkdat->request_queue, -1L);
diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c
index a85ad05e8548..6d4651684688 100644
--- a/drivers/sbus/char/jsflash.c
+++ b/drivers/sbus/char/jsflash.c
@@ -186,31 +186,31 @@ static void jsfd_do_request(struct request_queue *q)
 {
 	struct request *req;
 
-	while ((req = elv_next_request(q)) != NULL) {
+	req = blk_fetch_request(q);
+	while (req) {
 		struct jsfd_part *jdp = req->rq_disk->private_data;
-		unsigned long offset = req->sector << 9;
-		size_t len = req->current_nr_sectors << 9;
+		unsigned long offset = blk_rq_pos(req) << 9;
+		size_t len = blk_rq_cur_bytes(req);
+		int err = -EIO;
 
-		if ((offset + len) > jdp->dsize) {
-               		end_request(req, 0);
-			continue;
-		}
+		if ((offset + len) > jdp->dsize)
+			goto end;
 
 		if (rq_data_dir(req) != READ) {
 			printk(KERN_ERR "jsfd: write\n");
-			end_request(req, 0);
-			continue;
+			goto end;
 		}
 
 		if ((jdp->dbase & 0xff000000) != 0x20000000) {
 			printk(KERN_ERR "jsfd: bad base %x\n", (int)jdp->dbase);
-			end_request(req, 0);
-			continue;
+			goto end;
 		}
 
 		jsfd_read(req->buffer, jdp->dbase + offset, len);
-
-		end_request(req, 1);
+		err = 0;
+	end:
+		if (!__blk_end_request_cur(req, err))
+			req = blk_fetch_request(q);
 	}
 }
 
diff --git a/drivers/scsi/eata.c b/drivers/scsi/eata.c
index be5099dd94b5..c7076ce25e21 100644
--- a/drivers/scsi/eata.c
+++ b/drivers/scsi/eata.c
@@ -1825,7 +1825,7 @@ static int eata2x_queuecommand(struct scsi_cmnd *SCpnt,
 	if (linked_comm && SCpnt->device->queue_depth > 2
 	    && TLDEV(SCpnt->device->type)) {
 		ha->cp_stat[i] = READY;
-		flush_dev(SCpnt->device, SCpnt->request->sector, ha, 0);
+		flush_dev(SCpnt->device, blk_rq_pos(SCpnt->request), ha, 0);
 		return 0;
 	}
 
@@ -2144,13 +2144,13 @@ static int reorder(struct hostdata *ha, unsigned long cursec,
 		if (!cpp->din)
 			input_only = 0;
 
-		if (SCpnt->request->sector < minsec)
-			minsec = SCpnt->request->sector;
-		if (SCpnt->request->sector > maxsec)
-			maxsec = SCpnt->request->sector;
+		if (blk_rq_pos(SCpnt->request) < minsec)
+			minsec = blk_rq_pos(SCpnt->request);
+		if (blk_rq_pos(SCpnt->request) > maxsec)
+			maxsec = blk_rq_pos(SCpnt->request);
 
-		sl[n] = SCpnt->request->sector;
-		ioseek += SCpnt->request->nr_sectors;
+		sl[n] = blk_rq_pos(SCpnt->request);
+		ioseek += blk_rq_sectors(SCpnt->request);
 
 		if (!n)
 			continue;
@@ -2190,7 +2190,7 @@ static int reorder(struct hostdata *ha, unsigned long cursec,
 			k = il[n];
 			cpp = &ha->cp[k];
 			SCpnt = cpp->SCpnt;
-			ll[n] = SCpnt->request->nr_sectors;
+			ll[n] = blk_rq_sectors(SCpnt->request);
 			pl[n] = SCpnt->serial_number;
 
 			if (!n)
@@ -2236,12 +2236,12 @@ static int reorder(struct hostdata *ha, unsigned long cursec,
 			cpp = &ha->cp[k];
 			SCpnt = cpp->SCpnt;
 			scmd_printk(KERN_INFO, SCpnt,
-			    "%s pid %ld mb %d fc %d nr %d sec %ld ns %ld"
+			    "%s pid %ld mb %d fc %d nr %d sec %ld ns %u"
 			     " cur %ld s:%c r:%c rev:%c in:%c ov:%c xd %d.\n",
 			     (ihdlr ? "ihdlr" : "qcomm"),
 			     SCpnt->serial_number, k, flushcount,
-			     n_ready, SCpnt->request->sector,
-			     SCpnt->request->nr_sectors, cursec, YESNO(s),
+			     n_ready, blk_rq_pos(SCpnt->request),
+			     blk_rq_sectors(SCpnt->request), cursec, YESNO(s),
 			     YESNO(r), YESNO(rev), YESNO(input_only),
 			     YESNO(overlap), cpp->din);
 		}
@@ -2408,7 +2408,7 @@ static irqreturn_t ihdlr(struct Scsi_Host *shost)
 
 	if (linked_comm && SCpnt->device->queue_depth > 2
 	    && TLDEV(SCpnt->device->type))
-		flush_dev(SCpnt->device, SCpnt->request->sector, ha, 1);
+		flush_dev(SCpnt->device, blk_rq_pos(SCpnt->request), ha, 1);
 
 	tstatus = status_byte(spp->target_status);
 
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 3da02e436788..54fa1e42dc4d 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -1927,21 +1927,21 @@ int sas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	/* do we need to support multiple segments? */
 	if (req->bio->bi_vcnt > 1 || rsp->bio->bi_vcnt > 1) {
 		printk("%s: multiple segments req %u %u, rsp %u %u\n",
-		       __func__, req->bio->bi_vcnt, req->data_len,
-		       rsp->bio->bi_vcnt, rsp->data_len);
+		       __func__, req->bio->bi_vcnt, blk_rq_bytes(req),
+		       rsp->bio->bi_vcnt, blk_rq_bytes(rsp));
 		return -EINVAL;
 	}
 
-	ret = smp_execute_task(dev, bio_data(req->bio), req->data_len,
-			       bio_data(rsp->bio), rsp->data_len);
+	ret = smp_execute_task(dev, bio_data(req->bio), blk_rq_bytes(req),
+			       bio_data(rsp->bio), blk_rq_bytes(rsp));
 	if (ret > 0) {
 		/* positive number is the untransferred residual */
-		rsp->data_len = ret;
-		req->data_len = 0;
+		rsp->resid_len = ret;
+		req->resid_len = 0;
 		ret = 0;
 	} else if (ret == 0) {
-		rsp->data_len = 0;
-		req->data_len = 0;
+		rsp->resid_len = 0;
+		req->resid_len = 0;
 	}
 
 	return ret;
diff --git a/drivers/scsi/libsas/sas_host_smp.c b/drivers/scsi/libsas/sas_host_smp.c
index d110a366c48a..1bc3b7567994 100644
--- a/drivers/scsi/libsas/sas_host_smp.c
+++ b/drivers/scsi/libsas/sas_host_smp.c
@@ -134,24 +134,24 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 {
 	u8 *req_data = NULL, *resp_data = NULL, *buf;
 	struct sas_ha_struct *sas_ha = SHOST_TO_SAS_HA(shost);
-	int error = -EINVAL, resp_data_len = rsp->data_len;
+	int error = -EINVAL;
 
 	/* eight is the minimum size for request and response frames */
-	if (req->data_len < 8 || rsp->data_len < 8)
+	if (blk_rq_bytes(req) < 8 || blk_rq_bytes(rsp) < 8)
 		goto out;
 
-	if (bio_offset(req->bio) + req->data_len > PAGE_SIZE ||
-	    bio_offset(rsp->bio) + rsp->data_len > PAGE_SIZE) {
+	if (bio_offset(req->bio) + blk_rq_bytes(req) > PAGE_SIZE ||
+	    bio_offset(rsp->bio) + blk_rq_bytes(rsp) > PAGE_SIZE) {
 		shost_printk(KERN_ERR, shost,
 			"SMP request/response frame crosses page boundary");
 		goto out;
 	}
 
-	req_data = kzalloc(req->data_len, GFP_KERNEL);
+	req_data = kzalloc(blk_rq_bytes(req), GFP_KERNEL);
 
 	/* make sure frame can always be built ... we copy
 	 * back only the requested length */
-	resp_data = kzalloc(max(rsp->data_len, 128U), GFP_KERNEL);
+	resp_data = kzalloc(max(blk_rq_bytes(rsp), 128U), GFP_KERNEL);
 
 	if (!req_data || !resp_data) {
 		error = -ENOMEM;
@@ -160,7 +160,7 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 
 	local_irq_disable();
 	buf = kmap_atomic(bio_page(req->bio), KM_USER0) + bio_offset(req->bio);
-	memcpy(req_data, buf, req->data_len);
+	memcpy(req_data, buf, blk_rq_bytes(req));
 	kunmap_atomic(buf - bio_offset(req->bio), KM_USER0);
 	local_irq_enable();
 
@@ -178,15 +178,15 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 
 	switch (req_data[1]) {
 	case SMP_REPORT_GENERAL:
-		req->data_len -= 8;
-		resp_data_len -= 32;
+		req->resid_len -= 8;
+		rsp->resid_len -= 32;
 		resp_data[2] = SMP_RESP_FUNC_ACC;
 		resp_data[9] = sas_ha->num_phys;
 		break;
 
 	case SMP_REPORT_MANUF_INFO:
-		req->data_len -= 8;
-		resp_data_len -= 64;
+		req->resid_len -= 8;
+		rsp->resid_len -= 64;
 		resp_data[2] = SMP_RESP_FUNC_ACC;
 		memcpy(resp_data + 12, shost->hostt->name,
 		       SAS_EXPANDER_VENDOR_ID_LEN);
@@ -199,13 +199,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 		break;
 
 	case SMP_DISCOVER:
-		req->data_len -= 16;
-		if ((int)req->data_len < 0) {
-			req->data_len = 0;
+		req->resid_len -= 16;
+		if ((int)req->resid_len < 0) {
+			req->resid_len = 0;
 			error = -EINVAL;
 			goto out;
 		}
-		resp_data_len -= 56;
+		rsp->resid_len -= 56;
 		sas_host_smp_discover(sas_ha, resp_data, req_data[9]);
 		break;
 
@@ -215,13 +215,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 		break;
 
 	case SMP_REPORT_PHY_SATA:
-		req->data_len -= 16;
-		if ((int)req->data_len < 0) {
-			req->data_len = 0;
+		req->resid_len -= 16;
+		if ((int)req->resid_len < 0) {
+			req->resid_len = 0;
 			error = -EINVAL;
 			goto out;
 		}
-		resp_data_len -= 60;
+		rsp->resid_len -= 60;
 		sas_report_phy_sata(sas_ha, resp_data, req_data[9]);
 		break;
 
@@ -238,13 +238,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 		break;
 
 	case SMP_PHY_CONTROL:
-		req->data_len -= 44;
-		if ((int)req->data_len < 0) {
-			req->data_len = 0;
+		req->resid_len -= 44;
+		if ((int)req->resid_len < 0) {
+			req->resid_len = 0;
 			error = -EINVAL;
 			goto out;
 		}
-		resp_data_len -= 8;
+		rsp->resid_len -= 8;
 		sas_phy_control(sas_ha, req_data[9], req_data[10],
 				req_data[32] >> 4, req_data[33] >> 4,
 				resp_data);
@@ -261,11 +261,10 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 
 	local_irq_disable();
 	buf = kmap_atomic(bio_page(rsp->bio), KM_USER0) + bio_offset(rsp->bio);
-	memcpy(buf, resp_data, rsp->data_len);
+	memcpy(buf, resp_data, blk_rq_bytes(rsp));
 	flush_kernel_dcache_page(bio_page(rsp->bio));
 	kunmap_atomic(buf - bio_offset(rsp->bio), KM_USER0);
 	local_irq_enable();
-	rsp->data_len = resp_data_len;
 
  out:
 	kfree(req_data);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 167b66dd34c7..8032c5adb6a9 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -1312,10 +1312,10 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 	uint32_t bgstat = bgf->bgstat;
 	uint64_t failing_sector = 0;
 
-	printk(KERN_ERR "BG ERROR in cmd 0x%x lba 0x%llx blk cnt 0x%lx "
+	printk(KERN_ERR "BG ERROR in cmd 0x%x lba 0x%llx blk cnt 0x%x "
 			"bgstat=0x%x bghm=0x%x\n",
 			cmd->cmnd[0], (unsigned long long)scsi_get_lba(cmd),
-			cmd->request->nr_sectors, bgstat, bghm);
+			blk_rq_sectors(cmd->request), bgstat, bghm);
 
 	spin_lock(&_dump_buf_lock);
 	if (!_dump_buf_done) {
@@ -2378,15 +2378,15 @@ lpfc_queuecommand(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
 		if (cmnd->cmnd[0] == READ_10)
 			lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
 					"9035 BLKGRD: READ @ sector %llu, "
-					 "count %lu\n",
-					 (unsigned long long)scsi_get_lba(cmnd),
-					cmnd->request->nr_sectors);
+					"count %u\n",
+					(unsigned long long)scsi_get_lba(cmnd),
+					blk_rq_sectors(cmnd->request));
 		else if (cmnd->cmnd[0] == WRITE_10)
 			lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
 					"9036 BLKGRD: WRITE @ sector %llu, "
-					"count %lu cmd=%p\n",
+					"count %u cmd=%p\n",
 					(unsigned long long)scsi_get_lba(cmnd),
-					cmnd->request->nr_sectors,
+					blk_rq_sectors(cmnd->request),
 					cmnd);
 
 		err = lpfc_bg_scsi_prep_dma_buf(phba, lpfc_cmd);
@@ -2406,15 +2406,15 @@ lpfc_queuecommand(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd *))
 		if (cmnd->cmnd[0] == READ_10)
 			lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
 					 "9040 dbg: READ @ sector %llu, "
-					 "count %lu\n",
+					 "count %u\n",
 					 (unsigned long long)scsi_get_lba(cmnd),
-					 cmnd->request->nr_sectors);
+					 blk_rq_sectors(cmnd->request));
 		else if (cmnd->cmnd[0] == WRITE_10)
 			lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
 					 "9041 dbg: WRITE @ sector %llu, "
-					 "count %lu cmd=%p\n",
+					 "count %u cmd=%p\n",
 					 (unsigned long long)scsi_get_lba(cmnd),
-					 cmnd->request->nr_sectors, cmnd);
+					 blk_rq_sectors(cmnd->request), cmnd);
 		else
 			lpfc_printf_vlog(vport, KERN_WARNING, LOG_BG,
 					 "9042 dbg: parser not implemented\n");
diff --git a/drivers/scsi/mpt2sas/mpt2sas_transport.c b/drivers/scsi/mpt2sas/mpt2sas_transport.c
index e03dc0b1e1a0..5c65da519e39 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_transport.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_transport.c
@@ -1041,7 +1041,7 @@ transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	if (req->bio->bi_vcnt > 1 || rsp->bio->bi_vcnt > 1) {
 		printk(MPT2SAS_ERR_FMT "%s: multiple segments req %u %u, "
 		    "rsp %u %u\n", ioc->name, __func__, req->bio->bi_vcnt,
-		    req->data_len, rsp->bio->bi_vcnt, rsp->data_len);
+		    blk_rq_bytes(req), rsp->bio->bi_vcnt, blk_rq_bytes(rsp));
 		return -EINVAL;
 	}
 
@@ -1104,7 +1104,7 @@ transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	*((u64 *)&mpi_request->SASAddress) = (rphy) ?
 	    cpu_to_le64(rphy->identify.sas_address) :
 	    cpu_to_le64(ioc->sas_hba.sas_address);
-	mpi_request->RequestDataLength = cpu_to_le16(req->data_len - 4);
+	mpi_request->RequestDataLength = cpu_to_le16(blk_rq_bytes(req) - 4);
 	psge = &mpi_request->SGL;
 
 	/* WRITE sgel first */
@@ -1112,13 +1112,13 @@ transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	    MPI2_SGE_FLAGS_END_OF_BUFFER | MPI2_SGE_FLAGS_HOST_TO_IOC);
 	sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT;
 	dma_addr_out = pci_map_single(ioc->pdev, bio_data(req->bio),
-	      req->data_len, PCI_DMA_BIDIRECTIONAL);
+		blk_rq_bytes(req), PCI_DMA_BIDIRECTIONAL);
 	if (!dma_addr_out) {
 		mpt2sas_base_free_smid(ioc, le16_to_cpu(smid));
 		goto unmap;
 	}
 
-	ioc->base_add_sg_single(psge, sgl_flags | (req->data_len - 4),
+	ioc->base_add_sg_single(psge, sgl_flags | (blk_rq_bytes(req) - 4),
 	    dma_addr_out);
 
 	/* incr sgel */
@@ -1129,14 +1129,14 @@ transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	    MPI2_SGE_FLAGS_LAST_ELEMENT | MPI2_SGE_FLAGS_END_OF_BUFFER |
 	    MPI2_SGE_FLAGS_END_OF_LIST);
 	sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT;
-	dma_addr_in =  pci_map_single(ioc->pdev, bio_data(rsp->bio),
-	      rsp->data_len, PCI_DMA_BIDIRECTIONAL);
+	dma_addr_in = pci_map_single(ioc->pdev, bio_data(rsp->bio),
+				     blk_rq_bytes(rsp), PCI_DMA_BIDIRECTIONAL);
 	if (!dma_addr_in) {
 		mpt2sas_base_free_smid(ioc, le16_to_cpu(smid));
 		goto unmap;
 	}
 
-	ioc->base_add_sg_single(psge, sgl_flags | (rsp->data_len + 4),
+	ioc->base_add_sg_single(psge, sgl_flags | (blk_rq_bytes(rsp) + 4),
 	    dma_addr_in);
 
 	dtransportprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s - "
@@ -1170,9 +1170,8 @@ transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 
 		memcpy(req->sense, mpi_reply, sizeof(*mpi_reply));
 		req->sense_len = sizeof(*mpi_reply);
-		req->data_len = 0;
-		rsp->data_len -= mpi_reply->ResponseDataLength;
-
+		req->resid_len = 0;
+		rsp->resid_len -= mpi_reply->ResponseDataLength;
 	} else {
 		dtransportprintk(ioc, printk(MPT2SAS_DEBUG_FMT
 		    "%s - no reply\n", ioc->name, __func__));
@@ -1188,10 +1187,10 @@ transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 
  unmap:
 	if (dma_addr_out)
-		pci_unmap_single(ioc->pdev, dma_addr_out, req->data_len,
+		pci_unmap_single(ioc->pdev, dma_addr_out, blk_rq_bytes(req),
 		    PCI_DMA_BIDIRECTIONAL);
 	if (dma_addr_in)
-		pci_unmap_single(ioc->pdev, dma_addr_in, rsp->data_len,
+		pci_unmap_single(ioc->pdev, dma_addr_in, blk_rq_bytes(rsp),
 		    PCI_DMA_BIDIRECTIONAL);
 
  out:
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index 1ce6b24abab2..5776b2ab6b12 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -889,26 +889,6 @@ int osd_req_add_set_attr_list(struct osd_request *or,
 }
 EXPORT_SYMBOL(osd_req_add_set_attr_list);
 
-static int _append_map_kern(struct request *req,
-	void *buff, unsigned len, gfp_t flags)
-{
-	struct bio *bio;
-	int ret;
-
-	bio = bio_map_kern(req->q, buff, len, flags);
-	if (IS_ERR(bio)) {
-		OSD_ERR("Failed bio_map_kern(%p, %d) => %ld\n", buff, len,
-			PTR_ERR(bio));
-		return PTR_ERR(bio);
-	}
-	ret = blk_rq_append_bio(req->q, req, bio);
-	if (ret) {
-		OSD_ERR("Failed blk_rq_append_bio(%p) => %d\n", bio, ret);
-		bio_put(bio);
-	}
-	return ret;
-}
-
 static int _req_append_segment(struct osd_request *or,
 	unsigned padding, struct _osd_req_data_segment *seg,
 	struct _osd_req_data_segment *last_seg, struct _osd_io_info *io)
@@ -924,14 +904,14 @@ static int _req_append_segment(struct osd_request *or,
 		else
 			pad_buff = io->pad_buff;
 
-		ret = _append_map_kern(io->req, pad_buff, padding,
+		ret = blk_rq_map_kern(io->req->q, io->req, pad_buff, padding,
 				       or->alloc_flags);
 		if (ret)
 			return ret;
 		io->total_bytes += padding;
 	}
 
-	ret = _append_map_kern(io->req, seg->buff, seg->total_bytes,
+	ret = blk_rq_map_kern(io->req->q, io->req, seg->buff, seg->total_bytes,
 			       or->alloc_flags);
 	if (ret)
 		return ret;
@@ -1293,6 +1273,21 @@ static int _osd_req_finalize_data_integrity(struct osd_request *or,
 /*
  * osd_finalize_request and helpers
  */
+static struct request *_make_request(struct request_queue *q, bool has_write,
+			      struct _osd_io_info *oii, gfp_t flags)
+{
+	if (oii->bio)
+		return blk_make_request(q, oii->bio, flags);
+	else {
+		struct request *req;
+
+		req = blk_get_request(q, has_write ? WRITE : READ, flags);
+		if (unlikely(!req))
+			return ERR_PTR(-ENOMEM);
+
+		return req;
+	}
+}
 
 static int _init_blk_request(struct osd_request *or,
 	bool has_in, bool has_out)
@@ -1301,11 +1296,13 @@ static int _init_blk_request(struct osd_request *or,
 	struct scsi_device *scsi_device = or->osd_dev->scsi_device;
 	struct request_queue *q = scsi_device->request_queue;
 	struct request *req;
-	int ret = -ENOMEM;
+	int ret;
 
-	req = blk_get_request(q, has_out, flags);
-	if (!req)
+	req = _make_request(q, has_out, has_out ? &or->out : &or->in, flags);
+	if (IS_ERR(req)) {
+		ret = PTR_ERR(req);
 		goto out;
+	}
 
 	or->request = req;
 	req->cmd_type = REQ_TYPE_BLOCK_PC;
@@ -1318,9 +1315,10 @@ static int _init_blk_request(struct osd_request *or,
 		or->out.req = req;
 		if (has_in) {
 			/* allocate bidi request */
-			req = blk_get_request(q, READ, flags);
-			if (!req) {
+			req = _make_request(q, false, &or->in, flags);
+			if (IS_ERR(req)) {
 				OSD_DEBUG("blk_get_request for bidi failed\n");
+				ret = PTR_ERR(req);
 				goto out;
 			}
 			req->cmd_type = REQ_TYPE_BLOCK_PC;
@@ -1364,26 +1362,6 @@ int osd_finalize_request(struct osd_request *or,
 		return ret;
 	}
 
-	if (or->out.bio) {
-		ret = blk_rq_append_bio(or->request->q, or->out.req,
-					or->out.bio);
-		if (ret) {
-			OSD_DEBUG("blk_rq_append_bio out failed\n");
-			return ret;
-		}
-		OSD_DEBUG("out bytes=%llu (bytes_req=%u)\n",
-			_LLU(or->out.total_bytes), or->out.req->data_len);
-	}
-	if (or->in.bio) {
-		ret = blk_rq_append_bio(or->request->q, or->in.req, or->in.bio);
-		if (ret) {
-			OSD_DEBUG("blk_rq_append_bio in failed\n");
-			return ret;
-		}
-		OSD_DEBUG("in bytes=%llu (bytes_req=%u)\n",
-			_LLU(or->in.total_bytes), or->in.req->data_len);
-	}
-
 	or->out.pad_buff = sg_out_pad_buffer;
 	or->in.pad_buff = sg_in_pad_buffer;
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index bb218c8b6e98..dd3f9d2b99fd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -240,11 +240,11 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	 * is invalid.  Prevent the garbage from being misinterpreted
 	 * and prevent security leaks by zeroing out the excess data.
 	 */
-	if (unlikely(req->data_len > 0 && req->data_len <= bufflen))
-		memset(buffer + (bufflen - req->data_len), 0, req->data_len);
+	if (unlikely(req->resid_len > 0 && req->resid_len <= bufflen))
+		memset(buffer + (bufflen - req->resid_len), 0, req->resid_len);
 
 	if (resid)
-		*resid = req->data_len;
+		*resid = req->resid_len;
 	ret = req->errors;
  out:
 	blk_put_request(req);
@@ -546,14 +546,9 @@ static struct scsi_cmnd *scsi_end_request(struct scsi_cmnd *cmd, int error,
 	 * to queue the remainder of them.
 	 */
 	if (blk_end_request(req, error, bytes)) {
-		int leftover = (req->hard_nr_sectors << 9);
-
-		if (blk_pc_request(req))
-			leftover = req->data_len;
-
 		/* kill remainder if no retrys */
 		if (error && scsi_noretry_cmd(cmd))
-			blk_end_request(req, error, leftover);
+			blk_end_request_all(req, error);
 		else {
 			if (requeue) {
 				/*
@@ -672,34 +667,6 @@ void scsi_release_buffers(struct scsi_cmnd *cmd)
 }
 EXPORT_SYMBOL(scsi_release_buffers);
 
-/*
- * Bidi commands Must be complete as a whole, both sides at once.
- * If part of the bytes were written and lld returned
- * scsi_in()->resid and/or scsi_out()->resid this information will be left
- * in req->data_len and req->next_rq->data_len. The upper-layer driver can
- * decide what to do with this information.
- */
-static void scsi_end_bidi_request(struct scsi_cmnd *cmd)
-{
-	struct request *req = cmd->request;
-	unsigned int dlen = req->data_len;
-	unsigned int next_dlen = req->next_rq->data_len;
-
-	req->data_len = scsi_out(cmd)->resid;
-	req->next_rq->data_len = scsi_in(cmd)->resid;
-
-	/* The req and req->next_rq have not been completed */
-	BUG_ON(blk_end_bidi_request(req, 0, dlen, next_dlen));
-
-	scsi_release_buffers(cmd);
-
-	/*
-	 * This will goose the queue request function at the end, so we don't
-	 * need to worry about launching another command.
-	 */
-	scsi_next_command(cmd);
-}
-
 /*
  * Function:    scsi_io_completion()
  *
@@ -739,7 +706,6 @@ static void scsi_end_bidi_request(struct scsi_cmnd *cmd)
 void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 {
 	int result = cmd->result;
-	int this_count;
 	struct request_queue *q = cmd->device->request_queue;
 	struct request *req = cmd->request;
 	int error = 0;
@@ -773,12 +739,22 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			if (!sense_deferred)
 				error = -EIO;
 		}
+
+		req->resid_len = scsi_get_resid(cmd);
+
 		if (scsi_bidi_cmnd(cmd)) {
-			/* will also release_buffers */
-			scsi_end_bidi_request(cmd);
+			/*
+			 * Bidi commands Must be complete as a whole,
+			 * both sides at once.
+			 */
+			req->next_rq->resid_len = scsi_in(cmd)->resid;
+
+			blk_end_request_all(req, 0);
+
+			scsi_release_buffers(cmd);
+			scsi_next_command(cmd);
 			return;
 		}
-		req->data_len = scsi_get_resid(cmd);
 	}
 
 	BUG_ON(blk_bidi_rq(req)); /* bidi not support for !blk_pc_request yet */
@@ -787,9 +763,9 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	 * Next deal with any sectors which we were able to correctly
 	 * handle.
 	 */
-	SCSI_LOG_HLCOMPLETE(1, printk("%ld sectors total, "
+	SCSI_LOG_HLCOMPLETE(1, printk("%u sectors total, "
 				      "%d bytes done.\n",
-				      req->nr_sectors, good_bytes));
+				      blk_rq_sectors(req), good_bytes));
 
 	/*
 	 * Recovered errors need reporting, but they're always treated
@@ -812,7 +788,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	 */
 	if (scsi_end_request(cmd, error, good_bytes, result == 0) == NULL)
 		return;
-	this_count = blk_rq_bytes(req);
 
 	error = -EIO;
 
@@ -922,7 +897,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			if (driver_byte(result) & DRIVER_SENSE)
 				scsi_print_sense("", cmd);
 		}
-		blk_end_request(req, -EIO, blk_rq_bytes(req));
+		blk_end_request_all(req, -EIO);
 		scsi_next_command(cmd);
 		break;
 	case ACTION_REPREP:
@@ -965,10 +940,7 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
 	count = blk_rq_map_sg(req->q, req, sdb->table.sgl);
 	BUG_ON(count > sdb->table.nents);
 	sdb->table.nents = count;
-	if (blk_pc_request(req))
-		sdb->length = req->data_len;
-	else
-		sdb->length = req->nr_sectors << 9;
+	sdb->length = blk_rq_bytes(req);
 	return BLKPREP_OK;
 }
 
@@ -1087,22 +1059,21 @@ int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req)
 		if (unlikely(ret))
 			return ret;
 	} else {
-		BUG_ON(req->data_len);
-		BUG_ON(req->data);
+		BUG_ON(blk_rq_bytes(req));
 
 		memset(&cmd->sdb, 0, sizeof(cmd->sdb));
 		req->buffer = NULL;
 	}
 
 	cmd->cmd_len = req->cmd_len;
-	if (!req->data_len)
+	if (!blk_rq_bytes(req))
 		cmd->sc_data_direction = DMA_NONE;
 	else if (rq_data_dir(req) == WRITE)
 		cmd->sc_data_direction = DMA_TO_DEVICE;
 	else
 		cmd->sc_data_direction = DMA_FROM_DEVICE;
 	
-	cmd->transfersize = req->data_len;
+	cmd->transfersize = blk_rq_bytes(req);
 	cmd->allowed = req->retries;
 	return BLKPREP_OK;
 }
@@ -1212,7 +1183,7 @@ int scsi_prep_return(struct request_queue *q, struct request *req, int ret)
 		break;
 	case BLKPREP_DEFER:
 		/*
-		 * If we defer, the elv_next_request() returns NULL, but the
+		 * If we defer, the blk_peek_request() returns NULL, but the
 		 * queue must be restarted, so we plug here if no returning
 		 * command will automatically do that.
 		 */
@@ -1388,7 +1359,7 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
 	struct scsi_target *starget = scsi_target(sdev);
 	struct Scsi_Host *shost = sdev->host;
 
-	blkdev_dequeue_request(req);
+	blk_start_request(req);
 
 	if (unlikely(cmd == NULL)) {
 		printk(KERN_CRIT "impossible request in %s.\n",
@@ -1480,7 +1451,7 @@ static void scsi_request_fn(struct request_queue *q)
 
 	if (!sdev) {
 		printk("scsi: killing requests for dead queue\n");
-		while ((req = elv_next_request(q)) != NULL)
+		while ((req = blk_peek_request(q)) != NULL)
 			scsi_kill_request(req, q);
 		return;
 	}
@@ -1501,7 +1472,7 @@ static void scsi_request_fn(struct request_queue *q)
 		 * that the request is fully prepared even if we cannot 
 		 * accept it.
 		 */
-		req = elv_next_request(q);
+		req = blk_peek_request(q);
 		if (!req || !scsi_dev_queue_ready(q, sdev))
 			break;
 
@@ -1517,7 +1488,7 @@ static void scsi_request_fn(struct request_queue *q)
 		 * Remove the request from the request list.
 		 */
 		if (!(blk_queue_tagged(q) && !blk_queue_start_tag(q, req)))
-			blkdev_dequeue_request(req);
+			blk_start_request(req);
 		sdev->device_busy++;
 
 		spin_unlock(q->queue_lock);
diff --git a/drivers/scsi/scsi_tgt_lib.c b/drivers/scsi/scsi_tgt_lib.c
index 48ba413f7f6a..10303272ba45 100644
--- a/drivers/scsi/scsi_tgt_lib.c
+++ b/drivers/scsi/scsi_tgt_lib.c
@@ -387,7 +387,7 @@ static int scsi_map_user_pages(struct scsi_tgt_cmd *tcmd, struct scsi_cmnd *cmd,
 	 * we use REQ_TYPE_BLOCK_PC so scsi_init_io doesn't set the
 	 * length for us.
 	 */
-	cmd->sdb.length = rq->data_len;
+	cmd->sdb.length = blk_rq_bytes(rq);
 
 	return 0;
 
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 50988cbf7b2d..d606452297cf 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -163,12 +163,10 @@ static void sas_smp_request(struct request_queue *q, struct Scsi_Host *shost,
 	int (*handler)(struct Scsi_Host *, struct sas_rphy *, struct request *);
 
 	while (!blk_queue_plugged(q)) {
-		req = elv_next_request(q);
+		req = blk_fetch_request(q);
 		if (!req)
 			break;
 
-		blkdev_dequeue_request(req);
-
 		spin_unlock_irq(q->queue_lock);
 
 		handler = to_sas_internal(shost->transportt)->f->smp_handler;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 84044233b637..bcf3bd40bbd5 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -384,9 +384,9 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 	struct scsi_device *sdp = q->queuedata;
 	struct gendisk *disk = rq->rq_disk;
 	struct scsi_disk *sdkp;
-	sector_t block = rq->sector;
+	sector_t block = blk_rq_pos(rq);
 	sector_t threshold;
-	unsigned int this_count = rq->nr_sectors;
+	unsigned int this_count = blk_rq_sectors(rq);
 	int ret, host_dif;
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
@@ -413,10 +413,10 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 					this_count));
 
 	if (!sdp || !scsi_device_online(sdp) ||
- 	    block + rq->nr_sectors > get_capacity(disk)) {
+	    block + blk_rq_sectors(rq) > get_capacity(disk)) {
 		SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
-						"Finishing %ld sectors\n",
-						rq->nr_sectors));
+						"Finishing %u sectors\n",
+						blk_rq_sectors(rq)));
 		SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
 						"Retry with 0x%p\n", SCpnt));
 		goto out;
@@ -463,7 +463,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 	 * for this.
 	 */
 	if (sdp->sector_size == 1024) {
-		if ((block & 1) || (rq->nr_sectors & 1)) {
+		if ((block & 1) || (blk_rq_sectors(rq) & 1)) {
 			scmd_printk(KERN_ERR, SCpnt,
 				    "Bad block number requested\n");
 			goto out;
@@ -473,7 +473,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 		}
 	}
 	if (sdp->sector_size == 2048) {
-		if ((block & 3) || (rq->nr_sectors & 3)) {
+		if ((block & 3) || (blk_rq_sectors(rq) & 3)) {
 			scmd_printk(KERN_ERR, SCpnt,
 				    "Bad block number requested\n");
 			goto out;
@@ -483,7 +483,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 		}
 	}
 	if (sdp->sector_size == 4096) {
-		if ((block & 7) || (rq->nr_sectors & 7)) {
+		if ((block & 7) || (blk_rq_sectors(rq) & 7)) {
 			scmd_printk(KERN_ERR, SCpnt,
 				    "Bad block number requested\n");
 			goto out;
@@ -512,10 +512,10 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 	}
 
 	SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
-					"%s %d/%ld 512 byte blocks.\n",
+					"%s %d/%u 512 byte blocks.\n",
 					(rq_data_dir(rq) == WRITE) ?
 					"writing" : "reading", this_count,
-					rq->nr_sectors));
+					blk_rq_sectors(rq)));
 
 	/* Set RDPROTECT/WRPROTECT if disk is formatted with DIF */
 	host_dif = scsi_host_dif_capable(sdp->host, sdkp->protection_type);
@@ -971,8 +971,8 @@ static struct block_device_operations sd_fops = {
 
 static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd)
 {
-	u64 start_lba = scmd->request->sector;
-	u64 end_lba = scmd->request->sector + (scsi_bufflen(scmd) / 512);
+	u64 start_lba = blk_rq_pos(scmd->request);
+	u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512);
 	u64 bad_lba;
 	int info_valid;
 
@@ -1510,7 +1510,7 @@ got_data:
 		 */
 		sector_size = 512;
 	}
-	blk_queue_hardsect_size(sdp->request_queue, sector_size);
+	blk_queue_logical_block_size(sdp->request_queue, sector_size);
 
 	{
 		char cap_str_2[10], cap_str_10[10];
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 184dff492797..82f14a9482d0 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -507,7 +507,7 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 	sector_sz = scmd->device->sector_size;
 	sectors = good_bytes / sector_sz;
 
-	phys = scmd->request->sector & 0xffffffff;
+	phys = blk_rq_pos(scmd->request) & 0xffffffff;
 	if (sector_sz == 4096)
 		phys >>= 3;
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index e1716f14cd47..8201387b4daa 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -289,8 +289,8 @@ sg_open(struct inode *inode, struct file *filp)
 	if (list_empty(&sdp->sfds)) {	/* no existing opens on this device */
 		sdp->sgdebug = 0;
 		q = sdp->device->request_queue;
-		sdp->sg_tablesize = min(q->max_hw_segments,
-					q->max_phys_segments);
+		sdp->sg_tablesize = min(queue_max_hw_segments(q),
+					queue_max_phys_segments(q));
 	}
 	if ((sfp = sg_add_sfp(sdp, dev)))
 		filp->private_data = sfp;
@@ -909,7 +909,7 @@ sg_ioctl(struct inode *inode, struct file *filp,
                 if (val < 0)
                         return -EINVAL;
 		val = min_t(int, val,
-				sdp->device->request_queue->max_sectors * 512);
+			    queue_max_sectors(sdp->device->request_queue) * 512);
 		if (val != sfp->reserve.bufflen) {
 			if (sg_res_in_use(sfp) || sfp->mmap_called)
 				return -EBUSY;
@@ -919,7 +919,7 @@ sg_ioctl(struct inode *inode, struct file *filp,
 		return 0;
 	case SG_GET_RESERVED_SIZE:
 		val = min_t(int, sfp->reserve.bufflen,
-				sdp->device->request_queue->max_sectors * 512);
+			    queue_max_sectors(sdp->device->request_queue) * 512);
 		return put_user(val, ip);
 	case SG_SET_COMMAND_Q:
 		result = get_user(val, ip);
@@ -1059,12 +1059,13 @@ sg_ioctl(struct inode *inode, struct file *filp,
 			return -ENODEV;
 		return scsi_ioctl(sdp->device, cmd_in, p);
 	case BLKSECTGET:
-		return put_user(sdp->device->request_queue->max_sectors * 512,
+		return put_user(queue_max_sectors(sdp->device->request_queue) * 512,
 				ip);
 	case BLKTRACESETUP:
 		return blk_trace_setup(sdp->device->request_queue,
 				       sdp->disk->disk_name,
 				       MKDEV(SCSI_GENERIC_MAJOR, sdp->index),
+				       NULL,
 				       (char *)arg);
 	case BLKTRACESTART:
 		return blk_trace_startstop(sdp->device->request_queue, 1);
@@ -1260,7 +1261,7 @@ static void sg_rq_end_io(struct request *rq, int uptodate)
 
 	sense = rq->sense;
 	result = rq->errors;
-	resid = rq->data_len;
+	resid = rq->resid_len;
 
 	SCSI_LOG_TIMEOUT(4, printk("sg_cmd_done: %s, pack_id=%d, res=0x%x\n",
 		sdp->disk->disk_name, srp->header.pack_id, result));
@@ -1377,7 +1378,8 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp)
 	sdp->device = scsidp;
 	INIT_LIST_HEAD(&sdp->sfds);
 	init_waitqueue_head(&sdp->o_excl_wait);
-	sdp->sg_tablesize = min(q->max_hw_segments, q->max_phys_segments);
+	sdp->sg_tablesize = min(queue_max_hw_segments(q),
+				queue_max_phys_segments(q));
 	sdp->index = k;
 	kref_init(&sdp->d_ref);
 
@@ -2055,7 +2057,7 @@ sg_add_sfp(Sg_device * sdp, int dev)
 		sg_big_buff = def_reserved_size;
 
 	bufflen = min_t(int, sg_big_buff,
-			sdp->device->request_queue->max_sectors * 512);
+			queue_max_sectors(sdp->device->request_queue) * 512);
 	sg_build_reserve(sfp, bufflen);
 	SCSI_LOG_TIMEOUT(3, printk("sg_add_sfp:   bufflen=%d, k_use_sg=%d\n",
 			   sfp->reserve.bufflen, sfp->reserve.k_use_sg));
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 0e1a0f2d2ad5..cd350dfc1216 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -292,7 +292,8 @@ static int sr_done(struct scsi_cmnd *SCpnt)
 			if (cd->device->sector_size == 2048)
 				error_sector <<= 2;
 			error_sector &= ~(block_sectors - 1);
-			good_bytes = (error_sector - SCpnt->request->sector) << 9;
+			good_bytes = (error_sector -
+				      blk_rq_pos(SCpnt->request)) << 9;
 			if (good_bytes < 0 || good_bytes >= this_count)
 				good_bytes = 0;
 			/*
@@ -349,8 +350,8 @@ static int sr_prep_fn(struct request_queue *q, struct request *rq)
 				cd->disk->disk_name, block));
 
 	if (!cd->device || !scsi_device_online(cd->device)) {
-		SCSI_LOG_HLQUEUE(2, printk("Finishing %ld sectors\n",
-					rq->nr_sectors));
+		SCSI_LOG_HLQUEUE(2, printk("Finishing %u sectors\n",
+					   blk_rq_sectors(rq)));
 		SCSI_LOG_HLQUEUE(2, printk("Retry with 0x%p\n", SCpnt));
 		goto out;
 	}
@@ -413,7 +414,7 @@ static int sr_prep_fn(struct request_queue *q, struct request *rq)
 	/*
 	 * request doesn't start on hw block boundary, add scatter pads
 	 */
-	if (((unsigned int)rq->sector % (s_size >> 9)) ||
+	if (((unsigned int)blk_rq_pos(rq) % (s_size >> 9)) ||
 	    (scsi_bufflen(SCpnt) % s_size)) {
 		scmd_printk(KERN_NOTICE, SCpnt, "unaligned transfer\n");
 		goto out;
@@ -422,14 +423,14 @@ static int sr_prep_fn(struct request_queue *q, struct request *rq)
 	this_count = (scsi_bufflen(SCpnt) >> 9) / (s_size >> 9);
 
 
-	SCSI_LOG_HLQUEUE(2, printk("%s : %s %d/%ld 512 byte blocks.\n",
+	SCSI_LOG_HLQUEUE(2, printk("%s : %s %d/%u 512 byte blocks.\n",
 				cd->cdi.name,
 				(rq_data_dir(rq) == WRITE) ?
 					"writing" : "reading",
-				this_count, rq->nr_sectors));
+				this_count, blk_rq_sectors(rq)));
 
 	SCpnt->cmnd[1] = 0;
-	block = (unsigned int)rq->sector / (s_size >> 9);
+	block = (unsigned int)blk_rq_pos(rq) / (s_size >> 9);
 
 	if (this_count > 0xffff) {
 		this_count = 0xffff;
@@ -726,7 +727,7 @@ static void get_sectorsize(struct scsi_cd *cd)
 	}
 
 	queue = cd->device->request_queue;
-	blk_queue_hardsect_size(queue, sector_size);
+	blk_queue_logical_block_size(queue, sector_size);
 
 	return;
 }
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index eb24efea8f14..89bd438e1fe3 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -463,7 +463,7 @@ static void st_scsi_execute_end(struct request *req, int uptodate)
 	struct scsi_tape *STp = SRpnt->stp;
 
 	STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
-	STp->buffer->cmdstat.residual = req->data_len;
+	STp->buffer->cmdstat.residual = req->resid_len;
 
 	if (SRpnt->waiting)
 		complete(SRpnt->waiting);
@@ -3983,8 +3983,8 @@ static int st_probe(struct device *dev)
 		return -ENODEV;
 	}
 
-	i = min(SDp->request_queue->max_hw_segments,
-		SDp->request_queue->max_phys_segments);
+	i = min(queue_max_hw_segments(SDp->request_queue),
+		queue_max_phys_segments(SDp->request_queue));
 	if (st_max_sg_segs < i)
 		i = st_max_sg_segs;
 	buffer = new_tape_buffer((SDp->host)->unchecked_isa_dma, i);
diff --git a/drivers/scsi/u14-34f.c b/drivers/scsi/u14-34f.c
index 601e95141cbe..54023d41fd15 100644
--- a/drivers/scsi/u14-34f.c
+++ b/drivers/scsi/u14-34f.c
@@ -1306,7 +1306,7 @@ static int u14_34f_queuecommand(struct scsi_cmnd *SCpnt, void (*done)(struct scs
    if (linked_comm && SCpnt->device->queue_depth > 2
                                      && TLDEV(SCpnt->device->type)) {
       HD(j)->cp_stat[i] = READY;
-      flush_dev(SCpnt->device, SCpnt->request->sector, j, FALSE);
+      flush_dev(SCpnt->device, blk_rq_pos(SCpnt->request), j, FALSE);
       return 0;
       }
 
@@ -1610,11 +1610,13 @@ static int reorder(unsigned int j, unsigned long cursec,
 
       if (!(cpp->xdir == DTD_IN)) input_only = FALSE;
 
-      if (SCpnt->request->sector < minsec) minsec = SCpnt->request->sector;
-      if (SCpnt->request->sector > maxsec) maxsec = SCpnt->request->sector;
+      if (blk_rq_pos(SCpnt->request) < minsec)
+	 minsec = blk_rq_pos(SCpnt->request);
+      if (blk_rq_pos(SCpnt->request) > maxsec)
+	 maxsec = blk_rq_pos(SCpnt->request);
 
-      sl[n] = SCpnt->request->sector;
-      ioseek += SCpnt->request->nr_sectors;
+      sl[n] = blk_rq_pos(SCpnt->request);
+      ioseek += blk_rq_sectors(SCpnt->request);
 
       if (!n) continue;
 
@@ -1642,7 +1644,7 @@ static int reorder(unsigned int j, unsigned long cursec,
 
    if (!input_only) for (n = 0; n < n_ready; n++) {
       k = il[n]; cpp = &HD(j)->cp[k]; SCpnt = cpp->SCpnt;
-      ll[n] = SCpnt->request->nr_sectors; pl[n] = SCpnt->serial_number;
+      ll[n] = blk_rq_sectors(SCpnt->request); pl[n] = SCpnt->serial_number;
 
       if (!n) continue;
 
@@ -1666,12 +1668,12 @@ static int reorder(unsigned int j, unsigned long cursec,
    if (link_statistics && (overlap || !(flushcount % link_statistics)))
       for (n = 0; n < n_ready; n++) {
          k = il[n]; cpp = &HD(j)->cp[k]; SCpnt = cpp->SCpnt;
-         printk("%s %d.%d:%d pid %ld mb %d fc %d nr %d sec %ld ns %ld"\
+         printk("%s %d.%d:%d pid %ld mb %d fc %d nr %d sec %ld ns %u"\
                 " cur %ld s:%c r:%c rev:%c in:%c ov:%c xd %d.\n",
                 (ihdlr ? "ihdlr" : "qcomm"), SCpnt->channel, SCpnt->target,
                 SCpnt->lun, SCpnt->serial_number, k, flushcount, n_ready,
-                SCpnt->request->sector, SCpnt->request->nr_sectors, cursec,
-                YESNO(s), YESNO(r), YESNO(rev), YESNO(input_only),
+                blk_rq_pos(SCpnt->request), blk_rq_sectors(SCpnt->request),
+		cursec, YESNO(s), YESNO(r), YESNO(rev), YESNO(input_only),
                 YESNO(overlap), cpp->xdir);
          }
 #endif
@@ -1799,7 +1801,7 @@ static irqreturn_t ihdlr(unsigned int j)
 
    if (linked_comm && SCpnt->device->queue_depth > 2
                                      && TLDEV(SCpnt->device->type))
-      flush_dev(SCpnt->device, SCpnt->request->sector, j, TRUE);
+      flush_dev(SCpnt->device, blk_rq_pos(SCpnt->request), j, TRUE);
 
    tstatus = status_byte(spp->target_status);
 
diff --git a/drivers/serial/8250.c b/drivers/serial/8250.c
index a0127e93ade0..fb867a9f55e9 100644
--- a/drivers/serial/8250.c
+++ b/drivers/serial/8250.c
@@ -287,6 +287,13 @@ static const struct serial8250_config uart_config[] = {
 		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
 		.flags		= UART_CAP_FIFO,
 	},
+	[PORT_AR7] = {
+		.name		= "AR7",
+		.fifo_size	= 16,
+		.tx_loadsz	= 16,
+		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00,
+		.flags		= UART_CAP_FIFO | UART_CAP_AFE,
+	},
 };
 
 #if defined (CONFIG_SERIAL_8250_AU1X00)
diff --git a/drivers/serial/8250_pci.c b/drivers/serial/8250_pci.c
index 938bc1b6c3fa..e371a9c15341 100644
--- a/drivers/serial/8250_pci.c
+++ b/drivers/serial/8250_pci.c
@@ -2776,6 +2776,9 @@ static struct pci_device_id serial_pci_tbl[] = {
 	{	PCI_VENDOR_ID_OXSEMI, 0x950a,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 		pbn_b0_2_1130000 },
+	{	PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_C950,
+		PCI_VENDOR_ID_OXSEMI, PCI_SUBDEVICE_ID_OXSEMI_C950, 0, 0,
+		pbn_b0_1_921600 },
 	{	PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_16PCI954,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 		pbn_b0_4_115200 },
diff --git a/drivers/serial/Kconfig b/drivers/serial/Kconfig
index 343e3a35b6a3..641e800ed693 100644
--- a/drivers/serial/Kconfig
+++ b/drivers/serial/Kconfig
@@ -833,6 +833,7 @@ config SERIAL_IMX
 	bool "IMX serial port support"
 	depends on ARM && (ARCH_IMX || ARCH_MXC)
 	select SERIAL_CORE
+	select RATIONAL
 	help
 	  If you have a machine based on a Motorola IMX CPU you
 	  can enable its onboard serial port by enabling this option.
@@ -1433,4 +1434,11 @@ config SPORT_BAUD_RATE
 	default 19200 if (SERIAL_SPORT_BAUD_RATE_19200)
 	default 9600 if (SERIAL_SPORT_BAUD_RATE_9600)
 
+config SERIAL_TIMBERDALE
+	tristate "Support for timberdale UART"
+	depends on MFD_TIMBERDALE
+	select SERIAL_CORE
+	---help---
+	Add support for UART controller on timberdale.
+
 endmenu
diff --git a/drivers/serial/Makefile b/drivers/serial/Makefile
index d438eb2a73de..45a8658f54d5 100644
--- a/drivers/serial/Makefile
+++ b/drivers/serial/Makefile
@@ -77,3 +77,4 @@ obj-$(CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL) += nwpserial.o
 obj-$(CONFIG_SERIAL_KS8695) += serial_ks8695.o
 obj-$(CONFIG_KGDB_SERIAL_CONSOLE) += kgdboc.o
 obj-$(CONFIG_SERIAL_QE) += ucc_uart.o
+obj-$(CONFIG_SERIAL_TIMBERDALE)	+= timbuart.o
diff --git a/drivers/serial/bfin_5xx.c b/drivers/serial/bfin_5xx.c
index d86123e03391..e2f6b1bfac98 100644
--- a/drivers/serial/bfin_5xx.c
+++ b/drivers/serial/bfin_5xx.c
@@ -330,6 +330,11 @@ static void bfin_serial_tx_chars(struct bfin_serial_port *uart)
 		/* Clear TFI bit */
 		UART_PUT_LSR(uart, TFI);
 #endif
+		/* Anomaly notes:
+		 *  05000215 -	we always clear ETBEI within last UART TX
+		 *		interrupt to end a string. It is always set
+		 *		when start a new tx.
+		 */
 		UART_CLEAR_IER(uart, ETBEI);
 		return;
 	}
@@ -415,6 +420,7 @@ static void bfin_serial_dma_tx_chars(struct bfin_serial_port *uart)
 	set_dma_start_addr(uart->tx_dma_channel, (unsigned long)(xmit->buf+xmit->tail));
 	set_dma_x_count(uart->tx_dma_channel, uart->tx_count);
 	set_dma_x_modify(uart->tx_dma_channel, 1);
+	SSYNC();
 	enable_dma(uart->tx_dma_channel);
 
 	UART_SET_IER(uart, ETBEI);
@@ -473,27 +479,41 @@ static void bfin_serial_dma_rx_chars(struct bfin_serial_port *uart)
 void bfin_serial_rx_dma_timeout(struct bfin_serial_port *uart)
 {
 	int x_pos, pos;
-	unsigned long flags;
 
-	spin_lock_irqsave(&uart->port.lock, flags);
+	dma_disable_irq(uart->rx_dma_channel);
+	spin_lock_bh(&uart->port.lock);
 
+	/* 2D DMA RX buffer ring is used. Because curr_y_count and
+	 * curr_x_count can't be read as an atomic operation,
+	 * curr_y_count should be read before curr_x_count. When
+	 * curr_x_count is read, curr_y_count may already indicate
+	 * next buffer line. But, the position calculated here is
+	 * still indicate the old line. The wrong position data may
+	 * be smaller than current buffer tail, which cause garbages
+	 * are received if it is not prohibit.
+	 */
 	uart->rx_dma_nrows = get_dma_curr_ycount(uart->rx_dma_channel);
 	x_pos = get_dma_curr_xcount(uart->rx_dma_channel);
 	uart->rx_dma_nrows = DMA_RX_YCOUNT - uart->rx_dma_nrows;
-	if (uart->rx_dma_nrows == DMA_RX_YCOUNT)
+	if (uart->rx_dma_nrows == DMA_RX_YCOUNT || x_pos == 0)
 		uart->rx_dma_nrows = 0;
 	x_pos = DMA_RX_XCOUNT - x_pos;
 	if (x_pos == DMA_RX_XCOUNT)
 		x_pos = 0;
 
 	pos = uart->rx_dma_nrows * DMA_RX_XCOUNT + x_pos;
-	if (pos != uart->rx_dma_buf.tail) {
+	/* Ignore receiving data if new position is in the same line of
+	 * current buffer tail and small.
+	 */
+	if (pos > uart->rx_dma_buf.tail ||
+		uart->rx_dma_nrows < (uart->rx_dma_buf.tail/DMA_RX_XCOUNT)) {
 		uart->rx_dma_buf.head = pos;
 		bfin_serial_dma_rx_chars(uart);
 		uart->rx_dma_buf.tail = uart->rx_dma_buf.head;
 	}
 
-	spin_unlock_irqrestore(&uart->port.lock, flags);
+	spin_unlock_bh(&uart->port.lock);
+	dma_enable_irq(uart->rx_dma_channel);
 
 	mod_timer(&(uart->rx_dma_timer), jiffies + DMA_RX_FLUSH_JIFFIES);
 }
@@ -514,6 +534,11 @@ static irqreturn_t bfin_serial_dma_tx_int(int irq, void *dev_id)
 	if (!(get_dma_curr_irqstat(uart->tx_dma_channel)&DMA_RUN)) {
 		disable_dma(uart->tx_dma_channel);
 		clear_dma_irqstat(uart->tx_dma_channel);
+		/* Anomaly notes:
+		 *  05000215 -	we always clear ETBEI within last UART TX
+		 *		interrupt to end a string. It is always set
+		 *		when start a new tx.
+		 */
 		UART_CLEAR_IER(uart, ETBEI);
 		xmit->tail = (xmit->tail + uart->tx_count) & (UART_XMIT_SIZE - 1);
 		uart->port.icount.tx += uart->tx_count;
@@ -532,11 +557,26 @@ static irqreturn_t bfin_serial_dma_rx_int(int irq, void *dev_id)
 {
 	struct bfin_serial_port *uart = dev_id;
 	unsigned short irqstat;
+	int x_pos, pos;
 
 	spin_lock(&uart->port.lock);
 	irqstat = get_dma_curr_irqstat(uart->rx_dma_channel);
 	clear_dma_irqstat(uart->rx_dma_channel);
-	bfin_serial_dma_rx_chars(uart);
+
+	uart->rx_dma_nrows = get_dma_curr_ycount(uart->rx_dma_channel);
+	x_pos = get_dma_curr_xcount(uart->rx_dma_channel);
+	uart->rx_dma_nrows = DMA_RX_YCOUNT - uart->rx_dma_nrows;
+	if (uart->rx_dma_nrows == DMA_RX_YCOUNT || x_pos == 0)
+		uart->rx_dma_nrows = 0;
+
+	pos = uart->rx_dma_nrows * DMA_RX_XCOUNT;
+	if (pos > uart->rx_dma_buf.tail ||
+		uart->rx_dma_nrows < (uart->rx_dma_buf.tail/DMA_RX_XCOUNT)) {
+		uart->rx_dma_buf.head = pos;
+		bfin_serial_dma_rx_chars(uart);
+		uart->rx_dma_buf.tail = uart->rx_dma_buf.head;
+	}
+
 	spin_unlock(&uart->port.lock);
 
 	return IRQ_HANDLED;
@@ -789,8 +829,16 @@ bfin_serial_set_termios(struct uart_port *port, struct ktermios *termios,
 			__func__);
 	}
 
-	if (termios->c_cflag & CSTOPB)
-		lcr |= STB;
+	/* Anomaly notes:
+	 *  05000231 -  STOP bit is always set to 1 whatever the user is set.
+	 */
+	if (termios->c_cflag & CSTOPB) {
+		if (ANOMALY_05000231)
+			printk(KERN_WARNING "STOP bits other than 1 is not "
+				"supported in case of anomaly 05000231.\n");
+		else
+			lcr |= STB;
+	}
 	if (termios->c_cflag & PARENB)
 		lcr |= PEN;
 	if (!(termios->c_cflag & PARODD))
@@ -940,6 +988,10 @@ static void bfin_serial_reset_irda(struct uart_port *port)
 }
 
 #ifdef CONFIG_CONSOLE_POLL
+/* Anomaly notes:
+ *  05000099 -  Because we only use THRE in poll_put and DR in poll_get,
+ *		losing other bits of UART_LSR is not a problem here.
+ */
 static void bfin_serial_poll_put_char(struct uart_port *port, unsigned char chr)
 {
 	struct bfin_serial_port *uart = (struct bfin_serial_port *)port;
@@ -1245,12 +1297,17 @@ static __init void early_serial_write(struct console *con, const char *s,
 	}
 }
 
+/*
+ * This should have a .setup or .early_setup in it, but then things get called
+ * without the command line options, and the baud rate gets messed up - so
+ * don't let the common infrastructure play with things. (see calls to setup
+ * & earlysetup in ./kernel/printk.c:register_console()
+ */
 static struct __initdata console bfin_early_serial_console = {
 	.name = "early_BFuart",
 	.write = early_serial_write,
 	.device = uart_console_device,
 	.flags = CON_PRINTBUFFER,
-	.setup = bfin_serial_console_setup,
 	.index = -1,
 	.data  = &bfin_serial_reg,
 };
diff --git a/drivers/serial/bfin_sport_uart.c b/drivers/serial/bfin_sport_uart.c
index 529c0ff7952c..34b4ae0fe760 100644
--- a/drivers/serial/bfin_sport_uart.c
+++ b/drivers/serial/bfin_sport_uart.c
@@ -101,15 +101,16 @@ static inline void tx_one_byte(struct sport_uart_port *up, unsigned int value)
 {
 	pr_debug("%s value:%x\n", __func__, value);
 	/* Place a Start and Stop bit */
-	__asm__ volatile (
-		"R2 = b#01111111100;\n\t"
-		"R3 = b#10000000001;\n\t"
-		"%0 <<= 2;\n\t"
-		"%0 = %0 & R2;\n\t"
-		"%0 = %0 | R3;\n\t"
-		:"=r"(value)
-		:"0"(value)
-		:"R2", "R3");
+	__asm__ __volatile__ (
+		"R2 = b#01111111100;"
+		"R3 = b#10000000001;"
+		"%0 <<= 2;"
+		"%0 = %0 & R2;"
+		"%0 = %0 | R3;"
+		: "=d"(value)
+		: "d"(value)
+		: "ASTAT", "R2", "R3"
+	);
 	pr_debug("%s value:%x\n", __func__, value);
 
 	SPORT_PUT_TX(up, value);
@@ -118,27 +119,30 @@ static inline void tx_one_byte(struct sport_uart_port *up, unsigned int value)
 static inline unsigned int rx_one_byte(struct sport_uart_port *up)
 {
 	unsigned int value, extract;
+	u32 tmp_mask1, tmp_mask2, tmp_shift, tmp;
 
 	value = SPORT_GET_RX32(up);
 	pr_debug("%s value:%x\n", __func__, value);
 
 	/* Extract 8 bits data */
-	__asm__ volatile (
-		"R5 = 0;\n\t"
-		"P0 = 8;\n\t"
-		"R1 = 0x1801(Z);\n\t"
-		"R3 = 0x0300(Z);\n\t"
-		"R4 = 0;\n\t"
-		"LSETUP(loop_s, loop_e) LC0 = P0;\nloop_s:\t"
-		"R2 = extract(%1, R1.L)(Z);\n\t"
-		"R2 <<= R4;\n\t"
-		"R5 = R5 | R2;\n\t"
-		"R1 = R1 - R3;\nloop_e:\t"
-		"R4 += 1;\n\t"
-		"%0 = R5;\n\t"
-		:"=r"(extract)
-		:"r"(value)
-		:"P0", "R1", "R2","R3","R4", "R5");
+	__asm__ __volatile__ (
+		"%[extr] = 0;"
+		"%[mask1] = 0x1801(Z);"
+		"%[mask2] = 0x0300(Z);"
+		"%[shift] = 0;"
+		"LSETUP(.Lloop_s, .Lloop_e) LC0 = %[lc];"
+		".Lloop_s:"
+		"%[tmp] = extract(%[val], %[mask1].L)(Z);"
+		"%[tmp] <<= %[shift];"
+		"%[extr] = %[extr] | %[tmp];"
+		"%[mask1] = %[mask1] - %[mask2];"
+		".Lloop_e:"
+		"%[shift] += 1;"
+		: [val]"=d"(value), [extr]"=d"(extract), [shift]"=d"(tmp_shift), [tmp]"=d"(tmp),
+		  [mask1]"=d"(tmp_mask1), [mask2]"=d"(tmp_mask2)
+		: "d"(value), [lc]"a"(8)
+		: "ASTAT", "LB0", "LC0", "LT0"
+	);
 
 	pr_debug("	extract:%x\n", extract);
 	return extract;
@@ -149,7 +153,7 @@ static int sport_uart_setup(struct sport_uart_port *up, int sclk, int baud_rate)
 	int tclkdiv, tfsdiv, rclkdiv;
 
 	/* Set TCR1 and TCR2 */
-	SPORT_PUT_TCR1(up, (LTFS | ITFS | TFSR | TLSBIT | ITCLK));
+	SPORT_PUT_TCR1(up, (LATFS | ITFS | TFSR | TLSBIT | ITCLK));
 	SPORT_PUT_TCR2(up, 10);
 	pr_debug("%s TCR1:%x, TCR2:%x\n", __func__, SPORT_GET_TCR1(up), SPORT_GET_TCR2(up));
 
@@ -419,7 +423,7 @@ static void sport_shutdown(struct uart_port *port)
 }
 
 static void sport_set_termios(struct uart_port *port,
-		struct termios *termios, struct termios *old)
+		struct ktermios *termios, struct ktermios *old)
 {
 	pr_debug("%s enter, c_cflag:%08x\n", __func__, termios->c_cflag);
 	uart_update_timeout(port, CS8 ,port->uartclk);
diff --git a/drivers/serial/icom.c b/drivers/serial/icom.c
index a461b3b2c72d..9f2891c2c4a2 100644
--- a/drivers/serial/icom.c
+++ b/drivers/serial/icom.c
@@ -137,7 +137,12 @@ static LIST_HEAD(icom_adapter_head);
 static spinlock_t icom_lock;
 
 #ifdef ICOM_TRACE
-static inline void trace(struct icom_port *, char *, unsigned long) {};
+static inline void trace(struct icom_port *icom_port, char *trace_pt,
+			unsigned long trace_data)
+{
+	dev_info(&icom_port->adapter->pci_dev->dev, ":%d:%s - %lx\n",
+	icom_port->port, trace_pt, trace_data);
+}
 #else
 static inline void trace(struct icom_port *icom_port, char *trace_pt, unsigned long trace_data) {};
 #endif
@@ -408,7 +413,7 @@ static void load_code(struct icom_port *icom_port)
 	release_firmware(fw);
 
 	/* Set Hardware level */
-	if ((icom_port->adapter->version | ADAPTER_V2) == ADAPTER_V2)
+	if (icom_port->adapter->version == ADAPTER_V2)
 		writeb(V2_HARDWARE, &(icom_port->dram->misc_flags));
 
 	/* Start the processor in Adapter */
@@ -861,7 +866,7 @@ static irqreturn_t icom_interrupt(int irq, void *dev_id)
 	/* find icom_port for this interrupt */
 	icom_adapter = (struct icom_adapter *) dev_id;
 
-	if ((icom_adapter->version | ADAPTER_V2) == ADAPTER_V2) {
+	if (icom_adapter->version == ADAPTER_V2) {
 		int_reg = icom_adapter->base_addr + 0x8024;
 
 		adapter_interrupts = readl(int_reg);
@@ -1647,15 +1652,6 @@ static void __exit icom_exit(void)
 module_init(icom_init);
 module_exit(icom_exit);
 
-#ifdef ICOM_TRACE
-static inline void trace(struct icom_port *icom_port, char *trace_pt,
-		  unsigned long trace_data)
-{
-	dev_info(&icom_port->adapter->pci_dev->dev, ":%d:%s - %lx\n",
-		 icom_port->port, trace_pt, trace_data);
-}
-#endif
-
 MODULE_AUTHOR("Michael Anderson <mjanders@us.ibm.com>");
 MODULE_DESCRIPTION("IBM iSeries Serial IOA driver");
 MODULE_SUPPORTED_DEVICE
diff --git a/drivers/serial/imx.c b/drivers/serial/imx.c
index 5f0be40dfdab..7b5d1de9cfe3 100644
--- a/drivers/serial/imx.c
+++ b/drivers/serial/imx.c
@@ -8,6 +8,9 @@
  *  Author: Sascha Hauer <sascha@saschahauer.de>
  *  Copyright (C) 2004 Pengutronix
  *
+ *  Copyright (C) 2009 emlix GmbH
+ *  Author: Fabian Godehardt (added IrDA support for iMX)
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -41,6 +44,8 @@
 #include <linux/serial_core.h>
 #include <linux/serial.h>
 #include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/rational.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
@@ -148,6 +153,7 @@
 #define  UCR4_DREN  	 (1<<0)  /* Recv data ready interrupt enable */
 #define  UFCR_RXTL_SHF   0       /* Receiver trigger level shift */
 #define  UFCR_RFDIV      (7<<7)  /* Reference freq divider mask */
+#define  UFCR_RFDIV_REG(x)	(((x) < 7 ? 6 - (x) : 6) << 7)
 #define  UFCR_TXTL_SHF   10      /* Transmitter trigger level shift */
 #define  USR1_PARITYERR  (1<<15) /* Parity error interrupt flag */
 #define  USR1_RTSS  	 (1<<14) /* RTS pin status */
@@ -211,10 +217,20 @@ struct imx_port {
 	struct timer_list	timer;
 	unsigned int		old_status;
 	int			txirq,rxirq,rtsirq;
-	int			have_rtscts:1;
+	unsigned int		have_rtscts:1;
+	unsigned int		use_irda:1;
+	unsigned int		irda_inv_rx:1;
+	unsigned int		irda_inv_tx:1;
+	unsigned short		trcv_delay; /* transceiver delay */
 	struct clk		*clk;
 };
 
+#ifdef CONFIG_IRDA
+#define USE_IRDA(sport)	((sport)->use_irda)
+#else
+#define USE_IRDA(sport)	(0)
+#endif
+
 /*
  * Handle any change of modem status signal since we were last called.
  */
@@ -268,6 +284,48 @@ static void imx_stop_tx(struct uart_port *port)
 	struct imx_port *sport = (struct imx_port *)port;
 	unsigned long temp;
 
+	if (USE_IRDA(sport)) {
+		/* half duplex - wait for end of transmission */
+		int n = 256;
+		while ((--n > 0) &&
+		      !(readl(sport->port.membase + USR2) & USR2_TXDC)) {
+			udelay(5);
+			barrier();
+		}
+		/*
+		 * irda transceiver - wait a bit more to avoid
+		 * cutoff, hardware dependent
+		 */
+		udelay(sport->trcv_delay);
+
+		/*
+		 * half duplex - reactivate receive mode,
+		 * flush receive pipe echo crap
+		 */
+		if (readl(sport->port.membase + USR2) & USR2_TXDC) {
+			temp = readl(sport->port.membase + UCR1);
+			temp &= ~(UCR1_TXMPTYEN | UCR1_TRDYEN);
+			writel(temp, sport->port.membase + UCR1);
+
+			temp = readl(sport->port.membase + UCR4);
+			temp &= ~(UCR4_TCEN);
+			writel(temp, sport->port.membase + UCR4);
+
+			while (readl(sport->port.membase + URXD0) &
+			       URXD_CHARRDY)
+				barrier();
+
+			temp = readl(sport->port.membase + UCR1);
+			temp |= UCR1_RRDYEN;
+			writel(temp, sport->port.membase + UCR1);
+
+			temp = readl(sport->port.membase + UCR4);
+			temp |= UCR4_DREN;
+			writel(temp, sport->port.membase + UCR4);
+		}
+		return;
+	}
+
 	temp = readl(sport->port.membase + UCR1);
 	writel(temp & ~UCR1_TXMPTYEN, sport->port.membase + UCR1);
 }
@@ -302,13 +360,15 @@ static inline void imx_transmit_buffer(struct imx_port *sport)
 		/* send xmit->buf[xmit->tail]
 		 * out the port here */
 		writel(xmit->buf[xmit->tail], sport->port.membase + URTX0);
-		xmit->tail = (xmit->tail + 1) &
-		         (UART_XMIT_SIZE - 1);
+		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
 		sport->port.icount.tx++;
 		if (uart_circ_empty(xmit))
 			break;
 	}
 
+	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+		uart_write_wakeup(&sport->port);
+
 	if (uart_circ_empty(xmit))
 		imx_stop_tx(&sport->port);
 }
@@ -321,9 +381,30 @@ static void imx_start_tx(struct uart_port *port)
 	struct imx_port *sport = (struct imx_port *)port;
 	unsigned long temp;
 
+	if (USE_IRDA(sport)) {
+		/* half duplex in IrDA mode; have to disable receive mode */
+		temp = readl(sport->port.membase + UCR4);
+		temp &= ~(UCR4_DREN);
+		writel(temp, sport->port.membase + UCR4);
+
+		temp = readl(sport->port.membase + UCR1);
+		temp &= ~(UCR1_RRDYEN);
+		writel(temp, sport->port.membase + UCR1);
+	}
+
 	temp = readl(sport->port.membase + UCR1);
 	writel(temp | UCR1_TXMPTYEN, sport->port.membase + UCR1);
 
+	if (USE_IRDA(sport)) {
+		temp = readl(sport->port.membase + UCR1);
+		temp |= UCR1_TRDYEN;
+		writel(temp, sport->port.membase + UCR1);
+
+		temp = readl(sport->port.membase + UCR4);
+		temp |= UCR4_TCEN;
+		writel(temp, sport->port.membase + UCR4);
+	}
+
 	if (readl(sport->port.membase + UTS) & UTS_TXEMPTY)
 		imx_transmit_buffer(sport);
 }
@@ -395,8 +476,7 @@ static irqreturn_t imx_rxint(int irq, void *dev_id)
 				continue;
 		}
 
-		if (uart_handle_sysrq_char
-		            (&sport->port, (unsigned char)rx))
+		if (uart_handle_sysrq_char(&sport->port, (unsigned char)rx))
 			continue;
 
 		if (rx & (URXD_PRERR | URXD_OVRRUN | URXD_FRMERR) ) {
@@ -471,26 +551,26 @@ static unsigned int imx_tx_empty(struct uart_port *port)
  */
 static unsigned int imx_get_mctrl(struct uart_port *port)
 {
-        struct imx_port *sport = (struct imx_port *)port;
-        unsigned int tmp = TIOCM_DSR | TIOCM_CAR;
+	struct imx_port *sport = (struct imx_port *)port;
+	unsigned int tmp = TIOCM_DSR | TIOCM_CAR;
 
-        if (readl(sport->port.membase + USR1) & USR1_RTSS)
-                tmp |= TIOCM_CTS;
+	if (readl(sport->port.membase + USR1) & USR1_RTSS)
+		tmp |= TIOCM_CTS;
 
-        if (readl(sport->port.membase + UCR2) & UCR2_CTS)
-                tmp |= TIOCM_RTS;
+	if (readl(sport->port.membase + UCR2) & UCR2_CTS)
+		tmp |= TIOCM_RTS;
 
-        return tmp;
+	return tmp;
 }
 
 static void imx_set_mctrl(struct uart_port *port, unsigned int mctrl)
 {
-        struct imx_port *sport = (struct imx_port *)port;
+	struct imx_port *sport = (struct imx_port *)port;
 	unsigned long temp;
 
 	temp = readl(sport->port.membase + UCR2) & ~UCR2_CTS;
 
-        if (mctrl & TIOCM_RTS)
+	if (mctrl & TIOCM_RTS)
 		temp |= UCR2_CTS;
 
 	writel(temp, sport->port.membase + UCR2);
@@ -534,12 +614,7 @@ static int imx_setup_ufcr(struct imx_port *sport, unsigned int mode)
 	if(!ufcr_rfdiv)
 		ufcr_rfdiv = 1;
 
-	if(ufcr_rfdiv >= 7)
-		ufcr_rfdiv = 6;
-	else
-		ufcr_rfdiv = 6 - ufcr_rfdiv;
-
-	val |= UFCR_RFDIV & (ufcr_rfdiv << 7);
+	val |= UFCR_RFDIV_REG(ufcr_rfdiv);
 
 	writel(val, sport->port.membase + UFCR);
 
@@ -558,8 +633,24 @@ static int imx_startup(struct uart_port *port)
 	 * requesting IRQs
 	 */
 	temp = readl(sport->port.membase + UCR4);
+
+	if (USE_IRDA(sport))
+		temp |= UCR4_IRSC;
+
 	writel(temp & ~UCR4_DREN, sport->port.membase + UCR4);
 
+	if (USE_IRDA(sport)) {
+		/* reset fifo's and state machines */
+		int i = 100;
+		temp = readl(sport->port.membase + UCR2);
+		temp &= ~UCR2_SRST;
+		writel(temp, sport->port.membase + UCR2);
+		while (!(readl(sport->port.membase + UCR2) & UCR2_SRST) &&
+		    (--i > 0)) {
+			udelay(1);
+		}
+	}
+
 	/*
 	 * Allocate the IRQ(s) i.MX1 has three interrupts whereas later
 	 * chips only have one interrupt.
@@ -575,12 +666,16 @@ static int imx_startup(struct uart_port *port)
 		if (retval)
 			goto error_out2;
 
-		retval = request_irq(sport->rtsirq, imx_rtsint,
-			     (sport->rtsirq < MAX_INTERNAL_IRQ) ? 0 :
-			       IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
-				DRIVER_NAME, sport);
-		if (retval)
-			goto error_out3;
+		/* do not use RTS IRQ on IrDA */
+		if (!USE_IRDA(sport)) {
+			retval = request_irq(sport->rtsirq, imx_rtsint,
+				     (sport->rtsirq < MAX_INTERNAL_IRQ) ? 0 :
+				       IRQF_TRIGGER_FALLING |
+				       IRQF_TRIGGER_RISING,
+					DRIVER_NAME, sport);
+			if (retval)
+				goto error_out3;
+		}
 	} else {
 		retval = request_irq(sport->port.irq, imx_int, 0,
 				DRIVER_NAME, sport);
@@ -597,18 +692,49 @@ static int imx_startup(struct uart_port *port)
 
 	temp = readl(sport->port.membase + UCR1);
 	temp |= UCR1_RRDYEN | UCR1_RTSDEN | UCR1_UARTEN;
+
+	if (USE_IRDA(sport)) {
+		temp |= UCR1_IREN;
+		temp &= ~(UCR1_RTSDEN);
+	}
+
 	writel(temp, sport->port.membase + UCR1);
 
 	temp = readl(sport->port.membase + UCR2);
 	temp |= (UCR2_RXEN | UCR2_TXEN);
 	writel(temp, sport->port.membase + UCR2);
 
+	if (USE_IRDA(sport)) {
+		/* clear RX-FIFO */
+		int i = 64;
+		while ((--i > 0) &&
+			(readl(sport->port.membase + URXD0) & URXD_CHARRDY)) {
+			barrier();
+		}
+	}
+
 #if defined CONFIG_ARCH_MX2 || defined CONFIG_ARCH_MX3
 	temp = readl(sport->port.membase + UCR3);
 	temp |= UCR3_RXDMUXSEL;
 	writel(temp, sport->port.membase + UCR3);
 #endif
 
+	if (USE_IRDA(sport)) {
+		temp = readl(sport->port.membase + UCR4);
+		if (sport->irda_inv_rx)
+			temp |= UCR4_INVR;
+		else
+			temp &= ~(UCR4_INVR);
+		writel(temp | UCR4_DREN, sport->port.membase + UCR4);
+
+		temp = readl(sport->port.membase + UCR3);
+		if (sport->irda_inv_tx)
+			temp |= UCR3_INVT;
+		else
+			temp &= ~(UCR3_INVT);
+		writel(temp, sport->port.membase + UCR3);
+	}
+
 	/*
 	 * Enable modem status interrupts
 	 */
@@ -616,6 +742,16 @@ static int imx_startup(struct uart_port *port)
 	imx_enable_ms(&sport->port);
 	spin_unlock_irqrestore(&sport->port.lock,flags);
 
+	if (USE_IRDA(sport)) {
+		struct imxuart_platform_data *pdata;
+		pdata = sport->port.dev->platform_data;
+		sport->irda_inv_rx = pdata->irda_inv_rx;
+		sport->irda_inv_tx = pdata->irda_inv_tx;
+		sport->trcv_delay = pdata->transceiver_delay;
+		if (pdata->irda_enable)
+			pdata->irda_enable(1);
+	}
+
 	return 0;
 
 error_out3:
@@ -633,6 +769,17 @@ static void imx_shutdown(struct uart_port *port)
 	struct imx_port *sport = (struct imx_port *)port;
 	unsigned long temp;
 
+	temp = readl(sport->port.membase + UCR2);
+	temp &= ~(UCR2_TXEN);
+	writel(temp, sport->port.membase + UCR2);
+
+	if (USE_IRDA(sport)) {
+		struct imxuart_platform_data *pdata;
+		pdata = sport->port.dev->platform_data;
+		if (pdata->irda_enable)
+			pdata->irda_enable(0);
+	}
+
 	/*
 	 * Stop our timer.
 	 */
@@ -642,7 +789,8 @@ static void imx_shutdown(struct uart_port *port)
 	 * Free the interrupts
 	 */
 	if (sport->txirq > 0) {
-		free_irq(sport->rtsirq, sport);
+		if (!USE_IRDA(sport))
+			free_irq(sport->rtsirq, sport);
 		free_irq(sport->txirq, sport);
 		free_irq(sport->rxirq, sport);
 	} else
@@ -654,6 +802,9 @@ static void imx_shutdown(struct uart_port *port)
 
 	temp = readl(sport->port.membase + UCR1);
 	temp &= ~(UCR1_TXMPTYEN | UCR1_RRDYEN | UCR1_RTSDEN | UCR1_UARTEN);
+	if (USE_IRDA(sport))
+		temp &= ~(UCR1_IREN);
+
 	writel(temp, sport->port.membase + UCR1);
 }
 
@@ -665,7 +816,9 @@ imx_set_termios(struct uart_port *port, struct ktermios *termios,
 	unsigned long flags;
 	unsigned int ucr2, old_ucr1, old_txrxen, baud, quot;
 	unsigned int old_csize = old ? old->c_cflag & CSIZE : CS8;
-	unsigned int div, num, denom, ufcr;
+	unsigned int div, ufcr;
+	unsigned long num, denom;
+	uint64_t tdiv64;
 
 	/*
 	 * If we don't support modem control lines, don't allow
@@ -761,38 +914,39 @@ imx_set_termios(struct uart_port *port, struct ktermios *termios,
 			sport->port.membase + UCR2);
 	old_txrxen &= (UCR2_TXEN | UCR2_RXEN);
 
-	div = sport->port.uartclk / (baud * 16);
-	if (div > 7)
-		div = 7;
-	if (!div)
+	if (USE_IRDA(sport)) {
+		/*
+		 * use maximum available submodule frequency to
+		 * avoid missing short pulses due to low sampling rate
+		 */
 		div = 1;
-
-	num = baud;
-	denom = port->uartclk / div / 16;
-
-	/* shift num and denom right until they fit into 16 bits */
-	while (num > 0x10000 || denom > 0x10000) {
-		num >>= 1;
-		denom >>= 1;
+	} else {
+		div = sport->port.uartclk / (baud * 16);
+		if (div > 7)
+			div = 7;
+		if (!div)
+			div = 1;
 	}
-	if (num > 0)
-		num -= 1;
-	if (denom > 0)
-		denom -= 1;
+
+	rational_best_approximation(16 * div * baud, sport->port.uartclk,
+		1 << 16, 1 << 16, &num, &denom);
+
+	tdiv64 = sport->port.uartclk;
+	tdiv64 *= num;
+	do_div(tdiv64, denom * 16 * div);
+	tty_encode_baud_rate(sport->port.info->port.tty,
+		(speed_t)tdiv64, (speed_t)tdiv64);
+
+	num -= 1;
+	denom -= 1;
+
+	ufcr = readl(sport->port.membase + UFCR);
+	ufcr = (ufcr & (~UFCR_RFDIV)) | UFCR_RFDIV_REG(div);
+	writel(ufcr, sport->port.membase + UFCR);
 
 	writel(num, sport->port.membase + UBIR);
 	writel(denom, sport->port.membase + UBMR);
 
-	if (div == 7)
-		div = 6; /* 6 in RFDIV means divide by 7 */
-	else
-		div = 6 - div;
-
-	ufcr = readl(sport->port.membase + UFCR);
-	ufcr = (ufcr & (~UFCR_RFDIV)) |
-	    (div << 7);
-	writel(ufcr, sport->port.membase + UFCR);
-
 #ifdef ONEMS
 	writel(sport->port.uartclk / div / 1000, sport->port.membase + ONEMS);
 #endif
@@ -1072,22 +1226,22 @@ static struct uart_driver imx_reg = {
 
 static int serial_imx_suspend(struct platform_device *dev, pm_message_t state)
 {
-        struct imx_port *sport = platform_get_drvdata(dev);
+	struct imx_port *sport = platform_get_drvdata(dev);
 
-        if (sport)
-                uart_suspend_port(&imx_reg, &sport->port);
+	if (sport)
+		uart_suspend_port(&imx_reg, &sport->port);
 
-        return 0;
+	return 0;
 }
 
 static int serial_imx_resume(struct platform_device *dev)
 {
-        struct imx_port *sport = platform_get_drvdata(dev);
+	struct imx_port *sport = platform_get_drvdata(dev);
 
-        if (sport)
-                uart_resume_port(&imx_reg, &sport->port);
+	if (sport)
+		uart_resume_port(&imx_reg, &sport->port);
 
-        return 0;
+	return 0;
 }
 
 static int serial_imx_probe(struct platform_device *pdev)
@@ -1143,19 +1297,29 @@ static int serial_imx_probe(struct platform_device *pdev)
 	imx_ports[pdev->id] = sport;
 
 	pdata = pdev->dev.platform_data;
-	if(pdata && (pdata->flags & IMXUART_HAVE_RTSCTS))
+	if (pdata && (pdata->flags & IMXUART_HAVE_RTSCTS))
 		sport->have_rtscts = 1;
 
+#ifdef CONFIG_IRDA
+	if (pdata && (pdata->flags & IMXUART_IRDA))
+		sport->use_irda = 1;
+#endif
+
 	if (pdata->init) {
 		ret = pdata->init(pdev);
 		if (ret)
 			goto clkput;
 	}
 
-	uart_add_one_port(&imx_reg, &sport->port);
+	ret = uart_add_one_port(&imx_reg, &sport->port);
+	if (ret)
+		goto deinit;
 	platform_set_drvdata(pdev, &sport->port);
 
 	return 0;
+deinit:
+	if (pdata->exit)
+		pdata->exit(pdev);
 clkput:
 	clk_put(sport->clk);
 	clk_disable(sport->clk);
@@ -1193,13 +1357,13 @@ static int serial_imx_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver serial_imx_driver = {
-        .probe          = serial_imx_probe,
-        .remove         = serial_imx_remove,
+	.probe		= serial_imx_probe,
+	.remove		= serial_imx_remove,
 
 	.suspend	= serial_imx_suspend,
 	.resume		= serial_imx_resume,
 	.driver		= {
-	        .name	= "imx-uart",
+		.name	= "imx-uart",
 		.owner	= THIS_MODULE,
 	},
 };
diff --git a/drivers/serial/jsm/jsm.h b/drivers/serial/jsm/jsm.h
index c0a3e2734e24..4e5f3bde0461 100644
--- a/drivers/serial/jsm/jsm.h
+++ b/drivers/serial/jsm/jsm.h
@@ -61,6 +61,7 @@ enum {
 	if ((DBG_##nlevel & jsm_debug))			\
 	dev_printk(KERN_##klevel, pdev->dev, fmt, ## args)
 
+#define	MAXLINES	256
 #define MAXPORTS	8
 #define MAX_STOPS_SENT	5
 
diff --git a/drivers/serial/jsm/jsm_tty.c b/drivers/serial/jsm/jsm_tty.c
index 31496dc0a0d1..107ce2e187b8 100644
--- a/drivers/serial/jsm/jsm_tty.c
+++ b/drivers/serial/jsm/jsm_tty.c
@@ -33,6 +33,8 @@
 
 #include "jsm.h"
 
+static DECLARE_BITMAP(linemap, MAXLINES);
+
 static void jsm_carrier(struct jsm_channel *ch);
 
 static inline int jsm_get_mstat(struct jsm_channel *ch)
@@ -433,6 +435,7 @@ int __devinit jsm_tty_init(struct jsm_board *brd)
 int __devinit jsm_uart_port_init(struct jsm_board *brd)
 {
 	int i;
+	unsigned int line;
 	struct jsm_channel *ch;
 
 	if (!brd)
@@ -459,9 +462,15 @@ int __devinit jsm_uart_port_init(struct jsm_board *brd)
 		brd->channels[i]->uart_port.membase = brd->re_map_membase;
 		brd->channels[i]->uart_port.fifosize = 16;
 		brd->channels[i]->uart_port.ops = &jsm_ops;
-		brd->channels[i]->uart_port.line = brd->channels[i]->ch_portnum + brd->boardnum * 2;
+		line = find_first_zero_bit(linemap, MAXLINES);
+		if (line >= MAXLINES) {
+			printk(KERN_INFO "jsm: linemap is full, added device failed\n");
+			continue;
+		} else
+			set_bit((int)line, linemap);
+		brd->channels[i]->uart_port.line = line;
 		if (uart_add_one_port (&jsm_uart_driver, &brd->channels[i]->uart_port))
-			printk(KERN_INFO "Added device failed\n");
+			printk(KERN_INFO "jsm: add device failed\n");
 		else
 			printk(KERN_INFO "Added device \n");
 	}
@@ -494,6 +503,7 @@ int jsm_remove_uart_port(struct jsm_board *brd)
 
 		ch = brd->channels[i];
 
+		clear_bit((int)(ch->uart_port.line), linemap);
 		uart_remove_one_port(&jsm_uart_driver, &brd->channels[i]->uart_port);
 	}
 
diff --git a/drivers/serial/sh-sci.c b/drivers/serial/sh-sci.c
index dbf5357a77b3..a4cf1079b312 100644
--- a/drivers/serial/sh-sci.c
+++ b/drivers/serial/sh-sci.c
@@ -47,12 +47,17 @@
 #include <linux/clk.h>
 #include <linux/ctype.h>
 #include <linux/err.h>
+#include <linux/list.h>
 
 #ifdef CONFIG_SUPERH
 #include <asm/clock.h>
 #include <asm/sh_bios.h>
 #endif
 
+#ifdef CONFIG_H8300
+#include <asm/gpio.h>
+#endif
+
 #include "sh-sci.h"
 
 struct sci_port {
@@ -75,14 +80,22 @@ struct sci_port {
 	int			break_flag;
 
 #ifdef CONFIG_HAVE_CLK
-	/* Port clock */
-	struct clk		*clk;
+	/* Interface clock */
+	struct clk		*iclk;
+	/* Data clock */
+	struct clk		*dclk;
 #endif
+	struct list_head	node;
 };
 
-#ifdef CONFIG_SERIAL_SH_SCI_CONSOLE
-static struct sci_port *serial_console_port;
+struct sh_sci_priv {
+	spinlock_t lock;
+	struct list_head ports;
+
+#ifdef CONFIG_HAVE_CLK
+	struct notifier_block clk_nb;
 #endif
+};
 
 /* Function prototypes */
 static void sci_stop_tx(struct uart_port *port);
@@ -138,9 +151,8 @@ static void sci_poll_put_char(struct uart_port *port, unsigned char c)
 		status = sci_in(port, SCxSR);
 	} while (!(status & SCxSR_TDxE(port)));
 
-	sci_in(port, SCxSR);            /* Dummy read */
-	sci_out(port, SCxSR, SCxSR_TDxE_CLEAR(port) & ~SCxSR_TEND(port));
 	sci_out(port, SCxTDR, c);
+	sci_out(port, SCxSR, SCxSR_TDxE_CLEAR(port) & ~SCxSR_TEND(port));
 }
 #endif /* CONFIG_CONSOLE_POLL || CONFIG_SERIAL_SH_SCI_CONSOLE */
 
@@ -159,12 +171,12 @@ static void h8300_sci_config(struct uart_port *port, unsigned int ctrl)
 		*mstpcrl &= ~mask;
 }
 
-static inline void h8300_sci_enable(struct uart_port *port)
+static void h8300_sci_enable(struct uart_port *port)
 {
 	h8300_sci_config(port, sci_enable);
 }
 
-static inline void h8300_sci_disable(struct uart_port *port)
+static void h8300_sci_disable(struct uart_port *port)
 {
 	h8300_sci_config(port, sci_disable);
 }
@@ -611,7 +623,7 @@ static inline int sci_handle_breaks(struct uart_port *port)
 	int copied = 0;
 	unsigned short status = sci_in(port, SCxSR);
 	struct tty_struct *tty = port->info->port.tty;
-	struct sci_port *s = &sci_ports[port->line];
+	struct sci_port *s = to_sci_port(port);
 
 	if (uart_handle_break(port))
 		return 0;
@@ -726,19 +738,43 @@ static irqreturn_t sci_mpxed_interrupt(int irq, void *ptr)
 static int sci_notifier(struct notifier_block *self,
 			unsigned long phase, void *p)
 {
-	int i;
+	struct sh_sci_priv *priv = container_of(self,
+						struct sh_sci_priv, clk_nb);
+	struct sci_port *sci_port;
+	unsigned long flags;
 
 	if ((phase == CPUFREQ_POSTCHANGE) ||
-	    (phase == CPUFREQ_RESUMECHANGE))
-		for (i = 0; i < SCI_NPORTS; i++) {
-			struct sci_port *s = &sci_ports[i];
-			s->port.uartclk = clk_get_rate(s->clk);
-		}
+	    (phase == CPUFREQ_RESUMECHANGE)) {
+		spin_lock_irqsave(&priv->lock, flags);
+		list_for_each_entry(sci_port, &priv->ports, node)
+			sci_port->port.uartclk = clk_get_rate(sci_port->dclk);
+
+		spin_unlock_irqrestore(&priv->lock, flags);
+	}
 
 	return NOTIFY_OK;
 }
 
-static struct notifier_block sci_nb = { &sci_notifier, NULL, 0 };
+static void sci_clk_enable(struct uart_port *port)
+{
+	struct sci_port *sci_port = to_sci_port(port);
+
+	clk_enable(sci_port->dclk);
+	sci_port->port.uartclk = clk_get_rate(sci_port->dclk);
+
+	if (sci_port->iclk)
+		clk_enable(sci_port->iclk);
+}
+
+static void sci_clk_disable(struct uart_port *port)
+{
+	struct sci_port *sci_port = to_sci_port(port);
+
+	if (sci_port->iclk)
+		clk_disable(sci_port->iclk);
+
+	clk_disable(sci_port->dclk);
+}
 #endif
 
 static int sci_request_irq(struct sci_port *port)
@@ -865,15 +901,11 @@ static void sci_break_ctl(struct uart_port *port, int break_state)
 
 static int sci_startup(struct uart_port *port)
 {
-	struct sci_port *s = &sci_ports[port->line];
+	struct sci_port *s = to_sci_port(port);
 
 	if (s->enable)
 		s->enable(port);
 
-#ifdef CONFIG_HAVE_CLK
-	s->clk = clk_get(NULL, "module_clk");
-#endif
-
 	sci_request_irq(s);
 	sci_start_tx(port);
 	sci_start_rx(port, 1);
@@ -883,7 +915,7 @@ static int sci_startup(struct uart_port *port)
 
 static void sci_shutdown(struct uart_port *port)
 {
-	struct sci_port *s = &sci_ports[port->line];
+	struct sci_port *s = to_sci_port(port);
 
 	sci_stop_rx(port);
 	sci_stop_tx(port);
@@ -891,11 +923,6 @@ static void sci_shutdown(struct uart_port *port)
 
 	if (s->disable)
 		s->disable(port);
-
-#ifdef CONFIG_HAVE_CLK
-	clk_put(s->clk);
-	s->clk = NULL;
-#endif
 }
 
 static void sci_set_termios(struct uart_port *port, struct ktermios *termios,
@@ -980,25 +1007,31 @@ static int sci_request_port(struct uart_port *port)
 
 static void sci_config_port(struct uart_port *port, int flags)
 {
-	struct sci_port *s = &sci_ports[port->line];
+	struct sci_port *s = to_sci_port(port);
 
 	port->type = s->type;
 
-	if (port->flags & UPF_IOREMAP && !port->membase) {
-#if defined(CONFIG_SUPERH64)
-		port->mapbase = onchip_remap(SCIF_ADDR_SH5, 1024, "SCIF");
-		port->membase = (void __iomem *)port->mapbase;
-#else
-		port->membase = ioremap_nocache(port->mapbase, 0x40);
-#endif
+	if (port->membase)
+		return;
 
-		dev_err(port->dev, "can't remap port#%d\n", port->line);
+	if (port->flags & UPF_IOREMAP) {
+		port->membase = ioremap_nocache(port->mapbase, 0x40);
+
+		if (IS_ERR(port->membase))
+			dev_err(port->dev, "can't remap port#%d\n", port->line);
+	} else {
+		/*
+		 * For the simple (and majority of) cases where we don't
+		 * need to do any remapping, just cast the cookie
+		 * directly.
+		 */
+		port->membase = (void __iomem *)port->mapbase;
 	}
 }
 
 static int sci_verify_port(struct uart_port *port, struct serial_struct *ser)
 {
-	struct sci_port *s = &sci_ports[port->line];
+	struct sci_port *s = to_sci_port(port);
 
 	if (ser->irq != s->irqs[SCIx_TXI_IRQ] || ser->irq > nr_irqs)
 		return -EINVAL;
@@ -1032,63 +1065,60 @@ static struct uart_ops sci_uart_ops = {
 #endif
 };
 
-static void __init sci_init_ports(void)
+static void __devinit sci_init_single(struct platform_device *dev,
+				      struct sci_port *sci_port,
+				      unsigned int index,
+				      struct plat_sci_port *p)
 {
-	static int first = 1;
-	int i;
-
-	if (!first)
-		return;
-
-	first = 0;
-
-	for (i = 0; i < SCI_NPORTS; i++) {
-		sci_ports[i].port.ops		= &sci_uart_ops;
-		sci_ports[i].port.iotype	= UPIO_MEM;
-		sci_ports[i].port.line		= i;
-		sci_ports[i].port.fifosize	= 1;
+	sci_port->port.ops	= &sci_uart_ops;
+	sci_port->port.iotype	= UPIO_MEM;
+	sci_port->port.line	= index;
+	sci_port->port.fifosize	= 1;
 
 #if defined(__H8300H__) || defined(__H8300S__)
 #ifdef __H8300S__
-		sci_ports[i].enable	= h8300_sci_enable;
-		sci_ports[i].disable	= h8300_sci_disable;
+	sci_port->enable	= h8300_sci_enable;
+	sci_port->disable	= h8300_sci_disable;
 #endif
-		sci_ports[i].port.uartclk = CONFIG_CPU_CLOCK;
+	sci_port->port.uartclk	= CONFIG_CPU_CLOCK;
 #elif defined(CONFIG_HAVE_CLK)
-		/*
-		 * XXX: We should use a proper SCI/SCIF clock
-		 */
-		{
-			struct clk *clk = clk_get(NULL, "module_clk");
-			sci_ports[i].port.uartclk = clk_get_rate(clk);
-			clk_put(clk);
-		}
+	sci_port->iclk		= p->clk ? clk_get(&dev->dev, p->clk) : NULL;
+	sci_port->dclk		= clk_get(&dev->dev, "peripheral_clk");
+	sci_port->enable	= sci_clk_enable;
+	sci_port->disable	= sci_clk_disable;
 #else
 #error "Need a valid uartclk"
 #endif
 
-		sci_ports[i].break_timer.data = (unsigned long)&sci_ports[i];
-		sci_ports[i].break_timer.function = sci_break_timer;
+	sci_port->break_timer.data = (unsigned long)sci_port;
+	sci_port->break_timer.function = sci_break_timer;
+	init_timer(&sci_port->break_timer);
 
-		init_timer(&sci_ports[i].break_timer);
-	}
-}
+	sci_port->port.mapbase	= p->mapbase;
+	sci_port->port.membase	= p->membase;
 
-int __init early_sci_setup(struct uart_port *port)
-{
-	if (unlikely(port->line > SCI_NPORTS))
-		return -ENODEV;
+	sci_port->port.irq	= p->irqs[SCIx_TXI_IRQ];
+	sci_port->port.flags	= p->flags;
+	sci_port->port.dev	= &dev->dev;
+	sci_port->type		= sci_port->port.type = p->type;
 
-	sci_init_ports();
+	memcpy(&sci_port->irqs, &p->irqs, sizeof(p->irqs));
 
-	sci_ports[port->line].port.membase	= port->membase;
-	sci_ports[port->line].port.mapbase	= port->mapbase;
-	sci_ports[port->line].port.type		= port->type;
-
-	return 0;
 }
 
 #ifdef CONFIG_SERIAL_SH_SCI_CONSOLE
+static struct tty_driver *serial_console_device(struct console *co, int *index)
+{
+	struct uart_driver *p = &sci_uart_driver;
+	*index = co->index;
+	return p->tty_driver;
+}
+
+static void serial_console_putchar(struct uart_port *port, int ch)
+{
+	sci_poll_put_char(port, ch);
+}
+
 /*
  *	Print a string to the serial port trying not to disturb
  *	any possible real use of the port...
@@ -1096,25 +1126,27 @@ int __init early_sci_setup(struct uart_port *port)
 static void serial_console_write(struct console *co, const char *s,
 				 unsigned count)
 {
-	struct uart_port *port = &serial_console_port->port;
+	struct uart_port *port = co->data;
+	struct sci_port *sci_port = to_sci_port(port);
 	unsigned short bits;
-	int i;
 
-	for (i = 0; i < count; i++) {
-		if (*s == 10)
-			sci_poll_put_char(port, '\r');
+	if (sci_port->enable)
+		sci_port->enable(port);
 
-		sci_poll_put_char(port, *s++);
-	}
+	uart_console_write(port, s, count, serial_console_putchar);
 
 	/* wait until fifo is empty and last bit has been transmitted */
 	bits = SCxSR_TDxE(port) | SCxSR_TEND(port);
 	while ((sci_in(port, SCxSR) & bits) != bits)
 		cpu_relax();
+
+	if (sci_port->disable);
+		sci_port->disable(port);
 }
 
 static int __init serial_console_setup(struct console *co, char *options)
 {
+	struct sci_port *sci_port;
 	struct uart_port *port;
 	int baud = 115200;
 	int bits = 8;
@@ -1130,8 +1162,9 @@ static int __init serial_console_setup(struct console *co, char *options)
 	if (co->index >= SCI_NPORTS)
 		co->index = 0;
 
-	serial_console_port = &sci_ports[co->index];
-	port = &serial_console_port->port;
+	sci_port = &sci_ports[co->index];
+	port = &sci_port->port;
+	co->data = port;
 
 	/*
 	 * Also need to check port->type, we don't actually have any
@@ -1141,21 +1174,11 @@ static int __init serial_console_setup(struct console *co, char *options)
 	 */
 	if (!port->type)
 		return -ENODEV;
-	if (!port->membase || !port->mapbase)
-		return -ENODEV;
 
-	port->type = serial_console_port->type;
+	sci_config_port(port, 0);
 
-#ifdef CONFIG_HAVE_CLK
-	if (!serial_console_port->clk)
-		serial_console_port->clk = clk_get(NULL, "module_clk");
-#endif
-
-	if (port->flags & UPF_IOREMAP)
-		sci_config_port(port, 0);
-
-	if (serial_console_port->enable)
-		serial_console_port->enable(port);
+	if (sci_port->enable)
+		sci_port->enable(port);
 
 	if (options)
 		uart_parse_options(options, &baud, &parity, &bits, &flow);
@@ -1166,22 +1189,21 @@ static int __init serial_console_setup(struct console *co, char *options)
 	if (ret == 0)
 		sci_stop_rx(port);
 #endif
+	/* TODO: disable clock */
 	return ret;
 }
 
 static struct console serial_console = {
 	.name		= "ttySC",
-	.device		= uart_console_device,
+	.device		= serial_console_device,
 	.write		= serial_console_write,
 	.setup		= serial_console_setup,
 	.flags		= CON_PRINTBUFFER,
 	.index		= -1,
-	.data		= &sci_uart_driver,
 };
 
 static int __init sci_console_init(void)
 {
-	sci_init_ports();
 	register_console(&serial_console);
 	return 0;
 }
@@ -1207,6 +1229,61 @@ static struct uart_driver sci_uart_driver = {
 	.cons		= SCI_CONSOLE,
 };
 
+
+static int sci_remove(struct platform_device *dev)
+{
+	struct sh_sci_priv *priv = platform_get_drvdata(dev);
+	struct sci_port *p;
+	unsigned long flags;
+
+#ifdef CONFIG_HAVE_CLK
+	cpufreq_unregister_notifier(&priv->clk_nb, CPUFREQ_TRANSITION_NOTIFIER);
+#endif
+
+	spin_lock_irqsave(&priv->lock, flags);
+	list_for_each_entry(p, &priv->ports, node)
+		uart_remove_one_port(&sci_uart_driver, &p->port);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	kfree(priv);
+	return 0;
+}
+
+static int __devinit sci_probe_single(struct platform_device *dev,
+				      unsigned int index,
+				      struct plat_sci_port *p,
+				      struct sci_port *sciport)
+{
+	struct sh_sci_priv *priv = platform_get_drvdata(dev);
+	unsigned long flags;
+	int ret;
+
+	/* Sanity check */
+	if (unlikely(index >= SCI_NPORTS)) {
+		dev_notice(&dev->dev, "Attempting to register port "
+			   "%d when only %d are available.\n",
+			   index+1, SCI_NPORTS);
+		dev_notice(&dev->dev, "Consider bumping "
+			   "CONFIG_SERIAL_SH_SCI_NR_UARTS!\n");
+		return 0;
+	}
+
+	sci_init_single(dev, sciport, index, p);
+
+	ret = uart_add_one_port(&sci_uart_driver, &sciport->port);
+	if (ret)
+		return ret;
+
+	INIT_LIST_HEAD(&sciport->node);
+
+	spin_lock_irqsave(&priv->lock, flags);
+	list_add(&sciport->node, &priv->ports);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
 /*
  * Register a set of serial devices attached to a platform device.  The
  * list is terminated with a zero flags entry, which means we expect
@@ -1216,57 +1293,34 @@ static struct uart_driver sci_uart_driver = {
 static int __devinit sci_probe(struct platform_device *dev)
 {
 	struct plat_sci_port *p = dev->dev.platform_data;
+	struct sh_sci_priv *priv;
 	int i, ret = -EINVAL;
 
-	for (i = 0; p && p->flags != 0; p++, i++) {
-		struct sci_port *sciport = &sci_ports[i];
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
 
-		/* Sanity check */
-		if (unlikely(i == SCI_NPORTS)) {
-			dev_notice(&dev->dev, "Attempting to register port "
-				   "%d when only %d are available.\n",
-				   i+1, SCI_NPORTS);
-			dev_notice(&dev->dev, "Consider bumping "
-				   "CONFIG_SERIAL_SH_SCI_NR_UARTS!\n");
-			break;
-		}
-
-		sciport->port.mapbase	= p->mapbase;
-
-		if (p->mapbase && !p->membase) {
-			if (p->flags & UPF_IOREMAP) {
-				p->membase = ioremap_nocache(p->mapbase, 0x40);
-				if (IS_ERR(p->membase)) {
-					ret = PTR_ERR(p->membase);
-					goto err_unreg;
-				}
-			} else {
-				/*
-				 * For the simple (and majority of) cases
-				 * where we don't need to do any remapping,
-				 * just cast the cookie directly.
-				 */
-				p->membase = (void __iomem *)p->mapbase;
-			}
-		}
-
-		sciport->port.membase	= p->membase;
-
-		sciport->port.irq	= p->irqs[SCIx_TXI_IRQ];
-		sciport->port.flags	= p->flags;
-		sciport->port.dev	= &dev->dev;
-
-		sciport->type		= sciport->port.type = p->type;
-
-		memcpy(&sciport->irqs, &p->irqs, sizeof(p->irqs));
-
-		uart_add_one_port(&sci_uart_driver, &sciport->port);
-	}
+	INIT_LIST_HEAD(&priv->ports);
+	spin_lock_init(&priv->lock);
+	platform_set_drvdata(dev, priv);
 
 #ifdef CONFIG_HAVE_CLK
-	cpufreq_register_notifier(&sci_nb, CPUFREQ_TRANSITION_NOTIFIER);
+	priv->clk_nb.notifier_call = sci_notifier;
+	cpufreq_register_notifier(&priv->clk_nb, CPUFREQ_TRANSITION_NOTIFIER);
 #endif
 
+	if (dev->id != -1) {
+		ret = sci_probe_single(dev, dev->id, p, &sci_ports[dev->id]);
+		if (ret)
+			goto err_unreg;
+	} else {
+		for (i = 0; p && p->flags != 0; p++, i++) {
+			ret = sci_probe_single(dev, i, p, &sci_ports[i]);
+			if (ret)
+				goto err_unreg;
+		}
+	}
+
 #ifdef CONFIG_SH_STANDARD_BIOS
 	sh_bios_gdb_detach();
 #endif
@@ -1274,50 +1328,36 @@ static int __devinit sci_probe(struct platform_device *dev)
 	return 0;
 
 err_unreg:
-	for (i = i - 1; i >= 0; i--)
-		uart_remove_one_port(&sci_uart_driver, &sci_ports[i].port);
-
+	sci_remove(dev);
 	return ret;
 }
 
-static int __devexit sci_remove(struct platform_device *dev)
-{
-	int i;
-
-#ifdef CONFIG_HAVE_CLK
-	cpufreq_unregister_notifier(&sci_nb, CPUFREQ_TRANSITION_NOTIFIER);
-#endif
-
-	for (i = 0; i < SCI_NPORTS; i++)
-		uart_remove_one_port(&sci_uart_driver, &sci_ports[i].port);
-
-	return 0;
-}
-
 static int sci_suspend(struct platform_device *dev, pm_message_t state)
 {
-	int i;
+	struct sh_sci_priv *priv = platform_get_drvdata(dev);
+	struct sci_port *p;
+	unsigned long flags;
 
-	for (i = 0; i < SCI_NPORTS; i++) {
-		struct sci_port *p = &sci_ports[i];
+	spin_lock_irqsave(&priv->lock, flags);
+	list_for_each_entry(p, &priv->ports, node)
+		uart_suspend_port(&sci_uart_driver, &p->port);
 
-		if (p->type != PORT_UNKNOWN && p->port.dev == &dev->dev)
-			uart_suspend_port(&sci_uart_driver, &p->port);
-	}
+	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
 }
 
 static int sci_resume(struct platform_device *dev)
 {
-	int i;
+	struct sh_sci_priv *priv = platform_get_drvdata(dev);
+	struct sci_port *p;
+	unsigned long flags;
 
-	for (i = 0; i < SCI_NPORTS; i++) {
-		struct sci_port *p = &sci_ports[i];
+	spin_lock_irqsave(&priv->lock, flags);
+	list_for_each_entry(p, &priv->ports, node)
+		uart_resume_port(&sci_uart_driver, &p->port);
 
-		if (p->type != PORT_UNKNOWN && p->port.dev == &dev->dev)
-			uart_resume_port(&sci_uart_driver, &p->port);
-	}
+	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
 }
@@ -1339,8 +1379,6 @@ static int __init sci_init(void)
 
 	printk(banner);
 
-	sci_init_ports();
-
 	ret = uart_register_driver(&sci_uart_driver);
 	if (likely(ret == 0)) {
 		ret = platform_driver_register(&sci_driver);
diff --git a/drivers/serial/sh-sci.h b/drivers/serial/sh-sci.h
index d0aa82d7fce0..38072c15b845 100644
--- a/drivers/serial/sh-sci.h
+++ b/drivers/serial/sh-sci.h
@@ -91,6 +91,9 @@
 # define SCSPTR5                0xa4050128
 # define SCIF_ORER              0x0001  /* overrun error bit */
 # define SCSCR_INIT(port)       0x0038  /* TIE=0,RIE=0,TE=1,RE=1,REIE=1 */
+#elif defined(CONFIG_CPU_SUBTYPE_SH7724)
+# define SCIF_ORER              0x0001  /* overrun error bit */
+# define SCSCR_INIT(port)       0x0038  /* TIE=0,RIE=0,TE=1,RE=1,REIE=1 */
 #elif defined(CONFIG_CPU_SUBTYPE_SH4_202)
 # define SCSPTR2 0xffe80020 /* 16 bit SCIF */
 # define SCIF_ORER 0x0001   /* overrun error bit */
@@ -314,7 +317,18 @@
     }									\
   }
 
-#define CPU_SCIF_FNS(name, scif_offset, scif_size)				\
+#ifdef CONFIG_H8300
+/* h8300 don't have SCIF */
+#define CPU_SCIF_FNS(name)						\
+  static inline unsigned int sci_##name##_in(struct uart_port *port)	\
+  {									\
+    return 0;								\
+  }									\
+  static inline void sci_##name##_out(struct uart_port *port, unsigned int value) \
+  {									\
+  }
+#else
+#define CPU_SCIF_FNS(name, scif_offset, scif_size)			\
   static inline unsigned int sci_##name##_in(struct uart_port *port)	\
   {									\
     SCI_IN(scif_size, scif_offset);					\
@@ -323,6 +337,7 @@
   {									\
     SCI_OUT(scif_size, scif_offset, value);				\
   }
+#endif
 
 #define CPU_SCI_FNS(name, sci_offset, sci_size)				\
   static inline unsigned int sci_##name##_in(struct uart_port* port)	\
@@ -360,8 +375,10 @@
 		 sh3_scif_offset, sh3_scif_size, sh4_scif_offset, sh4_scif_size, \
                  h8_sci_offset, h8_sci_size) \
   CPU_SCI_FNS(name, h8_sci_offset, h8_sci_size)
-#define SCIF_FNS(name, sh3_scif_offset, sh3_scif_size, sh4_scif_offset, sh4_scif_size)
-#elif defined(CONFIG_CPU_SUBTYPE_SH7723)
+#define SCIF_FNS(name, sh3_scif_offset, sh3_scif_size, sh4_scif_offset, sh4_scif_size) \
+  CPU_SCIF_FNS(name)
+#elif defined(CONFIG_CPU_SUBTYPE_SH7723) ||\
+      defined(CONFIG_CPU_SUBTYPE_SH7724)
         #define SCIx_FNS(name, sh4_scifa_offset, sh4_scifa_size, sh4_scif_offset, sh4_scif_size) \
                 CPU_SCIx_FNS(name, sh4_scifa_offset, sh4_scifa_size, sh4_scif_offset, sh4_scif_size)
         #define SCIF_FNS(name, sh4_scif_offset, sh4_scif_size) \
@@ -390,7 +407,8 @@ SCIF_FNS(SCFDR,  0x1c, 16)
 SCIF_FNS(SCxTDR, 0x20,  8)
 SCIF_FNS(SCxRDR, 0x24,  8)
 SCIF_FNS(SCLSR,  0x24, 16)
-#elif defined(CONFIG_CPU_SUBTYPE_SH7723)
+#elif defined(CONFIG_CPU_SUBTYPE_SH7723) ||\
+      defined(CONFIG_CPU_SUBTYPE_SH7724)
 SCIx_FNS(SCSMR,  0x00, 16, 0x00, 16)
 SCIx_FNS(SCBRR,  0x04,  8, 0x04,  8)
 SCIx_FNS(SCSCR,  0x08, 16, 0x08, 16)
@@ -604,10 +622,21 @@ static inline int sci_rxd_in(struct uart_port *port)
                 return ctrl_inb(SCSPTR5) & 0x0008 ? 1 : 0; /* SCIF5 */
         return 1;
 }
+#elif defined(CONFIG_CPU_SUBTYPE_SH7724)
+#  define SCFSR    0x0010
+#  define SCASSR   0x0014
+static inline int sci_rxd_in(struct uart_port *port)
+{
+	if (port->type == PORT_SCIF)
+		return ctrl_inw((port->mapbase + SCFSR))  & SCIF_BRK ? 1 : 0;
+	if (port->type == PORT_SCIFA)
+		return ctrl_inw((port->mapbase + SCASSR)) & SCIF_BRK ? 1 : 0;
+	return 1;
+}
 #elif defined(CONFIG_CPU_SUBTYPE_SH5_101) || defined(CONFIG_CPU_SUBTYPE_SH5_103)
 static inline int sci_rxd_in(struct uart_port *port)
 {
-         return sci_in(port, SCSPTR2)&0x0001 ? 1 : 0; /* SCIF */
+         return sci_in(port, SCSPTR)&0x0001 ? 1 : 0; /* SCIF */
 }
 #elif defined(__H8300H__) || defined(__H8300S__)
 static inline int sci_rxd_in(struct uart_port *port)
@@ -757,7 +786,8 @@ static inline int sci_rxd_in(struct uart_port *port)
       defined(CONFIG_CPU_SUBTYPE_SH7720) || \
       defined(CONFIG_CPU_SUBTYPE_SH7721)
 #define SCBRR_VALUE(bps, clk) (((clk*2)+16*bps)/(32*bps)-1)
-#elif defined(CONFIG_CPU_SUBTYPE_SH7723)
+#elif defined(CONFIG_CPU_SUBTYPE_SH7723) ||\
+      defined(CONFIG_CPU_SUBTYPE_SH7724)
 static inline int scbrr_calc(struct uart_port *port, int bps, int clk)
 {
 	if (port->type == PORT_SCIF)
diff --git a/drivers/serial/timbuart.c b/drivers/serial/timbuart.c
new file mode 100644
index 000000000000..ac9e5d5f742e
--- /dev/null
+++ b/drivers/serial/timbuart.c
@@ -0,0 +1,526 @@
+/*
+ * timbuart.c timberdale FPGA UART driver
+ * Copyright (c) 2009 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/* Supports:
+ * Timberdale FPGA UART
+ */
+
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/serial_core.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/ioport.h>
+
+#include "timbuart.h"
+
+struct timbuart_port {
+	struct uart_port	port;
+	struct tasklet_struct	tasklet;
+	int			usedma;
+	u8			last_ier;
+	struct platform_device  *dev;
+};
+
+static int baudrates[] = {9600, 19200, 38400, 57600, 115200, 230400, 460800,
+	921600, 1843200, 3250000};
+
+static void timbuart_mctrl_check(struct uart_port *port, u8 isr, u8 *ier);
+
+static irqreturn_t timbuart_handleinterrupt(int irq, void *devid);
+
+static void timbuart_stop_rx(struct uart_port *port)
+{
+	/* spin lock held by upper layer, disable all RX interrupts */
+	u8 ier = ioread8(port->membase + TIMBUART_IER) & ~RXFLAGS;
+	iowrite8(ier, port->membase + TIMBUART_IER);
+}
+
+static void timbuart_stop_tx(struct uart_port *port)
+{
+	/* spinlock held by upper layer, disable TX interrupt */
+	u8 ier = ioread8(port->membase + TIMBUART_IER) & ~TXBAE;
+	iowrite8(ier, port->membase + TIMBUART_IER);
+}
+
+static void timbuart_start_tx(struct uart_port *port)
+{
+	struct timbuart_port *uart =
+		container_of(port, struct timbuart_port, port);
+
+	/* do not transfer anything here -> fire off the tasklet */
+	tasklet_schedule(&uart->tasklet);
+}
+
+static void timbuart_flush_buffer(struct uart_port *port)
+{
+	u8 ctl = ioread8(port->membase + TIMBUART_CTRL) | TIMBUART_CTRL_FLSHTX;
+
+	iowrite8(ctl, port->membase + TIMBUART_CTRL);
+	iowrite8(TXBF, port->membase + TIMBUART_ISR);
+}
+
+static void timbuart_rx_chars(struct uart_port *port)
+{
+	struct tty_struct *tty = port->info->port.tty;
+
+	while (ioread8(port->membase + TIMBUART_ISR) & RXDP) {
+		u8 ch = ioread8(port->membase + TIMBUART_RXFIFO);
+		port->icount.rx++;
+		tty_insert_flip_char(tty, ch, TTY_NORMAL);
+	}
+
+	spin_unlock(&port->lock);
+	tty_flip_buffer_push(port->info->port.tty);
+	spin_lock(&port->lock);
+
+	dev_dbg(port->dev, "%s - total read %d bytes\n",
+		__func__, port->icount.rx);
+}
+
+static void timbuart_tx_chars(struct uart_port *port)
+{
+	struct circ_buf *xmit = &port->info->xmit;
+
+	while (!(ioread8(port->membase + TIMBUART_ISR) & TXBF) &&
+		!uart_circ_empty(xmit)) {
+		iowrite8(xmit->buf[xmit->tail],
+			port->membase + TIMBUART_TXFIFO);
+		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
+		port->icount.tx++;
+	}
+
+	dev_dbg(port->dev,
+		"%s - total written %d bytes, CTL: %x, RTS: %x, baud: %x\n",
+		 __func__,
+		port->icount.tx,
+		ioread8(port->membase + TIMBUART_CTRL),
+		port->mctrl & TIOCM_RTS,
+		ioread8(port->membase + TIMBUART_BAUDRATE));
+}
+
+static void timbuart_handle_tx_port(struct uart_port *port, u8 isr, u8 *ier)
+{
+	struct timbuart_port *uart =
+		container_of(port, struct timbuart_port, port);
+	struct circ_buf *xmit = &port->info->xmit;
+
+	if (uart_circ_empty(xmit) || uart_tx_stopped(port))
+		return;
+
+	if (port->x_char)
+		return;
+
+	if (isr & TXFLAGS) {
+		timbuart_tx_chars(port);
+		/* clear all TX interrupts */
+		iowrite8(TXFLAGS, port->membase + TIMBUART_ISR);
+
+		if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+			uart_write_wakeup(port);
+	} else
+		/* Re-enable any tx interrupt */
+		*ier |= uart->last_ier & TXFLAGS;
+
+	/* enable interrupts if there are chars in the transmit buffer,
+	 * Or if we delivered some bytes and want the almost empty interrupt
+	 * we wake up the upper layer later when we got the interrupt
+	 * to give it some time to go out...
+	 */
+	if (!uart_circ_empty(xmit))
+		*ier |= TXBAE;
+
+	dev_dbg(port->dev, "%s - leaving\n", __func__);
+}
+
+void timbuart_handle_rx_port(struct uart_port *port, u8 isr, u8 *ier)
+{
+	if (isr & RXFLAGS) {
+		/* Some RX status is set */
+		if (isr & RXBF) {
+			u8 ctl = ioread8(port->membase + TIMBUART_CTRL) |
+				TIMBUART_CTRL_FLSHRX;
+			iowrite8(ctl, port->membase + TIMBUART_CTRL);
+			port->icount.overrun++;
+		} else if (isr & (RXDP))
+			timbuart_rx_chars(port);
+
+		/* ack all RX interrupts */
+		iowrite8(RXFLAGS, port->membase + TIMBUART_ISR);
+	}
+
+	/* always have the RX interrupts enabled */
+	*ier |= RXBAF | RXBF | RXTT;
+
+	dev_dbg(port->dev, "%s - leaving\n", __func__);
+}
+
+void timbuart_tasklet(unsigned long arg)
+{
+	struct timbuart_port *uart = (struct timbuart_port *)arg;
+	u8 isr, ier = 0;
+
+	spin_lock(&uart->port.lock);
+
+	isr = ioread8(uart->port.membase + TIMBUART_ISR);
+	dev_dbg(uart->port.dev, "%s ISR: %x\n", __func__, isr);
+
+	if (!uart->usedma)
+		timbuart_handle_tx_port(&uart->port, isr, &ier);
+
+	timbuart_mctrl_check(&uart->port, isr, &ier);
+
+	if (!uart->usedma)
+		timbuart_handle_rx_port(&uart->port, isr, &ier);
+
+	iowrite8(ier, uart->port.membase + TIMBUART_IER);
+
+	spin_unlock(&uart->port.lock);
+	dev_dbg(uart->port.dev, "%s leaving\n", __func__);
+}
+
+static unsigned int timbuart_tx_empty(struct uart_port *port)
+{
+	u8 isr = ioread8(port->membase + TIMBUART_ISR);
+
+	return (isr & TXBAE) ? TIOCSER_TEMT : 0;
+}
+
+static unsigned int timbuart_get_mctrl(struct uart_port *port)
+{
+	u8 cts = ioread8(port->membase + TIMBUART_CTRL);
+	dev_dbg(port->dev, "%s - cts %x\n", __func__, cts);
+
+	if (cts & TIMBUART_CTRL_CTS)
+		return TIOCM_CTS | TIOCM_DSR | TIOCM_CAR;
+	else
+		return TIOCM_DSR | TIOCM_CAR;
+}
+
+static void timbuart_set_mctrl(struct uart_port *port, unsigned int mctrl)
+{
+	dev_dbg(port->dev, "%s - %x\n", __func__, mctrl);
+
+	if (mctrl & TIOCM_RTS)
+		iowrite8(TIMBUART_CTRL_RTS, port->membase + TIMBUART_CTRL);
+	else
+		iowrite8(TIMBUART_CTRL_RTS, port->membase + TIMBUART_CTRL);
+}
+
+static void timbuart_mctrl_check(struct uart_port *port, u8 isr, u8 *ier)
+{
+	unsigned int cts;
+
+	if (isr & CTS_DELTA) {
+		/* ack */
+		iowrite8(CTS_DELTA, port->membase + TIMBUART_ISR);
+		cts = timbuart_get_mctrl(port);
+		uart_handle_cts_change(port, cts & TIOCM_CTS);
+		wake_up_interruptible(&port->info->delta_msr_wait);
+	}
+
+	*ier |= CTS_DELTA;
+}
+
+static void timbuart_enable_ms(struct uart_port *port)
+{
+	/* N/A */
+}
+
+static void timbuart_break_ctl(struct uart_port *port, int ctl)
+{
+	/* N/A */
+}
+
+static int timbuart_startup(struct uart_port *port)
+{
+	struct timbuart_port *uart =
+		container_of(port, struct timbuart_port, port);
+
+	dev_dbg(port->dev, "%s\n", __func__);
+
+	iowrite8(TIMBUART_CTRL_FLSHRX, port->membase + TIMBUART_CTRL);
+	iowrite8(0xff, port->membase + TIMBUART_ISR);
+	/* Enable all but TX interrupts */
+	iowrite8(RXBAF | RXBF | RXTT | CTS_DELTA,
+		port->membase + TIMBUART_IER);
+
+	return request_irq(port->irq, timbuart_handleinterrupt, IRQF_SHARED,
+		"timb-uart", uart);
+}
+
+static void timbuart_shutdown(struct uart_port *port)
+{
+	struct timbuart_port *uart =
+		container_of(port, struct timbuart_port, port);
+	dev_dbg(port->dev, "%s\n", __func__);
+	free_irq(port->irq, uart);
+	iowrite8(0, port->membase + TIMBUART_IER);
+}
+
+static int get_bindex(int baud)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(baudrates); i++)
+		if (baud <= baudrates[i])
+			return i;
+
+	return -1;
+}
+
+static void timbuart_set_termios(struct uart_port *port,
+	struct ktermios *termios,
+	struct ktermios *old)
+{
+	unsigned int baud;
+	short bindex;
+	unsigned long flags;
+
+	baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk / 16);
+	bindex = get_bindex(baud);
+	dev_dbg(port->dev, "%s - bindex %d\n", __func__, bindex);
+
+	if (bindex < 0)
+		bindex = 0;
+	baud = baudrates[bindex];
+
+	/* The serial layer calls into this once with old = NULL when setting
+	   up initially */
+	if (old)
+		tty_termios_copy_hw(termios, old);
+	tty_termios_encode_baud_rate(termios, baud, baud);
+
+	spin_lock_irqsave(&port->lock, flags);
+	iowrite8((u8)bindex, port->membase + TIMBUART_BAUDRATE);
+	uart_update_timeout(port, termios->c_cflag, baud);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static const char *timbuart_type(struct uart_port *port)
+{
+	return port->type == PORT_UNKNOWN ? "timbuart" : NULL;
+}
+
+/* We do not request/release mappings of the registers here,
+ * currently it's done in the proble function.
+ */
+static void timbuart_release_port(struct uart_port *port)
+{
+	struct platform_device *pdev = to_platform_device(port->dev);
+	int size =
+		resource_size(platform_get_resource(pdev, IORESOURCE_MEM, 0));
+
+	if (port->flags & UPF_IOREMAP) {
+		iounmap(port->membase);
+		port->membase = NULL;
+	}
+
+	release_mem_region(port->mapbase, size);
+}
+
+static int timbuart_request_port(struct uart_port *port)
+{
+	struct platform_device *pdev = to_platform_device(port->dev);
+	int size =
+		resource_size(platform_get_resource(pdev, IORESOURCE_MEM, 0));
+
+	if (!request_mem_region(port->mapbase, size, "timb-uart"))
+		return -EBUSY;
+
+	if (port->flags & UPF_IOREMAP) {
+		port->membase = ioremap(port->mapbase, size);
+		if (port->membase == NULL) {
+			release_mem_region(port->mapbase, size);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static irqreturn_t timbuart_handleinterrupt(int irq, void *devid)
+{
+	struct timbuart_port *uart = (struct timbuart_port *)devid;
+
+	if (ioread8(uart->port.membase + TIMBUART_IPR)) {
+		uart->last_ier = ioread8(uart->port.membase + TIMBUART_IER);
+
+		/* disable interrupts, the tasklet enables them again */
+		iowrite8(0, uart->port.membase + TIMBUART_IER);
+
+		/* fire off bottom half */
+		tasklet_schedule(&uart->tasklet);
+
+		return IRQ_HANDLED;
+	} else
+		return IRQ_NONE;
+}
+
+/*
+ * Configure/autoconfigure the port.
+ */
+static void timbuart_config_port(struct uart_port *port, int flags)
+{
+	if (flags & UART_CONFIG_TYPE) {
+		port->type = PORT_TIMBUART;
+		timbuart_request_port(port);
+	}
+}
+
+static int timbuart_verify_port(struct uart_port *port,
+	struct serial_struct *ser)
+{
+	/* we don't want the core code to modify any port params */
+	return -EINVAL;
+}
+
+static struct uart_ops timbuart_ops = {
+	.tx_empty = timbuart_tx_empty,
+	.set_mctrl = timbuart_set_mctrl,
+	.get_mctrl = timbuart_get_mctrl,
+	.stop_tx = timbuart_stop_tx,
+	.start_tx = timbuart_start_tx,
+	.flush_buffer = timbuart_flush_buffer,
+	.stop_rx = timbuart_stop_rx,
+	.enable_ms = timbuart_enable_ms,
+	.break_ctl = timbuart_break_ctl,
+	.startup = timbuart_startup,
+	.shutdown = timbuart_shutdown,
+	.set_termios = timbuart_set_termios,
+	.type = timbuart_type,
+	.release_port = timbuart_release_port,
+	.request_port = timbuart_request_port,
+	.config_port = timbuart_config_port,
+	.verify_port = timbuart_verify_port
+};
+
+static struct uart_driver timbuart_driver = {
+	.owner = THIS_MODULE,
+	.driver_name = "timberdale_uart",
+	.dev_name = "ttyTU",
+	.major = TIMBUART_MAJOR,
+	.minor = TIMBUART_MINOR,
+	.nr = 1
+};
+
+static int timbuart_probe(struct platform_device *dev)
+{
+	int err;
+	struct timbuart_port *uart;
+	struct resource *iomem;
+
+	dev_dbg(&dev->dev, "%s\n", __func__);
+
+	uart = kzalloc(sizeof(*uart), GFP_KERNEL);
+	if (!uart) {
+		err = -EINVAL;
+		goto err_mem;
+	}
+
+	uart->usedma = 0;
+
+	uart->port.uartclk = 3250000 * 16;
+	uart->port.fifosize  = TIMBUART_FIFO_SIZE;
+	uart->port.regshift  = 2;
+	uart->port.iotype  = UPIO_MEM;
+	uart->port.ops = &timbuart_ops;
+	uart->port.irq = 0;
+	uart->port.flags = UPF_BOOT_AUTOCONF | UPF_IOREMAP;
+	uart->port.line  = 0;
+	uart->port.dev	= &dev->dev;
+
+	iomem = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	if (!iomem) {
+		err = -ENOMEM;
+		goto err_register;
+	}
+	uart->port.mapbase = iomem->start;
+	uart->port.membase = NULL;
+
+	uart->port.irq = platform_get_irq(dev, 0);
+	if (uart->port.irq < 0) {
+		err = -EINVAL;
+		goto err_register;
+	}
+
+	tasklet_init(&uart->tasklet, timbuart_tasklet, (unsigned long)uart);
+
+	err = uart_register_driver(&timbuart_driver);
+	if (err)
+		goto err_register;
+
+	err = uart_add_one_port(&timbuart_driver, &uart->port);
+	if (err)
+		goto err_add_port;
+
+	platform_set_drvdata(dev, uart);
+
+	return 0;
+
+err_add_port:
+	uart_unregister_driver(&timbuart_driver);
+err_register:
+	kfree(uart);
+err_mem:
+	printk(KERN_ERR "timberdale: Failed to register Timberdale UART: %d\n",
+		err);
+
+	return err;
+}
+
+static int timbuart_remove(struct platform_device *dev)
+{
+	struct timbuart_port *uart = platform_get_drvdata(dev);
+
+	tasklet_kill(&uart->tasklet);
+	uart_remove_one_port(&timbuart_driver, &uart->port);
+	uart_unregister_driver(&timbuart_driver);
+	kfree(uart);
+
+	return 0;
+}
+
+static struct platform_driver timbuart_platform_driver = {
+	.driver = {
+		.name	= "timb-uart",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= timbuart_probe,
+	.remove		= timbuart_remove,
+};
+
+/*--------------------------------------------------------------------------*/
+
+static int __init timbuart_init(void)
+{
+	return platform_driver_register(&timbuart_platform_driver);
+}
+
+static void __exit timbuart_exit(void)
+{
+	platform_driver_unregister(&timbuart_platform_driver);
+}
+
+module_init(timbuart_init);
+module_exit(timbuart_exit);
+
+MODULE_DESCRIPTION("Timberdale UART driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:timb-uart");
+
diff --git a/drivers/serial/timbuart.h b/drivers/serial/timbuart.h
new file mode 100644
index 000000000000..7e566766bc43
--- /dev/null
+++ b/drivers/serial/timbuart.h
@@ -0,0 +1,58 @@
+/*
+ * timbuart.c timberdale FPGA GPIO driver
+ * Copyright (c) 2009 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/* Supports:
+ * Timberdale FPGA UART
+ */
+
+#ifndef _TIMBUART_H
+#define _TIMBUART_H
+
+#define TIMBUART_FIFO_SIZE	2048
+
+#define TIMBUART_RXFIFO		0x08
+#define TIMBUART_TXFIFO		0x0c
+#define TIMBUART_IER		0x10
+#define TIMBUART_IPR		0x14
+#define TIMBUART_ISR		0x18
+#define TIMBUART_CTRL		0x1c
+#define TIMBUART_BAUDRATE	0x20
+
+#define TIMBUART_CTRL_RTS	0x01
+#define TIMBUART_CTRL_CTS	0x02
+#define TIMBUART_CTRL_FLSHTX	0x40
+#define TIMBUART_CTRL_FLSHRX	0x80
+
+#define TXBF		0x01
+#define TXBAE		0x02
+#define CTS_DELTA	0x04
+#define RXDP		0x08
+#define RXBAF		0x10
+#define RXBF		0x20
+#define RXTT		0x40
+#define RXBNAE		0x80
+#define TXBE		0x100
+
+#define RXFLAGS (RXDP | RXBAF | RXBF | RXTT | RXBNAE)
+#define TXFLAGS (TXBF | TXBAE)
+
+#define TIMBUART_MAJOR 204
+#define TIMBUART_MINOR 192
+
+#endif /* _TIMBUART_H */
+
diff --git a/drivers/sh/intc.c b/drivers/sh/intc.c
index 12d13d99b6f0..d687a9b93d03 100644
--- a/drivers/sh/intc.c
+++ b/drivers/sh/intc.c
@@ -24,6 +24,7 @@
 #include <linux/sh_intc.h>
 #include <linux/sysdev.h>
 #include <linux/list.h>
+#include <linux/topology.h>
 
 #define _INTC_MK(fn, mode, addr_e, addr_d, width, shift) \
 	((shift) | ((width) << 5) | ((fn) << 9) | ((mode) << 13) | \
@@ -770,11 +771,19 @@ void __init register_intc_controller(struct intc_desc *desc)
 	/* register the vectors one by one */
 	for (i = 0; i < desc->nr_vectors; i++) {
 		struct intc_vect *vect = desc->vectors + i;
+		unsigned int irq = evt2irq(vect->vect);
+		struct irq_desc *irq_desc;
 
 		if (!vect->enum_id)
 			continue;
 
-		intc_register_irq(desc, d, vect->enum_id, evt2irq(vect->vect));
+		irq_desc = irq_to_desc_alloc_node(irq, numa_node_id());
+		if (unlikely(!irq_desc)) {
+			printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+			continue;
+		}
+
+		intc_register_irq(desc, d, vect->enum_id, irq);
 	}
 }
 
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 7a1164dd1d37..ddeb69192537 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -16,7 +16,8 @@
  *	v0.9  - thorough cleaning, URBification, almost a rewrite
  *	v0.10 - some more cleanups
  *	v0.11 - fixed flow control, read error doesn't stop reads
- *	v0.12 - added TIOCM ioctls, added break handling, made struct acm kmalloced
+ *	v0.12 - added TIOCM ioctls, added break handling, made struct acm
+ *		kmalloced
  *	v0.13 - added termios, added hangup
  *	v0.14 - sized down struct acm
  *	v0.15 - fixed flow control again - characters could be lost
@@ -62,7 +63,7 @@
 #include <linux/tty_flip.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/usb.h>
 #include <linux/usb/cdc.h>
 #include <asm/byteorder.h>
@@ -87,7 +88,10 @@ static struct acm *acm_table[ACM_TTY_MINORS];
 
 static DEFINE_MUTEX(open_mutex);
 
-#define ACM_READY(acm)	(acm && acm->dev && acm->used)
+#define ACM_READY(acm)	(acm && acm->dev && acm->port.count)
+
+static const struct tty_port_operations acm_port_ops = {
+};
 
 #ifdef VERBOSE_DEBUG
 #define verbose	1
@@ -99,13 +103,15 @@ static DEFINE_MUTEX(open_mutex);
  * Functions for ACM control messages.
  */
 
-static int acm_ctrl_msg(struct acm *acm, int request, int value, void *buf, int len)
+static int acm_ctrl_msg(struct acm *acm, int request, int value,
+							void *buf, int len)
 {
 	int retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
 		request, USB_RT_ACM, value,
 		acm->control->altsetting[0].desc.bInterfaceNumber,
 		buf, len, 5000);
-	dbg("acm_control_msg: rq: 0x%02x val: %#x len: %#x result: %d", request, value, len, retval);
+	dbg("acm_control_msg: rq: 0x%02x val: %#x len: %#x result: %d",
+						request, value, len, retval);
 	return retval < 0 ? retval : 0;
 }
 
@@ -150,9 +156,8 @@ static int acm_wb_is_avail(struct acm *acm)
 
 	n = ACM_NW;
 	spin_lock_irqsave(&acm->write_lock, flags);
-	for (i = 0; i < ACM_NW; i++) {
+	for (i = 0; i < ACM_NW; i++)
 		n -= acm->wb[i].use;
-	}
 	spin_unlock_irqrestore(&acm->write_lock, flags);
 	return n;
 }
@@ -183,7 +188,8 @@ static int acm_start_wb(struct acm *acm, struct acm_wb *wb)
 	wb->urb->transfer_buffer_length = wb->len;
 	wb->urb->dev = acm->dev;
 
-	if ((rc = usb_submit_urb(wb->urb, GFP_ATOMIC)) < 0) {
+	rc = usb_submit_urb(wb->urb, GFP_ATOMIC);
+	if (rc < 0) {
 		dbg("usb_submit_urb(write bulk) failed: %d", rc);
 		acm_write_done(acm, wb);
 	}
@@ -262,6 +268,7 @@ static void acm_ctrl_irq(struct urb *urb)
 {
 	struct acm *acm = urb->context;
 	struct usb_cdc_notification *dr = urb->transfer_buffer;
+	struct tty_struct *tty;
 	unsigned char *data;
 	int newctrl;
 	int retval;
@@ -287,40 +294,45 @@ static void acm_ctrl_irq(struct urb *urb)
 
 	data = (unsigned char *)(dr + 1);
 	switch (dr->bNotificationType) {
+	case USB_CDC_NOTIFY_NETWORK_CONNECTION:
+		dbg("%s network", dr->wValue ?
+					"connected to" : "disconnected from");
+		break;
 
-		case USB_CDC_NOTIFY_NETWORK_CONNECTION:
+	case USB_CDC_NOTIFY_SERIAL_STATE:
+		tty = tty_port_tty_get(&acm->port);
+		newctrl = get_unaligned_le16(data);
 
-			dbg("%s network", dr->wValue ? "connected to" : "disconnected from");
-			break;
-
-		case USB_CDC_NOTIFY_SERIAL_STATE:
-
-			newctrl = get_unaligned_le16(data);
-
-			if (acm->tty && !acm->clocal && (acm->ctrlin & ~newctrl & ACM_CTRL_DCD)) {
+		if (tty) {
+			if (!acm->clocal &&
+				(acm->ctrlin & ~newctrl & ACM_CTRL_DCD)) {
 				dbg("calling hangup");
-				tty_hangup(acm->tty);
+				tty_hangup(tty);
 			}
+			tty_kref_put(tty);
+		}
 
-			acm->ctrlin = newctrl;
-
-			dbg("input control lines: dcd%c dsr%c break%c ring%c framing%c parity%c overrun%c",
-				acm->ctrlin & ACM_CTRL_DCD ? '+' : '-',	acm->ctrlin & ACM_CTRL_DSR ? '+' : '-',
-				acm->ctrlin & ACM_CTRL_BRK ? '+' : '-',	acm->ctrlin & ACM_CTRL_RI  ? '+' : '-',
-				acm->ctrlin & ACM_CTRL_FRAMING ? '+' : '-',	acm->ctrlin & ACM_CTRL_PARITY ? '+' : '-',
-				acm->ctrlin & ACM_CTRL_OVERRUN ? '+' : '-');
+		acm->ctrlin = newctrl;
 
+		dbg("input control lines: dcd%c dsr%c break%c ring%c framing%c parity%c overrun%c",
+			acm->ctrlin & ACM_CTRL_DCD ? '+' : '-',
+			acm->ctrlin & ACM_CTRL_DSR ? '+' : '-',
+			acm->ctrlin & ACM_CTRL_BRK ? '+' : '-',
+			acm->ctrlin & ACM_CTRL_RI  ? '+' : '-',
+			acm->ctrlin & ACM_CTRL_FRAMING ? '+' : '-',
+			acm->ctrlin & ACM_CTRL_PARITY ? '+' : '-',
+			acm->ctrlin & ACM_CTRL_OVERRUN ? '+' : '-');
 			break;
 
-		default:
-			dbg("unknown notification %d received: index %d len %d data0 %d data1 %d",
-				dr->bNotificationType, dr->wIndex,
-				dr->wLength, data[0], data[1]);
-			break;
+	default:
+		dbg("unknown notification %d received: index %d len %d data0 %d data1 %d",
+			dr->bNotificationType, dr->wIndex,
+			dr->wLength, data[0], data[1]);
+		break;
 	}
 exit:
 	usb_mark_last_busy(acm->dev);
-	retval = usb_submit_urb (urb, GFP_ATOMIC);
+	retval = usb_submit_urb(urb, GFP_ATOMIC);
 	if (retval)
 		dev_err(&urb->dev->dev, "%s - usb_submit_urb failed with "
 			"result %d", __func__, retval);
@@ -371,15 +383,14 @@ static void acm_rx_tasklet(unsigned long _acm)
 {
 	struct acm *acm = (void *)_acm;
 	struct acm_rb *buf;
-	struct tty_struct *tty = acm->tty;
+	struct tty_struct *tty;
 	struct acm_ru *rcv;
 	unsigned long flags;
 	unsigned char throttled;
 
 	dbg("Entering acm_rx_tasklet");
 
-	if (!ACM_READY(acm))
-	{
+	if (!ACM_READY(acm)) {
 		dbg("acm_rx_tasklet: ACM not ready");
 		return;
 	}
@@ -387,12 +398,13 @@ static void acm_rx_tasklet(unsigned long _acm)
 	spin_lock_irqsave(&acm->throttle_lock, flags);
 	throttled = acm->throttle;
 	spin_unlock_irqrestore(&acm->throttle_lock, flags);
-	if (throttled)
-	{
+	if (throttled) {
 		dbg("acm_rx_tasklet: throttled");
 		return;
 	}
 
+	tty = tty_port_tty_get(&acm->port);
+
 next_buffer:
 	spin_lock_irqsave(&acm->read_lock, flags);
 	if (list_empty(&acm->filled_read_bufs)) {
@@ -406,20 +418,22 @@ next_buffer:
 
 	dbg("acm_rx_tasklet: procesing buf 0x%p, size = %d", buf, buf->size);
 
-	tty_buffer_request_room(tty, buf->size);
-	spin_lock_irqsave(&acm->throttle_lock, flags);
-	throttled = acm->throttle;
-	spin_unlock_irqrestore(&acm->throttle_lock, flags);
-	if (!throttled)
-		tty_insert_flip_string(tty, buf->base, buf->size);
-	tty_flip_buffer_push(tty);
-
-	if (throttled) {
-		dbg("Throttling noticed");
-		spin_lock_irqsave(&acm->read_lock, flags);
-		list_add(&buf->list, &acm->filled_read_bufs);
-		spin_unlock_irqrestore(&acm->read_lock, flags);
-		return;
+	if (tty) {
+		spin_lock_irqsave(&acm->throttle_lock, flags);
+		throttled = acm->throttle;
+		spin_unlock_irqrestore(&acm->throttle_lock, flags);
+		if (!throttled) {
+			tty_buffer_request_room(tty, buf->size);
+			tty_insert_flip_string(tty, buf->base, buf->size);
+			tty_flip_buffer_push(tty);
+		} else {
+			tty_kref_put(tty);
+			dbg("Throttling noticed");
+			spin_lock_irqsave(&acm->read_lock, flags);
+			list_add(&buf->list, &acm->filled_read_bufs);
+			spin_unlock_irqrestore(&acm->read_lock, flags);
+			return;
+		}
 	}
 
 	spin_lock_irqsave(&acm->read_lock, flags);
@@ -428,6 +442,8 @@ next_buffer:
 	goto next_buffer;
 
 urbs:
+	tty_kref_put(tty);
+
 	while (!list_empty(&acm->spare_read_bufs)) {
 		spin_lock_irqsave(&acm->read_lock, flags);
 		if (list_empty(&acm->spare_read_urbs)) {
@@ -454,10 +470,11 @@ urbs:
 		rcv->urb->transfer_dma = buf->dma;
 		rcv->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 
-		/* This shouldn't kill the driver as unsuccessful URBs are returned to the
-		   free-urbs-pool and resubmited ASAP */
+		/* This shouldn't kill the driver as unsuccessful URBs are
+		   returned to the free-urbs-pool and resubmited ASAP */
 		spin_lock_irqsave(&acm->read_lock, flags);
-		if (acm->susp_count || usb_submit_urb(rcv->urb, GFP_ATOMIC) < 0) {
+		if (acm->susp_count ||
+				usb_submit_urb(rcv->urb, GFP_ATOMIC) < 0) {
 			list_add(&buf->list, &acm->spare_read_bufs);
 			list_add(&rcv->list, &acm->spare_read_urbs);
 			acm->processing = 0;
@@ -499,11 +516,14 @@ static void acm_write_bulk(struct urb *urb)
 static void acm_softint(struct work_struct *work)
 {
 	struct acm *acm = container_of(work, struct acm, work);
+	struct tty_struct *tty;
 
 	dev_vdbg(&acm->data->dev, "tx work\n");
 	if (!ACM_READY(acm))
 		return;
-	tty_wakeup(acm->tty);
+	tty = tty_port_tty_get(&acm->port);
+	tty_wakeup(tty);
+	tty_kref_put(tty);
 }
 
 static void acm_waker(struct work_struct *waker)
@@ -543,8 +563,9 @@ static int acm_tty_open(struct tty_struct *tty, struct file *filp)
 		rv = 0;
 
 	set_bit(TTY_NO_WRITE_SPLIT, &tty->flags);
+
 	tty->driver_data = acm;
-	acm->tty = tty;
+	tty_port_tty_set(&acm->port, tty);
 
 	if (usb_autopm_get_interface(acm->control) < 0)
 		goto early_bail;
@@ -552,11 +573,10 @@ static int acm_tty_open(struct tty_struct *tty, struct file *filp)
 		acm->control->needs_remote_wakeup = 1;
 
 	mutex_lock(&acm->mutex);
-	if (acm->used++) {
+	if (acm->port.count++) {
 		usb_autopm_put_interface(acm->control);
 		goto done;
-        }
-
+	}
 
 	acm->ctrlurb->dev = acm->dev;
 	if (usb_submit_urb(acm->ctrlurb, GFP_KERNEL)) {
@@ -567,22 +587,22 @@ static int acm_tty_open(struct tty_struct *tty, struct file *filp)
 	if (0 > acm_set_control(acm, acm->ctrlout = ACM_CTRL_DTR | ACM_CTRL_RTS) &&
 	    (acm->ctrl_caps & USB_CDC_CAP_LINE))
 		goto full_bailout;
+
 	usb_autopm_put_interface(acm->control);
 
 	INIT_LIST_HEAD(&acm->spare_read_urbs);
 	INIT_LIST_HEAD(&acm->spare_read_bufs);
 	INIT_LIST_HEAD(&acm->filled_read_bufs);
-	for (i = 0; i < acm->rx_buflimit; i++) {
+
+	for (i = 0; i < acm->rx_buflimit; i++)
 		list_add(&(acm->ru[i].list), &acm->spare_read_urbs);
-	}
-	for (i = 0; i < acm->rx_buflimit; i++) {
+	for (i = 0; i < acm->rx_buflimit; i++)
 		list_add(&(acm->rb[i].list), &acm->spare_read_bufs);
-	}
 
 	acm->throttle = 0;
 
 	tasklet_schedule(&acm->urb_task);
-
+	rv = tty_port_block_til_ready(&acm->port, tty, filp);
 done:
 	mutex_unlock(&acm->mutex);
 err_out:
@@ -593,16 +613,17 @@ full_bailout:
 	usb_kill_urb(acm->ctrlurb);
 bail_out:
 	usb_autopm_put_interface(acm->control);
-	acm->used--;
+	acm->port.count--;
 	mutex_unlock(&acm->mutex);
 early_bail:
 	mutex_unlock(&open_mutex);
+	tty_port_tty_set(&acm->port, NULL);
 	return -EIO;
 }
 
 static void acm_tty_unregister(struct acm *acm)
 {
-	int i,nr;
+	int i, nr;
 
 	nr = acm->rx_buflimit;
 	tty_unregister_device(acm_tty_driver, acm->minor);
@@ -619,41 +640,56 @@ static void acm_tty_unregister(struct acm *acm)
 
 static int acm_tty_chars_in_buffer(struct tty_struct *tty);
 
-static void acm_tty_close(struct tty_struct *tty, struct file *filp)
+static void acm_port_down(struct acm *acm, int drain)
 {
-	struct acm *acm = tty->driver_data;
-	int i,nr;
-
-	if (!acm || !acm->used)
-		return;
-
-	nr = acm->rx_buflimit;
+	int i, nr = acm->rx_buflimit;
 	mutex_lock(&open_mutex);
-	if (!--acm->used) {
-		if (acm->dev) {
-			usb_autopm_get_interface(acm->control);
-			acm_set_control(acm, acm->ctrlout = 0);
-
-			/* try letting the last writes drain naturally */
+	if (acm->dev) {
+		usb_autopm_get_interface(acm->control);
+		acm_set_control(acm, acm->ctrlout = 0);
+		/* try letting the last writes drain naturally */
+		if (drain) {
 			wait_event_interruptible_timeout(acm->drain_wait,
-					(ACM_NW == acm_wb_is_avail(acm))
-						|| !acm->dev,
+				(ACM_NW == acm_wb_is_avail(acm)) || !acm->dev,
 					ACM_CLOSE_TIMEOUT * HZ);
-
-			usb_kill_urb(acm->ctrlurb);
-			for (i = 0; i < ACM_NW; i++)
-				usb_kill_urb(acm->wb[i].urb);
-			for (i = 0; i < nr; i++)
-				usb_kill_urb(acm->ru[i].urb);
-			acm->control->needs_remote_wakeup = 0;
-			usb_autopm_put_interface(acm->control);
-		} else
-			acm_tty_unregister(acm);
+		}
+		usb_kill_urb(acm->ctrlurb);
+		for (i = 0; i < ACM_NW; i++)
+			usb_kill_urb(acm->wb[i].urb);
+		for (i = 0; i < nr; i++)
+			usb_kill_urb(acm->ru[i].urb);
+		acm->control->needs_remote_wakeup = 0;
+		usb_autopm_put_interface(acm->control);
 	}
 	mutex_unlock(&open_mutex);
 }
 
-static int acm_tty_write(struct tty_struct *tty, const unsigned char *buf, int count)
+static void acm_tty_hangup(struct tty_struct *tty)
+{
+	struct acm *acm = tty->driver_data;
+	tty_port_hangup(&acm->port);
+	acm_port_down(acm, 0);
+}
+
+static void acm_tty_close(struct tty_struct *tty, struct file *filp)
+{
+	struct acm *acm = tty->driver_data;
+
+	/* Perform the closing process and see if we need to do the hardware
+	   shutdown */
+	if (tty_port_close_start(&acm->port, tty, filp) == 0)
+		return;
+	acm_port_down(acm, 0);
+	tty_port_close_end(&acm->port, tty);
+	mutex_lock(&open_mutex);
+	tty_port_tty_set(&acm->port, NULL);
+	if (!acm->dev)
+		acm_tty_unregister(acm);
+	mutex_unlock(&open_mutex);
+}
+
+static int acm_tty_write(struct tty_struct *tty,
+					const unsigned char *buf, int count)
 {
 	struct acm *acm = tty->driver_data;
 	int stat;
@@ -669,7 +705,8 @@ static int acm_tty_write(struct tty_struct *tty, const unsigned char *buf, int c
 		return 0;
 
 	spin_lock_irqsave(&acm->write_lock, flags);
-	if ((wbn = acm_wb_alloc(acm)) < 0) {
+	wbn = acm_wb_alloc(acm);
+	if (wbn < 0) {
 		spin_unlock_irqrestore(&acm->write_lock, flags);
 		return 0;
 	}
@@ -681,7 +718,8 @@ static int acm_tty_write(struct tty_struct *tty, const unsigned char *buf, int c
 	wb->len = count;
 	spin_unlock_irqrestore(&acm->write_lock, flags);
 
-	if ((stat = acm_write_start(acm, wbn)) < 0)
+	stat = acm_write_start(acm, wbn);
+	if (stat < 0)
 		return stat;
 	return count;
 }
@@ -767,8 +805,10 @@ static int acm_tty_tiocmset(struct tty_struct *tty, struct file *file,
 		return -EINVAL;
 
 	newctrl = acm->ctrlout;
-	set = (set & TIOCM_DTR ? ACM_CTRL_DTR : 0) | (set & TIOCM_RTS ? ACM_CTRL_RTS : 0);
-	clear = (clear & TIOCM_DTR ? ACM_CTRL_DTR : 0) | (clear & TIOCM_RTS ? ACM_CTRL_RTS : 0);
+	set = (set & TIOCM_DTR ? ACM_CTRL_DTR : 0) |
+					(set & TIOCM_RTS ? ACM_CTRL_RTS : 0);
+	clear = (clear & TIOCM_DTR ? ACM_CTRL_DTR : 0) |
+					(clear & TIOCM_RTS ? ACM_CTRL_RTS : 0);
 
 	newctrl = (newctrl & ~clear) | set;
 
@@ -777,7 +817,8 @@ static int acm_tty_tiocmset(struct tty_struct *tty, struct file *file,
 	return acm_set_control(acm, acm->ctrlout = newctrl);
 }
 
-static int acm_tty_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg)
+static int acm_tty_ioctl(struct tty_struct *tty, struct file *file,
+					unsigned int cmd, unsigned long arg)
 {
 	struct acm *acm = tty->driver_data;
 
@@ -799,7 +840,8 @@ static const __u8 acm_tty_size[] = {
 	5, 6, 7, 8
 };
 
-static void acm_tty_set_termios(struct tty_struct *tty, struct ktermios *termios_old)
+static void acm_tty_set_termios(struct tty_struct *tty,
+						struct ktermios *termios_old)
 {
 	struct acm *acm = tty->driver_data;
 	struct ktermios *termios = tty->termios;
@@ -809,19 +851,23 @@ static void acm_tty_set_termios(struct tty_struct *tty, struct ktermios *termios
 	if (!ACM_READY(acm))
 		return;
 
+	/* FIXME: Needs to support the tty_baud interface */
+	/* FIXME: Broken on sparc */
 	newline.dwDTERate = cpu_to_le32p(acm_tty_speed +
 		(termios->c_cflag & CBAUD & ~CBAUDEX) + (termios->c_cflag & CBAUDEX ? 15 : 0));
 	newline.bCharFormat = termios->c_cflag & CSTOPB ? 2 : 0;
 	newline.bParityType = termios->c_cflag & PARENB ?
-		(termios->c_cflag & PARODD ? 1 : 2) + (termios->c_cflag & CMSPAR ? 2 : 0) : 0;
+				(termios->c_cflag & PARODD ? 1 : 2) +
+				(termios->c_cflag & CMSPAR ? 2 : 0) : 0;
 	newline.bDataBits = acm_tty_size[(termios->c_cflag & CSIZE) >> 4];
-
+	/* FIXME: Needs to clear unsupported bits in the termios */
 	acm->clocal = ((termios->c_cflag & CLOCAL) != 0);
 
 	if (!newline.dwDTERate) {
 		newline.dwDTERate = acm->line.dwDTERate;
 		newctrl &= ~ACM_CTRL_DTR;
-	} else  newctrl |=  ACM_CTRL_DTR;
+	} else
+		newctrl |=  ACM_CTRL_DTR;
 
 	if (newctrl != acm->ctrlout)
 		acm_set_control(acm, acm->ctrlout = newctrl);
@@ -846,9 +892,8 @@ static void acm_write_buffers_free(struct acm *acm)
 	struct acm_wb *wb;
 	struct usb_device *usb_dev = interface_to_usbdev(acm->control);
 
-	for (wb = &acm->wb[0], i = 0; i < ACM_NW; i++, wb++) {
+	for (wb = &acm->wb[0], i = 0; i < ACM_NW; i++, wb++)
 		usb_buffer_free(usb_dev, acm->writesize, wb->buf, wb->dmah);
-	}
 }
 
 static void acm_read_buffers_free(struct acm *acm)
@@ -857,7 +902,8 @@ static void acm_read_buffers_free(struct acm *acm)
 	int i, n = acm->rx_buflimit;
 
 	for (i = 0; i < n; i++)
-		usb_buffer_free(usb_dev, acm->readsize, acm->rb[i].base, acm->rb[i].dma);
+		usb_buffer_free(usb_dev, acm->readsize,
+					acm->rb[i].base, acm->rb[i].dma);
 }
 
 /* Little helper: write buffers allocate */
@@ -882,8 +928,8 @@ static int acm_write_buffers_alloc(struct acm *acm)
 	return 0;
 }
 
-static int acm_probe (struct usb_interface *intf,
-		      const struct usb_device_id *id)
+static int acm_probe(struct usb_interface *intf,
+		     const struct usb_device_id *id)
 {
 	struct usb_cdc_union_desc *union_header = NULL;
 	struct usb_cdc_country_functional_desc *cfd = NULL;
@@ -897,7 +943,7 @@ static int acm_probe (struct usb_interface *intf,
 	struct usb_device *usb_dev = interface_to_usbdev(intf);
 	struct acm *acm;
 	int minor;
-	int ctrlsize,readsize;
+	int ctrlsize, readsize;
 	u8 *buf;
 	u8 ac_management_function = 0;
 	u8 call_management_function = 0;
@@ -917,7 +963,7 @@ static int acm_probe (struct usb_interface *intf,
 		control_interface = usb_ifnum_to_if(usb_dev, 0);
 		goto skip_normal_probe;
 	}
-	
+
 	/* normal probing*/
 	if (!buffer) {
 		dev_err(&intf->dev, "Weird descriptor references\n");
@@ -925,8 +971,10 @@ static int acm_probe (struct usb_interface *intf,
 	}
 
 	if (!buflen) {
-		if (intf->cur_altsetting->endpoint->extralen && intf->cur_altsetting->endpoint->extra) {
-			dev_dbg(&intf->dev,"Seeking extra descriptors on endpoint\n");
+		if (intf->cur_altsetting->endpoint->extralen &&
+				intf->cur_altsetting->endpoint->extra) {
+			dev_dbg(&intf->dev,
+				"Seeking extra descriptors on endpoint\n");
 			buflen = intf->cur_altsetting->endpoint->extralen;
 			buffer = intf->cur_altsetting->endpoint->extra;
 		} else {
@@ -937,47 +985,43 @@ static int acm_probe (struct usb_interface *intf,
 	}
 
 	while (buflen > 0) {
-		if (buffer [1] != USB_DT_CS_INTERFACE) {
+		if (buffer[1] != USB_DT_CS_INTERFACE) {
 			dev_err(&intf->dev, "skipping garbage\n");
 			goto next_desc;
 		}
 
-		switch (buffer [2]) {
-			case USB_CDC_UNION_TYPE: /* we've found it */
-				if (union_header) {
-					dev_err(&intf->dev, "More than one "
-						"union descriptor, "
-						"skipping ...\n");
-					goto next_desc;
-				}
-				union_header = (struct usb_cdc_union_desc *)
-							buffer;
-				break;
-			case USB_CDC_COUNTRY_TYPE: /* export through sysfs*/
-				cfd = (struct usb_cdc_country_functional_desc *)buffer;
-				break;
-			case USB_CDC_HEADER_TYPE: /* maybe check version */ 
-				break; /* for now we ignore it */ 
-			case USB_CDC_ACM_TYPE:
-				ac_management_function = buffer[3];
-				break;
-			case USB_CDC_CALL_MANAGEMENT_TYPE:
-				call_management_function = buffer[3];
-				call_interface_num = buffer[4];
-				if ((call_management_function & 3) != 3)
-					dev_err(&intf->dev, "This device "
-						"cannot do calls on its own. "
-						"It is no modem.\n");
-				break;
-			default:
-				/* there are LOTS more CDC descriptors that
-				 * could legitimately be found here.
-				 */
-				dev_dbg(&intf->dev, "Ignoring descriptor: "
-						"type %02x, length %d\n",
-						buffer[2], buffer[0]);
-				break;
+		switch (buffer[2]) {
+		case USB_CDC_UNION_TYPE: /* we've found it */
+			if (union_header) {
+				dev_err(&intf->dev, "More than one "
+					"union descriptor, skipping ...\n");
+				goto next_desc;
 			}
+			union_header = (struct usb_cdc_union_desc *)buffer;
+			break;
+		case USB_CDC_COUNTRY_TYPE: /* export through sysfs*/
+			cfd = (struct usb_cdc_country_functional_desc *)buffer;
+			break;
+		case USB_CDC_HEADER_TYPE: /* maybe check version */
+			break; /* for now we ignore it */
+		case USB_CDC_ACM_TYPE:
+			ac_management_function = buffer[3];
+			break;
+		case USB_CDC_CALL_MANAGEMENT_TYPE:
+			call_management_function = buffer[3];
+			call_interface_num = buffer[4];
+			if ((call_management_function & 3) != 3)
+				dev_err(&intf->dev, "This device cannot do calls on its own. It is not a modem.\n");
+			break;
+		default:
+			/* there are LOTS more CDC descriptors that
+			 * could legitimately be found here.
+			 */
+			dev_dbg(&intf->dev, "Ignoring descriptor: "
+					"type %02x, length %d\n",
+					buffer[2], buffer[0]);
+			break;
+		}
 next_desc:
 		buflen -= buffer[0];
 		buffer += buffer[0];
@@ -985,33 +1029,36 @@ next_desc:
 
 	if (!union_header) {
 		if (call_interface_num > 0) {
-			dev_dbg(&intf->dev,"No union descriptor, using call management descriptor\n");
+			dev_dbg(&intf->dev, "No union descriptor, using call management descriptor\n");
 			data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = call_interface_num));
 			control_interface = intf;
 		} else {
-			dev_dbg(&intf->dev,"No union descriptor, giving up\n");
+			dev_dbg(&intf->dev,
+					"No union descriptor, giving up\n");
 			return -ENODEV;
 		}
 	} else {
 		control_interface = usb_ifnum_to_if(usb_dev, union_header->bMasterInterface0);
 		data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = union_header->bSlaveInterface0));
 		if (!control_interface || !data_interface) {
-			dev_dbg(&intf->dev,"no interfaces\n");
+			dev_dbg(&intf->dev, "no interfaces\n");
 			return -ENODEV;
 		}
 	}
-	
+
 	if (data_interface_num != call_interface_num)
-		dev_dbg(&intf->dev,"Separate call control interface. That is not fully supported.\n");
+		dev_dbg(&intf->dev, "Separate call control interface. That is not fully supported.\n");
 
 skip_normal_probe:
 
 	/*workaround for switched interfaces */
-	if (data_interface->cur_altsetting->desc.bInterfaceClass != CDC_DATA_INTERFACE_TYPE) {
-		if (control_interface->cur_altsetting->desc.bInterfaceClass == CDC_DATA_INTERFACE_TYPE) {
+	if (data_interface->cur_altsetting->desc.bInterfaceClass
+						!= CDC_DATA_INTERFACE_TYPE) {
+		if (control_interface->cur_altsetting->desc.bInterfaceClass
+						== CDC_DATA_INTERFACE_TYPE) {
 			struct usb_interface *t;
-			dev_dbg(&intf->dev,"Your device has switched interfaces.\n");
-
+			dev_dbg(&intf->dev,
+				"Your device has switched interfaces.\n");
 			t = control_interface;
 			control_interface = data_interface;
 			data_interface = t;
@@ -1023,9 +1070,9 @@ skip_normal_probe:
 	/* Accept probe requests only for the control interface */
 	if (intf != control_interface)
 		return -ENODEV;
-	
+
 	if (usb_interface_claimed(data_interface)) { /* valid in this context */
-		dev_dbg(&intf->dev,"The data interface isn't available\n");
+		dev_dbg(&intf->dev, "The data interface isn't available\n");
 		return -EBUSY;
 	}
 
@@ -1042,8 +1089,8 @@ skip_normal_probe:
 	if (!usb_endpoint_dir_in(epread)) {
 		/* descriptors are swapped */
 		struct usb_endpoint_descriptor *t;
-		dev_dbg(&intf->dev,"The data interface has switched endpoints\n");
-		
+		dev_dbg(&intf->dev,
+			"The data interface has switched endpoints\n");
 		t = epread;
 		epread = epwrite;
 		epwrite = t;
@@ -1056,13 +1103,15 @@ skip_normal_probe:
 		return -ENODEV;
 	}
 
-	if (!(acm = kzalloc(sizeof(struct acm), GFP_KERNEL))) {
+	acm = kzalloc(sizeof(struct acm), GFP_KERNEL);
+	if (acm == NULL) {
 		dev_dbg(&intf->dev, "out of memory (acm kzalloc)\n");
 		goto alloc_fail;
 	}
 
 	ctrlsize = le16_to_cpu(epctrl->wMaxPacketSize);
-	readsize = le16_to_cpu(epread->wMaxPacketSize)* ( quirks == SINGLE_RX_URB ? 1 : 2);
+	readsize = le16_to_cpu(epread->wMaxPacketSize) *
+				(quirks == SINGLE_RX_URB ? 1 : 2);
 	acm->writesize = le16_to_cpu(epwrite->wMaxPacketSize) * 20;
 	acm->control = control_interface;
 	acm->data = data_interface;
@@ -1082,6 +1131,8 @@ skip_normal_probe:
 	spin_lock_init(&acm->read_lock);
 	mutex_init(&acm->mutex);
 	acm->rx_endpoint = usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress);
+	tty_port_init(&acm->port);
+	acm->port.ops = &acm_port_ops;
 
 	buf = usb_buffer_alloc(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma);
 	if (!buf) {
@@ -1103,8 +1154,10 @@ skip_normal_probe:
 	for (i = 0; i < num_rx_buf; i++) {
 		struct acm_ru *rcv = &(acm->ru[i]);
 
-		if (!(rcv->urb = usb_alloc_urb(0, GFP_KERNEL))) {
-			dev_dbg(&intf->dev, "out of memory (read urbs usb_alloc_urb)\n");
+		rcv->urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (rcv->urb == NULL) {
+			dev_dbg(&intf->dev,
+				"out of memory (read urbs usb_alloc_urb)\n");
 			goto alloc_fail7;
 		}
 
@@ -1117,26 +1170,29 @@ skip_normal_probe:
 		rb->base = usb_buffer_alloc(acm->dev, readsize,
 				GFP_KERNEL, &rb->dma);
 		if (!rb->base) {
-			dev_dbg(&intf->dev, "out of memory (read bufs usb_buffer_alloc)\n");
+			dev_dbg(&intf->dev,
+				"out of memory (read bufs usb_buffer_alloc)\n");
 			goto alloc_fail7;
 		}
 	}
-	for(i = 0; i < ACM_NW; i++)
-	{
+	for (i = 0; i < ACM_NW; i++) {
 		struct acm_wb *snd = &(acm->wb[i]);
 
-		if (!(snd->urb = usb_alloc_urb(0, GFP_KERNEL))) {
-			dev_dbg(&intf->dev, "out of memory (write urbs usb_alloc_urb)");
+		snd->urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (snd->urb == NULL) {
+			dev_dbg(&intf->dev,
+				"out of memory (write urbs usb_alloc_urb)");
 			goto alloc_fail7;
 		}
 
-		usb_fill_bulk_urb(snd->urb, usb_dev, usb_sndbulkpipe(usb_dev, epwrite->bEndpointAddress),
-				NULL, acm->writesize, acm_write_bulk, snd);
+		usb_fill_bulk_urb(snd->urb, usb_dev,
+			usb_sndbulkpipe(usb_dev, epwrite->bEndpointAddress),
+			NULL, acm->writesize, acm_write_bulk, snd);
 		snd->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 		snd->instance = acm;
 	}
 
-	usb_set_intfdata (intf, acm);
+	usb_set_intfdata(intf, acm);
 
 	i = device_create_file(&intf->dev, &dev_attr_bmCapabilities);
 	if (i < 0)
@@ -1147,7 +1203,8 @@ skip_normal_probe:
 		if (!acm->country_codes)
 			goto skip_countries;
 		acm->country_code_size = cfd->bLength - 4;
-		memcpy(acm->country_codes, (u8 *)&cfd->wCountyCode0, cfd->bLength - 4);
+		memcpy(acm->country_codes, (u8 *)&cfd->wCountyCode0,
+							cfd->bLength - 4);
 		acm->country_rel_date = cfd->iCountryCodeRelDate;
 
 		i = device_create_file(&intf->dev, &dev_attr_wCountryCodes);
@@ -1156,7 +1213,8 @@ skip_normal_probe:
 			goto skip_countries;
 		}
 
-		i = device_create_file(&intf->dev, &dev_attr_iCountryCodeRelDate);
+		i = device_create_file(&intf->dev,
+						&dev_attr_iCountryCodeRelDate);
 		if (i < 0) {
 			kfree(acm->country_codes);
 			goto skip_countries;
@@ -1164,8 +1222,10 @@ skip_normal_probe:
 	}
 
 skip_countries:
-	usb_fill_int_urb(acm->ctrlurb, usb_dev, usb_rcvintpipe(usb_dev, epctrl->bEndpointAddress),
-			 acm->ctrl_buffer, ctrlsize, acm_ctrl_irq, acm, epctrl->bInterval);
+	usb_fill_int_urb(acm->ctrlurb, usb_dev,
+			usb_rcvintpipe(usb_dev, epctrl->bEndpointAddress),
+			acm->ctrl_buffer, ctrlsize, acm_ctrl_irq, acm,
+			epctrl->bInterval);
 	acm->ctrlurb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 	acm->ctrlurb->transfer_dma = acm->ctrl_dma;
 
@@ -1212,7 +1272,7 @@ static void stop_data_traffic(struct acm *acm)
 	tasklet_disable(&acm->urb_task);
 
 	usb_kill_urb(acm->ctrlurb);
-	for(i = 0; i < ACM_NW; i++)
+	for (i = 0; i < ACM_NW; i++)
 		usb_kill_urb(acm->wb[i].urb);
 	for (i = 0; i < acm->rx_buflimit; i++)
 		usb_kill_urb(acm->ru[i].urb);
@@ -1227,13 +1287,14 @@ static void acm_disconnect(struct usb_interface *intf)
 {
 	struct acm *acm = usb_get_intfdata(intf);
 	struct usb_device *usb_dev = interface_to_usbdev(intf);
+	struct tty_struct *tty;
 
 	/* sibling interface is already cleaning up */
 	if (!acm)
 		return;
 
 	mutex_lock(&open_mutex);
-	if (acm->country_codes){
+	if (acm->country_codes) {
 		device_remove_file(&acm->control->dev,
 				&dev_attr_wCountryCodes);
 		device_remove_file(&acm->control->dev,
@@ -1247,22 +1308,25 @@ static void acm_disconnect(struct usb_interface *intf)
 	stop_data_traffic(acm);
 
 	acm_write_buffers_free(acm);
-	usb_buffer_free(usb_dev, acm->ctrlsize, acm->ctrl_buffer, acm->ctrl_dma);
+	usb_buffer_free(usb_dev, acm->ctrlsize, acm->ctrl_buffer,
+								acm->ctrl_dma);
 	acm_read_buffers_free(acm);
 
 	usb_driver_release_interface(&acm_driver, intf == acm->control ?
 					acm->data : acm->control);
 
-	if (!acm->used) {
+	if (acm->port.count == 0) {
 		acm_tty_unregister(acm);
 		mutex_unlock(&open_mutex);
 		return;
 	}
 
 	mutex_unlock(&open_mutex);
-
-	if (acm->tty)
-		tty_hangup(acm->tty);
+	tty = tty_port_tty_get(&acm->port);
+	if (tty) {
+		tty_hangup(tty);
+		tty_kref_put(tty);
+	}
 }
 
 #ifdef CONFIG_PM
@@ -1297,7 +1361,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 	*/
 	mutex_lock(&acm->mutex);
 
-	if (acm->used)
+	if (acm->port.count)
 		stop_data_traffic(acm);
 
 	mutex_unlock(&acm->mutex);
@@ -1319,7 +1383,7 @@ static int acm_resume(struct usb_interface *intf)
 		return 0;
 
 	mutex_lock(&acm->mutex);
-	if (acm->used) {
+	if (acm->port.count) {
 		rv = usb_submit_urb(acm->ctrlurb, GFP_NOIO);
 		if (rv < 0)
 			goto err_out;
@@ -1398,7 +1462,7 @@ static struct usb_device_id acm_ids[] = {
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
 		USB_CDC_ACM_PROTO_AT_GSM) },
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
-		USB_CDC_ACM_PROTO_AT_3G	) },
+		USB_CDC_ACM_PROTO_AT_3G) },
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
 		USB_CDC_ACM_PROTO_AT_CDMA) },
 
@@ -1406,7 +1470,7 @@ static struct usb_device_id acm_ids[] = {
 	{ }
 };
 
-MODULE_DEVICE_TABLE (usb, acm_ids);
+MODULE_DEVICE_TABLE(usb, acm_ids);
 
 static struct usb_driver acm_driver = {
 	.name =		"cdc_acm",
@@ -1429,6 +1493,7 @@ static struct usb_driver acm_driver = {
 static const struct tty_operations acm_ops = {
 	.open =			acm_tty_open,
 	.close =		acm_tty_close,
+	.hangup =		acm_tty_hangup,
 	.write =		acm_tty_write,
 	.write_room =		acm_tty_write_room,
 	.ioctl =		acm_tty_ioctl,
@@ -1460,7 +1525,8 @@ static int __init acm_init(void)
 	acm_tty_driver->subtype = SERIAL_TYPE_NORMAL,
 	acm_tty_driver->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV;
 	acm_tty_driver->init_termios = tty_std_termios;
-	acm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL;
+	acm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD |
+								HUPCL | CLOCAL;
 	tty_set_operations(acm_tty_driver, &acm_ops);
 
 	retval = tty_register_driver(acm_tty_driver);
@@ -1492,7 +1558,7 @@ static void __exit acm_exit(void)
 module_init(acm_init);
 module_exit(acm_exit);
 
-MODULE_AUTHOR( DRIVER_AUTHOR );
-MODULE_DESCRIPTION( DRIVER_DESC );
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_CHARDEV_MAJOR(ACM_TTY_MAJOR);
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index 1f95e7aa1b66..4c3856420add 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -89,8 +89,8 @@ struct acm {
 	struct usb_device *dev;				/* the corresponding usb device */
 	struct usb_interface *control;			/* control interface */
 	struct usb_interface *data;			/* data interface */
-	struct tty_struct *tty;				/* the corresponding tty */
-	struct urb *ctrlurb;			/* urbs */
+	struct tty_port port;			 	/* our tty port data */
+	struct urb *ctrlurb;				/* urbs */
 	u8 *ctrl_buffer;				/* buffers of urbs */
 	dma_addr_t ctrl_dma;				/* dma handles of buffers */
 	u8 *country_codes;				/* country codes from device */
@@ -120,7 +120,6 @@ struct acm {
 	unsigned int ctrlout;				/* output control lines (DTR, RTS) */
 	unsigned int writesize;				/* max packet size for the output bulk endpoint */
 	unsigned int readsize,ctrlsize;			/* buffer sizes for freeing */
-	unsigned int used;				/* someone has this acm's device open */
 	unsigned int minor;				/* acm minor number */
 	unsigned char throttle;				/* throttled by tty layer */
 	unsigned char clocal;				/* termios CLOCAL */
diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c
index dff5760a37f6..ffe75e83787c 100644
--- a/drivers/usb/core/inode.c
+++ b/drivers/usb/core/inode.c
@@ -39,6 +39,7 @@
 #include <linux/parser.h>
 #include <linux/notifier.h>
 #include <linux/seq_file.h>
+#include <linux/smp_lock.h>
 #include <asm/byteorder.h>
 #include "usb.h"
 #include "hcd.h"
@@ -265,9 +266,13 @@ static int remount(struct super_block *sb, int *flags, char *data)
 		return -EINVAL;
 	}
 
+	lock_kernel();
+
 	if (usbfs_mount && usbfs_mount->mnt_sb)
 		update_sb(usbfs_mount->mnt_sb);
 
+	unlock_kernel();
+
 	return 0;
 }
 
diff --git a/drivers/usb/serial/belkin_sa.c b/drivers/usb/serial/belkin_sa.c
index b7eacad4d48c..2bfd6dd85b5a 100644
--- a/drivers/usb/serial/belkin_sa.c
+++ b/drivers/usb/serial/belkin_sa.c
@@ -93,8 +93,7 @@ static int  belkin_sa_startup(struct usb_serial *serial);
 static void belkin_sa_shutdown(struct usb_serial *serial);
 static int  belkin_sa_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void belkin_sa_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+static void belkin_sa_close(struct usb_serial_port *port);
 static void belkin_sa_read_int_callback(struct urb *urb);
 static void belkin_sa_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios * old);
@@ -244,8 +243,7 @@ exit:
 } /* belkin_sa_open */
 
 
-static void belkin_sa_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void belkin_sa_close(struct usb_serial_port *port)
 {
 	dbg("%s port %d", __func__, port->number);
 
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index ab4cc277aa65..2830766f5b39 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -262,13 +262,33 @@ error:	kfree(priv);
 	return r;
 }
 
-static void ch341_close(struct tty_struct *tty, struct usb_serial_port *port,
-				struct file *filp)
+static int ch341_carrier_raised(struct usb_serial_port *port)
+{
+	struct ch341_private *priv = usb_get_serial_port_data(port);
+	if (priv->line_status & CH341_BIT_DCD)
+		return 1;
+	return 0;
+}
+
+static void ch341_dtr_rts(struct usb_serial_port *port, int on)
 {
 	struct ch341_private *priv = usb_get_serial_port_data(port);
 	unsigned long flags;
-	unsigned int c_cflag;
 
+	dbg("%s - port %d", __func__, port->number);
+	/* drop DTR and RTS */
+	spin_lock_irqsave(&priv->lock, flags);
+	if (on)
+		priv->line_control |= CH341_BIT_RTS | CH341_BIT_DTR;
+	else
+		priv->line_control &= ~(CH341_BIT_RTS | CH341_BIT_DTR);
+	spin_unlock_irqrestore(&priv->lock, flags);
+	ch341_set_handshake(port->serial->dev, priv->line_control);
+	wake_up_interruptible(&priv->delta_msr_wait);
+}
+
+static void ch341_close(struct usb_serial_port *port)
+{
 	dbg("%s - port %d", __func__, port->number);
 
 	/* shutdown our urbs */
@@ -276,18 +296,6 @@ static void ch341_close(struct tty_struct *tty, struct usb_serial_port *port,
 	usb_kill_urb(port->write_urb);
 	usb_kill_urb(port->read_urb);
 	usb_kill_urb(port->interrupt_in_urb);
-
-	if (tty) {
-		c_cflag = tty->termios->c_cflag;
-		if (c_cflag & HUPCL) {
-			/* drop DTR and RTS */
-			spin_lock_irqsave(&priv->lock, flags);
-			priv->line_control = 0;
-			spin_unlock_irqrestore(&priv->lock, flags);
-			ch341_set_handshake(port->serial->dev, 0);
-		}
-	}
-	wake_up_interruptible(&priv->delta_msr_wait);
 }
 
 
@@ -302,7 +310,6 @@ static int ch341_open(struct tty_struct *tty, struct usb_serial_port *port,
 	dbg("ch341_open()");
 
 	priv->baud_rate = DEFAULT_BAUD_RATE;
-	priv->line_control = CH341_BIT_RTS | CH341_BIT_DTR;
 
 	r = ch341_configure(serial->dev, priv);
 	if (r)
@@ -322,7 +329,7 @@ static int ch341_open(struct tty_struct *tty, struct usb_serial_port *port,
 	if (r) {
 		dev_err(&port->dev, "%s - failed submitting interrupt urb,"
 			" error %d\n", __func__, r);
-		ch341_close(tty, port, NULL);
+		ch341_close(port);
 		return -EPROTO;
 	}
 
@@ -343,9 +350,6 @@ static void ch341_set_termios(struct tty_struct *tty,
 
 	dbg("ch341_set_termios()");
 
-	if (!tty || !tty->termios)
-		return;
-
 	baud_rate = tty_get_baud_rate(tty);
 
 	priv->baud_rate = baud_rate;
@@ -568,6 +572,8 @@ static struct usb_serial_driver ch341_device = {
 	.usb_driver        = &ch341_driver,
 	.num_ports         = 1,
 	.open              = ch341_open,
+	.dtr_rts	   = ch341_dtr_rts,
+	.carrier_raised	   = ch341_carrier_raised,
 	.close             = ch341_close,
 	.ioctl             = ch341_ioctl,
 	.set_termios       = ch341_set_termios,
diff --git a/drivers/usb/serial/console.c b/drivers/usb/serial/console.c
index 19e24045b137..247b61bfb7f4 100644
--- a/drivers/usb/serial/console.c
+++ b/drivers/usb/serial/console.c
@@ -169,7 +169,9 @@ static int usb_console_setup(struct console *co, char *options)
 			kfree(tty);
 		}
 	}
-
+	/* So we know not to kill the hardware on a hangup on this
+	   port. We have also bumped the use count by one so it won't go
+	   idle */
 	port->console = 1;
 	retval = 0;
 
@@ -182,7 +184,7 @@ free_tty:
 	kfree(tty);
 reset_open_count:
 	port->port.count = 0;
-goto out;
+	goto out;
 }
 
 static void usb_console_write(struct console *co,
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index e8d5133ce9c8..16a154d3b2fe 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -1,5 +1,5 @@
 /*
- * Silicon Laboratories CP2101/CP2102 USB to RS232 serial adaptor driver
+ * Silicon Laboratories CP210x USB to RS232 serial adaptor driver
  *
  * Copyright (C) 2005 Craig Shelley (craig@microtron.org.uk)
  *
@@ -27,44 +27,46 @@
 /*
  * Version Information
  */
-#define DRIVER_VERSION "v0.08"
-#define DRIVER_DESC "Silicon Labs CP2101/CP2102 RS232 serial adaptor driver"
+#define DRIVER_VERSION "v0.09"
+#define DRIVER_DESC "Silicon Labs CP210x RS232 serial adaptor driver"
 
 /*
  * Function Prototypes
  */
-static int cp2101_open(struct tty_struct *, struct usb_serial_port *,
+static int cp210x_open(struct tty_struct *, struct usb_serial_port *,
 							struct file *);
-static void cp2101_cleanup(struct usb_serial_port *);
-static void cp2101_close(struct tty_struct *, struct usb_serial_port *,
-							struct file*);
-static void cp2101_get_termios(struct tty_struct *,
+static void cp210x_cleanup(struct usb_serial_port *);
+static void cp210x_close(struct usb_serial_port *);
+static void cp210x_get_termios(struct tty_struct *,
 	struct usb_serial_port *port);
-static void cp2101_get_termios_port(struct usb_serial_port *port,
+static void cp210x_get_termios_port(struct usb_serial_port *port,
 	unsigned int *cflagp, unsigned int *baudp);
-static void cp2101_set_termios(struct tty_struct *, struct usb_serial_port *,
+static void cp210x_set_termios(struct tty_struct *, struct usb_serial_port *,
 							struct ktermios*);
-static int cp2101_tiocmget(struct tty_struct *, struct file *);
-static int cp2101_tiocmset(struct tty_struct *, struct file *,
+static int cp210x_tiocmget(struct tty_struct *, struct file *);
+static int cp210x_tiocmset(struct tty_struct *, struct file *,
 		unsigned int, unsigned int);
-static int cp2101_tiocmset_port(struct usb_serial_port *port, struct file *,
+static int cp210x_tiocmset_port(struct usb_serial_port *port, struct file *,
 		unsigned int, unsigned int);
-static void cp2101_break_ctl(struct tty_struct *, int);
-static int cp2101_startup(struct usb_serial *);
-static void cp2101_shutdown(struct usb_serial *);
+static void cp210x_break_ctl(struct tty_struct *, int);
+static int cp210x_startup(struct usb_serial *);
+static void cp210x_shutdown(struct usb_serial *);
 
 static int debug;
 
 static struct usb_device_id id_table [] = {
 	{ USB_DEVICE(0x0471, 0x066A) }, /* AKTAKOM ACE-1001 cable */
 	{ USB_DEVICE(0x0489, 0xE000) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */
+	{ USB_DEVICE(0x0745, 0x1000) }, /* CipherLab USB CCD Barcode Scanner 1000 */
 	{ USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */
+	{ USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */
 	{ USB_DEVICE(0x0FCF, 0x1003) }, /* Dynastream ANT development board */
 	{ USB_DEVICE(0x0FCF, 0x1004) }, /* Dynastream ANT2USB */
 	{ USB_DEVICE(0x0FCF, 0x1006) }, /* Dynastream ANT development board */
 	{ USB_DEVICE(0x10A6, 0xAA26) }, /* Knock-off DCU-11 cable */
 	{ USB_DEVICE(0x10AB, 0x10C5) }, /* Siemens MC60 Cable */
 	{ USB_DEVICE(0x10B5, 0xAC70) }, /* Nokia CA-42 USB */
+	{ USB_DEVICE(0x10C4, 0x0F91) }, /* Vstabi */
 	{ USB_DEVICE(0x10C4, 0x800A) }, /* SPORTident BSM7-D-USB main station */
 	{ USB_DEVICE(0x10C4, 0x803B) }, /* Pololu USB-serial converter */
 	{ USB_DEVICE(0x10C4, 0x8053) }, /* Enfora EDG1228 */
@@ -85,10 +87,12 @@ static struct usb_device_id id_table [] = {
 	{ USB_DEVICE(0x10C4, 0x81C8) }, /* Lipowsky Industrie Elektronik GmbH, Baby-JTAG */
 	{ USB_DEVICE(0x10C4, 0x81E2) }, /* Lipowsky Industrie Elektronik GmbH, Baby-LIN */
 	{ USB_DEVICE(0x10C4, 0x81E7) }, /* Aerocomm Radio */
+	{ USB_DEVICE(0x10C4, 0x81F2) }, /* C1007 HF band RFID controller */
 	{ USB_DEVICE(0x10C4, 0x8218) }, /* Lipowsky Industrie Elektronik GmbH, HARP-1 */
 	{ USB_DEVICE(0x10C4, 0x822B) }, /* Modem EDGE(GSM) Comander 2 */
 	{ USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demostration module */
 	{ USB_DEVICE(0x10c4, 0x8293) }, /* Telegesys ETRX2USB */
+	{ USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */
 	{ USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */
 	{ USB_DEVICE(0x10C4, 0x83A8) }, /* Amber Wireless AMB2560 */
 	{ USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */
@@ -99,7 +103,9 @@ static struct usb_device_id id_table [] = {
 	{ USB_DEVICE(0x10C4, 0xF003) }, /* Elan Digital Systems USBpulse100 */
 	{ USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */
 	{ USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */
+	{ USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */
 	{ USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */
+	{ USB_DEVICE(0x1555, 0x0004) }, /* Owen AC4 USB-RS485 Converter */
 	{ USB_DEVICE(0x166A, 0x0303) }, /* Clipsal 5500PCU C-Bus USB interface */
 	{ USB_DEVICE(0x16D6, 0x0001) }, /* Jablotron serial interface */
 	{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
@@ -108,53 +114,70 @@ static struct usb_device_id id_table [] = {
 
 MODULE_DEVICE_TABLE(usb, id_table);
 
-static struct usb_driver cp2101_driver = {
-	.name		= "cp2101",
+static struct usb_driver cp210x_driver = {
+	.name		= "cp210x",
 	.probe		= usb_serial_probe,
 	.disconnect	= usb_serial_disconnect,
 	.id_table	= id_table,
 	.no_dynamic_id	= 	1,
 };
 
-static struct usb_serial_driver cp2101_device = {
+static struct usb_serial_driver cp210x_device = {
 	.driver = {
 		.owner =	THIS_MODULE,
-		.name = 	"cp2101",
+		.name = 	"cp210x",
 	},
-	.usb_driver		= &cp2101_driver,
+	.usb_driver		= &cp210x_driver,
 	.id_table		= id_table,
 	.num_ports		= 1,
-	.open			= cp2101_open,
-	.close			= cp2101_close,
-	.break_ctl		= cp2101_break_ctl,
-	.set_termios		= cp2101_set_termios,
-	.tiocmget 		= cp2101_tiocmget,
-	.tiocmset		= cp2101_tiocmset,
-	.attach			= cp2101_startup,
-	.shutdown		= cp2101_shutdown,
+	.open			= cp210x_open,
+	.close			= cp210x_close,
+	.break_ctl		= cp210x_break_ctl,
+	.set_termios		= cp210x_set_termios,
+	.tiocmget 		= cp210x_tiocmget,
+	.tiocmset		= cp210x_tiocmset,
+	.attach			= cp210x_startup,
+	.shutdown		= cp210x_shutdown,
 };
 
 /* Config request types */
 #define REQTYPE_HOST_TO_DEVICE	0x41
 #define REQTYPE_DEVICE_TO_HOST	0xc1
 
-/* Config SET requests. To GET, add 1 to the request number */
-#define CP2101_UART 		0x00	/* Enable / Disable */
-#define CP2101_BAUDRATE		0x01	/* (BAUD_RATE_GEN_FREQ / baudrate) */
-#define CP2101_BITS		0x03	/* 0x(0)(databits)(parity)(stopbits) */
-#define CP2101_BREAK		0x05	/* On / Off */
-#define CP2101_CONTROL		0x07	/* Flow control line states */
-#define CP2101_MODEMCTL		0x13	/* Modem controls */
-#define CP2101_CONFIG_6		0x19	/* 6 bytes of config data ??? */
+/* Config request codes */
+#define CP210X_IFC_ENABLE	0x00
+#define CP210X_SET_BAUDDIV	0x01
+#define CP210X_GET_BAUDDIV	0x02
+#define CP210X_SET_LINE_CTL	0x03
+#define CP210X_GET_LINE_CTL	0x04
+#define CP210X_SET_BREAK	0x05
+#define CP210X_IMM_CHAR		0x06
+#define CP210X_SET_MHS		0x07
+#define CP210X_GET_MDMSTS	0x08
+#define CP210X_SET_XON		0x09
+#define CP210X_SET_XOFF		0x0A
+#define CP210X_SET_EVENTMASK	0x0B
+#define CP210X_GET_EVENTMASK	0x0C
+#define CP210X_SET_CHAR		0x0D
+#define CP210X_GET_CHARS	0x0E
+#define CP210X_GET_PROPS	0x0F
+#define CP210X_GET_COMM_STATUS	0x10
+#define CP210X_RESET		0x11
+#define CP210X_PURGE		0x12
+#define CP210X_SET_FLOW		0x13
+#define CP210X_GET_FLOW		0x14
+#define CP210X_EMBED_EVENTS	0x15
+#define CP210X_GET_EVENTSTATE	0x16
+#define CP210X_SET_CHARS	0x19
 
-/* CP2101_UART */
+/* CP210X_IFC_ENABLE */
 #define UART_ENABLE		0x0001
 #define UART_DISABLE		0x0000
 
-/* CP2101_BAUDRATE */
+/* CP210X_(SET|GET)_BAUDDIV */
 #define BAUD_RATE_GEN_FREQ	0x384000
 
-/* CP2101_BITS */
+/* CP210X_(SET|GET)_LINE_CTL */
 #define BITS_DATA_MASK		0X0f00
 #define BITS_DATA_5		0X0500
 #define BITS_DATA_6		0X0600
@@ -174,11 +197,11 @@ static struct usb_serial_driver cp2101_device = {
 #define BITS_STOP_1_5		0x0001
 #define BITS_STOP_2		0x0002
 
-/* CP2101_BREAK */
+/* CP210X_SET_BREAK */
 #define BREAK_ON		0x0000
 #define BREAK_OFF		0x0001
 
-/* CP2101_CONTROL */
+/* CP210X_(SET_MHS|GET_MDMSTS) */
 #define CONTROL_DTR		0x0001
 #define CONTROL_RTS		0x0002
 #define CONTROL_CTS		0x0010
@@ -189,13 +212,13 @@ static struct usb_serial_driver cp2101_device = {
 #define CONTROL_WRITE_RTS	0x0200
 
 /*
- * cp2101_get_config
- * Reads from the CP2101 configuration registers
+ * cp210x_get_config
+ * Reads from the CP210x configuration registers
  * 'size' is specified in bytes.
  * 'data' is a pointer to a pre-allocated array of integers large
  * enough to hold 'size' bytes (with 4 bytes to each integer)
  */
-static int cp2101_get_config(struct usb_serial_port *port, u8 request,
+static int cp210x_get_config(struct usb_serial_port *port, u8 request,
 		unsigned int *data, int size)
 {
 	struct usb_serial *serial = port->serial;
@@ -211,9 +234,6 @@ static int cp2101_get_config(struct usb_serial_port *port, u8 request,
 		return -ENOMEM;
 	}
 
-	/* For get requests, the request number must be incremented */
-	request++;
-
 	/* Issue the request, attempting to read 'size' bytes */
 	result = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
 				request, REQTYPE_DEVICE_TO_HOST, 0x0000,
@@ -236,12 +256,12 @@ static int cp2101_get_config(struct usb_serial_port *port, u8 request,
 }
 
 /*
- * cp2101_set_config
- * Writes to the CP2101 configuration registers
+ * cp210x_set_config
+ * Writes to the CP210x configuration registers
  * Values less than 16 bits wide are sent directly
  * 'size' is specified in bytes.
  */
-static int cp2101_set_config(struct usb_serial_port *port, u8 request,
+static int cp210x_set_config(struct usb_serial_port *port, u8 request,
 		unsigned int *data, int size)
 {
 	struct usb_serial *serial = port->serial;
@@ -292,21 +312,21 @@ static int cp2101_set_config(struct usb_serial_port *port, u8 request,
 }
 
 /*
- * cp2101_set_config_single
- * Convenience function for calling cp2101_set_config on single data values
+ * cp210x_set_config_single
+ * Convenience function for calling cp210x_set_config on single data values
  * without requiring an integer pointer
  */
-static inline int cp2101_set_config_single(struct usb_serial_port *port,
+static inline int cp210x_set_config_single(struct usb_serial_port *port,
 		u8 request, unsigned int data)
 {
-	return cp2101_set_config(port, request, &data, 2);
+	return cp210x_set_config(port, request, &data, 2);
 }
 
 /*
- * cp2101_quantise_baudrate
+ * cp210x_quantise_baudrate
  * Quantises the baud rate as per AN205 Table 1
  */
-static unsigned int cp2101_quantise_baudrate(unsigned int baud) {
+static unsigned int cp210x_quantise_baudrate(unsigned int baud) {
 	if      (baud <= 56)       baud = 0;
 	else if (baud <= 300)      baud = 300;
 	else if (baud <= 600)      baud = 600;
@@ -343,7 +363,7 @@ static unsigned int cp2101_quantise_baudrate(unsigned int baud) {
 	return baud;
 }
 
-static int cp2101_open(struct tty_struct *tty, struct usb_serial_port *port,
+static int cp210x_open(struct tty_struct *tty, struct usb_serial_port *port,
 				struct file *filp)
 {
 	struct usb_serial *serial = port->serial;
@@ -351,7 +371,7 @@ static int cp2101_open(struct tty_struct *tty, struct usb_serial_port *port,
 
 	dbg("%s - port %d", __func__, port->number);
 
-	if (cp2101_set_config_single(port, CP2101_UART, UART_ENABLE)) {
+	if (cp210x_set_config_single(port, CP210X_IFC_ENABLE, UART_ENABLE)) {
 		dev_err(&port->dev, "%s - Unable to enable UART\n",
 				__func__);
 		return -EPROTO;
@@ -373,17 +393,17 @@ static int cp2101_open(struct tty_struct *tty, struct usb_serial_port *port,
 	}
 
 	/* Configure the termios structure */
-	cp2101_get_termios(tty, port);
+	cp210x_get_termios(tty, port);
 
 	/* Set the DTR and RTS pins low */
-	cp2101_tiocmset_port(tty ? (struct usb_serial_port *) tty->driver_data
+	cp210x_tiocmset_port(tty ? (struct usb_serial_port *) tty->driver_data
 			: port,
 		NULL, TIOCM_DTR | TIOCM_RTS, 0);
 
 	return 0;
 }
 
-static void cp2101_cleanup(struct usb_serial_port *port)
+static void cp210x_cleanup(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
 
@@ -398,8 +418,7 @@ static void cp2101_cleanup(struct usb_serial_port *port)
 	}
 }
 
-static void cp2101_close(struct tty_struct *tty, struct usb_serial_port *port,
-					struct file *filp)
+static void cp210x_close(struct usb_serial_port *port)
 {
 	dbg("%s - port %d", __func__, port->number);
 
@@ -410,23 +429,23 @@ static void cp2101_close(struct tty_struct *tty, struct usb_serial_port *port,
 
 	mutex_lock(&port->serial->disc_mutex);
 	if (!port->serial->disconnected)
-		cp2101_set_config_single(port, CP2101_UART, UART_DISABLE);
+		cp210x_set_config_single(port, CP210X_IFC_ENABLE, UART_DISABLE);
 	mutex_unlock(&port->serial->disc_mutex);
 }
 
 /*
- * cp2101_get_termios
+ * cp210x_get_termios
  * Reads the baud rate, data bits, parity, stop bits and flow control mode
  * from the device, corrects any unsupported values, and configures the
  * termios structure to reflect the state of the device
  */
-static void cp2101_get_termios(struct tty_struct *tty,
+static void cp210x_get_termios(struct tty_struct *tty,
 	struct usb_serial_port *port)
 {
 	unsigned int baud;
 
 	if (tty) {
-		cp2101_get_termios_port(tty->driver_data,
+		cp210x_get_termios_port(tty->driver_data,
 			&tty->termios->c_cflag, &baud);
 		tty_encode_baud_rate(tty, baud, baud);
 	}
@@ -434,15 +453,15 @@ static void cp2101_get_termios(struct tty_struct *tty,
 	else {
 		unsigned int cflag;
 		cflag = 0;
-		cp2101_get_termios_port(port, &cflag, &baud);
+		cp210x_get_termios_port(port, &cflag, &baud);
 	}
 }
 
 /*
- * cp2101_get_termios_port
- * This is the heart of cp2101_get_termios which always uses a &usb_serial_port.
+ * cp210x_get_termios_port
+ * This is the heart of cp210x_get_termios which always uses a &usb_serial_port.
  */
-static void cp2101_get_termios_port(struct usb_serial_port *port,
+static void cp210x_get_termios_port(struct usb_serial_port *port,
 	unsigned int *cflagp, unsigned int *baudp)
 {
 	unsigned int cflag, modem_ctl[4];
@@ -451,17 +470,17 @@ static void cp2101_get_termios_port(struct usb_serial_port *port,
 
 	dbg("%s - port %d", __func__, port->number);
 
-	cp2101_get_config(port, CP2101_BAUDRATE, &baud, 2);
+	cp210x_get_config(port, CP210X_GET_BAUDDIV, &baud, 2);
 	/* Convert to baudrate */
 	if (baud)
-		baud = cp2101_quantise_baudrate((BAUD_RATE_GEN_FREQ + baud/2)/ baud);
+		baud = cp210x_quantise_baudrate((BAUD_RATE_GEN_FREQ + baud/2)/ baud);
 
 	dbg("%s - baud rate = %d", __func__, baud);
 	*baudp = baud;
 
 	cflag = *cflagp;
 
-	cp2101_get_config(port, CP2101_BITS, &bits, 2);
+	cp210x_get_config(port, CP210X_GET_LINE_CTL, &bits, 2);
 	cflag &= ~CSIZE;
 	switch (bits & BITS_DATA_MASK) {
 	case BITS_DATA_5:
@@ -486,14 +505,14 @@ static void cp2101_get_termios_port(struct usb_serial_port *port,
 		cflag |= CS8;
 		bits &= ~BITS_DATA_MASK;
 		bits |= BITS_DATA_8;
-		cp2101_set_config(port, CP2101_BITS, &bits, 2);
+		cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
 		break;
 	default:
 		dbg("%s - Unknown number of data bits, using 8", __func__);
 		cflag |= CS8;
 		bits &= ~BITS_DATA_MASK;
 		bits |= BITS_DATA_8;
-		cp2101_set_config(port, CP2101_BITS, &bits, 2);
+		cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
 		break;
 	}
 
@@ -516,20 +535,20 @@ static void cp2101_get_termios_port(struct usb_serial_port *port,
 				__func__);
 		cflag &= ~PARENB;
 		bits &= ~BITS_PARITY_MASK;
-		cp2101_set_config(port, CP2101_BITS, &bits, 2);
+		cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
 		break;
 	case BITS_PARITY_SPACE:
 		dbg("%s - parity = SPACE (not supported, disabling parity)",
 				__func__);
 		cflag &= ~PARENB;
 		bits &= ~BITS_PARITY_MASK;
-		cp2101_set_config(port, CP2101_BITS, &bits, 2);
+		cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
 		break;
 	default:
 		dbg("%s - Unknown parity mode, disabling parity", __func__);
 		cflag &= ~PARENB;
 		bits &= ~BITS_PARITY_MASK;
-		cp2101_set_config(port, CP2101_BITS, &bits, 2);
+		cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
 		break;
 	}
 
@@ -542,7 +561,7 @@ static void cp2101_get_termios_port(struct usb_serial_port *port,
 		dbg("%s - stop bits = 1.5 (not supported, using 1 stop bit)",
 								__func__);
 		bits &= ~BITS_STOP_MASK;
-		cp2101_set_config(port, CP2101_BITS, &bits, 2);
+		cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
 		break;
 	case BITS_STOP_2:
 		dbg("%s - stop bits = 2", __func__);
@@ -552,11 +571,11 @@ static void cp2101_get_termios_port(struct usb_serial_port *port,
 		dbg("%s - Unknown number of stop bits, using 1 stop bit",
 								__func__);
 		bits &= ~BITS_STOP_MASK;
-		cp2101_set_config(port, CP2101_BITS, &bits, 2);
+		cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2);
 		break;
 	}
 
-	cp2101_get_config(port, CP2101_MODEMCTL, modem_ctl, 16);
+	cp210x_get_config(port, CP210X_GET_FLOW, modem_ctl, 16);
 	if (modem_ctl[0] & 0x0008) {
 		dbg("%s - flow control = CRTSCTS", __func__);
 		cflag |= CRTSCTS;
@@ -568,7 +587,7 @@ static void cp2101_get_termios_port(struct usb_serial_port *port,
 	*cflagp = cflag;
 }
 
-static void cp2101_set_termios(struct tty_struct *tty,
+static void cp210x_set_termios(struct tty_struct *tty,
 		struct usb_serial_port *port, struct ktermios *old_termios)
 {
 	unsigned int cflag, old_cflag;
@@ -583,13 +602,13 @@ static void cp2101_set_termios(struct tty_struct *tty,
 	tty->termios->c_cflag &= ~CMSPAR;
 	cflag = tty->termios->c_cflag;
 	old_cflag = old_termios->c_cflag;
-	baud = cp2101_quantise_baudrate(tty_get_baud_rate(tty));
+	baud = cp210x_quantise_baudrate(tty_get_baud_rate(tty));
 
 	/* If the baud rate is to be updated*/
 	if (baud != tty_termios_baud_rate(old_termios) && baud != 0) {
 		dbg("%s - Setting baud rate to %d baud", __func__,
 				baud);
-		if (cp2101_set_config_single(port, CP2101_BAUDRATE,
+		if (cp210x_set_config_single(port, CP210X_SET_BAUDDIV,
 					((BAUD_RATE_GEN_FREQ + baud/2) / baud))) {
 			dbg("Baud rate requested not supported by device\n");
 			baud = tty_termios_baud_rate(old_termios);
@@ -600,7 +619,7 @@ static void cp2101_set_termios(struct tty_struct *tty,
 
 	/* If the number of data bits is to be updated */
 	if ((cflag & CSIZE) != (old_cflag & CSIZE)) {
-		cp2101_get_config(port, CP2101_BITS, &bits, 2);
+		cp210x_get_config(port, CP210X_GET_LINE_CTL, &bits, 2);
 		bits &= ~BITS_DATA_MASK;
 		switch (cflag & CSIZE) {
 		case CS5:
@@ -624,19 +643,19 @@ static void cp2101_set_termios(struct tty_struct *tty,
 			dbg("%s - data bits = 9", __func__);
 			break;*/
 		default:
-			dbg("cp2101 driver does not "
+			dbg("cp210x driver does not "
 					"support the number of bits requested,"
 					" using 8 bit mode\n");
 				bits |= BITS_DATA_8;
 				break;
 		}
-		if (cp2101_set_config(port, CP2101_BITS, &bits, 2))
+		if (cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2))
 			dbg("Number of data bits requested "
 					"not supported by device\n");
 	}
 
 	if ((cflag & (PARENB|PARODD)) != (old_cflag & (PARENB|PARODD))) {
-		cp2101_get_config(port, CP2101_BITS, &bits, 2);
+		cp210x_get_config(port, CP210X_GET_LINE_CTL, &bits, 2);
 		bits &= ~BITS_PARITY_MASK;
 		if (cflag & PARENB) {
 			if (cflag & PARODD) {
@@ -647,13 +666,13 @@ static void cp2101_set_termios(struct tty_struct *tty,
 				dbg("%s - parity = EVEN", __func__);
 			}
 		}
-		if (cp2101_set_config(port, CP2101_BITS, &bits, 2))
+		if (cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2))
 			dbg("Parity mode not supported "
 					"by device\n");
 	}
 
 	if ((cflag & CSTOPB) != (old_cflag & CSTOPB)) {
-		cp2101_get_config(port, CP2101_BITS, &bits, 2);
+		cp210x_get_config(port, CP210X_GET_LINE_CTL, &bits, 2);
 		bits &= ~BITS_STOP_MASK;
 		if (cflag & CSTOPB) {
 			bits |= BITS_STOP_2;
@@ -662,13 +681,13 @@ static void cp2101_set_termios(struct tty_struct *tty,
 			bits |= BITS_STOP_1;
 			dbg("%s - stop bits = 1", __func__);
 		}
-		if (cp2101_set_config(port, CP2101_BITS, &bits, 2))
+		if (cp210x_set_config(port, CP210X_SET_LINE_CTL, &bits, 2))
 			dbg("Number of stop bits requested "
 					"not supported by device\n");
 	}
 
 	if ((cflag & CRTSCTS) != (old_cflag & CRTSCTS)) {
-		cp2101_get_config(port, CP2101_MODEMCTL, modem_ctl, 16);
+		cp210x_get_config(port, CP210X_GET_FLOW, modem_ctl, 16);
 		dbg("%s - read modem controls = 0x%.4x 0x%.4x 0x%.4x 0x%.4x",
 				__func__, modem_ctl[0], modem_ctl[1],
 				modem_ctl[2], modem_ctl[3]);
@@ -688,19 +707,19 @@ static void cp2101_set_termios(struct tty_struct *tty,
 		dbg("%s - write modem controls = 0x%.4x 0x%.4x 0x%.4x 0x%.4x",
 				__func__, modem_ctl[0], modem_ctl[1],
 				modem_ctl[2], modem_ctl[3]);
-		cp2101_set_config(port, CP2101_MODEMCTL, modem_ctl, 16);
+		cp210x_set_config(port, CP210X_SET_FLOW, modem_ctl, 16);
 	}
 
 }
 
-static int cp2101_tiocmset (struct tty_struct *tty, struct file *file,
+static int cp210x_tiocmset (struct tty_struct *tty, struct file *file,
 		unsigned int set, unsigned int clear)
 {
 	struct usb_serial_port *port = tty->driver_data;
-	return cp2101_tiocmset_port(port, file, set, clear);
+	return cp210x_tiocmset_port(port, file, set, clear);
 }
 
-static int cp2101_tiocmset_port(struct usb_serial_port *port, struct file *file,
+static int cp210x_tiocmset_port(struct usb_serial_port *port, struct file *file,
 		unsigned int set, unsigned int clear)
 {
 	unsigned int control = 0;
@@ -726,10 +745,10 @@ static int cp2101_tiocmset_port(struct usb_serial_port *port, struct file *file,
 
 	dbg("%s - control = 0x%.4x", __func__, control);
 
-	return cp2101_set_config(port, CP2101_CONTROL, &control, 2);
+	return cp210x_set_config(port, CP210X_SET_MHS, &control, 2);
 }
 
-static int cp2101_tiocmget (struct tty_struct *tty, struct file *file)
+static int cp210x_tiocmget (struct tty_struct *tty, struct file *file)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	unsigned int control;
@@ -737,7 +756,7 @@ static int cp2101_tiocmget (struct tty_struct *tty, struct file *file)
 
 	dbg("%s - port %d", __func__, port->number);
 
-	cp2101_get_config(port, CP2101_CONTROL, &control, 1);
+	cp210x_get_config(port, CP210X_GET_MDMSTS, &control, 1);
 
 	result = ((control & CONTROL_DTR) ? TIOCM_DTR : 0)
 		|((control & CONTROL_RTS) ? TIOCM_RTS : 0)
@@ -751,7 +770,7 @@ static int cp2101_tiocmget (struct tty_struct *tty, struct file *file)
 	return result;
 }
 
-static void cp2101_break_ctl (struct tty_struct *tty, int break_state)
+static void cp210x_break_ctl (struct tty_struct *tty, int break_state)
 {
 	struct usb_serial_port *port = tty->driver_data;
 	unsigned int state;
@@ -763,17 +782,17 @@ static void cp2101_break_ctl (struct tty_struct *tty, int break_state)
 		state = BREAK_ON;
 	dbg("%s - turning break %s", __func__,
 			state == BREAK_OFF ? "off" : "on");
-	cp2101_set_config(port, CP2101_BREAK, &state, 2);
+	cp210x_set_config(port, CP210X_SET_BREAK, &state, 2);
 }
 
-static int cp2101_startup(struct usb_serial *serial)
+static int cp210x_startup(struct usb_serial *serial)
 {
-	/* CP2101 buffers behave strangely unless device is reset */
+	/* cp210x buffers behave strangely unless device is reset */
 	usb_reset_device(serial->dev);
 	return 0;
 }
 
-static void cp2101_shutdown(struct usb_serial *serial)
+static void cp210x_shutdown(struct usb_serial *serial)
 {
 	int i;
 
@@ -781,21 +800,21 @@ static void cp2101_shutdown(struct usb_serial *serial)
 
 	/* Stop reads and writes on all ports */
 	for (i = 0; i < serial->num_ports; ++i)
-		cp2101_cleanup(serial->port[i]);
+		cp210x_cleanup(serial->port[i]);
 }
 
-static int __init cp2101_init(void)
+static int __init cp210x_init(void)
 {
 	int retval;
 
-	retval = usb_serial_register(&cp2101_device);
+	retval = usb_serial_register(&cp210x_device);
 	if (retval)
 		return retval; /* Failed to register */
 
-	retval = usb_register(&cp2101_driver);
+	retval = usb_register(&cp210x_driver);
 	if (retval) {
 		/* Failed to register */
-		usb_serial_deregister(&cp2101_device);
+		usb_serial_deregister(&cp210x_device);
 		return retval;
 	}
 
@@ -805,14 +824,14 @@ static int __init cp2101_init(void)
 	return 0;
 }
 
-static void __exit cp2101_exit(void)
+static void __exit cp210x_exit(void)
 {
-	usb_deregister(&cp2101_driver);
-	usb_serial_deregister(&cp2101_device);
+	usb_deregister(&cp210x_driver);
+	usb_serial_deregister(&cp210x_device);
 }
 
-module_init(cp2101_init);
-module_exit(cp2101_exit);
+module_init(cp210x_init);
+module_exit(cp210x_exit);
 
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_VERSION(DRIVER_VERSION);
diff --git a/drivers/usb/serial/cyberjack.c b/drivers/usb/serial/cyberjack.c
index dd501bb63ed6..933ba913e66c 100644
--- a/drivers/usb/serial/cyberjack.c
+++ b/drivers/usb/serial/cyberjack.c
@@ -61,8 +61,7 @@ static int cyberjack_startup(struct usb_serial *serial);
 static void cyberjack_shutdown(struct usb_serial *serial);
 static int  cyberjack_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void cyberjack_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+static void cyberjack_close(struct usb_serial_port *port);
 static int cyberjack_write(struct tty_struct *tty,
 	struct usb_serial_port *port, const unsigned char *buf, int count);
 static int cyberjack_write_room(struct tty_struct *tty);
@@ -185,8 +184,7 @@ static int  cyberjack_open(struct tty_struct *tty,
 	return result;
 }
 
-static void cyberjack_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void cyberjack_close(struct usb_serial_port *port)
 {
 	dbg("%s - port %d", __func__, port->number);
 
diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c
index e568710b263f..669f93848539 100644
--- a/drivers/usb/serial/cypress_m8.c
+++ b/drivers/usb/serial/cypress_m8.c
@@ -174,8 +174,8 @@ static int  cypress_ca42v2_startup(struct usb_serial *serial);
 static void cypress_shutdown(struct usb_serial *serial);
 static int  cypress_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void cypress_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+static void cypress_close(struct usb_serial_port *port);
+static void cypress_dtr_rts(struct usb_serial_port *port, int on);
 static int  cypress_write(struct tty_struct *tty, struct usb_serial_port *port,
 			const unsigned char *buf, int count);
 static void cypress_send(struct usb_serial_port *port);
@@ -218,6 +218,7 @@ static struct usb_serial_driver cypress_earthmate_device = {
 	.shutdown =			cypress_shutdown,
 	.open =				cypress_open,
 	.close =			cypress_close,
+	.dtr_rts =			cypress_dtr_rts,
 	.write =			cypress_write,
 	.write_room =			cypress_write_room,
 	.ioctl =			cypress_ioctl,
@@ -244,6 +245,7 @@ static struct usb_serial_driver cypress_hidcom_device = {
 	.shutdown =			cypress_shutdown,
 	.open =				cypress_open,
 	.close =			cypress_close,
+	.dtr_rts =			cypress_dtr_rts,
 	.write =			cypress_write,
 	.write_room =			cypress_write_room,
 	.ioctl =			cypress_ioctl,
@@ -270,6 +272,7 @@ static struct usb_serial_driver cypress_ca42v2_device = {
 	.shutdown =			cypress_shutdown,
 	.open =				cypress_open,
 	.close =			cypress_close,
+	.dtr_rts =			cypress_dtr_rts,
 	.write =			cypress_write,
 	.write_room =			cypress_write_room,
 	.ioctl =			cypress_ioctl,
@@ -656,11 +659,7 @@ static int cypress_open(struct tty_struct *tty,
 	priv->rx_flags = 0;
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	/* raise both lines and set termios */
-	spin_lock_irqsave(&priv->lock, flags);
-	priv->line_control = CONTROL_DTR | CONTROL_RTS;
-	priv->cmd_ctrl = 1;
-	spin_unlock_irqrestore(&priv->lock, flags);
+	/* Set termios */
 	result = cypress_write(tty, port, NULL, 0);
 
 	if (result) {
@@ -694,76 +693,42 @@ static int cypress_open(struct tty_struct *tty,
 							__func__, result);
 		cypress_set_dead(port);
 	}
-
+	port->port.drain_delay = 256;
 	return result;
 } /* cypress_open */
 
-
-static void cypress_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void cypress_dtr_rts(struct usb_serial_port *port, int on)
+{
+	struct cypress_private *priv = usb_get_serial_port_data(port);
+	/* drop dtr and rts */
+	priv = usb_get_serial_port_data(port);
+	spin_lock_irq(&priv->lock);
+	if (on == 0)
+		priv->line_control = 0;
+	else 
+		priv->line_control = CONTROL_DTR | CONTROL_RTS;
+	priv->cmd_ctrl = 1;
+	spin_unlock_irq(&priv->lock);
+	cypress_write(NULL, port, NULL, 0);
+}
+
+static void cypress_close(struct usb_serial_port *port)
 {
 	struct cypress_private *priv = usb_get_serial_port_data(port);
-	unsigned int c_cflag;
-	int bps;
-	long timeout;
-	wait_queue_t wait;
 
 	dbg("%s - port %d", __func__, port->number);
 
-	/* wait for data to drain from buffer */
-	spin_lock_irq(&priv->lock);
-	timeout = CYPRESS_CLOSING_WAIT;
-	init_waitqueue_entry(&wait, current);
-	add_wait_queue(&tty->write_wait, &wait);
-	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (cypress_buf_data_avail(priv->buf) == 0
-		|| timeout == 0 || signal_pending(current)
-		/* without mutex, allowed due to harmless failure mode */
-		|| port->serial->disconnected)
-			break;
-		spin_unlock_irq(&priv->lock);
-		timeout = schedule_timeout(timeout);
-		spin_lock_irq(&priv->lock);
-	}
-	set_current_state(TASK_RUNNING);
-	remove_wait_queue(&tty->write_wait, &wait);
-	/* clear out any remaining data in the buffer */
-	cypress_buf_clear(priv->buf);
-	spin_unlock_irq(&priv->lock);
-
 	/* writing is potentially harmful, lock must be taken */
 	mutex_lock(&port->serial->disc_mutex);
 	if (port->serial->disconnected) {
 		mutex_unlock(&port->serial->disc_mutex);
 		return;
 	}
-	/* wait for characters to drain from device */
-	if (tty) {
-		bps = tty_get_baud_rate(tty);
-		if (bps > 1200)
-			timeout = max((HZ * 2560) / bps, HZ / 10);
-		else
-			timeout = 2 * HZ;
-		schedule_timeout_interruptible(timeout);
-	}
-
+	cypress_buf_clear(priv->buf);
 	dbg("%s - stopping urbs", __func__);
 	usb_kill_urb(port->interrupt_in_urb);
 	usb_kill_urb(port->interrupt_out_urb);
 
-	if (tty) {
-		c_cflag = tty->termios->c_cflag;
-		if (c_cflag & HUPCL) {
-			/* drop dtr and rts */
-			priv = usb_get_serial_port_data(port);
-			spin_lock_irq(&priv->lock);
-			priv->line_control = 0;
-			priv->cmd_ctrl = 1;
-			spin_unlock_irq(&priv->lock);
-			cypress_write(tty, port, NULL, 0);
-		}
-	}
 
 	if (stats)
 		dev_info(&port->dev, "Statistics: %d Bytes In | %d Bytes Out | %d Commands Issued\n",
diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index 38ba4ea8b6bf..30f5140eff03 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -422,7 +422,6 @@ struct digi_port {
 	int dp_throttled;
 	int dp_throttle_restart;
 	wait_queue_head_t dp_flush_wait;
-	int dp_in_close;			/* close in progress */
 	wait_queue_head_t dp_close_wait;	/* wait queue for close */
 	struct work_struct dp_wakeup_work;
 	struct usb_serial_port *dp_port;
@@ -456,8 +455,9 @@ static int digi_write_room(struct tty_struct *tty);
 static int digi_chars_in_buffer(struct tty_struct *tty);
 static int digi_open(struct tty_struct *tty, struct usb_serial_port *port,
 	struct file *filp);
-static void digi_close(struct tty_struct *tty, struct usb_serial_port *port,
-	struct file *filp);
+static void digi_close(struct usb_serial_port *port);
+static int digi_carrier_raised(struct usb_serial_port *port);
+static void digi_dtr_rts(struct usb_serial_port *port, int on);
 static int digi_startup_device(struct usb_serial *serial);
 static int digi_startup(struct usb_serial *serial);
 static void digi_shutdown(struct usb_serial *serial);
@@ -510,6 +510,8 @@ static struct usb_serial_driver digi_acceleport_2_device = {
 	.num_ports =			3,
 	.open =				digi_open,
 	.close =			digi_close,
+	.dtr_rts =			digi_dtr_rts,
+	.carrier_raised =		digi_carrier_raised,
 	.write =			digi_write,
 	.write_room =			digi_write_room,
 	.write_bulk_callback = 		digi_write_bulk_callback,
@@ -1328,6 +1330,19 @@ static int digi_chars_in_buffer(struct tty_struct *tty)
 
 }
 
+static void digi_dtr_rts(struct usb_serial_port *port, int on)
+{
+	/* Adjust DTR and RTS */
+	digi_set_modem_signals(port, on * (TIOCM_DTR|TIOCM_RTS), 1);
+}
+
+static int digi_carrier_raised(struct usb_serial_port *port)
+{
+	struct digi_port *priv = usb_get_serial_port_data(port);
+	if (priv->dp_modem_signals & TIOCM_CD)
+		return 1;
+	return 0;
+}
 
 static int digi_open(struct tty_struct *tty, struct usb_serial_port *port,
 				struct file *filp)
@@ -1336,7 +1351,6 @@ static int digi_open(struct tty_struct *tty, struct usb_serial_port *port,
 	unsigned char buf[32];
 	struct digi_port *priv = usb_get_serial_port_data(port);
 	struct ktermios not_termios;
-	unsigned long flags = 0;
 
 	dbg("digi_open: TOP: port=%d, open_count=%d",
 		priv->dp_port_num, port->port.count);
@@ -1345,26 +1359,6 @@ static int digi_open(struct tty_struct *tty, struct usb_serial_port *port,
 	if (digi_startup_device(port->serial) != 0)
 		return -ENXIO;
 
-	spin_lock_irqsave(&priv->dp_port_lock, flags);
-
-	/* don't wait on a close in progress for non-blocking opens */
-	if (priv->dp_in_close && (filp->f_flags&(O_NDELAY|O_NONBLOCK)) == 0) {
-		spin_unlock_irqrestore(&priv->dp_port_lock, flags);
-		return -EAGAIN;
-	}
-
-	/* wait for a close in progress to finish */
-	while (priv->dp_in_close) {
-		cond_wait_interruptible_timeout_irqrestore(
-			&priv->dp_close_wait, DIGI_RETRY_TIMEOUT,
-			&priv->dp_port_lock, flags);
-		if (signal_pending(current))
-			return -EINTR;
-		spin_lock_irqsave(&priv->dp_port_lock, flags);
-	}
-
-	spin_unlock_irqrestore(&priv->dp_port_lock, flags);
-
 	/* read modem signals automatically whenever they change */
 	buf[0] = DIGI_CMD_READ_INPUT_SIGNALS;
 	buf[1] = priv->dp_port_num;
@@ -1387,16 +1381,11 @@ static int digi_open(struct tty_struct *tty, struct usb_serial_port *port,
 		not_termios.c_iflag = ~tty->termios->c_iflag;
 		digi_set_termios(tty, port, &not_termios);
 	}
-
-	/* set DTR and RTS */
-	digi_set_modem_signals(port, TIOCM_DTR|TIOCM_RTS, 1);
-
 	return 0;
 }
 
 
-static void digi_close(struct tty_struct *tty, struct usb_serial_port *port,
-				struct file *filp)
+static void digi_close(struct usb_serial_port *port)
 {
 	DEFINE_WAIT(wait);
 	int ret;
@@ -1411,28 +1400,9 @@ static void digi_close(struct tty_struct *tty, struct usb_serial_port *port,
 	if (port->serial->disconnected)
 		goto exit;
 
-	/* do cleanup only after final close on this port */
-	spin_lock_irq(&priv->dp_port_lock);
-	priv->dp_in_close = 1;
-	spin_unlock_irq(&priv->dp_port_lock);
-
-	/* tell line discipline to process only XON/XOFF */
-	tty->closing = 1;
-
-	/* wait for output to drain */
-	if ((filp->f_flags&(O_NDELAY|O_NONBLOCK)) == 0)
-		tty_wait_until_sent(tty, DIGI_CLOSE_TIMEOUT);
-
-	/* flush driver and line discipline buffers */
-	tty_driver_flush_buffer(tty);
-	tty_ldisc_flush(tty);
-
 	if (port->serial->dev) {
-		/* wait for transmit idle */
-		if ((filp->f_flags&(O_NDELAY|O_NONBLOCK)) == 0)
-			digi_transmit_idle(port, DIGI_CLOSE_TIMEOUT);
-		/* drop DTR and RTS */
-		digi_set_modem_signals(port, 0, 0);
+		/* FIXME: Transmit idle belongs in the wait_unti_sent path */
+		digi_transmit_idle(port, DIGI_CLOSE_TIMEOUT);
 
 		/* disable input flow control */
 		buf[0] = DIGI_CMD_SET_INPUT_FLOW_CONTROL;
@@ -1477,11 +1447,9 @@ static void digi_close(struct tty_struct *tty, struct usb_serial_port *port,
 		/* shutdown any outstanding bulk writes */
 		usb_kill_urb(port->write_urb);
 	}
-	tty->closing = 0;
 exit:
 	spin_lock_irq(&priv->dp_port_lock);
 	priv->dp_write_urb_in_use = 0;
-	priv->dp_in_close = 0;
 	wake_up_interruptible(&priv->dp_close_wait);
 	spin_unlock_irq(&priv->dp_port_lock);
 	mutex_unlock(&port->serial->disc_mutex);
@@ -1560,7 +1528,6 @@ static int digi_startup(struct usb_serial *serial)
 		priv->dp_throttled = 0;
 		priv->dp_throttle_restart = 0;
 		init_waitqueue_head(&priv->dp_flush_wait);
-		priv->dp_in_close = 0;
 		init_waitqueue_head(&priv->dp_close_wait);
 		INIT_WORK(&priv->dp_wakeup_work, digi_wakeup_write_lock);
 		priv->dp_port = serial->port[i];
diff --git a/drivers/usb/serial/empeg.c b/drivers/usb/serial/empeg.c
index c709ec474a80..2b141ccb0cd9 100644
--- a/drivers/usb/serial/empeg.c
+++ b/drivers/usb/serial/empeg.c
@@ -81,8 +81,7 @@ static int debug;
 /* function prototypes for an empeg-car player */
 static int  empeg_open(struct tty_struct *tty, struct usb_serial_port *port,
 						struct file *filp);
-static void empeg_close(struct tty_struct *tty, struct usb_serial_port *port,
-						struct file *filp);
+static void empeg_close(struct usb_serial_port *port);
 static int  empeg_write(struct tty_struct *tty, struct usb_serial_port *port,
 						const unsigned char *buf,
 						int count);
@@ -181,8 +180,7 @@ static int empeg_open(struct tty_struct *tty, struct usb_serial_port *port,
 }
 
 
-static void empeg_close(struct tty_struct *tty, struct usb_serial_port *port,
-				struct file *filp)
+static void empeg_close(struct usb_serial_port *port)
 {
 	dbg("%s - port %d", __func__, port->number);
 
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index d9fcdaedf389..683304d60615 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -89,6 +89,7 @@ struct ftdi_private {
 	int force_rtscts;	/* if non-zero, force RTS-CTS to always
 				   be enabled */
 
+	unsigned int latency;		/* latency setting in use */
 	spinlock_t tx_lock;	/* spinlock for transmit state */
 	unsigned long tx_bytes;
 	unsigned long tx_outstanding_bytes;
@@ -719,8 +720,8 @@ static int  ftdi_sio_port_probe(struct usb_serial_port *port);
 static int  ftdi_sio_port_remove(struct usb_serial_port *port);
 static int  ftdi_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void ftdi_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+static void ftdi_close(struct usb_serial_port *port);
+static void ftdi_dtr_rts(struct usb_serial_port *port, int on);
 static int  ftdi_write(struct tty_struct *tty, struct usb_serial_port *port,
 			const unsigned char *buf, int count);
 static int  ftdi_write_room(struct tty_struct *tty);
@@ -758,6 +759,7 @@ static struct usb_serial_driver ftdi_sio_device = {
 	.port_remove =		ftdi_sio_port_remove,
 	.open =			ftdi_open,
 	.close =		ftdi_close,
+	.dtr_rts =		ftdi_dtr_rts,
 	.throttle =		ftdi_throttle,
 	.unthrottle =		ftdi_unthrottle,
 	.write =		ftdi_write,
@@ -1037,7 +1039,54 @@ static int change_speed(struct tty_struct *tty, struct usb_serial_port *port)
 	return rv;
 }
 
+static int write_latency_timer(struct usb_serial_port *port)
+{
+	struct ftdi_private *priv = usb_get_serial_port_data(port);
+	struct usb_device *udev = port->serial->dev;
+	char buf[1];
+	int rv = 0;
+	int l = priv->latency;
 
+	if (priv->flags & ASYNC_LOW_LATENCY)
+		l = 1;
+
+	dbg("%s: setting latency timer = %i", __func__, l);
+
+	rv = usb_control_msg(udev,
+			     usb_sndctrlpipe(udev, 0),
+			     FTDI_SIO_SET_LATENCY_TIMER_REQUEST,
+			     FTDI_SIO_SET_LATENCY_TIMER_REQUEST_TYPE,
+			     l, priv->interface,
+			     buf, 0, WDR_TIMEOUT);
+
+	if (rv < 0)
+		dev_err(&port->dev, "Unable to write latency timer: %i\n", rv);
+	return rv;
+}
+
+static int read_latency_timer(struct usb_serial_port *port)
+{
+	struct ftdi_private *priv = usb_get_serial_port_data(port);
+	struct usb_device *udev = port->serial->dev;
+	unsigned short latency = 0;
+	int rv = 0;
+
+
+	dbg("%s", __func__);
+
+	rv = usb_control_msg(udev,
+			     usb_rcvctrlpipe(udev, 0),
+			     FTDI_SIO_GET_LATENCY_TIMER_REQUEST,
+			     FTDI_SIO_GET_LATENCY_TIMER_REQUEST_TYPE,
+			     0, priv->interface,
+			     (char *) &latency, 1, WDR_TIMEOUT);
+
+	if (rv < 0) {
+		dev_err(&port->dev, "Unable to read latency timer: %i\n", rv);
+		return -EIO;
+	}
+	return latency;
+}
 
 static int get_serial_info(struct usb_serial_port *port,
 				struct serial_struct __user *retinfo)
@@ -1097,6 +1146,7 @@ static int set_serial_info(struct tty_struct *tty,
 	priv->custom_divisor = new_serial.custom_divisor;
 
 	tty->low_latency = (priv->flags & ASYNC_LOW_LATENCY) ? 1 : 0;
+	write_latency_timer(port);
 
 check_and_exit:
 	if ((old_priv.flags & ASYNC_SPD_MASK) !=
@@ -1192,27 +1242,13 @@ static ssize_t show_latency_timer(struct device *dev,
 {
 	struct usb_serial_port *port = to_usb_serial_port(dev);
 	struct ftdi_private *priv = usb_get_serial_port_data(port);
-	struct usb_device *udev = port->serial->dev;
-	unsigned short latency = 0;
-	int rv = 0;
-
-
-	dbg("%s", __func__);
-
-	rv = usb_control_msg(udev,
-			     usb_rcvctrlpipe(udev, 0),
-			     FTDI_SIO_GET_LATENCY_TIMER_REQUEST,
-			     FTDI_SIO_GET_LATENCY_TIMER_REQUEST_TYPE,
-			     0, priv->interface,
-			     (char *) &latency, 1, WDR_TIMEOUT);
-
-	if (rv < 0) {
-		dev_err(dev, "Unable to read latency timer: %i\n", rv);
-		return -EIO;
-	}
-	return sprintf(buf, "%i\n", latency);
+	if (priv->flags & ASYNC_LOW_LATENCY)
+		return sprintf(buf, "1\n");
+	else
+		return sprintf(buf, "%i\n", priv->latency);
 }
 
+
 /* Write a new value of the latency timer, in units of milliseconds. */
 static ssize_t store_latency_timer(struct device *dev,
 			struct device_attribute *attr, const char *valbuf,
@@ -1220,25 +1256,13 @@ static ssize_t store_latency_timer(struct device *dev,
 {
 	struct usb_serial_port *port = to_usb_serial_port(dev);
 	struct ftdi_private *priv = usb_get_serial_port_data(port);
-	struct usb_device *udev = port->serial->dev;
-	char buf[1];
 	int v = simple_strtoul(valbuf, NULL, 10);
 	int rv = 0;
 
-	dbg("%s: setting latency timer = %i", __func__, v);
-
-	rv = usb_control_msg(udev,
-			     usb_sndctrlpipe(udev, 0),
-			     FTDI_SIO_SET_LATENCY_TIMER_REQUEST,
-			     FTDI_SIO_SET_LATENCY_TIMER_REQUEST_TYPE,
-			     v, priv->interface,
-			     buf, 0, WDR_TIMEOUT);
-
-	if (rv < 0) {
-		dev_err(dev, "Unable to write latency timer: %i\n", rv);
+	priv->latency = v;
+	rv = write_latency_timer(port);
+	if (rv < 0)
 		return -EIO;
-	}
-
 	return count;
 }
 
@@ -1392,6 +1416,7 @@ static int ftdi_sio_port_probe(struct usb_serial_port *port)
 	usb_set_serial_port_data(port, priv);
 
 	ftdi_determine_type(port);
+	read_latency_timer(port);
 	create_sysfs_attrs(port);
 	return 0;
 }
@@ -1514,6 +1539,8 @@ static int ftdi_open(struct tty_struct *tty,
 	if (tty)
 		tty->low_latency = (priv->flags & ASYNC_LOW_LATENCY) ? 1 : 0;
 
+	write_latency_timer(port);
+
 	/* No error checking for this (will get errors later anyway) */
 	/* See ftdi_sio.h for description of what is reset */
 	usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
@@ -1529,11 +1556,6 @@ static int ftdi_open(struct tty_struct *tty,
 	if (tty)
 		ftdi_set_termios(tty, port, tty->termios);
 
-	/* FIXME: Flow control might be enabled, so it should be checked -
-	   we have no control of defaults! */
-	/* Turn on RTS and DTR since we are not flow controlling by default */
-	set_mctrl(port, TIOCM_DTR | TIOCM_RTS);
-
 	/* Not throttled */
 	spin_lock_irqsave(&priv->rx_lock, flags);
 	priv->rx_flags &= ~(THROTTLED | ACTUALLY_THROTTLED);
@@ -1558,6 +1580,30 @@ static int ftdi_open(struct tty_struct *tty,
 } /* ftdi_open */
 
 
+static void ftdi_dtr_rts(struct usb_serial_port *port, int on)
+{
+	struct ftdi_private *priv = usb_get_serial_port_data(port);
+	char buf[1];
+
+	mutex_lock(&port->serial->disc_mutex);
+	if (!port->serial->disconnected) {
+		/* Disable flow control */
+		if (!on && usb_control_msg(port->serial->dev,
+			    usb_sndctrlpipe(port->serial->dev, 0),
+			    FTDI_SIO_SET_FLOW_CTRL_REQUEST,
+			    FTDI_SIO_SET_FLOW_CTRL_REQUEST_TYPE,
+			    0, priv->interface, buf, 0,
+			    WDR_TIMEOUT) < 0) {
+			    dev_err(&port->dev, "error from flowcontrol urb\n");
+		}
+		/* drop RTS and DTR */
+		if (on)
+			set_mctrl(port, TIOCM_DTR | TIOCM_RTS);
+		else
+			clear_mctrl(port, TIOCM_DTR | TIOCM_RTS);
+	}
+	mutex_unlock(&port->serial->disc_mutex);
+}
 
 /*
  * usbserial:__serial_close  only calls ftdi_close if the point is open
@@ -1567,31 +1613,12 @@ static int ftdi_open(struct tty_struct *tty,
  *
  */
 
-static void ftdi_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void ftdi_close(struct usb_serial_port *port)
 { /* ftdi_close */
-	unsigned int c_cflag = tty->termios->c_cflag;
 	struct ftdi_private *priv = usb_get_serial_port_data(port);
-	char buf[1];
 
 	dbg("%s", __func__);
 
-	mutex_lock(&port->serial->disc_mutex);
-	if (c_cflag & HUPCL && !port->serial->disconnected) {
-		/* Disable flow control */
-		if (usb_control_msg(port->serial->dev,
-				    usb_sndctrlpipe(port->serial->dev, 0),
-				    FTDI_SIO_SET_FLOW_CTRL_REQUEST,
-				    FTDI_SIO_SET_FLOW_CTRL_REQUEST_TYPE,
-				    0, priv->interface, buf, 0,
-				    WDR_TIMEOUT) < 0) {
-			dev_err(&port->dev, "error from flowcontrol urb\n");
-		}
-
-		/* drop RTS and DTR */
-		clear_mctrl(port, TIOCM_DTR | TIOCM_RTS);
-	} /* Note change no line if hupcl is off */
-	mutex_unlock(&port->serial->disc_mutex);
 
 	/* cancel any scheduled reading */
 	cancel_delayed_work_sync(&priv->rx_work);
diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c
index 586d30ff450b..ee25a3fe3b09 100644
--- a/drivers/usb/serial/garmin_gps.c
+++ b/drivers/usb/serial/garmin_gps.c
@@ -993,8 +993,7 @@ static int garmin_open(struct tty_struct *tty,
 }
 
 
-static void garmin_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void garmin_close(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
 	struct garmin_data *garmin_data_p = usb_get_serial_port_data(port);
diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index 4cec9906ccf3..be82ea956720 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -184,8 +184,7 @@ int usb_serial_generic_resume(struct usb_serial *serial)
 }
 EXPORT_SYMBOL_GPL(usb_serial_generic_resume);
 
-void usb_serial_generic_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+void usb_serial_generic_close(struct usb_serial_port *port)
 {
 	dbg("%s - port %d", __func__, port->number);
 	generic_cleanup(port);
diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index fb4a73d090f6..53ef5996e33d 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -207,8 +207,7 @@ static void edge_bulk_out_cmd_callback(struct urb *urb);
 /* function prototypes for the usbserial callbacks */
 static int edge_open(struct tty_struct *tty, struct usb_serial_port *port,
 					struct file *filp);
-static void edge_close(struct tty_struct *tty, struct usb_serial_port *port,
-					struct file *filp);
+static void edge_close(struct usb_serial_port *port);
 static int edge_write(struct tty_struct *tty, struct usb_serial_port *port,
 					const unsigned char *buf, int count);
 static int edge_write_room(struct tty_struct *tty);
@@ -965,7 +964,7 @@ static int edge_open(struct tty_struct *tty,
 
 	if (!edge_port->txfifo.fifo) {
 		dbg("%s - no memory", __func__);
-		edge_close(tty, port, filp);
+		edge_close(port);
 		return -ENOMEM;
 	}
 
@@ -975,7 +974,7 @@ static int edge_open(struct tty_struct *tty,
 
 	if (!edge_port->write_urb) {
 		dbg("%s - no memory", __func__);
-		edge_close(tty, port, filp);
+		edge_close(port);
 		return -ENOMEM;
 	}
 
@@ -1099,8 +1098,7 @@ static void block_until_tx_empty(struct edgeport_port *edge_port)
  * edge_close
  *	this function is called by the tty driver when a port is closed
  *****************************************************************************/
-static void edge_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void edge_close(struct usb_serial_port *port)
 {
 	struct edgeport_serial *edge_serial;
 	struct edgeport_port *edge_port;
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index 513b25e044c1..eabf20eeb370 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -2009,8 +2009,7 @@ release_es_lock:
 	return status;
 }
 
-static void edge_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void edge_close(struct usb_serial_port *port)
 {
 	struct edgeport_serial *edge_serial;
 	struct edgeport_port *edge_port;
diff --git a/drivers/usb/serial/ipaq.c b/drivers/usb/serial/ipaq.c
index cd62825a9ac3..c610a99fa477 100644
--- a/drivers/usb/serial/ipaq.c
+++ b/drivers/usb/serial/ipaq.c
@@ -76,8 +76,7 @@ static int initial_wait;
 /* Function prototypes for an ipaq */
 static int  ipaq_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void ipaq_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+static void ipaq_close(struct usb_serial_port *port);
 static int  ipaq_calc_num_ports(struct usb_serial *serial);
 static int  ipaq_startup(struct usb_serial *serial);
 static void ipaq_shutdown(struct usb_serial *serial);
@@ -714,8 +713,7 @@ error:
 }
 
 
-static void ipaq_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void ipaq_close(struct usb_serial_port *port)
 {
 	struct ipaq_private	*priv = usb_get_serial_port_data(port);
 
diff --git a/drivers/usb/serial/ipw.c b/drivers/usb/serial/ipw.c
index da2a2b46644a..29ad038b9c8d 100644
--- a/drivers/usb/serial/ipw.c
+++ b/drivers/usb/serial/ipw.c
@@ -302,23 +302,17 @@ static int ipw_open(struct tty_struct *tty,
 	return 0;
 }
 
-static void ipw_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void ipw_dtr_rts(struct usb_serial_port *port, int on)
 {
 	struct usb_device *dev = port->serial->dev;
 	int result;
 
-	if (tty_hung_up_p(filp)) {
-		dbg("%s: tty_hung_up_p ...", __func__);
-		return;
-	}
-
 	/*--1: drop the dtr */
 	dbg("%s:dropping dtr", __func__);
 	result = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
 			 IPW_SIO_SET_PIN,
 			 USB_TYPE_VENDOR | USB_RECIP_INTERFACE | USB_DIR_OUT,
-			 IPW_PIN_CLRDTR,
+			 on ? IPW_PIN_SETDTR : IPW_PIN_CLRDTR,
 			 0,
 			 NULL,
 			 0,
@@ -332,7 +326,7 @@ static void ipw_close(struct tty_struct *tty,
 	result = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
 			 IPW_SIO_SET_PIN, USB_TYPE_VENDOR |
 			 		USB_RECIP_INTERFACE | USB_DIR_OUT,
-			 IPW_PIN_CLRRTS,
+			 on ? IPW_PIN_SETRTS : IPW_PIN_CLRRTS,
 			 0,
 			 NULL,
 			 0,
@@ -340,7 +334,12 @@ static void ipw_close(struct tty_struct *tty,
 	if (result < 0)
 		dev_err(&port->dev,
 				"dropping rts failed (error = %d)\n", result);
+}
 
+static void ipw_close(struct usb_serial_port *port)
+{
+	struct usb_device *dev = port->serial->dev;
+	int result;
 
 	/*--3: purge */
 	dbg("%s:sending purge", __func__);
@@ -461,6 +460,7 @@ static struct usb_serial_driver ipw_device = {
 	.num_ports =		1,
 	.open =			ipw_open,
 	.close =		ipw_close,
+	.dtr_rts =		ipw_dtr_rts,
 	.port_probe = 		ipw_probe,
 	.port_remove =		ipw_disconnect,
 	.write =		ipw_write,
diff --git a/drivers/usb/serial/ir-usb.c b/drivers/usb/serial/ir-usb.c
index 4e2cda93da59..66009b6b763a 100644
--- a/drivers/usb/serial/ir-usb.c
+++ b/drivers/usb/serial/ir-usb.c
@@ -88,8 +88,7 @@ static int xbof = -1;
 static int  ir_startup (struct usb_serial *serial);
 static int  ir_open(struct tty_struct *tty, struct usb_serial_port *port,
 					struct file *filep);
-static void ir_close(struct tty_struct *tty, struct usb_serial_port *port,
-					struct file *filep);
+static void ir_close(struct usb_serial_port *port);
 static int  ir_write(struct tty_struct *tty, struct usb_serial_port *port,
 					const unsigned char *buf, int count);
 static void ir_write_bulk_callback (struct urb *urb);
@@ -346,8 +345,7 @@ static int ir_open(struct tty_struct *tty,
 	return result;
 }
 
-static void ir_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file * filp)
+static void ir_close(struct usb_serial_port *port)
 {
 	dbg("%s - port %d", __func__, port->number);
 
diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c
index 4473d442b2aa..76a3cc327bb9 100644
--- a/drivers/usb/serial/iuu_phoenix.c
+++ b/drivers/usb/serial/iuu_phoenix.c
@@ -40,7 +40,7 @@ static int debug;
 /*
  * Version Information
  */
-#define DRIVER_VERSION "v0.5"
+#define DRIVER_VERSION "v0.10"
 #define DRIVER_DESC "Infinity USB Unlimited Phoenix driver"
 
 static struct usb_device_id id_table[] = {
@@ -70,7 +70,6 @@ static void read_rxcmd_callback(struct urb *urb);
 struct iuu_private {
 	spinlock_t lock;	/* store irq state */
 	wait_queue_head_t delta_msr_wait;
-	u8 line_control;
 	u8 line_status;
 	u8 termios_initialized;
 	int tiostatus;		/* store IUART SIGNAL for tiocmget call */
@@ -651,32 +650,33 @@ static int iuu_bulk_write(struct usb_serial_port *port)
 	unsigned long flags;
 	int result;
 	int i;
+	int buf_len;
 	char *buf_ptr = port->write_urb->transfer_buffer;
 	dbg("%s - enter", __func__);
 
+	spin_lock_irqsave(&priv->lock, flags);
 	*buf_ptr++ = IUU_UART_ESC;
 	*buf_ptr++ = IUU_UART_TX;
 	*buf_ptr++ = priv->writelen;
 
-	memcpy(buf_ptr, priv->writebuf,
-	       priv->writelen);
+	memcpy(buf_ptr, priv->writebuf, priv->writelen);
+	buf_len = priv->writelen;
+	priv->writelen = 0;
+	spin_unlock_irqrestore(&priv->lock, flags);
 	if (debug == 1) {
-		for (i = 0; i < priv->writelen; i++)
+		for (i = 0; i < buf_len; i++)
 			sprintf(priv->dbgbuf + i*2 ,
 				"%02X", priv->writebuf[i]);
-		priv->dbgbuf[priv->writelen+i*2] = 0;
+		priv->dbgbuf[buf_len+i*2] = 0;
 		dbg("%s - writing %i chars : %s", __func__,
-		    priv->writelen, priv->dbgbuf);
+		    buf_len, priv->dbgbuf);
 	}
 	usb_fill_bulk_urb(port->write_urb, port->serial->dev,
 			  usb_sndbulkpipe(port->serial->dev,
 					  port->bulk_out_endpointAddress),
-			  port->write_urb->transfer_buffer, priv->writelen + 3,
+			  port->write_urb->transfer_buffer, buf_len + 3,
 			  iuu_rxcmd, port);
 	result = usb_submit_urb(port->write_urb, GFP_ATOMIC);
-	spin_lock_irqsave(&priv->lock, flags);
-	priv->writelen = 0;
-	spin_unlock_irqrestore(&priv->lock, flags);
 	usb_serial_port_softint(port);
 	return result;
 }
@@ -770,14 +770,10 @@ static int iuu_uart_write(struct tty_struct *tty, struct usb_serial_port *port,
 		return -ENOMEM;
 
 	spin_lock_irqsave(&priv->lock, flags);
-	if (priv->writelen > 0) {
-		/* buffer already filled but not commited */
-		spin_unlock_irqrestore(&priv->lock, flags);
-		return 0;
-	}
+
 	/* fill the buffer */
-	memcpy(priv->writebuf, buf, count);
-	priv->writelen = count;
+	memcpy(priv->writebuf + priv->writelen, buf, count);
+	priv->writelen += count;
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return count;
@@ -819,7 +815,7 @@ static int iuu_uart_on(struct usb_serial_port *port)
 	buf[0] = IUU_UART_ENABLE;
 	buf[1] = (u8) ((IUU_BAUD_9600 >> 8) & 0x00FF);
 	buf[2] = (u8) (0x00FF & IUU_BAUD_9600);
-	buf[3] = (u8) (0x0F0 & IUU_TWO_STOP_BITS) | (0x07 & IUU_PARITY_EVEN);
+	buf[3] = (u8) (0x0F0 & IUU_ONE_STOP_BIT) | (0x07 & IUU_PARITY_EVEN);
 
 	status = bulk_immediate(port, buf, 4);
 	if (status != IUU_OPERATION_OK) {
@@ -946,19 +942,59 @@ static int iuu_uart_baud(struct usb_serial_port *port, u32 baud,
 	return status;
 }
 
-static int set_control_lines(struct usb_device *dev, u8 value)
+static void iuu_set_termios(struct tty_struct *tty,
+		struct usb_serial_port *port, struct ktermios *old_termios)
 {
-	return 0;
+	const u32 supported_mask = CMSPAR|PARENB|PARODD;
+
+	unsigned int cflag = tty->termios->c_cflag;
+	int status;
+	u32 actual;
+	u32 parity;
+	int csize = CS7;
+	int baud = 9600;	/* Fixed for the moment */
+	u32 newval = cflag & supported_mask;
+
+	/* compute the parity parameter */
+	parity = 0;
+	if (cflag & CMSPAR) {	/* Using mark space */
+		if (cflag & PARODD)
+			parity |= IUU_PARITY_SPACE;
+		else
+			parity |= IUU_PARITY_MARK;
+	} else if (!(cflag & PARENB)) {
+		parity |= IUU_PARITY_NONE;
+		csize = CS8;
+	} else if (cflag & PARODD)
+		parity |= IUU_PARITY_ODD;
+	else
+		parity |= IUU_PARITY_EVEN;
+
+	parity |= (cflag & CSTOPB ? IUU_TWO_STOP_BITS : IUU_ONE_STOP_BIT);
+
+	/* set it */
+	status = iuu_uart_baud(port,
+			(clockmode == 2) ? 16457 : 9600 * boost / 100,
+			&actual, parity);
+
+	/* set the termios value to the real one, so the user now what has
+	 * changed. We support few fields so its easies to copy the old hw
+	 * settings back over and then adjust them
+	 */
+ 	if (old_termios)
+ 		tty_termios_copy_hw(tty->termios, old_termios);
+	if (status != 0)	/* Set failed - return old bits */
+		return;
+	/* Re-encode speed, parity and csize */
+	tty_encode_baud_rate(tty, baud, baud);
+	tty->termios->c_cflag &= ~(supported_mask|CSIZE);
+	tty->termios->c_cflag |= newval | csize;
 }
 
-static void iuu_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void iuu_close(struct usb_serial_port *port)
 {
 	/* iuu_led (port,255,0,0,0); */
 	struct usb_serial *serial;
-	struct iuu_private *priv = usb_get_serial_port_data(port);
-	unsigned long flags;
-	unsigned int c_cflag;
 
 	serial = port->serial;
 	if (!serial)
@@ -968,17 +1004,6 @@ static void iuu_close(struct tty_struct *tty,
 
 	iuu_uart_off(port);
 	if (serial->dev) {
-		if (tty) {
-			c_cflag = tty->termios->c_cflag;
-			if (c_cflag & HUPCL) {
-				/* drop DTR and RTS */
-				priv = usb_get_serial_port_data(port);
-				spin_lock_irqsave(&priv->lock, flags);
-				priv->line_control = 0;
-				spin_unlock_irqrestore(&priv->lock, flags);
-				set_control_lines(port->serial->dev, 0);
-			}
-		}
 		/* free writebuf */
 		/* shutdown our urbs */
 		dbg("%s - shutting down urbs", __func__);
@@ -1154,7 +1179,7 @@ static int iuu_open(struct tty_struct *tty,
 	if (result) {
 		dev_err(&port->dev, "%s - failed submitting read urb,"
 			" error %d\n", __func__, result);
-		iuu_close(tty, port, NULL);
+		iuu_close(port);
 		return -EPROTO;
 	} else {
 		dbg("%s - rxcmd OK", __func__);
@@ -1175,6 +1200,7 @@ static struct usb_serial_driver iuu_device = {
 	.read_bulk_callback = iuu_uart_read_callback,
 	.tiocmget = iuu_tiocmget,
 	.tiocmset = iuu_tiocmset,
+	.set_termios = iuu_set_termios,
 	.attach = iuu_startup,
 	.shutdown = iuu_shutdown,
 };
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index 00daa8f7759a..f1195a98f316 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -1298,8 +1298,16 @@ static inline void stop_urb(struct urb *urb)
 		usb_kill_urb(urb);
 }
 
-static void keyspan_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void keyspan_dtr_rts(struct usb_serial_port *port, int on)
+{
+	struct keyspan_port_private *p_priv = usb_get_serial_port_data(port);
+
+	p_priv->rts_state = on;
+	p_priv->dtr_state = on;
+	keyspan_send_setup(port, 0);
+}
+
+static void keyspan_close(struct usb_serial_port *port)
 {
 	int			i;
 	struct usb_serial	*serial = port->serial;
@@ -1336,7 +1344,6 @@ static void keyspan_close(struct tty_struct *tty,
 			stop_urb(p_priv->out_urbs[i]);
 		}
 	}
-	tty_port_tty_set(&port->port, NULL);
 }
 
 /* download the firmware to a pre-renumeration device */
diff --git a/drivers/usb/serial/keyspan.h b/drivers/usb/serial/keyspan.h
index 38b4582e0734..0d4569b60768 100644
--- a/drivers/usb/serial/keyspan.h
+++ b/drivers/usb/serial/keyspan.h
@@ -38,9 +38,8 @@
 static int  keyspan_open		(struct tty_struct *tty,
 					 struct usb_serial_port *port,
 					 struct file *filp);
-static void keyspan_close		(struct tty_struct *tty,
-					 struct usb_serial_port *port,
-					 struct file *filp);
+static void keyspan_close		(struct usb_serial_port *port);
+static void keyspan_dtr_rts		(struct usb_serial_port *port, int on);
 static int  keyspan_startup		(struct usb_serial *serial);
 static void keyspan_shutdown		(struct usb_serial *serial);
 static int  keyspan_write_room		(struct tty_struct *tty);
@@ -562,6 +561,7 @@ static struct usb_serial_driver keyspan_1port_device = {
 	.num_ports		= 1,
 	.open			= keyspan_open,
 	.close			= keyspan_close,
+	.dtr_rts		= keyspan_dtr_rts,
 	.write			= keyspan_write,
 	.write_room		= keyspan_write_room,
 	.set_termios		= keyspan_set_termios,
@@ -582,6 +582,7 @@ static struct usb_serial_driver keyspan_2port_device = {
 	.num_ports		= 2,
 	.open			= keyspan_open,
 	.close			= keyspan_close,
+	.dtr_rts		= keyspan_dtr_rts,
 	.write			= keyspan_write,
 	.write_room		= keyspan_write_room,
 	.set_termios		= keyspan_set_termios,
@@ -602,6 +603,7 @@ static struct usb_serial_driver keyspan_4port_device = {
 	.num_ports		= 4,
 	.open			= keyspan_open,
 	.close			= keyspan_close,
+	.dtr_rts		= keyspan_dtr_rts,
 	.write			= keyspan_write,
 	.write_room		= keyspan_write_room,
 	.set_termios		= keyspan_set_termios,
diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c
index bf1ae247da66..ab769dbea1b3 100644
--- a/drivers/usb/serial/keyspan_pda.c
+++ b/drivers/usb/serial/keyspan_pda.c
@@ -651,6 +651,35 @@ static int keyspan_pda_chars_in_buffer(struct tty_struct *tty)
 }
 
 
+static void keyspan_pda_dtr_rts(struct usb_serial_port *port, int on)
+{
+	struct usb_serial *serial = port->serial;
+
+	if (serial->dev) {
+		if (on)
+			keyspan_pda_set_modem_info(serial, (1<<7) | (1<< 2));
+		else
+			keyspan_pda_set_modem_info(serial, 0);
+	}
+}
+
+static int keyspan_pda_carrier_raised(struct usb_serial_port *port)
+{
+	struct usb_serial *serial = port->serial;
+	unsigned char modembits;
+
+	/* If we can read the modem status and the DCD is low then
+	   carrier is not raised yet */
+	if (keyspan_pda_get_modem_info(serial, &modembits) >= 0) {
+		if (!(modembits & (1>>6)))
+			return 0;
+	}
+	/* Carrier raised, or we failed (eg disconnected) so
+	   progress accordingly */
+	return 1;
+}
+
+
 static int keyspan_pda_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp)
 {
@@ -682,13 +711,6 @@ static int keyspan_pda_open(struct tty_struct *tty,
 	priv->tx_room = room;
 	priv->tx_throttled = room ? 0 : 1;
 
-	/* the normal serial device seems to always turn on DTR and RTS here,
-	   so do the same */
-	if (tty && (tty->termios->c_cflag & CBAUD))
-		keyspan_pda_set_modem_info(serial, (1<<7) | (1<<2));
-	else
-		keyspan_pda_set_modem_info(serial, 0);
-
 	/*Start reading from the device*/
 	port->interrupt_in_urb->dev = serial->dev;
 	rc = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
@@ -700,19 +722,11 @@ static int keyspan_pda_open(struct tty_struct *tty,
 error:
 	return rc;
 }
-
-
-static void keyspan_pda_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void keyspan_pda_close(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
 
 	if (serial->dev) {
-		/* the normal serial device seems to always shut
-		   off DTR and RTS now */
-		if (tty->termios->c_cflag & HUPCL)
-			keyspan_pda_set_modem_info(serial, 0);
-
 		/* shutdown our bulk reads and writes */
 		usb_kill_urb(port->write_urb);
 		usb_kill_urb(port->interrupt_in_urb);
@@ -839,6 +853,8 @@ static struct usb_serial_driver keyspan_pda_device = {
 	.usb_driver = 		&keyspan_pda_driver,
 	.id_table =		id_table_std,
 	.num_ports =		1,
+	.dtr_rts =		keyspan_pda_dtr_rts,
+	.carrier_raised	=	keyspan_pda_carrier_raised,
 	.open =			keyspan_pda_open,
 	.close =		keyspan_pda_close,
 	.write =		keyspan_pda_write,
diff --git a/drivers/usb/serial/kl5kusb105.c b/drivers/usb/serial/kl5kusb105.c
index fcd9082f3e7f..fa817c66b3e8 100644
--- a/drivers/usb/serial/kl5kusb105.c
+++ b/drivers/usb/serial/kl5kusb105.c
@@ -76,8 +76,7 @@ static int  klsi_105_startup(struct usb_serial *serial);
 static void klsi_105_shutdown(struct usb_serial *serial);
 static int  klsi_105_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void klsi_105_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+static void klsi_105_close(struct usb_serial_port *port);
 static int  klsi_105_write(struct tty_struct *tty,
 	struct usb_serial_port *port, const unsigned char *buf, int count);
 static void klsi_105_write_bulk_callback(struct urb *urb);
@@ -447,8 +446,7 @@ exit:
 } /* klsi_105_open */
 
 
-static void klsi_105_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void klsi_105_close(struct usb_serial_port *port)
 {
 	struct klsi_105_private *priv = usb_get_serial_port_data(port);
 	int rc;
diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c
index c148544953b3..6b570498287f 100644
--- a/drivers/usb/serial/kobil_sct.c
+++ b/drivers/usb/serial/kobil_sct.c
@@ -72,8 +72,7 @@ static int  kobil_startup(struct usb_serial *serial);
 static void kobil_shutdown(struct usb_serial *serial);
 static int  kobil_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void kobil_close(struct tty_struct *tty, struct usb_serial_port *port,
-			struct file *filp);
+static void kobil_close(struct usb_serial_port *port);
 static int  kobil_write(struct tty_struct *tty, struct usb_serial_port *port,
 			 const unsigned char *buf, int count);
 static int  kobil_write_room(struct tty_struct *tty);
@@ -209,7 +208,7 @@ static void kobil_shutdown(struct usb_serial *serial)
 
 	for (i = 0; i < serial->num_ports; ++i) {
 		while (serial->port[i]->port.count > 0)
-			kobil_close(NULL, serial->port[i], NULL);
+			kobil_close(serial->port[i]);
 		kfree(usb_get_serial_port_data(serial->port[i]));
 		usb_set_serial_port_data(serial->port[i], NULL);
 	}
@@ -346,11 +345,11 @@ static int kobil_open(struct tty_struct *tty,
 }
 
 
-static void kobil_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void kobil_close(struct usb_serial_port *port)
 {
 	dbg("%s - port %d", __func__, port->number);
 
+	/* FIXME: Add rts/dtr methods */
 	if (port->write_urb) {
 		usb_kill_urb(port->write_urb);
 		usb_free_urb(port->write_urb);
diff --git a/drivers/usb/serial/mct_u232.c b/drivers/usb/serial/mct_u232.c
index 82930a7d5093..873795548fc0 100644
--- a/drivers/usb/serial/mct_u232.c
+++ b/drivers/usb/serial/mct_u232.c
@@ -95,8 +95,8 @@ static int  mct_u232_startup(struct usb_serial *serial);
 static void mct_u232_shutdown(struct usb_serial *serial);
 static int  mct_u232_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void mct_u232_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+static void mct_u232_close(struct usb_serial_port *port);
+static void mct_u232_dtr_rts(struct usb_serial_port *port, int on);
 static void mct_u232_read_int_callback(struct urb *urb);
 static void mct_u232_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
@@ -140,6 +140,7 @@ static struct usb_serial_driver mct_u232_device = {
 	.num_ports =	     1,
 	.open =		     mct_u232_open,
 	.close =	     mct_u232_close,
+	.dtr_rts =	     mct_u232_dtr_rts,
 	.throttle =	     mct_u232_throttle,
 	.unthrottle =	     mct_u232_unthrottle,
 	.read_int_callback = mct_u232_read_int_callback,
@@ -496,29 +497,29 @@ error:
 	return retval;
 } /* mct_u232_open */
 
-
-static void mct_u232_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void mct_u232_dtr_rts(struct usb_serial_port *port, int on)
 {
-	unsigned int c_cflag;
 	unsigned int control_state;
 	struct mct_u232_private *priv = usb_get_serial_port_data(port);
-	dbg("%s port %d", __func__, port->number);
 
-	if (tty) {
-		c_cflag = tty->termios->c_cflag;
-		mutex_lock(&port->serial->disc_mutex);
-		if (c_cflag & HUPCL && !port->serial->disconnected) {
-			/* drop DTR and RTS */
-			spin_lock_irq(&priv->lock);
+	mutex_lock(&port->serial->disc_mutex);
+	if (!port->serial->disconnected) {
+		/* drop DTR and RTS */
+		spin_lock_irq(&priv->lock);
+		if (on)
+			priv->control_state |= TIOCM_DTR | TIOCM_RTS;
+		else
 			priv->control_state &= ~(TIOCM_DTR | TIOCM_RTS);
-			control_state = priv->control_state;
-			spin_unlock_irq(&priv->lock);
-			mct_u232_set_modem_ctrl(port->serial, control_state);
-		}
-		mutex_unlock(&port->serial->disc_mutex);
+		control_state = priv->control_state;
+		spin_unlock_irq(&priv->lock);
+		mct_u232_set_modem_ctrl(port->serial, control_state);
 	}
+	mutex_unlock(&port->serial->disc_mutex);
+}
 
+static void mct_u232_close(struct usb_serial_port *port)
+{
+	dbg("%s port %d", __func__, port->number);
 
 	if (port->serial->dev) {
 		/* shutdown our urbs */
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index 24e3b5d4b4d4..9e1a013ee7f6 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -533,8 +533,7 @@ static int mos7720_chars_in_buffer(struct tty_struct *tty)
 	return chars;
 }
 
-static void mos7720_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void mos7720_close(struct usb_serial_port *port)
 {
 	struct usb_serial *serial;
 	struct moschip_port *mos7720_port;
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index 84fb1dcd30dc..10b78a37214f 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -1135,54 +1135,12 @@ static int mos7840_chars_in_buffer(struct tty_struct *tty)
 
 }
 
-/************************************************************************
- *
- * mos7840_block_until_tx_empty
- *
- *	This function will block the close until one of the following:
- *		1. TX count are 0
- *		2. The mos7840 has stopped
- *		3. A timeout of 3 seconds without activity has expired
- *
- ************************************************************************/
-static void mos7840_block_until_tx_empty(struct tty_struct *tty,
-				struct moschip_port *mos7840_port)
-{
-	int timeout = HZ / 10;
-	int wait = 30;
-	int count;
-
-	while (1) {
-
-		count = mos7840_chars_in_buffer(tty);
-
-		/* Check for Buffer status */
-		if (count <= 0)
-			return;
-
-		/* Block the thread for a while */
-		interruptible_sleep_on_timeout(&mos7840_port->wait_chase,
-					       timeout);
-
-		/* No activity.. count down section */
-		wait--;
-		if (wait == 0) {
-			dbg("%s - TIMEOUT", __func__);
-			return;
-		} else {
-			/* Reset timeout value back to seconds */
-			wait = 30;
-		}
-	}
-}
-
 /*****************************************************************************
  * mos7840_close
  *	this function is called by the tty driver when a port is closed
  *****************************************************************************/
 
-static void mos7840_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void mos7840_close(struct usb_serial_port *port)
 {
 	struct usb_serial *serial;
 	struct moschip_port *mos7840_port;
@@ -1223,10 +1181,6 @@ static void mos7840_close(struct tty_struct *tty,
 		}
 	}
 
-	if (serial->dev)
-		/* flush and block until tx is empty */
-		mos7840_block_until_tx_empty(tty, mos7840_port);
-
 	/* While closing port, shutdown all bulk read, write  *
 	 * and interrupt read if they exists                  */
 	if (serial->dev) {
diff --git a/drivers/usb/serial/navman.c b/drivers/usb/serial/navman.c
index bcdcbb822705..f5f3751a888c 100644
--- a/drivers/usb/serial/navman.c
+++ b/drivers/usb/serial/navman.c
@@ -98,8 +98,7 @@ static int navman_open(struct tty_struct *tty,
 	return result;
 }
 
-static void navman_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void navman_close(struct usb_serial_port *port)
 {
 	dbg("%s - port %d", __func__, port->number);
 
diff --git a/drivers/usb/serial/omninet.c b/drivers/usb/serial/omninet.c
index df6539712726..1104617334f5 100644
--- a/drivers/usb/serial/omninet.c
+++ b/drivers/usb/serial/omninet.c
@@ -66,8 +66,7 @@ static int debug;
 /* function prototypes */
 static int  omninet_open(struct tty_struct *tty, struct usb_serial_port *port,
 							struct file *filp);
-static void omninet_close(struct tty_struct *tty, struct usb_serial_port *port,
-							struct file *filp);
+static void omninet_close(struct usb_serial_port *port);
 static void omninet_read_bulk_callback(struct urb *urb);
 static void omninet_write_bulk_callback(struct urb *urb);
 static int  omninet_write(struct tty_struct *tty, struct usb_serial_port *port,
@@ -189,8 +188,7 @@ static int omninet_open(struct tty_struct *tty,
 	return result;
 }
 
-static void omninet_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void omninet_close(struct usb_serial_port *port)
 {
 	dbg("%s - port %d", __func__, port->number);
 	usb_kill_urb(port->read_urb);
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
index b500ad10b758..c20480aa9755 100644
--- a/drivers/usb/serial/opticon.c
+++ b/drivers/usb/serial/opticon.c
@@ -173,8 +173,7 @@ static int opticon_open(struct tty_struct *tty, struct usb_serial_port *port,
 	return result;
 }
 
-static void opticon_close(struct tty_struct *tty, struct usb_serial_port *port,
-			  struct file *filp)
+static void opticon_close(struct usb_serial_port *port)
 {
 	struct opticon_private *priv = usb_get_serial_data(port->serial);
 
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 7817b82889ca..a16d69fadba1 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -45,8 +45,9 @@
 /* Function prototypes */
 static int  option_open(struct tty_struct *tty, struct usb_serial_port *port,
 							struct file *filp);
-static void option_close(struct tty_struct *tty, struct usb_serial_port *port,
-							struct file *filp);
+static void option_close(struct usb_serial_port *port);
+static void option_dtr_rts(struct usb_serial_port *port, int on);
+
 static int  option_startup(struct usb_serial *serial);
 static void option_shutdown(struct usb_serial *serial);
 static int  option_write_room(struct tty_struct *tty);
@@ -61,7 +62,7 @@ static void option_set_termios(struct tty_struct *tty,
 static int  option_tiocmget(struct tty_struct *tty, struct file *file);
 static int  option_tiocmset(struct tty_struct *tty, struct file *file,
 				unsigned int set, unsigned int clear);
-static int  option_send_setup(struct tty_struct *tty, struct usb_serial_port *port);
+static int  option_send_setup(struct usb_serial_port *port);
 static int  option_suspend(struct usb_serial *serial, pm_message_t message);
 static int  option_resume(struct usb_serial *serial);
 
@@ -551,6 +552,7 @@ static struct usb_serial_driver option_1port_device = {
 	.num_ports         = 1,
 	.open              = option_open,
 	.close             = option_close,
+	.dtr_rts	   = option_dtr_rts,
 	.write             = option_write,
 	.write_room        = option_write_room,
 	.chars_in_buffer   = option_chars_in_buffer,
@@ -630,7 +632,7 @@ static void option_set_termios(struct tty_struct *tty,
 	dbg("%s", __func__);
 	/* Doesn't support option setting */
 	tty_termios_copy_hw(tty->termios, old_termios);
-	option_send_setup(tty, port);
+	option_send_setup(port);
 }
 
 static int option_tiocmget(struct tty_struct *tty, struct file *file)
@@ -669,7 +671,7 @@ static int option_tiocmset(struct tty_struct *tty, struct file *file,
 		portdata->rts_state = 0;
 	if (clear & TIOCM_DTR)
 		portdata->dtr_state = 0;
-	return option_send_setup(tty, port);
+	return option_send_setup(port);
 }
 
 /* Write */
@@ -897,10 +899,6 @@ static int option_open(struct tty_struct *tty,
 
 	dbg("%s", __func__);
 
-	/* Set some sane defaults */
-	portdata->rts_state = 1;
-	portdata->dtr_state = 1;
-
 	/* Reset low level data toggle and start reading from endpoints */
 	for (i = 0; i < N_IN_URB; i++) {
 		urb = portdata->in_urbs[i];
@@ -936,13 +934,28 @@ static int option_open(struct tty_struct *tty,
 				usb_pipeout(urb->pipe), 0); */
 	}
 
-	option_send_setup(tty, port);
+	option_send_setup(port);
 
 	return 0;
 }
 
-static void option_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void option_dtr_rts(struct usb_serial_port *port, int on)
+{
+	struct usb_serial *serial = port->serial;
+	struct option_port_private *portdata;
+
+	dbg("%s", __func__);
+	portdata = usb_get_serial_port_data(port);
+	mutex_lock(&serial->disc_mutex);
+	portdata->rts_state = on;
+	portdata->dtr_state = on;
+	if (serial->dev)
+		option_send_setup(port);
+	mutex_unlock(&serial->disc_mutex);
+}
+
+
+static void option_close(struct usb_serial_port *port)
 {
 	int i;
 	struct usb_serial *serial = port->serial;
@@ -951,22 +964,13 @@ static void option_close(struct tty_struct *tty,
 	dbg("%s", __func__);
 	portdata = usb_get_serial_port_data(port);
 
-	portdata->rts_state = 0;
-	portdata->dtr_state = 0;
-
 	if (serial->dev) {
-		mutex_lock(&serial->disc_mutex);
-		if (!serial->disconnected)
-			option_send_setup(tty, port);
-		mutex_unlock(&serial->disc_mutex);
-
 		/* Stop reading/writing urbs */
 		for (i = 0; i < N_IN_URB; i++)
 			usb_kill_urb(portdata->in_urbs[i]);
 		for (i = 0; i < N_OUT_URB; i++)
 			usb_kill_urb(portdata->out_urbs[i]);
 	}
-	tty_port_tty_set(&port->port, NULL);
 }
 
 /* Helper functions used by option_setup_urbs */
@@ -1032,28 +1036,24 @@ static void option_setup_urbs(struct usb_serial *serial)
  * This is exactly the same as SET_CONTROL_LINE_STATE from the PSTN
  * CDC.
 */
-static int option_send_setup(struct tty_struct *tty,
-						struct usb_serial_port *port)
+static int option_send_setup(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
 	struct option_port_private *portdata;
 	int ifNum = serial->interface->cur_altsetting->desc.bInterfaceNumber;
+	int val = 0;
 	dbg("%s", __func__);
 
 	portdata = usb_get_serial_port_data(port);
 
-	if (tty) {
-		int val = 0;
-		if (portdata->dtr_state)
-			val |= 0x01;
-		if (portdata->rts_state)
-			val |= 0x02;
+	if (portdata->dtr_state)
+		val |= 0x01;
+	if (portdata->rts_state)
+		val |= 0x02;
 
-		return usb_control_msg(serial->dev,
-			usb_rcvctrlpipe(serial->dev, 0),
-			0x22, 0x21, val, ifNum, NULL, 0, USB_CTRL_SET_TIMEOUT);
-	}
-	return 0;
+	return usb_control_msg(serial->dev,
+		usb_rcvctrlpipe(serial->dev, 0),
+		0x22, 0x21, val, ifNum, NULL, 0, USB_CTRL_SET_TIMEOUT);
 }
 
 static int option_startup(struct usb_serial *serial)
diff --git a/drivers/usb/serial/oti6858.c b/drivers/usb/serial/oti6858.c
index ba551f00f16f..7de54781fe61 100644
--- a/drivers/usb/serial/oti6858.c
+++ b/drivers/usb/serial/oti6858.c
@@ -143,8 +143,7 @@ struct oti6858_control_pkt {
 /* function prototypes */
 static int oti6858_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void oti6858_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+static void oti6858_close(struct usb_serial_port *port);
 static void oti6858_set_termios(struct tty_struct *tty,
 			struct usb_serial_port *port, struct ktermios *old);
 static int oti6858_ioctl(struct tty_struct *tty, struct file *file,
@@ -622,67 +621,30 @@ static int oti6858_open(struct tty_struct *tty,
 	if (result != 0) {
 		dev_err(&port->dev, "%s(): usb_submit_urb() failed"
 			       " with error %d\n", __func__, result);
-		oti6858_close(tty, port, NULL);
+		oti6858_close(port);
 		return -EPROTO;
 	}
 
 	/* setup termios */
 	if (tty)
 		oti6858_set_termios(tty, port, &tmp_termios);
-
+	port->port.drain_delay = 256;	/* FIXME: check the FIFO length */
 	return 0;
 }
 
-static void oti6858_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void oti6858_close(struct usb_serial_port *port)
 {
 	struct oti6858_private *priv = usb_get_serial_port_data(port);
 	unsigned long flags;
-	long timeout;
-	wait_queue_t wait;
 
 	dbg("%s(port = %d)", __func__, port->number);
 
-	/* wait for data to drain from the buffer */
 	spin_lock_irqsave(&priv->lock, flags);
-	timeout = 30 * HZ;	/* PL2303_CLOSING_WAIT */
-	init_waitqueue_entry(&wait, current);
-	add_wait_queue(&tty->write_wait, &wait);
-	dbg("%s(): entering wait loop", __func__);
-	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (oti6858_buf_data_avail(priv->buf) == 0
-		|| timeout == 0 || signal_pending(current)
-		|| port->serial->disconnected)
-			break;
-		spin_unlock_irqrestore(&priv->lock, flags);
-		timeout = schedule_timeout(timeout);
-		spin_lock_irqsave(&priv->lock, flags);
-	}
-	set_current_state(TASK_RUNNING);
-	remove_wait_queue(&tty->write_wait, &wait);
-	dbg("%s(): after wait loop", __func__);
-
 	/* clear out any remaining data in the buffer */
 	oti6858_buf_clear(priv->buf);
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	/* wait for characters to drain from the device */
-	/* (this is long enough for the entire 256 byte */
-	/* pl2303 hardware buffer to drain with no flow */
-	/* control for data rates of 1200 bps or more, */
-	/* for lower rates we should really know how much */
-	/* data is in the buffer to compute a delay */
-	/* that is not unnecessarily long) */
-	/* FIXME
-	bps = tty_get_baud_rate(tty);
-	if (bps > 1200)
-		timeout = max((HZ*2560)/bps,HZ/10);
-	else
-	*/
-		timeout = 2*HZ;
-	schedule_timeout_interruptible(timeout);
-	dbg("%s(): after schedule_timeout_interruptible()", __func__);
+	dbg("%s(): after buf_clear()", __func__);
 
 	/* cancel scheduled setup */
 	cancel_delayed_work(&priv->delayed_setup_work);
@@ -694,15 +656,6 @@ static void oti6858_close(struct tty_struct *tty,
 	usb_kill_urb(port->write_urb);
 	usb_kill_urb(port->read_urb);
 	usb_kill_urb(port->interrupt_in_urb);
-
-	/*
-	if (tty && (tty->termios->c_cflag) & HUPCL) {
-		// drop DTR and RTS
-		spin_lock_irqsave(&priv->lock, flags);
-		priv->pending_setup.control &= ~CONTROL_MASK;
-		spin_unlock_irqrestore(&priv->lock, flags);
-	}
-	*/
 }
 
 static int oti6858_tiocmset(struct tty_struct *tty, struct file *file,
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 751a533a4347..e02dc3d643c7 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -652,69 +652,41 @@ static void pl2303_set_termios(struct tty_struct *tty,
 	kfree(buf);
 }
 
-static void pl2303_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void pl2303_dtr_rts(struct usb_serial_port *port, int on)
+{
+	struct pl2303_private *priv = usb_get_serial_port_data(port);
+	unsigned long flags;
+	u8 control;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	/* Change DTR and RTS */
+	if (on)
+		priv->line_control |= (CONTROL_DTR | CONTROL_RTS);
+	else
+		priv->line_control &= ~(CONTROL_DTR | CONTROL_RTS);
+	control = priv->line_control;
+	spin_unlock_irqrestore(&priv->lock, flags);
+	set_control_lines(port->serial->dev, control);
+}
+
+static void pl2303_close(struct usb_serial_port *port)
 {
 	struct pl2303_private *priv = usb_get_serial_port_data(port);
 	unsigned long flags;
-	unsigned int c_cflag;
-	int bps;
-	long timeout;
-	wait_queue_t wait;
 
 	dbg("%s - port %d", __func__, port->number);
 
-	/* wait for data to drain from the buffer */
 	spin_lock_irqsave(&priv->lock, flags);
-	timeout = PL2303_CLOSING_WAIT;
-	init_waitqueue_entry(&wait, current);
-	add_wait_queue(&tty->write_wait, &wait);
-	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (pl2303_buf_data_avail(priv->buf) == 0 ||
-		    timeout == 0 || signal_pending(current) ||
-		    port->serial->disconnected)
-			break;
-		spin_unlock_irqrestore(&priv->lock, flags);
-		timeout = schedule_timeout(timeout);
-		spin_lock_irqsave(&priv->lock, flags);
-	}
-	set_current_state(TASK_RUNNING);
-	remove_wait_queue(&tty->write_wait, &wait);
 	/* clear out any remaining data in the buffer */
 	pl2303_buf_clear(priv->buf);
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	/* wait for characters to drain from the device */
-	/* (this is long enough for the entire 256 byte */
-	/* pl2303 hardware buffer to drain with no flow */
-	/* control for data rates of 1200 bps or more, */
-	/* for lower rates we should really know how much */
-	/* data is in the buffer to compute a delay */
-	/* that is not unnecessarily long) */
-	bps = tty_get_baud_rate(tty);
-	if (bps > 1200)
-		timeout = max((HZ*2560)/bps, HZ/10);
-	else
-		timeout = 2*HZ;
-	schedule_timeout_interruptible(timeout);
-
 	/* shutdown our urbs */
 	dbg("%s - shutting down urbs", __func__);
 	usb_kill_urb(port->write_urb);
 	usb_kill_urb(port->read_urb);
 	usb_kill_urb(port->interrupt_in_urb);
 
-	if (tty) {
-		c_cflag = tty->termios->c_cflag;
-		if (c_cflag & HUPCL) {
-			/* drop DTR and RTS */
-			spin_lock_irqsave(&priv->lock, flags);
-			priv->line_control = 0;
-			spin_unlock_irqrestore(&priv->lock, flags);
-			set_control_lines(port->serial->dev, 0);
-		}
-	}
 }
 
 static int pl2303_open(struct tty_struct *tty,
@@ -748,7 +720,7 @@ static int pl2303_open(struct tty_struct *tty,
 	if (result) {
 		dev_err(&port->dev, "%s - failed submitting read urb,"
 			" error %d\n", __func__, result);
-		pl2303_close(tty, port, NULL);
+		pl2303_close(port);
 		return -EPROTO;
 	}
 
@@ -758,9 +730,10 @@ static int pl2303_open(struct tty_struct *tty,
 	if (result) {
 		dev_err(&port->dev, "%s - failed submitting interrupt urb,"
 			" error %d\n", __func__, result);
-		pl2303_close(tty, port, NULL);
+		pl2303_close(port);
 		return -EPROTO;
 	}
+	port->port.drain_delay = 256;
 	return 0;
 }
 
@@ -821,6 +794,14 @@ static int pl2303_tiocmget(struct tty_struct *tty, struct file *file)
 	return result;
 }
 
+static int pl2303_carrier_raised(struct usb_serial_port *port)
+{
+	struct pl2303_private *priv = usb_get_serial_port_data(port);
+	if (priv->line_status & UART_DCD)
+		return 1;
+	return 0;
+}
+
 static int wait_modem_info(struct usb_serial_port *port, unsigned int arg)
 {
 	struct pl2303_private *priv = usb_get_serial_port_data(port);
@@ -1125,6 +1106,8 @@ static struct usb_serial_driver pl2303_device = {
 	.num_ports =		1,
 	.open =			pl2303_open,
 	.close =		pl2303_close,
+	.dtr_rts = 		pl2303_dtr_rts,
+	.carrier_raised =	pl2303_carrier_raised,
 	.write =		pl2303_write,
 	.ioctl =		pl2303_ioctl,
 	.break_ctl =		pl2303_break_ctl,
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index 913225c61610..17ac34f4d668 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -26,12 +26,10 @@
 #include <linux/module.h>
 #include <linux/usb.h>
 #include <linux/usb/serial.h>
-#include <linux/usb/ch9.h>
 
 #define SWIMS_USB_REQUEST_SetPower	0x00
 #define SWIMS_USB_REQUEST_SetNmea	0x07
 
-/* per port private data */
 #define N_IN_URB	4
 #define N_OUT_URB	4
 #define IN_BUFLEN	4096
@@ -39,6 +37,12 @@
 static int debug;
 static int nmea;
 
+/* Used in interface blacklisting */
+struct sierra_iface_info {
+	const u32 infolen;	/* number of interface numbers on blacklist */
+	const u8  *ifaceinfo;	/* pointer to the array holding the numbers */
+};
+
 static int sierra_set_power_state(struct usb_device *udev, __u16 swiState)
 {
 	int result;
@@ -85,6 +89,23 @@ static int sierra_calc_num_ports(struct usb_serial *serial)
 	return result;
 }
 
+static int is_blacklisted(const u8 ifnum,
+				const struct sierra_iface_info *blacklist)
+{
+	const u8  *info;
+	int i;
+
+	if (blacklist) {
+		info = blacklist->ifaceinfo;
+
+		for (i = 0; i < blacklist->infolen; i++) {
+			if (info[i] == ifnum)
+				return 1;
+		}
+	}
+	return 0;
+}
+
 static int sierra_calc_interface(struct usb_serial *serial)
 {
 	int interface;
@@ -153,9 +174,25 @@ static int sierra_probe(struct usb_serial *serial,
 	 */
 	usb_set_serial_data(serial, (void *)num_ports);
 
+	/* ifnum could have changed - by calling usb_set_interface */
+	ifnum = sierra_calc_interface(serial);
+
+	if (is_blacklisted(ifnum,
+				(struct sierra_iface_info *)id->driver_info)) {
+		dev_dbg(&serial->dev->dev,
+			"Ignoring blacklisted interface #%d\n", ifnum);
+		return -ENODEV;
+	}
+
 	return result;
 }
 
+static const u8 direct_ip_non_serial_ifaces[] = { 7, 8, 9, 10, 11 };
+static const struct sierra_iface_info direct_ip_interface_blacklist = {
+	.infolen = ARRAY_SIZE(direct_ip_non_serial_ifaces),
+	.ifaceinfo = direct_ip_non_serial_ifaces,
+};
+
 static struct usb_device_id id_table [] = {
 	{ USB_DEVICE(0x1199, 0x0017) },	/* Sierra Wireless EM5625 */
 	{ USB_DEVICE(0x1199, 0x0018) },	/* Sierra Wireless MC5720 */
@@ -188,9 +225,11 @@ static struct usb_device_id id_table [] = {
 	{ USB_DEVICE(0x1199, 0x6833) },	/* Sierra Wireless MC8781 */
 	{ USB_DEVICE(0x1199, 0x683A) },	/* Sierra Wireless MC8785 */
 	{ USB_DEVICE(0x1199, 0x683B) },	/* Sierra Wireless MC8785 Composite */
-	{ USB_DEVICE(0x1199, 0x683C) },	/* Sierra Wireless MC8790 */
-	{ USB_DEVICE(0x1199, 0x683D) },	/* Sierra Wireless MC8790 */
-	{ USB_DEVICE(0x1199, 0x683E) },	/* Sierra Wireless MC8790 */
+	/* Sierra Wireless MC8790, MC8791, MC8792 Composite */
+	{ USB_DEVICE(0x1199, 0x683C) },
+	{ USB_DEVICE(0x1199, 0x683D) },	/* Sierra Wireless MC8791 Composite */
+	/* Sierra Wireless MC8790, MC8791, MC8792 */
+	{ USB_DEVICE(0x1199, 0x683E) },
 	{ USB_DEVICE(0x1199, 0x6850) },	/* Sierra Wireless AirCard 880 */
 	{ USB_DEVICE(0x1199, 0x6851) },	/* Sierra Wireless AirCard 881 */
 	{ USB_DEVICE(0x1199, 0x6852) },	/* Sierra Wireless AirCard 880 E */
@@ -211,6 +250,10 @@ static struct usb_device_id id_table [] = {
 	{ USB_DEVICE(0x1199, 0x0112) }, /* Sierra Wireless AirCard 580 */
 	{ USB_DEVICE(0x0F3D, 0x0112) }, /* Airprime/Sierra PC 5220 */
 
+	{ USB_DEVICE(0x1199, 0x68A3), 	/* Sierra Wireless Direct IP modems */
+	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
+	},
+
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, id_table);
@@ -229,7 +272,6 @@ struct sierra_port_private {
 
 	/* Input endpoints and buffers for this port */
 	struct urb *in_urbs[N_IN_URB];
-	char *in_buffer[N_IN_URB];
 
 	/* Settings for the port */
 	int rts_state;	/* Handshaking pins (outputs) */
@@ -240,57 +282,50 @@ struct sierra_port_private {
 	int ri_state;
 };
 
-static int sierra_send_setup(struct tty_struct *tty,
-						struct usb_serial_port *port)
+static int sierra_send_setup(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
 	struct sierra_port_private *portdata;
 	__u16 interface = 0;
+	int val = 0;
 
 	dev_dbg(&port->dev, "%s", __func__);
 
 	portdata = usb_get_serial_port_data(port);
 
-	if (tty) {
-		int val = 0;
-		if (portdata->dtr_state)
-			val |= 0x01;
-		if (portdata->rts_state)
-			val |= 0x02;
-
-		/* If composite device then properly report interface */
-		if (serial->num_ports == 1) {
-			interface = sierra_calc_interface(serial);
-
-			/* Control message is sent only to interfaces with
-			 * interrupt_in endpoints
-			 */
-			if (port->interrupt_in_urb) {
-				/* send control message */
-				return usb_control_msg(serial->dev,
-					usb_rcvctrlpipe(serial->dev, 0),
-					0x22, 0x21, val, interface,
-					NULL, 0, USB_CTRL_SET_TIMEOUT);
-			}
-		}
-
-		/* Otherwise the need to do non-composite mapping */
-		else {
-			if (port->bulk_out_endpointAddress == 2)
-				interface = 0;
-			else if (port->bulk_out_endpointAddress == 4)
-				interface = 1;
-			else if (port->bulk_out_endpointAddress == 5)
-				interface = 2;
+	if (portdata->dtr_state)
+		val |= 0x01;
+	if (portdata->rts_state)
+		val |= 0x02;
 
+	/* If composite device then properly report interface */
+	if (serial->num_ports == 1) {
+		interface = sierra_calc_interface(serial);
+		/* Control message is sent only to interfaces with
+		 * interrupt_in endpoints
+		 */
+		if (port->interrupt_in_urb) {
+			/* send control message */
 			return usb_control_msg(serial->dev,
 				usb_rcvctrlpipe(serial->dev, 0),
 				0x22, 0x21, val, interface,
 				NULL, 0, USB_CTRL_SET_TIMEOUT);
-
 		}
 	}
 
+	/* Otherwise the need to do non-composite mapping */
+	else {
+		if (port->bulk_out_endpointAddress == 2)
+			interface = 0;
+		else if (port->bulk_out_endpointAddress == 4)
+			interface = 1;
+		else if (port->bulk_out_endpointAddress == 5)
+			interface = 2;
+		return usb_control_msg(serial->dev,
+			usb_rcvctrlpipe(serial->dev, 0),
+			0x22, 0x21, val, interface,
+			NULL, 0, USB_CTRL_SET_TIMEOUT);
+	}
 	return 0;
 }
 
@@ -299,7 +334,7 @@ static void sierra_set_termios(struct tty_struct *tty,
 {
 	dev_dbg(&port->dev, "%s", __func__);
 	tty_termios_copy_hw(tty->termios, old_termios);
-	sierra_send_setup(tty, port);
+	sierra_send_setup(port);
 }
 
 static int sierra_tiocmget(struct tty_struct *tty, struct file *file)
@@ -338,7 +373,18 @@ static int sierra_tiocmset(struct tty_struct *tty, struct file *file,
 		portdata->rts_state = 0;
 	if (clear & TIOCM_DTR)
 		portdata->dtr_state = 0;
-	return sierra_send_setup(tty, port);
+	return sierra_send_setup(port);
+}
+
+static void sierra_release_urb(struct urb *urb)
+{
+	struct usb_serial_port *port;
+	if (urb) {
+		port =  urb->context;
+		dev_dbg(&port->dev, "%s: %p\n", __func__, urb);
+		kfree(urb->transfer_buffer);
+		usb_free_urb(urb);
+	}
 }
 
 static void sierra_outdat_callback(struct urb *urb)
@@ -465,7 +511,7 @@ static void sierra_indat_callback(struct urb *urb)
 				" received", __func__);
 
 		/* Resubmit urb so we continue receiving */
-		if (port->port.count && status != -ESHUTDOWN) {
+		if (port->port.count && status != -ESHUTDOWN && status != -EPERM) {
 			err = usb_submit_urb(urb, GFP_ATOMIC);
 			if (err)
 				dev_err(&port->dev, "resubmit read urb failed."
@@ -557,14 +603,129 @@ static int sierra_write_room(struct tty_struct *tty)
 	return 2048;
 }
 
+static void sierra_stop_rx_urbs(struct usb_serial_port *port)
+{
+	int i;
+	struct sierra_port_private *portdata = usb_get_serial_port_data(port);
+
+	for (i = 0; i < ARRAY_SIZE(portdata->in_urbs); i++)
+		usb_kill_urb(portdata->in_urbs[i]);
+
+	usb_kill_urb(port->interrupt_in_urb);
+}
+
+static int sierra_submit_rx_urbs(struct usb_serial_port *port, gfp_t mem_flags)
+{
+	int ok_cnt;
+	int err = -EINVAL;
+	int i;
+	struct urb *urb;
+	struct sierra_port_private *portdata = usb_get_serial_port_data(port);
+
+	ok_cnt = 0;
+	for (i = 0; i < ARRAY_SIZE(portdata->in_urbs); i++) {
+		urb = portdata->in_urbs[i];
+		if (!urb)
+			continue;
+		err = usb_submit_urb(urb, mem_flags);
+		if (err) {
+			dev_err(&port->dev, "%s: submit urb failed: %d\n",
+				__func__, err);
+		} else {
+			ok_cnt++;
+		}
+	}
+
+	if (ok_cnt && port->interrupt_in_urb) {
+		err = usb_submit_urb(port->interrupt_in_urb, mem_flags);
+		if (err) {
+			dev_err(&port->dev, "%s: submit intr urb failed: %d\n",
+				__func__, err);
+		}
+	}
+
+	if (ok_cnt > 0) /* at least one rx urb submitted */
+		return 0;
+	else
+		return err;
+}
+
+static struct urb *sierra_setup_urb(struct usb_serial *serial, int endpoint,
+					int dir, void *ctx, int len,
+					gfp_t mem_flags,
+					usb_complete_t callback)
+{
+	struct urb	*urb;
+	u8		*buf;
+
+	if (endpoint == -1)
+		return NULL;
+
+	urb = usb_alloc_urb(0, mem_flags);
+	if (urb == NULL) {
+		dev_dbg(&serial->dev->dev, "%s: alloc for endpoint %d failed\n",
+			__func__, endpoint);
+		return NULL;
+	}
+
+	buf = kmalloc(len, mem_flags);
+	if (buf) {
+		/* Fill URB using supplied data */
+		usb_fill_bulk_urb(urb, serial->dev,
+			usb_sndbulkpipe(serial->dev, endpoint) | dir,
+			buf, len, callback, ctx);
+
+		/* debug */
+		dev_dbg(&serial->dev->dev, "%s %c u : %p d:%p\n", __func__,
+				dir == USB_DIR_IN ? 'i' : 'o', urb, buf);
+	} else {
+		dev_dbg(&serial->dev->dev, "%s %c u:%p d:%p\n", __func__,
+				dir == USB_DIR_IN ? 'i' : 'o', urb, buf);
+
+		sierra_release_urb(urb);
+		urb = NULL;
+	}
+
+	return urb;
+}
+
+static void sierra_close(struct usb_serial_port *port)
+{
+	int i;
+	struct usb_serial *serial = port->serial;
+	struct sierra_port_private *portdata;
+
+	dev_dbg(&port->dev, "%s\n", __func__);
+	portdata = usb_get_serial_port_data(port);
+
+	portdata->rts_state = 0;
+	portdata->dtr_state = 0;
+
+	if (serial->dev) {
+		mutex_lock(&serial->disc_mutex);
+		if (!serial->disconnected)
+			sierra_send_setup(port);
+		mutex_unlock(&serial->disc_mutex);
+
+		/* Stop reading urbs */
+		sierra_stop_rx_urbs(port);
+		/* .. and release them */
+		for (i = 0; i < N_IN_URB; i++) {
+			sierra_release_urb(portdata->in_urbs[i]);
+			portdata->in_urbs[i] = NULL;
+		}
+	}
+}
+
 static int sierra_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp)
 {
 	struct sierra_port_private *portdata;
 	struct usb_serial *serial = port->serial;
 	int i;
+	int err;
+	int endpoint;
 	struct urb *urb;
-	int result;
 
 	portdata = usb_get_serial_port_data(port);
 
@@ -574,77 +735,52 @@ static int sierra_open(struct tty_struct *tty,
 	portdata->rts_state = 1;
 	portdata->dtr_state = 1;
 
-	/* Reset low level data toggle and start reading from endpoints */
-	for (i = 0; i < N_IN_URB; i++) {
-		urb = portdata->in_urbs[i];
-		if (!urb)
-			continue;
-		if (urb->dev != serial->dev) {
-			dev_dbg(&port->dev, "%s: dev %p != %p",
-				 __func__, urb->dev, serial->dev);
-			continue;
-		}
 
-		/*
-		 * make sure endpoint data toggle is synchronized with the
-		 * device
-		 */
-		usb_clear_halt(urb->dev, urb->pipe);
-
-		result = usb_submit_urb(urb, GFP_KERNEL);
-		if (result) {
-			dev_err(&port->dev, "submit urb %d failed (%d) %d\n",
-				i, result, urb->transfer_buffer_length);
-		}
+	endpoint = port->bulk_in_endpointAddress;
+	for (i = 0; i < ARRAY_SIZE(portdata->in_urbs); i++) {
+		urb = sierra_setup_urb(serial, endpoint, USB_DIR_IN, port,
+					IN_BUFLEN, GFP_KERNEL,
+					sierra_indat_callback);
+		portdata->in_urbs[i] = urb;
 	}
+	/* clear halt condition */
+	usb_clear_halt(serial->dev,
+			usb_sndbulkpipe(serial->dev, endpoint) | USB_DIR_IN);
 
-	sierra_send_setup(tty, port);
-
-	/* start up the interrupt endpoint if we have one */
-	if (port->interrupt_in_urb) {
-		result = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
-		if (result)
-			dev_err(&port->dev, "submit irq_in urb failed %d\n",
-				result);
+	err = sierra_submit_rx_urbs(port, GFP_KERNEL);
+	if (err) {
+		/* get rid of everything as in close */
+		sierra_close(port);
+		return err;
 	}
+	sierra_send_setup(port);
+
 	return 0;
 }
 
-static void sierra_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+
+static void sierra_dtr_rts(struct usb_serial_port *port, int on)
 {
-	int i;
 	struct usb_serial *serial = port->serial;
 	struct sierra_port_private *portdata;
 
-	dev_dbg(&port->dev, "%s", __func__);
 	portdata = usb_get_serial_port_data(port);
-
-	portdata->rts_state = 0;
-	portdata->dtr_state = 0;
+	portdata->rts_state = on;
+	portdata->dtr_state = on;
 
 	if (serial->dev) {
 		mutex_lock(&serial->disc_mutex);
 		if (!serial->disconnected)
-			sierra_send_setup(tty, port);
+			sierra_send_setup(port);
 		mutex_unlock(&serial->disc_mutex);
-
-		/* Stop reading/writing urbs */
-		for (i = 0; i < N_IN_URB; i++)
-			usb_kill_urb(portdata->in_urbs[i]);
 	}
-
-	usb_kill_urb(port->interrupt_in_urb);
-	tty_port_tty_set(&port->port, NULL);
 }
 
 static int sierra_startup(struct usb_serial *serial)
 {
 	struct usb_serial_port *port;
 	struct sierra_port_private *portdata;
-	struct urb *urb;
 	int i;
-	int j;
 
 	dev_dbg(&serial->dev->dev, "%s", __func__);
 
@@ -666,34 +802,8 @@ static int sierra_startup(struct usb_serial *serial)
 			return -ENOMEM;
 		}
 		spin_lock_init(&portdata->lock);
-		for (j = 0; j < N_IN_URB; j++) {
-			portdata->in_buffer[j] = kmalloc(IN_BUFLEN, GFP_KERNEL);
-			if (!portdata->in_buffer[j]) {
-				for (--j; j >= 0; j--)
-					kfree(portdata->in_buffer[j]);
-				kfree(portdata);
-				return -ENOMEM;
-			}
-		}
-
+		/* Set the port private data pointer */
 		usb_set_serial_port_data(port, portdata);
-
-		/* initialize the in urbs */
-		for (j = 0; j < N_IN_URB; ++j) {
-			urb = usb_alloc_urb(0, GFP_KERNEL);
-			if (urb == NULL) {
-				dev_dbg(&port->dev, "%s: alloc for in "
-					"port failed.", __func__);
-				continue;
-			}
-			/* Fill URB using supplied data. */
-			usb_fill_bulk_urb(urb, serial->dev,
-					  usb_rcvbulkpipe(serial->dev,
-						port->bulk_in_endpointAddress),
-					  portdata->in_buffer[j], IN_BUFLEN,
-					  sierra_indat_callback, port);
-			portdata->in_urbs[j] = urb;
-		}
 	}
 
 	return 0;
@@ -701,7 +811,7 @@ static int sierra_startup(struct usb_serial *serial)
 
 static void sierra_shutdown(struct usb_serial *serial)
 {
-	int i, j;
+	int i;
 	struct usb_serial_port *port;
 	struct sierra_port_private *portdata;
 
@@ -714,12 +824,6 @@ static void sierra_shutdown(struct usb_serial *serial)
 		portdata = usb_get_serial_port_data(port);
 		if (!portdata)
 			continue;
-
-		for (j = 0; j < N_IN_URB; j++) {
-			usb_kill_urb(portdata->in_urbs[j]);
-			usb_free_urb(portdata->in_urbs[j]);
-			kfree(portdata->in_buffer[j]);
-		}
 		kfree(portdata);
 		usb_set_serial_port_data(port, NULL);
 	}
@@ -737,6 +841,7 @@ static struct usb_serial_driver sierra_device = {
 	.probe		   = sierra_probe,
 	.open              = sierra_open,
 	.close             = sierra_close,
+	.dtr_rts	   = sierra_dtr_rts,
 	.write             = sierra_write,
 	.write_room        = sierra_write_room,
 	.set_termios       = sierra_set_termios,
diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c
index 5e7528cc81a8..8f7ed8f13996 100644
--- a/drivers/usb/serial/spcp8x5.c
+++ b/drivers/usb/serial/spcp8x5.c
@@ -446,66 +446,47 @@ static void spcp8x5_set_workMode(struct usb_device *dev, u16 value,
 			"RTSCTS usb_control_msg(enable flowctrl) = %d\n", ret);
 }
 
-/* close the serial port. We should wait for data sending to device 1st and
- * then kill all urb. */
-static void spcp8x5_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static int spcp8x5_carrier_raised(struct usb_serial_port *port)
+{
+	struct spcp8x5_private *priv = usb_get_serial_port_data(port);
+	if (priv->line_status & MSR_STATUS_LINE_DCD)
+		return 1;
+	return 0;
+}
+
+static void spcp8x5_dtr_rts(struct usb_serial_port *port, int on)
+{
+	struct spcp8x5_private *priv = usb_get_serial_port_data(port);
+	unsigned long flags;
+	u8 control;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (on)
+		priv->line_control = MCR_CONTROL_LINE_DTR
+						| MCR_CONTROL_LINE_RTS;
+	else
+		priv->line_control &= ~ (MCR_CONTROL_LINE_DTR
+						| MCR_CONTROL_LINE_RTS);
+	control = priv->line_control;
+	spin_unlock_irqrestore(&priv->lock, flags);
+	spcp8x5_set_ctrlLine(port->serial->dev, control , priv->type);
+}
+
+/* close the serial port. We should wait for data sending to device 1st and
+ * then kill all urb. */
+static void spcp8x5_close(struct usb_serial_port *port)
 {
 	struct spcp8x5_private *priv = usb_get_serial_port_data(port);
 	unsigned long flags;
-	unsigned int c_cflag;
-	int bps;
-	long timeout;
-	wait_queue_t wait;
 	int result;
 
 	dbg("%s - port %d", __func__, port->number);
 
-	/* wait for data to drain from the buffer */
 	spin_lock_irqsave(&priv->lock, flags);
-	timeout = SPCP8x5_CLOSING_WAIT;
-	init_waitqueue_entry(&wait, current);
-	add_wait_queue(&tty->write_wait, &wait);
-	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (ringbuf_avail_data(priv->buf) == 0 ||
-		    timeout == 0 || signal_pending(current))
-			break;
-		spin_unlock_irqrestore(&priv->lock, flags);
-		timeout = schedule_timeout(timeout);
-		spin_lock_irqsave(&priv->lock, flags);
-	}
-	set_current_state(TASK_RUNNING);
-	remove_wait_queue(&tty->write_wait, &wait);
-
 	/* clear out any remaining data in the buffer */
 	clear_ringbuf(priv->buf);
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	/* wait for characters to drain from the device (this is long enough
-	 * for the entire all byte spcp8x5 hardware buffer to drain with no
-	 * flow control for data rates of 1200 bps or more, for lower rates we
-	 * should really know how much data is in the buffer to compute a delay
-	 * that is not unnecessarily long) */
-	bps = tty_get_baud_rate(tty);
-	if (bps > 1200)
-		timeout = max((HZ*2560) / bps, HZ/10);
-	else
-		timeout = 2*HZ;
-	set_current_state(TASK_INTERRUPTIBLE);
-	schedule_timeout(timeout);
-
-	/* clear control lines */
-	if (tty) {
-		c_cflag = tty->termios->c_cflag;
-		if (c_cflag & HUPCL) {
-			spin_lock_irqsave(&priv->lock, flags);
-			priv->line_control = 0;
-			spin_unlock_irqrestore(&priv->lock, flags);
-			spcp8x5_set_ctrlLine(port->serial->dev, 0 , priv->type);
-		}
-	}
-
 	/* kill urb */
 	if (port->write_urb != NULL) {
 		result = usb_unlink_urb(port->write_urb);
@@ -665,13 +646,6 @@ static int spcp8x5_open(struct tty_struct *tty,
 	if (ret)
 		return ret;
 
-	spin_lock_irqsave(&priv->lock, flags);
-	if (tty && (tty->termios->c_cflag & CBAUD))
-		priv->line_control = MCR_DTR | MCR_RTS;
-	else
-		priv->line_control = 0;
-	spin_unlock_irqrestore(&priv->lock, flags);
-
 	spcp8x5_set_ctrlLine(serial->dev, priv->line_control , priv->type);
 
 	/* Setup termios */
@@ -691,9 +665,10 @@ static int spcp8x5_open(struct tty_struct *tty,
 	port->read_urb->dev = serial->dev;
 	ret = usb_submit_urb(port->read_urb, GFP_KERNEL);
 	if (ret) {
-		spcp8x5_close(tty, port, NULL);
+		spcp8x5_close(port);
 		return -EPROTO;
 	}
+	port->port.drain_delay = 256;
 	return 0;
 }
 
@@ -1033,6 +1008,8 @@ static struct usb_serial_driver spcp8x5_device = {
 	.num_ports		= 1,
 	.open 			= spcp8x5_open,
 	.close 			= spcp8x5_close,
+	.dtr_rts		= spcp8x5_dtr_rts,
+	.carrier_raised		= spcp8x5_carrier_raised,
 	.write 			= spcp8x5_write,
 	.set_termios 		= spcp8x5_set_termios,
 	.ioctl 			= spcp8x5_ioctl,
diff --git a/drivers/usb/serial/symbolserial.c b/drivers/usb/serial/symbolserial.c
index 69879e437940..8b07ebc6baeb 100644
--- a/drivers/usb/serial/symbolserial.c
+++ b/drivers/usb/serial/symbolserial.c
@@ -152,8 +152,7 @@ static int symbol_open(struct tty_struct *tty, struct usb_serial_port *port,
 	return result;
 }
 
-static void symbol_close(struct tty_struct *tty, struct usb_serial_port *port,
-			  struct file *filp)
+static void symbol_close(struct usb_serial_port *port)
 {
 	struct symbol_private *priv = usb_get_serial_data(port->serial);
 
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index 0a64bac306ee..42cb04c403be 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -100,8 +100,7 @@ static int ti_startup(struct usb_serial *serial);
 static void ti_shutdown(struct usb_serial *serial);
 static int ti_open(struct tty_struct *tty, struct usb_serial_port *port,
 		struct file *file);
-static void ti_close(struct tty_struct *tty, struct usb_serial_port *port,
-		struct file *file);
+static void ti_close(struct usb_serial_port *port);
 static int ti_write(struct tty_struct *tty, struct usb_serial_port *port,
 		const unsigned char *data, int count);
 static int ti_write_room(struct tty_struct *tty);
@@ -647,8 +646,7 @@ release_lock:
 }
 
 
-static void ti_close(struct tty_struct *tty, struct usb_serial_port *port,
-							struct file *file)
+static void ti_close(struct usb_serial_port *port)
 {
 	struct ti_device *tdev;
 	struct ti_port *tport;
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index f331e2bde88a..1967a7edc10c 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -238,9 +238,11 @@ static int serial_open (struct tty_struct *tty, struct file *filp)
 			goto bailout_interface_put;
 		mutex_unlock(&serial->disc_mutex);
 	}
-
 	mutex_unlock(&port->mutex);
-	return 0;
+	/* Now do the correct tty layer semantics */
+	retval = tty_port_block_til_ready(&port->port, tty, filp);
+	if (retval == 0)
+		return 0;
 
 bailout_interface_put:
 	usb_autopm_put_interface(serial->interface);
@@ -259,64 +261,89 @@ bailout_serial_put:
 	return retval;
 }
 
-static void serial_close(struct tty_struct *tty, struct file *filp)
+/**
+ *	serial_do_down		-	shut down hardware
+ *	@port: port to shut down
+ *
+ *	Shut down a USB port unless it is the console. We never shut down the
+ *	console hardware as it will always be in use.
+ *
+ *	Don't free any resources at this point
+ */
+static void serial_do_down(struct usb_serial_port *port)
 {
-	struct usb_serial_port *port = tty->driver_data;
+	struct usb_serial_driver *drv = port->serial->type;
 	struct usb_serial *serial;
 	struct module *owner;
-	int count;
 
-	if (!port)
+	/* The console is magical, do not hang up the console hardware
+	   or there will be tears */
+	if (port->console)
 		return;
 
-	dbg("%s - port %d", __func__, port->number);
-
 	mutex_lock(&port->mutex);
 	serial = port->serial;
 	owner = serial->type->driver.owner;
 
-	if (port->port.count == 0) {
-		mutex_unlock(&port->mutex);
-		return;
-	}
+	if (drv->close)
+		drv->close(port);
 
-	if (port->port.count == 1)
-		/* only call the device specific close if this
-		 * port is being closed by the last owner. Ensure we do
-		 * this before we drop the port count. The call is protected
-		 * by the port mutex
-		 */
-		serial->type->close(tty, port, filp);
-
-	if (port->port.count == (port->console ? 2 : 1)) {
-		struct tty_struct *tty = tty_port_tty_get(&port->port);
-		if (tty) {
-			/* We must do this before we drop the port count to
-			   zero. */
-			if (tty->driver_data)
-				tty->driver_data = NULL;
-			tty_port_tty_set(&port->port, NULL);
-			tty_kref_put(tty);
-		}
-	}
-
-	--port->port.count;
-	count = port->port.count;
 	mutex_unlock(&port->mutex);
+}
+
+/**
+ *	serial_do_free		-	free resources post close/hangup
+ *	@port: port to free up
+ *
+ *	Do the resource freeing and refcount dropping for the port. We must
+ *	be careful about ordering and we must avoid freeing up the console.
+ */
+
+static void serial_do_free(struct usb_serial_port *port)
+{
+	struct usb_serial *serial;
+	struct module *owner;
+
+	/* The console is magical, do not hang up the console hardware
+	   or there will be tears */
+	if (port->console)
+		return;
+
+	serial = port->serial;
+	owner = serial->type->driver.owner;
 	put_device(&port->dev);
-
 	/* Mustn't dereference port any more */
-	if (count == 0) {
-		mutex_lock(&serial->disc_mutex);
-		if (!serial->disconnected)
-			usb_autopm_put_interface(serial->interface);
-		mutex_unlock(&serial->disc_mutex);
-	}
+	mutex_lock(&serial->disc_mutex);
+	if (!serial->disconnected)
+		usb_autopm_put_interface(serial->interface);
+	mutex_unlock(&serial->disc_mutex);
 	usb_serial_put(serial);
-
 	/* Mustn't dereference serial any more */
-	if (count == 0)
-		module_put(owner);
+	module_put(owner);
+}
+
+static void serial_close(struct tty_struct *tty, struct file *filp)
+{
+	struct usb_serial_port *port = tty->driver_data;
+
+	dbg("%s - port %d", __func__, port->number);
+
+
+	if (tty_port_close_start(&port->port, tty, filp) == 0)
+		return;
+
+	serial_do_down(port);		
+	tty_port_close_end(&port->port, tty);
+	tty_port_tty_set(&port->port, NULL);
+	serial_do_free(port);
+}
+
+static void serial_hangup(struct tty_struct *tty)
+{
+	struct usb_serial_port *port = tty->driver_data;
+	serial_do_down(port);
+	tty_port_hangup(&port->port);
+	serial_do_free(port);
 }
 
 static int serial_write(struct tty_struct *tty, const unsigned char *buf,
@@ -648,6 +675,29 @@ static struct usb_serial_driver *search_serial_device(
 	return NULL;
 }
 
+static int serial_carrier_raised(struct tty_port *port)
+{
+	struct usb_serial_port *p = container_of(port, struct usb_serial_port, port);
+	struct usb_serial_driver *drv = p->serial->type;
+	if (drv->carrier_raised)
+		return drv->carrier_raised(p);
+	/* No carrier control - don't block */
+	return 1;	
+}
+
+static void serial_dtr_rts(struct tty_port *port, int on)
+{
+	struct usb_serial_port *p = container_of(port, struct usb_serial_port, port);
+	struct usb_serial_driver *drv = p->serial->type;
+	if (drv->dtr_rts)
+		drv->dtr_rts(p, on);
+}
+
+static const struct tty_port_operations serial_port_ops = {
+	.carrier_raised = serial_carrier_raised,
+	.dtr_rts = serial_dtr_rts,
+};
+
 int usb_serial_probe(struct usb_interface *interface,
 			       const struct usb_device_id *id)
 {
@@ -841,6 +891,7 @@ int usb_serial_probe(struct usb_interface *interface,
 		if (!port)
 			goto probe_error;
 		tty_port_init(&port->port);
+		port->port.ops = &serial_port_ops;
 		port->serial = serial;
 		spin_lock_init(&port->lock);
 		mutex_init(&port->mutex);
@@ -1071,6 +1122,9 @@ void usb_serial_disconnect(struct usb_interface *interface)
 		if (port) {
 			struct tty_struct *tty = tty_port_tty_get(&port->port);
 			if (tty) {
+				/* The hangup will occur asynchronously but
+				   the object refcounts will sort out all the
+				   cleanup */
 				tty_hangup(tty);
 				tty_kref_put(tty);
 			}
@@ -1135,6 +1189,7 @@ static const struct tty_operations serial_ops = {
 	.open =			serial_open,
 	.close =		serial_close,
 	.write =		serial_write,
+	.hangup = 		serial_hangup,
 	.write_room =		serial_write_room,
 	.ioctl =		serial_ioctl,
 	.set_termios =		serial_set_termios,
@@ -1147,6 +1202,7 @@ static const struct tty_operations serial_ops = {
 	.proc_fops =		&serial_proc_fops,
 };
 
+
 struct tty_driver *usb_serial_tty_driver;
 
 static int __init usb_serial_init(void)
diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c
index 5ac414bda718..b15f1c0e1d4a 100644
--- a/drivers/usb/serial/visor.c
+++ b/drivers/usb/serial/visor.c
@@ -38,8 +38,7 @@
 /* function prototypes for a handspring visor */
 static int  visor_open(struct tty_struct *tty, struct usb_serial_port *port,
 					struct file *filp);
-static void visor_close(struct tty_struct *tty, struct usb_serial_port *port,
-					struct file *filp);
+static void visor_close(struct usb_serial_port *port);
 static int  visor_write(struct tty_struct *tty, struct usb_serial_port *port,
 					const unsigned char *buf, int count);
 static int  visor_write_room(struct tty_struct *tty);
@@ -324,8 +323,7 @@ exit:
 }
 
 
-static void visor_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void visor_close(struct usb_serial_port *port)
 {
 	struct visor_private *priv = usb_get_serial_port_data(port);
 	unsigned char *transfer_buffer;
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index 5335d3211c07..7c7295d09f34 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -147,8 +147,7 @@ static int  whiteheat_attach(struct usb_serial *serial);
 static void whiteheat_shutdown(struct usb_serial *serial);
 static int  whiteheat_open(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-static void whiteheat_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+static void whiteheat_close(struct usb_serial_port *port);
 static int  whiteheat_write(struct tty_struct *tty,
 			struct usb_serial_port *port,
 			const unsigned char *buf, int count);
@@ -712,8 +711,7 @@ exit:
 }
 
 
-static void whiteheat_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp)
+static void whiteheat_close(struct usb_serial_port *port)
 {
 	struct whiteheat_private *info = usb_get_serial_port_data(port);
 	struct whiteheat_urb_wrap *wrap;
@@ -723,31 +721,7 @@ static void whiteheat_close(struct tty_struct *tty,
 
 	dbg("%s - port %d", __func__, port->number);
 
-	mutex_lock(&port->serial->disc_mutex);
-	/* filp is NULL when called from usb_serial_disconnect */
-	if ((filp && (tty_hung_up_p(filp))) || port->serial->disconnected) {
-		mutex_unlock(&port->serial->disc_mutex);
-		return;
-	}
-	mutex_unlock(&port->serial->disc_mutex);
-
-	tty->closing = 1;
-
-/*
- * Not currently in use; tty_wait_until_sent() calls
- * serial_chars_in_buffer() which deadlocks on the second semaphore
- * acquisition. This should be fixed at some point. Greg's been
- * notified.
-	if ((filp->f_flags & (O_NDELAY | O_NONBLOCK)) == 0) {
-		tty_wait_until_sent(tty, CLOSING_DELAY);
-	}
-*/
-
-	tty_driver_flush_buffer(tty);
-	tty_ldisc_flush(tty);
-
 	firm_report_tx_done(port);
-
 	firm_close(port);
 
 	/* shutdown our bulk reads and writes */
@@ -775,10 +749,7 @@ static void whiteheat_close(struct tty_struct *tty,
 	}
 	spin_unlock_irq(&info->lock);
 	mutex_unlock(&info->deathwarrant);
-
 	stop_command_port(port->serial);
-
-	tty->closing = 0;
 }
 
 
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 4ca3b5860643..cfa26d56ce60 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -132,7 +132,7 @@ static int slave_configure(struct scsi_device *sdev)
 
 		if (us->fflags & US_FL_MAX_SECTORS_MIN)
 			max_sectors = PAGE_CACHE_SIZE >> 9;
-		if (sdev->request_queue->max_sectors > max_sectors)
+		if (queue_max_sectors(sdev->request_queue) > max_sectors)
 			blk_queue_max_sectors(sdev->request_queue,
 					      max_sectors);
 	} else if (sdev->type == TYPE_TAPE) {
@@ -483,7 +483,7 @@ static ssize_t show_max_sectors(struct device *dev, struct device_attribute *att
 {
 	struct scsi_device *sdev = to_scsi_device(dev);
 
-	return sprintf(buf, "%u\n", sdev->request_queue->max_sectors);
+	return sprintf(buf, "%u\n", queue_max_sectors(sdev->request_queue));
 }
 
 /* Input routine for the sysfs max_sectors file */
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index 38e86b84dce0..59d7d5ec17a4 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -180,7 +180,7 @@ static inline void vga_set_mem_top(struct vc_data *c)
 }
 
 #ifdef CONFIG_VGACON_SOFT_SCROLLBACK
-#include <linux/bootmem.h>
+#include <linux/slab.h>
 /* software scrollback */
 static void *vgacon_scrollback;
 static int vgacon_scrollback_tail;
@@ -210,8 +210,7 @@ static void vgacon_scrollback_init(int pitch)
  */
 static void __init_refok vgacon_scrollback_startup(void)
 {
-	vgacon_scrollback = alloc_bootmem(CONFIG_VGACON_SOFT_SCROLLBACK_SIZE
-					  * 1024);
+	vgacon_scrollback = kcalloc(CONFIG_VGACON_SOFT_SCROLLBACK_SIZE, 1024, GFP_NOWAIT);
 	vgacon_scrollback_init(vga_video_num_columns * 2);
 }
 
diff --git a/drivers/video/hitfb.c b/drivers/video/hitfb.c
index e6467cf9f19f..020db7fc9153 100644
--- a/drivers/video/hitfb.c
+++ b/drivers/video/hitfb.c
@@ -335,9 +335,9 @@ static int __init hitfb_probe(struct platform_device *dev)
 	if (fb_get_options("hitfb", NULL))
 		return -ENODEV;
 
-	hitfb_fix.mmio_start = CONFIG_HD64461_IOBASE+0x1000;
+	hitfb_fix.mmio_start = HD64461_IO_OFFSET(0x1000);
 	hitfb_fix.mmio_len = 0x1000;
-	hitfb_fix.smem_start = CONFIG_HD64461_IOBASE + 0x02000000;
+	hitfb_fix.smem_start = HD64461_IO_OFFSET(0x02000000);
 	hitfb_fix.smem_len = 512 * 1024;
 
 	lcdclor = fb_readw(HD64461_LCDCLOR);
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 8ac9cddac575..cab100acf983 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -18,6 +18,16 @@ config XEN_SCRUB_PAGES
 	  secure, but slightly less efficient.
 	  If in doubt, say yes.
 
+config XEN_DEV_EVTCHN
+	tristate "Xen /dev/xen/evtchn device"
+	depends on XEN
+	default y
+	help
+	  The evtchn driver allows a userspace process to triger event
+	  channels and to receive notification of an event channel
+	  firing.
+	  If in doubt, say yes.
+
 config XENFS
 	tristate "Xen filesystem"
 	depends on XEN
@@ -41,3 +51,13 @@ config XEN_COMPAT_XENFS
          a xen platform.
          If in doubt, say yes.
 
+config XEN_SYS_HYPERVISOR
+       bool "Create xen entries under /sys/hypervisor"
+       depends on XEN && SYSFS
+       select SYS_HYPERVISOR
+       default y
+       help
+         Create entries under /sys/hypervisor describing the Xen
+	 hypervisor environment.  When running native or in another
+	 virtual environment, /sys/hypervisor will still be present,
+	 but will have no xen contents.
\ No newline at end of file
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index ff8accc9e103..ec2a39b1e26f 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -4,4 +4,6 @@ obj-y	+= xenbus/
 obj-$(CONFIG_HOTPLUG_CPU)	+= cpu_hotplug.o
 obj-$(CONFIG_XEN_XENCOMM)	+= xencomm.o
 obj-$(CONFIG_XEN_BALLOON)	+= balloon.o
-obj-$(CONFIG_XENFS)		+= xenfs/
\ No newline at end of file
+obj-$(CONFIG_XEN_DEV_EVTCHN)	+= evtchn.o
+obj-$(CONFIG_XENFS)		+= xenfs/
+obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
\ No newline at end of file
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 30963af5dba0..891d2e90753a 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -151,6 +151,12 @@ static unsigned int evtchn_from_irq(unsigned irq)
 	return info_for_irq(irq)->evtchn;
 }
 
+unsigned irq_from_evtchn(unsigned int evtchn)
+{
+	return evtchn_to_irq[evtchn];
+}
+EXPORT_SYMBOL_GPL(irq_from_evtchn);
+
 static enum ipi_vector ipi_from_irq(unsigned irq)
 {
 	struct irq_info *info = info_for_irq(irq);
@@ -335,7 +341,7 @@ static int find_unbound_irq(void)
 	if (irq == nr_irqs)
 		panic("No available IRQ to bind to: increase nr_irqs!\n");
 
-	desc = irq_to_desc_alloc_cpu(irq, 0);
+	desc = irq_to_desc_alloc_node(irq, 0);
 	if (WARN_ON(desc == NULL))
 		return -1;
 
@@ -688,13 +694,13 @@ void rebind_evtchn_irq(int evtchn, int irq)
 }
 
 /* Rebind an evtchn so that it gets delivered to a specific cpu */
-static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
+static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 {
 	struct evtchn_bind_vcpu bind_vcpu;
 	int evtchn = evtchn_from_irq(irq);
 
 	if (!VALID_EVTCHN(evtchn))
-		return;
+		return -1;
 
 	/* Send future instances of this interrupt to other vcpu. */
 	bind_vcpu.port = evtchn;
@@ -707,13 +713,15 @@ static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 	 */
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
 		bind_evtchn_to_cpu(evtchn, tcpu);
+
+	return 0;
 }
 
-
-static void set_affinity_irq(unsigned irq, const struct cpumask *dest)
+static int set_affinity_irq(unsigned irq, const struct cpumask *dest)
 {
 	unsigned tcpu = cpumask_first(dest);
-	rebind_irq_to_cpu(irq, tcpu);
+
+	return rebind_irq_to_cpu(irq, tcpu);
 }
 
 int resend_irq_on_evtchn(unsigned int irq)
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
new file mode 100644
index 000000000000..af031950f9b1
--- /dev/null
+++ b/drivers/xen/evtchn.c
@@ -0,0 +1,507 @@
+/******************************************************************************
+ * evtchn.c
+ *
+ * Driver for receiving and demuxing event-channel signals.
+ *
+ * Copyright (c) 2004-2005, K A Fraser
+ * Multi-process extensions Copyright (c) 2004, Steven Smith
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/errno.h>
+#include <linux/miscdevice.h>
+#include <linux/major.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/poll.h>
+#include <linux/irq.h>
+#include <linux/init.h>
+#include <linux/gfp.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+#include <xen/events.h>
+#include <xen/evtchn.h>
+#include <asm/xen/hypervisor.h>
+
+struct per_user_data {
+	struct mutex bind_mutex; /* serialize bind/unbind operations */
+
+	/* Notification ring, accessed via /dev/xen/evtchn. */
+#define EVTCHN_RING_SIZE     (PAGE_SIZE / sizeof(evtchn_port_t))
+#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
+	evtchn_port_t *ring;
+	unsigned int ring_cons, ring_prod, ring_overflow;
+	struct mutex ring_cons_mutex; /* protect against concurrent readers */
+
+	/* Processes wait on this queue when ring is empty. */
+	wait_queue_head_t evtchn_wait;
+	struct fasync_struct *evtchn_async_queue;
+	const char *name;
+};
+
+/* Who's bound to each port? */
+static struct per_user_data *port_user[NR_EVENT_CHANNELS];
+static DEFINE_SPINLOCK(port_user_lock); /* protects port_user[] and ring_prod */
+
+irqreturn_t evtchn_interrupt(int irq, void *data)
+{
+	unsigned int port = (unsigned long)data;
+	struct per_user_data *u;
+
+	spin_lock(&port_user_lock);
+
+	u = port_user[port];
+
+	disable_irq_nosync(irq);
+
+	if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
+		u->ring[EVTCHN_RING_MASK(u->ring_prod)] = port;
+		wmb(); /* Ensure ring contents visible */
+		if (u->ring_cons == u->ring_prod++) {
+			wake_up_interruptible(&u->evtchn_wait);
+			kill_fasync(&u->evtchn_async_queue,
+				    SIGIO, POLL_IN);
+		}
+	} else {
+		u->ring_overflow = 1;
+	}
+
+	spin_unlock(&port_user_lock);
+
+	return IRQ_HANDLED;
+}
+
+static ssize_t evtchn_read(struct file *file, char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	int rc;
+	unsigned int c, p, bytes1 = 0, bytes2 = 0;
+	struct per_user_data *u = file->private_data;
+
+	/* Whole number of ports. */
+	count &= ~(sizeof(evtchn_port_t)-1);
+
+	if (count == 0)
+		return 0;
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	for (;;) {
+		mutex_lock(&u->ring_cons_mutex);
+
+		rc = -EFBIG;
+		if (u->ring_overflow)
+			goto unlock_out;
+
+		c = u->ring_cons;
+		p = u->ring_prod;
+		if (c != p)
+			break;
+
+		mutex_unlock(&u->ring_cons_mutex);
+
+		if (file->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+
+		rc = wait_event_interruptible(u->evtchn_wait,
+					      u->ring_cons != u->ring_prod);
+		if (rc)
+			return rc;
+	}
+
+	/* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
+	if (((c ^ p) & EVTCHN_RING_SIZE) != 0) {
+		bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) *
+			sizeof(evtchn_port_t);
+		bytes2 = EVTCHN_RING_MASK(p) * sizeof(evtchn_port_t);
+	} else {
+		bytes1 = (p - c) * sizeof(evtchn_port_t);
+		bytes2 = 0;
+	}
+
+	/* Truncate chunks according to caller's maximum byte count. */
+	if (bytes1 > count) {
+		bytes1 = count;
+		bytes2 = 0;
+	} else if ((bytes1 + bytes2) > count) {
+		bytes2 = count - bytes1;
+	}
+
+	rc = -EFAULT;
+	rmb(); /* Ensure that we see the port before we copy it. */
+	if (copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
+	    ((bytes2 != 0) &&
+	     copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
+		goto unlock_out;
+
+	u->ring_cons += (bytes1 + bytes2) / sizeof(evtchn_port_t);
+	rc = bytes1 + bytes2;
+
+ unlock_out:
+	mutex_unlock(&u->ring_cons_mutex);
+	return rc;
+}
+
+static ssize_t evtchn_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	int rc, i;
+	evtchn_port_t *kbuf = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+	struct per_user_data *u = file->private_data;
+
+	if (kbuf == NULL)
+		return -ENOMEM;
+
+	/* Whole number of ports. */
+	count &= ~(sizeof(evtchn_port_t)-1);
+
+	rc = 0;
+	if (count == 0)
+		goto out;
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+
+	rc = -EFAULT;
+	if (copy_from_user(kbuf, buf, count) != 0)
+		goto out;
+
+	spin_lock_irq(&port_user_lock);
+	for (i = 0; i < (count/sizeof(evtchn_port_t)); i++)
+		if ((kbuf[i] < NR_EVENT_CHANNELS) && (port_user[kbuf[i]] == u))
+			enable_irq(irq_from_evtchn(kbuf[i]));
+	spin_unlock_irq(&port_user_lock);
+
+	rc = count;
+
+ out:
+	free_page((unsigned long)kbuf);
+	return rc;
+}
+
+static int evtchn_bind_to_user(struct per_user_data *u, int port)
+{
+	int rc = 0;
+
+	/*
+	 * Ports are never reused, so every caller should pass in a
+	 * unique port.
+	 *
+	 * (Locking not necessary because we haven't registered the
+	 * interrupt handler yet, and our caller has already
+	 * serialized bind operations.)
+	 */
+	BUG_ON(port_user[port] != NULL);
+	port_user[port] = u;
+
+	rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, IRQF_DISABLED,
+				       u->name, (void *)(unsigned long)port);
+	if (rc >= 0)
+		rc = 0;
+
+	return rc;
+}
+
+static void evtchn_unbind_from_user(struct per_user_data *u, int port)
+{
+	int irq = irq_from_evtchn(port);
+
+	unbind_from_irqhandler(irq, (void *)(unsigned long)port);
+
+	/* make sure we unbind the irq handler before clearing the port */
+	barrier();
+
+	port_user[port] = NULL;
+}
+
+static long evtchn_ioctl(struct file *file,
+			 unsigned int cmd, unsigned long arg)
+{
+	int rc;
+	struct per_user_data *u = file->private_data;
+	void __user *uarg = (void __user *) arg;
+
+	/* Prevent bind from racing with unbind */
+	mutex_lock(&u->bind_mutex);
+
+	switch (cmd) {
+	case IOCTL_EVTCHN_BIND_VIRQ: {
+		struct ioctl_evtchn_bind_virq bind;
+		struct evtchn_bind_virq bind_virq;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		bind_virq.virq = bind.virq;
+		bind_virq.vcpu = 0;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
+						 &bind_virq);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, bind_virq.port);
+		if (rc == 0)
+			rc = bind_virq.port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_BIND_INTERDOMAIN: {
+		struct ioctl_evtchn_bind_interdomain bind;
+		struct evtchn_bind_interdomain bind_interdomain;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		bind_interdomain.remote_dom  = bind.remote_domain;
+		bind_interdomain.remote_port = bind.remote_port;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+						 &bind_interdomain);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
+		if (rc == 0)
+			rc = bind_interdomain.local_port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_BIND_UNBOUND_PORT: {
+		struct ioctl_evtchn_bind_unbound_port bind;
+		struct evtchn_alloc_unbound alloc_unbound;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		alloc_unbound.dom        = DOMID_SELF;
+		alloc_unbound.remote_dom = bind.remote_domain;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+						 &alloc_unbound);
+		if (rc != 0)
+			break;
+
+		rc = evtchn_bind_to_user(u, alloc_unbound.port);
+		if (rc == 0)
+			rc = alloc_unbound.port;
+		break;
+	}
+
+	case IOCTL_EVTCHN_UNBIND: {
+		struct ioctl_evtchn_unbind unbind;
+
+		rc = -EFAULT;
+		if (copy_from_user(&unbind, uarg, sizeof(unbind)))
+			break;
+
+		rc = -EINVAL;
+		if (unbind.port >= NR_EVENT_CHANNELS)
+			break;
+
+		spin_lock_irq(&port_user_lock);
+
+		rc = -ENOTCONN;
+		if (port_user[unbind.port] != u) {
+			spin_unlock_irq(&port_user_lock);
+			break;
+		}
+
+		evtchn_unbind_from_user(u, unbind.port);
+
+		spin_unlock_irq(&port_user_lock);
+
+		rc = 0;
+		break;
+	}
+
+	case IOCTL_EVTCHN_NOTIFY: {
+		struct ioctl_evtchn_notify notify;
+
+		rc = -EFAULT;
+		if (copy_from_user(&notify, uarg, sizeof(notify)))
+			break;
+
+		if (notify.port >= NR_EVENT_CHANNELS) {
+			rc = -EINVAL;
+		} else if (port_user[notify.port] != u) {
+			rc = -ENOTCONN;
+		} else {
+			notify_remote_via_evtchn(notify.port);
+			rc = 0;
+		}
+		break;
+	}
+
+	case IOCTL_EVTCHN_RESET: {
+		/* Initialise the ring to empty. Clear errors. */
+		mutex_lock(&u->ring_cons_mutex);
+		spin_lock_irq(&port_user_lock);
+		u->ring_cons = u->ring_prod = u->ring_overflow = 0;
+		spin_unlock_irq(&port_user_lock);
+		mutex_unlock(&u->ring_cons_mutex);
+		rc = 0;
+		break;
+	}
+
+	default:
+		rc = -ENOSYS;
+		break;
+	}
+	mutex_unlock(&u->bind_mutex);
+
+	return rc;
+}
+
+static unsigned int evtchn_poll(struct file *file, poll_table *wait)
+{
+	unsigned int mask = POLLOUT | POLLWRNORM;
+	struct per_user_data *u = file->private_data;
+
+	poll_wait(file, &u->evtchn_wait, wait);
+	if (u->ring_cons != u->ring_prod)
+		mask |= POLLIN | POLLRDNORM;
+	if (u->ring_overflow)
+		mask = POLLERR;
+	return mask;
+}
+
+static int evtchn_fasync(int fd, struct file *filp, int on)
+{
+	struct per_user_data *u = filp->private_data;
+	return fasync_helper(fd, filp, on, &u->evtchn_async_queue);
+}
+
+static int evtchn_open(struct inode *inode, struct file *filp)
+{
+	struct per_user_data *u;
+
+	u = kzalloc(sizeof(*u), GFP_KERNEL);
+	if (u == NULL)
+		return -ENOMEM;
+
+	u->name = kasprintf(GFP_KERNEL, "evtchn:%s", current->comm);
+	if (u->name == NULL) {
+		kfree(u);
+		return -ENOMEM;
+	}
+
+	init_waitqueue_head(&u->evtchn_wait);
+
+	u->ring = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
+	if (u->ring == NULL) {
+		kfree(u->name);
+		kfree(u);
+		return -ENOMEM;
+	}
+
+	mutex_init(&u->bind_mutex);
+	mutex_init(&u->ring_cons_mutex);
+
+	filp->private_data = u;
+
+	return 0;
+}
+
+static int evtchn_release(struct inode *inode, struct file *filp)
+{
+	int i;
+	struct per_user_data *u = filp->private_data;
+
+	spin_lock_irq(&port_user_lock);
+
+	free_page((unsigned long)u->ring);
+
+	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
+		if (port_user[i] != u)
+			continue;
+
+		evtchn_unbind_from_user(port_user[i], i);
+	}
+
+	spin_unlock_irq(&port_user_lock);
+
+	kfree(u->name);
+	kfree(u);
+
+	return 0;
+}
+
+static const struct file_operations evtchn_fops = {
+	.owner   = THIS_MODULE,
+	.read    = evtchn_read,
+	.write   = evtchn_write,
+	.unlocked_ioctl = evtchn_ioctl,
+	.poll    = evtchn_poll,
+	.fasync  = evtchn_fasync,
+	.open    = evtchn_open,
+	.release = evtchn_release,
+};
+
+static struct miscdevice evtchn_miscdev = {
+	.minor        = MISC_DYNAMIC_MINOR,
+	.name         = "evtchn",
+	.fops         = &evtchn_fops,
+};
+static int __init evtchn_init(void)
+{
+	int err;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	spin_lock_init(&port_user_lock);
+	memset(port_user, 0, sizeof(port_user));
+
+	/* Create '/dev/misc/evtchn'. */
+	err = misc_register(&evtchn_miscdev);
+	if (err != 0) {
+		printk(KERN_ALERT "Could not register /dev/misc/evtchn\n");
+		return err;
+	}
+
+	printk(KERN_INFO "Event-channel device installed.\n");
+
+	return 0;
+}
+
+static void __exit evtchn_cleanup(void)
+{
+	misc_deregister(&evtchn_miscdev);
+}
+
+module_init(evtchn_init);
+module_exit(evtchn_cleanup);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 4b5b84837ee1..fddc2025dece 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -98,9 +98,8 @@ static void do_suspend(void)
 		goto out;
 	}
 
-	printk("suspending xenbus...\n");
-	/* XXX use normal device tree? */
-	xenbus_suspend();
+	printk(KERN_DEBUG "suspending xenstore...\n");
+	xs_suspend();
 
 	err = device_power_down(PMSG_SUSPEND);
 	if (err) {
@@ -116,9 +115,9 @@ static void do_suspend(void)
 
 	if (!cancelled) {
 		xen_arch_resume();
-		xenbus_resume();
+		xs_resume();
 	} else
-		xenbus_suspend_cancel();
+		xs_suspend_cancel();
 
 	device_power_up(PMSG_RESUME);
 
diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c
new file mode 100644
index 000000000000..88a60e03ccf0
--- /dev/null
+++ b/drivers/xen/sys-hypervisor.c
@@ -0,0 +1,445 @@
+/*
+ *  copyright (c) 2006 IBM Corporation
+ *  Authored by: Mike D. Day <ncmike@us.ibm.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xenbus.h>
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+
+#define HYPERVISOR_ATTR_RO(_name) \
+static struct hyp_sysfs_attr  _name##_attr = __ATTR_RO(_name)
+
+#define HYPERVISOR_ATTR_RW(_name) \
+static struct hyp_sysfs_attr _name##_attr = \
+	__ATTR(_name, 0644, _name##_show, _name##_store)
+
+struct hyp_sysfs_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct hyp_sysfs_attr *, char *);
+	ssize_t (*store)(struct hyp_sysfs_attr *, const char *, size_t);
+	void *hyp_attr_data;
+};
+
+static ssize_t type_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	return sprintf(buffer, "xen\n");
+}
+
+HYPERVISOR_ATTR_RO(type);
+
+static int __init xen_sysfs_type_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &type_attr.attr);
+}
+
+static void xen_sysfs_type_destroy(void)
+{
+	sysfs_remove_file(hypervisor_kobj, &type_attr.attr);
+}
+
+/* xen version attributes */
+static ssize_t major_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if (version)
+		return sprintf(buffer, "%d\n", version >> 16);
+	return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(major);
+
+static ssize_t minor_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if (version)
+		return sprintf(buffer, "%d\n", version & 0xff);
+	return -ENODEV;
+}
+
+HYPERVISOR_ATTR_RO(minor);
+
+static ssize_t extra_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *extra;
+
+	extra = kmalloc(XEN_EXTRAVERSION_LEN, GFP_KERNEL);
+	if (extra) {
+		ret = HYPERVISOR_xen_version(XENVER_extraversion, extra);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", extra);
+		kfree(extra);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(extra);
+
+static struct attribute *version_attrs[] = {
+	&major_attr.attr,
+	&minor_attr.attr,
+	&extra_attr.attr,
+	NULL
+};
+
+static struct attribute_group version_group = {
+	.name = "version",
+	.attrs = version_attrs,
+};
+
+static int __init xen_sysfs_version_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &version_group);
+}
+
+static void xen_sysfs_version_destroy(void)
+{
+	sysfs_remove_group(hypervisor_kobj, &version_group);
+}
+
+/* UUID */
+
+static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	char *vm, *val;
+	int ret;
+	extern int xenstored_ready;
+
+	if (!xenstored_ready)
+		return -EBUSY;
+
+	vm = xenbus_read(XBT_NIL, "vm", "", NULL);
+	if (IS_ERR(vm))
+		return PTR_ERR(vm);
+	val = xenbus_read(XBT_NIL, vm, "uuid", NULL);
+	kfree(vm);
+	if (IS_ERR(val))
+		return PTR_ERR(val);
+	ret = sprintf(buffer, "%s\n", val);
+	kfree(val);
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(uuid);
+
+static int __init xen_sysfs_uuid_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+static void xen_sysfs_uuid_destroy(void)
+{
+	sysfs_remove_file(hypervisor_kobj, &uuid_attr.attr);
+}
+
+/* xen compilation attributes */
+
+static ssize_t compiler_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compiler);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiler);
+
+static ssize_t compiled_by_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compile_by);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compiled_by);
+
+static ssize_t compile_date_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_compile_info *info;
+
+	info = kmalloc(sizeof(struct xen_compile_info), GFP_KERNEL);
+	if (info) {
+		ret = HYPERVISOR_xen_version(XENVER_compile_info, info);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", info->compile_date);
+		kfree(info);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(compile_date);
+
+static struct attribute *xen_compile_attrs[] = {
+	&compiler_attr.attr,
+	&compiled_by_attr.attr,
+	&compile_date_attr.attr,
+	NULL
+};
+
+static struct attribute_group xen_compilation_group = {
+	.name = "compilation",
+	.attrs = xen_compile_attrs,
+};
+
+int __init static xen_compilation_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+static void xen_compilation_destroy(void)
+{
+	sysfs_remove_group(hypervisor_kobj, &xen_compilation_group);
+}
+
+/* xen properties info */
+
+static ssize_t capabilities_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *caps;
+
+	caps = kmalloc(XEN_CAPABILITIES_INFO_LEN, GFP_KERNEL);
+	if (caps) {
+		ret = HYPERVISOR_xen_version(XENVER_capabilities, caps);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", caps);
+		kfree(caps);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(capabilities);
+
+static ssize_t changeset_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	char *cset;
+
+	cset = kmalloc(XEN_CHANGESET_INFO_LEN, GFP_KERNEL);
+	if (cset) {
+		ret = HYPERVISOR_xen_version(XENVER_changeset, cset);
+		if (!ret)
+			ret = sprintf(buffer, "%s\n", cset);
+		kfree(cset);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(changeset);
+
+static ssize_t virtual_start_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret = -ENOMEM;
+	struct xen_platform_parameters *parms;
+
+	parms = kmalloc(sizeof(struct xen_platform_parameters), GFP_KERNEL);
+	if (parms) {
+		ret = HYPERVISOR_xen_version(XENVER_platform_parameters,
+					     parms);
+		if (!ret)
+			ret = sprintf(buffer, "%lx\n", parms->virt_start);
+		kfree(parms);
+	}
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(virtual_start);
+
+static ssize_t pagesize_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	int ret;
+
+	ret = HYPERVISOR_xen_version(XENVER_pagesize, NULL);
+	if (ret > 0)
+		ret = sprintf(buffer, "%x\n", ret);
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(pagesize);
+
+static ssize_t xen_feature_show(int index, char *buffer)
+{
+	ssize_t ret;
+	struct xen_feature_info info;
+
+	info.submap_idx = index;
+	ret = HYPERVISOR_xen_version(XENVER_get_features, &info);
+	if (!ret)
+		ret = sprintf(buffer, "%08x", info.submap);
+
+	return ret;
+}
+
+static ssize_t features_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	ssize_t len;
+	int i;
+
+	len = 0;
+	for (i = XENFEAT_NR_SUBMAPS-1; i >= 0; i--) {
+		int ret = xen_feature_show(i, buffer + len);
+		if (ret < 0) {
+			if (len == 0)
+				len = ret;
+			break;
+		}
+		len += ret;
+	}
+	if (len > 0)
+		buffer[len++] = '\n';
+
+	return len;
+}
+
+HYPERVISOR_ATTR_RO(features);
+
+static struct attribute *xen_properties_attrs[] = {
+	&capabilities_attr.attr,
+	&changeset_attr.attr,
+	&virtual_start_attr.attr,
+	&pagesize_attr.attr,
+	&features_attr.attr,
+	NULL
+};
+
+static struct attribute_group xen_properties_group = {
+	.name = "properties",
+	.attrs = xen_properties_attrs,
+};
+
+static int __init xen_properties_init(void)
+{
+	return sysfs_create_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static void xen_properties_destroy(void)
+{
+	sysfs_remove_group(hypervisor_kobj, &xen_properties_group);
+}
+
+static int __init hyper_sysfs_init(void)
+{
+	int ret;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	ret = xen_sysfs_type_init();
+	if (ret)
+		goto out;
+	ret = xen_sysfs_version_init();
+	if (ret)
+		goto version_out;
+	ret = xen_compilation_init();
+	if (ret)
+		goto comp_out;
+	ret = xen_sysfs_uuid_init();
+	if (ret)
+		goto uuid_out;
+	ret = xen_properties_init();
+	if (ret)
+		goto prop_out;
+
+	goto out;
+
+prop_out:
+	xen_sysfs_uuid_destroy();
+uuid_out:
+	xen_compilation_destroy();
+comp_out:
+	xen_sysfs_version_destroy();
+version_out:
+	xen_sysfs_type_destroy();
+out:
+	return ret;
+}
+
+static void __exit hyper_sysfs_exit(void)
+{
+	xen_properties_destroy();
+	xen_compilation_destroy();
+	xen_sysfs_uuid_destroy();
+	xen_sysfs_version_destroy();
+	xen_sysfs_type_destroy();
+
+}
+module_init(hyper_sysfs_init);
+module_exit(hyper_sysfs_exit);
+
+static ssize_t hyp_sysfs_show(struct kobject *kobj,
+			      struct attribute *attr,
+			      char *buffer)
+{
+	struct hyp_sysfs_attr *hyp_attr;
+	hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+	if (hyp_attr->show)
+		return hyp_attr->show(hyp_attr, buffer);
+	return 0;
+}
+
+static ssize_t hyp_sysfs_store(struct kobject *kobj,
+			       struct attribute *attr,
+			       const char *buffer,
+			       size_t len)
+{
+	struct hyp_sysfs_attr *hyp_attr;
+	hyp_attr = container_of(attr, struct hyp_sysfs_attr, attr);
+	if (hyp_attr->store)
+		return hyp_attr->store(hyp_attr, buffer, len);
+	return 0;
+}
+
+static struct sysfs_ops hyp_sysfs_ops = {
+	.show = hyp_sysfs_show,
+	.store = hyp_sysfs_store,
+};
+
+static struct kobj_type hyp_sysfs_kobj_type = {
+	.sysfs_ops = &hyp_sysfs_ops,
+};
+
+static int __init hypervisor_subsys_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	hypervisor_kobj->ktype = &hyp_sysfs_kobj_type;
+	return 0;
+}
+device_initcall(hypervisor_subsys_init);
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 773d1cf23283..d42e25d5968d 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -71,6 +71,9 @@ static int xenbus_probe_frontend(const char *type, const char *name);
 
 static void xenbus_dev_shutdown(struct device *_dev);
 
+static int xenbus_dev_suspend(struct device *dev, pm_message_t state);
+static int xenbus_dev_resume(struct device *dev);
+
 /* If something in array of ids matches this device, return it. */
 static const struct xenbus_device_id *
 match_device(const struct xenbus_device_id *arr, struct xenbus_device *dev)
@@ -188,6 +191,9 @@ static struct xen_bus_type xenbus_frontend = {
 		.remove    = xenbus_dev_remove,
 		.shutdown  = xenbus_dev_shutdown,
 		.dev_attrs = xenbus_dev_attrs,
+
+		.suspend   = xenbus_dev_suspend,
+		.resume    = xenbus_dev_resume,
 	},
 };
 
@@ -654,6 +660,7 @@ void xenbus_dev_changed(const char *node, struct xen_bus_type *bus)
 
 	kfree(root);
 }
+EXPORT_SYMBOL_GPL(xenbus_dev_changed);
 
 static void frontend_changed(struct xenbus_watch *watch,
 			     const char **vec, unsigned int len)
@@ -669,7 +676,7 @@ static struct xenbus_watch fe_watch = {
 	.callback = frontend_changed,
 };
 
-static int suspend_dev(struct device *dev, void *data)
+static int xenbus_dev_suspend(struct device *dev, pm_message_t state)
 {
 	int err = 0;
 	struct xenbus_driver *drv;
@@ -682,35 +689,14 @@ static int suspend_dev(struct device *dev, void *data)
 	drv = to_xenbus_driver(dev->driver);
 	xdev = container_of(dev, struct xenbus_device, dev);
 	if (drv->suspend)
-		err = drv->suspend(xdev);
+		err = drv->suspend(xdev, state);
 	if (err)
 		printk(KERN_WARNING
 		       "xenbus: suspend %s failed: %i\n", dev_name(dev), err);
 	return 0;
 }
 
-static int suspend_cancel_dev(struct device *dev, void *data)
-{
-	int err = 0;
-	struct xenbus_driver *drv;
-	struct xenbus_device *xdev;
-
-	DPRINTK("");
-
-	if (dev->driver == NULL)
-		return 0;
-	drv = to_xenbus_driver(dev->driver);
-	xdev = container_of(dev, struct xenbus_device, dev);
-	if (drv->suspend_cancel)
-		err = drv->suspend_cancel(xdev);
-	if (err)
-		printk(KERN_WARNING
-		       "xenbus: suspend_cancel %s failed: %i\n",
-		       dev_name(dev), err);
-	return 0;
-}
-
-static int resume_dev(struct device *dev, void *data)
+static int xenbus_dev_resume(struct device *dev)
 {
 	int err;
 	struct xenbus_driver *drv;
@@ -755,33 +741,6 @@ static int resume_dev(struct device *dev, void *data)
 	return 0;
 }
 
-void xenbus_suspend(void)
-{
-	DPRINTK("");
-
-	bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, suspend_dev);
-	xenbus_backend_suspend(suspend_dev);
-	xs_suspend();
-}
-EXPORT_SYMBOL_GPL(xenbus_suspend);
-
-void xenbus_resume(void)
-{
-	xb_init_comms();
-	xs_resume();
-	bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, resume_dev);
-	xenbus_backend_resume(resume_dev);
-}
-EXPORT_SYMBOL_GPL(xenbus_resume);
-
-void xenbus_suspend_cancel(void)
-{
-	xs_suspend_cancel();
-	bus_for_each_dev(&xenbus_frontend.bus, NULL, NULL, suspend_cancel_dev);
-	xenbus_backend_resume(suspend_cancel_dev);
-}
-EXPORT_SYMBOL_GPL(xenbus_suspend_cancel);
-
 /* A flag to determine if xenstored is 'ready' (i.e. has started) */
 int xenstored_ready = 0;
 
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index e325eab4724d..eab33f1dbdf7 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -673,6 +673,8 @@ void xs_resume(void)
 	struct xenbus_watch *watch;
 	char token[sizeof(watch) * 2 + 1];
 
+	xb_init_comms();
+
 	mutex_unlock(&xs_state.response_mutex);
 	mutex_unlock(&xs_state.request_mutex);
 	up_write(&xs_state.transaction_mutex);
diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c
index 515741a8e6b8..6559e0c752ce 100644
--- a/drivers/xen/xenfs/super.c
+++ b/drivers/xen/xenfs/super.c
@@ -20,10 +20,27 @@
 MODULE_DESCRIPTION("Xen filesystem");
 MODULE_LICENSE("GPL");
 
+static ssize_t capabilities_read(struct file *file, char __user *buf,
+				 size_t size, loff_t *off)
+{
+	char *tmp = "";
+
+	if (xen_initial_domain())
+		tmp = "control_d\n";
+
+	return simple_read_from_buffer(buf, size, off, tmp, strlen(tmp));
+}
+
+static const struct file_operations capabilities_file_ops = {
+	.read = capabilities_read,
+};
+
 static int xenfs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	static struct tree_descr xenfs_files[] = {
-		[2] = {"xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR},
+		[1] = {},
+		{ "xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR },
+		{ "capabilities", &capabilities_file_ops, S_IRUGO },
 		{""},
 	};
 
diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h
index e0a85dbeeb88..a6665f37f456 100644
--- a/fs/adfs/adfs.h
+++ b/fs/adfs/adfs.h
@@ -53,6 +53,7 @@ struct adfs_dir_ops {
 	int	(*update)(struct adfs_dir *dir, struct object_info *obj);
 	int	(*create)(struct adfs_dir *dir, struct object_info *obj);
 	int	(*remove)(struct adfs_dir *dir, struct object_info *obj);
+	int	(*sync)(struct adfs_dir *dir);
 	void	(*free)(struct adfs_dir *dir);
 };
 
@@ -90,7 +91,8 @@ extern const struct dentry_operations adfs_dentry_operations;
 extern struct adfs_dir_ops adfs_f_dir_ops;
 extern struct adfs_dir_ops adfs_fplus_dir_ops;
 
-extern int adfs_dir_update(struct super_block *sb, struct object_info *obj);
+extern int adfs_dir_update(struct super_block *sb, struct object_info *obj,
+			   int wait);
 
 /* file.c */
 extern const struct inode_operations adfs_file_inode_operations;
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index e867ccf37246..4d4073447d1a 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -83,7 +83,7 @@ out:
 }
 
 int
-adfs_dir_update(struct super_block *sb, struct object_info *obj)
+adfs_dir_update(struct super_block *sb, struct object_info *obj, int wait)
 {
 	int ret = -EINVAL;
 #ifdef CONFIG_ADFS_FS_RW
@@ -106,6 +106,12 @@ adfs_dir_update(struct super_block *sb, struct object_info *obj)
 	ret = ops->update(&dir, obj);
 	write_unlock(&adfs_dir_lock);
 
+	if (wait) {
+		int err = ops->sync(&dir);
+		if (!ret)
+			ret = err;
+	}
+
 	ops->free(&dir);
 out:
 #endif
@@ -199,7 +205,7 @@ const struct file_operations adfs_dir_operations = {
 	.read		= generic_read_dir,
 	.llseek		= generic_file_llseek,
 	.readdir	= adfs_readdir,
-	.fsync		= file_fsync,
+	.fsync		= simple_fsync,
 };
 
 static int
diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c
index ea7df2146921..31df6adf0de6 100644
--- a/fs/adfs/dir_f.c
+++ b/fs/adfs/dir_f.c
@@ -437,6 +437,22 @@ bad_dir:
 #endif
 }
 
+static int
+adfs_f_sync(struct adfs_dir *dir)
+{
+	int err = 0;
+	int i;
+
+	for (i = dir->nr_buffers - 1; i >= 0; i--) {
+		struct buffer_head *bh = dir->bh[i];
+		sync_dirty_buffer(bh);
+		if (buffer_req(bh) && !buffer_uptodate(bh))
+			err = -EIO;
+	}
+
+	return err;
+}
+
 static void
 adfs_f_free(struct adfs_dir *dir)
 {
@@ -456,5 +472,6 @@ struct adfs_dir_ops adfs_f_dir_ops = {
 	.setpos		= adfs_f_setpos,
 	.getnext	= adfs_f_getnext,
 	.update		= adfs_f_update,
+	.sync		= adfs_f_sync,
 	.free		= adfs_f_free
 };
diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c
index 1ec644e32df9..139e0f345f18 100644
--- a/fs/adfs/dir_fplus.c
+++ b/fs/adfs/dir_fplus.c
@@ -161,6 +161,22 @@ out:
 	return ret;
 }
 
+static int
+adfs_fplus_sync(struct adfs_dir *dir)
+{
+	int err = 0;
+	int i;
+
+	for (i = dir->nr_buffers - 1; i >= 0; i--) {
+		struct buffer_head *bh = dir->bh[i];
+		sync_dirty_buffer(bh);
+		if (buffer_req(bh) && !buffer_uptodate(bh))
+			err = -EIO;
+	}
+
+	return err;
+}
+
 static void
 adfs_fplus_free(struct adfs_dir *dir)
 {
@@ -175,5 +191,6 @@ struct adfs_dir_ops adfs_fplus_dir_ops = {
 	.read		= adfs_fplus_read,
 	.setpos		= adfs_fplus_setpos,
 	.getnext	= adfs_fplus_getnext,
+	.sync		= adfs_fplus_sync,
 	.free		= adfs_fplus_free
 };
diff --git a/fs/adfs/file.c b/fs/adfs/file.c
index 36e381c6a99a..8224d54a2afb 100644
--- a/fs/adfs/file.c
+++ b/fs/adfs/file.c
@@ -30,7 +30,7 @@ const struct file_operations adfs_file_operations = {
 	.read		= do_sync_read,
 	.aio_read	= generic_file_aio_read,
 	.mmap		= generic_file_mmap,
-	.fsync		= file_fsync,
+	.fsync		= simple_fsync,
 	.write		= do_sync_write,
 	.aio_write	= generic_file_aio_write,
 	.splice_read	= generic_file_splice_read,
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index e647200262a2..05b3a677201d 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -376,7 +376,7 @@ out:
  * The adfs-specific inode data has already been updated by
  * adfs_notify_change()
  */
-int adfs_write_inode(struct inode *inode, int unused)
+int adfs_write_inode(struct inode *inode, int wait)
 {
 	struct super_block *sb = inode->i_sb;
 	struct object_info obj;
@@ -391,7 +391,7 @@ int adfs_write_inode(struct inode *inode, int unused)
 	obj.attr	= ADFS_I(inode)->attr;
 	obj.size	= inode->i_size;
 
-	ret = adfs_dir_update(sb, &obj);
+	ret = adfs_dir_update(sb, &obj, wait);
 	unlock_kernel();
 	return ret;
 }
diff --git a/fs/adfs/map.c b/fs/adfs/map.c
index 92ab4fbc2031..568081b93f73 100644
--- a/fs/adfs/map.c
+++ b/fs/adfs/map.c
@@ -62,7 +62,7 @@ static DEFINE_RWLOCK(adfs_map_lock);
 #define GET_FRAG_ID(_map,_start,_idmask)				\
 	({								\
 		unsigned char *_m = _map + (_start >> 3);		\
-		u32 _frag = get_unaligned((u32 *)_m);			\
+		u32 _frag = get_unaligned_le32(_m);			\
 		_frag >>= (_start & 7);					\
 		_frag & _idmask;					\
 	})
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index dd9becca4241..0ec5aaf47aa7 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -132,11 +132,15 @@ static void adfs_put_super(struct super_block *sb)
 	int i;
 	struct adfs_sb_info *asb = ADFS_SB(sb);
 
+	lock_kernel();
+
 	for (i = 0; i < asb->s_map_size; i++)
 		brelse(asb->s_map[i].dm_bh);
 	kfree(asb->s_map);
 	kfree(asb);
 	sb->s_fs_info = NULL;
+
+	unlock_kernel();
 }
 
 static int adfs_show_options(struct seq_file *seq, struct vfsmount *mnt)
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 1a2d5e3c7f4e..e511dc621a2e 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -182,6 +182,7 @@ extern int			 affs_add_entry(struct inode *dir, struct inode *inode, struct dent
 
 void		affs_free_prealloc(struct inode *inode);
 extern void	affs_truncate(struct inode *);
+int		affs_file_fsync(struct file *, struct dentry *, int);
 
 /* dir.c */
 
diff --git a/fs/affs/dir.c b/fs/affs/dir.c
index 7b36904dbeac..8ca8f3a55599 100644
--- a/fs/affs/dir.c
+++ b/fs/affs/dir.c
@@ -21,7 +21,7 @@ const struct file_operations affs_dir_operations = {
 	.read		= generic_read_dir,
 	.llseek		= generic_file_llseek,
 	.readdir	= affs_readdir,
-	.fsync		= file_fsync,
+	.fsync		= affs_file_fsync,
 };
 
 /*
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 9246cb4aa018..184e55c1c9ba 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -34,7 +34,7 @@ const struct file_operations affs_file_operations = {
 	.mmap		= generic_file_mmap,
 	.open		= affs_file_open,
 	.release	= affs_file_release,
-	.fsync		= file_fsync,
+	.fsync		= affs_file_fsync,
 	.splice_read	= generic_file_splice_read,
 };
 
@@ -915,3 +915,15 @@ affs_truncate(struct inode *inode)
 	}
 	affs_free_prealloc(inode);
 }
+
+int affs_file_fsync(struct file *filp, struct dentry *dentry, int datasync)
+{
+	struct inode * inode = dentry->d_inode;
+	int ret, err;
+
+	ret = write_inode_now(inode, 0);
+	err = sync_blockdev(inode->i_sb->s_bdev);
+	if (!ret)
+		ret = err;
+	return ret;
+}
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 63f5183f263b..104fdcb3a7fc 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -16,6 +16,7 @@
 #include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include "affs.h"
 
 extern struct timezone sys_tz;
@@ -23,50 +24,68 @@ extern struct timezone sys_tz;
 static int affs_statfs(struct dentry *dentry, struct kstatfs *buf);
 static int affs_remount (struct super_block *sb, int *flags, char *data);
 
+static void
+affs_commit_super(struct super_block *sb, int clean)
+{
+	struct affs_sb_info *sbi = AFFS_SB(sb);
+	struct buffer_head *bh = sbi->s_root_bh;
+	struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh);
+
+	tail->bm_flag = cpu_to_be32(clean);
+	secs_to_datestamp(get_seconds(), &tail->disk_change);
+	affs_fix_checksum(sb, bh);
+	mark_buffer_dirty(bh);
+}
+
 static void
 affs_put_super(struct super_block *sb)
 {
 	struct affs_sb_info *sbi = AFFS_SB(sb);
 	pr_debug("AFFS: put_super()\n");
 
-	if (!(sb->s_flags & MS_RDONLY)) {
-		AFFS_ROOT_TAIL(sb, sbi->s_root_bh)->bm_flag = cpu_to_be32(1);
-		secs_to_datestamp(get_seconds(),
-				  &AFFS_ROOT_TAIL(sb, sbi->s_root_bh)->disk_change);
-		affs_fix_checksum(sb, sbi->s_root_bh);
-		mark_buffer_dirty(sbi->s_root_bh);
-	}
+	lock_kernel();
+
+	if (!(sb->s_flags & MS_RDONLY))
+		affs_commit_super(sb, 1);
 
 	kfree(sbi->s_prefix);
 	affs_free_bitmap(sb);
 	affs_brelse(sbi->s_root_bh);
 	kfree(sbi);
 	sb->s_fs_info = NULL;
-	return;
+
+	unlock_kernel();
 }
 
 static void
 affs_write_super(struct super_block *sb)
 {
 	int clean = 2;
-	struct affs_sb_info *sbi = AFFS_SB(sb);
 
+	lock_super(sb);
 	if (!(sb->s_flags & MS_RDONLY)) {
 		//	if (sbi->s_bitmap[i].bm_bh) {
 		//		if (buffer_dirty(sbi->s_bitmap[i].bm_bh)) {
 		//			clean = 0;
-		AFFS_ROOT_TAIL(sb, sbi->s_root_bh)->bm_flag = cpu_to_be32(clean);
-		secs_to_datestamp(get_seconds(),
-				  &AFFS_ROOT_TAIL(sb, sbi->s_root_bh)->disk_change);
-		affs_fix_checksum(sb, sbi->s_root_bh);
-		mark_buffer_dirty(sbi->s_root_bh);
+		affs_commit_super(sb, clean);
 		sb->s_dirt = !clean;	/* redo until bitmap synced */
 	} else
 		sb->s_dirt = 0;
+	unlock_super(sb);
 
 	pr_debug("AFFS: write_super() at %lu, clean=%d\n", get_seconds(), clean);
 }
 
+static int
+affs_sync_fs(struct super_block *sb, int wait)
+{
+	lock_super(sb);
+	affs_commit_super(sb, 2);
+	sb->s_dirt = 0;
+	unlock_super(sb);
+	return 0;
+}
+
 static struct kmem_cache * affs_inode_cachep;
 
 static struct inode *affs_alloc_inode(struct super_block *sb)
@@ -124,6 +143,7 @@ static const struct super_operations affs_sops = {
 	.clear_inode	= affs_clear_inode,
 	.put_super	= affs_put_super,
 	.write_super	= affs_write_super,
+	.sync_fs	= affs_sync_fs,
 	.statfs		= affs_statfs,
 	.remount_fs	= affs_remount,
 	.show_options	= generic_show_options,
@@ -507,6 +527,7 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 		kfree(new_opts);
 		return -EINVAL;
 	}
+	lock_kernel();
 	replace_mount_options(sb, new_opts);
 
 	sbi->s_flags = mount_flags;
@@ -514,8 +535,10 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	sbi->s_uid   = uid;
 	sbi->s_gid   = gid;
 
-	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
+	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
+		unlock_kernel();
 		return 0;
+	}
 	if (*flags & MS_RDONLY) {
 		sb->s_dirt = 1;
 		while (sb->s_dirt)
@@ -524,6 +547,7 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	} else
 		res = affs_init_bitmap(sb, flags);
 
+	unlock_kernel();
 	return res;
 }
 
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 2b9e2d03a390..c52be53f6946 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -244,7 +244,7 @@ static void *afs_mntpt_follow_link(struct dentry *dentry, struct nameidata *nd)
 	case -EBUSY:
 		/* someone else made a mount here whilst we were busy */
 		while (d_mountpoint(nd->path.dentry) &&
-		       follow_down(&nd->path.mnt, &nd->path.dentry))
+		       follow_down(&nd->path))
 			;
 		err = 0;
 	default:
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 76828e5f8a39..ad0514d0115f 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -440,8 +440,12 @@ static void afs_put_super(struct super_block *sb)
 
 	_enter("");
 
+	lock_kernel();
+
 	afs_put_volume(as->volume);
 
+	unlock_kernel();
+
 	_leave("");
 }
 
diff --git a/fs/autofs/dirhash.c b/fs/autofs/dirhash.c
index 4eb4d8dfb2f1..2316e944a109 100644
--- a/fs/autofs/dirhash.c
+++ b/fs/autofs/dirhash.c
@@ -85,13 +85,12 @@ struct autofs_dir_ent *autofs_expire(struct super_block *sb,
 		}
 		path.mnt = mnt;
 		path_get(&path);
-		if (!follow_down(&path.mnt, &path.dentry)) {
+		if (!follow_down(&path)) {
 			path_put(&path);
 			DPRINTK(("autofs: not expirable (not a mounted directory): %s\n", ent->name));
 			continue;
 		}
-		while (d_mountpoint(path.dentry) &&
-		       follow_down(&path.mnt, &path.dentry))
+		while (d_mountpoint(path.dentry) && follow_down(&path));
 			;
 		umount_ok = may_umount(path.mnt);
 		path_put(&path);
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index b7ff33c63101..8f7cdde41733 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -223,12 +223,12 @@ int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify);
 int autofs4_wait_release(struct autofs_sb_info *,autofs_wqt_t,int);
 void autofs4_catatonic_mode(struct autofs_sb_info *);
 
-static inline int autofs4_follow_mount(struct vfsmount **mnt, struct dentry **dentry)
+static inline int autofs4_follow_mount(struct path *path)
 {
 	int res = 0;
 
-	while (d_mountpoint(*dentry)) {
-		int followed = follow_down(mnt, dentry);
+	while (d_mountpoint(path->dentry)) {
+		int followed = follow_down(path);
 		if (!followed)
 			break;
 		res = 1;
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 84168c0dcc2d..f3da2eb51f56 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -192,77 +192,42 @@ static int autofs_dev_ioctl_protosubver(struct file *fp,
 	return 0;
 }
 
-/*
- * Walk down the mount stack looking for an autofs mount that
- * has the requested device number (aka. new_encode_dev(sb->s_dev).
- */
-static int autofs_dev_ioctl_find_super(struct nameidata *nd, dev_t devno)
+static int find_autofs_mount(const char *pathname,
+			     struct path *res,
+			     int test(struct path *path, void *data),
+			     void *data)
 {
-	struct dentry *dentry;
-	struct inode *inode;
-	struct super_block *sb;
-	dev_t s_dev;
-	unsigned int err;
-
+	struct path path;
+	int err = kern_path(pathname, 0, &path);
+	if (err)
+		return err;
 	err = -ENOENT;
-
-	/* Lookup the dentry name at the base of our mount point */
-	dentry = d_lookup(nd->path.dentry, &nd->last);
-	if (!dentry)
-		goto out;
-
-	dput(nd->path.dentry);
-	nd->path.dentry = dentry;
-
-	/* And follow the mount stack looking for our autofs mount */
-	while (follow_down(&nd->path.mnt, &nd->path.dentry)) {
-		inode = nd->path.dentry->d_inode;
-		if (!inode)
-			break;
-
-		sb = inode->i_sb;
-		s_dev = new_encode_dev(sb->s_dev);
-		if (devno == s_dev) {
-			if (sb->s_magic == AUTOFS_SUPER_MAGIC) {
+	while (path.dentry == path.mnt->mnt_root) {
+		if (path.mnt->mnt_sb->s_magic == AUTOFS_SUPER_MAGIC) {
+			if (test(&path, data)) {
+				path_get(&path);
+				if (!err) /* already found some */
+					path_put(res);
+				*res = path;
 				err = 0;
-				break;
 			}
 		}
+		if (!follow_up(&path))
+			break;
 	}
-out:
+	path_put(&path);
 	return err;
 }
 
-/*
- * Walk down the mount stack looking for an autofs mount that
- * has the requested mount type (ie. indirect, direct or offset).
- */
-static int autofs_dev_ioctl_find_sbi_type(struct nameidata *nd, unsigned int type)
+static int test_by_dev(struct path *path, void *p)
 {
-	struct dentry *dentry;
-	struct autofs_info *ino;
-	unsigned int err;
+	return path->mnt->mnt_sb->s_dev == *(dev_t *)p;
+}
 
-	err = -ENOENT;
-
-	/* Lookup the dentry name at the base of our mount point */
-	dentry = d_lookup(nd->path.dentry, &nd->last);
-	if (!dentry)
-		goto out;
-
-	dput(nd->path.dentry);
-	nd->path.dentry = dentry;
-
-	/* And follow the mount stack looking for our autofs mount */
-	while (follow_down(&nd->path.mnt, &nd->path.dentry)) {
-		ino = autofs4_dentry_ino(nd->path.dentry);
-		if (ino && ino->sbi->type & type) {
-			err = 0;
-			break;
-		}
-	}
-out:
-	return err;
+static int test_by_type(struct path *path, void *p)
+{
+	struct autofs_info *ino = autofs4_dentry_ino(path->dentry);
+	return ino && ino->sbi->type & *(unsigned *)p;
 }
 
 static void autofs_dev_ioctl_fd_install(unsigned int fd, struct file *file)
@@ -283,31 +248,25 @@ static void autofs_dev_ioctl_fd_install(unsigned int fd, struct file *file)
  * Open a file descriptor on the autofs mount point corresponding
  * to the given path and device number (aka. new_encode_dev(sb->s_dev)).
  */
-static int autofs_dev_ioctl_open_mountpoint(const char *path, dev_t devid)
+static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid)
 {
-	struct file *filp;
-	struct nameidata nd;
 	int err, fd;
 
 	fd = get_unused_fd();
 	if (likely(fd >= 0)) {
-		/* Get nameidata of the parent directory */
-		err = path_lookup(path, LOOKUP_PARENT, &nd);
+		struct file *filp;
+		struct path path;
+
+		err = find_autofs_mount(name, &path, test_by_dev, &devid);
 		if (err)
 			goto out;
 
 		/*
-		 * Search down, within the parent, looking for an
-		 * autofs super block that has the device number
+		 * Find autofs super block that has the device number
 		 * corresponding to the autofs fs we want to open.
 		 */
-		err = autofs_dev_ioctl_find_super(&nd, devid);
-		if (err) {
-			path_put(&nd.path);
-			goto out;
-		}
 
-		filp = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY,
+		filp = dentry_open(path.dentry, path.mnt, O_RDONLY,
 				   current_cred());
 		if (IS_ERR(filp)) {
 			err = PTR_ERR(filp);
@@ -340,7 +299,7 @@ static int autofs_dev_ioctl_openmount(struct file *fp,
 	param->ioctlfd = -1;
 
 	path = param->path;
-	devid = param->openmount.devid;
+	devid = new_decode_dev(param->openmount.devid);
 
 	err = 0;
 	fd = autofs_dev_ioctl_open_mountpoint(path, devid);
@@ -475,8 +434,7 @@ static int autofs_dev_ioctl_requester(struct file *fp,
 				      struct autofs_dev_ioctl *param)
 {
 	struct autofs_info *ino;
-	struct nameidata nd;
-	const char *path;
+	struct path path;
 	dev_t devid;
 	int err = -ENOENT;
 
@@ -485,32 +443,24 @@ static int autofs_dev_ioctl_requester(struct file *fp,
 		goto out;
 	}
 
-	path = param->path;
-	devid = new_encode_dev(sbi->sb->s_dev);
+	devid = sbi->sb->s_dev;
 
 	param->requester.uid = param->requester.gid = -1;
 
-	/* Get nameidata of the parent directory */
-	err = path_lookup(path, LOOKUP_PARENT, &nd);
+	err = find_autofs_mount(param->path, &path, test_by_dev, &devid);
 	if (err)
 		goto out;
 
-	err = autofs_dev_ioctl_find_super(&nd, devid);
-	if (err)
-		goto out_release;
-
-	ino = autofs4_dentry_ino(nd.path.dentry);
+	ino = autofs4_dentry_ino(path.dentry);
 	if (ino) {
 		err = 0;
-		autofs4_expire_wait(nd.path.dentry);
+		autofs4_expire_wait(path.dentry);
 		spin_lock(&sbi->fs_lock);
 		param->requester.uid = ino->uid;
 		param->requester.gid = ino->gid;
 		spin_unlock(&sbi->fs_lock);
 	}
-
-out_release:
-	path_put(&nd.path);
+	path_put(&path);
 out:
 	return err;
 }
@@ -569,8 +519,8 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp,
 					 struct autofs_sb_info *sbi,
 					 struct autofs_dev_ioctl *param)
 {
-	struct nameidata nd;
-	const char *path;
+	struct path path;
+	const char *name;
 	unsigned int type;
 	unsigned int devid, magic;
 	int err = -ENOENT;
@@ -580,71 +530,46 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp,
 		goto out;
 	}
 
-	path = param->path;
+	name = param->path;
 	type = param->ismountpoint.in.type;
 
 	param->ismountpoint.out.devid = devid = 0;
 	param->ismountpoint.out.magic = magic = 0;
 
 	if (!fp || param->ioctlfd == -1) {
-		if (autofs_type_any(type)) {
-			struct super_block *sb;
-
-			err = path_lookup(path, LOOKUP_FOLLOW, &nd);
-			if (err)
-				goto out;
-
-			sb = nd.path.dentry->d_sb;
-			devid = new_encode_dev(sb->s_dev);
-		} else {
-			struct autofs_info *ino;
-
-			err = path_lookup(path, LOOKUP_PARENT, &nd);
-			if (err)
-				goto out;
-
-			err = autofs_dev_ioctl_find_sbi_type(&nd, type);
-			if (err)
-				goto out_release;
-
-			ino = autofs4_dentry_ino(nd.path.dentry);
-			devid = autofs4_get_dev(ino->sbi);
-		}
-
+		if (autofs_type_any(type))
+			err = kern_path(name, LOOKUP_FOLLOW, &path);
+		else
+			err = find_autofs_mount(name, &path, test_by_type, &type);
+		if (err)
+			goto out;
+		devid = new_encode_dev(path.mnt->mnt_sb->s_dev);
 		err = 0;
-		if (nd.path.dentry->d_inode &&
-		    nd.path.mnt->mnt_root == nd.path.dentry) {
+		if (path.dentry->d_inode &&
+		    path.mnt->mnt_root == path.dentry) {
 			err = 1;
-			magic = nd.path.dentry->d_inode->i_sb->s_magic;
+			magic = path.dentry->d_inode->i_sb->s_magic;
 		}
 	} else {
-		dev_t dev = autofs4_get_dev(sbi);
+		dev_t dev = sbi->sb->s_dev;
 
-		err = path_lookup(path, LOOKUP_PARENT, &nd);
+		err = find_autofs_mount(name, &path, test_by_dev, &dev);
 		if (err)
 			goto out;
 
-		err = autofs_dev_ioctl_find_super(&nd, dev);
-		if (err)
-			goto out_release;
+		devid = new_encode_dev(dev);
 
-		devid = dev;
+		err = have_submounts(path.dentry);
 
-		err = have_submounts(nd.path.dentry);
-
-		if (nd.path.mnt->mnt_mountpoint != nd.path.mnt->mnt_root) {
-			if (follow_down(&nd.path.mnt, &nd.path.dentry)) {
-				struct inode *inode = nd.path.dentry->d_inode;
-				magic = inode->i_sb->s_magic;
-			}
+		if (path.mnt->mnt_mountpoint != path.mnt->mnt_root) {
+			if (follow_down(&path))
+				magic = path.mnt->mnt_sb->s_magic;
 		}
 	}
 
 	param->ismountpoint.out.devid = devid;
 	param->ismountpoint.out.magic = magic;
-
-out_release:
-	path_put(&nd.path);
+	path_put(&path);
 out:
 	return err;
 }
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 3077d8f16523..aa39ae83f019 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -48,19 +48,19 @@ static inline int autofs4_can_expire(struct dentry *dentry,
 static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 {
 	struct dentry *top = dentry;
+	struct path path = {.mnt = mnt, .dentry = dentry};
 	int status = 1;
 
 	DPRINTK("dentry %p %.*s",
 		dentry, (int)dentry->d_name.len, dentry->d_name.name);
 
-	mntget(mnt);
-	dget(dentry);
+	path_get(&path);
 
-	if (!follow_down(&mnt, &dentry))
+	if (!follow_down(&path))
 		goto done;
 
-	if (is_autofs4_dentry(dentry)) {
-		struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+	if (is_autofs4_dentry(path.dentry)) {
+		struct autofs_sb_info *sbi = autofs4_sbi(path.dentry->d_sb);
 
 		/* This is an autofs submount, we can't expire it */
 		if (autofs_type_indirect(sbi->type))
@@ -70,7 +70,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 		 * Otherwise it's an offset mount and we need to check
 		 * if we can umount its mount, if there is one.
 		 */
-		if (!d_mountpoint(dentry)) {
+		if (!d_mountpoint(path.dentry)) {
 			status = 0;
 			goto done;
 		}
@@ -86,8 +86,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 	status = 0;
 done:
 	DPRINTK("returning = %d", status);
-	dput(dentry);
-	mntput(mnt);
+	path_put(&path);
 	return status;
 }
 
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index e383bf0334f1..b96a3c57359d 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -181,7 +181,7 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
 		nd->flags);
 	/*
 	 * For an expire of a covered direct or offset mount we need
-	 * to beeak out of follow_down() at the autofs mount trigger
+	 * to break out of follow_down() at the autofs mount trigger
 	 * (d_mounted--), so we can see the expiring flag, and manage
 	 * the blocking and following here until the expire is completed.
 	 */
@@ -190,7 +190,7 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
 		if (ino->flags & AUTOFS_INF_EXPIRING) {
 			spin_unlock(&sbi->fs_lock);
 			/* Follow down to our covering mount. */
-			if (!follow_down(&nd->path.mnt, &nd->path.dentry))
+			if (!follow_down(&nd->path))
 				goto done;
 			goto follow;
 		}
@@ -230,8 +230,7 @@ follow:
 	 * to follow it.
 	 */
 	if (d_mountpoint(dentry)) {
-		if (!autofs4_follow_mount(&nd->path.mnt,
-					  &nd->path.dentry)) {
+		if (!autofs4_follow_mount(&nd->path)) {
 			status = -ENOENT;
 			goto out_error;
 		}
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 76afd0d6b86c..9367b6297d84 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -737,6 +737,8 @@ parse_options(char *options, befs_mount_options * opts)
 static void
 befs_put_super(struct super_block *sb)
 {
+	lock_kernel();
+
 	kfree(BEFS_SB(sb)->mount_opts.iocharset);
 	BEFS_SB(sb)->mount_opts.iocharset = NULL;
 
@@ -747,7 +749,8 @@ befs_put_super(struct super_block *sb)
 
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
-	return;
+
+	unlock_kernel();
 }
 
 /* Allocate private field of the superblock, fill it.
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 4dd1b623f937..54bd07d44e68 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -79,7 +79,7 @@ static int bfs_readdir(struct file *f, void *dirent, filldir_t filldir)
 const struct file_operations bfs_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= bfs_readdir,
-	.fsync		= file_fsync,
+	.fsync		= simple_fsync,
 	.llseek		= generic_file_llseek,
 };
 
@@ -205,7 +205,7 @@ static int bfs_unlink(struct inode *dir, struct dentry *dentry)
 		inode->i_nlink = 1;
 	}
 	de->ino = 0;
-	mark_buffer_dirty(bh);
+	mark_buffer_dirty_inode(bh, dir);
 	dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC;
 	mark_inode_dirty(dir);
 	inode->i_ctime = dir->i_ctime;
@@ -267,7 +267,7 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		new_inode->i_ctime = CURRENT_TIME_SEC;
 		inode_dec_link_count(new_inode);
 	}
-	mark_buffer_dirty(old_bh);
+	mark_buffer_dirty_inode(old_bh, old_dir);
 	error = 0;
 
 end_rename:
@@ -320,7 +320,7 @@ static int bfs_add_entry(struct inode *dir, const unsigned char *name,
 				for (i = 0; i < BFS_NAMELEN; i++)
 					de->name[i] =
 						(i < namelen) ? name[i] : 0;
-				mark_buffer_dirty(bh);
+				mark_buffer_dirty_inode(bh, dir);
 				brelse(bh);
 				return 0;
 			}
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index cc4062d12ca2..6f60336c6628 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -30,6 +30,7 @@ MODULE_LICENSE("GPL");
 #define dprintf(x...)
 #endif
 
+static void bfs_write_super(struct super_block *s);
 void dump_imap(const char *prefix, struct super_block *s);
 
 struct inode *bfs_iget(struct super_block *sb, unsigned long ino)
@@ -97,14 +98,15 @@ error:
 	return ERR_PTR(-EIO);
 }
 
-static int bfs_write_inode(struct inode *inode, int unused)
+static int bfs_write_inode(struct inode *inode, int wait)
 {
+	struct bfs_sb_info *info = BFS_SB(inode->i_sb);
 	unsigned int ino = (u16)inode->i_ino;
         unsigned long i_sblock;
 	struct bfs_inode *di;
 	struct buffer_head *bh;
 	int block, off;
-	struct bfs_sb_info *info = BFS_SB(inode->i_sb);
+	int err = 0;
 
         dprintf("ino=%08x\n", ino);
 
@@ -145,9 +147,14 @@ static int bfs_write_inode(struct inode *inode, int unused)
 	di->i_eoffset = cpu_to_le32(i_sblock * BFS_BSIZE + inode->i_size - 1);
 
 	mark_buffer_dirty(bh);
+	if (wait) {
+		sync_dirty_buffer(bh);
+		if (buffer_req(bh) && !buffer_uptodate(bh))
+			err = -EIO;
+	}
 	brelse(bh);
 	mutex_unlock(&info->bfs_lock);
-	return 0;
+	return err;
 }
 
 static void bfs_delete_inode(struct inode *inode)
@@ -209,6 +216,26 @@ static void bfs_delete_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
+static int bfs_sync_fs(struct super_block *sb, int wait)
+{
+	struct bfs_sb_info *info = BFS_SB(sb);
+
+	mutex_lock(&info->bfs_lock);
+	mark_buffer_dirty(info->si_sbh);
+	sb->s_dirt = 0;
+	mutex_unlock(&info->bfs_lock);
+
+	return 0;
+}
+
+static void bfs_write_super(struct super_block *sb)
+{
+	if (!(sb->s_flags & MS_RDONLY))
+		bfs_sync_fs(sb, 1);
+	else
+		sb->s_dirt = 0;
+}
+
 static void bfs_put_super(struct super_block *s)
 {
 	struct bfs_sb_info *info = BFS_SB(s);
@@ -216,11 +243,18 @@ static void bfs_put_super(struct super_block *s)
 	if (!info)
 		return;
 
+	lock_kernel();
+
+	if (s->s_dirt)
+		bfs_write_super(s);
+
 	brelse(info->si_sbh);
 	mutex_destroy(&info->bfs_lock);
 	kfree(info->si_imap);
 	kfree(info);
 	s->s_fs_info = NULL;
+
+	unlock_kernel();
 }
 
 static int bfs_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -240,17 +274,6 @@ static int bfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0;
 }
 
-static void bfs_write_super(struct super_block *s)
-{
-	struct bfs_sb_info *info = BFS_SB(s);
-
-	mutex_lock(&info->bfs_lock);
-	if (!(s->s_flags & MS_RDONLY))
-		mark_buffer_dirty(info->si_sbh);
-	s->s_dirt = 0;
-	mutex_unlock(&info->bfs_lock);
-}
-
 static struct kmem_cache *bfs_inode_cachep;
 
 static struct inode *bfs_alloc_inode(struct super_block *sb)
@@ -298,6 +321,7 @@ static const struct super_operations bfs_sops = {
 	.delete_inode	= bfs_delete_inode,
 	.put_super	= bfs_put_super,
 	.write_super	= bfs_write_super,
+	.sync_fs	= bfs_sync_fs,
 	.statfs		= bfs_statfs,
 };
 
diff --git a/fs/bio.c b/fs/bio.c
index 98711647ece4..59000215e59b 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -26,10 +26,9 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
 #include <scsi/sg.h>		/* for struct sg_iovec */
 
-DEFINE_TRACE(block_split);
+#include <trace/events/block.h>
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
@@ -499,11 +498,11 @@ int bio_get_nr_vecs(struct block_device *bdev)
 	struct request_queue *q = bdev_get_queue(bdev);
 	int nr_pages;
 
-	nr_pages = ((q->max_sectors << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (nr_pages > q->max_phys_segments)
-		nr_pages = q->max_phys_segments;
-	if (nr_pages > q->max_hw_segments)
-		nr_pages = q->max_hw_segments;
+	nr_pages = ((queue_max_sectors(q) << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (nr_pages > queue_max_phys_segments(q))
+		nr_pages = queue_max_phys_segments(q);
+	if (nr_pages > queue_max_hw_segments(q))
+		nr_pages = queue_max_hw_segments(q);
 
 	return nr_pages;
 }
@@ -562,8 +561,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	 * make this too complex.
 	 */
 
-	while (bio->bi_phys_segments >= q->max_phys_segments
-	       || bio->bi_phys_segments >= q->max_hw_segments) {
+	while (bio->bi_phys_segments >= queue_max_phys_segments(q)
+	       || bio->bi_phys_segments >= queue_max_hw_segments(q)) {
 
 		if (retried_segments)
 			return 0;
@@ -634,7 +633,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
 		    unsigned int len, unsigned int offset)
 {
-	return __bio_add_page(q, bio, page, len, offset, q->max_hw_sectors);
+	return __bio_add_page(q, bio, page, len, offset,
+			      queue_max_hw_sectors(q));
 }
 
 /**
@@ -654,7 +654,7 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
 		 unsigned int offset)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	return __bio_add_page(q, bio, page, len, offset, q->max_sectors);
+	return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q));
 }
 
 struct bio_map_data {
@@ -721,7 +721,7 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
 
 		while (bv_len && iov_idx < iov_count) {
 			unsigned int bytes;
-			char *iov_addr;
+			char __user *iov_addr;
 
 			bytes = min_t(unsigned int,
 				      iov[iov_idx].iov_len - iov_off, bv_len);
@@ -1201,7 +1201,7 @@ static void bio_copy_kern_endio(struct bio *bio, int err)
 		char *addr = page_address(bvec->bv_page);
 		int len = bmd->iovecs[i].bv_len;
 
-		if (read && !err)
+		if (read)
 			memcpy(p, addr, len);
 
 		__free_page(bvec->bv_page);
@@ -1490,11 +1490,12 @@ struct bio_pair *bio_split(struct bio *bi, int first_sectors)
 sector_t bio_sector_offset(struct bio *bio, unsigned short index,
 			   unsigned int offset)
 {
-	unsigned int sector_sz = queue_hardsect_size(bio->bi_bdev->bd_disk->queue);
+	unsigned int sector_sz;
 	struct bio_vec *bv;
 	sector_t sectors;
 	int i;
 
+	sector_sz = queue_logical_block_size(bio->bi_bdev->bd_disk->queue);
 	sectors = 0;
 
 	if (index >= bio->bi_idx)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index f45dbc18dd17..3a6d4fb2a329 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -25,6 +25,7 @@
 #include <linux/uio.h>
 #include <linux/namei.h>
 #include <linux/log2.h>
+#include <linux/kmemleak.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -76,7 +77,7 @@ int set_blocksize(struct block_device *bdev, int size)
 		return -EINVAL;
 
 	/* Size cannot be smaller than the size supported by the device */
-	if (size < bdev_hardsect_size(bdev))
+	if (size < bdev_logical_block_size(bdev))
 		return -EINVAL;
 
 	/* Don't change the size if it is same as current */
@@ -106,7 +107,7 @@ EXPORT_SYMBOL(sb_set_blocksize);
 
 int sb_min_blocksize(struct super_block *sb, int size)
 {
-	int minsize = bdev_hardsect_size(sb->s_bdev);
+	int minsize = bdev_logical_block_size(sb->s_bdev);
 	if (size < minsize)
 		size = minsize;
 	return sb_set_blocksize(sb, size);
@@ -175,17 +176,22 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 				iov, offset, nr_segs, blkdev_get_blocks, NULL);
 }
 
+int __sync_blockdev(struct block_device *bdev, int wait)
+{
+	if (!bdev)
+		return 0;
+	if (!wait)
+		return filemap_flush(bdev->bd_inode->i_mapping);
+	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
+}
+
 /*
  * Write out and wait upon all the dirty data associated with a block
  * device via its mapping.  Does not take the superblock lock.
  */
 int sync_blockdev(struct block_device *bdev)
 {
-	int ret = 0;
-
-	if (bdev)
-		ret = filemap_write_and_wait(bdev->bd_inode->i_mapping);
-	return ret;
+	return __sync_blockdev(bdev, 1);
 }
 EXPORT_SYMBOL(sync_blockdev);
 
@@ -198,7 +204,7 @@ int fsync_bdev(struct block_device *bdev)
 {
 	struct super_block *sb = get_super(bdev);
 	if (sb) {
-		int res = fsync_super(sb);
+		int res = sync_filesystem(sb);
 		drop_super(sb);
 		return res;
 	}
@@ -240,7 +246,7 @@ struct super_block *freeze_bdev(struct block_device *bdev)
 		sb->s_frozen = SB_FREEZE_WRITE;
 		smp_wmb();
 
-		__fsync_super(sb);
+		sync_filesystem(sb);
 
 		sb->s_frozen = SB_FREEZE_TRANS;
 		smp_wmb();
@@ -492,6 +498,11 @@ void __init bdev_cache_init(void)
 	bd_mnt = kern_mount(&bd_type);
 	if (IS_ERR(bd_mnt))
 		panic("Cannot create bdev pseudo-fs");
+	/*
+	 * This vfsmount structure is only used to obtain the
+	 * blockdev_superblock, so tell kmemleak not to report it.
+	 */
+	kmemleak_not_leak(bd_mnt);
 	blockdev_superblock = bd_mnt->mnt_sb;	/* For writeback */
 }
 
@@ -1111,7 +1122,7 @@ EXPORT_SYMBOL(check_disk_change);
 
 void bd_set_size(struct block_device *bdev, loff_t size)
 {
-	unsigned bsize = bdev_hardsect_size(bdev);
+	unsigned bsize = bdev_logical_block_size(bdev);
 
 	bdev->bd_inode->i_size = size;
 	while (bsize < PAGE_CACHE_SIZE) {
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 94212844a9bc..a35eb36b32fd 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -6,5 +6,5 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   transaction.o inode.o file.o tree-defrag.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
-	   ref-cache.o export.o tree-log.o acl.o free-space-cache.o zlib.o \
-	   compression.o delayed-ref.o
+	   export.o tree-log.o acl.o free-space-cache.o zlib.o \
+	   compression.o delayed-ref.o relocation.o
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index cbba000dccbe..603972576f0f 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -351,9 +351,4 @@ int btrfs_init_acl(struct inode *inode, struct inode *dir)
 	return 0;
 }
 
-int btrfs_check_acl(struct inode *inode, int mask)
-{
-	return 0;
-}
-
 #endif /* CONFIG_FS_POSIX_ACL */
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 502c3d61de62..7f88628a1a72 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -294,10 +294,10 @@ int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
 		INIT_LIST_HEAD(&worker->worker_list);
 		spin_lock_init(&worker->lock);
 		atomic_set(&worker->num_pending, 0);
+		worker->workers = workers;
 		worker->task = kthread_run(worker_loop, worker,
 					   "btrfs-%s-%d", workers->name,
 					   workers->num_workers + i);
-		worker->workers = workers;
 		if (IS_ERR(worker->task)) {
 			kfree(worker);
 			ret = PTR_ERR(worker->task);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index b30986f00b9d..acb4f3517582 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -72,6 +72,9 @@ struct btrfs_inode {
 	 */
 	struct list_head ordered_operations;
 
+	/* node for the red-black tree that links inodes in subvolume root */
+	struct rb_node rb_node;
+
 	/* the space_info for where this inode's data allocations are done */
 	struct btrfs_space_info *space_info;
 
@@ -154,5 +157,4 @@ static inline void btrfs_i_size_write(struct inode *inode, u64 size)
 	BTRFS_I(inode)->disk_i_size = size;
 }
 
-
 #endif
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ab07627084f1..de1e2fd32080 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -123,7 +123,7 @@ static int check_compressed_csum(struct inode *inode,
 	u32 csum;
 	u32 *cb_sum = &cb->sums;
 
-	if (btrfs_test_flag(inode, NODATASUM))
+	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
 		return 0;
 
 	for (i = 0; i < cb->nr_pages; i++) {
@@ -670,7 +670,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			 */
 			atomic_inc(&cb->pending_bios);
 
-			if (!btrfs_test_flag(inode, NODATASUM)) {
+			if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
 				btrfs_lookup_bio_sums(root, inode, comp_bio,
 						      sums);
 			}
@@ -697,7 +697,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
 	BUG_ON(ret);
 
-	if (!btrfs_test_flag(inode, NODATASUM))
+	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
 		btrfs_lookup_bio_sums(root, inode, comp_bio, sums);
 
 	ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0);
diff --git a/fs/btrfs/crc32c.h b/fs/btrfs/crc32c.h
deleted file mode 100644
index 6e1b3de36700..000000000000
--- a/fs/btrfs/crc32c.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Copyright (C) 2008 Oracle.  All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public
- * License v2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public
- * License along with this program; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 021110-1307, USA.
- */
-
-#ifndef __BTRFS_CRC32C__
-#define __BTRFS_CRC32C__
-#include <linux/crc32c.h>
-
-/*
- * this file used to do more for selecting the HW version of crc32c,
- * perhaps it will one day again soon.
- */
-#define btrfs_crc32c(seed, data, length) crc32c(seed, data, length)
-#endif
-
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index fedf8b9f03a2..60a45f3a4e91 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -197,14 +197,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 	u32 nritems;
 	int ret = 0;
 	int level;
-	struct btrfs_root *new_root;
-
-	new_root = kmalloc(sizeof(*new_root), GFP_NOFS);
-	if (!new_root)
-		return -ENOMEM;
-
-	memcpy(new_root, root, sizeof(*new_root));
-	new_root->root_key.objectid = new_root_objectid;
+	struct btrfs_disk_key disk_key;
 
 	WARN_ON(root->ref_cows && trans->transid !=
 		root->fs_info->running_transaction->transid);
@@ -212,28 +205,37 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 
 	level = btrfs_header_level(buf);
 	nritems = btrfs_header_nritems(buf);
+	if (level == 0)
+		btrfs_item_key(buf, &disk_key, 0);
+	else
+		btrfs_node_key(buf, &disk_key, 0);
 
-	cow = btrfs_alloc_free_block(trans, new_root, buf->len, 0,
-				     new_root_objectid, trans->transid,
-				     level, buf->start, 0);
-	if (IS_ERR(cow)) {
-		kfree(new_root);
+	cow = btrfs_alloc_free_block(trans, root, buf->len, 0,
+				     new_root_objectid, &disk_key, level,
+				     buf->start, 0);
+	if (IS_ERR(cow))
 		return PTR_ERR(cow);
-	}
 
 	copy_extent_buffer(cow, buf, 0, 0, cow->len);
 	btrfs_set_header_bytenr(cow, cow->start);
 	btrfs_set_header_generation(cow, trans->transid);
-	btrfs_set_header_owner(cow, new_root_objectid);
-	btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN);
+	btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV);
+	btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN |
+				     BTRFS_HEADER_FLAG_RELOC);
+	if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
+		btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC);
+	else
+		btrfs_set_header_owner(cow, new_root_objectid);
 
 	write_extent_buffer(cow, root->fs_info->fsid,
 			    (unsigned long)btrfs_header_fsid(cow),
 			    BTRFS_FSID_SIZE);
 
 	WARN_ON(btrfs_header_generation(buf) > trans->transid);
-	ret = btrfs_inc_ref(trans, new_root, buf, cow, NULL);
-	kfree(new_root);
+	if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
+		ret = btrfs_inc_ref(trans, root, cow, 1);
+	else
+		ret = btrfs_inc_ref(trans, root, cow, 0);
 
 	if (ret)
 		return ret;
@@ -243,6 +245,125 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+/*
+ * check if the tree block can be shared by multiple trees
+ */
+int btrfs_block_can_be_shared(struct btrfs_root *root,
+			      struct extent_buffer *buf)
+{
+	/*
+	 * Tree blocks not in refernece counted trees and tree roots
+	 * are never shared. If a block was allocated after the last
+	 * snapshot and the block was not allocated by tree relocation,
+	 * we know the block is not shared.
+	 */
+	if (root->ref_cows &&
+	    buf != root->node && buf != root->commit_root &&
+	    (btrfs_header_generation(buf) <=
+	     btrfs_root_last_snapshot(&root->root_item) ||
+	     btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
+		return 1;
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	if (root->ref_cows &&
+	    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
+		return 1;
+#endif
+	return 0;
+}
+
+static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
+				       struct btrfs_root *root,
+				       struct extent_buffer *buf,
+				       struct extent_buffer *cow)
+{
+	u64 refs;
+	u64 owner;
+	u64 flags;
+	u64 new_flags = 0;
+	int ret;
+
+	/*
+	 * Backrefs update rules:
+	 *
+	 * Always use full backrefs for extent pointers in tree block
+	 * allocated by tree relocation.
+	 *
+	 * If a shared tree block is no longer referenced by its owner
+	 * tree (btrfs_header_owner(buf) == root->root_key.objectid),
+	 * use full backrefs for extent pointers in tree block.
+	 *
+	 * If a tree block is been relocating
+	 * (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID),
+	 * use full backrefs for extent pointers in tree block.
+	 * The reason for this is some operations (such as drop tree)
+	 * are only allowed for blocks use full backrefs.
+	 */
+
+	if (btrfs_block_can_be_shared(root, buf)) {
+		ret = btrfs_lookup_extent_info(trans, root, buf->start,
+					       buf->len, &refs, &flags);
+		BUG_ON(ret);
+		BUG_ON(refs == 0);
+	} else {
+		refs = 1;
+		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
+		    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
+			flags = BTRFS_BLOCK_FLAG_FULL_BACKREF;
+		else
+			flags = 0;
+	}
+
+	owner = btrfs_header_owner(buf);
+	BUG_ON(owner == BTRFS_TREE_RELOC_OBJECTID &&
+	       !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
+
+	if (refs > 1) {
+		if ((owner == root->root_key.objectid ||
+		     root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) &&
+		    !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) {
+			ret = btrfs_inc_ref(trans, root, buf, 1);
+			BUG_ON(ret);
+
+			if (root->root_key.objectid ==
+			    BTRFS_TREE_RELOC_OBJECTID) {
+				ret = btrfs_dec_ref(trans, root, buf, 0);
+				BUG_ON(ret);
+				ret = btrfs_inc_ref(trans, root, cow, 1);
+				BUG_ON(ret);
+			}
+			new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
+		} else {
+
+			if (root->root_key.objectid ==
+			    BTRFS_TREE_RELOC_OBJECTID)
+				ret = btrfs_inc_ref(trans, root, cow, 1);
+			else
+				ret = btrfs_inc_ref(trans, root, cow, 0);
+			BUG_ON(ret);
+		}
+		if (new_flags != 0) {
+			ret = btrfs_set_disk_extent_flags(trans, root,
+							  buf->start,
+							  buf->len,
+							  new_flags, 0);
+			BUG_ON(ret);
+		}
+	} else {
+		if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
+			if (root->root_key.objectid ==
+			    BTRFS_TREE_RELOC_OBJECTID)
+				ret = btrfs_inc_ref(trans, root, cow, 1);
+			else
+				ret = btrfs_inc_ref(trans, root, cow, 0);
+			BUG_ON(ret);
+			ret = btrfs_dec_ref(trans, root, buf, 1);
+			BUG_ON(ret);
+		}
+		clean_tree_block(trans, root, buf);
+	}
+	return 0;
+}
+
 /*
  * does the dirty work in cow of a single block.  The parent block (if
  * supplied) is updated to point to the new cow copy.  The new buffer is marked
@@ -262,34 +383,39 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 			     struct extent_buffer **cow_ret,
 			     u64 search_start, u64 empty_size)
 {
-	u64 parent_start;
+	struct btrfs_disk_key disk_key;
 	struct extent_buffer *cow;
-	u32 nritems;
-	int ret = 0;
 	int level;
 	int unlock_orig = 0;
+	u64 parent_start;
 
 	if (*cow_ret == buf)
 		unlock_orig = 1;
 
 	btrfs_assert_tree_locked(buf);
 
-	if (parent)
-		parent_start = parent->start;
-	else
-		parent_start = 0;
-
 	WARN_ON(root->ref_cows && trans->transid !=
 		root->fs_info->running_transaction->transid);
 	WARN_ON(root->ref_cows && trans->transid != root->last_trans);
 
 	level = btrfs_header_level(buf);
-	nritems = btrfs_header_nritems(buf);
 
-	cow = btrfs_alloc_free_block(trans, root, buf->len,
-				     parent_start, root->root_key.objectid,
-				     trans->transid, level,
-				     search_start, empty_size);
+	if (level == 0)
+		btrfs_item_key(buf, &disk_key, 0);
+	else
+		btrfs_node_key(buf, &disk_key, 0);
+
+	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
+		if (parent)
+			parent_start = parent->start;
+		else
+			parent_start = 0;
+	} else
+		parent_start = 0;
+
+	cow = btrfs_alloc_free_block(trans, root, buf->len, parent_start,
+				     root->root_key.objectid, &disk_key,
+				     level, search_start, empty_size);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
@@ -298,83 +424,53 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	copy_extent_buffer(cow, buf, 0, 0, cow->len);
 	btrfs_set_header_bytenr(cow, cow->start);
 	btrfs_set_header_generation(cow, trans->transid);
-	btrfs_set_header_owner(cow, root->root_key.objectid);
-	btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN);
+	btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV);
+	btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN |
+				     BTRFS_HEADER_FLAG_RELOC);
+	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+		btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC);
+	else
+		btrfs_set_header_owner(cow, root->root_key.objectid);
 
 	write_extent_buffer(cow, root->fs_info->fsid,
 			    (unsigned long)btrfs_header_fsid(cow),
 			    BTRFS_FSID_SIZE);
 
-	WARN_ON(btrfs_header_generation(buf) > trans->transid);
-	if (btrfs_header_generation(buf) != trans->transid) {
-		u32 nr_extents;
-		ret = btrfs_inc_ref(trans, root, buf, cow, &nr_extents);
-		if (ret)
-			return ret;
-
-		ret = btrfs_cache_ref(trans, root, buf, nr_extents);
-		WARN_ON(ret);
-	} else if (btrfs_header_owner(buf) == BTRFS_TREE_RELOC_OBJECTID) {
-		/*
-		 * There are only two places that can drop reference to
-		 * tree blocks owned by living reloc trees, one is here,
-		 * the other place is btrfs_drop_subtree. In both places,
-		 * we check reference count while tree block is locked.
-		 * Furthermore, if reference count is one, it won't get
-		 * increased by someone else.
-		 */
-		u32 refs;
-		ret = btrfs_lookup_extent_ref(trans, root, buf->start,
-					      buf->len, &refs);
-		BUG_ON(ret);
-		if (refs == 1) {
-			ret = btrfs_update_ref(trans, root, buf, cow,
-					       0, nritems);
-			clean_tree_block(trans, root, buf);
-		} else {
-			ret = btrfs_inc_ref(trans, root, buf, cow, NULL);
-		}
-		BUG_ON(ret);
-	} else {
-		ret = btrfs_update_ref(trans, root, buf, cow, 0, nritems);
-		if (ret)
-			return ret;
-		clean_tree_block(trans, root, buf);
-	}
-
-	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
-		ret = btrfs_reloc_tree_cache_ref(trans, root, cow, buf->start);
-		WARN_ON(ret);
-	}
+	update_ref_for_cow(trans, root, buf, cow);
 
 	if (buf == root->node) {
 		WARN_ON(parent && parent != buf);
+		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
+		    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
+			parent_start = buf->start;
+		else
+			parent_start = 0;
 
 		spin_lock(&root->node_lock);
 		root->node = cow;
 		extent_buffer_get(cow);
 		spin_unlock(&root->node_lock);
 
-		if (buf != root->commit_root) {
-			btrfs_free_extent(trans, root, buf->start,
-					  buf->len, buf->start,
-					  root->root_key.objectid,
-					  btrfs_header_generation(buf),
-					  level, 1);
-		}
+		btrfs_free_extent(trans, root, buf->start, buf->len,
+				  parent_start, root->root_key.objectid,
+				  level, 0);
 		free_extent_buffer(buf);
 		add_root_to_dirty_list(root);
 	} else {
+		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+			parent_start = parent->start;
+		else
+			parent_start = 0;
+
+		WARN_ON(trans->transid != btrfs_header_generation(parent));
 		btrfs_set_node_blockptr(parent, parent_slot,
 					cow->start);
-		WARN_ON(trans->transid == 0);
 		btrfs_set_node_ptr_generation(parent, parent_slot,
 					      trans->transid);
 		btrfs_mark_buffer_dirty(parent);
-		WARN_ON(btrfs_header_generation(parent) != trans->transid);
 		btrfs_free_extent(trans, root, buf->start, buf->len,
-				  parent_start, btrfs_header_owner(parent),
-				  btrfs_header_generation(parent), level, 1);
+				  parent_start, root->root_key.objectid,
+				  level, 0);
 	}
 	if (unlock_orig)
 		btrfs_tree_unlock(buf);
@@ -384,6 +480,18 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+static inline int should_cow_block(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root,
+				   struct extent_buffer *buf)
+{
+	if (btrfs_header_generation(buf) == trans->transid &&
+	    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
+	    !(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
+	      btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
+		return 0;
+	return 1;
+}
+
 /*
  * cows a single block, see __btrfs_cow_block for the real work.
  * This version of it has extra checks so that a block isn't cow'd more than
@@ -411,9 +519,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		WARN_ON(1);
 	}
 
-	if (btrfs_header_generation(buf) == trans->transid &&
-	    btrfs_header_owner(buf) == root->root_key.objectid &&
-	    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
+	if (!should_cow_block(trans, root, buf)) {
 		*cow_ret = buf;
 		return 0;
 	}
@@ -469,7 +575,7 @@ static int comp_keys(struct btrfs_disk_key *disk, struct btrfs_key *k2)
 /*
  * same as comp_keys only with two btrfs_key's
  */
-static int comp_cpu_keys(struct btrfs_key *k1, struct btrfs_key *k2)
+int btrfs_comp_cpu_keys(struct btrfs_key *k1, struct btrfs_key *k2)
 {
 	if (k1->objectid > k2->objectid)
 		return 1;
@@ -845,6 +951,12 @@ static int bin_search(struct extent_buffer *eb, struct btrfs_key *key,
 	return -1;
 }
 
+int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
+		     int level, int *slot)
+{
+	return bin_search(eb, key, level, slot);
+}
+
 /* given a node and slot number, this reads the blocks it points to.  The
  * extent buffer is returned with a reference taken (but unlocked).
  * NULL is returned on error.
@@ -921,13 +1033,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		root->node = child;
 		spin_unlock(&root->node_lock);
 
-		ret = btrfs_update_extent_ref(trans, root, child->start,
-					      child->len,
-					      mid->start, child->start,
-					      root->root_key.objectid,
-					      trans->transid, level - 1);
-		BUG_ON(ret);
-
 		add_root_to_dirty_list(root);
 		btrfs_tree_unlock(child);
 
@@ -938,9 +1043,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		/* once for the path */
 		free_extent_buffer(mid);
 		ret = btrfs_free_extent(trans, root, mid->start, mid->len,
-					mid->start, root->root_key.objectid,
-					btrfs_header_generation(mid),
-					level, 1);
+					0, root->root_key.objectid, level, 1);
 		/* once for the root ptr */
 		free_extent_buffer(mid);
 		return ret;
@@ -949,8 +1052,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 	    BTRFS_NODEPTRS_PER_BLOCK(root) / 4)
 		return 0;
 
-	if (trans->transaction->delayed_refs.flushing &&
-	    btrfs_header_nritems(mid) > 2)
+	if (btrfs_header_nritems(mid) > 2)
 		return 0;
 
 	if (btrfs_header_nritems(mid) < 2)
@@ -998,7 +1100,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			ret = wret;
 		if (btrfs_header_nritems(right) == 0) {
 			u64 bytenr = right->start;
-			u64 generation = btrfs_header_generation(parent);
 			u32 blocksize = right->len;
 
 			clean_tree_block(trans, root, right);
@@ -1010,9 +1111,9 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			if (wret)
 				ret = wret;
 			wret = btrfs_free_extent(trans, root, bytenr,
-						 blocksize, parent->start,
-						 btrfs_header_owner(parent),
-						 generation, level, 1);
+						 blocksize, 0,
+						 root->root_key.objectid,
+						 level, 0);
 			if (wret)
 				ret = wret;
 		} else {
@@ -1047,7 +1148,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 	}
 	if (btrfs_header_nritems(mid) == 0) {
 		/* we've managed to empty the middle node, drop it */
-		u64 root_gen = btrfs_header_generation(parent);
 		u64 bytenr = mid->start;
 		u32 blocksize = mid->len;
 
@@ -1059,9 +1159,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		if (wret)
 			ret = wret;
 		wret = btrfs_free_extent(trans, root, bytenr, blocksize,
-					 parent->start,
-					 btrfs_header_owner(parent),
-					 root_gen, level, 1);
+					 0, root->root_key.objectid,
+					 level, 0);
 		if (wret)
 			ret = wret;
 	} else {
@@ -1437,7 +1536,7 @@ noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
 {
 	int i;
 
-	if (path->keep_locks || path->lowest_level)
+	if (path->keep_locks)
 		return;
 
 	for (i = level; i < BTRFS_MAX_LEVEL; i++) {
@@ -1552,7 +1651,7 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans,
 		}
 		b = p->nodes[level];
 	} else if (ins_len < 0 && btrfs_header_nritems(b) <
-		   BTRFS_NODEPTRS_PER_BLOCK(root) / 4) {
+		   BTRFS_NODEPTRS_PER_BLOCK(root) / 2) {
 		int sret;
 
 		sret = reada_for_balance(root, p, level);
@@ -1614,10 +1713,17 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
 		lowest_unlock = 2;
 
 again:
-	if (p->skip_locking)
-		b = btrfs_root_node(root);
-	else
-		b = btrfs_lock_root_node(root);
+	if (p->search_commit_root) {
+		b = root->commit_root;
+		extent_buffer_get(b);
+		if (!p->skip_locking)
+			btrfs_tree_lock(b);
+	} else {
+		if (p->skip_locking)
+			b = btrfs_root_node(root);
+		else
+			b = btrfs_lock_root_node(root);
+	}
 
 	while (b) {
 		level = btrfs_header_level(b);
@@ -1638,11 +1744,9 @@ again:
 			 * then we don't want to set the path blocking,
 			 * so we test it here
 			 */
-			if (btrfs_header_generation(b) == trans->transid &&
-			    btrfs_header_owner(b) == root->root_key.objectid &&
-			    !btrfs_header_flag(b, BTRFS_HEADER_FLAG_WRITTEN)) {
+			if (!should_cow_block(trans, root, b))
 				goto cow_done;
-			}
+
 			btrfs_set_path_blocking(p);
 
 			wret = btrfs_cow_block(trans, root, b,
@@ -1764,138 +1868,6 @@ done:
 	return ret;
 }
 
-int btrfs_merge_path(struct btrfs_trans_handle *trans,
-		     struct btrfs_root *root,
-		     struct btrfs_key *node_keys,
-		     u64 *nodes, int lowest_level)
-{
-	struct extent_buffer *eb;
-	struct extent_buffer *parent;
-	struct btrfs_key key;
-	u64 bytenr;
-	u64 generation;
-	u32 blocksize;
-	int level;
-	int slot;
-	int key_match;
-	int ret;
-
-	eb = btrfs_lock_root_node(root);
-	ret = btrfs_cow_block(trans, root, eb, NULL, 0, &eb);
-	BUG_ON(ret);
-
-	btrfs_set_lock_blocking(eb);
-
-	parent = eb;
-	while (1) {
-		level = btrfs_header_level(parent);
-		if (level == 0 || level <= lowest_level)
-			break;
-
-		ret = bin_search(parent, &node_keys[lowest_level], level,
-				 &slot);
-		if (ret && slot > 0)
-			slot--;
-
-		bytenr = btrfs_node_blockptr(parent, slot);
-		if (nodes[level - 1] == bytenr)
-			break;
-
-		blocksize = btrfs_level_size(root, level - 1);
-		generation = btrfs_node_ptr_generation(parent, slot);
-		btrfs_node_key_to_cpu(eb, &key, slot);
-		key_match = !memcmp(&key, &node_keys[level - 1], sizeof(key));
-
-		if (generation == trans->transid) {
-			eb = read_tree_block(root, bytenr, blocksize,
-					     generation);
-			btrfs_tree_lock(eb);
-			btrfs_set_lock_blocking(eb);
-		}
-
-		/*
-		 * if node keys match and node pointer hasn't been modified
-		 * in the running transaction, we can merge the path. for
-		 * blocks owened by reloc trees, the node pointer check is
-		 * skipped, this is because these blocks are fully controlled
-		 * by the space balance code, no one else can modify them.
-		 */
-		if (!nodes[level - 1] || !key_match ||
-		    (generation == trans->transid &&
-		     btrfs_header_owner(eb) != BTRFS_TREE_RELOC_OBJECTID)) {
-			if (level == 1 || level == lowest_level + 1) {
-				if (generation == trans->transid) {
-					btrfs_tree_unlock(eb);
-					free_extent_buffer(eb);
-				}
-				break;
-			}
-
-			if (generation != trans->transid) {
-				eb = read_tree_block(root, bytenr, blocksize,
-						generation);
-				btrfs_tree_lock(eb);
-				btrfs_set_lock_blocking(eb);
-			}
-
-			ret = btrfs_cow_block(trans, root, eb, parent, slot,
-					      &eb);
-			BUG_ON(ret);
-
-			if (root->root_key.objectid ==
-			    BTRFS_TREE_RELOC_OBJECTID) {
-				if (!nodes[level - 1]) {
-					nodes[level - 1] = eb->start;
-					memcpy(&node_keys[level - 1], &key,
-					       sizeof(node_keys[0]));
-				} else {
-					WARN_ON(1);
-				}
-			}
-
-			btrfs_tree_unlock(parent);
-			free_extent_buffer(parent);
-			parent = eb;
-			continue;
-		}
-
-		btrfs_set_node_blockptr(parent, slot, nodes[level - 1]);
-		btrfs_set_node_ptr_generation(parent, slot, trans->transid);
-		btrfs_mark_buffer_dirty(parent);
-
-		ret = btrfs_inc_extent_ref(trans, root,
-					nodes[level - 1],
-					blocksize, parent->start,
-					btrfs_header_owner(parent),
-					btrfs_header_generation(parent),
-					level - 1);
-		BUG_ON(ret);
-
-		/*
-		 * If the block was created in the running transaction,
-		 * it's possible this is the last reference to it, so we
-		 * should drop the subtree.
-		 */
-		if (generation == trans->transid) {
-			ret = btrfs_drop_subtree(trans, root, eb, parent);
-			BUG_ON(ret);
-			btrfs_tree_unlock(eb);
-			free_extent_buffer(eb);
-		} else {
-			ret = btrfs_free_extent(trans, root, bytenr,
-					blocksize, parent->start,
-					btrfs_header_owner(parent),
-					btrfs_header_generation(parent),
-					level - 1, 1);
-			BUG_ON(ret);
-		}
-		break;
-	}
-	btrfs_tree_unlock(parent);
-	free_extent_buffer(parent);
-	return 0;
-}
-
 /*
  * adjust the pointers going up the tree, starting at level
  * making sure the right key of each node is points to 'key'.
@@ -2021,9 +1993,6 @@ static int push_node_left(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(src);
 	btrfs_mark_buffer_dirty(dst);
 
-	ret = btrfs_update_ref(trans, root, src, dst, dst_nritems, push_items);
-	BUG_ON(ret);
-
 	return ret;
 }
 
@@ -2083,9 +2052,6 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(src);
 	btrfs_mark_buffer_dirty(dst);
 
-	ret = btrfs_update_ref(trans, root, src, dst, 0, push_items);
-	BUG_ON(ret);
-
 	return ret;
 }
 
@@ -2105,7 +2071,6 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	struct extent_buffer *c;
 	struct extent_buffer *old;
 	struct btrfs_disk_key lower_key;
-	int ret;
 
 	BUG_ON(path->nodes[level]);
 	BUG_ON(path->nodes[level-1] != root->node);
@@ -2117,16 +2082,17 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 		btrfs_node_key(lower, &lower_key, 0);
 
 	c = btrfs_alloc_free_block(trans, root, root->nodesize, 0,
-				   root->root_key.objectid, trans->transid,
+				   root->root_key.objectid, &lower_key,
 				   level, root->node->start, 0);
 	if (IS_ERR(c))
 		return PTR_ERR(c);
 
-	memset_extent_buffer(c, 0, 0, root->nodesize);
+	memset_extent_buffer(c, 0, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_nritems(c, 1);
 	btrfs_set_header_level(c, level);
 	btrfs_set_header_bytenr(c, c->start);
 	btrfs_set_header_generation(c, trans->transid);
+	btrfs_set_header_backref_rev(c, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(c, root->root_key.objectid);
 
 	write_extent_buffer(c, root->fs_info->fsid,
@@ -2151,12 +2117,6 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	root->node = c;
 	spin_unlock(&root->node_lock);
 
-	ret = btrfs_update_extent_ref(trans, root, lower->start,
-				      lower->len, lower->start, c->start,
-				      root->root_key.objectid,
-				      trans->transid, level - 1);
-	BUG_ON(ret);
-
 	/* the super has an extra ref to root->node */
 	free_extent_buffer(old);
 
@@ -2233,7 +2193,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 		ret = insert_new_root(trans, root, path, level + 1);
 		if (ret)
 			return ret;
-	} else if (!trans->transaction->delayed_refs.flushing) {
+	} else {
 		ret = push_nodes_for_insert(trans, root, path, level);
 		c = path->nodes[level];
 		if (!ret && btrfs_header_nritems(c) <
@@ -2244,20 +2204,21 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	}
 
 	c_nritems = btrfs_header_nritems(c);
+	mid = (c_nritems + 1) / 2;
+	btrfs_node_key(c, &disk_key, mid);
 
-	split = btrfs_alloc_free_block(trans, root, root->nodesize,
-					path->nodes[level + 1]->start,
+	split = btrfs_alloc_free_block(trans, root, root->nodesize, 0,
 					root->root_key.objectid,
-					trans->transid, level, c->start, 0);
+					&disk_key, level, c->start, 0);
 	if (IS_ERR(split))
 		return PTR_ERR(split);
 
-	btrfs_set_header_flags(split, btrfs_header_flags(c));
+	memset_extent_buffer(split, 0, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_level(split, btrfs_header_level(c));
 	btrfs_set_header_bytenr(split, split->start);
 	btrfs_set_header_generation(split, trans->transid);
+	btrfs_set_header_backref_rev(split, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(split, root->root_key.objectid);
-	btrfs_set_header_flags(split, 0);
 	write_extent_buffer(split, root->fs_info->fsid,
 			    (unsigned long)btrfs_header_fsid(split),
 			    BTRFS_FSID_SIZE);
@@ -2265,7 +2226,6 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 			    (unsigned long)btrfs_header_chunk_tree_uuid(split),
 			    BTRFS_UUID_SIZE);
 
-	mid = (c_nritems + 1) / 2;
 
 	copy_extent_buffer(split, c,
 			   btrfs_node_key_ptr_offset(0),
@@ -2278,16 +2238,12 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(c);
 	btrfs_mark_buffer_dirty(split);
 
-	btrfs_node_key(split, &disk_key, 0);
 	wret = insert_ptr(trans, root, path, &disk_key, split->start,
 			  path->slots[level + 1] + 1,
 			  level + 1);
 	if (wret)
 		ret = wret;
 
-	ret = btrfs_update_ref(trans, root, c, split, 0, c_nritems - mid);
-	BUG_ON(ret);
-
 	if (path->slots[level] >= mid) {
 		path->slots[level] -= mid;
 		btrfs_tree_unlock(c);
@@ -2360,7 +2316,6 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 	u32 right_nritems;
 	u32 data_end;
 	u32 this_item_size;
-	int ret;
 
 	if (empty)
 		nr = 0;
@@ -2473,9 +2428,6 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 		btrfs_mark_buffer_dirty(left);
 	btrfs_mark_buffer_dirty(right);
 
-	ret = btrfs_update_ref(trans, root, left, right, 0, push_items);
-	BUG_ON(ret);
-
 	btrfs_item_key(right, &disk_key, 0);
 	btrfs_set_node_key(upper, &disk_key, slot + 1);
 	btrfs_mark_buffer_dirty(upper);
@@ -2720,10 +2672,6 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
 	if (right_nritems)
 		btrfs_mark_buffer_dirty(right);
 
-	ret = btrfs_update_ref(trans, root, right, left,
-			       old_left_nritems, push_items);
-	BUG_ON(ret);
-
 	btrfs_item_key(right, &disk_key, 0);
 	wret = fixup_low_keys(trans, root, path, &disk_key, 1);
 	if (wret)
@@ -2880,9 +2828,6 @@ static noinline int copy_for_split(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(l);
 	BUG_ON(path->slots[0] != slot);
 
-	ret = btrfs_update_ref(trans, root, l, right, 0, nritems);
-	BUG_ON(ret);
-
 	if (mid <= slot) {
 		btrfs_tree_unlock(path->nodes[0]);
 		free_extent_buffer(path->nodes[0]);
@@ -2911,6 +2856,7 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
 			       struct btrfs_path *path, int data_size,
 			       int extend)
 {
+	struct btrfs_disk_key disk_key;
 	struct extent_buffer *l;
 	u32 nritems;
 	int mid;
@@ -2918,12 +2864,11 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
 	struct extent_buffer *right;
 	int ret = 0;
 	int wret;
-	int double_split;
+	int split;
 	int num_doubles = 0;
 
 	/* first try to make some room by pushing left and right */
-	if (data_size && ins_key->type != BTRFS_DIR_ITEM_KEY &&
-	    !trans->transaction->delayed_refs.flushing) {
+	if (data_size && ins_key->type != BTRFS_DIR_ITEM_KEY) {
 		wret = push_leaf_right(trans, root, path, data_size, 0);
 		if (wret < 0)
 			return wret;
@@ -2945,16 +2890,53 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
 			return ret;
 	}
 again:
-	double_split = 0;
+	split = 1;
 	l = path->nodes[0];
 	slot = path->slots[0];
 	nritems = btrfs_header_nritems(l);
 	mid = (nritems + 1) / 2;
 
-	right = btrfs_alloc_free_block(trans, root, root->leafsize,
-					path->nodes[1]->start,
+	if (mid <= slot) {
+		if (nritems == 1 ||
+		    leaf_space_used(l, mid, nritems - mid) + data_size >
+			BTRFS_LEAF_DATA_SIZE(root)) {
+			if (slot >= nritems) {
+				split = 0;
+			} else {
+				mid = slot;
+				if (mid != nritems &&
+				    leaf_space_used(l, mid, nritems - mid) +
+				    data_size > BTRFS_LEAF_DATA_SIZE(root)) {
+					split = 2;
+				}
+			}
+		}
+	} else {
+		if (leaf_space_used(l, 0, mid) + data_size >
+			BTRFS_LEAF_DATA_SIZE(root)) {
+			if (!extend && data_size && slot == 0) {
+				split = 0;
+			} else if ((extend || !data_size) && slot == 0) {
+				mid = 1;
+			} else {
+				mid = slot;
+				if (mid != nritems &&
+				    leaf_space_used(l, mid, nritems - mid) +
+				    data_size > BTRFS_LEAF_DATA_SIZE(root)) {
+					split = 2 ;
+				}
+			}
+		}
+	}
+
+	if (split == 0)
+		btrfs_cpu_key_to_disk(&disk_key, ins_key);
+	else
+		btrfs_item_key(l, &disk_key, mid);
+
+	right = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
 					root->root_key.objectid,
-					trans->transid, 0, l->start, 0);
+					&disk_key, 0, l->start, 0);
 	if (IS_ERR(right)) {
 		BUG_ON(1);
 		return PTR_ERR(right);
@@ -2963,6 +2945,7 @@ again:
 	memset_extent_buffer(right, 0, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_bytenr(right, right->start);
 	btrfs_set_header_generation(right, trans->transid);
+	btrfs_set_header_backref_rev(right, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(right, root->root_key.objectid);
 	btrfs_set_header_level(right, 0);
 	write_extent_buffer(right, root->fs_info->fsid,
@@ -2973,79 +2956,47 @@ again:
 			    (unsigned long)btrfs_header_chunk_tree_uuid(right),
 			    BTRFS_UUID_SIZE);
 
-	if (mid <= slot) {
-		if (nritems == 1 ||
-		    leaf_space_used(l, mid, nritems - mid) + data_size >
-			BTRFS_LEAF_DATA_SIZE(root)) {
-			if (slot >= nritems) {
-				struct btrfs_disk_key disk_key;
+	if (split == 0) {
+		if (mid <= slot) {
+			btrfs_set_header_nritems(right, 0);
+			wret = insert_ptr(trans, root, path,
+					  &disk_key, right->start,
+					  path->slots[1] + 1, 1);
+			if (wret)
+				ret = wret;
 
-				btrfs_cpu_key_to_disk(&disk_key, ins_key);
-				btrfs_set_header_nritems(right, 0);
-				wret = insert_ptr(trans, root, path,
-						  &disk_key, right->start,
-						  path->slots[1] + 1, 1);
+			btrfs_tree_unlock(path->nodes[0]);
+			free_extent_buffer(path->nodes[0]);
+			path->nodes[0] = right;
+			path->slots[0] = 0;
+			path->slots[1] += 1;
+		} else {
+			btrfs_set_header_nritems(right, 0);
+			wret = insert_ptr(trans, root, path,
+					  &disk_key,
+					  right->start,
+					  path->slots[1], 1);
+			if (wret)
+				ret = wret;
+			btrfs_tree_unlock(path->nodes[0]);
+			free_extent_buffer(path->nodes[0]);
+			path->nodes[0] = right;
+			path->slots[0] = 0;
+			if (path->slots[1] == 0) {
+				wret = fixup_low_keys(trans, root,
+						path, &disk_key, 1);
 				if (wret)
 					ret = wret;
-
-				btrfs_tree_unlock(path->nodes[0]);
-				free_extent_buffer(path->nodes[0]);
-				path->nodes[0] = right;
-				path->slots[0] = 0;
-				path->slots[1] += 1;
-				btrfs_mark_buffer_dirty(right);
-				return ret;
-			}
-			mid = slot;
-			if (mid != nritems &&
-			    leaf_space_used(l, mid, nritems - mid) +
-			    data_size > BTRFS_LEAF_DATA_SIZE(root)) {
-				double_split = 1;
-			}
-		}
-	} else {
-		if (leaf_space_used(l, 0, mid) + data_size >
-			BTRFS_LEAF_DATA_SIZE(root)) {
-			if (!extend && data_size && slot == 0) {
-				struct btrfs_disk_key disk_key;
-
-				btrfs_cpu_key_to_disk(&disk_key, ins_key);
-				btrfs_set_header_nritems(right, 0);
-				wret = insert_ptr(trans, root, path,
-						  &disk_key,
-						  right->start,
-						  path->slots[1], 1);
-				if (wret)
-					ret = wret;
-				btrfs_tree_unlock(path->nodes[0]);
-				free_extent_buffer(path->nodes[0]);
-				path->nodes[0] = right;
-				path->slots[0] = 0;
-				if (path->slots[1] == 0) {
-					wret = fixup_low_keys(trans, root,
-						      path, &disk_key, 1);
-					if (wret)
-						ret = wret;
-				}
-				btrfs_mark_buffer_dirty(right);
-				return ret;
-			} else if ((extend || !data_size) && slot == 0) {
-				mid = 1;
-			} else {
-				mid = slot;
-				if (mid != nritems &&
-				    leaf_space_used(l, mid, nritems - mid) +
-				    data_size > BTRFS_LEAF_DATA_SIZE(root)) {
-					double_split = 1;
-				}
 			}
 		}
+		btrfs_mark_buffer_dirty(right);
+		return ret;
 	}
 
 	ret = copy_for_split(trans, root, path, l, right, slot, mid, nritems);
 	BUG_ON(ret);
 
-	if (double_split) {
+	if (split == 2) {
 		BUG_ON(num_doubles != 0);
 		num_doubles++;
 		goto again;
@@ -3447,7 +3398,7 @@ int btrfs_insert_some_items(struct btrfs_trans_handle *trans,
 		/* figure out how many keys we can insert in here */
 		total_data = data_size[0];
 		for (i = 1; i < nr; i++) {
-			if (comp_cpu_keys(&found_key, cpu_key + i) <= 0)
+			if (btrfs_comp_cpu_keys(&found_key, cpu_key + i) <= 0)
 				break;
 			total_data += data_size[i];
 		}
@@ -3745,9 +3696,7 @@ static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 /*
  * a helper function to delete the leaf pointed to by path->slots[1] and
- * path->nodes[1].  bytenr is the node block pointer, but since the callers
- * already know it, it is faster to have them pass it down than to
- * read it out of the node again.
+ * path->nodes[1].
  *
  * This deletes the pointer in path->nodes[1] and frees the leaf
  * block extent.  zero is returned if it all worked out, < 0 otherwise.
@@ -3755,15 +3704,14 @@ static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
  * The path must have already been setup for deleting the leaf, including
  * all the proper balancing.  path->nodes[1] must be locked.
  */
-noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root,
-			    struct btrfs_path *path, u64 bytenr)
+static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root,
+				   struct btrfs_path *path,
+				   struct extent_buffer *leaf)
 {
 	int ret;
-	u64 root_gen = btrfs_header_generation(path->nodes[1]);
-	u64 parent_start = path->nodes[1]->start;
-	u64 parent_owner = btrfs_header_owner(path->nodes[1]);
 
+	WARN_ON(btrfs_header_generation(leaf) != trans->transid);
 	ret = del_ptr(trans, root, path, 1, path->slots[1]);
 	if (ret)
 		return ret;
@@ -3774,10 +3722,8 @@ noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans,
 	 */
 	btrfs_unlock_up_safe(path, 0);
 
-	ret = btrfs_free_extent(trans, root, bytenr,
-				btrfs_level_size(root, 0),
-				parent_start, parent_owner,
-				root_gen, 0, 1);
+	ret = btrfs_free_extent(trans, root, leaf->start, leaf->len,
+				0, root->root_key.objectid, 0, 0);
 	return ret;
 }
 /*
@@ -3845,7 +3791,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		if (leaf == root->node) {
 			btrfs_set_header_level(leaf, 0);
 		} else {
-			ret = btrfs_del_leaf(trans, root, path, leaf->start);
+			ret = btrfs_del_leaf(trans, root, path, leaf);
 			BUG_ON(ret);
 		}
 	} else {
@@ -3861,8 +3807,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		}
 
 		/* delete the leaf if it is mostly empty */
-		if (used < BTRFS_LEAF_DATA_SIZE(root) / 4 &&
-		    !trans->transaction->delayed_refs.flushing) {
+		if (used < BTRFS_LEAF_DATA_SIZE(root) / 2) {
 			/* push_leaf_left fixes the path.
 			 * make sure the path still points to our leaf
 			 * for possible call to del_ptr below
@@ -3884,8 +3829,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 			if (btrfs_header_nritems(leaf) == 0) {
 				path->slots[1] = slot;
-				ret = btrfs_del_leaf(trans, root, path,
-						     leaf->start);
+				ret = btrfs_del_leaf(trans, root, path, leaf);
 				BUG_ON(ret);
 				free_extent_buffer(leaf);
 			} else {
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4414a5d9983a..03441a99ea38 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -45,6 +45,8 @@ struct btrfs_ordered_sum;
 
 #define BTRFS_MAX_LEVEL 8
 
+#define BTRFS_COMPAT_EXTENT_TREE_V0
+
 /*
  * files bigger than this get some pre-flushing when they are added
  * to the ordered operations list.  That way we limit the total
@@ -267,7 +269,18 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 }
 
 #define BTRFS_FSID_SIZE 16
-#define BTRFS_HEADER_FLAG_WRITTEN (1 << 0)
+#define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
+#define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
+#define BTRFS_SUPER_FLAG_SEEDING	(1ULL << 32)
+#define BTRFS_SUPER_FLAG_METADUMP	(1ULL << 33)
+
+#define BTRFS_BACKREF_REV_MAX		256
+#define BTRFS_BACKREF_REV_SHIFT		56
+#define BTRFS_BACKREF_REV_MASK		(((u64)BTRFS_BACKREF_REV_MAX - 1) << \
+					 BTRFS_BACKREF_REV_SHIFT)
+
+#define BTRFS_OLD_BACKREF_REV		0
+#define BTRFS_MIXED_BACKREF_REV		1
 
 /*
  * every tree block (leaf or node) starts with this header.
@@ -296,7 +309,6 @@ struct btrfs_header {
 					sizeof(struct btrfs_item) - \
 					sizeof(struct btrfs_file_extent_item))
 
-#define BTRFS_SUPER_FLAG_SEEDING (1ULL << 32)
 
 /*
  * this is a very generous portion of the super block, giving us
@@ -355,9 +367,12 @@ struct btrfs_super_block {
  * Compat flags that we support.  If any incompat flags are set other than the
  * ones specified below then we will fail to mount
  */
-#define BTRFS_FEATURE_COMPAT_SUPP	0x0
-#define BTRFS_FEATURE_COMPAT_RO_SUPP	0x0
-#define BTRFS_FEATURE_INCOMPAT_SUPP	0x0
+#define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
+
+#define BTRFS_FEATURE_COMPAT_SUPP		0ULL
+#define BTRFS_FEATURE_COMPAT_RO_SUPP		0ULL
+#define BTRFS_FEATURE_INCOMPAT_SUPP		\
+	BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF
 
 /*
  * A leaf is full of items. offset and size tell us where to find
@@ -421,23 +436,65 @@ struct btrfs_path {
 	unsigned int keep_locks:1;
 	unsigned int skip_locking:1;
 	unsigned int leave_spinning:1;
+	unsigned int search_commit_root:1;
 };
 
 /*
  * items in the extent btree are used to record the objectid of the
  * owner of the block and the number of references
  */
+
 struct btrfs_extent_item {
+	__le64 refs;
+	__le64 generation;
+	__le64 flags;
+} __attribute__ ((__packed__));
+
+struct btrfs_extent_item_v0 {
 	__le32 refs;
 } __attribute__ ((__packed__));
 
-struct btrfs_extent_ref {
+#define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r) >> 4) - \
+					sizeof(struct btrfs_item))
+
+#define BTRFS_EXTENT_FLAG_DATA		(1ULL << 0)
+#define BTRFS_EXTENT_FLAG_TREE_BLOCK	(1ULL << 1)
+
+/* following flags only apply to tree blocks */
+
+/* use full backrefs for extent pointers in the block */
+#define BTRFS_BLOCK_FLAG_FULL_BACKREF	(1ULL << 8)
+
+struct btrfs_tree_block_info {
+	struct btrfs_disk_key key;
+	u8 level;
+} __attribute__ ((__packed__));
+
+struct btrfs_extent_data_ref {
+	__le64 root;
+	__le64 objectid;
+	__le64 offset;
+	__le32 count;
+} __attribute__ ((__packed__));
+
+struct btrfs_shared_data_ref {
+	__le32 count;
+} __attribute__ ((__packed__));
+
+struct btrfs_extent_inline_ref {
+	u8 type;
+	u64 offset;
+} __attribute__ ((__packed__));
+
+/* old style backrefs item */
+struct btrfs_extent_ref_v0 {
 	__le64 root;
 	__le64 generation;
 	__le64 objectid;
-	__le32 num_refs;
+	__le32 count;
 } __attribute__ ((__packed__));
 
+
 /* dev extents record free space on individual devices.  The owner
  * field points back to the chunk allocation mapping tree that allocated
  * the extent.  The chunk tree uuid field is a way to double check the owner
@@ -695,12 +752,7 @@ struct btrfs_block_group_cache {
 	struct list_head cluster_list;
 };
 
-struct btrfs_leaf_ref_tree {
-	struct rb_root root;
-	struct list_head list;
-	spinlock_t lock;
-};
-
+struct reloc_control;
 struct btrfs_device;
 struct btrfs_fs_devices;
 struct btrfs_fs_info {
@@ -831,18 +883,11 @@ struct btrfs_fs_info {
 	struct task_struct *cleaner_kthread;
 	int thread_pool_size;
 
-	/* tree relocation relocated fields */
-	struct list_head dead_reloc_roots;
-	struct btrfs_leaf_ref_tree reloc_ref_tree;
-	struct btrfs_leaf_ref_tree shared_ref_tree;
-
 	struct kobject super_kobj;
 	struct completion kobj_unregister;
 	int do_barriers;
 	int closing;
 	int log_root_recovering;
-	atomic_t throttles;
-	atomic_t throttle_gen;
 
 	u64 total_pinned;
 
@@ -861,6 +906,8 @@ struct btrfs_fs_info {
 	 */
 	struct list_head space_info;
 
+	struct reloc_control *reloc_ctl;
+
 	spinlock_t delalloc_lock;
 	spinlock_t new_trans_lock;
 	u64 delalloc_bytes;
@@ -891,7 +938,6 @@ struct btrfs_fs_info {
  * in ram representation of the tree.  extent_root is used for all allocations
  * and for the extent tree extent_root root.
  */
-struct btrfs_dirty_root;
 struct btrfs_root {
 	struct extent_buffer *node;
 
@@ -899,9 +945,6 @@ struct btrfs_root {
 	spinlock_t node_lock;
 
 	struct extent_buffer *commit_root;
-	struct btrfs_leaf_ref_tree *ref_tree;
-	struct btrfs_leaf_ref_tree ref_tree_struct;
-	struct btrfs_dirty_root *dirty_root;
 	struct btrfs_root *log_root;
 	struct btrfs_root *reloc_root;
 
@@ -952,10 +995,15 @@ struct btrfs_root {
 	/* the dirty list is only used by non-reference counted roots */
 	struct list_head dirty_list;
 
+	struct list_head root_list;
+
 	spinlock_t list_lock;
-	struct list_head dead_list;
 	struct list_head orphan_list;
 
+	spinlock_t inode_lock;
+	/* red-black tree that keeps track of in-memory inodes */
+	struct rb_root inode_tree;
+
 	/*
 	 * right now this just gets used so that a root has its own devid
 	 * for stat.  It may be used for more later
@@ -1017,7 +1065,16 @@ struct btrfs_root {
  * are used, and how many references there are to each block
  */
 #define BTRFS_EXTENT_ITEM_KEY	168
-#define BTRFS_EXTENT_REF_KEY	180
+
+#define BTRFS_TREE_BLOCK_REF_KEY	176
+
+#define BTRFS_EXTENT_DATA_REF_KEY	178
+
+#define BTRFS_EXTENT_REF_V0_KEY		180
+
+#define BTRFS_SHARED_BLOCK_REF_KEY	182
+
+#define BTRFS_SHARED_DATA_REF_KEY	184
 
 /*
  * block groups give us hints into the extent allocation trees.  Which
@@ -1043,6 +1100,8 @@ struct btrfs_root {
 #define BTRFS_MOUNT_COMPRESS		(1 << 5)
 #define BTRFS_MOUNT_NOTREELOG           (1 << 6)
 #define BTRFS_MOUNT_FLUSHONCOMMIT       (1 << 7)
+#define BTRFS_MOUNT_SSD_SPREAD		(1 << 8)
+#define BTRFS_MOUNT_NOSSD		(1 << 9)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -1056,12 +1115,14 @@ struct btrfs_root {
 #define BTRFS_INODE_READONLY		(1 << 2)
 #define BTRFS_INODE_NOCOMPRESS		(1 << 3)
 #define BTRFS_INODE_PREALLOC		(1 << 4)
-#define btrfs_clear_flag(inode, flag)	(BTRFS_I(inode)->flags &= \
-					 ~BTRFS_INODE_##flag)
-#define btrfs_set_flag(inode, flag)	(BTRFS_I(inode)->flags |= \
-					 BTRFS_INODE_##flag)
-#define btrfs_test_flag(inode, flag)	(BTRFS_I(inode)->flags & \
-					 BTRFS_INODE_##flag)
+#define BTRFS_INODE_SYNC		(1 << 5)
+#define BTRFS_INODE_IMMUTABLE		(1 << 6)
+#define BTRFS_INODE_APPEND		(1 << 7)
+#define BTRFS_INODE_NODUMP		(1 << 8)
+#define BTRFS_INODE_NOATIME		(1 << 9)
+#define BTRFS_INODE_DIRSYNC		(1 << 10)
+
+
 /* some macros to generate set/get funcs for the struct fields.  This
  * assumes there is a lefoo_to_cpu for every type, so lets make a simple
  * one for u8:
@@ -1317,24 +1378,67 @@ static inline u8 *btrfs_dev_extent_chunk_tree_uuid(struct btrfs_dev_extent *dev)
 	return (u8 *)((unsigned long)dev + ptr);
 }
 
-/* struct btrfs_extent_ref */
-BTRFS_SETGET_FUNCS(ref_root, struct btrfs_extent_ref, root, 64);
-BTRFS_SETGET_FUNCS(ref_generation, struct btrfs_extent_ref, generation, 64);
-BTRFS_SETGET_FUNCS(ref_objectid, struct btrfs_extent_ref, objectid, 64);
-BTRFS_SETGET_FUNCS(ref_num_refs, struct btrfs_extent_ref, num_refs, 32);
+BTRFS_SETGET_FUNCS(extent_refs, struct btrfs_extent_item, refs, 64);
+BTRFS_SETGET_FUNCS(extent_generation, struct btrfs_extent_item,
+		   generation, 64);
+BTRFS_SETGET_FUNCS(extent_flags, struct btrfs_extent_item, flags, 64);
 
-BTRFS_SETGET_STACK_FUNCS(stack_ref_root, struct btrfs_extent_ref, root, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_ref_generation, struct btrfs_extent_ref,
-			 generation, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_ref_objectid, struct btrfs_extent_ref,
-			 objectid, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_ref_num_refs, struct btrfs_extent_ref,
-			 num_refs, 32);
+BTRFS_SETGET_FUNCS(extent_refs_v0, struct btrfs_extent_item_v0, refs, 32);
 
-/* struct btrfs_extent_item */
-BTRFS_SETGET_FUNCS(extent_refs, struct btrfs_extent_item, refs, 32);
-BTRFS_SETGET_STACK_FUNCS(stack_extent_refs, struct btrfs_extent_item,
-			 refs, 32);
+
+BTRFS_SETGET_FUNCS(tree_block_level, struct btrfs_tree_block_info, level, 8);
+
+static inline void btrfs_tree_block_key(struct extent_buffer *eb,
+					struct btrfs_tree_block_info *item,
+					struct btrfs_disk_key *key)
+{
+	read_eb_member(eb, item, struct btrfs_tree_block_info, key, key);
+}
+
+static inline void btrfs_set_tree_block_key(struct extent_buffer *eb,
+					    struct btrfs_tree_block_info *item,
+					    struct btrfs_disk_key *key)
+{
+	write_eb_member(eb, item, struct btrfs_tree_block_info, key, key);
+}
+
+BTRFS_SETGET_FUNCS(extent_data_ref_root, struct btrfs_extent_data_ref,
+		   root, 64);
+BTRFS_SETGET_FUNCS(extent_data_ref_objectid, struct btrfs_extent_data_ref,
+		   objectid, 64);
+BTRFS_SETGET_FUNCS(extent_data_ref_offset, struct btrfs_extent_data_ref,
+		   offset, 64);
+BTRFS_SETGET_FUNCS(extent_data_ref_count, struct btrfs_extent_data_ref,
+		   count, 32);
+
+BTRFS_SETGET_FUNCS(shared_data_ref_count, struct btrfs_shared_data_ref,
+		   count, 32);
+
+BTRFS_SETGET_FUNCS(extent_inline_ref_type, struct btrfs_extent_inline_ref,
+		   type, 8);
+BTRFS_SETGET_FUNCS(extent_inline_ref_offset, struct btrfs_extent_inline_ref,
+		   offset, 64);
+
+static inline u32 btrfs_extent_inline_ref_size(int type)
+{
+	if (type == BTRFS_TREE_BLOCK_REF_KEY ||
+	    type == BTRFS_SHARED_BLOCK_REF_KEY)
+		return sizeof(struct btrfs_extent_inline_ref);
+	if (type == BTRFS_SHARED_DATA_REF_KEY)
+		return sizeof(struct btrfs_shared_data_ref) +
+		       sizeof(struct btrfs_extent_inline_ref);
+	if (type == BTRFS_EXTENT_DATA_REF_KEY)
+		return sizeof(struct btrfs_extent_data_ref) +
+		       offsetof(struct btrfs_extent_inline_ref, offset);
+	BUG();
+	return 0;
+}
+
+BTRFS_SETGET_FUNCS(ref_root_v0, struct btrfs_extent_ref_v0, root, 64);
+BTRFS_SETGET_FUNCS(ref_generation_v0, struct btrfs_extent_ref_v0,
+		   generation, 64);
+BTRFS_SETGET_FUNCS(ref_objectid_v0, struct btrfs_extent_ref_v0, objectid, 64);
+BTRFS_SETGET_FUNCS(ref_count_v0, struct btrfs_extent_ref_v0, count, 32);
 
 /* struct btrfs_node */
 BTRFS_SETGET_FUNCS(key_blockptr, struct btrfs_key_ptr, blockptr, 64);
@@ -1558,6 +1662,21 @@ static inline int btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag)
 	return (flags & flag) == flag;
 }
 
+static inline int btrfs_header_backref_rev(struct extent_buffer *eb)
+{
+	u64 flags = btrfs_header_flags(eb);
+	return flags >> BTRFS_BACKREF_REV_SHIFT;
+}
+
+static inline void btrfs_set_header_backref_rev(struct extent_buffer *eb,
+						int rev)
+{
+	u64 flags = btrfs_header_flags(eb);
+	flags &= ~BTRFS_BACKREF_REV_MASK;
+	flags |= (u64)rev << BTRFS_BACKREF_REV_SHIFT;
+	btrfs_set_header_flags(eb, flags);
+}
+
 static inline u8 *btrfs_header_fsid(struct extent_buffer *eb)
 {
 	unsigned long ptr = offsetof(struct btrfs_header, fsid);
@@ -1790,39 +1909,32 @@ int btrfs_update_pinned_extents(struct btrfs_root *root,
 int btrfs_drop_leaf_ref(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root, struct extent_buffer *leaf);
 int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root, u64 objectid, u64 bytenr);
+			  struct btrfs_root *root,
+			  u64 objectid, u64 offset, u64 bytenr);
 int btrfs_copy_pinned(struct btrfs_root *root, struct extent_io_tree *copy);
 struct btrfs_block_group_cache *btrfs_lookup_block_group(
 						 struct btrfs_fs_info *info,
 						 u64 bytenr);
+void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 u64 btrfs_find_block_group(struct btrfs_root *root,
 			   u64 search_start, u64 search_hint, int owner);
 struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
-					     struct btrfs_root *root,
-					     u32 blocksize, u64 parent,
-					     u64 root_objectid,
-					     u64 ref_generation,
-					     int level,
-					     u64 hint,
-					     u64 empty_size);
+					struct btrfs_root *root, u32 blocksize,
+					u64 parent, u64 root_objectid,
+					struct btrfs_disk_key *key, int level,
+					u64 hint, u64 empty_size);
 struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
 					    struct btrfs_root *root,
 					    u64 bytenr, u32 blocksize,
 					    int level);
-int btrfs_alloc_extent(struct btrfs_trans_handle *trans,
-		       struct btrfs_root *root,
-		       u64 num_bytes, u64 parent, u64 min_bytes,
-		       u64 root_objectid, u64 ref_generation,
-		       u64 owner, u64 empty_size, u64 hint_byte,
-		       u64 search_end, struct btrfs_key *ins, u64 data);
-int btrfs_alloc_reserved_extent(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root, u64 parent,
-				u64 root_objectid, u64 ref_generation,
-				u64 owner, struct btrfs_key *ins);
-int btrfs_alloc_logged_extent(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root, u64 parent,
-				u64 root_objectid, u64 ref_generation,
-				u64 owner, struct btrfs_key *ins);
+int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
+				     struct btrfs_root *root,
+				     u64 root_objectid, u64 owner,
+				     u64 offset, struct btrfs_key *ins);
+int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root,
+				   u64 root_objectid, u64 owner, u64 offset,
+				   struct btrfs_key *ins);
 int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
 				  struct btrfs_root *root,
 				  u64 num_bytes, u64 min_alloc_size,
@@ -1830,18 +1942,18 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
 				  u64 search_end, struct btrfs_key *ins,
 				  u64 data);
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *orig_buf, struct extent_buffer *buf,
-		  u32 *nr_extents);
-int btrfs_cache_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		    struct extent_buffer *buf, u32 nr_extents);
-int btrfs_update_ref(struct btrfs_trans_handle *trans,
-		     struct btrfs_root *root, struct extent_buffer *orig_buf,
-		     struct extent_buffer *buf, int start_slot, int nr);
+		  struct extent_buffer *buf, int full_backref);
+int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		  struct extent_buffer *buf, int full_backref);
+int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				u64 bytenr, u64 num_bytes, u64 flags,
+				int is_data);
 int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root,
 		      u64 bytenr, u64 num_bytes, u64 parent,
-		      u64 root_objectid, u64 ref_generation,
-		      u64 owner_objectid, int pin);
+		      u64 root_objectid, u64 owner, u64 offset);
+
 int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
@@ -1849,13 +1961,8 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 u64 bytenr, u64 num_bytes, u64 parent,
-			 u64 root_objectid, u64 ref_generation,
-			 u64 owner_objectid);
-int btrfs_update_extent_ref(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root, u64 bytenr, u64 num_bytes,
-			    u64 orig_parent, u64 parent,
-			    u64 root_objectid, u64 ref_generation,
-			    u64 owner_objectid);
+			 u64 root_objectid, u64 owner, u64 offset);
+
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 				    struct btrfs_root *root);
 int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr);
@@ -1867,16 +1974,9 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 			   u64 size);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 group_start);
-int btrfs_relocate_block_group(struct btrfs_root *root, u64 group_start);
-int btrfs_free_reloc_root(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root);
-int btrfs_drop_dead_reloc_roots(struct btrfs_root *root);
-int btrfs_reloc_tree_cache_ref(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root,
-			       struct extent_buffer *buf, u64 orig_start);
-int btrfs_add_dead_reloc_root(struct btrfs_root *root);
-int btrfs_cleanup_reloc_trees(struct btrfs_root *root);
-int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len);
+int btrfs_prepare_block_group_relocation(struct btrfs_root *root,
+				struct btrfs_block_group_cache *group);
+
 u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags);
 void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
@@ -1891,13 +1991,12 @@ void btrfs_delalloc_reserve_space(struct btrfs_root *root, struct inode *inode,
 void btrfs_delalloc_free_space(struct btrfs_root *root, struct inode *inode,
 			      u64 bytes);
 /* ctree.c */
+int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
+		     int level, int *slot);
+int btrfs_comp_cpu_keys(struct btrfs_key *k1, struct btrfs_key *k2);
 int btrfs_previous_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid,
 			int type);
-int btrfs_merge_path(struct btrfs_trans_handle *trans,
-		     struct btrfs_root *root,
-		     struct btrfs_key *node_keys,
-		     u64 *nodes, int lowest_level);
 int btrfs_set_item_key_safe(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root, struct btrfs_path *path,
 			    struct btrfs_key *new_key);
@@ -1918,6 +2017,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root,
 		      struct extent_buffer *buf,
 		      struct extent_buffer **cow_ret, u64 new_root_objectid);
+int btrfs_block_can_be_shared(struct btrfs_root *root,
+			      struct extent_buffer *buf);
 int btrfs_extend_item(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, struct btrfs_path *path, u32 data_size);
 int btrfs_truncate_item(struct btrfs_trans_handle *trans,
@@ -1944,9 +2045,6 @@ void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
 
 int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		   struct btrfs_path *path, int slot, int nr);
-int btrfs_del_leaf(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root,
-			    struct btrfs_path *path, u64 bytenr);
 static inline int btrfs_del_item(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root,
 				 struct btrfs_path *path)
@@ -2005,8 +2103,9 @@ int btrfs_find_last_root(struct btrfs_root *root, u64 objectid, struct
 			 btrfs_root_item *item, struct btrfs_key *key);
 int btrfs_search_root(struct btrfs_root *root, u64 search_start,
 		      u64 *found_objectid);
-int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid,
-			  struct btrfs_root *latest_root);
+int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid);
+int btrfs_set_root_node(struct btrfs_root_item *item,
+			struct extent_buffer *node);
 /* dir-item.c */
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root, const char *name,
@@ -2139,7 +2238,6 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 int btrfs_readpage(struct file *file, struct page *page);
 void btrfs_delete_inode(struct inode *inode);
 void btrfs_put_inode(struct inode *inode);
-void btrfs_read_locked_inode(struct inode *inode);
 int btrfs_write_inode(struct inode *inode, int wait);
 void btrfs_dirty_inode(struct inode *inode);
 struct inode *btrfs_alloc_inode(struct super_block *sb);
@@ -2147,12 +2245,8 @@ void btrfs_destroy_inode(struct inode *inode);
 int btrfs_init_cachep(void);
 void btrfs_destroy_cachep(void);
 long btrfs_ioctl_trans_end(struct file *file);
-struct inode *btrfs_ilookup(struct super_block *s, u64 objectid,
-			    struct btrfs_root *root, int wait);
-struct inode *btrfs_iget_locked(struct super_block *s, u64 objectid,
-				struct btrfs_root *root);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
-			 struct btrfs_root *root, int *is_new);
+			 struct btrfs_root *root);
 int btrfs_commit_write(struct file *file, struct page *page,
 		       unsigned from, unsigned to);
 struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
@@ -2168,6 +2262,8 @@ int btrfs_cont_expand(struct inode *inode, loff_t size);
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+void btrfs_update_iflags(struct inode *inode);
+void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);
 
 /* file.c */
 int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync);
@@ -2205,8 +2301,20 @@ int btrfs_parse_options(struct btrfs_root *root, char *options);
 int btrfs_sync_fs(struct super_block *sb, int wait);
 
 /* acl.c */
+#ifdef CONFIG_FS_POSIX_ACL
 int btrfs_check_acl(struct inode *inode, int mask);
+#else
+#define btrfs_check_acl NULL
+#endif
 int btrfs_init_acl(struct inode *inode, struct inode *dir);
 int btrfs_acl_chmod(struct inode *inode);
 
+/* relocation.c */
+int btrfs_relocate_block_group(struct btrfs_root *root, u64 group_start);
+int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
+			  struct btrfs_root *root);
+int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root);
+int btrfs_recover_relocation(struct btrfs_root *root);
+int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len);
 #endif
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index d6c01c096a40..84e6781413b1 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -29,27 +29,87 @@
  * add extents in the middle of btrfs_search_slot, and it allows
  * us to buffer up frequently modified backrefs in an rb tree instead
  * of hammering updates on the extent allocation tree.
- *
- * Right now this code is only used for reference counted trees, but
- * the long term goal is to get rid of the similar code for delayed
- * extent tree modifications.
  */
 
 /*
- * entries in the rb tree are ordered by the byte number of the extent
- * and by the byte number of the parent block.
+ * compare two delayed tree backrefs with same bytenr and type
  */
-static int comp_entry(struct btrfs_delayed_ref_node *ref,
-		      u64 bytenr, u64 parent)
+static int comp_tree_refs(struct btrfs_delayed_tree_ref *ref2,
+			  struct btrfs_delayed_tree_ref *ref1)
 {
-	if (bytenr < ref->bytenr)
+	if (ref1->node.type == BTRFS_TREE_BLOCK_REF_KEY) {
+		if (ref1->root < ref2->root)
+			return -1;
+		if (ref1->root > ref2->root)
+			return 1;
+	} else {
+		if (ref1->parent < ref2->parent)
+			return -1;
+		if (ref1->parent > ref2->parent)
+			return 1;
+	}
+	return 0;
+}
+
+/*
+ * compare two delayed data backrefs with same bytenr and type
+ */
+static int comp_data_refs(struct btrfs_delayed_data_ref *ref2,
+			  struct btrfs_delayed_data_ref *ref1)
+{
+	if (ref1->node.type == BTRFS_EXTENT_DATA_REF_KEY) {
+		if (ref1->root < ref2->root)
+			return -1;
+		if (ref1->root > ref2->root)
+			return 1;
+		if (ref1->objectid < ref2->objectid)
+			return -1;
+		if (ref1->objectid > ref2->objectid)
+			return 1;
+		if (ref1->offset < ref2->offset)
+			return -1;
+		if (ref1->offset > ref2->offset)
+			return 1;
+	} else {
+		if (ref1->parent < ref2->parent)
+			return -1;
+		if (ref1->parent > ref2->parent)
+			return 1;
+	}
+	return 0;
+}
+
+/*
+ * entries in the rb tree are ordered by the byte number of the extent,
+ * type of the delayed backrefs and content of delayed backrefs.
+ */
+static int comp_entry(struct btrfs_delayed_ref_node *ref2,
+		      struct btrfs_delayed_ref_node *ref1)
+{
+	if (ref1->bytenr < ref2->bytenr)
 		return -1;
-	if (bytenr > ref->bytenr)
+	if (ref1->bytenr > ref2->bytenr)
 		return 1;
-	if (parent < ref->parent)
+	if (ref1->is_head && ref2->is_head)
+		return 0;
+	if (ref2->is_head)
 		return -1;
-	if (parent > ref->parent)
+	if (ref1->is_head)
 		return 1;
+	if (ref1->type < ref2->type)
+		return -1;
+	if (ref1->type > ref2->type)
+		return 1;
+	if (ref1->type == BTRFS_TREE_BLOCK_REF_KEY ||
+	    ref1->type == BTRFS_SHARED_BLOCK_REF_KEY) {
+		return comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref2),
+				      btrfs_delayed_node_to_tree_ref(ref1));
+	} else if (ref1->type == BTRFS_EXTENT_DATA_REF_KEY ||
+		   ref1->type == BTRFS_SHARED_DATA_REF_KEY) {
+		return comp_data_refs(btrfs_delayed_node_to_data_ref(ref2),
+				      btrfs_delayed_node_to_data_ref(ref1));
+	}
+	BUG();
 	return 0;
 }
 
@@ -59,20 +119,21 @@ static int comp_entry(struct btrfs_delayed_ref_node *ref,
  * inserted.
  */
 static struct btrfs_delayed_ref_node *tree_insert(struct rb_root *root,
-						  u64 bytenr, u64 parent,
 						  struct rb_node *node)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent_node = NULL;
 	struct btrfs_delayed_ref_node *entry;
+	struct btrfs_delayed_ref_node *ins;
 	int cmp;
 
+	ins = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
 	while (*p) {
 		parent_node = *p;
 		entry = rb_entry(parent_node, struct btrfs_delayed_ref_node,
 				 rb_node);
 
-		cmp = comp_entry(entry, bytenr, parent);
+		cmp = comp_entry(entry, ins);
 		if (cmp < 0)
 			p = &(*p)->rb_left;
 		else if (cmp > 0)
@@ -81,18 +142,17 @@ static struct btrfs_delayed_ref_node *tree_insert(struct rb_root *root,
 			return entry;
 	}
 
-	entry = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
 	rb_link_node(node, parent_node, p);
 	rb_insert_color(node, root);
 	return NULL;
 }
 
 /*
- * find an entry based on (bytenr,parent).  This returns the delayed
- * ref if it was able to find one, or NULL if nothing was in that spot
+ * find an head entry based on bytenr. This returns the delayed ref
+ * head if it was able to find one, or NULL if nothing was in that spot
  */
-static struct btrfs_delayed_ref_node *tree_search(struct rb_root *root,
-				  u64 bytenr, u64 parent,
+static struct btrfs_delayed_ref_node *find_ref_head(struct rb_root *root,
+				  u64 bytenr,
 				  struct btrfs_delayed_ref_node **last)
 {
 	struct rb_node *n = root->rb_node;
@@ -105,7 +165,15 @@ static struct btrfs_delayed_ref_node *tree_search(struct rb_root *root,
 		if (last)
 			*last = entry;
 
-		cmp = comp_entry(entry, bytenr, parent);
+		if (bytenr < entry->bytenr)
+			cmp = -1;
+		else if (bytenr > entry->bytenr)
+			cmp = 1;
+		else if (!btrfs_delayed_ref_is_head(entry))
+			cmp = 1;
+		else
+			cmp = 0;
+
 		if (cmp < 0)
 			n = n->rb_left;
 		else if (cmp > 0)
@@ -154,7 +222,7 @@ int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
 		node = rb_first(&delayed_refs->root);
 	} else {
 		ref = NULL;
-		tree_search(&delayed_refs->root, start, (u64)-1, &ref);
+		find_ref_head(&delayed_refs->root, start, &ref);
 		if (ref) {
 			struct btrfs_delayed_ref_node *tmp;
 
@@ -234,7 +302,7 @@ int btrfs_delayed_ref_pending(struct btrfs_trans_handle *trans, u64 bytenr)
 	delayed_refs = &trans->transaction->delayed_refs;
 	spin_lock(&delayed_refs->lock);
 
-	ref = tree_search(&delayed_refs->root, bytenr, (u64)-1, NULL);
+	ref = find_ref_head(&delayed_refs->root, bytenr, NULL);
 	if (ref) {
 		prev_node = rb_prev(&ref->rb_node);
 		if (!prev_node)
@@ -250,25 +318,28 @@ out:
 }
 
 /*
- * helper function to lookup reference count
+ * helper function to lookup reference count and flags of extent.
  *
  * the head node for delayed ref is used to store the sum of all the
- * reference count modifications queued up in the rbtree.  This way you
- * can check to see what the reference count would be if all of the
- * delayed refs are processed.
+ * reference count modifications queued up in the rbtree. the head
+ * node may also store the extent flags to set. This way you can check
+ * to see what the reference count and extent flags would be if all of
+ * the delayed refs are not processed.
  */
-int btrfs_lookup_extent_ref(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root, u64 bytenr,
-			    u64 num_bytes, u32 *refs)
+int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root, u64 bytenr,
+			     u64 num_bytes, u64 *refs, u64 *flags)
 {
 	struct btrfs_delayed_ref_node *ref;
 	struct btrfs_delayed_ref_head *head;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_path *path;
-	struct extent_buffer *leaf;
 	struct btrfs_extent_item *ei;
+	struct extent_buffer *leaf;
 	struct btrfs_key key;
-	u32 num_refs;
+	u32 item_size;
+	u64 num_refs;
+	u64 extent_flags;
 	int ret;
 
 	path = btrfs_alloc_path();
@@ -287,37 +358,60 @@ again:
 
 	if (ret == 0) {
 		leaf = path->nodes[0];
-		ei = btrfs_item_ptr(leaf, path->slots[0],
-				    struct btrfs_extent_item);
-		num_refs = btrfs_extent_refs(leaf, ei);
+		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+		if (item_size >= sizeof(*ei)) {
+			ei = btrfs_item_ptr(leaf, path->slots[0],
+					    struct btrfs_extent_item);
+			num_refs = btrfs_extent_refs(leaf, ei);
+			extent_flags = btrfs_extent_flags(leaf, ei);
+		} else {
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+			struct btrfs_extent_item_v0 *ei0;
+			BUG_ON(item_size != sizeof(*ei0));
+			ei0 = btrfs_item_ptr(leaf, path->slots[0],
+					     struct btrfs_extent_item_v0);
+			num_refs = btrfs_extent_refs_v0(leaf, ei0);
+			/* FIXME: this isn't correct for data */
+			extent_flags = BTRFS_BLOCK_FLAG_FULL_BACKREF;
+#else
+			BUG();
+#endif
+		}
+		BUG_ON(num_refs == 0);
 	} else {
 		num_refs = 0;
+		extent_flags = 0;
 		ret = 0;
 	}
 
 	spin_lock(&delayed_refs->lock);
-	ref = tree_search(&delayed_refs->root, bytenr, (u64)-1, NULL);
+	ref = find_ref_head(&delayed_refs->root, bytenr, NULL);
 	if (ref) {
 		head = btrfs_delayed_node_to_head(ref);
-		if (mutex_trylock(&head->mutex)) {
-			num_refs += ref->ref_mod;
+		if (!mutex_trylock(&head->mutex)) {
+			atomic_inc(&ref->refs);
+			spin_unlock(&delayed_refs->lock);
+
+			btrfs_release_path(root->fs_info->extent_root, path);
+
+			mutex_lock(&head->mutex);
 			mutex_unlock(&head->mutex);
-			*refs = num_refs;
-			goto out;
+			btrfs_put_delayed_ref(ref);
+			goto again;
 		}
+		if (head->extent_op && head->extent_op->update_flags)
+			extent_flags |= head->extent_op->flags_to_set;
+		else
+			BUG_ON(num_refs == 0);
 
-		atomic_inc(&ref->refs);
-		spin_unlock(&delayed_refs->lock);
-
-		btrfs_release_path(root->fs_info->extent_root, path);
-
-		mutex_lock(&head->mutex);
+		num_refs += ref->ref_mod;
 		mutex_unlock(&head->mutex);
-		btrfs_put_delayed_ref(ref);
-		goto again;
-	} else {
-		*refs = num_refs;
 	}
+	WARN_ON(num_refs == 0);
+	if (refs)
+		*refs = num_refs;
+	if (flags)
+		*flags = extent_flags;
 out:
 	spin_unlock(&delayed_refs->lock);
 	btrfs_free_path(path);
@@ -338,16 +432,7 @@ update_existing_ref(struct btrfs_trans_handle *trans,
 		    struct btrfs_delayed_ref_node *existing,
 		    struct btrfs_delayed_ref_node *update)
 {
-	struct btrfs_delayed_ref *existing_ref;
-	struct btrfs_delayed_ref *ref;
-
-	existing_ref = btrfs_delayed_node_to_ref(existing);
-	ref = btrfs_delayed_node_to_ref(update);
-
-	if (ref->pin)
-		existing_ref->pin = 1;
-
-	if (ref->action != existing_ref->action) {
+	if (update->action != existing->action) {
 		/*
 		 * this is effectively undoing either an add or a
 		 * drop.  We decrement the ref_mod, and if it goes
@@ -363,20 +448,13 @@ update_existing_ref(struct btrfs_trans_handle *trans,
 			delayed_refs->num_entries--;
 			if (trans->delayed_ref_updates)
 				trans->delayed_ref_updates--;
+		} else {
+			WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY ||
+				existing->type == BTRFS_SHARED_BLOCK_REF_KEY);
 		}
 	} else {
-		if (existing_ref->action == BTRFS_ADD_DELAYED_REF) {
-			/* if we're adding refs, make sure all the
-			 * details match up.  The extent could
-			 * have been totally freed and reallocated
-			 * by a different owner before the delayed
-			 * ref entries were removed.
-			 */
-			existing_ref->owner_objectid = ref->owner_objectid;
-			existing_ref->generation = ref->generation;
-			existing_ref->root = ref->root;
-			existing->num_bytes = update->num_bytes;
-		}
+		WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY ||
+			existing->type == BTRFS_SHARED_BLOCK_REF_KEY);
 		/*
 		 * the action on the existing ref matches
 		 * the action on the ref we're trying to add.
@@ -401,6 +479,7 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
 
 	existing_ref = btrfs_delayed_node_to_head(existing);
 	ref = btrfs_delayed_node_to_head(update);
+	BUG_ON(existing_ref->is_data != ref->is_data);
 
 	if (ref->must_insert_reserved) {
 		/* if the extent was freed and then
@@ -420,6 +499,24 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
 
 	}
 
+	if (ref->extent_op) {
+		if (!existing_ref->extent_op) {
+			existing_ref->extent_op = ref->extent_op;
+		} else {
+			if (ref->extent_op->update_key) {
+				memcpy(&existing_ref->extent_op->key,
+				       &ref->extent_op->key,
+				       sizeof(ref->extent_op->key));
+				existing_ref->extent_op->update_key = 1;
+			}
+			if (ref->extent_op->update_flags) {
+				existing_ref->extent_op->flags_to_set |=
+					ref->extent_op->flags_to_set;
+				existing_ref->extent_op->update_flags = 1;
+			}
+			kfree(ref->extent_op);
+		}
+	}
 	/*
 	 * update the reference mod on the head to reflect this new operation
 	 */
@@ -427,19 +524,16 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
 }
 
 /*
- * helper function to actually insert a delayed ref into the rbtree.
+ * helper function to actually insert a head node into the rbtree.
  * this does all the dirty work in terms of maintaining the correct
- * overall modification count in the head node and properly dealing
- * with updating existing nodes as new modifications are queued.
+ * overall modification count.
  */
-static noinline int __btrfs_add_delayed_ref(struct btrfs_trans_handle *trans,
-			  struct btrfs_delayed_ref_node *ref,
-			  u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root,
-			  u64 ref_generation, u64 owner_objectid, int action,
-			  int pin)
+static noinline int add_delayed_ref_head(struct btrfs_trans_handle *trans,
+					struct btrfs_delayed_ref_node *ref,
+					u64 bytenr, u64 num_bytes,
+					int action, int is_data)
 {
 	struct btrfs_delayed_ref_node *existing;
-	struct btrfs_delayed_ref *full_ref;
 	struct btrfs_delayed_ref_head *head_ref = NULL;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int count_mod = 1;
@@ -449,12 +543,10 @@ static noinline int __btrfs_add_delayed_ref(struct btrfs_trans_handle *trans,
 	 * the head node stores the sum of all the mods, so dropping a ref
 	 * should drop the sum in the head node by one.
 	 */
-	if (parent == (u64)-1) {
-		if (action == BTRFS_DROP_DELAYED_REF)
-			count_mod = -1;
-		else if (action == BTRFS_UPDATE_DELAYED_HEAD)
-			count_mod = 0;
-	}
+	if (action == BTRFS_UPDATE_DELAYED_HEAD)
+		count_mod = 0;
+	else if (action == BTRFS_DROP_DELAYED_REF)
+		count_mod = -1;
 
 	/*
 	 * BTRFS_ADD_DELAYED_EXTENT means that we need to update
@@ -467,57 +559,42 @@ static noinline int __btrfs_add_delayed_ref(struct btrfs_trans_handle *trans,
 	 * Once we record must_insert_reserved, switch the action to
 	 * BTRFS_ADD_DELAYED_REF because other special casing is not required.
 	 */
-	if (action == BTRFS_ADD_DELAYED_EXTENT) {
+	if (action == BTRFS_ADD_DELAYED_EXTENT)
 		must_insert_reserved = 1;
-		action = BTRFS_ADD_DELAYED_REF;
-	} else {
+	else
 		must_insert_reserved = 0;
-	}
-
 
 	delayed_refs = &trans->transaction->delayed_refs;
 
 	/* first set the basic ref node struct up */
 	atomic_set(&ref->refs, 1);
 	ref->bytenr = bytenr;
-	ref->parent = parent;
-	ref->ref_mod = count_mod;
-	ref->in_tree = 1;
 	ref->num_bytes = num_bytes;
+	ref->ref_mod = count_mod;
+	ref->type  = 0;
+	ref->action  = 0;
+	ref->is_head = 1;
+	ref->in_tree = 1;
 
-	if (btrfs_delayed_ref_is_head(ref)) {
-		head_ref = btrfs_delayed_node_to_head(ref);
-		head_ref->must_insert_reserved = must_insert_reserved;
-		INIT_LIST_HEAD(&head_ref->cluster);
-		mutex_init(&head_ref->mutex);
-	} else {
-		full_ref = btrfs_delayed_node_to_ref(ref);
-		full_ref->root = ref_root;
-		full_ref->generation = ref_generation;
-		full_ref->owner_objectid = owner_objectid;
-		full_ref->pin = pin;
-		full_ref->action = action;
-	}
+	head_ref = btrfs_delayed_node_to_head(ref);
+	head_ref->must_insert_reserved = must_insert_reserved;
+	head_ref->is_data = is_data;
 
-	existing = tree_insert(&delayed_refs->root, bytenr,
-			       parent, &ref->rb_node);
+	INIT_LIST_HEAD(&head_ref->cluster);
+	mutex_init(&head_ref->mutex);
+
+	existing = tree_insert(&delayed_refs->root, &ref->rb_node);
 
 	if (existing) {
-		if (btrfs_delayed_ref_is_head(ref))
-			update_existing_head_ref(existing, ref);
-		else
-			update_existing_ref(trans, delayed_refs, existing, ref);
-
+		update_existing_head_ref(existing, ref);
 		/*
 		 * we've updated the existing ref, free the newly
 		 * allocated ref
 		 */
 		kfree(ref);
 	} else {
-		if (btrfs_delayed_ref_is_head(ref)) {
-			delayed_refs->num_heads++;
-			delayed_refs->num_heads_ready++;
-		}
+		delayed_refs->num_heads++;
+		delayed_refs->num_heads_ready++;
 		delayed_refs->num_entries++;
 		trans->delayed_ref_updates++;
 	}
@@ -525,37 +602,139 @@ static noinline int __btrfs_add_delayed_ref(struct btrfs_trans_handle *trans,
 }
 
 /*
- * add a delayed ref to the tree.  This does all of the accounting required
+ * helper to insert a delayed tree ref into the rbtree.
+ */
+static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans,
+					 struct btrfs_delayed_ref_node *ref,
+					 u64 bytenr, u64 num_bytes, u64 parent,
+					 u64 ref_root, int level, int action)
+{
+	struct btrfs_delayed_ref_node *existing;
+	struct btrfs_delayed_tree_ref *full_ref;
+	struct btrfs_delayed_ref_root *delayed_refs;
+
+	if (action == BTRFS_ADD_DELAYED_EXTENT)
+		action = BTRFS_ADD_DELAYED_REF;
+
+	delayed_refs = &trans->transaction->delayed_refs;
+
+	/* first set the basic ref node struct up */
+	atomic_set(&ref->refs, 1);
+	ref->bytenr = bytenr;
+	ref->num_bytes = num_bytes;
+	ref->ref_mod = 1;
+	ref->action = action;
+	ref->is_head = 0;
+	ref->in_tree = 1;
+
+	full_ref = btrfs_delayed_node_to_tree_ref(ref);
+	if (parent) {
+		full_ref->parent = parent;
+		ref->type = BTRFS_SHARED_BLOCK_REF_KEY;
+	} else {
+		full_ref->root = ref_root;
+		ref->type = BTRFS_TREE_BLOCK_REF_KEY;
+	}
+	full_ref->level = level;
+
+	existing = tree_insert(&delayed_refs->root, &ref->rb_node);
+
+	if (existing) {
+		update_existing_ref(trans, delayed_refs, existing, ref);
+		/*
+		 * we've updated the existing ref, free the newly
+		 * allocated ref
+		 */
+		kfree(ref);
+	} else {
+		delayed_refs->num_entries++;
+		trans->delayed_ref_updates++;
+	}
+	return 0;
+}
+
+/*
+ * helper to insert a delayed data ref into the rbtree.
+ */
+static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans,
+					 struct btrfs_delayed_ref_node *ref,
+					 u64 bytenr, u64 num_bytes, u64 parent,
+					 u64 ref_root, u64 owner, u64 offset,
+					 int action)
+{
+	struct btrfs_delayed_ref_node *existing;
+	struct btrfs_delayed_data_ref *full_ref;
+	struct btrfs_delayed_ref_root *delayed_refs;
+
+	if (action == BTRFS_ADD_DELAYED_EXTENT)
+		action = BTRFS_ADD_DELAYED_REF;
+
+	delayed_refs = &trans->transaction->delayed_refs;
+
+	/* first set the basic ref node struct up */
+	atomic_set(&ref->refs, 1);
+	ref->bytenr = bytenr;
+	ref->num_bytes = num_bytes;
+	ref->ref_mod = 1;
+	ref->action = action;
+	ref->is_head = 0;
+	ref->in_tree = 1;
+
+	full_ref = btrfs_delayed_node_to_data_ref(ref);
+	if (parent) {
+		full_ref->parent = parent;
+		ref->type = BTRFS_SHARED_DATA_REF_KEY;
+	} else {
+		full_ref->root = ref_root;
+		ref->type = BTRFS_EXTENT_DATA_REF_KEY;
+	}
+	full_ref->objectid = owner;
+	full_ref->offset = offset;
+
+	existing = tree_insert(&delayed_refs->root, &ref->rb_node);
+
+	if (existing) {
+		update_existing_ref(trans, delayed_refs, existing, ref);
+		/*
+		 * we've updated the existing ref, free the newly
+		 * allocated ref
+		 */
+		kfree(ref);
+	} else {
+		delayed_refs->num_entries++;
+		trans->delayed_ref_updates++;
+	}
+	return 0;
+}
+
+/*
+ * add a delayed tree ref.  This does all of the accounting required
  * to make sure the delayed ref is eventually processed before this
  * transaction commits.
  */
-int btrfs_add_delayed_ref(struct btrfs_trans_handle *trans,
-			  u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root,
-			  u64 ref_generation, u64 owner_objectid, int action,
-			  int pin)
+int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
+			       u64 bytenr, u64 num_bytes, u64 parent,
+			       u64 ref_root,  int level, int action,
+			       struct btrfs_delayed_extent_op *extent_op)
 {
-	struct btrfs_delayed_ref *ref;
+	struct btrfs_delayed_tree_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int ret;
 
+	BUG_ON(extent_op && extent_op->is_data);
 	ref = kmalloc(sizeof(*ref), GFP_NOFS);
 	if (!ref)
 		return -ENOMEM;
 
-	/*
-	 * the parent = 0 case comes from cases where we don't actually
-	 * know the parent yet.  It will get updated later via a add/drop
-	 * pair.
-	 */
-	if (parent == 0)
-		parent = bytenr;
-
 	head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
 	if (!head_ref) {
 		kfree(ref);
 		return -ENOMEM;
 	}
+
+	head_ref->extent_op = extent_op;
+
 	delayed_refs = &trans->transaction->delayed_refs;
 	spin_lock(&delayed_refs->lock);
 
@@ -563,18 +742,88 @@ int btrfs_add_delayed_ref(struct btrfs_trans_handle *trans,
 	 * insert both the head node and the new ref without dropping
 	 * the spin lock
 	 */
-	ret = __btrfs_add_delayed_ref(trans, &head_ref->node, bytenr, num_bytes,
-				      (u64)-1, 0, 0, 0, action, pin);
+	ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes,
+				   action, 0);
 	BUG_ON(ret);
 
-	ret = __btrfs_add_delayed_ref(trans, &ref->node, bytenr, num_bytes,
-				      parent, ref_root, ref_generation,
-				      owner_objectid, action, pin);
+	ret = add_delayed_tree_ref(trans, &ref->node, bytenr, num_bytes,
+				   parent, ref_root, level, action);
 	BUG_ON(ret);
 	spin_unlock(&delayed_refs->lock);
 	return 0;
 }
 
+/*
+ * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
+ */
+int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
+			       u64 bytenr, u64 num_bytes,
+			       u64 parent, u64 ref_root,
+			       u64 owner, u64 offset, int action,
+			       struct btrfs_delayed_extent_op *extent_op)
+{
+	struct btrfs_delayed_data_ref *ref;
+	struct btrfs_delayed_ref_head *head_ref;
+	struct btrfs_delayed_ref_root *delayed_refs;
+	int ret;
+
+	BUG_ON(extent_op && !extent_op->is_data);
+	ref = kmalloc(sizeof(*ref), GFP_NOFS);
+	if (!ref)
+		return -ENOMEM;
+
+	head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
+	if (!head_ref) {
+		kfree(ref);
+		return -ENOMEM;
+	}
+
+	head_ref->extent_op = extent_op;
+
+	delayed_refs = &trans->transaction->delayed_refs;
+	spin_lock(&delayed_refs->lock);
+
+	/*
+	 * insert both the head node and the new ref without dropping
+	 * the spin lock
+	 */
+	ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes,
+				   action, 1);
+	BUG_ON(ret);
+
+	ret = add_delayed_data_ref(trans, &ref->node, bytenr, num_bytes,
+				   parent, ref_root, owner, offset, action);
+	BUG_ON(ret);
+	spin_unlock(&delayed_refs->lock);
+	return 0;
+}
+
+int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
+				u64 bytenr, u64 num_bytes,
+				struct btrfs_delayed_extent_op *extent_op)
+{
+	struct btrfs_delayed_ref_head *head_ref;
+	struct btrfs_delayed_ref_root *delayed_refs;
+	int ret;
+
+	head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
+	if (!head_ref)
+		return -ENOMEM;
+
+	head_ref->extent_op = extent_op;
+
+	delayed_refs = &trans->transaction->delayed_refs;
+	spin_lock(&delayed_refs->lock);
+
+	ret = add_delayed_ref_head(trans, &head_ref->node, bytenr,
+				   num_bytes, BTRFS_UPDATE_DELAYED_HEAD,
+				   extent_op->is_data);
+	BUG_ON(ret);
+
+	spin_unlock(&delayed_refs->lock);
+	return 0;
+}
+
 /*
  * this does a simple search for the head node for a given extent.
  * It must be called with the delayed ref spinlock held, and it returns
@@ -587,7 +836,7 @@ btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
 	struct btrfs_delayed_ref_root *delayed_refs;
 
 	delayed_refs = &trans->transaction->delayed_refs;
-	ref = tree_search(&delayed_refs->root, bytenr, (u64)-1, NULL);
+	ref = find_ref_head(&delayed_refs->root, bytenr, NULL);
 	if (ref)
 		return btrfs_delayed_node_to_head(ref);
 	return NULL;
@@ -603,6 +852,7 @@ btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
  *
  * It is the same as doing a ref add and delete in two separate calls.
  */
+#if 0
 int btrfs_update_delayed_ref(struct btrfs_trans_handle *trans,
 			  u64 bytenr, u64 num_bytes, u64 orig_parent,
 			  u64 parent, u64 orig_ref_root, u64 ref_root,
@@ -666,3 +916,4 @@ int btrfs_update_delayed_ref(struct btrfs_trans_handle *trans,
 	spin_unlock(&delayed_refs->lock);
 	return 0;
 }
+#endif
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 3bec2ff0b15c..f6fc67ddad36 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -30,9 +30,6 @@ struct btrfs_delayed_ref_node {
 	/* the starting bytenr of the extent */
 	u64 bytenr;
 
-	/* the parent our backref will point to */
-	u64 parent;
-
 	/* the size of the extent */
 	u64 num_bytes;
 
@@ -50,10 +47,21 @@ struct btrfs_delayed_ref_node {
 	 */
 	int ref_mod;
 
+	unsigned int action:8;
+	unsigned int type:8;
 	/* is this node still in the rbtree? */
+	unsigned int is_head:1;
 	unsigned int in_tree:1;
 };
 
+struct btrfs_delayed_extent_op {
+	struct btrfs_disk_key key;
+	u64 flags_to_set;
+	unsigned int update_key:1;
+	unsigned int update_flags:1;
+	unsigned int is_data:1;
+};
+
 /*
  * the head refs are used to hold a lock on a given extent, which allows us
  * to make sure that only one process is running the delayed refs
@@ -71,6 +79,7 @@ struct btrfs_delayed_ref_head {
 
 	struct list_head cluster;
 
+	struct btrfs_delayed_extent_op *extent_op;
 	/*
 	 * when a new extent is allocated, it is just reserved in memory
 	 * The actual extent isn't inserted into the extent allocation tree
@@ -84,27 +93,26 @@ struct btrfs_delayed_ref_head {
 	 * the free has happened.
 	 */
 	unsigned int must_insert_reserved:1;
+	unsigned int is_data:1;
 };
 
-struct btrfs_delayed_ref {
+struct btrfs_delayed_tree_ref {
 	struct btrfs_delayed_ref_node node;
+	union {
+		u64 root;
+		u64 parent;
+	};
+	int level;
+};
 
-	/* the root objectid our ref will point to */
-	u64 root;
-
-	/* the generation for the backref */
-	u64 generation;
-
-	/* owner_objectid of the backref  */
-	u64 owner_objectid;
-
-	/* operation done by this entry in the rbtree */
-	u8 action;
-
-	/* if pin == 1, when the extent is freed it will be pinned until
-	 * transaction commit
-	 */
-	unsigned int pin:1;
+struct btrfs_delayed_data_ref {
+	struct btrfs_delayed_ref_node node;
+	union {
+		u64 root;
+		u64 parent;
+	};
+	u64 objectid;
+	u64 offset;
 };
 
 struct btrfs_delayed_ref_root {
@@ -143,17 +151,25 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
 	}
 }
 
-int btrfs_add_delayed_ref(struct btrfs_trans_handle *trans,
-			  u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root,
-			  u64 ref_generation, u64 owner_objectid, int action,
-			  int pin);
+int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
+			       u64 bytenr, u64 num_bytes, u64 parent,
+			       u64 ref_root, int level, int action,
+			       struct btrfs_delayed_extent_op *extent_op);
+int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
+			       u64 bytenr, u64 num_bytes,
+			       u64 parent, u64 ref_root,
+			       u64 owner, u64 offset, int action,
+			       struct btrfs_delayed_extent_op *extent_op);
+int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
+				u64 bytenr, u64 num_bytes,
+				struct btrfs_delayed_extent_op *extent_op);
 
 struct btrfs_delayed_ref_head *
 btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr);
 int btrfs_delayed_ref_pending(struct btrfs_trans_handle *trans, u64 bytenr);
-int btrfs_lookup_extent_ref(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root, u64 bytenr,
-			    u64 num_bytes, u32 *refs);
+int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root, u64 bytenr,
+			     u64 num_bytes, u64 *refs, u64 *flags);
 int btrfs_update_delayed_ref(struct btrfs_trans_handle *trans,
 			  u64 bytenr, u64 num_bytes, u64 orig_parent,
 			  u64 parent, u64 orig_ref_root, u64 ref_root,
@@ -169,18 +185,24 @@ int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
  */
 static int btrfs_delayed_ref_is_head(struct btrfs_delayed_ref_node *node)
 {
-	return node->parent == (u64)-1;
+	return node->is_head;
 }
 
 /*
  * helper functions to cast a node into its container
  */
-static inline struct btrfs_delayed_ref *
-btrfs_delayed_node_to_ref(struct btrfs_delayed_ref_node *node)
+static inline struct btrfs_delayed_tree_ref *
+btrfs_delayed_node_to_tree_ref(struct btrfs_delayed_ref_node *node)
 {
 	WARN_ON(btrfs_delayed_ref_is_head(node));
-	return container_of(node, struct btrfs_delayed_ref, node);
+	return container_of(node, struct btrfs_delayed_tree_ref, node);
+}
 
+static inline struct btrfs_delayed_data_ref *
+btrfs_delayed_node_to_data_ref(struct btrfs_delayed_ref_node *node)
+{
+	WARN_ON(btrfs_delayed_ref_is_head(node));
+	return container_of(node, struct btrfs_delayed_data_ref, node);
 }
 
 static inline struct btrfs_delayed_ref_head *
@@ -188,6 +210,5 @@ btrfs_delayed_node_to_head(struct btrfs_delayed_ref_node *node)
 {
 	WARN_ON(!btrfs_delayed_ref_is_head(node));
 	return container_of(node, struct btrfs_delayed_ref_head, node);
-
 }
 #endif
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4b0ea0b80c23..0d50d49d990a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -26,8 +26,8 @@
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/crc32c.h>
 #include "compat.h"
-#include "crc32c.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -36,7 +36,6 @@
 #include "print-tree.h"
 #include "async-thread.h"
 #include "locking.h"
-#include "ref-cache.h"
 #include "tree-log.h"
 #include "free-space-cache.h"
 
@@ -172,7 +171,7 @@ out:
 
 u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len)
 {
-	return btrfs_crc32c(seed, data, len);
+	return crc32c(seed, data, len);
 }
 
 void btrfs_csum_final(u32 crc, char *result)
@@ -884,7 +883,6 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 {
 	root->node = NULL;
 	root->commit_root = NULL;
-	root->ref_tree = NULL;
 	root->sectorsize = sectorsize;
 	root->nodesize = nodesize;
 	root->leafsize = leafsize;
@@ -899,12 +897,14 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	root->last_inode_alloc = 0;
 	root->name = NULL;
 	root->in_sysfs = 0;
+	root->inode_tree.rb_node = NULL;
 
 	INIT_LIST_HEAD(&root->dirty_list);
 	INIT_LIST_HEAD(&root->orphan_list);
-	INIT_LIST_HEAD(&root->dead_list);
+	INIT_LIST_HEAD(&root->root_list);
 	spin_lock_init(&root->node_lock);
 	spin_lock_init(&root->list_lock);
+	spin_lock_init(&root->inode_lock);
 	mutex_init(&root->objectid_mutex);
 	mutex_init(&root->log_mutex);
 	init_waitqueue_head(&root->log_writer_wait);
@@ -918,9 +918,6 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	extent_io_tree_init(&root->dirty_log_pages,
 			     fs_info->btree_inode->i_mapping, GFP_NOFS);
 
-	btrfs_leaf_ref_tree_init(&root->ref_tree_struct);
-	root->ref_tree = &root->ref_tree_struct;
-
 	memset(&root->root_key, 0, sizeof(root->root_key));
 	memset(&root->root_item, 0, sizeof(root->root_item));
 	memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
@@ -959,6 +956,7 @@ static int find_and_setup_root(struct btrfs_root *tree_root,
 	blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
 	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
 				     blocksize, generation);
+	root->commit_root = btrfs_root_node(root);
 	BUG_ON(!root->node);
 	return 0;
 }
@@ -1025,20 +1023,19 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	 */
 	root->ref_cows = 0;
 
-	leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
-				      0, BTRFS_TREE_LOG_OBJECTID,
-				      trans->transid, 0, 0, 0);
+	leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
+				      BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		kfree(root);
 		return ERR_CAST(leaf);
 	}
 
+	memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
+	btrfs_set_header_bytenr(leaf, leaf->start);
+	btrfs_set_header_generation(leaf, trans->transid);
+	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
+	btrfs_set_header_owner(leaf, BTRFS_TREE_LOG_OBJECTID);
 	root->node = leaf;
-	btrfs_set_header_nritems(root->node, 0);
-	btrfs_set_header_level(root->node, 0);
-	btrfs_set_header_bytenr(root->node, root->node->start);
-	btrfs_set_header_generation(root->node, trans->transid);
-	btrfs_set_header_owner(root->node, BTRFS_TREE_LOG_OBJECTID);
 
 	write_extent_buffer(root->node, root->fs_info->fsid,
 			    (unsigned long)btrfs_header_fsid(root->node),
@@ -1081,8 +1078,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 	inode_item->nbytes = cpu_to_le64(root->leafsize);
 	inode_item->mode = cpu_to_le32(S_IFDIR | 0755);
 
-	btrfs_set_root_bytenr(&log_root->root_item, log_root->node->start);
-	btrfs_set_root_generation(&log_root->root_item, trans->transid);
+	btrfs_set_root_node(&log_root->root_item, log_root->node);
 
 	WARN_ON(root->log_root);
 	root->log_root = log_root;
@@ -1144,6 +1140,7 @@ out:
 	blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
 	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
 				     blocksize, generation);
+	root->commit_root = btrfs_root_node(root);
 	BUG_ON(!root->node);
 insert:
 	if (location->objectid != BTRFS_TREE_LOG_OBJECTID) {
@@ -1210,7 +1207,7 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
 	}
 	if (!(fs_info->sb->s_flags & MS_RDONLY)) {
 		ret = btrfs_find_dead_roots(fs_info->tree_root,
-					    root->root_key.objectid, root);
+					    root->root_key.objectid);
 		BUG_ON(ret);
 		btrfs_orphan_cleanup(root);
 	}
@@ -1569,8 +1566,6 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->async_delalloc_pages, 0);
 	atomic_set(&fs_info->async_submit_draining, 0);
 	atomic_set(&fs_info->nr_async_bios, 0);
-	atomic_set(&fs_info->throttles, 0);
-	atomic_set(&fs_info->throttle_gen, 0);
 	fs_info->sb = sb;
 	fs_info->max_extent = (u64)-1;
 	fs_info->max_inline = 8192 * 1024;
@@ -1598,6 +1593,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
 	fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;
 
+	RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
 	extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
 			     fs_info->btree_inode->i_mapping,
 			     GFP_NOFS);
@@ -1613,10 +1609,6 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 			     fs_info->btree_inode->i_mapping, GFP_NOFS);
 	fs_info->do_barriers = 1;
 
-	INIT_LIST_HEAD(&fs_info->dead_reloc_roots);
-	btrfs_leaf_ref_tree_init(&fs_info->reloc_ref_tree);
-	btrfs_leaf_ref_tree_init(&fs_info->shared_ref_tree);
-
 	BTRFS_I(fs_info->btree_inode)->root = tree_root;
 	memset(&BTRFS_I(fs_info->btree_inode)->location, 0,
 	       sizeof(struct btrfs_key));
@@ -1674,6 +1666,12 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		goto fail_iput;
 	}
 
+	features = btrfs_super_incompat_flags(disk_super);
+	if (!(features & BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF)) {
+		features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
+		btrfs_set_super_incompat_flags(disk_super, features);
+	}
+
 	features = btrfs_super_compat_ro_flags(disk_super) &
 		~BTRFS_FEATURE_COMPAT_RO_SUPP;
 	if (!(sb->s_flags & MS_RDONLY) && features) {
@@ -1771,7 +1769,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	if (ret) {
 		printk(KERN_WARNING "btrfs: failed to read the system "
 		       "array on %s\n", sb->s_id);
-		goto fail_sys_array;
+		goto fail_sb_buffer;
 	}
 
 	blocksize = btrfs_level_size(tree_root,
@@ -1785,6 +1783,8 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 					   btrfs_super_chunk_root(disk_super),
 					   blocksize, generation);
 	BUG_ON(!chunk_root->node);
+	btrfs_set_root_node(&chunk_root->root_item, chunk_root->node);
+	chunk_root->commit_root = btrfs_root_node(chunk_root);
 
 	read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid,
 	   (unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node),
@@ -1810,7 +1810,8 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 					  blocksize, generation);
 	if (!tree_root->node)
 		goto fail_chunk_root;
-
+	btrfs_set_root_node(&tree_root->root_item, tree_root->node);
+	tree_root->commit_root = btrfs_root_node(tree_root);
 
 	ret = find_and_setup_root(tree_root, fs_info,
 				  BTRFS_EXTENT_TREE_OBJECTID, extent_root);
@@ -1820,14 +1821,14 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
 	ret = find_and_setup_root(tree_root, fs_info,
 				  BTRFS_DEV_TREE_OBJECTID, dev_root);
-	dev_root->track_dirty = 1;
 	if (ret)
 		goto fail_extent_root;
+	dev_root->track_dirty = 1;
 
 	ret = find_and_setup_root(tree_root, fs_info,
 				  BTRFS_CSUM_TREE_OBJECTID, csum_root);
 	if (ret)
-		goto fail_extent_root;
+		goto fail_dev_root;
 
 	csum_root->track_dirty = 1;
 
@@ -1849,6 +1850,14 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	if (IS_ERR(fs_info->transaction_kthread))
 		goto fail_cleaner;
 
+	if (!btrfs_test_opt(tree_root, SSD) &&
+	    !btrfs_test_opt(tree_root, NOSSD) &&
+	    !fs_info->fs_devices->rotating) {
+		printk(KERN_INFO "Btrfs detected SSD devices, enabling SSD "
+		       "mode\n");
+		btrfs_set_opt(fs_info->mount_opt, SSD);
+	}
+
 	if (btrfs_super_log_root(disk_super) != 0) {
 		u64 bytenr = btrfs_super_log_root(disk_super);
 
@@ -1881,7 +1890,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	}
 
 	if (!(sb->s_flags & MS_RDONLY)) {
-		ret = btrfs_cleanup_reloc_trees(tree_root);
+		ret = btrfs_recover_relocation(tree_root);
 		BUG_ON(ret);
 	}
 
@@ -1892,6 +1901,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->fs_root = btrfs_read_fs_root_no_name(fs_info, &location);
 	if (!fs_info->fs_root)
 		goto fail_trans_kthread;
+
 	return tree_root;
 
 fail_trans_kthread:
@@ -1908,14 +1918,19 @@ fail_cleaner:
 
 fail_csum_root:
 	free_extent_buffer(csum_root->node);
+	free_extent_buffer(csum_root->commit_root);
+fail_dev_root:
+	free_extent_buffer(dev_root->node);
+	free_extent_buffer(dev_root->commit_root);
 fail_extent_root:
 	free_extent_buffer(extent_root->node);
+	free_extent_buffer(extent_root->commit_root);
 fail_tree_root:
 	free_extent_buffer(tree_root->node);
+	free_extent_buffer(tree_root->commit_root);
 fail_chunk_root:
 	free_extent_buffer(chunk_root->node);
-fail_sys_array:
-	free_extent_buffer(dev_root->node);
+	free_extent_buffer(chunk_root->commit_root);
 fail_sb_buffer:
 	btrfs_stop_workers(&fs_info->fixup_workers);
 	btrfs_stop_workers(&fs_info->delalloc_workers);
@@ -2005,6 +2020,17 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev)
 	return latest;
 }
 
+/*
+ * this should be called twice, once with wait == 0 and
+ * once with wait == 1.  When wait == 0 is done, all the buffer heads
+ * we write are pinned.
+ *
+ * They are released when wait == 1 is done.
+ * max_mirrors must be the same for both runs, and it indicates how
+ * many supers on this one device should be written.
+ *
+ * max_mirrors == 0 means to write them all.
+ */
 static int write_dev_supers(struct btrfs_device *device,
 			    struct btrfs_super_block *sb,
 			    int do_barriers, int wait, int max_mirrors)
@@ -2040,12 +2066,16 @@ static int write_dev_supers(struct btrfs_device *device,
 			bh = __find_get_block(device->bdev, bytenr / 4096,
 					      BTRFS_SUPER_INFO_SIZE);
 			BUG_ON(!bh);
-			brelse(bh);
 			wait_on_buffer(bh);
-			if (buffer_uptodate(bh)) {
-				brelse(bh);
-				continue;
-			}
+			if (!buffer_uptodate(bh))
+				errors++;
+
+			/* drop our reference */
+			brelse(bh);
+
+			/* drop the reference from the wait == 0 run */
+			brelse(bh);
+			continue;
 		} else {
 			btrfs_set_super_bytenr(sb, bytenr);
 
@@ -2056,12 +2086,18 @@ static int write_dev_supers(struct btrfs_device *device,
 					      BTRFS_CSUM_SIZE);
 			btrfs_csum_final(crc, sb->csum);
 
+			/*
+			 * one reference for us, and we leave it for the
+			 * caller
+			 */
 			bh = __getblk(device->bdev, bytenr / 4096,
 				      BTRFS_SUPER_INFO_SIZE);
 			memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE);
 
-			set_buffer_uptodate(bh);
+			/* one reference for submit_bh */
 			get_bh(bh);
+
+			set_buffer_uptodate(bh);
 			lock_buffer(bh);
 			bh->b_end_io = btrfs_end_buffer_write_sync;
 		}
@@ -2073,6 +2109,7 @@ static int write_dev_supers(struct btrfs_device *device,
 				       device->name);
 				set_buffer_uptodate(bh);
 				device->barriers = 0;
+				/* one reference for submit_bh */
 				get_bh(bh);
 				lock_buffer(bh);
 				ret = submit_bh(WRITE_SYNC, bh);
@@ -2081,22 +2118,15 @@ static int write_dev_supers(struct btrfs_device *device,
 			ret = submit_bh(WRITE_SYNC, bh);
 		}
 
-		if (!ret && wait) {
-			wait_on_buffer(bh);
-			if (!buffer_uptodate(bh))
-				errors++;
-		} else if (ret) {
+		if (ret)
 			errors++;
-		}
-		if (wait)
-			brelse(bh);
 	}
 	return errors < i ? 0 : -1;
 }
 
 int write_all_supers(struct btrfs_root *root, int max_mirrors)
 {
-	struct list_head *head = &root->fs_info->fs_devices->devices;
+	struct list_head *head;
 	struct btrfs_device *dev;
 	struct btrfs_super_block *sb;
 	struct btrfs_dev_item *dev_item;
@@ -2111,6 +2141,9 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors)
 
 	sb = &root->fs_info->super_for_commit;
 	dev_item = &sb->dev_item;
+
+	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+	head = &root->fs_info->fs_devices->devices;
 	list_for_each_entry(dev, head, dev_list) {
 		if (!dev->bdev) {
 			total_errors++;
@@ -2154,6 +2187,7 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors)
 		if (ret)
 			total_errors++;
 	}
+	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 	if (total_errors > max_errors) {
 		printk(KERN_ERR "btrfs: %d errors while writing supers\n",
 		       total_errors);
@@ -2173,6 +2207,7 @@ int write_ctree_super(struct btrfs_trans_handle *trans,
 
 int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
 {
+	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
 	radix_tree_delete(&fs_info->fs_roots_radix,
 			  (unsigned long)root->root_key.objectid);
 	if (root->anon_super.s_dev) {
@@ -2219,10 +2254,12 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 					     ARRAY_SIZE(gang));
 		if (!ret)
 			break;
+
+		root_objectid = gang[ret - 1]->root_key.objectid + 1;
 		for (i = 0; i < ret; i++) {
 			root_objectid = gang[i]->root_key.objectid;
 			ret = btrfs_find_dead_roots(fs_info->tree_root,
-						    root_objectid, gang[i]);
+						    root_objectid);
 			BUG_ON(ret);
 			btrfs_orphan_cleanup(gang[i]);
 		}
@@ -2278,20 +2315,16 @@ int close_ctree(struct btrfs_root *root)
 		       (unsigned long long)fs_info->total_ref_cache_size);
 	}
 
-	if (fs_info->extent_root->node)
-		free_extent_buffer(fs_info->extent_root->node);
-
-	if (fs_info->tree_root->node)
-		free_extent_buffer(fs_info->tree_root->node);
-
-	if (root->fs_info->chunk_root->node)
-		free_extent_buffer(root->fs_info->chunk_root->node);
-
-	if (root->fs_info->dev_root->node)
-		free_extent_buffer(root->fs_info->dev_root->node);
-
-	if (root->fs_info->csum_root->node)
-		free_extent_buffer(root->fs_info->csum_root->node);
+	free_extent_buffer(fs_info->extent_root->node);
+	free_extent_buffer(fs_info->extent_root->commit_root);
+	free_extent_buffer(fs_info->tree_root->node);
+	free_extent_buffer(fs_info->tree_root->commit_root);
+	free_extent_buffer(root->fs_info->chunk_root->node);
+	free_extent_buffer(root->fs_info->chunk_root->commit_root);
+	free_extent_buffer(root->fs_info->dev_root->node);
+	free_extent_buffer(root->fs_info->dev_root->commit_root);
+	free_extent_buffer(root->fs_info->csum_root->node);
+	free_extent_buffer(root->fs_info->csum_root->commit_root);
 
 	btrfs_free_block_groups(root->fs_info);
 
@@ -2373,17 +2406,14 @@ void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr)
 	 * looks as though older kernels can get into trouble with
 	 * this code, they end up stuck in balance_dirty_pages forever
 	 */
-	struct extent_io_tree *tree;
 	u64 num_dirty;
-	u64 start = 0;
 	unsigned long thresh = 32 * 1024 * 1024;
-	tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
 
 	if (current->flags & PF_MEMALLOC)
 		return;
 
-	num_dirty = count_range_bits(tree, &start, (u64)-1,
-				     thresh, EXTENT_DIRTY);
+	num_dirty = root->fs_info->dirty_metadata_bytes;
+
 	if (num_dirty > thresh) {
 		balance_dirty_pages_ratelimited_nr(
 				   root->fs_info->btree_inode->i_mapping, 1);
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 85315d2c90de..9596b40caa4e 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -78,7 +78,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
 	btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
 	key.offset = 0;
 
-	inode = btrfs_iget(sb, &key, root, NULL);
+	inode = btrfs_iget(sb, &key, root);
 	if (IS_ERR(inode))
 		return (void *)inode;
 
@@ -192,7 +192,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 	btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
 	key.offset = 0;
 
-	return d_obtain_alias(btrfs_iget(root->fs_info->sb, &key, root, NULL));
+	return d_obtain_alias(btrfs_iget(root->fs_info->sb, &key, root));
 }
 
 const struct export_operations btrfs_export_ops = {
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 35af93355063..edc7d208c5ce 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -23,50 +23,39 @@
 #include <linux/rcupdate.h>
 #include "compat.h"
 #include "hash.h"
-#include "crc32c.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "print-tree.h"
 #include "transaction.h"
 #include "volumes.h"
 #include "locking.h"
-#include "ref-cache.h"
 #include "free-space-cache.h"
 
-#define PENDING_EXTENT_INSERT 0
-#define PENDING_EXTENT_DELETE 1
-#define PENDING_BACKREF_UPDATE 2
-
-struct pending_extent_op {
-	int type;
-	u64 bytenr;
-	u64 num_bytes;
-	u64 parent;
-	u64 orig_parent;
-	u64 generation;
-	u64 orig_generation;
-	int level;
-	struct list_head list;
-	int del;
-};
-
-static int __btrfs_alloc_reserved_extent(struct btrfs_trans_handle *trans,
-					 struct btrfs_root *root, u64 parent,
-					 u64 root_objectid, u64 ref_generation,
-					 u64 owner, struct btrfs_key *ins,
-					 int ref_mod);
 static int update_reserved_extents(struct btrfs_root *root,
 				   u64 bytenr, u64 num, int reserve);
 static int update_block_group(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      u64 bytenr, u64 num_bytes, int alloc,
 			      int mark_free);
-static noinline int __btrfs_free_extent(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root,
-					u64 bytenr, u64 num_bytes, u64 parent,
-					u64 root_objectid, u64 ref_generation,
-					u64 owner_objectid, int pin,
-					int ref_to_drop);
+static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				u64 bytenr, u64 num_bytes, u64 parent,
+				u64 root_objectid, u64 owner_objectid,
+				u64 owner_offset, int refs_to_drop,
+				struct btrfs_delayed_extent_op *extra_op);
+static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
+				    struct extent_buffer *leaf,
+				    struct btrfs_extent_item *ei);
+static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
+				      struct btrfs_root *root,
+				      u64 parent, u64 root_objectid,
+				      u64 flags, u64 owner, u64 offset,
+				      struct btrfs_key *ins, int ref_mod);
+static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
+				     struct btrfs_root *root,
+				     u64 parent, u64 root_objectid,
+				     u64 flags, struct btrfs_disk_key *key,
+				     int level, struct btrfs_key *ins);
 
 static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *extent_root, u64 alloc_bytes,
@@ -453,199 +442,969 @@ int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len)
  *    maintenance.  This is actually the same as #2, but with a slightly
  *    different use case.
  *
+ * There are two kinds of back refs. The implicit back refs is optimized
+ * for pointers in non-shared tree blocks. For a given pointer in a block,
+ * back refs of this kind provide information about the block's owner tree
+ * and the pointer's key. These information allow us to find the block by
+ * b-tree searching. The full back refs is for pointers in tree blocks not
+ * referenced by their owner trees. The location of tree block is recorded
+ * in the back refs. Actually the full back refs is generic, and can be
+ * used in all cases the implicit back refs is used. The major shortcoming
+ * of the full back refs is its overhead. Every time a tree block gets
+ * COWed, we have to update back refs entry for all pointers in it.
+ *
+ * For a newly allocated tree block, we use implicit back refs for
+ * pointers in it. This means most tree related operations only involve
+ * implicit back refs. For a tree block created in old transaction, the
+ * only way to drop a reference to it is COW it. So we can detect the
+ * event that tree block loses its owner tree's reference and do the
+ * back refs conversion.
+ *
+ * When a tree block is COW'd through a tree, there are four cases:
+ *
+ * The reference count of the block is one and the tree is the block's
+ * owner tree. Nothing to do in this case.
+ *
+ * The reference count of the block is one and the tree is not the
+ * block's owner tree. In this case, full back refs is used for pointers
+ * in the block. Remove these full back refs, add implicit back refs for
+ * every pointers in the new block.
+ *
+ * The reference count of the block is greater than one and the tree is
+ * the block's owner tree. In this case, implicit back refs is used for
+ * pointers in the block. Add full back refs for every pointers in the
+ * block, increase lower level extents' reference counts. The original
+ * implicit back refs are entailed to the new block.
+ *
+ * The reference count of the block is greater than one and the tree is
+ * not the block's owner tree. Add implicit back refs for every pointer in
+ * the new block, increase lower level extents' reference count.
+ *
+ * Back Reference Key composing:
+ *
+ * The key objectid corresponds to the first byte in the extent,
+ * The key type is used to differentiate between types of back refs.
+ * There are different meanings of the key offset for different types
+ * of back refs.
+ *
  * File extents can be referenced by:
  *
  * - multiple snapshots, subvolumes, or different generations in one subvol
  * - different files inside a single subvolume
  * - different offsets inside a file (bookend extents in file.c)
  *
- * The extent ref structure has fields for:
+ * The extent ref structure for the implicit back refs has fields for:
  *
  * - Objectid of the subvolume root
- * - Generation number of the tree holding the reference
  * - objectid of the file holding the reference
- * - number of references holding by parent node (alway 1 for tree blocks)
+ * - original offset in the file
+ * - how many bookend extents
  *
- * Btree leaf may hold multiple references to a file extent. In most cases,
- * these references are from same file and the corresponding offsets inside
- * the file are close together.
+ * The key offset for the implicit back refs is hash of the first
+ * three fields.
  *
- * When a file extent is allocated the fields are filled in:
- *     (root_key.objectid, trans->transid, inode objectid, 1)
+ * The extent ref structure for the full back refs has field for:
  *
- * When a leaf is cow'd new references are added for every file extent found
- * in the leaf.  It looks similar to the create case, but trans->transid will
- * be different when the block is cow'd.
+ * - number of pointers in the tree leaf
  *
- *     (root_key.objectid, trans->transid, inode objectid,
- *      number of references in the leaf)
+ * The key offset for the implicit back refs is the first byte of
+ * the tree leaf
  *
- * When a file extent is removed either during snapshot deletion or
- * file truncation, we find the corresponding back reference and check
- * the following fields:
+ * When a file extent is allocated, The implicit back refs is used.
+ * the fields are filled in:
  *
- *     (btrfs_header_owner(leaf), btrfs_header_generation(leaf),
- *      inode objectid)
+ *     (root_key.objectid, inode objectid, offset in file, 1)
+ *
+ * When a file extent is removed file truncation, we find the
+ * corresponding implicit back refs and check the following fields:
+ *
+ *     (btrfs_header_owner(leaf), inode objectid, offset in file)
  *
  * Btree extents can be referenced by:
  *
  * - Different subvolumes
- * - Different generations of the same subvolume
  *
- * When a tree block is created, back references are inserted:
+ * Both the implicit back refs and the full back refs for tree blocks
+ * only consist of key. The key offset for the implicit back refs is
+ * objectid of block's owner tree. The key offset for the full back refs
+ * is the first byte of parent block.
  *
- * (root->root_key.objectid, trans->transid, level, 1)
- *
- * When a tree block is cow'd, new back references are added for all the
- * blocks it points to. If the tree block isn't in reference counted root,
- * the old back references are removed. These new back references are of
- * the form (trans->transid will have increased since creation):
- *
- * (root->root_key.objectid, trans->transid, level, 1)
- *
- * When a backref is in deleting, the following fields are checked:
- *
- * if backref was for a tree root:
- *     (btrfs_header_owner(itself), btrfs_header_generation(itself), level)
- * else
- *     (btrfs_header_owner(parent), btrfs_header_generation(parent), level)
- *
- * Back Reference Key composing:
- *
- * The key objectid corresponds to the first byte in the extent, the key
- * type is set to BTRFS_EXTENT_REF_KEY, and the key offset is the first
- * byte of parent extent. If a extent is tree root, the key offset is set
- * to the key objectid.
+ * When implicit back refs is used, information about the lowest key and
+ * level of the tree block are required. These information are stored in
+ * tree block info structure.
  */
 
-static noinline int lookup_extent_backref(struct btrfs_trans_handle *trans,
-					  struct btrfs_root *root,
-					  struct btrfs_path *path,
-					  u64 bytenr, u64 parent,
-					  u64 ref_root, u64 ref_generation,
-					  u64 owner_objectid, int del)
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
+				  struct btrfs_root *root,
+				  struct btrfs_path *path,
+				  u64 owner, u32 extra_size)
 {
-	struct btrfs_key key;
-	struct btrfs_extent_ref *ref;
+	struct btrfs_extent_item *item;
+	struct btrfs_extent_item_v0 *ei0;
+	struct btrfs_extent_ref_v0 *ref0;
+	struct btrfs_tree_block_info *bi;
 	struct extent_buffer *leaf;
-	u64 ref_objectid;
+	struct btrfs_key key;
+	struct btrfs_key found_key;
+	u32 new_size = sizeof(*item);
+	u64 refs;
 	int ret;
 
-	key.objectid = bytenr;
-	key.type = BTRFS_EXTENT_REF_KEY;
-	key.offset = parent;
+	leaf = path->nodes[0];
+	BUG_ON(btrfs_item_size_nr(leaf, path->slots[0]) != sizeof(*ei0));
 
-	ret = btrfs_search_slot(trans, root, &key, path, del ? -1 : 0, 1);
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+	ei0 = btrfs_item_ptr(leaf, path->slots[0],
+			     struct btrfs_extent_item_v0);
+	refs = btrfs_extent_refs_v0(leaf, ei0);
+
+	if (owner == (u64)-1) {
+		while (1) {
+			if (path->slots[0] >= btrfs_header_nritems(leaf)) {
+				ret = btrfs_next_leaf(root, path);
+				if (ret < 0)
+					return ret;
+				BUG_ON(ret > 0);
+				leaf = path->nodes[0];
+			}
+			btrfs_item_key_to_cpu(leaf, &found_key,
+					      path->slots[0]);
+			BUG_ON(key.objectid != found_key.objectid);
+			if (found_key.type != BTRFS_EXTENT_REF_V0_KEY) {
+				path->slots[0]++;
+				continue;
+			}
+			ref0 = btrfs_item_ptr(leaf, path->slots[0],
+					      struct btrfs_extent_ref_v0);
+			owner = btrfs_ref_objectid_v0(leaf, ref0);
+			break;
+		}
+	}
+	btrfs_release_path(root, path);
+
+	if (owner < BTRFS_FIRST_FREE_OBJECTID)
+		new_size += sizeof(*bi);
+
+	new_size -= sizeof(*ei0);
+	ret = btrfs_search_slot(trans, root, &key, path,
+				new_size + extra_size, 1);
 	if (ret < 0)
-		goto out;
-	if (ret > 0) {
-		ret = -ENOENT;
-		goto out;
+		return ret;
+	BUG_ON(ret);
+
+	ret = btrfs_extend_item(trans, root, path, new_size);
+	BUG_ON(ret);
+
+	leaf = path->nodes[0];
+	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+	btrfs_set_extent_refs(leaf, item, refs);
+	/* FIXME: get real generation */
+	btrfs_set_extent_generation(leaf, item, 0);
+	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+		btrfs_set_extent_flags(leaf, item,
+				       BTRFS_EXTENT_FLAG_TREE_BLOCK |
+				       BTRFS_BLOCK_FLAG_FULL_BACKREF);
+		bi = (struct btrfs_tree_block_info *)(item + 1);
+		/* FIXME: get first key of the block */
+		memset_extent_buffer(leaf, 0, (unsigned long)bi, sizeof(*bi));
+		btrfs_set_tree_block_level(leaf, bi, (int)owner);
+	} else {
+		btrfs_set_extent_flags(leaf, item, BTRFS_EXTENT_FLAG_DATA);
+	}
+	btrfs_mark_buffer_dirty(leaf);
+	return 0;
+}
+#endif
+
+static u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset)
+{
+	u32 high_crc = ~(u32)0;
+	u32 low_crc = ~(u32)0;
+	__le64 lenum;
+
+	lenum = cpu_to_le64(root_objectid);
+	high_crc = crc32c(high_crc, &lenum, sizeof(lenum));
+	lenum = cpu_to_le64(owner);
+	low_crc = crc32c(low_crc, &lenum, sizeof(lenum));
+	lenum = cpu_to_le64(offset);
+	low_crc = crc32c(low_crc, &lenum, sizeof(lenum));
+
+	return ((u64)high_crc << 31) ^ (u64)low_crc;
+}
+
+static u64 hash_extent_data_ref_item(struct extent_buffer *leaf,
+				     struct btrfs_extent_data_ref *ref)
+{
+	return hash_extent_data_ref(btrfs_extent_data_ref_root(leaf, ref),
+				    btrfs_extent_data_ref_objectid(leaf, ref),
+				    btrfs_extent_data_ref_offset(leaf, ref));
+}
+
+static int match_extent_data_ref(struct extent_buffer *leaf,
+				 struct btrfs_extent_data_ref *ref,
+				 u64 root_objectid, u64 owner, u64 offset)
+{
+	if (btrfs_extent_data_ref_root(leaf, ref) != root_objectid ||
+	    btrfs_extent_data_ref_objectid(leaf, ref) != owner ||
+	    btrfs_extent_data_ref_offset(leaf, ref) != offset)
+		return 0;
+	return 1;
+}
+
+static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans,
+					   struct btrfs_root *root,
+					   struct btrfs_path *path,
+					   u64 bytenr, u64 parent,
+					   u64 root_objectid,
+					   u64 owner, u64 offset)
+{
+	struct btrfs_key key;
+	struct btrfs_extent_data_ref *ref;
+	struct extent_buffer *leaf;
+	u32 nritems;
+	int ret;
+	int recow;
+	int err = -ENOENT;
+
+	key.objectid = bytenr;
+	if (parent) {
+		key.type = BTRFS_SHARED_DATA_REF_KEY;
+		key.offset = parent;
+	} else {
+		key.type = BTRFS_EXTENT_DATA_REF_KEY;
+		key.offset = hash_extent_data_ref(root_objectid,
+						  owner, offset);
+	}
+again:
+	recow = 0;
+	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+	if (ret < 0) {
+		err = ret;
+		goto fail;
+	}
+
+	if (parent) {
+		if (!ret)
+			return 0;
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+		key.type = BTRFS_EXTENT_REF_V0_KEY;
+		btrfs_release_path(root, path);
+		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+		if (ret < 0) {
+			err = ret;
+			goto fail;
+		}
+		if (!ret)
+			return 0;
+#endif
+		goto fail;
 	}
 
 	leaf = path->nodes[0];
-	ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_ref);
-	ref_objectid = btrfs_ref_objectid(leaf, ref);
-	if (btrfs_ref_root(leaf, ref) != ref_root ||
-	    btrfs_ref_generation(leaf, ref) != ref_generation ||
-	    (ref_objectid != owner_objectid &&
-	     ref_objectid != BTRFS_MULTIPLE_OBJECTIDS)) {
-		ret = -EIO;
-		WARN_ON(1);
-		goto out;
+	nritems = btrfs_header_nritems(leaf);
+	while (1) {
+		if (path->slots[0] >= nritems) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				err = ret;
+			if (ret)
+				goto fail;
+
+			leaf = path->nodes[0];
+			nritems = btrfs_header_nritems(leaf);
+			recow = 1;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+		if (key.objectid != bytenr ||
+		    key.type != BTRFS_EXTENT_DATA_REF_KEY)
+			goto fail;
+
+		ref = btrfs_item_ptr(leaf, path->slots[0],
+				     struct btrfs_extent_data_ref);
+
+		if (match_extent_data_ref(leaf, ref, root_objectid,
+					  owner, offset)) {
+			if (recow) {
+				btrfs_release_path(root, path);
+				goto again;
+			}
+			err = 0;
+			break;
+		}
+		path->slots[0]++;
 	}
-	ret = 0;
-out:
-	return ret;
+fail:
+	return err;
 }
 
-static noinline int insert_extent_backref(struct btrfs_trans_handle *trans,
-					  struct btrfs_root *root,
-					  struct btrfs_path *path,
-					  u64 bytenr, u64 parent,
-					  u64 ref_root, u64 ref_generation,
-					  u64 owner_objectid,
-					  int refs_to_add)
+static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
+					   struct btrfs_root *root,
+					   struct btrfs_path *path,
+					   u64 bytenr, u64 parent,
+					   u64 root_objectid, u64 owner,
+					   u64 offset, int refs_to_add)
 {
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
-	struct btrfs_extent_ref *ref;
+	u32 size;
 	u32 num_refs;
 	int ret;
 
 	key.objectid = bytenr;
-	key.type = BTRFS_EXTENT_REF_KEY;
-	key.offset = parent;
-
-	ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*ref));
-	if (ret == 0) {
-		leaf = path->nodes[0];
-		ref = btrfs_item_ptr(leaf, path->slots[0],
-				     struct btrfs_extent_ref);
-		btrfs_set_ref_root(leaf, ref, ref_root);
-		btrfs_set_ref_generation(leaf, ref, ref_generation);
-		btrfs_set_ref_objectid(leaf, ref, owner_objectid);
-		btrfs_set_ref_num_refs(leaf, ref, refs_to_add);
-	} else if (ret == -EEXIST) {
-		u64 existing_owner;
-
-		BUG_ON(owner_objectid < BTRFS_FIRST_FREE_OBJECTID);
-		leaf = path->nodes[0];
-		ref = btrfs_item_ptr(leaf, path->slots[0],
-				     struct btrfs_extent_ref);
-		if (btrfs_ref_root(leaf, ref) != ref_root ||
-		    btrfs_ref_generation(leaf, ref) != ref_generation) {
-			ret = -EIO;
-			WARN_ON(1);
-			goto out;
-		}
-
-		num_refs = btrfs_ref_num_refs(leaf, ref);
-		BUG_ON(num_refs == 0);
-		btrfs_set_ref_num_refs(leaf, ref, num_refs + refs_to_add);
-
-		existing_owner = btrfs_ref_objectid(leaf, ref);
-		if (existing_owner != owner_objectid &&
-		    existing_owner != BTRFS_MULTIPLE_OBJECTIDS) {
-			btrfs_set_ref_objectid(leaf, ref,
-					BTRFS_MULTIPLE_OBJECTIDS);
-		}
-		ret = 0;
+	if (parent) {
+		key.type = BTRFS_SHARED_DATA_REF_KEY;
+		key.offset = parent;
+		size = sizeof(struct btrfs_shared_data_ref);
 	} else {
-		goto out;
+		key.type = BTRFS_EXTENT_DATA_REF_KEY;
+		key.offset = hash_extent_data_ref(root_objectid,
+						  owner, offset);
+		size = sizeof(struct btrfs_extent_data_ref);
 	}
-	btrfs_unlock_up_safe(path, 1);
-	btrfs_mark_buffer_dirty(path->nodes[0]);
-out:
+
+	ret = btrfs_insert_empty_item(trans, root, path, &key, size);
+	if (ret && ret != -EEXIST)
+		goto fail;
+
+	leaf = path->nodes[0];
+	if (parent) {
+		struct btrfs_shared_data_ref *ref;
+		ref = btrfs_item_ptr(leaf, path->slots[0],
+				     struct btrfs_shared_data_ref);
+		if (ret == 0) {
+			btrfs_set_shared_data_ref_count(leaf, ref, refs_to_add);
+		} else {
+			num_refs = btrfs_shared_data_ref_count(leaf, ref);
+			num_refs += refs_to_add;
+			btrfs_set_shared_data_ref_count(leaf, ref, num_refs);
+		}
+	} else {
+		struct btrfs_extent_data_ref *ref;
+		while (ret == -EEXIST) {
+			ref = btrfs_item_ptr(leaf, path->slots[0],
+					     struct btrfs_extent_data_ref);
+			if (match_extent_data_ref(leaf, ref, root_objectid,
+						  owner, offset))
+				break;
+			btrfs_release_path(root, path);
+			key.offset++;
+			ret = btrfs_insert_empty_item(trans, root, path, &key,
+						      size);
+			if (ret && ret != -EEXIST)
+				goto fail;
+
+			leaf = path->nodes[0];
+		}
+		ref = btrfs_item_ptr(leaf, path->slots[0],
+				     struct btrfs_extent_data_ref);
+		if (ret == 0) {
+			btrfs_set_extent_data_ref_root(leaf, ref,
+						       root_objectid);
+			btrfs_set_extent_data_ref_objectid(leaf, ref, owner);
+			btrfs_set_extent_data_ref_offset(leaf, ref, offset);
+			btrfs_set_extent_data_ref_count(leaf, ref, refs_to_add);
+		} else {
+			num_refs = btrfs_extent_data_ref_count(leaf, ref);
+			num_refs += refs_to_add;
+			btrfs_set_extent_data_ref_count(leaf, ref, num_refs);
+		}
+	}
+	btrfs_mark_buffer_dirty(leaf);
+	ret = 0;
+fail:
 	btrfs_release_path(root, path);
 	return ret;
 }
 
-static noinline int remove_extent_backref(struct btrfs_trans_handle *trans,
-					  struct btrfs_root *root,
-					  struct btrfs_path *path,
-					  int refs_to_drop)
+static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
+					   struct btrfs_root *root,
+					   struct btrfs_path *path,
+					   int refs_to_drop)
 {
+	struct btrfs_key key;
+	struct btrfs_extent_data_ref *ref1 = NULL;
+	struct btrfs_shared_data_ref *ref2 = NULL;
 	struct extent_buffer *leaf;
-	struct btrfs_extent_ref *ref;
-	u32 num_refs;
+	u32 num_refs = 0;
 	int ret = 0;
 
 	leaf = path->nodes[0];
-	ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_ref);
-	num_refs = btrfs_ref_num_refs(leaf, ref);
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+
+	if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
+		ref1 = btrfs_item_ptr(leaf, path->slots[0],
+				      struct btrfs_extent_data_ref);
+		num_refs = btrfs_extent_data_ref_count(leaf, ref1);
+	} else if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
+		ref2 = btrfs_item_ptr(leaf, path->slots[0],
+				      struct btrfs_shared_data_ref);
+		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
+		struct btrfs_extent_ref_v0 *ref0;
+		ref0 = btrfs_item_ptr(leaf, path->slots[0],
+				      struct btrfs_extent_ref_v0);
+		num_refs = btrfs_ref_count_v0(leaf, ref0);
+#endif
+	} else {
+		BUG();
+	}
+
 	BUG_ON(num_refs < refs_to_drop);
 	num_refs -= refs_to_drop;
+
 	if (num_refs == 0) {
 		ret = btrfs_del_item(trans, root, path);
 	} else {
-		btrfs_set_ref_num_refs(leaf, ref, num_refs);
+		if (key.type == BTRFS_EXTENT_DATA_REF_KEY)
+			btrfs_set_extent_data_ref_count(leaf, ref1, num_refs);
+		else if (key.type == BTRFS_SHARED_DATA_REF_KEY)
+			btrfs_set_shared_data_ref_count(leaf, ref2, num_refs);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+		else {
+			struct btrfs_extent_ref_v0 *ref0;
+			ref0 = btrfs_item_ptr(leaf, path->slots[0],
+					struct btrfs_extent_ref_v0);
+			btrfs_set_ref_count_v0(leaf, ref0, num_refs);
+		}
+#endif
 		btrfs_mark_buffer_dirty(leaf);
 	}
+	return ret;
+}
+
+static noinline u32 extent_data_ref_count(struct btrfs_root *root,
+					  struct btrfs_path *path,
+					  struct btrfs_extent_inline_ref *iref)
+{
+	struct btrfs_key key;
+	struct extent_buffer *leaf;
+	struct btrfs_extent_data_ref *ref1;
+	struct btrfs_shared_data_ref *ref2;
+	u32 num_refs = 0;
+
+	leaf = path->nodes[0];
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+	if (iref) {
+		if (btrfs_extent_inline_ref_type(leaf, iref) ==
+		    BTRFS_EXTENT_DATA_REF_KEY) {
+			ref1 = (struct btrfs_extent_data_ref *)(&iref->offset);
+			num_refs = btrfs_extent_data_ref_count(leaf, ref1);
+		} else {
+			ref2 = (struct btrfs_shared_data_ref *)(iref + 1);
+			num_refs = btrfs_shared_data_ref_count(leaf, ref2);
+		}
+	} else if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
+		ref1 = btrfs_item_ptr(leaf, path->slots[0],
+				      struct btrfs_extent_data_ref);
+		num_refs = btrfs_extent_data_ref_count(leaf, ref1);
+	} else if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
+		ref2 = btrfs_item_ptr(leaf, path->slots[0],
+				      struct btrfs_shared_data_ref);
+		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
+		struct btrfs_extent_ref_v0 *ref0;
+		ref0 = btrfs_item_ptr(leaf, path->slots[0],
+				      struct btrfs_extent_ref_v0);
+		num_refs = btrfs_ref_count_v0(leaf, ref0);
+#endif
+	} else {
+		WARN_ON(1);
+	}
+	return num_refs;
+}
+
+static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
+					  struct btrfs_root *root,
+					  struct btrfs_path *path,
+					  u64 bytenr, u64 parent,
+					  u64 root_objectid)
+{
+	struct btrfs_key key;
+	int ret;
+
+	key.objectid = bytenr;
+	if (parent) {
+		key.type = BTRFS_SHARED_BLOCK_REF_KEY;
+		key.offset = parent;
+	} else {
+		key.type = BTRFS_TREE_BLOCK_REF_KEY;
+		key.offset = root_objectid;
+	}
+
+	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+	if (ret > 0)
+		ret = -ENOENT;
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	if (ret == -ENOENT && parent) {
+		btrfs_release_path(root, path);
+		key.type = BTRFS_EXTENT_REF_V0_KEY;
+		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+		if (ret > 0)
+			ret = -ENOENT;
+	}
+#endif
+	return ret;
+}
+
+static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
+					  struct btrfs_root *root,
+					  struct btrfs_path *path,
+					  u64 bytenr, u64 parent,
+					  u64 root_objectid)
+{
+	struct btrfs_key key;
+	int ret;
+
+	key.objectid = bytenr;
+	if (parent) {
+		key.type = BTRFS_SHARED_BLOCK_REF_KEY;
+		key.offset = parent;
+	} else {
+		key.type = BTRFS_TREE_BLOCK_REF_KEY;
+		key.offset = root_objectid;
+	}
+
+	ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
 	btrfs_release_path(root, path);
 	return ret;
 }
 
+static inline int extent_ref_type(u64 parent, u64 owner)
+{
+	int type;
+	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+		if (parent > 0)
+			type = BTRFS_SHARED_BLOCK_REF_KEY;
+		else
+			type = BTRFS_TREE_BLOCK_REF_KEY;
+	} else {
+		if (parent > 0)
+			type = BTRFS_SHARED_DATA_REF_KEY;
+		else
+			type = BTRFS_EXTENT_DATA_REF_KEY;
+	}
+	return type;
+}
+
+static int find_next_key(struct btrfs_path *path, struct btrfs_key *key)
+
+{
+	int level;
+	BUG_ON(!path->keep_locks);
+	for (level = 0; level < BTRFS_MAX_LEVEL; level++) {
+		if (!path->nodes[level])
+			break;
+		btrfs_assert_tree_locked(path->nodes[level]);
+		if (path->slots[level] + 1 >=
+		    btrfs_header_nritems(path->nodes[level]))
+			continue;
+		if (level == 0)
+			btrfs_item_key_to_cpu(path->nodes[level], key,
+					      path->slots[level] + 1);
+		else
+			btrfs_node_key_to_cpu(path->nodes[level], key,
+					      path->slots[level] + 1);
+		return 0;
+	}
+	return 1;
+}
+
+/*
+ * look for inline back ref. if back ref is found, *ref_ret is set
+ * to the address of inline back ref, and 0 is returned.
+ *
+ * if back ref isn't found, *ref_ret is set to the address where it
+ * should be inserted, and -ENOENT is returned.
+ *
+ * if insert is true and there are too many inline back refs, the path
+ * points to the extent item, and -EAGAIN is returned.
+ *
+ * NOTE: inline back refs are ordered in the same way that back ref
+ *	 items in the tree are ordered.
+ */
+static noinline_for_stack
+int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 struct btrfs_extent_inline_ref **ref_ret,
+				 u64 bytenr, u64 num_bytes,
+				 u64 parent, u64 root_objectid,
+				 u64 owner, u64 offset, int insert)
+{
+	struct btrfs_key key;
+	struct extent_buffer *leaf;
+	struct btrfs_extent_item *ei;
+	struct btrfs_extent_inline_ref *iref;
+	u64 flags;
+	u64 item_size;
+	unsigned long ptr;
+	unsigned long end;
+	int extra_size;
+	int type;
+	int want;
+	int ret;
+	int err = 0;
+
+	key.objectid = bytenr;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = num_bytes;
+
+	want = extent_ref_type(parent, owner);
+	if (insert) {
+		extra_size = btrfs_extent_inline_ref_size(want);
+		path->keep_locks = 1;
+	} else
+		extra_size = -1;
+	ret = btrfs_search_slot(trans, root, &key, path, extra_size, 1);
+	if (ret < 0) {
+		err = ret;
+		goto out;
+	}
+	BUG_ON(ret);
+
+	leaf = path->nodes[0];
+	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	if (item_size < sizeof(*ei)) {
+		if (!insert) {
+			err = -ENOENT;
+			goto out;
+		}
+		ret = convert_extent_item_v0(trans, root, path, owner,
+					     extra_size);
+		if (ret < 0) {
+			err = ret;
+			goto out;
+		}
+		leaf = path->nodes[0];
+		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+	}
+#endif
+	BUG_ON(item_size < sizeof(*ei));
+
+	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+	flags = btrfs_extent_flags(leaf, ei);
+
+	ptr = (unsigned long)(ei + 1);
+	end = (unsigned long)ei + item_size;
+
+	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+		ptr += sizeof(struct btrfs_tree_block_info);
+		BUG_ON(ptr > end);
+	} else {
+		BUG_ON(!(flags & BTRFS_EXTENT_FLAG_DATA));
+	}
+
+	err = -ENOENT;
+	while (1) {
+		if (ptr >= end) {
+			WARN_ON(ptr > end);
+			break;
+		}
+		iref = (struct btrfs_extent_inline_ref *)ptr;
+		type = btrfs_extent_inline_ref_type(leaf, iref);
+		if (want < type)
+			break;
+		if (want > type) {
+			ptr += btrfs_extent_inline_ref_size(type);
+			continue;
+		}
+
+		if (type == BTRFS_EXTENT_DATA_REF_KEY) {
+			struct btrfs_extent_data_ref *dref;
+			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+			if (match_extent_data_ref(leaf, dref, root_objectid,
+						  owner, offset)) {
+				err = 0;
+				break;
+			}
+			if (hash_extent_data_ref_item(leaf, dref) <
+			    hash_extent_data_ref(root_objectid, owner, offset))
+				break;
+		} else {
+			u64 ref_offset;
+			ref_offset = btrfs_extent_inline_ref_offset(leaf, iref);
+			if (parent > 0) {
+				if (parent == ref_offset) {
+					err = 0;
+					break;
+				}
+				if (ref_offset < parent)
+					break;
+			} else {
+				if (root_objectid == ref_offset) {
+					err = 0;
+					break;
+				}
+				if (ref_offset < root_objectid)
+					break;
+			}
+		}
+		ptr += btrfs_extent_inline_ref_size(type);
+	}
+	if (err == -ENOENT && insert) {
+		if (item_size + extra_size >=
+		    BTRFS_MAX_EXTENT_ITEM_SIZE(root)) {
+			err = -EAGAIN;
+			goto out;
+		}
+		/*
+		 * To add new inline back ref, we have to make sure
+		 * there is no corresponding back ref item.
+		 * For simplicity, we just do not add new inline back
+		 * ref if there is any kind of item for this block
+		 */
+		if (find_next_key(path, &key) == 0 && key.objectid == bytenr &&
+		    key.type < BTRFS_BLOCK_GROUP_ITEM_KEY) {
+			err = -EAGAIN;
+			goto out;
+		}
+	}
+	*ref_ret = (struct btrfs_extent_inline_ref *)ptr;
+out:
+	if (insert) {
+		path->keep_locks = 0;
+		btrfs_unlock_up_safe(path, 1);
+	}
+	return err;
+}
+
+/*
+ * helper to add new inline back ref
+ */
+static noinline_for_stack
+int setup_inline_extent_backref(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				struct btrfs_path *path,
+				struct btrfs_extent_inline_ref *iref,
+				u64 parent, u64 root_objectid,
+				u64 owner, u64 offset, int refs_to_add,
+				struct btrfs_delayed_extent_op *extent_op)
+{
+	struct extent_buffer *leaf;
+	struct btrfs_extent_item *ei;
+	unsigned long ptr;
+	unsigned long end;
+	unsigned long item_offset;
+	u64 refs;
+	int size;
+	int type;
+	int ret;
+
+	leaf = path->nodes[0];
+	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+	item_offset = (unsigned long)iref - (unsigned long)ei;
+
+	type = extent_ref_type(parent, owner);
+	size = btrfs_extent_inline_ref_size(type);
+
+	ret = btrfs_extend_item(trans, root, path, size);
+	BUG_ON(ret);
+
+	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+	refs = btrfs_extent_refs(leaf, ei);
+	refs += refs_to_add;
+	btrfs_set_extent_refs(leaf, ei, refs);
+	if (extent_op)
+		__run_delayed_extent_op(extent_op, leaf, ei);
+
+	ptr = (unsigned long)ei + item_offset;
+	end = (unsigned long)ei + btrfs_item_size_nr(leaf, path->slots[0]);
+	if (ptr < end - size)
+		memmove_extent_buffer(leaf, ptr + size, ptr,
+				      end - size - ptr);
+
+	iref = (struct btrfs_extent_inline_ref *)ptr;
+	btrfs_set_extent_inline_ref_type(leaf, iref, type);
+	if (type == BTRFS_EXTENT_DATA_REF_KEY) {
+		struct btrfs_extent_data_ref *dref;
+		dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+		btrfs_set_extent_data_ref_root(leaf, dref, root_objectid);
+		btrfs_set_extent_data_ref_objectid(leaf, dref, owner);
+		btrfs_set_extent_data_ref_offset(leaf, dref, offset);
+		btrfs_set_extent_data_ref_count(leaf, dref, refs_to_add);
+	} else if (type == BTRFS_SHARED_DATA_REF_KEY) {
+		struct btrfs_shared_data_ref *sref;
+		sref = (struct btrfs_shared_data_ref *)(iref + 1);
+		btrfs_set_shared_data_ref_count(leaf, sref, refs_to_add);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
+	} else if (type == BTRFS_SHARED_BLOCK_REF_KEY) {
+		btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
+	} else {
+		btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid);
+	}
+	btrfs_mark_buffer_dirty(leaf);
+	return 0;
+}
+
+static int lookup_extent_backref(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 struct btrfs_extent_inline_ref **ref_ret,
+				 u64 bytenr, u64 num_bytes, u64 parent,
+				 u64 root_objectid, u64 owner, u64 offset)
+{
+	int ret;
+
+	ret = lookup_inline_extent_backref(trans, root, path, ref_ret,
+					   bytenr, num_bytes, parent,
+					   root_objectid, owner, offset, 0);
+	if (ret != -ENOENT)
+		return ret;
+
+	btrfs_release_path(root, path);
+	*ref_ret = NULL;
+
+	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+		ret = lookup_tree_block_ref(trans, root, path, bytenr, parent,
+					    root_objectid);
+	} else {
+		ret = lookup_extent_data_ref(trans, root, path, bytenr, parent,
+					     root_objectid, owner, offset);
+	}
+	return ret;
+}
+
+/*
+ * helper to update/remove inline back ref
+ */
+static noinline_for_stack
+int update_inline_extent_backref(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 struct btrfs_extent_inline_ref *iref,
+				 int refs_to_mod,
+				 struct btrfs_delayed_extent_op *extent_op)
+{
+	struct extent_buffer *leaf;
+	struct btrfs_extent_item *ei;
+	struct btrfs_extent_data_ref *dref = NULL;
+	struct btrfs_shared_data_ref *sref = NULL;
+	unsigned long ptr;
+	unsigned long end;
+	u32 item_size;
+	int size;
+	int type;
+	int ret;
+	u64 refs;
+
+	leaf = path->nodes[0];
+	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+	refs = btrfs_extent_refs(leaf, ei);
+	WARN_ON(refs_to_mod < 0 && refs + refs_to_mod <= 0);
+	refs += refs_to_mod;
+	btrfs_set_extent_refs(leaf, ei, refs);
+	if (extent_op)
+		__run_delayed_extent_op(extent_op, leaf, ei);
+
+	type = btrfs_extent_inline_ref_type(leaf, iref);
+
+	if (type == BTRFS_EXTENT_DATA_REF_KEY) {
+		dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+		refs = btrfs_extent_data_ref_count(leaf, dref);
+	} else if (type == BTRFS_SHARED_DATA_REF_KEY) {
+		sref = (struct btrfs_shared_data_ref *)(iref + 1);
+		refs = btrfs_shared_data_ref_count(leaf, sref);
+	} else {
+		refs = 1;
+		BUG_ON(refs_to_mod != -1);
+	}
+
+	BUG_ON(refs_to_mod < 0 && refs < -refs_to_mod);
+	refs += refs_to_mod;
+
+	if (refs > 0) {
+		if (type == BTRFS_EXTENT_DATA_REF_KEY)
+			btrfs_set_extent_data_ref_count(leaf, dref, refs);
+		else
+			btrfs_set_shared_data_ref_count(leaf, sref, refs);
+	} else {
+		size =  btrfs_extent_inline_ref_size(type);
+		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+		ptr = (unsigned long)iref;
+		end = (unsigned long)ei + item_size;
+		if (ptr + size < end)
+			memmove_extent_buffer(leaf, ptr, ptr + size,
+					      end - ptr - size);
+		item_size -= size;
+		ret = btrfs_truncate_item(trans, root, path, item_size, 1);
+		BUG_ON(ret);
+	}
+	btrfs_mark_buffer_dirty(leaf);
+	return 0;
+}
+
+static noinline_for_stack
+int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 u64 bytenr, u64 num_bytes, u64 parent,
+				 u64 root_objectid, u64 owner,
+				 u64 offset, int refs_to_add,
+				 struct btrfs_delayed_extent_op *extent_op)
+{
+	struct btrfs_extent_inline_ref *iref;
+	int ret;
+
+	ret = lookup_inline_extent_backref(trans, root, path, &iref,
+					   bytenr, num_bytes, parent,
+					   root_objectid, owner, offset, 1);
+	if (ret == 0) {
+		BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
+		ret = update_inline_extent_backref(trans, root, path, iref,
+						   refs_to_add, extent_op);
+	} else if (ret == -ENOENT) {
+		ret = setup_inline_extent_backref(trans, root, path, iref,
+						  parent, root_objectid,
+						  owner, offset, refs_to_add,
+						  extent_op);
+	}
+	return ret;
+}
+
+static int insert_extent_backref(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 u64 bytenr, u64 parent, u64 root_objectid,
+				 u64 owner, u64 offset, int refs_to_add)
+{
+	int ret;
+	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+		BUG_ON(refs_to_add != 1);
+		ret = insert_tree_block_ref(trans, root, path, bytenr,
+					    parent, root_objectid);
+	} else {
+		ret = insert_extent_data_ref(trans, root, path, bytenr,
+					     parent, root_objectid,
+					     owner, offset, refs_to_add);
+	}
+	return ret;
+}
+
+static int remove_extent_backref(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 struct btrfs_extent_inline_ref *iref,
+				 int refs_to_drop, int is_data)
+{
+	int ret;
+
+	BUG_ON(!is_data && refs_to_drop != 1);
+	if (iref) {
+		ret = update_inline_extent_backref(trans, root, path, iref,
+						   -refs_to_drop, NULL);
+	} else if (is_data) {
+		ret = remove_extent_data_ref(trans, root, path, refs_to_drop);
+	} else {
+		ret = btrfs_del_item(trans, root, path);
+	}
+	return ret;
+}
+
 #ifdef BIO_RW_DISCARD
 static void btrfs_issue_discard(struct block_device *bdev,
 				u64 start, u64 len)
@@ -686,71 +1445,40 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 #endif
 }
 
-static int __btrfs_update_extent_ref(struct btrfs_trans_handle *trans,
-				     struct btrfs_root *root, u64 bytenr,
-				     u64 num_bytes,
-				     u64 orig_parent, u64 parent,
-				     u64 orig_root, u64 ref_root,
-				     u64 orig_generation, u64 ref_generation,
-				     u64 owner_objectid)
+int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
+			 struct btrfs_root *root,
+			 u64 bytenr, u64 num_bytes, u64 parent,
+			 u64 root_objectid, u64 owner, u64 offset)
 {
 	int ret;
-	int pin = owner_objectid < BTRFS_FIRST_FREE_OBJECTID;
+	BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID &&
+	       root_objectid == BTRFS_TREE_LOG_OBJECTID);
 
-	ret = btrfs_update_delayed_ref(trans, bytenr, num_bytes,
-				       orig_parent, parent, orig_root,
-				       ref_root, orig_generation,
-				       ref_generation, owner_objectid, pin);
-	BUG_ON(ret);
+	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+		ret = btrfs_add_delayed_tree_ref(trans, bytenr, num_bytes,
+					parent, root_objectid, (int)owner,
+					BTRFS_ADD_DELAYED_REF, NULL);
+	} else {
+		ret = btrfs_add_delayed_data_ref(trans, bytenr, num_bytes,
+					parent, root_objectid, owner, offset,
+					BTRFS_ADD_DELAYED_REF, NULL);
+	}
 	return ret;
 }
 
-int btrfs_update_extent_ref(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root, u64 bytenr,
-			    u64 num_bytes, u64 orig_parent, u64 parent,
-			    u64 ref_root, u64 ref_generation,
-			    u64 owner_objectid)
-{
-	int ret;
-	if (ref_root == BTRFS_TREE_LOG_OBJECTID &&
-	    owner_objectid < BTRFS_FIRST_FREE_OBJECTID)
-		return 0;
-
-	ret = __btrfs_update_extent_ref(trans, root, bytenr, num_bytes,
-					orig_parent, parent, ref_root,
-					ref_root, ref_generation,
-					ref_generation, owner_objectid);
-	return ret;
-}
 static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
-				  struct btrfs_root *root, u64 bytenr,
-				  u64 num_bytes,
-				  u64 orig_parent, u64 parent,
-				  u64 orig_root, u64 ref_root,
-				  u64 orig_generation, u64 ref_generation,
-				  u64 owner_objectid)
-{
-	int ret;
-
-	ret = btrfs_add_delayed_ref(trans, bytenr, num_bytes, parent, ref_root,
-				    ref_generation, owner_objectid,
-				    BTRFS_ADD_DELAYED_REF, 0);
-	BUG_ON(ret);
-	return ret;
-}
-
-static noinline_for_stack int add_extent_ref(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root, u64 bytenr,
-			  u64 num_bytes, u64 parent, u64 ref_root,
-			  u64 ref_generation, u64 owner_objectid,
-			  int refs_to_add)
+				  struct btrfs_root *root,
+				  u64 bytenr, u64 num_bytes,
+				  u64 parent, u64 root_objectid,
+				  u64 owner, u64 offset, int refs_to_add,
+				  struct btrfs_delayed_extent_op *extent_op)
 {
 	struct btrfs_path *path;
-	int ret;
-	struct btrfs_key key;
-	struct extent_buffer *l;
+	struct extent_buffer *leaf;
 	struct btrfs_extent_item *item;
-	u32 refs;
+	u64 refs;
+	int ret;
+	int err = 0;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -758,43 +1486,27 @@ static noinline_for_stack int add_extent_ref(struct btrfs_trans_handle *trans,
 
 	path->reada = 1;
 	path->leave_spinning = 1;
-	key.objectid = bytenr;
-	key.type = BTRFS_EXTENT_ITEM_KEY;
-	key.offset = num_bytes;
+	/* this will setup the path even if it fails to insert the back ref */
+	ret = insert_inline_extent_backref(trans, root->fs_info->extent_root,
+					   path, bytenr, num_bytes, parent,
+					   root_objectid, owner, offset,
+					   refs_to_add, extent_op);
+	if (ret == 0)
+		goto out;
 
-	/* first find the extent item and update its reference count */
-	ret = btrfs_search_slot(trans, root->fs_info->extent_root, &key,
-				path, 0, 1);
-	if (ret < 0) {
-		btrfs_set_path_blocking(path);
-		return ret;
+	if (ret != -EAGAIN) {
+		err = ret;
+		goto out;
 	}
 
-	if (ret > 0) {
-		WARN_ON(1);
-		btrfs_free_path(path);
-		return -EIO;
-	}
-	l = path->nodes[0];
-
-	btrfs_item_key_to_cpu(l, &key, path->slots[0]);
-	if (key.objectid != bytenr) {
-		btrfs_print_leaf(root->fs_info->extent_root, path->nodes[0]);
-		printk(KERN_ERR "btrfs wanted %llu found %llu\n",
-		       (unsigned long long)bytenr,
-		       (unsigned long long)key.objectid);
-		BUG();
-	}
-	BUG_ON(key.type != BTRFS_EXTENT_ITEM_KEY);
-
-	item = btrfs_item_ptr(l, path->slots[0], struct btrfs_extent_item);
-
-	refs = btrfs_extent_refs(l, item);
-	btrfs_set_extent_refs(l, item, refs + refs_to_add);
-	btrfs_unlock_up_safe(path, 1);
-
-	btrfs_mark_buffer_dirty(path->nodes[0]);
+	leaf = path->nodes[0];
+	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+	refs = btrfs_extent_refs(leaf, item);
+	btrfs_set_extent_refs(leaf, item, refs + refs_to_add);
+	if (extent_op)
+		__run_delayed_extent_op(extent_op, leaf, item);
 
+	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(root->fs_info->extent_root, path);
 
 	path->reada = 1;
@@ -802,56 +1514,197 @@ static noinline_for_stack int add_extent_ref(struct btrfs_trans_handle *trans,
 
 	/* now insert the actual backref */
 	ret = insert_extent_backref(trans, root->fs_info->extent_root,
-				    path, bytenr, parent,
-				    ref_root, ref_generation,
-				    owner_objectid, refs_to_add);
+				    path, bytenr, parent, root_objectid,
+				    owner, offset, refs_to_add);
 	BUG_ON(ret);
+out:
 	btrfs_free_path(path);
-	return 0;
+	return err;
 }
 
-int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
-			 struct btrfs_root *root,
-			 u64 bytenr, u64 num_bytes, u64 parent,
-			 u64 ref_root, u64 ref_generation,
-			 u64 owner_objectid)
-{
-	int ret;
-	if (ref_root == BTRFS_TREE_LOG_OBJECTID &&
-	    owner_objectid < BTRFS_FIRST_FREE_OBJECTID)
-		return 0;
-
-	ret = __btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0, parent,
-				     0, ref_root, 0, ref_generation,
-				     owner_objectid);
-	return ret;
-}
-
-static int drop_delayed_ref(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root,
-					struct btrfs_delayed_ref_node *node)
+static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				struct btrfs_delayed_ref_node *node,
+				struct btrfs_delayed_extent_op *extent_op,
+				int insert_reserved)
 {
 	int ret = 0;
-	struct btrfs_delayed_ref *ref = btrfs_delayed_node_to_ref(node);
+	struct btrfs_delayed_data_ref *ref;
+	struct btrfs_key ins;
+	u64 parent = 0;
+	u64 ref_root = 0;
+	u64 flags = 0;
 
-	BUG_ON(node->ref_mod == 0);
-	ret = __btrfs_free_extent(trans, root, node->bytenr, node->num_bytes,
-				  node->parent, ref->root, ref->generation,
-				  ref->owner_objectid, ref->pin, node->ref_mod);
+	ins.objectid = node->bytenr;
+	ins.offset = node->num_bytes;
+	ins.type = BTRFS_EXTENT_ITEM_KEY;
 
+	ref = btrfs_delayed_node_to_data_ref(node);
+	if (node->type == BTRFS_SHARED_DATA_REF_KEY)
+		parent = ref->parent;
+	else
+		ref_root = ref->root;
+
+	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
+		if (extent_op) {
+			BUG_ON(extent_op->update_key);
+			flags |= extent_op->flags_to_set;
+		}
+		ret = alloc_reserved_file_extent(trans, root,
+						 parent, ref_root, flags,
+						 ref->objectid, ref->offset,
+						 &ins, node->ref_mod);
+		update_reserved_extents(root, ins.objectid, ins.offset, 0);
+	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
+		ret = __btrfs_inc_extent_ref(trans, root, node->bytenr,
+					     node->num_bytes, parent,
+					     ref_root, ref->objectid,
+					     ref->offset, node->ref_mod,
+					     extent_op);
+	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
+		ret = __btrfs_free_extent(trans, root, node->bytenr,
+					  node->num_bytes, parent,
+					  ref_root, ref->objectid,
+					  ref->offset, node->ref_mod,
+					  extent_op);
+	} else {
+		BUG();
+	}
 	return ret;
 }
 
+static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
+				    struct extent_buffer *leaf,
+				    struct btrfs_extent_item *ei)
+{
+	u64 flags = btrfs_extent_flags(leaf, ei);
+	if (extent_op->update_flags) {
+		flags |= extent_op->flags_to_set;
+		btrfs_set_extent_flags(leaf, ei, flags);
+	}
+
+	if (extent_op->update_key) {
+		struct btrfs_tree_block_info *bi;
+		BUG_ON(!(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK));
+		bi = (struct btrfs_tree_block_info *)(ei + 1);
+		btrfs_set_tree_block_key(leaf, bi, &extent_op->key);
+	}
+}
+
+static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_delayed_ref_node *node,
+				 struct btrfs_delayed_extent_op *extent_op)
+{
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	struct btrfs_extent_item *ei;
+	struct extent_buffer *leaf;
+	u32 item_size;
+	int ret;
+	int err = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = node->bytenr;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = node->num_bytes;
+
+	path->reada = 1;
+	path->leave_spinning = 1;
+	ret = btrfs_search_slot(trans, root->fs_info->extent_root, &key,
+				path, 0, 1);
+	if (ret < 0) {
+		err = ret;
+		goto out;
+	}
+	if (ret > 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	leaf = path->nodes[0];
+	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	if (item_size < sizeof(*ei)) {
+		ret = convert_extent_item_v0(trans, root->fs_info->extent_root,
+					     path, (u64)-1, 0);
+		if (ret < 0) {
+			err = ret;
+			goto out;
+		}
+		leaf = path->nodes[0];
+		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+	}
+#endif
+	BUG_ON(item_size < sizeof(*ei));
+	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+	__run_delayed_extent_op(extent_op, leaf, ei);
+
+	btrfs_mark_buffer_dirty(leaf);
+out:
+	btrfs_free_path(path);
+	return err;
+}
+
+static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				struct btrfs_delayed_ref_node *node,
+				struct btrfs_delayed_extent_op *extent_op,
+				int insert_reserved)
+{
+	int ret = 0;
+	struct btrfs_delayed_tree_ref *ref;
+	struct btrfs_key ins;
+	u64 parent = 0;
+	u64 ref_root = 0;
+
+	ins.objectid = node->bytenr;
+	ins.offset = node->num_bytes;
+	ins.type = BTRFS_EXTENT_ITEM_KEY;
+
+	ref = btrfs_delayed_node_to_tree_ref(node);
+	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY)
+		parent = ref->parent;
+	else
+		ref_root = ref->root;
+
+	BUG_ON(node->ref_mod != 1);
+	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
+		BUG_ON(!extent_op || !extent_op->update_flags ||
+		       !extent_op->update_key);
+		ret = alloc_reserved_tree_block(trans, root,
+						parent, ref_root,
+						extent_op->flags_to_set,
+						&extent_op->key,
+						ref->level, &ins);
+		update_reserved_extents(root, ins.objectid, ins.offset, 0);
+	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
+		ret = __btrfs_inc_extent_ref(trans, root, node->bytenr,
+					     node->num_bytes, parent, ref_root,
+					     ref->level, 0, 1, extent_op);
+	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
+		ret = __btrfs_free_extent(trans, root, node->bytenr,
+					  node->num_bytes, parent, ref_root,
+					  ref->level, 0, 1, extent_op);
+	} else {
+		BUG();
+	}
+	return ret;
+}
+
+
 /* helper function to actually process a single delayed ref entry */
-static noinline int run_one_delayed_ref(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root,
-					struct btrfs_delayed_ref_node *node,
-					int insert_reserved)
+static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root,
+			       struct btrfs_delayed_ref_node *node,
+			       struct btrfs_delayed_extent_op *extent_op,
+			       int insert_reserved)
 {
 	int ret;
-	struct btrfs_delayed_ref *ref;
-
-	if (node->parent == (u64)-1) {
+	if (btrfs_delayed_ref_is_head(node)) {
 		struct btrfs_delayed_ref_head *head;
 		/*
 		 * we've hit the end of the chain and we were supposed
@@ -859,44 +1712,35 @@ static noinline int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 		 * deleted before we ever needed to insert it, so all
 		 * we have to do is clean up the accounting
 		 */
+		BUG_ON(extent_op);
+		head = btrfs_delayed_node_to_head(node);
 		if (insert_reserved) {
+			if (head->is_data) {
+				ret = btrfs_del_csums(trans, root,
+						      node->bytenr,
+						      node->num_bytes);
+				BUG_ON(ret);
+			}
+			btrfs_update_pinned_extents(root, node->bytenr,
+						    node->num_bytes, 1);
 			update_reserved_extents(root, node->bytenr,
 						node->num_bytes, 0);
 		}
-		head = btrfs_delayed_node_to_head(node);
 		mutex_unlock(&head->mutex);
 		return 0;
 	}
 
-	ref = btrfs_delayed_node_to_ref(node);
-	if (ref->action == BTRFS_ADD_DELAYED_REF) {
-		if (insert_reserved) {
-			struct btrfs_key ins;
-
-			ins.objectid = node->bytenr;
-			ins.offset = node->num_bytes;
-			ins.type = BTRFS_EXTENT_ITEM_KEY;
-
-			/* record the full extent allocation */
-			ret = __btrfs_alloc_reserved_extent(trans, root,
-					node->parent, ref->root,
-					ref->generation, ref->owner_objectid,
-					&ins, node->ref_mod);
-			update_reserved_extents(root, node->bytenr,
-						node->num_bytes, 0);
-		} else {
-			/* just add one backref */
-			ret = add_extent_ref(trans, root, node->bytenr,
-				     node->num_bytes,
-				     node->parent, ref->root, ref->generation,
-				     ref->owner_objectid, node->ref_mod);
-		}
-		BUG_ON(ret);
-	} else if (ref->action == BTRFS_DROP_DELAYED_REF) {
-		WARN_ON(insert_reserved);
-		ret = drop_delayed_ref(trans, root, node);
-	}
-	return 0;
+	if (node->type == BTRFS_TREE_BLOCK_REF_KEY ||
+	    node->type == BTRFS_SHARED_BLOCK_REF_KEY)
+		ret = run_delayed_tree_ref(trans, root, node, extent_op,
+					   insert_reserved);
+	else if (node->type == BTRFS_EXTENT_DATA_REF_KEY ||
+		 node->type == BTRFS_SHARED_DATA_REF_KEY)
+		ret = run_delayed_data_ref(trans, root, node, extent_op,
+					   insert_reserved);
+	else
+		BUG();
+	return ret;
 }
 
 static noinline struct btrfs_delayed_ref_node *
@@ -919,7 +1763,7 @@ again:
 				rb_node);
 		if (ref->bytenr != head->node.bytenr)
 			break;
-		if (btrfs_delayed_node_to_ref(ref)->action == action)
+		if (ref->action == action)
 			return ref;
 		node = rb_prev(node);
 	}
@@ -937,6 +1781,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_delayed_ref_node *ref;
 	struct btrfs_delayed_ref_head *locked_ref = NULL;
+	struct btrfs_delayed_extent_op *extent_op;
 	int ret;
 	int count = 0;
 	int must_insert_reserved = 0;
@@ -975,6 +1820,9 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 		must_insert_reserved = locked_ref->must_insert_reserved;
 		locked_ref->must_insert_reserved = 0;
 
+		extent_op = locked_ref->extent_op;
+		locked_ref->extent_op = NULL;
+
 		/*
 		 * locked_ref is the head node, so we have to go one
 		 * node back for any delayed ref updates
@@ -986,6 +1834,25 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 			 * so that any accounting fixes can happen
 			 */
 			ref = &locked_ref->node;
+
+			if (extent_op && must_insert_reserved) {
+				kfree(extent_op);
+				extent_op = NULL;
+			}
+
+			if (extent_op) {
+				spin_unlock(&delayed_refs->lock);
+
+				ret = run_delayed_extent_op(trans, root,
+							    ref, extent_op);
+				BUG_ON(ret);
+				kfree(extent_op);
+
+				cond_resched();
+				spin_lock(&delayed_refs->lock);
+				continue;
+			}
+
 			list_del_init(&locked_ref->cluster);
 			locked_ref = NULL;
 		}
@@ -993,14 +1860,17 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 		ref->in_tree = 0;
 		rb_erase(&ref->rb_node, &delayed_refs->root);
 		delayed_refs->num_entries--;
+
 		spin_unlock(&delayed_refs->lock);
 
-		ret = run_one_delayed_ref(trans, root, ref,
+		ret = run_one_delayed_ref(trans, root, ref, extent_op,
 					  must_insert_reserved);
 		BUG_ON(ret);
-		btrfs_put_delayed_ref(ref);
 
+		btrfs_put_delayed_ref(ref);
+		kfree(extent_op);
 		count++;
+
 		cond_resched();
 		spin_lock(&delayed_refs->lock);
 	}
@@ -1095,25 +1965,112 @@ out:
 	return 0;
 }
 
-int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root, u64 objectid, u64 bytenr)
+int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				u64 bytenr, u64 num_bytes, u64 flags,
+				int is_data)
+{
+	struct btrfs_delayed_extent_op *extent_op;
+	int ret;
+
+	extent_op = kmalloc(sizeof(*extent_op), GFP_NOFS);
+	if (!extent_op)
+		return -ENOMEM;
+
+	extent_op->flags_to_set = flags;
+	extent_op->update_flags = 1;
+	extent_op->update_key = 0;
+	extent_op->is_data = is_data ? 1 : 0;
+
+	ret = btrfs_add_delayed_extent_op(trans, bytenr, num_bytes, extent_op);
+	if (ret)
+		kfree(extent_op);
+	return ret;
+}
+
+static noinline int check_delayed_ref(struct btrfs_trans_handle *trans,
+				      struct btrfs_root *root,
+				      struct btrfs_path *path,
+				      u64 objectid, u64 offset, u64 bytenr)
+{
+	struct btrfs_delayed_ref_head *head;
+	struct btrfs_delayed_ref_node *ref;
+	struct btrfs_delayed_data_ref *data_ref;
+	struct btrfs_delayed_ref_root *delayed_refs;
+	struct rb_node *node;
+	int ret = 0;
+
+	ret = -ENOENT;
+	delayed_refs = &trans->transaction->delayed_refs;
+	spin_lock(&delayed_refs->lock);
+	head = btrfs_find_delayed_ref_head(trans, bytenr);
+	if (!head)
+		goto out;
+
+	if (!mutex_trylock(&head->mutex)) {
+		atomic_inc(&head->node.refs);
+		spin_unlock(&delayed_refs->lock);
+
+		btrfs_release_path(root->fs_info->extent_root, path);
+
+		mutex_lock(&head->mutex);
+		mutex_unlock(&head->mutex);
+		btrfs_put_delayed_ref(&head->node);
+		return -EAGAIN;
+	}
+
+	node = rb_prev(&head->node.rb_node);
+	if (!node)
+		goto out_unlock;
+
+	ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
+
+	if (ref->bytenr != bytenr)
+		goto out_unlock;
+
+	ret = 1;
+	if (ref->type != BTRFS_EXTENT_DATA_REF_KEY)
+		goto out_unlock;
+
+	data_ref = btrfs_delayed_node_to_data_ref(ref);
+
+	node = rb_prev(node);
+	if (node) {
+		ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
+		if (ref->bytenr == bytenr)
+			goto out_unlock;
+	}
+
+	if (data_ref->root != root->root_key.objectid ||
+	    data_ref->objectid != objectid || data_ref->offset != offset)
+		goto out_unlock;
+
+	ret = 0;
+out_unlock:
+	mutex_unlock(&head->mutex);
+out:
+	spin_unlock(&delayed_refs->lock);
+	return ret;
+}
+
+static noinline int check_committed_ref(struct btrfs_trans_handle *trans,
+					struct btrfs_root *root,
+					struct btrfs_path *path,
+					u64 objectid, u64 offset, u64 bytenr)
 {
 	struct btrfs_root *extent_root = root->fs_info->extent_root;
-	struct btrfs_path *path;
 	struct extent_buffer *leaf;
-	struct btrfs_extent_ref *ref_item;
+	struct btrfs_extent_data_ref *ref;
+	struct btrfs_extent_inline_ref *iref;
+	struct btrfs_extent_item *ei;
 	struct btrfs_key key;
-	struct btrfs_key found_key;
-	u64 ref_root;
-	u64 last_snapshot;
-	u32 nritems;
+	u32 item_size;
 	int ret;
 
 	key.objectid = bytenr;
 	key.offset = (u64)-1;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
 
-	path = btrfs_alloc_path();
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
@@ -1125,55 +2082,83 @@ int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
 
 	path->slots[0]--;
 	leaf = path->nodes[0];
-	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 
-	if (found_key.objectid != bytenr ||
-	    found_key.type != BTRFS_EXTENT_ITEM_KEY)
+	if (key.objectid != bytenr || key.type != BTRFS_EXTENT_ITEM_KEY)
 		goto out;
 
-	last_snapshot = btrfs_root_last_snapshot(&root->root_item);
-	while (1) {
-		leaf = path->nodes[0];
-		nritems = btrfs_header_nritems(leaf);
-		if (path->slots[0] >= nritems) {
-			ret = btrfs_next_leaf(extent_root, path);
-			if (ret < 0)
-				goto out;
-			if (ret == 0)
-				continue;
-			break;
-		}
-		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-		if (found_key.objectid != bytenr)
-			break;
-
-		if (found_key.type != BTRFS_EXTENT_REF_KEY) {
-			path->slots[0]++;
-			continue;
-		}
-
-		ref_item = btrfs_item_ptr(leaf, path->slots[0],
-					  struct btrfs_extent_ref);
-		ref_root = btrfs_ref_root(leaf, ref_item);
-		if ((ref_root != root->root_key.objectid &&
-		     ref_root != BTRFS_TREE_LOG_OBJECTID) ||
-		     objectid != btrfs_ref_objectid(leaf, ref_item)) {
-			ret = 1;
-			goto out;
-		}
-		if (btrfs_ref_generation(leaf, ref_item) <= last_snapshot) {
-			ret = 1;
-			goto out;
-		}
-
-		path->slots[0]++;
+	ret = 1;
+	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	if (item_size < sizeof(*ei)) {
+		WARN_ON(item_size != sizeof(struct btrfs_extent_item_v0));
+		goto out;
 	}
+#endif
+	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+
+	if (item_size != sizeof(*ei) +
+	    btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY))
+		goto out;
+
+	if (btrfs_extent_generation(leaf, ei) <=
+	    btrfs_root_last_snapshot(&root->root_item))
+		goto out;
+
+	iref = (struct btrfs_extent_inline_ref *)(ei + 1);
+	if (btrfs_extent_inline_ref_type(leaf, iref) !=
+	    BTRFS_EXTENT_DATA_REF_KEY)
+		goto out;
+
+	ref = (struct btrfs_extent_data_ref *)(&iref->offset);
+	if (btrfs_extent_refs(leaf, ei) !=
+	    btrfs_extent_data_ref_count(leaf, ref) ||
+	    btrfs_extent_data_ref_root(leaf, ref) !=
+	    root->root_key.objectid ||
+	    btrfs_extent_data_ref_objectid(leaf, ref) != objectid ||
+	    btrfs_extent_data_ref_offset(leaf, ref) != offset)
+		goto out;
+
 	ret = 0;
+out:
+	return ret;
+}
+
+int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
+			  struct btrfs_root *root,
+			  u64 objectid, u64 offset, u64 bytenr)
+{
+	struct btrfs_path *path;
+	int ret;
+	int ret2;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOENT;
+
+	do {
+		ret = check_committed_ref(trans, root, path, objectid,
+					  offset, bytenr);
+		if (ret && ret != -ENOENT)
+			goto out;
+
+		ret2 = check_delayed_ref(trans, root, path, objectid,
+					 offset, bytenr);
+	} while (ret2 == -EAGAIN);
+
+	if (ret2 && ret2 != -ENOENT) {
+		ret = ret2;
+		goto out;
+	}
+
+	if (ret != -ENOENT || ret2 != -ENOENT)
+		ret = 0;
 out:
 	btrfs_free_path(path);
 	return ret;
 }
 
+#if 0
 int btrfs_cache_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		    struct extent_buffer *buf, u32 nr_extents)
 {
@@ -1291,62 +2276,44 @@ static int refsort_cmp(const void *a_void, const void *b_void)
 		return 1;
 	return 0;
 }
+#endif
 
-
-noinline int btrfs_inc_ref(struct btrfs_trans_handle *trans,
+static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
-			   struct extent_buffer *orig_buf,
-			   struct extent_buffer *buf, u32 *nr_extents)
+			   struct extent_buffer *buf,
+			   int full_backref, int inc)
 {
 	u64 bytenr;
+	u64 num_bytes;
+	u64 parent;
 	u64 ref_root;
-	u64 orig_root;
-	u64 ref_generation;
-	u64 orig_generation;
-	struct refsort *sorted;
 	u32 nritems;
-	u32 nr_file_extents = 0;
 	struct btrfs_key key;
 	struct btrfs_file_extent_item *fi;
 	int i;
 	int level;
 	int ret = 0;
-	int faili = 0;
-	int refi = 0;
-	int slot;
 	int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *,
-			    u64, u64, u64, u64, u64, u64, u64, u64, u64);
+			    u64, u64, u64, u64, u64, u64);
 
 	ref_root = btrfs_header_owner(buf);
-	ref_generation = btrfs_header_generation(buf);
-	orig_root = btrfs_header_owner(orig_buf);
-	orig_generation = btrfs_header_generation(orig_buf);
-
 	nritems = btrfs_header_nritems(buf);
 	level = btrfs_header_level(buf);
 
-	sorted = kmalloc(sizeof(struct refsort) * nritems, GFP_NOFS);
-	BUG_ON(!sorted);
+	if (!root->ref_cows && level == 0)
+		return 0;
 
-	if (root->ref_cows) {
-		process_func = __btrfs_inc_extent_ref;
-	} else {
-		if (level == 0 &&
-		    root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
-			goto out;
-		if (level != 0 &&
-		    root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID)
-			goto out;
-		process_func = __btrfs_update_extent_ref;
-	}
+	if (inc)
+		process_func = btrfs_inc_extent_ref;
+	else
+		process_func = btrfs_free_extent;
+
+	if (full_backref)
+		parent = buf->start;
+	else
+		parent = 0;
 
-	/*
-	 * we make two passes through the items.  In the first pass we
-	 * only record the byte number and slot.  Then we sort based on
-	 * byte number and do the actual work based on the sorted results
-	 */
 	for (i = 0; i < nritems; i++) {
-		cond_resched();
 		if (level == 0) {
 			btrfs_item_key_to_cpu(buf, &key, i);
 			if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
@@ -1360,151 +2327,38 @@ noinline int btrfs_inc_ref(struct btrfs_trans_handle *trans,
 			if (bytenr == 0)
 				continue;
 
-			nr_file_extents++;
-			sorted[refi].bytenr = bytenr;
-			sorted[refi].slot = i;
-			refi++;
+			num_bytes = btrfs_file_extent_disk_num_bytes(buf, fi);
+			key.offset -= btrfs_file_extent_offset(buf, fi);
+			ret = process_func(trans, root, bytenr, num_bytes,
+					   parent, ref_root, key.objectid,
+					   key.offset);
+			if (ret)
+				goto fail;
 		} else {
 			bytenr = btrfs_node_blockptr(buf, i);
-			sorted[refi].bytenr = bytenr;
-			sorted[refi].slot = i;
-			refi++;
-		}
-	}
-	/*
-	 * if refi == 0, we didn't actually put anything into the sorted
-	 * array and we're done
-	 */
-	if (refi == 0)
-		goto out;
-
-	sort(sorted, refi, sizeof(struct refsort), refsort_cmp, NULL);
-
-	for (i = 0; i < refi; i++) {
-		cond_resched();
-		slot = sorted[i].slot;
-		bytenr = sorted[i].bytenr;
-
-		if (level == 0) {
-			btrfs_item_key_to_cpu(buf, &key, slot);
-			fi = btrfs_item_ptr(buf, slot,
-					    struct btrfs_file_extent_item);
-
-			bytenr = btrfs_file_extent_disk_bytenr(buf, fi);
-			if (bytenr == 0)
-				continue;
-
-			ret = process_func(trans, root, bytenr,
-				   btrfs_file_extent_disk_num_bytes(buf, fi),
-				   orig_buf->start, buf->start,
-				   orig_root, ref_root,
-				   orig_generation, ref_generation,
-				   key.objectid);
-
-			if (ret) {
-				faili = slot;
-				WARN_ON(1);
+			num_bytes = btrfs_level_size(root, level - 1);
+			ret = process_func(trans, root, bytenr, num_bytes,
+					   parent, ref_root, level - 1, 0);
+			if (ret)
 				goto fail;
-			}
-		} else {
-			ret = process_func(trans, root, bytenr, buf->len,
-					   orig_buf->start, buf->start,
-					   orig_root, ref_root,
-					   orig_generation, ref_generation,
-					   level - 1);
-			if (ret) {
-				faili = slot;
-				WARN_ON(1);
-				goto fail;
-			}
 		}
 	}
-out:
-	kfree(sorted);
-	if (nr_extents) {
-		if (level == 0)
-			*nr_extents = nr_file_extents;
-		else
-			*nr_extents = nritems;
-	}
 	return 0;
 fail:
-	kfree(sorted);
-	WARN_ON(1);
+	BUG();
 	return ret;
 }
 
-int btrfs_update_ref(struct btrfs_trans_handle *trans,
-		     struct btrfs_root *root, struct extent_buffer *orig_buf,
-		     struct extent_buffer *buf, int start_slot, int nr)
-
+int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		  struct extent_buffer *buf, int full_backref)
 {
-	u64 bytenr;
-	u64 ref_root;
-	u64 orig_root;
-	u64 ref_generation;
-	u64 orig_generation;
-	struct btrfs_key key;
-	struct btrfs_file_extent_item *fi;
-	int i;
-	int ret;
-	int slot;
-	int level;
+	return __btrfs_mod_ref(trans, root, buf, full_backref, 1);
+}
 
-	BUG_ON(start_slot < 0);
-	BUG_ON(start_slot + nr > btrfs_header_nritems(buf));
-
-	ref_root = btrfs_header_owner(buf);
-	ref_generation = btrfs_header_generation(buf);
-	orig_root = btrfs_header_owner(orig_buf);
-	orig_generation = btrfs_header_generation(orig_buf);
-	level = btrfs_header_level(buf);
-
-	if (!root->ref_cows) {
-		if (level == 0 &&
-		    root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
-			return 0;
-		if (level != 0 &&
-		    root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID)
-			return 0;
-	}
-
-	for (i = 0, slot = start_slot; i < nr; i++, slot++) {
-		cond_resched();
-		if (level == 0) {
-			btrfs_item_key_to_cpu(buf, &key, slot);
-			if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
-				continue;
-			fi = btrfs_item_ptr(buf, slot,
-					    struct btrfs_file_extent_item);
-			if (btrfs_file_extent_type(buf, fi) ==
-			    BTRFS_FILE_EXTENT_INLINE)
-				continue;
-			bytenr = btrfs_file_extent_disk_bytenr(buf, fi);
-			if (bytenr == 0)
-				continue;
-			ret = __btrfs_update_extent_ref(trans, root, bytenr,
-				    btrfs_file_extent_disk_num_bytes(buf, fi),
-				    orig_buf->start, buf->start,
-				    orig_root, ref_root, orig_generation,
-				    ref_generation, key.objectid);
-			if (ret)
-				goto fail;
-		} else {
-			bytenr = btrfs_node_blockptr(buf, slot);
-			ret = __btrfs_update_extent_ref(trans, root, bytenr,
-					    buf->len, orig_buf->start,
-					    buf->start, orig_root, ref_root,
-					    orig_generation, ref_generation,
-					    level - 1);
-			if (ret)
-				goto fail;
-		}
-	}
-	return 0;
-fail:
-	WARN_ON(1);
-	return -1;
+int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		  struct extent_buffer *buf, int full_backref)
+{
+	return __btrfs_mod_ref(trans, root, buf, full_backref, 0);
 }
 
 static int write_one_cache_group(struct btrfs_trans_handle *trans,
@@ -2007,6 +2861,24 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 	u64 old_val;
 	u64 byte_in_group;
 
+	/* block accounting for super block */
+	spin_lock(&info->delalloc_lock);
+	old_val = btrfs_super_bytes_used(&info->super_copy);
+	if (alloc)
+		old_val += num_bytes;
+	else
+		old_val -= num_bytes;
+	btrfs_set_super_bytes_used(&info->super_copy, old_val);
+
+	/* block accounting for root item */
+	old_val = btrfs_root_used(&root->root_item);
+	if (alloc)
+		old_val += num_bytes;
+	else
+		old_val -= num_bytes;
+	btrfs_set_root_used(&root->root_item, old_val);
+	spin_unlock(&info->delalloc_lock);
+
 	while (total) {
 		cache = btrfs_lookup_block_group(info, bytenr);
 		if (!cache)
@@ -2216,8 +3088,6 @@ static int pin_down_bytes(struct btrfs_trans_handle *trans,
 		u64 header_owner = btrfs_header_owner(buf);
 		u64 header_transid = btrfs_header_generation(buf);
 		if (header_owner != BTRFS_TREE_LOG_OBJECTID &&
-		    header_owner != BTRFS_TREE_RELOC_OBJECTID &&
-		    header_owner != BTRFS_DATA_RELOC_TREE_OBJECTID &&
 		    header_transid == trans->transid &&
 		    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
 			*must_clean = buf;
@@ -2235,63 +3105,77 @@ pinit:
 	return 0;
 }
 
-/*
- * remove an extent from the root, returns 0 on success
- */
-static int __free_extent(struct btrfs_trans_handle *trans,
-			 struct btrfs_root *root,
-			 u64 bytenr, u64 num_bytes, u64 parent,
-			 u64 root_objectid, u64 ref_generation,
-			 u64 owner_objectid, int pin, int mark_free,
-			 int refs_to_drop)
+
+static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				u64 bytenr, u64 num_bytes, u64 parent,
+				u64 root_objectid, u64 owner_objectid,
+				u64 owner_offset, int refs_to_drop,
+				struct btrfs_delayed_extent_op *extent_op)
 {
-	struct btrfs_path *path;
 	struct btrfs_key key;
+	struct btrfs_path *path;
 	struct btrfs_fs_info *info = root->fs_info;
 	struct btrfs_root *extent_root = info->extent_root;
 	struct extent_buffer *leaf;
+	struct btrfs_extent_item *ei;
+	struct btrfs_extent_inline_ref *iref;
 	int ret;
+	int is_data;
 	int extent_slot = 0;
 	int found_extent = 0;
 	int num_to_del = 1;
-	struct btrfs_extent_item *ei;
-	u32 refs;
+	u32 item_size;
+	u64 refs;
 
-	key.objectid = bytenr;
-	btrfs_set_key_type(&key, BTRFS_EXTENT_ITEM_KEY);
-	key.offset = num_bytes;
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
 	path->reada = 1;
 	path->leave_spinning = 1;
-	ret = lookup_extent_backref(trans, extent_root, path,
-				    bytenr, parent, root_objectid,
-				    ref_generation, owner_objectid, 1);
+
+	is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID;
+	BUG_ON(!is_data && refs_to_drop != 1);
+
+	ret = lookup_extent_backref(trans, extent_root, path, &iref,
+				    bytenr, num_bytes, parent,
+				    root_objectid, owner_objectid,
+				    owner_offset);
 	if (ret == 0) {
-		struct btrfs_key found_key;
 		extent_slot = path->slots[0];
-		while (extent_slot > 0) {
-			extent_slot--;
-			btrfs_item_key_to_cpu(path->nodes[0], &found_key,
+		while (extent_slot >= 0) {
+			btrfs_item_key_to_cpu(path->nodes[0], &key,
 					      extent_slot);
-			if (found_key.objectid != bytenr)
+			if (key.objectid != bytenr)
 				break;
-			if (found_key.type == BTRFS_EXTENT_ITEM_KEY &&
-			    found_key.offset == num_bytes) {
+			if (key.type == BTRFS_EXTENT_ITEM_KEY &&
+			    key.offset == num_bytes) {
 				found_extent = 1;
 				break;
 			}
 			if (path->slots[0] - extent_slot > 5)
 				break;
+			extent_slot--;
 		}
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+		item_size = btrfs_item_size_nr(path->nodes[0], extent_slot);
+		if (found_extent && item_size < sizeof(*ei))
+			found_extent = 0;
+#endif
 		if (!found_extent) {
+			BUG_ON(iref);
 			ret = remove_extent_backref(trans, extent_root, path,
-						    refs_to_drop);
+						    NULL, refs_to_drop,
+						    is_data);
 			BUG_ON(ret);
 			btrfs_release_path(extent_root, path);
 			path->leave_spinning = 1;
+
+			key.objectid = bytenr;
+			key.type = BTRFS_EXTENT_ITEM_KEY;
+			key.offset = num_bytes;
+
 			ret = btrfs_search_slot(trans, extent_root,
 						&key, path, -1, 1);
 			if (ret) {
@@ -2307,82 +3191,98 @@ static int __free_extent(struct btrfs_trans_handle *trans,
 		btrfs_print_leaf(extent_root, path->nodes[0]);
 		WARN_ON(1);
 		printk(KERN_ERR "btrfs unable to find ref byte nr %llu "
-		       "parent %llu root %llu gen %llu owner %llu\n",
+		       "parent %llu root %llu  owner %llu offset %llu\n",
 		       (unsigned long long)bytenr,
 		       (unsigned long long)parent,
 		       (unsigned long long)root_objectid,
-		       (unsigned long long)ref_generation,
-		       (unsigned long long)owner_objectid);
+		       (unsigned long long)owner_objectid,
+		       (unsigned long long)owner_offset);
 	}
 
 	leaf = path->nodes[0];
+	item_size = btrfs_item_size_nr(leaf, extent_slot);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	if (item_size < sizeof(*ei)) {
+		BUG_ON(found_extent || extent_slot != path->slots[0]);
+		ret = convert_extent_item_v0(trans, extent_root, path,
+					     owner_objectid, 0);
+		BUG_ON(ret < 0);
+
+		btrfs_release_path(extent_root, path);
+		path->leave_spinning = 1;
+
+		key.objectid = bytenr;
+		key.type = BTRFS_EXTENT_ITEM_KEY;
+		key.offset = num_bytes;
+
+		ret = btrfs_search_slot(trans, extent_root, &key, path,
+					-1, 1);
+		if (ret) {
+			printk(KERN_ERR "umm, got %d back from search"
+			       ", was looking for %llu\n", ret,
+			       (unsigned long long)bytenr);
+			btrfs_print_leaf(extent_root, path->nodes[0]);
+		}
+		BUG_ON(ret);
+		extent_slot = path->slots[0];
+		leaf = path->nodes[0];
+		item_size = btrfs_item_size_nr(leaf, extent_slot);
+	}
+#endif
+	BUG_ON(item_size < sizeof(*ei));
 	ei = btrfs_item_ptr(leaf, extent_slot,
 			    struct btrfs_extent_item);
-	refs = btrfs_extent_refs(leaf, ei);
-
-	/*
-	 * we're not allowed to delete the extent item if there
-	 * are other delayed ref updates pending
-	 */
-
-	BUG_ON(refs < refs_to_drop);
-	refs -= refs_to_drop;
-	btrfs_set_extent_refs(leaf, ei, refs);
-	btrfs_mark_buffer_dirty(leaf);
-
-	if (refs == 0 && found_extent &&
-	    path->slots[0] == extent_slot + 1) {
-		struct btrfs_extent_ref *ref;
-		ref = btrfs_item_ptr(leaf, path->slots[0],
-				     struct btrfs_extent_ref);
-		BUG_ON(btrfs_ref_num_refs(leaf, ref) != refs_to_drop);
-		/* if the back ref and the extent are next to each other
-		 * they get deleted below in one shot
-		 */
-		path->slots[0] = extent_slot;
-		num_to_del = 2;
-	} else if (found_extent) {
-		/* otherwise delete the extent back ref */
-		ret = remove_extent_backref(trans, extent_root, path,
-					    refs_to_drop);
-		BUG_ON(ret);
-		/* if refs are 0, we need to setup the path for deletion */
-		if (refs == 0) {
-			btrfs_release_path(extent_root, path);
-			path->leave_spinning = 1;
-			ret = btrfs_search_slot(trans, extent_root, &key, path,
-						-1, 1);
-			BUG_ON(ret);
-		}
+	if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID) {
+		struct btrfs_tree_block_info *bi;
+		BUG_ON(item_size < sizeof(*ei) + sizeof(*bi));
+		bi = (struct btrfs_tree_block_info *)(ei + 1);
+		WARN_ON(owner_objectid != btrfs_tree_block_level(leaf, bi));
 	}
 
-	if (refs == 0) {
-		u64 super_used;
-		u64 root_used;
+	refs = btrfs_extent_refs(leaf, ei);
+	BUG_ON(refs < refs_to_drop);
+	refs -= refs_to_drop;
+
+	if (refs > 0) {
+		if (extent_op)
+			__run_delayed_extent_op(extent_op, leaf, ei);
+		/*
+		 * In the case of inline back ref, reference count will
+		 * be updated by remove_extent_backref
+		 */
+		if (iref) {
+			BUG_ON(!found_extent);
+		} else {
+			btrfs_set_extent_refs(leaf, ei, refs);
+			btrfs_mark_buffer_dirty(leaf);
+		}
+		if (found_extent) {
+			ret = remove_extent_backref(trans, extent_root, path,
+						    iref, refs_to_drop,
+						    is_data);
+			BUG_ON(ret);
+		}
+	} else {
+		int mark_free = 0;
 		struct extent_buffer *must_clean = NULL;
 
-		if (pin) {
-			ret = pin_down_bytes(trans, root, path,
-				bytenr, num_bytes,
-				owner_objectid >= BTRFS_FIRST_FREE_OBJECTID,
-				&must_clean);
-			if (ret > 0)
-				mark_free = 1;
-			BUG_ON(ret < 0);
+		if (found_extent) {
+			BUG_ON(is_data && refs_to_drop !=
+			       extent_data_ref_count(root, path, iref));
+			if (iref) {
+				BUG_ON(path->slots[0] != extent_slot);
+			} else {
+				BUG_ON(path->slots[0] != extent_slot + 1);
+				path->slots[0] = extent_slot;
+				num_to_del = 2;
+			}
 		}
 
-		/* block accounting for super block */
-		spin_lock(&info->delalloc_lock);
-		super_used = btrfs_super_bytes_used(&info->super_copy);
-		btrfs_set_super_bytes_used(&info->super_copy,
-					   super_used - num_bytes);
-
-		/* block accounting for root item */
-		root_used = btrfs_root_used(&root->root_item);
-		btrfs_set_root_used(&root->root_item,
-					   root_used - num_bytes);
-		spin_unlock(&info->delalloc_lock);
-
+		ret = pin_down_bytes(trans, root, path, bytenr,
+				     num_bytes, is_data, &must_clean);
+		if (ret > 0)
+			mark_free = 1;
+		BUG_ON(ret < 0);
 		/*
 		 * it is going to be very rare for someone to be waiting
 		 * on the block we're freeing.  del_items might need to
@@ -2403,7 +3303,7 @@ static int __free_extent(struct btrfs_trans_handle *trans,
 			free_extent_buffer(must_clean);
 		}
 
-		if (owner_objectid >= BTRFS_FIRST_FREE_OBJECTID) {
+		if (is_data) {
 			ret = btrfs_del_csums(trans, root, bytenr, num_bytes);
 			BUG_ON(ret);
 		} else {
@@ -2420,34 +3320,6 @@ static int __free_extent(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-/*
- * remove an extent from the root, returns 0 on success
- */
-static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root,
-					u64 bytenr, u64 num_bytes, u64 parent,
-					u64 root_objectid, u64 ref_generation,
-					u64 owner_objectid, int pin,
-					int refs_to_drop)
-{
-	WARN_ON(num_bytes < root->sectorsize);
-
-	/*
-	 * if metadata always pin
-	 * if data pin when any transaction has committed this
-	 */
-	if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID ||
-	    ref_generation != trans->transid)
-		pin = 1;
-
-	if (ref_generation != trans->transid)
-		pin = 1;
-
-	return __free_extent(trans, root, bytenr, num_bytes, parent,
-			    root_objectid, ref_generation,
-			    owner_objectid, pin, pin == 0, refs_to_drop);
-}
-
 /*
  * when we free an extent, it is possible (and likely) that we free the last
  * delayed ref for that extent as well.  This searches the delayed ref tree for
@@ -2479,6 +3351,13 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
 	if (ref->bytenr == bytenr)
 		goto out;
 
+	if (head->extent_op) {
+		if (!head->must_insert_reserved)
+			goto out;
+		kfree(head->extent_op);
+		head->extent_op = NULL;
+	}
+
 	/*
 	 * waiting for the lock here would deadlock.  If someone else has it
 	 * locked they are already in the process of dropping it anyway
@@ -2507,7 +3386,8 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
 	spin_unlock(&delayed_refs->lock);
 
 	ret = run_one_delayed_ref(trans, root->fs_info->tree_root,
-				  &head->node, head->must_insert_reserved);
+				  &head->node, head->extent_op,
+				  head->must_insert_reserved);
 	BUG_ON(ret);
 	btrfs_put_delayed_ref(&head->node);
 	return 0;
@@ -2519,32 +3399,32 @@ out:
 int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root,
 		      u64 bytenr, u64 num_bytes, u64 parent,
-		      u64 root_objectid, u64 ref_generation,
-		      u64 owner_objectid, int pin)
+		      u64 root_objectid, u64 owner, u64 offset)
 {
 	int ret;
 
 	/*
 	 * tree log blocks never actually go into the extent allocation
 	 * tree, just update pinning info and exit early.
-	 *
-	 * data extents referenced by the tree log do need to have
-	 * their reference counts bumped.
 	 */
-	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID &&
-	    owner_objectid < BTRFS_FIRST_FREE_OBJECTID) {
+	if (root_objectid == BTRFS_TREE_LOG_OBJECTID) {
+		WARN_ON(owner >= BTRFS_FIRST_FREE_OBJECTID);
 		/* unlocks the pinned mutex */
 		btrfs_update_pinned_extents(root, bytenr, num_bytes, 1);
 		update_reserved_extents(root, bytenr, num_bytes, 0);
 		ret = 0;
-	} else {
-		ret = btrfs_add_delayed_ref(trans, bytenr, num_bytes, parent,
-				       root_objectid, ref_generation,
-				       owner_objectid,
-				       BTRFS_DROP_DELAYED_REF, 1);
+	} else if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+		ret = btrfs_add_delayed_tree_ref(trans, bytenr, num_bytes,
+					parent, root_objectid, (int)owner,
+					BTRFS_DROP_DELAYED_REF, NULL);
 		BUG_ON(ret);
 		ret = check_ref_cleanup(trans, root, bytenr);
 		BUG_ON(ret);
+	} else {
+		ret = btrfs_add_delayed_data_ref(trans, bytenr, num_bytes,
+					parent, root_objectid, owner,
+					offset, BTRFS_DROP_DELAYED_REF, NULL);
+		BUG_ON(ret);
 	}
 	return ret;
 }
@@ -2719,7 +3599,7 @@ refill_cluster:
 			last_ptr_loop = 0;
 
 			/* allocate a cluster in this block group */
-			ret = btrfs_find_space_cluster(trans,
+			ret = btrfs_find_space_cluster(trans, root,
 					       block_group, last_ptr,
 					       offset, num_bytes,
 					       empty_cluster + empty_size);
@@ -2969,99 +3849,147 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static int __btrfs_alloc_reserved_extent(struct btrfs_trans_handle *trans,
-					 struct btrfs_root *root, u64 parent,
-					 u64 root_objectid, u64 ref_generation,
-					 u64 owner, struct btrfs_key *ins,
-					 int ref_mod)
+static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
+				      struct btrfs_root *root,
+				      u64 parent, u64 root_objectid,
+				      u64 flags, u64 owner, u64 offset,
+				      struct btrfs_key *ins, int ref_mod)
 {
 	int ret;
-	u64 super_used;
-	u64 root_used;
-	u64 num_bytes = ins->offset;
-	u32 sizes[2];
-	struct btrfs_fs_info *info = root->fs_info;
-	struct btrfs_root *extent_root = info->extent_root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_extent_item *extent_item;
-	struct btrfs_extent_ref *ref;
+	struct btrfs_extent_inline_ref *iref;
 	struct btrfs_path *path;
-	struct btrfs_key keys[2];
+	struct extent_buffer *leaf;
+	int type;
+	u32 size;
 
-	if (parent == 0)
-		parent = ins->objectid;
+	if (parent > 0)
+		type = BTRFS_SHARED_DATA_REF_KEY;
+	else
+		type = BTRFS_EXTENT_DATA_REF_KEY;
 
-	/* block accounting for super block */
-	spin_lock(&info->delalloc_lock);
-	super_used = btrfs_super_bytes_used(&info->super_copy);
-	btrfs_set_super_bytes_used(&info->super_copy, super_used + num_bytes);
-
-	/* block accounting for root item */
-	root_used = btrfs_root_used(&root->root_item);
-	btrfs_set_root_used(&root->root_item, root_used + num_bytes);
-	spin_unlock(&info->delalloc_lock);
-
-	memcpy(&keys[0], ins, sizeof(*ins));
-	keys[1].objectid = ins->objectid;
-	keys[1].type = BTRFS_EXTENT_REF_KEY;
-	keys[1].offset = parent;
-	sizes[0] = sizeof(*extent_item);
-	sizes[1] = sizeof(*ref);
+	size = sizeof(*extent_item) + btrfs_extent_inline_ref_size(type);
 
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
 
 	path->leave_spinning = 1;
-	ret = btrfs_insert_empty_items(trans, extent_root, path, keys,
-				       sizes, 2);
+	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
+				      ins, size);
 	BUG_ON(ret);
 
-	extent_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+	leaf = path->nodes[0];
+	extent_item = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_extent_item);
-	btrfs_set_extent_refs(path->nodes[0], extent_item, ref_mod);
-	ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
-			     struct btrfs_extent_ref);
+	btrfs_set_extent_refs(leaf, extent_item, ref_mod);
+	btrfs_set_extent_generation(leaf, extent_item, trans->transid);
+	btrfs_set_extent_flags(leaf, extent_item,
+			       flags | BTRFS_EXTENT_FLAG_DATA);
 
-	btrfs_set_ref_root(path->nodes[0], ref, root_objectid);
-	btrfs_set_ref_generation(path->nodes[0], ref, ref_generation);
-	btrfs_set_ref_objectid(path->nodes[0], ref, owner);
-	btrfs_set_ref_num_refs(path->nodes[0], ref, ref_mod);
+	iref = (struct btrfs_extent_inline_ref *)(extent_item + 1);
+	btrfs_set_extent_inline_ref_type(leaf, iref, type);
+	if (parent > 0) {
+		struct btrfs_shared_data_ref *ref;
+		ref = (struct btrfs_shared_data_ref *)(iref + 1);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
+		btrfs_set_shared_data_ref_count(leaf, ref, ref_mod);
+	} else {
+		struct btrfs_extent_data_ref *ref;
+		ref = (struct btrfs_extent_data_ref *)(&iref->offset);
+		btrfs_set_extent_data_ref_root(leaf, ref, root_objectid);
+		btrfs_set_extent_data_ref_objectid(leaf, ref, owner);
+		btrfs_set_extent_data_ref_offset(leaf, ref, offset);
+		btrfs_set_extent_data_ref_count(leaf, ref, ref_mod);
+	}
 
 	btrfs_mark_buffer_dirty(path->nodes[0]);
-
-	trans->alloc_exclude_start = 0;
-	trans->alloc_exclude_nr = 0;
 	btrfs_free_path(path);
 
-	if (ret)
-		goto out;
-
-	ret = update_block_group(trans, root, ins->objectid,
-				 ins->offset, 1, 0);
+	ret = update_block_group(trans, root, ins->objectid, ins->offset,
+				 1, 0);
 	if (ret) {
 		printk(KERN_ERR "btrfs update block group failed for %llu "
 		       "%llu\n", (unsigned long long)ins->objectid,
 		       (unsigned long long)ins->offset);
 		BUG();
 	}
-out:
 	return ret;
 }
 
-int btrfs_alloc_reserved_extent(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root, u64 parent,
-				u64 root_objectid, u64 ref_generation,
-				u64 owner, struct btrfs_key *ins)
+static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
+				     struct btrfs_root *root,
+				     u64 parent, u64 root_objectid,
+				     u64 flags, struct btrfs_disk_key *key,
+				     int level, struct btrfs_key *ins)
+{
+	int ret;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_extent_item *extent_item;
+	struct btrfs_tree_block_info *block_info;
+	struct btrfs_extent_inline_ref *iref;
+	struct btrfs_path *path;
+	struct extent_buffer *leaf;
+	u32 size = sizeof(*extent_item) + sizeof(*block_info) + sizeof(*iref);
+
+	path = btrfs_alloc_path();
+	BUG_ON(!path);
+
+	path->leave_spinning = 1;
+	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
+				      ins, size);
+	BUG_ON(ret);
+
+	leaf = path->nodes[0];
+	extent_item = btrfs_item_ptr(leaf, path->slots[0],
+				     struct btrfs_extent_item);
+	btrfs_set_extent_refs(leaf, extent_item, 1);
+	btrfs_set_extent_generation(leaf, extent_item, trans->transid);
+	btrfs_set_extent_flags(leaf, extent_item,
+			       flags | BTRFS_EXTENT_FLAG_TREE_BLOCK);
+	block_info = (struct btrfs_tree_block_info *)(extent_item + 1);
+
+	btrfs_set_tree_block_key(leaf, block_info, key);
+	btrfs_set_tree_block_level(leaf, block_info, level);
+
+	iref = (struct btrfs_extent_inline_ref *)(block_info + 1);
+	if (parent > 0) {
+		BUG_ON(!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
+		btrfs_set_extent_inline_ref_type(leaf, iref,
+						 BTRFS_SHARED_BLOCK_REF_KEY);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
+	} else {
+		btrfs_set_extent_inline_ref_type(leaf, iref,
+						 BTRFS_TREE_BLOCK_REF_KEY);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid);
+	}
+
+	btrfs_mark_buffer_dirty(leaf);
+	btrfs_free_path(path);
+
+	ret = update_block_group(trans, root, ins->objectid, ins->offset,
+				 1, 0);
+	if (ret) {
+		printk(KERN_ERR "btrfs update block group failed for %llu "
+		       "%llu\n", (unsigned long long)ins->objectid,
+		       (unsigned long long)ins->offset);
+		BUG();
+	}
+	return ret;
+}
+
+int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
+				     struct btrfs_root *root,
+				     u64 root_objectid, u64 owner,
+				     u64 offset, struct btrfs_key *ins)
 {
 	int ret;
 
-	if (root_objectid == BTRFS_TREE_LOG_OBJECTID)
-		return 0;
+	BUG_ON(root_objectid == BTRFS_TREE_LOG_OBJECTID);
 
-	ret = btrfs_add_delayed_ref(trans, ins->objectid,
-				    ins->offset, parent, root_objectid,
-				    ref_generation, owner,
-				    BTRFS_ADD_DELAYED_EXTENT, 0);
-	BUG_ON(ret);
+	ret = btrfs_add_delayed_data_ref(trans, ins->objectid, ins->offset,
+					 0, root_objectid, owner, offset,
+					 BTRFS_ADD_DELAYED_EXTENT, NULL);
 	return ret;
 }
 
@@ -3070,10 +3998,10 @@ int btrfs_alloc_reserved_extent(struct btrfs_trans_handle *trans,
  * an extent has been allocated and makes sure to clear the free
  * space cache bits as well
  */
-int btrfs_alloc_logged_extent(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root, u64 parent,
-				u64 root_objectid, u64 ref_generation,
-				u64 owner, struct btrfs_key *ins)
+int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root,
+				   u64 root_objectid, u64 owner, u64 offset,
+				   struct btrfs_key *ins)
 {
 	int ret;
 	struct btrfs_block_group_cache *block_group;
@@ -3087,8 +4015,8 @@ int btrfs_alloc_logged_extent(struct btrfs_trans_handle *trans,
 				      ins->offset);
 	BUG_ON(ret);
 	btrfs_put_block_group(block_group);
-	ret = __btrfs_alloc_reserved_extent(trans, root, parent, root_objectid,
-					    ref_generation, owner, ins, 1);
+	ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
+					 0, owner, offset, ins, 1);
 	return ret;
 }
 
@@ -3099,26 +4027,48 @@ int btrfs_alloc_logged_extent(struct btrfs_trans_handle *trans,
  *
  * returns 0 if everything worked, non-zero otherwise.
  */
-int btrfs_alloc_extent(struct btrfs_trans_handle *trans,
-		       struct btrfs_root *root,
-		       u64 num_bytes, u64 parent, u64 min_alloc_size,
-		       u64 root_objectid, u64 ref_generation,
-		       u64 owner_objectid, u64 empty_size, u64 hint_byte,
-		       u64 search_end, struct btrfs_key *ins, u64 data)
+static int alloc_tree_block(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root,
+			    u64 num_bytes, u64 parent, u64 root_objectid,
+			    struct btrfs_disk_key *key, int level,
+			    u64 empty_size, u64 hint_byte, u64 search_end,
+			    struct btrfs_key *ins)
 {
 	int ret;
-	ret = __btrfs_reserve_extent(trans, root, num_bytes,
-				     min_alloc_size, empty_size, hint_byte,
-				     search_end, ins, data);
+	u64 flags = 0;
+
+	ret = __btrfs_reserve_extent(trans, root, num_bytes, num_bytes,
+				     empty_size, hint_byte, search_end,
+				     ins, 0);
 	BUG_ON(ret);
+
+	if (root_objectid == BTRFS_TREE_RELOC_OBJECTID) {
+		if (parent == 0)
+			parent = ins->objectid;
+		flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
+	} else
+		BUG_ON(parent > 0);
+
+	update_reserved_extents(root, ins->objectid, ins->offset, 1);
 	if (root_objectid != BTRFS_TREE_LOG_OBJECTID) {
-		ret = btrfs_add_delayed_ref(trans, ins->objectid,
-					    ins->offset, parent, root_objectid,
-					    ref_generation, owner_objectid,
-					    BTRFS_ADD_DELAYED_EXTENT, 0);
+		struct btrfs_delayed_extent_op *extent_op;
+		extent_op = kmalloc(sizeof(*extent_op), GFP_NOFS);
+		BUG_ON(!extent_op);
+		if (key)
+			memcpy(&extent_op->key, key, sizeof(extent_op->key));
+		else
+			memset(&extent_op->key, 0, sizeof(extent_op->key));
+		extent_op->flags_to_set = flags;
+		extent_op->update_key = 1;
+		extent_op->update_flags = 1;
+		extent_op->is_data = 0;
+
+		ret = btrfs_add_delayed_tree_ref(trans, ins->objectid,
+					ins->offset, parent, root_objectid,
+					level, BTRFS_ADD_DELAYED_EXTENT,
+					extent_op);
 		BUG_ON(ret);
 	}
-	update_reserved_extents(root, ins->objectid, ins->offset, 1);
 	return ret;
 }
 
@@ -3157,21 +4107,17 @@ struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
  * returns the tree buffer or NULL.
  */
 struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
-					     struct btrfs_root *root,
-					     u32 blocksize, u64 parent,
-					     u64 root_objectid,
-					     u64 ref_generation,
-					     int level,
-					     u64 hint,
-					     u64 empty_size)
+					struct btrfs_root *root, u32 blocksize,
+					u64 parent, u64 root_objectid,
+					struct btrfs_disk_key *key, int level,
+					u64 hint, u64 empty_size)
 {
 	struct btrfs_key ins;
 	int ret;
 	struct extent_buffer *buf;
 
-	ret = btrfs_alloc_extent(trans, root, blocksize, parent, blocksize,
-				 root_objectid, ref_generation, level,
-				 empty_size, hint, (u64)-1, &ins, 0);
+	ret = alloc_tree_block(trans, root, blocksize, parent, root_objectid,
+			       key, level, empty_size, hint, (u64)-1, &ins);
 	if (ret) {
 		BUG_ON(ret > 0);
 		return ERR_PTR(ret);
@@ -3185,32 +4131,19 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 int btrfs_drop_leaf_ref(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root, struct extent_buffer *leaf)
 {
-	u64 leaf_owner;
-	u64 leaf_generation;
-	struct refsort *sorted;
+	u64 disk_bytenr;
+	u64 num_bytes;
 	struct btrfs_key key;
 	struct btrfs_file_extent_item *fi;
+	u32 nritems;
 	int i;
-	int nritems;
 	int ret;
-	int refi = 0;
-	int slot;
 
 	BUG_ON(!btrfs_is_leaf(leaf));
 	nritems = btrfs_header_nritems(leaf);
-	leaf_owner = btrfs_header_owner(leaf);
-	leaf_generation = btrfs_header_generation(leaf);
 
-	sorted = kmalloc(sizeof(*sorted) * nritems, GFP_NOFS);
-	/* we do this loop twice.  The first time we build a list
-	 * of the extents we have a reference on, then we sort the list
-	 * by bytenr.  The second time around we actually do the
-	 * extent freeing.
-	 */
 	for (i = 0; i < nritems; i++) {
-		u64 disk_bytenr;
 		cond_resched();
-
 		btrfs_item_key_to_cpu(leaf, &key, i);
 
 		/* only extents have references, skip everything else */
@@ -3230,45 +4163,16 @@ int btrfs_drop_leaf_ref(struct btrfs_trans_handle *trans,
 		if (disk_bytenr == 0)
 			continue;
 
-		sorted[refi].bytenr = disk_bytenr;
-		sorted[refi].slot = i;
-		refi++;
-	}
-
-	if (refi == 0)
-		goto out;
-
-	sort(sorted, refi, sizeof(struct refsort), refsort_cmp, NULL);
-
-	for (i = 0; i < refi; i++) {
-		u64 disk_bytenr;
-
-		disk_bytenr = sorted[i].bytenr;
-		slot = sorted[i].slot;
-
-		cond_resched();
-
-		btrfs_item_key_to_cpu(leaf, &key, slot);
-		if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
-			continue;
-
-		fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
-
-		ret = btrfs_free_extent(trans, root, disk_bytenr,
-				btrfs_file_extent_disk_num_bytes(leaf, fi),
-				leaf->start, leaf_owner, leaf_generation,
-				key.objectid, 0);
+		num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
+		ret = btrfs_free_extent(trans, root, disk_bytenr, num_bytes,
+					leaf->start, 0, key.objectid, 0);
 		BUG_ON(ret);
-
-		atomic_inc(&root->fs_info->throttle_gen);
-		wake_up(&root->fs_info->transaction_throttle);
-		cond_resched();
 	}
-out:
-	kfree(sorted);
 	return 0;
 }
 
+#if 0
+
 static noinline int cache_drop_leaf_ref(struct btrfs_trans_handle *trans,
 					struct btrfs_root *root,
 					struct btrfs_leaf_ref *ref)
@@ -3311,13 +4215,14 @@ static noinline int cache_drop_leaf_ref(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+
 static int drop_snap_lookup_refcount(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root, u64 start,
 				     u64 len, u32 *refs)
 {
 	int ret;
 
-	ret = btrfs_lookup_extent_ref(trans, root, start, len, refs);
+	ret = btrfs_lookup_extent_refs(trans, root, start, len, refs);
 	BUG_ON(ret);
 
 #if 0 /* some debugging code in case we see problems here */
@@ -3352,6 +4257,7 @@ static int drop_snap_lookup_refcount(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+
 /*
  * this is used while deleting old snapshots, and it drops the refs
  * on a whole subtree starting from a level 1 node.
@@ -3645,32 +4551,36 @@ out:
 	cond_resched();
 	return 0;
 }
+#endif
 
 /*
  * helper function for drop_subtree, this function is similar to
  * walk_down_tree. The main difference is that it checks reference
  * counts while tree blocks are locked.
  */
-static noinline int walk_down_subtree(struct btrfs_trans_handle *trans,
-				      struct btrfs_root *root,
-				      struct btrfs_path *path, int *level)
+static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root,
+				   struct btrfs_path *path, int *level)
 {
 	struct extent_buffer *next;
 	struct extent_buffer *cur;
 	struct extent_buffer *parent;
 	u64 bytenr;
 	u64 ptr_gen;
+	u64 refs;
+	u64 flags;
 	u32 blocksize;
-	u32 refs;
 	int ret;
 
 	cur = path->nodes[*level];
-	ret = btrfs_lookup_extent_ref(trans, root, cur->start, cur->len,
-				      &refs);
+	ret = btrfs_lookup_extent_info(trans, root, cur->start, cur->len,
+				       &refs, &flags);
 	BUG_ON(ret);
 	if (refs > 1)
 		goto out;
 
+	BUG_ON(!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
+
 	while (*level >= 0) {
 		cur = path->nodes[*level];
 		if (*level == 0) {
@@ -3692,16 +4602,15 @@ static noinline int walk_down_subtree(struct btrfs_trans_handle *trans,
 		btrfs_tree_lock(next);
 		btrfs_set_lock_blocking(next);
 
-		ret = btrfs_lookup_extent_ref(trans, root, bytenr, blocksize,
-					      &refs);
+		ret = btrfs_lookup_extent_info(trans, root, bytenr, blocksize,
+					       &refs, &flags);
 		BUG_ON(ret);
 		if (refs > 1) {
 			parent = path->nodes[*level];
 			ret = btrfs_free_extent(trans, root, bytenr,
-					blocksize, parent->start,
-					btrfs_header_owner(parent),
-					btrfs_header_generation(parent),
-					*level - 1, 1);
+						blocksize, parent->start,
+						btrfs_header_owner(parent),
+						*level - 1, 0);
 			BUG_ON(ret);
 			path->slots[*level]++;
 			btrfs_tree_unlock(next);
@@ -3709,6 +4618,8 @@ static noinline int walk_down_subtree(struct btrfs_trans_handle *trans,
 			continue;
 		}
 
+		BUG_ON(!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
+
 		*level = btrfs_header_level(next);
 		path->nodes[*level] = next;
 		path->slots[*level] = 0;
@@ -3716,13 +4627,15 @@ static noinline int walk_down_subtree(struct btrfs_trans_handle *trans,
 		cond_resched();
 	}
 out:
-	parent = path->nodes[*level + 1];
+	if (path->nodes[*level] == root->node)
+		parent = path->nodes[*level];
+	else
+		parent = path->nodes[*level + 1];
 	bytenr = path->nodes[*level]->start;
 	blocksize = path->nodes[*level]->len;
 
-	ret = btrfs_free_extent(trans, root, bytenr, blocksize,
-			parent->start, btrfs_header_owner(parent),
-			btrfs_header_generation(parent), *level, 1);
+	ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent->start,
+				btrfs_header_owner(parent), *level, 0);
 	BUG_ON(ret);
 
 	if (path->locks[*level]) {
@@ -3746,8 +4659,6 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
 				 struct btrfs_path *path,
 				 int *level, int max_level)
 {
-	u64 root_owner;
-	u64 root_gen;
 	struct btrfs_root_item *root_item = &root->root_item;
 	int i;
 	int slot;
@@ -3755,24 +4666,22 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
 
 	for (i = *level; i < max_level && path->nodes[i]; i++) {
 		slot = path->slots[i];
-		if (slot < btrfs_header_nritems(path->nodes[i]) - 1) {
-			struct extent_buffer *node;
-			struct btrfs_disk_key disk_key;
-
+		if (slot + 1 < btrfs_header_nritems(path->nodes[i])) {
 			/*
 			 * there is more work to do in this level.
 			 * Update the drop_progress marker to reflect
 			 * the work we've done so far, and then bump
 			 * the slot number
 			 */
-			node = path->nodes[i];
 			path->slots[i]++;
-			*level = i;
 			WARN_ON(*level == 0);
-			btrfs_node_key(node, &disk_key, path->slots[i]);
-			memcpy(&root_item->drop_progress,
-			       &disk_key, sizeof(disk_key));
-			root_item->drop_level = i;
+			if (max_level == BTRFS_MAX_LEVEL) {
+				btrfs_node_key(path->nodes[i],
+					       &root_item->drop_progress,
+					       path->slots[i]);
+				root_item->drop_level = i;
+			}
+			*level = i;
 			return 0;
 		} else {
 			struct extent_buffer *parent;
@@ -3786,22 +4695,20 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
 			else
 				parent = path->nodes[*level + 1];
 
-			root_owner = btrfs_header_owner(parent);
-			root_gen = btrfs_header_generation(parent);
-
-			clean_tree_block(trans, root, path->nodes[*level]);
+			clean_tree_block(trans, root, path->nodes[i]);
 			ret = btrfs_free_extent(trans, root,
-						path->nodes[*level]->start,
-						path->nodes[*level]->len,
-						parent->start, root_owner,
-						root_gen, *level, 1);
+						path->nodes[i]->start,
+						path->nodes[i]->len,
+						parent->start,
+						btrfs_header_owner(parent),
+						*level, 0);
 			BUG_ON(ret);
 			if (path->locks[*level]) {
-				btrfs_tree_unlock(path->nodes[*level]);
-				path->locks[*level] = 0;
+				btrfs_tree_unlock(path->nodes[i]);
+				path->locks[i] = 0;
 			}
-			free_extent_buffer(path->nodes[*level]);
-			path->nodes[*level] = NULL;
+			free_extent_buffer(path->nodes[i]);
+			path->nodes[i] = NULL;
 			*level = i + 1;
 		}
 	}
@@ -3820,21 +4727,18 @@ int btrfs_drop_snapshot(struct btrfs_trans_handle *trans, struct btrfs_root
 	int wret;
 	int level;
 	struct btrfs_path *path;
-	int i;
-	int orig_level;
 	int update_count;
 	struct btrfs_root_item *root_item = &root->root_item;
 
-	WARN_ON(!mutex_is_locked(&root->fs_info->drop_mutex));
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
 
 	level = btrfs_header_level(root->node);
-	orig_level = level;
 	if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
-		path->nodes[level] = root->node;
-		extent_buffer_get(root->node);
+		path->nodes[level] = btrfs_lock_root_node(root);
+		btrfs_set_lock_blocking(path->nodes[level]);
 		path->slots[level] = 0;
+		path->locks[level] = 1;
 	} else {
 		struct btrfs_key key;
 		struct btrfs_disk_key found_key;
@@ -3856,12 +4760,7 @@ int btrfs_drop_snapshot(struct btrfs_trans_handle *trans, struct btrfs_root
 		 * unlock our path, this is safe because only this
 		 * function is allowed to delete this snapshot
 		 */
-		for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
-			if (path->nodes[i] && path->locks[i]) {
-				path->locks[i] = 0;
-				btrfs_tree_unlock(path->nodes[i]);
-			}
-		}
+		btrfs_unlock_up_safe(path, 0);
 	}
 	while (1) {
 		unsigned long update;
@@ -3882,8 +4781,6 @@ int btrfs_drop_snapshot(struct btrfs_trans_handle *trans, struct btrfs_root
 			ret = -EAGAIN;
 			break;
 		}
-		atomic_inc(&root->fs_info->throttle_gen);
-		wake_up(&root->fs_info->transaction_throttle);
 		for (update_count = 0; update_count < 16; update_count++) {
 			update = trans->delayed_ref_updates;
 			trans->delayed_ref_updates = 0;
@@ -3893,12 +4790,6 @@ int btrfs_drop_snapshot(struct btrfs_trans_handle *trans, struct btrfs_root
 				break;
 		}
 	}
-	for (i = 0; i <= orig_level; i++) {
-		if (path->nodes[i]) {
-			free_extent_buffer(path->nodes[i]);
-			path->nodes[i] = NULL;
-		}
-	}
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -3931,7 +4822,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	path->slots[level] = 0;
 
 	while (1) {
-		wret = walk_down_subtree(trans, root, path, &level);
+		wret = walk_down_tree(trans, root, path, &level);
 		if (wret < 0)
 			ret = wret;
 		if (wret != 0)
@@ -3948,6 +4839,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+#if 0
 static unsigned long calc_ra(unsigned long start, unsigned long last,
 			     unsigned long nr)
 {
@@ -5429,6 +6321,7 @@ out:
 	kfree(ref_path);
 	return ret;
 }
+#endif
 
 static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
 {
@@ -5477,7 +6370,8 @@ static int __alloc_chunk_for_shrink(struct btrfs_root *root,
 	u64 calc;
 
 	spin_lock(&shrink_block_group->lock);
-	if (btrfs_block_group_used(&shrink_block_group->item) > 0) {
+	if (btrfs_block_group_used(&shrink_block_group->item) +
+	    shrink_block_group->reserved > 0) {
 		spin_unlock(&shrink_block_group->lock);
 
 		trans = btrfs_start_transaction(root, 1);
@@ -5502,6 +6396,17 @@ static int __alloc_chunk_for_shrink(struct btrfs_root *root,
 	return 0;
 }
 
+
+int btrfs_prepare_block_group_relocation(struct btrfs_root *root,
+					 struct btrfs_block_group_cache *group)
+
+{
+	__alloc_chunk_for_shrink(root, group, 1);
+	set_block_group_readonly(group);
+	return 0;
+}
+
+#if 0
 static int __insert_orphan_inode(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root,
 				 u64 objectid, u64 size)
@@ -5781,6 +6686,7 @@ out:
 	btrfs_free_path(path);
 	return ret;
 }
+#endif
 
 static int find_first_block_group(struct btrfs_root *root,
 		struct btrfs_path *path, struct btrfs_key *key)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index fe9eb990e443..68260180f587 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -476,6 +476,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	struct extent_state *state;
 	struct extent_state *prealloc = NULL;
 	struct rb_node *node;
+	u64 last_end;
 	int err;
 	int set = 0;
 
@@ -498,6 +499,7 @@ again:
 	if (state->start > end)
 		goto out;
 	WARN_ON(state->end < start);
+	last_end = state->end;
 
 	/*
 	 *     | ---- desired range ---- |
@@ -524,9 +526,11 @@ again:
 		if (err)
 			goto out;
 		if (state->end <= end) {
-			start = state->end + 1;
 			set |= clear_state_bit(tree, state, bits,
 					wake, delete);
+			if (last_end == (u64)-1)
+				goto out;
+			start = last_end + 1;
 		} else {
 			start = state->start;
 		}
@@ -552,8 +556,10 @@ again:
 		goto out;
 	}
 
-	start = state->end + 1;
 	set |= clear_state_bit(tree, state, bits, wake, delete);
+	if (last_end == (u64)-1)
+		goto out;
+	start = last_end + 1;
 	goto search_again;
 
 out:
@@ -707,8 +713,10 @@ again:
 			goto out;
 		}
 		set_state_bits(tree, state, bits);
-		start = state->end + 1;
 		merge_state(tree, state);
+		if (last_end == (u64)-1)
+			goto out;
+		start = last_end + 1;
 		goto search_again;
 	}
 
@@ -742,8 +750,10 @@ again:
 			goto out;
 		if (state->end <= end) {
 			set_state_bits(tree, state, bits);
-			start = state->end + 1;
 			merge_state(tree, state);
+			if (last_end == (u64)-1)
+				goto out;
+			start = last_end + 1;
 		} else {
 			start = state->start;
 		}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 1d51dc38bb49..126477eaecf5 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -291,16 +291,12 @@ noinline int btrfs_drop_extents(struct btrfs_trans_handle *trans,
 {
 	u64 extent_end = 0;
 	u64 search_start = start;
-	u64 leaf_start;
 	u64 ram_bytes = 0;
-	u64 orig_parent = 0;
 	u64 disk_bytenr = 0;
 	u64 orig_locked_end = locked_end;
 	u8 compression;
 	u8 encryption;
 	u16 other_encoding = 0;
-	u64 root_gen;
-	u64 root_owner;
 	struct extent_buffer *leaf;
 	struct btrfs_file_extent_item *extent;
 	struct btrfs_path *path;
@@ -340,9 +336,6 @@ next_slot:
 		bookend = 0;
 		found_extent = 0;
 		found_inline = 0;
-		leaf_start = 0;
-		root_gen = 0;
-		root_owner = 0;
 		compression = 0;
 		encryption = 0;
 		extent = NULL;
@@ -417,9 +410,6 @@ next_slot:
 		if (found_extent) {
 			read_extent_buffer(leaf, &old, (unsigned long)extent,
 					   sizeof(old));
-			root_gen = btrfs_header_generation(leaf);
-			root_owner = btrfs_header_owner(leaf);
-			leaf_start = leaf->start;
 		}
 
 		if (end < extent_end && end >= key.offset) {
@@ -443,14 +433,14 @@ next_slot:
 				}
 				locked_end = extent_end;
 			}
-			orig_parent = path->nodes[0]->start;
 			disk_bytenr = le64_to_cpu(old.disk_bytenr);
 			if (disk_bytenr != 0) {
 				ret = btrfs_inc_extent_ref(trans, root,
 					   disk_bytenr,
-					   le64_to_cpu(old.disk_num_bytes),
-					   orig_parent, root->root_key.objectid,
-					   trans->transid, inode->i_ino);
+					   le64_to_cpu(old.disk_num_bytes), 0,
+					   root->root_key.objectid,
+					   key.objectid, key.offset -
+					   le64_to_cpu(old.offset));
 				BUG_ON(ret);
 			}
 		}
@@ -568,17 +558,6 @@ next_slot:
 			btrfs_mark_buffer_dirty(path->nodes[0]);
 			btrfs_set_lock_blocking(path->nodes[0]);
 
-			if (disk_bytenr != 0) {
-				ret = btrfs_update_extent_ref(trans, root,
-						disk_bytenr,
-						le64_to_cpu(old.disk_num_bytes),
-						orig_parent,
-						leaf->start,
-						root->root_key.objectid,
-						trans->transid, ins.objectid);
-
-				BUG_ON(ret);
-			}
 			path->leave_spinning = 0;
 			btrfs_release_path(root, path);
 			if (disk_bytenr != 0)
@@ -594,8 +573,9 @@ next_slot:
 				ret = btrfs_free_extent(trans, root,
 						old_disk_bytenr,
 						le64_to_cpu(old.disk_num_bytes),
-						leaf_start, root_owner,
-						root_gen, key.objectid, 0);
+						0, root->root_key.objectid,
+						key.objectid, key.offset -
+						le64_to_cpu(old.offset));
 				BUG_ON(ret);
 				*hint_byte = old_disk_bytenr;
 			}
@@ -664,12 +644,11 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 	u64 bytenr;
 	u64 num_bytes;
 	u64 extent_end;
-	u64 extent_offset;
+	u64 orig_offset;
 	u64 other_start;
 	u64 other_end;
 	u64 split = start;
 	u64 locked_end = end;
-	u64 orig_parent;
 	int extent_type;
 	int split_end = 1;
 	int ret;
@@ -703,7 +682,7 @@ again:
 
 	bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
 	num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
-	extent_offset = btrfs_file_extent_offset(leaf, fi);
+	orig_offset = key.offset - btrfs_file_extent_offset(leaf, fi);
 
 	if (key.offset == start)
 		split = end;
@@ -711,8 +690,6 @@ again:
 	if (key.offset == start && extent_end == end) {
 		int del_nr = 0;
 		int del_slot = 0;
-		u64 leaf_owner = btrfs_header_owner(leaf);
-		u64 leaf_gen = btrfs_header_generation(leaf);
 		other_start = end;
 		other_end = 0;
 		if (extent_mergeable(leaf, path->slots[0] + 1, inode->i_ino,
@@ -721,8 +698,8 @@ again:
 			del_slot = path->slots[0] + 1;
 			del_nr++;
 			ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
-						leaf->start, leaf_owner,
-						leaf_gen, inode->i_ino, 0);
+						0, root->root_key.objectid,
+						inode->i_ino, orig_offset);
 			BUG_ON(ret);
 		}
 		other_start = 0;
@@ -733,8 +710,8 @@ again:
 			del_slot = path->slots[0];
 			del_nr++;
 			ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
-						leaf->start, leaf_owner,
-						leaf_gen, inode->i_ino, 0);
+						0, root->root_key.objectid,
+						inode->i_ino, orig_offset);
 			BUG_ON(ret);
 		}
 		split_end = 0;
@@ -768,13 +745,12 @@ again:
 			locked_end = extent_end;
 		}
 		btrfs_set_file_extent_num_bytes(leaf, fi, split - key.offset);
-		extent_offset += split - key.offset;
 	} else  {
 		BUG_ON(key.offset != start);
-		btrfs_set_file_extent_offset(leaf, fi, extent_offset +
-					     split - key.offset);
-		btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - split);
 		key.offset = split;
+		btrfs_set_file_extent_offset(leaf, fi, key.offset -
+					     orig_offset);
+		btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - split);
 		btrfs_set_item_key_safe(trans, root, path, &key);
 		extent_end = split;
 	}
@@ -793,7 +769,8 @@ again:
 					    struct btrfs_file_extent_item);
 			key.offset = split;
 			btrfs_set_item_key_safe(trans, root, path, &key);
-			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
+			btrfs_set_file_extent_offset(leaf, fi, key.offset -
+						     orig_offset);
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							other_end - split);
 			goto done;
@@ -815,10 +792,9 @@ again:
 
 	btrfs_mark_buffer_dirty(leaf);
 
-	orig_parent = leaf->start;
-	ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes,
-				   orig_parent, root->root_key.objectid,
-				   trans->transid, inode->i_ino);
+	ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
+				   root->root_key.objectid,
+				   inode->i_ino, orig_offset);
 	BUG_ON(ret);
 	btrfs_release_path(root, path);
 
@@ -833,20 +809,12 @@ again:
 	btrfs_set_file_extent_type(leaf, fi, extent_type);
 	btrfs_set_file_extent_disk_bytenr(leaf, fi, bytenr);
 	btrfs_set_file_extent_disk_num_bytes(leaf, fi, num_bytes);
-	btrfs_set_file_extent_offset(leaf, fi, extent_offset);
+	btrfs_set_file_extent_offset(leaf, fi, key.offset - orig_offset);
 	btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - key.offset);
 	btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 	btrfs_set_file_extent_compression(leaf, fi, 0);
 	btrfs_set_file_extent_encryption(leaf, fi, 0);
 	btrfs_set_file_extent_other_encoding(leaf, fi, 0);
-
-	if (orig_parent != leaf->start) {
-		ret = btrfs_update_extent_ref(trans, root, bytenr, num_bytes,
-					      orig_parent, leaf->start,
-					      root->root_key.objectid,
-					      trans->transid, inode->i_ino);
-		BUG_ON(ret);
-	}
 done:
 	btrfs_mark_buffer_dirty(leaf);
 
@@ -1189,6 +1157,8 @@ int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync)
 	btrfs_wait_ordered_range(inode, 0, (u64)-1);
 	root->log_batch++;
 
+	if (datasync && !(inode->i_state & I_DIRTY_PAGES))
+		goto out;
 	/*
 	 * ok we haven't committed the transaction yet, lets do a commit
 	 */
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 0bc93657b460..4538e48581a5 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -579,6 +579,7 @@ out:
  * it returns -enospc
  */
 int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root,
 			     struct btrfs_block_group_cache *block_group,
 			     struct btrfs_free_cluster *cluster,
 			     u64 offset, u64 bytes, u64 empty_size)
@@ -595,7 +596,9 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
 	int ret;
 
 	/* for metadata, allow allocates with more holes */
-	if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) {
+	if (btrfs_test_opt(root, SSD_SPREAD)) {
+		min_bytes = bytes + empty_size;
+	} else if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) {
 		/*
 		 * we want to do larger allocations when we are
 		 * flushing out the delayed refs, it helps prevent
@@ -645,14 +648,15 @@ again:
 		 * we haven't filled the empty size and the window is
 		 * very large.  reset and try again
 		 */
-		if (next->offset - window_start > (bytes + empty_size) * 2) {
+		if (next->offset - (last->offset + last->bytes) > 128 * 1024 ||
+		    next->offset - window_start > (bytes + empty_size) * 2) {
 			entry = next;
 			window_start = entry->offset;
 			window_free = entry->bytes;
 			last = entry;
 			max_extent = 0;
 			total_retries++;
-			if (total_retries % 256 == 0) {
+			if (total_retries % 64 == 0) {
 				if (min_bytes >= (bytes + empty_size)) {
 					ret = -ENOSPC;
 					goto out;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index ab0bdc0a63ce..266fb8764054 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -31,6 +31,7 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 			   u64 bytes);
 u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group);
 int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root,
 			     struct btrfs_block_group_cache *block_group,
 			     struct btrfs_free_cluster *cluster,
 			     u64 offset, u64 bytes, u64 empty_size);
diff --git a/fs/btrfs/hash.h b/fs/btrfs/hash.h
index 2a020b276768..db2ff9773b99 100644
--- a/fs/btrfs/hash.h
+++ b/fs/btrfs/hash.h
@@ -19,9 +19,9 @@
 #ifndef __HASH__
 #define __HASH__
 
-#include "crc32c.h"
+#include <linux/crc32c.h>
 static inline u64 btrfs_name_hash(const char *name, int len)
 {
-	return btrfs_crc32c((u32)~1, name, len);
+	return crc32c((u32)~1, name, len);
 }
 #endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 1c8b0190d031..8612b3a09811 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -48,7 +48,6 @@
 #include "ordered-data.h"
 #include "xattr.h"
 #include "tree-log.h"
-#include "ref-cache.h"
 #include "compression.h"
 #include "locking.h"
 
@@ -369,7 +368,7 @@ again:
 	 * inode has not been flagged as nocompress.  This flag can
 	 * change at any time if we discover bad compression ratios.
 	 */
-	if (!btrfs_test_flag(inode, NOCOMPRESS) &&
+	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) &&
 	    btrfs_test_opt(root, COMPRESS)) {
 		WARN_ON(pages);
 		pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
@@ -470,7 +469,7 @@ again:
 		nr_pages_ret = 0;
 
 		/* flag the file so we don't compress in the future */
-		btrfs_set_flag(inode, NOCOMPRESS);
+		BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
 	}
 	if (will_compress) {
 		*num_added += 1;
@@ -863,7 +862,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		async_cow->locked_page = locked_page;
 		async_cow->start = start;
 
-		if (btrfs_test_flag(inode, NOCOMPRESS))
+		if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS)
 			cur_end = end;
 		else
 			cur_end = min(end, start + 512 * 1024 - 1);
@@ -944,6 +943,7 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	u64 cow_start;
 	u64 cur_offset;
 	u64 extent_end;
+	u64 extent_offset;
 	u64 disk_bytenr;
 	u64 num_bytes;
 	int extent_type;
@@ -1005,6 +1005,7 @@ next_slot:
 		if (extent_type == BTRFS_FILE_EXTENT_REG ||
 		    extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
 			disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
+			extent_offset = btrfs_file_extent_offset(leaf, fi);
 			extent_end = found_key.offset +
 				btrfs_file_extent_num_bytes(leaf, fi);
 			if (extent_end <= start) {
@@ -1022,9 +1023,10 @@ next_slot:
 			if (btrfs_extent_readonly(root, disk_bytenr))
 				goto out_check;
 			if (btrfs_cross_ref_exist(trans, root, inode->i_ino,
-						  disk_bytenr))
+						  found_key.offset -
+						  extent_offset, disk_bytenr))
 				goto out_check;
-			disk_bytenr += btrfs_file_extent_offset(leaf, fi);
+			disk_bytenr += extent_offset;
 			disk_bytenr += cur_offset - found_key.offset;
 			num_bytes = min(end + 1, extent_end) - cur_offset;
 			/*
@@ -1131,10 +1133,10 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
 	int ret;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 
-	if (btrfs_test_flag(inode, NODATACOW))
+	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)
 		ret = run_delalloc_nocow(inode, locked_page, start, end,
 					 page_started, 1, nr_written);
-	else if (btrfs_test_flag(inode, PREALLOC))
+	else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)
 		ret = run_delalloc_nocow(inode, locked_page, start, end,
 					 page_started, 0, nr_written);
 	else if (!btrfs_test_opt(root, COMPRESS))
@@ -1288,7 +1290,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 	int ret = 0;
 	int skip_sum;
 
-	skip_sum = btrfs_test_flag(inode, NODATASUM);
+	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
 	ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
 	BUG_ON(ret);
@@ -1489,9 +1491,9 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 	ins.objectid = disk_bytenr;
 	ins.offset = disk_num_bytes;
 	ins.type = BTRFS_EXTENT_ITEM_KEY;
-	ret = btrfs_alloc_reserved_extent(trans, root, leaf->start,
-					  root->root_key.objectid,
-					  trans->transid, inode->i_ino, &ins);
+	ret = btrfs_alloc_reserved_file_extent(trans, root,
+					root->root_key.objectid,
+					inode->i_ino, file_pos, &ins);
 	BUG_ON(ret);
 	btrfs_free_path(path);
 
@@ -1788,7 +1790,8 @@ static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 		ClearPageChecked(page);
 		goto good;
 	}
-	if (btrfs_test_flag(inode, NODATASUM))
+
+	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
 		return 0;
 
 	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
@@ -1956,23 +1959,13 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 		 * crossing root thing.  we store the inode number in the
 		 * offset of the orphan item.
 		 */
-		inode = btrfs_iget_locked(root->fs_info->sb,
-					  found_key.offset, root);
-		if (!inode)
+		found_key.objectid = found_key.offset;
+		found_key.type = BTRFS_INODE_ITEM_KEY;
+		found_key.offset = 0;
+		inode = btrfs_iget(root->fs_info->sb, &found_key, root);
+		if (IS_ERR(inode))
 			break;
 
-		if (inode->i_state & I_NEW) {
-			BTRFS_I(inode)->root = root;
-
-			/* have to set the location manually */
-			BTRFS_I(inode)->location.objectid = inode->i_ino;
-			BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
-			BTRFS_I(inode)->location.offset = 0;
-
-			btrfs_read_locked_inode(inode);
-			unlock_new_inode(inode);
-		}
-
 		/*
 		 * add this inode to the orphan list so btrfs_orphan_del does
 		 * the proper thing when we hit it
@@ -2069,7 +2062,7 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
 /*
  * read an inode from the btree into the in-memory inode
  */
-void btrfs_read_locked_inode(struct inode *inode)
+static void btrfs_read_locked_inode(struct inode *inode)
 {
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
@@ -2164,6 +2157,8 @@ void btrfs_read_locked_inode(struct inode *inode)
 		init_special_inode(inode, inode->i_mode, rdev);
 		break;
 	}
+
+	btrfs_update_iflags(inode);
 	return;
 
 make_bad:
@@ -2327,7 +2322,6 @@ err:
 	btrfs_update_inode(trans, root, dir);
 	btrfs_drop_nlink(inode);
 	ret = btrfs_update_inode(trans, root, inode);
-	dir->i_sb->s_dirt = 1;
 out:
 	return ret;
 }
@@ -2599,9 +2593,8 @@ noinline int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	struct btrfs_file_extent_item *fi;
 	u64 extent_start = 0;
 	u64 extent_num_bytes = 0;
+	u64 extent_offset = 0;
 	u64 item_end = 0;
-	u64 root_gen = 0;
-	u64 root_owner = 0;
 	int found_extent;
 	int del_item;
 	int pending_del_nr = 0;
@@ -2716,6 +2709,9 @@ search_again:
 				extent_num_bytes =
 					btrfs_file_extent_disk_num_bytes(leaf,
 									 fi);
+				extent_offset = found_key.offset -
+					btrfs_file_extent_offset(leaf, fi);
+
 				/* FIXME blocksize != 4096 */
 				num_dec = btrfs_file_extent_num_bytes(leaf, fi);
 				if (extent_start != 0) {
@@ -2723,8 +2719,6 @@ search_again:
 					if (root->ref_cows)
 						inode_sub_bytes(inode, num_dec);
 				}
-				root_gen = btrfs_header_generation(leaf);
-				root_owner = btrfs_header_owner(leaf);
 			}
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			/*
@@ -2768,12 +2762,12 @@ delete:
 		} else {
 			break;
 		}
-		if (found_extent) {
+		if (found_extent && root->ref_cows) {
 			btrfs_set_path_blocking(path);
 			ret = btrfs_free_extent(trans, root, extent_start,
-						extent_num_bytes,
-						leaf->start, root_owner,
-						root_gen, inode->i_ino, 0);
+						extent_num_bytes, 0,
+						btrfs_header_owner(leaf),
+						inode->i_ino, extent_offset);
 			BUG_ON(ret);
 		}
 next:
@@ -2811,7 +2805,6 @@ error:
 				      pending_del_nr);
 	}
 	btrfs_free_path(path);
-	inode->i_sb->s_dirt = 1;
 	return ret;
 }
 
@@ -3105,6 +3098,45 @@ static int fixup_tree_root_location(struct btrfs_root *root,
 	return 0;
 }
 
+static void inode_tree_add(struct inode *inode)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_inode *entry;
+	struct rb_node **p = &root->inode_tree.rb_node;
+	struct rb_node *parent = NULL;
+
+	spin_lock(&root->inode_lock);
+	while (*p) {
+		parent = *p;
+		entry = rb_entry(parent, struct btrfs_inode, rb_node);
+
+		if (inode->i_ino < entry->vfs_inode.i_ino)
+			p = &(*p)->rb_left;
+		else if (inode->i_ino > entry->vfs_inode.i_ino)
+			p = &(*p)->rb_right;
+		else {
+			WARN_ON(!(entry->vfs_inode.i_state &
+				  (I_WILL_FREE | I_FREEING | I_CLEAR)));
+			break;
+		}
+	}
+	rb_link_node(&BTRFS_I(inode)->rb_node, parent, p);
+	rb_insert_color(&BTRFS_I(inode)->rb_node, &root->inode_tree);
+	spin_unlock(&root->inode_lock);
+}
+
+static void inode_tree_del(struct inode *inode)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+
+	if (!RB_EMPTY_NODE(&BTRFS_I(inode)->rb_node)) {
+		spin_lock(&root->inode_lock);
+		rb_erase(&BTRFS_I(inode)->rb_node, &root->inode_tree);
+		spin_unlock(&root->inode_lock);
+		RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
+	}
+}
+
 static noinline void init_btrfs_i(struct inode *inode)
 {
 	struct btrfs_inode *bi = BTRFS_I(inode);
@@ -3130,6 +3162,7 @@ static noinline void init_btrfs_i(struct inode *inode)
 			     inode->i_mapping, GFP_NOFS);
 	INIT_LIST_HEAD(&BTRFS_I(inode)->delalloc_inodes);
 	INIT_LIST_HEAD(&BTRFS_I(inode)->ordered_operations);
+	RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
 	btrfs_ordered_inode_tree_init(&BTRFS_I(inode)->ordered_tree);
 	mutex_init(&BTRFS_I(inode)->extent_mutex);
 	mutex_init(&BTRFS_I(inode)->log_mutex);
@@ -3152,26 +3185,9 @@ static int btrfs_find_actor(struct inode *inode, void *opaque)
 		args->root == BTRFS_I(inode)->root;
 }
 
-struct inode *btrfs_ilookup(struct super_block *s, u64 objectid,
-			    struct btrfs_root *root, int wait)
-{
-	struct inode *inode;
-	struct btrfs_iget_args args;
-	args.ino = objectid;
-	args.root = root;
-
-	if (wait) {
-		inode = ilookup5(s, objectid, btrfs_find_actor,
-				 (void *)&args);
-	} else {
-		inode = ilookup5_nowait(s, objectid, btrfs_find_actor,
-					(void *)&args);
-	}
-	return inode;
-}
-
-struct inode *btrfs_iget_locked(struct super_block *s, u64 objectid,
-				struct btrfs_root *root)
+static struct inode *btrfs_iget_locked(struct super_block *s,
+				       u64 objectid,
+				       struct btrfs_root *root)
 {
 	struct inode *inode;
 	struct btrfs_iget_args args;
@@ -3188,24 +3204,21 @@ struct inode *btrfs_iget_locked(struct super_block *s, u64 objectid,
  * Returns in *is_new if the inode was read from disk
  */
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
-			 struct btrfs_root *root, int *is_new)
+			 struct btrfs_root *root)
 {
 	struct inode *inode;
 
 	inode = btrfs_iget_locked(s, location->objectid, root);
 	if (!inode)
-		return ERR_PTR(-EACCES);
+		return ERR_PTR(-ENOMEM);
 
 	if (inode->i_state & I_NEW) {
 		BTRFS_I(inode)->root = root;
 		memcpy(&BTRFS_I(inode)->location, location, sizeof(*location));
 		btrfs_read_locked_inode(inode);
+
+		inode_tree_add(inode);
 		unlock_new_inode(inode);
-		if (is_new)
-			*is_new = 1;
-	} else {
-		if (is_new)
-			*is_new = 0;
 	}
 
 	return inode;
@@ -3218,7 +3231,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 	struct btrfs_root *root = bi->root;
 	struct btrfs_root *sub_root = root;
 	struct btrfs_key location;
-	int ret, new;
+	int ret;
 
 	if (dentry->d_name.len > BTRFS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -3236,7 +3249,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 			return ERR_PTR(ret);
 		if (ret > 0)
 			return ERR_PTR(-ENOENT);
-		inode = btrfs_iget(dir->i_sb, &location, sub_root, &new);
+		inode = btrfs_iget(dir->i_sb, &location, sub_root);
 		if (IS_ERR(inode))
 			return ERR_CAST(inode);
 	}
@@ -3574,9 +3587,9 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 			btrfs_find_block_group(root, 0, alloc_hint, owner);
 	if ((mode & S_IFREG)) {
 		if (btrfs_test_opt(root, NODATASUM))
-			btrfs_set_flag(inode, NODATASUM);
+			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
 		if (btrfs_test_opt(root, NODATACOW))
-			btrfs_set_flag(inode, NODATACOW);
+			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW;
 	}
 
 	key[0].objectid = objectid;
@@ -3630,7 +3643,10 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	location->offset = 0;
 	btrfs_set_key_type(location, BTRFS_INODE_ITEM_KEY);
 
+	btrfs_inherit_iflags(inode, dir);
+
 	insert_inode_hash(inode);
+	inode_tree_add(inode);
 	return inode;
 fail:
 	if (dir)
@@ -3750,7 +3766,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 		init_special_inode(inode, inode->i_mode, rdev);
 		btrfs_update_inode(trans, root, inode);
 	}
-	dir->i_sb->s_dirt = 1;
 	btrfs_update_inode_block_group(trans, inode);
 	btrfs_update_inode_block_group(trans, dir);
 out_unlock:
@@ -3815,7 +3830,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 		inode->i_op = &btrfs_file_inode_operations;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	}
-	dir->i_sb->s_dirt = 1;
 	btrfs_update_inode_block_group(trans, inode);
 	btrfs_update_inode_block_group(trans, dir);
 out_unlock:
@@ -3862,7 +3876,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	if (err)
 		drop_inode = 1;
 
-	dir->i_sb->s_dirt = 1;
 	btrfs_update_inode_block_group(trans, dir);
 	err = btrfs_update_inode(trans, root, inode);
 
@@ -3944,7 +3957,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
 	d_instantiate(dentry, inode);
 	drop_on_err = 0;
-	dir->i_sb->s_dirt = 1;
 	btrfs_update_inode_block_group(trans, inode);
 	btrfs_update_inode_block_group(trans, dir);
 
@@ -4683,6 +4695,7 @@ void btrfs_destroy_inode(struct inode *inode)
 			btrfs_put_ordered_extent(ordered);
 		}
 	}
+	inode_tree_del(inode);
 	btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
 	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
 }
@@ -4972,7 +4985,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 		inode->i_op = &btrfs_file_inode_operations;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	}
-	dir->i_sb->s_dirt = 1;
 	btrfs_update_inode_block_group(trans, inode);
 	btrfs_update_inode_block_group(trans, dir);
 	if (drop_inode)
@@ -5061,7 +5073,7 @@ static int prealloc_file_range(struct btrfs_trans_handle *trans,
 out:
 	if (cur_offset > start) {
 		inode->i_ctime = CURRENT_TIME;
-		btrfs_set_flag(inode, PREALLOC);
+		BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC;
 		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
 		    cur_offset > i_size_read(inode))
 			btrfs_i_size_write(inode, cur_offset);
@@ -5182,7 +5194,7 @@ static int btrfs_set_page_dirty(struct page *page)
 
 static int btrfs_permission(struct inode *inode, int mask)
 {
-	if (btrfs_test_flag(inode, READONLY) && (mask & MAY_WRITE))
+	if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE))
 		return -EACCES;
 	return generic_permission(inode, mask, btrfs_check_acl);
 }
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2624b53ea783..eff18f5b5362 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -50,7 +50,177 @@
 #include "volumes.h"
 #include "locking.h"
 
+/* Mask out flags that are inappropriate for the given type of inode. */
+static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
+{
+	if (S_ISDIR(mode))
+		return flags;
+	else if (S_ISREG(mode))
+		return flags & ~FS_DIRSYNC_FL;
+	else
+		return flags & (FS_NODUMP_FL | FS_NOATIME_FL);
+}
 
+/*
+ * Export inode flags to the format expected by the FS_IOC_GETFLAGS ioctl.
+ */
+static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
+{
+	unsigned int iflags = 0;
+
+	if (flags & BTRFS_INODE_SYNC)
+		iflags |= FS_SYNC_FL;
+	if (flags & BTRFS_INODE_IMMUTABLE)
+		iflags |= FS_IMMUTABLE_FL;
+	if (flags & BTRFS_INODE_APPEND)
+		iflags |= FS_APPEND_FL;
+	if (flags & BTRFS_INODE_NODUMP)
+		iflags |= FS_NODUMP_FL;
+	if (flags & BTRFS_INODE_NOATIME)
+		iflags |= FS_NOATIME_FL;
+	if (flags & BTRFS_INODE_DIRSYNC)
+		iflags |= FS_DIRSYNC_FL;
+
+	return iflags;
+}
+
+/*
+ * Update inode->i_flags based on the btrfs internal flags.
+ */
+void btrfs_update_iflags(struct inode *inode)
+{
+	struct btrfs_inode *ip = BTRFS_I(inode);
+
+	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+
+	if (ip->flags & BTRFS_INODE_SYNC)
+		inode->i_flags |= S_SYNC;
+	if (ip->flags & BTRFS_INODE_IMMUTABLE)
+		inode->i_flags |= S_IMMUTABLE;
+	if (ip->flags & BTRFS_INODE_APPEND)
+		inode->i_flags |= S_APPEND;
+	if (ip->flags & BTRFS_INODE_NOATIME)
+		inode->i_flags |= S_NOATIME;
+	if (ip->flags & BTRFS_INODE_DIRSYNC)
+		inode->i_flags |= S_DIRSYNC;
+}
+
+/*
+ * Inherit flags from the parent inode.
+ *
+ * Unlike extN we don't have any flags we don't want to inherit currently.
+ */
+void btrfs_inherit_iflags(struct inode *inode, struct inode *dir)
+{
+	unsigned int flags;
+
+	if (!dir)
+		return;
+
+	flags = BTRFS_I(dir)->flags;
+
+	if (S_ISREG(inode->i_mode))
+		flags &= ~BTRFS_INODE_DIRSYNC;
+	else if (!S_ISDIR(inode->i_mode))
+		flags &= (BTRFS_INODE_NODUMP | BTRFS_INODE_NOATIME);
+
+	BTRFS_I(inode)->flags = flags;
+	btrfs_update_iflags(inode);
+}
+
+static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
+{
+	struct btrfs_inode *ip = BTRFS_I(file->f_path.dentry->d_inode);
+	unsigned int flags = btrfs_flags_to_ioctl(ip->flags);
+
+	if (copy_to_user(arg, &flags, sizeof(flags)))
+		return -EFAULT;
+	return 0;
+}
+
+static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct btrfs_inode *ip = BTRFS_I(inode);
+	struct btrfs_root *root = ip->root;
+	struct btrfs_trans_handle *trans;
+	unsigned int flags, oldflags;
+	int ret;
+
+	if (copy_from_user(&flags, arg, sizeof(flags)))
+		return -EFAULT;
+
+	if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
+		      FS_NOATIME_FL | FS_NODUMP_FL | \
+		      FS_SYNC_FL | FS_DIRSYNC_FL))
+		return -EOPNOTSUPP;
+
+	if (!is_owner_or_cap(inode))
+		return -EACCES;
+
+	mutex_lock(&inode->i_mutex);
+
+	flags = btrfs_mask_flags(inode->i_mode, flags);
+	oldflags = btrfs_flags_to_ioctl(ip->flags);
+	if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
+		if (!capable(CAP_LINUX_IMMUTABLE)) {
+			ret = -EPERM;
+			goto out_unlock;
+		}
+	}
+
+	ret = mnt_want_write(file->f_path.mnt);
+	if (ret)
+		goto out_unlock;
+
+	if (flags & FS_SYNC_FL)
+		ip->flags |= BTRFS_INODE_SYNC;
+	else
+		ip->flags &= ~BTRFS_INODE_SYNC;
+	if (flags & FS_IMMUTABLE_FL)
+		ip->flags |= BTRFS_INODE_IMMUTABLE;
+	else
+		ip->flags &= ~BTRFS_INODE_IMMUTABLE;
+	if (flags & FS_APPEND_FL)
+		ip->flags |= BTRFS_INODE_APPEND;
+	else
+		ip->flags &= ~BTRFS_INODE_APPEND;
+	if (flags & FS_NODUMP_FL)
+		ip->flags |= BTRFS_INODE_NODUMP;
+	else
+		ip->flags &= ~BTRFS_INODE_NODUMP;
+	if (flags & FS_NOATIME_FL)
+		ip->flags |= BTRFS_INODE_NOATIME;
+	else
+		ip->flags &= ~BTRFS_INODE_NOATIME;
+	if (flags & FS_DIRSYNC_FL)
+		ip->flags |= BTRFS_INODE_DIRSYNC;
+	else
+		ip->flags &= ~BTRFS_INODE_DIRSYNC;
+
+
+	trans = btrfs_join_transaction(root, 1);
+	BUG_ON(!trans);
+
+	ret = btrfs_update_inode(trans, root, inode);
+	BUG_ON(ret);
+
+	btrfs_update_iflags(inode);
+	inode->i_ctime = CURRENT_TIME;
+	btrfs_end_transaction(trans, root);
+
+	mnt_drop_write(file->f_path.mnt);
+ out_unlock:
+	mutex_unlock(&inode->i_mutex);
+	return 0;
+}
+
+static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+
+	return put_user(inode->i_generation, arg);
+}
 
 static noinline int create_subvol(struct btrfs_root *root,
 				  struct dentry *dentry,
@@ -82,22 +252,25 @@ static noinline int create_subvol(struct btrfs_root *root,
 	if (ret)
 		goto fail;
 
-	leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
-				      objectid, trans->transid, 0, 0, 0);
+	leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
+				      0, objectid, NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		goto fail;
 	}
 
-	btrfs_set_header_nritems(leaf, 0);
-	btrfs_set_header_level(leaf, 0);
+	memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_bytenr(leaf, leaf->start);
 	btrfs_set_header_generation(leaf, trans->transid);
+	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(leaf, objectid);
 
 	write_extent_buffer(leaf, root->fs_info->fsid,
 			    (unsigned long)btrfs_header_fsid(leaf),
 			    BTRFS_FSID_SIZE);
+	write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid,
+			    (unsigned long)btrfs_header_chunk_tree_uuid(leaf),
+			    BTRFS_UUID_SIZE);
 	btrfs_mark_buffer_dirty(leaf);
 
 	inode_item = &root_item.inode;
@@ -125,7 +298,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 	btrfs_set_root_dirid(&root_item, new_dirid);
 
 	key.objectid = objectid;
-	key.offset = 1;
+	key.offset = 0;
 	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
 	ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
 				&root_item);
@@ -911,10 +1084,10 @@ static long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 				if (disko) {
 					inode_add_bytes(inode, datal);
 					ret = btrfs_inc_extent_ref(trans, root,
-						   disko, diskl, leaf->start,
-						   root->root_key.objectid,
-						   trans->transid,
-						   inode->i_ino);
+							disko, diskl, 0,
+							root->root_key.objectid,
+							inode->i_ino,
+							new_key.offset - datao);
 					BUG_ON(ret);
 				}
 			} else if (type == BTRFS_FILE_EXTENT_INLINE) {
@@ -1074,6 +1247,12 @@ long btrfs_ioctl(struct file *file, unsigned int
 	void __user *argp = (void __user *)arg;
 
 	switch (cmd) {
+	case FS_IOC_GETFLAGS:
+		return btrfs_ioctl_getflags(file, argp);
+	case FS_IOC_SETFLAGS:
+		return btrfs_ioctl_setflags(file, argp);
+	case FS_IOC_GETVERSION:
+		return btrfs_ioctl_getversion(file, argp);
 	case BTRFS_IOC_SNAP_CREATE:
 		return btrfs_ioctl_snap_create(file, argp, 0);
 	case BTRFS_IOC_SUBVOL_CREATE:
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 5f8f218c1005..6d6523da0a30 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -45,22 +45,132 @@ static void print_dev_item(struct extent_buffer *eb,
 	       (unsigned long long)btrfs_device_total_bytes(eb, dev_item),
 	       (unsigned long long)btrfs_device_bytes_used(eb, dev_item));
 }
+static void print_extent_data_ref(struct extent_buffer *eb,
+				  struct btrfs_extent_data_ref *ref)
+{
+	printk(KERN_INFO "\t\textent data backref root %llu "
+	       "objectid %llu offset %llu count %u\n",
+	       (unsigned long long)btrfs_extent_data_ref_root(eb, ref),
+	       (unsigned long long)btrfs_extent_data_ref_objectid(eb, ref),
+	       (unsigned long long)btrfs_extent_data_ref_offset(eb, ref),
+	       btrfs_extent_data_ref_count(eb, ref));
+}
+
+static void print_extent_item(struct extent_buffer *eb, int slot)
+{
+	struct btrfs_extent_item *ei;
+	struct btrfs_extent_inline_ref *iref;
+	struct btrfs_extent_data_ref *dref;
+	struct btrfs_shared_data_ref *sref;
+	struct btrfs_disk_key key;
+	unsigned long end;
+	unsigned long ptr;
+	int type;
+	u32 item_size = btrfs_item_size_nr(eb, slot);
+	u64 flags;
+	u64 offset;
+
+	if (item_size < sizeof(*ei)) {
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+		struct btrfs_extent_item_v0 *ei0;
+		BUG_ON(item_size != sizeof(*ei0));
+		ei0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_item_v0);
+		printk(KERN_INFO "\t\textent refs %u\n",
+		       btrfs_extent_refs_v0(eb, ei0));
+		return;
+#else
+		BUG();
+#endif
+	}
+
+	ei = btrfs_item_ptr(eb, slot, struct btrfs_extent_item);
+	flags = btrfs_extent_flags(eb, ei);
+
+	printk(KERN_INFO "\t\textent refs %llu gen %llu flags %llu\n",
+	       (unsigned long long)btrfs_extent_refs(eb, ei),
+	       (unsigned long long)btrfs_extent_generation(eb, ei),
+	       (unsigned long long)flags);
+
+	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+		struct btrfs_tree_block_info *info;
+		info = (struct btrfs_tree_block_info *)(ei + 1);
+		btrfs_tree_block_key(eb, info, &key);
+		printk(KERN_INFO "\t\ttree block key (%llu %x %llu) "
+		       "level %d\n",
+		       (unsigned long long)btrfs_disk_key_objectid(&key),
+		       key.type,
+		       (unsigned long long)btrfs_disk_key_offset(&key),
+		       btrfs_tree_block_level(eb, info));
+		iref = (struct btrfs_extent_inline_ref *)(info + 1);
+	} else {
+		iref = (struct btrfs_extent_inline_ref *)(ei + 1);
+	}
+
+	ptr = (unsigned long)iref;
+	end = (unsigned long)ei + item_size;
+	while (ptr < end) {
+		iref = (struct btrfs_extent_inline_ref *)ptr;
+		type = btrfs_extent_inline_ref_type(eb, iref);
+		offset = btrfs_extent_inline_ref_offset(eb, iref);
+		switch (type) {
+		case BTRFS_TREE_BLOCK_REF_KEY:
+			printk(KERN_INFO "\t\ttree block backref "
+				"root %llu\n", (unsigned long long)offset);
+			break;
+		case BTRFS_SHARED_BLOCK_REF_KEY:
+			printk(KERN_INFO "\t\tshared block backref "
+				"parent %llu\n", (unsigned long long)offset);
+			break;
+		case BTRFS_EXTENT_DATA_REF_KEY:
+			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+			print_extent_data_ref(eb, dref);
+			break;
+		case BTRFS_SHARED_DATA_REF_KEY:
+			sref = (struct btrfs_shared_data_ref *)(iref + 1);
+			printk(KERN_INFO "\t\tshared data backref "
+			       "parent %llu count %u\n",
+			       (unsigned long long)offset,
+			       btrfs_shared_data_ref_count(eb, sref));
+			break;
+		default:
+			BUG();
+		}
+		ptr += btrfs_extent_inline_ref_size(type);
+	}
+	WARN_ON(ptr > end);
+}
+
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+static void print_extent_ref_v0(struct extent_buffer *eb, int slot)
+{
+	struct btrfs_extent_ref_v0 *ref0;
+
+	ref0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_ref_v0);
+	printk("\t\textent back ref root %llu gen %llu "
+		"owner %llu num_refs %lu\n",
+		(unsigned long long)btrfs_ref_root_v0(eb, ref0),
+		(unsigned long long)btrfs_ref_generation_v0(eb, ref0),
+		(unsigned long long)btrfs_ref_objectid_v0(eb, ref0),
+		(unsigned long)btrfs_ref_count_v0(eb, ref0));
+}
+#endif
+
 void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 {
 	int i;
+	u32 type;
 	u32 nr = btrfs_header_nritems(l);
 	struct btrfs_item *item;
-	struct btrfs_extent_item *ei;
 	struct btrfs_root_item *ri;
 	struct btrfs_dir_item *di;
 	struct btrfs_inode_item *ii;
 	struct btrfs_block_group_item *bi;
 	struct btrfs_file_extent_item *fi;
+	struct btrfs_extent_data_ref *dref;
+	struct btrfs_shared_data_ref *sref;
+	struct btrfs_dev_extent *dev_extent;
 	struct btrfs_key key;
 	struct btrfs_key found_key;
-	struct btrfs_extent_ref *ref;
-	struct btrfs_dev_extent *dev_extent;
-	u32 type;
 
 	printk(KERN_INFO "leaf %llu total ptrs %d free space %d\n",
 		(unsigned long long)btrfs_header_bytenr(l), nr,
@@ -100,20 +210,25 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 				btrfs_disk_root_refs(l, ri));
 			break;
 		case BTRFS_EXTENT_ITEM_KEY:
-			ei = btrfs_item_ptr(l, i, struct btrfs_extent_item);
-			printk(KERN_INFO "\t\textent data refs %u\n",
-				btrfs_extent_refs(l, ei));
+			print_extent_item(l, i);
 			break;
-		case BTRFS_EXTENT_REF_KEY:
-			ref = btrfs_item_ptr(l, i, struct btrfs_extent_ref);
-			printk(KERN_INFO "\t\textent back ref root %llu "
-			       "gen %llu owner %llu num_refs %lu\n",
-			       (unsigned long long)btrfs_ref_root(l, ref),
-			       (unsigned long long)btrfs_ref_generation(l, ref),
-			       (unsigned long long)btrfs_ref_objectid(l, ref),
-			       (unsigned long)btrfs_ref_num_refs(l, ref));
+		case BTRFS_TREE_BLOCK_REF_KEY:
+			printk(KERN_INFO "\t\ttree block backref\n");
+			break;
+		case BTRFS_SHARED_BLOCK_REF_KEY:
+			printk(KERN_INFO "\t\tshared block backref\n");
+			break;
+		case BTRFS_EXTENT_DATA_REF_KEY:
+			dref = btrfs_item_ptr(l, i,
+					      struct btrfs_extent_data_ref);
+			print_extent_data_ref(l, dref);
+			break;
+		case BTRFS_SHARED_DATA_REF_KEY:
+			sref = btrfs_item_ptr(l, i,
+					      struct btrfs_shared_data_ref);
+			printk(KERN_INFO "\t\tshared data backref count %u\n",
+			       btrfs_shared_data_ref_count(l, sref));
 			break;
-
 		case BTRFS_EXTENT_DATA_KEY:
 			fi = btrfs_item_ptr(l, i,
 					    struct btrfs_file_extent_item);
@@ -139,6 +254,12 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 			       (unsigned long long)
 			       btrfs_file_extent_ram_bytes(l, fi));
 			break;
+		case BTRFS_EXTENT_REF_V0_KEY:
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+			print_extent_ref_v0(l, i);
+#else
+			BUG();
+#endif
 		case BTRFS_BLOCK_GROUP_ITEM_KEY:
 			bi = btrfs_item_ptr(l, i,
 					    struct btrfs_block_group_item);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
new file mode 100644
index 000000000000..b23dc209ae10
--- /dev/null
+++ b/fs/btrfs/relocation.c
@@ -0,0 +1,3711 @@
+/*
+ * Copyright (C) 2009 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/sched.h>
+#include <linux/pagemap.h>
+#include <linux/writeback.h>
+#include <linux/blkdev.h>
+#include <linux/rbtree.h>
+#include "ctree.h"
+#include "disk-io.h"
+#include "transaction.h"
+#include "volumes.h"
+#include "locking.h"
+#include "btrfs_inode.h"
+#include "async-thread.h"
+
+/*
+ * backref_node, mapping_node and tree_block start with this
+ */
+struct tree_entry {
+	struct rb_node rb_node;
+	u64 bytenr;
+};
+
+/*
+ * present a tree block in the backref cache
+ */
+struct backref_node {
+	struct rb_node rb_node;
+	u64 bytenr;
+	/* objectid tree block owner */
+	u64 owner;
+	/* list of upper level blocks reference this block */
+	struct list_head upper;
+	/* list of child blocks in the cache */
+	struct list_head lower;
+	/* NULL if this node is not tree root */
+	struct btrfs_root *root;
+	/* extent buffer got by COW the block */
+	struct extent_buffer *eb;
+	/* level of tree block */
+	unsigned int level:8;
+	/* 1 if the block is root of old snapshot */
+	unsigned int old_root:1;
+	/* 1 if no child blocks in the cache */
+	unsigned int lowest:1;
+	/* is the extent buffer locked */
+	unsigned int locked:1;
+	/* has the block been processed */
+	unsigned int processed:1;
+	/* have backrefs of this block been checked */
+	unsigned int checked:1;
+};
+
+/*
+ * present a block pointer in the backref cache
+ */
+struct backref_edge {
+	struct list_head list[2];
+	struct backref_node *node[2];
+	u64 blockptr;
+};
+
+#define LOWER	0
+#define UPPER	1
+
+struct backref_cache {
+	/* red black tree of all backref nodes in the cache */
+	struct rb_root rb_root;
+	/* list of backref nodes with no child block in the cache */
+	struct list_head pending[BTRFS_MAX_LEVEL];
+	spinlock_t lock;
+};
+
+/*
+ * map address of tree root to tree
+ */
+struct mapping_node {
+	struct rb_node rb_node;
+	u64 bytenr;
+	void *data;
+};
+
+struct mapping_tree {
+	struct rb_root rb_root;
+	spinlock_t lock;
+};
+
+/*
+ * present a tree block to process
+ */
+struct tree_block {
+	struct rb_node rb_node;
+	u64 bytenr;
+	struct btrfs_key key;
+	unsigned int level:8;
+	unsigned int key_ready:1;
+};
+
+/* inode vector */
+#define INODEVEC_SIZE 16
+
+struct inodevec {
+	struct list_head list;
+	struct inode *inode[INODEVEC_SIZE];
+	int nr;
+};
+
+struct reloc_control {
+	/* block group to relocate */
+	struct btrfs_block_group_cache *block_group;
+	/* extent tree */
+	struct btrfs_root *extent_root;
+	/* inode for moving data */
+	struct inode *data_inode;
+	struct btrfs_workers workers;
+	/* tree blocks have been processed */
+	struct extent_io_tree processed_blocks;
+	/* map start of tree root to corresponding reloc tree */
+	struct mapping_tree reloc_root_tree;
+	/* list of reloc trees */
+	struct list_head reloc_roots;
+	u64 search_start;
+	u64 extents_found;
+	u64 extents_skipped;
+	int stage;
+	int create_reloc_root;
+	unsigned int found_file_extent:1;
+	unsigned int found_old_snapshot:1;
+};
+
+/* stages of data relocation */
+#define MOVE_DATA_EXTENTS	0
+#define UPDATE_DATA_PTRS	1
+
+/*
+ * merge reloc tree to corresponding fs tree in worker threads
+ */
+struct async_merge {
+	struct btrfs_work work;
+	struct reloc_control *rc;
+	struct btrfs_root *root;
+	struct completion *done;
+	atomic_t *num_pending;
+};
+
+static void mapping_tree_init(struct mapping_tree *tree)
+{
+	tree->rb_root.rb_node = NULL;
+	spin_lock_init(&tree->lock);
+}
+
+static void backref_cache_init(struct backref_cache *cache)
+{
+	int i;
+	cache->rb_root.rb_node = NULL;
+	for (i = 0; i < BTRFS_MAX_LEVEL; i++)
+		INIT_LIST_HEAD(&cache->pending[i]);
+	spin_lock_init(&cache->lock);
+}
+
+static void backref_node_init(struct backref_node *node)
+{
+	memset(node, 0, sizeof(*node));
+	INIT_LIST_HEAD(&node->upper);
+	INIT_LIST_HEAD(&node->lower);
+	RB_CLEAR_NODE(&node->rb_node);
+}
+
+static struct rb_node *tree_insert(struct rb_root *root, u64 bytenr,
+				   struct rb_node *node)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct tree_entry *entry;
+
+	while (*p) {
+		parent = *p;
+		entry = rb_entry(parent, struct tree_entry, rb_node);
+
+		if (bytenr < entry->bytenr)
+			p = &(*p)->rb_left;
+		else if (bytenr > entry->bytenr)
+			p = &(*p)->rb_right;
+		else
+			return parent;
+	}
+
+	rb_link_node(node, parent, p);
+	rb_insert_color(node, root);
+	return NULL;
+}
+
+static struct rb_node *tree_search(struct rb_root *root, u64 bytenr)
+{
+	struct rb_node *n = root->rb_node;
+	struct tree_entry *entry;
+
+	while (n) {
+		entry = rb_entry(n, struct tree_entry, rb_node);
+
+		if (bytenr < entry->bytenr)
+			n = n->rb_left;
+		else if (bytenr > entry->bytenr)
+			n = n->rb_right;
+		else
+			return n;
+	}
+	return NULL;
+}
+
+/*
+ * walk up backref nodes until reach node presents tree root
+ */
+static struct backref_node *walk_up_backref(struct backref_node *node,
+					    struct backref_edge *edges[],
+					    int *index)
+{
+	struct backref_edge *edge;
+	int idx = *index;
+
+	while (!list_empty(&node->upper)) {
+		edge = list_entry(node->upper.next,
+				  struct backref_edge, list[LOWER]);
+		edges[idx++] = edge;
+		node = edge->node[UPPER];
+	}
+	*index = idx;
+	return node;
+}
+
+/*
+ * walk down backref nodes to find start of next reference path
+ */
+static struct backref_node *walk_down_backref(struct backref_edge *edges[],
+					      int *index)
+{
+	struct backref_edge *edge;
+	struct backref_node *lower;
+	int idx = *index;
+
+	while (idx > 0) {
+		edge = edges[idx - 1];
+		lower = edge->node[LOWER];
+		if (list_is_last(&edge->list[LOWER], &lower->upper)) {
+			idx--;
+			continue;
+		}
+		edge = list_entry(edge->list[LOWER].next,
+				  struct backref_edge, list[LOWER]);
+		edges[idx - 1] = edge;
+		*index = idx;
+		return edge->node[UPPER];
+	}
+	*index = 0;
+	return NULL;
+}
+
+static void drop_node_buffer(struct backref_node *node)
+{
+	if (node->eb) {
+		if (node->locked) {
+			btrfs_tree_unlock(node->eb);
+			node->locked = 0;
+		}
+		free_extent_buffer(node->eb);
+		node->eb = NULL;
+	}
+}
+
+static void drop_backref_node(struct backref_cache *tree,
+			      struct backref_node *node)
+{
+	BUG_ON(!node->lowest);
+	BUG_ON(!list_empty(&node->upper));
+
+	drop_node_buffer(node);
+	list_del(&node->lower);
+
+	rb_erase(&node->rb_node, &tree->rb_root);
+	kfree(node);
+}
+
+/*
+ * remove a backref node from the backref cache
+ */
+static void remove_backref_node(struct backref_cache *cache,
+				struct backref_node *node)
+{
+	struct backref_node *upper;
+	struct backref_edge *edge;
+
+	if (!node)
+		return;
+
+	BUG_ON(!node->lowest);
+	while (!list_empty(&node->upper)) {
+		edge = list_entry(node->upper.next, struct backref_edge,
+				  list[LOWER]);
+		upper = edge->node[UPPER];
+		list_del(&edge->list[LOWER]);
+		list_del(&edge->list[UPPER]);
+		kfree(edge);
+		/*
+		 * add the node to pending list if no other
+		 * child block cached.
+		 */
+		if (list_empty(&upper->lower)) {
+			list_add_tail(&upper->lower,
+				      &cache->pending[upper->level]);
+			upper->lowest = 1;
+		}
+	}
+	drop_backref_node(cache, node);
+}
+
+/*
+ * find reloc tree by address of tree root
+ */
+static struct btrfs_root *find_reloc_root(struct reloc_control *rc,
+					  u64 bytenr)
+{
+	struct rb_node *rb_node;
+	struct mapping_node *node;
+	struct btrfs_root *root = NULL;
+
+	spin_lock(&rc->reloc_root_tree.lock);
+	rb_node = tree_search(&rc->reloc_root_tree.rb_root, bytenr);
+	if (rb_node) {
+		node = rb_entry(rb_node, struct mapping_node, rb_node);
+		root = (struct btrfs_root *)node->data;
+	}
+	spin_unlock(&rc->reloc_root_tree.lock);
+	return root;
+}
+
+static int is_cowonly_root(u64 root_objectid)
+{
+	if (root_objectid == BTRFS_ROOT_TREE_OBJECTID ||
+	    root_objectid == BTRFS_EXTENT_TREE_OBJECTID ||
+	    root_objectid == BTRFS_CHUNK_TREE_OBJECTID ||
+	    root_objectid == BTRFS_DEV_TREE_OBJECTID ||
+	    root_objectid == BTRFS_TREE_LOG_OBJECTID ||
+	    root_objectid == BTRFS_CSUM_TREE_OBJECTID)
+		return 1;
+	return 0;
+}
+
+static struct btrfs_root *read_fs_root(struct btrfs_fs_info *fs_info,
+					u64 root_objectid)
+{
+	struct btrfs_key key;
+
+	key.objectid = root_objectid;
+	key.type = BTRFS_ROOT_ITEM_KEY;
+	if (is_cowonly_root(root_objectid))
+		key.offset = 0;
+	else
+		key.offset = (u64)-1;
+
+	return btrfs_read_fs_root_no_name(fs_info, &key);
+}
+
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+static noinline_for_stack
+struct btrfs_root *find_tree_root(struct reloc_control *rc,
+				  struct extent_buffer *leaf,
+				  struct btrfs_extent_ref_v0 *ref0)
+{
+	struct btrfs_root *root;
+	u64 root_objectid = btrfs_ref_root_v0(leaf, ref0);
+	u64 generation = btrfs_ref_generation_v0(leaf, ref0);
+
+	BUG_ON(root_objectid == BTRFS_TREE_RELOC_OBJECTID);
+
+	root = read_fs_root(rc->extent_root->fs_info, root_objectid);
+	BUG_ON(IS_ERR(root));
+
+	if (root->ref_cows &&
+	    generation != btrfs_root_generation(&root->root_item))
+		return NULL;
+
+	return root;
+}
+#endif
+
+static noinline_for_stack
+int find_inline_backref(struct extent_buffer *leaf, int slot,
+			unsigned long *ptr, unsigned long *end)
+{
+	struct btrfs_extent_item *ei;
+	struct btrfs_tree_block_info *bi;
+	u32 item_size;
+
+	item_size = btrfs_item_size_nr(leaf, slot);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	if (item_size < sizeof(*ei)) {
+		WARN_ON(item_size != sizeof(struct btrfs_extent_item_v0));
+		return 1;
+	}
+#endif
+	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
+	WARN_ON(!(btrfs_extent_flags(leaf, ei) &
+		  BTRFS_EXTENT_FLAG_TREE_BLOCK));
+
+	if (item_size <= sizeof(*ei) + sizeof(*bi)) {
+		WARN_ON(item_size < sizeof(*ei) + sizeof(*bi));
+		return 1;
+	}
+
+	bi = (struct btrfs_tree_block_info *)(ei + 1);
+	*ptr = (unsigned long)(bi + 1);
+	*end = (unsigned long)ei + item_size;
+	return 0;
+}
+
+/*
+ * build backref tree for a given tree block. root of the backref tree
+ * corresponds the tree block, leaves of the backref tree correspond
+ * roots of b-trees that reference the tree block.
+ *
+ * the basic idea of this function is check backrefs of a given block
+ * to find upper level blocks that refernece the block, and then check
+ * bakcrefs of these upper level blocks recursively. the recursion stop
+ * when tree root is reached or backrefs for the block is cached.
+ *
+ * NOTE: if we find backrefs for a block are cached, we know backrefs
+ * for all upper level blocks that directly/indirectly reference the
+ * block are also cached.
+ */
+static struct backref_node *build_backref_tree(struct reloc_control *rc,
+					       struct backref_cache *cache,
+					       struct btrfs_key *node_key,
+					       int level, u64 bytenr)
+{
+	struct btrfs_path *path1;
+	struct btrfs_path *path2;
+	struct extent_buffer *eb;
+	struct btrfs_root *root;
+	struct backref_node *cur;
+	struct backref_node *upper;
+	struct backref_node *lower;
+	struct backref_node *node = NULL;
+	struct backref_node *exist = NULL;
+	struct backref_edge *edge;
+	struct rb_node *rb_node;
+	struct btrfs_key key;
+	unsigned long end;
+	unsigned long ptr;
+	LIST_HEAD(list);
+	int ret;
+	int err = 0;
+
+	path1 = btrfs_alloc_path();
+	path2 = btrfs_alloc_path();
+	if (!path1 || !path2) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	node = kmalloc(sizeof(*node), GFP_NOFS);
+	if (!node) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	backref_node_init(node);
+	node->bytenr = bytenr;
+	node->owner = 0;
+	node->level = level;
+	node->lowest = 1;
+	cur = node;
+again:
+	end = 0;
+	ptr = 0;
+	key.objectid = cur->bytenr;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = (u64)-1;
+
+	path1->search_commit_root = 1;
+	path1->skip_locking = 1;
+	ret = btrfs_search_slot(NULL, rc->extent_root, &key, path1,
+				0, 0);
+	if (ret < 0) {
+		err = ret;
+		goto out;
+	}
+	BUG_ON(!ret || !path1->slots[0]);
+
+	path1->slots[0]--;
+
+	WARN_ON(cur->checked);
+	if (!list_empty(&cur->upper)) {
+		/*
+		 * the backref was added previously when processsing
+		 * backref of type BTRFS_TREE_BLOCK_REF_KEY
+		 */
+		BUG_ON(!list_is_singular(&cur->upper));
+		edge = list_entry(cur->upper.next, struct backref_edge,
+				  list[LOWER]);
+		BUG_ON(!list_empty(&edge->list[UPPER]));
+		exist = edge->node[UPPER];
+		/*
+		 * add the upper level block to pending list if we need
+		 * check its backrefs
+		 */
+		if (!exist->checked)
+			list_add_tail(&edge->list[UPPER], &list);
+	} else {
+		exist = NULL;
+	}
+
+	while (1) {
+		cond_resched();
+		eb = path1->nodes[0];
+
+		if (ptr >= end) {
+			if (path1->slots[0] >= btrfs_header_nritems(eb)) {
+				ret = btrfs_next_leaf(rc->extent_root, path1);
+				if (ret < 0) {
+					err = ret;
+					goto out;
+				}
+				if (ret > 0)
+					break;
+				eb = path1->nodes[0];
+			}
+
+			btrfs_item_key_to_cpu(eb, &key, path1->slots[0]);
+			if (key.objectid != cur->bytenr) {
+				WARN_ON(exist);
+				break;
+			}
+
+			if (key.type == BTRFS_EXTENT_ITEM_KEY) {
+				ret = find_inline_backref(eb, path1->slots[0],
+							  &ptr, &end);
+				if (ret)
+					goto next;
+			}
+		}
+
+		if (ptr < end) {
+			/* update key for inline back ref */
+			struct btrfs_extent_inline_ref *iref;
+			iref = (struct btrfs_extent_inline_ref *)ptr;
+			key.type = btrfs_extent_inline_ref_type(eb, iref);
+			key.offset = btrfs_extent_inline_ref_offset(eb, iref);
+			WARN_ON(key.type != BTRFS_TREE_BLOCK_REF_KEY &&
+				key.type != BTRFS_SHARED_BLOCK_REF_KEY);
+		}
+
+		if (exist &&
+		    ((key.type == BTRFS_TREE_BLOCK_REF_KEY &&
+		      exist->owner == key.offset) ||
+		     (key.type == BTRFS_SHARED_BLOCK_REF_KEY &&
+		      exist->bytenr == key.offset))) {
+			exist = NULL;
+			goto next;
+		}
+
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY ||
+		    key.type == BTRFS_EXTENT_REF_V0_KEY) {
+			if (key.objectid == key.offset &&
+			    key.type == BTRFS_EXTENT_REF_V0_KEY) {
+				struct btrfs_extent_ref_v0 *ref0;
+				ref0 = btrfs_item_ptr(eb, path1->slots[0],
+						struct btrfs_extent_ref_v0);
+				root = find_tree_root(rc, eb, ref0);
+				if (root)
+					cur->root = root;
+				else
+					cur->old_root = 1;
+				break;
+			}
+#else
+		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
+		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
+#endif
+			if (key.objectid == key.offset) {
+				/*
+				 * only root blocks of reloc trees use
+				 * backref of this type.
+				 */
+				root = find_reloc_root(rc, cur->bytenr);
+				BUG_ON(!root);
+				cur->root = root;
+				break;
+			}
+
+			edge = kzalloc(sizeof(*edge), GFP_NOFS);
+			if (!edge) {
+				err = -ENOMEM;
+				goto out;
+			}
+			rb_node = tree_search(&cache->rb_root, key.offset);
+			if (!rb_node) {
+				upper = kmalloc(sizeof(*upper), GFP_NOFS);
+				if (!upper) {
+					kfree(edge);
+					err = -ENOMEM;
+					goto out;
+				}
+				backref_node_init(upper);
+				upper->bytenr = key.offset;
+				upper->owner = 0;
+				upper->level = cur->level + 1;
+				/*
+				 *  backrefs for the upper level block isn't
+				 *  cached, add the block to pending list
+				 */
+				list_add_tail(&edge->list[UPPER], &list);
+			} else {
+				upper = rb_entry(rb_node, struct backref_node,
+						 rb_node);
+				INIT_LIST_HEAD(&edge->list[UPPER]);
+			}
+			list_add(&edge->list[LOWER], &cur->upper);
+			edge->node[UPPER] = upper;
+			edge->node[LOWER] = cur;
+
+			goto next;
+		} else if (key.type != BTRFS_TREE_BLOCK_REF_KEY) {
+			goto next;
+		}
+
+		/* key.type == BTRFS_TREE_BLOCK_REF_KEY */
+		root = read_fs_root(rc->extent_root->fs_info, key.offset);
+		if (IS_ERR(root)) {
+			err = PTR_ERR(root);
+			goto out;
+		}
+
+		if (btrfs_root_level(&root->root_item) == cur->level) {
+			/* tree root */
+			BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+			       cur->bytenr);
+			cur->root = root;
+			break;
+		}
+
+		level = cur->level + 1;
+
+		/*
+		 * searching the tree to find upper level blocks
+		 * reference the block.
+		 */
+		path2->search_commit_root = 1;
+		path2->skip_locking = 1;
+		path2->lowest_level = level;
+		ret = btrfs_search_slot(NULL, root, node_key, path2, 0, 0);
+		path2->lowest_level = 0;
+		if (ret < 0) {
+			err = ret;
+			goto out;
+		}
+
+		eb = path2->nodes[level];
+		WARN_ON(btrfs_node_blockptr(eb, path2->slots[level]) !=
+			cur->bytenr);
+
+		lower = cur;
+		for (; level < BTRFS_MAX_LEVEL; level++) {
+			if (!path2->nodes[level]) {
+				BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+				       lower->bytenr);
+				lower->root = root;
+				break;
+			}
+
+			edge = kzalloc(sizeof(*edge), GFP_NOFS);
+			if (!edge) {
+				err = -ENOMEM;
+				goto out;
+			}
+
+			eb = path2->nodes[level];
+			rb_node = tree_search(&cache->rb_root, eb->start);
+			if (!rb_node) {
+				upper = kmalloc(sizeof(*upper), GFP_NOFS);
+				if (!upper) {
+					kfree(edge);
+					err = -ENOMEM;
+					goto out;
+				}
+				backref_node_init(upper);
+				upper->bytenr = eb->start;
+				upper->owner = btrfs_header_owner(eb);
+				upper->level = lower->level + 1;
+
+				/*
+				 * if we know the block isn't shared
+				 * we can void checking its backrefs.
+				 */
+				if (btrfs_block_can_be_shared(root, eb))
+					upper->checked = 0;
+				else
+					upper->checked = 1;
+
+				/*
+				 * add the block to pending list if we
+				 * need check its backrefs. only block
+				 * at 'cur->level + 1' is added to the
+				 * tail of pending list. this guarantees
+				 * we check backrefs from lower level
+				 * blocks to upper level blocks.
+				 */
+				if (!upper->checked &&
+				    level == cur->level + 1) {
+					list_add_tail(&edge->list[UPPER],
+						      &list);
+				} else
+					INIT_LIST_HEAD(&edge->list[UPPER]);
+			} else {
+				upper = rb_entry(rb_node, struct backref_node,
+						 rb_node);
+				BUG_ON(!upper->checked);
+				INIT_LIST_HEAD(&edge->list[UPPER]);
+			}
+			list_add_tail(&edge->list[LOWER], &lower->upper);
+			edge->node[UPPER] = upper;
+			edge->node[LOWER] = lower;
+
+			if (rb_node)
+				break;
+			lower = upper;
+			upper = NULL;
+		}
+		btrfs_release_path(root, path2);
+next:
+		if (ptr < end) {
+			ptr += btrfs_extent_inline_ref_size(key.type);
+			if (ptr >= end) {
+				WARN_ON(ptr > end);
+				ptr = 0;
+				end = 0;
+			}
+		}
+		if (ptr >= end)
+			path1->slots[0]++;
+	}
+	btrfs_release_path(rc->extent_root, path1);
+
+	cur->checked = 1;
+	WARN_ON(exist);
+
+	/* the pending list isn't empty, take the first block to process */
+	if (!list_empty(&list)) {
+		edge = list_entry(list.next, struct backref_edge, list[UPPER]);
+		list_del_init(&edge->list[UPPER]);
+		cur = edge->node[UPPER];
+		goto again;
+	}
+
+	/*
+	 * everything goes well, connect backref nodes and insert backref nodes
+	 * into the cache.
+	 */
+	BUG_ON(!node->checked);
+	rb_node = tree_insert(&cache->rb_root, node->bytenr, &node->rb_node);
+	BUG_ON(rb_node);
+
+	list_for_each_entry(edge, &node->upper, list[LOWER])
+		list_add_tail(&edge->list[UPPER], &list);
+
+	while (!list_empty(&list)) {
+		edge = list_entry(list.next, struct backref_edge, list[UPPER]);
+		list_del_init(&edge->list[UPPER]);
+		upper = edge->node[UPPER];
+
+		if (!RB_EMPTY_NODE(&upper->rb_node)) {
+			if (upper->lowest) {
+				list_del_init(&upper->lower);
+				upper->lowest = 0;
+			}
+
+			list_add_tail(&edge->list[UPPER], &upper->lower);
+			continue;
+		}
+
+		BUG_ON(!upper->checked);
+		rb_node = tree_insert(&cache->rb_root, upper->bytenr,
+				      &upper->rb_node);
+		BUG_ON(rb_node);
+
+		list_add_tail(&edge->list[UPPER], &upper->lower);
+
+		list_for_each_entry(edge, &upper->upper, list[LOWER])
+			list_add_tail(&edge->list[UPPER], &list);
+	}
+out:
+	btrfs_free_path(path1);
+	btrfs_free_path(path2);
+	if (err) {
+		INIT_LIST_HEAD(&list);
+		upper = node;
+		while (upper) {
+			if (RB_EMPTY_NODE(&upper->rb_node)) {
+				list_splice_tail(&upper->upper, &list);
+				kfree(upper);
+			}
+
+			if (list_empty(&list))
+				break;
+
+			edge = list_entry(list.next, struct backref_edge,
+					  list[LOWER]);
+			upper = edge->node[UPPER];
+			kfree(edge);
+		}
+		return ERR_PTR(err);
+	}
+	return node;
+}
+
+/*
+ * helper to add 'address of tree root -> reloc tree' mapping
+ */
+static int __add_reloc_root(struct btrfs_root *root)
+{
+	struct rb_node *rb_node;
+	struct mapping_node *node;
+	struct reloc_control *rc = root->fs_info->reloc_ctl;
+
+	node = kmalloc(sizeof(*node), GFP_NOFS);
+	BUG_ON(!node);
+
+	node->bytenr = root->node->start;
+	node->data = root;
+
+	spin_lock(&rc->reloc_root_tree.lock);
+	rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
+			      node->bytenr, &node->rb_node);
+	spin_unlock(&rc->reloc_root_tree.lock);
+	BUG_ON(rb_node);
+
+	list_add_tail(&root->root_list, &rc->reloc_roots);
+	return 0;
+}
+
+/*
+ * helper to update/delete the 'address of tree root -> reloc tree'
+ * mapping
+ */
+static int __update_reloc_root(struct btrfs_root *root, int del)
+{
+	struct rb_node *rb_node;
+	struct mapping_node *node = NULL;
+	struct reloc_control *rc = root->fs_info->reloc_ctl;
+
+	spin_lock(&rc->reloc_root_tree.lock);
+	rb_node = tree_search(&rc->reloc_root_tree.rb_root,
+			      root->commit_root->start);
+	if (rb_node) {
+		node = rb_entry(rb_node, struct mapping_node, rb_node);
+		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
+	}
+	spin_unlock(&rc->reloc_root_tree.lock);
+
+	BUG_ON((struct btrfs_root *)node->data != root);
+
+	if (!del) {
+		spin_lock(&rc->reloc_root_tree.lock);
+		node->bytenr = root->node->start;
+		rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
+				      node->bytenr, &node->rb_node);
+		spin_unlock(&rc->reloc_root_tree.lock);
+		BUG_ON(rb_node);
+	} else {
+		list_del_init(&root->root_list);
+		kfree(node);
+	}
+	return 0;
+}
+
+/*
+ * create reloc tree for a given fs tree. reloc tree is just a
+ * snapshot of the fs tree with special root objectid.
+ */
+int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
+			  struct btrfs_root *root)
+{
+	struct btrfs_root *reloc_root;
+	struct extent_buffer *eb;
+	struct btrfs_root_item *root_item;
+	struct btrfs_key root_key;
+	int ret;
+
+	if (root->reloc_root) {
+		reloc_root = root->reloc_root;
+		reloc_root->last_trans = trans->transid;
+		return 0;
+	}
+
+	if (!root->fs_info->reloc_ctl ||
+	    !root->fs_info->reloc_ctl->create_reloc_root ||
+	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+		return 0;
+
+	root_item = kmalloc(sizeof(*root_item), GFP_NOFS);
+	BUG_ON(!root_item);
+
+	root_key.objectid = BTRFS_TREE_RELOC_OBJECTID;
+	root_key.type = BTRFS_ROOT_ITEM_KEY;
+	root_key.offset = root->root_key.objectid;
+
+	ret = btrfs_copy_root(trans, root, root->commit_root, &eb,
+			      BTRFS_TREE_RELOC_OBJECTID);
+	BUG_ON(ret);
+
+	btrfs_set_root_last_snapshot(&root->root_item, trans->transid - 1);
+	memcpy(root_item, &root->root_item, sizeof(*root_item));
+	btrfs_set_root_refs(root_item, 1);
+	btrfs_set_root_bytenr(root_item, eb->start);
+	btrfs_set_root_level(root_item, btrfs_header_level(eb));
+	btrfs_set_root_generation(root_item, trans->transid);
+	memset(&root_item->drop_progress, 0, sizeof(struct btrfs_disk_key));
+	root_item->drop_level = 0;
+
+	btrfs_tree_unlock(eb);
+	free_extent_buffer(eb);
+
+	ret = btrfs_insert_root(trans, root->fs_info->tree_root,
+				&root_key, root_item);
+	BUG_ON(ret);
+	kfree(root_item);
+
+	reloc_root = btrfs_read_fs_root_no_radix(root->fs_info->tree_root,
+						 &root_key);
+	BUG_ON(IS_ERR(reloc_root));
+	reloc_root->last_trans = trans->transid;
+
+	__add_reloc_root(reloc_root);
+	root->reloc_root = reloc_root;
+	return 0;
+}
+
+/*
+ * update root item of reloc tree
+ */
+int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root)
+{
+	struct btrfs_root *reloc_root;
+	struct btrfs_root_item *root_item;
+	int del = 0;
+	int ret;
+
+	if (!root->reloc_root)
+		return 0;
+
+	reloc_root = root->reloc_root;
+	root_item = &reloc_root->root_item;
+
+	if (btrfs_root_refs(root_item) == 0) {
+		root->reloc_root = NULL;
+		del = 1;
+	}
+
+	__update_reloc_root(reloc_root, del);
+
+	if (reloc_root->commit_root != reloc_root->node) {
+		btrfs_set_root_node(root_item, reloc_root->node);
+		free_extent_buffer(reloc_root->commit_root);
+		reloc_root->commit_root = btrfs_root_node(reloc_root);
+	}
+
+	ret = btrfs_update_root(trans, root->fs_info->tree_root,
+				&reloc_root->root_key, root_item);
+	BUG_ON(ret);
+	return 0;
+}
+
+/*
+ * helper to find first cached inode with inode number >= objectid
+ * in a subvolume
+ */
+static struct inode *find_next_inode(struct btrfs_root *root, u64 objectid)
+{
+	struct rb_node *node;
+	struct rb_node *prev;
+	struct btrfs_inode *entry;
+	struct inode *inode;
+
+	spin_lock(&root->inode_lock);
+again:
+	node = root->inode_tree.rb_node;
+	prev = NULL;
+	while (node) {
+		prev = node;
+		entry = rb_entry(node, struct btrfs_inode, rb_node);
+
+		if (objectid < entry->vfs_inode.i_ino)
+			node = node->rb_left;
+		else if (objectid > entry->vfs_inode.i_ino)
+			node = node->rb_right;
+		else
+			break;
+	}
+	if (!node) {
+		while (prev) {
+			entry = rb_entry(prev, struct btrfs_inode, rb_node);
+			if (objectid <= entry->vfs_inode.i_ino) {
+				node = prev;
+				break;
+			}
+			prev = rb_next(prev);
+		}
+	}
+	while (node) {
+		entry = rb_entry(node, struct btrfs_inode, rb_node);
+		inode = igrab(&entry->vfs_inode);
+		if (inode) {
+			spin_unlock(&root->inode_lock);
+			return inode;
+		}
+
+		objectid = entry->vfs_inode.i_ino + 1;
+		if (cond_resched_lock(&root->inode_lock))
+			goto again;
+
+		node = rb_next(node);
+	}
+	spin_unlock(&root->inode_lock);
+	return NULL;
+}
+
+static int in_block_group(u64 bytenr,
+			  struct btrfs_block_group_cache *block_group)
+{
+	if (bytenr >= block_group->key.objectid &&
+	    bytenr < block_group->key.objectid + block_group->key.offset)
+		return 1;
+	return 0;
+}
+
+/*
+ * get new location of data
+ */
+static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr,
+			    u64 bytenr, u64 num_bytes)
+{
+	struct btrfs_root *root = BTRFS_I(reloc_inode)->root;
+	struct btrfs_path *path;
+	struct btrfs_file_extent_item *fi;
+	struct extent_buffer *leaf;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	bytenr -= BTRFS_I(reloc_inode)->index_cnt;
+	ret = btrfs_lookup_file_extent(NULL, root, path, reloc_inode->i_ino,
+				       bytenr, 0);
+	if (ret < 0)
+		goto out;
+	if (ret > 0) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	leaf = path->nodes[0];
+	fi = btrfs_item_ptr(leaf, path->slots[0],
+			    struct btrfs_file_extent_item);
+
+	BUG_ON(btrfs_file_extent_offset(leaf, fi) ||
+	       btrfs_file_extent_compression(leaf, fi) ||
+	       btrfs_file_extent_encryption(leaf, fi) ||
+	       btrfs_file_extent_other_encoding(leaf, fi));
+
+	if (num_bytes != btrfs_file_extent_disk_num_bytes(leaf, fi)) {
+		ret = 1;
+		goto out;
+	}
+
+	if (new_bytenr)
+		*new_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+/*
+ * update file extent items in the tree leaf to point to
+ * the new locations.
+ */
+static int replace_file_extents(struct btrfs_trans_handle *trans,
+				struct reloc_control *rc,
+				struct btrfs_root *root,
+				struct extent_buffer *leaf,
+				struct list_head *inode_list)
+{
+	struct btrfs_key key;
+	struct btrfs_file_extent_item *fi;
+	struct inode *inode = NULL;
+	struct inodevec *ivec = NULL;
+	u64 parent;
+	u64 bytenr;
+	u64 new_bytenr;
+	u64 num_bytes;
+	u64 end;
+	u32 nritems;
+	u32 i;
+	int ret;
+	int first = 1;
+	int dirty = 0;
+
+	if (rc->stage != UPDATE_DATA_PTRS)
+		return 0;
+
+	/* reloc trees always use full backref */
+	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+		parent = leaf->start;
+	else
+		parent = 0;
+
+	nritems = btrfs_header_nritems(leaf);
+	for (i = 0; i < nritems; i++) {
+		cond_resched();
+		btrfs_item_key_to_cpu(leaf, &key, i);
+		if (key.type != BTRFS_EXTENT_DATA_KEY)
+			continue;
+		fi = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
+		if (btrfs_file_extent_type(leaf, fi) ==
+		    BTRFS_FILE_EXTENT_INLINE)
+			continue;
+		bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
+		num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
+		if (bytenr == 0)
+			continue;
+		if (!in_block_group(bytenr, rc->block_group))
+			continue;
+
+		/*
+		 * if we are modifying block in fs tree, wait for readpage
+		 * to complete and drop the extent cache
+		 */
+		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
+			if (!ivec || ivec->nr == INODEVEC_SIZE) {
+				ivec = kmalloc(sizeof(*ivec), GFP_NOFS);
+				BUG_ON(!ivec);
+				ivec->nr = 0;
+				list_add_tail(&ivec->list, inode_list);
+			}
+			if (first) {
+				inode = find_next_inode(root, key.objectid);
+				if (inode)
+					ivec->inode[ivec->nr++] = inode;
+				first = 0;
+			} else if (inode && inode->i_ino < key.objectid) {
+				inode = find_next_inode(root, key.objectid);
+				if (inode)
+					ivec->inode[ivec->nr++] = inode;
+			}
+			if (inode && inode->i_ino == key.objectid) {
+				end = key.offset +
+				      btrfs_file_extent_num_bytes(leaf, fi);
+				WARN_ON(!IS_ALIGNED(key.offset,
+						    root->sectorsize));
+				WARN_ON(!IS_ALIGNED(end, root->sectorsize));
+				end--;
+				ret = try_lock_extent(&BTRFS_I(inode)->io_tree,
+						      key.offset, end,
+						      GFP_NOFS);
+				if (!ret)
+					continue;
+
+				btrfs_drop_extent_cache(inode, key.offset, end,
+							1);
+				unlock_extent(&BTRFS_I(inode)->io_tree,
+					      key.offset, end, GFP_NOFS);
+			}
+		}
+
+		ret = get_new_location(rc->data_inode, &new_bytenr,
+				       bytenr, num_bytes);
+		if (ret > 0)
+			continue;
+		BUG_ON(ret < 0);
+
+		btrfs_set_file_extent_disk_bytenr(leaf, fi, new_bytenr);
+		dirty = 1;
+
+		key.offset -= btrfs_file_extent_offset(leaf, fi);
+		ret = btrfs_inc_extent_ref(trans, root, new_bytenr,
+					   num_bytes, parent,
+					   btrfs_header_owner(leaf),
+					   key.objectid, key.offset);
+		BUG_ON(ret);
+
+		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
+					parent, btrfs_header_owner(leaf),
+					key.objectid, key.offset);
+		BUG_ON(ret);
+	}
+	if (dirty)
+		btrfs_mark_buffer_dirty(leaf);
+	return 0;
+}
+
+static noinline_for_stack
+int memcmp_node_keys(struct extent_buffer *eb, int slot,
+		     struct btrfs_path *path, int level)
+{
+	struct btrfs_disk_key key1;
+	struct btrfs_disk_key key2;
+	btrfs_node_key(eb, &key1, slot);
+	btrfs_node_key(path->nodes[level], &key2, path->slots[level]);
+	return memcmp(&key1, &key2, sizeof(key1));
+}
+
+/*
+ * try to replace tree blocks in fs tree with the new blocks
+ * in reloc tree. tree blocks haven't been modified since the
+ * reloc tree was create can be replaced.
+ *
+ * if a block was replaced, level of the block + 1 is returned.
+ * if no block got replaced, 0 is returned. if there are other
+ * errors, a negative error number is returned.
+ */
+static int replace_path(struct btrfs_trans_handle *trans,
+			struct btrfs_root *dest, struct btrfs_root *src,
+			struct btrfs_path *path, struct btrfs_key *next_key,
+			struct extent_buffer **leaf,
+			int lowest_level, int max_level)
+{
+	struct extent_buffer *eb;
+	struct extent_buffer *parent;
+	struct btrfs_key key;
+	u64 old_bytenr;
+	u64 new_bytenr;
+	u64 old_ptr_gen;
+	u64 new_ptr_gen;
+	u64 last_snapshot;
+	u32 blocksize;
+	int level;
+	int ret;
+	int slot;
+
+	BUG_ON(src->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
+	BUG_ON(dest->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID);
+	BUG_ON(lowest_level > 1 && leaf);
+
+	last_snapshot = btrfs_root_last_snapshot(&src->root_item);
+
+	slot = path->slots[lowest_level];
+	btrfs_node_key_to_cpu(path->nodes[lowest_level], &key, slot);
+
+	eb = btrfs_lock_root_node(dest);
+	btrfs_set_lock_blocking(eb);
+	level = btrfs_header_level(eb);
+
+	if (level < lowest_level) {
+		btrfs_tree_unlock(eb);
+		free_extent_buffer(eb);
+		return 0;
+	}
+
+	ret = btrfs_cow_block(trans, dest, eb, NULL, 0, &eb);
+	BUG_ON(ret);
+	btrfs_set_lock_blocking(eb);
+
+	if (next_key) {
+		next_key->objectid = (u64)-1;
+		next_key->type = (u8)-1;
+		next_key->offset = (u64)-1;
+	}
+
+	parent = eb;
+	while (1) {
+		level = btrfs_header_level(parent);
+		BUG_ON(level < lowest_level);
+
+		ret = btrfs_bin_search(parent, &key, level, &slot);
+		if (ret && slot > 0)
+			slot--;
+
+		if (next_key && slot + 1 < btrfs_header_nritems(parent))
+			btrfs_node_key_to_cpu(parent, next_key, slot + 1);
+
+		old_bytenr = btrfs_node_blockptr(parent, slot);
+		blocksize = btrfs_level_size(dest, level - 1);
+		old_ptr_gen = btrfs_node_ptr_generation(parent, slot);
+
+		if (level <= max_level) {
+			eb = path->nodes[level];
+			new_bytenr = btrfs_node_blockptr(eb,
+							path->slots[level]);
+			new_ptr_gen = btrfs_node_ptr_generation(eb,
+							path->slots[level]);
+		} else {
+			new_bytenr = 0;
+			new_ptr_gen = 0;
+		}
+
+		if (new_bytenr > 0 && new_bytenr == old_bytenr) {
+			WARN_ON(1);
+			ret = level;
+			break;
+		}
+
+		if (new_bytenr == 0 || old_ptr_gen > last_snapshot ||
+		    memcmp_node_keys(parent, slot, path, level)) {
+			if (level <= lowest_level && !leaf) {
+				ret = 0;
+				break;
+			}
+
+			eb = read_tree_block(dest, old_bytenr, blocksize,
+					     old_ptr_gen);
+			btrfs_tree_lock(eb);
+			ret = btrfs_cow_block(trans, dest, eb, parent,
+					      slot, &eb);
+			BUG_ON(ret);
+			btrfs_set_lock_blocking(eb);
+
+			if (level <= lowest_level) {
+				*leaf = eb;
+				ret = 0;
+				break;
+			}
+
+			btrfs_tree_unlock(parent);
+			free_extent_buffer(parent);
+
+			parent = eb;
+			continue;
+		}
+
+		btrfs_node_key_to_cpu(path->nodes[level], &key,
+				      path->slots[level]);
+		btrfs_release_path(src, path);
+
+		path->lowest_level = level;
+		ret = btrfs_search_slot(trans, src, &key, path, 0, 1);
+		path->lowest_level = 0;
+		BUG_ON(ret);
+
+		/*
+		 * swap blocks in fs tree and reloc tree.
+		 */
+		btrfs_set_node_blockptr(parent, slot, new_bytenr);
+		btrfs_set_node_ptr_generation(parent, slot, new_ptr_gen);
+		btrfs_mark_buffer_dirty(parent);
+
+		btrfs_set_node_blockptr(path->nodes[level],
+					path->slots[level], old_bytenr);
+		btrfs_set_node_ptr_generation(path->nodes[level],
+					      path->slots[level], old_ptr_gen);
+		btrfs_mark_buffer_dirty(path->nodes[level]);
+
+		ret = btrfs_inc_extent_ref(trans, src, old_bytenr, blocksize,
+					path->nodes[level]->start,
+					src->root_key.objectid, level - 1, 0);
+		BUG_ON(ret);
+		ret = btrfs_inc_extent_ref(trans, dest, new_bytenr, blocksize,
+					0, dest->root_key.objectid, level - 1,
+					0);
+		BUG_ON(ret);
+
+		ret = btrfs_free_extent(trans, src, new_bytenr, blocksize,
+					path->nodes[level]->start,
+					src->root_key.objectid, level - 1, 0);
+		BUG_ON(ret);
+
+		ret = btrfs_free_extent(trans, dest, old_bytenr, blocksize,
+					0, dest->root_key.objectid, level - 1,
+					0);
+		BUG_ON(ret);
+
+		btrfs_unlock_up_safe(path, 0);
+
+		ret = level;
+		break;
+	}
+	btrfs_tree_unlock(parent);
+	free_extent_buffer(parent);
+	return ret;
+}
+
+/*
+ * helper to find next relocated block in reloc tree
+ */
+static noinline_for_stack
+int walk_up_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
+		       int *level)
+{
+	struct extent_buffer *eb;
+	int i;
+	u64 last_snapshot;
+	u32 nritems;
+
+	last_snapshot = btrfs_root_last_snapshot(&root->root_item);
+
+	for (i = 0; i < *level; i++) {
+		free_extent_buffer(path->nodes[i]);
+		path->nodes[i] = NULL;
+	}
+
+	for (i = *level; i < BTRFS_MAX_LEVEL && path->nodes[i]; i++) {
+		eb = path->nodes[i];
+		nritems = btrfs_header_nritems(eb);
+		while (path->slots[i] + 1 < nritems) {
+			path->slots[i]++;
+			if (btrfs_node_ptr_generation(eb, path->slots[i]) <=
+			    last_snapshot)
+				continue;
+
+			*level = i;
+			return 0;
+		}
+		free_extent_buffer(path->nodes[i]);
+		path->nodes[i] = NULL;
+	}
+	return 1;
+}
+
+/*
+ * walk down reloc tree to find relocated block of lowest level
+ */
+static noinline_for_stack
+int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
+			 int *level)
+{
+	struct extent_buffer *eb = NULL;
+	int i;
+	u64 bytenr;
+	u64 ptr_gen = 0;
+	u64 last_snapshot;
+	u32 blocksize;
+	u32 nritems;
+
+	last_snapshot = btrfs_root_last_snapshot(&root->root_item);
+
+	for (i = *level; i > 0; i--) {
+		eb = path->nodes[i];
+		nritems = btrfs_header_nritems(eb);
+		while (path->slots[i] < nritems) {
+			ptr_gen = btrfs_node_ptr_generation(eb, path->slots[i]);
+			if (ptr_gen > last_snapshot)
+				break;
+			path->slots[i]++;
+		}
+		if (path->slots[i] >= nritems) {
+			if (i == *level)
+				break;
+			*level = i + 1;
+			return 0;
+		}
+		if (i == 1) {
+			*level = i;
+			return 0;
+		}
+
+		bytenr = btrfs_node_blockptr(eb, path->slots[i]);
+		blocksize = btrfs_level_size(root, i - 1);
+		eb = read_tree_block(root, bytenr, blocksize, ptr_gen);
+		BUG_ON(btrfs_header_level(eb) != i - 1);
+		path->nodes[i - 1] = eb;
+		path->slots[i - 1] = 0;
+	}
+	return 1;
+}
+
+/*
+ * invalidate extent cache for file extents whose key in range of
+ * [min_key, max_key)
+ */
+static int invalidate_extent_cache(struct btrfs_root *root,
+				   struct btrfs_key *min_key,
+				   struct btrfs_key *max_key)
+{
+	struct inode *inode = NULL;
+	u64 objectid;
+	u64 start, end;
+
+	objectid = min_key->objectid;
+	while (1) {
+		cond_resched();
+		iput(inode);
+
+		if (objectid > max_key->objectid)
+			break;
+
+		inode = find_next_inode(root, objectid);
+		if (!inode)
+			break;
+
+		if (inode->i_ino > max_key->objectid) {
+			iput(inode);
+			break;
+		}
+
+		objectid = inode->i_ino + 1;
+		if (!S_ISREG(inode->i_mode))
+			continue;
+
+		if (unlikely(min_key->objectid == inode->i_ino)) {
+			if (min_key->type > BTRFS_EXTENT_DATA_KEY)
+				continue;
+			if (min_key->type < BTRFS_EXTENT_DATA_KEY)
+				start = 0;
+			else {
+				start = min_key->offset;
+				WARN_ON(!IS_ALIGNED(start, root->sectorsize));
+			}
+		} else {
+			start = 0;
+		}
+
+		if (unlikely(max_key->objectid == inode->i_ino)) {
+			if (max_key->type < BTRFS_EXTENT_DATA_KEY)
+				continue;
+			if (max_key->type > BTRFS_EXTENT_DATA_KEY) {
+				end = (u64)-1;
+			} else {
+				if (max_key->offset == 0)
+					continue;
+				end = max_key->offset;
+				WARN_ON(!IS_ALIGNED(end, root->sectorsize));
+				end--;
+			}
+		} else {
+			end = (u64)-1;
+		}
+
+		/* the lock_extent waits for readpage to complete */
+		lock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+		btrfs_drop_extent_cache(inode, start, end, 1);
+		unlock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+	}
+	return 0;
+}
+
+static int find_next_key(struct btrfs_path *path, int level,
+			 struct btrfs_key *key)
+
+{
+	while (level < BTRFS_MAX_LEVEL) {
+		if (!path->nodes[level])
+			break;
+		if (path->slots[level] + 1 <
+		    btrfs_header_nritems(path->nodes[level])) {
+			btrfs_node_key_to_cpu(path->nodes[level], key,
+					      path->slots[level] + 1);
+			return 0;
+		}
+		level++;
+	}
+	return 1;
+}
+
+/*
+ * merge the relocated tree blocks in reloc tree with corresponding
+ * fs tree.
+ */
+static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
+					       struct btrfs_root *root)
+{
+	LIST_HEAD(inode_list);
+	struct btrfs_key key;
+	struct btrfs_key next_key;
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *reloc_root;
+	struct btrfs_root_item *root_item;
+	struct btrfs_path *path;
+	struct extent_buffer *leaf = NULL;
+	unsigned long nr;
+	int level;
+	int max_level;
+	int replaced = 0;
+	int ret;
+	int err = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	reloc_root = root->reloc_root;
+	root_item = &reloc_root->root_item;
+
+	if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
+		level = btrfs_root_level(root_item);
+		extent_buffer_get(reloc_root->node);
+		path->nodes[level] = reloc_root->node;
+		path->slots[level] = 0;
+	} else {
+		btrfs_disk_key_to_cpu(&key, &root_item->drop_progress);
+
+		level = root_item->drop_level;
+		BUG_ON(level == 0);
+		path->lowest_level = level;
+		ret = btrfs_search_slot(NULL, reloc_root, &key, path, 0, 0);
+		if (ret < 0) {
+			btrfs_free_path(path);
+			return ret;
+		}
+
+		btrfs_node_key_to_cpu(path->nodes[level], &next_key,
+				      path->slots[level]);
+		WARN_ON(memcmp(&key, &next_key, sizeof(key)));
+
+		btrfs_unlock_up_safe(path, 0);
+	}
+
+	if (level == 0 && rc->stage == UPDATE_DATA_PTRS) {
+		trans = btrfs_start_transaction(root, 1);
+
+		leaf = path->nodes[0];
+		btrfs_item_key_to_cpu(leaf, &key, 0);
+		btrfs_release_path(reloc_root, path);
+
+		ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+		if (ret < 0) {
+			err = ret;
+			goto out;
+		}
+
+		leaf = path->nodes[0];
+		btrfs_unlock_up_safe(path, 1);
+		ret = replace_file_extents(trans, rc, root, leaf,
+					   &inode_list);
+		if (ret < 0)
+			err = ret;
+		goto out;
+	}
+
+	memset(&next_key, 0, sizeof(next_key));
+
+	while (1) {
+		leaf = NULL;
+		replaced = 0;
+		trans = btrfs_start_transaction(root, 1);
+		max_level = level;
+
+		ret = walk_down_reloc_tree(reloc_root, path, &level);
+		if (ret < 0) {
+			err = ret;
+			goto out;
+		}
+		if (ret > 0)
+			break;
+
+		if (!find_next_key(path, level, &key) &&
+		    btrfs_comp_cpu_keys(&next_key, &key) >= 0) {
+			ret = 0;
+		} else if (level == 1 && rc->stage == UPDATE_DATA_PTRS) {
+			ret = replace_path(trans, root, reloc_root,
+					   path, &next_key, &leaf,
+					   level, max_level);
+		} else {
+			ret = replace_path(trans, root, reloc_root,
+					   path, &next_key, NULL,
+					   level, max_level);
+		}
+		if (ret < 0) {
+			err = ret;
+			goto out;
+		}
+
+		if (ret > 0) {
+			level = ret;
+			btrfs_node_key_to_cpu(path->nodes[level], &key,
+					      path->slots[level]);
+			replaced = 1;
+		} else if (leaf) {
+			/*
+			 * no block got replaced, try replacing file extents
+			 */
+			btrfs_item_key_to_cpu(leaf, &key, 0);
+			ret = replace_file_extents(trans, rc, root, leaf,
+						   &inode_list);
+			btrfs_tree_unlock(leaf);
+			free_extent_buffer(leaf);
+			BUG_ON(ret < 0);
+		}
+
+		ret = walk_up_reloc_tree(reloc_root, path, &level);
+		if (ret > 0)
+			break;
+
+		BUG_ON(level == 0);
+		/*
+		 * save the merging progress in the drop_progress.
+		 * this is OK since root refs == 1 in this case.
+		 */
+		btrfs_node_key(path->nodes[level], &root_item->drop_progress,
+			       path->slots[level]);
+		root_item->drop_level = level;
+
+		nr = trans->blocks_used;
+		btrfs_end_transaction(trans, root);
+
+		btrfs_btree_balance_dirty(root, nr);
+
+		if (replaced && rc->stage == UPDATE_DATA_PTRS)
+			invalidate_extent_cache(root, &key, &next_key);
+	}
+
+	/*
+	 * handle the case only one block in the fs tree need to be
+	 * relocated and the block is tree root.
+	 */
+	leaf = btrfs_lock_root_node(root);
+	ret = btrfs_cow_block(trans, root, leaf, NULL, 0, &leaf);
+	btrfs_tree_unlock(leaf);
+	free_extent_buffer(leaf);
+	if (ret < 0)
+		err = ret;
+out:
+	btrfs_free_path(path);
+
+	if (err == 0) {
+		memset(&root_item->drop_progress, 0,
+		       sizeof(root_item->drop_progress));
+		root_item->drop_level = 0;
+		btrfs_set_root_refs(root_item, 0);
+	}
+
+	nr = trans->blocks_used;
+	btrfs_end_transaction(trans, root);
+
+	btrfs_btree_balance_dirty(root, nr);
+
+	/*
+	 * put inodes while we aren't holding the tree locks
+	 */
+	while (!list_empty(&inode_list)) {
+		struct inodevec *ivec;
+		ivec = list_entry(inode_list.next, struct inodevec, list);
+		list_del(&ivec->list);
+		while (ivec->nr > 0) {
+			ivec->nr--;
+			iput(ivec->inode[ivec->nr]);
+		}
+		kfree(ivec);
+	}
+
+	if (replaced && rc->stage == UPDATE_DATA_PTRS)
+		invalidate_extent_cache(root, &key, &next_key);
+
+	return err;
+}
+
+/*
+ * callback for the work threads.
+ * this function merges reloc tree with corresponding fs tree,
+ * and then drops the reloc tree.
+ */
+static void merge_func(struct btrfs_work *work)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *root;
+	struct btrfs_root *reloc_root;
+	struct async_merge *async;
+
+	async = container_of(work, struct async_merge, work);
+	reloc_root = async->root;
+
+	if (btrfs_root_refs(&reloc_root->root_item) > 0) {
+		root = read_fs_root(reloc_root->fs_info,
+				    reloc_root->root_key.offset);
+		BUG_ON(IS_ERR(root));
+		BUG_ON(root->reloc_root != reloc_root);
+
+		merge_reloc_root(async->rc, root);
+
+		trans = btrfs_start_transaction(root, 1);
+		btrfs_update_reloc_root(trans, root);
+		btrfs_end_transaction(trans, root);
+	}
+
+	btrfs_drop_dead_root(reloc_root);
+
+	if (atomic_dec_and_test(async->num_pending))
+		complete(async->done);
+
+	kfree(async);
+}
+
+static int merge_reloc_roots(struct reloc_control *rc)
+{
+	struct async_merge *async;
+	struct btrfs_root *root;
+	struct completion done;
+	atomic_t num_pending;
+
+	init_completion(&done);
+	atomic_set(&num_pending, 1);
+
+	while (!list_empty(&rc->reloc_roots)) {
+		root = list_entry(rc->reloc_roots.next,
+				  struct btrfs_root, root_list);
+		list_del_init(&root->root_list);
+
+		async = kmalloc(sizeof(*async), GFP_NOFS);
+		BUG_ON(!async);
+		async->work.func = merge_func;
+		async->work.flags = 0;
+		async->rc = rc;
+		async->root = root;
+		async->done = &done;
+		async->num_pending = &num_pending;
+		atomic_inc(&num_pending);
+		btrfs_queue_worker(&rc->workers, &async->work);
+	}
+
+	if (!atomic_dec_and_test(&num_pending))
+		wait_for_completion(&done);
+
+	BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
+	return 0;
+}
+
+static void free_block_list(struct rb_root *blocks)
+{
+	struct tree_block *block;
+	struct rb_node *rb_node;
+	while ((rb_node = rb_first(blocks))) {
+		block = rb_entry(rb_node, struct tree_block, rb_node);
+		rb_erase(rb_node, blocks);
+		kfree(block);
+	}
+}
+
+static int record_reloc_root_in_trans(struct btrfs_trans_handle *trans,
+				      struct btrfs_root *reloc_root)
+{
+	struct btrfs_root *root;
+
+	if (reloc_root->last_trans == trans->transid)
+		return 0;
+
+	root = read_fs_root(reloc_root->fs_info, reloc_root->root_key.offset);
+	BUG_ON(IS_ERR(root));
+	BUG_ON(root->reloc_root != reloc_root);
+
+	return btrfs_record_root_in_trans(trans, root);
+}
+
+/*
+ * select one tree from trees that references the block.
+ * for blocks in refernce counted trees, we preper reloc tree.
+ * if no reloc tree found and reloc_only is true, NULL is returned.
+ */
+static struct btrfs_root *__select_one_root(struct btrfs_trans_handle *trans,
+					    struct backref_node *node,
+					    struct backref_edge *edges[],
+					    int *nr, int reloc_only)
+{
+	struct backref_node *next;
+	struct btrfs_root *root;
+	int index;
+	int loop = 0;
+again:
+	index = 0;
+	next = node;
+	while (1) {
+		cond_resched();
+		next = walk_up_backref(next, edges, &index);
+		root = next->root;
+		if (!root) {
+			BUG_ON(!node->old_root);
+			goto skip;
+		}
+
+		/* no other choice for non-refernce counted tree */
+		if (!root->ref_cows) {
+			BUG_ON(reloc_only);
+			break;
+		}
+
+		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
+			record_reloc_root_in_trans(trans, root);
+			break;
+		}
+
+		if (loop) {
+			btrfs_record_root_in_trans(trans, root);
+			break;
+		}
+
+		if (reloc_only || next != node) {
+			if (!root->reloc_root)
+				btrfs_record_root_in_trans(trans, root);
+			root = root->reloc_root;
+			/*
+			 * if the reloc tree was created in current
+			 * transation, there is no node in backref tree
+			 * corresponds to the root of the reloc tree.
+			 */
+			if (btrfs_root_last_snapshot(&root->root_item) ==
+			    trans->transid - 1)
+				break;
+		}
+skip:
+		root = NULL;
+		next = walk_down_backref(edges, &index);
+		if (!next || next->level <= node->level)
+			break;
+	}
+
+	if (!root && !loop && !reloc_only) {
+		loop = 1;
+		goto again;
+	}
+
+	if (root)
+		*nr = index;
+	else
+		*nr = 0;
+
+	return root;
+}
+
+static noinline_for_stack
+struct btrfs_root *select_one_root(struct btrfs_trans_handle *trans,
+				   struct backref_node *node)
+{
+	struct backref_edge *edges[BTRFS_MAX_LEVEL - 1];
+	int nr;
+	return __select_one_root(trans, node, edges, &nr, 0);
+}
+
+static noinline_for_stack
+struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans,
+				     struct backref_node *node,
+				     struct backref_edge *edges[], int *nr)
+{
+	return __select_one_root(trans, node, edges, nr, 1);
+}
+
+static void grab_path_buffers(struct btrfs_path *path,
+			      struct backref_node *node,
+			      struct backref_edge *edges[], int nr)
+{
+	int i = 0;
+	while (1) {
+		drop_node_buffer(node);
+		node->eb = path->nodes[node->level];
+		BUG_ON(!node->eb);
+		if (path->locks[node->level])
+			node->locked = 1;
+		path->nodes[node->level] = NULL;
+		path->locks[node->level] = 0;
+
+		if (i >= nr)
+			break;
+
+		edges[i]->blockptr = node->eb->start;
+		node = edges[i]->node[UPPER];
+		i++;
+	}
+}
+
+/*
+ * relocate a block tree, and then update pointers in upper level
+ * blocks that reference the block to point to the new location.
+ *
+ * if called by link_to_upper, the block has already been relocated.
+ * in that case this function just updates pointers.
+ */
+static int do_relocation(struct btrfs_trans_handle *trans,
+			 struct backref_node *node,
+			 struct btrfs_key *key,
+			 struct btrfs_path *path, int lowest)
+{
+	struct backref_node *upper;
+	struct backref_edge *edge;
+	struct backref_edge *edges[BTRFS_MAX_LEVEL - 1];
+	struct btrfs_root *root;
+	struct extent_buffer *eb;
+	u32 blocksize;
+	u64 bytenr;
+	u64 generation;
+	int nr;
+	int slot;
+	int ret;
+	int err = 0;
+
+	BUG_ON(lowest && node->eb);
+
+	path->lowest_level = node->level + 1;
+	list_for_each_entry(edge, &node->upper, list[LOWER]) {
+		cond_resched();
+		if (node->eb && node->eb->start == edge->blockptr)
+			continue;
+
+		upper = edge->node[UPPER];
+		root = select_reloc_root(trans, upper, edges, &nr);
+		if (!root)
+			continue;
+
+		if (upper->eb && !upper->locked)
+			drop_node_buffer(upper);
+
+		if (!upper->eb) {
+			ret = btrfs_search_slot(trans, root, key, path, 0, 1);
+			if (ret < 0) {
+				err = ret;
+				break;
+			}
+			BUG_ON(ret > 0);
+
+			slot = path->slots[upper->level];
+
+			btrfs_unlock_up_safe(path, upper->level + 1);
+			grab_path_buffers(path, upper, edges, nr);
+
+			btrfs_release_path(NULL, path);
+		} else {
+			ret = btrfs_bin_search(upper->eb, key, upper->level,
+					       &slot);
+			BUG_ON(ret);
+		}
+
+		bytenr = btrfs_node_blockptr(upper->eb, slot);
+		if (!lowest) {
+			if (node->eb->start == bytenr) {
+				btrfs_tree_unlock(upper->eb);
+				upper->locked = 0;
+				continue;
+			}
+		} else {
+			BUG_ON(node->bytenr != bytenr);
+		}
+
+		blocksize = btrfs_level_size(root, node->level);
+		generation = btrfs_node_ptr_generation(upper->eb, slot);
+		eb = read_tree_block(root, bytenr, blocksize, generation);
+		btrfs_tree_lock(eb);
+		btrfs_set_lock_blocking(eb);
+
+		if (!node->eb) {
+			ret = btrfs_cow_block(trans, root, eb, upper->eb,
+					      slot, &eb);
+			if (ret < 0) {
+				err = ret;
+				break;
+			}
+			btrfs_set_lock_blocking(eb);
+			node->eb = eb;
+			node->locked = 1;
+		} else {
+			btrfs_set_node_blockptr(upper->eb, slot,
+						node->eb->start);
+			btrfs_set_node_ptr_generation(upper->eb, slot,
+						      trans->transid);
+			btrfs_mark_buffer_dirty(upper->eb);
+
+			ret = btrfs_inc_extent_ref(trans, root,
+						node->eb->start, blocksize,
+						upper->eb->start,
+						btrfs_header_owner(upper->eb),
+						node->level, 0);
+			BUG_ON(ret);
+
+			ret = btrfs_drop_subtree(trans, root, eb, upper->eb);
+			BUG_ON(ret);
+
+			btrfs_tree_unlock(eb);
+			free_extent_buffer(eb);
+		}
+		if (!lowest) {
+			btrfs_tree_unlock(upper->eb);
+			upper->locked = 0;
+		}
+	}
+	path->lowest_level = 0;
+	return err;
+}
+
+static int link_to_upper(struct btrfs_trans_handle *trans,
+			 struct backref_node *node,
+			 struct btrfs_path *path)
+{
+	struct btrfs_key key;
+	if (!node->eb || list_empty(&node->upper))
+		return 0;
+
+	btrfs_node_key_to_cpu(node->eb, &key, 0);
+	return do_relocation(trans, node, &key, path, 0);
+}
+
+static int finish_pending_nodes(struct btrfs_trans_handle *trans,
+				struct backref_cache *cache,
+				struct btrfs_path *path)
+{
+	struct backref_node *node;
+	int level;
+	int ret;
+	int err = 0;
+
+	for (level = 0; level < BTRFS_MAX_LEVEL; level++) {
+		while (!list_empty(&cache->pending[level])) {
+			node = list_entry(cache->pending[level].next,
+					  struct backref_node, lower);
+			BUG_ON(node->level != level);
+
+			ret = link_to_upper(trans, node, path);
+			if (ret < 0)
+				err = ret;
+			/*
+			 * this remove the node from the pending list and
+			 * may add some other nodes to the level + 1
+			 * pending list
+			 */
+			remove_backref_node(cache, node);
+		}
+	}
+	BUG_ON(!RB_EMPTY_ROOT(&cache->rb_root));
+	return err;
+}
+
+static void mark_block_processed(struct reloc_control *rc,
+				 struct backref_node *node)
+{
+	u32 blocksize;
+	if (node->level == 0 ||
+	    in_block_group(node->bytenr, rc->block_group)) {
+		blocksize = btrfs_level_size(rc->extent_root, node->level);
+		set_extent_bits(&rc->processed_blocks, node->bytenr,
+				node->bytenr + blocksize - 1, EXTENT_DIRTY,
+				GFP_NOFS);
+	}
+	node->processed = 1;
+}
+
+/*
+ * mark a block and all blocks directly/indirectly reference the block
+ * as processed.
+ */
+static void update_processed_blocks(struct reloc_control *rc,
+				    struct backref_node *node)
+{
+	struct backref_node *next = node;
+	struct backref_edge *edge;
+	struct backref_edge *edges[BTRFS_MAX_LEVEL - 1];
+	int index = 0;
+
+	while (next) {
+		cond_resched();
+		while (1) {
+			if (next->processed)
+				break;
+
+			mark_block_processed(rc, next);
+
+			if (list_empty(&next->upper))
+				break;
+
+			edge = list_entry(next->upper.next,
+					  struct backref_edge, list[LOWER]);
+			edges[index++] = edge;
+			next = edge->node[UPPER];
+		}
+		next = walk_down_backref(edges, &index);
+	}
+}
+
+static int tree_block_processed(u64 bytenr, u32 blocksize,
+				struct reloc_control *rc)
+{
+	if (test_range_bit(&rc->processed_blocks, bytenr,
+			   bytenr + blocksize - 1, EXTENT_DIRTY, 1))
+		return 1;
+	return 0;
+}
+
+/*
+ * check if there are any file extent pointers in the leaf point to
+ * data require processing
+ */
+static int check_file_extents(struct reloc_control *rc,
+			      u64 bytenr, u32 blocksize, u64 ptr_gen)
+{
+	struct btrfs_key found_key;
+	struct btrfs_file_extent_item *fi;
+	struct extent_buffer *leaf;
+	u32 nritems;
+	int i;
+	int ret = 0;
+
+	leaf = read_tree_block(rc->extent_root, bytenr, blocksize, ptr_gen);
+
+	nritems = btrfs_header_nritems(leaf);
+	for (i = 0; i < nritems; i++) {
+		cond_resched();
+		btrfs_item_key_to_cpu(leaf, &found_key, i);
+		if (found_key.type != BTRFS_EXTENT_DATA_KEY)
+			continue;
+		fi = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
+		if (btrfs_file_extent_type(leaf, fi) ==
+		    BTRFS_FILE_EXTENT_INLINE)
+			continue;
+		bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
+		if (bytenr == 0)
+			continue;
+		if (in_block_group(bytenr, rc->block_group)) {
+			ret = 1;
+			break;
+		}
+	}
+	free_extent_buffer(leaf);
+	return ret;
+}
+
+/*
+ * scan child blocks of a given block to find blocks require processing
+ */
+static int add_child_blocks(struct btrfs_trans_handle *trans,
+			    struct reloc_control *rc,
+			    struct backref_node *node,
+			    struct rb_root *blocks)
+{
+	struct tree_block *block;
+	struct rb_node *rb_node;
+	u64 bytenr;
+	u64 ptr_gen;
+	u32 blocksize;
+	u32 nritems;
+	int i;
+	int err = 0;
+
+	nritems = btrfs_header_nritems(node->eb);
+	blocksize = btrfs_level_size(rc->extent_root, node->level - 1);
+	for (i = 0; i < nritems; i++) {
+		cond_resched();
+		bytenr = btrfs_node_blockptr(node->eb, i);
+		ptr_gen = btrfs_node_ptr_generation(node->eb, i);
+		if (ptr_gen == trans->transid)
+			continue;
+		if (!in_block_group(bytenr, rc->block_group) &&
+		    (node->level > 1 || rc->stage == MOVE_DATA_EXTENTS))
+			continue;
+		if (tree_block_processed(bytenr, blocksize, rc))
+			continue;
+
+		readahead_tree_block(rc->extent_root,
+				     bytenr, blocksize, ptr_gen);
+	}
+
+	for (i = 0; i < nritems; i++) {
+		cond_resched();
+		bytenr = btrfs_node_blockptr(node->eb, i);
+		ptr_gen = btrfs_node_ptr_generation(node->eb, i);
+		if (ptr_gen == trans->transid)
+			continue;
+		if (!in_block_group(bytenr, rc->block_group) &&
+		    (node->level > 1 || rc->stage == MOVE_DATA_EXTENTS))
+			continue;
+		if (tree_block_processed(bytenr, blocksize, rc))
+			continue;
+		if (!in_block_group(bytenr, rc->block_group) &&
+		    !check_file_extents(rc, bytenr, blocksize, ptr_gen))
+			continue;
+
+		block = kmalloc(sizeof(*block), GFP_NOFS);
+		if (!block) {
+			err = -ENOMEM;
+			break;
+		}
+		block->bytenr = bytenr;
+		btrfs_node_key_to_cpu(node->eb, &block->key, i);
+		block->level = node->level - 1;
+		block->key_ready = 1;
+		rb_node = tree_insert(blocks, block->bytenr, &block->rb_node);
+		BUG_ON(rb_node);
+	}
+	if (err)
+		free_block_list(blocks);
+	return err;
+}
+
+/*
+ * find adjacent blocks require processing
+ */
+static noinline_for_stack
+int add_adjacent_blocks(struct btrfs_trans_handle *trans,
+			struct reloc_control *rc,
+			struct backref_cache *cache,
+			struct rb_root *blocks, int level,
+			struct backref_node **upper)
+{
+	struct backref_node *node;
+	int ret = 0;
+
+	WARN_ON(!list_empty(&cache->pending[level]));
+
+	if (list_empty(&cache->pending[level + 1]))
+		return 1;
+
+	node = list_entry(cache->pending[level + 1].next,
+			  struct backref_node, lower);
+	if (node->eb)
+		ret = add_child_blocks(trans, rc, node, blocks);
+
+	*upper = node;
+	return ret;
+}
+
+static int get_tree_block_key(struct reloc_control *rc,
+			      struct tree_block *block)
+{
+	struct extent_buffer *eb;
+
+	BUG_ON(block->key_ready);
+	eb = read_tree_block(rc->extent_root, block->bytenr,
+			     block->key.objectid, block->key.offset);
+	WARN_ON(btrfs_header_level(eb) != block->level);
+	if (block->level == 0)
+		btrfs_item_key_to_cpu(eb, &block->key, 0);
+	else
+		btrfs_node_key_to_cpu(eb, &block->key, 0);
+	free_extent_buffer(eb);
+	block->key_ready = 1;
+	return 0;
+}
+
+static int reada_tree_block(struct reloc_control *rc,
+			    struct tree_block *block)
+{
+	BUG_ON(block->key_ready);
+	readahead_tree_block(rc->extent_root, block->bytenr,
+			     block->key.objectid, block->key.offset);
+	return 0;
+}
+
+/*
+ * helper function to relocate a tree block
+ */
+static int relocate_tree_block(struct btrfs_trans_handle *trans,
+				struct reloc_control *rc,
+				struct backref_node *node,
+				struct btrfs_key *key,
+				struct btrfs_path *path)
+{
+	struct btrfs_root *root;
+	int ret;
+
+	root = select_one_root(trans, node);
+	if (unlikely(!root)) {
+		rc->found_old_snapshot = 1;
+		update_processed_blocks(rc, node);
+		return 0;
+	}
+
+	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
+		ret = do_relocation(trans, node, key, path, 1);
+		if (ret < 0)
+			goto out;
+		if (node->level == 0 && rc->stage == UPDATE_DATA_PTRS) {
+			ret = replace_file_extents(trans, rc, root,
+						   node->eb, NULL);
+			if (ret < 0)
+				goto out;
+		}
+		drop_node_buffer(node);
+	} else if (!root->ref_cows) {
+		path->lowest_level = node->level;
+		ret = btrfs_search_slot(trans, root, key, path, 0, 1);
+		btrfs_release_path(root, path);
+		if (ret < 0)
+			goto out;
+	} else if (root != node->root) {
+		WARN_ON(node->level > 0 || rc->stage != UPDATE_DATA_PTRS);
+	}
+
+	update_processed_blocks(rc, node);
+	ret = 0;
+out:
+	drop_node_buffer(node);
+	return ret;
+}
+
+/*
+ * relocate a list of blocks
+ */
+static noinline_for_stack
+int relocate_tree_blocks(struct btrfs_trans_handle *trans,
+			 struct reloc_control *rc, struct rb_root *blocks)
+{
+	struct backref_cache *cache;
+	struct backref_node *node;
+	struct btrfs_path *path;
+	struct tree_block *block;
+	struct rb_node *rb_node;
+	int level = -1;
+	int ret;
+	int err = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	cache = kmalloc(sizeof(*cache), GFP_NOFS);
+	if (!cache) {
+		btrfs_free_path(path);
+		return -ENOMEM;
+	}
+
+	backref_cache_init(cache);
+
+	rb_node = rb_first(blocks);
+	while (rb_node) {
+		block = rb_entry(rb_node, struct tree_block, rb_node);
+		if (level == -1)
+			level = block->level;
+		else
+			BUG_ON(level != block->level);
+		if (!block->key_ready)
+			reada_tree_block(rc, block);
+		rb_node = rb_next(rb_node);
+	}
+
+	rb_node = rb_first(blocks);
+	while (rb_node) {
+		block = rb_entry(rb_node, struct tree_block, rb_node);
+		if (!block->key_ready)
+			get_tree_block_key(rc, block);
+		rb_node = rb_next(rb_node);
+	}
+
+	rb_node = rb_first(blocks);
+	while (rb_node) {
+		block = rb_entry(rb_node, struct tree_block, rb_node);
+
+		node = build_backref_tree(rc, cache, &block->key,
+					  block->level, block->bytenr);
+		if (IS_ERR(node)) {
+			err = PTR_ERR(node);
+			goto out;
+		}
+
+		ret = relocate_tree_block(trans, rc, node, &block->key,
+					  path);
+		if (ret < 0) {
+			err = ret;
+			goto out;
+		}
+		remove_backref_node(cache, node);
+		rb_node = rb_next(rb_node);
+	}
+
+	if (level > 0)
+		goto out;
+
+	free_block_list(blocks);
+
+	/*
+	 * now backrefs of some upper level tree blocks have been cached,
+	 * try relocating blocks referenced by these upper level blocks.
+	 */
+	while (1) {
+		struct backref_node *upper = NULL;
+		if (trans->transaction->in_commit ||
+		    trans->transaction->delayed_refs.flushing)
+			break;
+
+		ret = add_adjacent_blocks(trans, rc, cache, blocks, level,
+					  &upper);
+		if (ret < 0)
+			err = ret;
+		if (ret != 0)
+			break;
+
+		rb_node = rb_first(blocks);
+		while (rb_node) {
+			block = rb_entry(rb_node, struct tree_block, rb_node);
+			if (trans->transaction->in_commit ||
+			    trans->transaction->delayed_refs.flushing)
+				goto out;
+			BUG_ON(!block->key_ready);
+			node = build_backref_tree(rc, cache, &block->key,
+						  level, block->bytenr);
+			if (IS_ERR(node)) {
+				err = PTR_ERR(node);
+				goto out;
+			}
+
+			ret = relocate_tree_block(trans, rc, node,
+						  &block->key, path);
+			if (ret < 0) {
+				err = ret;
+				goto out;
+			}
+			remove_backref_node(cache, node);
+			rb_node = rb_next(rb_node);
+		}
+		free_block_list(blocks);
+
+		if (upper) {
+			ret = link_to_upper(trans, upper, path);
+			if (ret < 0) {
+				err = ret;
+				break;
+			}
+			remove_backref_node(cache, upper);
+		}
+	}
+out:
+	free_block_list(blocks);
+
+	ret = finish_pending_nodes(trans, cache, path);
+	if (ret < 0)
+		err = ret;
+
+	kfree(cache);
+	btrfs_free_path(path);
+	return err;
+}
+
+static noinline_for_stack
+int relocate_inode_pages(struct inode *inode, u64 start, u64 len)
+{
+	u64 page_start;
+	u64 page_end;
+	unsigned long i;
+	unsigned long first_index;
+	unsigned long last_index;
+	unsigned int total_read = 0;
+	unsigned int total_dirty = 0;
+	struct page *page;
+	struct file_ra_state *ra;
+	struct btrfs_ordered_extent *ordered;
+	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+	int ret = 0;
+
+	ra = kzalloc(sizeof(*ra), GFP_NOFS);
+	if (!ra)
+		return -ENOMEM;
+
+	mutex_lock(&inode->i_mutex);
+	first_index = start >> PAGE_CACHE_SHIFT;
+	last_index = (start + len - 1) >> PAGE_CACHE_SHIFT;
+
+	/* make sure the dirty trick played by the caller work */
+	ret = invalidate_inode_pages2_range(inode->i_mapping,
+					    first_index, last_index);
+	if (ret)
+		goto out_unlock;
+
+	file_ra_state_init(ra, inode->i_mapping);
+
+	for (i = first_index ; i <= last_index; i++) {
+		if (total_read % ra->ra_pages == 0) {
+			btrfs_force_ra(inode->i_mapping, ra, NULL, i,
+				min(last_index, ra->ra_pages + i - 1));
+		}
+		total_read++;
+again:
+		if (((u64)i << PAGE_CACHE_SHIFT) > i_size_read(inode))
+			BUG_ON(1);
+		page = grab_cache_page(inode->i_mapping, i);
+		if (!page) {
+			ret = -ENOMEM;
+			goto out_unlock;
+		}
+		if (!PageUptodate(page)) {
+			btrfs_readpage(NULL, page);
+			lock_page(page);
+			if (!PageUptodate(page)) {
+				unlock_page(page);
+				page_cache_release(page);
+				ret = -EIO;
+				goto out_unlock;
+			}
+		}
+		wait_on_page_writeback(page);
+
+		page_start = (u64)page->index << PAGE_CACHE_SHIFT;
+		page_end = page_start + PAGE_CACHE_SIZE - 1;
+		lock_extent(io_tree, page_start, page_end, GFP_NOFS);
+
+		ordered = btrfs_lookup_ordered_extent(inode, page_start);
+		if (ordered) {
+			unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
+			unlock_page(page);
+			page_cache_release(page);
+			btrfs_start_ordered_extent(inode, ordered, 1);
+			btrfs_put_ordered_extent(ordered);
+			goto again;
+		}
+		set_page_extent_mapped(page);
+
+		if (i == first_index)
+			set_extent_bits(io_tree, page_start, page_end,
+					EXTENT_BOUNDARY, GFP_NOFS);
+		btrfs_set_extent_delalloc(inode, page_start, page_end);
+
+		set_page_dirty(page);
+		total_dirty++;
+
+		unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
+		unlock_page(page);
+		page_cache_release(page);
+	}
+out_unlock:
+	mutex_unlock(&inode->i_mutex);
+	kfree(ra);
+	balance_dirty_pages_ratelimited_nr(inode->i_mapping, total_dirty);
+	return ret;
+}
+
+static noinline_for_stack
+int relocate_data_extent(struct inode *inode, struct btrfs_key *extent_key)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map *em;
+	u64 start = extent_key->objectid - BTRFS_I(inode)->index_cnt;
+	u64 end = start + extent_key->offset - 1;
+
+	em = alloc_extent_map(GFP_NOFS);
+	em->start = start;
+	em->len = extent_key->offset;
+	em->block_len = extent_key->offset;
+	em->block_start = extent_key->objectid;
+	em->bdev = root->fs_info->fs_devices->latest_bdev;
+	set_bit(EXTENT_FLAG_PINNED, &em->flags);
+
+	/* setup extent map to cheat btrfs_readpage */
+	lock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+	while (1) {
+		int ret;
+		spin_lock(&em_tree->lock);
+		ret = add_extent_mapping(em_tree, em);
+		spin_unlock(&em_tree->lock);
+		if (ret != -EEXIST) {
+			free_extent_map(em);
+			break;
+		}
+		btrfs_drop_extent_cache(inode, start, end, 0);
+	}
+	unlock_extent(&BTRFS_I(inode)->io_tree, start, end, GFP_NOFS);
+
+	return relocate_inode_pages(inode, start, extent_key->offset);
+}
+
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+static int get_ref_objectid_v0(struct reloc_control *rc,
+			       struct btrfs_path *path,
+			       struct btrfs_key *extent_key,
+			       u64 *ref_objectid, int *path_change)
+{
+	struct btrfs_key key;
+	struct extent_buffer *leaf;
+	struct btrfs_extent_ref_v0 *ref0;
+	int ret;
+	int slot;
+
+	leaf = path->nodes[0];
+	slot = path->slots[0];
+	while (1) {
+		if (slot >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(rc->extent_root, path);
+			if (ret < 0)
+				return ret;
+			BUG_ON(ret > 0);
+			leaf = path->nodes[0];
+			slot = path->slots[0];
+			if (path_change)
+				*path_change = 1;
+		}
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid != extent_key->objectid)
+			return -ENOENT;
+
+		if (key.type != BTRFS_EXTENT_REF_V0_KEY) {
+			slot++;
+			continue;
+		}
+		ref0 = btrfs_item_ptr(leaf, slot,
+				struct btrfs_extent_ref_v0);
+		*ref_objectid = btrfs_ref_objectid_v0(leaf, ref0);
+		break;
+	}
+	return 0;
+}
+#endif
+
+/*
+ * helper to add a tree block to the list.
+ * the major work is getting the generation and level of the block
+ */
+static int add_tree_block(struct reloc_control *rc,
+			  struct btrfs_key *extent_key,
+			  struct btrfs_path *path,
+			  struct rb_root *blocks)
+{
+	struct extent_buffer *eb;
+	struct btrfs_extent_item *ei;
+	struct btrfs_tree_block_info *bi;
+	struct tree_block *block;
+	struct rb_node *rb_node;
+	u32 item_size;
+	int level = -1;
+	int generation;
+
+	eb =  path->nodes[0];
+	item_size = btrfs_item_size_nr(eb, path->slots[0]);
+
+	if (item_size >= sizeof(*ei) + sizeof(*bi)) {
+		ei = btrfs_item_ptr(eb, path->slots[0],
+				struct btrfs_extent_item);
+		bi = (struct btrfs_tree_block_info *)(ei + 1);
+		generation = btrfs_extent_generation(eb, ei);
+		level = btrfs_tree_block_level(eb, bi);
+	} else {
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+		u64 ref_owner;
+		int ret;
+
+		BUG_ON(item_size != sizeof(struct btrfs_extent_item_v0));
+		ret = get_ref_objectid_v0(rc, path, extent_key,
+					  &ref_owner, NULL);
+		BUG_ON(ref_owner >= BTRFS_MAX_LEVEL);
+		level = (int)ref_owner;
+		/* FIXME: get real generation */
+		generation = 0;
+#else
+		BUG();
+#endif
+	}
+
+	btrfs_release_path(rc->extent_root, path);
+
+	BUG_ON(level == -1);
+
+	block = kmalloc(sizeof(*block), GFP_NOFS);
+	if (!block)
+		return -ENOMEM;
+
+	block->bytenr = extent_key->objectid;
+	block->key.objectid = extent_key->offset;
+	block->key.offset = generation;
+	block->level = level;
+	block->key_ready = 0;
+
+	rb_node = tree_insert(blocks, block->bytenr, &block->rb_node);
+	BUG_ON(rb_node);
+
+	return 0;
+}
+
+/*
+ * helper to add tree blocks for backref of type BTRFS_SHARED_DATA_REF_KEY
+ */
+static int __add_tree_block(struct reloc_control *rc,
+			    u64 bytenr, u32 blocksize,
+			    struct rb_root *blocks)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	int ret;
+
+	if (tree_block_processed(bytenr, blocksize, rc))
+		return 0;
+
+	if (tree_search(blocks, bytenr))
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = bytenr;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = blocksize;
+
+	path->search_commit_root = 1;
+	path->skip_locking = 1;
+	ret = btrfs_search_slot(NULL, rc->extent_root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	BUG_ON(ret);
+
+	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+	ret = add_tree_block(rc, &key, path, blocks);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+/*
+ * helper to check if the block use full backrefs for pointers in it
+ */
+static int block_use_full_backref(struct reloc_control *rc,
+				  struct extent_buffer *eb)
+{
+	struct btrfs_path *path;
+	struct btrfs_extent_item *ei;
+	struct btrfs_key key;
+	u64 flags;
+	int ret;
+
+	if (btrfs_header_flag(eb, BTRFS_HEADER_FLAG_RELOC) ||
+	    btrfs_header_backref_rev(eb) < BTRFS_MIXED_BACKREF_REV)
+		return 1;
+
+	path = btrfs_alloc_path();
+	BUG_ON(!path);
+
+	key.objectid = eb->start;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = eb->len;
+
+	path->search_commit_root = 1;
+	path->skip_locking = 1;
+	ret = btrfs_search_slot(NULL, rc->extent_root,
+				&key, path, 0, 0);
+	BUG_ON(ret);
+
+	ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
+			    struct btrfs_extent_item);
+	flags = btrfs_extent_flags(path->nodes[0], ei);
+	BUG_ON(!(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK));
+	if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)
+		ret = 1;
+	else
+		ret = 0;
+	btrfs_free_path(path);
+	return ret;
+}
+
+/*
+ * helper to add tree blocks for backref of type BTRFS_EXTENT_DATA_REF_KEY
+ * this function scans fs tree to find blocks reference the data extent
+ */
+static int find_data_references(struct reloc_control *rc,
+				struct btrfs_key *extent_key,
+				struct extent_buffer *leaf,
+				struct btrfs_extent_data_ref *ref,
+				struct rb_root *blocks)
+{
+	struct btrfs_path *path;
+	struct tree_block *block;
+	struct btrfs_root *root;
+	struct btrfs_file_extent_item *fi;
+	struct rb_node *rb_node;
+	struct btrfs_key key;
+	u64 ref_root;
+	u64 ref_objectid;
+	u64 ref_offset;
+	u32 ref_count;
+	u32 nritems;
+	int err = 0;
+	int added = 0;
+	int counted;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	ref_root = btrfs_extent_data_ref_root(leaf, ref);
+	ref_objectid = btrfs_extent_data_ref_objectid(leaf, ref);
+	ref_offset = btrfs_extent_data_ref_offset(leaf, ref);
+	ref_count = btrfs_extent_data_ref_count(leaf, ref);
+
+	root = read_fs_root(rc->extent_root->fs_info, ref_root);
+	if (IS_ERR(root)) {
+		err = PTR_ERR(root);
+		goto out;
+	}
+
+	key.objectid = ref_objectid;
+	key.offset = ref_offset;
+	key.type = BTRFS_EXTENT_DATA_KEY;
+
+	path->search_commit_root = 1;
+	path->skip_locking = 1;
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0) {
+		err = ret;
+		goto out;
+	}
+
+	leaf = path->nodes[0];
+	nritems = btrfs_header_nritems(leaf);
+	/*
+	 * the references in tree blocks that use full backrefs
+	 * are not counted in
+	 */
+	if (block_use_full_backref(rc, leaf))
+		counted = 0;
+	else
+		counted = 1;
+	rb_node = tree_search(blocks, leaf->start);
+	if (rb_node) {
+		if (counted)
+			added = 1;
+		else
+			path->slots[0] = nritems;
+	}
+
+	while (ref_count > 0) {
+		while (path->slots[0] >= nritems) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0) {
+				err = ret;
+				goto out;
+			}
+			if (ret > 0) {
+				WARN_ON(1);
+				goto out;
+			}
+
+			leaf = path->nodes[0];
+			nritems = btrfs_header_nritems(leaf);
+			added = 0;
+
+			if (block_use_full_backref(rc, leaf))
+				counted = 0;
+			else
+				counted = 1;
+			rb_node = tree_search(blocks, leaf->start);
+			if (rb_node) {
+				if (counted)
+					added = 1;
+				else
+					path->slots[0] = nritems;
+			}
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+		if (key.objectid != ref_objectid ||
+		    key.type != BTRFS_EXTENT_DATA_KEY) {
+			WARN_ON(1);
+			break;
+		}
+
+		fi = btrfs_item_ptr(leaf, path->slots[0],
+				    struct btrfs_file_extent_item);
+
+		if (btrfs_file_extent_type(leaf, fi) ==
+		    BTRFS_FILE_EXTENT_INLINE)
+			goto next;
+
+		if (btrfs_file_extent_disk_bytenr(leaf, fi) !=
+		    extent_key->objectid)
+			goto next;
+
+		key.offset -= btrfs_file_extent_offset(leaf, fi);
+		if (key.offset != ref_offset)
+			goto next;
+
+		if (counted)
+			ref_count--;
+		if (added)
+			goto next;
+
+		if (!tree_block_processed(leaf->start, leaf->len, rc)) {
+			block = kmalloc(sizeof(*block), GFP_NOFS);
+			if (!block) {
+				err = -ENOMEM;
+				break;
+			}
+			block->bytenr = leaf->start;
+			btrfs_item_key_to_cpu(leaf, &block->key, 0);
+			block->level = 0;
+			block->key_ready = 1;
+			rb_node = tree_insert(blocks, block->bytenr,
+					      &block->rb_node);
+			BUG_ON(rb_node);
+		}
+		if (counted)
+			added = 1;
+		else
+			path->slots[0] = nritems;
+next:
+		path->slots[0]++;
+
+	}
+out:
+	btrfs_free_path(path);
+	return err;
+}
+
+/*
+ * hepler to find all tree blocks that reference a given data extent
+ */
+static noinline_for_stack
+int add_data_references(struct reloc_control *rc,
+			struct btrfs_key *extent_key,
+			struct btrfs_path *path,
+			struct rb_root *blocks)
+{
+	struct btrfs_key key;
+	struct extent_buffer *eb;
+	struct btrfs_extent_data_ref *dref;
+	struct btrfs_extent_inline_ref *iref;
+	unsigned long ptr;
+	unsigned long end;
+	u32 blocksize;
+	int ret;
+	int err = 0;
+
+	ret = get_new_location(rc->data_inode, NULL, extent_key->objectid,
+			       extent_key->offset);
+	BUG_ON(ret < 0);
+	if (ret > 0) {
+		/* the relocated data is fragmented */
+		rc->extents_skipped++;
+		btrfs_release_path(rc->extent_root, path);
+		return 0;
+	}
+
+	blocksize = btrfs_level_size(rc->extent_root, 0);
+
+	eb = path->nodes[0];
+	ptr = btrfs_item_ptr_offset(eb, path->slots[0]);
+	end = ptr + btrfs_item_size_nr(eb, path->slots[0]);
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+	if (ptr + sizeof(struct btrfs_extent_item_v0) == end)
+		ptr = end;
+	else
+#endif
+		ptr += sizeof(struct btrfs_extent_item);
+
+	while (ptr < end) {
+		iref = (struct btrfs_extent_inline_ref *)ptr;
+		key.type = btrfs_extent_inline_ref_type(eb, iref);
+		if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
+			key.offset = btrfs_extent_inline_ref_offset(eb, iref);
+			ret = __add_tree_block(rc, key.offset, blocksize,
+					       blocks);
+		} else if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
+			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+			ret = find_data_references(rc, extent_key,
+						   eb, dref, blocks);
+		} else {
+			BUG();
+		}
+		ptr += btrfs_extent_inline_ref_size(key.type);
+	}
+	WARN_ON(ptr > end);
+
+	while (1) {
+		cond_resched();
+		eb = path->nodes[0];
+		if (path->slots[0] >= btrfs_header_nritems(eb)) {
+			ret = btrfs_next_leaf(rc->extent_root, path);
+			if (ret < 0) {
+				err = ret;
+				break;
+			}
+			if (ret > 0)
+				break;
+			eb = path->nodes[0];
+		}
+
+		btrfs_item_key_to_cpu(eb, &key, path->slots[0]);
+		if (key.objectid != extent_key->objectid)
+			break;
+
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+		if (key.type == BTRFS_SHARED_DATA_REF_KEY ||
+		    key.type == BTRFS_EXTENT_REF_V0_KEY) {
+#else
+		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
+		if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
+#endif
+			ret = __add_tree_block(rc, key.offset, blocksize,
+					       blocks);
+		} else if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
+			dref = btrfs_item_ptr(eb, path->slots[0],
+					      struct btrfs_extent_data_ref);
+			ret = find_data_references(rc, extent_key,
+						   eb, dref, blocks);
+		} else {
+			ret = 0;
+		}
+		if (ret) {
+			err = ret;
+			break;
+		}
+		path->slots[0]++;
+	}
+	btrfs_release_path(rc->extent_root, path);
+	if (err)
+		free_block_list(blocks);
+	return err;
+}
+
+/*
+ * hepler to find next unprocessed extent
+ */
+static noinline_for_stack
+int find_next_extent(struct btrfs_trans_handle *trans,
+		     struct reloc_control *rc, struct btrfs_path *path)
+{
+	struct btrfs_key key;
+	struct extent_buffer *leaf;
+	u64 start, end, last;
+	int ret;
+
+	last = rc->block_group->key.objectid + rc->block_group->key.offset;
+	while (1) {
+		cond_resched();
+		if (rc->search_start >= last) {
+			ret = 1;
+			break;
+		}
+
+		key.objectid = rc->search_start;
+		key.type = BTRFS_EXTENT_ITEM_KEY;
+		key.offset = 0;
+
+		path->search_commit_root = 1;
+		path->skip_locking = 1;
+		ret = btrfs_search_slot(NULL, rc->extent_root, &key, path,
+					0, 0);
+		if (ret < 0)
+			break;
+next:
+		leaf = path->nodes[0];
+		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(rc->extent_root, path);
+			if (ret != 0)
+				break;
+			leaf = path->nodes[0];
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+		if (key.objectid >= last) {
+			ret = 1;
+			break;
+		}
+
+		if (key.type != BTRFS_EXTENT_ITEM_KEY ||
+		    key.objectid + key.offset <= rc->search_start) {
+			path->slots[0]++;
+			goto next;
+		}
+
+		ret = find_first_extent_bit(&rc->processed_blocks,
+					    key.objectid, &start, &end,
+					    EXTENT_DIRTY);
+
+		if (ret == 0 && start <= key.objectid) {
+			btrfs_release_path(rc->extent_root, path);
+			rc->search_start = end + 1;
+		} else {
+			rc->search_start = key.objectid + key.offset;
+			return 0;
+		}
+	}
+	btrfs_release_path(rc->extent_root, path);
+	return ret;
+}
+
+static void set_reloc_control(struct reloc_control *rc)
+{
+	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
+	mutex_lock(&fs_info->trans_mutex);
+	fs_info->reloc_ctl = rc;
+	mutex_unlock(&fs_info->trans_mutex);
+}
+
+static void unset_reloc_control(struct reloc_control *rc)
+{
+	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
+	mutex_lock(&fs_info->trans_mutex);
+	fs_info->reloc_ctl = NULL;
+	mutex_unlock(&fs_info->trans_mutex);
+}
+
+static int check_extent_flags(u64 flags)
+{
+	if ((flags & BTRFS_EXTENT_FLAG_DATA) &&
+	    (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK))
+		return 1;
+	if (!(flags & BTRFS_EXTENT_FLAG_DATA) &&
+	    !(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK))
+		return 1;
+	if ((flags & BTRFS_EXTENT_FLAG_DATA) &&
+	    (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))
+		return 1;
+	return 0;
+}
+
+static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
+{
+	struct rb_root blocks = RB_ROOT;
+	struct btrfs_key key;
+	struct btrfs_trans_handle *trans = NULL;
+	struct btrfs_path *path;
+	struct btrfs_extent_item *ei;
+	unsigned long nr;
+	u64 flags;
+	u32 item_size;
+	int ret;
+	int err = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	rc->search_start = rc->block_group->key.objectid;
+	clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY,
+			  GFP_NOFS);
+
+	rc->create_reloc_root = 1;
+	set_reloc_control(rc);
+
+	trans = btrfs_start_transaction(rc->extent_root, 1);
+	btrfs_commit_transaction(trans, rc->extent_root);
+
+	while (1) {
+		trans = btrfs_start_transaction(rc->extent_root, 1);
+
+		ret = find_next_extent(trans, rc, path);
+		if (ret < 0)
+			err = ret;
+		if (ret != 0)
+			break;
+
+		rc->extents_found++;
+
+		ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				    struct btrfs_extent_item);
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+		item_size = btrfs_item_size_nr(path->nodes[0],
+					       path->slots[0]);
+		if (item_size >= sizeof(*ei)) {
+			flags = btrfs_extent_flags(path->nodes[0], ei);
+			ret = check_extent_flags(flags);
+			BUG_ON(ret);
+
+		} else {
+#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
+			u64 ref_owner;
+			int path_change = 0;
+
+			BUG_ON(item_size !=
+			       sizeof(struct btrfs_extent_item_v0));
+			ret = get_ref_objectid_v0(rc, path, &key, &ref_owner,
+						  &path_change);
+			if (ref_owner < BTRFS_FIRST_FREE_OBJECTID)
+				flags = BTRFS_EXTENT_FLAG_TREE_BLOCK;
+			else
+				flags = BTRFS_EXTENT_FLAG_DATA;
+
+			if (path_change) {
+				btrfs_release_path(rc->extent_root, path);
+
+				path->search_commit_root = 1;
+				path->skip_locking = 1;
+				ret = btrfs_search_slot(NULL, rc->extent_root,
+							&key, path, 0, 0);
+				if (ret < 0) {
+					err = ret;
+					break;
+				}
+				BUG_ON(ret > 0);
+			}
+#else
+			BUG();
+#endif
+		}
+
+		if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+			ret = add_tree_block(rc, &key, path, &blocks);
+		} else if (rc->stage == UPDATE_DATA_PTRS &&
+			 (flags & BTRFS_EXTENT_FLAG_DATA)) {
+			ret = add_data_references(rc, &key, path, &blocks);
+		} else {
+			btrfs_release_path(rc->extent_root, path);
+			ret = 0;
+		}
+		if (ret < 0) {
+			err = 0;
+			break;
+		}
+
+		if (!RB_EMPTY_ROOT(&blocks)) {
+			ret = relocate_tree_blocks(trans, rc, &blocks);
+			if (ret < 0) {
+				err = ret;
+				break;
+			}
+		}
+
+		nr = trans->blocks_used;
+		btrfs_end_transaction_throttle(trans, rc->extent_root);
+		trans = NULL;
+		btrfs_btree_balance_dirty(rc->extent_root, nr);
+
+		if (rc->stage == MOVE_DATA_EXTENTS &&
+		    (flags & BTRFS_EXTENT_FLAG_DATA)) {
+			rc->found_file_extent = 1;
+			ret = relocate_data_extent(rc->data_inode, &key);
+			if (ret < 0) {
+				err = ret;
+				break;
+			}
+		}
+	}
+	btrfs_free_path(path);
+
+	if (trans) {
+		nr = trans->blocks_used;
+		btrfs_end_transaction(trans, rc->extent_root);
+		btrfs_btree_balance_dirty(rc->extent_root, nr);
+	}
+
+	rc->create_reloc_root = 0;
+	smp_mb();
+
+	if (rc->extents_found > 0) {
+		trans = btrfs_start_transaction(rc->extent_root, 1);
+		btrfs_commit_transaction(trans, rc->extent_root);
+	}
+
+	merge_reloc_roots(rc);
+
+	unset_reloc_control(rc);
+
+	/* get rid of pinned extents */
+	trans = btrfs_start_transaction(rc->extent_root, 1);
+	btrfs_commit_transaction(trans, rc->extent_root);
+
+	return err;
+}
+
+static int __insert_orphan_inode(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 u64 objectid, u64 size)
+{
+	struct btrfs_path *path;
+	struct btrfs_inode_item *item;
+	struct extent_buffer *leaf;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	ret = btrfs_insert_empty_inode(trans, root, path, objectid);
+	if (ret)
+		goto out;
+
+	leaf = path->nodes[0];
+	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_item);
+	memset_extent_buffer(leaf, 0, (unsigned long)item, sizeof(*item));
+	btrfs_set_inode_generation(leaf, item, 1);
+	btrfs_set_inode_size(leaf, item, size);
+	btrfs_set_inode_mode(leaf, item, S_IFREG | 0600);
+	btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS);
+	btrfs_mark_buffer_dirty(leaf);
+	btrfs_release_path(root, path);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+/*
+ * helper to create inode for data relocation.
+ * the inode is in data relocation tree and its link count is 0
+ */
+static struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
+					struct btrfs_block_group_cache *group)
+{
+	struct inode *inode = NULL;
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *root;
+	struct btrfs_key key;
+	unsigned long nr;
+	u64 objectid = BTRFS_FIRST_FREE_OBJECTID;
+	int err = 0;
+
+	root = read_fs_root(fs_info, BTRFS_DATA_RELOC_TREE_OBJECTID);
+	if (IS_ERR(root))
+		return ERR_CAST(root);
+
+	trans = btrfs_start_transaction(root, 1);
+	BUG_ON(!trans);
+
+	err = btrfs_find_free_objectid(trans, root, objectid, &objectid);
+	if (err)
+		goto out;
+
+	err = __insert_orphan_inode(trans, root, objectid, group->key.offset);
+	BUG_ON(err);
+
+	err = btrfs_insert_file_extent(trans, root, objectid, 0, 0, 0,
+				       group->key.offset, 0, group->key.offset,
+				       0, 0, 0);
+	BUG_ON(err);
+
+	key.objectid = objectid;
+	key.type = BTRFS_INODE_ITEM_KEY;
+	key.offset = 0;
+	inode = btrfs_iget(root->fs_info->sb, &key, root);
+	BUG_ON(IS_ERR(inode) || is_bad_inode(inode));
+	BTRFS_I(inode)->index_cnt = group->key.objectid;
+
+	err = btrfs_orphan_add(trans, inode);
+out:
+	nr = trans->blocks_used;
+	btrfs_end_transaction(trans, root);
+
+	btrfs_btree_balance_dirty(root, nr);
+	if (err) {
+		if (inode)
+			iput(inode);
+		inode = ERR_PTR(err);
+	}
+	return inode;
+}
+
+/*
+ * function to relocate all extents in a block group.
+ */
+int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
+{
+	struct btrfs_fs_info *fs_info = extent_root->fs_info;
+	struct reloc_control *rc;
+	int ret;
+	int err = 0;
+
+	rc = kzalloc(sizeof(*rc), GFP_NOFS);
+	if (!rc)
+		return -ENOMEM;
+
+	mapping_tree_init(&rc->reloc_root_tree);
+	extent_io_tree_init(&rc->processed_blocks, NULL, GFP_NOFS);
+	INIT_LIST_HEAD(&rc->reloc_roots);
+
+	rc->block_group = btrfs_lookup_block_group(fs_info, group_start);
+	BUG_ON(!rc->block_group);
+
+	btrfs_init_workers(&rc->workers, "relocate",
+			   fs_info->thread_pool_size);
+
+	rc->extent_root = extent_root;
+	btrfs_prepare_block_group_relocation(extent_root, rc->block_group);
+
+	rc->data_inode = create_reloc_inode(fs_info, rc->block_group);
+	if (IS_ERR(rc->data_inode)) {
+		err = PTR_ERR(rc->data_inode);
+		rc->data_inode = NULL;
+		goto out;
+	}
+
+	printk(KERN_INFO "btrfs: relocating block group %llu flags %llu\n",
+	       (unsigned long long)rc->block_group->key.objectid,
+	       (unsigned long long)rc->block_group->flags);
+
+	btrfs_start_delalloc_inodes(fs_info->tree_root);
+	btrfs_wait_ordered_extents(fs_info->tree_root, 0);
+
+	while (1) {
+		mutex_lock(&fs_info->cleaner_mutex);
+		btrfs_clean_old_snapshots(fs_info->tree_root);
+		mutex_unlock(&fs_info->cleaner_mutex);
+
+		rc->extents_found = 0;
+		rc->extents_skipped = 0;
+
+		ret = relocate_block_group(rc);
+		if (ret < 0) {
+			err = ret;
+			break;
+		}
+
+		if (rc->extents_found == 0)
+			break;
+
+		printk(KERN_INFO "btrfs: found %llu extents\n",
+			(unsigned long long)rc->extents_found);
+
+		if (rc->stage == MOVE_DATA_EXTENTS && rc->found_file_extent) {
+			btrfs_wait_ordered_range(rc->data_inode, 0, (u64)-1);
+			invalidate_mapping_pages(rc->data_inode->i_mapping,
+						 0, -1);
+			rc->stage = UPDATE_DATA_PTRS;
+		} else if (rc->stage == UPDATE_DATA_PTRS &&
+			   rc->extents_skipped >= rc->extents_found) {
+			iput(rc->data_inode);
+			rc->data_inode = create_reloc_inode(fs_info,
+							    rc->block_group);
+			if (IS_ERR(rc->data_inode)) {
+				err = PTR_ERR(rc->data_inode);
+				rc->data_inode = NULL;
+				break;
+			}
+			rc->stage = MOVE_DATA_EXTENTS;
+			rc->found_file_extent = 0;
+		}
+	}
+
+	filemap_fdatawrite_range(fs_info->btree_inode->i_mapping,
+				 rc->block_group->key.objectid,
+				 rc->block_group->key.objectid +
+				 rc->block_group->key.offset - 1);
+
+	WARN_ON(rc->block_group->pinned > 0);
+	WARN_ON(rc->block_group->reserved > 0);
+	WARN_ON(btrfs_block_group_used(&rc->block_group->item) > 0);
+out:
+	iput(rc->data_inode);
+	btrfs_stop_workers(&rc->workers);
+	btrfs_put_block_group(rc->block_group);
+	kfree(rc);
+	return err;
+}
+
+/*
+ * recover relocation interrupted by system crash.
+ *
+ * this function resumes merging reloc trees with corresponding fs trees.
+ * this is important for keeping the sharing of tree blocks
+ */
+int btrfs_recover_relocation(struct btrfs_root *root)
+{
+	LIST_HEAD(reloc_roots);
+	struct btrfs_key key;
+	struct btrfs_root *fs_root;
+	struct btrfs_root *reloc_root;
+	struct btrfs_path *path;
+	struct extent_buffer *leaf;
+	struct reloc_control *rc = NULL;
+	struct btrfs_trans_handle *trans;
+	int ret;
+	int err = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = BTRFS_TREE_RELOC_OBJECTID;
+	key.type = BTRFS_ROOT_ITEM_KEY;
+	key.offset = (u64)-1;
+
+	while (1) {
+		ret = btrfs_search_slot(NULL, root->fs_info->tree_root, &key,
+					path, 0, 0);
+		if (ret < 0) {
+			err = ret;
+			goto out;
+		}
+		if (ret > 0) {
+			if (path->slots[0] == 0)
+				break;
+			path->slots[0]--;
+		}
+		leaf = path->nodes[0];
+		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+		btrfs_release_path(root->fs_info->tree_root, path);
+
+		if (key.objectid != BTRFS_TREE_RELOC_OBJECTID ||
+		    key.type != BTRFS_ROOT_ITEM_KEY)
+			break;
+
+		reloc_root = btrfs_read_fs_root_no_radix(root, &key);
+		if (IS_ERR(reloc_root)) {
+			err = PTR_ERR(reloc_root);
+			goto out;
+		}
+
+		list_add(&reloc_root->root_list, &reloc_roots);
+
+		if (btrfs_root_refs(&reloc_root->root_item) > 0) {
+			fs_root = read_fs_root(root->fs_info,
+					       reloc_root->root_key.offset);
+			if (IS_ERR(fs_root)) {
+				err = PTR_ERR(fs_root);
+				goto out;
+			}
+		}
+
+		if (key.offset == 0)
+			break;
+
+		key.offset--;
+	}
+	btrfs_release_path(root->fs_info->tree_root, path);
+
+	if (list_empty(&reloc_roots))
+		goto out;
+
+	rc = kzalloc(sizeof(*rc), GFP_NOFS);
+	if (!rc) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	mapping_tree_init(&rc->reloc_root_tree);
+	INIT_LIST_HEAD(&rc->reloc_roots);
+	btrfs_init_workers(&rc->workers, "relocate",
+			   root->fs_info->thread_pool_size);
+	rc->extent_root = root->fs_info->extent_root;
+
+	set_reloc_control(rc);
+
+	while (!list_empty(&reloc_roots)) {
+		reloc_root = list_entry(reloc_roots.next,
+					struct btrfs_root, root_list);
+		list_del(&reloc_root->root_list);
+
+		if (btrfs_root_refs(&reloc_root->root_item) == 0) {
+			list_add_tail(&reloc_root->root_list,
+				      &rc->reloc_roots);
+			continue;
+		}
+
+		fs_root = read_fs_root(root->fs_info,
+				       reloc_root->root_key.offset);
+		BUG_ON(IS_ERR(fs_root));
+
+		__add_reloc_root(reloc_root);
+		fs_root->reloc_root = reloc_root;
+	}
+
+	trans = btrfs_start_transaction(rc->extent_root, 1);
+	btrfs_commit_transaction(trans, rc->extent_root);
+
+	merge_reloc_roots(rc);
+
+	unset_reloc_control(rc);
+
+	trans = btrfs_start_transaction(rc->extent_root, 1);
+	btrfs_commit_transaction(trans, rc->extent_root);
+out:
+	if (rc) {
+		btrfs_stop_workers(&rc->workers);
+		kfree(rc);
+	}
+	while (!list_empty(&reloc_roots)) {
+		reloc_root = list_entry(reloc_roots.next,
+					struct btrfs_root, root_list);
+		list_del(&reloc_root->root_list);
+		free_extent_buffer(reloc_root->node);
+		free_extent_buffer(reloc_root->commit_root);
+		kfree(reloc_root);
+	}
+	btrfs_free_path(path);
+
+	if (err == 0) {
+		/* cleanup orphan inode in data relocation tree */
+		fs_root = read_fs_root(root->fs_info,
+				       BTRFS_DATA_RELOC_TREE_OBJECTID);
+		if (IS_ERR(fs_root))
+			err = PTR_ERR(fs_root);
+	}
+	return err;
+}
+
+/*
+ * helper to add ordered checksum for data relocation.
+ *
+ * cloning checksum properly handles the nodatasum extents.
+ * it also saves CPU time to re-calculate the checksum.
+ */
+int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len)
+{
+	struct btrfs_ordered_sum *sums;
+	struct btrfs_sector_sum *sector_sum;
+	struct btrfs_ordered_extent *ordered;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	size_t offset;
+	int ret;
+	u64 disk_bytenr;
+	LIST_HEAD(list);
+
+	ordered = btrfs_lookup_ordered_extent(inode, file_pos);
+	BUG_ON(ordered->file_offset != file_pos || ordered->len != len);
+
+	disk_bytenr = file_pos + BTRFS_I(inode)->index_cnt;
+	ret = btrfs_lookup_csums_range(root->fs_info->csum_root, disk_bytenr,
+				       disk_bytenr + len - 1, &list);
+
+	while (!list_empty(&list)) {
+		sums = list_entry(list.next, struct btrfs_ordered_sum, list);
+		list_del_init(&sums->list);
+
+		sector_sum = sums->sums;
+		sums->bytenr = ordered->start;
+
+		offset = 0;
+		while (offset < sums->len) {
+			sector_sum->bytenr += ordered->start - disk_bytenr;
+			sector_sum++;
+			offset += root->sectorsize;
+		}
+
+		btrfs_add_ordered_sum(inode, ordered, sums);
+	}
+	btrfs_put_ordered_extent(ordered);
+	return 0;
+}
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index b48650de4472..0ddc6d61c55a 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -111,6 +111,15 @@ out:
 	return ret;
 }
 
+int btrfs_set_root_node(struct btrfs_root_item *item,
+			struct extent_buffer *node)
+{
+	btrfs_set_root_bytenr(item, node->start);
+	btrfs_set_root_level(item, btrfs_header_level(node));
+	btrfs_set_root_generation(item, btrfs_header_generation(node));
+	return 0;
+}
+
 /*
  * copy the data in 'item' into the btree
  */
@@ -164,8 +173,7 @@ int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root
  * offset lower than the latest root.  They need to be queued for deletion to
  * finish what was happening when we crashed.
  */
-int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid,
-			  struct btrfs_root *latest)
+int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid)
 {
 	struct btrfs_root *dead_root;
 	struct btrfs_item *item;
@@ -227,10 +235,7 @@ again:
 			goto err;
 		}
 
-		if (objectid == BTRFS_TREE_RELOC_OBJECTID)
-			ret = btrfs_add_dead_reloc_root(dead_root);
-		else
-			ret = btrfs_add_dead_root(dead_root, latest);
+		ret = btrfs_add_dead_root(dead_root);
 		if (ret)
 			goto err;
 		goto again;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 2ff7cd2db25f..9f179d4832d5 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -52,7 +52,6 @@
 #include "export.h"
 #include "compression.h"
 
-
 static struct super_operations btrfs_super_ops;
 
 static void btrfs_put_super(struct super_block *sb)
@@ -67,8 +66,8 @@ static void btrfs_put_super(struct super_block *sb)
 enum {
 	Opt_degraded, Opt_subvol, Opt_device, Opt_nodatasum, Opt_nodatacow,
 	Opt_max_extent, Opt_max_inline, Opt_alloc_start, Opt_nobarrier,
-	Opt_ssd, Opt_thread_pool, Opt_noacl,  Opt_compress, Opt_notreelog,
-	Opt_ratio, Opt_flushoncommit, Opt_err,
+	Opt_ssd, Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl,
+	Opt_compress, Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -84,6 +83,8 @@ static match_table_t tokens = {
 	{Opt_thread_pool, "thread_pool=%d"},
 	{Opt_compress, "compress"},
 	{Opt_ssd, "ssd"},
+	{Opt_ssd_spread, "ssd_spread"},
+	{Opt_nossd, "nossd"},
 	{Opt_noacl, "noacl"},
 	{Opt_notreelog, "notreelog"},
 	{Opt_flushoncommit, "flushoncommit"},
@@ -158,7 +159,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			 */
 			break;
 		case Opt_nodatasum:
-			printk(KERN_INFO "btrfs: setting nodatacsum\n");
+			printk(KERN_INFO "btrfs: setting nodatasum\n");
 			btrfs_set_opt(info->mount_opt, NODATASUM);
 			break;
 		case Opt_nodatacow:
@@ -174,6 +175,19 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
 			btrfs_set_opt(info->mount_opt, SSD);
 			break;
+		case Opt_ssd_spread:
+			printk(KERN_INFO "btrfs: use spread ssd "
+			       "allocation scheme\n");
+			btrfs_set_opt(info->mount_opt, SSD);
+			btrfs_set_opt(info->mount_opt, SSD_SPREAD);
+			break;
+		case Opt_nossd:
+			printk(KERN_INFO "btrfs: not using ssd allocation "
+			       "scheme\n");
+			btrfs_set_opt(info->mount_opt, NOSSD);
+			btrfs_clear_opt(info->mount_opt, SSD);
+			btrfs_clear_opt(info->mount_opt, SSD_SPREAD);
+			break;
 		case Opt_nobarrier:
 			printk(KERN_INFO "btrfs: turning off barriers\n");
 			btrfs_set_opt(info->mount_opt, NOBARRIER);
@@ -322,7 +336,7 @@ static int btrfs_fill_super(struct super_block *sb,
 	struct dentry *root_dentry;
 	struct btrfs_super_block *disk_super;
 	struct btrfs_root *tree_root;
-	struct btrfs_inode *bi;
+	struct btrfs_key key;
 	int err;
 
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
@@ -341,23 +355,15 @@ static int btrfs_fill_super(struct super_block *sb,
 	}
 	sb->s_fs_info = tree_root;
 	disk_super = &tree_root->fs_info->super_copy;
-	inode = btrfs_iget_locked(sb, BTRFS_FIRST_FREE_OBJECTID,
-				  tree_root->fs_info->fs_root);
-	bi = BTRFS_I(inode);
-	bi->location.objectid = inode->i_ino;
-	bi->location.offset = 0;
-	bi->root = tree_root->fs_info->fs_root;
 
-	btrfs_set_key_type(&bi->location, BTRFS_INODE_ITEM_KEY);
-
-	if (!inode) {
-		err = -ENOMEM;
+	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
+	key.type = BTRFS_INODE_ITEM_KEY;
+	key.offset = 0;
+	inode = btrfs_iget(sb, &key, tree_root->fs_info->fs_root);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
 		goto fail_close;
 	}
-	if (inode->i_state & I_NEW) {
-		btrfs_read_locked_inode(inode);
-		unlock_new_inode(inode);
-	}
 
 	root_dentry = d_alloc_root(inode);
 	if (!root_dentry) {
@@ -388,10 +394,6 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 	struct btrfs_root *root = btrfs_sb(sb);
 	int ret;
 
-	if (sb->s_flags & MS_RDONLY)
-		return 0;
-
-	sb->s_dirt = 0;
 	if (!wait) {
 		filemap_flush(root->fs_info->btree_inode->i_mapping);
 		return 0;
@@ -402,7 +404,6 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 
 	trans = btrfs_start_transaction(root, 1);
 	ret = btrfs_commit_transaction(trans, root);
-	sb->s_dirt = 0;
 	return ret;
 }
 
@@ -433,7 +434,11 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
 	if (btrfs_test_opt(root, COMPRESS))
 		seq_puts(seq, ",compress");
-	if (btrfs_test_opt(root, SSD))
+	if (btrfs_test_opt(root, NOSSD))
+		seq_puts(seq, ",nossd");
+	if (btrfs_test_opt(root, SSD_SPREAD))
+		seq_puts(seq, ",ssd_spread");
+	else if (btrfs_test_opt(root, SSD))
 		seq_puts(seq, ",ssd");
 	if (btrfs_test_opt(root, NOTREELOG))
 		seq_puts(seq, ",notreelog");
@@ -444,11 +449,6 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	return 0;
 }
 
-static void btrfs_write_super(struct super_block *sb)
-{
-	sb->s_dirt = 0;
-}
-
 static int btrfs_test_super(struct super_block *s, void *data)
 {
 	struct btrfs_fs_devices *test_fs_devices = data;
@@ -584,7 +584,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		if (btrfs_super_log_root(&root->fs_info->super_copy) != 0)
 			return -EINVAL;
 
-		ret = btrfs_cleanup_reloc_trees(root);
+		/* recover relocation */
+		ret = btrfs_recover_relocation(root);
 		WARN_ON(ret);
 
 		ret = btrfs_cleanup_fs_roots(root->fs_info);
@@ -678,7 +679,6 @@ static int btrfs_unfreeze(struct super_block *sb)
 static struct super_operations btrfs_super_ops = {
 	.delete_inode	= btrfs_delete_inode,
 	.put_super	= btrfs_put_super,
-	.write_super	= btrfs_write_super,
 	.sync_fs	= btrfs_sync_fs,
 	.show_options	= btrfs_show_options,
 	.write_inode	= btrfs_write_inode,
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 01b143605ec1..2e177d7f4bb9 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -25,7 +25,6 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "locking.h"
-#include "ref-cache.h"
 #include "tree-log.h"
 
 #define BTRFS_ROOT_TRANS_TAG 0
@@ -94,48 +93,40 @@ static noinline int join_transaction(struct btrfs_root *root)
  * to make sure the old root from before we joined the transaction is deleted
  * when the transaction commits
  */
-noinline int btrfs_record_root_in_trans(struct btrfs_root *root)
+static noinline int record_root_in_trans(struct btrfs_trans_handle *trans,
+					 struct btrfs_root *root)
 {
-	struct btrfs_dirty_root *dirty;
-	u64 running_trans_id = root->fs_info->running_transaction->transid;
-	if (root->ref_cows && root->last_trans < running_trans_id) {
+	if (root->ref_cows && root->last_trans < trans->transid) {
 		WARN_ON(root == root->fs_info->extent_root);
-		if (root->root_item.refs != 0) {
-			radix_tree_tag_set(&root->fs_info->fs_roots_radix,
-				   (unsigned long)root->root_key.objectid,
-				   BTRFS_ROOT_TRANS_TAG);
+		WARN_ON(root->root_item.refs == 0);
+		WARN_ON(root->commit_root != root->node);
 
-			dirty = kmalloc(sizeof(*dirty), GFP_NOFS);
-			BUG_ON(!dirty);
-			dirty->root = kmalloc(sizeof(*dirty->root), GFP_NOFS);
-			BUG_ON(!dirty->root);
-			dirty->latest_root = root;
-			INIT_LIST_HEAD(&dirty->list);
-
-			root->commit_root = btrfs_root_node(root);
-
-			memcpy(dirty->root, root, sizeof(*root));
-			spin_lock_init(&dirty->root->node_lock);
-			spin_lock_init(&dirty->root->list_lock);
-			mutex_init(&dirty->root->objectid_mutex);
-			mutex_init(&dirty->root->log_mutex);
-			INIT_LIST_HEAD(&dirty->root->dead_list);
-			dirty->root->node = root->commit_root;
-			dirty->root->commit_root = NULL;
-
-			spin_lock(&root->list_lock);
-			list_add(&dirty->root->dead_list, &root->dead_list);
-			spin_unlock(&root->list_lock);
-
-			root->dirty_root = dirty;
-		} else {
-			WARN_ON(1);
-		}
-		root->last_trans = running_trans_id;
+		radix_tree_tag_set(&root->fs_info->fs_roots_radix,
+			   (unsigned long)root->root_key.objectid,
+			   BTRFS_ROOT_TRANS_TAG);
+		root->last_trans = trans->transid;
+		btrfs_init_reloc_root(trans, root);
 	}
 	return 0;
 }
 
+int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root)
+{
+	if (!root->ref_cows)
+		return 0;
+
+	mutex_lock(&root->fs_info->trans_mutex);
+	if (root->last_trans == trans->transid) {
+		mutex_unlock(&root->fs_info->trans_mutex);
+		return 0;
+	}
+
+	record_root_in_trans(trans, root);
+	mutex_unlock(&root->fs_info->trans_mutex);
+	return 0;
+}
+
 /* wait for commit against the current transaction to become unblocked
  * when this is done, it is safe to start a new transaction, but the current
  * transaction might not be fully on disk.
@@ -181,7 +172,6 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 	ret = join_transaction(root);
 	BUG_ON(ret);
 
-	btrfs_record_root_in_trans(root);
 	h->transid = root->fs_info->running_transaction->transid;
 	h->transaction = root->fs_info->running_transaction;
 	h->blocks_reserved = num_blocks;
@@ -192,6 +182,7 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 	h->delayed_ref_updates = 0;
 
 	root->fs_info->running_transaction->use_count++;
+	record_root_in_trans(h, root);
 	mutex_unlock(&root->fs_info->trans_mutex);
 	return h;
 }
@@ -233,6 +224,7 @@ static noinline int wait_for_commit(struct btrfs_root *root,
 	return 0;
 }
 
+#if 0
 /*
  * rate limit against the drop_snapshot code.  This helps to slow down new
  * operations if the drop_snapshot code isn't able to keep up.
@@ -273,6 +265,7 @@ harder:
 			goto harder;
 	}
 }
+#endif
 
 void btrfs_throttle(struct btrfs_root *root)
 {
@@ -280,7 +273,6 @@ void btrfs_throttle(struct btrfs_root *root)
 	if (!root->fs_info->open_ioctl_trans)
 		wait_current_trans(root);
 	mutex_unlock(&root->fs_info->trans_mutex);
-	throttle_on_drops(root);
 }
 
 static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
@@ -323,9 +315,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	memset(trans, 0, sizeof(*trans));
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 
-	if (throttle)
-		throttle_on_drops(root);
-
 	return 0;
 }
 
@@ -462,12 +451,8 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
 		old_root_bytenr = btrfs_root_bytenr(&root->root_item);
 		if (old_root_bytenr == root->node->start)
 			break;
-		btrfs_set_root_bytenr(&root->root_item,
-				       root->node->start);
-		btrfs_set_root_level(&root->root_item,
-				     btrfs_header_level(root->node));
-		btrfs_set_root_generation(&root->root_item, trans->transid);
 
+		btrfs_set_root_node(&root->root_item, root->node);
 		ret = btrfs_update_root(trans, tree_root,
 					&root->root_key,
 					&root->root_item);
@@ -477,14 +462,16 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
 		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
 		BUG_ON(ret);
 	}
+	free_extent_buffer(root->commit_root);
+	root->commit_root = btrfs_root_node(root);
 	return 0;
 }
 
 /*
  * update all the cowonly tree roots on disk
  */
-int btrfs_commit_tree_roots(struct btrfs_trans_handle *trans,
-			    struct btrfs_root *root)
+static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
+					 struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct list_head *next;
@@ -520,118 +507,54 @@ int btrfs_commit_tree_roots(struct btrfs_trans_handle *trans,
  * a dirty root struct and adds it into the list of dead roots that need to
  * be deleted
  */
-int btrfs_add_dead_root(struct btrfs_root *root, struct btrfs_root *latest)
+int btrfs_add_dead_root(struct btrfs_root *root)
 {
-	struct btrfs_dirty_root *dirty;
-
-	dirty = kmalloc(sizeof(*dirty), GFP_NOFS);
-	if (!dirty)
-		return -ENOMEM;
-	dirty->root = root;
-	dirty->latest_root = latest;
-
 	mutex_lock(&root->fs_info->trans_mutex);
-	list_add(&dirty->list, &latest->fs_info->dead_roots);
+	list_add(&root->root_list, &root->fs_info->dead_roots);
 	mutex_unlock(&root->fs_info->trans_mutex);
 	return 0;
 }
 
 /*
- * at transaction commit time we need to schedule the old roots for
- * deletion via btrfs_drop_snapshot.  This runs through all the
- * reference counted roots that were modified in the current
- * transaction and puts them into the drop list
+ * update all the cowonly tree roots on disk
  */
-static noinline int add_dirty_roots(struct btrfs_trans_handle *trans,
-				    struct radix_tree_root *radix,
-				    struct list_head *list)
+static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
+				    struct btrfs_root *root)
 {
-	struct btrfs_dirty_root *dirty;
 	struct btrfs_root *gang[8];
-	struct btrfs_root *root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	int i;
 	int ret;
 	int err = 0;
-	u32 refs;
 
 	while (1) {
-		ret = radix_tree_gang_lookup_tag(radix, (void **)gang, 0,
+		ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
+						 (void **)gang, 0,
 						 ARRAY_SIZE(gang),
 						 BTRFS_ROOT_TRANS_TAG);
 		if (ret == 0)
 			break;
 		for (i = 0; i < ret; i++) {
 			root = gang[i];
-			radix_tree_tag_clear(radix,
-				     (unsigned long)root->root_key.objectid,
-				     BTRFS_ROOT_TRANS_TAG);
-
-			BUG_ON(!root->ref_tree);
-			dirty = root->dirty_root;
+			radix_tree_tag_clear(&fs_info->fs_roots_radix,
+					(unsigned long)root->root_key.objectid,
+					BTRFS_ROOT_TRANS_TAG);
 
 			btrfs_free_log(trans, root);
-			btrfs_free_reloc_root(trans, root);
+			btrfs_update_reloc_root(trans, root);
 
-			if (root->commit_root == root->node) {
-				WARN_ON(root->node->start !=
-					btrfs_root_bytenr(&root->root_item));
-
-				free_extent_buffer(root->commit_root);
-				root->commit_root = NULL;
-				root->dirty_root = NULL;
-
-				spin_lock(&root->list_lock);
-				list_del_init(&dirty->root->dead_list);
-				spin_unlock(&root->list_lock);
-
-				kfree(dirty->root);
-				kfree(dirty);
-
-				/* make sure to update the root on disk
-				 * so we get any updates to the block used
-				 * counts
-				 */
-				err = btrfs_update_root(trans,
-						root->fs_info->tree_root,
-						&root->root_key,
-						&root->root_item);
+			if (root->commit_root == root->node)
 				continue;
-			}
 
-			memset(&root->root_item.drop_progress, 0,
-			       sizeof(struct btrfs_disk_key));
-			root->root_item.drop_level = 0;
-			root->commit_root = NULL;
-			root->dirty_root = NULL;
-			root->root_key.offset = root->fs_info->generation;
-			btrfs_set_root_bytenr(&root->root_item,
-					      root->node->start);
-			btrfs_set_root_level(&root->root_item,
-					     btrfs_header_level(root->node));
-			btrfs_set_root_generation(&root->root_item,
-						  root->root_key.offset);
+			free_extent_buffer(root->commit_root);
+			root->commit_root = btrfs_root_node(root);
 
-			err = btrfs_insert_root(trans, root->fs_info->tree_root,
+			btrfs_set_root_node(&root->root_item, root->node);
+			err = btrfs_update_root(trans, fs_info->tree_root,
 						&root->root_key,
 						&root->root_item);
 			if (err)
 				break;
-
-			refs = btrfs_root_refs(&dirty->root->root_item);
-			btrfs_set_root_refs(&dirty->root->root_item, refs - 1);
-			err = btrfs_update_root(trans, root->fs_info->tree_root,
-						&dirty->root->root_key,
-						&dirty->root->root_item);
-
-			BUG_ON(err);
-			if (refs == 1) {
-				list_add(&dirty->list, list);
-			} else {
-				WARN_ON(1);
-				free_extent_buffer(dirty->root->node);
-				kfree(dirty->root);
-				kfree(dirty);
-			}
 		}
 	}
 	return err;
@@ -688,12 +611,8 @@ static noinline int wait_transaction_pre_flush(struct btrfs_fs_info *info)
 				TASK_UNINTERRUPTIBLE);
 		mutex_unlock(&info->trans_mutex);
 
-		atomic_dec(&info->throttles);
-		wake_up(&info->transaction_throttle);
-
 		schedule();
 
-		atomic_inc(&info->throttles);
 		mutex_lock(&info->trans_mutex);
 		finish_wait(&info->transaction_wait, &wait);
 	}
@@ -705,111 +624,61 @@ static noinline int wait_transaction_pre_flush(struct btrfs_fs_info *info)
  * Given a list of roots that need to be deleted, call btrfs_drop_snapshot on
  * all of them
  */
-static noinline int drop_dirty_roots(struct btrfs_root *tree_root,
-				     struct list_head *list)
+int btrfs_drop_dead_root(struct btrfs_root *root)
 {
-	struct btrfs_dirty_root *dirty;
 	struct btrfs_trans_handle *trans;
+	struct btrfs_root *tree_root = root->fs_info->tree_root;
 	unsigned long nr;
-	u64 num_bytes;
-	u64 bytes_used;
-	u64 max_useless;
-	int ret = 0;
-	int err;
+	int ret;
 
-	while (!list_empty(list)) {
-		struct btrfs_root *root;
+	while (1) {
+		/*
+		 * we don't want to jump in and create a bunch of
+		 * delayed refs if the transaction is starting to close
+		 */
+		wait_transaction_pre_flush(tree_root->fs_info);
+		trans = btrfs_start_transaction(tree_root, 1);
 
-		dirty = list_entry(list->prev, struct btrfs_dirty_root, list);
-		list_del_init(&dirty->list);
-
-		num_bytes = btrfs_root_used(&dirty->root->root_item);
-		root = dirty->latest_root;
-		atomic_inc(&root->fs_info->throttles);
-
-		while (1) {
-			/*
-			 * we don't want to jump in and create a bunch of
-			 * delayed refs if the transaction is starting to close
-			 */
-			wait_transaction_pre_flush(tree_root->fs_info);
-			trans = btrfs_start_transaction(tree_root, 1);
-
-			/*
-			 * we've joined a transaction, make sure it isn't
-			 * closing right now
-			 */
-			if (trans->transaction->delayed_refs.flushing) {
-				btrfs_end_transaction(trans, tree_root);
-				continue;
-			}
-
-			mutex_lock(&root->fs_info->drop_mutex);
-			ret = btrfs_drop_snapshot(trans, dirty->root);
-			if (ret != -EAGAIN)
-				break;
-			mutex_unlock(&root->fs_info->drop_mutex);
-
-			err = btrfs_update_root(trans,
-					tree_root,
-					&dirty->root->root_key,
-					&dirty->root->root_item);
-			if (err)
-				ret = err;
-			nr = trans->blocks_used;
-			ret = btrfs_end_transaction(trans, tree_root);
-			BUG_ON(ret);
-
-			btrfs_btree_balance_dirty(tree_root, nr);
-			cond_resched();
-		}
-		BUG_ON(ret);
-		atomic_dec(&root->fs_info->throttles);
-		wake_up(&root->fs_info->transaction_throttle);
-
-		num_bytes -= btrfs_root_used(&dirty->root->root_item);
-		bytes_used = btrfs_root_used(&root->root_item);
-		if (num_bytes) {
-			mutex_lock(&root->fs_info->trans_mutex);
-			btrfs_record_root_in_trans(root);
-			mutex_unlock(&root->fs_info->trans_mutex);
-			btrfs_set_root_used(&root->root_item,
-					    bytes_used - num_bytes);
+		/*
+		 * we've joined a transaction, make sure it isn't
+		 * closing right now
+		 */
+		if (trans->transaction->delayed_refs.flushing) {
+			btrfs_end_transaction(trans, tree_root);
+			continue;
 		}
 
-		ret = btrfs_del_root(trans, tree_root, &dirty->root->root_key);
-		if (ret) {
-			BUG();
+		ret = btrfs_drop_snapshot(trans, root);
+		if (ret != -EAGAIN)
 			break;
-		}
-		mutex_unlock(&root->fs_info->drop_mutex);
 
-		spin_lock(&root->list_lock);
-		list_del_init(&dirty->root->dead_list);
-		if (!list_empty(&root->dead_list)) {
-			struct btrfs_root *oldest;
-			oldest = list_entry(root->dead_list.prev,
-					    struct btrfs_root, dead_list);
-			max_useless = oldest->root_key.offset - 1;
-		} else {
-			max_useless = root->root_key.offset - 1;
-		}
-		spin_unlock(&root->list_lock);
+		ret = btrfs_update_root(trans, tree_root,
+					&root->root_key,
+					&root->root_item);
+		if (ret)
+			break;
 
 		nr = trans->blocks_used;
 		ret = btrfs_end_transaction(trans, tree_root);
 		BUG_ON(ret);
 
-		ret = btrfs_remove_leaf_refs(root, max_useless, 0);
-		BUG_ON(ret);
-
-		free_extent_buffer(dirty->root->node);
-		kfree(dirty->root);
-		kfree(dirty);
-
 		btrfs_btree_balance_dirty(tree_root, nr);
 		cond_resched();
 	}
+	BUG_ON(ret);
+
+	ret = btrfs_del_root(trans, tree_root, &root->root_key);
+	BUG_ON(ret);
+
+	nr = trans->blocks_used;
+	ret = btrfs_end_transaction(trans, tree_root);
+	BUG_ON(ret);
+
+	free_extent_buffer(root->node);
+	free_extent_buffer(root->commit_root);
+	kfree(root);
+
+	btrfs_btree_balance_dirty(tree_root, nr);
 	return ret;
 }
 
@@ -839,24 +708,23 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto fail;
 
-	btrfs_record_root_in_trans(root);
+	record_root_in_trans(trans, root);
 	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
 	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
 
 	key.objectid = objectid;
-	key.offset = trans->transid;
+	key.offset = 0;
 	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
 
 	old = btrfs_lock_root_node(root);
 	btrfs_cow_block(trans, root, old, NULL, 0, &old);
+	btrfs_set_lock_blocking(old);
 
 	btrfs_copy_root(trans, root, old, &tmp, objectid);
 	btrfs_tree_unlock(old);
 	free_extent_buffer(old);
 
-	btrfs_set_root_bytenr(new_root_item, tmp->start);
-	btrfs_set_root_level(new_root_item, btrfs_header_level(tmp));
-	btrfs_set_root_generation(new_root_item, trans->transid);
+	btrfs_set_root_node(new_root_item, tmp);
 	ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
 				new_root_item);
 	btrfs_tree_unlock(tmp);
@@ -964,6 +832,24 @@ static noinline int finish_pending_snapshots(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+static void update_super_roots(struct btrfs_root *root)
+{
+	struct btrfs_root_item *root_item;
+	struct btrfs_super_block *super;
+
+	super = &root->fs_info->super_copy;
+
+	root_item = &root->fs_info->chunk_root->root_item;
+	super->chunk_root = root_item->bytenr;
+	super->chunk_root_generation = root_item->generation;
+	super->chunk_root_level = root_item->level;
+
+	root_item = &root->fs_info->tree_root->root_item;
+	super->root = root_item->bytenr;
+	super->generation = root_item->generation;
+	super->root_level = root_item->level;
+}
+
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root)
 {
@@ -971,8 +857,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	unsigned long timeout = 1;
 	struct btrfs_transaction *cur_trans;
 	struct btrfs_transaction *prev_trans = NULL;
-	struct btrfs_root *chunk_root = root->fs_info->chunk_root;
-	struct list_head dirty_fs_roots;
 	struct extent_io_tree *pinned_copy;
 	DEFINE_WAIT(wait);
 	int ret;
@@ -999,7 +883,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	BUG_ON(ret);
 
 	mutex_lock(&root->fs_info->trans_mutex);
-	INIT_LIST_HEAD(&dirty_fs_roots);
 	if (cur_trans->in_commit) {
 		cur_trans->use_count++;
 		mutex_unlock(&root->fs_info->trans_mutex);
@@ -1105,41 +988,36 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	 * with the tree-log code.
 	 */
 	mutex_lock(&root->fs_info->tree_log_mutex);
-	/*
-	 * keep tree reloc code from adding new reloc trees
-	 */
-	mutex_lock(&root->fs_info->tree_reloc_mutex);
 
-
-	ret = add_dirty_roots(trans, &root->fs_info->fs_roots_radix,
-			      &dirty_fs_roots);
+	ret = commit_fs_roots(trans, root);
 	BUG_ON(ret);
 
-	/* add_dirty_roots gets rid of all the tree log roots, it is now
+	/* commit_fs_roots gets rid of all the tree log roots, it is now
 	 * safe to free the root of tree log roots
 	 */
 	btrfs_free_log_root_tree(trans, root->fs_info);
 
-	ret = btrfs_commit_tree_roots(trans, root);
+	ret = commit_cowonly_roots(trans, root);
 	BUG_ON(ret);
 
 	cur_trans = root->fs_info->running_transaction;
 	spin_lock(&root->fs_info->new_trans_lock);
 	root->fs_info->running_transaction = NULL;
 	spin_unlock(&root->fs_info->new_trans_lock);
-	btrfs_set_super_generation(&root->fs_info->super_copy,
-				   cur_trans->transid);
-	btrfs_set_super_root(&root->fs_info->super_copy,
-			     root->fs_info->tree_root->node->start);
-	btrfs_set_super_root_level(&root->fs_info->super_copy,
-			   btrfs_header_level(root->fs_info->tree_root->node));
 
-	btrfs_set_super_chunk_root(&root->fs_info->super_copy,
-				   chunk_root->node->start);
-	btrfs_set_super_chunk_root_level(&root->fs_info->super_copy,
-					 btrfs_header_level(chunk_root->node));
-	btrfs_set_super_chunk_root_generation(&root->fs_info->super_copy,
-				btrfs_header_generation(chunk_root->node));
+	btrfs_set_root_node(&root->fs_info->tree_root->root_item,
+			    root->fs_info->tree_root->node);
+	free_extent_buffer(root->fs_info->tree_root->commit_root);
+	root->fs_info->tree_root->commit_root =
+				btrfs_root_node(root->fs_info->tree_root);
+
+	btrfs_set_root_node(&root->fs_info->chunk_root->root_item,
+			    root->fs_info->chunk_root->node);
+	free_extent_buffer(root->fs_info->chunk_root->commit_root);
+	root->fs_info->chunk_root->commit_root =
+				btrfs_root_node(root->fs_info->chunk_root);
+
+	update_super_roots(root);
 
 	if (!root->fs_info->log_root_recovering) {
 		btrfs_set_super_log_root(&root->fs_info->super_copy, 0);
@@ -1153,7 +1031,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	trans->transaction->blocked = 0;
 
-	wake_up(&root->fs_info->transaction_throttle);
 	wake_up(&root->fs_info->transaction_wait);
 
 	mutex_unlock(&root->fs_info->trans_mutex);
@@ -1170,9 +1047,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	btrfs_finish_extent_commit(trans, root, pinned_copy);
 	kfree(pinned_copy);
 
-	btrfs_drop_dead_reloc_roots(root);
-	mutex_unlock(&root->fs_info->tree_reloc_mutex);
-
 	/* do the directory inserts of any pending snapshot creations */
 	finish_pending_snapshots(trans, root->fs_info);
 
@@ -1186,16 +1060,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	put_transaction(cur_trans);
 	put_transaction(cur_trans);
 
-	list_splice_init(&dirty_fs_roots, &root->fs_info->dead_roots);
-	if (root->fs_info->closing)
-		list_splice_init(&root->fs_info->dead_roots, &dirty_fs_roots);
-
 	mutex_unlock(&root->fs_info->trans_mutex);
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
-
-	if (root->fs_info->closing)
-		drop_dirty_roots(root->fs_info->tree_root, &dirty_fs_roots);
 	return ret;
 }
 
@@ -1204,16 +1071,17 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
  */
 int btrfs_clean_old_snapshots(struct btrfs_root *root)
 {
-	struct list_head dirty_roots;
-	INIT_LIST_HEAD(&dirty_roots);
-again:
-	mutex_lock(&root->fs_info->trans_mutex);
-	list_splice_init(&root->fs_info->dead_roots, &dirty_roots);
-	mutex_unlock(&root->fs_info->trans_mutex);
+	LIST_HEAD(list);
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	if (!list_empty(&dirty_roots)) {
-		drop_dirty_roots(root, &dirty_roots);
-		goto again;
+	mutex_lock(&fs_info->trans_mutex);
+	list_splice_init(&fs_info->dead_roots, &list);
+	mutex_unlock(&fs_info->trans_mutex);
+
+	while (!list_empty(&list)) {
+		root = list_entry(list.next, struct btrfs_root, root_list);
+		list_del_init(&root->root_list);
+		btrfs_drop_dead_root(root);
 	}
 	return 0;
 }
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 94f5bde2b58d..961c3ee5a2e1 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -62,12 +62,6 @@ struct btrfs_pending_snapshot {
 	struct list_head list;
 };
 
-struct btrfs_dirty_root {
-	struct list_head list;
-	struct btrfs_root *root;
-	struct btrfs_root *latest_root;
-};
-
 static inline void btrfs_set_trans_block_group(struct btrfs_trans_handle *trans,
 					       struct inode *inode)
 {
@@ -100,7 +94,8 @@ int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
 int btrfs_commit_tree_roots(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root);
 
-int btrfs_add_dead_root(struct btrfs_root *root, struct btrfs_root *latest);
+int btrfs_add_dead_root(struct btrfs_root *root);
+int btrfs_drop_dead_root(struct btrfs_root *root);
 int btrfs_defrag_root(struct btrfs_root *root, int cacheonly);
 int btrfs_clean_old_snapshots(struct btrfs_root *root);
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
@@ -108,7 +103,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root);
 void btrfs_throttle(struct btrfs_root *root);
-int btrfs_record_root_in_trans(struct btrfs_root *root);
+int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root);
 int btrfs_write_and_wait_marked_extents(struct btrfs_root *root,
 					struct extent_io_tree *dirty_pages);
 #endif
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index db5e212e8445..c13922206d1b 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -430,18 +430,16 @@ no_copy:
 static noinline struct inode *read_one_inode(struct btrfs_root *root,
 					     u64 objectid)
 {
+	struct btrfs_key key;
 	struct inode *inode;
-	inode = btrfs_iget_locked(root->fs_info->sb, objectid, root);
-	if (inode->i_state & I_NEW) {
-		BTRFS_I(inode)->root = root;
-		BTRFS_I(inode)->location.objectid = objectid;
-		BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
-		BTRFS_I(inode)->location.offset = 0;
-		btrfs_read_locked_inode(inode);
-		unlock_new_inode(inode);
 
-	}
-	if (is_bad_inode(inode)) {
+	key.objectid = objectid;
+	key.type = BTRFS_INODE_ITEM_KEY;
+	key.offset = 0;
+	inode = btrfs_iget(root->fs_info->sb, &key, root);
+	if (IS_ERR(inode)) {
+		inode = NULL;
+	} else if (is_bad_inode(inode)) {
 		iput(inode);
 		inode = NULL;
 	}
@@ -541,6 +539,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+		u64 offset;
 		unsigned long dest_offset;
 		struct btrfs_key ins;
 
@@ -555,6 +554,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		ins.objectid = btrfs_file_extent_disk_bytenr(eb, item);
 		ins.offset = btrfs_file_extent_disk_num_bytes(eb, item);
 		ins.type = BTRFS_EXTENT_ITEM_KEY;
+		offset = key->offset - btrfs_file_extent_offset(eb, item);
 
 		if (ins.objectid > 0) {
 			u64 csum_start;
@@ -569,19 +569,16 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 			if (ret == 0) {
 				ret = btrfs_inc_extent_ref(trans, root,
 						ins.objectid, ins.offset,
-						path->nodes[0]->start,
-						root->root_key.objectid,
-						trans->transid, key->objectid);
+						0, root->root_key.objectid,
+						key->objectid, offset);
 			} else {
 				/*
 				 * insert the extent pointer in the extent
 				 * allocation tree
 				 */
-				ret = btrfs_alloc_logged_extent(trans, root,
-						path->nodes[0]->start,
-						root->root_key.objectid,
-						trans->transid, key->objectid,
-						&ins);
+				ret = btrfs_alloc_logged_file_extent(trans,
+						root, root->root_key.objectid,
+						key->objectid, offset, &ins);
 				BUG_ON(ret);
 			}
 			btrfs_release_path(root, path);
@@ -1706,9 +1703,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 				btrfs_wait_tree_block_writeback(next);
 				btrfs_tree_unlock(next);
 
-				ret = btrfs_drop_leaf_ref(trans, root, next);
-				BUG_ON(ret);
-
 				WARN_ON(root_owner !=
 					BTRFS_TREE_LOG_OBJECTID);
 				ret = btrfs_free_reserved_extent(root,
@@ -1753,10 +1747,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 		btrfs_wait_tree_block_writeback(next);
 		btrfs_tree_unlock(next);
 
-		if (*level == 0) {
-			ret = btrfs_drop_leaf_ref(trans, root, next);
-			BUG_ON(ret);
-		}
 		WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID);
 		ret = btrfs_free_reserved_extent(root, bytenr, blocksize);
 		BUG_ON(ret);
@@ -1811,12 +1801,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 				btrfs_wait_tree_block_writeback(next);
 				btrfs_tree_unlock(next);
 
-				if (*level == 0) {
-					ret = btrfs_drop_leaf_ref(trans, root,
-								  next);
-					BUG_ON(ret);
-				}
-
 				WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID);
 				ret = btrfs_free_reserved_extent(root,
 						path->nodes[*level]->start,
@@ -1884,11 +1868,6 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 			btrfs_wait_tree_block_writeback(next);
 			btrfs_tree_unlock(next);
 
-			if (orig_level == 0) {
-				ret = btrfs_drop_leaf_ref(trans, log,
-							  next);
-				BUG_ON(ret);
-			}
 			WARN_ON(log->root_key.objectid !=
 				BTRFS_TREE_LOG_OBJECTID);
 			ret = btrfs_free_reserved_extent(log, next->start,
@@ -2027,9 +2006,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	ret = btrfs_write_and_wait_marked_extents(log, &log->dirty_log_pages);
 	BUG_ON(ret);
 
-	btrfs_set_root_bytenr(&log->root_item, log->node->start);
-	btrfs_set_root_generation(&log->root_item, trans->transid);
-	btrfs_set_root_level(&log->root_item, btrfs_header_level(log->node));
+	btrfs_set_root_node(&log->root_item, log->node);
 
 	root->log_batch = 0;
 	root->log_transid++;
@@ -2581,7 +2558,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 				       ins_keys, ins_sizes, nr);
 	BUG_ON(ret);
 
-	for (i = 0; i < nr; i++) {
+	for (i = 0; i < nr; i++, dst_path->slots[0]++) {
 		dst_offset = btrfs_item_ptr_offset(dst_path->nodes[0],
 						   dst_path->slots[0]);
 
@@ -2617,36 +2594,31 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 			found_type = btrfs_file_extent_type(src, extent);
 			if (found_type == BTRFS_FILE_EXTENT_REG ||
 			    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
-				u64 ds = btrfs_file_extent_disk_bytenr(src,
-								   extent);
-				u64 dl = btrfs_file_extent_disk_num_bytes(src,
-								      extent);
-				u64 cs = btrfs_file_extent_offset(src, extent);
-				u64 cl = btrfs_file_extent_num_bytes(src,
-								     extent);;
+				u64 ds, dl, cs, cl;
+				ds = btrfs_file_extent_disk_bytenr(src,
+								extent);
+				/* ds == 0 is a hole */
+				if (ds == 0)
+					continue;
+
+				dl = btrfs_file_extent_disk_num_bytes(src,
+								extent);
+				cs = btrfs_file_extent_offset(src, extent);
+				cl = btrfs_file_extent_num_bytes(src,
+								extent);;
 				if (btrfs_file_extent_compression(src,
 								  extent)) {
 					cs = 0;
 					cl = dl;
 				}
-				/* ds == 0 is a hole */
-				if (ds != 0) {
-					ret = btrfs_inc_extent_ref(trans, log,
-						   ds, dl,
-						   dst_path->nodes[0]->start,
-						   BTRFS_TREE_LOG_OBJECTID,
-						   trans->transid,
-						   ins_keys[i].objectid);
-					BUG_ON(ret);
-					ret = btrfs_lookup_csums_range(
-						   log->fs_info->csum_root,
-						   ds + cs, ds + cs + cl - 1,
-						   &ordered_sums);
-					BUG_ON(ret);
-				}
+
+				ret = btrfs_lookup_csums_range(
+						log->fs_info->csum_root,
+						ds + cs, ds + cs + cl - 1,
+						&ordered_sums);
+				BUG_ON(ret);
 			}
 		}
-		dst_path->slots[0]++;
 	}
 
 	btrfs_mark_buffer_dirty(dst_path->nodes[0]);
@@ -3029,9 +3001,7 @@ again:
 		BUG_ON(!wc.replay_dest);
 
 		wc.replay_dest->log_root = log;
-		mutex_lock(&fs_info->trans_mutex);
-		btrfs_record_root_in_trans(wc.replay_dest);
-		mutex_unlock(&fs_info->trans_mutex);
+		btrfs_record_root_in_trans(trans, wc.replay_dest);
 		ret = walk_log_tree(trans, log, &wc);
 		BUG_ON(ret);
 
@@ -3049,6 +3019,7 @@ again:
 		key.offset = found_key.offset - 1;
 		wc.replay_dest->log_root = NULL;
 		free_extent_buffer(log->node);
+		free_extent_buffer(log->commit_root);
 		kfree(log);
 
 		if (found_key.offset == 0)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a6d35b0054ca..3ab80e9cd767 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -161,8 +161,10 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 	int again = 0;
 	unsigned long num_run;
 	unsigned long num_sync_run;
+	unsigned long batch_run = 0;
 	unsigned long limit;
 	unsigned long last_waited = 0;
+	int force_reg = 0;
 
 	bdi = blk_get_backing_dev_info(device->bdev);
 	fs_info = device->dev_root->fs_info;
@@ -176,19 +178,22 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 
 loop:
 	spin_lock(&device->io_lock);
-	num_run = 0;
 
 loop_lock:
+	num_run = 0;
 
 	/* take all the bios off the list at once and process them
 	 * later on (without the lock held).  But, remember the
 	 * tail and other pointers so the bios can be properly reinserted
 	 * into the list if we hit congestion
 	 */
-	if (device->pending_sync_bios.head)
+	if (!force_reg && device->pending_sync_bios.head) {
 		pending_bios = &device->pending_sync_bios;
-	else
+		force_reg = 1;
+	} else {
 		pending_bios = &device->pending_bios;
+		force_reg = 0;
+	}
 
 	pending = pending_bios->head;
 	tail = pending_bios->tail;
@@ -228,10 +233,14 @@ loop_lock:
 	while (pending) {
 
 		rmb();
-		if (pending_bios != &device->pending_sync_bios &&
-		    device->pending_sync_bios.head &&
-		    num_run > 16) {
-			cond_resched();
+		/* we want to work on both lists, but do more bios on the
+		 * sync list than the regular list
+		 */
+		if ((num_run > 32 &&
+		    pending_bios != &device->pending_sync_bios &&
+		    device->pending_sync_bios.head) ||
+		   (num_run > 64 && pending_bios == &device->pending_sync_bios &&
+		    device->pending_bios.head)) {
 			spin_lock(&device->io_lock);
 			requeue_list(pending_bios, pending, tail);
 			goto loop_lock;
@@ -249,6 +258,8 @@ loop_lock:
 		BUG_ON(atomic_read(&cur->bi_cnt) == 0);
 		submit_bio(cur->bi_rw, cur);
 		num_run++;
+		batch_run++;
+
 		if (bio_sync(cur))
 			num_sync_run++;
 
@@ -265,7 +276,7 @@ loop_lock:
 		 * is now congested.  Back off and let other work structs
 		 * run instead
 		 */
-		if (pending && bdi_write_congested(bdi) && num_run > 16 &&
+		if (pending && bdi_write_congested(bdi) && batch_run > 32 &&
 		    fs_info->fs_devices->open_devices > 1) {
 			struct io_context *ioc;
 
@@ -366,6 +377,7 @@ static noinline int device_list_add(const char *path,
 		memcpy(fs_devices->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
 		fs_devices->latest_devid = devid;
 		fs_devices->latest_trans = found_transid;
+		mutex_init(&fs_devices->device_list_mutex);
 		device = NULL;
 	} else {
 		device = __find_device(&fs_devices->devices, devid,
@@ -392,7 +404,11 @@ static noinline int device_list_add(const char *path,
 			return -ENOMEM;
 		}
 		INIT_LIST_HEAD(&device->dev_alloc_list);
+
+		mutex_lock(&fs_devices->device_list_mutex);
 		list_add(&device->dev_list, &fs_devices->devices);
+		mutex_unlock(&fs_devices->device_list_mutex);
+
 		device->fs_devices = fs_devices;
 		fs_devices->num_devices++;
 	}
@@ -418,10 +434,12 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 	INIT_LIST_HEAD(&fs_devices->devices);
 	INIT_LIST_HEAD(&fs_devices->alloc_list);
 	INIT_LIST_HEAD(&fs_devices->list);
+	mutex_init(&fs_devices->device_list_mutex);
 	fs_devices->latest_devid = orig->latest_devid;
 	fs_devices->latest_trans = orig->latest_trans;
 	memcpy(fs_devices->fsid, orig->fsid, sizeof(fs_devices->fsid));
 
+	mutex_lock(&orig->device_list_mutex);
 	list_for_each_entry(orig_dev, &orig->devices, dev_list) {
 		device = kzalloc(sizeof(*device), GFP_NOFS);
 		if (!device)
@@ -443,8 +461,10 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		device->fs_devices = fs_devices;
 		fs_devices->num_devices++;
 	}
+	mutex_unlock(&orig->device_list_mutex);
 	return fs_devices;
 error:
+	mutex_unlock(&orig->device_list_mutex);
 	free_fs_devices(fs_devices);
 	return ERR_PTR(-ENOMEM);
 }
@@ -455,6 +475,7 @@ int btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices)
 
 	mutex_lock(&uuid_mutex);
 again:
+	mutex_lock(&fs_devices->device_list_mutex);
 	list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
 		if (device->in_fs_metadata)
 			continue;
@@ -474,6 +495,7 @@ again:
 		kfree(device->name);
 		kfree(device);
 	}
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	if (fs_devices->seed) {
 		fs_devices = fs_devices->seed;
@@ -594,6 +616,9 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		device->in_fs_metadata = 0;
 		device->mode = flags;
 
+		if (!blk_queue_nonrot(bdev_get_queue(bdev)))
+			fs_devices->rotating = 1;
+
 		fs_devices->open_devices++;
 		if (device->writeable) {
 			fs_devices->rw_devices++;
@@ -1121,12 +1146,14 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 
 		device = NULL;
 		devices = &root->fs_info->fs_devices->devices;
+		mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 		list_for_each_entry(tmp, devices, dev_list) {
 			if (tmp->in_fs_metadata && !tmp->bdev) {
 				device = tmp;
 				break;
 			}
 		}
+		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 		bdev = NULL;
 		bh = NULL;
 		disk_super = NULL;
@@ -1181,7 +1208,16 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		goto error_brelse;
 
 	device->in_fs_metadata = 0;
+
+	/*
+	 * the device list mutex makes sure that we don't change
+	 * the device list while someone else is writing out all
+	 * the device supers.
+	 */
+	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	list_del_init(&device->dev_list);
+	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+
 	device->fs_devices->num_devices--;
 
 	next_device = list_entry(root->fs_info->fs_devices->devices.next,
@@ -1275,6 +1311,7 @@ static int btrfs_prepare_sprout(struct btrfs_trans_handle *trans,
 	seed_devices->opened = 1;
 	INIT_LIST_HEAD(&seed_devices->devices);
 	INIT_LIST_HEAD(&seed_devices->alloc_list);
+	mutex_init(&seed_devices->device_list_mutex);
 	list_splice_init(&fs_devices->devices, &seed_devices->devices);
 	list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list);
 	list_for_each_entry(device, &seed_devices->devices, dev_list) {
@@ -1400,6 +1437,10 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	mutex_lock(&root->fs_info->volume_mutex);
 
 	devices = &root->fs_info->fs_devices->devices;
+	/*
+	 * we have the volume lock, so we don't need the extra
+	 * device list mutex while reading the list here.
+	 */
 	list_for_each_entry(device, devices, dev_list) {
 		if (device->bdev == bdev) {
 			ret = -EEXIST;
@@ -1454,6 +1495,12 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	}
 
 	device->fs_devices = root->fs_info->fs_devices;
+
+	/*
+	 * we don't want write_supers to jump in here with our device
+	 * half setup
+	 */
+	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	list_add(&device->dev_list, &root->fs_info->fs_devices->devices);
 	list_add(&device->dev_alloc_list,
 		 &root->fs_info->fs_devices->alloc_list);
@@ -1462,6 +1509,9 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	root->fs_info->fs_devices->rw_devices++;
 	root->fs_info->fs_devices->total_rw_bytes += device->total_bytes;
 
+	if (!blk_queue_nonrot(bdev_get_queue(bdev)))
+		root->fs_info->fs_devices->rotating = 1;
+
 	total_bytes = btrfs_super_total_bytes(&root->fs_info->super_copy);
 	btrfs_set_super_total_bytes(&root->fs_info->super_copy,
 				    total_bytes + device->total_bytes);
@@ -1469,6 +1519,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	total_bytes = btrfs_super_num_devices(&root->fs_info->super_copy);
 	btrfs_set_super_num_devices(&root->fs_info->super_copy,
 				    total_bytes + 1);
+	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
 	if (seeding_dev) {
 		ret = init_first_rw_device(trans, root, device);
@@ -1671,8 +1722,6 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
 	int ret;
 	int i;
 
-	printk(KERN_INFO "btrfs relocating chunk %llu\n",
-	       (unsigned long long)chunk_offset);
 	root = root->fs_info->chunk_root;
 	extent_root = root->fs_info->extent_root;
 	em_tree = &root->fs_info->mapping_tree.map_tree;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 5c3ff6d02fd7..5139a833f721 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -96,7 +96,12 @@ struct btrfs_fs_devices {
 	u64 rw_devices;
 	u64 total_rw_bytes;
 	struct block_device *latest_bdev;
-	/* all of the devices in the FS */
+
+	/* all of the devices in the FS, protected by a mutex
+	 * so we can safely walk it to write out the supers without
+	 * worrying about add/remove by the multi-device code
+	 */
+	struct mutex device_list_mutex;
 	struct list_head devices;
 
 	/* devices not currently being allocated */
@@ -107,6 +112,11 @@ struct btrfs_fs_devices {
 	int seeding;
 
 	int opened;
+
+	/* set when we find or add a device that doesn't have the
+	 * nonrot flag set
+	 */
+	int rotating;
 };
 
 struct btrfs_bio_stripe {
diff --git a/fs/buffer.c b/fs/buffer.c
index 49106127a4aa..a3ef091a45bd 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1085,12 +1085,12 @@ static struct buffer_head *
 __getblk_slow(struct block_device *bdev, sector_t block, int size)
 {
 	/* Size must be multiple of hard sectorsize */
-	if (unlikely(size & (bdev_hardsect_size(bdev)-1) ||
+	if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
 			(size < 512 || size > PAGE_SIZE))) {
 		printk(KERN_ERR "getblk(): invalid block size %d requested\n",
 					size);
-		printk(KERN_ERR "hardsect size: %d\n",
-					bdev_hardsect_size(bdev));
+		printk(KERN_ERR "logical block size: %d\n",
+					bdev_logical_block_size(bdev));
 
 		dump_stack();
 		return NULL;
@@ -2935,6 +2935,8 @@ int submit_bh(int rw, struct buffer_head * bh)
 	BUG_ON(!buffer_locked(bh));
 	BUG_ON(!buffer_mapped(bh));
 	BUG_ON(!bh->b_end_io);
+	BUG_ON(buffer_delay(bh));
+	BUG_ON(buffer_unwritten(bh));
 
 	/*
 	 * Mask in barrier bit for a write (could be either a WRITE or a
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 1e962348d111..431accd475a7 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -354,7 +354,9 @@ static void cachefiles_sync_cache(struct fscache_cache *_cache)
 	/* make sure all pages pinned by operations on behalf of the netfs are
 	 * written to disc */
 	cachefiles_begin_secure(cache, &saved_cred);
-	ret = fsync_super(cache->mnt->mnt_sb);
+	down_read(&cache->mnt->mnt_sb->s_umount);
+	ret = sync_filesystem(cache->mnt->mnt_sb);
+	up_read(&cache->mnt->mnt_sb->s_umount);
 	cachefiles_end_secure(cache, saved_cred);
 
 	if (ret == -EIO)
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 38f71222a552..b7c9d5187a75 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -375,7 +375,6 @@ static int chrdev_open(struct inode *inode, struct file *filp)
 		p = inode->i_cdev;
 		if (!p) {
 			inode->i_cdev = p = new;
-			inode->i_cindex = idx;
 			list_add(&inode->i_devices, &p->list);
 			new = NULL;
 		} else if (!cdev_get(p))
@@ -405,6 +404,18 @@ static int chrdev_open(struct inode *inode, struct file *filp)
 	return ret;
 }
 
+int cdev_index(struct inode *inode)
+{
+	int idx;
+	struct kobject *kobj;
+
+	kobj = kobj_lookup(cdev_map, inode->i_rdev, &idx);
+	if (!kobj)
+		return -1;
+	kobject_put(kobj);
+	return idx;
+}
+
 void cd_forget(struct inode *inode)
 {
 	spin_lock(&cdev_lock);
@@ -557,6 +568,7 @@ EXPORT_SYMBOL(cdev_init);
 EXPORT_SYMBOL(cdev_alloc);
 EXPORT_SYMBOL(cdev_del);
 EXPORT_SYMBOL(cdev_add);
+EXPORT_SYMBOL(cdev_index);
 EXPORT_SYMBOL(register_chrdev);
 EXPORT_SYMBOL(unregister_chrdev);
 EXPORT_SYMBOL(directly_mappable_cdev_bdi);
diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES
index f20c4069c220..b48689839428 100644
--- a/fs/cifs/CHANGES
+++ b/fs/cifs/CHANGES
@@ -1,3 +1,12 @@
+Version 1.59
+------------
+Client uses server inode numbers (which are persistent) rather than
+client generated ones by default (mount option "serverino" turned
+on by default if server supports it).  Add forceuid and forcegid
+mount options (so that when negotiating unix extensions specifying
+which uid mounted does not immediately force the server's reported
+uids to be overridden).
+
 Version 1.58
 ------------
 Guard against buffer overruns in various UCS-2 to UTF-8 string conversions
@@ -10,6 +19,8 @@ we converted from).  Fix endianness of the vcnum field used during
 session setup to distinguish multiple mounts to same server from different
 userids. Raw NTLMSSP fixed (it requires /proc/fs/cifs/experimental
 flag to be set to 2, and mount must enable krb5 to turn on extended security).
+Performance of file create to Samba improved (posix create on lookup
+removes 1 of 2 network requests sent on file create)
  
 Version 1.57
 ------------
diff --git a/fs/cifs/README b/fs/cifs/README
index db208ddb9899..ad92921dbde4 100644
--- a/fs/cifs/README
+++ b/fs/cifs/README
@@ -262,7 +262,8 @@ A partial list of the supported mount options follows:
 		mount.	
   domain	Set the SMB/CIFS workgroup name prepended to the
 		username during CIFS session establishment
-  uid		Set the default uid for inodes. For mounts to servers
+  forceuid	Set the default uid for inodes based on the uid
+		passed in. For mounts to servers
 		which do support the CIFS Unix extensions, such as a
 		properly configured Samba server, the server provides
 		the uid, gid and mode so this parameter should  not be
@@ -292,6 +293,12 @@ A partial list of the supported mount options follows:
 		the client.  Note that the mount.cifs helper must be
 		at version 1.10 or higher to support specifying the uid
 		(or gid) in non-numeric form.
+  forcegid	(similar to above but for the groupid instead of uid)
+  uid		Set the default uid for inodes, and indicate to the
+		cifs kernel driver which local user mounted . If the server
+		supports the unix extensions the default uid is
+		not used to fill in the owner fields of inodes (files)
+		unless the "forceuid" parameter is specified.
   gid		Set the default gid for inodes (similar to above).
   file_mode     If CIFS Unix extensions are not supported by the server
 		this overrides the default mode for file inodes.
@@ -388,8 +395,13 @@ A partial list of the supported mount options follows:
 		or the CIFS Unix Extensions equivalent and for those
 		this mount option will have no effect.  Exporting cifs mounts
 		under nfsd requires this mount option on the cifs mount.
+		This is now the default if server supports the 
+		required network operation.
   noserverino   Client generates inode numbers (rather than using the actual one
-		from the server) by default.
+		from the server). These inode numbers will vary after
+		unmount or reboot which can confuse some applications,
+		but not all server filesystems support unique inode
+		numbers.
   setuids       If the CIFS Unix extensions are negotiated with the server
 		the client will attempt to set the effective uid and gid of
 		the local process on newly created files, directories, and
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 83d62759c7c7..3bb11be8b6a8 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -275,7 +275,7 @@ static int add_mount_helper(struct vfsmount *newmnt, struct nameidata *nd,
 	case -EBUSY:
 		/* someone else made a mount here whilst we were busy */
 		while (d_mountpoint(nd->path.dentry) &&
-		       follow_down(&nd->path.mnt, &nd->path.dentry))
+		       follow_down(&nd->path))
 			;
 		err = 0;
 	default:
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 67bf93a40d2e..4a4581cb2b5e 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -23,6 +23,7 @@
 #include <linux/string.h>
 #include <keys/user-type.h>
 #include <linux/key-type.h>
+#include <linux/inet.h>
 #include "cifsglob.h"
 #include "cifs_spnego.h"
 #include "cifs_debug.h"
@@ -73,9 +74,6 @@ struct key_type cifs_spnego_key_type = {
  * strlen(";sec=ntlmsspi") */
 #define MAX_MECH_STR_LEN	13
 
-/* max possible addr len eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/128 */
-#define MAX_IPV6_ADDR_LEN	43
-
 /* strlen of "host=" */
 #define HOST_KEY_LEN		5
 
@@ -102,7 +100,7 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo)
 	   host=hostname sec=mechanism uid=0xFF user=username */
 	desc_len = MAX_VER_STR_LEN +
 		   HOST_KEY_LEN + strlen(hostname) +
-		   IP_KEY_LEN + MAX_IPV6_ADDR_LEN +
+		   IP_KEY_LEN + INET6_ADDRSTRLEN +
 		   MAX_MECH_STR_LEN +
 		   UID_KEY_LEN + (sizeof(uid_t) * 2) +
 		   USER_KEY_LEN + strlen(sesInfo->userName) + 1;
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 57ecdc83c26f..1403b5d86a73 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -552,130 +552,138 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
 	return rc;
 }
 
-
-/* Retrieve an ACL from the server */
-static struct cifs_ntsd *get_cifs_acl(u32 *pacllen, struct inode *inode,
-				       const char *path, const __u16 *pfid)
+static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
+		__u16 fid, u32 *pacllen)
 {
-	struct cifsFileInfo *open_file = NULL;
-	bool unlock_file = false;
-	int xid;
-	int rc = -EIO;
-	__u16 fid;
-	struct super_block *sb;
-	struct cifs_sb_info *cifs_sb;
 	struct cifs_ntsd *pntsd = NULL;
-
-	cFYI(1, ("get mode from ACL for %s", path));
-
-	if (inode == NULL)
-		return NULL;
+	int xid, rc;
 
 	xid = GetXid();
-	if (pfid == NULL)
-		open_file = find_readable_file(CIFS_I(inode));
-	else
-		fid = *pfid;
+	rc = CIFSSMBGetCIFSACL(xid, cifs_sb->tcon, fid, &pntsd, pacllen);
+	FreeXid(xid);
 
-	sb = inode->i_sb;
-	if (sb == NULL) {
-		FreeXid(xid);
-		return NULL;
-	}
-	cifs_sb = CIFS_SB(sb);
 
-	if (open_file) {
-		unlock_file = true;
-		fid = open_file->netfid;
-	} else if (pfid == NULL) {
-		int oplock = 0;
-		/* open file */
-		rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN,
-				READ_CONTROL, 0, &fid, &oplock, NULL,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
-		if (rc != 0) {
-			cERROR(1, ("Unable to open file to get ACL"));
-			FreeXid(xid);
-			return NULL;
-		}
+	cFYI(1, ("GetCIFSACL rc = %d ACL len %d", rc, *pacllen));
+	return pntsd;
+}
+
+static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb,
+		const char *path, u32 *pacllen)
+{
+	struct cifs_ntsd *pntsd = NULL;
+	int oplock = 0;
+	int xid, rc;
+	__u16 fid;
+
+	xid = GetXid();
+
+	rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, READ_CONTROL, 0,
+			 &fid, &oplock, NULL, cifs_sb->local_nls,
+			 cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+	if (rc) {
+		cERROR(1, ("Unable to open file to get ACL"));
+		goto out;
 	}
 
 	rc = CIFSSMBGetCIFSACL(xid, cifs_sb->tcon, fid, &pntsd, pacllen);
 	cFYI(1, ("GetCIFSACL rc = %d ACL len %d", rc, *pacllen));
-	if (unlock_file == true) /* find_readable_file increments ref count */
-		atomic_dec(&open_file->wrtPending);
-	else if (pfid == NULL) /* if opened above we have to close the handle */
-		CIFSSMBClose(xid, cifs_sb->tcon, fid);
-	/* else handle was passed in by caller */
 
+	CIFSSMBClose(xid, cifs_sb->tcon, fid);
+ out:
 	FreeXid(xid);
 	return pntsd;
 }
 
+/* Retrieve an ACL from the server */
+static struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
+				      struct inode *inode, const char *path,
+				      u32 *pacllen)
+{
+	struct cifs_ntsd *pntsd = NULL;
+	struct cifsFileInfo *open_file = NULL;
+
+	if (inode)
+		open_file = find_readable_file(CIFS_I(inode));
+	if (!open_file)
+		return get_cifs_acl_by_path(cifs_sb, path, pacllen);
+
+	pntsd = get_cifs_acl_by_fid(cifs_sb, open_file->netfid, pacllen);
+	atomic_dec(&open_file->wrtPending);
+	return pntsd;
+}
+
+static int set_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, __u16 fid,
+		struct cifs_ntsd *pnntsd, u32 acllen)
+{
+	int xid, rc;
+
+	xid = GetXid();
+	rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen);
+	FreeXid(xid);
+
+	cFYI(DBG2, ("SetCIFSACL rc = %d", rc));
+	return rc;
+}
+
+static int set_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, const char *path,
+		struct cifs_ntsd *pnntsd, u32 acllen)
+{
+	int oplock = 0;
+	int xid, rc;
+	__u16 fid;
+
+	xid = GetXid();
+
+	rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, WRITE_DAC, 0,
+			 &fid, &oplock, NULL, cifs_sb->local_nls,
+			 cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+	if (rc) {
+		cERROR(1, ("Unable to open file to set ACL"));
+		goto out;
+	}
+
+	rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen);
+	cFYI(DBG2, ("SetCIFSACL rc = %d", rc));
+
+	CIFSSMBClose(xid, cifs_sb->tcon, fid);
+ out:
+	FreeXid(xid);
+	return rc;
+}
+
 /* Set an ACL on the server */
 static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
 				struct inode *inode, const char *path)
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifsFileInfo *open_file;
-	bool unlock_file = false;
-	int xid;
-	int rc = -EIO;
-	__u16 fid;
-	struct super_block *sb;
-	struct cifs_sb_info *cifs_sb;
+	int rc;
 
 	cFYI(DBG2, ("set ACL for %s from mode 0x%x", path, inode->i_mode));
 
-	if (!inode)
-		return rc;
-
-	sb = inode->i_sb;
-	if (sb == NULL)
-		return rc;
-
-	cifs_sb = CIFS_SB(sb);
-	xid = GetXid();
-
 	open_file = find_readable_file(CIFS_I(inode));
-	if (open_file) {
-		unlock_file = true;
-		fid = open_file->netfid;
-	} else {
-		int oplock = 0;
-		/* open file */
-		rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN,
-				WRITE_DAC, 0, &fid, &oplock, NULL,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
-		if (rc != 0) {
-			cERROR(1, ("Unable to open file to set ACL"));
-			FreeXid(xid);
-			return rc;
-		}
-	}
-
-	rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen);
-	cFYI(DBG2, ("SetCIFSACL rc = %d", rc));
-	if (unlock_file)
-		atomic_dec(&open_file->wrtPending);
-	else
-		CIFSSMBClose(xid, cifs_sb->tcon, fid);
-
-	FreeXid(xid);
+	if (!open_file)
+		return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen);
 
+	rc = set_cifs_acl_by_fid(cifs_sb, open_file->netfid, pnntsd, acllen);
+	atomic_dec(&open_file->wrtPending);
 	return rc;
 }
 
 /* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */
-void acl_to_uid_mode(struct inode *inode, const char *path, const __u16 *pfid)
+void acl_to_uid_mode(struct cifs_sb_info *cifs_sb, struct inode *inode,
+		     const char *path, const __u16 *pfid)
 {
 	struct cifs_ntsd *pntsd = NULL;
 	u32 acllen = 0;
 	int rc = 0;
 
 	cFYI(DBG2, ("converting ACL to mode for %s", path));
-	pntsd = get_cifs_acl(&acllen, inode, path, pfid);
+
+	if (pfid)
+		pntsd = get_cifs_acl_by_fid(cifs_sb, *pfid, &acllen);
+	else
+		pntsd = get_cifs_acl(cifs_sb, inode, path, &acllen);
 
 	/* if we can retrieve the ACL, now parse Access Control Entries, ACEs */
 	if (pntsd)
@@ -698,7 +706,7 @@ int mode_to_acl(struct inode *inode, const char *path, __u64 nmode)
 	cFYI(DBG2, ("set ACL from mode for %s", path));
 
 	/* Get the security descriptor */
-	pntsd = get_cifs_acl(&secdesclen, inode, path, NULL);
+	pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen);
 
 	/* Add three ACEs for owner, group, everyone getting rid of
 	   other ACEs as chmod disables ACEs and set the security descriptor */
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 5e6d35804d73..0d92114195ab 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -146,7 +146,7 @@ cifs_read_super(struct super_block *sb, void *data,
 #endif
 	sb->s_blocksize = CIFS_MAX_MSGSIZE;
 	sb->s_blocksize_bits = 14;	/* default 2**14 = CIFS_MAX_MSGSIZE */
-	inode = cifs_iget(sb, ROOT_I);
+	inode = cifs_root_iget(sb, ROOT_I);
 
 	if (IS_ERR(inode)) {
 		rc = PTR_ERR(inode);
@@ -204,6 +204,9 @@ cifs_put_super(struct super_block *sb)
 		cFYI(1, ("Empty cifs superblock info passed to unmount"));
 		return;
 	}
+
+	lock_kernel();
+
 	rc = cifs_umount(sb, cifs_sb);
 	if (rc)
 		cERROR(1, ("cifs_umount failed with return code %d", rc));
@@ -216,7 +219,8 @@ cifs_put_super(struct super_block *sb)
 
 	unload_nls(cifs_sb->local_nls);
 	kfree(cifs_sb);
-	return;
+
+	unlock_kernel();
 }
 
 static int
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 051b71cfdea9..9570a0e8023f 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -36,7 +36,7 @@ extern void cifs_read_inode(struct inode *);
 
 /* Functions related to inodes */
 extern const struct inode_operations cifs_dir_inode_ops;
-extern struct inode *cifs_iget(struct super_block *, unsigned long);
+extern struct inode *cifs_root_iget(struct super_block *, unsigned long);
 extern int cifs_create(struct inode *, struct dentry *, int,
 		       struct nameidata *);
 extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
@@ -100,5 +100,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 extern const struct export_operations cifs_export_ops;
 #endif /* EXPERIMENTAL */
 
-#define CIFS_VERSION   "1.58"
+#define CIFS_VERSION   "1.59"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index fae083930eee..f9452329bcce 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -90,10 +90,10 @@ extern struct oplock_q_entry *AllocOplockQEntry(struct inode *, u16,
 						 struct cifsTconInfo *);
 extern void DeleteOplockQEntry(struct oplock_q_entry *);
 extern void DeleteTconOplockQEntries(struct cifsTconInfo *);
-extern struct timespec cifs_NTtimeToUnix(u64 utc_nanoseconds_since_1601);
+extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
 extern u64 cifs_UnixTimeToNT(struct timespec);
-extern __le64 cnvrtDosCifsTm(__u16 date, __u16 time);
-extern struct timespec cnvrtDosUnixTm(__u16 date, __u16 time);
+extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
+				      int offset);
 
 extern int cifs_posix_open(char *full_path, struct inode **pinode,
 			   struct super_block *sb, int mode, int oflags,
@@ -108,8 +108,8 @@ extern int cifs_get_inode_info(struct inode **pinode,
 extern int cifs_get_inode_info_unix(struct inode **pinode,
 			const unsigned char *search_path,
 			struct super_block *sb, int xid);
-extern void acl_to_uid_mode(struct inode *inode, const char *path,
-			    const __u16 *pfid);
+extern void acl_to_uid_mode(struct cifs_sb_info *cifs_sb, struct inode *inode,
+			    const char *path, const __u16 *pfid);
 extern int mode_to_acl(struct inode *inode, const char *path, __u64);
 
 extern int cifs_mount(struct super_block *, struct cifs_sb_info *, char *,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index d06260251c30..b84c61d5bca4 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -524,8 +524,8 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 			int val, seconds, remain, result;
 			struct timespec ts, utc;
 			utc = CURRENT_TIME;
-			ts = cnvrtDosUnixTm(le16_to_cpu(rsp->SrvTime.Date),
-						le16_to_cpu(rsp->SrvTime.Time));
+			ts = cnvrtDosUnixTm(rsp->SrvTime.Date,
+					    rsp->SrvTime.Time, 0);
 			cFYI(1, ("SrvTime %d sec since 1970 (utc: %d) diff: %d",
 				(int)ts.tv_sec, (int)utc.tv_sec,
 				(int)(utc.tv_sec - ts.tv_sec)));
@@ -2427,8 +2427,7 @@ querySymLinkRetry:
 	params = 2 /* level */  + 4 /* rsrvd */  + name_len /* incl null */ ;
 	pSMB->TotalDataCount = 0;
 	pSMB->MaxParameterCount = cpu_to_le16(2);
-	/* BB find exact max data count below from sess structure BB */
-	pSMB->MaxDataCount = cpu_to_le16(4000);
+	pSMB->MaxDataCount = cpu_to_le16(CIFSMaxBufSize);
 	pSMB->MaxSetupCount = 0;
 	pSMB->Reserved = 0;
 	pSMB->Flags = 0;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 4aa81a507b74..97f4311b9a8e 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -35,6 +35,7 @@
 #include <linux/namei.h>
 #include <asm/uaccess.h>
 #include <asm/processor.h>
+#include <linux/inet.h>
 #include <net/ipv6.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
@@ -61,7 +62,6 @@ struct smb_vol {
 	char *domainname;
 	char *UNC;
 	char *UNCip;
-	char *in6_addr;   /* ipv6 address as human readable form of in6_addr */
 	char *iocharset;  /* local code page for mapping to and from Unicode */
 	char source_rfc1001_name[16]; /* netbios name of client */
 	char target_rfc1001_name[16]; /* netbios name of server for Win9x/ME */
@@ -827,14 +827,16 @@ cifs_parse_mount_options(char *options, const char *devname,
 	vol->target_rfc1001_name[0] = 0;
 	vol->linux_uid = current_uid();  /* use current_euid() instead? */
 	vol->linux_gid = current_gid();
-	vol->dir_mode = S_IRWXUGO;
-	/* 2767 perms indicate mandatory locking support */
-	vol->file_mode = (S_IRWXUGO | S_ISGID) & (~S_IXGRP);
+
+	/* default to only allowing write access to owner of the mount */
+	vol->dir_mode = vol->file_mode = S_IRUGO | S_IXUGO | S_IWUSR;
 
 	/* vol->retry default is 0 (i.e. "soft" limited retry not hard retry) */
 	vol->rw = true;
 	/* default is always to request posix paths. */
 	vol->posix_paths = 1;
+	/* default to using server inode numbers where available */
+	vol->server_ino = 1;
 
 	if (!options)
 		return 1;
@@ -955,10 +957,12 @@ cifs_parse_mount_options(char *options, const char *devname,
 				}
 				strcpy(vol->password, value);
 			}
-		} else if (strnicmp(data, "ip", 2) == 0) {
+		} else if (!strnicmp(data, "ip", 2) ||
+			   !strnicmp(data, "addr", 4)) {
 			if (!value || !*value) {
 				vol->UNCip = NULL;
-			} else if (strnlen(value, 35) < 35) {
+			} else if (strnlen(value, INET6_ADDRSTRLEN) <
+							INET6_ADDRSTRLEN) {
 				vol->UNCip = value;
 			} else {
 				printk(KERN_WARNING "CIFS: ip address "
@@ -1092,17 +1096,17 @@ cifs_parse_mount_options(char *options, const char *devname,
 				return 1;
 			}
 		} else if (strnicmp(data, "uid", 3) == 0) {
-			if (value && *value) {
+			if (value && *value)
 				vol->linux_uid =
 					simple_strtoul(value, &value, 0);
+		} else if (strnicmp(data, "forceuid", 8) == 0) {
 				vol->override_uid = 1;
-			}
 		} else if (strnicmp(data, "gid", 3) == 0) {
-			if (value && *value) {
+			if (value && *value)
 				vol->linux_gid =
 					simple_strtoul(value, &value, 0);
+		} else if (strnicmp(data, "forcegid", 8) == 0) {
 				vol->override_gid = 1;
-			}
 		} else if (strnicmp(data, "file_mode", 4) == 0) {
 			if (value && *value) {
 				vol->file_mode =
@@ -1315,16 +1319,6 @@ cifs_parse_mount_options(char *options, const char *devname,
 			vol->direct_io = 1;
 		} else if (strnicmp(data, "forcedirectio", 13) == 0) {
 			vol->direct_io = 1;
-		} else if (strnicmp(data, "in6_addr", 8) == 0) {
-			if (!value || !*value) {
-				vol->in6_addr = NULL;
-			} else if (strnlen(value, 49) == 48) {
-				vol->in6_addr = value;
-			} else {
-				printk(KERN_WARNING "CIFS: ip v6 address not "
-						    "48 characters long\n");
-				return 1;
-			}
 		} else if (strnicmp(data, "noac", 4) == 0) {
 			printk(KERN_WARNING "CIFS: Mount option noac not "
 				"supported. Instead set "
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 302ea15f02e6..06866841b97f 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -241,7 +241,7 @@ static inline int cifs_open_inode_helper(struct inode *inode, struct file *file,
 	/* BB need same check in cifs_create too? */
 	/* if not oplocked, invalidate inode pages if mtime or file
 	   size changed */
-	temp = cifs_NTtimeToUnix(le64_to_cpu(buf->LastWriteTime));
+	temp = cifs_NTtimeToUnix(buf->LastWriteTime);
 	if (timespec_equal(&file->f_path.dentry->d_inode->i_mtime, &temp) &&
 			   (file->f_path.dentry->d_inode->i_size ==
 			    (loff_t)le64_to_cpu(buf->EndOfFile))) {
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 9c869a6dcba1..fad882b075ba 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -85,10 +85,10 @@ static void cifs_unix_info_to_inode(struct inode *inode,
 	__u64 num_of_bytes = le64_to_cpu(info->NumOfBytes);
 	__u64 end_of_file = le64_to_cpu(info->EndOfFile);
 
-	inode->i_atime = cifs_NTtimeToUnix(le64_to_cpu(info->LastAccessTime));
+	inode->i_atime = cifs_NTtimeToUnix(info->LastAccessTime);
 	inode->i_mtime =
-		cifs_NTtimeToUnix(le64_to_cpu(info->LastModificationTime));
-	inode->i_ctime = cifs_NTtimeToUnix(le64_to_cpu(info->LastStatusChange));
+		cifs_NTtimeToUnix(info->LastModificationTime);
+	inode->i_ctime = cifs_NTtimeToUnix(info->LastStatusChange);
 	inode->i_mode = le64_to_cpu(info->Permissions);
 
 	/*
@@ -554,14 +554,11 @@ int cifs_get_inode_info(struct inode **pinode,
 
 	/* Linux can not store file creation time so ignore it */
 	if (pfindData->LastAccessTime)
-		inode->i_atime = cifs_NTtimeToUnix
-			(le64_to_cpu(pfindData->LastAccessTime));
+		inode->i_atime = cifs_NTtimeToUnix(pfindData->LastAccessTime);
 	else /* do not need to use current_fs_time - time not stored */
 		inode->i_atime = CURRENT_TIME;
-	inode->i_mtime =
-		    cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastWriteTime));
-	inode->i_ctime =
-	    cifs_NTtimeToUnix(le64_to_cpu(pfindData->ChangeTime));
+	inode->i_mtime = cifs_NTtimeToUnix(pfindData->LastWriteTime);
+	inode->i_ctime = cifs_NTtimeToUnix(pfindData->ChangeTime);
 	cFYI(DBG2, ("Attributes came in as 0x%x", attr));
 	if (adjustTZ && (pTcon->ses) && (pTcon->ses->server)) {
 		inode->i_ctime.tv_sec += pTcon->ses->server->timeAdj;
@@ -629,7 +626,7 @@ int cifs_get_inode_info(struct inode **pinode,
 	/* fill in 0777 bits from ACL */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
 		cFYI(1, ("Getting mode bits from ACL"));
-		acl_to_uid_mode(inode, full_path, pfid);
+		acl_to_uid_mode(cifs_sb, inode, full_path, pfid);
 	}
 #endif
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
@@ -699,7 +696,7 @@ char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb)
 }
 
 /* gets root inode */
-struct inode *cifs_iget(struct super_block *sb, unsigned long ino)
+struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino)
 {
 	int xid;
 	struct cifs_sb_info *cifs_sb;
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index e2fe998989a3..32d6baa0a54f 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -853,12 +853,12 @@ smbCalcSize_LE(struct smb_hdr *ptr)
 
 #define NTFS_TIME_OFFSET ((u64)(369*365 + 89) * 24 * 3600 * 10000000)
 
-    /*
-     * Convert the NT UTC (based 1601-01-01, in hundred nanosecond units)
-     * into Unix UTC (based 1970-01-01, in seconds).
-     */
+/*
+ * Convert the NT UTC (based 1601-01-01, in hundred nanosecond units)
+ * into Unix UTC (based 1970-01-01, in seconds).
+ */
 struct timespec
-cifs_NTtimeToUnix(u64 ntutc)
+cifs_NTtimeToUnix(__le64 ntutc)
 {
 	struct timespec ts;
 	/* BB what about the timezone? BB */
@@ -866,7 +866,7 @@ cifs_NTtimeToUnix(u64 ntutc)
 	/* Subtract the NTFS time offset, then convert to 1s intervals. */
 	u64 t;
 
-	t = ntutc - NTFS_TIME_OFFSET;
+	t = le64_to_cpu(ntutc) - NTFS_TIME_OFFSET;
 	ts.tv_nsec = do_div(t, 10000000) * 100;
 	ts.tv_sec = t;
 	return ts;
@@ -883,16 +883,12 @@ cifs_UnixTimeToNT(struct timespec t)
 static int total_days_of_prev_months[] =
 {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334};
 
-
-__le64 cnvrtDosCifsTm(__u16 date, __u16 time)
-{
-	return cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(date, time)));
-}
-
-struct timespec cnvrtDosUnixTm(__u16 date, __u16 time)
+struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
 {
 	struct timespec ts;
 	int sec, min, days, month, year;
+	u16 date = le16_to_cpu(le_date);
+	u16 time = le16_to_cpu(le_time);
 	SMB_TIME *st = (SMB_TIME *)&time;
 	SMB_DATE *sd = (SMB_DATE *)&date;
 
@@ -933,7 +929,7 @@ struct timespec cnvrtDosUnixTm(__u16 date, __u16 time)
 		days -= ((year & 0x03) == 0) && (month < 2 ? 1 : 0);
 	sec += 24 * 60 * 60 * days;
 
-	ts.tv_sec = sec;
+	ts.tv_sec = sec + offset;
 
 	/* cFYI(1,("sec after cnvrt dos to unix time %d",sec)); */
 
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 964e097c8203..86d0055dc529 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -115,17 +115,6 @@ construct_dentry(struct qstr *qstring, struct file *file,
 	return rc;
 }
 
-static void AdjustForTZ(struct cifsTconInfo *tcon, struct inode *inode)
-{
-	if ((tcon) && (tcon->ses) && (tcon->ses->server)) {
-		inode->i_ctime.tv_sec += tcon->ses->server->timeAdj;
-		inode->i_mtime.tv_sec += tcon->ses->server->timeAdj;
-		inode->i_atime.tv_sec += tcon->ses->server->timeAdj;
-	}
-	return;
-}
-
-
 static void fill_in_inode(struct inode *tmp_inode, int new_buf_type,
 			  char *buf, unsigned int *pobject_type, int isNewInode)
 {
@@ -150,26 +139,25 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type,
 		allocation_size = le64_to_cpu(pfindData->AllocationSize);
 		end_of_file = le64_to_cpu(pfindData->EndOfFile);
 		tmp_inode->i_atime =
-		      cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastAccessTime));
+			cifs_NTtimeToUnix(pfindData->LastAccessTime);
 		tmp_inode->i_mtime =
-		      cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastWriteTime));
+			cifs_NTtimeToUnix(pfindData->LastWriteTime);
 		tmp_inode->i_ctime =
-		      cifs_NTtimeToUnix(le64_to_cpu(pfindData->ChangeTime));
+			cifs_NTtimeToUnix(pfindData->ChangeTime);
 	} else { /* legacy, OS2 and DOS style */
-/*		struct timespec ts;*/
+		int offset = cifs_sb->tcon->ses->server->timeAdj;
 		FIND_FILE_STANDARD_INFO *pfindData =
 			(FIND_FILE_STANDARD_INFO *)buf;
 
-		tmp_inode->i_mtime = cnvrtDosUnixTm(
-				le16_to_cpu(pfindData->LastWriteDate),
-				le16_to_cpu(pfindData->LastWriteTime));
-		tmp_inode->i_atime = cnvrtDosUnixTm(
-				le16_to_cpu(pfindData->LastAccessDate),
-				le16_to_cpu(pfindData->LastAccessTime));
-		tmp_inode->i_ctime = cnvrtDosUnixTm(
-				le16_to_cpu(pfindData->LastWriteDate),
-				le16_to_cpu(pfindData->LastWriteTime));
-		AdjustForTZ(cifs_sb->tcon, tmp_inode);
+		tmp_inode->i_mtime = cnvrtDosUnixTm(pfindData->LastWriteDate,
+						    pfindData->LastWriteTime,
+						    offset);
+		tmp_inode->i_atime = cnvrtDosUnixTm(pfindData->LastAccessDate,
+						    pfindData->LastAccessTime,
+						    offset);
+		tmp_inode->i_ctime = cnvrtDosUnixTm(pfindData->LastWriteDate,
+						    pfindData->LastWriteTime,
+						    offset);
 		attr = le16_to_cpu(pfindData->Attributes);
 		allocation_size = le32_to_cpu(pfindData->AllocationSize);
 		end_of_file = le32_to_cpu(pfindData->DataSize);
@@ -331,11 +319,11 @@ static void unix_fill_in_inode(struct inode *tmp_inode,
 	local_size  = tmp_inode->i_size;
 
 	tmp_inode->i_atime =
-	    cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastAccessTime));
+	    cifs_NTtimeToUnix(pfindData->LastAccessTime);
 	tmp_inode->i_mtime =
-	    cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastModificationTime));
+	    cifs_NTtimeToUnix(pfindData->LastModificationTime);
 	tmp_inode->i_ctime =
-	    cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastStatusChange));
+	    cifs_NTtimeToUnix(pfindData->LastStatusChange);
 
 	tmp_inode->i_mode = le64_to_cpu(pfindData->Permissions);
 	/* since we set the inode type below we need to mask off type
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 6a347fbc998a..ffd42815fda1 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -47,6 +47,8 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos,
 		      struct pipe_inode_info *pipe, size_t count,
 		      unsigned int flags)
 {
+	ssize_t (*splice_read)(struct file *, loff_t *,
+			       struct pipe_inode_info *, size_t, unsigned int);
 	struct coda_file_info *cfi;
 	struct file *host_file;
 
@@ -54,10 +56,11 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos,
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
-	if (!host_file->f_op || !host_file->f_op->splice_read)
-		return -EINVAL;
+	splice_read = host_file->f_op->splice_read;
+	if (!splice_read)
+		splice_read = default_file_splice_read;
 
-	return host_file->f_op->splice_read(host_file, ppos, pipe, count,flags);
+	return splice_read(host_file, ppos, pipe, count, flags);
 }
 
 static ssize_t
diff --git a/fs/compat.c b/fs/compat.c
index 681ed81e6be0..6aefb776dfeb 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -812,10 +812,8 @@ asmlinkage long compat_sys_mount(char __user * dev_name, char __user * dir_name,
 		}
 	}
 
-	lock_kernel();
 	retval = do_mount((char*)dev_page, dir_page, (char*)type_page,
 			flags, (void*)data_page);
-	unlock_kernel();
 
  out4:
 	free_page(data_page);
@@ -1488,7 +1486,7 @@ int compat_do_execve(char * filename,
 	if (!bprm)
 		goto out_files;
 
-	retval = mutex_lock_interruptible(&current->cred_exec_mutex);
+	retval = mutex_lock_interruptible(&current->cred_guard_mutex);
 	if (retval < 0)
 		goto out_free;
 	current->in_execve = 1;
@@ -1550,7 +1548,7 @@ int compat_do_execve(char * filename,
 	/* execve succeeded */
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
-	mutex_unlock(&current->cred_exec_mutex);
+	mutex_unlock(&current->cred_guard_mutex);
 	acct_update_integrals(current);
 	free_bprm(bprm);
 	if (displaced)
@@ -1573,7 +1571,7 @@ out_unmark:
 
 out_unlock:
 	current->in_execve = 0;
-	mutex_unlock(&current->cred_exec_mutex);
+	mutex_unlock(&current->cred_guard_mutex);
 
 out_free:
 	free_bprm(bprm);
diff --git a/fs/dcache.c b/fs/dcache.c
index 75659a6fd1f8..9e5cd3c3a6ba 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1910,7 +1910,7 @@ char *__d_path(const struct path *path, struct path *root,
 
 	spin_lock(&vfsmount_lock);
 	prepend(&end, &buflen, "\0", 1);
-	if (!IS_ROOT(dentry) && d_unhashed(dentry) &&
+	if (d_unlinked(dentry) &&
 		(prepend(&end, &buflen, " (deleted)", 10) != 0))
 			goto Elong;
 
@@ -2035,7 +2035,7 @@ char *dentry_path(struct dentry *dentry, char *buf, int buflen)
 
 	spin_lock(&dcache_lock);
 	prepend(&end, &buflen, "\0", 1);
-	if (!IS_ROOT(dentry) && d_unhashed(dentry) &&
+	if (d_unlinked(dentry) &&
 		(prepend(&end, &buflen, "//deleted", 9) != 0))
 			goto Elong;
 	if (buflen < 1)
@@ -2097,9 +2097,8 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 	read_unlock(&current->fs->lock);
 
 	error = -ENOENT;
-	/* Has the current directory has been unlinked? */
 	spin_lock(&dcache_lock);
-	if (IS_ROOT(pwd.dentry) || !d_unhashed(pwd.dentry)) {
+	if (!d_unlinked(pwd.dentry)) {
 		unsigned long len;
 		struct path tmp = root;
 		char * cwd;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index c68edb969441..9b1d285f9fe6 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -557,8 +557,10 @@ static int __init init_devpts_fs(void)
 	int err = register_filesystem(&devpts_fs_type);
 	if (!err) {
 		devpts_mnt = kern_mount(&devpts_fs_type);
-		if (IS_ERR(devpts_mnt))
+		if (IS_ERR(devpts_mnt)) {
 			err = PTR_ERR(devpts_mnt);
+			unregister_filesystem(&devpts_fs_type);
+		}
 	}
 	return err;
 }
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 05763bbc2050..8b10b87dc01a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1127,7 +1127,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 		rw = WRITE_ODIRECT;
 
 	if (bdev)
-		bdev_blkbits = blksize_bits(bdev_hardsect_size(bdev));
+		bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev));
 
 	if (offset & blocksize_mask) {
 		if (bdev)
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index fa4c7e7d15d9..12d649602d3a 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -27,6 +27,7 @@
 #include <linux/mount.h>
 #include <linux/key.h>
 #include <linux/seq_file.h>
+#include <linux/smp_lock.h>
 #include <linux/file.h>
 #include <linux/crypto.h>
 #include "ecryptfs_kernel.h"
@@ -120,9 +121,13 @@ static void ecryptfs_put_super(struct super_block *sb)
 {
 	struct ecryptfs_sb_info *sb_info = ecryptfs_superblock_to_private(sb);
 
+	lock_kernel();
+
 	ecryptfs_destroy_mount_crypt_stat(&sb_info->mount_crypt_stat);
 	kmem_cache_free(ecryptfs_sb_info_cache, sb_info);
 	ecryptfs_set_superblock_private(sb, NULL);
+
+	unlock_kernel();
 }
 
 /**
diff --git a/fs/exec.c b/fs/exec.c
index 895823d0149d..e639957d7a57 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -33,6 +33,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/pagemap.h>
+#include <linux/perf_counter.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
 #include <linux/key.h>
@@ -922,6 +923,7 @@ void set_task_comm(struct task_struct *tsk, char *buf)
 	task_lock(tsk);
 	strlcpy(tsk->comm, buf, sizeof(tsk->comm));
 	task_unlock(tsk);
+	perf_counter_comm(tsk);
 }
 
 int flush_old_exec(struct linux_binprm * bprm)
@@ -990,6 +992,13 @@ int flush_old_exec(struct linux_binprm * bprm)
 
 	current->personality &= ~bprm->per_clear;
 
+	/*
+	 * Flush performance counters when crossing a
+	 * security domain:
+	 */
+	if (!get_dumpable(current->mm))
+		perf_counter_exit_task(current);
+
 	/* An exec changes our domain. We are no longer part of the thread
 	   group */
 
@@ -1016,7 +1025,7 @@ void install_exec_creds(struct linux_binprm *bprm)
 	commit_creds(bprm->cred);
 	bprm->cred = NULL;
 
-	/* cred_exec_mutex must be held at least to this point to prevent
+	/* cred_guard_mutex must be held at least to this point to prevent
 	 * ptrace_attach() from altering our determination of the task's
 	 * credentials; any time after this it may be unlocked */
 
@@ -1026,7 +1035,7 @@ EXPORT_SYMBOL(install_exec_creds);
 
 /*
  * determine how safe it is to execute the proposed program
- * - the caller must hold current->cred_exec_mutex to protect against
+ * - the caller must hold current->cred_guard_mutex to protect against
  *   PTRACE_ATTACH
  */
 int check_unsafe_exec(struct linux_binprm *bprm)
@@ -1268,7 +1277,7 @@ int do_execve(char * filename,
 	if (!bprm)
 		goto out_files;
 
-	retval = mutex_lock_interruptible(&current->cred_exec_mutex);
+	retval = mutex_lock_interruptible(&current->cred_guard_mutex);
 	if (retval < 0)
 		goto out_free;
 	current->in_execve = 1;
@@ -1331,7 +1340,7 @@ int do_execve(char * filename,
 	/* execve succeeded */
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
-	mutex_unlock(&current->cred_exec_mutex);
+	mutex_unlock(&current->cred_guard_mutex);
 	acct_update_integrals(current);
 	free_bprm(bprm);
 	if (displaced)
@@ -1354,7 +1363,7 @@ out_unmark:
 
 out_unlock:
 	current->in_execve = 0;
-	mutex_unlock(&current->cred_exec_mutex);
+	mutex_unlock(&current->cred_guard_mutex);
 
 out_free:
 	free_bprm(bprm);
diff --git a/fs/exofs/osd.c b/fs/exofs/osd.c
index b249ae97fb15..06ca92672eb5 100644
--- a/fs/exofs/osd.c
+++ b/fs/exofs/osd.c
@@ -50,10 +50,10 @@ int exofs_check_ok_resid(struct osd_request *or, u64 *in_resid, u64 *out_resid)
 
 	/* FIXME: should be include in osd_sense_info */
 	if (in_resid)
-		*in_resid = or->in.req ? or->in.req->data_len : 0;
+		*in_resid = or->in.req ? or->in.req->resid_len : 0;
 
 	if (out_resid)
-		*out_resid = or->out.req ? or->out.req->data_len : 0;
+		*out_resid = or->out.req ? or->out.req->resid_len : 0;
 
 	return ret;
 }
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 9f1985e857e2..8216c5b77b53 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -200,20 +200,21 @@ static const struct export_operations exofs_export_ops;
 /*
  * Write the superblock to the OSD
  */
-static void exofs_write_super(struct super_block *sb)
+static int exofs_sync_fs(struct super_block *sb, int wait)
 {
 	struct exofs_sb_info *sbi;
 	struct exofs_fscb *fscb;
 	struct osd_request *or;
 	struct osd_obj_id obj;
-	int ret;
+	int ret = -ENOMEM;
 
 	fscb = kzalloc(sizeof(struct exofs_fscb), GFP_KERNEL);
 	if (!fscb) {
 		EXOFS_ERR("exofs_write_super: memory allocation failed.\n");
-		return;
+		return -ENOMEM;
 	}
 
+	lock_super(sb);
 	lock_kernel();
 	sbi = sb->s_fs_info;
 	fscb->s_nextid = cpu_to_le64(sbi->s_nextid);
@@ -246,7 +247,17 @@ out:
 	if (or)
 		osd_end_request(or);
 	unlock_kernel();
+	unlock_super(sb);
 	kfree(fscb);
+	return ret;
+}
+
+static void exofs_write_super(struct super_block *sb)
+{
+	if (!(sb->s_flags & MS_RDONLY))
+		exofs_sync_fs(sb, 1);
+	else
+		sb->s_dirt = 0;
 }
 
 /*
@@ -258,6 +269,11 @@ static void exofs_put_super(struct super_block *sb)
 	int num_pend;
 	struct exofs_sb_info *sbi = sb->s_fs_info;
 
+	lock_kernel();
+
+	if (sb->s_dirt)
+		exofs_write_super(sb);
+
 	/* make sure there are no pending commands */
 	for (num_pend = atomic_read(&sbi->s_curr_pending); num_pend > 0;
 	     num_pend = atomic_read(&sbi->s_curr_pending)) {
@@ -271,6 +287,8 @@ static void exofs_put_super(struct super_block *sb)
 	osduld_put_device(sbi->s_dev);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
+
+	unlock_kernel();
 }
 
 /*
@@ -484,6 +502,7 @@ static const struct super_operations exofs_sops = {
 	.delete_inode   = exofs_delete_inode,
 	.put_super      = exofs_put_super,
 	.write_super    = exofs_write_super,
+	.sync_fs	= exofs_sync_fs,
 	.statfs         = exofs_statfs,
 };
 
diff --git a/fs/ext2/Makefile b/fs/ext2/Makefile
index e0b2b43c1fdb..f42af45cfd88 100644
--- a/fs/ext2/Makefile
+++ b/fs/ext2/Makefile
@@ -4,7 +4,7 @@
 
 obj-$(CONFIG_EXT2_FS) += ext2.o
 
-ext2-y := balloc.o dir.o file.o fsync.o ialloc.o inode.o \
+ext2-y := balloc.o dir.o file.o ialloc.o inode.o \
 	  ioctl.o namei.o super.o symlink.o
 
 ext2-$(CONFIG_EXT2_FS_XATTR)	 += xattr.o xattr_user.o xattr_trusted.o
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 2999d72153b7..003500498c22 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -720,5 +720,5 @@ const struct file_operations ext2_dir_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,
 #endif
-	.fsync		= ext2_sync_file,
+	.fsync		= simple_fsync,
 };
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 3203042b36ef..b2bbf45039e0 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -113,9 +113,6 @@ extern int ext2_empty_dir (struct inode *);
 extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **);
 extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *);
 
-/* fsync.c */
-extern int ext2_sync_file (struct file *, struct dentry *, int);
-
 /* ialloc.c */
 extern struct inode * ext2_new_inode (struct inode *, int);
 extern void ext2_free_inode (struct inode *);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 45ed07122182..2b9e47dc9222 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -55,7 +55,7 @@ const struct file_operations ext2_file_operations = {
 	.mmap		= generic_file_mmap,
 	.open		= generic_file_open,
 	.release	= ext2_release_file,
-	.fsync		= ext2_sync_file,
+	.fsync		= simple_fsync,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= generic_file_splice_write,
 };
@@ -72,7 +72,7 @@ const struct file_operations ext2_xip_file_operations = {
 	.mmap		= xip_file_mmap,
 	.open		= generic_file_open,
 	.release	= ext2_release_file,
-	.fsync		= ext2_sync_file,
+	.fsync		= simple_fsync,
 };
 #endif
 
diff --git a/fs/ext2/fsync.c b/fs/ext2/fsync.c
deleted file mode 100644
index fc66c93fcb5c..000000000000
--- a/fs/ext2/fsync.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- *  linux/fs/ext2/fsync.c
- *
- *  Copyright (C) 1993  Stephen Tweedie (sct@dcs.ed.ac.uk)
- *  from
- *  Copyright (C) 1992  Remy Card (card@masi.ibp.fr)
- *                      Laboratoire MASI - Institut Blaise Pascal
- *                      Universite Pierre et Marie Curie (Paris VI)
- *  from
- *  linux/fs/minix/truncate.c   Copyright (C) 1991, 1992  Linus Torvalds
- * 
- *  ext2fs fsync primitive
- *
- *  Big-endian to little-endian byte-swapping/bitmaps by
- *        David S. Miller (davem@caip.rutgers.edu), 1995
- * 
- *  Removed unnecessary code duplication for little endian machines
- *  and excessive __inline__s. 
- *        Andi Kleen, 1997
- *
- * Major simplications and cleanup - we only need to do the metadata, because
- * we can depend on generic_block_fdatasync() to sync the data blocks.
- */
-
-#include "ext2.h"
-#include <linux/buffer_head.h>		/* for sync_mapping_buffers() */
-
-
-/*
- *	File may be NULL when we are called. Perhaps we shouldn't
- *	even pass file to fsync ?
- */
-
-int ext2_sync_file(struct file *file, struct dentry *dentry, int datasync)
-{
-	struct inode *inode = dentry->d_inode;
-	int err;
-	int ret;
-
-	ret = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY))
-		return ret;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		return ret;
-
-	err = ext2_sync_inode(inode);
-	if (ret == 0)
-		ret = err;
-	return ret;
-}
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index acf678831103..29ed682061f6 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -41,8 +41,6 @@ MODULE_AUTHOR("Remy Card and others");
 MODULE_DESCRIPTION("Second Extended Filesystem");
 MODULE_LICENSE("GPL");
 
-static int ext2_update_inode(struct inode * inode, int do_sync);
-
 /*
  * Test whether an inode is a fast symlink.
  */
@@ -66,7 +64,7 @@ void ext2_delete_inode (struct inode * inode)
 		goto no_delete;
 	EXT2_I(inode)->i_dtime	= get_seconds();
 	mark_inode_dirty(inode);
-	ext2_update_inode(inode, inode_needs_sync(inode));
+	ext2_write_inode(inode, inode_needs_sync(inode));
 
 	inode->i_size = 0;
 	if (inode->i_blocks)
@@ -1337,7 +1335,7 @@ bad_inode:
 	return ERR_PTR(ret);
 }
 
-static int ext2_update_inode(struct inode * inode, int do_sync)
+int ext2_write_inode(struct inode *inode, int do_sync)
 {
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -1442,11 +1440,6 @@ static int ext2_update_inode(struct inode * inode, int do_sync)
 	return err;
 }
 
-int ext2_write_inode(struct inode *inode, int wait)
-{
-	return ext2_update_inode(inode, wait);
-}
-
 int ext2_sync_inode(struct inode *inode)
 {
 	struct writeback_control wbc = {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 5c4afe652245..458999638c3d 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -42,6 +42,7 @@ static void ext2_sync_super(struct super_block *sb,
 			    struct ext2_super_block *es);
 static int ext2_remount (struct super_block * sb, int * flags, char * data);
 static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf);
+static int ext2_sync_fs(struct super_block *sb, int wait);
 
 void ext2_error (struct super_block * sb, const char * function,
 		 const char * fmt, ...)
@@ -114,6 +115,11 @@ static void ext2_put_super (struct super_block * sb)
 	int i;
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 
+	lock_kernel();
+
+	if (sb->s_dirt)
+		ext2_write_super(sb);
+
 	ext2_xattr_put_super(sb);
 	if (!(sb->s_flags & MS_RDONLY)) {
 		struct ext2_super_block *es = sbi->s_es;
@@ -135,7 +141,7 @@ static void ext2_put_super (struct super_block * sb)
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
 
-	return;
+	unlock_kernel();
 }
 
 static struct kmem_cache * ext2_inode_cachep;
@@ -304,6 +310,7 @@ static const struct super_operations ext2_sops = {
 	.delete_inode	= ext2_delete_inode,
 	.put_super	= ext2_put_super,
 	.write_super	= ext2_write_super,
+	.sync_fs	= ext2_sync_fs,
 	.statfs		= ext2_statfs,
 	.remount_fs	= ext2_remount,
 	.clear_inode	= ext2_clear_inode,
@@ -1093,6 +1100,7 @@ failed_mount:
 	brelse(bh);
 failed_sbi:
 	sb->s_fs_info = NULL;
+	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
 	return ret;
 }
@@ -1126,25 +1134,36 @@ static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es)
  * set s_state to EXT2_VALID_FS after some corrections.
  */
 
-void ext2_write_super (struct super_block * sb)
+static int ext2_sync_fs(struct super_block *sb, int wait)
 {
-	struct ext2_super_block * es;
-	lock_kernel();
-	if (!(sb->s_flags & MS_RDONLY)) {
-		es = EXT2_SB(sb)->s_es;
+	struct ext2_super_block *es = EXT2_SB(sb)->s_es;
 
-		if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) {
-			ext2_debug ("setting valid to 0\n");
-			es->s_state &= cpu_to_le16(~EXT2_VALID_FS);
-			es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
-			es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
-			es->s_mtime = cpu_to_le32(get_seconds());
-			ext2_sync_super(sb, es);
-		} else
-			ext2_commit_super (sb, es);
+	lock_kernel();
+	if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) {
+		ext2_debug("setting valid to 0\n");
+		es->s_state &= cpu_to_le16(~EXT2_VALID_FS);
+		es->s_free_blocks_count =
+			cpu_to_le32(ext2_count_free_blocks(sb));
+		es->s_free_inodes_count =
+			cpu_to_le32(ext2_count_free_inodes(sb));
+		es->s_mtime = cpu_to_le32(get_seconds());
+		ext2_sync_super(sb, es);
+	} else {
+		ext2_commit_super(sb, es);
 	}
 	sb->s_dirt = 0;
 	unlock_kernel();
+
+	return 0;
+}
+
+
+void ext2_write_super(struct super_block *sb)
+{
+	if (!(sb->s_flags & MS_RDONLY))
+		ext2_sync_fs(sb, 1);
+	else
+		sb->s_dirt = 0;
 }
 
 static int ext2_remount (struct super_block * sb, int * flags, char * data)
@@ -1156,6 +1175,8 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	unsigned long old_sb_flags;
 	int err;
 
+	lock_kernel();
+
 	/* Store the old options */
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;
@@ -1191,12 +1212,16 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 		sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;
 		sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP;
 	}
-	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
+	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
+		unlock_kernel();
 		return 0;
+	}
 	if (*flags & MS_RDONLY) {
 		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
-		    !(sbi->s_mount_state & EXT2_VALID_FS))
+		    !(sbi->s_mount_state & EXT2_VALID_FS)) {
+			unlock_kernel();
 			return 0;
+		}
 		/*
 		 * OK, we are remounting a valid rw partition rdonly, so set
 		 * the rdonly flag and then mark the partition as valid again.
@@ -1223,12 +1248,14 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 			sb->s_flags &= ~MS_RDONLY;
 	}
 	ext2_sync_super(sb, es);
+	unlock_kernel();
 	return 0;
 restore_opts:
 	sbi->s_mount_opt = old_opts.s_mount_opt;
 	sbi->s_resuid = old_opts.s_resuid;
 	sbi->s_resgid = old_opts.s_resgid;
 	sb->s_flags = old_sb_flags;
+	unlock_kernel();
 	return err;
 }
 
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 225202db8974..27967f92e820 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -649,7 +649,7 @@ do_more:
 		count = overflow;
 		goto do_more;
 	}
-	sb->s_dirt = 1;
+
 error_return:
 	brelse(bitmap_bh);
 	ext3_std_error(sb, err);
@@ -1708,7 +1708,6 @@ allocated:
 	if (!fatal)
 		fatal = err;
 
-	sb->s_dirt = 1;
 	if (fatal)
 		goto out;
 
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index dd13d60d524b..b39991285136 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -181,7 +181,7 @@ void ext3_free_inode (handle_t *handle, struct inode * inode)
 	err = ext3_journal_dirty_metadata(handle, bitmap_bh);
 	if (!fatal)
 		fatal = err;
-	sb->s_dirt = 1;
+
 error_return:
 	brelse(bitmap_bh);
 	ext3_std_error(sb, fatal);
@@ -537,7 +537,6 @@ got:
 	percpu_counter_dec(&sbi->s_freeinodes_counter);
 	if (S_ISDIR(mode))
 		percpu_counter_inc(&sbi->s_dirs_counter);
-	sb->s_dirt = 1;
 
 	inode->i_uid = current_fsuid();
 	if (test_opt (sb, GRPID))
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index fcfa24361856..b0248c6d5d4c 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -2960,7 +2960,6 @@ static int ext3_do_update_inode(handle_t *handle,
 				ext3_update_dynamic_rev(sb);
 				EXT3_SET_RO_COMPAT_FEATURE(sb,
 					EXT3_FEATURE_RO_COMPAT_LARGE_FILE);
-				sb->s_dirt = 1;
 				handle->h_sync = 1;
 				err = ext3_journal_dirty_metadata(handle,
 						EXT3_SB(sb)->s_sbh);
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index 78fdf3836370..8a0b26340b54 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -934,7 +934,6 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 			   EXT3_INODES_PER_GROUP(sb));
 
 	ext3_journal_dirty_metadata(handle, sbi->s_sbh);
-	sb->s_dirt = 1;
 
 exit_journal:
 	unlock_super(sb);
@@ -1066,7 +1065,6 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 	}
 	es->s_blocks_count = cpu_to_le32(o_blocks_count + add);
 	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
-	sb->s_dirt = 1;
 	unlock_super(sb);
 	ext3_debug("freeing blocks %lu through "E3FSBLK"\n", o_blocks_count,
 		   o_blocks_count + add);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 599dbfe504c3..26aa64dee6aa 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -67,7 +67,6 @@ static const char *ext3_decode_error(struct super_block * sb, int errno,
 static int ext3_remount (struct super_block * sb, int * flags, char * data);
 static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf);
 static int ext3_unfreeze(struct super_block *sb);
-static void ext3_write_super (struct super_block * sb);
 static int ext3_freeze(struct super_block *sb);
 
 /*
@@ -399,6 +398,8 @@ static void ext3_put_super (struct super_block * sb)
 	struct ext3_super_block *es = sbi->s_es;
 	int i, err;
 
+	lock_kernel();
+
 	ext3_xattr_put_super(sb);
 	err = journal_destroy(sbi->s_journal);
 	sbi->s_journal = NULL;
@@ -447,7 +448,8 @@ static void ext3_put_super (struct super_block * sb)
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
-	return;
+
+	unlock_kernel();
 }
 
 static struct kmem_cache *ext3_inode_cachep;
@@ -761,7 +763,6 @@ static const struct super_operations ext3_sops = {
 	.dirty_inode	= ext3_dirty_inode,
 	.delete_inode	= ext3_delete_inode,
 	.put_super	= ext3_put_super,
-	.write_super	= ext3_write_super,
 	.sync_fs	= ext3_sync_fs,
 	.freeze_fs	= ext3_freeze,
 	.unfreeze_fs	= ext3_unfreeze,
@@ -1696,7 +1697,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
-	hblock = bdev_hardsect_size(sb->s_bdev);
+	hblock = bdev_logical_block_size(sb->s_bdev);
 	if (sb->s_blocksize != blocksize) {
 		/*
 		 * Make sure the blocksize for the filesystem is larger
@@ -1785,7 +1786,6 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 #else
 		es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
 #endif
-		sb->s_dirt = 1;
 	}
 
 	if (sbi->s_blocks_per_group > blocksize * 8) {
@@ -2021,6 +2021,7 @@ failed_mount:
 	brelse(bh);
 out_fail:
 	sb->s_fs_info = NULL;
+	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
 	lock_kernel();
 	return ret;
@@ -2119,7 +2120,7 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb,
 	}
 
 	blocksize = sb->s_blocksize;
-	hblock = bdev_hardsect_size(bdev);
+	hblock = bdev_logical_block_size(bdev);
 	if (blocksize < hblock) {
 		printk(KERN_ERR
 			"EXT3-fs: blocksize too small for journal device.\n");
@@ -2264,7 +2265,6 @@ static int ext3_load_journal(struct super_block *sb,
 	if (journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
 		es->s_journal_dev = cpu_to_le32(journal_devnum);
-		sb->s_dirt = 1;
 
 		/* Make sure we flush the recovery flag to disk. */
 		ext3_commit_super(sb, es, 1);
@@ -2307,7 +2307,6 @@ static int ext3_create_journal(struct super_block * sb,
 	EXT3_SET_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL);
 
 	es->s_journal_inum = cpu_to_le32(journal_inum);
-	sb->s_dirt = 1;
 
 	/* Make sure we flush the recovery flag to disk. */
 	ext3_commit_super(sb, es, 1);
@@ -2353,7 +2352,6 @@ static void ext3_mark_recovery_complete(struct super_block * sb,
 	if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) &&
 	    sb->s_flags & MS_RDONLY) {
 		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
-		sb->s_dirt = 0;
 		ext3_commit_super(sb, es, 1);
 	}
 	unlock_super(sb);
@@ -2412,29 +2410,14 @@ int ext3_force_commit(struct super_block *sb)
 		return 0;
 
 	journal = EXT3_SB(sb)->s_journal;
-	sb->s_dirt = 0;
 	ret = ext3_journal_force_commit(journal);
 	return ret;
 }
 
-/*
- * Ext3 always journals updates to the superblock itself, so we don't
- * have to propagate any other updates to the superblock on disk at this
- * point.  (We can probably nuke this function altogether, and remove
- * any mention to sb->s_dirt in all of fs/ext3; eventual cleanup...)
- */
-static void ext3_write_super (struct super_block * sb)
-{
-	if (mutex_trylock(&sb->s_lock) != 0)
-		BUG();
-	sb->s_dirt = 0;
-}
-
 static int ext3_sync_fs(struct super_block *sb, int wait)
 {
 	tid_t target;
 
-	sb->s_dirt = 0;
 	if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) {
 		if (wait)
 			log_wait_commit(EXT3_SB(sb)->s_journal, target);
@@ -2450,7 +2433,6 @@ static int ext3_freeze(struct super_block *sb)
 {
 	int error = 0;
 	journal_t *journal;
-	sb->s_dirt = 0;
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		journal = EXT3_SB(sb)->s_journal;
@@ -2508,7 +2490,10 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
 	int i;
 #endif
 
+	lock_kernel();
+
 	/* Store the original options */
+	lock_super(sb);
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;
 	old_opts.s_resuid = sbi->s_resuid;
@@ -2616,6 +2601,8 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
 		    old_opts.s_qf_names[i] != sbi->s_qf_names[i])
 			kfree(old_opts.s_qf_names[i]);
 #endif
+	unlock_super(sb);
+	unlock_kernel();
 	return 0;
 restore_opts:
 	sb->s_flags = old_sb_flags;
@@ -2632,6 +2619,8 @@ restore_opts:
 		sbi->s_qf_names[i] = old_opts.s_qf_names[i];
 	}
 #endif
+	unlock_super(sb);
+	unlock_kernel();
 	return err;
 }
 
diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c
index 83b7be849bd5..545e37c4b91e 100644
--- a/fs/ext3/xattr.c
+++ b/fs/ext3/xattr.c
@@ -463,7 +463,6 @@ static void ext3_xattr_update_super_block(handle_t *handle,
 
 	if (ext3_journal_get_write_access(handle, EXT3_SB(sb)->s_sbh) == 0) {
 		EXT3_SET_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_EXT_ATTR);
-		sb->s_dirt = 1;
 		ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
 	}
 }
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index a8ff003a00f7..8a34710ecf40 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -5,8 +5,8 @@
 obj-$(CONFIG_EXT4_FS) += ext4.o
 
 ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
-		   ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
-		   ext4_jbd2.o migrate.o mballoc.o
+		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
+		ext4_jbd2.o migrate.o mballoc.o block_validity.o
 
 ext4-$(CONFIG_EXT4_FS_XATTR)		+= xattr.o xattr_user.o xattr_trusted.o
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 53c72ad85877..e2126d70dff5 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -19,7 +19,6 @@
 #include <linux/buffer_head.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
-#include "group.h"
 #include "mballoc.h"
 
 /*
@@ -88,6 +87,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 ext4_group_t block_group, struct ext4_group_desc *gdp)
 {
 	int bit, bit_max;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	unsigned free_blocks, group_blocks;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
@@ -123,7 +123,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		bit_max += ext4_bg_num_gdb(sb, block_group);
 	}
 
-	if (block_group == sbi->s_groups_count - 1) {
+	if (block_group == ngroups - 1) {
 		/*
 		 * Even though mke2fs always initialize first and last group
 		 * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
@@ -131,7 +131,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 */
 		group_blocks = ext4_blocks_count(sbi->s_es) -
 			le32_to_cpu(sbi->s_es->s_first_data_block) -
-			(EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count - 1));
+			(EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1));
 	} else {
 		group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
 	}
@@ -205,18 +205,18 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 {
 	unsigned int group_desc;
 	unsigned int offset;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (block_group >= sbi->s_groups_count) {
+	if (block_group >= ngroups) {
 		ext4_error(sb, "ext4_get_group_desc",
 			   "block_group >= groups_count - "
 			   "block_group = %u, groups_count = %u",
-			   block_group, sbi->s_groups_count);
+			   block_group, ngroups);
 
 		return NULL;
 	}
-	smp_rmb();
 
 	group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
 	offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
@@ -326,16 +326,16 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 		unlock_buffer(bh);
 		return bh;
 	}
-	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
-		spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
 		return bh;
 	}
-	spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	ext4_unlock_group(sb, block_group);
 	if (buffer_uptodate(bh)) {
 		/*
 		 * if not uninit if bh is uptodate,
@@ -451,7 +451,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
 	down_write(&grp->alloc_sem);
 	for (i = 0, blocks_freed = 0; i < count; i++) {
 		BUFFER_TRACE(bitmap_bh, "clear bit");
-		if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
+		if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
 						bit + i, bitmap_bh->b_data)) {
 			ext4_error(sb, __func__,
 				   "bit already cleared for block %llu",
@@ -461,11 +461,11 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
 			blocks_freed++;
 		}
 	}
-	spin_lock(sb_bgl_lock(sbi, block_group));
+	ext4_lock_group(sb, block_group);
 	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
 	ext4_free_blks_set(sb, desc, blk_free_count);
 	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
-	spin_unlock(sb_bgl_lock(sbi, block_group));
+	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
 
 	if (sbi->s_log_groups_per_flex) {
@@ -665,7 +665,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 	ext4_fsblk_t desc_count;
 	struct ext4_group_desc *gdp;
 	ext4_group_t i;
-	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 #ifdef EXT4FS_DEBUG
 	struct ext4_super_block *es;
 	ext4_fsblk_t bitmap_count;
@@ -677,7 +677,6 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 	bitmap_count = 0;
 	gdp = NULL;
 
-	smp_rmb();
 	for (i = 0; i < ngroups; i++) {
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
@@ -700,7 +699,6 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 	return bitmap_count;
 #else
 	desc_count = 0;
-	smp_rmb();
 	for (i = 0; i < ngroups; i++) {
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
new file mode 100644
index 000000000000..50784ef07563
--- /dev/null
+++ b/fs/ext4/block_validity.c
@@ -0,0 +1,244 @@
+/*
+ *  linux/fs/ext4/block_validity.c
+ *
+ * Copyright (C) 2009
+ * Theodore Ts'o (tytso@mit.edu)
+ *
+ * Track which blocks in the filesystem are metadata blocks that
+ * should never be used as data blocks by files or directories.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/version.h>
+#include <linux/blkdev.h>
+#include <linux/mutex.h>
+#include "ext4.h"
+
+struct ext4_system_zone {
+	struct rb_node	node;
+	ext4_fsblk_t	start_blk;
+	unsigned int	count;
+};
+
+static struct kmem_cache *ext4_system_zone_cachep;
+
+int __init init_ext4_system_zone(void)
+{
+	ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone,
+					     SLAB_RECLAIM_ACCOUNT);
+	if (ext4_system_zone_cachep == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void exit_ext4_system_zone(void)
+{
+	kmem_cache_destroy(ext4_system_zone_cachep);
+}
+
+static inline int can_merge(struct ext4_system_zone *entry1,
+		     struct ext4_system_zone *entry2)
+{
+	if ((entry1->start_blk + entry1->count) == entry2->start_blk)
+		return 1;
+	return 0;
+}
+
+/*
+ * Mark a range of blocks as belonging to the "system zone" --- that
+ * is, filesystem metadata blocks which should never be used by
+ * inodes.
+ */
+static int add_system_zone(struct ext4_sb_info *sbi,
+			   ext4_fsblk_t start_blk,
+			   unsigned int count)
+{
+	struct ext4_system_zone *new_entry = NULL, *entry;
+	struct rb_node **n = &sbi->system_blks.rb_node, *node;
+	struct rb_node *parent = NULL, *new_node = NULL;
+
+	while (*n) {
+		parent = *n;
+		entry = rb_entry(parent, struct ext4_system_zone, node);
+		if (start_blk < entry->start_blk)
+			n = &(*n)->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = &(*n)->rb_right;
+		else {
+			if (start_blk + count > (entry->start_blk + 
+						 entry->count))
+				entry->count = (start_blk + count - 
+						entry->start_blk);
+			new_node = *n;
+			new_entry = rb_entry(new_node, struct ext4_system_zone,
+					     node);
+			break;
+		}
+	}
+
+	if (!new_entry) {
+		new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
+					     GFP_KERNEL);
+		if (!new_entry)
+			return -ENOMEM;
+		new_entry->start_blk = start_blk;
+		new_entry->count = count;
+		new_node = &new_entry->node;
+
+		rb_link_node(new_node, parent, n);
+		rb_insert_color(new_node, &sbi->system_blks);
+	}
+
+	/* Can we merge to the left? */
+	node = rb_prev(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		if (can_merge(entry, new_entry)) {
+			new_entry->start_blk = entry->start_blk;
+			new_entry->count += entry->count;
+			rb_erase(node, &sbi->system_blks);
+			kmem_cache_free(ext4_system_zone_cachep, entry);
+		}
+	}
+
+	/* Can we merge to the right? */
+	node = rb_next(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		if (can_merge(new_entry, entry)) {
+			new_entry->count += entry->count;
+			rb_erase(node, &sbi->system_blks);
+			kmem_cache_free(ext4_system_zone_cachep, entry);
+		}
+	}
+	return 0;
+}
+
+static void debug_print_tree(struct ext4_sb_info *sbi)
+{
+	struct rb_node *node;
+	struct ext4_system_zone *entry;
+	int first = 1;
+
+	printk(KERN_INFO "System zones: ");
+	node = rb_first(&sbi->system_blks);
+	while (node) {
+		entry = rb_entry(node, struct ext4_system_zone, node);
+		printk("%s%llu-%llu", first ? "" : ", ",
+		       entry->start_blk, entry->start_blk + entry->count - 1);
+		first = 0;
+		node = rb_next(node);
+	}
+	printk("\n");
+}
+
+int ext4_setup_system_zone(struct super_block *sb)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp;
+	ext4_group_t i;
+	int flex_size = ext4_flex_bg_size(sbi);
+	int ret;
+
+	if (!test_opt(sb, BLOCK_VALIDITY)) {
+		if (EXT4_SB(sb)->system_blks.rb_node)
+			ext4_release_system_zone(sb);
+		return 0;
+	}
+	if (EXT4_SB(sb)->system_blks.rb_node)
+		return 0;
+
+	for (i=0; i < ngroups; i++) {
+		if (ext4_bg_has_super(sb, i) &&
+		    ((i < 5) || ((i % flex_size) == 0)))
+			add_system_zone(sbi, ext4_group_first_block_no(sb, i),
+					sbi->s_gdb_count + 1);
+		gdp = ext4_get_group_desc(sb, i, NULL);
+		ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1);
+		if (ret)
+			return ret;
+		ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1);
+		if (ret)
+			return ret;
+		ret = add_system_zone(sbi, ext4_inode_table(sb, gdp),
+				sbi->s_itb_per_group);
+		if (ret)
+			return ret;
+	}
+
+	if (test_opt(sb, DEBUG))
+		debug_print_tree(EXT4_SB(sb));
+	return 0;
+}
+
+/* Called when the filesystem is unmounted */
+void ext4_release_system_zone(struct super_block *sb)
+{
+	struct rb_node	*n = EXT4_SB(sb)->system_blks.rb_node;
+	struct rb_node	*parent;
+	struct ext4_system_zone	*entry;
+
+	while (n) {
+		/* Do the node's children first */
+		if (n->rb_left) {
+			n = n->rb_left;
+			continue;
+		}
+		if (n->rb_right) {
+			n = n->rb_right;
+			continue;
+		}
+		/*
+		 * The node has no children; free it, and then zero
+		 * out parent's link to it.  Finally go to the
+		 * beginning of the loop and try to free the parent
+		 * node.
+		 */
+		parent = rb_parent(n);
+		entry = rb_entry(n, struct ext4_system_zone, node);
+		kmem_cache_free(ext4_system_zone_cachep, entry);
+		if (!parent)
+			EXT4_SB(sb)->system_blks.rb_node = NULL;
+		else if (parent->rb_left == n)
+			parent->rb_left = NULL;
+		else if (parent->rb_right == n)
+			parent->rb_right = NULL;
+		n = parent;
+	}
+	EXT4_SB(sb)->system_blks.rb_node = NULL;
+}
+
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with filesystem metadata blocks.
+ */
+int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
+			  unsigned int count)
+{
+	struct ext4_system_zone *entry;
+	struct rb_node *n = sbi->system_blks.rb_node;
+
+	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+	    (start_blk + count > ext4_blocks_count(sbi->s_es)))
+		return 0;
+	while (n) {
+		entry = rb_entry(n, struct ext4_system_zone, node);
+		if (start_blk + count - 1 < entry->start_blk)
+			n = n->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = n->rb_right;
+		else
+			return 0;
+	}
+	return 1;
+}
+
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index b64789929a65..9dc93168e262 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -131,8 +131,7 @@ static int ext4_readdir(struct file *filp,
 		struct buffer_head *bh = NULL;
 
 		map_bh.b_state = 0;
-		err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh,
-						0, 0, 0);
+		err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0);
 		if (err > 0) {
 			pgoff_t index = map_bh.b_blocknr >>
 					(PAGE_CACHE_SHIFT - inode->i_blkbits);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index d0f15ef56de1..cc7d5edc38c9 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -21,7 +21,14 @@
 #include <linux/magic.h>
 #include <linux/jbd2.h>
 #include <linux/quota.h>
-#include "ext4_i.h"
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <linux/seqlock.h>
+#include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
 
 /*
  * The fourth extended filesystem constants/structures
@@ -46,6 +53,19 @@
 #define ext4_debug(f, a...)	do {} while (0)
 #endif
 
+/* data type for block offset of block group */
+typedef int ext4_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long long ext4_fsblk_t;
+
+/* data type for file logical block number */
+typedef __u32 ext4_lblk_t;
+
+/* data type for block group number */
+typedef unsigned int ext4_group_t;
+
+
 /* prefer goal again. length */
 #define EXT4_MB_HINT_MERGE		1
 /* blocks already reserved */
@@ -179,9 +199,6 @@ struct flex_groups {
 #define EXT4_BG_BLOCK_UNINIT	0x0002 /* Block bitmap not in use */
 #define EXT4_BG_INODE_ZEROED	0x0004 /* On-disk itable initialized to zero */
 
-#ifdef __KERNEL__
-#include "ext4_sb.h"
-#endif
 /*
  * Macro-instructions used to manage group descriptors
  */
@@ -297,10 +314,23 @@ struct ext4_new_group_data {
 };
 
 /*
- * Following is used by preallocation code to tell get_blocks() that we
- * want uninitialzed extents.
+ * Flags used by ext4_get_blocks()
  */
-#define EXT4_CREATE_UNINITIALIZED_EXT		2
+	/* Allocate any needed blocks and/or convert an unitialized
+	   extent to be an initialized ext4 */
+#define EXT4_GET_BLOCKS_CREATE			0x0001
+	/* Request the creation of an unitialized extent */
+#define EXT4_GET_BLOCKS_UNINIT_EXT		0x0002
+#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT	(EXT4_GET_BLOCKS_UNINIT_EXT|\
+						 EXT4_GET_BLOCKS_CREATE)
+	/* Caller is from the delayed allocation writeout path,
+	   so set the magic i_delalloc_reserve_flag after taking the 
+	   inode allocation semaphore for */
+#define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
+	/* Call ext4_da_update_reserve_space() after successfully 
+	   allocating the blocks */
+#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE	0x0008
+
 
 /*
  * ioctl commands
@@ -515,6 +545,110 @@ do {									       \
 
 #endif /* defined(__KERNEL__) || defined(__linux__) */
 
+/*
+ * storage for cached extent
+ */
+struct ext4_ext_cache {
+	ext4_fsblk_t	ec_start;
+	ext4_lblk_t	ec_block;
+	__u32		ec_len; /* must be 32bit to return holes */
+	__u32		ec_type;
+};
+
+/*
+ * fourth extended file system inode data in memory
+ */
+struct ext4_inode_info {
+	__le32	i_data[15];	/* unconverted */
+	__u32	i_flags;
+	ext4_fsblk_t	i_file_acl;
+	__u32	i_dtime;
+
+	/*
+	 * i_block_group is the number of the block group which contains
+	 * this file's inode.  Constant across the lifetime of the inode,
+	 * it is ued for making block allocation decisions - we try to
+	 * place a file's data blocks near its inode block, and new inodes
+	 * near to their parent directory's inode.
+	 */
+	ext4_group_t	i_block_group;
+	__u32	i_state;		/* Dynamic state flags for ext4 */
+
+	ext4_lblk_t		i_dir_start_lookup;
+#ifdef CONFIG_EXT4_FS_XATTR
+	/*
+	 * Extended attributes can be read independently of the main file
+	 * data. Taking i_mutex even when reading would cause contention
+	 * between readers of EAs and writers of regular file data, so
+	 * instead we synchronize on xattr_sem when reading or changing
+	 * EAs.
+	 */
+	struct rw_semaphore xattr_sem;
+#endif
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+	struct posix_acl	*i_acl;
+	struct posix_acl	*i_default_acl;
+#endif
+
+	struct list_head i_orphan;	/* unlinked but open inodes */
+
+	/*
+	 * i_disksize keeps track of what the inode size is ON DISK, not
+	 * in memory.  During truncate, i_size is set to the new size by
+	 * the VFS prior to calling ext4_truncate(), but the filesystem won't
+	 * set i_disksize to 0 until the truncate is actually under way.
+	 *
+	 * The intent is that i_disksize always represents the blocks which
+	 * are used by this file.  This allows recovery to restart truncate
+	 * on orphans if we crash during truncate.  We actually write i_disksize
+	 * into the on-disk inode when writing inodes out, instead of i_size.
+	 *
+	 * The only time when i_disksize and i_size may be different is when
+	 * a truncate is in progress.  The only things which change i_disksize
+	 * are ext4_get_block (growth) and ext4_truncate (shrinkth).
+	 */
+	loff_t	i_disksize;
+
+	/*
+	 * i_data_sem is for serialising ext4_truncate() against
+	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
+	 * data tree are chopped off during truncate. We can't do that in
+	 * ext4 because whenever we perform intermediate commits during
+	 * truncate, the inode and all the metadata blocks *must* be in a
+	 * consistent state which allows truncation of the orphans to restart
+	 * during recovery.  Hence we must fix the get_block-vs-truncate race
+	 * by other means, so we have i_data_sem.
+	 */
+	struct rw_semaphore i_data_sem;
+	struct inode vfs_inode;
+	struct jbd2_inode jinode;
+
+	struct ext4_ext_cache i_cached_extent;
+	/*
+	 * File creation time. Its function is same as that of
+	 * struct timespec i_{a,c,m}time in the generic inode.
+	 */
+	struct timespec i_crtime;
+
+	/* mballoc */
+	struct list_head i_prealloc_list;
+	spinlock_t i_prealloc_lock;
+
+	/* ialloc */
+	ext4_group_t	i_last_alloc_group;
+
+	/* allocation reservation info for delalloc */
+	unsigned int i_reserved_data_blocks;
+	unsigned int i_reserved_meta_blocks;
+	unsigned int i_allocated_meta_blocks;
+	unsigned short i_delalloc_reserved_flag;
+
+	/* on-disk additional length */
+	__u16 i_extra_isize;
+
+	spinlock_t i_block_reservation_lock;
+};
+
 /*
  * File system states
  */
@@ -560,6 +694,7 @@ do {									       \
 #define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
+#define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
 
 /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
@@ -689,6 +824,137 @@ struct ext4_super_block {
 };
 
 #ifdef __KERNEL__
+/*
+ * fourth extended-fs super-block data in memory
+ */
+struct ext4_sb_info {
+	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
+	unsigned long s_inodes_per_block;/* Number of inodes per block */
+	unsigned long s_blocks_per_group;/* Number of blocks in a group */
+	unsigned long s_inodes_per_group;/* Number of inodes in a group */
+	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
+	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
+	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
+	ext4_group_t s_groups_count;	/* Number of groups in the fs */
+	unsigned long s_overhead_last;  /* Last calculated overhead */
+	unsigned long s_blocks_last;    /* Last seen block count */
+	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
+	struct buffer_head * s_sbh;	/* Buffer containing the super block */
+	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head **s_group_desc;
+	unsigned long  s_mount_opt;
+	ext4_fsblk_t s_sb_block;
+	uid_t s_resuid;
+	gid_t s_resgid;
+	unsigned short s_mount_state;
+	unsigned short s_pad;
+	int s_addr_per_block_bits;
+	int s_desc_per_block_bits;
+	int s_inode_size;
+	int s_first_ino;
+	unsigned int s_inode_readahead_blks;
+	spinlock_t s_next_gen_lock;
+	u32 s_next_generation;
+	u32 s_hash_seed[4];
+	int s_def_hash_version;
+	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
+	struct percpu_counter s_freeblocks_counter;
+	struct percpu_counter s_freeinodes_counter;
+	struct percpu_counter s_dirs_counter;
+	struct percpu_counter s_dirtyblocks_counter;
+	struct blockgroup_lock *s_blockgroup_lock;
+	struct proc_dir_entry *s_proc;
+	struct kobject s_kobj;
+	struct completion s_kobj_unregister;
+
+	/* Journaling */
+	struct inode *s_journal_inode;
+	struct journal_s *s_journal;
+	struct list_head s_orphan;
+	struct mutex s_orphan_lock;
+	struct mutex s_resize_lock;
+	unsigned long s_commit_interval;
+	u32 s_max_batch_time;
+	u32 s_min_batch_time;
+	struct block_device *journal_bdev;
+#ifdef CONFIG_JBD2_DEBUG
+	struct timer_list turn_ro_timer;	/* For turning read-only (crash simulation) */
+	wait_queue_head_t ro_wait_queue;	/* For people waiting for the fs to go read-only */
+#endif
+#ifdef CONFIG_QUOTA
+	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
+	int s_jquota_fmt;			/* Format of quota to use */
+#endif
+	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
+	struct rb_root system_blks;
+
+#ifdef EXTENTS_STATS
+	/* ext4 extents stats */
+	unsigned long s_ext_min;
+	unsigned long s_ext_max;
+	unsigned long s_depth_max;
+	spinlock_t s_ext_stats_lock;
+	unsigned long s_ext_blocks;
+	unsigned long s_ext_extents;
+#endif
+
+	/* for buddy allocator */
+	struct ext4_group_info ***s_group_info;
+	struct inode *s_buddy_cache;
+	long s_blocks_reserved;
+	spinlock_t s_reserve_lock;
+	spinlock_t s_md_lock;
+	tid_t s_last_transaction;
+	unsigned short *s_mb_offsets;
+	unsigned int *s_mb_maxs;
+
+	/* tunables */
+	unsigned long s_stripe;
+	unsigned int s_mb_stream_request;
+	unsigned int s_mb_max_to_scan;
+	unsigned int s_mb_min_to_scan;
+	unsigned int s_mb_stats;
+	unsigned int s_mb_order2_reqs;
+	unsigned int s_mb_group_prealloc;
+	/* where last allocation was done - for stream allocation */
+	unsigned long s_mb_last_group;
+	unsigned long s_mb_last_start;
+
+	/* history to debug policy */
+	struct ext4_mb_history *s_mb_history;
+	int s_mb_history_cur;
+	int s_mb_history_max;
+	int s_mb_history_num;
+	spinlock_t s_mb_history_lock;
+	int s_mb_history_filter;
+
+	/* stats for buddy allocator */
+	spinlock_t s_mb_pa_lock;
+	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
+	atomic_t s_bal_success;	/* we found long enough chunks */
+	atomic_t s_bal_allocated;	/* in blocks */
+	atomic_t s_bal_ex_scanned;	/* total extents scanned */
+	atomic_t s_bal_goals;	/* goal hits */
+	atomic_t s_bal_breaks;	/* too long searches */
+	atomic_t s_bal_2orders;	/* 2^order hits */
+	spinlock_t s_bal_lock;
+	unsigned long s_mb_buddies_generated;
+	unsigned long long s_mb_generation_time;
+	atomic_t s_mb_lost_chunks;
+	atomic_t s_mb_preallocated;
+	atomic_t s_mb_discarded;
+
+	/* locality groups */
+	struct ext4_locality_group *s_locality_groups;
+
+	/* for write statistics */
+	unsigned long s_sectors_written_start;
+	u64 s_kbytes_written;
+
+	unsigned int s_log_groups_per_flex;
+	struct flex_groups *s_flex_groups;
+};
+
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
@@ -704,7 +970,6 @@ static inline struct timespec ext4_current_time(struct inode *inode)
 		current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
 }
 
-
 static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 {
 	return ino == EXT4_ROOT_INO ||
@@ -1014,6 +1279,14 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 						    ext4_group_t block_group,
 						    struct buffer_head ** bh);
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
+struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
+				      ext4_group_t block_group);
+extern unsigned ext4_init_block_bitmap(struct super_block *sb,
+				       struct buffer_head *bh,
+				       ext4_group_t group,
+				       struct ext4_group_desc *desc);
+#define ext4_free_blocks_after_init(sb, group, desc)			\
+		ext4_init_block_bitmap(sb, NULL, group, desc)
 
 /* dir.c */
 extern int ext4_check_dir_entry(const char *, struct inode *,
@@ -1038,6 +1311,11 @@ extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
 extern unsigned long ext4_count_free_inodes(struct super_block *);
 extern unsigned long ext4_count_dirs(struct super_block *);
 extern void ext4_check_inodes_bitmap(struct super_block *);
+extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
+				       struct buffer_head *bh,
+				       ext4_group_t group,
+				       struct ext4_group_desc *desc);
+extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
 
 /* mballoc.c */
 extern long ext4_mb_stats;
@@ -1123,6 +1401,8 @@ extern void ext4_abort(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
 extern void ext4_warning(struct super_block *, const char *, const char *, ...)
 	__attribute__ ((format (printf, 3, 4)));
+extern void ext4_msg(struct super_block *, const char *, const char *, ...)
+	__attribute__ ((format (printf, 3, 4)));
 extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
 				const char *, const char *, ...)
 	__attribute__ ((format (printf, 4, 5)));
@@ -1161,6 +1441,10 @@ extern void ext4_used_dirs_set(struct super_block *sb,
 				struct ext4_group_desc *bg, __u32 count);
 extern void ext4_itable_unused_set(struct super_block *sb,
 				   struct ext4_group_desc *bg, __u32 count);
+extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
+				   struct ext4_group_desc *gdp);
+extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
+				       struct ext4_group_desc *gdp);
 
 static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
 {
@@ -1228,6 +1512,18 @@ struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
 	 return grp_info[indexv][indexh];
 }
 
+/*
+ * Reading s_groups_count requires using smp_rmb() afterwards.  See
+ * the locking protocol documented in the comments of ext4_group_add()
+ * in resize.c
+ */
+static inline ext4_group_t ext4_get_groups_count(struct super_block *sb)
+{
+	ext4_group_t	ngroups = EXT4_SB(sb)->s_groups_count;
+
+	smp_rmb();
+	return ngroups;
+}
 
 static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi,
 					     ext4_group_t block_group)
@@ -1283,33 +1579,25 @@ struct ext4_group_info {
 };
 
 #define EXT4_GROUP_INFO_NEED_INIT_BIT	0
-#define EXT4_GROUP_INFO_LOCKED_BIT	1
 
 #define EXT4_MB_GRP_NEED_INIT(grp)	\
 	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
 
+static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
+					      ext4_group_t group)
+{
+	return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
+}
+
 static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
 {
-	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
-	bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+	spin_lock(ext4_group_lock_ptr(sb, group));
 }
 
 static inline void ext4_unlock_group(struct super_block *sb,
 					ext4_group_t group)
 {
-	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
-	bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
-}
-
-static inline int ext4_is_group_locked(struct super_block *sb,
-					ext4_group_t group)
-{
-	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
-
-	return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
-						&(grinfo->bb_state));
+	spin_unlock(ext4_group_lock_ptr(sb, group));
 }
 
 /*
@@ -1326,11 +1614,21 @@ extern const struct file_operations ext4_file_operations;
 /* namei.c */
 extern const struct inode_operations ext4_dir_inode_operations;
 extern const struct inode_operations ext4_special_inode_operations;
+extern struct dentry *ext4_get_parent(struct dentry *child);
 
 /* symlink.c */
 extern const struct inode_operations ext4_symlink_inode_operations;
 extern const struct inode_operations ext4_fast_symlink_inode_operations;
 
+/* block_validity */
+extern void ext4_release_system_zone(struct super_block *sb);
+extern int ext4_setup_system_zone(struct super_block *sb);
+extern int __init init_ext4_system_zone(void);
+extern void exit_ext4_system_zone(void);
+extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
+				 ext4_fsblk_t start_blk,
+				 unsigned int count);
+
 /* extents.c */
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
 extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
@@ -1338,17 +1636,15 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
 				       int chunk);
 extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			       ext4_lblk_t iblock, unsigned int max_blocks,
-			       struct buffer_head *bh_result,
-			       int create, int extend_disksize);
+			       struct buffer_head *bh_result, int flags);
 extern void ext4_ext_truncate(struct inode *);
 extern void ext4_ext_init(struct super_block *);
 extern void ext4_ext_release(struct super_block *);
 extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
 			  loff_t len);
-extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode,
-			sector_t block, unsigned int max_blocks,
-			struct buffer_head *bh, int create,
-			int extend_disksize, int flag);
+extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
+			   sector_t block, unsigned int max_blocks,
+			   struct buffer_head *bh, int flags);
 extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len);
 
diff --git a/fs/ext4/ext4_i.h b/fs/ext4/ext4_i.h
deleted file mode 100644
index 4ce2187123aa..000000000000
--- a/fs/ext4/ext4_i.h
+++ /dev/null
@@ -1,140 +0,0 @@
-/*
- *  ext4_i.h
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- *  from
- *
- *  linux/include/linux/minix_fs_i.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _EXT4_I
-#define _EXT4_I
-
-#include <linux/rwsem.h>
-#include <linux/rbtree.h>
-#include <linux/seqlock.h>
-#include <linux/mutex.h>
-
-/* data type for block offset of block group */
-typedef int ext4_grpblk_t;
-
-/* data type for filesystem-wide blocks number */
-typedef unsigned long long ext4_fsblk_t;
-
-/* data type for file logical block number */
-typedef __u32 ext4_lblk_t;
-
-/* data type for block group number */
-typedef unsigned int ext4_group_t;
-
-/*
- * storage for cached extent
- */
-struct ext4_ext_cache {
-	ext4_fsblk_t	ec_start;
-	ext4_lblk_t	ec_block;
-	__u32		ec_len; /* must be 32bit to return holes */
-	__u32		ec_type;
-};
-
-/*
- * fourth extended file system inode data in memory
- */
-struct ext4_inode_info {
-	__le32	i_data[15];	/* unconverted */
-	__u32	i_flags;
-	ext4_fsblk_t	i_file_acl;
-	__u32	i_dtime;
-
-	/*
-	 * i_block_group is the number of the block group which contains
-	 * this file's inode.  Constant across the lifetime of the inode,
-	 * it is ued for making block allocation decisions - we try to
-	 * place a file's data blocks near its inode block, and new inodes
-	 * near to their parent directory's inode.
-	 */
-	ext4_group_t	i_block_group;
-	__u32	i_state;		/* Dynamic state flags for ext4 */
-
-	ext4_lblk_t		i_dir_start_lookup;
-#ifdef CONFIG_EXT4_FS_XATTR
-	/*
-	 * Extended attributes can be read independently of the main file
-	 * data. Taking i_mutex even when reading would cause contention
-	 * between readers of EAs and writers of regular file data, so
-	 * instead we synchronize on xattr_sem when reading or changing
-	 * EAs.
-	 */
-	struct rw_semaphore xattr_sem;
-#endif
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
-	struct posix_acl	*i_acl;
-	struct posix_acl	*i_default_acl;
-#endif
-
-	struct list_head i_orphan;	/* unlinked but open inodes */
-
-	/*
-	 * i_disksize keeps track of what the inode size is ON DISK, not
-	 * in memory.  During truncate, i_size is set to the new size by
-	 * the VFS prior to calling ext4_truncate(), but the filesystem won't
-	 * set i_disksize to 0 until the truncate is actually under way.
-	 *
-	 * The intent is that i_disksize always represents the blocks which
-	 * are used by this file.  This allows recovery to restart truncate
-	 * on orphans if we crash during truncate.  We actually write i_disksize
-	 * into the on-disk inode when writing inodes out, instead of i_size.
-	 *
-	 * The only time when i_disksize and i_size may be different is when
-	 * a truncate is in progress.  The only things which change i_disksize
-	 * are ext4_get_block (growth) and ext4_truncate (shrinkth).
-	 */
-	loff_t	i_disksize;
-
-	/*
-	 * i_data_sem is for serialising ext4_truncate() against
-	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
-	 * data tree are chopped off during truncate. We can't do that in
-	 * ext4 because whenever we perform intermediate commits during
-	 * truncate, the inode and all the metadata blocks *must* be in a
-	 * consistent state which allows truncation of the orphans to restart
-	 * during recovery.  Hence we must fix the get_block-vs-truncate race
-	 * by other means, so we have i_data_sem.
-	 */
-	struct rw_semaphore i_data_sem;
-	struct inode vfs_inode;
-	struct jbd2_inode jinode;
-
-	struct ext4_ext_cache i_cached_extent;
-	/*
-	 * File creation time. Its function is same as that of
-	 * struct timespec i_{a,c,m}time in the generic inode.
-	 */
-	struct timespec i_crtime;
-
-	/* mballoc */
-	struct list_head i_prealloc_list;
-	spinlock_t i_prealloc_lock;
-
-	/* ialloc */
-	ext4_group_t	i_last_alloc_group;
-
-	/* allocation reservation info for delalloc */
-	unsigned int i_reserved_data_blocks;
-	unsigned int i_reserved_meta_blocks;
-	unsigned int i_allocated_meta_blocks;
-	unsigned short i_delalloc_reserved_flag;
-
-	/* on-disk additional length */
-	__u16 i_extra_isize;
-
-	spinlock_t i_block_reservation_lock;
-};
-
-#endif	/* _EXT4_I */
diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h
deleted file mode 100644
index 57b71fefbccf..000000000000
--- a/fs/ext4/ext4_sb.h
+++ /dev/null
@@ -1,161 +0,0 @@
-/*
- *  ext4_sb.h
- *
- * Copyright (C) 1992, 1993, 1994, 1995
- * Remy Card (card@masi.ibp.fr)
- * Laboratoire MASI - Institut Blaise Pascal
- * Universite Pierre et Marie Curie (Paris VI)
- *
- *  from
- *
- *  linux/include/linux/minix_fs_sb.h
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-#ifndef _EXT4_SB
-#define _EXT4_SB
-
-#ifdef __KERNEL__
-#include <linux/timer.h>
-#include <linux/wait.h>
-#include <linux/blockgroup_lock.h>
-#include <linux/percpu_counter.h>
-#endif
-#include <linux/rbtree.h>
-
-/*
- * fourth extended-fs super-block data in memory
- */
-struct ext4_sb_info {
-	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
-	unsigned long s_inodes_per_block;/* Number of inodes per block */
-	unsigned long s_blocks_per_group;/* Number of blocks in a group */
-	unsigned long s_inodes_per_group;/* Number of inodes in a group */
-	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
-	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
-	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
-	ext4_group_t s_groups_count;	/* Number of groups in the fs */
-	unsigned long s_overhead_last;  /* Last calculated overhead */
-	unsigned long s_blocks_last;    /* Last seen block count */
-	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
-	struct buffer_head * s_sbh;	/* Buffer containing the super block */
-	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
-	struct buffer_head **s_group_desc;
-	unsigned long  s_mount_opt;
-	ext4_fsblk_t s_sb_block;
-	uid_t s_resuid;
-	gid_t s_resgid;
-	unsigned short s_mount_state;
-	unsigned short s_pad;
-	int s_addr_per_block_bits;
-	int s_desc_per_block_bits;
-	int s_inode_size;
-	int s_first_ino;
-	unsigned int s_inode_readahead_blks;
-	spinlock_t s_next_gen_lock;
-	u32 s_next_generation;
-	u32 s_hash_seed[4];
-	int s_def_hash_version;
-	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
-	struct percpu_counter s_freeblocks_counter;
-	struct percpu_counter s_freeinodes_counter;
-	struct percpu_counter s_dirs_counter;
-	struct percpu_counter s_dirtyblocks_counter;
-	struct blockgroup_lock *s_blockgroup_lock;
-	struct proc_dir_entry *s_proc;
-	struct kobject s_kobj;
-	struct completion s_kobj_unregister;
-
-	/* Journaling */
-	struct inode *s_journal_inode;
-	struct journal_s *s_journal;
-	struct list_head s_orphan;
-	unsigned long s_commit_interval;
-	u32 s_max_batch_time;
-	u32 s_min_batch_time;
-	struct block_device *journal_bdev;
-#ifdef CONFIG_JBD2_DEBUG
-	struct timer_list turn_ro_timer;	/* For turning read-only (crash simulation) */
-	wait_queue_head_t ro_wait_queue;	/* For people waiting for the fs to go read-only */
-#endif
-#ifdef CONFIG_QUOTA
-	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
-	int s_jquota_fmt;			/* Format of quota to use */
-#endif
-	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
-
-#ifdef EXTENTS_STATS
-	/* ext4 extents stats */
-	unsigned long s_ext_min;
-	unsigned long s_ext_max;
-	unsigned long s_depth_max;
-	spinlock_t s_ext_stats_lock;
-	unsigned long s_ext_blocks;
-	unsigned long s_ext_extents;
-#endif
-
-	/* for buddy allocator */
-	struct ext4_group_info ***s_group_info;
-	struct inode *s_buddy_cache;
-	long s_blocks_reserved;
-	spinlock_t s_reserve_lock;
-	spinlock_t s_md_lock;
-	tid_t s_last_transaction;
-	unsigned short *s_mb_offsets;
-	unsigned int *s_mb_maxs;
-
-	/* tunables */
-	unsigned long s_stripe;
-	unsigned int s_mb_stream_request;
-	unsigned int s_mb_max_to_scan;
-	unsigned int s_mb_min_to_scan;
-	unsigned int s_mb_stats;
-	unsigned int s_mb_order2_reqs;
-	unsigned int s_mb_group_prealloc;
-	/* where last allocation was done - for stream allocation */
-	unsigned long s_mb_last_group;
-	unsigned long s_mb_last_start;
-
-	/* history to debug policy */
-	struct ext4_mb_history *s_mb_history;
-	int s_mb_history_cur;
-	int s_mb_history_max;
-	int s_mb_history_num;
-	spinlock_t s_mb_history_lock;
-	int s_mb_history_filter;
-
-	/* stats for buddy allocator */
-	spinlock_t s_mb_pa_lock;
-	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
-	atomic_t s_bal_success;	/* we found long enough chunks */
-	atomic_t s_bal_allocated;	/* in blocks */
-	atomic_t s_bal_ex_scanned;	/* total extents scanned */
-	atomic_t s_bal_goals;	/* goal hits */
-	atomic_t s_bal_breaks;	/* too long searches */
-	atomic_t s_bal_2orders;	/* 2^order hits */
-	spinlock_t s_bal_lock;
-	unsigned long s_mb_buddies_generated;
-	unsigned long long s_mb_generation_time;
-	atomic_t s_mb_lost_chunks;
-	atomic_t s_mb_preallocated;
-	atomic_t s_mb_discarded;
-
-	/* locality groups */
-	struct ext4_locality_group *s_locality_groups;
-
-	/* for write statistics */
-	unsigned long s_sectors_written_start;
-	u64 s_kbytes_written;
-
-	unsigned int s_log_groups_per_flex;
-	struct flex_groups *s_flex_groups;
-};
-
-static inline spinlock_t *
-sb_bgl_lock(struct ext4_sb_info *sbi, unsigned int block_group)
-{
-	return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
-}
-
-#endif	/* _EXT4_SB */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e3a55eb8b26a..2593f748c3a4 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -326,32 +326,18 @@ ext4_ext_max_entries(struct inode *inode, int depth)
 
 static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 {
-	ext4_fsblk_t block = ext_pblock(ext), valid_block;
+	ext4_fsblk_t block = ext_pblock(ext);
 	int len = ext4_ext_get_actual_len(ext);
-	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
 
-	valid_block = le32_to_cpu(es->s_first_data_block) +
-		EXT4_SB(inode->i_sb)->s_gdb_count;
-	if (unlikely(block <= valid_block ||
-		     ((block + len) > ext4_blocks_count(es))))
-		return 0;
-	else
-		return 1;
+	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
 
 static int ext4_valid_extent_idx(struct inode *inode,
 				struct ext4_extent_idx *ext_idx)
 {
-	ext4_fsblk_t block = idx_pblock(ext_idx), valid_block;
-	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+	ext4_fsblk_t block = idx_pblock(ext_idx);
 
-	valid_block = le32_to_cpu(es->s_first_data_block) +
-		EXT4_SB(inode->i_sb)->s_gdb_count;
-	if (unlikely(block <= valid_block ||
-		     (block >= ext4_blocks_count(es))))
-		return 0;
-	else
-		return 1;
+	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
 }
 
 static int ext4_valid_extent_entries(struct inode *inode,
@@ -2097,12 +2083,16 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	ex = EXT_LAST_EXTENT(eh);
 
 	ex_ee_block = le32_to_cpu(ex->ee_block);
-	if (ext4_ext_is_uninitialized(ex))
-		uninitialized = 1;
 	ex_ee_len = ext4_ext_get_actual_len(ex);
 
 	while (ex >= EXT_FIRST_EXTENT(eh) &&
 			ex_ee_block + ex_ee_len > start) {
+
+		if (ext4_ext_is_uninitialized(ex))
+			uninitialized = 1;
+		else
+			uninitialized = 0;
+
 		ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len);
 		path[depth].p_ext = ex;
 
@@ -2784,7 +2774,7 @@ fix_extent_len:
 int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock,
 			unsigned int max_blocks, struct buffer_head *bh_result,
-			int create, int extend_disksize)
+			int flags)
 {
 	struct ext4_ext_path *path = NULL;
 	struct ext4_extent_header *eh;
@@ -2793,7 +2783,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	int err = 0, depth, ret, cache_type;
 	unsigned int allocated = 0;
 	struct ext4_allocation_request ar;
-	loff_t disksize;
 
 	__clear_bit(BH_New, &bh_result->b_state);
 	ext_debug("blocks %u/%u requested for inode %u\n",
@@ -2803,7 +2792,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	cache_type = ext4_ext_in_cache(inode, iblock, &newex);
 	if (cache_type) {
 		if (cache_type == EXT4_EXT_CACHE_GAP) {
-			if (!create) {
+			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
 				/*
 				 * block isn't allocated yet and
 				 * user doesn't want to allocate it
@@ -2869,9 +2858,11 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 							EXT4_EXT_CACHE_EXTENT);
 				goto out;
 			}
-			if (create == EXT4_CREATE_UNINITIALIZED_EXT)
+			if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)
 				goto out;
-			if (!create) {
+			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
+				if (allocated > max_blocks)
+					allocated = max_blocks;
 				/*
 				 * We have blocks reserved already.  We
 				 * return allocated blocks so that delalloc
@@ -2879,8 +2870,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 				 * the buffer head will be unmapped so that
 				 * a read from the block returns 0s.
 				 */
-				if (allocated > max_blocks)
-					allocated = max_blocks;
 				set_buffer_unwritten(bh_result);
 				bh_result->b_bdev = inode->i_sb->s_bdev;
 				bh_result->b_blocknr = newblock;
@@ -2903,7 +2892,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	 * requested block isn't allocated yet;
 	 * we couldn't try to create block if create flag is zero
 	 */
-	if (!create) {
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
 		/*
 		 * put just found gap into cache to speed up
 		 * subsequent requests
@@ -2932,10 +2921,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	 * EXT_UNINIT_MAX_LEN.
 	 */
 	if (max_blocks > EXT_INIT_MAX_LEN &&
-	    create != EXT4_CREATE_UNINITIALIZED_EXT)
+	    !(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
 		max_blocks = EXT_INIT_MAX_LEN;
 	else if (max_blocks > EXT_UNINIT_MAX_LEN &&
-		 create == EXT4_CREATE_UNINITIALIZED_EXT)
+		 (flags & EXT4_GET_BLOCKS_UNINIT_EXT))
 		max_blocks = EXT_UNINIT_MAX_LEN;
 
 	/* Check if we can really insert (iblock)::(iblock+max_blocks) extent */
@@ -2966,7 +2955,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	/* try to insert new extent into found leaf and return */
 	ext4_ext_store_pblock(&newex, newblock);
 	newex.ee_len = cpu_to_le16(ar.len);
-	if (create == EXT4_CREATE_UNINITIALIZED_EXT)  /* Mark uninitialized */
+	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)  /* Mark uninitialized */
 		ext4_ext_mark_uninitialized(&newex);
 	err = ext4_ext_insert_extent(handle, inode, path, &newex);
 	if (err) {
@@ -2983,18 +2972,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	newblock = ext_pblock(&newex);
 	allocated = ext4_ext_get_actual_len(&newex);
 outnew:
-	if (extend_disksize) {
-		disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits;
-		if (disksize > i_size_read(inode))
-			disksize = i_size_read(inode);
-		if (disksize > EXT4_I(inode)->i_disksize)
-			EXT4_I(inode)->i_disksize = disksize;
-	}
-
 	set_buffer_new(bh_result);
 
 	/* Cache only when it is _not_ an uninitialized extent */
-	if (create != EXT4_CREATE_UNINITIALIZED_EXT)
+	if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
 		ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
 						EXT4_EXT_CACHE_EXTENT);
 out:
@@ -3150,9 +3131,10 @@ retry:
 			ret = PTR_ERR(handle);
 			break;
 		}
-		ret = ext4_get_blocks_wrap(handle, inode, block,
-					  max_blocks, &map_bh,
-					  EXT4_CREATE_UNINITIALIZED_EXT, 0, 0);
+		map_bh.b_state = 0;
+		ret = ext4_get_blocks(handle, inode, block,
+				      max_blocks, &map_bh,
+				      EXT4_GET_BLOCKS_CREATE_UNINIT_EXT);
 		if (ret <= 0) {
 #ifdef EXT4FS_DEBUG
 			WARN_ON(ret <= 0);
@@ -3195,7 +3177,7 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 		       void *data)
 {
 	struct fiemap_extent_info *fieinfo = data;
-	unsigned long blksize_bits = inode->i_sb->s_blocksize_bits;
+	unsigned char blksize_bits = inode->i_sb->s_blocksize_bits;
 	__u64	logical;
 	__u64	physical;
 	__u64	length;
@@ -3242,9 +3224,16 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 	 *
 	 * XXX this might miss a single-block extent at EXT_MAX_BLOCK
 	 */
-	if (logical + length - 1 == EXT_MAX_BLOCK ||
-	    ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK)
+	if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK ||
+	    newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) {
+		loff_t size = i_size_read(inode);
+		loff_t bs = EXT4_BLOCK_SIZE(inode->i_sb);
+
 		flags |= FIEMAP_EXTENT_LAST;
+		if ((flags & FIEMAP_EXTENT_DELALLOC) &&
+		    logical+length > size)
+			length = (size - logical + bs - 1) & ~(bs-1);
+	}
 
 	error = fiemap_fill_next_extent(fieinfo, logical, physical,
 					length, flags);
@@ -3318,10 +3307,10 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		 * Walk the extent tree gathering extent information.
 		 * ext4_ext_fiemap_cb will push extents back to user.
 		 */
-		down_write(&EXT4_I(inode)->i_data_sem);
+		down_read(&EXT4_I(inode)->i_data_sem);
 		error = ext4_ext_walk_space(inode, start_blk, len_blks,
 					  ext4_ext_fiemap_cb, fieinfo);
-		up_write(&EXT4_I(inode)->i_data_sem);
+		up_read(&EXT4_I(inode)->i_data_sem);
 	}
 
 	return error;
diff --git a/fs/ext4/group.h b/fs/ext4/group.h
deleted file mode 100644
index c2c0a8d06d0e..000000000000
--- a/fs/ext4/group.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- *  linux/fs/ext4/group.h
- *
- * Copyright (C) 2007 Cluster File Systems, Inc
- *
- * Author: Andreas Dilger <adilger@clusterfs.com>
- */
-
-#ifndef _LINUX_EXT4_GROUP_H
-#define _LINUX_EXT4_GROUP_H
-
-extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
-				   struct ext4_group_desc *gdp);
-extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
-				       struct ext4_group_desc *gdp);
-struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
-				      ext4_group_t block_group);
-extern unsigned ext4_init_block_bitmap(struct super_block *sb,
-				       struct buffer_head *bh,
-				       ext4_group_t group,
-				       struct ext4_group_desc *desc);
-#define ext4_free_blocks_after_init(sb, group, desc)			\
-		ext4_init_block_bitmap(sb, NULL, group, desc)
-extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
-				       struct buffer_head *bh,
-				       ext4_group_t group,
-				       struct ext4_group_desc *desc);
-extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
-#endif /* _LINUX_EXT4_GROUP_H */
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f18e0a08a6b5..3743bd849bce 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -27,7 +27,6 @@
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "group.h"
 
 /*
  * ialloc.c contains the inodes allocation and deallocation routines
@@ -123,16 +122,16 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		unlock_buffer(bh);
 		return bh;
 	}
-	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
 		ext4_init_inode_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
-		spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
 		return bh;
 	}
-	spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	ext4_unlock_group(sb, block_group);
 	if (buffer_uptodate(bh)) {
 		/*
 		 * if not uninit if bh is uptodate,
@@ -247,9 +246,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 		goto error_return;
 
 	/* Ok, now we can actually update the inode bitmaps.. */
-	spin_lock(sb_bgl_lock(sbi, block_group));
-	cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
-	spin_unlock(sb_bgl_lock(sbi, block_group));
+	cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
+					bit, bitmap_bh->b_data);
 	if (!cleared)
 		ext4_error(sb, "ext4_free_inode",
 			   "bit already cleared for inode %lu", ino);
@@ -261,7 +259,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 		if (fatal) goto error_return;
 
 		if (gdp) {
-			spin_lock(sb_bgl_lock(sbi, block_group));
+			ext4_lock_group(sb, block_group);
 			count = ext4_free_inodes_count(sb, gdp) + 1;
 			ext4_free_inodes_set(sb, gdp, count);
 			if (is_directory) {
@@ -277,7 +275,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 			}
 			gdp->bg_checksum = ext4_group_desc_csum(sbi,
 							block_group, gdp);
-			spin_unlock(sb_bgl_lock(sbi, block_group));
+			ext4_unlock_group(sb, block_group);
 			percpu_counter_inc(&sbi->s_freeinodes_counter);
 			if (is_directory)
 				percpu_counter_dec(&sbi->s_dirs_counter);
@@ -316,7 +314,7 @@ error_return:
 static int find_group_dir(struct super_block *sb, struct inode *parent,
 				ext4_group_t *best_group)
 {
-	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	unsigned int freei, avefreei;
 	struct ext4_group_desc *desc, *best_desc = NULL;
 	ext4_group_t group;
@@ -349,11 +347,10 @@ static int find_group_flex(struct super_block *sb, struct inode *parent,
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_desc *desc;
-	struct buffer_head *bh;
 	struct flex_groups *flex_group = sbi->s_flex_groups;
 	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
 	ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
-	ext4_group_t ngroups = sbi->s_groups_count;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	int flex_size = ext4_flex_bg_size(sbi);
 	ext4_group_t best_flex = parent_fbg_group;
 	int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
@@ -362,7 +359,7 @@ static int find_group_flex(struct super_block *sb, struct inode *parent,
 	ext4_group_t n_fbg_groups;
 	ext4_group_t i;
 
-	n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >>
+	n_fbg_groups = (ngroups + flex_size - 1) >>
 		sbi->s_log_groups_per_flex;
 
 find_close_to_parent:
@@ -404,7 +401,7 @@ find_close_to_parent:
 found_flexbg:
 	for (i = best_flex * flex_size; i < ngroups &&
 		     i < (best_flex + 1) * flex_size; i++) {
-		desc = ext4_get_group_desc(sb, i, &bh);
+		desc = ext4_get_group_desc(sb, i, NULL);
 		if (ext4_free_inodes_count(sb, desc)) {
 			*best_group = i;
 			goto out;
@@ -478,20 +475,21 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 {
 	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	ext4_group_t ngroups = sbi->s_groups_count;
+	ext4_group_t real_ngroups = ext4_get_groups_count(sb);
 	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
 	unsigned int freei, avefreei;
 	ext4_fsblk_t freeb, avefreeb;
 	unsigned int ndirs;
 	int max_dirs, min_inodes;
 	ext4_grpblk_t min_blocks;
-	ext4_group_t i, grp, g;
+	ext4_group_t i, grp, g, ngroups;
 	struct ext4_group_desc *desc;
 	struct orlov_stats stats;
 	int flex_size = ext4_flex_bg_size(sbi);
 
+	ngroups = real_ngroups;
 	if (flex_size > 1) {
-		ngroups = (ngroups + flex_size - 1) >>
+		ngroups = (real_ngroups + flex_size - 1) >>
 			sbi->s_log_groups_per_flex;
 		parent_group >>= sbi->s_log_groups_per_flex;
 	}
@@ -543,7 +541,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 		 */
 		grp *= flex_size;
 		for (i = 0; i < flex_size; i++) {
-			if (grp+i >= sbi->s_groups_count)
+			if (grp+i >= real_ngroups)
 				break;
 			desc = ext4_get_group_desc(sb, grp+i, NULL);
 			if (desc && ext4_free_inodes_count(sb, desc)) {
@@ -583,7 +581,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 	}
 
 fallback:
-	ngroups = sbi->s_groups_count;
+	ngroups = real_ngroups;
 	avefreei = freei / ngroups;
 fallback_retry:
 	parent_group = EXT4_I(parent)->i_block_group;
@@ -613,9 +611,8 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 			    ext4_group_t *group, int mode)
 {
 	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
-	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t i, last, ngroups = ext4_get_groups_count(sb);
 	struct ext4_group_desc *desc;
-	ext4_group_t i, last;
 	int flex_size = ext4_flex_bg_size(EXT4_SB(sb));
 
 	/*
@@ -708,10 +705,10 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 
 /*
  * claim the inode from the inode bitmap. If the group
- * is uninit we need to take the groups's sb_bgl_lock
+ * is uninit we need to take the groups's ext4_group_lock
  * and clear the uninit flag. The inode bitmap update
  * and group desc uninit flag clear should be done
- * after holding sb_bgl_lock so that ext4_read_inode_bitmap
+ * after holding ext4_group_lock so that ext4_read_inode_bitmap
  * doesn't race with the ext4_claim_inode
  */
 static int ext4_claim_inode(struct super_block *sb,
@@ -722,7 +719,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
 
-	spin_lock(sb_bgl_lock(sbi, group));
+	ext4_lock_group(sb, group);
 	if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
 		/* not a free inode */
 		retval = 1;
@@ -731,7 +728,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	ino++;
 	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
 			ino > EXT4_INODES_PER_GROUP(sb)) {
-		spin_unlock(sb_bgl_lock(sbi, group));
+		ext4_unlock_group(sb, group);
 		ext4_error(sb, __func__,
 			   "reserved inode or inode > inodes count - "
 			   "block_group = %u, inode=%lu", group,
@@ -780,7 +777,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	}
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
 err_ret:
-	spin_unlock(sb_bgl_lock(sbi, group));
+	ext4_unlock_group(sb, group);
 	return retval;
 }
 
@@ -799,11 +796,10 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 	struct super_block *sb;
 	struct buffer_head *inode_bitmap_bh = NULL;
 	struct buffer_head *group_desc_bh;
-	ext4_group_t group = 0;
+	ext4_group_t ngroups, group = 0;
 	unsigned long ino = 0;
 	struct inode *inode;
 	struct ext4_group_desc *gdp = NULL;
-	struct ext4_super_block *es;
 	struct ext4_inode_info *ei;
 	struct ext4_sb_info *sbi;
 	int ret2, err = 0;
@@ -818,15 +814,14 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 		return ERR_PTR(-EPERM);
 
 	sb = dir->i_sb;
+	ngroups = ext4_get_groups_count(sb);
 	trace_mark(ext4_request_inode, "dev %s dir %lu mode %d", sb->s_id,
 		   dir->i_ino, mode);
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	ei = EXT4_I(inode);
-
 	sbi = EXT4_SB(sb);
-	es = sbi->s_es;
 
 	if (sbi->s_log_groups_per_flex && test_opt(sb, OLDALLOC)) {
 		ret2 = find_group_flex(sb, dir, &group);
@@ -856,7 +851,7 @@ got_group:
 	if (ret2 == -1)
 		goto out;
 
-	for (i = 0; i < sbi->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		err = -EIO;
 
 		gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
@@ -917,7 +912,7 @@ repeat_in_this_group:
 		 * group descriptor metadata has not yet been updated.
 		 * So we just go onto the next blockgroup.
 		 */
-		if (++group == sbi->s_groups_count)
+		if (++group == ngroups)
 			group = 0;
 	}
 	err = -ENOSPC;
@@ -938,7 +933,7 @@ got:
 		}
 
 		free = 0;
-		spin_lock(sb_bgl_lock(sbi, group));
+		ext4_lock_group(sb, group);
 		/* recheck and clear flag under lock if we still need to */
 		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 			free = ext4_free_blocks_after_init(sb, group, gdp);
@@ -947,7 +942,7 @@ got:
 			gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
 								gdp);
 		}
-		spin_unlock(sb_bgl_lock(sbi, group));
+		ext4_unlock_group(sb, group);
 
 		/* Don't need to dirty bitmap block if we didn't change it */
 		if (free) {
@@ -1158,7 +1153,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 {
 	unsigned long desc_count;
 	struct ext4_group_desc *gdp;
-	ext4_group_t i;
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
 #ifdef EXT4FS_DEBUG
 	struct ext4_super_block *es;
 	unsigned long bitmap_count, x;
@@ -1168,7 +1163,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 	desc_count = 0;
 	bitmap_count = 0;
 	gdp = NULL;
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
@@ -1190,7 +1185,7 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 	return desc_count;
 #else
 	desc_count = 0;
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
@@ -1205,9 +1200,9 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 unsigned long ext4_count_dirs(struct super_block * sb)
 {
 	unsigned long count = 0;
-	ext4_group_t i;
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
 
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2a9ffd528dd1..875db944b22f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -372,20 +372,21 @@ static int ext4_block_to_path(struct inode *inode,
 }
 
 static int __ext4_check_blockref(const char *function, struct inode *inode,
-				 __le32 *p, unsigned int max) {
-
-	unsigned int maxblocks = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es);
+				 __le32 *p, unsigned int max)
+{
 	__le32 *bref = p;
+	unsigned int blk;
+
 	while (bref < p+max) {
-		if (unlikely(le32_to_cpu(*bref) >= maxblocks)) {
+		blk = le32_to_cpu(*bref++);
+		if (blk && 
+		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), 
+						    blk, 1))) {
 			ext4_error(inode->i_sb, function,
-				   "block reference %u >= max (%u) "
-				   "in inode #%lu, offset=%d",
-				   le32_to_cpu(*bref), maxblocks,
-				   inode->i_ino, (int)(bref-p));
+				   "invalid block reference %u "
+				   "in inode #%lu", blk, inode->i_ino);
  			return -EIO;
  		}
-		bref++;
  	}
  	return 0;
 }
@@ -892,6 +893,10 @@ err_out:
 }
 
 /*
+ * The ext4_ind_get_blocks() function handles non-extents inodes
+ * (i.e., using the traditional indirect/double-indirect i_blocks
+ * scheme) for ext4_get_blocks().
+ *
  * Allocation strategy is simple: if we have to allocate something, we will
  * have to go the whole way to leaf. So let's do it before attaching anything
  * to tree, set linkage between the newborn blocks, write them if sync is
@@ -909,15 +914,16 @@ err_out:
  * return = 0, if plain lookup failed.
  * return < 0, error case.
  *
- *
- * Need to be called with
- * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
- * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
+ * The ext4_ind_get_blocks() function should be called with
+ * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem
+ * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or
+ * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
+ * blocks.
  */
-static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
+static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
 				  ext4_lblk_t iblock, unsigned int maxblocks,
 				  struct buffer_head *bh_result,
-				  int create, int extend_disksize)
+				  int flags)
 {
 	int err = -EIO;
 	ext4_lblk_t offsets[4];
@@ -927,14 +933,11 @@ static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
 	int indirect_blks;
 	int blocks_to_boundary = 0;
 	int depth;
-	struct ext4_inode_info *ei = EXT4_I(inode);
 	int count = 0;
 	ext4_fsblk_t first_block = 0;
-	loff_t disksize;
-
 
 	J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
-	J_ASSERT(handle != NULL || create == 0);
+	J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
 	depth = ext4_block_to_path(inode, iblock, offsets,
 					&blocks_to_boundary);
 
@@ -963,7 +966,7 @@ static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
 	}
 
 	/* Next simple case - plain lookup or failed read of indirect block */
-	if (!create || err == -EIO)
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
 		goto cleanup;
 
 	/*
@@ -997,19 +1000,7 @@ static int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
 	if (!err)
 		err = ext4_splice_branch(handle, inode, iblock,
 					partial, indirect_blks, count);
-	/*
-	 * i_disksize growing is protected by i_data_sem.  Don't forget to
-	 * protect it if you're about to implement concurrent
-	 * ext4_get_block() -bzzz
-	*/
-	if (!err && extend_disksize) {
-		disksize = ((loff_t) iblock + count) << inode->i_blkbits;
-		if (disksize > i_size_read(inode))
-			disksize = i_size_read(inode);
-		if (disksize > ei->i_disksize)
-			ei->i_disksize = disksize;
-	}
-	if (err)
+	else 
 		goto cleanup;
 
 	set_buffer_new(bh_result);
@@ -1120,8 +1111,23 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
 		ext4_discard_preallocations(inode);
 }
 
+static int check_block_validity(struct inode *inode, sector_t logical,
+				sector_t phys, int len)
+{
+	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) {
+		ext4_error(inode->i_sb, "check_block_validity",
+			   "inode #%lu logical block %llu mapped to %llu "
+			   "(size %d)", inode->i_ino,
+			   (unsigned long long) logical,
+			   (unsigned long long) phys, len);
+		WARN_ON(1);
+		return -EIO;
+	}
+	return 0;
+}
+
 /*
- * The ext4_get_blocks_wrap() function try to look up the requested blocks,
+ * The ext4_get_blocks() function tries to look up the requested blocks,
  * and returns if the blocks are already mapped.
  *
  * Otherwise it takes the write lock of the i_data_sem and allocate blocks
@@ -1129,7 +1135,7 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
  * mapped.
  *
  * If file type is extents based, it will call ext4_ext_get_blocks(),
- * Otherwise, call with ext4_get_blocks_handle() to handle indirect mapping
+ * Otherwise, call with ext4_ind_get_blocks() to handle indirect mapping
  * based files
  *
  * On success, it returns the number of blocks being mapped or allocate.
@@ -1142,9 +1148,9 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
  *
  * It returns the error in case of allocation failure.
  */
-int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
-			unsigned int max_blocks, struct buffer_head *bh,
-			int create, int extend_disksize, int flag)
+int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
+		    unsigned int max_blocks, struct buffer_head *bh,
+		    int flags)
 {
 	int retval;
 
@@ -1152,21 +1158,28 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 	clear_buffer_unwritten(bh);
 
 	/*
-	 * Try to see if we can get  the block without requesting
-	 * for new file system block.
+	 * Try to see if we can get the block without requesting a new
+	 * file system block.
 	 */
 	down_read((&EXT4_I(inode)->i_data_sem));
 	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
 		retval =  ext4_ext_get_blocks(handle, inode, block, max_blocks,
-				bh, 0, 0);
+				bh, 0);
 	} else {
-		retval = ext4_get_blocks_handle(handle,
-				inode, block, max_blocks, bh, 0, 0);
+		retval = ext4_ind_get_blocks(handle, inode, block, max_blocks,
+					     bh, 0);
 	}
 	up_read((&EXT4_I(inode)->i_data_sem));
 
+	if (retval > 0 && buffer_mapped(bh)) {
+		int ret = check_block_validity(inode, block, 
+					       bh->b_blocknr, retval);
+		if (ret != 0)
+			return ret;
+	}
+
 	/* If it is only a block(s) look up */
-	if (!create)
+	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
 		return retval;
 
 	/*
@@ -1205,7 +1218,7 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 	 * let the underlying get_block() function know to
 	 * avoid double accounting
 	 */
-	if (flag)
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
 		EXT4_I(inode)->i_delalloc_reserved_flag = 1;
 	/*
 	 * We need to check for EXT4 here because migrate
@@ -1213,10 +1226,10 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 	 */
 	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
 		retval =  ext4_ext_get_blocks(handle, inode, block, max_blocks,
-				bh, create, extend_disksize);
+					      bh, flags);
 	} else {
-		retval = ext4_get_blocks_handle(handle, inode, block,
-				max_blocks, bh, create, extend_disksize);
+		retval = ext4_ind_get_blocks(handle, inode, block,
+					     max_blocks, bh, flags);
 
 		if (retval > 0 && buffer_new(bh)) {
 			/*
@@ -1229,18 +1242,23 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 		}
 	}
 
-	if (flag) {
+	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
 		EXT4_I(inode)->i_delalloc_reserved_flag = 0;
-		/*
-		 * Update reserved blocks/metadata blocks
-		 * after successful block allocation
-		 * which were deferred till now
-		 */
-		if ((retval > 0) && buffer_delay(bh))
-			ext4_da_update_reserve_space(inode, retval);
-	}
+
+	/*
+	 * Update reserved blocks/metadata blocks after successful
+	 * block allocation which had been deferred till now.
+	 */
+	if ((retval > 0) && (flags & EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE))
+		ext4_da_update_reserve_space(inode, retval);
 
 	up_write((&EXT4_I(inode)->i_data_sem));
+	if (retval > 0 && buffer_mapped(bh)) {
+		int ret = check_block_validity(inode, block, 
+					       bh->b_blocknr, retval);
+		if (ret != 0)
+			return ret;
+	}
 	return retval;
 }
 
@@ -1268,8 +1286,8 @@ int ext4_get_block(struct inode *inode, sector_t iblock,
 		started = 1;
 	}
 
-	ret = ext4_get_blocks_wrap(handle, inode, iblock,
-					max_blocks, bh_result, create, 0, 0);
+	ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
+			      create ? EXT4_GET_BLOCKS_CREATE : 0);
 	if (ret > 0) {
 		bh_result->b_size = (ret << inode->i_blkbits);
 		ret = 0;
@@ -1288,17 +1306,19 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 {
 	struct buffer_head dummy;
 	int fatal = 0, err;
+	int flags = 0;
 
 	J_ASSERT(handle != NULL || create == 0);
 
 	dummy.b_state = 0;
 	dummy.b_blocknr = -1000;
 	buffer_trace_init(&dummy.b_history);
-	err = ext4_get_blocks_wrap(handle, inode, block, 1,
-					&dummy, create, 1, 0);
+	if (create)
+		flags |= EXT4_GET_BLOCKS_CREATE;
+	err = ext4_get_blocks(handle, inode, block, 1, &dummy, flags);
 	/*
-	 * ext4_get_blocks_handle() returns number of blocks
-	 * mapped. 0 in case of a HOLE.
+	 * ext4_get_blocks() returns number of blocks mapped. 0 in
+	 * case of a HOLE.
 	 */
 	if (err > 0) {
 		if (err > 1)
@@ -1439,7 +1459,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 				struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
-	int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
+	int ret, needed_blocks;
 	handle_t *handle;
 	int retries = 0;
 	struct page *page;
@@ -1450,6 +1470,11 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 		   "dev %s ino %lu pos %llu len %u flags %u",
 		   inode->i_sb->s_id, inode->i_ino,
 		   (unsigned long long) pos, len, flags);
+	/*
+	 * Reserve one block more for addition to orphan list in case
+	 * we allocate blocks but write fails for some reason
+	 */
+	needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
  	index = pos >> PAGE_CACHE_SHIFT;
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
@@ -1483,15 +1508,30 @@ retry:
 
 	if (ret) {
 		unlock_page(page);
-		ext4_journal_stop(handle);
 		page_cache_release(page);
 		/*
 		 * block_write_begin may have instantiated a few blocks
 		 * outside i_size.  Trim these off again. Don't need
 		 * i_size_read because we hold i_mutex.
+		 *
+		 * Add inode to orphan list in case we crash before
+		 * truncate finishes
 		 */
 		if (pos + len > inode->i_size)
+			ext4_orphan_add(handle, inode);
+
+		ext4_journal_stop(handle);
+		if (pos + len > inode->i_size) {
 			vmtruncate(inode, inode->i_size);
+			/* 
+			 * If vmtruncate failed early the inode might
+			 * still be on the orphan list; we need to
+			 * make sure the inode is removed from the
+			 * orphan list in that case.
+			 */
+			if (inode->i_nlink)
+				ext4_orphan_del(NULL, inode);
+		}
 	}
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -1509,6 +1549,52 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh)
 	return ext4_handle_dirty_metadata(handle, NULL, bh);
 }
 
+static int ext4_generic_write_end(struct file *file,
+				struct address_space *mapping,
+				loff_t pos, unsigned len, unsigned copied,
+				struct page *page, void *fsdata)
+{
+	int i_size_changed = 0;
+	struct inode *inode = mapping->host;
+	handle_t *handle = ext4_journal_current_handle();
+
+	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+	/*
+	 * No need to use i_size_read() here, the i_size
+	 * cannot change under us because we hold i_mutex.
+	 *
+	 * But it's important to update i_size while still holding page lock:
+	 * page writeout could otherwise come in and zero beyond i_size.
+	 */
+	if (pos + copied > inode->i_size) {
+		i_size_write(inode, pos + copied);
+		i_size_changed = 1;
+	}
+
+	if (pos + copied >  EXT4_I(inode)->i_disksize) {
+		/* We need to mark inode dirty even if
+		 * new_i_size is less that inode->i_size
+		 * bu greater than i_disksize.(hint delalloc)
+		 */
+		ext4_update_i_disksize(inode, (pos + copied));
+		i_size_changed = 1;
+	}
+	unlock_page(page);
+	page_cache_release(page);
+
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (i_size_changed)
+		ext4_mark_inode_dirty(handle, inode);
+
+	return copied;
+}
+
 /*
  * We need to pick up the new inode size which generic_commit_write gave us
  * `file' can be NULL - eg, when called from page_symlink().
@@ -1532,21 +1618,15 @@ static int ext4_ordered_write_end(struct file *file,
 	ret = ext4_jbd2_file_inode(handle, inode);
 
 	if (ret == 0) {
-		loff_t new_i_size;
-
-		new_i_size = pos + copied;
-		if (new_i_size > EXT4_I(inode)->i_disksize) {
-			ext4_update_i_disksize(inode, new_i_size);
-			/* We need to mark inode dirty even if
-			 * new_i_size is less that inode->i_size
-			 * bu greater than i_disksize.(hint delalloc)
-			 */
-			ext4_mark_inode_dirty(handle, inode);
-		}
-
-		ret2 = generic_write_end(file, mapping, pos, len, copied,
+		ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 		copied = ret2;
+		if (pos + len > inode->i_size)
+			/* if we have allocated more blocks and copied
+			 * less. We will have blocks allocated outside
+			 * inode->i_size. So truncate them
+			 */
+			ext4_orphan_add(handle, inode);
 		if (ret2 < 0)
 			ret = ret2;
 	}
@@ -1554,6 +1634,18 @@ static int ext4_ordered_write_end(struct file *file,
 	if (!ret)
 		ret = ret2;
 
+	if (pos + len > inode->i_size) {
+		vmtruncate(inode, inode->i_size);
+		/* 
+		 * If vmtruncate failed early the inode might still be
+		 * on the orphan list; we need to make sure the inode
+		 * is removed from the orphan list in that case.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
+
+
 	return ret ? ret : copied;
 }
 
@@ -1565,25 +1657,21 @@ static int ext4_writeback_write_end(struct file *file,
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
-	loff_t new_i_size;
 
 	trace_mark(ext4_writeback_write_end,
 		   "dev %s ino %lu pos %llu len %u copied %u",
 		   inode->i_sb->s_id, inode->i_ino,
 		   (unsigned long long) pos, len, copied);
-	new_i_size = pos + copied;
-	if (new_i_size > EXT4_I(inode)->i_disksize) {
-		ext4_update_i_disksize(inode, new_i_size);
-		/* We need to mark inode dirty even if
-		 * new_i_size is less that inode->i_size
-		 * bu greater than i_disksize.(hint delalloc)
-		 */
-		ext4_mark_inode_dirty(handle, inode);
-	}
-
-	ret2 = generic_write_end(file, mapping, pos, len, copied,
+	ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 	copied = ret2;
+	if (pos + len > inode->i_size)
+		/* if we have allocated more blocks and copied
+		 * less. We will have blocks allocated outside
+		 * inode->i_size. So truncate them
+		 */
+		ext4_orphan_add(handle, inode);
+
 	if (ret2 < 0)
 		ret = ret2;
 
@@ -1591,6 +1679,17 @@ static int ext4_writeback_write_end(struct file *file,
 	if (!ret)
 		ret = ret2;
 
+	if (pos + len > inode->i_size) {
+		vmtruncate(inode, inode->i_size);
+		/* 
+		 * If vmtruncate failed early the inode might still be
+		 * on the orphan list; we need to make sure the inode
+		 * is removed from the orphan list in that case.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
+
 	return ret ? ret : copied;
 }
 
@@ -1635,10 +1734,27 @@ static int ext4_journalled_write_end(struct file *file,
 	}
 
 	unlock_page(page);
+	page_cache_release(page);
+	if (pos + len > inode->i_size)
+		/* if we have allocated more blocks and copied
+		 * less. We will have blocks allocated outside
+		 * inode->i_size. So truncate them
+		 */
+		ext4_orphan_add(handle, inode);
+
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	page_cache_release(page);
+	if (pos + len > inode->i_size) {
+		vmtruncate(inode, inode->i_size);
+		/* 
+		 * If vmtruncate failed early the inode might still be
+		 * on the orphan list; we need to make sure the inode
+		 * is removed from the orphan list in that case.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
 
 	return ret ? ret : copied;
 }
@@ -1852,7 +1968,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
  * @logical - first logical block to start assignment with
  *
  * the function goes through all passed space and put actual disk
- * block numbers into buffer heads, dropping BH_Delay
+ * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten
  */
 static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
 				 struct buffer_head *exbh)
@@ -1902,16 +2018,24 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
 			do {
 				if (cur_logical >= logical + blocks)
 					break;
-				if (buffer_delay(bh)) {
-					bh->b_blocknr = pblock;
-					clear_buffer_delay(bh);
-					bh->b_bdev = inode->i_sb->s_bdev;
-				} else if (buffer_unwritten(bh)) {
-					bh->b_blocknr = pblock;
-					clear_buffer_unwritten(bh);
-					set_buffer_mapped(bh);
-					set_buffer_new(bh);
-					bh->b_bdev = inode->i_sb->s_bdev;
+
+				if (buffer_delay(bh) ||
+						buffer_unwritten(bh)) {
+
+					BUG_ON(bh->b_bdev != inode->i_sb->s_bdev);
+
+					if (buffer_delay(bh)) {
+						clear_buffer_delay(bh);
+						bh->b_blocknr = pblock;
+					} else {
+						/*
+						 * unwritten already should have
+						 * blocknr assigned. Verify that
+						 */
+						clear_buffer_unwritten(bh);
+						BUG_ON(bh->b_blocknr != pblock);
+					}
+
 				} else if (buffer_mapped(bh))
 					BUG_ON(bh->b_blocknr != pblock);
 
@@ -1990,51 +2114,6 @@ static void ext4_print_free_blocks(struct inode *inode)
 	return;
 }
 
-#define		EXT4_DELALLOC_RSVED	1
-static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
-				   struct buffer_head *bh_result, int create)
-{
-	int ret;
-	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
-	loff_t disksize = EXT4_I(inode)->i_disksize;
-	handle_t *handle = NULL;
-
-	handle = ext4_journal_current_handle();
-	BUG_ON(!handle);
-	ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
-				   bh_result, create, 0, EXT4_DELALLOC_RSVED);
-	if (ret <= 0)
-		return ret;
-
-	bh_result->b_size = (ret << inode->i_blkbits);
-
-	if (ext4_should_order_data(inode)) {
-		int retval;
-		retval = ext4_jbd2_file_inode(handle, inode);
-		if (retval)
-			/*
-			 * Failed to add inode for ordered mode. Don't
-			 * update file size
-			 */
-			return retval;
-	}
-
-	/*
-	 * Update on-disk size along with block allocation we don't
-	 * use 'extend_disksize' as size may change within already
-	 * allocated block -bzzz
-	 */
-	disksize = ((loff_t) iblock + ret) << inode->i_blkbits;
-	if (disksize > i_size_read(inode))
-		disksize = i_size_read(inode);
-	if (disksize > EXT4_I(inode)->i_disksize) {
-		ext4_update_i_disksize(inode, disksize);
-		ret = ext4_mark_inode_dirty(handle, inode);
-		return ret;
-	}
-	return 0;
-}
-
 /*
  * mpage_da_map_blocks - go through given space
  *
@@ -2045,29 +2124,57 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
  */
 static int mpage_da_map_blocks(struct mpage_da_data *mpd)
 {
-	int err = 0;
+	int err, blks, get_blocks_flags;
 	struct buffer_head new;
-	sector_t next;
+	sector_t next = mpd->b_blocknr;
+	unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits;
+	loff_t disksize = EXT4_I(mpd->inode)->i_disksize;
+	handle_t *handle = NULL;
 
 	/*
 	 * We consider only non-mapped and non-allocated blocks
 	 */
 	if ((mpd->b_state  & (1 << BH_Mapped)) &&
-	    !(mpd->b_state & (1 << BH_Delay)))
-		return 0;
-	new.b_state = mpd->b_state;
-	new.b_blocknr = 0;
-	new.b_size = mpd->b_size;
-	next = mpd->b_blocknr;
-	/*
-	 * If we didn't accumulate anything
-	 * to write simply return
-	 */
-	if (!new.b_size)
+		!(mpd->b_state & (1 << BH_Delay)) &&
+		!(mpd->b_state & (1 << BH_Unwritten)))
 		return 0;
 
-	err = ext4_da_get_block_write(mpd->inode, next, &new, 1);
-	if (err) {
+	/*
+	 * If we didn't accumulate anything to write simply return
+	 */
+	if (!mpd->b_size)
+		return 0;
+
+	handle = ext4_journal_current_handle();
+	BUG_ON(!handle);
+
+	/*
+	 * Call ext4_get_blocks() to allocate any delayed allocation
+	 * blocks, or to convert an uninitialized extent to be
+	 * initialized (in the case where we have written into
+	 * one or more preallocated blocks).
+	 *
+	 * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to
+	 * indicate that we are on the delayed allocation path.  This
+	 * affects functions in many different parts of the allocation
+	 * call path.  This flag exists primarily because we don't
+	 * want to change *many* call functions, so ext4_get_blocks()
+	 * will set the magic i_delalloc_reserved_flag once the
+	 * inode's allocation semaphore is taken.
+	 *
+	 * If the blocks in questions were delalloc blocks, set
+	 * EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting
+	 * variables are updated after the blocks have been allocated.
+	 */
+	new.b_state = 0;
+	get_blocks_flags = (EXT4_GET_BLOCKS_CREATE |
+			    EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+	if (mpd->b_state & (1 << BH_Delay))
+		get_blocks_flags |= EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE;
+	blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks,
+			       &new, get_blocks_flags);
+	if (blks < 0) {
+		err = blks;
 		/*
 		 * If get block returns with error we simply
 		 * return. Later writepage will redirty the page and
@@ -2100,12 +2207,14 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
 		if (err == -ENOSPC) {
 			ext4_print_free_blocks(mpd->inode);
 		}
-		/* invlaidate all the pages */
+		/* invalidate all the pages */
 		ext4_da_block_invalidatepages(mpd, next,
 				mpd->b_size >> mpd->inode->i_blkbits);
 		return err;
 	}
-	BUG_ON(new.b_size == 0);
+	BUG_ON(blks == 0);
+
+	new.b_size = (blks << mpd->inode->i_blkbits);
 
 	if (buffer_new(&new))
 		__unmap_underlying_blocks(mpd->inode, &new);
@@ -2118,6 +2227,23 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
 	    (mpd->b_state & (1 << BH_Unwritten)))
 		mpage_put_bnr_to_bhs(mpd, next, &new);
 
+	if (ext4_should_order_data(mpd->inode)) {
+		err = ext4_jbd2_file_inode(handle, mpd->inode);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * Update on-disk size along with block allocation.
+	 */
+	disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits;
+	if (disksize > i_size_read(mpd->inode))
+		disksize = i_size_read(mpd->inode);
+	if (disksize > EXT4_I(mpd->inode)->i_disksize) {
+		ext4_update_i_disksize(mpd->inode, disksize);
+		return ext4_mark_inode_dirty(handle, mpd->inode);
+	}
+
 	return 0;
 }
 
@@ -2192,6 +2318,17 @@ flush_it:
 	return;
 }
 
+static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
+{
+	/*
+	 * unmapped buffer is possible for holes.
+	 * delay buffer is possible with delayed allocation.
+	 * We also need to consider unwritten buffer as unmapped.
+	 */
+	return (!buffer_mapped(bh) || buffer_delay(bh) ||
+				buffer_unwritten(bh)) && buffer_dirty(bh);
+}
+
 /*
  * __mpage_da_writepage - finds extent of pages and blocks
  *
@@ -2276,8 +2413,7 @@ static int __mpage_da_writepage(struct page *page,
 			 * Otherwise we won't make progress
 			 * with the page in ext4_da_writepage
 			 */
-			if (buffer_dirty(bh) &&
-			    (!buffer_mapped(bh) || buffer_delay(bh))) {
+			if (ext4_bh_unmapped_or_delay(NULL, bh)) {
 				mpage_add_bh_to_extent(mpd, logical,
 						       bh->b_size,
 						       bh->b_state);
@@ -2303,8 +2439,16 @@ static int __mpage_da_writepage(struct page *page,
 }
 
 /*
- * this is a special callback for ->write_begin() only
- * it's intention is to return mapped block or reserve space
+ * This is a special get_blocks_t callback which is used by
+ * ext4_da_write_begin().  It will either return mapped block or
+ * reserve space for a single block.
+ *
+ * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set.
+ * We also have b_blocknr = -1 and b_bdev initialized properly
+ *
+ * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set.
+ * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev
+ * initialized properly.
  */
 static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 				  struct buffer_head *bh_result, int create)
@@ -2323,7 +2467,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 	 * preallocated blocks are unmapped but should treated
 	 * the same as allocated blocks.
 	 */
-	ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1,  bh_result, 0, 0, 0);
+	ret = ext4_get_blocks(NULL, inode, iblock, 1,  bh_result, 0);
 	if ((ret == 0) && !buffer_delay(bh_result)) {
 		/* the block isn't (pre)allocated yet, let's reserve space */
 		/*
@@ -2340,40 +2484,53 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		set_buffer_delay(bh_result);
 	} else if (ret > 0) {
 		bh_result->b_size = (ret << inode->i_blkbits);
-		/*
-		 * With sub-block writes into unwritten extents
-		 * we also need to mark the buffer as new so that
-		 * the unwritten parts of the buffer gets correctly zeroed.
-		 */
-		if (buffer_unwritten(bh_result))
+		if (buffer_unwritten(bh_result)) {
+			/* A delayed write to unwritten bh should
+			 * be marked new and mapped.  Mapped ensures
+			 * that we don't do get_block multiple times
+			 * when we write to the same offset and new
+			 * ensures that we do proper zero out for
+			 * partial write.
+			 */
 			set_buffer_new(bh_result);
+			set_buffer_mapped(bh_result);
+		}
 		ret = 0;
 	}
 
 	return ret;
 }
 
-static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
-{
-	/*
-	 * unmapped buffer is possible for holes.
-	 * delay buffer is possible with delayed allocation
-	 */
-	return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh));
-}
-
-static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock,
+/*
+ * This function is used as a standard get_block_t calback function
+ * when there is no desire to allocate any blocks.  It is used as a
+ * callback function for block_prepare_write(), nobh_writepage(), and
+ * block_write_full_page().  These functions should only try to map a
+ * single block at a time.
+ *
+ * Since this function doesn't do block allocations even if the caller
+ * requests it by passing in create=1, it is critically important that
+ * any caller checks to make sure that any buffer heads are returned
+ * by this function are either all already mapped or marked for
+ * delayed allocation before calling nobh_writepage() or
+ * block_write_full_page().  Otherwise, b_blocknr could be left
+ * unitialized, and the page write functions will be taken by
+ * surprise.
+ */
+static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
 {
 	int ret = 0;
 	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
 
+	BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
+
 	/*
 	 * we don't want to do block allocation in writepage
 	 * so call get_block_wrap with create = 0
 	 */
-	ret = ext4_get_blocks_wrap(NULL, inode, iblock, max_blocks,
-				   bh_result, 0, 0, 0);
+	ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0);
+	BUG_ON(create && ret == 0);
 	if (ret > 0) {
 		bh_result->b_size = (ret << inode->i_blkbits);
 		ret = 0;
@@ -2382,10 +2539,11 @@ static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock,
 }
 
 /*
- * get called vi ext4_da_writepages after taking page lock (have journal handle)
- * get called via journal_submit_inode_data_buffers (no journal handle)
- * get called via shrink_page_list via pdflush (no journal handle)
- * or grab_page_cache when doing write_begin (have journal handle)
+ * This function can get called via...
+ *   - ext4_da_writepages after taking page lock (have journal handle)
+ *   - journal_submit_inode_data_buffers (no journal handle)
+ *   - shrink_page_list via pdflush (no journal handle)
+ *   - grab_page_cache when doing write_begin (have journal handle)
  */
 static int ext4_da_writepage(struct page *page,
 				struct writeback_control *wbc)
@@ -2436,7 +2594,7 @@ static int ext4_da_writepage(struct page *page,
 		 * do block allocation here.
 		 */
 		ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
-						ext4_normal_get_block_write);
+					  noalloc_get_block_write);
 		if (!ret) {
 			page_bufs = page_buffers(page);
 			/* check whether all are mapped and non delay */
@@ -2461,11 +2619,10 @@ static int ext4_da_writepage(struct page *page,
 	}
 
 	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
-		ret = nobh_writepage(page, ext4_normal_get_block_write, wbc);
+		ret = nobh_writepage(page, noalloc_get_block_write, wbc);
 	else
-		ret = block_write_full_page(page,
-						ext4_normal_get_block_write,
-						wbc);
+		ret = block_write_full_page(page, noalloc_get_block_write,
+					    wbc);
 
 	return ret;
 }
@@ -2777,7 +2934,7 @@ retry:
 	*pagep = page;
 
 	ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
-							ext4_da_get_block_prep);
+				ext4_da_get_block_prep);
 	if (ret < 0) {
 		unlock_page(page);
 		ext4_journal_stop(handle);
@@ -2815,7 +2972,7 @@ static int ext4_da_should_update_i_disksize(struct page *page,
 	for (i = 0; i < idx; i++)
 		bh = bh->b_this_page;
 
-	if (!buffer_mapped(bh) || (buffer_delay(bh)))
+	if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh))
 		return 0;
 	return 1;
 }
@@ -3085,12 +3242,10 @@ static int __ext4_normal_writepage(struct page *page,
 	struct inode *inode = page->mapping->host;
 
 	if (test_opt(inode->i_sb, NOBH))
-		return nobh_writepage(page,
-					ext4_normal_get_block_write, wbc);
+		return nobh_writepage(page, noalloc_get_block_write, wbc);
 	else
-		return block_write_full_page(page,
-						ext4_normal_get_block_write,
-						wbc);
+		return block_write_full_page(page, noalloc_get_block_write,
+					     wbc);
 }
 
 static int ext4_normal_writepage(struct page *page,
@@ -3142,7 +3297,7 @@ static int __ext4_journalled_writepage(struct page *page,
 	int err;
 
 	ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
-					ext4_normal_get_block_write);
+				  noalloc_get_block_write);
 	if (ret != 0)
 		goto out_unlock;
 
@@ -3227,9 +3382,8 @@ static int ext4_journalled_writepage(struct page *page,
 		 * really know unless we go poke around in the buffer_heads.
 		 * But block_write_full_page will do the right thing.
 		 */
-		return block_write_full_page(page,
-						ext4_normal_get_block_write,
-						wbc);
+		return block_write_full_page(page, noalloc_get_block_write,
+					     wbc);
 	}
 no_write:
 	redirty_page_for_writepage(wbc, page);
@@ -3973,7 +4127,8 @@ void ext4_truncate(struct inode *inode)
 	if (!ext4_can_truncate(inode))
 		return;
 
-	if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
+	if (ei->i_disksize && inode->i_size == 0 &&
+	    !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
 		ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE;
 
 	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
@@ -4715,25 +4870,6 @@ int ext4_write_inode(struct inode *inode, int wait)
 	return ext4_force_commit(inode->i_sb);
 }
 
-int __ext4_write_dirty_metadata(struct inode *inode, struct buffer_head *bh)
-{
-	int err = 0;
-
-	mark_buffer_dirty(bh);
-	if (inode && inode_needs_sync(inode)) {
-		sync_dirty_buffer(bh);
-		if (buffer_req(bh) && !buffer_uptodate(bh)) {
-			ext4_error(inode->i_sb, __func__,
-				   "IO error syncing inode, "
-				   "inode=%lu, block=%llu",
-				   inode->i_ino,
-				   (unsigned long long)bh->b_blocknr);
-			err = -EIO;
-		}
-	}
-	return err;
-}
-
 /*
  * ext4_setattr()
  *
@@ -4930,7 +5066,8 @@ static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
  */
 int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 {
-	int groups, gdpblocks;
+	ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
+	int gdpblocks;
 	int idxblocks;
 	int ret = 0;
 
@@ -4957,8 +5094,8 @@ int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 		groups += nrblocks;
 
 	gdpblocks = groups;
-	if (groups > EXT4_SB(inode->i_sb)->s_groups_count)
-		groups = EXT4_SB(inode->i_sb)->s_groups_count;
+	if (groups > ngroups)
+		groups = ngroups;
 	if (groups > EXT4_SB(inode->i_sb)->s_gdb_count)
 		gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count;
 
@@ -4998,7 +5135,7 @@ int ext4_writepage_trans_blocks(struct inode *inode)
  * Calculate the journal credits for a chunk of data modification.
  *
  * This is called from DIO, fallocate or whoever calling
- * ext4_get_blocks_wrap() to map/allocate a chunk of contigous disk blocks.
+ * ext4_get_blocks() to map/allocate a chunk of contigous disk blocks.
  *
  * journal buffers for data blocks are not included here, as DIO
  * and fallocate do no need to journal data buffers.
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f871677a7984..ed8482e22c0e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -372,24 +372,12 @@ static inline void mb_set_bit(int bit, void *addr)
 	ext4_set_bit(bit, addr);
 }
 
-static inline void mb_set_bit_atomic(spinlock_t *lock, int bit, void *addr)
-{
-	addr = mb_correct_addr_and_bit(&bit, addr);
-	ext4_set_bit_atomic(lock, bit, addr);
-}
-
 static inline void mb_clear_bit(int bit, void *addr)
 {
 	addr = mb_correct_addr_and_bit(&bit, addr);
 	ext4_clear_bit(bit, addr);
 }
 
-static inline void mb_clear_bit_atomic(spinlock_t *lock, int bit, void *addr)
-{
-	addr = mb_correct_addr_and_bit(&bit, addr);
-	ext4_clear_bit_atomic(lock, bit, addr);
-}
-
 static inline int mb_find_next_zero_bit(void *addr, int max, int start)
 {
 	int fix = 0, ret, tmpmax;
@@ -448,7 +436,7 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
 
 	if (unlikely(e4b->bd_info->bb_bitmap == NULL))
 		return;
-	BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	for (i = 0; i < count; i++) {
 		if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) {
 			ext4_fsblk_t blocknr;
@@ -472,7 +460,7 @@ static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count)
 
 	if (unlikely(e4b->bd_info->bb_bitmap == NULL))
 		return;
-	BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
 	for (i = 0; i < count; i++) {
 		BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap));
 		mb_set_bit(first + i, e4b->bd_info->bb_bitmap);
@@ -739,6 +727,7 @@ static void ext4_mb_generate_buddy(struct super_block *sb,
 
 static int ext4_mb_init_cache(struct page *page, char *incore)
 {
+	ext4_group_t ngroups;
 	int blocksize;
 	int blocks_per_page;
 	int groups_per_page;
@@ -757,6 +746,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 
 	inode = page->mapping->host;
 	sb = inode->i_sb;
+	ngroups = ext4_get_groups_count(sb);
 	blocksize = 1 << inode->i_blkbits;
 	blocks_per_page = PAGE_CACHE_SIZE / blocksize;
 
@@ -780,7 +770,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 	for (i = 0; i < groups_per_page; i++) {
 		struct ext4_group_desc *desc;
 
-		if (first_group + i >= EXT4_SB(sb)->s_groups_count)
+		if (first_group + i >= ngroups)
 			break;
 
 		err = -EIO;
@@ -801,17 +791,17 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 			unlock_buffer(bh[i]);
 			continue;
 		}
-		spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+		ext4_lock_group(sb, first_group + i);
 		if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 			ext4_init_block_bitmap(sb, bh[i],
 						first_group + i, desc);
 			set_bitmap_uptodate(bh[i]);
 			set_buffer_uptodate(bh[i]);
-			spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+			ext4_unlock_group(sb, first_group + i);
 			unlock_buffer(bh[i]);
 			continue;
 		}
-		spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+		ext4_unlock_group(sb, first_group + i);
 		if (buffer_uptodate(bh[i])) {
 			/*
 			 * if not uninit if bh is uptodate,
@@ -852,7 +842,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
 		struct ext4_group_info *grinfo;
 
 		group = (first_block + i) >> 1;
-		if (group >= EXT4_SB(sb)->s_groups_count)
+		if (group >= ngroups)
 			break;
 
 		/*
@@ -1078,7 +1068,7 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
 	return 0;
 }
 
-static void mb_clear_bits(spinlock_t *lock, void *bm, int cur, int len)
+static void mb_clear_bits(void *bm, int cur, int len)
 {
 	__u32 *addr;
 
@@ -1091,15 +1081,12 @@ static void mb_clear_bits(spinlock_t *lock, void *bm, int cur, int len)
 			cur += 32;
 			continue;
 		}
-		if (lock)
-			mb_clear_bit_atomic(lock, cur, bm);
-		else
-			mb_clear_bit(cur, bm);
+		mb_clear_bit(cur, bm);
 		cur++;
 	}
 }
 
-static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len)
+static void mb_set_bits(void *bm, int cur, int len)
 {
 	__u32 *addr;
 
@@ -1112,10 +1099,7 @@ static void mb_set_bits(spinlock_t *lock, void *bm, int cur, int len)
 			cur += 32;
 			continue;
 		}
-		if (lock)
-			mb_set_bit_atomic(lock, cur, bm);
-		else
-			mb_set_bit(cur, bm);
+		mb_set_bit(cur, bm);
 		cur++;
 	}
 }
@@ -1131,7 +1115,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	struct super_block *sb = e4b->bd_sb;
 
 	BUG_ON(first + count > (sb->s_blocksize << 3));
-	BUG_ON(!ext4_is_group_locked(sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	mb_check_buddy(e4b);
 	mb_free_blocks_double(inode, e4b, first, count);
 
@@ -1212,7 +1196,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block,
 	int ord;
 	void *buddy;
 
-	BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
 	BUG_ON(ex == NULL);
 
 	buddy = mb_find_buddy(e4b, order, &max);
@@ -1276,7 +1260,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 
 	BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3));
 	BUG_ON(e4b->bd_group != ex->fe_group);
-	BUG_ON(!ext4_is_group_locked(e4b->bd_sb, e4b->bd_group));
+	assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
 	mb_check_buddy(e4b);
 	mb_mark_used_double(e4b, start, len);
 
@@ -1330,8 +1314,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 		e4b->bd_info->bb_counters[ord]++;
 	}
 
-	mb_set_bits(sb_bgl_lock(EXT4_SB(e4b->bd_sb), ex->fe_group),
-			EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
+	mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
 	mb_check_buddy(e4b);
 
 	return ret;
@@ -1726,7 +1709,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
 	unsigned free, fragments;
 	unsigned i, bits;
 	int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb));
-	struct ext4_group_desc *desc;
 	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
 
 	BUG_ON(cr < 0 || cr >= 4);
@@ -1742,10 +1724,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
 	switch (cr) {
 	case 0:
 		BUG_ON(ac->ac_2order == 0);
-		/* If this group is uninitialized, skip it initially */
-		desc = ext4_get_group_desc(ac->ac_sb, group, NULL);
-		if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
-			return 0;
 
 		/* Avoid using the first bg of a flexgroup for data files */
 		if ((ac->ac_flags & EXT4_MB_HINT_DATA) &&
@@ -1788,6 +1766,7 @@ int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group)
 	int block, pnum;
 	int blocks_per_page;
 	int groups_per_page;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t first_group;
 	struct ext4_group_info *grp;
 
@@ -1807,7 +1786,7 @@ int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group)
 	/* read all groups the page covers into the cache */
 	for (i = 0; i < groups_per_page; i++) {
 
-		if ((first_group + i) >= EXT4_SB(sb)->s_groups_count)
+		if ((first_group + i) >= ngroups)
 			break;
 		grp = ext4_get_group_info(sb, first_group + i);
 		/* take all groups write allocation
@@ -1945,8 +1924,7 @@ err:
 static noinline_for_stack int
 ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 {
-	ext4_group_t group;
-	ext4_group_t i;
+	ext4_group_t ngroups, group, i;
 	int cr;
 	int err = 0;
 	int bsbits;
@@ -1957,6 +1935,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 
 	sb = ac->ac_sb;
 	sbi = EXT4_SB(sb);
+	ngroups = ext4_get_groups_count(sb);
 	BUG_ON(ac->ac_status == AC_STATUS_FOUND);
 
 	/* first, try the goal */
@@ -2017,11 +1996,11 @@ repeat:
 		 */
 		group = ac->ac_g_ex.fe_group;
 
-		for (i = 0; i < EXT4_SB(sb)->s_groups_count; group++, i++) {
+		for (i = 0; i < ngroups; group++, i++) {
 			struct ext4_group_info *grp;
 			struct ext4_group_desc *desc;
 
-			if (group == EXT4_SB(sb)->s_groups_count)
+			if (group == ngroups)
 				group = 0;
 
 			/* quick check to skip empty groups */
@@ -2064,9 +2043,7 @@ repeat:
 
 			ac->ac_groups_scanned++;
 			desc = ext4_get_group_desc(sb, group, NULL);
-			if (cr == 0 || (desc->bg_flags &
-					cpu_to_le16(EXT4_BG_BLOCK_UNINIT) &&
-					ac->ac_2order != 0))
+			if (cr == 0)
 				ext4_mb_simple_scan_group(ac, &e4b);
 			else if (cr == 1 &&
 					ac->ac_g_ex.fe_len == sbi->s_stripe)
@@ -2315,12 +2292,10 @@ static struct file_operations ext4_mb_seq_history_fops = {
 static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
 {
 	struct super_block *sb = seq->private;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_group_t group;
 
-	if (*pos < 0 || *pos >= sbi->s_groups_count)
+	if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
 		return NULL;
-
 	group = *pos + 1;
 	return (void *) ((unsigned long) group);
 }
@@ -2328,11 +2303,10 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
 static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct super_block *sb = seq->private;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_group_t group;
 
 	++*pos;
-	if (*pos < 0 || *pos >= sbi->s_groups_count)
+	if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
 		return NULL;
 	group = *pos + 1;
 	return (void *) ((unsigned long) group);
@@ -2420,7 +2394,8 @@ static void ext4_mb_history_release(struct super_block *sb)
 
 	if (sbi->s_proc != NULL) {
 		remove_proc_entry("mb_groups", sbi->s_proc);
-		remove_proc_entry("mb_history", sbi->s_proc);
+		if (sbi->s_mb_history_max)
+			remove_proc_entry("mb_history", sbi->s_proc);
 	}
 	kfree(sbi->s_mb_history);
 }
@@ -2431,17 +2406,17 @@ static void ext4_mb_history_init(struct super_block *sb)
 	int i;
 
 	if (sbi->s_proc != NULL) {
-		proc_create_data("mb_history", S_IRUGO, sbi->s_proc,
-				 &ext4_mb_seq_history_fops, sb);
+		if (sbi->s_mb_history_max)
+			proc_create_data("mb_history", S_IRUGO, sbi->s_proc,
+					 &ext4_mb_seq_history_fops, sb);
 		proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
 				 &ext4_mb_seq_groups_fops, sb);
 	}
 
-	sbi->s_mb_history_max = 1000;
 	sbi->s_mb_history_cur = 0;
 	spin_lock_init(&sbi->s_mb_history_lock);
 	i = sbi->s_mb_history_max * sizeof(struct ext4_mb_history);
-	sbi->s_mb_history = kzalloc(i, GFP_KERNEL);
+	sbi->s_mb_history = i ? kzalloc(i, GFP_KERNEL) : NULL;
 	/* if we can't allocate history, then we simple won't use it */
 }
 
@@ -2451,7 +2426,7 @@ ext4_mb_store_history(struct ext4_allocation_context *ac)
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_mb_history h;
 
-	if (unlikely(sbi->s_mb_history == NULL))
+	if (sbi->s_mb_history == NULL)
 		return;
 
 	if (!(ac->ac_op & sbi->s_mb_history_filter))
@@ -2587,6 +2562,7 @@ void ext4_mb_update_group_info(struct ext4_group_info *grp, ext4_grpblk_t add)
 
 static int ext4_mb_init_backend(struct super_block *sb)
 {
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
 	int metalen;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2598,7 +2574,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
 	struct ext4_group_desc *desc;
 
 	/* This is the number of blocks used by GDT */
-	num_meta_group_infos = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) -
+	num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) -
 				1) >> EXT4_DESC_PER_BLOCK_BITS(sb);
 
 	/*
@@ -2644,7 +2620,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
 	for (i = 0; i < num_meta_group_infos; i++) {
 		if ((i + 1) == num_meta_group_infos)
 			metalen = sizeof(*meta_group_info) *
-				(sbi->s_groups_count -
+				(ngroups -
 					(i << EXT4_DESC_PER_BLOCK_BITS(sb)));
 		meta_group_info = kmalloc(metalen, GFP_KERNEL);
 		if (meta_group_info == NULL) {
@@ -2655,7 +2631,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
 		sbi->s_group_info[i] = meta_group_info;
 	}
 
-	for (i = 0; i < sbi->s_groups_count; i++) {
+	for (i = 0; i < ngroups; i++) {
 		desc = ext4_get_group_desc(sb, i, NULL);
 		if (desc == NULL) {
 			printk(KERN_ERR
@@ -2761,7 +2737,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	return 0;
 }
 
-/* need to called with ext4 group lock (ext4_lock_group) */
+/* need to called with the ext4 group lock held */
 static void ext4_mb_cleanup_pa(struct ext4_group_info *grp)
 {
 	struct ext4_prealloc_space *pa;
@@ -2781,13 +2757,14 @@ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp)
 
 int ext4_mb_release(struct super_block *sb)
 {
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
 	int num_meta_group_infos;
 	struct ext4_group_info *grinfo;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (sbi->s_group_info) {
-		for (i = 0; i < sbi->s_groups_count; i++) {
+		for (i = 0; i < ngroups; i++) {
 			grinfo = ext4_get_group_info(sb, i);
 #ifdef DOUBLE_CHECK
 			kfree(grinfo->bb_bitmap);
@@ -2797,7 +2774,7 @@ int ext4_mb_release(struct super_block *sb)
 			ext4_unlock_group(sb, i);
 			kfree(grinfo);
 		}
-		num_meta_group_infos = (sbi->s_groups_count +
+		num_meta_group_infos = (ngroups +
 				EXT4_DESC_PER_BLOCK(sb) - 1) >>
 			EXT4_DESC_PER_BLOCK_BITS(sb);
 		for (i = 0; i < num_meta_group_infos; i++)
@@ -2984,27 +2961,25 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		+ le32_to_cpu(es->s_first_data_block);
 
 	len = ac->ac_b_ex.fe_len;
-	if (in_range(ext4_block_bitmap(sb, gdp), block, len) ||
-	    in_range(ext4_inode_bitmap(sb, gdp), block, len) ||
-	    in_range(block, ext4_inode_table(sb, gdp),
-		     EXT4_SB(sb)->s_itb_per_group) ||
-	    in_range(block + len - 1, ext4_inode_table(sb, gdp),
-		     EXT4_SB(sb)->s_itb_per_group)) {
+	if (!ext4_data_block_valid(sbi, block, len)) {
 		ext4_error(sb, __func__,
-			   "Allocating block %llu in system zone of %d group\n",
-			   block, ac->ac_b_ex.fe_group);
+			   "Allocating blocks %llu-%llu which overlap "
+			   "fs metadata\n", block, block+len);
 		/* File system mounted not to panic on error
 		 * Fix the bitmap and repeat the block allocation
 		 * We leak some of the blocks here.
 		 */
-		mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group),
-				bitmap_bh->b_data, ac->ac_b_ex.fe_start,
-				ac->ac_b_ex.fe_len);
+		ext4_lock_group(sb, ac->ac_b_ex.fe_group);
+		mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+			    ac->ac_b_ex.fe_len);
+		ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
 		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
 		if (!err)
 			err = -EAGAIN;
 		goto out_err;
 	}
+
+	ext4_lock_group(sb, ac->ac_b_ex.fe_group);
 #ifdef AGGRESSIVE_CHECK
 	{
 		int i;
@@ -3014,9 +2989,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		}
 	}
 #endif
-	spin_lock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
-	mb_set_bits(NULL, bitmap_bh->b_data,
-				ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len);
+	mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,ac->ac_b_ex.fe_len);
 	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 		ext4_free_blks_set(sb, gdp,
@@ -3026,7 +2999,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	len = ext4_free_blks_count(sb, gdp) - ac->ac_b_ex.fe_len;
 	ext4_free_blks_set(sb, gdp, len);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
-	spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
+
+	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
 	percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
 	/*
 	 * Now reduce the dirty block count also. Should not go negative
@@ -3459,7 +3433,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
  * the function goes through all block freed in the group
  * but not yet committed and marks them used in in-core bitmap.
  * buddy must be generated from this bitmap
- * Need to be called with ext4 group lock (ext4_lock_group)
+ * Need to be called with the ext4 group lock held
  */
 static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 						ext4_group_t group)
@@ -3473,9 +3447,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 
 	while (n) {
 		entry = rb_entry(n, struct ext4_free_data, node);
-		mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group),
-				bitmap, entry->start_blk,
-				entry->count);
+		mb_set_bits(bitmap, entry->start_blk, entry->count);
 		n = rb_next(n);
 	}
 	return;
@@ -3484,7 +3456,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 /*
  * the function goes through all preallocation in this group and marks them
  * used in in-core bitmap. buddy must be generated from this bitmap
- * Need to be called with ext4 group lock (ext4_lock_group)
+ * Need to be called with ext4 group lock held
  */
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group)
@@ -3516,8 +3488,7 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 		if (unlikely(len == 0))
 			continue;
 		BUG_ON(groupnr != group);
-		mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group),
-						bitmap, start, len);
+		mb_set_bits(bitmap, start, len);
 		preallocated += len;
 		count++;
 	}
@@ -4121,7 +4092,7 @@ static void ext4_mb_return_to_preallocation(struct inode *inode,
 static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 {
 	struct super_block *sb = ac->ac_sb;
-	ext4_group_t i;
+	ext4_group_t ngroups, i;
 
 	printk(KERN_ERR "EXT4-fs: Can't allocate:"
 			" Allocation context details:\n");
@@ -4145,7 +4116,8 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 	printk(KERN_ERR "EXT4-fs: %lu scanned, %d found\n", ac->ac_ex_scanned,
 		ac->ac_found);
 	printk(KERN_ERR "EXT4-fs: groups: \n");
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+	ngroups = ext4_get_groups_count(sb);
+	for (i = 0; i < ngroups; i++) {
 		struct ext4_group_info *grp = ext4_get_group_info(sb, i);
 		struct ext4_prealloc_space *pa;
 		ext4_grpblk_t start;
@@ -4469,13 +4441,13 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 
 static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
 {
-	ext4_group_t i;
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
 	int ret;
 	int freed = 0;
 
 	trace_mark(ext4_mb_discard_preallocations, "dev %s needed %d",
 		   sb->s_id, needed);
-	for (i = 0; i < EXT4_SB(sb)->s_groups_count && needed > 0; i++) {
+	for (i = 0; i < ngroups && needed > 0; i++) {
 		ret = ext4_mb_discard_group_preallocations(sb, i, needed);
 		freed += ret;
 		needed -= ret;
@@ -4859,29 +4831,25 @@ do_more:
 		new_entry->group  = block_group;
 		new_entry->count = count;
 		new_entry->t_tid = handle->h_transaction->t_tid;
+
 		ext4_lock_group(sb, block_group);
-		mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
-				bit, count);
+		mb_clear_bits(bitmap_bh->b_data, bit, count);
 		ext4_mb_free_metadata(handle, &e4b, new_entry);
-		ext4_unlock_group(sb, block_group);
 	} else {
-		ext4_lock_group(sb, block_group);
 		/* need to update group_info->bb_free and bitmap
 		 * with group lock held. generate_buddy look at
 		 * them with group lock_held
 		 */
-		mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
-				bit, count);
+		ext4_lock_group(sb, block_group);
+		mb_clear_bits(bitmap_bh->b_data, bit, count);
 		mb_free_blocks(inode, &e4b, bit, count);
 		ext4_mb_return_to_preallocation(inode, &e4b, block, count);
-		ext4_unlock_group(sb, block_group);
 	}
 
-	spin_lock(sb_bgl_lock(sbi, block_group));
 	ret = ext4_free_blks_count(sb, gdp) + count;
 	ext4_free_blks_set(sb, gdp, ret);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
-	spin_unlock(sb_bgl_lock(sbi, block_group));
+	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeblocks_counter, count);
 
 	if (sbi->s_log_groups_per_flex) {
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index dd9e6cd5f6cf..75e34f69215b 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -23,7 +23,6 @@
 #include <linux/mutex.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
-#include "group.h"
 
 /*
  * with AGGRESSIVE_CHECK allocator runs consistency checks over
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 22098e1cd085..07eb6649e4fa 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -37,7 +37,6 @@
 #include "ext4.h"
 #include "ext4_jbd2.h"
 
-#include "namei.h"
 #include "xattr.h"
 #include "acl.h"
 
@@ -750,7 +749,7 @@ static int dx_make_map(struct ext4_dir_entry_2 *de, unsigned blocksize,
 			ext4fs_dirhash(de->name, de->name_len, &h);
 			map_tail--;
 			map_tail->hash = h.hash;
-			map_tail->offs = (u16) ((char *) de - base);
+			map_tail->offs = ((char *) de - base)>>2;
 			map_tail->size = le16_to_cpu(de->rec_len);
 			count++;
 			cond_resched();
@@ -1148,7 +1147,8 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count,
 	unsigned rec_len = 0;
 
 	while (count--) {
-		struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + map->offs);
+		struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) 
+						(from + (map->offs<<2));
 		rec_len = EXT4_DIR_REC_LEN(de->name_len);
 		memcpy (to, de, rec_len);
 		((struct ext4_dir_entry_2 *) to)->rec_len =
@@ -1997,7 +1997,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	if (!ext4_handle_valid(handle))
 		return 0;
 
-	lock_super(sb);
+	mutex_lock(&EXT4_SB(sb)->s_orphan_lock);
 	if (!list_empty(&EXT4_I(inode)->i_orphan))
 		goto out_unlock;
 
@@ -2006,9 +2006,13 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 
 	/* @@@ FIXME: Observation from aviro:
 	 * I think I can trigger J_ASSERT in ext4_orphan_add().  We block
-	 * here (on lock_super()), so race with ext4_link() which might bump
+	 * here (on s_orphan_lock), so race with ext4_link() which might bump
 	 * ->i_nlink. For, say it, character device. Not a regular file,
 	 * not a directory, not a symlink and ->i_nlink > 0.
+	 *
+	 * tytso, 4/25/2009: I'm not sure how that could happen;
+	 * shouldn't the fs core protect us from these sort of
+	 * unlink()/link() races?
 	 */
 	J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 		  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
@@ -2045,7 +2049,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	jbd_debug(4, "orphan inode %lu will point to %d\n",
 			inode->i_ino, NEXT_ORPHAN(inode));
 out_unlock:
-	unlock_super(sb);
+	mutex_unlock(&EXT4_SB(sb)->s_orphan_lock);
 	ext4_std_error(inode->i_sb, err);
 	return err;
 }
@@ -2066,11 +2070,9 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 	if (!ext4_handle_valid(handle))
 		return 0;
 
-	lock_super(inode->i_sb);
-	if (list_empty(&ei->i_orphan)) {
-		unlock_super(inode->i_sb);
-		return 0;
-	}
+	mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
+	if (list_empty(&ei->i_orphan))
+		goto out;
 
 	ino_next = NEXT_ORPHAN(inode);
 	prev = ei->i_orphan.prev;
@@ -2120,7 +2122,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 out_err:
 	ext4_std_error(inode->i_sb, err);
 out:
-	unlock_super(inode->i_sb);
+	mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
 	return err;
 
 out_brelse:
@@ -2533,6 +2535,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 	.removexattr	= generic_removexattr,
 #endif
 	.permission	= ext4_permission,
+	.fiemap         = ext4_fiemap,
 };
 
 const struct inode_operations ext4_special_inode_operations = {
diff --git a/fs/ext4/namei.h b/fs/ext4/namei.h
deleted file mode 100644
index 5e4dfff36a00..000000000000
--- a/fs/ext4/namei.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/*  linux/fs/ext4/namei.h
- *
- * Copyright (C) 2005 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
-*/
-
-extern struct dentry *ext4_get_parent(struct dentry *child);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 546c7dd869e1..27eb289eea37 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -15,7 +15,6 @@
 #include <linux/slab.h>
 
 #include "ext4_jbd2.h"
-#include "group.h"
 
 #define outside(b, first, last)	((b) < (first) || (b) >= (last))
 #define inside(b, first, last)	((b) >= (first) && (b) < (last))
@@ -193,7 +192,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_resize_lock);
 	if (input->group != sbi->s_groups_count) {
 		err = -EBUSY;
 		goto exit_journal;
@@ -302,7 +301,7 @@ exit_bh:
 	brelse(bh);
 
 exit_journal:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_resize_lock);
 	if ((err2 = ext4_journal_stop(handle)) && !err)
 		err = err2;
 
@@ -643,11 +642,12 @@ exit_free:
  * important part is that the new block and inode counts are in the backup
  * superblocks, and the location of the new group metadata in the GDT backups.
  *
- * We do not need lock_super() for this, because these blocks are not
- * otherwise touched by the filesystem code when it is mounted.  We don't
- * need to worry about last changing from sbi->s_groups_count, because the
- * worst that can happen is that we do not copy the full number of backups
- * at this time.  The resize which changed s_groups_count will backup again.
+ * We do not need take the s_resize_lock for this, because these
+ * blocks are not otherwise touched by the filesystem code when it is
+ * mounted.  We don't need to worry about last changing from
+ * sbi->s_groups_count, because the worst that can happen is that we
+ * do not copy the full number of backups at this time.  The resize
+ * which changed s_groups_count will backup again.
  */
 static void update_backups(struct super_block *sb,
 			   int blk_off, char *data, int size)
@@ -809,7 +809,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 		goto exit_put;
 	}
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_resize_lock);
 	if (input->group != sbi->s_groups_count) {
 		ext4_warning(sb, __func__,
 			     "multiple resizers run on filesystem!");
@@ -840,7 +840,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
         /*
          * OK, now we've set up the new group.  Time to make it active.
          *
-         * Current kernels don't lock all allocations via lock_super(),
+         * We do not lock all allocations via s_resize_lock
          * so we have to be safe wrt. concurrent accesses the group
          * data.  So we need to be careful to set all of the relevant
          * group descriptor data etc. *before* we enable the group.
@@ -900,12 +900,12 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	 *
 	 * The precise rules we use are:
 	 *
-	 * * Writers of s_groups_count *must* hold lock_super
+	 * * Writers of s_groups_count *must* hold s_resize_lock
 	 * AND
 	 * * Writers must perform a smp_wmb() after updating all dependent
 	 *   data and before modifying the groups count
 	 *
-	 * * Readers must hold lock_super() over the access
+	 * * Readers must hold s_resize_lock over the access
 	 * OR
 	 * * Readers must perform an smp_rmb() after reading the groups count
 	 *   and before reading any dependent data.
@@ -948,7 +948,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	sb->s_dirt = 1;
 
 exit_journal:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_resize_lock);
 	if ((err2 = ext4_journal_stop(handle)) && !err)
 		err = err2;
 	if (!err) {
@@ -986,7 +986,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 
 	/* We don't need to worry about locking wrt other resizers just
 	 * yet: we're going to revalidate es->s_blocks_count after
-	 * taking lock_super() below. */
+	 * taking the s_resize_lock below. */
 	o_blocks_count = ext4_blocks_count(es);
 	o_groups_count = EXT4_SB(sb)->s_groups_count;
 
@@ -1056,11 +1056,11 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 		goto exit_put;
 	}
 
-	lock_super(sb);
+	mutex_lock(&EXT4_SB(sb)->s_resize_lock);
 	if (o_blocks_count != ext4_blocks_count(es)) {
 		ext4_warning(sb, __func__,
 			     "multiple resizers run on filesystem!");
-		unlock_super(sb);
+		mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
 		ext4_journal_stop(handle);
 		err = -EBUSY;
 		goto exit_put;
@@ -1070,14 +1070,14 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 						 EXT4_SB(sb)->s_sbh))) {
 		ext4_warning(sb, __func__,
 			     "error %d on journal write access", err);
-		unlock_super(sb);
+		mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
 		ext4_journal_stop(handle);
 		goto exit_put;
 	}
 	ext4_blocks_count_set(es, o_blocks_count + add);
 	ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
 	sb->s_dirt = 1;
-	unlock_super(sb);
+	mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
 	ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
 		   o_blocks_count + add);
 	/* We add the blocks to the bitmap and set the group need init bit */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2958f4e6f222..012c4251397e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -20,6 +20,7 @@
 #include <linux/string.h>
 #include <linux/fs.h>
 #include <linux/time.h>
+#include <linux/vmalloc.h>
 #include <linux/jbd2.h>
 #include <linux/slab.h>
 #include <linux/init.h>
@@ -45,16 +46,20 @@
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "namei.h"
-#include "group.h"
+
+static int default_mb_history_length = 1000;
+
+module_param_named(default_mb_history_length, default_mb_history_length,
+		   int, 0644);
+MODULE_PARM_DESC(default_mb_history_length,
+		 "Default number of entries saved for mb_history");
 
 struct proc_dir_entry *ext4_proc_root;
 static struct kset *ext4_kset;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
-static int ext4_commit_super(struct super_block *sb,
-			      struct ext4_super_block *es, int sync);
+static int ext4_commit_super(struct super_block *sb, int sync);
 static void ext4_mark_recovery_complete(struct super_block *sb,
 					struct ext4_super_block *es);
 static void ext4_clear_journal_err(struct super_block *sb,
@@ -74,7 +79,7 @@ ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
 {
 	return le32_to_cpu(bg->bg_block_bitmap_lo) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
-		(ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
+		 (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
 }
 
 ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
@@ -82,7 +87,7 @@ ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
 {
 	return le32_to_cpu(bg->bg_inode_bitmap_lo) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
-		(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
+		 (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
 }
 
 ext4_fsblk_t ext4_inode_table(struct super_block *sb,
@@ -90,7 +95,7 @@ ext4_fsblk_t ext4_inode_table(struct super_block *sb,
 {
 	return le32_to_cpu(bg->bg_inode_table_lo) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
-		(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
+		 (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
 }
 
 __u32 ext4_free_blks_count(struct super_block *sb,
@@ -98,7 +103,7 @@ __u32 ext4_free_blks_count(struct super_block *sb,
 {
 	return le16_to_cpu(bg->bg_free_blocks_count_lo) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
-		(__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
+		 (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
 }
 
 __u32 ext4_free_inodes_count(struct super_block *sb,
@@ -106,7 +111,7 @@ __u32 ext4_free_inodes_count(struct super_block *sb,
 {
 	return le16_to_cpu(bg->bg_free_inodes_count_lo) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
-		(__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
+		 (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
 }
 
 __u32 ext4_used_dirs_count(struct super_block *sb,
@@ -114,7 +119,7 @@ __u32 ext4_used_dirs_count(struct super_block *sb,
 {
 	return le16_to_cpu(bg->bg_used_dirs_count_lo) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
-		(__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
+		 (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
 }
 
 __u32 ext4_itable_unused_count(struct super_block *sb,
@@ -122,7 +127,7 @@ __u32 ext4_itable_unused_count(struct super_block *sb,
 {
 	return le16_to_cpu(bg->bg_itable_unused_lo) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
-		(__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
+		 (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
 }
 
 void ext4_block_bitmap_set(struct super_block *sb,
@@ -202,8 +207,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
 	journal = EXT4_SB(sb)->s_journal;
 	if (journal) {
 		if (is_journal_aborted(journal)) {
-			ext4_abort(sb, __func__,
-				   "Detected aborted journal");
+			ext4_abort(sb, __func__, "Detected aborted journal");
 			return ERR_PTR(-EROFS);
 		}
 		return jbd2_journal_start(journal, nblocks);
@@ -302,10 +306,10 @@ static void ext4_handle_error(struct super_block *sb)
 			jbd2_journal_abort(journal, -EIO);
 	}
 	if (test_opt(sb, ERRORS_RO)) {
-		printk(KERN_CRIT "Remounting filesystem read-only\n");
+		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		sb->s_flags |= MS_RDONLY;
 	}
-	ext4_commit_super(sb, es, 1);
+	ext4_commit_super(sb, 1);
 	if (test_opt(sb, ERRORS_PANIC))
 		panic("EXT4-fs (device %s): panic forced after error\n",
 			sb->s_id);
@@ -395,8 +399,6 @@ void ext4_abort(struct super_block *sb, const char *function,
 {
 	va_list args;
 
-	printk(KERN_CRIT "ext4_abort called.\n");
-
 	va_start(args, fmt);
 	printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function);
 	vprintk(fmt, args);
@@ -409,7 +411,7 @@ void ext4_abort(struct super_block *sb, const char *function,
 	if (sb->s_flags & MS_RDONLY)
 		return;
 
-	printk(KERN_CRIT "Remounting filesystem read-only\n");
+	ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 	sb->s_flags |= MS_RDONLY;
 	EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
@@ -417,6 +419,18 @@ void ext4_abort(struct super_block *sb, const char *function,
 		jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 }
 
+void ext4_msg (struct super_block * sb, const char *prefix,
+		   const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	printk("%sEXT4-fs (%s): ", prefix, sb->s_id);
+	vprintk(fmt, args);
+	printk("\n");
+	va_end(args);
+}
+
 void ext4_warning(struct super_block *sb, const char *function,
 		  const char *fmt, ...)
 {
@@ -431,7 +445,7 @@ void ext4_warning(struct super_block *sb, const char *function,
 }
 
 void ext4_grp_locked_error(struct super_block *sb, ext4_group_t grp,
-				const char *function, const char *fmt, ...)
+			   const char *function, const char *fmt, ...)
 __releases(bitlock)
 __acquires(bitlock)
 {
@@ -447,7 +461,7 @@ __acquires(bitlock)
 	if (test_opt(sb, ERRORS_CONT)) {
 		EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 		es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-		ext4_commit_super(sb, es, 0);
+		ext4_commit_super(sb, 0);
 		return;
 	}
 	ext4_unlock_group(sb, grp);
@@ -467,7 +481,6 @@ __acquires(bitlock)
 	return;
 }
 
-
 void ext4_update_dynamic_rev(struct super_block *sb)
 {
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
@@ -496,7 +509,7 @@ void ext4_update_dynamic_rev(struct super_block *sb)
 /*
  * Open the external journal device
  */
-static struct block_device *ext4_blkdev_get(dev_t dev)
+static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
 {
 	struct block_device *bdev;
 	char b[BDEVNAME_SIZE];
@@ -507,7 +520,7 @@ static struct block_device *ext4_blkdev_get(dev_t dev)
 	return bdev;
 
 fail:
-	printk(KERN_ERR "EXT4-fs: failed to open journal device %s: %ld\n",
+	ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld",
 			__bdevname(dev, b), PTR_ERR(bdev));
 	return NULL;
 }
@@ -543,8 +556,8 @@ static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi)
 {
 	struct list_head *l;
 
-	printk(KERN_ERR "sb orphan head is %d\n",
-	       le32_to_cpu(sbi->s_es->s_last_orphan));
+	ext4_msg(sb, KERN_ERR, "sb orphan head is %d",
+		 le32_to_cpu(sbi->s_es->s_last_orphan));
 
 	printk(KERN_ERR "sb_info orphan list:\n");
 	list_for_each(l, &sbi->s_orphan) {
@@ -563,6 +576,12 @@ static void ext4_put_super(struct super_block *sb)
 	struct ext4_super_block *es = sbi->s_es;
 	int i, err;
 
+	lock_super(sb);
+	lock_kernel();
+	if (sb->s_dirt)
+		ext4_commit_super(sb, 1);
+
+	ext4_release_system_zone(sb);
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
 	ext4_xattr_put_super(sb);
@@ -576,7 +595,7 @@ static void ext4_put_super(struct super_block *sb)
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
-		ext4_commit_super(sb, es, 1);
+		ext4_commit_super(sb, 1);
 	}
 	if (sbi->s_proc) {
 		remove_proc_entry(sb->s_id, ext4_proc_root);
@@ -586,7 +605,10 @@ static void ext4_put_super(struct super_block *sb)
 	for (i = 0; i < sbi->s_gdb_count; i++)
 		brelse(sbi->s_group_desc[i]);
 	kfree(sbi->s_group_desc);
-	kfree(sbi->s_flex_groups);
+	if (is_vmalloc_addr(sbi->s_flex_groups))
+		vfree(sbi->s_flex_groups);
+	else
+		kfree(sbi->s_flex_groups);
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -625,11 +647,8 @@ static void ext4_put_super(struct super_block *sb)
 	unlock_super(sb);
 	kobject_put(&sbi->s_kobj);
 	wait_for_completion(&sbi->s_kobj_unregister);
-	lock_super(sb);
-	lock_kernel();
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
-	return;
 }
 
 static struct kmem_cache *ext4_inode_cachep;
@@ -644,6 +663,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
 	if (!ei)
 		return NULL;
+
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	ei->i_acl = EXT4_ACL_NOT_CACHED;
 	ei->i_default_acl = EXT4_ACL_NOT_CACHED;
@@ -664,14 +684,16 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_allocated_meta_blocks = 0;
 	ei->i_delalloc_reserved_flag = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));
+
 	return &ei->vfs_inode;
 }
 
 static void ext4_destroy_inode(struct inode *inode)
 {
 	if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
-		printk("EXT4 Inode %p: orphan list check failed!\n",
-			EXT4_I(inode));
+		ext4_msg(inode->i_sb, KERN_ERR,
+			 "Inode %lu (%p): orphan list check failed!",
+			 inode->i_ino, EXT4_I(inode));
 		print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4,
 				EXT4_I(inode), sizeof(struct ext4_inode_info),
 				true);
@@ -870,12 +892,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",noauto_da_alloc");
 
 	ext4_show_quota_options(seq, sb);
+
 	return 0;
 }
 
-
 static struct inode *ext4_nfs_get_inode(struct super_block *sb,
-		u64 ino, u32 generation)
+					u64 ino, u32 generation)
 {
 	struct inode *inode;
 
@@ -904,14 +926,14 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb,
 }
 
 static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
+					int fh_len, int fh_type)
 {
 	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
 				    ext4_nfs_get_inode);
 }
 
 static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
+					int fh_len, int fh_type)
 {
 	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
 				    ext4_nfs_get_inode);
@@ -923,7 +945,8 @@ static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
  * which would prevent try_to_free_buffers() from freeing them, we must use
  * jbd2 layer's try_to_free_buffers() function to release them.
  */
-static int bdev_try_to_free_page(struct super_block *sb, struct page *page, gfp_t wait)
+static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
+				 gfp_t wait)
 {
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 
@@ -992,7 +1015,6 @@ static const struct super_operations ext4_sops = {
 	.dirty_inode	= ext4_dirty_inode,
 	.delete_inode	= ext4_delete_inode,
 	.put_super	= ext4_put_super,
-	.write_super	= ext4_write_super,
 	.sync_fs	= ext4_sync_fs,
 	.freeze_fs	= ext4_freeze,
 	.unfreeze_fs	= ext4_unfreeze,
@@ -1007,6 +1029,25 @@ static const struct super_operations ext4_sops = {
 	.bdev_try_to_free_page = bdev_try_to_free_page,
 };
 
+static const struct super_operations ext4_nojournal_sops = {
+	.alloc_inode	= ext4_alloc_inode,
+	.destroy_inode	= ext4_destroy_inode,
+	.write_inode	= ext4_write_inode,
+	.dirty_inode	= ext4_dirty_inode,
+	.delete_inode	= ext4_delete_inode,
+	.write_super	= ext4_write_super,
+	.put_super	= ext4_put_super,
+	.statfs		= ext4_statfs,
+	.remount_fs	= ext4_remount,
+	.clear_inode	= ext4_clear_inode,
+	.show_options	= ext4_show_options,
+#ifdef CONFIG_QUOTA
+	.quota_read	= ext4_quota_read,
+	.quota_write	= ext4_quota_write,
+#endif
+	.bdev_try_to_free_page = bdev_try_to_free_page,
+};
+
 static const struct export_operations ext4_export_ops = {
 	.fh_to_dentry = ext4_fh_to_dentry,
 	.fh_to_parent = ext4_fh_to_parent,
@@ -1023,12 +1064,13 @@ enum {
 	Opt_journal_update, Opt_journal_dev,
 	Opt_journal_checksum, Opt_journal_async_commit,
 	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
-	Opt_data_err_abort, Opt_data_err_ignore,
+	Opt_data_err_abort, Opt_data_err_ignore, Opt_mb_history_length,
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
 	Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize,
 	Opt_usrquota, Opt_grpquota, Opt_i_version,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc,
+	Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio
 };
 
@@ -1069,6 +1111,7 @@ static const match_table_t tokens = {
 	{Opt_data_writeback, "data=writeback"},
 	{Opt_data_err_abort, "data_err=abort"},
 	{Opt_data_err_ignore, "data_err=ignore"},
+	{Opt_mb_history_length, "mb_history_length=%u"},
 	{Opt_offusrjquota, "usrjquota="},
 	{Opt_usrjquota, "usrjquota=%s"},
 	{Opt_offgrpjquota, "grpjquota="},
@@ -1087,6 +1130,8 @@ static const match_table_t tokens = {
 	{Opt_resize, "resize"},
 	{Opt_delalloc, "delalloc"},
 	{Opt_nodelalloc, "nodelalloc"},
+	{Opt_block_validity, "block_validity"},
+	{Opt_noblock_validity, "noblock_validity"},
 	{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
 	{Opt_journal_ioprio, "journal_ioprio=%u"},
 	{Opt_auto_da_alloc, "auto_da_alloc=%u"},
@@ -1102,8 +1147,9 @@ static ext4_fsblk_t get_sb_block(void **data)
 
 	if (!options || strncmp(options, "sb=", 3) != 0)
 		return 1;	/* Default location */
+
 	options += 3;
-	/*todo: use simple_strtoll with >32bit ext4 */
+	/* TODO: use simple_strtoll with >32bit ext4 */
 	sb_block = simple_strtoul(options, &options, 0);
 	if (*options && *options != ',') {
 		printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n",
@@ -1113,6 +1159,7 @@ static ext4_fsblk_t get_sb_block(void **data)
 	if (*options == ',')
 		options++;
 	*data = (void *) options;
+
 	return sb_block;
 }
 
@@ -1206,8 +1253,7 @@ static int parse_options(char *options, struct super_block *sb,
 #else
 		case Opt_user_xattr:
 		case Opt_nouser_xattr:
-			printk(KERN_ERR "EXT4 (no)user_xattr options "
-			       "not supported\n");
+			ext4_msg(sb, KERN_ERR, "(no)user_xattr options not supported");
 			break;
 #endif
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
@@ -1220,8 +1266,7 @@ static int parse_options(char *options, struct super_block *sb,
 #else
 		case Opt_acl:
 		case Opt_noacl:
-			printk(KERN_ERR "EXT4 (no)acl options "
-			       "not supported\n");
+			ext4_msg(sb, KERN_ERR, "(no)acl options not supported");
 			break;
 #endif
 		case Opt_journal_update:
@@ -1231,16 +1276,16 @@ static int parse_options(char *options, struct super_block *sb,
 			   user to specify an existing inode to be the
 			   journal file. */
 			if (is_remount) {
-				printk(KERN_ERR "EXT4-fs: cannot specify "
-				       "journal on remount\n");
+				ext4_msg(sb, KERN_ERR,
+					 "Cannot specify journal on remount");
 				return 0;
 			}
 			set_opt(sbi->s_mount_opt, UPDATE_JOURNAL);
 			break;
 		case Opt_journal_dev:
 			if (is_remount) {
-				printk(KERN_ERR "EXT4-fs: cannot specify "
-				       "journal on remount\n");
+				ext4_msg(sb, KERN_ERR,
+					"Cannot specify journal on remount");
 				return 0;
 			}
 			if (match_int(&args[0], &option))
@@ -1294,9 +1339,8 @@ static int parse_options(char *options, struct super_block *sb,
 			if (is_remount) {
 				if ((sbi->s_mount_opt & EXT4_MOUNT_DATA_FLAGS)
 						!= data_opt) {
-					printk(KERN_ERR
-						"EXT4-fs: cannot change data "
-						"mode on remount\n");
+					ext4_msg(sb, KERN_ERR,
+						"Cannot change data mode on remount");
 					return 0;
 				}
 			} else {
@@ -1310,6 +1354,13 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_data_err_ignore:
 			clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
 			break;
+		case Opt_mb_history_length:
+			if (match_int(&args[0], &option))
+				return 0;
+			if (option < 0)
+				return 0;
+			sbi->s_mb_history_max = option;
+			break;
 #ifdef CONFIG_QUOTA
 		case Opt_usrjquota:
 			qtype = USRQUOTA;
@@ -1319,31 +1370,31 @@ static int parse_options(char *options, struct super_block *sb,
 set_qf_name:
 			if (sb_any_quota_loaded(sb) &&
 			    !sbi->s_qf_names[qtype]) {
-				printk(KERN_ERR
-				       "EXT4-fs: Cannot change journaled "
-				       "quota options when quota turned on.\n");
+				ext4_msg(sb, KERN_ERR,
+				       "Cannot change journaled "
+				       "quota options when quota turned on");
 				return 0;
 			}
 			qname = match_strdup(&args[0]);
 			if (!qname) {
-				printk(KERN_ERR
-					"EXT4-fs: not enough memory for "
-					"storing quotafile name.\n");
+				ext4_msg(sb, KERN_ERR,
+					"Not enough memory for "
+					"storing quotafile name");
 				return 0;
 			}
 			if (sbi->s_qf_names[qtype] &&
 			    strcmp(sbi->s_qf_names[qtype], qname)) {
-				printk(KERN_ERR
-					"EXT4-fs: %s quota file already "
-					"specified.\n", QTYPE2NAME(qtype));
+				ext4_msg(sb, KERN_ERR,
+					"%s quota file already "
+					"specified", QTYPE2NAME(qtype));
 				kfree(qname);
 				return 0;
 			}
 			sbi->s_qf_names[qtype] = qname;
 			if (strchr(sbi->s_qf_names[qtype], '/')) {
-				printk(KERN_ERR
-					"EXT4-fs: quotafile must be on "
-					"filesystem root.\n");
+				ext4_msg(sb, KERN_ERR,
+					"quotafile must be on "
+					"filesystem root");
 				kfree(sbi->s_qf_names[qtype]);
 				sbi->s_qf_names[qtype] = NULL;
 				return 0;
@@ -1358,9 +1409,9 @@ set_qf_name:
 clear_qf_name:
 			if (sb_any_quota_loaded(sb) &&
 			    sbi->s_qf_names[qtype]) {
-				printk(KERN_ERR "EXT4-fs: Cannot change "
+				ext4_msg(sb, KERN_ERR, "Cannot change "
 					"journaled quota options when "
-					"quota turned on.\n");
+					"quota turned on");
 				return 0;
 			}
 			/*
@@ -1377,9 +1428,9 @@ clear_qf_name:
 set_qf_format:
 			if (sb_any_quota_loaded(sb) &&
 			    sbi->s_jquota_fmt != qfmt) {
-				printk(KERN_ERR "EXT4-fs: Cannot change "
+				ext4_msg(sb, KERN_ERR, "Cannot change "
 					"journaled quota options when "
-					"quota turned on.\n");
+					"quota turned on");
 				return 0;
 			}
 			sbi->s_jquota_fmt = qfmt;
@@ -1395,8 +1446,8 @@ set_qf_format:
 			break;
 		case Opt_noquota:
 			if (sb_any_quota_loaded(sb)) {
-				printk(KERN_ERR "EXT4-fs: Cannot change quota "
-					"options when quota turned on.\n");
+				ext4_msg(sb, KERN_ERR, "Cannot change quota "
+					"options when quota turned on");
 				return 0;
 			}
 			clear_opt(sbi->s_mount_opt, QUOTA);
@@ -1407,8 +1458,8 @@ set_qf_format:
 		case Opt_quota:
 		case Opt_usrquota:
 		case Opt_grpquota:
-			printk(KERN_ERR
-				"EXT4-fs: quota options not supported.\n");
+			ext4_msg(sb, KERN_ERR,
+				"quota options not supported");
 			break;
 		case Opt_usrjquota:
 		case Opt_grpjquota:
@@ -1416,9 +1467,8 @@ set_qf_format:
 		case Opt_offgrpjquota:
 		case Opt_jqfmt_vfsold:
 		case Opt_jqfmt_vfsv0:
-			printk(KERN_ERR
-				"EXT4-fs: journaled quota options not "
-				"supported.\n");
+			ext4_msg(sb, KERN_ERR,
+				"journaled quota options not supported");
 			break;
 		case Opt_noquota:
 			break;
@@ -1443,8 +1493,9 @@ set_qf_format:
 			break;
 		case Opt_resize:
 			if (!is_remount) {
-				printk("EXT4-fs: resize option only available "
-					"for remount\n");
+				ext4_msg(sb, KERN_ERR,
+					"resize option only available "
+					"for remount");
 				return 0;
 			}
 			if (match_int(&args[0], &option) != 0)
@@ -1474,14 +1525,21 @@ set_qf_format:
 		case Opt_delalloc:
 			set_opt(sbi->s_mount_opt, DELALLOC);
 			break;
+		case Opt_block_validity:
+			set_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+			break;
+		case Opt_noblock_validity:
+			clear_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+			break;
 		case Opt_inode_readahead_blks:
 			if (match_int(&args[0], &option))
 				return 0;
 			if (option < 0 || option > (1 << 30))
 				return 0;
-			if (option & (option - 1)) {
-				printk(KERN_ERR "EXT4-fs: inode_readahead_blks"
-				       " must be a power of 2\n");
+			if (!is_power_of_2(option)) {
+				ext4_msg(sb, KERN_ERR,
+					 "EXT4-fs: inode_readahead_blks"
+					 " must be a power of 2");
 				return 0;
 			}
 			sbi->s_inode_readahead_blks = option;
@@ -1508,9 +1566,9 @@ set_qf_format:
 				set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
 			break;
 		default:
-			printk(KERN_ERR
-			       "EXT4-fs: Unrecognized mount option \"%s\" "
-			       "or missing value\n", p);
+			ext4_msg(sb, KERN_ERR,
+			       "Unrecognized mount option \"%s\" "
+			       "or missing value", p);
 			return 0;
 		}
 	}
@@ -1528,21 +1586,21 @@ set_qf_format:
 				(sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)) ||
 		    (sbi->s_qf_names[GRPQUOTA] &&
 				(sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA))) {
-			printk(KERN_ERR "EXT4-fs: old and new quota "
-					"format mixing.\n");
+			ext4_msg(sb, KERN_ERR, "old and new quota "
+					"format mixing");
 			return 0;
 		}
 
 		if (!sbi->s_jquota_fmt) {
-			printk(KERN_ERR "EXT4-fs: journaled quota format "
-					"not specified.\n");
+			ext4_msg(sb, KERN_ERR, "journaled quota format "
+					"not specified");
 			return 0;
 		}
 	} else {
 		if (sbi->s_jquota_fmt) {
-			printk(KERN_ERR "EXT4-fs: journaled quota format "
+			ext4_msg(sb, KERN_ERR, "journaled quota format "
 					"specified with no journaling "
-					"enabled.\n");
+					"enabled");
 			return 0;
 		}
 	}
@@ -1557,32 +1615,32 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	int res = 0;
 
 	if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
-		printk(KERN_ERR "EXT4-fs warning: revision level too high, "
-		       "forcing read-only mode\n");
+		ext4_msg(sb, KERN_ERR, "revision level too high, "
+			 "forcing read-only mode");
 		res = MS_RDONLY;
 	}
 	if (read_only)
 		return res;
 	if (!(sbi->s_mount_state & EXT4_VALID_FS))
-		printk(KERN_WARNING "EXT4-fs warning: mounting unchecked fs, "
-		       "running e2fsck is recommended\n");
+		ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
+			 "running e2fsck is recommended");
 	else if ((sbi->s_mount_state & EXT4_ERROR_FS))
-		printk(KERN_WARNING
-		       "EXT4-fs warning: mounting fs with errors, "
-		       "running e2fsck is recommended\n");
+		ext4_msg(sb, KERN_WARNING,
+			 "warning: mounting fs with errors, "
+			 "running e2fsck is recommended");
 	else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
 		 le16_to_cpu(es->s_mnt_count) >=
 		 (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
-		printk(KERN_WARNING
-		       "EXT4-fs warning: maximal mount count reached, "
-		       "running e2fsck is recommended\n");
+		ext4_msg(sb, KERN_WARNING,
+			 "warning: maximal mount count reached, "
+			 "running e2fsck is recommended");
 	else if (le32_to_cpu(es->s_checkinterval) &&
 		(le32_to_cpu(es->s_lastcheck) +
 			le32_to_cpu(es->s_checkinterval) <= get_seconds()))
-		printk(KERN_WARNING
-		       "EXT4-fs warning: checktime reached, "
-		       "running e2fsck is recommended\n");
-	if (!sbi->s_journal) 
+		ext4_msg(sb, KERN_WARNING,
+			 "warning: checktime reached, "
+			 "running e2fsck is recommended");
+	if (!sbi->s_journal)
 		es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
 	if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
 		es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
@@ -1592,7 +1650,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	if (sbi->s_journal)
 		EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 
-	ext4_commit_super(sb, es, 1);
+	ext4_commit_super(sb, 1);
 	if (test_opt(sb, DEBUG))
 		printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
 				"bpg=%lu, ipg=%lu, mo=%04lx]\n",
@@ -1603,11 +1661,11 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 			sbi->s_mount_opt);
 
 	if (EXT4_SB(sb)->s_journal) {
-		printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
-		       sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
+		ext4_msg(sb, KERN_INFO, "%s journal on %s",
+		       EXT4_SB(sb)->s_journal->j_inode ? "internal" :
 		       "external", EXT4_SB(sb)->s_journal->j_devname);
 	} else {
-		printk(KERN_INFO "EXT4 FS on %s, no journal\n", sb->s_id);
+		ext4_msg(sb, KERN_INFO, "no journal");
 	}
 	return res;
 }
@@ -1616,10 +1674,10 @@ static int ext4_fill_flex_info(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_desc *gdp = NULL;
-	struct buffer_head *bh;
 	ext4_group_t flex_group_count;
 	ext4_group_t flex_group;
 	int groups_per_flex = 0;
+	size_t size;
 	int i;
 
 	if (!sbi->s_es->s_log_groups_per_flex) {
@@ -1634,16 +1692,21 @@ static int ext4_fill_flex_info(struct super_block *sb)
 	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
 			((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
 			      EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
-	sbi->s_flex_groups = kzalloc(flex_group_count *
-				     sizeof(struct flex_groups), GFP_KERNEL);
+	size = flex_group_count * sizeof(struct flex_groups);
+	sbi->s_flex_groups = kzalloc(size, GFP_KERNEL);
 	if (sbi->s_flex_groups == NULL) {
-		printk(KERN_ERR "EXT4-fs: not enough memory for "
-				"%u flex groups\n", flex_group_count);
+		sbi->s_flex_groups = vmalloc(size);
+		if (sbi->s_flex_groups)
+			memset(sbi->s_flex_groups, 0, size);
+	}
+	if (sbi->s_flex_groups == NULL) {
+		ext4_msg(sb, KERN_ERR, "not enough memory for "
+				"%u flex groups", flex_group_count);
 		goto failed;
 	}
 
 	for (i = 0; i < sbi->s_groups_count; i++) {
-		gdp = ext4_get_group_desc(sb, i, &bh);
+		gdp = ext4_get_group_desc(sb, i, NULL);
 
 		flex_group = ext4_flex_group(sbi, i);
 		atomic_set(&sbi->s_flex_groups[flex_group].free_inodes,
@@ -1724,44 +1787,44 @@ static int ext4_check_descriptors(struct super_block *sb)
 
 		block_bitmap = ext4_block_bitmap(sb, gdp);
 		if (block_bitmap < first_block || block_bitmap > last_block) {
-			printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Block bitmap for group %u not in group "
-			       "(block %llu)!\n", i, block_bitmap);
+			       "(block %llu)!", i, block_bitmap);
 			return 0;
 		}
 		inode_bitmap = ext4_inode_bitmap(sb, gdp);
 		if (inode_bitmap < first_block || inode_bitmap > last_block) {
-			printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Inode bitmap for group %u not in group "
-			       "(block %llu)!\n", i, inode_bitmap);
+			       "(block %llu)!", i, inode_bitmap);
 			return 0;
 		}
 		inode_table = ext4_inode_table(sb, gdp);
 		if (inode_table < first_block ||
 		    inode_table + sbi->s_itb_per_group - 1 > last_block) {
-			printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Inode table for group %u not in group "
-			       "(block %llu)!\n", i, inode_table);
+			       "(block %llu)!", i, inode_table);
 			return 0;
 		}
-		spin_lock(sb_bgl_lock(sbi, i));
+		ext4_lock_group(sb, i);
 		if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
-			printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
-			       "Checksum for group %u failed (%u!=%u)\n",
-			       i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
-			       gdp)), le16_to_cpu(gdp->bg_checksum));
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Checksum for group %u failed (%u!=%u)",
+				 i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
+				     gdp)), le16_to_cpu(gdp->bg_checksum));
 			if (!(sb->s_flags & MS_RDONLY)) {
-				spin_unlock(sb_bgl_lock(sbi, i));
+				ext4_unlock_group(sb, i);
 				return 0;
 			}
 		}
-		spin_unlock(sb_bgl_lock(sbi, i));
+		ext4_unlock_group(sb, i);
 		if (!flexbg_flag)
 			first_block += EXT4_BLOCKS_PER_GROUP(sb);
 	}
 
 	ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
-	sbi->s_es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb));
+	sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
 	return 1;
 }
 
@@ -1796,8 +1859,8 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 	}
 
 	if (bdev_read_only(sb->s_bdev)) {
-		printk(KERN_ERR "EXT4-fs: write access "
-			"unavailable, skipping orphan cleanup.\n");
+		ext4_msg(sb, KERN_ERR, "write access "
+			"unavailable, skipping orphan cleanup");
 		return;
 	}
 
@@ -1811,8 +1874,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 	}
 
 	if (s_flags & MS_RDONLY) {
-		printk(KERN_INFO "EXT4-fs: %s: orphan cleanup on readonly fs\n",
-		       sb->s_id);
+		ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs");
 		sb->s_flags &= ~MS_RDONLY;
 	}
 #ifdef CONFIG_QUOTA
@@ -1823,9 +1885,9 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 		if (EXT4_SB(sb)->s_qf_names[i]) {
 			int ret = ext4_quota_on_mount(sb, i);
 			if (ret < 0)
-				printk(KERN_ERR
-					"EXT4-fs: Cannot turn on journaled "
-					"quota: error %d\n", ret);
+				ext4_msg(sb, KERN_ERR,
+					"Cannot turn on journaled "
+					"quota: error %d", ret);
 		}
 	}
 #endif
@@ -1842,16 +1904,16 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 		list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
 		vfs_dq_init(inode);
 		if (inode->i_nlink) {
-			printk(KERN_DEBUG
-				"%s: truncating inode %lu to %lld bytes\n",
+			ext4_msg(sb, KERN_DEBUG,
+				"%s: truncating inode %lu to %lld bytes",
 				__func__, inode->i_ino, inode->i_size);
 			jbd_debug(2, "truncating inode %lu to %lld bytes\n",
 				  inode->i_ino, inode->i_size);
 			ext4_truncate(inode);
 			nr_truncates++;
 		} else {
-			printk(KERN_DEBUG
-				"%s: deleting unreferenced inode %lu\n",
+			ext4_msg(sb, KERN_DEBUG,
+				"%s: deleting unreferenced inode %lu",
 				__func__, inode->i_ino);
 			jbd_debug(2, "deleting unreferenced inode %lu\n",
 				  inode->i_ino);
@@ -1863,11 +1925,11 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 #define PLURAL(x) (x), ((x) == 1) ? "" : "s"
 
 	if (nr_orphans)
-		printk(KERN_INFO "EXT4-fs: %s: %d orphan inode%s deleted\n",
-		       sb->s_id, PLURAL(nr_orphans));
+		ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted",
+		       PLURAL(nr_orphans));
 	if (nr_truncates)
-		printk(KERN_INFO "EXT4-fs: %s: %d truncate%s cleaned up\n",
-		       sb->s_id, PLURAL(nr_truncates));
+		ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up",
+		       PLURAL(nr_truncates));
 #ifdef CONFIG_QUOTA
 	/* Turn quotas off */
 	for (i = 0; i < MAXQUOTAS; i++) {
@@ -1877,6 +1939,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 #endif
 	sb->s_flags = s_flags; /* Restore MS_RDONLY status */
 }
+
 /*
  * Maximal extent format file size.
  * Resulting logical blkno at s_maxbytes must fit in our on-disk
@@ -1927,19 +1990,19 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
 	loff_t res = EXT4_NDIR_BLOCKS;
 	int meta_blocks;
 	loff_t upper_limit;
-	/* This is calculated to be the largest file size for a
-	 * dense, bitmapped file such that the total number of
-	 * sectors in the file, including data and all indirect blocks,
-	 * does not exceed 2^48 -1
-	 * __u32 i_blocks_lo and _u16 i_blocks_high representing the
-	 * total number of  512 bytes blocks of the file
+	/* This is calculated to be the largest file size for a dense, block
+	 * mapped file such that the file's total number of 512-byte sectors,
+	 * including data and all indirect blocks, does not exceed (2^48 - 1).
+	 *
+	 * __u32 i_blocks_lo and _u16 i_blocks_high represent the total
+	 * number of 512-byte sectors of the file.
 	 */
 
 	if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
 		/*
-		 * !has_huge_files or CONFIG_LBD is not enabled
-		 * implies the inode i_block represent total blocks in
-		 * 512 bytes 32 == size of vfs inode i_blocks * 8
+		 * !has_huge_files or CONFIG_LBD not enabled implies that
+		 * the inode i_block field represents total file blocks in
+		 * 2^32 512-byte sectors == size of vfs inode i_blocks * 8
 		 */
 		upper_limit = (1LL << 32) - 1;
 
@@ -1981,7 +2044,7 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
 }
 
 static ext4_fsblk_t descriptor_loc(struct super_block *sb,
-				ext4_fsblk_t logical_sb_block, int nr)
+				   ext4_fsblk_t logical_sb_block, int nr)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_group_t bg, first_meta_bg;
@@ -1995,6 +2058,7 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb,
 	bg = sbi->s_desc_per_block * nr;
 	if (ext4_bg_has_super(sb, bg))
 		has_super = 1;
+
 	return (has_super + ext4_group_first_block_no(sb, bg));
 }
 
@@ -2091,8 +2155,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
 	if (parse_strtoul(buf, 0x40000000, &t))
 		return -EINVAL;
 
-	/* inode_readahead_blks must be a power of 2 */
-	if (t & (t-1))
+	if (!is_power_of_2(t))
 		return -EINVAL;
 
 	sbi->s_inode_readahead_blks = t;
@@ -2100,7 +2163,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
 }
 
 static ssize_t sbi_ui_show(struct ext4_attr *a,
-				struct ext4_sb_info *sbi, char *buf)
+			   struct ext4_sb_info *sbi, char *buf)
 {
 	unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
 
@@ -2205,7 +2268,6 @@ static struct kobj_type ext4_ktype = {
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				__releases(kernel_lock)
 				__acquires(kernel_lock)
-
 {
 	struct buffer_head *bh;
 	struct ext4_super_block *es = NULL;
@@ -2256,7 +2318,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 	blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
 	if (!blocksize) {
-		printk(KERN_ERR "EXT4-fs: unable to set blocksize\n");
+		ext4_msg(sb, KERN_ERR, "unable to set blocksize");
 		goto out_fail;
 	}
 
@@ -2272,7 +2334,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	if (!(bh = sb_bread(sb, logical_sb_block))) {
-		printk(KERN_ERR "EXT4-fs: unable to read superblock\n");
+		ext4_msg(sb, KERN_ERR, "unable to read superblock");
 		goto out_fail;
 	}
 	/*
@@ -2321,6 +2383,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
 	sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
 	sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
+	sbi->s_mb_history_max = default_mb_history_length;
 
 	set_opt(sbi->s_mount_opt, BARRIER);
 
@@ -2330,7 +2393,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	set_opt(sbi->s_mount_opt, DELALLOC);
 
-
 	if (!parse_options((char *) data, sb, &journal_devnum,
 			   &journal_ioprio, NULL, 0))
 		goto failed_mount;
@@ -2342,9 +2404,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	    (EXT4_HAS_COMPAT_FEATURE(sb, ~0U) ||
 	     EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
 	     EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U)))
-		printk(KERN_WARNING
-		       "EXT4-fs warning: feature flags set on rev 0 fs, "
-		       "running e2fsck is recommended\n");
+		ext4_msg(sb, KERN_WARNING,
+		       "feature flags set on rev 0 fs, "
+		       "running e2fsck is recommended");
 
 	/*
 	 * Check feature flags regardless of the revision level, since we
@@ -2353,16 +2415,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP);
 	if (features) {
-		printk(KERN_ERR "EXT4-fs: %s: couldn't mount because of "
-		       "unsupported optional features (%x).\n", sb->s_id,
+		ext4_msg(sb, KERN_ERR,
+			"Couldn't mount because of "
+			"unsupported optional features (%x)",
 			(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
 			~EXT4_FEATURE_INCOMPAT_SUPP));
 		goto failed_mount;
 	}
 	features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP);
 	if (!(sb->s_flags & MS_RDONLY) && features) {
-		printk(KERN_ERR "EXT4-fs: %s: couldn't mount RDWR because of "
-		       "unsupported optional features (%x).\n", sb->s_id,
+		ext4_msg(sb, KERN_ERR,
+			"Couldn't mount RDWR because of "
+			"unsupported optional features (%x)",
 			(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
 			~EXT4_FEATURE_RO_COMPAT_SUPP));
 		goto failed_mount;
@@ -2376,9 +2440,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		 */
 		if (sizeof(root->i_blocks) < sizeof(u64) &&
 				!(sb->s_flags & MS_RDONLY)) {
-			printk(KERN_ERR "EXT4-fs: %s: Filesystem with huge "
+			ext4_msg(sb, KERN_ERR, "Filesystem with huge "
 					"files cannot be mounted read-write "
-					"without CONFIG_LBD.\n", sb->s_id);
+					"without CONFIG_LBD");
 			goto failed_mount;
 		}
 	}
@@ -2386,17 +2450,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
 	    blocksize > EXT4_MAX_BLOCK_SIZE) {
-		printk(KERN_ERR
-		       "EXT4-fs: Unsupported filesystem blocksize %d on %s.\n",
-		       blocksize, sb->s_id);
+		ext4_msg(sb, KERN_ERR,
+		       "Unsupported filesystem blocksize %d", blocksize);
 		goto failed_mount;
 	}
 
 	if (sb->s_blocksize != blocksize) {
-
 		/* Validate the filesystem blocksize */
 		if (!sb_set_blocksize(sb, blocksize)) {
-			printk(KERN_ERR "EXT4-fs: bad block size %d.\n",
+			ext4_msg(sb, KERN_ERR, "bad block size %d",
 					blocksize);
 			goto failed_mount;
 		}
@@ -2406,15 +2468,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		offset = do_div(logical_sb_block, blocksize);
 		bh = sb_bread(sb, logical_sb_block);
 		if (!bh) {
-			printk(KERN_ERR
-			       "EXT4-fs: Can't read superblock on 2nd try.\n");
+			ext4_msg(sb, KERN_ERR,
+			       "Can't read superblock on 2nd try");
 			goto failed_mount;
 		}
 		es = (struct ext4_super_block *)(((char *)bh->b_data) + offset);
 		sbi->s_es = es;
 		if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) {
-			printk(KERN_ERR
-			       "EXT4-fs: Magic mismatch, very weird !\n");
+			ext4_msg(sb, KERN_ERR,
+			       "Magic mismatch, very weird!");
 			goto failed_mount;
 		}
 	}
@@ -2432,30 +2494,33 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
 		    (!is_power_of_2(sbi->s_inode_size)) ||
 		    (sbi->s_inode_size > blocksize)) {
-			printk(KERN_ERR
-			       "EXT4-fs: unsupported inode size: %d\n",
+			ext4_msg(sb, KERN_ERR,
+			       "unsupported inode size: %d",
 			       sbi->s_inode_size);
 			goto failed_mount;
 		}
 		if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE)
 			sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2);
 	}
+
 	sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) {
 		if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
 		    sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
 		    !is_power_of_2(sbi->s_desc_size)) {
-			printk(KERN_ERR
-			       "EXT4-fs: unsupported descriptor size %lu\n",
+			ext4_msg(sb, KERN_ERR,
+			       "unsupported descriptor size %lu",
 			       sbi->s_desc_size);
 			goto failed_mount;
 		}
 	} else
 		sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
+
 	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
 	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
 	if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0)
 		goto cantfind_ext4;
+
 	sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
 	if (sbi->s_inodes_per_block == 0)
 		goto cantfind_ext4;
@@ -2466,6 +2531,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_mount_state = le16_to_cpu(es->s_state);
 	sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
 	sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
+
 	for (i = 0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 	sbi->s_def_hash_version = es->s_def_hash_version;
@@ -2483,25 +2549,24 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	if (sbi->s_blocks_per_group > blocksize * 8) {
-		printk(KERN_ERR
-		       "EXT4-fs: #blocks per group too big: %lu\n",
+		ext4_msg(sb, KERN_ERR,
+		       "#blocks per group too big: %lu",
 		       sbi->s_blocks_per_group);
 		goto failed_mount;
 	}
 	if (sbi->s_inodes_per_group > blocksize * 8) {
-		printk(KERN_ERR
-		       "EXT4-fs: #inodes per group too big: %lu\n",
+		ext4_msg(sb, KERN_ERR,
+		       "#inodes per group too big: %lu",
 		       sbi->s_inodes_per_group);
 		goto failed_mount;
 	}
 
 	if (ext4_blocks_count(es) >
 		    (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
-		printk(KERN_ERR "EXT4-fs: filesystem on %s:"
-			" too large to mount safely\n", sb->s_id);
+		ext4_msg(sb, KERN_ERR, "filesystem"
+			" too large to mount safely");
 		if (sizeof(sector_t) < 8)
-			printk(KERN_WARNING "EXT4-fs: CONFIG_LBD not "
-					"enabled\n");
+			ext4_msg(sb, KERN_WARNING, "CONFIG_LBD not enabled");
 		goto failed_mount;
 	}
 
@@ -2511,21 +2576,21 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/* check blocks count against device size */
 	blocks_count = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
 	if (blocks_count && ext4_blocks_count(es) > blocks_count) {
-		printk(KERN_WARNING "EXT4-fs: bad geometry: block count %llu "
-		       "exceeds size of device (%llu blocks)\n",
+		ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu "
+		       "exceeds size of device (%llu blocks)",
 		       ext4_blocks_count(es), blocks_count);
 		goto failed_mount;
 	}
 
-        /*
-         * It makes no sense for the first data block to be beyond the end
-         * of the filesystem.
-         */
-        if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
-                printk(KERN_WARNING "EXT4-fs: bad geometry: first data"
-		       "block %u is beyond end of filesystem (%llu)\n",
-		       le32_to_cpu(es->s_first_data_block),
-		       ext4_blocks_count(es));
+	/*
+	 * It makes no sense for the first data block to be beyond the end
+	 * of the filesystem.
+	 */
+	if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
+                ext4_msg(sb, KERN_WARNING, "bad geometry: first data"
+			 "block %u is beyond end of filesystem (%llu)",
+			 le32_to_cpu(es->s_first_data_block),
+			 ext4_blocks_count(es));
 		goto failed_mount;
 	}
 	blocks_count = (ext4_blocks_count(es) -
@@ -2533,9 +2598,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			EXT4_BLOCKS_PER_GROUP(sb) - 1);
 	do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
 	if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) {
-		printk(KERN_WARNING "EXT4-fs: groups count too large: %u "
+		ext4_msg(sb, KERN_WARNING, "groups count too large: %u "
 		       "(block count %llu, first data block %u, "
-		       "blocks per group %lu)\n", sbi->s_groups_count,
+		       "blocks per group %lu)", sbi->s_groups_count,
 		       ext4_blocks_count(es),
 		       le32_to_cpu(es->s_first_data_block),
 		       EXT4_BLOCKS_PER_GROUP(sb));
@@ -2547,7 +2612,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *),
 				    GFP_KERNEL);
 	if (sbi->s_group_desc == NULL) {
-		printk(KERN_ERR "EXT4-fs: not enough memory\n");
+		ext4_msg(sb, KERN_ERR, "not enough memory");
 		goto failed_mount;
 	}
 
@@ -2562,21 +2627,21 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		block = descriptor_loc(sb, logical_sb_block, i);
 		sbi->s_group_desc[i] = sb_bread(sb, block);
 		if (!sbi->s_group_desc[i]) {
-			printk(KERN_ERR "EXT4-fs: "
-			       "can't read group descriptor %d\n", i);
+			ext4_msg(sb, KERN_ERR,
+			       "can't read group descriptor %d", i);
 			db_count = i;
 			goto failed_mount2;
 		}
 	}
 	if (!ext4_check_descriptors(sb)) {
-		printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n");
+		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
 		goto failed_mount2;
 	}
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
 		if (!ext4_fill_flex_info(sb)) {
-			printk(KERN_ERR
-			       "EXT4-fs: unable to initialize "
-			       "flex_bg meta info!\n");
+			ext4_msg(sb, KERN_ERR,
+			       "unable to initialize "
+			       "flex_bg meta info!");
 			goto failed_mount2;
 		}
 
@@ -2598,7 +2663,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
 	}
 	if (err) {
-		printk(KERN_ERR "EXT4-fs: insufficient memory\n");
+		ext4_msg(sb, KERN_ERR, "insufficient memory");
 		goto failed_mount3;
 	}
 
@@ -2607,7 +2672,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/*
 	 * set up enough so that it can read an inode
 	 */
-	sb->s_op = &ext4_sops;
+	if (!test_opt(sb, NOLOAD) &&
+	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+		sb->s_op = &ext4_sops;
+	else
+		sb->s_op = &ext4_nojournal_sops;
 	sb->s_export_op = &ext4_export_ops;
 	sb->s_xattr = ext4_xattr_handlers;
 #ifdef CONFIG_QUOTA
@@ -2615,6 +2684,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sb->dq_op = &ext4_quota_operations;
 #endif
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
+	mutex_init(&sbi->s_orphan_lock);
+	mutex_init(&sbi->s_resize_lock);
 
 	sb->s_root = NULL;
 
@@ -2632,13 +2703,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount3;
 		if (!(sb->s_flags & MS_RDONLY) &&
 		    EXT4_SB(sb)->s_journal->j_failed_commit) {
-			printk(KERN_CRIT "EXT4-fs error (device %s): "
+			ext4_msg(sb, KERN_CRIT, "error: "
 			       "ext4_fill_super: Journal transaction "
-			       "%u is corrupt\n", sb->s_id,
+			       "%u is corrupt",
 			       EXT4_SB(sb)->s_journal->j_failed_commit);
 			if (test_opt(sb, ERRORS_RO)) {
-				printk(KERN_CRIT
-				       "Mounting filesystem read-only\n");
+				ext4_msg(sb, KERN_CRIT,
+				       "Mounting filesystem read-only");
 				sb->s_flags |= MS_RDONLY;
 				EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 				es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
@@ -2646,14 +2717,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			if (test_opt(sb, ERRORS_PANIC)) {
 				EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 				es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-				ext4_commit_super(sb, es, 1);
+				ext4_commit_super(sb, 1);
 				goto failed_mount4;
 			}
 		}
 	} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
 	      EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
-		printk(KERN_ERR "EXT4-fs: required journal recovery "
-		       "suppressed and not mounted read-only\n");
+		ext4_msg(sb, KERN_ERR, "required journal recovery "
+		       "suppressed and not mounted read-only");
 		goto failed_mount4;
 	} else {
 		clear_opt(sbi->s_mount_opt, DATA_FLAGS);
@@ -2666,7 +2737,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (ext4_blocks_count(es) > 0xffffffffULL &&
 	    !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
 				       JBD2_FEATURE_INCOMPAT_64BIT)) {
-		printk(KERN_ERR "EXT4-fs: Failed to set 64-bit journal feature\n");
+		ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
 		goto failed_mount4;
 	}
 
@@ -2704,8 +2775,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	case EXT4_MOUNT_WRITEBACK_DATA:
 		if (!jbd2_journal_check_available_features
 		    (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
-			printk(KERN_ERR "EXT4-fs: Journal does not support "
-			       "requested data journaling mode\n");
+			ext4_msg(sb, KERN_ERR, "Journal does not support "
+			       "requested data journaling mode");
 			goto failed_mount4;
 		}
 	default:
@@ -2717,8 +2788,8 @@ no_journal:
 
 	if (test_opt(sb, NOBH)) {
 		if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
-			printk(KERN_WARNING "EXT4-fs: Ignoring nobh option - "
-				"its supported only with writeback mode\n");
+			ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
+				"its supported only with writeback mode");
 			clear_opt(sbi->s_mount_opt, NOBH);
 		}
 	}
@@ -2729,18 +2800,18 @@ no_journal:
 
 	root = ext4_iget(sb, EXT4_ROOT_INO);
 	if (IS_ERR(root)) {
-		printk(KERN_ERR "EXT4-fs: get root inode failed\n");
+		ext4_msg(sb, KERN_ERR, "get root inode failed");
 		ret = PTR_ERR(root);
 		goto failed_mount4;
 	}
 	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
 		iput(root);
-		printk(KERN_ERR "EXT4-fs: corrupt root inode, run e2fsck\n");
+		ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck");
 		goto failed_mount4;
 	}
 	sb->s_root = d_alloc_root(root);
 	if (!sb->s_root) {
-		printk(KERN_ERR "EXT4-fs: get root dentry failed\n");
+		ext4_msg(sb, KERN_ERR, "get root dentry failed");
 		iput(root);
 		ret = -ENOMEM;
 		goto failed_mount4;
@@ -2769,22 +2840,29 @@ no_journal:
 							sbi->s_inode_size) {
 		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
 						       EXT4_GOOD_OLD_INODE_SIZE;
-		printk(KERN_INFO "EXT4-fs: required extra inode space not"
-			"available.\n");
+		ext4_msg(sb, KERN_INFO, "required extra inode space not"
+			 "available");
 	}
 
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
-		printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - "
-				"requested data journaling mode\n");
+		ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
+			 "requested data journaling mode");
 		clear_opt(sbi->s_mount_opt, DELALLOC);
 	} else if (test_opt(sb, DELALLOC))
-		printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n");
+		ext4_msg(sb, KERN_INFO, "delayed allocation enabled");
+
+	err = ext4_setup_system_zone(sb);
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "failed to initialize system "
+			 "zone (%d)\n", err);
+		goto failed_mount4;
+	}
 
 	ext4_ext_init(sb);
 	err = ext4_mb_init(sb, needs_recovery);
 	if (err) {
-		printk(KERN_ERR "EXT4-fs: failed to initalize mballoc (%d)\n",
-		       err);
+		ext4_msg(sb, KERN_ERR, "failed to initalize mballoc (%d)",
+			 err);
 		goto failed_mount4;
 	}
 
@@ -2798,19 +2876,11 @@ no_journal:
 		goto failed_mount4;
 	};
 
-	/*
-	 * akpm: core read_super() calls in here with the superblock locked.
-	 * That deadlocks, because orphan cleanup needs to lock the superblock
-	 * in numerous places.  Here we just pop the lock - it's relatively
-	 * harmless, because we are now ready to accept write_super() requests,
-	 * and aviro says that's the only reason for hanging onto the
-	 * superblock lock.
-	 */
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
 	EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
 	if (needs_recovery) {
-		printk(KERN_INFO "EXT4-fs: recovery complete.\n");
+		ext4_msg(sb, KERN_INFO, "recovery complete");
 		ext4_mark_recovery_complete(sb, es);
 	}
 	if (EXT4_SB(sb)->s_journal) {
@@ -2823,25 +2893,30 @@ no_journal:
 	} else
 		descr = "out journal";
 
-	printk(KERN_INFO "EXT4-fs: mounted filesystem %s with%s\n",
-	       sb->s_id, descr);
+	ext4_msg(sb, KERN_INFO, "mounted filesystem with%s", descr);
 
 	lock_kernel();
 	return 0;
 
 cantfind_ext4:
 	if (!silent)
-		printk(KERN_ERR "VFS: Can't find ext4 filesystem on dev %s.\n",
-		       sb->s_id);
+		ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
 	goto failed_mount;
 
 failed_mount4:
-	printk(KERN_ERR "EXT4-fs (device %s): mount failed\n", sb->s_id);
+	ext4_msg(sb, KERN_ERR, "mount failed");
+	ext4_release_system_zone(sb);
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
 	}
 failed_mount3:
+	if (sbi->s_flex_groups) {
+		if (is_vmalloc_addr(sbi->s_flex_groups))
+			vfree(sbi->s_flex_groups);
+		else
+			kfree(sbi->s_flex_groups);
+	}
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -2862,6 +2937,7 @@ failed_mount:
 	brelse(bh);
 out_fail:
 	sb->s_fs_info = NULL;
+	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
 	lock_kernel();
 	return ret;
@@ -2906,27 +2982,27 @@ static journal_t *ext4_get_journal(struct super_block *sb,
 
 	journal_inode = ext4_iget(sb, journal_inum);
 	if (IS_ERR(journal_inode)) {
-		printk(KERN_ERR "EXT4-fs: no journal found.\n");
+		ext4_msg(sb, KERN_ERR, "no journal found");
 		return NULL;
 	}
 	if (!journal_inode->i_nlink) {
 		make_bad_inode(journal_inode);
 		iput(journal_inode);
-		printk(KERN_ERR "EXT4-fs: journal inode is deleted.\n");
+		ext4_msg(sb, KERN_ERR, "journal inode is deleted");
 		return NULL;
 	}
 
 	jbd_debug(2, "Journal inode found at %p: %lld bytes\n",
 		  journal_inode, journal_inode->i_size);
 	if (!S_ISREG(journal_inode->i_mode)) {
-		printk(KERN_ERR "EXT4-fs: invalid journal inode.\n");
+		ext4_msg(sb, KERN_ERR, "invalid journal inode");
 		iput(journal_inode);
 		return NULL;
 	}
 
 	journal = jbd2_journal_init_inode(journal_inode);
 	if (!journal) {
-		printk(KERN_ERR "EXT4-fs: Could not load journal inode\n");
+		ext4_msg(sb, KERN_ERR, "Could not load journal inode");
 		iput(journal_inode);
 		return NULL;
 	}
@@ -2950,22 +3026,22 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 
 	BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
 
-	bdev = ext4_blkdev_get(j_dev);
+	bdev = ext4_blkdev_get(j_dev, sb);
 	if (bdev == NULL)
 		return NULL;
 
 	if (bd_claim(bdev, sb)) {
-		printk(KERN_ERR
-			"EXT4-fs: failed to claim external journal device.\n");
+		ext4_msg(sb, KERN_ERR,
+			"failed to claim external journal device");
 		blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 		return NULL;
 	}
 
 	blocksize = sb->s_blocksize;
-	hblock = bdev_hardsect_size(bdev);
+	hblock = bdev_logical_block_size(bdev);
 	if (blocksize < hblock) {
-		printk(KERN_ERR
-			"EXT4-fs: blocksize too small for journal device.\n");
+		ext4_msg(sb, KERN_ERR,
+			"blocksize too small for journal device");
 		goto out_bdev;
 	}
 
@@ -2973,8 +3049,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	offset = EXT4_MIN_BLOCK_SIZE % blocksize;
 	set_blocksize(bdev, blocksize);
 	if (!(bh = __bread(bdev, sb_block, blocksize))) {
-		printk(KERN_ERR "EXT4-fs: couldn't read superblock of "
-		       "external journal\n");
+		ext4_msg(sb, KERN_ERR, "couldn't read superblock of "
+		       "external journal");
 		goto out_bdev;
 	}
 
@@ -2982,14 +3058,14 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) ||
 	    !(le32_to_cpu(es->s_feature_incompat) &
 	      EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) {
-		printk(KERN_ERR "EXT4-fs: external journal has "
-					"bad superblock\n");
+		ext4_msg(sb, KERN_ERR, "external journal has "
+					"bad superblock");
 		brelse(bh);
 		goto out_bdev;
 	}
 
 	if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
-		printk(KERN_ERR "EXT4-fs: journal UUID does not match\n");
+		ext4_msg(sb, KERN_ERR, "journal UUID does not match");
 		brelse(bh);
 		goto out_bdev;
 	}
@@ -3001,25 +3077,26 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	journal = jbd2_journal_init_dev(bdev, sb->s_bdev,
 					start, len, blocksize);
 	if (!journal) {
-		printk(KERN_ERR "EXT4-fs: failed to create device journal\n");
+		ext4_msg(sb, KERN_ERR, "failed to create device journal");
 		goto out_bdev;
 	}
 	journal->j_private = sb;
 	ll_rw_block(READ, 1, &journal->j_sb_buffer);
 	wait_on_buffer(journal->j_sb_buffer);
 	if (!buffer_uptodate(journal->j_sb_buffer)) {
-		printk(KERN_ERR "EXT4-fs: I/O error on journal device\n");
+		ext4_msg(sb, KERN_ERR, "I/O error on journal device");
 		goto out_journal;
 	}
 	if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
-		printk(KERN_ERR "EXT4-fs: External journal has more than one "
-					"user (unsupported) - %d\n",
+		ext4_msg(sb, KERN_ERR, "External journal has more than one "
+					"user (unsupported) - %d",
 			be32_to_cpu(journal->j_superblock->s_nr_users));
 		goto out_journal;
 	}
 	EXT4_SB(sb)->journal_bdev = bdev;
 	ext4_init_journal_params(sb, journal);
 	return journal;
+
 out_journal:
 	jbd2_journal_destroy(journal);
 out_bdev:
@@ -3041,8 +3118,8 @@ static int ext4_load_journal(struct super_block *sb,
 
 	if (journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
-		printk(KERN_INFO "EXT4-fs: external journal device major/minor "
-			"numbers have changed\n");
+		ext4_msg(sb, KERN_INFO, "external journal device major/minor "
+			"numbers have changed");
 		journal_dev = new_decode_dev(journal_devnum);
 	} else
 		journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
@@ -3054,24 +3131,23 @@ static int ext4_load_journal(struct super_block *sb,
 	 * crash?  For recovery, we need to check in advance whether we
 	 * can get read-write access to the device.
 	 */
-
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
 		if (sb->s_flags & MS_RDONLY) {
-			printk(KERN_INFO "EXT4-fs: INFO: recovery "
-					"required on readonly filesystem.\n");
+			ext4_msg(sb, KERN_INFO, "INFO: recovery "
+					"required on readonly filesystem");
 			if (really_read_only) {
-				printk(KERN_ERR "EXT4-fs: write access "
-					"unavailable, cannot proceed.\n");
+				ext4_msg(sb, KERN_ERR, "write access "
+					"unavailable, cannot proceed");
 				return -EROFS;
 			}
-			printk(KERN_INFO "EXT4-fs: write access will "
-			       "be enabled during recovery.\n");
+			ext4_msg(sb, KERN_INFO, "write access will "
+			       "be enabled during recovery");
 		}
 	}
 
 	if (journal_inum && journal_dev) {
-		printk(KERN_ERR "EXT4-fs: filesystem has both journal "
-		       "and inode journals!\n");
+		ext4_msg(sb, KERN_ERR, "filesystem has both journal "
+		       "and inode journals!");
 		return -EINVAL;
 	}
 
@@ -3084,14 +3160,14 @@ static int ext4_load_journal(struct super_block *sb,
 	}
 
 	if (journal->j_flags & JBD2_BARRIER)
-		printk(KERN_INFO "EXT4-fs: barriers enabled\n");
+		ext4_msg(sb, KERN_INFO, "barriers enabled");
 	else
-		printk(KERN_INFO "EXT4-fs: barriers disabled\n");
+		ext4_msg(sb, KERN_INFO, "barriers disabled");
 
 	if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
 		err = jbd2_journal_update_format(journal);
 		if (err)  {
-			printk(KERN_ERR "EXT4-fs: error updating journal.\n");
+			ext4_msg(sb, KERN_ERR, "error updating journal");
 			jbd2_journal_destroy(journal);
 			return err;
 		}
@@ -3103,7 +3179,7 @@ static int ext4_load_journal(struct super_block *sb,
 		err = jbd2_journal_load(journal);
 
 	if (err) {
-		printk(KERN_ERR "EXT4-fs: error loading journal.\n");
+		ext4_msg(sb, KERN_ERR, "error loading journal");
 		jbd2_journal_destroy(journal);
 		return err;
 	}
@@ -3114,18 +3190,17 @@ static int ext4_load_journal(struct super_block *sb,
 	if (journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
 		es->s_journal_dev = cpu_to_le32(journal_devnum);
-		sb->s_dirt = 1;
 
 		/* Make sure we flush the recovery flag to disk. */
-		ext4_commit_super(sb, es, 1);
+		ext4_commit_super(sb, 1);
 	}
 
 	return 0;
 }
 
-static int ext4_commit_super(struct super_block *sb,
-			      struct ext4_super_block *es, int sync)
+static int ext4_commit_super(struct super_block *sb, int sync)
 {
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 	struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
 	int error = 0;
 
@@ -3140,8 +3215,8 @@ static int ext4_commit_super(struct super_block *sb,
 		 * be remapped.  Nothing we can do but to retry the
 		 * write and hope for the best.
 		 */
-		printk(KERN_ERR "EXT4-fs: previous I/O error to "
-		       "superblock detected for %s.\n", sb->s_id);
+		ext4_msg(sb, KERN_ERR, "previous I/O error to "
+		       "superblock detected");
 		clear_buffer_write_io_error(sbh);
 		set_buffer_uptodate(sbh);
 	}
@@ -3154,7 +3229,7 @@ static int ext4_commit_super(struct super_block *sb,
 					&EXT4_SB(sb)->s_freeblocks_counter));
 	es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive(
 					&EXT4_SB(sb)->s_freeinodes_counter));
-
+	sb->s_dirt = 0;
 	BUFFER_TRACE(sbh, "marking dirty");
 	mark_buffer_dirty(sbh);
 	if (sync) {
@@ -3164,8 +3239,8 @@ static int ext4_commit_super(struct super_block *sb,
 
 		error = buffer_write_io_error(sbh);
 		if (error) {
-			printk(KERN_ERR "EXT4-fs: I/O error while writing "
-			       "superblock for %s.\n", sb->s_id);
+			ext4_msg(sb, KERN_ERR, "I/O error while writing "
+			       "superblock");
 			clear_buffer_write_io_error(sbh);
 			set_buffer_uptodate(sbh);
 		}
@@ -3173,7 +3248,6 @@ static int ext4_commit_super(struct super_block *sb,
 	return error;
 }
 
-
 /*
  * Have we just finished recovery?  If so, and if we are mounting (or
  * remounting) the filesystem readonly, then we will end up with a
@@ -3192,14 +3266,11 @@ static void ext4_mark_recovery_complete(struct super_block *sb,
 	if (jbd2_journal_flush(journal) < 0)
 		goto out;
 
-	lock_super(sb);
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) &&
 	    sb->s_flags & MS_RDONLY) {
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
-		sb->s_dirt = 0;
-		ext4_commit_super(sb, es, 1);
+		ext4_commit_super(sb, 1);
 	}
-	unlock_super(sb);
 
 out:
 	jbd2_journal_unlock_updates(journal);
@@ -3238,7 +3309,7 @@ static void ext4_clear_journal_err(struct super_block *sb,
 
 		EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 		es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-		ext4_commit_super(sb, es, 1);
+		ext4_commit_super(sb, 1);
 
 		jbd2_journal_clear_err(journal);
 	}
@@ -3257,29 +3328,17 @@ int ext4_force_commit(struct super_block *sb)
 		return 0;
 
 	journal = EXT4_SB(sb)->s_journal;
-	if (journal) {
-		sb->s_dirt = 0;
+	if (journal)
 		ret = ext4_journal_force_commit(journal);
-	}
 
 	return ret;
 }
 
-/*
- * Ext4 always journals updates to the superblock itself, so we don't
- * have to propagate any other updates to the superblock on disk at this
- * point.  (We can probably nuke this function altogether, and remove
- * any mention to sb->s_dirt in all of fs/ext4; eventual cleanup...)
- */
 static void ext4_write_super(struct super_block *sb)
 {
-	if (EXT4_SB(sb)->s_journal) {
-		if (mutex_trylock(&sb->s_lock) != 0)
-			BUG();
-		sb->s_dirt = 0;
-	} else {
-		ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
-	}
+	lock_super(sb);
+	ext4_commit_super(sb, 1);
+	unlock_super(sb);
 }
 
 static int ext4_sync_fs(struct super_block *sb, int wait)
@@ -3288,16 +3347,9 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	tid_t target;
 
 	trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
-	sb->s_dirt = 0;
-	if (EXT4_SB(sb)->s_journal) {
-		if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal,
-					      &target)) {
-			if (wait)
-				jbd2_log_wait_commit(EXT4_SB(sb)->s_journal,
-						     target);
-		}
-	} else {
-		ext4_commit_super(sb, EXT4_SB(sb)->s_es, wait);
+	if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
+		if (wait)
+			jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target);
 	}
 	return ret;
 }
@@ -3310,34 +3362,32 @@ static int ext4_freeze(struct super_block *sb)
 {
 	int error = 0;
 	journal_t *journal;
-	sb->s_dirt = 0;
 
-	if (!(sb->s_flags & MS_RDONLY)) {
-		journal = EXT4_SB(sb)->s_journal;
+	if (sb->s_flags & MS_RDONLY)
+		return 0;
 
-		if (journal) {
-			/* Now we set up the journal barrier. */
-			jbd2_journal_lock_updates(journal);
+	journal = EXT4_SB(sb)->s_journal;
 
-			/*
-			 * We don't want to clear needs_recovery flag when we
-			 * failed to flush the journal.
-			 */
-			error = jbd2_journal_flush(journal);
-			if (error < 0)
-				goto out;
-		}
+	/* Now we set up the journal barrier. */
+	jbd2_journal_lock_updates(journal);
 
-		/* Journal blocked and flushed, clear needs_recovery flag. */
-		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
-		error = ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
-		if (error)
-			goto out;
+	/*
+	 * Don't clear the needs_recovery flag if we failed to flush
+	 * the journal.
+	 */
+	error = jbd2_journal_flush(journal);
+	if (error < 0) {
+	out:
+		jbd2_journal_unlock_updates(journal);
+		return error;
 	}
+
+	/* Journal blocked and flushed, clear needs_recovery flag. */
+	EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+	error = ext4_commit_super(sb, 1);
+	if (error)
+		goto out;
 	return 0;
-out:
-	jbd2_journal_unlock_updates(journal);
-	return error;
 }
 
 /*
@@ -3346,14 +3396,15 @@ out:
  */
 static int ext4_unfreeze(struct super_block *sb)
 {
-	if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) {
-		lock_super(sb);
-		/* Reser the needs_recovery flag before the fs is unlocked. */
-		EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
-		ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
-		unlock_super(sb);
-		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
-	}
+	if (sb->s_flags & MS_RDONLY)
+		return 0;
+
+	lock_super(sb);
+	/* Reset the needs_recovery flag before the fs is unlocked. */
+	EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+	ext4_commit_super(sb, 1);
+	unlock_super(sb);
+	jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 	return 0;
 }
 
@@ -3371,7 +3422,10 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	int i;
 #endif
 
+	lock_kernel();
+
 	/* Store the original options */
+	lock_super(sb);
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;
 	old_opts.s_resuid = sbi->s_resuid;
@@ -3432,22 +3486,15 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			    (sbi->s_mount_state & EXT4_VALID_FS))
 				es->s_state = cpu_to_le16(sbi->s_mount_state);
 
-			/*
-			 * We have to unlock super so that we can wait for
-			 * transactions.
-			 */
-			if (sbi->s_journal) {
-				unlock_super(sb);
+			if (sbi->s_journal)
 				ext4_mark_recovery_complete(sb, es);
-				lock_super(sb);
-			}
 		} else {
 			int ret;
 			if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb,
 					~EXT4_FEATURE_RO_COMPAT_SUPP))) {
-				printk(KERN_WARNING "EXT4-fs: %s: couldn't "
+				ext4_msg(sb, KERN_WARNING, "couldn't "
 				       "remount RDWR because of unsupported "
-				       "optional features (%x).\n", sb->s_id,
+				       "optional features (%x)",
 				(le32_to_cpu(sbi->s_es->s_feature_ro_compat) &
 					~EXT4_FEATURE_RO_COMPAT_SUPP));
 				err = -EROFS;
@@ -3456,17 +3503,15 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 
 			/*
 			 * Make sure the group descriptor checksums
-			 * are sane.  If they aren't, refuse to
-			 * remount r/w.
+			 * are sane.  If they aren't, refuse to remount r/w.
 			 */
 			for (g = 0; g < sbi->s_groups_count; g++) {
 				struct ext4_group_desc *gdp =
 					ext4_get_group_desc(sb, g, NULL);
 
 				if (!ext4_group_desc_csum_verify(sbi, g, gdp)) {
-					printk(KERN_ERR
-	       "EXT4-fs: ext4_remount: "
-		"Checksum for group %u failed (%u!=%u)\n",
+					ext4_msg(sb, KERN_ERR,
+	       "ext4_remount: Checksum for group %u failed (%u!=%u)",
 		g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)),
 					       le16_to_cpu(gdp->bg_checksum));
 					err = -EINVAL;
@@ -3480,11 +3525,10 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			 * require a full umount/remount for now.
 			 */
 			if (es->s_last_orphan) {
-				printk(KERN_WARNING "EXT4-fs: %s: couldn't "
+				ext4_msg(sb, KERN_WARNING, "Couldn't "
 				       "remount RDWR because of unprocessed "
 				       "orphan inode list.  Please "
-				       "umount/remount instead.\n",
-				       sb->s_id);
+				       "umount/remount instead");
 				err = -EINVAL;
 				goto restore_opts;
 			}
@@ -3504,8 +3548,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 				sb->s_flags &= ~MS_RDONLY;
 		}
 	}
+	ext4_setup_system_zone(sb);
 	if (sbi->s_journal == NULL)
-		ext4_commit_super(sb, es, 1);
+		ext4_commit_super(sb, 1);
 
 #ifdef CONFIG_QUOTA
 	/* Release old quota file names */
@@ -3514,7 +3559,10 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		    old_opts.s_qf_names[i] != sbi->s_qf_names[i])
 			kfree(old_opts.s_qf_names[i]);
 #endif
+	unlock_super(sb);
+	unlock_kernel();
 	return 0;
+
 restore_opts:
 	sb->s_flags = old_sb_flags;
 	sbi->s_mount_opt = old_opts.s_mount_opt;
@@ -3532,6 +3580,8 @@ restore_opts:
 		sbi->s_qf_names[i] = old_opts.s_qf_names[i];
 	}
 #endif
+	unlock_super(sb);
+	unlock_kernel();
 	return err;
 }
 
@@ -3545,9 +3595,8 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	if (test_opt(sb, MINIX_DF)) {
 		sbi->s_overhead_last = 0;
 	} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
-		ext4_group_t ngroups = sbi->s_groups_count, i;
+		ext4_group_t i, ngroups = ext4_get_groups_count(sb);
 		ext4_fsblk_t overhead = 0;
-		smp_rmb();
 
 		/*
 		 * Compute the overhead (FS structures).  This is constant
@@ -3599,11 +3648,12 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
 	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
 	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
+
 	return 0;
 }
 
-/* Helper function for writing quotas on sync - we need to start transaction before quota file
- * is locked for write. Otherwise the are possible deadlocks:
+/* Helper function for writing quotas on sync - we need to start transaction
+ * before quota file is locked for write. Otherwise the are possible deadlocks:
  * Process 1                         Process 2
  * ext4_create()                     quota_sync()
  *   jbd2_journal_start()                  write_dquot()
@@ -3627,7 +3677,7 @@ static int ext4_write_dquot(struct dquot *dquot)
 
 	inode = dquot_to_inode(dquot);
 	handle = ext4_journal_start(inode,
-					EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
+				    EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 	ret = dquot_commit(dquot);
@@ -3643,7 +3693,7 @@ static int ext4_acquire_dquot(struct dquot *dquot)
 	handle_t *handle;
 
 	handle = ext4_journal_start(dquot_to_inode(dquot),
-					EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb));
+				    EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 	ret = dquot_acquire(dquot);
@@ -3659,7 +3709,7 @@ static int ext4_release_dquot(struct dquot *dquot)
 	handle_t *handle;
 
 	handle = ext4_journal_start(dquot_to_inode(dquot),
-					EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
+				    EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
 	if (IS_ERR(handle)) {
 		/* Release dquot anyway to avoid endless cycle in dqput() */
 		dquot_release(dquot);
@@ -3707,7 +3757,7 @@ static int ext4_write_info(struct super_block *sb, int type)
 static int ext4_quota_on_mount(struct super_block *sb, int type)
 {
 	return vfs_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
-			EXT4_SB(sb)->s_jquota_fmt, type);
+				  EXT4_SB(sb)->s_jquota_fmt, type);
 }
 
 /*
@@ -3738,9 +3788,9 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 	if (EXT4_SB(sb)->s_qf_names[type]) {
 		/* Quotafile not in fs root? */
 		if (path.dentry->d_parent != sb->s_root)
-			printk(KERN_WARNING
-				"EXT4-fs: Quota file not on filesystem root. "
-				"Journaled quota will not work.\n");
+			ext4_msg(sb, KERN_WARNING,
+				"Quota file not on filesystem root. "
+				"Journaled quota will not work");
 	}
 
 	/*
@@ -3823,8 +3873,8 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 	handle_t *handle = journal_current_handle();
 
 	if (EXT4_SB(sb)->s_journal && !handle) {
-		printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)"
-			" cancelled because transaction is not started.\n",
+		ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
+			" cancelled because transaction is not started",
 			(unsigned long long)off, (unsigned long long)len);
 		return -EIO;
 	}
@@ -3878,10 +3928,10 @@ out:
 
 #endif
 
-static int ext4_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static int ext4_get_sb(struct file_system_type *fs_type, int flags,
+		       const char *dev_name, void *data, struct vfsmount *mnt)
 {
-	return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt);
+	return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
 }
 
 static struct file_system_type ext4_fs_type = {
@@ -3893,14 +3943,14 @@ static struct file_system_type ext4_fs_type = {
 };
 
 #ifdef CONFIG_EXT4DEV_COMPAT
-static int ext4dev_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static int ext4dev_get_sb(struct file_system_type *fs_type, int flags,
+			  const char *dev_name, void *data,struct vfsmount *mnt)
 {
-	printk(KERN_WARNING "EXT4-fs: Update your userspace programs "
-	       "to mount using ext4\n");
-	printk(KERN_WARNING "EXT4-fs: ext4dev backwards compatibility "
-	       "will go away by 2.6.31\n");
-	return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt);
+	printk(KERN_WARNING "EXT4-fs (%s): Update your userspace programs "
+	       "to mount using ext4\n", dev_name);
+	printk(KERN_WARNING "EXT4-fs (%s): ext4dev backwards compatibility "
+	       "will go away by 2.6.31\n", dev_name);
+	return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
 }
 
 static struct file_system_type ext4dev_fs_type = {
@@ -3917,13 +3967,16 @@ static int __init init_ext4_fs(void)
 {
 	int err;
 
+	err = init_ext4_system_zone();
+	if (err)
+		return err;
 	ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
 	if (!ext4_kset)
-		return -ENOMEM;
+		goto out4;
 	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
 	err = init_ext4_mballoc();
 	if (err)
-		return err;
+		goto out3;
 
 	err = init_ext4_xattr();
 	if (err)
@@ -3948,6 +4001,11 @@ out1:
 	exit_ext4_xattr();
 out2:
 	exit_ext4_mballoc();
+out3:
+	remove_proc_entry("fs/ext4", NULL);
+	kset_unregister(ext4_kset);
+out4:
+	exit_ext4_system_zone();
 	return err;
 }
 
@@ -3962,6 +4020,7 @@ static void __exit exit_ext4_fs(void)
 	exit_ext4_mballoc();
 	remove_proc_entry("fs/ext4", NULL);
 	kset_unregister(ext4_kset);
+	exit_ext4_system_zone();
 }
 
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 3a7f603b6982..f3500294eec5 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -840,7 +840,7 @@ const struct file_operations fat_dir_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= fat_compat_dir_ioctl,
 #endif
-	.fsync		= file_fsync,
+	.fsync		= fat_file_fsync,
 };
 
 static int fat_get_short_entry(struct inode *dir, loff_t *pos,
@@ -967,7 +967,7 @@ static int __fat_remove_entries(struct inode *dir, loff_t pos, int nr_slots)
 			de++;
 			nr_slots--;
 		}
-		mark_buffer_dirty(bh);
+		mark_buffer_dirty_inode(bh, dir);
 		if (IS_DIRSYNC(dir))
 			err = sync_dirty_buffer(bh);
 		brelse(bh);
@@ -1001,7 +1001,7 @@ int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo)
 		de--;
 		nr_slots--;
 	}
-	mark_buffer_dirty(bh);
+	mark_buffer_dirty_inode(bh, dir);
 	if (IS_DIRSYNC(dir))
 		err = sync_dirty_buffer(bh);
 	brelse(bh);
@@ -1051,7 +1051,7 @@ static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used,
 		}
 		memset(bhs[n]->b_data, 0, sb->s_blocksize);
 		set_buffer_uptodate(bhs[n]);
-		mark_buffer_dirty(bhs[n]);
+		mark_buffer_dirty_inode(bhs[n], dir);
 
 		n++;
 		blknr++;
@@ -1131,7 +1131,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts)
 	de[0].size = de[1].size = 0;
 	memset(de + 2, 0, sb->s_blocksize - 2 * sizeof(*de));
 	set_buffer_uptodate(bhs[0]);
-	mark_buffer_dirty(bhs[0]);
+	mark_buffer_dirty_inode(bhs[0], dir);
 
 	err = fat_zeroed_cluster(dir, blknr, 1, bhs, MAX_BUF_PER_PAGE);
 	if (err)
@@ -1193,7 +1193,7 @@ static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots,
 			slots += copy;
 			size -= copy;
 			set_buffer_uptodate(bhs[n]);
-			mark_buffer_dirty(bhs[n]);
+			mark_buffer_dirty_inode(bhs[n], dir);
 			if (!size)
 				break;
 			n++;
@@ -1293,7 +1293,7 @@ found:
 		for (i = 0; i < long_bhs; i++) {
 			int copy = min_t(int, sb->s_blocksize - offset, size);
 			memcpy(bhs[i]->b_data + offset, slots, copy);
-			mark_buffer_dirty(bhs[i]);
+			mark_buffer_dirty_inode(bhs[i], dir);
 			offset = 0;
 			slots += copy;
 			size -= copy;
@@ -1304,7 +1304,7 @@ found:
 			/* Fill the short name slot. */
 			int copy = min_t(int, sb->s_blocksize - offset, size);
 			memcpy(bhs[i]->b_data + offset, slots, copy);
-			mark_buffer_dirty(bhs[i]);
+			mark_buffer_dirty_inode(bhs[i], dir);
 			if (IS_DIRSYNC(dir))
 				err = sync_dirty_buffer(bhs[i]);
 		}
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index ea440d65819c..e4d88527b5dd 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -74,6 +74,7 @@ struct msdos_sb_info {
 
 	int fatent_shift;
 	struct fatent_operations *fatent_ops;
+	struct inode *fat_inode;
 
 	spinlock_t inode_hash_lock;
 	struct hlist_head inode_hashtable[FAT_HASH_SIZE];
@@ -251,6 +252,7 @@ struct fat_entry {
 	} u;
 	int nr_bhs;
 	struct buffer_head *bhs[2];
+	struct inode *fat_inode;
 };
 
 static inline void fatent_init(struct fat_entry *fatent)
@@ -259,6 +261,7 @@ static inline void fatent_init(struct fat_entry *fatent)
 	fatent->entry = 0;
 	fatent->u.ent32_p = NULL;
 	fatent->bhs[0] = fatent->bhs[1] = NULL;
+	fatent->fat_inode = NULL;
 }
 
 static inline void fatent_set_entry(struct fat_entry *fatent, int entry)
@@ -275,6 +278,7 @@ static inline void fatent_brelse(struct fat_entry *fatent)
 		brelse(fatent->bhs[i]);
 	fatent->nr_bhs = 0;
 	fatent->bhs[0] = fatent->bhs[1] = NULL;
+	fatent->fat_inode = NULL;
 }
 
 extern void fat_ent_access_init(struct super_block *sb);
@@ -296,6 +300,8 @@ extern int fat_setattr(struct dentry * dentry, struct iattr * attr);
 extern void fat_truncate(struct inode *inode);
 extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		       struct kstat *stat);
+extern int fat_file_fsync(struct file *file, struct dentry *dentry,
+			  int datasync);
 
 /* fat/inode.c */
 extern void fat_attach(struct inode *inode, loff_t i_pos);
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index da6eea47872f..618f5305c2e4 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -73,6 +73,8 @@ static int fat12_ent_bread(struct super_block *sb, struct fat_entry *fatent,
 	struct buffer_head **bhs = fatent->bhs;
 
 	WARN_ON(blocknr < MSDOS_SB(sb)->fat_start);
+	fatent->fat_inode = MSDOS_SB(sb)->fat_inode;
+
 	bhs[0] = sb_bread(sb, blocknr);
 	if (!bhs[0])
 		goto err;
@@ -103,6 +105,7 @@ static int fat_ent_bread(struct super_block *sb, struct fat_entry *fatent,
 	struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
 
 	WARN_ON(blocknr < MSDOS_SB(sb)->fat_start);
+	fatent->fat_inode = MSDOS_SB(sb)->fat_inode;
 	fatent->bhs[0] = sb_bread(sb, blocknr);
 	if (!fatent->bhs[0]) {
 		printk(KERN_ERR "FAT: FAT read failed (blocknr %llu)\n",
@@ -167,9 +170,9 @@ static void fat12_ent_put(struct fat_entry *fatent, int new)
 	}
 	spin_unlock(&fat12_entry_lock);
 
-	mark_buffer_dirty(fatent->bhs[0]);
+	mark_buffer_dirty_inode(fatent->bhs[0], fatent->fat_inode);
 	if (fatent->nr_bhs == 2)
-		mark_buffer_dirty(fatent->bhs[1]);
+		mark_buffer_dirty_inode(fatent->bhs[1], fatent->fat_inode);
 }
 
 static void fat16_ent_put(struct fat_entry *fatent, int new)
@@ -178,7 +181,7 @@ static void fat16_ent_put(struct fat_entry *fatent, int new)
 		new = EOF_FAT16;
 
 	*fatent->u.ent16_p = cpu_to_le16(new);
-	mark_buffer_dirty(fatent->bhs[0]);
+	mark_buffer_dirty_inode(fatent->bhs[0], fatent->fat_inode);
 }
 
 static void fat32_ent_put(struct fat_entry *fatent, int new)
@@ -189,7 +192,7 @@ static void fat32_ent_put(struct fat_entry *fatent, int new)
 	WARN_ON(new & 0xf0000000);
 	new |= le32_to_cpu(*fatent->u.ent32_p) & ~0x0fffffff;
 	*fatent->u.ent32_p = cpu_to_le32(new);
-	mark_buffer_dirty(fatent->bhs[0]);
+	mark_buffer_dirty_inode(fatent->bhs[0], fatent->fat_inode);
 }
 
 static int fat12_ent_next(struct fat_entry *fatent)
@@ -381,7 +384,7 @@ static int fat_mirror_bhs(struct super_block *sb, struct buffer_head **bhs,
 			}
 			memcpy(c_bh->b_data, bhs[n]->b_data, sb->s_blocksize);
 			set_buffer_uptodate(c_bh);
-			mark_buffer_dirty(c_bh);
+			mark_buffer_dirty_inode(c_bh, sbi->fat_inode);
 			if (sb->s_flags & MS_SYNCHRONOUS)
 				err = sync_dirty_buffer(c_bh);
 			brelse(c_bh);
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 0a7f4a9918b3..e955a56b4e5e 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -133,6 +133,18 @@ static int fat_file_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+int fat_file_fsync(struct file *filp, struct dentry *dentry, int datasync)
+{
+	struct inode *inode = dentry->d_inode;
+	int res, err;
+
+	res = simple_fsync(filp, dentry, datasync);
+	err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping);
+
+	return res ? res : err;
+}
+
+
 const struct file_operations fat_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
@@ -142,7 +154,7 @@ const struct file_operations fat_file_operations = {
 	.mmap		= generic_file_mmap,
 	.release	= fat_file_release,
 	.ioctl		= fat_generic_ioctl,
-	.fsync		= file_fsync,
+	.fsync		= fat_file_fsync,
 	.splice_read	= generic_file_splice_read,
 };
 
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 296785a0dec8..51a5ecf9000a 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -441,16 +441,35 @@ static void fat_clear_inode(struct inode *inode)
 
 static void fat_write_super(struct super_block *sb)
 {
+	lock_super(sb);
 	sb->s_dirt = 0;
 
 	if (!(sb->s_flags & MS_RDONLY))
 		fat_clusters_flush(sb);
+	unlock_super(sb);
+}
+
+static int fat_sync_fs(struct super_block *sb, int wait)
+{
+	lock_super(sb);
+	fat_clusters_flush(sb);
+	sb->s_dirt = 0;
+	unlock_super(sb);
+
+	return 0;
 }
 
 static void fat_put_super(struct super_block *sb)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 
+	lock_kernel();
+
+	if (sb->s_dirt)
+		fat_write_super(sb);
+
+	iput(sbi->fat_inode);
+
 	if (sbi->nls_disk) {
 		unload_nls(sbi->nls_disk);
 		sbi->nls_disk = NULL;
@@ -467,6 +486,8 @@ static void fat_put_super(struct super_block *sb)
 
 	sb->s_fs_info = NULL;
 	kfree(sbi);
+
+	unlock_kernel();
 }
 
 static struct kmem_cache *fat_inode_cachep;
@@ -632,6 +653,7 @@ static const struct super_operations fat_sops = {
 	.delete_inode	= fat_delete_inode,
 	.put_super	= fat_put_super,
 	.write_super	= fat_write_super,
+	.sync_fs	= fat_sync_fs,
 	.statfs		= fat_statfs,
 	.clear_inode	= fat_clear_inode,
 	.remount_fs	= fat_remount,
@@ -1174,7 +1196,7 @@ static int fat_read_root(struct inode *inode)
 int fat_fill_super(struct super_block *sb, void *data, int silent,
 		   const struct inode_operations *fs_dir_inode_ops, int isvfat)
 {
-	struct inode *root_inode = NULL;
+	struct inode *root_inode = NULL, *fat_inode = NULL;
 	struct buffer_head *bh;
 	struct fat_boot_sector *b;
 	struct msdos_sb_info *sbi;
@@ -1414,6 +1436,11 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
 	}
 
 	error = -ENOMEM;
+	fat_inode = new_inode(sb);
+	if (!fat_inode)
+		goto out_fail;
+	MSDOS_I(fat_inode)->i_pos = 0;
+	sbi->fat_inode = fat_inode;
 	root_inode = new_inode(sb);
 	if (!root_inode)
 		goto out_fail;
@@ -1439,6 +1466,8 @@ out_invalid:
 		       " on dev %s.\n", sb->s_id);
 
 out_fail:
+	if (fat_inode)
+		iput(fat_inode);
 	if (root_inode)
 		iput(root_inode);
 	if (sbi->nls_io)
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index da3f361a37dd..20f522861355 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -544,7 +544,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 		int start = MSDOS_I(new_dir)->i_logstart;
 		dotdot_de->start = cpu_to_le16(start);
 		dotdot_de->starthi = cpu_to_le16(start >> 16);
-		mark_buffer_dirty(dotdot_bh);
+		mark_buffer_dirty_inode(dotdot_bh, old_inode);
 		if (IS_DIRSYNC(new_dir)) {
 			err = sync_dirty_buffer(dotdot_bh);
 			if (err)
@@ -586,7 +586,7 @@ error_dotdot:
 		int start = MSDOS_I(old_dir)->i_logstart;
 		dotdot_de->start = cpu_to_le16(start);
 		dotdot_de->starthi = cpu_to_le16(start >> 16);
-		mark_buffer_dirty(dotdot_bh);
+		mark_buffer_dirty_inode(dotdot_bh, old_inode);
 		corrupt |= sync_dirty_buffer(dotdot_bh);
 	}
 error_inode:
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index a0e00e3a46e9..b50ecbe97f83 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -965,7 +965,7 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
 		int start = MSDOS_I(new_dir)->i_logstart;
 		dotdot_de->start = cpu_to_le16(start);
 		dotdot_de->starthi = cpu_to_le16(start >> 16);
-		mark_buffer_dirty(dotdot_bh);
+		mark_buffer_dirty_inode(dotdot_bh, old_inode);
 		if (IS_DIRSYNC(new_dir)) {
 			err = sync_dirty_buffer(dotdot_bh);
 			if (err)
@@ -1009,7 +1009,7 @@ error_dotdot:
 		int start = MSDOS_I(old_dir)->i_logstart;
 		dotdot_de->start = cpu_to_le16(start);
 		dotdot_de->starthi = cpu_to_le16(start >> 16);
-		mark_buffer_dirty(dotdot_bh);
+		mark_buffer_dirty_inode(dotdot_bh, old_inode);
 		corrupt |= sync_dirty_buffer(dotdot_bh);
 	}
 error_inode:
diff --git a/fs/file_table.c b/fs/file_table.c
index 54018fe48840..334ce39881f8 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -214,7 +214,7 @@ int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry,
 	 */
 	if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) {
 		file_take_write(file);
-		error = mnt_want_write(mnt);
+		error = mnt_clone_write(mnt);
 		WARN_ON(error);
 	}
 	return error;
@@ -399,6 +399,44 @@ too_bad:
 	return 0;
 }
 
+/**
+ *	mark_files_ro - mark all files read-only
+ *	@sb: superblock in question
+ *
+ *	All files are marked read-only.  We don't care about pending
+ *	delete files so this should be used in 'force' mode only.
+ */
+void mark_files_ro(struct super_block *sb)
+{
+	struct file *f;
+
+retry:
+	file_list_lock();
+	list_for_each_entry(f, &sb->s_files, f_u.fu_list) {
+		struct vfsmount *mnt;
+		if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
+		       continue;
+		if (!file_count(f))
+			continue;
+		if (!(f->f_mode & FMODE_WRITE))
+			continue;
+		f->f_mode &= ~FMODE_WRITE;
+		if (file_check_writeable(f) != 0)
+			continue;
+		file_release_write(f);
+		mnt = mntget(f->f_path.mnt);
+		file_list_unlock();
+		/*
+		 * This can sleep, so we can't hold
+		 * the file_list_lock() spinlock.
+		 */
+		mnt_drop_write(mnt);
+		mntput(mnt);
+		goto retry;
+	}
+	file_list_unlock();
+}
+
 void __init files_init(unsigned long mempages)
 { 
 	int n; 
diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c
index 1dacda831577..cdbd1654e4cd 100644
--- a/fs/freevxfs/vxfs_super.c
+++ b/fs/freevxfs/vxfs_super.c
@@ -80,12 +80,16 @@ vxfs_put_super(struct super_block *sbp)
 {
 	struct vxfs_sb_info	*infp = VXFS_SBI(sbp);
 
+	lock_kernel();
+
 	vxfs_put_fake_inode(infp->vsi_fship);
 	vxfs_put_fake_inode(infp->vsi_ilist);
 	vxfs_put_fake_inode(infp->vsi_stilist);
 
 	brelse(infp->vsi_bp);
 	kfree(infp);
+
+	unlock_kernel();
 }
 
 /**
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 91013ff7dd53..40308e98c6a4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -64,6 +64,28 @@ static void writeback_release(struct backing_dev_info *bdi)
 	clear_bit(BDI_pdflush, &bdi->state);
 }
 
+static noinline void block_dump___mark_inode_dirty(struct inode *inode)
+{
+	if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
+		struct dentry *dentry;
+		const char *name = "?";
+
+		dentry = d_find_alias(inode);
+		if (dentry) {
+			spin_lock(&dentry->d_lock);
+			name = (const char *) dentry->d_name.name;
+		}
+		printk(KERN_DEBUG
+		       "%s(%d): dirtied inode %lu (%s) on %s\n",
+		       current->comm, task_pid_nr(current), inode->i_ino,
+		       name, inode->i_sb->s_id);
+		if (dentry) {
+			spin_unlock(&dentry->d_lock);
+			dput(dentry);
+		}
+	}
+}
+
 /**
  *	__mark_inode_dirty -	internal function
  *	@inode: inode to mark
@@ -114,23 +136,8 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	if ((inode->i_state & flags) == flags)
 		return;
 
-	if (unlikely(block_dump)) {
-		struct dentry *dentry = NULL;
-		const char *name = "?";
-
-		if (!list_empty(&inode->i_dentry)) {
-			dentry = list_entry(inode->i_dentry.next,
-					    struct dentry, d_alias);
-			if (dentry && dentry->d_name.name)
-				name = (const char *) dentry->d_name.name;
-		}
-
-		if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev"))
-			printk(KERN_DEBUG
-			       "%s(%d): dirtied inode %lu (%s) on %s\n",
-			       current->comm, task_pid_nr(current), inode->i_ino,
-			       name, inode->i_sb->s_id);
-	}
+	if (unlikely(block_dump))
+		block_dump___mark_inode_dirty(inode);
 
 	spin_lock(&inode_lock);
 	if ((inode->i_state & flags) != flags) {
@@ -289,7 +296,6 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
 	int ret;
 
 	BUG_ON(inode->i_state & I_SYNC);
-	WARN_ON(inode->i_state & I_NEW);
 
 	/* Set I_SYNC, reset I_DIRTY */
 	dirty = inode->i_state & I_DIRTY;
@@ -314,7 +320,6 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
 	}
 
 	spin_lock(&inode_lock);
-	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state &= ~I_SYNC;
 	if (!(inode->i_state & I_FREEING)) {
 		if (!(inode->i_state & I_DIRTY) &&
@@ -678,55 +683,6 @@ void sync_inodes_sb(struct super_block *sb, int wait)
 	sync_sb_inodes(sb, &wbc);
 }
 
-/**
- * sync_inodes - writes all inodes to disk
- * @wait: wait for completion
- *
- * sync_inodes() goes through each super block's dirty inode list, writes the
- * inodes out, waits on the writeout and puts the inodes back on the normal
- * list.
- *
- * This is for sys_sync().  fsync_dev() uses the same algorithm.  The subtle
- * part of the sync functions is that the blockdev "superblock" is processed
- * last.  This is because the write_inode() function of a typical fs will
- * perform no I/O, but will mark buffers in the blockdev mapping as dirty.
- * What we want to do is to perform all that dirtying first, and then write
- * back all those inode blocks via the blockdev mapping in one sweep.  So the
- * additional (somewhat redundant) sync_blockdev() calls here are to make
- * sure that really happens.  Because if we call sync_inodes_sb(wait=1) with
- * outstanding dirty inodes, the writeback goes block-at-a-time within the
- * filesystem's write_inode().  This is extremely slow.
- */
-static void __sync_inodes(int wait)
-{
-	struct super_block *sb;
-
-	spin_lock(&sb_lock);
-restart:
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		sb->s_count++;
-		spin_unlock(&sb_lock);
-		down_read(&sb->s_umount);
-		if (sb->s_root) {
-			sync_inodes_sb(sb, wait);
-			sync_blockdev(sb->s_bdev);
-		}
-		up_read(&sb->s_umount);
-		spin_lock(&sb_lock);
-		if (__put_super_and_need_restart(sb))
-			goto restart;
-	}
-	spin_unlock(&sb_lock);
-}
-
-void sync_inodes(int wait)
-{
-	__sync_inodes(0);
-
-	if (wait)
-		__sync_inodes(1);
-}
-
 /**
  * write_inode_now	-	write an inode to disk
  * @inode: inode to write to disk
diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig
index 3a981b7f64ca..cad957cdb1e5 100644
--- a/fs/gfs2/Kconfig
+++ b/fs/gfs2/Kconfig
@@ -7,6 +7,7 @@ config GFS2_FS
 	select IP_SCTP if DLM_SCTP
 	select FS_POSIX_ACL
 	select CRC32
+	select SLOW_WORK
 	help
 	  A cluster filesystem.
 
diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
index a851ea4bdf70..d53a9bea1c2f 100644
--- a/fs/gfs2/Makefile
+++ b/fs/gfs2/Makefile
@@ -1,8 +1,8 @@
 obj-$(CONFIG_GFS2_FS) += gfs2.o
 gfs2-y := acl.o bmap.o dir.o eaops.o eattr.o glock.o \
 	glops.o inode.o log.o lops.o main.o meta_io.o \
-	mount.o ops_address.o ops_dentry.o ops_export.o ops_file.o \
-	ops_fstype.o ops_inode.o ops_super.o quota.o \
+	aops.o dentry.o export.o file.o \
+	ops_fstype.o ops_inode.o quota.o \
 	recovery.o rgrp.o super.o sys.o trans.o util.o
 
 gfs2-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/aops.c
similarity index 98%
rename from fs/gfs2/ops_address.c
rename to fs/gfs2/aops.c
index a6dde1751e17..03ebb439ace0 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/aops.c
@@ -28,7 +28,6 @@
 #include "inode.h"
 #include "log.h"
 #include "meta_io.h"
-#include "ops_address.h"
 #include "quota.h"
 #include "trans.h"
 #include "rgrp.h"
@@ -781,10 +780,12 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 	unlock_page(page);
 	page_cache_release(page);
 
-	if (inode->i_size < to) {
-		i_size_write(inode, to);
-		ip->i_disksize = inode->i_size;
-		di->di_size = cpu_to_be64(inode->i_size);
+	if (copied) {
+		if (inode->i_size < to) {
+			i_size_write(inode, to);
+			ip->i_disksize = inode->i_size;
+		}
+		gfs2_dinode_out(ip, di);
 		mark_inode_dirty(inode);
 	}
 
@@ -824,7 +825,6 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct buffer_head *dibh;
 	struct gfs2_alloc *al = ip->i_alloc;
-	struct gfs2_dinode *di;
 	unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
 	unsigned int to = from + len;
 	int ret;
@@ -847,11 +847,10 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 		gfs2_page_add_databufs(ip, page, from, to);
 
 	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
-
-	if (likely(ret >= 0) && (inode->i_size > ip->i_disksize)) {
-		di = (struct gfs2_dinode *)dibh->b_data;
-		ip->i_disksize = inode->i_size;
-		di->di_size = cpu_to_be64(inode->i_size);
+	if (ret > 0) {
+		if (inode->i_size > ip->i_disksize)
+			ip->i_disksize = inode->i_size;
+		gfs2_dinode_out(ip, dibh->b_data);
 		mark_inode_dirty(inode);
 	}
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 3a5d3f883e10..329763530dc0 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -25,7 +25,6 @@
 #include "trans.h"
 #include "dir.h"
 #include "util.h"
-#include "ops_address.h"
 
 /* This doesn't need to be that large as max 64 bit pointers in a 4k
  * block is 512, so __u16 is fine for that. It saves stack space to
@@ -136,7 +135,9 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
 		   and write it out to disk */
 
 		unsigned int n = 1;
-		block = gfs2_alloc_block(ip, &n);
+		error = gfs2_alloc_block(ip, &block, &n);
+		if (error)
+			goto out_brelse;
 		if (isdir) {
 			gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1);
 			error = gfs2_dir_get_new_buffer(ip, block, &bh);
@@ -476,8 +477,11 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 	blks = dblks + iblks;
 	i = sheight;
 	do {
+		int error;
 		n = blks - alloced;
-		bn = gfs2_alloc_block(ip, &n);
+		error = gfs2_alloc_block(ip, &bn, &n);
+		if (error)
+			return error;
 		alloced += n;
 		if (state != ALLOC_DATA || gfs2_is_jdata(ip))
 			gfs2_trans_add_unrevoke(sdp, bn, n);
@@ -1008,7 +1012,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping)
 		gfs2_trans_add_bh(ip->i_gl, bh, 0);
 
 	zero_user(page, offset, length);
-
+	mark_buffer_dirty(bh);
 unlock:
 	unlock_page(page);
 	page_cache_release(page);
diff --git a/fs/gfs2/ops_dentry.c b/fs/gfs2/dentry.c
similarity index 100%
rename from fs/gfs2/ops_dentry.c
rename to fs/gfs2/dentry.c
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index aef4d0c06748..297d7e5cebad 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -803,13 +803,20 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh,
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	unsigned int n = 1;
-	u64 bn = gfs2_alloc_block(ip, &n);
-	struct buffer_head *bh = gfs2_meta_new(ip->i_gl, bn);
+	u64 bn;
+	int error;
+	struct buffer_head *bh;
 	struct gfs2_leaf *leaf;
 	struct gfs2_dirent *dent;
 	struct qstr name = { .name = "", .len = 0, .hash = 0 };
+
+	error = gfs2_alloc_block(ip, &bn, &n);
+	if (error)
+		return NULL;
+	bh = gfs2_meta_new(ip->i_gl, bn);
 	if (!bh)
 		return NULL;
+
 	gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1);
 	gfs2_trans_add_bh(ip->i_gl, bh, 1);
 	gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF);
diff --git a/fs/gfs2/eattr.c b/fs/gfs2/eattr.c
index 899763aed217..07ea9529adda 100644
--- a/fs/gfs2/eattr.c
+++ b/fs/gfs2/eattr.c
@@ -582,8 +582,11 @@ static int ea_alloc_blk(struct gfs2_inode *ip, struct buffer_head **bhp)
 	struct gfs2_ea_header *ea;
 	unsigned int n = 1;
 	u64 block;
+	int error;
 
-	block = gfs2_alloc_block(ip, &n);
+	error = gfs2_alloc_block(ip, &block, &n);
+	if (error)
+		return error;
 	gfs2_trans_add_unrevoke(sdp, block, 1);
 	*bhp = gfs2_meta_new(ip->i_gl, block);
 	gfs2_trans_add_bh(ip->i_gl, *bhp, 1);
@@ -617,6 +620,7 @@ static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea,
 		    struct gfs2_ea_request *er)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	int error;
 
 	ea->ea_data_len = cpu_to_be32(er->er_data_len);
 	ea->ea_name_len = er->er_name_len;
@@ -642,7 +646,9 @@ static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea,
 			int mh_size = sizeof(struct gfs2_meta_header);
 			unsigned int n = 1;
 
-			block = gfs2_alloc_block(ip, &n);
+			error = gfs2_alloc_block(ip, &block, &n);
+			if (error)
+				return error;
 			gfs2_trans_add_unrevoke(sdp, block, 1);
 			bh = gfs2_meta_new(ip->i_gl, block);
 			gfs2_trans_add_bh(ip->i_gl, bh, 1);
@@ -963,7 +969,9 @@ static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er,
 	} else {
 		u64 blk;
 		unsigned int n = 1;
-		blk = gfs2_alloc_block(ip, &n);
+		error = gfs2_alloc_block(ip, &blk, &n);
+		if (error)
+			return error;
 		gfs2_trans_add_unrevoke(sdp, blk, 1);
 		indbh = gfs2_meta_new(ip->i_gl, blk);
 		gfs2_trans_add_bh(ip->i_gl, indbh, 1);
diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/export.c
similarity index 100%
rename from fs/gfs2/ops_export.c
rename to fs/gfs2/export.c
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/file.c
similarity index 97%
rename from fs/gfs2/ops_file.c
rename to fs/gfs2/file.c
index 5d82e91887e3..73318a3ce6f1 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/file.c
@@ -39,7 +39,6 @@
 #include "trans.h"
 #include "util.h"
 #include "eaops.h"
-#include "ops_address.h"
 
 /**
  * gfs2_llseek - seek to a location in a file
@@ -425,33 +424,36 @@ static struct vm_operations_struct gfs2_vm_ops = {
 	.page_mkwrite = gfs2_page_mkwrite,
 };
 
-
 /**
  * gfs2_mmap -
  * @file: The file to map
  * @vma: The VMA which described the mapping
  *
- * Returns: 0 or error code
+ * There is no need to get a lock here unless we should be updating
+ * atime. We ignore any locking errors since the only consequence is
+ * a missed atime update (which will just be deferred until later).
+ *
+ * Returns: 0
  */
 
 static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-	struct gfs2_holder i_gh;
-	int error;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
-	error = gfs2_glock_nq(&i_gh);
-	if (error) {
-		gfs2_holder_uninit(&i_gh);
-		return error;
+	if (!(file->f_flags & O_NOATIME)) {
+		struct gfs2_holder i_gh;
+		int error;
+
+		gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+		error = gfs2_glock_nq(&i_gh);
+		file_accessed(file);
+		if (error == 0)
+			gfs2_glock_dq_uninit(&i_gh);
 	}
-
 	vma->vm_ops = &gfs2_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
 
-	gfs2_glock_dq_uninit(&i_gh);
-
-	return error;
+	return 0;
 }
 
 /**
@@ -692,12 +694,10 @@ static void do_unflock(struct file *file, struct file_lock *fl)
 
 static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 {
-	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-
 	if (!(fl->fl_flags & FL_FLOCK))
 		return -ENOLCK;
-	if (__mandatory_lock(&ip->i_inode))
-		return -ENOLCK;
+	if (fl->fl_type & LOCK_MAND)
+		return -EOPNOTSUPP;
 
 	if (fl->fl_type == F_UNLCK) {
 		do_unflock(file, fl);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index ff4981090489..2bf62bcc5181 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -796,22 +796,37 @@ void gfs2_holder_uninit(struct gfs2_holder *gh)
 	gh->gh_ip = 0;
 }
 
-static int just_schedule(void *word)
+/**
+ * gfs2_glock_holder_wait
+ * @word: unused
+ *
+ * This function and gfs2_glock_demote_wait both show up in the WCHAN
+ * field. Thus I've separated these otherwise identical functions in
+ * order to be more informative to the user.
+ */
+
+static int gfs2_glock_holder_wait(void *word)
 {
         schedule();
         return 0;
 }
 
+static int gfs2_glock_demote_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
 static void wait_on_holder(struct gfs2_holder *gh)
 {
 	might_sleep();
-	wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE);
 }
 
 static void wait_on_demote(struct gfs2_glock *gl)
 {
 	might_sleep();
-	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, just_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE);
 }
 
 /**
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 70f87f43afa2..d5e4ab155ca0 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -309,24 +309,6 @@ static void rgrp_go_unlock(struct gfs2_holder *gh)
 	gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
 }
 
-/**
- * rgrp_go_dump - print out an rgrp
- * @seq: The iterator
- * @gl: The glock in question
- *
- */
-
-static int rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
-{
-	const struct gfs2_rgrpd *rgd = gl->gl_object;
-	if (rgd == NULL)
-		return 0;
-	gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n",
-		       (unsigned long long)rgd->rd_addr, rgd->rd_flags,
-		       rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes);
-	return 0;
-}
-
 /**
  * trans_go_sync - promote/demote the transaction glock
  * @gl: the glock
@@ -410,7 +392,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_demote_ok = rgrp_go_demote_ok,
 	.go_lock = rgrp_go_lock,
 	.go_unlock = rgrp_go_unlock,
-	.go_dump = rgrp_go_dump,
+	.go_dump = gfs2_rgrp_dump,
 	.go_type = LM_TYPE_RGRP,
 	.go_min_hold_time = HZ / 5,
 };
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 399d1b978049..225347fbff3c 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -12,6 +12,7 @@
 
 #include <linux/fs.h>
 #include <linux/workqueue.h>
+#include <linux/slow-work.h>
 #include <linux/dlm.h>
 #include <linux/buffer_head.h>
 
@@ -63,9 +64,12 @@ struct gfs2_log_element {
 	const struct gfs2_log_operations *le_ops;
 };
 
+#define GBF_FULL 1
+
 struct gfs2_bitmap {
 	struct buffer_head *bi_bh;
 	char *bi_clone;
+	unsigned long bi_flags;
 	u32 bi_offset;
 	u32 bi_start;
 	u32 bi_len;
@@ -90,10 +94,11 @@ struct gfs2_rgrpd {
 	struct gfs2_sbd *rd_sbd;
 	unsigned int rd_bh_count;
 	u32 rd_last_alloc;
-	unsigned char rd_flags;
-#define GFS2_RDF_CHECK        0x01      /* Need to check for unlinked inodes */
-#define GFS2_RDF_NOALLOC      0x02      /* rg prohibits allocation */
-#define GFS2_RDF_UPTODATE     0x04      /* rg is up to date */
+	u32 rd_flags;
+#define GFS2_RDF_CHECK		0x10000000 /* check for unlinked inodes */
+#define GFS2_RDF_UPTODATE	0x20000000 /* rg is up to date */
+#define GFS2_RDF_ERROR		0x40000000 /* error in rg */
+#define GFS2_RDF_MASK		0xf0000000 /* mask for internal flags */
 };
 
 enum gfs2_state_bits {
@@ -376,11 +381,11 @@ struct gfs2_journal_extent {
 struct gfs2_jdesc {
 	struct list_head jd_list;
 	struct list_head extent_list;
-
+	struct slow_work jd_work;
 	struct inode *jd_inode;
+	unsigned long jd_flags;
+#define JDF_RECOVERY 1
 	unsigned int jd_jid;
-	int jd_dirty;
-
 	unsigned int jd_blocks;
 };
 
@@ -390,9 +395,6 @@ struct gfs2_statfs_change_host {
 	s64 sc_dinodes;
 };
 
-#define GFS2_GLOCKD_DEFAULT	1
-#define GFS2_GLOCKD_MAX		16
-
 #define GFS2_QUOTA_DEFAULT	GFS2_QUOTA_OFF
 #define GFS2_QUOTA_OFF		0
 #define GFS2_QUOTA_ACCOUNT	1
@@ -418,6 +420,7 @@ struct gfs2_args {
 	unsigned int ar_data:2;			/* ordered/writeback */
 	unsigned int ar_meta:1;			/* mount metafs */
 	unsigned int ar_discard:1;		/* discard requests */
+	int ar_commit;				/* Commit interval */
 };
 
 struct gfs2_tune {
@@ -426,7 +429,6 @@ struct gfs2_tune {
 	unsigned int gt_incore_log_blocks;
 	unsigned int gt_log_flush_secs;
 
-	unsigned int gt_recoverd_secs;
 	unsigned int gt_logd_secs;
 
 	unsigned int gt_quota_simul_sync; /* Max quotavals to sync at once */
@@ -447,6 +449,7 @@ enum {
 	SDF_JOURNAL_LIVE	= 1,
 	SDF_SHUTDOWN		= 2,
 	SDF_NOBARRIERS		= 3,
+	SDF_NORECOVERY		= 4,
 };
 
 #define GFS2_FSNAME_LEN		256
@@ -493,7 +496,6 @@ struct lm_lockstruct {
 	unsigned long ls_flags;
 	dlm_lockspace_t *ls_dlm;
 
-	int ls_recover_jid;
 	int ls_recover_jid_done;
 	int ls_recover_jid_status;
 };
@@ -582,7 +584,6 @@ struct gfs2_sbd {
 
 	/* Daemon stuff */
 
-	struct task_struct *sd_recoverd_process;
 	struct task_struct *sd_logd_process;
 	struct task_struct *sd_quotad_process;
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 5a31d426116f..2f94bd723698 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -30,7 +30,6 @@
 #include "inode.h"
 #include "log.h"
 #include "meta_io.h"
-#include "ops_address.h"
 #include "quota.h"
 #include "rgrp.h"
 #include "trans.h"
@@ -1047,154 +1046,7 @@ fail:
 	return ERR_PTR(error);
 }
 
-/**
- * gfs2_rmdiri - Remove a directory
- * @dip: The parent directory of the directory to be removed
- * @name: The name of the directory to be removed
- * @ip: The GFS2 inode of the directory to be removed
- *
- * Assumes Glocks on dip and ip are held
- *
- * Returns: errno
- */
-
-int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
-		struct gfs2_inode *ip)
-{
-	struct qstr dotname;
-	int error;
-
-	if (ip->i_entries != 2) {
-		if (gfs2_consist_inode(ip))
-			gfs2_dinode_print(ip);
-		return -EIO;
-	}
-
-	error = gfs2_dir_del(dip, name);
-	if (error)
-		return error;
-
-	error = gfs2_change_nlink(dip, -1);
-	if (error)
-		return error;
-
-	gfs2_str2qstr(&dotname, ".");
-	error = gfs2_dir_del(ip, &dotname);
-	if (error)
-		return error;
-
-	gfs2_str2qstr(&dotname, "..");
-	error = gfs2_dir_del(ip, &dotname);
-	if (error)
-		return error;
-
-	/* It looks odd, but it really should be done twice */
-	error = gfs2_change_nlink(ip, -1);
-	if (error)
-		return error;
-
-	error = gfs2_change_nlink(ip, -1);
-	if (error)
-		return error;
-
-	return error;
-}
-
-/*
- * gfs2_unlink_ok - check to see that a inode is still in a directory
- * @dip: the directory
- * @name: the name of the file
- * @ip: the inode
- *
- * Assumes that the lock on (at least) @dip is held.
- *
- * Returns: 0 if the parent/child relationship is correct, errno if it isn't
- */
-
-int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
-		   const struct gfs2_inode *ip)
-{
-	int error;
-
-	if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
-		return -EPERM;
-
-	if ((dip->i_inode.i_mode & S_ISVTX) &&
-	    dip->i_inode.i_uid != current_fsuid() &&
-	    ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
-		return -EPERM;
-
-	if (IS_APPEND(&dip->i_inode))
-		return -EPERM;
-
-	error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
-	if (error)
-		return error;
-
-	error = gfs2_dir_check(&dip->i_inode, name, ip);
-	if (error)
-		return error;
-
-	return 0;
-}
-
-/**
- * gfs2_readlinki - return the contents of a symlink
- * @ip: the symlink's inode
- * @buf: a pointer to the buffer to be filled
- * @len: a pointer to the length of @buf
- *
- * If @buf is too small, a piece of memory is kmalloc()ed and needs
- * to be freed by the caller.
- *
- * Returns: errno
- */
-
-int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len)
-{
-	struct gfs2_holder i_gh;
-	struct buffer_head *dibh;
-	unsigned int x;
-	int error;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
-	error = gfs2_glock_nq(&i_gh);
-	if (error) {
-		gfs2_holder_uninit(&i_gh);
-		return error;
-	}
-
-	if (!ip->i_disksize) {
-		gfs2_consist_inode(ip);
-		error = -EIO;
-		goto out;
-	}
-
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (error)
-		goto out;
-
-	x = ip->i_disksize + 1;
-	if (x > *len) {
-		*buf = kmalloc(x, GFP_NOFS);
-		if (!*buf) {
-			error = -ENOMEM;
-			goto out_brelse;
-		}
-	}
-
-	memcpy(*buf, dibh->b_data + sizeof(struct gfs2_dinode), x);
-	*len = x;
-
-out_brelse:
-	brelse(dibh);
-out:
-	gfs2_glock_dq_uninit(&i_gh);
-	return error;
-}
-
-static int
-__gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
+static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
 {
 	struct buffer_head *dibh;
 	int error;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index c30be2b66580..c341aaf67adb 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -11,8 +11,16 @@
 #define __INODE_DOT_H__
 
 #include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/mm.h>
 #include "util.h"
 
+extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
+extern int gfs2_internal_read(struct gfs2_inode *ip,
+			      struct file_ra_state *ra_state,
+			      char *buf, loff_t *pos, unsigned size);
+extern void gfs2_set_aops(struct inode *inode);
+
 static inline int gfs2_is_stuffed(const struct gfs2_inode *ip)
 {
 	return !ip->i_height;
@@ -73,30 +81,26 @@ static inline void gfs2_inum_out(const struct gfs2_inode *ip,
 }
 
 
-void gfs2_set_iop(struct inode *inode);
-struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
-				u64 no_addr, u64 no_formal_ino,
-				int skip_freeing);
-struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
+extern void gfs2_set_iop(struct inode *inode);
+extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
+				       u64 no_addr, u64 no_formal_ino,
+				       int skip_freeing);
+extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
 
-int gfs2_inode_refresh(struct gfs2_inode *ip);
+extern int gfs2_inode_refresh(struct gfs2_inode *ip);
 
-int gfs2_dinode_dealloc(struct gfs2_inode *inode);
-int gfs2_change_nlink(struct gfs2_inode *ip, int diff);
-struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
-			   int is_root);
-struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
-			   unsigned int mode, dev_t dev);
-int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
-		struct gfs2_inode *ip);
-int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
-		   const struct gfs2_inode *ip);
-int gfs2_permission(struct inode *inode, int mask);
-int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
-int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
-struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
-void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
-void gfs2_dinode_print(const struct gfs2_inode *ip);
+extern int gfs2_dinode_dealloc(struct gfs2_inode *inode);
+extern int gfs2_change_nlink(struct gfs2_inode *ip, int diff);
+extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
+				  int is_root);
+extern struct inode *gfs2_createi(struct gfs2_holder *ghs,
+				  const struct qstr *name,
+				  unsigned int mode, dev_t dev);
+extern int gfs2_permission(struct inode *inode, int mask);
+extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
+extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
+extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
+extern void gfs2_dinode_print(const struct gfs2_inode *ip);
 
 extern const struct inode_operations gfs2_file_iops;
 extern const struct inode_operations gfs2_dir_iops;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 98918a756410..f2e449c595b4 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -120,7 +120,7 @@ __acquires(&sdp->sd_log_lock)
 			lock_buffer(bh);
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
-				submit_bh(WRITE, bh);
+				submit_bh(WRITE_SYNC_PLUG, bh);
 			} else {
 				unlock_buffer(bh);
 				brelse(bh);
@@ -604,7 +604,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
 		goto skip_barrier;
 	get_bh(bh);
-	submit_bh(WRITE_BARRIER | (1 << BIO_RW_META), bh);
+	submit_bh(WRITE_SYNC | (1 << BIO_RW_BARRIER) | (1 << BIO_RW_META), bh);
 	wait_on_buffer(bh);
 	if (buffer_eopnotsupp(bh)) {
 		clear_buffer_eopnotsupp(bh);
@@ -664,7 +664,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 		lock_buffer(bh);
 		if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) {
 			bh->b_end_io = end_buffer_write_sync;
-			submit_bh(WRITE, bh);
+			submit_bh(WRITE_SYNC_PLUG, bh);
 		} else {
 			unlock_buffer(bh);
 			brelse(bh);
@@ -764,7 +764,6 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
 	}
 	gfs2_log_unlock(sdp);
 
-	sdp->sd_vfs->s_dirt = 0;
 	up_write(&sdp->sd_log_flush_lock);
 
 	kfree(ai);
@@ -823,7 +822,6 @@ void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	log_refund(sdp, tr);
 	buf_lo_incore_commit(sdp, tr);
 
-	sdp->sd_vfs->s_dirt = 1;
 	up_read(&sdp->sd_log_flush_lock);
 
 	gfs2_log_lock(sdp);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 80e4f5f898bb..00315f50fa46 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -13,6 +13,8 @@
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
 #include <linux/gfs2_ondisk.h>
+#include <linux/bio.h>
+#include <linux/fs.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -189,7 +191,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 		}
 
 		gfs2_log_unlock(sdp);
-		submit_bh(WRITE, bh);
+		submit_bh(WRITE_SYNC_PLUG, bh);
 		gfs2_log_lock(sdp);
 
 		n = 0;
@@ -199,7 +201,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 			gfs2_log_unlock(sdp);
 			lock_buffer(bd2->bd_bh);
 			bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
-			submit_bh(WRITE, bh);
+			submit_bh(WRITE_SYNC_PLUG, bh);
 			gfs2_log_lock(sdp);
 			if (++n >= num)
 				break;
@@ -341,7 +343,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 		sdp->sd_log_num_revoke--;
 
 		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
-			submit_bh(WRITE, bh);
+			submit_bh(WRITE_SYNC_PLUG, bh);
 
 			bh = gfs2_log_get_buf(sdp);
 			mh = (struct gfs2_meta_header *)bh->b_data;
@@ -358,7 +360,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 	}
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
 
-	submit_bh(WRITE, bh);
+	submit_bh(WRITE_SYNC_PLUG, bh);
 }
 
 static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
@@ -560,7 +562,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
 	ptr = bh_log_ptr(bh);
 	
 	get_bh(bh);
-	submit_bh(WRITE, bh);
+	submit_bh(WRITE_SYNC_PLUG, bh);
 	gfs2_log_lock(sdp);
 	while(!list_empty(list)) {
 		bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list);
@@ -586,7 +588,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
 		} else {
 			bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh);
 		}
-		submit_bh(WRITE, bh1);
+		submit_bh(WRITE_SYNC_PLUG, bh1);
 		gfs2_log_lock(sdp);
 		ptr += 2;
 	}
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index a6892ed0840a..eacd78a5d082 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/gfs2_ondisk.h>
 #include <asm/atomic.h>
+#include <linux/slow-work.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -113,12 +114,18 @@ static int __init init_gfs2_fs(void)
 	if (error)
 		goto fail_unregister;
 
+	error = slow_work_register_user();
+	if (error)
+		goto fail_slow;
+
 	gfs2_register_debugfs();
 
 	printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__);
 
 	return 0;
 
+fail_slow:
+	unregister_filesystem(&gfs2meta_fs_type);
 fail_unregister:
 	unregister_filesystem(&gfs2_fs_type);
 fail:
@@ -156,6 +163,7 @@ static void __exit exit_gfs2_fs(void)
 	gfs2_unregister_debugfs();
 	unregister_filesystem(&gfs2_fs_type);
 	unregister_filesystem(&gfs2meta_fs_type);
+	slow_work_unregister_user();
 
 	kmem_cache_destroy(gfs2_quotad_cachep);
 	kmem_cache_destroy(gfs2_rgrpd_cachep);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 8d6f13256b26..cb8d7a93d5ec 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -31,19 +31,66 @@
 #include "rgrp.h"
 #include "trans.h"
 #include "util.h"
-#include "ops_address.h"
 
-static int aspace_get_block(struct inode *inode, sector_t lblock,
-			    struct buffer_head *bh_result, int create)
+static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
 {
-	gfs2_assert_warn(inode->i_sb->s_fs_info, 0);
-	return -EOPNOTSUPP;
-}
+	int err;
+	struct buffer_head *bh, *head;
+	int nr_underway = 0;
+	int write_op = (1 << BIO_RW_META) | ((wbc->sync_mode == WB_SYNC_ALL ?
+			WRITE_SYNC_PLUG : WRITE));
 
-static int gfs2_aspace_writepage(struct page *page,
-				 struct writeback_control *wbc)
-{
-	return block_write_full_page(page, aspace_get_block, wbc);
+	BUG_ON(!PageLocked(page));
+	BUG_ON(!page_has_buffers(page));
+
+	head = page_buffers(page);
+	bh = head;
+
+	do {
+		if (!buffer_mapped(bh))
+			continue;
+		/*
+		 * If it's a fully non-blocking write attempt and we cannot
+		 * lock the buffer then redirty the page.  Note that this can
+		 * potentially cause a busy-wait loop from pdflush and kswapd
+		 * activity, but those code paths have their own higher-level
+		 * throttling.
+		 */
+		if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
+			lock_buffer(bh);
+		} else if (!trylock_buffer(bh)) {
+			redirty_page_for_writepage(wbc, page);
+			continue;
+		}
+		if (test_clear_buffer_dirty(bh)) {
+			mark_buffer_async_write(bh);
+		} else {
+			unlock_buffer(bh);
+		}
+	} while ((bh = bh->b_this_page) != head);
+
+	/*
+	 * The page and its buffers are protected by PageWriteback(), so we can
+	 * drop the bh refcounts early.
+	 */
+	BUG_ON(PageWriteback(page));
+	set_page_writeback(page);
+
+	do {
+		struct buffer_head *next = bh->b_this_page;
+		if (buffer_async_write(bh)) {
+			submit_bh(write_op, bh);
+			nr_underway++;
+		}
+		bh = next;
+	} while (bh != head);
+	unlock_page(page);
+
+	err = 0;
+	if (nr_underway == 0)
+		end_page_writeback(page);
+
+	return err;
 }
 
 static const struct address_space_operations aspace_aops = {
@@ -201,16 +248,32 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
 int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 		   struct buffer_head **bhp)
 {
-	*bhp = gfs2_getbuf(gl, blkno, CREATE);
-	if (!buffer_uptodate(*bhp)) {
-		ll_rw_block(READ_META, 1, bhp);
-		if (flags & DIO_WAIT) {
-			int error = gfs2_meta_wait(gl->gl_sbd, *bhp);
-			if (error) {
-				brelse(*bhp);
-				return error;
-			}
-		}
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct buffer_head *bh;
+
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return -EIO;
+
+	*bhp = bh = gfs2_getbuf(gl, blkno, CREATE);
+
+	lock_buffer(bh);
+	if (buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return 0;
+	}
+	bh->b_end_io = end_buffer_read_sync;
+	get_bh(bh);
+	submit_bh(READ_SYNC | (1 << BIO_RW_META), bh);
+	if (!(flags & DIO_WAIT))
+		return 0;
+
+	wait_on_buffer(bh);
+	if (unlikely(!buffer_uptodate(bh))) {
+		struct gfs2_trans *tr = current->journal_info;
+		if (tr && tr->tr_touched)
+			gfs2_io_error_bh(sdp, bh);
+		brelse(bh);
+		return -EIO;
 	}
 
 	return 0;
@@ -404,7 +467,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
 	if (buffer_uptodate(first_bh))
 		goto out;
 	if (!buffer_locked(first_bh))
-		ll_rw_block(READ_META, 1, &first_bh);
+		ll_rw_block(READ_SYNC | (1 << BIO_RW_META), 1, &first_bh);
 
 	dblock++;
 	extlen--;
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
deleted file mode 100644
index f7e8527a21e0..000000000000
--- a/fs/gfs2/mount.c
+++ /dev/null
@@ -1,185 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/parser.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "super.h"
-#include "sys.h"
-#include "util.h"
-
-enum {
-	Opt_lockproto,
-	Opt_locktable,
-	Opt_hostdata,
-	Opt_spectator,
-	Opt_ignore_local_fs,
-	Opt_localflocks,
-	Opt_localcaching,
-	Opt_debug,
-	Opt_nodebug,
-	Opt_upgrade,
-	Opt_acl,
-	Opt_noacl,
-	Opt_quota_off,
-	Opt_quota_account,
-	Opt_quota_on,
-	Opt_quota,
-	Opt_noquota,
-	Opt_suiddir,
-	Opt_nosuiddir,
-	Opt_data_writeback,
-	Opt_data_ordered,
-	Opt_meta,
-	Opt_discard,
-	Opt_nodiscard,
-	Opt_err,
-};
-
-static const match_table_t tokens = {
-	{Opt_lockproto, "lockproto=%s"},
-	{Opt_locktable, "locktable=%s"},
-	{Opt_hostdata, "hostdata=%s"},
-	{Opt_spectator, "spectator"},
-	{Opt_ignore_local_fs, "ignore_local_fs"},
-	{Opt_localflocks, "localflocks"},
-	{Opt_localcaching, "localcaching"},
-	{Opt_debug, "debug"},
-	{Opt_nodebug, "nodebug"},
-	{Opt_upgrade, "upgrade"},
-	{Opt_acl, "acl"},
-	{Opt_noacl, "noacl"},
-	{Opt_quota_off, "quota=off"},
-	{Opt_quota_account, "quota=account"},
-	{Opt_quota_on, "quota=on"},
-	{Opt_quota, "quota"},
-	{Opt_noquota, "noquota"},
-	{Opt_suiddir, "suiddir"},
-	{Opt_nosuiddir, "nosuiddir"},
-	{Opt_data_writeback, "data=writeback"},
-	{Opt_data_ordered, "data=ordered"},
-	{Opt_meta, "meta"},
-	{Opt_discard, "discard"},
-	{Opt_nodiscard, "nodiscard"},
-	{Opt_err, NULL}
-};
-
-/**
- * gfs2_mount_args - Parse mount options
- * @sdp:
- * @data:
- *
- * Return: errno
- */
-
-int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options)
-{
-	char *o;
-	int token;
-	substring_t tmp[MAX_OPT_ARGS];
-
-	/* Split the options into tokens with the "," character and
-	   process them */
-
-	while (1) {
-		o = strsep(&options, ",");
-		if (o == NULL)
-			break;
-		if (*o == '\0')
-			continue;
-
-		token = match_token(o, tokens, tmp);
-		switch (token) {
-		case Opt_lockproto:
-			match_strlcpy(args->ar_lockproto, &tmp[0],
-				      GFS2_LOCKNAME_LEN);
-			break;
-		case Opt_locktable:
-			match_strlcpy(args->ar_locktable, &tmp[0],
-				      GFS2_LOCKNAME_LEN);
-			break;
-		case Opt_hostdata:
-			match_strlcpy(args->ar_hostdata, &tmp[0],
-				      GFS2_LOCKNAME_LEN);
-			break;
-		case Opt_spectator:
-			args->ar_spectator = 1;
-			break;
-		case Opt_ignore_local_fs:
-			args->ar_ignore_local_fs = 1;
-			break;
-		case Opt_localflocks:
-			args->ar_localflocks = 1;
-			break;
-		case Opt_localcaching:
-			args->ar_localcaching = 1;
-			break;
-		case Opt_debug:
-			args->ar_debug = 1;
-			break;
-		case Opt_nodebug:
-			args->ar_debug = 0;
-			break;
-		case Opt_upgrade:
-			args->ar_upgrade = 1;
-			break;
-		case Opt_acl:
-			args->ar_posix_acl = 1;
-			break;
-		case Opt_noacl:
-			args->ar_posix_acl = 0;
-			break;
-		case Opt_quota_off:
-		case Opt_noquota:
-			args->ar_quota = GFS2_QUOTA_OFF;
-			break;
-		case Opt_quota_account:
-			args->ar_quota = GFS2_QUOTA_ACCOUNT;
-			break;
-		case Opt_quota_on:
-		case Opt_quota:
-			args->ar_quota = GFS2_QUOTA_ON;
-			break;
-		case Opt_suiddir:
-			args->ar_suiddir = 1;
-			break;
-		case Opt_nosuiddir:
-			args->ar_suiddir = 0;
-			break;
-		case Opt_data_writeback:
-			args->ar_data = GFS2_DATA_WRITEBACK;
-			break;
-		case Opt_data_ordered:
-			args->ar_data = GFS2_DATA_ORDERED;
-			break;
-		case Opt_meta:
-			args->ar_meta = 1;
-			break;
-		case Opt_discard:
-			args->ar_discard = 1;
-			break;
-		case Opt_nodiscard:
-			args->ar_discard = 0;
-			break;
-		case Opt_err:
-		default:
-			fs_info(sdp, "invalid mount option: %s\n", o);
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-
diff --git a/fs/gfs2/ops_address.h b/fs/gfs2/ops_address.h
deleted file mode 100644
index 5da21285bba4..000000000000
--- a/fs/gfs2/ops_address.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#ifndef __OPS_ADDRESS_DOT_H__
-#define __OPS_ADDRESS_DOT_H__
-
-#include <linux/fs.h>
-#include <linux/buffer_head.h>
-#include <linux/mm.h>
-
-extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
-extern int gfs2_internal_read(struct gfs2_inode *ip,
-			      struct file_ra_state *ra_state,
-			      char *buf, loff_t *pos, unsigned size);
-extern void gfs2_set_aops(struct inode *inode);
-
-#endif /* __OPS_ADDRESS_DOT_H__ */
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 1ff9473ea753..cc34f271b3e7 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -17,6 +17,7 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/gfs2_ondisk.h>
+#include <linux/slow-work.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -55,8 +56,6 @@ static void gfs2_tune_init(struct gfs2_tune *gt)
 	spin_lock_init(&gt->gt_spin);
 
 	gt->gt_incore_log_blocks = 1024;
-	gt->gt_log_flush_secs = 60;
-	gt->gt_recoverd_secs = 60;
 	gt->gt_logd_secs = 1;
 	gt->gt_quota_simul_sync = 64;
 	gt->gt_quota_warn_period = 10;
@@ -526,11 +525,11 @@ static int init_sb(struct gfs2_sbd *sdp, int silent)
 	}
 
 	/* Set up the buffer cache and SB for real */
-	if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) {
+	if (sdp->sd_sb.sb_bsize < bdev_logical_block_size(sb->s_bdev)) {
 		ret = -EINVAL;
 		fs_err(sdp, "FS block size (%u) is too small for device "
 		       "block size (%u)\n",
-		       sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev));
+		       sdp->sd_sb.sb_bsize, bdev_logical_block_size(sb->s_bdev));
 		goto out;
 	}
 	if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
@@ -676,6 +675,7 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
 			break;
 
 		INIT_LIST_HEAD(&jd->extent_list);
+		slow_work_init(&jd->jd_work, &gfs2_recover_ops);
 		jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1);
 		if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
 			if (!jd->jd_inode)
@@ -701,14 +701,13 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 {
 	struct inode *master = sdp->sd_master_dir->d_inode;
 	struct gfs2_holder ji_gh;
-	struct task_struct *p;
 	struct gfs2_inode *ip;
 	int jindex = 1;
 	int error = 0;
 
 	if (undo) {
 		jindex = 0;
-		goto fail_recoverd;
+		goto fail_jinode_gh;
 	}
 
 	sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
@@ -801,18 +800,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 	gfs2_glock_dq_uninit(&ji_gh);
 	jindex = 0;
 
-	p = kthread_run(gfs2_recoverd, sdp, "gfs2_recoverd");
-	error = IS_ERR(p);
-	if (error) {
-		fs_err(sdp, "can't start recoverd thread: %d\n", error);
-		goto fail_jinode_gh;
-	}
-	sdp->sd_recoverd_process = p;
-
 	return 0;
 
-fail_recoverd:
-	kthread_stop(sdp->sd_recoverd_process);
 fail_jinode_gh:
 	if (!sdp->sd_args.ar_spectator)
 		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
@@ -1165,6 +1154,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 
 	sdp->sd_args.ar_quota = GFS2_QUOTA_DEFAULT;
 	sdp->sd_args.ar_data = GFS2_DATA_DEFAULT;
+	sdp->sd_args.ar_commit = 60;
 
 	error = gfs2_mount_args(sdp, &sdp->sd_args, data);
 	if (error) {
@@ -1172,8 +1162,10 @@ static int fill_super(struct super_block *sb, void *data, int silent)
 		goto fail;
 	}
 
-	if (sdp->sd_args.ar_spectator)
+	if (sdp->sd_args.ar_spectator) {
                 sb->s_flags |= MS_RDONLY;
+		set_bit(SDF_NORECOVERY, &sdp->sd_flags);
+	}
 	if (sdp->sd_args.ar_posix_acl)
 		sb->s_flags |= MS_POSIXACL;
 
@@ -1191,6 +1183,8 @@ static int fill_super(struct super_block *sb, void *data, int silent)
                                GFS2_BASIC_BLOCK_SHIFT;
 	sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
 
+	sdp->sd_tune.gt_log_flush_secs = sdp->sd_args.ar_commit;
+
 	error = init_names(sdp, silent);
 	if (error)
 		goto fail;
@@ -1279,9 +1273,22 @@ static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
 	return get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
 }
 
-static struct super_block *get_gfs2_sb(const char *dev_name)
+static int test_meta_super(struct super_block *s, void *ptr)
 {
-	struct super_block *sb;
+	struct block_device *bdev = ptr;
+	return (bdev == s->s_bdev);
+}
+
+static int set_meta_super(struct super_block *s, void *ptr)
+{
+	return -EINVAL;
+}
+
+static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
+			    const char *dev_name, void *data, struct vfsmount *mnt)
+{
+	struct super_block *s;
+	struct gfs2_sbd *sdp;
 	struct path path;
 	int error;
 
@@ -1289,30 +1296,17 @@ static struct super_block *get_gfs2_sb(const char *dev_name)
 	if (error) {
 		printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
 		       dev_name, error);
-		return NULL;
+		return error;
 	}
-	sb = path.dentry->d_inode->i_sb;
-	if (sb && (sb->s_type == &gfs2_fs_type))
-		atomic_inc(&sb->s_active);
-	else
-		sb = NULL;
+	s = sget(&gfs2_fs_type, test_meta_super, set_meta_super,
+		 path.dentry->d_inode->i_sb->s_bdev);
 	path_put(&path);
-	return sb;
-}
-
-static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
-			    const char *dev_name, void *data, struct vfsmount *mnt)
-{
-	struct super_block *sb = NULL;
-	struct gfs2_sbd *sdp;
-
-	sb = get_gfs2_sb(dev_name);
-	if (!sb) {
+	if (IS_ERR(s)) {
 		printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
-		return -ENOENT;
+		return PTR_ERR(s);
 	}
-	sdp = sb->s_fs_info;
-	mnt->mnt_sb = sb;
+	sdp = s->s_fs_info;
+	mnt->mnt_sb = s;
 	mnt->mnt_root = dget(sdp->sd_master_dir);
 	return 0;
 }
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 1c70fa5168d6..f8bd20baf99c 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -262,6 +262,44 @@ out_parent:
 	return error;
 }
 
+/*
+ * gfs2_unlink_ok - check to see that a inode is still in a directory
+ * @dip: the directory
+ * @name: the name of the file
+ * @ip: the inode
+ *
+ * Assumes that the lock on (at least) @dip is held.
+ *
+ * Returns: 0 if the parent/child relationship is correct, errno if it isn't
+ */
+
+static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
+			  const struct gfs2_inode *ip)
+{
+	int error;
+
+	if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
+		return -EPERM;
+
+	if ((dip->i_inode.i_mode & S_ISVTX) &&
+	    dip->i_inode.i_uid != current_fsuid() &&
+	    ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
+		return -EPERM;
+
+	if (IS_APPEND(&dip->i_inode))
+		return -EPERM;
+
+	error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
+	if (error)
+		return error;
+
+	error = gfs2_dir_check(&dip->i_inode, name, ip);
+	if (error)
+		return error;
+
+	return 0;
+}
+
 /**
  * gfs2_unlink - Unlink a file
  * @dir: The inode of the directory containing the file to unlink
@@ -472,6 +510,59 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	return 0;
 }
 
+/**
+ * gfs2_rmdiri - Remove a directory
+ * @dip: The parent directory of the directory to be removed
+ * @name: The name of the directory to be removed
+ * @ip: The GFS2 inode of the directory to be removed
+ *
+ * Assumes Glocks on dip and ip are held
+ *
+ * Returns: errno
+ */
+
+static int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
+		       struct gfs2_inode *ip)
+{
+	struct qstr dotname;
+	int error;
+
+	if (ip->i_entries != 2) {
+		if (gfs2_consist_inode(ip))
+			gfs2_dinode_print(ip);
+		return -EIO;
+	}
+
+	error = gfs2_dir_del(dip, name);
+	if (error)
+		return error;
+
+	error = gfs2_change_nlink(dip, -1);
+	if (error)
+		return error;
+
+	gfs2_str2qstr(&dotname, ".");
+	error = gfs2_dir_del(ip, &dotname);
+	if (error)
+		return error;
+
+	gfs2_str2qstr(&dotname, "..");
+	error = gfs2_dir_del(ip, &dotname);
+	if (error)
+		return error;
+
+	/* It looks odd, but it really should be done twice */
+	error = gfs2_change_nlink(ip, -1);
+	if (error)
+		return error;
+
+	error = gfs2_change_nlink(ip, -1);
+	if (error)
+		return error;
+
+	return error;
+}
+
 /**
  * gfs2_rmdir - Remove a directory
  * @dir: The parent directory of the directory to be removed
@@ -884,6 +975,61 @@ out:
 	return error;
 }
 
+/**
+ * gfs2_readlinki - return the contents of a symlink
+ * @ip: the symlink's inode
+ * @buf: a pointer to the buffer to be filled
+ * @len: a pointer to the length of @buf
+ *
+ * If @buf is too small, a piece of memory is kmalloc()ed and needs
+ * to be freed by the caller.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len)
+{
+	struct gfs2_holder i_gh;
+	struct buffer_head *dibh;
+	unsigned int x;
+	int error;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
+	error = gfs2_glock_nq(&i_gh);
+	if (error) {
+		gfs2_holder_uninit(&i_gh);
+		return error;
+	}
+
+	if (!ip->i_disksize) {
+		gfs2_consist_inode(ip);
+		error = -EIO;
+		goto out;
+	}
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (error)
+		goto out;
+
+	x = ip->i_disksize + 1;
+	if (x > *len) {
+		*buf = kmalloc(x, GFP_NOFS);
+		if (!*buf) {
+			error = -ENOMEM;
+			goto out_brelse;
+		}
+	}
+
+	memcpy(*buf, dibh->b_data + sizeof(struct gfs2_dinode), x);
+	*len = x;
+
+out_brelse:
+	brelse(dibh);
+out:
+	gfs2_glock_dq_uninit(&i_gh);
+	return error;
+}
+
 /**
  * gfs2_readlink - Read the value of a symlink
  * @dentry: the symlink
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
deleted file mode 100644
index 458019569dcb..000000000000
--- a/fs/gfs2/ops_super.c
+++ /dev/null
@@ -1,723 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/statfs.h>
-#include <linux/seq_file.h>
-#include <linux/mount.h>
-#include <linux/kthread.h>
-#include <linux/delay.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/crc32.h>
-#include <linux/time.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "glock.h"
-#include "inode.h"
-#include "log.h"
-#include "quota.h"
-#include "recovery.h"
-#include "rgrp.h"
-#include "super.h"
-#include "sys.h"
-#include "util.h"
-#include "trans.h"
-#include "dir.h"
-#include "eattr.h"
-#include "bmap.h"
-#include "meta_io.h"
-
-#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x)
-
-/**
- * gfs2_write_inode - Make sure the inode is stable on the disk
- * @inode: The inode
- * @sync: synchronous write flag
- *
- * Returns: errno
- */
-
-static int gfs2_write_inode(struct inode *inode, int sync)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_holder gh;
-	struct buffer_head *bh;
-	struct timespec atime;
-	struct gfs2_dinode *di;
-	int ret = 0;
-
-	/* Check this is a "normal" inode, etc */
-	if (!test_bit(GIF_USER, &ip->i_flags) ||
-	    (current->flags & PF_MEMALLOC))
-		return 0;
-	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-	if (ret)
-		goto do_flush;
-	ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
-	if (ret)
-		goto do_unlock;
-	ret = gfs2_meta_inode_buffer(ip, &bh);
-	if (ret == 0) {
-		di = (struct gfs2_dinode *)bh->b_data;
-		atime.tv_sec = be64_to_cpu(di->di_atime);
-		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
-		if (timespec_compare(&inode->i_atime, &atime) > 0) {
-			gfs2_trans_add_bh(ip->i_gl, bh, 1);
-			gfs2_dinode_out(ip, bh->b_data);
-		}
-		brelse(bh);
-	}
-	gfs2_trans_end(sdp);
-do_unlock:
-	gfs2_glock_dq_uninit(&gh);
-do_flush:
-	if (sync != 0)
-		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
-	return ret;
-}
-
-/**
- * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
- * @sdp: the filesystem
- *
- * Returns: errno
- */
-
-static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
-{
-	struct gfs2_holder t_gh;
-	int error;
-
-	gfs2_quota_sync(sdp);
-	gfs2_statfs_sync(sdp);
-
-	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
-				   &t_gh);
-	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
-		return error;
-
-	gfs2_meta_syncfs(sdp);
-	gfs2_log_shutdown(sdp);
-
-	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
-
-	if (t_gh.gh_gl)
-		gfs2_glock_dq_uninit(&t_gh);
-
-	gfs2_quota_cleanup(sdp);
-
-	return error;
-}
-
-/**
- * gfs2_put_super - Unmount the filesystem
- * @sb: The VFS superblock
- *
- */
-
-static void gfs2_put_super(struct super_block *sb)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	int error;
-
-	/*  Unfreeze the filesystem, if we need to  */
-
-	mutex_lock(&sdp->sd_freeze_lock);
-	if (sdp->sd_freeze_count)
-		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
-	mutex_unlock(&sdp->sd_freeze_lock);
-
-	kthread_stop(sdp->sd_quotad_process);
-	kthread_stop(sdp->sd_logd_process);
-	kthread_stop(sdp->sd_recoverd_process);
-
-	if (!(sb->s_flags & MS_RDONLY)) {
-		error = gfs2_make_fs_ro(sdp);
-		if (error)
-			gfs2_io_error(sdp);
-	}
-	/*  At this point, we're through modifying the disk  */
-
-	/*  Release stuff  */
-
-	iput(sdp->sd_jindex);
-	iput(sdp->sd_inum_inode);
-	iput(sdp->sd_statfs_inode);
-	iput(sdp->sd_rindex);
-	iput(sdp->sd_quota_inode);
-
-	gfs2_glock_put(sdp->sd_rename_gl);
-	gfs2_glock_put(sdp->sd_trans_gl);
-
-	if (!sdp->sd_args.ar_spectator) {
-		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
-		iput(sdp->sd_ir_inode);
-		iput(sdp->sd_sc_inode);
-		iput(sdp->sd_qc_inode);
-	}
-
-	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
-	gfs2_clear_rgrpd(sdp);
-	gfs2_jindex_free(sdp);
-	/*  Take apart glock structures and buffer lists  */
-	gfs2_gl_hash_clear(sdp);
-	/*  Unmount the locking protocol  */
-	gfs2_lm_unmount(sdp);
-
-	/*  At this point, we're through participating in the lockspace  */
-	gfs2_sys_fs_del(sdp);
-}
-
-/**
- * gfs2_write_super
- * @sb: the superblock
- *
- */
-
-static void gfs2_write_super(struct super_block *sb)
-{
-	sb->s_dirt = 0;
-}
-
-/**
- * gfs2_sync_fs - sync the filesystem
- * @sb: the superblock
- *
- * Flushes the log to disk.
- */
-
-static int gfs2_sync_fs(struct super_block *sb, int wait)
-{
-	sb->s_dirt = 0;
-	if (wait && sb->s_fs_info)
-		gfs2_log_flush(sb->s_fs_info, NULL);
-	return 0;
-}
-
-/**
- * gfs2_freeze - prevent further writes to the filesystem
- * @sb: the VFS structure for the filesystem
- *
- */
-
-static int gfs2_freeze(struct super_block *sb)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	int error;
-
-	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
-		return -EINVAL;
-
-	for (;;) {
-		error = gfs2_freeze_fs(sdp);
-		if (!error)
-			break;
-
-		switch (error) {
-		case -EBUSY:
-			fs_err(sdp, "waiting for recovery before freeze\n");
-			break;
-
-		default:
-			fs_err(sdp, "error freezing FS: %d\n", error);
-			break;
-		}
-
-		fs_err(sdp, "retrying...\n");
-		msleep(1000);
-	}
-	return 0;
-}
-
-/**
- * gfs2_unfreeze - reallow writes to the filesystem
- * @sb: the VFS structure for the filesystem
- *
- */
-
-static int gfs2_unfreeze(struct super_block *sb)
-{
-	gfs2_unfreeze_fs(sb->s_fs_info);
-	return 0;
-}
-
-/**
- * statfs_fill - fill in the sg for a given RG
- * @rgd: the RG
- * @sc: the sc structure
- *
- * Returns: 0 on success, -ESTALE if the LVB is invalid
- */
-
-static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
-			    struct gfs2_statfs_change_host *sc)
-{
-	gfs2_rgrp_verify(rgd);
-	sc->sc_total += rgd->rd_data;
-	sc->sc_free += rgd->rd_free;
-	sc->sc_dinodes += rgd->rd_dinodes;
-	return 0;
-}
-
-/**
- * gfs2_statfs_slow - Stat a filesystem using asynchronous locking
- * @sdp: the filesystem
- * @sc: the sc info that will be returned
- *
- * Any error (other than a signal) will cause this routine to fall back
- * to the synchronous version.
- *
- * FIXME: This really shouldn't busy wait like this.
- *
- * Returns: errno
- */
-
-static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
-{
-	struct gfs2_holder ri_gh;
-	struct gfs2_rgrpd *rgd_next;
-	struct gfs2_holder *gha, *gh;
-	unsigned int slots = 64;
-	unsigned int x;
-	int done;
-	int error = 0, err;
-
-	memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
-	gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
-	if (!gha)
-		return -ENOMEM;
-
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		goto out;
-
-	rgd_next = gfs2_rgrpd_get_first(sdp);
-
-	for (;;) {
-		done = 1;
-
-		for (x = 0; x < slots; x++) {
-			gh = gha + x;
-
-			if (gh->gh_gl && gfs2_glock_poll(gh)) {
-				err = gfs2_glock_wait(gh);
-				if (err) {
-					gfs2_holder_uninit(gh);
-					error = err;
-				} else {
-					if (!error)
-						error = statfs_slow_fill(
-							gh->gh_gl->gl_object, sc);
-					gfs2_glock_dq_uninit(gh);
-				}
-			}
-
-			if (gh->gh_gl)
-				done = 0;
-			else if (rgd_next && !error) {
-				error = gfs2_glock_nq_init(rgd_next->rd_gl,
-							   LM_ST_SHARED,
-							   GL_ASYNC,
-							   gh);
-				rgd_next = gfs2_rgrpd_get_next(rgd_next);
-				done = 0;
-			}
-
-			if (signal_pending(current))
-				error = -ERESTARTSYS;
-		}
-
-		if (done)
-			break;
-
-		yield();
-	}
-
-	gfs2_glock_dq_uninit(&ri_gh);
-
-out:
-	kfree(gha);
-	return error;
-}
-
-/**
- * gfs2_statfs_i - Do a statfs
- * @sdp: the filesystem
- * @sg: the sg structure
- *
- * Returns: errno
- */
-
-static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
-{
-	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
-	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
-
-	spin_lock(&sdp->sd_statfs_spin);
-
-	*sc = *m_sc;
-	sc->sc_total += l_sc->sc_total;
-	sc->sc_free += l_sc->sc_free;
-	sc->sc_dinodes += l_sc->sc_dinodes;
-
-	spin_unlock(&sdp->sd_statfs_spin);
-
-	if (sc->sc_free < 0)
-		sc->sc_free = 0;
-	if (sc->sc_free > sc->sc_total)
-		sc->sc_free = sc->sc_total;
-	if (sc->sc_dinodes < 0)
-		sc->sc_dinodes = 0;
-
-	return 0;
-}
-
-/**
- * gfs2_statfs - Gather and return stats about the filesystem
- * @sb: The superblock
- * @statfsbuf: The buffer
- *
- * Returns: 0 on success or error code
- */
-
-static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
-{
-	struct super_block *sb = dentry->d_inode->i_sb;
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	struct gfs2_statfs_change_host sc;
-	int error;
-
-	if (gfs2_tune_get(sdp, gt_statfs_slow))
-		error = gfs2_statfs_slow(sdp, &sc);
-	else
-		error = gfs2_statfs_i(sdp, &sc);
-
-	if (error)
-		return error;
-
-	buf->f_type = GFS2_MAGIC;
-	buf->f_bsize = sdp->sd_sb.sb_bsize;
-	buf->f_blocks = sc.sc_total;
-	buf->f_bfree = sc.sc_free;
-	buf->f_bavail = sc.sc_free;
-	buf->f_files = sc.sc_dinodes + sc.sc_free;
-	buf->f_ffree = sc.sc_free;
-	buf->f_namelen = GFS2_FNAMESIZE;
-
-	return 0;
-}
-
-/**
- * gfs2_remount_fs - called when the FS is remounted
- * @sb:  the filesystem
- * @flags:  the remount flags
- * @data:  extra data passed in (not used right now)
- *
- * Returns: errno
- */
-
-static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
-{
-	struct gfs2_sbd *sdp = sb->s_fs_info;
-	struct gfs2_args args = sdp->sd_args; /* Default to current settings */
-	int error;
-
-	error = gfs2_mount_args(sdp, &args, data);
-	if (error)
-		return error;
-
-	/* Not allowed to change locking details */
-	if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) ||
-	    strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) ||
-	    strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata))
-		return -EINVAL;
-
-	/* Some flags must not be changed */
-	if (args_neq(&args, &sdp->sd_args, spectator) ||
-	    args_neq(&args, &sdp->sd_args, ignore_local_fs) ||
-	    args_neq(&args, &sdp->sd_args, localflocks) ||
-	    args_neq(&args, &sdp->sd_args, localcaching) ||
-	    args_neq(&args, &sdp->sd_args, meta))
-		return -EINVAL;
-
-	if (sdp->sd_args.ar_spectator)
-		*flags |= MS_RDONLY;
-
-	if ((sb->s_flags ^ *flags) & MS_RDONLY) {
-		if (*flags & MS_RDONLY)
-			error = gfs2_make_fs_ro(sdp);
-		else
-			error = gfs2_make_fs_rw(sdp);
-		if (error)
-			return error;
-	}
-
-	sdp->sd_args = args;
-	if (sdp->sd_args.ar_posix_acl)
-		sb->s_flags |= MS_POSIXACL;
-	else
-		sb->s_flags &= ~MS_POSIXACL;
-	return 0;
-}
-
-/**
- * gfs2_drop_inode - Drop an inode (test for remote unlink)
- * @inode: The inode to drop
- *
- * If we've received a callback on an iopen lock then its because a
- * remote node tried to deallocate the inode but failed due to this node
- * still having the inode open. Here we mark the link count zero
- * since we know that it must have reached zero if the GLF_DEMOTE flag
- * is set on the iopen glock. If we didn't do a disk read since the
- * remote node removed the final link then we might otherwise miss
- * this event. This check ensures that this node will deallocate the
- * inode's blocks, or alternatively pass the baton on to another
- * node for later deallocation.
- */
-
-static void gfs2_drop_inode(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-
-	if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) {
-		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
-		if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
-			clear_nlink(inode);
-	}
-	generic_drop_inode(inode);
-}
-
-/**
- * gfs2_clear_inode - Deallocate an inode when VFS is done with it
- * @inode: The VFS inode
- *
- */
-
-static void gfs2_clear_inode(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-
-	/* This tells us its a "real" inode and not one which only
-	 * serves to contain an address space (see rgrp.c, meta_io.c)
-	 * which therefore doesn't have its own glocks.
-	 */
-	if (test_bit(GIF_USER, &ip->i_flags)) {
-		ip->i_gl->gl_object = NULL;
-		gfs2_glock_put(ip->i_gl);
-		ip->i_gl = NULL;
-		if (ip->i_iopen_gh.gh_gl) {
-			ip->i_iopen_gh.gh_gl->gl_object = NULL;
-			gfs2_glock_dq_uninit(&ip->i_iopen_gh);
-		}
-	}
-}
-
-static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
-{
-	do {
-		if (d1 == d2)
-			return 1;
-		d1 = d1->d_parent;
-	} while (!IS_ROOT(d1));
-	return 0;
-}
-
-/**
- * gfs2_show_options - Show mount options for /proc/mounts
- * @s: seq_file structure
- * @mnt: vfsmount
- *
- * Returns: 0 on success or error code
- */
-
-static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
-{
-	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
-	struct gfs2_args *args = &sdp->sd_args;
-
-	if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
-		seq_printf(s, ",meta");
-	if (args->ar_lockproto[0])
-		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
-	if (args->ar_locktable[0])
-		seq_printf(s, ",locktable=%s", args->ar_locktable);
-	if (args->ar_hostdata[0])
-		seq_printf(s, ",hostdata=%s", args->ar_hostdata);
-	if (args->ar_spectator)
-		seq_printf(s, ",spectator");
-	if (args->ar_ignore_local_fs)
-		seq_printf(s, ",ignore_local_fs");
-	if (args->ar_localflocks)
-		seq_printf(s, ",localflocks");
-	if (args->ar_localcaching)
-		seq_printf(s, ",localcaching");
-	if (args->ar_debug)
-		seq_printf(s, ",debug");
-	if (args->ar_upgrade)
-		seq_printf(s, ",upgrade");
-	if (args->ar_posix_acl)
-		seq_printf(s, ",acl");
-	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
-		char *state;
-		switch (args->ar_quota) {
-		case GFS2_QUOTA_OFF:
-			state = "off";
-			break;
-		case GFS2_QUOTA_ACCOUNT:
-			state = "account";
-			break;
-		case GFS2_QUOTA_ON:
-			state = "on";
-			break;
-		default:
-			state = "unknown";
-			break;
-		}
-		seq_printf(s, ",quota=%s", state);
-	}
-	if (args->ar_suiddir)
-		seq_printf(s, ",suiddir");
-	if (args->ar_data != GFS2_DATA_DEFAULT) {
-		char *state;
-		switch (args->ar_data) {
-		case GFS2_DATA_WRITEBACK:
-			state = "writeback";
-			break;
-		case GFS2_DATA_ORDERED:
-			state = "ordered";
-			break;
-		default:
-			state = "unknown";
-			break;
-		}
-		seq_printf(s, ",data=%s", state);
-	}
-	if (args->ar_discard)
-		seq_printf(s, ",discard");
-
-	return 0;
-}
-
-/*
- * We have to (at the moment) hold the inodes main lock to cover
- * the gap between unlocking the shared lock on the iopen lock and
- * taking the exclusive lock. I'd rather do a shared -> exclusive
- * conversion on the iopen lock, but we can change that later. This
- * is safe, just less efficient.
- */
-
-static void gfs2_delete_inode(struct inode *inode)
-{
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_holder gh;
-	int error;
-
-	if (!test_bit(GIF_USER, &ip->i_flags))
-		goto out;
-
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-	if (unlikely(error)) {
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
-		goto out;
-	}
-
-	gfs2_glock_dq_wait(&ip->i_iopen_gh);
-	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
-	error = gfs2_glock_nq(&ip->i_iopen_gh);
-	if (error)
-		goto out_truncate;
-
-	if (S_ISDIR(inode->i_mode) &&
-	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
-		error = gfs2_dir_exhash_dealloc(ip);
-		if (error)
-			goto out_unlock;
-	}
-
-	if (ip->i_eattr) {
-		error = gfs2_ea_dealloc(ip);
-		if (error)
-			goto out_unlock;
-	}
-
-	if (!gfs2_is_stuffed(ip)) {
-		error = gfs2_file_dealloc(ip);
-		if (error)
-			goto out_unlock;
-	}
-
-	error = gfs2_dinode_dealloc(ip);
-	if (error)
-		goto out_unlock;
-
-out_truncate:
-	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
-	if (error)
-		goto out_unlock;
-	/* Needs to be done before glock release & also in a transaction */
-	truncate_inode_pages(&inode->i_data, 0);
-	gfs2_trans_end(sdp);
-
-out_unlock:
-	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
-		gfs2_glock_dq(&ip->i_iopen_gh);
-	gfs2_holder_uninit(&ip->i_iopen_gh);
-	gfs2_glock_dq_uninit(&gh);
-	if (error && error != GLR_TRYFAILED)
-		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
-out:
-	truncate_inode_pages(&inode->i_data, 0);
-	clear_inode(inode);
-}
-
-static struct inode *gfs2_alloc_inode(struct super_block *sb)
-{
-	struct gfs2_inode *ip;
-
-	ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL);
-	if (ip) {
-		ip->i_flags = 0;
-		ip->i_gl = NULL;
-	}
-	return &ip->i_inode;
-}
-
-static void gfs2_destroy_inode(struct inode *inode)
-{
-	kmem_cache_free(gfs2_inode_cachep, inode);
-}
-
-const struct super_operations gfs2_super_ops = {
-	.alloc_inode		= gfs2_alloc_inode,
-	.destroy_inode		= gfs2_destroy_inode,
-	.write_inode		= gfs2_write_inode,
-	.delete_inode		= gfs2_delete_inode,
-	.put_super		= gfs2_put_super,
-	.write_super		= gfs2_write_super,
-	.sync_fs		= gfs2_sync_fs,
-	.freeze_fs 		= gfs2_freeze,
-	.unfreeze_fs		= gfs2_unfreeze,
-	.statfs			= gfs2_statfs,
-	.remount_fs		= gfs2_remount_fs,
-	.clear_inode		= gfs2_clear_inode,
-	.drop_inode		= gfs2_drop_inode,
-	.show_options		= gfs2_show_options,
-};
-
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 152e6c4a0dca..2e9b9326bfc9 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -60,7 +60,6 @@
 #include "super.h"
 #include "trans.h"
 #include "inode.h"
-#include "ops_address.h"
 #include "util.h"
 
 #define QUOTA_USER 1
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 247e8f7d6b3d..59d2695509d3 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -13,8 +13,7 @@
 #include <linux/buffer_head.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
-#include <linux/kthread.h>
-#include <linux/freezer.h>
+#include <linux/slow-work.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -441,18 +440,25 @@ static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
         kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
 }
 
-/**
- * gfs2_recover_journal - recover a given journal
- * @jd: the struct gfs2_jdesc describing the journal
- *
- * Acquire the journal's lock, check to see if the journal is clean, and
- * do recovery if necessary.
- *
- * Returns: errno
- */
-
-int gfs2_recover_journal(struct gfs2_jdesc *jd)
+static int gfs2_recover_get_ref(struct slow_work *work)
 {
+	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
+	if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags))
+		return -EBUSY;
+	return 0;
+}
+
+static void gfs2_recover_put_ref(struct slow_work *work)
+{
+	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
+	clear_bit(JDF_RECOVERY, &jd->jd_flags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
+}
+
+static void gfs2_recover_work(struct slow_work *work)
+{
+	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
 	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
 	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
 	struct gfs2_log_header_host head;
@@ -569,7 +575,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd)
 		gfs2_glock_dq_uninit(&j_gh);
 
 	fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
-	return 0;
+	return;
 
 fail_gunlock_tr:
 	gfs2_glock_dq_uninit(&t_gh);
@@ -584,70 +590,28 @@ fail_gunlock_j:
 
 fail:
 	gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
-	return error;
 }
 
-static struct gfs2_jdesc *gfs2_jdesc_find_dirty(struct gfs2_sbd *sdp)
+struct slow_work_ops gfs2_recover_ops = {
+	.get_ref = gfs2_recover_get_ref,
+	.put_ref = gfs2_recover_put_ref,
+	.execute = gfs2_recover_work,
+};
+
+
+static int gfs2_recovery_wait(void *word)
 {
-	struct gfs2_jdesc *jd;
-	int found = 0;
-
-	spin_lock(&sdp->sd_jindex_spin);
-
-	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
-		if (jd->jd_dirty) {
-			jd->jd_dirty = 0;
-			found = 1;
-			break;
-		}
-	}
-	spin_unlock(&sdp->sd_jindex_spin);
-
-	if (!found)
-		jd = NULL;
-
-	return jd;
-}
-
-/**
- * gfs2_check_journals - Recover any dirty journals
- * @sdp: the filesystem
- *
- */
-
-static void gfs2_check_journals(struct gfs2_sbd *sdp)
-{
-	struct gfs2_jdesc *jd;
-
-	for (;;) {
-		jd = gfs2_jdesc_find_dirty(sdp);
-		if (!jd)
-			break;
-
-		if (jd != sdp->sd_jdesc)
-			gfs2_recover_journal(jd);
-	}
-}
-
-/**
- * gfs2_recoverd - Recover dead machine's journals
- * @sdp: Pointer to GFS2 superblock
- *
- */
-
-int gfs2_recoverd(void *data)
-{
-	struct gfs2_sbd *sdp = data;
-	unsigned long t;
-
-	while (!kthread_should_stop()) {
-		gfs2_check_journals(sdp);
-		t = gfs2_tune_get(sdp,  gt_recoverd_secs) * HZ;
-		if (freezing(current))
-			refrigerator();
-		schedule_timeout_interruptible(t);
-	}
-
+	schedule();
+	return 0;
+}
+
+int gfs2_recover_journal(struct gfs2_jdesc *jd)
+{
+	int rv;
+	rv = slow_work_enqueue(&jd->jd_work);
+	if (rv)
+		return rv;
+	wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, TASK_UNINTERRUPTIBLE);
 	return 0;
 }
 
diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h
index a8218ea15b57..1616ac22569a 100644
--- a/fs/gfs2/recovery.h
+++ b/fs/gfs2/recovery.h
@@ -28,7 +28,7 @@ extern void gfs2_revoke_clean(struct gfs2_sbd *sdp);
 extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
 		    struct gfs2_log_header_host *head);
 extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd);
-extern int gfs2_recoverd(void *data);
+extern struct slow_work_ops gfs2_recover_ops;
 
 #endif /* __RECOVERY_DOT_H__ */
 
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 565038243fa2..de3239731db8 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -29,7 +29,6 @@
 #include "util.h"
 #include "log.h"
 #include "inode.h"
-#include "ops_address.h"
 
 #define BFITNOENT ((u32)~0)
 #define NO_BLOCK ((u64)~0)
@@ -442,6 +441,7 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd)
 	for (x = 0; x < length; x++) {
 		bi = rgd->rd_bits + x;
 
+		bi->bi_flags = 0;
 		/* small rgrp; bitmap stored completely in header block */
 		if (length == 1) {
 			bytes = bytes_left;
@@ -580,7 +580,6 @@ static int read_rindex_entry(struct gfs2_inode *ip,
 
 	rgd->rd_gl->gl_object = rgd;
 	rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
-	rgd->rd_flags |= GFS2_RDF_CHECK;
 	return error;
 }
 
@@ -701,10 +700,9 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
 	u32 rg_flags;
 
 	rg_flags = be32_to_cpu(str->rg_flags);
-	if (rg_flags & GFS2_RGF_NOALLOC)
-		rgd->rd_flags |= GFS2_RDF_NOALLOC;
-	else
-		rgd->rd_flags &= ~GFS2_RDF_NOALLOC;
+	rg_flags &= ~GFS2_RDF_MASK;
+	rgd->rd_flags &= GFS2_RDF_MASK;
+	rgd->rd_flags |= rg_flags;
 	rgd->rd_free = be32_to_cpu(str->rg_free);
 	rgd->rd_dinodes = be32_to_cpu(str->rg_dinodes);
 	rgd->rd_igeneration = be64_to_cpu(str->rg_igeneration);
@@ -713,11 +711,8 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
 static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
 {
 	struct gfs2_rgrp *str = buf;
-	u32 rg_flags = 0;
 
-	if (rgd->rd_flags & GFS2_RDF_NOALLOC)
-		rg_flags |= GFS2_RGF_NOALLOC;
-	str->rg_flags = cpu_to_be32(rg_flags);
+	str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK);
 	str->rg_free = cpu_to_be32(rgd->rd_free);
 	str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes);
 	str->__pad = cpu_to_be32(0);
@@ -775,8 +770,10 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 	}
 
 	if (!(rgd->rd_flags & GFS2_RDF_UPTODATE)) {
+		for (x = 0; x < length; x++)
+			clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags);
 		gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
-		rgd->rd_flags |= GFS2_RDF_UPTODATE;
+		rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
 	}
 
 	spin_lock(&sdp->sd_rindex_spin);
@@ -845,7 +842,7 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
 	struct super_block *sb = sdp->sd_vfs;
 	struct block_device *bdev = sb->s_bdev;
 	const unsigned int sects_per_blk = sdp->sd_sb.sb_bsize /
-					   bdev_hardsect_size(sb->s_bdev);
+					   bdev_logical_block_size(sb->s_bdev);
 	u64 blk;
 	sector_t start = 0;
 	sector_t nr_sects = 0;
@@ -903,6 +900,7 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd)
 			continue;
 		if (sdp->sd_args.ar_discard)
 			gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bi);
+		clear_bit(GBF_FULL, &bi->bi_flags);
 		memcpy(bi->bi_clone + bi->bi_offset,
 		       bi->bi_bh->b_data + bi->bi_offset, bi->bi_len);
 	}
@@ -942,7 +940,7 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
 	struct gfs2_sbd *sdp = rgd->rd_sbd;
 	int ret = 0;
 
-	if (rgd->rd_flags & GFS2_RDF_NOALLOC)
+	if (rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR))
 		return 0;
 
 	spin_lock(&sdp->sd_rindex_spin);
@@ -1315,30 +1313,37 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 {
 	struct gfs2_bitmap *bi = NULL;
 	const u32 length = rgd->rd_length;
-	u32 blk = 0;
+	u32 blk = BFITNOENT;
 	unsigned int buf, x;
 	const unsigned int elen = *n;
-	const u8 *buffer;
+	const u8 *buffer = NULL;
 
 	*n = 0;
 	/* Find bitmap block that contains bits for goal block */
 	for (buf = 0; buf < length; buf++) {
 		bi = rgd->rd_bits + buf;
-		if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY)
-			break;
+		/* Convert scope of "goal" from rgrp-wide to within found bit block */
+		if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) {
+			goal -= bi->bi_start * GFS2_NBBY;
+			goto do_search;
+		}
 	}
+	buf = 0;
+	goal = 0;
 
-	gfs2_assert(rgd->rd_sbd, buf < length);
-
-	/* Convert scope of "goal" from rgrp-wide to within found bit block */
-	goal -= bi->bi_start * GFS2_NBBY;
-
+do_search:
 	/* Search (up to entire) bitmap in this rgrp for allocatable block.
 	   "x <= length", instead of "x < length", because we typically start
 	   the search in the middle of a bit block, but if we can't find an
 	   allocatable block anywhere else, we want to be able wrap around and
 	   search in the first part of our first-searched bit block.  */
 	for (x = 0; x <= length; x++) {
+		bi = rgd->rd_bits + buf;
+
+		if (test_bit(GBF_FULL, &bi->bi_flags) &&
+		    (old_state == GFS2_BLKST_FREE))
+			goto skip;
+
 		/* The GFS2_BLKST_UNLINKED state doesn't apply to the clone
 		   bitmaps, so we must search the originals for that. */
 		buffer = bi->bi_bh->b_data + bi->bi_offset;
@@ -1349,33 +1354,39 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
 		if (blk != BFITNOENT)
 			break;
 
+		if ((goal == 0) && (old_state == GFS2_BLKST_FREE))
+			set_bit(GBF_FULL, &bi->bi_flags);
+
 		/* Try next bitmap block (wrap back to rgrp header if at end) */
-		buf = (buf + 1) % length;
-		bi = rgd->rd_bits + buf;
+skip:
+		buf++;
+		buf %= length;
 		goal = 0;
 	}
 
-	if (blk != BFITNOENT && old_state != new_state) {
-		*n = 1;
-		gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
-		gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
-			    bi->bi_len, blk, new_state);
-		goal = blk;
-		while (*n < elen) {
-			goal++;
-			if (goal >= (bi->bi_len * GFS2_NBBY))
-				break;
-			if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) !=
-			    GFS2_BLKST_FREE)
-				break;
-			gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone,
-				    bi->bi_offset, bi->bi_len, goal,
-				    new_state);
-			(*n)++;
-		}
-	}
+	if (blk == BFITNOENT)
+		return blk;
+	*n = 1;
+	if (old_state == new_state)
+		goto out;
 
-	return (blk == BFITNOENT) ? blk : (bi->bi_start * GFS2_NBBY) + blk;
+	gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
+	gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
+		    bi->bi_len, blk, new_state);
+	goal = blk;
+	while (*n < elen) {
+		goal++;
+		if (goal >= (bi->bi_len * GFS2_NBBY))
+			break;
+		if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) !=
+		    GFS2_BLKST_FREE)
+			break;
+		gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
+			    bi->bi_len, goal, new_state);
+		(*n)++;
+	}
+out:
+	return (bi->bi_start * GFS2_NBBY) + blk;
 }
 
 /**
@@ -1435,13 +1446,33 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart,
 }
 
 /**
- * gfs2_alloc_block - Allocate a block
- * @ip: the inode to allocate the block for
+ * gfs2_rgrp_dump - print out an rgrp
+ * @seq: The iterator
+ * @gl: The glock in question
  *
- * Returns: the allocated block
  */
 
-u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n)
+int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+	const struct gfs2_rgrpd *rgd = gl->gl_object;
+	if (rgd == NULL)
+		return 0;
+	gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n",
+		       (unsigned long long)rgd->rd_addr, rgd->rd_flags,
+		       rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes);
+	return 0;
+}
+
+/**
+ * gfs2_alloc_block - Allocate one or more blocks
+ * @ip: the inode to allocate the block for
+ * @bn: Used to return the starting block number
+ * @n: requested number of blocks/extent length (value/result)
+ *
+ * Returns: 0 or error
+ */
+
+int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct buffer_head *dibh;
@@ -1457,7 +1488,10 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n)
 		goal = rgd->rd_last_alloc;
 
 	blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED, n);
-	BUG_ON(blk == BFITNOENT);
+
+	/* Since all blocks are reserved in advance, this shouldn't happen */
+	if (blk == BFITNOENT)
+		goto rgrp_error;
 
 	rgd->rd_last_alloc = blk;
 	block = rgd->rd_data0 + blk;
@@ -1469,7 +1503,9 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n)
 		di->di_goal_meta = di->di_goal_data = cpu_to_be64(ip->i_goal);
 		brelse(dibh);
 	}
-	gfs2_assert_withdraw(sdp, rgd->rd_free >= *n);
+	if (rgd->rd_free < *n)
+		goto rgrp_error;
+
 	rgd->rd_free -= *n;
 
 	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
@@ -1484,7 +1520,16 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n)
 	rgd->rd_free_clone -= *n;
 	spin_unlock(&sdp->sd_rindex_spin);
 
-	return block;
+	*bn = block;
+	return 0;
+
+rgrp_error:
+	fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n",
+	        (unsigned long long)rgd->rd_addr);
+	fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n");
+	gfs2_rgrp_dump(NULL, rgd->rd_gl);
+	rgd->rd_flags |= GFS2_RDF_ERROR;
+	return -EIO;
 }
 
 /**
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 3181c7e624bf..1e76ff0f3e00 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -14,22 +14,22 @@ struct gfs2_rgrpd;
 struct gfs2_sbd;
 struct gfs2_holder;
 
-void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
 
 struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk);
 struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
 struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
 
-void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
-int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh);
+extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
+extern int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh);
 
-int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd);
-void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd);
-void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd);
+extern int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd);
 
-void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd);
+extern void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd);
 
-struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
+extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
 static inline void gfs2_alloc_put(struct gfs2_inode *ip)
 {
 	BUG_ON(ip->i_alloc == NULL);
@@ -37,22 +37,22 @@ static inline void gfs2_alloc_put(struct gfs2_inode *ip)
 	ip->i_alloc = NULL;
 }
 
-int gfs2_inplace_reserve_i(struct gfs2_inode *ip,
-			 char *file, unsigned int line);
+extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file,
+				  unsigned int line);
 #define gfs2_inplace_reserve(ip) \
 gfs2_inplace_reserve_i((ip), __FILE__, __LINE__)
 
-void gfs2_inplace_release(struct gfs2_inode *ip);
+extern void gfs2_inplace_release(struct gfs2_inode *ip);
 
-unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block);
+extern unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block);
 
-u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n);
-u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation);
+extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n);
+extern u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation);
 
-void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
-void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
-void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
-void gfs2_unlink_di(struct inode *inode);
+extern void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
+extern void gfs2_unlink_di(struct inode *inode);
 
 struct gfs2_rgrp_list {
 	unsigned int rl_rgrps;
@@ -61,10 +61,11 @@ struct gfs2_rgrp_list {
 	struct gfs2_holder *rl_ghs;
 };
 
-void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
-		    u64 block);
-void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
-void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
-u64 gfs2_ri_total(struct gfs2_sbd *sdp);
+extern void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
+			   u64 block);
+extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
+extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
+extern u64 gfs2_ri_total(struct gfs2_sbd *sdp);
+extern int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl);
 
 #endif /* __RGRP_DOT_H__ */
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 601913e0a482..c8930b31cdf0 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -7,14 +7,20 @@
  * of the GNU General Public License version 2.
  */
 
+#include <linux/bio.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
-#include <linux/crc32.h>
+#include <linux/statfs.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
 #include <linux/gfs2_ondisk.h>
-#include <linux/bio.h>
+#include <linux/crc32.h>
+#include <linux/time.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -31,6 +37,183 @@
 #include "super.h"
 #include "trans.h"
 #include "util.h"
+#include "sys.h"
+#include "eattr.h"
+
+#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x)
+
+enum {
+	Opt_lockproto,
+	Opt_locktable,
+	Opt_hostdata,
+	Opt_spectator,
+	Opt_ignore_local_fs,
+	Opt_localflocks,
+	Opt_localcaching,
+	Opt_debug,
+	Opt_nodebug,
+	Opt_upgrade,
+	Opt_acl,
+	Opt_noacl,
+	Opt_quota_off,
+	Opt_quota_account,
+	Opt_quota_on,
+	Opt_quota,
+	Opt_noquota,
+	Opt_suiddir,
+	Opt_nosuiddir,
+	Opt_data_writeback,
+	Opt_data_ordered,
+	Opt_meta,
+	Opt_discard,
+	Opt_nodiscard,
+	Opt_commit,
+	Opt_error,
+};
+
+static const match_table_t tokens = {
+	{Opt_lockproto, "lockproto=%s"},
+	{Opt_locktable, "locktable=%s"},
+	{Opt_hostdata, "hostdata=%s"},
+	{Opt_spectator, "spectator"},
+	{Opt_ignore_local_fs, "ignore_local_fs"},
+	{Opt_localflocks, "localflocks"},
+	{Opt_localcaching, "localcaching"},
+	{Opt_debug, "debug"},
+	{Opt_nodebug, "nodebug"},
+	{Opt_upgrade, "upgrade"},
+	{Opt_acl, "acl"},
+	{Opt_noacl, "noacl"},
+	{Opt_quota_off, "quota=off"},
+	{Opt_quota_account, "quota=account"},
+	{Opt_quota_on, "quota=on"},
+	{Opt_quota, "quota"},
+	{Opt_noquota, "noquota"},
+	{Opt_suiddir, "suiddir"},
+	{Opt_nosuiddir, "nosuiddir"},
+	{Opt_data_writeback, "data=writeback"},
+	{Opt_data_ordered, "data=ordered"},
+	{Opt_meta, "meta"},
+	{Opt_discard, "discard"},
+	{Opt_nodiscard, "nodiscard"},
+	{Opt_commit, "commit=%d"},
+	{Opt_error, NULL}
+};
+
+/**
+ * gfs2_mount_args - Parse mount options
+ * @sdp:
+ * @data:
+ *
+ * Return: errno
+ */
+
+int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options)
+{
+	char *o;
+	int token;
+	substring_t tmp[MAX_OPT_ARGS];
+	int rv;
+
+	/* Split the options into tokens with the "," character and
+	   process them */
+
+	while (1) {
+		o = strsep(&options, ",");
+		if (o == NULL)
+			break;
+		if (*o == '\0')
+			continue;
+
+		token = match_token(o, tokens, tmp);
+		switch (token) {
+		case Opt_lockproto:
+			match_strlcpy(args->ar_lockproto, &tmp[0],
+				      GFS2_LOCKNAME_LEN);
+			break;
+		case Opt_locktable:
+			match_strlcpy(args->ar_locktable, &tmp[0],
+				      GFS2_LOCKNAME_LEN);
+			break;
+		case Opt_hostdata:
+			match_strlcpy(args->ar_hostdata, &tmp[0],
+				      GFS2_LOCKNAME_LEN);
+			break;
+		case Opt_spectator:
+			args->ar_spectator = 1;
+			break;
+		case Opt_ignore_local_fs:
+			args->ar_ignore_local_fs = 1;
+			break;
+		case Opt_localflocks:
+			args->ar_localflocks = 1;
+			break;
+		case Opt_localcaching:
+			args->ar_localcaching = 1;
+			break;
+		case Opt_debug:
+			args->ar_debug = 1;
+			break;
+		case Opt_nodebug:
+			args->ar_debug = 0;
+			break;
+		case Opt_upgrade:
+			args->ar_upgrade = 1;
+			break;
+		case Opt_acl:
+			args->ar_posix_acl = 1;
+			break;
+		case Opt_noacl:
+			args->ar_posix_acl = 0;
+			break;
+		case Opt_quota_off:
+		case Opt_noquota:
+			args->ar_quota = GFS2_QUOTA_OFF;
+			break;
+		case Opt_quota_account:
+			args->ar_quota = GFS2_QUOTA_ACCOUNT;
+			break;
+		case Opt_quota_on:
+		case Opt_quota:
+			args->ar_quota = GFS2_QUOTA_ON;
+			break;
+		case Opt_suiddir:
+			args->ar_suiddir = 1;
+			break;
+		case Opt_nosuiddir:
+			args->ar_suiddir = 0;
+			break;
+		case Opt_data_writeback:
+			args->ar_data = GFS2_DATA_WRITEBACK;
+			break;
+		case Opt_data_ordered:
+			args->ar_data = GFS2_DATA_ORDERED;
+			break;
+		case Opt_meta:
+			args->ar_meta = 1;
+			break;
+		case Opt_discard:
+			args->ar_discard = 1;
+			break;
+		case Opt_nodiscard:
+			args->ar_discard = 0;
+			break;
+		case Opt_commit:
+			rv = match_int(&tmp[0], &args->ar_commit);
+			if (rv || args->ar_commit <= 0) {
+				fs_info(sdp, "commit mount option requires a positive numeric argument\n");
+				return rv ? rv : -EINVAL;
+			}
+			break;
+		case Opt_error:
+		default:
+			fs_info(sdp, "invalid mount option: %s\n", o);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
 
 /**
  * gfs2_jindex_free - Clear all the journal index information
@@ -436,3 +619,710 @@ void gfs2_unfreeze_fs(struct gfs2_sbd *sdp)
 	mutex_unlock(&sdp->sd_freeze_lock);
 }
 
+
+/**
+ * gfs2_write_inode - Make sure the inode is stable on the disk
+ * @inode: The inode
+ * @sync: synchronous write flag
+ *
+ * Returns: errno
+ */
+
+static int gfs2_write_inode(struct inode *inode, int sync)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder gh;
+	struct buffer_head *bh;
+	struct timespec atime;
+	struct gfs2_dinode *di;
+	int ret = 0;
+
+	/* Check this is a "normal" inode, etc */
+	if (!test_bit(GIF_USER, &ip->i_flags) ||
+	    (current->flags & PF_MEMALLOC))
+		return 0;
+	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (ret)
+		goto do_flush;
+	ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	if (ret)
+		goto do_unlock;
+	ret = gfs2_meta_inode_buffer(ip, &bh);
+	if (ret == 0) {
+		di = (struct gfs2_dinode *)bh->b_data;
+		atime.tv_sec = be64_to_cpu(di->di_atime);
+		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
+		if (timespec_compare(&inode->i_atime, &atime) > 0) {
+			gfs2_trans_add_bh(ip->i_gl, bh, 1);
+			gfs2_dinode_out(ip, bh->b_data);
+		}
+		brelse(bh);
+	}
+	gfs2_trans_end(sdp);
+do_unlock:
+	gfs2_glock_dq_uninit(&gh);
+do_flush:
+	if (sync != 0)
+		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+	return ret;
+}
+
+/**
+ * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
+ * @sdp: the filesystem
+ *
+ * Returns: errno
+ */
+
+static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+{
+	struct gfs2_holder t_gh;
+	int error;
+
+	gfs2_quota_sync(sdp);
+	gfs2_statfs_sync(sdp);
+
+	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
+				   &t_gh);
+	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return error;
+
+	gfs2_meta_syncfs(sdp);
+	gfs2_log_shutdown(sdp);
+
+	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
+	if (t_gh.gh_gl)
+		gfs2_glock_dq_uninit(&t_gh);
+
+	gfs2_quota_cleanup(sdp);
+
+	return error;
+}
+
+static int gfs2_umount_recovery_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
+/**
+ * gfs2_put_super - Unmount the filesystem
+ * @sb: The VFS superblock
+ *
+ */
+
+static void gfs2_put_super(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+	struct gfs2_jdesc *jd;
+
+	lock_kernel();
+
+	/*  Unfreeze the filesystem, if we need to  */
+
+	mutex_lock(&sdp->sd_freeze_lock);
+	if (sdp->sd_freeze_count)
+		gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
+	mutex_unlock(&sdp->sd_freeze_lock);
+
+	/* No more recovery requests */
+	set_bit(SDF_NORECOVERY, &sdp->sd_flags);
+	smp_mb();
+
+	/* Wait on outstanding recovery */
+restart:
+	spin_lock(&sdp->sd_jindex_spin);
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		if (!test_bit(JDF_RECOVERY, &jd->jd_flags))
+			continue;
+		spin_unlock(&sdp->sd_jindex_spin);
+		wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
+			    gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE);
+		goto restart;
+	}
+	spin_unlock(&sdp->sd_jindex_spin);
+
+	kthread_stop(sdp->sd_quotad_process);
+	kthread_stop(sdp->sd_logd_process);
+
+	if (!(sb->s_flags & MS_RDONLY)) {
+		error = gfs2_make_fs_ro(sdp);
+		if (error)
+			gfs2_io_error(sdp);
+	}
+	/*  At this point, we're through modifying the disk  */
+
+	/*  Release stuff  */
+
+	iput(sdp->sd_jindex);
+	iput(sdp->sd_inum_inode);
+	iput(sdp->sd_statfs_inode);
+	iput(sdp->sd_rindex);
+	iput(sdp->sd_quota_inode);
+
+	gfs2_glock_put(sdp->sd_rename_gl);
+	gfs2_glock_put(sdp->sd_trans_gl);
+
+	if (!sdp->sd_args.ar_spectator) {
+		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_ir_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
+		iput(sdp->sd_ir_inode);
+		iput(sdp->sd_sc_inode);
+		iput(sdp->sd_qc_inode);
+	}
+
+	gfs2_glock_dq_uninit(&sdp->sd_live_gh);
+	gfs2_clear_rgrpd(sdp);
+	gfs2_jindex_free(sdp);
+	/*  Take apart glock structures and buffer lists  */
+	gfs2_gl_hash_clear(sdp);
+	/*  Unmount the locking protocol  */
+	gfs2_lm_unmount(sdp);
+
+	/*  At this point, we're through participating in the lockspace  */
+	gfs2_sys_fs_del(sdp);
+
+	unlock_kernel();
+}
+
+/**
+ * gfs2_sync_fs - sync the filesystem
+ * @sb: the superblock
+ *
+ * Flushes the log to disk.
+ */
+
+static int gfs2_sync_fs(struct super_block *sb, int wait)
+{
+	if (wait && sb->s_fs_info)
+		gfs2_log_flush(sb->s_fs_info, NULL);
+	return 0;
+}
+
+/**
+ * gfs2_freeze - prevent further writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static int gfs2_freeze(struct super_block *sb)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	int error;
+
+	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+		return -EINVAL;
+
+	for (;;) {
+		error = gfs2_freeze_fs(sdp);
+		if (!error)
+			break;
+
+		switch (error) {
+		case -EBUSY:
+			fs_err(sdp, "waiting for recovery before freeze\n");
+			break;
+
+		default:
+			fs_err(sdp, "error freezing FS: %d\n", error);
+			break;
+		}
+
+		fs_err(sdp, "retrying...\n");
+		msleep(1000);
+	}
+	return 0;
+}
+
+/**
+ * gfs2_unfreeze - reallow writes to the filesystem
+ * @sb: the VFS structure for the filesystem
+ *
+ */
+
+static int gfs2_unfreeze(struct super_block *sb)
+{
+	gfs2_unfreeze_fs(sb->s_fs_info);
+	return 0;
+}
+
+/**
+ * statfs_fill - fill in the sg for a given RG
+ * @rgd: the RG
+ * @sc: the sc structure
+ *
+ * Returns: 0 on success, -ESTALE if the LVB is invalid
+ */
+
+static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
+			    struct gfs2_statfs_change_host *sc)
+{
+	gfs2_rgrp_verify(rgd);
+	sc->sc_total += rgd->rd_data;
+	sc->sc_free += rgd->rd_free;
+	sc->sc_dinodes += rgd->rd_dinodes;
+	return 0;
+}
+
+/**
+ * gfs2_statfs_slow - Stat a filesystem using asynchronous locking
+ * @sdp: the filesystem
+ * @sc: the sc info that will be returned
+ *
+ * Any error (other than a signal) will cause this routine to fall back
+ * to the synchronous version.
+ *
+ * FIXME: This really shouldn't busy wait like this.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
+{
+	struct gfs2_holder ri_gh;
+	struct gfs2_rgrpd *rgd_next;
+	struct gfs2_holder *gha, *gh;
+	unsigned int slots = 64;
+	unsigned int x;
+	int done;
+	int error = 0, err;
+
+	memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
+	gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
+	if (!gha)
+		return -ENOMEM;
+
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		goto out;
+
+	rgd_next = gfs2_rgrpd_get_first(sdp);
+
+	for (;;) {
+		done = 1;
+
+		for (x = 0; x < slots; x++) {
+			gh = gha + x;
+
+			if (gh->gh_gl && gfs2_glock_poll(gh)) {
+				err = gfs2_glock_wait(gh);
+				if (err) {
+					gfs2_holder_uninit(gh);
+					error = err;
+				} else {
+					if (!error)
+						error = statfs_slow_fill(
+							gh->gh_gl->gl_object, sc);
+					gfs2_glock_dq_uninit(gh);
+				}
+			}
+
+			if (gh->gh_gl)
+				done = 0;
+			else if (rgd_next && !error) {
+				error = gfs2_glock_nq_init(rgd_next->rd_gl,
+							   LM_ST_SHARED,
+							   GL_ASYNC,
+							   gh);
+				rgd_next = gfs2_rgrpd_get_next(rgd_next);
+				done = 0;
+			}
+
+			if (signal_pending(current))
+				error = -ERESTARTSYS;
+		}
+
+		if (done)
+			break;
+
+		yield();
+	}
+
+	gfs2_glock_dq_uninit(&ri_gh);
+
+out:
+	kfree(gha);
+	return error;
+}
+
+/**
+ * gfs2_statfs_i - Do a statfs
+ * @sdp: the filesystem
+ * @sg: the sg structure
+ *
+ * Returns: errno
+ */
+
+static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
+{
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+
+	spin_lock(&sdp->sd_statfs_spin);
+
+	*sc = *m_sc;
+	sc->sc_total += l_sc->sc_total;
+	sc->sc_free += l_sc->sc_free;
+	sc->sc_dinodes += l_sc->sc_dinodes;
+
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	if (sc->sc_free < 0)
+		sc->sc_free = 0;
+	if (sc->sc_free > sc->sc_total)
+		sc->sc_free = sc->sc_total;
+	if (sc->sc_dinodes < 0)
+		sc->sc_dinodes = 0;
+
+	return 0;
+}
+
+/**
+ * gfs2_statfs - Gather and return stats about the filesystem
+ * @sb: The superblock
+ * @statfsbuf: The buffer
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct super_block *sb = dentry->d_inode->i_sb;
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_statfs_change_host sc;
+	int error;
+
+	if (gfs2_tune_get(sdp, gt_statfs_slow))
+		error = gfs2_statfs_slow(sdp, &sc);
+	else
+		error = gfs2_statfs_i(sdp, &sc);
+
+	if (error)
+		return error;
+
+	buf->f_type = GFS2_MAGIC;
+	buf->f_bsize = sdp->sd_sb.sb_bsize;
+	buf->f_blocks = sc.sc_total;
+	buf->f_bfree = sc.sc_free;
+	buf->f_bavail = sc.sc_free;
+	buf->f_files = sc.sc_dinodes + sc.sc_free;
+	buf->f_ffree = sc.sc_free;
+	buf->f_namelen = GFS2_FNAMESIZE;
+
+	return 0;
+}
+
+/**
+ * gfs2_remount_fs - called when the FS is remounted
+ * @sb:  the filesystem
+ * @flags:  the remount flags
+ * @data:  extra data passed in (not used right now)
+ *
+ * Returns: errno
+ */
+
+static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	struct gfs2_sbd *sdp = sb->s_fs_info;
+	struct gfs2_args args = sdp->sd_args; /* Default to current settings */
+	struct gfs2_tune *gt = &sdp->sd_tune;
+	int error;
+
+	spin_lock(&gt->gt_spin);
+	args.ar_commit = gt->gt_log_flush_secs;
+	spin_unlock(&gt->gt_spin);
+	error = gfs2_mount_args(sdp, &args, data);
+	if (error)
+		return error;
+
+	/* Not allowed to change locking details */
+	if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) ||
+	    strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) ||
+	    strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata))
+		return -EINVAL;
+
+	/* Some flags must not be changed */
+	if (args_neq(&args, &sdp->sd_args, spectator) ||
+	    args_neq(&args, &sdp->sd_args, ignore_local_fs) ||
+	    args_neq(&args, &sdp->sd_args, localflocks) ||
+	    args_neq(&args, &sdp->sd_args, localcaching) ||
+	    args_neq(&args, &sdp->sd_args, meta))
+		return -EINVAL;
+
+	if (sdp->sd_args.ar_spectator)
+		*flags |= MS_RDONLY;
+
+	if ((sb->s_flags ^ *flags) & MS_RDONLY) {
+		if (*flags & MS_RDONLY)
+			error = gfs2_make_fs_ro(sdp);
+		else
+			error = gfs2_make_fs_rw(sdp);
+		if (error)
+			return error;
+	}
+
+	sdp->sd_args = args;
+	if (sdp->sd_args.ar_posix_acl)
+		sb->s_flags |= MS_POSIXACL;
+	else
+		sb->s_flags &= ~MS_POSIXACL;
+	spin_lock(&gt->gt_spin);
+	gt->gt_log_flush_secs = args.ar_commit;
+	spin_unlock(&gt->gt_spin);
+
+	return 0;
+}
+
+/**
+ * gfs2_drop_inode - Drop an inode (test for remote unlink)
+ * @inode: The inode to drop
+ *
+ * If we've received a callback on an iopen lock then its because a
+ * remote node tried to deallocate the inode but failed due to this node
+ * still having the inode open. Here we mark the link count zero
+ * since we know that it must have reached zero if the GLF_DEMOTE flag
+ * is set on the iopen glock. If we didn't do a disk read since the
+ * remote node removed the final link then we might otherwise miss
+ * this event. This check ensures that this node will deallocate the
+ * inode's blocks, or alternatively pass the baton on to another
+ * node for later deallocation.
+ */
+
+static void gfs2_drop_inode(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) {
+		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
+		if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
+			clear_nlink(inode);
+	}
+	generic_drop_inode(inode);
+}
+
+/**
+ * gfs2_clear_inode - Deallocate an inode when VFS is done with it
+ * @inode: The VFS inode
+ *
+ */
+
+static void gfs2_clear_inode(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	/* This tells us its a "real" inode and not one which only
+	 * serves to contain an address space (see rgrp.c, meta_io.c)
+	 * which therefore doesn't have its own glocks.
+	 */
+	if (test_bit(GIF_USER, &ip->i_flags)) {
+		ip->i_gl->gl_object = NULL;
+		gfs2_glock_put(ip->i_gl);
+		ip->i_gl = NULL;
+		if (ip->i_iopen_gh.gh_gl) {
+			ip->i_iopen_gh.gh_gl->gl_object = NULL;
+			gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		}
+	}
+}
+
+static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
+{
+	do {
+		if (d1 == d2)
+			return 1;
+		d1 = d1->d_parent;
+	} while (!IS_ROOT(d1));
+	return 0;
+}
+
+/**
+ * gfs2_show_options - Show mount options for /proc/mounts
+ * @s: seq_file structure
+ * @mnt: vfsmount
+ *
+ * Returns: 0 on success or error code
+ */
+
+static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
+{
+	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
+	struct gfs2_args *args = &sdp->sd_args;
+	int lfsecs;
+
+	if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
+		seq_printf(s, ",meta");
+	if (args->ar_lockproto[0])
+		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
+	if (args->ar_locktable[0])
+		seq_printf(s, ",locktable=%s", args->ar_locktable);
+	if (args->ar_hostdata[0])
+		seq_printf(s, ",hostdata=%s", args->ar_hostdata);
+	if (args->ar_spectator)
+		seq_printf(s, ",spectator");
+	if (args->ar_ignore_local_fs)
+		seq_printf(s, ",ignore_local_fs");
+	if (args->ar_localflocks)
+		seq_printf(s, ",localflocks");
+	if (args->ar_localcaching)
+		seq_printf(s, ",localcaching");
+	if (args->ar_debug)
+		seq_printf(s, ",debug");
+	if (args->ar_upgrade)
+		seq_printf(s, ",upgrade");
+	if (args->ar_posix_acl)
+		seq_printf(s, ",acl");
+	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
+		char *state;
+		switch (args->ar_quota) {
+		case GFS2_QUOTA_OFF:
+			state = "off";
+			break;
+		case GFS2_QUOTA_ACCOUNT:
+			state = "account";
+			break;
+		case GFS2_QUOTA_ON:
+			state = "on";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",quota=%s", state);
+	}
+	if (args->ar_suiddir)
+		seq_printf(s, ",suiddir");
+	if (args->ar_data != GFS2_DATA_DEFAULT) {
+		char *state;
+		switch (args->ar_data) {
+		case GFS2_DATA_WRITEBACK:
+			state = "writeback";
+			break;
+		case GFS2_DATA_ORDERED:
+			state = "ordered";
+			break;
+		default:
+			state = "unknown";
+			break;
+		}
+		seq_printf(s, ",data=%s", state);
+	}
+	if (args->ar_discard)
+		seq_printf(s, ",discard");
+	lfsecs = sdp->sd_tune.gt_log_flush_secs;
+	if (lfsecs != 60)
+		seq_printf(s, ",commit=%d", lfsecs);
+	return 0;
+}
+
+/*
+ * We have to (at the moment) hold the inodes main lock to cover
+ * the gap between unlocking the shared lock on the iopen lock and
+ * taking the exclusive lock. I'd rather do a shared -> exclusive
+ * conversion on the iopen lock, but we can change that later. This
+ * is safe, just less efficient.
+ */
+
+static void gfs2_delete_inode(struct inode *inode)
+{
+	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int error;
+
+	if (!test_bit(GIF_USER, &ip->i_flags))
+		goto out;
+
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	if (unlikely(error)) {
+		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		goto out;
+	}
+
+	gfs2_glock_dq_wait(&ip->i_iopen_gh);
+	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
+	error = gfs2_glock_nq(&ip->i_iopen_gh);
+	if (error)
+		goto out_truncate;
+
+	if (S_ISDIR(inode->i_mode) &&
+	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
+		error = gfs2_dir_exhash_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (ip->i_eattr) {
+		error = gfs2_ea_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	if (!gfs2_is_stuffed(ip)) {
+		error = gfs2_file_dealloc(ip);
+		if (error)
+			goto out_unlock;
+	}
+
+	error = gfs2_dinode_dealloc(ip);
+	if (error)
+		goto out_unlock;
+
+out_truncate:
+	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
+	if (error)
+		goto out_unlock;
+	/* Needs to be done before glock release & also in a transaction */
+	truncate_inode_pages(&inode->i_data, 0);
+	gfs2_trans_end(sdp);
+
+out_unlock:
+	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
+		gfs2_glock_dq(&ip->i_iopen_gh);
+	gfs2_holder_uninit(&ip->i_iopen_gh);
+	gfs2_glock_dq_uninit(&gh);
+	if (error && error != GLR_TRYFAILED && error != -EROFS)
+		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
+out:
+	truncate_inode_pages(&inode->i_data, 0);
+	clear_inode(inode);
+}
+
+static struct inode *gfs2_alloc_inode(struct super_block *sb)
+{
+	struct gfs2_inode *ip;
+
+	ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL);
+	if (ip) {
+		ip->i_flags = 0;
+		ip->i_gl = NULL;
+	}
+	return &ip->i_inode;
+}
+
+static void gfs2_destroy_inode(struct inode *inode)
+{
+	kmem_cache_free(gfs2_inode_cachep, inode);
+}
+
+const struct super_operations gfs2_super_ops = {
+	.alloc_inode		= gfs2_alloc_inode,
+	.destroy_inode		= gfs2_destroy_inode,
+	.write_inode		= gfs2_write_inode,
+	.delete_inode		= gfs2_delete_inode,
+	.put_super		= gfs2_put_super,
+	.sync_fs		= gfs2_sync_fs,
+	.freeze_fs 		= gfs2_freeze,
+	.unfreeze_fs		= gfs2_unfreeze,
+	.statfs			= gfs2_statfs,
+	.remount_fs		= gfs2_remount_fs,
+	.clear_inode		= gfs2_clear_inode,
+	.drop_inode		= gfs2_drop_inode,
+	.show_options		= gfs2_show_options,
+};
+
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 7655f5025fec..23419dc3027b 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -26,6 +26,36 @@
 #include "util.h"
 #include "glops.h"
 
+struct gfs2_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct gfs2_sbd *, char *);
+	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
+};
+
+static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->show ? a->show(sdp, buf) : 0;
+}
+
+static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr,
+			       const char *buf, size_t len)
+{
+	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
+	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
+	return a->store ? a->store(sdp, buf, len) : len;
+}
+
+static struct sysfs_ops gfs2_attr_ops = {
+	.show  = gfs2_attr_show,
+	.store = gfs2_attr_store,
+};
+
+
+static struct kset *gfs2_kset;
+
 static ssize_t id_show(struct gfs2_sbd *sdp, char *buf)
 {
 	return snprintf(buf, PAGE_SIZE, "%u:%u\n",
@@ -212,11 +242,6 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len
 	return len;
 }
 
-struct gfs2_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *, char *);
-	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
-};
 
 #define GFS2_ATTR(name, mode, show, store) \
 static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store)
@@ -246,58 +271,11 @@ static struct attribute *gfs2_attrs[] = {
 	NULL,
 };
 
-static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr,
-			      char *buf)
-{
-	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
-	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
-	return a->show ? a->show(sdp, buf) : 0;
-}
-
-static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr,
-			       const char *buf, size_t len)
-{
-	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
-	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
-	return a->store ? a->store(sdp, buf, len) : len;
-}
-
-static struct sysfs_ops gfs2_attr_ops = {
-	.show  = gfs2_attr_show,
-	.store = gfs2_attr_store,
-};
-
 static struct kobj_type gfs2_ktype = {
 	.default_attrs = gfs2_attrs,
 	.sysfs_ops     = &gfs2_attr_ops,
 };
 
-static struct kset *gfs2_kset;
-
-/*
- * display struct lm_lockstruct fields
- */
-
-struct lockstruct_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *, char *);
-};
-
-#define LOCKSTRUCT_ATTR(name, fmt)                                          \
-static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                 \
-{                                                                           \
-	return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_lockstruct.ls_##name); \
-}                                                                           \
-static struct lockstruct_attr lockstruct_attr_##name = __ATTR_RO(name)
-
-LOCKSTRUCT_ATTR(jid,      "%u\n");
-LOCKSTRUCT_ATTR(first,    "%u\n");
-
-static struct attribute *lockstruct_attrs[] = {
-	&lockstruct_attr_jid.attr,
-	&lockstruct_attr_first.attr,
-	NULL,
-};
 
 /*
  * lock_module. Originally from lock_dlm
@@ -359,34 +337,33 @@ static ssize_t first_done_show(struct gfs2_sbd *sdp, char *buf)
 	return sprintf(buf, "%d\n", ls->ls_first_done);
 }
 
-static ssize_t recover_show(struct gfs2_sbd *sdp, char *buf)
-{
-	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
-	return sprintf(buf, "%d\n", ls->ls_recover_jid);
-}
-
-static void gfs2_jdesc_make_dirty(struct gfs2_sbd *sdp, unsigned int jid)
+static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
 {
+	unsigned jid;
 	struct gfs2_jdesc *jd;
+	int rv;
 
+	rv = sscanf(buf, "%u", &jid);
+	if (rv != 1)
+		return -EINVAL;
+
+	rv = -ESHUTDOWN;
 	spin_lock(&sdp->sd_jindex_spin);
+	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags))
+		goto out;
+	rv = -EBUSY;
+	if (sdp->sd_jdesc->jd_jid == jid)
+		goto out;
+	rv = -ENOENT;
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
 		if (jd->jd_jid != jid)
 			continue;
-		jd->jd_dirty = 1;
+		rv = slow_work_enqueue(&jd->jd_work);
 		break;
 	}
+out:
 	spin_unlock(&sdp->sd_jindex_spin);
-}
-
-static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
-{
-	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
-	ls->ls_recover_jid = simple_strtol(buf, NULL, 0);
-	gfs2_jdesc_make_dirty(sdp, ls->ls_recover_jid);
-	if (sdp->sd_recoverd_process)
-		wake_up_process(sdp->sd_recoverd_process);
-	return len;
+	return rv ? rv : len;
 }
 
 static ssize_t recover_done_show(struct gfs2_sbd *sdp, char *buf)
@@ -401,31 +378,31 @@ static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf)
 	return sprintf(buf, "%d\n", ls->ls_recover_jid_status);
 }
 
-struct gdlm_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *sdp, char *);
-	ssize_t (*store)(struct gfs2_sbd *sdp, const char *, size_t);
-};
+static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
+{
+	return sprintf(buf, "%u\n", sdp->sd_lockstruct.ls_jid);
+}
 
 #define GDLM_ATTR(_name,_mode,_show,_store) \
-static struct gdlm_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
+static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
 
-GDLM_ATTR(proto_name,     0444, proto_name_show,     NULL);
-GDLM_ATTR(block,          0644, block_show,          block_store);
-GDLM_ATTR(withdraw,       0644, withdraw_show,       withdraw_store);
-GDLM_ATTR(id,             0444, lkid_show,           NULL);
-GDLM_ATTR(first,          0444, lkfirst_show,        NULL);
-GDLM_ATTR(first_done,     0444, first_done_show,     NULL);
-GDLM_ATTR(recover,        0644, recover_show,        recover_store);
-GDLM_ATTR(recover_done,   0444, recover_done_show,   NULL);
-GDLM_ATTR(recover_status, 0444, recover_status_show, NULL);
+GDLM_ATTR(proto_name,     0444, proto_name_show,	NULL);
+GDLM_ATTR(block,          0644, block_show,		block_store);
+GDLM_ATTR(withdraw,       0644, withdraw_show,		withdraw_store);
+GDLM_ATTR(id,             0444, lkid_show,		NULL);
+GDLM_ATTR(jid,		  0444, jid_show,		NULL);
+GDLM_ATTR(first,          0444, lkfirst_show,		NULL);
+GDLM_ATTR(first_done,     0444, first_done_show,	NULL);
+GDLM_ATTR(recover,        0200, NULL,			recover_store);
+GDLM_ATTR(recover_done,   0444, recover_done_show,	NULL);
+GDLM_ATTR(recover_status, 0444, recover_status_show,	NULL);
 
 static struct attribute *lock_module_attrs[] = {
 	&gdlm_attr_proto_name.attr,
 	&gdlm_attr_block.attr,
 	&gdlm_attr_withdraw.attr,
 	&gdlm_attr_id.attr,
-	&lockstruct_attr_jid.attr,
+	&gdlm_attr_jid.attr,
 	&gdlm_attr_first.attr,
 	&gdlm_attr_first_done.attr,
 	&gdlm_attr_recover.attr,
@@ -434,53 +411,6 @@ static struct attribute *lock_module_attrs[] = {
 	NULL,
 };
 
-/*
- * display struct gfs2_args fields
- */
-
-struct args_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *, char *);
-};
-
-#define ARGS_ATTR(name, fmt)                                                \
-static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                 \
-{                                                                           \
-	return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_args.ar_##name);       \
-}                                                                           \
-static struct args_attr args_attr_##name = __ATTR_RO(name)
-
-ARGS_ATTR(lockproto,       "%s\n");
-ARGS_ATTR(locktable,       "%s\n");
-ARGS_ATTR(hostdata,        "%s\n");
-ARGS_ATTR(spectator,       "%d\n");
-ARGS_ATTR(ignore_local_fs, "%d\n");
-ARGS_ATTR(localcaching,    "%d\n");
-ARGS_ATTR(localflocks,     "%d\n");
-ARGS_ATTR(debug,           "%d\n");
-ARGS_ATTR(upgrade,         "%d\n");
-ARGS_ATTR(posix_acl,       "%d\n");
-ARGS_ATTR(quota,           "%u\n");
-ARGS_ATTR(suiddir,         "%d\n");
-ARGS_ATTR(data,            "%d\n");
-
-static struct attribute *args_attrs[] = {
-	&args_attr_lockproto.attr,
-	&args_attr_locktable.attr,
-	&args_attr_hostdata.attr,
-	&args_attr_spectator.attr,
-	&args_attr_ignore_local_fs.attr,
-	&args_attr_localcaching.attr,
-	&args_attr_localflocks.attr,
-	&args_attr_debug.attr,
-	&args_attr_upgrade.attr,
-	&args_attr_posix_acl.attr,
-	&args_attr_quota.attr,
-	&args_attr_suiddir.attr,
-	&args_attr_data.attr,
-	NULL,
-};
-
 /*
  * get and set struct gfs2_tune fields
  */
@@ -531,14 +461,8 @@ static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field,
 	return len;
 }
 
-struct tune_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct gfs2_sbd *, char *);
-	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
-};
-
 #define TUNE_ATTR_3(name, show, store)                                        \
-static struct tune_attr tune_attr_##name = __ATTR(name, 0644, show, store)
+static struct gfs2_attr tune_attr_##name = __ATTR(name, 0644, show, store)
 
 #define TUNE_ATTR_2(name, store)                                              \
 static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                   \
@@ -554,15 +478,6 @@ static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
 }                                                                             \
 TUNE_ATTR_2(name, name##_store)
 
-#define TUNE_ATTR_DAEMON(name, process)                                       \
-static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
-{                                                                             \
-	ssize_t r = tune_set(sdp, &sdp->sd_tune.gt_##name, 1, buf, len);      \
-	wake_up_process(sdp->sd_##process);                                   \
-	return r;                                                             \
-}                                                                             \
-TUNE_ATTR_2(name, name##_store)
-
 TUNE_ATTR(incore_log_blocks, 0);
 TUNE_ATTR(log_flush_secs, 0);
 TUNE_ATTR(quota_warn_period, 0);
@@ -574,8 +489,6 @@ TUNE_ATTR(new_files_jdata, 0);
 TUNE_ATTR(quota_simul_sync, 1);
 TUNE_ATTR(stall_secs, 1);
 TUNE_ATTR(statfs_quantum, 1);
-TUNE_ATTR_DAEMON(recoverd_secs, recoverd_process);
-TUNE_ATTR_DAEMON(logd_secs, logd_process);
 TUNE_ATTR_3(quota_scale, quota_scale_show, quota_scale_store);
 
 static struct attribute *tune_attrs[] = {
@@ -589,23 +502,11 @@ static struct attribute *tune_attrs[] = {
 	&tune_attr_quota_simul_sync.attr,
 	&tune_attr_stall_secs.attr,
 	&tune_attr_statfs_quantum.attr,
-	&tune_attr_recoverd_secs.attr,
-	&tune_attr_logd_secs.attr,
 	&tune_attr_quota_scale.attr,
 	&tune_attr_new_files_jdata.attr,
 	NULL,
 };
 
-static struct attribute_group lockstruct_group = {
-	.name = "lockstruct",
-	.attrs = lockstruct_attrs,
-};
-
-static struct attribute_group args_group = {
-	.name = "args",
-	.attrs = args_attrs,
-};
-
 static struct attribute_group tune_group = {
 	.name = "tune",
 	.attrs = tune_attrs,
@@ -626,17 +527,9 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
 	if (error)
 		goto fail;
 
-	error = sysfs_create_group(&sdp->sd_kobj, &lockstruct_group);
-	if (error)
-		goto fail_reg;
-
-	error = sysfs_create_group(&sdp->sd_kobj, &args_group);
-	if (error)
-		goto fail_lockstruct;
-
 	error = sysfs_create_group(&sdp->sd_kobj, &tune_group);
 	if (error)
-		goto fail_args;
+		goto fail_reg;
 
 	error = sysfs_create_group(&sdp->sd_kobj, &lock_module_group);
 	if (error)
@@ -647,10 +540,6 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
 
 fail_tune:
 	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
-fail_args:
-	sysfs_remove_group(&sdp->sd_kobj, &args_group);
-fail_lockstruct:
-	sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group);
 fail_reg:
 	kobject_put(&sdp->sd_kobj);
 fail:
@@ -661,8 +550,6 @@ fail:
 void gfs2_sys_fs_del(struct gfs2_sbd *sdp)
 {
 	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
-	sysfs_remove_group(&sdp->sd_kobj, &args_group);
-	sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group);
 	sysfs_remove_group(&sdp->sd_kobj, &lock_module_group);
 	kobject_put(&sdp->sd_kobj);
 }
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 053752d4b27f..4ef0e9fa3549 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -33,6 +33,9 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	BUG_ON(current->journal_info);
 	BUG_ON(blocks == 0 && revokes == 0);
 
+	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+		return -EROFS;
+
 	tr = kzalloc(sizeof(struct gfs2_trans), GFP_NOFS);
 	if (!tr)
 		return -ENOMEM;
@@ -54,12 +57,6 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	if (error)
 		goto fail_holder_uninit;
 
-	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-		tr->tr_t_gh.gh_flags |= GL_NOCACHE;
-		error = -EROFS;
-		goto fail_gunlock;
-	}
-
 	error = gfs2_log_reserve(sdp, tr->tr_reserved);
 	if (error)
 		goto fail_gunlock;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index a36bb749926d..6f833dc8e910 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -49,11 +49,23 @@ MODULE_LICENSE("GPL");
  */
 static void hfs_write_super(struct super_block *sb)
 {
+	lock_super(sb);
 	sb->s_dirt = 0;
-	if (sb->s_flags & MS_RDONLY)
-		return;
+
 	/* sync everything to the buffers */
+	if (!(sb->s_flags & MS_RDONLY))
+		hfs_mdb_commit(sb);
+	unlock_super(sb);
+}
+
+static int hfs_sync_fs(struct super_block *sb, int wait)
+{
+	lock_super(sb);
 	hfs_mdb_commit(sb);
+	sb->s_dirt = 0;
+	unlock_super(sb);
+
+	return 0;
 }
 
 /*
@@ -65,9 +77,15 @@ static void hfs_write_super(struct super_block *sb)
  */
 static void hfs_put_super(struct super_block *sb)
 {
+	lock_kernel();
+
+	if (sb->s_dirt)
+		hfs_write_super(sb);
 	hfs_mdb_close(sb);
 	/* release the MDB's resources */
 	hfs_mdb_put(sb);
+
+	unlock_kernel();
 }
 
 /*
@@ -164,6 +182,7 @@ static const struct super_operations hfs_super_operations = {
 	.clear_inode	= hfs_clear_inode,
 	.put_super	= hfs_put_super,
 	.write_super	= hfs_write_super,
+	.sync_fs	= hfs_sync_fs,
 	.statfs		= hfs_statfs,
 	.remount_fs     = hfs_remount,
 	.show_options	= hfs_show_options,
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index f2a64020f42e..9fc3af0c0dab 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -152,15 +152,14 @@ static void hfsplus_clear_inode(struct inode *inode)
 	}
 }
 
-static void hfsplus_write_super(struct super_block *sb)
+static int hfsplus_sync_fs(struct super_block *sb, int wait)
 {
 	struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
 
 	dprint(DBG_SUPER, "hfsplus_write_super\n");
+
+	lock_super(sb);
 	sb->s_dirt = 0;
-	if (sb->s_flags & MS_RDONLY)
-		/* warn? */
-		return;
 
 	vhdr->free_blocks = cpu_to_be32(HFSPLUS_SB(sb).free_blocks);
 	vhdr->next_alloc = cpu_to_be32(HFSPLUS_SB(sb).next_alloc);
@@ -192,6 +191,16 @@ static void hfsplus_write_super(struct super_block *sb)
 		}
 		HFSPLUS_SB(sb).flags &= ~HFSPLUS_SB_WRITEBACKUP;
 	}
+	unlock_super(sb);
+	return 0;
+}
+
+static void hfsplus_write_super(struct super_block *sb)
+{
+	if (!(sb->s_flags & MS_RDONLY))
+		hfsplus_sync_fs(sb, 1);
+	else
+		sb->s_dirt = 0;
 }
 
 static void hfsplus_put_super(struct super_block *sb)
@@ -199,6 +208,11 @@ static void hfsplus_put_super(struct super_block *sb)
 	dprint(DBG_SUPER, "hfsplus_put_super\n");
 	if (!sb->s_fs_info)
 		return;
+
+	lock_kernel();
+
+	if (sb->s_dirt)
+		hfsplus_write_super(sb);
 	if (!(sb->s_flags & MS_RDONLY) && HFSPLUS_SB(sb).s_vhdr) {
 		struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
 
@@ -218,6 +232,8 @@ static void hfsplus_put_super(struct super_block *sb)
 		unload_nls(HFSPLUS_SB(sb).nls);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
+
+	unlock_kernel();
 }
 
 static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -279,6 +295,7 @@ static const struct super_operations hfsplus_sops = {
 	.clear_inode	= hfsplus_clear_inode,
 	.put_super	= hfsplus_put_super,
 	.write_super	= hfsplus_write_super,
+	.sync_fs	= hfsplus_sync_fs,
 	.statfs		= hfsplus_statfs,
 	.remount_fs	= hfsplus_remount,
 	.show_options	= hfsplus_show_options,
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index fc77965be841..f2feaa06bf26 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -13,6 +13,7 @@
 #include <linux/statfs.h>
 #include <linux/magic.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 
 /* Mark the filesystem dirty, so that chkdsk checks it when os/2 booted */
 
@@ -99,11 +100,16 @@ int hpfs_stop_cycles(struct super_block *s, int key, int *c1, int *c2,
 static void hpfs_put_super(struct super_block *s)
 {
 	struct hpfs_sb_info *sbi = hpfs_sb(s);
+
+	lock_kernel();
+
 	kfree(sbi->sb_cp_table);
 	kfree(sbi->sb_bmp_dir);
 	unmark_dirty(s);
 	s->s_fs_info = NULL;
 	kfree(sbi);
+
+	unlock_kernel();
 }
 
 unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno)
@@ -393,6 +399,8 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
 	
 	*flags |= MS_NOATIME;
 	
+	lock_kernel();
+	lock_super(s);
 	uid = sbi->sb_uid; gid = sbi->sb_gid;
 	umask = 0777 & ~sbi->sb_mode;
 	lowercase = sbi->sb_lowercase; conv = sbi->sb_conv;
@@ -425,9 +433,13 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
 
 	replace_mount_options(s, new_opts);
 
+	unlock_super(s);
+	unlock_kernel();
 	return 0;
 
 out_err:
+	unlock_super(s);
+	unlock_kernel();
 	kfree(new_opts);
 	return -EINVAL;
 }
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index c1462d43e721..941c8425c10b 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -30,6 +30,7 @@
 #include <linux/dnotify.h>
 #include <linux/statfs.h>
 #include <linux/security.h>
+#include <linux/ima.h>
 
 #include <asm/uaccess.h>
 
@@ -986,6 +987,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag)
 			&hugetlbfs_file_operations);
 	if (!file)
 		goto out_dentry; /* inode is already attached */
+	ima_counts_get(file);
 
 	return file;
 
diff --git a/fs/inode.c b/fs/inode.c
index bca0c618fdb3..a88baebf77cf 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -22,6 +22,7 @@
 #include <linux/cdev.h>
 #include <linux/bootmem.h>
 #include <linux/inotify.h>
+#include <linux/fsnotify.h>
 #include <linux/mount.h>
 #include <linux/async.h>
 
@@ -189,6 +190,10 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_private = NULL;
 	inode->i_mapping = mapping;
 
+#ifdef CONFIG_FSNOTIFY
+	inode->i_fsnotify_mask = 0;
+#endif
+
 	return inode;
 
 out_free_security:
@@ -221,6 +226,7 @@ void destroy_inode(struct inode *inode)
 	BUG_ON(inode_has_buffers(inode));
 	ima_inode_free(inode);
 	security_inode_free(inode);
+	fsnotify_inode_delete(inode);
 	if (inode->i_sb->s_op->destroy_inode)
 		inode->i_sb->s_op->destroy_inode(inode);
 	else
@@ -252,6 +258,9 @@ void inode_init_once(struct inode *inode)
 	INIT_LIST_HEAD(&inode->inotify_watches);
 	mutex_init(&inode->inotify_mutex);
 #endif
+#ifdef CONFIG_FSNOTIFY
+	INIT_HLIST_HEAD(&inode->i_fsnotify_mark_entries);
+#endif
 }
 EXPORT_SYMBOL(inode_init_once);
 
@@ -398,6 +407,7 @@ int invalidate_inodes(struct super_block *sb)
 	mutex_lock(&iprune_mutex);
 	spin_lock(&inode_lock);
 	inotify_unmount_inodes(&sb->s_inodes);
+	fsnotify_unmount_inodes(&sb->s_inodes);
 	busy = invalidate_list(&sb->s_inodes, &throw_away);
 	spin_unlock(&inode_lock);
 
@@ -1412,7 +1422,7 @@ void file_update_time(struct file *file)
 	if (IS_NOCMTIME(inode))
 		return;
 
-	err = mnt_want_write(file->f_path.mnt);
+	err = mnt_want_write_file(file);
 	if (err)
 		return;
 
diff --git a/fs/internal.h b/fs/internal.h
index b4dac4fb6b61..d55ef562f0bb 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -25,6 +25,8 @@ static inline int sb_is_blkdev_sb(struct super_block *sb)
 	return sb == blockdev_superblock;
 }
 
+extern int __sync_blockdev(struct block_device *bdev, int wait);
+
 #else
 static inline void bdev_cache_init(void)
 {
@@ -34,6 +36,11 @@ static inline int sb_is_blkdev_sb(struct super_block *sb)
 {
 	return 0;
 }
+
+static inline int __sync_blockdev(struct block_device *bdev, int wait)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -66,3 +73,13 @@ extern void __init mnt_init(void);
  * fs_struct.c
  */
 extern void chroot_fs_refs(struct path *, struct path *);
+
+/*
+ * file_table.c
+ */
+extern void mark_files_ro(struct super_block *);
+
+/*
+ * super.c
+ */
+extern int do_remount_sb(struct super_block *, int, void *, int);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 82d9c42b8bac..286f38dfc6c0 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -414,10 +414,6 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
 	switch (cmd) {
 	case FIBMAP:
 		return ioctl_fibmap(filp, p);
-	case FS_IOC_FIEMAP:
-		return ioctl_fiemap(filp, arg);
-	case FIGETBSZ:
-		return put_user(inode->i_sb->s_blocksize, p);
 	case FIONREAD:
 		return put_user(i_size_read(inode) - filp->f_pos, p);
 	}
@@ -557,6 +553,16 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		error = ioctl_fsthaw(filp);
 		break;
 
+	case FS_IOC_FIEMAP:
+		return ioctl_fiemap(filp, arg);
+
+	case FIGETBSZ:
+	{
+		struct inode *inode = filp->f_path.dentry->d_inode;
+		int __user *p = (int __user *)arg;
+		return put_user(inode->i_sb->s_blocksize, p);
+	}
+
 	default:
 		if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
 			error = file_ioctl(filp, cmd, arg);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index b4cbe9603c7d..068b34b5a107 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -42,11 +42,16 @@ static int isofs_dentry_cmp_ms(struct dentry *dentry, struct qstr *a, struct qst
 static void isofs_put_super(struct super_block *sb)
 {
 	struct isofs_sb_info *sbi = ISOFS_SB(sb);
+
 #ifdef CONFIG_JOLIET
+	lock_kernel();
+
 	if (sbi->s_nls_iocharset) {
 		unload_nls(sbi->s_nls_iocharset);
 		sbi->s_nls_iocharset = NULL;
 	}
+
+	unlock_kernel();
 #endif
 
 	kfree(sbi);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 58144102bf25..62be7d294ec2 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1781,7 +1781,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
  * Journal abort has very specific semantics, which we describe
  * for journal abort.
  *
- * Two internal function, which provide abort to te jbd layer
+ * Two internal functions, which provide abort to the jbd layer
  * itself are here.
  */
 
@@ -1879,7 +1879,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
  * int jbd2_journal_errno () - returns the journal's error state.
  * @journal: journal to examine.
  *
- * This is the errno numbet set with jbd2_journal_abort(), the last
+ * This is the errno number set with jbd2_journal_abort(), the last
  * time the journal was mounted - if the journal was stopped
  * without calling abort this will be 0.
  *
@@ -1903,7 +1903,7 @@ int jbd2_journal_errno(journal_t *journal)
  * int jbd2_journal_clear_err () - clears the journal's error state
  * @journal: journal to act on.
  *
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
  * mode.
  */
 int jbd2_journal_clear_err(journal_t *journal)
@@ -1923,7 +1923,7 @@ int jbd2_journal_clear_err(journal_t *journal)
  * void jbd2_journal_ack_err() - Ack journal err.
  * @journal: journal to act on.
  *
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
  * mode.
  */
 void jbd2_journal_ack_err(journal_t *journal)
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 249305d65d5b..3451a81b2142 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -20,6 +20,7 @@
 #include <linux/vmalloc.h>
 #include <linux/vfs.h>
 #include <linux/crc32.h>
+#include <linux/smp_lock.h>
 #include "nodelist.h"
 
 static int jffs2_flash_setup(struct jffs2_sb_info *c);
@@ -387,6 +388,7 @@ int jffs2_remount_fs (struct super_block *sb, int *flags, char *data)
 	   This also catches the case where it was stopped and this
 	   is just a remount to restart it.
 	   Flush the writebuffer, if neccecary, else we loose it */
+	lock_kernel();
 	if (!(sb->s_flags & MS_RDONLY)) {
 		jffs2_stop_garbage_collect_thread(c);
 		mutex_lock(&c->alloc_sem);
@@ -399,24 +401,10 @@ int jffs2_remount_fs (struct super_block *sb, int *flags, char *data)
 
 	*flags |= MS_NOATIME;
 
+	unlock_kernel();
 	return 0;
 }
 
-void jffs2_write_super (struct super_block *sb)
-{
-	struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
-	sb->s_dirt = 0;
-
-	if (sb->s_flags & MS_RDONLY)
-		return;
-
-	D1(printk(KERN_DEBUG "jffs2_write_super()\n"));
-	jffs2_garbage_collect_trigger(c);
-	jffs2_erase_pending_blocks(c, 0);
-	jffs2_flush_wbuf_gc(c, 0);
-}
-
-
 /* jffs2_new_inode: allocate a new inode and inocache, add it to the hash,
    fill in the raw_inode while you're at it. */
 struct inode *jffs2_new_inode (struct inode *dir_i, int mode, struct jffs2_raw_inode *ri)
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index 5e194a5c8e29..2228380c47b9 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -181,7 +181,6 @@ void jffs2_dirty_inode(struct inode *inode);
 struct inode *jffs2_new_inode (struct inode *dir_i, int mode,
 			       struct jffs2_raw_inode *ri);
 int jffs2_statfs (struct dentry *, struct kstatfs *);
-void jffs2_write_super (struct super_block *);
 int jffs2_remount_fs (struct super_block *, int *, char *);
 int jffs2_do_fill_super(struct super_block *sb, void *data, int silent);
 void jffs2_gc_release_inode(struct jffs2_sb_info *c,
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 4c4e18c54a51..07a22caf2687 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -53,10 +53,29 @@ static void jffs2_i_init_once(void *foo)
 	inode_init_once(&f->vfs_inode);
 }
 
+static void jffs2_write_super(struct super_block *sb)
+{
+	struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
+
+	lock_super(sb);
+	sb->s_dirt = 0;
+
+	if (!(sb->s_flags & MS_RDONLY)) {
+		D1(printk(KERN_DEBUG "jffs2_write_super()\n"));
+		jffs2_garbage_collect_trigger(c);
+		jffs2_erase_pending_blocks(c, 0);
+		jffs2_flush_wbuf_gc(c, 0);
+	}
+
+	unlock_super(sb);
+}
+
 static int jffs2_sync_fs(struct super_block *sb, int wait)
 {
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
 
+	jffs2_write_super(sb);
+
 	mutex_lock(&c->alloc_sem);
 	jffs2_flush_wbuf_pad(c);
 	mutex_unlock(&c->alloc_sem);
@@ -174,6 +193,11 @@ static void jffs2_put_super (struct super_block *sb)
 
 	D2(printk(KERN_DEBUG "jffs2: jffs2_put_super()\n"));
 
+	lock_kernel();
+
+	if (sb->s_dirt)
+		jffs2_write_super(sb);
+
 	mutex_lock(&c->alloc_sem);
 	jffs2_flush_wbuf_pad(c);
 	mutex_unlock(&c->alloc_sem);
@@ -192,6 +216,8 @@ static void jffs2_put_super (struct super_block *sb)
 	if (c->mtd->sync)
 		c->mtd->sync(c->mtd);
 
+	unlock_kernel();
+
 	D1(printk(KERN_DEBUG "jffs2_put_super returning\n"));
 }
 
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index 346057218edc..0fc30407f039 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -2571,6 +2571,7 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp)
 
 			txAbort(tid, 0);
 			txEnd(tid);
+			mutex_unlock(&JFS_IP(ipimap)->commit_mutex);
 
 			/* release the inode map lock */
 			IWRITE_UNLOCK(ipimap);
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 6f21adf9479a..09b1b6ee2186 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -32,6 +32,7 @@
 #include <linux/crc32.h>
 #include <asm/uaccess.h>
 #include <linux/seq_file.h>
+#include <linux/smp_lock.h>
 
 #include "jfs_incore.h"
 #include "jfs_filsys.h"
@@ -183,6 +184,9 @@ static void jfs_put_super(struct super_block *sb)
 	int rc;
 
 	jfs_info("In jfs_put_super");
+
+	lock_kernel();
+
 	rc = jfs_umount(sb);
 	if (rc)
 		jfs_err("jfs_umount failed with return code %d", rc);
@@ -195,6 +199,8 @@ static void jfs_put_super(struct super_block *sb)
 	sbi->direct_inode = NULL;
 
 	kfree(sbi);
+
+	unlock_kernel();
 }
 
 enum {
@@ -370,19 +376,24 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data)
 	s64 newLVSize = 0;
 	int rc = 0;
 	int flag = JFS_SBI(sb)->flag;
+	int ret;
 
 	if (!parse_options(data, sb, &newLVSize, &flag)) {
 		return -EINVAL;
 	}
+	lock_kernel();
 	if (newLVSize) {
 		if (sb->s_flags & MS_RDONLY) {
 			printk(KERN_ERR
 		  "JFS: resize requires volume to be mounted read-write\n");
+			unlock_kernel();
 			return -EROFS;
 		}
 		rc = jfs_extendfs(sb, newLVSize, 0);
-		if (rc)
+		if (rc) {
+			unlock_kernel();
 			return rc;
+		}
 	}
 
 	if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) {
@@ -393,23 +404,31 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data)
 		truncate_inode_pages(JFS_SBI(sb)->direct_inode->i_mapping, 0);
 
 		JFS_SBI(sb)->flag = flag;
-		return jfs_mount_rw(sb, 1);
+		ret = jfs_mount_rw(sb, 1);
+		unlock_kernel();
+		return ret;
 	}
 	if ((!(sb->s_flags & MS_RDONLY)) && (*flags & MS_RDONLY)) {
 		rc = jfs_umount_rw(sb);
 		JFS_SBI(sb)->flag = flag;
+		unlock_kernel();
 		return rc;
 	}
 	if ((JFS_SBI(sb)->flag & JFS_NOINTEGRITY) != (flag & JFS_NOINTEGRITY))
 		if (!(sb->s_flags & MS_RDONLY)) {
 			rc = jfs_umount_rw(sb);
-			if (rc)
+			if (rc) {
+				unlock_kernel();
 				return rc;
+			}
 			JFS_SBI(sb)->flag = flag;
-			return jfs_mount_rw(sb, 1);
+			ret = jfs_mount_rw(sb, 1);
+			unlock_kernel();
+			return ret;
 		}
 	JFS_SBI(sb)->flag = flag;
 
+	unlock_kernel();
 	return 0;
 }
 
@@ -720,8 +739,10 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type,
 		blk++;
 	}
 out:
-	if (len == towrite)
+	if (len == towrite) {
+		mutex_unlock(&inode->i_mutex);
 		return err;
+	}
 	if (inode->i_size < off+len-towrite)
 		i_size_write(inode, off+len-towrite);
 	inode->i_version++;
diff --git a/fs/libfs.c b/fs/libfs.c
index 80046ddf5063..ddfa89948c3f 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -9,6 +9,8 @@
 #include <linux/vfs.h>
 #include <linux/mutex.h>
 #include <linux/exportfs.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
 
 #include <asm/uaccess.h>
 
@@ -807,6 +809,29 @@ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid,
 }
 EXPORT_SYMBOL_GPL(generic_fh_to_parent);
 
+int simple_fsync(struct file *file, struct dentry *dentry, int datasync)
+{
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = 0, /* metadata-only; caller takes care of data */
+	};
+	struct inode *inode = dentry->d_inode;
+	int err;
+	int ret;
+
+	ret = sync_mapping_buffers(inode->i_mapping);
+	if (!(inode->i_state & I_DIRTY))
+		return ret;
+	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+		return ret;
+
+	err = sync_inode(inode, &wbc);
+	if (ret == 0)
+		ret = err;
+	return ret;
+}
+EXPORT_SYMBOL(simple_fsync);
+
 EXPORT_SYMBOL(dcache_dir_close);
 EXPORT_SYMBOL(dcache_dir_lseek);
 EXPORT_SYMBOL(dcache_dir_open);
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index d4946c4c90e2..e5f206467e40 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -22,7 +22,7 @@ static int minix_readdir(struct file *, void *, filldir_t);
 const struct file_operations minix_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= minix_readdir,
-	.fsync		= minix_sync_file,
+	.fsync		= simple_fsync,
 };
 
 static inline void dir_put_page(struct page *page)
diff --git a/fs/minix/file.c b/fs/minix/file.c
index 17765f697e50..3eec3e607a87 100644
--- a/fs/minix/file.c
+++ b/fs/minix/file.c
@@ -6,15 +6,12 @@
  *  minix regular file handling primitives
  */
 
-#include <linux/buffer_head.h>		/* for fsync_inode_buffers() */
 #include "minix.h"
 
 /*
  * We have mostly NULLs here: the current defaults are OK for
  * the minix filesystem.
  */
-int minix_sync_file(struct file *, struct dentry *, int);
-
 const struct file_operations minix_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
@@ -22,7 +19,7 @@ const struct file_operations minix_file_operations = {
 	.write		= do_sync_write,
 	.aio_write	= generic_file_aio_write,
 	.mmap		= generic_file_mmap,
-	.fsync		= minix_sync_file,
+	.fsync		= simple_fsync,
 	.splice_read	= generic_file_splice_read,
 };
 
@@ -30,18 +27,3 @@ const struct inode_operations minix_file_inode_operations = {
 	.truncate	= minix_truncate,
 	.getattr	= minix_getattr,
 };
-
-int minix_sync_file(struct file * file, struct dentry *dentry, int datasync)
-{
-	struct inode *inode = dentry->d_inode;
-	int err;
-
-	err = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY))
-		return err;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		return err;
-	
-	err |= minix_sync_inode(inode);
-	return err ? -EIO : 0;
-}
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index daad3c2740db..f91a23693597 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -35,6 +35,8 @@ static void minix_put_super(struct super_block *sb)
 	int i;
 	struct minix_sb_info *sbi = minix_sb(sb);
 
+	lock_kernel();
+
 	if (!(sb->s_flags & MS_RDONLY)) {
 		if (sbi->s_version != MINIX_V3)	 /* s_state is now out from V3 sb */
 			sbi->s_ms->s_state = sbi->s_mount_state;
@@ -49,7 +51,7 @@ static void minix_put_super(struct super_block *sb)
 	sb->s_fs_info = NULL;
 	kfree(sbi);
 
-	return;
+	unlock_kernel();
 }
 
 static struct kmem_cache * minix_inode_cachep;
@@ -554,38 +556,25 @@ static struct buffer_head * V2_minix_update_inode(struct inode * inode)
 	return bh;
 }
 
-static struct buffer_head *minix_update_inode(struct inode *inode)
-{
-	if (INODE_VERSION(inode) == MINIX_V1)
-		return V1_minix_update_inode(inode);
-	else
-		return V2_minix_update_inode(inode);
-}
-
-static int minix_write_inode(struct inode * inode, int wait)
-{
-	brelse(minix_update_inode(inode));
-	return 0;
-}
-
-int minix_sync_inode(struct inode * inode)
+static int minix_write_inode(struct inode *inode, int wait)
 {
 	int err = 0;
 	struct buffer_head *bh;
 
-	bh = minix_update_inode(inode);
-	if (bh && buffer_dirty(bh))
-	{
+	if (INODE_VERSION(inode) == MINIX_V1)
+		bh = V1_minix_update_inode(inode);
+	else
+		bh = V2_minix_update_inode(inode);
+	if (!bh)
+		return -EIO;
+	if (wait && buffer_dirty(bh)) {
 		sync_dirty_buffer(bh);
-		if (buffer_req(bh) && !buffer_uptodate(bh))
-		{
+		if (buffer_req(bh) && !buffer_uptodate(bh)) {
 			printk("IO error syncing minix inode [%s:%08lx]\n",
 				inode->i_sb->s_id, inode->i_ino);
-			err = -1;
+			err = -EIO;
 		}
 	}
-	else if (!bh)
-		err = -1;
 	brelse (bh);
 	return err;
 }
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index e6a0b193bea4..cb7fdd11f9a5 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -57,7 +57,6 @@ extern int __minix_write_begin(struct file *file, struct address_space *mapping,
 extern void V1_minix_truncate(struct inode *);
 extern void V2_minix_truncate(struct inode *);
 extern void minix_truncate(struct inode *);
-extern int minix_sync_inode(struct inode *);
 extern void minix_set_inode(struct inode *, dev_t);
 extern int V1_minix_get_block(struct inode *, long, struct buffer_head *, int);
 extern int V2_minix_get_block(struct inode *, long, struct buffer_head *, int);
@@ -72,7 +71,6 @@ extern int minix_empty_dir(struct inode*);
 extern void minix_set_link(struct minix_dir_entry*, struct page*, struct inode*);
 extern struct minix_dir_entry *minix_dotdot(struct inode*, struct page**);
 extern ino_t minix_inode_by_name(struct dentry*);
-extern int minix_sync_file(struct file *, struct dentry *, int);
 
 extern const struct inode_operations minix_file_inode_operations;
 extern const struct inode_operations minix_dir_inode_operations;
diff --git a/fs/mpage.c b/fs/mpage.c
index 680ba60863ff..42381bd6543b 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -379,7 +379,8 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
 
-	clear_buffer_mapped(&map_bh);
+	map_bh.b_state = 0;
+	map_bh.b_size = 0;
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = list_entry(pages->prev, struct page, lru);
 
@@ -412,7 +413,8 @@ int mpage_readpage(struct page *page, get_block_t get_block)
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
 
-	clear_buffer_mapped(&map_bh);
+	map_bh.b_state = 0;
+	map_bh.b_size = 0;
 	bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
 			&map_bh, &first_logical_block, get_block);
 	if (bio)
diff --git a/fs/namei.c b/fs/namei.c
index 967c3db92724..527119afb6a5 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -552,6 +552,17 @@ static __always_inline int link_path_walk(const char *name, struct nameidata *nd
 	return result;
 }
 
+static __always_inline void set_root(struct nameidata *nd)
+{
+	if (!nd->root.mnt) {
+		struct fs_struct *fs = current->fs;
+		read_lock(&fs->lock);
+		nd->root = fs->root;
+		path_get(&nd->root);
+		read_unlock(&fs->lock);
+	}
+}
+
 static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
 {
 	int res = 0;
@@ -560,14 +571,10 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l
 		goto fail;
 
 	if (*link == '/') {
-		struct fs_struct *fs = current->fs;
-
+		set_root(nd);
 		path_put(&nd->path);
-
-		read_lock(&fs->lock);
-		nd->path = fs->root;
-		path_get(&fs->root);
-		read_unlock(&fs->lock);
+		nd->path = nd->root;
+		path_get(&nd->root);
 	}
 
 	res = link_path_walk(link, nd);
@@ -668,23 +675,23 @@ loop:
 	return err;
 }
 
-int follow_up(struct vfsmount **mnt, struct dentry **dentry)
+int follow_up(struct path *path)
 {
 	struct vfsmount *parent;
 	struct dentry *mountpoint;
 	spin_lock(&vfsmount_lock);
-	parent=(*mnt)->mnt_parent;
-	if (parent == *mnt) {
+	parent = path->mnt->mnt_parent;
+	if (parent == path->mnt) {
 		spin_unlock(&vfsmount_lock);
 		return 0;
 	}
 	mntget(parent);
-	mountpoint=dget((*mnt)->mnt_mountpoint);
+	mountpoint = dget(path->mnt->mnt_mountpoint);
 	spin_unlock(&vfsmount_lock);
-	dput(*dentry);
-	*dentry = mountpoint;
-	mntput(*mnt);
-	*mnt = parent;
+	dput(path->dentry);
+	path->dentry = mountpoint;
+	mntput(path->mnt);
+	path->mnt = parent;
 	return 1;
 }
 
@@ -695,7 +702,7 @@ static int __follow_mount(struct path *path)
 {
 	int res = 0;
 	while (d_mountpoint(path->dentry)) {
-		struct vfsmount *mounted = lookup_mnt(path->mnt, path->dentry);
+		struct vfsmount *mounted = lookup_mnt(path);
 		if (!mounted)
 			break;
 		dput(path->dentry);
@@ -708,32 +715,32 @@ static int __follow_mount(struct path *path)
 	return res;
 }
 
-static void follow_mount(struct vfsmount **mnt, struct dentry **dentry)
+static void follow_mount(struct path *path)
 {
-	while (d_mountpoint(*dentry)) {
-		struct vfsmount *mounted = lookup_mnt(*mnt, *dentry);
+	while (d_mountpoint(path->dentry)) {
+		struct vfsmount *mounted = lookup_mnt(path);
 		if (!mounted)
 			break;
-		dput(*dentry);
-		mntput(*mnt);
-		*mnt = mounted;
-		*dentry = dget(mounted->mnt_root);
+		dput(path->dentry);
+		mntput(path->mnt);
+		path->mnt = mounted;
+		path->dentry = dget(mounted->mnt_root);
 	}
 }
 
 /* no need for dcache_lock, as serialization is taken care in
  * namespace.c
  */
-int follow_down(struct vfsmount **mnt, struct dentry **dentry)
+int follow_down(struct path *path)
 {
 	struct vfsmount *mounted;
 
-	mounted = lookup_mnt(*mnt, *dentry);
+	mounted = lookup_mnt(path);
 	if (mounted) {
-		dput(*dentry);
-		mntput(*mnt);
-		*mnt = mounted;
-		*dentry = dget(mounted->mnt_root);
+		dput(path->dentry);
+		mntput(path->mnt);
+		path->mnt = mounted;
+		path->dentry = dget(mounted->mnt_root);
 		return 1;
 	}
 	return 0;
@@ -741,19 +748,16 @@ int follow_down(struct vfsmount **mnt, struct dentry **dentry)
 
 static __always_inline void follow_dotdot(struct nameidata *nd)
 {
-	struct fs_struct *fs = current->fs;
+	set_root(nd);
 
 	while(1) {
 		struct vfsmount *parent;
 		struct dentry *old = nd->path.dentry;
 
-                read_lock(&fs->lock);
-		if (nd->path.dentry == fs->root.dentry &&
-		    nd->path.mnt == fs->root.mnt) {
-                        read_unlock(&fs->lock);
+		if (nd->path.dentry == nd->root.dentry &&
+		    nd->path.mnt == nd->root.mnt) {
 			break;
 		}
-                read_unlock(&fs->lock);
 		spin_lock(&dcache_lock);
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
 			nd->path.dentry = dget(nd->path.dentry->d_parent);
@@ -775,7 +779,7 @@ static __always_inline void follow_dotdot(struct nameidata *nd)
 		mntput(nd->path.mnt);
 		nd->path.mnt = parent;
 	}
-	follow_mount(&nd->path.mnt, &nd->path.dentry);
+	follow_mount(&nd->path);
 }
 
 /*
@@ -853,7 +857,8 @@ static int __link_path_walk(const char *name, struct nameidata *nd)
 			err = inode_permission(nd->path.dentry->d_inode,
 					       MAY_EXEC);
 		if (!err)
-			err = ima_path_check(&nd->path, MAY_EXEC);
+			err = ima_path_check(&nd->path, MAY_EXEC,
+				             IMA_COUNT_UPDATE);
  		if (err)
 			break;
 
@@ -1016,25 +1021,23 @@ static int path_walk(const char *name, struct nameidata *nd)
 	return link_path_walk(name, nd);
 }
 
-/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
-static int do_path_lookup(int dfd, const char *name,
-				unsigned int flags, struct nameidata *nd)
+static int path_init(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
 {
 	int retval = 0;
 	int fput_needed;
 	struct file *file;
-	struct fs_struct *fs = current->fs;
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags;
 	nd->depth = 0;
+	nd->root.mnt = NULL;
 
 	if (*name=='/') {
-		read_lock(&fs->lock);
-		nd->path = fs->root;
-		path_get(&fs->root);
-		read_unlock(&fs->lock);
+		set_root(nd);
+		nd->path = nd->root;
+		path_get(&nd->root);
 	} else if (dfd == AT_FDCWD) {
+		struct fs_struct *fs = current->fs;
 		read_lock(&fs->lock);
 		nd->path = fs->pwd;
 		path_get(&fs->pwd);
@@ -1062,17 +1065,29 @@ static int do_path_lookup(int dfd, const char *name,
 
 		fput_light(file, fput_needed);
 	}
-
-	retval = path_walk(name, nd);
-	if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
-				nd->path.dentry->d_inode))
-		audit_inode(name, nd->path.dentry);
-out_fail:
-	return retval;
+	return 0;
 
 fput_fail:
 	fput_light(file, fput_needed);
-	goto out_fail;
+out_fail:
+	return retval;
+}
+
+/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
+static int do_path_lookup(int dfd, const char *name,
+				unsigned int flags, struct nameidata *nd)
+{
+	int retval = path_init(dfd, name, flags, nd);
+	if (!retval)
+		retval = path_walk(name, nd);
+	if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
+				nd->path.dentry->d_inode))
+		audit_inode(name, nd->path.dentry);
+	if (nd->root.mnt) {
+		path_put(&nd->root);
+		nd->root.mnt = NULL;
+	}
+	return retval;
 }
 
 int path_lookup(const char *name, unsigned int flags,
@@ -1112,14 +1127,18 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 	nd->path.dentry = dentry;
 	nd->path.mnt = mnt;
 	path_get(&nd->path);
+	nd->root = nd->path;
+	path_get(&nd->root);
 
 	retval = path_walk(name, nd);
 	if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
 				nd->path.dentry->d_inode))
 		audit_inode(name, nd->path.dentry);
 
-	return retval;
+	path_put(&nd->root);
+	nd->root.mnt = NULL;
 
+	return retval;
 }
 
 /**
@@ -1515,7 +1534,8 @@ int may_open(struct path *path, int acc_mode, int flag)
 		return error;
 
 	error = ima_path_check(path,
-			       acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC));
+			       acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC),
+			       IMA_COUNT_UPDATE);
 	if (error)
 		return error;
 	/*
@@ -1674,9 +1694,14 @@ struct file *do_filp_open(int dfd, const char *pathname,
 	/*
 	 * Create - we need to know the parent.
 	 */
-	error = do_path_lookup(dfd, pathname, LOOKUP_PARENT, &nd);
+	error = path_init(dfd, pathname, LOOKUP_PARENT, &nd);
 	if (error)
 		return ERR_PTR(error);
+	error = path_walk(pathname, &nd);
+	if (error)
+		return ERR_PTR(error);
+	if (unlikely(!audit_dummy_context()))
+		audit_inode(pathname, nd.path.dentry);
 
 	/*
 	 * We have the parent and last component. First of all, check
@@ -1804,6 +1829,8 @@ exit:
 	if (!IS_ERR(nd.intent.open.file))
 		release_open_intent(&nd);
 exit_parent:
+	if (nd.root.mnt)
+		path_put(&nd.root);
 	path_put(&nd.path);
 	return ERR_PTR(error);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 134d494158d9..2dd333b0fe7f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -131,10 +131,20 @@ struct vfsmount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_share);
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
-		atomic_set(&mnt->__mnt_writers, 0);
+#ifdef CONFIG_SMP
+		mnt->mnt_writers = alloc_percpu(int);
+		if (!mnt->mnt_writers)
+			goto out_free_devname;
+#else
+		mnt->mnt_writers = 0;
+#endif
 	}
 	return mnt;
 
+#ifdef CONFIG_SMP
+out_free_devname:
+	kfree(mnt->mnt_devname);
+#endif
 out_free_id:
 	mnt_free_id(mnt);
 out_free_cache:
@@ -171,65 +181,38 @@ int __mnt_is_readonly(struct vfsmount *mnt)
 }
 EXPORT_SYMBOL_GPL(__mnt_is_readonly);
 
-struct mnt_writer {
-	/*
-	 * If holding multiple instances of this lock, they
-	 * must be ordered by cpu number.
-	 */
-	spinlock_t lock;
-	struct lock_class_key lock_class; /* compiles out with !lockdep */
-	unsigned long count;
-	struct vfsmount *mnt;
-} ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(struct mnt_writer, mnt_writers);
-
-static int __init init_mnt_writers(void)
+static inline void inc_mnt_writers(struct vfsmount *mnt)
 {
-	int cpu;
-	for_each_possible_cpu(cpu) {
-		struct mnt_writer *writer = &per_cpu(mnt_writers, cpu);
-		spin_lock_init(&writer->lock);
-		lockdep_set_class(&writer->lock, &writer->lock_class);
-		writer->count = 0;
-	}
-	return 0;
+#ifdef CONFIG_SMP
+	(*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))++;
+#else
+	mnt->mnt_writers++;
+#endif
 }
-fs_initcall(init_mnt_writers);
 
-static void unlock_mnt_writers(void)
+static inline void dec_mnt_writers(struct vfsmount *mnt)
 {
+#ifdef CONFIG_SMP
+	(*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))--;
+#else
+	mnt->mnt_writers--;
+#endif
+}
+
+static unsigned int count_mnt_writers(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+	unsigned int count = 0;
 	int cpu;
-	struct mnt_writer *cpu_writer;
 
 	for_each_possible_cpu(cpu) {
-		cpu_writer = &per_cpu(mnt_writers, cpu);
-		spin_unlock(&cpu_writer->lock);
+		count += *per_cpu_ptr(mnt->mnt_writers, cpu);
 	}
-}
 
-static inline void __clear_mnt_count(struct mnt_writer *cpu_writer)
-{
-	if (!cpu_writer->mnt)
-		return;
-	/*
-	 * This is in case anyone ever leaves an invalid,
-	 * old ->mnt and a count of 0.
-	 */
-	if (!cpu_writer->count)
-		return;
-	atomic_add(cpu_writer->count, &cpu_writer->mnt->__mnt_writers);
-	cpu_writer->count = 0;
-}
- /*
- * must hold cpu_writer->lock
- */
-static inline void use_cpu_writer_for_mount(struct mnt_writer *cpu_writer,
-					  struct vfsmount *mnt)
-{
-	if (cpu_writer->mnt == mnt)
-		return;
-	__clear_mnt_count(cpu_writer);
-	cpu_writer->mnt = mnt;
+	return count;
+#else
+	return mnt->mnt_writers;
+#endif
 }
 
 /*
@@ -253,74 +236,73 @@ static inline void use_cpu_writer_for_mount(struct mnt_writer *cpu_writer,
 int mnt_want_write(struct vfsmount *mnt)
 {
 	int ret = 0;
-	struct mnt_writer *cpu_writer;
 
-	cpu_writer = &get_cpu_var(mnt_writers);
-	spin_lock(&cpu_writer->lock);
+	preempt_disable();
+	inc_mnt_writers(mnt);
+	/*
+	 * The store to inc_mnt_writers must be visible before we pass
+	 * MNT_WRITE_HOLD loop below, so that the slowpath can see our
+	 * incremented count after it has set MNT_WRITE_HOLD.
+	 */
+	smp_mb();
+	while (mnt->mnt_flags & MNT_WRITE_HOLD)
+		cpu_relax();
+	/*
+	 * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
+	 * be set to match its requirements. So we must not load that until
+	 * MNT_WRITE_HOLD is cleared.
+	 */
+	smp_rmb();
 	if (__mnt_is_readonly(mnt)) {
+		dec_mnt_writers(mnt);
 		ret = -EROFS;
 		goto out;
 	}
-	use_cpu_writer_for_mount(cpu_writer, mnt);
-	cpu_writer->count++;
 out:
-	spin_unlock(&cpu_writer->lock);
-	put_cpu_var(mnt_writers);
+	preempt_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mnt_want_write);
 
-static void lock_mnt_writers(void)
-{
-	int cpu;
-	struct mnt_writer *cpu_writer;
-
-	for_each_possible_cpu(cpu) {
-		cpu_writer = &per_cpu(mnt_writers, cpu);
-		spin_lock(&cpu_writer->lock);
-		__clear_mnt_count(cpu_writer);
-		cpu_writer->mnt = NULL;
-	}
-}
-
-/*
- * These per-cpu write counts are not guaranteed to have
- * matched increments and decrements on any given cpu.
- * A file open()ed for write on one cpu and close()d on
- * another cpu will imbalance this count.  Make sure it
- * does not get too far out of whack.
+/**
+ * mnt_clone_write - get write access to a mount
+ * @mnt: the mount on which to take a write
+ *
+ * This is effectively like mnt_want_write, except
+ * it must only be used to take an extra write reference
+ * on a mountpoint that we already know has a write reference
+ * on it. This allows some optimisation.
+ *
+ * After finished, mnt_drop_write must be called as usual to
+ * drop the reference.
  */
-static void handle_write_count_underflow(struct vfsmount *mnt)
+int mnt_clone_write(struct vfsmount *mnt)
 {
-	if (atomic_read(&mnt->__mnt_writers) >=
-	    MNT_WRITER_UNDERFLOW_LIMIT)
-		return;
-	/*
-	 * It isn't necessary to hold all of the locks
-	 * at the same time, but doing it this way makes
-	 * us share a lot more code.
-	 */
-	lock_mnt_writers();
-	/*
-	 * vfsmount_lock is for mnt_flags.
-	 */
-	spin_lock(&vfsmount_lock);
-	/*
-	 * If coalescing the per-cpu writer counts did not
-	 * get us back to a positive writer count, we have
-	 * a bug.
-	 */
-	if ((atomic_read(&mnt->__mnt_writers) < 0) &&
-	    !(mnt->mnt_flags & MNT_IMBALANCED_WRITE_COUNT)) {
-		WARN(1, KERN_DEBUG "leak detected on mount(%p) writers "
-				"count: %d\n",
-			mnt, atomic_read(&mnt->__mnt_writers));
-		/* use the flag to keep the dmesg spam down */
-		mnt->mnt_flags |= MNT_IMBALANCED_WRITE_COUNT;
-	}
-	spin_unlock(&vfsmount_lock);
-	unlock_mnt_writers();
+	/* superblock may be r/o */
+	if (__mnt_is_readonly(mnt))
+		return -EROFS;
+	preempt_disable();
+	inc_mnt_writers(mnt);
+	preempt_enable();
+	return 0;
 }
+EXPORT_SYMBOL_GPL(mnt_clone_write);
+
+/**
+ * mnt_want_write_file - get write access to a file's mount
+ * @file: the file who's mount on which to take a write
+ *
+ * This is like mnt_want_write, but it takes a file and can
+ * do some optimisations if the file is open for write already
+ */
+int mnt_want_write_file(struct file *file)
+{
+	if (!(file->f_mode & FMODE_WRITE))
+		return mnt_want_write(file->f_path.mnt);
+	else
+		return mnt_clone_write(file->f_path.mnt);
+}
+EXPORT_SYMBOL_GPL(mnt_want_write_file);
 
 /**
  * mnt_drop_write - give up write access to a mount
@@ -332,37 +314,9 @@ static void handle_write_count_underflow(struct vfsmount *mnt)
  */
 void mnt_drop_write(struct vfsmount *mnt)
 {
-	int must_check_underflow = 0;
-	struct mnt_writer *cpu_writer;
-
-	cpu_writer = &get_cpu_var(mnt_writers);
-	spin_lock(&cpu_writer->lock);
-
-	use_cpu_writer_for_mount(cpu_writer, mnt);
-	if (cpu_writer->count > 0) {
-		cpu_writer->count--;
-	} else {
-		must_check_underflow = 1;
-		atomic_dec(&mnt->__mnt_writers);
-	}
-
-	spin_unlock(&cpu_writer->lock);
-	/*
-	 * Logically, we could call this each time,
-	 * but the __mnt_writers cacheline tends to
-	 * be cold, and makes this expensive.
-	 */
-	if (must_check_underflow)
-		handle_write_count_underflow(mnt);
-	/*
-	 * This could be done right after the spinlock
-	 * is taken because the spinlock keeps us on
-	 * the cpu, and disables preemption.  However,
-	 * putting it here bounds the amount that
-	 * __mnt_writers can underflow.  Without it,
-	 * we could theoretically wrap __mnt_writers.
-	 */
-	put_cpu_var(mnt_writers);
+	preempt_disable();
+	dec_mnt_writers(mnt);
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(mnt_drop_write);
 
@@ -370,24 +324,41 @@ static int mnt_make_readonly(struct vfsmount *mnt)
 {
 	int ret = 0;
 
-	lock_mnt_writers();
-	/*
-	 * With all the locks held, this value is stable
-	 */
-	if (atomic_read(&mnt->__mnt_writers) > 0) {
-		ret = -EBUSY;
-		goto out;
-	}
-	/*
-	 * nobody can do a successful mnt_want_write() with all
-	 * of the counts in MNT_DENIED_WRITE and the locks held.
-	 */
 	spin_lock(&vfsmount_lock);
-	if (!ret)
+	mnt->mnt_flags |= MNT_WRITE_HOLD;
+	/*
+	 * After storing MNT_WRITE_HOLD, we'll read the counters. This store
+	 * should be visible before we do.
+	 */
+	smp_mb();
+
+	/*
+	 * With writers on hold, if this value is zero, then there are
+	 * definitely no active writers (although held writers may subsequently
+	 * increment the count, they'll have to wait, and decrement it after
+	 * seeing MNT_READONLY).
+	 *
+	 * It is OK to have counter incremented on one CPU and decremented on
+	 * another: the sum will add up correctly. The danger would be when we
+	 * sum up each counter, if we read a counter before it is incremented,
+	 * but then read another CPU's count which it has been subsequently
+	 * decremented from -- we would see more decrements than we should.
+	 * MNT_WRITE_HOLD protects against this scenario, because
+	 * mnt_want_write first increments count, then smp_mb, then spins on
+	 * MNT_WRITE_HOLD, so it can't be decremented by another CPU while
+	 * we're counting up here.
+	 */
+	if (count_mnt_writers(mnt) > 0)
+		ret = -EBUSY;
+	else
 		mnt->mnt_flags |= MNT_READONLY;
+	/*
+	 * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers
+	 * that become unheld will see MNT_READONLY.
+	 */
+	smp_wmb();
+	mnt->mnt_flags &= ~MNT_WRITE_HOLD;
 	spin_unlock(&vfsmount_lock);
-out:
-	unlock_mnt_writers();
 	return ret;
 }
 
@@ -410,6 +381,9 @@ void free_vfsmnt(struct vfsmount *mnt)
 {
 	kfree(mnt->mnt_devname);
 	mnt_free_id(mnt);
+#ifdef CONFIG_SMP
+	free_percpu(mnt->mnt_writers);
+#endif
 	kmem_cache_free(mnt_cache, mnt);
 }
 
@@ -442,11 +416,11 @@ struct vfsmount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry,
  * lookup_mnt increments the ref count before returning
  * the vfsmount struct.
  */
-struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
+struct vfsmount *lookup_mnt(struct path *path)
 {
 	struct vfsmount *child_mnt;
 	spin_lock(&vfsmount_lock);
-	if ((child_mnt = __lookup_mnt(mnt, dentry, 1)))
+	if ((child_mnt = __lookup_mnt(path->mnt, path->dentry, 1)))
 		mntget(child_mnt);
 	spin_unlock(&vfsmount_lock);
 	return child_mnt;
@@ -604,38 +578,18 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
 
 static inline void __mntput(struct vfsmount *mnt)
 {
-	int cpu;
 	struct super_block *sb = mnt->mnt_sb;
-	/*
-	 * We don't have to hold all of the locks at the
-	 * same time here because we know that we're the
-	 * last reference to mnt and that no new writers
-	 * can come in.
-	 */
-	for_each_possible_cpu(cpu) {
-		struct mnt_writer *cpu_writer = &per_cpu(mnt_writers, cpu);
-		spin_lock(&cpu_writer->lock);
-		if (cpu_writer->mnt != mnt) {
-			spin_unlock(&cpu_writer->lock);
-			continue;
-		}
-		atomic_add(cpu_writer->count, &mnt->__mnt_writers);
-		cpu_writer->count = 0;
-		/*
-		 * Might as well do this so that no one
-		 * ever sees the pointer and expects
-		 * it to be valid.
-		 */
-		cpu_writer->mnt = NULL;
-		spin_unlock(&cpu_writer->lock);
-	}
 	/*
 	 * This probably indicates that somebody messed
 	 * up a mnt_want/drop_write() pair.  If this
 	 * happens, the filesystem was probably unable
 	 * to make r/w->r/o transitions.
 	 */
-	WARN_ON(atomic_read(&mnt->__mnt_writers));
+	/*
+	 * atomic_dec_and_lock() used to deal with ->mnt_count decrements
+	 * provides barriers, so count_mnt_writers() below is safe.  AV
+	 */
+	WARN_ON(count_mnt_writers(mnt));
 	dput(mnt->mnt_root);
 	free_vfsmnt(mnt);
 	deactivate_super(sb);
@@ -1106,11 +1060,8 @@ static int do_umount(struct vfsmount *mnt, int flags)
 		 * we just try to remount it readonly.
 		 */
 		down_write(&sb->s_umount);
-		if (!(sb->s_flags & MS_RDONLY)) {
-			lock_kernel();
+		if (!(sb->s_flags & MS_RDONLY))
 			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
-			unlock_kernel();
-		}
 		up_write(&sb->s_umount);
 		return retval;
 	}
@@ -1253,11 +1204,11 @@ Enomem:
 	return NULL;
 }
 
-struct vfsmount *collect_mounts(struct vfsmount *mnt, struct dentry *dentry)
+struct vfsmount *collect_mounts(struct path *path)
 {
 	struct vfsmount *tree;
 	down_write(&namespace_sem);
-	tree = copy_tree(mnt, dentry, CL_COPY_ALL | CL_PRIVATE);
+	tree = copy_tree(path->mnt, path->dentry, CL_COPY_ALL | CL_PRIVATE);
 	up_write(&namespace_sem);
 	return tree;
 }
@@ -1430,7 +1381,7 @@ static int graft_tree(struct vfsmount *mnt, struct path *path)
 		goto out_unlock;
 
 	err = -ENOENT;
-	if (IS_ROOT(path->dentry) || !d_unhashed(path->dentry))
+	if (!d_unlinked(path->dentry))
 		err = attach_recursive_mnt(mnt, path, NULL);
 out_unlock:
 	mutex_unlock(&path->dentry->d_inode->i_mutex);
@@ -1601,7 +1552,7 @@ static int do_move_mount(struct path *path, char *old_name)
 
 	down_write(&namespace_sem);
 	while (d_mountpoint(path->dentry) &&
-	       follow_down(&path->mnt, &path->dentry))
+	       follow_down(path))
 		;
 	err = -EINVAL;
 	if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
@@ -1612,7 +1563,7 @@ static int do_move_mount(struct path *path, char *old_name)
 	if (IS_DEADDIR(path->dentry->d_inode))
 		goto out1;
 
-	if (!IS_ROOT(path->dentry) && d_unhashed(path->dentry))
+	if (d_unlinked(path->dentry))
 		goto out1;
 
 	err = -EINVAL;
@@ -1676,7 +1627,9 @@ static int do_new_mount(struct path *path, char *type, int flags,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	lock_kernel();
 	mnt = do_kern_mount(type, flags, name, data);
+	unlock_kernel();
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
 
@@ -1695,10 +1648,10 @@ int do_add_mount(struct vfsmount *newmnt, struct path *path,
 	down_write(&namespace_sem);
 	/* Something was mounted here while we slept */
 	while (d_mountpoint(path->dentry) &&
-	       follow_down(&path->mnt, &path->dentry))
+	       follow_down(path))
 		;
 	err = -EINVAL;
-	if (!check_mnt(path->mnt))
+	if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
 		goto unlock;
 
 	/* Refuse the same filesystem on the same mount point */
@@ -2092,10 +2045,8 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	if (retval < 0)
 		goto out3;
 
-	lock_kernel();
 	retval = do_mount((char *)dev_page, dir_page, (char *)type_page,
 			  flags, (void *)data_page);
-	unlock_kernel();
 	free_page(data_page);
 
 out3:
@@ -2175,9 +2126,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	error = -ENOENT;
 	if (IS_DEADDIR(new.dentry->d_inode))
 		goto out2;
-	if (d_unhashed(new.dentry) && !IS_ROOT(new.dentry))
+	if (d_unlinked(new.dentry))
 		goto out2;
-	if (d_unhashed(old.dentry) && !IS_ROOT(old.dentry))
+	if (d_unlinked(old.dentry))
 		goto out2;
 	error = -EBUSY;
 	if (new.mnt == root.mnt ||
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index d642f0e5b365..b99ce205b1bd 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -736,6 +736,8 @@ static void ncp_put_super(struct super_block *sb)
 {
 	struct ncp_server *server = NCP_SBP(sb);
 
+	lock_kernel();
+
 	ncp_lock_server(server);
 	ncp_disconnect(server);
 	ncp_unlock_server(server);
@@ -769,6 +771,8 @@ static void ncp_put_super(struct super_block *sb)
 	vfree(server->packet);
 	sb->s_fs_info = NULL;
 	kfree(server);
+
+	unlock_kernel();
 }
 
 static int ncp_statfs(struct dentry *dentry, struct kstatfs *buf)
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 64a288ee046d..f01caec84463 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -154,7 +154,7 @@ out_err:
 	goto out;
 out_follow:
 	while (d_mountpoint(nd->path.dentry) &&
-	       follow_down(&nd->path.mnt, &nd->path.dentry))
+	       follow_down(&nd->path))
 		;
 	err = 0;
 	goto out;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index d2d67781c579..26127b69a275 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1813,6 +1813,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	if (data == NULL)
 		return -ENOMEM;
 
+	lock_kernel();
 	/* fill out struct with values from existing mount */
 	data->flags = nfss->flags;
 	data->rsize = nfss->rsize;
@@ -1837,6 +1838,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	error = nfs_compare_remount_data(nfss, data);
 out:
 	kfree(data);
+	unlock_kernel();
 	return error;
 }
 
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 5839b229cd0e..8b1f8efb4690 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -847,9 +847,8 @@ exp_get_fsid_key(svc_client *clp, int fsid)
 	return exp_find_key(clp, FSID_NUM, fsidv, NULL);
 }
 
-static svc_export *exp_get_by_name(svc_client *clp, struct vfsmount *mnt,
-				   struct dentry *dentry,
-				   struct cache_req *reqp)
+static svc_export *exp_get_by_name(svc_client *clp, const struct path *path,
+				     struct cache_req *reqp)
 {
 	struct svc_export *exp, key;
 	int err;
@@ -858,8 +857,7 @@ static svc_export *exp_get_by_name(svc_client *clp, struct vfsmount *mnt,
 		return ERR_PTR(-ENOENT);
 
 	key.ex_client = clp;
-	key.ex_path.mnt = mnt;
-	key.ex_path.dentry = dentry;
+	key.ex_path = *path;
 
 	exp = svc_export_lookup(&key);
 	if (exp == NULL)
@@ -873,24 +871,19 @@ static svc_export *exp_get_by_name(svc_client *clp, struct vfsmount *mnt,
 /*
  * Find the export entry for a given dentry.
  */
-static struct svc_export *exp_parent(svc_client *clp, struct vfsmount *mnt,
-				     struct dentry *dentry,
-				     struct cache_req *reqp)
+static struct svc_export *exp_parent(svc_client *clp, struct path *path)
 {
-	svc_export *exp;
+	struct dentry *saved = dget(path->dentry);
+	svc_export *exp = exp_get_by_name(clp, path, NULL);
 
-	dget(dentry);
-	exp = exp_get_by_name(clp, mnt, dentry, reqp);
-
-	while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(dentry)) {
-		struct dentry *parent;
-
-		parent = dget_parent(dentry);
-		dput(dentry);
-		dentry = parent;
-		exp = exp_get_by_name(clp, mnt, dentry, reqp);
+	while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(path->dentry)) {
+		struct dentry *parent = dget_parent(path->dentry);
+		dput(path->dentry);
+		path->dentry = parent;
+		exp = exp_get_by_name(clp, path, NULL);
 	}
-	dput(dentry);
+	dput(path->dentry);
+	path->dentry = saved;
 	return exp;
 }
 
@@ -1018,7 +1011,7 @@ exp_export(struct nfsctl_export *nxp)
 		goto out_put_clp;
 	err = -EINVAL;
 
-	exp = exp_get_by_name(clp, path.mnt, path.dentry, NULL);
+	exp = exp_get_by_name(clp, &path, NULL);
 
 	memset(&new, 0, sizeof(new));
 
@@ -1135,7 +1128,7 @@ exp_unexport(struct nfsctl_export *nxp)
 		goto out_domain;
 
 	err = -EINVAL;
-	exp = exp_get_by_name(dom, path.mnt, path.dentry, NULL);
+	exp = exp_get_by_name(dom, &path, NULL);
 	path_put(&path);
 	if (IS_ERR(exp))
 		goto out_domain;
@@ -1177,7 +1170,7 @@ exp_rootfh(svc_client *clp, char *name, struct knfsd_fh *f, int maxsize)
 	dprintk("nfsd: exp_rootfh(%s [%p] %s:%s/%ld)\n",
 		 name, path.dentry, clp->name,
 		 inode->i_sb->s_id, inode->i_ino);
-	exp = exp_parent(clp, path.mnt, path.dentry, NULL);
+	exp = exp_parent(clp, &path);
 	if (IS_ERR(exp)) {
 		err = PTR_ERR(exp);
 		goto out;
@@ -1207,7 +1200,7 @@ static struct svc_export *exp_find(struct auth_domain *clp, int fsid_type,
 	if (IS_ERR(ek))
 		return ERR_CAST(ek);
 
-	exp = exp_get_by_name(clp, ek->ek_path.mnt, ek->ek_path.dentry, reqp);
+	exp = exp_get_by_name(clp, &ek->ek_path, reqp);
 	cache_put(&ek->h, &svc_expkey_cache);
 
 	if (IS_ERR(exp))
@@ -1247,8 +1240,7 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
  * use exp_get_by_name() or exp_find().
  */
 struct svc_export *
-rqst_exp_get_by_name(struct svc_rqst *rqstp, struct vfsmount *mnt,
-		struct dentry *dentry)
+rqst_exp_get_by_name(struct svc_rqst *rqstp, struct path *path)
 {
 	struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT);
 
@@ -1256,8 +1248,7 @@ rqst_exp_get_by_name(struct svc_rqst *rqstp, struct vfsmount *mnt,
 		goto gss;
 
 	/* First try the auth_unix client: */
-	exp = exp_get_by_name(rqstp->rq_client, mnt, dentry,
-						&rqstp->rq_chandle);
+	exp = exp_get_by_name(rqstp->rq_client, path, &rqstp->rq_chandle);
 	if (PTR_ERR(exp) == -ENOENT)
 		goto gss;
 	if (IS_ERR(exp))
@@ -1269,8 +1260,7 @@ gss:
 	/* Otherwise, try falling back on gss client */
 	if (rqstp->rq_gssclient == NULL)
 		return exp;
-	gssexp = exp_get_by_name(rqstp->rq_gssclient, mnt, dentry,
-						&rqstp->rq_chandle);
+	gssexp = exp_get_by_name(rqstp->rq_gssclient, path, &rqstp->rq_chandle);
 	if (PTR_ERR(gssexp) == -ENOENT)
 		return exp;
 	if (!IS_ERR(exp))
@@ -1309,23 +1299,19 @@ gss:
 }
 
 struct svc_export *
-rqst_exp_parent(struct svc_rqst *rqstp, struct vfsmount *mnt,
-		struct dentry *dentry)
+rqst_exp_parent(struct svc_rqst *rqstp, struct path *path)
 {
-	struct svc_export *exp;
+	struct dentry *saved = dget(path->dentry);
+	struct svc_export *exp = rqst_exp_get_by_name(rqstp, path);
 
-	dget(dentry);
-	exp = rqst_exp_get_by_name(rqstp, mnt, dentry);
-
-	while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(dentry)) {
-		struct dentry *parent;
-
-		parent = dget_parent(dentry);
-		dput(dentry);
-		dentry = parent;
-		exp = rqst_exp_get_by_name(rqstp, mnt, dentry);
+	while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(path->dentry)) {
+		struct dentry *parent = dget_parent(path->dentry);
+		dput(path->dentry);
+		path->dentry = parent;
+		exp = rqst_exp_get_by_name(rqstp, path);
 	}
-	dput(dentry);
+	dput(path->dentry);
+	path->dentry = saved;
 	return exp;
 }
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index b660435978d2..99f835753596 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -55,6 +55,7 @@
 #include <linux/security.h>
 #endif /* CONFIG_NFSD_V4 */
 #include <linux/jhash.h>
+#include <linux/ima.h>
 
 #include <asm/uaccess.h>
 
@@ -100,36 +101,35 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 {
 	struct svc_export *exp = *expp, *exp2 = NULL;
 	struct dentry *dentry = *dpp;
-	struct vfsmount *mnt = mntget(exp->ex_path.mnt);
-	struct dentry *mounts = dget(dentry);
+	struct path path = {.mnt = mntget(exp->ex_path.mnt),
+			    .dentry = dget(dentry)};
 	int err = 0;
 
-	while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts));
+	while (d_mountpoint(path.dentry) && follow_down(&path))
+		;
 
-	exp2 = rqst_exp_get_by_name(rqstp, mnt, mounts);
+	exp2 = rqst_exp_get_by_name(rqstp, &path);
 	if (IS_ERR(exp2)) {
 		if (PTR_ERR(exp2) != -ENOENT)
 			err = PTR_ERR(exp2);
-		dput(mounts);
-		mntput(mnt);
+		path_put(&path);
 		goto out;
 	}
 	if ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
 		/* successfully crossed mount point */
 		/*
-		 * This is subtle: dentry is *not* under mnt at this point.
-		 * The only reason we are safe is that original mnt is pinned
-		 * down by exp, so we should dput before putting exp.
+		 * This is subtle: path.dentry is *not* on path.mnt
+		 * at this point.  The only reason we are safe is that
+		 * original mnt is pinned down by exp, so we should
+		 * put path *before* putting exp
 		 */
-		dput(dentry);
-		*dpp = mounts;
-		exp_put(exp);
+		*dpp = path.dentry;
+		path.dentry = dentry;
 		*expp = exp2;
-	} else {
-		exp_put(exp2);
-		dput(mounts);
+		exp2 = exp;
 	}
-	mntput(mnt);
+	path_put(&path);
+	exp_put(exp2);
 out:
 	return err;
 }
@@ -168,28 +168,29 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			/* checking mountpoint crossing is very different when stepping up */
 			struct svc_export *exp2 = NULL;
 			struct dentry *dp;
-			struct vfsmount *mnt = mntget(exp->ex_path.mnt);
-			dentry = dget(dparent);
-			while(dentry == mnt->mnt_root && follow_up(&mnt, &dentry))
-				;
-			dp = dget_parent(dentry);
-			dput(dentry);
-			dentry = dp;
+			struct path path = {.mnt = mntget(exp->ex_path.mnt),
+					    .dentry = dget(dparent)};
 
-			exp2 = rqst_exp_parent(rqstp, mnt, dentry);
+			while (path.dentry == path.mnt->mnt_root &&
+			       follow_up(&path))
+				;
+			dp = dget_parent(path.dentry);
+			dput(path.dentry);
+			path.dentry = dp;
+
+			exp2 = rqst_exp_parent(rqstp, &path);
 			if (PTR_ERR(exp2) == -ENOENT) {
-				dput(dentry);
 				dentry = dget(dparent);
 			} else if (IS_ERR(exp2)) {
 				host_err = PTR_ERR(exp2);
-				dput(dentry);
-				mntput(mnt);
+				path_put(&path);
 				goto out_nfserr;
 			} else {
+				dentry = dget(path.dentry);
 				exp_put(exp);
 				exp = exp2;
 			}
-			mntput(mnt);
+			path_put(&path);
 		}
 	} else {
 		fh_lock(fhp);
@@ -735,6 +736,8 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 			    flags, cred);
 	if (IS_ERR(*filp))
 		host_err = PTR_ERR(*filp);
+	else
+		ima_counts_get(*filp);
 out_nfserr:
 	err = nfserrno(host_err);
 out:
@@ -2024,6 +2027,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 					struct dentry *dentry, int acc)
 {
 	struct inode	*inode = dentry->d_inode;
+	struct path	path;
 	int		err;
 
 	if (acc == NFSD_MAY_NOP)
@@ -2096,7 +2100,17 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 	if (err == -EACCES && S_ISREG(inode->i_mode) &&
 	    acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE))
 		err = inode_permission(inode, MAY_EXEC);
+	if (err)
+		goto nfsd_out;
 
+	/* Do integrity (permission) checking now, but defer incrementing
+	 * IMA counts to the actual file open.
+	 */
+	path.mnt = exp->ex_path.mnt;
+	path.dentry = dentry;
+	err = ima_path_check(&path, acc & (MAY_READ | MAY_WRITE | MAY_EXEC),
+			     IMA_COUNT_LEAVE);
+nfsd_out:
 	return err? nfserrno(err) : 0;
 }
 
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index 300f1cdfa862..cadd36b14d07 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -864,11 +864,11 @@ int nilfs_cpfile_change_cpmode(struct inode *cpfile, __u64 cno, int mode)
 	case NILFS_CHECKPOINT:
 		/*
 		 * Check for protecting existing snapshot mounts:
-		 * bd_mount_sem is used to make this operation atomic and
+		 * ns_mount_mutex is used to make this operation atomic and
 		 * exclusive with a new mount job.  Though it doesn't cover
 		 * umount, it's enough for the purpose.
 		 */
-		down(&nilfs->ns_bdev->bd_mount_sem);
+		mutex_lock(&nilfs->ns_mount_mutex);
 		if (nilfs_checkpoint_is_mounted(nilfs, cno, 1)) {
 			/* Current implementation does not have to protect
 			   plain read-only mounts since they are exclusive
@@ -877,7 +877,7 @@ int nilfs_cpfile_change_cpmode(struct inode *cpfile, __u64 cno, int mode)
 			ret = -EBUSY;
 		} else
 			ret = nilfs_cpfile_clear_snapshot(cpfile, cno);
-		up(&nilfs->ns_bdev->bd_mount_sem);
+		mutex_unlock(&nilfs->ns_mount_mutex);
 		return ret;
 	case NILFS_SNAPSHOT:
 		return nilfs_cpfile_set_snapshot(cpfile, cno);
diff --git a/fs/nilfs2/sb.h b/fs/nilfs2/sb.h
index adccd4fc654e..0776ccc2504a 100644
--- a/fs/nilfs2/sb.h
+++ b/fs/nilfs2/sb.h
@@ -60,6 +60,7 @@ struct nilfs_sb_info {
 	struct super_block *s_super;	/* reverse pointer to super_block */
 	struct the_nilfs *s_nilfs;
 	struct list_head s_list;	/* list head for nilfs->ns_supers */
+	atomic_t s_count;		/* reference count */
 
 	/* Segment constructor */
 	struct list_head s_dirty_files;	/* dirty files list */
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 6989b03e97ab..1777a3467bd2 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -65,9 +65,8 @@ MODULE_DESCRIPTION("A New Implementation of the Log-structured Filesystem "
 		   "(NILFS)");
 MODULE_LICENSE("GPL");
 
+static void nilfs_write_super(struct super_block *sb);
 static int nilfs_remount(struct super_block *sb, int *flags, char *data);
-static int test_exclusive_mount(struct file_system_type *fs_type,
-				struct block_device *bdev, int flags);
 
 /**
  * nilfs_error() - report failure condition on a filesystem
@@ -315,6 +314,11 @@ static void nilfs_put_super(struct super_block *sb)
 	struct nilfs_sb_info *sbi = NILFS_SB(sb);
 	struct the_nilfs *nilfs = sbi->s_nilfs;
 
+	lock_kernel();
+
+	if (sb->s_dirt)
+		nilfs_write_super(sb);
+
 	nilfs_detach_segment_constructor(sbi);
 
 	if (!(sb->s_flags & MS_RDONLY)) {
@@ -323,12 +327,18 @@ static void nilfs_put_super(struct super_block *sb)
 		nilfs_commit_super(sbi, 1);
 		up_write(&nilfs->ns_sem);
 	}
+	down_write(&nilfs->ns_super_sem);
+	if (nilfs->ns_current == sbi)
+		nilfs->ns_current = NULL;
+	up_write(&nilfs->ns_super_sem);
 
 	nilfs_detach_checkpoint(sbi);
 	put_nilfs(sbi->s_nilfs);
 	sbi->s_super = NULL;
 	sb->s_fs_info = NULL;
-	kfree(sbi);
+	nilfs_put_sbinfo(sbi);
+
+	unlock_kernel();
 }
 
 /**
@@ -383,6 +393,8 @@ static int nilfs_sync_fs(struct super_block *sb, int wait)
 {
 	int err = 0;
 
+	nilfs_write_super(sb);
+
 	/* This function is called when super block should be written back */
 	if (wait)
 		err = nilfs_construct_segment(sb);
@@ -396,9 +408,9 @@ int nilfs_attach_checkpoint(struct nilfs_sb_info *sbi, __u64 cno)
 	struct buffer_head *bh_cp;
 	int err;
 
-	down_write(&nilfs->ns_sem);
+	down_write(&nilfs->ns_super_sem);
 	list_add(&sbi->s_list, &nilfs->ns_supers);
-	up_write(&nilfs->ns_sem);
+	up_write(&nilfs->ns_super_sem);
 
 	sbi->s_ifile = nilfs_mdt_new(
 		nilfs, sbi->s_super, NILFS_IFILE_INO, NILFS_IFILE_GFP);
@@ -436,9 +448,9 @@ int nilfs_attach_checkpoint(struct nilfs_sb_info *sbi, __u64 cno)
 	nilfs_mdt_destroy(sbi->s_ifile);
 	sbi->s_ifile = NULL;
 
-	down_write(&nilfs->ns_sem);
+	down_write(&nilfs->ns_super_sem);
 	list_del_init(&sbi->s_list);
-	up_write(&nilfs->ns_sem);
+	up_write(&nilfs->ns_super_sem);
 
 	return err;
 }
@@ -450,9 +462,9 @@ void nilfs_detach_checkpoint(struct nilfs_sb_info *sbi)
 	nilfs_mdt_clear(sbi->s_ifile);
 	nilfs_mdt_destroy(sbi->s_ifile);
 	sbi->s_ifile = NULL;
-	down_write(&nilfs->ns_sem);
+	down_write(&nilfs->ns_super_sem);
 	list_del_init(&sbi->s_list);
-	up_write(&nilfs->ns_sem);
+	up_write(&nilfs->ns_super_sem);
 }
 
 static int nilfs_mark_recovery_complete(struct nilfs_sb_info *sbi)
@@ -752,7 +764,7 @@ int nilfs_store_magic_and_option(struct super_block *sb,
  * @silent: silent mode flag
  * @nilfs: the_nilfs struct
  *
- * This function is called exclusively by bd_mount_mutex.
+ * This function is called exclusively by nilfs->ns_mount_mutex.
  * So, the recovery process is protected from other simultaneous mounts.
  */
 static int
@@ -773,6 +785,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent,
 	get_nilfs(nilfs);
 	sbi->s_nilfs = nilfs;
 	sbi->s_super = sb;
+	atomic_set(&sbi->s_count, 1);
 
 	err = init_nilfs(nilfs, sbi, (char *)data);
 	if (err)
@@ -870,6 +883,11 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent,
 		goto failed_root;
 	}
 
+	down_write(&nilfs->ns_super_sem);
+	if (!nilfs_test_opt(sbi, SNAPSHOT))
+		nilfs->ns_current = sbi;
+	up_write(&nilfs->ns_super_sem);
+
 	return 0;
 
  failed_root:
@@ -885,7 +903,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent,
  failed_sbi:
 	put_nilfs(nilfs);
 	sb->s_fs_info = NULL;
-	kfree(sbi);
+	nilfs_put_sbinfo(sbi);
 	return err;
 }
 
@@ -898,6 +916,9 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 	struct nilfs_mount_options old_opts;
 	int err;
 
+	lock_kernel();
+
+	down_write(&nilfs->ns_super_sem);
 	old_sb_flags = sb->s_flags;
 	old_opts.mount_opt = sbi->s_mount_opt;
 	old_opts.snapshot_cno = sbi->s_snapshot_cno;
@@ -945,14 +966,12 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 		 * store the current valid flag.  (It may have been changed
 		 * by fsck since we originally mounted the partition.)
 		 */
-		down(&sb->s_bdev->bd_mount_sem);
-		/* Check existing RW-mount */
-		if (test_exclusive_mount(sb->s_type, sb->s_bdev, 0)) {
+		if (nilfs->ns_current && nilfs->ns_current != sbi) {
 			printk(KERN_WARNING "NILFS (device %s): couldn't "
-			       "remount because a RW-mount exists.\n",
+			       "remount because an RW-mount exists.\n",
 			       sb->s_id);
 			err = -EBUSY;
-			goto rw_remount_failed;
+			goto restore_opts;
 		}
 		if (sbi->s_snapshot_cno != nilfs_last_cno(nilfs)) {
 			printk(KERN_WARNING "NILFS (device %s): couldn't "
@@ -960,7 +979,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 			       "the latest one.\n",
 			       sb->s_id);
 			err = -EINVAL;
-			goto rw_remount_failed;
+			goto restore_opts;
 		}
 		sb->s_flags &= ~MS_RDONLY;
 		nilfs_clear_opt(sbi, SNAPSHOT);
@@ -968,28 +987,31 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 
 		err = nilfs_attach_segment_constructor(sbi);
 		if (err)
-			goto rw_remount_failed;
+			goto restore_opts;
 
 		down_write(&nilfs->ns_sem);
 		nilfs_setup_super(sbi);
 		up_write(&nilfs->ns_sem);
 
-		up(&sb->s_bdev->bd_mount_sem);
+		nilfs->ns_current = sbi;
 	}
  out:
+	up_write(&nilfs->ns_super_sem);
+	unlock_kernel();
 	return 0;
 
- rw_remount_failed:
-	up(&sb->s_bdev->bd_mount_sem);
  restore_opts:
 	sb->s_flags = old_sb_flags;
 	sbi->s_mount_opt = old_opts.mount_opt;
 	sbi->s_snapshot_cno = old_opts.snapshot_cno;
+	up_write(&nilfs->ns_super_sem);
+	unlock_kernel();
 	return err;
 }
 
 struct nilfs_super_data {
 	struct block_device *bdev;
+	struct nilfs_sb_info *sbi;
 	__u64 cno;
 	int flags;
 };
@@ -1048,33 +1070,7 @@ static int nilfs_test_bdev_super(struct super_block *s, void *data)
 {
 	struct nilfs_super_data *sd = data;
 
-	return s->s_bdev == sd->bdev;
-}
-
-static int nilfs_test_bdev_super2(struct super_block *s, void *data)
-{
-	struct nilfs_super_data *sd = data;
-	int ret;
-
-	if (s->s_bdev != sd->bdev)
-		return 0;
-
-	if (!((s->s_flags | sd->flags) & MS_RDONLY))
-		return 1; /* Reuse an old R/W-mode super_block */
-
-	if (s->s_flags & sd->flags & MS_RDONLY) {
-		if (down_read_trylock(&s->s_umount)) {
-			ret = s->s_root &&
-				(sd->cno == NILFS_SB(s)->s_snapshot_cno);
-			up_read(&s->s_umount);
-			/*
-			 * This path is locked with sb_lock by sget().
-			 * So, drop_super() causes deadlock.
-			 */
-			return ret;
-		}
-	}
-	return 0;
+	return sd->sbi && s->s_fs_info == (void *)sd->sbi;
 }
 
 static int
@@ -1082,8 +1078,8 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags,
 	     const char *dev_name, void *data, struct vfsmount *mnt)
 {
 	struct nilfs_super_data sd;
-	struct super_block *s, *s2;
-	struct the_nilfs *nilfs = NULL;
+	struct super_block *s;
+	struct the_nilfs *nilfs;
 	int err, need_to_close = 1;
 
 	sd.bdev = open_bdev_exclusive(dev_name, flags, fs_type);
@@ -1095,7 +1091,6 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags,
 	 * much more information than normal filesystems to identify mount
 	 * instance.  For snapshot mounts, not only a mount type (ro-mount
 	 * or rw-mount) but also a checkpoint number is required.
-	 * The results are passed in sget() using nilfs_super_data.
 	 */
 	sd.cno = 0;
 	sd.flags = flags;
@@ -1104,64 +1099,59 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags,
 		goto failed;
 	}
 
-	/*
-	 * once the super is inserted into the list by sget, s_umount
-	 * will protect the lockfs code from trying to start a snapshot
-	 * while we are mounting
-	 */
-	down(&sd.bdev->bd_mount_sem);
-	if (!sd.cno &&
-	    (err = test_exclusive_mount(fs_type, sd.bdev, flags ^ MS_RDONLY))) {
-		err = (err < 0) ? : -EBUSY;
-		goto failed_unlock;
+	nilfs = find_or_create_nilfs(sd.bdev);
+	if (!nilfs) {
+		err = -ENOMEM;
+		goto failed;
+	}
+
+	mutex_lock(&nilfs->ns_mount_mutex);
+
+	if (!sd.cno) {
+		/*
+		 * Check if an exclusive mount exists or not.
+		 * Snapshot mounts coexist with a current mount
+		 * (i.e. rw-mount or ro-mount), whereas rw-mount and
+		 * ro-mount are mutually exclusive.
+		 */
+		down_read(&nilfs->ns_super_sem);
+		if (nilfs->ns_current &&
+		    ((nilfs->ns_current->s_super->s_flags ^ flags)
+		     & MS_RDONLY)) {
+			up_read(&nilfs->ns_super_sem);
+			err = -EBUSY;
+			goto failed_unlock;
+		}
+		up_read(&nilfs->ns_super_sem);
 	}
 
 	/*
-	 * Phase-1: search any existent instance and get the_nilfs
+	 * Find existing nilfs_sb_info struct
+	 */
+	sd.sbi = nilfs_find_sbinfo(nilfs, !(flags & MS_RDONLY), sd.cno);
+
+	if (!sd.cno)
+		/* trying to get the latest checkpoint.  */
+		sd.cno = nilfs_last_cno(nilfs);
+
+	/*
+	 * Get super block instance holding the nilfs_sb_info struct.
+	 * A new instance is allocated if no existing mount is present or
+	 * existing instance has been unmounted.
 	 */
 	s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, &sd);
-	if (IS_ERR(s))
-		goto error_s;
+	if (sd.sbi)
+		nilfs_put_sbinfo(sd.sbi);
 
-	if (!s->s_root) {
-		err = -ENOMEM;
-		nilfs = alloc_nilfs(sd.bdev);
-		if (!nilfs)
-			goto cancel_new;
-	} else {
-		struct nilfs_sb_info *sbi = NILFS_SB(s);
-
-		/*
-		 * s_umount protects super_block from unmount process;
-		 * It covers pointers of nilfs_sb_info and the_nilfs.
-		 */
-		nilfs = sbi->s_nilfs;
-		get_nilfs(nilfs);
-		up_write(&s->s_umount);
-
-		/*
-		 * Phase-2: search specified snapshot or R/W mode super_block
-		 */
-		if (!sd.cno)
-			/* trying to get the latest checkpoint.  */
-			sd.cno = nilfs_last_cno(nilfs);
-
-		s2 = sget(fs_type, nilfs_test_bdev_super2,
-			  nilfs_set_bdev_super, &sd);
-		deactivate_super(s);
-		/*
-		 * Although deactivate_super() invokes close_bdev_exclusive() at
-		 * kill_block_super().  Here, s is an existent mount; we need
-		 * one more close_bdev_exclusive() call.
-		 */
-		s = s2;
-		if (IS_ERR(s))
-			goto error_s;
+	if (IS_ERR(s)) {
+		err = PTR_ERR(s);
+		goto failed_unlock;
 	}
 
 	if (!s->s_root) {
 		char b[BDEVNAME_SIZE];
 
+		/* New superblock instance created */
 		s->s_flags = flags;
 		strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id));
 		sb_set_blocksize(s, block_size(sd.bdev));
@@ -1172,26 +1162,18 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags,
 
 		s->s_flags |= MS_ACTIVE;
 		need_to_close = 0;
-	} else if (!(s->s_flags & MS_RDONLY)) {
-		err = -EBUSY;
 	}
 
-	up(&sd.bdev->bd_mount_sem);
+	mutex_unlock(&nilfs->ns_mount_mutex);
 	put_nilfs(nilfs);
 	if (need_to_close)
 		close_bdev_exclusive(sd.bdev, flags);
 	simple_set_mnt(mnt, s);
 	return 0;
 
- error_s:
-	up(&sd.bdev->bd_mount_sem);
-	if (nilfs)
-		put_nilfs(nilfs);
-	close_bdev_exclusive(sd.bdev, flags);
-	return PTR_ERR(s);
-
  failed_unlock:
-	up(&sd.bdev->bd_mount_sem);
+	mutex_unlock(&nilfs->ns_mount_mutex);
+	put_nilfs(nilfs);
  failed:
 	close_bdev_exclusive(sd.bdev, flags);
 
@@ -1199,70 +1181,18 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags,
 
  cancel_new:
 	/* Abandoning the newly allocated superblock */
-	up(&sd.bdev->bd_mount_sem);
-	if (nilfs)
-		put_nilfs(nilfs);
+	mutex_unlock(&nilfs->ns_mount_mutex);
+	put_nilfs(nilfs);
 	up_write(&s->s_umount);
 	deactivate_super(s);
 	/*
 	 * deactivate_super() invokes close_bdev_exclusive().
 	 * We must finish all post-cleaning before this call;
-	 * put_nilfs() and unlocking bd_mount_sem need the block device.
+	 * put_nilfs() needs the block device.
 	 */
 	return err;
 }
 
-static int nilfs_test_bdev_super3(struct super_block *s, void *data)
-{
-	struct nilfs_super_data *sd = data;
-	int ret;
-
-	if (s->s_bdev != sd->bdev)
-		return 0;
-	if (down_read_trylock(&s->s_umount)) {
-		ret = (s->s_flags & MS_RDONLY) && s->s_root &&
-			nilfs_test_opt(NILFS_SB(s), SNAPSHOT);
-		up_read(&s->s_umount);
-		if (ret)
-			return 0; /* ignore snapshot mounts */
-	}
-	return !((sd->flags ^ s->s_flags) & MS_RDONLY);
-}
-
-static int __false_bdev_super(struct super_block *s, void *data)
-{
-#if 0 /* XXX: workaround for lock debug. This is not good idea */
-	up_write(&s->s_umount);
-#endif
-	return -EFAULT;
-}
-
-/**
- * test_exclusive_mount - check whether an exclusive RW/RO mount exists or not.
- * fs_type: filesystem type
- * bdev: block device
- * flag: 0 (check rw-mount) or MS_RDONLY (check ro-mount)
- * res: pointer to an integer to store result
- *
- * This function must be called within a section protected by bd_mount_mutex.
- */
-static int test_exclusive_mount(struct file_system_type *fs_type,
-				struct block_device *bdev, int flags)
-{
-	struct super_block *s;
-	struct nilfs_super_data sd = { .flags = flags, .bdev = bdev };
-
-	s = sget(fs_type, nilfs_test_bdev_super3, __false_bdev_super, &sd);
-	if (IS_ERR(s)) {
-		if (PTR_ERR(s) != -EFAULT)
-			return PTR_ERR(s);
-		return 0;  /* Not found */
-	}
-	up_write(&s->s_umount);
-	deactivate_super(s);
-	return 1;  /* Found */
-}
-
 struct file_system_type nilfs_fs_type = {
 	.owner    = THIS_MODULE,
 	.name     = "nilfs2",
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 7f65b3be4aa9..e4e5c78bcc93 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -35,6 +35,10 @@
 #include "seglist.h"
 #include "segbuf.h"
 
+
+static LIST_HEAD(nilfs_objects);
+static DEFINE_SPINLOCK(nilfs_lock);
+
 void nilfs_set_last_segment(struct the_nilfs *nilfs,
 			    sector_t start_blocknr, u64 seq, __u64 cno)
 {
@@ -55,7 +59,7 @@ void nilfs_set_last_segment(struct the_nilfs *nilfs,
  * Return Value: On success, pointer to the_nilfs is returned.
  * On error, NULL is returned.
  */
-struct the_nilfs *alloc_nilfs(struct block_device *bdev)
+static struct the_nilfs *alloc_nilfs(struct block_device *bdev)
 {
 	struct the_nilfs *nilfs;
 
@@ -68,7 +72,10 @@ struct the_nilfs *alloc_nilfs(struct block_device *bdev)
 	atomic_set(&nilfs->ns_writer_refcount, -1);
 	atomic_set(&nilfs->ns_ndirtyblks, 0);
 	init_rwsem(&nilfs->ns_sem);
+	init_rwsem(&nilfs->ns_super_sem);
+	mutex_init(&nilfs->ns_mount_mutex);
 	mutex_init(&nilfs->ns_writer_mutex);
+	INIT_LIST_HEAD(&nilfs->ns_list);
 	INIT_LIST_HEAD(&nilfs->ns_supers);
 	spin_lock_init(&nilfs->ns_last_segment_lock);
 	nilfs->ns_gc_inodes_h = NULL;
@@ -77,6 +84,45 @@ struct the_nilfs *alloc_nilfs(struct block_device *bdev)
 	return nilfs;
 }
 
+/**
+ * find_or_create_nilfs - find or create nilfs object
+ * @bdev: block device to which the_nilfs is related
+ *
+ * find_nilfs() looks up an existent nilfs object created on the
+ * device and gets the reference count of the object.  If no nilfs object
+ * is found on the device, a new nilfs object is allocated.
+ *
+ * Return Value: On success, pointer to the nilfs object is returned.
+ * On error, NULL is returned.
+ */
+struct the_nilfs *find_or_create_nilfs(struct block_device *bdev)
+{
+	struct the_nilfs *nilfs, *new = NULL;
+
+ retry:
+	spin_lock(&nilfs_lock);
+	list_for_each_entry(nilfs, &nilfs_objects, ns_list) {
+		if (nilfs->ns_bdev == bdev) {
+			get_nilfs(nilfs);
+			spin_unlock(&nilfs_lock);
+			if (new)
+				put_nilfs(new);
+			return nilfs; /* existing object */
+		}
+	}
+	if (new) {
+		list_add_tail(&new->ns_list, &nilfs_objects);
+		spin_unlock(&nilfs_lock);
+		return new; /* new object */
+	}
+	spin_unlock(&nilfs_lock);
+
+	new = alloc_nilfs(bdev);
+	if (new)
+		goto retry;
+	return NULL; /* insufficient memory */
+}
+
 /**
  * put_nilfs - release a reference to the_nilfs
  * @nilfs: the_nilfs structure to be released
@@ -86,13 +132,20 @@ struct the_nilfs *alloc_nilfs(struct block_device *bdev)
  */
 void put_nilfs(struct the_nilfs *nilfs)
 {
-	if (!atomic_dec_and_test(&nilfs->ns_count))
+	spin_lock(&nilfs_lock);
+	if (!atomic_dec_and_test(&nilfs->ns_count)) {
+		spin_unlock(&nilfs_lock);
 		return;
+	}
+	list_del_init(&nilfs->ns_list);
+	spin_unlock(&nilfs_lock);
+
 	/*
-	 * Increment of ns_count never occur below because the caller
+	 * Increment of ns_count never occurs below because the caller
 	 * of get_nilfs() holds at least one reference to the_nilfs.
 	 * Thus its exclusion control is not required here.
 	 */
+
 	might_sleep();
 	if (nilfs_loaded(nilfs)) {
 		nilfs_mdt_clear(nilfs->ns_sufile);
@@ -515,7 +568,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi, char *data)
 
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbp->s_log_block_size);
 	if (sb->s_blocksize != blocksize) {
-		int hw_blocksize = bdev_hardsect_size(sb->s_bdev);
+		int hw_blocksize = bdev_logical_block_size(sb->s_bdev);
 
 		if (blocksize < hw_blocksize) {
 			printk(KERN_ERR
@@ -613,13 +666,63 @@ int nilfs_near_disk_full(struct the_nilfs *nilfs)
 	return ret;
 }
 
+/**
+ * nilfs_find_sbinfo - find existing nilfs_sb_info structure
+ * @nilfs: nilfs object
+ * @rw_mount: mount type (non-zero value for read/write mount)
+ * @cno: checkpoint number (zero for read-only mount)
+ *
+ * nilfs_find_sbinfo() returns the nilfs_sb_info structure which
+ * @rw_mount and @cno (in case of snapshots) matched.  If no instance
+ * was found, NULL is returned.  Although the super block instance can
+ * be unmounted after this function returns, the nilfs_sb_info struct
+ * is kept on memory until nilfs_put_sbinfo() is called.
+ */
+struct nilfs_sb_info *nilfs_find_sbinfo(struct the_nilfs *nilfs,
+					int rw_mount, __u64 cno)
+{
+	struct nilfs_sb_info *sbi;
+
+	down_read(&nilfs->ns_super_sem);
+	/*
+	 * The SNAPSHOT flag and sb->s_flags are supposed to be
+	 * protected with nilfs->ns_super_sem.
+	 */
+	sbi = nilfs->ns_current;
+	if (rw_mount) {
+		if (sbi && !(sbi->s_super->s_flags & MS_RDONLY))
+			goto found; /* read/write mount */
+		else
+			goto out;
+	} else if (cno == 0) {
+		if (sbi && (sbi->s_super->s_flags & MS_RDONLY))
+			goto found; /* read-only mount */
+		else
+			goto out;
+	}
+
+	list_for_each_entry(sbi, &nilfs->ns_supers, s_list) {
+		if (nilfs_test_opt(sbi, SNAPSHOT) &&
+		    sbi->s_snapshot_cno == cno)
+			goto found; /* snapshot mount */
+	}
+ out:
+	up_read(&nilfs->ns_super_sem);
+	return NULL;
+
+ found:
+	atomic_inc(&sbi->s_count);
+	up_read(&nilfs->ns_super_sem);
+	return sbi;
+}
+
 int nilfs_checkpoint_is_mounted(struct the_nilfs *nilfs, __u64 cno,
 				int snapshot_mount)
 {
 	struct nilfs_sb_info *sbi;
 	int ret = 0;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_super_sem);
 	if (cno == 0 || cno > nilfs->ns_cno)
 		goto out_unlock;
 
@@ -636,6 +739,6 @@ int nilfs_checkpoint_is_mounted(struct the_nilfs *nilfs, __u64 cno,
 		ret++;
 
  out_unlock:
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_super_sem);
 	return ret;
 }
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 30fe58778d05..e8adbffc626f 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -43,12 +43,16 @@ enum {
  * struct the_nilfs - struct to supervise multiple nilfs mount points
  * @ns_flags: flags
  * @ns_count: reference count
+ * @ns_list: list head for nilfs_list
  * @ns_bdev: block device
  * @ns_bdi: backing dev info
  * @ns_writer: back pointer to writable nilfs_sb_info
  * @ns_sem: semaphore for shared states
+ * @ns_super_sem: semaphore for global operations across super block instances
+ * @ns_mount_mutex: mutex protecting mount process of nilfs
  * @ns_writer_mutex: mutex protecting ns_writer attach/detach
  * @ns_writer_refcount: number of referrers on ns_writer
+ * @ns_current: back pointer to current mount
  * @ns_sbh: buffer heads of on-disk super blocks
  * @ns_sbp: pointers to super block data
  * @ns_sbwtime: previous write time of super blocks
@@ -88,14 +92,23 @@ enum {
 struct the_nilfs {
 	unsigned long		ns_flags;
 	atomic_t		ns_count;
+	struct list_head	ns_list;
 
 	struct block_device    *ns_bdev;
 	struct backing_dev_info *ns_bdi;
 	struct nilfs_sb_info   *ns_writer;
 	struct rw_semaphore	ns_sem;
+	struct rw_semaphore	ns_super_sem;
+	struct mutex		ns_mount_mutex;
 	struct mutex		ns_writer_mutex;
 	atomic_t		ns_writer_refcount;
 
+	/*
+	 * components protected by ns_super_sem
+	 */
+	struct nilfs_sb_info   *ns_current;
+	struct list_head	ns_supers;
+
 	/*
 	 * used for
 	 * - loading the latest checkpoint exclusively.
@@ -108,7 +121,6 @@ struct the_nilfs {
 	time_t			ns_sbwtime[2];
 	unsigned		ns_sbsize;
 	unsigned		ns_mount_state;
-	struct list_head	ns_supers;
 
 	/*
 	 * Following fields are dedicated to a writable FS-instance.
@@ -191,11 +203,12 @@ THE_NILFS_FNS(DISCONTINUED, discontinued)
 #define NILFS_ALTSB_FREQ	60  /* spare superblock */
 
 void nilfs_set_last_segment(struct the_nilfs *, sector_t, u64, __u64);
-struct the_nilfs *alloc_nilfs(struct block_device *);
+struct the_nilfs *find_or_create_nilfs(struct block_device *);
 void put_nilfs(struct the_nilfs *);
 int init_nilfs(struct the_nilfs *, struct nilfs_sb_info *, char *);
 int load_nilfs(struct the_nilfs *, struct nilfs_sb_info *);
 int nilfs_count_free_blocks(struct the_nilfs *, sector_t *);
+struct nilfs_sb_info *nilfs_find_sbinfo(struct the_nilfs *, int, __u64);
 int nilfs_checkpoint_is_mounted(struct the_nilfs *, __u64, int);
 int nilfs_near_disk_full(struct the_nilfs *);
 void nilfs_fall_back_super_block(struct the_nilfs *);
@@ -238,6 +251,12 @@ nilfs_detach_writer(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
 	mutex_unlock(&nilfs->ns_writer_mutex);
 }
 
+static inline void nilfs_put_sbinfo(struct nilfs_sb_info *sbi)
+{
+	if (!atomic_dec_and_test(&sbi->s_count))
+		kfree(sbi);
+}
+
 static inline void
 nilfs_get_segment_range(struct the_nilfs *nilfs, __u64 segnum,
 			sector_t *seg_start, sector_t *seg_end)
diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig
index 50914d7303c6..31dac7e3b0f1 100644
--- a/fs/notify/Kconfig
+++ b/fs/notify/Kconfig
@@ -1,2 +1,15 @@
+config FSNOTIFY
+	bool "Filesystem notification backend"
+	default y
+	---help---
+	   fsnotify is a backend for filesystem notification.  fsnotify does
+	   not provide any userspace interface but does provide the basis
+	   needed for other notification schemes such as dnotify, inotify,
+	   and fanotify.
+
+	   Say Y here to enable fsnotify suport.
+
+	   If unsure, say Y.
+
 source "fs/notify/dnotify/Kconfig"
 source "fs/notify/inotify/Kconfig"
diff --git a/fs/notify/Makefile b/fs/notify/Makefile
index 5a95b6010ce7..0922cc826c46 100644
--- a/fs/notify/Makefile
+++ b/fs/notify/Makefile
@@ -1,2 +1,4 @@
+obj-$(CONFIG_FSNOTIFY)		+= fsnotify.o notification.o group.o inode_mark.o
+
 obj-y			+= dnotify/
 obj-y			+= inotify/
diff --git a/fs/notify/dnotify/Kconfig b/fs/notify/dnotify/Kconfig
index 26adf5dfa646..904ff8d5405a 100644
--- a/fs/notify/dnotify/Kconfig
+++ b/fs/notify/dnotify/Kconfig
@@ -1,5 +1,6 @@
 config DNOTIFY
 	bool "Dnotify support"
+	depends on FSNOTIFY
 	default y
 	help
 	  Dnotify is a directory-based per-fd file change notification system
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index b0aa2cde80bd..828a889be909 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -3,6 +3,9 @@
  *
  * Copyright (C) 2000,2001,2002 Stephen Rothwell
  *
+ * Copyright (C) 2009 Eric Paris <Red Hat Inc>
+ * dnotify was largly rewritten to use the new fsnotify infrastructure
+ *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
  * Free Software Foundation; either version 2, or (at your option) any
@@ -21,170 +24,417 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/fdtable.h>
+#include <linux/fsnotify_backend.h>
 
 int dir_notify_enable __read_mostly = 1;
 
-static struct kmem_cache *dn_cache __read_mostly;
+static struct kmem_cache *dnotify_struct_cache __read_mostly;
+static struct kmem_cache *dnotify_mark_entry_cache __read_mostly;
+static struct fsnotify_group *dnotify_group __read_mostly;
+static DEFINE_MUTEX(dnotify_mark_mutex);
 
-static void redo_inode_mask(struct inode *inode)
-{
-	unsigned long new_mask;
+/*
+ * dnotify will attach one of these to each inode (i_fsnotify_mark_entries) which
+ * is being watched by dnotify.  If multiple userspace applications are watching
+ * the same directory with dnotify their information is chained in dn
+ */
+struct dnotify_mark_entry {
+	struct fsnotify_mark_entry fsn_entry;
 	struct dnotify_struct *dn;
+};
 
+/*
+ * When a process starts or stops watching an inode the set of events which
+ * dnotify cares about for that inode may change.  This function runs the
+ * list of everything receiving dnotify events about this directory and calculates
+ * the set of all those events.  After it updates what dnotify is interested in
+ * it calls the fsnotify function so it can update the set of all events relevant
+ * to this inode.
+ */
+static void dnotify_recalc_inode_mask(struct fsnotify_mark_entry *entry)
+{
+	__u32 new_mask, old_mask;
+	struct dnotify_struct *dn;
+	struct dnotify_mark_entry *dnentry  = container_of(entry,
+							   struct dnotify_mark_entry,
+							   fsn_entry);
+
+	assert_spin_locked(&entry->lock);
+
+	old_mask = entry->mask;
 	new_mask = 0;
-	for (dn = inode->i_dnotify; dn != NULL; dn = dn->dn_next)
-		new_mask |= dn->dn_mask & ~DN_MULTISHOT;
-	inode->i_dnotify_mask = new_mask;
-}
+	for (dn = dnentry->dn; dn != NULL; dn = dn->dn_next)
+		new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT);
+	entry->mask = new_mask;
 
-void dnotify_flush(struct file *filp, fl_owner_t id)
-{
-	struct dnotify_struct *dn;
-	struct dnotify_struct **prev;
-	struct inode *inode;
-
-	inode = filp->f_path.dentry->d_inode;
-	if (!S_ISDIR(inode->i_mode))
+	if (old_mask == new_mask)
 		return;
-	spin_lock(&inode->i_lock);
-	prev = &inode->i_dnotify;
-	while ((dn = *prev) != NULL) {
-		if ((dn->dn_owner == id) && (dn->dn_filp == filp)) {
-			*prev = dn->dn_next;
-			redo_inode_mask(inode);
-			kmem_cache_free(dn_cache, dn);
-			break;
-		}
-		prev = &dn->dn_next;
-	}
-	spin_unlock(&inode->i_lock);
+
+	if (entry->inode)
+		fsnotify_recalc_inode_mask(entry->inode);
 }
 
-int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
+/*
+ * Mains fsnotify call where events are delivered to dnotify.
+ * Find the dnotify mark on the relevant inode, run the list of dnotify structs
+ * on that mark and determine which of them has expressed interest in receiving
+ * events of this type.  When found send the correct process and signal and
+ * destroy the dnotify struct if it was not registered to receive multiple
+ * events.
+ */
+static int dnotify_handle_event(struct fsnotify_group *group,
+				struct fsnotify_event *event)
 {
+	struct fsnotify_mark_entry *entry = NULL;
+	struct dnotify_mark_entry *dnentry;
+	struct inode *to_tell;
 	struct dnotify_struct *dn;
-	struct dnotify_struct *odn;
 	struct dnotify_struct **prev;
-	struct inode *inode;
-	fl_owner_t id = current->files;
-	struct file *f;
-	int error = 0;
+	struct fown_struct *fown;
 
-	if ((arg & ~DN_MULTISHOT) == 0) {
-		dnotify_flush(filp, id);
+	to_tell = event->to_tell;
+
+	spin_lock(&to_tell->i_lock);
+	entry = fsnotify_find_mark_entry(group, to_tell);
+	spin_unlock(&to_tell->i_lock);
+
+	/* unlikely since we alreay passed dnotify_should_send_event() */
+	if (unlikely(!entry))
 		return 0;
-	}
-	if (!dir_notify_enable)
-		return -EINVAL;
-	inode = filp->f_path.dentry->d_inode;
-	if (!S_ISDIR(inode->i_mode))
-		return -ENOTDIR;
-	dn = kmem_cache_alloc(dn_cache, GFP_KERNEL);
-	if (dn == NULL)
-		return -ENOMEM;
-	spin_lock(&inode->i_lock);
-	prev = &inode->i_dnotify;
-	while ((odn = *prev) != NULL) {
-		if ((odn->dn_owner == id) && (odn->dn_filp == filp)) {
-			odn->dn_fd = fd;
-			odn->dn_mask |= arg;
-			inode->i_dnotify_mask |= arg & ~DN_MULTISHOT;
-			goto out_free;
-		}
-		prev = &odn->dn_next;
-	}
+	dnentry = container_of(entry, struct dnotify_mark_entry, fsn_entry);
 
-	rcu_read_lock();
-	f = fcheck(fd);
-	rcu_read_unlock();
-	/* we'd lost the race with close(), sod off silently */
-	/* note that inode->i_lock prevents reordering problems
-	 * between accesses to descriptor table and ->i_dnotify */
-	if (f != filp)
-		goto out_free;
-
-	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
-	if (error)
-		goto out_free;
-
-	dn->dn_mask = arg;
-	dn->dn_fd = fd;
-	dn->dn_filp = filp;
-	dn->dn_owner = id;
-	inode->i_dnotify_mask |= arg & ~DN_MULTISHOT;
-	dn->dn_next = inode->i_dnotify;
-	inode->i_dnotify = dn;
-	spin_unlock(&inode->i_lock);
-	return 0;
-
-out_free:
-	spin_unlock(&inode->i_lock);
-	kmem_cache_free(dn_cache, dn);
-	return error;
-}
-
-void __inode_dir_notify(struct inode *inode, unsigned long event)
-{
-	struct dnotify_struct *	dn;
-	struct dnotify_struct **prev;
-	struct fown_struct *	fown;
-	int			changed = 0;
-
-	spin_lock(&inode->i_lock);
-	prev = &inode->i_dnotify;
+	spin_lock(&entry->lock);
+	prev = &dnentry->dn;
 	while ((dn = *prev) != NULL) {
-		if ((dn->dn_mask & event) == 0) {
+		if ((dn->dn_mask & event->mask) == 0) {
 			prev = &dn->dn_next;
 			continue;
 		}
 		fown = &dn->dn_filp->f_owner;
 		send_sigio(fown, dn->dn_fd, POLL_MSG);
-		if (dn->dn_mask & DN_MULTISHOT)
+		if (dn->dn_mask & FS_DN_MULTISHOT)
 			prev = &dn->dn_next;
 		else {
 			*prev = dn->dn_next;
-			changed = 1;
-			kmem_cache_free(dn_cache, dn);
+			kmem_cache_free(dnotify_struct_cache, dn);
+			dnotify_recalc_inode_mask(entry);
 		}
 	}
-	if (changed)
-		redo_inode_mask(inode);
-	spin_unlock(&inode->i_lock);
-}
 
-EXPORT_SYMBOL(__inode_dir_notify);
+	spin_unlock(&entry->lock);
+	fsnotify_put_mark(entry);
+
+	return 0;
+}
 
 /*
- * This is hopelessly wrong, but unfixable without API changes.  At
- * least it doesn't oops the kernel...
- *
- * To safely access ->d_parent we need to keep d_move away from it.  Use the
- * dentry's d_lock for this.
+ * Given an inode and mask determine if dnotify would be interested in sending
+ * userspace notification for that pair.
  */
-void dnotify_parent(struct dentry *dentry, unsigned long event)
+static bool dnotify_should_send_event(struct fsnotify_group *group,
+				      struct inode *inode, __u32 mask)
 {
-	struct dentry *parent;
+	struct fsnotify_mark_entry *entry;
+	bool send;
 
+	/* !dir_notify_enable should never get here, don't waste time checking
 	if (!dir_notify_enable)
+		return 0; */
+
+	/* not a dir, dnotify doesn't care */
+	if (!S_ISDIR(inode->i_mode))
+		return false;
+
+	spin_lock(&inode->i_lock);
+	entry = fsnotify_find_mark_entry(group, inode);
+	spin_unlock(&inode->i_lock);
+
+	/* no mark means no dnotify watch */
+	if (!entry)
+		return false;
+
+	mask = (mask & ~FS_EVENT_ON_CHILD);
+	send = (mask & entry->mask);
+
+	fsnotify_put_mark(entry); /* matches fsnotify_find_mark_entry */
+
+	return send;
+}
+
+static void dnotify_free_mark(struct fsnotify_mark_entry *entry)
+{
+	struct dnotify_mark_entry *dnentry = container_of(entry,
+							  struct dnotify_mark_entry,
+							  fsn_entry);
+
+	BUG_ON(dnentry->dn);
+
+	kmem_cache_free(dnotify_mark_entry_cache, dnentry);
+}
+
+static struct fsnotify_ops dnotify_fsnotify_ops = {
+	.handle_event = dnotify_handle_event,
+	.should_send_event = dnotify_should_send_event,
+	.free_group_priv = NULL,
+	.freeing_mark = NULL,
+	.free_event_priv = NULL,
+};
+
+/*
+ * Called every time a file is closed.  Looks first for a dnotify mark on the
+ * inode.  If one is found run all of the ->dn entries attached to that
+ * mark for one relevant to this process closing the file and remove that
+ * dnotify_struct.  If that was the last dnotify_struct also remove the
+ * fsnotify_mark_entry.
+ */
+void dnotify_flush(struct file *filp, fl_owner_t id)
+{
+	struct fsnotify_mark_entry *entry;
+	struct dnotify_mark_entry *dnentry;
+	struct dnotify_struct *dn;
+	struct dnotify_struct **prev;
+	struct inode *inode;
+
+	inode = filp->f_path.dentry->d_inode;
+	if (!S_ISDIR(inode->i_mode))
 		return;
 
-	spin_lock(&dentry->d_lock);
-	parent = dentry->d_parent;
-	if (parent->d_inode->i_dnotify_mask & event) {
-		dget(parent);
-		spin_unlock(&dentry->d_lock);
-		__inode_dir_notify(parent->d_inode, event);
-		dput(parent);
-	} else {
-		spin_unlock(&dentry->d_lock);
+	spin_lock(&inode->i_lock);
+	entry = fsnotify_find_mark_entry(dnotify_group, inode);
+	spin_unlock(&inode->i_lock);
+	if (!entry)
+		return;
+	dnentry = container_of(entry, struct dnotify_mark_entry, fsn_entry);
+
+	mutex_lock(&dnotify_mark_mutex);
+
+	spin_lock(&entry->lock);
+	prev = &dnentry->dn;
+	while ((dn = *prev) != NULL) {
+		if ((dn->dn_owner == id) && (dn->dn_filp == filp)) {
+			*prev = dn->dn_next;
+			kmem_cache_free(dnotify_struct_cache, dn);
+			dnotify_recalc_inode_mask(entry);
+			break;
+		}
+		prev = &dn->dn_next;
 	}
+
+	spin_unlock(&entry->lock);
+
+	/* nothing else could have found us thanks to the dnotify_mark_mutex */
+	if (dnentry->dn == NULL)
+		fsnotify_destroy_mark_by_entry(entry);
+
+	fsnotify_recalc_group_mask(dnotify_group);
+
+	mutex_unlock(&dnotify_mark_mutex);
+
+	fsnotify_put_mark(entry);
+}
+
+/* this conversion is done only at watch creation */
+static __u32 convert_arg(unsigned long arg)
+{
+	__u32 new_mask = FS_EVENT_ON_CHILD;
+
+	if (arg & DN_MULTISHOT)
+		new_mask |= FS_DN_MULTISHOT;
+	if (arg & DN_DELETE)
+		new_mask |= (FS_DELETE | FS_MOVED_FROM);
+	if (arg & DN_MODIFY)
+		new_mask |= FS_MODIFY;
+	if (arg & DN_ACCESS)
+		new_mask |= FS_ACCESS;
+	if (arg & DN_ATTRIB)
+		new_mask |= FS_ATTRIB;
+	if (arg & DN_RENAME)
+		new_mask |= FS_DN_RENAME;
+	if (arg & DN_CREATE)
+		new_mask |= (FS_CREATE | FS_MOVED_TO);
+
+	return new_mask;
+}
+
+/*
+ * If multiple processes watch the same inode with dnotify there is only one
+ * dnotify mark in inode->i_fsnotify_mark_entries but we chain a dnotify_struct
+ * onto that mark.  This function either attaches the new dnotify_struct onto
+ * that list, or it |= the mask onto an existing dnofiy_struct.
+ */
+static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark_entry *dnentry,
+		     fl_owner_t id, int fd, struct file *filp, __u32 mask)
+{
+	struct dnotify_struct *odn;
+
+	odn = dnentry->dn;
+	while (odn != NULL) {
+		/* adding more events to existing dnofiy_struct? */
+		if ((odn->dn_owner == id) && (odn->dn_filp == filp)) {
+			odn->dn_fd = fd;
+			odn->dn_mask |= mask;
+			return -EEXIST;
+		}
+		odn = odn->dn_next;
+	}
+
+	dn->dn_mask = mask;
+	dn->dn_fd = fd;
+	dn->dn_filp = filp;
+	dn->dn_owner = id;
+	dn->dn_next = dnentry->dn;
+	dnentry->dn = dn;
+
+	return 0;
+}
+
+/*
+ * When a process calls fcntl to attach a dnotify watch to a directory it ends
+ * up here.  Allocate both a mark for fsnotify to add and a dnotify_struct to be
+ * attached to the fsnotify_mark.
+ */
+int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
+{
+	struct dnotify_mark_entry *new_dnentry, *dnentry;
+	struct fsnotify_mark_entry *new_entry, *entry;
+	struct dnotify_struct *dn;
+	struct inode *inode;
+	fl_owner_t id = current->files;
+	struct file *f;
+	int destroy = 0, error = 0;
+	__u32 mask;
+
+	/* we use these to tell if we need to kfree */
+	new_entry = NULL;
+	dn = NULL;
+
+	if (!dir_notify_enable) {
+		error = -EINVAL;
+		goto out_err;
+	}
+
+	/* a 0 mask means we are explicitly removing the watch */
+	if ((arg & ~DN_MULTISHOT) == 0) {
+		dnotify_flush(filp, id);
+		error = 0;
+		goto out_err;
+	}
+
+	/* dnotify only works on directories */
+	inode = filp->f_path.dentry->d_inode;
+	if (!S_ISDIR(inode->i_mode)) {
+		error = -ENOTDIR;
+		goto out_err;
+	}
+
+	/* expect most fcntl to add new rather than augment old */
+	dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL);
+	if (!dn) {
+		error = -ENOMEM;
+		goto out_err;
+	}
+
+	/* new fsnotify mark, we expect most fcntl calls to add a new mark */
+	new_dnentry = kmem_cache_alloc(dnotify_mark_entry_cache, GFP_KERNEL);
+	if (!new_dnentry) {
+		error = -ENOMEM;
+		goto out_err;
+	}
+
+	/* convert the userspace DN_* "arg" to the internal FS_* defines in fsnotify */
+	mask = convert_arg(arg);
+
+	/* set up the new_entry and new_dnentry */
+	new_entry = &new_dnentry->fsn_entry;
+	fsnotify_init_mark(new_entry, dnotify_free_mark);
+	new_entry->mask = mask;
+	new_dnentry->dn = NULL;
+
+	/* this is needed to prevent the fcntl/close race described below */
+	mutex_lock(&dnotify_mark_mutex);
+
+	/* add the new_entry or find an old one. */
+	spin_lock(&inode->i_lock);
+	entry = fsnotify_find_mark_entry(dnotify_group, inode);
+	spin_unlock(&inode->i_lock);
+	if (entry) {
+		dnentry = container_of(entry, struct dnotify_mark_entry, fsn_entry);
+		spin_lock(&entry->lock);
+	} else {
+		fsnotify_add_mark(new_entry, dnotify_group, inode);
+		spin_lock(&new_entry->lock);
+		entry = new_entry;
+		dnentry = new_dnentry;
+		/* we used new_entry, so don't free it */
+		new_entry = NULL;
+	}
+
+	rcu_read_lock();
+	f = fcheck(fd);
+	rcu_read_unlock();
+
+	/* if (f != filp) means that we lost a race and another task/thread
+	 * actually closed the fd we are still playing with before we grabbed
+	 * the dnotify_mark_mutex and entry->lock.  Since closing the fd is the
+	 * only time we clean up the mark entries we need to get our mark off
+	 * the list. */
+	if (f != filp) {
+		/* if we added ourselves, shoot ourselves, it's possible that
+		 * the flush actually did shoot this entry.  That's fine too
+		 * since multiple calls to destroy_mark is perfectly safe, if
+		 * we found a dnentry already attached to the inode, just sod
+		 * off silently as the flush at close time dealt with it.
+		 */
+		if (dnentry == new_dnentry)
+			destroy = 1;
+		goto out;
+	}
+
+	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
+	if (error) {
+		/* if we added, we must shoot */
+		if (dnentry == new_dnentry)
+			destroy = 1;
+		goto out;
+	}
+
+	error = attach_dn(dn, dnentry, id, fd, filp, mask);
+	/* !error means that we attached the dn to the dnentry, so don't free it */
+	if (!error)
+		dn = NULL;
+	/* -EEXIST means that we didn't add this new dn and used an old one.
+	 * that isn't an error (and the unused dn should be freed) */
+	else if (error == -EEXIST)
+		error = 0;
+
+	dnotify_recalc_inode_mask(entry);
+out:
+	spin_unlock(&entry->lock);
+
+	if (destroy)
+		fsnotify_destroy_mark_by_entry(entry);
+
+	fsnotify_recalc_group_mask(dnotify_group);
+
+	mutex_unlock(&dnotify_mark_mutex);
+	fsnotify_put_mark(entry);
+out_err:
+	if (new_entry)
+		fsnotify_put_mark(new_entry);
+	if (dn)
+		kmem_cache_free(dnotify_struct_cache, dn);
+	return error;
 }
-EXPORT_SYMBOL_GPL(dnotify_parent);
 
 static int __init dnotify_init(void)
 {
-	dn_cache = kmem_cache_create("dnotify_cache",
-		sizeof(struct dnotify_struct), 0, SLAB_PANIC, NULL);
+	dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC);
+	dnotify_mark_entry_cache = KMEM_CACHE(dnotify_mark_entry, SLAB_PANIC);
+
+	dnotify_group = fsnotify_obtain_group(DNOTIFY_GROUP_NUM,
+					      0, &dnotify_fsnotify_ops);
+	if (IS_ERR(dnotify_group))
+		panic("unable to allocate fsnotify group for dnotify\n");
 	return 0;
 }
 
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
new file mode 100644
index 000000000000..ec2f7bd76818
--- /dev/null
+++ b/fs/notify/fsnotify.c
@@ -0,0 +1,186 @@
+/*
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2, or (at your option)
+ *  any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; see the file COPYING.  If not, write to
+ *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/dcache.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/srcu.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+/*
+ * Clear all of the marks on an inode when it is being evicted from core
+ */
+void __fsnotify_inode_delete(struct inode *inode)
+{
+	fsnotify_clear_marks_by_inode(inode);
+}
+EXPORT_SYMBOL_GPL(__fsnotify_inode_delete);
+
+/*
+ * Given an inode, first check if we care what happens to our children.  Inotify
+ * and dnotify both tell their parents about events.  If we care about any event
+ * on a child we run all of our children and set a dentry flag saying that the
+ * parent cares.  Thus when an event happens on a child it can quickly tell if
+ * if there is a need to find a parent and send the event to the parent.
+ */
+void __fsnotify_update_child_dentry_flags(struct inode *inode)
+{
+	struct dentry *alias;
+	int watched;
+
+	if (!S_ISDIR(inode->i_mode))
+		return;
+
+	/* determine if the children should tell inode about their events */
+	watched = fsnotify_inode_watches_children(inode);
+
+	spin_lock(&dcache_lock);
+	/* run all of the dentries associated with this inode.  Since this is a
+	 * directory, there damn well better only be one item on this list */
+	list_for_each_entry(alias, &inode->i_dentry, d_alias) {
+		struct dentry *child;
+
+		/* run all of the children of the original inode and fix their
+		 * d_flags to indicate parental interest (their parent is the
+		 * original inode) */
+		list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) {
+			if (!child->d_inode)
+				continue;
+
+			spin_lock(&child->d_lock);
+			if (watched)
+				child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
+			else
+				child->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+			spin_unlock(&child->d_lock);
+		}
+	}
+	spin_unlock(&dcache_lock);
+}
+
+/* Notify this dentry's parent about a child's events. */
+void __fsnotify_parent(struct dentry *dentry, __u32 mask)
+{
+	struct dentry *parent;
+	struct inode *p_inode;
+	bool send = false;
+	bool should_update_children = false;
+
+	if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
+		return;
+
+	spin_lock(&dentry->d_lock);
+	parent = dentry->d_parent;
+	p_inode = parent->d_inode;
+
+	if (fsnotify_inode_watches_children(p_inode)) {
+		if (p_inode->i_fsnotify_mask & mask) {
+			dget(parent);
+			send = true;
+		}
+	} else {
+		/*
+		 * The parent doesn't care about events on it's children but
+		 * at least one child thought it did.  We need to run all the
+		 * children and update their d_flags to let them know p_inode
+		 * doesn't care about them any more.
+		 */
+		dget(parent);
+		should_update_children = true;
+	}
+
+	spin_unlock(&dentry->d_lock);
+
+	if (send) {
+		/* we are notifying a parent so come up with the new mask which
+		 * specifies these are events which came from a child. */
+		mask |= FS_EVENT_ON_CHILD;
+
+		fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
+			 dentry->d_name.name, 0);
+		dput(parent);
+	}
+
+	if (unlikely(should_update_children)) {
+		__fsnotify_update_child_dentry_flags(p_inode);
+		dput(parent);
+	}
+}
+EXPORT_SYMBOL_GPL(__fsnotify_parent);
+
+/*
+ * This is the main call to fsnotify.  The VFS calls into hook specific functions
+ * in linux/fsnotify.h.  Those functions then in turn call here.  Here will call
+ * out to all of the registered fsnotify_group.  Those groups can then use the
+ * notification event in whatever means they feel necessary.
+ */
+void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, const char *file_name, u32 cookie)
+{
+	struct fsnotify_group *group;
+	struct fsnotify_event *event = NULL;
+	int idx;
+	/* global tests shouldn't care about events on child only the specific event */
+	__u32 test_mask = (mask & ~FS_EVENT_ON_CHILD);
+
+	if (list_empty(&fsnotify_groups))
+		return;
+
+	if (!(test_mask & fsnotify_mask))
+		return;
+
+	if (!(test_mask & to_tell->i_fsnotify_mask))
+		return;
+	/*
+	 * SRCU!!  the groups list is very very much read only and the path is
+	 * very hot.  The VAST majority of events are not going to need to do
+	 * anything other than walk the list so it's crazy to pre-allocate.
+	 */
+	idx = srcu_read_lock(&fsnotify_grp_srcu);
+	list_for_each_entry_rcu(group, &fsnotify_groups, group_list) {
+		if (test_mask & group->mask) {
+			if (!group->ops->should_send_event(group, to_tell, mask))
+				continue;
+			if (!event) {
+				event = fsnotify_create_event(to_tell, mask, data, data_is, file_name, cookie);
+				/* shit, we OOM'd and now we can't tell, maybe
+				 * someday someone else will want to do something
+				 * here */
+				if (!event)
+					break;
+			}
+			group->ops->handle_event(group, event);
+		}
+	}
+	srcu_read_unlock(&fsnotify_grp_srcu, idx);
+	/*
+	 * fsnotify_create_event() took a reference so the event can't be cleaned
+	 * up while we are still trying to add it to lists, drop that one.
+	 */
+	if (event)
+		fsnotify_put_event(event);
+}
+EXPORT_SYMBOL_GPL(fsnotify);
+
+static __init int fsnotify_init(void)
+{
+	return init_srcu_struct(&fsnotify_grp_srcu);
+}
+subsys_initcall(fsnotify_init);
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
new file mode 100644
index 000000000000..4dc240824b2d
--- /dev/null
+++ b/fs/notify/fsnotify.h
@@ -0,0 +1,34 @@
+#ifndef __FS_NOTIFY_FSNOTIFY_H_
+#define __FS_NOTIFY_FSNOTIFY_H_
+
+#include <linux/list.h>
+#include <linux/fsnotify.h>
+#include <linux/srcu.h>
+#include <linux/types.h>
+
+/* protects reads of fsnotify_groups */
+extern struct srcu_struct fsnotify_grp_srcu;
+/* all groups which receive fsnotify events */
+extern struct list_head fsnotify_groups;
+/* all bitwise OR of all event types (FS_*) for all fsnotify_groups */
+extern __u32 fsnotify_mask;
+
+/* destroy all events sitting in this groups notification queue */
+extern void fsnotify_flush_notify(struct fsnotify_group *group);
+
+/* final kfree of a group */
+extern void fsnotify_final_destroy_group(struct fsnotify_group *group);
+
+/* run the list of all marks associated with inode and flag them to be freed */
+extern void fsnotify_clear_marks_by_inode(struct inode *inode);
+/*
+ * update the dentry->d_flags of all of inode's children to indicate if inode cares
+ * about events that happen to its children.
+ */
+extern void __fsnotify_update_child_dentry_flags(struct inode *inode);
+
+/* allocate and destroy and event holder to attach events to notification/access queues */
+extern struct fsnotify_event_holder *fsnotify_alloc_event_holder(void);
+extern void fsnotify_destroy_event_holder(struct fsnotify_event_holder *holder);
+
+#endif	/* __FS_NOTIFY_FSNOTIFY_H_ */
diff --git a/fs/notify/group.c b/fs/notify/group.c
new file mode 100644
index 000000000000..0e1677144bc5
--- /dev/null
+++ b/fs/notify/group.c
@@ -0,0 +1,254 @@
+/*
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2, or (at your option)
+ *  any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; see the file COPYING.  If not, write to
+ *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/srcu.h>
+#include <linux/rculist.h>
+#include <linux/wait.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+#include <asm/atomic.h>
+
+/* protects writes to fsnotify_groups and fsnotify_mask */
+static DEFINE_MUTEX(fsnotify_grp_mutex);
+/* protects reads while running the fsnotify_groups list */
+struct srcu_struct fsnotify_grp_srcu;
+/* all groups registered to receive filesystem notifications */
+LIST_HEAD(fsnotify_groups);
+/* bitwise OR of all events (FS_*) interesting to some group on this system */
+__u32 fsnotify_mask;
+
+/*
+ * When a new group registers or changes it's set of interesting events
+ * this function updates the fsnotify_mask to contain all interesting events
+ */
+void fsnotify_recalc_global_mask(void)
+{
+	struct fsnotify_group *group;
+	__u32 mask = 0;
+	int idx;
+
+	idx = srcu_read_lock(&fsnotify_grp_srcu);
+	list_for_each_entry_rcu(group, &fsnotify_groups, group_list)
+		mask |= group->mask;
+	srcu_read_unlock(&fsnotify_grp_srcu, idx);
+	fsnotify_mask = mask;
+}
+
+/*
+ * Update the group->mask by running all of the marks associated with this
+ * group and finding the bitwise | of all of the mark->mask.  If we change
+ * the group->mask we need to update the global mask of events interesting
+ * to the system.
+ */
+void fsnotify_recalc_group_mask(struct fsnotify_group *group)
+{
+	__u32 mask = 0;
+	__u32 old_mask = group->mask;
+	struct fsnotify_mark_entry *entry;
+
+	spin_lock(&group->mark_lock);
+	list_for_each_entry(entry, &group->mark_entries, g_list)
+		mask |= entry->mask;
+	spin_unlock(&group->mark_lock);
+
+	group->mask = mask;
+
+	if (old_mask != mask)
+		fsnotify_recalc_global_mask();
+}
+
+/*
+ * Take a reference to a group so things found under the fsnotify_grp_mutex
+ * can't get freed under us
+ */
+static void fsnotify_get_group(struct fsnotify_group *group)
+{
+	atomic_inc(&group->refcnt);
+}
+
+/*
+ * Final freeing of a group
+ */
+void fsnotify_final_destroy_group(struct fsnotify_group *group)
+{
+	/* clear the notification queue of all events */
+	fsnotify_flush_notify(group);
+
+	if (group->ops->free_group_priv)
+		group->ops->free_group_priv(group);
+
+	kfree(group);
+}
+
+/*
+ * Trying to get rid of a group.  We need to first get rid of any outstanding
+ * allocations and then free the group.  Remember that fsnotify_clear_marks_by_group
+ * could miss marks that are being freed by inode and those marks could still
+ * hold a reference to this group (via group->num_marks)  If we get into that
+ * situtation, the fsnotify_final_destroy_group will get called when that final
+ * mark is freed.
+ */
+static void fsnotify_destroy_group(struct fsnotify_group *group)
+{
+	/* clear all inode mark entries for this group */
+	fsnotify_clear_marks_by_group(group);
+
+	/* past the point of no return, matches the initial value of 1 */
+	if (atomic_dec_and_test(&group->num_marks))
+		fsnotify_final_destroy_group(group);
+}
+
+/*
+ * Remove this group from the global list of groups that will get events
+ * this can be done even if there are still references and things still using
+ * this group.  This just stops the group from getting new events.
+ */
+static void __fsnotify_evict_group(struct fsnotify_group *group)
+{
+	BUG_ON(!mutex_is_locked(&fsnotify_grp_mutex));
+
+	if (group->on_group_list)
+		list_del_rcu(&group->group_list);
+	group->on_group_list = 0;
+}
+
+/*
+ * Called when a group is no longer interested in getting events.  This can be
+ * used if a group is misbehaving or if for some reason a group should no longer
+ * get any filesystem events.
+ */
+void fsnotify_evict_group(struct fsnotify_group *group)
+{
+	mutex_lock(&fsnotify_grp_mutex);
+	__fsnotify_evict_group(group);
+	mutex_unlock(&fsnotify_grp_mutex);
+}
+
+/*
+ * Drop a reference to a group.  Free it if it's through.
+ */
+void fsnotify_put_group(struct fsnotify_group *group)
+{
+	if (!atomic_dec_and_mutex_lock(&group->refcnt, &fsnotify_grp_mutex))
+		return;
+
+	/*
+	 * OK, now we know that there's no other users *and* we hold mutex,
+	 * so no new references will appear
+	 */
+	__fsnotify_evict_group(group);
+
+	/*
+	 * now it's off the list, so the only thing we might care about is
+	 * srcu access....
+	 */
+	mutex_unlock(&fsnotify_grp_mutex);
+	synchronize_srcu(&fsnotify_grp_srcu);
+
+	/* and now it is really dead. _Nothing_ could be seeing it */
+	fsnotify_recalc_global_mask();
+	fsnotify_destroy_group(group);
+}
+
+/*
+ * Simply run the fsnotify_groups list and find a group which matches
+ * the given parameters.  If a group is found we take a reference to that
+ * group.
+ */
+static struct fsnotify_group *fsnotify_find_group(unsigned int group_num, __u32 mask,
+						  const struct fsnotify_ops *ops)
+{
+	struct fsnotify_group *group_iter;
+	struct fsnotify_group *group = NULL;
+
+	BUG_ON(!mutex_is_locked(&fsnotify_grp_mutex));
+
+	list_for_each_entry_rcu(group_iter, &fsnotify_groups, group_list) {
+		if (group_iter->group_num == group_num) {
+			if ((group_iter->mask == mask) &&
+			    (group_iter->ops == ops)) {
+				fsnotify_get_group(group_iter);
+				group = group_iter;
+			} else
+				group = ERR_PTR(-EEXIST);
+		}
+	}
+	return group;
+}
+
+/*
+ * Either finds an existing group which matches the group_num, mask, and ops or
+ * creates a new group and adds it to the global group list.  In either case we
+ * take a reference for the group returned.
+ */
+struct fsnotify_group *fsnotify_obtain_group(unsigned int group_num, __u32 mask,
+					     const struct fsnotify_ops *ops)
+{
+	struct fsnotify_group *group, *tgroup;
+
+	/* very low use, simpler locking if we just always alloc */
+	group = kmalloc(sizeof(struct fsnotify_group), GFP_KERNEL);
+	if (!group)
+		return ERR_PTR(-ENOMEM);
+
+	atomic_set(&group->refcnt, 1);
+
+	group->on_group_list = 0;
+	group->group_num = group_num;
+	group->mask = mask;
+
+	mutex_init(&group->notification_mutex);
+	INIT_LIST_HEAD(&group->notification_list);
+	init_waitqueue_head(&group->notification_waitq);
+	group->q_len = 0;
+	group->max_events = UINT_MAX;
+
+	spin_lock_init(&group->mark_lock);
+	atomic_set(&group->num_marks, 0);
+	INIT_LIST_HEAD(&group->mark_entries);
+
+	group->ops = ops;
+
+	mutex_lock(&fsnotify_grp_mutex);
+	tgroup = fsnotify_find_group(group_num, mask, ops);
+	if (tgroup) {
+		/* group already exists */
+		mutex_unlock(&fsnotify_grp_mutex);
+		/* destroy the new one we made */
+		fsnotify_put_group(group);
+		return tgroup;
+	}
+
+	/* group not found, add a new one */
+	list_add_rcu(&group->group_list, &fsnotify_groups);
+	group->on_group_list = 1;
+	/* being on the fsnotify_groups list holds one num_marks */
+	atomic_inc(&group->num_marks);
+
+	mutex_unlock(&fsnotify_grp_mutex);
+
+	if (mask)
+		fsnotify_recalc_global_mask();
+
+	return group;
+}
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
new file mode 100644
index 000000000000..c8a07c65482b
--- /dev/null
+++ b/fs/notify/inode_mark.c
@@ -0,0 +1,426 @@
+/*
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2, or (at your option)
+ *  any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; see the file COPYING.  If not, write to
+ *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * fsnotify inode mark locking/lifetime/and refcnting
+ *
+ * REFCNT:
+ * The mark->refcnt tells how many "things" in the kernel currently are
+ * referencing this object.  The object typically will live inside the kernel
+ * with a refcnt of 2, one for each list it is on (i_list, g_list).  Any task
+ * which can find this object holding the appropriete locks, can take a reference
+ * and the object itself is guarenteed to survive until the reference is dropped.
+ *
+ * LOCKING:
+ * There are 3 spinlocks involved with fsnotify inode marks and they MUST
+ * be taken in order as follows:
+ *
+ * entry->lock
+ * group->mark_lock
+ * inode->i_lock
+ *
+ * entry->lock protects 2 things, entry->group and entry->inode.  You must hold
+ * that lock to dereference either of these things (they could be NULL even with
+ * the lock)
+ *
+ * group->mark_lock protects the mark_entries list anchored inside a given group
+ * and each entry is hooked via the g_list.  It also sorta protects the
+ * free_g_list, which when used is anchored by a private list on the stack of the
+ * task which held the group->mark_lock.
+ *
+ * inode->i_lock protects the i_fsnotify_mark_entries list anchored inside a
+ * given inode and each entry is hooked via the i_list. (and sorta the
+ * free_i_list)
+ *
+ *
+ * LIFETIME:
+ * Inode marks survive between when they are added to an inode and when their
+ * refcnt==0.
+ *
+ * The inode mark can be cleared for a number of different reasons including:
+ * - The inode is unlinked for the last time.  (fsnotify_inode_remove)
+ * - The inode is being evicted from cache. (fsnotify_inode_delete)
+ * - The fs the inode is on is unmounted.  (fsnotify_inode_delete/fsnotify_unmount_inodes)
+ * - Something explicitly requests that it be removed.  (fsnotify_destroy_mark_by_entry)
+ * - The fsnotify_group associated with the mark is going away and all such marks
+ *   need to be cleaned up. (fsnotify_clear_marks_by_group)
+ *
+ * Worst case we are given an inode and need to clean up all the marks on that
+ * inode.  We take i_lock and walk the i_fsnotify_mark_entries safely.  For each
+ * mark on the list we take a reference (so the mark can't disappear under us).
+ * We remove that mark form the inode's list of marks and we add this mark to a
+ * private list anchored on the stack using i_free_list;  At this point we no
+ * longer fear anything finding the mark using the inode's list of marks.
+ *
+ * We can safely and locklessly run the private list on the stack of everything
+ * we just unattached from the original inode.  For each mark on the private list
+ * we grab the mark-> and can thus dereference mark->group and mark->inode.  If
+ * we see the group and inode are not NULL we take those locks.  Now holding all
+ * 3 locks we can completely remove the mark from other tasks finding it in the
+ * future.  Remember, 10 things might already be referencing this mark, but they
+ * better be holding a ref.  We drop our reference we took before we unhooked it
+ * from the inode.  When the ref hits 0 we can free the mark.
+ *
+ * Very similarly for freeing by group, except we use free_g_list.
+ *
+ * This has the very interesting property of being able to run concurrently with
+ * any (or all) other directions.
+ */
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/writeback.h> /* for inode_lock */
+
+#include <asm/atomic.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+void fsnotify_get_mark(struct fsnotify_mark_entry *entry)
+{
+	atomic_inc(&entry->refcnt);
+}
+
+void fsnotify_put_mark(struct fsnotify_mark_entry *entry)
+{
+	if (atomic_dec_and_test(&entry->refcnt))
+		entry->free_mark(entry);
+}
+
+/*
+ * Recalculate the mask of events relevant to a given inode locked.
+ */
+static void fsnotify_recalc_inode_mask_locked(struct inode *inode)
+{
+	struct fsnotify_mark_entry *entry;
+	struct hlist_node *pos;
+	__u32 new_mask = 0;
+
+	assert_spin_locked(&inode->i_lock);
+
+	hlist_for_each_entry(entry, pos, &inode->i_fsnotify_mark_entries, i_list)
+		new_mask |= entry->mask;
+	inode->i_fsnotify_mask = new_mask;
+}
+
+/*
+ * Recalculate the inode->i_fsnotify_mask, or the mask of all FS_* event types
+ * any notifier is interested in hearing for this inode.
+ */
+void fsnotify_recalc_inode_mask(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	fsnotify_recalc_inode_mask_locked(inode);
+	spin_unlock(&inode->i_lock);
+
+	__fsnotify_update_child_dentry_flags(inode);
+}
+
+/*
+ * Any time a mark is getting freed we end up here.
+ * The caller had better be holding a reference to this mark so we don't actually
+ * do the final put under the entry->lock
+ */
+void fsnotify_destroy_mark_by_entry(struct fsnotify_mark_entry *entry)
+{
+	struct fsnotify_group *group;
+	struct inode *inode;
+
+	spin_lock(&entry->lock);
+
+	group = entry->group;
+	inode = entry->inode;
+
+	BUG_ON(group && !inode);
+	BUG_ON(!group && inode);
+
+	/* if !group something else already marked this to die */
+	if (!group) {
+		spin_unlock(&entry->lock);
+		return;
+	}
+
+	/* 1 from caller and 1 for being on i_list/g_list */
+	BUG_ON(atomic_read(&entry->refcnt) < 2);
+
+	spin_lock(&group->mark_lock);
+	spin_lock(&inode->i_lock);
+
+	hlist_del_init(&entry->i_list);
+	entry->inode = NULL;
+
+	list_del_init(&entry->g_list);
+	entry->group = NULL;
+
+	fsnotify_put_mark(entry); /* for i_list and g_list */
+
+	/*
+	 * this mark is now off the inode->i_fsnotify_mark_entries list and we
+	 * hold the inode->i_lock, so this is the perfect time to update the
+	 * inode->i_fsnotify_mask
+	 */
+	fsnotify_recalc_inode_mask_locked(inode);
+
+	spin_unlock(&inode->i_lock);
+	spin_unlock(&group->mark_lock);
+	spin_unlock(&entry->lock);
+
+	/*
+	 * Some groups like to know that marks are being freed.  This is a
+	 * callback to the group function to let it know that this entry
+	 * is being freed.
+	 */
+	if (group->ops->freeing_mark)
+		group->ops->freeing_mark(entry, group);
+
+	/*
+	 * __fsnotify_update_child_dentry_flags(inode);
+	 *
+	 * I really want to call that, but we can't, we have no idea if the inode
+	 * still exists the second we drop the entry->lock.
+	 *
+	 * The next time an event arrive to this inode from one of it's children
+	 * __fsnotify_parent will see that the inode doesn't care about it's
+	 * children and will update all of these flags then.  So really this
+	 * is just a lazy update (and could be a perf win...)
+	 */
+
+
+	iput(inode);
+
+	/*
+	 * it's possible that this group tried to destroy itself, but this
+	 * this mark was simultaneously being freed by inode.  If that's the
+	 * case, we finish freeing the group here.
+	 */
+	if (unlikely(atomic_dec_and_test(&group->num_marks)))
+		fsnotify_final_destroy_group(group);
+}
+
+/*
+ * Given a group, destroy all of the marks associated with that group.
+ */
+void fsnotify_clear_marks_by_group(struct fsnotify_group *group)
+{
+	struct fsnotify_mark_entry *lentry, *entry;
+	LIST_HEAD(free_list);
+
+	spin_lock(&group->mark_lock);
+	list_for_each_entry_safe(entry, lentry, &group->mark_entries, g_list) {
+		list_add(&entry->free_g_list, &free_list);
+		list_del_init(&entry->g_list);
+		fsnotify_get_mark(entry);
+	}
+	spin_unlock(&group->mark_lock);
+
+	list_for_each_entry_safe(entry, lentry, &free_list, free_g_list) {
+		fsnotify_destroy_mark_by_entry(entry);
+		fsnotify_put_mark(entry);
+	}
+}
+
+/*
+ * Given an inode, destroy all of the marks associated with that inode.
+ */
+void fsnotify_clear_marks_by_inode(struct inode *inode)
+{
+	struct fsnotify_mark_entry *entry, *lentry;
+	struct hlist_node *pos, *n;
+	LIST_HEAD(free_list);
+
+	spin_lock(&inode->i_lock);
+	hlist_for_each_entry_safe(entry, pos, n, &inode->i_fsnotify_mark_entries, i_list) {
+		list_add(&entry->free_i_list, &free_list);
+		hlist_del_init(&entry->i_list);
+		fsnotify_get_mark(entry);
+	}
+	spin_unlock(&inode->i_lock);
+
+	list_for_each_entry_safe(entry, lentry, &free_list, free_i_list) {
+		fsnotify_destroy_mark_by_entry(entry);
+		fsnotify_put_mark(entry);
+	}
+}
+
+/*
+ * given a group and inode, find the mark associated with that combination.
+ * if found take a reference to that mark and return it, else return NULL
+ */
+struct fsnotify_mark_entry *fsnotify_find_mark_entry(struct fsnotify_group *group,
+						     struct inode *inode)
+{
+	struct fsnotify_mark_entry *entry;
+	struct hlist_node *pos;
+
+	assert_spin_locked(&inode->i_lock);
+
+	hlist_for_each_entry(entry, pos, &inode->i_fsnotify_mark_entries, i_list) {
+		if (entry->group == group) {
+			fsnotify_get_mark(entry);
+			return entry;
+		}
+	}
+	return NULL;
+}
+
+/*
+ * Nothing fancy, just initialize lists and locks and counters.
+ */
+void fsnotify_init_mark(struct fsnotify_mark_entry *entry,
+			void (*free_mark)(struct fsnotify_mark_entry *entry))
+
+{
+	spin_lock_init(&entry->lock);
+	atomic_set(&entry->refcnt, 1);
+	INIT_HLIST_NODE(&entry->i_list);
+	entry->group = NULL;
+	entry->mask = 0;
+	entry->inode = NULL;
+	entry->free_mark = free_mark;
+}
+
+/*
+ * Attach an initialized mark entry to a given group and inode.
+ * These marks may be used for the fsnotify backend to determine which
+ * event types should be delivered to which group and for which inodes.
+ */
+int fsnotify_add_mark(struct fsnotify_mark_entry *entry,
+		      struct fsnotify_group *group, struct inode *inode)
+{
+	struct fsnotify_mark_entry *lentry;
+	int ret = 0;
+
+	inode = igrab(inode);
+	if (unlikely(!inode))
+		return -EINVAL;
+
+	/*
+	 * LOCKING ORDER!!!!
+	 * entry->lock
+	 * group->mark_lock
+	 * inode->i_lock
+	 */
+	spin_lock(&entry->lock);
+	spin_lock(&group->mark_lock);
+	spin_lock(&inode->i_lock);
+
+	entry->group = group;
+	entry->inode = inode;
+
+	lentry = fsnotify_find_mark_entry(group, inode);
+	if (!lentry) {
+		hlist_add_head(&entry->i_list, &inode->i_fsnotify_mark_entries);
+		list_add(&entry->g_list, &group->mark_entries);
+
+		fsnotify_get_mark(entry); /* for i_list and g_list */
+
+		atomic_inc(&group->num_marks);
+
+		fsnotify_recalc_inode_mask_locked(inode);
+	}
+
+	spin_unlock(&inode->i_lock);
+	spin_unlock(&group->mark_lock);
+	spin_unlock(&entry->lock);
+
+	if (lentry) {
+		ret = -EEXIST;
+		iput(inode);
+		fsnotify_put_mark(lentry);
+	} else {
+		__fsnotify_update_child_dentry_flags(inode);
+	}
+
+	return ret;
+}
+
+/**
+ * fsnotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
+ * @list: list of inodes being unmounted (sb->s_inodes)
+ *
+ * Called with inode_lock held, protecting the unmounting super block's list
+ * of inodes, and with iprune_mutex held, keeping shrink_icache_memory() at bay.
+ * We temporarily drop inode_lock, however, and CAN block.
+ */
+void fsnotify_unmount_inodes(struct list_head *list)
+{
+	struct inode *inode, *next_i, *need_iput = NULL;
+
+	list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
+		struct inode *need_iput_tmp;
+
+		/*
+		 * We cannot __iget() an inode in state I_CLEAR, I_FREEING,
+		 * I_WILL_FREE, or I_NEW which is fine because by that point
+		 * the inode cannot have any associated watches.
+		 */
+		if (inode->i_state & (I_CLEAR|I_FREEING|I_WILL_FREE|I_NEW))
+			continue;
+
+		/*
+		 * If i_count is zero, the inode cannot have any watches and
+		 * doing an __iget/iput with MS_ACTIVE clear would actually
+		 * evict all inodes with zero i_count from icache which is
+		 * unnecessarily violent and may in fact be illegal to do.
+		 */
+		if (!atomic_read(&inode->i_count))
+			continue;
+
+		need_iput_tmp = need_iput;
+		need_iput = NULL;
+
+		/* In case fsnotify_inode_delete() drops a reference. */
+		if (inode != need_iput_tmp)
+			__iget(inode);
+		else
+			need_iput_tmp = NULL;
+
+		/* In case the dropping of a reference would nuke next_i. */
+		if ((&next_i->i_sb_list != list) &&
+		    atomic_read(&next_i->i_count) &&
+		    !(next_i->i_state & (I_CLEAR | I_FREEING | I_WILL_FREE))) {
+			__iget(next_i);
+			need_iput = next_i;
+		}
+
+		/*
+		 * We can safely drop inode_lock here because we hold
+		 * references on both inode and next_i.  Also no new inodes
+		 * will be added since the umount has begun.  Finally,
+		 * iprune_mutex keeps shrink_icache_memory() away.
+		 */
+		spin_unlock(&inode_lock);
+
+		if (need_iput_tmp)
+			iput(need_iput_tmp);
+
+		/* for each watch, send FS_UNMOUNT and then remove it */
+		fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+
+		fsnotify_inode_delete(inode);
+
+		iput(inode);
+
+		spin_lock(&inode_lock);
+	}
+}
diff --git a/fs/notify/inotify/Kconfig b/fs/notify/inotify/Kconfig
index 446792841023..5356884289a1 100644
--- a/fs/notify/inotify/Kconfig
+++ b/fs/notify/inotify/Kconfig
@@ -1,26 +1,30 @@
 config INOTIFY
 	bool "Inotify file change notification support"
-	default y
+	default n
 	---help---
-	  Say Y here to enable inotify support.  Inotify is a file change
-	  notification system and a replacement for dnotify.  Inotify fixes
-	  numerous shortcomings in dnotify and introduces several new features
-	  including multiple file events, one-shot support, and unmount
-	  notification.
+	  Say Y here to enable legacy in kernel inotify support.  Inotify is a
+	  file change notification system.  It is a replacement for dnotify.
+	  This option only provides the legacy inotify in kernel API.  There
+	  are no in tree kernel users of this interface since it is deprecated.
+	  You only need this if you are loading an out of tree kernel module
+	  that uses inotify.
 
 	  For more information, see <file:Documentation/filesystems/inotify.txt>
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 config INOTIFY_USER
 	bool "Inotify support for userspace"
-	depends on INOTIFY
+	depends on FSNOTIFY
 	default y
 	---help---
 	  Say Y here to enable inotify support for userspace, including the
 	  associated system calls.  Inotify allows monitoring of both files and
 	  directories via a single open fd.  Events are read from the file
 	  descriptor, which is also select()- and poll()-able.
+	  Inotify fixes numerous shortcomings in dnotify and introduces several
+	  new features including multiple file events, one-shot support, and
+	  unmount notification.
 
 	  For more information, see <file:Documentation/filesystems/inotify.txt>
 
diff --git a/fs/notify/inotify/Makefile b/fs/notify/inotify/Makefile
index e290f3bb9d8d..943828171362 100644
--- a/fs/notify/inotify/Makefile
+++ b/fs/notify/inotify/Makefile
@@ -1,2 +1,2 @@
 obj-$(CONFIG_INOTIFY)		+= inotify.o
-obj-$(CONFIG_INOTIFY_USER)	+= inotify_user.o
+obj-$(CONFIG_INOTIFY_USER)	+= inotify_fsnotify.o inotify_user.o
diff --git a/fs/notify/inotify/inotify.c b/fs/notify/inotify/inotify.c
index 220c13f0d73d..40b1cf914ccb 100644
--- a/fs/notify/inotify/inotify.c
+++ b/fs/notify/inotify/inotify.c
@@ -32,6 +32,7 @@
 #include <linux/list.h>
 #include <linux/writeback.h>
 #include <linux/inotify.h>
+#include <linux/fsnotify_backend.h>
 
 static atomic_t inotify_cookie;
 
@@ -905,6 +906,25 @@ EXPORT_SYMBOL_GPL(inotify_rm_watch);
  */
 static int __init inotify_setup(void)
 {
+	BUILD_BUG_ON(IN_ACCESS != FS_ACCESS);
+	BUILD_BUG_ON(IN_MODIFY != FS_MODIFY);
+	BUILD_BUG_ON(IN_ATTRIB != FS_ATTRIB);
+	BUILD_BUG_ON(IN_CLOSE_WRITE != FS_CLOSE_WRITE);
+	BUILD_BUG_ON(IN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
+	BUILD_BUG_ON(IN_OPEN != FS_OPEN);
+	BUILD_BUG_ON(IN_MOVED_FROM != FS_MOVED_FROM);
+	BUILD_BUG_ON(IN_MOVED_TO != FS_MOVED_TO);
+	BUILD_BUG_ON(IN_CREATE != FS_CREATE);
+	BUILD_BUG_ON(IN_DELETE != FS_DELETE);
+	BUILD_BUG_ON(IN_DELETE_SELF != FS_DELETE_SELF);
+	BUILD_BUG_ON(IN_MOVE_SELF != FS_MOVE_SELF);
+	BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW);
+
+	BUILD_BUG_ON(IN_UNMOUNT != FS_UNMOUNT);
+	BUILD_BUG_ON(IN_ISDIR != FS_IN_ISDIR);
+	BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED);
+	BUILD_BUG_ON(IN_ONESHOT != FS_IN_ONESHOT);
+
 	atomic_set(&inotify_cookie, 0);
 
 	return 0;
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
new file mode 100644
index 000000000000..ea2605a58b8a
--- /dev/null
+++ b/fs/notify/inotify/inotify.h
@@ -0,0 +1,21 @@
+#include <linux/fsnotify_backend.h>
+#include <linux/inotify.h>
+#include <linux/slab.h> /* struct kmem_cache */
+
+extern struct kmem_cache *event_priv_cachep;
+
+struct inotify_event_private_data {
+	struct fsnotify_event_private_data fsnotify_event_priv_data;
+	int wd;
+};
+
+struct inotify_inode_mark_entry {
+	/* fsnotify_mark_entry MUST be the first thing */
+	struct fsnotify_mark_entry fsn_entry;
+	int wd;
+};
+
+extern void inotify_destroy_mark_entry(struct fsnotify_mark_entry *entry, struct fsnotify_group *group);
+extern void inotify_free_event_priv(struct fsnotify_event_private_data *event_priv);
+
+extern const struct fsnotify_ops inotify_fsnotify_ops;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
new file mode 100644
index 000000000000..7ef75b83247e
--- /dev/null
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -0,0 +1,138 @@
+/*
+ * fs/inotify_user.c - inotify support for userspace
+ *
+ * Authors:
+ *	John McCutchan	<ttb@tentacle.dhs.org>
+ *	Robert Love	<rml@novell.com>
+ *
+ * Copyright (C) 2005 John McCutchan
+ * Copyright 2006 Hewlett-Packard Development Company, L.P.
+ *
+ * Copyright (C) 2009 Eric Paris <Red Hat Inc>
+ * inotify was largely rewriten to make use of the fsnotify infrastructure
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/fs.h> /* struct inode */
+#include <linux/fsnotify_backend.h>
+#include <linux/inotify.h>
+#include <linux/path.h> /* struct path */
+#include <linux/slab.h> /* kmem_* */
+#include <linux/types.h>
+
+#include "inotify.h"
+
+static int inotify_handle_event(struct fsnotify_group *group, struct fsnotify_event *event)
+{
+	struct fsnotify_mark_entry *entry;
+	struct inotify_inode_mark_entry *ientry;
+	struct inode *to_tell;
+	struct inotify_event_private_data *event_priv;
+	struct fsnotify_event_private_data *fsn_event_priv;
+	int wd, ret;
+
+	to_tell = event->to_tell;
+
+	spin_lock(&to_tell->i_lock);
+	entry = fsnotify_find_mark_entry(group, to_tell);
+	spin_unlock(&to_tell->i_lock);
+	/* race with watch removal?  We already passes should_send */
+	if (unlikely(!entry))
+		return 0;
+	ientry = container_of(entry, struct inotify_inode_mark_entry,
+			      fsn_entry);
+	wd = ientry->wd;
+
+	event_priv = kmem_cache_alloc(event_priv_cachep, GFP_KERNEL);
+	if (unlikely(!event_priv))
+		return -ENOMEM;
+
+	fsn_event_priv = &event_priv->fsnotify_event_priv_data;
+
+	fsn_event_priv->group = group;
+	event_priv->wd = wd;
+
+	ret = fsnotify_add_notify_event(group, event, fsn_event_priv);
+	/* EEXIST is not an error */
+	if (ret == -EEXIST)
+		ret = 0;
+
+	/* did event_priv get attached? */
+	if (list_empty(&fsn_event_priv->event_list))
+		inotify_free_event_priv(fsn_event_priv);
+
+	/*
+	 * If we hold the entry until after the event is on the queue
+	 * IN_IGNORED won't be able to pass this event in the queue
+	 */
+	fsnotify_put_mark(entry);
+
+	return ret;
+}
+
+static void inotify_freeing_mark(struct fsnotify_mark_entry *entry, struct fsnotify_group *group)
+{
+	inotify_destroy_mark_entry(entry, group);
+}
+
+static bool inotify_should_send_event(struct fsnotify_group *group, struct inode *inode, __u32 mask)
+{
+	struct fsnotify_mark_entry *entry;
+	bool send;
+
+	spin_lock(&inode->i_lock);
+	entry = fsnotify_find_mark_entry(group, inode);
+	spin_unlock(&inode->i_lock);
+	if (!entry)
+		return false;
+
+	mask = (mask & ~FS_EVENT_ON_CHILD);
+	send = (entry->mask & mask);
+
+	/* find took a reference */
+	fsnotify_put_mark(entry);
+
+	return send;
+}
+
+static int idr_callback(int id, void *p, void *data)
+{
+	BUG();
+	return 0;
+}
+
+static void inotify_free_group_priv(struct fsnotify_group *group)
+{
+	/* ideally the idr is empty and we won't hit the BUG in teh callback */
+	idr_for_each(&group->inotify_data.idr, idr_callback, NULL);
+	idr_remove_all(&group->inotify_data.idr);
+	idr_destroy(&group->inotify_data.idr);
+}
+
+void inotify_free_event_priv(struct fsnotify_event_private_data *fsn_event_priv)
+{
+	struct inotify_event_private_data *event_priv;
+
+
+	event_priv = container_of(fsn_event_priv, struct inotify_event_private_data,
+				  fsnotify_event_priv_data);
+
+	kmem_cache_free(event_priv_cachep, event_priv);
+}
+
+const struct fsnotify_ops inotify_fsnotify_ops = {
+	.handle_event = inotify_handle_event,
+	.should_send_event = inotify_should_send_event,
+	.free_group_priv = inotify_free_group_priv,
+	.free_event_priv = inotify_free_event_priv,
+	.freeing_mark = inotify_freeing_mark,
+};
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 1634319e2404..982a412ac5bc 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -8,6 +8,9 @@
  * Copyright (C) 2005 John McCutchan
  * Copyright 2006 Hewlett-Packard Development Company, L.P.
  *
+ * Copyright (C) 2009 Eric Paris <Red Hat Inc>
+ * inotify was largely rewriten to make use of the fsnotify infrastructure
+ *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
  * Free Software Foundation; either version 2, or (at your option) any
@@ -19,94 +22,48 @@
  * General Public License for more details.
  */
 
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/fs.h>
 #include <linux/file.h>
-#include <linux/mount.h>
-#include <linux/namei.h>
-#include <linux/poll.h>
-#include <linux/init.h>
-#include <linux/list.h>
+#include <linux/fs.h> /* struct inode */
+#include <linux/fsnotify_backend.h>
+#include <linux/idr.h>
+#include <linux/init.h> /* module_init */
 #include <linux/inotify.h>
+#include <linux/kernel.h> /* roundup() */
+#include <linux/magic.h> /* superblock magic number */
+#include <linux/mount.h> /* mntget */
+#include <linux/namei.h> /* LOOKUP_FOLLOW */
+#include <linux/path.h> /* struct path */
+#include <linux/sched.h> /* struct user */
+#include <linux/slab.h> /* struct kmem_cache */
 #include <linux/syscalls.h>
-#include <linux/magic.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/poll.h>
+#include <linux/wait.h>
+
+#include "inotify.h"
 
 #include <asm/ioctls.h>
 
-static struct kmem_cache *watch_cachep __read_mostly;
-static struct kmem_cache *event_cachep __read_mostly;
-
 static struct vfsmount *inotify_mnt __read_mostly;
 
+/* this just sits here and wastes global memory.  used to just pad userspace messages with zeros */
+static struct inotify_event nul_inotify_event;
+
 /* these are configurable via /proc/sys/fs/inotify/ */
 static int inotify_max_user_instances __read_mostly;
-static int inotify_max_user_watches __read_mostly;
 static int inotify_max_queued_events __read_mostly;
+int inotify_max_user_watches __read_mostly;
+
+static struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
+struct kmem_cache *event_priv_cachep __read_mostly;
+static struct fsnotify_event *inotify_ignored_event;
 
 /*
- * Lock ordering:
- *
- * inotify_dev->up_mutex (ensures we don't re-add the same watch)
- * 	inode->inotify_mutex (protects inode's watch list)
- * 		inotify_handle->mutex (protects inotify_handle's watch list)
- * 			inotify_dev->ev_mutex (protects device's event queue)
+ * When inotify registers a new group it increments this and uses that
+ * value as an offset to set the fsnotify group "name" and priority.
  */
-
-/*
- * Lifetimes of the main data structures:
- *
- * inotify_device: Lifetime is managed by reference count, from
- * sys_inotify_init() until release.  Additional references can bump the count
- * via get_inotify_dev() and drop the count via put_inotify_dev().
- *
- * inotify_user_watch: Lifetime is from create_watch() to the receipt of an
- * IN_IGNORED event from inotify, or when using IN_ONESHOT, to receipt of the
- * first event, or to inotify_destroy().
- */
-
-/*
- * struct inotify_device - represents an inotify instance
- *
- * This structure is protected by the mutex 'mutex'.
- */
-struct inotify_device {
-	wait_queue_head_t 	wq;		/* wait queue for i/o */
-	struct mutex		ev_mutex;	/* protects event queue */
-	struct mutex		up_mutex;	/* synchronizes watch updates */
-	struct list_head 	events;		/* list of queued events */
-	struct user_struct	*user;		/* user who opened this dev */
-	struct inotify_handle	*ih;		/* inotify handle */
-	struct fasync_struct    *fa;            /* async notification */
-	atomic_t		count;		/* reference count */
-	unsigned int		queue_size;	/* size of the queue (bytes) */
-	unsigned int		event_count;	/* number of pending events */
-	unsigned int		max_events;	/* maximum number of events */
-};
-
-/*
- * struct inotify_kernel_event - An inotify event, originating from a watch and
- * queued for user-space.  A list of these is attached to each instance of the
- * device.  In read(), this list is walked and all events that can fit in the
- * buffer are returned.
- *
- * Protected by dev->ev_mutex of the device in which we are queued.
- */
-struct inotify_kernel_event {
-	struct inotify_event	event;	/* the user-space event */
-	struct list_head        list;	/* entry in inotify_device's list */
-	char			*name;	/* filename, if any */
-};
-
-/*
- * struct inotify_user_watch - our version of an inotify_watch, we add
- * a reference to the associated inotify_device.
- */
-struct inotify_user_watch {
-	struct inotify_device	*dev;	/* associated device */
-	struct inotify_watch	wdata;	/* inotify watch data */
-};
+static atomic_t inotify_grp_num;
 
 #ifdef CONFIG_SYSCTL
 
@@ -149,280 +106,36 @@ ctl_table inotify_table[] = {
 };
 #endif /* CONFIG_SYSCTL */
 
-static inline void get_inotify_dev(struct inotify_device *dev)
+static inline __u32 inotify_arg_to_mask(u32 arg)
 {
-	atomic_inc(&dev->count);
+	__u32 mask;
+
+	/* everything should accept their own ignored and cares about children */
+	mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD);
+
+	/* mask off the flags used to open the fd */
+	mask |= (arg & (IN_ALL_EVENTS | IN_ONESHOT));
+
+	return mask;
 }
 
-static inline void put_inotify_dev(struct inotify_device *dev)
+static inline u32 inotify_mask_to_arg(__u32 mask)
 {
-	if (atomic_dec_and_test(&dev->count)) {
-		atomic_dec(&dev->user->inotify_devs);
-		free_uid(dev->user);
-		kfree(dev);
-	}
+	return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED |
+		       IN_Q_OVERFLOW);
 }
 
-/*
- * free_inotify_user_watch - cleans up the watch and its references
- */
-static void free_inotify_user_watch(struct inotify_watch *w)
-{
-	struct inotify_user_watch *watch;
-	struct inotify_device *dev;
-
-	watch = container_of(w, struct inotify_user_watch, wdata);
-	dev = watch->dev;
-
-	atomic_dec(&dev->user->inotify_watches);
-	put_inotify_dev(dev);
-	kmem_cache_free(watch_cachep, watch);
-}
-
-/*
- * kernel_event - create a new kernel event with the given parameters
- *
- * This function can sleep.
- */
-static struct inotify_kernel_event * kernel_event(s32 wd, u32 mask, u32 cookie,
-						  const char *name)
-{
-	struct inotify_kernel_event *kevent;
-
-	kevent = kmem_cache_alloc(event_cachep, GFP_NOFS);
-	if (unlikely(!kevent))
-		return NULL;
-
-	/* we hand this out to user-space, so zero it just in case */
-	memset(&kevent->event, 0, sizeof(struct inotify_event));
-
-	kevent->event.wd = wd;
-	kevent->event.mask = mask;
-	kevent->event.cookie = cookie;
-
-	INIT_LIST_HEAD(&kevent->list);
-
-	if (name) {
-		size_t len, rem, event_size = sizeof(struct inotify_event);
-
-		/*
-		 * We need to pad the filename so as to properly align an
-		 * array of inotify_event structures.  Because the structure is
-		 * small and the common case is a small filename, we just round
-		 * up to the next multiple of the structure's sizeof.  This is
-		 * simple and safe for all architectures.
-		 */
-		len = strlen(name) + 1;
-		rem = event_size - len;
-		if (len > event_size) {
-			rem = event_size - (len % event_size);
-			if (len % event_size == 0)
-				rem = 0;
-		}
-
-		kevent->name = kmalloc(len + rem, GFP_NOFS);
-		if (unlikely(!kevent->name)) {
-			kmem_cache_free(event_cachep, kevent);
-			return NULL;
-		}
-		memcpy(kevent->name, name, len);
-		if (rem)
-			memset(kevent->name + len, 0, rem);
-		kevent->event.len = len + rem;
-	} else {
-		kevent->event.len = 0;
-		kevent->name = NULL;
-	}
-
-	return kevent;
-}
-
-/*
- * inotify_dev_get_event - return the next event in the given dev's queue
- *
- * Caller must hold dev->ev_mutex.
- */
-static inline struct inotify_kernel_event *
-inotify_dev_get_event(struct inotify_device *dev)
-{
-	return list_entry(dev->events.next, struct inotify_kernel_event, list);
-}
-
-/*
- * inotify_dev_get_last_event - return the last event in the given dev's queue
- *
- * Caller must hold dev->ev_mutex.
- */
-static inline struct inotify_kernel_event *
-inotify_dev_get_last_event(struct inotify_device *dev)
-{
-	if (list_empty(&dev->events))
-		return NULL;
-	return list_entry(dev->events.prev, struct inotify_kernel_event, list);
-}
-
-/*
- * inotify_dev_queue_event - event handler registered with core inotify, adds
- * a new event to the given device
- *
- * Can sleep (calls kernel_event()).
- */
-static void inotify_dev_queue_event(struct inotify_watch *w, u32 wd, u32 mask,
-				    u32 cookie, const char *name,
-				    struct inode *ignored)
-{
-	struct inotify_user_watch *watch;
-	struct inotify_device *dev;
-	struct inotify_kernel_event *kevent, *last;
-
-	watch = container_of(w, struct inotify_user_watch, wdata);
-	dev = watch->dev;
-
-	mutex_lock(&dev->ev_mutex);
-
-	/* we can safely put the watch as we don't reference it while
-	 * generating the event
-	 */
-	if (mask & IN_IGNORED || w->mask & IN_ONESHOT)
-		put_inotify_watch(w); /* final put */
-
-	/* coalescing: drop this event if it is a dupe of the previous */
-	last = inotify_dev_get_last_event(dev);
-	if (last && last->event.mask == mask && last->event.wd == wd &&
-			last->event.cookie == cookie) {
-		const char *lastname = last->name;
-
-		if (!name && !lastname)
-			goto out;
-		if (name && lastname && !strcmp(lastname, name))
-			goto out;
-	}
-
-	/* the queue overflowed and we already sent the Q_OVERFLOW event */
-	if (unlikely(dev->event_count > dev->max_events))
-		goto out;
-
-	/* if the queue overflows, we need to notify user space */
-	if (unlikely(dev->event_count == dev->max_events))
-		kevent = kernel_event(-1, IN_Q_OVERFLOW, cookie, NULL);
-	else
-		kevent = kernel_event(wd, mask, cookie, name);
-
-	if (unlikely(!kevent))
-		goto out;
-
-	/* queue the event and wake up anyone waiting */
-	dev->event_count++;
-	dev->queue_size += sizeof(struct inotify_event) + kevent->event.len;
-	list_add_tail(&kevent->list, &dev->events);
-	wake_up_interruptible(&dev->wq);
-	kill_fasync(&dev->fa, SIGIO, POLL_IN);
-
-out:
-	mutex_unlock(&dev->ev_mutex);
-}
-
-/*
- * remove_kevent - cleans up the given kevent
- *
- * Caller must hold dev->ev_mutex.
- */
-static void remove_kevent(struct inotify_device *dev,
-			  struct inotify_kernel_event *kevent)
-{
-	list_del(&kevent->list);
-
-	dev->event_count--;
-	dev->queue_size -= sizeof(struct inotify_event) + kevent->event.len;
-}
-
-/*
- * free_kevent - frees the given kevent.
- */
-static void free_kevent(struct inotify_kernel_event *kevent)
-{
-	kfree(kevent->name);
-	kmem_cache_free(event_cachep, kevent);
-}
-
-/*
- * inotify_dev_event_dequeue - destroy an event on the given device
- *
- * Caller must hold dev->ev_mutex.
- */
-static void inotify_dev_event_dequeue(struct inotify_device *dev)
-{
-	if (!list_empty(&dev->events)) {
-		struct inotify_kernel_event *kevent;
-		kevent = inotify_dev_get_event(dev);
-		remove_kevent(dev, kevent);
-		free_kevent(kevent);
-	}
-}
-
-/*
- * find_inode - resolve a user-given path to a specific inode
- */
-static int find_inode(const char __user *dirname, struct path *path,
-		      unsigned flags)
-{
-	int error;
-
-	error = user_path_at(AT_FDCWD, dirname, flags, path);
-	if (error)
-		return error;
-	/* you can only watch an inode if you have read permissions on it */
-	error = inode_permission(path->dentry->d_inode, MAY_READ);
-	if (error)
-		path_put(path);
-	return error;
-}
-
-/*
- * create_watch - creates a watch on the given device.
- *
- * Callers must hold dev->up_mutex.
- */
-static int create_watch(struct inotify_device *dev, struct inode *inode,
-			u32 mask)
-{
-	struct inotify_user_watch *watch;
-	int ret;
-
-	if (atomic_read(&dev->user->inotify_watches) >=
-			inotify_max_user_watches)
-		return -ENOSPC;
-
-	watch = kmem_cache_alloc(watch_cachep, GFP_KERNEL);
-	if (unlikely(!watch))
-		return -ENOMEM;
-
-	/* save a reference to device and bump the count to make it official */
-	get_inotify_dev(dev);
-	watch->dev = dev;
-
-	atomic_inc(&dev->user->inotify_watches);
-
-	inotify_init_watch(&watch->wdata);
-	ret = inotify_add_watch(dev->ih, &watch->wdata, inode, mask);
-	if (ret < 0)
-		free_inotify_user_watch(&watch->wdata);
-
-	return ret;
-}
-
-/* Device Interface */
-
+/* intofiy userspace file descriptor functions */
 static unsigned int inotify_poll(struct file *file, poll_table *wait)
 {
-	struct inotify_device *dev = file->private_data;
+	struct fsnotify_group *group = file->private_data;
 	int ret = 0;
 
-	poll_wait(file, &dev->wq, wait);
-	mutex_lock(&dev->ev_mutex);
-	if (!list_empty(&dev->events))
+	poll_wait(file, &group->notification_waitq, wait);
+	mutex_lock(&group->notification_mutex);
+	if (!fsnotify_notify_queue_is_empty(group))
 		ret = POLLIN | POLLRDNORM;
-	mutex_unlock(&dev->ev_mutex);
+	mutex_unlock(&group->notification_mutex);
 
 	return ret;
 }
@@ -432,26 +145,29 @@ static unsigned int inotify_poll(struct file *file, poll_table *wait)
  * enough to fit in "count". Return an error pointer if
  * not large enough.
  *
- * Called with the device ev_mutex held.
+ * Called with the group->notification_mutex held.
  */
-static struct inotify_kernel_event *get_one_event(struct inotify_device *dev,
-						  size_t count)
+static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
+					    size_t count)
 {
 	size_t event_size = sizeof(struct inotify_event);
-	struct inotify_kernel_event *kevent;
+	struct fsnotify_event *event;
 
-	if (list_empty(&dev->events))
+	if (fsnotify_notify_queue_is_empty(group))
 		return NULL;
 
-	kevent = inotify_dev_get_event(dev);
-	if (kevent->name)
-		event_size += kevent->event.len;
+	event = fsnotify_peek_notify_event(group);
+
+	event_size += roundup(event->name_len, event_size);
 
 	if (event_size > count)
 		return ERR_PTR(-EINVAL);
 
-	remove_kevent(dev, kevent);
-	return kevent;
+	/* held the notification_mutex the whole time, so this is the
+	 * same event we peeked above */
+	fsnotify_remove_notify_event(group);
+
+	return event;
 }
 
 /*
@@ -460,51 +176,90 @@ static struct inotify_kernel_event *get_one_event(struct inotify_device *dev,
  * We already checked that the event size is smaller than the
  * buffer we had in "get_one_event()" above.
  */
-static ssize_t copy_event_to_user(struct inotify_kernel_event *kevent,
+static ssize_t copy_event_to_user(struct fsnotify_group *group,
+				  struct fsnotify_event *event,
 				  char __user *buf)
 {
+	struct inotify_event inotify_event;
+	struct fsnotify_event_private_data *fsn_priv;
+	struct inotify_event_private_data *priv;
 	size_t event_size = sizeof(struct inotify_event);
+	size_t name_len;
 
-	if (copy_to_user(buf, &kevent->event, event_size))
+	/* we get the inotify watch descriptor from the event private data */
+	spin_lock(&event->lock);
+	fsn_priv = fsnotify_remove_priv_from_event(group, event);
+	spin_unlock(&event->lock);
+
+	if (!fsn_priv)
+		inotify_event.wd = -1;
+	else {
+		priv = container_of(fsn_priv, struct inotify_event_private_data,
+				    fsnotify_event_priv_data);
+		inotify_event.wd = priv->wd;
+		inotify_free_event_priv(fsn_priv);
+	}
+
+	/* round up event->name_len so it is a multiple of event_size */
+	name_len = roundup(event->name_len, event_size);
+	inotify_event.len = name_len;
+
+	inotify_event.mask = inotify_mask_to_arg(event->mask);
+	inotify_event.cookie = event->sync_cookie;
+
+	/* send the main event */
+	if (copy_to_user(buf, &inotify_event, event_size))
 		return -EFAULT;
 
-	if (kevent->name) {
-		buf += event_size;
+	buf += event_size;
 
-		if (copy_to_user(buf, kevent->name, kevent->event.len))
+	/*
+	 * fsnotify only stores the pathname, so here we have to send the pathname
+	 * and then pad that pathname out to a multiple of sizeof(inotify_event)
+	 * with zeros.  I get my zeros from the nul_inotify_event.
+	 */
+	if (name_len) {
+		unsigned int len_to_zero = name_len - event->name_len;
+		/* copy the path name */
+		if (copy_to_user(buf, event->file_name, event->name_len))
 			return -EFAULT;
+		buf += event->name_len;
 
-		event_size += kevent->event.len;
+		/* fill userspace with 0's from nul_inotify_event */
+		if (copy_to_user(buf, &nul_inotify_event, len_to_zero))
+			return -EFAULT;
+		buf += len_to_zero;
+		event_size += name_len;
 	}
+
 	return event_size;
 }
 
 static ssize_t inotify_read(struct file *file, char __user *buf,
 			    size_t count, loff_t *pos)
 {
-	struct inotify_device *dev;
+	struct fsnotify_group *group;
+	struct fsnotify_event *kevent;
 	char __user *start;
 	int ret;
 	DEFINE_WAIT(wait);
 
 	start = buf;
-	dev = file->private_data;
+	group = file->private_data;
 
 	while (1) {
-		struct inotify_kernel_event *kevent;
+		prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);
 
-		prepare_to_wait(&dev->wq, &wait, TASK_INTERRUPTIBLE);
-
-		mutex_lock(&dev->ev_mutex);
-		kevent = get_one_event(dev, count);
-		mutex_unlock(&dev->ev_mutex);
+		mutex_lock(&group->notification_mutex);
+		kevent = get_one_event(group, count);
+		mutex_unlock(&group->notification_mutex);
 
 		if (kevent) {
 			ret = PTR_ERR(kevent);
 			if (IS_ERR(kevent))
 				break;
-			ret = copy_event_to_user(kevent, buf);
-			free_kevent(kevent);
+			ret = copy_event_to_user(group, kevent, buf);
+			fsnotify_put_event(kevent);
 			if (ret < 0)
 				break;
 			buf += ret;
@@ -525,7 +280,7 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 		schedule();
 	}
 
-	finish_wait(&dev->wq, &wait);
+	finish_wait(&group->notification_waitq, &wait);
 	if (start != buf && ret != -EFAULT)
 		ret = buf - start;
 	return ret;
@@ -533,25 +288,19 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 
 static int inotify_fasync(int fd, struct file *file, int on)
 {
-	struct inotify_device *dev = file->private_data;
+	struct fsnotify_group *group = file->private_data;
 
-	return fasync_helper(fd, file, on, &dev->fa) >= 0 ? 0 : -EIO;
+	return fasync_helper(fd, file, on, &group->inotify_data.fa) >= 0 ? 0 : -EIO;
 }
 
 static int inotify_release(struct inode *ignored, struct file *file)
 {
-	struct inotify_device *dev = file->private_data;
+	struct fsnotify_group *group = file->private_data;
 
-	inotify_destroy(dev->ih);
+	fsnotify_clear_marks_by_group(group);
 
-	/* destroy all of the events on this device */
-	mutex_lock(&dev->ev_mutex);
-	while (!list_empty(&dev->events))
-		inotify_dev_event_dequeue(dev);
-	mutex_unlock(&dev->ev_mutex);
-
-	/* free this device: the put matching the get in inotify_init() */
-	put_inotify_dev(dev);
+	/* free this group, matching get was inotify_init->fsnotify_obtain_group */
+	fsnotify_put_group(group);
 
 	return 0;
 }
@@ -559,16 +308,27 @@ static int inotify_release(struct inode *ignored, struct file *file)
 static long inotify_ioctl(struct file *file, unsigned int cmd,
 			  unsigned long arg)
 {
-	struct inotify_device *dev;
+	struct fsnotify_group *group;
+	struct fsnotify_event_holder *holder;
+	struct fsnotify_event *event;
 	void __user *p;
 	int ret = -ENOTTY;
+	size_t send_len = 0;
 
-	dev = file->private_data;
+	group = file->private_data;
 	p = (void __user *) arg;
 
 	switch (cmd) {
 	case FIONREAD:
-		ret = put_user(dev->queue_size, (int __user *) p);
+		mutex_lock(&group->notification_mutex);
+		list_for_each_entry(holder, &group->notification_list, event_list) {
+			event = holder->event;
+			send_len += sizeof(struct inotify_event);
+			send_len += roundup(event->name_len,
+					     sizeof(struct inotify_event));
+		}
+		mutex_unlock(&group->notification_mutex);
+		ret = put_user(send_len, (int __user *) p);
 		break;
 	}
 
@@ -576,23 +336,233 @@ static long inotify_ioctl(struct file *file, unsigned int cmd,
 }
 
 static const struct file_operations inotify_fops = {
-	.poll           = inotify_poll,
-	.read           = inotify_read,
-	.fasync         = inotify_fasync,
-	.release        = inotify_release,
-	.unlocked_ioctl = inotify_ioctl,
+	.poll		= inotify_poll,
+	.read		= inotify_read,
+	.fasync		= inotify_fasync,
+	.release	= inotify_release,
+	.unlocked_ioctl	= inotify_ioctl,
 	.compat_ioctl	= inotify_ioctl,
 };
 
-static const struct inotify_operations inotify_user_ops = {
-	.handle_event	= inotify_dev_queue_event,
-	.destroy_watch	= free_inotify_user_watch,
-};
 
+/*
+ * find_inode - resolve a user-given path to a specific inode
+ */
+static int inotify_find_inode(const char __user *dirname, struct path *path, unsigned flags)
+{
+	int error;
+
+	error = user_path_at(AT_FDCWD, dirname, flags, path);
+	if (error)
+		return error;
+	/* you can only watch an inode if you have read permissions on it */
+	error = inode_permission(path->dentry->d_inode, MAY_READ);
+	if (error)
+		path_put(path);
+	return error;
+}
+
+/*
+ * When, for whatever reason, inotify is done with a mark (or what used to be a
+ * watch) we need to remove that watch from the idr and we need to send IN_IGNORED
+ * for the given wd.
+ *
+ * There is a bit of recursion here.  The loop looks like:
+ * 	inotify_destroy_mark_entry -> fsnotify_destroy_mark_by_entry ->
+ *	inotify_freeing_mark -> inotify_destory_mark_entry -> restart
+ * But the loop is broken in 2 places.  fsnotify_destroy_mark_by_entry sets
+ * entry->group = NULL before the call to inotify_freeing_mark, so the if (egroup)
+ * test below will not call back to fsnotify again.  But even if that test wasn't
+ * there this would still be safe since fsnotify_destroy_mark_by_entry() is
+ * safe from recursion.
+ */
+void inotify_destroy_mark_entry(struct fsnotify_mark_entry *entry, struct fsnotify_group *group)
+{
+	struct inotify_inode_mark_entry *ientry;
+	struct inotify_event_private_data *event_priv;
+	struct fsnotify_event_private_data *fsn_event_priv;
+	struct fsnotify_group *egroup;
+	struct idr *idr;
+
+	spin_lock(&entry->lock);
+	egroup = entry->group;
+
+	/* if egroup we aren't really done and something might still send events
+	 * for this inode, on the callback we'll send the IN_IGNORED */
+	if (egroup) {
+		spin_unlock(&entry->lock);
+		fsnotify_destroy_mark_by_entry(entry);
+		return;
+	}
+	spin_unlock(&entry->lock);
+
+	ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
+
+	event_priv = kmem_cache_alloc(event_priv_cachep, GFP_KERNEL);
+	if (unlikely(!event_priv))
+		goto skip_send_ignore;
+
+	fsn_event_priv = &event_priv->fsnotify_event_priv_data;
+
+	fsn_event_priv->group = group;
+	event_priv->wd = ientry->wd;
+
+	fsnotify_add_notify_event(group, inotify_ignored_event, fsn_event_priv);
+
+	/* did the private data get added? */
+	if (list_empty(&fsn_event_priv->event_list))
+		inotify_free_event_priv(fsn_event_priv);
+
+skip_send_ignore:
+
+	/* remove this entry from the idr */
+	spin_lock(&group->inotify_data.idr_lock);
+	idr = &group->inotify_data.idr;
+	idr_remove(idr, ientry->wd);
+	spin_unlock(&group->inotify_data.idr_lock);
+
+	/* removed from idr, drop that reference */
+	fsnotify_put_mark(entry);
+}
+
+/* ding dong the mark is dead */
+static void inotify_free_mark(struct fsnotify_mark_entry *entry)
+{
+	struct inotify_inode_mark_entry *ientry = (struct inotify_inode_mark_entry *)entry;
+
+	kmem_cache_free(inotify_inode_mark_cachep, ientry);
+}
+
+static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
+{
+	struct fsnotify_mark_entry *entry = NULL;
+	struct inotify_inode_mark_entry *ientry;
+	int ret = 0;
+	int add = (arg & IN_MASK_ADD);
+	__u32 mask;
+	__u32 old_mask, new_mask;
+
+	/* don't allow invalid bits: we don't want flags set */
+	mask = inotify_arg_to_mask(arg);
+	if (unlikely(!mask))
+		return -EINVAL;
+
+	ientry = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
+	if (unlikely(!ientry))
+		return -ENOMEM;
+	/* we set the mask at the end after attaching it */
+	fsnotify_init_mark(&ientry->fsn_entry, inotify_free_mark);
+	ientry->wd = 0;
+
+find_entry:
+	spin_lock(&inode->i_lock);
+	entry = fsnotify_find_mark_entry(group, inode);
+	spin_unlock(&inode->i_lock);
+	if (entry) {
+		kmem_cache_free(inotify_inode_mark_cachep, ientry);
+		ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
+	} else {
+		if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches) {
+			ret = -ENOSPC;
+			goto out_err;
+		}
+
+		ret = fsnotify_add_mark(&ientry->fsn_entry, group, inode);
+		if (ret == -EEXIST)
+			goto find_entry;
+		else if (ret)
+			goto out_err;
+
+		entry = &ientry->fsn_entry;
+retry:
+		ret = -ENOMEM;
+		if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
+			goto out_err;
+
+		spin_lock(&group->inotify_data.idr_lock);
+		/* if entry is added to the idr we keep the reference obtained
+		 * through fsnotify_mark_add.  remember to drop this reference
+		 * when entry is removed from idr */
+		ret = idr_get_new_above(&group->inotify_data.idr, entry,
+					++group->inotify_data.last_wd,
+					&ientry->wd);
+		spin_unlock(&group->inotify_data.idr_lock);
+		if (ret) {
+			if (ret == -EAGAIN)
+				goto retry;
+			goto out_err;
+		}
+		atomic_inc(&group->inotify_data.user->inotify_watches);
+	}
+
+	spin_lock(&entry->lock);
+
+	old_mask = entry->mask;
+	if (add) {
+		entry->mask |= mask;
+		new_mask = entry->mask;
+	} else {
+		entry->mask = mask;
+		new_mask = entry->mask;
+	}
+
+	spin_unlock(&entry->lock);
+
+	if (old_mask != new_mask) {
+		/* more bits in old than in new? */
+		int dropped = (old_mask & ~new_mask);
+		/* more bits in this entry than the inode's mask? */
+		int do_inode = (new_mask & ~inode->i_fsnotify_mask);
+		/* more bits in this entry than the group? */
+		int do_group = (new_mask & ~group->mask);
+
+		/* update the inode with this new entry */
+		if (dropped || do_inode)
+			fsnotify_recalc_inode_mask(inode);
+
+		/* update the group mask with the new mask */
+		if (dropped || do_group)
+			fsnotify_recalc_group_mask(group);
+	}
+
+	return ientry->wd;
+
+out_err:
+	/* see this isn't supposed to happen, just kill the watch */
+	if (entry) {
+		fsnotify_destroy_mark_by_entry(entry);
+		fsnotify_put_mark(entry);
+	}
+	return ret;
+}
+
+static struct fsnotify_group *inotify_new_group(struct user_struct *user, unsigned int max_events)
+{
+	struct fsnotify_group *group;
+	unsigned int grp_num;
+
+	/* fsnotify_obtain_group took a reference to group, we put this when we kill the file in the end */
+	grp_num = (INOTIFY_GROUP_NUM - atomic_inc_return(&inotify_grp_num));
+	group = fsnotify_obtain_group(grp_num, 0, &inotify_fsnotify_ops);
+	if (IS_ERR(group))
+		return group;
+
+	group->max_events = max_events;
+
+	spin_lock_init(&group->inotify_data.idr_lock);
+	idr_init(&group->inotify_data.idr);
+	group->inotify_data.last_wd = 0;
+	group->inotify_data.user = user;
+	group->inotify_data.fa = NULL;
+
+	return group;
+}
+
+
+/* inotify syscalls */
 SYSCALL_DEFINE1(inotify_init1, int, flags)
 {
-	struct inotify_device *dev;
-	struct inotify_handle *ih;
+	struct fsnotify_group *group;
 	struct user_struct *user;
 	struct file *filp;
 	int fd, ret;
@@ -621,45 +591,27 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
 		goto out_free_uid;
 	}
 
-	dev = kmalloc(sizeof(struct inotify_device), GFP_KERNEL);
-	if (unlikely(!dev)) {
-		ret = -ENOMEM;
+	/* fsnotify_obtain_group took a reference to group, we put this when we kill the file in the end */
+	group = inotify_new_group(user, inotify_max_queued_events);
+	if (IS_ERR(group)) {
+		ret = PTR_ERR(group);
 		goto out_free_uid;
 	}
 
-	ih = inotify_init(&inotify_user_ops);
-	if (IS_ERR(ih)) {
-		ret = PTR_ERR(ih);
-		goto out_free_dev;
-	}
-	dev->ih = ih;
-	dev->fa = NULL;
-
 	filp->f_op = &inotify_fops;
 	filp->f_path.mnt = mntget(inotify_mnt);
 	filp->f_path.dentry = dget(inotify_mnt->mnt_root);
 	filp->f_mapping = filp->f_path.dentry->d_inode->i_mapping;
 	filp->f_mode = FMODE_READ;
 	filp->f_flags = O_RDONLY | (flags & O_NONBLOCK);
-	filp->private_data = dev;
+	filp->private_data = group;
 
-	INIT_LIST_HEAD(&dev->events);
-	init_waitqueue_head(&dev->wq);
-	mutex_init(&dev->ev_mutex);
-	mutex_init(&dev->up_mutex);
-	dev->event_count = 0;
-	dev->queue_size = 0;
-	dev->max_events = inotify_max_queued_events;
-	dev->user = user;
-	atomic_set(&dev->count, 0);
-
-	get_inotify_dev(dev);
 	atomic_inc(&user->inotify_devs);
+
 	fd_install(fd, filp);
 
 	return fd;
-out_free_dev:
-	kfree(dev);
+
 out_free_uid:
 	free_uid(user);
 	put_filp(filp);
@@ -676,8 +628,8 @@ SYSCALL_DEFINE0(inotify_init)
 SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 		u32, mask)
 {
+	struct fsnotify_group *group;
 	struct inode *inode;
-	struct inotify_device *dev;
 	struct path path;
 	struct file *filp;
 	int ret, fput_needed;
@@ -698,20 +650,20 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 	if (mask & IN_ONLYDIR)
 		flags |= LOOKUP_DIRECTORY;
 
-	ret = find_inode(pathname, &path, flags);
-	if (unlikely(ret))
+	ret = inotify_find_inode(pathname, &path, flags);
+	if (ret)
 		goto fput_and_out;
 
-	/* inode held in place by reference to path; dev by fget on fd */
+	/* inode held in place by reference to path; group by fget on fd */
 	inode = path.dentry->d_inode;
-	dev = filp->private_data;
+	group = filp->private_data;
 
-	mutex_lock(&dev->up_mutex);
-	ret = inotify_find_update_watch(dev->ih, inode, mask);
-	if (ret == -ENOENT)
-		ret = create_watch(dev, inode, mask);
-	mutex_unlock(&dev->up_mutex);
+	/* create/update an inode mark */
+	ret = inotify_update_watch(group, inode, mask);
+	if (unlikely(ret))
+		goto path_put_and_out;
 
+path_put_and_out:
 	path_put(&path);
 fput_and_out:
 	fput_light(filp, fput_needed);
@@ -720,9 +672,10 @@ fput_and_out:
 
 SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
 {
+	struct fsnotify_group *group;
+	struct fsnotify_mark_entry *entry;
 	struct file *filp;
-	struct inotify_device *dev;
-	int ret, fput_needed;
+	int ret = 0, fput_needed;
 
 	filp = fget_light(fd, &fput_needed);
 	if (unlikely(!filp))
@@ -734,10 +687,20 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
 		goto out;
 	}
 
-	dev = filp->private_data;
+	group = filp->private_data;
 
-	/* we free our watch data when we get IN_IGNORED */
-	ret = inotify_rm_wd(dev->ih, wd);
+	spin_lock(&group->inotify_data.idr_lock);
+	entry = idr_find(&group->inotify_data.idr, wd);
+	if (unlikely(!entry)) {
+		spin_unlock(&group->inotify_data.idr_lock);
+		ret = -EINVAL;
+		goto out;
+	}
+	fsnotify_get_mark(entry);
+	spin_unlock(&group->inotify_data.idr_lock);
+
+	inotify_destroy_mark_entry(entry, group);
+	fsnotify_put_mark(entry);
 
 out:
 	fput_light(filp, fput_needed);
@@ -753,9 +716,9 @@ inotify_get_sb(struct file_system_type *fs_type, int flags,
 }
 
 static struct file_system_type inotify_fs_type = {
-    .name           = "inotifyfs",
-    .get_sb         = inotify_get_sb,
-    .kill_sb        = kill_anon_super,
+    .name	= "inotifyfs",
+    .get_sb	= inotify_get_sb,
+    .kill_sb	= kill_anon_super,
 };
 
 /*
@@ -775,18 +738,16 @@ static int __init inotify_user_setup(void)
 	if (IS_ERR(inotify_mnt))
 		panic("inotify: kern_mount ret %ld!\n", PTR_ERR(inotify_mnt));
 
+	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark_entry, SLAB_PANIC);
+	event_priv_cachep = KMEM_CACHE(inotify_event_private_data, SLAB_PANIC);
+	inotify_ignored_event = fsnotify_create_event(NULL, FS_IN_IGNORED, NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
+	if (!inotify_ignored_event)
+		panic("unable to allocate the inotify ignored event\n");
+
 	inotify_max_queued_events = 16384;
 	inotify_max_user_instances = 128;
 	inotify_max_user_watches = 8192;
 
-	watch_cachep = kmem_cache_create("inotify_watch_cache",
-					 sizeof(struct inotify_user_watch),
-					 0, SLAB_PANIC, NULL);
-	event_cachep = kmem_cache_create("inotify_event_cache",
-					 sizeof(struct inotify_kernel_event),
-					 0, SLAB_PANIC, NULL);
-
 	return 0;
 }
-
 module_init(inotify_user_setup);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
new file mode 100644
index 000000000000..959b73e756fd
--- /dev/null
+++ b/fs/notify/notification.c
@@ -0,0 +1,411 @@
+/*
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2, or (at your option)
+ *  any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; see the file COPYING.  If not, write to
+ *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * Basic idea behind the notification queue: An fsnotify group (like inotify)
+ * sends the userspace notification about events asyncronously some time after
+ * the event happened.  When inotify gets an event it will need to add that
+ * event to the group notify queue.  Since a single event might need to be on
+ * multiple group's notification queues we can't add the event directly to each
+ * queue and instead add a small "event_holder" to each queue.  This event_holder
+ * has a pointer back to the original event.  Since the majority of events are
+ * going to end up on one, and only one, notification queue we embed one
+ * event_holder into each event.  This means we have a single allocation instead
+ * of always needing two.  If the embedded event_holder is already in use by
+ * another group a new event_holder (from fsnotify_event_holder_cachep) will be
+ * allocated and used.
+ */
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/mutex.h>
+#include <linux/namei.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <asm/atomic.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+static struct kmem_cache *fsnotify_event_cachep;
+static struct kmem_cache *fsnotify_event_holder_cachep;
+/*
+ * This is a magic event we send when the q is too full.  Since it doesn't
+ * hold real event information we just keep one system wide and use it any time
+ * it is needed.  It's refcnt is set 1 at kernel init time and will never
+ * get set to 0 so it will never get 'freed'
+ */
+static struct fsnotify_event q_overflow_event;
+static atomic_t fsnotify_sync_cookie = ATOMIC_INIT(0);
+
+/**
+ * fsnotify_get_cookie - return a unique cookie for use in synchronizing events.
+ * Called from fsnotify_move, which is inlined into filesystem modules.
+ */
+u32 fsnotify_get_cookie(void)
+{
+	return atomic_inc_return(&fsnotify_sync_cookie);
+}
+EXPORT_SYMBOL_GPL(fsnotify_get_cookie);
+
+/* return true if the notify queue is empty, false otherwise */
+bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group)
+{
+	BUG_ON(!mutex_is_locked(&group->notification_mutex));
+	return list_empty(&group->notification_list) ? true : false;
+}
+
+void fsnotify_get_event(struct fsnotify_event *event)
+{
+	atomic_inc(&event->refcnt);
+}
+
+void fsnotify_put_event(struct fsnotify_event *event)
+{
+	if (!event)
+		return;
+
+	if (atomic_dec_and_test(&event->refcnt)) {
+		if (event->data_type == FSNOTIFY_EVENT_PATH)
+			path_put(&event->path);
+
+		BUG_ON(!list_empty(&event->private_data_list));
+
+		kfree(event->file_name);
+		kmem_cache_free(fsnotify_event_cachep, event);
+	}
+}
+
+struct fsnotify_event_holder *fsnotify_alloc_event_holder(void)
+{
+	return kmem_cache_alloc(fsnotify_event_holder_cachep, GFP_KERNEL);
+}
+
+void fsnotify_destroy_event_holder(struct fsnotify_event_holder *holder)
+{
+	kmem_cache_free(fsnotify_event_holder_cachep, holder);
+}
+
+/*
+ * Find the private data that the group previously attached to this event when
+ * the group added the event to the notification queue (fsnotify_add_notify_event)
+ */
+struct fsnotify_event_private_data *fsnotify_remove_priv_from_event(struct fsnotify_group *group, struct fsnotify_event *event)
+{
+	struct fsnotify_event_private_data *lpriv;
+	struct fsnotify_event_private_data *priv = NULL;
+
+	assert_spin_locked(&event->lock);
+
+	list_for_each_entry(lpriv, &event->private_data_list, event_list) {
+		if (lpriv->group == group) {
+			priv = lpriv;
+			list_del(&priv->event_list);
+			break;
+		}
+	}
+	return priv;
+}
+
+/*
+ * Check if 2 events contain the same information.  We do not compare private data
+ * but at this moment that isn't a problem for any know fsnotify listeners.
+ */
+static bool event_compare(struct fsnotify_event *old, struct fsnotify_event *new)
+{
+	if ((old->mask == new->mask) &&
+	    (old->to_tell == new->to_tell) &&
+	    (old->data_type == new->data_type)) {
+		switch (old->data_type) {
+		case (FSNOTIFY_EVENT_INODE):
+			if (old->inode == new->inode)
+				return true;
+			break;
+		case (FSNOTIFY_EVENT_PATH):
+			if ((old->path.mnt == new->path.mnt) &&
+			    (old->path.dentry == new->path.dentry))
+				return true;
+		case (FSNOTIFY_EVENT_NONE):
+			return true;
+		};
+	}
+	return false;
+}
+
+/*
+ * Add an event to the group notification queue.  The group can later pull this
+ * event off the queue to deal with.  If the event is successfully added to the
+ * group's notification queue, a reference is taken on event.
+ */
+int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_event *event,
+			      struct fsnotify_event_private_data *priv)
+{
+	struct fsnotify_event_holder *holder = NULL;
+	struct list_head *list = &group->notification_list;
+	struct fsnotify_event_holder *last_holder;
+	struct fsnotify_event *last_event;
+
+	/* easy to tell if priv was attached to the event */
+	INIT_LIST_HEAD(&priv->event_list);
+
+	/*
+	 * There is one fsnotify_event_holder embedded inside each fsnotify_event.
+	 * Check if we expect to be able to use that holder.  If not alloc a new
+	 * holder.
+	 * For the overflow event it's possible that something will use the in
+	 * event holder before we get the lock so we may need to jump back and
+	 * alloc a new holder, this can't happen for most events...
+	 */
+	if (!list_empty(&event->holder.event_list)) {
+alloc_holder:
+		holder = fsnotify_alloc_event_holder();
+		if (!holder)
+			return -ENOMEM;
+	}
+
+	mutex_lock(&group->notification_mutex);
+
+	if (group->q_len >= group->max_events) {
+		event = &q_overflow_event;
+		/* sorry, no private data on the overflow event */
+		priv = NULL;
+	}
+
+	spin_lock(&event->lock);
+
+	if (list_empty(&event->holder.event_list)) {
+		if (unlikely(holder))
+			fsnotify_destroy_event_holder(holder);
+		holder = &event->holder;
+	} else if (unlikely(!holder)) {
+		/* between the time we checked above and got the lock the in
+		 * event holder was used, go back and get a new one */
+		spin_unlock(&event->lock);
+		mutex_unlock(&group->notification_mutex);
+		goto alloc_holder;
+	}
+
+	if (!list_empty(list)) {
+		last_holder = list_entry(list->prev, struct fsnotify_event_holder, event_list);
+		last_event = last_holder->event;
+		if (event_compare(last_event, event)) {
+			spin_unlock(&event->lock);
+			mutex_unlock(&group->notification_mutex);
+			if (holder != &event->holder)
+				fsnotify_destroy_event_holder(holder);
+			return -EEXIST;
+		}
+	}
+
+	group->q_len++;
+	holder->event = event;
+
+	fsnotify_get_event(event);
+	list_add_tail(&holder->event_list, list);
+	if (priv)
+		list_add_tail(&priv->event_list, &event->private_data_list);
+	spin_unlock(&event->lock);
+	mutex_unlock(&group->notification_mutex);
+
+	wake_up(&group->notification_waitq);
+	return 0;
+}
+
+/*
+ * Remove and return the first event from the notification list.  There is a
+ * reference held on this event since it was on the list.  It is the responsibility
+ * of the caller to drop this reference.
+ */
+struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group)
+{
+	struct fsnotify_event *event;
+	struct fsnotify_event_holder *holder;
+
+	BUG_ON(!mutex_is_locked(&group->notification_mutex));
+
+	holder = list_first_entry(&group->notification_list, struct fsnotify_event_holder, event_list);
+
+	event = holder->event;
+
+	spin_lock(&event->lock);
+	holder->event = NULL;
+	list_del_init(&holder->event_list);
+	spin_unlock(&event->lock);
+
+	/* event == holder means we are referenced through the in event holder */
+	if (holder != &event->holder)
+		fsnotify_destroy_event_holder(holder);
+
+	group->q_len--;
+
+	return event;
+}
+
+/*
+ * This will not remove the event, that must be done with fsnotify_remove_notify_event()
+ */
+struct fsnotify_event *fsnotify_peek_notify_event(struct fsnotify_group *group)
+{
+	struct fsnotify_event *event;
+	struct fsnotify_event_holder *holder;
+
+	BUG_ON(!mutex_is_locked(&group->notification_mutex));
+
+	holder = list_first_entry(&group->notification_list, struct fsnotify_event_holder, event_list);
+	event = holder->event;
+
+	return event;
+}
+
+/*
+ * Called when a group is being torn down to clean up any outstanding
+ * event notifications.
+ */
+void fsnotify_flush_notify(struct fsnotify_group *group)
+{
+	struct fsnotify_event *event;
+	struct fsnotify_event_private_data *priv;
+
+	mutex_lock(&group->notification_mutex);
+	while (!fsnotify_notify_queue_is_empty(group)) {
+		event = fsnotify_remove_notify_event(group);
+		/* if they don't implement free_event_priv they better not have attached any */
+		if (group->ops->free_event_priv) {
+			spin_lock(&event->lock);
+			priv = fsnotify_remove_priv_from_event(group, event);
+			spin_unlock(&event->lock);
+			if (priv)
+				group->ops->free_event_priv(priv);
+		}
+		fsnotify_put_event(event); /* matches fsnotify_add_notify_event */
+	}
+	mutex_unlock(&group->notification_mutex);
+}
+
+static void initialize_event(struct fsnotify_event *event)
+{
+	event->holder.event = NULL;
+	INIT_LIST_HEAD(&event->holder.event_list);
+	atomic_set(&event->refcnt, 1);
+
+	spin_lock_init(&event->lock);
+
+	event->path.dentry = NULL;
+	event->path.mnt = NULL;
+	event->inode = NULL;
+	event->data_type = FSNOTIFY_EVENT_NONE;
+
+	INIT_LIST_HEAD(&event->private_data_list);
+
+	event->to_tell = NULL;
+
+	event->file_name = NULL;
+	event->name_len = 0;
+
+	event->sync_cookie = 0;
+}
+
+/*
+ * fsnotify_create_event - Allocate a new event which will be sent to each
+ * group's handle_event function if the group was interested in this
+ * particular event.
+ *
+ * @to_tell the inode which is supposed to receive the event (sometimes a
+ *	parent of the inode to which the event happened.
+ * @mask what actually happened.
+ * @data pointer to the object which was actually affected
+ * @data_type flag indication if the data is a file, path, inode, nothing...
+ * @name the filename, if available
+ */
+struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 mask, void *data,
+					     int data_type, const char *name, u32 cookie)
+{
+	struct fsnotify_event *event;
+
+	event = kmem_cache_alloc(fsnotify_event_cachep, GFP_KERNEL);
+	if (!event)
+		return NULL;
+
+	initialize_event(event);
+
+	if (name) {
+		event->file_name = kstrdup(name, GFP_KERNEL);
+		if (!event->file_name) {
+			kmem_cache_free(fsnotify_event_cachep, event);
+			return NULL;
+		}
+		event->name_len = strlen(event->file_name);
+	}
+
+	event->sync_cookie = cookie;
+	event->to_tell = to_tell;
+
+	switch (data_type) {
+	case FSNOTIFY_EVENT_FILE: {
+		struct file *file = data;
+		struct path *path = &file->f_path;
+		event->path.dentry = path->dentry;
+		event->path.mnt = path->mnt;
+		path_get(&event->path);
+		event->data_type = FSNOTIFY_EVENT_PATH;
+		break;
+	}
+	case FSNOTIFY_EVENT_PATH: {
+		struct path *path = data;
+		event->path.dentry = path->dentry;
+		event->path.mnt = path->mnt;
+		path_get(&event->path);
+		event->data_type = FSNOTIFY_EVENT_PATH;
+		break;
+	}
+	case FSNOTIFY_EVENT_INODE:
+		event->inode = data;
+		event->data_type = FSNOTIFY_EVENT_INODE;
+		break;
+	case FSNOTIFY_EVENT_NONE:
+		event->inode = NULL;
+		event->path.dentry = NULL;
+		event->path.mnt = NULL;
+		break;
+	default:
+		BUG();
+	}
+
+	event->mask = mask;
+
+	return event;
+}
+
+__init int fsnotify_notification_init(void)
+{
+	fsnotify_event_cachep = KMEM_CACHE(fsnotify_event, SLAB_PANIC);
+	fsnotify_event_holder_cachep = KMEM_CACHE(fsnotify_event_holder, SLAB_PANIC);
+
+	initialize_event(&q_overflow_event);
+	q_overflow_event.mask = FS_Q_OVERFLOW;
+
+	return 0;
+}
+subsys_initcall(fsnotify_notification_init);
+
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index f76951dcd4a6..abaaa1cbf8de 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -25,7 +25,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
-#include <linux/blkdev.h>	/* For bdev_hardsect_size(). */
+#include <linux/blkdev.h>	/* For bdev_logical_block_size(). */
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
@@ -443,6 +443,8 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
 	ntfs_volume *vol = NTFS_SB(sb);
 
 	ntfs_debug("Entering with remount options string: %s", opt);
+
+	lock_kernel();
 #ifndef NTFS_RW
 	/* For read-only compiled driver, enforce read-only flag. */
 	*flags |= MS_RDONLY;
@@ -466,15 +468,18 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
 		if (NVolErrors(vol)) {
 			ntfs_error(sb, "Volume has errors and is read-only%s",
 					es);
+			unlock_kernel();
 			return -EROFS;
 		}
 		if (vol->vol_flags & VOLUME_IS_DIRTY) {
 			ntfs_error(sb, "Volume is dirty and read-only%s", es);
+			unlock_kernel();
 			return -EROFS;
 		}
 		if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
 			ntfs_error(sb, "Volume has been modified by chkdsk "
 					"and is read-only%s", es);
+			unlock_kernel();
 			return -EROFS;
 		}
 		if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
@@ -482,11 +487,13 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
 					"(0x%x) and is read-only%s",
 					(unsigned)le16_to_cpu(vol->vol_flags),
 					es);
+			unlock_kernel();
 			return -EROFS;
 		}
 		if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
 			ntfs_error(sb, "Failed to set dirty bit in volume "
 					"information flags%s", es);
+			unlock_kernel();
 			return -EROFS;
 		}
 #if 0
@@ -506,18 +513,21 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
 			ntfs_error(sb, "Failed to empty journal $LogFile%s",
 					es);
 			NVolSetErrors(vol);
+			unlock_kernel();
 			return -EROFS;
 		}
 		if (!ntfs_mark_quotas_out_of_date(vol)) {
 			ntfs_error(sb, "Failed to mark quotas out of date%s",
 					es);
 			NVolSetErrors(vol);
+			unlock_kernel();
 			return -EROFS;
 		}
 		if (!ntfs_stamp_usnjrnl(vol)) {
 			ntfs_error(sb, "Failed to stamp transation log "
 					"($UsnJrnl)%s", es);
 			NVolSetErrors(vol);
+			unlock_kernel();
 			return -EROFS;
 		}
 	} else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) {
@@ -533,8 +543,11 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
 
 	// TODO: Deal with *flags.
 
-	if (!parse_options(vol, opt))
+	if (!parse_options(vol, opt)) {
+		unlock_kernel();
 		return -EINVAL;
+	}
+	unlock_kernel();
 	ntfs_debug("Done.");
 	return 0;
 }
@@ -2246,6 +2259,9 @@ static void ntfs_put_super(struct super_block *sb)
 	ntfs_volume *vol = NTFS_SB(sb);
 
 	ntfs_debug("Entering.");
+
+	lock_kernel();
+
 #ifdef NTFS_RW
 	/*
 	 * Commit all inodes while they are still open in case some of them
@@ -2373,39 +2389,12 @@ static void ntfs_put_super(struct super_block *sb)
 		vol->mftmirr_ino = NULL;
 	}
 	/*
-	 * If any dirty inodes are left, throw away all mft data page cache
-	 * pages to allow a clean umount.  This should never happen any more
-	 * due to mft.c::ntfs_mft_writepage() cleaning all the dirty pages as
-	 * the underlying mft records are written out and cleaned.  If it does,
-	 * happen anyway, we want to know...
+	 * We should have no dirty inodes left, due to
+	 * mft.c::ntfs_mft_writepage() cleaning all the dirty pages as
+	 * the underlying mft records are written out and cleaned.
 	 */
 	ntfs_commit_inode(vol->mft_ino);
 	write_inode_now(vol->mft_ino, 1);
-	if (sb_has_dirty_inodes(sb)) {
-		const char *s1, *s2;
-
-		mutex_lock(&vol->mft_ino->i_mutex);
-		truncate_inode_pages(vol->mft_ino->i_mapping, 0);
-		mutex_unlock(&vol->mft_ino->i_mutex);
-		write_inode_now(vol->mft_ino, 1);
-		if (sb_has_dirty_inodes(sb)) {
-			static const char *_s1 = "inodes";
-			static const char *_s2 = "";
-			s1 = _s1;
-			s2 = _s2;
-		} else {
-			static const char *_s1 = "mft pages";
-			static const char *_s2 = "They have been thrown "
-					"away.  ";
-			s1 = _s1;
-			s2 = _s2;
-		}
-		ntfs_error(sb, "Dirty %s found at umount time.  %sYou should "
-				"run chkdsk.  Please email "
-				"linux-ntfs-dev@lists.sourceforge.net and say "
-				"that you saw this message.  Thank you.", s1,
-				s2);
-	}
 #endif /* NTFS_RW */
 
 	iput(vol->mft_ino);
@@ -2444,7 +2433,8 @@ static void ntfs_put_super(struct super_block *sb)
 	}
 	sb->s_fs_info = NULL;
 	kfree(vol);
-	return;
+
+	unlock_kernel();
 }
 
 /**
@@ -2785,13 +2775,13 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
 		goto err_out_now;
 
 	/* We support sector sizes up to the PAGE_CACHE_SIZE. */
-	if (bdev_hardsect_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
+	if (bdev_logical_block_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
 		if (!silent)
 			ntfs_error(sb, "Device has unsupported sector size "
 					"(%i).  The maximum supported sector "
 					"size on this architecture is %lu "
 					"bytes.",
-					bdev_hardsect_size(sb->s_bdev),
+					bdev_logical_block_size(sb->s_bdev),
 					PAGE_CACHE_SIZE);
 		goto err_out_now;
 	}
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 4f85eceab376..09cc25d04611 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1371,7 +1371,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 
 	bdevname(reg->hr_bdev, reg->hr_dev_name);
 
-	sectsize = bdev_hardsect_size(reg->hr_bdev);
+	sectsize = bdev_logical_block_size(reg->hr_bdev);
 	if (sectsize != reg->hr_block_bytes) {
 		mlog(ML_ERROR,
 		     "blocksize %u incorrect for device, expected %d",
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 79ff8d9d37e0..201b40a441fe 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -42,6 +42,7 @@
 #include <linux/mount.h>
 #include <linux/seq_file.h>
 #include <linux/quotaops.h>
+#include <linux/smp_lock.h>
 
 #define MLOG_MASK_PREFIX ML_SUPER
 #include <cluster/masklog.h>
@@ -126,7 +127,6 @@ static int ocfs2_get_sector(struct super_block *sb,
 			    struct buffer_head **bh,
 			    int block,
 			    int sect_size);
-static void ocfs2_write_super(struct super_block *sb);
 static struct inode *ocfs2_alloc_inode(struct super_block *sb);
 static void ocfs2_destroy_inode(struct inode *inode);
 static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend);
@@ -141,7 +141,6 @@ static const struct super_operations ocfs2_sops = {
 	.clear_inode	= ocfs2_clear_inode,
 	.delete_inode	= ocfs2_delete_inode,
 	.sync_fs	= ocfs2_sync_fs,
-	.write_super	= ocfs2_write_super,
 	.put_super	= ocfs2_put_super,
 	.remount_fs	= ocfs2_remount,
 	.show_options   = ocfs2_show_options,
@@ -365,24 +364,12 @@ static struct file_operations ocfs2_osb_debug_fops = {
 	.llseek =	generic_file_llseek,
 };
 
-/*
- * write_super and sync_fs ripped right out of ext3.
- */
-static void ocfs2_write_super(struct super_block *sb)
-{
-	if (mutex_trylock(&sb->s_lock) != 0)
-		BUG();
-	sb->s_dirt = 0;
-}
-
 static int ocfs2_sync_fs(struct super_block *sb, int wait)
 {
 	int status;
 	tid_t target;
 	struct ocfs2_super *osb = OCFS2_SB(sb);
 
-	sb->s_dirt = 0;
-
 	if (ocfs2_is_hard_readonly(osb))
 		return -EROFS;
 
@@ -595,6 +582,8 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
 	struct mount_options parsed_options;
 	struct ocfs2_super *osb = OCFS2_SB(sb);
 
+	lock_kernel();
+
 	if (!ocfs2_parse_options(sb, data, &parsed_options, 1)) {
 		ret = -EINVAL;
 		goto out;
@@ -698,6 +687,7 @@ unlock_osb:
 			ocfs2_set_journal_params(osb);
 	}
 out:
+	unlock_kernel();
 	return ret;
 }
 
@@ -713,7 +703,7 @@ static int ocfs2_sb_probe(struct super_block *sb,
 	*bh = NULL;
 
 	/* may be > 512 */
-	*sector_size = bdev_hardsect_size(sb->s_bdev);
+	*sector_size = bdev_logical_block_size(sb->s_bdev);
 	if (*sector_size > OCFS2_MAX_BLOCKSIZE) {
 		mlog(ML_ERROR, "Hardware sector size too large: %d (max=%d)\n",
 		     *sector_size, OCFS2_MAX_BLOCKSIZE);
@@ -1550,9 +1540,13 @@ static void ocfs2_put_super(struct super_block *sb)
 {
 	mlog_entry("(0x%p)\n", sb);
 
+	lock_kernel();
+
 	ocfs2_sync_blockdev(sb);
 	ocfs2_dismount_volume(sb, 0);
 
+	unlock_kernel();
+
 	mlog_exit_void();
 }
 
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index 834b2331f6b3..d17e774eaf45 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -11,21 +11,6 @@
 #include <linux/mpage.h>
 #include "omfs.h"
 
-static int omfs_sync_file(struct file *file, struct dentry *dentry,
-		int datasync)
-{
-	struct inode *inode = dentry->d_inode;
-	int err;
-
-	err = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY))
-		return err;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		return err;
-	err |= omfs_sync_inode(inode);
-	return err ? -EIO : 0;
-}
-
 static u32 omfs_max_extents(struct omfs_sb_info *sbi, int offset)
 {
 	return (sbi->s_sys_blocksize - offset -
@@ -344,7 +329,7 @@ struct file_operations omfs_file_operations = {
 	.aio_read = generic_file_aio_read,
 	.aio_write = generic_file_aio_write,
 	.mmap = generic_file_mmap,
-	.fsync = omfs_sync_file,
+	.fsync = simple_fsync,
 	.splice_read = generic_file_splice_read,
 };
 
diff --git a/fs/open.c b/fs/open.c
index bdfbf03615a4..7200e23d9258 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -612,7 +612,7 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, mode_t, mode)
 
 	audit_inode(NULL, dentry);
 
-	err = mnt_want_write(file->f_path.mnt);
+	err = mnt_want_write_file(file);
 	if (err)
 		goto out_putf;
 	mutex_lock(&inode->i_mutex);
@@ -761,7 +761,7 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 	if (!file)
 		goto out;
 
-	error = mnt_want_write(file->f_path.mnt);
+	error = mnt_want_write_file(file);
 	if (error)
 		goto out_fput;
 	dentry = file->f_path.dentry;
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 99e33ef40be4..0af36085eb28 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -219,6 +219,13 @@ ssize_t part_size_show(struct device *dev,
 	return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
 }
 
+ssize_t part_alignment_offset_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+	return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset);
+}
+
 ssize_t part_stat_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
@@ -272,6 +279,7 @@ ssize_t part_fail_store(struct device *dev,
 static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
 static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
+static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
@@ -282,6 +290,7 @@ static struct attribute *part_attrs[] = {
 	&dev_attr_partition.attr,
 	&dev_attr_start.attr,
 	&dev_attr_size.attr,
+	&dev_attr_alignment_offset.attr,
 	&dev_attr_stat.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
@@ -383,6 +392,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	pdev = part_to_dev(p);
 
 	p->start_sect = start;
+	p->alignment_offset = queue_sector_alignment_offset(disk->queue, start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
diff --git a/fs/partitions/ibm.c b/fs/partitions/ibm.c
index 46297683cd34..fc71aab08460 100644
--- a/fs/partitions/ibm.c
+++ b/fs/partitions/ibm.c
@@ -76,7 +76,7 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev)
 	Sector sect;
 
 	res = 0;
-	blocksize = bdev_hardsect_size(bdev);
+	blocksize = bdev_logical_block_size(bdev);
 	if (blocksize <= 0)
 		goto out_exit;
 	i_size = i_size_read(bdev->bd_inode);
diff --git a/fs/partitions/msdos.c b/fs/partitions/msdos.c
index 796511886f28..0028d2ef0662 100644
--- a/fs/partitions/msdos.c
+++ b/fs/partitions/msdos.c
@@ -110,7 +110,7 @@ parse_extended(struct parsed_partitions *state, struct block_device *bdev,
 	Sector sect;
 	unsigned char *data;
 	u32 this_sector, this_size;
-	int sector_size = bdev_hardsect_size(bdev) / 512;
+	int sector_size = bdev_logical_block_size(bdev) / 512;
 	int loopct = 0;		/* number of links followed
 				   without finding a data partition */
 	int i;
@@ -415,7 +415,7 @@ static struct {
  
 int msdos_partition(struct parsed_partitions *state, struct block_device *bdev)
 {
-	int sector_size = bdev_hardsect_size(bdev) / 512;
+	int sector_size = bdev_logical_block_size(bdev) / 512;
 	Sector sect;
 	unsigned char *data;
 	struct partition *p;
diff --git a/fs/pipe.c b/fs/pipe.c
index 13414ec45b8d..f7dd21ad85a6 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -302,6 +302,20 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *info,
 	return 0;
 }
 
+/**
+ * generic_pipe_buf_release - put a reference to a &struct pipe_buffer
+ * @pipe:	the pipe that the buffer belongs to
+ * @buf:	the buffer to put a reference to
+ *
+ * Description:
+ *	This function releases a reference to @buf.
+ */
+void generic_pipe_buf_release(struct pipe_inode_info *pipe,
+			      struct pipe_buffer *buf)
+{
+	page_cache_release(buf->page);
+}
+
 static const struct pipe_buf_operations anon_pipe_buf_ops = {
 	.can_merge = 1,
 	.map = generic_pipe_buf_map,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 3326bbf9ab95..1539e630c47d 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2128,9 +2128,15 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 	if (copy_from_user(page, buf, count))
 		goto out_free;
 
+	/* Guard against adverse ptrace interaction */
+	length = mutex_lock_interruptible(&task->cred_guard_mutex);
+	if (length < 0)
+		goto out_free;
+
 	length = security_setprocattr(task,
 				      (char*)file->f_path.dentry->d_name.name,
 				      (void*)page, count);
+	mutex_unlock(&task->cred_guard_mutex);
 out_free:
 	free_page((unsigned long) page);
 out:
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index f6db9618a888..753ca37002c8 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -92,3 +92,28 @@ struct pde_opener {
 	struct list_head lh;
 };
 void pde_users_dec(struct proc_dir_entry *pde);
+
+extern spinlock_t proc_subdir_lock;
+
+struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *);
+int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
+unsigned long task_vsize(struct mm_struct *);
+int task_statm(struct mm_struct *, int *, int *, int *, int *);
+void task_mem(struct seq_file *, struct mm_struct *);
+
+struct proc_dir_entry *de_get(struct proc_dir_entry *de);
+void de_put(struct proc_dir_entry *de);
+
+extern struct vfsmount *proc_mnt;
+int proc_fill_super(struct super_block *);
+struct inode *proc_get_inode(struct super_block *, unsigned int, struct proc_dir_entry *);
+
+/*
+ * These are generic /proc routines that use the internal
+ * "struct proc_dir_entry" tree to traverse the filesystem.
+ *
+ * The /proc root directory has extended versions to take care
+ * of the /proc/<pid> subdirectories.
+ */
+int proc_readdir(struct file *, void *, filldir_t);
+struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index 9bca39cf99ee..1afa4dd4cae2 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -12,20 +12,14 @@
 
 static int loadavg_proc_show(struct seq_file *m, void *v)
 {
-	int a, b, c;
-	unsigned long seq;
+	unsigned long avnrun[3];
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		a = avenrun[0] + (FIXED_1/200);
-		b = avenrun[1] + (FIXED_1/200);
-		c = avenrun[2] + (FIXED_1/200);
-	} while (read_seqretry(&xtime_lock, seq));
+	get_avenrun(avnrun, FIXED_1/200, 0);
 
-	seq_printf(m, "%d.%02d %d.%02d %d.%02d %ld/%d %d\n",
-		LOAD_INT(a), LOAD_FRAC(a),
-		LOAD_INT(b), LOAD_FRAC(b),
-		LOAD_INT(c), LOAD_FRAC(c),
+	seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n",
+		LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]),
+		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
+		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
 		nr_running(), nr_threads,
 		task_active_pid_ns(current)->last_pid);
 	return 0;
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
index de2bba5a3440..fc6c3025befd 100644
--- a/fs/proc/proc_devtree.c
+++ b/fs/proc/proc_devtree.c
@@ -11,6 +11,7 @@
 #include <linux/string.h>
 #include <asm/prom.h>
 #include <asm/uaccess.h>
+#include "internal.h"
 
 #ifndef HAVE_ARCH_DEVTREE_FIXUPS
 static inline void set_node_proc_entry(struct device_node *np,
diff --git a/fs/qnx4/Makefile b/fs/qnx4/Makefile
index 502d7fe98bab..e4d408cc5473 100644
--- a/fs/qnx4/Makefile
+++ b/fs/qnx4/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_QNX4FS_FS) += qnx4.o
 
-qnx4-objs := inode.o dir.o namei.o file.o bitmap.o truncate.o fsync.o
+qnx4-objs := inode.o dir.o namei.o file.o bitmap.o truncate.o
diff --git a/fs/qnx4/bitmap.c b/fs/qnx4/bitmap.c
index 8425cf6e9624..e1cd061a25f7 100644
--- a/fs/qnx4/bitmap.c
+++ b/fs/qnx4/bitmap.c
@@ -13,14 +13,9 @@
  * 28-06-1998 by Frank Denis : qnx4_free_inode (to be fixed) .
  */
 
-#include <linux/time.h>
-#include <linux/fs.h>
-#include <linux/qnx4_fs.h>
-#include <linux/stat.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
 #include <linux/buffer_head.h>
 #include <linux/bitops.h>
+#include "qnx4.h"
 
 #if 0
 int qnx4_new_block(struct super_block *sb)
diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c
index ea9ffefb48ad..003c68f3238b 100644
--- a/fs/qnx4/dir.c
+++ b/fs/qnx4/dir.c
@@ -11,14 +11,9 @@
  * 20-06-1998 by Frank Denis : Linux 2.1.99+ & dcache support.
  */
 
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/qnx4_fs.h>
-#include <linux/stat.h>
 #include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
-
+#include "qnx4.h"
 
 static int qnx4_readdir(struct file *filp, void *dirent, filldir_t filldir)
 {
@@ -84,7 +79,7 @@ const struct file_operations qnx4_dir_operations =
 {
 	.read		= generic_read_dir,
 	.readdir	= qnx4_readdir,
-	.fsync		= file_fsync,
+	.fsync		= simple_fsync,
 };
 
 const struct inode_operations qnx4_dir_inode_operations =
diff --git a/fs/qnx4/file.c b/fs/qnx4/file.c
index 867f42b02035..09b170ac936c 100644
--- a/fs/qnx4/file.c
+++ b/fs/qnx4/file.c
@@ -12,8 +12,7 @@
  * 27-06-1998 by Frank Denis : file overwriting.
  */
 
-#include <linux/fs.h>
-#include <linux/qnx4_fs.h>
+#include "qnx4.h"
 
 /*
  * We have mostly NULL's here: the current defaults are ok for
@@ -29,7 +28,7 @@ const struct file_operations qnx4_file_operations =
 #ifdef CONFIG_QNX4FS_RW
 	.write		= do_sync_write,
 	.aio_write	= generic_file_aio_write,
-	.fsync		= qnx4_sync_file,
+	.fsync		= simple_fsync,
 #endif
 };
 
diff --git a/fs/qnx4/fsync.c b/fs/qnx4/fsync.c
deleted file mode 100644
index aa3b19544bee..000000000000
--- a/fs/qnx4/fsync.c
+++ /dev/null
@@ -1,169 +0,0 @@
-/* 
- * QNX4 file system, Linux implementation.
- * 
- * Version : 0.1
- * 
- * Using parts of the xiafs filesystem.
- * 
- * History :
- * 
- * 24-03-1998 by Richard Frowijn : first release.
- */
-
-#include <linux/errno.h>
-#include <linux/time.h>
-#include <linux/stat.h>
-#include <linux/fcntl.h>
-#include <linux/smp_lock.h>
-#include <linux/buffer_head.h>
-
-#include <linux/fs.h>
-#include <linux/qnx4_fs.h>
-
-#include <asm/system.h>
-
-/*
- * The functions for qnx4 fs file synchronization.
- */
-
-#ifdef CONFIG_QNX4FS_RW
-
-static int sync_block(struct inode *inode, unsigned short *block, int wait)
-{
-	struct buffer_head *bh;
-	unsigned short tmp;
-
-	if (!*block)
-		return 0;
-	tmp = *block;
-	bh = sb_find_get_block(inode->i_sb, *block);
-	if (!bh)
-		return 0;
-	if (*block != tmp) {
-		brelse(bh);
-		return 1;
-	}
-	if (wait && buffer_req(bh) && !buffer_uptodate(bh)) {
-		brelse(bh);
-		return -1;
-	}
-	if (wait || !buffer_uptodate(bh) || !buffer_dirty(bh)) {
-		brelse(bh);
-		return 0;
-	}
-	ll_rw_block(WRITE, 1, &bh);
-	atomic_dec(&bh->b_count);
-	return 0;
-}
-
-#ifdef WTF
-static int sync_iblock(struct inode *inode, unsigned short *iblock,
-		       struct buffer_head **bh, int wait)
-{
-	int rc;
-	unsigned short tmp;
-
-	*bh = NULL;
-	tmp = *iblock;
-	if (!tmp)
-		return 0;
-	rc = sync_block(inode, iblock, wait);
-	if (rc)
-		return rc;
-	*bh = sb_bread(inode->i_sb, tmp);
-	if (tmp != *iblock) {
-		brelse(*bh);
-		*bh = NULL;
-		return 1;
-	}
-	if (!*bh)
-		return -1;
-	return 0;
-}
-#endif
-
-static int sync_direct(struct inode *inode, int wait)
-{
-	int i;
-	int rc, err = 0;
-
-	for (i = 0; i < 7; i++) {
-		rc = sync_block(inode,
-				(unsigned short *) qnx4_raw_inode(inode)->di_first_xtnt.xtnt_blk + i, wait);
-		if (rc > 0)
-			break;
-		if (rc)
-			err = rc;
-	}
-	return err;
-}
-
-#ifdef WTF
-static int sync_indirect(struct inode *inode, unsigned short *iblock, int wait)
-{
-	int i;
-	struct buffer_head *ind_bh;
-	int rc, err = 0;
-
-	rc = sync_iblock(inode, iblock, &ind_bh, wait);
-	if (rc || !ind_bh)
-		return rc;
-
-	for (i = 0; i < 512; i++) {
-		rc = sync_block(inode,
-				((unsigned short *) ind_bh->b_data) + i,
-				wait);
-		if (rc > 0)
-			break;
-		if (rc)
-			err = rc;
-	}
-	brelse(ind_bh);
-	return err;
-}
-
-static int sync_dindirect(struct inode *inode, unsigned short *diblock,
-			  int wait)
-{
-	int i;
-	struct buffer_head *dind_bh;
-	int rc, err = 0;
-
-	rc = sync_iblock(inode, diblock, &dind_bh, wait);
-	if (rc || !dind_bh)
-		return rc;
-
-	for (i = 0; i < 512; i++) {
-		rc = sync_indirect(inode,
-				((unsigned short *) dind_bh->b_data) + i,
-				   wait);
-		if (rc > 0)
-			break;
-		if (rc)
-			err = rc;
-	}
-	brelse(dind_bh);
-	return err;
-}
-#endif
-
-int qnx4_sync_file(struct file *file, struct dentry *dentry, int unused)
-{
-        struct inode *inode = dentry->d_inode;
-	int wait, err = 0;
-        
-        (void) file;
-	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-	      S_ISLNK(inode->i_mode)))
-		return -EINVAL;
-
-	lock_kernel();
-	for (wait = 0; wait <= 1; wait++) {
-		err |= sync_direct(inode, wait);
-	}
-	err |= qnx4_sync_inode(inode);
-	unlock_kernel();
-	return (err < 0) ? -EIO : 0;
-}
-
-#endif
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index fe1f0f31d11c..681df5fcd161 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -13,19 +13,15 @@
  */
 
 #include <linux/module.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/slab.h>
-#include <linux/fs.h>
-#include <linux/qnx4_fs.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/highuid.h>
 #include <linux/smp_lock.h>
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
-#include <linux/vfs.h>
-#include <asm/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/statfs.h>
+#include "qnx4.h"
 
 #define QNX4_VERSION  4
 #define QNX4_BMNAME   ".bitmap"
@@ -34,31 +30,6 @@ static const struct super_operations qnx4_sops;
 
 #ifdef CONFIG_QNX4FS_RW
 
-int qnx4_sync_inode(struct inode *inode)
-{
-	int err = 0;
-# if 0
-	struct buffer_head *bh;
-
-   	bh = qnx4_update_inode(inode);
-	if (bh && buffer_dirty(bh))
-	{
-		sync_dirty_buffer(bh);
-		if (buffer_req(bh) && !buffer_uptodate(bh))
-		{
-			printk ("IO error syncing qnx4 inode [%s:%08lx]\n",
-				inode->i_sb->s_id, inode->i_ino);
-			err = -1;
-		}
-	        brelse (bh);
-	} else if (!bh) {
-		err = -1;
-	}
-# endif
-
-	return err;
-}
-
 static void qnx4_delete_inode(struct inode *inode)
 {
 	QNX4DEBUG(("qnx4: deleting inode [%lu]\n", (unsigned long) inode->i_ino));
@@ -70,15 +41,7 @@ static void qnx4_delete_inode(struct inode *inode)
 	unlock_kernel();
 }
 
-static void qnx4_write_super(struct super_block *sb)
-{
-	lock_kernel();
-	QNX4DEBUG(("qnx4: write_super\n"));
-	sb->s_dirt = 0;
-	unlock_kernel();
-}
-
-static int qnx4_write_inode(struct inode *inode, int unused)
+static int qnx4_write_inode(struct inode *inode, int do_sync)
 {
 	struct qnx4_inode_entry *raw_inode;
 	int block, ino;
@@ -115,6 +78,16 @@ static int qnx4_write_inode(struct inode *inode, int unused)
 	raw_inode->di_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
 	raw_inode->di_first_xtnt.xtnt_size = cpu_to_le32(inode->i_blocks);
 	mark_buffer_dirty(bh);
+	if (do_sync) {
+		sync_dirty_buffer(bh);
+		if (buffer_req(bh) && !buffer_uptodate(bh)) {
+			printk("qnx4: IO error syncing inode [%s:%08x]\n",
+					inode->i_sb->s_id, ino);
+			brelse(bh);
+			unlock_kernel();
+			return -EIO;
+		}
+	}
 	brelse(bh);
 	unlock_kernel();
 	return 0;
@@ -138,7 +111,6 @@ static const struct super_operations qnx4_sops =
 #ifdef CONFIG_QNX4FS_RW
 	.write_inode	= qnx4_write_inode,
 	.delete_inode	= qnx4_delete_inode,
-	.write_super	= qnx4_write_super,
 #endif
 };
 
diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c
index 775eed3a4085..5972ed214937 100644
--- a/fs/qnx4/namei.c
+++ b/fs/qnx4/namei.c
@@ -12,16 +12,9 @@
  * 04-07-1998 by Frank Denis : first step for rmdir/unlink.
  */
 
-#include <linux/time.h>
-#include <linux/fs.h>
-#include <linux/qnx4_fs.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/stat.h>
-#include <linux/fcntl.h>
-#include <linux/errno.h>
 #include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
+#include "qnx4.h"
 
 
 /*
@@ -187,7 +180,7 @@ int qnx4_rmdir(struct inode *dir, struct dentry *dentry)
 	de->di_status = 0;
 	memset(de->di_fname, 0, sizeof de->di_fname);
 	de->di_mode = 0;
-	mark_buffer_dirty(bh);
+	mark_buffer_dirty_inode(bh, dir);
 	clear_nlink(inode);
 	mark_inode_dirty(inode);
 	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC;
@@ -232,7 +225,7 @@ int qnx4_unlink(struct inode *dir, struct dentry *dentry)
 	de->di_status = 0;
 	memset(de->di_fname, 0, sizeof de->di_fname);
 	de->di_mode = 0;
-	mark_buffer_dirty(bh);
+	mark_buffer_dirty_inode(bh, dir);
 	dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC;
 	mark_inode_dirty(dir);
 	inode->i_ctime = dir->i_ctime;
diff --git a/fs/qnx4/qnx4.h b/fs/qnx4/qnx4.h
new file mode 100644
index 000000000000..9efc089454f6
--- /dev/null
+++ b/fs/qnx4/qnx4.h
@@ -0,0 +1,57 @@
+#include <linux/fs.h>
+#include <linux/qnx4_fs.h>
+
+#define QNX4_DEBUG 0
+
+#if QNX4_DEBUG
+#define QNX4DEBUG(X) printk X
+#else
+#define QNX4DEBUG(X) (void) 0
+#endif
+
+struct qnx4_sb_info {
+	struct buffer_head	*sb_buf;	/* superblock buffer */
+	struct qnx4_super_block	*sb;		/* our superblock */
+	unsigned int		Version;	/* may be useful */
+	struct qnx4_inode_entry	*BitMap;	/* useful */
+};
+
+struct qnx4_inode_info {
+	struct qnx4_inode_entry raw;
+	loff_t mmu_private;
+	struct inode vfs_inode;
+};
+
+extern struct inode *qnx4_iget(struct super_block *, unsigned long);
+extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd);
+extern unsigned long qnx4_count_free_blocks(struct super_block *sb);
+extern unsigned long qnx4_block_map(struct inode *inode, long iblock);
+
+extern struct buffer_head *qnx4_bread(struct inode *, int, int);
+
+extern const struct inode_operations qnx4_file_inode_operations;
+extern const struct inode_operations qnx4_dir_inode_operations;
+extern const struct file_operations qnx4_file_operations;
+extern const struct file_operations qnx4_dir_operations;
+extern int qnx4_is_free(struct super_block *sb, long block);
+extern int qnx4_set_bitmap(struct super_block *sb, long block, int busy);
+extern int qnx4_create(struct inode *inode, struct dentry *dentry, int mode, struct nameidata *nd);
+extern void qnx4_truncate(struct inode *inode);
+extern void qnx4_free_inode(struct inode *inode);
+extern int qnx4_unlink(struct inode *dir, struct dentry *dentry);
+extern int qnx4_rmdir(struct inode *dir, struct dentry *dentry);
+
+static inline struct qnx4_sb_info *qnx4_sb(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+static inline struct qnx4_inode_info *qnx4_i(struct inode *inode)
+{
+	return container_of(inode, struct qnx4_inode_info, vfs_inode);
+}
+
+static inline struct qnx4_inode_entry *qnx4_raw_inode(struct inode *inode)
+{
+	return &qnx4_i(inode)->raw;
+}
diff --git a/fs/qnx4/truncate.c b/fs/qnx4/truncate.c
index 6437c1c3d1dd..d94d9ee241fe 100644
--- a/fs/qnx4/truncate.c
+++ b/fs/qnx4/truncate.c
@@ -10,12 +10,8 @@
  * 30-06-1998 by Frank DENIS : ugly filler.
  */
 
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/qnx4_fs.h>
 #include <linux/smp_lock.h>
-#include <asm/uaccess.h>
+#include "qnx4.h"
 
 #ifdef CONFIG_QNX4FS_RW
 
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index b7f5a468f076..95c5b42384b2 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -159,10 +159,14 @@ static int check_quotactl_valid(struct super_block *sb, int type, int cmd,
 	return error;
 }
 
-static void quota_sync_sb(struct super_block *sb, int type)
+#ifdef CONFIG_QUOTA
+void sync_quota_sb(struct super_block *sb, int type)
 {
 	int cnt;
 
+	if (!sb->s_qcop->quota_sync)
+		return;
+
 	sb->s_qcop->quota_sync(sb, type);
 
 	if (sb_dqopt(sb)->flags & DQUOT_QUOTA_SYS_FILE)
@@ -191,17 +195,13 @@ static void quota_sync_sb(struct super_block *sb, int type)
 	}
 	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
 }
+#endif
 
-void sync_dquots(struct super_block *sb, int type)
+static void sync_dquots(int type)
 {
+	struct super_block *sb;
 	int cnt;
 
-	if (sb) {
-		if (sb->s_qcop->quota_sync)
-			quota_sync_sb(sb, type);
-		return;
-	}
-
 	spin_lock(&sb_lock);
 restart:
 	list_for_each_entry(sb, &super_blocks, s_list) {
@@ -222,8 +222,8 @@ restart:
 		sb->s_count++;
 		spin_unlock(&sb_lock);
 		down_read(&sb->s_umount);
-		if (sb->s_root && sb->s_qcop->quota_sync)
-			quota_sync_sb(sb, type);
+		if (sb->s_root)
+			sync_quota_sb(sb, type);
 		up_read(&sb->s_umount);
 		spin_lock(&sb_lock);
 		if (__put_super_and_need_restart(sb))
@@ -301,7 +301,10 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 			return sb->s_qcop->set_dqblk(sb, type, id, &idq);
 		}
 		case Q_SYNC:
-			sync_dquots(sb, type);
+			if (sb)
+				sync_quota_sb(sb, type);
+			else
+				sync_dquots(type);
 			return 0;
 
 		case Q_XQUOTAON:
diff --git a/fs/read_write.c b/fs/read_write.c
index 9d1e76bb9ee1..6c8c55dec2bc 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -805,12 +805,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		goto out;
 	if (!(in_file->f_mode & FMODE_READ))
 		goto fput_in;
-	retval = -EINVAL;
-	in_inode = in_file->f_path.dentry->d_inode;
-	if (!in_inode)
-		goto fput_in;
-	if (!in_file->f_op || !in_file->f_op->splice_read)
-		goto fput_in;
 	retval = -ESPIPE;
 	if (!ppos)
 		ppos = &in_file->f_pos;
@@ -834,6 +828,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	retval = -EINVAL;
 	if (!out_file->f_op || !out_file->f_op->sendpage)
 		goto fput_out;
+	in_inode = in_file->f_path.dentry->d_inode;
 	out_inode = out_file->f_path.dentry->d_inode;
 	retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
 	if (retval < 0)
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 45ee3d357c70..6d2668fdc384 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -44,13 +44,11 @@ static int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry,
 static inline bool is_privroot_deh(struct dentry *dir,
 				   struct reiserfs_de_head *deh)
 {
-	int ret = 0;
-#ifdef CONFIG_REISERFS_FS_XATTR
 	struct dentry *privroot = REISERFS_SB(dir->d_sb)->priv_root;
-	ret = (dir == dir->d_parent && privroot->d_inode &&
-	       deh->deh_objectid == INODE_PKEY(privroot->d_inode)->k_objectid);
-#endif
-	return ret;
+	if (reiserfs_expose_privroot(dir->d_sb))
+		return 0;
+	return (dir == dir->d_parent && privroot->d_inode &&
+	        deh->deh_objectid == INODE_PKEY(privroot->d_inode)->k_objectid);
 }
 
 int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 3567fb9e3fb1..2969773cfc22 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -28,6 +28,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/crc32.h>
+#include <linux/smp_lock.h>
 
 struct file_system_type reiserfs_fs_type;
 
@@ -64,18 +65,15 @@ static int reiserfs_statfs(struct dentry *dentry, struct kstatfs *buf);
 
 static int reiserfs_sync_fs(struct super_block *s, int wait)
 {
-	if (!(s->s_flags & MS_RDONLY)) {
-		struct reiserfs_transaction_handle th;
-		reiserfs_write_lock(s);
-		if (!journal_begin(&th, s, 1))
-			if (!journal_end_sync(&th, s, 1))
-				reiserfs_flush_old_commits(s);
-		s->s_dirt = 0;	/* Even if it's not true.
-				 * We'll loop forever in sync_supers otherwise */
-		reiserfs_write_unlock(s);
-	} else {
-		s->s_dirt = 0;
-	}
+	struct reiserfs_transaction_handle th;
+
+	reiserfs_write_lock(s);
+	if (!journal_begin(&th, s, 1))
+		if (!journal_end_sync(&th, s, 1))
+			reiserfs_flush_old_commits(s);
+	s->s_dirt = 0;	/* Even if it's not true.
+			 * We'll loop forever in sync_supers otherwise */
+	reiserfs_write_unlock(s);
 	return 0;
 }
 
@@ -468,6 +466,11 @@ static void reiserfs_put_super(struct super_block *s)
 	struct reiserfs_transaction_handle th;
 	th.t_trans_id = 0;
 
+	lock_kernel();
+
+	if (s->s_dirt)
+		reiserfs_write_super(s);
+
 	/* change file system state to current state if it was mounted with read-write permissions */
 	if (!(s->s_flags & MS_RDONLY)) {
 		if (!journal_begin(&th, s, 10)) {
@@ -500,7 +503,7 @@ static void reiserfs_put_super(struct super_block *s)
 	kfree(s->s_fs_info);
 	s->s_fs_info = NULL;
 
-	return;
+	unlock_kernel();
 }
 
 static struct kmem_cache *reiserfs_inode_cachep;
@@ -898,6 +901,7 @@ static int reiserfs_parse_options(struct super_block *s, char *options,	/* strin
 		{"conv",.setmask = 1 << REISERFS_CONVERT},
 		{"attrs",.setmask = 1 << REISERFS_ATTRS},
 		{"noattrs",.clrmask = 1 << REISERFS_ATTRS},
+		{"expose_privroot", .setmask = 1 << REISERFS_EXPOSE_PRIVROOT},
 #ifdef CONFIG_REISERFS_FS_XATTR
 		{"user_xattr",.setmask = 1 << REISERFS_XATTRS_USER},
 		{"nouser_xattr",.clrmask = 1 << REISERFS_XATTRS_USER},
@@ -1193,6 +1197,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	memcpy(qf_names, REISERFS_SB(s)->s_qf_names, sizeof(qf_names));
 #endif
 
+	lock_kernel();
 	rs = SB_DISK_SUPER_BLOCK(s);
 
 	if (!reiserfs_parse_options
@@ -1315,10 +1320,12 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 
 out_ok:
 	replace_mount_options(s, new_opts);
+	unlock_kernel();
 	return 0;
 
 out_err:
 	kfree(new_opts);
+	unlock_kernel();
 	return err;
 }
 
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 8e7deb0e6964..f3d47d856848 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -981,7 +981,8 @@ int reiserfs_lookup_privroot(struct super_block *s)
 				strlen(PRIVROOT_NAME));
 	if (!IS_ERR(dentry)) {
 		REISERFS_SB(s)->priv_root = dentry;
-		s->s_root->d_op = &xattr_lookup_poison_ops;
+		if (!reiserfs_expose_privroot(s))
+			s->s_root->d_op = &xattr_lookup_poison_ops;
 		if (dentry->d_inode)
 			dentry->d_inode->i_flags |= S_PRIVATE;
 	} else
diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c
index fc27fbfc5397..1402d2d54f52 100644
--- a/fs/smbfs/inode.c
+++ b/fs/smbfs/inode.c
@@ -474,6 +474,8 @@ smb_put_super(struct super_block *sb)
 {
 	struct smb_sb_info *server = SMB_SB(sb);
 
+	lock_kernel();
+
 	smb_lock_server(server);
 	server->state = CONN_INVALID;
 	smbiod_unregister_server(server);
@@ -489,6 +491,8 @@ smb_put_super(struct super_block *sb)
 	smb_unlock_server(server);
 	put_pid(server->conn_pid);
 	kfree(server);
+
+	unlock_kernel();
 }
 
 static int smb_fill_super(struct super_block *sb, void *raw_data, int silent)
diff --git a/fs/splice.c b/fs/splice.c
index 666953d59a35..73766d24f97b 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -507,9 +507,131 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 
 	return ret;
 }
-
 EXPORT_SYMBOL(generic_file_splice_read);
 
+static const struct pipe_buf_operations default_pipe_buf_ops = {
+	.can_merge = 0,
+	.map = generic_pipe_buf_map,
+	.unmap = generic_pipe_buf_unmap,
+	.confirm = generic_pipe_buf_confirm,
+	.release = generic_pipe_buf_release,
+	.steal = generic_pipe_buf_steal,
+	.get = generic_pipe_buf_get,
+};
+
+static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
+			    unsigned long vlen, loff_t offset)
+{
+	mm_segment_t old_fs;
+	loff_t pos = offset;
+	ssize_t res;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	/* The cast to a user pointer is valid due to the set_fs() */
+	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos);
+	set_fs(old_fs);
+
+	return res;
+}
+
+static ssize_t kernel_write(struct file *file, const char *buf, size_t count,
+			    loff_t pos)
+{
+	mm_segment_t old_fs;
+	ssize_t res;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	/* The cast to a user pointer is valid due to the set_fs() */
+	res = vfs_write(file, (const char __user *)buf, count, &pos);
+	set_fs(old_fs);
+
+	return res;
+}
+
+ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
+				 struct pipe_inode_info *pipe, size_t len,
+				 unsigned int flags)
+{
+	unsigned int nr_pages;
+	unsigned int nr_freed;
+	size_t offset;
+	struct page *pages[PIPE_BUFFERS];
+	struct partial_page partial[PIPE_BUFFERS];
+	struct iovec vec[PIPE_BUFFERS];
+	pgoff_t index;
+	ssize_t res;
+	size_t this_len;
+	int error;
+	int i;
+	struct splice_pipe_desc spd = {
+		.pages = pages,
+		.partial = partial,
+		.flags = flags,
+		.ops = &default_pipe_buf_ops,
+		.spd_release = spd_release_page,
+	};
+
+	index = *ppos >> PAGE_CACHE_SHIFT;
+	offset = *ppos & ~PAGE_CACHE_MASK;
+	nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+	for (i = 0; i < nr_pages && i < PIPE_BUFFERS && len; i++) {
+		struct page *page;
+
+		page = alloc_page(GFP_USER);
+		error = -ENOMEM;
+		if (!page)
+			goto err;
+
+		this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset);
+		vec[i].iov_base = (void __user *) page_address(page);
+		vec[i].iov_len = this_len;
+		pages[i] = page;
+		spd.nr_pages++;
+		len -= this_len;
+		offset = 0;
+	}
+
+	res = kernel_readv(in, vec, spd.nr_pages, *ppos);
+	if (res < 0) {
+		error = res;
+		goto err;
+	}
+
+	error = 0;
+	if (!res)
+		goto err;
+
+	nr_freed = 0;
+	for (i = 0; i < spd.nr_pages; i++) {
+		this_len = min_t(size_t, vec[i].iov_len, res);
+		partial[i].offset = 0;
+		partial[i].len = this_len;
+		if (!this_len) {
+			__free_page(pages[i]);
+			pages[i] = NULL;
+			nr_freed++;
+		}
+		res -= this_len;
+	}
+	spd.nr_pages -= nr_freed;
+
+	res = splice_to_pipe(pipe, &spd);
+	if (res > 0)
+		*ppos += res;
+
+	return res;
+
+err:
+	for (i = 0; i < spd.nr_pages; i++)
+		__free_page(pages[i]);
+
+	return error;
+}
+EXPORT_SYMBOL(default_file_splice_read);
+
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -881,6 +1003,36 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_file_splice_write);
 
+static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
+			  struct splice_desc *sd)
+{
+	int ret;
+	void *data;
+
+	ret = buf->ops->confirm(pipe, buf);
+	if (ret)
+		return ret;
+
+	data = buf->ops->map(pipe, buf, 0);
+	ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
+	buf->ops->unmap(pipe, buf, data);
+
+	return ret;
+}
+
+static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
+					 struct file *out, loff_t *ppos,
+					 size_t len, unsigned int flags)
+{
+	ssize_t ret;
+
+	ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
+	if (ret > 0)
+		*ppos += ret;
+
+	return ret;
+}
+
 /**
  * generic_splice_sendpage - splice data from a pipe to a socket
  * @pipe:	pipe to splice from
@@ -908,11 +1060,10 @@ EXPORT_SYMBOL(generic_splice_sendpage);
 static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 			   loff_t *ppos, size_t len, unsigned int flags)
 {
+	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *,
+				loff_t *, size_t, unsigned int);
 	int ret;
 
-	if (unlikely(!out->f_op || !out->f_op->splice_write))
-		return -EINVAL;
-
 	if (unlikely(!(out->f_mode & FMODE_WRITE)))
 		return -EBADF;
 
@@ -923,7 +1074,11 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 	if (unlikely(ret < 0))
 		return ret;
 
-	return out->f_op->splice_write(pipe, out, ppos, len, flags);
+	splice_write = out->f_op->splice_write;
+	if (!splice_write)
+		splice_write = default_file_splice_write;
+
+	return splice_write(pipe, out, ppos, len, flags);
 }
 
 /*
@@ -933,11 +1088,10 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 			 struct pipe_inode_info *pipe, size_t len,
 			 unsigned int flags)
 {
+	ssize_t (*splice_read)(struct file *, loff_t *,
+			       struct pipe_inode_info *, size_t, unsigned int);
 	int ret;
 
-	if (unlikely(!in->f_op || !in->f_op->splice_read))
-		return -EINVAL;
-
 	if (unlikely(!(in->f_mode & FMODE_READ)))
 		return -EBADF;
 
@@ -945,7 +1099,11 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(ret < 0))
 		return ret;
 
-	return in->f_op->splice_read(in, ppos, pipe, len, flags);
+	splice_read = in->f_op->splice_read;
+	if (!splice_read)
+		splice_read = default_file_splice_read;
+
+	return splice_read(in, ppos, pipe, len, flags);
 }
 
 /**
@@ -1112,6 +1270,9 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 	return ret;
 }
 
+static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
+			       struct pipe_inode_info *opipe,
+			       size_t len, unsigned int flags);
 /*
  * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same
  * location, so checking ->i_pipe is not enough to verify that this is a
@@ -1132,12 +1293,32 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		      struct file *out, loff_t __user *off_out,
 		      size_t len, unsigned int flags)
 {
-	struct pipe_inode_info *pipe;
+	struct pipe_inode_info *ipipe;
+	struct pipe_inode_info *opipe;
 	loff_t offset, *off;
 	long ret;
 
-	pipe = pipe_info(in->f_path.dentry->d_inode);
-	if (pipe) {
+	ipipe = pipe_info(in->f_path.dentry->d_inode);
+	opipe = pipe_info(out->f_path.dentry->d_inode);
+
+	if (ipipe && opipe) {
+		if (off_in || off_out)
+			return -ESPIPE;
+
+		if (!(in->f_mode & FMODE_READ))
+			return -EBADF;
+
+		if (!(out->f_mode & FMODE_WRITE))
+			return -EBADF;
+
+		/* Splicing to self would be fun, but... */
+		if (ipipe == opipe)
+			return -EINVAL;
+
+		return splice_pipe_to_pipe(ipipe, opipe, len, flags);
+	}
+
+	if (ipipe) {
 		if (off_in)
 			return -ESPIPE;
 		if (off_out) {
@@ -1149,7 +1330,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		} else
 			off = &out->f_pos;
 
-		ret = do_splice_from(pipe, out, off, len, flags);
+		ret = do_splice_from(ipipe, out, off, len, flags);
 
 		if (off_out && copy_to_user(off_out, off, sizeof(loff_t)))
 			ret = -EFAULT;
@@ -1157,8 +1338,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		return ret;
 	}
 
-	pipe = pipe_info(out->f_path.dentry->d_inode);
-	if (pipe) {
+	if (opipe) {
 		if (off_out)
 			return -ESPIPE;
 		if (off_in) {
@@ -1170,7 +1350,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		} else
 			off = &in->f_pos;
 
-		ret = do_splice_to(in, off, pipe, len, flags);
+		ret = do_splice_to(in, off, opipe, len, flags);
 
 		if (off_in && copy_to_user(off_in, off, sizeof(loff_t)))
 			ret = -EFAULT;
@@ -1511,7 +1691,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
  * Make sure there's data to read. Wait for input if we can, otherwise
  * return an appropriate error.
  */
-static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
+static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 {
 	int ret;
 
@@ -1549,7 +1729,7 @@ static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
  * Make sure there's writeable room. Wait for room if we can, otherwise
  * return an appropriate error.
  */
-static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
+static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 {
 	int ret;
 
@@ -1586,6 +1766,124 @@ static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 	return ret;
 }
 
+/*
+ * Splice contents of ipipe to opipe.
+ */
+static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
+			       struct pipe_inode_info *opipe,
+			       size_t len, unsigned int flags)
+{
+	struct pipe_buffer *ibuf, *obuf;
+	int ret = 0, nbuf;
+	bool input_wakeup = false;
+
+
+retry:
+	ret = ipipe_prep(ipipe, flags);
+	if (ret)
+		return ret;
+
+	ret = opipe_prep(opipe, flags);
+	if (ret)
+		return ret;
+
+	/*
+	 * Potential ABBA deadlock, work around it by ordering lock
+	 * grabbing by pipe info address. Otherwise two different processes
+	 * could deadlock (one doing tee from A -> B, the other from B -> A).
+	 */
+	pipe_double_lock(ipipe, opipe);
+
+	do {
+		if (!opipe->readers) {
+			send_sig(SIGPIPE, current, 0);
+			if (!ret)
+				ret = -EPIPE;
+			break;
+		}
+
+		if (!ipipe->nrbufs && !ipipe->writers)
+			break;
+
+		/*
+		 * Cannot make any progress, because either the input
+		 * pipe is empty or the output pipe is full.
+		 */
+		if (!ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS) {
+			/* Already processed some buffers, break */
+			if (ret)
+				break;
+
+			if (flags & SPLICE_F_NONBLOCK) {
+				ret = -EAGAIN;
+				break;
+			}
+
+			/*
+			 * We raced with another reader/writer and haven't
+			 * managed to process any buffers.  A zero return
+			 * value means EOF, so retry instead.
+			 */
+			pipe_unlock(ipipe);
+			pipe_unlock(opipe);
+			goto retry;
+		}
+
+		ibuf = ipipe->bufs + ipipe->curbuf;
+		nbuf = (opipe->curbuf + opipe->nrbufs) % PIPE_BUFFERS;
+		obuf = opipe->bufs + nbuf;
+
+		if (len >= ibuf->len) {
+			/*
+			 * Simply move the whole buffer from ipipe to opipe
+			 */
+			*obuf = *ibuf;
+			ibuf->ops = NULL;
+			opipe->nrbufs++;
+			ipipe->curbuf = (ipipe->curbuf + 1) % PIPE_BUFFERS;
+			ipipe->nrbufs--;
+			input_wakeup = true;
+		} else {
+			/*
+			 * Get a reference to this pipe buffer,
+			 * so we can copy the contents over.
+			 */
+			ibuf->ops->get(ipipe, ibuf);
+			*obuf = *ibuf;
+
+			/*
+			 * Don't inherit the gift flag, we need to
+			 * prevent multiple steals of this page.
+			 */
+			obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
+
+			obuf->len = len;
+			opipe->nrbufs++;
+			ibuf->offset += obuf->len;
+			ibuf->len -= obuf->len;
+		}
+		ret += obuf->len;
+		len -= obuf->len;
+	} while (len);
+
+	pipe_unlock(ipipe);
+	pipe_unlock(opipe);
+
+	/*
+	 * If we put data in the output pipe, wakeup any potential readers.
+	 */
+	if (ret > 0) {
+		smp_mb();
+		if (waitqueue_active(&opipe->wait))
+			wake_up_interruptible(&opipe->wait);
+		kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
+	}
+	if (input_wakeup)
+		wakeup_pipe_writers(ipipe);
+
+	return ret;
+}
+
 /*
  * Link contents of ipipe to opipe.
  */
@@ -1690,9 +1988,9 @@ static long do_tee(struct file *in, struct file *out, size_t len,
 		 * Keep going, unless we encounter an error. The ipipe/opipe
 		 * ordering doesn't really matter.
 		 */
-		ret = link_ipipe_prep(ipipe, flags);
+		ret = ipipe_prep(ipipe, flags);
 		if (!ret) {
-			ret = link_opipe_prep(opipe, flags);
+			ret = opipe_prep(opipe, flags);
 			if (!ret)
 				ret = link_pipe(ipipe, opipe, len, flags);
 		}
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 0adc624c956f..3b52770f46ff 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -338,6 +338,8 @@ static int squashfs_remount(struct super_block *sb, int *flags, char *data)
 
 static void squashfs_put_super(struct super_block *sb)
 {
+	lock_kernel();
+
 	if (sb->s_fs_info) {
 		struct squashfs_sb_info *sbi = sb->s_fs_info;
 		squashfs_cache_delete(sbi->block_cache);
@@ -350,6 +352,8 @@ static void squashfs_put_super(struct super_block *sb)
 		kfree(sb->s_fs_info);
 		sb->s_fs_info = NULL;
 	}
+
+	unlock_kernel();
 }
 
 
diff --git a/fs/super.c b/fs/super.c
index 1943fdf655fa..83b47416d006 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -28,7 +28,6 @@
 #include <linux/blkdev.h>
 #include <linux/quotaops.h>
 #include <linux/namei.h>
-#include <linux/buffer_head.h>		/* for fsync_super() */
 #include <linux/mount.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
@@ -38,7 +37,6 @@
 #include <linux/kobject.h>
 #include <linux/mutex.h>
 #include <linux/file.h>
-#include <linux/async.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -72,7 +70,6 @@ static struct super_block *alloc_super(struct file_system_type *type)
 		INIT_HLIST_HEAD(&s->s_anon);
 		INIT_LIST_HEAD(&s->s_inodes);
 		INIT_LIST_HEAD(&s->s_dentry_lru);
-		INIT_LIST_HEAD(&s->s_async_list);
 		init_rwsem(&s->s_umount);
 		mutex_init(&s->s_lock);
 		lockdep_set_class(&s->s_umount, &type->s_umount_key);
@@ -285,38 +282,6 @@ void unlock_super(struct super_block * sb)
 EXPORT_SYMBOL(lock_super);
 EXPORT_SYMBOL(unlock_super);
 
-/*
- * Write out and wait upon all dirty data associated with this
- * superblock.  Filesystem data as well as the underlying block
- * device.  Takes the superblock lock.  Requires a second blkdev
- * flush by the caller to complete the operation.
- */
-void __fsync_super(struct super_block *sb)
-{
-	sync_inodes_sb(sb, 0);
-	vfs_dq_sync(sb);
-	lock_super(sb);
-	if (sb->s_dirt && sb->s_op->write_super)
-		sb->s_op->write_super(sb);
-	unlock_super(sb);
-	if (sb->s_op->sync_fs)
-		sb->s_op->sync_fs(sb, 1);
-	sync_blockdev(sb->s_bdev);
-	sync_inodes_sb(sb, 1);
-}
-
-/*
- * Write out and wait upon all dirty data associated with this
- * superblock.  Filesystem data as well as the underlying block
- * device.  Takes the superblock lock.
- */
-int fsync_super(struct super_block *sb)
-{
-	__fsync_super(sb);
-	return sync_blockdev(sb->s_bdev);
-}
-EXPORT_SYMBOL_GPL(fsync_super);
-
 /**
  *	generic_shutdown_super	-	common helper for ->kill_sb()
  *	@sb: superblock to kill
@@ -338,21 +303,13 @@ void generic_shutdown_super(struct super_block *sb)
 
 	if (sb->s_root) {
 		shrink_dcache_for_umount(sb);
-		fsync_super(sb);
-		lock_super(sb);
+		sync_filesystem(sb);
+		get_fs_excl();
 		sb->s_flags &= ~MS_ACTIVE;
 
-		/*
-		 * wait for asynchronous fs operations to finish before going further
-		 */
-		async_synchronize_full_domain(&sb->s_async_list);
-
 		/* bad name - it should be evict_inodes() */
 		invalidate_inodes(sb);
-		lock_kernel();
 
-		if (sop->write_super && sb->s_dirt)
-			sop->write_super(sb);
 		if (sop->put_super)
 			sop->put_super(sb);
 
@@ -362,9 +319,7 @@ void generic_shutdown_super(struct super_block *sb)
 			   "Self-destruct in 5 seconds.  Have a nice day...\n",
 			   sb->s_id);
 		}
-
-		unlock_kernel();
-		unlock_super(sb);
+		put_fs_excl();
 	}
 	spin_lock(&sb_lock);
 	/* should be initialized for __put_super_and_need_restart() */
@@ -441,16 +396,14 @@ void drop_super(struct super_block *sb)
 
 EXPORT_SYMBOL(drop_super);
 
-static inline void write_super(struct super_block *sb)
-{
-	lock_super(sb);
-	if (sb->s_root && sb->s_dirt)
-		if (sb->s_op->write_super)
-			sb->s_op->write_super(sb);
-	unlock_super(sb);
-}
-
-/*
+/**
+ * sync_supers - helper for periodic superblock writeback
+ *
+ * Call the write_super method if present on all dirty superblocks in
+ * the system.  This is for the periodic writeback used by most older
+ * filesystems.  For data integrity superblock writeback use
+ * sync_filesystems() instead.
+ *
  * Note: check the dirty flag before waiting, so we don't
  * hold up the sync while mounting a device. (The newly
  * mounted device won't need syncing.)
@@ -462,12 +415,15 @@ void sync_supers(void)
 	spin_lock(&sb_lock);
 restart:
 	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (sb->s_dirt) {
+		if (sb->s_op->write_super && sb->s_dirt) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
+
 			down_read(&sb->s_umount);
-			write_super(sb);
+			if (sb->s_root && sb->s_dirt)
+				sb->s_op->write_super(sb);
 			up_read(&sb->s_umount);
+
 			spin_lock(&sb_lock);
 			if (__put_super_and_need_restart(sb))
 				goto restart;
@@ -476,60 +432,6 @@ restart:
 	spin_unlock(&sb_lock);
 }
 
-/*
- * Call the ->sync_fs super_op against all filesystems which are r/w and
- * which implement it.
- *
- * This operation is careful to avoid the livelock which could easily happen
- * if two or more filesystems are being continuously dirtied.  s_need_sync_fs
- * is used only here.  We set it against all filesystems and then clear it as
- * we sync them.  So redirtied filesystems are skipped.
- *
- * But if process A is currently running sync_filesystems and then process B
- * calls sync_filesystems as well, process B will set all the s_need_sync_fs
- * flags again, which will cause process A to resync everything.  Fix that with
- * a local mutex.
- *
- * (Fabian) Avoid sync_fs with clean fs & wait mode 0
- */
-void sync_filesystems(int wait)
-{
-	struct super_block *sb;
-	static DEFINE_MUTEX(mutex);
-
-	mutex_lock(&mutex);		/* Could be down_interruptible */
-	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (!sb->s_op->sync_fs)
-			continue;
-		if (sb->s_flags & MS_RDONLY)
-			continue;
-		sb->s_need_sync_fs = 1;
-	}
-
-restart:
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (!sb->s_need_sync_fs)
-			continue;
-		sb->s_need_sync_fs = 0;
-		if (sb->s_flags & MS_RDONLY)
-			continue;	/* hm.  Was remounted r/o meanwhile */
-		sb->s_count++;
-		spin_unlock(&sb_lock);
-		down_read(&sb->s_umount);
-		async_synchronize_full_domain(&sb->s_async_list);
-		if (sb->s_root && (wait || sb->s_dirt))
-			sb->s_op->sync_fs(sb, wait);
-		up_read(&sb->s_umount);
-		/* restart only when sb is no longer on the list */
-		spin_lock(&sb_lock);
-		if (__put_super_and_need_restart(sb))
-			goto restart;
-	}
-	spin_unlock(&sb_lock);
-	mutex_unlock(&mutex);
-}
-
 /**
  *	get_super - get the superblock of a device
  *	@bdev: device to get the superblock for
@@ -615,45 +517,6 @@ out:
 	return err;
 }
 
-/**
- *	mark_files_ro - mark all files read-only
- *	@sb: superblock in question
- *
- *	All files are marked read-only.  We don't care about pending
- *	delete files so this should be used in 'force' mode only.
- */
-
-static void mark_files_ro(struct super_block *sb)
-{
-	struct file *f;
-
-retry:
-	file_list_lock();
-	list_for_each_entry(f, &sb->s_files, f_u.fu_list) {
-		struct vfsmount *mnt;
-		if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
-		       continue;
-		if (!file_count(f))
-			continue;
-		if (!(f->f_mode & FMODE_WRITE))
-			continue;
-		f->f_mode &= ~FMODE_WRITE;
-		if (file_check_writeable(f) != 0)
-			continue;
-		file_release_write(f);
-		mnt = mntget(f->f_path.mnt);
-		file_list_unlock();
-		/*
-		 * This can sleep, so we can't hold
-		 * the file_list_lock() spinlock.
-		 */
-		mnt_drop_write(mnt);
-		mntput(mnt);
-		goto retry;
-	}
-	file_list_unlock();
-}
-
 /**
  *	do_remount_sb - asks filesystem to change mount options.
  *	@sb:	superblock in question
@@ -675,27 +538,31 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 	if (flags & MS_RDONLY)
 		acct_auto_close(sb);
 	shrink_dcache_sb(sb);
-	fsync_super(sb);
+	sync_filesystem(sb);
 
 	/* If we are remounting RDONLY and current sb is read/write,
 	   make sure there are no rw files opened */
 	if ((flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY)) {
 		if (force)
 			mark_files_ro(sb);
-		else if (!fs_may_remount_ro(sb))
+		else if (!fs_may_remount_ro(sb)) {
+			unlock_kernel();
 			return -EBUSY;
+		}
 		retval = vfs_dq_off(sb, 1);
-		if (retval < 0 && retval != -ENOSYS)
+		if (retval < 0 && retval != -ENOSYS) {
+			unlock_kernel();
 			return -EBUSY;
+		}
 	}
 	remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY);
 
 	if (sb->s_op->remount_fs) {
-		lock_super(sb);
 		retval = sb->s_op->remount_fs(sb, &flags, data);
-		unlock_super(sb);
-		if (retval)
+		if (retval) {
+			unlock_kernel();
 			return retval;
+		}
 	}
 	sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
 	if (remount_rw)
@@ -711,18 +578,17 @@ static void do_emergency_remount(struct work_struct *work)
 	list_for_each_entry(sb, &super_blocks, s_list) {
 		sb->s_count++;
 		spin_unlock(&sb_lock);
-		down_read(&sb->s_umount);
+		down_write(&sb->s_umount);
 		if (sb->s_root && sb->s_bdev && !(sb->s_flags & MS_RDONLY)) {
 			/*
 			 * ->remount_fs needs lock_kernel().
 			 *
 			 * What lock protects sb->s_flags??
 			 */
-			lock_kernel();
 			do_remount_sb(sb, MS_RDONLY, NULL, 1);
-			unlock_kernel();
 		}
-		drop_super(sb);
+		up_write(&sb->s_umount);
+		put_super(sb);
 		spin_lock(&sb_lock);
 	}
 	spin_unlock(&sb_lock);
diff --git a/fs/sync.c b/fs/sync.c
index 7abc65fbf21d..dd200025af85 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -13,38 +13,123 @@
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
+#include "internal.h"
 
 #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
 			SYNC_FILE_RANGE_WAIT_AFTER)
 
 /*
- * sync everything.  Start out by waking pdflush, because that writes back
- * all queues in parallel.
+ * Do the filesystem syncing work. For simple filesystems sync_inodes_sb(sb, 0)
+ * just dirties buffers with inodes so we have to submit IO for these buffers
+ * via __sync_blockdev(). This also speeds up the wait == 1 case since in that
+ * case write_inode() functions do sync_dirty_buffer() and thus effectively
+ * write one block at a time.
  */
-static void do_sync(unsigned long wait)
+static int __sync_filesystem(struct super_block *sb, int wait)
 {
-	wakeup_pdflush(0);
-	sync_inodes(0);		/* All mappings, inodes and their blockdevs */
-	vfs_dq_sync(NULL);
-	sync_supers();		/* Write the superblocks */
-	sync_filesystems(0);	/* Start syncing the filesystems */
-	sync_filesystems(wait);	/* Waitingly sync the filesystems */
-	sync_inodes(wait);	/* Mappings, inodes and blockdevs, again. */
+	/* Avoid doing twice syncing and cache pruning for quota sync */
 	if (!wait)
-		printk("Emergency Sync complete\n");
-	if (unlikely(laptop_mode))
-		laptop_sync_completion();
+		writeout_quota_sb(sb, -1);
+	else
+		sync_quota_sb(sb, -1);
+	sync_inodes_sb(sb, wait);
+	if (sb->s_op->sync_fs)
+		sb->s_op->sync_fs(sb, wait);
+	return __sync_blockdev(sb->s_bdev, wait);
+}
+
+/*
+ * Write out and wait upon all dirty data associated with this
+ * superblock.  Filesystem data as well as the underlying block
+ * device.  Takes the superblock lock.
+ */
+int sync_filesystem(struct super_block *sb)
+{
+	int ret;
+
+	/*
+	 * We need to be protected against the filesystem going from
+	 * r/o to r/w or vice versa.
+	 */
+	WARN_ON(!rwsem_is_locked(&sb->s_umount));
+
+	/*
+	 * No point in syncing out anything if the filesystem is read-only.
+	 */
+	if (sb->s_flags & MS_RDONLY)
+		return 0;
+
+	ret = __sync_filesystem(sb, 0);
+	if (ret < 0)
+		return ret;
+	return __sync_filesystem(sb, 1);
+}
+EXPORT_SYMBOL_GPL(sync_filesystem);
+
+/*
+ * Sync all the data for all the filesystems (called by sys_sync() and
+ * emergency sync)
+ *
+ * This operation is careful to avoid the livelock which could easily happen
+ * if two or more filesystems are being continuously dirtied.  s_need_sync
+ * is used only here.  We set it against all filesystems and then clear it as
+ * we sync them.  So redirtied filesystems are skipped.
+ *
+ * But if process A is currently running sync_filesystems and then process B
+ * calls sync_filesystems as well, process B will set all the s_need_sync
+ * flags again, which will cause process A to resync everything.  Fix that with
+ * a local mutex.
+ */
+static void sync_filesystems(int wait)
+{
+	struct super_block *sb;
+	static DEFINE_MUTEX(mutex);
+
+	mutex_lock(&mutex);		/* Could be down_interruptible */
+	spin_lock(&sb_lock);
+	list_for_each_entry(sb, &super_blocks, s_list)
+		sb->s_need_sync = 1;
+
+restart:
+	list_for_each_entry(sb, &super_blocks, s_list) {
+		if (!sb->s_need_sync)
+			continue;
+		sb->s_need_sync = 0;
+		sb->s_count++;
+		spin_unlock(&sb_lock);
+
+		down_read(&sb->s_umount);
+		if (!(sb->s_flags & MS_RDONLY) && sb->s_root)
+			__sync_filesystem(sb, wait);
+		up_read(&sb->s_umount);
+
+		/* restart only when sb is no longer on the list */
+		spin_lock(&sb_lock);
+		if (__put_super_and_need_restart(sb))
+			goto restart;
+	}
+	spin_unlock(&sb_lock);
+	mutex_unlock(&mutex);
 }
 
 SYSCALL_DEFINE0(sync)
 {
-	do_sync(1);
+	sync_filesystems(0);
+	sync_filesystems(1);
+	if (unlikely(laptop_mode))
+		laptop_sync_completion();
 	return 0;
 }
 
 static void do_sync_work(struct work_struct *work)
 {
-	do_sync(0);
+	/*
+	 * Sync twice to reduce the possibility we skipped some inodes / pages
+	 * because they were temporarily locked
+	 */
+	sync_filesystems(0);
+	sync_filesystems(0);
+	printk("Emergency Sync complete\n");
 	kfree(work);
 }
 
@@ -75,10 +160,8 @@ int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
 
 	/* sync the superblock to buffers */
 	sb = inode->i_sb;
-	lock_super(sb);
 	if (sb->s_dirt && sb->s_op->write_super)
 		sb->s_op->write_super(sb);
-	unlock_super(sb);
 
 	/* .. finally sync the buffers to disk */
 	err = sync_blockdev(sb->s_bdev);
diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index 56f655254bfe..c7798079e644 100644
--- a/fs/sysv/dir.c
+++ b/fs/sysv/dir.c
@@ -24,7 +24,7 @@ static int sysv_readdir(struct file *, void *, filldir_t);
 const struct file_operations sysv_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= sysv_readdir,
-	.fsync		= sysv_sync_file,
+	.fsync		= simple_fsync,
 };
 
 static inline void dir_put_page(struct page *page)
diff --git a/fs/sysv/file.c b/fs/sysv/file.c
index 589be21d884e..96340c01f4a7 100644
--- a/fs/sysv/file.c
+++ b/fs/sysv/file.c
@@ -26,7 +26,7 @@ const struct file_operations sysv_file_operations = {
 	.write		= do_sync_write,
 	.aio_write	= generic_file_aio_write,
 	.mmap		= generic_file_mmap,
-	.fsync		= sysv_sync_file,
+	.fsync		= simple_fsync,
 	.splice_read	= generic_file_splice_read,
 };
 
@@ -34,18 +34,3 @@ const struct inode_operations sysv_file_inode_operations = {
 	.truncate	= sysv_truncate,
 	.getattr	= sysv_getattr,
 };
-
-int sysv_sync_file(struct file * file, struct dentry *dentry, int datasync)
-{
-	struct inode *inode = dentry->d_inode;
-	int err;
-
-	err = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY))
-		return err;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		return err;
-	
-	err |= sysv_sync_inode(inode);
-	return err ? -EIO : 0;
-}
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index da20b48d350f..479923456a54 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -31,15 +31,13 @@
 #include <asm/byteorder.h>
 #include "sysv.h"
 
-/* This is only called on sync() and umount(), when s_dirt=1. */
-static void sysv_write_super(struct super_block *sb)
+static int sysv_sync_fs(struct super_block *sb, int wait)
 {
 	struct sysv_sb_info *sbi = SYSV_SB(sb);
 	unsigned long time = get_seconds(), old_time;
 
+	lock_super(sb);
 	lock_kernel();
-	if (sb->s_flags & MS_RDONLY)
-		goto clean;
 
 	/*
 	 * If we are going to write out the super block,
@@ -53,18 +51,30 @@ static void sysv_write_super(struct super_block *sb)
 		*sbi->s_sb_time = cpu_to_fs32(sbi, time);
 		mark_buffer_dirty(sbi->s_bh2);
 	}
-clean:
-	sb->s_dirt = 0;
+
 	unlock_kernel();
+	unlock_super(sb);
+
+	return 0;
+}
+
+static void sysv_write_super(struct super_block *sb)
+{
+	if (!(sb->s_flags & MS_RDONLY))
+		sysv_sync_fs(sb, 1);
+	else
+		sb->s_dirt = 0;
 }
 
 static int sysv_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct sysv_sb_info *sbi = SYSV_SB(sb);
+	lock_super(sb);
 	if (sbi->s_forced_ro)
 		*flags |= MS_RDONLY;
 	if (!(*flags & MS_RDONLY))
 		sb->s_dirt = 1;
+	unlock_super(sb);
 	return 0;
 }
 
@@ -72,6 +82,11 @@ static void sysv_put_super(struct super_block *sb)
 {
 	struct sysv_sb_info *sbi = SYSV_SB(sb);
 
+	lock_kernel();
+
+	if (sb->s_dirt)
+		sysv_write_super(sb);
+
 	if (!(sb->s_flags & MS_RDONLY)) {
 		/* XXX ext2 also updates the state here */
 		mark_buffer_dirty(sbi->s_bh1);
@@ -84,6 +99,8 @@ static void sysv_put_super(struct super_block *sb)
 		brelse(sbi->s_bh2);
 
 	kfree(sbi);
+
+	unlock_kernel();
 }
 
 static int sysv_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -236,7 +253,7 @@ bad_inode:
 	return ERR_PTR(-EIO);
 }
 
-static struct buffer_head * sysv_update_inode(struct inode * inode)
+int sysv_write_inode(struct inode *inode, int wait)
 {
 	struct super_block * sb = inode->i_sb;
 	struct sysv_sb_info * sbi = SYSV_SB(sb);
@@ -244,19 +261,21 @@ static struct buffer_head * sysv_update_inode(struct inode * inode)
 	struct sysv_inode * raw_inode;
 	struct sysv_inode_info * si;
 	unsigned int ino, block;
+	int err = 0;
 
 	ino = inode->i_ino;
 	if (!ino || ino > sbi->s_ninodes) {
 		printk("Bad inode number on dev %s: %d is out of range\n",
 		       inode->i_sb->s_id, ino);
-		return NULL;
+		return -EIO;
 	}
 	raw_inode = sysv_raw_inode(sb, ino, &bh);
 	if (!raw_inode) {
 		printk("unable to read i-node block\n");
-		return NULL;
+		return -EIO;
 	}
 
+	lock_kernel();
 	raw_inode->i_mode = cpu_to_fs16(sbi, inode->i_mode);
 	raw_inode->i_uid = cpu_to_fs16(sbi, fs_high2lowuid(inode->i_uid));
 	raw_inode->i_gid = cpu_to_fs16(sbi, fs_high2lowgid(inode->i_gid));
@@ -272,38 +291,23 @@ static struct buffer_head * sysv_update_inode(struct inode * inode)
 	for (block = 0; block < 10+1+1+1; block++)
 		write3byte(sbi, (u8 *)&si->i_data[block],
 			&raw_inode->i_data[3*block]);
-	mark_buffer_dirty(bh);
-	return bh;
-}
-
-int sysv_write_inode(struct inode * inode, int wait)
-{
-	struct buffer_head *bh;
-	lock_kernel();
-	bh = sysv_update_inode(inode);
-	brelse(bh);
 	unlock_kernel();
+	mark_buffer_dirty(bh);
+	if (wait) {
+                sync_dirty_buffer(bh);
+                if (buffer_req(bh) && !buffer_uptodate(bh)) {
+                        printk ("IO error syncing sysv inode [%s:%08x]\n",
+                                sb->s_id, ino);
+                        err = -EIO;
+                }
+        }
+	brelse(bh);
 	return 0;
 }
 
-int sysv_sync_inode(struct inode * inode)
+int sysv_sync_inode(struct inode *inode)
 {
-        int err = 0;
-        struct buffer_head *bh;
-
-        bh = sysv_update_inode(inode);
-        if (bh && buffer_dirty(bh)) {
-                sync_dirty_buffer(bh);
-                if (buffer_req(bh) && !buffer_uptodate(bh)) {
-                        printk ("IO error syncing sysv inode [%s:%08lx]\n",
-                                inode->i_sb->s_id, inode->i_ino);
-                        err = -1;
-                }
-        }
-        else if (!bh)
-                err = -1;
-        brelse (bh);
-        return err;
+	return sysv_write_inode(inode, 1);
 }
 
 static void sysv_delete_inode(struct inode *inode)
@@ -347,6 +351,7 @@ const struct super_operations sysv_sops = {
 	.delete_inode	= sysv_delete_inode,
 	.put_super	= sysv_put_super,
 	.write_super	= sysv_write_super,
+	.sync_fs	= sysv_sync_fs,
 	.remount_fs	= sysv_remount,
 	.statfs		= sysv_statfs,
 };
diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h
index 5784a318c883..53786eb5cf60 100644
--- a/fs/sysv/sysv.h
+++ b/fs/sysv/sysv.h
@@ -144,7 +144,6 @@ extern int __sysv_write_begin(struct file *file, struct address_space *mapping,
 extern struct inode *sysv_iget(struct super_block *, unsigned int);
 extern int sysv_write_inode(struct inode *, int);
 extern int sysv_sync_inode(struct inode *);
-extern int sysv_sync_file(struct file *, struct dentry *, int);
 extern void sysv_set_inode(struct inode *, dev_t);
 extern int sysv_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern int sysv_init_icache(void);
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index e9f7a754c4f7..3589eab02a2f 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -36,6 +36,7 @@
 #include <linux/mount.h>
 #include <linux/math64.h>
 #include <linux/writeback.h>
+#include <linux/smp_lock.h>
 #include "ubifs.h"
 
 /*
@@ -447,9 +448,6 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
 	if (!wait)
 		return 0;
 
-	if (sb->s_flags & MS_RDONLY)
-		return 0;
-
 	/*
 	 * VFS calls '->sync_fs()' before synchronizing all dirty inodes and
 	 * pages, so synchronize them first, then commit the journal. Strictly
@@ -1687,6 +1685,9 @@ static void ubifs_put_super(struct super_block *sb)
 
 	ubifs_msg("un-mount UBI device %d, volume %d", c->vi.ubi_num,
 		  c->vi.vol_id);
+
+	lock_kernel();
+
 	/*
 	 * The following asserts are only valid if there has not been a failure
 	 * of the media. For example, there will be dirty inodes if we failed
@@ -1753,6 +1754,8 @@ static void ubifs_put_super(struct super_block *sb)
 	ubi_close_volume(c->ubi);
 	mutex_unlock(&c->umount_mutex);
 	kfree(c);
+
+	unlock_kernel();
 }
 
 static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
@@ -1768,17 +1771,22 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
 		return err;
 	}
 
+	lock_kernel();
 	if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) {
 		if (c->ro_media) {
 			ubifs_msg("cannot re-mount due to prior errors");
+			unlock_kernel();
 			return -EROFS;
 		}
 		err = ubifs_remount_rw(c);
-		if (err)
+		if (err) {
+			unlock_kernel();
 			return err;
+		}
 	} else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) {
 		if (c->ro_media) {
 			ubifs_msg("cannot re-mount due to prior errors");
+			unlock_kernel();
 			return -EROFS;
 		}
 		ubifs_remount_ro(c);
@@ -1793,6 +1801,7 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
 	}
 
 	ubifs_assert(c->lst.taken_empty_lebs > 0);
+	unlock_kernel();
 	return 0;
 }
 
diff --git a/fs/udf/Makefile b/fs/udf/Makefile
index 0d4503f7446d..eb880f66c23a 100644
--- a/fs/udf/Makefile
+++ b/fs/udf/Makefile
@@ -5,5 +5,5 @@
 obj-$(CONFIG_UDF_FS) += udf.o
 
 udf-objs     := balloc.o dir.o file.o ialloc.o inode.o lowlevel.o namei.o \
-		partition.o super.o truncate.o symlink.o fsync.o \
+		partition.o super.o truncate.o symlink.o \
 		directory.o misc.o udftime.o unicode.o
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 2efd4d5291b6..61d9a76a3a69 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -210,5 +210,5 @@ const struct file_operations udf_dir_operations = {
 	.read			= generic_read_dir,
 	.readdir		= udf_readdir,
 	.ioctl			= udf_ioctl,
-	.fsync			= udf_fsync_file,
+	.fsync			= simple_fsync,
 };
diff --git a/fs/udf/file.c b/fs/udf/file.c
index eb91f3b70320..7464305382b5 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -209,7 +209,7 @@ const struct file_operations udf_file_operations = {
 	.write			= do_sync_write,
 	.aio_write		= udf_file_aio_write,
 	.release		= udf_release_file,
-	.fsync			= udf_fsync_file,
+	.fsync			= simple_fsync,
 	.splice_read		= generic_file_splice_read,
 	.llseek			= generic_file_llseek,
 };
diff --git a/fs/udf/fsync.c b/fs/udf/fsync.c
deleted file mode 100644
index b2c472b733b8..000000000000
--- a/fs/udf/fsync.c
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * fsync.c
- *
- * PURPOSE
- *  Fsync handling routines for the OSTA-UDF(tm) filesystem.
- *
- * COPYRIGHT
- *  This file is distributed under the terms of the GNU General Public
- *  License (GPL). Copies of the GPL can be obtained from:
- *      ftp://prep.ai.mit.edu/pub/gnu/GPL
- *  Each contributing author retains all rights to their own work.
- *
- *  (C) 1999-2001 Ben Fennema
- *  (C) 1999-2000 Stelias Computing Inc
- *
- * HISTORY
- *
- *  05/22/99 blf  Created.
- */
-
-#include "udfdecl.h"
-
-#include <linux/fs.h>
-
-static int udf_fsync_inode(struct inode *, int);
-
-/*
- *	File may be NULL when we are called. Perhaps we shouldn't
- *	even pass file to fsync ?
- */
-
-int udf_fsync_file(struct file *file, struct dentry *dentry, int datasync)
-{
-	struct inode *inode = dentry->d_inode;
-
-	return udf_fsync_inode(inode, datasync);
-}
-
-static int udf_fsync_inode(struct inode *inode, int datasync)
-{
-	int err;
-
-	err = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY))
-		return err;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		return err;
-
-	err |= udf_sync_inode(inode);
-
-	return err ? -EIO : 0;
-}
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 72348cc855a4..6832135159b6 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -568,6 +568,7 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
 	if (!udf_parse_options(options, &uopt, true))
 		return -EINVAL;
 
+	lock_kernel();
 	sbi->s_flags = uopt.flags;
 	sbi->s_uid   = uopt.uid;
 	sbi->s_gid   = uopt.gid;
@@ -581,13 +582,16 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
 			*flags |= MS_RDONLY;
 	}
 
-	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
+	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
+		unlock_kernel();
 		return 0;
+	}
 	if (*flags & MS_RDONLY)
 		udf_close_lvid(sb);
 	else
 		udf_open_lvid(sb);
 
+	unlock_kernel();
 	return 0;
 }
 
@@ -1915,7 +1919,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 	if (uopt.flags & (1 << UDF_FLAG_BLOCKSIZE_SET)) {
 		ret = udf_load_vrs(sb, &uopt, silent, &fileset);
 	} else {
-		uopt.blocksize = bdev_hardsect_size(sb->s_bdev);
+		uopt.blocksize = bdev_logical_block_size(sb->s_bdev);
 		ret = udf_load_vrs(sb, &uopt, silent, &fileset);
 		if (!ret && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
 			if (!silent)
@@ -2062,6 +2066,9 @@ static void udf_put_super(struct super_block *sb)
 	struct udf_sb_info *sbi;
 
 	sbi = UDF_SB(sb);
+
+	lock_kernel();
+
 	if (sbi->s_vat_inode)
 		iput(sbi->s_vat_inode);
 	if (sbi->s_partitions)
@@ -2077,6 +2084,8 @@ static void udf_put_super(struct super_block *sb)
 	kfree(sbi->s_partmaps);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
+
+	unlock_kernel();
 }
 
 static int udf_sync_fs(struct super_block *sb, int wait)
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index cac51b77a5d1..8d46f4294ee7 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -223,9 +223,6 @@ extern int udf_prealloc_blocks(struct super_block *, struct inode *, uint16_t,
 extern int udf_new_block(struct super_block *, struct inode *, uint16_t,
 			 uint32_t, int *);
 
-/* fsync.c */
-extern int udf_fsync_file(struct file *, struct dentry *, int);
-
 /* directory.c */
 extern struct fileIdentDesc *udf_fileident_read(struct inode *, loff_t *,
 						struct udf_fileident_bh *,
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 6321b797061b..6f671f1ac271 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -666,6 +666,6 @@ not_empty:
 const struct file_operations ufs_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= ufs_readdir,
-	.fsync		= ufs_sync_file,
+	.fsync		= simple_fsync,
 	.llseek		= generic_file_llseek,
 };
diff --git a/fs/ufs/file.c b/fs/ufs/file.c
index 2bd3a1615714..73655c61240a 100644
--- a/fs/ufs/file.c
+++ b/fs/ufs/file.c
@@ -24,31 +24,10 @@
  */
 
 #include <linux/fs.h>
-#include <linux/buffer_head.h>	/* for sync_mapping_buffers() */
 
 #include "ufs_fs.h"
 #include "ufs.h"
 
-
-int ufs_sync_file(struct file *file, struct dentry *dentry, int datasync)
-{
-	struct inode *inode = dentry->d_inode;
-	int err;
-	int ret;
-
-	ret = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY))
-		return ret;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		return ret;
-
-	err = ufs_sync_inode(inode);
-	if (ret == 0)
-		ret = err;
-	return ret;
-}
-
-
 /*
  * We have mostly NULL's here: the current defaults are ok for
  * the ufs filesystem.
@@ -62,6 +41,6 @@ const struct file_operations ufs_file_operations = {
 	.aio_write	= generic_file_aio_write,
 	.mmap		= generic_file_mmap,
 	.open           = generic_file_open,
-	.fsync		= ufs_sync_file,
+	.fsync		= simple_fsync,
 	.splice_read	= generic_file_splice_read,
 };
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 60359291761f..5faed7954d0a 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -263,6 +263,7 @@ void ufs_panic (struct super_block * sb, const char * function,
 	struct ufs_super_block_first * usb1;
 	va_list args;
 	
+	lock_kernel();
 	uspi = UFS_SB(sb)->s_uspi;
 	usb1 = ubh_get_usb_first(uspi);
 	
@@ -594,6 +595,9 @@ static void ufs_put_super_internal(struct super_block *sb)
 
 	
 	UFSD("ENTER\n");
+
+	lock_kernel();
+
 	ufs_put_cstotal(sb);
 	size = uspi->s_cssize;
 	blks = (size + uspi->s_fsize - 1) >> uspi->s_fshift;
@@ -621,6 +625,9 @@ static void ufs_put_super_internal(struct super_block *sb)
 		brelse (sbi->s_ucg[i]);
 	kfree (sbi->s_ucg);
 	kfree (base);
+
+	unlock_kernel();
+
 	UFSD("EXIT\n");
 }
 
@@ -1118,32 +1125,45 @@ failed_nomem:
 	return -ENOMEM;
 }
 
-static void ufs_write_super(struct super_block *sb)
+static int ufs_sync_fs(struct super_block *sb, int wait)
 {
 	struct ufs_sb_private_info * uspi;
 	struct ufs_super_block_first * usb1;
 	struct ufs_super_block_third * usb3;
 	unsigned flags;
 
+	lock_super(sb);
 	lock_kernel();
+
 	UFSD("ENTER\n");
+
 	flags = UFS_SB(sb)->s_flags;
 	uspi = UFS_SB(sb)->s_uspi;
 	usb1 = ubh_get_usb_first(uspi);
 	usb3 = ubh_get_usb_third(uspi);
 
-	if (!(sb->s_flags & MS_RDONLY)) {
-		usb1->fs_time = cpu_to_fs32(sb, get_seconds());
-		if ((flags & UFS_ST_MASK) == UFS_ST_SUN 
-		  || (flags & UFS_ST_MASK) == UFS_ST_SUNOS
-		  || (flags & UFS_ST_MASK) == UFS_ST_SUNx86)
-			ufs_set_fs_state(sb, usb1, usb3,
-					UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time));
-		ufs_put_cstotal(sb);
-	}
+	usb1->fs_time = cpu_to_fs32(sb, get_seconds());
+	if ((flags & UFS_ST_MASK) == UFS_ST_SUN  ||
+	    (flags & UFS_ST_MASK) == UFS_ST_SUNOS ||
+	    (flags & UFS_ST_MASK) == UFS_ST_SUNx86)
+		ufs_set_fs_state(sb, usb1, usb3,
+				UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time));
+	ufs_put_cstotal(sb);
 	sb->s_dirt = 0;
+
 	UFSD("EXIT\n");
 	unlock_kernel();
+	unlock_super(sb);
+
+	return 0;
+}
+
+static void ufs_write_super(struct super_block *sb)
+{
+	if (!(sb->s_flags & MS_RDONLY))
+		ufs_sync_fs(sb, 1);
+	else
+		sb->s_dirt = 0;
 }
 
 static void ufs_put_super(struct super_block *sb)
@@ -1152,6 +1172,9 @@ static void ufs_put_super(struct super_block *sb)
 		
 	UFSD("ENTER\n");
 
+	if (sb->s_dirt)
+		ufs_write_super(sb);
+
 	if (!(sb->s_flags & MS_RDONLY))
 		ufs_put_super_internal(sb);
 	
@@ -1171,7 +1194,9 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	struct ufs_super_block_third * usb3;
 	unsigned new_mount_opt, ufstype;
 	unsigned flags;
-	
+
+	lock_kernel();
+	lock_super(sb);
 	uspi = UFS_SB(sb)->s_uspi;
 	flags = UFS_SB(sb)->s_flags;
 	usb1 = ubh_get_usb_first(uspi);
@@ -1184,17 +1209,24 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	ufstype = UFS_SB(sb)->s_mount_opt & UFS_MOUNT_UFSTYPE;
 	new_mount_opt = 0;
 	ufs_set_opt (new_mount_opt, ONERROR_LOCK);
-	if (!ufs_parse_options (data, &new_mount_opt))
+	if (!ufs_parse_options (data, &new_mount_opt)) {
+		unlock_super(sb);
+		unlock_kernel();
 		return -EINVAL;
+	}
 	if (!(new_mount_opt & UFS_MOUNT_UFSTYPE)) {
 		new_mount_opt |= ufstype;
 	} else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) {
 		printk("ufstype can't be changed during remount\n");
+		unlock_super(sb);
+		unlock_kernel();
 		return -EINVAL;
 	}
 
 	if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		UFS_SB(sb)->s_mount_opt = new_mount_opt;
+		unlock_super(sb);
+		unlock_kernel();
 		return 0;
 	}
 	
@@ -1219,6 +1251,8 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 #ifndef CONFIG_UFS_FS_WRITE
 		printk("ufs was compiled with read-only support, "
 		"can't be mounted as read-write\n");
+		unlock_super(sb);
+		unlock_kernel();
 		return -EINVAL;
 #else
 		if (ufstype != UFS_MOUNT_UFSTYPE_SUN && 
@@ -1227,16 +1261,22 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 		    ufstype != UFS_MOUNT_UFSTYPE_SUNx86 &&
 		    ufstype != UFS_MOUNT_UFSTYPE_UFS2) {
 			printk("this ufstype is read-only supported\n");
+			unlock_super(sb);
+			unlock_kernel();
 			return -EINVAL;
 		}
 		if (!ufs_read_cylinder_structures(sb)) {
 			printk("failed during remounting\n");
+			unlock_super(sb);
+			unlock_kernel();
 			return -EPERM;
 		}
 		sb->s_flags &= ~MS_RDONLY;
 #endif
 	}
 	UFS_SB(sb)->s_mount_opt = new_mount_opt;
+	unlock_super(sb);
+	unlock_kernel();
 	return 0;
 }
 
@@ -1352,6 +1392,7 @@ static const struct super_operations ufs_super_ops = {
 	.delete_inode	= ufs_delete_inode,
 	.put_super	= ufs_put_super,
 	.write_super	= ufs_write_super,
+	.sync_fs	= ufs_sync_fs,
 	.statfs		= ufs_statfs,
 	.remount_fs	= ufs_remount,
 	.show_options   = ufs_show_options,
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index d0c4acd4f1f3..644e77e13599 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -99,7 +99,6 @@ extern void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
 extern const struct inode_operations ufs_file_inode_operations;
 extern const struct file_operations ufs_file_operations;
 extern const struct address_space_operations ufs_aops;
-extern int ufs_sync_file(struct file *, struct dentry *, int);
 
 /* ialloc.c */
 extern void ufs_free_inode (struct inode *inode);
diff --git a/fs/xattr.c b/fs/xattr.c
index d51b8f9db921..1c3d0af59ddf 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -297,7 +297,7 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
 		return error;
 	dentry = f->f_path.dentry;
 	audit_inode(NULL, dentry);
-	error = mnt_want_write(f->f_path.mnt);
+	error = mnt_want_write_file(f);
 	if (!error) {
 		error = setxattr(dentry, name, value, size, flags);
 		mnt_drop_write(f->f_path.mnt);
@@ -524,7 +524,7 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
 		return error;
 	dentry = f->f_path.dentry;
 	audit_inode(NULL, dentry);
-	error = mnt_want_write(f->f_path.mnt);
+	error = mnt_want_write_file(f);
 	if (!error) {
 		error = removexattr(dentry, name);
 		mnt_drop_write(f->f_path.mnt);
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index e28800a9f2b5..1418b916fc27 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1501,7 +1501,7 @@ xfs_setsize_buftarg_early(
 	struct block_device	*bdev)
 {
 	return xfs_setsize_buftarg_flags(btp,
-			PAGE_CACHE_SIZE, bdev_hardsect_size(bdev), 0);
+			PAGE_CACHE_SIZE, bdev_logical_block_size(bdev), 0);
 }
 
 int
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index bb685269f832..08d6bd9a3947 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -1104,15 +1104,6 @@ xfs_fs_put_super(
 	kfree(mp);
 }
 
-STATIC void
-xfs_fs_write_super(
-	struct super_block	*sb)
-{
-	if (!(sb->s_flags & MS_RDONLY))
-		xfs_sync_fsdata(XFS_M(sb), 0);
-	sb->s_dirt = 0;
-}
-
 STATIC int
 xfs_fs_sync_super(
 	struct super_block	*sb,
@@ -1137,7 +1128,6 @@ xfs_fs_sync_super(
 		error = xfs_quiesce_data(mp);
 	else
 		error = xfs_sync_fsdata(mp, 0);
-	sb->s_dirt = 0;
 
 	if (unlikely(laptop_mode)) {
 		int	prev_sync_seq = mp->m_sync_seq;
@@ -1443,7 +1433,6 @@ xfs_fs_fill_super(
 
 	XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, mtpt, mp->m_fsname);
 
-	sb->s_dirt = 1;
 	sb->s_magic = XFS_SB_MAGIC;
 	sb->s_blocksize = mp->m_sb.sb_blocksize;
 	sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
@@ -1533,7 +1522,6 @@ static struct super_operations xfs_super_operations = {
 	.write_inode		= xfs_fs_write_inode,
 	.clear_inode		= xfs_fs_clear_inode,
 	.put_super		= xfs_fs_put_super,
-	.write_super		= xfs_fs_write_super,
 	.sync_fs		= xfs_fs_sync_super,
 	.freeze_fs		= xfs_fs_freeze,
 	.statfs			= xfs_fs_statfs,
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 8570b826fedd..bcc39d358ad3 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -628,8 +628,6 @@ xfs_trans_apply_sb_deltas(
 		xfs_trans_log_buf(tp, bp, offsetof(xfs_dsb_t, sb_icount),
 				  offsetof(xfs_dsb_t, sb_frextents) +
 				  sizeof(sbp->sb_frextents) - 1);
-
-	tp->t_mountp->m_super->s_dirt = 1;
 }
 
 /*
diff --git a/include/Kbuild b/include/Kbuild
index d8c3e3cbf416..fe36accd4328 100644
--- a/include/Kbuild
+++ b/include/Kbuild
@@ -8,3 +8,4 @@ header-y += mtd/
 header-y += rdma/
 header-y += video/
 header-y += drm/
+header-y += xen/
diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index 76e27d66c055..b7babf0206b8 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -134,7 +134,7 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
 #define atomic_long_cmpxchg(l, old, new) \
 	(atomic64_cmpxchg((atomic64_t *)(l), (old), (new)))
 #define atomic_long_xchg(v, new) \
-	(atomic64_xchg((atomic64_t *)(l), (new)))
+	(atomic64_xchg((atomic64_t *)(v), (new)))
 
 #else  /*  BITS_PER_LONG == 64  */
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 8e6d0ca70aba..e410f602cab1 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -280,17 +280,18 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 #endif
 
 /*
- * A facility to provide batching of the reload of page tables with the
- * actual context switch code for paravirtualized guests.  By convention,
- * only one of the lazy modes (CPU, MMU) should be active at any given
- * time, entry should never be nested, and entry and exits should always
- * be paired.  This is for sanity of maintaining and reasoning about the
- * kernel code.
+ * A facility to provide batching of the reload of page tables and
+ * other process state with the actual context switch code for
+ * paravirtualized guests.  By convention, only one of the batched
+ * update (lazy) modes (CPU, MMU) should be active at any given time,
+ * entry should never be nested, and entry and exits should always be
+ * paired.  This is for sanity of maintaining and reasoning about the
+ * kernel code.  In this case, the exit (end of the context switch) is
+ * in architecture-specific code, and so doesn't need a generic
+ * definition.
  */
-#ifndef __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-#define arch_enter_lazy_cpu_mode()	do {} while (0)
-#define arch_leave_lazy_cpu_mode()	do {} while (0)
-#define arch_flush_lazy_cpu_mode()	do {} while (0)
+#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
+#define arch_start_context_switch(prev)	do {} while (0)
 #endif
 
 #ifndef __HAVE_PFNMAP_TRACKING
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 89853bcd27a6..f1736ca7922c 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -63,7 +63,7 @@
 #define BRANCH_PROFILE()
 #endif
 
-#ifdef CONFIG_EVENT_TRACER
+#ifdef CONFIG_EVENT_TRACING
 #define FTRACE_EVENTS()	VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
 			*(_ftrace_events)				\
 			VMLINUX_SYMBOL(__stop_ftrace_events) = .;
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 3f0eaa397ef5..b3afd2219ad2 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -135,6 +135,7 @@ header-y += posix_types.h
 header-y += ppdev.h
 header-y += prctl.h
 header-y += qnxtypes.h
+header-y += qnx4_fs.h
 header-y += radeonfb.h
 header-y += raw.h
 header-y += resource.h
@@ -308,7 +309,6 @@ unifdef-y += poll.h
 unifdef-y += ppp_defs.h
 unifdef-y += ppp-comp.h
 unifdef-y += ptrace.h
-unifdef-y += qnx4_fs.h
 unifdef-y += quota.h
 unifdef-y += random.h
 unifdef-y += irqnr.h
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 88be890ee3c7..51b4b0a5ce8c 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -119,7 +119,7 @@ extern int pci_mmcfg_config_num;
 extern int sbf_port;
 extern unsigned long acpi_realmode_flags;
 
-int acpi_register_gsi (u32 gsi, int triggering, int polarity);
+int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
 int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
 
 #ifdef CONFIG_X86_IO_APIC
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7b214fd672a2..12737be58601 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -218,12 +218,12 @@ struct bio {
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
 #define bio_empty_barrier(bio)	(bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))
 
-static inline unsigned int bio_cur_sectors(struct bio *bio)
+static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
 	if (bio->bi_vcnt)
-		return bio_iovec(bio)->bv_len >> 9;
+		return bio_iovec(bio)->bv_len;
 	else /* dataless requests such as discard */
-		return bio->bi_size >> 9;
+		return bio->bi_size;
 }
 
 static inline void *bio_data(struct bio *bio)
@@ -279,7 +279,7 @@ static inline int bio_has_allocated_vec(struct bio *bio)
 #define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \
 	(((addr1) | (mask)) == (((addr2) - 1) | (mask)))
 #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
-	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, (q)->seg_boundary_mask)
+	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q)))
 #define BIO_SEG_BOUNDARY(q, b1, b2) \
 	BIOVEC_SEG_BOUNDARY((q), __BVEC_END((b1)), __BVEC_START((b2)))
 
@@ -506,7 +506,7 @@ static inline int bio_has_data(struct bio *bio)
 }
 
 /*
- * BIO list managment for use by remapping drivers (e.g. DM or MD).
+ * BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
  *
  * A bio_list anchors a singly-linked list of bios chained through the bi_next
  * member of the bio.  The bio_list also caches the last list member to allow
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b4f71f1a4af7..ebdfde8fe556 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -166,19 +166,9 @@ struct request {
 	enum rq_cmd_type_bits cmd_type;
 	unsigned long atomic_flags;
 
-	/* Maintain bio traversal state for part by part I/O submission.
-	 * hard_* are block layer internals, no driver should touch them!
-	 */
-
-	sector_t sector;		/* next sector to submit */
-	sector_t hard_sector;		/* next sector to complete */
-	unsigned long nr_sectors;	/* no. of sectors left to submit */
-	unsigned long hard_nr_sectors;	/* no. of sectors left to complete */
-	/* no. of sectors left to submit in the current segment */
-	unsigned int current_nr_sectors;
-
-	/* no. of sectors left to complete in the current segment */
-	unsigned int hard_cur_sectors;
+	/* the following two fields are internal, NEVER access directly */
+	sector_t __sector;		/* sector cursor */
+	unsigned int __data_len;	/* total data len */
 
 	struct bio *bio;
 	struct bio *biotail;
@@ -211,8 +201,8 @@ struct request {
 
 	unsigned short ioprio;
 
-	void *special;
-	char *buffer;
+	void *special;		/* opaque pointer available for LLD use */
+	char *buffer;		/* kaddr of the current segment if available */
 
 	int tag;
 	int errors;
@@ -226,10 +216,9 @@ struct request {
 	unsigned char __cmd[BLK_MAX_CDB];
 	unsigned char *cmd;
 
-	unsigned int data_len;
 	unsigned int extra_len;	/* length of alignment and padding */
 	unsigned int sense_len;
-	void *data;
+	unsigned int resid_len;	/* residual count */
 	void *sense;
 
 	unsigned long deadline;
@@ -318,6 +307,26 @@ struct blk_cmd_filter {
 	struct kobject kobj;
 };
 
+struct queue_limits {
+	unsigned long		bounce_pfn;
+	unsigned long		seg_boundary_mask;
+
+	unsigned int		max_hw_sectors;
+	unsigned int		max_sectors;
+	unsigned int		max_segment_size;
+	unsigned int		physical_block_size;
+	unsigned int		alignment_offset;
+	unsigned int		io_min;
+	unsigned int		io_opt;
+
+	unsigned short		logical_block_size;
+	unsigned short		max_hw_segments;
+	unsigned short		max_phys_segments;
+
+	unsigned char		misaligned;
+	unsigned char		no_cluster;
+};
+
 struct request_queue
 {
 	/*
@@ -369,7 +378,6 @@ struct request_queue
 	/*
 	 * queue needs bounce pages for pages above this limit
 	 */
-	unsigned long		bounce_pfn;
 	gfp_t			bounce_gfp;
 
 	/*
@@ -398,14 +406,6 @@ struct request_queue
 	unsigned int		nr_congestion_off;
 	unsigned int		nr_batching;
 
-	unsigned int		max_sectors;
-	unsigned int		max_hw_sectors;
-	unsigned short		max_phys_segments;
-	unsigned short		max_hw_segments;
-	unsigned short		hardsect_size;
-	unsigned int		max_segment_size;
-
-	unsigned long		seg_boundary_mask;
 	void			*dma_drain_buffer;
 	unsigned int		dma_drain_size;
 	unsigned int		dma_pad_mask;
@@ -415,12 +415,14 @@ struct request_queue
 	struct list_head	tag_busy_list;
 
 	unsigned int		nr_sorted;
-	unsigned int		in_flight;
+	unsigned int		in_flight[2];
 
 	unsigned int		rq_timeout;
 	struct timer_list	timeout;
 	struct list_head	timeout_list;
 
+	struct queue_limits	limits;
+
 	/*
 	 * sg stuff
 	 */
@@ -522,6 +524,11 @@ static inline void queue_flag_clear_unlocked(unsigned int flag,
 	__clear_bit(flag, &q->queue_flags);
 }
 
+static inline int queue_in_flight(struct request_queue *q)
+{
+	return q->in_flight[0] + q->in_flight[1];
+}
+
 static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 {
 	WARN_ON_ONCE(!queue_is_locked(q));
@@ -752,10 +759,17 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
+extern struct request *blk_make_request(struct request_queue *, struct bio *,
+					gfp_t);
 extern void blk_insert_request(struct request_queue *, struct request *, int, void *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
 extern int blk_lld_busy(struct request_queue *q);
+extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
+			     struct bio_set *bs, gfp_t gfp_mask,
+			     int (*bio_ctr)(struct bio *, struct bio *, void *),
+			     void *data);
+extern void blk_rq_unprep_clone(struct request *rq);
 extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern void blk_plug_device(struct request_queue *);
@@ -767,12 +781,6 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 			 struct scsi_ioctl_command __user *);
 
-/*
- * Temporary export, until SCSI gets fixed up.
- */
-extern int blk_rq_append_bio(struct request_queue *q, struct request *rq,
-			     struct bio *bio);
-
 /*
  * A queue has just exitted congestion.  Note this in the global counter of
  * congested queues, and wake up anyone who was waiting for requests to be
@@ -798,7 +806,6 @@ extern void blk_sync_queue(struct request_queue *q);
 extern void __blk_stop_queue(struct request_queue *q);
 extern void __blk_run_queue(struct request_queue *);
 extern void blk_run_queue(struct request_queue *);
-extern void blk_start_queueing(struct request_queue *);
 extern int blk_rq_map_user(struct request_queue *, struct request *,
 			   struct rq_map_data *, void __user *, unsigned long,
 			   gfp_t);
@@ -831,41 +838,73 @@ static inline void blk_run_address_space(struct address_space *mapping)
 		blk_run_backing_dev(mapping->backing_dev_info, NULL);
 }
 
-extern void blkdev_dequeue_request(struct request *req);
+/*
+ * blk_rq_pos()		: the current sector
+ * blk_rq_bytes()	: bytes left in the entire request
+ * blk_rq_cur_bytes()	: bytes left in the current segment
+ * blk_rq_sectors()	: sectors left in the entire request
+ * blk_rq_cur_sectors()	: sectors left in the current segment
+ */
+static inline sector_t blk_rq_pos(const struct request *rq)
+{
+	return rq->__sector;
+}
+
+static inline unsigned int blk_rq_bytes(const struct request *rq)
+{
+	return rq->__data_len;
+}
+
+static inline int blk_rq_cur_bytes(const struct request *rq)
+{
+	return rq->bio ? bio_cur_bytes(rq->bio) : 0;
+}
+
+static inline unsigned int blk_rq_sectors(const struct request *rq)
+{
+	return blk_rq_bytes(rq) >> 9;
+}
+
+static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
+{
+	return blk_rq_cur_bytes(rq) >> 9;
+}
 
 /*
- * blk_end_request() and friends.
- * __blk_end_request() and end_request() must be called with
- * the request queue spinlock acquired.
+ * Request issue related functions.
+ */
+extern struct request *blk_peek_request(struct request_queue *q);
+extern void blk_start_request(struct request *rq);
+extern struct request *blk_fetch_request(struct request_queue *q);
+
+/*
+ * Request completion related functions.
+ *
+ * blk_update_request() completes given number of bytes and updates
+ * the request without completing it.
+ *
+ * blk_end_request() and friends.  __blk_end_request() must be called
+ * with the request queue spinlock acquired.
  *
  * Several drivers define their own end_request and call
  * blk_end_request() for parts of the original function.
  * This prevents code duplication in drivers.
  */
-extern int blk_end_request(struct request *rq, int error,
-				unsigned int nr_bytes);
-extern int __blk_end_request(struct request *rq, int error,
-				unsigned int nr_bytes);
-extern int blk_end_bidi_request(struct request *rq, int error,
-				unsigned int nr_bytes, unsigned int bidi_bytes);
-extern void end_request(struct request *, int);
-extern int blk_end_request_callback(struct request *rq, int error,
-				unsigned int nr_bytes,
-				int (drv_callback)(struct request *));
+extern bool blk_update_request(struct request *rq, int error,
+			       unsigned int nr_bytes);
+extern bool blk_end_request(struct request *rq, int error,
+			    unsigned int nr_bytes);
+extern void blk_end_request_all(struct request *rq, int error);
+extern bool blk_end_request_cur(struct request *rq, int error);
+extern bool __blk_end_request(struct request *rq, int error,
+			      unsigned int nr_bytes);
+extern void __blk_end_request_all(struct request *rq, int error);
+extern bool __blk_end_request_cur(struct request *rq, int error);
+
 extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
 extern void blk_abort_request(struct request *);
 extern void blk_abort_queue(struct request_queue *);
-extern void blk_update_request(struct request *rq, int error,
-			       unsigned int nr_bytes);
-
-/*
- * blk_end_request() takes bytes instead of sectors as a complete size.
- * blk_rq_bytes() returns bytes left to complete in the entire request.
- * blk_rq_cur_bytes() returns bytes left to complete in the current segment.
- */
-extern unsigned int blk_rq_bytes(struct request *rq);
-extern unsigned int blk_rq_cur_bytes(struct request *rq);
 
 /*
  * Access functions for manipulating queue properties
@@ -877,10 +916,20 @@ extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
 extern void blk_queue_max_sectors(struct request_queue *, unsigned int);
+extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
-extern void blk_queue_hardsect_size(struct request_queue *, unsigned short);
+extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
+extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
+extern void blk_queue_alignment_offset(struct request_queue *q,
+				       unsigned int alignment);
+extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
+extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
+extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
+			    sector_t offset);
+extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
+			      sector_t offset);
 extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
 extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
@@ -967,19 +1016,87 @@ extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
 
 #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
 
-static inline int queue_hardsect_size(struct request_queue *q)
+static inline unsigned long queue_bounce_pfn(struct request_queue *q)
+{
+	return q->limits.bounce_pfn;
+}
+
+static inline unsigned long queue_segment_boundary(struct request_queue *q)
+{
+	return q->limits.seg_boundary_mask;
+}
+
+static inline unsigned int queue_max_sectors(struct request_queue *q)
+{
+	return q->limits.max_sectors;
+}
+
+static inline unsigned int queue_max_hw_sectors(struct request_queue *q)
+{
+	return q->limits.max_hw_sectors;
+}
+
+static inline unsigned short queue_max_hw_segments(struct request_queue *q)
+{
+	return q->limits.max_hw_segments;
+}
+
+static inline unsigned short queue_max_phys_segments(struct request_queue *q)
+{
+	return q->limits.max_phys_segments;
+}
+
+static inline unsigned int queue_max_segment_size(struct request_queue *q)
+{
+	return q->limits.max_segment_size;
+}
+
+static inline unsigned short queue_logical_block_size(struct request_queue *q)
 {
 	int retval = 512;
 
-	if (q && q->hardsect_size)
-		retval = q->hardsect_size;
+	if (q && q->limits.logical_block_size)
+		retval = q->limits.logical_block_size;
 
 	return retval;
 }
 
-static inline int bdev_hardsect_size(struct block_device *bdev)
+static inline unsigned short bdev_logical_block_size(struct block_device *bdev)
 {
-	return queue_hardsect_size(bdev_get_queue(bdev));
+	return queue_logical_block_size(bdev_get_queue(bdev));
+}
+
+static inline unsigned int queue_physical_block_size(struct request_queue *q)
+{
+	return q->limits.physical_block_size;
+}
+
+static inline unsigned int queue_io_min(struct request_queue *q)
+{
+	return q->limits.io_min;
+}
+
+static inline unsigned int queue_io_opt(struct request_queue *q)
+{
+	return q->limits.io_opt;
+}
+
+static inline int queue_alignment_offset(struct request_queue *q)
+{
+	if (q && q->limits.misaligned)
+		return -1;
+
+	if (q && q->limits.alignment_offset)
+		return q->limits.alignment_offset;
+
+	return 0;
+}
+
+static inline int queue_sector_alignment_offset(struct request_queue *q,
+						sector_t sector)
+{
+	return ((sector << 9) - q->limits.alignment_offset)
+		& (q->limits.io_min - 1);
 }
 
 static inline int queue_dma_alignment(struct request_queue *q)
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index d960889e92ef..7e4350ece0f8 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -116,9 +116,9 @@ struct blk_io_trace {
  * The remap event
  */
 struct blk_io_trace_remap {
-	__be32 device;
 	__be32 device_from;
-	__be64 sector;
+	__be32 device_to;
+	__be64 sector_from;
 };
 
 enum {
@@ -165,8 +165,9 @@ struct blk_trace {
 
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(struct request_queue *);
-extern int do_blk_trace_setup(struct request_queue *q,
-	char *name, dev_t dev, struct blk_user_trace_setup *buts);
+extern int do_blk_trace_setup(struct request_queue *q, char *name,
+			      dev_t dev, struct block_device *bdev,
+			      struct blk_user_trace_setup *buts);
 extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 
 /**
@@ -193,22 +194,42 @@ extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
 				void *data, size_t len);
 extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+			   struct block_device *bdev,
 			   char __user *arg);
 extern int blk_trace_startstop(struct request_queue *q, int start);
 extern int blk_trace_remove(struct request_queue *q);
+extern int blk_trace_init_sysfs(struct device *dev);
 
 extern struct attribute_group blk_trace_attr_group;
 
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
-#define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
-#define blk_trace_shutdown(q)			do { } while (0)
-#define do_blk_trace_setup(q, name, dev, buts)	(-ENOTTY)
-#define blk_add_driver_data(q, rq, data, len)	do {} while (0)
-#define blk_trace_setup(q, name, dev, arg)	(-ENOTTY)
-#define blk_trace_startstop(q, start)		(-ENOTTY)
-#define blk_trace_remove(q)			(-ENOTTY)
-#define blk_add_trace_msg(q, fmt, ...)		do { } while (0)
+# define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
+# define blk_trace_shutdown(q)				do { } while (0)
+# define do_blk_trace_setup(q, name, dev, bdev, buts)	(-ENOTTY)
+# define blk_add_driver_data(q, rq, data, len)		do {} while (0)
+# define blk_trace_setup(q, name, dev, bdev, arg)	(-ENOTTY)
+# define blk_trace_startstop(q, start)			(-ENOTTY)
+# define blk_trace_remove(q)				(-ENOTTY)
+# define blk_add_trace_msg(q, fmt, ...)			do { } while (0)
+static inline int blk_trace_init_sysfs(struct device *dev)
+{
+	return 0;
+}
 
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
+
+static inline int blk_cmd_buf_len(struct request *rq)
+{
+	return blk_pc_request(rq) ? rq->cmd_len * 3 : 1;
+}
+
+extern void blk_dump_cmd(char *buf, struct request *rq);
+extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes);
+extern void blk_fill_rwbs_rq(char *rwbs, struct request *rq);
+
+#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
+
 #endif /* __KERNEL__ */
 #endif
diff --git a/include/linux/cdev.h b/include/linux/cdev.h
index fb4591977b03..f389e319a454 100644
--- a/include/linux/cdev.h
+++ b/include/linux/cdev.h
@@ -28,6 +28,8 @@ int cdev_add(struct cdev *, dev_t, unsigned);
 
 void cdev_del(struct cdev *);
 
+int cdev_index(struct inode *inode);
+
 void cd_forget(struct inode *);
 
 extern struct backing_dev_info directly_mappable_cdev_bdi;
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 5a40d14daa9f..c56457c8334e 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -288,7 +288,15 @@ static inline cycle_t clocksource_read(struct clocksource *cs)
  */
 static inline int clocksource_enable(struct clocksource *cs)
 {
-	return cs->enable ? cs->enable(cs) : 0;
+	int ret = 0;
+
+	if (cs->enable)
+		ret = cs->enable(cs);
+
+	/* save mult_orig on enable */
+	cs->mult_orig = cs->mult;
+
+	return ret;
 }
 
 /**
diff --git a/include/linux/compat.h b/include/linux/compat.h
index f2ded21f9a3c..af931ee43dd8 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -222,6 +222,8 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from);
 int copy_siginfo_to_user32(struct compat_siginfo __user *to, siginfo_t *from);
 int get_compat_sigevent(struct sigevent *event,
 		const struct compat_sigevent __user *u_event);
+long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig,
+				  struct compat_siginfo __user *uinfo);
 
 static inline int compat_timeval_compare(struct compat_timeval *lhs,
 					struct compat_timeval *rhs)
diff --git a/include/linux/cramfs_fs.h b/include/linux/cramfs_fs.h
index 3be4e5a27d82..6fc2bed368b8 100644
--- a/include/linux/cramfs_fs.h
+++ b/include/linux/cramfs_fs.h
@@ -2,9 +2,8 @@
 #define __CRAMFS_H
 
 #include <linux/types.h>
+#include <linux/magic.h>
 
-#define CRAMFS_MAGIC		0x28cd3d45	/* some random number */
-#define CRAMFS_MAGIC_WEND	0x453dcd28	/* magic number with the wrong endianess */
 #define CRAMFS_SIGNATURE	"Compressed ROMFS"
 
 /*
diff --git a/include/linux/cyclades.h b/include/linux/cyclades.h
index 788850ba4e75..1fbdea4f08eb 100644
--- a/include/linux/cyclades.h
+++ b/include/linux/cyclades.h
@@ -142,19 +142,6 @@ struct CYZ_BOOT_CTRL {
 
 
 #ifndef DP_WINDOW_SIZE
-/* #include "cyclomz.h" */
-/****************** ****************** *******************/
-/*
- *	The data types defined below are used in all ZFIRM interface
- *	data structures. They accomodate differences between HW
- *	architectures and compilers.
- */
-
-typedef __u64  ucdouble;		/* 64 bits, unsigned */
-typedef __u32  uclong;			/* 32 bits, unsigned */
-typedef __u16  ucshort;		/* 16 bits, unsigned */
-typedef __u8   ucchar;			/* 8 bits, unsigned */
-
 /*
  *	Memory Window Sizes
  */
@@ -507,16 +494,20 @@ struct ZFW_CTRL {
 
 /* Per card data structure */
 struct cyclades_card {
-    void __iomem *base_addr;
-    void __iomem *ctl_addr;
-    int irq;
-    unsigned int num_chips;	/* 0 if card absent, -1 if Z/PCI, else Y */
-    unsigned int first_line;	/* minor number of first channel on card */
-    unsigned int nports;	/* Number of ports in the card */
-    int bus_index;		/* address shift - 0 for ISA, 1 for PCI */
-    int intr_enabled;		/* FW Interrupt flag - 0 disabled, 1 enabled */
-    spinlock_t card_lock;
-    struct cyclades_port *ports;
+	void __iomem *base_addr;
+	union {
+		void __iomem *p9050;
+		struct RUNTIME_9060 __iomem *p9060;
+	} ctl_addr;
+	int irq;
+	unsigned int num_chips;	/* 0 if card absent, -1 if Z/PCI, else Y */
+	unsigned int first_line;	/* minor number of first channel on card */
+	unsigned int nports;	/* Number of ports in the card */
+	int bus_index;		/* address shift - 0 for ISA, 1 for PCI */
+	int intr_enabled;		/* FW Interrupt flag - 0 disabled, 1 enabled */
+	u32 hw_ver;
+	spinlock_t card_lock;
+	struct cyclades_port *ports;
 };
 
 /***************************************
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 15156364d196..30b93b2a01a4 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -180,10 +180,12 @@ d_iput:		no		no		no       yes
 #define DCACHE_REFERENCED	0x0008  /* Recently used, don't discard. */
 #define DCACHE_UNHASHED		0x0010	
 
-#define DCACHE_INOTIFY_PARENT_WATCHED	0x0020 /* Parent inode is watched */
+#define DCACHE_INOTIFY_PARENT_WATCHED	0x0020 /* Parent inode is watched by inotify */
 
 #define DCACHE_COOKIE		0x0040	/* For use by dcookie subsystem */
 
+#define DCACHE_FSNOTIFY_PARENT_WATCHED	0x0080 /* Parent inode is watched by some fsnotify listener */
+
 extern spinlock_t dcache_lock;
 extern seqlock_t rename_lock;
 
@@ -351,6 +353,11 @@ static inline int d_unhashed(struct dentry *dentry)
 	return (dentry->d_flags & DCACHE_UNHASHED);
 }
 
+static inline int d_unlinked(struct dentry *dentry)
+{
+	return d_unhashed(dentry) && !IS_ROOT(dentry);
+}
+
 static inline struct dentry *dget_parent(struct dentry *dentry)
 {
 	struct dentry *ret;
@@ -368,7 +375,7 @@ static inline int d_mountpoint(struct dentry *dentry)
 	return dentry->d_mounted;
 }
 
-extern struct vfsmount *lookup_mnt(struct vfsmount *, struct dentry *);
+extern struct vfsmount *lookup_mnt(struct path *);
 extern struct dentry *lookup_create(struct nameidata *nd, int is_dir);
 
 extern int sysctl_vfs_cache_pressure;
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index ded2d7c42668..49c2362977fd 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -149,7 +149,7 @@ struct io_restrictions {
 	unsigned max_hw_sectors;
 	unsigned max_sectors;
 	unsigned max_segment_size;
-	unsigned short hardsect_size;
+	unsigned short logical_block_size;
 	unsigned short max_hw_segments;
 	unsigned short max_phys_segments;
 	unsigned char no_cluster; /* inverted so that 0 is default */
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index 28d53cb7b5a2..171ad8aedc83 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -32,6 +32,8 @@ extern void dma_debug_add_bus(struct bus_type *bus);
 
 extern void dma_debug_init(u32 num_entries);
 
+extern int dma_debug_resize_entries(u32 num_entries);
+
 extern void debug_dma_map_page(struct device *dev, struct page *page,
 			       size_t offset, size_t size,
 			       int direction, dma_addr_t dma_addr,
@@ -91,6 +93,11 @@ static inline void dma_debug_init(u32 num_entries)
 {
 }
 
+static inline int dma_debug_resize_entries(u32 num_entries)
+{
+	return 0;
+}
+
 static inline void debug_dma_map_page(struct device *dev, struct page *page,
 				      size_t offset, size_t size,
 				      int direction, dma_addr_t dma_addr,
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index e397dc342cda..10ff5c498824 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -108,6 +108,7 @@ struct irte {
 };
 #ifdef CONFIG_INTR_REMAP
 extern int intr_remapping_enabled;
+extern int intr_remapping_supported(void);
 extern int enable_intr_remapping(int);
 extern void disable_intr_remapping(void);
 extern int reenable_intr_remapping(int);
@@ -157,6 +158,8 @@ static inline struct intel_iommu *map_ioapic_to_ir(int apic)
 }
 #define irq_remapped(irq)		(0)
 #define enable_intr_remapping(mode)	(-1)
+#define disable_intr_remapping()	(0)
+#define reenable_intr_remapping(mode)	(0)
 #define intr_remapping_enabled		(0)
 #endif
 
diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h
index 102a902b4396..ecc06286226d 100644
--- a/include/linux/dnotify.h
+++ b/include/linux/dnotify.h
@@ -10,7 +10,7 @@
 
 struct dnotify_struct {
 	struct dnotify_struct *	dn_next;
-	unsigned long		dn_mask;
+	__u32			dn_mask;
 	int			dn_fd;
 	struct file *		dn_filp;
 	fl_owner_t		dn_owner;
@@ -21,23 +21,18 @@ struct dnotify_struct {
 
 #ifdef CONFIG_DNOTIFY
 
-extern void __inode_dir_notify(struct inode *, unsigned long);
+#define DNOTIFY_ALL_EVENTS (FS_DELETE | FS_DELETE_CHILD |\
+			    FS_MODIFY | FS_MODIFY_CHILD |\
+			    FS_ACCESS | FS_ACCESS_CHILD |\
+			    FS_ATTRIB | FS_ATTRIB_CHILD |\
+			    FS_CREATE | FS_DN_RENAME |\
+			    FS_MOVED_FROM | FS_MOVED_TO)
+
 extern void dnotify_flush(struct file *, fl_owner_t);
 extern int fcntl_dirnotify(int, struct file *, unsigned long);
-extern void dnotify_parent(struct dentry *, unsigned long);
-
-static inline void inode_dir_notify(struct inode *inode, unsigned long event)
-{
-	if (inode->i_dnotify_mask & (event))
-		__inode_dir_notify(inode, event);
-}
 
 #else
 
-static inline void __inode_dir_notify(struct inode *inode, unsigned long event)
-{
-}
-
 static inline void dnotify_flush(struct file *filp, fl_owner_t id)
 {
 }
@@ -47,14 +42,6 @@ static inline int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 	return -EINVAL;
 }
 
-static inline void dnotify_parent(struct dentry *dentry, unsigned long event)
-{
-}
-
-static inline void inode_dir_notify(struct inode *inode, unsigned long event)
-{
-}
-
 #endif /* CONFIG_DNOTIFY */
 
 #endif /* __KERNEL __ */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index c59b769f62b0..1cb3372e65d8 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -103,10 +103,8 @@ extern int elv_merge(struct request_queue *, struct request **, struct bio *);
 extern void elv_merge_requests(struct request_queue *, struct request *,
 			       struct request *);
 extern void elv_merged_request(struct request_queue *, struct request *, int);
-extern void elv_dequeue_request(struct request_queue *, struct request *);
 extern void elv_requeue_request(struct request_queue *, struct request *);
 extern int elv_queue_empty(struct request_queue *);
-extern struct request *elv_next_request(struct request_queue *q);
 extern struct request *elv_former_request(struct request_queue *, struct request *);
 extern struct request *elv_latter_request(struct request_queue *, struct request *);
 extern int elv_register_queue(struct request_queue *q);
@@ -171,7 +169,7 @@ enum {
 	ELV_MQUEUE_MUST,
 };
 
-#define rq_end_sector(rq)	((rq)->sector + (rq)->nr_sectors)
+#define rq_end_sector(rq)	(blk_rq_pos(rq) + blk_rq_sectors(rq))
 #define rb_entry_rq(node)	rb_entry((node), struct request, rb_node)
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3b534e527e09..ede84fa7da5d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -729,8 +729,8 @@ struct inode {
 	struct timespec		i_atime;
 	struct timespec		i_mtime;
 	struct timespec		i_ctime;
-	unsigned int		i_blkbits;
 	blkcnt_t		i_blocks;
+	unsigned int		i_blkbits;
 	unsigned short          i_bytes;
 	umode_t			i_mode;
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
@@ -751,13 +751,12 @@ struct inode {
 		struct block_device	*i_bdev;
 		struct cdev		*i_cdev;
 	};
-	int			i_cindex;
 
 	__u32			i_generation;
 
-#ifdef CONFIG_DNOTIFY
-	unsigned long		i_dnotify_mask; /* Directory notify events */
-	struct dnotify_struct	*i_dnotify; /* for directory notifications */
+#ifdef CONFIG_FSNOTIFY
+	__u32			i_fsnotify_mask; /* all events this inode cares about */
+	struct hlist_head	i_fsnotify_mark_entries; /* fsnotify mark entries */
 #endif
 
 #ifdef CONFIG_INOTIFY
@@ -1321,7 +1320,7 @@ struct super_block {
 	struct rw_semaphore	s_umount;
 	struct mutex		s_lock;
 	int			s_count;
-	int			s_need_sync_fs;
+	int			s_need_sync;
 	atomic_t		s_active;
 #ifdef CONFIG_SECURITY
 	void                    *s_security;
@@ -1372,11 +1371,6 @@ struct super_block {
 	 * generic_show_options()
 	 */
 	char *s_options;
-
-	/*
-	 * storage for asynchronous operations
-	 */
-	struct list_head s_async_list;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
@@ -1800,7 +1794,7 @@ extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
 extern long do_mount(char *, char *, char *, unsigned long, void *);
-extern struct vfsmount *collect_mounts(struct vfsmount *, struct dentry *);
+extern struct vfsmount *collect_mounts(struct path *);
 extern void drop_collected_mounts(struct vfsmount *);
 
 extern int vfs_statfs(struct dentry *, struct kstatfs *);
@@ -1947,8 +1941,6 @@ extern struct super_block *freeze_bdev(struct block_device *);
 extern void emergency_thaw_all(void);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 extern int fsync_bdev(struct block_device *);
-extern int fsync_super(struct super_block *);
-extern int fsync_no_super(struct block_device *);
 #else
 static inline void bd_forget(struct inode *inode) {}
 static inline int sync_blockdev(struct block_device *bdev) { return 0; }
@@ -1964,6 +1956,7 @@ static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 	return 0;
 }
 #endif
+extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
 extern const struct file_operations bad_sock_fops;
@@ -2082,12 +2075,8 @@ extern int filemap_fdatawrite_range(struct address_space *mapping,
 
 extern int vfs_fsync(struct file *file, struct dentry *dentry, int datasync);
 extern void sync_supers(void);
-extern void sync_filesystems(int wait);
-extern void __fsync_super(struct super_block *sb);
 extern void emergency_sync(void);
 extern void emergency_remount(void);
-extern int do_remount_sb(struct super_block *sb, int flags,
-			 void *data, int force);
 #ifdef CONFIG_BLOCK
 extern sector_t bmap(struct inode *, sector_t);
 #endif
@@ -2205,6 +2194,8 @@ extern int generic_segment_checks(const struct iovec *iov,
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);
+extern ssize_t default_file_splice_read(struct file *, loff_t *,
+		struct pipe_inode_info *, size_t, unsigned int);
 extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
@@ -2354,6 +2345,8 @@ extern void simple_release_fs(struct vfsmount **mount, int *count);
 extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
 			loff_t *ppos, const void *from, size_t available);
 
+extern int simple_fsync(struct file *, struct dentry *, int);
+
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
 				struct page *, struct page *);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 00fbd5b245c9..936f9aa8bb97 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -13,6 +13,7 @@
 
 #include <linux/dnotify.h>
 #include <linux/inotify.h>
+#include <linux/fsnotify_backend.h>
 #include <linux/audit.h>
 
 /*
@@ -22,18 +23,44 @@
 static inline void fsnotify_d_instantiate(struct dentry *entry,
 						struct inode *inode)
 {
+	__fsnotify_d_instantiate(entry, inode);
+
 	inotify_d_instantiate(entry, inode);
 }
 
+/* Notify this dentry's parent about a child's events. */
+static inline void fsnotify_parent(struct dentry *dentry, __u32 mask)
+{
+	__fsnotify_parent(dentry, mask);
+
+	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
+}
+
 /*
  * fsnotify_d_move - entry has been moved
  * Called with dcache_lock and entry->d_lock held.
  */
 static inline void fsnotify_d_move(struct dentry *entry)
 {
+	/*
+	 * On move we need to update entry->d_flags to indicate if the new parent
+	 * cares about events from this entry.
+	 */
+	__fsnotify_update_dcache_flags(entry);
+
 	inotify_d_move(entry);
 }
 
+/*
+ * fsnotify_link_count - inode's link count changed
+ */
+static inline void fsnotify_link_count(struct inode *inode)
+{
+	inotify_inode_queue_event(inode, IN_ATTRIB, 0, NULL, NULL);
+
+	fsnotify(inode, FS_ATTRIB, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+}
+
 /*
  * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir
  */
@@ -42,42 +69,62 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 				 int isdir, struct inode *target, struct dentry *moved)
 {
 	struct inode *source = moved->d_inode;
-	u32 cookie = inotify_get_cookie();
+	u32 in_cookie = inotify_get_cookie();
+	u32 fs_cookie = fsnotify_get_cookie();
+	__u32 old_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_FROM);
+	__u32 new_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_TO);
 
 	if (old_dir == new_dir)
-		inode_dir_notify(old_dir, DN_RENAME);
-	else {
-		inode_dir_notify(old_dir, DN_DELETE);
-		inode_dir_notify(new_dir, DN_CREATE);
+		old_dir_mask |= FS_DN_RENAME;
+
+	if (isdir) {
+		isdir = IN_ISDIR;
+		old_dir_mask |= FS_IN_ISDIR;
+		new_dir_mask |= FS_IN_ISDIR;
 	}
 
-	if (isdir)
-		isdir = IN_ISDIR;
-	inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir,cookie,old_name,
+	inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir, in_cookie, old_name,
 				  source);
-	inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, cookie, new_name,
+	inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, in_cookie, new_name,
 				  source);
 
+	fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie);
+	fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie);
+
 	if (target) {
 		inotify_inode_queue_event(target, IN_DELETE_SELF, 0, NULL, NULL);
 		inotify_inode_is_dead(target);
+
+		/* this is really a link_count change not a removal */
+		fsnotify_link_count(target);
 	}
 
 	if (source) {
 		inotify_inode_queue_event(source, IN_MOVE_SELF, 0, NULL, NULL);
+		fsnotify(source, FS_MOVE_SELF, moved->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 	}
 	audit_inode_child(new_name, moved, new_dir);
 }
 
+/*
+ * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed
+ */
+static inline void fsnotify_inode_delete(struct inode *inode)
+{
+	__fsnotify_inode_delete(inode);
+}
+
 /*
  * fsnotify_nameremove - a filename was removed from a directory
  */
 static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
 {
+	__u32 mask = FS_DELETE;
+
 	if (isdir)
-		isdir = IN_ISDIR;
-	dnotify_parent(dentry, DN_DELETE);
-	inotify_dentry_parent_queue_event(dentry, IN_DELETE|isdir, 0, dentry->d_name.name);
+		mask |= FS_IN_ISDIR;
+
+	fsnotify_parent(dentry, mask);
 }
 
 /*
@@ -87,14 +134,9 @@ static inline void fsnotify_inoderemove(struct inode *inode)
 {
 	inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL, NULL);
 	inotify_inode_is_dead(inode);
-}
 
-/*
- * fsnotify_link_count - inode's link count changed
- */
-static inline void fsnotify_link_count(struct inode *inode)
-{
-	inotify_inode_queue_event(inode, IN_ATTRIB, 0, NULL, NULL);
+	fsnotify(inode, FS_DELETE_SELF, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	__fsnotify_inode_delete(inode);
 }
 
 /*
@@ -102,10 +144,11 @@ static inline void fsnotify_link_count(struct inode *inode)
  */
 static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
 {
-	inode_dir_notify(inode, DN_CREATE);
 	inotify_inode_queue_event(inode, IN_CREATE, 0, dentry->d_name.name,
 				  dentry->d_inode);
 	audit_inode_child(dentry->d_name.name, dentry, inode);
+
+	fsnotify(inode, FS_CREATE, dentry->d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0);
 }
 
 /*
@@ -115,11 +158,12 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
  */
 static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry)
 {
-	inode_dir_notify(dir, DN_CREATE);
 	inotify_inode_queue_event(dir, IN_CREATE, 0, new_dentry->d_name.name,
 				  inode);
 	fsnotify_link_count(inode);
 	audit_inode_child(new_dentry->d_name.name, new_dentry, dir);
+
+	fsnotify(dir, FS_CREATE, inode, FSNOTIFY_EVENT_INODE, new_dentry->d_name.name, 0);
 }
 
 /*
@@ -127,10 +171,13 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct
  */
 static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 {
-	inode_dir_notify(inode, DN_CREATE);
-	inotify_inode_queue_event(inode, IN_CREATE | IN_ISDIR, 0, 
-				  dentry->d_name.name, dentry->d_inode);
+	__u32 mask = (FS_CREATE | FS_IN_ISDIR);
+	struct inode *d_inode = dentry->d_inode;
+
+	inotify_inode_queue_event(inode, mask, 0, dentry->d_name.name, d_inode);
 	audit_inode_child(dentry->d_name.name, dentry, inode);
+
+	fsnotify(inode, mask, d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0);
 }
 
 /*
@@ -139,14 +186,15 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 static inline void fsnotify_access(struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
-	u32 mask = IN_ACCESS;
+	__u32 mask = FS_ACCESS;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= IN_ISDIR;
+		mask |= FS_IN_ISDIR;
 
-	dnotify_parent(dentry, DN_ACCESS);
-	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
 	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+	fsnotify_parent(dentry, mask);
+	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -155,14 +203,15 @@ static inline void fsnotify_access(struct dentry *dentry)
 static inline void fsnotify_modify(struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
-	u32 mask = IN_MODIFY;
+	__u32 mask = FS_MODIFY;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= IN_ISDIR;
+		mask |= FS_IN_ISDIR;
 
-	dnotify_parent(dentry, DN_MODIFY);
-	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
 	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+	fsnotify_parent(dentry, mask);
+	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -171,13 +220,15 @@ static inline void fsnotify_modify(struct dentry *dentry)
 static inline void fsnotify_open(struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
-	u32 mask = IN_OPEN;
+	__u32 mask = FS_OPEN;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= IN_ISDIR;
+		mask |= FS_IN_ISDIR;
 
-	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
 	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+	fsnotify_parent(dentry, mask);
+	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -187,15 +238,16 @@ static inline void fsnotify_close(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
-	const char *name = dentry->d_name.name;
 	fmode_t mode = file->f_mode;
-	u32 mask = (mode & FMODE_WRITE) ? IN_CLOSE_WRITE : IN_CLOSE_NOWRITE;
+	__u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= IN_ISDIR;
+		mask |= FS_IN_ISDIR;
 
-	inotify_dentry_parent_queue_event(dentry, mask, 0, name);
 	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+	fsnotify_parent(dentry, mask);
+	fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0);
 }
 
 /*
@@ -204,13 +256,15 @@ static inline void fsnotify_close(struct file *file)
 static inline void fsnotify_xattr(struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
-	u32 mask = IN_ATTRIB;
+	__u32 mask = FS_ATTRIB;
 
 	if (S_ISDIR(inode->i_mode))
-		mask |= IN_ISDIR;
+		mask |= FS_IN_ISDIR;
 
-	inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
 	inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+	fsnotify_parent(dentry, mask);
+	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -220,50 +274,37 @@ static inline void fsnotify_xattr(struct dentry *dentry)
 static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 {
 	struct inode *inode = dentry->d_inode;
-	int dn_mask = 0;
-	u32 in_mask = 0;
+	__u32 mask = 0;
+
+	if (ia_valid & ATTR_UID)
+		mask |= FS_ATTRIB;
+	if (ia_valid & ATTR_GID)
+		mask |= FS_ATTRIB;
+	if (ia_valid & ATTR_SIZE)
+		mask |= FS_MODIFY;
 
-	if (ia_valid & ATTR_UID) {
-		in_mask |= IN_ATTRIB;
-		dn_mask |= DN_ATTRIB;
-	}
-	if (ia_valid & ATTR_GID) {
-		in_mask |= IN_ATTRIB;
-		dn_mask |= DN_ATTRIB;
-	}
-	if (ia_valid & ATTR_SIZE) {
-		in_mask |= IN_MODIFY;
-		dn_mask |= DN_MODIFY;
-	}
 	/* both times implies a utime(s) call */
 	if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME))
-	{
-		in_mask |= IN_ATTRIB;
-		dn_mask |= DN_ATTRIB;
-	} else if (ia_valid & ATTR_ATIME) {
-		in_mask |= IN_ACCESS;
-		dn_mask |= DN_ACCESS;
-	} else if (ia_valid & ATTR_MTIME) {
-		in_mask |= IN_MODIFY;
-		dn_mask |= DN_MODIFY;
-	}
-	if (ia_valid & ATTR_MODE) {
-		in_mask |= IN_ATTRIB;
-		dn_mask |= DN_ATTRIB;
-	}
+		mask |= FS_ATTRIB;
+	else if (ia_valid & ATTR_ATIME)
+		mask |= FS_ACCESS;
+	else if (ia_valid & ATTR_MTIME)
+		mask |= FS_MODIFY;
 
-	if (dn_mask)
-		dnotify_parent(dentry, dn_mask);
-	if (in_mask) {
+	if (ia_valid & ATTR_MODE)
+		mask |= FS_ATTRIB;
+
+	if (mask) {
 		if (S_ISDIR(inode->i_mode))
-			in_mask |= IN_ISDIR;
-		inotify_inode_queue_event(inode, in_mask, 0, NULL, NULL);
-		inotify_dentry_parent_queue_event(dentry, in_mask, 0,
-						  dentry->d_name.name);
+			mask |= FS_IN_ISDIR;
+		inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+		fsnotify_parent(dentry, mask);
+		fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 	}
 }
 
-#ifdef CONFIG_INOTIFY	/* inotify helpers */
+#if defined(CONFIG_INOTIFY) || defined(CONFIG_FSNOTIFY)	/* notify helpers */
 
 /*
  * fsnotify_oldname_init - save off the old filename before we change it
@@ -281,7 +322,7 @@ static inline void fsnotify_oldname_free(const char *old_name)
 	kfree(old_name);
 }
 
-#else	/* CONFIG_INOTIFY */
+#else	/* CONFIG_INOTIFY || CONFIG_FSNOTIFY */
 
 static inline const char *fsnotify_oldname_init(const char *name)
 {
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
new file mode 100644
index 000000000000..44848aa830dc
--- /dev/null
+++ b/include/linux/fsnotify_backend.h
@@ -0,0 +1,387 @@
+/*
+ * Filesystem access notification for Linux
+ *
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+#ifndef __LINUX_FSNOTIFY_BACKEND_H
+#define __LINUX_FSNOTIFY_BACKEND_H
+
+#ifdef __KERNEL__
+
+#include <linux/idr.h> /* inotify uses this */
+#include <linux/fs.h> /* struct inode */
+#include <linux/list.h>
+#include <linux/path.h> /* struct path */
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include <asm/atomic.h>
+
+/*
+ * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily
+ * convert between them.  dnotify only needs conversion at watch creation
+ * so no perf loss there.  fanotify isn't defined yet, so it can use the
+ * wholes if it needs more events.
+ */
+#define FS_ACCESS		0x00000001	/* File was accessed */
+#define FS_MODIFY		0x00000002	/* File was modified */
+#define FS_ATTRIB		0x00000004	/* Metadata changed */
+#define FS_CLOSE_WRITE		0x00000008	/* Writtable file was closed */
+#define FS_CLOSE_NOWRITE	0x00000010	/* Unwrittable file closed */
+#define FS_OPEN			0x00000020	/* File was opened */
+#define FS_MOVED_FROM		0x00000040	/* File was moved from X */
+#define FS_MOVED_TO		0x00000080	/* File was moved to Y */
+#define FS_CREATE		0x00000100	/* Subfile was created */
+#define FS_DELETE		0x00000200	/* Subfile was deleted */
+#define FS_DELETE_SELF		0x00000400	/* Self was deleted */
+#define FS_MOVE_SELF		0x00000800	/* Self was moved */
+
+#define FS_UNMOUNT		0x00002000	/* inode on umount fs */
+#define FS_Q_OVERFLOW		0x00004000	/* Event queued overflowed */
+#define FS_IN_IGNORED		0x00008000	/* last inotify event here */
+
+#define FS_IN_ISDIR		0x40000000	/* event occurred against dir */
+#define FS_IN_ONESHOT		0x80000000	/* only send event once */
+
+#define FS_DN_RENAME		0x10000000	/* file renamed */
+#define FS_DN_MULTISHOT		0x20000000	/* dnotify multishot */
+
+/* This inode cares about things that happen to its children.  Always set for
+ * dnotify and inotify. */
+#define FS_EVENT_ON_CHILD	0x08000000
+
+/* This is a list of all events that may get sent to a parernt based on fs event
+ * happening to inodes inside that directory */
+#define FS_EVENTS_POSS_ON_CHILD   (FS_ACCESS | FS_MODIFY | FS_ATTRIB |\
+				   FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN |\
+				   FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE |\
+				   FS_DELETE)
+
+/* listeners that hard code group numbers near the top */
+#define DNOTIFY_GROUP_NUM	UINT_MAX
+#define INOTIFY_GROUP_NUM	(DNOTIFY_GROUP_NUM-1)
+
+struct fsnotify_group;
+struct fsnotify_event;
+struct fsnotify_mark_entry;
+struct fsnotify_event_private_data;
+
+/*
+ * Each group much define these ops.  The fsnotify infrastructure will call
+ * these operations for each relevant group.
+ *
+ * should_send_event - given a group, inode, and mask this function determines
+ *		if the group is interested in this event.
+ * handle_event - main call for a group to handle an fs event
+ * free_group_priv - called when a group refcnt hits 0 to clean up the private union
+ * freeing-mark - this means that a mark has been flagged to die when everything
+ *		finishes using it.  The function is supplied with what must be a
+ *		valid group and inode to use to clean up.
+ */
+struct fsnotify_ops {
+	bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, __u32 mask);
+	int (*handle_event)(struct fsnotify_group *group, struct fsnotify_event *event);
+	void (*free_group_priv)(struct fsnotify_group *group);
+	void (*freeing_mark)(struct fsnotify_mark_entry *entry, struct fsnotify_group *group);
+	void (*free_event_priv)(struct fsnotify_event_private_data *priv);
+};
+
+/*
+ * A group is a "thing" that wants to receive notification about filesystem
+ * events.  The mask holds the subset of event types this group cares about.
+ * refcnt on a group is up to the implementor and at any moment if it goes 0
+ * everything will be cleaned up.
+ */
+struct fsnotify_group {
+	/*
+	 * global list of all groups receiving events from fsnotify.
+	 * anchored by fsnotify_groups and protected by either fsnotify_grp_mutex
+	 * or fsnotify_grp_srcu depending on write vs read.
+	 */
+	struct list_head group_list;
+
+	/*
+	 * Defines all of the event types in which this group is interested.
+	 * This mask is a bitwise OR of the FS_* events from above.  Each time
+	 * this mask changes for a group (if it changes) the correct functions
+	 * must be called to update the global structures which indicate global
+	 * interest in event types.
+	 */
+	__u32 mask;
+
+	/*
+	 * How the refcnt is used is up to each group.  When the refcnt hits 0
+	 * fsnotify will clean up all of the resources associated with this group.
+	 * As an example, the dnotify group will always have a refcnt=1 and that
+	 * will never change.  Inotify, on the other hand, has a group per
+	 * inotify_init() and the refcnt will hit 0 only when that fd has been
+	 * closed.
+	 */
+	atomic_t refcnt;		/* things with interest in this group */
+	unsigned int group_num;		/* simply prevents accidental group collision */
+
+	const struct fsnotify_ops *ops;	/* how this group handles things */
+
+	/* needed to send notification to userspace */
+	struct mutex notification_mutex;	/* protect the notification_list */
+	struct list_head notification_list;	/* list of event_holder this group needs to send to userspace */
+	wait_queue_head_t notification_waitq;	/* read() on the notification file blocks on this waitq */
+	unsigned int q_len;			/* events on the queue */
+	unsigned int max_events;		/* maximum events allowed on the list */
+
+	/* stores all fastapth entries assoc with this group so they can be cleaned on unregister */
+	spinlock_t mark_lock;		/* protect mark_entries list */
+	atomic_t num_marks;		/* 1 for each mark entry and 1 for not being
+					 * past the point of no return when freeing
+					 * a group */
+	struct list_head mark_entries;	/* all inode mark entries for this group */
+
+	/* prevents double list_del of group_list.  protected by global fsnotify_grp_mutex */
+	bool on_group_list;
+
+	/* groups can define private fields here or use the void *private */
+	union {
+		void *private;
+#ifdef CONFIG_INOTIFY_USER
+		struct inotify_group_private_data {
+			spinlock_t	idr_lock;
+			struct idr      idr;
+			u32             last_wd;
+			struct fasync_struct    *fa;    /* async notification */
+			struct user_struct      *user;
+		} inotify_data;
+#endif
+	};
+};
+
+/*
+ * A single event can be queued in multiple group->notification_lists.
+ *
+ * each group->notification_list will point to an event_holder which in turns points
+ * to the actual event that needs to be sent to userspace.
+ *
+ * Seemed cheaper to create a refcnt'd event and a small holder for every group
+ * than create a different event for every group
+ *
+ */
+struct fsnotify_event_holder {
+	struct fsnotify_event *event;
+	struct list_head event_list;
+};
+
+/*
+ * Inotify needs to tack data onto an event.  This struct lets us later find the
+ * correct private data of the correct group.
+ */
+struct fsnotify_event_private_data {
+	struct fsnotify_group *group;
+	struct list_head event_list;
+};
+
+/*
+ * all of the information about the original object we want to now send to
+ * a group.  If you want to carry more info from the accessing task to the
+ * listener this structure is where you need to be adding fields.
+ */
+struct fsnotify_event {
+	/*
+	 * If we create an event we are also likely going to need a holder
+	 * to link to a group.  So embed one holder in the event.  Means only
+	 * one allocation for the common case where we only have one group
+	 */
+	struct fsnotify_event_holder holder;
+	spinlock_t lock;	/* protection for the associated event_holder and private_list */
+	/* to_tell may ONLY be dereferenced during handle_event(). */
+	struct inode *to_tell;	/* either the inode the event happened to or its parent */
+	/*
+	 * depending on the event type we should have either a path or inode
+	 * We hold a reference on path, but NOT on inode.  Since we have the ref on
+	 * the path, it may be dereferenced at any point during this object's
+	 * lifetime.  That reference is dropped when this object's refcnt hits
+	 * 0.  If this event contains an inode instead of a path, the inode may
+	 * ONLY be used during handle_event().
+	 */
+	union {
+		struct path path;
+		struct inode *inode;
+	};
+/* when calling fsnotify tell it if the data is a path or inode */
+#define FSNOTIFY_EVENT_NONE	0
+#define FSNOTIFY_EVENT_PATH	1
+#define FSNOTIFY_EVENT_INODE	2
+#define FSNOTIFY_EVENT_FILE	3
+	int data_type;		/* which of the above union we have */
+	atomic_t refcnt;	/* how many groups still are using/need to send this event */
+	__u32 mask;		/* the type of access, bitwise OR for FS_* event types */
+
+	u32 sync_cookie;	/* used to corrolate events, namely inotify mv events */
+	char *file_name;
+	size_t name_len;
+
+	struct list_head private_data_list;	/* groups can store private data here */
+};
+
+/*
+ * a mark is simply an entry attached to an in core inode which allows an
+ * fsnotify listener to indicate they are either no longer interested in events
+ * of a type matching mask or only interested in those events.
+ *
+ * these are flushed when an inode is evicted from core and may be flushed
+ * when the inode is modified (as seen by fsnotify_access).  Some fsnotify users
+ * (such as dnotify) will flush these when the open fd is closed and not at
+ * inode eviction or modification.
+ */
+struct fsnotify_mark_entry {
+	__u32 mask;			/* mask this mark entry is for */
+	/* we hold ref for each i_list and g_list.  also one ref for each 'thing'
+	 * in kernel that found and may be using this mark. */
+	atomic_t refcnt;		/* active things looking at this mark */
+	struct inode *inode;		/* inode this entry is associated with */
+	struct fsnotify_group *group;	/* group this mark entry is for */
+	struct hlist_node i_list;	/* list of mark_entries by inode->i_fsnotify_mark_entries */
+	struct list_head g_list;	/* list of mark_entries by group->i_fsnotify_mark_entries */
+	spinlock_t lock;		/* protect group, inode, and killme */
+	struct list_head free_i_list;	/* tmp list used when freeing this mark */
+	struct list_head free_g_list;	/* tmp list used when freeing this mark */
+	void (*free_mark)(struct fsnotify_mark_entry *entry); /* called on final put+free */
+};
+
+#ifdef CONFIG_FSNOTIFY
+
+/* called from the vfs helpers */
+
+/* main fsnotify call to send events */
+extern void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
+		     const char *name, u32 cookie);
+extern void __fsnotify_parent(struct dentry *dentry, __u32 mask);
+extern void __fsnotify_inode_delete(struct inode *inode);
+extern u32 fsnotify_get_cookie(void);
+
+static inline int fsnotify_inode_watches_children(struct inode *inode)
+{
+	/* FS_EVENT_ON_CHILD is set if the inode may care */
+	if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD))
+		return 0;
+	/* this inode might care about child events, does it care about the
+	 * specific set of events that can happen on a child? */
+	return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD;
+}
+
+/*
+ * Update the dentry with a flag indicating the interest of its parent to receive
+ * filesystem events when those events happens to this dentry->d_inode.
+ */
+static inline void __fsnotify_update_dcache_flags(struct dentry *dentry)
+{
+	struct dentry *parent;
+
+	assert_spin_locked(&dcache_lock);
+	assert_spin_locked(&dentry->d_lock);
+
+	parent = dentry->d_parent;
+	if (fsnotify_inode_watches_children(parent->d_inode))
+		dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
+	else
+		dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+}
+
+/*
+ * fsnotify_d_instantiate - instantiate a dentry for inode
+ * Called with dcache_lock held.
+ */
+static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode)
+{
+	if (!inode)
+		return;
+
+	assert_spin_locked(&dcache_lock);
+
+	spin_lock(&dentry->d_lock);
+	__fsnotify_update_dcache_flags(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+/* called from fsnotify listeners, such as fanotify or dnotify */
+
+/* must call when a group changes its ->mask */
+extern void fsnotify_recalc_global_mask(void);
+/* get a reference to an existing or create a new group */
+extern struct fsnotify_group *fsnotify_obtain_group(unsigned int group_num,
+						    __u32 mask,
+						    const struct fsnotify_ops *ops);
+/* run all marks associated with this group and update group->mask */
+extern void fsnotify_recalc_group_mask(struct fsnotify_group *group);
+/* drop reference on a group from fsnotify_obtain_group */
+extern void fsnotify_put_group(struct fsnotify_group *group);
+
+/* take a reference to an event */
+extern void fsnotify_get_event(struct fsnotify_event *event);
+extern void fsnotify_put_event(struct fsnotify_event *event);
+/* find private data previously attached to an event and unlink it */
+extern struct fsnotify_event_private_data *fsnotify_remove_priv_from_event(struct fsnotify_group *group,
+									   struct fsnotify_event *event);
+
+/* attach the event to the group notification queue */
+extern int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_event *event,
+				     struct fsnotify_event_private_data *priv);
+/* true if the group notification queue is empty */
+extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
+/* return, but do not dequeue the first event on the notification queue */
+extern struct fsnotify_event *fsnotify_peek_notify_event(struct fsnotify_group *group);
+/* return AND dequeue the first event on the notification queue */
+extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group);
+
+/* functions used to manipulate the marks attached to inodes */
+
+/* run all marks associated with an inode and update inode->i_fsnotify_mask */
+extern void fsnotify_recalc_inode_mask(struct inode *inode);
+extern void fsnotify_init_mark(struct fsnotify_mark_entry *entry, void (*free_mark)(struct fsnotify_mark_entry *entry));
+/* find (and take a reference) to a mark associated with group and inode */
+extern struct fsnotify_mark_entry *fsnotify_find_mark_entry(struct fsnotify_group *group, struct inode *inode);
+/* attach the mark to both the group and the inode */
+extern int fsnotify_add_mark(struct fsnotify_mark_entry *entry, struct fsnotify_group *group, struct inode *inode);
+/* given a mark, flag it to be freed when all references are dropped */
+extern void fsnotify_destroy_mark_by_entry(struct fsnotify_mark_entry *entry);
+/* run all the marks in a group, and flag them to be freed */
+extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group);
+extern void fsnotify_get_mark(struct fsnotify_mark_entry *entry);
+extern void fsnotify_put_mark(struct fsnotify_mark_entry *entry);
+extern void fsnotify_unmount_inodes(struct list_head *list);
+
+/* put here because inotify does some weird stuff when destroying watches */
+extern struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 mask,
+						    void *data, int data_is, const char *name,
+						    u32 cookie);
+
+#else
+
+static inline void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
+			    const char *name, u32 cookie)
+{}
+
+static inline void __fsnotify_parent(struct dentry *dentry, __u32 mask)
+{}
+
+static inline void __fsnotify_inode_delete(struct inode *inode)
+{}
+
+static inline void __fsnotify_update_dcache_flags(struct dentry *dentry)
+{}
+
+static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode)
+{}
+
+static inline u32 fsnotify_get_cookie(void)
+{
+	return 0;
+}
+
+static inline void fsnotify_unmount_inodes(struct list_head *list)
+{}
+
+#endif	/* CONFIG_FSNOTIFY */
+
+#endif	/* __KERNEL __ */
+
+#endif	/* __LINUX_FSNOTIFY_BACKEND_H */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8a0c2f221e6b..39b95c56587e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -233,8 +233,6 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
 
-extern void ftrace_release(void *start, unsigned long size);
-
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
 #else
@@ -325,13 +323,8 @@ static inline void __ftrace_enabled_restore(int enabled)
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
-extern void ftrace_init_module(struct module *mod,
-			       unsigned long *start, unsigned long *end);
 #else
 static inline void ftrace_init(void) { }
-static inline void
-ftrace_init_module(struct module *mod,
-		   unsigned long *start, unsigned long *end) { }
 #endif
 
 /*
@@ -368,6 +361,7 @@ struct ftrace_ret_stack {
 	unsigned long ret;
 	unsigned long func;
 	unsigned long long calltime;
+	unsigned long long subtime;
 };
 
 /*
@@ -379,8 +373,6 @@ extern void return_to_handler(void);
 
 extern int
 ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth);
-extern void
-ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret);
 
 /*
  * Sometimes we don't want to trace a function with the function
@@ -496,8 +488,15 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 
 extern int ftrace_dump_on_oops;
 
+#ifdef CONFIG_PREEMPT
+#define INIT_TRACE_RECURSION		.trace_recursion = 0,
+#endif
+
 #endif /* CONFIG_TRACING */
 
+#ifndef INIT_TRACE_RECURSION
+#define INIT_TRACE_RECURSION
+#endif
 
 #ifdef CONFIG_HW_BRANCH_TRACER
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
new file mode 100644
index 000000000000..5c093ffc655b
--- /dev/null
+++ b/include/linux/ftrace_event.h
@@ -0,0 +1,172 @@
+#ifndef _LINUX_FTRACE_EVENT_H
+#define _LINUX_FTRACE_EVENT_H
+
+#include <linux/trace_seq.h>
+#include <linux/ring_buffer.h>
+#include <linux/percpu.h>
+
+struct trace_array;
+struct tracer;
+struct dentry;
+
+DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq);
+
+struct trace_print_flags {
+	unsigned long		mask;
+	const char		*name;
+};
+
+const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
+				   unsigned long flags,
+				   const struct trace_print_flags *flag_array);
+
+const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
+				     const struct trace_print_flags *symbol_array);
+
+/*
+ * The trace entry - the most basic unit of tracing. This is what
+ * is printed in the end as a single line in the trace output, such as:
+ *
+ *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
+ */
+struct trace_entry {
+	unsigned short		type;
+	unsigned char		flags;
+	unsigned char		preempt_count;
+	int			pid;
+	int			tgid;
+};
+
+#define FTRACE_MAX_EVENT						\
+	((1 << (sizeof(((struct trace_entry *)0)->type) * 8)) - 1)
+
+/*
+ * Trace iterator - used by printout routines who present trace
+ * results to users and which routines might sleep, etc:
+ */
+struct trace_iterator {
+	struct trace_array	*tr;
+	struct tracer		*trace;
+	void			*private;
+	int			cpu_file;
+	struct mutex		mutex;
+	struct ring_buffer_iter	*buffer_iter[NR_CPUS];
+	unsigned long		iter_flags;
+
+	/* The below is zeroed out in pipe_read */
+	struct trace_seq	seq;
+	struct trace_entry	*ent;
+	int			cpu;
+	u64			ts;
+
+	loff_t			pos;
+	long			idx;
+
+	cpumask_var_t		started;
+};
+
+
+typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
+					      int flags);
+struct trace_event {
+	struct hlist_node	node;
+	struct list_head	list;
+	int			type;
+	trace_print_func	trace;
+	trace_print_func	raw;
+	trace_print_func	hex;
+	trace_print_func	binary;
+};
+
+extern int register_ftrace_event(struct trace_event *event);
+extern int unregister_ftrace_event(struct trace_event *event);
+
+/* Return values for print_line callback */
+enum print_line_t {
+	TRACE_TYPE_PARTIAL_LINE	= 0,	/* Retry after flushing the seq */
+	TRACE_TYPE_HANDLED	= 1,
+	TRACE_TYPE_UNHANDLED	= 2,	/* Relay to other output functions */
+	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
+};
+
+
+struct ring_buffer_event *
+trace_current_buffer_lock_reserve(int type, unsigned long len,
+				  unsigned long flags, int pc);
+void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
+void trace_current_buffer_discard_commit(struct ring_buffer_event *event);
+
+void tracing_record_cmdline(struct task_struct *tsk);
+
+struct ftrace_event_call {
+	struct list_head	list;
+	char			*name;
+	char			*system;
+	struct dentry		*dir;
+	struct trace_event	*event;
+	int			enabled;
+	int			(*regfunc)(void);
+	void			(*unregfunc)(void);
+	int			id;
+	int			(*raw_init)(void);
+	int			(*show_format)(struct trace_seq *s);
+	int			(*define_fields)(void);
+	struct list_head	fields;
+	int			filter_active;
+	void			*filter;
+	void			*mod;
+
+#ifdef CONFIG_EVENT_PROFILE
+	atomic_t	profile_count;
+	int		(*profile_enable)(struct ftrace_event_call *);
+	void		(*profile_disable)(struct ftrace_event_call *);
+#endif
+};
+
+#define MAX_FILTER_PRED		32
+#define MAX_FILTER_STR_VAL	128
+
+extern int init_preds(struct ftrace_event_call *call);
+extern void destroy_preds(struct ftrace_event_call *call);
+extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern int filter_current_check_discard(struct ftrace_event_call *call,
+					void *rec,
+					struct ring_buffer_event *event);
+
+extern int trace_define_field(struct ftrace_event_call *call, char *type,
+			      char *name, int offset, int size, int is_signed);
+
+#define is_signed_type(type)	(((type)(-1)) < 0)
+
+int trace_set_clr_event(const char *system, const char *event, int set);
+
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement optimizing out.
+ */
+#define event_trace_printk(ip, fmt, args...)				\
+do {									\
+	__trace_printk_check_format(fmt, ##args);			\
+	tracing_record_cmdline(current);				\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
+	} else								\
+		__trace_printk(ip, fmt, ##args);			\
+} while (0)
+
+#define __common_field(type, item, is_signed)				\
+	ret = trace_define_field(event_call, #type, "common_" #item,	\
+				 offsetof(typeof(field.ent), item),	\
+				 sizeof(field.ent.item), is_signed);	\
+	if (ret)							\
+		return ret;
+
+#endif /* _LINUX_FTRACE_EVENT_H */
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 3bf5bb5a34f9..34956c8fdebf 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -23,6 +23,8 @@ union ktime;
 #define FUTEX_TRYLOCK_PI	8
 #define FUTEX_WAIT_BITSET	9
 #define FUTEX_WAKE_BITSET	10
+#define FUTEX_WAIT_REQUEUE_PI	11
+#define FUTEX_CMP_REQUEUE_PI	12
 
 #define FUTEX_PRIVATE_FLAG	128
 #define FUTEX_CLOCK_REALTIME	256
@@ -38,6 +40,10 @@ union ktime;
 #define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAIT_BITSET_PRIVATE	(FUTEX_WAIT_BITS | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAKE_BITSET_PRIVATE	(FUTEX_WAKE_BITS | FUTEX_PRIVATE_FLAG)
+#define FUTEX_WAIT_REQUEUE_PI_PRIVATE	(FUTEX_WAIT_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
+#define FUTEX_CMP_REQUEUE_PI_PRIVATE	(FUTEX_CMP_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
 
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index a1a28caed23d..149fda264c86 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -90,6 +90,7 @@ struct disk_stats {
 struct hd_struct {
 	sector_t start_sect;
 	sector_t nr_sects;
+	sector_t alignment_offset;
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 9fed365a598b..867cb68d8461 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -26,6 +26,9 @@
 #include <asm/io.h>
 #include <asm/mutex.h>
 
+/* for request_sense */
+#include <linux/cdrom.h>
+
 #if defined(CONFIG_CRIS) || defined(CONFIG_FRV) || defined(CONFIG_MN10300)
 # define SUPPORT_VLB_SYNC 0
 #else
@@ -324,7 +327,6 @@ struct ide_cmd {
 	unsigned int		cursg_ofs;
 
 	struct request		*rq;		/* copy of request */
-	void			*special;	/* valid_t generally */
 };
 
 /* ATAPI packet command flags */
@@ -360,11 +362,7 @@ struct ide_atapi_pc {
 
 	/* data buffer */
 	u8 *buf;
-	/* current buffer position */
-	u8 *cur_pos;
 	int buf_size;
-	/* missing/available data on the current buffer */
-	int b_count;
 
 	/* the corresponding request */
 	struct request *rq;
@@ -377,10 +375,6 @@ struct ide_atapi_pc {
 	 */
 	u8 pc_buf[IDE_PC_BUFFER_SIZE];
 
-	/* idetape only */
-	struct idetape_bh *bh;
-	char *b_data;
-
 	unsigned long timeout;
 };
 
@@ -593,16 +587,16 @@ struct ide_drive_s {
 	/* callback for packet commands */
 	int  (*pc_callback)(struct ide_drive_s *, int);
 
-	void (*pc_update_buffers)(struct ide_drive_s *, struct ide_atapi_pc *);
-	int  (*pc_io_buffers)(struct ide_drive_s *, struct ide_atapi_pc *,
-			      unsigned int, int);
-
 	ide_startstop_t (*irq_handler)(struct ide_drive_s *);
 
 	unsigned long atapi_flags;
 
 	struct ide_atapi_pc request_sense_pc;
-	struct request request_sense_rq;
+
+	/* current sense rq and buffer */
+	bool sense_rq_armed;
+	struct request sense_rq;
+	struct request_sense sense_data;
 };
 
 typedef struct ide_drive_s ide_drive_t;
@@ -1174,7 +1168,10 @@ int ide_do_test_unit_ready(ide_drive_t *, struct gendisk *);
 int ide_do_start_stop(ide_drive_t *, struct gendisk *, int);
 int ide_set_media_lock(ide_drive_t *, struct gendisk *, int);
 void ide_create_request_sense_cmd(ide_drive_t *, struct ide_atapi_pc *);
-void ide_retry_pc(ide_drive_t *, struct gendisk *);
+void ide_retry_pc(ide_drive_t *drive);
+
+void ide_prep_sense(ide_drive_t *drive, struct request *rq);
+int ide_queue_sense_rq(ide_drive_t *drive, void *special);
 
 int ide_cd_expiry(ide_drive_t *);
 
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 0e2aa45cb0ce..b1b827d091a9 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -13,14 +13,17 @@
 #include <linux/fs.h>
 struct linux_binprm;
 
+#define IMA_COUNT_UPDATE 1
+#define IMA_COUNT_LEAVE 0
+
 #ifdef CONFIG_IMA
 extern int ima_bprm_check(struct linux_binprm *bprm);
 extern int ima_inode_alloc(struct inode *inode);
 extern void ima_inode_free(struct inode *inode);
-extern int ima_path_check(struct path *path, int mask);
+extern int ima_path_check(struct path *path, int mask, int update_counts);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
-extern void ima_shm_check(struct file *file);
+extern void ima_counts_get(struct file *file);
 
 #else
 static inline int ima_bprm_check(struct linux_binprm *bprm)
@@ -38,7 +41,7 @@ static inline void ima_inode_free(struct inode *inode)
 	return;
 }
 
-static inline int ima_path_check(struct path *path, int mask)
+static inline int ima_path_check(struct path *path, int mask, int update_counts)
 {
 	return 0;
 }
@@ -53,7 +56,7 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot)
 	return 0;
 }
 
-static inline void ima_shm_check(struct file *file)
+static inline void ima_counts_get(struct file *file)
 {
 	return;
 }
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index d87247d2641f..28b1f30601b5 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -108,6 +108,15 @@ extern struct group_info init_groups;
 
 extern struct cred init_cred;
 
+#ifdef CONFIG_PERF_COUNTERS
+# define INIT_PERF_COUNTERS(tsk)					\
+	.perf_counter_mutex = 						\
+		 __MUTEX_INITIALIZER(tsk.perf_counter_mutex),		\
+	.perf_counter_list = LIST_HEAD_INIT(tsk.perf_counter_list),
+#else
+# define INIT_PERF_COUNTERS(tsk)
+#endif
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -145,8 +154,8 @@ extern struct cred init_cred;
 	.group_leader	= &tsk,						\
 	.real_cred	= &init_cred,					\
 	.cred		= &init_cred,					\
-	.cred_exec_mutex =						\
-		 __MUTEX_INITIALIZER(tsk.cred_exec_mutex),		\
+	.cred_guard_mutex =						\
+		 __MUTEX_INITIALIZER(tsk.cred_guard_mutex),		\
 	.comm		= "swapper",					\
 	.thread		= INIT_THREAD,					\
 	.fs		= &init_fs,					\
@@ -171,9 +180,11 @@ extern struct cred init_cred;
 	},								\
 	.dirties = INIT_PROP_LOCAL_SINGLE(dirties),			\
 	INIT_IDS							\
+	INIT_PERF_COUNTERS(tsk)						\
 	INIT_TRACE_IRQFLAGS						\
 	INIT_LOCKDEP							\
 	INIT_FTRACE_GRAPH						\
+	INIT_TRACE_RECURSION						\
 }
 
 
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 91bb76f44f14..ff374ceface0 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -566,6 +566,6 @@ struct irq_desc;
 extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
-extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
+extern int arch_init_chip_data(struct irq_desc *desc, int node);
 
 #endif
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 08b987bccf89..dd05434fa45f 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -64,7 +64,7 @@ struct cfq_io_context {
  * and kmalloc'ed. These could be shared between processes.
  */
 struct io_context {
-	atomic_t refcount;
+	atomic_long_t refcount;
 	atomic_t nr_tasks;
 
 	/* all the fields below are protected by this lock */
@@ -91,8 +91,8 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc)
 	 * if ref count is zero, don't allow sharing (ioc is going away, it's
 	 * a race).
 	 */
-	if (ioc && atomic_inc_not_zero(&ioc->refcount)) {
-		atomic_inc(&ioc->nr_tasks);
+	if (ioc && atomic_long_inc_not_zero(&ioc->refcount)) {
+		atomic_long_inc(&ioc->refcount);
 		return ioc;
 	}
 
diff --git a/include/linux/irq.h b/include/linux/irq.h
index b7cbeed972e4..1e50c34f0062 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -117,7 +117,7 @@ struct irq_chip {
 	void		(*eoi)(unsigned int irq);
 
 	void		(*end)(unsigned int irq);
-	void		(*set_affinity)(unsigned int irq,
+	int		(*set_affinity)(unsigned int irq,
 					const struct cpumask *dest);
 	int		(*retrigger)(unsigned int irq);
 	int		(*set_type)(unsigned int irq, unsigned int flow_type);
@@ -187,7 +187,7 @@ struct irq_desc {
 	spinlock_t		lock;
 #ifdef CONFIG_SMP
 	cpumask_var_t		affinity;
-	unsigned int		cpu;
+	unsigned int		node;
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_var_t		pending_mask;
 #endif
@@ -201,26 +201,23 @@ struct irq_desc {
 } ____cacheline_internodealigned_in_smp;
 
 extern void arch_init_copy_chip_data(struct irq_desc *old_desc,
-					struct irq_desc *desc, int cpu);
+					struct irq_desc *desc, int node);
 extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc);
 
 #ifndef CONFIG_SPARSE_IRQ
 extern struct irq_desc irq_desc[NR_IRQS];
-#else /* CONFIG_SPARSE_IRQ */
-extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int cpu);
-#endif /* CONFIG_SPARSE_IRQ */
-
-extern struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu);
-
-static inline struct irq_desc *
-irq_remap_to_desc(unsigned int irq, struct irq_desc *desc)
-{
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-	return irq_to_desc(irq);
-#else
-	return desc;
 #endif
+
+#ifdef CONFIG_NUMA_IRQ_DESC
+extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int node);
+#else
+static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
+{
+	return desc;
 }
+#endif
+
+extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
 
 /*
  * Migration helpers for obsolete names, they will go away:
@@ -386,7 +383,7 @@ extern void set_irq_noprobe(unsigned int irq);
 extern void set_irq_probe(unsigned int irq);
 
 /* Handle dynamic irq creation and destruction */
-extern unsigned int create_irq_nr(unsigned int irq_want);
+extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
 extern void destroy_irq(unsigned int irq);
 
@@ -424,47 +421,44 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
 #ifdef CONFIG_SMP
 /**
- * init_alloc_desc_masks - allocate cpumasks for irq_desc
+ * alloc_desc_masks - allocate cpumasks for irq_desc
  * @desc:	pointer to irq_desc struct
  * @cpu:	cpu which will be handling the cpumasks
  * @boot:	true if need bootmem
  *
  * Allocates affinity and pending_mask cpumask if required.
  * Returns true if successful (or not required).
- * Side effect: affinity has all bits set, pending_mask has all bits clear.
  */
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
-								bool boot)
+static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
+							bool boot)
 {
-	int node;
+	gfp_t gfp = GFP_ATOMIC;
 
-	if (boot) {
-		alloc_bootmem_cpumask_var(&desc->affinity);
-		cpumask_setall(desc->affinity);
+	if (boot)
+		gfp = GFP_NOWAIT;
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-		alloc_bootmem_cpumask_var(&desc->pending_mask);
-		cpumask_clear(desc->pending_mask);
-#endif
-		return true;
-	}
-
-	node = cpu_to_node(cpu);
-
-	if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	if (!alloc_cpumask_var_node(&desc->affinity, gfp, node))
 		return false;
-	cpumask_setall(desc->affinity);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
+	if (!alloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
 		free_cpumask_var(desc->affinity);
 		return false;
 	}
-	cpumask_clear(desc->pending_mask);
+#endif
 #endif
 	return true;
 }
 
+static inline void init_desc_masks(struct irq_desc *desc)
+{
+	cpumask_setall(desc->affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_clear(desc->pending_mask);
+#endif
+}
+
 /**
  * init_copy_desc_masks - copy cpumasks for irq_desc
  * @old_desc:	pointer to old irq_desc struct
@@ -478,7 +472,7 @@ static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
 static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 					struct irq_desc *new_desc)
 {
-#ifdef CONFIG_CPUMASKS_OFFSTACK
+#ifdef CONFIG_CPUMASK_OFFSTACK
 	cpumask_copy(new_desc->affinity, old_desc->affinity);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -499,12 +493,16 @@ static inline void free_desc_masks(struct irq_desc *old_desc,
 
 #else /* !CONFIG_SMP */
 
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
 								bool boot)
 {
 	return true;
 }
 
+static inline void init_desc_masks(struct irq_desc *desc)
+{
+}
+
 static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 					struct irq_desc *new_desc)
 {
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 0c8b89f28a95..a77c6007dc99 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -81,7 +81,12 @@ static inline unsigned int kstat_irqs(unsigned int irq)
 	return sum;
 }
 
+
+/*
+ * Lock/unlock the current runqueue - to extract task statistics:
+ */
 extern unsigned long long task_delta_exec(struct task_struct *);
+
 extern void account_user_time(struct task_struct *, cputime_t, cputime_t);
 extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t);
 extern void account_steal_time(cputime_t);
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
new file mode 100644
index 000000000000..7796aed6cdd5
--- /dev/null
+++ b/include/linux/kmemleak.h
@@ -0,0 +1,96 @@
+/*
+ * include/linux/kmemleak.h
+ *
+ * Copyright (C) 2008 ARM Limited
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __KMEMLEAK_H
+#define __KMEMLEAK_H
+
+#ifdef CONFIG_DEBUG_KMEMLEAK
+
+extern void kmemleak_init(void);
+extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
+			   gfp_t gfp);
+extern void kmemleak_free(const void *ptr);
+extern void kmemleak_padding(const void *ptr, unsigned long offset,
+			     size_t size);
+extern void kmemleak_not_leak(const void *ptr);
+extern void kmemleak_ignore(const void *ptr);
+extern void kmemleak_scan_area(const void *ptr, unsigned long offset,
+			       size_t length, gfp_t gfp);
+extern void kmemleak_no_scan(const void *ptr);
+
+static inline void kmemleak_alloc_recursive(const void *ptr, size_t size,
+					    int min_count, unsigned long flags,
+					    gfp_t gfp)
+{
+	if (!(flags & SLAB_NOLEAKTRACE))
+		kmemleak_alloc(ptr, size, min_count, gfp);
+}
+
+static inline void kmemleak_free_recursive(const void *ptr, unsigned long flags)
+{
+	if (!(flags & SLAB_NOLEAKTRACE))
+		kmemleak_free(ptr);
+}
+
+static inline void kmemleak_erase(void **ptr)
+{
+	*ptr = NULL;
+}
+
+#else
+
+static inline void kmemleak_init(void)
+{
+}
+static inline void kmemleak_alloc(const void *ptr, size_t size, int min_count,
+				  gfp_t gfp)
+{
+}
+static inline void kmemleak_alloc_recursive(const void *ptr, size_t size,
+					    int min_count, unsigned long flags,
+					    gfp_t gfp)
+{
+}
+static inline void kmemleak_free(const void *ptr)
+{
+}
+static inline void kmemleak_free_recursive(const void *ptr, unsigned long flags)
+{
+}
+static inline void kmemleak_not_leak(const void *ptr)
+{
+}
+static inline void kmemleak_ignore(const void *ptr)
+{
+}
+static inline void kmemleak_scan_area(const void *ptr, unsigned long offset,
+				      size_t length, gfp_t gfp)
+{
+}
+static inline void kmemleak_erase(void **ptr)
+{
+}
+static inline void kmemleak_no_scan(const void *ptr)
+{
+}
+
+#endif	/* CONFIG_DEBUG_KMEMLEAK */
+
+#endif	/* __KMEMLEAK_H */
diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h
new file mode 100644
index 000000000000..b616d3930c3b
--- /dev/null
+++ b/include/linux/kmemtrace.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2008 Eduard - Gabriel Munteanu
+ *
+ * This file is released under GPL version 2.
+ */
+
+#ifndef _LINUX_KMEMTRACE_H
+#define _LINUX_KMEMTRACE_H
+
+#ifdef __KERNEL__
+
+#include <trace/events/kmem.h>
+
+#ifdef CONFIG_KMEMTRACE
+extern void kmemtrace_init(void);
+#else
+static inline void kmemtrace_init(void)
+{
+}
+#endif
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_KMEMTRACE_H */
+
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 8cc137911b34..3db5d8d37485 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -119,7 +119,7 @@ struct kvm_run {
 			__u32 error_code;
 		} ex;
 		/* KVM_EXIT_IO */
-		struct kvm_io {
+		struct {
 #define KVM_EXIT_IO_IN  0
 #define KVM_EXIT_IO_OUT 1
 			__u8 direction;
@@ -224,10 +224,10 @@ struct kvm_interrupt {
 /* for KVM_GET_DIRTY_LOG */
 struct kvm_dirty_log {
 	__u32 slot;
-	__u32 padding;
+	__u32 padding1;
 	union {
 		void __user *dirty_bitmap; /* one bit per page */
-		__u64 padding;
+		__u64 padding2;
 	};
 };
 
@@ -409,6 +409,10 @@ struct kvm_trace_rec {
 #ifdef __KVM_HAVE_DEVICE_ASSIGNMENT
 #define KVM_CAP_DEVICE_DEASSIGNMENT 27
 #endif
+#ifdef __KVM_HAVE_MSIX
+#define KVM_CAP_DEVICE_MSIX 28
+#endif
+#define KVM_CAP_ASSIGN_DEV_IRQ 29
 /* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30
 
@@ -482,11 +486,18 @@ struct kvm_irq_routing {
 #define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \
 				   struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO, 0x6a, struct kvm_irq_routing)
+/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
 #define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \
 			    struct kvm_assigned_irq)
+#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO, 0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO, 0x71)
 #define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \
 				     struct kvm_assigned_pci_dev)
+#define KVM_ASSIGN_SET_MSIX_NR \
+			_IOW(KVMIO, 0x73, struct kvm_assigned_msix_nr)
+#define KVM_ASSIGN_SET_MSIX_ENTRY \
+			_IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry)
+#define KVM_DEASSIGN_DEV_IRQ       _IOW(KVMIO, 0x75, struct kvm_assigned_irq)
 
 /*
  * ioctls for vcpu fds
@@ -577,6 +588,8 @@ struct kvm_debug_guest {
 #define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
 #define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
 
+#define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
+
 struct kvm_assigned_pci_dev {
 	__u32 assigned_dev_id;
 	__u32 busnr;
@@ -587,6 +600,17 @@ struct kvm_assigned_pci_dev {
 	};
 };
 
+#define KVM_DEV_IRQ_HOST_INTX    (1 << 0)
+#define KVM_DEV_IRQ_HOST_MSI     (1 << 1)
+#define KVM_DEV_IRQ_HOST_MSIX    (1 << 2)
+
+#define KVM_DEV_IRQ_GUEST_INTX   (1 << 8)
+#define KVM_DEV_IRQ_GUEST_MSI    (1 << 9)
+#define KVM_DEV_IRQ_GUEST_MSIX   (1 << 10)
+
+#define KVM_DEV_IRQ_HOST_MASK	 0x00ff
+#define KVM_DEV_IRQ_GUEST_MASK   0xff00
+
 struct kvm_assigned_irq {
 	__u32 assigned_dev_id;
 	__u32 host_irq;
@@ -602,9 +626,19 @@ struct kvm_assigned_irq {
 	};
 };
 
-#define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 
-#define KVM_DEV_IRQ_ASSIGN_MSI_ACTION	KVM_DEV_IRQ_ASSIGN_ENABLE_MSI
-#define KVM_DEV_IRQ_ASSIGN_ENABLE_MSI	(1 << 0)
+struct kvm_assigned_msix_nr {
+	__u32 assigned_dev_id;
+	__u16 entry_nr;
+	__u16 padding;
+};
+
+#define KVM_MAX_MSIX_PER_DEV		512
+struct kvm_assigned_msix_entry {
+	__u32 assigned_dev_id;
+	__u32 gsi;
+	__u16 entry; /* The index of entry in the MSI-X table */
+	__u16 padding[3];
+};
 
 #endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 894a56e365e8..aacc5449f586 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -38,6 +38,7 @@
 #define KVM_REQ_UNHALT             6
 #define KVM_REQ_MMU_SYNC           7
 #define KVM_REQ_KVMCLOCK_UPDATE    8
+#define KVM_REQ_KICK               9
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID	0
 
@@ -72,7 +73,6 @@ struct kvm_vcpu {
 	struct mutex mutex;
 	int   cpu;
 	struct kvm_run *run;
-	int guest_mode;
 	unsigned long requests;
 	unsigned long guest_debug;
 	int fpu_active;
@@ -298,6 +298,7 @@ int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 
 void kvm_free_physmem(struct kvm *kvm);
 
@@ -319,6 +320,13 @@ struct kvm_irq_ack_notifier {
 	void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
 };
 
+#define KVM_ASSIGNED_MSIX_PENDING		0x1
+struct kvm_guest_msix_entry {
+	u32 vector;
+	u16 entry;
+	u16 flags;
+};
+
 struct kvm_assigned_dev_kernel {
 	struct kvm_irq_ack_notifier ack_notifier;
 	struct work_struct interrupt_work;
@@ -326,18 +334,18 @@ struct kvm_assigned_dev_kernel {
 	int assigned_dev_id;
 	int host_busnr;
 	int host_devfn;
+	unsigned int entries_nr;
 	int host_irq;
 	bool host_irq_disabled;
+	struct msix_entry *host_msix_entries;
 	int guest_irq;
-#define KVM_ASSIGNED_DEV_GUEST_INTX	(1 << 0)
-#define KVM_ASSIGNED_DEV_GUEST_MSI	(1 << 1)
-#define KVM_ASSIGNED_DEV_HOST_INTX	(1 << 8)
-#define KVM_ASSIGNED_DEV_HOST_MSI	(1 << 9)
+	struct kvm_guest_msix_entry *guest_msix_entries;
 	unsigned long irq_requested_type;
 	int irq_source_id;
 	int flags;
 	struct pci_dev *dev;
 	struct kvm *kvm;
+	spinlock_t assigned_dev_lock;
 };
 
 struct kvm_irq_mask_notifier {
@@ -360,6 +368,9 @@ void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian);
 int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 
+/* For vcpu->arch.iommu_flags */
+#define KVM_IOMMU_CACHE_COHERENCY	0x1
+
 #ifdef CONFIG_IOMMU_API
 int kvm_iommu_map_pages(struct kvm *kvm, gfn_t base_gfn,
 			unsigned long npages);
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 2b8318c83e53..fb46efbeabec 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -40,4 +40,31 @@ typedef unsigned long  hfn_t;
 
 typedef hfn_t pfn_t;
 
+union kvm_ioapic_redirect_entry {
+	u64 bits;
+	struct {
+		u8 vector;
+		u8 delivery_mode:3;
+		u8 dest_mode:1;
+		u8 delivery_status:1;
+		u8 polarity:1;
+		u8 remote_irr:1;
+		u8 trig_mode:1;
+		u8 mask:1;
+		u8 reserve:7;
+		u8 reserved[4];
+		u8 dest_id;
+	} fields;
+};
+
+struct kvm_lapic_irq {
+	u32 vector;
+	u32 delivery_mode;
+	u32 dest_mode;
+	u32 level;
+	u32 trig_mode;
+	u32 shorthand;
+	u32 dest_id;
+};
+
 #endif /* __KVM_TYPES_H__ */
diff --git a/include/linux/loop.h b/include/linux/loop.h
index 40725447f5e0..66c194e2d9b9 100644
--- a/include/linux/loop.h
+++ b/include/linux/loop.h
@@ -56,8 +56,7 @@ struct loop_device {
 	gfp_t		old_gfp_mask;
 
 	spinlock_t		lo_lock;
-	struct bio 		*lo_bio;
-	struct bio		*lo_biotail;
+	struct bio_list		lo_bio_list;
 	int			lo_state;
 	struct mutex		lo_ctl_mutex;
 	struct task_struct	*lo_thread;
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
new file mode 100644
index 000000000000..e461b2c3d711
--- /dev/null
+++ b/include/linux/lsm_audit.h
@@ -0,0 +1,111 @@
+/*
+ * Common LSM logging functions
+ * Heavily borrowed from selinux/avc.h
+ *
+ * Author : Etienne BASSET  <etienne.basset@ensta.org>
+ *
+ * All credits to : Stephen Smalley, <sds@epoch.ncsc.mil>
+ * All BUGS to : Etienne BASSET  <etienne.basset@ensta.org>
+ */
+#ifndef _LSM_COMMON_LOGGING_
+#define _LSM_COMMON_LOGGING_
+
+#include <linux/stddef.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/kdev_t.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/audit.h>
+#include <linux/in6.h>
+#include <linux/path.h>
+#include <linux/key.h>
+#include <linux/skbuff.h>
+#include <asm/system.h>
+
+
+/* Auxiliary data to use in generating the audit record. */
+struct common_audit_data {
+	char    type;
+#define LSM_AUDIT_DATA_FS      1
+#define LSM_AUDIT_DATA_NET     2
+#define LSM_AUDIT_DATA_CAP     3
+#define LSM_AUDIT_DATA_IPC     4
+#define LSM_AUDIT_DATA_TASK    5
+#define LSM_AUDIT_DATA_KEY     6
+	struct task_struct *tsk;
+	union 	{
+		struct {
+			struct path path;
+			struct inode *inode;
+		} fs;
+		struct {
+			int netif;
+			struct sock *sk;
+			u16 family;
+			__be16 dport;
+			__be16 sport;
+			union {
+				struct {
+					__be32 daddr;
+					__be32 saddr;
+				} v4;
+				struct {
+					struct in6_addr daddr;
+					struct in6_addr saddr;
+				} v6;
+			} fam;
+		} net;
+		int cap;
+		int ipc_id;
+		struct task_struct *tsk;
+#ifdef CONFIG_KEYS
+		struct {
+			key_serial_t key;
+			char *key_desc;
+		} key_struct;
+#endif
+	} u;
+	const char *function;
+	/* this union contains LSM specific data */
+	union {
+		/* SMACK data */
+		struct smack_audit_data {
+			char *subject;
+			char *object;
+			char *request;
+			int result;
+		} smack_audit_data;
+		/* SELinux data */
+		struct {
+			u32 ssid;
+			u32 tsid;
+			u16 tclass;
+			u32 requested;
+			u32 audited;
+			struct av_decision *avd;
+			int result;
+		} selinux_audit_data;
+	} lsm_priv;
+	/* these callback will be implemented by a specific LSM */
+	void (*lsm_pre_audit)(struct audit_buffer *, void *);
+	void (*lsm_post_audit)(struct audit_buffer *, void *);
+};
+
+#define v4info fam.v4
+#define v6info fam.v6
+
+int ipv4_skb_to_auditdata(struct sk_buff *skb,
+		struct common_audit_data *ad, u8 *proto);
+
+int ipv6_skb_to_auditdata(struct sk_buff *skb,
+		struct common_audit_data *ad, u8 *proto);
+
+/* Initialize an LSM audit data structure. */
+#define COMMON_AUDIT_DATA_INIT(_d, _t) \
+	{ memset((_d), 0, sizeof(struct common_audit_data)); \
+	 (_d)->type = LSM_AUDIT_DATA_##_t; (_d)->function = __func__; }
+
+void common_lsm_audit(struct common_audit_data *a);
+
+#endif
diff --git a/include/linux/magic.h b/include/linux/magic.h
index 5b4e28bcb788..1923327b9869 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -6,9 +6,12 @@
 #define AFS_SUPER_MAGIC                0x5346414F
 #define AUTOFS_SUPER_MAGIC	0x0187
 #define CODA_SUPER_MAGIC	0x73757245
+#define CRAMFS_MAGIC		0x28cd3d45	/* some random number */
+#define CRAMFS_MAGIC_WEND	0x453dcd28	/* magic number with the wrong endianess */
 #define DEBUGFS_MAGIC          0x64626720
 #define SYSFS_MAGIC		0x62656572
 #define SECURITYFS_MAGIC	0x73636673
+#define SELINUX_MAGIC		0xf97cff8c
 #define TMPFS_MAGIC		0x01021994
 #define SQUASHFS_MAGIC		0x73717368
 #define EFS_SUPER_MAGIC		0x414A53
diff --git a/include/linux/mg_disk.h b/include/linux/mg_disk.h
deleted file mode 100644
index 1f76b1ebf627..000000000000
--- a/include/linux/mg_disk.h
+++ /dev/null
@@ -1,206 +0,0 @@
-/*
- *  include/linux/mg_disk.c
- *
- *  Support for the mGine m[g]flash IO mode.
- *  Based on legacy hd.c
- *
- * (c) 2008 mGine Co.,LTD
- * (c) 2008 unsik Kim <donari75@gmail.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
-
-#ifndef __MG_DISK_H__
-#define __MG_DISK_H__
-
-#include <linux/blkdev.h>
-#include <linux/ata.h>
-
-/* name for block device */
-#define MG_DISK_NAME "mgd"
-/* name for platform device */
-#define MG_DEV_NAME "mg_disk"
-
-#define MG_DISK_MAJ 0
-#define MG_DISK_MAX_PART 16
-#define MG_SECTOR_SIZE 512
-#define MG_MAX_SECTS 256
-
-/* Register offsets */
-#define MG_BUFF_OFFSET			0x8000
-#define MG_STORAGE_BUFFER_SIZE		0x200
-#define MG_REG_OFFSET			0xC000
-#define MG_REG_FEATURE			(MG_REG_OFFSET + 2)	/* write case */
-#define MG_REG_ERROR			(MG_REG_OFFSET + 2)	/* read case */
-#define MG_REG_SECT_CNT			(MG_REG_OFFSET + 4)
-#define MG_REG_SECT_NUM			(MG_REG_OFFSET + 6)
-#define MG_REG_CYL_LOW			(MG_REG_OFFSET + 8)
-#define MG_REG_CYL_HIGH			(MG_REG_OFFSET + 0xA)
-#define MG_REG_DRV_HEAD			(MG_REG_OFFSET + 0xC)
-#define MG_REG_COMMAND			(MG_REG_OFFSET + 0xE)	/* write case */
-#define MG_REG_STATUS			(MG_REG_OFFSET + 0xE)	/* read  case */
-#define MG_REG_DRV_CTRL			(MG_REG_OFFSET + 0x10)
-#define MG_REG_BURST_CTRL		(MG_REG_OFFSET + 0x12)
-
-/* "Drive Select/Head Register" bit values */
-#define MG_REG_HEAD_MUST_BE_ON		0xA0 /* These 2 bits are always on */
-#define MG_REG_HEAD_DRIVE_MASTER	(0x00 | MG_REG_HEAD_MUST_BE_ON)
-#define MG_REG_HEAD_DRIVE_SLAVE		(0x10 | MG_REG_HEAD_MUST_BE_ON)
-#define MG_REG_HEAD_LBA_MODE		(0x40 | MG_REG_HEAD_MUST_BE_ON)
-
-
-/* "Device Control Register" bit values */
-#define MG_REG_CTRL_INTR_ENABLE			0x0
-#define MG_REG_CTRL_INTR_DISABLE		(0x1<<1)
-#define MG_REG_CTRL_RESET			(0x1<<2)
-#define MG_REG_CTRL_INTR_POLA_ACTIVE_HIGH	0x0
-#define MG_REG_CTRL_INTR_POLA_ACTIVE_LOW	(0x1<<4)
-#define MG_REG_CTRL_DPD_POLA_ACTIVE_LOW		0x0
-#define MG_REG_CTRL_DPD_POLA_ACTIVE_HIGH	(0x1<<5)
-#define MG_REG_CTRL_DPD_DISABLE			0x0
-#define MG_REG_CTRL_DPD_ENABLE			(0x1<<6)
-
-/* Status register bit */
-/* error bit in status register */
-#define MG_REG_STATUS_BIT_ERROR			0x01
-/* corrected error in status register */
-#define MG_REG_STATUS_BIT_CORRECTED_ERROR	0x04
-/* data request bit in status register */
-#define MG_REG_STATUS_BIT_DATA_REQ		0x08
-/* DSC - Drive Seek Complete */
-#define MG_REG_STATUS_BIT_SEEK_DONE		0x10
-/* DWF - Drive Write Fault */
-#define MG_REG_STATUS_BIT_WRITE_FAULT		0x20
-#define MG_REG_STATUS_BIT_READY			0x40
-#define MG_REG_STATUS_BIT_BUSY			0x80
-
-/* handy status */
-#define MG_STAT_READY	(MG_REG_STATUS_BIT_READY | MG_REG_STATUS_BIT_SEEK_DONE)
-#define MG_READY_OK(s)	(((s) & (MG_STAT_READY | \
-				(MG_REG_STATUS_BIT_BUSY | \
-				 MG_REG_STATUS_BIT_WRITE_FAULT | \
-				 MG_REG_STATUS_BIT_ERROR))) == MG_STAT_READY)
-
-/* Error register */
-#define MG_REG_ERR_AMNF		0x01
-#define MG_REG_ERR_ABRT		0x04
-#define MG_REG_ERR_IDNF		0x10
-#define MG_REG_ERR_UNC		0x40
-#define MG_REG_ERR_BBK		0x80
-
-/* error code for others */
-#define MG_ERR_NONE		0
-#define MG_ERR_TIMEOUT		0x100
-#define MG_ERR_INIT_STAT	0x101
-#define MG_ERR_TRANSLATION	0x102
-#define MG_ERR_CTRL_RST		0x103
-#define MG_ERR_INV_STAT		0x104
-#define MG_ERR_RSTOUT		0x105
-
-#define MG_MAX_ERRORS	6	/* Max read/write errors */
-
-/* command */
-#define MG_CMD_RD 0x20
-#define MG_CMD_WR 0x30
-#define MG_CMD_SLEEP 0x99
-#define MG_CMD_WAKEUP 0xC3
-#define MG_CMD_ID 0xEC
-#define MG_CMD_WR_CONF 0x3C
-#define MG_CMD_RD_CONF 0x40
-
-/* operation mode */
-#define MG_OP_CASCADE (1 << 0)
-#define MG_OP_CASCADE_SYNC_RD (1 << 1)
-#define MG_OP_CASCADE_SYNC_WR (1 << 2)
-#define MG_OP_INTERLEAVE (1 << 3)
-
-/* synchronous */
-#define MG_BURST_LAT_4 (3 << 4)
-#define MG_BURST_LAT_5 (4 << 4)
-#define MG_BURST_LAT_6 (5 << 4)
-#define MG_BURST_LAT_7 (6 << 4)
-#define MG_BURST_LAT_8 (7 << 4)
-#define MG_BURST_LEN_4 (1 << 1)
-#define MG_BURST_LEN_8 (2 << 1)
-#define MG_BURST_LEN_16 (3 << 1)
-#define MG_BURST_LEN_32 (4 << 1)
-#define MG_BURST_LEN_CONT (0 << 1)
-
-/* timeout value (unit: ms) */
-#define MG_TMAX_CONF_TO_CMD	1
-#define MG_TMAX_WAIT_RD_DRQ	10
-#define MG_TMAX_WAIT_WR_DRQ	500
-#define MG_TMAX_RST_TO_BUSY	10
-#define MG_TMAX_HDRST_TO_RDY	500
-#define MG_TMAX_SWRST_TO_RDY	500
-#define MG_TMAX_RSTOUT		3000
-
-/* device attribution */
-/* use mflash as boot device */
-#define MG_BOOT_DEV		(1 << 0)
-/* use mflash as storage device */
-#define MG_STORAGE_DEV		(1 << 1)
-/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */
-#define MG_STORAGE_DEV_SKIP_RST	(1 << 2)
-
-#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
-
-/* names of GPIO resource */
-#define MG_RST_PIN	"mg_rst"
-/* except MG_BOOT_DEV, reset-out pin should be assigned */
-#define MG_RSTOUT_PIN	"mg_rstout"
-
-/* private driver data */
-struct mg_drv_data {
-	/* disk resource */
-	u32 use_polling;
-
-	/* device attribution */
-	u32 dev_attr;
-
-	/* internally used */
-	struct mg_host *host;
-};
-
-/* main structure for mflash driver */
-struct mg_host {
-	struct device *dev;
-
-	struct request_queue *breq;
-	spinlock_t lock;
-	struct gendisk *gd;
-
-	struct timer_list timer;
-	void (*mg_do_intr) (struct mg_host *);
-
-	u16 id[ATA_ID_WORDS];
-
-	u16 cyls;
-	u16 heads;
-	u16 sectors;
-	u32 n_sectors;
-	u32 nres_sectors;
-
-	void __iomem *dev_base;
-	unsigned int irq;
-	unsigned int rst;
-	unsigned int rstout;
-
-	u32 major;
-	u32 error;
-};
-
-/*
- * Debugging macro and defines
- */
-#undef DO_MG_DEBUG
-#ifdef DO_MG_DEBUG
-#  define MG_DBG(fmt, args...) \
-	printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
-#else /* CONFIG_MG_DEBUG */
-#  define MG_DBG(fmt, args...) do { } while (0)
-#endif /* CONFIG_MG_DEBUG */
-
-#endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bff1f0d475c7..ad613ed66ab0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -19,6 +19,7 @@ struct anon_vma;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
+struct rlimit;
 
 #ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
@@ -580,12 +581,10 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
  */
 static inline unsigned long round_hint_to_min(unsigned long hint)
 {
-#ifdef CONFIG_SECURITY
 	hint &= PAGE_MASK;
 	if (((void *)hint != NULL) &&
 	    (hint < mmap_min_addr))
 		return PAGE_ALIGN(mmap_min_addr);
-#endif
 	return hint;
 }
 
@@ -1031,8 +1030,6 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn,
 					unsigned long end_pfn);
 extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
 					unsigned long end_pfn);
-extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn,
-					unsigned long end_pfn);
 extern void remove_all_active_ranges(void);
 extern unsigned long absent_pages_in_range(unsigned long start_pfn,
 						unsigned long end_pfn);
@@ -1319,8 +1316,8 @@ int vmemmap_populate_basepages(struct page *start_page,
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
 
-extern void *alloc_locked_buffer(size_t size);
-extern void free_locked_buffer(void *buffer, size_t size);
-extern void release_locked_buffer(void *buffer, size_t size);
+extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+				 size_t size);
+extern void refund_locked_memory(struct mm_struct *mm, size_t size);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index 3d1b7bde1283..97491f78b08c 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -30,6 +30,8 @@ extern unsigned int kmmio_count;
 
 extern int register_kmmio_probe(struct kmmio_probe *p);
 extern void unregister_kmmio_probe(struct kmmio_probe *p);
+extern int kmmio_init(void);
+extern void kmmio_cleanup(void);
 
 #ifdef CONFIG_MMIOTRACE
 /* kmmio is active by some kmmio_probes? */
diff --git a/include/linux/module.h b/include/linux/module.h
index 627ac082e2a6..a8f2c0aa4c32 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -337,6 +337,14 @@ struct module
 	const char **trace_bprintk_fmt_start;
 	unsigned int num_trace_bprintk_fmt;
 #endif
+#ifdef CONFIG_EVENT_TRACING
+	struct ftrace_event_call *trace_events;
+	unsigned int num_trace_events;
+#endif
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+	unsigned long *ftrace_callsites;
+	unsigned int num_ftrace_callsites;
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 51f55f903aff..5d5275364867 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -30,7 +30,7 @@ struct mnt_namespace;
 #define MNT_STRICTATIME 0x80
 
 #define MNT_SHRINKABLE	0x100
-#define MNT_IMBALANCED_WRITE_COUNT	0x200 /* just for debugging */
+#define MNT_WRITE_HOLD	0x200
 
 #define MNT_SHARED	0x1000	/* if the vfsmount is a shared mount */
 #define MNT_UNBINDABLE	0x2000	/* if the vfsmount is a unbindable mount */
@@ -65,13 +65,22 @@ struct vfsmount {
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	int mnt_pinned;
 	int mnt_ghosts;
-	/*
-	 * This value is not stable unless all of the mnt_writers[] spinlocks
-	 * are held, and all mnt_writer[]s on this mount have 0 as their ->count
-	 */
-	atomic_t __mnt_writers;
+#ifdef CONFIG_SMP
+	int *mnt_writers;
+#else
+	int mnt_writers;
+#endif
 };
 
+static inline int *get_mnt_writers_ptr(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+	return mnt->mnt_writers;
+#else
+	return &mnt->mnt_writers;
+#endif
+}
+
 static inline struct vfsmount *mntget(struct vfsmount *mnt)
 {
 	if (mnt)
@@ -79,7 +88,11 @@ static inline struct vfsmount *mntget(struct vfsmount *mnt)
 	return mnt;
 }
 
+struct file; /* forward dec */
+
 extern int mnt_want_write(struct vfsmount *mnt);
+extern int mnt_want_write_file(struct file *file);
+extern int mnt_clone_write(struct vfsmount *mnt);
 extern void mnt_drop_write(struct vfsmount *mnt);
 extern void mntput_no_expire(struct vfsmount *mnt);
 extern void mnt_pin(struct vfsmount *mnt);
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 3069ec7e0ab8..878cab4f5fcc 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -150,5 +150,6 @@ extern int __must_check mutex_lock_killable(struct mutex *lock);
  */
 extern int mutex_trylock(struct mutex *lock);
 extern void mutex_unlock(struct mutex *lock);
+extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
 #endif
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 518098fe63af..d870ae2faedc 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -18,6 +18,7 @@ enum { MAX_NESTED_LINKS = 8 };
 struct nameidata {
 	struct path	path;
 	struct qstr	last;
+	struct path	root;
 	unsigned int	flags;
 	int		last_type;
 	unsigned	depth;
@@ -77,8 +78,8 @@ extern void release_open_intent(struct nameidata *);
 extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
 extern struct dentry *lookup_one_noperm(const char *, struct dentry *);
 
-extern int follow_down(struct vfsmount **, struct dentry **);
-extern int follow_up(struct vfsmount **, struct dentry **);
+extern int follow_down(struct path *);
+extern int follow_up(struct path *);
 
 extern struct dentry *lock_rename(struct dentry *, struct dentry *);
 extern void unlock_rename(struct dentry *, struct dentry *);
diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h
index bcd0201589f8..a6d9ef2bb34a 100644
--- a/include/linux/nfsd/export.h
+++ b/include/linux/nfsd/export.h
@@ -125,11 +125,9 @@ void			nfsd_export_flush(void);
 void			exp_readlock(void);
 void			exp_readunlock(void);
 struct svc_export *	rqst_exp_get_by_name(struct svc_rqst *,
-					     struct vfsmount *,
-					     struct dentry *);
+					     struct path *);
 struct svc_export *	rqst_exp_parent(struct svc_rqst *,
-					struct vfsmount *mnt,
-					struct dentry *dentry);
+					struct path *);
 int			exp_rootfh(struct auth_domain *, 
 					char *path, struct knfsd_fh *, int maxsize);
 __be32			exp_pseudoroot(struct svc_rqst *, struct svc_fh *);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 0f71812d67d3..d7d1c41a0b17 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1996,10 +1996,12 @@
 #define PCI_DEVICE_ID_OXSEMI_PCIe952_1_U	0xC118
 #define PCI_DEVICE_ID_OXSEMI_PCIe952_1_GU	0xC11C
 #define PCI_DEVICE_ID_OXSEMI_16PCI954	0x9501
+#define PCI_DEVICE_ID_OXSEMI_C950	0x950B
 #define PCI_DEVICE_ID_OXSEMI_16PCI95N	0x9511
 #define PCI_DEVICE_ID_OXSEMI_16PCI954PP	0x9513
 #define PCI_DEVICE_ID_OXSEMI_16PCI952	0x9521
 #define PCI_DEVICE_ID_OXSEMI_16PCI952PP	0x9523
+#define PCI_SUBDEVICE_ID_OXSEMI_C950	0x0001
 
 #define PCI_VENDOR_ID_CHELSIO		0x1425
 
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 1581ff235c7e..26fd9d12f050 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -86,7 +86,12 @@ struct percpu_data {
 	void *ptrs[1];
 };
 
+/* pointer disguising messes up the kmemleak objects tracking */
+#ifndef CONFIG_DEBUG_KMEMLEAK
 #define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
+#else
+#define __percpu_disguise(pdata) (struct percpu_data *)(pdata)
+#endif
 
 #define per_cpu_ptr(ptr, cpu)						\
 ({									\
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
new file mode 100644
index 000000000000..6e133954e2e4
--- /dev/null
+++ b/include/linux/perf_counter.h
@@ -0,0 +1,697 @@
+/*
+ *  Performance counters:
+ *
+ *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2009, Red Hat, Inc., Peter Zijlstra
+ *
+ *  Data type definitions, declarations, prototypes.
+ *
+ *    Started by: Thomas Gleixner and Ingo Molnar
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+#ifndef _LINUX_PERF_COUNTER_H
+#define _LINUX_PERF_COUNTER_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+	PERF_TYPE_HARDWARE			= 0,
+	PERF_TYPE_SOFTWARE			= 1,
+	PERF_TYPE_TRACEPOINT			= 2,
+	PERF_TYPE_HW_CACHE			= 3,
+	PERF_TYPE_RAW				= 4,
+
+	PERF_TYPE_MAX,				/* non-ABI */
+};
+
+/*
+ * Generalized performance counter event types, used by the
+ * attr.event_id parameter of the sys_perf_counter_open()
+ * syscall:
+ */
+enum perf_hw_id {
+	/*
+	 * Common hardware events, generalized by the kernel:
+	 */
+	PERF_COUNT_HW_CPU_CYCLES		= 0,
+	PERF_COUNT_HW_INSTRUCTIONS		= 1,
+	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
+	PERF_COUNT_HW_CACHE_MISSES		= 3,
+	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
+	PERF_COUNT_HW_BRANCH_MISSES		= 5,
+	PERF_COUNT_HW_BUS_CYCLES		= 6,
+
+	PERF_COUNT_HW_MAX,			/* non-ABI */
+};
+
+/*
+ * Generalized hardware cache counters:
+ *
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x
+ *       { read, write, prefetch } x
+ *       { accesses, misses }
+ */
+enum perf_hw_cache_id {
+	PERF_COUNT_HW_CACHE_L1D			= 0,
+	PERF_COUNT_HW_CACHE_L1I			= 1,
+	PERF_COUNT_HW_CACHE_LL			= 2,
+	PERF_COUNT_HW_CACHE_DTLB		= 3,
+	PERF_COUNT_HW_CACHE_ITLB		= 4,
+	PERF_COUNT_HW_CACHE_BPU			= 5,
+
+	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+	PERF_COUNT_HW_CACHE_OP_READ		= 0,
+	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
+	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,
+
+	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
+	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,
+
+	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
+};
+
+/*
+ * Special "software" counters provided by the kernel, even if the hardware
+ * does not support performance counters. These counters measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+	PERF_COUNT_SW_CPU_CLOCK			= 0,
+	PERF_COUNT_SW_TASK_CLOCK		= 1,
+	PERF_COUNT_SW_PAGE_FAULTS		= 2,
+	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
+	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
+	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
+	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+
+	PERF_COUNT_SW_MAX,			/* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_counter_sample_format {
+	PERF_SAMPLE_IP				= 1U << 0,
+	PERF_SAMPLE_TID				= 1U << 1,
+	PERF_SAMPLE_TIME			= 1U << 2,
+	PERF_SAMPLE_ADDR			= 1U << 3,
+	PERF_SAMPLE_GROUP			= 1U << 4,
+	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
+	PERF_SAMPLE_ID				= 1U << 6,
+	PERF_SAMPLE_CPU				= 1U << 7,
+	PERF_SAMPLE_PERIOD			= 1U << 8,
+};
+
+/*
+ * Bits that can be set in attr.read_format to request that
+ * reads on the counter should return the indicated quantities,
+ * in increasing order of bit value, after the counter value.
+ */
+enum perf_counter_read_format {
+	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
+	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
+	PERF_FORMAT_ID				= 1U << 2,
+};
+
+/*
+ * Hardware event to monitor via a performance monitoring counter:
+ */
+struct perf_counter_attr {
+	/*
+	 * Major type: hardware/software/tracepoint/etc.
+	 */
+	__u32			type;
+	__u32			__reserved_1;
+
+	/*
+	 * Type specific configuration information.
+	 */
+	__u64			config;
+
+	union {
+		__u64		sample_period;
+		__u64		sample_freq;
+	};
+
+	__u64			sample_type;
+	__u64			read_format;
+
+	__u64			disabled       :  1, /* off by default        */
+				inherit	       :  1, /* children inherit it   */
+				pinned	       :  1, /* must always be on PMU */
+				exclusive      :  1, /* only group on PMU     */
+				exclude_user   :  1, /* don't count user      */
+				exclude_kernel :  1, /* ditto kernel          */
+				exclude_hv     :  1, /* ditto hypervisor      */
+				exclude_idle   :  1, /* don't count when idle */
+				mmap           :  1, /* include mmap data     */
+				comm	       :  1, /* include comm data     */
+				freq           :  1, /* use freq, not period  */
+
+				__reserved_2   : 53;
+
+	__u32			wakeup_events;	/* wakeup every n events */
+	__u32			__reserved_3;
+
+	__u64			__reserved_4;
+};
+
+/*
+ * Ioctls that can be done on a perf counter fd:
+ */
+#define PERF_COUNTER_IOC_ENABLE		_IO ('$', 0)
+#define PERF_COUNTER_IOC_DISABLE	_IO ('$', 1)
+#define PERF_COUNTER_IOC_REFRESH	_IO ('$', 2)
+#define PERF_COUNTER_IOC_RESET		_IO ('$', 3)
+#define PERF_COUNTER_IOC_PERIOD		_IOW('$', 4, u64)
+
+enum perf_counter_ioc_flags {
+	PERF_IOC_FLAG_GROUP		= 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_counter_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+
+	/*
+	 * Bits needed to read the hw counters in user-space.
+	 *
+	 *   u32 seq;
+	 *   s64 count;
+	 *
+	 *   do {
+	 *     seq = pc->lock;
+	 *
+	 *     barrier()
+	 *     if (pc->index) {
+	 *       count = pmc_read(pc->index - 1);
+	 *       count += pc->offset;
+	 *     } else
+	 *       goto regular_read;
+	 *
+	 *     barrier();
+	 *   } while (pc->lock != seq);
+	 *
+	 * NOTE: for obvious reason this only works on self-monitoring
+	 *       processes.
+	 */
+	__u32	lock;			/* seqlock for synchronization */
+	__u32	index;			/* hardware counter identifier */
+	__s64	offset;			/* add to hardware counter value */
+
+	/*
+	 * Control data for the mmap() data buffer.
+	 *
+	 * User-space reading this value should issue an rmb(), on SMP capable
+	 * platforms, after reading this value -- see perf_counter_wakeup().
+	 */
+	__u64   data_head;		/* head in the data section */
+};
+
+#define PERF_EVENT_MISC_CPUMODE_MASK		(3 << 0)
+#define PERF_EVENT_MISC_CPUMODE_UNKNOWN		(0 << 0)
+#define PERF_EVENT_MISC_KERNEL			(1 << 0)
+#define PERF_EVENT_MISC_USER			(2 << 0)
+#define PERF_EVENT_MISC_HYPERVISOR		(3 << 0)
+#define PERF_EVENT_MISC_OVERFLOW		(1 << 2)
+
+struct perf_event_header {
+	__u32	type;
+	__u16	misc;
+	__u16	size;
+};
+
+enum perf_event_type {
+
+	/*
+	 * The MMAP events record the PROT_EXEC mappings so that we can
+	 * correlate userspace IPs to code. They have the following structure:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	char				filename[];
+	 * };
+	 */
+	PERF_EVENT_MMAP			= 1,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	char				comm[];
+	 * };
+	 */
+	PERF_EVENT_COMM			= 3,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 *	u64				sample_period;
+	 * };
+	 */
+	PERF_EVENT_PERIOD		= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 * };
+	 */
+	PERF_EVENT_THROTTLE		= 5,
+	PERF_EVENT_UNTHROTTLE		= 6,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 * };
+	 */
+	PERF_EVENT_FORK			= 7,
+
+	/*
+	 * When header.misc & PERF_EVENT_MISC_OVERFLOW the event_type field
+	 * will be PERF_RECORD_*
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	{ u64			ip;	  } && PERF_RECORD_IP
+	 *	{ u32			pid, tid; } && PERF_RECORD_TID
+	 *	{ u64			time;     } && PERF_RECORD_TIME
+	 *	{ u64			addr;     } && PERF_RECORD_ADDR
+	 *	{ u64			config;   } && PERF_RECORD_CONFIG
+	 *	{ u32			cpu, res; } && PERF_RECORD_CPU
+	 *
+	 *	{ u64			nr;
+	 *	  { u64 id, val; }	cnt[nr];  } && PERF_RECORD_GROUP
+	 *
+	 *	{ u16			nr,
+	 *				hv,
+	 *				kernel,
+	 *				user;
+	 *	  u64			ips[nr];  } && PERF_RECORD_CALLCHAIN
+	 * };
+	 */
+};
+
+#ifdef __KERNEL__
+/*
+ * Kernel-internal data types and definitions:
+ */
+
+#ifdef CONFIG_PERF_COUNTERS
+# include <asm/perf_counter.h>
+#endif
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/spinlock.h>
+#include <linux/hrtimer.h>
+#include <linux/fs.h>
+#include <linux/pid_namespace.h>
+#include <asm/atomic.h>
+
+struct task_struct;
+
+/**
+ * struct hw_perf_counter - performance counter hardware details:
+ */
+struct hw_perf_counter {
+#ifdef CONFIG_PERF_COUNTERS
+	union {
+		struct { /* hardware */
+			u64		config;
+			unsigned long	config_base;
+			unsigned long	counter_base;
+			int		idx;
+		};
+		union { /* software */
+			atomic64_t	count;
+			struct hrtimer	hrtimer;
+		};
+	};
+	atomic64_t			prev_count;
+	u64				sample_period;
+	u64				last_period;
+	atomic64_t			period_left;
+	u64				interrupts;
+
+	u64				freq_count;
+	u64				freq_interrupts;
+	u64				freq_stamp;
+#endif
+};
+
+struct perf_counter;
+
+/**
+ * struct pmu - generic performance monitoring unit
+ */
+struct pmu {
+	int (*enable)			(struct perf_counter *counter);
+	void (*disable)			(struct perf_counter *counter);
+	void (*read)			(struct perf_counter *counter);
+	void (*unthrottle)		(struct perf_counter *counter);
+};
+
+/**
+ * enum perf_counter_active_state - the states of a counter
+ */
+enum perf_counter_active_state {
+	PERF_COUNTER_STATE_ERROR	= -2,
+	PERF_COUNTER_STATE_OFF		= -1,
+	PERF_COUNTER_STATE_INACTIVE	=  0,
+	PERF_COUNTER_STATE_ACTIVE	=  1,
+};
+
+struct file;
+
+struct perf_mmap_data {
+	struct rcu_head			rcu_head;
+	int				nr_pages;	/* nr of data pages  */
+	int				nr_locked;	/* nr pages mlocked  */
+
+	atomic_t			poll;		/* POLL_ for wakeups */
+	atomic_t			events;		/* event limit       */
+
+	atomic_long_t			head;		/* write position    */
+	atomic_long_t			done_head;	/* completed head    */
+
+	atomic_t			lock;		/* concurrent writes */
+
+	atomic_t			wakeup;		/* needs a wakeup    */
+
+	struct perf_counter_mmap_page   *user_page;
+	void				*data_pages[0];
+};
+
+struct perf_pending_entry {
+	struct perf_pending_entry *next;
+	void (*func)(struct perf_pending_entry *);
+};
+
+/**
+ * struct perf_counter - performance counter kernel representation:
+ */
+struct perf_counter {
+#ifdef CONFIG_PERF_COUNTERS
+	struct list_head		list_entry;
+	struct list_head		event_entry;
+	struct list_head		sibling_list;
+	int				nr_siblings;
+	struct perf_counter		*group_leader;
+	const struct pmu		*pmu;
+
+	enum perf_counter_active_state	state;
+	atomic64_t			count;
+
+	/*
+	 * These are the total time in nanoseconds that the counter
+	 * has been enabled (i.e. eligible to run, and the task has
+	 * been scheduled in, if this is a per-task counter)
+	 * and running (scheduled onto the CPU), respectively.
+	 *
+	 * They are computed from tstamp_enabled, tstamp_running and
+	 * tstamp_stopped when the counter is in INACTIVE or ACTIVE state.
+	 */
+	u64				total_time_enabled;
+	u64				total_time_running;
+
+	/*
+	 * These are timestamps used for computing total_time_enabled
+	 * and total_time_running when the counter is in INACTIVE or
+	 * ACTIVE state, measured in nanoseconds from an arbitrary point
+	 * in time.
+	 * tstamp_enabled: the notional time when the counter was enabled
+	 * tstamp_running: the notional time when the counter was scheduled on
+	 * tstamp_stopped: in INACTIVE state, the notional time when the
+	 *	counter was scheduled off.
+	 */
+	u64				tstamp_enabled;
+	u64				tstamp_running;
+	u64				tstamp_stopped;
+
+	struct perf_counter_attr	attr;
+	struct hw_perf_counter		hw;
+
+	struct perf_counter_context	*ctx;
+	struct file			*filp;
+
+	/*
+	 * These accumulate total time (in nanoseconds) that children
+	 * counters have been enabled and running, respectively.
+	 */
+	atomic64_t			child_total_time_enabled;
+	atomic64_t			child_total_time_running;
+
+	/*
+	 * Protect attach/detach and child_list:
+	 */
+	struct mutex			child_mutex;
+	struct list_head		child_list;
+	struct perf_counter		*parent;
+
+	int				oncpu;
+	int				cpu;
+
+	struct list_head		owner_entry;
+	struct task_struct		*owner;
+
+	/* mmap bits */
+	struct mutex			mmap_mutex;
+	atomic_t			mmap_count;
+	struct perf_mmap_data		*data;
+
+	/* poll related */
+	wait_queue_head_t		waitq;
+	struct fasync_struct		*fasync;
+
+	/* delayed work for NMIs and such */
+	int				pending_wakeup;
+	int				pending_kill;
+	int				pending_disable;
+	struct perf_pending_entry	pending;
+
+	atomic_t			event_limit;
+
+	void (*destroy)(struct perf_counter *);
+	struct rcu_head			rcu_head;
+
+	struct pid_namespace		*ns;
+	u64				id;
+#endif
+};
+
+/**
+ * struct perf_counter_context - counter context structure
+ *
+ * Used as a container for task counters and CPU counters as well:
+ */
+struct perf_counter_context {
+	/*
+	 * Protect the states of the counters in the list,
+	 * nr_active, and the list:
+	 */
+	spinlock_t			lock;
+	/*
+	 * Protect the list of counters.  Locking either mutex or lock
+	 * is sufficient to ensure the list doesn't change; to change
+	 * the list you need to lock both the mutex and the spinlock.
+	 */
+	struct mutex			mutex;
+
+	struct list_head		counter_list;
+	struct list_head		event_list;
+	int				nr_counters;
+	int				nr_active;
+	int				is_active;
+	atomic_t			refcount;
+	struct task_struct		*task;
+
+	/*
+	 * Context clock, runs when context enabled.
+	 */
+	u64				time;
+	u64				timestamp;
+
+	/*
+	 * These fields let us detect when two contexts have both
+	 * been cloned (inherited) from a common ancestor.
+	 */
+	struct perf_counter_context	*parent_ctx;
+	u64				parent_gen;
+	u64				generation;
+	int				pin_count;
+	struct rcu_head			rcu_head;
+};
+
+/**
+ * struct perf_counter_cpu_context - per cpu counter context structure
+ */
+struct perf_cpu_context {
+	struct perf_counter_context	ctx;
+	struct perf_counter_context	*task_ctx;
+	int				active_oncpu;
+	int				max_pertask;
+	int				exclusive;
+
+	/*
+	 * Recursion avoidance:
+	 *
+	 * task, softirq, irq, nmi context
+	 */
+	int				recursion[4];
+};
+
+#ifdef CONFIG_PERF_COUNTERS
+
+/*
+ * Set by architecture code:
+ */
+extern int perf_max_counters;
+
+extern const struct pmu *hw_perf_counter_init(struct perf_counter *counter);
+
+extern void perf_counter_task_sched_in(struct task_struct *task, int cpu);
+extern void perf_counter_task_sched_out(struct task_struct *task,
+					struct task_struct *next, int cpu);
+extern void perf_counter_task_tick(struct task_struct *task, int cpu);
+extern int perf_counter_init_task(struct task_struct *child);
+extern void perf_counter_exit_task(struct task_struct *child);
+extern void perf_counter_free_task(struct task_struct *task);
+extern void perf_counter_do_pending(void);
+extern void perf_counter_print_debug(void);
+extern void __perf_disable(void);
+extern bool __perf_enable(void);
+extern void perf_disable(void);
+extern void perf_enable(void);
+extern int perf_counter_task_disable(void);
+extern int perf_counter_task_enable(void);
+extern int hw_perf_group_sched_in(struct perf_counter *group_leader,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_counter_context *ctx, int cpu);
+extern void perf_counter_update_userpage(struct perf_counter *counter);
+
+struct perf_sample_data {
+	struct pt_regs			*regs;
+	u64				addr;
+	u64				period;
+};
+
+extern int perf_counter_overflow(struct perf_counter *counter, int nmi,
+				 struct perf_sample_data *data);
+
+/*
+ * Return 1 for a software counter, 0 for a hardware counter
+ */
+static inline int is_software_counter(struct perf_counter *counter)
+{
+	return (counter->attr.type != PERF_TYPE_RAW) &&
+		(counter->attr.type != PERF_TYPE_HARDWARE);
+}
+
+extern void perf_swcounter_event(u32, u64, int, struct pt_regs *, u64);
+
+extern void __perf_counter_mmap(struct vm_area_struct *vma);
+
+static inline void perf_counter_mmap(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_EXEC)
+		__perf_counter_mmap(vma);
+}
+
+extern void perf_counter_comm(struct task_struct *tsk);
+extern void perf_counter_fork(struct task_struct *tsk);
+
+extern void perf_counter_task_migration(struct task_struct *task, int cpu);
+
+#define MAX_STACK_DEPTH			255
+
+struct perf_callchain_entry {
+	u16				nr;
+	u16				hv;
+	u16				kernel;
+	u16				user;
+	u64				ip[MAX_STACK_DEPTH];
+};
+
+extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+
+extern int sysctl_perf_counter_paranoid;
+extern int sysctl_perf_counter_mlock;
+extern int sysctl_perf_counter_sample_rate;
+
+extern void perf_counter_init(void);
+
+#ifndef perf_misc_flags
+#define perf_misc_flags(regs)	(user_mode(regs) ? PERF_EVENT_MISC_USER : \
+				 PERF_EVENT_MISC_KERNEL)
+#define perf_instruction_pointer(regs)	instruction_pointer(regs)
+#endif
+
+#else
+static inline void
+perf_counter_task_sched_in(struct task_struct *task, int cpu)		{ }
+static inline void
+perf_counter_task_sched_out(struct task_struct *task,
+			    struct task_struct *next, int cpu)		{ }
+static inline void
+perf_counter_task_tick(struct task_struct *task, int cpu)		{ }
+static inline int perf_counter_init_task(struct task_struct *child)	{ return 0; }
+static inline void perf_counter_exit_task(struct task_struct *child)	{ }
+static inline void perf_counter_free_task(struct task_struct *task)	{ }
+static inline void perf_counter_do_pending(void)			{ }
+static inline void perf_counter_print_debug(void)			{ }
+static inline void perf_disable(void)					{ }
+static inline void perf_enable(void)					{ }
+static inline int perf_counter_task_disable(void)	{ return -EINVAL; }
+static inline int perf_counter_task_enable(void)	{ return -EINVAL; }
+
+static inline void
+perf_swcounter_event(u32 event, u64 nr, int nmi,
+		     struct pt_regs *regs, u64 addr)			{ }
+
+static inline void perf_counter_mmap(struct vm_area_struct *vma)	{ }
+static inline void perf_counter_comm(struct task_struct *tsk)		{ }
+static inline void perf_counter_fork(struct task_struct *tsk)		{ }
+static inline void perf_counter_init(void)				{ }
+static inline void perf_counter_task_migration(struct task_struct *task,
+					       int cpu)			{ }
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* _LINUX_PERF_COUNTER_H */
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index c8f038554e80..b43a9e039059 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -152,5 +152,6 @@ void generic_pipe_buf_unmap(struct pipe_inode_info *, struct pipe_buffer *, void
 void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
+void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 
 #endif
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index 48d887e3c6e7..b00df4c79c63 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -85,4 +85,7 @@
 #define PR_SET_TIMERSLACK 29
 #define PR_GET_TIMERSLACK 30
 
+#define PR_TASK_PERF_COUNTERS_DISABLE		31
+#define PR_TASK_PERF_COUNTERS_ENABLE		32
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index fbfa3d44d33d..e6e77d31c418 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -93,20 +93,9 @@ struct vmcore {
 
 #ifdef CONFIG_PROC_FS
 
-extern spinlock_t proc_subdir_lock;
-
 extern void proc_root_init(void);
 
 void proc_flush_task(struct task_struct *task);
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *);
-int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
-unsigned long task_vsize(struct mm_struct *);
-int task_statm(struct mm_struct *, int *, int *, int *, int *);
-void task_mem(struct seq_file *, struct mm_struct *);
-void clear_refs_smap(struct mm_struct *mm);
-
-struct proc_dir_entry *de_get(struct proc_dir_entry *de);
-void de_put(struct proc_dir_entry *de);
 
 extern struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
 						struct proc_dir_entry *parent);
@@ -116,20 +105,7 @@ struct proc_dir_entry *proc_create_data(const char *name, mode_t mode,
 				void *data);
 extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent);
 
-extern struct vfsmount *proc_mnt;
 struct pid_namespace;
-extern int proc_fill_super(struct super_block *);
-extern struct inode *proc_get_inode(struct super_block *, unsigned int, struct proc_dir_entry *);
-
-/*
- * These are generic /proc routines that use the internal
- * "struct proc_dir_entry" tree to traverse the filesystem.
- *
- * The /proc root directory has extended versions to take care
- * of the /proc/<pid> subdirectories.
- */
-extern int proc_readdir(struct file *, void *, filldir_t);
-extern struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);
 
 extern int pid_ns_prepare_proc(struct pid_namespace *ns);
 extern void pid_ns_release_proc(struct pid_namespace *ns);
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 67c15653fc23..59e133d39d50 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -95,7 +95,6 @@ extern void __ptrace_link(struct task_struct *child,
 			  struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
 extern void exit_ptrace(struct task_struct *tracer);
-extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags);
 #define PTRACE_MODE_READ   1
 #define PTRACE_MODE_ATTACH 2
 /* Returns 0 on success, -errno on denial. */
@@ -327,15 +326,6 @@ static inline void user_enable_block_step(struct task_struct *task)
 #define arch_ptrace_untrace(task)		do { } while (0)
 #endif
 
-#ifndef arch_ptrace_fork
-/*
- * Do machine-specific work to initialize a new task.
- *
- * This is called from copy_process().
- */
-#define arch_ptrace_fork(child, clone_flags)	do { } while (0)
-#endif
-
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
diff --git a/include/linux/qnx4_fs.h b/include/linux/qnx4_fs.h
index 787d19ea9f46..8b9aee1a9ce3 100644
--- a/include/linux/qnx4_fs.h
+++ b/include/linux/qnx4_fs.h
@@ -85,65 +85,4 @@ struct qnx4_super_block {
 	struct qnx4_inode_entry AltBoot;
 };
 
-#ifdef __KERNEL__
-
-#define QNX4_DEBUG 0
-
-#if QNX4_DEBUG
-#define QNX4DEBUG(X) printk X
-#else
-#define QNX4DEBUG(X) (void) 0
-#endif
-
-struct qnx4_sb_info {
-	struct buffer_head	*sb_buf;	/* superblock buffer */
-	struct qnx4_super_block	*sb;		/* our superblock */
-	unsigned int		Version;	/* may be useful */
-	struct qnx4_inode_entry	*BitMap;	/* useful */
-};
-
-struct qnx4_inode_info {
-	struct qnx4_inode_entry raw;
-	loff_t mmu_private;
-	struct inode vfs_inode;
-};
-
-extern struct inode *qnx4_iget(struct super_block *, unsigned long);
-extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd);
-extern unsigned long qnx4_count_free_blocks(struct super_block *sb);
-extern unsigned long qnx4_block_map(struct inode *inode, long iblock);
-
-extern struct buffer_head *qnx4_bread(struct inode *, int, int);
-
-extern const struct inode_operations qnx4_file_inode_operations;
-extern const struct inode_operations qnx4_dir_inode_operations;
-extern const struct file_operations qnx4_file_operations;
-extern const struct file_operations qnx4_dir_operations;
-extern int qnx4_is_free(struct super_block *sb, long block);
-extern int qnx4_set_bitmap(struct super_block *sb, long block, int busy);
-extern int qnx4_create(struct inode *inode, struct dentry *dentry, int mode, struct nameidata *nd);
-extern void qnx4_truncate(struct inode *inode);
-extern void qnx4_free_inode(struct inode *inode);
-extern int qnx4_unlink(struct inode *dir, struct dentry *dentry);
-extern int qnx4_rmdir(struct inode *dir, struct dentry *dentry);
-extern int qnx4_sync_file(struct file *file, struct dentry *dentry, int);
-extern int qnx4_sync_inode(struct inode *inode);
-
-static inline struct qnx4_sb_info *qnx4_sb(struct super_block *sb)
-{
-	return sb->s_fs_info;
-}
-
-static inline struct qnx4_inode_info *qnx4_i(struct inode *inode)
-{
-	return container_of(inode, struct qnx4_inode_info, vfs_inode);
-}
-
-static inline struct qnx4_inode_entry *qnx4_raw_inode(struct inode *inode)
-{
-	return &qnx4_i(inode)->raw;
-}
-
-#endif				/* __KERNEL__ */
-
 #endif
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 36353d95c8db..7bc457593684 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -20,7 +20,12 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb)
 /*
  * declaration of quota_function calls in kernel.
  */
-void sync_dquots(struct super_block *sb, int type);
+void sync_quota_sb(struct super_block *sb, int type);
+static inline void writeout_quota_sb(struct super_block *sb, int type)
+{
+	if (sb->s_qcop->quota_sync)
+		sb->s_qcop->quota_sync(sb, type);
+}
 
 int dquot_initialize(struct inode *inode, int type);
 int dquot_drop(struct inode *inode);
@@ -253,12 +258,7 @@ static inline void vfs_dq_free_inode(struct inode *inode)
 		inode->i_sb->dq_op->free_inode(inode, 1);
 }
 
-/* The following two functions cannot be called inside a transaction */
-static inline void vfs_dq_sync(struct super_block *sb)
-{
-	sync_dquots(sb, -1);
-}
-
+/* Cannot be called inside a transaction */
 static inline int vfs_dq_off(struct super_block *sb, int remount)
 {
 	int ret = -ENOSYS;
@@ -334,7 +334,11 @@ static inline void vfs_dq_free_inode(struct inode *inode)
 {
 }
 
-static inline void vfs_dq_sync(struct super_block *sb)
+static inline void sync_quota_sb(struct super_block *sb, int type)
+{
+}
+
+static inline void writeout_quota_sb(struct super_block *sb, int type)
 {
 }
 
diff --git a/include/linux/rational.h b/include/linux/rational.h
new file mode 100644
index 000000000000..4f532fcd9eea
--- /dev/null
+++ b/include/linux/rational.h
@@ -0,0 +1,19 @@
+/*
+ * rational fractions
+ *
+ * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <os@emlix.com>
+ *
+ * helper functions when coping with rational numbers,
+ * e.g. when calculating optimum numerator/denominator pairs for
+ * pll configuration taking into account restricted register size
+ */
+
+#ifndef _LINUX_RATIONAL_H
+#define _LINUX_RATIONAL_H
+
+void rational_best_approximation(
+	unsigned long given_numerator, unsigned long given_denominator,
+	unsigned long max_numerator, unsigned long max_denominator,
+	unsigned long *best_numerator, unsigned long *best_denominator);
+
+#endif /* _LINUX_RATIONAL_H */
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index e649bd3f2c97..5710f43bbc9e 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -198,6 +198,32 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	at->prev = last;
 }
 
+/**
+ * list_entry_rcu - get the struct for this entry
+ * @ptr:        the &struct list_head pointer.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_struct within the struct.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_entry_rcu(ptr, type, member) \
+	container_of(rcu_dereference(ptr), type, member)
+
+/**
+ * list_first_entry_rcu - get the first element from a list
+ * @ptr:        the list head to take the element from.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_first_entry_rcu(ptr, type, member) \
+	list_entry_rcu((ptr)->next, type, member)
+
 #define __list_for_each_rcu(pos, head) \
 	for (pos = rcu_dereference((head)->next); \
 		pos != (head); \
@@ -214,9 +240,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * as long as the traversal is guarded by rcu_read_lock().
  */
 #define list_for_each_entry_rcu(pos, head, member) \
-	for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \
+	for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \
 		prefetch(pos->member.next), &pos->member != (head); \
-		pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member))
+		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
 
 /**
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 58b2aa5312b9..5a5153806c42 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -161,8 +161,15 @@ struct rcu_data {
 	unsigned long offline_fqs;	/* Kicked due to being offline. */
 	unsigned long resched_ipi;	/* Sent a resched IPI. */
 
-	/* 5) For future __rcu_pending statistics. */
+	/* 5) __rcu_pending() statistics. */
 	long n_rcu_pending;		/* rcu_pending() calls since boot. */
+	long n_rp_qs_pending;
+	long n_rp_cb_ready;
+	long n_rp_cpu_needs_gp;
+	long n_rp_gp_completed;
+	long n_rp_gp_started;
+	long n_rp_need_fqs;
+	long n_rp_need_nothing;
 
 	int cpu;
 };
diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h
index 6473650c28f1..dab68bbed675 100644
--- a/include/linux/reiserfs_fs_sb.h
+++ b/include/linux/reiserfs_fs_sb.h
@@ -453,6 +453,7 @@ enum reiserfs_mount_options {
 	REISERFS_ATTRS,
 	REISERFS_XATTRS_USER,
 	REISERFS_POSIXACL,
+	REISERFS_EXPOSE_PRIVROOT,
 	REISERFS_BARRIER_NONE,
 	REISERFS_BARRIER_FLUSH,
 
@@ -490,6 +491,7 @@ enum reiserfs_mount_options {
 #define reiserfs_data_writeback(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_WRITEBACK))
 #define reiserfs_xattrs_user(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_XATTRS_USER))
 #define reiserfs_posixacl(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_POSIXACL))
+#define reiserfs_expose_privroot(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_EXPOSE_PRIVROOT))
 #define reiserfs_xattrs_optional(s) (reiserfs_xattrs_user(s) || reiserfs_posixacl(s))
 #define reiserfs_barrier_none(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_BARRIER_NONE))
 #define reiserfs_barrier_flush(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_BARRIER_FLUSH))
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index e1b7b2173885..8670f1575fe1 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -11,7 +11,7 @@ struct ring_buffer_iter;
  * Don't refer to this struct directly, use functions below.
  */
 struct ring_buffer_event {
-	u32		type:2, len:3, time_delta:27;
+	u32		type_len:5, time_delta:27;
 	u32		array[];
 };
 
@@ -24,7 +24,8 @@ struct ring_buffer_event {
  *				  size is variable depending on how much
  *				  padding is needed
  *				 If time_delta is non zero:
- *				  everything else same as RINGBUF_TYPE_DATA
+ *				  array[0] holds the actual length
+ *				  size = 4 + length (bytes)
  *
  * @RINGBUF_TYPE_TIME_EXTEND:	Extend the time delta
  *				 array[0] = time delta (28 .. 59)
@@ -35,22 +36,23 @@ struct ring_buffer_event {
  *				 array[1..2] = tv_sec
  *				 size = 16 bytes
  *
- * @RINGBUF_TYPE_DATA:		Data record
- *				 If len is zero:
+ * <= @RINGBUF_TYPE_DATA_TYPE_LEN_MAX:
+ *				Data record
+ *				 If type_len is zero:
  *				  array[0] holds the actual length
  *				  array[1..(length+3)/4] holds data
- *				  size = 4 + 4 + length (bytes)
+ *				  size = 4 + length (bytes)
  *				 else
- *				  length = len << 2
+ *				  length = type_len << 2
  *				  array[0..(length+3)/4-1] holds data
  *				  size = 4 + length (bytes)
  */
 enum ring_buffer_type {
+	RINGBUF_TYPE_DATA_TYPE_LEN_MAX = 28,
 	RINGBUF_TYPE_PADDING,
 	RINGBUF_TYPE_TIME_EXTEND,
 	/* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
 	RINGBUF_TYPE_TIME_STAMP,
-	RINGBUF_TYPE_DATA,
 };
 
 unsigned ring_buffer_event_length(struct ring_buffer_event *event);
@@ -68,13 +70,54 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
 	return event->time_delta;
 }
 
+/*
+ * ring_buffer_event_discard can discard any event in the ring buffer.
+ *   it is up to the caller to protect against a reader from
+ *   consuming it or a writer from wrapping and replacing it.
+ *
+ * No external protection is needed if this is called before
+ * the event is commited. But in that case it would be better to
+ * use ring_buffer_discard_commit.
+ *
+ * Note, if an event that has not been committed is discarded
+ * with ring_buffer_event_discard, it must still be committed.
+ */
 void ring_buffer_event_discard(struct ring_buffer_event *event);
 
+/*
+ * ring_buffer_discard_commit will remove an event that has not
+ *   ben committed yet. If this is used, then ring_buffer_unlock_commit
+ *   must not be called on the discarded event. This function
+ *   will try to remove the event from the ring buffer completely
+ *   if another event has not been written after it.
+ *
+ * Example use:
+ *
+ *  if (some_condition)
+ *    ring_buffer_discard_commit(buffer, event);
+ *  else
+ *    ring_buffer_unlock_commit(buffer, event);
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event);
+
 /*
  * size is in bytes for each per CPU buffer.
  */
 struct ring_buffer *
-ring_buffer_alloc(unsigned long size, unsigned flags);
+__ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key);
+
+/*
+ * Because the ring buffer is generic, if other users of the ring buffer get
+ * traced by ftrace, it can produce lockdep warnings. We need to keep each
+ * ring buffer's lock class separate.
+ */
+#define ring_buffer_alloc(size, flags)			\
+({							\
+	static struct lock_class_key __key;		\
+	__ring_buffer_alloc((size), (flags), &__key);	\
+})
+
 void ring_buffer_free(struct ring_buffer *buffer);
 
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
@@ -122,6 +165,8 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer);
 unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
@@ -137,6 +182,11 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data);
 int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
 			  size_t len, int cpu, int full);
 
+struct trace_seq;
+
+int ring_buffer_print_entry_header(struct trace_seq *s);
+int ring_buffer_print_page_header(struct trace_seq *s);
+
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
 };
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b4c38bc8049c..4896fdfec913 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -77,6 +77,7 @@ struct sched_param {
 #include <linux/proportions.h>
 #include <linux/seccomp.h>
 #include <linux/rcupdate.h>
+#include <linux/rculist.h>
 #include <linux/rtmutex.h>
 
 #include <linux/time.h>
@@ -96,8 +97,9 @@ struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
 struct bio;
-struct bts_tracer;
 struct fs_struct;
+struct bts_context;
+struct perf_counter_context;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -116,6 +118,7 @@ struct fs_struct;
  *    11 bit fractions.
  */
 extern unsigned long avenrun[];		/* Load averages */
+extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
 
 #define FSHIFT		11		/* nr of bits of precision */
 #define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
@@ -135,8 +138,9 @@ DECLARE_PER_CPU(unsigned long, process_counts);
 extern int nr_processes(void);
 extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
-extern unsigned long nr_active(void);
 extern unsigned long nr_iowait(void);
+extern void calc_global_load(void);
+extern u64 cpu_nr_migrations(int cpu);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -672,6 +676,10 @@ struct user_struct {
 	struct work_struct work;
 #endif
 #endif
+
+#ifdef CONFIG_PERF_COUNTERS
+	atomic_long_t locked_vm;
+#endif
 };
 
 extern int uids_sysfs_init(void);
@@ -838,7 +846,17 @@ struct sched_group {
 	 */
 	u32 reciprocal_cpu_power;
 
-	unsigned long cpumask[];
+	/*
+	 * The CPUs this group covers.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 *
+	 * It is also be embedded into static data structures at build
+	 * time. (See 'struct static_sched_group' in kernel/sched.c)
+	 */
+	unsigned long cpumask[0];
 };
 
 static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
@@ -924,8 +942,17 @@ struct sched_domain {
 	char *name;
 #endif
 
-	/* span of all CPUs in this domain */
-	unsigned long span[];
+	/*
+	 * Span of all CPUs in this domain.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 *
+	 * It is also be embedded into static data structures at build
+	 * time. (See 'struct static_sched_domain' in kernel/sched.c)
+	 */
+	unsigned long span[0];
 };
 
 static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
@@ -1052,9 +1079,10 @@ struct sched_entity {
 	u64			last_wakeup;
 	u64			avg_overlap;
 
+	u64			nr_migrations;
+
 	u64			start_runtime;
 	u64			avg_wakeup;
-	u64			nr_migrations;
 
 #ifdef CONFIG_SCHEDSTATS
 	u64			wait_start;
@@ -1209,18 +1237,11 @@ struct task_struct {
 	struct list_head ptraced;
 	struct list_head ptrace_entry;
 
-#ifdef CONFIG_X86_PTRACE_BTS
 	/*
 	 * This is the tracer handle for the ptrace BTS extension.
 	 * This field actually belongs to the ptracer task.
 	 */
-	struct bts_tracer *bts;
-	/*
-	 * The buffer to hold the BTS data.
-	 */
-	void *bts_buffer;
-	size_t bts_size;
-#endif /* CONFIG_X86_PTRACE_BTS */
+	struct bts_context *bts;
 
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
@@ -1247,7 +1268,9 @@ struct task_struct {
 					 * credentials (COW) */
 	const struct cred *cred;	/* effective (overridable) subjective task
 					 * credentials (COW) */
-	struct mutex cred_exec_mutex;	/* execve vs ptrace cred calculation mutex */
+	struct mutex cred_guard_mutex;	/* guard against foreign influences on
+					 * credential calculations
+					 * (notably. ptrace) */
 
 	char comm[TASK_COMM_LEN]; /* executable name excluding path
 				     - access with [gs]et_task_comm (which lock
@@ -1380,6 +1403,11 @@ struct task_struct {
 	struct list_head pi_state_list;
 	struct futex_pi_state *pi_state_cache;
 #endif
+#ifdef CONFIG_PERF_COUNTERS
+	struct perf_counter_context *perf_counter_ctxp;
+	struct mutex perf_counter_mutex;
+	struct list_head perf_counter_list;
+#endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *mempolicy;
 	short il_next;
@@ -1428,7 +1456,9 @@ struct task_struct {
 #ifdef CONFIG_TRACING
 	/* state flags for use by tracers */
 	unsigned long trace;
-#endif
+	/* bitmask of trace recursion */
+	unsigned long trace_recursion;
+#endif /* CONFIG_TRACING */
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -1885,6 +1915,7 @@ extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
 extern void flush_signals(struct task_struct *);
+extern void __flush_signals(struct task_struct *);
 extern void ignore_signals(struct task_struct *);
 extern void flush_signal_handlers(struct task_struct *, int force_default);
 extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
@@ -2001,8 +2032,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
+extern void wait_task_context_switch(struct task_struct *p);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
+static inline void wait_task_context_switch(struct task_struct *p) {}
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {
@@ -2010,7 +2043,8 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
-#define next_task(p)	list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
+#define next_task(p) \
+	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
 
 #define for_each_process(p) \
 	for (p = &init_task ; (p = next_task(p)) != &init_task ; )
@@ -2049,8 +2083,8 @@ int same_thread_group(struct task_struct *p1, struct task_struct *p2)
 
 static inline struct task_struct *next_thread(const struct task_struct *p)
 {
-	return list_entry(rcu_dereference(p->thread_group.next),
-			  struct task_struct, thread_group);
+	return list_entry_rcu(p->thread_group.next,
+			      struct task_struct, thread_group);
 }
 
 static inline int thread_group_empty(struct task_struct *p)
@@ -2388,6 +2422,13 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
+/*
+ * Call the function if the target task is executing on a CPU right now:
+ */
+extern void task_oncpu_function_call(struct task_struct *p,
+				     void (*func) (void *info), void *info);
+
+
 #ifdef CONFIG_MM_OWNER
 extern void mm_update_next_owner(struct mm_struct *mm);
 extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
diff --git a/include/linux/security.h b/include/linux/security.h
index d5fd6163606f..5eff459b3833 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -2197,6 +2197,8 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot,
 				     unsigned long addr,
 				     unsigned long addr_only)
 {
+	if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO))
+		return -EACCES;
 	return 0;
 }
 
diff --git a/include/linux/serial.h b/include/linux/serial.h
index 9136cc5608c3..e5bb75a63802 100644
--- a/include/linux/serial.h
+++ b/include/linux/serial.h
@@ -96,54 +96,76 @@ struct serial_uart_config {
 
 /*
  * Definitions for async_struct (and serial_struct) flags field
+ *
+ * Define ASYNCB_* for convenient use with {test,set,clear}_bit.
  */
-#define ASYNC_HUP_NOTIFY 0x0001 /* Notify getty on hangups and closes 
-				   on the callout port */
-#define ASYNC_FOURPORT  0x0002	/* Set OU1, OUT2 per AST Fourport settings */
-#define ASYNC_SAK	0x0004	/* Secure Attention Key (Orange book) */
-#define ASYNC_SPLIT_TERMIOS 0x0008 /* Separate termios for dialin/callout */
+#define ASYNCB_HUP_NOTIFY	 0 /* Notify getty on hangups and closes
+				    * on the callout port */
+#define ASYNCB_FOURPORT		 1 /* Set OU1, OUT2 per AST Fourport settings */
+#define ASYNCB_SAK		 2 /* Secure Attention Key (Orange book) */
+#define ASYNCB_SPLIT_TERMIOS	 3 /* Separate termios for dialin/callout */
+#define ASYNCB_SPD_HI		 4 /* Use 56000 instead of 38400 bps */
+#define ASYNCB_SPD_VHI		 5 /* Use 115200 instead of 38400 bps */
+#define ASYNCB_SKIP_TEST	 6 /* Skip UART test during autoconfiguration */
+#define ASYNCB_AUTO_IRQ		 7 /* Do automatic IRQ during
+				    * autoconfiguration */
+#define ASYNCB_SESSION_LOCKOUT	 8 /* Lock out cua opens based on session */
+#define ASYNCB_PGRP_LOCKOUT	 9 /* Lock out cua opens based on pgrp */
+#define ASYNCB_CALLOUT_NOHUP	10 /* Don't do hangups for cua device */
+#define ASYNCB_HARDPPS_CD	11 /* Call hardpps when CD goes high  */
+#define ASYNCB_SPD_SHI		12 /* Use 230400 instead of 38400 bps */
+#define ASYNCB_LOW_LATENCY	13 /* Request low latency behaviour */
+#define ASYNCB_BUGGY_UART	14 /* This is a buggy UART, skip some safety
+				    * checks.  Note: can be dangerous! */
+#define ASYNCB_AUTOPROBE	15 /* Port was autoprobed by PCI or PNP code */
+#define ASYNCB_LAST_USER	15
 
-#define ASYNC_SPD_MASK	0x1030
-#define ASYNC_SPD_HI	0x0010	/* Use 56000 instead of 38400 bps */
+/* Internal flags used only by kernel */
+#define ASYNCB_INITIALIZED	31 /* Serial port was initialized */
+#define ASYNCB_NORMAL_ACTIVE	29 /* Normal device is active */
+#define ASYNCB_BOOT_AUTOCONF	28 /* Autoconfigure port on bootup */
+#define ASYNCB_CLOSING		27 /* Serial port is closing */
+#define ASYNCB_CTS_FLOW		26 /* Do CTS flow control */
+#define ASYNCB_CHECK_CD		25 /* i.e., CLOCAL */
+#define ASYNCB_SHARE_IRQ	24 /* for multifunction cards, no longer used */
+#define ASYNCB_CONS_FLOW	23 /* flow control for console  */
+#define ASYNCB_BOOT_ONLYMCA	22 /* Probe only if MCA bus */
+#define ASYNCB_FIRST_KERNEL	22
 
-#define ASYNC_SPD_VHI	0x0020  /* Use 115200 instead of 38400 bps */
-#define ASYNC_SPD_CUST	0x0030  /* Use user-specified divisor */
+#define ASYNC_HUP_NOTIFY	(1U << ASYNCB_HUP_NOTIFY)
+#define ASYNC_FOURPORT		(1U << ASYNCB_FOURPORT)
+#define ASYNC_SAK		(1U << ASYNCB_SAK)
+#define ASYNC_SPLIT_TERMIOS	(1U << ASYNCB_SPLIT_TERMIOS)
+#define ASYNC_SPD_HI		(1U << ASYNCB_SPD_HI)
+#define ASYNC_SPD_VHI		(1U << ASYNCB_SPD_VHI)
+#define ASYNC_SKIP_TEST		(1U << ASYNCB_SKIP_TEST)
+#define ASYNC_AUTO_IRQ		(1U << ASYNCB_AUTO_IRQ)
+#define ASYNC_SESSION_LOCKOUT	(1U << ASYNCB_SESSION_LOCKOUT)
+#define ASYNC_PGRP_LOCKOUT	(1U << ASYNCB_PGRP_LOCKOUT)
+#define ASYNC_CALLOUT_NOHUP	(1U << ASYNCB_CALLOUT_NOHUP)
+#define ASYNC_HARDPPS_CD	(1U << ASYNCB_HARDPPS_CD)
+#define ASYNC_SPD_SHI		(1U << ASYNCB_SPD_SHI)
+#define ASYNC_LOW_LATENCY	(1U << ASYNCB_LOW_LATENCY)
+#define ASYNC_BUGGY_UART	(1U << ASYNCB_BUGGY_UART)
+#define ASYNC_AUTOPROBE		(1U << ASYNCB_AUTOPROBE)
 
-#define ASYNC_SKIP_TEST	0x0040 /* Skip UART test during autoconfiguration */
-#define ASYNC_AUTO_IRQ  0x0080 /* Do automatic IRQ during autoconfiguration */
-#define ASYNC_SESSION_LOCKOUT 0x0100 /* Lock out cua opens based on session */
-#define ASYNC_PGRP_LOCKOUT    0x0200 /* Lock out cua opens based on pgrp */
-#define ASYNC_CALLOUT_NOHUP   0x0400 /* Don't do hangups for cua device */
+#define ASYNC_FLAGS		((1U << ASYNCB_LAST_USER) - 1)
+#define ASYNC_USR_MASK		(ASYNC_SPD_HI|ASYNC_SPD_VHI| \
+		ASYNC_CALLOUT_NOHUP|ASYNC_SPD_SHI|ASYNC_LOW_LATENCY)
+#define ASYNC_SPD_CUST		(ASYNC_SPD_HI|ASYNC_SPD_VHI)
+#define ASYNC_SPD_WARP		(ASYNC_SPD_HI|ASYNC_SPD_SHI)
+#define ASYNC_SPD_MASK		(ASYNC_SPD_HI|ASYNC_SPD_VHI|ASYNC_SPD_SHI)
 
-#define ASYNC_HARDPPS_CD	0x0800	/* Call hardpps when CD goes high  */
-
-#define ASYNC_SPD_SHI	0x1000	/* Use 230400 instead of 38400 bps */
-#define ASYNC_SPD_WARP	0x1010	/* Use 460800 instead of 38400 bps */
-
-#define ASYNC_LOW_LATENCY 0x2000 /* Request low latency behaviour */
-
-#define ASYNC_BUGGY_UART  0x4000 /* This is a buggy UART, skip some safety
-				  * checks.  Note: can be dangerous! */
-
-#define ASYNC_AUTOPROBE	 0x8000 /* Port was autoprobed by PCI or PNP code */
-
-#define ASYNC_FLAGS	0x7FFF	/* Possible legal async flags */
-#define ASYNC_USR_MASK	0x3430	/* Legal flags that non-privileged
-				 * users can set or reset */
-
-/* Internal flags used only by kernel/chr_drv/serial.c */
-#define ASYNC_INITIALIZED	0x80000000 /* Serial port was initialized */
-#define ASYNC_NORMAL_ACTIVE	0x20000000 /* Normal device is active */
-#define ASYNC_BOOT_AUTOCONF	0x10000000 /* Autoconfigure port on bootup */
-#define ASYNC_CLOSING		0x08000000 /* Serial port is closing */
-#define ASYNC_CTS_FLOW		0x04000000 /* Do CTS flow control */
-#define ASYNC_CHECK_CD		0x02000000 /* i.e., CLOCAL */
-#define ASYNC_SHARE_IRQ		0x01000000 /* for multifunction cards
-					     --- no longer used */
-#define ASYNC_CONS_FLOW		0x00800000 /* flow control for console  */
-
-#define ASYNC_BOOT_ONLYMCA	0x00400000 /* Probe only if MCA bus */
-#define ASYNC_INTERNAL_FLAGS	0xFFC00000 /* Internal flags */
+#define ASYNC_INITIALIZED	(1U << ASYNCB_INITIALIZED)
+#define ASYNC_NORMAL_ACTIVE	(1U << ASYNCB_NORMAL_ACTIVE)
+#define ASYNC_BOOT_AUTOCONF	(1U << ASYNCB_BOOT_AUTOCONF)
+#define ASYNC_CLOSING		(1U << ASYNCB_CLOSING)
+#define ASYNC_CTS_FLOW		(1U << ASYNCB_CTS_FLOW)
+#define ASYNC_CHECK_CD		(1U << ASYNCB_CHECK_CD)
+#define ASYNC_SHARE_IRQ		(1U << ASYNCB_SHARE_IRQ)
+#define ASYNC_CONS_FLOW		(1U << ASYNCB_CONS_FLOW)
+#define ASYNC_BOOT_ONLYMCA	(1U << ASYNCB_BOOT_ONLYMCA)
+#define ASYNC_INTERNAL_FLAGS	(~((1U << ASYNCB_FIRST_KERNEL) - 1))
 
 /*
  * Multiport serial configuration structure --- external structure
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 57a97e52e58d..6fd80c4243f1 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -41,7 +41,8 @@
 #define PORT_XSCALE	15
 #define PORT_RM9000	16	/* PMC-Sierra RM9xxx internal UART */
 #define PORT_OCTEON	17	/* Cavium OCTEON internal UART */
-#define PORT_MAX_8250	17	/* max port ID */
+#define PORT_AR7	18	/* Texas Instruments AR7 internal UART */
+#define PORT_MAX_8250	18	/* max port ID */
 
 /*
  * ARM specific type numbers.  These are not currently guaranteed
@@ -167,6 +168,9 @@
 /* MAX3100 */
 #define PORT_MAX3100    86
 
+/* Timberdale UART */
+#define PORT_TIMBUART	87
+
 #ifdef __KERNEL__
 
 #include <linux/compiler.h>
diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h
index 893cc53486bc..1c297ddc9d5a 100644
--- a/include/linux/serial_sci.h
+++ b/include/linux/serial_sci.h
@@ -25,8 +25,7 @@ struct plat_sci_port {
 	unsigned int	irqs[SCIx_NR_IRQS];	/* ERI, RXI, TXI, BRI */
 	unsigned int	type;			/* SCI / SCIF / IRDA */
 	upf_t		flags;			/* UPF_* flags */
+	char		*clk;			/* clock string */
 };
 
-int early_sci_setup(struct uart_port *port);
-
 #endif /* __LINUX_SERIAL_SCI_H */
diff --git a/include/linux/sh_cmt.h b/include/linux/sh_cmt.h
deleted file mode 100644
index 68cacde5954f..000000000000
--- a/include/linux/sh_cmt.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __SH_CMT_H__
-#define __SH_CMT_H__
-
-struct sh_cmt_config {
-	char *name;
-	unsigned long channel_offset;
-	int timer_bit;
-	char *clk;
-	unsigned long clockevent_rating;
-	unsigned long clocksource_rating;
-};
-
-#endif /* __SH_CMT_H__ */
diff --git a/include/linux/sh_timer.h b/include/linux/sh_timer.h
new file mode 100644
index 000000000000..864bd56bd3b0
--- /dev/null
+++ b/include/linux/sh_timer.h
@@ -0,0 +1,13 @@
+#ifndef __SH_TIMER_H__
+#define __SH_TIMER_H__
+
+struct sh_timer_config {
+	char *name;
+	long channel_offset;
+	int timer_bit;
+	char *clk;
+	unsigned long clockevent_rating;
+	unsigned long clocksource_rating;
+};
+
+#endif /* __SH_TIMER_H__ */
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 84f997f8aa53..c7552836bd95 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -235,6 +235,8 @@ static inline int valid_signal(unsigned long sig)
 extern int next_signal(struct sigpending *pending, sigset_t *mask);
 extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p);
 extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *);
+extern long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig,
+				 siginfo_t *info);
 extern long do_sigpending(void __user *, unsigned long);
 extern int sigprocmask(int, sigset_t *, sigset_t *);
 extern int show_unhandled_signals;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 24c5602bee99..48803064cedf 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -62,6 +62,8 @@
 # define SLAB_DEBUG_OBJECTS	0x00000000UL
 #endif
 
+#define SLAB_NOLEAKTRACE	0x00800000UL	/* Avoid kmemleak tracing */
+
 /* The following flags affect the page allocator grouping pages by mobility */
 #define SLAB_RECLAIM_ACCOUNT	0x00020000UL		/* Objects are reclaimable */
 #define SLAB_TEMPORARY		SLAB_RECLAIM_ACCOUNT	/* Objects are short-lived */
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 5ac9b0bcaf9a..713f841ecaa9 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -14,7 +14,7 @@
 #include <asm/page.h>		/* kmalloc_sizes.h needs PAGE_SIZE */
 #include <asm/cache.h>		/* kmalloc_sizes.h needs L1_CACHE_BYTES */
 #include <linux/compiler.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 /* Size description struct for general caches. */
 struct cache_sizes {
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 5046f90c1171..be5d40c43bd2 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -10,7 +10,7 @@
 #include <linux/gfp.h>
 #include <linux/workqueue.h>
 #include <linux/kobject.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index 938234c4a996..d4841ed8215b 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -60,6 +60,7 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 #define __raw_spin_is_locked(lock)	((void)(lock), 0)
 /* for sched.c and kernel_lock.c: */
 # define __raw_spin_lock(lock)		do { (void)(lock); } while (0)
+# define __raw_spin_lock_flags(lock, flags)	do { (void)(lock); } while (0)
 # define __raw_spin_unlock(lock)	do { (void)(lock); } while (0)
 # define __raw_spin_trylock(lock)	({ (void)(lock); 1; })
 #endif /* DEBUG_SPINLOCK */
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 5f3faa9d15ae..18e7c7c0cae6 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -11,8 +11,7 @@
 #include <linux/pipe_fs_i.h>
 
 /*
- * splice is tied to pipes as a transport (at least for now), so we'll just
- * add the splice flags here.
+ * Flags passed in from splice/tee/vmsplice
  */
 #define SPLICE_F_MOVE	(0x01)	/* move pages instead of copying */
 #define SPLICE_F_NONBLOCK (0x02) /* don't block on the pipe splicing (but */
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ac9ff54f7cb3..cb1a6631b8f4 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -29,7 +29,8 @@ extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
 
 extern dma_addr_t swiotlb_phys_to_bus(struct device *hwdev,
 				      phys_addr_t address);
-extern phys_addr_t swiotlb_bus_to_phys(dma_addr_t address);
+extern phys_addr_t swiotlb_bus_to_phys(struct device *hwdev,
+				       dma_addr_t address);
 
 extern int swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size);
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 30520844b8da..c6c84ad8bd71 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -55,6 +55,7 @@ struct compat_timeval;
 struct robust_list_head;
 struct getcpu_cache;
 struct old_linux_dirent;
+struct perf_counter_attr;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -755,4 +756,8 @@ asmlinkage long sys_pipe(int __user *);
 
 int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
 
+
+asmlinkage long sys_perf_counter_open(
+		const struct perf_counter_attr __user *attr_uptr,
+		pid_t pid, int cpu, int group_fd, unsigned long flags);
 #endif
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e6b820f8b56b..a8cc4e13434c 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -21,13 +21,14 @@ struct restart_block {
 		struct {
 			unsigned long arg0, arg1, arg2, arg3;
 		};
-		/* For futex_wait */
+		/* For futex_wait and futex_wait_requeue_pi */
 		struct {
 			u32 *uaddr;
 			u32 val;
 			u32 flags;
 			u32 bitset;
 			u64 time;
+			u32 *uaddr2;
 		} futex;
 		/* For nanosleep */
 		struct {
diff --git a/include/linux/time.h b/include/linux/time.h
index 242f62499bb7..ea16c1a01d51 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -113,6 +113,21 @@ struct timespec current_kernel_time(void);
 #define CURRENT_TIME		(current_kernel_time())
 #define CURRENT_TIME_SEC	((struct timespec) { get_seconds(), 0 })
 
+/* Some architectures do not supply their own clocksource.
+ * This is mainly the case in architectures that get their
+ * inter-tick times by reading the counter on their interval
+ * timer. Since these timers wrap every tick, they're not really
+ * useful as clocksources. Wrapping them to act like one is possible
+ * but not very efficient. So we provide a callout these arches
+ * can implement for use with the jiffies clocksource to provide
+ * finer then tick granular time.
+ */
+#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
+extern u32 arch_gettimeoffset(void);
+#else
+static inline u32 arch_gettimeoffset(void) { return 0; }
+#endif
+
 extern void do_gettimeofday(struct timeval *tv);
 extern int do_settimeofday(struct timespec *tv);
 extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz);
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
new file mode 100644
index 000000000000..c68bccba2074
--- /dev/null
+++ b/include/linux/trace_seq.h
@@ -0,0 +1,92 @@
+#ifndef _LINUX_TRACE_SEQ_H
+#define _LINUX_TRACE_SEQ_H
+
+#include <linux/fs.h>
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE.
+ */
+
+struct trace_seq {
+	unsigned char		buffer[PAGE_SIZE];
+	unsigned int		len;
+	unsigned int		readpos;
+};
+
+static inline void
+trace_seq_init(struct trace_seq *s)
+{
+	s->len = 0;
+	s->readpos = 0;
+}
+
+/*
+ * Currently only defined when tracing is enabled.
+ */
+#ifdef CONFIG_TRACING
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+	__attribute__ ((format (printf, 2, 0)));
+extern int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
+extern void trace_print_seq(struct seq_file *m, struct trace_seq *s);
+extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+				 size_t cnt);
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
+extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+				size_t len);
+extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
+extern int trace_seq_path(struct trace_seq *s, struct path *path);
+
+#else /* CONFIG_TRACING */
+static inline int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+{
+	return 0;
+}
+static inline int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
+{
+	return 0;
+}
+
+static inline void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+}
+static inline ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+				 size_t cnt)
+{
+	return 0;
+}
+static inline int trace_seq_puts(struct trace_seq *s, const char *str)
+{
+	return 0;
+}
+static inline int trace_seq_putc(struct trace_seq *s, unsigned char c)
+{
+	return 0;
+}
+static inline int
+trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
+{
+	return 0;
+}
+static inline int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+				       size_t len)
+{
+	return 0;
+}
+static inline void *trace_seq_reserve(struct trace_seq *s, size_t len)
+{
+	return NULL;
+}
+static inline int trace_seq_path(struct trace_seq *s, struct path *path)
+{
+	return 0;
+}
+#endif /* CONFIG_TRACING */
+
+#endif /* _LINUX_TRACE_SEQ_H */
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index d35a7ee7611f..14df7e635d43 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -31,6 +31,8 @@ struct tracepoint {
 					 * Keep in sync with vmlinux.lds.h.
 					 */
 
+#ifndef DECLARE_TRACE
+
 #define TP_PROTO(args...)	args
 #define TP_ARGS(args...)		args
 
@@ -114,6 +116,7 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	struct tracepoint *end)
 { }
 #endif /* CONFIG_TRACEPOINTS */
+#endif /* DECLARE_TRACE */
 
 /*
  * Connect a probe to a tracepoint.
@@ -154,10 +157,8 @@ static inline void tracepoint_synchronize_unregister(void)
 }
 
 #define PARAMS(args...) args
-#define TRACE_FORMAT(name, proto, args, fmt)		\
-	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-
 
+#ifndef TRACE_EVENT
 /*
  * For use with the TRACE_EVENT macro:
  *
@@ -262,5 +263,6 @@ static inline void tracepoint_synchronize_unregister(void)
 
 #define TRACE_EVENT(name, proto, args, struct, assign, print)	\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#endif
 
 #endif
diff --git a/include/linux/tty.h b/include/linux/tty.h
index fc39db95499f..1488d8c81aac 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -185,7 +185,7 @@ struct tty_port;
 struct tty_port_operations {
 	/* Return 1 if the carrier is raised */
 	int (*carrier_raised)(struct tty_port *port);
-	void (*raise_dtr_rts)(struct tty_port *port);
+	void (*dtr_rts)(struct tty_port *port, int raise);
 };
 	
 struct tty_port {
@@ -201,6 +201,9 @@ struct tty_port {
 	unsigned char		*xmit_buf;	/* Optional buffer */
 	int			close_delay;	/* Close port delay */
 	int			closing_wait;	/* Delay for output */
+	int			drain_delay;	/* Set to zero if no pure time
+						   based drain is needed else
+						   set to size of fifo */
 };
 
 /*
@@ -223,8 +226,11 @@ struct tty_struct {
 	struct tty_driver *driver;
 	const struct tty_operations *ops;
 	int index;
-	/* The ldisc objects are protected by tty_ldisc_lock at the moment */
-	struct tty_ldisc ldisc;
+
+	/* Protects ldisc changes: Lock tty not pty */
+	struct mutex ldisc_mutex;
+	struct tty_ldisc *ldisc;
+
 	struct mutex termios_mutex;
 	spinlock_t ctrl_lock;
 	/* Termios values are protected by the termios mutex */
@@ -311,6 +317,7 @@ struct tty_struct {
 #define TTY_CLOSING 		7	/* ->close() in progress */
 #define TTY_LDISC 		9	/* Line discipline attached */
 #define TTY_LDISC_CHANGING 	10	/* Line discipline changing */
+#define TTY_LDISC_OPEN	 	11	/* Line discipline is open */
 #define TTY_HW_COOK_OUT 	14	/* Hardware can do output cooking */
 #define TTY_HW_COOK_IN 		15	/* Hardware can do input cooking */
 #define TTY_PTY_LOCK 		16	/* pty private */
@@ -403,6 +410,7 @@ extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b);
 extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *);
 extern void tty_ldisc_deref(struct tty_ldisc *);
 extern struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *);
+extern void tty_ldisc_hangup(struct tty_struct *tty);
 extern const struct file_operations tty_ldiscs_proc_fops;
 
 extern void tty_wakeup(struct tty_struct *tty);
@@ -425,6 +433,9 @@ extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx,
 extern void tty_release_dev(struct file *filp);
 extern int tty_init_termios(struct tty_struct *tty);
 
+extern struct tty_struct *tty_pair_get_tty(struct tty_struct *tty);
+extern struct tty_struct *tty_pair_get_pty(struct tty_struct *tty);
+
 extern struct mutex tty_mutex;
 
 extern void tty_write_unlock(struct tty_struct *tty);
@@ -438,6 +449,7 @@ extern struct tty_struct *tty_port_tty_get(struct tty_port *port);
 extern void tty_port_tty_set(struct tty_port *port, struct tty_struct *tty);
 extern int tty_port_carrier_raised(struct tty_port *port);
 extern void tty_port_raise_dtr_rts(struct tty_port *port);
+extern void tty_port_lower_dtr_rts(struct tty_port *port);
 extern void tty_port_hangup(struct tty_port *port);
 extern int tty_port_block_til_ready(struct tty_port *port,
 				struct tty_struct *tty, struct file *filp);
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index bcba84ea2d86..3566129384a4 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -127,7 +127,8 @@
  * 	the line discipline are close to full, and it should somehow
  * 	signal that no more characters should be sent to the tty.
  *
- *	Optional: Always invoke via tty_throttle();
+ *	Optional: Always invoke via tty_throttle(), called under the
+ *	termios lock.
  * 
  * void (*unthrottle)(struct tty_struct * tty);
  *
@@ -135,7 +136,8 @@
  * 	that characters can now be sent to the tty without fear of
  * 	overrunning the input buffers of the line disciplines.
  * 
- *	Optional: Always invoke via tty_unthrottle();
+ *	Optional: Always invoke via tty_unthrottle(), called under the
+ *	termios lock.
  *
  * void (*stop)(struct tty_struct *tty);
  *
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 625e9e4639c6..8cdfed738fe4 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -224,8 +224,7 @@ struct usb_serial_driver {
 	/* Called by console with tty = NULL and by tty */
 	int  (*open)(struct tty_struct *tty,
 			struct usb_serial_port *port, struct file *filp);
-	void (*close)(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+	void (*close)(struct usb_serial_port *port);
 	int  (*write)(struct tty_struct *tty, struct usb_serial_port *port,
 			const unsigned char *buf, int count);
 	/* Called only by the tty layer */
@@ -241,6 +240,10 @@ struct usb_serial_driver {
 	int  (*tiocmget)(struct tty_struct *tty, struct file *file);
 	int  (*tiocmset)(struct tty_struct *tty, struct file *file,
 			 unsigned int set, unsigned int clear);
+	/* Called by the tty layer for port level work. There may or may not
+	   be an attached tty at this point */
+	void (*dtr_rts)(struct usb_serial_port *port, int on);
+	int  (*carrier_raised)(struct usb_serial_port *port);
 	/* USB events */
 	void (*read_int_callback)(struct urb *urb);
 	void (*write_int_callback)(struct urb *urb);
@@ -283,8 +286,7 @@ extern int usb_serial_generic_open(struct tty_struct *tty,
 		struct usb_serial_port *port, struct file *filp);
 extern int usb_serial_generic_write(struct tty_struct *tty,
 	struct usb_serial_port *port, const unsigned char *buf, int count);
-extern void usb_serial_generic_close(struct tty_struct *tty,
-			struct usb_serial_port *port, struct file *filp);
+extern void usb_serial_generic_close(struct usb_serial_port *port);
 extern int usb_serial_generic_resume(struct usb_serial *serial);
 extern int usb_serial_generic_write_room(struct tty_struct *tty);
 extern int usb_serial_generic_chars_in_buffer(struct tty_struct *tty);
diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h
index 94c56d29869d..be7d255fc7cf 100644
--- a/include/linux/virtio_blk.h
+++ b/include/linux/virtio_blk.h
@@ -15,6 +15,10 @@
 #define VIRTIO_BLK_F_GEOMETRY	4	/* Legacy geometry available  */
 #define VIRTIO_BLK_F_RO		5	/* Disk is read-only */
 #define VIRTIO_BLK_F_BLK_SIZE	6	/* Block size of disk is available*/
+#define VIRTIO_BLK_F_SCSI	7	/* Supports scsi command passthru */
+#define VIRTIO_BLK_F_IDENTIFY	8	/* ATA IDENTIFY supported */
+
+#define VIRTIO_BLK_ID_BYTES	(sizeof(__u16[256]))	/* IDENTIFY DATA */
 
 struct virtio_blk_config
 {
@@ -32,6 +36,7 @@ struct virtio_blk_config
 	} geometry;
 	/* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */
 	__u32 blk_size;
+	__u8 identify[VIRTIO_BLK_ID_BYTES];
 } __attribute__((packed));
 
 /* These two define direction. */
@@ -55,6 +60,13 @@ struct virtio_blk_outhdr
 	__u64 sector;
 };
 
+struct virtio_scsi_inhdr {
+	__u32 errors;
+	__u32 data_len;
+	__u32 sense_len;
+	__u32 residual;
+};
+
 /* And this is the final byte of the write scatter-gather list. */
 #define VIRTIO_BLK_S_OK		0
 #define VIRTIO_BLK_S_IOERR	1
diff --git a/include/linux/wait.h b/include/linux/wait.h
index bc024632f365..6788e1a4d4ca 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -132,8 +132,6 @@ static inline void __remove_wait_queue(wait_queue_head_t *head,
 	list_del(&old->task_list);
 }
 
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-			int nr_exclusive, int sync, void *key);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 93445477f86a..3224820c8514 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -79,7 +79,6 @@ struct writeback_control {
 void writeback_inodes(struct writeback_control *wbc);
 int inode_wait(void *);
 void sync_inodes_sb(struct super_block *, int wait);
-void sync_inodes(int wait);
 
 /* writeback.h requires fs.h; it, too, is not included from here. */
 static inline void wait_on_inode(struct inode *inode)
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 43b50d36925c..3878d1dc7f59 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -270,7 +270,7 @@ static inline unsigned char scsi_get_prot_type(struct scsi_cmnd *scmd)
 
 static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd)
 {
-	return scmd->request->sector;
+	return blk_rq_pos(scmd->request);
 }
 
 static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd)
diff --git a/include/trace/block.h b/include/trace/block.h
deleted file mode 100644
index 25b7068b819e..000000000000
--- a/include/trace/block.h
+++ /dev/null
@@ -1,76 +0,0 @@
-#ifndef _TRACE_BLOCK_H
-#define _TRACE_BLOCK_H
-
-#include <linux/blkdev.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(block_rq_abort,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_insert,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_issue,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_requeue,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_complete,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_bio_bounce,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_complete,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_backmerge,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_frontmerge,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_queue,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_getrq,
-	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
-	      TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_sleeprq,
-	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
-	      TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_plug,
-	TP_PROTO(struct request_queue *q),
-	      TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_timer,
-	TP_PROTO(struct request_queue *q),
-	      TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_io,
-	TP_PROTO(struct request_queue *q),
-	      TP_ARGS(q));
-
-DECLARE_TRACE(block_split,
-	TP_PROTO(struct request_queue *q, struct bio *bio, unsigned int pdu),
-	      TP_ARGS(q, bio, pdu));
-
-DECLARE_TRACE(block_remap,
-	TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
-		 sector_t from, sector_t to),
-	      TP_ARGS(q, bio, dev, from, to));
-
-#endif
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
new file mode 100644
index 000000000000..f7a7ae1e8f90
--- /dev/null
+++ b/include/trace/define_trace.h
@@ -0,0 +1,75 @@
+/*
+ * Trace files that want to automate creationg of all tracepoints defined
+ * in their file should include this file. The following are macros that the
+ * trace file may define:
+ *
+ * TRACE_SYSTEM defines the system the tracepoint is for
+ *
+ * TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h
+ *     This macro may be defined to tell define_trace.h what file to include.
+ *     Note, leave off the ".h".
+ *
+ * TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace
+ *     then this macro can define the path to use. Note, the path is relative to
+ *     define_trace.h, not the file including it. Full path names for out of tree
+ *     modules must be used.
+ */
+
+#ifdef CREATE_TRACE_POINTS
+
+/* Prevent recursion */
+#undef CREATE_TRACE_POINTS
+
+#include <linux/stringify.h>
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
+	DEFINE_TRACE(name)
+
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args)	\
+	DEFINE_TRACE(name)
+
+#undef TRACE_INCLUDE
+#undef __TRACE_INCLUDE
+
+#ifndef TRACE_INCLUDE_FILE
+# define TRACE_INCLUDE_FILE TRACE_SYSTEM
+# define UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifndef TRACE_INCLUDE_PATH
+# define __TRACE_INCLUDE(system) <trace/events/system.h>
+# define UNDEF_TRACE_INCLUDE_PATH
+#else
+# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h)
+#endif
+
+# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system)
+
+/* Let the trace headers be reread */
+#define TRACE_HEADER_MULTI_READ
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#ifdef CONFIG_EVENT_TRACING
+#include <trace/ftrace.h>
+#endif
+
+#undef TRACE_HEADER_MULTI_READ
+
+/* Only undef what we defined in this file */
+#ifdef UNDEF_TRACE_INCLUDE_FILE
+# undef TRACE_INCLUDE_FILE
+# undef UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifdef UNDEF_TRACE_INCLUDE_PATH
+# undef TRACE_INCLUDE_PATH
+# undef UNDEF_TRACE_INCLUDE_PATH
+#endif
+
+/* We may be processing more files */
+#define CREATE_TRACE_POINTS
+
+#endif /* CREATE_TRACE_POINTS */
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
new file mode 100644
index 000000000000..d6b05f42dd44
--- /dev/null
+++ b/include/trace/events/block.h
@@ -0,0 +1,493 @@
+#if !defined(_TRACE_BLOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BLOCK_H
+
+#include <linux/blktrace_api.h>
+#include <linux/blkdev.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM block
+
+TRACE_EVENT(block_rq_abort,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	6		)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_insert,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  unsigned int,	bytes			)
+		__array(  char,		rwbs,	6		)
+		__array(  char,         comm,   TASK_COMM_LEN   )
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+		__entry->bytes     = blk_pc_request(rq) ? blk_rq_bytes(rq) : 0;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __entry->bytes, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_issue,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  unsigned int,	bytes			)
+		__array(  char,		rwbs,	6		)
+		__array(  char,		comm,   TASK_COMM_LEN   )
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+		__entry->bytes     = blk_pc_request(rq) ? blk_rq_bytes(rq) : 0;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __entry->bytes, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_requeue,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	6		)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+		__entry->errors	   = rq->errors;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_complete,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	6		)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+		__entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
+);
+TRACE_EVENT(block_bio_bounce,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_complete,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( sector_t,	sector		)
+		__field( unsigned,	nr_sector	)
+		__field( int,		error		)
+		__array( char,		rwbs,	6	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->error)
+);
+
+TRACE_EVENT(block_bio_backmerge,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_frontmerge,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_queue,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_getrq,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+	TP_ARGS(q, bio, rw),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+        ),
+
+	TP_fast_assign(
+		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
+		__entry->sector		= bio ? bio->bi_sector : 0;
+		__entry->nr_sector	= bio ? bio->bi_size >> 9 : 0;
+		blk_fill_rwbs(__entry->rwbs,
+			      bio ? bio->bi_rw : 0, __entry->nr_sector);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_sleeprq,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+	TP_ARGS(q, bio, rw),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
+		__entry->sector		= bio ? bio->bi_sector : 0;
+		__entry->nr_sector	= bio ? bio->bi_size >> 9 : 0;
+		blk_fill_rwbs(__entry->rwbs,
+			    bio ? bio->bi_rw : 0, __entry->nr_sector);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_plug,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s]", __entry->comm)
+);
+
+TRACE_EVENT(block_unplug_timer,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__field( int,		nr_rq			)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_rq	= q->rq.count[READ] + q->rq.count[WRITE];
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_unplug_io,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__field( int,		nr_rq			)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_rq	= q->rq.count[READ] + q->rq.count[WRITE];
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_split,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio,
+		 unsigned int new_sector),
+
+	TP_ARGS(q, bio, new_sector),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev				)
+		__field( sector_t,	sector				)
+		__field( sector_t,	new_sector			)
+		__array( char,		rwbs,		6		)
+		__array( char,		comm,		TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->new_sector	= new_sector;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu / %llu [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  (unsigned long long)__entry->new_sector,
+		  __entry->comm)
+);
+
+TRACE_EVENT(block_remap,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
+		 sector_t from),
+
+	TP_ARGS(q, bio, dev, from),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( sector_t,	sector		)
+		__field( unsigned int,	nr_sector	)
+		__field( dev_t,		old_dev		)
+		__field( sector_t,	old_sector	)
+		__array( char,		rwbs,	6	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->old_dev	= dev;
+		__entry->old_sector	= from;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+	),
+
+	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector,
+		  MAJOR(__entry->old_dev), MINOR(__entry->old_dev),
+		  (unsigned long long)__entry->old_sector)
+);
+
+#endif /* _TRACE_BLOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
new file mode 100644
index 000000000000..b0c7ede55eb1
--- /dev/null
+++ b/include/trace/events/irq.h
@@ -0,0 +1,145 @@
+#if !defined(_TRACE_IRQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IRQ_H
+
+#include <linux/tracepoint.h>
+#include <linux/interrupt.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq
+
+#define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
+#define show_softirq_name(val)			\
+	__print_symbolic(val,			\
+			 softirq_name(HI),	\
+			 softirq_name(TIMER),	\
+			 softirq_name(NET_TX),	\
+			 softirq_name(NET_RX),	\
+			 softirq_name(BLOCK),	\
+			 softirq_name(TASKLET),	\
+			 softirq_name(SCHED),	\
+			 softirq_name(HRTIMER),	\
+			 softirq_name(RCU))
+
+/**
+ * irq_handler_entry - called immediately before the irq action handler
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ *
+ * The struct irqaction pointed to by @action contains various
+ * information about the handler, including the device name,
+ * @action->name, and the device id, @action->dev_id. When used in
+ * conjunction with the irq_handler_exit tracepoint, we can figure
+ * out irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_entry,
+
+	TP_PROTO(int irq, struct irqaction *action),
+
+	TP_ARGS(irq, action),
+
+	TP_STRUCT__entry(
+		__field(	int,	irq		)
+		__string(	name,	action->name	)
+	),
+
+	TP_fast_assign(
+		__entry->irq = irq;
+		__assign_str(name, action->name);
+	),
+
+	TP_printk("irq=%d handler=%s", __entry->irq, __get_str(name))
+);
+
+/**
+ * irq_handler_exit - called immediately after the irq action handler returns
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ * @ret: return value
+ *
+ * If the @ret value is set to IRQ_HANDLED, then we know that the corresponding
+ * @action->handler scuccessully handled this irq. Otherwise, the irq might be
+ * a shared irq line, or the irq was not handled successfully. Can be used in
+ * conjunction with the irq_handler_entry to understand irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_exit,
+
+	TP_PROTO(int irq, struct irqaction *action, int ret),
+
+	TP_ARGS(irq, action, ret),
+
+	TP_STRUCT__entry(
+		__field(	int,	irq	)
+		__field(	int,	ret	)
+	),
+
+	TP_fast_assign(
+		__entry->irq	= irq;
+		__entry->ret	= ret;
+	),
+
+	TP_printk("irq=%d return=%s",
+		  __entry->irq, __entry->ret ? "handled" : "unhandled")
+);
+
+/**
+ * softirq_entry - called immediately before the softirq handler
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter, contains a pointer to the struct softirq_action
+ * which has a pointer to the action handler that is called. By subtracting
+ * the @vec pointer from the @h pointer, we can determine the softirq
+ * number. Also, when used in combination with the softirq_exit tracepoint
+ * we can determine the softirq latency.
+ */
+TRACE_EVENT(softirq_entry,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec),
+
+	TP_STRUCT__entry(
+		__field(	int,	vec			)
+	),
+
+	TP_fast_assign(
+		__entry->vec = (int)(h - vec);
+	),
+
+	TP_printk("softirq=%d action=%s", __entry->vec,
+		  show_softirq_name(__entry->vec))
+);
+
+/**
+ * softirq_exit - called immediately after the softirq handler returns
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter contains a pointer to the struct softirq_action
+ * that has handled the softirq. By subtracting the @vec pointer from
+ * the @h pointer, we can determine the softirq number. Also, when used in
+ * combination with the softirq_entry tracepoint we can determine the softirq
+ * latency.
+ */
+TRACE_EVENT(softirq_exit,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec),
+
+	TP_STRUCT__entry(
+		__field(	int,	vec			)
+	),
+
+	TP_fast_assign(
+		__entry->vec = (int)(h - vec);
+	),
+
+	TP_printk("softirq=%d action=%s", __entry->vec,
+		  show_softirq_name(__entry->vec))
+);
+
+#endif /*  _TRACE_IRQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
new file mode 100644
index 000000000000..9baba50d6512
--- /dev/null
+++ b/include/trace/events/kmem.h
@@ -0,0 +1,231 @@
+#if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KMEM_H
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kmem
+
+/*
+ * The order of these masks is important. Matching masks will be seen
+ * first and the left over flags will end up showing by themselves.
+ *
+ * For example, if we have GFP_KERNEL before GFP_USER we wil get:
+ *
+ *  GFP_KERNEL|GFP_HARDWALL
+ *
+ * Thus most bits set go first.
+ */
+#define show_gfp_flags(flags)						\
+	(flags) ? __print_flags(flags, "|",				\
+	{(unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"}, \
+	{(unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
+	{(unsigned long)GFP_USER,		"GFP_USER"},		\
+	{(unsigned long)GFP_TEMPORARY,		"GFP_TEMPORARY"},	\
+	{(unsigned long)GFP_KERNEL,		"GFP_KERNEL"},		\
+	{(unsigned long)GFP_NOFS,		"GFP_NOFS"},		\
+	{(unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
+	{(unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
+	{(unsigned long)__GFP_HIGH,		"GFP_HIGH"},		\
+	{(unsigned long)__GFP_WAIT,		"GFP_WAIT"},		\
+	{(unsigned long)__GFP_IO,		"GFP_IO"},		\
+	{(unsigned long)__GFP_COLD,		"GFP_COLD"},		\
+	{(unsigned long)__GFP_NOWARN,		"GFP_NOWARN"},		\
+	{(unsigned long)__GFP_REPEAT,		"GFP_REPEAT"},		\
+	{(unsigned long)__GFP_NOFAIL,		"GFP_NOFAIL"},		\
+	{(unsigned long)__GFP_NORETRY,		"GFP_NORETRY"},		\
+	{(unsigned long)__GFP_COMP,		"GFP_COMP"},		\
+	{(unsigned long)__GFP_ZERO,		"GFP_ZERO"},		\
+	{(unsigned long)__GFP_NOMEMALLOC,	"GFP_NOMEMALLOC"},	\
+	{(unsigned long)__GFP_HARDWALL,		"GFP_HARDWALL"},	\
+	{(unsigned long)__GFP_THISNODE,		"GFP_THISNODE"},	\
+	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
+	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"}		\
+	) : "GFP_NOWAIT"
+
+TRACE_EVENT(kmalloc,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmem_cache_alloc,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmalloc_node,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags,
+		 int node),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+		__field(	int,		node		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+		__entry->node		= node;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->node)
+);
+
+TRACE_EVENT(kmem_cache_alloc_node,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags,
+		 int node),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+		__field(	int,		node		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+		__entry->node		= node;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->node)
+);
+
+TRACE_EVENT(kfree,
+
+	TP_PROTO(unsigned long call_site, const void *ptr),
+
+	TP_ARGS(call_site, ptr),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+	),
+
+	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+
+TRACE_EVENT(kmem_cache_free,
+
+	TP_PROTO(unsigned long call_site, const void *ptr),
+
+	TP_ARGS(call_site, ptr),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+	),
+
+	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+#endif /* _TRACE_KMEM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/lockdep.h b/include/trace/events/lockdep.h
new file mode 100644
index 000000000000..0e956c9dfd7e
--- /dev/null
+++ b/include/trace/events/lockdep.h
@@ -0,0 +1,96 @@
+#if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOCKDEP_H
+
+#include <linux/lockdep.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lockdep
+
+#ifdef CONFIG_LOCKDEP
+
+TRACE_EVENT(lock_acquire,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
+		int trylock, int read, int check,
+		struct lockdep_map *next_lock, unsigned long ip),
+
+	TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, flags)
+		__string(name, lock->name)
+	),
+
+	TP_fast_assign(
+		__entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
+		__assign_str(name, lock->name);
+	),
+
+	TP_printk("%s%s%s", (__entry->flags & 1) ? "try " : "",
+		  (__entry->flags & 2) ? "read " : "",
+		  __get_str(name))
+);
+
+TRACE_EVENT(lock_release,
+
+	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+
+	TP_ARGS(lock, nested, ip),
+
+	TP_STRUCT__entry(
+		__string(name, lock->name)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+	),
+
+	TP_printk("%s", __get_str(name))
+);
+
+#ifdef CONFIG_LOCK_STAT
+
+TRACE_EVENT(lock_contended,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip),
+
+	TP_STRUCT__entry(
+		__string(name, lock->name)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+	),
+
+	TP_printk("%s", __get_str(name))
+);
+
+TRACE_EVENT(lock_acquired,
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+
+	TP_ARGS(lock, ip, waittime),
+
+	TP_STRUCT__entry(
+		__string(name, lock->name)
+		__field(unsigned long, wait_usec)
+		__field(unsigned long, wait_nsec_rem)
+	),
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+		__entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC);
+		__entry->wait_usec = (unsigned long) waittime;
+	),
+	TP_printk("%s (%lu.%03lu us)", __get_str(name), __entry->wait_usec,
+				       __entry->wait_nsec_rem)
+);
+
+#endif
+#endif
+
+#endif /* _TRACE_LOCKDEP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/sched_event_types.h b/include/trace/events/sched.h
similarity index 91%
rename from include/trace/sched_event_types.h
rename to include/trace/events/sched.h
index 63547dc1125f..24ab5bcff7b2 100644
--- a/include/trace/sched_event_types.h
+++ b/include/trace/events/sched.h
@@ -1,9 +1,8 @@
+#if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SCHED_H
 
-/* use <trace/sched.h> instead */
-#ifndef TRACE_EVENT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM sched
@@ -157,6 +156,7 @@ TRACE_EVENT(sched_switch,
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	prev_pid			)
 		__field(	int,	prev_prio			)
+		__field(	long,	prev_state			)
 		__array(	char,	next_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	next_pid			)
 		__field(	int,	next_prio			)
@@ -166,13 +166,19 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
 		__entry->prev_pid	= prev->pid;
 		__entry->prev_prio	= prev->prio;
+		__entry->prev_state	= prev->state;
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
 	),
 
-	TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
+	TP_printk("task %s:%d [%d] (%s) ==> %s:%d [%d]",
 		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
+		__entry->prev_state ?
+		  __print_flags(__entry->prev_state, "|",
+				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
+				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
+				{ 128, "W" }) : "R",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
 
@@ -181,9 +187,9 @@ TRACE_EVENT(sched_switch,
  */
 TRACE_EVENT(sched_migrate_task,
 
-	TP_PROTO(struct task_struct *p, int orig_cpu, int dest_cpu),
+	TP_PROTO(struct task_struct *p, int dest_cpu),
 
-	TP_ARGS(p, orig_cpu, dest_cpu),
+	TP_ARGS(p, dest_cpu),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -197,7 +203,7 @@ TRACE_EVENT(sched_migrate_task,
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
-		__entry->orig_cpu	= orig_cpu;
+		__entry->orig_cpu	= task_cpu(p);
 		__entry->dest_cpu	= dest_cpu;
 	),
 
@@ -334,4 +340,7 @@ TRACE_EVENT(sched_signal_send,
 		  __entry->sig, __entry->comm, __entry->pid)
 );
 
-#undef TRACE_SYSTEM
+#endif /* _TRACE_SCHED_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
new file mode 100644
index 000000000000..1e8fabb57c06
--- /dev/null
+++ b/include/trace/events/skb.h
@@ -0,0 +1,40 @@
+#if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SKB_H
+
+#include <linux/skbuff.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM skb
+
+/*
+ * Tracepoint for free an sk_buff:
+ */
+TRACE_EVENT(kfree_skb,
+
+	TP_PROTO(struct sk_buff *skb, void *location),
+
+	TP_ARGS(skb, location),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned short,	protocol	)
+		__field(	void *,		location	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		if (skb) {
+			__entry->protocol = ntohs(skb->protocol);
+		}
+		__entry->location = location;
+	),
+
+	TP_printk("skbaddr=%p protocol=%u location=%p",
+		__entry->skbaddr, __entry->protocol, __entry->location)
+);
+
+#endif /* _TRACE_SKB_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
new file mode 100644
index 000000000000..035f1bff288e
--- /dev/null
+++ b/include/trace/events/workqueue.h
@@ -0,0 +1,100 @@
+#if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WORKQUEUE_H
+
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM workqueue
+
+TRACE_EVENT(workqueue_insertion,
+
+	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+	TP_ARGS(wq_thread, work),
+
+	TP_STRUCT__entry(
+		__array(char,		thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,		thread_pid)
+		__field(work_func_t,	func)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+		__entry->func		= work->func;
+	),
+
+	TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+		__entry->thread_pid, __entry->func)
+);
+
+TRACE_EVENT(workqueue_execution,
+
+	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+	TP_ARGS(wq_thread, work),
+
+	TP_STRUCT__entry(
+		__array(char,		thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,		thread_pid)
+		__field(work_func_t,	func)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+		__entry->func		= work->func;
+	),
+
+	TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+		__entry->thread_pid, __entry->func)
+);
+
+/* Trace the creation of one workqueue thread on a cpu */
+TRACE_EVENT(workqueue_creation,
+
+	TP_PROTO(struct task_struct *wq_thread, int cpu),
+
+	TP_ARGS(wq_thread, cpu),
+
+	TP_STRUCT__entry(
+		__array(char,	thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,	thread_pid)
+		__field(int,	cpu)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+		__entry->cpu		= cpu;
+	),
+
+	TP_printk("thread=%s:%d cpu=%d", __entry->thread_comm,
+		__entry->thread_pid, __entry->cpu)
+);
+
+TRACE_EVENT(workqueue_destruction,
+
+	TP_PROTO(struct task_struct *wq_thread),
+
+	TP_ARGS(wq_thread),
+
+	TP_STRUCT__entry(
+		__array(char,	thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,	thread_pid)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+	),
+
+	TP_printk("thread=%s:%d", __entry->thread_comm, __entry->thread_pid)
+);
+
+#endif /* _TRACE_WORKQUEUE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
new file mode 100644
index 000000000000..1867553c61e5
--- /dev/null
+++ b/include/trace/ftrace.h
@@ -0,0 +1,591 @@
+/*
+ * Stage 1 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * struct ftrace_raw_<call> {
+ *	struct trace_entry		ent;
+ *	<type>				<item>;
+ *	<type2>				<item2>[<len>];
+ *	[...]
+ * };
+ *
+ * The <type> <item> is created by the __field(type, item) macro or
+ * the __array(type2, item2, len) macro.
+ * We simply do "type item;", and that will create the fields
+ * in the structure.
+ */
+
+#include <linux/ftrace_event.h>
+
+#undef __field
+#define __field(type, item)		type	item;
+
+#undef __array
+#define __array(type, item, len)	type	item[len];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) unsigned short __data_loc_##item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
+	struct ftrace_raw_##name {				\
+		struct trace_entry	ent;			\
+		tstruct						\
+		char			__data[0];		\
+	};							\
+	static struct ftrace_event_call event_##name
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+
+/*
+ * Stage 2 of the trace events.
+ *
+ * Include the following:
+ *
+ * struct ftrace_data_offsets_<call> {
+ *	int				<item1>;
+ *	int				<item2>;
+ *	[...]
+ * };
+ *
+ * The __dynamic_array() macro will create each int <item>, this is
+ * to keep the offset of each array from the beginning of the event.
+ */
+
+#undef __field
+#define __field(type, item);
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)	int item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+	struct ftrace_data_offsets_##call {				\
+		tstruct;						\
+	};
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Setup the showing format of trace point.
+ *
+ * int
+ * ftrace_format_##call(struct trace_seq *s)
+ * {
+ *	struct ftrace_raw_##call field;
+ *	int ret;
+ *
+ *	ret = trace_seq_printf(s, #type " " #item ";"
+ *			       " offset:%u; size:%u;\n",
+ *			       offsetof(struct ftrace_raw_##call, item),
+ *			       sizeof(field.type));
+ *
+ * }
+ */
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef __field
+#define __field(type, item)					\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
+			       "offset:%u;\tsize:%u;\n",		\
+			       (unsigned int)offsetof(typeof(field), item), \
+			       (unsigned int)sizeof(field.item));	\
+	if (!ret)							\
+		return 0;
+
+#undef __array
+#define __array(type, item, len)						\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"	\
+			       "offset:%u;\tsize:%u;\n",		\
+			       (unsigned int)offsetof(typeof(field), item), \
+			       (unsigned int)sizeof(field.item));	\
+	if (!ret)							\
+		return 0;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				       \
+	ret = trace_seq_printf(s, "\tfield:__data_loc " #item ";\t"	       \
+			       "offset:%u;\tsize:%u;\n",		       \
+			       (unsigned int)offsetof(typeof(field),	       \
+					__data_loc_##item),		       \
+			       (unsigned int)sizeof(field.__data_loc_##item)); \
+	if (!ret)							       \
+		return 0;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __entry
+#define __entry REC
+
+#undef __print_symbolic
+#undef __get_dynamic_array
+#undef __get_str
+
+#undef TP_printk
+#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
+
+#undef TP_fast_assign
+#define TP_fast_assign(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+static int								\
+ftrace_format_##call(struct trace_seq *s)				\
+{									\
+	struct ftrace_raw_##call field __attribute__((unused));		\
+	int ret = 0;							\
+									\
+	tstruct;							\
+									\
+	trace_seq_printf(s, "\nprint fmt: " print);			\
+									\
+	return ret;							\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 3 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * enum print_line_t
+ * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
+ * {
+ *	struct trace_seq *s = &iter->seq;
+ *	struct ftrace_raw_<call> *field; <-- defined in stage 1
+ *	struct trace_entry *entry;
+ *	struct trace_seq *p;
+ *	int ret;
+ *
+ *	entry = iter->ent;
+ *
+ *	if (entry->type != event_<call>.id) {
+ *		WARN_ON_ONCE(1);
+ *		return TRACE_TYPE_UNHANDLED;
+ *	}
+ *
+ *	field = (typeof(field))entry;
+ *
+ *	p = get_cpu_var(ftrace_event_seq);
+ *	trace_seq_init(p);
+ *	ret = trace_seq_printf(s, <TP_printk> "\n");
+ *	put_cpu();
+ *	if (!ret)
+ *		return TRACE_TYPE_PARTIAL_LINE;
+ *
+ *	return TRACE_TYPE_HANDLED;
+ * }
+ *
+ * This is the method used to print the raw event to the trace
+ * output format. Note, this is not needed if the data is read
+ * in binary.
+ */
+
+#undef __entry
+#define __entry field
+
+#undef TP_printk
+#define TP_printk(fmt, args...) fmt "\n", args
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field)	\
+		((void *)__entry + __entry->__data_loc_##field)
+
+#undef __get_str
+#define __get_str(field) (char *)__get_dynamic_array(field)
+
+#undef __print_flags
+#define __print_flags(flag, delim, flag_array...)			\
+	({								\
+		static const struct trace_print_flags flags[] =		\
+			{ flag_array, { -1, NULL }};			\
+		ftrace_print_flags_seq(p, delim, flag, flags);		\
+	})
+
+#undef __print_symbolic
+#define __print_symbolic(value, symbol_array...)			\
+	({								\
+		static const struct trace_print_flags symbols[] =	\
+			{ symbol_array, { -1, NULL }};			\
+		ftrace_print_symbols_seq(p, value, symbols);		\
+	})
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+enum print_line_t							\
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
+{									\
+	struct trace_seq *s = &iter->seq;				\
+	struct ftrace_raw_##call *field;				\
+	struct trace_entry *entry;					\
+	struct trace_seq *p;						\
+	int ret;							\
+									\
+	entry = iter->ent;						\
+									\
+	if (entry->type != event_##call.id) {				\
+		WARN_ON_ONCE(1);					\
+		return TRACE_TYPE_UNHANDLED;				\
+	}								\
+									\
+	field = (typeof(field))entry;					\
+									\
+	p = &get_cpu_var(ftrace_event_seq);				\
+	trace_seq_init(p);						\
+	ret = trace_seq_printf(s, #call ": " print);			\
+	put_cpu();							\
+	if (!ret)							\
+		return TRACE_TYPE_PARTIAL_LINE;				\
+									\
+	return TRACE_TYPE_HANDLED;					\
+}
+	
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef __field
+#define __field(type, item)						\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), is_signed_type(type));	\
+	if (ret)							\
+		return ret;
+
+#undef __array
+#define __array(type, item, len)					\
+	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), 0);		\
+	if (ret)							\
+		return ret;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				       \
+	ret = trace_define_field(event_call, "__data_loc" "[" #type "]", #item,\
+				offsetof(typeof(field), __data_loc_##item),    \
+				 sizeof(field.__data_loc_##item), 0);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+int									\
+ftrace_define_fields_##call(void)					\
+{									\
+	struct ftrace_raw_##call field;					\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	int ret;							\
+									\
+	__common_field(int, type, 1);					\
+	__common_field(unsigned char, flags, 0);			\
+	__common_field(unsigned char, preempt_count, 0);		\
+	__common_field(int, pid, 1);					\
+	__common_field(int, tgid, 1);					\
+									\
+	tstruct;							\
+									\
+	return ret;							\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * remember the offset of each array from the beginning of the event.
+ */
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				\
+	__data_offsets->item = __data_size +				\
+			       offsetof(typeof(*entry), __data);	\
+	__data_size += (len) * sizeof(type);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1)       \
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+static inline int ftrace_get_offsets_##call(				\
+	struct ftrace_data_offsets_##call *__data_offsets, proto)       \
+{									\
+	int __data_size = 0;						\
+	struct ftrace_raw_##call __maybe_unused *entry;			\
+									\
+	tstruct;							\
+									\
+	return __data_size;						\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 4 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * static void ftrace_event_<call>(proto)
+ * {
+ *	event_trace_printk(_RET_IP_, "<call>: " <fmt>);
+ * }
+ *
+ * static int ftrace_reg_event_<call>(void)
+ * {
+ *	int ret;
+ *
+ *	ret = register_trace_<call>(ftrace_event_<call>);
+ *	if (!ret)
+ *		pr_info("event trace: Could not activate trace point "
+ *			"probe to  <call>");
+ *	return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ *	unregister_trace_<call>(ftrace_event_<call>);
+ * }
+ *
+ *
+ * For those macros defined with TRACE_EVENT:
+ *
+ * static struct ftrace_event_call event_<call>;
+ *
+ * static void ftrace_raw_event_<call>(proto)
+ * {
+ *	struct ring_buffer_event *event;
+ *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ *	unsigned long irq_flags;
+ *	int pc;
+ *
+ *	local_save_flags(irq_flags);
+ *	pc = preempt_count();
+ *
+ *	event = trace_current_buffer_lock_reserve(event_<call>.id,
+ *				  sizeof(struct ftrace_raw_<call>),
+ *				  irq_flags, pc);
+ *	if (!event)
+ *		return;
+ *	entry	= ring_buffer_event_data(event);
+ *
+ *	<assign>;  <-- Here we assign the entries by the __field and
+ *			__array macros.
+ *
+ *	trace_current_buffer_unlock_commit(event, irq_flags, pc);
+ * }
+ *
+ * static int ftrace_raw_reg_event_<call>(void)
+ * {
+ *	int ret;
+ *
+ *	ret = register_trace_<call>(ftrace_raw_event_<call>);
+ *	if (!ret)
+ *		pr_info("event trace: Could not activate trace point "
+ *			"probe to <call>");
+ *	return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ *	unregister_trace_<call>(ftrace_raw_event_<call>);
+ * }
+ *
+ * static struct trace_event ftrace_event_type_<call> = {
+ *	.trace			= ftrace_raw_output_<call>, <-- stage 2
+ * };
+ *
+ * static int ftrace_raw_init_event_<call>(void)
+ * {
+ *	int id;
+ *
+ *	id = register_ftrace_event(&ftrace_event_type_<call>);
+ *	if (!id)
+ *		return -ENODEV;
+ *	event_<call>.id = id;
+ *	return 0;
+ * }
+ *
+ * static struct ftrace_event_call __used
+ * __attribute__((__aligned__(4)))
+ * __attribute__((section("_ftrace_events"))) event_<call> = {
+ *	.name			= "<call>",
+ *	.system			= "<system>",
+ *	.raw_init		= ftrace_raw_init_event_<call>,
+ *	.regfunc		= ftrace_reg_event_<call>,
+ *	.unregfunc		= ftrace_unreg_event_<call>,
+ *	.show_format		= ftrace_format_<call>,
+ * }
+ *
+ */
+
+#undef TP_FMT
+#define TP_FMT(fmt, args...)	fmt "\n", ##args
+
+#ifdef CONFIG_EVENT_PROFILE
+#define _TRACE_PROFILE(call, proto, args)				\
+static void ftrace_profile_##call(proto)				\
+{									\
+	extern void perf_tpcounter_event(int);				\
+	perf_tpcounter_event(event_##call.id);				\
+}									\
+									\
+static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
+{									\
+	int ret = 0;							\
+									\
+	if (!atomic_inc_return(&event_call->profile_count))		\
+		ret = register_trace_##call(ftrace_profile_##call);	\
+									\
+	return ret;							\
+}									\
+									\
+static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
+{									\
+	if (atomic_add_negative(-1, &event_call->profile_count))	\
+		unregister_trace_##call(ftrace_profile_##call);		\
+}
+
+#define _TRACE_PROFILE_INIT(call)					\
+	.profile_count = ATOMIC_INIT(-1),				\
+	.profile_enable = ftrace_profile_enable_##call,			\
+	.profile_disable = ftrace_profile_disable_##call,
+
+#else
+#define _TRACE_PROFILE(call, proto, args)
+#define _TRACE_PROFILE_INIT(call)
+#endif
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				\
+	__entry->__data_loc_##item = __data_offsets.item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)       	\
+
+#undef __assign_str
+#define __assign_str(dst, src)						\
+	strcpy(__get_str(dst), src);
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
+									\
+static struct ftrace_event_call event_##call;				\
+									\
+static void ftrace_raw_event_##call(proto)				\
+{									\
+	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	struct ring_buffer_event *event;				\
+	struct ftrace_raw_##call *entry;				\
+	unsigned long irq_flags;					\
+	int __data_size;						\
+	int pc;								\
+									\
+	local_save_flags(irq_flags);					\
+	pc = preempt_count();						\
+									\
+	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+									\
+	event = trace_current_buffer_lock_reserve(event_##call.id,	\
+				 sizeof(*entry) + __data_size,		\
+				 irq_flags, pc);			\
+	if (!event)							\
+		return;							\
+	entry	= ring_buffer_event_data(event);			\
+									\
+									\
+	tstruct								\
+									\
+	{ assign; }							\
+									\
+	if (!filter_current_check_discard(event_call, entry, event))	\
+		trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
+}									\
+									\
+static int ftrace_raw_reg_event_##call(void)				\
+{									\
+	int ret;							\
+									\
+	ret = register_trace_##call(ftrace_raw_event_##call);		\
+	if (ret)							\
+		pr_info("event trace: Could not activate trace point "	\
+			"probe to " #call "\n");			\
+	return ret;							\
+}									\
+									\
+static void ftrace_raw_unreg_event_##call(void)				\
+{									\
+	unregister_trace_##call(ftrace_raw_event_##call);		\
+}									\
+									\
+static struct trace_event ftrace_event_type_##call = {			\
+	.trace			= ftrace_raw_output_##call,		\
+};									\
+									\
+static int ftrace_raw_init_event_##call(void)				\
+{									\
+	int id;								\
+									\
+	id = register_ftrace_event(&ftrace_event_type_##call);		\
+	if (!id)							\
+		return -ENODEV;						\
+	event_##call.id = id;						\
+	INIT_LIST_HEAD(&event_##call.fields);				\
+	init_preds(&event_##call);					\
+	return 0;							\
+}									\
+									\
+static struct ftrace_event_call __used					\
+__attribute__((__aligned__(4)))						\
+__attribute__((section("_ftrace_events"))) event_##call = {		\
+	.name			= #call,				\
+	.system			= __stringify(TRACE_SYSTEM),		\
+	.event			= &ftrace_event_type_##call,		\
+	.raw_init		= ftrace_raw_init_event_##call,		\
+	.regfunc		= ftrace_raw_reg_event_##call,		\
+	.unregfunc		= ftrace_raw_unreg_event_##call,	\
+	.show_format		= ftrace_format_##call,			\
+	.define_fields		= ftrace_define_fields_##call,		\
+	_TRACE_PROFILE_INIT(call)					\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef _TRACE_PROFILE
+#undef _TRACE_PROFILE_INIT
+
diff --git a/include/trace/irq.h b/include/trace/irq.h
deleted file mode 100644
index ff5d4495dc37..000000000000
--- a/include/trace/irq.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_IRQ_H
-#define _TRACE_IRQ_H
-
-#include <linux/interrupt.h>
-#include <linux/tracepoint.h>
-
-#include <trace/irq_event_types.h>
-
-#endif
diff --git a/include/trace/irq_event_types.h b/include/trace/irq_event_types.h
deleted file mode 100644
index 85964ebd47ec..000000000000
--- a/include/trace/irq_event_types.h
+++ /dev/null
@@ -1,55 +0,0 @@
-
-/* use <trace/irq.h> instead */
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM irq
-
-/*
- * Tracepoint for entry of interrupt handler:
- */
-TRACE_FORMAT(irq_handler_entry,
-	TP_PROTO(int irq, struct irqaction *action),
-	TP_ARGS(irq, action),
-	TP_FMT("irq=%d handler=%s", irq, action->name)
-	);
-
-/*
- * Tracepoint for return of an interrupt handler:
- */
-TRACE_EVENT(irq_handler_exit,
-
-	TP_PROTO(int irq, struct irqaction *action, int ret),
-
-	TP_ARGS(irq, action, ret),
-
-	TP_STRUCT__entry(
-		__field(	int,	irq	)
-		__field(	int,	ret	)
-	),
-
-	TP_fast_assign(
-		__entry->irq	= irq;
-		__entry->ret	= ret;
-	),
-
-	TP_printk("irq=%d return=%s",
-		  __entry->irq, __entry->ret ? "handled" : "unhandled")
-);
-
-TRACE_FORMAT(softirq_entry,
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
-	TP_ARGS(h, vec),
-	TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
-	);
-
-TRACE_FORMAT(softirq_exit,
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
-	TP_ARGS(h, vec),
-	TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
-	);
-
-#undef TRACE_SYSTEM
diff --git a/include/trace/kmemtrace.h b/include/trace/kmemtrace.h
deleted file mode 100644
index 28ee69f9cd46..000000000000
--- a/include/trace/kmemtrace.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- *
- * This file is released under GPL version 2.
- */
-
-#ifndef _LINUX_KMEMTRACE_H
-#define _LINUX_KMEMTRACE_H
-
-#ifdef __KERNEL__
-
-#include <linux/tracepoint.h>
-#include <linux/types.h>
-
-#ifdef CONFIG_KMEMTRACE
-extern void kmemtrace_init(void);
-#else
-static inline void kmemtrace_init(void)
-{
-}
-#endif
-
-DECLARE_TRACE(kmalloc,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmem_cache_alloc,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmalloc_node,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags,
-		      int node),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kmem_cache_alloc_node,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags,
-		      int node),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kfree,
-	      TP_PROTO(unsigned long call_site, const void *ptr),
-	      TP_ARGS(call_site, ptr));
-DECLARE_TRACE(kmem_cache_free,
-	      TP_PROTO(unsigned long call_site, const void *ptr),
-	      TP_ARGS(call_site, ptr));
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_KMEMTRACE_H */
-
diff --git a/include/trace/lockdep.h b/include/trace/lockdep.h
deleted file mode 100644
index 5ca67df87f2a..000000000000
--- a/include/trace/lockdep.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_LOCKDEP_H
-#define _TRACE_LOCKDEP_H
-
-#include <linux/lockdep.h>
-#include <linux/tracepoint.h>
-
-#include <trace/lockdep_event_types.h>
-
-#endif
diff --git a/include/trace/lockdep_event_types.h b/include/trace/lockdep_event_types.h
deleted file mode 100644
index adccfcd2ec8f..000000000000
--- a/include/trace/lockdep_event_types.h
+++ /dev/null
@@ -1,44 +0,0 @@
-
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM lock
-
-#ifdef CONFIG_LOCKDEP
-
-TRACE_FORMAT(lock_acquire,
-	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
-		int trylock, int read, int check,
-		struct lockdep_map *next_lock, unsigned long ip),
-	TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
-	TP_FMT("%s%s%s", trylock ? "try " : "",
-		read ? "read " : "", lock->name)
-	);
-
-TRACE_FORMAT(lock_release,
-	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
-	TP_ARGS(lock, nested, ip),
-	TP_FMT("%s", lock->name)
-	);
-
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_FORMAT(lock_contended,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
-	TP_ARGS(lock, ip),
-	TP_FMT("%s", lock->name)
-	);
-
-TRACE_FORMAT(lock_acquired,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
-	TP_ARGS(lock, ip),
-	TP_FMT("%s", lock->name)
-	);
-
-#endif
-#endif
-
-#undef TRACE_SYSTEM
diff --git a/include/trace/sched.h b/include/trace/sched.h
deleted file mode 100644
index 4e372a1a29bf..000000000000
--- a/include/trace/sched.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_SCHED_H
-#define _TRACE_SCHED_H
-
-#include <linux/sched.h>
-#include <linux/tracepoint.h>
-
-#include <trace/sched_event_types.h>
-
-#endif
diff --git a/include/trace/skb.h b/include/trace/skb.h
deleted file mode 100644
index b66206d9be72..000000000000
--- a/include/trace/skb.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _TRACE_SKB_H_
-#define _TRACE_SKB_H_
-
-#include <linux/skbuff.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(kfree_skb,
-	TP_PROTO(struct sk_buff *skb, void *location),
-	TP_ARGS(skb, location));
-
-#endif
diff --git a/include/trace/trace_event_types.h b/include/trace/trace_event_types.h
deleted file mode 100644
index df56f5694be6..000000000000
--- a/include/trace/trace_event_types.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* trace/<type>_event_types.h here */
-
-#include <trace/sched_event_types.h>
-#include <trace/irq_event_types.h>
-#include <trace/lockdep_event_types.h>
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
deleted file mode 100644
index fd13750ca4ba..000000000000
--- a/include/trace/trace_events.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* trace/<type>.h here */
-
-#include <trace/sched.h>
-#include <trace/irq.h>
-#include <trace/lockdep.h>
diff --git a/include/trace/workqueue.h b/include/trace/workqueue.h
deleted file mode 100644
index 7626523deeba..000000000000
--- a/include/trace/workqueue.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __TRACE_WORKQUEUE_H
-#define __TRACE_WORKQUEUE_H
-
-#include <linux/tracepoint.h>
-#include <linux/workqueue.h>
-#include <linux/sched.h>
-
-DECLARE_TRACE(workqueue_insertion,
-	   TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-	   TP_ARGS(wq_thread, work));
-
-DECLARE_TRACE(workqueue_execution,
-	   TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-	   TP_ARGS(wq_thread, work));
-
-/* Trace the creation of one workqueue thread on a cpu */
-DECLARE_TRACE(workqueue_creation,
-	   TP_PROTO(struct task_struct *wq_thread, int cpu),
-	   TP_ARGS(wq_thread, cpu));
-
-DECLARE_TRACE(workqueue_destruction,
-	   TP_PROTO(struct task_struct *wq_thread),
-	   TP_ARGS(wq_thread));
-
-#endif /* __TRACE_WORKQUEUE_H */
diff --git a/include/xen/Kbuild b/include/xen/Kbuild
new file mode 100644
index 000000000000..4e65c16a445b
--- /dev/null
+++ b/include/xen/Kbuild
@@ -0,0 +1 @@
+header-y += evtchn.h
diff --git a/include/xen/events.h b/include/xen/events.h
index 0d5f1adc0363..e68d59a90ca8 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -53,4 +53,7 @@ bool xen_test_irq_pending(int irq);
    irq will be disabled so it won't deliver an interrupt. */
 void xen_poll_irq(int irq);
 
+/* Determine the IRQ which is bound to an event channel */
+unsigned irq_from_evtchn(unsigned int evtchn);
+
 #endif	/* _XEN_EVENTS_H */
diff --git a/include/xen/evtchn.h b/include/xen/evtchn.h
new file mode 100644
index 000000000000..14e833ee4e0b
--- /dev/null
+++ b/include/xen/evtchn.h
@@ -0,0 +1,88 @@
+/******************************************************************************
+ * evtchn.h
+ *
+ * Interface to /dev/xen/evtchn.
+ *
+ * Copyright (c) 2003-2005, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __LINUX_PUBLIC_EVTCHN_H__
+#define __LINUX_PUBLIC_EVTCHN_H__
+
+/*
+ * Bind a fresh port to VIRQ @virq.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_VIRQ				\
+	_IOC(_IOC_NONE, 'E', 0, sizeof(struct ioctl_evtchn_bind_virq))
+struct ioctl_evtchn_bind_virq {
+	unsigned int virq;
+};
+
+/*
+ * Bind a fresh port to remote <@remote_domain, @remote_port>.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_INTERDOMAIN			\
+	_IOC(_IOC_NONE, 'E', 1, sizeof(struct ioctl_evtchn_bind_interdomain))
+struct ioctl_evtchn_bind_interdomain {
+	unsigned int remote_domain, remote_port;
+};
+
+/*
+ * Allocate a fresh port for binding to @remote_domain.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_UNBOUND_PORT			\
+	_IOC(_IOC_NONE, 'E', 2, sizeof(struct ioctl_evtchn_bind_unbound_port))
+struct ioctl_evtchn_bind_unbound_port {
+	unsigned int remote_domain;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_UNBIND				\
+	_IOC(_IOC_NONE, 'E', 3, sizeof(struct ioctl_evtchn_unbind))
+struct ioctl_evtchn_unbind {
+	unsigned int port;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_NOTIFY				\
+	_IOC(_IOC_NONE, 'E', 4, sizeof(struct ioctl_evtchn_notify))
+struct ioctl_evtchn_notify {
+	unsigned int port;
+};
+
+/* Clear and reinitialise the event buffer. Clear error condition. */
+#define IOCTL_EVTCHN_RESET				\
+	_IOC(_IOC_NONE, 'E', 5, 0)
+
+#endif /* __LINUX_PUBLIC_EVTCHN_H__ */
diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h
index 453235e923f0..e8b6519d47e9 100644
--- a/include/xen/interface/version.h
+++ b/include/xen/interface/version.h
@@ -57,4 +57,7 @@ struct xen_feature_info {
 /* Declares the features reported by XENVER_get_features. */
 #include "features.h"
 
+/* arg == NULL; returns host memory page size. */
+#define XENVER_pagesize 7
+
 #endif /* __XEN_PUBLIC_VERSION_H__ */
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index f87f9614844d..b9763badbd77 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -91,8 +91,7 @@ struct xenbus_driver {
 	void (*otherend_changed)(struct xenbus_device *dev,
 				 enum xenbus_state backend_state);
 	int (*remove)(struct xenbus_device *dev);
-	int (*suspend)(struct xenbus_device *dev);
-	int (*suspend_cancel)(struct xenbus_device *dev);
+	int (*suspend)(struct xenbus_device *dev, pm_message_t state);
 	int (*resume)(struct xenbus_device *dev);
 	int (*uevent)(struct xenbus_device *, char **, int, char *, int);
 	struct device_driver driver;
diff --git a/init/Kconfig b/init/Kconfig
index 7be4d3836745..c649657e2259 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -302,13 +302,14 @@ config AUDITSYSCALL
 
 config AUDIT_TREE
 	def_bool y
-	depends on AUDITSYSCALL && INOTIFY
+	depends on AUDITSYSCALL
+	select INOTIFY
 
 menu "RCU Subsystem"
 
 choice
 	prompt "RCU Implementation"
-	default CLASSIC_RCU
+	default TREE_RCU
 
 config CLASSIC_RCU
 	bool "Classic RCU"
@@ -933,6 +934,40 @@ config AIO
           by some high performance threaded applications. Disabling
           this option saves about 7k.
 
+config HAVE_PERF_COUNTERS
+	bool
+
+menu "Performance Counters"
+
+config PERF_COUNTERS
+	bool "Kernel Performance Counters"
+	depends on HAVE_PERF_COUNTERS
+	select ANON_INODES
+	help
+	  Enable kernel support for performance counter hardware.
+
+	  Performance counters are special hardware registers available
+	  on most modern CPUs. These registers count the number of certain
+	  types of hw events: such as instructions executed, cachemisses
+	  suffered, or branches mis-predicted - without slowing down the
+	  kernel or applications. These registers can also trigger interrupts
+	  when a threshold number of events have passed - and can thus be
+	  used to profile the code that runs on that CPU.
+
+	  The Linux Performance Counter subsystem provides an abstraction of
+	  these hardware capabilities, available via a system call. It
+	  provides per task and per CPU counters, and it provides event
+	  capabilities on top of those.
+
+	  Say Y if unsure.
+
+config EVENT_PROFILE
+	bool "Tracepoint profile sources"
+	depends on PERF_COUNTERS && EVENT_TRACER
+	default y
+
+endmenu
+
 config VM_EVENT_COUNTERS
 	default y
 	bool "Enable VM event counters for /proc/vmstat" if EMBEDDED
diff --git a/init/main.c b/init/main.c
index d721dad05dd7..5616661eac01 100644
--- a/init/main.c
+++ b/init/main.c
@@ -56,6 +56,7 @@
 #include <linux/debug_locks.h>
 #include <linux/debugobjects.h>
 #include <linux/lockdep.h>
+#include <linux/kmemleak.h>
 #include <linux/pid_namespace.h>
 #include <linux/device.h>
 #include <linux/kthread.h>
@@ -64,6 +65,7 @@
 #include <linux/idr.h>
 #include <linux/ftrace.h>
 #include <linux/async.h>
+#include <linux/kmemtrace.h>
 #include <trace/boot.h>
 
 #include <asm/io.h>
@@ -71,7 +73,6 @@
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
-#include <trace/kmemtrace.h>
 
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/smp.h>
@@ -533,6 +534,16 @@ void __init __weak thread_info_cache_init(void)
 {
 }
 
+/*
+ * Set up kernel memory allocators
+ */
+static void __init mm_init(void)
+{
+	mem_init();
+	kmem_cache_init();
+	vmalloc_init();
+}
+
 asmlinkage void __init start_kernel(void)
 {
 	char * command_line;
@@ -574,6 +585,23 @@ asmlinkage void __init start_kernel(void)
 	setup_nr_cpu_ids();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 
+	build_all_zonelists();
+	page_alloc_init();
+
+	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
+	parse_early_param();
+	parse_args("Booting kernel", static_command_line, __start___param,
+		   __stop___param - __start___param,
+		   &unknown_bootoption);
+	/*
+	 * These use large bootmem allocations and must precede
+	 * kmem_cache_init()
+	 */
+	pidhash_init();
+	vfs_caches_init_early();
+	sort_main_extable();
+	trap_init();
+	mm_init();
 	/*
 	 * Set up the scheduler prior starting any interrupts (such as the
 	 * timer interrupt). Full topology setup happens at smp_init()
@@ -585,25 +613,16 @@ asmlinkage void __init start_kernel(void)
 	 * fragile until we cpu_idle() for the first time.
 	 */
 	preempt_disable();
-	build_all_zonelists();
-	page_alloc_init();
-	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
-	parse_early_param();
-	parse_args("Booting kernel", static_command_line, __start___param,
-		   __stop___param - __start___param,
-		   &unknown_bootoption);
 	if (!irqs_disabled()) {
 		printk(KERN_WARNING "start_kernel(): bug: interrupts were "
 				"enabled *very* early, fixing it\n");
 		local_irq_disable();
 	}
-	sort_main_extable();
-	trap_init();
 	rcu_init();
 	/* init some links before init_ISA_irqs() */
 	early_irq_init();
 	init_IRQ();
-	pidhash_init();
+	prio_tree_init();
 	init_timers();
 	hrtimers_init();
 	softirq_init();
@@ -645,15 +664,12 @@ asmlinkage void __init start_kernel(void)
 		initrd_start = 0;
 	}
 #endif
-	vmalloc_init();
-	vfs_caches_init_early();
 	cpuset_init_early();
 	page_cgroup_init();
-	mem_init();
 	enable_debug_pagealloc();
 	cpu_hotplug_init();
-	kmem_cache_init();
 	kmemtrace_init();
+	kmemleak_init();
 	debug_objects_mem_init();
 	idr_init_cache();
 	setup_per_cpu_pageset();
@@ -663,7 +679,6 @@ asmlinkage void __init start_kernel(void)
 	calibrate_delay();
 	pidmap_init();
 	pgtable_cache_init();
-	prio_tree_init();
 	anon_vma_init();
 #ifdef CONFIG_X86
 	if (efi_enabled)
diff --git a/ipc/sem.c b/ipc/sem.c
index 16a2189e96f9..87c2b641fd7b 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -1290,8 +1290,8 @@ void exit_sem(struct task_struct *tsk)
 		int i;
 
 		rcu_read_lock();
-		un = list_entry(rcu_dereference(ulp->list_proc.next),
-					struct sem_undo, list_proc);
+		un = list_entry_rcu(ulp->list_proc.next,
+				    struct sem_undo, list_proc);
 		if (&un->list_proc == &ulp->list_proc)
 			semid = -1;
 		 else
diff --git a/ipc/shm.c b/ipc/shm.c
index 425971600485..15dd238e5338 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -384,7 +384,6 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto no_file;
-	ima_shm_check(file);
 
 	id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
 	if (id < 0) {
@@ -891,7 +890,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr)
 	file = alloc_file(path.mnt, path.dentry, f_mode, &shm_file_operations);
 	if (!file)
 		goto out_free;
-	ima_shm_check(file);
+	ima_counts_get(file);
 
 	file->private_data = sfd;
 	file->f_mapping = shp->shm_file->f_mapping;
diff --git a/kernel/Makefile b/kernel/Makefile
index 42423665660a..90b53f6dc226 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -93,8 +93,10 @@ obj-$(CONFIG_LATENCYTOP) += latencytop.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
+obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
+obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 6e7351739a82..1f6396d76687 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -568,7 +568,7 @@ void audit_trim_trees(void)
 		if (err)
 			goto skip_it;
 
-		root_mnt = collect_mounts(path.mnt, path.dentry);
+		root_mnt = collect_mounts(&path);
 		path_put(&path);
 		if (!root_mnt)
 			goto skip_it;
@@ -660,7 +660,7 @@ int audit_add_tree_rule(struct audit_krule *rule)
 	err = kern_path(tree->pathname, 0, &path);
 	if (err)
 		goto Err;
-	mnt = collect_mounts(path.mnt, path.dentry);
+	mnt = collect_mounts(&path);
 	path_put(&path);
 	if (!mnt) {
 		err = -ENOMEM;
@@ -720,7 +720,7 @@ int audit_tag_tree(char *old, char *new)
 	err = kern_path(new, 0, &path);
 	if (err)
 		return err;
-	tagged = collect_mounts(path.mnt, path.dentry);
+	tagged = collect_mounts(&path);
 	path_put(&path);
 	if (!tagged)
 		return -ENOMEM;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a7267bfd3765..3fb789f6df94 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -46,6 +46,7 @@
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
 #include <linux/namei.h>
+#include <linux/smp_lock.h>
 
 #include <asm/atomic.h>
 
@@ -900,6 +901,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgroup_sb_opts opts;
 
+	lock_kernel();
 	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
 	mutex_lock(&cgroup_mutex);
 
@@ -927,6 +929,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	kfree(opts.release_agent);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+	unlock_kernel();
 	return ret;
 }
 
diff --git a/kernel/compat.c b/kernel/compat.c
index 42d56544460f..f6c204f07ea6 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -882,6 +882,17 @@ compat_sys_rt_sigtimedwait (compat_sigset_t __user *uthese,
 
 }
 
+asmlinkage long
+compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig,
+			     struct compat_siginfo __user *uinfo)
+{
+	siginfo_t info;
+
+	if (copy_siginfo_from_user32(&info, uinfo))
+		return -EFAULT;
+	return do_rt_tgsigqueueinfo(tgid, pid, sig, &info);
+}
+
 #ifdef __ARCH_WANT_COMPAT_SYS_TIME
 
 /* compat_time_t is a 32 bit "long" and needs to get converted. */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 026faccca869..d5a7e17474ee 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1857,7 +1857,7 @@ struct cgroup_subsys cpuset_subsys = {
 
 int __init cpuset_init_early(void)
 {
-	alloc_bootmem_cpumask_var(&top_cpuset.cpus_allowed);
+	alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_NOWAIT);
 
 	top_cpuset.mems_generation = cpuset_mems_generation++;
 	return 0;
diff --git a/kernel/cred.c b/kernel/cred.c
index 3a039189d707..1bb4d7e5d616 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -167,7 +167,7 @@ EXPORT_SYMBOL(prepare_creds);
 
 /*
  * Prepare credentials for current to perform an execve()
- * - The caller must hold current->cred_exec_mutex
+ * - The caller must hold current->cred_guard_mutex
  */
 struct cred *prepare_exec_creds(void)
 {
@@ -276,7 +276,7 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	struct cred *new;
 	int ret;
 
-	mutex_init(&p->cred_exec_mutex);
+	mutex_init(&p->cred_guard_mutex);
 
 	if (
 #ifdef CONFIG_KEYS
diff --git a/kernel/exit.c b/kernel/exit.c
index abf9cf3b95c6..b6c90b5ef509 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -48,7 +48,8 @@
 #include <linux/tracehook.h>
 #include <linux/fs_struct.h>
 #include <linux/init_task.h>
-#include <trace/sched.h>
+#include <linux/perf_counter.h>
+#include <trace/events/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -56,10 +57,6 @@
 #include <asm/mmu_context.h>
 #include "cred-internals.h"
 
-DEFINE_TRACE(sched_process_free);
-DEFINE_TRACE(sched_process_exit);
-DEFINE_TRACE(sched_process_wait);
-
 static void exit_mm(struct task_struct * tsk);
 
 static void __unhash_process(struct task_struct *p)
@@ -158,6 +155,9 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
+#ifdef CONFIG_PERF_COUNTERS
+	WARN_ON_ONCE(tsk->perf_counter_ctxp);
+#endif
 	trace_sched_process_free(tsk);
 	put_task_struct(tsk);
 }
@@ -174,6 +174,7 @@ repeat:
 	atomic_dec(&__task_cred(p)->user->processes);
 
 	proc_flush_task(p);
+
 	write_lock_irq(&tasklist_lock);
 	tracehook_finish_release_task(p);
 	__exit_signal(p);
@@ -975,16 +976,19 @@ NORET_TYPE void do_exit(long code)
 		module_put(tsk->binfmt->module);
 
 	proc_exit_connector(tsk);
+
+	/*
+	 * Flush inherited counters to the parent - before the parent
+	 * gets woken up by child-exit notifications.
+	 */
+	perf_counter_exit_task(tsk);
+
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
 	mpol_put(tsk->mempolicy);
 	tsk->mempolicy = NULL;
 #endif
 #ifdef CONFIG_FUTEX
-	/*
-	 * This must happen late, after the PID is not
-	 * hashed anymore:
-	 */
 	if (unlikely(!list_empty(&tsk->pi_state_list)))
 		exit_pi_state_list(tsk);
 	if (unlikely(current->pi_state_cache))
@@ -1476,6 +1480,7 @@ static int wait_consider_task(struct task_struct *parent, int ptrace,
 		 */
 		if (*notask_error)
 			*notask_error = ret;
+		return 0;
 	}
 
 	if (likely(!ptrace) && unlikely(p->ptrace)) {
diff --git a/kernel/fork.c b/kernel/fork.c
index 875ffbdd96d0..4430eb1376f2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -61,8 +61,8 @@
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
 #include <linux/fs_struct.h>
-#include <trace/sched.h>
 #include <linux/magic.h>
+#include <linux/perf_counter.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -71,6 +71,8 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
+#include <trace/events/sched.h>
+
 /*
  * Protected counters by write_lock_irq(&tasklist_lock)
  */
@@ -83,8 +85,6 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
-DEFINE_TRACE(sched_process_fork);
-
 int nr_processes(void)
 {
 	int cpu;
@@ -982,6 +982,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (!p)
 		goto fork_out;
 
+	ftrace_graph_init_task(p);
+
 	rt_mutex_init_task(p);
 
 #ifdef CONFIG_PROVE_LOCKING
@@ -1089,12 +1091,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
-	if (unlikely(current->ptrace))
-		ptrace_fork(p, clone_flags);
+
+	p->bts = NULL;
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	sched_fork(p, clone_flags);
 
+	retval = perf_counter_init_task(p);
+	if (retval)
+		goto bad_fork_cleanup_policy;
+
 	if ((retval = audit_alloc(p)))
 		goto bad_fork_cleanup_policy;
 	/* copy all the process information */
@@ -1131,8 +1137,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		}
 	}
 
-	ftrace_graph_init_task(p);
-
 	p->pid = pid_nr(pid);
 	p->tgid = p->pid;
 	if (clone_flags & CLONE_THREAD)
@@ -1141,7 +1145,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (current->nsproxy != p->nsproxy) {
 		retval = ns_cgroup_clone(p, pid);
 		if (retval)
-			goto bad_fork_free_graph;
+			goto bad_fork_free_pid;
 	}
 
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
@@ -1233,7 +1237,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		spin_unlock(&current->sighand->siglock);
 		write_unlock_irq(&tasklist_lock);
 		retval = -ERESTARTNOINTR;
-		goto bad_fork_free_graph;
+		goto bad_fork_free_pid;
 	}
 
 	if (clone_flags & CLONE_THREAD) {
@@ -1268,8 +1272,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	cgroup_post_fork(p);
 	return p;
 
-bad_fork_free_graph:
-	ftrace_graph_exit_task(p);
 bad_fork_free_pid:
 	if (pid != &init_struct_pid)
 		free_pid(pid);
@@ -1293,6 +1295,7 @@ bad_fork_cleanup_semundo:
 bad_fork_cleanup_audit:
 	audit_free(p);
 bad_fork_cleanup_policy:
+	perf_counter_free_task(p);
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
@@ -1406,6 +1409,12 @@ long do_fork(unsigned long clone_flags,
 		if (clone_flags & CLONE_VFORK) {
 			p->vfork_done = &vfork;
 			init_completion(&vfork);
+		} else if (!(clone_flags & CLONE_VM)) {
+			/*
+			 * vfork will do an exec which will call
+			 * set_task_comm()
+			 */
+			perf_counter_fork(p);
 		}
 
 		audit_finish_fork(p);
diff --git a/kernel/futex.c b/kernel/futex.c
index d546b2d53a62..80b5ce716596 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -19,6 +19,10 @@
  *  PRIVATE futexes by Eric Dumazet
  *  Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com>
  *
+ *  Requeue-PI support by Darren Hart <dvhltc@us.ibm.com>
+ *  Copyright (C) IBM Corporation, 2009
+ *  Thanks to Thomas Gleixner for conceptual design and careful reviews.
+ *
  *  Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
  *  enough at me, Linus for the original (flawed) idea, Matthew
  *  Kirkwood for proof-of-concept implementation.
@@ -96,8 +100,8 @@ struct futex_pi_state {
  */
 struct futex_q {
 	struct plist_node list;
-	/* There can only be a single waiter */
-	wait_queue_head_t waiter;
+	/* Waiter reference */
+	struct task_struct *task;
 
 	/* Which hash list lock to use: */
 	spinlock_t *lock_ptr;
@@ -107,7 +111,9 @@ struct futex_q {
 
 	/* Optional priority inheritance state: */
 	struct futex_pi_state *pi_state;
-	struct task_struct *task;
+
+	/* rt_waiter storage for requeue_pi: */
+	struct rt_mutex_waiter *rt_waiter;
 
 	/* Bitset for the optional bitmasked wakeup */
 	u32 bitset;
@@ -278,6 +284,25 @@ void put_futex_key(int fshared, union futex_key *key)
 	drop_futex_key_refs(key);
 }
 
+/**
+ * futex_top_waiter() - Return the highest priority waiter on a futex
+ * @hb:     the hash bucket the futex_q's reside in
+ * @key:    the futex key (to distinguish it from other futex futex_q's)
+ *
+ * Must be called with the hb lock held.
+ */
+static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
+					union futex_key *key)
+{
+	struct futex_q *this;
+
+	plist_for_each_entry(this, &hb->chain, list) {
+		if (match_futex(&this->key, key))
+			return this;
+	}
+	return NULL;
+}
+
 static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
 {
 	u32 curval;
@@ -539,28 +564,160 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	return 0;
 }
 
+/**
+ * futex_lock_pi_atomic() - atomic work required to acquire a pi aware futex
+ * @uaddr:		the pi futex user address
+ * @hb:			the pi futex hash bucket
+ * @key:		the futex key associated with uaddr and hb
+ * @ps:			the pi_state pointer where we store the result of the
+ *			lookup
+ * @task:		the task to perform the atomic lock work for.  This will
+ *			be "current" except in the case of requeue pi.
+ * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Returns:
+ *  0 - ready to wait
+ *  1 - acquired the lock
+ * <0 - error
+ *
+ * The hb->lock and futex_key refs shall be held by the caller.
+ */
+static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
+				union futex_key *key,
+				struct futex_pi_state **ps,
+				struct task_struct *task, int set_waiters)
+{
+	int lock_taken, ret, ownerdied = 0;
+	u32 uval, newval, curval;
+
+retry:
+	ret = lock_taken = 0;
+
+	/*
+	 * To avoid races, we attempt to take the lock here again
+	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
+	 * the locks. It will most likely not succeed.
+	 */
+	newval = task_pid_vnr(task);
+	if (set_waiters)
+		newval |= FUTEX_WAITERS;
+
+	curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
+
+	if (unlikely(curval == -EFAULT))
+		return -EFAULT;
+
+	/*
+	 * Detect deadlocks.
+	 */
+	if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+		return -EDEADLK;
+
+	/*
+	 * Surprise - we got the lock. Just return to userspace:
+	 */
+	if (unlikely(!curval))
+		return 1;
+
+	uval = curval;
+
+	/*
+	 * Set the FUTEX_WAITERS flag, so the owner will know it has someone
+	 * to wake at the next unlock.
+	 */
+	newval = curval | FUTEX_WAITERS;
+
+	/*
+	 * There are two cases, where a futex might have no owner (the
+	 * owner TID is 0): OWNER_DIED. We take over the futex in this
+	 * case. We also do an unconditional take over, when the owner
+	 * of the futex died.
+	 *
+	 * This is safe as we are protected by the hash bucket lock !
+	 */
+	if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
+		/* Keep the OWNER_DIED bit */
+		newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+		ownerdied = 0;
+		lock_taken = 1;
+	}
+
+	curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
+
+	if (unlikely(curval == -EFAULT))
+		return -EFAULT;
+	if (unlikely(curval != uval))
+		goto retry;
+
+	/*
+	 * We took the lock due to owner died take over.
+	 */
+	if (unlikely(lock_taken))
+		return 1;
+
+	/*
+	 * We dont have the lock. Look up the PI state (or create it if
+	 * we are the first waiter):
+	 */
+	ret = lookup_pi_state(uval, hb, key, ps);
+
+	if (unlikely(ret)) {
+		switch (ret) {
+		case -ESRCH:
+			/*
+			 * No owner found for this futex. Check if the
+			 * OWNER_DIED bit is set to figure out whether
+			 * this is a robust futex or not.
+			 */
+			if (get_futex_value_locked(&curval, uaddr))
+				return -EFAULT;
+
+			/*
+			 * We simply start over in case of a robust
+			 * futex. The code above will take the futex
+			 * and return happy.
+			 */
+			if (curval & FUTEX_OWNER_DIED) {
+				ownerdied = 1;
+				goto retry;
+			}
+		default:
+			break;
+		}
+	}
+
+	return ret;
+}
+
 /*
  * The hash bucket lock must be held when this is called.
  * Afterwards, the futex_q must not be accessed.
  */
 static void wake_futex(struct futex_q *q)
 {
+	struct task_struct *p = q->task;
+
+	/*
+	 * We set q->lock_ptr = NULL _before_ we wake up the task. If
+	 * a non futex wake up happens on another CPU then the task
+	 * might exit and p would dereference a non existing task
+	 * struct. Prevent this by holding a reference on p across the
+	 * wake up.
+	 */
+	get_task_struct(p);
+
 	plist_del(&q->list, &q->list.plist);
 	/*
-	 * The lock in wake_up_all() is a crucial memory barrier after the
-	 * plist_del() and also before assigning to q->lock_ptr.
-	 */
-	wake_up(&q->waiter);
-	/*
-	 * The waiting task can free the futex_q as soon as this is written,
-	 * without taking any locks.  This must come last.
-	 *
-	 * A memory barrier is required here to prevent the following store to
-	 * lock_ptr from getting ahead of the wakeup. Clearing the lock at the
-	 * end of wake_up() does not prevent this store from moving.
+	 * The waiting task can free the futex_q as soon as
+	 * q->lock_ptr = NULL is written, without taking any locks. A
+	 * memory barrier is required here to prevent the following
+	 * store to lock_ptr from getting ahead of the plist_del.
 	 */
 	smp_wmb();
 	q->lock_ptr = NULL;
+
+	wake_up_state(p, TASK_NORMAL);
+	put_task_struct(p);
 }
 
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
@@ -689,7 +846,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 
 	plist_for_each_entry_safe(this, next, head, list) {
 		if (match_futex (&this->key, &key)) {
-			if (this->pi_state) {
+			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
 				break;
 			}
@@ -802,24 +959,185 @@ out:
 	return ret;
 }
 
-/*
- * Requeue all waiters hashed on one physical page to another
- * physical page.
+/**
+ * requeue_futex() - Requeue a futex_q from one hb to another
+ * @q:		the futex_q to requeue
+ * @hb1:	the source hash_bucket
+ * @hb2:	the target hash_bucket
+ * @key2:	the new key for the requeued futex_q
+ */
+static inline
+void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
+		   struct futex_hash_bucket *hb2, union futex_key *key2)
+{
+
+	/*
+	 * If key1 and key2 hash to the same bucket, no need to
+	 * requeue.
+	 */
+	if (likely(&hb1->chain != &hb2->chain)) {
+		plist_del(&q->list, &hb1->chain);
+		plist_add(&q->list, &hb2->chain);
+		q->lock_ptr = &hb2->lock;
+#ifdef CONFIG_DEBUG_PI_LIST
+		q->list.plist.lock = &hb2->lock;
+#endif
+	}
+	get_futex_key_refs(key2);
+	q->key = *key2;
+}
+
+/**
+ * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
+ * q:	the futex_q
+ * key:	the key of the requeue target futex
+ *
+ * During futex_requeue, with requeue_pi=1, it is possible to acquire the
+ * target futex if it is uncontended or via a lock steal.  Set the futex_q key
+ * to the requeue target futex so the waiter can detect the wakeup on the right
+ * futex, but remove it from the hb and NULL the rt_waiter so it can detect
+ * atomic lock acquisition.  Must be called with the q->lock_ptr held.
+ */
+static inline
+void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key)
+{
+	drop_futex_key_refs(&q->key);
+	get_futex_key_refs(key);
+	q->key = *key;
+
+	WARN_ON(plist_node_empty(&q->list));
+	plist_del(&q->list, &q->list.plist);
+
+	WARN_ON(!q->rt_waiter);
+	q->rt_waiter = NULL;
+
+	wake_up_state(q->task, TASK_NORMAL);
+}
+
+/**
+ * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter
+ * @pifutex:		the user address of the to futex
+ * @hb1:		the from futex hash bucket, must be locked by the caller
+ * @hb2:		the to futex hash bucket, must be locked by the caller
+ * @key1:		the from futex key
+ * @key2:		the to futex key
+ * @ps:			address to store the pi_state pointer
+ * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Try and get the lock on behalf of the top waiter if we can do it atomically.
+ * Wake the top waiter if we succeed.  If the caller specified set_waiters,
+ * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
+ * hb1 and hb2 must be held by the caller.
+ *
+ * Returns:
+ *  0 - failed to acquire the lock atomicly
+ *  1 - acquired the lock
+ * <0 - error
+ */
+static int futex_proxy_trylock_atomic(u32 __user *pifutex,
+				 struct futex_hash_bucket *hb1,
+				 struct futex_hash_bucket *hb2,
+				 union futex_key *key1, union futex_key *key2,
+				 struct futex_pi_state **ps, int set_waiters)
+{
+	struct futex_q *top_waiter = NULL;
+	u32 curval;
+	int ret;
+
+	if (get_futex_value_locked(&curval, pifutex))
+		return -EFAULT;
+
+	/*
+	 * Find the top_waiter and determine if there are additional waiters.
+	 * If the caller intends to requeue more than 1 waiter to pifutex,
+	 * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now,
+	 * as we have means to handle the possible fault.  If not, don't set
+	 * the bit unecessarily as it will force the subsequent unlock to enter
+	 * the kernel.
+	 */
+	top_waiter = futex_top_waiter(hb1, key1);
+
+	/* There are no waiters, nothing for us to do. */
+	if (!top_waiter)
+		return 0;
+
+	/*
+	 * Try to take the lock for top_waiter.  Set the FUTEX_WAITERS bit in
+	 * the contended case or if set_waiters is 1.  The pi_state is returned
+	 * in ps in contended cases.
+	 */
+	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
+				   set_waiters);
+	if (ret == 1)
+		requeue_pi_wake_futex(top_waiter, key2);
+
+	return ret;
+}
+
+/**
+ * futex_requeue() - Requeue waiters from uaddr1 to uaddr2
+ * uaddr1:	source futex user address
+ * uaddr2:	target futex user address
+ * nr_wake:	number of waiters to wake (must be 1 for requeue_pi)
+ * nr_requeue:	number of waiters to requeue (0-INT_MAX)
+ * requeue_pi:	if we are attempting to requeue from a non-pi futex to a
+ * 		pi futex (pi to pi requeue is not supported)
+ *
+ * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
+ * uaddr2 atomically on behalf of the top waiter.
+ *
+ * Returns:
+ * >=0 - on success, the number of tasks requeued or woken
+ *  <0 - on error
  */
 static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
-			 int nr_wake, int nr_requeue, u32 *cmpval)
+			 int nr_wake, int nr_requeue, u32 *cmpval,
+			 int requeue_pi)
 {
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
+	int drop_count = 0, task_count = 0, ret;
+	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head1;
 	struct futex_q *this, *next;
-	int ret, drop_count = 0;
+	u32 curval2;
+
+	if (requeue_pi) {
+		/*
+		 * requeue_pi requires a pi_state, try to allocate it now
+		 * without any locks in case it fails.
+		 */
+		if (refill_pi_state_cache())
+			return -ENOMEM;
+		/*
+		 * requeue_pi must wake as many tasks as it can, up to nr_wake
+		 * + nr_requeue, since it acquires the rt_mutex prior to
+		 * returning to userspace, so as to not leave the rt_mutex with
+		 * waiters and no owner.  However, second and third wake-ups
+		 * cannot be predicted as they involve race conditions with the
+		 * first wake and a fault while looking up the pi_state.  Both
+		 * pthread_cond_signal() and pthread_cond_broadcast() should
+		 * use nr_wake=1.
+		 */
+		if (nr_wake != 1)
+			return -EINVAL;
+	}
 
 retry:
+	if (pi_state != NULL) {
+		/*
+		 * We will have to lookup the pi_state again, so free this one
+		 * to keep the accounting correct.
+		 */
+		free_pi_state(pi_state);
+		pi_state = NULL;
+	}
+
 	ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_READ);
+	ret = get_futex_key(uaddr2, fshared, &key2,
+			    requeue_pi ? VERIFY_WRITE : VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -854,32 +1172,99 @@ retry_private:
 		}
 	}
 
+	if (requeue_pi && (task_count - nr_wake < nr_requeue)) {
+		/*
+		 * Attempt to acquire uaddr2 and wake the top waiter. If we
+		 * intend to requeue waiters, force setting the FUTEX_WAITERS
+		 * bit.  We force this here where we are able to easily handle
+		 * faults rather in the requeue loop below.
+		 */
+		ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
+						 &key2, &pi_state, nr_requeue);
+
+		/*
+		 * At this point the top_waiter has either taken uaddr2 or is
+		 * waiting on it.  If the former, then the pi_state will not
+		 * exist yet, look it up one more time to ensure we have a
+		 * reference to it.
+		 */
+		if (ret == 1) {
+			WARN_ON(pi_state);
+			task_count++;
+			ret = get_futex_value_locked(&curval2, uaddr2);
+			if (!ret)
+				ret = lookup_pi_state(curval2, hb2, &key2,
+						      &pi_state);
+		}
+
+		switch (ret) {
+		case 0:
+			break;
+		case -EFAULT:
+			double_unlock_hb(hb1, hb2);
+			put_futex_key(fshared, &key2);
+			put_futex_key(fshared, &key1);
+			ret = get_user(curval2, uaddr2);
+			if (!ret)
+				goto retry;
+			goto out;
+		case -EAGAIN:
+			/* The owner was exiting, try again. */
+			double_unlock_hb(hb1, hb2);
+			put_futex_key(fshared, &key2);
+			put_futex_key(fshared, &key1);
+			cond_resched();
+			goto retry;
+		default:
+			goto out_unlock;
+		}
+	}
+
 	head1 = &hb1->chain;
 	plist_for_each_entry_safe(this, next, head1, list) {
-		if (!match_futex (&this->key, &key1))
-			continue;
-		if (++ret <= nr_wake) {
-			wake_futex(this);
-		} else {
-			/*
-			 * If key1 and key2 hash to the same bucket, no need to
-			 * requeue.
-			 */
-			if (likely(head1 != &hb2->chain)) {
-				plist_del(&this->list, &hb1->chain);
-				plist_add(&this->list, &hb2->chain);
-				this->lock_ptr = &hb2->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
-				this->list.plist.lock = &hb2->lock;
-#endif
-			}
-			this->key = key2;
-			get_futex_key_refs(&key2);
-			drop_count++;
+		if (task_count - nr_wake >= nr_requeue)
+			break;
 
-			if (ret - nr_wake >= nr_requeue)
-				break;
+		if (!match_futex(&this->key, &key1))
+			continue;
+
+		WARN_ON(!requeue_pi && this->rt_waiter);
+		WARN_ON(requeue_pi && !this->rt_waiter);
+
+		/*
+		 * Wake nr_wake waiters.  For requeue_pi, if we acquired the
+		 * lock, we already woke the top_waiter.  If not, it will be
+		 * woken by futex_unlock_pi().
+		 */
+		if (++task_count <= nr_wake && !requeue_pi) {
+			wake_futex(this);
+			continue;
 		}
+
+		/*
+		 * Requeue nr_requeue waiters and possibly one more in the case
+		 * of requeue_pi if we couldn't acquire the lock atomically.
+		 */
+		if (requeue_pi) {
+			/* Prepare the waiter to take the rt_mutex. */
+			atomic_inc(&pi_state->refcount);
+			this->pi_state = pi_state;
+			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
+							this->rt_waiter,
+							this->task, 1);
+			if (ret == 1) {
+				/* We got the lock. */
+				requeue_pi_wake_futex(this, &key2);
+				continue;
+			} else if (ret) {
+				/* -EDEADLK */
+				this->pi_state = NULL;
+				free_pi_state(pi_state);
+				goto out_unlock;
+			}
+		}
+		requeue_futex(this, hb1, hb2, &key2);
+		drop_count++;
 	}
 
 out_unlock:
@@ -899,7 +1284,9 @@ out_put_keys:
 out_put_key1:
 	put_futex_key(fshared, &key1);
 out:
-	return ret;
+	if (pi_state != NULL)
+		free_pi_state(pi_state);
+	return ret ? ret : task_count;
 }
 
 /* The key must be already stored in q->key. */
@@ -907,8 +1294,6 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 {
 	struct futex_hash_bucket *hb;
 
-	init_waitqueue_head(&q->waiter);
-
 	get_futex_key_refs(&q->key);
 	hb = hash_futex(&q->key);
 	q->lock_ptr = &hb->lock;
@@ -1119,35 +1504,149 @@ handle_fault:
  */
 #define FLAGS_SHARED		0x01
 #define FLAGS_CLOCKRT		0x02
+#define FLAGS_HAS_TIMEOUT	0x04
 
 static long futex_wait_restart(struct restart_block *restart);
 
-static int futex_wait(u32 __user *uaddr, int fshared,
-		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
+/**
+ * fixup_owner() - Post lock pi_state and corner case management
+ * @uaddr:	user address of the futex
+ * @fshared:	whether the futex is shared (1) or not (0)
+ * @q:		futex_q (contains pi_state and access to the rt_mutex)
+ * @locked:	if the attempt to take the rt_mutex succeeded (1) or not (0)
+ *
+ * After attempting to lock an rt_mutex, this function is called to cleanup
+ * the pi_state owner as well as handle race conditions that may allow us to
+ * acquire the lock. Must be called with the hb lock held.
+ *
+ * Returns:
+ *  1 - success, lock taken
+ *  0 - success, lock not taken
+ * <0 - on error (-EFAULT)
+ */
+static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
+		       int locked)
+{
+	struct task_struct *owner;
+	int ret = 0;
+
+	if (locked) {
+		/*
+		 * Got the lock. We might not be the anticipated owner if we
+		 * did a lock-steal - fix up the PI-state in that case:
+		 */
+		if (q->pi_state->owner != current)
+			ret = fixup_pi_state_owner(uaddr, q, current, fshared);
+		goto out;
+	}
+
+	/*
+	 * Catch the rare case, where the lock was released when we were on the
+	 * way back before we locked the hash bucket.
+	 */
+	if (q->pi_state->owner == current) {
+		/*
+		 * Try to get the rt_mutex now. This might fail as some other
+		 * task acquired the rt_mutex after we removed ourself from the
+		 * rt_mutex waiters list.
+		 */
+		if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
+			locked = 1;
+			goto out;
+		}
+
+		/*
+		 * pi_state is incorrect, some other task did a lock steal and
+		 * we returned due to timeout or signal without taking the
+		 * rt_mutex. Too late. We can access the rt_mutex_owner without
+		 * locking, as the other task is now blocked on the hash bucket
+		 * lock. Fix the state up.
+		 */
+		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
+		ret = fixup_pi_state_owner(uaddr, q, owner, fshared);
+		goto out;
+	}
+
+	/*
+	 * Paranoia check. If we did not take the lock, then we should not be
+	 * the owner, nor the pending owner, of the rt_mutex.
+	 */
+	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
+				"pi-state %p\n", ret,
+				q->pi_state->pi_mutex.owner,
+				q->pi_state->owner);
+
+out:
+	return ret ? ret : locked;
+}
+
+/**
+ * futex_wait_queue_me() - queue_me() and wait for wakeup, timeout, or signal
+ * @hb:		the futex hash bucket, must be locked by the caller
+ * @q:		the futex_q to queue up on
+ * @timeout:	the prepared hrtimer_sleeper, or null for no timeout
+ */
+static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
+				struct hrtimer_sleeper *timeout)
+{
+	queue_me(q, hb);
+
+	/*
+	 * There might have been scheduling since the queue_me(), as we
+	 * cannot hold a spinlock across the get_user() in case it
+	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
+	 * queueing ourselves into the futex hash. This code thus has to
+	 * rely on the futex_wake() code removing us from hash when it
+	 * wakes us up.
+	 */
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	/* Arm the timer */
+	if (timeout) {
+		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
+		if (!hrtimer_active(&timeout->timer))
+			timeout->task = NULL;
+	}
+
+	/*
+	 * !plist_node_empty() is safe here without any lock.
+	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
+	 */
+	if (likely(!plist_node_empty(&q->list))) {
+		/*
+		 * If the timer has already expired, current will already be
+		 * flagged for rescheduling. Only call schedule if there
+		 * is no timeout, or if it has yet to expire.
+		 */
+		if (!timeout || timeout->task)
+			schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
+/**
+ * futex_wait_setup() - Prepare to wait on a futex
+ * @uaddr:	the futex userspace address
+ * @val:	the expected value
+ * @fshared:	whether the futex is shared (1) or not (0)
+ * @q:		the associated futex_q
+ * @hb:		storage for hash_bucket pointer to be returned to caller
+ *
+ * Setup the futex_q and locate the hash_bucket.  Get the futex value and
+ * compare it with the expected value.  Handle atomic faults internally.
+ * Return with the hb lock held and a q.key reference on success, and unlocked
+ * with no q.key reference on failure.
+ *
+ * Returns:
+ *  0 - uaddr contains val and hb has been locked
+ * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlcoked
+ */
+static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared,
+			   struct futex_q *q, struct futex_hash_bucket **hb)
 {
-	struct task_struct *curr = current;
-	struct restart_block *restart;
-	DECLARE_WAITQUEUE(wait, curr);
-	struct futex_hash_bucket *hb;
-	struct futex_q q;
 	u32 uval;
 	int ret;
-	struct hrtimer_sleeper t;
-	int rem = 0;
-
-	if (!bitset)
-		return -EINVAL;
-
-	q.pi_state = NULL;
-	q.bitset = bitset;
-retry:
-	q.key = FUTEX_KEY_INIT;
-	ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_READ);
-	if (unlikely(ret != 0))
-		goto out;
-
-retry_private:
-	hb = queue_lock(&q);
 
 	/*
 	 * Access the page AFTER the hash-bucket is locked.
@@ -1165,95 +1664,83 @@ retry_private:
 	 * A consequence is that futex_wait() can return zero and absorb
 	 * a wakeup when *uaddr != val on entry to the syscall.  This is
 	 * rare, but normal.
-	 *
-	 * For shared futexes, we hold the mmap semaphore, so the mapping
-	 * cannot have changed since we looked it up in get_futex_key.
 	 */
+retry:
+	q->key = FUTEX_KEY_INIT;
+	ret = get_futex_key(uaddr, fshared, &q->key, VERIFY_READ);
+	if (unlikely(ret != 0))
+		return ret;
+
+retry_private:
+	*hb = queue_lock(q);
+
 	ret = get_futex_value_locked(&uval, uaddr);
 
-	if (unlikely(ret)) {
-		queue_unlock(&q, hb);
+	if (ret) {
+		queue_unlock(q, *hb);
 
 		ret = get_user(uval, uaddr);
 		if (ret)
-			goto out_put_key;
+			goto out;
 
 		if (!fshared)
 			goto retry_private;
 
-		put_futex_key(fshared, &q.key);
+		put_futex_key(fshared, &q->key);
 		goto retry;
 	}
-	ret = -EWOULDBLOCK;
-	if (unlikely(uval != val)) {
-		queue_unlock(&q, hb);
-		goto out_put_key;
+
+	if (uval != val) {
+		queue_unlock(q, *hb);
+		ret = -EWOULDBLOCK;
 	}
 
-	/* Only actually queue if *uaddr contained val.  */
-	queue_me(&q, hb);
+out:
+	if (ret)
+		put_futex_key(fshared, &q->key);
+	return ret;
+}
 
-	/*
-	 * There might have been scheduling since the queue_me(), as we
-	 * cannot hold a spinlock across the get_user() in case it
-	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
-	 * queueing ourselves into the futex hash.  This code thus has to
-	 * rely on the futex_wake() code removing us from hash when it
-	 * wakes us up.
-	 */
+static int futex_wait(u32 __user *uaddr, int fshared,
+		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
+{
+	struct hrtimer_sleeper timeout, *to = NULL;
+	struct restart_block *restart;
+	struct futex_hash_bucket *hb;
+	struct futex_q q;
+	int ret;
 
-	/* add_wait_queue is the barrier after __set_current_state. */
-	__set_current_state(TASK_INTERRUPTIBLE);
-	add_wait_queue(&q.waiter, &wait);
-	/*
-	 * !plist_node_empty() is safe here without any lock.
-	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
-	 */
-	if (likely(!plist_node_empty(&q.list))) {
-		if (!abs_time)
-			schedule();
-		else {
-			hrtimer_init_on_stack(&t.timer,
-					      clockrt ? CLOCK_REALTIME :
-					      CLOCK_MONOTONIC,
-					      HRTIMER_MODE_ABS);
-			hrtimer_init_sleeper(&t, current);
-			hrtimer_set_expires_range_ns(&t.timer, *abs_time,
-						     current->timer_slack_ns);
+	if (!bitset)
+		return -EINVAL;
 
-			hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
-			if (!hrtimer_active(&t.timer))
-				t.task = NULL;
+	q.pi_state = NULL;
+	q.bitset = bitset;
+	q.rt_waiter = NULL;
 
-			/*
-			 * the timer could have already expired, in which
-			 * case current would be flagged for rescheduling.
-			 * Don't bother calling schedule.
-			 */
-			if (likely(t.task))
-				schedule();
+	if (abs_time) {
+		to = &timeout;
 
-			hrtimer_cancel(&t.timer);
-
-			/* Flag if a timeout occured */
-			rem = (t.task == NULL);
-
-			destroy_hrtimer_on_stack(&t.timer);
-		}
+		hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
+				      CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+		hrtimer_init_sleeper(to, current);
+		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
+					     current->timer_slack_ns);
 	}
-	__set_current_state(TASK_RUNNING);
 
-	/*
-	 * NOTE: we don't remove ourselves from the waitqueue because
-	 * we are the only user of it.
-	 */
+	/* Prepare to wait on uaddr. */
+	ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+	if (ret)
+		goto out;
+
+	/* queue_me and wait for wakeup, timeout, or a signal. */
+	futex_wait_queue_me(hb, &q, to);
 
 	/* If we were woken (and unqueued), we succeeded, whatever. */
 	ret = 0;
 	if (!unqueue_me(&q))
 		goto out_put_key;
 	ret = -ETIMEDOUT;
-	if (rem)
+	if (to && !to->task)
 		goto out_put_key;
 
 	/*
@@ -1270,7 +1757,7 @@ retry_private:
 	restart->futex.val = val;
 	restart->futex.time = abs_time->tv64;
 	restart->futex.bitset = bitset;
-	restart->futex.flags = 0;
+	restart->futex.flags = FLAGS_HAS_TIMEOUT;
 
 	if (fshared)
 		restart->futex.flags |= FLAGS_SHARED;
@@ -1282,6 +1769,10 @@ retry_private:
 out_put_key:
 	put_futex_key(fshared, &q.key);
 out:
+	if (to) {
+		hrtimer_cancel(&to->timer);
+		destroy_hrtimer_on_stack(&to->timer);
+	}
 	return ret;
 }
 
@@ -1290,13 +1781,16 @@ static long futex_wait_restart(struct restart_block *restart)
 {
 	u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
 	int fshared = 0;
-	ktime_t t;
+	ktime_t t, *tp = NULL;
 
-	t.tv64 = restart->futex.time;
+	if (restart->futex.flags & FLAGS_HAS_TIMEOUT) {
+		t.tv64 = restart->futex.time;
+		tp = &t;
+	}
 	restart->fn = do_no_restart_syscall;
 	if (restart->futex.flags & FLAGS_SHARED)
 		fshared = 1;
-	return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
+	return (long)futex_wait(uaddr, fshared, restart->futex.val, tp,
 				restart->futex.bitset,
 				restart->futex.flags & FLAGS_CLOCKRT);
 }
@@ -1312,11 +1806,10 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 			 int detect, ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
-	struct task_struct *curr = current;
 	struct futex_hash_bucket *hb;
-	u32 uval, newval, curval;
+	u32 uval;
 	struct futex_q q;
-	int ret, lock_taken, ownerdied = 0;
+	int res, ret;
 
 	if (refill_pi_state_cache())
 		return -ENOMEM;
@@ -1330,6 +1823,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 	}
 
 	q.pi_state = NULL;
+	q.rt_waiter = NULL;
 retry:
 	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE);
@@ -1339,81 +1833,15 @@ retry:
 retry_private:
 	hb = queue_lock(&q);
 
-retry_locked:
-	ret = lock_taken = 0;
-
-	/*
-	 * To avoid races, we attempt to take the lock here again
-	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
-	 * the locks. It will most likely not succeed.
-	 */
-	newval = task_pid_vnr(current);
-
-	curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
-
-	if (unlikely(curval == -EFAULT))
-		goto uaddr_faulted;
-
-	/*
-	 * Detect deadlocks. In case of REQUEUE_PI this is a valid
-	 * situation and we return success to user space.
-	 */
-	if (unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(current))) {
-		ret = -EDEADLK;
-		goto out_unlock_put_key;
-	}
-
-	/*
-	 * Surprise - we got the lock. Just return to userspace:
-	 */
-	if (unlikely(!curval))
-		goto out_unlock_put_key;
-
-	uval = curval;
-
-	/*
-	 * Set the WAITERS flag, so the owner will know it has someone
-	 * to wake at next unlock
-	 */
-	newval = curval | FUTEX_WAITERS;
-
-	/*
-	 * There are two cases, where a futex might have no owner (the
-	 * owner TID is 0): OWNER_DIED. We take over the futex in this
-	 * case. We also do an unconditional take over, when the owner
-	 * of the futex died.
-	 *
-	 * This is safe as we are protected by the hash bucket lock !
-	 */
-	if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
-		/* Keep the OWNER_DIED bit */
-		newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(current);
-		ownerdied = 0;
-		lock_taken = 1;
-	}
-
-	curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
-
-	if (unlikely(curval == -EFAULT))
-		goto uaddr_faulted;
-	if (unlikely(curval != uval))
-		goto retry_locked;
-
-	/*
-	 * We took the lock due to owner died take over.
-	 */
-	if (unlikely(lock_taken))
-		goto out_unlock_put_key;
-
-	/*
-	 * We dont have the lock. Look up the PI state (or create it if
-	 * we are the first waiter):
-	 */
-	ret = lookup_pi_state(uval, hb, &q.key, &q.pi_state);
-
+	ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0);
 	if (unlikely(ret)) {
 		switch (ret) {
-
+		case 1:
+			/* We got the lock. */
+			ret = 0;
+			goto out_unlock_put_key;
+		case -EFAULT:
+			goto uaddr_faulted;
 		case -EAGAIN:
 			/*
 			 * Task is exiting and we just wait for the
@@ -1423,25 +1851,6 @@ retry_locked:
 			put_futex_key(fshared, &q.key);
 			cond_resched();
 			goto retry;
-
-		case -ESRCH:
-			/*
-			 * No owner found for this futex. Check if the
-			 * OWNER_DIED bit is set to figure out whether
-			 * this is a robust futex or not.
-			 */
-			if (get_futex_value_locked(&curval, uaddr))
-				goto uaddr_faulted;
-
-			/*
-			 * We simply start over in case of a robust
-			 * futex. The code above will take the futex
-			 * and return happy.
-			 */
-			if (curval & FUTEX_OWNER_DIED) {
-				ownerdied = 1;
-				goto retry_locked;
-			}
 		default:
 			goto out_unlock_put_key;
 		}
@@ -1465,71 +1874,21 @@ retry_locked:
 	}
 
 	spin_lock(q.lock_ptr);
-
-	if (!ret) {
-		/*
-		 * Got the lock. We might not be the anticipated owner
-		 * if we did a lock-steal - fix up the PI-state in
-		 * that case:
-		 */
-		if (q.pi_state->owner != curr)
-			ret = fixup_pi_state_owner(uaddr, &q, curr, fshared);
-	} else {
-		/*
-		 * Catch the rare case, where the lock was released
-		 * when we were on the way back before we locked the
-		 * hash bucket.
-		 */
-		if (q.pi_state->owner == curr) {
-			/*
-			 * Try to get the rt_mutex now. This might
-			 * fail as some other task acquired the
-			 * rt_mutex after we removed ourself from the
-			 * rt_mutex waiters list.
-			 */
-			if (rt_mutex_trylock(&q.pi_state->pi_mutex))
-				ret = 0;
-			else {
-				/*
-				 * pi_state is incorrect, some other
-				 * task did a lock steal and we
-				 * returned due to timeout or signal
-				 * without taking the rt_mutex. Too
-				 * late. We can access the
-				 * rt_mutex_owner without locking, as
-				 * the other task is now blocked on
-				 * the hash bucket lock. Fix the state
-				 * up.
-				 */
-				struct task_struct *owner;
-				int res;
-
-				owner = rt_mutex_owner(&q.pi_state->pi_mutex);
-				res = fixup_pi_state_owner(uaddr, &q, owner,
-							   fshared);
-
-				/* propagate -EFAULT, if the fixup failed */
-				if (res)
-					ret = res;
-			}
-		} else {
-			/*
-			 * Paranoia check. If we did not take the lock
-			 * in the trylock above, then we should not be
-			 * the owner of the rtmutex, neither the real
-			 * nor the pending one:
-			 */
-			if (rt_mutex_owner(&q.pi_state->pi_mutex) == curr)
-				printk(KERN_ERR "futex_lock_pi: ret = %d "
-				       "pi-mutex: %p pi-state %p\n", ret,
-				       q.pi_state->pi_mutex.owner,
-				       q.pi_state->owner);
-		}
-	}
+	/*
+	 * Fixup the pi_state owner and possibly acquire the lock if we
+	 * haven't already.
+	 */
+	res = fixup_owner(uaddr, fshared, &q, !ret);
+	/*
+	 * If fixup_owner() returned an error, proprogate that.  If it acquired
+	 * the lock, clear our -ETIMEDOUT or -EINTR.
+	 */
+	if (res)
+		ret = (res < 0) ? res : 0;
 
 	/*
-	 * If fixup_pi_state_owner() faulted and was unable to handle the
-	 * fault, unlock it and return the fault to userspace.
+	 * If fixup_owner() faulted and was unable to handle the fault, unlock
+	 * it and return the fault to userspace.
 	 */
 	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
 		rt_mutex_unlock(&q.pi_state->pi_mutex);
@@ -1537,9 +1896,7 @@ retry_locked:
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
 
-	if (to)
-		destroy_hrtimer_on_stack(&to->timer);
-	return ret != -EINTR ? ret : -ERESTARTNOINTR;
+	goto out;
 
 out_unlock_put_key:
 	queue_unlock(&q, hb);
@@ -1549,7 +1906,7 @@ out_put_key:
 out:
 	if (to)
 		destroy_hrtimer_on_stack(&to->timer);
-	return ret;
+	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:
 	/*
@@ -1572,7 +1929,6 @@ uaddr_faulted:
 	goto retry;
 }
 
-
 /*
  * Userspace attempted a TID -> 0 atomic transition, and failed.
  * This is the in-kernel slowpath: we look up the PI state (if any),
@@ -1674,6 +2030,229 @@ pi_faulted:
 	return ret;
 }
 
+/**
+ * handle_early_requeue_pi_wakeup() - Detect early wakeup on the initial futex
+ * @hb:		the hash_bucket futex_q was original enqueued on
+ * @q:		the futex_q woken while waiting to be requeued
+ * @key2:	the futex_key of the requeue target futex
+ * @timeout:	the timeout associated with the wait (NULL if none)
+ *
+ * Detect if the task was woken on the initial futex as opposed to the requeue
+ * target futex.  If so, determine if it was a timeout or a signal that caused
+ * the wakeup and return the appropriate error code to the caller.  Must be
+ * called with the hb lock held.
+ *
+ * Returns
+ *  0 - no early wakeup detected
+ * <0 - -ETIMEDOUT or -ERESTARTNOINTR
+ */
+static inline
+int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
+				   struct futex_q *q, union futex_key *key2,
+				   struct hrtimer_sleeper *timeout)
+{
+	int ret = 0;
+
+	/*
+	 * With the hb lock held, we avoid races while we process the wakeup.
+	 * We only need to hold hb (and not hb2) to ensure atomicity as the
+	 * wakeup code can't change q.key from uaddr to uaddr2 if we hold hb.
+	 * It can't be requeued from uaddr2 to something else since we don't
+	 * support a PI aware source futex for requeue.
+	 */
+	if (!match_futex(&q->key, key2)) {
+		WARN_ON(q->lock_ptr && (&hb->lock != q->lock_ptr));
+		/*
+		 * We were woken prior to requeue by a timeout or a signal.
+		 * Unqueue the futex_q and determine which it was.
+		 */
+		plist_del(&q->list, &q->list.plist);
+		drop_futex_key_refs(&q->key);
+
+		if (timeout && !timeout->task)
+			ret = -ETIMEDOUT;
+		else
+			ret = -ERESTARTNOINTR;
+	}
+	return ret;
+}
+
+/**
+ * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
+ * @uaddr:	the futex we initialyl wait on (non-pi)
+ * @fshared:	whether the futexes are shared (1) or not (0).  They must be
+ * 		the same type, no requeueing from private to shared, etc.
+ * @val:	the expected value of uaddr
+ * @abs_time:	absolute timeout
+ * @bitset:	32 bit wakeup bitset set by userspace, defaults to all.
+ * @clockrt:	whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0)
+ * @uaddr2:	the pi futex we will take prior to returning to user-space
+ *
+ * The caller will wait on uaddr and will be requeued by futex_requeue() to
+ * uaddr2 which must be PI aware.  Normal wakeup will wake on uaddr2 and
+ * complete the acquisition of the rt_mutex prior to returning to userspace.
+ * This ensures the rt_mutex maintains an owner when it has waiters; without
+ * one, the pi logic wouldn't know which task to boost/deboost, if there was a
+ * need to.
+ *
+ * We call schedule in futex_wait_queue_me() when we enqueue and return there
+ * via the following:
+ * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
+ * 2) wakeup on uaddr2 after a requeue and subsequent unlock
+ * 3) signal (before or after requeue)
+ * 4) timeout (before or after requeue)
+ *
+ * If 3, we setup a restart_block with futex_wait_requeue_pi() as the function.
+ *
+ * If 2, we may then block on trying to take the rt_mutex and return via:
+ * 5) successful lock
+ * 6) signal
+ * 7) timeout
+ * 8) other lock acquisition failure
+ *
+ * If 6, we setup a restart_block with futex_lock_pi() as the function.
+ *
+ * If 4 or 7, we cleanup and return with -ETIMEDOUT.
+ *
+ * Returns:
+ *  0 - On success
+ * <0 - On error
+ */
+static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
+				 u32 val, ktime_t *abs_time, u32 bitset,
+				 int clockrt, u32 __user *uaddr2)
+{
+	struct hrtimer_sleeper timeout, *to = NULL;
+	struct rt_mutex_waiter rt_waiter;
+	struct rt_mutex *pi_mutex = NULL;
+	struct futex_hash_bucket *hb;
+	union futex_key key2;
+	struct futex_q q;
+	int res, ret;
+
+	if (!bitset)
+		return -EINVAL;
+
+	if (abs_time) {
+		to = &timeout;
+		hrtimer_init_on_stack(&to->timer, clockrt ? CLOCK_REALTIME :
+				      CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+		hrtimer_init_sleeper(to, current);
+		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
+					     current->timer_slack_ns);
+	}
+
+	/*
+	 * The waiter is allocated on our stack, manipulated by the requeue
+	 * code while we sleep on uaddr.
+	 */
+	debug_rt_mutex_init_waiter(&rt_waiter);
+	rt_waiter.task = NULL;
+
+	q.pi_state = NULL;
+	q.bitset = bitset;
+	q.rt_waiter = &rt_waiter;
+
+	key2 = FUTEX_KEY_INIT;
+	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
+	if (unlikely(ret != 0))
+		goto out;
+
+	/* Prepare to wait on uaddr. */
+	ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
+	if (ret)
+		goto out_key2;
+
+	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
+	futex_wait_queue_me(hb, &q, to);
+
+	spin_lock(&hb->lock);
+	ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
+	spin_unlock(&hb->lock);
+	if (ret)
+		goto out_put_keys;
+
+	/*
+	 * In order for us to be here, we know our q.key == key2, and since
+	 * we took the hb->lock above, we also know that futex_requeue() has
+	 * completed and we no longer have to concern ourselves with a wakeup
+	 * race with the atomic proxy lock acquition by the requeue code.
+	 */
+
+	/* Check if the requeue code acquired the second futex for us. */
+	if (!q.rt_waiter) {
+		/*
+		 * Got the lock. We might not be the anticipated owner if we
+		 * did a lock-steal - fix up the PI-state in that case.
+		 */
+		if (q.pi_state && (q.pi_state->owner != current)) {
+			spin_lock(q.lock_ptr);
+			ret = fixup_pi_state_owner(uaddr2, &q, current,
+						   fshared);
+			spin_unlock(q.lock_ptr);
+		}
+	} else {
+		/*
+		 * We have been woken up by futex_unlock_pi(), a timeout, or a
+		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
+		 * the pi_state.
+		 */
+		WARN_ON(!&q.pi_state);
+		pi_mutex = &q.pi_state->pi_mutex;
+		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
+		debug_rt_mutex_free_waiter(&rt_waiter);
+
+		spin_lock(q.lock_ptr);
+		/*
+		 * Fixup the pi_state owner and possibly acquire the lock if we
+		 * haven't already.
+		 */
+		res = fixup_owner(uaddr2, fshared, &q, !ret);
+		/*
+		 * If fixup_owner() returned an error, proprogate that.  If it
+		 * acquired the lock, clear our -ETIMEDOUT or -EINTR.
+		 */
+		if (res)
+			ret = (res < 0) ? res : 0;
+
+		/* Unqueue and drop the lock. */
+		unqueue_me_pi(&q);
+	}
+
+	/*
+	 * If fixup_pi_state_owner() faulted and was unable to handle the
+	 * fault, unlock the rt_mutex and return the fault to userspace.
+	 */
+	if (ret == -EFAULT) {
+		if (rt_mutex_owner(pi_mutex) == current)
+			rt_mutex_unlock(pi_mutex);
+	} else if (ret == -EINTR) {
+		/*
+		 * We've already been requeued, but we have no way to
+		 * restart by calling futex_lock_pi() directly. We
+		 * could restart the syscall, but that will look at
+		 * the user space value and return right away. So we
+		 * drop back with EWOULDBLOCK to tell user space that
+		 * "val" has been changed. That's the same what the
+		 * restart of the syscall would do in
+		 * futex_wait_setup().
+		 */
+		ret = -EWOULDBLOCK;
+	}
+
+out_put_keys:
+	put_futex_key(fshared, &q.key);
+out_key2:
+	put_futex_key(fshared, &key2);
+
+out:
+	if (to) {
+		hrtimer_cancel(&to->timer);
+		destroy_hrtimer_on_stack(&to->timer);
+	}
+	return ret;
+}
+
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.
@@ -1896,7 +2475,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		fshared = 1;
 
 	clockrt = op & FUTEX_CLOCK_REALTIME;
-	if (clockrt && cmd != FUTEX_WAIT_BITSET)
+	if (clockrt && cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI)
 		return -ENOSYS;
 
 	switch (cmd) {
@@ -1911,10 +2490,11 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		ret = futex_wake(uaddr, fshared, val, val3);
 		break;
 	case FUTEX_REQUEUE:
-		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL);
+		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL, 0);
 		break;
 	case FUTEX_CMP_REQUEUE:
-		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3);
+		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
+				    0);
 		break;
 	case FUTEX_WAKE_OP:
 		ret = futex_wake_op(uaddr, fshared, uaddr2, val, val2, val3);
@@ -1931,6 +2511,15 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		if (futex_cmpxchg_enabled)
 			ret = futex_lock_pi(uaddr, fshared, 0, timeout, 1);
 		break;
+	case FUTEX_WAIT_REQUEUE_PI:
+		val3 = FUTEX_BITSET_MATCH_ANY;
+		ret = futex_wait_requeue_pi(uaddr, fshared, val, timeout, val3,
+					    clockrt, uaddr2);
+		break;
+	case FUTEX_CMP_REQUEUE_PI:
+		ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, &val3,
+				    1);
+		break;
 	default:
 		ret = -ENOSYS;
 	}
@@ -1948,7 +2537,8 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 	int cmd = op & FUTEX_CMD_MASK;
 
 	if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
-		      cmd == FUTEX_WAIT_BITSET)) {
+		      cmd == FUTEX_WAIT_BITSET ||
+		      cmd == FUTEX_WAIT_REQUEUE_PI)) {
 		if (copy_from_user(&ts, utime, sizeof(ts)) != 0)
 			return -EFAULT;
 		if (!timespec_valid(&ts))
@@ -1960,11 +2550,11 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 		tp = &t;
 	}
 	/*
-	 * requeue parameter in 'utime' if cmd == FUTEX_REQUEUE.
+	 * requeue parameter in 'utime' if cmd == FUTEX_*_REQUEUE_*.
 	 * number of waiters to wake in 'utime' if cmd == FUTEX_WAKE_OP.
 	 */
 	if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||
-	    cmd == FUTEX_WAKE_OP)
+	    cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP)
 		val2 = (u32) (unsigned long) utime;
 
 	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 3394f8f52964..7d047808419d 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -3,5 +3,5 @@ obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
-obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o
+obj-$(CONFIG_NUMA_IRQ_DESC) += numa_migrate.o
 obj-$(CONFIG_PM_SLEEP) += pm.o
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index c687ba4363f2..13c68e71b726 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -359,7 +359,6 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
 	spin_lock(&desc->lock);
 	mask_ack_irq(desc, irq);
-	desc = irq_remap_to_desc(irq, desc);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
@@ -438,7 +437,6 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	desc->status &= ~IRQ_INPROGRESS;
 out:
 	desc->chip->eoi(irq);
-	desc = irq_remap_to_desc(irq, desc);
 
 	spin_unlock(&desc->lock);
 }
@@ -475,7 +473,6 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		    !desc->action)) {
 		desc->status |= (IRQ_PENDING | IRQ_MASKED);
 		mask_ack_irq(desc, irq);
-		desc = irq_remap_to_desc(irq, desc);
 		goto out_unlock;
 	}
 	kstat_incr_irqs_this_cpu(irq, desc);
@@ -483,7 +480,6 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	/* Start handling the irq */
 	if (desc->chip->ack)
 		desc->chip->ack(irq);
-	desc = irq_remap_to_desc(irq, desc);
 
 	/* Mark the IRQ currently in progress.*/
 	desc->status |= IRQ_INPROGRESS;
@@ -544,10 +540,8 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 	if (!noirqdebug)
 		note_interrupt(irq, desc, action_ret);
 
-	if (desc->chip->eoi) {
+	if (desc->chip->eoi)
 		desc->chip->eoi(irq);
-		desc = irq_remap_to_desc(irq, desc);
-	}
 }
 
 void
@@ -582,10 +576,8 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 
 	/* Uninstall? */
 	if (handle == handle_bad_irq) {
-		if (desc->chip != &no_irq_chip) {
+		if (desc->chip != &no_irq_chip)
 			mask_ack_irq(desc, irq);
-			desc = irq_remap_to_desc(irq, desc);
-		}
 		desc->status |= IRQ_DISABLED;
 		desc->depth = 1;
 	}
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 26e08754744f..104578541230 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -11,14 +11,15 @@
  */
 
 #include <linux/irq.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
-#include <trace/irq.h>
 #include <linux/bootmem.h>
+#include <trace/events/irq.h>
 
 #include "internals.h"
 
@@ -81,45 +82,48 @@ static struct irq_desc irq_desc_init = {
 	.lock       = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
 };
 
-void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
+void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
 {
-	int node;
 	void *ptr;
 
-	node = cpu_to_node(cpu);
-	ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), GFP_ATOMIC, node);
+	if (slab_is_available())
+		ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
+				   GFP_ATOMIC, node);
+	else
+		ptr = alloc_bootmem_node(NODE_DATA(node),
+				nr * sizeof(*desc->kstat_irqs));
 
 	/*
 	 * don't overwite if can not get new one
 	 * init_copy_kstat_irqs() could still use old one
 	 */
 	if (ptr) {
-		printk(KERN_DEBUG "  alloc kstat_irqs on cpu %d node %d\n",
-			 cpu, node);
+		printk(KERN_DEBUG "  alloc kstat_irqs on node %d\n", node);
 		desc->kstat_irqs = ptr;
 	}
 }
 
-static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
+static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
 {
 	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
 
 	spin_lock_init(&desc->lock);
 	desc->irq = irq;
 #ifdef CONFIG_SMP
-	desc->cpu = cpu;
+	desc->node = node;
 #endif
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	init_kstat_irqs(desc, cpu, nr_cpu_ids);
+	init_kstat_irqs(desc, node, nr_cpu_ids);
 	if (!desc->kstat_irqs) {
 		printk(KERN_ERR "can not alloc kstat_irqs\n");
 		BUG_ON(1);
 	}
-	if (!init_alloc_desc_masks(desc, cpu, false)) {
+	if (!alloc_desc_masks(desc, node, false)) {
 		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
 		BUG_ON(1);
 	}
-	arch_init_chip_data(desc, cpu);
+	init_desc_masks(desc);
+	arch_init_chip_data(desc, node);
 }
 
 /*
@@ -146,6 +150,7 @@ int __init early_irq_init(void)
 {
 	struct irq_desc *desc;
 	int legacy_count;
+	int node;
 	int i;
 
 	init_irq_default_affinity();
@@ -156,20 +161,21 @@ int __init early_irq_init(void)
 
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
+ 	node = first_online_node;
 
 	/* allocate irq_desc_ptrs array based on nr_irqs */
-	irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
+	irq_desc_ptrs = kcalloc(nr_irqs, sizeof(void *), GFP_NOWAIT);
 
 	/* allocate based on nr_cpu_ids */
-	/* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */
-	kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids *
-					  sizeof(int));
+	kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
+					  sizeof(int), GFP_NOWAIT, node);
 
 	for (i = 0; i < legacy_count; i++) {
 		desc[i].irq = i;
 		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		init_alloc_desc_masks(&desc[i], 0, true);
+		alloc_desc_masks(&desc[i], node, true);
+		init_desc_masks(&desc[i]);
 		irq_desc_ptrs[i] = desc + i;
 	}
 
@@ -187,11 +193,10 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 	return NULL;
 }
 
-struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
 {
 	struct irq_desc *desc;
 	unsigned long flags;
-	int node;
 
 	if (irq >= nr_irqs) {
 		WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
@@ -210,15 +215,17 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 	if (desc)
 		goto out_unlock;
 
-	node = cpu_to_node(cpu);
-	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-	printk(KERN_DEBUG "  alloc irq_desc for %d on cpu %d node %d\n",
-		 irq, cpu, node);
+	if (slab_is_available())
+		desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
+	else
+		desc = alloc_bootmem_node(NODE_DATA(node), sizeof(*desc));
+
+	printk(KERN_DEBUG "  alloc irq_desc for %d on node %d\n", irq, node);
 	if (!desc) {
 		printk(KERN_ERR "can not alloc irq_desc\n");
 		BUG_ON(1);
 	}
-	init_one_irq_desc(irq, desc, cpu);
+	init_one_irq_desc(irq, desc, node);
 
 	irq_desc_ptrs[irq] = desc;
 
@@ -256,7 +263,8 @@ int __init early_irq_init(void)
 
 	for (i = 0; i < count; i++) {
 		desc[i].irq = i;
-		init_alloc_desc_masks(&desc[i], 0, true);
+		alloc_desc_masks(&desc[i], 0, true);
+		init_desc_masks(&desc[i]);
 		desc[i].kstat_irqs = kstat_irqs_all[i];
 	}
 	return arch_early_irq_init();
@@ -267,7 +275,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
 }
 
-struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
 {
 	return irq_to_desc(irq);
 }
@@ -348,9 +356,6 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
 	       "but no thread function available.", irq, action->name);
 }
 
-DEFINE_TRACE(irq_handler_entry);
-DEFINE_TRACE(irq_handler_exit);
-
 /**
  * handle_IRQ_event - irq action chain handler
  * @irq:	the interrupt number
@@ -453,11 +458,8 @@ unsigned int __do_IRQ(unsigned int irq)
 		/*
 		 * No locking required for CPU-local interrupts:
 		 */
-		if (desc->chip->ack) {
+		if (desc->chip->ack)
 			desc->chip->ack(irq);
-			/* get new one */
-			desc = irq_remap_to_desc(irq, desc);
-		}
 		if (likely(!(desc->status & IRQ_DISABLED))) {
 			action_ret = handle_IRQ_event(irq, desc->action);
 			if (!noirqdebug)
@@ -468,10 +470,8 @@ unsigned int __do_IRQ(unsigned int irq)
 	}
 
 	spin_lock(&desc->lock);
-	if (desc->chip->ack) {
+	if (desc->chip->ack)
 		desc->chip->ack(irq);
-		desc = irq_remap_to_desc(irq, desc);
-	}
 	/*
 	 * REPLAY is when Linux resends an IRQ that was dropped earlier
 	 * WAITING is used by probe to mark irqs that are being tested
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 01ce20eab38f..73468253143b 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -16,7 +16,7 @@ extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
 extern struct lock_class_key irq_desc_lock_class;
-extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
+extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 extern void clear_kstat_irqs(struct irq_desc *desc);
 extern spinlock_t sparse_irq_lock;
 
@@ -42,6 +42,9 @@ static inline void unregister_handler_proc(unsigned int irq,
 
 extern int irq_select_affinity_usr(unsigned int irq);
 
+extern void
+irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask);
+
 /*
  * Debugging printout:
  */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 2734eca59243..aaf5c9d05770 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -80,7 +80,7 @@ int irq_can_set_affinity(unsigned int irq)
 	return 1;
 }
 
-static void
+void
 irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
 {
 	struct irqaction *action = desc->action;
@@ -109,17 +109,22 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	spin_lock_irqsave(&desc->lock, flags);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (desc->status & IRQ_MOVE_PCNTXT)
-		desc->chip->set_affinity(irq, cpumask);
+	if (desc->status & IRQ_MOVE_PCNTXT) {
+		if (!desc->chip->set_affinity(irq, cpumask)) {
+			cpumask_copy(desc->affinity, cpumask);
+			irq_set_thread_affinity(desc, cpumask);
+		}
+	}
 	else {
 		desc->status |= IRQ_MOVE_PENDING;
 		cpumask_copy(desc->pending_mask, cpumask);
 	}
 #else
-	cpumask_copy(desc->affinity, cpumask);
-	desc->chip->set_affinity(irq, cpumask);
+	if (!desc->chip->set_affinity(irq, cpumask)) {
+		cpumask_copy(desc->affinity, cpumask);
+		irq_set_thread_affinity(desc, cpumask);
+	}
 #endif
-	irq_set_thread_affinity(desc, cpumask);
 	desc->status |= IRQ_AFFINITY_SET;
 	spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index e05ad9be43b7..cfe767ca1545 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -1,5 +1,8 @@
 
 #include <linux/irq.h>
+#include <linux/interrupt.h>
+
+#include "internals.h"
 
 void move_masked_irq(int irq)
 {
@@ -39,11 +42,12 @@ void move_masked_irq(int irq)
 	 * masking the irqs.
 	 */
 	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
-		   < nr_cpu_ids)) {
-		cpumask_and(desc->affinity,
-			    desc->pending_mask, cpu_online_mask);
-		desc->chip->set_affinity(irq, desc->affinity);
-	}
+		   < nr_cpu_ids))
+		if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
+			cpumask_copy(desc->affinity, desc->pending_mask);
+			irq_set_thread_affinity(desc, desc->pending_mask);
+		}
+
 	cpumask_clear(desc->pending_mask);
 }
 
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 44bbdcbaf8d2..2f69bee57bf2 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -15,9 +15,9 @@
 
 static void init_copy_kstat_irqs(struct irq_desc *old_desc,
 				 struct irq_desc *desc,
-				 int cpu, int nr)
+				 int node, int nr)
 {
-	init_kstat_irqs(desc, cpu, nr);
+	init_kstat_irqs(desc, node, nr);
 
 	if (desc->kstat_irqs != old_desc->kstat_irqs)
 		memcpy(desc->kstat_irqs, old_desc->kstat_irqs,
@@ -34,20 +34,20 @@ static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
 }
 
 static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
-		 struct irq_desc *desc, int cpu)
+		 struct irq_desc *desc, int node)
 {
 	memcpy(desc, old_desc, sizeof(struct irq_desc));
-	if (!init_alloc_desc_masks(desc, cpu, false)) {
+	if (!alloc_desc_masks(desc, node, false)) {
 		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
 				"for migration.\n", irq);
 		return false;
 	}
 	spin_lock_init(&desc->lock);
-	desc->cpu = cpu;
+	desc->node = node;
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+	init_copy_kstat_irqs(old_desc, desc, node, nr_cpu_ids);
 	init_copy_desc_masks(old_desc, desc);
-	arch_init_copy_chip_data(old_desc, desc, cpu);
+	arch_init_copy_chip_data(old_desc, desc, node);
 	return true;
 }
 
@@ -59,12 +59,11 @@ static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
 }
 
 static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
-						int cpu)
+						int node)
 {
 	struct irq_desc *desc;
 	unsigned int irq;
 	unsigned long flags;
-	int node;
 
 	irq = old_desc->irq;
 
@@ -76,7 +75,6 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	if (desc && old_desc != desc)
 		goto out_unlock;
 
-	node = cpu_to_node(cpu);
 	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
 	if (!desc) {
 		printk(KERN_ERR "irq %d: can not get new irq_desc "
@@ -85,7 +83,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 		desc = old_desc;
 		goto out_unlock;
 	}
-	if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) {
+	if (!init_copy_one_irq_desc(irq, old_desc, desc, node)) {
 		/* still use old one */
 		kfree(desc);
 		desc = old_desc;
@@ -97,9 +95,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 
 	/* free the old one */
 	free_one_irq_desc(old_desc, desc);
-	spin_unlock(&old_desc->lock);
 	kfree(old_desc);
-	spin_lock(&desc->lock);
 
 	return desc;
 
@@ -109,24 +105,14 @@ out_unlock:
 	return desc;
 }
 
-struct irq_desc *move_irq_desc(struct irq_desc *desc, int cpu)
+struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
 {
-	int old_cpu;
-	int node, old_node;
-
 	/* those all static, do move them */
 	if (desc->irq < NR_IRQS_LEGACY)
 		return desc;
 
-	old_cpu = desc->cpu;
-	if (old_cpu != cpu) {
-		node = cpu_to_node(cpu);
-		old_node = cpu_to_node(old_cpu);
-		if (old_node != node)
-			desc = __real_move_irq_desc(desc, cpu);
-		else
-			desc->cpu = cpu;
-	}
+	if (desc->node != node)
+		desc = __real_move_irq_desc(desc, node);
 
 	return desc;
 }
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 4ebaf8519abf..41c88fe40500 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -13,7 +13,7 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #define KTHREAD_NICE_LEVEL (-5)
 
@@ -21,9 +21,6 @@ static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
 struct task_struct *kthreadd_task;
 
-DEFINE_TRACE(sched_kthread_stop);
-DEFINE_TRACE(sched_kthread_stop_ret);
-
 struct kthread_create_info
 {
 	/* Information passed to kthread() from kthreadd. */
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index accb40cdb12a..8bbeef996c76 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -42,12 +42,14 @@
 #include <linux/hash.h>
 #include <linux/ftrace.h>
 #include <linux/stringify.h>
-#include <trace/lockdep.h>
 
 #include <asm/sections.h>
 
 #include "lockdep_internals.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/lockdep.h>
+
 #ifdef CONFIG_PROVE_LOCKING
 int prove_locking = 1;
 module_param(prove_locking, int, 0644);
@@ -2935,8 +2937,6 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
 }
 EXPORT_SYMBOL_GPL(lock_set_class);
 
-DEFINE_TRACE(lock_acquire);
-
 /*
  * We are not always called with irqs disabled - do that here,
  * and also avoid lockdep recursion:
@@ -2963,8 +2963,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 }
 EXPORT_SYMBOL_GPL(lock_acquire);
 
-DEFINE_TRACE(lock_release);
-
 void lock_release(struct lockdep_map *lock, int nested,
 			  unsigned long ip)
 {
@@ -3105,6 +3103,8 @@ found_it:
 		hlock->holdtime_stamp = now;
 	}
 
+	trace_lock_acquired(lock, ip, waittime);
+
 	stats = get_lock_stats(hlock_class(hlock));
 	if (waittime) {
 		if (hlock->read)
@@ -3120,8 +3120,6 @@ found_it:
 	lock->ip = ip;
 }
 
-DEFINE_TRACE(lock_contended);
-
 void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
@@ -3143,14 +3141,10 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_contended);
 
-DEFINE_TRACE(lock_acquired);
-
 void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	trace_lock_acquired(lock, ip);
-
 	if (unlikely(!lock_stat))
 		return;
 
diff --git a/kernel/module.c b/kernel/module.c
index e797812a4d95..35f7de00bf0d 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -18,6 +18,7 @@
 */
 #include <linux/module.h>
 #include <linux/moduleloader.h>
+#include <linux/ftrace_event.h>
 #include <linux/init.h>
 #include <linux/kallsyms.h>
 #include <linux/fs.h>
@@ -52,6 +53,7 @@
 #include <linux/ftrace.h>
 #include <linux/async.h>
 #include <linux/percpu.h>
+#include <linux/kmemleak.h>
 
 #if 0
 #define DEBUGP printk
@@ -72,6 +74,9 @@ DEFINE_MUTEX(module_mutex);
 EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
 
+/* Block module loading/unloading? */
+int modules_disabled = 0;
+
 /* Waiting for a module to finish initializing? */
 static DECLARE_WAIT_QUEUE_HEAD(module_wq);
 
@@ -429,6 +434,7 @@ static void *percpu_modalloc(unsigned long size, unsigned long align,
 	unsigned long extra;
 	unsigned int i;
 	void *ptr;
+	int cpu;
 
 	if (align > PAGE_SIZE) {
 		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
@@ -458,6 +464,11 @@ static void *percpu_modalloc(unsigned long size, unsigned long align,
 			if (!split_block(i, size))
 				return NULL;
 
+		/* add the per-cpu scanning areas */
+		for_each_possible_cpu(cpu)
+			kmemleak_alloc(ptr + per_cpu_offset(cpu), size, 0,
+				       GFP_KERNEL);
+
 		/* Mark allocated */
 		pcpu_size[i] = -pcpu_size[i];
 		return ptr;
@@ -472,6 +483,7 @@ static void percpu_modfree(void *freeme)
 {
 	unsigned int i;
 	void *ptr = __per_cpu_start + block_size(pcpu_size[0]);
+	int cpu;
 
 	/* First entry is core kernel percpu data. */
 	for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
@@ -483,6 +495,10 @@ static void percpu_modfree(void *freeme)
 	BUG();
 
  free:
+	/* remove the per-cpu scanning areas */
+	for_each_possible_cpu(cpu)
+		kmemleak_free(freeme + per_cpu_offset(cpu));
+
 	/* Merge with previous? */
 	if (pcpu_size[i-1] >= 0) {
 		pcpu_size[i-1] += pcpu_size[i];
@@ -777,7 +793,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 	char name[MODULE_NAME_LEN];
 	int ret, forced = 0;
 
-	if (!capable(CAP_SYS_MODULE))
+	if (!capable(CAP_SYS_MODULE) || modules_disabled)
 		return -EPERM;
 
 	if (strncpy_from_user(name, name_user, MODULE_NAME_LEN-1) < 0)
@@ -1489,9 +1505,6 @@ static void free_module(struct module *mod)
 	/* Free any allocated parameters. */
 	destroy_params(mod->kp, mod->num_kp);
 
-	/* release any pointers to mcount in this module */
-	ftrace_release(mod->module_core, mod->core_size);
-
 	/* This may be NULL, but that's OK */
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
@@ -1878,6 +1891,36 @@ static void *module_alloc_update_bounds(unsigned long size)
 	return ret;
 }
 
+#ifdef CONFIG_DEBUG_KMEMLEAK
+static void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr,
+				 Elf_Shdr *sechdrs, char *secstrings)
+{
+	unsigned int i;
+
+	/* only scan the sections containing data */
+	kmemleak_scan_area(mod->module_core, (unsigned long)mod -
+			   (unsigned long)mod->module_core,
+			   sizeof(struct module), GFP_KERNEL);
+
+	for (i = 1; i < hdr->e_shnum; i++) {
+		if (!(sechdrs[i].sh_flags & SHF_ALLOC))
+			continue;
+		if (strncmp(secstrings + sechdrs[i].sh_name, ".data", 5) != 0
+		    && strncmp(secstrings + sechdrs[i].sh_name, ".bss", 4) != 0)
+			continue;
+
+		kmemleak_scan_area(mod->module_core, sechdrs[i].sh_addr -
+				   (unsigned long)mod->module_core,
+				   sechdrs[i].sh_size, GFP_KERNEL);
+	}
+}
+#else
+static inline void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr,
+					Elf_Shdr *sechdrs, char *secstrings)
+{
+}
+#endif
+
 /* Allocate and load the module: note that size of section 0 is always
    zero, and we rely on this for optional sections. */
 static noinline struct module *load_module(void __user *umod,
@@ -1892,11 +1935,9 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int symindex = 0;
 	unsigned int strindex = 0;
 	unsigned int modindex, versindex, infoindex, pcpuindex;
-	unsigned int num_mcount;
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
-	unsigned long *mseg;
 	mm_segment_t old_fs;
 
 	DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
@@ -2050,6 +2091,12 @@ static noinline struct module *load_module(void __user *umod,
 
 	/* Do the allocs. */
 	ptr = module_alloc_update_bounds(mod->core_size);
+	/*
+	 * The pointer to this block is stored in the module structure
+	 * which is inside the block. Just mark it as not being a
+	 * leak.
+	 */
+	kmemleak_not_leak(ptr);
 	if (!ptr) {
 		err = -ENOMEM;
 		goto free_percpu;
@@ -2058,6 +2105,13 @@ static noinline struct module *load_module(void __user *umod,
 	mod->module_core = ptr;
 
 	ptr = module_alloc_update_bounds(mod->init_size);
+	/*
+	 * The pointer to this block is stored in the module structure
+	 * which is inside the block. This block doesn't need to be
+	 * scanned as it contains data and code that will be freed
+	 * after the module is initialized.
+	 */
+	kmemleak_ignore(ptr);
 	if (!ptr && mod->init_size) {
 		err = -ENOMEM;
 		goto free_core;
@@ -2088,6 +2142,7 @@ static noinline struct module *load_module(void __user *umod,
 	}
 	/* Module has been moved. */
 	mod = (void *)sechdrs[modindex].sh_addr;
+	kmemleak_load_module(mod, hdr, sechdrs, secstrings);
 
 #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
 	mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
@@ -2172,7 +2227,19 @@ static noinline struct module *load_module(void __user *umod,
 					sizeof(*mod->tracepoints),
 					&mod->num_tracepoints);
 #endif
-
+#ifdef CONFIG_EVENT_TRACING
+	mod->trace_events = section_objs(hdr, sechdrs, secstrings,
+					 "_ftrace_events",
+					 sizeof(*mod->trace_events),
+					 &mod->num_trace_events);
+#endif
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+	/* sechdrs[0].sh_size is always zero */
+	mod->ftrace_callsites = section_objs(hdr, sechdrs, secstrings,
+					     "__mcount_loc",
+					     sizeof(*mod->ftrace_callsites),
+					     &mod->num_ftrace_callsites);
+#endif
 #ifdef CONFIG_MODVERSIONS
 	if ((mod->num_syms && !mod->crcs)
 	    || (mod->num_gpl_syms && !mod->gpl_crcs)
@@ -2237,11 +2304,6 @@ static noinline struct module *load_module(void __user *umod,
 			dynamic_debug_setup(debug, num_debug);
 	}
 
-	/* sechdrs[0].sh_size is always zero */
-	mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
-			    sizeof(*mseg), &num_mcount);
-	ftrace_init_module(mod, mseg, mseg + num_mcount);
-
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
 		goto cleanup;
@@ -2302,7 +2364,6 @@ static noinline struct module *load_module(void __user *umod,
  cleanup:
 	kobject_del(&mod->mkobj.kobj);
 	kobject_put(&mod->mkobj.kobj);
-	ftrace_release(mod->module_core, mod->core_size);
  free_unload:
 	module_unload_free(mod);
 #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
@@ -2336,7 +2397,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 	int ret = 0;
 
 	/* Must have permission */
-	if (!capable(CAP_SYS_MODULE))
+	if (!capable(CAP_SYS_MODULE) || modules_disabled)
 		return -EPERM;
 
 	/* Only one module load at a time, please */
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 507cf2b5e9f1..947b3ad551f8 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -89,7 +89,7 @@ __mutex_lock_slowpath(atomic_t *lock_count);
  *
  * This function is similar to (but not equivalent to) down().
  */
-void inline __sched mutex_lock(struct mutex *lock)
+void __sched mutex_lock(struct mutex *lock)
 {
 	might_sleep();
 	/*
@@ -249,7 +249,9 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 		/* didnt get the lock, go to sleep: */
 		spin_unlock_mutex(&lock->wait_lock, flags);
-		__schedule();
+		preempt_enable_no_resched();
+		schedule();
+		preempt_disable();
 		spin_lock_mutex(&lock->wait_lock, flags);
 	}
 
@@ -471,5 +473,28 @@ int __sched mutex_trylock(struct mutex *lock)
 
 	return ret;
 }
-
 EXPORT_SYMBOL(mutex_trylock);
+
+/**
+ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
+ * @cnt: the atomic which we are to dec
+ * @lock: the mutex to return holding if we dec to 0
+ *
+ * return true and hold lock if we dec to 0, return false otherwise
+ */
+int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
+{
+	/* dec if we can't possibly hit 0 */
+	if (atomic_add_unless(cnt, -1, 1))
+		return 0;
+	/* we might hit 0, so take the lock */
+	mutex_lock(lock);
+	if (!atomic_dec_and_test(cnt)) {
+		/* when we actually did the dec, we didn't hit 0 */
+		mutex_unlock(lock);
+		return 0;
+	}
+	/* we hit 0, and we hold the lock */
+	return 1;
+}
+EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
new file mode 100644
index 000000000000..ef5d8a5b2453
--- /dev/null
+++ b/kernel/perf_counter.c
@@ -0,0 +1,4260 @@
+/*
+ * Performance counter core code
+ *
+ *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ *  For licensing details see kernel-base/COPYING
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/sysfs.h>
+#include <linux/dcache.h>
+#include <linux/percpu.h>
+#include <linux/ptrace.h>
+#include <linux/vmstat.h>
+#include <linux/hardirq.h>
+#include <linux/rculist.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/anon_inodes.h>
+#include <linux/kernel_stat.h>
+#include <linux/perf_counter.h>
+
+#include <asm/irq_regs.h>
+
+/*
+ * Each CPU has a list of per CPU counters:
+ */
+DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
+
+int perf_max_counters __read_mostly = 1;
+static int perf_reserved_percpu __read_mostly;
+static int perf_overcommit __read_mostly = 1;
+
+static atomic_t nr_counters __read_mostly;
+static atomic_t nr_mmap_counters __read_mostly;
+static atomic_t nr_comm_counters __read_mostly;
+
+/*
+ * perf counter paranoia level:
+ *  0 - not paranoid
+ *  1 - disallow cpu counters to unpriv
+ *  2 - disallow kernel profiling to unpriv
+ */
+int sysctl_perf_counter_paranoid __read_mostly;
+
+static inline bool perf_paranoid_cpu(void)
+{
+	return sysctl_perf_counter_paranoid > 0;
+}
+
+static inline bool perf_paranoid_kernel(void)
+{
+	return sysctl_perf_counter_paranoid > 1;
+}
+
+int sysctl_perf_counter_mlock __read_mostly = 512; /* 'free' kb per user */
+
+/*
+ * max perf counter sample rate
+ */
+int sysctl_perf_counter_sample_rate __read_mostly = 100000;
+
+static atomic64_t perf_counter_id;
+
+/*
+ * Lock for (sysadmin-configurable) counter reservations:
+ */
+static DEFINE_SPINLOCK(perf_resource_lock);
+
+/*
+ * Architecture provided APIs - weak aliases:
+ */
+extern __weak const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
+{
+	return NULL;
+}
+
+void __weak hw_perf_disable(void)		{ barrier(); }
+void __weak hw_perf_enable(void)		{ barrier(); }
+
+void __weak hw_perf_counter_setup(int cpu)	{ barrier(); }
+
+int __weak
+hw_perf_group_sched_in(struct perf_counter *group_leader,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_counter_context *ctx, int cpu)
+{
+	return 0;
+}
+
+void __weak perf_counter_print_debug(void)	{ }
+
+static DEFINE_PER_CPU(int, disable_count);
+
+void __perf_disable(void)
+{
+	__get_cpu_var(disable_count)++;
+}
+
+bool __perf_enable(void)
+{
+	return !--__get_cpu_var(disable_count);
+}
+
+void perf_disable(void)
+{
+	__perf_disable();
+	hw_perf_disable();
+}
+
+void perf_enable(void)
+{
+	if (__perf_enable())
+		hw_perf_enable();
+}
+
+static void get_ctx(struct perf_counter_context *ctx)
+{
+	atomic_inc(&ctx->refcount);
+}
+
+static void free_ctx(struct rcu_head *head)
+{
+	struct perf_counter_context *ctx;
+
+	ctx = container_of(head, struct perf_counter_context, rcu_head);
+	kfree(ctx);
+}
+
+static void put_ctx(struct perf_counter_context *ctx)
+{
+	if (atomic_dec_and_test(&ctx->refcount)) {
+		if (ctx->parent_ctx)
+			put_ctx(ctx->parent_ctx);
+		if (ctx->task)
+			put_task_struct(ctx->task);
+		call_rcu(&ctx->rcu_head, free_ctx);
+	}
+}
+
+/*
+ * Get the perf_counter_context for a task and lock it.
+ * This has to cope with with the fact that until it is locked,
+ * the context could get moved to another task.
+ */
+static struct perf_counter_context *
+perf_lock_task_context(struct task_struct *task, unsigned long *flags)
+{
+	struct perf_counter_context *ctx;
+
+	rcu_read_lock();
+ retry:
+	ctx = rcu_dereference(task->perf_counter_ctxp);
+	if (ctx) {
+		/*
+		 * If this context is a clone of another, it might
+		 * get swapped for another underneath us by
+		 * perf_counter_task_sched_out, though the
+		 * rcu_read_lock() protects us from any context
+		 * getting freed.  Lock the context and check if it
+		 * got swapped before we could get the lock, and retry
+		 * if so.  If we locked the right context, then it
+		 * can't get swapped on us any more.
+		 */
+		spin_lock_irqsave(&ctx->lock, *flags);
+		if (ctx != rcu_dereference(task->perf_counter_ctxp)) {
+			spin_unlock_irqrestore(&ctx->lock, *flags);
+			goto retry;
+		}
+	}
+	rcu_read_unlock();
+	return ctx;
+}
+
+/*
+ * Get the context for a task and increment its pin_count so it
+ * can't get swapped to another task.  This also increments its
+ * reference count so that the context can't get freed.
+ */
+static struct perf_counter_context *perf_pin_task_context(struct task_struct *task)
+{
+	struct perf_counter_context *ctx;
+	unsigned long flags;
+
+	ctx = perf_lock_task_context(task, &flags);
+	if (ctx) {
+		++ctx->pin_count;
+		get_ctx(ctx);
+		spin_unlock_irqrestore(&ctx->lock, flags);
+	}
+	return ctx;
+}
+
+static void perf_unpin_context(struct perf_counter_context *ctx)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	--ctx->pin_count;
+	spin_unlock_irqrestore(&ctx->lock, flags);
+	put_ctx(ctx);
+}
+
+/*
+ * Add a counter from the lists for its context.
+ * Must be called with ctx->mutex and ctx->lock held.
+ */
+static void
+list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
+{
+	struct perf_counter *group_leader = counter->group_leader;
+
+	/*
+	 * Depending on whether it is a standalone or sibling counter,
+	 * add it straight to the context's counter list, or to the group
+	 * leader's sibling list:
+	 */
+	if (group_leader == counter)
+		list_add_tail(&counter->list_entry, &ctx->counter_list);
+	else {
+		list_add_tail(&counter->list_entry, &group_leader->sibling_list);
+		group_leader->nr_siblings++;
+	}
+
+	list_add_rcu(&counter->event_entry, &ctx->event_list);
+	ctx->nr_counters++;
+}
+
+/*
+ * Remove a counter from the lists for its context.
+ * Must be called with ctx->mutex and ctx->lock held.
+ */
+static void
+list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
+{
+	struct perf_counter *sibling, *tmp;
+
+	if (list_empty(&counter->list_entry))
+		return;
+	ctx->nr_counters--;
+
+	list_del_init(&counter->list_entry);
+	list_del_rcu(&counter->event_entry);
+
+	if (counter->group_leader != counter)
+		counter->group_leader->nr_siblings--;
+
+	/*
+	 * If this was a group counter with sibling counters then
+	 * upgrade the siblings to singleton counters by adding them
+	 * to the context list directly:
+	 */
+	list_for_each_entry_safe(sibling, tmp,
+				 &counter->sibling_list, list_entry) {
+
+		list_move_tail(&sibling->list_entry, &ctx->counter_list);
+		sibling->group_leader = sibling;
+	}
+}
+
+static void
+counter_sched_out(struct perf_counter *counter,
+		  struct perf_cpu_context *cpuctx,
+		  struct perf_counter_context *ctx)
+{
+	if (counter->state != PERF_COUNTER_STATE_ACTIVE)
+		return;
+
+	counter->state = PERF_COUNTER_STATE_INACTIVE;
+	counter->tstamp_stopped = ctx->time;
+	counter->pmu->disable(counter);
+	counter->oncpu = -1;
+
+	if (!is_software_counter(counter))
+		cpuctx->active_oncpu--;
+	ctx->nr_active--;
+	if (counter->attr.exclusive || !cpuctx->active_oncpu)
+		cpuctx->exclusive = 0;
+}
+
+static void
+group_sched_out(struct perf_counter *group_counter,
+		struct perf_cpu_context *cpuctx,
+		struct perf_counter_context *ctx)
+{
+	struct perf_counter *counter;
+
+	if (group_counter->state != PERF_COUNTER_STATE_ACTIVE)
+		return;
+
+	counter_sched_out(group_counter, cpuctx, ctx);
+
+	/*
+	 * Schedule out siblings (if any):
+	 */
+	list_for_each_entry(counter, &group_counter->sibling_list, list_entry)
+		counter_sched_out(counter, cpuctx, ctx);
+
+	if (group_counter->attr.exclusive)
+		cpuctx->exclusive = 0;
+}
+
+/*
+ * Cross CPU call to remove a performance counter
+ *
+ * We disable the counter on the hardware level first. After that we
+ * remove it from the context list.
+ */
+static void __perf_counter_remove_from_context(void *info)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_counter *counter = info;
+	struct perf_counter_context *ctx = counter->ctx;
+
+	/*
+	 * If this is a task context, we need to check whether it is
+	 * the current task context of this cpu. If not it has been
+	 * scheduled out before the smp call arrived.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx)
+		return;
+
+	spin_lock(&ctx->lock);
+	/*
+	 * Protect the list operation against NMI by disabling the
+	 * counters on a global level.
+	 */
+	perf_disable();
+
+	counter_sched_out(counter, cpuctx, ctx);
+
+	list_del_counter(counter, ctx);
+
+	if (!ctx->task) {
+		/*
+		 * Allow more per task counters with respect to the
+		 * reservation:
+		 */
+		cpuctx->max_pertask =
+			min(perf_max_counters - ctx->nr_counters,
+			    perf_max_counters - perf_reserved_percpu);
+	}
+
+	perf_enable();
+	spin_unlock(&ctx->lock);
+}
+
+
+/*
+ * Remove the counter from a task's (or a CPU's) list of counters.
+ *
+ * Must be called with ctx->mutex held.
+ *
+ * CPU counters are removed with a smp call. For task counters we only
+ * call when the task is on a CPU.
+ *
+ * If counter->ctx is a cloned context, callers must make sure that
+ * every task struct that counter->ctx->task could possibly point to
+ * remains valid.  This is OK when called from perf_release since
+ * that only calls us on the top-level context, which can't be a clone.
+ * When called from perf_counter_exit_task, it's OK because the
+ * context has been detached from its task.
+ */
+static void perf_counter_remove_from_context(struct perf_counter *counter)
+{
+	struct perf_counter_context *ctx = counter->ctx;
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		/*
+		 * Per cpu counters are removed via an smp call and
+		 * the removal is always sucessful.
+		 */
+		smp_call_function_single(counter->cpu,
+					 __perf_counter_remove_from_context,
+					 counter, 1);
+		return;
+	}
+
+retry:
+	task_oncpu_function_call(task, __perf_counter_remove_from_context,
+				 counter);
+
+	spin_lock_irq(&ctx->lock);
+	/*
+	 * If the context is active we need to retry the smp call.
+	 */
+	if (ctx->nr_active && !list_empty(&counter->list_entry)) {
+		spin_unlock_irq(&ctx->lock);
+		goto retry;
+	}
+
+	/*
+	 * The lock prevents that this context is scheduled in so we
+	 * can remove the counter safely, if the call above did not
+	 * succeed.
+	 */
+	if (!list_empty(&counter->list_entry)) {
+		list_del_counter(counter, ctx);
+	}
+	spin_unlock_irq(&ctx->lock);
+}
+
+static inline u64 perf_clock(void)
+{
+	return cpu_clock(smp_processor_id());
+}
+
+/*
+ * Update the record of the current time in a context.
+ */
+static void update_context_time(struct perf_counter_context *ctx)
+{
+	u64 now = perf_clock();
+
+	ctx->time += now - ctx->timestamp;
+	ctx->timestamp = now;
+}
+
+/*
+ * Update the total_time_enabled and total_time_running fields for a counter.
+ */
+static void update_counter_times(struct perf_counter *counter)
+{
+	struct perf_counter_context *ctx = counter->ctx;
+	u64 run_end;
+
+	if (counter->state < PERF_COUNTER_STATE_INACTIVE)
+		return;
+
+	counter->total_time_enabled = ctx->time - counter->tstamp_enabled;
+
+	if (counter->state == PERF_COUNTER_STATE_INACTIVE)
+		run_end = counter->tstamp_stopped;
+	else
+		run_end = ctx->time;
+
+	counter->total_time_running = run_end - counter->tstamp_running;
+}
+
+/*
+ * Update total_time_enabled and total_time_running for all counters in a group.
+ */
+static void update_group_times(struct perf_counter *leader)
+{
+	struct perf_counter *counter;
+
+	update_counter_times(leader);
+	list_for_each_entry(counter, &leader->sibling_list, list_entry)
+		update_counter_times(counter);
+}
+
+/*
+ * Cross CPU call to disable a performance counter
+ */
+static void __perf_counter_disable(void *info)
+{
+	struct perf_counter *counter = info;
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_counter_context *ctx = counter->ctx;
+
+	/*
+	 * If this is a per-task counter, need to check whether this
+	 * counter's task is the current task on this cpu.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx)
+		return;
+
+	spin_lock(&ctx->lock);
+
+	/*
+	 * If the counter is on, turn it off.
+	 * If it is in error state, leave it in error state.
+	 */
+	if (counter->state >= PERF_COUNTER_STATE_INACTIVE) {
+		update_context_time(ctx);
+		update_counter_times(counter);
+		if (counter == counter->group_leader)
+			group_sched_out(counter, cpuctx, ctx);
+		else
+			counter_sched_out(counter, cpuctx, ctx);
+		counter->state = PERF_COUNTER_STATE_OFF;
+	}
+
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Disable a counter.
+ *
+ * If counter->ctx is a cloned context, callers must make sure that
+ * every task struct that counter->ctx->task could possibly point to
+ * remains valid.  This condition is satisifed when called through
+ * perf_counter_for_each_child or perf_counter_for_each because they
+ * hold the top-level counter's child_mutex, so any descendant that
+ * goes to exit will block in sync_child_counter.
+ * When called from perf_pending_counter it's OK because counter->ctx
+ * is the current context on this CPU and preemption is disabled,
+ * hence we can't get into perf_counter_task_sched_out for this context.
+ */
+static void perf_counter_disable(struct perf_counter *counter)
+{
+	struct perf_counter_context *ctx = counter->ctx;
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		/*
+		 * Disable the counter on the cpu that it's on
+		 */
+		smp_call_function_single(counter->cpu, __perf_counter_disable,
+					 counter, 1);
+		return;
+	}
+
+ retry:
+	task_oncpu_function_call(task, __perf_counter_disable, counter);
+
+	spin_lock_irq(&ctx->lock);
+	/*
+	 * If the counter is still active, we need to retry the cross-call.
+	 */
+	if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
+		spin_unlock_irq(&ctx->lock);
+		goto retry;
+	}
+
+	/*
+	 * Since we have the lock this context can't be scheduled
+	 * in, so we can change the state safely.
+	 */
+	if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
+		update_counter_times(counter);
+		counter->state = PERF_COUNTER_STATE_OFF;
+	}
+
+	spin_unlock_irq(&ctx->lock);
+}
+
+static int
+counter_sched_in(struct perf_counter *counter,
+		 struct perf_cpu_context *cpuctx,
+		 struct perf_counter_context *ctx,
+		 int cpu)
+{
+	if (counter->state <= PERF_COUNTER_STATE_OFF)
+		return 0;
+
+	counter->state = PERF_COUNTER_STATE_ACTIVE;
+	counter->oncpu = cpu;	/* TODO: put 'cpu' into cpuctx->cpu */
+	/*
+	 * The new state must be visible before we turn it on in the hardware:
+	 */
+	smp_wmb();
+
+	if (counter->pmu->enable(counter)) {
+		counter->state = PERF_COUNTER_STATE_INACTIVE;
+		counter->oncpu = -1;
+		return -EAGAIN;
+	}
+
+	counter->tstamp_running += ctx->time - counter->tstamp_stopped;
+
+	if (!is_software_counter(counter))
+		cpuctx->active_oncpu++;
+	ctx->nr_active++;
+
+	if (counter->attr.exclusive)
+		cpuctx->exclusive = 1;
+
+	return 0;
+}
+
+static int
+group_sched_in(struct perf_counter *group_counter,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_counter_context *ctx,
+	       int cpu)
+{
+	struct perf_counter *counter, *partial_group;
+	int ret;
+
+	if (group_counter->state == PERF_COUNTER_STATE_OFF)
+		return 0;
+
+	ret = hw_perf_group_sched_in(group_counter, cpuctx, ctx, cpu);
+	if (ret)
+		return ret < 0 ? ret : 0;
+
+	if (counter_sched_in(group_counter, cpuctx, ctx, cpu))
+		return -EAGAIN;
+
+	/*
+	 * Schedule in siblings as one group (if any):
+	 */
+	list_for_each_entry(counter, &group_counter->sibling_list, list_entry) {
+		if (counter_sched_in(counter, cpuctx, ctx, cpu)) {
+			partial_group = counter;
+			goto group_error;
+		}
+	}
+
+	return 0;
+
+group_error:
+	/*
+	 * Groups can be scheduled in as one unit only, so undo any
+	 * partial group before returning:
+	 */
+	list_for_each_entry(counter, &group_counter->sibling_list, list_entry) {
+		if (counter == partial_group)
+			break;
+		counter_sched_out(counter, cpuctx, ctx);
+	}
+	counter_sched_out(group_counter, cpuctx, ctx);
+
+	return -EAGAIN;
+}
+
+/*
+ * Return 1 for a group consisting entirely of software counters,
+ * 0 if the group contains any hardware counters.
+ */
+static int is_software_only_group(struct perf_counter *leader)
+{
+	struct perf_counter *counter;
+
+	if (!is_software_counter(leader))
+		return 0;
+
+	list_for_each_entry(counter, &leader->sibling_list, list_entry)
+		if (!is_software_counter(counter))
+			return 0;
+
+	return 1;
+}
+
+/*
+ * Work out whether we can put this counter group on the CPU now.
+ */
+static int group_can_go_on(struct perf_counter *counter,
+			   struct perf_cpu_context *cpuctx,
+			   int can_add_hw)
+{
+	/*
+	 * Groups consisting entirely of software counters can always go on.
+	 */
+	if (is_software_only_group(counter))
+		return 1;
+	/*
+	 * If an exclusive group is already on, no other hardware
+	 * counters can go on.
+	 */
+	if (cpuctx->exclusive)
+		return 0;
+	/*
+	 * If this group is exclusive and there are already
+	 * counters on the CPU, it can't go on.
+	 */
+	if (counter->attr.exclusive && cpuctx->active_oncpu)
+		return 0;
+	/*
+	 * Otherwise, try to add it if all previous groups were able
+	 * to go on.
+	 */
+	return can_add_hw;
+}
+
+static void add_counter_to_ctx(struct perf_counter *counter,
+			       struct perf_counter_context *ctx)
+{
+	list_add_counter(counter, ctx);
+	counter->tstamp_enabled = ctx->time;
+	counter->tstamp_running = ctx->time;
+	counter->tstamp_stopped = ctx->time;
+}
+
+/*
+ * Cross CPU call to install and enable a performance counter
+ *
+ * Must be called with ctx->mutex held
+ */
+static void __perf_install_in_context(void *info)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_counter *counter = info;
+	struct perf_counter_context *ctx = counter->ctx;
+	struct perf_counter *leader = counter->group_leader;
+	int cpu = smp_processor_id();
+	int err;
+
+	/*
+	 * If this is a task context, we need to check whether it is
+	 * the current task context of this cpu. If not it has been
+	 * scheduled out before the smp call arrived.
+	 * Or possibly this is the right context but it isn't
+	 * on this cpu because it had no counters.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx) {
+		if (cpuctx->task_ctx || ctx->task != current)
+			return;
+		cpuctx->task_ctx = ctx;
+	}
+
+	spin_lock(&ctx->lock);
+	ctx->is_active = 1;
+	update_context_time(ctx);
+
+	/*
+	 * Protect the list operation against NMI by disabling the
+	 * counters on a global level. NOP for non NMI based counters.
+	 */
+	perf_disable();
+
+	add_counter_to_ctx(counter, ctx);
+
+	/*
+	 * Don't put the counter on if it is disabled or if
+	 * it is in a group and the group isn't on.
+	 */
+	if (counter->state != PERF_COUNTER_STATE_INACTIVE ||
+	    (leader != counter && leader->state != PERF_COUNTER_STATE_ACTIVE))
+		goto unlock;
+
+	/*
+	 * An exclusive counter can't go on if there are already active
+	 * hardware counters, and no hardware counter can go on if there
+	 * is already an exclusive counter on.
+	 */
+	if (!group_can_go_on(counter, cpuctx, 1))
+		err = -EEXIST;
+	else
+		err = counter_sched_in(counter, cpuctx, ctx, cpu);
+
+	if (err) {
+		/*
+		 * This counter couldn't go on.  If it is in a group
+		 * then we have to pull the whole group off.
+		 * If the counter group is pinned then put it in error state.
+		 */
+		if (leader != counter)
+			group_sched_out(leader, cpuctx, ctx);
+		if (leader->attr.pinned) {
+			update_group_times(leader);
+			leader->state = PERF_COUNTER_STATE_ERROR;
+		}
+	}
+
+	if (!err && !ctx->task && cpuctx->max_pertask)
+		cpuctx->max_pertask--;
+
+ unlock:
+	perf_enable();
+
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Attach a performance counter to a context
+ *
+ * First we add the counter to the list with the hardware enable bit
+ * in counter->hw_config cleared.
+ *
+ * If the counter is attached to a task which is on a CPU we use a smp
+ * call to enable it in the task context. The task might have been
+ * scheduled away, but we check this in the smp call again.
+ *
+ * Must be called with ctx->mutex held.
+ */
+static void
+perf_install_in_context(struct perf_counter_context *ctx,
+			struct perf_counter *counter,
+			int cpu)
+{
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		/*
+		 * Per cpu counters are installed via an smp call and
+		 * the install is always sucessful.
+		 */
+		smp_call_function_single(cpu, __perf_install_in_context,
+					 counter, 1);
+		return;
+	}
+
+retry:
+	task_oncpu_function_call(task, __perf_install_in_context,
+				 counter);
+
+	spin_lock_irq(&ctx->lock);
+	/*
+	 * we need to retry the smp call.
+	 */
+	if (ctx->is_active && list_empty(&counter->list_entry)) {
+		spin_unlock_irq(&ctx->lock);
+		goto retry;
+	}
+
+	/*
+	 * The lock prevents that this context is scheduled in so we
+	 * can add the counter safely, if it the call above did not
+	 * succeed.
+	 */
+	if (list_empty(&counter->list_entry))
+		add_counter_to_ctx(counter, ctx);
+	spin_unlock_irq(&ctx->lock);
+}
+
+/*
+ * Cross CPU call to enable a performance counter
+ */
+static void __perf_counter_enable(void *info)
+{
+	struct perf_counter *counter = info;
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_counter_context *ctx = counter->ctx;
+	struct perf_counter *leader = counter->group_leader;
+	int err;
+
+	/*
+	 * If this is a per-task counter, need to check whether this
+	 * counter's task is the current task on this cpu.
+	 */
+	if (ctx->task && cpuctx->task_ctx != ctx) {
+		if (cpuctx->task_ctx || ctx->task != current)
+			return;
+		cpuctx->task_ctx = ctx;
+	}
+
+	spin_lock(&ctx->lock);
+	ctx->is_active = 1;
+	update_context_time(ctx);
+
+	if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+		goto unlock;
+	counter->state = PERF_COUNTER_STATE_INACTIVE;
+	counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+
+	/*
+	 * If the counter is in a group and isn't the group leader,
+	 * then don't put it on unless the group is on.
+	 */
+	if (leader != counter && leader->state != PERF_COUNTER_STATE_ACTIVE)
+		goto unlock;
+
+	if (!group_can_go_on(counter, cpuctx, 1)) {
+		err = -EEXIST;
+	} else {
+		perf_disable();
+		if (counter == leader)
+			err = group_sched_in(counter, cpuctx, ctx,
+					     smp_processor_id());
+		else
+			err = counter_sched_in(counter, cpuctx, ctx,
+					       smp_processor_id());
+		perf_enable();
+	}
+
+	if (err) {
+		/*
+		 * If this counter can't go on and it's part of a
+		 * group, then the whole group has to come off.
+		 */
+		if (leader != counter)
+			group_sched_out(leader, cpuctx, ctx);
+		if (leader->attr.pinned) {
+			update_group_times(leader);
+			leader->state = PERF_COUNTER_STATE_ERROR;
+		}
+	}
+
+ unlock:
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Enable a counter.
+ *
+ * If counter->ctx is a cloned context, callers must make sure that
+ * every task struct that counter->ctx->task could possibly point to
+ * remains valid.  This condition is satisfied when called through
+ * perf_counter_for_each_child or perf_counter_for_each as described
+ * for perf_counter_disable.
+ */
+static void perf_counter_enable(struct perf_counter *counter)
+{
+	struct perf_counter_context *ctx = counter->ctx;
+	struct task_struct *task = ctx->task;
+
+	if (!task) {
+		/*
+		 * Enable the counter on the cpu that it's on
+		 */
+		smp_call_function_single(counter->cpu, __perf_counter_enable,
+					 counter, 1);
+		return;
+	}
+
+	spin_lock_irq(&ctx->lock);
+	if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+		goto out;
+
+	/*
+	 * If the counter is in error state, clear that first.
+	 * That way, if we see the counter in error state below, we
+	 * know that it has gone back into error state, as distinct
+	 * from the task having been scheduled away before the
+	 * cross-call arrived.
+	 */
+	if (counter->state == PERF_COUNTER_STATE_ERROR)
+		counter->state = PERF_COUNTER_STATE_OFF;
+
+ retry:
+	spin_unlock_irq(&ctx->lock);
+	task_oncpu_function_call(task, __perf_counter_enable, counter);
+
+	spin_lock_irq(&ctx->lock);
+
+	/*
+	 * If the context is active and the counter is still off,
+	 * we need to retry the cross-call.
+	 */
+	if (ctx->is_active && counter->state == PERF_COUNTER_STATE_OFF)
+		goto retry;
+
+	/*
+	 * Since we have the lock this context can't be scheduled
+	 * in, so we can change the state safely.
+	 */
+	if (counter->state == PERF_COUNTER_STATE_OFF) {
+		counter->state = PERF_COUNTER_STATE_INACTIVE;
+		counter->tstamp_enabled =
+			ctx->time - counter->total_time_enabled;
+	}
+ out:
+	spin_unlock_irq(&ctx->lock);
+}
+
+static int perf_counter_refresh(struct perf_counter *counter, int refresh)
+{
+	/*
+	 * not supported on inherited counters
+	 */
+	if (counter->attr.inherit)
+		return -EINVAL;
+
+	atomic_add(refresh, &counter->event_limit);
+	perf_counter_enable(counter);
+
+	return 0;
+}
+
+void __perf_counter_sched_out(struct perf_counter_context *ctx,
+			      struct perf_cpu_context *cpuctx)
+{
+	struct perf_counter *counter;
+
+	spin_lock(&ctx->lock);
+	ctx->is_active = 0;
+	if (likely(!ctx->nr_counters))
+		goto out;
+	update_context_time(ctx);
+
+	perf_disable();
+	if (ctx->nr_active) {
+		list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+			if (counter != counter->group_leader)
+				counter_sched_out(counter, cpuctx, ctx);
+			else
+				group_sched_out(counter, cpuctx, ctx);
+		}
+	}
+	perf_enable();
+ out:
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Test whether two contexts are equivalent, i.e. whether they
+ * have both been cloned from the same version of the same context
+ * and they both have the same number of enabled counters.
+ * If the number of enabled counters is the same, then the set
+ * of enabled counters should be the same, because these are both
+ * inherited contexts, therefore we can't access individual counters
+ * in them directly with an fd; we can only enable/disable all
+ * counters via prctl, or enable/disable all counters in a family
+ * via ioctl, which will have the same effect on both contexts.
+ */
+static int context_equiv(struct perf_counter_context *ctx1,
+			 struct perf_counter_context *ctx2)
+{
+	return ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx
+		&& ctx1->parent_gen == ctx2->parent_gen
+		&& !ctx1->pin_count && !ctx2->pin_count;
+}
+
+/*
+ * Called from scheduler to remove the counters of the current task,
+ * with interrupts disabled.
+ *
+ * We stop each counter and update the counter value in counter->count.
+ *
+ * This does not protect us against NMI, but disable()
+ * sets the disabled bit in the control field of counter _before_
+ * accessing the counter control register. If a NMI hits, then it will
+ * not restart the counter.
+ */
+void perf_counter_task_sched_out(struct task_struct *task,
+				 struct task_struct *next, int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct perf_counter_context *ctx = task->perf_counter_ctxp;
+	struct perf_counter_context *next_ctx;
+	struct perf_counter_context *parent;
+	struct pt_regs *regs;
+	int do_switch = 1;
+
+	regs = task_pt_regs(task);
+	perf_swcounter_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
+
+	if (likely(!ctx || !cpuctx->task_ctx))
+		return;
+
+	update_context_time(ctx);
+
+	rcu_read_lock();
+	parent = rcu_dereference(ctx->parent_ctx);
+	next_ctx = next->perf_counter_ctxp;
+	if (parent && next_ctx &&
+	    rcu_dereference(next_ctx->parent_ctx) == parent) {
+		/*
+		 * Looks like the two contexts are clones, so we might be
+		 * able to optimize the context switch.  We lock both
+		 * contexts and check that they are clones under the
+		 * lock (including re-checking that neither has been
+		 * uncloned in the meantime).  It doesn't matter which
+		 * order we take the locks because no other cpu could
+		 * be trying to lock both of these tasks.
+		 */
+		spin_lock(&ctx->lock);
+		spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
+		if (context_equiv(ctx, next_ctx)) {
+			/*
+			 * XXX do we need a memory barrier of sorts
+			 * wrt to rcu_dereference() of perf_counter_ctxp
+			 */
+			task->perf_counter_ctxp = next_ctx;
+			next->perf_counter_ctxp = ctx;
+			ctx->task = next;
+			next_ctx->task = task;
+			do_switch = 0;
+		}
+		spin_unlock(&next_ctx->lock);
+		spin_unlock(&ctx->lock);
+	}
+	rcu_read_unlock();
+
+	if (do_switch) {
+		__perf_counter_sched_out(ctx, cpuctx);
+		cpuctx->task_ctx = NULL;
+	}
+}
+
+/*
+ * Called with IRQs disabled
+ */
+static void __perf_counter_task_sched_out(struct perf_counter_context *ctx)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+
+	if (!cpuctx->task_ctx)
+		return;
+
+	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
+		return;
+
+	__perf_counter_sched_out(ctx, cpuctx);
+	cpuctx->task_ctx = NULL;
+}
+
+/*
+ * Called with IRQs disabled
+ */
+static void perf_counter_cpu_sched_out(struct perf_cpu_context *cpuctx)
+{
+	__perf_counter_sched_out(&cpuctx->ctx, cpuctx);
+}
+
+static void
+__perf_counter_sched_in(struct perf_counter_context *ctx,
+			struct perf_cpu_context *cpuctx, int cpu)
+{
+	struct perf_counter *counter;
+	int can_add_hw = 1;
+
+	spin_lock(&ctx->lock);
+	ctx->is_active = 1;
+	if (likely(!ctx->nr_counters))
+		goto out;
+
+	ctx->timestamp = perf_clock();
+
+	perf_disable();
+
+	/*
+	 * First go through the list and put on any pinned groups
+	 * in order to give them the best chance of going on.
+	 */
+	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+		if (counter->state <= PERF_COUNTER_STATE_OFF ||
+		    !counter->attr.pinned)
+			continue;
+		if (counter->cpu != -1 && counter->cpu != cpu)
+			continue;
+
+		if (counter != counter->group_leader)
+			counter_sched_in(counter, cpuctx, ctx, cpu);
+		else {
+			if (group_can_go_on(counter, cpuctx, 1))
+				group_sched_in(counter, cpuctx, ctx, cpu);
+		}
+
+		/*
+		 * If this pinned group hasn't been scheduled,
+		 * put it in error state.
+		 */
+		if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
+			update_group_times(counter);
+			counter->state = PERF_COUNTER_STATE_ERROR;
+		}
+	}
+
+	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+		/*
+		 * Ignore counters in OFF or ERROR state, and
+		 * ignore pinned counters since we did them already.
+		 */
+		if (counter->state <= PERF_COUNTER_STATE_OFF ||
+		    counter->attr.pinned)
+			continue;
+
+		/*
+		 * Listen to the 'cpu' scheduling filter constraint
+		 * of counters:
+		 */
+		if (counter->cpu != -1 && counter->cpu != cpu)
+			continue;
+
+		if (counter != counter->group_leader) {
+			if (counter_sched_in(counter, cpuctx, ctx, cpu))
+				can_add_hw = 0;
+		} else {
+			if (group_can_go_on(counter, cpuctx, can_add_hw)) {
+				if (group_sched_in(counter, cpuctx, ctx, cpu))
+					can_add_hw = 0;
+			}
+		}
+	}
+	perf_enable();
+ out:
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Called from scheduler to add the counters of the current task
+ * with interrupts disabled.
+ *
+ * We restore the counter value and then enable it.
+ *
+ * This does not protect us against NMI, but enable()
+ * sets the enabled bit in the control field of counter _before_
+ * accessing the counter control register. If a NMI hits, then it will
+ * keep the counter running.
+ */
+void perf_counter_task_sched_in(struct task_struct *task, int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct perf_counter_context *ctx = task->perf_counter_ctxp;
+
+	if (likely(!ctx))
+		return;
+	if (cpuctx->task_ctx == ctx)
+		return;
+	__perf_counter_sched_in(ctx, cpuctx, cpu);
+	cpuctx->task_ctx = ctx;
+}
+
+static void perf_counter_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu)
+{
+	struct perf_counter_context *ctx = &cpuctx->ctx;
+
+	__perf_counter_sched_in(ctx, cpuctx, cpu);
+}
+
+#define MAX_INTERRUPTS (~0ULL)
+
+static void perf_log_throttle(struct perf_counter *counter, int enable);
+static void perf_log_period(struct perf_counter *counter, u64 period);
+
+static void perf_adjust_period(struct perf_counter *counter, u64 events)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+	u64 period, sample_period;
+	s64 delta;
+
+	events *= hwc->sample_period;
+	period = div64_u64(events, counter->attr.sample_freq);
+
+	delta = (s64)(period - hwc->sample_period);
+	delta = (delta + 7) / 8; /* low pass filter */
+
+	sample_period = hwc->sample_period + delta;
+
+	if (!sample_period)
+		sample_period = 1;
+
+	perf_log_period(counter, sample_period);
+
+	hwc->sample_period = sample_period;
+}
+
+static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
+{
+	struct perf_counter *counter;
+	struct hw_perf_counter *hwc;
+	u64 interrupts, freq;
+
+	spin_lock(&ctx->lock);
+	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+		if (counter->state != PERF_COUNTER_STATE_ACTIVE)
+			continue;
+
+		hwc = &counter->hw;
+
+		interrupts = hwc->interrupts;
+		hwc->interrupts = 0;
+
+		/*
+		 * unthrottle counters on the tick
+		 */
+		if (interrupts == MAX_INTERRUPTS) {
+			perf_log_throttle(counter, 1);
+			counter->pmu->unthrottle(counter);
+			interrupts = 2*sysctl_perf_counter_sample_rate/HZ;
+		}
+
+		if (!counter->attr.freq || !counter->attr.sample_freq)
+			continue;
+
+		/*
+		 * if the specified freq < HZ then we need to skip ticks
+		 */
+		if (counter->attr.sample_freq < HZ) {
+			freq = counter->attr.sample_freq;
+
+			hwc->freq_count += freq;
+			hwc->freq_interrupts += interrupts;
+
+			if (hwc->freq_count < HZ)
+				continue;
+
+			interrupts = hwc->freq_interrupts;
+			hwc->freq_interrupts = 0;
+			hwc->freq_count -= HZ;
+		} else
+			freq = HZ;
+
+		perf_adjust_period(counter, freq * interrupts);
+
+		/*
+		 * In order to avoid being stalled by an (accidental) huge
+		 * sample period, force reset the sample period if we didn't
+		 * get any events in this freq period.
+		 */
+		if (!interrupts) {
+			perf_disable();
+			counter->pmu->disable(counter);
+			atomic_set(&hwc->period_left, 0);
+			counter->pmu->enable(counter);
+			perf_enable();
+		}
+	}
+	spin_unlock(&ctx->lock);
+}
+
+/*
+ * Round-robin a context's counters:
+ */
+static void rotate_ctx(struct perf_counter_context *ctx)
+{
+	struct perf_counter *counter;
+
+	if (!ctx->nr_counters)
+		return;
+
+	spin_lock(&ctx->lock);
+	/*
+	 * Rotate the first entry last (works just fine for group counters too):
+	 */
+	perf_disable();
+	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+		list_move_tail(&counter->list_entry, &ctx->counter_list);
+		break;
+	}
+	perf_enable();
+
+	spin_unlock(&ctx->lock);
+}
+
+void perf_counter_task_tick(struct task_struct *curr, int cpu)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_counter_context *ctx;
+
+	if (!atomic_read(&nr_counters))
+		return;
+
+	cpuctx = &per_cpu(perf_cpu_context, cpu);
+	ctx = curr->perf_counter_ctxp;
+
+	perf_ctx_adjust_freq(&cpuctx->ctx);
+	if (ctx)
+		perf_ctx_adjust_freq(ctx);
+
+	perf_counter_cpu_sched_out(cpuctx);
+	if (ctx)
+		__perf_counter_task_sched_out(ctx);
+
+	rotate_ctx(&cpuctx->ctx);
+	if (ctx)
+		rotate_ctx(ctx);
+
+	perf_counter_cpu_sched_in(cpuctx, cpu);
+	if (ctx)
+		perf_counter_task_sched_in(curr, cpu);
+}
+
+/*
+ * Cross CPU call to read the hardware counter
+ */
+static void __read(void *info)
+{
+	struct perf_counter *counter = info;
+	struct perf_counter_context *ctx = counter->ctx;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (ctx->is_active)
+		update_context_time(ctx);
+	counter->pmu->read(counter);
+	update_counter_times(counter);
+	local_irq_restore(flags);
+}
+
+static u64 perf_counter_read(struct perf_counter *counter)
+{
+	/*
+	 * If counter is enabled and currently active on a CPU, update the
+	 * value in the counter structure:
+	 */
+	if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
+		smp_call_function_single(counter->oncpu,
+					 __read, counter, 1);
+	} else if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
+		update_counter_times(counter);
+	}
+
+	return atomic64_read(&counter->count);
+}
+
+/*
+ * Initialize the perf_counter context in a task_struct:
+ */
+static void
+__perf_counter_init_context(struct perf_counter_context *ctx,
+			    struct task_struct *task)
+{
+	memset(ctx, 0, sizeof(*ctx));
+	spin_lock_init(&ctx->lock);
+	mutex_init(&ctx->mutex);
+	INIT_LIST_HEAD(&ctx->counter_list);
+	INIT_LIST_HEAD(&ctx->event_list);
+	atomic_set(&ctx->refcount, 1);
+	ctx->task = task;
+}
+
+static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
+{
+	struct perf_counter_context *parent_ctx;
+	struct perf_counter_context *ctx;
+	struct perf_cpu_context *cpuctx;
+	struct task_struct *task;
+	unsigned long flags;
+	int err;
+
+	/*
+	 * If cpu is not a wildcard then this is a percpu counter:
+	 */
+	if (cpu != -1) {
+		/* Must be root to operate on a CPU counter: */
+		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+			return ERR_PTR(-EACCES);
+
+		if (cpu < 0 || cpu > num_possible_cpus())
+			return ERR_PTR(-EINVAL);
+
+		/*
+		 * We could be clever and allow to attach a counter to an
+		 * offline CPU and activate it when the CPU comes up, but
+		 * that's for later.
+		 */
+		if (!cpu_isset(cpu, cpu_online_map))
+			return ERR_PTR(-ENODEV);
+
+		cpuctx = &per_cpu(perf_cpu_context, cpu);
+		ctx = &cpuctx->ctx;
+		get_ctx(ctx);
+
+		return ctx;
+	}
+
+	rcu_read_lock();
+	if (!pid)
+		task = current;
+	else
+		task = find_task_by_vpid(pid);
+	if (task)
+		get_task_struct(task);
+	rcu_read_unlock();
+
+	if (!task)
+		return ERR_PTR(-ESRCH);
+
+	/*
+	 * Can't attach counters to a dying task.
+	 */
+	err = -ESRCH;
+	if (task->flags & PF_EXITING)
+		goto errout;
+
+	/* Reuse ptrace permission checks for now. */
+	err = -EACCES;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto errout;
+
+ retry:
+	ctx = perf_lock_task_context(task, &flags);
+	if (ctx) {
+		parent_ctx = ctx->parent_ctx;
+		if (parent_ctx) {
+			put_ctx(parent_ctx);
+			ctx->parent_ctx = NULL;		/* no longer a clone */
+		}
+		/*
+		 * Get an extra reference before dropping the lock so that
+		 * this context won't get freed if the task exits.
+		 */
+		get_ctx(ctx);
+		spin_unlock_irqrestore(&ctx->lock, flags);
+	}
+
+	if (!ctx) {
+		ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL);
+		err = -ENOMEM;
+		if (!ctx)
+			goto errout;
+		__perf_counter_init_context(ctx, task);
+		get_ctx(ctx);
+		if (cmpxchg(&task->perf_counter_ctxp, NULL, ctx)) {
+			/*
+			 * We raced with some other task; use
+			 * the context they set.
+			 */
+			kfree(ctx);
+			goto retry;
+		}
+		get_task_struct(task);
+	}
+
+	put_task_struct(task);
+	return ctx;
+
+ errout:
+	put_task_struct(task);
+	return ERR_PTR(err);
+}
+
+static void free_counter_rcu(struct rcu_head *head)
+{
+	struct perf_counter *counter;
+
+	counter = container_of(head, struct perf_counter, rcu_head);
+	if (counter->ns)
+		put_pid_ns(counter->ns);
+	kfree(counter);
+}
+
+static void perf_pending_sync(struct perf_counter *counter);
+
+static void free_counter(struct perf_counter *counter)
+{
+	perf_pending_sync(counter);
+
+	atomic_dec(&nr_counters);
+	if (counter->attr.mmap)
+		atomic_dec(&nr_mmap_counters);
+	if (counter->attr.comm)
+		atomic_dec(&nr_comm_counters);
+
+	if (counter->destroy)
+		counter->destroy(counter);
+
+	put_ctx(counter->ctx);
+	call_rcu(&counter->rcu_head, free_counter_rcu);
+}
+
+/*
+ * Called when the last reference to the file is gone.
+ */
+static int perf_release(struct inode *inode, struct file *file)
+{
+	struct perf_counter *counter = file->private_data;
+	struct perf_counter_context *ctx = counter->ctx;
+
+	file->private_data = NULL;
+
+	WARN_ON_ONCE(ctx->parent_ctx);
+	mutex_lock(&ctx->mutex);
+	perf_counter_remove_from_context(counter);
+	mutex_unlock(&ctx->mutex);
+
+	mutex_lock(&counter->owner->perf_counter_mutex);
+	list_del_init(&counter->owner_entry);
+	mutex_unlock(&counter->owner->perf_counter_mutex);
+	put_task_struct(counter->owner);
+
+	free_counter(counter);
+
+	return 0;
+}
+
+/*
+ * Read the performance counter - simple non blocking version for now
+ */
+static ssize_t
+perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
+{
+	u64 values[3];
+	int n;
+
+	/*
+	 * Return end-of-file for a read on a counter that is in
+	 * error state (i.e. because it was pinned but it couldn't be
+	 * scheduled on to the CPU at some point).
+	 */
+	if (counter->state == PERF_COUNTER_STATE_ERROR)
+		return 0;
+
+	WARN_ON_ONCE(counter->ctx->parent_ctx);
+	mutex_lock(&counter->child_mutex);
+	values[0] = perf_counter_read(counter);
+	n = 1;
+	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		values[n++] = counter->total_time_enabled +
+			atomic64_read(&counter->child_total_time_enabled);
+	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		values[n++] = counter->total_time_running +
+			atomic64_read(&counter->child_total_time_running);
+	if (counter->attr.read_format & PERF_FORMAT_ID)
+		values[n++] = counter->id;
+	mutex_unlock(&counter->child_mutex);
+
+	if (count < n * sizeof(u64))
+		return -EINVAL;
+	count = n * sizeof(u64);
+
+	if (copy_to_user(buf, values, count))
+		return -EFAULT;
+
+	return count;
+}
+
+static ssize_t
+perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	struct perf_counter *counter = file->private_data;
+
+	return perf_read_hw(counter, buf, count);
+}
+
+static unsigned int perf_poll(struct file *file, poll_table *wait)
+{
+	struct perf_counter *counter = file->private_data;
+	struct perf_mmap_data *data;
+	unsigned int events = POLL_HUP;
+
+	rcu_read_lock();
+	data = rcu_dereference(counter->data);
+	if (data)
+		events = atomic_xchg(&data->poll, 0);
+	rcu_read_unlock();
+
+	poll_wait(file, &counter->waitq, wait);
+
+	return events;
+}
+
+static void perf_counter_reset(struct perf_counter *counter)
+{
+	(void)perf_counter_read(counter);
+	atomic64_set(&counter->count, 0);
+	perf_counter_update_userpage(counter);
+}
+
+static void perf_counter_for_each_sibling(struct perf_counter *counter,
+					  void (*func)(struct perf_counter *))
+{
+	struct perf_counter_context *ctx = counter->ctx;
+	struct perf_counter *sibling;
+
+	WARN_ON_ONCE(ctx->parent_ctx);
+	mutex_lock(&ctx->mutex);
+	counter = counter->group_leader;
+
+	func(counter);
+	list_for_each_entry(sibling, &counter->sibling_list, list_entry)
+		func(sibling);
+	mutex_unlock(&ctx->mutex);
+}
+
+/*
+ * Holding the top-level counter's child_mutex means that any
+ * descendant process that has inherited this counter will block
+ * in sync_child_counter if it goes to exit, thus satisfying the
+ * task existence requirements of perf_counter_enable/disable.
+ */
+static void perf_counter_for_each_child(struct perf_counter *counter,
+					void (*func)(struct perf_counter *))
+{
+	struct perf_counter *child;
+
+	WARN_ON_ONCE(counter->ctx->parent_ctx);
+	mutex_lock(&counter->child_mutex);
+	func(counter);
+	list_for_each_entry(child, &counter->child_list, child_list)
+		func(child);
+	mutex_unlock(&counter->child_mutex);
+}
+
+static void perf_counter_for_each(struct perf_counter *counter,
+				  void (*func)(struct perf_counter *))
+{
+	struct perf_counter *child;
+
+	WARN_ON_ONCE(counter->ctx->parent_ctx);
+	mutex_lock(&counter->child_mutex);
+	perf_counter_for_each_sibling(counter, func);
+	list_for_each_entry(child, &counter->child_list, child_list)
+		perf_counter_for_each_sibling(child, func);
+	mutex_unlock(&counter->child_mutex);
+}
+
+static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
+{
+	struct perf_counter_context *ctx = counter->ctx;
+	unsigned long size;
+	int ret = 0;
+	u64 value;
+
+	if (!counter->attr.sample_period)
+		return -EINVAL;
+
+	size = copy_from_user(&value, arg, sizeof(value));
+	if (size != sizeof(value))
+		return -EFAULT;
+
+	if (!value)
+		return -EINVAL;
+
+	spin_lock_irq(&ctx->lock);
+	if (counter->attr.freq) {
+		if (value > sysctl_perf_counter_sample_rate) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+
+		counter->attr.sample_freq = value;
+	} else {
+		perf_log_period(counter, value);
+
+		counter->attr.sample_period = value;
+		counter->hw.sample_period = value;
+	}
+unlock:
+	spin_unlock_irq(&ctx->lock);
+
+	return ret;
+}
+
+static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct perf_counter *counter = file->private_data;
+	void (*func)(struct perf_counter *);
+	u32 flags = arg;
+
+	switch (cmd) {
+	case PERF_COUNTER_IOC_ENABLE:
+		func = perf_counter_enable;
+		break;
+	case PERF_COUNTER_IOC_DISABLE:
+		func = perf_counter_disable;
+		break;
+	case PERF_COUNTER_IOC_RESET:
+		func = perf_counter_reset;
+		break;
+
+	case PERF_COUNTER_IOC_REFRESH:
+		return perf_counter_refresh(counter, arg);
+
+	case PERF_COUNTER_IOC_PERIOD:
+		return perf_counter_period(counter, (u64 __user *)arg);
+
+	default:
+		return -ENOTTY;
+	}
+
+	if (flags & PERF_IOC_FLAG_GROUP)
+		perf_counter_for_each(counter, func);
+	else
+		perf_counter_for_each_child(counter, func);
+
+	return 0;
+}
+
+int perf_counter_task_enable(void)
+{
+	struct perf_counter *counter;
+
+	mutex_lock(&current->perf_counter_mutex);
+	list_for_each_entry(counter, &current->perf_counter_list, owner_entry)
+		perf_counter_for_each_child(counter, perf_counter_enable);
+	mutex_unlock(&current->perf_counter_mutex);
+
+	return 0;
+}
+
+int perf_counter_task_disable(void)
+{
+	struct perf_counter *counter;
+
+	mutex_lock(&current->perf_counter_mutex);
+	list_for_each_entry(counter, &current->perf_counter_list, owner_entry)
+		perf_counter_for_each_child(counter, perf_counter_disable);
+	mutex_unlock(&current->perf_counter_mutex);
+
+	return 0;
+}
+
+/*
+ * Callers need to ensure there can be no nesting of this function, otherwise
+ * the seqlock logic goes bad. We can not serialize this because the arch
+ * code calls this from NMI context.
+ */
+void perf_counter_update_userpage(struct perf_counter *counter)
+{
+	struct perf_counter_mmap_page *userpg;
+	struct perf_mmap_data *data;
+
+	rcu_read_lock();
+	data = rcu_dereference(counter->data);
+	if (!data)
+		goto unlock;
+
+	userpg = data->user_page;
+
+	/*
+	 * Disable preemption so as to not let the corresponding user-space
+	 * spin too long if we get preempted.
+	 */
+	preempt_disable();
+	++userpg->lock;
+	barrier();
+	userpg->index = counter->hw.idx;
+	userpg->offset = atomic64_read(&counter->count);
+	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
+		userpg->offset -= atomic64_read(&counter->hw.prev_count);
+
+	barrier();
+	++userpg->lock;
+	preempt_enable();
+unlock:
+	rcu_read_unlock();
+}
+
+static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct perf_counter *counter = vma->vm_file->private_data;
+	struct perf_mmap_data *data;
+	int ret = VM_FAULT_SIGBUS;
+
+	rcu_read_lock();
+	data = rcu_dereference(counter->data);
+	if (!data)
+		goto unlock;
+
+	if (vmf->pgoff == 0) {
+		vmf->page = virt_to_page(data->user_page);
+	} else {
+		int nr = vmf->pgoff - 1;
+
+		if ((unsigned)nr > data->nr_pages)
+			goto unlock;
+
+		vmf->page = virt_to_page(data->data_pages[nr]);
+	}
+	get_page(vmf->page);
+	ret = 0;
+unlock:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int perf_mmap_data_alloc(struct perf_counter *counter, int nr_pages)
+{
+	struct perf_mmap_data *data;
+	unsigned long size;
+	int i;
+
+	WARN_ON(atomic_read(&counter->mmap_count));
+
+	size = sizeof(struct perf_mmap_data);
+	size += nr_pages * sizeof(void *);
+
+	data = kzalloc(size, GFP_KERNEL);
+	if (!data)
+		goto fail;
+
+	data->user_page = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!data->user_page)
+		goto fail_user_page;
+
+	for (i = 0; i < nr_pages; i++) {
+		data->data_pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
+		if (!data->data_pages[i])
+			goto fail_data_pages;
+	}
+
+	data->nr_pages = nr_pages;
+	atomic_set(&data->lock, -1);
+
+	rcu_assign_pointer(counter->data, data);
+
+	return 0;
+
+fail_data_pages:
+	for (i--; i >= 0; i--)
+		free_page((unsigned long)data->data_pages[i]);
+
+	free_page((unsigned long)data->user_page);
+
+fail_user_page:
+	kfree(data);
+
+fail:
+	return -ENOMEM;
+}
+
+static void __perf_mmap_data_free(struct rcu_head *rcu_head)
+{
+	struct perf_mmap_data *data;
+	int i;
+
+	data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
+
+	free_page((unsigned long)data->user_page);
+	for (i = 0; i < data->nr_pages; i++)
+		free_page((unsigned long)data->data_pages[i]);
+	kfree(data);
+}
+
+static void perf_mmap_data_free(struct perf_counter *counter)
+{
+	struct perf_mmap_data *data = counter->data;
+
+	WARN_ON(atomic_read(&counter->mmap_count));
+
+	rcu_assign_pointer(counter->data, NULL);
+	call_rcu(&data->rcu_head, __perf_mmap_data_free);
+}
+
+static void perf_mmap_open(struct vm_area_struct *vma)
+{
+	struct perf_counter *counter = vma->vm_file->private_data;
+
+	atomic_inc(&counter->mmap_count);
+}
+
+static void perf_mmap_close(struct vm_area_struct *vma)
+{
+	struct perf_counter *counter = vma->vm_file->private_data;
+
+	WARN_ON_ONCE(counter->ctx->parent_ctx);
+	if (atomic_dec_and_mutex_lock(&counter->mmap_count, &counter->mmap_mutex)) {
+		struct user_struct *user = current_user();
+
+		atomic_long_sub(counter->data->nr_pages + 1, &user->locked_vm);
+		vma->vm_mm->locked_vm -= counter->data->nr_locked;
+		perf_mmap_data_free(counter);
+		mutex_unlock(&counter->mmap_mutex);
+	}
+}
+
+static struct vm_operations_struct perf_mmap_vmops = {
+	.open  = perf_mmap_open,
+	.close = perf_mmap_close,
+	.fault = perf_mmap_fault,
+};
+
+static int perf_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct perf_counter *counter = file->private_data;
+	unsigned long user_locked, user_lock_limit;
+	struct user_struct *user = current_user();
+	unsigned long locked, lock_limit;
+	unsigned long vma_size;
+	unsigned long nr_pages;
+	long user_extra, extra;
+	int ret = 0;
+
+	if (!(vma->vm_flags & VM_SHARED) || (vma->vm_flags & VM_WRITE))
+		return -EINVAL;
+
+	vma_size = vma->vm_end - vma->vm_start;
+	nr_pages = (vma_size / PAGE_SIZE) - 1;
+
+	/*
+	 * If we have data pages ensure they're a power-of-two number, so we
+	 * can do bitmasks instead of modulo.
+	 */
+	if (nr_pages != 0 && !is_power_of_2(nr_pages))
+		return -EINVAL;
+
+	if (vma_size != PAGE_SIZE * (1 + nr_pages))
+		return -EINVAL;
+
+	if (vma->vm_pgoff != 0)
+		return -EINVAL;
+
+	WARN_ON_ONCE(counter->ctx->parent_ctx);
+	mutex_lock(&counter->mmap_mutex);
+	if (atomic_inc_not_zero(&counter->mmap_count)) {
+		if (nr_pages != counter->data->nr_pages)
+			ret = -EINVAL;
+		goto unlock;
+	}
+
+	user_extra = nr_pages + 1;
+	user_lock_limit = sysctl_perf_counter_mlock >> (PAGE_SHIFT - 10);
+
+	/*
+	 * Increase the limit linearly with more CPUs:
+	 */
+	user_lock_limit *= num_online_cpus();
+
+	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
+
+	extra = 0;
+	if (user_locked > user_lock_limit)
+		extra = user_locked - user_lock_limit;
+
+	lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+	lock_limit >>= PAGE_SHIFT;
+	locked = vma->vm_mm->locked_vm + extra;
+
+	if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	WARN_ON(counter->data);
+	ret = perf_mmap_data_alloc(counter, nr_pages);
+	if (ret)
+		goto unlock;
+
+	atomic_set(&counter->mmap_count, 1);
+	atomic_long_add(user_extra, &user->locked_vm);
+	vma->vm_mm->locked_vm += extra;
+	counter->data->nr_locked = extra;
+unlock:
+	mutex_unlock(&counter->mmap_mutex);
+
+	vma->vm_flags &= ~VM_MAYWRITE;
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_ops = &perf_mmap_vmops;
+
+	return ret;
+}
+
+static int perf_fasync(int fd, struct file *filp, int on)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct perf_counter *counter = filp->private_data;
+	int retval;
+
+	mutex_lock(&inode->i_mutex);
+	retval = fasync_helper(fd, filp, on, &counter->fasync);
+	mutex_unlock(&inode->i_mutex);
+
+	if (retval < 0)
+		return retval;
+
+	return 0;
+}
+
+static const struct file_operations perf_fops = {
+	.release		= perf_release,
+	.read			= perf_read,
+	.poll			= perf_poll,
+	.unlocked_ioctl		= perf_ioctl,
+	.compat_ioctl		= perf_ioctl,
+	.mmap			= perf_mmap,
+	.fasync			= perf_fasync,
+};
+
+/*
+ * Perf counter wakeup
+ *
+ * If there's data, ensure we set the poll() state and publish everything
+ * to user-space before waking everybody up.
+ */
+
+void perf_counter_wakeup(struct perf_counter *counter)
+{
+	wake_up_all(&counter->waitq);
+
+	if (counter->pending_kill) {
+		kill_fasync(&counter->fasync, SIGIO, counter->pending_kill);
+		counter->pending_kill = 0;
+	}
+}
+
+/*
+ * Pending wakeups
+ *
+ * Handle the case where we need to wakeup up from NMI (or rq->lock) context.
+ *
+ * The NMI bit means we cannot possibly take locks. Therefore, maintain a
+ * single linked list and use cmpxchg() to add entries lockless.
+ */
+
+static void perf_pending_counter(struct perf_pending_entry *entry)
+{
+	struct perf_counter *counter = container_of(entry,
+			struct perf_counter, pending);
+
+	if (counter->pending_disable) {
+		counter->pending_disable = 0;
+		perf_counter_disable(counter);
+	}
+
+	if (counter->pending_wakeup) {
+		counter->pending_wakeup = 0;
+		perf_counter_wakeup(counter);
+	}
+}
+
+#define PENDING_TAIL ((struct perf_pending_entry *)-1UL)
+
+static DEFINE_PER_CPU(struct perf_pending_entry *, perf_pending_head) = {
+	PENDING_TAIL,
+};
+
+static void perf_pending_queue(struct perf_pending_entry *entry,
+			       void (*func)(struct perf_pending_entry *))
+{
+	struct perf_pending_entry **head;
+
+	if (cmpxchg(&entry->next, NULL, PENDING_TAIL) != NULL)
+		return;
+
+	entry->func = func;
+
+	head = &get_cpu_var(perf_pending_head);
+
+	do {
+		entry->next = *head;
+	} while (cmpxchg(head, entry->next, entry) != entry->next);
+
+	set_perf_counter_pending();
+
+	put_cpu_var(perf_pending_head);
+}
+
+static int __perf_pending_run(void)
+{
+	struct perf_pending_entry *list;
+	int nr = 0;
+
+	list = xchg(&__get_cpu_var(perf_pending_head), PENDING_TAIL);
+	while (list != PENDING_TAIL) {
+		void (*func)(struct perf_pending_entry *);
+		struct perf_pending_entry *entry = list;
+
+		list = list->next;
+
+		func = entry->func;
+		entry->next = NULL;
+		/*
+		 * Ensure we observe the unqueue before we issue the wakeup,
+		 * so that we won't be waiting forever.
+		 * -- see perf_not_pending().
+		 */
+		smp_wmb();
+
+		func(entry);
+		nr++;
+	}
+
+	return nr;
+}
+
+static inline int perf_not_pending(struct perf_counter *counter)
+{
+	/*
+	 * If we flush on whatever cpu we run, there is a chance we don't
+	 * need to wait.
+	 */
+	get_cpu();
+	__perf_pending_run();
+	put_cpu();
+
+	/*
+	 * Ensure we see the proper queue state before going to sleep
+	 * so that we do not miss the wakeup. -- see perf_pending_handle()
+	 */
+	smp_rmb();
+	return counter->pending.next == NULL;
+}
+
+static void perf_pending_sync(struct perf_counter *counter)
+{
+	wait_event(counter->waitq, perf_not_pending(counter));
+}
+
+void perf_counter_do_pending(void)
+{
+	__perf_pending_run();
+}
+
+/*
+ * Callchain support -- arch specific
+ */
+
+__weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	return NULL;
+}
+
+/*
+ * Output
+ */
+
+struct perf_output_handle {
+	struct perf_counter	*counter;
+	struct perf_mmap_data	*data;
+	unsigned long		head;
+	unsigned long		offset;
+	int			nmi;
+	int			overflow;
+	int			locked;
+	unsigned long		flags;
+};
+
+static void perf_output_wakeup(struct perf_output_handle *handle)
+{
+	atomic_set(&handle->data->poll, POLL_IN);
+
+	if (handle->nmi) {
+		handle->counter->pending_wakeup = 1;
+		perf_pending_queue(&handle->counter->pending,
+				   perf_pending_counter);
+	} else
+		perf_counter_wakeup(handle->counter);
+}
+
+/*
+ * Curious locking construct.
+ *
+ * We need to ensure a later event doesn't publish a head when a former
+ * event isn't done writing. However since we need to deal with NMIs we
+ * cannot fully serialize things.
+ *
+ * What we do is serialize between CPUs so we only have to deal with NMI
+ * nesting on a single CPU.
+ *
+ * We only publish the head (and generate a wakeup) when the outer-most
+ * event completes.
+ */
+static void perf_output_lock(struct perf_output_handle *handle)
+{
+	struct perf_mmap_data *data = handle->data;
+	int cpu;
+
+	handle->locked = 0;
+
+	local_irq_save(handle->flags);
+	cpu = smp_processor_id();
+
+	if (in_nmi() && atomic_read(&data->lock) == cpu)
+		return;
+
+	while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
+		cpu_relax();
+
+	handle->locked = 1;
+}
+
+static void perf_output_unlock(struct perf_output_handle *handle)
+{
+	struct perf_mmap_data *data = handle->data;
+	unsigned long head;
+	int cpu;
+
+	data->done_head = data->head;
+
+	if (!handle->locked)
+		goto out;
+
+again:
+	/*
+	 * The xchg implies a full barrier that ensures all writes are done
+	 * before we publish the new head, matched by a rmb() in userspace when
+	 * reading this position.
+	 */
+	while ((head = atomic_long_xchg(&data->done_head, 0)))
+		data->user_page->data_head = head;
+
+	/*
+	 * NMI can happen here, which means we can miss a done_head update.
+	 */
+
+	cpu = atomic_xchg(&data->lock, -1);
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
+	/*
+	 * Therefore we have to validate we did not indeed do so.
+	 */
+	if (unlikely(atomic_long_read(&data->done_head))) {
+		/*
+		 * Since we had it locked, we can lock it again.
+		 */
+		while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
+			cpu_relax();
+
+		goto again;
+	}
+
+	if (atomic_xchg(&data->wakeup, 0))
+		perf_output_wakeup(handle);
+out:
+	local_irq_restore(handle->flags);
+}
+
+static int perf_output_begin(struct perf_output_handle *handle,
+			     struct perf_counter *counter, unsigned int size,
+			     int nmi, int overflow)
+{
+	struct perf_mmap_data *data;
+	unsigned int offset, head;
+
+	/*
+	 * For inherited counters we send all the output towards the parent.
+	 */
+	if (counter->parent)
+		counter = counter->parent;
+
+	rcu_read_lock();
+	data = rcu_dereference(counter->data);
+	if (!data)
+		goto out;
+
+	handle->data	 = data;
+	handle->counter	 = counter;
+	handle->nmi	 = nmi;
+	handle->overflow = overflow;
+
+	if (!data->nr_pages)
+		goto fail;
+
+	perf_output_lock(handle);
+
+	do {
+		offset = head = atomic_long_read(&data->head);
+		head += size;
+	} while (atomic_long_cmpxchg(&data->head, offset, head) != offset);
+
+	handle->offset	= offset;
+	handle->head	= head;
+
+	if ((offset >> PAGE_SHIFT) != (head >> PAGE_SHIFT))
+		atomic_set(&data->wakeup, 1);
+
+	return 0;
+
+fail:
+	perf_output_wakeup(handle);
+out:
+	rcu_read_unlock();
+
+	return -ENOSPC;
+}
+
+static void perf_output_copy(struct perf_output_handle *handle,
+			     const void *buf, unsigned int len)
+{
+	unsigned int pages_mask;
+	unsigned int offset;
+	unsigned int size;
+	void **pages;
+
+	offset		= handle->offset;
+	pages_mask	= handle->data->nr_pages - 1;
+	pages		= handle->data->data_pages;
+
+	do {
+		unsigned int page_offset;
+		int nr;
+
+		nr	    = (offset >> PAGE_SHIFT) & pages_mask;
+		page_offset = offset & (PAGE_SIZE - 1);
+		size	    = min_t(unsigned int, PAGE_SIZE - page_offset, len);
+
+		memcpy(pages[nr] + page_offset, buf, size);
+
+		len	    -= size;
+		buf	    += size;
+		offset	    += size;
+	} while (len);
+
+	handle->offset = offset;
+
+	/*
+	 * Check we didn't copy past our reservation window, taking the
+	 * possible unsigned int wrap into account.
+	 */
+	WARN_ON_ONCE(((long)(handle->head - handle->offset)) < 0);
+}
+
+#define perf_output_put(handle, x) \
+	perf_output_copy((handle), &(x), sizeof(x))
+
+static void perf_output_end(struct perf_output_handle *handle)
+{
+	struct perf_counter *counter = handle->counter;
+	struct perf_mmap_data *data = handle->data;
+
+	int wakeup_events = counter->attr.wakeup_events;
+
+	if (handle->overflow && wakeup_events) {
+		int events = atomic_inc_return(&data->events);
+		if (events >= wakeup_events) {
+			atomic_sub(wakeup_events, &data->events);
+			atomic_set(&data->wakeup, 1);
+		}
+	}
+
+	perf_output_unlock(handle);
+	rcu_read_unlock();
+}
+
+static u32 perf_counter_pid(struct perf_counter *counter, struct task_struct *p)
+{
+	/*
+	 * only top level counters have the pid namespace they were created in
+	 */
+	if (counter->parent)
+		counter = counter->parent;
+
+	return task_tgid_nr_ns(p, counter->ns);
+}
+
+static u32 perf_counter_tid(struct perf_counter *counter, struct task_struct *p)
+{
+	/*
+	 * only top level counters have the pid namespace they were created in
+	 */
+	if (counter->parent)
+		counter = counter->parent;
+
+	return task_pid_nr_ns(p, counter->ns);
+}
+
+static void perf_counter_output(struct perf_counter *counter, int nmi,
+				struct perf_sample_data *data)
+{
+	int ret;
+	u64 sample_type = counter->attr.sample_type;
+	struct perf_output_handle handle;
+	struct perf_event_header header;
+	u64 ip;
+	struct {
+		u32 pid, tid;
+	} tid_entry;
+	struct {
+		u64 id;
+		u64 counter;
+	} group_entry;
+	struct perf_callchain_entry *callchain = NULL;
+	int callchain_size = 0;
+	u64 time;
+	struct {
+		u32 cpu, reserved;
+	} cpu_entry;
+
+	header.type = 0;
+	header.size = sizeof(header);
+
+	header.misc = PERF_EVENT_MISC_OVERFLOW;
+	header.misc |= perf_misc_flags(data->regs);
+
+	if (sample_type & PERF_SAMPLE_IP) {
+		ip = perf_instruction_pointer(data->regs);
+		header.type |= PERF_SAMPLE_IP;
+		header.size += sizeof(ip);
+	}
+
+	if (sample_type & PERF_SAMPLE_TID) {
+		/* namespace issues */
+		tid_entry.pid = perf_counter_pid(counter, current);
+		tid_entry.tid = perf_counter_tid(counter, current);
+
+		header.type |= PERF_SAMPLE_TID;
+		header.size += sizeof(tid_entry);
+	}
+
+	if (sample_type & PERF_SAMPLE_TIME) {
+		/*
+		 * Maybe do better on x86 and provide cpu_clock_nmi()
+		 */
+		time = sched_clock();
+
+		header.type |= PERF_SAMPLE_TIME;
+		header.size += sizeof(u64);
+	}
+
+	if (sample_type & PERF_SAMPLE_ADDR) {
+		header.type |= PERF_SAMPLE_ADDR;
+		header.size += sizeof(u64);
+	}
+
+	if (sample_type & PERF_SAMPLE_ID) {
+		header.type |= PERF_SAMPLE_ID;
+		header.size += sizeof(u64);
+	}
+
+	if (sample_type & PERF_SAMPLE_CPU) {
+		header.type |= PERF_SAMPLE_CPU;
+		header.size += sizeof(cpu_entry);
+
+		cpu_entry.cpu = raw_smp_processor_id();
+	}
+
+	if (sample_type & PERF_SAMPLE_PERIOD) {
+		header.type |= PERF_SAMPLE_PERIOD;
+		header.size += sizeof(u64);
+	}
+
+	if (sample_type & PERF_SAMPLE_GROUP) {
+		header.type |= PERF_SAMPLE_GROUP;
+		header.size += sizeof(u64) +
+			counter->nr_siblings * sizeof(group_entry);
+	}
+
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+		callchain = perf_callchain(data->regs);
+
+		if (callchain) {
+			callchain_size = (1 + callchain->nr) * sizeof(u64);
+
+			header.type |= PERF_SAMPLE_CALLCHAIN;
+			header.size += callchain_size;
+		}
+	}
+
+	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, header);
+
+	if (sample_type & PERF_SAMPLE_IP)
+		perf_output_put(&handle, ip);
+
+	if (sample_type & PERF_SAMPLE_TID)
+		perf_output_put(&handle, tid_entry);
+
+	if (sample_type & PERF_SAMPLE_TIME)
+		perf_output_put(&handle, time);
+
+	if (sample_type & PERF_SAMPLE_ADDR)
+		perf_output_put(&handle, data->addr);
+
+	if (sample_type & PERF_SAMPLE_ID)
+		perf_output_put(&handle, counter->id);
+
+	if (sample_type & PERF_SAMPLE_CPU)
+		perf_output_put(&handle, cpu_entry);
+
+	if (sample_type & PERF_SAMPLE_PERIOD)
+		perf_output_put(&handle, data->period);
+
+	/*
+	 * XXX PERF_SAMPLE_GROUP vs inherited counters seems difficult.
+	 */
+	if (sample_type & PERF_SAMPLE_GROUP) {
+		struct perf_counter *leader, *sub;
+		u64 nr = counter->nr_siblings;
+
+		perf_output_put(&handle, nr);
+
+		leader = counter->group_leader;
+		list_for_each_entry(sub, &leader->sibling_list, list_entry) {
+			if (sub != counter)
+				sub->pmu->read(sub);
+
+			group_entry.id = sub->id;
+			group_entry.counter = atomic64_read(&sub->count);
+
+			perf_output_put(&handle, group_entry);
+		}
+	}
+
+	if (callchain)
+		perf_output_copy(&handle, callchain, callchain_size);
+
+	perf_output_end(&handle);
+}
+
+/*
+ * fork tracking
+ */
+
+struct perf_fork_event {
+	struct task_struct	*task;
+
+	struct {
+		struct perf_event_header	header;
+
+		u32				pid;
+		u32				ppid;
+	} event;
+};
+
+static void perf_counter_fork_output(struct perf_counter *counter,
+				     struct perf_fork_event *fork_event)
+{
+	struct perf_output_handle handle;
+	int size = fork_event->event.header.size;
+	struct task_struct *task = fork_event->task;
+	int ret = perf_output_begin(&handle, counter, size, 0, 0);
+
+	if (ret)
+		return;
+
+	fork_event->event.pid = perf_counter_pid(counter, task);
+	fork_event->event.ppid = perf_counter_pid(counter, task->real_parent);
+
+	perf_output_put(&handle, fork_event->event);
+	perf_output_end(&handle);
+}
+
+static int perf_counter_fork_match(struct perf_counter *counter)
+{
+	if (counter->attr.comm || counter->attr.mmap)
+		return 1;
+
+	return 0;
+}
+
+static void perf_counter_fork_ctx(struct perf_counter_context *ctx,
+				  struct perf_fork_event *fork_event)
+{
+	struct perf_counter *counter;
+
+	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
+		if (perf_counter_fork_match(counter))
+			perf_counter_fork_output(counter, fork_event);
+	}
+	rcu_read_unlock();
+}
+
+static void perf_counter_fork_event(struct perf_fork_event *fork_event)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_counter_context *ctx;
+
+	cpuctx = &get_cpu_var(perf_cpu_context);
+	perf_counter_fork_ctx(&cpuctx->ctx, fork_event);
+	put_cpu_var(perf_cpu_context);
+
+	rcu_read_lock();
+	/*
+	 * doesn't really matter which of the child contexts the
+	 * events ends up in.
+	 */
+	ctx = rcu_dereference(current->perf_counter_ctxp);
+	if (ctx)
+		perf_counter_fork_ctx(ctx, fork_event);
+	rcu_read_unlock();
+}
+
+void perf_counter_fork(struct task_struct *task)
+{
+	struct perf_fork_event fork_event;
+
+	if (!atomic_read(&nr_comm_counters) &&
+	    !atomic_read(&nr_mmap_counters))
+		return;
+
+	fork_event = (struct perf_fork_event){
+		.task	= task,
+		.event  = {
+			.header = {
+				.type = PERF_EVENT_FORK,
+				.size = sizeof(fork_event.event),
+			},
+		},
+	};
+
+	perf_counter_fork_event(&fork_event);
+}
+
+/*
+ * comm tracking
+ */
+
+struct perf_comm_event {
+	struct task_struct	*task;
+	char			*comm;
+	int			comm_size;
+
+	struct {
+		struct perf_event_header	header;
+
+		u32				pid;
+		u32				tid;
+	} event;
+};
+
+static void perf_counter_comm_output(struct perf_counter *counter,
+				     struct perf_comm_event *comm_event)
+{
+	struct perf_output_handle handle;
+	int size = comm_event->event.header.size;
+	int ret = perf_output_begin(&handle, counter, size, 0, 0);
+
+	if (ret)
+		return;
+
+	comm_event->event.pid = perf_counter_pid(counter, comm_event->task);
+	comm_event->event.tid = perf_counter_tid(counter, comm_event->task);
+
+	perf_output_put(&handle, comm_event->event);
+	perf_output_copy(&handle, comm_event->comm,
+				   comm_event->comm_size);
+	perf_output_end(&handle);
+}
+
+static int perf_counter_comm_match(struct perf_counter *counter)
+{
+	if (counter->attr.comm)
+		return 1;
+
+	return 0;
+}
+
+static void perf_counter_comm_ctx(struct perf_counter_context *ctx,
+				  struct perf_comm_event *comm_event)
+{
+	struct perf_counter *counter;
+
+	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
+		if (perf_counter_comm_match(counter))
+			perf_counter_comm_output(counter, comm_event);
+	}
+	rcu_read_unlock();
+}
+
+static void perf_counter_comm_event(struct perf_comm_event *comm_event)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_counter_context *ctx;
+	unsigned int size;
+	char *comm = comm_event->task->comm;
+
+	size = ALIGN(strlen(comm)+1, sizeof(u64));
+
+	comm_event->comm = comm;
+	comm_event->comm_size = size;
+
+	comm_event->event.header.size = sizeof(comm_event->event) + size;
+
+	cpuctx = &get_cpu_var(perf_cpu_context);
+	perf_counter_comm_ctx(&cpuctx->ctx, comm_event);
+	put_cpu_var(perf_cpu_context);
+
+	rcu_read_lock();
+	/*
+	 * doesn't really matter which of the child contexts the
+	 * events ends up in.
+	 */
+	ctx = rcu_dereference(current->perf_counter_ctxp);
+	if (ctx)
+		perf_counter_comm_ctx(ctx, comm_event);
+	rcu_read_unlock();
+}
+
+void perf_counter_comm(struct task_struct *task)
+{
+	struct perf_comm_event comm_event;
+
+	if (!atomic_read(&nr_comm_counters))
+		return;
+
+	comm_event = (struct perf_comm_event){
+		.task	= task,
+		.event  = {
+			.header = { .type = PERF_EVENT_COMM, },
+		},
+	};
+
+	perf_counter_comm_event(&comm_event);
+}
+
+/*
+ * mmap tracking
+ */
+
+struct perf_mmap_event {
+	struct vm_area_struct	*vma;
+
+	const char		*file_name;
+	int			file_size;
+
+	struct {
+		struct perf_event_header	header;
+
+		u32				pid;
+		u32				tid;
+		u64				start;
+		u64				len;
+		u64				pgoff;
+	} event;
+};
+
+static void perf_counter_mmap_output(struct perf_counter *counter,
+				     struct perf_mmap_event *mmap_event)
+{
+	struct perf_output_handle handle;
+	int size = mmap_event->event.header.size;
+	int ret = perf_output_begin(&handle, counter, size, 0, 0);
+
+	if (ret)
+		return;
+
+	mmap_event->event.pid = perf_counter_pid(counter, current);
+	mmap_event->event.tid = perf_counter_tid(counter, current);
+
+	perf_output_put(&handle, mmap_event->event);
+	perf_output_copy(&handle, mmap_event->file_name,
+				   mmap_event->file_size);
+	perf_output_end(&handle);
+}
+
+static int perf_counter_mmap_match(struct perf_counter *counter,
+				   struct perf_mmap_event *mmap_event)
+{
+	if (counter->attr.mmap)
+		return 1;
+
+	return 0;
+}
+
+static void perf_counter_mmap_ctx(struct perf_counter_context *ctx,
+				  struct perf_mmap_event *mmap_event)
+{
+	struct perf_counter *counter;
+
+	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
+		if (perf_counter_mmap_match(counter, mmap_event))
+			perf_counter_mmap_output(counter, mmap_event);
+	}
+	rcu_read_unlock();
+}
+
+static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_counter_context *ctx;
+	struct vm_area_struct *vma = mmap_event->vma;
+	struct file *file = vma->vm_file;
+	unsigned int size;
+	char tmp[16];
+	char *buf = NULL;
+	const char *name;
+
+	if (file) {
+		buf = kzalloc(PATH_MAX, GFP_KERNEL);
+		if (!buf) {
+			name = strncpy(tmp, "//enomem", sizeof(tmp));
+			goto got_name;
+		}
+		name = d_path(&file->f_path, buf, PATH_MAX);
+		if (IS_ERR(name)) {
+			name = strncpy(tmp, "//toolong", sizeof(tmp));
+			goto got_name;
+		}
+	} else {
+		name = arch_vma_name(mmap_event->vma);
+		if (name)
+			goto got_name;
+
+		if (!vma->vm_mm) {
+			name = strncpy(tmp, "[vdso]", sizeof(tmp));
+			goto got_name;
+		}
+
+		name = strncpy(tmp, "//anon", sizeof(tmp));
+		goto got_name;
+	}
+
+got_name:
+	size = ALIGN(strlen(name)+1, sizeof(u64));
+
+	mmap_event->file_name = name;
+	mmap_event->file_size = size;
+
+	mmap_event->event.header.size = sizeof(mmap_event->event) + size;
+
+	cpuctx = &get_cpu_var(perf_cpu_context);
+	perf_counter_mmap_ctx(&cpuctx->ctx, mmap_event);
+	put_cpu_var(perf_cpu_context);
+
+	rcu_read_lock();
+	/*
+	 * doesn't really matter which of the child contexts the
+	 * events ends up in.
+	 */
+	ctx = rcu_dereference(current->perf_counter_ctxp);
+	if (ctx)
+		perf_counter_mmap_ctx(ctx, mmap_event);
+	rcu_read_unlock();
+
+	kfree(buf);
+}
+
+void __perf_counter_mmap(struct vm_area_struct *vma)
+{
+	struct perf_mmap_event mmap_event;
+
+	if (!atomic_read(&nr_mmap_counters))
+		return;
+
+	mmap_event = (struct perf_mmap_event){
+		.vma	= vma,
+		.event  = {
+			.header = { .type = PERF_EVENT_MMAP, },
+			.start  = vma->vm_start,
+			.len    = vma->vm_end - vma->vm_start,
+			.pgoff  = vma->vm_pgoff,
+		},
+	};
+
+	perf_counter_mmap_event(&mmap_event);
+}
+
+/*
+ * Log sample_period changes so that analyzing tools can re-normalize the
+ * event flow.
+ */
+
+struct freq_event {
+	struct perf_event_header	header;
+	u64				time;
+	u64				id;
+	u64				period;
+};
+
+static void perf_log_period(struct perf_counter *counter, u64 period)
+{
+	struct perf_output_handle handle;
+	struct freq_event event;
+	int ret;
+
+	if (counter->hw.sample_period == period)
+		return;
+
+	if (counter->attr.sample_type & PERF_SAMPLE_PERIOD)
+		return;
+
+	event = (struct freq_event) {
+		.header = {
+			.type = PERF_EVENT_PERIOD,
+			.misc = 0,
+			.size = sizeof(event),
+		},
+		.time = sched_clock(),
+		.id = counter->id,
+		.period = period,
+	};
+
+	ret = perf_output_begin(&handle, counter, sizeof(event), 1, 0);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, event);
+	perf_output_end(&handle);
+}
+
+/*
+ * IRQ throttle logging
+ */
+
+static void perf_log_throttle(struct perf_counter *counter, int enable)
+{
+	struct perf_output_handle handle;
+	int ret;
+
+	struct {
+		struct perf_event_header	header;
+		u64				time;
+		u64				id;
+	} throttle_event = {
+		.header = {
+			.type = PERF_EVENT_THROTTLE + 1,
+			.misc = 0,
+			.size = sizeof(throttle_event),
+		},
+		.time	= sched_clock(),
+		.id	= counter->id,
+	};
+
+	ret = perf_output_begin(&handle, counter, sizeof(throttle_event), 1, 0);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, throttle_event);
+	perf_output_end(&handle);
+}
+
+/*
+ * Generic counter overflow handling.
+ */
+
+int perf_counter_overflow(struct perf_counter *counter, int nmi,
+			  struct perf_sample_data *data)
+{
+	int events = atomic_read(&counter->event_limit);
+	int throttle = counter->pmu->unthrottle != NULL;
+	struct hw_perf_counter *hwc = &counter->hw;
+	int ret = 0;
+
+	if (!throttle) {
+		hwc->interrupts++;
+	} else {
+		if (hwc->interrupts != MAX_INTERRUPTS) {
+			hwc->interrupts++;
+			if (HZ * hwc->interrupts >
+					(u64)sysctl_perf_counter_sample_rate) {
+				hwc->interrupts = MAX_INTERRUPTS;
+				perf_log_throttle(counter, 0);
+				ret = 1;
+			}
+		} else {
+			/*
+			 * Keep re-disabling counters even though on the previous
+			 * pass we disabled it - just in case we raced with a
+			 * sched-in and the counter got enabled again:
+			 */
+			ret = 1;
+		}
+	}
+
+	if (counter->attr.freq) {
+		u64 now = sched_clock();
+		s64 delta = now - hwc->freq_stamp;
+
+		hwc->freq_stamp = now;
+
+		if (delta > 0 && delta < TICK_NSEC)
+			perf_adjust_period(counter, NSEC_PER_SEC / (int)delta);
+	}
+
+	/*
+	 * XXX event_limit might not quite work as expected on inherited
+	 * counters
+	 */
+
+	counter->pending_kill = POLL_IN;
+	if (events && atomic_dec_and_test(&counter->event_limit)) {
+		ret = 1;
+		counter->pending_kill = POLL_HUP;
+		if (nmi) {
+			counter->pending_disable = 1;
+			perf_pending_queue(&counter->pending,
+					   perf_pending_counter);
+		} else
+			perf_counter_disable(counter);
+	}
+
+	perf_counter_output(counter, nmi, data);
+	return ret;
+}
+
+/*
+ * Generic software counter infrastructure
+ */
+
+static void perf_swcounter_update(struct perf_counter *counter)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+	u64 prev, now;
+	s64 delta;
+
+again:
+	prev = atomic64_read(&hwc->prev_count);
+	now = atomic64_read(&hwc->count);
+	if (atomic64_cmpxchg(&hwc->prev_count, prev, now) != prev)
+		goto again;
+
+	delta = now - prev;
+
+	atomic64_add(delta, &counter->count);
+	atomic64_sub(delta, &hwc->period_left);
+}
+
+static void perf_swcounter_set_period(struct perf_counter *counter)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+	s64 left = atomic64_read(&hwc->period_left);
+	s64 period = hwc->sample_period;
+
+	if (unlikely(left <= -period)) {
+		left = period;
+		atomic64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+	}
+
+	if (unlikely(left <= 0)) {
+		left += period;
+		atomic64_add(period, &hwc->period_left);
+		hwc->last_period = period;
+	}
+
+	atomic64_set(&hwc->prev_count, -left);
+	atomic64_set(&hwc->count, -left);
+}
+
+static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
+{
+	enum hrtimer_restart ret = HRTIMER_RESTART;
+	struct perf_sample_data data;
+	struct perf_counter *counter;
+	u64 period;
+
+	counter	= container_of(hrtimer, struct perf_counter, hw.hrtimer);
+	counter->pmu->read(counter);
+
+	data.addr = 0;
+	data.regs = get_irq_regs();
+	/*
+	 * In case we exclude kernel IPs or are somehow not in interrupt
+	 * context, provide the next best thing, the user IP.
+	 */
+	if ((counter->attr.exclude_kernel || !data.regs) &&
+			!counter->attr.exclude_user)
+		data.regs = task_pt_regs(current);
+
+	if (data.regs) {
+		if (perf_counter_overflow(counter, 0, &data))
+			ret = HRTIMER_NORESTART;
+	}
+
+	period = max_t(u64, 10000, counter->hw.sample_period);
+	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
+
+	return ret;
+}
+
+static void perf_swcounter_overflow(struct perf_counter *counter,
+				    int nmi, struct pt_regs *regs, u64 addr)
+{
+	struct perf_sample_data data = {
+		.regs	= regs,
+		.addr	= addr,
+		.period	= counter->hw.last_period,
+	};
+
+	perf_swcounter_update(counter);
+	perf_swcounter_set_period(counter);
+	if (perf_counter_overflow(counter, nmi, &data))
+		/* soft-disable the counter */
+		;
+
+}
+
+static int perf_swcounter_is_counting(struct perf_counter *counter)
+{
+	struct perf_counter_context *ctx;
+	unsigned long flags;
+	int count;
+
+	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
+		return 1;
+
+	if (counter->state != PERF_COUNTER_STATE_INACTIVE)
+		return 0;
+
+	/*
+	 * If the counter is inactive, it could be just because
+	 * its task is scheduled out, or because it's in a group
+	 * which could not go on the PMU.  We want to count in
+	 * the first case but not the second.  If the context is
+	 * currently active then an inactive software counter must
+	 * be the second case.  If it's not currently active then
+	 * we need to know whether the counter was active when the
+	 * context was last active, which we can determine by
+	 * comparing counter->tstamp_stopped with ctx->time.
+	 *
+	 * We are within an RCU read-side critical section,
+	 * which protects the existence of *ctx.
+	 */
+	ctx = counter->ctx;
+	spin_lock_irqsave(&ctx->lock, flags);
+	count = 1;
+	/* Re-check state now we have the lock */
+	if (counter->state < PERF_COUNTER_STATE_INACTIVE ||
+	    counter->ctx->is_active ||
+	    counter->tstamp_stopped < ctx->time)
+		count = 0;
+	spin_unlock_irqrestore(&ctx->lock, flags);
+	return count;
+}
+
+static int perf_swcounter_match(struct perf_counter *counter,
+				enum perf_type_id type,
+				u32 event, struct pt_regs *regs)
+{
+	if (!perf_swcounter_is_counting(counter))
+		return 0;
+
+	if (counter->attr.type != type)
+		return 0;
+	if (counter->attr.config != event)
+		return 0;
+
+	if (regs) {
+		if (counter->attr.exclude_user && user_mode(regs))
+			return 0;
+
+		if (counter->attr.exclude_kernel && !user_mode(regs))
+			return 0;
+	}
+
+	return 1;
+}
+
+static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
+			       int nmi, struct pt_regs *regs, u64 addr)
+{
+	int neg = atomic64_add_negative(nr, &counter->hw.count);
+
+	if (counter->hw.sample_period && !neg && regs)
+		perf_swcounter_overflow(counter, nmi, regs, addr);
+}
+
+static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
+				     enum perf_type_id type, u32 event,
+				     u64 nr, int nmi, struct pt_regs *regs,
+				     u64 addr)
+{
+	struct perf_counter *counter;
+
+	if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
+		if (perf_swcounter_match(counter, type, event, regs))
+			perf_swcounter_add(counter, nr, nmi, regs, addr);
+	}
+	rcu_read_unlock();
+}
+
+static int *perf_swcounter_recursion_context(struct perf_cpu_context *cpuctx)
+{
+	if (in_nmi())
+		return &cpuctx->recursion[3];
+
+	if (in_irq())
+		return &cpuctx->recursion[2];
+
+	if (in_softirq())
+		return &cpuctx->recursion[1];
+
+	return &cpuctx->recursion[0];
+}
+
+static void __perf_swcounter_event(enum perf_type_id type, u32 event,
+				   u64 nr, int nmi, struct pt_regs *regs,
+				   u64 addr)
+{
+	struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
+	int *recursion = perf_swcounter_recursion_context(cpuctx);
+	struct perf_counter_context *ctx;
+
+	if (*recursion)
+		goto out;
+
+	(*recursion)++;
+	barrier();
+
+	perf_swcounter_ctx_event(&cpuctx->ctx, type, event,
+				 nr, nmi, regs, addr);
+	rcu_read_lock();
+	/*
+	 * doesn't really matter which of the child contexts the
+	 * events ends up in.
+	 */
+	ctx = rcu_dereference(current->perf_counter_ctxp);
+	if (ctx)
+		perf_swcounter_ctx_event(ctx, type, event, nr, nmi, regs, addr);
+	rcu_read_unlock();
+
+	barrier();
+	(*recursion)--;
+
+out:
+	put_cpu_var(perf_cpu_context);
+}
+
+void
+perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+{
+	__perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi, regs, addr);
+}
+
+static void perf_swcounter_read(struct perf_counter *counter)
+{
+	perf_swcounter_update(counter);
+}
+
+static int perf_swcounter_enable(struct perf_counter *counter)
+{
+	perf_swcounter_set_period(counter);
+	return 0;
+}
+
+static void perf_swcounter_disable(struct perf_counter *counter)
+{
+	perf_swcounter_update(counter);
+}
+
+static const struct pmu perf_ops_generic = {
+	.enable		= perf_swcounter_enable,
+	.disable	= perf_swcounter_disable,
+	.read		= perf_swcounter_read,
+};
+
+/*
+ * Software counter: cpu wall time clock
+ */
+
+static void cpu_clock_perf_counter_update(struct perf_counter *counter)
+{
+	int cpu = raw_smp_processor_id();
+	s64 prev;
+	u64 now;
+
+	now = cpu_clock(cpu);
+	prev = atomic64_read(&counter->hw.prev_count);
+	atomic64_set(&counter->hw.prev_count, now);
+	atomic64_add(now - prev, &counter->count);
+}
+
+static int cpu_clock_perf_counter_enable(struct perf_counter *counter)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+	int cpu = raw_smp_processor_id();
+
+	atomic64_set(&hwc->prev_count, cpu_clock(cpu));
+	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hwc->hrtimer.function = perf_swcounter_hrtimer;
+	if (hwc->sample_period) {
+		u64 period = max_t(u64, 10000, hwc->sample_period);
+		__hrtimer_start_range_ns(&hwc->hrtimer,
+				ns_to_ktime(period), 0,
+				HRTIMER_MODE_REL, 0);
+	}
+
+	return 0;
+}
+
+static void cpu_clock_perf_counter_disable(struct perf_counter *counter)
+{
+	if (counter->hw.sample_period)
+		hrtimer_cancel(&counter->hw.hrtimer);
+	cpu_clock_perf_counter_update(counter);
+}
+
+static void cpu_clock_perf_counter_read(struct perf_counter *counter)
+{
+	cpu_clock_perf_counter_update(counter);
+}
+
+static const struct pmu perf_ops_cpu_clock = {
+	.enable		= cpu_clock_perf_counter_enable,
+	.disable	= cpu_clock_perf_counter_disable,
+	.read		= cpu_clock_perf_counter_read,
+};
+
+/*
+ * Software counter: task time clock
+ */
+
+static void task_clock_perf_counter_update(struct perf_counter *counter, u64 now)
+{
+	u64 prev;
+	s64 delta;
+
+	prev = atomic64_xchg(&counter->hw.prev_count, now);
+	delta = now - prev;
+	atomic64_add(delta, &counter->count);
+}
+
+static int task_clock_perf_counter_enable(struct perf_counter *counter)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+	u64 now;
+
+	now = counter->ctx->time;
+
+	atomic64_set(&hwc->prev_count, now);
+	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hwc->hrtimer.function = perf_swcounter_hrtimer;
+	if (hwc->sample_period) {
+		u64 period = max_t(u64, 10000, hwc->sample_period);
+		__hrtimer_start_range_ns(&hwc->hrtimer,
+				ns_to_ktime(period), 0,
+				HRTIMER_MODE_REL, 0);
+	}
+
+	return 0;
+}
+
+static void task_clock_perf_counter_disable(struct perf_counter *counter)
+{
+	if (counter->hw.sample_period)
+		hrtimer_cancel(&counter->hw.hrtimer);
+	task_clock_perf_counter_update(counter, counter->ctx->time);
+
+}
+
+static void task_clock_perf_counter_read(struct perf_counter *counter)
+{
+	u64 time;
+
+	if (!in_nmi()) {
+		update_context_time(counter->ctx);
+		time = counter->ctx->time;
+	} else {
+		u64 now = perf_clock();
+		u64 delta = now - counter->ctx->timestamp;
+		time = counter->ctx->time + delta;
+	}
+
+	task_clock_perf_counter_update(counter, time);
+}
+
+static const struct pmu perf_ops_task_clock = {
+	.enable		= task_clock_perf_counter_enable,
+	.disable	= task_clock_perf_counter_disable,
+	.read		= task_clock_perf_counter_read,
+};
+
+/*
+ * Software counter: cpu migrations
+ */
+void perf_counter_task_migration(struct task_struct *task, int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct perf_counter_context *ctx;
+
+	perf_swcounter_ctx_event(&cpuctx->ctx, PERF_TYPE_SOFTWARE,
+				 PERF_COUNT_SW_CPU_MIGRATIONS,
+				 1, 1, NULL, 0);
+
+	ctx = perf_pin_task_context(task);
+	if (ctx) {
+		perf_swcounter_ctx_event(ctx, PERF_TYPE_SOFTWARE,
+					 PERF_COUNT_SW_CPU_MIGRATIONS,
+					 1, 1, NULL, 0);
+		perf_unpin_context(ctx);
+	}
+}
+
+#ifdef CONFIG_EVENT_PROFILE
+void perf_tpcounter_event(int event_id)
+{
+	struct pt_regs *regs = get_irq_regs();
+
+	if (!regs)
+		regs = task_pt_regs(current);
+
+	__perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, regs, 0);
+}
+EXPORT_SYMBOL_GPL(perf_tpcounter_event);
+
+extern int ftrace_profile_enable(int);
+extern void ftrace_profile_disable(int);
+
+static void tp_perf_counter_destroy(struct perf_counter *counter)
+{
+	ftrace_profile_disable(perf_event_id(&counter->attr));
+}
+
+static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
+{
+	int event_id = perf_event_id(&counter->attr);
+	int ret;
+
+	ret = ftrace_profile_enable(event_id);
+	if (ret)
+		return NULL;
+
+	counter->destroy = tp_perf_counter_destroy;
+
+	return &perf_ops_generic;
+}
+#else
+static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
+{
+	return NULL;
+}
+#endif
+
+static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
+{
+	const struct pmu *pmu = NULL;
+
+	/*
+	 * Software counters (currently) can't in general distinguish
+	 * between user, kernel and hypervisor events.
+	 * However, context switches and cpu migrations are considered
+	 * to be kernel events, and page faults are never hypervisor
+	 * events.
+	 */
+	switch (counter->attr.config) {
+	case PERF_COUNT_SW_CPU_CLOCK:
+		pmu = &perf_ops_cpu_clock;
+
+		break;
+	case PERF_COUNT_SW_TASK_CLOCK:
+		/*
+		 * If the user instantiates this as a per-cpu counter,
+		 * use the cpu_clock counter instead.
+		 */
+		if (counter->ctx->task)
+			pmu = &perf_ops_task_clock;
+		else
+			pmu = &perf_ops_cpu_clock;
+
+		break;
+	case PERF_COUNT_SW_PAGE_FAULTS:
+	case PERF_COUNT_SW_PAGE_FAULTS_MIN:
+	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
+	case PERF_COUNT_SW_CONTEXT_SWITCHES:
+	case PERF_COUNT_SW_CPU_MIGRATIONS:
+		pmu = &perf_ops_generic;
+		break;
+	}
+
+	return pmu;
+}
+
+/*
+ * Allocate and initialize a counter structure
+ */
+static struct perf_counter *
+perf_counter_alloc(struct perf_counter_attr *attr,
+		   int cpu,
+		   struct perf_counter_context *ctx,
+		   struct perf_counter *group_leader,
+		   gfp_t gfpflags)
+{
+	const struct pmu *pmu;
+	struct perf_counter *counter;
+	struct hw_perf_counter *hwc;
+	long err;
+
+	counter = kzalloc(sizeof(*counter), gfpflags);
+	if (!counter)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * Single counters are their own group leaders, with an
+	 * empty sibling list:
+	 */
+	if (!group_leader)
+		group_leader = counter;
+
+	mutex_init(&counter->child_mutex);
+	INIT_LIST_HEAD(&counter->child_list);
+
+	INIT_LIST_HEAD(&counter->list_entry);
+	INIT_LIST_HEAD(&counter->event_entry);
+	INIT_LIST_HEAD(&counter->sibling_list);
+	init_waitqueue_head(&counter->waitq);
+
+	mutex_init(&counter->mmap_mutex);
+
+	counter->cpu		= cpu;
+	counter->attr		= *attr;
+	counter->group_leader	= group_leader;
+	counter->pmu		= NULL;
+	counter->ctx		= ctx;
+	counter->oncpu		= -1;
+
+	counter->ns		= get_pid_ns(current->nsproxy->pid_ns);
+	counter->id		= atomic64_inc_return(&perf_counter_id);
+
+	counter->state		= PERF_COUNTER_STATE_INACTIVE;
+
+	if (attr->disabled)
+		counter->state = PERF_COUNTER_STATE_OFF;
+
+	pmu = NULL;
+
+	hwc = &counter->hw;
+	hwc->sample_period = attr->sample_period;
+	if (attr->freq && attr->sample_freq)
+		hwc->sample_period = 1;
+
+	atomic64_set(&hwc->period_left, hwc->sample_period);
+
+	/*
+	 * we currently do not support PERF_SAMPLE_GROUP on inherited counters
+	 */
+	if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP))
+		goto done;
+
+	if (attr->type == PERF_TYPE_RAW) {
+		pmu = hw_perf_counter_init(counter);
+		goto done;
+	}
+
+	switch (attr->type) {
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		pmu = hw_perf_counter_init(counter);
+		break;
+
+	case PERF_TYPE_SOFTWARE:
+		pmu = sw_perf_counter_init(counter);
+		break;
+
+	case PERF_TYPE_TRACEPOINT:
+		pmu = tp_perf_counter_init(counter);
+		break;
+	}
+done:
+	err = 0;
+	if (!pmu)
+		err = -EINVAL;
+	else if (IS_ERR(pmu))
+		err = PTR_ERR(pmu);
+
+	if (err) {
+		if (counter->ns)
+			put_pid_ns(counter->ns);
+		kfree(counter);
+		return ERR_PTR(err);
+	}
+
+	counter->pmu = pmu;
+
+	atomic_inc(&nr_counters);
+	if (counter->attr.mmap)
+		atomic_inc(&nr_mmap_counters);
+	if (counter->attr.comm)
+		atomic_inc(&nr_comm_counters);
+
+	return counter;
+}
+
+/**
+ * sys_perf_counter_open - open a performance counter, associate it to a task/cpu
+ *
+ * @attr_uptr:	event type attributes for monitoring/sampling
+ * @pid:		target pid
+ * @cpu:		target cpu
+ * @group_fd:		group leader counter fd
+ */
+SYSCALL_DEFINE5(perf_counter_open,
+		const struct perf_counter_attr __user *, attr_uptr,
+		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
+{
+	struct perf_counter *counter, *group_leader;
+	struct perf_counter_attr attr;
+	struct perf_counter_context *ctx;
+	struct file *counter_file = NULL;
+	struct file *group_file = NULL;
+	int fput_needed = 0;
+	int fput_needed2 = 0;
+	int ret;
+
+	/* for future expandability... */
+	if (flags)
+		return -EINVAL;
+
+	if (copy_from_user(&attr, attr_uptr, sizeof(attr)) != 0)
+		return -EFAULT;
+
+	if (!attr.exclude_kernel) {
+		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
+	}
+
+	if (attr.freq) {
+		if (attr.sample_freq > sysctl_perf_counter_sample_rate)
+			return -EINVAL;
+	}
+
+	/*
+	 * Get the target context (task or percpu):
+	 */
+	ctx = find_get_context(pid, cpu);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	/*
+	 * Look up the group leader (we will attach this counter to it):
+	 */
+	group_leader = NULL;
+	if (group_fd != -1) {
+		ret = -EINVAL;
+		group_file = fget_light(group_fd, &fput_needed);
+		if (!group_file)
+			goto err_put_context;
+		if (group_file->f_op != &perf_fops)
+			goto err_put_context;
+
+		group_leader = group_file->private_data;
+		/*
+		 * Do not allow a recursive hierarchy (this new sibling
+		 * becoming part of another group-sibling):
+		 */
+		if (group_leader->group_leader != group_leader)
+			goto err_put_context;
+		/*
+		 * Do not allow to attach to a group in a different
+		 * task or CPU context:
+		 */
+		if (group_leader->ctx != ctx)
+			goto err_put_context;
+		/*
+		 * Only a group leader can be exclusive or pinned
+		 */
+		if (attr.exclusive || attr.pinned)
+			goto err_put_context;
+	}
+
+	counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
+				     GFP_KERNEL);
+	ret = PTR_ERR(counter);
+	if (IS_ERR(counter))
+		goto err_put_context;
+
+	ret = anon_inode_getfd("[perf_counter]", &perf_fops, counter, 0);
+	if (ret < 0)
+		goto err_free_put_context;
+
+	counter_file = fget_light(ret, &fput_needed2);
+	if (!counter_file)
+		goto err_free_put_context;
+
+	counter->filp = counter_file;
+	WARN_ON_ONCE(ctx->parent_ctx);
+	mutex_lock(&ctx->mutex);
+	perf_install_in_context(ctx, counter, cpu);
+	++ctx->generation;
+	mutex_unlock(&ctx->mutex);
+
+	counter->owner = current;
+	get_task_struct(current);
+	mutex_lock(&current->perf_counter_mutex);
+	list_add_tail(&counter->owner_entry, &current->perf_counter_list);
+	mutex_unlock(&current->perf_counter_mutex);
+
+	fput_light(counter_file, fput_needed2);
+
+out_fput:
+	fput_light(group_file, fput_needed);
+
+	return ret;
+
+err_free_put_context:
+	kfree(counter);
+
+err_put_context:
+	put_ctx(ctx);
+
+	goto out_fput;
+}
+
+/*
+ * inherit a counter from parent task to child task:
+ */
+static struct perf_counter *
+inherit_counter(struct perf_counter *parent_counter,
+	      struct task_struct *parent,
+	      struct perf_counter_context *parent_ctx,
+	      struct task_struct *child,
+	      struct perf_counter *group_leader,
+	      struct perf_counter_context *child_ctx)
+{
+	struct perf_counter *child_counter;
+
+	/*
+	 * Instead of creating recursive hierarchies of counters,
+	 * we link inherited counters back to the original parent,
+	 * which has a filp for sure, which we use as the reference
+	 * count:
+	 */
+	if (parent_counter->parent)
+		parent_counter = parent_counter->parent;
+
+	child_counter = perf_counter_alloc(&parent_counter->attr,
+					   parent_counter->cpu, child_ctx,
+					   group_leader, GFP_KERNEL);
+	if (IS_ERR(child_counter))
+		return child_counter;
+	get_ctx(child_ctx);
+
+	/*
+	 * Make the child state follow the state of the parent counter,
+	 * not its attr.disabled bit.  We hold the parent's mutex,
+	 * so we won't race with perf_counter_{en, dis}able_family.
+	 */
+	if (parent_counter->state >= PERF_COUNTER_STATE_INACTIVE)
+		child_counter->state = PERF_COUNTER_STATE_INACTIVE;
+	else
+		child_counter->state = PERF_COUNTER_STATE_OFF;
+
+	if (parent_counter->attr.freq)
+		child_counter->hw.sample_period = parent_counter->hw.sample_period;
+
+	/*
+	 * Link it up in the child's context:
+	 */
+	add_counter_to_ctx(child_counter, child_ctx);
+
+	child_counter->parent = parent_counter;
+	/*
+	 * inherit into child's child as well:
+	 */
+	child_counter->attr.inherit = 1;
+
+	/*
+	 * Get a reference to the parent filp - we will fput it
+	 * when the child counter exits. This is safe to do because
+	 * we are in the parent and we know that the filp still
+	 * exists and has a nonzero count:
+	 */
+	atomic_long_inc(&parent_counter->filp->f_count);
+
+	/*
+	 * Link this into the parent counter's child list
+	 */
+	WARN_ON_ONCE(parent_counter->ctx->parent_ctx);
+	mutex_lock(&parent_counter->child_mutex);
+	list_add_tail(&child_counter->child_list, &parent_counter->child_list);
+	mutex_unlock(&parent_counter->child_mutex);
+
+	return child_counter;
+}
+
+static int inherit_group(struct perf_counter *parent_counter,
+	      struct task_struct *parent,
+	      struct perf_counter_context *parent_ctx,
+	      struct task_struct *child,
+	      struct perf_counter_context *child_ctx)
+{
+	struct perf_counter *leader;
+	struct perf_counter *sub;
+	struct perf_counter *child_ctr;
+
+	leader = inherit_counter(parent_counter, parent, parent_ctx,
+				 child, NULL, child_ctx);
+	if (IS_ERR(leader))
+		return PTR_ERR(leader);
+	list_for_each_entry(sub, &parent_counter->sibling_list, list_entry) {
+		child_ctr = inherit_counter(sub, parent, parent_ctx,
+					    child, leader, child_ctx);
+		if (IS_ERR(child_ctr))
+			return PTR_ERR(child_ctr);
+	}
+	return 0;
+}
+
+static void sync_child_counter(struct perf_counter *child_counter,
+			       struct perf_counter *parent_counter)
+{
+	u64 child_val;
+
+	child_val = atomic64_read(&child_counter->count);
+
+	/*
+	 * Add back the child's count to the parent's count:
+	 */
+	atomic64_add(child_val, &parent_counter->count);
+	atomic64_add(child_counter->total_time_enabled,
+		     &parent_counter->child_total_time_enabled);
+	atomic64_add(child_counter->total_time_running,
+		     &parent_counter->child_total_time_running);
+
+	/*
+	 * Remove this counter from the parent's list
+	 */
+	WARN_ON_ONCE(parent_counter->ctx->parent_ctx);
+	mutex_lock(&parent_counter->child_mutex);
+	list_del_init(&child_counter->child_list);
+	mutex_unlock(&parent_counter->child_mutex);
+
+	/*
+	 * Release the parent counter, if this was the last
+	 * reference to it.
+	 */
+	fput(parent_counter->filp);
+}
+
+static void
+__perf_counter_exit_task(struct perf_counter *child_counter,
+			 struct perf_counter_context *child_ctx)
+{
+	struct perf_counter *parent_counter;
+
+	update_counter_times(child_counter);
+	perf_counter_remove_from_context(child_counter);
+
+	parent_counter = child_counter->parent;
+	/*
+	 * It can happen that parent exits first, and has counters
+	 * that are still around due to the child reference. These
+	 * counters need to be zapped - but otherwise linger.
+	 */
+	if (parent_counter) {
+		sync_child_counter(child_counter, parent_counter);
+		free_counter(child_counter);
+	}
+}
+
+/*
+ * When a child task exits, feed back counter values to parent counters.
+ */
+void perf_counter_exit_task(struct task_struct *child)
+{
+	struct perf_counter *child_counter, *tmp;
+	struct perf_counter_context *child_ctx;
+	unsigned long flags;
+
+	if (likely(!child->perf_counter_ctxp))
+		return;
+
+	local_irq_save(flags);
+	/*
+	 * We can't reschedule here because interrupts are disabled,
+	 * and either child is current or it is a task that can't be
+	 * scheduled, so we are now safe from rescheduling changing
+	 * our context.
+	 */
+	child_ctx = child->perf_counter_ctxp;
+	__perf_counter_task_sched_out(child_ctx);
+
+	/*
+	 * Take the context lock here so that if find_get_context is
+	 * reading child->perf_counter_ctxp, we wait until it has
+	 * incremented the context's refcount before we do put_ctx below.
+	 */
+	spin_lock(&child_ctx->lock);
+	child->perf_counter_ctxp = NULL;
+	if (child_ctx->parent_ctx) {
+		/*
+		 * This context is a clone; unclone it so it can't get
+		 * swapped to another process while we're removing all
+		 * the counters from it.
+		 */
+		put_ctx(child_ctx->parent_ctx);
+		child_ctx->parent_ctx = NULL;
+	}
+	spin_unlock(&child_ctx->lock);
+	local_irq_restore(flags);
+
+	/*
+	 * We can recurse on the same lock type through:
+	 *
+	 *   __perf_counter_exit_task()
+	 *     sync_child_counter()
+	 *       fput(parent_counter->filp)
+	 *         perf_release()
+	 *           mutex_lock(&ctx->mutex)
+	 *
+	 * But since its the parent context it won't be the same instance.
+	 */
+	mutex_lock_nested(&child_ctx->mutex, SINGLE_DEPTH_NESTING);
+
+again:
+	list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list,
+				 list_entry)
+		__perf_counter_exit_task(child_counter, child_ctx);
+
+	/*
+	 * If the last counter was a group counter, it will have appended all
+	 * its siblings to the list, but we obtained 'tmp' before that which
+	 * will still point to the list head terminating the iteration.
+	 */
+	if (!list_empty(&child_ctx->counter_list))
+		goto again;
+
+	mutex_unlock(&child_ctx->mutex);
+
+	put_ctx(child_ctx);
+}
+
+/*
+ * free an unexposed, unused context as created by inheritance by
+ * init_task below, used by fork() in case of fail.
+ */
+void perf_counter_free_task(struct task_struct *task)
+{
+	struct perf_counter_context *ctx = task->perf_counter_ctxp;
+	struct perf_counter *counter, *tmp;
+
+	if (!ctx)
+		return;
+
+	mutex_lock(&ctx->mutex);
+again:
+	list_for_each_entry_safe(counter, tmp, &ctx->counter_list, list_entry) {
+		struct perf_counter *parent = counter->parent;
+
+		if (WARN_ON_ONCE(!parent))
+			continue;
+
+		mutex_lock(&parent->child_mutex);
+		list_del_init(&counter->child_list);
+		mutex_unlock(&parent->child_mutex);
+
+		fput(parent->filp);
+
+		list_del_counter(counter, ctx);
+		free_counter(counter);
+	}
+
+	if (!list_empty(&ctx->counter_list))
+		goto again;
+
+	mutex_unlock(&ctx->mutex);
+
+	put_ctx(ctx);
+}
+
+/*
+ * Initialize the perf_counter context in task_struct
+ */
+int perf_counter_init_task(struct task_struct *child)
+{
+	struct perf_counter_context *child_ctx, *parent_ctx;
+	struct perf_counter_context *cloned_ctx;
+	struct perf_counter *counter;
+	struct task_struct *parent = current;
+	int inherited_all = 1;
+	int ret = 0;
+
+	child->perf_counter_ctxp = NULL;
+
+	mutex_init(&child->perf_counter_mutex);
+	INIT_LIST_HEAD(&child->perf_counter_list);
+
+	if (likely(!parent->perf_counter_ctxp))
+		return 0;
+
+	/*
+	 * This is executed from the parent task context, so inherit
+	 * counters that have been marked for cloning.
+	 * First allocate and initialize a context for the child.
+	 */
+
+	child_ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL);
+	if (!child_ctx)
+		return -ENOMEM;
+
+	__perf_counter_init_context(child_ctx, child);
+	child->perf_counter_ctxp = child_ctx;
+	get_task_struct(child);
+
+	/*
+	 * If the parent's context is a clone, pin it so it won't get
+	 * swapped under us.
+	 */
+	parent_ctx = perf_pin_task_context(parent);
+
+	/*
+	 * No need to check if parent_ctx != NULL here; since we saw
+	 * it non-NULL earlier, the only reason for it to become NULL
+	 * is if we exit, and since we're currently in the middle of
+	 * a fork we can't be exiting at the same time.
+	 */
+
+	/*
+	 * Lock the parent list. No need to lock the child - not PID
+	 * hashed yet and not running, so nobody can access it.
+	 */
+	mutex_lock(&parent_ctx->mutex);
+
+	/*
+	 * We dont have to disable NMIs - we are only looking at
+	 * the list, not manipulating it:
+	 */
+	list_for_each_entry_rcu(counter, &parent_ctx->event_list, event_entry) {
+		if (counter != counter->group_leader)
+			continue;
+
+		if (!counter->attr.inherit) {
+			inherited_all = 0;
+			continue;
+		}
+
+		ret = inherit_group(counter, parent, parent_ctx,
+					     child, child_ctx);
+		if (ret) {
+			inherited_all = 0;
+			break;
+		}
+	}
+
+	if (inherited_all) {
+		/*
+		 * Mark the child context as a clone of the parent
+		 * context, or of whatever the parent is a clone of.
+		 * Note that if the parent is a clone, it could get
+		 * uncloned at any point, but that doesn't matter
+		 * because the list of counters and the generation
+		 * count can't have changed since we took the mutex.
+		 */
+		cloned_ctx = rcu_dereference(parent_ctx->parent_ctx);
+		if (cloned_ctx) {
+			child_ctx->parent_ctx = cloned_ctx;
+			child_ctx->parent_gen = parent_ctx->parent_gen;
+		} else {
+			child_ctx->parent_ctx = parent_ctx;
+			child_ctx->parent_gen = parent_ctx->generation;
+		}
+		get_ctx(child_ctx->parent_ctx);
+	}
+
+	mutex_unlock(&parent_ctx->mutex);
+
+	perf_unpin_context(parent_ctx);
+
+	return ret;
+}
+
+static void __cpuinit perf_counter_init_cpu(int cpu)
+{
+	struct perf_cpu_context *cpuctx;
+
+	cpuctx = &per_cpu(perf_cpu_context, cpu);
+	__perf_counter_init_context(&cpuctx->ctx, NULL);
+
+	spin_lock(&perf_resource_lock);
+	cpuctx->max_pertask = perf_max_counters - perf_reserved_percpu;
+	spin_unlock(&perf_resource_lock);
+
+	hw_perf_counter_setup(cpu);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void __perf_counter_exit_cpu(void *info)
+{
+	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_counter_context *ctx = &cpuctx->ctx;
+	struct perf_counter *counter, *tmp;
+
+	list_for_each_entry_safe(counter, tmp, &ctx->counter_list, list_entry)
+		__perf_counter_remove_from_context(counter);
+}
+static void perf_counter_exit_cpu(int cpu)
+{
+	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct perf_counter_context *ctx = &cpuctx->ctx;
+
+	mutex_lock(&ctx->mutex);
+	smp_call_function_single(cpu, __perf_counter_exit_cpu, NULL, 1);
+	mutex_unlock(&ctx->mutex);
+}
+#else
+static inline void perf_counter_exit_cpu(int cpu) { }
+#endif
+
+static int __cpuinit
+perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action) {
+
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		perf_counter_init_cpu(cpu);
+		break;
+
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		perf_counter_exit_cpu(cpu);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+/*
+ * This has to have a higher priority than migration_notifier in sched.c.
+ */
+static struct notifier_block __cpuinitdata perf_cpu_nb = {
+	.notifier_call		= perf_cpu_notify,
+	.priority		= 20,
+};
+
+void __init perf_counter_init(void)
+{
+	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
+			(void *)(long)smp_processor_id());
+	register_cpu_notifier(&perf_cpu_nb);
+}
+
+static ssize_t perf_show_reserve_percpu(struct sysdev_class *class, char *buf)
+{
+	return sprintf(buf, "%d\n", perf_reserved_percpu);
+}
+
+static ssize_t
+perf_set_reserve_percpu(struct sysdev_class *class,
+			const char *buf,
+			size_t count)
+{
+	struct perf_cpu_context *cpuctx;
+	unsigned long val;
+	int err, cpu, mpt;
+
+	err = strict_strtoul(buf, 10, &val);
+	if (err)
+		return err;
+	if (val > perf_max_counters)
+		return -EINVAL;
+
+	spin_lock(&perf_resource_lock);
+	perf_reserved_percpu = val;
+	for_each_online_cpu(cpu) {
+		cpuctx = &per_cpu(perf_cpu_context, cpu);
+		spin_lock_irq(&cpuctx->ctx.lock);
+		mpt = min(perf_max_counters - cpuctx->ctx.nr_counters,
+			  perf_max_counters - perf_reserved_percpu);
+		cpuctx->max_pertask = mpt;
+		spin_unlock_irq(&cpuctx->ctx.lock);
+	}
+	spin_unlock(&perf_resource_lock);
+
+	return count;
+}
+
+static ssize_t perf_show_overcommit(struct sysdev_class *class, char *buf)
+{
+	return sprintf(buf, "%d\n", perf_overcommit);
+}
+
+static ssize_t
+perf_set_overcommit(struct sysdev_class *class, const char *buf, size_t count)
+{
+	unsigned long val;
+	int err;
+
+	err = strict_strtoul(buf, 10, &val);
+	if (err)
+		return err;
+	if (val > 1)
+		return -EINVAL;
+
+	spin_lock(&perf_resource_lock);
+	perf_overcommit = val;
+	spin_unlock(&perf_resource_lock);
+
+	return count;
+}
+
+static SYSDEV_CLASS_ATTR(
+				reserve_percpu,
+				0644,
+				perf_show_reserve_percpu,
+				perf_set_reserve_percpu
+			);
+
+static SYSDEV_CLASS_ATTR(
+				overcommit,
+				0644,
+				perf_show_overcommit,
+				perf_set_overcommit
+			);
+
+static struct attribute *perfclass_attrs[] = {
+	&attr_reserve_percpu.attr,
+	&attr_overcommit.attr,
+	NULL
+};
+
+static struct attribute_group perfclass_attr_group = {
+	.attrs			= perfclass_attrs,
+	.name			= "perf_counters",
+};
+
+static int __init perf_counter_sysfs_init(void)
+{
+	return sysfs_create_group(&cpu_sysdev_class.kset.kobj,
+				  &perfclass_attr_group);
+}
+device_initcall(perf_counter_sysfs_init);
diff --git a/kernel/profile.c b/kernel/profile.c
index 7724e0409bae..28cf26ad2d24 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -111,12 +111,6 @@ int __ref profile_init(void)
 	/* only text is profiled */
 	prof_len = (_etext - _stext) >> prof_shift;
 	buffer_bytes = prof_len*sizeof(atomic_t);
-	if (!slab_is_available()) {
-		prof_buffer = alloc_bootmem(buffer_bytes);
-		alloc_bootmem_cpumask_var(&prof_cpu_mask);
-		cpumask_copy(prof_cpu_mask, cpu_possible_mask);
-		return 0;
-	}
 
 	if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 42c317874cfa..f6d8b8cb5e34 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -24,16 +24,6 @@
 #include <linux/uaccess.h>
 
 
-/*
- * Initialize a new task whose father had been ptraced.
- *
- * Called from copy_process().
- */
-void ptrace_fork(struct task_struct *child, unsigned long clone_flags)
-{
-	arch_ptrace_fork(child, clone_flags);
-}
-
 /*
  * ptrace a task: make the debugger its new parent and
  * move it to the ptrace list.
@@ -185,10 +175,11 @@ int ptrace_attach(struct task_struct *task)
 	if (same_thread_group(task, current))
 		goto out;
 
-	/* Protect exec's credential calculations against our interference;
-	 * SUID, SGID and LSM creds get determined differently under ptrace.
+	/* Protect the target's credential calculations against our
+	 * interference; SUID, SGID and LSM creds get determined differently
+	 * under ptrace.
 	 */
-	retval = mutex_lock_interruptible(&task->cred_exec_mutex);
+	retval = mutex_lock_interruptible(&task->cred_guard_mutex);
 	if (retval  < 0)
 		goto out;
 
@@ -232,7 +223,7 @@ repeat:
 bad:
 	write_unlock_irqrestore(&tasklist_lock, flags);
 	task_unlock(task);
-	mutex_unlock(&task->cred_exec_mutex);
+	mutex_unlock(&task->cred_guard_mutex);
 out:
 	return retval;
 }
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index ce97a4df64d3..beb0e659adcc 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -1356,17 +1356,11 @@ static int rcu_sched_grace_period(void *arg)
 
 		rcu_ctrlblk.sched_sleep = rcu_sched_sleeping;
 		spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
-		ret = 0;
+		ret = 0; /* unused */
 		__wait_event_interruptible(rcu_ctrlblk.sched_wq,
 			rcu_ctrlblk.sched_sleep != rcu_sched_sleeping,
 			ret);
 
-		/*
-		 * Signals would prevent us from sleeping, and we cannot
-		 * do much with them in any case.  So flush them.
-		 */
-		if (ret)
-			flush_signals(current);
 		couldsleepnext = 0;
 
 	} while (!kthread_should_stop());
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index d2a372fb0b9b..0dccfbba6d26 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1259,31 +1259,44 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	check_cpu_stall(rsp, rdp);
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
-	if (rdp->qs_pending)
+	if (rdp->qs_pending) {
+		rdp->n_rp_qs_pending++;
 		return 1;
+	}
 
 	/* Does this CPU have callbacks ready to invoke? */
-	if (cpu_has_callbacks_ready_to_invoke(rdp))
+	if (cpu_has_callbacks_ready_to_invoke(rdp)) {
+		rdp->n_rp_cb_ready++;
 		return 1;
+	}
 
 	/* Has RCU gone idle with this CPU needing another grace period? */
-	if (cpu_needs_another_gp(rsp, rdp))
+	if (cpu_needs_another_gp(rsp, rdp)) {
+		rdp->n_rp_cpu_needs_gp++;
 		return 1;
+	}
 
 	/* Has another RCU grace period completed?  */
-	if (ACCESS_ONCE(rsp->completed) != rdp->completed) /* outside of lock */
+	if (ACCESS_ONCE(rsp->completed) != rdp->completed) { /* outside lock */
+		rdp->n_rp_gp_completed++;
 		return 1;
+	}
 
 	/* Has a new RCU grace period started? */
-	if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) /* outside of lock */
+	if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) { /* outside lock */
+		rdp->n_rp_gp_started++;
 		return 1;
+	}
 
 	/* Has an RCU GP gone long enough to send resched IPIs &c? */
 	if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) &&
-	    ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0))
+	    ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)) {
+		rdp->n_rp_need_fqs++;
 		return 1;
+	}
 
 	/* nothing to do */
+	rdp->n_rp_need_nothing++;
 	return 0;
 }
 
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 4b1875ba9404..fe1dcdbf1ca3 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -213,7 +213,63 @@ static struct file_operations rcugp_fops = {
 	.release = single_release,
 };
 
-static struct dentry *rcudir, *datadir, *datadir_csv, *hierdir, *gpdir;
+static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
+{
+	seq_printf(m, "%3d%cnp=%ld "
+		   "qsp=%ld cbr=%ld cng=%ld gpc=%ld gps=%ld nf=%ld nn=%ld\n",
+		   rdp->cpu,
+		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
+		   rdp->n_rcu_pending,
+		   rdp->n_rp_qs_pending,
+		   rdp->n_rp_cb_ready,
+		   rdp->n_rp_cpu_needs_gp,
+		   rdp->n_rp_gp_completed,
+		   rdp->n_rp_gp_started,
+		   rdp->n_rp_need_fqs,
+		   rdp->n_rp_need_nothing);
+}
+
+static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp)
+{
+	int cpu;
+	struct rcu_data *rdp;
+
+	for_each_possible_cpu(cpu) {
+		rdp = rsp->rda[cpu];
+		if (rdp->beenonline)
+			print_one_rcu_pending(m, rdp);
+	}
+}
+
+static int show_rcu_pending(struct seq_file *m, void *unused)
+{
+	seq_puts(m, "rcu:\n");
+	print_rcu_pendings(m, &rcu_state);
+	seq_puts(m, "rcu_bh:\n");
+	print_rcu_pendings(m, &rcu_bh_state);
+	return 0;
+}
+
+static int rcu_pending_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcu_pending, NULL);
+}
+
+static struct file_operations rcu_pending_fops = {
+	.owner = THIS_MODULE,
+	.open = rcu_pending_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static struct dentry *rcudir;
+static struct dentry *datadir;
+static struct dentry *datadir_csv;
+static struct dentry *gpdir;
+static struct dentry *hierdir;
+static struct dentry *rcu_pendingdir;
+
 static int __init rcuclassic_trace_init(void)
 {
 	rcudir = debugfs_create_dir("rcu", NULL);
@@ -238,6 +294,11 @@ static int __init rcuclassic_trace_init(void)
 						NULL, &rcuhier_fops);
 	if (!hierdir)
 		goto free_out;
+
+	rcu_pendingdir = debugfs_create_file("rcu_pending", 0444, rcudir,
+						NULL, &rcu_pending_fops);
+	if (!rcu_pendingdir)
+		goto free_out;
 	return 0;
 free_out:
 	if (datadir)
@@ -257,6 +318,7 @@ static void __exit rcuclassic_trace_cleanup(void)
 	debugfs_remove(datadir_csv);
 	debugfs_remove(gpdir);
 	debugfs_remove(hierdir);
+	debugfs_remove(rcu_pendingdir);
 	debugfs_remove(rcudir);
 }
 
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 69d9cb921ffa..820c5af44f3e 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -300,7 +300,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
  * assigned pending owner [which might not have taken the
  * lock yet]:
  */
-static inline int try_to_steal_lock(struct rt_mutex *lock)
+static inline int try_to_steal_lock(struct rt_mutex *lock,
+				    struct task_struct *task)
 {
 	struct task_struct *pendowner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *next;
@@ -309,11 +310,11 @@ static inline int try_to_steal_lock(struct rt_mutex *lock)
 	if (!rt_mutex_owner_pending(lock))
 		return 0;
 
-	if (pendowner == current)
+	if (pendowner == task)
 		return 1;
 
 	spin_lock_irqsave(&pendowner->pi_lock, flags);
-	if (current->prio >= pendowner->prio) {
+	if (task->prio >= pendowner->prio) {
 		spin_unlock_irqrestore(&pendowner->pi_lock, flags);
 		return 0;
 	}
@@ -338,21 +339,21 @@ static inline int try_to_steal_lock(struct rt_mutex *lock)
 	 * We are going to steal the lock and a waiter was
 	 * enqueued on the pending owners pi_waiters queue. So
 	 * we have to enqueue this waiter into
-	 * current->pi_waiters list. This covers the case,
-	 * where current is boosted because it holds another
+	 * task->pi_waiters list. This covers the case,
+	 * where task is boosted because it holds another
 	 * lock and gets unboosted because the booster is
 	 * interrupted, so we would delay a waiter with higher
-	 * priority as current->normal_prio.
+	 * priority as task->normal_prio.
 	 *
 	 * Note: in the rare case of a SCHED_OTHER task changing
 	 * its priority and thus stealing the lock, next->task
-	 * might be current:
+	 * might be task:
 	 */
-	if (likely(next->task != current)) {
-		spin_lock_irqsave(&current->pi_lock, flags);
-		plist_add(&next->pi_list_entry, &current->pi_waiters);
-		__rt_mutex_adjust_prio(current);
-		spin_unlock_irqrestore(&current->pi_lock, flags);
+	if (likely(next->task != task)) {
+		spin_lock_irqsave(&task->pi_lock, flags);
+		plist_add(&next->pi_list_entry, &task->pi_waiters);
+		__rt_mutex_adjust_prio(task);
+		spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
 	return 1;
 }
@@ -389,7 +390,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
 	 */
 	mark_rt_mutex_waiters(lock);
 
-	if (rt_mutex_owner(lock) && !try_to_steal_lock(lock))
+	if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, current))
 		return 0;
 
 	/* We got the lock. */
@@ -411,6 +412,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
  */
 static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 				   struct rt_mutex_waiter *waiter,
+				   struct task_struct *task,
 				   int detect_deadlock)
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
@@ -418,21 +420,21 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	unsigned long flags;
 	int chain_walk = 0, res;
 
-	spin_lock_irqsave(&current->pi_lock, flags);
-	__rt_mutex_adjust_prio(current);
-	waiter->task = current;
+	spin_lock_irqsave(&task->pi_lock, flags);
+	__rt_mutex_adjust_prio(task);
+	waiter->task = task;
 	waiter->lock = lock;
-	plist_node_init(&waiter->list_entry, current->prio);
-	plist_node_init(&waiter->pi_list_entry, current->prio);
+	plist_node_init(&waiter->list_entry, task->prio);
+	plist_node_init(&waiter->pi_list_entry, task->prio);
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
 		top_waiter = rt_mutex_top_waiter(lock);
 	plist_add(&waiter->list_entry, &lock->wait_list);
 
-	current->pi_blocked_on = waiter;
+	task->pi_blocked_on = waiter;
 
-	spin_unlock_irqrestore(&current->pi_lock, flags);
+	spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		spin_lock_irqsave(&owner->pi_lock, flags);
@@ -460,7 +462,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	spin_unlock(&lock->wait_lock);
 
 	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
-					 current);
+					 task);
 
 	spin_lock(&lock->wait_lock);
 
@@ -605,6 +607,85 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
 }
 
+/**
+ * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
+ * @lock:		 the rt_mutex to take
+ * @state:		 the state the task should block in (TASK_INTERRUPTIBLE
+ * 			 or TASK_UNINTERRUPTIBLE)
+ * @timeout:		 the pre-initialized and started timer, or NULL for none
+ * @waiter:		 the pre-initialized rt_mutex_waiter
+ * @detect_deadlock:	 passed to task_blocks_on_rt_mutex
+ *
+ * lock->wait_lock must be held by the caller.
+ */
+static int __sched
+__rt_mutex_slowlock(struct rt_mutex *lock, int state,
+		    struct hrtimer_sleeper *timeout,
+		    struct rt_mutex_waiter *waiter,
+		    int detect_deadlock)
+{
+	int ret = 0;
+
+	for (;;) {
+		/* Try to acquire the lock: */
+		if (try_to_take_rt_mutex(lock))
+			break;
+
+		/*
+		 * TASK_INTERRUPTIBLE checks for signals and
+		 * timeout. Ignored otherwise.
+		 */
+		if (unlikely(state == TASK_INTERRUPTIBLE)) {
+			/* Signal pending? */
+			if (signal_pending(current))
+				ret = -EINTR;
+			if (timeout && !timeout->task)
+				ret = -ETIMEDOUT;
+			if (ret)
+				break;
+		}
+
+		/*
+		 * waiter->task is NULL the first time we come here and
+		 * when we have been woken up by the previous owner
+		 * but the lock got stolen by a higher prio task.
+		 */
+		if (!waiter->task) {
+			ret = task_blocks_on_rt_mutex(lock, waiter, current,
+						      detect_deadlock);
+			/*
+			 * If we got woken up by the owner then start loop
+			 * all over without going into schedule to try
+			 * to get the lock now:
+			 */
+			if (unlikely(!waiter->task)) {
+				/*
+				 * Reset the return value. We might
+				 * have returned with -EDEADLK and the
+				 * owner released the lock while we
+				 * were walking the pi chain.
+				 */
+				ret = 0;
+				continue;
+			}
+			if (unlikely(ret))
+				break;
+		}
+
+		spin_unlock(&lock->wait_lock);
+
+		debug_rt_mutex_print_deadlock(waiter);
+
+		if (waiter->task)
+			schedule_rt_mutex(lock);
+
+		spin_lock(&lock->wait_lock);
+		set_current_state(state);
+	}
+
+	return ret;
+}
+
 /*
  * Slow path lock function:
  */
@@ -636,62 +717,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 			timeout->task = NULL;
 	}
 
-	for (;;) {
-		/* Try to acquire the lock: */
-		if (try_to_take_rt_mutex(lock))
-			break;
-
-		/*
-		 * TASK_INTERRUPTIBLE checks for signals and
-		 * timeout. Ignored otherwise.
-		 */
-		if (unlikely(state == TASK_INTERRUPTIBLE)) {
-			/* Signal pending? */
-			if (signal_pending(current))
-				ret = -EINTR;
-			if (timeout && !timeout->task)
-				ret = -ETIMEDOUT;
-			if (ret)
-				break;
-		}
-
-		/*
-		 * waiter.task is NULL the first time we come here and
-		 * when we have been woken up by the previous owner
-		 * but the lock got stolen by a higher prio task.
-		 */
-		if (!waiter.task) {
-			ret = task_blocks_on_rt_mutex(lock, &waiter,
-						      detect_deadlock);
-			/*
-			 * If we got woken up by the owner then start loop
-			 * all over without going into schedule to try
-			 * to get the lock now:
-			 */
-			if (unlikely(!waiter.task)) {
-				/*
-				 * Reset the return value. We might
-				 * have returned with -EDEADLK and the
-				 * owner released the lock while we
-				 * were walking the pi chain.
-				 */
-				ret = 0;
-				continue;
-			}
-			if (unlikely(ret))
-				break;
-		}
-
-		spin_unlock(&lock->wait_lock);
-
-		debug_rt_mutex_print_deadlock(&waiter);
-
-		if (waiter.task)
-			schedule_rt_mutex(lock);
-
-		spin_lock(&lock->wait_lock);
-		set_current_state(state);
-	}
+	ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
+				  detect_deadlock);
 
 	set_current_state(TASK_RUNNING);
 
@@ -864,9 +891,9 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock,
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
 /**
- * rt_mutex_lock_interruptible_ktime - lock a rt_mutex interruptible
- *				       the timeout structure is provided
- *				       by the caller
+ * rt_mutex_timed_lock - lock a rt_mutex interruptible
+ *			the timeout structure is provided
+ *			by the caller
  *
  * @lock: 		the rt_mutex to be locked
  * @timeout:		timeout structure or NULL (no timeout)
@@ -913,7 +940,7 @@ void __sched rt_mutex_unlock(struct rt_mutex *lock)
 }
 EXPORT_SYMBOL_GPL(rt_mutex_unlock);
 
-/***
+/**
  * rt_mutex_destroy - mark a mutex unusable
  * @lock: the mutex to be destroyed
  *
@@ -985,6 +1012,59 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 	rt_mutex_deadlock_account_unlock(proxy_owner);
 }
 
+/**
+ * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ * @detect_deadlock:	perform deadlock detection (1) or not (0)
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for FUTEX_REQUEUE_PI support.
+ */
+int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+			      struct rt_mutex_waiter *waiter,
+			      struct task_struct *task, int detect_deadlock)
+{
+	int ret;
+
+	spin_lock(&lock->wait_lock);
+
+	mark_rt_mutex_waiters(lock);
+
+	if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
+		/* We got the lock for task. */
+		debug_rt_mutex_lock(lock);
+
+		rt_mutex_set_owner(lock, task, 0);
+
+		rt_mutex_deadlock_account_lock(lock, task);
+		return 1;
+	}
+
+	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+
+
+	if (ret && !waiter->task) {
+		/*
+		 * Reset the return value. We might have
+		 * returned with -EDEADLK and the owner
+		 * released the lock while we were walking the
+		 * pi chain.  Let the waiter sort it out.
+		 */
+		ret = 0;
+	}
+	spin_unlock(&lock->wait_lock);
+
+	debug_rt_mutex_print_deadlock(waiter);
+
+	return ret;
+}
+
 /**
  * rt_mutex_next_owner - return the next owner of the lock
  *
@@ -1004,3 +1084,57 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
 
 	return rt_mutex_top_waiter(lock)->task;
 }
+
+/**
+ * rt_mutex_finish_proxy_lock() - Complete lock acquisition
+ * @lock:		the rt_mutex we were woken on
+ * @to:			the timeout, null if none. hrtimer should already have
+ * 			been started.
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @detect_deadlock:	perform deadlock detection (1) or not (0)
+ *
+ * Complete the lock acquisition started our behalf by another thread.
+ *
+ * Returns:
+ *  0 - success
+ * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
+ *
+ * Special API call for PI-futex requeue support
+ */
+int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+			       struct hrtimer_sleeper *to,
+			       struct rt_mutex_waiter *waiter,
+			       int detect_deadlock)
+{
+	int ret;
+
+	spin_lock(&lock->wait_lock);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
+				  detect_deadlock);
+
+	set_current_state(TASK_RUNNING);
+
+	if (unlikely(waiter->task))
+		remove_waiter(lock, waiter);
+
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+
+	spin_unlock(&lock->wait_lock);
+
+	/*
+	 * Readjust priority, when we did not get the lock. We might have been
+	 * the pending owner and boosted. Since we did not take the lock, the
+	 * PI boost has to go.
+	 */
+	if (unlikely(ret))
+		rt_mutex_adjust_prio(current);
+
+	return ret;
+}
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index e124bf5800ea..97a2f81866af 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -120,6 +120,14 @@ extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
+extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task,
+				     int detect_deadlock);
+extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+				      struct hrtimer_sleeper *to,
+				      struct rt_mutex_waiter *waiter,
+				      int detect_deadlock);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"
diff --git a/kernel/sched.c b/kernel/sched.c
index 26efa475bdc1..f04aa9664504 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -39,6 +39,7 @@
 #include <linux/completion.h>
 #include <linux/kernel_stat.h>
 #include <linux/debug_locks.h>
+#include <linux/perf_counter.h>
 #include <linux/security.h>
 #include <linux/notifier.h>
 #include <linux/profile.h>
@@ -68,17 +69,18 @@
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
-#include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
-#include <trace/sched.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
 
 #include "sched_cpupri.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+
 /*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
@@ -118,12 +120,6 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
-DEFINE_TRACE(sched_wait_task);
-DEFINE_TRACE(sched_wakeup);
-DEFINE_TRACE(sched_wakeup_new);
-DEFINE_TRACE(sched_switch);
-DEFINE_TRACE(sched_migrate_task);
-
 #ifdef CONFIG_SMP
 
 static void double_rq_lock(struct rq *rq1, struct rq *rq2);
@@ -584,6 +580,7 @@ struct rq {
 	struct load_weight load;
 	unsigned long nr_load_updates;
 	u64 nr_switches;
+	u64 nr_migrations_in;
 
 	struct cfs_rq cfs;
 	struct rt_rq rt;
@@ -630,6 +627,10 @@ struct rq {
 	struct list_head migration_queue;
 #endif
 
+	/* calc_load related fields */
+	unsigned long calc_load_update;
+	long calc_load_active;
+
 #ifdef CONFIG_SCHED_HRTICK
 #ifdef CONFIG_SMP
 	int hrtick_csd_pending;
@@ -692,7 +693,7 @@ static inline int cpu_of(struct rq *rq)
 #define task_rq(p)		cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
 
-static inline void update_rq_clock(struct rq *rq)
+inline void update_rq_clock(struct rq *rq)
 {
 	rq->clock = sched_clock_cpu(cpu_of(rq));
 }
@@ -1728,6 +1729,8 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 }
 #endif
 
+static void calc_load_account_active(struct rq *this_rq);
+
 #include "sched_stats.h"
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -1958,7 +1961,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
 	clock_offset = old_rq->clock - new_rq->clock;
 
-	trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+	trace_sched_migrate_task(p, new_cpu);
 
 #ifdef CONFIG_SCHEDSTATS
 	if (p->se.wait_start)
@@ -1967,12 +1970,16 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		p->se.sleep_start -= clock_offset;
 	if (p->se.block_start)
 		p->se.block_start -= clock_offset;
+#endif
 	if (old_cpu != new_cpu) {
-		schedstat_inc(p, se.nr_migrations);
+		p->se.nr_migrations++;
+		new_rq->nr_migrations_in++;
+#ifdef CONFIG_SCHEDSTATS
 		if (task_hot(p, old_rq->clock, NULL))
 			schedstat_inc(p, se.nr_forced2_migrations);
-	}
 #endif
+		perf_counter_task_migration(p, new_cpu);
+	}
 	p->se.vruntime -= old_cfsrq->min_vruntime -
 					 new_cfsrq->min_vruntime;
 
@@ -2014,6 +2021,49 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 	return 1;
 }
 
+/*
+ * wait_task_context_switch -	wait for a thread to complete at least one
+ *				context switch.
+ *
+ * @p must not be current.
+ */
+void wait_task_context_switch(struct task_struct *p)
+{
+	unsigned long nvcsw, nivcsw, flags;
+	int running;
+	struct rq *rq;
+
+	nvcsw	= p->nvcsw;
+	nivcsw	= p->nivcsw;
+	for (;;) {
+		/*
+		 * The runqueue is assigned before the actual context
+		 * switch. We need to take the runqueue lock.
+		 *
+		 * We could check initially without the lock but it is
+		 * very likely that we need to take the lock in every
+		 * iteration.
+		 */
+		rq = task_rq_lock(p, &flags);
+		running = task_running(rq, p);
+		task_rq_unlock(rq, &flags);
+
+		if (likely(!running))
+			break;
+		/*
+		 * The switch count is incremented before the actual
+		 * context switch. We thus wait for two switches to be
+		 * sure at least one completed.
+		 */
+		if ((p->nvcsw - nvcsw) > 1)
+			break;
+		if ((p->nivcsw - nivcsw) > 1)
+			break;
+
+		cpu_relax();
+	}
+}
+
 /*
  * wait_task_inactive - wait for a thread to unschedule.
  *
@@ -2324,6 +2374,27 @@ static int sched_balance_self(int cpu, int flag)
 
 #endif /* CONFIG_SMP */
 
+/**
+ * task_oncpu_function_call - call a function on the cpu on which a task runs
+ * @p:		the task to evaluate
+ * @func:	the function to be called
+ * @info:	the function call argument
+ *
+ * Calls the function @func when the task is currently running. This might
+ * be on the current CPU, which just calls the function directly
+ */
+void task_oncpu_function_call(struct task_struct *p,
+			      void (*func) (void *info), void *info)
+{
+	int cpu;
+
+	preempt_disable();
+	cpu = task_cpu(p);
+	if (task_curr(p))
+		smp_call_function_single(cpu, func, info, 1);
+	preempt_enable();
+}
+
 /***
  * try_to_wake_up - wake up a thread
  * @p: the to-be-woken-up thread
@@ -2458,6 +2529,17 @@ out:
 	return success;
 }
 
+/**
+ * wake_up_process - Wake up a specific process
+ * @p: The process to be woken up.
+ *
+ * Attempt to wake up the nominated process and move it to the set of runnable
+ * processes.  Returns 1 if the process was woken up, 0 if it was already
+ * running.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
 int wake_up_process(struct task_struct *p)
 {
 	return try_to_wake_up(p, TASK_ALL, 0);
@@ -2480,6 +2562,7 @@ static void __sched_fork(struct task_struct *p)
 	p->se.exec_start		= 0;
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
+	p->se.nr_migrations		= 0;
 	p->se.last_wakeup		= 0;
 	p->se.avg_overlap		= 0;
 	p->se.start_runtime		= 0;
@@ -2710,6 +2793,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	 */
 	prev_state = prev->state;
 	finish_arch_switch(prev);
+	perf_counter_task_sched_in(current, cpu_of(rq));
 	finish_lock_switch(rq, prev);
 #ifdef CONFIG_SMP
 	if (post_schedule)
@@ -2766,7 +2850,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 * combine the page table reload and the switch backend into
 	 * one hypercall.
 	 */
-	arch_enter_lazy_cpu_mode();
+	arch_start_context_switch(prev);
 
 	if (unlikely(!mm)) {
 		next->active_mm = oldmm;
@@ -2856,19 +2940,81 @@ unsigned long nr_iowait(void)
 	return sum;
 }
 
-unsigned long nr_active(void)
+/* Variables and functions for calc_load */
+static atomic_long_t calc_load_tasks;
+static unsigned long calc_load_update;
+unsigned long avenrun[3];
+EXPORT_SYMBOL(avenrun);
+
+/**
+ * get_avenrun - get the load average array
+ * @loads:	pointer to dest load array
+ * @offset:	offset to add
+ * @shift:	shift count to shift the result left
+ *
+ * These values are estimates at best, so no need for locking.
+ */
+void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
 {
-	unsigned long i, running = 0, uninterruptible = 0;
+	loads[0] = (avenrun[0] + offset) << shift;
+	loads[1] = (avenrun[1] + offset) << shift;
+	loads[2] = (avenrun[2] + offset) << shift;
+}
 
-	for_each_online_cpu(i) {
-		running += cpu_rq(i)->nr_running;
-		uninterruptible += cpu_rq(i)->nr_uninterruptible;
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+	load *= exp;
+	load += active * (FIXED_1 - exp);
+	return load >> FSHIFT;
+}
+
+/*
+ * calc_load - update the avenrun load estimates 10 ticks after the
+ * CPUs have updated calc_load_tasks.
+ */
+void calc_global_load(void)
+{
+	unsigned long upd = calc_load_update + 10;
+	long active;
+
+	if (time_before(jiffies, upd))
+		return;
+
+	active = atomic_long_read(&calc_load_tasks);
+	active = active > 0 ? active * FIXED_1 : 0;
+
+	avenrun[0] = calc_load(avenrun[0], EXP_1, active);
+	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
+	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
+
+	calc_load_update += LOAD_FREQ;
+}
+
+/*
+ * Either called from update_cpu_load() or from a cpu going idle
+ */
+static void calc_load_account_active(struct rq *this_rq)
+{
+	long nr_active, delta;
+
+	nr_active = this_rq->nr_running;
+	nr_active += (long) this_rq->nr_uninterruptible;
+
+	if (nr_active != this_rq->calc_load_active) {
+		delta = nr_active - this_rq->calc_load_active;
+		this_rq->calc_load_active = nr_active;
+		atomic_long_add(delta, &calc_load_tasks);
 	}
+}
 
-	if (unlikely((long)uninterruptible < 0))
-		uninterruptible = 0;
-
-	return running + uninterruptible;
+/*
+ * Externally visible per-cpu scheduler statistics:
+ * cpu_nr_migrations(cpu) - number of migrations into that cpu
+ */
+u64 cpu_nr_migrations(int cpu)
+{
+	return cpu_rq(cpu)->nr_migrations_in;
 }
 
 /*
@@ -2899,6 +3045,11 @@ static void update_cpu_load(struct rq *this_rq)
 			new_load += scale-1;
 		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
 	}
+
+	if (time_after_eq(jiffies, this_rq->calc_load_update)) {
+		this_rq->calc_load_update += LOAD_FREQ;
+		calc_load_account_active(this_rq);
+	}
 }
 
 #ifdef CONFIG_SMP
@@ -4240,10 +4391,126 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 static struct {
 	atomic_t load_balancer;
 	cpumask_var_t cpu_mask;
+	cpumask_var_t ilb_grp_nohz_mask;
 } nohz ____cacheline_aligned = {
 	.load_balancer = ATOMIC_INIT(-1),
 };
 
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * lowest_flag_domain - Return lowest sched_domain containing flag.
+ * @cpu:	The cpu whose lowest level of sched domain is to
+ *		be returned.
+ * @flag:	The flag to check for the lowest sched_domain
+ *		for the given cpu.
+ *
+ * Returns the lowest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
+{
+	struct sched_domain *sd;
+
+	for_each_domain(cpu, sd)
+		if (sd && (sd->flags & flag))
+			break;
+
+	return sd;
+}
+
+/**
+ * for_each_flag_domain - Iterates over sched_domains containing the flag.
+ * @cpu:	The cpu whose domains we're iterating over.
+ * @sd:		variable holding the value of the power_savings_sd
+ *		for cpu.
+ * @flag:	The flag to filter the sched_domains to be iterated.
+ *
+ * Iterates over all the scheduler domains for a given cpu that has the 'flag'
+ * set, starting from the lowest sched_domain to the highest.
+ */
+#define for_each_flag_domain(cpu, sd, flag) \
+	for (sd = lowest_flag_domain(cpu, flag); \
+		(sd && (sd->flags & flag)); sd = sd->parent)
+
+/**
+ * is_semi_idle_group - Checks if the given sched_group is semi-idle.
+ * @ilb_group:	group to be checked for semi-idleness
+ *
+ * Returns:	1 if the group is semi-idle. 0 otherwise.
+ *
+ * We define a sched_group to be semi idle if it has atleast one idle-CPU
+ * and atleast one non-idle CPU. This helper function checks if the given
+ * sched_group is semi-idle or not.
+ */
+static inline int is_semi_idle_group(struct sched_group *ilb_group)
+{
+	cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
+					sched_group_cpus(ilb_group));
+
+	/*
+	 * A sched_group is semi-idle when it has atleast one busy cpu
+	 * and atleast one idle cpu.
+	 */
+	if (cpumask_empty(nohz.ilb_grp_nohz_mask))
+		return 0;
+
+	if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
+		return 0;
+
+	return 1;
+}
+/**
+ * find_new_ilb - Finds the optimum idle load balancer for nomination.
+ * @cpu:	The cpu which is nominating a new idle_load_balancer.
+ *
+ * Returns:	Returns the id of the idle load balancer if it exists,
+ *		Else, returns >= nr_cpu_ids.
+ *
+ * This algorithm picks the idle load balancer such that it belongs to a
+ * semi-idle powersavings sched_domain. The idea is to try and avoid
+ * completely idle packages/cores just for the purpose of idle load balancing
+ * when there are other idle cpu's which are better suited for that job.
+ */
+static int find_new_ilb(int cpu)
+{
+	struct sched_domain *sd;
+	struct sched_group *ilb_group;
+
+	/*
+	 * Have idle load balancer selection from semi-idle packages only
+	 * when power-aware load balancing is enabled
+	 */
+	if (!(sched_smt_power_savings || sched_mc_power_savings))
+		goto out_done;
+
+	/*
+	 * Optimize for the case when we have no idle CPUs or only one
+	 * idle CPU. Don't walk the sched_domain hierarchy in such cases
+	 */
+	if (cpumask_weight(nohz.cpu_mask) < 2)
+		goto out_done;
+
+	for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
+		ilb_group = sd->groups;
+
+		do {
+			if (is_semi_idle_group(ilb_group))
+				return cpumask_first(nohz.ilb_grp_nohz_mask);
+
+			ilb_group = ilb_group->next;
+
+		} while (ilb_group != sd->groups);
+	}
+
+out_done:
+	return cpumask_first(nohz.cpu_mask);
+}
+#else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
+static inline int find_new_ilb(int call_cpu)
+{
+	return cpumask_first(nohz.cpu_mask);
+}
+#endif
+
 /*
  * This routine will try to nominate the ilb (idle load balancing)
  * owner among the cpus whose ticks are stopped. ilb owner will do the idle
@@ -4298,8 +4565,24 @@ int select_nohz_load_balancer(int stop_tick)
 			/* make me the ilb owner */
 			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
 				return 1;
-		} else if (atomic_read(&nohz.load_balancer) == cpu)
+		} else if (atomic_read(&nohz.load_balancer) == cpu) {
+			int new_ilb;
+
+			if (!(sched_smt_power_savings ||
+						sched_mc_power_savings))
+				return 1;
+			/*
+			 * Check to see if there is a more power-efficient
+			 * ilb.
+			 */
+			new_ilb = find_new_ilb(cpu);
+			if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
+				atomic_set(&nohz.load_balancer, -1);
+				resched_cpu(new_ilb);
+				return 0;
+			}
 			return 1;
+		}
 	} else {
 		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
 			return 0;
@@ -4468,15 +4751,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu)
 		}
 
 		if (atomic_read(&nohz.load_balancer) == -1) {
-			/*
-			 * simple selection for now: Nominate the
-			 * first cpu in the nohz list to be the next
-			 * ilb owner.
-			 *
-			 * TBD: Traverse the sched domains and nominate
-			 * the nearest cpu in the nohz.cpu_mask.
-			 */
-			int ilb = cpumask_first(nohz.cpu_mask);
+			int ilb = find_new_ilb(cpu);
 
 			if (ilb < nr_cpu_ids)
 				resched_cpu(ilb);
@@ -4840,6 +5115,8 @@ void scheduler_tick(void)
 	curr->sched_class->task_tick(rq, curr, 0);
 	spin_unlock(&rq->lock);
 
+	perf_counter_task_tick(curr, cpu);
+
 #ifdef CONFIG_SMP
 	rq->idle_at_tick = idle_cpu(cpu);
 	trigger_load_balance(rq, cpu);
@@ -5007,13 +5284,15 @@ pick_next_task(struct rq *rq)
 /*
  * schedule() is the main scheduler function.
  */
-asmlinkage void __sched __schedule(void)
+asmlinkage void __sched schedule(void)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
 	struct rq *rq;
 	int cpu;
 
+need_resched:
+	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
 	rcu_qsctr_inc(cpu);
@@ -5053,6 +5332,7 @@ need_resched_nonpreemptible:
 
 	if (likely(prev != next)) {
 		sched_info_switch(prev, next);
+		perf_counter_task_sched_out(prev, next, cpu);
 
 		rq->nr_switches++;
 		rq->curr = next;
@@ -5070,15 +5350,9 @@ need_resched_nonpreemptible:
 
 	if (unlikely(reacquire_kernel_lock(current) < 0))
 		goto need_resched_nonpreemptible;
-}
 
-asmlinkage void __sched schedule(void)
-{
-need_resched:
-	preempt_disable();
-	__schedule();
 	preempt_enable_no_resched();
-	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+	if (need_resched())
 		goto need_resched;
 }
 EXPORT_SYMBOL(schedule);
@@ -5221,7 +5495,7 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, int sync, void *key)
 {
 	wait_queue_t *curr, *next;
@@ -5241,6 +5515,9 @@ void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void __wake_up(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -5279,6 +5556,9 @@ void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
  * with each other. This can prevent needless bouncing between CPUs.
  *
  * On UP it can prevent extra preemption.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -5315,6 +5595,9 @@ EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
  * awakened in the same order in which they were queued.
  *
  * See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void complete(struct completion *x)
 {
@@ -5332,6 +5615,9 @@ EXPORT_SYMBOL(complete);
  * @x:  holds the state of this particular completion
  *
  * This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void complete_all(struct completion *x)
 {
@@ -6490,8 +6776,9 @@ void sched_show_task(struct task_struct *p)
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
-	printk(KERN_CONT "%5lu %5d %6d\n", free,
-		task_pid_nr(p), task_pid_nr(p->real_parent));
+	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
+		task_pid_nr(p), task_pid_nr(p->real_parent),
+		(unsigned long)task_thread_info(p)->flags);
 
 	show_stack(p, NULL);
 }
@@ -6970,6 +7257,14 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 
 	}
 }
+
+/*
+ * remove the tasks which were accounted by rq from calc_load_tasks.
+ */
+static void calc_global_load_remove(struct rq *rq)
+{
+	atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+}
 #endif /* CONFIG_HOTPLUG_CPU */
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
@@ -7204,6 +7499,8 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		/* Update our root-domain */
 		rq = cpu_rq(cpu);
 		spin_lock_irqsave(&rq->lock, flags);
+		rq->calc_load_update = calc_load_update;
+		rq->calc_load_active = 0;
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 
@@ -7243,7 +7540,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		cpuset_unlock();
 		migrate_nr_uninterruptible(rq);
 		BUG_ON(rq->nr_running != 0);
-
+		calc_global_load_remove(rq);
 		/*
 		 * No need to migrate the tasks: it was best-effort if
 		 * they didn't take sched_hotcpu_mutex. Just wake up
@@ -7279,8 +7576,10 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	return NOTIFY_OK;
 }
 
-/* Register at highest priority so that task migration (migrate_all_tasks)
- * happens before everything else.
+/*
+ * Register at high priority so that task migration (migrate_all_tasks)
+ * happens before everything else.  This has to be lower priority than
+ * the notifier in the perf_counter subsystem, though.
  */
 static struct notifier_block __cpuinitdata migration_notifier = {
 	.notifier_call = migration_call,
@@ -7525,24 +7824,21 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 
 static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
 {
+	gfp_t gfp = GFP_KERNEL;
+
 	memset(rd, 0, sizeof(*rd));
 
-	if (bootmem) {
-		alloc_bootmem_cpumask_var(&def_root_domain.span);
-		alloc_bootmem_cpumask_var(&def_root_domain.online);
-		alloc_bootmem_cpumask_var(&def_root_domain.rto_mask);
-		cpupri_init(&rd->cpupri, true);
-		return 0;
-	}
+	if (bootmem)
+		gfp = GFP_NOWAIT;
 
-	if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->span, gfp))
 		goto out;
-	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->online, gfp))
 		goto free_span;
-	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->rto_mask, gfp))
 		goto free_online;
 
-	if (cpupri_init(&rd->cpupri, false) != 0)
+	if (cpupri_init(&rd->cpupri, bootmem) != 0)
 		goto free_rto_mask;
 	return 0;
 
@@ -7753,8 +8049,9 @@ int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 
 /*
  * The cpus mask in sched_group and sched_domain hangs off the end.
- * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space
- * for nr_cpu_ids < CONFIG_NR_CPUS.
+ *
+ * ( See the the comments in include/linux/sched.h:struct sched_group
+ *   and struct sched_domain. )
  */
 struct static_sched_group {
 	struct sched_group sg;
@@ -7875,7 +8172,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
 			struct sched_domain *sd;
 
 			sd = &per_cpu(phys_domains, j).sd;
-			if (j != cpumask_first(sched_group_cpus(sd->groups))) {
+			if (j != group_first_cpu(sd->groups)) {
 				/*
 				 * Only add "power" once for each
 				 * physical package.
@@ -7953,7 +8250,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	WARN_ON(!sd || !sd->groups);
 
-	if (cpu != cpumask_first(sched_group_cpus(sd->groups)))
+	if (cpu != group_first_cpu(sd->groups))
 		return;
 
 	child = sd->child;
@@ -8865,7 +9162,7 @@ void __init sched_init(void)
 	 * we use alloc_bootmem().
 	 */
 	if (alloc_size) {
-		ptr = (unsigned long)alloc_bootmem(alloc_size);
+		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		init_task_group.se = (struct sched_entity **)ptr;
@@ -8938,6 +9235,8 @@ void __init sched_init(void)
 		rq = cpu_rq(i);
 		spin_lock_init(&rq->lock);
 		rq->nr_running = 0;
+		rq->calc_load_active = 0;
+		rq->calc_load_update = jiffies + LOAD_FREQ;
 		init_cfs_rq(&rq->cfs, rq);
 		init_rt_rq(&rq->rt, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -8958,7 +9257,7 @@ void __init sched_init(void)
 		 * 1024) and two child groups A0 and A1 (of weight 1024 each),
 		 * then A0's share of the cpu resource is:
 		 *
-		 * 	A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
+		 *	A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
 		 *
 		 * We achieve this by letting init_task_group's tasks sit
 		 * directly in rq->cfs (i.e init_task_group->se[] = NULL).
@@ -9045,20 +9344,26 @@ void __init sched_init(void)
 	 * when this runqueue becomes "idle".
 	 */
 	init_idle(current, smp_processor_id());
+
+	calc_load_update = jiffies + LOAD_FREQ;
+
 	/*
 	 * During early bootup we pretend to be a normal task:
 	 */
 	current->sched_class = &fair_sched_class;
 
 	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
-	alloc_bootmem_cpumask_var(&nohz_cpu_mask);
+	alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ
-	alloc_bootmem_cpumask_var(&nohz.cpu_mask);
+	alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+	alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
 #endif
-	alloc_bootmem_cpumask_var(&cpu_isolated_map);
+	alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
 
+	perf_counter_init();
+
 	scheduler_running = 1;
 }
 
@@ -9800,6 +10105,13 @@ static int sched_rt_global_constraints(void)
 	if (sysctl_sched_rt_period <= 0)
 		return -EINVAL;
 
+	/*
+	 * There's always some RT tasks in the root group
+	 * -- migration, kstopmachine etc..
+	 */
+	if (sysctl_sched_rt_runtime == 0)
+		return -EBUSY;
+
 	spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
 	for_each_possible_cpu(i) {
 		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index 344712a5e3ed..7deffc9f0e5f 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -154,8 +154,12 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
  */
 int __init_refok cpupri_init(struct cpupri *cp, bool bootmem)
 {
+	gfp_t gfp = GFP_KERNEL;
 	int i;
 
+	if (bootmem)
+		gfp = GFP_NOWAIT;
+
 	memset(cp, 0, sizeof(*cp));
 
 	for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
@@ -163,9 +167,7 @@ int __init_refok cpupri_init(struct cpupri *cp, bool bootmem)
 
 		spin_lock_init(&vec->lock);
 		vec->count = 0;
-		if (bootmem)
-			alloc_bootmem_cpumask_var(&vec->mask);
-		else if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL))
+		if (!zalloc_cpumask_var(&vec->mask, gfp))
 			goto cleanup;
 	}
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 3816f217f119..5f9650e8fe75 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1487,17 +1487,10 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 
 	find_matching_se(&se, &pse);
 
-	while (se) {
-		BUG_ON(!pse);
+	BUG_ON(!pse);
 
-		if (wakeup_preempt_entity(se, pse) == 1) {
-			resched_task(curr);
-			break;
-		}
-
-		se = parent_entity(se);
-		pse = parent_entity(pse);
-	}
+	if (wakeup_preempt_entity(se, pse) == 1)
+		resched_task(curr);
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 8a21a2e28c13..499672c10cbd 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -22,7 +22,8 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sy
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	schedstat_inc(rq, sched_goidle);
-
+	/* adjust the active tasks as we might go into a long sleep */
+	calc_load_account_active(rq);
 	return rq->idle;
 }
 
diff --git a/kernel/signal.c b/kernel/signal.c
index d8034737db4c..809a228019ad 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -27,7 +27,7 @@
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
 #include <linux/nsproxy.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #include <asm/param.h>
 #include <asm/uaccess.h>
@@ -41,8 +41,6 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
-DEFINE_TRACE(sched_signal_send);
-
 static void __user *sig_handler(struct task_struct *t, int sig)
 {
 	return t->sighand->action[sig - 1].sa.sa_handler;
@@ -249,14 +247,19 @@ void flush_sigqueue(struct sigpending *queue)
 /*
  * Flush all pending signals for a task.
  */
+void __flush_signals(struct task_struct *t)
+{
+	clear_tsk_thread_flag(t, TIF_SIGPENDING);
+	flush_sigqueue(&t->pending);
+	flush_sigqueue(&t->signal->shared_pending);
+}
+
 void flush_signals(struct task_struct *t)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&t->sighand->siglock, flags);
-	clear_tsk_thread_flag(t, TIF_SIGPENDING);
-	flush_sigqueue(&t->pending);
-	flush_sigqueue(&t->signal->shared_pending);
+	__flush_signals(t);
 	spin_unlock_irqrestore(&t->sighand->siglock, flags);
 }
 
@@ -2278,24 +2281,17 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
 	return kill_something_info(sig, &info, pid);
 }
 
-static int do_tkill(pid_t tgid, pid_t pid, int sig)
+static int
+do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 {
-	int error;
-	struct siginfo info;
 	struct task_struct *p;
 	unsigned long flags;
-
-	error = -ESRCH;
-	info.si_signo = sig;
-	info.si_errno = 0;
-	info.si_code = SI_TKILL;
-	info.si_pid = task_tgid_vnr(current);
-	info.si_uid = current_uid();
+	int error = -ESRCH;
 
 	rcu_read_lock();
 	p = find_task_by_vpid(pid);
 	if (p && (tgid <= 0 || task_tgid_vnr(p) == tgid)) {
-		error = check_kill_permission(sig, &info, p);
+		error = check_kill_permission(sig, info, p);
 		/*
 		 * The null signal is a permissions and process existence
 		 * probe.  No signal is actually delivered.
@@ -2305,7 +2301,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig)
 		 * signal is private anyway.
 		 */
 		if (!error && sig && lock_task_sighand(p, &flags)) {
-			error = specific_send_sig_info(sig, &info, p);
+			error = specific_send_sig_info(sig, info, p);
 			unlock_task_sighand(p, &flags);
 		}
 	}
@@ -2314,6 +2310,19 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig)
 	return error;
 }
 
+static int do_tkill(pid_t tgid, pid_t pid, int sig)
+{
+	struct siginfo info;
+
+	info.si_signo = sig;
+	info.si_errno = 0;
+	info.si_code = SI_TKILL;
+	info.si_pid = task_tgid_vnr(current);
+	info.si_uid = current_uid();
+
+	return do_send_specific(tgid, pid, sig, &info);
+}
+
 /**
  *  sys_tgkill - send signal to one specific thread
  *  @tgid: the thread group ID of the thread
@@ -2363,6 +2372,32 @@ SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig,
 	return kill_proc_info(sig, &info, pid);
 }
 
+long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info)
+{
+	/* This is only valid for single tasks */
+	if (pid <= 0 || tgid <= 0)
+		return -EINVAL;
+
+	/* Not even root can pretend to send signals from the kernel.
+	   Nor can they impersonate a kill(), which adds source info.  */
+	if (info->si_code >= 0)
+		return -EPERM;
+	info->si_signo = sig;
+
+	return do_send_specific(tgid, pid, sig, info);
+}
+
+SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig,
+		siginfo_t __user *, uinfo)
+{
+	siginfo_t info;
+
+	if (copy_from_user(&info, uinfo, sizeof(siginfo_t)))
+		return -EFAULT;
+
+	return do_rt_tgsigqueueinfo(tgid, pid, sig, &info);
+}
+
 int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
 {
 	struct task_struct *t = current;
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index b28d19135f43..521ed2004d63 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -372,8 +372,8 @@ static int slow_work_thread(void *_data)
 		vsmax *= atomic_read(&slow_work_thread_count);
 		vsmax /= 100;
 
-		prepare_to_wait(&slow_work_thread_wq, &wait,
-				TASK_INTERRUPTIBLE);
+		prepare_to_wait_exclusive(&slow_work_thread_wq, &wait,
+					  TASK_INTERRUPTIBLE);
 		if (!freezing(current) &&
 		    !slow_work_threads_should_exit &&
 		    !slow_work_available(vsmax) &&
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b525dd348511..258885a543db 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -24,7 +24,9 @@
 #include <linux/ftrace.h>
 #include <linux/smp.h>
 #include <linux/tick.h>
-#include <trace/irq.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/irq.h>
 
 #include <asm/irq.h>
 /*
@@ -186,9 +188,6 @@ EXPORT_SYMBOL(local_bh_enable_ip);
  */
 #define MAX_SOFTIRQ_RESTART 10
 
-DEFINE_TRACE(softirq_entry);
-DEFINE_TRACE(softirq_exit);
-
 asmlinkage void __do_softirq(void)
 {
 	struct softirq_action *h;
@@ -828,7 +827,7 @@ int __init __weak arch_early_irq_init(void)
 	return 0;
 }
 
-int __weak arch_init_chip_data(struct irq_desc *desc, int cpu)
+int __weak arch_init_chip_data(struct irq_desc *desc, int node)
 {
 	return 0;
 }
diff --git a/kernel/sys.c b/kernel/sys.c
index e7998cf31498..438d99a38c87 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -14,6 +14,7 @@
 #include <linux/prctl.h>
 #include <linux/highuid.h>
 #include <linux/fs.h>
+#include <linux/perf_counter.h>
 #include <linux/resource.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
@@ -1793,6 +1794,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		case PR_SET_TSC:
 			error = SET_TSC_CTL(arg2);
 			break;
+		case PR_TASK_PERF_COUNTERS_DISABLE:
+			error = perf_counter_task_disable();
+			break;
+		case PR_TASK_PERF_COUNTERS_ENABLE:
+			error = perf_counter_task_enable();
+			break;
 		case PR_GET_TIMERSLACK:
 			error = current->timer_slack_ns;
 			break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 27dad2967387..68320f6b07b5 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -175,3 +175,6 @@ cond_syscall(compat_sys_timerfd_settime);
 cond_syscall(compat_sys_timerfd_gettime);
 cond_syscall(sys_eventfd);
 cond_syscall(sys_eventfd2);
+
+/* performance counters: */
+cond_syscall(sys_perf_counter_open);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b2970d56fb76..ce664f98e3fb 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -49,6 +49,7 @@
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
 #include <linux/slow-work.h>
+#include <linux/perf_counter.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -114,6 +115,7 @@ static int ngroups_max = NGROUPS_MAX;
 
 #ifdef CONFIG_MODULES
 extern char modprobe_path[];
+extern int modules_disabled;
 #endif
 #ifdef CONFIG_CHR_DEV_SG
 extern int sg_big_buff;
@@ -534,6 +536,17 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dostring,
 		.strategy	= &sysctl_string,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "modules_disabled",
+		.data		= &modules_disabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		/* only handle a transition from default "0" to "1" */
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &one,
+	},
 #endif
 #if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
 	{
@@ -729,6 +742,14 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0444,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "bootloader_version",
+		.data		= &bootloader_version,
+		.maxlen		= sizeof (int),
+		.mode		= 0444,
+		.proc_handler	= &proc_dointvec,
+	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "kstack_depth_to_print",
@@ -912,6 +933,32 @@ static struct ctl_table kern_table[] = {
 		.child		= slow_work_sysctls,
 	},
 #endif
+#ifdef CONFIG_PERF_COUNTERS
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "perf_counter_paranoid",
+		.data		= &sysctl_perf_counter_paranoid,
+		.maxlen		= sizeof(sysctl_perf_counter_paranoid),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "perf_counter_mlock_kb",
+		.data		= &sysctl_perf_counter_mlock,
+		.maxlen		= sizeof(sysctl_perf_counter_mlock),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "perf_counter_max_sample_rate",
+		.data		= &sysctl_perf_counter_sample_rate,
+		.maxlen		= sizeof(sysctl_perf_counter_sample_rate),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
@@ -1225,7 +1272,6 @@ static struct ctl_table vm_table[] = {
 		.strategy	= &sysctl_jiffies,
 	},
 #endif
-#ifdef CONFIG_SECURITY
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "mmap_min_addr",
@@ -1234,7 +1280,6 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_doulongvec_minmax,
 	},
-#endif
 #ifdef CONFIG_NUMA
 	{
 		.ctl_name	= CTL_UNNUMBERED,
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index ecfd7b5187e0..80189f6f1c5a 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -402,9 +402,6 @@ int clocksource_register(struct clocksource *c)
 	unsigned long flags;
 	int ret;
 
-	/* save mult_orig on registration */
-	c->mult_orig = c->mult;
-
 	spin_lock_irqsave(&clocksource_lock, flags);
 	ret = clocksource_enqueue(c);
 	if (!ret)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 687dff49f6e7..e8c77d9c633a 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -22,7 +22,7 @@
 
 /*
  * This read-write spinlock protects us from races in SMP while
- * playing with xtime and avenrun.
+ * playing with xtime.
  */
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
 
@@ -77,6 +77,10 @@ static void clocksource_forward_now(void)
 	clock->cycle_last = cycle_now;
 
 	nsec = cyc2ns(clock, cycle_delta);
+
+	/* If arch requires, add in gettimeoffset() */
+	nsec += arch_gettimeoffset();
+
 	timespec_add_ns(&xtime, nsec);
 
 	nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
@@ -111,6 +115,9 @@ void getnstimeofday(struct timespec *ts)
 		/* convert to nanoseconds: */
 		nsecs = cyc2ns(clock, cycle_delta);
 
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
+
 	} while (read_seqretry(&xtime_lock, seq));
 
 	timespec_add_ns(ts, nsecs);
diff --git a/kernel/timer.c b/kernel/timer.c
index cffffad01c31..c01e568935ea 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -37,6 +37,7 @@
 #include <linux/delay.h>
 #include <linux/tick.h>
 #include <linux/kallsyms.h>
+#include <linux/perf_counter.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -1122,47 +1123,6 @@ void update_process_times(int user_tick)
 	run_posix_cpu_timers(p);
 }
 
-/*
- * Nr of active tasks - counted in fixed-point numbers
- */
-static unsigned long count_active_tasks(void)
-{
-	return nr_active() * FIXED_1;
-}
-
-/*
- * Hmm.. Changed this, as the GNU make sources (load.c) seems to
- * imply that avenrun[] is the standard name for this kind of thing.
- * Nothing else seems to be standardized: the fractional size etc
- * all seem to differ on different machines.
- *
- * Requires xtime_lock to access.
- */
-unsigned long avenrun[3];
-
-EXPORT_SYMBOL(avenrun);
-
-/*
- * calc_load - given tick count, update the avenrun load estimates.
- * This is called while holding a write_lock on xtime_lock.
- */
-static inline void calc_load(unsigned long ticks)
-{
-	unsigned long active_tasks; /* fixed-point */
-	static int count = LOAD_FREQ;
-
-	count -= ticks;
-	if (unlikely(count < 0)) {
-		active_tasks = count_active_tasks();
-		do {
-			CALC_LOAD(avenrun[0], EXP_1, active_tasks);
-			CALC_LOAD(avenrun[1], EXP_5, active_tasks);
-			CALC_LOAD(avenrun[2], EXP_15, active_tasks);
-			count += LOAD_FREQ;
-		} while (count < 0);
-	}
-}
-
 /*
  * This function runs timers and the timer-tq in bottom half context.
  */
@@ -1170,6 +1130,8 @@ static void run_timer_softirq(struct softirq_action *h)
 {
 	struct tvec_base *base = __get_cpu_var(tvec_bases);
 
+	perf_counter_do_pending();
+
 	hrtimer_run_pending();
 
 	if (time_after_eq(jiffies, base->timer_jiffies))
@@ -1186,16 +1148,6 @@ void run_local_timers(void)
 	softlockup_tick();
 }
 
-/*
- * Called by the timer interrupt. xtime_lock must already be taken
- * by the timer IRQ!
- */
-static inline void update_times(unsigned long ticks)
-{
-	update_wall_time();
-	calc_load(ticks);
-}
-
 /*
  * The 64-bit jiffies value is not atomic - you MUST NOT read it
  * without sampling the sequence number in xtime_lock.
@@ -1205,7 +1157,8 @@ static inline void update_times(unsigned long ticks)
 void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
-	update_times(ticks);
+	update_wall_time();
+	calc_global_load();
 }
 
 #ifdef __ARCH_WANT_SYS_ALARM
@@ -1406,37 +1359,17 @@ int do_sysinfo(struct sysinfo *info)
 {
 	unsigned long mem_total, sav_total;
 	unsigned int mem_unit, bitcount;
-	unsigned long seq;
+	struct timespec tp;
 
 	memset(info, 0, sizeof(struct sysinfo));
 
-	do {
-		struct timespec tp;
-		seq = read_seqbegin(&xtime_lock);
+	ktime_get_ts(&tp);
+	monotonic_to_bootbased(&tp);
+	info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
 
-		/*
-		 * This is annoying.  The below is the same thing
-		 * posix_get_clock_monotonic() does, but it wants to
-		 * take the lock which we want to cover the loads stuff
-		 * too.
-		 */
+	get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
 
-		getnstimeofday(&tp);
-		tp.tv_sec += wall_to_monotonic.tv_sec;
-		tp.tv_nsec += wall_to_monotonic.tv_nsec;
-		monotonic_to_bootbased(&tp);
-		if (tp.tv_nsec - NSEC_PER_SEC >= 0) {
-			tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC;
-			tp.tv_sec++;
-		}
-		info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
-
-		info->loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT);
-		info->loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT);
-		info->loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT);
-
-		info->procs = nr_threads;
-	} while (read_seqretry(&xtime_lock, seq));
+	info->procs = nr_threads;
 
 	si_meminfo(info);
 	si_swapinfo(info);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 417d1985e299..4a13e5a01ce3 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -48,6 +48,21 @@ config FTRACE_NMI_ENTER
        depends on HAVE_FTRACE_NMI_ENTER
        default y
 
+config EVENT_TRACING
+	select CONTEXT_SWITCH_TRACER
+	bool
+
+config CONTEXT_SWITCH_TRACER
+	select MARKERS
+	bool
+
+# All tracer options should select GENERIC_TRACER. For those options that are
+# enabled by all tracers (context switch and event tracer) they select TRACING.
+# This allows those options to appear when no other tracer is selected. But the
+# options do not appear when something else selects it. We need the two options
+# GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
+# hidding of the automatic options options.
+
 config TRACING
 	bool
 	select DEBUG_FS
@@ -56,6 +71,11 @@ config TRACING
 	select TRACEPOINTS
 	select NOP_TRACER
 	select BINARY_PRINTF
+	select EVENT_TRACING
+
+config GENERIC_TRACER
+	bool
+	select TRACING
 
 #
 # Minimum requirements an architecture has to meet for us to
@@ -73,14 +93,20 @@ config TRACING_SUPPORT
 
 if TRACING_SUPPORT
 
-menu "Tracers"
+menuconfig FTRACE
+	bool "Tracers"
+	default y if DEBUG_KERNEL
+	help
+	 Enable the kernel tracing infrastructure.
+
+if FTRACE
 
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
 	select FRAME_POINTER
 	select KALLSYMS
-	select TRACING
+	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	help
 	  Enable the kernel to trace every kernel function. This is done
@@ -104,13 +130,14 @@ config FUNCTION_GRAPH_TRACER
 	  the return value. This is done by setting the current return 
 	  address on the current task structure into a stack of calls.
 
+
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
 	depends on TRACE_IRQFLAGS_SUPPORT
 	depends on GENERIC_TIME
 	select TRACE_IRQFLAGS
-	select TRACING
+	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
 	help
 	  This option measures the time spent in irqs-off critical
@@ -131,7 +158,7 @@ config PREEMPT_TRACER
 	default n
 	depends on GENERIC_TIME
 	depends on PREEMPT
-	select TRACING
+	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
 	help
 	  This option measures the time spent in preemption off critical
@@ -150,7 +177,7 @@ config PREEMPT_TRACER
 config SYSPROF_TRACER
 	bool "Sysprof Tracer"
 	depends on X86
-	select TRACING
+	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	help
 	  This tracer provides the trace needed by the 'Sysprof' userspace
@@ -158,40 +185,33 @@ config SYSPROF_TRACER
 
 config SCHED_TRACER
 	bool "Scheduling Latency Tracer"
-	select TRACING
+	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	select TRACER_MAX_TRACE
 	help
 	  This tracer tracks the latency of the highest priority task
 	  to be scheduled in, starting from the point it has woken up.
 
-config CONTEXT_SWITCH_TRACER
-	bool "Trace process context switches"
-	select TRACING
-	select MARKERS
-	help
-	  This tracer gets called from the context switch and records
-	  all switching of tasks.
-
-config EVENT_TRACER
-	bool "Trace various events in the kernel"
+config ENABLE_DEFAULT_TRACERS
+	bool "Trace process context switches and events"
+	depends on !GENERIC_TRACER
 	select TRACING
 	help
 	  This tracer hooks to various trace points in the kernel
 	  allowing the user to pick and choose which trace point they
-	  want to trace.
+	  want to trace. It also includes the sched_switch tracer plugin.
 
 config FTRACE_SYSCALLS
 	bool "Trace syscalls"
 	depends on HAVE_FTRACE_SYSCALLS
-	select TRACING
+	select GENERIC_TRACER
 	select KALLSYMS
 	help
 	  Basic tracer to catch the syscall entry and exit events.
 
 config BOOT_TRACER
 	bool "Trace boot initcalls"
-	select TRACING
+	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
 	help
 	  This tracer helps developers to optimize boot times: it records
@@ -207,8 +227,36 @@ config BOOT_TRACER
 	  to enable this on bootup.
 
 config TRACE_BRANCH_PROFILING
+	bool
+	select GENERIC_TRACER
+
+choice
+	prompt "Branch Profiling"
+	default BRANCH_PROFILE_NONE
+	help
+	 The branch profiling is a software profiler. It will add hooks
+	 into the C conditionals to test which path a branch takes.
+
+	 The likely/unlikely profiler only looks at the conditions that
+	 are annotated with a likely or unlikely macro.
+
+	 The "all branch" profiler will profile every if statement in the
+	 kernel. This profiler will also enable the likely/unlikely
+	 profiler as well.
+
+	 Either of the above profilers add a bit of overhead to the system.
+	 If unsure choose "No branch profiling".
+
+config BRANCH_PROFILE_NONE
+	bool "No branch profiling"
+	help
+	 No branch profiling. Branch profiling adds a bit of overhead.
+	 Only enable it if you want to analyse the branching behavior.
+	 Otherwise keep it disabled.
+
+config PROFILE_ANNOTATED_BRANCHES
 	bool "Trace likely/unlikely profiler"
-	select TRACING
+	select TRACE_BRANCH_PROFILING
 	help
 	  This tracer profiles all the the likely and unlikely macros
 	  in the kernel. It will display the results in:
@@ -218,11 +266,9 @@ config TRACE_BRANCH_PROFILING
 	  Note: this will add a significant overhead, only turn this
 	  on if you need to profile the system's use of these macros.
 
-	  Say N if unsure.
-
 config PROFILE_ALL_BRANCHES
 	bool "Profile all if conditionals"
-	depends on TRACE_BRANCH_PROFILING
+	select TRACE_BRANCH_PROFILING
 	help
 	  This tracer profiles all branch conditions. Every if ()
 	  taken in the kernel is recorded whether it hit or miss.
@@ -230,11 +276,12 @@ config PROFILE_ALL_BRANCHES
 
 	  /debugfs/tracing/profile_branch
 
+	  This option also enables the likely/unlikely profiler.
+
 	  This configuration, when enabled, will impose a great overhead
 	  on the system. This should only be enabled when the system
 	  is to be analyzed
-
-	  Say N if unsure.
+endchoice
 
 config TRACING_BRANCHES
 	bool
@@ -261,7 +308,7 @@ config BRANCH_TRACER
 config POWER_TRACER
 	bool "Trace power consumption behavior"
 	depends on X86
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  This tracer helps developers to analyze and optimize the kernels
 	  power management decisions, specifically the C-state and P-state
@@ -295,14 +342,14 @@ config STACK_TRACER
 config HW_BRANCH_TRACER
 	depends on HAVE_HW_BRANCH_TRACER
 	bool "Trace hw branches"
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  This tracer records all branches on the system in a circular
 	  buffer giving access to the last N branches for each cpu.
 
 config KMEMTRACE
 	bool "Trace SLAB allocations"
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  kmemtrace provides tracing for slab allocator functions, such as
 	  kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
@@ -322,7 +369,7 @@ config KMEMTRACE
 
 config WORKQUEUE_TRACER
 	bool "Trace workqueues"
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  The workqueue tracer provides some statistical informations
           about each cpu workqueue thread such as the number of the
@@ -338,7 +385,7 @@ config BLK_DEV_IO_TRACE
 	select RELAY
 	select DEBUG_FS
 	select TRACEPOINTS
-	select TRACING
+	select GENERIC_TRACER
 	select STACKTRACE
 	help
 	  Say Y here if you want to be able to trace the block layer actions
@@ -375,6 +422,20 @@ config DYNAMIC_FTRACE
 	 were made. If so, it runs stop_machine (stops all CPUS)
 	 and modifies the code to jump over the call to ftrace.
 
+config FUNCTION_PROFILER
+	bool "Kernel function profiler"
+	depends on FUNCTION_TRACER
+	default n
+	help
+	 This option enables the kernel function profiler. A file is created
+	 in debugfs called function_profile_enabled which defaults to zero.
+	 When a 1 is echoed into this file profiling begins, and when a
+	 zero is entered, profiling stops. A file in the trace_stats
+	 directory called functions, that show the list of functions that
+	 have been hit and their counters.
+
+	 If in doubt, say N
+
 config FTRACE_MCOUNT_RECORD
 	def_bool y
 	depends on DYNAMIC_FTRACE
@@ -385,7 +446,7 @@ config FTRACE_SELFTEST
 
 config FTRACE_STARTUP_TEST
 	bool "Perform a startup test on ftrace"
-	depends on TRACING
+	depends on GENERIC_TRACER
 	select FTRACE_SELFTEST
 	help
 	  This option performs a series of startup tests on ftrace. On bootup
@@ -396,7 +457,7 @@ config FTRACE_STARTUP_TEST
 config MMIOTRACE
 	bool "Memory mapped IO tracing"
 	depends on HAVE_MMIOTRACE_SUPPORT && PCI
-	select TRACING
+	select GENERIC_TRACER
 	help
 	  Mmiotrace traces Memory Mapped I/O access and is meant for
 	  debugging and reverse engineering. It is called from the ioremap
@@ -416,7 +477,23 @@ config MMIOTRACE_TEST
 
 	  Say N, unless you absolutely know what you are doing.
 
-endmenu
+config RING_BUFFER_BENCHMARK
+	tristate "Ring buffer benchmark stress tester"
+	depends on RING_BUFFER
+	help
+	  This option creates a test to stress the ring buffer and bench mark it.
+	  It creates its own ring buffer such that it will not interfer with
+	  any other users of the ring buffer (such as ftrace). It then creates
+	  a producer and consumer that will run for 10 seconds and sleep for
+	  10 seconds. Each interval it will print out the number of events
+	  it recorded and give a rough estimate of how long each iteration took.
+
+	  It does not disable interrupts or raise its priority, so it may be
+	  affected by processes that are running.
+
+	  If unsure, say N
+
+endif # FTRACE
 
 endif # TRACING_SUPPORT
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 2630f5121ec1..844164dca90a 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -15,11 +15,17 @@ ifdef CONFIG_TRACING_BRANCHES
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 endif
 
+#
+# Make the trace clocks available generally: it's infrastructure
+# relied on by ptrace for example:
+#
+obj-y += trace_clock.o
+
 obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
 obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
+obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
 
 obj-$(CONFIG_TRACING) += trace.o
-obj-$(CONFIG_TRACING) += trace_clock.o
 obj-$(CONFIG_TRACING) += trace_output.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
@@ -39,12 +45,14 @@ obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
 obj-$(CONFIG_POWER_TRACER) += trace_power.o
 obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
-obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
-obj-$(CONFIG_EVENT_TRACER) += trace_events.o
-obj-$(CONFIG_EVENT_TRACER) += events.o
-obj-$(CONFIG_EVENT_TRACER) += trace_export.o
+obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
+ifeq ($(CONFIG_BLOCK),y)
+obj-$(CONFIG_EVENT_TRACING) += blktrace.o
+endif
+obj-$(CONFIG_EVENT_TRACING) += trace_events.o
+obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
-obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 921ef5d1f0ba..39af8af6fc30 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -23,10 +23,14 @@
 #include <linux/mutex.h>
 #include <linux/debugfs.h>
 #include <linux/time.h>
-#include <trace/block.h>
 #include <linux/uaccess.h>
+
+#include <trace/events/block.h>
+
 #include "trace_output.h"
 
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+
 static unsigned int blktrace_seq __read_mostly = 1;
 
 static struct trace_array *blk_tr;
@@ -147,7 +151,7 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 {
 	if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
 		return 1;
-	if (sector < bt->start_lba || sector > bt->end_lba)
+	if (sector && (sector < bt->start_lba || sector > bt->end_lba))
 		return 1;
 	if (bt->pid && pid != bt->pid)
 		return 1;
@@ -192,7 +196,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(rw, DISCARD);
 
 	pid = tsk->pid;
-	if (unlikely(act_log_check(bt, what, sector, pid)))
+	if (act_log_check(bt, what, sector, pid))
 		return;
 	cpu = raw_smp_processor_id();
 
@@ -262,6 +266,7 @@ static void blk_trace_free(struct blk_trace *bt)
 {
 	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
+	debugfs_remove(bt->dir);
 	relay_close(bt->rchan);
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
@@ -403,11 +408,29 @@ static struct rchan_callbacks blk_relay_callbacks = {
 	.remove_buf_file	= blk_remove_buf_file_callback,
 };
 
+static void blk_trace_setup_lba(struct blk_trace *bt,
+				struct block_device *bdev)
+{
+	struct hd_struct *part = NULL;
+
+	if (bdev)
+		part = bdev->bd_part;
+
+	if (part) {
+		bt->start_lba = part->start_sect;
+		bt->end_lba = part->start_sect + part->nr_sects;
+	} else {
+		bt->start_lba = 0;
+		bt->end_lba = -1ULL;
+	}
+}
+
 /*
  * Setup everything required to start tracing
  */
 int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-			struct blk_user_trace_setup *buts)
+		       struct block_device *bdev,
+		       struct blk_user_trace_setup *buts)
 {
 	struct blk_trace *old_bt, *bt = NULL;
 	struct dentry *dir = NULL;
@@ -480,10 +503,13 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->act_mask)
 		bt->act_mask = (u16) -1;
 
-	bt->start_lba = buts->start_lba;
-	bt->end_lba = buts->end_lba;
-	if (!bt->end_lba)
-		bt->end_lba = -1ULL;
+	blk_trace_setup_lba(bt, bdev);
+
+	/* overwrite with user settings */
+	if (buts->start_lba)
+		bt->start_lba = buts->start_lba;
+	if (buts->end_lba)
+		bt->end_lba = buts->end_lba;
 
 	bt->pid = buts->pid;
 	bt->trace_state = Blktrace_setup;
@@ -505,6 +531,7 @@ err:
 }
 
 int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+		    struct block_device *bdev,
 		    char __user *arg)
 {
 	struct blk_user_trace_setup buts;
@@ -514,7 +541,7 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (ret)
 		return -EFAULT;
 
-	ret = do_blk_trace_setup(q, name, dev, &buts);
+	ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
 	if (ret)
 		return ret;
 
@@ -582,7 +609,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	switch (cmd) {
 	case BLKTRACESETUP:
 		bdevname(bdev, b);
-		ret = blk_trace_setup(q, b, bdev->bd_dev, arg);
+		ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 	case BLKTRACESTART:
 		start = 1;
@@ -642,12 +669,12 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 
 	if (blk_pc_request(rq)) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors,
-				rq->cmd_len, rq->cmd);
+		__blk_add_trace(bt, 0, blk_rq_bytes(rq), rw,
+				what, rq->errors, rq->cmd_len, rq->cmd);
 	} else  {
 		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
-				rw, what, rq->errors, 0, NULL);
+		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rw,
+				what, rq->errors, 0, NULL);
 	}
 }
 
@@ -809,7 +836,6 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
  * @bio:	the source bio
  * @dev:	target device
  * @from:	source sector
- * @to:		target sector
  *
  * Description:
  *     Device mapper or raid target sometimes need to split a bio because
@@ -817,7 +843,7 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
  *
  **/
 static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
-				       dev_t dev, sector_t from, sector_t to)
+				       dev_t dev, sector_t from)
 {
 	struct blk_trace *bt = q->blk_trace;
 	struct blk_io_trace_remap r;
@@ -825,12 +851,13 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
 	if (likely(!bt))
 		return;
 
-	r.device = cpu_to_be32(dev);
-	r.device_from = cpu_to_be32(bio->bi_bdev->bd_dev);
-	r.sector = cpu_to_be64(to);
+	r.device_from = cpu_to_be32(dev);
+	r.device_to   = cpu_to_be32(bio->bi_bdev->bd_dev);
+	r.sector_from = cpu_to_be64(from);
 
-	__blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP,
-			!bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
+	__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
+			BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE),
+			sizeof(r), &r);
 }
 
 /**
@@ -854,11 +881,11 @@ void blk_add_driver_data(struct request_queue *q,
 		return;
 
 	if (blk_pc_request(rq))
-		__blk_add_trace(bt, 0, rq->data_len, 0, BLK_TA_DRV_DATA,
-				rq->errors, len, data);
+		__blk_add_trace(bt, 0, blk_rq_bytes(rq), 0,
+				BLK_TA_DRV_DATA, rq->errors, len, data);
 	else
-		__blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
-				0, BLK_TA_DRV_DATA, rq->errors, len, data);
+		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0,
+				BLK_TA_DRV_DATA, rq->errors, len, data);
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
 
@@ -971,6 +998,16 @@ static inline const void *pdu_start(const struct trace_entry *ent)
 	return te_blk_io_trace(ent) + 1;
 }
 
+static inline u32 t_action(const struct trace_entry *ent)
+{
+	return te_blk_io_trace(ent)->action;
+}
+
+static inline u32 t_bytes(const struct trace_entry *ent)
+{
+	return te_blk_io_trace(ent)->bytes;
+}
+
 static inline u32 t_sec(const struct trace_entry *ent)
 {
 	return te_blk_io_trace(ent)->bytes >> 9;
@@ -996,11 +1033,11 @@ static void get_pdu_remap(const struct trace_entry *ent,
 			  struct blk_io_trace_remap *r)
 {
 	const struct blk_io_trace_remap *__r = pdu_start(ent);
-	__u64 sector = __r->sector;
+	__u64 sector_from = __r->sector_from;
 
-	r->device = be32_to_cpu(__r->device);
 	r->device_from = be32_to_cpu(__r->device_from);
-	r->sector = be64_to_cpu(sector);
+	r->device_to   = be32_to_cpu(__r->device_to);
+	r->sector_from = be64_to_cpu(sector_from);
 }
 
 typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
@@ -1031,36 +1068,98 @@ static int blk_log_action(struct trace_iterator *iter, const char *act)
 				MAJOR(t->device), MINOR(t->device), act, rwbs);
 }
 
+static int blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent)
+{
+	const unsigned char *pdu_buf;
+	int pdu_len;
+	int i, end, ret;
+
+	pdu_buf = pdu_start(ent);
+	pdu_len = te_blk_io_trace(ent)->pdu_len;
+
+	if (!pdu_len)
+		return 1;
+
+	/* find the last zero that needs to be printed */
+	for (end = pdu_len - 1; end >= 0; end--)
+		if (pdu_buf[end])
+			break;
+	end++;
+
+	if (!trace_seq_putc(s, '('))
+		return 0;
+
+	for (i = 0; i < pdu_len; i++) {
+
+		ret = trace_seq_printf(s, "%s%02x",
+				       i == 0 ? "" : " ", pdu_buf[i]);
+		if (!ret)
+			return ret;
+
+		/*
+		 * stop when the rest is just zeroes and indicate so
+		 * with a ".." appended
+		 */
+		if (i == end && end != pdu_len - 1)
+			return trace_seq_puts(s, " ..) ");
+	}
+
+	return trace_seq_puts(s, ") ");
+}
+
 static int blk_log_generic(struct trace_seq *s, const struct trace_entry *ent)
 {
 	char cmd[TASK_COMM_LEN];
 
 	trace_find_cmdline(ent->pid, cmd);
 
-	if (t_sec(ent))
-		return trace_seq_printf(s, "%llu + %u [%s]\n",
-					t_sector(ent), t_sec(ent), cmd);
-	return trace_seq_printf(s, "[%s]\n", cmd);
+	if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+		int ret;
+
+		ret = trace_seq_printf(s, "%u ", t_bytes(ent));
+		if (!ret)
+			return 0;
+		ret = blk_log_dump_pdu(s, ent);
+		if (!ret)
+			return 0;
+		return trace_seq_printf(s, "[%s]\n", cmd);
+	} else {
+		if (t_sec(ent))
+			return trace_seq_printf(s, "%llu + %u [%s]\n",
+						t_sector(ent), t_sec(ent), cmd);
+		return trace_seq_printf(s, "[%s]\n", cmd);
+	}
 }
 
 static int blk_log_with_error(struct trace_seq *s,
 			      const struct trace_entry *ent)
 {
-	if (t_sec(ent))
-		return trace_seq_printf(s, "%llu + %u [%d]\n", t_sector(ent),
-					t_sec(ent), t_error(ent));
-	return trace_seq_printf(s, "%llu [%d]\n", t_sector(ent), t_error(ent));
+	if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) {
+		int ret;
+
+		ret = blk_log_dump_pdu(s, ent);
+		if (ret)
+			return trace_seq_printf(s, "[%d]\n", t_error(ent));
+		return 0;
+	} else {
+		if (t_sec(ent))
+			return trace_seq_printf(s, "%llu + %u [%d]\n",
+						t_sector(ent),
+						t_sec(ent), t_error(ent));
+		return trace_seq_printf(s, "%llu [%d]\n",
+					t_sector(ent), t_error(ent));
+	}
 }
 
 static int blk_log_remap(struct trace_seq *s, const struct trace_entry *ent)
 {
-	struct blk_io_trace_remap r = { .device = 0, };
+	struct blk_io_trace_remap r = { .device_from = 0, };
 
 	get_pdu_remap(ent, &r);
 	return trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
-			       t_sector(ent),
-			       t_sec(ent), MAJOR(r.device), MINOR(r.device),
-			       (unsigned long long)r.sector);
+				t_sector(ent), t_sec(ent),
+				MAJOR(r.device_from), MINOR(r.device_from),
+				(unsigned long long)r.sector_from);
 }
 
 static int blk_log_plug(struct trace_seq *s, const struct trace_entry *ent)
@@ -1117,7 +1216,6 @@ static void blk_tracer_print_header(struct seq_file *m)
 static void blk_tracer_start(struct trace_array *tr)
 {
 	blk_tracer_enabled = true;
-	trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
 }
 
 static int blk_tracer_init(struct trace_array *tr)
@@ -1130,7 +1228,6 @@ static int blk_tracer_init(struct trace_array *tr)
 static void blk_tracer_stop(struct trace_array *tr)
 {
 	blk_tracer_enabled = false;
-	trace_flags |= TRACE_ITER_CONTEXT_INFO;
 }
 
 static void blk_tracer_reset(struct trace_array *tr)
@@ -1182,7 +1279,7 @@ static enum print_line_t print_one_line(struct trace_iterator *iter,
 	}
 
 	if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
-		ret = trace_seq_printf(s, "Bad pc action %x\n", what);
+		ret = trace_seq_printf(s, "Unknown action %x\n", what);
 	else {
 		ret = log_action(iter, what2act[what].act[long_act]);
 		if (ret)
@@ -1195,9 +1292,6 @@ out:
 static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
 					       int flags)
 {
-	if (!trace_print_context(iter))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return print_one_line(iter, false);
 }
 
@@ -1232,6 +1326,18 @@ static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
 	return print_one_line(iter, true);
 }
 
+static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set)
+{
+	/* don't output context-info for blk_classic output */
+	if (bit == TRACE_BLK_OPT_CLASSIC) {
+		if (set)
+			trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
+		else
+			trace_flags |= TRACE_ITER_CONTEXT_INFO;
+	}
+	return 0;
+}
+
 static struct tracer blk_tracer __read_mostly = {
 	.name		= "blk",
 	.init		= blk_tracer_init,
@@ -1241,6 +1347,7 @@ static struct tracer blk_tracer __read_mostly = {
 	.print_header	= blk_tracer_print_header,
 	.print_line	= blk_tracer_print_line,
 	.flags		= &blk_tracer_flags,
+	.set_flag	= blk_tracer_set_flag,
 };
 
 static struct trace_event trace_blk_event = {
@@ -1285,7 +1392,8 @@ static int blk_trace_remove_queue(struct request_queue *q)
 /*
  * Setup everything required to start tracing
  */
-static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
+static int blk_trace_setup_queue(struct request_queue *q,
+				 struct block_device *bdev)
 {
 	struct blk_trace *old_bt, *bt = NULL;
 	int ret = -ENOMEM;
@@ -1298,9 +1406,10 @@ static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
 	if (!bt->msg_data)
 		goto free_bt;
 
-	bt->dev = dev;
+	bt->dev = bdev->bd_dev;
 	bt->act_mask = (u16)-1;
-	bt->end_lba = -1ULL;
+
+	blk_trace_setup_lba(bt, bdev);
 
 	old_bt = xchg(&q->blk_trace, bt);
 	if (old_bt != NULL) {
@@ -1517,7 +1626,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 
 	if (attr == &dev_attr_enable) {
 		if (value)
-			ret = blk_trace_setup_queue(q, bdev->bd_dev);
+			ret = blk_trace_setup_queue(q, bdev);
 		else
 			ret = blk_trace_remove_queue(q);
 		goto out_unlock_bdev;
@@ -1525,7 +1634,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 
 	ret = 0;
 	if (q->blk_trace == NULL)
-		ret = blk_trace_setup_queue(q, bdev->bd_dev);
+		ret = blk_trace_setup_queue(q, bdev);
 
 	if (ret == 0) {
 		if (attr == &dev_attr_act_mask)
@@ -1548,3 +1657,77 @@ out:
 	return ret ? ret : count;
 }
 
+int blk_trace_init_sysfs(struct device *dev)
+{
+	return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
+}
+
+#endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#ifdef CONFIG_EVENT_TRACING
+
+void blk_dump_cmd(char *buf, struct request *rq)
+{
+	int i, end;
+	int len = rq->cmd_len;
+	unsigned char *cmd = rq->cmd;
+
+	if (!blk_pc_request(rq)) {
+		buf[0] = '\0';
+		return;
+	}
+
+	for (end = len - 1; end >= 0; end--)
+		if (cmd[end])
+			break;
+	end++;
+
+	for (i = 0; i < len; i++) {
+		buf += sprintf(buf, "%s%02x", i == 0 ? "" : " ", cmd[i]);
+		if (i == end && end != len - 1) {
+			sprintf(buf, " ..");
+			break;
+		}
+	}
+}
+
+void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
+{
+	int i = 0;
+
+	if (rw & WRITE)
+		rwbs[i++] = 'W';
+	else if (rw & 1 << BIO_RW_DISCARD)
+		rwbs[i++] = 'D';
+	else if (bytes)
+		rwbs[i++] = 'R';
+	else
+		rwbs[i++] = 'N';
+
+	if (rw & 1 << BIO_RW_AHEAD)
+		rwbs[i++] = 'A';
+	if (rw & 1 << BIO_RW_BARRIER)
+		rwbs[i++] = 'B';
+	if (rw & 1 << BIO_RW_SYNCIO)
+		rwbs[i++] = 'S';
+	if (rw & 1 << BIO_RW_META)
+		rwbs[i++] = 'M';
+
+	rwbs[i] = '\0';
+}
+
+void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
+{
+	int rw = rq->cmd_flags & 0x03;
+	int bytes;
+
+	if (blk_discard_rq(rq))
+		rw |= (1 << BIO_RW_DISCARD);
+
+	bytes = blk_rq_bytes(rq);
+
+	blk_fill_rwbs(rwbs, rw, bytes);
+}
+
+#endif /* CONFIG_EVENT_TRACING */
+
diff --git a/kernel/trace/events.c b/kernel/trace/events.c
deleted file mode 100644
index 246f2aa6dc46..000000000000
--- a/kernel/trace/events.c
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * This is the place to register all trace points as events.
- */
-
-#include <linux/stringify.h>
-
-#include <trace/trace_events.h>
-
-#include "trace_output.h"
-
-#include "trace_events_stage_1.h"
-#include "trace_events_stage_2.h"
-#include "trace_events_stage_3.h"
-
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f1ed080406c3..bb60732ade0c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -29,11 +29,13 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #include <asm/ftrace.h>
+#include <asm/setup.h>
 
-#include "trace.h"
+#include "trace_output.h"
+#include "trace_stat.h"
 
 #define FTRACE_WARN_ON(cond)			\
 	do {					\
@@ -68,7 +70,7 @@ static DEFINE_MUTEX(ftrace_lock);
 
 static struct ftrace_ops ftrace_list_end __read_mostly =
 {
-	.func = ftrace_stub,
+	.func		= ftrace_stub,
 };
 
 static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
@@ -240,6 +242,580 @@ static void ftrace_update_pid_func(void)
 #endif
 }
 
+#ifdef CONFIG_FUNCTION_PROFILER
+struct ftrace_profile {
+	struct hlist_node		node;
+	unsigned long			ip;
+	unsigned long			counter;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	unsigned long long		time;
+#endif
+};
+
+struct ftrace_profile_page {
+	struct ftrace_profile_page	*next;
+	unsigned long			index;
+	struct ftrace_profile		records[];
+};
+
+struct ftrace_profile_stat {
+	atomic_t			disabled;
+	struct hlist_head		*hash;
+	struct ftrace_profile_page	*pages;
+	struct ftrace_profile_page	*start;
+	struct tracer_stat		stat;
+};
+
+#define PROFILE_RECORDS_SIZE						\
+	(PAGE_SIZE - offsetof(struct ftrace_profile_page, records))
+
+#define PROFILES_PER_PAGE					\
+	(PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
+
+static int ftrace_profile_bits __read_mostly;
+static int ftrace_profile_enabled __read_mostly;
+
+/* ftrace_profile_lock - synchronize the enable and disable of the profiler */
+static DEFINE_MUTEX(ftrace_profile_lock);
+
+static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
+
+#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+
+static void *
+function_stat_next(void *v, int idx)
+{
+	struct ftrace_profile *rec = v;
+	struct ftrace_profile_page *pg;
+
+	pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
+
+ again:
+	rec++;
+	if ((void *)rec >= (void *)&pg->records[pg->index]) {
+		pg = pg->next;
+		if (!pg)
+			return NULL;
+		rec = &pg->records[0];
+		if (!rec->counter)
+			goto again;
+	}
+
+	return rec;
+}
+
+static void *function_stat_start(struct tracer_stat *trace)
+{
+	struct ftrace_profile_stat *stat =
+		container_of(trace, struct ftrace_profile_stat, stat);
+
+	if (!stat || !stat->start)
+		return NULL;
+
+	return function_stat_next(&stat->start->records[0], 0);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/* function graph compares on total time */
+static int function_stat_cmp(void *p1, void *p2)
+{
+	struct ftrace_profile *a = p1;
+	struct ftrace_profile *b = p2;
+
+	if (a->time < b->time)
+		return -1;
+	if (a->time > b->time)
+		return 1;
+	else
+		return 0;
+}
+#else
+/* not function graph compares against hits */
+static int function_stat_cmp(void *p1, void *p2)
+{
+	struct ftrace_profile *a = p1;
+	struct ftrace_profile *b = p2;
+
+	if (a->counter < b->counter)
+		return -1;
+	if (a->counter > b->counter)
+		return 1;
+	else
+		return 0;
+}
+#endif
+
+static int function_stat_headers(struct seq_file *m)
+{
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	seq_printf(m, "  Function                               "
+		   "Hit    Time            Avg\n"
+		      "  --------                               "
+		   "---    ----            ---\n");
+#else
+	seq_printf(m, "  Function                               Hit\n"
+		      "  --------                               ---\n");
+#endif
+	return 0;
+}
+
+static int function_stat_show(struct seq_file *m, void *v)
+{
+	struct ftrace_profile *rec = v;
+	char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	static DEFINE_MUTEX(mutex);
+	static struct trace_seq s;
+	unsigned long long avg;
+#endif
+
+	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
+	seq_printf(m, "  %-30.30s  %10lu", str, rec->counter);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	seq_printf(m, "    ");
+	avg = rec->time;
+	do_div(avg, rec->counter);
+
+	mutex_lock(&mutex);
+	trace_seq_init(&s);
+	trace_print_graph_duration(rec->time, &s);
+	trace_seq_puts(&s, "    ");
+	trace_print_graph_duration(avg, &s);
+	trace_print_seq(m, &s);
+	mutex_unlock(&mutex);
+#endif
+	seq_putc(m, '\n');
+
+	return 0;
+}
+
+static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
+{
+	struct ftrace_profile_page *pg;
+
+	pg = stat->pages = stat->start;
+
+	while (pg) {
+		memset(pg->records, 0, PROFILE_RECORDS_SIZE);
+		pg->index = 0;
+		pg = pg->next;
+	}
+
+	memset(stat->hash, 0,
+	       FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head));
+}
+
+int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
+{
+	struct ftrace_profile_page *pg;
+	int functions;
+	int pages;
+	int i;
+
+	/* If we already allocated, do nothing */
+	if (stat->pages)
+		return 0;
+
+	stat->pages = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!stat->pages)
+		return -ENOMEM;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+	functions = ftrace_update_tot_cnt;
+#else
+	/*
+	 * We do not know the number of functions that exist because
+	 * dynamic tracing is what counts them. With past experience
+	 * we have around 20K functions. That should be more than enough.
+	 * It is highly unlikely we will execute every function in
+	 * the kernel.
+	 */
+	functions = 20000;
+#endif
+
+	pg = stat->start = stat->pages;
+
+	pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
+
+	for (i = 0; i < pages; i++) {
+		pg->next = (void *)get_zeroed_page(GFP_KERNEL);
+		if (!pg->next)
+			goto out_free;
+		pg = pg->next;
+	}
+
+	return 0;
+
+ out_free:
+	pg = stat->start;
+	while (pg) {
+		unsigned long tmp = (unsigned long)pg;
+
+		pg = pg->next;
+		free_page(tmp);
+	}
+
+	free_page((unsigned long)stat->pages);
+	stat->pages = NULL;
+	stat->start = NULL;
+
+	return -ENOMEM;
+}
+
+static int ftrace_profile_init_cpu(int cpu)
+{
+	struct ftrace_profile_stat *stat;
+	int size;
+
+	stat = &per_cpu(ftrace_profile_stats, cpu);
+
+	if (stat->hash) {
+		/* If the profile is already created, simply reset it */
+		ftrace_profile_reset(stat);
+		return 0;
+	}
+
+	/*
+	 * We are profiling all functions, but usually only a few thousand
+	 * functions are hit. We'll make a hash of 1024 items.
+	 */
+	size = FTRACE_PROFILE_HASH_SIZE;
+
+	stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL);
+
+	if (!stat->hash)
+		return -ENOMEM;
+
+	if (!ftrace_profile_bits) {
+		size--;
+
+		for (; size; size >>= 1)
+			ftrace_profile_bits++;
+	}
+
+	/* Preallocate the function profiling pages */
+	if (ftrace_profile_pages_init(stat) < 0) {
+		kfree(stat->hash);
+		stat->hash = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int ftrace_profile_init(void)
+{
+	int cpu;
+	int ret = 0;
+
+	for_each_online_cpu(cpu) {
+		ret = ftrace_profile_init_cpu(cpu);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+/* interrupts must be disabled */
+static struct ftrace_profile *
+ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+	struct ftrace_profile *rec;
+	struct hlist_head *hhd;
+	struct hlist_node *n;
+	unsigned long key;
+
+	key = hash_long(ip, ftrace_profile_bits);
+	hhd = &stat->hash[key];
+
+	if (hlist_empty(hhd))
+		return NULL;
+
+	hlist_for_each_entry_rcu(rec, n, hhd, node) {
+		if (rec->ip == ip)
+			return rec;
+	}
+
+	return NULL;
+}
+
+static void ftrace_add_profile(struct ftrace_profile_stat *stat,
+			       struct ftrace_profile *rec)
+{
+	unsigned long key;
+
+	key = hash_long(rec->ip, ftrace_profile_bits);
+	hlist_add_head_rcu(&rec->node, &stat->hash[key]);
+}
+
+/*
+ * The memory is already allocated, this simply finds a new record to use.
+ */
+static struct ftrace_profile *
+ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+	struct ftrace_profile *rec = NULL;
+
+	/* prevent recursion (from NMIs) */
+	if (atomic_inc_return(&stat->disabled) != 1)
+		goto out;
+
+	/*
+	 * Try to find the function again since an NMI
+	 * could have added it
+	 */
+	rec = ftrace_find_profiled_func(stat, ip);
+	if (rec)
+		goto out;
+
+	if (stat->pages->index == PROFILES_PER_PAGE) {
+		if (!stat->pages->next)
+			goto out;
+		stat->pages = stat->pages->next;
+	}
+
+	rec = &stat->pages->records[stat->pages->index++];
+	rec->ip = ip;
+	ftrace_add_profile(stat, rec);
+
+ out:
+	atomic_dec(&stat->disabled);
+
+	return rec;
+}
+
+static void
+function_profile_call(unsigned long ip, unsigned long parent_ip)
+{
+	struct ftrace_profile_stat *stat;
+	struct ftrace_profile *rec;
+	unsigned long flags;
+
+	if (!ftrace_profile_enabled)
+		return;
+
+	local_irq_save(flags);
+
+	stat = &__get_cpu_var(ftrace_profile_stats);
+	if (!stat->hash || !ftrace_profile_enabled)
+		goto out;
+
+	rec = ftrace_find_profiled_func(stat, ip);
+	if (!rec) {
+		rec = ftrace_profile_alloc(stat, ip);
+		if (!rec)
+			goto out;
+	}
+
+	rec->counter++;
+ out:
+	local_irq_restore(flags);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int profile_graph_entry(struct ftrace_graph_ent *trace)
+{
+	function_profile_call(trace->func, 0);
+	return 1;
+}
+
+static void profile_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct ftrace_profile_stat *stat;
+	unsigned long long calltime;
+	struct ftrace_profile *rec;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	stat = &__get_cpu_var(ftrace_profile_stats);
+	if (!stat->hash || !ftrace_profile_enabled)
+		goto out;
+
+	calltime = trace->rettime - trace->calltime;
+
+	if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
+		int index;
+
+		index = trace->depth;
+
+		/* Append this call time to the parent time to subtract */
+		if (index)
+			current->ret_stack[index - 1].subtime += calltime;
+
+		if (current->ret_stack[index].subtime < calltime)
+			calltime -= current->ret_stack[index].subtime;
+		else
+			calltime = 0;
+	}
+
+	rec = ftrace_find_profiled_func(stat, trace->func);
+	if (rec)
+		rec->time += calltime;
+
+ out:
+	local_irq_restore(flags);
+}
+
+static int register_ftrace_profiler(void)
+{
+	return register_ftrace_graph(&profile_graph_return,
+				     &profile_graph_entry);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+	unregister_ftrace_graph();
+}
+#else
+static struct ftrace_ops ftrace_profile_ops __read_mostly =
+{
+	.func		= function_profile_call,
+};
+
+static int register_ftrace_profiler(void)
+{
+	return register_ftrace_function(&ftrace_profile_ops);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+	unregister_ftrace_function(&ftrace_profile_ops);
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+static ssize_t
+ftrace_profile_write(struct file *filp, const char __user *ubuf,
+		     size_t cnt, loff_t *ppos)
+{
+	unsigned long val;
+	char buf[64];		/* big enough to hold a number */
+	int ret;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	val = !!val;
+
+	mutex_lock(&ftrace_profile_lock);
+	if (ftrace_profile_enabled ^ val) {
+		if (val) {
+			ret = ftrace_profile_init();
+			if (ret < 0) {
+				cnt = ret;
+				goto out;
+			}
+
+			ret = register_ftrace_profiler();
+			if (ret < 0) {
+				cnt = ret;
+				goto out;
+			}
+			ftrace_profile_enabled = 1;
+		} else {
+			ftrace_profile_enabled = 0;
+			/*
+			 * unregister_ftrace_profiler calls stop_machine
+			 * so this acts like an synchronize_sched.
+			 */
+			unregister_ftrace_profiler();
+		}
+	}
+ out:
+	mutex_unlock(&ftrace_profile_lock);
+
+	filp->f_pos += cnt;
+
+	return cnt;
+}
+
+static ssize_t
+ftrace_profile_read(struct file *filp, char __user *ubuf,
+		     size_t cnt, loff_t *ppos)
+{
+	char buf[64];		/* big enough to hold a number */
+	int r;
+
+	r = sprintf(buf, "%u\n", ftrace_profile_enabled);
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static const struct file_operations ftrace_profile_fops = {
+	.open		= tracing_open_generic,
+	.read		= ftrace_profile_read,
+	.write		= ftrace_profile_write,
+};
+
+/* used to initialize the real stat files */
+static struct tracer_stat function_stats __initdata = {
+	.name		= "functions",
+	.stat_start	= function_stat_start,
+	.stat_next	= function_stat_next,
+	.stat_cmp	= function_stat_cmp,
+	.stat_headers	= function_stat_headers,
+	.stat_show	= function_stat_show
+};
+
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+	struct ftrace_profile_stat *stat;
+	struct dentry *entry;
+	char *name;
+	int ret;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		stat = &per_cpu(ftrace_profile_stats, cpu);
+
+		/* allocate enough for function name + cpu number */
+		name = kmalloc(32, GFP_KERNEL);
+		if (!name) {
+			/*
+			 * The files created are permanent, if something happens
+			 * we still do not free memory.
+			 */
+			kfree(stat);
+			WARN(1,
+			     "Could not allocate stat file for cpu %d\n",
+			     cpu);
+			return;
+		}
+		stat->stat = function_stats;
+		snprintf(name, 32, "function%d", cpu);
+		stat->stat.name = name;
+		ret = register_stat_tracer(&stat->stat);
+		if (ret) {
+			WARN(1,
+			     "Could not register function stat for cpu %d\n",
+			     cpu);
+			kfree(name);
+			return;
+		}
+	}
+
+	entry = debugfs_create_file("function_profile_enabled", 0644,
+				    d_tracer, NULL, &ftrace_profile_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'function_profile_enabled' entry\n");
+}
+
+#else /* CONFIG_FUNCTION_PROFILER */
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+}
+#endif /* CONFIG_FUNCTION_PROFILER */
+
 /* set when tracing only a pid */
 struct pid *ftrace_pid_trace;
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
@@ -261,7 +837,6 @@ struct ftrace_func_probe {
 	struct rcu_head		rcu;
 };
 
-
 enum {
 	FTRACE_ENABLE_CALLS		= (1 << 0),
 	FTRACE_DISABLE_CALLS		= (1 << 1),
@@ -346,30 +921,6 @@ static void ftrace_free_rec(struct dyn_ftrace *rec)
 	rec->flags |= FTRACE_FL_FREE;
 }
 
-void ftrace_release(void *start, unsigned long size)
-{
-	struct dyn_ftrace *rec;
-	struct ftrace_page *pg;
-	unsigned long s = (unsigned long)start;
-	unsigned long e = s + size;
-
-	if (ftrace_disabled || !start)
-		return;
-
-	mutex_lock(&ftrace_lock);
-	do_for_each_ftrace_rec(pg, rec) {
-		if ((rec->ip >= s) && (rec->ip < e)) {
-			/*
-			 * rec->ip is changed in ftrace_free_rec()
-			 * It should not between s and e if record was freed.
-			 */
-			FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
-			ftrace_free_rec(rec);
-		}
-	} while_for_each_ftrace_rec();
-	mutex_unlock(&ftrace_lock);
-}
-
 static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
 {
 	struct dyn_ftrace *rec;
@@ -1408,7 +1959,7 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
 
 static struct ftrace_ops trace_probe_ops __read_mostly =
 {
-	.func = function_trace_probe_call,
+	.func		= function_trace_probe_call,
 };
 
 static int ftrace_probe_registered;
@@ -1823,6 +2374,45 @@ void ftrace_set_notrace(unsigned char *buf, int len, int reset)
 	ftrace_set_regex(buf, len, reset, 0);
 }
 
+/*
+ * command line interface to allow users to set filters on boot up.
+ */
+#define FTRACE_FILTER_SIZE		COMMAND_LINE_SIZE
+static char ftrace_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
+static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata;
+
+static int __init set_ftrace_notrace(char *str)
+{
+	strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE);
+	return 1;
+}
+__setup("ftrace_notrace=", set_ftrace_notrace);
+
+static int __init set_ftrace_filter(char *str)
+{
+	strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE);
+	return 1;
+}
+__setup("ftrace_filter=", set_ftrace_filter);
+
+static void __init set_ftrace_early_filter(char *buf, int enable)
+{
+	char *func;
+
+	while (buf) {
+		func = strsep(&buf, ",");
+		ftrace_set_regex(func, strlen(func), 0, enable);
+	}
+}
+
+static void __init set_ftrace_early_filters(void)
+{
+	if (ftrace_filter_buf[0])
+		set_ftrace_early_filter(ftrace_filter_buf, 1);
+	if (ftrace_notrace_buf[0])
+		set_ftrace_early_filter(ftrace_notrace_buf, 0);
+}
+
 static int
 ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 {
@@ -2128,38 +2718,23 @@ static const struct file_operations ftrace_graph_fops = {
 
 static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 {
-	struct dentry *entry;
 
-	entry = debugfs_create_file("available_filter_functions", 0444,
-				    d_tracer, NULL, &ftrace_avail_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'available_filter_functions' entry\n");
+	trace_create_file("available_filter_functions", 0444,
+			d_tracer, NULL, &ftrace_avail_fops);
 
-	entry = debugfs_create_file("failures", 0444,
-				    d_tracer, NULL, &ftrace_failures_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'failures' entry\n");
+	trace_create_file("failures", 0444,
+			d_tracer, NULL, &ftrace_failures_fops);
 
-	entry = debugfs_create_file("set_ftrace_filter", 0644, d_tracer,
-				    NULL, &ftrace_filter_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'set_ftrace_filter' entry\n");
+	trace_create_file("set_ftrace_filter", 0644, d_tracer,
+			NULL, &ftrace_filter_fops);
 
-	entry = debugfs_create_file("set_ftrace_notrace", 0644, d_tracer,
+	trace_create_file("set_ftrace_notrace", 0644, d_tracer,
 				    NULL, &ftrace_notrace_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'set_ftrace_notrace' entry\n");
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	entry = debugfs_create_file("set_graph_function", 0444, d_tracer,
+	trace_create_file("set_graph_function", 0444, d_tracer,
 				    NULL,
 				    &ftrace_graph_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'set_graph_function' entry\n");
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 	return 0;
@@ -2197,14 +2772,72 @@ static int ftrace_convert_nops(struct module *mod,
 	return 0;
 }
 
-void ftrace_init_module(struct module *mod,
-			unsigned long *start, unsigned long *end)
+#ifdef CONFIG_MODULES
+void ftrace_release(void *start, void *end)
+{
+	struct dyn_ftrace *rec;
+	struct ftrace_page *pg;
+	unsigned long s = (unsigned long)start;
+	unsigned long e = (unsigned long)end;
+
+	if (ftrace_disabled || !start || start == end)
+		return;
+
+	mutex_lock(&ftrace_lock);
+	do_for_each_ftrace_rec(pg, rec) {
+		if ((rec->ip >= s) && (rec->ip < e)) {
+			/*
+			 * rec->ip is changed in ftrace_free_rec()
+			 * It should not between s and e if record was freed.
+			 */
+			FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
+			ftrace_free_rec(rec);
+		}
+	} while_for_each_ftrace_rec();
+	mutex_unlock(&ftrace_lock);
+}
+
+static void ftrace_init_module(struct module *mod,
+			       unsigned long *start, unsigned long *end)
 {
 	if (ftrace_disabled || start == end)
 		return;
 	ftrace_convert_nops(mod, start, end);
 }
 
+static int ftrace_module_notify(struct notifier_block *self,
+				unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		ftrace_init_module(mod, mod->ftrace_callsites,
+				   mod->ftrace_callsites +
+				   mod->num_ftrace_callsites);
+		break;
+	case MODULE_STATE_GOING:
+		ftrace_release(mod->ftrace_callsites,
+			       mod->ftrace_callsites +
+			       mod->num_ftrace_callsites);
+		break;
+	}
+
+	return 0;
+}
+#else
+static int ftrace_module_notify(struct notifier_block *self,
+				unsigned long val, void *data)
+{
+	return 0;
+}
+#endif /* CONFIG_MODULES */
+
+struct notifier_block ftrace_module_nb = {
+	.notifier_call = ftrace_module_notify,
+	.priority = 0,
+};
+
 extern unsigned long __start_mcount_loc[];
 extern unsigned long __stop_mcount_loc[];
 
@@ -2236,6 +2869,12 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
+	ret = register_module_notifier(&ftrace_module_nb);
+	if (ret)
+		pr_warning("Failed to register trace ftrace module notifier\n");
+
+	set_ftrace_early_filters();
+
 	return;
  failed:
 	ftrace_disabled = 1;
@@ -2417,7 +3056,6 @@ static const struct file_operations ftrace_pid_fops = {
 static __init int ftrace_init_debugfs(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -2425,11 +3063,11 @@ static __init int ftrace_init_debugfs(void)
 
 	ftrace_init_dyn_debugfs(d_tracer);
 
-	entry = debugfs_create_file("set_ftrace_pid", 0644, d_tracer,
-				    NULL, &ftrace_pid_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'set_ftrace_pid' entry\n");
+	trace_create_file("set_ftrace_pid", 0644, d_tracer,
+			    NULL, &ftrace_pid_fops);
+
+	ftrace_profile_debugfs(d_tracer);
+
 	return 0;
 }
 fs_initcall(ftrace_init_debugfs);
@@ -2538,7 +3176,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
-static atomic_t ftrace_graph_active;
+static int ftrace_graph_active;
 static struct notifier_block ftrace_suspend_notifier;
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
@@ -2580,12 +3218,12 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 		}
 
 		if (t->ret_stack == NULL) {
-			t->curr_ret_stack = -1;
-			/* Make sure IRQs see the -1 first: */
-			barrier();
-			t->ret_stack = ret_stack_list[start++];
 			atomic_set(&t->tracing_graph_pause, 0);
 			atomic_set(&t->trace_overrun, 0);
+			t->curr_ret_stack = -1;
+			/* Make sure the tasks see the -1 first: */
+			smp_wmb();
+			t->ret_stack = ret_stack_list[start++];
 		}
 	} while_each_thread(g, t);
 
@@ -2643,8 +3281,10 @@ static int start_graph_tracing(void)
 		return -ENOMEM;
 
 	/* The cpu_boot init_task->ret_stack will never be freed */
-	for_each_online_cpu(cpu)
-		ftrace_graph_init_task(idle_task(cpu));
+	for_each_online_cpu(cpu) {
+		if (!idle_task(cpu)->ret_stack)
+			ftrace_graph_init_task(idle_task(cpu));
+	}
 
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
@@ -2690,7 +3330,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	mutex_lock(&ftrace_lock);
 
 	/* we currently allow only one tracer registered at a time */
-	if (atomic_read(&ftrace_graph_active)) {
+	if (ftrace_graph_active) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -2698,10 +3338,10 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
 	register_pm_notifier(&ftrace_suspend_notifier);
 
-	atomic_inc(&ftrace_graph_active);
+	ftrace_graph_active++;
 	ret = start_graph_tracing();
 	if (ret) {
-		atomic_dec(&ftrace_graph_active);
+		ftrace_graph_active--;
 		goto out;
 	}
 
@@ -2719,10 +3359,10 @@ void unregister_ftrace_graph(void)
 {
 	mutex_lock(&ftrace_lock);
 
-	if (!unlikely(atomic_read(&ftrace_graph_active)))
+	if (unlikely(!ftrace_graph_active))
 		goto out;
 
-	atomic_dec(&ftrace_graph_active);
+	ftrace_graph_active--;
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
@@ -2736,18 +3376,25 @@ void unregister_ftrace_graph(void)
 /* Allocate a return stack for newly created task */
 void ftrace_graph_init_task(struct task_struct *t)
 {
-	if (atomic_read(&ftrace_graph_active)) {
-		t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+	/* Make sure we do not use the parent ret_stack */
+	t->ret_stack = NULL;
+
+	if (ftrace_graph_active) {
+		struct ftrace_ret_stack *ret_stack;
+
+		ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
 				* sizeof(struct ftrace_ret_stack),
 				GFP_KERNEL);
-		if (!t->ret_stack)
+		if (!ret_stack)
 			return;
 		t->curr_ret_stack = -1;
 		atomic_set(&t->tracing_graph_pause, 0);
 		atomic_set(&t->trace_overrun, 0);
 		t->ftrace_timestamp = 0;
-	} else
-		t->ret_stack = NULL;
+		/* make curr_ret_stack visable before we add the ret_stack */
+		smp_wmb();
+		t->ret_stack = ret_stack;
+	}
 }
 
 void ftrace_graph_exit_task(struct task_struct *t)
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 5011f4d91e37..86cdf671d7e2 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -12,7 +12,7 @@
 #include <linux/dcache.h>
 #include <linux/fs.h>
 
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 #include "trace_output.h"
 #include "trace.h"
@@ -42,6 +42,7 @@ static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
 				   gfp_t gfp_flags,
 				   int node)
 {
+	struct ftrace_event_call *call = &event_kmem_alloc;
 	struct trace_array *tr = kmemtrace_array;
 	struct kmemtrace_alloc_entry *entry;
 	struct ring_buffer_event *event;
@@ -62,7 +63,8 @@ static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
 	entry->gfp_flags	= gfp_flags;
 	entry->node		= node;
 
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
 	trace_wake_up();
 }
@@ -71,6 +73,7 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
 				  unsigned long call_site,
 				  const void *ptr)
 {
+	struct ftrace_event_call *call = &event_kmem_free;
 	struct trace_array *tr = kmemtrace_array;
 	struct kmemtrace_free_entry *entry;
 	struct ring_buffer_event *event;
@@ -86,7 +89,8 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
 	entry->call_site	= call_site;
 	entry->ptr		= ptr;
 
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
 	trace_wake_up();
 }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 960cbf44c844..2e642b2b7253 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -21,6 +21,28 @@
 
 #include "trace.h"
 
+/*
+ * The ring buffer header is special. We must manually up keep it.
+ */
+int ring_buffer_print_entry_header(struct trace_seq *s)
+{
+	int ret;
+
+	ret = trace_seq_printf(s, "# compressed entry header\n");
+	ret = trace_seq_printf(s, "\ttype_len    :    5 bits\n");
+	ret = trace_seq_printf(s, "\ttime_delta  :   27 bits\n");
+	ret = trace_seq_printf(s, "\tarray       :   32 bits\n");
+	ret = trace_seq_printf(s, "\n");
+	ret = trace_seq_printf(s, "\tpadding     : type == %d\n",
+			       RINGBUF_TYPE_PADDING);
+	ret = trace_seq_printf(s, "\ttime_extend : type == %d\n",
+			       RINGBUF_TYPE_TIME_EXTEND);
+	ret = trace_seq_printf(s, "\tdata max type_len  == %d\n",
+			       RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+
+	return ret;
+}
+
 /*
  * The ring buffer is made up of a list of pages. A separate list of pages is
  * allocated for each CPU. A writer may only write to a buffer that is
@@ -182,7 +204,10 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
 
 #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
 #define RB_ALIGNMENT		4U
-#define RB_MAX_SMALL_DATA	28
+#define RB_MAX_SMALL_DATA	(RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+
+/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
+#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
 
 enum {
 	RB_LEN_TIME_EXTEND = 8,
@@ -191,48 +216,28 @@ enum {
 
 static inline int rb_null_event(struct ring_buffer_event *event)
 {
-	return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0;
+	return event->type_len == RINGBUF_TYPE_PADDING
+			&& event->time_delta == 0;
 }
 
 static inline int rb_discarded_event(struct ring_buffer_event *event)
 {
-	return event->type == RINGBUF_TYPE_PADDING && event->time_delta;
+	return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta;
 }
 
 static void rb_event_set_padding(struct ring_buffer_event *event)
 {
-	event->type = RINGBUF_TYPE_PADDING;
+	event->type_len = RINGBUF_TYPE_PADDING;
 	event->time_delta = 0;
 }
 
-/**
- * ring_buffer_event_discard - discard an event in the ring buffer
- * @buffer: the ring buffer
- * @event: the event to discard
- *
- * Sometimes a event that is in the ring buffer needs to be ignored.
- * This function lets the user discard an event in the ring buffer
- * and then that event will not be read later.
- *
- * Note, it is up to the user to be careful with this, and protect
- * against races. If the user discards an event that has been consumed
- * it is possible that it could corrupt the ring buffer.
- */
-void ring_buffer_event_discard(struct ring_buffer_event *event)
-{
-	event->type = RINGBUF_TYPE_PADDING;
-	/* time delta must be non zero */
-	if (!event->time_delta)
-		event->time_delta = 1;
-}
-
 static unsigned
 rb_event_data_length(struct ring_buffer_event *event)
 {
 	unsigned length;
 
-	if (event->len)
-		length = event->len * RB_ALIGNMENT;
+	if (event->type_len)
+		length = event->type_len * RB_ALIGNMENT;
 	else
 		length = event->array[0];
 	return length + RB_EVNT_HDR_SIZE;
@@ -242,12 +247,12 @@ rb_event_data_length(struct ring_buffer_event *event)
 static unsigned
 rb_event_length(struct ring_buffer_event *event)
 {
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		if (rb_null_event(event))
 			/* undefined */
 			return -1;
-		return rb_event_data_length(event);
+		return  event->array[0] + RB_EVNT_HDR_SIZE;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		return RB_LEN_TIME_EXTEND;
@@ -271,7 +276,7 @@ rb_event_length(struct ring_buffer_event *event)
 unsigned ring_buffer_event_length(struct ring_buffer_event *event)
 {
 	unsigned length = rb_event_length(event);
-	if (event->type != RINGBUF_TYPE_DATA)
+	if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
 		return length;
 	length -= RB_EVNT_HDR_SIZE;
 	if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
@@ -284,9 +289,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_length);
 static void *
 rb_event_data(struct ring_buffer_event *event)
 {
-	BUG_ON(event->type != RINGBUF_TYPE_DATA);
+	BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
 	/* If length is in len field, then array[0] has the data */
-	if (event->len)
+	if (event->type_len)
 		return (void *)&event->array[0];
 	/* Otherwise length is in array[0] and array[1] has the data */
 	return (void *)&event->array[1];
@@ -316,9 +321,10 @@ struct buffer_data_page {
 };
 
 struct buffer_page {
+	struct list_head list;		/* list of buffer pages */
 	local_t		 write;		/* index for next write */
 	unsigned	 read;		/* index for next read */
-	struct list_head list;		/* list of free pages */
+	local_t		 entries;	/* entries on this page */
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
@@ -361,6 +367,34 @@ static inline int test_time_stamp(u64 delta)
 
 #define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
 
+/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
+#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
+
+/* Max number of timestamps that can fit on a page */
+#define RB_TIMESTAMPS_PER_PAGE	(BUF_PAGE_SIZE / RB_LEN_TIME_STAMP)
+
+int ring_buffer_print_page_header(struct trace_seq *s)
+{
+	struct buffer_data_page field;
+	int ret;
+
+	ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+			       "offset:0;\tsize:%u;\n",
+			       (unsigned int)sizeof(field.time_stamp));
+
+	ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
+			       "offset:%u;\tsize:%u;\n",
+			       (unsigned int)offsetof(typeof(field), commit),
+			       (unsigned int)sizeof(field.commit));
+
+	ret = trace_seq_printf(s, "\tfield: char data;\t"
+			       "offset:%u;\tsize:%u;\n",
+			       (unsigned int)offsetof(typeof(field), data),
+			       (unsigned int)BUF_PAGE_SIZE);
+
+	return ret;
+}
+
 /*
  * head_page == tail_page && head == tail then buffer is empty.
  */
@@ -375,8 +409,11 @@ struct ring_buffer_per_cpu {
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
 	struct buffer_page		*reader_page;
+	unsigned long			nmi_dropped;
+	unsigned long			commit_overrun;
 	unsigned long			overrun;
-	unsigned long			entries;
+	unsigned long			read;
+	local_t				entries;
 	u64				write_stamp;
 	u64				read_stamp;
 	atomic_t			record_disabled;
@@ -389,6 +426,8 @@ struct ring_buffer {
 	atomic_t			record_disabled;
 	cpumask_var_t			cpumask;
 
+	struct lock_class_key		*reader_lock_key;
+
 	struct mutex			mutex;
 
 	struct ring_buffer_per_cpu	**buffers;
@@ -420,13 +459,18 @@ struct ring_buffer_iter {
 /* Up this if you want to test the TIME_EXTENTS and normalization */
 #define DEBUG_SHIFT 0
 
+static inline u64 rb_time_stamp(struct ring_buffer *buffer, int cpu)
+{
+	/* shift to debug/test normalization and TIME_EXTENTS */
+	return buffer->clock() << DEBUG_SHIFT;
+}
+
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
 {
 	u64 time;
 
 	preempt_disable_notrace();
-	/* shift to debug/test normalization and TIME_EXTENTS */
-	time = buffer->clock() << DEBUG_SHIFT;
+	time = rb_time_stamp(buffer, cpu);
 	preempt_enable_no_resched_notrace();
 
 	return time;
@@ -523,6 +567,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 	cpu_buffer->cpu = cpu;
 	cpu_buffer->buffer = buffer;
 	spin_lock_init(&cpu_buffer->reader_lock);
+	lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
 	cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 	INIT_LIST_HEAD(&cpu_buffer->pages);
 
@@ -593,7 +638,8 @@ static int rb_cpu_notify(struct notifier_block *self,
  * when the buffer wraps. If this flag is not set, the buffer will
  * drop data when the tail hits the head.
  */
-struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
+struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
+					struct lock_class_key *key)
 {
 	struct ring_buffer *buffer;
 	int bsize;
@@ -616,6 +662,7 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 	buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 	buffer->flags = flags;
 	buffer->clock = trace_clock_local;
+	buffer->reader_lock_key = key;
 
 	/* need at least two pages */
 	if (buffer->pages == 1)
@@ -673,7 +720,7 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 	kfree(buffer);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(ring_buffer_alloc);
+EXPORT_SYMBOL_GPL(__ring_buffer_alloc);
 
 /**
  * ring_buffer_free - free a ring buffer.
@@ -947,31 +994,6 @@ static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
 	return rb_page_commit(cpu_buffer->head_page);
 }
 
-/*
- * When the tail hits the head and the buffer is in overwrite mode,
- * the head jumps to the next page and all content on the previous
- * page is discarded. But before doing so, we update the overrun
- * variable of the buffer.
- */
-static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	struct ring_buffer_event *event;
-	unsigned long head;
-
-	for (head = 0; head < rb_head_size(cpu_buffer);
-	     head += rb_event_length(event)) {
-
-		event = __rb_page_index(cpu_buffer->head_page, head);
-		if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
-			return;
-		/* Only count data entries */
-		if (event->type != RINGBUF_TYPE_DATA)
-			continue;
-		cpu_buffer->overrun++;
-		cpu_buffer->entries--;
-	}
-}
-
 static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
 			       struct buffer_page **bpage)
 {
@@ -991,7 +1013,7 @@ rb_event_index(struct ring_buffer_event *event)
 	return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
 }
 
-static int
+static inline int
 rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 	     struct ring_buffer_event *event)
 {
@@ -1110,28 +1132,21 @@ static void
 rb_update_event(struct ring_buffer_event *event,
 			 unsigned type, unsigned length)
 {
-	event->type = type;
+	event->type_len = type;
 
 	switch (type) {
 
 	case RINGBUF_TYPE_PADDING:
-		break;
-
 	case RINGBUF_TYPE_TIME_EXTEND:
-		event->len = DIV_ROUND_UP(RB_LEN_TIME_EXTEND, RB_ALIGNMENT);
-		break;
-
 	case RINGBUF_TYPE_TIME_STAMP:
-		event->len = DIV_ROUND_UP(RB_LEN_TIME_STAMP, RB_ALIGNMENT);
 		break;
 
-	case RINGBUF_TYPE_DATA:
+	case 0:
 		length -= RB_EVNT_HDR_SIZE;
-		if (length > RB_MAX_SMALL_DATA) {
-			event->len = 0;
+		if (length > RB_MAX_SMALL_DATA)
 			event->array[0] = length;
-		} else
-			event->len = DIV_ROUND_UP(length, RB_ALIGNMENT);
+		else
+			event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
 		break;
 	default:
 		BUG();
@@ -1155,16 +1170,144 @@ static unsigned rb_calculate_event_length(unsigned length)
 	return length;
 }
 
+
+static struct ring_buffer_event *
+rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
+	     unsigned long length, unsigned long tail,
+	     struct buffer_page *commit_page,
+	     struct buffer_page *tail_page, u64 *ts)
+{
+	struct buffer_page *next_page, *head_page, *reader_page;
+	struct ring_buffer *buffer = cpu_buffer->buffer;
+	struct ring_buffer_event *event;
+	bool lock_taken = false;
+	unsigned long flags;
+
+	next_page = tail_page;
+
+	local_irq_save(flags);
+	/*
+	 * Since the write to the buffer is still not
+	 * fully lockless, we must be careful with NMIs.
+	 * The locks in the writers are taken when a write
+	 * crosses to a new page. The locks protect against
+	 * races with the readers (this will soon be fixed
+	 * with a lockless solution).
+	 *
+	 * Because we can not protect against NMIs, and we
+	 * want to keep traces reentrant, we need to manage
+	 * what happens when we are in an NMI.
+	 *
+	 * NMIs can happen after we take the lock.
+	 * If we are in an NMI, only take the lock
+	 * if it is not already taken. Otherwise
+	 * simply fail.
+	 */
+	if (unlikely(in_nmi())) {
+		if (!__raw_spin_trylock(&cpu_buffer->lock)) {
+			cpu_buffer->nmi_dropped++;
+			goto out_reset;
+		}
+	} else
+		__raw_spin_lock(&cpu_buffer->lock);
+
+	lock_taken = true;
+
+	rb_inc_page(cpu_buffer, &next_page);
+
+	head_page = cpu_buffer->head_page;
+	reader_page = cpu_buffer->reader_page;
+
+	/* we grabbed the lock before incrementing */
+	if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+		goto out_reset;
+
+	/*
+	 * If for some reason, we had an interrupt storm that made
+	 * it all the way around the buffer, bail, and warn
+	 * about it.
+	 */
+	if (unlikely(next_page == commit_page)) {
+		cpu_buffer->commit_overrun++;
+		goto out_reset;
+	}
+
+	if (next_page == head_page) {
+		if (!(buffer->flags & RB_FL_OVERWRITE))
+			goto out_reset;
+
+		/* tail_page has not moved yet? */
+		if (tail_page == cpu_buffer->tail_page) {
+			/* count overflows */
+			cpu_buffer->overrun +=
+				local_read(&head_page->entries);
+
+			rb_inc_page(cpu_buffer, &head_page);
+			cpu_buffer->head_page = head_page;
+			cpu_buffer->head_page->read = 0;
+		}
+	}
+
+	/*
+	 * If the tail page is still the same as what we think
+	 * it is, then it is up to us to update the tail
+	 * pointer.
+	 */
+	if (tail_page == cpu_buffer->tail_page) {
+		local_set(&next_page->write, 0);
+		local_set(&next_page->entries, 0);
+		local_set(&next_page->page->commit, 0);
+		cpu_buffer->tail_page = next_page;
+
+		/* reread the time stamp */
+		*ts = rb_time_stamp(buffer, cpu_buffer->cpu);
+		cpu_buffer->tail_page->page->time_stamp = *ts;
+	}
+
+	/*
+	 * The actual tail page has moved forward.
+	 */
+	if (tail < BUF_PAGE_SIZE) {
+		/* Mark the rest of the page with padding */
+		event = __rb_page_index(tail_page, tail);
+		rb_event_set_padding(event);
+	}
+
+	/* Set the write back to the previous setting */
+	local_sub(length, &tail_page->write);
+
+	/*
+	 * If this was a commit entry that failed,
+	 * increment that too
+	 */
+	if (tail_page == cpu_buffer->commit_page &&
+	    tail == rb_commit_index(cpu_buffer)) {
+		rb_set_commit_to_write(cpu_buffer);
+	}
+
+	__raw_spin_unlock(&cpu_buffer->lock);
+	local_irq_restore(flags);
+
+	/* fail and let the caller try again */
+	return ERR_PTR(-EAGAIN);
+
+ out_reset:
+	/* reset write */
+	local_sub(length, &tail_page->write);
+
+	if (likely(lock_taken))
+		__raw_spin_unlock(&cpu_buffer->lock);
+	local_irq_restore(flags);
+	return NULL;
+}
+
 static struct ring_buffer_event *
 __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		  unsigned type, unsigned long length, u64 *ts)
 {
-	struct buffer_page *tail_page, *head_page, *reader_page, *commit_page;
-	unsigned long tail, write;
-	struct ring_buffer *buffer = cpu_buffer->buffer;
+	struct buffer_page *tail_page, *commit_page;
 	struct ring_buffer_event *event;
-	unsigned long flags;
-	bool lock_taken = false;
+	unsigned long tail, write;
 
 	commit_page = cpu_buffer->commit_page;
 	/* we just need to protect against interrupts */
@@ -1174,112 +1317,9 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	tail = write - length;
 
 	/* See if we shot pass the end of this buffer page */
-	if (write > BUF_PAGE_SIZE) {
-		struct buffer_page *next_page = tail_page;
-
-		local_irq_save(flags);
-		/*
-		 * Since the write to the buffer is still not
-		 * fully lockless, we must be careful with NMIs.
-		 * The locks in the writers are taken when a write
-		 * crosses to a new page. The locks protect against
-		 * races with the readers (this will soon be fixed
-		 * with a lockless solution).
-		 *
-		 * Because we can not protect against NMIs, and we
-		 * want to keep traces reentrant, we need to manage
-		 * what happens when we are in an NMI.
-		 *
-		 * NMIs can happen after we take the lock.
-		 * If we are in an NMI, only take the lock
-		 * if it is not already taken. Otherwise
-		 * simply fail.
-		 */
-		if (unlikely(in_nmi())) {
-			if (!__raw_spin_trylock(&cpu_buffer->lock))
-				goto out_reset;
-		} else
-			__raw_spin_lock(&cpu_buffer->lock);
-
-		lock_taken = true;
-
-		rb_inc_page(cpu_buffer, &next_page);
-
-		head_page = cpu_buffer->head_page;
-		reader_page = cpu_buffer->reader_page;
-
-		/* we grabbed the lock before incrementing */
-		if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
-			goto out_reset;
-
-		/*
-		 * If for some reason, we had an interrupt storm that made
-		 * it all the way around the buffer, bail, and warn
-		 * about it.
-		 */
-		if (unlikely(next_page == commit_page)) {
-			WARN_ON_ONCE(1);
-			goto out_reset;
-		}
-
-		if (next_page == head_page) {
-			if (!(buffer->flags & RB_FL_OVERWRITE))
-				goto out_reset;
-
-			/* tail_page has not moved yet? */
-			if (tail_page == cpu_buffer->tail_page) {
-				/* count overflows */
-				rb_update_overflow(cpu_buffer);
-
-				rb_inc_page(cpu_buffer, &head_page);
-				cpu_buffer->head_page = head_page;
-				cpu_buffer->head_page->read = 0;
-			}
-		}
-
-		/*
-		 * If the tail page is still the same as what we think
-		 * it is, then it is up to us to update the tail
-		 * pointer.
-		 */
-		if (tail_page == cpu_buffer->tail_page) {
-			local_set(&next_page->write, 0);
-			local_set(&next_page->page->commit, 0);
-			cpu_buffer->tail_page = next_page;
-
-			/* reread the time stamp */
-			*ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu);
-			cpu_buffer->tail_page->page->time_stamp = *ts;
-		}
-
-		/*
-		 * The actual tail page has moved forward.
-		 */
-		if (tail < BUF_PAGE_SIZE) {
-			/* Mark the rest of the page with padding */
-			event = __rb_page_index(tail_page, tail);
-			rb_event_set_padding(event);
-		}
-
-		if (tail <= BUF_PAGE_SIZE)
-			/* Set the write back to the previous setting */
-			local_set(&tail_page->write, tail);
-
-		/*
-		 * If this was a commit entry that failed,
-		 * increment that too
-		 */
-		if (tail_page == cpu_buffer->commit_page &&
-		    tail == rb_commit_index(cpu_buffer)) {
-			rb_set_commit_to_write(cpu_buffer);
-		}
-
-		__raw_spin_unlock(&cpu_buffer->lock);
-		local_irq_restore(flags);
-
-		/* fail and let the caller try again */
-		return ERR_PTR(-EAGAIN);
-	}
+	if (write > BUF_PAGE_SIZE)
+		return rb_move_tail(cpu_buffer, length, tail,
+				    commit_page, tail_page, ts);
 
 	/* We reserved something on the buffer */
 
@@ -1289,6 +1329,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	event = __rb_page_index(tail_page, tail);
 	rb_update_event(event, type, length);
 
+	/* The passed in type is zero for DATA */
+	if (likely(!type))
+		local_inc(&tail_page->entries);
+
 	/*
 	 * If this is a commit and the tail is zero, then update
 	 * this page's time stamp.
@@ -1297,16 +1341,38 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		cpu_buffer->commit_page->page->time_stamp = *ts;
 
 	return event;
+}
 
- out_reset:
-	/* reset write */
-	if (tail <= BUF_PAGE_SIZE)
-		local_set(&tail_page->write, tail);
+static inline int
+rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
+		  struct ring_buffer_event *event)
+{
+	unsigned long new_index, old_index;
+	struct buffer_page *bpage;
+	unsigned long index;
+	unsigned long addr;
 
-	if (likely(lock_taken))
-		__raw_spin_unlock(&cpu_buffer->lock);
-	local_irq_restore(flags);
-	return NULL;
+	new_index = rb_event_index(event);
+	old_index = new_index + rb_event_length(event);
+	addr = (unsigned long)event;
+	addr &= PAGE_MASK;
+
+	bpage = cpu_buffer->tail_page;
+
+	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
+		/*
+		 * This is on the tail page. It is possible that
+		 * a write could come in and move the tail page
+		 * and write to the next page. That is fine
+		 * because we just shorten what is on this page.
+		 */
+		index = local_cmpxchg(&bpage->write, old_index, new_index);
+		if (index == old_index)
+			return 1;
+	}
+
+	/* could not discard */
+	return 0;
 }
 
 static int
@@ -1351,16 +1417,23 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 			event->array[0] = *delta >> TS_SHIFT;
 		} else {
 			cpu_buffer->commit_page->page->time_stamp = *ts;
-			event->time_delta = 0;
-			event->array[0] = 0;
+			/* try to discard, since we do not need this */
+			if (!rb_try_to_discard(cpu_buffer, event)) {
+				/* nope, just zero it */
+				event->time_delta = 0;
+				event->array[0] = 0;
+			}
 		}
 		cpu_buffer->write_stamp = *ts;
 		/* let the caller know this was the commit */
 		ret = 1;
 	} else {
-		/* Darn, this is just wasted space */
-		event->time_delta = 0;
-		event->array[0] = 0;
+		/* Try to discard the event */
+		if (!rb_try_to_discard(cpu_buffer, event)) {
+			/* Darn, this is just wasted space */
+			event->time_delta = 0;
+			event->array[0] = 0;
+		}
 		ret = 0;
 	}
 
@@ -1371,13 +1444,14 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 
 static struct ring_buffer_event *
 rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
-		      unsigned type, unsigned long length)
+		      unsigned long length)
 {
 	struct ring_buffer_event *event;
-	u64 ts, delta;
+	u64 ts, delta = 0;
 	int commit = 0;
 	int nr_loops = 0;
 
+	length = rb_calculate_event_length(length);
  again:
 	/*
 	 * We allow for interrupts to reenter here and do a trace.
@@ -1391,7 +1465,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
 		return NULL;
 
-	ts = ring_buffer_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
+	ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
 
 	/*
 	 * Only the first commit can update the timestamp.
@@ -1401,23 +1475,24 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	 * also be made. But only the entry that did the actual
 	 * commit will be something other than zero.
 	 */
-	if (cpu_buffer->tail_page == cpu_buffer->commit_page &&
-	    rb_page_write(cpu_buffer->tail_page) ==
-	    rb_commit_index(cpu_buffer)) {
+	if (likely(cpu_buffer->tail_page == cpu_buffer->commit_page &&
+		   rb_page_write(cpu_buffer->tail_page) ==
+		   rb_commit_index(cpu_buffer))) {
+		u64 diff;
 
-		delta = ts - cpu_buffer->write_stamp;
+		diff = ts - cpu_buffer->write_stamp;
 
-		/* make sure this delta is calculated here */
+		/* make sure this diff is calculated here */
 		barrier();
 
 		/* Did the write stamp get updated already? */
 		if (unlikely(ts < cpu_buffer->write_stamp))
-			delta = 0;
+			goto get_event;
 
-		if (test_time_stamp(delta)) {
+		delta = diff;
+		if (unlikely(test_time_stamp(delta))) {
 
 			commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
-
 			if (commit == -EBUSY)
 				return NULL;
 
@@ -1426,12 +1501,11 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 
 			RB_WARN_ON(cpu_buffer, commit < 0);
 		}
-	} else
-		/* Non commits have zero deltas */
-		delta = 0;
+	}
 
-	event = __rb_reserve_next(cpu_buffer, type, length, &ts);
-	if (PTR_ERR(event) == -EAGAIN)
+ get_event:
+	event = __rb_reserve_next(cpu_buffer, 0, length, &ts);
+	if (unlikely(PTR_ERR(event) == -EAGAIN))
 		goto again;
 
 	if (!event) {
@@ -1448,7 +1522,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	 * If the timestamp was commited, make the commit our entry
 	 * now so that we will update it when needed.
 	 */
-	if (commit)
+	if (unlikely(commit))
 		rb_set_commit_event(cpu_buffer, event);
 	else if (!rb_is_commit(cpu_buffer, event))
 		delta = 0;
@@ -1458,6 +1532,36 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 }
 
+#define TRACE_RECURSIVE_DEPTH 16
+
+static int trace_recursive_lock(void)
+{
+	current->trace_recursion++;
+
+	if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+		return 0;
+
+	/* Disable all tracing before we do anything else */
+	tracing_off_permanent();
+
+	printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
+		    "HC[%lu]:SC[%lu]:NMI[%lu]\n",
+		    current->trace_recursion,
+		    hardirq_count() >> HARDIRQ_SHIFT,
+		    softirq_count() >> SOFTIRQ_SHIFT,
+		    in_nmi());
+
+	WARN_ON_ONCE(1);
+	return -1;
+}
+
+static void trace_recursive_unlock(void)
+{
+	WARN_ON_ONCE(!current->trace_recursion);
+
+	current->trace_recursion--;
+}
+
 static DEFINE_PER_CPU(int, rb_need_resched);
 
 /**
@@ -1491,6 +1595,9 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	/* If we are tracing schedule, we don't want to recurse */
 	resched = ftrace_preempt_disable();
 
+	if (trace_recursive_lock())
+		goto out_nocheck;
+
 	cpu = raw_smp_processor_id();
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
@@ -1501,11 +1608,10 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	if (atomic_read(&cpu_buffer->record_disabled))
 		goto out;
 
-	length = rb_calculate_event_length(length);
-	if (length > BUF_PAGE_SIZE)
+	if (length > BUF_MAX_DATA_SIZE)
 		goto out;
 
-	event = rb_reserve_next_event(cpu_buffer, RINGBUF_TYPE_DATA, length);
+	event = rb_reserve_next_event(cpu_buffer, length);
 	if (!event)
 		goto out;
 
@@ -1520,6 +1626,9 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	return event;
 
  out:
+	trace_recursive_unlock();
+
+ out_nocheck:
 	ftrace_preempt_enable(resched);
 	return NULL;
 }
@@ -1528,7 +1637,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
 static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		      struct ring_buffer_event *event)
 {
-	cpu_buffer->entries++;
+	local_inc(&cpu_buffer->entries);
 
 	/* Only process further if we own the commit */
 	if (!rb_is_commit(cpu_buffer, event))
@@ -1558,6 +1667,8 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
 	rb_commit(cpu_buffer, event);
 
+	trace_recursive_unlock();
+
 	/*
 	 * Only the last preempt count needs to restore preemption.
 	 */
@@ -1570,6 +1681,99 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 
+static inline void rb_event_discard(struct ring_buffer_event *event)
+{
+	/* array[0] holds the actual length for the discarded event */
+	event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE;
+	event->type_len = RINGBUF_TYPE_PADDING;
+	/* time delta must be non zero */
+	if (!event->time_delta)
+		event->time_delta = 1;
+}
+
+/**
+ * ring_buffer_event_discard - discard any event in the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
+{
+	rb_event_discard(event);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_event_discard);
+
+/**
+ * ring_buffer_commit_discard - discard an event that has not been committed
+ * @buffer: the ring buffer
+ * @event: non committed event to discard
+ *
+ * This is similar to ring_buffer_event_discard but must only be
+ * performed on an event that has not been committed yet. The difference
+ * is that this will also try to free the event from the ring buffer
+ * if another event has not been added behind it.
+ *
+ * If another event has been added behind it, it will set the event
+ * up as discarded, and perform the commit.
+ *
+ * If this function is called, do not call ring_buffer_unlock_commit on
+ * the event.
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int cpu;
+
+	/* The event is discarded regardless */
+	rb_event_discard(event);
+
+	/*
+	 * This must only be called if the event has not been
+	 * committed yet. Thus we can assume that preemption
+	 * is still disabled.
+	 */
+	RB_WARN_ON(buffer, preemptible());
+
+	cpu = smp_processor_id();
+	cpu_buffer = buffer->buffers[cpu];
+
+	if (!rb_try_to_discard(cpu_buffer, event))
+		goto out;
+
+	/*
+	 * The commit is still visible by the reader, so we
+	 * must increment entries.
+	 */
+	local_inc(&cpu_buffer->entries);
+ out:
+	/*
+	 * If a write came in and pushed the tail page
+	 * we still need to update the commit pointer
+	 * if we were the commit.
+	 */
+	if (rb_is_commit(cpu_buffer, event))
+		rb_set_commit_to_write(cpu_buffer);
+
+	trace_recursive_unlock();
+
+	/*
+	 * Only the last preempt count needs to restore preemption.
+	 */
+	if (preempt_count() == 1)
+		ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+	else
+		preempt_enable_no_resched_notrace();
+
+}
+EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
+
 /**
  * ring_buffer_write - write data to the buffer without reserving
  * @buffer: The ring buffer to write to.
@@ -1589,7 +1793,6 @@ int ring_buffer_write(struct ring_buffer *buffer,
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
-	unsigned long event_length;
 	void *body;
 	int ret = -EBUSY;
 	int cpu, resched;
@@ -1612,9 +1815,10 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	if (atomic_read(&cpu_buffer->record_disabled))
 		goto out;
 
-	event_length = rb_calculate_event_length(length);
-	event = rb_reserve_next_event(cpu_buffer,
-				      RINGBUF_TYPE_DATA, event_length);
+	if (length > BUF_MAX_DATA_SIZE)
+		goto out;
+
+	event = rb_reserve_next_event(cpu_buffer, length);
 	if (!event)
 		goto out;
 
@@ -1728,7 +1932,8 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->entries;
+	ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
+		- cpu_buffer->read;
 
 	return ret;
 }
@@ -1754,6 +1959,47 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
+/**
+ * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long ret;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	ret = cpu_buffer->nmi_dropped;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
+
+/**
+ * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long
+ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long ret;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	ret = cpu_buffer->commit_overrun;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu);
+
 /**
  * ring_buffer_entries - get the number of entries in a buffer
  * @buffer: The ring buffer
@@ -1770,7 +2016,8 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 	/* if you care about this being correct, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		entries += cpu_buffer->entries;
+		entries += (local_read(&cpu_buffer->entries) -
+			    cpu_buffer->overrun) - cpu_buffer->read;
 	}
 
 	return entries;
@@ -1862,7 +2109,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 {
 	u64 delta;
 
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		return;
 
@@ -1893,7 +2140,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 {
 	u64 delta;
 
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		return;
 
@@ -1966,6 +2213,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->reader_page->list.prev = reader->list.prev;
 
 	local_set(&cpu_buffer->reader_page->write, 0);
+	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
 
 	/* Make the reader page now replace the head */
@@ -2008,8 +2256,9 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 	event = rb_reader_event(cpu_buffer);
 
-	if (event->type == RINGBUF_TYPE_DATA || rb_discarded_event(event))
-		cpu_buffer->entries--;
+	if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX
+			|| rb_discarded_event(event))
+		cpu_buffer->read++;
 
 	rb_update_read_stamp(cpu_buffer, event);
 
@@ -2031,8 +2280,8 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	 * Check if we are at the end of the buffer.
 	 */
 	if (iter->head >= rb_page_size(iter->head_page)) {
-		if (RB_WARN_ON(buffer,
-			       iter->head_page == cpu_buffer->commit_page))
+		/* discarded commits can make the page empty */
+		if (iter->head_page == cpu_buffer->commit_page)
 			return;
 		rb_inc_iter(iter);
 		return;
@@ -2075,12 +2324,10 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	/*
 	 * We repeat when a timestamp is encountered. It is possible
 	 * to get multiple timestamps from an interrupt entering just
-	 * as one timestamp is about to be written. The max times
-	 * that this can happen is the number of nested interrupts we
-	 * can have.  Nesting 10 deep of interrupts is clearly
-	 * an anomaly.
+	 * as one timestamp is about to be written, or from discarded
+	 * commits. The most that we can have is the number on a single page.
 	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
 		return NULL;
 
 	reader = rb_get_reader_page(cpu_buffer);
@@ -2089,7 +2336,7 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 
 	event = rb_reader_event(cpu_buffer);
 
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		if (rb_null_event(event))
 			RB_WARN_ON(cpu_buffer, 1);
@@ -2146,14 +2393,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
  again:
 	/*
-	 * We repeat when a timestamp is encountered. It is possible
-	 * to get multiple timestamps from an interrupt entering just
-	 * as one timestamp is about to be written. The max times
-	 * that this can happen is the number of nested interrupts we
-	 * can have. Nesting 10 deep of interrupts is clearly
-	 * an anomaly.
+	 * We repeat when a timestamp is encountered.
+	 * We can get multiple timestamps by nested interrupts or also
+	 * if filtering is on (discarding commits). Since discarding
+	 * commits can be frequent we can get a lot of timestamps.
+	 * But we limit them by not adding timestamps if they begin
+	 * at the start of a page.
 	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
 		return NULL;
 
 	if (rb_per_cpu_empty(cpu_buffer))
@@ -2161,7 +2408,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
 	event = rb_iter_head_event(iter);
 
-	switch (event->type) {
+	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
 		if (rb_null_event(event)) {
 			rb_inc_iter(iter);
@@ -2220,7 +2467,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	event = rb_buffer_peek(buffer, cpu, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type == RINGBUF_TYPE_PADDING) {
+	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
 		cpu_relax();
 		goto again;
 	}
@@ -2248,7 +2495,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	event = rb_iter_peek(iter, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type == RINGBUF_TYPE_PADDING) {
+	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
 		cpu_relax();
 		goto again;
 	}
@@ -2293,7 +2540,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
  out:
 	preempt_enable();
 
-	if (event && event->type == RINGBUF_TYPE_PADDING) {
+	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
 		cpu_relax();
 		goto again;
 	}
@@ -2386,7 +2633,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
  out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	if (event && event->type == RINGBUF_TYPE_PADDING) {
+	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
 		cpu_relax();
 		goto again;
 	}
@@ -2411,6 +2658,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->head_page
 		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
 	local_set(&cpu_buffer->head_page->write, 0);
+	local_set(&cpu_buffer->head_page->entries, 0);
 	local_set(&cpu_buffer->head_page->page->commit, 0);
 
 	cpu_buffer->head_page->read = 0;
@@ -2420,11 +2668,15 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
 	local_set(&cpu_buffer->reader_page->write, 0);
+	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
 	cpu_buffer->reader_page->read = 0;
 
+	cpu_buffer->nmi_dropped = 0;
+	cpu_buffer->commit_overrun = 0;
 	cpu_buffer->overrun = 0;
-	cpu_buffer->entries = 0;
+	cpu_buffer->read = 0;
+	local_set(&cpu_buffer->entries, 0);
 
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
@@ -2443,6 +2695,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
 
+	atomic_inc(&cpu_buffer->record_disabled);
+
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
 	__raw_spin_lock(&cpu_buffer->lock);
@@ -2452,6 +2706,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	__raw_spin_unlock(&cpu_buffer->lock);
 
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	atomic_dec(&cpu_buffer->record_disabled);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
@@ -2578,28 +2834,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
 
-static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
-			      struct buffer_data_page *bpage,
-			      unsigned int offset)
-{
-	struct ring_buffer_event *event;
-	unsigned long head;
-
-	__raw_spin_lock(&cpu_buffer->lock);
-	for (head = offset; head < local_read(&bpage->commit);
-	     head += rb_event_length(event)) {
-
-		event = __rb_data_page_index(bpage, head);
-		if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
-			return;
-		/* Only count data entries */
-		if (event->type != RINGBUF_TYPE_DATA)
-			continue;
-		cpu_buffer->entries--;
-	}
-	__raw_spin_unlock(&cpu_buffer->lock);
-}
-
 /**
  * ring_buffer_alloc_read_page - allocate a page to read from buffer
  * @buffer: the buffer to allocate for.
@@ -2630,6 +2864,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
 
 	return bpage;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
 
 /**
  * ring_buffer_free_read_page - free an allocated read page
@@ -2642,6 +2877,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
 {
 	free_page((unsigned long)data);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
 
 /**
  * ring_buffer_read_page - extract a page from the ring buffer
@@ -2768,16 +3004,17 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		/* we copied everything to the beginning */
 		read = 0;
 	} else {
+		/* update the entry counter */
+		cpu_buffer->read += local_read(&reader->entries);
+
 		/* swap the pages */
 		rb_init_page(bpage);
 		bpage = reader->page;
 		reader->page = *data_page;
 		local_set(&reader->write, 0);
+		local_set(&reader->entries, 0);
 		reader->read = 0;
 		*data_page = bpage;
-
-		/* update the entry counter */
-		rb_remove_entries(cpu_buffer, bpage, read);
 	}
 	ret = read;
 
@@ -2787,6 +3024,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
  out:
 	return ret;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
 static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
@@ -2845,14 +3083,11 @@ static const struct file_operations rb_simple_fops = {
 static __init int rb_init_debugfs(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 
 	d_tracer = tracing_init_dentry();
 
-	entry = debugfs_create_file("tracing_on", 0644, d_tracer,
-				    &ring_buffer_flags, &rb_simple_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'tracing_on' entry\n");
+	trace_create_file("tracing_on", 0644, d_tracer,
+			    &ring_buffer_flags, &rb_simple_fops);
 
 	return 0;
 }
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
new file mode 100644
index 000000000000..8d68e149a8b3
--- /dev/null
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -0,0 +1,416 @@
+/*
+ * ring buffer tester and benchmark
+ *
+ * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/time.h>
+
+struct rb_page {
+	u64		ts;
+	local_t		commit;
+	char		data[4080];
+};
+
+/* run time and sleep time in seconds */
+#define RUN_TIME	10
+#define SLEEP_TIME	10
+
+/* number of events for writer to wake up the reader */
+static int wakeup_interval = 100;
+
+static int reader_finish;
+static struct completion read_start;
+static struct completion read_done;
+
+static struct ring_buffer *buffer;
+static struct task_struct *producer;
+static struct task_struct *consumer;
+static unsigned long read;
+
+static int disable_reader;
+module_param(disable_reader, uint, 0644);
+MODULE_PARM_DESC(disable_reader, "only run producer");
+
+static int read_events;
+
+static int kill_test;
+
+#define KILL_TEST()				\
+	do {					\
+		if (!kill_test) {		\
+			kill_test = 1;		\
+			WARN_ON(1);		\
+		}				\
+	} while (0)
+
+enum event_status {
+	EVENT_FOUND,
+	EVENT_DROPPED,
+};
+
+static enum event_status read_event(int cpu)
+{
+	struct ring_buffer_event *event;
+	int *entry;
+	u64 ts;
+
+	event = ring_buffer_consume(buffer, cpu, &ts);
+	if (!event)
+		return EVENT_DROPPED;
+
+	entry = ring_buffer_event_data(event);
+	if (*entry != cpu) {
+		KILL_TEST();
+		return EVENT_DROPPED;
+	}
+
+	read++;
+	return EVENT_FOUND;
+}
+
+static enum event_status read_page(int cpu)
+{
+	struct ring_buffer_event *event;
+	struct rb_page *rpage;
+	unsigned long commit;
+	void *bpage;
+	int *entry;
+	int ret;
+	int inc;
+	int i;
+
+	bpage = ring_buffer_alloc_read_page(buffer);
+	if (!bpage)
+		return EVENT_DROPPED;
+
+	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+	if (ret >= 0) {
+		rpage = bpage;
+		commit = local_read(&rpage->commit);
+		for (i = 0; i < commit && !kill_test; i += inc) {
+
+			if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+				KILL_TEST();
+				break;
+			}
+
+			inc = -1;
+			event = (void *)&rpage->data[i];
+			switch (event->type_len) {
+			case RINGBUF_TYPE_PADDING:
+				/* We don't expect any padding */
+				KILL_TEST();
+				break;
+			case RINGBUF_TYPE_TIME_EXTEND:
+				inc = 8;
+				break;
+			case 0:
+				entry = ring_buffer_event_data(event);
+				if (*entry != cpu) {
+					KILL_TEST();
+					break;
+				}
+				read++;
+				if (!event->array[0]) {
+					KILL_TEST();
+					break;
+				}
+				inc = event->array[0];
+				break;
+			default:
+				entry = ring_buffer_event_data(event);
+				if (*entry != cpu) {
+					KILL_TEST();
+					break;
+				}
+				read++;
+				inc = ((event->type_len + 1) * 4);
+			}
+			if (kill_test)
+				break;
+
+			if (inc <= 0) {
+				KILL_TEST();
+				break;
+			}
+		}
+	}
+	ring_buffer_free_read_page(buffer, bpage);
+
+	if (ret < 0)
+		return EVENT_DROPPED;
+	return EVENT_FOUND;
+}
+
+static void ring_buffer_consumer(void)
+{
+	/* toggle between reading pages and events */
+	read_events ^= 1;
+
+	read = 0;
+	while (!reader_finish && !kill_test) {
+		int found;
+
+		do {
+			int cpu;
+
+			found = 0;
+			for_each_online_cpu(cpu) {
+				enum event_status stat;
+
+				if (read_events)
+					stat = read_event(cpu);
+				else
+					stat = read_page(cpu);
+
+				if (kill_test)
+					break;
+				if (stat == EVENT_FOUND)
+					found = 1;
+			}
+		} while (found && !kill_test);
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (reader_finish)
+			break;
+
+		schedule();
+		__set_current_state(TASK_RUNNING);
+	}
+	reader_finish = 0;
+	complete(&read_done);
+}
+
+static void ring_buffer_producer(void)
+{
+	struct timeval start_tv;
+	struct timeval end_tv;
+	unsigned long long time;
+	unsigned long long entries;
+	unsigned long long overruns;
+	unsigned long missed = 0;
+	unsigned long hit = 0;
+	unsigned long avg;
+	int cnt = 0;
+
+	/*
+	 * Hammer the buffer for 10 secs (this may
+	 * make the system stall)
+	 */
+	pr_info("Starting ring buffer hammer\n");
+	do_gettimeofday(&start_tv);
+	do {
+		struct ring_buffer_event *event;
+		int *entry;
+
+		event = ring_buffer_lock_reserve(buffer, 10);
+		if (!event) {
+			missed++;
+		} else {
+			hit++;
+			entry = ring_buffer_event_data(event);
+			*entry = smp_processor_id();
+			ring_buffer_unlock_commit(buffer, event);
+		}
+		do_gettimeofday(&end_tv);
+
+		cnt++;
+		if (consumer && !(cnt % wakeup_interval))
+			wake_up_process(consumer);
+
+#ifndef CONFIG_PREEMPT
+		/*
+		 * If we are a non preempt kernel, the 10 second run will
+		 * stop everything while it runs. Instead, we will call
+		 * cond_resched and also add any time that was lost by a
+		 * rescedule.
+		 *
+		 * Do a cond resched at the same frequency we would wake up
+		 * the reader.
+		 */
+		if (cnt % wakeup_interval)
+			cond_resched();
+#endif
+
+	} while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
+	pr_info("End ring buffer hammer\n");
+
+	if (consumer) {
+		/* Init both completions here to avoid races */
+		init_completion(&read_start);
+		init_completion(&read_done);
+		/* the completions must be visible before the finish var */
+		smp_wmb();
+		reader_finish = 1;
+		/* finish var visible before waking up the consumer */
+		smp_wmb();
+		wake_up_process(consumer);
+		wait_for_completion(&read_done);
+	}
+
+	time = end_tv.tv_sec - start_tv.tv_sec;
+	time *= USEC_PER_SEC;
+	time += (long long)((long)end_tv.tv_usec - (long)start_tv.tv_usec);
+
+	entries = ring_buffer_entries(buffer);
+	overruns = ring_buffer_overruns(buffer);
+
+	if (kill_test)
+		pr_info("ERROR!\n");
+	pr_info("Time:     %lld (usecs)\n", time);
+	pr_info("Overruns: %lld\n", overruns);
+	if (disable_reader)
+		pr_info("Read:     (reader disabled)\n");
+	else
+		pr_info("Read:     %ld  (by %s)\n", read,
+			read_events ? "events" : "pages");
+	pr_info("Entries:  %lld\n", entries);
+	pr_info("Total:    %lld\n", entries + overruns + read);
+	pr_info("Missed:   %ld\n", missed);
+	pr_info("Hit:      %ld\n", hit);
+
+	/* Convert time from usecs to millisecs */
+	do_div(time, USEC_PER_MSEC);
+	if (time)
+		hit /= (long)time;
+	else
+		pr_info("TIME IS ZERO??\n");
+
+	pr_info("Entries per millisec: %ld\n", hit);
+
+	if (hit) {
+		/* Calculate the average time in nanosecs */
+		avg = NSEC_PER_MSEC / hit;
+		pr_info("%ld ns per entry\n", avg);
+	}
+
+	if (missed) {
+		if (time)
+			missed /= (long)time;
+
+		pr_info("Total iterations per millisec: %ld\n", hit + missed);
+
+		/* it is possible that hit + missed will overflow and be zero */
+		if (!(hit + missed)) {
+			pr_info("hit + missed overflowed and totalled zero!\n");
+			hit--; /* make it non zero */
+		}
+
+		/* Caculate the average time in nanosecs */
+		avg = NSEC_PER_MSEC / (hit + missed);
+		pr_info("%ld ns per entry\n", avg);
+	}
+}
+
+static void wait_to_die(void)
+{
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
+static int ring_buffer_consumer_thread(void *arg)
+{
+	while (!kthread_should_stop() && !kill_test) {
+		complete(&read_start);
+
+		ring_buffer_consumer();
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_stop() || kill_test)
+			break;
+
+		schedule();
+		__set_current_state(TASK_RUNNING);
+	}
+	__set_current_state(TASK_RUNNING);
+
+	if (kill_test)
+		wait_to_die();
+
+	return 0;
+}
+
+static int ring_buffer_producer_thread(void *arg)
+{
+	init_completion(&read_start);
+
+	while (!kthread_should_stop() && !kill_test) {
+		ring_buffer_reset(buffer);
+
+		if (consumer) {
+			smp_wmb();
+			wake_up_process(consumer);
+			wait_for_completion(&read_start);
+		}
+
+		ring_buffer_producer();
+
+		pr_info("Sleeping for 10 secs\n");
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(HZ * SLEEP_TIME);
+		__set_current_state(TASK_RUNNING);
+	}
+
+	if (kill_test)
+		wait_to_die();
+
+	return 0;
+}
+
+static int __init ring_buffer_benchmark_init(void)
+{
+	int ret;
+
+	/* make a one meg buffer in overwite mode */
+	buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE);
+	if (!buffer)
+		return -ENOMEM;
+
+	if (!disable_reader) {
+		consumer = kthread_create(ring_buffer_consumer_thread,
+					  NULL, "rb_consumer");
+		ret = PTR_ERR(consumer);
+		if (IS_ERR(consumer))
+			goto out_fail;
+	}
+
+	producer = kthread_run(ring_buffer_producer_thread,
+			       NULL, "rb_producer");
+	ret = PTR_ERR(producer);
+
+	if (IS_ERR(producer))
+		goto out_kill;
+
+	return 0;
+
+ out_kill:
+	if (consumer)
+		kthread_stop(consumer);
+
+ out_fail:
+	ring_buffer_free(buffer);
+	return ret;
+}
+
+static void __exit ring_buffer_benchmark_exit(void)
+{
+	kthread_stop(producer);
+	if (consumer)
+		kthread_stop(consumer);
+	ring_buffer_free(buffer);
+}
+
+module_init(ring_buffer_benchmark_init);
+module_exit(ring_buffer_benchmark_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("ring_buffer_benchmark");
+MODULE_LICENSE("GPL");
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index cda81ec58d9f..8acd9b81a5d7 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -171,6 +171,13 @@ static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
+int filter_current_check_discard(struct ftrace_event_call *call, void *rec,
+				 struct ring_buffer_event *event)
+{
+	return filter_check_discard(call, rec, global_trace.buffer, event);
+}
+EXPORT_SYMBOL_GPL(filter_current_check_discard);
+
 cycle_t ftrace_now(int cpu)
 {
 	u64 ts;
@@ -255,7 +262,8 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
-	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME;
+	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
+	TRACE_ITER_GRAPH_TIME;
 
 /**
  * trace_wake_up - wake up tasks waiting for trace input
@@ -317,6 +325,7 @@ static const char *trace_options[] = {
 	"latency-format",
 	"global-clock",
 	"sleep-time",
+	"graph-time",
 	NULL
 };
 
@@ -402,17 +411,6 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	return cnt;
 }
 
-static void
-trace_print_seq(struct seq_file *m, struct trace_seq *s)
-{
-	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
-
-	s->buffer[len] = 0;
-	seq_puts(m, s->buffer);
-
-	trace_seq_init(s);
-}
-
 /**
  * update_max_tr - snapshot all trace buffers from global_trace to max_tr
  * @tr: tracer
@@ -641,6 +639,16 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 		tracing_reset(tr, cpu);
 }
 
+void tracing_reset_current(int cpu)
+{
+	tracing_reset(&global_trace, cpu);
+}
+
+void tracing_reset_current_online_cpus(void)
+{
+	tracing_reset_online_cpus(&global_trace);
+}
+
 #define SAVED_CMDLINES 128
 #define NO_CMDLINE_MAP UINT_MAX
 static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
@@ -800,6 +808,7 @@ void trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
+	preempt_disable();
 	__raw_spin_lock(&trace_cmdline_lock);
 	map = map_pid_to_cmdline[pid];
 	if (map != NO_CMDLINE_MAP)
@@ -808,6 +817,7 @@ void trace_find_cmdline(int pid, char comm[])
 		strcpy(comm, "<...>");
 
 	__raw_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
 }
 
 void tracing_record_cmdline(struct task_struct *tsk)
@@ -840,7 +850,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 }
 
 struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    unsigned char type,
+						    int type,
 						    unsigned long len,
 						    unsigned long flags, int pc)
 {
@@ -883,30 +893,40 @@ void trace_buffer_unlock_commit(struct trace_array *tr,
 }
 
 struct ring_buffer_event *
-trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
+trace_current_buffer_lock_reserve(int type, unsigned long len,
 				  unsigned long flags, int pc)
 {
 	return trace_buffer_lock_reserve(&global_trace,
 					 type, len, flags, pc);
 }
+EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
 
 void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
 }
+EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
 
 void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
 }
+EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
+
+void trace_current_buffer_discard_commit(struct ring_buffer_event *event)
+{
+	ring_buffer_discard_commit(global_trace.buffer, event);
+}
+EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
 
 void
 trace_function(struct trace_array *tr,
 	       unsigned long ip, unsigned long parent_ip, unsigned long flags,
 	       int pc)
 {
+	struct ftrace_event_call *call = &event_function;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
 
@@ -921,7 +941,9 @@ trace_function(struct trace_array *tr,
 	entry	= ring_buffer_event_data(event);
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
-	ring_buffer_unlock_commit(tr->buffer, event);
+
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -930,6 +952,7 @@ static int __trace_graph_entry(struct trace_array *tr,
 				unsigned long flags,
 				int pc)
 {
+	struct ftrace_event_call *call = &event_funcgraph_entry;
 	struct ring_buffer_event *event;
 	struct ftrace_graph_ent_entry *entry;
 
@@ -942,7 +965,8 @@ static int __trace_graph_entry(struct trace_array *tr,
 		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
-	ring_buffer_unlock_commit(global_trace.buffer, event);
+	if (!filter_current_check_discard(call, entry, event))
+		ring_buffer_unlock_commit(global_trace.buffer, event);
 
 	return 1;
 }
@@ -952,6 +976,7 @@ static void __trace_graph_return(struct trace_array *tr,
 				unsigned long flags,
 				int pc)
 {
+	struct ftrace_event_call *call = &event_funcgraph_exit;
 	struct ring_buffer_event *event;
 	struct ftrace_graph_ret_entry *entry;
 
@@ -964,7 +989,8 @@ static void __trace_graph_return(struct trace_array *tr,
 		return;
 	entry	= ring_buffer_event_data(event);
 	entry->ret				= *trace;
-	ring_buffer_unlock_commit(global_trace.buffer, event);
+	if (!filter_current_check_discard(call, entry, event))
+		ring_buffer_unlock_commit(global_trace.buffer, event);
 }
 #endif
 
@@ -982,6 +1008,7 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 				 int skip, int pc)
 {
 #ifdef CONFIG_STACKTRACE
+	struct ftrace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 	struct stack_trace trace;
@@ -999,7 +1026,8 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace(&trace);
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 #endif
 }
 
@@ -1024,6 +1052,7 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 				   unsigned long flags, int pc)
 {
 #ifdef CONFIG_STACKTRACE
+	struct ftrace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
 	struct stack_trace trace;
@@ -1045,7 +1074,8 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace_user(&trace);
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 #endif
 }
 
@@ -1089,6 +1119,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 			   struct task_struct *next,
 			   unsigned long flags, int pc)
 {
+	struct ftrace_event_call *call = &event_context_switch;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 
@@ -1104,7 +1135,9 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_prio		= next->prio;
 	entry->next_state		= next->state;
 	entry->next_cpu	= task_cpu(next);
-	trace_buffer_unlock_commit(tr, event, flags, pc);
+
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		trace_buffer_unlock_commit(tr, event, flags, pc);
 }
 
 void
@@ -1113,6 +1146,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 			   struct task_struct *curr,
 			   unsigned long flags, int pc)
 {
+	struct ftrace_event_call *call = &event_wakeup;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 
@@ -1129,7 +1163,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_state		= wakee->state;
 	entry->next_cpu			= task_cpu(wakee);
 
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 	ftrace_trace_stack(tr, flags, 6, pc);
 	ftrace_trace_userstack(tr, flags, pc);
 }
@@ -1230,11 +1265,13 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 		(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 	static u32 trace_buf[TRACE_BUF_SIZE];
 
+	struct ftrace_event_call *call = &event_bprint;
 	struct ring_buffer_event *event;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
 	struct bprint_entry *entry;
 	unsigned long flags;
+	int disable;
 	int resched;
 	int cpu, len = 0, size, pc;
 
@@ -1249,7 +1286,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
 
-	if (unlikely(atomic_read(&data->disabled)))
+	disable = atomic_inc_return(&data->disabled);
+	if (unlikely(disable != 1))
 		goto out;
 
 	/* Lockdep uses trace_printk for lock tracing */
@@ -1269,13 +1307,15 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
 out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
 	local_irq_restore(flags);
 
 out:
+	atomic_dec_return(&data->disabled);
 	ftrace_preempt_enable(resched);
 	unpause_graph_tracing();
 
@@ -1288,12 +1328,14 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
 	static char trace_buf[TRACE_BUF_SIZE];
 
+	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
 	int cpu, len = 0, size, pc;
 	struct print_entry *entry;
 	unsigned long irq_flags;
+	int disable;
 
 	if (tracing_disabled || tracing_selftest_running)
 		return 0;
@@ -1303,7 +1345,8 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
 
-	if (unlikely(atomic_read(&data->disabled)))
+	disable = atomic_inc_return(&data->disabled);
+	if (unlikely(disable != 1))
 		goto out;
 
 	pause_graph_tracing();
@@ -1323,13 +1366,15 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = 0;
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
  out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
 	raw_local_irq_restore(irq_flags);
 	unpause_graph_tracing();
  out:
+	atomic_dec_return(&data->disabled);
 	preempt_enable_notrace();
 
 	return len;
@@ -1526,12 +1571,14 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		p = s_next(m, p, &l);
 	}
 
+	trace_event_read_lock();
 	return p;
 }
 
 static void s_stop(struct seq_file *m, void *p)
 {
 	atomic_dec(&trace_record_cmdline_disabled);
+	trace_event_read_unlock();
 }
 
 static void print_lat_help_header(struct seq_file *m)
@@ -1774,6 +1821,7 @@ static int trace_empty(struct trace_iterator *iter)
 	return 1;
 }
 
+/*  Called with trace_event_read_lock() held. */
 static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
 	enum print_line_t ret;
@@ -2396,6 +2444,56 @@ static const struct file_operations tracing_readme_fops = {
 	.read		= tracing_readme_read,
 };
 
+static ssize_t
+tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	char *buf_comm;
+	char *file_buf;
+	char *buf;
+	int len = 0;
+	int pid;
+	int i;
+
+	file_buf = kmalloc(SAVED_CMDLINES*(16+TASK_COMM_LEN), GFP_KERNEL);
+	if (!file_buf)
+		return -ENOMEM;
+
+	buf_comm = kmalloc(TASK_COMM_LEN, GFP_KERNEL);
+	if (!buf_comm) {
+		kfree(file_buf);
+		return -ENOMEM;
+	}
+
+	buf = file_buf;
+
+	for (i = 0; i < SAVED_CMDLINES; i++) {
+		int r;
+
+		pid = map_cmdline_to_pid[i];
+		if (pid == -1 || pid == NO_CMDLINE_MAP)
+			continue;
+
+		trace_find_cmdline(pid, buf_comm);
+		r = sprintf(buf, "%d %s\n", pid, buf_comm);
+		buf += r;
+		len += r;
+	}
+
+	len = simple_read_from_buffer(ubuf, cnt, ppos,
+				      file_buf, len);
+
+	kfree(file_buf);
+	kfree(buf_comm);
+
+	return len;
+}
+
+static const struct file_operations tracing_saved_cmdlines_fops = {
+    .open       = tracing_open_generic,
+    .read       = tracing_saved_cmdlines_read,
+};
+
 static ssize_t
 tracing_ctrl_read(struct file *filp, char __user *ubuf,
 		  size_t cnt, loff_t *ppos)
@@ -2728,6 +2826,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	/* trace pipe does not show start of buffer */
 	cpumask_setall(iter->started);
 
+	if (trace_flags & TRACE_ITER_LATENCY_FMT)
+		iter->iter_flags |= TRACE_FILE_LAT_FMT;
+
 	iter->cpu_file = cpu_file;
 	iter->tr = &global_trace;
 	mutex_init(&iter->mutex);
@@ -2915,6 +3016,7 @@ waitagain:
 	       offsetof(struct trace_iterator, seq));
 	iter->pos = -1;
 
+	trace_event_read_lock();
 	while (find_next_entry_inc(iter) != NULL) {
 		enum print_line_t ret;
 		int len = iter->seq.len;
@@ -2931,6 +3033,7 @@ waitagain:
 		if (iter->seq.len >= cnt)
 			break;
 	}
+	trace_event_read_unlock();
 
 	/* Now copy what we have to the user */
 	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
@@ -3053,6 +3156,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		goto out_err;
 	}
 
+	trace_event_read_lock();
+
 	/* Fill as many pages as possible. */
 	for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
 		pages[i] = alloc_page(GFP_KERNEL);
@@ -3075,6 +3180,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		trace_seq_init(&iter->seq);
 	}
 
+	trace_event_read_unlock();
 	mutex_unlock(&iter->mutex);
 
 	spd.nr_pages = i;
@@ -3425,7 +3531,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
-	int size, i;
+	int entries, size, i;
 	size_t ret;
 
 	if (*ppos & (PAGE_SIZE - 1)) {
@@ -3440,7 +3546,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		len &= PAGE_MASK;
 	}
 
-	for (i = 0; i < PIPE_BUFFERS && len; i++, len -= PAGE_SIZE) {
+	entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
+
+	for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
 		struct page *page;
 		int r;
 
@@ -3457,7 +3565,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		}
 
 		r = ring_buffer_read_page(ref->buffer, &ref->page,
-					  len, info->cpu, 0);
+					  len, info->cpu, 1);
 		if (r < 0) {
 			ring_buffer_free_read_page(ref->buffer,
 						   ref->page);
@@ -3481,6 +3589,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		spd.partial[i].private = (unsigned long)ref;
 		spd.nr_pages++;
 		*ppos += PAGE_SIZE;
+
+		entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 	}
 
 	spd.nr_pages = i;
@@ -3508,6 +3618,45 @@ static const struct file_operations tracing_buffers_fops = {
 	.llseek		= no_llseek,
 };
 
+static ssize_t
+tracing_stats_read(struct file *filp, char __user *ubuf,
+		   size_t count, loff_t *ppos)
+{
+	unsigned long cpu = (unsigned long)filp->private_data;
+	struct trace_array *tr = &global_trace;
+	struct trace_seq *s;
+	unsigned long cnt;
+
+	s = kmalloc(sizeof(*s), GFP_ATOMIC);
+	if (!s)
+		return ENOMEM;
+
+	trace_seq_init(s);
+
+	cnt = ring_buffer_entries_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "entries: %ld\n", cnt);
+
+	cnt = ring_buffer_overrun_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "overrun: %ld\n", cnt);
+
+	cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "commit overrun: %ld\n", cnt);
+
+	cnt = ring_buffer_nmi_dropped_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "nmi dropped: %ld\n", cnt);
+
+	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+	kfree(s);
+
+	return count;
+}
+
+static const struct file_operations tracing_stats_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_stats_read,
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 int __weak ftrace_arch_read_dyn_info(char *buf, int size)
@@ -3597,7 +3746,7 @@ struct dentry *tracing_dentry_percpu(void)
 static void tracing_init_debugfs_percpu(long cpu)
 {
 	struct dentry *d_percpu = tracing_dentry_percpu();
-	struct dentry *entry, *d_cpu;
+	struct dentry *d_cpu;
 	/* strlen(cpu) + MAX(log10(cpu)) + '\0' */
 	char cpu_dir[7];
 
@@ -3612,21 +3761,18 @@ static void tracing_init_debugfs_percpu(long cpu)
 	}
 
 	/* per cpu trace_pipe */
-	entry = debugfs_create_file("trace_pipe", 0444, d_cpu,
-				(void *) cpu, &tracing_pipe_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace_pipe' entry\n");
+	trace_create_file("trace_pipe", 0444, d_cpu,
+			(void *) cpu, &tracing_pipe_fops);
 
 	/* per cpu trace */
-	entry = debugfs_create_file("trace", 0644, d_cpu,
-				(void *) cpu, &tracing_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace' entry\n");
+	trace_create_file("trace", 0644, d_cpu,
+			(void *) cpu, &tracing_fops);
 
-	entry = debugfs_create_file("trace_pipe_raw", 0444, d_cpu,
-				    (void *) cpu, &tracing_buffers_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace_pipe_raw' entry\n");
+	trace_create_file("trace_pipe_raw", 0444, d_cpu,
+			(void *) cpu, &tracing_buffers_fops);
+
+	trace_create_file("stats", 0444, d_cpu,
+			(void *) cpu, &tracing_stats_fops);
 }
 
 #ifdef CONFIG_FTRACE_SELFTEST
@@ -3782,6 +3928,22 @@ static const struct file_operations trace_options_core_fops = {
 	.write = trace_options_core_write,
 };
 
+struct dentry *trace_create_file(const char *name,
+				 mode_t mode,
+				 struct dentry *parent,
+				 void *data,
+				 const struct file_operations *fops)
+{
+	struct dentry *ret;
+
+	ret = debugfs_create_file(name, mode, parent, data, fops);
+	if (!ret)
+		pr_warning("Could not create debugfs '%s' entry\n", name);
+
+	return ret;
+}
+
+
 static struct dentry *trace_options_init_dentry(void)
 {
 	struct dentry *d_tracer;
@@ -3809,7 +3971,6 @@ create_trace_option_file(struct trace_option_dentry *topt,
 			 struct tracer_opt *opt)
 {
 	struct dentry *t_options;
-	struct dentry *entry;
 
 	t_options = trace_options_init_dentry();
 	if (!t_options)
@@ -3818,11 +3979,9 @@ create_trace_option_file(struct trace_option_dentry *topt,
 	topt->flags = flags;
 	topt->opt = opt;
 
-	entry = debugfs_create_file(opt->name, 0644, t_options, topt,
+	topt->entry = trace_create_file(opt->name, 0644, t_options, topt,
 				    &trace_options_fops);
 
-	topt->entry = entry;
-
 }
 
 static struct trace_option_dentry *
@@ -3877,123 +4036,84 @@ static struct dentry *
 create_trace_option_core_file(const char *option, long index)
 {
 	struct dentry *t_options;
-	struct dentry *entry;
 
 	t_options = trace_options_init_dentry();
 	if (!t_options)
 		return NULL;
 
-	entry = debugfs_create_file(option, 0644, t_options, (void *)index,
+	return trace_create_file(option, 0644, t_options, (void *)index,
 				    &trace_options_core_fops);
-
-	return entry;
 }
 
 static __init void create_trace_options_dir(void)
 {
 	struct dentry *t_options;
-	struct dentry *entry;
 	int i;
 
 	t_options = trace_options_init_dentry();
 	if (!t_options)
 		return;
 
-	for (i = 0; trace_options[i]; i++) {
-		entry = create_trace_option_core_file(trace_options[i], i);
-		if (!entry)
-			pr_warning("Could not create debugfs %s entry\n",
-				   trace_options[i]);
-	}
+	for (i = 0; trace_options[i]; i++)
+		create_trace_option_core_file(trace_options[i], i);
 }
 
 static __init int tracer_init_debugfs(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 	int cpu;
 
 	d_tracer = tracing_init_dentry();
 
-	entry = debugfs_create_file("tracing_enabled", 0644, d_tracer,
-				    &global_trace, &tracing_ctrl_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'tracing_enabled' entry\n");
+	trace_create_file("tracing_enabled", 0644, d_tracer,
+			&global_trace, &tracing_ctrl_fops);
 
-	entry = debugfs_create_file("trace_options", 0644, d_tracer,
-				    NULL, &tracing_iter_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace_options' entry\n");
+	trace_create_file("trace_options", 0644, d_tracer,
+			NULL, &tracing_iter_fops);
 
-	create_trace_options_dir();
+	trace_create_file("tracing_cpumask", 0644, d_tracer,
+			NULL, &tracing_cpumask_fops);
 
-	entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer,
-				    NULL, &tracing_cpumask_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'tracing_cpumask' entry\n");
+	trace_create_file("trace", 0644, d_tracer,
+			(void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
 
-	entry = debugfs_create_file("trace", 0644, d_tracer,
-				 (void *) TRACE_PIPE_ALL_CPU, &tracing_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'trace' entry\n");
+	trace_create_file("available_tracers", 0444, d_tracer,
+			&global_trace, &show_traces_fops);
 
-	entry = debugfs_create_file("available_tracers", 0444, d_tracer,
-				    &global_trace, &show_traces_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'available_tracers' entry\n");
+	trace_create_file("current_tracer", 0644, d_tracer,
+			&global_trace, &set_tracer_fops);
 
-	entry = debugfs_create_file("current_tracer", 0444, d_tracer,
-				    &global_trace, &set_tracer_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'current_tracer' entry\n");
+	trace_create_file("tracing_max_latency", 0644, d_tracer,
+			&tracing_max_latency, &tracing_max_lat_fops);
 
-	entry = debugfs_create_file("tracing_max_latency", 0644, d_tracer,
-				    &tracing_max_latency,
-				    &tracing_max_lat_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'tracing_max_latency' entry\n");
+	trace_create_file("tracing_thresh", 0644, d_tracer,
+			&tracing_thresh, &tracing_max_lat_fops);
 
-	entry = debugfs_create_file("tracing_thresh", 0644, d_tracer,
-				    &tracing_thresh, &tracing_max_lat_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'tracing_thresh' entry\n");
-	entry = debugfs_create_file("README", 0644, d_tracer,
-				    NULL, &tracing_readme_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'README' entry\n");
+	trace_create_file("README", 0444, d_tracer,
+			NULL, &tracing_readme_fops);
 
-	entry = debugfs_create_file("trace_pipe", 0444, d_tracer,
+	trace_create_file("trace_pipe", 0444, d_tracer,
 			(void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'trace_pipe' entry\n");
 
-	entry = debugfs_create_file("buffer_size_kb", 0644, d_tracer,
-				    &global_trace, &tracing_entries_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'buffer_size_kb' entry\n");
+	trace_create_file("buffer_size_kb", 0644, d_tracer,
+			&global_trace, &tracing_entries_fops);
 
-	entry = debugfs_create_file("trace_marker", 0220, d_tracer,
-				    NULL, &tracing_mark_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'trace_marker' entry\n");
+	trace_create_file("trace_marker", 0220, d_tracer,
+			NULL, &tracing_mark_fops);
+
+	trace_create_file("saved_cmdlines", 0444, d_tracer,
+			NULL, &tracing_saved_cmdlines_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
-				    &ftrace_update_tot_cnt,
-				    &tracing_dyn_info_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'dyn_ftrace_total_info' entry\n");
+	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
+			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
 #endif
 #ifdef CONFIG_SYSPROF_TRACER
 	init_tracer_sysprof_debugfs(d_tracer);
 #endif
 
+	create_trace_options_dir();
+
 	for_each_tracing_cpu(cpu)
 		tracing_init_debugfs_percpu(cpu);
 
@@ -4064,7 +4184,8 @@ trace_printk_seq(struct trace_seq *s)
 
 static void __ftrace_dump(bool disable_tracing)
 {
-	static DEFINE_SPINLOCK(ftrace_dump_lock);
+	static raw_spinlock_t ftrace_dump_lock =
+		(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
 	unsigned int old_userobj;
@@ -4073,7 +4194,8 @@ static void __ftrace_dump(bool disable_tracing)
 	int cnt = 0, cpu;
 
 	/* only one dump */
-	spin_lock_irqsave(&ftrace_dump_lock, flags);
+	local_irq_save(flags);
+	__raw_spin_lock(&ftrace_dump_lock);
 	if (dump_ran)
 		goto out;
 
@@ -4145,7 +4267,8 @@ static void __ftrace_dump(bool disable_tracing)
 	}
 
  out:
-	spin_unlock_irqrestore(&ftrace_dump_lock, flags);
+	__raw_spin_unlock(&ftrace_dump_lock);
+	local_irq_restore(flags);
 }
 
 /* By default: disable tracing after the dump */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e685ac2b2ba1..6e735d4771f8 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -9,9 +9,12 @@
 #include <linux/mmiotrace.h>
 #include <linux/ftrace.h>
 #include <trace/boot.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 #include <trace/power.h>
 
+#include <linux/trace_seq.h>
+#include <linux/ftrace_event.h>
+
 enum trace_type {
 	__TRACE_FIRST_TYPE = 0,
 
@@ -41,20 +44,6 @@ enum trace_type {
 	__TRACE_LAST_TYPE,
 };
 
-/*
- * The trace entry - the most basic unit of tracing. This is what
- * is printed in the end as a single line in the trace output, such as:
- *
- *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
- */
-struct trace_entry {
-	unsigned char		type;
-	unsigned char		flags;
-	unsigned char		preempt_count;
-	int			pid;
-	int			tgid;
-};
-
 /*
  * Function trace entry - function address and parent function addres:
  */
@@ -263,8 +252,6 @@ struct trace_array_cpu {
 	char			comm[TASK_COMM_LEN];
 };
 
-struct trace_iterator;
-
 /*
  * The trace array - an array of per-CPU trace arrays. This is the
  * highest level data structure that individual tracers deal with.
@@ -339,15 +326,6 @@ extern void __ftrace_bad_type(void);
 		__ftrace_bad_type();					\
 	} while (0)
 
-/* Return values for print_line callback */
-enum print_line_t {
-	TRACE_TYPE_PARTIAL_LINE	= 0,	/* Retry after flushing the seq */
-	TRACE_TYPE_HANDLED	= 1,
-	TRACE_TYPE_UNHANDLED	= 2,	/* Relay to other output functions */
-	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
-};
-
-
 /*
  * An option specific to a tracer. This is a boolean value.
  * The bit is the bit index that sets its value on the
@@ -423,60 +401,30 @@ struct tracer {
 	struct tracer_stat	*stats;
 };
 
-struct trace_seq {
-	unsigned char		buffer[PAGE_SIZE];
-	unsigned int		len;
-	unsigned int		readpos;
-};
-
-static inline void
-trace_seq_init(struct trace_seq *s)
-{
-	s->len = 0;
-	s->readpos = 0;
-}
-
 
 #define TRACE_PIPE_ALL_CPU	-1
 
-/*
- * Trace iterator - used by printout routines who present trace
- * results to users and which routines might sleep, etc:
- */
-struct trace_iterator {
-	struct trace_array	*tr;
-	struct tracer		*trace;
-	void			*private;
-	int			cpu_file;
-	struct mutex		mutex;
-	struct ring_buffer_iter	*buffer_iter[NR_CPUS];
-
-	/* The below is zeroed out in pipe_read */
-	struct trace_seq	seq;
-	struct trace_entry	*ent;
-	int			cpu;
-	u64			ts;
-
-	unsigned long		iter_flags;
-	loff_t			pos;
-	long			idx;
-
-	cpumask_var_t		started;
-};
-
 int tracer_init(struct tracer *t, struct trace_array *tr);
 int tracing_is_enabled(void);
 void trace_wake_up(void);
 void tracing_reset(struct trace_array *tr, int cpu);
 void tracing_reset_online_cpus(struct trace_array *tr);
+void tracing_reset_current(int cpu);
+void tracing_reset_current_online_cpus(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
+struct dentry *trace_create_file(const char *name,
+				 mode_t mode,
+				 struct dentry *parent,
+				 void *data,
+				 const struct file_operations *fops);
+
 struct dentry *tracing_init_dentry(void);
 void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
 
 struct ring_buffer_event;
 
 struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    unsigned char type,
+						    int type,
 						    unsigned long len,
 						    unsigned long flags,
 						    int pc);
@@ -484,14 +432,6 @@ void trace_buffer_unlock_commit(struct trace_array *tr,
 				struct ring_buffer_event *event,
 				unsigned long flags, int pc);
 
-struct ring_buffer_event *
-trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
-				  unsigned long flags, int pc);
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
-					unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
-					unsigned long flags, int pc);
-
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
 
@@ -514,7 +454,6 @@ void tracing_sched_switch_trace(struct trace_array *tr,
 				struct task_struct *prev,
 				struct task_struct *next,
 				unsigned long flags, int pc);
-void tracing_record_cmdline(struct task_struct *tsk);
 
 void tracing_sched_wakeup_trace(struct trace_array *tr,
 				struct task_struct *wakee,
@@ -599,6 +538,8 @@ extern int trace_selftest_startup_sysprof(struct tracer *trace,
 					       struct trace_array *tr);
 extern int trace_selftest_startup_branch(struct tracer *trace,
 					 struct trace_array *tr);
+extern int trace_selftest_startup_hw_branches(struct tracer *trace,
+					      struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
@@ -613,6 +554,8 @@ extern unsigned long trace_flags;
 /* Standard output formatting function used for function return traces */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 /* TODO: make this variable */
@@ -644,7 +587,6 @@ static inline int ftrace_graph_addr(unsigned long addr)
 	return 1;
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
-
 #else /* CONFIG_FUNCTION_GRAPH_TRACER */
 static inline enum print_line_t
 print_graph_function(struct trace_iterator *iter)
@@ -692,6 +634,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_LATENCY_FMT		= 0x40000,
 	TRACE_ITER_GLOBAL_CLK		= 0x80000,
 	TRACE_ITER_SLEEP_TIME		= 0x100000,
+	TRACE_ITER_GRAPH_TIME		= 0x200000,
 };
 
 /*
@@ -790,103 +733,113 @@ struct ftrace_event_field {
 	char			*type;
 	int			offset;
 	int			size;
+	int			is_signed;
 };
 
-struct ftrace_event_call {
-	char			*name;
-	char			*system;
-	struct dentry		*dir;
-	int			enabled;
-	int			(*regfunc)(void);
-	void			(*unregfunc)(void);
-	int			id;
-	int			(*raw_init)(void);
-	int			(*show_format)(struct trace_seq *s);
-	int			(*define_fields)(void);
-	struct list_head	fields;
+struct event_filter {
+	int			n_preds;
 	struct filter_pred	**preds;
-
-#ifdef CONFIG_EVENT_PROFILE
-	atomic_t	profile_count;
-	int		(*profile_enable)(struct ftrace_event_call *);
-	void		(*profile_disable)(struct ftrace_event_call *);
-#endif
+	char			*filter_string;
 };
 
 struct event_subsystem {
 	struct list_head	list;
 	const char		*name;
 	struct dentry		*entry;
-	struct filter_pred	**preds;
+	void			*filter;
 };
 
-#define events_for_each(event)						\
-	for (event = __start_ftrace_events;				\
-	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
-	     event++)
-
-#define MAX_FILTER_PRED 8
-
 struct filter_pred;
 
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
+				 int val1, int val2);
 
 struct filter_pred {
 	filter_pred_fn_t fn;
 	u64 val;
-	char *str_val;
+	char str_val[MAX_FILTER_STR_VAL];
 	int str_len;
 	char *field_name;
 	int offset;
 	int not;
-	int or;
-	int compound;
-	int clear;
+	int op;
+	int pop_n;
 };
 
-int trace_define_field(struct ftrace_event_call *call, char *type,
-		       char *name, int offset, int size);
-extern void filter_free_pred(struct filter_pred *pred);
-extern void filter_print_preds(struct filter_pred **preds,
+extern void print_event_filter(struct ftrace_event_call *call,
 			       struct trace_seq *s);
-extern int filter_parse(char **pbuf, struct filter_pred *pred);
-extern int filter_add_pred(struct ftrace_event_call *call,
-			   struct filter_pred *pred);
-extern void filter_free_preds(struct ftrace_event_call *call);
-extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
-extern void filter_free_subsystem_preds(struct event_subsystem *system);
-extern int filter_add_subsystem_pred(struct event_subsystem *system,
-				     struct filter_pred *pred);
+extern int apply_event_filter(struct ftrace_event_call *call,
+			      char *filter_string);
+extern int apply_subsystem_event_filter(struct event_subsystem *system,
+					char *filter_string);
+extern void print_subsystem_event_filter(struct event_subsystem *system,
+					 struct trace_seq *s);
 
-void event_trace_printk(unsigned long ip, const char *fmt, ...);
-extern struct ftrace_event_call __start_ftrace_events[];
-extern struct ftrace_event_call __stop_ftrace_events[];
+static inline int
+filter_check_discard(struct ftrace_event_call *call, void *rec,
+		     struct ring_buffer *buffer,
+		     struct ring_buffer_event *event)
+{
+	if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) {
+		ring_buffer_discard_commit(buffer, event);
+		return 1;
+	}
 
-#define for_each_event(event)						\
-	for (event = __start_ftrace_events;				\
-	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
-	     event++)
+	return 0;
+}
+
+#define DEFINE_COMPARISON_PRED(type)					\
+static int filter_pred_##type(struct filter_pred *pred, void *event,	\
+			      int val1, int val2)			\
+{									\
+	type *addr = (type *)(event + pred->offset);			\
+	type val = (type)pred->val;					\
+	int match = 0;							\
+									\
+	switch (pred->op) {						\
+	case OP_LT:							\
+		match = (*addr < val);					\
+		break;							\
+	case OP_LE:							\
+		match = (*addr <= val);					\
+		break;							\
+	case OP_GT:							\
+		match = (*addr > val);					\
+		break;							\
+	case OP_GE:							\
+		match = (*addr >= val);					\
+		break;							\
+	default:							\
+		break;							\
+	}								\
+									\
+	return match;							\
+}
+
+#define DEFINE_EQUALITY_PRED(size)					\
+static int filter_pred_##size(struct filter_pred *pred, void *event,	\
+			      int val1, int val2)			\
+{									\
+	u##size *addr = (u##size *)(event + pred->offset);		\
+	u##size val = (u##size)pred->val;				\
+	int match;							\
+									\
+	match = (val == *addr) ^ pred->not;				\
+									\
+	return match;							\
+}
+
+extern struct mutex event_mutex;
+extern struct list_head ftrace_events;
 
 extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
-/*
- * The double __builtin_constant_p is because gcc will give us an error
- * if we try to allocate the static variable to fmt if it is not a
- * constant. Even with the outer if statement optimizing out.
- */
-#define event_trace_printk(ip, fmt, args...)				\
-do {									\
-	__trace_printk_check_format(fmt, ##args);			\
-	tracing_record_cmdline(current);				\
-	if (__builtin_constant_p(fmt)) {				\
-		static const char *trace_printk_fmt			\
-		  __attribute__((section("__trace_printk_fmt"))) =	\
-			__builtin_constant_p(fmt) ? fmt : NULL;		\
-									\
-		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
-	} else								\
-		__trace_printk(ip, fmt, ##args);			\
-} while (0)
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+	extern struct ftrace_event_call event_##call;
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, tpfmt)
+#include "trace_event_types.h"
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 7a30fc4c3642..a29ef23ffb47 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -9,6 +9,7 @@
 #include <linux/debugfs.h>
 #include <linux/ftrace.h>
 #include <linux/kallsyms.h>
+#include <linux/time.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -67,7 +68,7 @@ initcall_call_print_line(struct trace_iterator *iter)
 	trace_assign_type(field, entry);
 	call = &field->boot_call;
 	ts = iter->ts;
-	nsec_rem = do_div(ts, 1000000000);
+	nsec_rem = do_div(ts, NSEC_PER_SEC);
 
 	ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
 			(unsigned long)ts, nsec_rem, call->func, call->caller);
@@ -92,7 +93,7 @@ initcall_ret_print_line(struct trace_iterator *iter)
 	trace_assign_type(field, entry);
 	init_ret = &field->boot_ret;
 	ts = iter->ts;
-	nsec_rem = do_div(ts, 1000000000);
+	nsec_rem = do_div(ts, NSEC_PER_SEC);
 
 	ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
 			"returned %d after %llu msecs\n",
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 8333715e4066..7a7a9fd249a9 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -30,6 +30,7 @@ static struct trace_array *branch_tracer;
 static void
 probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 {
+	struct ftrace_event_call *call = &event_branch;
 	struct trace_array *tr = branch_tracer;
 	struct ring_buffer_event *event;
 	struct trace_branch *entry;
@@ -73,7 +74,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	entry->line = f->line;
 	entry->correct = val == expect;
 
-	ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
 
  out:
 	atomic_dec(&tr->data[cpu]->disabled);
@@ -271,7 +273,7 @@ static int branch_stat_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static void *annotated_branch_stat_start(void)
+static void *annotated_branch_stat_start(struct tracer_stat *trace)
 {
 	return __start_annotated_branch_profile;
 }
@@ -346,7 +348,7 @@ static int all_branch_stat_headers(struct seq_file *m)
 	return 0;
 }
 
-static void *all_branch_stat_start(void)
+static void *all_branch_stat_start(struct tracer_stat *trace)
 {
 	return __start_branch_profile;
 }
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
index 22cba9970776..5b5895afecfe 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_profile.c
@@ -10,22 +10,30 @@
 int ftrace_profile_enable(int event_id)
 {
 	struct ftrace_event_call *event;
+	int ret = -EINVAL;
 
-	for_each_event(event) {
-		if (event->id == event_id)
-			return event->profile_enable(event);
+	mutex_lock(&event_mutex);
+	list_for_each_entry(event, &ftrace_events, list) {
+		if (event->id == event_id) {
+			ret = event->profile_enable(event);
+			break;
+		}
 	}
+	mutex_unlock(&event_mutex);
 
-	return -EINVAL;
+	return ret;
 }
 
 void ftrace_profile_disable(int event_id)
 {
 	struct ftrace_event_call *event;
 
-	for_each_event(event) {
-		if (event->id == event_id)
-			return event->profile_disable(event);
+	mutex_lock(&event_mutex);
+	list_for_each_entry(event, &ftrace_events, list) {
+		if (event->id == event_id) {
+			event->profile_disable(event);
+			break;
+		}
 	}
+	mutex_unlock(&event_mutex);
 }
-
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
index fd78bee71dd7..5e32e375134d 100644
--- a/kernel/trace/trace_event_types.h
+++ b/kernel/trace/trace_event_types.h
@@ -57,7 +57,7 @@ TRACE_EVENT_FORMAT(context_switch, TRACE_CTX, ctx_switch_entry, ignore,
 	TP_RAW_FMT("%u:%u:%u  ==+ %u:%u:%u [%03u]")
 );
 
-TRACE_EVENT_FORMAT(special, TRACE_SPECIAL, special_entry, ignore,
+TRACE_EVENT_FORMAT_NOFILTER(special, TRACE_SPECIAL, special_entry, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned long, arg1, arg1)
 		TRACE_FIELD(unsigned long, arg2, arg2)
@@ -122,8 +122,10 @@ TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore,
 TRACE_EVENT_FORMAT(branch, TRACE_BRANCH, trace_branch, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned int, line, line)
-		TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func, func)
-		TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file, file)
+		TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func,
+				    TRACE_FUNC_SIZE+1, func)
+		TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file,
+				    TRACE_FUNC_SIZE+1, file)
 		TRACE_FIELD(char, correct, correct)
 	),
 	TP_RAW_FMT("%u:%s:%s (%u)")
@@ -139,8 +141,8 @@ TRACE_EVENT_FORMAT(hw_branch, TRACE_HW_BRANCHES, hw_branch_entry, ignore,
 
 TRACE_EVENT_FORMAT(power, TRACE_POWER, trace_power, ignore,
 	TRACE_STRUCT(
-		TRACE_FIELD(ktime_t, state_data.stamp, stamp)
-		TRACE_FIELD(ktime_t, state_data.end, end)
+		TRACE_FIELD_SIGN(ktime_t, state_data.stamp, stamp, 1)
+		TRACE_FIELD_SIGN(ktime_t, state_data.end, end, 1)
 		TRACE_FIELD(int, state_data.type, type)
 		TRACE_FIELD(int, state_data.state, state)
 	),
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 576f4fa2af0d..aa08be69a1b6 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -8,19 +8,25 @@
  *
  */
 
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/delay.h>
 
 #include "trace_output.h"
 
 #define TRACE_SYSTEM "TRACE_SYSTEM"
 
-static DEFINE_MUTEX(event_mutex);
+DEFINE_MUTEX(event_mutex);
+
+LIST_HEAD(ftrace_events);
 
 int trace_define_field(struct ftrace_event_call *call, char *type,
-		       char *name, int offset, int size)
+		       char *name, int offset, int size, int is_signed)
 {
 	struct ftrace_event_field *field;
 
@@ -38,6 +44,7 @@ int trace_define_field(struct ftrace_event_call *call, char *type,
 
 	field->offset = offset;
 	field->size = size;
+	field->is_signed = is_signed;
 	list_add(&field->link, &call->fields);
 
 	return 0;
@@ -51,47 +58,94 @@ err:
 
 	return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(trace_define_field);
 
-static void ftrace_clear_events(void)
+#ifdef CONFIG_MODULES
+
+static void trace_destroy_fields(struct ftrace_event_call *call)
 {
-	struct ftrace_event_call *call = (void *)__start_ftrace_events;
+	struct ftrace_event_field *field, *next;
 
-
-	while ((unsigned long)call < (unsigned long)__stop_ftrace_events) {
-
-		if (call->enabled) {
-			call->enabled = 0;
-			call->unregfunc();
-		}
-		call++;
+	list_for_each_entry_safe(field, next, &call->fields, link) {
+		list_del(&field->link);
+		kfree(field->type);
+		kfree(field->name);
+		kfree(field);
 	}
 }
 
+#endif /* CONFIG_MODULES */
+
 static void ftrace_event_enable_disable(struct ftrace_event_call *call,
 					int enable)
 {
-
 	switch (enable) {
 	case 0:
 		if (call->enabled) {
 			call->enabled = 0;
+			tracing_stop_cmdline_record();
 			call->unregfunc();
 		}
 		break;
 	case 1:
 		if (!call->enabled) {
 			call->enabled = 1;
+			tracing_start_cmdline_record();
 			call->regfunc();
 		}
 		break;
 	}
 }
 
+static void ftrace_clear_events(void)
+{
+	struct ftrace_event_call *call;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+		ftrace_event_enable_disable(call, 0);
+	}
+	mutex_unlock(&event_mutex);
+}
+
+/*
+ * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
+ */
+static int __ftrace_set_clr_event(const char *match, const char *sub,
+				  const char *event, int set)
+{
+	struct ftrace_event_call *call;
+	int ret = -EINVAL;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+
+		if (!call->name || !call->regfunc)
+			continue;
+
+		if (match &&
+		    strcmp(match, call->name) != 0 &&
+		    strcmp(match, call->system) != 0)
+			continue;
+
+		if (sub && strcmp(sub, call->system) != 0)
+			continue;
+
+		if (event && strcmp(event, call->name) != 0)
+			continue;
+
+		ftrace_event_enable_disable(call, set);
+
+		ret = 0;
+	}
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
 static int ftrace_set_clr_event(char *buf, int set)
 {
-	struct ftrace_event_call *call = __start_ftrace_events;
 	char *event = NULL, *sub = NULL, *match;
-	int ret = -EINVAL;
 
 	/*
 	 * The buf format can be <subsystem>:<event-name>
@@ -117,30 +171,24 @@ static int ftrace_set_clr_event(char *buf, int set)
 			event = NULL;
 	}
 
-	mutex_lock(&event_mutex);
-	for_each_event(call) {
+	return __ftrace_set_clr_event(match, sub, event, set);
+}
 
-		if (!call->name || !call->regfunc)
-			continue;
-
-		if (match &&
-		    strcmp(match, call->name) != 0 &&
-		    strcmp(match, call->system) != 0)
-			continue;
-
-		if (sub && strcmp(sub, call->system) != 0)
-			continue;
-
-		if (event && strcmp(event, call->name) != 0)
-			continue;
-
-		ftrace_event_enable_disable(call, set);
-
-		ret = 0;
-	}
-	mutex_unlock(&event_mutex);
-
-	return ret;
+/**
+ * trace_set_clr_event - enable or disable an event
+ * @system: system name to match (NULL for any system)
+ * @event: event name to match (NULL for all events, within system)
+ * @set: 1 to enable, 0 to disable
+ *
+ * This is a way for other parts of the kernel to enable or disable
+ * event recording.
+ *
+ * Returns 0 on success, -EINVAL if the parameters do not match any
+ * registered events.
+ */
+int trace_set_clr_event(const char *system, const char *event, int set)
+{
+	return __ftrace_set_clr_event(NULL, system, event, set);
 }
 
 /* 128 should be much more than enough */
@@ -224,15 +272,17 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct ftrace_event_call *call = m->private;
-	struct ftrace_event_call *next = call;
+	struct list_head *list = m->private;
+	struct ftrace_event_call *call;
 
 	(*pos)++;
 
 	for (;;) {
-		if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+		if (list == &ftrace_events)
 			return NULL;
 
+		call = list_entry(list, struct ftrace_event_call, list);
+
 		/*
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
@@ -240,45 +290,51 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		if (call->regfunc)
 			break;
 
-		call++;
-		next = call;
+		list = list->next;
 	}
 
-	m->private = ++next;
+	m->private = list->next;
 
 	return call;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
+	mutex_lock(&event_mutex);
+	if (*pos == 0)
+		m->private = ftrace_events.next;
 	return t_next(m, NULL, pos);
 }
 
 static void *
 s_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct ftrace_event_call *call = m->private;
-	struct ftrace_event_call *next;
+	struct list_head *list = m->private;
+	struct ftrace_event_call *call;
 
 	(*pos)++;
 
  retry:
-	if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+	if (list == &ftrace_events)
 		return NULL;
 
+	call = list_entry(list, struct ftrace_event_call, list);
+
 	if (!call->enabled) {
-		call++;
+		list = list->next;
 		goto retry;
 	}
 
-	next = call;
-	m->private = ++next;
+	m->private = list->next;
 
 	return call;
 }
 
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
+	mutex_lock(&event_mutex);
+	if (*pos == 0)
+		m->private = ftrace_events.next;
 	return s_next(m, NULL, pos);
 }
 
@@ -295,12 +351,12 @@ static int t_show(struct seq_file *m, void *v)
 
 static void t_stop(struct seq_file *m, void *p)
 {
+	mutex_unlock(&event_mutex);
 }
 
 static int
 ftrace_event_seq_open(struct inode *inode, struct file *file)
 {
-	int ret;
 	const struct seq_operations *seq_ops;
 
 	if ((file->f_mode & FMODE_WRITE) &&
@@ -308,13 +364,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file)
 		ftrace_clear_events();
 
 	seq_ops = inode->i_private;
-	ret = seq_open(file, seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-
-		m->private = __start_ftrace_events;
-	}
-	return ret;
+	return seq_open(file, seq_ops);
 }
 
 static ssize_t
@@ -374,8 +424,93 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	return cnt;
 }
 
+static ssize_t
+system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
+		   loff_t *ppos)
+{
+	const char set_to_char[4] = { '?', '0', '1', 'X' };
+	const char *system = filp->private_data;
+	struct ftrace_event_call *call;
+	char buf[2];
+	int set = 0;
+	int ret;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (!call->name || !call->regfunc)
+			continue;
+
+		if (system && strcmp(call->system, system) != 0)
+			continue;
+
+		/*
+		 * We need to find out if all the events are set
+		 * or if all events or cleared, or if we have
+		 * a mixture.
+		 */
+		set |= (1 << !!call->enabled);
+
+		/*
+		 * If we have a mixture, no need to look further.
+		 */
+		if (set == 3)
+			break;
+	}
+	mutex_unlock(&event_mutex);
+
+	buf[0] = set_to_char[set];
+	buf[1] = '\n';
+
+	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+
+	return ret;
+}
+
+static ssize_t
+system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		    loff_t *ppos)
+{
+	const char *system = filp->private_data;
+	unsigned long val;
+	char buf[64];
+	ssize_t ret;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	ret = tracing_update_buffers();
+	if (ret < 0)
+		return ret;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	ret = __ftrace_set_clr_event(NULL, system, NULL, val);
+	if (ret)
+		goto out;
+
+	ret = cnt;
+
+out:
+	*ppos += cnt;
+
+	return ret;
+}
+
+extern char *__bad_type_size(void);
+
 #undef FIELD
 #define FIELD(type, name)						\
+	sizeof(type) != sizeof(field.name) ? __bad_type_size() :	\
 	#type, "common_" #name, offsetof(typeof(field), name),		\
 		sizeof(field.name)
 
@@ -391,7 +526,7 @@ static int trace_write_header(struct trace_seq *s)
 				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
 				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
 				"\n",
-				FIELD(unsigned char, type),
+				FIELD(unsigned short, type),
 				FIELD(unsigned char, flags),
 				FIELD(unsigned char, preempt_count),
 				FIELD(int, pid),
@@ -481,7 +616,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	trace_seq_init(s);
 
-	filter_print_preds(call->preds, s);
+	print_event_filter(call, s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -494,38 +629,26 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		   loff_t *ppos)
 {
 	struct ftrace_event_call *call = filp->private_data;
-	char buf[64], *pbuf = buf;
-	struct filter_pred *pred;
+	char *buf;
 	int err;
 
-	if (cnt >= sizeof(buf))
+	if (cnt >= PAGE_SIZE)
 		return -EINVAL;
 
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-	buf[cnt] = '\0';
-
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
 		return -ENOMEM;
 
-	err = filter_parse(&pbuf, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
-		return err;
+	if (copy_from_user(buf, ubuf, cnt)) {
+		free_page((unsigned long) buf);
+		return -EFAULT;
 	}
+	buf[cnt] = '\0';
 
-	if (pred->clear) {
-		filter_free_preds(call);
-		filter_free_pred(pred);
-		return cnt;
-	}
-
-	err = filter_add_pred(call, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
+	err = apply_event_filter(call, buf);
+	free_page((unsigned long) buf);
+	if (err < 0)
 		return err;
-	}
 
 	*ppos += cnt;
 
@@ -549,7 +672,7 @@ subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	trace_seq_init(s);
 
-	filter_print_preds(system->preds, s);
+	print_subsystem_event_filter(system, s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -562,45 +685,56 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		       loff_t *ppos)
 {
 	struct event_subsystem *system = filp->private_data;
-	char buf[64], *pbuf = buf;
-	struct filter_pred *pred;
+	char *buf;
 	int err;
 
-	if (cnt >= sizeof(buf))
+	if (cnt >= PAGE_SIZE)
 		return -EINVAL;
 
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-	buf[cnt] = '\0';
-
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
 		return -ENOMEM;
 
-	err = filter_parse(&pbuf, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
-		return err;
+	if (copy_from_user(buf, ubuf, cnt)) {
+		free_page((unsigned long) buf);
+		return -EFAULT;
 	}
+	buf[cnt] = '\0';
 
-	if (pred->clear) {
-		filter_free_subsystem_preds(system);
-		filter_free_pred(pred);
-		return cnt;
-	}
-
-	err = filter_add_subsystem_pred(system, pred);
-	if (err < 0) {
-		filter_free_subsystem_preds(system);
-		filter_free_pred(pred);
+	err = apply_subsystem_event_filter(system, buf);
+	free_page((unsigned long) buf);
+	if (err < 0)
 		return err;
-	}
 
 	*ppos += cnt;
 
 	return cnt;
 }
 
+static ssize_t
+show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	int (*func)(struct trace_seq *s) = filp->private_data;
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	func(s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+	kfree(s);
+
+	return r;
+}
+
 static const struct seq_operations show_event_seq_ops = {
 	.start = t_start,
 	.next = t_next,
@@ -658,6 +792,17 @@ static const struct file_operations ftrace_subsystem_filter_fops = {
 	.write = subsystem_filter_write,
 };
 
+static const struct file_operations ftrace_system_enable_fops = {
+	.open = tracing_open_generic,
+	.read = system_enable_read,
+	.write = system_enable_write,
+};
+
+static const struct file_operations ftrace_show_header_fops = {
+	.open = tracing_open_generic,
+	.read = show_header,
+};
+
 static struct dentry *event_trace_events_dir(void)
 {
 	static struct dentry *d_tracer;
@@ -684,6 +829,7 @@ static struct dentry *
 event_subsystem_dir(const char *name, struct dentry *d_events)
 {
 	struct event_subsystem *system;
+	struct dentry *entry;
 
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
@@ -707,16 +853,46 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 		return d_events;
 	}
 
-	system->name = name;
+	system->name = kstrdup(name, GFP_KERNEL);
+	if (!system->name) {
+		debugfs_remove(system->entry);
+		kfree(system);
+		return d_events;
+	}
+
 	list_add(&system->list, &event_subsystems);
 
-	system->preds = NULL;
+	system->filter = NULL;
+
+	system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
+	if (!system->filter) {
+		pr_warning("Could not allocate filter for subsystem "
+			   "'%s'\n", name);
+		return system->entry;
+	}
+
+	entry = debugfs_create_file("filter", 0644, system->entry, system,
+				    &ftrace_subsystem_filter_fops);
+	if (!entry) {
+		kfree(system->filter);
+		system->filter = NULL;
+		pr_warning("Could not create debugfs "
+			   "'%s/filter' entry\n", name);
+	}
+
+	entry = trace_create_file("enable", 0644, system->entry,
+				  (void *)system->name,
+				  &ftrace_system_enable_fops);
 
 	return system->entry;
 }
 
 static int
-event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
+event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
+		 const struct file_operations *id,
+		 const struct file_operations *enable,
+		 const struct file_operations *filter,
+		 const struct file_operations *format)
 {
 	struct dentry *entry;
 	int ret;
@@ -725,7 +901,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 	 * If the trace point header did not define TRACE_SYSTEM
 	 * then the system would be called "TRACE_SYSTEM".
 	 */
-	if (strcmp(call->system, "TRACE_SYSTEM") != 0)
+	if (strcmp(call->system, TRACE_SYSTEM) != 0)
 		d_events = event_subsystem_dir(call->system, d_events);
 
 	if (call->raw_init) {
@@ -744,21 +920,13 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 		return -1;
 	}
 
-	if (call->regfunc) {
-		entry = debugfs_create_file("enable", 0644, call->dir, call,
-					    &ftrace_enable_fops);
-		if (!entry)
-			pr_warning("Could not create debugfs "
-				   "'%s/enable' entry\n", call->name);
-	}
+	if (call->regfunc)
+		entry = trace_create_file("enable", 0644, call->dir, call,
+					  enable);
 
-	if (call->id) {
-		entry = debugfs_create_file("id", 0444, call->dir, call,
-				&ftrace_event_id_fops);
-		if (!entry)
-			pr_warning("Could not create debugfs '%s/id' entry\n",
-					call->name);
-	}
+	if (call->id)
+		entry = trace_create_file("id", 0444, call->dir, call,
+					  id);
 
 	if (call->define_fields) {
 		ret = call->define_fields();
@@ -767,32 +935,195 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 				   " events/%s\n", call->name);
 			return ret;
 		}
-		entry = debugfs_create_file("filter", 0644, call->dir, call,
-					    &ftrace_event_filter_fops);
-		if (!entry)
-			pr_warning("Could not create debugfs "
-				   "'%s/filter' entry\n", call->name);
+		entry = trace_create_file("filter", 0644, call->dir, call,
+					  filter);
 	}
 
 	/* A trace may not want to export its format */
 	if (!call->show_format)
 		return 0;
 
-	entry = debugfs_create_file("format", 0444, call->dir, call,
-				    &ftrace_event_format_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'%s/format' entry\n", call->name);
+	entry = trace_create_file("format", 0444, call->dir, call,
+				  format);
 
 	return 0;
 }
 
+#define for_each_event(event, start, end)			\
+	for (event = start;					\
+	     (unsigned long)event < (unsigned long)end;		\
+	     event++)
+
+#ifdef CONFIG_MODULES
+
+static LIST_HEAD(ftrace_module_file_list);
+
+/*
+ * Modules must own their file_operations to keep up with
+ * reference counting.
+ */
+struct ftrace_module_file_ops {
+	struct list_head		list;
+	struct module			*mod;
+	struct file_operations		id;
+	struct file_operations		enable;
+	struct file_operations		format;
+	struct file_operations		filter;
+};
+
+static struct ftrace_module_file_ops *
+trace_create_file_ops(struct module *mod)
+{
+	struct ftrace_module_file_ops *file_ops;
+
+	/*
+	 * This is a bit of a PITA. To allow for correct reference
+	 * counting, modules must "own" their file_operations.
+	 * To do this, we allocate the file operations that will be
+	 * used in the event directory.
+	 */
+
+	file_ops = kmalloc(sizeof(*file_ops), GFP_KERNEL);
+	if (!file_ops)
+		return NULL;
+
+	file_ops->mod = mod;
+
+	file_ops->id = ftrace_event_id_fops;
+	file_ops->id.owner = mod;
+
+	file_ops->enable = ftrace_enable_fops;
+	file_ops->enable.owner = mod;
+
+	file_ops->filter = ftrace_event_filter_fops;
+	file_ops->filter.owner = mod;
+
+	file_ops->format = ftrace_event_format_fops;
+	file_ops->format.owner = mod;
+
+	list_add(&file_ops->list, &ftrace_module_file_list);
+
+	return file_ops;
+}
+
+static void trace_module_add_events(struct module *mod)
+{
+	struct ftrace_module_file_ops *file_ops = NULL;
+	struct ftrace_event_call *call, *start, *end;
+	struct dentry *d_events;
+
+	start = mod->trace_events;
+	end = mod->trace_events + mod->num_trace_events;
+
+	if (start == end)
+		return;
+
+	d_events = event_trace_events_dir();
+	if (!d_events)
+		return;
+
+	for_each_event(call, start, end) {
+		/* The linker may leave blanks */
+		if (!call->name)
+			continue;
+
+		/*
+		 * This module has events, create file ops for this module
+		 * if not already done.
+		 */
+		if (!file_ops) {
+			file_ops = trace_create_file_ops(mod);
+			if (!file_ops)
+				return;
+		}
+		call->mod = mod;
+		list_add(&call->list, &ftrace_events);
+		event_create_dir(call, d_events,
+				 &file_ops->id, &file_ops->enable,
+				 &file_ops->filter, &file_ops->format);
+	}
+}
+
+static void trace_module_remove_events(struct module *mod)
+{
+	struct ftrace_module_file_ops *file_ops;
+	struct ftrace_event_call *call, *p;
+	bool found = false;
+
+	down_write(&trace_event_mutex);
+	list_for_each_entry_safe(call, p, &ftrace_events, list) {
+		if (call->mod == mod) {
+			found = true;
+			ftrace_event_enable_disable(call, 0);
+			if (call->event)
+				__unregister_ftrace_event(call->event);
+			debugfs_remove_recursive(call->dir);
+			list_del(&call->list);
+			trace_destroy_fields(call);
+			destroy_preds(call);
+		}
+	}
+
+	/* Now free the file_operations */
+	list_for_each_entry(file_ops, &ftrace_module_file_list, list) {
+		if (file_ops->mod == mod)
+			break;
+	}
+	if (&file_ops->list != &ftrace_module_file_list) {
+		list_del(&file_ops->list);
+		kfree(file_ops);
+	}
+
+	/*
+	 * It is safest to reset the ring buffer if the module being unloaded
+	 * registered any events.
+	 */
+	if (found)
+		tracing_reset_current_online_cpus();
+	up_write(&trace_event_mutex);
+}
+
+static int trace_module_notify(struct notifier_block *self,
+			       unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	mutex_lock(&event_mutex);
+	switch (val) {
+	case MODULE_STATE_COMING:
+		trace_module_add_events(mod);
+		break;
+	case MODULE_STATE_GOING:
+		trace_module_remove_events(mod);
+		break;
+	}
+	mutex_unlock(&event_mutex);
+
+	return 0;
+}
+#else
+static int trace_module_notify(struct notifier_block *self,
+			       unsigned long val, void *data)
+{
+	return 0;
+}
+#endif /* CONFIG_MODULES */
+
+struct notifier_block trace_module_nb = {
+	.notifier_call = trace_module_notify,
+	.priority = 0,
+};
+
+extern struct ftrace_event_call __start_ftrace_events[];
+extern struct ftrace_event_call __stop_ftrace_events[];
+
 static __init int event_trace_init(void)
 {
-	struct ftrace_event_call *call = __start_ftrace_events;
+	struct ftrace_event_call *call;
 	struct dentry *d_tracer;
 	struct dentry *entry;
 	struct dentry *d_events;
+	int ret;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -816,13 +1147,243 @@ static __init int event_trace_init(void)
 	if (!d_events)
 		return 0;
 
-	for_each_event(call) {
+	/* ring buffer internal formats */
+	trace_create_file("header_page", 0444, d_events,
+			  ring_buffer_print_page_header,
+			  &ftrace_show_header_fops);
+
+	trace_create_file("header_event", 0444, d_events,
+			  ring_buffer_print_entry_header,
+			  &ftrace_show_header_fops);
+
+	trace_create_file("enable", 0644, d_events,
+			  NULL, &ftrace_system_enable_fops);
+
+	for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
 		/* The linker may leave blanks */
 		if (!call->name)
 			continue;
-		event_create_dir(call, d_events);
+		list_add(&call->list, &ftrace_events);
+		event_create_dir(call, d_events, &ftrace_event_id_fops,
+				 &ftrace_enable_fops, &ftrace_event_filter_fops,
+				 &ftrace_event_format_fops);
 	}
 
+	ret = register_module_notifier(&trace_module_nb);
+	if (ret)
+		pr_warning("Failed to register trace events module notifier\n");
+
 	return 0;
 }
 fs_initcall(event_trace_init);
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static DEFINE_SPINLOCK(test_spinlock);
+static DEFINE_SPINLOCK(test_spinlock_irq);
+static DEFINE_MUTEX(test_mutex);
+
+static __init void test_work(struct work_struct *dummy)
+{
+	spin_lock(&test_spinlock);
+	spin_lock_irq(&test_spinlock_irq);
+	udelay(1);
+	spin_unlock_irq(&test_spinlock_irq);
+	spin_unlock(&test_spinlock);
+
+	mutex_lock(&test_mutex);
+	msleep(1);
+	mutex_unlock(&test_mutex);
+}
+
+static __init int event_test_thread(void *unused)
+{
+	void *test_malloc;
+
+	test_malloc = kmalloc(1234, GFP_KERNEL);
+	if (!test_malloc)
+		pr_info("failed to kmalloc\n");
+
+	schedule_on_each_cpu(test_work);
+
+	kfree(test_malloc);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop())
+		schedule();
+
+	return 0;
+}
+
+/*
+ * Do various things that may trigger events.
+ */
+static __init void event_test_stuff(void)
+{
+	struct task_struct *test_thread;
+
+	test_thread = kthread_run(event_test_thread, NULL, "test-events");
+	msleep(1);
+	kthread_stop(test_thread);
+}
+
+/*
+ * For every trace event defined, we will test each trace point separately,
+ * and then by groups, and finally all trace points.
+ */
+static __init void event_trace_self_tests(void)
+{
+	struct ftrace_event_call *call;
+	struct event_subsystem *system;
+	int ret;
+
+	pr_info("Running tests on trace events:\n");
+
+	list_for_each_entry(call, &ftrace_events, list) {
+
+		/* Only test those that have a regfunc */
+		if (!call->regfunc)
+			continue;
+
+		pr_info("Testing event %s: ", call->name);
+
+		/*
+		 * If an event is already enabled, someone is using
+		 * it and the self test should not be on.
+		 */
+		if (call->enabled) {
+			pr_warning("Enabled event during self test!\n");
+			WARN_ON_ONCE(1);
+			continue;
+		}
+
+		ftrace_event_enable_disable(call, 1);
+		event_test_stuff();
+		ftrace_event_enable_disable(call, 0);
+
+		pr_cont("OK\n");
+	}
+
+	/* Now test at the sub system level */
+
+	pr_info("Running tests on trace event systems:\n");
+
+	list_for_each_entry(system, &event_subsystems, list) {
+
+		/* the ftrace system is special, skip it */
+		if (strcmp(system->name, "ftrace") == 0)
+			continue;
+
+		pr_info("Testing event system %s: ", system->name);
+
+		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 1);
+		if (WARN_ON_ONCE(ret)) {
+			pr_warning("error enabling system %s\n",
+				   system->name);
+			continue;
+		}
+
+		event_test_stuff();
+
+		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0);
+		if (WARN_ON_ONCE(ret))
+			pr_warning("error disabling system %s\n",
+				   system->name);
+
+		pr_cont("OK\n");
+	}
+
+	/* Test with all events enabled */
+
+	pr_info("Running tests on all trace events:\n");
+	pr_info("Testing all events: ");
+
+	ret = __ftrace_set_clr_event(NULL, NULL, NULL, 1);
+	if (WARN_ON_ONCE(ret)) {
+		pr_warning("error enabling all events\n");
+		return;
+	}
+
+	event_test_stuff();
+
+	/* reset sysname */
+	ret = __ftrace_set_clr_event(NULL, NULL, NULL, 0);
+	if (WARN_ON_ONCE(ret)) {
+		pr_warning("error disabling all events\n");
+		return;
+	}
+
+	pr_cont("OK\n");
+}
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+static DEFINE_PER_CPU(atomic_t, test_event_disable);
+
+static void
+function_test_events_call(unsigned long ip, unsigned long parent_ip)
+{
+	struct ring_buffer_event *event;
+	struct ftrace_entry *entry;
+	unsigned long flags;
+	long disabled;
+	int resched;
+	int cpu;
+	int pc;
+
+	pc = preempt_count();
+	resched = ftrace_preempt_disable();
+	cpu = raw_smp_processor_id();
+	disabled = atomic_inc_return(&per_cpu(test_event_disable, cpu));
+
+	if (disabled != 1)
+		goto out;
+
+	local_save_flags(flags);
+
+	event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+						  flags, pc);
+	if (!event)
+		goto out;
+	entry	= ring_buffer_event_data(event);
+	entry->ip			= ip;
+	entry->parent_ip		= parent_ip;
+
+	trace_nowake_buffer_unlock_commit(event, flags, pc);
+
+ out:
+	atomic_dec(&per_cpu(test_event_disable, cpu));
+	ftrace_preempt_enable(resched);
+}
+
+static struct ftrace_ops trace_ops __initdata  =
+{
+	.func = function_test_events_call,
+};
+
+static __init void event_trace_self_test_with_function(void)
+{
+	register_ftrace_function(&trace_ops);
+	pr_info("Running tests again, along with the function tracer\n");
+	event_trace_self_tests();
+	unregister_ftrace_function(&trace_ops);
+}
+#else
+static __init void event_trace_self_test_with_function(void)
+{
+}
+#endif
+
+static __init int event_trace_self_tests_init(void)
+{
+
+	event_trace_self_tests();
+
+	event_trace_self_test_with_function();
+
+	return 0;
+}
+
+late_initcall(event_trace_self_tests_init);
+
+#endif
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e03cbf1e38f3..db6e54bdb596 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -22,55 +22,138 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/mutex.h>
 
 #include "trace.h"
 #include "trace_output.h"
 
-static int filter_pred_64(struct filter_pred *pred, void *event)
+static DEFINE_MUTEX(filter_mutex);
+
+enum filter_op_ids
 {
-	u64 *addr = (u64 *)(event + pred->offset);
-	u64 val = (u64)pred->val;
-	int match;
+	OP_OR,
+	OP_AND,
+	OP_NE,
+	OP_EQ,
+	OP_LT,
+	OP_LE,
+	OP_GT,
+	OP_GE,
+	OP_NONE,
+	OP_OPEN_PAREN,
+};
 
-	match = (val == *addr) ^ pred->not;
+struct filter_op {
+	int id;
+	char *string;
+	int precedence;
+};
 
-	return match;
+static struct filter_op filter_ops[] = {
+	{ OP_OR, "||", 1 },
+	{ OP_AND, "&&", 2 },
+	{ OP_NE, "!=", 4 },
+	{ OP_EQ, "==", 4 },
+	{ OP_LT, "<", 5 },
+	{ OP_LE, "<=", 5 },
+	{ OP_GT, ">", 5 },
+	{ OP_GE, ">=", 5 },
+	{ OP_NONE, "OP_NONE", 0 },
+	{ OP_OPEN_PAREN, "(", 0 },
+};
+
+enum {
+	FILT_ERR_NONE,
+	FILT_ERR_INVALID_OP,
+	FILT_ERR_UNBALANCED_PAREN,
+	FILT_ERR_TOO_MANY_OPERANDS,
+	FILT_ERR_OPERAND_TOO_LONG,
+	FILT_ERR_FIELD_NOT_FOUND,
+	FILT_ERR_ILLEGAL_FIELD_OP,
+	FILT_ERR_ILLEGAL_INTVAL,
+	FILT_ERR_BAD_SUBSYS_FILTER,
+	FILT_ERR_TOO_MANY_PREDS,
+	FILT_ERR_MISSING_FIELD,
+	FILT_ERR_INVALID_FILTER,
+};
+
+static char *err_text[] = {
+	"No error",
+	"Invalid operator",
+	"Unbalanced parens",
+	"Too many operands",
+	"Operand too long",
+	"Field not found",
+	"Illegal operation for field type",
+	"Illegal integer value",
+	"Couldn't find or set field in one of a subsystem's events",
+	"Too many terms in predicate expression",
+	"Missing field name and/or value",
+	"Meaningless filter expression",
+};
+
+struct opstack_op {
+	int op;
+	struct list_head list;
+};
+
+struct postfix_elt {
+	int op;
+	char *operand;
+	struct list_head list;
+};
+
+struct filter_parse_state {
+	struct filter_op *ops;
+	struct list_head opstack;
+	struct list_head postfix;
+	int lasterr;
+	int lasterr_pos;
+
+	struct {
+		char *string;
+		unsigned int cnt;
+		unsigned int tail;
+	} infix;
+
+	struct {
+		char string[MAX_FILTER_STR_VAL];
+		int pos;
+		unsigned int tail;
+	} operand;
+};
+
+DEFINE_COMPARISON_PRED(s64);
+DEFINE_COMPARISON_PRED(u64);
+DEFINE_COMPARISON_PRED(s32);
+DEFINE_COMPARISON_PRED(u32);
+DEFINE_COMPARISON_PRED(s16);
+DEFINE_COMPARISON_PRED(u16);
+DEFINE_COMPARISON_PRED(s8);
+DEFINE_COMPARISON_PRED(u8);
+
+DEFINE_EQUALITY_PRED(64);
+DEFINE_EQUALITY_PRED(32);
+DEFINE_EQUALITY_PRED(16);
+DEFINE_EQUALITY_PRED(8);
+
+static int filter_pred_and(struct filter_pred *pred __attribute((unused)),
+			   void *event __attribute((unused)),
+			   int val1, int val2)
+{
+	return val1 && val2;
 }
 
-static int filter_pred_32(struct filter_pred *pred, void *event)
+static int filter_pred_or(struct filter_pred *pred __attribute((unused)),
+			  void *event __attribute((unused)),
+			  int val1, int val2)
 {
-	u32 *addr = (u32 *)(event + pred->offset);
-	u32 val = (u32)pred->val;
-	int match;
-
-	match = (val == *addr) ^ pred->not;
-
-	return match;
+	return val1 || val2;
 }
 
-static int filter_pred_16(struct filter_pred *pred, void *event)
-{
-	u16 *addr = (u16 *)(event + pred->offset);
-	u16 val = (u16)pred->val;
-	int match;
-
-	match = (val == *addr) ^ pred->not;
-
-	return match;
-}
-
-static int filter_pred_8(struct filter_pred *pred, void *event)
-{
-	u8 *addr = (u8 *)(event + pred->offset);
-	u8 val = (u8)pred->val;
-	int match;
-
-	match = (val == *addr) ^ pred->not;
-
-	return match;
-}
-
-static int filter_pred_string(struct filter_pred *pred, void *event)
+/* Filter predicate for fixed sized arrays of characters */
+static int filter_pred_string(struct filter_pred *pred, void *event,
+			      int val1, int val2)
 {
 	char *addr = (char *)(event + pred->offset);
 	int cmp, match;
@@ -82,59 +165,154 @@ static int filter_pred_string(struct filter_pred *pred, void *event)
 	return match;
 }
 
+/*
+ * Filter predicate for dynamic sized arrays of characters.
+ * These are implemented through a list of strings at the end
+ * of the entry.
+ * Also each of these strings have a field in the entry which
+ * contains its offset from the beginning of the entry.
+ * We have then first to get this field, dereference it
+ * and add it to the address of the entry, and at last we have
+ * the address of the string.
+ */
+static int filter_pred_strloc(struct filter_pred *pred, void *event,
+			      int val1, int val2)
+{
+	int str_loc = *(int *)(event + pred->offset);
+	char *addr = (char *)(event + str_loc);
+	int cmp, match;
+
+	cmp = strncmp(addr, pred->str_val, pred->str_len);
+
+	match = (!cmp) ^ pred->not;
+
+	return match;
+}
+
+static int filter_pred_none(struct filter_pred *pred, void *event,
+			    int val1, int val2)
+{
+	return 0;
+}
+
 /* return 1 if event matches, 0 otherwise (discard) */
 int filter_match_preds(struct ftrace_event_call *call, void *rec)
 {
-	int i, matched, and_failed = 0;
-	struct filter_pred *pred;
-
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (call->preds[i]) {
-			pred = call->preds[i];
-			if (and_failed && !pred->or)
-				continue;
-			matched = pred->fn(pred, rec);
-			if (!matched && !pred->or) {
-				and_failed = 1;
-				continue;
-			} else if (matched && pred->or)
-				return 1;
-		} else
-			break;
-	}
-
-	if (and_failed)
-		return 0;
-
-	return 1;
-}
-
-void filter_print_preds(struct filter_pred **preds, struct trace_seq *s)
-{
-	char *field_name;
+	struct event_filter *filter = call->filter;
+	int match, top = 0, val1 = 0, val2 = 0;
+	int stack[MAX_FILTER_PRED];
 	struct filter_pred *pred;
 	int i;
 
-	if (!preds) {
-		trace_seq_printf(s, "none\n");
-		return;
+	for (i = 0; i < filter->n_preds; i++) {
+		pred = filter->preds[i];
+		if (!pred->pop_n) {
+			match = pred->fn(pred, rec, val1, val2);
+			stack[top++] = match;
+			continue;
+		}
+		if (pred->pop_n > top) {
+			WARN_ON_ONCE(1);
+			return 0;
+		}
+		val1 = stack[--top];
+		val2 = stack[--top];
+		match = pred->fn(pred, rec, val1, val2);
+		stack[top++] = match;
 	}
 
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (preds[i]) {
-			pred = preds[i];
-			field_name = pred->field_name;
-			if (i)
-				trace_seq_printf(s, pred->or ? "|| " : "&& ");
-			trace_seq_printf(s, "%s ", field_name);
-			trace_seq_printf(s, pred->not ? "!= " : "== ");
-			if (pred->str_val)
-				trace_seq_printf(s, "%s\n", pred->str_val);
-			else
-				trace_seq_printf(s, "%llu\n", pred->val);
-		} else
-			break;
-	}
+	return stack[--top];
+}
+EXPORT_SYMBOL_GPL(filter_match_preds);
+
+static void parse_error(struct filter_parse_state *ps, int err, int pos)
+{
+	ps->lasterr = err;
+	ps->lasterr_pos = pos;
+}
+
+static void remove_filter_string(struct event_filter *filter)
+{
+	kfree(filter->filter_string);
+	filter->filter_string = NULL;
+}
+
+static int replace_filter_string(struct event_filter *filter,
+				 char *filter_string)
+{
+	kfree(filter->filter_string);
+	filter->filter_string = kstrdup(filter_string, GFP_KERNEL);
+	if (!filter->filter_string)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int append_filter_string(struct event_filter *filter,
+				char *string)
+{
+	int newlen;
+	char *new_filter_string;
+
+	BUG_ON(!filter->filter_string);
+	newlen = strlen(filter->filter_string) + strlen(string) + 1;
+	new_filter_string = kmalloc(newlen, GFP_KERNEL);
+	if (!new_filter_string)
+		return -ENOMEM;
+
+	strcpy(new_filter_string, filter->filter_string);
+	strcat(new_filter_string, string);
+	kfree(filter->filter_string);
+	filter->filter_string = new_filter_string;
+
+	return 0;
+}
+
+static void append_filter_err(struct filter_parse_state *ps,
+			      struct event_filter *filter)
+{
+	int pos = ps->lasterr_pos;
+	char *buf, *pbuf;
+
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
+		return;
+
+	append_filter_string(filter, "\n");
+	memset(buf, ' ', PAGE_SIZE);
+	if (pos > PAGE_SIZE - 128)
+		pos = 0;
+	buf[pos] = '^';
+	pbuf = &buf[pos] + 1;
+
+	sprintf(pbuf, "\nparse_error: %s\n", err_text[ps->lasterr]);
+	append_filter_string(filter, buf);
+	free_page((unsigned long) buf);
+}
+
+void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
+{
+	struct event_filter *filter = call->filter;
+
+	mutex_lock(&filter_mutex);
+	if (filter->filter_string)
+		trace_seq_printf(s, "%s\n", filter->filter_string);
+	else
+		trace_seq_printf(s, "none\n");
+	mutex_unlock(&filter_mutex);
+}
+
+void print_subsystem_event_filter(struct event_subsystem *system,
+				  struct trace_seq *s)
+{
+	struct event_filter *filter = system->filter;
+
+	mutex_lock(&filter_mutex);
+	if (filter->filter_string)
+		trace_seq_printf(s, "%s\n", filter->filter_string);
+	else
+		trace_seq_printf(s, "none\n");
+	mutex_unlock(&filter_mutex);
 }
 
 static struct ftrace_event_field *
@@ -150,284 +328,828 @@ find_event_field(struct ftrace_event_call *call, char *name)
 	return NULL;
 }
 
-void filter_free_pred(struct filter_pred *pred)
+static void filter_free_pred(struct filter_pred *pred)
 {
 	if (!pred)
 		return;
 
 	kfree(pred->field_name);
-	kfree(pred->str_val);
 	kfree(pred);
 }
 
-void filter_free_preds(struct ftrace_event_call *call)
+static void filter_clear_pred(struct filter_pred *pred)
 {
-	int i;
-
-	if (call->preds) {
-		for (i = 0; i < MAX_FILTER_PRED; i++)
-			filter_free_pred(call->preds[i]);
-		kfree(call->preds);
-		call->preds = NULL;
-	}
+	kfree(pred->field_name);
+	pred->field_name = NULL;
+	pred->str_len = 0;
 }
 
-void filter_free_subsystem_preds(struct event_subsystem *system)
+static int filter_set_pred(struct filter_pred *dest,
+			   struct filter_pred *src,
+			   filter_pred_fn_t fn)
 {
-	struct ftrace_event_call *call = __start_ftrace_events;
-	int i;
-
-	if (system->preds) {
-		for (i = 0; i < MAX_FILTER_PRED; i++)
-			filter_free_pred(system->preds[i]);
-		kfree(system->preds);
-		system->preds = NULL;
-	}
-
-	events_for_each(call) {
-		if (!call->name || !call->regfunc)
-			continue;
-
-		if (!strcmp(call->system, system->name))
-			filter_free_preds(call);
-	}
-}
-
-static int __filter_add_pred(struct ftrace_event_call *call,
-			     struct filter_pred *pred)
-{
-	int i;
-
-	if (call->preds && !pred->compound)
-		filter_free_preds(call);
-
-	if (!call->preds) {
-		call->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
-				      GFP_KERNEL);
-		if (!call->preds)
+	*dest = *src;
+	if (src->field_name) {
+		dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
+		if (!dest->field_name)
 			return -ENOMEM;
 	}
-
-	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (!call->preds[i]) {
-			call->preds[i] = pred;
-			return 0;
-		}
-	}
-
-	return -ENOSPC;
-}
-
-static int is_string_field(const char *type)
-{
-	if (strchr(type, '[') && strstr(type, "char"))
-		return 1;
+	dest->fn = fn;
 
 	return 0;
 }
 
-int filter_add_pred(struct ftrace_event_call *call, struct filter_pred *pred)
+static void filter_disable_preds(struct ftrace_event_call *call)
 {
-	struct ftrace_event_field *field;
-
-	field = find_event_field(call, pred->field_name);
-	if (!field)
-		return -EINVAL;
-
-	pred->offset = field->offset;
-
-	if (is_string_field(field->type)) {
-		if (!pred->str_val)
-			return -EINVAL;
-		pred->fn = filter_pred_string;
-		pred->str_len = field->size;
-		return __filter_add_pred(call, pred);
-	} else {
-		if (pred->str_val)
-			return -EINVAL;
-	}
-
-	switch (field->size) {
-	case 8:
-		pred->fn = filter_pred_64;
-		break;
-	case 4:
-		pred->fn = filter_pred_32;
-		break;
-	case 2:
-		pred->fn = filter_pred_16;
-		break;
-	case 1:
-		pred->fn = filter_pred_8;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return __filter_add_pred(call, pred);
-}
-
-static struct filter_pred *copy_pred(struct filter_pred *pred)
-{
-	struct filter_pred *new_pred = kmalloc(sizeof(*pred), GFP_KERNEL);
-	if (!new_pred)
-		return NULL;
-
-	memcpy(new_pred, pred, sizeof(*pred));
-
-	if (pred->field_name) {
-		new_pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
-		if (!new_pred->field_name) {
-			kfree(new_pred);
-			return NULL;
-		}
-	}
-
-	if (pred->str_val) {
-		new_pred->str_val = kstrdup(pred->str_val, GFP_KERNEL);
-		if (!new_pred->str_val) {
-			filter_free_pred(new_pred);
-			return NULL;
-		}
-	}
-
-	return new_pred;
-}
-
-int filter_add_subsystem_pred(struct event_subsystem *system,
-			      struct filter_pred *pred)
-{
-	struct ftrace_event_call *call = __start_ftrace_events;
-	struct filter_pred *event_pred;
+	struct event_filter *filter = call->filter;
 	int i;
 
-	if (system->preds && !pred->compound)
-		filter_free_subsystem_preds(system);
+	call->filter_active = 0;
+	filter->n_preds = 0;
 
-	if (!system->preds) {
-		system->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
-					GFP_KERNEL);
-		if (!system->preds)
-			return -ENOMEM;
-	}
+	for (i = 0; i < MAX_FILTER_PRED; i++)
+		filter->preds[i]->fn = filter_pred_none;
+}
+
+void destroy_preds(struct ftrace_event_call *call)
+{
+	struct event_filter *filter = call->filter;
+	int i;
 
 	for (i = 0; i < MAX_FILTER_PRED; i++) {
-		if (!system->preds[i]) {
-			system->preds[i] = pred;
-			break;
-		}
+		if (filter->preds[i])
+			filter_free_pred(filter->preds[i]);
 	}
+	kfree(filter->preds);
+	kfree(filter);
+	call->filter = NULL;
+}
 
-	if (i == MAX_FILTER_PRED)
-		return -ENOSPC;
+int init_preds(struct ftrace_event_call *call)
+{
+	struct event_filter *filter;
+	struct filter_pred *pred;
+	int i;
 
-	events_for_each(call) {
-		int err;
+	filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	if (!call->filter)
+		return -ENOMEM;
 
-		if (!call->name || !call->regfunc)
-			continue;
+	call->filter_active = 0;
+	filter->n_preds = 0;
 
-		if (strcmp(call->system, system->name))
-			continue;
+	filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
+	if (!filter->preds)
+		goto oom;
 
-		if (!find_event_field(call, pred->field_name))
-			continue;
-
-		event_pred = copy_pred(pred);
-		if (!event_pred)
-			goto oom;
-
-		err = filter_add_pred(call, event_pred);
-		if (err)
-			filter_free_pred(event_pred);
-		if (err == -ENOMEM)
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+		if (!pred)
 			goto oom;
+		pred->fn = filter_pred_none;
+		filter->preds[i] = pred;
 	}
 
 	return 0;
 
 oom:
-	system->preds[i] = NULL;
+	destroy_preds(call);
+
 	return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(init_preds);
 
-int filter_parse(char **pbuf, struct filter_pred *pred)
+static void filter_free_subsystem_preds(struct event_subsystem *system)
 {
-	char *tmp, *tok, *val_str = NULL;
-	int tok_n = 0;
+	struct event_filter *filter = system->filter;
+	struct ftrace_event_call *call;
+	int i;
 
-	/* field ==/!= number, or/and field ==/!= number, number */
-	while ((tok = strsep(pbuf, " \n"))) {
-		if (tok_n == 0) {
-			if (!strcmp(tok, "0")) {
-				pred->clear = 1;
-				return 0;
-			} else if (!strcmp(tok, "&&")) {
-				pred->or = 0;
-				pred->compound = 1;
-			} else if (!strcmp(tok, "||")) {
-				pred->or = 1;
-				pred->compound = 1;
-			} else
-				pred->field_name = tok;
-			tok_n = 1;
-			continue;
-		}
-		if (tok_n == 1) {
-			if (!pred->field_name)
-				pred->field_name = tok;
-			else if (!strcmp(tok, "!="))
-				pred->not = 1;
-			else if (!strcmp(tok, "=="))
-				pred->not = 0;
-			else {
-				pred->field_name = NULL;
-				return -EINVAL;
-			}
-			tok_n = 2;
-			continue;
-		}
-		if (tok_n == 2) {
-			if (pred->compound) {
-				if (!strcmp(tok, "!="))
-					pred->not = 1;
-				else if (!strcmp(tok, "=="))
-					pred->not = 0;
-				else {
-					pred->field_name = NULL;
-					return -EINVAL;
-				}
-			} else {
-				val_str = tok;
-				break; /* done */
-			}
-			tok_n = 3;
-			continue;
-		}
-		if (tok_n == 3) {
-			val_str = tok;
-			break; /* done */
-		}
+	if (filter->n_preds) {
+		for (i = 0; i < filter->n_preds; i++)
+			filter_free_pred(filter->preds[i]);
+		kfree(filter->preds);
+		filter->preds = NULL;
+		filter->n_preds = 0;
 	}
 
-	if (!val_str) {
-		pred->field_name = NULL;
-		return -EINVAL;
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (!call->define_fields)
+			continue;
+
+		if (!strcmp(call->system, system->name)) {
+			filter_disable_preds(call);
+			remove_filter_string(call->filter);
+		}
+	}
+	mutex_unlock(&event_mutex);
+}
+
+static int filter_add_pred_fn(struct filter_parse_state *ps,
+			      struct ftrace_event_call *call,
+			      struct filter_pred *pred,
+			      filter_pred_fn_t fn)
+{
+	struct event_filter *filter = call->filter;
+	int idx, err;
+
+	if (filter->n_preds == MAX_FILTER_PRED) {
+		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+		return -ENOSPC;
 	}
 
-	pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
-	if (!pred->field_name)
-		return -ENOMEM;
+	idx = filter->n_preds;
+	filter_clear_pred(filter->preds[idx]);
+	err = filter_set_pred(filter->preds[idx], pred, fn);
+	if (err)
+		return err;
 
-	pred->val = simple_strtoull(val_str, &tmp, 0);
-	if (tmp == val_str) {
-		pred->str_val = kstrdup(val_str, GFP_KERNEL);
-		if (!pred->str_val)
-			return -ENOMEM;
-	} else if (*tmp != '\0')
-		return -EINVAL;
+	filter->n_preds++;
+	call->filter_active = 1;
 
 	return 0;
 }
 
+enum {
+	FILTER_STATIC_STRING = 1,
+	FILTER_DYN_STRING
+};
+
+static int is_string_field(const char *type)
+{
+	if (strstr(type, "__data_loc") && strstr(type, "char"))
+		return FILTER_DYN_STRING;
+
+	if (strchr(type, '[') && strstr(type, "char"))
+		return FILTER_STATIC_STRING;
+
+	return 0;
+}
+
+static int is_legal_op(struct ftrace_event_field *field, int op)
+{
+	if (is_string_field(field->type) && (op != OP_EQ && op != OP_NE))
+		return 0;
+
+	return 1;
+}
+
+static filter_pred_fn_t select_comparison_fn(int op, int field_size,
+					     int field_is_signed)
+{
+	filter_pred_fn_t fn = NULL;
+
+	switch (field_size) {
+	case 8:
+		if (op == OP_EQ || op == OP_NE)
+			fn = filter_pred_64;
+		else if (field_is_signed)
+			fn = filter_pred_s64;
+		else
+			fn = filter_pred_u64;
+		break;
+	case 4:
+		if (op == OP_EQ || op == OP_NE)
+			fn = filter_pred_32;
+		else if (field_is_signed)
+			fn = filter_pred_s32;
+		else
+			fn = filter_pred_u32;
+		break;
+	case 2:
+		if (op == OP_EQ || op == OP_NE)
+			fn = filter_pred_16;
+		else if (field_is_signed)
+			fn = filter_pred_s16;
+		else
+			fn = filter_pred_u16;
+		break;
+	case 1:
+		if (op == OP_EQ || op == OP_NE)
+			fn = filter_pred_8;
+		else if (field_is_signed)
+			fn = filter_pred_s8;
+		else
+			fn = filter_pred_u8;
+		break;
+	}
+
+	return fn;
+}
+
+static int filter_add_pred(struct filter_parse_state *ps,
+			   struct ftrace_event_call *call,
+			   struct filter_pred *pred)
+{
+	struct ftrace_event_field *field;
+	filter_pred_fn_t fn;
+	unsigned long long val;
+	int string_type;
+
+	pred->fn = filter_pred_none;
+
+	if (pred->op == OP_AND) {
+		pred->pop_n = 2;
+		return filter_add_pred_fn(ps, call, pred, filter_pred_and);
+	} else if (pred->op == OP_OR) {
+		pred->pop_n = 2;
+		return filter_add_pred_fn(ps, call, pred, filter_pred_or);
+	}
+
+	field = find_event_field(call, pred->field_name);
+	if (!field) {
+		parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
+		return -EINVAL;
+	}
+
+	pred->offset = field->offset;
+
+	if (!is_legal_op(field, pred->op)) {
+		parse_error(ps, FILT_ERR_ILLEGAL_FIELD_OP, 0);
+		return -EINVAL;
+	}
+
+	string_type = is_string_field(field->type);
+	if (string_type) {
+		if (string_type == FILTER_STATIC_STRING)
+			fn = filter_pred_string;
+		else
+			fn = filter_pred_strloc;
+		pred->str_len = field->size;
+		if (pred->op == OP_NE)
+			pred->not = 1;
+		return filter_add_pred_fn(ps, call, pred, fn);
+	} else {
+		if (strict_strtoull(pred->str_val, 0, &val)) {
+			parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
+			return -EINVAL;
+		}
+		pred->val = val;
+	}
+
+	fn = select_comparison_fn(pred->op, field->size, field->is_signed);
+	if (!fn) {
+		parse_error(ps, FILT_ERR_INVALID_OP, 0);
+		return -EINVAL;
+	}
+
+	if (pred->op == OP_NE)
+		pred->not = 1;
+
+	return filter_add_pred_fn(ps, call, pred, fn);
+}
+
+static int filter_add_subsystem_pred(struct filter_parse_state *ps,
+				     struct event_subsystem *system,
+				     struct filter_pred *pred,
+				     char *filter_string)
+{
+	struct event_filter *filter = system->filter;
+	struct ftrace_event_call *call;
+	int err = 0;
+
+	if (!filter->preds) {
+		filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+					GFP_KERNEL);
+
+		if (!filter->preds)
+			return -ENOMEM;
+	}
+
+	if (filter->n_preds == MAX_FILTER_PRED) {
+		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+		return -ENOSPC;
+	}
+
+	filter->preds[filter->n_preds] = pred;
+	filter->n_preds++;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+
+		if (!call->define_fields)
+			continue;
+
+		if (strcmp(call->system, system->name))
+			continue;
+
+		err = filter_add_pred(ps, call, pred);
+		if (err) {
+			mutex_unlock(&event_mutex);
+			filter_free_subsystem_preds(system);
+			parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+			goto out;
+		}
+		replace_filter_string(call->filter, filter_string);
+	}
+	mutex_unlock(&event_mutex);
+out:
+	return err;
+}
+
+static void parse_init(struct filter_parse_state *ps,
+		       struct filter_op *ops,
+		       char *infix_string)
+{
+	memset(ps, '\0', sizeof(*ps));
+
+	ps->infix.string = infix_string;
+	ps->infix.cnt = strlen(infix_string);
+	ps->ops = ops;
+
+	INIT_LIST_HEAD(&ps->opstack);
+	INIT_LIST_HEAD(&ps->postfix);
+}
+
+static char infix_next(struct filter_parse_state *ps)
+{
+	ps->infix.cnt--;
+
+	return ps->infix.string[ps->infix.tail++];
+}
+
+static char infix_peek(struct filter_parse_state *ps)
+{
+	if (ps->infix.tail == strlen(ps->infix.string))
+		return 0;
+
+	return ps->infix.string[ps->infix.tail];
+}
+
+static void infix_advance(struct filter_parse_state *ps)
+{
+	ps->infix.cnt--;
+	ps->infix.tail++;
+}
+
+static inline int is_precedence_lower(struct filter_parse_state *ps,
+				      int a, int b)
+{
+	return ps->ops[a].precedence < ps->ops[b].precedence;
+}
+
+static inline int is_op_char(struct filter_parse_state *ps, char c)
+{
+	int i;
+
+	for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+		if (ps->ops[i].string[0] == c)
+			return 1;
+	}
+
+	return 0;
+}
+
+static int infix_get_op(struct filter_parse_state *ps, char firstc)
+{
+	char nextc = infix_peek(ps);
+	char opstr[3];
+	int i;
+
+	opstr[0] = firstc;
+	opstr[1] = nextc;
+	opstr[2] = '\0';
+
+	for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+		if (!strcmp(opstr, ps->ops[i].string)) {
+			infix_advance(ps);
+			return ps->ops[i].id;
+		}
+	}
+
+	opstr[1] = '\0';
+
+	for (i = 0; strcmp(ps->ops[i].string, "OP_NONE"); i++) {
+		if (!strcmp(opstr, ps->ops[i].string))
+			return ps->ops[i].id;
+	}
+
+	return OP_NONE;
+}
+
+static inline void clear_operand_string(struct filter_parse_state *ps)
+{
+	memset(ps->operand.string, '\0', MAX_FILTER_STR_VAL);
+	ps->operand.tail = 0;
+}
+
+static inline int append_operand_char(struct filter_parse_state *ps, char c)
+{
+	if (ps->operand.tail == MAX_FILTER_STR_VAL - 1)
+		return -EINVAL;
+
+	ps->operand.string[ps->operand.tail++] = c;
+
+	return 0;
+}
+
+static int filter_opstack_push(struct filter_parse_state *ps, int op)
+{
+	struct opstack_op *opstack_op;
+
+	opstack_op = kmalloc(sizeof(*opstack_op), GFP_KERNEL);
+	if (!opstack_op)
+		return -ENOMEM;
+
+	opstack_op->op = op;
+	list_add(&opstack_op->list, &ps->opstack);
+
+	return 0;
+}
+
+static int filter_opstack_empty(struct filter_parse_state *ps)
+{
+	return list_empty(&ps->opstack);
+}
+
+static int filter_opstack_top(struct filter_parse_state *ps)
+{
+	struct opstack_op *opstack_op;
+
+	if (filter_opstack_empty(ps))
+		return OP_NONE;
+
+	opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+
+	return opstack_op->op;
+}
+
+static int filter_opstack_pop(struct filter_parse_state *ps)
+{
+	struct opstack_op *opstack_op;
+	int op;
+
+	if (filter_opstack_empty(ps))
+		return OP_NONE;
+
+	opstack_op = list_first_entry(&ps->opstack, struct opstack_op, list);
+	op = opstack_op->op;
+	list_del(&opstack_op->list);
+
+	kfree(opstack_op);
+
+	return op;
+}
+
+static void filter_opstack_clear(struct filter_parse_state *ps)
+{
+	while (!filter_opstack_empty(ps))
+		filter_opstack_pop(ps);
+}
+
+static char *curr_operand(struct filter_parse_state *ps)
+{
+	return ps->operand.string;
+}
+
+static int postfix_append_operand(struct filter_parse_state *ps, char *operand)
+{
+	struct postfix_elt *elt;
+
+	elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+	if (!elt)
+		return -ENOMEM;
+
+	elt->op = OP_NONE;
+	elt->operand = kstrdup(operand, GFP_KERNEL);
+	if (!elt->operand) {
+		kfree(elt);
+		return -ENOMEM;
+	}
+
+	list_add_tail(&elt->list, &ps->postfix);
+
+	return 0;
+}
+
+static int postfix_append_op(struct filter_parse_state *ps, int op)
+{
+	struct postfix_elt *elt;
+
+	elt = kmalloc(sizeof(*elt), GFP_KERNEL);
+	if (!elt)
+		return -ENOMEM;
+
+	elt->op = op;
+	elt->operand = NULL;
+
+	list_add_tail(&elt->list, &ps->postfix);
+
+	return 0;
+}
+
+static void postfix_clear(struct filter_parse_state *ps)
+{
+	struct postfix_elt *elt;
+
+	while (!list_empty(&ps->postfix)) {
+		elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
+		kfree(elt->operand);
+		list_del(&elt->list);
+	}
+}
+
+static int filter_parse(struct filter_parse_state *ps)
+{
+	int in_string = 0;
+	int op, top_op;
+	char ch;
+
+	while ((ch = infix_next(ps))) {
+		if (ch == '"') {
+			in_string ^= 1;
+			continue;
+		}
+
+		if (in_string)
+			goto parse_operand;
+
+		if (isspace(ch))
+			continue;
+
+		if (is_op_char(ps, ch)) {
+			op = infix_get_op(ps, ch);
+			if (op == OP_NONE) {
+				parse_error(ps, FILT_ERR_INVALID_OP, 0);
+				return -EINVAL;
+			}
+
+			if (strlen(curr_operand(ps))) {
+				postfix_append_operand(ps, curr_operand(ps));
+				clear_operand_string(ps);
+			}
+
+			while (!filter_opstack_empty(ps)) {
+				top_op = filter_opstack_top(ps);
+				if (!is_precedence_lower(ps, top_op, op)) {
+					top_op = filter_opstack_pop(ps);
+					postfix_append_op(ps, top_op);
+					continue;
+				}
+				break;
+			}
+
+			filter_opstack_push(ps, op);
+			continue;
+		}
+
+		if (ch == '(') {
+			filter_opstack_push(ps, OP_OPEN_PAREN);
+			continue;
+		}
+
+		if (ch == ')') {
+			if (strlen(curr_operand(ps))) {
+				postfix_append_operand(ps, curr_operand(ps));
+				clear_operand_string(ps);
+			}
+
+			top_op = filter_opstack_pop(ps);
+			while (top_op != OP_NONE) {
+				if (top_op == OP_OPEN_PAREN)
+					break;
+				postfix_append_op(ps, top_op);
+				top_op = filter_opstack_pop(ps);
+			}
+			if (top_op == OP_NONE) {
+				parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+				return -EINVAL;
+			}
+			continue;
+		}
+parse_operand:
+		if (append_operand_char(ps, ch)) {
+			parse_error(ps, FILT_ERR_OPERAND_TOO_LONG, 0);
+			return -EINVAL;
+		}
+	}
+
+	if (strlen(curr_operand(ps)))
+		postfix_append_operand(ps, curr_operand(ps));
+
+	while (!filter_opstack_empty(ps)) {
+		top_op = filter_opstack_pop(ps);
+		if (top_op == OP_NONE)
+			break;
+		if (top_op == OP_OPEN_PAREN) {
+			parse_error(ps, FILT_ERR_UNBALANCED_PAREN, 0);
+			return -EINVAL;
+		}
+		postfix_append_op(ps, top_op);
+	}
+
+	return 0;
+}
+
+static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
+{
+	struct filter_pred *pred;
+
+	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+	if (!pred)
+		return NULL;
+
+	pred->field_name = kstrdup(operand1, GFP_KERNEL);
+	if (!pred->field_name) {
+		kfree(pred);
+		return NULL;
+	}
+
+	strcpy(pred->str_val, operand2);
+	pred->str_len = strlen(operand2);
+
+	pred->op = op;
+
+	return pred;
+}
+
+static struct filter_pred *create_logical_pred(int op)
+{
+	struct filter_pred *pred;
+
+	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+	if (!pred)
+		return NULL;
+
+	pred->op = op;
+
+	return pred;
+}
+
+static int check_preds(struct filter_parse_state *ps)
+{
+	int n_normal_preds = 0, n_logical_preds = 0;
+	struct postfix_elt *elt;
+
+	list_for_each_entry(elt, &ps->postfix, list) {
+		if (elt->op == OP_NONE)
+			continue;
+
+		if (elt->op == OP_AND || elt->op == OP_OR) {
+			n_logical_preds++;
+			continue;
+		}
+		n_normal_preds++;
+	}
+
+	if (!n_normal_preds || n_logical_preds >= n_normal_preds) {
+		parse_error(ps, FILT_ERR_INVALID_FILTER, 0);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int replace_preds(struct event_subsystem *system,
+			 struct ftrace_event_call *call,
+			 struct filter_parse_state *ps,
+			 char *filter_string)
+{
+	char *operand1 = NULL, *operand2 = NULL;
+	struct filter_pred *pred;
+	struct postfix_elt *elt;
+	int err;
+
+	err = check_preds(ps);
+	if (err)
+		return err;
+
+	list_for_each_entry(elt, &ps->postfix, list) {
+		if (elt->op == OP_NONE) {
+			if (!operand1)
+				operand1 = elt->operand;
+			else if (!operand2)
+				operand2 = elt->operand;
+			else {
+				parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0);
+				return -EINVAL;
+			}
+			continue;
+		}
+
+		if (elt->op == OP_AND || elt->op == OP_OR) {
+			pred = create_logical_pred(elt->op);
+			if (call) {
+				err = filter_add_pred(ps, call, pred);
+				filter_free_pred(pred);
+			} else
+				err = filter_add_subsystem_pred(ps, system,
+							pred, filter_string);
+			if (err)
+				return err;
+
+			operand1 = operand2 = NULL;
+			continue;
+		}
+
+		if (!operand1 || !operand2) {
+			parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
+			return -EINVAL;
+		}
+
+		pred = create_pred(elt->op, operand1, operand2);
+		if (call) {
+			err = filter_add_pred(ps, call, pred);
+			filter_free_pred(pred);
+		} else
+			err = filter_add_subsystem_pred(ps, system, pred,
+							filter_string);
+		if (err)
+			return err;
+
+		operand1 = operand2 = NULL;
+	}
+
+	return 0;
+}
+
+int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+{
+	int err;
+
+	struct filter_parse_state *ps;
+
+	mutex_lock(&filter_mutex);
+
+	if (!strcmp(strstrip(filter_string), "0")) {
+		filter_disable_preds(call);
+		remove_filter_string(call->filter);
+		mutex_unlock(&filter_mutex);
+		return 0;
+	}
+
+	err = -ENOMEM;
+	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+	if (!ps)
+		goto out_unlock;
+
+	filter_disable_preds(call);
+	replace_filter_string(call->filter, filter_string);
+
+	parse_init(ps, filter_ops, filter_string);
+	err = filter_parse(ps);
+	if (err) {
+		append_filter_err(ps, call->filter);
+		goto out;
+	}
+
+	err = replace_preds(NULL, call, ps, filter_string);
+	if (err)
+		append_filter_err(ps, call->filter);
+
+out:
+	filter_opstack_clear(ps);
+	postfix_clear(ps);
+	kfree(ps);
+out_unlock:
+	mutex_unlock(&filter_mutex);
+
+	return err;
+}
+
+int apply_subsystem_event_filter(struct event_subsystem *system,
+				 char *filter_string)
+{
+	int err;
+
+	struct filter_parse_state *ps;
+
+	mutex_lock(&filter_mutex);
+
+	if (!strcmp(strstrip(filter_string), "0")) {
+		filter_free_subsystem_preds(system);
+		remove_filter_string(system->filter);
+		mutex_unlock(&filter_mutex);
+		return 0;
+	}
+
+	err = -ENOMEM;
+	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+	if (!ps)
+		goto out_unlock;
+
+	filter_free_subsystem_preds(system);
+	replace_filter_string(system->filter, filter_string);
+
+	parse_init(ps, filter_ops, filter_string);
+	err = filter_parse(ps);
+	if (err) {
+		append_filter_err(ps, system->filter);
+		goto out;
+	}
+
+	err = replace_preds(system, NULL, ps, filter_string);
+	if (err)
+		append_filter_err(ps, system->filter);
+
+out:
+	filter_opstack_clear(ps);
+	postfix_clear(ps);
+	kfree(ps);
+out_unlock:
+	mutex_unlock(&filter_mutex);
+
+	return err;
+}
 
diff --git a/kernel/trace/trace_events_stage_1.h b/kernel/trace/trace_events_stage_1.h
deleted file mode 100644
index 38985f9b379c..000000000000
--- a/kernel/trace/trace_events_stage_1.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Stage 1 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * struct ftrace_raw_<call> {
- *	struct trace_entry		ent;
- *	<type>				<item>;
- *	<type2>				<item2>[<len>];
- *	[...]
- * };
- *
- * The <type> <item> is created by the __field(type, item) macro or
- * the __array(type2, item2, len) macro.
- * We simply do "type item;", and that will create the fields
- * in the structure.
- */
-
-#undef TRACE_FORMAT
-#define TRACE_FORMAT(call, proto, args, fmt)
-
-#undef __array
-#define __array(type, item, len)	type	item[len];
-
-#undef __field
-#define __field(type, item)		type	item;
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
-	struct ftrace_raw_##name {				\
-		struct trace_entry	ent;			\
-		tstruct						\
-	};							\
-	static struct ftrace_event_call event_##name
-
-#include <trace/trace_event_types.h>
diff --git a/kernel/trace/trace_events_stage_2.h b/kernel/trace/trace_events_stage_2.h
deleted file mode 100644
index d363c6672c6c..000000000000
--- a/kernel/trace/trace_events_stage_2.h
+++ /dev/null
@@ -1,176 +0,0 @@
-/*
- * Stage 2 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * enum print_line_t
- * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
- * {
- *	struct trace_seq *s = &iter->seq;
- *	struct ftrace_raw_<call> *field; <-- defined in stage 1
- *	struct trace_entry *entry;
- *	int ret;
- *
- *	entry = iter->ent;
- *
- *	if (entry->type != event_<call>.id) {
- *		WARN_ON_ONCE(1);
- *		return TRACE_TYPE_UNHANDLED;
- *	}
- *
- *	field = (typeof(field))entry;
- *
- *	ret = trace_seq_printf(s, <TP_printk> "\n");
- *	if (!ret)
- *		return TRACE_TYPE_PARTIAL_LINE;
- *
- *	return TRACE_TYPE_HANDLED;
- * }
- *
- * This is the method used to print the raw event to the trace
- * output format. Note, this is not needed if the data is read
- * in binary.
- */
-
-#undef __entry
-#define __entry field
-
-#undef TP_printk
-#define TP_printk(fmt, args...) fmt "\n", args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
-enum print_line_t							\
-ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
-{									\
-	struct trace_seq *s = &iter->seq;				\
-	struct ftrace_raw_##call *field;				\
-	struct trace_entry *entry;					\
-	int ret;							\
-									\
-	entry = iter->ent;						\
-									\
-	if (entry->type != event_##call.id) {				\
-		WARN_ON_ONCE(1);					\
-		return TRACE_TYPE_UNHANDLED;				\
-	}								\
-									\
-	field = (typeof(field))entry;					\
-									\
-	ret = trace_seq_printf(s, #call ": " print);			\
-	if (!ret)							\
-		return TRACE_TYPE_PARTIAL_LINE;				\
-									\
-	return TRACE_TYPE_HANDLED;					\
-}
-	
-#include <trace/trace_event_types.h>
-
-/*
- * Setup the showing format of trace point.
- *
- * int
- * ftrace_format_##call(struct trace_seq *s)
- * {
- *	struct ftrace_raw_##call field;
- *	int ret;
- *
- *	ret = trace_seq_printf(s, #type " " #item ";"
- *			       " offset:%u; size:%u;\n",
- *			       offsetof(struct ftrace_raw_##call, item),
- *			       sizeof(field.type));
- *
- * }
- */
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
-
-#undef __field
-#define __field(type, item)					\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%u;\tsize:%u;\n",		\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item));	\
-	if (!ret)							\
-		return 0;
-
-#undef __array
-#define __array(type, item, len)						\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"	\
-			       "offset:%u;\tsize:%u;\n",		\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item));	\
-	if (!ret)							\
-		return 0;
-
-#undef __entry
-#define __entry REC
-
-#undef TP_printk
-#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
-
-#undef TP_fast_assign
-#define TP_fast_assign(args...) args
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
-static int								\
-ftrace_format_##call(struct trace_seq *s)				\
-{									\
-	struct ftrace_raw_##call field;					\
-	int ret;							\
-									\
-	tstruct;							\
-									\
-	trace_seq_printf(s, "\nprint fmt: " print);			\
-									\
-	return ret;							\
-}
-
-#include <trace/trace_event_types.h>
-
-#undef __field
-#define __field(type, item)						\
-	ret = trace_define_field(event_call, #type, #item,		\
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item));			\
-	if (ret)							\
-		return ret;
-
-#undef __array
-#define __array(type, item, len)					\
-	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item));			\
-	if (ret)							\
-		return ret;
-
-#define __common_field(type, item)					\
-	ret = trace_define_field(event_call, #type, "common_" #item,	\
-				 offsetof(typeof(field.ent), item),	\
-				 sizeof(field.ent.item));		\
-	if (ret)							\
-		return ret;
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
-int									\
-ftrace_define_fields_##call(void)					\
-{									\
-	struct ftrace_raw_##call field;					\
-	struct ftrace_event_call *event_call = &event_##call;		\
-	int ret;							\
-									\
-	__common_field(unsigned char, type);				\
-	__common_field(unsigned char, flags);				\
-	__common_field(unsigned char, preempt_count);			\
-	__common_field(int, pid);					\
-	__common_field(int, tgid);					\
-									\
-	tstruct;							\
-									\
-	return ret;							\
-}
-
-#include <trace/trace_event_types.h>
diff --git a/kernel/trace/trace_events_stage_3.h b/kernel/trace/trace_events_stage_3.h
deleted file mode 100644
index 9d2fa78cecca..000000000000
--- a/kernel/trace/trace_events_stage_3.h
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * Stage 3 of the trace events.
- *
- * Override the macros in <trace/trace_event_types.h> to include the following:
- *
- * static void ftrace_event_<call>(proto)
- * {
- *	event_trace_printk(_RET_IP_, "<call>: " <fmt>);
- * }
- *
- * static int ftrace_reg_event_<call>(void)
- * {
- *	int ret;
- *
- *	ret = register_trace_<call>(ftrace_event_<call>);
- *	if (!ret)
- *		pr_info("event trace: Could not activate trace point "
- *			"probe to  <call>");
- *	return ret;
- * }
- *
- * static void ftrace_unreg_event_<call>(void)
- * {
- *	unregister_trace_<call>(ftrace_event_<call>);
- * }
- *
- * For those macros defined with TRACE_FORMAT:
- *
- * static struct ftrace_event_call __used
- * __attribute__((__aligned__(4)))
- * __attribute__((section("_ftrace_events"))) event_<call> = {
- *	.name			= "<call>",
- *	.regfunc		= ftrace_reg_event_<call>,
- *	.unregfunc		= ftrace_unreg_event_<call>,
- * }
- *
- *
- * For those macros defined with TRACE_EVENT:
- *
- * static struct ftrace_event_call event_<call>;
- *
- * static void ftrace_raw_event_<call>(proto)
- * {
- *	struct ring_buffer_event *event;
- *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
- *	unsigned long irq_flags;
- *	int pc;
- *
- *	local_save_flags(irq_flags);
- *	pc = preempt_count();
- *
- *	event = trace_current_buffer_lock_reserve(event_<call>.id,
- *				  sizeof(struct ftrace_raw_<call>),
- *				  irq_flags, pc);
- *	if (!event)
- *		return;
- *	entry	= ring_buffer_event_data(event);
- *
- *	<assign>;  <-- Here we assign the entries by the __field and
- *			__array macros.
- *
- *	trace_current_buffer_unlock_commit(event, irq_flags, pc);
- * }
- *
- * static int ftrace_raw_reg_event_<call>(void)
- * {
- *	int ret;
- *
- *	ret = register_trace_<call>(ftrace_raw_event_<call>);
- *	if (!ret)
- *		pr_info("event trace: Could not activate trace point "
- *			"probe to <call>");
- *	return ret;
- * }
- *
- * static void ftrace_unreg_event_<call>(void)
- * {
- *	unregister_trace_<call>(ftrace_raw_event_<call>);
- * }
- *
- * static struct trace_event ftrace_event_type_<call> = {
- *	.trace			= ftrace_raw_output_<call>, <-- stage 2
- * };
- *
- * static int ftrace_raw_init_event_<call>(void)
- * {
- *	int id;
- *
- *	id = register_ftrace_event(&ftrace_event_type_<call>);
- *	if (!id)
- *		return -ENODEV;
- *	event_<call>.id = id;
- *	return 0;
- * }
- *
- * static struct ftrace_event_call __used
- * __attribute__((__aligned__(4)))
- * __attribute__((section("_ftrace_events"))) event_<call> = {
- *	.name			= "<call>",
- *	.system			= "<system>",
- *	.raw_init		= ftrace_raw_init_event_<call>,
- *	.regfunc		= ftrace_reg_event_<call>,
- *	.unregfunc		= ftrace_unreg_event_<call>,
- *	.show_format		= ftrace_format_<call>,
- * }
- *
- */
-
-#undef TP_FMT
-#define TP_FMT(fmt, args...)	fmt "\n", ##args
-
-#ifdef CONFIG_EVENT_PROFILE
-#define _TRACE_PROFILE(call, proto, args)				\
-static void ftrace_profile_##call(proto)				\
-{									\
-	extern void perf_tpcounter_event(int);				\
-	perf_tpcounter_event(event_##call.id);				\
-}									\
-									\
-static int ftrace_profile_enable_##call(struct ftrace_event_call *call) \
-{									\
-	int ret = 0;							\
-									\
-	if (!atomic_inc_return(&call->profile_count))			\
-		ret = register_trace_##call(ftrace_profile_##call);	\
-									\
-	return ret;							\
-}									\
-									\
-static void ftrace_profile_disable_##call(struct ftrace_event_call *call) \
-{									\
-	if (atomic_add_negative(-1, &call->profile_count))		\
-		unregister_trace_##call(ftrace_profile_##call);		\
-}
-
-#define _TRACE_PROFILE_INIT(call)					\
-	.profile_count = ATOMIC_INIT(-1),				\
-	.profile_enable = ftrace_profile_enable_##call,			\
-	.profile_disable = ftrace_profile_disable_##call,
-
-#else
-#define _TRACE_PROFILE(call, proto, args)
-#define _TRACE_PROFILE_INIT(call)
-#endif
-
-#define _TRACE_FORMAT(call, proto, args, fmt)				\
-static void ftrace_event_##call(proto)					\
-{									\
-	event_trace_printk(_RET_IP_, #call ": " fmt);			\
-}									\
-									\
-static int ftrace_reg_event_##call(void)				\
-{									\
-	int ret;							\
-									\
-	ret = register_trace_##call(ftrace_event_##call);		\
-	if (ret)							\
-		pr_info("event trace: Could not activate trace point "	\
-			"probe to " #call "\n");			\
-	return ret;							\
-}									\
-									\
-static void ftrace_unreg_event_##call(void)				\
-{									\
-	unregister_trace_##call(ftrace_event_##call);			\
-}									\
-									\
-static struct ftrace_event_call event_##call;				\
-									\
-static int ftrace_init_event_##call(void)				\
-{									\
-	int id;								\
-									\
-	id = register_ftrace_event(NULL);				\
-	if (!id)							\
-		return -ENODEV;						\
-	event_##call.id = id;						\
-	return 0;							\
-}
-
-#undef TRACE_FORMAT
-#define TRACE_FORMAT(call, proto, args, fmt)				\
-_TRACE_FORMAT(call, PARAMS(proto), PARAMS(args), PARAMS(fmt))		\
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
-static struct ftrace_event_call __used					\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
-	.name			= #call,				\
-	.system			= __stringify(TRACE_SYSTEM),		\
-	.raw_init		= ftrace_init_event_##call,		\
-	.regfunc		= ftrace_reg_event_##call,		\
-	.unregfunc		= ftrace_unreg_event_##call,		\
-	_TRACE_PROFILE_INIT(call)					\
-}
-
-#undef __entry
-#define __entry entry
-
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
-									\
-static struct ftrace_event_call event_##call;				\
-									\
-static void ftrace_raw_event_##call(proto)				\
-{									\
-	struct ftrace_event_call *call = &event_##call;			\
-	struct ring_buffer_event *event;				\
-	struct ftrace_raw_##call *entry;				\
-	unsigned long irq_flags;					\
-	int pc;								\
-									\
-	local_save_flags(irq_flags);					\
-	pc = preempt_count();						\
-									\
-	event = trace_current_buffer_lock_reserve(event_##call.id,	\
-				  sizeof(struct ftrace_raw_##call),	\
-				  irq_flags, pc);			\
-	if (!event)							\
-		return;							\
-	entry	= ring_buffer_event_data(event);			\
-									\
-	assign;								\
-									\
-	if (call->preds && !filter_match_preds(call, entry))		\
-		ring_buffer_event_discard(event);			\
-									\
-	trace_nowake_buffer_unlock_commit(event, irq_flags, pc);	\
-									\
-}									\
-									\
-static int ftrace_raw_reg_event_##call(void)				\
-{									\
-	int ret;							\
-									\
-	ret = register_trace_##call(ftrace_raw_event_##call);		\
-	if (ret)							\
-		pr_info("event trace: Could not activate trace point "	\
-			"probe to " #call "\n");			\
-	return ret;							\
-}									\
-									\
-static void ftrace_raw_unreg_event_##call(void)				\
-{									\
-	unregister_trace_##call(ftrace_raw_event_##call);		\
-}									\
-									\
-static struct trace_event ftrace_event_type_##call = {			\
-	.trace			= ftrace_raw_output_##call,		\
-};									\
-									\
-static int ftrace_raw_init_event_##call(void)				\
-{									\
-	int id;								\
-									\
-	id = register_ftrace_event(&ftrace_event_type_##call);		\
-	if (!id)							\
-		return -ENODEV;						\
-	event_##call.id = id;						\
-	INIT_LIST_HEAD(&event_##call.fields);				\
-	return 0;							\
-}									\
-									\
-static struct ftrace_event_call __used					\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
-	.name			= #call,				\
-	.system			= __stringify(TRACE_SYSTEM),		\
-	.raw_init		= ftrace_raw_init_event_##call,		\
-	.regfunc		= ftrace_raw_reg_event_##call,		\
-	.unregfunc		= ftrace_raw_unreg_event_##call,	\
-	.show_format		= ftrace_format_##call,			\
-	.define_fields		= ftrace_define_fields_##call,		\
-	_TRACE_PROFILE_INIT(call)					\
-}
-
-#include <trace/trace_event_types.h>
-
-#undef _TRACE_PROFILE
-#undef _TRACE_PROFILE_INIT
-
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 07a22c33ebf3..d06cf898dc86 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -19,8 +19,12 @@
 #undef TRACE_STRUCT
 #define TRACE_STRUCT(args...) args
 
+extern void __bad_type_size(void);
+
 #undef TRACE_FIELD
 #define TRACE_FIELD(type, item, assign)					\
+	if (sizeof(type) != sizeof(field.item))				\
+		__bad_type_size();					\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
 			       "offset:%u;\tsize:%u;\n",		\
 			       (unsigned int)offsetof(typeof(field), item), \
@@ -30,7 +34,7 @@
 
 
 #undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, cmd)			\
+#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd)			\
 	ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t"	\
 			       "offset:%u;\tsize:%u;\n",		\
 			       (unsigned int)offsetof(typeof(field), item), \
@@ -46,6 +50,9 @@
 	if (!ret)							\
 		return 0;
 
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed)	\
+	TRACE_FIELD(type, item, assign)
 
 #undef TP_RAW_FMT
 #define TP_RAW_FMT(args...) args
@@ -65,6 +72,22 @@ ftrace_format_##call(struct trace_seq *s)				\
 	return ret;							\
 }
 
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
+				    tpfmt)				\
+static int								\
+ftrace_format_##call(struct trace_seq *s)				\
+{									\
+	struct args field;						\
+	int ret;							\
+									\
+	tstruct;							\
+									\
+	trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt);		\
+									\
+	return ret;							\
+}
+
 #include "trace_event_types.h"
 
 #undef TRACE_ZERO_CHAR
@@ -78,6 +101,10 @@ ftrace_format_##call(struct trace_seq *s)				\
 #define TRACE_FIELD(type, item, assign)\
 	entry->item = assign;
 
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed)	\
+	TRACE_FIELD(type, item, assign)
+
 #undef TP_CMD
 #define TP_CMD(cmd...)	cmd
 
@@ -85,18 +112,95 @@ ftrace_format_##call(struct trace_seq *s)				\
 #define TRACE_ENTRY	entry
 
 #undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, cmd) \
+#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd)	\
 	cmd;
 
 #undef TRACE_EVENT_FORMAT
 #define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+int ftrace_define_fields_##call(void);					\
+static int ftrace_raw_init_event_##call(void);				\
 									\
-static struct ftrace_event_call __used					\
+struct ftrace_event_call __used						\
+__attribute__((__aligned__(4)))						\
+__attribute__((section("_ftrace_events"))) event_##call = {		\
+	.name			= #call,				\
+	.id			= proto,				\
+	.system			= __stringify(TRACE_SYSTEM),		\
+	.raw_init		= ftrace_raw_init_event_##call,		\
+	.show_format		= ftrace_format_##call,			\
+	.define_fields		= ftrace_define_fields_##call,		\
+};									\
+static int ftrace_raw_init_event_##call(void)				\
+{									\
+	INIT_LIST_HEAD(&event_##call.fields);				\
+	init_preds(&event_##call);					\
+	return 0;							\
+}									\
+
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
+				    tpfmt)				\
+									\
+struct ftrace_event_call __used						\
 __attribute__((__aligned__(4)))						\
 __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.name			= #call,				\
 	.id			= proto,				\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.show_format		= ftrace_format_##call,			\
-}
+};
+
+#include "trace_event_types.h"
+
+#undef TRACE_FIELD
+#define TRACE_FIELD(type, item, assign)					\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), is_signed_type(type));	\
+	if (ret)							\
+		return ret;
+
+#undef TRACE_FIELD_SPECIAL
+#define TRACE_FIELD_SPECIAL(type, item, len, cmd)			\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), 0);		\
+	if (ret)							\
+		return ret;
+
+#undef TRACE_FIELD_SIGN
+#define TRACE_FIELD_SIGN(type, item, assign, is_signed)			\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), is_signed);	\
+	if (ret)							\
+		return ret;
+
+#undef TRACE_FIELD_ZERO_CHAR
+#define TRACE_FIELD_ZERO_CHAR(item)
+
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+int									\
+ftrace_define_fields_##call(void)					\
+{									\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	struct args field;						\
+	int ret;							\
+									\
+	__common_field(unsigned char, type, 0);				\
+	__common_field(unsigned char, flags, 0);			\
+	__common_field(unsigned char, preempt_count, 0);		\
+	__common_field(int, pid, 1);					\
+	__common_field(int, tgid, 1);					\
+									\
+	tstruct;							\
+									\
+	return ret;							\
+}
+
+#undef TRACE_EVENT_FORMAT_NOFILTER
+#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,	\
+				    tpfmt)
+
 #include "trace_event_types.h"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index d28687e7b3a7..8b592418d8b2 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -65,6 +65,12 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 	if (!current->ret_stack)
 		return -EBUSY;
 
+	/*
+	 * We must make sure the ret_stack is tested before we read
+	 * anything else.
+	 */
+	smp_rmb();
+
 	/* The return trace stack is full */
 	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
 		atomic_inc(&current->trace_overrun);
@@ -78,13 +84,14 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 	current->ret_stack[index].ret = ret;
 	current->ret_stack[index].func = func;
 	current->ret_stack[index].calltime = calltime;
+	current->ret_stack[index].subtime = 0;
 	*depth = index;
 
 	return 0;
 }
 
 /* Retrieve a function return address to the trace stack on thread info.*/
-void
+static void
 ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 {
 	int index;
@@ -104,9 +111,6 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
 	trace->calltime = current->ret_stack[index].calltime;
 	trace->overrun = atomic_read(&current->trace_overrun);
 	trace->depth = index;
-	barrier();
-	current->curr_ret_stack--;
-
 }
 
 /*
@@ -121,6 +125,8 @@ unsigned long ftrace_return_to_handler(void)
 	ftrace_pop_return_trace(&trace, &ret);
 	trace.rettime = trace_clock_local();
 	ftrace_graph_return(&trace);
+	barrier();
+	current->curr_ret_stack--;
 
 	if (unlikely(!ret)) {
 		ftrace_graph_stop();
@@ -426,8 +432,8 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 	return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t
-print_graph_duration(unsigned long long duration, struct trace_seq *s)
+enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 {
 	unsigned long nsecs_rem = do_div(duration, 1000);
 	/* log10(ULONG_MAX) + '\0' */
@@ -464,12 +470,23 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s)
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_duration(unsigned long long duration, struct trace_seq *s)
+{
+	int ret;
+
+	ret = trace_print_graph_duration(duration, s);
+	if (ret != TRACE_TYPE_HANDLED)
+		return ret;
 
 	ret = trace_seq_printf(s, "|  ");
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
-	return TRACE_TYPE_HANDLED;
 
+	return TRACE_TYPE_HANDLED;
 }
 
 /* Case of a leaf function on its call entry */
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index 7bfdf4c2347f..ca7d7c4d0c2a 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -1,10 +1,9 @@
 /*
- * h/w branch tracer for x86 based on bts
+ * h/w branch tracer for x86 based on BTS
  *
  * Copyright (C) 2008-2009 Intel Corporation.
  * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009
  */
-#include <linux/spinlock.h>
 #include <linux/kallsyms.h>
 #include <linux/debugfs.h>
 #include <linux/ftrace.h>
@@ -15,110 +14,119 @@
 
 #include <asm/ds.h>
 
-#include "trace.h"
 #include "trace_output.h"
+#include "trace.h"
 
 
-#define SIZEOF_BTS (1 << 13)
+#define BTS_BUFFER_SIZE (1 << 13)
 
-/*
- * The tracer lock protects the below per-cpu tracer array.
- * It needs to be held to:
- * - start tracing on all cpus
- * - stop tracing on all cpus
- * - start tracing on a single hotplug cpu
- * - stop tracing on a single hotplug cpu
- * - read the trace from all cpus
- * - read the trace from a single cpu
- */
-static DEFINE_SPINLOCK(bts_tracer_lock);
 static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer);
+static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], buffer);
 
 #define this_tracer per_cpu(tracer, smp_processor_id())
-#define this_buffer per_cpu(buffer, smp_processor_id())
 
-static int __read_mostly trace_hw_branches_enabled;
+static int trace_hw_branches_enabled __read_mostly;
+static int trace_hw_branches_suspended __read_mostly;
 static struct trace_array *hw_branch_trace __read_mostly;
 
 
-/*
- * Start tracing on the current cpu.
- * The argument is ignored.
- *
- * pre: bts_tracer_lock must be locked.
- */
-static void bts_trace_start_cpu(void *arg)
+static void bts_trace_init_cpu(int cpu)
 {
-	if (this_tracer)
-		ds_release_bts(this_tracer);
+	per_cpu(tracer, cpu) =
+		ds_request_bts_cpu(cpu, per_cpu(buffer, cpu), BTS_BUFFER_SIZE,
+				   NULL, (size_t)-1, BTS_KERNEL);
 
-	this_tracer =
-		ds_request_bts(/* task = */ NULL, this_buffer, SIZEOF_BTS,
-			       /* ovfl = */ NULL, /* th = */ (size_t)-1,
-			       BTS_KERNEL);
-	if (IS_ERR(this_tracer)) {
-		this_tracer = NULL;
-		return;
+	if (IS_ERR(per_cpu(tracer, cpu)))
+		per_cpu(tracer, cpu) = NULL;
+}
+
+static int bts_trace_init(struct trace_array *tr)
+{
+	int cpu;
+
+	hw_branch_trace = tr;
+	trace_hw_branches_enabled = 0;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		bts_trace_init_cpu(cpu);
+
+		if (likely(per_cpu(tracer, cpu)))
+			trace_hw_branches_enabled = 1;
 	}
+	trace_hw_branches_suspended = 0;
+	put_online_cpus();
+
+	/* If we could not enable tracing on a single cpu, we fail. */
+	return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP;
+}
+
+static void bts_trace_reset(struct trace_array *tr)
+{
+	int cpu;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		if (likely(per_cpu(tracer, cpu))) {
+			ds_release_bts(per_cpu(tracer, cpu));
+			per_cpu(tracer, cpu) = NULL;
+		}
+	}
+	trace_hw_branches_enabled = 0;
+	trace_hw_branches_suspended = 0;
+	put_online_cpus();
 }
 
 static void bts_trace_start(struct trace_array *tr)
 {
-	spin_lock(&bts_tracer_lock);
+	int cpu;
 
-	on_each_cpu(bts_trace_start_cpu, NULL, 1);
-	trace_hw_branches_enabled = 1;
-
-	spin_unlock(&bts_tracer_lock);
-}
-
-/*
- * Stop tracing on the current cpu.
- * The argument is ignored.
- *
- * pre: bts_tracer_lock must be locked.
- */
-static void bts_trace_stop_cpu(void *arg)
-{
-	if (this_tracer) {
-		ds_release_bts(this_tracer);
-		this_tracer = NULL;
-	}
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		if (likely(per_cpu(tracer, cpu)))
+			ds_resume_bts(per_cpu(tracer, cpu));
+	trace_hw_branches_suspended = 0;
+	put_online_cpus();
 }
 
 static void bts_trace_stop(struct trace_array *tr)
 {
-	spin_lock(&bts_tracer_lock);
+	int cpu;
 
-	trace_hw_branches_enabled = 0;
-	on_each_cpu(bts_trace_stop_cpu, NULL, 1);
-
-	spin_unlock(&bts_tracer_lock);
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		if (likely(per_cpu(tracer, cpu)))
+			ds_suspend_bts(per_cpu(tracer, cpu));
+	trace_hw_branches_suspended = 1;
+	put_online_cpus();
 }
 
 static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
 				     unsigned long action, void *hcpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-
-	spin_lock(&bts_tracer_lock);
-
-	if (!trace_hw_branches_enabled)
-		goto out;
+	int cpu = (long)hcpu;
 
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
-		smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1);
+		/* The notification is sent with interrupts enabled. */
+		if (trace_hw_branches_enabled) {
+			bts_trace_init_cpu(cpu);
+
+			if (trace_hw_branches_suspended &&
+			    likely(per_cpu(tracer, cpu)))
+				ds_suspend_bts(per_cpu(tracer, cpu));
+		}
 		break;
+
 	case CPU_DOWN_PREPARE:
-		smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1);
-		break;
+		/* The notification is sent with interrupts enabled. */
+		if (likely(per_cpu(tracer, cpu))) {
+			ds_release_bts(per_cpu(tracer, cpu));
+			per_cpu(tracer, cpu) = NULL;
+		}
 	}
 
- out:
-	spin_unlock(&bts_tracer_lock);
 	return NOTIFY_DONE;
 }
 
@@ -126,20 +134,6 @@ static struct notifier_block bts_hotcpu_notifier __cpuinitdata = {
 	.notifier_call = bts_hotcpu_handler
 };
 
-static int bts_trace_init(struct trace_array *tr)
-{
-	hw_branch_trace = tr;
-
-	bts_trace_start(tr);
-
-	return 0;
-}
-
-static void bts_trace_reset(struct trace_array *tr)
-{
-	bts_trace_stop(tr);
-}
-
 static void bts_trace_print_header(struct seq_file *m)
 {
 	seq_puts(m, "# CPU#        TO  <-  FROM\n");
@@ -147,10 +141,10 @@ static void bts_trace_print_header(struct seq_file *m)
 
 static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
 {
+	unsigned long symflags = TRACE_ITER_SYM_OFFSET;
 	struct trace_entry *entry = iter->ent;
 	struct trace_seq *seq = &iter->seq;
 	struct hw_branch_entry *it;
-	unsigned long symflags = TRACE_ITER_SYM_OFFSET;
 
 	trace_assign_type(it, entry);
 
@@ -168,6 +162,7 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
 
 void trace_hw_branch(u64 from, u64 to)
 {
+	struct ftrace_event_call *call = &event_hw_branch;
 	struct trace_array *tr = hw_branch_trace;
 	struct ring_buffer_event *event;
 	struct hw_branch_entry *entry;
@@ -194,7 +189,8 @@ void trace_hw_branch(u64 from, u64 to)
 	entry->ent.type = TRACE_HW_BRANCHES;
 	entry->from = from;
 	entry->to   = to;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		trace_buffer_unlock_commit(tr, event, 0, 0);
 
  out:
 	atomic_dec(&tr->data[cpu]->disabled);
@@ -224,11 +220,11 @@ static void trace_bts_at(const struct bts_trace *trace, void *at)
 /*
  * Collect the trace on the current cpu and write it into the ftrace buffer.
  *
- * pre: bts_tracer_lock must be locked
+ * pre: tracing must be suspended on the current cpu
  */
 static void trace_bts_cpu(void *arg)
 {
-	struct trace_array *tr = (struct trace_array *) arg;
+	struct trace_array *tr = (struct trace_array *)arg;
 	const struct bts_trace *trace;
 	unsigned char *at;
 
@@ -241,10 +237,9 @@ static void trace_bts_cpu(void *arg)
 	if (unlikely(!this_tracer))
 		return;
 
-	ds_suspend_bts(this_tracer);
 	trace = ds_read_bts(this_tracer);
 	if (!trace)
-		goto out;
+		return;
 
 	for (at = trace->ds.top; (void *)at < trace->ds.end;
 	     at += trace->ds.size)
@@ -253,18 +248,27 @@ static void trace_bts_cpu(void *arg)
 	for (at = trace->ds.begin; (void *)at < trace->ds.top;
 	     at += trace->ds.size)
 		trace_bts_at(trace, at);
-
-out:
-	ds_resume_bts(this_tracer);
 }
 
 static void trace_bts_prepare(struct trace_iterator *iter)
 {
-	spin_lock(&bts_tracer_lock);
+	int cpu;
 
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		if (likely(per_cpu(tracer, cpu)))
+			ds_suspend_bts(per_cpu(tracer, cpu));
+	/*
+	 * We need to collect the trace on the respective cpu since ftrace
+	 * implicitly adds the record for the current cpu.
+	 * Once that is more flexible, we could collect the data from any cpu.
+	 */
 	on_each_cpu(trace_bts_cpu, iter->tr, 1);
 
-	spin_unlock(&bts_tracer_lock);
+	for_each_online_cpu(cpu)
+		if (likely(per_cpu(tracer, cpu)))
+			ds_resume_bts(per_cpu(tracer, cpu));
+	put_online_cpus();
 }
 
 static void trace_bts_close(struct trace_iterator *iter)
@@ -274,11 +278,11 @@ static void trace_bts_close(struct trace_iterator *iter)
 
 void trace_hw_branch_oops(void)
 {
-	spin_lock(&bts_tracer_lock);
-
-	trace_bts_cpu(hw_branch_trace);
-
-	spin_unlock(&bts_tracer_lock);
+	if (this_tracer) {
+		ds_suspend_bts_noirq(this_tracer);
+		trace_bts_cpu(hw_branch_trace);
+		ds_resume_bts_noirq(this_tracer);
+	}
 }
 
 struct tracer bts_tracer __read_mostly =
@@ -291,7 +295,10 @@ struct tracer bts_tracer __read_mostly =
 	.start		= bts_trace_start,
 	.stop		= bts_trace_stop,
 	.open		= trace_bts_prepare,
-	.close		= trace_bts_close
+	.close		= trace_bts_close,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest	= trace_selftest_startup_hw_branches,
+#endif /* CONFIG_FTRACE_SELFTEST */
 };
 
 __init static int init_bts_trace(void)
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 8e37fcddd8b4..d53b45ed0806 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,8 @@
 #include <linux/kernel.h>
 #include <linux/mmiotrace.h>
 #include <linux/pci.h>
+#include <linux/time.h>
+
 #include <asm/atomic.h>
 
 #include "trace.h"
@@ -174,7 +176,7 @@ static enum print_line_t mmio_print_rw(struct trace_iterator *iter)
 	struct mmiotrace_rw *rw;
 	struct trace_seq *s	= &iter->seq;
 	unsigned long long t	= ns2usecs(iter->ts);
-	unsigned long usec_rem	= do_div(t, 1000000ULL);
+	unsigned long usec_rem	= do_div(t, USEC_PER_SEC);
 	unsigned secs		= (unsigned long)t;
 	int ret = 1;
 
@@ -221,7 +223,7 @@ static enum print_line_t mmio_print_map(struct trace_iterator *iter)
 	struct mmiotrace_map *m;
 	struct trace_seq *s	= &iter->seq;
 	unsigned long long t	= ns2usecs(iter->ts);
-	unsigned long usec_rem	= do_div(t, 1000000ULL);
+	unsigned long usec_rem	= do_div(t, USEC_PER_SEC);
 	unsigned secs		= (unsigned long)t;
 	int ret;
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 64b54a59c55b..7938f3ae93e3 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -14,11 +14,25 @@
 /* must be a power of 2 */
 #define EVENT_HASHSIZE	128
 
-static DEFINE_MUTEX(trace_event_mutex);
+DECLARE_RWSEM(trace_event_mutex);
+
+DEFINE_PER_CPU(struct trace_seq, ftrace_event_seq);
+EXPORT_PER_CPU_SYMBOL(ftrace_event_seq);
+
 static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
 static int next_event_type = __TRACE_LAST_TYPE + 1;
 
+void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
+
+	s->buffer[len] = 0;
+	seq_puts(m, s->buffer);
+
+	trace_seq_init(s);
+}
+
 enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
@@ -84,6 +98,39 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 
 	return len;
 }
+EXPORT_SYMBOL_GPL(trace_seq_printf);
+
+/**
+ * trace_seq_vprintf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+int
+trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+{
+	int len = (PAGE_SIZE - 1) - s->len;
+	int ret;
+
+	if (!len)
+		return 0;
+
+	ret = vsnprintf(s->buffer + s->len, len, fmt, args);
+
+	/* If we can't write it all, don't bother writing anything */
+	if (ret >= len)
+		return 0;
+
+	s->len += ret;
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(trace_seq_vprintf);
 
 int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
 {
@@ -201,6 +248,67 @@ int trace_seq_path(struct trace_seq *s, struct path *path)
 	return 0;
 }
 
+const char *
+ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
+		       unsigned long flags,
+		       const struct trace_print_flags *flag_array)
+{
+	unsigned long mask;
+	const char *str;
+	const char *ret = p->buffer + p->len;
+	int i;
+
+	for (i = 0;  flag_array[i].name && flags; i++) {
+
+		mask = flag_array[i].mask;
+		if ((flags & mask) != mask)
+			continue;
+
+		str = flag_array[i].name;
+		flags &= ~mask;
+		if (p->len && delim)
+			trace_seq_puts(p, delim);
+		trace_seq_puts(p, str);
+	}
+
+	/* check for left over flags */
+	if (flags) {
+		if (p->len && delim)
+			trace_seq_puts(p, delim);
+		trace_seq_printf(p, "0x%lx", flags);
+	}
+
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(ftrace_print_flags_seq);
+
+const char *
+ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
+			 const struct trace_print_flags *symbol_array)
+{
+	int i;
+	const char *ret = p->buffer + p->len;
+
+	for (i = 0;  symbol_array[i].name; i++) {
+
+		if (val != symbol_array[i].mask)
+			continue;
+
+		trace_seq_puts(p, symbol_array[i].name);
+		break;
+	}
+
+	if (!p->len)
+		trace_seq_printf(p, "0x%lx", val);
+		
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(ftrace_print_symbols_seq);
+
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {
@@ -311,17 +419,20 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
 
 		if (ip == ULONG_MAX || !ret)
 			break;
-		if (i && ret)
-			ret = trace_seq_puts(s, " <- ");
+		if (ret)
+			ret = trace_seq_puts(s, " => ");
 		if (!ip) {
 			if (ret)
 				ret = trace_seq_puts(s, "??");
+			if (ret)
+				ret = trace_seq_puts(s, "\n");
 			continue;
 		}
 		if (!ret)
 			break;
 		if (ret)
 			ret = seq_print_user_ip(s, mm, ip, sym_flags);
+		ret = trace_seq_puts(s, "\n");
 	}
 
 	if (mm)
@@ -455,6 +566,7 @@ static int task_state_char(unsigned long state)
  * @type: the type of event to look for
  *
  * Returns an event of type @type otherwise NULL
+ * Called with trace_event_read_lock() held.
  */
 struct trace_event *ftrace_find_event(int type)
 {
@@ -464,7 +576,7 @@ struct trace_event *ftrace_find_event(int type)
 
 	key = type & (EVENT_HASHSIZE - 1);
 
-	hlist_for_each_entry_rcu(event, n, &event_hash[key], node) {
+	hlist_for_each_entry(event, n, &event_hash[key], node) {
 		if (event->type == type)
 			return event;
 	}
@@ -472,6 +584,46 @@ struct trace_event *ftrace_find_event(int type)
 	return NULL;
 }
 
+static LIST_HEAD(ftrace_event_list);
+
+static int trace_search_list(struct list_head **list)
+{
+	struct trace_event *e;
+	int last = __TRACE_LAST_TYPE;
+
+	if (list_empty(&ftrace_event_list)) {
+		*list = &ftrace_event_list;
+		return last + 1;
+	}
+
+	/*
+	 * We used up all possible max events,
+	 * lets see if somebody freed one.
+	 */
+	list_for_each_entry(e, &ftrace_event_list, list) {
+		if (e->type != last + 1)
+			break;
+		last++;
+	}
+
+	/* Did we used up all 65 thousand events??? */
+	if ((last + 1) > FTRACE_MAX_EVENT)
+		return 0;
+
+	*list = &e->list;
+	return last + 1;
+}
+
+void trace_event_read_lock(void)
+{
+	down_read(&trace_event_mutex);
+}
+
+void trace_event_read_unlock(void)
+{
+	up_read(&trace_event_mutex);
+}
+
 /**
  * register_ftrace_event - register output for an event type
  * @event: the event type to register
@@ -492,22 +644,42 @@ int register_ftrace_event(struct trace_event *event)
 	unsigned key;
 	int ret = 0;
 
-	mutex_lock(&trace_event_mutex);
+	down_write(&trace_event_mutex);
 
-	if (!event) {
-		ret = next_event_type++;
+	if (WARN_ON(!event))
 		goto out;
-	}
 
-	if (!event->type)
-		event->type = next_event_type++;
-	else if (event->type > __TRACE_LAST_TYPE) {
+	INIT_LIST_HEAD(&event->list);
+
+	if (!event->type) {
+		struct list_head *list = NULL;
+
+		if (next_event_type > FTRACE_MAX_EVENT) {
+
+			event->type = trace_search_list(&list);
+			if (!event->type)
+				goto out;
+
+		} else {
+			
+			event->type = next_event_type++;
+			list = &ftrace_event_list;
+		}
+
+		if (WARN_ON(ftrace_find_event(event->type)))
+			goto out;
+
+		list_add_tail(&event->list, list);
+
+	} else if (event->type > __TRACE_LAST_TYPE) {
 		printk(KERN_WARNING "Need to add type to trace.h\n");
 		WARN_ON(1);
-	}
-
-	if (ftrace_find_event(event->type))
 		goto out;
+	} else {
+		/* Is this event already used */
+		if (ftrace_find_event(event->type))
+			goto out;
+	}
 
 	if (event->trace == NULL)
 		event->trace = trace_nop_print;
@@ -520,14 +692,25 @@ int register_ftrace_event(struct trace_event *event)
 
 	key = event->type & (EVENT_HASHSIZE - 1);
 
-	hlist_add_head_rcu(&event->node, &event_hash[key]);
+	hlist_add_head(&event->node, &event_hash[key]);
 
 	ret = event->type;
  out:
-	mutex_unlock(&trace_event_mutex);
+	up_write(&trace_event_mutex);
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(register_ftrace_event);
+
+/*
+ * Used by module code with the trace_event_mutex held for write.
+ */
+int __unregister_ftrace_event(struct trace_event *event)
+{
+	hlist_del(&event->node);
+	list_del(&event->list);
+	return 0;
+}
 
 /**
  * unregister_ftrace_event - remove a no longer used event
@@ -535,12 +718,13 @@ int register_ftrace_event(struct trace_event *event)
  */
 int unregister_ftrace_event(struct trace_event *event)
 {
-	mutex_lock(&trace_event_mutex);
-	hlist_del(&event->node);
-	mutex_unlock(&trace_event_mutex);
+	down_write(&trace_event_mutex);
+	__unregister_ftrace_event(event);
+	up_write(&trace_event_mutex);
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(unregister_ftrace_event);
 
 /*
  * Standard events
@@ -833,14 +1017,16 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
+	if (!trace_seq_puts(s, "<stack trace>\n"))
+		goto partial;
 	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
-		if (i) {
-			if (!trace_seq_puts(s, " <= "))
-				goto partial;
+		if (!field->caller[i] || (field->caller[i] == ULONG_MAX))
+			break;
+		if (!trace_seq_puts(s, " => "))
+			goto partial;
 
-			if (!seq_print_ip_sym(s, field->caller[i], flags))
-				goto partial;
-		}
+		if (!seq_print_ip_sym(s, field->caller[i], flags))
+			goto partial;
 		if (!trace_seq_puts(s, "\n"))
 			goto partial;
 	}
@@ -868,10 +1054,10 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
-	if (!seq_print_userip_objs(field, s, flags))
+	if (!trace_seq_puts(s, "<user stack trace>\n"))
 		goto partial;
 
-	if (!trace_seq_putc(s, '\n'))
+	if (!seq_print_userip_objs(field, s, flags))
 		goto partial;
 
 	return TRACE_TYPE_HANDLED;
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index e0bde39c2dd9..d38bec4a9c30 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -1,41 +1,17 @@
 #ifndef __TRACE_EVENTS_H
 #define __TRACE_EVENTS_H
 
+#include <linux/trace_seq.h>
 #include "trace.h"
 
-typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
-					      int flags);
-
-struct trace_event {
-	struct hlist_node	node;
-	int			type;
-	trace_print_func	trace;
-	trace_print_func	raw;
-	trace_print_func	hex;
-	trace_print_func	binary;
-};
-
 extern enum print_line_t
 trace_print_bprintk_msg_only(struct trace_iterator *iter);
 extern enum print_line_t
 trace_print_printk_msg_only(struct trace_iterator *iter);
 
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
-	__attribute__ ((format (printf, 2, 3)));
-extern int
-trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
 extern int
 seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
 		unsigned long sym_flags);
-extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
-				 size_t cnt);
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
-extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
-				size_t len);
-extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
-extern int trace_seq_path(struct trace_seq *s, struct path *path);
 extern int seq_print_userip_objs(const struct userstack_entry *entry,
 				 struct trace_seq *s, unsigned long sym_flags);
 extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
@@ -44,13 +20,17 @@ extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
 extern int trace_print_context(struct trace_iterator *iter);
 extern int trace_print_lat_context(struct trace_iterator *iter);
 
+extern void trace_event_read_lock(void);
+extern void trace_event_read_unlock(void);
 extern struct trace_event *ftrace_find_event(int type);
-extern int register_ftrace_event(struct trace_event *event);
-extern int unregister_ftrace_event(struct trace_event *event);
 
 extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
 					 int flags);
 
+/* used by module unregistering */
+extern int __unregister_ftrace_event(struct trace_event *event);
+extern struct rw_semaphore trace_event_mutex;
+
 #define MAX_MEMHEX_BYTES	8
 #define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)
 
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index 118439709fb7..8a30d9874cd4 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -36,6 +36,7 @@ static void probe_power_start(struct power_trace *it, unsigned int type,
 
 static void probe_power_end(struct power_trace *it)
 {
+	struct ftrace_event_call *call = &event_power;
 	struct ring_buffer_event *event;
 	struct trace_power *entry;
 	struct trace_array_cpu *data;
@@ -54,7 +55,8 @@ static void probe_power_end(struct power_trace *it)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->state_data = *it;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		trace_buffer_unlock_commit(tr, event, 0, 0);
  out:
 	preempt_enable();
 }
@@ -62,6 +64,7 @@ static void probe_power_end(struct power_trace *it)
 static void probe_power_mark(struct power_trace *it, unsigned int type,
 				unsigned int level)
 {
+	struct ftrace_event_call *call = &event_power;
 	struct ring_buffer_event *event;
 	struct trace_power *entry;
 	struct trace_array_cpu *data;
@@ -84,7 +87,8 @@ static void probe_power_mark(struct power_trace *it, unsigned int type,
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->state_data = *it;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		trace_buffer_unlock_commit(tr, event, 0, 0);
  out:
 	preempt_enable();
 }
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index eb81556107fe..9bece9687b62 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -245,17 +245,13 @@ static const struct file_operations ftrace_formats_fops = {
 static __init int init_trace_printk_function_export(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
 		return 0;
 
-	entry = debugfs_create_file("printk_formats", 0444, d_tracer,
+	trace_create_file("printk_formats", 0444, d_tracer,
 				    NULL, &ftrace_formats_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'printk_formats' entry\n");
 
 	return 0;
 }
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 9117cea6f1ae..a98106dd979c 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -10,7 +10,7 @@
 #include <linux/kallsyms.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #include "trace.h"
 
@@ -29,13 +29,13 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 	int cpu;
 	int pc;
 
-	if (!sched_ref || sched_stopped)
+	if (unlikely(!sched_ref))
 		return;
 
 	tracing_record_cmdline(prev);
 	tracing_record_cmdline(next);
 
-	if (!tracer_enabled)
+	if (!tracer_enabled || sched_stopped)
 		return;
 
 	pc = preempt_count();
@@ -56,15 +56,15 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
 	unsigned long flags;
 	int cpu, pc;
 
-	if (!likely(tracer_enabled))
+	if (unlikely(!sched_ref))
+		return;
+
+	tracing_record_cmdline(current);
+
+	if (!tracer_enabled || sched_stopped)
 		return;
 
 	pc = preempt_count();
-	tracing_record_cmdline(current);
-
-	if (sched_stopped)
-		return;
-
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = ctx_trace->data[cpu];
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 5bc00e8f153e..eacb27225173 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -15,7 +15,7 @@
 #include <linux/kallsyms.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
-#include <trace/sched.h>
+#include <trace/events/sched.h>
 
 #include "trace.h"
 
@@ -138,9 +138,6 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
 
 	pc = preempt_count();
 
-	/* The task we are waiting for is waking up */
-	data = wakeup_trace->data[wakeup_cpu];
-
 	/* disable local data, not wakeup_cpu data */
 	cpu = raw_smp_processor_id();
 	disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
@@ -154,6 +151,9 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
 	if (unlikely(!tracer_enabled || next != wakeup_task))
 		goto out_unlock;
 
+	/* The task we are waiting for is waking up */
+	data = wakeup_trace->data[wakeup_cpu];
+
 	trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
 	tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
 
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 08f4eb2763d1..00dd6485bdd7 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -16,6 +16,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_BRANCH:
 	case TRACE_GRAPH_ENT:
 	case TRACE_GRAPH_RET:
+	case TRACE_HW_BRANCHES:
 		return 1;
 	}
 	return 0;
@@ -188,6 +189,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 #else
 # define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; })
 #endif /* CONFIG_DYNAMIC_FTRACE */
+
 /*
  * Simple verification test of ftrace function tracer.
  * Enable ftrace, sleep 1/10 second, and then read the trace
@@ -749,3 +751,59 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
 	return ret;
 }
 #endif /* CONFIG_BRANCH_TRACER */
+
+#ifdef CONFIG_HW_BRANCH_TRACER
+int
+trace_selftest_startup_hw_branches(struct tracer *trace,
+				   struct trace_array *tr)
+{
+	struct trace_iterator *iter;
+	struct tracer tracer;
+	unsigned long count;
+	int ret;
+
+	if (!trace->open) {
+		printk(KERN_CONT "missing open function...");
+		return -1;
+	}
+
+	ret = tracer_init(trace, tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
+	/*
+	 * The hw-branch tracer needs to collect the trace from the various
+	 * cpu trace buffers - before tracing is stopped.
+	 */
+	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+	if (!iter)
+		return -ENOMEM;
+
+	memcpy(&tracer, trace, sizeof(tracer));
+
+	iter->trace = &tracer;
+	iter->tr = tr;
+	iter->pos = -1;
+	mutex_init(&iter->mutex);
+
+	trace->open(iter);
+
+	mutex_destroy(&iter->mutex);
+	kfree(iter);
+
+	tracing_stop();
+
+	ret = trace_test_buffer(tr, &count);
+	trace->reset(tr);
+	tracing_start();
+
+	if (!ret && !count) {
+		printk(KERN_CONT "no entries found..");
+		ret = -1;
+	}
+
+	return ret;
+}
+#endif /* CONFIG_HW_BRANCH_TRACER */
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index c750f65f9661..2d7aebd71dbd 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -265,7 +265,7 @@ static int t_show(struct seq_file *m, void *v)
 		seq_printf(m, "        Depth    Size   Location"
 			   "    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   max_stack_trace.nr_entries);
+			   max_stack_trace.nr_entries - 1);
 
 		if (!stack_tracer_enabled && !max_stack_size)
 			print_disabled(m);
@@ -352,19 +352,14 @@ __setup("stacktrace", enable_stacktrace);
 static __init int stack_trace_init(void)
 {
 	struct dentry *d_tracer;
-	struct dentry *entry;
 
 	d_tracer = tracing_init_dentry();
 
-	entry = debugfs_create_file("stack_max_size", 0644, d_tracer,
-				    &max_stack_size, &stack_max_size_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'stack_max_size' entry\n");
+	trace_create_file("stack_max_size", 0644, d_tracer,
+			&max_stack_size, &stack_max_size_fops);
 
-	entry = debugfs_create_file("stack_trace", 0444, d_tracer,
-				    NULL, &stack_trace_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs 'stack_trace' entry\n");
+	trace_create_file("stack_trace", 0444, d_tracer,
+			NULL, &stack_trace_fops);
 
 	if (stack_tracer_enabled)
 		register_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index acdebd771a93..c00643733f4c 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -1,7 +1,7 @@
 /*
  * Infrastructure for statistic tracing (histogram output).
  *
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com>
  *
  * Based on the code from trace_branch.c which is
  * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
@@ -10,22 +10,27 @@
 
 
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/debugfs.h>
 #include "trace_stat.h"
 #include "trace.h"
 
 
-/* List of stat entries from a tracer */
-struct trace_stat_list {
-	struct list_head	list;
+/*
+ * List of stat red-black nodes from a tracer
+ * We use a such tree to sort quickly the stat
+ * entries from the tracer.
+ */
+struct stat_node {
+	struct rb_node		node;
 	void			*stat;
 };
 
 /* A stat session is the stats output in one file */
-struct tracer_stat_session {
+struct stat_session {
 	struct list_head	session_list;
 	struct tracer_stat	*ts;
-	struct list_head	stat_list;
+	struct rb_root		stat_root;
 	struct mutex		stat_mutex;
 	struct dentry		*file;
 };
@@ -37,18 +42,48 @@ static DEFINE_MUTEX(all_stat_sessions_mutex);
 /* The root directory for all stat files */
 static struct dentry		*stat_dir;
 
-
-static void reset_stat_session(struct tracer_stat_session *session)
+/*
+ * Iterate through the rbtree using a post order traversal path
+ * to release the next node.
+ * It won't necessary release one at each iteration
+ * but it will at least advance closer to the next one
+ * to be released.
+ */
+static struct rb_node *release_next(struct rb_node *node)
 {
-	struct trace_stat_list *node, *next;
+	struct stat_node *snode;
+	struct rb_node *parent = rb_parent(node);
 
-	list_for_each_entry_safe(node, next, &session->stat_list, list)
-		kfree(node);
+	if (node->rb_left)
+		return node->rb_left;
+	else if (node->rb_right)
+		return node->rb_right;
+	else {
+		if (!parent)
+			;
+		else if (parent->rb_left == node)
+			parent->rb_left = NULL;
+		else
+			parent->rb_right = NULL;
 
-	INIT_LIST_HEAD(&session->stat_list);
+		snode = container_of(node, struct stat_node, node);
+		kfree(snode);
+
+		return parent;
+	}
 }
 
-static void destroy_session(struct tracer_stat_session *session)
+static void reset_stat_session(struct stat_session *session)
+{
+	struct rb_node *node = session->stat_root.rb_node;
+
+	while (node)
+		node = release_next(node);
+
+	session->stat_root = RB_ROOT;
+}
+
+static void destroy_session(struct stat_session *session)
 {
 	debugfs_remove(session->file);
 	reset_stat_session(session);
@@ -56,25 +91,60 @@ static void destroy_session(struct tracer_stat_session *session)
 	kfree(session);
 }
 
-/*
- * For tracers that don't provide a stat_cmp callback.
- * This one will force an immediate insertion on tail of
- * the list.
- */
-static int dummy_cmp(void *p1, void *p2)
+typedef int (*cmp_stat_t)(void *, void *);
+
+static int insert_stat(struct rb_root *root, void *stat, cmp_stat_t cmp)
 {
-	return 1;
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct stat_node *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	data->stat = stat;
+
+	/*
+	 * Figure out where to put new node
+	 * This is a descendent sorting
+	 */
+	while (*new) {
+		struct stat_node *this;
+		int result;
+
+		this = container_of(*new, struct stat_node, node);
+		result = cmp(data->stat, this->stat);
+
+		parent = *new;
+		if (result >= 0)
+			new = &((*new)->rb_left);
+		else
+			new = &((*new)->rb_right);
+	}
+
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+	return 0;
 }
 
 /*
- * Initialize the stat list at each trace_stat file opening.
+ * For tracers that don't provide a stat_cmp callback.
+ * This one will force an insertion as right-most node
+ * in the rbtree.
+ */
+static int dummy_cmp(void *p1, void *p2)
+{
+	return -1;
+}
+
+/*
+ * Initialize the stat rbtree at each trace_stat file opening.
  * All of these copies and sorting are required on all opening
  * since the stats could have changed between two file sessions.
  */
-static int stat_seq_init(struct tracer_stat_session *session)
+static int stat_seq_init(struct stat_session *session)
 {
-	struct trace_stat_list *iter_entry, *new_entry;
 	struct tracer_stat *ts = session->ts;
+	struct rb_root *root = &session->stat_root;
 	void *stat;
 	int ret = 0;
 	int i;
@@ -85,29 +155,16 @@ static int stat_seq_init(struct tracer_stat_session *session)
 	if (!ts->stat_cmp)
 		ts->stat_cmp = dummy_cmp;
 
-	stat = ts->stat_start();
+	stat = ts->stat_start(ts);
 	if (!stat)
 		goto exit;
 
-	/*
-	 * The first entry. Actually this is the second, but the first
-	 * one (the stat_list head) is pointless.
-	 */
-	new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL);
-	if (!new_entry) {
-		ret = -ENOMEM;
+	ret = insert_stat(root, stat, ts->stat_cmp);
+	if (ret)
 		goto exit;
-	}
-
-	INIT_LIST_HEAD(&new_entry->list);
-
-	list_add(&new_entry->list, &session->stat_list);
-
-	new_entry->stat = stat;
 
 	/*
-	 * Iterate over the tracer stat entries and store them in a sorted
-	 * list.
+	 * Iterate over the tracer stat entries and store them in an rbtree.
 	 */
 	for (i = 1; ; i++) {
 		stat = ts->stat_next(stat, i);
@@ -116,36 +173,16 @@ static int stat_seq_init(struct tracer_stat_session *session)
 		if (!stat)
 			break;
 
-		new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL);
-		if (!new_entry) {
-			ret = -ENOMEM;
-			goto exit_free_list;
-		}
-
-		INIT_LIST_HEAD(&new_entry->list);
-		new_entry->stat = stat;
-
-		list_for_each_entry_reverse(iter_entry, &session->stat_list,
-				list) {
-
-			/* Insertion with a descendent sorting */
-			if (ts->stat_cmp(iter_entry->stat,
-					new_entry->stat) >= 0) {
-
-				list_add(&new_entry->list, &iter_entry->list);
-				break;
-			}
-		}
-
-		/* The current larger value */
-		if (list_empty(&new_entry->list))
-			list_add(&new_entry->list, &session->stat_list);
+		ret = insert_stat(root, stat, ts->stat_cmp);
+		if (ret)
+			goto exit_free_rbtree;
 	}
+
 exit:
 	mutex_unlock(&session->stat_mutex);
 	return ret;
 
-exit_free_list:
+exit_free_rbtree:
 	reset_stat_session(session);
 	mutex_unlock(&session->stat_mutex);
 	return ret;
@@ -154,38 +191,51 @@ exit_free_list:
 
 static void *stat_seq_start(struct seq_file *s, loff_t *pos)
 {
-	struct tracer_stat_session *session = s->private;
+	struct stat_session *session = s->private;
+	struct rb_node *node;
+	int i;
 
-	/* Prevent from tracer switch or stat_list modification */
+	/* Prevent from tracer switch or rbtree modification */
 	mutex_lock(&session->stat_mutex);
 
 	/* If we are in the beginning of the file, print the headers */
-	if (!*pos && session->ts->stat_headers)
+	if (!*pos && session->ts->stat_headers) {
+		(*pos)++;
 		return SEQ_START_TOKEN;
+	}
 
-	return seq_list_start(&session->stat_list, *pos);
+	node = rb_first(&session->stat_root);
+	for (i = 0; node && i < *pos; i++)
+		node = rb_next(node);
+
+	(*pos)++;
+
+	return node;
 }
 
 static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos)
 {
-	struct tracer_stat_session *session = s->private;
+	struct stat_session *session = s->private;
+	struct rb_node *node = p;
+
+	(*pos)++;
 
 	if (p == SEQ_START_TOKEN)
-		return seq_list_start(&session->stat_list, *pos);
+		return rb_first(&session->stat_root);
 
-	return seq_list_next(p, &session->stat_list, pos);
+	return rb_next(node);
 }
 
 static void stat_seq_stop(struct seq_file *s, void *p)
 {
-	struct tracer_stat_session *session = s->private;
+	struct stat_session *session = s->private;
 	mutex_unlock(&session->stat_mutex);
 }
 
 static int stat_seq_show(struct seq_file *s, void *v)
 {
-	struct tracer_stat_session *session = s->private;
-	struct trace_stat_list *l = list_entry(v, struct trace_stat_list, list);
+	struct stat_session *session = s->private;
+	struct stat_node *l = container_of(v, struct stat_node, node);
 
 	if (v == SEQ_START_TOKEN)
 		return session->ts->stat_headers(s);
@@ -205,7 +255,7 @@ static int tracing_stat_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
-	struct tracer_stat_session *session = inode->i_private;
+	struct stat_session *session = inode->i_private;
 
 	ret = seq_open(file, &trace_stat_seq_ops);
 	if (!ret) {
@@ -218,11 +268,11 @@ static int tracing_stat_open(struct inode *inode, struct file *file)
 }
 
 /*
- * Avoid consuming memory with our now useless list.
+ * Avoid consuming memory with our now useless rbtree.
  */
 static int tracing_stat_release(struct inode *i, struct file *f)
 {
-	struct tracer_stat_session *session = i->i_private;
+	struct stat_session *session = i->i_private;
 
 	mutex_lock(&session->stat_mutex);
 	reset_stat_session(session);
@@ -251,7 +301,7 @@ static int tracing_stat_init(void)
 	return 0;
 }
 
-static int init_stat_file(struct tracer_stat_session *session)
+static int init_stat_file(struct stat_session *session)
 {
 	if (!stat_dir && tracing_stat_init())
 		return -ENODEV;
@@ -266,7 +316,7 @@ static int init_stat_file(struct tracer_stat_session *session)
 
 int register_stat_tracer(struct tracer_stat *trace)
 {
-	struct tracer_stat_session *session, *node, *tmp;
+	struct stat_session *session, *node;
 	int ret;
 
 	if (!trace)
@@ -277,7 +327,7 @@ int register_stat_tracer(struct tracer_stat *trace)
 
 	/* Already registered? */
 	mutex_lock(&all_stat_sessions_mutex);
-	list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) {
+	list_for_each_entry(node, &all_stat_sessions, session_list) {
 		if (node->ts == trace) {
 			mutex_unlock(&all_stat_sessions_mutex);
 			return -EINVAL;
@@ -286,15 +336,13 @@ int register_stat_tracer(struct tracer_stat *trace)
 	mutex_unlock(&all_stat_sessions_mutex);
 
 	/* Init the session */
-	session = kmalloc(sizeof(struct tracer_stat_session), GFP_KERNEL);
+	session = kzalloc(sizeof(*session), GFP_KERNEL);
 	if (!session)
 		return -ENOMEM;
 
 	session->ts = trace;
 	INIT_LIST_HEAD(&session->session_list);
-	INIT_LIST_HEAD(&session->stat_list);
 	mutex_init(&session->stat_mutex);
-	session->file = NULL;
 
 	ret = init_stat_file(session);
 	if (ret) {
@@ -312,7 +360,7 @@ int register_stat_tracer(struct tracer_stat *trace)
 
 void unregister_stat_tracer(struct tracer_stat *trace)
 {
-	struct tracer_stat_session *node, *tmp;
+	struct stat_session *node, *tmp;
 
 	mutex_lock(&all_stat_sessions_mutex);
 	list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) {
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
index 202274cf7f3d..f3546a2cd826 100644
--- a/kernel/trace/trace_stat.h
+++ b/kernel/trace/trace_stat.h
@@ -12,7 +12,7 @@ struct tracer_stat {
 	/* The name of your stat file */
 	const char		*name;
 	/* Iteration over statistic entries */
-	void			*(*stat_start)(void);
+	void			*(*stat_start)(struct tracer_stat *trace);
 	void			*(*stat_next)(void *prev, int idx);
 	/* Compare two entries for stats sorting */
 	int			(*stat_cmp)(void *p1, void *p2);
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index 91fd19c2149f..e04b76cc238a 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -321,11 +321,7 @@ static const struct file_operations sysprof_sample_fops = {
 
 void init_tracer_sysprof_debugfs(struct dentry *d_tracer)
 {
-	struct dentry *entry;
 
-	entry = debugfs_create_file("sysprof_sample_period", 0644,
+	trace_create_file("sysprof_sample_period", 0644,
 			d_tracer, NULL, &sysprof_sample_fops);
-	if (entry)
-		return;
-	pr_warning("Could not create debugfs 'sysprof_sample_period' entry\n");
 }
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 797201e4a137..97fcea4acce1 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -6,7 +6,7 @@
  */
 
 
-#include <trace/workqueue.h>
+#include <trace/events/workqueue.h>
 #include <linux/list.h>
 #include <linux/percpu.h>
 #include "trace_stat.h"
@@ -16,8 +16,6 @@
 /* A cpu workqueue thread */
 struct cpu_workqueue_stats {
 	struct list_head            list;
-/* Useful to know if we print the cpu headers */
-	bool		            first_entry;
 	int		            cpu;
 	pid_t			    pid;
 /* Can be inserted from interrupt or user context, need to be atomic */
@@ -47,12 +45,11 @@ probe_workqueue_insertion(struct task_struct *wq_thread,
 			  struct work_struct *work)
 {
 	int cpu = cpumask_first(&wq_thread->cpus_allowed);
-	struct cpu_workqueue_stats *node, *next;
+	struct cpu_workqueue_stats *node;
 	unsigned long flags;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list,
-							list) {
+	list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
 		if (node->pid == wq_thread->pid) {
 			atomic_inc(&node->inserted);
 			goto found;
@@ -69,12 +66,11 @@ probe_workqueue_execution(struct task_struct *wq_thread,
 			  struct work_struct *work)
 {
 	int cpu = cpumask_first(&wq_thread->cpus_allowed);
-	struct cpu_workqueue_stats *node, *next;
+	struct cpu_workqueue_stats *node;
 	unsigned long flags;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	list_for_each_entry_safe(node, next, &workqueue_cpu_stat(cpu)->list,
-							list) {
+	list_for_each_entry(node, &workqueue_cpu_stat(cpu)->list, list) {
 		if (node->pid == wq_thread->pid) {
 			node->executed++;
 			goto found;
@@ -105,8 +101,6 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
 	cws->pid = wq_thread->pid;
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	if (list_empty(&workqueue_cpu_stat(cpu)->list))
-		cws->first_entry = true;
 	list_add_tail(&cws->list, &workqueue_cpu_stat(cpu)->list);
 	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
 }
@@ -152,7 +146,7 @@ static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu)
 	return ret;
 }
 
-static void *workqueue_stat_start(void)
+static void *workqueue_stat_start(struct tracer_stat *trace)
 {
 	int cpu;
 	void *ret = NULL;
@@ -191,16 +185,9 @@ static void *workqueue_stat_next(void *prev, int idx)
 static int workqueue_stat_show(struct seq_file *s, void *p)
 {
 	struct cpu_workqueue_stats *cws = p;
-	unsigned long flags;
-	int cpu = cws->cpu;
 	struct pid *pid;
 	struct task_struct *tsk;
 
-	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	if (&cws->list == workqueue_cpu_stat(cpu)->list.next)
-		seq_printf(s, "\n");
-	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
-
 	pid = find_get_pid(cws->pid);
 	if (pid) {
 		tsk = get_pid_task(pid, PIDTYPE_PID);
diff --git a/kernel/wait.c b/kernel/wait.c
index 42a2dbc181c8..ea7c3b4275cf 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -154,7 +154,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
 	if (!list_empty(&wait->task_list))
 		list_del_init(&wait->task_list);
 	else if (waitqueue_active(q))
-		__wake_up_common(q, mode, 1, 0, key);
+		__wake_up_locked_key(q, mode, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(abort_exclusive_wait);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f71fb2a08950..0668795d8818 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -33,7 +33,8 @@
 #include <linux/kallsyms.h>
 #include <linux/debug_locks.h>
 #include <linux/lockdep.h>
-#include <trace/workqueue.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
 
 /*
  * The per-CPU workqueue (if single thread, we always use the first
@@ -124,8 +125,6 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
 	return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK);
 }
 
-DEFINE_TRACE(workqueue_insertion);
-
 static void insert_work(struct cpu_workqueue_struct *cwq,
 			struct work_struct *work, struct list_head *head)
 {
@@ -262,8 +261,6 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 }
 EXPORT_SYMBOL_GPL(queue_delayed_work_on);
 
-DEFINE_TRACE(workqueue_execution);
-
 static void run_workqueue(struct cpu_workqueue_struct *cwq)
 {
 	spin_lock_irq(&cwq->lock);
@@ -753,8 +750,6 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu)
 	return cwq;
 }
 
-DEFINE_TRACE(workqueue_creation);
-
 static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
@@ -860,8 +855,6 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 }
 EXPORT_SYMBOL_GPL(__create_workqueue_key);
 
-DEFINE_TRACE(workqueue_destruction);
-
 static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
 {
 	/*
diff --git a/lib/Kconfig b/lib/Kconfig
index 8ade0a7a91e0..9960be04cbbe 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -10,6 +10,9 @@ menu "Library routines"
 config BITREVERSE
 	tristate
 
+config RATIONAL
+	boolean
+
 config GENERIC_FIND_FIRST_BIT
 	bool
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 6cdcf38f2da9..116a35051be6 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -336,6 +336,38 @@ config SLUB_STATS
 	  out which slabs are relevant to a particular load.
 	  Try running: slabinfo -DA
 
+config DEBUG_KMEMLEAK
+	bool "Kernel memory leak detector"
+	depends on DEBUG_KERNEL && EXPERIMENTAL && (X86 || ARM) && \
+		!MEMORY_HOTPLUG
+	select DEBUG_SLAB if SLAB
+	select SLUB_DEBUG if SLUB
+	select DEBUG_FS if SYSFS
+	select STACKTRACE if STACKTRACE_SUPPORT
+	select KALLSYMS
+	help
+	  Say Y here if you want to enable the memory leak
+	  detector. The memory allocation/freeing is traced in a way
+	  similar to the Boehm's conservative garbage collector, the
+	  difference being that the orphan objects are not freed but
+	  only shown in /sys/kernel/debug/kmemleak. Enabling this
+	  feature will introduce an overhead to memory
+	  allocations. See Documentation/kmemleak.txt for more
+	  details.
+
+	  In order to access the kmemleak file, debugfs needs to be
+	  mounted (usually at /sys/kernel/debug).
+
+config DEBUG_KMEMLEAK_TEST
+	tristate "Simple test for the kernel memory leak detector"
+	depends on DEBUG_KMEMLEAK
+	help
+	  Say Y or M here to build a test for the kernel memory leak
+	  detector. This option enables a module that explicitly leaks
+	  memory.
+
+	  If unsure, say N.
+
 config DEBUG_PREEMPT
 	bool "Debug preemptible kernel"
 	depends on DEBUG_KERNEL && PREEMPT && (TRACE_IRQFLAGS_SUPPORT || PPC64)
diff --git a/lib/Makefile b/lib/Makefile
index b6869e12e743..34c5c0e6222e 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -50,6 +50,7 @@ ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
 endif
 
 obj-$(CONFIG_BITREVERSE) += bitrev.o
+obj-$(CONFIG_RATIONAL)	+= rational.o
 obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
 obj-$(CONFIG_CRC16)	+= crc16.o
 obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o
diff --git a/lib/cpumask.c b/lib/cpumask.c
index eb23aaa0c7b8..7bb4142a502f 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -92,15 +92,8 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
  */
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 {
-	if (likely(slab_is_available()))
-		*mask = kmalloc_node(cpumask_size(), flags, node);
-	else {
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-		printk(KERN_ERR
-			"=> alloc_cpumask_var: kmalloc not available!\n");
-#endif
-		*mask = NULL;
-	}
+	*mask = kmalloc_node(cpumask_size(), flags, node);
+
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 	if (!*mask) {
 		printk(KERN_ERR "=> alloc_cpumask_var: failed!\n");
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 69da09a085a1..ad65fc0317d9 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -23,9 +23,11 @@
 #include <linux/dma-debug.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
+#include <linux/uaccess.h>
 #include <linux/device.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/slab.h>
 
@@ -85,6 +87,7 @@ static u32 show_num_errors = 1;
 
 static u32 num_free_entries;
 static u32 min_free_entries;
+static u32 nr_total_entries;
 
 /* number of preallocated entries requested by kernel cmdline */
 static u32 req_entries;
@@ -97,6 +100,16 @@ static struct dentry *show_all_errors_dent  __read_mostly;
 static struct dentry *show_num_errors_dent  __read_mostly;
 static struct dentry *num_free_entries_dent __read_mostly;
 static struct dentry *min_free_entries_dent __read_mostly;
+static struct dentry *filter_dent           __read_mostly;
+
+/* per-driver filter related state */
+
+#define NAME_MAX_LEN	64
+
+static char                  current_driver_name[NAME_MAX_LEN] __read_mostly;
+static struct device_driver *current_driver                    __read_mostly;
+
+static DEFINE_RWLOCK(driver_name_lock);
 
 static const char *type2name[4] = { "single", "page",
 				    "scather-gather", "coherent" };
@@ -104,6 +117,11 @@ static const char *type2name[4] = { "single", "page",
 static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
 				   "DMA_FROM_DEVICE", "DMA_NONE" };
 
+/* little merge helper - remove it after the merge window */
+#ifndef BUS_NOTIFY_UNBOUND_DRIVER
+#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
+#endif
+
 /*
  * The access to some variables in this macro is racy. We can't use atomic_t
  * here because all these variables are exported to debugfs. Some of them even
@@ -121,15 +139,54 @@ static inline void dump_entry_trace(struct dma_debug_entry *entry)
 {
 #ifdef CONFIG_STACKTRACE
 	if (entry) {
-		printk(KERN_WARNING "Mapped at:\n");
+		pr_warning("Mapped at:\n");
 		print_stack_trace(&entry->stacktrace, 0);
 	}
 #endif
 }
 
+static bool driver_filter(struct device *dev)
+{
+	struct device_driver *drv;
+	unsigned long flags;
+	bool ret;
+
+	/* driver filter off */
+	if (likely(!current_driver_name[0]))
+		return true;
+
+	/* driver filter on and initialized */
+	if (current_driver && dev->driver == current_driver)
+		return true;
+
+	if (current_driver || !current_driver_name[0])
+		return false;
+
+	/* driver filter on but not yet initialized */
+	drv = get_driver(dev->driver);
+	if (!drv)
+		return false;
+
+	/* lock to protect against change of current_driver_name */
+	read_lock_irqsave(&driver_name_lock, flags);
+
+	ret = false;
+	if (drv->name &&
+	    strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) {
+		current_driver = drv;
+		ret = true;
+	}
+
+	read_unlock_irqrestore(&driver_name_lock, flags);
+	put_driver(drv);
+
+	return ret;
+}
+
 #define err_printk(dev, entry, format, arg...) do {		\
 		error_count += 1;				\
-		if (show_all_errors || show_num_errors > 0) {	\
+		if (driver_filter(dev) &&			\
+		    (show_all_errors || show_num_errors > 0)) {	\
 			WARN(1, "%s %s: " format,		\
 			     dev_driver_string(dev),		\
 			     dev_name(dev) , ## arg);		\
@@ -185,15 +242,50 @@ static void put_hash_bucket(struct hash_bucket *bucket,
 static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
 						struct dma_debug_entry *ref)
 {
-	struct dma_debug_entry *entry;
+	struct dma_debug_entry *entry, *ret = NULL;
+	int matches = 0, match_lvl, last_lvl = 0;
 
 	list_for_each_entry(entry, &bucket->list, list) {
-		if ((entry->dev_addr == ref->dev_addr) &&
-		    (entry->dev == ref->dev))
+		if ((entry->dev_addr != ref->dev_addr) ||
+		    (entry->dev != ref->dev))
+			continue;
+
+		/*
+		 * Some drivers map the same physical address multiple
+		 * times. Without a hardware IOMMU this results in the
+		 * same device addresses being put into the dma-debug
+		 * hash multiple times too. This can result in false
+		 * positives being reported. Therfore we implement a
+		 * best-fit algorithm here which returns the entry from
+		 * the hash which fits best to the reference value
+		 * instead of the first-fit.
+		 */
+		matches += 1;
+		match_lvl = 0;
+		entry->size      == ref->size      ? ++match_lvl : match_lvl;
+		entry->type      == ref->type      ? ++match_lvl : match_lvl;
+		entry->direction == ref->direction ? ++match_lvl : match_lvl;
+
+		if (match_lvl == 3) {
+			/* perfect-fit - return the result */
 			return entry;
+		} else if (match_lvl > last_lvl) {
+			/*
+			 * We found an entry that fits better then the
+			 * previous one
+			 */
+			last_lvl = match_lvl;
+			ret      = entry;
+		}
 	}
 
-	return NULL;
+	/*
+	 * If we have multiple matches but no perfect-fit, just return
+	 * NULL.
+	 */
+	ret = (matches == 1) ? ret : NULL;
+
+	return ret;
 }
 
 /*
@@ -257,6 +349,21 @@ static void add_dma_entry(struct dma_debug_entry *entry)
 	put_hash_bucket(bucket, &flags);
 }
 
+static struct dma_debug_entry *__dma_entry_alloc(void)
+{
+	struct dma_debug_entry *entry;
+
+	entry = list_entry(free_entries.next, struct dma_debug_entry, list);
+	list_del(&entry->list);
+	memset(entry, 0, sizeof(*entry));
+
+	num_free_entries -= 1;
+	if (num_free_entries < min_free_entries)
+		min_free_entries = num_free_entries;
+
+	return entry;
+}
+
 /* struct dma_entry allocator
  *
  * The next two functions implement the allocator for
@@ -270,15 +377,12 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	spin_lock_irqsave(&free_entries_lock, flags);
 
 	if (list_empty(&free_entries)) {
-		printk(KERN_ERR "DMA-API: debugging out of memory "
-				"- disabling\n");
+		pr_err("DMA-API: debugging out of memory - disabling\n");
 		global_disable = true;
 		goto out;
 	}
 
-	entry = list_entry(free_entries.next, struct dma_debug_entry, list);
-	list_del(&entry->list);
-	memset(entry, 0, sizeof(*entry));
+	entry = __dma_entry_alloc();
 
 #ifdef CONFIG_STACKTRACE
 	entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
@@ -286,9 +390,6 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	entry->stacktrace.skip = 2;
 	save_stack_trace(&entry->stacktrace);
 #endif
-	num_free_entries -= 1;
-	if (num_free_entries < min_free_entries)
-		min_free_entries = num_free_entries;
 
 out:
 	spin_unlock_irqrestore(&free_entries_lock, flags);
@@ -310,6 +411,53 @@ static void dma_entry_free(struct dma_debug_entry *entry)
 	spin_unlock_irqrestore(&free_entries_lock, flags);
 }
 
+int dma_debug_resize_entries(u32 num_entries)
+{
+	int i, delta, ret = 0;
+	unsigned long flags;
+	struct dma_debug_entry *entry;
+	LIST_HEAD(tmp);
+
+	spin_lock_irqsave(&free_entries_lock, flags);
+
+	if (nr_total_entries < num_entries) {
+		delta = num_entries - nr_total_entries;
+
+		spin_unlock_irqrestore(&free_entries_lock, flags);
+
+		for (i = 0; i < delta; i++) {
+			entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+			if (!entry)
+				break;
+
+			list_add_tail(&entry->list, &tmp);
+		}
+
+		spin_lock_irqsave(&free_entries_lock, flags);
+
+		list_splice(&tmp, &free_entries);
+		nr_total_entries += i;
+		num_free_entries += i;
+	} else {
+		delta = nr_total_entries - num_entries;
+
+		for (i = 0; i < delta && !list_empty(&free_entries); i++) {
+			entry = __dma_entry_alloc();
+			kfree(entry);
+		}
+
+		nr_total_entries -= i;
+	}
+
+	if (nr_total_entries != num_entries)
+		ret = 1;
+
+	spin_unlock_irqrestore(&free_entries_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(dma_debug_resize_entries);
+
 /*
  * DMA-API debugging init code
  *
@@ -334,8 +482,7 @@ static int prealloc_memory(u32 num_entries)
 	num_free_entries = num_entries;
 	min_free_entries = num_entries;
 
-	printk(KERN_INFO "DMA-API: preallocated %d debug entries\n",
-			num_entries);
+	pr_info("DMA-API: preallocated %d debug entries\n", num_entries);
 
 	return 0;
 
@@ -349,11 +496,102 @@ out_err:
 	return -ENOMEM;
 }
 
+static ssize_t filter_read(struct file *file, char __user *user_buf,
+			   size_t count, loff_t *ppos)
+{
+	char buf[NAME_MAX_LEN + 1];
+	unsigned long flags;
+	int len;
+
+	if (!current_driver_name[0])
+		return 0;
+
+	/*
+	 * We can't copy to userspace directly because current_driver_name can
+	 * only be read under the driver_name_lock with irqs disabled. So
+	 * create a temporary copy first.
+	 */
+	read_lock_irqsave(&driver_name_lock, flags);
+	len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name);
+	read_unlock_irqrestore(&driver_name_lock, flags);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t filter_write(struct file *file, const char __user *userbuf,
+			    size_t count, loff_t *ppos)
+{
+	char buf[NAME_MAX_LEN];
+	unsigned long flags;
+	size_t len;
+	int i;
+
+	/*
+	 * We can't copy from userspace directly. Access to
+	 * current_driver_name is protected with a write_lock with irqs
+	 * disabled. Since copy_from_user can fault and may sleep we
+	 * need to copy to temporary buffer first
+	 */
+	len = min(count, (size_t)(NAME_MAX_LEN - 1));
+	if (copy_from_user(buf, userbuf, len))
+		return -EFAULT;
+
+	buf[len] = 0;
+
+	write_lock_irqsave(&driver_name_lock, flags);
+
+	/*
+	 * Now handle the string we got from userspace very carefully.
+	 * The rules are:
+	 *         - only use the first token we got
+	 *         - token delimiter is everything looking like a space
+	 *           character (' ', '\n', '\t' ...)
+	 *
+	 */
+	if (!isalnum(buf[0])) {
+		/*
+		 * If the first character userspace gave us is not
+		 * alphanumerical then assume the filter should be
+		 * switched off.
+		 */
+		if (current_driver_name[0])
+			pr_info("DMA-API: switching off dma-debug driver filter\n");
+		current_driver_name[0] = 0;
+		current_driver = NULL;
+		goto out_unlock;
+	}
+
+	/*
+	 * Now parse out the first token and use it as the name for the
+	 * driver to filter for.
+	 */
+	for (i = 0; i < NAME_MAX_LEN; ++i) {
+		current_driver_name[i] = buf[i];
+		if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
+			break;
+	}
+	current_driver_name[i] = 0;
+	current_driver = NULL;
+
+	pr_info("DMA-API: enable driver filter for driver [%s]\n",
+		current_driver_name);
+
+out_unlock:
+	write_unlock_irqrestore(&driver_name_lock, flags);
+
+	return count;
+}
+
+const struct file_operations filter_fops = {
+	.read  = filter_read,
+	.write = filter_write,
+};
+
 static int dma_debug_fs_init(void)
 {
 	dma_debug_dent = debugfs_create_dir("dma-api", NULL);
 	if (!dma_debug_dent) {
-		printk(KERN_ERR "DMA-API: can not create debugfs directory\n");
+		pr_err("DMA-API: can not create debugfs directory\n");
 		return -ENOMEM;
 	}
 
@@ -392,6 +630,11 @@ static int dma_debug_fs_init(void)
 	if (!min_free_entries_dent)
 		goto out_err;
 
+	filter_dent = debugfs_create_file("driver_filter", 0644,
+					  dma_debug_dent, NULL, &filter_fops);
+	if (!filter_dent)
+		goto out_err;
+
 	return 0;
 
 out_err:
@@ -400,9 +643,64 @@ out_err:
 	return -ENOMEM;
 }
 
+static int device_dma_allocations(struct device *dev)
+{
+	struct dma_debug_entry *entry;
+	unsigned long flags;
+	int count = 0, i;
+
+	local_irq_save(flags);
+
+	for (i = 0; i < HASH_SIZE; ++i) {
+		spin_lock(&dma_entry_hash[i].lock);
+		list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
+			if (entry->dev == dev)
+				count += 1;
+		}
+		spin_unlock(&dma_entry_hash[i].lock);
+	}
+
+	local_irq_restore(flags);
+
+	return count;
+}
+
+static int dma_debug_device_change(struct notifier_block *nb,
+				    unsigned long action, void *data)
+{
+	struct device *dev = data;
+	int count;
+
+
+	switch (action) {
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		count = device_dma_allocations(dev);
+		if (count == 0)
+			break;
+		err_printk(dev, NULL, "DMA-API: device driver has pending "
+				"DMA allocations while released from device "
+				"[count=%d]\n", count);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 void dma_debug_add_bus(struct bus_type *bus)
 {
-	/* FIXME: register notifier */
+	struct notifier_block *nb;
+
+	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
+	if (nb == NULL) {
+		pr_err("dma_debug_add_bus: out of memory\n");
+		return;
+	}
+
+	nb->notifier_call = dma_debug_device_change;
+
+	bus_register_notifier(bus, nb);
 }
 
 /*
@@ -421,8 +719,7 @@ void dma_debug_init(u32 num_entries)
 	}
 
 	if (dma_debug_fs_init() != 0) {
-		printk(KERN_ERR "DMA-API: error creating debugfs entries "
-				"- disabling\n");
+		pr_err("DMA-API: error creating debugfs entries - disabling\n");
 		global_disable = true;
 
 		return;
@@ -432,14 +729,15 @@ void dma_debug_init(u32 num_entries)
 		num_entries = req_entries;
 
 	if (prealloc_memory(num_entries) != 0) {
-		printk(KERN_ERR "DMA-API: debugging out of memory error "
-				"- disabled\n");
+		pr_err("DMA-API: debugging out of memory error - disabled\n");
 		global_disable = true;
 
 		return;
 	}
 
-	printk(KERN_INFO "DMA-API: debugging enabled by kernel config\n");
+	nr_total_entries = num_free_entries;
+
+	pr_info("DMA-API: debugging enabled by kernel config\n");
 }
 
 static __init int dma_debug_cmdline(char *str)
@@ -448,8 +746,7 @@ static __init int dma_debug_cmdline(char *str)
 		return -EINVAL;
 
 	if (strncmp(str, "off", 3) == 0) {
-		printk(KERN_INFO "DMA-API: debugging disabled on kernel "
-				 "command line\n");
+		pr_info("DMA-API: debugging disabled on kernel command line\n");
 		global_disable = true;
 	}
 
@@ -723,15 +1020,15 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		entry->type           = dma_debug_sg;
 		entry->dev            = dev;
 		entry->paddr          = sg_phys(s);
-		entry->size           = s->length;
-		entry->dev_addr       = s->dma_address;
+		entry->size           = sg_dma_len(s);
+		entry->dev_addr       = sg_dma_address(s);
 		entry->direction      = direction;
 		entry->sg_call_ents   = nents;
 		entry->sg_mapped_ents = mapped_ents;
 
 		if (!PageHighMem(sg_page(s))) {
 			check_for_stack(dev, sg_virt(s));
-			check_for_illegal_area(dev, sg_virt(s), s->length);
+			check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
 		}
 
 		add_dma_entry(entry);
@@ -739,13 +1036,33 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 }
 EXPORT_SYMBOL(debug_dma_map_sg);
 
+static int get_nr_mapped_entries(struct device *dev, struct scatterlist *s)
+{
+	struct dma_debug_entry *entry, ref;
+	struct hash_bucket *bucket;
+	unsigned long flags;
+	int mapped_ents;
+
+	ref.dev      = dev;
+	ref.dev_addr = sg_dma_address(s);
+	ref.size     = sg_dma_len(s),
+
+	bucket       = get_hash_bucket(&ref, &flags);
+	entry        = hash_bucket_find(bucket, &ref);
+	mapped_ents  = 0;
+
+	if (entry)
+		mapped_ents = entry->sg_mapped_ents;
+	put_hash_bucket(bucket, &flags);
+
+	return mapped_ents;
+}
+
 void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 			int nelems, int dir)
 {
-	struct dma_debug_entry *entry;
 	struct scatterlist *s;
 	int mapped_ents = 0, i;
-	unsigned long flags;
 
 	if (unlikely(global_disable))
 		return;
@@ -756,8 +1073,8 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 			.type           = dma_debug_sg,
 			.dev            = dev,
 			.paddr          = sg_phys(s),
-			.dev_addr       = s->dma_address,
-			.size           = s->length,
+			.dev_addr       = sg_dma_address(s),
+			.size           = sg_dma_len(s),
 			.direction      = dir,
 			.sg_call_ents   = 0,
 		};
@@ -765,14 +1082,9 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		if (mapped_ents && i >= mapped_ents)
 			break;
 
-		if (mapped_ents == 0) {
-			struct hash_bucket *bucket;
+		if (!i) {
 			ref.sg_call_ents = nelems;
-			bucket = get_hash_bucket(&ref, &flags);
-			entry = hash_bucket_find(bucket, &ref);
-			if (entry)
-				mapped_ents = entry->sg_mapped_ents;
-			put_hash_bucket(bucket, &flags);
+			mapped_ents = get_nr_mapped_entries(dev, s);
 		}
 
 		check_unmap(&ref);
@@ -874,14 +1186,20 @@ void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 			       int nelems, int direction)
 {
 	struct scatterlist *s;
-	int i;
+	int mapped_ents = 0, i;
 
 	if (unlikely(global_disable))
 		return;
 
 	for_each_sg(sg, s, nelems, i) {
-		check_sync(dev, s->dma_address, s->dma_length, 0,
-				direction, true);
+		if (!i)
+			mapped_ents = get_nr_mapped_entries(dev, s);
+
+		if (i >= mapped_ents)
+			break;
+
+		check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
+			   direction, true);
 	}
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
@@ -890,15 +1208,39 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 				  int nelems, int direction)
 {
 	struct scatterlist *s;
-	int i;
+	int mapped_ents = 0, i;
 
 	if (unlikely(global_disable))
 		return;
 
 	for_each_sg(sg, s, nelems, i) {
-		check_sync(dev, s->dma_address, s->dma_length, 0,
-				direction, false);
+		if (!i)
+			mapped_ents = get_nr_mapped_entries(dev, s);
+
+		if (i >= mapped_ents)
+			break;
+
+		check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
+			   direction, false);
 	}
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
 
+static int __init dma_debug_driver_setup(char *str)
+{
+	int i;
+
+	for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) {
+		current_driver_name[i] = *str;
+		if (*str == 0)
+			break;
+	}
+
+	if (current_driver_name[0])
+		pr_info("DMA-API: enable driver filter for driver [%s]\n",
+			current_driver_name);
+
+
+	return 1;
+}
+__setup("dma_debug_driver=", dma_debug_driver_setup);
diff --git a/lib/rational.c b/lib/rational.c
new file mode 100644
index 000000000000..b3c099b5478e
--- /dev/null
+++ b/lib/rational.c
@@ -0,0 +1,62 @@
+/*
+ * rational fractions
+ *
+ * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <os@emlix.com>
+ *
+ * helper functions when coping with rational numbers
+ */
+
+#include <linux/rational.h>
+
+/*
+ * calculate best rational approximation for a given fraction
+ * taking into account restricted register size, e.g. to find
+ * appropriate values for a pll with 5 bit denominator and
+ * 8 bit numerator register fields, trying to set up with a
+ * frequency ratio of 3.1415, one would say:
+ *
+ * rational_best_approximation(31415, 10000,
+ *		(1 << 8) - 1, (1 << 5) - 1, &n, &d);
+ *
+ * you may look at given_numerator as a fixed point number,
+ * with the fractional part size described in given_denominator.
+ *
+ * for theoretical background, see:
+ * http://en.wikipedia.org/wiki/Continued_fraction
+ */
+
+void rational_best_approximation(
+	unsigned long given_numerator, unsigned long given_denominator,
+	unsigned long max_numerator, unsigned long max_denominator,
+	unsigned long *best_numerator, unsigned long *best_denominator)
+{
+	unsigned long n, d, n0, d0, n1, d1;
+	n = given_numerator;
+	d = given_denominator;
+	n0 = d1 = 0;
+	n1 = d0 = 1;
+	for (;;) {
+		unsigned long t, a;
+		if ((n1 > max_numerator) || (d1 > max_denominator)) {
+			n1 = n0;
+			d1 = d0;
+			break;
+		}
+		if (d == 0)
+			break;
+		t = d;
+		a = n / d;
+		d = n % d;
+		n = t;
+		t = n0 + a * n1;
+		n0 = n1;
+		n1 = t;
+		t = d0 + a * d1;
+		d0 = d1;
+		d1 = t;
+	}
+	*best_numerator = n1;
+	*best_denominator = d1;
+}
+
+EXPORT_SYMBOL(rational_best_approximation);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 2b0b5a7d2ced..bffe6d7ef9d9 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -60,8 +60,8 @@ enum dma_sync_target {
 int swiotlb_force;
 
 /*
- * Used to do a quick range check in swiotlb_unmap_single and
- * swiotlb_sync_single_*, to see if the memory was in fact allocated by this
+ * Used to do a quick range check in unmap_single and
+ * sync_single_*, to see if the memory was in fact allocated by this
  * API.
  */
 static char *io_tlb_start, *io_tlb_end;
@@ -129,7 +129,7 @@ dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
 	return paddr;
 }
 
-phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr)
+phys_addr_t __weak swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
 {
 	return baddr;
 }
@@ -140,9 +140,15 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
 	return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
 }
 
-static void *swiotlb_bus_to_virt(dma_addr_t address)
+void * __weak swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t address)
 {
-	return phys_to_virt(swiotlb_bus_to_phys(address));
+	return phys_to_virt(swiotlb_bus_to_phys(hwdev, address));
+}
+
+int __weak swiotlb_arch_address_needs_mapping(struct device *hwdev,
+					       dma_addr_t addr, size_t size)
+{
+	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
 }
 
 int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
@@ -309,10 +315,10 @@ cleanup1:
 	return -ENOMEM;
 }
 
-static int
+static inline int
 address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
 {
-	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+	return swiotlb_arch_address_needs_mapping(hwdev, addr, size);
 }
 
 static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
@@ -341,7 +347,7 @@ static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
 		unsigned long flags;
 
 		while (size) {
-			sz = min(PAGE_SIZE - offset, size);
+			sz = min_t(size_t, PAGE_SIZE - offset, size);
 
 			local_irq_save(flags);
 			buffer = kmap_atomic(pfn_to_page(pfn),
@@ -476,7 +482,7 @@ found:
  * dma_addr is the kernel virtual address of the bounce buffer to unmap.
  */
 static void
-unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
+do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
 {
 	unsigned long flags;
 	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
@@ -560,7 +566,6 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 				   size)) {
 		/*
 		 * The allocated memory isn't reachable by the device.
-		 * Fall back on swiotlb_map_single().
 		 */
 		free_pages((unsigned long) ret, order);
 		ret = NULL;
@@ -568,9 +573,8 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	if (!ret) {
 		/*
 		 * We are either out of memory or the device can't DMA
-		 * to GFP_DMA memory; fall back on
-		 * swiotlb_map_single(), which will grab memory from
-		 * the lowest available address range.
+		 * to GFP_DMA memory; fall back on map_single(), which
+		 * will grab memory from the lowest available address range.
 		 */
 		ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
 		if (!ret)
@@ -587,7 +591,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		       (unsigned long long)dev_addr);
 
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-		unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
+		do_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
 		return NULL;
 	}
 	*dma_handle = dev_addr;
@@ -604,7 +608,7 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 		free_pages((unsigned long) vaddr, get_order(size));
 	else
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-		unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
+		do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
 }
 EXPORT_SYMBOL(swiotlb_free_coherent);
 
@@ -634,7 +638,7 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
  * physical address to use is returned.
  *
  * Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
+ * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
  */
 dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 			    unsigned long offset, size_t size,
@@ -642,18 +646,17 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 			    struct dma_attrs *attrs)
 {
 	phys_addr_t phys = page_to_phys(page) + offset;
-	void *ptr = page_address(page) + offset;
 	dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
 	void *map;
 
 	BUG_ON(dir == DMA_NONE);
 	/*
-	 * If the pointer passed in happens to be in the device's DMA window,
+	 * If the address happens to be in the device's DMA window,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
 	if (!address_needs_mapping(dev, dev_addr, size) &&
-	    !range_needs_mapping(virt_to_phys(ptr), size))
+	    !range_needs_mapping(phys, size))
 		return dev_addr;
 
 	/*
@@ -679,23 +682,35 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page);
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_single call.  All
+ * match what was provided for in a previous swiotlb_map_page call.  All
  * other usages are undefined.
  *
  * After this call, reads by the cpu to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
+static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+			 size_t size, int dir)
+{
+	char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	if (is_swiotlb_buffer(dma_addr)) {
+		do_unmap_single(hwdev, dma_addr, size, dir);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	dma_mark_clean(dma_addr, size);
+}
+
 void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
 			size_t size, enum dma_data_direction dir,
 			struct dma_attrs *attrs)
 {
-	char *dma_addr = swiotlb_bus_to_virt(dev_addr);
-
-	BUG_ON(dir == DMA_NONE);
-	if (is_swiotlb_buffer(dma_addr))
-		unmap_single(hwdev, dma_addr, size, dir);
-	else if (dir == DMA_FROM_DEVICE)
-		dma_mark_clean(dma_addr, size);
+	unmap_single(hwdev, dev_addr, size, dir);
 }
 EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
 
@@ -703,7 +718,7 @@ EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
  * Make physical memory consistent for a single streaming mode DMA translation
  * after a transfer.
  *
- * If you perform a swiotlb_map_single() but wish to interrogate the buffer
+ * If you perform a swiotlb_map_page() but wish to interrogate the buffer
  * using the cpu, yet do not wish to teardown the dma mapping, you must
  * call this function before doing so.  At the next point you give the dma
  * address back to the card, you must first perform a
@@ -713,13 +728,19 @@ static void
 swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 		    size_t size, int dir, int target)
 {
-	char *dma_addr = swiotlb_bus_to_virt(dev_addr);
+	char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
-	if (is_swiotlb_buffer(dma_addr))
+
+	if (is_swiotlb_buffer(dma_addr)) {
 		sync_single(hwdev, dma_addr, size, dir, target);
-	else if (dir == DMA_FROM_DEVICE)
-		dma_mark_clean(dma_addr, size);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	dma_mark_clean(dma_addr, size);
 }
 
 void
@@ -746,13 +767,7 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
 			  unsigned long offset, size_t size,
 			  int dir, int target)
 {
-	char *dma_addr = swiotlb_bus_to_virt(dev_addr) + offset;
-
-	BUG_ON(dir == DMA_NONE);
-	if (is_swiotlb_buffer(dma_addr))
-		sync_single(hwdev, dma_addr, size, dir, target);
-	else if (dir == DMA_FROM_DEVICE)
-		dma_mark_clean(dma_addr, size);
+	swiotlb_sync_single(hwdev, dev_addr + offset, size, dir, target);
 }
 
 void
@@ -777,7 +792,7 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
 
 /*
  * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the above swiotlb_map_single
+ * This is the scatter-gather version of the above swiotlb_map_page
  * interface.  Here the scatter gather list elements are each tagged with the
  * appropriate dma address and length.  They are obtained via
  * sg_dma_{address,length}(SG).
@@ -788,7 +803,7 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
  *       The routine returns the number of addr/length pairs actually
  *       used, at most nents.
  *
- * Device ownership issues as mentioned above for swiotlb_map_single are the
+ * Device ownership issues as mentioned above for swiotlb_map_page are the
  * same here.
  */
 int
@@ -836,7 +851,7 @@ EXPORT_SYMBOL(swiotlb_map_sg);
 
 /*
  * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_single() above.
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
  */
 void
 swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
@@ -847,13 +862,9 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 
 	BUG_ON(dir == DMA_NONE);
 
-	for_each_sg(sgl, sg, nelems, i) {
-		if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg)))
-			unmap_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
-				     sg->dma_length, dir);
-		else if (dir == DMA_FROM_DEVICE)
-			dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
-	}
+	for_each_sg(sgl, sg, nelems, i)
+		unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);
+
 }
 EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
 
@@ -879,15 +890,9 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
 	struct scatterlist *sg;
 	int i;
 
-	BUG_ON(dir == DMA_NONE);
-
-	for_each_sg(sgl, sg, nelems, i) {
-		if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg)))
-			sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
+	for_each_sg(sgl, sg, nelems, i)
+		swiotlb_sync_single(hwdev, sg->dma_address,
 				    sg->dma_length, dir, target);
-		else if (dir == DMA_FROM_DEVICE)
-			dma_mark_clean(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
-	}
 }
 
 void
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 7536acea135b..756ccafa9cec 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -408,6 +408,8 @@ enum format_type {
 	FORMAT_TYPE_LONG_LONG,
 	FORMAT_TYPE_ULONG,
 	FORMAT_TYPE_LONG,
+	FORMAT_TYPE_UBYTE,
+	FORMAT_TYPE_BYTE,
 	FORMAT_TYPE_USHORT,
 	FORMAT_TYPE_SHORT,
 	FORMAT_TYPE_UINT,
@@ -573,12 +575,15 @@ static char *string(char *buf, char *end, char *s, struct printf_spec spec)
 }
 
 static char *symbol_string(char *buf, char *end, void *ptr,
-				struct printf_spec spec)
+				struct printf_spec spec, char ext)
 {
 	unsigned long value = (unsigned long) ptr;
 #ifdef CONFIG_KALLSYMS
 	char sym[KSYM_SYMBOL_LEN];
-	sprint_symbol(sym, value);
+	if (ext != 'f')
+		sprint_symbol(sym, value);
+	else
+		kallsyms_lookup(value, NULL, NULL, NULL, sym);
 	return string(buf, end, sym, spec);
 #else
 	spec.field_width = 2*sizeof(void *);
@@ -690,7 +695,8 @@ static char *ip4_addr_string(char *buf, char *end, u8 *addr,
  *
  * Right now we handle:
  *
- * - 'F' For symbolic function descriptor pointers
+ * - 'F' For symbolic function descriptor pointers with offset
+ * - 'f' For simple symbolic function names without offset
  * - 'S' For symbolic direct pointers
  * - 'R' For a struct resource pointer, it prints the range of
  *       addresses (not the name nor the flags)
@@ -713,10 +719,11 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 
 	switch (*fmt) {
 	case 'F':
+	case 'f':
 		ptr = dereference_function_descriptor(ptr);
 		/* Fallthrough */
 	case 'S':
-		return symbol_string(buf, end, ptr, spec);
+		return symbol_string(buf, end, ptr, spec, *fmt);
 	case 'R':
 		return resource_string(buf, end, ptr, spec);
 	case 'm':
@@ -853,11 +860,15 @@ qualifier:
 	spec->qualifier = -1;
 	if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' ||
 	    *fmt == 'Z' || *fmt == 'z' || *fmt == 't') {
-		spec->qualifier = *fmt;
-		++fmt;
-		if (spec->qualifier == 'l' && *fmt == 'l') {
-			spec->qualifier = 'L';
-			++fmt;
+		spec->qualifier = *fmt++;
+		if (unlikely(spec->qualifier == *fmt)) {
+			if (spec->qualifier == 'l') {
+				spec->qualifier = 'L';
+				++fmt;
+			} else if (spec->qualifier == 'h') {
+				spec->qualifier = 'H';
+				++fmt;
+			}
 		}
 	}
 
@@ -919,6 +930,11 @@ qualifier:
 		spec->type = FORMAT_TYPE_SIZE_T;
 	} else if (spec->qualifier == 't') {
 		spec->type = FORMAT_TYPE_PTRDIFF;
+	} else if (spec->qualifier == 'H') {
+		if (spec->flags & SIGN)
+			spec->type = FORMAT_TYPE_BYTE;
+		else
+			spec->type = FORMAT_TYPE_UBYTE;
 	} else if (spec->qualifier == 'h') {
 		if (spec->flags & SIGN)
 			spec->type = FORMAT_TYPE_SHORT;
@@ -943,7 +959,8 @@ qualifier:
  *
  * This function follows C99 vsnprintf, but has some extensions:
  * %pS output the name of a text symbol
- * %pF output the name of a function pointer
+ * %pF output the name of a function pointer with its offset
+ * %pf output the name of a function pointer without its offset
  * %pR output the address range in a struct resource
  *
  * The return value is the number of characters which would
@@ -1087,6 +1104,12 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 			case FORMAT_TYPE_PTRDIFF:
 				num = va_arg(args, ptrdiff_t);
 				break;
+			case FORMAT_TYPE_UBYTE:
+				num = (unsigned char) va_arg(args, int);
+				break;
+			case FORMAT_TYPE_BYTE:
+				num = (signed char) va_arg(args, int);
+				break;
 			case FORMAT_TYPE_USHORT:
 				num = (unsigned short) va_arg(args, int);
 				break;
@@ -1363,6 +1386,10 @@ do {									\
 			case FORMAT_TYPE_PTRDIFF:
 				save_arg(ptrdiff_t);
 				break;
+			case FORMAT_TYPE_UBYTE:
+			case FORMAT_TYPE_BYTE:
+				save_arg(char);
+				break;
 			case FORMAT_TYPE_USHORT:
 			case FORMAT_TYPE_SHORT:
 				save_arg(short);
@@ -1391,7 +1418,8 @@ EXPORT_SYMBOL_GPL(vbin_printf);
  *
  * The format follows C99 vsnprintf, but has some extensions:
  * %pS output the name of a text symbol
- * %pF output the name of a function pointer
+ * %pF output the name of a function pointer with its offset
+ * %pf output the name of a function pointer without its offset
  * %pR output the address range in a struct resource
  * %n is ignored
  *
@@ -1538,6 +1566,12 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf)
 			case FORMAT_TYPE_PTRDIFF:
 				num = get_arg(ptrdiff_t);
 				break;
+			case FORMAT_TYPE_UBYTE:
+				num = get_arg(unsigned char);
+				break;
+			case FORMAT_TYPE_BYTE:
+				num = get_arg(signed char);
+				break;
 			case FORMAT_TYPE_USHORT:
 				num = get_arg(unsigned short);
 				break;
diff --git a/mm/Kconfig b/mm/Kconfig
index c2b57d81e153..71830ba7b986 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -226,6 +226,25 @@ config HAVE_MLOCKED_PAGE_BIT
 config MMU_NOTIFIER
 	bool
 
+config DEFAULT_MMAP_MIN_ADDR
+        int "Low address space to protect from user allocation"
+        default 4096
+        help
+	  This is the portion of low virtual memory which should be protected
+	  from userspace allocation.  Keeping a user from writing to low pages
+	  can help reduce the impact of kernel NULL pointer bugs.
+
+	  For most ia64, ppc64 and x86 users with lots of address space
+	  a value of 65536 is reasonable and should cause no problems.
+	  On arm and other archs it should not be higher than 32768.
+	  Programs which use vm86 functionality would either need additional
+	  permissions from either the LSM or the capabilities module or have
+	  this protection disabled.
+
+	  This value can be changed after boot using the
+	  /proc/sys/vm/mmap_min_addr tunable.
+
+
 config NOMMU_INITIAL_TRIM_EXCESS
 	int "Turn on mmap() excess space trimming before booting"
 	depends on !MMU
diff --git a/mm/Makefile b/mm/Makefile
index ec73c68b6015..e89acb090b4d 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -38,3 +38,5 @@ obj-$(CONFIG_SMP) += allocpercpu.o
 endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
+obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
+obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
diff --git a/mm/bootmem.c b/mm/bootmem.c
index daf92713f7de..282df0a09e6f 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -532,6 +532,9 @@ static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata,
 					unsigned long size, unsigned long align,
 					unsigned long goal, unsigned long limit)
 {
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc(size, GFP_NOWAIT);
+
 #ifdef CONFIG_HAVE_ARCH_BOOTMEM
 	bootmem_data_t *p_bdata;
 
@@ -662,6 +665,9 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
 void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
 	return ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
 }
 
@@ -693,6 +699,9 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
 {
 	void *ptr;
 
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
 	ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0);
 	if (ptr)
 		return ptr;
@@ -745,6 +754,9 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
 {
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
 	return ___alloc_bootmem_node(pgdat->bdata, size, align,
 				goal, ARCH_LOW_ADDRESS_LIMIT);
 }
diff --git a/mm/bounce.c b/mm/bounce.c
index e590272fe7a8..4ebe3ea83795 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -14,16 +14,15 @@
 #include <linux/hash.h>
 #include <linux/highmem.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
 #include <asm/tlbflush.h>
 
+#include <trace/events/block.h>
+
 #define POOL_SIZE	64
 #define ISA_POOL_SIZE	16
 
 static mempool_t *page_pool, *isa_page_pool;
 
-DEFINE_TRACE(block_bio_bounce);
-
 #ifdef CONFIG_HIGHMEM
 static __init int init_emergency_pool(void)
 {
@@ -192,7 +191,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 		/*
 		 * is destination page below bounce pfn?
 		 */
-		if (page_to_pfn(page) <= q->bounce_pfn)
+		if (page_to_pfn(page) <= queue_bounce_pfn(q))
 			continue;
 
 		/*
@@ -284,7 +283,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	 * don't waste time iterating over bio segments
 	 */
 	if (!(q->bounce_gfp & GFP_DMA)) {
-		if (q->bounce_pfn >= blk_max_pfn)
+		if (queue_bounce_pfn(q) >= blk_max_pfn)
 			return;
 		pool = page_pool;
 	} else {
diff --git a/mm/kmemleak-test.c b/mm/kmemleak-test.c
new file mode 100644
index 000000000000..d5292fc6f523
--- /dev/null
+++ b/mm/kmemleak-test.c
@@ -0,0 +1,111 @@
+/*
+ * mm/kmemleak-test.c
+ *
+ * Copyright (C) 2008 ARM Limited
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/list.h>
+#include <linux/percpu.h>
+#include <linux/fdtable.h>
+
+#include <linux/kmemleak.h>
+
+struct test_node {
+	long header[25];
+	struct list_head list;
+	long footer[25];
+};
+
+static LIST_HEAD(test_list);
+static DEFINE_PER_CPU(void *, test_pointer);
+
+/*
+ * Some very simple testing. This function needs to be extended for
+ * proper testing.
+ */
+static int __init kmemleak_test_init(void)
+{
+	struct test_node *elem;
+	int i;
+
+	printk(KERN_INFO "Kmemleak testing\n");
+
+	/* make some orphan objects */
+	pr_info("kmemleak: kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL));
+	pr_info("kmemleak: kmalloc(32) = %p\n", kmalloc(32, GFP_KERNEL));
+	pr_info("kmemleak: kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL));
+	pr_info("kmemleak: kmalloc(1024) = %p\n", kmalloc(1024, GFP_KERNEL));
+	pr_info("kmemleak: kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL));
+	pr_info("kmemleak: kmalloc(2048) = %p\n", kmalloc(2048, GFP_KERNEL));
+	pr_info("kmemleak: kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL));
+	pr_info("kmemleak: kmalloc(4096) = %p\n", kmalloc(4096, GFP_KERNEL));
+#ifndef CONFIG_MODULES
+	pr_info("kmemleak: kmem_cache_alloc(files_cachep) = %p\n",
+		kmem_cache_alloc(files_cachep, GFP_KERNEL));
+	pr_info("kmemleak: kmem_cache_alloc(files_cachep) = %p\n",
+		kmem_cache_alloc(files_cachep, GFP_KERNEL));
+#endif
+	pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64));
+	pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64));
+	pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64));
+	pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64));
+	pr_info("kmemleak: vmalloc(64) = %p\n", vmalloc(64));
+
+	/*
+	 * Add elements to a list. They should only appear as orphan
+	 * after the module is removed.
+	 */
+	for (i = 0; i < 10; i++) {
+		elem = kmalloc(sizeof(*elem), GFP_KERNEL);
+		pr_info("kmemleak: kmalloc(sizeof(*elem)) = %p\n", elem);
+		if (!elem)
+			return -ENOMEM;
+		memset(elem, 0, sizeof(*elem));
+		INIT_LIST_HEAD(&elem->list);
+
+		list_add_tail(&elem->list, &test_list);
+	}
+
+	for_each_possible_cpu(i) {
+		per_cpu(test_pointer, i) = kmalloc(129, GFP_KERNEL);
+		pr_info("kmemleak: kmalloc(129) = %p\n",
+			per_cpu(test_pointer, i));
+	}
+
+	return 0;
+}
+module_init(kmemleak_test_init);
+
+static void __exit kmemleak_test_exit(void)
+{
+	struct test_node *elem, *tmp;
+
+	/*
+	 * Remove the list elements without actually freeing the
+	 * memory.
+	 */
+	list_for_each_entry_safe(elem, tmp, &test_list, list)
+		list_del(&elem->list);
+}
+module_exit(kmemleak_test_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
new file mode 100644
index 000000000000..58ec86c9e58a
--- /dev/null
+++ b/mm/kmemleak.c
@@ -0,0 +1,1498 @@
+/*
+ * mm/kmemleak.c
+ *
+ * Copyright (C) 2008 ARM Limited
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ *
+ * For more information on the algorithm and kmemleak usage, please see
+ * Documentation/kmemleak.txt.
+ *
+ * Notes on locking
+ * ----------------
+ *
+ * The following locks and mutexes are used by kmemleak:
+ *
+ * - kmemleak_lock (rwlock): protects the object_list modifications and
+ *   accesses to the object_tree_root. The object_list is the main list
+ *   holding the metadata (struct kmemleak_object) for the allocated memory
+ *   blocks. The object_tree_root is a priority search tree used to look-up
+ *   metadata based on a pointer to the corresponding memory block.  The
+ *   kmemleak_object structures are added to the object_list and
+ *   object_tree_root in the create_object() function called from the
+ *   kmemleak_alloc() callback and removed in delete_object() called from the
+ *   kmemleak_free() callback
+ * - kmemleak_object.lock (spinlock): protects a kmemleak_object. Accesses to
+ *   the metadata (e.g. count) are protected by this lock. Note that some
+ *   members of this structure may be protected by other means (atomic or
+ *   kmemleak_lock). This lock is also held when scanning the corresponding
+ *   memory block to avoid the kernel freeing it via the kmemleak_free()
+ *   callback. This is less heavyweight than holding a global lock like
+ *   kmemleak_lock during scanning
+ * - scan_mutex (mutex): ensures that only one thread may scan the memory for
+ *   unreferenced objects at a time. The gray_list contains the objects which
+ *   are already referenced or marked as false positives and need to be
+ *   scanned. This list is only modified during a scanning episode when the
+ *   scan_mutex is held. At the end of a scan, the gray_list is always empty.
+ *   Note that the kmemleak_object.use_count is incremented when an object is
+ *   added to the gray_list and therefore cannot be freed
+ * - kmemleak_mutex (mutex): prevents multiple users of the "kmemleak" debugfs
+ *   file together with modifications to the memory scanning parameters
+ *   including the scan_thread pointer
+ *
+ * The kmemleak_object structures have a use_count incremented or decremented
+ * using the get_object()/put_object() functions. When the use_count becomes
+ * 0, this count can no longer be incremented and put_object() schedules the
+ * kmemleak_object freeing via an RCU callback. All calls to the get_object()
+ * function must be protected by rcu_read_lock() to avoid accessing a freed
+ * structure.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/sched.h>
+#include <linux/jiffies.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/prio_tree.h>
+#include <linux/gfp.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/cpumask.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/rcupdate.h>
+#include <linux/stacktrace.h>
+#include <linux/cache.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/mmzone.h>
+#include <linux/slab.h>
+#include <linux/thread_info.h>
+#include <linux/err.h>
+#include <linux/uaccess.h>
+#include <linux/string.h>
+#include <linux/nodemask.h>
+#include <linux/mm.h>
+
+#include <asm/sections.h>
+#include <asm/processor.h>
+#include <asm/atomic.h>
+
+#include <linux/kmemleak.h>
+
+/*
+ * Kmemleak configuration and common defines.
+ */
+#define MAX_TRACE		16	/* stack trace length */
+#define REPORTS_NR		50	/* maximum number of reported leaks */
+#define MSECS_MIN_AGE		5000	/* minimum object age for reporting */
+#define MSECS_SCAN_YIELD	10	/* CPU yielding period */
+#define SECS_FIRST_SCAN		60	/* delay before the first scan */
+#define SECS_SCAN_WAIT		600	/* subsequent auto scanning delay */
+
+#define BYTES_PER_POINTER	sizeof(void *)
+
+/* scanning area inside a memory block */
+struct kmemleak_scan_area {
+	struct hlist_node node;
+	unsigned long offset;
+	size_t length;
+};
+
+/*
+ * Structure holding the metadata for each allocated memory block.
+ * Modifications to such objects should be made while holding the
+ * object->lock. Insertions or deletions from object_list, gray_list or
+ * tree_node are already protected by the corresponding locks or mutex (see
+ * the notes on locking above). These objects are reference-counted
+ * (use_count) and freed using the RCU mechanism.
+ */
+struct kmemleak_object {
+	spinlock_t lock;
+	unsigned long flags;		/* object status flags */
+	struct list_head object_list;
+	struct list_head gray_list;
+	struct prio_tree_node tree_node;
+	struct rcu_head rcu;		/* object_list lockless traversal */
+	/* object usage count; object freed when use_count == 0 */
+	atomic_t use_count;
+	unsigned long pointer;
+	size_t size;
+	/* minimum number of a pointers found before it is considered leak */
+	int min_count;
+	/* the total number of pointers found pointing to this object */
+	int count;
+	/* memory ranges to be scanned inside an object (empty for all) */
+	struct hlist_head area_list;
+	unsigned long trace[MAX_TRACE];
+	unsigned int trace_len;
+	unsigned long jiffies;		/* creation timestamp */
+	pid_t pid;			/* pid of the current task */
+	char comm[TASK_COMM_LEN];	/* executable name */
+};
+
+/* flag representing the memory block allocation status */
+#define OBJECT_ALLOCATED	(1 << 0)
+/* flag set after the first reporting of an unreference object */
+#define OBJECT_REPORTED		(1 << 1)
+/* flag set to not scan the object */
+#define OBJECT_NO_SCAN		(1 << 2)
+
+/* the list of all allocated objects */
+static LIST_HEAD(object_list);
+/* the list of gray-colored objects (see color_gray comment below) */
+static LIST_HEAD(gray_list);
+/* prio search tree for object boundaries */
+static struct prio_tree_root object_tree_root;
+/* rw_lock protecting the access to object_list and prio_tree_root */
+static DEFINE_RWLOCK(kmemleak_lock);
+
+/* allocation caches for kmemleak internal data */
+static struct kmem_cache *object_cache;
+static struct kmem_cache *scan_area_cache;
+
+/* set if tracing memory operations is enabled */
+static atomic_t kmemleak_enabled = ATOMIC_INIT(0);
+/* set in the late_initcall if there were no errors */
+static atomic_t kmemleak_initialized = ATOMIC_INIT(0);
+/* enables or disables early logging of the memory operations */
+static atomic_t kmemleak_early_log = ATOMIC_INIT(1);
+/* set if a fata kmemleak error has occurred */
+static atomic_t kmemleak_error = ATOMIC_INIT(0);
+
+/* minimum and maximum address that may be valid pointers */
+static unsigned long min_addr = ULONG_MAX;
+static unsigned long max_addr;
+
+/* used for yielding the CPU to other tasks during scanning */
+static unsigned long next_scan_yield;
+static struct task_struct *scan_thread;
+static unsigned long jiffies_scan_yield;
+static unsigned long jiffies_min_age;
+/* delay between automatic memory scannings */
+static signed long jiffies_scan_wait;
+/* enables or disables the task stacks scanning */
+static int kmemleak_stack_scan;
+/* mutex protecting the memory scanning */
+static DEFINE_MUTEX(scan_mutex);
+/* mutex protecting the access to the /sys/kernel/debug/kmemleak file */
+static DEFINE_MUTEX(kmemleak_mutex);
+
+/* number of leaks reported (for limitation purposes) */
+static int reported_leaks;
+
+/*
+ * Early object allocation/freeing logging. Kkmemleak is initialized after the
+ * kernel allocator. However, both the kernel allocator and kmemleak may
+ * allocate memory blocks which need to be tracked. Kkmemleak defines an
+ * arbitrary buffer to hold the allocation/freeing information before it is
+ * fully initialized.
+ */
+
+/* kmemleak operation type for early logging */
+enum {
+	KMEMLEAK_ALLOC,
+	KMEMLEAK_FREE,
+	KMEMLEAK_NOT_LEAK,
+	KMEMLEAK_IGNORE,
+	KMEMLEAK_SCAN_AREA,
+	KMEMLEAK_NO_SCAN
+};
+
+/*
+ * Structure holding the information passed to kmemleak callbacks during the
+ * early logging.
+ */
+struct early_log {
+	int op_type;			/* kmemleak operation type */
+	const void *ptr;		/* allocated/freed memory block */
+	size_t size;			/* memory block size */
+	int min_count;			/* minimum reference count */
+	unsigned long offset;		/* scan area offset */
+	size_t length;			/* scan area length */
+};
+
+/* early logging buffer and current position */
+static struct early_log early_log[200];
+static int crt_early_log;
+
+static void kmemleak_disable(void);
+
+/*
+ * Print a warning and dump the stack trace.
+ */
+#define kmemleak_warn(x...)	do {	\
+	pr_warning(x);			\
+	dump_stack();			\
+} while (0)
+
+/*
+ * Macro invoked when a serious kmemleak condition occured and cannot be
+ * recovered from. Kkmemleak will be disabled and further allocation/freeing
+ * tracing no longer available.
+ */
+#define kmemleak_panic(x...)	do {	\
+	kmemleak_warn(x);		\
+	kmemleak_disable();		\
+} while (0)
+
+/*
+ * Object colors, encoded with count and min_count:
+ * - white - orphan object, not enough references to it (count < min_count)
+ * - gray  - not orphan, not marked as false positive (min_count == 0) or
+ *		sufficient references to it (count >= min_count)
+ * - black - ignore, it doesn't contain references (e.g. text section)
+ *		(min_count == -1). No function defined for this color.
+ * Newly created objects don't have any color assigned (object->count == -1)
+ * before the next memory scan when they become white.
+ */
+static int color_white(const struct kmemleak_object *object)
+{
+	return object->count != -1 && object->count < object->min_count;
+}
+
+static int color_gray(const struct kmemleak_object *object)
+{
+	return object->min_count != -1 && object->count >= object->min_count;
+}
+
+/*
+ * Objects are considered referenced if their color is gray and they have not
+ * been deleted.
+ */
+static int referenced_object(struct kmemleak_object *object)
+{
+	return (object->flags & OBJECT_ALLOCATED) && color_gray(object);
+}
+
+/*
+ * Objects are considered unreferenced only if their color is white, they have
+ * not be deleted and have a minimum age to avoid false positives caused by
+ * pointers temporarily stored in CPU registers.
+ */
+static int unreferenced_object(struct kmemleak_object *object)
+{
+	return (object->flags & OBJECT_ALLOCATED) && color_white(object) &&
+		time_is_before_eq_jiffies(object->jiffies + jiffies_min_age);
+}
+
+/*
+ * Printing of the (un)referenced objects information, either to the seq file
+ * or to the kernel log. The print_referenced/print_unreferenced functions
+ * must be called with the object->lock held.
+ */
+#define print_helper(seq, x...)	do {	\
+	struct seq_file *s = (seq);	\
+	if (s)				\
+		seq_printf(s, x);	\
+	else				\
+		pr_info(x);		\
+} while (0)
+
+static void print_referenced(struct kmemleak_object *object)
+{
+	pr_info("kmemleak: referenced object 0x%08lx (size %zu)\n",
+		object->pointer, object->size);
+}
+
+static void print_unreferenced(struct seq_file *seq,
+			       struct kmemleak_object *object)
+{
+	int i;
+
+	print_helper(seq, "kmemleak: unreferenced object 0x%08lx (size %zu):\n",
+		     object->pointer, object->size);
+	print_helper(seq, "  comm \"%s\", pid %d, jiffies %lu\n",
+		     object->comm, object->pid, object->jiffies);
+	print_helper(seq, "  backtrace:\n");
+
+	for (i = 0; i < object->trace_len; i++) {
+		void *ptr = (void *)object->trace[i];
+		print_helper(seq, "    [<%p>] %pS\n", ptr, ptr);
+	}
+}
+
+/*
+ * Print the kmemleak_object information. This function is used mainly for
+ * debugging special cases when kmemleak operations. It must be called with
+ * the object->lock held.
+ */
+static void dump_object_info(struct kmemleak_object *object)
+{
+	struct stack_trace trace;
+
+	trace.nr_entries = object->trace_len;
+	trace.entries = object->trace;
+
+	pr_notice("kmemleak: Object 0x%08lx (size %zu):\n",
+		  object->tree_node.start, object->size);
+	pr_notice("  comm \"%s\", pid %d, jiffies %lu\n",
+		  object->comm, object->pid, object->jiffies);
+	pr_notice("  min_count = %d\n", object->min_count);
+	pr_notice("  count = %d\n", object->count);
+	pr_notice("  backtrace:\n");
+	print_stack_trace(&trace, 4);
+}
+
+/*
+ * Look-up a memory block metadata (kmemleak_object) in the priority search
+ * tree based on a pointer value. If alias is 0, only values pointing to the
+ * beginning of the memory block are allowed. The kmemleak_lock must be held
+ * when calling this function.
+ */
+static struct kmemleak_object *lookup_object(unsigned long ptr, int alias)
+{
+	struct prio_tree_node *node;
+	struct prio_tree_iter iter;
+	struct kmemleak_object *object;
+
+	prio_tree_iter_init(&iter, &object_tree_root, ptr, ptr);
+	node = prio_tree_next(&iter);
+	if (node) {
+		object = prio_tree_entry(node, struct kmemleak_object,
+					 tree_node);
+		if (!alias && object->pointer != ptr) {
+			kmemleak_warn("kmemleak: Found object by alias");
+			object = NULL;
+		}
+	} else
+		object = NULL;
+
+	return object;
+}
+
+/*
+ * Increment the object use_count. Return 1 if successful or 0 otherwise. Note
+ * that once an object's use_count reached 0, the RCU freeing was already
+ * registered and the object should no longer be used. This function must be
+ * called under the protection of rcu_read_lock().
+ */
+static int get_object(struct kmemleak_object *object)
+{
+	return atomic_inc_not_zero(&object->use_count);
+}
+
+/*
+ * RCU callback to free a kmemleak_object.
+ */
+static void free_object_rcu(struct rcu_head *rcu)
+{
+	struct hlist_node *elem, *tmp;
+	struct kmemleak_scan_area *area;
+	struct kmemleak_object *object =
+		container_of(rcu, struct kmemleak_object, rcu);
+
+	/*
+	 * Once use_count is 0 (guaranteed by put_object), there is no other
+	 * code accessing this object, hence no need for locking.
+	 */
+	hlist_for_each_entry_safe(area, elem, tmp, &object->area_list, node) {
+		hlist_del(elem);
+		kmem_cache_free(scan_area_cache, area);
+	}
+	kmem_cache_free(object_cache, object);
+}
+
+/*
+ * Decrement the object use_count. Once the count is 0, free the object using
+ * an RCU callback. Since put_object() may be called via the kmemleak_free() ->
+ * delete_object() path, the delayed RCU freeing ensures that there is no
+ * recursive call to the kernel allocator. Lock-less RCU object_list traversal
+ * is also possible.
+ */
+static void put_object(struct kmemleak_object *object)
+{
+	if (!atomic_dec_and_test(&object->use_count))
+		return;
+
+	/* should only get here after delete_object was called */
+	WARN_ON(object->flags & OBJECT_ALLOCATED);
+
+	call_rcu(&object->rcu, free_object_rcu);
+}
+
+/*
+ * Look up an object in the prio search tree and increase its use_count.
+ */
+static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias)
+{
+	unsigned long flags;
+	struct kmemleak_object *object = NULL;
+
+	rcu_read_lock();
+	read_lock_irqsave(&kmemleak_lock, flags);
+	if (ptr >= min_addr && ptr < max_addr)
+		object = lookup_object(ptr, alias);
+	read_unlock_irqrestore(&kmemleak_lock, flags);
+
+	/* check whether the object is still available */
+	if (object && !get_object(object))
+		object = NULL;
+	rcu_read_unlock();
+
+	return object;
+}
+
+/*
+ * Create the metadata (struct kmemleak_object) corresponding to an allocated
+ * memory block and add it to the object_list and object_tree_root.
+ */
+static void create_object(unsigned long ptr, size_t size, int min_count,
+			  gfp_t gfp)
+{
+	unsigned long flags;
+	struct kmemleak_object *object;
+	struct prio_tree_node *node;
+	struct stack_trace trace;
+
+	object = kmem_cache_alloc(object_cache, gfp & ~GFP_SLAB_BUG_MASK);
+	if (!object) {
+		kmemleak_panic("kmemleak: Cannot allocate a kmemleak_object "
+			       "structure\n");
+		return;
+	}
+
+	INIT_LIST_HEAD(&object->object_list);
+	INIT_LIST_HEAD(&object->gray_list);
+	INIT_HLIST_HEAD(&object->area_list);
+	spin_lock_init(&object->lock);
+	atomic_set(&object->use_count, 1);
+	object->flags = OBJECT_ALLOCATED;
+	object->pointer = ptr;
+	object->size = size;
+	object->min_count = min_count;
+	object->count = -1;			/* no color initially */
+	object->jiffies = jiffies;
+
+	/* task information */
+	if (in_irq()) {
+		object->pid = 0;
+		strncpy(object->comm, "hardirq", sizeof(object->comm));
+	} else if (in_softirq()) {
+		object->pid = 0;
+		strncpy(object->comm, "softirq", sizeof(object->comm));
+	} else {
+		object->pid = current->pid;
+		/*
+		 * There is a small chance of a race with set_task_comm(),
+		 * however using get_task_comm() here may cause locking
+		 * dependency issues with current->alloc_lock. In the worst
+		 * case, the command line is not correct.
+		 */
+		strncpy(object->comm, current->comm, sizeof(object->comm));
+	}
+
+	/* kernel backtrace */
+	trace.max_entries = MAX_TRACE;
+	trace.nr_entries = 0;
+	trace.entries = object->trace;
+	trace.skip = 1;
+	save_stack_trace(&trace);
+	object->trace_len = trace.nr_entries;
+
+	INIT_PRIO_TREE_NODE(&object->tree_node);
+	object->tree_node.start = ptr;
+	object->tree_node.last = ptr + size - 1;
+
+	write_lock_irqsave(&kmemleak_lock, flags);
+	min_addr = min(min_addr, ptr);
+	max_addr = max(max_addr, ptr + size);
+	node = prio_tree_insert(&object_tree_root, &object->tree_node);
+	/*
+	 * The code calling the kernel does not yet have the pointer to the
+	 * memory block to be able to free it.  However, we still hold the
+	 * kmemleak_lock here in case parts of the kernel started freeing
+	 * random memory blocks.
+	 */
+	if (node != &object->tree_node) {
+		unsigned long flags;
+
+		kmemleak_panic("kmemleak: Cannot insert 0x%lx into the object "
+			       "search tree (already existing)\n", ptr);
+		object = lookup_object(ptr, 1);
+		spin_lock_irqsave(&object->lock, flags);
+		dump_object_info(object);
+		spin_unlock_irqrestore(&object->lock, flags);
+
+		goto out;
+	}
+	list_add_tail_rcu(&object->object_list, &object_list);
+out:
+	write_unlock_irqrestore(&kmemleak_lock, flags);
+}
+
+/*
+ * Remove the metadata (struct kmemleak_object) for a memory block from the
+ * object_list and object_tree_root and decrement its use_count.
+ */
+static void delete_object(unsigned long ptr)
+{
+	unsigned long flags;
+	struct kmemleak_object *object;
+
+	write_lock_irqsave(&kmemleak_lock, flags);
+	object = lookup_object(ptr, 0);
+	if (!object) {
+		kmemleak_warn("kmemleak: Freeing unknown object at 0x%08lx\n",
+			      ptr);
+		write_unlock_irqrestore(&kmemleak_lock, flags);
+		return;
+	}
+	prio_tree_remove(&object_tree_root, &object->tree_node);
+	list_del_rcu(&object->object_list);
+	write_unlock_irqrestore(&kmemleak_lock, flags);
+
+	WARN_ON(!(object->flags & OBJECT_ALLOCATED));
+	WARN_ON(atomic_read(&object->use_count) < 1);
+
+	/*
+	 * Locking here also ensures that the corresponding memory block
+	 * cannot be freed when it is being scanned.
+	 */
+	spin_lock_irqsave(&object->lock, flags);
+	if (object->flags & OBJECT_REPORTED)
+		print_referenced(object);
+	object->flags &= ~OBJECT_ALLOCATED;
+	spin_unlock_irqrestore(&object->lock, flags);
+	put_object(object);
+}
+
+/*
+ * Make a object permanently as gray-colored so that it can no longer be
+ * reported as a leak. This is used in general to mark a false positive.
+ */
+static void make_gray_object(unsigned long ptr)
+{
+	unsigned long flags;
+	struct kmemleak_object *object;
+
+	object = find_and_get_object(ptr, 0);
+	if (!object) {
+		kmemleak_warn("kmemleak: Graying unknown object at 0x%08lx\n",
+			      ptr);
+		return;
+	}
+
+	spin_lock_irqsave(&object->lock, flags);
+	object->min_count = 0;
+	spin_unlock_irqrestore(&object->lock, flags);
+	put_object(object);
+}
+
+/*
+ * Mark the object as black-colored so that it is ignored from scans and
+ * reporting.
+ */
+static void make_black_object(unsigned long ptr)
+{
+	unsigned long flags;
+	struct kmemleak_object *object;
+
+	object = find_and_get_object(ptr, 0);
+	if (!object) {
+		kmemleak_warn("kmemleak: Blacking unknown object at 0x%08lx\n",
+			      ptr);
+		return;
+	}
+
+	spin_lock_irqsave(&object->lock, flags);
+	object->min_count = -1;
+	spin_unlock_irqrestore(&object->lock, flags);
+	put_object(object);
+}
+
+/*
+ * Add a scanning area to the object. If at least one such area is added,
+ * kmemleak will only scan these ranges rather than the whole memory block.
+ */
+static void add_scan_area(unsigned long ptr, unsigned long offset,
+			  size_t length, gfp_t gfp)
+{
+	unsigned long flags;
+	struct kmemleak_object *object;
+	struct kmemleak_scan_area *area;
+
+	object = find_and_get_object(ptr, 0);
+	if (!object) {
+		kmemleak_warn("kmemleak: Adding scan area to unknown "
+			      "object at 0x%08lx\n", ptr);
+		return;
+	}
+
+	area = kmem_cache_alloc(scan_area_cache, gfp & ~GFP_SLAB_BUG_MASK);
+	if (!area) {
+		kmemleak_warn("kmemleak: Cannot allocate a scan area\n");
+		goto out;
+	}
+
+	spin_lock_irqsave(&object->lock, flags);
+	if (offset + length > object->size) {
+		kmemleak_warn("kmemleak: Scan area larger than object "
+			      "0x%08lx\n", ptr);
+		dump_object_info(object);
+		kmem_cache_free(scan_area_cache, area);
+		goto out_unlock;
+	}
+
+	INIT_HLIST_NODE(&area->node);
+	area->offset = offset;
+	area->length = length;
+
+	hlist_add_head(&area->node, &object->area_list);
+out_unlock:
+	spin_unlock_irqrestore(&object->lock, flags);
+out:
+	put_object(object);
+}
+
+/*
+ * Set the OBJECT_NO_SCAN flag for the object corresponding to the give
+ * pointer. Such object will not be scanned by kmemleak but references to it
+ * are searched.
+ */
+static void object_no_scan(unsigned long ptr)
+{
+	unsigned long flags;
+	struct kmemleak_object *object;
+
+	object = find_and_get_object(ptr, 0);
+	if (!object) {
+		kmemleak_warn("kmemleak: Not scanning unknown object at "
+			      "0x%08lx\n", ptr);
+		return;
+	}
+
+	spin_lock_irqsave(&object->lock, flags);
+	object->flags |= OBJECT_NO_SCAN;
+	spin_unlock_irqrestore(&object->lock, flags);
+	put_object(object);
+}
+
+/*
+ * Log an early kmemleak_* call to the early_log buffer. These calls will be
+ * processed later once kmemleak is fully initialized.
+ */
+static void log_early(int op_type, const void *ptr, size_t size,
+		      int min_count, unsigned long offset, size_t length)
+{
+	unsigned long flags;
+	struct early_log *log;
+
+	if (crt_early_log >= ARRAY_SIZE(early_log)) {
+		kmemleak_panic("kmemleak: Early log buffer exceeded\n");
+		return;
+	}
+
+	/*
+	 * There is no need for locking since the kernel is still in UP mode
+	 * at this stage. Disabling the IRQs is enough.
+	 */
+	local_irq_save(flags);
+	log = &early_log[crt_early_log];
+	log->op_type = op_type;
+	log->ptr = ptr;
+	log->size = size;
+	log->min_count = min_count;
+	log->offset = offset;
+	log->length = length;
+	crt_early_log++;
+	local_irq_restore(flags);
+}
+
+/*
+ * Memory allocation function callback. This function is called from the
+ * kernel allocators when a new block is allocated (kmem_cache_alloc, kmalloc,
+ * vmalloc etc.).
+ */
+void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp)
+{
+	pr_debug("%s(0x%p, %zu, %d)\n", __func__, ptr, size, min_count);
+
+	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+		create_object((unsigned long)ptr, size, min_count, gfp);
+	else if (atomic_read(&kmemleak_early_log))
+		log_early(KMEMLEAK_ALLOC, ptr, size, min_count, 0, 0);
+}
+EXPORT_SYMBOL_GPL(kmemleak_alloc);
+
+/*
+ * Memory freeing function callback. This function is called from the kernel
+ * allocators when a block is freed (kmem_cache_free, kfree, vfree etc.).
+ */
+void kmemleak_free(const void *ptr)
+{
+	pr_debug("%s(0x%p)\n", __func__, ptr);
+
+	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+		delete_object((unsigned long)ptr);
+	else if (atomic_read(&kmemleak_early_log))
+		log_early(KMEMLEAK_FREE, ptr, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL_GPL(kmemleak_free);
+
+/*
+ * Mark an already allocated memory block as a false positive. This will cause
+ * the block to no longer be reported as leak and always be scanned.
+ */
+void kmemleak_not_leak(const void *ptr)
+{
+	pr_debug("%s(0x%p)\n", __func__, ptr);
+
+	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+		make_gray_object((unsigned long)ptr);
+	else if (atomic_read(&kmemleak_early_log))
+		log_early(KMEMLEAK_NOT_LEAK, ptr, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(kmemleak_not_leak);
+
+/*
+ * Ignore a memory block. This is usually done when it is known that the
+ * corresponding block is not a leak and does not contain any references to
+ * other allocated memory blocks.
+ */
+void kmemleak_ignore(const void *ptr)
+{
+	pr_debug("%s(0x%p)\n", __func__, ptr);
+
+	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+		make_black_object((unsigned long)ptr);
+	else if (atomic_read(&kmemleak_early_log))
+		log_early(KMEMLEAK_IGNORE, ptr, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(kmemleak_ignore);
+
+/*
+ * Limit the range to be scanned in an allocated memory block.
+ */
+void kmemleak_scan_area(const void *ptr, unsigned long offset, size_t length,
+			gfp_t gfp)
+{
+	pr_debug("%s(0x%p)\n", __func__, ptr);
+
+	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+		add_scan_area((unsigned long)ptr, offset, length, gfp);
+	else if (atomic_read(&kmemleak_early_log))
+		log_early(KMEMLEAK_SCAN_AREA, ptr, 0, 0, offset, length);
+}
+EXPORT_SYMBOL(kmemleak_scan_area);
+
+/*
+ * Inform kmemleak not to scan the given memory block.
+ */
+void kmemleak_no_scan(const void *ptr)
+{
+	pr_debug("%s(0x%p)\n", __func__, ptr);
+
+	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+		object_no_scan((unsigned long)ptr);
+	else if (atomic_read(&kmemleak_early_log))
+		log_early(KMEMLEAK_NO_SCAN, ptr, 0, 0, 0, 0);
+}
+EXPORT_SYMBOL(kmemleak_no_scan);
+
+/*
+ * Yield the CPU so that other tasks get a chance to run.  The yielding is
+ * rate-limited to avoid excessive number of calls to the schedule() function
+ * during memory scanning.
+ */
+static void scan_yield(void)
+{
+	might_sleep();
+
+	if (time_is_before_eq_jiffies(next_scan_yield)) {
+		schedule();
+		next_scan_yield = jiffies + jiffies_scan_yield;
+	}
+}
+
+/*
+ * Memory scanning is a long process and it needs to be interruptable. This
+ * function checks whether such interrupt condition occured.
+ */
+static int scan_should_stop(void)
+{
+	if (!atomic_read(&kmemleak_enabled))
+		return 1;
+
+	/*
+	 * This function may be called from either process or kthread context,
+	 * hence the need to check for both stop conditions.
+	 */
+	if (current->mm)
+		return signal_pending(current);
+	else
+		return kthread_should_stop();
+
+	return 0;
+}
+
+/*
+ * Scan a memory block (exclusive range) for valid pointers and add those
+ * found to the gray list.
+ */
+static void scan_block(void *_start, void *_end,
+		       struct kmemleak_object *scanned)
+{
+	unsigned long *ptr;
+	unsigned long *start = PTR_ALIGN(_start, BYTES_PER_POINTER);
+	unsigned long *end = _end - (BYTES_PER_POINTER - 1);
+
+	for (ptr = start; ptr < end; ptr++) {
+		unsigned long flags;
+		unsigned long pointer = *ptr;
+		struct kmemleak_object *object;
+
+		if (scan_should_stop())
+			break;
+
+		/*
+		 * When scanning a memory block with a corresponding
+		 * kmemleak_object, the CPU yielding is handled in the calling
+		 * code since it holds the object->lock to avoid the block
+		 * freeing.
+		 */
+		if (!scanned)
+			scan_yield();
+
+		object = find_and_get_object(pointer, 1);
+		if (!object)
+			continue;
+		if (object == scanned) {
+			/* self referenced, ignore */
+			put_object(object);
+			continue;
+		}
+
+		/*
+		 * Avoid the lockdep recursive warning on object->lock being
+		 * previously acquired in scan_object(). These locks are
+		 * enclosed by scan_mutex.
+		 */
+		spin_lock_irqsave_nested(&object->lock, flags,
+					 SINGLE_DEPTH_NESTING);
+		if (!color_white(object)) {
+			/* non-orphan, ignored or new */
+			spin_unlock_irqrestore(&object->lock, flags);
+			put_object(object);
+			continue;
+		}
+
+		/*
+		 * Increase the object's reference count (number of pointers
+		 * to the memory block). If this count reaches the required
+		 * minimum, the object's color will become gray and it will be
+		 * added to the gray_list.
+		 */
+		object->count++;
+		if (color_gray(object))
+			list_add_tail(&object->gray_list, &gray_list);
+		else
+			put_object(object);
+		spin_unlock_irqrestore(&object->lock, flags);
+	}
+}
+
+/*
+ * Scan a memory block corresponding to a kmemleak_object. A condition is
+ * that object->use_count >= 1.
+ */
+static void scan_object(struct kmemleak_object *object)
+{
+	struct kmemleak_scan_area *area;
+	struct hlist_node *elem;
+	unsigned long flags;
+
+	/*
+	 * Once the object->lock is aquired, the corresponding memory block
+	 * cannot be freed (the same lock is aquired in delete_object).
+	 */
+	spin_lock_irqsave(&object->lock, flags);
+	if (object->flags & OBJECT_NO_SCAN)
+		goto out;
+	if (!(object->flags & OBJECT_ALLOCATED))
+		/* already freed object */
+		goto out;
+	if (hlist_empty(&object->area_list))
+		scan_block((void *)object->pointer,
+			   (void *)(object->pointer + object->size), object);
+	else
+		hlist_for_each_entry(area, elem, &object->area_list, node)
+			scan_block((void *)(object->pointer + area->offset),
+				   (void *)(object->pointer + area->offset
+					    + area->length), object);
+out:
+	spin_unlock_irqrestore(&object->lock, flags);
+}
+
+/*
+ * Scan data sections and all the referenced memory blocks allocated via the
+ * kernel's standard allocators. This function must be called with the
+ * scan_mutex held.
+ */
+static void kmemleak_scan(void)
+{
+	unsigned long flags;
+	struct kmemleak_object *object, *tmp;
+	struct task_struct *task;
+	int i;
+
+	/* prepare the kmemleak_object's */
+	rcu_read_lock();
+	list_for_each_entry_rcu(object, &object_list, object_list) {
+		spin_lock_irqsave(&object->lock, flags);
+#ifdef DEBUG
+		/*
+		 * With a few exceptions there should be a maximum of
+		 * 1 reference to any object at this point.
+		 */
+		if (atomic_read(&object->use_count) > 1) {
+			pr_debug("kmemleak: object->use_count = %d\n",
+				 atomic_read(&object->use_count));
+			dump_object_info(object);
+		}
+#endif
+		/* reset the reference count (whiten the object) */
+		object->count = 0;
+		if (color_gray(object) && get_object(object))
+			list_add_tail(&object->gray_list, &gray_list);
+
+		spin_unlock_irqrestore(&object->lock, flags);
+	}
+	rcu_read_unlock();
+
+	/* data/bss scanning */
+	scan_block(_sdata, _edata, NULL);
+	scan_block(__bss_start, __bss_stop, NULL);
+
+#ifdef CONFIG_SMP
+	/* per-cpu sections scanning */
+	for_each_possible_cpu(i)
+		scan_block(__per_cpu_start + per_cpu_offset(i),
+			   __per_cpu_end + per_cpu_offset(i), NULL);
+#endif
+
+	/*
+	 * Struct page scanning for each node. The code below is not yet safe
+	 * with MEMORY_HOTPLUG.
+	 */
+	for_each_online_node(i) {
+		pg_data_t *pgdat = NODE_DATA(i);
+		unsigned long start_pfn = pgdat->node_start_pfn;
+		unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
+		unsigned long pfn;
+
+		for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+			struct page *page;
+
+			if (!pfn_valid(pfn))
+				continue;
+			page = pfn_to_page(pfn);
+			/* only scan if page is in use */
+			if (page_count(page) == 0)
+				continue;
+			scan_block(page, page + 1, NULL);
+		}
+	}
+
+	/*
+	 * Scanning the task stacks may introduce false negatives and it is
+	 * not enabled by default.
+	 */
+	if (kmemleak_stack_scan) {
+		read_lock(&tasklist_lock);
+		for_each_process(task)
+			scan_block(task_stack_page(task),
+				   task_stack_page(task) + THREAD_SIZE, NULL);
+		read_unlock(&tasklist_lock);
+	}
+
+	/*
+	 * Scan the objects already referenced from the sections scanned
+	 * above. More objects will be referenced and, if there are no memory
+	 * leaks, all the objects will be scanned. The list traversal is safe
+	 * for both tail additions and removals from inside the loop. The
+	 * kmemleak objects cannot be freed from outside the loop because their
+	 * use_count was increased.
+	 */
+	object = list_entry(gray_list.next, typeof(*object), gray_list);
+	while (&object->gray_list != &gray_list) {
+		scan_yield();
+
+		/* may add new objects to the list */
+		if (!scan_should_stop())
+			scan_object(object);
+
+		tmp = list_entry(object->gray_list.next, typeof(*object),
+				 gray_list);
+
+		/* remove the object from the list and release it */
+		list_del(&object->gray_list);
+		put_object(object);
+
+		object = tmp;
+	}
+	WARN_ON(!list_empty(&gray_list));
+}
+
+/*
+ * Thread function performing automatic memory scanning. Unreferenced objects
+ * at the end of a memory scan are reported but only the first time.
+ */
+static int kmemleak_scan_thread(void *arg)
+{
+	static int first_run = 1;
+
+	pr_info("kmemleak: Automatic memory scanning thread started\n");
+
+	/*
+	 * Wait before the first scan to allow the system to fully initialize.
+	 */
+	if (first_run) {
+		first_run = 0;
+		ssleep(SECS_FIRST_SCAN);
+	}
+
+	while (!kthread_should_stop()) {
+		struct kmemleak_object *object;
+		signed long timeout = jiffies_scan_wait;
+
+		mutex_lock(&scan_mutex);
+
+		kmemleak_scan();
+		reported_leaks = 0;
+
+		rcu_read_lock();
+		list_for_each_entry_rcu(object, &object_list, object_list) {
+			unsigned long flags;
+
+			if (reported_leaks >= REPORTS_NR)
+				break;
+			spin_lock_irqsave(&object->lock, flags);
+			if (!(object->flags & OBJECT_REPORTED) &&
+			    unreferenced_object(object)) {
+				print_unreferenced(NULL, object);
+				object->flags |= OBJECT_REPORTED;
+				reported_leaks++;
+			} else if ((object->flags & OBJECT_REPORTED) &&
+				   referenced_object(object)) {
+				print_referenced(object);
+				object->flags &= ~OBJECT_REPORTED;
+			}
+			spin_unlock_irqrestore(&object->lock, flags);
+		}
+		rcu_read_unlock();
+
+		mutex_unlock(&scan_mutex);
+		/* wait before the next scan */
+		while (timeout && !kthread_should_stop())
+			timeout = schedule_timeout_interruptible(timeout);
+	}
+
+	pr_info("kmemleak: Automatic memory scanning thread ended\n");
+
+	return 0;
+}
+
+/*
+ * Start the automatic memory scanning thread. This function must be called
+ * with the kmemleak_mutex held.
+ */
+void start_scan_thread(void)
+{
+	if (scan_thread)
+		return;
+	scan_thread = kthread_run(kmemleak_scan_thread, NULL, "kmemleak");
+	if (IS_ERR(scan_thread)) {
+		pr_warning("kmemleak: Failed to create the scan thread\n");
+		scan_thread = NULL;
+	}
+}
+
+/*
+ * Stop the automatic memory scanning thread. This function must be called
+ * with the kmemleak_mutex held.
+ */
+void stop_scan_thread(void)
+{
+	if (scan_thread) {
+		kthread_stop(scan_thread);
+		scan_thread = NULL;
+	}
+}
+
+/*
+ * Iterate over the object_list and return the first valid object at or after
+ * the required position with its use_count incremented. The function triggers
+ * a memory scanning when the pos argument points to the first position.
+ */
+static void *kmemleak_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct kmemleak_object *object;
+	loff_t n = *pos;
+
+	if (!n) {
+		kmemleak_scan();
+		reported_leaks = 0;
+	}
+	if (reported_leaks >= REPORTS_NR)
+		return NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(object, &object_list, object_list) {
+		if (n-- > 0)
+			continue;
+		if (get_object(object))
+			goto out;
+	}
+	object = NULL;
+out:
+	rcu_read_unlock();
+	return object;
+}
+
+/*
+ * Return the next object in the object_list. The function decrements the
+ * use_count of the previous object and increases that of the next one.
+ */
+static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct kmemleak_object *prev_obj = v;
+	struct kmemleak_object *next_obj = NULL;
+	struct list_head *n = &prev_obj->object_list;
+
+	++(*pos);
+	if (reported_leaks >= REPORTS_NR)
+		goto out;
+
+	rcu_read_lock();
+	list_for_each_continue_rcu(n, &object_list) {
+		next_obj = list_entry(n, struct kmemleak_object, object_list);
+		if (get_object(next_obj))
+			break;
+	}
+	rcu_read_unlock();
+out:
+	put_object(prev_obj);
+	return next_obj;
+}
+
+/*
+ * Decrement the use_count of the last object required, if any.
+ */
+static void kmemleak_seq_stop(struct seq_file *seq, void *v)
+{
+	if (v)
+		put_object(v);
+}
+
+/*
+ * Print the information for an unreferenced object to the seq file.
+ */
+static int kmemleak_seq_show(struct seq_file *seq, void *v)
+{
+	struct kmemleak_object *object = v;
+	unsigned long flags;
+
+	spin_lock_irqsave(&object->lock, flags);
+	if (!unreferenced_object(object))
+		goto out;
+	print_unreferenced(seq, object);
+	reported_leaks++;
+out:
+	spin_unlock_irqrestore(&object->lock, flags);
+	return 0;
+}
+
+static const struct seq_operations kmemleak_seq_ops = {
+	.start = kmemleak_seq_start,
+	.next  = kmemleak_seq_next,
+	.stop  = kmemleak_seq_stop,
+	.show  = kmemleak_seq_show,
+};
+
+static int kmemleak_open(struct inode *inode, struct file *file)
+{
+	int ret = 0;
+
+	if (!atomic_read(&kmemleak_enabled))
+		return -EBUSY;
+
+	ret = mutex_lock_interruptible(&kmemleak_mutex);
+	if (ret < 0)
+		goto out;
+	if (file->f_mode & FMODE_READ) {
+		ret = mutex_lock_interruptible(&scan_mutex);
+		if (ret < 0)
+			goto kmemleak_unlock;
+		ret = seq_open(file, &kmemleak_seq_ops);
+		if (ret < 0)
+			goto scan_unlock;
+	}
+	return ret;
+
+scan_unlock:
+	mutex_unlock(&scan_mutex);
+kmemleak_unlock:
+	mutex_unlock(&kmemleak_mutex);
+out:
+	return ret;
+}
+
+static int kmemleak_release(struct inode *inode, struct file *file)
+{
+	int ret = 0;
+
+	if (file->f_mode & FMODE_READ) {
+		seq_release(inode, file);
+		mutex_unlock(&scan_mutex);
+	}
+	mutex_unlock(&kmemleak_mutex);
+
+	return ret;
+}
+
+/*
+ * File write operation to configure kmemleak at run-time. The following
+ * commands can be written to the /sys/kernel/debug/kmemleak file:
+ *   off	- disable kmemleak (irreversible)
+ *   stack=on	- enable the task stacks scanning
+ *   stack=off	- disable the tasks stacks scanning
+ *   scan=on	- start the automatic memory scanning thread
+ *   scan=off	- stop the automatic memory scanning thread
+ *   scan=...	- set the automatic memory scanning period in seconds (0 to
+ *		  disable it)
+ */
+static ssize_t kmemleak_write(struct file *file, const char __user *user_buf,
+			      size_t size, loff_t *ppos)
+{
+	char buf[64];
+	int buf_size;
+
+	if (!atomic_read(&kmemleak_enabled))
+		return -EBUSY;
+
+	buf_size = min(size, (sizeof(buf) - 1));
+	if (strncpy_from_user(buf, user_buf, buf_size) < 0)
+		return -EFAULT;
+	buf[buf_size] = 0;
+
+	if (strncmp(buf, "off", 3) == 0)
+		kmemleak_disable();
+	else if (strncmp(buf, "stack=on", 8) == 0)
+		kmemleak_stack_scan = 1;
+	else if (strncmp(buf, "stack=off", 9) == 0)
+		kmemleak_stack_scan = 0;
+	else if (strncmp(buf, "scan=on", 7) == 0)
+		start_scan_thread();
+	else if (strncmp(buf, "scan=off", 8) == 0)
+		stop_scan_thread();
+	else if (strncmp(buf, "scan=", 5) == 0) {
+		unsigned long secs;
+		int err;
+
+		err = strict_strtoul(buf + 5, 0, &secs);
+		if (err < 0)
+			return err;
+		stop_scan_thread();
+		if (secs) {
+			jiffies_scan_wait = msecs_to_jiffies(secs * 1000);
+			start_scan_thread();
+		}
+	} else
+		return -EINVAL;
+
+	/* ignore the rest of the buffer, only one command at a time */
+	*ppos += size;
+	return size;
+}
+
+static const struct file_operations kmemleak_fops = {
+	.owner		= THIS_MODULE,
+	.open		= kmemleak_open,
+	.read		= seq_read,
+	.write		= kmemleak_write,
+	.llseek		= seq_lseek,
+	.release	= kmemleak_release,
+};
+
+/*
+ * Perform the freeing of the kmemleak internal objects after waiting for any
+ * current memory scan to complete.
+ */
+static int kmemleak_cleanup_thread(void *arg)
+{
+	struct kmemleak_object *object;
+
+	mutex_lock(&kmemleak_mutex);
+	stop_scan_thread();
+	mutex_unlock(&kmemleak_mutex);
+
+	mutex_lock(&scan_mutex);
+	rcu_read_lock();
+	list_for_each_entry_rcu(object, &object_list, object_list)
+		delete_object(object->pointer);
+	rcu_read_unlock();
+	mutex_unlock(&scan_mutex);
+
+	return 0;
+}
+
+/*
+ * Start the clean-up thread.
+ */
+static void kmemleak_cleanup(void)
+{
+	struct task_struct *cleanup_thread;
+
+	cleanup_thread = kthread_run(kmemleak_cleanup_thread, NULL,
+				     "kmemleak-clean");
+	if (IS_ERR(cleanup_thread))
+		pr_warning("kmemleak: Failed to create the clean-up thread\n");
+}
+
+/*
+ * Disable kmemleak. No memory allocation/freeing will be traced once this
+ * function is called. Disabling kmemleak is an irreversible operation.
+ */
+static void kmemleak_disable(void)
+{
+	/* atomically check whether it was already invoked */
+	if (atomic_cmpxchg(&kmemleak_error, 0, 1))
+		return;
+
+	/* stop any memory operation tracing */
+	atomic_set(&kmemleak_early_log, 0);
+	atomic_set(&kmemleak_enabled, 0);
+
+	/* check whether it is too early for a kernel thread */
+	if (atomic_read(&kmemleak_initialized))
+		kmemleak_cleanup();
+
+	pr_info("Kernel memory leak detector disabled\n");
+}
+
+/*
+ * Allow boot-time kmemleak disabling (enabled by default).
+ */
+static int kmemleak_boot_config(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	if (strcmp(str, "off") == 0)
+		kmemleak_disable();
+	else if (strcmp(str, "on") != 0)
+		return -EINVAL;
+	return 0;
+}
+early_param("kmemleak", kmemleak_boot_config);
+
+/*
+ * Kkmemleak initialization.
+ */
+void __init kmemleak_init(void)
+{
+	int i;
+	unsigned long flags;
+
+	jiffies_scan_yield = msecs_to_jiffies(MSECS_SCAN_YIELD);
+	jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE);
+	jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000);
+
+	object_cache = KMEM_CACHE(kmemleak_object, SLAB_NOLEAKTRACE);
+	scan_area_cache = KMEM_CACHE(kmemleak_scan_area, SLAB_NOLEAKTRACE);
+	INIT_PRIO_TREE_ROOT(&object_tree_root);
+
+	/* the kernel is still in UP mode, so disabling the IRQs is enough */
+	local_irq_save(flags);
+	if (!atomic_read(&kmemleak_error)) {
+		atomic_set(&kmemleak_enabled, 1);
+		atomic_set(&kmemleak_early_log, 0);
+	}
+	local_irq_restore(flags);
+
+	/*
+	 * This is the point where tracking allocations is safe. Automatic
+	 * scanning is started during the late initcall. Add the early logged
+	 * callbacks to the kmemleak infrastructure.
+	 */
+	for (i = 0; i < crt_early_log; i++) {
+		struct early_log *log = &early_log[i];
+
+		switch (log->op_type) {
+		case KMEMLEAK_ALLOC:
+			kmemleak_alloc(log->ptr, log->size, log->min_count,
+				       GFP_KERNEL);
+			break;
+		case KMEMLEAK_FREE:
+			kmemleak_free(log->ptr);
+			break;
+		case KMEMLEAK_NOT_LEAK:
+			kmemleak_not_leak(log->ptr);
+			break;
+		case KMEMLEAK_IGNORE:
+			kmemleak_ignore(log->ptr);
+			break;
+		case KMEMLEAK_SCAN_AREA:
+			kmemleak_scan_area(log->ptr, log->offset, log->length,
+					   GFP_KERNEL);
+			break;
+		case KMEMLEAK_NO_SCAN:
+			kmemleak_no_scan(log->ptr);
+			break;
+		default:
+			WARN_ON(1);
+		}
+	}
+}
+
+/*
+ * Late initialization function.
+ */
+static int __init kmemleak_late_init(void)
+{
+	struct dentry *dentry;
+
+	atomic_set(&kmemleak_initialized, 1);
+
+	if (atomic_read(&kmemleak_error)) {
+		/*
+		 * Some error occured and kmemleak was disabled. There is a
+		 * small chance that kmemleak_disable() was called immediately
+		 * after setting kmemleak_initialized and we may end up with
+		 * two clean-up threads but serialized by scan_mutex.
+		 */
+		kmemleak_cleanup();
+		return -ENOMEM;
+	}
+
+	dentry = debugfs_create_file("kmemleak", S_IRUGO, NULL, NULL,
+				     &kmemleak_fops);
+	if (!dentry)
+		pr_warning("kmemleak: Failed to create the debugfs kmemleak "
+			   "file\n");
+	mutex_lock(&kmemleak_mutex);
+	start_scan_thread();
+	mutex_unlock(&kmemleak_mutex);
+
+	pr_info("Kernel memory leak detector initialized\n");
+
+	return 0;
+}
+late_initcall(kmemleak_late_init);
diff --git a/mm/mlock.c b/mm/mlock.c
index cbe9e0581b75..ac130433c7d3 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -629,52 +629,43 @@ void user_shm_unlock(size_t size, struct user_struct *user)
 	free_uid(user);
 }
 
-void *alloc_locked_buffer(size_t size)
+int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+			  size_t size)
 {
-	unsigned long rlim, vm, pgsz;
-	void *buffer = NULL;
+	unsigned long lim, vm, pgsz;
+	int error = -ENOMEM;
 
 	pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
-	down_write(&current->mm->mmap_sem);
+	down_write(&mm->mmap_sem);
 
-	rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
-	vm   = current->mm->total_vm + pgsz;
-	if (rlim < vm)
+	lim = rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+	vm   = mm->total_vm + pgsz;
+	if (lim < vm)
 		goto out;
 
-	rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
-	vm   = current->mm->locked_vm + pgsz;
-	if (rlim < vm)
+	lim = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+	vm   = mm->locked_vm + pgsz;
+	if (lim < vm)
 		goto out;
 
-	buffer = kzalloc(size, GFP_KERNEL);
-	if (!buffer)
-		goto out;
-
-	current->mm->total_vm  += pgsz;
-	current->mm->locked_vm += pgsz;
+	mm->total_vm  += pgsz;
+	mm->locked_vm += pgsz;
 
+	error = 0;
  out:
-	up_write(&current->mm->mmap_sem);
-	return buffer;
+	up_write(&mm->mmap_sem);
+	return error;
 }
 
-void release_locked_buffer(void *buffer, size_t size)
+void refund_locked_memory(struct mm_struct *mm, size_t size)
 {
 	unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
-	down_write(&current->mm->mmap_sem);
+	down_write(&mm->mmap_sem);
 
-	current->mm->total_vm  -= pgsz;
-	current->mm->locked_vm -= pgsz;
+	mm->total_vm  -= pgsz;
+	mm->locked_vm -= pgsz;
 
-	up_write(&current->mm->mmap_sem);
-}
-
-void free_locked_buffer(void *buffer, size_t size)
-{
-	release_locked_buffer(buffer, size);
-
-	kfree(buffer);
+	up_write(&mm->mmap_sem);
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 6b7b1a95944b..34579b23ebd5 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -28,6 +28,7 @@
 #include <linux/mempolicy.h>
 #include <linux/rmap.h>
 #include <linux/mmu_notifier.h>
+#include <linux/perf_counter.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -87,6 +88,9 @@ int sysctl_overcommit_ratio = 50;	/* default is 50% */
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
 struct percpu_counter vm_committed_as;
 
+/* amount of vm to protect from userspace access */
+unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+
 /*
  * Check that a process has enough memory to allocate a new virtual
  * mapping. 0 means there is enough memory for the allocation to
@@ -1219,6 +1223,8 @@ munmap_back:
 	if (correct_wcount)
 		atomic_inc(&inode->i_writecount);
 out:
+	perf_counter_mmap(vma);
+
 	mm->total_vm += len >> PAGE_SHIFT;
 	vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
 	if (vm_flags & VM_LOCKED) {
@@ -2305,6 +2311,8 @@ int install_special_mapping(struct mm_struct *mm,
 
 	mm->total_vm += len >> PAGE_SHIFT;
 
+	perf_counter_mmap(vma);
+
 	return 0;
 }
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 258197b76fb4..d80311baeb2d 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -23,6 +23,7 @@
 #include <linux/swapops.h>
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
+#include <linux/perf_counter.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
@@ -299,6 +300,7 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
 		if (error)
 			goto out;
+		perf_counter_mmap(vma);
 		nstart = tmp;
 
 		if (nstart < prev->vm_end)
diff --git a/mm/nommu.c b/mm/nommu.c
index b571ef707428..2fd2ad5da98e 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -69,6 +69,9 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
 int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
 int heap_stack_gap = 0;
 
+/* amount of vm to protect from userspace access */
+unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+
 atomic_long_t mmap_pages_allocated;
 
 EXPORT_SYMBOL(mem_map);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fe753ecf2aa5..17d5f539a9aa 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -46,6 +46,7 @@
 #include <linux/page-isolation.h>
 #include <linux/page_cgroup.h>
 #include <linux/debugobjects.h>
+#include <linux/kmemleak.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -149,10 +150,6 @@ static unsigned long __meminitdata dma_reserve;
   static int __meminitdata nr_nodemap_entries;
   static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
   static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-  static unsigned long __meminitdata node_boundary_start_pfn[MAX_NUMNODES];
-  static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
   static unsigned long __initdata required_kernelcore;
   static unsigned long __initdata required_movablecore;
   static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
@@ -3102,64 +3099,6 @@ void __init sparse_memory_present_with_active_regions(int nid)
 				early_node_map[i].end_pfn);
 }
 
-/**
- * push_node_boundaries - Push node boundaries to at least the requested boundary
- * @nid: The nid of the node to push the boundary for
- * @start_pfn: The start pfn of the node
- * @end_pfn: The end pfn of the node
- *
- * In reserve-based hot-add, mem_map is allocated that is unused until hotadd
- * time. Specifically, on x86_64, SRAT will report ranges that can potentially
- * be hotplugged even though no physical memory exists. This function allows
- * an arch to push out the node boundaries so mem_map is allocated that can
- * be used later.
- */
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-void __init push_node_boundaries(unsigned int nid,
-		unsigned long start_pfn, unsigned long end_pfn)
-{
-	mminit_dprintk(MMINIT_TRACE, "zoneboundary",
-			"Entering push_node_boundaries(%u, %lu, %lu)\n",
-			nid, start_pfn, end_pfn);
-
-	/* Initialise the boundary for this node if necessary */
-	if (node_boundary_end_pfn[nid] == 0)
-		node_boundary_start_pfn[nid] = -1UL;
-
-	/* Update the boundaries */
-	if (node_boundary_start_pfn[nid] > start_pfn)
-		node_boundary_start_pfn[nid] = start_pfn;
-	if (node_boundary_end_pfn[nid] < end_pfn)
-		node_boundary_end_pfn[nid] = end_pfn;
-}
-
-/* If necessary, push the node boundary out for reserve hotadd */
-static void __meminit account_node_boundary(unsigned int nid,
-		unsigned long *start_pfn, unsigned long *end_pfn)
-{
-	mminit_dprintk(MMINIT_TRACE, "zoneboundary",
-			"Entering account_node_boundary(%u, %lu, %lu)\n",
-			nid, *start_pfn, *end_pfn);
-
-	/* Return if boundary information has not been provided */
-	if (node_boundary_end_pfn[nid] == 0)
-		return;
-
-	/* Check the boundaries and update if necessary */
-	if (node_boundary_start_pfn[nid] < *start_pfn)
-		*start_pfn = node_boundary_start_pfn[nid];
-	if (node_boundary_end_pfn[nid] > *end_pfn)
-		*end_pfn = node_boundary_end_pfn[nid];
-}
-#else
-void __init push_node_boundaries(unsigned int nid,
-		unsigned long start_pfn, unsigned long end_pfn) {}
-
-static void __meminit account_node_boundary(unsigned int nid,
-		unsigned long *start_pfn, unsigned long *end_pfn) {}
-#endif
-
-
 /**
  * get_pfn_range_for_nid - Return the start and end page frames for a node
  * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
@@ -3185,9 +3124,6 @@ void __meminit get_pfn_range_for_nid(unsigned int nid,
 
 	if (*start_pfn == -1UL)
 		*start_pfn = 0;
-
-	/* Push the node boundaries out if requested */
-	account_node_boundary(nid, start_pfn, end_pfn);
 }
 
 /*
@@ -3793,10 +3729,6 @@ void __init remove_all_active_ranges(void)
 {
 	memset(early_node_map, 0, sizeof(early_node_map));
 	nr_nodemap_entries = 0;
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-	memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn));
-	memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn));
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
 }
 
 /* Compare two active node_active_regions */
@@ -4615,6 +4547,16 @@ void *__init alloc_large_system_hash(const char *tablename,
 	if (_hash_mask)
 		*_hash_mask = (1 << log2qty) - 1;
 
+	/*
+	 * If hashdist is set, the table allocation is done with __vmalloc()
+	 * which invokes the kmemleak_alloc() callback. This function may also
+	 * be called before the slab and kmemleak are initialised when
+	 * kmemleak simply buffers the request to be executed later
+	 * (GFP_ATOMIC flag ignored in this case).
+	 */
+	if (!hashdist)
+		kmemleak_alloc(table, size, 1, GFP_ATOMIC);
+
 	return table;
 }
 
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 791905c991df..3dd4a909a1de 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -47,6 +47,8 @@ static int __init alloc_node_page_cgroup(int nid)
 	struct page_cgroup *base, *pc;
 	unsigned long table_size;
 	unsigned long start_pfn, nr_pages, index;
+	struct page *page;
+	unsigned int order;
 
 	start_pfn = NODE_DATA(nid)->node_start_pfn;
 	nr_pages = NODE_DATA(nid)->node_spanned_pages;
@@ -55,11 +57,13 @@ static int __init alloc_node_page_cgroup(int nid)
 		return 0;
 
 	table_size = sizeof(struct page_cgroup) * nr_pages;
-
-	base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
-			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
-	if (!base)
+	order = get_order(table_size);
+	page = alloc_pages_node(nid, GFP_NOWAIT | __GFP_ZERO, order);
+	if (!page)
+		page = alloc_pages_node(-1, GFP_NOWAIT | __GFP_ZERO, order);
+	if (!page)
 		return -ENOMEM;
+	base = page_address(page);
 	for (index = 0; index < nr_pages; index++) {
 		pc = base + index;
 		__init_page_cgroup(pc, start_pfn + index);
diff --git a/mm/percpu.c b/mm/percpu.c
index 1aa5d8fbca12..c0b2c1a76e81 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -23,7 +23,7 @@
  * Allocation is done in offset-size areas of single unit space.  Ie,
  * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0,
  * c1:u1, c1:u2 and c1:u3.  Percpu access can be done by configuring
- * percpu base registers UNIT_SIZE apart.
+ * percpu base registers pcpu_unit_size apart.
  *
  * There are usually many small percpu allocations many of them as
  * small as 4 bytes.  The allocator organizes chunks into lists
@@ -38,8 +38,8 @@
  * region and negative allocated.  Allocation inside a chunk is done
  * by scanning this map sequentially and serving the first matching
  * entry.  This is mostly copied from the percpu_modalloc() allocator.
- * Chunks are also linked into a rb tree to ease address to chunk
- * mapping during free.
+ * Chunks can be determined from the address using the index field
+ * in the page struct. The index field contains a pointer to the chunk.
  *
  * To use this allocator, arch code should do the followings.
  *
@@ -61,7 +61,6 @@
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/pfn.h>
-#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
@@ -88,7 +87,6 @@
 
 struct pcpu_chunk {
 	struct list_head	list;		/* linked to pcpu_slot lists */
-	struct rb_node		rb_node;	/* key is chunk->vm->addr */
 	int			free_size;	/* free bytes in the chunk */
 	int			contig_hint;	/* max contiguous size hint */
 	struct vm_struct	*vm;		/* mapped vmalloc region */
@@ -110,9 +108,21 @@ static size_t pcpu_chunk_struct_size __read_mostly;
 void *pcpu_base_addr __read_mostly;
 EXPORT_SYMBOL_GPL(pcpu_base_addr);
 
-/* optional reserved chunk, only accessible for reserved allocations */
+/*
+ * The first chunk which always exists.  Note that unlike other
+ * chunks, this one can be allocated and mapped in several different
+ * ways and thus often doesn't live in the vmalloc area.
+ */
+static struct pcpu_chunk *pcpu_first_chunk;
+
+/*
+ * Optional reserved chunk.  This chunk reserves part of the first
+ * chunk and serves it for reserved allocations.  The amount of
+ * reserved offset is in pcpu_reserved_chunk_limit.  When reserved
+ * area doesn't exist, the following variables contain NULL and 0
+ * respectively.
+ */
 static struct pcpu_chunk *pcpu_reserved_chunk;
-/* offset limit of the reserved chunk */
 static int pcpu_reserved_chunk_limit;
 
 /*
@@ -121,7 +131,7 @@ static int pcpu_reserved_chunk_limit;
  * There are two locks - pcpu_alloc_mutex and pcpu_lock.  The former
  * protects allocation/reclaim paths, chunks and chunk->page arrays.
  * The latter is a spinlock and protects the index data structures -
- * chunk slots, rbtree, chunks and area maps in chunks.
+ * chunk slots, chunks and area maps in chunks.
  *
  * During allocation, pcpu_alloc_mutex is kept locked all the time and
  * pcpu_lock is grabbed and released as necessary.  All actual memory
@@ -140,7 +150,6 @@ static DEFINE_MUTEX(pcpu_alloc_mutex);	/* protects whole alloc and reclaim */
 static DEFINE_SPINLOCK(pcpu_lock);	/* protects index data structures */
 
 static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
-static struct rb_root pcpu_addr_root = RB_ROOT;	/* chunks by address */
 
 /* reclaim work to release fully free chunks, scheduled from free path */
 static void pcpu_reclaim(struct work_struct *work);
@@ -191,6 +200,18 @@ static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk,
 	return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL;
 }
 
+/* set the pointer to a chunk in a page struct */
+static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu)
+{
+	page->index = (unsigned long)pcpu;
+}
+
+/* obtain pointer to a chunk from a page struct */
+static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page)
+{
+	return (struct pcpu_chunk *)page->index;
+}
+
 /**
  * pcpu_mem_alloc - allocate memory
  * @size: bytes to allocate
@@ -257,93 +278,26 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
 	}
 }
 
-static struct rb_node **pcpu_chunk_rb_search(void *addr,
-					     struct rb_node **parentp)
-{
-	struct rb_node **p = &pcpu_addr_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct pcpu_chunk *chunk;
-
-	while (*p) {
-		parent = *p;
-		chunk = rb_entry(parent, struct pcpu_chunk, rb_node);
-
-		if (addr < chunk->vm->addr)
-			p = &(*p)->rb_left;
-		else if (addr > chunk->vm->addr)
-			p = &(*p)->rb_right;
-		else
-			break;
-	}
-
-	if (parentp)
-		*parentp = parent;
-	return p;
-}
-
 /**
- * pcpu_chunk_addr_search - search for chunk containing specified address
- * @addr: address to search for
- *
- * Look for chunk which might contain @addr.  More specifically, it
- * searchs for the chunk with the highest start address which isn't
- * beyond @addr.
- *
- * CONTEXT:
- * pcpu_lock.
+ * pcpu_chunk_addr_search - determine chunk containing specified address
+ * @addr: address for which the chunk needs to be determined.
  *
  * RETURNS:
  * The address of the found chunk.
  */
 static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 {
-	struct rb_node *n, *parent;
-	struct pcpu_chunk *chunk;
+	void *first_start = pcpu_first_chunk->vm->addr;
 
-	/* is it in the reserved chunk? */
-	if (pcpu_reserved_chunk) {
-		void *start = pcpu_reserved_chunk->vm->addr;
-
-		if (addr >= start && addr < start + pcpu_reserved_chunk_limit)
+	/* is it in the first chunk? */
+	if (addr >= first_start && addr < first_start + pcpu_chunk_size) {
+		/* is it in the reserved area? */
+		if (addr < first_start + pcpu_reserved_chunk_limit)
 			return pcpu_reserved_chunk;
+		return pcpu_first_chunk;
 	}
 
-	/* nah... search the regular ones */
-	n = *pcpu_chunk_rb_search(addr, &parent);
-	if (!n) {
-		/* no exactly matching chunk, the parent is the closest */
-		n = parent;
-		BUG_ON(!n);
-	}
-	chunk = rb_entry(n, struct pcpu_chunk, rb_node);
-
-	if (addr < chunk->vm->addr) {
-		/* the parent was the next one, look for the previous one */
-		n = rb_prev(n);
-		BUG_ON(!n);
-		chunk = rb_entry(n, struct pcpu_chunk, rb_node);
-	}
-
-	return chunk;
-}
-
-/**
- * pcpu_chunk_addr_insert - insert chunk into address rb tree
- * @new: chunk to insert
- *
- * Insert @new into address rb tree.
- *
- * CONTEXT:
- * pcpu_lock.
- */
-static void pcpu_chunk_addr_insert(struct pcpu_chunk *new)
-{
-	struct rb_node **p, *parent;
-
-	p = pcpu_chunk_rb_search(new->vm->addr, &parent);
-	BUG_ON(*p);
-	rb_link_node(&new->rb_node, parent, p);
-	rb_insert_color(&new->rb_node, &pcpu_addr_root);
+	return pcpu_get_page_chunk(vmalloc_to_page(addr));
 }
 
 /**
@@ -755,6 +709,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
 						  alloc_mask, 0);
 			if (!*pagep)
 				goto err;
+			pcpu_set_page_chunk(*pagep, chunk);
 		}
 	}
 
@@ -879,7 +834,6 @@ restart:
 
 	spin_lock_irq(&pcpu_lock);
 	pcpu_chunk_relocate(chunk, -1);
-	pcpu_chunk_addr_insert(chunk);
 	goto restart;
 
 area_found:
@@ -968,7 +922,6 @@ static void pcpu_reclaim(struct work_struct *work)
 		if (chunk == list_first_entry(head, struct pcpu_chunk, list))
 			continue;
 
-		rb_erase(&chunk->rb_node, &pcpu_addr_root);
 		list_move(&chunk->list, &todo);
 	}
 
@@ -1147,7 +1100,8 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 
 	if (reserved_size) {
 		schunk->free_size = reserved_size;
-		pcpu_reserved_chunk = schunk;	/* not for dynamic alloc */
+		pcpu_reserved_chunk = schunk;
+		pcpu_reserved_chunk_limit = static_size + reserved_size;
 	} else {
 		schunk->free_size = dyn_size;
 		dyn_size = 0;			/* dynamic area covered */
@@ -1158,8 +1112,6 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 	if (schunk->free_size)
 		schunk->map[schunk->map_used++] = schunk->free_size;
 
-	pcpu_reserved_chunk_limit = static_size + schunk->free_size;
-
 	/* init dynamic chunk if necessary */
 	if (dyn_size) {
 		dchunk = alloc_bootmem(sizeof(struct pcpu_chunk));
@@ -1226,13 +1178,8 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 	}
 
 	/* link the first chunk in */
-	if (!dchunk) {
-		pcpu_chunk_relocate(schunk, -1);
-		pcpu_chunk_addr_insert(schunk);
-	} else {
-		pcpu_chunk_relocate(dchunk, -1);
-		pcpu_chunk_addr_insert(dchunk);
-	}
+	pcpu_first_chunk = dchunk ?: schunk;
+	pcpu_chunk_relocate(pcpu_first_chunk, -1);
 
 	/* we're done */
 	pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0);
diff --git a/mm/shmem.c b/mm/shmem.c
index b25f95ce3db7..0132fbd45a23 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2659,6 +2659,7 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 	if (error)
 		goto close_file;
 #endif
+	ima_counts_get(file);
 	return file;
 
 close_file:
@@ -2684,7 +2685,6 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ima_shm_check(file);
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	vma->vm_file = file;
diff --git a/mm/slab.c b/mm/slab.c
index 9a90b00d2f91..f46b65d124e5 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -102,11 +102,12 @@
 #include	<linux/cpu.h>
 #include	<linux/sysctl.h>
 #include	<linux/module.h>
-#include	<trace/kmemtrace.h>
+#include	<linux/kmemtrace.h>
 #include	<linux/rcupdate.h>
 #include	<linux/string.h>
 #include	<linux/uaccess.h>
 #include	<linux/nodemask.h>
+#include	<linux/kmemleak.h>
 #include	<linux/mempolicy.h>
 #include	<linux/mutex.h>
 #include	<linux/fault-inject.h>
@@ -178,13 +179,13 @@
 			 SLAB_STORE_USER | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
-			 SLAB_DEBUG_OBJECTS)
+			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE)
 #else
 # define CREATE_MASK	(SLAB_HWCACHE_ALIGN | \
 			 SLAB_CACHE_DMA | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
-			 SLAB_DEBUG_OBJECTS)
+			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE)
 #endif
 
 /*
@@ -315,7 +316,7 @@ static int drain_freelist(struct kmem_cache *cache,
 			struct kmem_list3 *l3, int tofree);
 static void free_block(struct kmem_cache *cachep, void **objpp, int len,
 			int node);
-static int enable_cpucache(struct kmem_cache *cachep);
+static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp);
 static void cache_reap(struct work_struct *unused);
 
 /*
@@ -958,12 +959,20 @@ static void __cpuinit start_cpu_timer(int cpu)
 }
 
 static struct array_cache *alloc_arraycache(int node, int entries,
-					    int batchcount)
+					    int batchcount, gfp_t gfp)
 {
 	int memsize = sizeof(void *) * entries + sizeof(struct array_cache);
 	struct array_cache *nc = NULL;
 
-	nc = kmalloc_node(memsize, GFP_KERNEL, node);
+	nc = kmalloc_node(memsize, gfp, node);
+	/*
+	 * The array_cache structures contain pointers to free object.
+	 * However, when such objects are allocated or transfered to another
+	 * cache the pointers are not cleared and they could be counted as
+	 * valid references during a kmemleak scan. Therefore, kmemleak must
+	 * not scan such objects.
+	 */
+	kmemleak_no_scan(nc);
 	if (nc) {
 		nc->avail = 0;
 		nc->limit = entries;
@@ -1003,7 +1012,7 @@ static int transfer_objects(struct array_cache *to,
 #define drain_alien_cache(cachep, alien) do { } while (0)
 #define reap_alien(cachep, l3) do { } while (0)
 
-static inline struct array_cache **alloc_alien_cache(int node, int limit)
+static inline struct array_cache **alloc_alien_cache(int node, int limit, gfp_t gfp)
 {
 	return (struct array_cache **)BAD_ALIEN_MAGIC;
 }
@@ -1034,7 +1043,7 @@ static inline void *____cache_alloc_node(struct kmem_cache *cachep,
 static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
 static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
 
-static struct array_cache **alloc_alien_cache(int node, int limit)
+static struct array_cache **alloc_alien_cache(int node, int limit, gfp_t gfp)
 {
 	struct array_cache **ac_ptr;
 	int memsize = sizeof(void *) * nr_node_ids;
@@ -1042,14 +1051,14 @@ static struct array_cache **alloc_alien_cache(int node, int limit)
 
 	if (limit > 1)
 		limit = 12;
-	ac_ptr = kmalloc_node(memsize, GFP_KERNEL, node);
+	ac_ptr = kmalloc_node(memsize, gfp, node);
 	if (ac_ptr) {
 		for_each_node(i) {
 			if (i == node || !node_online(i)) {
 				ac_ptr[i] = NULL;
 				continue;
 			}
-			ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d);
+			ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d, gfp);
 			if (!ac_ptr[i]) {
 				for (i--; i >= 0; i--)
 					kfree(ac_ptr[i]);
@@ -1282,20 +1291,20 @@ static int __cpuinit cpuup_prepare(long cpu)
 		struct array_cache **alien = NULL;
 
 		nc = alloc_arraycache(node, cachep->limit,
-					cachep->batchcount);
+					cachep->batchcount, GFP_KERNEL);
 		if (!nc)
 			goto bad;
 		if (cachep->shared) {
 			shared = alloc_arraycache(node,
 				cachep->shared * cachep->batchcount,
-				0xbaadf00d);
+				0xbaadf00d, GFP_KERNEL);
 			if (!shared) {
 				kfree(nc);
 				goto bad;
 			}
 		}
 		if (use_alien_caches) {
-			alien = alloc_alien_cache(node, cachep->limit);
+			alien = alloc_alien_cache(node, cachep->limit, GFP_KERNEL);
 			if (!alien) {
 				kfree(shared);
 				kfree(nc);
@@ -1399,10 +1408,9 @@ static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
 {
 	struct kmem_list3 *ptr;
 
-	ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid);
+	ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_NOWAIT, nodeid);
 	BUG_ON(!ptr);
 
-	local_irq_disable();
 	memcpy(ptr, list, sizeof(struct kmem_list3));
 	/*
 	 * Do not assume that spinlocks can be initialized via memcpy:
@@ -1411,7 +1419,6 @@ static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
 
 	MAKE_ALL_LISTS(cachep, ptr, nodeid);
 	cachep->nodelists[nodeid] = ptr;
-	local_irq_enable();
 }
 
 /*
@@ -1575,9 +1582,8 @@ void __init kmem_cache_init(void)
 	{
 		struct array_cache *ptr;
 
-		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
+		ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
 
-		local_irq_disable();
 		BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache);
 		memcpy(ptr, cpu_cache_get(&cache_cache),
 		       sizeof(struct arraycache_init));
@@ -1587,11 +1593,9 @@ void __init kmem_cache_init(void)
 		spin_lock_init(&ptr->lock);
 
 		cache_cache.array[smp_processor_id()] = ptr;
-		local_irq_enable();
 
-		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
+		ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
 
-		local_irq_disable();
 		BUG_ON(cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep)
 		       != &initarray_generic.cache);
 		memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep),
@@ -1603,7 +1607,6 @@ void __init kmem_cache_init(void)
 
 		malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] =
 		    ptr;
-		local_irq_enable();
 	}
 	/* 5) Replace the bootstrap kmem_list3's */
 	{
@@ -1627,7 +1630,7 @@ void __init kmem_cache_init(void)
 		struct kmem_cache *cachep;
 		mutex_lock(&cache_chain_mutex);
 		list_for_each_entry(cachep, &cache_chain, next)
-			if (enable_cpucache(cachep))
+			if (enable_cpucache(cachep, GFP_NOWAIT))
 				BUG();
 		mutex_unlock(&cache_chain_mutex);
 	}
@@ -2064,10 +2067,10 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 	return left_over;
 }
 
-static int __init_refok setup_cpu_cache(struct kmem_cache *cachep)
+static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	if (g_cpucache_up == FULL)
-		return enable_cpucache(cachep);
+		return enable_cpucache(cachep, gfp);
 
 	if (g_cpucache_up == NONE) {
 		/*
@@ -2089,7 +2092,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep)
 			g_cpucache_up = PARTIAL_AC;
 	} else {
 		cachep->array[smp_processor_id()] =
-			kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
+			kmalloc(sizeof(struct arraycache_init), gfp);
 
 		if (g_cpucache_up == PARTIAL_AC) {
 			set_up_list3s(cachep, SIZE_L3);
@@ -2153,6 +2156,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 {
 	size_t left_over, slab_size, ralign;
 	struct kmem_cache *cachep = NULL, *pc;
+	gfp_t gfp;
 
 	/*
 	 * Sanity checks... these are all serious usage bugs.
@@ -2168,8 +2172,10 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	 * We use cache_chain_mutex to ensure a consistent view of
 	 * cpu_online_mask as well.  Please see cpuup_callback
 	 */
-	get_online_cpus();
-	mutex_lock(&cache_chain_mutex);
+	if (slab_is_available()) {
+		get_online_cpus();
+		mutex_lock(&cache_chain_mutex);
+	}
 
 	list_for_each_entry(pc, &cache_chain, next) {
 		char tmp;
@@ -2278,8 +2284,13 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	 */
 	align = ralign;
 
+	if (slab_is_available())
+		gfp = GFP_KERNEL;
+	else
+		gfp = GFP_NOWAIT;
+
 	/* Get cache's description obj. */
-	cachep = kmem_cache_zalloc(&cache_cache, GFP_KERNEL);
+	cachep = kmem_cache_zalloc(&cache_cache, gfp);
 	if (!cachep)
 		goto oops;
 
@@ -2382,7 +2393,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	cachep->ctor = ctor;
 	cachep->name = name;
 
-	if (setup_cpu_cache(cachep)) {
+	if (setup_cpu_cache(cachep, gfp)) {
 		__kmem_cache_destroy(cachep);
 		cachep = NULL;
 		goto oops;
@@ -2394,8 +2405,10 @@ oops:
 	if (!cachep && (flags & SLAB_PANIC))
 		panic("kmem_cache_create(): failed to create slab `%s'\n",
 		      name);
-	mutex_unlock(&cache_chain_mutex);
-	put_online_cpus();
+	if (slab_is_available()) {
+		mutex_unlock(&cache_chain_mutex);
+		put_online_cpus();
+	}
 	return cachep;
 }
 EXPORT_SYMBOL(kmem_cache_create);
@@ -2621,6 +2634,14 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
 		/* Slab management obj is off-slab. */
 		slabp = kmem_cache_alloc_node(cachep->slabp_cache,
 					      local_flags, nodeid);
+		/*
+		 * If the first object in the slab is leaked (it's allocated
+		 * but no one has a reference to it), we want to make sure
+		 * kmemleak does not treat the ->s_mem pointer as a reference
+		 * to the object. Otherwise we will not report the leak.
+		 */
+		kmemleak_scan_area(slabp, offsetof(struct slab, list),
+				   sizeof(struct list_head), local_flags);
 		if (!slabp)
 			return NULL;
 	} else {
@@ -3141,6 +3162,12 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 		STATS_INC_ALLOCMISS(cachep);
 		objp = cache_alloc_refill(cachep, flags);
 	}
+	/*
+	 * To avoid a false negative, if an object that is in one of the
+	 * per-CPU caches is leaked, we need to make sure kmemleak doesn't
+	 * treat the array pointers as a reference to the object.
+	 */
+	kmemleak_erase(&ac->entry[ac->avail]);
 	return objp;
 }
 
@@ -3360,6 +3387,8 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
   out:
 	local_irq_restore(save_flags);
 	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
+	kmemleak_alloc_recursive(ptr, obj_size(cachep), 1, cachep->flags,
+				 flags);
 
 	if (unlikely((flags & __GFP_ZERO) && ptr))
 		memset(ptr, 0, obj_size(cachep));
@@ -3415,6 +3444,8 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 	objp = __do_cache_alloc(cachep, flags);
 	local_irq_restore(save_flags);
 	objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
+	kmemleak_alloc_recursive(objp, obj_size(cachep), 1, cachep->flags,
+				 flags);
 	prefetchw(objp);
 
 	if (unlikely((flags & __GFP_ZERO) && objp))
@@ -3530,6 +3561,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
 	struct array_cache *ac = cpu_cache_get(cachep);
 
 	check_irq_off();
+	kmemleak_free_recursive(objp, cachep->flags);
 	objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
 
 	/*
@@ -3802,7 +3834,7 @@ EXPORT_SYMBOL_GPL(kmem_cache_name);
 /*
  * This initializes kmem_list3 or resizes various caches for all nodes.
  */
-static int alloc_kmemlist(struct kmem_cache *cachep)
+static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp)
 {
 	int node;
 	struct kmem_list3 *l3;
@@ -3812,7 +3844,7 @@ static int alloc_kmemlist(struct kmem_cache *cachep)
 	for_each_online_node(node) {
 
                 if (use_alien_caches) {
-                        new_alien = alloc_alien_cache(node, cachep->limit);
+                        new_alien = alloc_alien_cache(node, cachep->limit, gfp);
                         if (!new_alien)
                                 goto fail;
                 }
@@ -3821,7 +3853,7 @@ static int alloc_kmemlist(struct kmem_cache *cachep)
 		if (cachep->shared) {
 			new_shared = alloc_arraycache(node,
 				cachep->shared*cachep->batchcount,
-					0xbaadf00d);
+					0xbaadf00d, gfp);
 			if (!new_shared) {
 				free_alien_cache(new_alien);
 				goto fail;
@@ -3850,7 +3882,7 @@ static int alloc_kmemlist(struct kmem_cache *cachep)
 			free_alien_cache(new_alien);
 			continue;
 		}
-		l3 = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, node);
+		l3 = kmalloc_node(sizeof(struct kmem_list3), gfp, node);
 		if (!l3) {
 			free_alien_cache(new_alien);
 			kfree(new_shared);
@@ -3906,18 +3938,18 @@ static void do_ccupdate_local(void *info)
 
 /* Always called with the cache_chain_mutex held */
 static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
-				int batchcount, int shared)
+				int batchcount, int shared, gfp_t gfp)
 {
 	struct ccupdate_struct *new;
 	int i;
 
-	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	new = kzalloc(sizeof(*new), gfp);
 	if (!new)
 		return -ENOMEM;
 
 	for_each_online_cpu(i) {
 		new->new[i] = alloc_arraycache(cpu_to_node(i), limit,
-						batchcount);
+						batchcount, gfp);
 		if (!new->new[i]) {
 			for (i--; i >= 0; i--)
 				kfree(new->new[i]);
@@ -3944,11 +3976,11 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 		kfree(ccold);
 	}
 	kfree(new);
-	return alloc_kmemlist(cachep);
+	return alloc_kmemlist(cachep, gfp);
 }
 
 /* Called with cache_chain_mutex held always */
-static int enable_cpucache(struct kmem_cache *cachep)
+static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	int err;
 	int limit, shared;
@@ -3994,7 +4026,7 @@ static int enable_cpucache(struct kmem_cache *cachep)
 	if (limit > 32)
 		limit = 32;
 #endif
-	err = do_tune_cpucache(cachep, limit, (limit + 1) / 2, shared);
+	err = do_tune_cpucache(cachep, limit, (limit + 1) / 2, shared, gfp);
 	if (err)
 		printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n",
 		       cachep->name, -err);
@@ -4300,7 +4332,8 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer,
 				res = 0;
 			} else {
 				res = do_tune_cpucache(cachep, limit,
-						       batchcount, shared);
+						       batchcount, shared,
+						       GFP_KERNEL);
 			}
 			break;
 		}
diff --git a/mm/slob.c b/mm/slob.c
index f92e66d558bd..12f261499925 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -66,7 +66,8 @@
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <linux/list.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
+#include <linux/kmemleak.h>
 #include <asm/atomic.h>
 
 /*
@@ -509,6 +510,7 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
 				   size, PAGE_SIZE << order, gfp, node);
 	}
 
+	kmemleak_alloc(ret, size, 1, gfp);
 	return ret;
 }
 EXPORT_SYMBOL(__kmalloc_node);
@@ -521,6 +523,7 @@ void kfree(const void *block)
 
 	if (unlikely(ZERO_OR_NULL_PTR(block)))
 		return;
+	kmemleak_free(block);
 
 	sp = slob_page(block);
 	if (is_slob_page(sp)) {
@@ -584,12 +587,14 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 	} else if (flags & SLAB_PANIC)
 		panic("Cannot create slab cache %s\n", name);
 
+	kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL);
 	return c;
 }
 EXPORT_SYMBOL(kmem_cache_create);
 
 void kmem_cache_destroy(struct kmem_cache *c)
 {
+	kmemleak_free(c);
 	slob_free(c, sizeof(struct kmem_cache));
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
@@ -613,6 +618,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 	if (c->ctor)
 		c->ctor(b);
 
+	kmemleak_alloc_recursive(b, c->size, 1, c->flags, flags);
 	return b;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_node);
@@ -635,6 +641,7 @@ static void kmem_rcu_free(struct rcu_head *head)
 
 void kmem_cache_free(struct kmem_cache *c, void *b)
 {
+	kmemleak_free_recursive(b, c->flags);
 	if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
 		struct slob_rcu *slob_rcu;
 		slob_rcu = b + (c->size - sizeof(struct slob_rcu));
diff --git a/mm/slub.c b/mm/slub.c
index 65ffda5934b0..3964d3ce4c15 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -17,9 +17,10 @@
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
+#include <linux/kmemleak.h>
 #include <linux/mempolicy.h>
 #include <linux/ctype.h>
 #include <linux/debugobjects.h>
@@ -143,7 +144,7 @@
  * Set of flags that will prevent slab merging
  */
 #define SLUB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
-		SLAB_TRACE | SLAB_DESTROY_BY_RCU)
+		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE)
 
 #define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
 		SLAB_CACHE_DMA)
@@ -1617,6 +1618,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	if (unlikely((gfpflags & __GFP_ZERO) && object))
 		memset(object, 0, objsize);
 
+	kmemleak_alloc_recursive(object, objsize, 1, s->flags, gfpflags);
 	return object;
 }
 
@@ -1746,6 +1748,7 @@ static __always_inline void slab_free(struct kmem_cache *s,
 	struct kmem_cache_cpu *c;
 	unsigned long flags;
 
+	kmemleak_free_recursive(x, s->flags);
 	local_irq_save(flags);
 	c = get_cpu_slab(s, smp_processor_id());
 	debug_check_no_locks_freed(object, c->objsize);
@@ -2557,13 +2560,16 @@ static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
 	if (gfp_flags & SLUB_DMA)
 		flags = SLAB_CACHE_DMA;
 
-	down_write(&slub_lock);
+	/*
+	 * This function is called with IRQs disabled during early-boot on
+	 * single CPU so there's no need to take slub_lock here.
+	 */
 	if (!kmem_cache_open(s, gfp_flags, name, size, ARCH_KMALLOC_MINALIGN,
 								flags, NULL))
 		goto panic;
 
 	list_add(&s->list, &slab_caches);
-	up_write(&slub_lock);
+
 	if (sysfs_slab_add(s))
 		goto panic;
 	return s;
@@ -3021,7 +3027,7 @@ void __init kmem_cache_init(void)
 	 * kmem_cache_open for slab_state == DOWN.
 	 */
 	create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node",
-		sizeof(struct kmem_cache_node), GFP_KERNEL);
+		sizeof(struct kmem_cache_node), GFP_NOWAIT);
 	kmalloc_caches[0].refcount = -1;
 	caches++;
 
@@ -3034,16 +3040,16 @@ void __init kmem_cache_init(void)
 	/* Caches that are not of the two-to-the-power-of size */
 	if (KMALLOC_MIN_SIZE <= 64) {
 		create_kmalloc_cache(&kmalloc_caches[1],
-				"kmalloc-96", 96, GFP_KERNEL);
+				"kmalloc-96", 96, GFP_NOWAIT);
 		caches++;
 		create_kmalloc_cache(&kmalloc_caches[2],
-				"kmalloc-192", 192, GFP_KERNEL);
+				"kmalloc-192", 192, GFP_NOWAIT);
 		caches++;
 	}
 
 	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
 		create_kmalloc_cache(&kmalloc_caches[i],
-			"kmalloc", 1 << i, GFP_KERNEL);
+			"kmalloc", 1 << i, GFP_NOWAIT);
 		caches++;
 	}
 
@@ -3080,7 +3086,7 @@ void __init kmem_cache_init(void)
 	/* Provide the correct kmalloc names now that the caches are up */
 	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++)
 		kmalloc_caches[i]. name =
-			kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i);
+			kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i);
 
 #ifdef CONFIG_SMP
 	register_cpu_notifier(&slab_notifier);
diff --git a/mm/util.c b/mm/util.c
index 55bef160b9f1..abc65aa7cdfc 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -4,9 +4,11 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/sched.h>
-#include <linux/tracepoint.h>
 #include <asm/uaccess.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/kmem.h>
+
 /**
  * kstrdup - allocate space for and copy an existing string
  * @s: the string to duplicate
@@ -255,13 +257,6 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
 
 /* Tracepoints definitions. */
-DEFINE_TRACE(kmalloc);
-DEFINE_TRACE(kmem_cache_alloc);
-DEFINE_TRACE(kmalloc_node);
-DEFINE_TRACE(kmem_cache_alloc_node);
-DEFINE_TRACE(kfree);
-DEFINE_TRACE(kmem_cache_free);
-
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
 EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 083716ea38c9..f8189a4b3e13 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -23,8 +23,8 @@
 #include <linux/rbtree.h>
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
-#include <linux/bootmem.h>
 #include <linux/pfn.h>
+#include <linux/kmemleak.h>
 
 #include <asm/atomic.h>
 #include <asm/uaccess.h>
@@ -1032,7 +1032,7 @@ void __init vmalloc_init(void)
 
 	/* Import existing vmlist entries. */
 	for (tmp = vmlist; tmp; tmp = tmp->next) {
-		va = alloc_bootmem(sizeof(struct vmap_area));
+		va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT);
 		va->flags = tmp->flags | VM_VM_AREA;
 		va->va_start = (unsigned long)tmp->addr;
 		va->va_end = va->va_start + tmp->size;
@@ -1327,6 +1327,9 @@ static void __vunmap(const void *addr, int deallocate_pages)
 void vfree(const void *addr)
 {
 	BUG_ON(in_interrupt());
+
+	kmemleak_free(addr);
+
 	__vunmap(addr, 1);
 }
 EXPORT_SYMBOL(vfree);
@@ -1439,8 +1442,17 @@ fail:
 
 void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
 {
-	return __vmalloc_area_node(area, gfp_mask, prot, -1,
-					__builtin_return_address(0));
+	void *addr = __vmalloc_area_node(area, gfp_mask, prot, -1,
+					 __builtin_return_address(0));
+
+	/*
+	 * A ref_count = 3 is needed because the vm_struct and vmap_area
+	 * structures allocated in the __get_vm_area_node() function contain
+	 * references to the virtual address of the vmalloc'ed block.
+	 */
+	kmemleak_alloc(addr, area->size - PAGE_SIZE, 3, gfp_mask);
+
+	return addr;
 }
 
 /**
@@ -1459,6 +1471,8 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
 						int node, void *caller)
 {
 	struct vm_struct *area;
+	void *addr;
+	unsigned long real_size = size;
 
 	size = PAGE_ALIGN(size);
 	if (!size || (size >> PAGE_SHIFT) > num_physpages)
@@ -1470,7 +1484,16 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
 	if (!area)
 		return NULL;
 
-	return __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+	addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+
+	/*
+	 * A ref_count = 3 is needed because the vm_struct and vmap_area
+	 * structures allocated in the __get_vm_area_node() function contain
+	 * references to the virtual address of the vmalloc'ed block.
+	 */
+	kmemleak_alloc(addr, real_size, 3, gfp_mask);
+
+	return addr;
 }
 
 void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 9fd0dc3cca99..b75b6cea49da 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -23,7 +23,7 @@
 #include <linux/bitops.h>
 #include <net/genetlink.h>
 
-#include <trace/skb.h>
+#include <trace/events/skb.h>
 
 #include <asm/unaligned.h>
 
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index c8fb45665e4f..499a67eaf3ae 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -19,11 +19,11 @@
 #include <linux/workqueue.h>
 #include <linux/netlink.h>
 #include <linux/net_dropmon.h>
-#include <trace/skb.h>
 
 #include <asm/unaligned.h>
 #include <asm/bitops.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/skb.h>
 
-DEFINE_TRACE(kfree_skb);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e505b5392e1e..c2e4fb8f3546 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -65,7 +65,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
-#include <trace/skb.h>
+#include <trace/events/skb.h>
 
 #include "kmap_skb.h"
 
diff --git a/samples/Kconfig b/samples/Kconfig
index 4b02f5a0e656..b75d28cba3f7 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -19,6 +19,12 @@ config SAMPLE_TRACEPOINTS
 	help
 	  This build tracepoints example modules.
 
+config SAMPLE_TRACE_EVENTS
+	tristate "Build trace_events examples -- loadable modules only"
+	depends on EVENT_TRACING && m
+	help
+	  This build trace event example modules.
+
 config SAMPLE_KOBJECT
 	tristate "Build kobject examples"
 	help
diff --git a/samples/Makefile b/samples/Makefile
index 10eaca89fe17..13e4b470b539 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -1,3 +1,3 @@
 # Makefile for Linux samples code
 
-obj-$(CONFIG_SAMPLES)	+= markers/ kobject/ kprobes/ tracepoints/
+obj-$(CONFIG_SAMPLES)	+= markers/ kobject/ kprobes/ tracepoints/ trace_events/
diff --git a/samples/trace_events/Makefile b/samples/trace_events/Makefile
new file mode 100644
index 000000000000..0d428dc67283
--- /dev/null
+++ b/samples/trace_events/Makefile
@@ -0,0 +1,6 @@
+# builds the trace events example kernel modules;
+# then to use one (as root):  insmod <module_name.ko>
+
+CFLAGS_trace-events-sample.o := -I$(src)
+
+obj-$(CONFIG_SAMPLE_TRACE_EVENTS) += trace-events-sample.o
diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c
new file mode 100644
index 000000000000..aabc4e970911
--- /dev/null
+++ b/samples/trace_events/trace-events-sample.c
@@ -0,0 +1,52 @@
+#include <linux/module.h>
+#include <linux/kthread.h>
+
+/*
+ * Any file that uses trace points, must include the header.
+ * But only one file, must include the header by defining
+ * CREATE_TRACE_POINTS first.  This will make the C code that
+ * creates the handles for the trace points.
+ */
+#define CREATE_TRACE_POINTS
+#include "trace-events-sample.h"
+
+
+static void simple_thread_func(int cnt)
+{
+	set_current_state(TASK_INTERRUPTIBLE);
+	schedule_timeout(HZ);
+	trace_foo_bar("hello", cnt);
+}
+
+static int simple_thread(void *arg)
+{
+	int cnt = 0;
+
+	while (!kthread_should_stop())
+		simple_thread_func(cnt++);
+
+	return 0;
+}
+
+static struct task_struct *simple_tsk;
+
+static int __init trace_event_init(void)
+{
+	simple_tsk = kthread_run(simple_thread, NULL, "event-sample");
+	if (IS_ERR(simple_tsk))
+		return -1;
+
+	return 0;
+}
+
+static void __exit trace_event_exit(void)
+{
+	kthread_stop(simple_tsk);
+}
+
+module_init(trace_event_init);
+module_exit(trace_event_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("trace-events-sample");
+MODULE_LICENSE("GPL");
diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h
new file mode 100644
index 000000000000..128a897687c5
--- /dev/null
+++ b/samples/trace_events/trace-events-sample.h
@@ -0,0 +1,129 @@
+/*
+ * Notice that this file is not protected like a normal header.
+ * We also must allow for rereading of this file. The
+ *
+ *  || defined(TRACE_HEADER_MULTI_READ)
+ *
+ * serves this purpose.
+ */
+#if !defined(_TRACE_EVENT_SAMPLE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EVENT_SAMPLE_H
+
+/*
+ * All trace headers should include tracepoint.h, until we finally
+ * make it into a standard header.
+ */
+#include <linux/tracepoint.h>
+
+/*
+ * If TRACE_SYSTEM is defined, that will be the directory created
+ * in the ftrace directory under /debugfs/tracing/events/<system>
+ *
+ * The define_trace.h belowe will also look for a file name of
+ * TRACE_SYSTEM.h where TRACE_SYSTEM is what is defined here.
+ *
+ * If you want a different system than file name, you can override
+ * the header name by defining TRACE_INCLUDE_FILE
+ *
+ * If this file was called, goofy.h, then we would define:
+ *
+ * #define TRACE_INCLUDE_FILE goofy
+ *
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sample
+
+/*
+ * The TRACE_EVENT macro is broken up into 5 parts.
+ *
+ * name: name of the trace point. This is also how to enable the tracepoint.
+ *   A function called trace_foo_bar() will be created.
+ *
+ * proto: the prototype of the function trace_foo_bar()
+ *   Here it is trace_foo_bar(char *foo, int bar).
+ *
+ * args:  must match the arguments in the prototype.
+ *    Here it is simply "foo, bar".
+ *
+ * struct:  This defines the way the data will be stored in the ring buffer.
+ *    There are currently two types of elements. __field and __array.
+ *    a __field is broken up into (type, name). Where type can be any
+ *    type but an array.
+ *    For an array. there are three fields. (type, name, size). The
+ *    type of elements in the array, the name of the field and the size
+ *    of the array.
+ *
+ *    __array( char, foo, 10) is the same as saying   char foo[10].
+ *
+ * fast_assign: This is a C like function that is used to store the items
+ *    into the ring buffer.
+ *
+ * printk: This is a way to print out the data in pretty print. This is
+ *    useful if the system crashes and you are logging via a serial line,
+ *    the data can be printed to the console using this "printk" method.
+ *
+ * Note, that for both the assign and the printk, __entry is the handler
+ * to the data structure in the ring buffer, and is defined by the
+ * TP_STRUCT__entry.
+ */
+TRACE_EVENT(foo_bar,
+
+	TP_PROTO(char *foo, int bar),
+
+	TP_ARGS(foo, bar),
+
+	TP_STRUCT__entry(
+		__array(	char,	foo,    10		)
+		__field(	int,	bar			)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->foo, foo, 10);
+		__entry->bar	= bar;
+	),
+
+	TP_printk("foo %s %d", __entry->foo, __entry->bar)
+);
+#endif
+
+/***** NOTICE! The #if protection ends here. *****/
+
+
+/*
+ * There are several ways I could have done this. If I left out the
+ * TRACE_INCLUDE_PATH, then it would default to the kernel source
+ * include/trace/events directory.
+ *
+ * I could specify a path from the define_trace.h file back to this
+ * file.
+ *
+ * #define TRACE_INCLUDE_PATH ../../samples/trace_events
+ *
+ * But I chose to simply make it use the current directory and then in
+ * the Makefile I added:
+ *
+ * CFLAGS_trace-events-sample.o := -I$(PWD)/samples/trace_events/
+ *
+ * This will make sure the current path is part of the include
+ * structure for our file so that we can find it.
+ *
+ * I could have made only the top level directory the include:
+ *
+ * CFLAGS_trace-events-sample.o := -I$(PWD)
+ *
+ * And then let the path to this directory be the TRACE_INCLUDE_PATH:
+ *
+ * #define TRACE_INCLUDE_PATH samples/trace_events
+ *
+ * But then if something defines "samples" or "trace_events" then we
+ * could risk that being converted too, and give us an unexpected
+ * result.
+ */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+/*
+ * TRACE_INCLUDE_FILE is not needed if the filename and TRACE_SYSTEM are equal
+ */
+#define TRACE_INCLUDE_FILE trace-events-sample
+#include <trace/define_trace.h>
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index cba61ca403ca..2b706617c89a 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -188,20 +188,34 @@ cmd_objcopy = $(OBJCOPY) $(OBJCOPYFLAGS) $(OBJCOPYFLAGS_$(@F)) $< $@
 # ---------------------------------------------------------------------------
 
 quiet_cmd_gzip = GZIP    $@
-cmd_gzip = gzip -f -9 < $< > $@
+cmd_gzip = (cat $(filter-out FORCE,$^) | gzip -f -9 > $@) || \
+	(rm -f $@ ; false)
 
 
 # Bzip2
 # ---------------------------------------------------------------------------
 
-# Bzip2 does not include size in file... so we have to fake that
-size_append=$(CONFIG_SHELL) $(srctree)/scripts/bin_size
+# Bzip2 and LZMA do not include size in file... so we have to fake that;
+# append the size as a 32-bit littleendian number as gzip does.
+size_append = echo -ne $(shell						\
+dec_size=0;								\
+for F in $1; do								\
+	fsize=$$(stat -c "%s" $$F);					\
+	dec_size=$$(expr $$dec_size + $$fsize);				\
+done;									\
+printf "%08x" $$dec_size |						\
+	sed 's/\(..\)\(..\)\(..\)\(..\)/\\\\x\4\\\\x\3\\\\x\2\\\\x\1/g'	\
+)
 
-quiet_cmd_bzip2 = BZIP2    $@
-cmd_bzip2 = (bzip2 -9 < $< && $(size_append) $<) > $@ || (rm -f $@ ; false)
+quiet_cmd_bzip2 = BZIP2   $@
+cmd_bzip2 = (cat $(filter-out FORCE,$^) | \
+	bzip2 -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
+	(rm -f $@ ; false)
 
 # Lzma
 # ---------------------------------------------------------------------------
 
 quiet_cmd_lzma = LZMA    $@
-cmd_lzma = (lzma -9 -c $< && $(size_append) $<) >$@ || (rm -f $@ ; false)
+cmd_lzma = (cat $(filter-out FORCE,$^) | \
+	lzma -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
+	(rm -f $@ ; false)
diff --git a/scripts/bin_size b/scripts/bin_size
deleted file mode 100644
index 43e1b360cee6..000000000000
--- a/scripts/bin_size
+++ /dev/null
@@ -1,10 +0,0 @@
-#!/bin/sh
-
-if [ $# = 0 ] ; then
-   echo Usage: $0 file
-fi
-
-size_dec=`stat -c "%s" $1`
-size_hex_echo_string=`printf "%08x" $size_dec |
-     sed 's/\(..\)\(..\)\(..\)\(..\)/\\\\x\4\\\\x\3\\\\x\2\\\\x\1/g'`
-/bin/echo -ne $size_hex_echo_string
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 3208a3a7e7fe..acd8c4a8e3e0 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1828,6 +1828,25 @@ sub reset_state {
     $state = 0;
 }
 
+sub tracepoint_munge($) {
+	my $file = shift;
+	my $tracepointname = 0;
+	my $tracepointargs = 0;
+
+	if($prototype =~ m/TRACE_EVENT\((.*?),/) {
+		$tracepointname = $1;
+	}
+	if($prototype =~ m/TP_PROTO\((.*?)\)/) {
+		$tracepointargs = $1;
+	}
+	if (($tracepointname eq 0) || ($tracepointargs eq 0)) {
+		print STDERR "Warning(${file}:$.): Unrecognized tracepoint format: \n".
+			     "$prototype\n";
+	} else {
+		$prototype = "static inline void trace_$tracepointname($tracepointargs)";
+	}
+}
+
 sub syscall_munge() {
 	my $void = 0;
 
@@ -1882,6 +1901,9 @@ sub process_state3_function($$) {
 	if ($prototype =~ /SYSCALL_DEFINE/) {
 		syscall_munge();
 	}
+	if ($prototype =~ /TRACE_EVENT/) {
+		tracepoint_munge($file);
+	}
 	dump_function($prototype, $file);
 	reset_state();
     }
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 409596eca124..0fae7da0529c 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -26,7 +26,7 @@
 # which will also be the location of that section after final link.
 # e.g.
 #
-#  .section ".text.sched"
+#  .section ".sched.text", "ax"
 #  .globl my_func
 #  my_func:
 #        [...]
@@ -39,7 +39,7 @@
 #        [...]
 #
 # Both relocation offsets for the mcounts in the above example will be
-# offset from .text.sched. If we make another file called tmp.s with:
+# offset from .sched.text. If we make another file called tmp.s with:
 #
 #  .section __mcount_loc
 #  .quad  my_func + 0x5
@@ -51,7 +51,7 @@
 # But this gets hard if my_func is not globl (a static function).
 # In such a case we have:
 #
-#  .section ".text.sched"
+#  .section ".sched.text", "ax"
 #  my_func:
 #        [...]
 #        call mcount  (offset: 0x5)
diff --git a/security/Kconfig b/security/Kconfig
index bb244774e9d7..d23c839038f0 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -110,29 +110,9 @@ config SECURITY_ROOTPLUG
 
 	  See <http://www.linuxjournal.com/article.php?sid=6279> for
 	  more information about this module.
-	  
+
 	  If you are unsure how to answer this question, answer N.
 
-config SECURITY_DEFAULT_MMAP_MIN_ADDR
-        int "Low address space to protect from user allocation"
-        depends on SECURITY
-        default 0
-        help
-	  This is the portion of low virtual memory which should be protected
-	  from userspace allocation.  Keeping a user from writing to low pages
-	  can help reduce the impact of kernel NULL pointer bugs.
-
-	  For most ia64, ppc64 and x86 users with lots of address space
-	  a value of 65536 is reasonable and should cause no problems.
-	  On arm and other archs it should not be higher than 32768.
-	  Programs which use vm86 functionality would either need additional
-	  permissions from either the LSM or the capabilities module or have
-	  this protection disabled.
-
-	  This value can be changed after boot using the
-	  /proc/sys/vm/mmap_min_addr tunable.
-
-
 source security/selinux/Kconfig
 source security/smack/Kconfig
 source security/tomoyo/Kconfig
diff --git a/security/Makefile b/security/Makefile
index fa77021d9778..c67557cdaa85 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -16,6 +16,9 @@ obj-$(CONFIG_SECURITYFS)		+= inode.o
 # Must precede capability.o in order to stack properly.
 obj-$(CONFIG_SECURITY_SELINUX)		+= selinux/built-in.o
 obj-$(CONFIG_SECURITY_SMACK)		+= smack/built-in.o
+ifeq ($(CONFIG_AUDIT),y)
+obj-$(CONFIG_SECURITY_SMACK)		+= lsm_audit.o
+endif
 obj-$(CONFIG_SECURITY_TOMOYO)		+= tomoyo/built-in.o
 obj-$(CONFIG_SECURITY_ROOTPLUG)		+= root_plug.o
 obj-$(CONFIG_CGROUP_DEVICE)		+= device_cgroup.o
diff --git a/security/commoncap.c b/security/commoncap.c
index beac0258c2a8..48b7e0228fa3 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -28,6 +28,28 @@
 #include <linux/prctl.h>
 #include <linux/securebits.h>
 
+/*
+ * If a non-root user executes a setuid-root binary in
+ * !secure(SECURE_NOROOT) mode, then we raise capabilities.
+ * However if fE is also set, then the intent is for only
+ * the file capabilities to be applied, and the setuid-root
+ * bit is left on either to change the uid (plausible) or
+ * to get full privilege on a kernel without file capabilities
+ * support.  So in that case we do not raise capabilities.
+ *
+ * Warn if that happens, once per boot.
+ */
+static void warn_setuid_and_fcaps_mixed(char *fname)
+{
+	static int warned;
+	if (!warned) {
+		printk(KERN_INFO "warning: `%s' has both setuid-root and"
+			" effective capabilities. Therefore not raising all"
+			" capabilities.\n", fname);
+		warned = 1;
+	}
+}
+
 int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
 	NETLINK_CB(skb).eff_cap = current_cap();
@@ -463,6 +485,15 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 		return ret;
 
 	if (!issecure(SECURE_NOROOT)) {
+		/*
+		 * If the legacy file capability is set, then don't set privs
+		 * for a setuid root binary run by a non-root user.  Do set it
+		 * for a root user just to cause least surprise to an admin.
+		 */
+		if (effective && new->uid != 0 && new->euid == 0) {
+			warn_setuid_and_fcaps_mixed(bprm->filename);
+			goto skip;
+		}
 		/*
 		 * To support inheritance of root-permissions and suid-root
 		 * executables under compatibility mode, we override the
@@ -478,6 +509,7 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 		if (new->euid == 0)
 			effective = true;
 	}
+skip:
 
 	/* Don't let someone trace a set[ug]id/setpcap binary with the revised
 	 * credentials unless they have the appropriate permit
diff --git a/security/inode.c b/security/inode.c
index f3b91bfbe4cb..f7496c6a022b 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -287,7 +287,7 @@ void securityfs_remove(struct dentry *dentry)
 {
 	struct dentry *parent;
 
-	if (!dentry)
+	if (!dentry || IS_ERR(dentry))
 		return;
 
 	parent = dentry->d_parent;
diff --git a/security/integrity/ima/ima_audit.c b/security/integrity/ima/ima_audit.c
index 1e082bb987be..ff513ff737f5 100644
--- a/security/integrity/ima/ima_audit.c
+++ b/security/integrity/ima/ima_audit.c
@@ -22,18 +22,9 @@ static int ima_audit;
 static int __init ima_audit_setup(char *str)
 {
 	unsigned long audit;
-	int rc, result = 0;
-	char *op = "ima_audit";
-	char *cause;
 
-	rc = strict_strtoul(str, 0, &audit);
-	if (rc || audit > 1)
-		result = 1;
-	else
-		ima_audit = audit;
-	cause = ima_audit ? "enabled" : "not_enabled";
-	integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL, NULL,
-			    op, cause, result, 0);
+	if (!strict_strtoul(str, 0, &audit))
+		ima_audit = audit ? 1 : 0;
 	return 1;
 }
 __setup("ima_audit=", ima_audit_setup);
@@ -50,23 +41,14 @@ void integrity_audit_msg(int audit_msgno, struct inode *inode,
 
 	ab = audit_log_start(current->audit_context, GFP_KERNEL, audit_msgno);
 	audit_log_format(ab, "integrity: pid=%d uid=%u auid=%u ses=%u",
-			 current->pid, current->cred->uid,
+			 current->pid, current_cred()->uid,
 			 audit_get_loginuid(current),
 			 audit_get_sessionid(current));
 	audit_log_task_context(ab);
-	switch (audit_msgno) {
-	case AUDIT_INTEGRITY_DATA:
-	case AUDIT_INTEGRITY_METADATA:
-	case AUDIT_INTEGRITY_PCR:
-	case AUDIT_INTEGRITY_STATUS:
-		audit_log_format(ab, " op=%s cause=%s", op, cause);
-		break;
-	case AUDIT_INTEGRITY_HASH:
-		audit_log_format(ab, " op=%s hash=%s", op, cause);
-		break;
-	default:
-		audit_log_format(ab, " op=%s", op);
-	}
+	audit_log_format(ab, " op=");
+	audit_log_string(ab, op);
+	audit_log_format(ab, " cause=");
+	audit_log_string(ab, cause);
 	audit_log_format(ab, " comm=");
 	audit_log_untrustedstring(ab, current->comm);
 	if (fname) {
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 50d572b74caf..63003a63aaee 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -103,7 +103,7 @@ int ima_calc_template_hash(int template_len, void *template, char *digest)
 	return rc;
 }
 
-static void ima_pcrread(int idx, u8 *pcr)
+static void __init ima_pcrread(int idx, u8 *pcr)
 {
 	if (!ima_used_chip)
 		return;
@@ -115,7 +115,7 @@ static void ima_pcrread(int idx, u8 *pcr)
 /*
  * Calculate the boot aggregate hash
  */
-int ima_calc_boot_aggregate(char *digest)
+int __init ima_calc_boot_aggregate(char *digest)
 {
 	struct hash_desc desc;
 	struct scatterlist sg;
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index ffbe259700b1..6bfc7eaebfda 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -15,6 +15,7 @@
  *	implemenents security file system for reporting
  *	current measurement list and IMA statistics
  */
+#include <linux/fcntl.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/rculist.h>
@@ -84,8 +85,8 @@ static void *ima_measurements_next(struct seq_file *m, void *v, loff_t *pos)
 	 * against concurrent list-extension
 	 */
 	rcu_read_lock();
-	qe = list_entry(rcu_dereference(qe->later.next),
-			struct ima_queue_entry, later);
+	qe = list_entry_rcu(qe->later.next,
+			    struct ima_queue_entry, later);
 	rcu_read_unlock();
 	(*pos)++;
 
@@ -283,6 +284,9 @@ static atomic_t policy_opencount = ATOMIC_INIT(1);
  */
 int ima_open_policy(struct inode * inode, struct file * filp)
 {
+	/* No point in being allowed to open it if you aren't going to write */
+	if (!(filp->f_flags & O_WRONLY))
+		return -EACCES;
 	if (atomic_dec_and_test(&policy_opencount))
 		return 0;
 	return -EBUSY;
@@ -315,7 +319,7 @@ static struct file_operations ima_measure_policy_ops = {
 	.release = ima_release_policy
 };
 
-int ima_fs_init(void)
+int __init ima_fs_init(void)
 {
 	ima_dir = securityfs_create_dir("ima", NULL);
 	if (IS_ERR(ima_dir))
@@ -349,7 +353,7 @@ int ima_fs_init(void)
 		goto out;
 
 	ima_policy = securityfs_create_file("policy",
-					    S_IRUSR | S_IRGRP | S_IWUSR,
+					    S_IWUSR,
 					    ima_dir, NULL,
 					    &ima_measure_policy_ops);
 	if (IS_ERR(ima_policy))
diff --git a/security/integrity/ima/ima_iint.c b/security/integrity/ima/ima_iint.c
index ec79f1ee992c..b8dd693f8790 100644
--- a/security/integrity/ima/ima_iint.c
+++ b/security/integrity/ima/ima_iint.c
@@ -196,7 +196,7 @@ static void init_once(void *foo)
 	kref_set(&iint->refcount, 1);
 }
 
-void ima_iintcache_init(void)
+void __init ima_iintcache_init(void)
 {
 	iint_cache =
 	    kmem_cache_create("iint_cache", sizeof(struct ima_iint_cache), 0,
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 0b0bb8c978cc..a40da7ae5900 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -38,7 +38,7 @@ int ima_used_chip;
  * a different value.) Violations add a zero entry to the measurement
  * list and extend the aggregate PCR value with ff...ff's.
  */
-static void ima_add_boot_aggregate(void)
+static void __init ima_add_boot_aggregate(void)
 {
 	struct ima_template_entry *entry;
 	const char *op = "add_boot_aggregate";
@@ -71,7 +71,7 @@ err_out:
 			    audit_cause, result, 0);
 }
 
-int ima_init(void)
+int __init ima_init(void)
 {
 	u8 pcr_i[IMA_DIGEST_SIZE];
 	int rc;
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index f4e7266f5aee..6f611874d10e 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -29,20 +29,8 @@ int ima_initialized;
 char *ima_hash = "sha1";
 static int __init hash_setup(char *str)
 {
-	const char *op = "hash_setup";
-	const char *hash = "sha1";
-	int result = 0;
-	int audit_info = 0;
-
-	if (strncmp(str, "md5", 3) == 0) {
-		hash = "md5";
-		ima_hash = str;
-	} else if (strncmp(str, "sha1", 4) != 0) {
-		hash = "invalid_hash_type";
-		result = 1;
-	}
-	integrity_audit_msg(AUDIT_INTEGRITY_HASH, NULL, NULL, op, hash,
-			    result, audit_info);
+	if (strncmp(str, "md5", 3) == 0)
+		ima_hash = "md5";
 	return 1;
 }
 __setup("ima_hash=", hash_setup);
@@ -128,10 +116,6 @@ static int get_path_measurement(struct ima_iint_cache *iint, struct file *file,
 {
 	int rc = 0;
 
-	if (IS_ERR(file)) {
-		pr_info("%s dentry_open failed\n", filename);
-		return rc;
-	}
 	iint->opencount++;
 	iint->readcount++;
 
@@ -141,6 +125,15 @@ static int get_path_measurement(struct ima_iint_cache *iint, struct file *file,
 	return rc;
 }
 
+static void ima_update_counts(struct ima_iint_cache *iint, int mask)
+{
+	iint->opencount++;
+	if ((mask & MAY_WRITE) || (mask == 0))
+		iint->writecount++;
+	else if (mask & (MAY_READ | MAY_EXEC))
+		iint->readcount++;
+}
+
 /**
  * ima_path_check - based on policy, collect/store measurement.
  * @path: contains a pointer to the path to be measured
@@ -156,10 +149,10 @@ static int get_path_measurement(struct ima_iint_cache *iint, struct file *file,
  *	- Opening a file for read when already open for write,
  * 	  could result in a file measurement error.
  *
- * Return 0 on success, an error code on failure.
- * (Based on the results of appraise_measurement().)
+ * Always return 0 and audit dentry_open failures.
+ * (Return code will be based upon measurement appraisal.)
  */
-int ima_path_check(struct path *path, int mask)
+int ima_path_check(struct path *path, int mask, int update_counts)
 {
 	struct inode *inode = path->dentry->d_inode;
 	struct ima_iint_cache *iint;
@@ -173,11 +166,8 @@ int ima_path_check(struct path *path, int mask)
 		return 0;
 
 	mutex_lock(&iint->mutex);
-	iint->opencount++;
-	if ((mask & MAY_WRITE) || (mask == 0))
-		iint->writecount++;
-	else if (mask & (MAY_READ | MAY_EXEC))
-		iint->readcount++;
+	if (update_counts)
+		ima_update_counts(iint, mask);
 
 	rc = ima_must_measure(iint, inode, MAY_READ, PATH_CHECK);
 	if (rc < 0)
@@ -196,7 +186,19 @@ int ima_path_check(struct path *path, int mask)
 		struct dentry *dentry = dget(path->dentry);
 		struct vfsmount *mnt = mntget(path->mnt);
 
-		file = dentry_open(dentry, mnt, O_RDONLY, current->cred);
+		file = dentry_open(dentry, mnt, O_RDONLY | O_LARGEFILE,
+				   current_cred());
+		if (IS_ERR(file)) {
+			int audit_info = 0;
+
+			integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
+					    dentry->d_name.name,
+					    "add_measurement",
+					    "dentry_open failed",
+					    1, audit_info);
+			file = NULL;
+			goto out;
+		}
 		rc = get_path_measurement(iint, file, dentry->d_name.name);
 	}
 out:
@@ -206,6 +208,7 @@ out:
 	kref_put(&iint->refcount, iint_free);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ima_path_check);
 
 static int process_measurement(struct file *file, const unsigned char *filename,
 			       int mask, int function)
@@ -234,7 +237,16 @@ out:
 	return rc;
 }
 
-static void opencount_get(struct file *file)
+/*
+ * ima_opens_get - increment file counts
+ *
+ * - for IPC shm and shmat file.
+ * - for nfsd exported files.
+ *
+ * Increment the counts for these files to prevent unnecessary
+ * imbalance messages.
+ */
+void ima_counts_get(struct file *file)
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ima_iint_cache *iint;
@@ -246,8 +258,14 @@ static void opencount_get(struct file *file)
 		return;
 	mutex_lock(&iint->mutex);
 	iint->opencount++;
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+		iint->readcount++;
+
+	if (file->f_mode & FMODE_WRITE)
+		iint->writecount++;
 	mutex_unlock(&iint->mutex);
 }
+EXPORT_SYMBOL_GPL(ima_counts_get);
 
 /**
  * ima_file_mmap - based on policy, collect/store measurement.
@@ -272,18 +290,6 @@ int ima_file_mmap(struct file *file, unsigned long prot)
 	return 0;
 }
 
-/*
- * ima_shm_check - IPC shm and shmat create/fput a file
- *
- * Maintain the opencount for these files to prevent unnecessary
- * imbalance messages.
- */
-void ima_shm_check(struct file *file)
-{
-	opencount_get(file);
-	return;
-}
-
 /**
  * ima_bprm_check - based on policy, collect/store measurement.
  * @bprm: contains the linux_binprm structure
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index b5291ad5ef56..e1278399b345 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -45,24 +45,30 @@ struct ima_measure_rule_entry {
 	} lsm[MAX_LSM_RULES];
 };
 
-/* Without LSM specific knowledge, the default policy can only be
+/*
+ * Without LSM specific knowledge, the default policy can only be
  * written in terms of .action, .func, .mask, .fsmagic, and .uid
  */
+
+/*
+ * The minimum rule set to allow for full TCB coverage.  Measures all files
+ * opened or mmap for exec and everything read by root.  Dangerous because
+ * normal users can easily run the machine out of memory simply building
+ * and running executables.
+ */
 static struct ima_measure_rule_entry default_rules[] = {
-	{.action = DONT_MEASURE,.fsmagic = PROC_SUPER_MAGIC,
-	 .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE,.fsmagic = PROC_SUPER_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = SYSFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = DEBUGFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = TMPFS_MAGIC,.flags = IMA_FSMAGIC},
-	{.action = DONT_MEASURE,.fsmagic = SECURITYFS_MAGIC,
-	 .flags = IMA_FSMAGIC},
-	{.action = DONT_MEASURE,.fsmagic = 0xF97CFF8C,.flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE,.fsmagic = SECURITYFS_MAGIC,.flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE,.fsmagic = SELINUX_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = MEASURE,.func = FILE_MMAP,.mask = MAY_EXEC,
 	 .flags = IMA_FUNC | IMA_MASK},
 	{.action = MEASURE,.func = BPRM_CHECK,.mask = MAY_EXEC,
 	 .flags = IMA_FUNC | IMA_MASK},
 	{.action = MEASURE,.func = PATH_CHECK,.mask = MAY_READ,.uid = 0,
-	 .flags = IMA_FUNC | IMA_MASK | IMA_UID}
+	 .flags = IMA_FUNC | IMA_MASK | IMA_UID},
 };
 
 static LIST_HEAD(measure_default_rules);
@@ -71,6 +77,14 @@ static struct list_head *ima_measure;
 
 static DEFINE_MUTEX(ima_measure_mutex);
 
+static bool ima_use_tcb __initdata;
+static int __init default_policy_setup(char *str)
+{
+	ima_use_tcb = 1;
+	return 1;
+}
+__setup("ima_tcb", default_policy_setup);
+
 /**
  * ima_match_rules - determine whether an inode matches the measure rule.
  * @rule: a pointer to a rule
@@ -96,7 +110,7 @@ static bool ima_match_rules(struct ima_measure_rule_entry *rule,
 	if ((rule->flags & IMA_UID) && rule->uid != tsk->cred->uid)
 		return false;
 	for (i = 0; i < MAX_LSM_RULES; i++) {
-		int rc;
+		int rc = 0;
 		u32 osid, sid;
 
 		if (!rule->lsm[i].rule)
@@ -109,7 +123,7 @@ static bool ima_match_rules(struct ima_measure_rule_entry *rule,
 			security_inode_getsecid(inode, &osid);
 			rc = security_filter_rule_match(osid,
 							rule->lsm[i].type,
-							AUDIT_EQUAL,
+							Audit_equal,
 							rule->lsm[i].rule,
 							NULL);
 			break;
@@ -119,7 +133,7 @@ static bool ima_match_rules(struct ima_measure_rule_entry *rule,
 			security_task_getsecid(tsk, &sid);
 			rc = security_filter_rule_match(sid,
 							rule->lsm[i].type,
-							AUDIT_EQUAL,
+							Audit_equal,
 							rule->lsm[i].rule,
 							NULL);
 		default:
@@ -164,11 +178,17 @@ int ima_match_policy(struct inode *inode, enum ima_hooks func, int mask)
  * ima_measure points to either the measure_default_rules or the
  * the new measure_policy_rules.
  */
-void ima_init_policy(void)
+void __init ima_init_policy(void)
 {
-	int i;
+	int i, entries;
 
-	for (i = 0; i < ARRAY_SIZE(default_rules); i++)
+	/* if !ima_use_tcb set entries = 0 so we load NO default rules */
+	if (ima_use_tcb)
+		entries = ARRAY_SIZE(default_rules);
+	else
+		entries = 0;
+
+	for (i = 0; i < entries; i++)
 		list_add_tail(&default_rules[i].list, &measure_default_rules);
 	ima_measure = &measure_default_rules;
 }
@@ -227,7 +247,7 @@ static int ima_lsm_rule_init(struct ima_measure_rule_entry *entry,
 
 	entry->lsm[lsm_rule].type = audit_type;
 	result = security_filter_rule_init(entry->lsm[lsm_rule].type,
-					   AUDIT_EQUAL, args,
+					   Audit_equal, args,
 					   &entry->lsm[lsm_rule].rule);
 	return result;
 }
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
new file mode 100644
index 000000000000..94b868494b31
--- /dev/null
+++ b/security/lsm_audit.c
@@ -0,0 +1,386 @@
+/*
+ * common LSM auditing functions
+ *
+ * Based on code written for SELinux by :
+ *			Stephen Smalley, <sds@epoch.ncsc.mil>
+ * 			James Morris <jmorris@redhat.com>
+ * Author : Etienne Basset, <etienne.basset@ensta.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <net/sock.h>
+#include <linux/un.h>
+#include <net/af_unix.h>
+#include <linux/audit.h>
+#include <linux/ipv6.h>
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/dccp.h>
+#include <linux/sctp.h>
+#include <linux/lsm_audit.h>
+
+/**
+ * ipv4_skb_to_auditdata : fill auditdata from skb
+ * @skb : the skb
+ * @ad : the audit data to fill
+ * @proto : the layer 4 protocol
+ *
+ * return  0 on success
+ */
+int ipv4_skb_to_auditdata(struct sk_buff *skb,
+		struct common_audit_data *ad, u8 *proto)
+{
+	int ret = 0;
+	struct iphdr *ih;
+
+	ih = ip_hdr(skb);
+	if (ih == NULL)
+		return -EINVAL;
+
+	ad->u.net.v4info.saddr = ih->saddr;
+	ad->u.net.v4info.daddr = ih->daddr;
+
+	if (proto)
+		*proto = ih->protocol;
+	/* non initial fragment */
+	if (ntohs(ih->frag_off) & IP_OFFSET)
+		return 0;
+
+	switch (ih->protocol) {
+	case IPPROTO_TCP: {
+		struct tcphdr *th = tcp_hdr(skb);
+		if (th == NULL)
+			break;
+
+		ad->u.net.sport = th->source;
+		ad->u.net.dport = th->dest;
+		break;
+	}
+	case IPPROTO_UDP: {
+		struct udphdr *uh = udp_hdr(skb);
+		if (uh == NULL)
+			break;
+
+		ad->u.net.sport = uh->source;
+		ad->u.net.dport = uh->dest;
+		break;
+	}
+	case IPPROTO_DCCP: {
+		struct dccp_hdr *dh = dccp_hdr(skb);
+		if (dh == NULL)
+			break;
+
+		ad->u.net.sport = dh->dccph_sport;
+		ad->u.net.dport = dh->dccph_dport;
+		break;
+	}
+	case IPPROTO_SCTP: {
+		struct sctphdr *sh = sctp_hdr(skb);
+		if (sh == NULL)
+			break;
+		ad->u.net.sport = sh->source;
+		ad->u.net.dport = sh->dest;
+		break;
+	}
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+/**
+ * ipv6_skb_to_auditdata : fill auditdata from skb
+ * @skb : the skb
+ * @ad : the audit data to fill
+ * @proto : the layer 4 protocol
+ *
+ * return  0 on success
+ */
+int ipv6_skb_to_auditdata(struct sk_buff *skb,
+		struct common_audit_data *ad, u8 *proto)
+{
+	int offset, ret = 0;
+	struct ipv6hdr *ip6;
+	u8 nexthdr;
+
+	ip6 = ipv6_hdr(skb);
+	if (ip6 == NULL)
+		return -EINVAL;
+	ipv6_addr_copy(&ad->u.net.v6info.saddr, &ip6->saddr);
+	ipv6_addr_copy(&ad->u.net.v6info.daddr, &ip6->daddr);
+	ret = 0;
+	/* IPv6 can have several extension header before the Transport header
+	 * skip them */
+	offset = skb_network_offset(skb);
+	offset += sizeof(*ip6);
+	nexthdr = ip6->nexthdr;
+	offset = ipv6_skip_exthdr(skb, offset, &nexthdr);
+	if (offset < 0)
+		return 0;
+	if (proto)
+		*proto = nexthdr;
+	switch (nexthdr) {
+	case IPPROTO_TCP: {
+		struct tcphdr _tcph, *th;
+
+		th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
+		if (th == NULL)
+			break;
+
+		ad->u.net.sport = th->source;
+		ad->u.net.dport = th->dest;
+		break;
+	}
+	case IPPROTO_UDP: {
+		struct udphdr _udph, *uh;
+
+		uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
+		if (uh == NULL)
+			break;
+
+		ad->u.net.sport = uh->source;
+		ad->u.net.dport = uh->dest;
+		break;
+	}
+	case IPPROTO_DCCP: {
+		struct dccp_hdr _dccph, *dh;
+
+		dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph);
+		if (dh == NULL)
+			break;
+
+		ad->u.net.sport = dh->dccph_sport;
+		ad->u.net.dport = dh->dccph_dport;
+		break;
+	}
+	case IPPROTO_SCTP: {
+		struct sctphdr _sctph, *sh;
+
+		sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph);
+		if (sh == NULL)
+			break;
+		ad->u.net.sport = sh->source;
+		ad->u.net.dport = sh->dest;
+		break;
+	}
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+#endif
+
+
+static inline void print_ipv6_addr(struct audit_buffer *ab,
+				   struct in6_addr *addr, __be16 port,
+				   char *name1, char *name2)
+{
+	if (!ipv6_addr_any(addr))
+		audit_log_format(ab, " %s=%pI6", name1, addr);
+	if (port)
+		audit_log_format(ab, " %s=%d", name2, ntohs(port));
+}
+
+static inline void print_ipv4_addr(struct audit_buffer *ab, __be32 addr,
+				   __be16 port, char *name1, char *name2)
+{
+	if (addr)
+		audit_log_format(ab, " %s=%pI4", name1, &addr);
+	if (port)
+		audit_log_format(ab, " %s=%d", name2, ntohs(port));
+}
+
+/**
+ * dump_common_audit_data - helper to dump common audit data
+ * @a : common audit data
+ *
+ */
+static void dump_common_audit_data(struct audit_buffer *ab,
+				   struct common_audit_data *a)
+{
+	struct inode *inode = NULL;
+	struct task_struct *tsk = current;
+
+	if (a->tsk)
+		tsk = a->tsk;
+	if (tsk && tsk->pid) {
+		audit_log_format(ab, " pid=%d comm=", tsk->pid);
+		audit_log_untrustedstring(ab, tsk->comm);
+	}
+
+	switch (a->type) {
+	case LSM_AUDIT_DATA_IPC:
+		audit_log_format(ab, " key=%d ", a->u.ipc_id);
+		break;
+	case LSM_AUDIT_DATA_CAP:
+		audit_log_format(ab, " capability=%d ", a->u.cap);
+		break;
+	case LSM_AUDIT_DATA_FS:
+		if (a->u.fs.path.dentry) {
+			struct dentry *dentry = a->u.fs.path.dentry;
+			if (a->u.fs.path.mnt) {
+				audit_log_d_path(ab, "path=", &a->u.fs.path);
+			} else {
+				audit_log_format(ab, " name=");
+				audit_log_untrustedstring(ab,
+						 dentry->d_name.name);
+			}
+			inode = dentry->d_inode;
+		} else if (a->u.fs.inode) {
+			struct dentry *dentry;
+			inode = a->u.fs.inode;
+			dentry = d_find_alias(inode);
+			if (dentry) {
+				audit_log_format(ab, " name=");
+				audit_log_untrustedstring(ab,
+						 dentry->d_name.name);
+				dput(dentry);
+			}
+		}
+		if (inode)
+			audit_log_format(ab, " dev=%s ino=%lu",
+					inode->i_sb->s_id,
+					inode->i_ino);
+		break;
+	case LSM_AUDIT_DATA_TASK:
+		tsk = a->u.tsk;
+		if (tsk && tsk->pid) {
+			audit_log_format(ab, " pid=%d comm=", tsk->pid);
+			audit_log_untrustedstring(ab, tsk->comm);
+		}
+		break;
+	case LSM_AUDIT_DATA_NET:
+		if (a->u.net.sk) {
+			struct sock *sk = a->u.net.sk;
+			struct unix_sock *u;
+			int len = 0;
+			char *p = NULL;
+
+			switch (sk->sk_family) {
+			case AF_INET: {
+				struct inet_sock *inet = inet_sk(sk);
+
+				print_ipv4_addr(ab, inet->rcv_saddr,
+						inet->sport,
+						"laddr", "lport");
+				print_ipv4_addr(ab, inet->daddr,
+						inet->dport,
+						"faddr", "fport");
+				break;
+			}
+			case AF_INET6: {
+				struct inet_sock *inet = inet_sk(sk);
+				struct ipv6_pinfo *inet6 = inet6_sk(sk);
+
+				print_ipv6_addr(ab, &inet6->rcv_saddr,
+						inet->sport,
+						"laddr", "lport");
+				print_ipv6_addr(ab, &inet6->daddr,
+						inet->dport,
+						"faddr", "fport");
+				break;
+			}
+			case AF_UNIX:
+				u = unix_sk(sk);
+				if (u->dentry) {
+					struct path path = {
+						.dentry = u->dentry,
+						.mnt = u->mnt
+					};
+					audit_log_d_path(ab, "path=", &path);
+					break;
+				}
+				if (!u->addr)
+					break;
+				len = u->addr->len-sizeof(short);
+				p = &u->addr->name->sun_path[0];
+				audit_log_format(ab, " path=");
+				if (*p)
+					audit_log_untrustedstring(ab, p);
+				else
+					audit_log_n_hex(ab, p, len);
+				break;
+			}
+		}
+
+		switch (a->u.net.family) {
+		case AF_INET:
+			print_ipv4_addr(ab, a->u.net.v4info.saddr,
+					a->u.net.sport,
+					"saddr", "src");
+			print_ipv4_addr(ab, a->u.net.v4info.daddr,
+					a->u.net.dport,
+					"daddr", "dest");
+			break;
+		case AF_INET6:
+			print_ipv6_addr(ab, &a->u.net.v6info.saddr,
+					a->u.net.sport,
+					"saddr", "src");
+			print_ipv6_addr(ab, &a->u.net.v6info.daddr,
+					a->u.net.dport,
+					"daddr", "dest");
+			break;
+		}
+		if (a->u.net.netif > 0) {
+			struct net_device *dev;
+
+			/* NOTE: we always use init's namespace */
+			dev = dev_get_by_index(&init_net, a->u.net.netif);
+			if (dev) {
+				audit_log_format(ab, " netif=%s", dev->name);
+				dev_put(dev);
+			}
+		}
+		break;
+#ifdef CONFIG_KEYS
+	case LSM_AUDIT_DATA_KEY:
+		audit_log_format(ab, " key_serial=%u", a->u.key_struct.key);
+		if (a->u.key_struct.key_desc) {
+			audit_log_format(ab, " key_desc=");
+			audit_log_untrustedstring(ab, a->u.key_struct.key_desc);
+		}
+		break;
+#endif
+	} /* switch (a->type) */
+}
+
+/**
+ * common_lsm_audit - generic LSM auditing function
+ * @a:  auxiliary audit data
+ *
+ * setup the audit buffer for common security information
+ * uses callback to print LSM specific information
+ */
+void common_lsm_audit(struct common_audit_data *a)
+{
+	struct audit_buffer *ab;
+
+	if (a == NULL)
+		return;
+	/* we use GFP_ATOMIC so we won't sleep */
+	ab = audit_log_start(current->audit_context, GFP_ATOMIC, AUDIT_AVC);
+
+	if (ab == NULL)
+		return;
+
+	if (a->lsm_pre_audit)
+		a->lsm_pre_audit(ab, a);
+
+	dump_common_audit_data(ab, a);
+
+	if (a->lsm_post_audit)
+		a->lsm_post_audit(ab, a);
+
+	audit_log_end(ab);
+}
diff --git a/security/root_plug.c b/security/root_plug.c
index 40fb4f15e27b..2f7ffa67c4d2 100644
--- a/security/root_plug.c
+++ b/security/root_plug.c
@@ -71,18 +71,6 @@ static int rootplug_bprm_check_security (struct linux_binprm *bprm)
 }
 
 static struct security_operations rootplug_security_ops = {
-	/* Use the capability functions for some of the hooks */
-	.ptrace_may_access =		cap_ptrace_may_access,
-	.ptrace_traceme =		cap_ptrace_traceme,
-	.capget =			cap_capget,
-	.capset =			cap_capset,
-	.capable =			cap_capable,
-
-	.bprm_set_creds =		cap_bprm_set_creds,
-
-	.task_fix_setuid =		cap_task_fix_setuid,
-	.task_prctl =			cap_task_prctl,
-
 	.bprm_check_security =		rootplug_bprm_check_security,
 };
 
diff --git a/security/security.c b/security/security.c
index 5284255c5cdf..dc7674fbfc7a 100644
--- a/security/security.c
+++ b/security/security.c
@@ -26,9 +26,6 @@ extern void security_fixup_ops(struct security_operations *ops);
 
 struct security_operations *security_ops;	/* Initialized to NULL */
 
-/* amount of vm to protect from userspace access */
-unsigned long mmap_min_addr = CONFIG_SECURITY_DEFAULT_MMAP_MIN_ADDR;
-
 static inline int verify(struct security_operations *ops)
 {
 	/* verify the security_operations structure exists */
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 7f9b5fac8779..b2ab60859832 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -927,7 +927,7 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 	if (denied) {
 		if (flags & AVC_STRICT)
 			rc = -EACCES;
-		else if (!selinux_enforcing || security_permissive_sid(ssid))
+		else if (!selinux_enforcing || (avd->flags & AVD_FLAGS_PERMISSIVE))
 			avc_update_node(AVC_CALLBACK_GRANT, requested, ssid,
 					tsid, tclass, avd->seqno);
 		else
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 2fcad7c33eaf..195906bce266 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1980,10 +1980,6 @@ static int selinux_sysctl(ctl_table *table, int op)
 	u32 tsid, sid;
 	int rc;
 
-	rc = secondary_ops->sysctl(table, op);
-	if (rc)
-		return rc;
-
 	sid = current_sid();
 
 	rc = selinux_sysctl_get_sid(table, (op == 0001) ?
@@ -2375,10 +2371,8 @@ static void selinux_bprm_committed_creds(struct linux_binprm *bprm)
 {
 	const struct task_security_struct *tsec = current_security();
 	struct itimerval itimer;
-	struct sighand_struct *psig;
 	u32 osid, sid;
 	int rc, i;
-	unsigned long flags;
 
 	osid = tsec->osid;
 	sid = tsec->sid;
@@ -2398,22 +2392,20 @@ static void selinux_bprm_committed_creds(struct linux_binprm *bprm)
 		memset(&itimer, 0, sizeof itimer);
 		for (i = 0; i < 3; i++)
 			do_setitimer(i, &itimer, NULL);
-		flush_signals(current);
 		spin_lock_irq(&current->sighand->siglock);
-		flush_signal_handlers(current, 1);
-		sigemptyset(&current->blocked);
-		recalc_sigpending();
+		if (!(current->signal->flags & SIGNAL_GROUP_EXIT)) {
+			__flush_signals(current);
+			flush_signal_handlers(current, 1);
+			sigemptyset(&current->blocked);
+		}
 		spin_unlock_irq(&current->sighand->siglock);
 	}
 
 	/* Wake up the parent if it is waiting so that it can recheck
 	 * wait permission to the new task SID. */
-	read_lock_irq(&tasklist_lock);
-	psig = current->parent->sighand;
-	spin_lock_irqsave(&psig->siglock, flags);
-	wake_up_interruptible(&current->parent->signal->wait_chldexit);
-	spin_unlock_irqrestore(&psig->siglock, flags);
-	read_unlock_irq(&tasklist_lock);
+	read_lock(&tasklist_lock);
+	wake_up_interruptible(&current->real_parent->signal->wait_chldexit);
+	read_unlock(&tasklist_lock);
 }
 
 /* superblock security operations */
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 5c3434f7626f..ca835795a8b3 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -8,14 +8,13 @@
 #ifndef _SELINUX_SECURITY_H_
 #define _SELINUX_SECURITY_H_
 
+#include <linux/magic.h>
 #include "flask.h"
 
 #define SECSID_NULL			0x00000000 /* unspecified SID */
 #define SECSID_WILD			0xffffffff /* wildcard SID */
 #define SECCLASS_NULL			0x0000 /* no class */
 
-#define SELINUX_MAGIC 0xf97cff8c
-
 /* Identify specific policy version changes */
 #define POLICYDB_VERSION_BASE		15
 #define POLICYDB_VERSION_BOOL		16
@@ -91,9 +90,11 @@ struct av_decision {
 	u32 auditallow;
 	u32 auditdeny;
 	u32 seqno;
+	u32 flags;
 };
 
-int security_permissive_sid(u32 sid);
+/* definitions of av_decision.flags */
+#define AVD_FLAGS_PERMISSIVE	0x0001
 
 int security_compute_av(u32 ssid, u32 tsid,
 	u16 tclass, u32 requested,
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index c6875fd3b9d6..dd7cc6de77f9 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -112,6 +112,8 @@ static struct nlmsg_perm nlmsg_audit_perms[] =
 	{ AUDIT_DEL_RULE,	NETLINK_AUDIT_SOCKET__NLMSG_WRITE    },
 	{ AUDIT_USER,		NETLINK_AUDIT_SOCKET__NLMSG_RELAY    },
 	{ AUDIT_SIGNAL_INFO,	NETLINK_AUDIT_SOCKET__NLMSG_READ     },
+	{ AUDIT_TRIM,		NETLINK_AUDIT_SOCKET__NLMSG_WRITE    },
+	{ AUDIT_MAKE_EQUIV,	NETLINK_AUDIT_SOCKET__NLMSG_WRITE    },
 	{ AUDIT_TTY_GET,	NETLINK_AUDIT_SOCKET__NLMSG_READ     },
 	{ AUDIT_TTY_SET,	NETLINK_AUDIT_SOCKET__NLMSG_TTY_AUDIT	},
 };
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 2d5136ec3d54..b4fc506e7a87 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -527,10 +527,10 @@ static ssize_t sel_write_access(struct file *file, char *buf, size_t size)
 		goto out2;
 
 	length = scnprintf(buf, SIMPLE_TRANSACTION_LIMIT,
-			  "%x %x %x %x %u",
+			  "%x %x %x %x %u %x",
 			  avd.allowed, 0xffffffff,
 			  avd.auditallow, avd.auditdeny,
-			  avd.seqno);
+			  avd.seqno, avd.flags);
 out2:
 	kfree(tcon);
 out:
@@ -803,10 +803,6 @@ static ssize_t sel_read_bool(struct file *filep, char __user *buf,
 		goto out;
 	}
 
-	if (count > PAGE_SIZE) {
-		ret = -EINVAL;
-		goto out;
-	}
 	page = (char *)get_zeroed_page(GFP_KERNEL);
 	if (!page) {
 		ret = -ENOMEM;
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index deeec6c013ae..500e6f78e115 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -410,6 +410,7 @@ static int context_struct_compute_av(struct context *scontext,
 	avd->auditallow = 0;
 	avd->auditdeny = 0xffffffff;
 	avd->seqno = latest_granting;
+	avd->flags = 0;
 
 	/*
 	 * Check for all the invalid cases.
@@ -528,31 +529,6 @@ inval_class:
 	return 0;
 }
 
-/*
- * Given a sid find if the type has the permissive flag set
- */
-int security_permissive_sid(u32 sid)
-{
-	struct context *context;
-	u32 type;
-	int rc;
-
-	read_lock(&policy_rwlock);
-
-	context = sidtab_search(&sidtab, sid);
-	BUG_ON(!context);
-
-	type = context->type;
-	/*
-	 * we are intentionally using type here, not type-1, the 0th bit may
-	 * someday indicate that we are globally setting permissive in policy.
-	 */
-	rc = ebitmap_get_bit(&policydb.permissive_map, type);
-
-	read_unlock(&policy_rwlock);
-	return rc;
-}
-
 static int security_validtrans_handle_fail(struct context *ocontext,
 					   struct context *ncontext,
 					   struct context *tcontext,
@@ -767,6 +743,10 @@ int security_compute_av(u32 ssid,
 
 	rc = context_struct_compute_av(scontext, tcontext, tclass,
 				       requested, avd);
+
+	/* permissive domain? */
+	if (ebitmap_get_bit(&policydb.permissive_map, scontext->type))
+	    avd->flags |= AVD_FLAGS_PERMISSIVE;
 out:
 	read_unlock(&policy_rwlock);
 	return rc;
diff --git a/security/smack/smack.h b/security/smack/smack.h
index 42ef313f9856..243bec175be0 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -20,6 +20,7 @@
 #include <net/netlabel.h>
 #include <linux/list.h>
 #include <linux/rculist.h>
+#include <linux/lsm_audit.h>
 
 /*
  * Why 23? CIPSO is constrained to 30, so a 32 byte buffer is
@@ -178,6 +179,20 @@ struct smack_known {
 #define MAY_READWRITE	(MAY_READ | MAY_WRITE)
 #define MAY_NOT		0
 
+/*
+ * Number of access types used by Smack (rwxa)
+ */
+#define SMK_NUM_ACCESS_TYPE 4
+
+/*
+ * Smack audit data; is empty if CONFIG_AUDIT not set
+ * to save some stack
+ */
+struct smk_audit_info {
+#ifdef CONFIG_AUDIT
+	struct common_audit_data a;
+#endif
+};
 /*
  * These functions are in smack_lsm.c
  */
@@ -186,8 +201,8 @@ struct inode_smack *new_inode_smack(char *);
 /*
  * These functions are in smack_access.c
  */
-int smk_access(char *, char *, int);
-int smk_curacc(char *, u32);
+int smk_access(char *, char *, int, struct smk_audit_info *);
+int smk_curacc(char *, u32, struct smk_audit_info *);
 int smack_to_cipso(const char *, struct smack_cipso *);
 void smack_from_cipso(u32, char *, char *);
 char *smack_from_secid(const u32);
@@ -237,4 +252,93 @@ static inline char *smk_of_inode(const struct inode *isp)
 	return sip->smk_inode;
 }
 
+/*
+ * logging functions
+ */
+#define SMACK_AUDIT_DENIED 0x1
+#define SMACK_AUDIT_ACCEPT 0x2
+extern int log_policy;
+
+void smack_log(char *subject_label, char *object_label,
+		int request,
+		int result, struct smk_audit_info *auditdata);
+
+#ifdef CONFIG_AUDIT
+
+/*
+ * some inline functions to set up audit data
+ * they do nothing if CONFIG_AUDIT is not set
+ *
+ */
+static inline void smk_ad_init(struct smk_audit_info *a, const char *func,
+			       char type)
+{
+	memset(a, 0, sizeof(*a));
+	a->a.type = type;
+	a->a.function = func;
+}
+
+static inline void smk_ad_setfield_u_tsk(struct smk_audit_info *a,
+					 struct task_struct *t)
+{
+	a->a.u.tsk = t;
+}
+static inline void smk_ad_setfield_u_fs_path_dentry(struct smk_audit_info *a,
+						    struct dentry *d)
+{
+	a->a.u.fs.path.dentry = d;
+}
+static inline void smk_ad_setfield_u_fs_path_mnt(struct smk_audit_info *a,
+						 struct vfsmount *m)
+{
+	a->a.u.fs.path.mnt = m;
+}
+static inline void smk_ad_setfield_u_fs_inode(struct smk_audit_info *a,
+					      struct inode *i)
+{
+	a->a.u.fs.inode = i;
+}
+static inline void smk_ad_setfield_u_fs_path(struct smk_audit_info *a,
+					     struct path p)
+{
+	a->a.u.fs.path = p;
+}
+static inline void smk_ad_setfield_u_net_sk(struct smk_audit_info *a,
+					    struct sock *sk)
+{
+	a->a.u.net.sk = sk;
+}
+
+#else /* no AUDIT */
+
+static inline void smk_ad_init(struct smk_audit_info *a, const char *func,
+			       char type)
+{
+}
+static inline void smk_ad_setfield_u_tsk(struct smk_audit_info *a,
+					 struct task_struct *t)
+{
+}
+static inline void smk_ad_setfield_u_fs_path_dentry(struct smk_audit_info *a,
+						    struct dentry *d)
+{
+}
+static inline void smk_ad_setfield_u_fs_path_mnt(struct smk_audit_info *a,
+						 struct vfsmount *m)
+{
+}
+static inline void smk_ad_setfield_u_fs_inode(struct smk_audit_info *a,
+					      struct inode *i)
+{
+}
+static inline void smk_ad_setfield_u_fs_path(struct smk_audit_info *a,
+					     struct path p)
+{
+}
+static inline void smk_ad_setfield_u_net_sk(struct smk_audit_info *a,
+					    struct sock *sk)
+{
+}
+#endif
+
 #endif  /* _SECURITY_SMACK_H */
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c
index ac0a2707f6d4..513dc1aa16dd 100644
--- a/security/smack/smack_access.c
+++ b/security/smack/smack_access.c
@@ -59,11 +59,18 @@ LIST_HEAD(smack_known_list);
  */
 static u32 smack_next_secid = 10;
 
+/*
+ * what events do we log
+ * can be overwritten at run-time by /smack/logging
+ */
+int log_policy = SMACK_AUDIT_DENIED;
+
 /**
  * smk_access - determine if a subject has a specific access to an object
  * @subject_label: a pointer to the subject's Smack label
  * @object_label: a pointer to the object's Smack label
  * @request: the access requested, in "MAY" format
+ * @a : a pointer to the audit data
  *
  * This function looks up the subject/object pair in the
  * access rule list and returns 0 if the access is permitted,
@@ -78,10 +85,12 @@ static u32 smack_next_secid = 10;
  * will be on the list, so checking the pointers may be a worthwhile
  * optimization.
  */
-int smk_access(char *subject_label, char *object_label, int request)
+int smk_access(char *subject_label, char *object_label, int request,
+	       struct smk_audit_info *a)
 {
 	u32 may = MAY_NOT;
 	struct smack_rule *srp;
+	int rc = 0;
 
 	/*
 	 * Hardcoded comparisons.
@@ -89,8 +98,10 @@ int smk_access(char *subject_label, char *object_label, int request)
 	 * A star subject can't access any object.
 	 */
 	if (subject_label == smack_known_star.smk_known ||
-	    strcmp(subject_label, smack_known_star.smk_known) == 0)
-		return -EACCES;
+	    strcmp(subject_label, smack_known_star.smk_known) == 0) {
+		rc = -EACCES;
+		goto out_audit;
+	}
 	/*
 	 * An internet object can be accessed by any subject.
 	 * Tasks cannot be assigned the internet label.
@@ -100,20 +111,20 @@ int smk_access(char *subject_label, char *object_label, int request)
 	    subject_label == smack_known_web.smk_known ||
 	    strcmp(object_label, smack_known_web.smk_known) == 0 ||
 	    strcmp(subject_label, smack_known_web.smk_known) == 0)
-		return 0;
+		goto out_audit;
 	/*
 	 * A star object can be accessed by any subject.
 	 */
 	if (object_label == smack_known_star.smk_known ||
 	    strcmp(object_label, smack_known_star.smk_known) == 0)
-		return 0;
+		goto out_audit;
 	/*
 	 * An object can be accessed in any way by a subject
 	 * with the same label.
 	 */
 	if (subject_label == object_label ||
 	    strcmp(subject_label, object_label) == 0)
-		return 0;
+		goto out_audit;
 	/*
 	 * A hat subject can read any object.
 	 * A floor object can be read by any subject.
@@ -121,10 +132,10 @@ int smk_access(char *subject_label, char *object_label, int request)
 	if ((request & MAY_ANYREAD) == request) {
 		if (object_label == smack_known_floor.smk_known ||
 		    strcmp(object_label, smack_known_floor.smk_known) == 0)
-			return 0;
+			goto out_audit;
 		if (subject_label == smack_known_hat.smk_known ||
 		    strcmp(subject_label, smack_known_hat.smk_known) == 0)
-			return 0;
+			goto out_audit;
 	}
 	/*
 	 * Beyond here an explicit relationship is required.
@@ -148,28 +159,36 @@ int smk_access(char *subject_label, char *object_label, int request)
 	 * This is a bit map operation.
 	 */
 	if ((request & may) == request)
-		return 0;
+		goto out_audit;
 
-	return -EACCES;
+	rc = -EACCES;
+out_audit:
+#ifdef CONFIG_AUDIT
+	if (a)
+		smack_log(subject_label, object_label, request, rc, a);
+#endif
+	return rc;
 }
 
 /**
  * smk_curacc - determine if current has a specific access to an object
  * @obj_label: a pointer to the object's Smack label
  * @mode: the access requested, in "MAY" format
+ * @a : common audit data
  *
  * This function checks the current subject label/object label pair
  * in the access rule list and returns 0 if the access is permitted,
  * non zero otherwise. It allows that current may have the capability
  * to override the rules.
  */
-int smk_curacc(char *obj_label, u32 mode)
+int smk_curacc(char *obj_label, u32 mode, struct smk_audit_info *a)
 {
 	int rc;
+	char *sp = current_security();
 
-	rc = smk_access(current_security(), obj_label, mode);
+	rc = smk_access(sp, obj_label, mode, NULL);
 	if (rc == 0)
-		return 0;
+		goto out_audit;
 
 	/*
 	 * Return if a specific label has been designated as the
@@ -177,14 +196,105 @@ int smk_curacc(char *obj_label, u32 mode)
 	 * have that label.
 	 */
 	if (smack_onlycap != NULL && smack_onlycap != current->cred->security)
-		return rc;
+		goto out_audit;
 
 	if (capable(CAP_MAC_OVERRIDE))
 		return 0;
 
+out_audit:
+#ifdef CONFIG_AUDIT
+	if (a)
+		smack_log(sp, obj_label, mode, rc, a);
+#endif
 	return rc;
 }
 
+#ifdef CONFIG_AUDIT
+/**
+ * smack_str_from_perm : helper to transalate an int to a
+ * readable string
+ * @string : the string to fill
+ * @access : the int
+ *
+ */
+static inline void smack_str_from_perm(char *string, int access)
+{
+	int i = 0;
+	if (access & MAY_READ)
+		string[i++] = 'r';
+	if (access & MAY_WRITE)
+		string[i++] = 'w';
+	if (access & MAY_EXEC)
+		string[i++] = 'x';
+	if (access & MAY_APPEND)
+		string[i++] = 'a';
+	string[i] = '\0';
+}
+/**
+ * smack_log_callback - SMACK specific information
+ * will be called by generic audit code
+ * @ab : the audit_buffer
+ * @a  : audit_data
+ *
+ */
+static void smack_log_callback(struct audit_buffer *ab, void *a)
+{
+	struct common_audit_data *ad = a;
+	struct smack_audit_data *sad = &ad->lsm_priv.smack_audit_data;
+	audit_log_format(ab, "lsm=SMACK fn=%s action=%s", ad->function,
+			 sad->result ? "denied" : "granted");
+	audit_log_format(ab, " subject=");
+	audit_log_untrustedstring(ab, sad->subject);
+	audit_log_format(ab, " object=");
+	audit_log_untrustedstring(ab, sad->object);
+	audit_log_format(ab, " requested=%s", sad->request);
+}
+
+/**
+ *  smack_log - Audit the granting or denial of permissions.
+ *  @subject_label : smack label of the requester
+ *  @object_label  : smack label of the object being accessed
+ *  @request: requested permissions
+ *  @result: result from smk_access
+ *  @a:  auxiliary audit data
+ *
+ * Audit the granting or denial of permissions in accordance
+ * with the policy.
+ */
+void smack_log(char *subject_label, char *object_label, int request,
+	       int result, struct smk_audit_info *ad)
+{
+	char request_buffer[SMK_NUM_ACCESS_TYPE + 1];
+	struct smack_audit_data *sad;
+	struct common_audit_data *a = &ad->a;
+
+	/* check if we have to log the current event */
+	if (result != 0 && (log_policy & SMACK_AUDIT_DENIED) == 0)
+		return;
+	if (result == 0 && (log_policy & SMACK_AUDIT_ACCEPT) == 0)
+		return;
+
+	if (a->function == NULL)
+		a->function = "unknown";
+
+	/* end preparing the audit data */
+	sad = &a->lsm_priv.smack_audit_data;
+	smack_str_from_perm(request_buffer, request);
+	sad->subject = subject_label;
+	sad->object  = object_label;
+	sad->request = request_buffer;
+	sad->result  = result;
+	a->lsm_pre_audit = smack_log_callback;
+
+	common_lsm_audit(a);
+}
+#else /* #ifdef CONFIG_AUDIT */
+void smack_log(char *subject_label, char *object_label, int request,
+               int result, struct smk_audit_info *ad)
+{
+}
+#endif
+
 static DEFINE_MUTEX(smack_known_lock);
 
 /**
@@ -209,7 +319,8 @@ struct smack_known *smk_import_entry(const char *string, int len)
 		if (found)
 			smack[i] = '\0';
 		else if (i >= len || string[i] > '~' || string[i] <= ' ' ||
-			 string[i] == '/') {
+			 string[i] == '/' || string[i] == '"' ||
+			 string[i] == '\\' || string[i] == '\'') {
 			smack[i] = '\0';
 			found = 1;
 		} else
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 98b3195347ab..0023182078c7 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -30,7 +30,6 @@
 #include <net/netlabel.h>
 #include <net/cipso_ipv4.h>
 #include <linux/audit.h>
-
 #include "smack.h"
 
 #define task_security(task)	(task_cred_xxx((task), security))
@@ -103,14 +102,24 @@ struct inode_smack *new_inode_smack(char *smack)
 static int smack_ptrace_may_access(struct task_struct *ctp, unsigned int mode)
 {
 	int rc;
+	struct smk_audit_info ad;
+	char *sp, *tsp;
 
 	rc = cap_ptrace_may_access(ctp, mode);
 	if (rc != 0)
 		return rc;
 
-	rc = smk_access(current_security(), task_security(ctp), MAY_READWRITE);
+	sp = current_security();
+	tsp = task_security(ctp);
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_tsk(&ad, ctp);
+
+	/* we won't log here, because rc can be overriden */
+	rc = smk_access(sp, tsp, MAY_READWRITE, NULL);
 	if (rc != 0 && capable(CAP_MAC_OVERRIDE))
-		return 0;
+		rc = 0;
+
+	smack_log(sp, tsp, MAY_READWRITE, rc, &ad);
 	return rc;
 }
 
@@ -125,14 +134,24 @@ static int smack_ptrace_may_access(struct task_struct *ctp, unsigned int mode)
 static int smack_ptrace_traceme(struct task_struct *ptp)
 {
 	int rc;
+	struct smk_audit_info ad;
+	char *sp, *tsp;
 
 	rc = cap_ptrace_traceme(ptp);
 	if (rc != 0)
 		return rc;
 
-	rc = smk_access(task_security(ptp), current_security(), MAY_READWRITE);
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_tsk(&ad, ptp);
+
+	sp = current_security();
+	tsp = task_security(ptp);
+	/* we won't log here, because rc can be overriden */
+	rc = smk_access(tsp, sp, MAY_READWRITE, NULL);
 	if (rc != 0 && has_capability(ptp, CAP_MAC_OVERRIDE))
-		return 0;
+		rc = 0;
+
+	smack_log(tsp, sp, MAY_READWRITE, rc, &ad);
 	return rc;
 }
 
@@ -327,8 +346,14 @@ static int smack_sb_kern_mount(struct super_block *sb, int flags, void *data)
 static int smack_sb_statfs(struct dentry *dentry)
 {
 	struct superblock_smack *sbp = dentry->d_sb->s_security;
+	int rc;
+	struct smk_audit_info ad;
 
-	return smk_curacc(sbp->smk_floor, MAY_READ);
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	rc = smk_curacc(sbp->smk_floor, MAY_READ, &ad);
+	return rc;
 }
 
 /**
@@ -346,8 +371,12 @@ static int smack_sb_mount(char *dev_name, struct path *path,
 			  char *type, unsigned long flags, void *data)
 {
 	struct superblock_smack *sbp = path->mnt->mnt_sb->s_security;
+	struct smk_audit_info ad;
 
-	return smk_curacc(sbp->smk_floor, MAY_WRITE);
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path(&ad, *path);
+
+	return smk_curacc(sbp->smk_floor, MAY_WRITE, &ad);
 }
 
 /**
@@ -361,10 +390,14 @@ static int smack_sb_mount(char *dev_name, struct path *path,
 static int smack_sb_umount(struct vfsmount *mnt, int flags)
 {
 	struct superblock_smack *sbp;
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, mnt->mnt_mountpoint);
+	smk_ad_setfield_u_fs_path_mnt(&ad, mnt);
 
 	sbp = mnt->mnt_sb->s_security;
-
-	return smk_curacc(sbp->smk_floor, MAY_WRITE);
+	return smk_curacc(sbp->smk_floor, MAY_WRITE, &ad);
 }
 
 /*
@@ -441,15 +474,20 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir,
 static int smack_inode_link(struct dentry *old_dentry, struct inode *dir,
 			    struct dentry *new_dentry)
 {
-	int rc;
 	char *isp;
+	struct smk_audit_info ad;
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, old_dentry);
 
 	isp = smk_of_inode(old_dentry->d_inode);
-	rc = smk_curacc(isp, MAY_WRITE);
+	rc = smk_curacc(isp, MAY_WRITE, &ad);
 
 	if (rc == 0 && new_dentry->d_inode != NULL) {
 		isp = smk_of_inode(new_dentry->d_inode);
-		rc = smk_curacc(isp, MAY_WRITE);
+		smk_ad_setfield_u_fs_path_dentry(&ad, new_dentry);
+		rc = smk_curacc(isp, MAY_WRITE, &ad);
 	}
 
 	return rc;
@@ -466,18 +504,24 @@ static int smack_inode_link(struct dentry *old_dentry, struct inode *dir,
 static int smack_inode_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *ip = dentry->d_inode;
+	struct smk_audit_info ad;
 	int rc;
 
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
 	/*
 	 * You need write access to the thing you're unlinking
 	 */
-	rc = smk_curacc(smk_of_inode(ip), MAY_WRITE);
-	if (rc == 0)
+	rc = smk_curacc(smk_of_inode(ip), MAY_WRITE, &ad);
+	if (rc == 0) {
 		/*
 		 * You also need write access to the containing directory
 		 */
-		rc = smk_curacc(smk_of_inode(dir), MAY_WRITE);
-
+		smk_ad_setfield_u_fs_path_dentry(&ad, NULL);
+		smk_ad_setfield_u_fs_inode(&ad, dir);
+		rc = smk_curacc(smk_of_inode(dir), MAY_WRITE, &ad);
+	}
 	return rc;
 }
 
@@ -491,17 +535,24 @@ static int smack_inode_unlink(struct inode *dir, struct dentry *dentry)
  */
 static int smack_inode_rmdir(struct inode *dir, struct dentry *dentry)
 {
+	struct smk_audit_info ad;
 	int rc;
 
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
 	/*
 	 * You need write access to the thing you're removing
 	 */
-	rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE);
-	if (rc == 0)
+	rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
+	if (rc == 0) {
 		/*
 		 * You also need write access to the containing directory
 		 */
-		rc = smk_curacc(smk_of_inode(dir), MAY_WRITE);
+		smk_ad_setfield_u_fs_path_dentry(&ad, NULL);
+		smk_ad_setfield_u_fs_inode(&ad, dir);
+		rc = smk_curacc(smk_of_inode(dir), MAY_WRITE, &ad);
+	}
 
 	return rc;
 }
@@ -525,15 +576,19 @@ static int smack_inode_rename(struct inode *old_inode,
 {
 	int rc;
 	char *isp;
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, old_dentry);
 
 	isp = smk_of_inode(old_dentry->d_inode);
-	rc = smk_curacc(isp, MAY_READWRITE);
+	rc = smk_curacc(isp, MAY_READWRITE, &ad);
 
 	if (rc == 0 && new_dentry->d_inode != NULL) {
 		isp = smk_of_inode(new_dentry->d_inode);
-		rc = smk_curacc(isp, MAY_READWRITE);
+		smk_ad_setfield_u_fs_path_dentry(&ad, new_dentry);
+		rc = smk_curacc(isp, MAY_READWRITE, &ad);
 	}
-
 	return rc;
 }
 
@@ -548,13 +603,15 @@ static int smack_inode_rename(struct inode *old_inode,
  */
 static int smack_inode_permission(struct inode *inode, int mask)
 {
+	struct smk_audit_info ad;
 	/*
 	 * No permission to check. Existence test. Yup, it's there.
 	 */
 	if (mask == 0)
 		return 0;
-
-	return smk_curacc(smk_of_inode(inode), mask);
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_inode(&ad, inode);
+	return smk_curacc(smk_of_inode(inode), mask, &ad);
 }
 
 /**
@@ -566,13 +623,16 @@ static int smack_inode_permission(struct inode *inode, int mask)
  */
 static int smack_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 {
+	struct smk_audit_info ad;
 	/*
 	 * Need to allow for clearing the setuid bit.
 	 */
 	if (iattr->ia_valid & ATTR_FORCE)
 		return 0;
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
 
-	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE);
+	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
 }
 
 /**
@@ -584,7 +644,12 @@ static int smack_inode_setattr(struct dentry *dentry, struct iattr *iattr)
  */
 static int smack_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
 {
-	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ);
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+	smk_ad_setfield_u_fs_path_mnt(&ad, mnt);
+	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad);
 }
 
 /**
@@ -602,6 +667,7 @@ static int smack_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
 static int smack_inode_setxattr(struct dentry *dentry, const char *name,
 				const void *value, size_t size, int flags)
 {
+	struct smk_audit_info ad;
 	int rc = 0;
 
 	if (strcmp(name, XATTR_NAME_SMACK) == 0 ||
@@ -619,8 +685,11 @@ static int smack_inode_setxattr(struct dentry *dentry, const char *name,
 	} else
 		rc = cap_inode_setxattr(dentry, name, value, size, flags);
 
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
 	if (rc == 0)
-		rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE);
+		rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
 
 	return rc;
 }
@@ -672,7 +741,12 @@ static void smack_inode_post_setxattr(struct dentry *dentry, const char *name,
  */
 static int smack_inode_getxattr(struct dentry *dentry, const char *name)
 {
-	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ);
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad);
 }
 
 /*
@@ -686,6 +760,7 @@ static int smack_inode_getxattr(struct dentry *dentry, const char *name)
  */
 static int smack_inode_removexattr(struct dentry *dentry, const char *name)
 {
+	struct smk_audit_info ad;
 	int rc = 0;
 
 	if (strcmp(name, XATTR_NAME_SMACK) == 0 ||
@@ -696,8 +771,10 @@ static int smack_inode_removexattr(struct dentry *dentry, const char *name)
 	} else
 		rc = cap_inode_removexattr(dentry, name);
 
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
 	if (rc == 0)
-		rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE);
+		rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
 
 	return rc;
 }
@@ -856,12 +933,16 @@ static int smack_file_ioctl(struct file *file, unsigned int cmd,
 			    unsigned long arg)
 {
 	int rc = 0;
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
 
 	if (_IOC_DIR(cmd) & _IOC_WRITE)
-		rc = smk_curacc(file->f_security, MAY_WRITE);
+		rc = smk_curacc(file->f_security, MAY_WRITE, &ad);
 
 	if (rc == 0 && (_IOC_DIR(cmd) & _IOC_READ))
-		rc = smk_curacc(file->f_security, MAY_READ);
+		rc = smk_curacc(file->f_security, MAY_READ, &ad);
 
 	return rc;
 }
@@ -875,7 +956,11 @@ static int smack_file_ioctl(struct file *file, unsigned int cmd,
  */
 static int smack_file_lock(struct file *file, unsigned int cmd)
 {
-	return smk_curacc(file->f_security, MAY_WRITE);
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path_dentry(&ad, file->f_path.dentry);
+	return smk_curacc(file->f_security, MAY_WRITE, &ad);
 }
 
 /**
@@ -889,8 +974,12 @@ static int smack_file_lock(struct file *file, unsigned int cmd)
 static int smack_file_fcntl(struct file *file, unsigned int cmd,
 			    unsigned long arg)
 {
+	struct smk_audit_info ad;
 	int rc;
 
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
+
 	switch (cmd) {
 	case F_DUPFD:
 	case F_GETFD:
@@ -898,7 +987,7 @@ static int smack_file_fcntl(struct file *file, unsigned int cmd,
 	case F_GETLK:
 	case F_GETOWN:
 	case F_GETSIG:
-		rc = smk_curacc(file->f_security, MAY_READ);
+		rc = smk_curacc(file->f_security, MAY_READ, &ad);
 		break;
 	case F_SETFD:
 	case F_SETFL:
@@ -906,10 +995,10 @@ static int smack_file_fcntl(struct file *file, unsigned int cmd,
 	case F_SETLKW:
 	case F_SETOWN:
 	case F_SETSIG:
-		rc = smk_curacc(file->f_security, MAY_WRITE);
+		rc = smk_curacc(file->f_security, MAY_WRITE, &ad);
 		break;
 	default:
-		rc = smk_curacc(file->f_security, MAY_READWRITE);
+		rc = smk_curacc(file->f_security, MAY_READWRITE, &ad);
 	}
 
 	return rc;
@@ -944,14 +1033,21 @@ static int smack_file_send_sigiotask(struct task_struct *tsk,
 {
 	struct file *file;
 	int rc;
+	char *tsp = tsk->cred->security;
+	struct smk_audit_info ad;
 
 	/*
 	 * struct fown_struct is never outside the context of a struct file
 	 */
 	file = container_of(fown, struct file, f_owner);
-	rc = smk_access(file->f_security, tsk->cred->security, MAY_WRITE);
+	/* we don't log here as rc can be overriden */
+	rc = smk_access(file->f_security, tsp, MAY_WRITE, NULL);
 	if (rc != 0 && has_capability(tsk, CAP_MAC_OVERRIDE))
-		return 0;
+		rc = 0;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_tsk(&ad, tsk);
+	smack_log(file->f_security, tsp, MAY_WRITE, rc, &ad);
 	return rc;
 }
 
@@ -964,7 +1060,10 @@ static int smack_file_send_sigiotask(struct task_struct *tsk,
 static int smack_file_receive(struct file *file)
 {
 	int may = 0;
+	struct smk_audit_info ad;
 
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
 	/*
 	 * This code relies on bitmasks.
 	 */
@@ -973,7 +1072,7 @@ static int smack_file_receive(struct file *file)
 	if (file->f_mode & FMODE_WRITE)
 		may |= MAY_WRITE;
 
-	return smk_curacc(file->f_security, may);
+	return smk_curacc(file->f_security, may, &ad);
 }
 
 /*
@@ -1052,6 +1151,22 @@ static int smack_kernel_create_files_as(struct cred *new,
 	return 0;
 }
 
+/**
+ * smk_curacc_on_task - helper to log task related access
+ * @p: the task object
+ * @access : the access requested
+ *
+ * Return 0 if access is permitted
+ */
+static int smk_curacc_on_task(struct task_struct *p, int access)
+{
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_tsk(&ad, p);
+	return smk_curacc(task_security(p), access, &ad);
+}
+
 /**
  * smack_task_setpgid - Smack check on setting pgid
  * @p: the task object
@@ -1061,7 +1176,7 @@ static int smack_kernel_create_files_as(struct cred *new,
  */
 static int smack_task_setpgid(struct task_struct *p, pid_t pgid)
 {
-	return smk_curacc(task_security(p), MAY_WRITE);
+	return smk_curacc_on_task(p, MAY_WRITE);
 }
 
 /**
@@ -1072,7 +1187,7 @@ static int smack_task_setpgid(struct task_struct *p, pid_t pgid)
  */
 static int smack_task_getpgid(struct task_struct *p)
 {
-	return smk_curacc(task_security(p), MAY_READ);
+	return smk_curacc_on_task(p, MAY_READ);
 }
 
 /**
@@ -1083,7 +1198,7 @@ static int smack_task_getpgid(struct task_struct *p)
  */
 static int smack_task_getsid(struct task_struct *p)
 {
-	return smk_curacc(task_security(p), MAY_READ);
+	return smk_curacc_on_task(p, MAY_READ);
 }
 
 /**
@@ -1111,7 +1226,7 @@ static int smack_task_setnice(struct task_struct *p, int nice)
 
 	rc = cap_task_setnice(p, nice);
 	if (rc == 0)
-		rc = smk_curacc(task_security(p), MAY_WRITE);
+		rc = smk_curacc_on_task(p, MAY_WRITE);
 	return rc;
 }
 
@@ -1128,7 +1243,7 @@ static int smack_task_setioprio(struct task_struct *p, int ioprio)
 
 	rc = cap_task_setioprio(p, ioprio);
 	if (rc == 0)
-		rc = smk_curacc(task_security(p), MAY_WRITE);
+		rc = smk_curacc_on_task(p, MAY_WRITE);
 	return rc;
 }
 
@@ -1140,7 +1255,7 @@ static int smack_task_setioprio(struct task_struct *p, int ioprio)
  */
 static int smack_task_getioprio(struct task_struct *p)
 {
-	return smk_curacc(task_security(p), MAY_READ);
+	return smk_curacc_on_task(p, MAY_READ);
 }
 
 /**
@@ -1158,7 +1273,7 @@ static int smack_task_setscheduler(struct task_struct *p, int policy,
 
 	rc = cap_task_setscheduler(p, policy, lp);
 	if (rc == 0)
-		rc = smk_curacc(task_security(p), MAY_WRITE);
+		rc = smk_curacc_on_task(p, MAY_WRITE);
 	return rc;
 }
 
@@ -1170,7 +1285,7 @@ static int smack_task_setscheduler(struct task_struct *p, int policy,
  */
 static int smack_task_getscheduler(struct task_struct *p)
 {
-	return smk_curacc(task_security(p), MAY_READ);
+	return smk_curacc_on_task(p, MAY_READ);
 }
 
 /**
@@ -1181,7 +1296,7 @@ static int smack_task_getscheduler(struct task_struct *p)
  */
 static int smack_task_movememory(struct task_struct *p)
 {
-	return smk_curacc(task_security(p), MAY_WRITE);
+	return smk_curacc_on_task(p, MAY_WRITE);
 }
 
 /**
@@ -1199,18 +1314,23 @@ static int smack_task_movememory(struct task_struct *p)
 static int smack_task_kill(struct task_struct *p, struct siginfo *info,
 			   int sig, u32 secid)
 {
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_tsk(&ad, p);
 	/*
 	 * Sending a signal requires that the sender
 	 * can write the receiver.
 	 */
 	if (secid == 0)
-		return smk_curacc(task_security(p), MAY_WRITE);
+		return smk_curacc(task_security(p), MAY_WRITE, &ad);
 	/*
 	 * If the secid isn't 0 we're dealing with some USB IO
 	 * specific behavior. This is not clean. For one thing
 	 * we can't take privilege into account.
 	 */
-	return smk_access(smack_from_secid(secid), task_security(p), MAY_WRITE);
+	return smk_access(smack_from_secid(secid), task_security(p),
+			  MAY_WRITE, &ad);
 }
 
 /**
@@ -1221,11 +1341,15 @@ static int smack_task_kill(struct task_struct *p, struct siginfo *info,
  */
 static int smack_task_wait(struct task_struct *p)
 {
+	struct smk_audit_info ad;
+	char *sp = current_security();
+	char *tsp = task_security(p);
 	int rc;
 
-	rc = smk_access(current_security(), task_security(p), MAY_WRITE);
+	/* we don't log here, we can be overriden */
+	rc = smk_access(sp, tsp, MAY_WRITE, NULL);
 	if (rc == 0)
-		return 0;
+		goto out_log;
 
 	/*
 	 * Allow the operation to succeed if either task
@@ -1239,8 +1363,12 @@ static int smack_task_wait(struct task_struct *p)
 	 * the smack value.
 	 */
 	if (capable(CAP_MAC_OVERRIDE) || has_capability(p, CAP_MAC_OVERRIDE))
-		return 0;
-
+		rc = 0;
+	/* we log only if we didn't get overriden */
+ out_log:
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_tsk(&ad, p);
+	smack_log(sp, tsp, MAY_WRITE, rc, &ad);
 	return rc;
 }
 
@@ -1456,12 +1584,19 @@ static int smack_netlabel_send(struct sock *sk, struct sockaddr_in *sap)
 	int sk_lbl;
 	char *hostsp;
 	struct socket_smack *ssp = sk->sk_security;
+	struct smk_audit_info ad;
 
 	rcu_read_lock();
 	hostsp = smack_host_label(sap);
 	if (hostsp != NULL) {
 		sk_lbl = SMACK_UNLABELED_SOCKET;
-		rc = smk_access(ssp->smk_out, hostsp, MAY_WRITE);
+#ifdef CONFIG_AUDIT
+		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+		ad.a.u.net.family = sap->sin_family;
+		ad.a.u.net.dport = sap->sin_port;
+		ad.a.u.net.v4info.daddr = sap->sin_addr.s_addr;
+#endif
+		rc = smk_access(ssp->smk_out, hostsp, MAY_WRITE, &ad);
 	} else {
 		sk_lbl = SMACK_CIPSO_SOCKET;
 		rc = 0;
@@ -1656,6 +1791,25 @@ static void smack_shm_free_security(struct shmid_kernel *shp)
 	isp->security = NULL;
 }
 
+/**
+ * smk_curacc_shm : check if current has access on shm
+ * @shp : the object
+ * @access : access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smk_curacc_shm(struct shmid_kernel *shp, int access)
+{
+	char *ssp = smack_of_shm(shp);
+	struct smk_audit_info ad;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+	ad.a.u.ipc_id = shp->shm_perm.id;
+#endif
+	return smk_curacc(ssp, access, &ad);
+}
+
 /**
  * smack_shm_associate - Smack access check for shm
  * @shp: the object
@@ -1665,11 +1819,10 @@ static void smack_shm_free_security(struct shmid_kernel *shp)
  */
 static int smack_shm_associate(struct shmid_kernel *shp, int shmflg)
 {
-	char *ssp = smack_of_shm(shp);
 	int may;
 
 	may = smack_flags_to_may(shmflg);
-	return smk_curacc(ssp, may);
+	return smk_curacc_shm(shp, may);
 }
 
 /**
@@ -1681,7 +1834,6 @@ static int smack_shm_associate(struct shmid_kernel *shp, int shmflg)
  */
 static int smack_shm_shmctl(struct shmid_kernel *shp, int cmd)
 {
-	char *ssp;
 	int may;
 
 	switch (cmd) {
@@ -1704,9 +1856,7 @@ static int smack_shm_shmctl(struct shmid_kernel *shp, int cmd)
 	default:
 		return -EINVAL;
 	}
-
-	ssp = smack_of_shm(shp);
-	return smk_curacc(ssp, may);
+	return smk_curacc_shm(shp, may);
 }
 
 /**
@@ -1720,11 +1870,10 @@ static int smack_shm_shmctl(struct shmid_kernel *shp, int cmd)
 static int smack_shm_shmat(struct shmid_kernel *shp, char __user *shmaddr,
 			   int shmflg)
 {
-	char *ssp = smack_of_shm(shp);
 	int may;
 
 	may = smack_flags_to_may(shmflg);
-	return smk_curacc(ssp, may);
+	return smk_curacc_shm(shp, may);
 }
 
 /**
@@ -1765,6 +1914,25 @@ static void smack_sem_free_security(struct sem_array *sma)
 	isp->security = NULL;
 }
 
+/**
+ * smk_curacc_sem : check if current has access on sem
+ * @sma : the object
+ * @access : access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smk_curacc_sem(struct sem_array *sma, int access)
+{
+	char *ssp = smack_of_sem(sma);
+	struct smk_audit_info ad;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+	ad.a.u.ipc_id = sma->sem_perm.id;
+#endif
+	return smk_curacc(ssp, access, &ad);
+}
+
 /**
  * smack_sem_associate - Smack access check for sem
  * @sma: the object
@@ -1774,11 +1942,10 @@ static void smack_sem_free_security(struct sem_array *sma)
  */
 static int smack_sem_associate(struct sem_array *sma, int semflg)
 {
-	char *ssp = smack_of_sem(sma);
 	int may;
 
 	may = smack_flags_to_may(semflg);
-	return smk_curacc(ssp, may);
+	return smk_curacc_sem(sma, may);
 }
 
 /**
@@ -1790,7 +1957,6 @@ static int smack_sem_associate(struct sem_array *sma, int semflg)
  */
 static int smack_sem_semctl(struct sem_array *sma, int cmd)
 {
-	char *ssp;
 	int may;
 
 	switch (cmd) {
@@ -1819,8 +1985,7 @@ static int smack_sem_semctl(struct sem_array *sma, int cmd)
 		return -EINVAL;
 	}
 
-	ssp = smack_of_sem(sma);
-	return smk_curacc(ssp, may);
+	return smk_curacc_sem(sma, may);
 }
 
 /**
@@ -1837,9 +2002,7 @@ static int smack_sem_semctl(struct sem_array *sma, int cmd)
 static int smack_sem_semop(struct sem_array *sma, struct sembuf *sops,
 			   unsigned nsops, int alter)
 {
-	char *ssp = smack_of_sem(sma);
-
-	return smk_curacc(ssp, MAY_READWRITE);
+	return smk_curacc_sem(sma, MAY_READWRITE);
 }
 
 /**
@@ -1880,6 +2043,25 @@ static char *smack_of_msq(struct msg_queue *msq)
 	return (char *)msq->q_perm.security;
 }
 
+/**
+ * smk_curacc_msq : helper to check if current has access on msq
+ * @msq : the msq
+ * @access : access requested
+ *
+ * return 0 if current has access, error otherwise
+ */
+static int smk_curacc_msq(struct msg_queue *msq, int access)
+{
+	char *msp = smack_of_msq(msq);
+	struct smk_audit_info ad;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+	ad.a.u.ipc_id = msq->q_perm.id;
+#endif
+	return smk_curacc(msp, access, &ad);
+}
+
 /**
  * smack_msg_queue_associate - Smack access check for msg_queue
  * @msq: the object
@@ -1889,11 +2071,10 @@ static char *smack_of_msq(struct msg_queue *msq)
  */
 static int smack_msg_queue_associate(struct msg_queue *msq, int msqflg)
 {
-	char *msp = smack_of_msq(msq);
 	int may;
 
 	may = smack_flags_to_may(msqflg);
-	return smk_curacc(msp, may);
+	return smk_curacc_msq(msq, may);
 }
 
 /**
@@ -1905,7 +2086,6 @@ static int smack_msg_queue_associate(struct msg_queue *msq, int msqflg)
  */
 static int smack_msg_queue_msgctl(struct msg_queue *msq, int cmd)
 {
-	char *msp;
 	int may;
 
 	switch (cmd) {
@@ -1927,8 +2107,7 @@ static int smack_msg_queue_msgctl(struct msg_queue *msq, int cmd)
 		return -EINVAL;
 	}
 
-	msp = smack_of_msq(msq);
-	return smk_curacc(msp, may);
+	return smk_curacc_msq(msq, may);
 }
 
 /**
@@ -1942,11 +2121,10 @@ static int smack_msg_queue_msgctl(struct msg_queue *msq, int cmd)
 static int smack_msg_queue_msgsnd(struct msg_queue *msq, struct msg_msg *msg,
 				  int msqflg)
 {
-	char *msp = smack_of_msq(msq);
-	int rc;
+	int may;
 
-	rc = smack_flags_to_may(msqflg);
-	return smk_curacc(msp, rc);
+	may = smack_flags_to_may(msqflg);
+	return smk_curacc_msq(msq, may);
 }
 
 /**
@@ -1962,9 +2140,7 @@ static int smack_msg_queue_msgsnd(struct msg_queue *msq, struct msg_msg *msg,
 static int smack_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg,
 			struct task_struct *target, long type, int mode)
 {
-	char *msp = smack_of_msq(msq);
-
-	return smk_curacc(msp, MAY_READWRITE);
+	return smk_curacc_msq(msq, MAY_READWRITE);
 }
 
 /**
@@ -1977,10 +2153,14 @@ static int smack_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg,
 static int smack_ipc_permission(struct kern_ipc_perm *ipp, short flag)
 {
 	char *isp = ipp->security;
-	int may;
+	int may = smack_flags_to_may(flag);
+	struct smk_audit_info ad;
 
-	may = smack_flags_to_may(flag);
-	return smk_curacc(isp, may);
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+	ad.a.u.ipc_id = ipp->id;
+#endif
+	return smk_curacc(isp, may, &ad);
 }
 
 /**
@@ -2239,8 +2419,12 @@ static int smack_unix_stream_connect(struct socket *sock,
 {
 	struct inode *sp = SOCK_INODE(sock);
 	struct inode *op = SOCK_INODE(other);
+	struct smk_audit_info ad;
 
-	return smk_access(smk_of_inode(sp), smk_of_inode(op), MAY_READWRITE);
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+	smk_ad_setfield_u_net_sk(&ad, other->sk);
+	return smk_access(smk_of_inode(sp), smk_of_inode(op),
+				 MAY_READWRITE, &ad);
 }
 
 /**
@@ -2255,8 +2439,11 @@ static int smack_unix_may_send(struct socket *sock, struct socket *other)
 {
 	struct inode *sp = SOCK_INODE(sock);
 	struct inode *op = SOCK_INODE(other);
+	struct smk_audit_info ad;
 
-	return smk_access(smk_of_inode(sp), smk_of_inode(op), MAY_WRITE);
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+	smk_ad_setfield_u_net_sk(&ad, other->sk);
+	return smk_access(smk_of_inode(sp), smk_of_inode(op), MAY_WRITE, &ad);
 }
 
 /**
@@ -2371,7 +2558,7 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	char smack[SMK_LABELLEN];
 	char *csp;
 	int rc;
-
+	struct smk_audit_info ad;
 	if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)
 		return 0;
 
@@ -2389,13 +2576,19 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	netlbl_secattr_destroy(&secattr);
 
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+	ad.a.u.net.family = sk->sk_family;
+	ad.a.u.net.netif = skb->iif;
+	ipv4_skb_to_auditdata(skb, &ad.a, NULL);
+#endif
 	/*
 	 * Receiving a packet requires that the other end
 	 * be able to write here. Read access is not required.
 	 * This is the simplist possible security model
 	 * for networking.
 	 */
-	rc = smk_access(csp, ssp->smk_in, MAY_WRITE);
+	rc = smk_access(csp, ssp->smk_in, MAY_WRITE, &ad);
 	if (rc != 0)
 		netlbl_skbuff_err(skb, rc, 0);
 	return rc;
@@ -2524,6 +2717,7 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	struct iphdr *hdr;
 	char smack[SMK_LABELLEN];
 	int rc;
+	struct smk_audit_info ad;
 
 	/* handle mapped IPv4 packets arriving via IPv6 sockets */
 	if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
@@ -2537,11 +2731,17 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 		strncpy(smack, smack_known_huh.smk_known, SMK_MAXLEN);
 	netlbl_secattr_destroy(&secattr);
 
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET);
+	ad.a.u.net.family = family;
+	ad.a.u.net.netif = skb->iif;
+	ipv4_skb_to_auditdata(skb, &ad.a, NULL);
+#endif
 	/*
 	 * Receiving a packet requires that the other end be able to write
 	 * here. Read access is not required.
 	 */
-	rc = smk_access(smack, ssp->smk_in, MAY_WRITE);
+	rc = smk_access(smack, ssp->smk_in, MAY_WRITE, &ad);
 	if (rc != 0)
 		return rc;
 
@@ -2643,6 +2843,7 @@ static int smack_key_permission(key_ref_t key_ref,
 				const struct cred *cred, key_perm_t perm)
 {
 	struct key *keyp;
+	struct smk_audit_info ad;
 
 	keyp = key_ref_to_ptr(key_ref);
 	if (keyp == NULL)
@@ -2658,8 +2859,13 @@ static int smack_key_permission(key_ref_t key_ref,
 	 */
 	if (cred->security == NULL)
 		return -EACCES;
-
-	return smk_access(cred->security, keyp->security, MAY_READWRITE);
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_KEY);
+	ad.a.u.key_struct.key = keyp->serial;
+	ad.a.u.key_struct.key_desc = keyp->description;
+#endif
+	return smk_access(cred->security, keyp->security,
+				 MAY_READWRITE, &ad);
 }
 #endif /* CONFIG_KEYS */
 
@@ -2828,15 +3034,7 @@ struct security_operations smack_ops = {
 
 	.ptrace_may_access =		smack_ptrace_may_access,
 	.ptrace_traceme =		smack_ptrace_traceme,
-	.capget = 			cap_capget,
-	.capset = 			cap_capset,
-	.capable = 			cap_capable,
 	.syslog = 			smack_syslog,
-	.settime = 			cap_settime,
-	.vm_enough_memory = 		cap_vm_enough_memory,
-
-	.bprm_set_creds = 		cap_bprm_set_creds,
-	.bprm_secureexec = 		cap_bprm_secureexec,
 
 	.sb_alloc_security = 		smack_sb_alloc_security,
 	.sb_free_security = 		smack_sb_free_security,
@@ -2860,8 +3058,6 @@ struct security_operations smack_ops = {
 	.inode_post_setxattr = 		smack_inode_post_setxattr,
 	.inode_getxattr = 		smack_inode_getxattr,
 	.inode_removexattr = 		smack_inode_removexattr,
-	.inode_need_killpriv =		cap_inode_need_killpriv,
-	.inode_killpriv =		cap_inode_killpriv,
 	.inode_getsecurity = 		smack_inode_getsecurity,
 	.inode_setsecurity = 		smack_inode_setsecurity,
 	.inode_listsecurity = 		smack_inode_listsecurity,
@@ -2882,7 +3078,6 @@ struct security_operations smack_ops = {
 	.cred_commit =			smack_cred_commit,
 	.kernel_act_as =		smack_kernel_act_as,
 	.kernel_create_files_as =	smack_kernel_create_files_as,
-	.task_fix_setuid =		cap_task_fix_setuid,
 	.task_setpgid = 		smack_task_setpgid,
 	.task_getpgid = 		smack_task_getpgid,
 	.task_getsid = 			smack_task_getsid,
@@ -2896,7 +3091,6 @@ struct security_operations smack_ops = {
 	.task_kill = 			smack_task_kill,
 	.task_wait = 			smack_task_wait,
 	.task_to_inode = 		smack_task_to_inode,
-	.task_prctl =			cap_task_prctl,
 
 	.ipc_permission = 		smack_ipc_permission,
 	.ipc_getsecid =			smack_ipc_getsecid,
@@ -2923,9 +3117,6 @@ struct security_operations smack_ops = {
 	.sem_semctl = 			smack_sem_semctl,
 	.sem_semop = 			smack_sem_semop,
 
-	.netlink_send =			cap_netlink_send,
-	.netlink_recv = 		cap_netlink_recv,
-
 	.d_instantiate = 		smack_d_instantiate,
 
 	.getprocattr = 			smack_getprocattr,
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index e03a7e19c73b..f83a80980726 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -41,6 +41,7 @@ enum smk_inos {
 	SMK_AMBIENT	= 7,	/* internet ambient label */
 	SMK_NETLBLADDR	= 8,	/* single label hosts */
 	SMK_ONLYCAP	= 9,	/* the only "capable" label */
+	SMK_LOGGING	= 10,	/* logging */
 };
 
 /*
@@ -734,8 +735,8 @@ static void smk_netlbladdr_insert(struct smk_netlbladdr *new)
 		return;
 	}
 
-	m = list_entry(rcu_dereference(smk_netlbladdr_list.next),
-			 struct smk_netlbladdr, list);
+	m = list_entry_rcu(smk_netlbladdr_list.next,
+			   struct smk_netlbladdr, list);
 
 	/* the comparison '>' is a bit hacky, but works */
 	if (new->smk_mask.s_addr > m->smk_mask.s_addr) {
@@ -748,8 +749,8 @@ static void smk_netlbladdr_insert(struct smk_netlbladdr *new)
 			list_add_rcu(&new->list, &m->list);
 			return;
 		}
-		m_next = list_entry(rcu_dereference(m->list.next),
-				 struct smk_netlbladdr, list);
+		m_next = list_entry_rcu(m->list.next,
+					struct smk_netlbladdr, list);
 		if (new->smk_mask.s_addr > m_next->smk_mask.s_addr) {
 			list_add_rcu(&new->list, &m->list);
 			return;
@@ -775,7 +776,7 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf,
 	struct sockaddr_in newname;
 	char smack[SMK_LABELLEN];
 	char *sp;
-	char data[SMK_NETLBLADDRMAX];
+	char data[SMK_NETLBLADDRMAX + 1];
 	char *host = (char *)&newname.sin_addr.s_addr;
 	int rc;
 	struct netlbl_audit audit_info;
@@ -1191,6 +1192,69 @@ static const struct file_operations smk_onlycap_ops = {
 	.write		= smk_write_onlycap,
 };
 
+/**
+ * smk_read_logging - read() for /smack/logging
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @cn: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_logging(struct file *filp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char temp[32];
+	ssize_t rc;
+
+	if (*ppos != 0)
+		return 0;
+
+	sprintf(temp, "%d\n", log_policy);
+	rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
+	return rc;
+}
+
+/**
+ * smk_write_logging - write() for /smack/logging
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_logging(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char temp[32];
+	int i;
+
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (count >= sizeof(temp) || count == 0)
+		return -EINVAL;
+
+	if (copy_from_user(temp, buf, count) != 0)
+		return -EFAULT;
+
+	temp[count] = '\0';
+
+	if (sscanf(temp, "%d", &i) != 1)
+		return -EINVAL;
+	if (i < 0 || i > 3)
+		return -EINVAL;
+	log_policy = i;
+	return count;
+}
+
+
+
+static const struct file_operations smk_logging_ops = {
+	.read		= smk_read_logging,
+	.write		= smk_write_logging,
+};
 /**
  * smk_fill_super - fill the /smackfs superblock
  * @sb: the empty superblock
@@ -1221,6 +1285,8 @@ static int smk_fill_super(struct super_block *sb, void *data, int silent)
 			{"netlabel", &smk_netlbladdr_ops, S_IRUGO|S_IWUSR},
 		[SMK_ONLYCAP]	=
 			{"onlycap", &smk_onlycap_ops, S_IRUGO|S_IWUSR},
+		[SMK_LOGGING]	=
+			{"logging", &smk_logging_ops, S_IRUGO|S_IWUSR},
 		/* last one */ {""}
 	};
 
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index ddfb9cccf468..fdd1f4b8c448 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -28,7 +28,13 @@ static const char *tomoyo_mode_2[4] = {
 	"disabled", "enabled", "enabled", "enabled"
 };
 
-/* Table for profile. */
+/*
+ * tomoyo_control_array is a static data which contains
+ *
+ *  (1) functionality name used by /sys/kernel/security/tomoyo/profile .
+ *  (2) initial values for "struct tomoyo_profile".
+ *  (3) max values for "struct tomoyo_profile".
+ */
 static struct {
 	const char *keyword;
 	unsigned int current_value;
@@ -39,7 +45,13 @@ static struct {
 	[TOMOYO_VERBOSE]          = { "TOMOYO_VERBOSE",      1,       1 },
 };
 
-/* Profile table. Memory is allocated as needed. */
+/*
+ * tomoyo_profile is a structure which is used for holding the mode of access
+ * controls. TOMOYO has 4 modes: disabled, learning, permissive, enforcing.
+ * An administrator can define up to 256 profiles.
+ * The ->profile of "struct tomoyo_domain_info" is used for remembering
+ * the profile's number (0 - 255) assigned to that domain.
+ */
 static struct tomoyo_profile {
 	unsigned int value[TOMOYO_MAX_CONTROL_INDEX];
 	const struct tomoyo_path_info *comment;
@@ -428,7 +440,6 @@ void tomoyo_fill_path_info(struct tomoyo_path_info *ptr)
 	const char *name = ptr->name;
 	const int len = strlen(name);
 
-	ptr->total_len = len;
 	ptr->const_len = tomoyo_const_part_length(name);
 	ptr->is_dir = len && (name[len - 1] == '/');
 	ptr->is_patterned = (ptr->const_len < len);
@@ -866,7 +877,6 @@ static struct tomoyo_profile *tomoyo_find_or_assign_new_profile(const unsigned
 
 	if (profile >= TOMOYO_MAX_PROFILES)
 		return NULL;
-	/***** EXCLUSIVE SECTION START *****/
 	mutex_lock(&lock);
 	ptr = tomoyo_profile_ptr[profile];
 	if (ptr)
@@ -880,7 +890,6 @@ static struct tomoyo_profile *tomoyo_find_or_assign_new_profile(const unsigned
 	tomoyo_profile_ptr[profile] = ptr;
  ok:
 	mutex_unlock(&lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return ptr;
 }
 
@@ -1009,7 +1018,19 @@ static int tomoyo_read_profile(struct tomoyo_io_buffer *head)
 	return 0;
 }
 
-/* Structure for policy manager. */
+/*
+ * tomoyo_policy_manager_entry is a structure which is used for holding list of
+ * domainnames or programs which are permitted to modify configuration via
+ * /sys/kernel/security/tomoyo/ interface.
+ * It has following fields.
+ *
+ *  (1) "list" which is linked to tomoyo_policy_manager_list .
+ *  (2) "manager" is a domainname or a program's pathname.
+ *  (3) "is_domain" is a bool which is true if "manager" is a domainname, false
+ *      otherwise.
+ *  (4) "is_deleted" is a bool which is true if marked as deleted, false
+ *      otherwise.
+ */
 struct tomoyo_policy_manager_entry {
 	struct list_head list;
 	/* A path to program or a domainname. */
@@ -1018,7 +1039,36 @@ struct tomoyo_policy_manager_entry {
 	bool is_deleted; /* True if this entry is deleted. */
 };
 
-/* The list for "struct tomoyo_policy_manager_entry". */
+/*
+ * tomoyo_policy_manager_list is used for holding list of domainnames or
+ * programs which are permitted to modify configuration via
+ * /sys/kernel/security/tomoyo/ interface.
+ *
+ * An entry is added by
+ *
+ * # echo '<kernel> /sbin/mingetty /bin/login /bin/bash' > \
+ *                                        /sys/kernel/security/tomoyo/manager
+ *  (if you want to specify by a domainname)
+ *
+ *  or
+ *
+ * # echo '/usr/lib/ccs/editpolicy' > /sys/kernel/security/tomoyo/manager
+ *  (if you want to specify by a program's location)
+ *
+ * and is deleted by
+ *
+ * # echo 'delete <kernel> /sbin/mingetty /bin/login /bin/bash' > \
+ *                                        /sys/kernel/security/tomoyo/manager
+ *
+ *  or
+ *
+ * # echo 'delete /usr/lib/ccs/editpolicy' > \
+ *                                        /sys/kernel/security/tomoyo/manager
+ *
+ * and all entries are retrieved by
+ *
+ * # cat /sys/kernel/security/tomoyo/manager
+ */
 static LIST_HEAD(tomoyo_policy_manager_list);
 static DECLARE_RWSEM(tomoyo_policy_manager_list_lock);
 
@@ -1050,7 +1100,6 @@ static int tomoyo_update_manager_entry(const char *manager,
 	saved_manager = tomoyo_save_name(manager);
 	if (!saved_manager)
 		return -ENOMEM;
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_policy_manager_list_lock);
 	list_for_each_entry(ptr, &tomoyo_policy_manager_list, list) {
 		if (ptr->manager != saved_manager)
@@ -1072,7 +1121,6 @@ static int tomoyo_update_manager_entry(const char *manager,
 	error = 0;
  out:
 	up_write(&tomoyo_policy_manager_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return error;
 }
 
@@ -1117,10 +1165,9 @@ static int tomoyo_read_manager_policy(struct tomoyo_io_buffer *head)
 				 list);
 		if (ptr->is_deleted)
 			continue;
-		if (!tomoyo_io_printf(head, "%s\n", ptr->manager->name)) {
-			done = false;
+		done = tomoyo_io_printf(head, "%s\n", ptr->manager->name);
+		if (!done)
 			break;
-		}
 	}
 	up_read(&tomoyo_policy_manager_list_lock);
 	head->read_eof = done;
@@ -1197,13 +1244,11 @@ static bool tomoyo_is_select_one(struct tomoyo_io_buffer *head,
 
 	if (sscanf(data, "pid=%u", &pid) == 1) {
 		struct task_struct *p;
-		/***** CRITICAL SECTION START *****/
 		read_lock(&tasklist_lock);
 		p = find_task_by_vpid(pid);
 		if (p)
 			domain = tomoyo_real_domain(p);
 		read_unlock(&tasklist_lock);
-		/***** CRITICAL SECTION END *****/
 	} else if (!strncmp(data, "domain=", 7)) {
 		if (tomoyo_is_domain_def(data + 7)) {
 			down_read(&tomoyo_domain_list_lock);
@@ -1447,15 +1492,14 @@ static int tomoyo_read_domain_policy(struct tomoyo_io_buffer *head)
 		    TOMOYO_DOMAIN_FLAGS_IGNORE_GLOBAL_ALLOW_READ)
 			ignore_global_allow_read
 				= TOMOYO_KEYWORD_IGNORE_GLOBAL_ALLOW_READ "\n";
-		if (!tomoyo_io_printf(head,
-				      "%s\n" TOMOYO_KEYWORD_USE_PROFILE "%u\n"
-				      "%s%s%s\n", domain->domainname->name,
-				      domain->profile, quota_exceeded,
-				      transition_failed,
-				      ignore_global_allow_read)) {
-			done = false;
+		done = tomoyo_io_printf(head, "%s\n" TOMOYO_KEYWORD_USE_PROFILE
+					"%u\n%s%s%s\n",
+					domain->domainname->name,
+					domain->profile, quota_exceeded,
+					transition_failed,
+					ignore_global_allow_read);
+		if (!done)
 			break;
-		}
 		head->read_step = 2;
 acl_loop:
 		if (head->read_step == 3)
@@ -1463,24 +1507,22 @@ acl_loop:
 		/* Print ACL entries in the domain. */
 		down_read(&tomoyo_domain_acl_info_list_lock);
 		list_for_each_cookie(apos, head->read_var2,
-				      &domain->acl_info_list) {
+				     &domain->acl_info_list) {
 			struct tomoyo_acl_info *ptr
 				= list_entry(apos, struct tomoyo_acl_info,
-					      list);
-			if (!tomoyo_print_entry(head, ptr)) {
-				done = false;
+					     list);
+			done = tomoyo_print_entry(head, ptr);
+			if (!done)
 				break;
-			}
 		}
 		up_read(&tomoyo_domain_acl_info_list_lock);
 		if (!done)
 			break;
 		head->read_step = 3;
 tail_mark:
-		if (!tomoyo_io_printf(head, "\n")) {
-			done = false;
+		done = tomoyo_io_printf(head, "\n");
+		if (!done)
 			break;
-		}
 		head->read_step = 1;
 		if (head->read_single_domain)
 			break;
@@ -1550,11 +1592,10 @@ static int tomoyo_read_domain_profile(struct tomoyo_io_buffer *head)
 		domain = list_entry(pos, struct tomoyo_domain_info, list);
 		if (domain->is_deleted)
 			continue;
-		if (!tomoyo_io_printf(head, "%u %s\n", domain->profile,
-				      domain->domainname->name)) {
-			done = false;
+		done = tomoyo_io_printf(head, "%u %s\n", domain->profile,
+					domain->domainname->name);
+		if (!done)
 			break;
-		}
 	}
 	up_read(&tomoyo_domain_list_lock);
 	head->read_eof = done;
@@ -1594,13 +1635,11 @@ static int tomoyo_read_pid(struct tomoyo_io_buffer *head)
 		const int pid = head->read_step;
 		struct task_struct *p;
 		struct tomoyo_domain_info *domain = NULL;
-		/***** CRITICAL SECTION START *****/
 		read_lock(&tasklist_lock);
 		p = find_task_by_vpid(pid);
 		if (p)
 			domain = tomoyo_real_domain(p);
 		read_unlock(&tasklist_lock);
-		/***** CRITICAL SECTION END *****/
 		if (domain)
 			tomoyo_io_printf(head, "%d %u %s", pid, domain->profile,
 					 domain->domainname->name);
@@ -2138,7 +2177,13 @@ static ssize_t tomoyo_write(struct file *file, const char __user *buf,
 	return tomoyo_write_control(file, buf, count);
 }
 
-/* Operations for /sys/kernel/security/tomoyo/ interface. */
+/*
+ * tomoyo_operations is a "struct file_operations" which is used for handling
+ * /sys/kernel/security/tomoyo/ interface.
+ *
+ * Some files under /sys/kernel/security/tomoyo/ directory accept open(O_RDWR).
+ * See tomoyo_io_buffer for internals.
+ */
 static const struct file_operations tomoyo_operations = {
 	.open    = tomoyo_open,
 	.release = tomoyo_release,
diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h
index 678f4ff16aa4..6d6ba09af457 100644
--- a/security/tomoyo/common.h
+++ b/security/tomoyo/common.h
@@ -26,16 +26,43 @@
 struct dentry;
 struct vfsmount;
 
-/* Temporary buffer for holding pathnames. */
+/*
+ * tomoyo_page_buffer is a structure which is used for holding a pathname
+ * obtained from "struct dentry" and "struct vfsmount" pair.
+ * As of now, it is 4096 bytes. If users complain that 4096 bytes is too small
+ * (because TOMOYO escapes non ASCII printable characters using \ooo format),
+ * we will make the buffer larger.
+ */
 struct tomoyo_page_buffer {
 	char buffer[4096];
 };
 
-/* Structure for holding a token. */
+/*
+ * tomoyo_path_info is a structure which is used for holding a string data
+ * used by TOMOYO.
+ * This structure has several fields for supporting pattern matching.
+ *
+ * (1) "name" is the '\0' terminated string data.
+ * (2) "hash" is full_name_hash(name, strlen(name)).
+ *     This allows tomoyo_pathcmp() to compare by hash before actually compare
+ *     using strcmp().
+ * (3) "const_len" is the length of the initial segment of "name" which
+ *     consists entirely of non wildcard characters. In other words, the length
+ *     which we can compare two strings using strncmp().
+ * (4) "is_dir" is a bool which is true if "name" ends with "/",
+ *     false otherwise.
+ *     TOMOYO distinguishes directory and non-directory. A directory ends with
+ *     "/" and non-directory does not end with "/".
+ * (5) "is_patterned" is a bool which is true if "name" contains wildcard
+ *     characters, false otherwise. This allows TOMOYO to use "hash" and
+ *     strcmp() for string comparison if "is_patterned" is false.
+ * (6) "depth" is calculated using the number of "/" characters in "name".
+ *     This allows TOMOYO to avoid comparing two pathnames which never match
+ *     (e.g. whether "/var/www/html/index.html" matches "/tmp/sh-thd-\$").
+ */
 struct tomoyo_path_info {
 	const char *name;
 	u32 hash;          /* = full_name_hash(name, strlen(name)) */
-	u16 total_len;     /* = strlen(name)                       */
 	u16 const_len;     /* = tomoyo_const_part_length(name)     */
 	bool is_dir;       /* = tomoyo_strendswith(name, "/")      */
 	bool is_patterned; /* = tomoyo_path_contains_pattern(name) */
@@ -51,7 +78,20 @@ struct tomoyo_path_info {
  */
 #define TOMOYO_MAX_PATHNAME_LEN 4000
 
-/* Structure for holding requested pathname. */
+/*
+ * tomoyo_path_info_with_data is a structure which is used for holding a
+ * pathname obtained from "struct dentry" and "struct vfsmount" pair.
+ *
+ * "struct tomoyo_path_info_with_data" consists of "struct tomoyo_path_info"
+ * and buffer for the pathname, while "struct tomoyo_page_buffer" consists of
+ * buffer for the pathname only.
+ *
+ * "struct tomoyo_path_info_with_data" is intended to allow TOMOYO to release
+ * both "struct tomoyo_path_info" and buffer for the pathname by single kfree()
+ * so that we don't need to return two pointers to the caller. If the caller
+ * puts "struct tomoyo_path_info" on stack memory, we will be able to remove
+ * "struct tomoyo_path_info_with_data".
+ */
 struct tomoyo_path_info_with_data {
 	/* Keep "head" first, for this pointer is passed to tomoyo_free(). */
 	struct tomoyo_path_info head;
@@ -61,7 +101,15 @@ struct tomoyo_path_info_with_data {
 };
 
 /*
- * Common header for holding ACL entries.
+ * tomoyo_acl_info is a structure which is used for holding
+ *
+ *  (1) "list" which is linked to the ->acl_info_list of
+ *      "struct tomoyo_domain_info"
+ *  (2) "type" which tells
+ *      (a) type & 0x7F : type of the entry (either
+ *          "struct tomoyo_single_path_acl_record" or
+ *          "struct tomoyo_double_path_acl_record")
+ *      (b) type & 0x80 : whether the entry is marked as "deleted".
  *
  * Packing "struct tomoyo_acl_info" allows
  * "struct tomoyo_single_path_acl_record" to embed "u16" and
@@ -81,7 +129,28 @@ struct tomoyo_acl_info {
 /* This ACL entry is deleted.           */
 #define TOMOYO_ACL_DELETED        0x80
 
-/* Structure for domain information. */
+/*
+ * tomoyo_domain_info is a structure which is used for holding permissions
+ * (e.g. "allow_read /lib/libc-2.5.so") given to each domain.
+ * It has following fields.
+ *
+ *  (1) "list" which is linked to tomoyo_domain_list .
+ *  (2) "acl_info_list" which is linked to "struct tomoyo_acl_info".
+ *  (3) "domainname" which holds the name of the domain.
+ *  (4) "profile" which remembers profile number assigned to this domain.
+ *  (5) "is_deleted" is a bool which is true if this domain is marked as
+ *      "deleted", false otherwise.
+ *  (6) "quota_warned" is a bool which is used for suppressing warning message
+ *      when learning mode learned too much entries.
+ *  (7) "flags" which remembers this domain's attributes.
+ *
+ * A domain's lifecycle is an analogy of files on / directory.
+ * Multiple domains with the same domainname cannot be created (as with
+ * creating files with the same filename fails with -EEXIST).
+ * If a process reached a domain, that process can reside in that domain after
+ * that domain is marked as "deleted" (as with a process can access an already
+ * open()ed file after that file was unlink()ed).
+ */
 struct tomoyo_domain_info {
 	struct list_head list;
 	struct list_head acl_info_list;
@@ -108,10 +177,18 @@ struct tomoyo_domain_info {
 #define TOMOYO_DOMAIN_FLAGS_TRANSITION_FAILED        2
 
 /*
- * Structure for "allow_read/write", "allow_execute", "allow_read",
- * "allow_write", "allow_create", "allow_unlink", "allow_mkdir", "allow_rmdir",
- * "allow_mkfifo", "allow_mksock", "allow_mkblock", "allow_mkchar",
- * "allow_truncate", "allow_symlink" and "allow_rewrite" directive.
+ * tomoyo_single_path_acl_record is a structure which is used for holding an
+ * entry with one pathname operation (e.g. open(), mkdir()).
+ * It has following fields.
+ *
+ *  (1) "head" which is a "struct tomoyo_acl_info".
+ *  (2) "perm" which is a bitmask of permitted operations.
+ *  (3) "filename" is the pathname.
+ *
+ * Directives held by this structure are "allow_read/write", "allow_execute",
+ * "allow_read", "allow_write", "allow_create", "allow_unlink", "allow_mkdir",
+ * "allow_rmdir", "allow_mkfifo", "allow_mksock", "allow_mkblock",
+ * "allow_mkchar", "allow_truncate", "allow_symlink" and "allow_rewrite".
  */
 struct tomoyo_single_path_acl_record {
 	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_SINGLE_PATH_ACL */
@@ -120,7 +197,18 @@ struct tomoyo_single_path_acl_record {
 	const struct tomoyo_path_info *filename;
 };
 
-/* Structure for "allow_rename" and "allow_link" directive. */
+/*
+ * tomoyo_double_path_acl_record is a structure which is used for holding an
+ * entry with two pathnames operation (i.e. link() and rename()).
+ * It has following fields.
+ *
+ *  (1) "head" which is a "struct tomoyo_acl_info".
+ *  (2) "perm" which is a bitmask of permitted operations.
+ *  (3) "filename1" is the source/old pathname.
+ *  (4) "filename2" is the destination/new pathname.
+ *
+ * Directives held by this structure are "allow_rename" and "allow_link".
+ */
 struct tomoyo_double_path_acl_record {
 	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_DOUBLE_PATH_ACL */
 	u8 perm;
@@ -153,7 +241,29 @@ struct tomoyo_double_path_acl_record {
 #define TOMOYO_VERBOSE                       2
 #define TOMOYO_MAX_CONTROL_INDEX             3
 
-/* Structure for reading/writing policy via securityfs interfaces. */
+/*
+ * tomoyo_io_buffer is a structure which is used for reading and modifying
+ * configuration via /sys/kernel/security/tomoyo/ interface.
+ * It has many fields. ->read_var1 , ->read_var2 , ->write_var1 are used as
+ * cursors.
+ *
+ * Since the content of /sys/kernel/security/tomoyo/domain_policy is a list of
+ * "struct tomoyo_domain_info" entries and each "struct tomoyo_domain_info"
+ * entry has a list of "struct tomoyo_acl_info", we need two cursors when
+ * reading (one is for traversing tomoyo_domain_list and the other is for
+ * traversing "struct tomoyo_acl_info"->acl_info_list ).
+ *
+ * If a line written to /sys/kernel/security/tomoyo/domain_policy starts with
+ * "select ", TOMOYO seeks the cursor ->read_var1 and ->write_var1 to the
+ * domain with the domainname specified by the rest of that line (NULL is set
+ * if seek failed).
+ * If a line written to /sys/kernel/security/tomoyo/domain_policy starts with
+ * "delete ", TOMOYO deletes an entry or a domain specified by the rest of that
+ * line (->write_var1 is set to NULL if a domain was deleted).
+ * If a line written to /sys/kernel/security/tomoyo/domain_policy starts with
+ * neither "select " nor "delete ", an entry or a domain specified by that line
+ * is appended.
+ */
 struct tomoyo_io_buffer {
 	int (*read) (struct tomoyo_io_buffer *);
 	int (*write) (struct tomoyo_io_buffer *);
diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c
index 2d6748741a26..1d8b16960576 100644
--- a/security/tomoyo/domain.c
+++ b/security/tomoyo/domain.c
@@ -19,11 +19,63 @@
 /* The initial domain. */
 struct tomoyo_domain_info tomoyo_kernel_domain;
 
-/* The list for "struct tomoyo_domain_info". */
+/*
+ * tomoyo_domain_list is used for holding list of domains.
+ * The ->acl_info_list of "struct tomoyo_domain_info" is used for holding
+ * permissions (e.g. "allow_read /lib/libc-2.5.so") given to each domain.
+ *
+ * An entry is added by
+ *
+ * # ( echo "<kernel>"; echo "allow_execute /sbin/init" ) > \
+ *                                  /sys/kernel/security/tomoyo/domain_policy
+ *
+ * and is deleted by
+ *
+ * # ( echo "<kernel>"; echo "delete allow_execute /sbin/init" ) > \
+ *                                  /sys/kernel/security/tomoyo/domain_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # cat /sys/kernel/security/tomoyo/domain_policy
+ *
+ * A domain is added by
+ *
+ * # echo "<kernel>" > /sys/kernel/security/tomoyo/domain_policy
+ *
+ * and is deleted by
+ *
+ * # echo "delete <kernel>" > /sys/kernel/security/tomoyo/domain_policy
+ *
+ * and all domains are retrieved by
+ *
+ * # grep '^<kernel>' /sys/kernel/security/tomoyo/domain_policy
+ *
+ * Normally, a domainname is monotonically getting longer because a domainname
+ * which the process will belong to if an execve() operation succeeds is
+ * defined as a concatenation of "current domainname" + "pathname passed to
+ * execve()".
+ * See tomoyo_domain_initializer_list and tomoyo_domain_keeper_list for
+ * exceptions.
+ */
 LIST_HEAD(tomoyo_domain_list);
 DECLARE_RWSEM(tomoyo_domain_list_lock);
 
-/* Structure for "initialize_domain" and "no_initialize_domain" keyword. */
+/*
+ * tomoyo_domain_initializer_entry is a structure which is used for holding
+ * "initialize_domain" and "no_initialize_domain" entries.
+ * It has following fields.
+ *
+ *  (1) "list" which is linked to tomoyo_domain_initializer_list .
+ *  (2) "domainname" which is "a domainname" or "the last component of a
+ *      domainname". This field is NULL if "from" clause is not specified.
+ *  (3) "program" which is a program's pathname.
+ *  (4) "is_deleted" is a bool which is true if marked as deleted, false
+ *      otherwise.
+ *  (5) "is_not" is a bool which is true if "no_initialize_domain", false
+ *      otherwise.
+ *  (6) "is_last_name" is a bool which is true if "domainname" is "the last
+ *      component of a domainname", false otherwise.
+ */
 struct tomoyo_domain_initializer_entry {
 	struct list_head list;
 	const struct tomoyo_path_info *domainname;    /* This may be NULL */
@@ -34,7 +86,23 @@ struct tomoyo_domain_initializer_entry {
 	bool is_last_name;
 };
 
-/* Structure for "keep_domain" and "no_keep_domain" keyword. */
+/*
+ * tomoyo_domain_keeper_entry is a structure which is used for holding
+ * "keep_domain" and "no_keep_domain" entries.
+ * It has following fields.
+ *
+ *  (1) "list" which is linked to tomoyo_domain_keeper_list .
+ *  (2) "domainname" which is "a domainname" or "the last component of a
+ *      domainname".
+ *  (3) "program" which is a program's pathname.
+ *      This field is NULL if "from" clause is not specified.
+ *  (4) "is_deleted" is a bool which is true if marked as deleted, false
+ *      otherwise.
+ *  (5) "is_not" is a bool which is true if "no_initialize_domain", false
+ *      otherwise.
+ *  (6) "is_last_name" is a bool which is true if "domainname" is "the last
+ *      component of a domainname", false otherwise.
+ */
 struct tomoyo_domain_keeper_entry {
 	struct list_head list;
 	const struct tomoyo_path_info *domainname;
@@ -45,7 +113,16 @@ struct tomoyo_domain_keeper_entry {
 	bool is_last_name;
 };
 
-/* Structure for "alias" keyword. */
+/*
+ * tomoyo_alias_entry is a structure which is used for holding "alias" entries.
+ * It has following fields.
+ *
+ *  (1) "list" which is linked to tomoyo_alias_list .
+ *  (2) "original_name" which is a dereferenced pathname.
+ *  (3) "aliased_name" which is a symlink's pathname.
+ *  (4) "is_deleted" is a bool which is true if marked as deleted, false
+ *      otherwise.
+ */
 struct tomoyo_alias_entry {
 	struct list_head list;
 	const struct tomoyo_path_info *original_name;
@@ -67,14 +144,12 @@ void tomoyo_set_domain_flag(struct tomoyo_domain_info *domain,
 {
 	/* We need to serialize because this is bitfield operation. */
 	static DEFINE_SPINLOCK(lock);
-	/***** CRITICAL SECTION START *****/
 	spin_lock(&lock);
 	if (!is_delete)
 		domain->flags |= flags;
 	else
 		domain->flags &= ~flags;
 	spin_unlock(&lock);
-	/***** CRITICAL SECTION END *****/
 }
 
 /**
@@ -94,7 +169,42 @@ const char *tomoyo_get_last_name(const struct tomoyo_domain_info *domain)
 	return cp0;
 }
 
-/* The list for "struct tomoyo_domain_initializer_entry". */
+/*
+ * tomoyo_domain_initializer_list is used for holding list of programs which
+ * triggers reinitialization of domainname. Normally, a domainname is
+ * monotonically getting longer. But sometimes, we restart daemon programs.
+ * It would be convenient for us that "a daemon started upon system boot" and
+ * "the daemon restarted from console" belong to the same domain. Thus, TOMOYO
+ * provides a way to shorten domainnames.
+ *
+ * An entry is added by
+ *
+ * # echo 'initialize_domain /usr/sbin/httpd' > \
+ *                               /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete initialize_domain /usr/sbin/httpd' > \
+ *                               /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^initialize_domain /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, /usr/sbin/httpd will belong to
+ * "<kernel> /usr/sbin/httpd" domain.
+ *
+ * You may specify a domainname using "from" keyword.
+ * "initialize_domain /usr/sbin/httpd from <kernel> /etc/rc.d/init.d/httpd"
+ * will cause "/usr/sbin/httpd" executed from "<kernel> /etc/rc.d/init.d/httpd"
+ * domain to belong to "<kernel> /usr/sbin/httpd" domain.
+ *
+ * You may add "no_" prefix to "initialize_domain".
+ * "initialize_domain /usr/sbin/httpd" and
+ * "no_initialize_domain /usr/sbin/httpd from <kernel> /etc/rc.d/init.d/httpd"
+ * will cause "/usr/sbin/httpd" to belong to "<kernel> /usr/sbin/httpd" domain
+ * unless executed from "<kernel> /etc/rc.d/init.d/httpd" domain.
+ */
 static LIST_HEAD(tomoyo_domain_initializer_list);
 static DECLARE_RWSEM(tomoyo_domain_initializer_list_lock);
 
@@ -135,7 +245,6 @@ static int tomoyo_update_domain_initializer_entry(const char *domainname,
 	saved_program = tomoyo_save_name(program);
 	if (!saved_program)
 		return -ENOMEM;
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_domain_initializer_list_lock);
 	list_for_each_entry(ptr, &tomoyo_domain_initializer_list, list) {
 		if (ptr->is_not != is_not ||
@@ -161,7 +270,6 @@ static int tomoyo_update_domain_initializer_entry(const char *domainname,
 	error = 0;
  out:
 	up_write(&tomoyo_domain_initializer_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return error;
 }
 
@@ -193,13 +301,12 @@ bool tomoyo_read_domain_initializer_policy(struct tomoyo_io_buffer *head)
 			from = " from ";
 			domain = ptr->domainname->name;
 		}
-		if (!tomoyo_io_printf(head,
-				      "%s" TOMOYO_KEYWORD_INITIALIZE_DOMAIN
-				      "%s%s%s\n", no, ptr->program->name, from,
-				      domain)) {
-			done = false;
+		done = tomoyo_io_printf(head,
+					"%s" TOMOYO_KEYWORD_INITIALIZE_DOMAIN
+					"%s%s%s\n", no, ptr->program->name,
+					from, domain);
+		if (!done)
 			break;
-		}
 	}
 	up_read(&tomoyo_domain_initializer_list_lock);
 	return done;
@@ -273,7 +380,44 @@ static bool tomoyo_is_domain_initializer(const struct tomoyo_path_info *
 	return flag;
 }
 
-/* The list for "struct tomoyo_domain_keeper_entry". */
+/*
+ * tomoyo_domain_keeper_list is used for holding list of domainnames which
+ * suppresses domain transition. Normally, a domainname is monotonically
+ * getting longer. But sometimes, we want to suppress domain transition.
+ * It would be convenient for us that programs executed from a login session
+ * belong to the same domain. Thus, TOMOYO provides a way to suppress domain
+ * transition.
+ *
+ * An entry is added by
+ *
+ * # echo 'keep_domain <kernel> /usr/sbin/sshd /bin/bash' > \
+ *                              /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete keep_domain <kernel> /usr/sbin/sshd /bin/bash' > \
+ *                              /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^keep_domain /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, any process which belongs to
+ * "<kernel> /usr/sbin/sshd /bin/bash" domain will remain in that domain,
+ * unless explicitly specified by "initialize_domain" or "no_keep_domain".
+ *
+ * You may specify a program using "from" keyword.
+ * "keep_domain /bin/pwd from <kernel> /usr/sbin/sshd /bin/bash"
+ * will cause "/bin/pwd" executed from "<kernel> /usr/sbin/sshd /bin/bash"
+ * domain to remain in "<kernel> /usr/sbin/sshd /bin/bash" domain.
+ *
+ * You may add "no_" prefix to "keep_domain".
+ * "keep_domain <kernel> /usr/sbin/sshd /bin/bash" and
+ * "no_keep_domain /usr/bin/passwd from <kernel> /usr/sbin/sshd /bin/bash" will
+ * cause "/usr/bin/passwd" to belong to
+ * "<kernel> /usr/sbin/sshd /bin/bash /usr/bin/passwd" domain, unless
+ * explicitly specified by "initialize_domain".
+ */
 static LIST_HEAD(tomoyo_domain_keeper_list);
 static DECLARE_RWSEM(tomoyo_domain_keeper_list_lock);
 
@@ -296,7 +440,6 @@ static int tomoyo_update_domain_keeper_entry(const char *domainname,
 	struct tomoyo_domain_keeper_entry *ptr;
 	const struct tomoyo_path_info *saved_domainname;
 	const struct tomoyo_path_info *saved_program = NULL;
-	static DEFINE_MUTEX(lock);
 	int error = -ENOMEM;
 	bool is_last_name = false;
 
@@ -315,7 +458,6 @@ static int tomoyo_update_domain_keeper_entry(const char *domainname,
 	saved_domainname = tomoyo_save_name(domainname);
 	if (!saved_domainname)
 		return -ENOMEM;
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_domain_keeper_list_lock);
 	list_for_each_entry(ptr, &tomoyo_domain_keeper_list, list) {
 		if (ptr->is_not != is_not ||
@@ -341,7 +483,6 @@ static int tomoyo_update_domain_keeper_entry(const char *domainname,
 	error = 0;
  out:
 	up_write(&tomoyo_domain_keeper_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return error;
 }
 
@@ -394,13 +535,12 @@ bool tomoyo_read_domain_keeper_policy(struct tomoyo_io_buffer *head)
 			from = " from ";
 			program = ptr->program->name;
 		}
-		if (!tomoyo_io_printf(head,
-				      "%s" TOMOYO_KEYWORD_KEEP_DOMAIN
-				      "%s%s%s\n", no, program, from,
-				      ptr->domainname->name)) {
-			done = false;
+		done = tomoyo_io_printf(head,
+					"%s" TOMOYO_KEYWORD_KEEP_DOMAIN
+					"%s%s%s\n", no, program, from,
+					ptr->domainname->name);
+		if (!done)
 			break;
-		}
 	}
 	up_read(&tomoyo_domain_keeper_list_lock);
 	return done;
@@ -446,7 +586,36 @@ static bool tomoyo_is_domain_keeper(const struct tomoyo_path_info *domainname,
 	return flag;
 }
 
-/* The list for "struct tomoyo_alias_entry". */
+/*
+ * tomoyo_alias_list is used for holding list of symlink's pathnames which are
+ * allowed to be passed to an execve() request. Normally, the domainname which
+ * the current process will belong to after execve() succeeds is calculated
+ * using dereferenced pathnames. But some programs behave differently depending
+ * on the name passed to argv[0]. For busybox, calculating domainname using
+ * dereferenced pathnames will cause all programs in the busybox to belong to
+ * the same domain. Thus, TOMOYO provides a way to allow use of symlink's
+ * pathname for checking execve()'s permission and calculating domainname which
+ * the current process will belong to after execve() succeeds.
+ *
+ * An entry is added by
+ *
+ * # echo 'alias /bin/busybox /bin/cat' > \
+ *                            /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete alias /bin/busybox /bin/cat' > \
+ *                            /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^alias /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, if /bin/cat is a symlink to /bin/busybox and execution
+ * of /bin/cat is requested, permission is checked for /bin/cat rather than
+ * /bin/busybox and domainname which the current process will belong to after
+ * execve() succeeds is calculated using /bin/cat rather than /bin/busybox .
+ */
 static LIST_HEAD(tomoyo_alias_list);
 static DECLARE_RWSEM(tomoyo_alias_list_lock);
 
@@ -476,7 +645,6 @@ static int tomoyo_update_alias_entry(const char *original_name,
 	saved_aliased_name = tomoyo_save_name(aliased_name);
 	if (!saved_original_name || !saved_aliased_name)
 		return -ENOMEM;
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_alias_list_lock);
 	list_for_each_entry(ptr, &tomoyo_alias_list, list) {
 		if (ptr->original_name != saved_original_name ||
@@ -499,7 +667,6 @@ static int tomoyo_update_alias_entry(const char *original_name,
 	error = 0;
  out:
 	up_write(&tomoyo_alias_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return error;
 }
 
@@ -522,12 +689,11 @@ bool tomoyo_read_alias_policy(struct tomoyo_io_buffer *head)
 		ptr = list_entry(pos, struct tomoyo_alias_entry, list);
 		if (ptr->is_deleted)
 			continue;
-		if (!tomoyo_io_printf(head, TOMOYO_KEYWORD_ALIAS "%s %s\n",
-				      ptr->original_name->name,
-				      ptr->aliased_name->name)) {
-			done = false;
+		done = tomoyo_io_printf(head, TOMOYO_KEYWORD_ALIAS "%s %s\n",
+					ptr->original_name->name,
+					ptr->aliased_name->name);
+		if (!done)
 			break;
-		}
 	}
 	up_read(&tomoyo_alias_list_lock);
 	return done;
@@ -567,7 +733,6 @@ int tomoyo_delete_domain(char *domainname)
 
 	name.name = domainname;
 	tomoyo_fill_path_info(&name);
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_domain_list_lock);
 	/* Is there an active domain? */
 	list_for_each_entry(domain, &tomoyo_domain_list, list) {
@@ -581,7 +746,6 @@ int tomoyo_delete_domain(char *domainname)
 		break;
 	}
 	up_write(&tomoyo_domain_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return 0;
 }
 
@@ -600,7 +764,6 @@ struct tomoyo_domain_info *tomoyo_find_or_assign_new_domain(const char *
 	struct tomoyo_domain_info *domain = NULL;
 	const struct tomoyo_path_info *saved_domainname;
 
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_domain_list_lock);
 	domain = tomoyo_find_domain(domainname);
 	if (domain)
@@ -619,7 +782,6 @@ struct tomoyo_domain_info *tomoyo_find_or_assign_new_domain(const char *
 		    domain->domainname != saved_domainname)
 			continue;
 		flag = false;
-		/***** CRITICAL SECTION START *****/
 		read_lock(&tasklist_lock);
 		for_each_process(p) {
 			if (tomoyo_real_domain(p) != domain)
@@ -628,7 +790,6 @@ struct tomoyo_domain_info *tomoyo_find_or_assign_new_domain(const char *
 			break;
 		}
 		read_unlock(&tasklist_lock);
-		/***** CRITICAL SECTION END *****/
 		if (flag)
 			continue;
 		list_for_each_entry(ptr, &domain->acl_info_list, list) {
@@ -651,7 +812,6 @@ struct tomoyo_domain_info *tomoyo_find_or_assign_new_domain(const char *
 	}
  out:
 	up_write(&tomoyo_domain_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return domain;
 }
 
@@ -739,7 +899,7 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm,
 	}
 
 	/* Check execute permission. */
-	retval = tomoyo_check_exec_perm(old_domain, &r, tmp);
+	retval = tomoyo_check_exec_perm(old_domain, &r);
 	if (retval < 0)
 		goto out;
 
diff --git a/security/tomoyo/file.c b/security/tomoyo/file.c
index 2316da8ec5bc..5ae3a571559f 100644
--- a/security/tomoyo/file.c
+++ b/security/tomoyo/file.c
@@ -14,21 +14,50 @@
 #include "realpath.h"
 #define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])
 
-/* Structure for "allow_read" keyword. */
+/*
+ * tomoyo_globally_readable_file_entry is a structure which is used for holding
+ * "allow_read" entries.
+ * It has following fields.
+ *
+ *  (1) "list" which is linked to tomoyo_globally_readable_list .
+ *  (2) "filename" is a pathname which is allowed to open(O_RDONLY).
+ *  (3) "is_deleted" is a bool which is true if marked as deleted, false
+ *      otherwise.
+ */
 struct tomoyo_globally_readable_file_entry {
 	struct list_head list;
 	const struct tomoyo_path_info *filename;
 	bool is_deleted;
 };
 
-/* Structure for "file_pattern" keyword. */
+/*
+ * tomoyo_pattern_entry is a structure which is used for holding
+ * "tomoyo_pattern_list" entries.
+ * It has following fields.
+ *
+ *  (1) "list" which is linked to tomoyo_pattern_list .
+ *  (2) "pattern" is a pathname pattern which is used for converting pathnames
+ *      to pathname patterns during learning mode.
+ *  (3) "is_deleted" is a bool which is true if marked as deleted, false
+ *      otherwise.
+ */
 struct tomoyo_pattern_entry {
 	struct list_head list;
 	const struct tomoyo_path_info *pattern;
 	bool is_deleted;
 };
 
-/* Structure for "deny_rewrite" keyword. */
+/*
+ * tomoyo_no_rewrite_entry is a structure which is used for holding
+ * "deny_rewrite" entries.
+ * It has following fields.
+ *
+ *  (1) "list" which is linked to tomoyo_no_rewrite_list .
+ *  (2) "pattern" is a pathname which is by default not permitted to modify
+ *      already existing content.
+ *  (3) "is_deleted" is a bool which is true if marked as deleted, false
+ *      otherwise.
+ */
 struct tomoyo_no_rewrite_entry {
 	struct list_head list;
 	const struct tomoyo_path_info *pattern;
@@ -141,7 +170,31 @@ static int tomoyo_update_single_path_acl(const u8 type, const char *filename,
 					 struct tomoyo_domain_info *
 					 const domain, const bool is_delete);
 
-/* The list for "struct tomoyo_globally_readable_file_entry". */
+/*
+ * tomoyo_globally_readable_list is used for holding list of pathnames which
+ * are by default allowed to be open()ed for reading by any process.
+ *
+ * An entry is added by
+ *
+ * # echo 'allow_read /lib/libc-2.5.so' > \
+ *                               /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete allow_read /lib/libc-2.5.so' > \
+ *                               /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^allow_read /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, any process is allowed to
+ * open("/lib/libc-2.5.so", O_RDONLY).
+ * One exception is, if the domain which current process belongs to is marked
+ * as "ignore_global_allow_read", current process can't do so unless explicitly
+ * given "allow_read /lib/libc-2.5.so" to the domain which current process
+ * belongs to.
+ */
 static LIST_HEAD(tomoyo_globally_readable_list);
 static DECLARE_RWSEM(tomoyo_globally_readable_list_lock);
 
@@ -166,7 +219,6 @@ static int tomoyo_update_globally_readable_entry(const char *filename,
 	saved_filename = tomoyo_save_name(filename);
 	if (!saved_filename)
 		return -ENOMEM;
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_globally_readable_list_lock);
 	list_for_each_entry(ptr, &tomoyo_globally_readable_list, list) {
 		if (ptr->filename != saved_filename)
@@ -187,7 +239,6 @@ static int tomoyo_update_globally_readable_entry(const char *filename,
 	error = 0;
  out:
 	up_write(&tomoyo_globally_readable_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return error;
 }
 
@@ -249,17 +300,44 @@ bool tomoyo_read_globally_readable_policy(struct tomoyo_io_buffer *head)
 				 list);
 		if (ptr->is_deleted)
 			continue;
-		if (!tomoyo_io_printf(head, TOMOYO_KEYWORD_ALLOW_READ "%s\n",
-				      ptr->filename->name)) {
-			done = false;
+		done = tomoyo_io_printf(head, TOMOYO_KEYWORD_ALLOW_READ "%s\n",
+					ptr->filename->name);
+		if (!done)
 			break;
-		}
 	}
 	up_read(&tomoyo_globally_readable_list_lock);
 	return done;
 }
 
-/* The list for "struct tomoyo_pattern_entry". */
+/* tomoyo_pattern_list is used for holding list of pathnames which are used for
+ * converting pathnames to pathname patterns during learning mode.
+ *
+ * An entry is added by
+ *
+ * # echo 'file_pattern /proc/\$/mounts' > \
+ *                             /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete file_pattern /proc/\$/mounts' > \
+ *                             /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^file_pattern /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, if a process which belongs to a domain which is in
+ * learning mode requested open("/proc/1/mounts", O_RDONLY),
+ * "allow_read /proc/\$/mounts" is automatically added to the domain which that
+ * process belongs to.
+ *
+ * It is not a desirable behavior that we have to use /proc/\$/ instead of
+ * /proc/self/ when current process needs to access only current process's
+ * information. As of now, LSM version of TOMOYO is using __d_path() for
+ * calculating pathname. Non LSM version of TOMOYO is using its own function
+ * which pretends as if /proc/self/ is not a symlink; so that we can forbid
+ * current process from accessing other process's information.
+ */
 static LIST_HEAD(tomoyo_pattern_list);
 static DECLARE_RWSEM(tomoyo_pattern_list_lock);
 
@@ -284,7 +362,6 @@ static int tomoyo_update_file_pattern_entry(const char *pattern,
 	saved_pattern = tomoyo_save_name(pattern);
 	if (!saved_pattern)
 		return -ENOMEM;
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_pattern_list_lock);
 	list_for_each_entry(ptr, &tomoyo_pattern_list, list) {
 		if (saved_pattern != ptr->pattern)
@@ -305,7 +382,6 @@ static int tomoyo_update_file_pattern_entry(const char *pattern,
 	error = 0;
  out:
 	up_write(&tomoyo_pattern_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return error;
 }
 
@@ -373,17 +449,44 @@ bool tomoyo_read_file_pattern(struct tomoyo_io_buffer *head)
 		ptr = list_entry(pos, struct tomoyo_pattern_entry, list);
 		if (ptr->is_deleted)
 			continue;
-		if (!tomoyo_io_printf(head, TOMOYO_KEYWORD_FILE_PATTERN "%s\n",
-				      ptr->pattern->name)) {
-			done = false;
+		done = tomoyo_io_printf(head, TOMOYO_KEYWORD_FILE_PATTERN
+					"%s\n", ptr->pattern->name);
+		if (!done)
 			break;
-		}
 	}
 	up_read(&tomoyo_pattern_list_lock);
 	return done;
 }
 
-/* The list for "struct tomoyo_no_rewrite_entry". */
+/*
+ * tomoyo_no_rewrite_list is used for holding list of pathnames which are by
+ * default forbidden to modify already written content of a file.
+ *
+ * An entry is added by
+ *
+ * # echo 'deny_rewrite /var/log/messages' > \
+ *                              /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and is deleted by
+ *
+ * # echo 'delete deny_rewrite /var/log/messages' > \
+ *                              /sys/kernel/security/tomoyo/exception_policy
+ *
+ * and all entries are retrieved by
+ *
+ * # grep ^deny_rewrite /sys/kernel/security/tomoyo/exception_policy
+ *
+ * In the example above, if a process requested to rewrite /var/log/messages ,
+ * the process can't rewrite unless the domain which that process belongs to
+ * has "allow_rewrite /var/log/messages" entry.
+ *
+ * It is not a desirable behavior that we have to add "\040(deleted)" suffix
+ * when we want to allow rewriting already unlink()ed file. As of now,
+ * LSM version of TOMOYO is using __d_path() for calculating pathname.
+ * Non LSM version of TOMOYO is using its own function which doesn't append
+ * " (deleted)" suffix if the file is already unlink()ed; so that we don't
+ * need to worry whether the file is already unlink()ed or not.
+ */
 static LIST_HEAD(tomoyo_no_rewrite_list);
 static DECLARE_RWSEM(tomoyo_no_rewrite_list_lock);
 
@@ -407,7 +510,6 @@ static int tomoyo_update_no_rewrite_entry(const char *pattern,
 	saved_pattern = tomoyo_save_name(pattern);
 	if (!saved_pattern)
 		return -ENOMEM;
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_no_rewrite_list_lock);
 	list_for_each_entry(ptr, &tomoyo_no_rewrite_list, list) {
 		if (ptr->pattern != saved_pattern)
@@ -428,7 +530,6 @@ static int tomoyo_update_no_rewrite_entry(const char *pattern,
 	error = 0;
  out:
 	up_write(&tomoyo_no_rewrite_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return error;
 }
 
@@ -489,11 +590,10 @@ bool tomoyo_read_no_rewrite_policy(struct tomoyo_io_buffer *head)
 		ptr = list_entry(pos, struct tomoyo_no_rewrite_entry, list);
 		if (ptr->is_deleted)
 			continue;
-		if (!tomoyo_io_printf(head, TOMOYO_KEYWORD_DENY_REWRITE "%s\n",
-				      ptr->pattern->name)) {
-			done = false;
+		done = tomoyo_io_printf(head, TOMOYO_KEYWORD_DENY_REWRITE
+					"%s\n", ptr->pattern->name);
+		if (!done)
 			break;
-		}
 	}
 	up_read(&tomoyo_no_rewrite_list_lock);
 	return done;
@@ -745,7 +845,6 @@ static int tomoyo_update_single_path_acl(const u8 type, const char *filename,
 	saved_filename = tomoyo_save_name(filename);
 	if (!saved_filename)
 		return -ENOMEM;
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_domain_acl_info_list_lock);
 	if (is_delete)
 		goto delete;
@@ -800,7 +899,6 @@ static int tomoyo_update_single_path_acl(const u8 type, const char *filename,
 	}
  out:
 	up_write(&tomoyo_domain_acl_info_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return error;
 }
 
@@ -836,7 +934,6 @@ static int tomoyo_update_double_path_acl(const u8 type, const char *filename1,
 	saved_filename2 = tomoyo_save_name(filename2);
 	if (!saved_filename1 || !saved_filename2)
 		return -ENOMEM;
-	/***** EXCLUSIVE SECTION START *****/
 	down_write(&tomoyo_domain_acl_info_list_lock);
 	if (is_delete)
 		goto delete;
@@ -884,7 +981,6 @@ static int tomoyo_update_double_path_acl(const u8 type, const char *filename1,
 	}
  out:
 	up_write(&tomoyo_domain_acl_info_list_lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return error;
 }
 
@@ -1025,13 +1121,11 @@ int tomoyo_check_file_perm(struct tomoyo_domain_info *domain,
  *
  * @domain:   Pointer to "struct tomoyo_domain_info".
  * @filename: Check permission for "execute".
- * @tmp:      Buffer for temporary use.
  *
  * Returns 0 on success, negativevalue otherwise.
  */
 int tomoyo_check_exec_perm(struct tomoyo_domain_info *domain,
-			   const struct tomoyo_path_info *filename,
-			   struct tomoyo_page_buffer *tmp)
+			   const struct tomoyo_path_info *filename)
 {
 	const u8 mode = tomoyo_check_flags(domain, TOMOYO_MAC_FOR_FILE);
 
diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c
index 40927a84cb6e..5f2e33263371 100644
--- a/security/tomoyo/realpath.c
+++ b/security/tomoyo/realpath.c
@@ -220,7 +220,6 @@ void *tomoyo_alloc_element(const unsigned int size)
 		= roundup(size, max(sizeof(void *), sizeof(long)));
 	if (word_aligned_size > PATH_MAX)
 		return NULL;
-	/***** EXCLUSIVE SECTION START *****/
 	mutex_lock(&lock);
 	if (buf_used_len + word_aligned_size > PATH_MAX) {
 		if (!tomoyo_quota_for_elements ||
@@ -251,7 +250,6 @@ void *tomoyo_alloc_element(const unsigned int size)
 		}
 	}
 	mutex_unlock(&lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return ptr;
 }
 
@@ -267,7 +265,16 @@ static unsigned int tomoyo_quota_for_savename;
  */
 #define TOMOYO_MAX_HASH 256
 
-/* Structure for string data. */
+/*
+ * tomoyo_name_entry is a structure which is used for linking
+ * "struct tomoyo_path_info" into tomoyo_name_list .
+ *
+ * Since tomoyo_name_list manages a list of strings which are shared by
+ * multiple processes (whereas "struct tomoyo_path_info" inside
+ * "struct tomoyo_path_info_with_data" is not shared), a reference counter will
+ * be added to "struct tomoyo_name_entry" rather than "struct tomoyo_path_info"
+ * when TOMOYO starts supporting garbage collector.
+ */
 struct tomoyo_name_entry {
 	struct list_head list;
 	struct tomoyo_path_info entry;
@@ -281,10 +288,10 @@ struct tomoyo_free_memory_block_list {
 };
 
 /*
- * The list for "struct tomoyo_name_entry".
- *
- * This list is updated only inside tomoyo_save_name(), thus
- * no global mutex exists.
+ * tomoyo_name_list is used for holding string data used by TOMOYO.
+ * Since same string data is likely used for multiple times (e.g.
+ * "/lib/libc-2.5.so"), TOMOYO shares string data in the form of
+ * "const struct tomoyo_path_info *".
  */
 static struct list_head tomoyo_name_list[TOMOYO_MAX_HASH];
 
@@ -318,7 +325,6 @@ const struct tomoyo_path_info *tomoyo_save_name(const char *name)
 		return NULL;
 	}
 	hash = full_name_hash((const unsigned char *) name, len - 1);
-	/***** EXCLUSIVE SECTION START *****/
 	mutex_lock(&lock);
 	list_for_each_entry(ptr, &tomoyo_name_list[hash % TOMOYO_MAX_HASH],
 			     list) {
@@ -366,7 +372,6 @@ const struct tomoyo_path_info *tomoyo_save_name(const char *name)
 	}
  out:
 	mutex_unlock(&lock);
-	/***** EXCLUSIVE SECTION END *****/
 	return ptr ? &ptr->entry : NULL;
 }
 
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index e42be5c4f055..3194d09fe0f4 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -262,6 +262,10 @@ static int tomoyo_dentry_open(struct file *f, const struct cred *cred)
 	return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path, flags);
 }
 
+/*
+ * tomoyo_security_ops is a "struct security_operations" which is used for
+ * registering TOMOYO.
+ */
 static struct security_operations tomoyo_security_ops = {
 	.name                = "tomoyo",
 	.cred_prepare        = tomoyo_cred_prepare,
diff --git a/security/tomoyo/tomoyo.h b/security/tomoyo/tomoyo.h
index 41c6ebafb9c5..0fd588a629cf 100644
--- a/security/tomoyo/tomoyo.h
+++ b/security/tomoyo/tomoyo.h
@@ -17,13 +17,11 @@ struct path;
 struct inode;
 struct linux_binprm;
 struct pt_regs;
-struct tomoyo_page_buffer;
 
 int tomoyo_check_file_perm(struct tomoyo_domain_info *domain,
 			   const char *filename, const u8 perm);
 int tomoyo_check_exec_perm(struct tomoyo_domain_info *domain,
-			   const struct tomoyo_path_info *filename,
-			   struct tomoyo_page_buffer *buf);
+			   const struct tomoyo_path_info *filename);
 int tomoyo_check_open_permission(struct tomoyo_domain_info *domain,
 				 struct path *path, const int flag);
 int tomoyo_check_1path_perm(struct tomoyo_domain_info *domain,
@@ -90,17 +88,10 @@ static inline struct tomoyo_domain_info *tomoyo_domain(void)
 	return current_cred()->security;
 }
 
-/* Caller holds tasklist_lock spinlock. */
 static inline struct tomoyo_domain_info *tomoyo_real_domain(struct task_struct
 							    *task)
 {
-	/***** CRITICAL SECTION START *****/
-	const struct cred *cred = get_task_cred(task);
-	struct tomoyo_domain_info *domain = cred->security;
-
-	put_cred(cred);
-	return domain;
-	/***** CRITICAL SECTION END *****/
+	return task_cred_xxx(task, security);
 }
 
 #endif /* !defined(_SECURITY_TOMOYO_TOMOYO_H) */
diff --git a/sound/oss/Kconfig b/sound/oss/Kconfig
index 1ca7427c4b6d..bcf2a0698d54 100644
--- a/sound/oss/Kconfig
+++ b/sound/oss/Kconfig
@@ -561,7 +561,7 @@ endif	# SOUND_OSS
 
 config SOUND_SH_DAC_AUDIO
 	tristate "SuperH DAC audio support"
-	depends on CPU_SH3
+	depends on CPU_SH3 && HIGH_RES_TIMERS
 
 config SOUND_SH_DAC_AUDIO_CHANNEL
 	int "DAC channel"
diff --git a/sound/oss/sh_dac_audio.c b/sound/oss/sh_dac_audio.c
index 78cfb66e4c59..b2ed8757542a 100644
--- a/sound/oss/sh_dac_audio.c
+++ b/sound/oss/sh_dac_audio.c
@@ -18,47 +18,36 @@
 #include <linux/sound.h>
 #include <linux/soundcard.h>
 #include <linux/interrupt.h>
+#include <linux/hrtimer.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/irq.h>
 #include <asm/delay.h>
 #include <asm/clock.h>
-#include <asm/cpu/dac.h>
-#include <asm/cpu/timer.h>
+#include <cpu/dac.h>
 #include <asm/machvec.h>
 #include <mach/hp6xx.h>
 #include <asm/hd64461.h>
 
 #define MODNAME "sh_dac_audio"
 
-#define TMU_TOCR_INIT	0x00
-
-#define TMU1_TCR_INIT	0x0020	/* Clock/4, rising edge; interrupt on */
-#define TMU1_TSTR_INIT  0x02	/* Bit to turn on TMU1 */
-
 #define BUFFER_SIZE 48000
 
 static int rate;
 static int empty;
 static char *data_buffer, *buffer_begin, *buffer_end;
 static int in_use, device_major;
+static struct hrtimer hrtimer;
+static ktime_t wakeups_per_second;
 
 static void dac_audio_start_timer(void)
 {
-	u8 tstr;
-
-	tstr = ctrl_inb(TMU_TSTR);
-	tstr |= TMU1_TSTR_INIT;
-	ctrl_outb(tstr, TMU_TSTR);
+	hrtimer_start(&hrtimer, wakeups_per_second, HRTIMER_MODE_REL);
 }
 
 static void dac_audio_stop_timer(void)
 {
-	u8 tstr;
-
-	tstr = ctrl_inb(TMU_TSTR);
-	tstr &= ~TMU1_TSTR_INIT;
-	ctrl_outb(tstr, TMU_TSTR);
+	hrtimer_cancel(&hrtimer);
 }
 
 static void dac_audio_reset(void)
@@ -77,38 +66,30 @@ static void dac_audio_sync(void)
 static void dac_audio_start(void)
 {
 	if (mach_is_hp6xx()) {
-		u16 v = inw(HD64461_GPADR);
+		u16 v = __raw_readw(HD64461_GPADR);
 		v &= ~HD64461_GPADR_SPEAKER;
-		outw(v, HD64461_GPADR);
+		__raw_writew(v, HD64461_GPADR);
 	}
 
 	sh_dac_enable(CONFIG_SOUND_SH_DAC_AUDIO_CHANNEL);
-	ctrl_outw(TMU1_TCR_INIT, TMU1_TCR);
 }
 static void dac_audio_stop(void)
 {
 	dac_audio_stop_timer();
 
 	if (mach_is_hp6xx()) {
-		u16 v = inw(HD64461_GPADR);
+		u16 v = __raw_readw(HD64461_GPADR);
 		v |= HD64461_GPADR_SPEAKER;
-		outw(v, HD64461_GPADR);
+		__raw_writew(v, HD64461_GPADR);
 	}
 
- 	sh_dac_output(0, CONFIG_SOUND_SH_DAC_AUDIO_CHANNEL);
+	sh_dac_output(0, CONFIG_SOUND_SH_DAC_AUDIO_CHANNEL);
 	sh_dac_disable(CONFIG_SOUND_SH_DAC_AUDIO_CHANNEL);
 }
 
 static void dac_audio_set_rate(void)
 {
-	unsigned long interval;
- 	struct clk *clk;
-
- 	clk = clk_get(NULL, "module_clk");
- 	interval = (clk_get_rate(clk) / 4) / rate;
- 	clk_put(clk);
-	ctrl_outl(interval, TMU1_TCOR);
-	ctrl_outl(interval, TMU1_TCNT);
+	wakeups_per_second = ktime_set(0, 1000000000 / rate);
 }
 
 static int dac_audio_ioctl(struct inode *inode, struct file *file,
@@ -265,32 +246,26 @@ const struct file_operations dac_audio_fops = {
       .release =	dac_audio_release,
 };
 
-static irqreturn_t timer1_interrupt(int irq, void *dev)
+static enum hrtimer_restart sh_dac_audio_timer(struct hrtimer *handle)
 {
-	unsigned long timer_status;
-
-	timer_status = ctrl_inw(TMU1_TCR);
-	timer_status &= ~0x100;
-	ctrl_outw(timer_status, TMU1_TCR);
-
 	if (!empty) {
 		sh_dac_output(*buffer_begin, CONFIG_SOUND_SH_DAC_AUDIO_CHANNEL);
 		buffer_begin++;
 
 		if (buffer_begin == data_buffer + BUFFER_SIZE)
 			buffer_begin = data_buffer;
-		if (buffer_begin == buffer_end) {
+		if (buffer_begin == buffer_end)
 			empty = 1;
-			dac_audio_stop_timer();
-		}
 	}
-	return IRQ_HANDLED;
+
+	if (!empty)
+		hrtimer_start(&hrtimer, wakeups_per_second, HRTIMER_MODE_REL);
+
+	return HRTIMER_NORESTART;
 }
 
 static int __init dac_audio_init(void)
 {
-	int retval;
-
 	if ((device_major = register_sound_dsp(&dac_audio_fops, -1)) < 0) {
 		printk(KERN_ERR "Cannot register dsp device");
 		return device_major;
@@ -306,21 +281,25 @@ static int __init dac_audio_init(void)
 	rate = 8000;
 	dac_audio_set_rate();
 
-	retval =
-	    request_irq(TIMER1_IRQ, timer1_interrupt, IRQF_DISABLED, MODNAME, 0);
-	if (retval < 0) {
-		printk(KERN_ERR "sh_dac_audio: IRQ %d request failed\n",
-		       TIMER1_IRQ);
-		return retval;
-	}
+	/* Today: High Resolution Timer driven DAC playback.
+	 * The timer callback gets called once per sample. Ouch.
+	 *
+	 * Future: A much better approach would be to use the
+	 * SH7720 CMT+DMAC+DAC hardware combination like this:
+	 * - Program sample rate using CMT0 or CMT1
+	 * - Program DMAC to use CMT for timing and output to DAC
+	 * - Play sound using DMAC, let CPU sleep.
+	 * - While at it, rewrite this driver to use ALSA.
+	 */
+
+	hrtimer_init(&hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer.function = sh_dac_audio_timer;
 
 	return 0;
 }
 
 static void __exit dac_audio_exit(void)
 {
-	free_irq(TIMER1_IRQ, 0);
-
 	unregister_sound_dsp(device_major);
 	kfree((void *)data_buffer);
 }
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
new file mode 100644
index 000000000000..d69a759a1046
--- /dev/null
+++ b/tools/perf/.gitignore
@@ -0,0 +1,16 @@
+PERF-BUILD-OPTIONS
+PERF-CFLAGS
+PERF-GUI-VARS
+PERF-VERSION-FILE
+perf
+perf-help
+perf-record
+perf-report
+perf-stat
+perf-top
+perf*.1
+perf*.xml
+common-cmds.h
+tags
+TAGS
+cscope*
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
new file mode 100644
index 000000000000..5457192e1b41
--- /dev/null
+++ b/tools/perf/Documentation/Makefile
@@ -0,0 +1,300 @@
+MAN1_TXT= \
+	$(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \
+		$(wildcard perf-*.txt)) \
+	perf.txt
+MAN5_TXT=
+MAN7_TXT=
+
+MAN_TXT = $(MAN1_TXT) $(MAN5_TXT) $(MAN7_TXT)
+MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT))
+MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT))
+
+DOC_HTML=$(MAN_HTML)
+
+ARTICLES =
+# with their own formatting rules.
+SP_ARTICLES =
+API_DOCS = $(patsubst %.txt,%,$(filter-out technical/api-index-skel.txt technical/api-index.txt, $(wildcard technical/api-*.txt)))
+SP_ARTICLES += $(API_DOCS)
+SP_ARTICLES += technical/api-index
+
+DOC_HTML += $(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES))
+
+DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
+DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
+DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
+
+prefix?=$(HOME)
+bindir?=$(prefix)/bin
+htmldir?=$(prefix)/share/doc/perf-doc
+pdfdir?=$(prefix)/share/doc/perf-doc
+mandir?=$(prefix)/share/man
+man1dir=$(mandir)/man1
+man5dir=$(mandir)/man5
+man7dir=$(mandir)/man7
+# DESTDIR=
+
+ASCIIDOC=asciidoc
+ASCIIDOC_EXTRA =
+MANPAGE_XSL = manpage-normal.xsl
+XMLTO_EXTRA =
+INSTALL?=install
+RM ?= rm -f
+DOC_REF = origin/man
+HTML_REF = origin/html
+
+infodir?=$(prefix)/share/info
+MAKEINFO=makeinfo
+INSTALL_INFO=install-info
+DOCBOOK2X_TEXI=docbook2x-texi
+DBLATEX=dblatex
+ifndef PERL_PATH
+	PERL_PATH = /usr/bin/perl
+endif
+
+-include ../config.mak.autogen
+-include ../config.mak
+
+#
+# For asciidoc ...
+#	-7.1.2,	no extra settings are needed.
+#	8.0-,	set ASCIIDOC8.
+#
+
+#
+# For docbook-xsl ...
+#	-1.68.1,	set ASCIIDOC_NO_ROFF? (based on changelog from 1.73.0)
+#	1.69.0,		no extra settings are needed?
+#	1.69.1-1.71.0,	set DOCBOOK_SUPPRESS_SP?
+#	1.71.1,		no extra settings are needed?
+#	1.72.0,		set DOCBOOK_XSL_172.
+#	1.73.0-,	set ASCIIDOC_NO_ROFF
+#
+
+#
+# If you had been using DOCBOOK_XSL_172 in an attempt to get rid
+# of 'the ".ft C" problem' in your generated manpages, and you
+# instead ended up with weird characters around callouts, try
+# using ASCIIDOC_NO_ROFF instead (it works fine with ASCIIDOC8).
+#
+
+ifdef ASCIIDOC8
+ASCIIDOC_EXTRA += -a asciidoc7compatible
+endif
+ifdef DOCBOOK_XSL_172
+ASCIIDOC_EXTRA += -a perf-asciidoc-no-roff
+MANPAGE_XSL = manpage-1.72.xsl
+else
+	ifdef ASCIIDOC_NO_ROFF
+	# docbook-xsl after 1.72 needs the regular XSL, but will not
+	# pass-thru raw roff codes from asciidoc.conf, so turn them off.
+	ASCIIDOC_EXTRA += -a perf-asciidoc-no-roff
+	endif
+endif
+ifdef MAN_BOLD_LITERAL
+XMLTO_EXTRA += -m manpage-bold-literal.xsl
+endif
+ifdef DOCBOOK_SUPPRESS_SP
+XMLTO_EXTRA += -m manpage-suppress-sp.xsl
+endif
+
+SHELL_PATH ?= $(SHELL)
+# Shell quote;
+SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
+
+#
+# Please note that there is a minor bug in asciidoc.
+# The version after 6.0.3 _will_ include the patch found here:
+#   http://marc.theaimsgroup.com/?l=perf&m=111558757202243&w=2
+#
+# Until that version is released you may have to apply the patch
+# yourself - yes, all 6 characters of it!
+#
+
+QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
+QUIET_SUBDIR1  =
+
+ifneq ($(findstring $(MAKEFLAGS),w),w)
+PRINT_DIR = --no-print-directory
+else # "make -w"
+NO_SUBDIR = :
+endif
+
+ifneq ($(findstring $(MAKEFLAGS),s),s)
+ifndef V
+	QUIET_ASCIIDOC	= @echo '   ' ASCIIDOC $@;
+	QUIET_XMLTO	= @echo '   ' XMLTO $@;
+	QUIET_DB2TEXI	= @echo '   ' DB2TEXI $@;
+	QUIET_MAKEINFO	= @echo '   ' MAKEINFO $@;
+	QUIET_DBLATEX	= @echo '   ' DBLATEX $@;
+	QUIET_XSLTPROC	= @echo '   ' XSLTPROC $@;
+	QUIET_GEN	= @echo '   ' GEN $@;
+	QUIET_STDERR	= 2> /dev/null
+	QUIET_SUBDIR0	= +@subdir=
+	QUIET_SUBDIR1	= ;$(NO_SUBDIR) echo '   ' SUBDIR $$subdir; \
+			  $(MAKE) $(PRINT_DIR) -C $$subdir
+	export V
+endif
+endif
+
+all: html man
+
+html: $(DOC_HTML)
+
+$(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7): asciidoc.conf
+
+man: man1 man5 man7
+man1: $(DOC_MAN1)
+man5: $(DOC_MAN5)
+man7: $(DOC_MAN7)
+
+info: perf.info perfman.info
+
+pdf: user-manual.pdf
+
+install: install-man
+
+install-man: man
+	$(INSTALL) -d -m 755 $(DESTDIR)$(man1dir)
+#	$(INSTALL) -d -m 755 $(DESTDIR)$(man5dir)
+#	$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
+	$(INSTALL) -m 644 $(DOC_MAN1) $(DESTDIR)$(man1dir)
+#	$(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir)
+#	$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+
+install-info: info
+	$(INSTALL) -d -m 755 $(DESTDIR)$(infodir)
+	$(INSTALL) -m 644 perf.info perfman.info $(DESTDIR)$(infodir)
+	if test -r $(DESTDIR)$(infodir)/dir; then \
+	  $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\
+	  $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\
+	else \
+	  echo "No directory found in $(DESTDIR)$(infodir)" >&2 ; \
+	fi
+
+install-pdf: pdf
+	$(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
+	$(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir)
+
+install-html: html
+	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
+
+../PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
+	$(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) PERF-VERSION-FILE
+
+-include ../PERF-VERSION-FILE
+
+#
+# Determine "include::" file references in asciidoc files.
+#
+doc.dep : $(wildcard *.txt) build-docdep.perl
+	$(QUIET_GEN)$(RM) $@+ $@ && \
+	$(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \
+	mv $@+ $@
+
+-include doc.dep
+
+cmds_txt = cmds-ancillaryinterrogators.txt \
+	cmds-ancillarymanipulators.txt \
+	cmds-mainporcelain.txt \
+	cmds-plumbinginterrogators.txt \
+	cmds-plumbingmanipulators.txt \
+	cmds-synchingrepositories.txt \
+	cmds-synchelpers.txt \
+	cmds-purehelpers.txt \
+	cmds-foreignscminterface.txt
+
+$(cmds_txt): cmd-list.made
+
+cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT)
+	$(QUIET_GEN)$(RM) $@ && \
+	$(PERL_PATH) ./cmd-list.perl ../command-list.txt $(QUIET_STDERR) && \
+	date >$@
+
+clean:
+	$(RM) *.xml *.xml+ *.html *.html+ *.1 *.5 *.7
+	$(RM) *.texi *.texi+ *.texi++ perf.info perfman.info
+	$(RM) howto-index.txt howto/*.html doc.dep
+	$(RM) technical/api-*.html technical/api-index.txt
+	$(RM) $(cmds_txt) *.made
+
+$(MAN_HTML): %.html : %.txt
+	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+	$(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \
+		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+	mv $@+ $@
+
+%.1 %.5 %.7 : %.xml
+	$(QUIET_XMLTO)$(RM) $@ && \
+	xmlto -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
+
+%.xml : %.txt
+	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+	$(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \
+		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+	mv $@+ $@
+
+XSLT = docbook.xsl
+XSLTOPTS = --xinclude --stringparam html.stylesheet docbook-xsl.css
+
+user-manual.html: user-manual.xml
+	$(QUIET_XSLTPROC)xsltproc $(XSLTOPTS) -o $@ $(XSLT) $<
+
+perf.info: user-manual.texi
+	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ user-manual.texi
+
+user-manual.texi: user-manual.xml
+	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
+	$(DOCBOOK2X_TEXI) user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \
+	$(PERL_PATH) fix-texi.perl <$@++ >$@+ && \
+	rm $@++ && \
+	mv $@+ $@
+
+user-manual.pdf: user-manual.xml
+	$(QUIET_DBLATEX)$(RM) $@+ $@ && \
+	$(DBLATEX) -o $@+ -p /etc/asciidoc/dblatex/asciidoc-dblatex.xsl -s /etc/asciidoc/dblatex/asciidoc-dblatex.sty $< && \
+	mv $@+ $@
+
+perfman.texi: $(MAN_XML) cat-texi.perl
+	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
+	($(foreach xml,$(MAN_XML),$(DOCBOOK2X_TEXI) --encoding=UTF-8 \
+		--to-stdout $(xml) &&) true) > $@++ && \
+	$(PERL_PATH) cat-texi.perl $@ <$@++ >$@+ && \
+	rm $@++ && \
+	mv $@+ $@
+
+perfman.info: perfman.texi
+	$(QUIET_MAKEINFO)$(MAKEINFO) --no-split --no-validate $*.texi
+
+$(patsubst %.txt,%.texi,$(MAN_TXT)): %.texi : %.xml
+	$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
+	$(DOCBOOK2X_TEXI) --to-stdout $*.xml >$@+ && \
+	mv $@+ $@
+
+howto-index.txt: howto-index.sh $(wildcard howto/*.txt)
+	$(QUIET_GEN)$(RM) $@+ $@ && \
+	'$(SHELL_PATH_SQ)' ./howto-index.sh $(wildcard howto/*.txt) >$@+ && \
+	mv $@+ $@
+
+$(patsubst %,%.html,$(ARTICLES)) : %.html : %.txt
+	$(QUIET_ASCIIDOC)$(ASCIIDOC) -b xhtml11 $*.txt
+
+WEBDOC_DEST = /pub/software/tools/perf/docs
+
+$(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt
+	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+	sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \
+	mv $@+ $@
+
+install-webdoc : html
+	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
+
+quick-install: quick-install-man
+
+quick-install-man:
+	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
+
+quick-install-html:
+	'$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
+
+.PHONY: .FORCE-PERF-VERSION-FILE
diff --git a/tools/perf/Documentation/asciidoc.conf b/tools/perf/Documentation/asciidoc.conf
new file mode 100644
index 000000000000..356b23a40339
--- /dev/null
+++ b/tools/perf/Documentation/asciidoc.conf
@@ -0,0 +1,91 @@
+## linkperf: macro
+#
+# Usage: linkperf:command[manpage-section]
+#
+# Note, {0} is the manpage section, while {target} is the command.
+#
+# Show PERF link as: <command>(<section>); if section is defined, else just show
+# the command.
+
+[macros]
+(?su)[\\]?(?P<name>linkperf):(?P<target>\S*?)\[(?P<attrlist>.*?)\]=
+
+[attributes]
+asterisk=&#42;
+plus=&#43;
+caret=&#94;
+startsb=&#91;
+endsb=&#93;
+tilde=&#126;
+
+ifdef::backend-docbook[]
+[linkperf-inlinemacro]
+{0%{target}}
+{0#<citerefentry>}
+{0#<refentrytitle>{target}</refentrytitle><manvolnum>{0}</manvolnum>}
+{0#</citerefentry>}
+endif::backend-docbook[]
+
+ifdef::backend-docbook[]
+ifndef::perf-asciidoc-no-roff[]
+# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this.
+# v1.72 breaks with this because it replaces dots not in roff requests.
+[listingblock]
+<example><title>{title}</title>
+<literallayout>
+ifdef::doctype-manpage[]
+&#10;.ft C&#10;
+endif::doctype-manpage[]
+|
+ifdef::doctype-manpage[]
+&#10;.ft&#10;
+endif::doctype-manpage[]
+</literallayout>
+{title#}</example>
+endif::perf-asciidoc-no-roff[]
+
+ifdef::perf-asciidoc-no-roff[]
+ifdef::doctype-manpage[]
+# The following two small workarounds insert a simple paragraph after screen
+[listingblock]
+<example><title>{title}</title>
+<literallayout>
+|
+</literallayout><simpara></simpara>
+{title#}</example>
+
+[verseblock]
+<formalpara{id? id="{id}"}><title>{title}</title><para>
+{title%}<literallayout{id? id="{id}"}>
+{title#}<literallayout>
+|
+</literallayout>
+{title#}</para></formalpara>
+{title%}<simpara></simpara>
+endif::doctype-manpage[]
+endif::perf-asciidoc-no-roff[]
+endif::backend-docbook[]
+
+ifdef::doctype-manpage[]
+ifdef::backend-docbook[]
+[header]
+template::[header-declarations]
+<refentry>
+<refmeta>
+<refentrytitle>{mantitle}</refentrytitle>
+<manvolnum>{manvolnum}</manvolnum>
+<refmiscinfo class="source">perf</refmiscinfo>
+<refmiscinfo class="version">{perf_version}</refmiscinfo>
+<refmiscinfo class="manual">perf Manual</refmiscinfo>
+</refmeta>
+<refnamediv>
+  <refname>{manname}</refname>
+  <refpurpose>{manpurpose}</refpurpose>
+</refnamediv>
+endif::backend-docbook[]
+endif::doctype-manpage[]
+
+ifdef::backend-xhtml11[]
+[linkperf-inlinemacro]
+<a href="{target}.html">{target}{0?({0})}</a>
+endif::backend-xhtml11[]
diff --git a/tools/perf/Documentation/manpage-1.72.xsl b/tools/perf/Documentation/manpage-1.72.xsl
new file mode 100644
index 000000000000..b4d315cb8c47
--- /dev/null
+++ b/tools/perf/Documentation/manpage-1.72.xsl
@@ -0,0 +1,14 @@
+<!-- manpage-1.72.xsl:
+     special settings for manpages rendered from asciidoc+docbook
+     handles peculiarities in docbook-xsl 1.72.0 -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<xsl:import href="manpage-base.xsl"/>
+
+<!-- these are the special values for the roff control characters
+     needed for docbook-xsl 1.72.0 -->
+<xsl:param name="git.docbook.backslash">&#x2593;</xsl:param>
+<xsl:param name="git.docbook.dot"      >&#x2302;</xsl:param>
+
+</xsl:stylesheet>
diff --git a/tools/perf/Documentation/manpage-base.xsl b/tools/perf/Documentation/manpage-base.xsl
new file mode 100644
index 000000000000..a264fa616093
--- /dev/null
+++ b/tools/perf/Documentation/manpage-base.xsl
@@ -0,0 +1,35 @@
+<!-- manpage-base.xsl:
+     special formatting for manpages rendered from asciidoc+docbook -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<!-- these params silence some output from xmlto -->
+<xsl:param name="man.output.quietly" select="1"/>
+<xsl:param name="refentry.meta.get.quietly" select="1"/>
+
+<!-- convert asciidoc callouts to man page format;
+     git.docbook.backslash and git.docbook.dot params
+     must be supplied by another XSL file or other means -->
+<xsl:template match="co">
+	<xsl:value-of select="concat(
+			      $git.docbook.backslash,'fB(',
+			      substring-after(@id,'-'),')',
+			      $git.docbook.backslash,'fR')"/>
+</xsl:template>
+<xsl:template match="calloutlist">
+	<xsl:value-of select="$git.docbook.dot"/>
+	<xsl:text>sp&#10;</xsl:text>
+	<xsl:apply-templates/>
+	<xsl:text>&#10;</xsl:text>
+</xsl:template>
+<xsl:template match="callout">
+	<xsl:value-of select="concat(
+			      $git.docbook.backslash,'fB',
+			      substring-after(@arearefs,'-'),
+			      '. ',$git.docbook.backslash,'fR')"/>
+	<xsl:apply-templates/>
+	<xsl:value-of select="$git.docbook.dot"/>
+	<xsl:text>br&#10;</xsl:text>
+</xsl:template>
+
+</xsl:stylesheet>
diff --git a/tools/perf/Documentation/manpage-bold-literal.xsl b/tools/perf/Documentation/manpage-bold-literal.xsl
new file mode 100644
index 000000000000..608eb5df6281
--- /dev/null
+++ b/tools/perf/Documentation/manpage-bold-literal.xsl
@@ -0,0 +1,17 @@
+<!-- manpage-bold-literal.xsl:
+     special formatting for manpages rendered from asciidoc+docbook -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<!-- render literal text as bold (instead of plain or monospace);
+     this makes literal text easier to distinguish in manpages
+     viewed on a tty -->
+<xsl:template match="literal">
+	<xsl:value-of select="$git.docbook.backslash"/>
+	<xsl:text>fB</xsl:text>
+	<xsl:apply-templates/>
+	<xsl:value-of select="$git.docbook.backslash"/>
+	<xsl:text>fR</xsl:text>
+</xsl:template>
+
+</xsl:stylesheet>
diff --git a/tools/perf/Documentation/manpage-normal.xsl b/tools/perf/Documentation/manpage-normal.xsl
new file mode 100644
index 000000000000..a48f5b11f3dc
--- /dev/null
+++ b/tools/perf/Documentation/manpage-normal.xsl
@@ -0,0 +1,13 @@
+<!-- manpage-normal.xsl:
+     special settings for manpages rendered from asciidoc+docbook
+     handles anything we want to keep away from docbook-xsl 1.72.0 -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<xsl:import href="manpage-base.xsl"/>
+
+<!-- these are the normal values for the roff control characters -->
+<xsl:param name="git.docbook.backslash">\</xsl:param>
+<xsl:param name="git.docbook.dot"	>.</xsl:param>
+
+</xsl:stylesheet>
diff --git a/tools/perf/Documentation/manpage-suppress-sp.xsl b/tools/perf/Documentation/manpage-suppress-sp.xsl
new file mode 100644
index 000000000000..a63c7632a87d
--- /dev/null
+++ b/tools/perf/Documentation/manpage-suppress-sp.xsl
@@ -0,0 +1,21 @@
+<!-- manpage-suppress-sp.xsl:
+     special settings for manpages rendered from asciidoc+docbook
+     handles erroneous, inline .sp in manpage output of some
+     versions of docbook-xsl -->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+		version="1.0">
+
+<!-- attempt to work around spurious .sp at the tail of the line
+     that some versions of docbook stylesheets seem to add -->
+<xsl:template match="simpara">
+  <xsl:variable name="content">
+    <xsl:apply-templates/>
+  </xsl:variable>
+  <xsl:value-of select="normalize-space($content)"/>
+  <xsl:if test="not(ancestor::authorblurb) and
+                not(ancestor::personblurb)">
+    <xsl:text>&#10;&#10;</xsl:text>
+  </xsl:if>
+</xsl:template>
+
+</xsl:stylesheet>
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
new file mode 100644
index 000000000000..c9dcade06831
--- /dev/null
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -0,0 +1,29 @@
+perf-annotate(1)
+==============
+
+NAME
+----
+perf-annotate - Read perf.data (created by perf record) and display annotated code
+
+SYNOPSIS
+--------
+[verse]
+'perf annotate' [-i <file> | --input=file] symbol_name
+
+DESCRIPTION
+-----------
+This command reads the input file and displays an annotated version of the
+code. If the object file has debug symbols then the source code will be
+displayed alongside assembly code.
+
+If there is no debug info in the object, then annotated assembly is displayed.
+
+OPTIONS
+-------
+-i::
+--input=::
+        Input file name. (default: perf.data)
+
+SEE ALSO
+--------
+linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-help.txt b/tools/perf/Documentation/perf-help.txt
new file mode 100644
index 000000000000..514391818d1f
--- /dev/null
+++ b/tools/perf/Documentation/perf-help.txt
@@ -0,0 +1,38 @@
+perf-help(1)
+============
+
+NAME
+----
+perf-help - display help information about perf
+
+SYNOPSIS
+--------
+'perf help' [-a|--all] [COMMAND]
+
+DESCRIPTION
+-----------
+
+With no options and no COMMAND given, the synopsis of the 'perf'
+command and a list of the most commonly used perf commands are printed
+on the standard output.
+
+If the option '--all' or '-a' is given, then all available commands are
+printed on the standard output.
+
+If a perf command is named, a manual page for that command is brought
+up. The 'man' program is used by default for this purpose, but this
+can be overridden by other options or configuration variables.
+
+Note that `perf --help ...` is identical to `perf help ...` because the
+former is internally converted into the latter.
+
+OPTIONS
+-------
+-a::
+--all::
+	Prints all the available commands on the standard output. This
+	option supersedes any other option.
+
+PERF
+----
+Part of the linkperf:perf[1] suite
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
new file mode 100644
index 000000000000..8290b9422668
--- /dev/null
+++ b/tools/perf/Documentation/perf-list.txt
@@ -0,0 +1,25 @@
+perf-list(1)
+============
+
+NAME
+----
+perf-list - List all symbolic event types
+
+SYNOPSIS
+--------
+[verse]
+'perf list'
+
+DESCRIPTION
+-----------
+This command displays the symbolic event types which can be selected in the
+various perf commands with the -e option.
+
+OPTIONS
+-------
+None
+
+SEE ALSO
+--------
+linkperf:perf-stat[1], linkperf:perf-top[1],
+linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
new file mode 100644
index 000000000000..1dbc1eeb4c01
--- /dev/null
+++ b/tools/perf/Documentation/perf-record.txt
@@ -0,0 +1,42 @@
+perf-record(1)
+==============
+
+NAME
+----
+perf-record - Run a command and record its profile into perf.data
+
+SYNOPSIS
+--------
+[verse]
+'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
+'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>]
+
+DESCRIPTION
+-----------
+This command runs a command and gathers a performance counter profile
+from it, into perf.data - without displaying anything.
+
+This file can then be inspected later on, using 'perf report'.
+
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+-e::
+--event=::
+	Select the PMU event. Selection can be a symbolic event name
+	(use 'perf list' to list all events) or a raw PMU
+	event (eventsel+umask) in the form of rNNN where NNN is a
+	 hexadecimal event descriptor.
+
+-a::
+        system-wide collection
+
+-l::
+        scale counter values
+
+SEE ALSO
+--------
+linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
new file mode 100644
index 000000000000..52d3fc6846a9
--- /dev/null
+++ b/tools/perf/Documentation/perf-report.txt
@@ -0,0 +1,26 @@
+perf-report(1)
+==============
+
+NAME
+----
+perf-report - Read perf.data (created by perf record) and display the profile
+
+SYNOPSIS
+--------
+[verse]
+'perf report' [-i <file> | --input=file]
+
+DESCRIPTION
+-----------
+This command displays the performance counter profile information recorded
+via perf report.
+
+OPTIONS
+-------
+-i::
+--input=::
+        Input file name. (default: perf.data)
+
+SEE ALSO
+--------
+linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
new file mode 100644
index 000000000000..c368a72721d7
--- /dev/null
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -0,0 +1,66 @@
+perf-stat(1)
+============
+
+NAME
+----
+perf-stat - Run a command and gather performance counter statistics
+
+SYNOPSIS
+--------
+[verse]
+'perf stat' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
+'perf stat' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>]
+
+DESCRIPTION
+-----------
+This command runs a command and gathers performance counter statistics
+from it.
+
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+
+-e::
+--event=::
+	Select the PMU event. Selection can be a symbolic event name
+	(use 'perf list' to list all events) or a raw PMU
+	event (eventsel+umask) in the form of rNNN where NNN is a
+	 hexadecimal event descriptor.
+
+-i::
+--inherit::
+        child tasks inherit counters
+-p::
+--pid=<pid>::
+        stat events on existing pid
+
+-a::
+        system-wide collection
+
+-l::
+        scale counter values
+
+EXAMPLES
+--------
+
+$ perf stat -- make -j
+
+ Performance counter stats for 'make -j':
+
+    8117.370256  task clock ticks     #      11.281 CPU utilization factor
+            678  context switches     #       0.000 M/sec
+            133  CPU migrations       #       0.000 M/sec
+         235724  pagefaults           #       0.029 M/sec
+    24821162526  CPU cycles           #    3057.784 M/sec
+    18687303457  instructions         #    2302.138 M/sec
+      172158895  cache references     #      21.209 M/sec
+       27075259  cache misses         #       3.335 M/sec
+
+ Wall-clock time elapsed:   719.554352 msecs
+
+SEE ALSO
+--------
+linkperf:perf-top[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
new file mode 100644
index 000000000000..539d01289725
--- /dev/null
+++ b/tools/perf/Documentation/perf-top.txt
@@ -0,0 +1,39 @@
+perf-top(1)
+===========
+
+NAME
+----
+perf-top - Run a command and profile it
+
+SYNOPSIS
+--------
+[verse]
+'perf top' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
+
+DESCRIPTION
+-----------
+This command runs a command and gathers a performance counter profile
+from it.
+
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+-e::
+--event=::
+	Select the PMU event. Selection can be a symbolic event name
+	(use 'perf list' to list all events) or a raw PMU
+	event (eventsel+umask) in the form of rNNN where NNN is a
+	 hexadecimal event descriptor.
+
+-a::
+        system-wide collection
+
+-l::
+        scale counter values
+
+SEE ALSO
+--------
+linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
new file mode 100644
index 000000000000..69c832557199
--- /dev/null
+++ b/tools/perf/Documentation/perf.txt
@@ -0,0 +1,24 @@
+perf(1)
+=======
+
+NAME
+----
+perf - Performance analysis tools for Linux
+
+SYNOPSIS
+--------
+[verse]
+'perf' [--version] [--help] COMMAND [ARGS]
+
+DESCRIPTION
+-----------
+Performance counters for Linux are are a new kernel-based subsystem
+that provide a framework for all things performance analysis. It
+covers hardware level (CPU/PMU, Performance Monitoring Unit) features
+and software features (software counters, tracepoints) as well.
+
+SEE ALSO
+--------
+linkperf:perf-stat[1], linkperf:perf-top[1],
+linkperf:perf-record[1], linkperf:perf-report[1],
+linkperf:perf-list[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
new file mode 100644
index 000000000000..0cbd5d6874ec
--- /dev/null
+++ b/tools/perf/Makefile
@@ -0,0 +1,929 @@
+# The default target of this Makefile is...
+all::
+
+# Define V=1 to have a more verbose compile.
+#
+# Define SNPRINTF_RETURNS_BOGUS if your are on a system which snprintf()
+# or vsnprintf() return -1 instead of number of characters which would
+# have been written to the final string if enough space had been available.
+#
+# Define FREAD_READS_DIRECTORIES if your are on a system which succeeds
+# when attempting to read from an fopen'ed directory.
+#
+# Define NO_OPENSSL environment variable if you do not have OpenSSL.
+# This also implies MOZILLA_SHA1.
+#
+# Define CURLDIR=/foo/bar if your curl header and library files are in
+# /foo/bar/include and /foo/bar/lib directories.
+#
+# Define EXPATDIR=/foo/bar if your expat header and library files are in
+# /foo/bar/include and /foo/bar/lib directories.
+#
+# Define NO_D_INO_IN_DIRENT if you don't have d_ino in your struct dirent.
+#
+# Define NO_D_TYPE_IN_DIRENT if your platform defines DT_UNKNOWN but lacks
+# d_type in struct dirent (latest Cygwin -- will be fixed soonish).
+#
+# Define NO_C99_FORMAT if your formatted IO functions (printf/scanf et.al.)
+# do not support the 'size specifiers' introduced by C99, namely ll, hh,
+# j, z, t. (representing long long int, char, intmax_t, size_t, ptrdiff_t).
+# some C compilers supported these specifiers prior to C99 as an extension.
+#
+# Define NO_STRCASESTR if you don't have strcasestr.
+#
+# Define NO_MEMMEM if you don't have memmem.
+#
+# Define NO_STRTOUMAX if you don't have strtoumax in the C library.
+# If your compiler also does not support long long or does not have
+# strtoull, define NO_STRTOULL.
+#
+# Define NO_SETENV if you don't have setenv in the C library.
+#
+# Define NO_UNSETENV if you don't have unsetenv in the C library.
+#
+# Define NO_MKDTEMP if you don't have mkdtemp in the C library.
+#
+# Define NO_SYS_SELECT_H if you don't have sys/select.h.
+#
+# Define NO_SYMLINK_HEAD if you never want .perf/HEAD to be a symbolic link.
+# Enable it on Windows.  By default, symrefs are still used.
+#
+# Define NO_SVN_TESTS if you want to skip time-consuming SVN interoperability
+# tests.  These tests take up a significant amount of the total test time
+# but are not needed unless you plan to talk to SVN repos.
+#
+# Define NO_FINK if you are building on Darwin/Mac OS X, have Fink
+# installed in /sw, but don't want PERF to link against any libraries
+# installed there.  If defined you may specify your own (or Fink's)
+# include directories and library directories by defining CFLAGS
+# and LDFLAGS appropriately.
+#
+# Define NO_DARWIN_PORTS if you are building on Darwin/Mac OS X,
+# have DarwinPorts installed in /opt/local, but don't want PERF to
+# link against any libraries installed there.  If defined you may
+# specify your own (or DarwinPort's) include directories and
+# library directories by defining CFLAGS and LDFLAGS appropriately.
+#
+# Define PPC_SHA1 environment variable when running make to make use of
+# a bundled SHA1 routine optimized for PowerPC.
+#
+# Define ARM_SHA1 environment variable when running make to make use of
+# a bundled SHA1 routine optimized for ARM.
+#
+# Define MOZILLA_SHA1 environment variable when running make to make use of
+# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast
+# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default
+# choice) has very fast version optimized for i586.
+#
+# Define NEEDS_SSL_WITH_CRYPTO if you need -lcrypto with -lssl (Darwin).
+#
+# Define NEEDS_LIBICONV if linking with libc is not enough (Darwin).
+#
+# Define NEEDS_SOCKET if linking with libc is not enough (SunOS,
+# Patrick Mauritz).
+#
+# Define NO_MMAP if you want to avoid mmap.
+#
+# Define NO_PTHREADS if you do not have or do not want to use Pthreads.
+#
+# Define NO_PREAD if you have a problem with pread() system call (e.g.
+# cygwin.dll before v1.5.22).
+#
+# Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is
+# generally faster on your platform than accessing the working directory.
+#
+# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support
+# the executable mode bit, but doesn't really do so.
+#
+# Define NO_IPV6 if you lack IPv6 support and getaddrinfo().
+#
+# Define NO_SOCKADDR_STORAGE if your platform does not have struct
+# sockaddr_storage.
+#
+# Define NO_ICONV if your libc does not properly support iconv.
+#
+# Define OLD_ICONV if your library has an old iconv(), where the second
+# (input buffer pointer) parameter is declared with type (const char **).
+#
+# Define NO_DEFLATE_BOUND if your zlib does not have deflateBound.
+#
+# Define NO_R_TO_GCC_LINKER if your gcc does not like "-R/path/lib"
+# that tells runtime paths to dynamic libraries;
+# "-Wl,-rpath=/path/lib" is used instead.
+#
+# Define USE_NSEC below if you want perf to care about sub-second file mtimes
+# and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and
+# it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely
+# randomly break unless your underlying filesystem supports those sub-second
+# times (my ext3 doesn't).
+#
+# Define USE_ST_TIMESPEC if your "struct stat" uses "st_ctimespec" instead of
+# "st_ctim"
+#
+# Define NO_NSEC if your "struct stat" does not have "st_ctim.tv_nsec"
+# available.  This automatically turns USE_NSEC off.
+#
+# Define USE_STDEV below if you want perf to care about the underlying device
+# change being considered an inode change from the update-index perspective.
+#
+# Define NO_ST_BLOCKS_IN_STRUCT_STAT if your platform does not have st_blocks
+# field that counts the on-disk footprint in 512-byte blocks.
+#
+# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
+#
+# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
+#
+# Define NO_PERL_MAKEMAKER if you cannot use Makefiles generated by perl's
+# MakeMaker (e.g. using ActiveState under Cygwin).
+#
+# Define NO_PERL if you do not want Perl scripts or libraries at all.
+#
+# Define INTERNAL_QSORT to use Git's implementation of qsort(), which
+# is a simplified version of the merge sort used in glibc. This is
+# recommended if Git triggers O(n^2) behavior in your platform's qsort().
+#
+# Define NO_EXTERNAL_GREP if you don't want "perf grep" to ever call
+# your external grep (e.g., if your system lacks grep, if its grep is
+# broken, or spawning external process is slower than built-in grep perf has).
+
+PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
+	@$(SHELL_PATH) util/PERF-VERSION-GEN
+-include PERF-VERSION-FILE
+
+uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not')
+uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not')
+uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not')
+uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not')
+uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not')
+uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not')
+
+# CFLAGS and LDFLAGS are for the users to override from the command line.
+
+CFLAGS = -ggdb3 -Wall -Werror -Wstrict-prototypes -Wmissing-declarations -Wmissing-prototypes -std=gnu99 -Wdeclaration-after-statement -O6
+LDFLAGS = -lpthread -lrt -lelf
+ALL_CFLAGS = $(CFLAGS)
+ALL_LDFLAGS = $(LDFLAGS)
+STRIP ?= strip
+
+# Among the variables below, these:
+#   perfexecdir
+#   template_dir
+#   mandir
+#   infodir
+#   htmldir
+#   ETC_PERFCONFIG (but not sysconfdir)
+# can be specified as a relative path some/where/else;
+# this is interpreted as relative to $(prefix) and "perf" at
+# runtime figures out where they are based on the path to the executable.
+# This can help installing the suite in a relocatable way.
+
+prefix = $(HOME)
+bindir_relative = bin
+bindir = $(prefix)/$(bindir_relative)
+mandir = share/man
+infodir = share/info
+perfexecdir = libexec/perf-core
+sharedir = $(prefix)/share
+template_dir = share/perf-core/templates
+htmldir = share/doc/perf-doc
+ifeq ($(prefix),/usr)
+sysconfdir = /etc
+ETC_PERFCONFIG = $(sysconfdir)/perfconfig
+else
+sysconfdir = $(prefix)/etc
+ETC_PERFCONFIG = etc/perfconfig
+endif
+lib = lib
+# DESTDIR=
+
+export prefix bindir sharedir sysconfdir
+
+CC = gcc
+AR = ar
+RM = rm -f
+TAR = tar
+FIND = find
+INSTALL = install
+RPMBUILD = rpmbuild
+PTHREAD_LIBS = -lpthread
+
+# sparse is architecture-neutral, which means that we need to tell it
+# explicitly what architecture to check for. Fix this up for yours..
+SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
+
+
+
+### --- END CONFIGURATION SECTION ---
+
+# Those must not be GNU-specific; they are shared with perl/ which may
+# be built by a different compiler. (Note that this is an artifact now
+# but it still might be nice to keep that distinction.)
+BASIC_CFLAGS =
+BASIC_LDFLAGS =
+
+# Guard against environment variables
+BUILTIN_OBJS =
+BUILT_INS =
+COMPAT_CFLAGS =
+COMPAT_OBJS =
+LIB_H =
+LIB_OBJS =
+SCRIPT_PERL =
+SCRIPT_SH =
+TEST_PROGRAMS =
+
+#
+# No scripts right now:
+#
+
+# SCRIPT_SH += perf-am.sh
+
+#
+# No Perl scripts right now:
+#
+
+# SCRIPT_PERL += perf-add--interactive.perl
+
+SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \
+	  $(patsubst %.perl,%,$(SCRIPT_PERL))
+
+# Empty...
+EXTRA_PROGRAMS =
+
+# ... and all the rest that could be moved out of bindir to perfexecdir
+PROGRAMS += $(EXTRA_PROGRAMS)
+
+#
+# Single 'perf' binary right now:
+#
+PROGRAMS += perf
+
+# List built-in command $C whose implementation cmd_$C() is not in
+# builtin-$C.o but is linked in as part of some other command.
+#
+# None right now:
+#
+# BUILT_INS += perf-init $X
+
+# what 'all' will build and 'install' will install, in perfexecdir
+ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
+
+# what 'all' will build but not install in perfexecdir
+OTHER_PROGRAMS = perf$X
+
+# Set paths to tools early so that they can be used for version tests.
+ifndef SHELL_PATH
+	SHELL_PATH = /bin/sh
+endif
+ifndef PERL_PATH
+	PERL_PATH = /usr/bin/perl
+endif
+
+export PERL_PATH
+
+LIB_FILE=libperf.a
+
+LIB_H += ../../include/linux/perf_counter.h
+LIB_H += perf.h
+LIB_H += util/list.h
+LIB_H += util/rbtree.h
+LIB_H += util/levenshtein.h
+LIB_H += util/parse-options.h
+LIB_H += util/parse-events.h
+LIB_H += util/quote.h
+LIB_H += util/util.h
+LIB_H += util/help.h
+LIB_H += util/strbuf.h
+LIB_H += util/string.h
+LIB_H += util/run-command.h
+LIB_H += util/sigchain.h
+LIB_H += util/symbol.h
+LIB_H += util/color.h
+
+LIB_OBJS += util/abspath.o
+LIB_OBJS += util/alias.o
+LIB_OBJS += util/config.o
+LIB_OBJS += util/ctype.o
+LIB_OBJS += util/environment.o
+LIB_OBJS += util/exec_cmd.o
+LIB_OBJS += util/help.o
+LIB_OBJS += util/levenshtein.o
+LIB_OBJS += util/parse-options.o
+LIB_OBJS += util/parse-events.o
+LIB_OBJS += util/path.o
+LIB_OBJS += util/rbtree.o
+LIB_OBJS += util/run-command.o
+LIB_OBJS += util/quote.o
+LIB_OBJS += util/strbuf.o
+LIB_OBJS += util/string.o
+LIB_OBJS += util/usage.o
+LIB_OBJS += util/wrapper.o
+LIB_OBJS += util/sigchain.o
+LIB_OBJS += util/symbol.o
+LIB_OBJS += util/color.o
+LIB_OBJS += util/pager.o
+
+BUILTIN_OBJS += builtin-annotate.o
+BUILTIN_OBJS += builtin-help.o
+BUILTIN_OBJS += builtin-list.o
+BUILTIN_OBJS += builtin-record.o
+BUILTIN_OBJS += builtin-report.o
+BUILTIN_OBJS += builtin-stat.o
+BUILTIN_OBJS += builtin-top.o
+
+PERFLIBS = $(LIB_FILE)
+EXTLIBS =
+
+#
+# Platform specific tweaks
+#
+
+# We choose to avoid "if .. else if .. else .. endif endif"
+# because maintaining the nesting to match is a pain.  If
+# we had "elif" things would have been much nicer...
+
+-include config.mak.autogen
+-include config.mak
+
+ifeq ($(uname_S),Darwin)
+	ifndef NO_FINK
+		ifeq ($(shell test -d /sw/lib && echo y),y)
+			BASIC_CFLAGS += -I/sw/include
+			BASIC_LDFLAGS += -L/sw/lib
+		endif
+	endif
+	ifndef NO_DARWIN_PORTS
+		ifeq ($(shell test -d /opt/local/lib && echo y),y)
+			BASIC_CFLAGS += -I/opt/local/include
+			BASIC_LDFLAGS += -L/opt/local/lib
+		endif
+	endif
+	PTHREAD_LIBS =
+endif
+
+ifndef CC_LD_DYNPATH
+	ifdef NO_R_TO_GCC_LINKER
+		# Some gcc does not accept and pass -R to the linker to specify
+		# the runtime dynamic library path.
+		CC_LD_DYNPATH = -Wl,-rpath,
+	else
+		CC_LD_DYNPATH = -R
+	endif
+endif
+
+ifdef ZLIB_PATH
+	BASIC_CFLAGS += -I$(ZLIB_PATH)/include
+	EXTLIBS += -L$(ZLIB_PATH)/$(lib) $(CC_LD_DYNPATH)$(ZLIB_PATH)/$(lib)
+endif
+EXTLIBS += -lz
+
+ifdef NEEDS_SOCKET
+	EXTLIBS += -lsocket
+endif
+ifdef NEEDS_NSL
+	EXTLIBS += -lnsl
+endif
+ifdef NO_D_TYPE_IN_DIRENT
+	BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT
+endif
+ifdef NO_D_INO_IN_DIRENT
+	BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT
+endif
+ifdef NO_ST_BLOCKS_IN_STRUCT_STAT
+	BASIC_CFLAGS += -DNO_ST_BLOCKS_IN_STRUCT_STAT
+endif
+ifdef USE_NSEC
+	BASIC_CFLAGS += -DUSE_NSEC
+endif
+ifdef USE_ST_TIMESPEC
+	BASIC_CFLAGS += -DUSE_ST_TIMESPEC
+endif
+ifdef NO_NSEC
+	BASIC_CFLAGS += -DNO_NSEC
+endif
+ifdef NO_C99_FORMAT
+	BASIC_CFLAGS += -DNO_C99_FORMAT
+endif
+ifdef SNPRINTF_RETURNS_BOGUS
+	COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS
+	COMPAT_OBJS += compat/snprintf.o
+endif
+ifdef FREAD_READS_DIRECTORIES
+	COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES
+	COMPAT_OBJS += compat/fopen.o
+endif
+ifdef NO_SYMLINK_HEAD
+	BASIC_CFLAGS += -DNO_SYMLINK_HEAD
+endif
+ifdef NO_STRCASESTR
+	COMPAT_CFLAGS += -DNO_STRCASESTR
+	COMPAT_OBJS += compat/strcasestr.o
+endif
+ifdef NO_STRTOUMAX
+	COMPAT_CFLAGS += -DNO_STRTOUMAX
+	COMPAT_OBJS += compat/strtoumax.o
+endif
+ifdef NO_STRTOULL
+	COMPAT_CFLAGS += -DNO_STRTOULL
+endif
+ifdef NO_SETENV
+	COMPAT_CFLAGS += -DNO_SETENV
+	COMPAT_OBJS += compat/setenv.o
+endif
+ifdef NO_MKDTEMP
+	COMPAT_CFLAGS += -DNO_MKDTEMP
+	COMPAT_OBJS += compat/mkdtemp.o
+endif
+ifdef NO_UNSETENV
+	COMPAT_CFLAGS += -DNO_UNSETENV
+	COMPAT_OBJS += compat/unsetenv.o
+endif
+ifdef NO_SYS_SELECT_H
+	BASIC_CFLAGS += -DNO_SYS_SELECT_H
+endif
+ifdef NO_MMAP
+	COMPAT_CFLAGS += -DNO_MMAP
+	COMPAT_OBJS += compat/mmap.o
+else
+	ifdef USE_WIN32_MMAP
+		COMPAT_CFLAGS += -DUSE_WIN32_MMAP
+		COMPAT_OBJS += compat/win32mmap.o
+	endif
+endif
+ifdef NO_PREAD
+	COMPAT_CFLAGS += -DNO_PREAD
+	COMPAT_OBJS += compat/pread.o
+endif
+ifdef NO_FAST_WORKING_DIRECTORY
+	BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY
+endif
+ifdef NO_TRUSTABLE_FILEMODE
+	BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE
+endif
+ifdef NO_IPV6
+	BASIC_CFLAGS += -DNO_IPV6
+endif
+ifdef NO_UINTMAX_T
+	BASIC_CFLAGS += -Duintmax_t=uint32_t
+endif
+ifdef NO_SOCKADDR_STORAGE
+ifdef NO_IPV6
+	BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in
+else
+	BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in6
+endif
+endif
+ifdef NO_INET_NTOP
+	LIB_OBJS += compat/inet_ntop.o
+endif
+ifdef NO_INET_PTON
+	LIB_OBJS += compat/inet_pton.o
+endif
+
+ifdef NO_ICONV
+	BASIC_CFLAGS += -DNO_ICONV
+endif
+
+ifdef OLD_ICONV
+	BASIC_CFLAGS += -DOLD_ICONV
+endif
+
+ifdef NO_DEFLATE_BOUND
+	BASIC_CFLAGS += -DNO_DEFLATE_BOUND
+endif
+
+ifdef PPC_SHA1
+	SHA1_HEADER = "ppc/sha1.h"
+	LIB_OBJS += ppc/sha1.o ppc/sha1ppc.o
+else
+ifdef ARM_SHA1
+	SHA1_HEADER = "arm/sha1.h"
+	LIB_OBJS += arm/sha1.o arm/sha1_arm.o
+else
+ifdef MOZILLA_SHA1
+	SHA1_HEADER = "mozilla-sha1/sha1.h"
+	LIB_OBJS += mozilla-sha1/sha1.o
+else
+	SHA1_HEADER = <openssl/sha.h>
+	EXTLIBS += $(LIB_4_CRYPTO)
+endif
+endif
+endif
+ifdef NO_PERL_MAKEMAKER
+	export NO_PERL_MAKEMAKER
+endif
+ifdef NO_HSTRERROR
+	COMPAT_CFLAGS += -DNO_HSTRERROR
+	COMPAT_OBJS += compat/hstrerror.o
+endif
+ifdef NO_MEMMEM
+	COMPAT_CFLAGS += -DNO_MEMMEM
+	COMPAT_OBJS += compat/memmem.o
+endif
+ifdef INTERNAL_QSORT
+	COMPAT_CFLAGS += -DINTERNAL_QSORT
+	COMPAT_OBJS += compat/qsort.o
+endif
+ifdef RUNTIME_PREFIX
+	COMPAT_CFLAGS += -DRUNTIME_PREFIX
+endif
+
+ifdef DIR_HAS_BSD_GROUP_SEMANTICS
+	COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS
+endif
+ifdef NO_EXTERNAL_GREP
+	BASIC_CFLAGS += -DNO_EXTERNAL_GREP
+endif
+
+ifeq ($(PERL_PATH),)
+NO_PERL=NoThanks
+endif
+
+QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
+QUIET_SUBDIR1  =
+
+ifneq ($(findstring $(MAKEFLAGS),w),w)
+PRINT_DIR = --no-print-directory
+else # "make -w"
+NO_SUBDIR = :
+endif
+
+ifneq ($(findstring $(MAKEFLAGS),s),s)
+ifndef V
+	QUIET_CC       = @echo '   ' CC $@;
+	QUIET_AR       = @echo '   ' AR $@;
+	QUIET_LINK     = @echo '   ' LINK $@;
+	QUIET_BUILT_IN = @echo '   ' BUILTIN $@;
+	QUIET_GEN      = @echo '   ' GEN $@;
+	QUIET_SUBDIR0  = +@subdir=
+	QUIET_SUBDIR1  = ;$(NO_SUBDIR) echo '   ' SUBDIR $$subdir; \
+			 $(MAKE) $(PRINT_DIR) -C $$subdir
+	export V
+	export QUIET_GEN
+	export QUIET_BUILT_IN
+endif
+endif
+
+ifdef ASCIIDOC8
+	export ASCIIDOC8
+endif
+
+# Shell quote (do not use $(call) to accommodate ancient setups);
+
+SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER))
+ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
+
+DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
+bindir_SQ = $(subst ','\'',$(bindir))
+bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+mandir_SQ = $(subst ','\'',$(mandir))
+infodir_SQ = $(subst ','\'',$(infodir))
+perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
+template_dir_SQ = $(subst ','\'',$(template_dir))
+htmldir_SQ = $(subst ','\'',$(htmldir))
+prefix_SQ = $(subst ','\'',$(prefix))
+
+SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
+PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH))
+
+LIBS = $(PERFLIBS) $(EXTLIBS)
+
+BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \
+	$(COMPAT_CFLAGS)
+LIB_OBJS += $(COMPAT_OBJS)
+
+ALL_CFLAGS += $(BASIC_CFLAGS)
+ALL_LDFLAGS += $(BASIC_LDFLAGS)
+
+export TAR INSTALL DESTDIR SHELL_PATH
+
+
+### Build rules
+
+SHELL = $(SHELL_PATH)
+
+all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) PERF-BUILD-OPTIONS
+ifneq (,$X)
+	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';)
+endif
+
+all::
+
+please_set_SHELL_PATH_to_a_more_modern_shell:
+	@$$(:)
+
+shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
+
+strip: $(PROGRAMS) perf$X
+	$(STRIP) $(STRIP_OPTS) $(PROGRAMS) perf$X
+
+perf.o: perf.c common-cmds.h PERF-CFLAGS
+	$(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \
+		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
+		$(ALL_CFLAGS) -c $(filter %.c,$^)
+
+perf$X: perf.o $(BUILTIN_OBJS) $(PERFLIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ perf.o \
+		$(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS)
+
+builtin-help.o: builtin-help.c common-cmds.h PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \
+		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
+		'-DPERF_MAN_PATH="$(mandir_SQ)"' \
+		'-DPERF_INFO_PATH="$(infodir_SQ)"' $<
+
+$(BUILT_INS): perf$X
+	$(QUIET_BUILT_IN)$(RM) $@ && \
+	ln perf$X $@ 2>/dev/null || \
+	ln -s perf$X $@ 2>/dev/null || \
+	cp perf$X $@
+
+common-cmds.h: util/generate-cmdlist.sh command-list.txt
+
+common-cmds.h: $(wildcard Documentation/perf-*.txt)
+	$(QUIET_GEN)util/generate-cmdlist.sh > $@+ && mv $@+ $@
+
+$(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
+	$(QUIET_GEN)$(RM) $@ $@+ && \
+	sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \
+	    -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \
+	    -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \
+	    -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
+	    -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
+	    $@.sh >$@+ && \
+	chmod +x $@+ && \
+	mv $@+ $@
+
+configure: configure.ac
+	$(QUIET_GEN)$(RM) $@ $<+ && \
+	sed -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
+	    $< > $<+ && \
+	autoconf -o $@ $<+ && \
+	$(RM) $<+
+
+# These can record PERF_VERSION
+perf.o perf.spec \
+	$(patsubst %.sh,%,$(SCRIPT_SH)) \
+	$(patsubst %.perl,%,$(SCRIPT_PERL)) \
+	: PERF-VERSION-FILE
+
+%.o: %.c PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $<
+%.s: %.c PERF-CFLAGS
+	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
+%.o: %.S
+	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $<
+
+util/exec_cmd.o: util/exec_cmd.c PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \
+		'-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \
+		'-DBINDIR="$(bindir_relative_SQ)"' \
+		'-DPREFIX="$(prefix_SQ)"' \
+		$<
+
+builtin-init-db.o: builtin-init-db.c PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $<
+
+util/config.o: util/config.c PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
+perf-%$X: %.o $(PERFLIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
+
+$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
+$(patsubst perf-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
+builtin-revert.o wt-status.o: wt-status.h
+
+$(LIB_FILE): $(LIB_OBJS)
+	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS)
+
+doc:
+	$(MAKE) -C Documentation all
+
+man:
+	$(MAKE) -C Documentation man
+
+html:
+	$(MAKE) -C Documentation html
+
+info:
+	$(MAKE) -C Documentation info
+
+pdf:
+	$(MAKE) -C Documentation pdf
+
+TAGS:
+	$(RM) TAGS
+	$(FIND) . -name '*.[hcS]' -print | xargs etags -a
+
+tags:
+	$(RM) tags
+	$(FIND) . -name '*.[hcS]' -print | xargs ctags -a
+
+cscope:
+	$(RM) cscope*
+	$(FIND) . -name '*.[hcS]' -print | xargs cscope -b
+
+### Detect prefix changes
+TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\
+             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
+
+PERF-CFLAGS: .FORCE-PERF-CFLAGS
+	@FLAGS='$(TRACK_CFLAGS)'; \
+	    if test x"$$FLAGS" != x"`cat PERF-CFLAGS 2>/dev/null`" ; then \
+		echo 1>&2 "    * new build flags or prefix"; \
+		echo "$$FLAGS" >PERF-CFLAGS; \
+            fi
+
+# We need to apply sq twice, once to protect from the shell
+# that runs PERF-BUILD-OPTIONS, and then again to protect it
+# and the first level quoting from the shell that runs "echo".
+PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS
+	@echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@
+	@echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@
+	@echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@
+	@echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@
+
+### Testing rules
+
+#
+# None right now:
+#
+# TEST_PROGRAMS += test-something$X
+
+all:: $(TEST_PROGRAMS)
+
+# GNU make supports exporting all variables by "export" without parameters.
+# However, the environment gets quite big, and some programs have problems
+# with that.
+
+export NO_SVN_TESTS
+
+check: common-cmds.h
+	if sparse; \
+	then \
+		for i in *.c */*.c; \
+		do \
+			sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
+		done; \
+	else \
+		echo 2>&1 "Did you mean 'make test'?"; \
+		exit 1; \
+	fi
+
+remove-dashes:
+	./fixup-builtins $(BUILT_INS) $(PROGRAMS) $(SCRIPTS)
+
+### Installation rules
+
+ifneq ($(filter /%,$(firstword $(template_dir))),)
+template_instdir = $(template_dir)
+else
+template_instdir = $(prefix)/$(template_dir)
+endif
+export template_instdir
+
+ifneq ($(filter /%,$(firstword $(perfexecdir))),)
+perfexec_instdir = $(perfexecdir)
+else
+perfexec_instdir = $(prefix)/$(perfexecdir)
+endif
+perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+export perfexec_instdir
+
+install: all
+	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
+	$(INSTALL) perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
+ifdef BUILT_INS
+	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+	$(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ifneq (,$X)
+	$(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';)
+endif
+endif
+
+install-doc:
+	$(MAKE) -C Documentation install
+
+install-man:
+	$(MAKE) -C Documentation install-man
+
+install-html:
+	$(MAKE) -C Documentation install-html
+
+install-info:
+	$(MAKE) -C Documentation install-info
+
+install-pdf:
+	$(MAKE) -C Documentation install-pdf
+
+quick-install-doc:
+	$(MAKE) -C Documentation quick-install
+
+quick-install-man:
+	$(MAKE) -C Documentation quick-install-man
+
+quick-install-html:
+	$(MAKE) -C Documentation quick-install-html
+
+
+### Maintainer's dist rules
+#
+# None right now
+#
+#
+# perf.spec: perf.spec.in
+#	sed -e 's/@@VERSION@@/$(PERF_VERSION)/g' < $< > $@+
+#	mv $@+ $@
+#
+# PERF_TARNAME=perf-$(PERF_VERSION)
+# dist: perf.spec perf-archive$(X) configure
+#	./perf-archive --format=tar \
+#		--prefix=$(PERF_TARNAME)/ HEAD^{tree} > $(PERF_TARNAME).tar
+#	@mkdir -p $(PERF_TARNAME)
+#	@cp perf.spec configure $(PERF_TARNAME)
+#	@echo $(PERF_VERSION) > $(PERF_TARNAME)/version
+#	$(TAR) rf $(PERF_TARNAME).tar \
+#		$(PERF_TARNAME)/perf.spec \
+#		$(PERF_TARNAME)/configure \
+#		$(PERF_TARNAME)/version
+#	@$(RM) -r $(PERF_TARNAME)
+#	gzip -f -9 $(PERF_TARNAME).tar
+#
+# htmldocs = perf-htmldocs-$(PERF_VERSION)
+# manpages = perf-manpages-$(PERF_VERSION)
+# dist-doc:
+#	$(RM) -r .doc-tmp-dir
+#	mkdir .doc-tmp-dir
+#	$(MAKE) -C Documentation WEBDOC_DEST=../.doc-tmp-dir install-webdoc
+#	cd .doc-tmp-dir && $(TAR) cf ../$(htmldocs).tar .
+#	gzip -n -9 -f $(htmldocs).tar
+#	:
+#	$(RM) -r .doc-tmp-dir
+#	mkdir -p .doc-tmp-dir/man1 .doc-tmp-dir/man5 .doc-tmp-dir/man7
+#	$(MAKE) -C Documentation DESTDIR=./ \
+#		man1dir=../.doc-tmp-dir/man1 \
+#		man5dir=../.doc-tmp-dir/man5 \
+#		man7dir=../.doc-tmp-dir/man7 \
+#		install
+#	cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar .
+#	gzip -n -9 -f $(manpages).tar
+#	$(RM) -r .doc-tmp-dir
+#
+# rpm: dist
+#	$(RPMBUILD) -ta $(PERF_TARNAME).tar.gz
+
+### Cleaning rules
+
+distclean: clean
+#	$(RM) configure
+
+clean:
+	$(RM) *.o */*.o $(LIB_FILE)
+	$(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X
+	$(RM) $(TEST_PROGRAMS)
+	$(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags cscope*
+	$(RM) -r autom4te.cache
+	$(RM) config.log config.mak.autogen config.mak.append config.status config.cache
+	$(RM) -r $(PERF_TARNAME) .doc-tmp-dir
+	$(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz
+	$(RM) $(htmldocs).tar.gz $(manpages).tar.gz
+	$(MAKE) -C Documentation/ clean
+	$(RM) PERF-VERSION-FILE PERF-CFLAGS PERF-BUILD-OPTIONS
+
+.PHONY: all install clean strip
+.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
+.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS
+.PHONY: .FORCE-PERF-BUILD-OPTIONS
+
+### Make sure built-ins do not have dups and listed in perf.c
+#
+check-builtins::
+	./check-builtins.sh
+
+### Test suite coverage testing
+#
+# None right now
+#
+# .PHONY: coverage coverage-clean coverage-build coverage-report
+#
+# coverage:
+#	$(MAKE) coverage-build
+#	$(MAKE) coverage-report
+#
+# coverage-clean:
+#	rm -f *.gcda *.gcno
+#
+# COVERAGE_CFLAGS = $(CFLAGS) -O0 -ftest-coverage -fprofile-arcs
+# COVERAGE_LDFLAGS = $(CFLAGS)  -O0 -lgcov
+#
+# coverage-build: coverage-clean
+#	$(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" all
+#	$(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" \
+#		-j1 test
+#
+# coverage-report:
+#	gcov -b *.c */*.c
+#	grep '^function.*called 0 ' *.c.gcov */*.c.gcov \
+#		| sed -e 's/\([^:]*\)\.gcov: *function \([^ ]*\) called.*/\1: \2/' \
+#		| tee coverage-untested-functions
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
new file mode 100644
index 000000000000..b1ed5f766cb3
--- /dev/null
+++ b/tools/perf/builtin-annotate.c
@@ -0,0 +1,1356 @@
+/*
+ * builtin-annotate.c
+ *
+ * Builtin annotate command: Analyze the perf.data input file,
+ * look up and read DSOs and symbol information and display
+ * a histogram of results, along various sorting keys.
+ */
+#include "builtin.h"
+
+#include "util/util.h"
+
+#include "util/color.h"
+#include "util/list.h"
+#include "util/cache.h"
+#include "util/rbtree.h"
+#include "util/symbol.h"
+#include "util/string.h"
+
+#include "perf.h"
+
+#include "util/parse-options.h"
+#include "util/parse-events.h"
+
+#define SHOW_KERNEL	1
+#define SHOW_USER	2
+#define SHOW_HV		4
+
+static char		const *input_name = "perf.data";
+static char		*vmlinux = "vmlinux";
+
+static char		default_sort_order[] = "comm,symbol";
+static char		*sort_order = default_sort_order;
+
+static int		input;
+static int		show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV;
+
+static int		dump_trace = 0;
+#define dprintf(x...)	do { if (dump_trace) printf(x); } while (0)
+
+static int		verbose;
+
+static unsigned long	page_size;
+static unsigned long	mmap_window = 32;
+
+struct ip_event {
+	struct perf_event_header header;
+	__u64 ip;
+	__u32 pid, tid;
+};
+
+struct mmap_event {
+	struct perf_event_header header;
+	__u32 pid, tid;
+	__u64 start;
+	__u64 len;
+	__u64 pgoff;
+	char filename[PATH_MAX];
+};
+
+struct comm_event {
+	struct perf_event_header header;
+	__u32 pid, tid;
+	char comm[16];
+};
+
+struct fork_event {
+	struct perf_event_header header;
+	__u32 pid, ppid;
+};
+
+struct period_event {
+	struct perf_event_header header;
+	__u64 time;
+	__u64 id;
+	__u64 sample_period;
+};
+
+typedef union event_union {
+	struct perf_event_header	header;
+	struct ip_event			ip;
+	struct mmap_event		mmap;
+	struct comm_event		comm;
+	struct fork_event		fork;
+	struct period_event		period;
+} event_t;
+
+static LIST_HEAD(dsos);
+static struct dso *kernel_dso;
+static struct dso *vdso;
+
+
+static void dsos__add(struct dso *dso)
+{
+	list_add_tail(&dso->node, &dsos);
+}
+
+static struct dso *dsos__find(const char *name)
+{
+	struct dso *pos;
+
+	list_for_each_entry(pos, &dsos, node)
+		if (strcmp(pos->name, name) == 0)
+			return pos;
+	return NULL;
+}
+
+static struct dso *dsos__findnew(const char *name)
+{
+	struct dso *dso = dsos__find(name);
+	int nr;
+
+	if (dso)
+		return dso;
+
+	dso = dso__new(name, 0);
+	if (!dso)
+		goto out_delete_dso;
+
+	nr = dso__load(dso, NULL, verbose);
+	if (nr < 0) {
+		if (verbose)
+			fprintf(stderr, "Failed to open: %s\n", name);
+		goto out_delete_dso;
+	}
+	if (!nr && verbose) {
+		fprintf(stderr,
+		"No symbols found in: %s, maybe install a debug package?\n",
+				name);
+	}
+
+	dsos__add(dso);
+
+	return dso;
+
+out_delete_dso:
+	dso__delete(dso);
+	return NULL;
+}
+
+static void dsos__fprintf(FILE *fp)
+{
+	struct dso *pos;
+
+	list_for_each_entry(pos, &dsos, node)
+		dso__fprintf(pos, fp);
+}
+
+static struct symbol *vdso__find_symbol(struct dso *dso, __u64 ip)
+{
+	return dso__find_symbol(kernel_dso, ip);
+}
+
+static int load_kernel(void)
+{
+	int err;
+
+	kernel_dso = dso__new("[kernel]", 0);
+	if (!kernel_dso)
+		return -1;
+
+	err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose);
+	if (err) {
+		dso__delete(kernel_dso);
+		kernel_dso = NULL;
+	} else
+		dsos__add(kernel_dso);
+
+	vdso = dso__new("[vdso]", 0);
+	if (!vdso)
+		return -1;
+
+	vdso->find_symbol = vdso__find_symbol;
+
+	dsos__add(vdso);
+
+	return err;
+}
+
+struct map {
+	struct list_head node;
+	__u64	 start;
+	__u64	 end;
+	__u64	 pgoff;
+	__u64	 (*map_ip)(struct map *, __u64);
+	struct dso	 *dso;
+};
+
+static __u64 map__map_ip(struct map *map, __u64 ip)
+{
+	return ip - map->start + map->pgoff;
+}
+
+static __u64 vdso__map_ip(struct map *map, __u64 ip)
+{
+	return ip;
+}
+
+static struct map *map__new(struct mmap_event *event)
+{
+	struct map *self = malloc(sizeof(*self));
+
+	if (self != NULL) {
+		const char *filename = event->filename;
+
+		self->start = event->start;
+		self->end   = event->start + event->len;
+		self->pgoff = event->pgoff;
+
+		self->dso = dsos__findnew(filename);
+		if (self->dso == NULL)
+			goto out_delete;
+
+		if (self->dso == vdso)
+			self->map_ip = vdso__map_ip;
+		else
+			self->map_ip = map__map_ip;
+	}
+	return self;
+out_delete:
+	free(self);
+	return NULL;
+}
+
+static struct map *map__clone(struct map *self)
+{
+	struct map *map = malloc(sizeof(*self));
+
+	if (!map)
+		return NULL;
+
+	memcpy(map, self, sizeof(*self));
+
+	return map;
+}
+
+static int map__overlap(struct map *l, struct map *r)
+{
+	if (l->start > r->start) {
+		struct map *t = l;
+		l = r;
+		r = t;
+	}
+
+	if (l->end > r->start)
+		return 1;
+
+	return 0;
+}
+
+static size_t map__fprintf(struct map *self, FILE *fp)
+{
+	return fprintf(fp, " %Lx-%Lx %Lx %s\n",
+		       self->start, self->end, self->pgoff, self->dso->name);
+}
+
+
+struct thread {
+	struct rb_node	 rb_node;
+	struct list_head maps;
+	pid_t		 pid;
+	char		 *comm;
+};
+
+static struct thread *thread__new(pid_t pid)
+{
+	struct thread *self = malloc(sizeof(*self));
+
+	if (self != NULL) {
+		self->pid = pid;
+		self->comm = malloc(32);
+		if (self->comm)
+			snprintf(self->comm, 32, ":%d", self->pid);
+		INIT_LIST_HEAD(&self->maps);
+	}
+
+	return self;
+}
+
+static int thread__set_comm(struct thread *self, const char *comm)
+{
+	if (self->comm)
+		free(self->comm);
+	self->comm = strdup(comm);
+	return self->comm ? 0 : -ENOMEM;
+}
+
+static size_t thread__fprintf(struct thread *self, FILE *fp)
+{
+	struct map *pos;
+	size_t ret = fprintf(fp, "Thread %d %s\n", self->pid, self->comm);
+
+	list_for_each_entry(pos, &self->maps, node)
+		ret += map__fprintf(pos, fp);
+
+	return ret;
+}
+
+
+static struct rb_root threads;
+static struct thread *last_match;
+
+static struct thread *threads__findnew(pid_t pid)
+{
+	struct rb_node **p = &threads.rb_node;
+	struct rb_node *parent = NULL;
+	struct thread *th;
+
+	/*
+	 * Font-end cache - PID lookups come in blocks,
+	 * so most of the time we dont have to look up
+	 * the full rbtree:
+	 */
+	if (last_match && last_match->pid == pid)
+		return last_match;
+
+	while (*p != NULL) {
+		parent = *p;
+		th = rb_entry(parent, struct thread, rb_node);
+
+		if (th->pid == pid) {
+			last_match = th;
+			return th;
+		}
+
+		if (pid < th->pid)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	th = thread__new(pid);
+	if (th != NULL) {
+		rb_link_node(&th->rb_node, parent, p);
+		rb_insert_color(&th->rb_node, &threads);
+		last_match = th;
+	}
+
+	return th;
+}
+
+static void thread__insert_map(struct thread *self, struct map *map)
+{
+	struct map *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, &self->maps, node) {
+		if (map__overlap(pos, map)) {
+			list_del_init(&pos->node);
+			/* XXX leaks dsos */
+			free(pos);
+		}
+	}
+
+	list_add_tail(&map->node, &self->maps);
+}
+
+static int thread__fork(struct thread *self, struct thread *parent)
+{
+	struct map *map;
+
+	if (self->comm)
+		free(self->comm);
+	self->comm = strdup(parent->comm);
+	if (!self->comm)
+		return -ENOMEM;
+
+	list_for_each_entry(map, &parent->maps, node) {
+		struct map *new = map__clone(map);
+		if (!new)
+			return -ENOMEM;
+		thread__insert_map(self, new);
+	}
+
+	return 0;
+}
+
+static struct map *thread__find_map(struct thread *self, __u64 ip)
+{
+	struct map *pos;
+
+	if (self == NULL)
+		return NULL;
+
+	list_for_each_entry(pos, &self->maps, node)
+		if (ip >= pos->start && ip <= pos->end)
+			return pos;
+
+	return NULL;
+}
+
+static size_t threads__fprintf(FILE *fp)
+{
+	size_t ret = 0;
+	struct rb_node *nd;
+
+	for (nd = rb_first(&threads); nd; nd = rb_next(nd)) {
+		struct thread *pos = rb_entry(nd, struct thread, rb_node);
+
+		ret += thread__fprintf(pos, fp);
+	}
+
+	return ret;
+}
+
+/*
+ * histogram, sorted on item, collects counts
+ */
+
+static struct rb_root hist;
+
+struct hist_entry {
+	struct rb_node	 rb_node;
+
+	struct thread	 *thread;
+	struct map	 *map;
+	struct dso	 *dso;
+	struct symbol	 *sym;
+	__u64	 ip;
+	char		 level;
+
+	uint32_t	 count;
+};
+
+/*
+ * configurable sorting bits
+ */
+
+struct sort_entry {
+	struct list_head list;
+
+	char *header;
+
+	int64_t (*cmp)(struct hist_entry *, struct hist_entry *);
+	int64_t (*collapse)(struct hist_entry *, struct hist_entry *);
+	size_t	(*print)(FILE *fp, struct hist_entry *);
+};
+
+/* --sort pid */
+
+static int64_t
+sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->thread->pid - left->thread->pid;
+}
+
+static size_t
+sort__thread_print(FILE *fp, struct hist_entry *self)
+{
+	return fprintf(fp, "%16s:%5d", self->thread->comm ?: "", self->thread->pid);
+}
+
+static struct sort_entry sort_thread = {
+	.header = "         Command:  Pid",
+	.cmp	= sort__thread_cmp,
+	.print	= sort__thread_print,
+};
+
+/* --sort comm */
+
+static int64_t
+sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->thread->pid - left->thread->pid;
+}
+
+static int64_t
+sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	char *comm_l = left->thread->comm;
+	char *comm_r = right->thread->comm;
+
+	if (!comm_l || !comm_r) {
+		if (!comm_l && !comm_r)
+			return 0;
+		else if (!comm_l)
+			return -1;
+		else
+			return 1;
+	}
+
+	return strcmp(comm_l, comm_r);
+}
+
+static size_t
+sort__comm_print(FILE *fp, struct hist_entry *self)
+{
+	return fprintf(fp, "%16s", self->thread->comm);
+}
+
+static struct sort_entry sort_comm = {
+	.header		= "         Command",
+	.cmp		= sort__comm_cmp,
+	.collapse	= sort__comm_collapse,
+	.print		= sort__comm_print,
+};
+
+/* --sort dso */
+
+static int64_t
+sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct dso *dso_l = left->dso;
+	struct dso *dso_r = right->dso;
+
+	if (!dso_l || !dso_r) {
+		if (!dso_l && !dso_r)
+			return 0;
+		else if (!dso_l)
+			return -1;
+		else
+			return 1;
+	}
+
+	return strcmp(dso_l->name, dso_r->name);
+}
+
+static size_t
+sort__dso_print(FILE *fp, struct hist_entry *self)
+{
+	if (self->dso)
+		return fprintf(fp, "%-25s", self->dso->name);
+
+	return fprintf(fp, "%016llx         ", (__u64)self->ip);
+}
+
+static struct sort_entry sort_dso = {
+	.header = "Shared Object            ",
+	.cmp	= sort__dso_cmp,
+	.print	= sort__dso_print,
+};
+
+/* --sort symbol */
+
+static int64_t
+sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	__u64 ip_l, ip_r;
+
+	if (left->sym == right->sym)
+		return 0;
+
+	ip_l = left->sym ? left->sym->start : left->ip;
+	ip_r = right->sym ? right->sym->start : right->ip;
+
+	return (int64_t)(ip_r - ip_l);
+}
+
+static size_t
+sort__sym_print(FILE *fp, struct hist_entry *self)
+{
+	size_t ret = 0;
+
+	if (verbose)
+		ret += fprintf(fp, "%#018llx  ", (__u64)self->ip);
+
+	if (self->sym) {
+		ret += fprintf(fp, "[%c] %s",
+			self->dso == kernel_dso ? 'k' : '.', self->sym->name);
+	} else {
+		ret += fprintf(fp, "%#016llx", (__u64)self->ip);
+	}
+
+	return ret;
+}
+
+static struct sort_entry sort_sym = {
+	.header = "Symbol",
+	.cmp	= sort__sym_cmp,
+	.print	= sort__sym_print,
+};
+
+static int sort__need_collapse = 0;
+
+struct sort_dimension {
+	char			*name;
+	struct sort_entry	*entry;
+	int			taken;
+};
+
+static struct sort_dimension sort_dimensions[] = {
+	{ .name = "pid",	.entry = &sort_thread,	},
+	{ .name = "comm",	.entry = &sort_comm,	},
+	{ .name = "dso",	.entry = &sort_dso,	},
+	{ .name = "symbol",	.entry = &sort_sym,	},
+};
+
+static LIST_HEAD(hist_entry__sort_list);
+
+static int sort_dimension__add(char *tok)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
+		struct sort_dimension *sd = &sort_dimensions[i];
+
+		if (sd->taken)
+			continue;
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		if (sd->entry->collapse)
+			sort__need_collapse = 1;
+
+		list_add_tail(&sd->entry->list, &hist_entry__sort_list);
+		sd->taken = 1;
+
+		return 0;
+	}
+
+	return -ESRCH;
+}
+
+static int64_t
+hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct sort_entry *se;
+	int64_t cmp = 0;
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		cmp = se->cmp(left, right);
+		if (cmp)
+			break;
+	}
+
+	return cmp;
+}
+
+static int64_t
+hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	struct sort_entry *se;
+	int64_t cmp = 0;
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		int64_t (*f)(struct hist_entry *, struct hist_entry *);
+
+		f = se->collapse ?: se->cmp;
+
+		cmp = f(left, right);
+		if (cmp)
+			break;
+	}
+
+	return cmp;
+}
+
+/*
+ * collect histogram counts
+ */
+static void hist_hit(struct hist_entry *he, __u64 ip)
+{
+	unsigned int sym_size, offset;
+	struct symbol *sym = he->sym;
+
+	he->count++;
+
+	if (!sym || !sym->hist)
+		return;
+
+	sym_size = sym->end - sym->start;
+	offset = ip - sym->start;
+
+	if (offset >= sym_size)
+		return;
+
+	sym->hist_sum++;
+	sym->hist[offset]++;
+
+	if (verbose >= 3)
+		printf("%p %s: count++ [ip: %p, %08Lx] => %Ld\n",
+			(void *)(unsigned long)he->sym->start,
+			he->sym->name,
+			(void *)(unsigned long)ip, ip - he->sym->start,
+			sym->hist[offset]);
+}
+
+static int
+hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
+		struct symbol *sym, __u64 ip, char level)
+{
+	struct rb_node **p = &hist.rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *he;
+	struct hist_entry entry = {
+		.thread	= thread,
+		.map	= map,
+		.dso	= dso,
+		.sym	= sym,
+		.ip	= ip,
+		.level	= level,
+		.count	= 1,
+	};
+	int cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		he = rb_entry(parent, struct hist_entry, rb_node);
+
+		cmp = hist_entry__cmp(&entry, he);
+
+		if (!cmp) {
+			hist_hit(he, ip);
+
+			return 0;
+		}
+
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	he = malloc(sizeof(*he));
+	if (!he)
+		return -ENOMEM;
+	*he = entry;
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, &hist);
+
+	return 0;
+}
+
+static void hist_entry__free(struct hist_entry *he)
+{
+	free(he);
+}
+
+/*
+ * collapse the histogram
+ */
+
+static struct rb_root collapse_hists;
+
+static void collapse__insert_entry(struct hist_entry *he)
+{
+	struct rb_node **p = &collapse_hists.rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	int64_t cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		cmp = hist_entry__collapse(iter, he);
+
+		if (!cmp) {
+			iter->count += he->count;
+			hist_entry__free(he);
+			return;
+		}
+
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, &collapse_hists);
+}
+
+static void collapse__resort(void)
+{
+	struct rb_node *next;
+	struct hist_entry *n;
+
+	if (!sort__need_collapse)
+		return;
+
+	next = rb_first(&hist);
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		next = rb_next(&n->rb_node);
+
+		rb_erase(&n->rb_node, &hist);
+		collapse__insert_entry(n);
+	}
+}
+
+/*
+ * reverse the map, sort on count.
+ */
+
+static struct rb_root output_hists;
+
+static void output__insert_entry(struct hist_entry *he)
+{
+	struct rb_node **p = &output_hists.rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (he->count > iter->count)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, &output_hists);
+}
+
+static void output__resort(void)
+{
+	struct rb_node *next;
+	struct hist_entry *n;
+	struct rb_root *tree = &hist;
+
+	if (sort__need_collapse)
+		tree = &collapse_hists;
+
+	next = rb_first(tree);
+
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		next = rb_next(&n->rb_node);
+
+		rb_erase(&n->rb_node, tree);
+		output__insert_entry(n);
+	}
+}
+
+static void register_idle_thread(void)
+{
+	struct thread *thread = threads__findnew(0);
+
+	if (thread == NULL ||
+			thread__set_comm(thread, "[idle]")) {
+		fprintf(stderr, "problem inserting idle task.\n");
+		exit(-1);
+	}
+}
+
+static unsigned long total = 0,
+		     total_mmap = 0,
+		     total_comm = 0,
+		     total_fork = 0,
+		     total_unknown = 0;
+
+static int
+process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	char level;
+	int show = 0;
+	struct dso *dso = NULL;
+	struct thread *thread = threads__findnew(event->ip.pid);
+	__u64 ip = event->ip.ip;
+	struct map *map = NULL;
+
+	dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->header.misc,
+		event->ip.pid,
+		(void *)(long)ip);
+
+	dprintf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+
+	if (thread == NULL) {
+		fprintf(stderr, "problem processing %d event, skipping it.\n",
+			event->header.type);
+		return -1;
+	}
+
+	if (event->header.misc & PERF_EVENT_MISC_KERNEL) {
+		show = SHOW_KERNEL;
+		level = 'k';
+
+		dso = kernel_dso;
+
+		dprintf(" ...... dso: %s\n", dso->name);
+
+	} else if (event->header.misc & PERF_EVENT_MISC_USER) {
+
+		show = SHOW_USER;
+		level = '.';
+
+		map = thread__find_map(thread, ip);
+		if (map != NULL) {
+			ip = map->map_ip(map, ip);
+			dso = map->dso;
+		} else {
+			/*
+			 * If this is outside of all known maps,
+			 * and is a negative address, try to look it
+			 * up in the kernel dso, as it might be a
+			 * vsyscall (which executes in user-mode):
+			 */
+			if ((long long)ip < 0)
+				dso = kernel_dso;
+		}
+		dprintf(" ...... dso: %s\n", dso ? dso->name : "<not found>");
+
+	} else {
+		show = SHOW_HV;
+		level = 'H';
+		dprintf(" ...... dso: [hypervisor]\n");
+	}
+
+	if (show & show_mask) {
+		struct symbol *sym = NULL;
+
+		if (dso)
+			sym = dso->find_symbol(dso, ip);
+
+		if (hist_entry__add(thread, map, dso, sym, ip, level)) {
+			fprintf(stderr,
+		"problem incrementing symbol count, skipping event\n");
+			return -1;
+		}
+	}
+	total++;
+
+	return 0;
+}
+
+static int
+process_mmap_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	struct thread *thread = threads__findnew(event->mmap.pid);
+	struct map *map = map__new(&event->mmap);
+
+	dprintf("%p [%p]: PERF_EVENT_MMAP %d: [%p(%p) @ %p]: %s\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->mmap.pid,
+		(void *)(long)event->mmap.start,
+		(void *)(long)event->mmap.len,
+		(void *)(long)event->mmap.pgoff,
+		event->mmap.filename);
+
+	if (thread == NULL || map == NULL) {
+		dprintf("problem processing PERF_EVENT_MMAP, skipping event.\n");
+		return 0;
+	}
+
+	thread__insert_map(thread, map);
+	total_mmap++;
+
+	return 0;
+}
+
+static int
+process_comm_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	struct thread *thread = threads__findnew(event->comm.pid);
+
+	dprintf("%p [%p]: PERF_EVENT_COMM: %s:%d\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->comm.comm, event->comm.pid);
+
+	if (thread == NULL ||
+	    thread__set_comm(thread, event->comm.comm)) {
+		dprintf("problem processing PERF_EVENT_COMM, skipping event.\n");
+		return -1;
+	}
+	total_comm++;
+
+	return 0;
+}
+
+static int
+process_fork_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	struct thread *thread = threads__findnew(event->fork.pid);
+	struct thread *parent = threads__findnew(event->fork.ppid);
+
+	dprintf("%p [%p]: PERF_EVENT_FORK: %d:%d\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->fork.pid, event->fork.ppid);
+
+	if (!thread || !parent || thread__fork(thread, parent)) {
+		dprintf("problem processing PERF_EVENT_FORK, skipping event.\n");
+		return -1;
+	}
+	total_fork++;
+
+	return 0;
+}
+
+static int
+process_period_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	dprintf("%p [%p]: PERF_EVENT_PERIOD: time:%Ld, id:%Ld: period:%Ld\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->period.time,
+		event->period.id,
+		event->period.sample_period);
+
+	return 0;
+}
+
+static int
+process_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	if (event->header.misc & PERF_EVENT_MISC_OVERFLOW)
+		return process_overflow_event(event, offset, head);
+
+	switch (event->header.type) {
+	case PERF_EVENT_MMAP:
+		return process_mmap_event(event, offset, head);
+
+	case PERF_EVENT_COMM:
+		return process_comm_event(event, offset, head);
+
+	case PERF_EVENT_FORK:
+		return process_fork_event(event, offset, head);
+
+	case PERF_EVENT_PERIOD:
+		return process_period_event(event, offset, head);
+	/*
+	 * We dont process them right now but they are fine:
+	 */
+
+	case PERF_EVENT_THROTTLE:
+	case PERF_EVENT_UNTHROTTLE:
+		return 0;
+
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+
+static int
+parse_line(FILE *file, struct symbol *sym, __u64 start, __u64 len)
+{
+	char *line = NULL, *tmp, *tmp2;
+	unsigned int offset;
+	size_t line_len;
+	__u64 line_ip;
+	int ret;
+	char *c;
+
+	if (getline(&line, &line_len, file) < 0)
+		return -1;
+	if (!line)
+		return -1;
+
+	c = strchr(line, '\n');
+	if (c)
+		*c = 0;
+
+	line_ip = -1;
+	offset = 0;
+	ret = -2;
+
+	/*
+	 * Strip leading spaces:
+	 */
+	tmp = line;
+	while (*tmp) {
+		if (*tmp != ' ')
+			break;
+		tmp++;
+	}
+
+	if (*tmp) {
+		/*
+		 * Parse hexa addresses followed by ':'
+		 */
+		line_ip = strtoull(tmp, &tmp2, 16);
+		if (*tmp2 != ':')
+			line_ip = -1;
+	}
+
+	if (line_ip != -1) {
+		unsigned int hits = 0;
+		double percent = 0.0;
+		char *color = PERF_COLOR_NORMAL;
+
+		offset = line_ip - start;
+		if (offset < len)
+			hits = sym->hist[offset];
+
+		if (sym->hist_sum)
+			percent = 100.0 * hits / sym->hist_sum;
+
+		/*
+		 * We color high-overhead entries in red, mid-overhead
+		 * entries in green - and keep the low overhead places
+		 * normal:
+		 */
+		if (percent >= 5.0)
+			color = PERF_COLOR_RED;
+		else {
+			if (percent > 0.5)
+				color = PERF_COLOR_GREEN;
+		}
+
+		color_fprintf(stdout, color, " %7.2f", percent);
+		printf(" :	");
+		color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", line);
+	} else {
+		if (!*line)
+			printf("         :\n");
+		else
+			printf("         :	%s\n", line);
+	}
+
+	return 0;
+}
+
+static void annotate_sym(struct dso *dso, struct symbol *sym)
+{
+	char *filename = dso->name;
+	__u64 start, end, len;
+	char command[PATH_MAX*2];
+	FILE *file;
+
+	if (!filename)
+		return;
+	if (dso == kernel_dso)
+		filename = vmlinux;
+
+	printf("\n------------------------------------------------\n");
+	printf(" Percent |	Source code & Disassembly of %s\n", filename);
+	printf("------------------------------------------------\n");
+
+	if (verbose >= 2)
+		printf("annotating [%p] %30s : [%p] %30s\n", dso, dso->name, sym, sym->name);
+
+	start = sym->obj_start;
+	if (!start)
+		start = sym->start;
+
+	end = start + sym->end - sym->start + 1;
+	len = sym->end - sym->start;
+
+	sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s", (__u64)start, (__u64)end, filename);
+
+	if (verbose >= 3)
+		printf("doing: %s\n", command);
+
+	file = popen(command, "r");
+	if (!file)
+		return;
+
+	while (!feof(file)) {
+		if (parse_line(file, sym, start, len) < 0)
+			break;
+	}
+
+	pclose(file);
+}
+
+static void find_annotations(void)
+{
+	struct rb_node *nd;
+	struct dso *dso;
+	int count = 0;
+
+	list_for_each_entry(dso, &dsos, node) {
+
+		for (nd = rb_first(&dso->syms); nd; nd = rb_next(nd)) {
+			struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
+
+			if (sym->hist) {
+				annotate_sym(dso, sym);
+				count++;
+			}
+		}
+	}
+
+	if (!count)
+		printf(" Error: symbol '%s' not present amongst the samples.\n", sym_hist_filter);
+}
+
+static int __cmd_annotate(void)
+{
+	int ret, rc = EXIT_FAILURE;
+	unsigned long offset = 0;
+	unsigned long head = 0;
+	struct stat stat;
+	event_t *event;
+	uint32_t size;
+	char *buf;
+
+	register_idle_thread();
+
+	input = open(input_name, O_RDONLY);
+	if (input < 0) {
+		perror("failed to open file");
+		exit(-1);
+	}
+
+	ret = fstat(input, &stat);
+	if (ret < 0) {
+		perror("failed to stat file");
+		exit(-1);
+	}
+
+	if (!stat.st_size) {
+		fprintf(stderr, "zero-sized file, nothing to do!\n");
+		exit(0);
+	}
+
+	if (load_kernel() < 0) {
+		perror("failed to load kernel symbols");
+		return EXIT_FAILURE;
+	}
+
+remap:
+	buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ,
+			   MAP_SHARED, input, offset);
+	if (buf == MAP_FAILED) {
+		perror("failed to mmap file");
+		exit(-1);
+	}
+
+more:
+	event = (event_t *)(buf + head);
+
+	size = event->header.size;
+	if (!size)
+		size = 8;
+
+	if (head + event->header.size >= page_size * mmap_window) {
+		unsigned long shift = page_size * (head / page_size);
+		int ret;
+
+		ret = munmap(buf, page_size * mmap_window);
+		assert(ret == 0);
+
+		offset += shift;
+		head -= shift;
+		goto remap;
+	}
+
+	size = event->header.size;
+
+	dprintf("%p [%p]: event: %d\n",
+			(void *)(offset + head),
+			(void *)(long)event->header.size,
+			event->header.type);
+
+	if (!size || process_event(event, offset, head) < 0) {
+
+		dprintf("%p [%p]: skipping unknown header type: %d\n",
+			(void *)(offset + head),
+			(void *)(long)(event->header.size),
+			event->header.type);
+
+		total_unknown++;
+
+		/*
+		 * assume we lost track of the stream, check alignment, and
+		 * increment a single u64 in the hope to catch on again 'soon'.
+		 */
+
+		if (unlikely(head & 7))
+			head &= ~7ULL;
+
+		size = 8;
+	}
+
+	head += size;
+
+	if (offset + head < stat.st_size)
+		goto more;
+
+	rc = EXIT_SUCCESS;
+	close(input);
+
+	dprintf("      IP events: %10ld\n", total);
+	dprintf("    mmap events: %10ld\n", total_mmap);
+	dprintf("    comm events: %10ld\n", total_comm);
+	dprintf("    fork events: %10ld\n", total_fork);
+	dprintf(" unknown events: %10ld\n", total_unknown);
+
+	if (dump_trace)
+		return 0;
+
+	if (verbose >= 3)
+		threads__fprintf(stdout);
+
+	if (verbose >= 2)
+		dsos__fprintf(stdout);
+
+	collapse__resort();
+	output__resort();
+
+	find_annotations();
+
+	return rc;
+}
+
+static const char * const annotate_usage[] = {
+	"perf annotate [<options>] <command>",
+	NULL
+};
+
+static const struct option options[] = {
+	OPT_STRING('i', "input", &input_name, "file",
+		    "input file name"),
+	OPT_STRING('s', "symbol", &sym_hist_filter, "symbol",
+		    "symbol to annotate"),
+	OPT_BOOLEAN('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"),
+	OPT_END()
+};
+
+static void setup_sorting(void)
+{
+	char *tmp, *tok, *str = strdup(sort_order);
+
+	for (tok = strtok_r(str, ", ", &tmp);
+			tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		if (sort_dimension__add(tok) < 0) {
+			error("Unknown --sort key: `%s'", tok);
+			usage_with_options(annotate_usage, options);
+		}
+	}
+
+	free(str);
+}
+
+int cmd_annotate(int argc, const char **argv, const char *prefix)
+{
+	symbol__init();
+
+	page_size = getpagesize();
+
+	argc = parse_options(argc, argv, options, annotate_usage, 0);
+
+	setup_sorting();
+
+	if (argc) {
+		/*
+		 * Special case: if there's an argument left then assume tha
+		 * it's a symbol filter:
+		 */
+		if (argc > 1)
+			usage_with_options(annotate_usage, options);
+
+		sym_hist_filter = argv[0];
+	}
+
+	if (!sym_hist_filter)
+		usage_with_options(annotate_usage, options);
+
+	setup_pager();
+
+	return __cmd_annotate();
+}
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
new file mode 100644
index 000000000000..0f32dc3f3c4c
--- /dev/null
+++ b/tools/perf/builtin-help.c
@@ -0,0 +1,461 @@
+/*
+ * builtin-help.c
+ *
+ * Builtin help command
+ */
+#include "util/cache.h"
+#include "builtin.h"
+#include "util/exec_cmd.h"
+#include "common-cmds.h"
+#include "util/parse-options.h"
+#include "util/run-command.h"
+#include "util/help.h"
+
+static struct man_viewer_list {
+	struct man_viewer_list *next;
+	char name[FLEX_ARRAY];
+} *man_viewer_list;
+
+static struct man_viewer_info_list {
+	struct man_viewer_info_list *next;
+	const char *info;
+	char name[FLEX_ARRAY];
+} *man_viewer_info_list;
+
+enum help_format {
+	HELP_FORMAT_MAN,
+	HELP_FORMAT_INFO,
+	HELP_FORMAT_WEB,
+};
+
+static int show_all = 0;
+static enum help_format help_format = HELP_FORMAT_MAN;
+static struct option builtin_help_options[] = {
+	OPT_BOOLEAN('a', "all", &show_all, "print all available commands"),
+	OPT_SET_INT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN),
+	OPT_SET_INT('w', "web", &help_format, "show manual in web browser",
+			HELP_FORMAT_WEB),
+	OPT_SET_INT('i', "info", &help_format, "show info page",
+			HELP_FORMAT_INFO),
+	OPT_END(),
+};
+
+static const char * const builtin_help_usage[] = {
+	"perf help [--all] [--man|--web|--info] [command]",
+	NULL
+};
+
+static enum help_format parse_help_format(const char *format)
+{
+	if (!strcmp(format, "man"))
+		return HELP_FORMAT_MAN;
+	if (!strcmp(format, "info"))
+		return HELP_FORMAT_INFO;
+	if (!strcmp(format, "web") || !strcmp(format, "html"))
+		return HELP_FORMAT_WEB;
+	die("unrecognized help format '%s'", format);
+}
+
+static const char *get_man_viewer_info(const char *name)
+{
+	struct man_viewer_info_list *viewer;
+
+	for (viewer = man_viewer_info_list; viewer; viewer = viewer->next)
+	{
+		if (!strcasecmp(name, viewer->name))
+			return viewer->info;
+	}
+	return NULL;
+}
+
+static int check_emacsclient_version(void)
+{
+	struct strbuf buffer = STRBUF_INIT;
+	struct child_process ec_process;
+	const char *argv_ec[] = { "emacsclient", "--version", NULL };
+	int version;
+
+	/* emacsclient prints its version number on stderr */
+	memset(&ec_process, 0, sizeof(ec_process));
+	ec_process.argv = argv_ec;
+	ec_process.err = -1;
+	ec_process.stdout_to_stderr = 1;
+	if (start_command(&ec_process)) {
+		fprintf(stderr, "Failed to start emacsclient.\n");
+		return -1;
+	}
+	strbuf_read(&buffer, ec_process.err, 20);
+	close(ec_process.err);
+
+	/*
+	 * Don't bother checking return value, because "emacsclient --version"
+	 * seems to always exits with code 1.
+	 */
+	finish_command(&ec_process);
+
+	if (prefixcmp(buffer.buf, "emacsclient")) {
+		fprintf(stderr, "Failed to parse emacsclient version.\n");
+		strbuf_release(&buffer);
+		return -1;
+	}
+
+	strbuf_remove(&buffer, 0, strlen("emacsclient"));
+	version = atoi(buffer.buf);
+
+	if (version < 22) {
+		fprintf(stderr,
+			"emacsclient version '%d' too old (< 22).\n",
+			version);
+		strbuf_release(&buffer);
+		return -1;
+	}
+
+	strbuf_release(&buffer);
+	return 0;
+}
+
+static void exec_woman_emacs(const char* path, const char *page)
+{
+	if (!check_emacsclient_version()) {
+		/* This works only with emacsclient version >= 22. */
+		struct strbuf man_page = STRBUF_INIT;
+
+		if (!path)
+			path = "emacsclient";
+		strbuf_addf(&man_page, "(woman \"%s\")", page);
+		execlp(path, "emacsclient", "-e", man_page.buf, NULL);
+		warning("failed to exec '%s': %s", path, strerror(errno));
+	}
+}
+
+static void exec_man_konqueror(const char* path, const char *page)
+{
+	const char *display = getenv("DISPLAY");
+	if (display && *display) {
+		struct strbuf man_page = STRBUF_INIT;
+		const char *filename = "kfmclient";
+
+		/* It's simpler to launch konqueror using kfmclient. */
+		if (path) {
+			const char *file = strrchr(path, '/');
+			if (file && !strcmp(file + 1, "konqueror")) {
+				char *new = strdup(path);
+				char *dest = strrchr(new, '/');
+
+				/* strlen("konqueror") == strlen("kfmclient") */
+				strcpy(dest + 1, "kfmclient");
+				path = new;
+			}
+			if (file)
+				filename = file;
+		} else
+			path = "kfmclient";
+		strbuf_addf(&man_page, "man:%s(1)", page);
+		execlp(path, filename, "newTab", man_page.buf, NULL);
+		warning("failed to exec '%s': %s", path, strerror(errno));
+	}
+}
+
+static void exec_man_man(const char* path, const char *page)
+{
+	if (!path)
+		path = "man";
+	execlp(path, "man", page, NULL);
+	warning("failed to exec '%s': %s", path, strerror(errno));
+}
+
+static void exec_man_cmd(const char *cmd, const char *page)
+{
+	struct strbuf shell_cmd = STRBUF_INIT;
+	strbuf_addf(&shell_cmd, "%s %s", cmd, page);
+	execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL);
+	warning("failed to exec '%s': %s", cmd, strerror(errno));
+}
+
+static void add_man_viewer(const char *name)
+{
+	struct man_viewer_list **p = &man_viewer_list;
+	size_t len = strlen(name);
+
+	while (*p)
+		p = &((*p)->next);
+	*p = calloc(1, (sizeof(**p) + len + 1));
+	strncpy((*p)->name, name, len);
+}
+
+static int supported_man_viewer(const char *name, size_t len)
+{
+	return (!strncasecmp("man", name, len) ||
+		!strncasecmp("woman", name, len) ||
+		!strncasecmp("konqueror", name, len));
+}
+
+static void do_add_man_viewer_info(const char *name,
+				   size_t len,
+				   const char *value)
+{
+	struct man_viewer_info_list *new = calloc(1, sizeof(*new) + len + 1);
+
+	strncpy(new->name, name, len);
+	new->info = strdup(value);
+	new->next = man_viewer_info_list;
+	man_viewer_info_list = new;
+}
+
+static int add_man_viewer_path(const char *name,
+			       size_t len,
+			       const char *value)
+{
+	if (supported_man_viewer(name, len))
+		do_add_man_viewer_info(name, len, value);
+	else
+		warning("'%s': path for unsupported man viewer.\n"
+			"Please consider using 'man.<tool>.cmd' instead.",
+			name);
+
+	return 0;
+}
+
+static int add_man_viewer_cmd(const char *name,
+			      size_t len,
+			      const char *value)
+{
+	if (supported_man_viewer(name, len))
+		warning("'%s': cmd for supported man viewer.\n"
+			"Please consider using 'man.<tool>.path' instead.",
+			name);
+	else
+		do_add_man_viewer_info(name, len, value);
+
+	return 0;
+}
+
+static int add_man_viewer_info(const char *var, const char *value)
+{
+	const char *name = var + 4;
+	const char *subkey = strrchr(name, '.');
+
+	if (!subkey)
+		return error("Config with no key for man viewer: %s", name);
+
+	if (!strcmp(subkey, ".path")) {
+		if (!value)
+			return config_error_nonbool(var);
+		return add_man_viewer_path(name, subkey - name, value);
+	}
+	if (!strcmp(subkey, ".cmd")) {
+		if (!value)
+			return config_error_nonbool(var);
+		return add_man_viewer_cmd(name, subkey - name, value);
+	}
+
+	warning("'%s': unsupported man viewer sub key.", subkey);
+	return 0;
+}
+
+static int perf_help_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "help.format")) {
+		if (!value)
+			return config_error_nonbool(var);
+		help_format = parse_help_format(value);
+		return 0;
+	}
+	if (!strcmp(var, "man.viewer")) {
+		if (!value)
+			return config_error_nonbool(var);
+		add_man_viewer(value);
+		return 0;
+	}
+	if (!prefixcmp(var, "man."))
+		return add_man_viewer_info(var, value);
+
+	return perf_default_config(var, value, cb);
+}
+
+static struct cmdnames main_cmds, other_cmds;
+
+void list_common_cmds_help(void)
+{
+	int i, longest = 0;
+
+	for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
+		if (longest < strlen(common_cmds[i].name))
+			longest = strlen(common_cmds[i].name);
+	}
+
+	puts(" The most commonly used perf commands are:");
+	for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
+		printf("   %s   ", common_cmds[i].name);
+		mput_char(' ', longest - strlen(common_cmds[i].name));
+		puts(common_cmds[i].help);
+	}
+}
+
+static int is_perf_command(const char *s)
+{
+	return is_in_cmdlist(&main_cmds, s) ||
+		is_in_cmdlist(&other_cmds, s);
+}
+
+static const char *prepend(const char *prefix, const char *cmd)
+{
+	size_t pre_len = strlen(prefix);
+	size_t cmd_len = strlen(cmd);
+	char *p = malloc(pre_len + cmd_len + 1);
+	memcpy(p, prefix, pre_len);
+	strcpy(p + pre_len, cmd);
+	return p;
+}
+
+static const char *cmd_to_page(const char *perf_cmd)
+{
+	if (!perf_cmd)
+		return "perf";
+	else if (!prefixcmp(perf_cmd, "perf"))
+		return perf_cmd;
+	else if (is_perf_command(perf_cmd))
+		return prepend("perf-", perf_cmd);
+	else
+		return prepend("perf-", perf_cmd);
+}
+
+static void setup_man_path(void)
+{
+	struct strbuf new_path = STRBUF_INIT;
+	const char *old_path = getenv("MANPATH");
+
+	/* We should always put ':' after our path. If there is no
+	 * old_path, the ':' at the end will let 'man' to try
+	 * system-wide paths after ours to find the manual page. If
+	 * there is old_path, we need ':' as delimiter. */
+	strbuf_addstr(&new_path, system_path(PERF_MAN_PATH));
+	strbuf_addch(&new_path, ':');
+	if (old_path)
+		strbuf_addstr(&new_path, old_path);
+
+	setenv("MANPATH", new_path.buf, 1);
+
+	strbuf_release(&new_path);
+}
+
+static void exec_viewer(const char *name, const char *page)
+{
+	const char *info = get_man_viewer_info(name);
+
+	if (!strcasecmp(name, "man"))
+		exec_man_man(info, page);
+	else if (!strcasecmp(name, "woman"))
+		exec_woman_emacs(info, page);
+	else if (!strcasecmp(name, "konqueror"))
+		exec_man_konqueror(info, page);
+	else if (info)
+		exec_man_cmd(info, page);
+	else
+		warning("'%s': unknown man viewer.", name);
+}
+
+static void show_man_page(const char *perf_cmd)
+{
+	struct man_viewer_list *viewer;
+	const char *page = cmd_to_page(perf_cmd);
+	const char *fallback = getenv("PERF_MAN_VIEWER");
+
+	setup_man_path();
+	for (viewer = man_viewer_list; viewer; viewer = viewer->next)
+	{
+		exec_viewer(viewer->name, page); /* will return when unable */
+	}
+	if (fallback)
+		exec_viewer(fallback, page);
+	exec_viewer("man", page);
+	die("no man viewer handled the request");
+}
+
+static void show_info_page(const char *perf_cmd)
+{
+	const char *page = cmd_to_page(perf_cmd);
+	setenv("INFOPATH", system_path(PERF_INFO_PATH), 1);
+	execlp("info", "info", "perfman", page, NULL);
+}
+
+static void get_html_page_path(struct strbuf *page_path, const char *page)
+{
+	struct stat st;
+	const char *html_path = system_path(PERF_HTML_PATH);
+
+	/* Check that we have a perf documentation directory. */
+	if (stat(mkpath("%s/perf.html", html_path), &st)
+	    || !S_ISREG(st.st_mode))
+		die("'%s': not a documentation directory.", html_path);
+
+	strbuf_init(page_path, 0);
+	strbuf_addf(page_path, "%s/%s.html", html_path, page);
+}
+
+/*
+ * If open_html is not defined in a platform-specific way (see for
+ * example compat/mingw.h), we use the script web--browse to display
+ * HTML.
+ */
+#ifndef open_html
+static void open_html(const char *path)
+{
+	execl_perf_cmd("web--browse", "-c", "help.browser", path, NULL);
+}
+#endif
+
+static void show_html_page(const char *perf_cmd)
+{
+	const char *page = cmd_to_page(perf_cmd);
+	struct strbuf page_path; /* it leaks but we exec bellow */
+
+	get_html_page_path(&page_path, page);
+
+	open_html(page_path.buf);
+}
+
+int cmd_help(int argc, const char **argv, const char *prefix)
+{
+	const char *alias;
+	load_command_list("perf-", &main_cmds, &other_cmds);
+
+	perf_config(perf_help_config, NULL);
+
+	argc = parse_options(argc, argv, builtin_help_options,
+			builtin_help_usage, 0);
+
+	if (show_all) {
+		printf("\n usage: %s\n\n", perf_usage_string);
+		list_commands("perf commands", &main_cmds, &other_cmds);
+		printf(" %s\n\n", perf_more_info_string);
+		return 0;
+	}
+
+	if (!argv[0]) {
+		printf("\n usage: %s\n\n", perf_usage_string);
+		list_common_cmds_help();
+		printf("\n %s\n\n", perf_more_info_string);
+		return 0;
+	}
+
+	alias = alias_lookup(argv[0]);
+	if (alias && !is_perf_command(argv[0])) {
+		printf("`perf %s' is aliased to `%s'\n", argv[0], alias);
+		return 0;
+	}
+
+	switch (help_format) {
+	case HELP_FORMAT_MAN:
+		show_man_page(argv[0]);
+		break;
+	case HELP_FORMAT_INFO:
+		show_info_page(argv[0]);
+		break;
+	case HELP_FORMAT_WEB:
+		show_html_page(argv[0]);
+		break;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
new file mode 100644
index 000000000000..fe60e37c96ef
--- /dev/null
+++ b/tools/perf/builtin-list.c
@@ -0,0 +1,20 @@
+/*
+ * builtin-list.c
+ *
+ * Builtin list command: list all event types
+ *
+ * Copyright (C) 2009, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright (C) 2008-2009, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ */
+#include "builtin.h"
+
+#include "perf.h"
+
+#include "util/parse-options.h"
+#include "util/parse-events.h"
+
+int cmd_list(int argc, const char **argv, const char *prefix)
+{
+	print_events();
+	return 0;
+}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
new file mode 100644
index 000000000000..29259e74dcfa
--- /dev/null
+++ b/tools/perf/builtin-record.c
@@ -0,0 +1,582 @@
+/*
+ * builtin-record.c
+ *
+ * Builtin record command: Record the profile of a workload
+ * (or a CPU, or a PID) into the perf.data output file - for
+ * later analysis via perf report.
+ */
+#include "builtin.h"
+
+#include "perf.h"
+
+#include "util/util.h"
+#include "util/parse-options.h"
+#include "util/parse-events.h"
+#include "util/string.h"
+
+#include <unistd.h>
+#include <sched.h>
+
+#define ALIGN(x, a)		__ALIGN_MASK(x, (typeof(x))(a)-1)
+#define __ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
+
+static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+
+static long			default_interval		= 100000;
+
+static int			nr_cpus				= 0;
+static unsigned int		page_size;
+static unsigned int		mmap_pages			= 128;
+static int			freq				= 0;
+static int			output;
+static const char		*output_name			= "perf.data";
+static int			group				= 0;
+static unsigned int		realtime_prio			= 0;
+static int			system_wide			= 0;
+static pid_t			target_pid			= -1;
+static int			inherit				= 1;
+static int			force				= 0;
+static int			append_file			= 0;
+static int			verbose				= 0;
+
+static long			samples;
+static struct timeval		last_read;
+static struct timeval		this_read;
+
+static __u64			bytes_written;
+
+static struct pollfd		event_array[MAX_NR_CPUS * MAX_COUNTERS];
+
+static int			nr_poll;
+static int			nr_cpu;
+
+struct mmap_event {
+	struct perf_event_header	header;
+	__u32				pid;
+	__u32				tid;
+	__u64				start;
+	__u64				len;
+	__u64				pgoff;
+	char				filename[PATH_MAX];
+};
+
+struct comm_event {
+	struct perf_event_header	header;
+	__u32				pid;
+	__u32				tid;
+	char				comm[16];
+};
+
+
+struct mmap_data {
+	int			counter;
+	void			*base;
+	unsigned int		mask;
+	unsigned int		prev;
+};
+
+static struct mmap_data		mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+
+static unsigned int mmap_read_head(struct mmap_data *md)
+{
+	struct perf_counter_mmap_page *pc = md->base;
+	int head;
+
+	head = pc->data_head;
+	rmb();
+
+	return head;
+}
+
+static void mmap_read(struct mmap_data *md)
+{
+	unsigned int head = mmap_read_head(md);
+	unsigned int old = md->prev;
+	unsigned char *data = md->base + page_size;
+	unsigned long size;
+	void *buf;
+	int diff;
+
+	gettimeofday(&this_read, NULL);
+
+	/*
+	 * If we're further behind than half the buffer, there's a chance
+	 * the writer will bite our tail and mess up the samples under us.
+	 *
+	 * If we somehow ended up ahead of the head, we got messed up.
+	 *
+	 * In either case, truncate and restart at head.
+	 */
+	diff = head - old;
+	if (diff > md->mask / 2 || diff < 0) {
+		struct timeval iv;
+		unsigned long msecs;
+
+		timersub(&this_read, &last_read, &iv);
+		msecs = iv.tv_sec*1000 + iv.tv_usec/1000;
+
+		fprintf(stderr, "WARNING: failed to keep up with mmap data."
+				"  Last read %lu msecs ago.\n", msecs);
+
+		/*
+		 * head points to a known good entry, start there.
+		 */
+		old = head;
+	}
+
+	last_read = this_read;
+
+	if (old != head)
+		samples++;
+
+	size = head - old;
+
+	if ((old & md->mask) + size != (head & md->mask)) {
+		buf = &data[old & md->mask];
+		size = md->mask + 1 - (old & md->mask);
+		old += size;
+
+		while (size) {
+			int ret = write(output, buf, size);
+
+			if (ret < 0)
+				die("failed to write");
+
+			size -= ret;
+			buf += ret;
+
+			bytes_written += ret;
+		}
+	}
+
+	buf = &data[old & md->mask];
+	size = head - old;
+	old += size;
+
+	while (size) {
+		int ret = write(output, buf, size);
+
+		if (ret < 0)
+			die("failed to write");
+
+		size -= ret;
+		buf += ret;
+
+		bytes_written += ret;
+	}
+
+	md->prev = old;
+}
+
+static volatile int done = 0;
+static volatile int signr = -1;
+
+static void sig_handler(int sig)
+{
+	done = 1;
+	signr = sig;
+}
+
+static void sig_atexit(void)
+{
+	if (signr == -1)
+		return;
+
+	signal(signr, SIG_DFL);
+	kill(getpid(), signr);
+}
+
+static void pid_synthesize_comm_event(pid_t pid, int full)
+{
+	struct comm_event comm_ev;
+	char filename[PATH_MAX];
+	char bf[BUFSIZ];
+	int fd, ret;
+	size_t size;
+	char *field, *sep;
+	DIR *tasks;
+	struct dirent dirent, *next;
+
+	snprintf(filename, sizeof(filename), "/proc/%d/stat", pid);
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0) {
+		fprintf(stderr, "couldn't open %s\n", filename);
+		exit(EXIT_FAILURE);
+	}
+	if (read(fd, bf, sizeof(bf)) < 0) {
+		fprintf(stderr, "couldn't read %s\n", filename);
+		exit(EXIT_FAILURE);
+	}
+	close(fd);
+
+	/* 9027 (cat) R 6747 9027 6747 34816 9027 ... */
+	memset(&comm_ev, 0, sizeof(comm_ev));
+	field = strchr(bf, '(');
+	if (field == NULL)
+		goto out_failure;
+	sep = strchr(++field, ')');
+	if (sep == NULL)
+		goto out_failure;
+	size = sep - field;
+	memcpy(comm_ev.comm, field, size++);
+
+	comm_ev.pid = pid;
+	comm_ev.header.type = PERF_EVENT_COMM;
+	size = ALIGN(size, sizeof(__u64));
+	comm_ev.header.size = sizeof(comm_ev) - (sizeof(comm_ev.comm) - size);
+
+	if (!full) {
+		comm_ev.tid = pid;
+
+		ret = write(output, &comm_ev, comm_ev.header.size);
+		if (ret < 0) {
+			perror("failed to write");
+			exit(-1);
+		}
+		return;
+	}
+
+	snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
+
+	tasks = opendir(filename);
+	while (!readdir_r(tasks, &dirent, &next) && next) {
+		char *end;
+		pid = strtol(dirent.d_name, &end, 10);
+		if (*end)
+			continue;
+
+		comm_ev.tid = pid;
+
+		ret = write(output, &comm_ev, comm_ev.header.size);
+		if (ret < 0) {
+			perror("failed to write");
+			exit(-1);
+		}
+	}
+	closedir(tasks);
+	return;
+
+out_failure:
+	fprintf(stderr, "couldn't get COMM and pgid, malformed %s\n",
+		filename);
+	exit(EXIT_FAILURE);
+}
+
+static void pid_synthesize_mmap_samples(pid_t pid)
+{
+	char filename[PATH_MAX];
+	FILE *fp;
+
+	snprintf(filename, sizeof(filename), "/proc/%d/maps", pid);
+
+	fp = fopen(filename, "r");
+	if (fp == NULL) {
+		fprintf(stderr, "couldn't open %s\n", filename);
+		exit(EXIT_FAILURE);
+	}
+	while (1) {
+		char bf[BUFSIZ], *pbf = bf;
+		struct mmap_event mmap_ev = {
+			.header.type = PERF_EVENT_MMAP,
+		};
+		int n;
+		size_t size;
+		if (fgets(bf, sizeof(bf), fp) == NULL)
+			break;
+
+		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
+		n = hex2u64(pbf, &mmap_ev.start);
+		if (n < 0)
+			continue;
+		pbf += n + 1;
+		n = hex2u64(pbf, &mmap_ev.len);
+		if (n < 0)
+			continue;
+		pbf += n + 3;
+		if (*pbf == 'x') { /* vm_exec */
+			char *execname = strrchr(bf, ' ');
+
+			if (execname == NULL || execname[1] != '/')
+				continue;
+
+			execname += 1;
+			size = strlen(execname);
+			execname[size - 1] = '\0'; /* Remove \n */
+			memcpy(mmap_ev.filename, execname, size);
+			size = ALIGN(size, sizeof(__u64));
+			mmap_ev.len -= mmap_ev.start;
+			mmap_ev.header.size = (sizeof(mmap_ev) -
+					       (sizeof(mmap_ev.filename) - size));
+			mmap_ev.pid = pid;
+			mmap_ev.tid = pid;
+
+			if (write(output, &mmap_ev, mmap_ev.header.size) < 0) {
+				perror("failed to write");
+				exit(-1);
+			}
+		}
+	}
+
+	fclose(fp);
+}
+
+static void synthesize_samples(void)
+{
+	DIR *proc;
+	struct dirent dirent, *next;
+
+	proc = opendir("/proc");
+
+	while (!readdir_r(proc, &dirent, &next) && next) {
+		char *end;
+		pid_t pid;
+
+		pid = strtol(dirent.d_name, &end, 10);
+		if (*end) /* only interested in proper numerical dirents */
+			continue;
+
+		pid_synthesize_comm_event(pid, 1);
+		pid_synthesize_mmap_samples(pid);
+	}
+
+	closedir(proc);
+}
+
+static int group_fd;
+
+static void create_counter(int counter, int cpu, pid_t pid)
+{
+	struct perf_counter_attr *attr = attrs + counter;
+	int track = 1;
+
+	attr->sample_type	= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+	if (freq) {
+		attr->sample_type	|= PERF_SAMPLE_PERIOD;
+		attr->freq		= 1;
+		attr->sample_freq	= freq;
+	}
+	attr->mmap		= track;
+	attr->comm		= track;
+	attr->inherit		= (cpu < 0) && inherit;
+	attr->disabled		= 1;
+
+	track = 0; /* only the first counter needs these */
+
+try_again:
+	fd[nr_cpu][counter] = sys_perf_counter_open(attr, pid, cpu, group_fd, 0);
+
+	if (fd[nr_cpu][counter] < 0) {
+		int err = errno;
+
+		if (err == EPERM)
+			die("Permission error - are you root?\n");
+
+		/*
+		 * If it's cycles then fall back to hrtimer
+		 * based cpu-clock-tick sw counter, which
+		 * is always available even if no PMU support:
+		 */
+		if (attr->type == PERF_TYPE_HARDWARE
+			&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+
+			if (verbose)
+				warning(" ... trying to fall back to cpu-clock-ticks\n");
+			attr->type = PERF_TYPE_SOFTWARE;
+			attr->config = PERF_COUNT_SW_CPU_CLOCK;
+			goto try_again;
+		}
+		printf("\n");
+		error("perfcounter syscall returned with %d (%s)\n",
+			fd[nr_cpu][counter], strerror(err));
+		die("No CONFIG_PERF_COUNTERS=y kernel support configured?\n");
+		exit(-1);
+	}
+
+	assert(fd[nr_cpu][counter] >= 0);
+	fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK);
+
+	/*
+	 * First counter acts as the group leader:
+	 */
+	if (group && group_fd == -1)
+		group_fd = fd[nr_cpu][counter];
+
+	event_array[nr_poll].fd = fd[nr_cpu][counter];
+	event_array[nr_poll].events = POLLIN;
+	nr_poll++;
+
+	mmap_array[nr_cpu][counter].counter = counter;
+	mmap_array[nr_cpu][counter].prev = 0;
+	mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1;
+	mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
+			PROT_READ, MAP_SHARED, fd[nr_cpu][counter], 0);
+	if (mmap_array[nr_cpu][counter].base == MAP_FAILED) {
+		error("failed to mmap with %d (%s)\n", errno, strerror(errno));
+		exit(-1);
+	}
+
+	ioctl(fd[nr_cpu][counter], PERF_COUNTER_IOC_ENABLE);
+}
+
+static void open_counters(int cpu, pid_t pid)
+{
+	int counter;
+
+	if (pid > 0) {
+		pid_synthesize_comm_event(pid, 0);
+		pid_synthesize_mmap_samples(pid);
+	}
+
+	group_fd = -1;
+	for (counter = 0; counter < nr_counters; counter++)
+		create_counter(counter, cpu, pid);
+
+	nr_cpu++;
+}
+
+static int __cmd_record(int argc, const char **argv)
+{
+	int i, counter;
+	struct stat st;
+	pid_t pid;
+	int flags;
+	int ret;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	assert(nr_cpus <= MAX_NR_CPUS);
+	assert(nr_cpus >= 0);
+
+	if (!stat(output_name, &st) && !force && !append_file) {
+		fprintf(stderr, "Error, output file %s exists, use -A to append or -f to overwrite.\n",
+				output_name);
+		exit(-1);
+	}
+
+	flags = O_CREAT|O_RDWR;
+	if (append_file)
+		flags |= O_APPEND;
+	else
+		flags |= O_TRUNC;
+
+	output = open(output_name, flags, S_IRUSR|S_IWUSR);
+	if (output < 0) {
+		perror("failed to create output file");
+		exit(-1);
+	}
+
+	if (!system_wide) {
+		open_counters(-1, target_pid != -1 ? target_pid : getpid());
+	} else for (i = 0; i < nr_cpus; i++)
+		open_counters(i, target_pid);
+
+	atexit(sig_atexit);
+	signal(SIGCHLD, sig_handler);
+	signal(SIGINT, sig_handler);
+
+	if (target_pid == -1 && argc) {
+		pid = fork();
+		if (pid < 0)
+			perror("failed to fork");
+
+		if (!pid) {
+			if (execvp(argv[0], (char **)argv)) {
+				perror(argv[0]);
+				exit(-1);
+			}
+		}
+	}
+
+	if (realtime_prio) {
+		struct sched_param param;
+
+		param.sched_priority = realtime_prio;
+		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
+			printf("Could not set realtime priority.\n");
+			exit(-1);
+		}
+	}
+
+	if (system_wide)
+		synthesize_samples();
+
+	while (!done) {
+		int hits = samples;
+
+		for (i = 0; i < nr_cpu; i++) {
+			for (counter = 0; counter < nr_counters; counter++)
+				mmap_read(&mmap_array[i][counter]);
+		}
+
+		if (hits == samples)
+			ret = poll(event_array, nr_poll, 100);
+	}
+
+	/*
+	 * Approximate RIP event size: 24 bytes.
+	 */
+	fprintf(stderr,
+		"[ perf record: Captured and wrote %.3f MB %s (~%lld samples) ]\n",
+		(double)bytes_written / 1024.0 / 1024.0,
+		output_name,
+		bytes_written / 24);
+
+	return 0;
+}
+
+static const char * const record_usage[] = {
+	"perf record [<options>] [<command>]",
+	"perf record [<options>] -- <command> [<options>]",
+	NULL
+};
+
+static const struct option options[] = {
+	OPT_CALLBACK('e', "event", NULL, "event",
+		     "event selector. use 'perf list' to list available events",
+		     parse_events),
+	OPT_INTEGER('p', "pid", &target_pid,
+		    "record events on existing pid"),
+	OPT_INTEGER('r', "realtime", &realtime_prio,
+		    "collect data with this RT SCHED_FIFO priority"),
+	OPT_BOOLEAN('a', "all-cpus", &system_wide,
+			    "system-wide collection from all CPUs"),
+	OPT_BOOLEAN('A', "append", &append_file,
+			    "append to the output file to do incremental profiling"),
+	OPT_BOOLEAN('f', "force", &force,
+			"overwrite existing data file"),
+	OPT_LONG('c', "count", &default_interval,
+		    "event period to sample"),
+	OPT_STRING('o', "output", &output_name, "file",
+		    "output file name"),
+	OPT_BOOLEAN('i', "inherit", &inherit,
+		    "child tasks inherit counters"),
+	OPT_INTEGER('F', "freq", &freq,
+		    "profile at this frequency"),
+	OPT_INTEGER('m', "mmap-pages", &mmap_pages,
+		    "number of mmap data pages"),
+	OPT_BOOLEAN('v', "verbose", &verbose,
+		    "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+};
+
+int cmd_record(int argc, const char **argv, const char *prefix)
+{
+	int counter;
+
+	argc = parse_options(argc, argv, options, record_usage, 0);
+	if (!argc && target_pid == -1 && !system_wide)
+		usage_with_options(record_usage, options);
+
+	if (!nr_counters)
+		nr_counters = 1;
+
+	for (counter = 0; counter < nr_counters; counter++) {
+		if (attrs[counter].sample_period)
+			continue;
+
+		attrs[counter].sample_period = default_interval;
+	}
+
+	return __cmd_record(argc, argv);
+}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
new file mode 100644
index 000000000000..82fa93b4db99
--- /dev/null
+++ b/tools/perf/builtin-report.c
@@ -0,0 +1,1316 @@
+/*
+ * builtin-report.c
+ *
+ * Builtin report command: Analyze the perf.data input file,
+ * look up and read DSOs and symbol information and display
+ * a histogram of results, along various sorting keys.
+ */
+#include "builtin.h"
+
+#include "util/util.h"
+
+#include "util/color.h"
+#include "util/list.h"
+#include "util/cache.h"
+#include "util/rbtree.h"
+#include "util/symbol.h"
+#include "util/string.h"
+
+#include "perf.h"
+
+#include "util/parse-options.h"
+#include "util/parse-events.h"
+
+#define SHOW_KERNEL	1
+#define SHOW_USER	2
+#define SHOW_HV		4
+
+static char		const *input_name = "perf.data";
+static char		*vmlinux = NULL;
+
+static char		default_sort_order[] = "comm,dso";
+static char		*sort_order = default_sort_order;
+
+static int		input;
+static int		show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV;
+
+static int		dump_trace = 0;
+#define dprintf(x...)	do { if (dump_trace) printf(x); } while (0)
+
+static int		verbose;
+static int		full_paths;
+
+static unsigned long	page_size;
+static unsigned long	mmap_window = 32;
+
+struct ip_event {
+	struct perf_event_header header;
+	__u64 ip;
+	__u32 pid, tid;
+	__u64 period;
+};
+
+struct mmap_event {
+	struct perf_event_header header;
+	__u32 pid, tid;
+	__u64 start;
+	__u64 len;
+	__u64 pgoff;
+	char filename[PATH_MAX];
+};
+
+struct comm_event {
+	struct perf_event_header header;
+	__u32 pid, tid;
+	char comm[16];
+};
+
+struct fork_event {
+	struct perf_event_header header;
+	__u32 pid, ppid;
+};
+
+struct period_event {
+	struct perf_event_header header;
+	__u64 time;
+	__u64 id;
+	__u64 sample_period;
+};
+
+typedef union event_union {
+	struct perf_event_header	header;
+	struct ip_event			ip;
+	struct mmap_event		mmap;
+	struct comm_event		comm;
+	struct fork_event		fork;
+	struct period_event		period;
+} event_t;
+
+static LIST_HEAD(dsos);
+static struct dso *kernel_dso;
+static struct dso *vdso;
+
+static void dsos__add(struct dso *dso)
+{
+	list_add_tail(&dso->node, &dsos);
+}
+
+static struct dso *dsos__find(const char *name)
+{
+	struct dso *pos;
+
+	list_for_each_entry(pos, &dsos, node)
+		if (strcmp(pos->name, name) == 0)
+			return pos;
+	return NULL;
+}
+
+static struct dso *dsos__findnew(const char *name)
+{
+	struct dso *dso = dsos__find(name);
+	int nr;
+
+	if (dso)
+		return dso;
+
+	dso = dso__new(name, 0);
+	if (!dso)
+		goto out_delete_dso;
+
+	nr = dso__load(dso, NULL, verbose);
+	if (nr < 0) {
+		if (verbose)
+			fprintf(stderr, "Failed to open: %s\n", name);
+		goto out_delete_dso;
+	}
+	if (!nr && verbose) {
+		fprintf(stderr,
+		"No symbols found in: %s, maybe install a debug package?\n",
+				name);
+	}
+
+	dsos__add(dso);
+
+	return dso;
+
+out_delete_dso:
+	dso__delete(dso);
+	return NULL;
+}
+
+static void dsos__fprintf(FILE *fp)
+{
+	struct dso *pos;
+
+	list_for_each_entry(pos, &dsos, node)
+		dso__fprintf(pos, fp);
+}
+
+static struct symbol *vdso__find_symbol(struct dso *dso, __u64 ip)
+{
+	return dso__find_symbol(kernel_dso, ip);
+}
+
+static int load_kernel(void)
+{
+	int err;
+
+	kernel_dso = dso__new("[kernel]", 0);
+	if (!kernel_dso)
+		return -1;
+
+	err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose);
+	if (err) {
+		dso__delete(kernel_dso);
+		kernel_dso = NULL;
+	} else
+		dsos__add(kernel_dso);
+
+	vdso = dso__new("[vdso]", 0);
+	if (!vdso)
+		return -1;
+
+	vdso->find_symbol = vdso__find_symbol;
+
+	dsos__add(vdso);
+
+	return err;
+}
+
+static char __cwd[PATH_MAX];
+static char *cwd = __cwd;
+static int cwdlen;
+
+static int strcommon(const char *pathname)
+{
+	int n = 0;
+
+	while (pathname[n] == cwd[n] && n < cwdlen)
+		++n;
+
+	return n;
+}
+
+struct map {
+	struct list_head node;
+	__u64	 start;
+	__u64	 end;
+	__u64	 pgoff;
+	__u64	 (*map_ip)(struct map *, __u64);
+	struct dso	 *dso;
+};
+
+static __u64 map__map_ip(struct map *map, __u64 ip)
+{
+	return ip - map->start + map->pgoff;
+}
+
+static __u64 vdso__map_ip(struct map *map, __u64 ip)
+{
+	return ip;
+}
+
+static inline int is_anon_memory(const char *filename)
+{
+     return strcmp(filename, "//anon") == 0;
+}
+
+static struct map *map__new(struct mmap_event *event)
+{
+	struct map *self = malloc(sizeof(*self));
+
+	if (self != NULL) {
+		const char *filename = event->filename;
+		char newfilename[PATH_MAX];
+		int anon;
+
+		if (cwd) {
+			int n = strcommon(filename);
+
+			if (n == cwdlen) {
+				snprintf(newfilename, sizeof(newfilename),
+					 ".%s", filename + n);
+				filename = newfilename;
+			}
+		}
+
+		anon = is_anon_memory(filename);
+
+		if (anon) {
+			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", event->pid);
+			filename = newfilename;
+		}
+
+		self->start = event->start;
+		self->end   = event->start + event->len;
+		self->pgoff = event->pgoff;
+
+		self->dso = dsos__findnew(filename);
+		if (self->dso == NULL)
+			goto out_delete;
+
+		if (self->dso == vdso || anon)
+			self->map_ip = vdso__map_ip;
+		else
+			self->map_ip = map__map_ip;
+	}
+	return self;
+out_delete:
+	free(self);
+	return NULL;
+}
+
+static struct map *map__clone(struct map *self)
+{
+	struct map *map = malloc(sizeof(*self));
+
+	if (!map)
+		return NULL;
+
+	memcpy(map, self, sizeof(*self));
+
+	return map;
+}
+
+static int map__overlap(struct map *l, struct map *r)
+{
+	if (l->start > r->start) {
+		struct map *t = l;
+		l = r;
+		r = t;
+	}
+
+	if (l->end > r->start)
+		return 1;
+
+	return 0;
+}
+
+static size_t map__fprintf(struct map *self, FILE *fp)
+{
+	return fprintf(fp, " %Lx-%Lx %Lx %s\n",
+		       self->start, self->end, self->pgoff, self->dso->name);
+}
+
+
+struct thread {
+	struct rb_node	 rb_node;
+	struct list_head maps;
+	pid_t		 pid;
+	char		 *comm;
+};
+
+static struct thread *thread__new(pid_t pid)
+{
+	struct thread *self = malloc(sizeof(*self));
+
+	if (self != NULL) {
+		self->pid = pid;
+		self->comm = malloc(32);
+		if (self->comm)
+			snprintf(self->comm, 32, ":%d", self->pid);
+		INIT_LIST_HEAD(&self->maps);
+	}
+
+	return self;
+}
+
+static int thread__set_comm(struct thread *self, const char *comm)
+{
+	if (self->comm)
+		free(self->comm);
+	self->comm = strdup(comm);
+	return self->comm ? 0 : -ENOMEM;
+}
+
+static size_t thread__fprintf(struct thread *self, FILE *fp)
+{
+	struct map *pos;
+	size_t ret = fprintf(fp, "Thread %d %s\n", self->pid, self->comm);
+
+	list_for_each_entry(pos, &self->maps, node)
+		ret += map__fprintf(pos, fp);
+
+	return ret;
+}
+
+
+static struct rb_root threads;
+static struct thread *last_match;
+
+static struct thread *threads__findnew(pid_t pid)
+{
+	struct rb_node **p = &threads.rb_node;
+	struct rb_node *parent = NULL;
+	struct thread *th;
+
+	/*
+	 * Font-end cache - PID lookups come in blocks,
+	 * so most of the time we dont have to look up
+	 * the full rbtree:
+	 */
+	if (last_match && last_match->pid == pid)
+		return last_match;
+
+	while (*p != NULL) {
+		parent = *p;
+		th = rb_entry(parent, struct thread, rb_node);
+
+		if (th->pid == pid) {
+			last_match = th;
+			return th;
+		}
+
+		if (pid < th->pid)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	th = thread__new(pid);
+	if (th != NULL) {
+		rb_link_node(&th->rb_node, parent, p);
+		rb_insert_color(&th->rb_node, &threads);
+		last_match = th;
+	}
+
+	return th;
+}
+
+static void thread__insert_map(struct thread *self, struct map *map)
+{
+	struct map *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, &self->maps, node) {
+		if (map__overlap(pos, map)) {
+			list_del_init(&pos->node);
+			/* XXX leaks dsos */
+			free(pos);
+		}
+	}
+
+	list_add_tail(&map->node, &self->maps);
+}
+
+static int thread__fork(struct thread *self, struct thread *parent)
+{
+	struct map *map;
+
+	if (self->comm)
+		free(self->comm);
+	self->comm = strdup(parent->comm);
+	if (!self->comm)
+		return -ENOMEM;
+
+	list_for_each_entry(map, &parent->maps, node) {
+		struct map *new = map__clone(map);
+		if (!new)
+			return -ENOMEM;
+		thread__insert_map(self, new);
+	}
+
+	return 0;
+}
+
+static struct map *thread__find_map(struct thread *self, __u64 ip)
+{
+	struct map *pos;
+
+	if (self == NULL)
+		return NULL;
+
+	list_for_each_entry(pos, &self->maps, node)
+		if (ip >= pos->start && ip <= pos->end)
+			return pos;
+
+	return NULL;
+}
+
+static size_t threads__fprintf(FILE *fp)
+{
+	size_t ret = 0;
+	struct rb_node *nd;
+
+	for (nd = rb_first(&threads); nd; nd = rb_next(nd)) {
+		struct thread *pos = rb_entry(nd, struct thread, rb_node);
+
+		ret += thread__fprintf(pos, fp);
+	}
+
+	return ret;
+}
+
+/*
+ * histogram, sorted on item, collects counts
+ */
+
+static struct rb_root hist;
+
+struct hist_entry {
+	struct rb_node	 rb_node;
+
+	struct thread	 *thread;
+	struct map	 *map;
+	struct dso	 *dso;
+	struct symbol	 *sym;
+	__u64		 ip;
+	char		 level;
+
+	__u64		 count;
+};
+
+/*
+ * configurable sorting bits
+ */
+
+struct sort_entry {
+	struct list_head list;
+
+	char *header;
+
+	int64_t (*cmp)(struct hist_entry *, struct hist_entry *);
+	int64_t (*collapse)(struct hist_entry *, struct hist_entry *);
+	size_t	(*print)(FILE *fp, struct hist_entry *);
+};
+
+/* --sort pid */
+
+static int64_t
+sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->thread->pid - left->thread->pid;
+}
+
+static size_t
+sort__thread_print(FILE *fp, struct hist_entry *self)
+{
+	return fprintf(fp, "%16s:%5d", self->thread->comm ?: "", self->thread->pid);
+}
+
+static struct sort_entry sort_thread = {
+	.header = "         Command:  Pid",
+	.cmp	= sort__thread_cmp,
+	.print	= sort__thread_print,
+};
+
+/* --sort comm */
+
+static int64_t
+sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->thread->pid - left->thread->pid;
+}
+
+static int64_t
+sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	char *comm_l = left->thread->comm;
+	char *comm_r = right->thread->comm;
+
+	if (!comm_l || !comm_r) {
+		if (!comm_l && !comm_r)
+			return 0;
+		else if (!comm_l)
+			return -1;
+		else
+			return 1;
+	}
+
+	return strcmp(comm_l, comm_r);
+}
+
+static size_t
+sort__comm_print(FILE *fp, struct hist_entry *self)
+{
+	return fprintf(fp, "%16s", self->thread->comm);
+}
+
+static struct sort_entry sort_comm = {
+	.header		= "         Command",
+	.cmp		= sort__comm_cmp,
+	.collapse	= sort__comm_collapse,
+	.print		= sort__comm_print,
+};
+
+/* --sort dso */
+
+static int64_t
+sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct dso *dso_l = left->dso;
+	struct dso *dso_r = right->dso;
+
+	if (!dso_l || !dso_r) {
+		if (!dso_l && !dso_r)
+			return 0;
+		else if (!dso_l)
+			return -1;
+		else
+			return 1;
+	}
+
+	return strcmp(dso_l->name, dso_r->name);
+}
+
+static size_t
+sort__dso_print(FILE *fp, struct hist_entry *self)
+{
+	if (self->dso)
+		return fprintf(fp, "%-25s", self->dso->name);
+
+	return fprintf(fp, "%016llx         ", (__u64)self->ip);
+}
+
+static struct sort_entry sort_dso = {
+	.header = "Shared Object            ",
+	.cmp	= sort__dso_cmp,
+	.print	= sort__dso_print,
+};
+
+/* --sort symbol */
+
+static int64_t
+sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	__u64 ip_l, ip_r;
+
+	if (left->sym == right->sym)
+		return 0;
+
+	ip_l = left->sym ? left->sym->start : left->ip;
+	ip_r = right->sym ? right->sym->start : right->ip;
+
+	return (int64_t)(ip_r - ip_l);
+}
+
+static size_t
+sort__sym_print(FILE *fp, struct hist_entry *self)
+{
+	size_t ret = 0;
+
+	if (verbose)
+		ret += fprintf(fp, "%#018llx  ", (__u64)self->ip);
+
+	if (self->sym) {
+		ret += fprintf(fp, "[%c] %s",
+			self->dso == kernel_dso ? 'k' : '.', self->sym->name);
+	} else {
+		ret += fprintf(fp, "%#016llx", (__u64)self->ip);
+	}
+
+	return ret;
+}
+
+static struct sort_entry sort_sym = {
+	.header = "Symbol",
+	.cmp	= sort__sym_cmp,
+	.print	= sort__sym_print,
+};
+
+static int sort__need_collapse = 0;
+
+struct sort_dimension {
+	char			*name;
+	struct sort_entry	*entry;
+	int			taken;
+};
+
+static struct sort_dimension sort_dimensions[] = {
+	{ .name = "pid",	.entry = &sort_thread,	},
+	{ .name = "comm",	.entry = &sort_comm,	},
+	{ .name = "dso",	.entry = &sort_dso,	},
+	{ .name = "symbol",	.entry = &sort_sym,	},
+};
+
+static LIST_HEAD(hist_entry__sort_list);
+
+static int sort_dimension__add(char *tok)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
+		struct sort_dimension *sd = &sort_dimensions[i];
+
+		if (sd->taken)
+			continue;
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		if (sd->entry->collapse)
+			sort__need_collapse = 1;
+
+		list_add_tail(&sd->entry->list, &hist_entry__sort_list);
+		sd->taken = 1;
+
+		return 0;
+	}
+
+	return -ESRCH;
+}
+
+static int64_t
+hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct sort_entry *se;
+	int64_t cmp = 0;
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		cmp = se->cmp(left, right);
+		if (cmp)
+			break;
+	}
+
+	return cmp;
+}
+
+static int64_t
+hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	struct sort_entry *se;
+	int64_t cmp = 0;
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		int64_t (*f)(struct hist_entry *, struct hist_entry *);
+
+		f = se->collapse ?: se->cmp;
+
+		cmp = f(left, right);
+		if (cmp)
+			break;
+	}
+
+	return cmp;
+}
+
+static size_t
+hist_entry__fprintf(FILE *fp, struct hist_entry *self, __u64 total_samples)
+{
+	struct sort_entry *se;
+	size_t ret;
+
+	if (total_samples) {
+		double percent = self->count * 100.0 / total_samples;
+		char *color = PERF_COLOR_NORMAL;
+
+		/*
+		 * We color high-overhead entries in red, mid-overhead
+		 * entries in green - and keep the low overhead places
+		 * normal:
+		 */
+		if (percent >= 5.0) {
+			color = PERF_COLOR_RED;
+		} else {
+			if (percent >= 0.5)
+				color = PERF_COLOR_GREEN;
+		}
+
+		ret = color_fprintf(fp, color, "   %6.2f%%",
+				(self->count * 100.0) / total_samples);
+	} else
+		ret = fprintf(fp, "%12Ld ", self->count);
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		fprintf(fp, "  ");
+		ret += se->print(fp, self);
+	}
+
+	ret += fprintf(fp, "\n");
+
+	return ret;
+}
+
+/*
+ * collect histogram counts
+ */
+
+static int
+hist_entry__add(struct thread *thread, struct map *map, struct dso *dso,
+		struct symbol *sym, __u64 ip, char level, __u64 count)
+{
+	struct rb_node **p = &hist.rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *he;
+	struct hist_entry entry = {
+		.thread	= thread,
+		.map	= map,
+		.dso	= dso,
+		.sym	= sym,
+		.ip	= ip,
+		.level	= level,
+		.count	= count,
+	};
+	int cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		he = rb_entry(parent, struct hist_entry, rb_node);
+
+		cmp = hist_entry__cmp(&entry, he);
+
+		if (!cmp) {
+			he->count += count;
+			return 0;
+		}
+
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	he = malloc(sizeof(*he));
+	if (!he)
+		return -ENOMEM;
+	*he = entry;
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, &hist);
+
+	return 0;
+}
+
+static void hist_entry__free(struct hist_entry *he)
+{
+	free(he);
+}
+
+/*
+ * collapse the histogram
+ */
+
+static struct rb_root collapse_hists;
+
+static void collapse__insert_entry(struct hist_entry *he)
+{
+	struct rb_node **p = &collapse_hists.rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	int64_t cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		cmp = hist_entry__collapse(iter, he);
+
+		if (!cmp) {
+			iter->count += he->count;
+			hist_entry__free(he);
+			return;
+		}
+
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, &collapse_hists);
+}
+
+static void collapse__resort(void)
+{
+	struct rb_node *next;
+	struct hist_entry *n;
+
+	if (!sort__need_collapse)
+		return;
+
+	next = rb_first(&hist);
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		next = rb_next(&n->rb_node);
+
+		rb_erase(&n->rb_node, &hist);
+		collapse__insert_entry(n);
+	}
+}
+
+/*
+ * reverse the map, sort on count.
+ */
+
+static struct rb_root output_hists;
+
+static void output__insert_entry(struct hist_entry *he)
+{
+	struct rb_node **p = &output_hists.rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (he->count > iter->count)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, &output_hists);
+}
+
+static void output__resort(void)
+{
+	struct rb_node *next;
+	struct hist_entry *n;
+	struct rb_root *tree = &hist;
+
+	if (sort__need_collapse)
+		tree = &collapse_hists;
+
+	next = rb_first(tree);
+
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		next = rb_next(&n->rb_node);
+
+		rb_erase(&n->rb_node, tree);
+		output__insert_entry(n);
+	}
+}
+
+static size_t output__fprintf(FILE *fp, __u64 total_samples)
+{
+	struct hist_entry *pos;
+	struct sort_entry *se;
+	struct rb_node *nd;
+	size_t ret = 0;
+
+	fprintf(fp, "\n");
+	fprintf(fp, "#\n");
+	fprintf(fp, "# (%Ld samples)\n", (__u64)total_samples);
+	fprintf(fp, "#\n");
+
+	fprintf(fp, "# Overhead");
+	list_for_each_entry(se, &hist_entry__sort_list, list)
+		fprintf(fp, "  %s", se->header);
+	fprintf(fp, "\n");
+
+	fprintf(fp, "# ........");
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		int i;
+
+		fprintf(fp, "  ");
+		for (i = 0; i < strlen(se->header); i++)
+			fprintf(fp, ".");
+	}
+	fprintf(fp, "\n");
+
+	fprintf(fp, "#\n");
+
+	for (nd = rb_first(&output_hists); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct hist_entry, rb_node);
+		ret += hist_entry__fprintf(fp, pos, total_samples);
+	}
+
+	if (!strcmp(sort_order, default_sort_order)) {
+		fprintf(fp, "#\n");
+		fprintf(fp, "# (For more details, try: perf report --sort comm,dso,symbol)\n");
+		fprintf(fp, "#\n");
+	}
+	fprintf(fp, "\n");
+
+	return ret;
+}
+
+static void register_idle_thread(void)
+{
+	struct thread *thread = threads__findnew(0);
+
+	if (thread == NULL ||
+			thread__set_comm(thread, "[idle]")) {
+		fprintf(stderr, "problem inserting idle task.\n");
+		exit(-1);
+	}
+}
+
+static unsigned long total = 0,
+		     total_mmap = 0,
+		     total_comm = 0,
+		     total_fork = 0,
+		     total_unknown = 0;
+
+static int
+process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	char level;
+	int show = 0;
+	struct dso *dso = NULL;
+	struct thread *thread = threads__findnew(event->ip.pid);
+	__u64 ip = event->ip.ip;
+	__u64 period = 1;
+	struct map *map = NULL;
+
+	if (event->header.type & PERF_SAMPLE_PERIOD)
+		period = event->ip.period;
+
+	dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p period: %Ld\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->header.misc,
+		event->ip.pid,
+		(void *)(long)ip,
+		(long long)period);
+
+	dprintf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+
+	if (thread == NULL) {
+		fprintf(stderr, "problem processing %d event, skipping it.\n",
+			event->header.type);
+		return -1;
+	}
+
+	if (event->header.misc & PERF_EVENT_MISC_KERNEL) {
+		show = SHOW_KERNEL;
+		level = 'k';
+
+		dso = kernel_dso;
+
+		dprintf(" ...... dso: %s\n", dso->name);
+
+	} else if (event->header.misc & PERF_EVENT_MISC_USER) {
+
+		show = SHOW_USER;
+		level = '.';
+
+		map = thread__find_map(thread, ip);
+		if (map != NULL) {
+			ip = map->map_ip(map, ip);
+			dso = map->dso;
+		} else {
+			/*
+			 * If this is outside of all known maps,
+			 * and is a negative address, try to look it
+			 * up in the kernel dso, as it might be a
+			 * vsyscall (which executes in user-mode):
+			 */
+			if ((long long)ip < 0)
+				dso = kernel_dso;
+		}
+		dprintf(" ...... dso: %s\n", dso ? dso->name : "<not found>");
+
+	} else {
+		show = SHOW_HV;
+		level = 'H';
+		dprintf(" ...... dso: [hypervisor]\n");
+	}
+
+	if (show & show_mask) {
+		struct symbol *sym = NULL;
+
+		if (dso)
+			sym = dso->find_symbol(dso, ip);
+
+		if (hist_entry__add(thread, map, dso, sym, ip, level, period)) {
+			fprintf(stderr,
+		"problem incrementing symbol count, skipping event\n");
+			return -1;
+		}
+	}
+	total += period;
+
+	return 0;
+}
+
+static int
+process_mmap_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	struct thread *thread = threads__findnew(event->mmap.pid);
+	struct map *map = map__new(&event->mmap);
+
+	dprintf("%p [%p]: PERF_EVENT_MMAP %d: [%p(%p) @ %p]: %s\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->mmap.pid,
+		(void *)(long)event->mmap.start,
+		(void *)(long)event->mmap.len,
+		(void *)(long)event->mmap.pgoff,
+		event->mmap.filename);
+
+	if (thread == NULL || map == NULL) {
+		dprintf("problem processing PERF_EVENT_MMAP, skipping event.\n");
+		return 0;
+	}
+
+	thread__insert_map(thread, map);
+	total_mmap++;
+
+	return 0;
+}
+
+static int
+process_comm_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	struct thread *thread = threads__findnew(event->comm.pid);
+
+	dprintf("%p [%p]: PERF_EVENT_COMM: %s:%d\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->comm.comm, event->comm.pid);
+
+	if (thread == NULL ||
+	    thread__set_comm(thread, event->comm.comm)) {
+		dprintf("problem processing PERF_EVENT_COMM, skipping event.\n");
+		return -1;
+	}
+	total_comm++;
+
+	return 0;
+}
+
+static int
+process_fork_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	struct thread *thread = threads__findnew(event->fork.pid);
+	struct thread *parent = threads__findnew(event->fork.ppid);
+
+	dprintf("%p [%p]: PERF_EVENT_FORK: %d:%d\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->fork.pid, event->fork.ppid);
+
+	if (!thread || !parent || thread__fork(thread, parent)) {
+		dprintf("problem processing PERF_EVENT_FORK, skipping event.\n");
+		return -1;
+	}
+	total_fork++;
+
+	return 0;
+}
+
+static int
+process_period_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	dprintf("%p [%p]: PERF_EVENT_PERIOD: time:%Ld, id:%Ld: period:%Ld\n",
+		(void *)(offset + head),
+		(void *)(long)(event->header.size),
+		event->period.time,
+		event->period.id,
+		event->period.sample_period);
+
+	return 0;
+}
+
+static int
+process_event(event_t *event, unsigned long offset, unsigned long head)
+{
+	if (event->header.misc & PERF_EVENT_MISC_OVERFLOW)
+		return process_overflow_event(event, offset, head);
+
+	switch (event->header.type) {
+	case PERF_EVENT_MMAP:
+		return process_mmap_event(event, offset, head);
+
+	case PERF_EVENT_COMM:
+		return process_comm_event(event, offset, head);
+
+	case PERF_EVENT_FORK:
+		return process_fork_event(event, offset, head);
+
+	case PERF_EVENT_PERIOD:
+		return process_period_event(event, offset, head);
+	/*
+	 * We dont process them right now but they are fine:
+	 */
+
+	case PERF_EVENT_THROTTLE:
+	case PERF_EVENT_UNTHROTTLE:
+		return 0;
+
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+
+static int __cmd_report(void)
+{
+	int ret, rc = EXIT_FAILURE;
+	unsigned long offset = 0;
+	unsigned long head = 0;
+	struct stat stat;
+	event_t *event;
+	uint32_t size;
+	char *buf;
+
+	register_idle_thread();
+
+	input = open(input_name, O_RDONLY);
+	if (input < 0) {
+		fprintf(stderr, " failed to open file: %s", input_name);
+		if (!strcmp(input_name, "perf.data"))
+			fprintf(stderr, "  (try 'perf record' first)");
+		fprintf(stderr, "\n");
+		exit(-1);
+	}
+
+	ret = fstat(input, &stat);
+	if (ret < 0) {
+		perror("failed to stat file");
+		exit(-1);
+	}
+
+	if (!stat.st_size) {
+		fprintf(stderr, "zero-sized file, nothing to do!\n");
+		exit(0);
+	}
+
+	if (load_kernel() < 0) {
+		perror("failed to load kernel symbols");
+		return EXIT_FAILURE;
+	}
+
+	if (!full_paths) {
+		if (getcwd(__cwd, sizeof(__cwd)) == NULL) {
+			perror("failed to get the current directory");
+			return EXIT_FAILURE;
+		}
+		cwdlen = strlen(cwd);
+	} else {
+		cwd = NULL;
+		cwdlen = 0;
+	}
+remap:
+	buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ,
+			   MAP_SHARED, input, offset);
+	if (buf == MAP_FAILED) {
+		perror("failed to mmap file");
+		exit(-1);
+	}
+
+more:
+	event = (event_t *)(buf + head);
+
+	size = event->header.size;
+	if (!size)
+		size = 8;
+
+	if (head + event->header.size >= page_size * mmap_window) {
+		unsigned long shift = page_size * (head / page_size);
+		int ret;
+
+		ret = munmap(buf, page_size * mmap_window);
+		assert(ret == 0);
+
+		offset += shift;
+		head -= shift;
+		goto remap;
+	}
+
+	size = event->header.size;
+
+	dprintf("%p [%p]: event: %d\n",
+			(void *)(offset + head),
+			(void *)(long)event->header.size,
+			event->header.type);
+
+	if (!size || process_event(event, offset, head) < 0) {
+
+		dprintf("%p [%p]: skipping unknown header type: %d\n",
+			(void *)(offset + head),
+			(void *)(long)(event->header.size),
+			event->header.type);
+
+		total_unknown++;
+
+		/*
+		 * assume we lost track of the stream, check alignment, and
+		 * increment a single u64 in the hope to catch on again 'soon'.
+		 */
+
+		if (unlikely(head & 7))
+			head &= ~7ULL;
+
+		size = 8;
+	}
+
+	head += size;
+
+	if (offset + head < stat.st_size)
+		goto more;
+
+	rc = EXIT_SUCCESS;
+	close(input);
+
+	dprintf("      IP events: %10ld\n", total);
+	dprintf("    mmap events: %10ld\n", total_mmap);
+	dprintf("    comm events: %10ld\n", total_comm);
+	dprintf("    fork events: %10ld\n", total_fork);
+	dprintf(" unknown events: %10ld\n", total_unknown);
+
+	if (dump_trace)
+		return 0;
+
+	if (verbose >= 3)
+		threads__fprintf(stdout);
+
+	if (verbose >= 2)
+		dsos__fprintf(stdout);
+
+	collapse__resort();
+	output__resort();
+	output__fprintf(stdout, total);
+
+	return rc;
+}
+
+static const char * const report_usage[] = {
+	"perf report [<options>] <command>",
+	NULL
+};
+
+static const struct option options[] = {
+	OPT_STRING('i', "input", &input_name, "file",
+		    "input file name"),
+	OPT_BOOLEAN('v', "verbose", &verbose,
+		    "be more verbose (show symbol address, etc)"),
+	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+		    "dump raw trace in ASCII"),
+	OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"),
+	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
+		   "sort by key(s): pid, comm, dso, symbol. Default: pid,symbol"),
+	OPT_BOOLEAN('P', "full-paths", &full_paths,
+		    "Don't shorten the pathnames taking into account the cwd"),
+	OPT_END()
+};
+
+static void setup_sorting(void)
+{
+	char *tmp, *tok, *str = strdup(sort_order);
+
+	for (tok = strtok_r(str, ", ", &tmp);
+			tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		if (sort_dimension__add(tok) < 0) {
+			error("Unknown --sort key: `%s'", tok);
+			usage_with_options(report_usage, options);
+		}
+	}
+
+	free(str);
+}
+
+int cmd_report(int argc, const char **argv, const char *prefix)
+{
+	symbol__init();
+
+	page_size = getpagesize();
+
+	argc = parse_options(argc, argv, options, report_usage, 0);
+
+	setup_sorting();
+
+	/*
+	 * Any (unrecognized) arguments left?
+	 */
+	if (argc)
+		usage_with_options(report_usage, options);
+
+	setup_pager();
+
+	return __cmd_report();
+}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
new file mode 100644
index 000000000000..c43e4a97dc42
--- /dev/null
+++ b/tools/perf/builtin-stat.c
@@ -0,0 +1,367 @@
+/*
+ * builtin-stat.c
+ *
+ * Builtin stat command: Give a precise performance counters summary
+ * overview about any workload, CPU or specific PID.
+ *
+ * Sample output:
+
+   $ perf stat ~/hackbench 10
+   Time: 0.104
+
+    Performance counter stats for '/home/mingo/hackbench':
+
+       1255.538611  task clock ticks     #      10.143 CPU utilization factor
+             54011  context switches     #       0.043 M/sec
+               385  CPU migrations       #       0.000 M/sec
+             17755  pagefaults           #       0.014 M/sec
+        3808323185  CPU cycles           #    3033.219 M/sec
+        1575111190  instructions         #    1254.530 M/sec
+          17367895  cache references     #      13.833 M/sec
+           7674421  cache misses         #       6.112 M/sec
+
+    Wall-clock time elapsed:   123.786620 msecs
+
+ *
+ * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ *
+ * Improvements and fixes by:
+ *
+ *   Arjan van de Ven <arjan@linux.intel.com>
+ *   Yanmin Zhang <yanmin.zhang@intel.com>
+ *   Wu Fengguang <fengguang.wu@intel.com>
+ *   Mike Galbraith <efault@gmx.de>
+ *   Paul Mackerras <paulus@samba.org>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "perf.h"
+#include "builtin.h"
+#include "util/util.h"
+#include "util/parse-options.h"
+#include "util/parse-events.h"
+
+#include <sys/prctl.h>
+
+static struct perf_counter_attr default_attrs[MAX_COUNTERS] = {
+
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK	},
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES},
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS	},
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS	},
+
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES	},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS	},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES},
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES	},
+
+};
+
+static int			system_wide			=  0;
+static int			inherit				=  1;
+static int			verbose				=  0;
+
+static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+
+static int			target_pid			= -1;
+static int			nr_cpus				=  0;
+static unsigned int		page_size;
+
+static int			scale				=  1;
+
+static const unsigned int default_count[] = {
+	1000000,
+	1000000,
+	  10000,
+	  10000,
+	1000000,
+	  10000,
+};
+
+static __u64			event_res[MAX_COUNTERS][3];
+static __u64			event_scaled[MAX_COUNTERS];
+
+static __u64			runtime_nsecs;
+static __u64			walltime_nsecs;
+static __u64			runtime_cycles;
+
+static void create_perf_stat_counter(int counter)
+{
+	struct perf_counter_attr *attr = attrs + counter;
+
+	if (scale)
+		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+				    PERF_FORMAT_TOTAL_TIME_RUNNING;
+
+	if (system_wide) {
+		int cpu;
+		for (cpu = 0; cpu < nr_cpus; cpu ++) {
+			fd[cpu][counter] = sys_perf_counter_open(attr, -1, cpu, -1, 0);
+			if (fd[cpu][counter] < 0 && verbose) {
+				printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[cpu][counter], strerror(errno));
+			}
+		}
+	} else {
+		attr->inherit	= inherit;
+		attr->disabled	= 1;
+
+		fd[0][counter] = sys_perf_counter_open(attr, 0, -1, -1, 0);
+		if (fd[0][counter] < 0 && verbose) {
+			printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[0][counter], strerror(errno));
+		}
+	}
+}
+
+/*
+ * Does the counter have nsecs as a unit?
+ */
+static inline int nsec_counter(int counter)
+{
+	if (attrs[counter].type != PERF_TYPE_SOFTWARE)
+		return 0;
+
+	if (attrs[counter].config == PERF_COUNT_SW_CPU_CLOCK)
+		return 1;
+
+	if (attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK)
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Read out the results of a single counter:
+ */
+static void read_counter(int counter)
+{
+	__u64 *count, single_count[3];
+	ssize_t res;
+	int cpu, nv;
+	int scaled;
+
+	count = event_res[counter];
+
+	count[0] = count[1] = count[2] = 0;
+
+	nv = scale ? 3 : 1;
+	for (cpu = 0; cpu < nr_cpus; cpu ++) {
+		if (fd[cpu][counter] < 0)
+			continue;
+
+		res = read(fd[cpu][counter], single_count, nv * sizeof(__u64));
+		assert(res == nv * sizeof(__u64));
+
+		count[0] += single_count[0];
+		if (scale) {
+			count[1] += single_count[1];
+			count[2] += single_count[2];
+		}
+	}
+
+	scaled = 0;
+	if (scale) {
+		if (count[2] == 0) {
+			event_scaled[counter] = -1;
+			count[0] = 0;
+			return;
+		}
+
+		if (count[2] < count[1]) {
+			event_scaled[counter] = 1;
+			count[0] = (unsigned long long)
+				((double)count[0] * count[1] / count[2] + 0.5);
+		}
+	}
+	/*
+	 * Save the full runtime - to allow normalization during printout:
+	 */
+	if (attrs[counter].type == PERF_TYPE_SOFTWARE &&
+		attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK)
+		runtime_nsecs = count[0];
+	if (attrs[counter].type == PERF_TYPE_HARDWARE &&
+		attrs[counter].config == PERF_COUNT_HW_CPU_CYCLES)
+		runtime_cycles = count[0];
+}
+
+/*
+ * Print out the results of a single counter:
+ */
+static void print_counter(int counter)
+{
+	__u64 *count;
+	int scaled;
+
+	count = event_res[counter];
+	scaled = event_scaled[counter];
+
+	if (scaled == -1) {
+		fprintf(stderr, " %14s  %-20s\n",
+			"<not counted>", event_name(counter));
+		return;
+	}
+
+	if (nsec_counter(counter)) {
+		double msecs = (double)count[0] / 1000000;
+
+		fprintf(stderr, " %14.6f  %-20s",
+			msecs, event_name(counter));
+		if (attrs[counter].type == PERF_TYPE_SOFTWARE &&
+			attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) {
+
+			if (walltime_nsecs)
+				fprintf(stderr, " # %11.3f CPU utilization factor",
+					(double)count[0] / (double)walltime_nsecs);
+		}
+	} else {
+		fprintf(stderr, " %14Ld  %-20s",
+			count[0], event_name(counter));
+		if (runtime_nsecs)
+			fprintf(stderr, " # %11.3f M/sec",
+				(double)count[0]/runtime_nsecs*1000.0);
+		if (runtime_cycles &&
+			attrs[counter].type == PERF_TYPE_HARDWARE &&
+				attrs[counter].config == PERF_COUNT_HW_INSTRUCTIONS) {
+
+			fprintf(stderr, " # %1.3f per cycle",
+				(double)count[0] / (double)runtime_cycles);
+		}
+	}
+	if (scaled)
+		fprintf(stderr, "  (scaled from %.2f%%)",
+			(double) count[2] / count[1] * 100);
+	fprintf(stderr, "\n");
+}
+
+static int do_perf_stat(int argc, const char **argv)
+{
+	unsigned long long t0, t1;
+	int counter;
+	int status;
+	int pid;
+	int i;
+
+	if (!system_wide)
+		nr_cpus = 1;
+
+	for (counter = 0; counter < nr_counters; counter++)
+		create_perf_stat_counter(counter);
+
+	/*
+	 * Enable counters and exec the command:
+	 */
+	t0 = rdclock();
+	prctl(PR_TASK_PERF_COUNTERS_ENABLE);
+
+	if ((pid = fork()) < 0)
+		perror("failed to fork");
+
+	if (!pid) {
+		if (execvp(argv[0], (char **)argv)) {
+			perror(argv[0]);
+			exit(-1);
+		}
+	}
+
+	while (wait(&status) >= 0)
+		;
+
+	prctl(PR_TASK_PERF_COUNTERS_DISABLE);
+	t1 = rdclock();
+
+	walltime_nsecs = t1 - t0;
+
+	fflush(stdout);
+
+	fprintf(stderr, "\n");
+	fprintf(stderr, " Performance counter stats for \'%s", argv[0]);
+
+	for (i = 1; i < argc; i++)
+		fprintf(stderr, " %s", argv[i]);
+
+	fprintf(stderr, "\':\n");
+	fprintf(stderr, "\n");
+
+	for (counter = 0; counter < nr_counters; counter++)
+		read_counter(counter);
+
+	for (counter = 0; counter < nr_counters; counter++)
+		print_counter(counter);
+
+
+	fprintf(stderr, "\n");
+	fprintf(stderr, " Wall-clock time elapsed: %12.6f msecs\n",
+			(double)(t1-t0)/1e6);
+	fprintf(stderr, "\n");
+
+	return 0;
+}
+
+static volatile int signr = -1;
+
+static void skip_signal(int signo)
+{
+	signr = signo;
+}
+
+static void sig_atexit(void)
+{
+	if (signr == -1)
+		return;
+
+	signal(signr, SIG_DFL);
+	kill(getpid(), signr);
+}
+
+static const char * const stat_usage[] = {
+	"perf stat [<options>] <command>",
+	NULL
+};
+
+static const struct option options[] = {
+	OPT_CALLBACK('e', "event", NULL, "event",
+		     "event selector. use 'perf list' to list available events",
+		     parse_events),
+	OPT_BOOLEAN('i', "inherit", &inherit,
+		    "child tasks inherit counters"),
+	OPT_INTEGER('p', "pid", &target_pid,
+		    "stat events on existing pid"),
+	OPT_BOOLEAN('a', "all-cpus", &system_wide,
+			    "system-wide collection from all CPUs"),
+	OPT_BOOLEAN('S', "scale", &scale,
+			    "scale/normalize counters"),
+	OPT_BOOLEAN('v', "verbose", &verbose,
+		    "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+};
+
+int cmd_stat(int argc, const char **argv, const char *prefix)
+{
+	page_size = sysconf(_SC_PAGE_SIZE);
+
+	memcpy(attrs, default_attrs, sizeof(attrs));
+
+	argc = parse_options(argc, argv, options, stat_usage, 0);
+	if (!argc)
+		usage_with_options(stat_usage, options);
+
+	if (!nr_counters)
+		nr_counters = 8;
+
+	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	assert(nr_cpus <= MAX_NR_CPUS);
+	assert(nr_cpus >= 0);
+
+	/*
+	 * We dont want to block the signals - that would cause
+	 * child tasks to inherit that and Ctrl-C would not work.
+	 * What we want is for Ctrl-C to work in the exec()-ed
+	 * task, but being ignored by perf stat itself:
+	 */
+	atexit(sig_atexit);
+	signal(SIGINT,  skip_signal);
+	signal(SIGALRM, skip_signal);
+	signal(SIGABRT, skip_signal);
+
+	return do_perf_stat(argc, argv);
+}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
new file mode 100644
index 000000000000..fe338d3c5d7e
--- /dev/null
+++ b/tools/perf/builtin-top.c
@@ -0,0 +1,736 @@
+/*
+ * builtin-top.c
+ *
+ * Builtin top command: Display a continuously updated profile of
+ * any workload, CPU or specific PID.
+ *
+ * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ *
+ * Improvements and fixes by:
+ *
+ *   Arjan van de Ven <arjan@linux.intel.com>
+ *   Yanmin Zhang <yanmin.zhang@intel.com>
+ *   Wu Fengguang <fengguang.wu@intel.com>
+ *   Mike Galbraith <efault@gmx.de>
+ *   Paul Mackerras <paulus@samba.org>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "builtin.h"
+
+#include "perf.h"
+
+#include "util/symbol.h"
+#include "util/color.h"
+#include "util/util.h"
+#include "util/rbtree.h"
+#include "util/parse-options.h"
+#include "util/parse-events.h"
+
+#include <assert.h>
+#include <fcntl.h>
+
+#include <stdio.h>
+
+#include <errno.h>
+#include <time.h>
+#include <sched.h>
+#include <pthread.h>
+
+#include <sys/syscall.h>
+#include <sys/ioctl.h>
+#include <sys/poll.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <sys/uio.h>
+#include <sys/mman.h>
+
+#include <linux/unistd.h>
+#include <linux/types.h>
+
+static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
+
+static int			system_wide			=  0;
+
+static int			default_interval		= 100000;
+
+static __u64			count_filter			=  5;
+static int			print_entries			= 15;
+
+static int			target_pid			= -1;
+static int			profile_cpu			= -1;
+static int			nr_cpus				=  0;
+static unsigned int		realtime_prio			=  0;
+static int			group				=  0;
+static unsigned int		page_size;
+static unsigned int		mmap_pages			= 16;
+static int			freq				=  0;
+static int			verbose				=  0;
+
+static char			*sym_filter;
+static unsigned long		filter_start;
+static unsigned long		filter_end;
+
+static int			delay_secs			=  2;
+static int			zero;
+static int			dump_symtab;
+
+/*
+ * Symbols
+ */
+
+static __u64			min_ip;
+static __u64			max_ip = -1ll;
+
+struct sym_entry {
+	struct rb_node		rb_node;
+	struct list_head	node;
+	unsigned long		count[MAX_COUNTERS];
+	unsigned long		snap_count;
+	double			weight;
+	int			skip;
+};
+
+struct sym_entry		*sym_filter_entry;
+
+struct dso			*kernel_dso;
+
+/*
+ * Symbols will be added here in record_ip and will get out
+ * after decayed.
+ */
+static LIST_HEAD(active_symbols);
+static pthread_mutex_t active_symbols_lock = PTHREAD_MUTEX_INITIALIZER;
+
+/*
+ * Ordering weight: count-1 * count-2 * ... / count-n
+ */
+static double sym_weight(const struct sym_entry *sym)
+{
+	double weight = sym->snap_count;
+	int counter;
+
+	for (counter = 1; counter < nr_counters-1; counter++)
+		weight *= sym->count[counter];
+
+	weight /= (sym->count[counter] + 1);
+
+	return weight;
+}
+
+static long			samples;
+static long			userspace_samples;
+static const char		CONSOLE_CLEAR[] = "";
+
+static void __list_insert_active_sym(struct sym_entry *syme)
+{
+	list_add(&syme->node, &active_symbols);
+}
+
+static void list_remove_active_sym(struct sym_entry *syme)
+{
+	pthread_mutex_lock(&active_symbols_lock);
+	list_del_init(&syme->node);
+	pthread_mutex_unlock(&active_symbols_lock);
+}
+
+static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se)
+{
+	struct rb_node **p = &tree->rb_node;
+	struct rb_node *parent = NULL;
+	struct sym_entry *iter;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct sym_entry, rb_node);
+
+		if (se->weight > iter->weight)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&se->rb_node, parent, p);
+	rb_insert_color(&se->rb_node, tree);
+}
+
+static void print_sym_table(void)
+{
+	int printed = 0, j;
+	int counter;
+	float samples_per_sec = samples/delay_secs;
+	float ksamples_per_sec = (samples-userspace_samples)/delay_secs;
+	float sum_ksamples = 0.0;
+	struct sym_entry *syme, *n;
+	struct rb_root tmp = RB_ROOT;
+	struct rb_node *nd;
+
+	samples = userspace_samples = 0;
+
+	/* Sort the active symbols */
+	pthread_mutex_lock(&active_symbols_lock);
+	syme = list_entry(active_symbols.next, struct sym_entry, node);
+	pthread_mutex_unlock(&active_symbols_lock);
+
+	list_for_each_entry_safe_from(syme, n, &active_symbols, node) {
+		syme->snap_count = syme->count[0];
+		if (syme->snap_count != 0) {
+			syme->weight = sym_weight(syme);
+			rb_insert_active_sym(&tmp, syme);
+			sum_ksamples += syme->snap_count;
+
+			for (j = 0; j < nr_counters; j++)
+				syme->count[j] = zero ? 0 : syme->count[j] * 7 / 8;
+		} else
+			list_remove_active_sym(syme);
+	}
+
+	puts(CONSOLE_CLEAR);
+
+	printf(
+"------------------------------------------------------------------------------\n");
+	printf( "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% [",
+		samples_per_sec,
+		100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec)));
+
+	if (nr_counters == 1) {
+		printf("%Ld", attrs[0].sample_period);
+		if (freq)
+			printf("Hz ");
+		else
+			printf(" ");
+	}
+
+	for (counter = 0; counter < nr_counters; counter++) {
+		if (counter)
+			printf("/");
+
+		printf("%s", event_name(counter));
+	}
+
+	printf( "], ");
+
+	if (target_pid != -1)
+		printf(" (target_pid: %d", target_pid);
+	else
+		printf(" (all");
+
+	if (profile_cpu != -1)
+		printf(", cpu: %d)\n", profile_cpu);
+	else {
+		if (target_pid != -1)
+			printf(")\n");
+		else
+			printf(", %d CPUs)\n", nr_cpus);
+	}
+
+	printf("------------------------------------------------------------------------------\n\n");
+
+	if (nr_counters == 1)
+		printf("             samples    pcnt");
+	else
+		printf("  weight     samples    pcnt");
+
+	printf("         RIP          kernel function\n"
+	       	       "  ______     _______   _____   ________________   _______________\n\n"
+	);
+
+	for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) {
+		struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node);
+		struct symbol *sym = (struct symbol *)(syme + 1);
+		char *color = PERF_COLOR_NORMAL;
+		double pcnt;
+
+		if (++printed > print_entries || syme->snap_count < count_filter)
+			continue;
+
+		pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) /
+					 sum_ksamples));
+
+		/*
+		 * We color high-overhead entries in red, mid-overhead
+		 * entries in green - and keep the low overhead places
+		 * normal:
+		 */
+		if (pcnt >= 5.0) {
+			color = PERF_COLOR_RED;
+		} else {
+			if (pcnt >= 0.5)
+				color = PERF_COLOR_GREEN;
+		}
+
+		if (nr_counters == 1)
+			printf("%20.2f - ", syme->weight);
+		else
+			printf("%9.1f %10ld - ", syme->weight, syme->snap_count);
+
+		color_fprintf(stdout, color, "%4.1f%%", pcnt);
+		printf(" - %016llx : %s\n", sym->start, sym->name);
+	}
+}
+
+static void *display_thread(void *arg)
+{
+	struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
+	int delay_msecs = delay_secs * 1000;
+
+	printf("PerfTop refresh period: %d seconds\n", delay_secs);
+
+	do {
+		print_sym_table();
+	} while (!poll(&stdin_poll, 1, delay_msecs) == 1);
+
+	printf("key pressed - exiting.\n");
+	exit(0);
+
+	return NULL;
+}
+
+static int symbol_filter(struct dso *self, struct symbol *sym)
+{
+	static int filter_match;
+	struct sym_entry *syme;
+	const char *name = sym->name;
+
+	if (!strcmp(name, "_text") ||
+	    !strcmp(name, "_etext") ||
+	    !strcmp(name, "_sinittext") ||
+	    !strncmp("init_module", name, 11) ||
+	    !strncmp("cleanup_module", name, 14) ||
+	    strstr(name, "_text_start") ||
+	    strstr(name, "_text_end"))
+		return 1;
+
+	syme = dso__sym_priv(self, sym);
+	/* Tag samples to be skipped. */
+	if (!strcmp("default_idle", name) ||
+	    !strcmp("cpu_idle", name) ||
+	    !strcmp("enter_idle", name) ||
+	    !strcmp("exit_idle", name) ||
+	    !strcmp("mwait_idle", name))
+		syme->skip = 1;
+
+	if (filter_match == 1) {
+		filter_end = sym->start;
+		filter_match = -1;
+		if (filter_end - filter_start > 10000) {
+			fprintf(stderr,
+				"hm, too large filter symbol <%s> - skipping.\n",
+				sym_filter);
+			fprintf(stderr, "symbol filter start: %016lx\n",
+				filter_start);
+			fprintf(stderr, "                end: %016lx\n",
+				filter_end);
+			filter_end = filter_start = 0;
+			sym_filter = NULL;
+			sleep(1);
+		}
+	}
+
+	if (filter_match == 0 && sym_filter && !strcmp(name, sym_filter)) {
+		filter_match = 1;
+		filter_start = sym->start;
+	}
+
+
+	return 0;
+}
+
+static int parse_symbols(void)
+{
+	struct rb_node *node;
+	struct symbol  *sym;
+
+	kernel_dso = dso__new("[kernel]", sizeof(struct sym_entry));
+	if (kernel_dso == NULL)
+		return -1;
+
+	if (dso__load_kernel(kernel_dso, NULL, symbol_filter, 1) != 0)
+		goto out_delete_dso;
+
+	node = rb_first(&kernel_dso->syms);
+	sym = rb_entry(node, struct symbol, rb_node);
+	min_ip = sym->start;
+
+	node = rb_last(&kernel_dso->syms);
+	sym = rb_entry(node, struct symbol, rb_node);
+	max_ip = sym->end;
+
+	if (dump_symtab)
+		dso__fprintf(kernel_dso, stderr);
+
+	return 0;
+
+out_delete_dso:
+	dso__delete(kernel_dso);
+	kernel_dso = NULL;
+	return -1;
+}
+
+#define TRACE_COUNT     3
+
+/*
+ * Binary search in the histogram table and record the hit:
+ */
+static void record_ip(__u64 ip, int counter)
+{
+	struct symbol *sym = dso__find_symbol(kernel_dso, ip);
+
+	if (sym != NULL) {
+		struct sym_entry *syme = dso__sym_priv(kernel_dso, sym);
+
+		if (!syme->skip) {
+			syme->count[counter]++;
+			pthread_mutex_lock(&active_symbols_lock);
+			if (list_empty(&syme->node) || !syme->node.next)
+				__list_insert_active_sym(syme);
+			pthread_mutex_unlock(&active_symbols_lock);
+			return;
+		}
+	}
+
+	samples--;
+}
+
+static void process_event(__u64 ip, int counter)
+{
+	samples++;
+
+	if (ip < min_ip || ip > max_ip) {
+		userspace_samples++;
+		return;
+	}
+
+	record_ip(ip, counter);
+}
+
+struct mmap_data {
+	int			counter;
+	void			*base;
+	unsigned int		mask;
+	unsigned int		prev;
+};
+
+static unsigned int mmap_read_head(struct mmap_data *md)
+{
+	struct perf_counter_mmap_page *pc = md->base;
+	int head;
+
+	head = pc->data_head;
+	rmb();
+
+	return head;
+}
+
+struct timeval last_read, this_read;
+
+static void mmap_read_counter(struct mmap_data *md)
+{
+	unsigned int head = mmap_read_head(md);
+	unsigned int old = md->prev;
+	unsigned char *data = md->base + page_size;
+	int diff;
+
+	gettimeofday(&this_read, NULL);
+
+	/*
+	 * If we're further behind than half the buffer, there's a chance
+	 * the writer will bite our tail and mess up the samples under us.
+	 *
+	 * If we somehow ended up ahead of the head, we got messed up.
+	 *
+	 * In either case, truncate and restart at head.
+	 */
+	diff = head - old;
+	if (diff > md->mask / 2 || diff < 0) {
+		struct timeval iv;
+		unsigned long msecs;
+
+		timersub(&this_read, &last_read, &iv);
+		msecs = iv.tv_sec*1000 + iv.tv_usec/1000;
+
+		fprintf(stderr, "WARNING: failed to keep up with mmap data."
+				"  Last read %lu msecs ago.\n", msecs);
+
+		/*
+		 * head points to a known good entry, start there.
+		 */
+		old = head;
+	}
+
+	last_read = this_read;
+
+	for (; old != head;) {
+		struct ip_event {
+			struct perf_event_header header;
+			__u64 ip;
+			__u32 pid, target_pid;
+		};
+		struct mmap_event {
+			struct perf_event_header header;
+			__u32 pid, target_pid;
+			__u64 start;
+			__u64 len;
+			__u64 pgoff;
+			char filename[PATH_MAX];
+		};
+
+		typedef union event_union {
+			struct perf_event_header header;
+			struct ip_event ip;
+			struct mmap_event mmap;
+		} event_t;
+
+		event_t *event = (event_t *)&data[old & md->mask];
+
+		event_t event_copy;
+
+		size_t size = event->header.size;
+
+		/*
+		 * Event straddles the mmap boundary -- header should always
+		 * be inside due to u64 alignment of output.
+		 */
+		if ((old & md->mask) + size != ((old + size) & md->mask)) {
+			unsigned int offset = old;
+			unsigned int len = min(sizeof(*event), size), cpy;
+			void *dst = &event_copy;
+
+			do {
+				cpy = min(md->mask + 1 - (offset & md->mask), len);
+				memcpy(dst, &data[offset & md->mask], cpy);
+				offset += cpy;
+				dst += cpy;
+				len -= cpy;
+			} while (len);
+
+			event = &event_copy;
+		}
+
+		old += size;
+
+		if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) {
+			if (event->header.type & PERF_SAMPLE_IP)
+				process_event(event->ip.ip, md->counter);
+		}
+	}
+
+	md->prev = old;
+}
+
+static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
+static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+
+static void mmap_read(void)
+{
+	int i, counter;
+
+	for (i = 0; i < nr_cpus; i++) {
+		for (counter = 0; counter < nr_counters; counter++)
+			mmap_read_counter(&mmap_array[i][counter]);
+	}
+}
+
+int nr_poll;
+int group_fd;
+
+static void start_counter(int i, int counter)
+{
+	struct perf_counter_attr *attr;
+	unsigned int cpu;
+
+	cpu = profile_cpu;
+	if (target_pid == -1 && profile_cpu == -1)
+		cpu = i;
+
+	attr = attrs + counter;
+
+	attr->sample_type	= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+	attr->freq		= freq;
+
+try_again:
+	fd[i][counter] = sys_perf_counter_open(attr, target_pid, cpu, group_fd, 0);
+
+	if (fd[i][counter] < 0) {
+		int err = errno;
+
+		if (err == EPERM)
+			die("No permission - are you root?\n");
+		/*
+		 * If it's cycles then fall back to hrtimer
+		 * based cpu-clock-tick sw counter, which
+		 * is always available even if no PMU support:
+		 */
+		if (attr->type == PERF_TYPE_HARDWARE
+			&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+
+			if (verbose)
+				warning(" ... trying to fall back to cpu-clock-ticks\n");
+
+			attr->type = PERF_TYPE_SOFTWARE;
+			attr->config = PERF_COUNT_SW_CPU_CLOCK;
+			goto try_again;
+		}
+		printf("\n");
+		error("perfcounter syscall returned with %d (%s)\n",
+			fd[i][counter], strerror(err));
+		die("No CONFIG_PERF_COUNTERS=y kernel support configured?\n");
+		exit(-1);
+	}
+	assert(fd[i][counter] >= 0);
+	fcntl(fd[i][counter], F_SETFL, O_NONBLOCK);
+
+	/*
+	 * First counter acts as the group leader:
+	 */
+	if (group && group_fd == -1)
+		group_fd = fd[i][counter];
+
+	event_array[nr_poll].fd = fd[i][counter];
+	event_array[nr_poll].events = POLLIN;
+	nr_poll++;
+
+	mmap_array[i][counter].counter = counter;
+	mmap_array[i][counter].prev = 0;
+	mmap_array[i][counter].mask = mmap_pages*page_size - 1;
+	mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
+			PROT_READ, MAP_SHARED, fd[i][counter], 0);
+	if (mmap_array[i][counter].base == MAP_FAILED)
+		die("failed to mmap with %d (%s)\n", errno, strerror(errno));
+}
+
+static int __cmd_top(void)
+{
+	pthread_t thread;
+	int i, counter;
+	int ret;
+
+	for (i = 0; i < nr_cpus; i++) {
+		group_fd = -1;
+		for (counter = 0; counter < nr_counters; counter++)
+			start_counter(i, counter);
+	}
+
+	/* Wait for a minimal set of events before starting the snapshot */
+	poll(event_array, nr_poll, 100);
+
+	mmap_read();
+
+	if (pthread_create(&thread, NULL, display_thread, NULL)) {
+		printf("Could not create display thread.\n");
+		exit(-1);
+	}
+
+	if (realtime_prio) {
+		struct sched_param param;
+
+		param.sched_priority = realtime_prio;
+		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
+			printf("Could not set realtime priority.\n");
+			exit(-1);
+		}
+	}
+
+	while (1) {
+		int hits = samples;
+
+		mmap_read();
+
+		if (hits == samples)
+			ret = poll(event_array, nr_poll, 100);
+	}
+
+	return 0;
+}
+
+static const char * const top_usage[] = {
+	"perf top [<options>]",
+	NULL
+};
+
+static const struct option options[] = {
+	OPT_CALLBACK('e', "event", NULL, "event",
+		     "event selector. use 'perf list' to list available events",
+		     parse_events),
+	OPT_INTEGER('c', "count", &default_interval,
+		    "event period to sample"),
+	OPT_INTEGER('p', "pid", &target_pid,
+		    "profile events on existing pid"),
+	OPT_BOOLEAN('a', "all-cpus", &system_wide,
+			    "system-wide collection from all CPUs"),
+	OPT_INTEGER('C', "CPU", &profile_cpu,
+		    "CPU to profile on"),
+	OPT_INTEGER('m', "mmap-pages", &mmap_pages,
+		    "number of mmap data pages"),
+	OPT_INTEGER('r', "realtime", &realtime_prio,
+		    "collect data with this RT SCHED_FIFO priority"),
+	OPT_INTEGER('d', "delay", &delay_secs,
+		    "number of seconds to delay between refreshes"),
+	OPT_BOOLEAN('D', "dump-symtab", &dump_symtab,
+			    "dump the symbol table used for profiling"),
+	OPT_INTEGER('f', "count-filter", &count_filter,
+		    "only display functions with more events than this"),
+	OPT_BOOLEAN('g', "group", &group,
+			    "put the counters into a counter group"),
+	OPT_STRING('s', "sym-filter", &sym_filter, "pattern",
+		    "only display symbols matchig this pattern"),
+	OPT_BOOLEAN('z', "zero", &group,
+		    "zero history across updates"),
+	OPT_INTEGER('F', "freq", &freq,
+		    "profile at this frequency"),
+	OPT_INTEGER('E', "entries", &print_entries,
+		    "display this many functions"),
+	OPT_BOOLEAN('v', "verbose", &verbose,
+		    "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+};
+
+int cmd_top(int argc, const char **argv, const char *prefix)
+{
+	int counter;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+
+	argc = parse_options(argc, argv, options, top_usage, 0);
+	if (argc)
+		usage_with_options(top_usage, options);
+
+	if (freq) {
+		default_interval = freq;
+		freq = 1;
+	}
+
+	/* CPU and PID are mutually exclusive */
+	if (target_pid != -1 && profile_cpu != -1) {
+		printf("WARNING: PID switch overriding CPU\n");
+		sleep(1);
+		profile_cpu = -1;
+	}
+
+	if (!nr_counters)
+		nr_counters = 1;
+
+	if (delay_secs < 1)
+		delay_secs = 1;
+
+	parse_symbols();
+
+	/*
+	 * Fill in the ones not specifically initialized via -c:
+	 */
+	for (counter = 0; counter < nr_counters; counter++) {
+		if (attrs[counter].sample_period)
+			continue;
+
+		attrs[counter].sample_period = default_interval;
+	}
+
+	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	assert(nr_cpus <= MAX_NR_CPUS);
+	assert(nr_cpus >= 0);
+
+	if (target_pid != -1 || profile_cpu != -1)
+		nr_cpus = 1;
+
+	return __cmd_top();
+}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
new file mode 100644
index 000000000000..51d168230ee7
--- /dev/null
+++ b/tools/perf/builtin.h
@@ -0,0 +1,26 @@
+#ifndef BUILTIN_H
+#define BUILTIN_H
+
+#include "util/util.h"
+#include "util/strbuf.h"
+
+extern const char perf_version_string[];
+extern const char perf_usage_string[];
+extern const char perf_more_info_string[];
+
+extern void list_common_cmds_help(void);
+extern const char *help_unknown_cmd(const char *cmd);
+extern void prune_packed_objects(int);
+extern int read_line_with_nul(char *buf, int size, FILE *file);
+extern int check_pager_config(const char *cmd);
+
+extern int cmd_annotate(int argc, const char **argv, const char *prefix);
+extern int cmd_help(int argc, const char **argv, const char *prefix);
+extern int cmd_record(int argc, const char **argv, const char *prefix);
+extern int cmd_report(int argc, const char **argv, const char *prefix);
+extern int cmd_stat(int argc, const char **argv, const char *prefix);
+extern int cmd_top(int argc, const char **argv, const char *prefix);
+extern int cmd_version(int argc, const char **argv, const char *prefix);
+extern int cmd_list(int argc, const char **argv, const char *prefix);
+
+#endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
new file mode 100644
index 000000000000..eebce30afbc0
--- /dev/null
+++ b/tools/perf/command-list.txt
@@ -0,0 +1,10 @@
+#
+# List of known perf commands.
+# command name			category [deprecated] [common]
+#
+perf-annotate			mainporcelain common
+perf-list			mainporcelain common
+perf-record			mainporcelain common
+perf-report			mainporcelain common
+perf-stat			mainporcelain common
+perf-top			mainporcelain common
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
new file mode 100644
index 000000000000..860e116d979c
--- /dev/null
+++ b/tools/perf/design.txt
@@ -0,0 +1,442 @@
+
+Performance Counters for Linux
+------------------------------
+
+Performance counters are special hardware registers available on most modern
+CPUs. These registers count the number of certain types of hw events: such
+as instructions executed, cachemisses suffered, or branches mis-predicted -
+without slowing down the kernel or applications. These registers can also
+trigger interrupts when a threshold number of events have passed - and can
+thus be used to profile the code that runs on that CPU.
+
+The Linux Performance Counter subsystem provides an abstraction of these
+hardware capabilities. It provides per task and per CPU counters, counter
+groups, and it provides event capabilities on top of those.  It
+provides "virtual" 64-bit counters, regardless of the width of the
+underlying hardware counters.
+
+Performance counters are accessed via special file descriptors.
+There's one file descriptor per virtual counter used.
+
+The special file descriptor is opened via the perf_counter_open()
+system call:
+
+   int sys_perf_counter_open(struct perf_counter_hw_event *hw_event_uptr,
+			     pid_t pid, int cpu, int group_fd,
+			     unsigned long flags);
+
+The syscall returns the new fd. The fd can be used via the normal
+VFS system calls: read() can be used to read the counter, fcntl()
+can be used to set the blocking mode, etc.
+
+Multiple counters can be kept open at a time, and the counters
+can be poll()ed.
+
+When creating a new counter fd, 'perf_counter_hw_event' is:
+
+struct perf_counter_hw_event {
+        /*
+         * The MSB of the config word signifies if the rest contains cpu
+         * specific (raw) counter configuration data, if unset, the next
+         * 7 bits are an event type and the rest of the bits are the event
+         * identifier.
+         */
+        __u64                   config;
+
+        __u64                   irq_period;
+        __u32                   record_type;
+        __u32                   read_format;
+
+        __u64                   disabled       :  1, /* off by default        */
+                                inherit        :  1, /* children inherit it   */
+                                pinned         :  1, /* must always be on PMU */
+                                exclusive      :  1, /* only group on PMU     */
+                                exclude_user   :  1, /* don't count user      */
+                                exclude_kernel :  1, /* ditto kernel          */
+                                exclude_hv     :  1, /* ditto hypervisor      */
+                                exclude_idle   :  1, /* don't count when idle */
+                                mmap           :  1, /* include mmap data     */
+                                munmap         :  1, /* include munmap data   */
+                                comm           :  1, /* include comm data     */
+
+                                __reserved_1   : 52;
+
+        __u32                   extra_config_len;
+        __u32                   wakeup_events;  /* wakeup every n events */
+
+        __u64                   __reserved_2;
+        __u64                   __reserved_3;
+};
+
+The 'config' field specifies what the counter should count.  It
+is divided into 3 bit-fields:
+
+raw_type: 1 bit   (most significant bit)	0x8000_0000_0000_0000
+type:	  7 bits  (next most significant)	0x7f00_0000_0000_0000
+event_id: 56 bits (least significant)		0x00ff_ffff_ffff_ffff
+
+If 'raw_type' is 1, then the counter will count a hardware event
+specified by the remaining 63 bits of event_config.  The encoding is
+machine-specific.
+
+If 'raw_type' is 0, then the 'type' field says what kind of counter
+this is, with the following encoding:
+
+enum perf_event_types {
+	PERF_TYPE_HARDWARE		= 0,
+	PERF_TYPE_SOFTWARE		= 1,
+	PERF_TYPE_TRACEPOINT		= 2,
+};
+
+A counter of PERF_TYPE_HARDWARE will count the hardware event
+specified by 'event_id':
+
+/*
+ * Generalized performance counter event types, used by the hw_event.event_id
+ * parameter of the sys_perf_counter_open() syscall:
+ */
+enum hw_event_ids {
+	/*
+	 * Common hardware events, generalized by the kernel:
+	 */
+	PERF_COUNT_HW_CPU_CYCLES		= 0,
+	PERF_COUNT_HW_INSTRUCTIONS		= 1,
+	PERF_COUNT_HW_CACHE_REFERENCES	= 2,
+	PERF_COUNT_HW_CACHE_MISSES		= 3,
+	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
+	PERF_COUNT_HW_BRANCH_MISSES	= 5,
+	PERF_COUNT_HW_BUS_CYCLES		= 6,
+};
+
+These are standardized types of events that work relatively uniformly
+on all CPUs that implement Performance Counters support under Linux,
+although there may be variations (e.g., different CPUs might count
+cache references and misses at different levels of the cache hierarchy).
+If a CPU is not able to count the selected event, then the system call
+will return -EINVAL.
+
+More hw_event_types are supported as well, but they are CPU-specific
+and accessed as raw events.  For example, to count "External bus
+cycles while bus lock signal asserted" events on Intel Core CPUs, pass
+in a 0x4064 event_id value and set hw_event.raw_type to 1.
+
+A counter of type PERF_TYPE_SOFTWARE will count one of the available
+software events, selected by 'event_id':
+
+/*
+ * Special "software" counters provided by the kernel, even if the hardware
+ * does not support performance counters. These counters measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum sw_event_ids {
+	PERF_COUNT_SW_CPU_CLOCK		= 0,
+	PERF_COUNT_SW_TASK_CLOCK		= 1,
+	PERF_COUNT_SW_PAGE_FAULTS		= 2,
+	PERF_COUNT_SW_CONTEXT_SWITCHES	= 3,
+	PERF_COUNT_SW_CPU_MIGRATIONS	= 4,
+	PERF_COUNT_SW_PAGE_FAULTS_MIN	= 5,
+	PERF_COUNT_SW_PAGE_FAULTS_MAJ	= 6,
+};
+
+Counters of the type PERF_TYPE_TRACEPOINT are available when the ftrace event
+tracer is available, and event_id values can be obtained from
+/debug/tracing/events/*/*/id
+
+
+Counters come in two flavours: counting counters and sampling
+counters.  A "counting" counter is one that is used for counting the
+number of events that occur, and is characterised by having
+irq_period = 0.
+
+
+A read() on a counter returns the current value of the counter and possible
+additional values as specified by 'read_format', each value is a u64 (8 bytes)
+in size.
+
+/*
+ * Bits that can be set in hw_event.read_format to request that
+ * reads on the counter should return the indicated quantities,
+ * in increasing order of bit value, after the counter value.
+ */
+enum perf_counter_read_format {
+        PERF_FORMAT_TOTAL_TIME_ENABLED  =  1,
+        PERF_FORMAT_TOTAL_TIME_RUNNING  =  2,
+};
+
+Using these additional values one can establish the overcommit ratio for a
+particular counter allowing one to take the round-robin scheduling effect
+into account.
+
+
+A "sampling" counter is one that is set up to generate an interrupt
+every N events, where N is given by 'irq_period'.  A sampling counter
+has irq_period > 0. The record_type controls what data is recorded on each
+interrupt:
+
+/*
+ * Bits that can be set in hw_event.record_type to request information
+ * in the overflow packets.
+ */
+enum perf_counter_record_format {
+        PERF_RECORD_IP          = 1U << 0,
+        PERF_RECORD_TID         = 1U << 1,
+        PERF_RECORD_TIME        = 1U << 2,
+        PERF_RECORD_ADDR        = 1U << 3,
+        PERF_RECORD_GROUP       = 1U << 4,
+        PERF_RECORD_CALLCHAIN   = 1U << 5,
+};
+
+Such (and other) events will be recorded in a ring-buffer, which is
+available to user-space using mmap() (see below).
+
+The 'disabled' bit specifies whether the counter starts out disabled
+or enabled.  If it is initially disabled, it can be enabled by ioctl
+or prctl (see below).
+
+The 'inherit' bit, if set, specifies that this counter should count
+events on descendant tasks as well as the task specified.  This only
+applies to new descendents, not to any existing descendents at the
+time the counter is created (nor to any new descendents of existing
+descendents).
+
+The 'pinned' bit, if set, specifies that the counter should always be
+on the CPU if at all possible.  It only applies to hardware counters
+and only to group leaders.  If a pinned counter cannot be put onto the
+CPU (e.g. because there are not enough hardware counters or because of
+a conflict with some other event), then the counter goes into an
+'error' state, where reads return end-of-file (i.e. read() returns 0)
+until the counter is subsequently enabled or disabled.
+
+The 'exclusive' bit, if set, specifies that when this counter's group
+is on the CPU, it should be the only group using the CPU's counters.
+In future, this will allow sophisticated monitoring programs to supply
+extra configuration information via 'extra_config_len' to exploit
+advanced features of the CPU's Performance Monitor Unit (PMU) that are
+not otherwise accessible and that might disrupt other hardware
+counters.
+
+The 'exclude_user', 'exclude_kernel' and 'exclude_hv' bits provide a
+way to request that counting of events be restricted to times when the
+CPU is in user, kernel and/or hypervisor mode.
+
+The 'mmap' and 'munmap' bits allow recording of PROT_EXEC mmap/munmap
+operations, these can be used to relate userspace IP addresses to actual
+code, even after the mapping (or even the whole process) is gone,
+these events are recorded in the ring-buffer (see below).
+
+The 'comm' bit allows tracking of process comm data on process creation.
+This too is recorded in the ring-buffer (see below).
+
+The 'pid' parameter to the perf_counter_open() system call allows the
+counter to be specific to a task:
+
+ pid == 0: if the pid parameter is zero, the counter is attached to the
+ current task.
+
+ pid > 0: the counter is attached to a specific task (if the current task
+ has sufficient privilege to do so)
+
+ pid < 0: all tasks are counted (per cpu counters)
+
+The 'cpu' parameter allows a counter to be made specific to a CPU:
+
+ cpu >= 0: the counter is restricted to a specific CPU
+ cpu == -1: the counter counts on all CPUs
+
+(Note: the combination of 'pid == -1' and 'cpu == -1' is not valid.)
+
+A 'pid > 0' and 'cpu == -1' counter is a per task counter that counts
+events of that task and 'follows' that task to whatever CPU the task
+gets schedule to. Per task counters can be created by any user, for
+their own tasks.
+
+A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts
+all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege.
+
+The 'flags' parameter is currently unused and must be zero.
+
+The 'group_fd' parameter allows counter "groups" to be set up.  A
+counter group has one counter which is the group "leader".  The leader
+is created first, with group_fd = -1 in the perf_counter_open call
+that creates it.  The rest of the group members are created
+subsequently, with group_fd giving the fd of the group leader.
+(A single counter on its own is created with group_fd = -1 and is
+considered to be a group with only 1 member.)
+
+A counter group is scheduled onto the CPU as a unit, that is, it will
+only be put onto the CPU if all of the counters in the group can be
+put onto the CPU.  This means that the values of the member counters
+can be meaningfully compared, added, divided (to get ratios), etc.,
+with each other, since they have counted events for the same set of
+executed instructions.
+
+
+Like stated, asynchronous events, like counter overflow or PROT_EXEC mmap
+tracking are logged into a ring-buffer. This ring-buffer is created and
+accessed through mmap().
+
+The mmap size should be 1+2^n pages, where the first page is a meta-data page
+(struct perf_counter_mmap_page) that contains various bits of information such
+as where the ring-buffer head is.
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_counter_mmap_page {
+        __u32   version;                /* version number of this structure */
+        __u32   compat_version;         /* lowest version this is compat with */
+
+        /*
+         * Bits needed to read the hw counters in user-space.
+         *
+         *   u32 seq;
+         *   s64 count;
+         *
+         *   do {
+         *     seq = pc->lock;
+         *
+         *     barrier()
+         *     if (pc->index) {
+         *       count = pmc_read(pc->index - 1);
+         *       count += pc->offset;
+         *     } else
+         *       goto regular_read;
+         *
+         *     barrier();
+         *   } while (pc->lock != seq);
+         *
+         * NOTE: for obvious reason this only works on self-monitoring
+         *       processes.
+         */
+        __u32   lock;                   /* seqlock for synchronization */
+        __u32   index;                  /* hardware counter identifier */
+        __s64   offset;                 /* add to hardware counter value */
+
+        /*
+         * Control data for the mmap() data buffer.
+         *
+         * User-space reading this value should issue an rmb(), on SMP capable
+         * platforms, after reading this value -- see perf_counter_wakeup().
+         */
+        __u32   data_head;              /* head in the data section */
+};
+
+NOTE: the hw-counter userspace bits are arch specific and are currently only
+      implemented on powerpc.
+
+The following 2^n pages are the ring-buffer which contains events of the form:
+
+#define PERF_EVENT_MISC_KERNEL          (1 << 0)
+#define PERF_EVENT_MISC_USER            (1 << 1)
+#define PERF_EVENT_MISC_OVERFLOW        (1 << 2)
+
+struct perf_event_header {
+        __u32   type;
+        __u16   misc;
+        __u16   size;
+};
+
+enum perf_event_type {
+
+        /*
+         * The MMAP events record the PROT_EXEC mappings so that we can
+         * correlate userspace IPs to code. They have the following structure:
+         *
+         * struct {
+         *      struct perf_event_header        header;
+         *
+         *      u32                             pid, tid;
+         *      u64                             addr;
+         *      u64                             len;
+         *      u64                             pgoff;
+         *      char                            filename[];
+         * };
+         */
+        PERF_EVENT_MMAP                 = 1,
+        PERF_EVENT_MUNMAP               = 2,
+
+        /*
+         * struct {
+         *      struct perf_event_header        header;
+         *
+         *      u32                             pid, tid;
+         *      char                            comm[];
+         * };
+         */
+        PERF_EVENT_COMM                 = 3,
+
+        /*
+         * When header.misc & PERF_EVENT_MISC_OVERFLOW the event_type field
+         * will be PERF_RECORD_*
+         *
+         * struct {
+         *      struct perf_event_header        header;
+         *
+         *      { u64                   ip;       } && PERF_RECORD_IP
+         *      { u32                   pid, tid; } && PERF_RECORD_TID
+         *      { u64                   time;     } && PERF_RECORD_TIME
+         *      { u64                   addr;     } && PERF_RECORD_ADDR
+         *
+         *      { u64                   nr;
+         *        { u64 event, val; }   cnt[nr];  } && PERF_RECORD_GROUP
+         *
+         *      { u16                   nr,
+         *                              hv,
+         *                              kernel,
+         *                              user;
+         *        u64                   ips[nr];  } && PERF_RECORD_CALLCHAIN
+         * };
+         */
+};
+
+NOTE: PERF_RECORD_CALLCHAIN is arch specific and currently only implemented
+      on x86.
+
+Notification of new events is possible through poll()/select()/epoll() and
+fcntl() managing signals.
+
+Normally a notification is generated for every page filled, however one can
+additionally set perf_counter_hw_event.wakeup_events to generate one every
+so many counter overflow events.
+
+Future work will include a splice() interface to the ring-buffer.
+
+
+Counters can be enabled and disabled in two ways: via ioctl and via
+prctl.  When a counter is disabled, it doesn't count or generate
+events but does continue to exist and maintain its count value.
+
+An individual counter or counter group can be enabled with
+
+	ioctl(fd, PERF_COUNTER_IOC_ENABLE);
+
+or disabled with
+
+	ioctl(fd, PERF_COUNTER_IOC_DISABLE);
+
+Enabling or disabling the leader of a group enables or disables the
+whole group; that is, while the group leader is disabled, none of the
+counters in the group will count.  Enabling or disabling a member of a
+group other than the leader only affects that counter - disabling an
+non-leader stops that counter from counting but doesn't affect any
+other counter.
+
+Additionally, non-inherited overflow counters can use
+
+	ioctl(fd, PERF_COUNTER_IOC_REFRESH, nr);
+
+to enable a counter for 'nr' events, after which it gets disabled again.
+
+A process can enable or disable all the counter groups that are
+attached to it, using prctl:
+
+	prctl(PR_TASK_PERF_COUNTERS_ENABLE);
+
+	prctl(PR_TASK_PERF_COUNTERS_DISABLE);
+
+This applies to all counters on the current process, whether created
+by this process or by another, and doesn't affect any counters that
+this process has created on other processes.  It only enables or
+disables the group leaders, not any other members in the groups.
+
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
new file mode 100644
index 000000000000..4eb725933703
--- /dev/null
+++ b/tools/perf/perf.c
@@ -0,0 +1,428 @@
+/*
+ * perf.c
+ *
+ * Performance analysis utility.
+ *
+ * This is the main hub from which the sub-commands (perf stat,
+ * perf top, perf record, perf report, etc.) are started.
+ */
+#include "builtin.h"
+
+#include "util/exec_cmd.h"
+#include "util/cache.h"
+#include "util/quote.h"
+#include "util/run-command.h"
+
+const char perf_usage_string[] =
+	"perf [--version] [--help] COMMAND [ARGS]";
+
+const char perf_more_info_string[] =
+	"See 'perf help COMMAND' for more information on a specific command.";
+
+static int use_pager = -1;
+struct pager_config {
+	const char *cmd;
+	int val;
+};
+
+static int pager_command_config(const char *var, const char *value, void *data)
+{
+	struct pager_config *c = data;
+	if (!prefixcmp(var, "pager.") && !strcmp(var + 6, c->cmd))
+		c->val = perf_config_bool(var, value);
+	return 0;
+}
+
+/* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */
+int check_pager_config(const char *cmd)
+{
+	struct pager_config c;
+	c.cmd = cmd;
+	c.val = -1;
+	perf_config(pager_command_config, &c);
+	return c.val;
+}
+
+static void commit_pager_choice(void) {
+	switch (use_pager) {
+	case 0:
+		setenv("PERF_PAGER", "cat", 1);
+		break;
+	case 1:
+		/* setup_pager(); */
+		break;
+	default:
+		break;
+	}
+}
+
+static int handle_options(const char*** argv, int* argc, int* envchanged)
+{
+	int handled = 0;
+
+	while (*argc > 0) {
+		const char *cmd = (*argv)[0];
+		if (cmd[0] != '-')
+			break;
+
+		/*
+		 * For legacy reasons, the "version" and "help"
+		 * commands can be written with "--" prepended
+		 * to make them look like flags.
+		 */
+		if (!strcmp(cmd, "--help") || !strcmp(cmd, "--version"))
+			break;
+
+		/*
+		 * Check remaining flags.
+		 */
+		if (!prefixcmp(cmd, "--exec-path")) {
+			cmd += 11;
+			if (*cmd == '=')
+				perf_set_argv_exec_path(cmd + 1);
+			else {
+				puts(perf_exec_path());
+				exit(0);
+			}
+		} else if (!strcmp(cmd, "--html-path")) {
+			puts(system_path(PERF_HTML_PATH));
+			exit(0);
+		} else if (!strcmp(cmd, "-p") || !strcmp(cmd, "--paginate")) {
+			use_pager = 1;
+		} else if (!strcmp(cmd, "--no-pager")) {
+			use_pager = 0;
+			if (envchanged)
+				*envchanged = 1;
+		} else if (!strcmp(cmd, "--perf-dir")) {
+			if (*argc < 2) {
+				fprintf(stderr, "No directory given for --perf-dir.\n" );
+				usage(perf_usage_string);
+			}
+			setenv(PERF_DIR_ENVIRONMENT, (*argv)[1], 1);
+			if (envchanged)
+				*envchanged = 1;
+			(*argv)++;
+			(*argc)--;
+			handled++;
+		} else if (!prefixcmp(cmd, "--perf-dir=")) {
+			setenv(PERF_DIR_ENVIRONMENT, cmd + 10, 1);
+			if (envchanged)
+				*envchanged = 1;
+		} else if (!strcmp(cmd, "--work-tree")) {
+			if (*argc < 2) {
+				fprintf(stderr, "No directory given for --work-tree.\n" );
+				usage(perf_usage_string);
+			}
+			setenv(PERF_WORK_TREE_ENVIRONMENT, (*argv)[1], 1);
+			if (envchanged)
+				*envchanged = 1;
+			(*argv)++;
+			(*argc)--;
+		} else if (!prefixcmp(cmd, "--work-tree=")) {
+			setenv(PERF_WORK_TREE_ENVIRONMENT, cmd + 12, 1);
+			if (envchanged)
+				*envchanged = 1;
+		} else {
+			fprintf(stderr, "Unknown option: %s\n", cmd);
+			usage(perf_usage_string);
+		}
+
+		(*argv)++;
+		(*argc)--;
+		handled++;
+	}
+	return handled;
+}
+
+static int handle_alias(int *argcp, const char ***argv)
+{
+	int envchanged = 0, ret = 0, saved_errno = errno;
+	int count, option_count;
+	const char** new_argv;
+	const char *alias_command;
+	char *alias_string;
+
+	alias_command = (*argv)[0];
+	alias_string = alias_lookup(alias_command);
+	if (alias_string) {
+		if (alias_string[0] == '!') {
+			if (*argcp > 1) {
+				struct strbuf buf;
+
+				strbuf_init(&buf, PATH_MAX);
+				strbuf_addstr(&buf, alias_string);
+				sq_quote_argv(&buf, (*argv) + 1, PATH_MAX);
+				free(alias_string);
+				alias_string = buf.buf;
+			}
+			ret = system(alias_string + 1);
+			if (ret >= 0 && WIFEXITED(ret) &&
+			    WEXITSTATUS(ret) != 127)
+				exit(WEXITSTATUS(ret));
+			die("Failed to run '%s' when expanding alias '%s'",
+			    alias_string + 1, alias_command);
+		}
+		count = split_cmdline(alias_string, &new_argv);
+		if (count < 0)
+			die("Bad alias.%s string", alias_command);
+		option_count = handle_options(&new_argv, &count, &envchanged);
+		if (envchanged)
+			die("alias '%s' changes environment variables\n"
+				 "You can use '!perf' in the alias to do this.",
+				 alias_command);
+		memmove(new_argv - option_count, new_argv,
+				count * sizeof(char *));
+		new_argv -= option_count;
+
+		if (count < 1)
+			die("empty alias for %s", alias_command);
+
+		if (!strcmp(alias_command, new_argv[0]))
+			die("recursive alias: %s", alias_command);
+
+		new_argv = realloc(new_argv, sizeof(char*) *
+				    (count + *argcp + 1));
+		/* insert after command name */
+		memcpy(new_argv + count, *argv + 1, sizeof(char*) * *argcp);
+		new_argv[count+*argcp] = NULL;
+
+		*argv = new_argv;
+		*argcp += count - 1;
+
+		ret = 1;
+	}
+
+	errno = saved_errno;
+
+	return ret;
+}
+
+const char perf_version_string[] = PERF_VERSION;
+
+#define RUN_SETUP	(1<<0)
+#define USE_PAGER	(1<<1)
+/*
+ * require working tree to be present -- anything uses this needs
+ * RUN_SETUP for reading from the configuration file.
+ */
+#define NEED_WORK_TREE	(1<<2)
+
+struct cmd_struct {
+	const char *cmd;
+	int (*fn)(int, const char **, const char *);
+	int option;
+};
+
+static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
+{
+	int status;
+	struct stat st;
+	const char *prefix;
+
+	prefix = NULL;
+	if (p->option & RUN_SETUP)
+		prefix = NULL; /* setup_perf_directory(); */
+
+	if (use_pager == -1 && p->option & RUN_SETUP)
+		use_pager = check_pager_config(p->cmd);
+	if (use_pager == -1 && p->option & USE_PAGER)
+		use_pager = 1;
+	commit_pager_choice();
+
+	if (p->option & NEED_WORK_TREE)
+		/* setup_work_tree() */;
+
+	status = p->fn(argc, argv, prefix);
+	if (status)
+		return status & 0xff;
+
+	/* Somebody closed stdout? */
+	if (fstat(fileno(stdout), &st))
+		return 0;
+	/* Ignore write errors for pipes and sockets.. */
+	if (S_ISFIFO(st.st_mode) || S_ISSOCK(st.st_mode))
+		return 0;
+
+	/* Check for ENOSPC and EIO errors.. */
+	if (fflush(stdout))
+		die("write failure on standard output: %s", strerror(errno));
+	if (ferror(stdout))
+		die("unknown write failure on standard output");
+	if (fclose(stdout))
+		die("close failed on standard output: %s", strerror(errno));
+	return 0;
+}
+
+static void handle_internal_command(int argc, const char **argv)
+{
+	const char *cmd = argv[0];
+	static struct cmd_struct commands[] = {
+		{ "help", cmd_help, 0 },
+		{ "list", cmd_list, 0 },
+		{ "record", cmd_record, 0 },
+		{ "report", cmd_report, 0 },
+		{ "stat", cmd_stat, 0 },
+		{ "top", cmd_top, 0 },
+		{ "annotate", cmd_annotate, 0 },
+		{ "version", cmd_version, 0 },
+	};
+	int i;
+	static const char ext[] = STRIP_EXTENSION;
+
+	if (sizeof(ext) > 1) {
+		i = strlen(argv[0]) - strlen(ext);
+		if (i > 0 && !strcmp(argv[0] + i, ext)) {
+			char *argv0 = strdup(argv[0]);
+			argv[0] = cmd = argv0;
+			argv0[i] = '\0';
+		}
+	}
+
+	/* Turn "perf cmd --help" into "perf help cmd" */
+	if (argc > 1 && !strcmp(argv[1], "--help")) {
+		argv[1] = argv[0];
+		argv[0] = cmd = "help";
+	}
+
+	for (i = 0; i < ARRAY_SIZE(commands); i++) {
+		struct cmd_struct *p = commands+i;
+		if (strcmp(p->cmd, cmd))
+			continue;
+		exit(run_builtin(p, argc, argv));
+	}
+}
+
+static void execv_dashed_external(const char **argv)
+{
+	struct strbuf cmd = STRBUF_INIT;
+	const char *tmp;
+	int status;
+
+	strbuf_addf(&cmd, "perf-%s", argv[0]);
+
+	/*
+	 * argv[0] must be the perf command, but the argv array
+	 * belongs to the caller, and may be reused in
+	 * subsequent loop iterations. Save argv[0] and
+	 * restore it on error.
+	 */
+	tmp = argv[0];
+	argv[0] = cmd.buf;
+
+	/*
+	 * if we fail because the command is not found, it is
+	 * OK to return. Otherwise, we just pass along the status code.
+	 */
+	status = run_command_v_opt(argv, 0);
+	if (status != -ERR_RUN_COMMAND_EXEC) {
+		if (IS_RUN_COMMAND_ERR(status))
+			die("unable to run '%s'", argv[0]);
+		exit(-status);
+	}
+	errno = ENOENT; /* as if we called execvp */
+
+	argv[0] = tmp;
+
+	strbuf_release(&cmd);
+}
+
+static int run_argv(int *argcp, const char ***argv)
+{
+	int done_alias = 0;
+
+	while (1) {
+		/* See if it's an internal command */
+		handle_internal_command(*argcp, *argv);
+
+		/* .. then try the external ones */
+		execv_dashed_external(*argv);
+
+		/* It could be an alias -- this works around the insanity
+		 * of overriding "perf log" with "perf show" by having
+		 * alias.log = show
+		 */
+		if (done_alias || !handle_alias(argcp, argv))
+			break;
+		done_alias = 1;
+	}
+
+	return done_alias;
+}
+
+
+int main(int argc, const char **argv)
+{
+	const char *cmd;
+
+	cmd = perf_extract_argv0_path(argv[0]);
+	if (!cmd)
+		cmd = "perf-help";
+
+	/*
+	 * "perf-xxxx" is the same as "perf xxxx", but we obviously:
+	 *
+	 *  - cannot take flags in between the "perf" and the "xxxx".
+	 *  - cannot execute it externally (since it would just do
+	 *    the same thing over again)
+	 *
+	 * So we just directly call the internal command handler, and
+	 * die if that one cannot handle it.
+	 */
+	if (!prefixcmp(cmd, "perf-")) {
+		cmd += 5;
+		argv[0] = cmd;
+		handle_internal_command(argc, argv);
+		die("cannot handle %s internally", cmd);
+	}
+
+	/* Look for flags.. */
+	argv++;
+	argc--;
+	handle_options(&argv, &argc, NULL);
+	commit_pager_choice();
+	if (argc > 0) {
+		if (!prefixcmp(argv[0], "--"))
+			argv[0] += 2;
+	} else {
+		/* The user didn't specify a command; give them help */
+		printf("\n usage: %s\n\n", perf_usage_string);
+		list_common_cmds_help();
+		printf("\n %s\n\n", perf_more_info_string);
+		exit(1);
+	}
+	cmd = argv[0];
+
+	/*
+	 * We use PATH to find perf commands, but we prepend some higher
+	 * precidence paths: the "--exec-path" option, the PERF_EXEC_PATH
+	 * environment, and the $(perfexecdir) from the Makefile at build
+	 * time.
+	 */
+	setup_path();
+
+	while (1) {
+		static int done_help = 0;
+		static int was_alias = 0;
+
+		was_alias = run_argv(&argc, &argv);
+		if (errno != ENOENT)
+			break;
+
+		if (was_alias) {
+			fprintf(stderr, "Expansion of alias '%s' failed; "
+				"'%s' is not a perf-command\n",
+				cmd, argv[0]);
+			exit(1);
+		}
+		if (!done_help) {
+			cmd = argv[0] = help_unknown_cmd(cmd);
+			done_help = 1;
+		} else
+			break;
+	}
+
+	fprintf(stderr, "Failed to run command '%s': %s\n",
+		cmd, strerror(errno));
+
+	return 1;
+}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
new file mode 100644
index 000000000000..af0a5046d743
--- /dev/null
+++ b/tools/perf/perf.h
@@ -0,0 +1,67 @@
+#ifndef _PERF_PERF_H
+#define _PERF_PERF_H
+
+#if defined(__x86_64__) || defined(__i386__)
+#include "../../arch/x86/include/asm/unistd.h"
+#define rmb()		asm volatile("lfence" ::: "memory")
+#define cpu_relax()	asm volatile("rep; nop" ::: "memory");
+#endif
+
+#ifdef __powerpc__
+#include "../../arch/powerpc/include/asm/unistd.h"
+#define rmb()		asm volatile ("sync" ::: "memory")
+#define cpu_relax()	asm volatile ("" ::: "memory");
+#endif
+
+#include <time.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/syscall.h>
+
+#include "../../include/linux/perf_counter.h"
+
+/*
+ * prctl(PR_TASK_PERF_COUNTERS_DISABLE) will (cheaply) disable all
+ * counters in the current task.
+ */
+#define PR_TASK_PERF_COUNTERS_DISABLE   31
+#define PR_TASK_PERF_COUNTERS_ENABLE    32
+
+#ifndef NSEC_PER_SEC
+# define NSEC_PER_SEC			1000000000ULL
+#endif
+
+static inline unsigned long long rdclock(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
+}
+
+/*
+ * Pick up some kernel type conventions:
+ */
+#define __user
+#define asmlinkage
+
+#define unlikely(x)	__builtin_expect(!!(x), 0)
+#define min(x, y) ({				\
+	typeof(x) _min1 = (x);			\
+	typeof(y) _min2 = (y);			\
+	(void) (&_min1 == &_min2);		\
+	_min1 < _min2 ? _min1 : _min2; })
+
+static inline int
+sys_perf_counter_open(struct perf_counter_attr *attr_uptr,
+		      pid_t pid, int cpu, int group_fd,
+		      unsigned long flags)
+{
+	return syscall(__NR_perf_counter_open, attr_uptr, pid, cpu,
+		       group_fd, flags);
+}
+
+#define MAX_COUNTERS			256
+#define MAX_NR_CPUS			256
+
+#endif
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
new file mode 100755
index 000000000000..c561d1538c03
--- /dev/null
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -0,0 +1,42 @@
+#!/bin/sh
+
+GVF=PERF-VERSION-FILE
+DEF_VER=v0.0.1.PERF
+
+LF='
+'
+
+# First see if there is a version file (included in release tarballs),
+# then try git-describe, then default.
+if test -f version
+then
+	VN=$(cat version) || VN="$DEF_VER"
+elif test -d .git -o -f .git &&
+	VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
+	case "$VN" in
+	*$LF*) (exit 1) ;;
+	v[0-9]*)
+		git update-index -q --refresh
+		test -z "$(git diff-index --name-only HEAD --)" ||
+		VN="$VN-dirty" ;;
+	esac
+then
+	VN=$(echo "$VN" | sed -e 's/-/./g');
+else
+	VN="$DEF_VER"
+fi
+
+VN=$(expr "$VN" : v*'\(.*\)')
+
+if test -r $GVF
+then
+	VC=$(sed -e 's/^PERF_VERSION = //' <$GVF)
+else
+	VC=unset
+fi
+test "$VN" = "$VC" || {
+	echo >&2 "PERF_VERSION = $VN"
+	echo "PERF_VERSION = $VN" >$GVF
+}
+
+
diff --git a/tools/perf/util/abspath.c b/tools/perf/util/abspath.c
new file mode 100644
index 000000000000..61d33b81fc97
--- /dev/null
+++ b/tools/perf/util/abspath.c
@@ -0,0 +1,117 @@
+#include "cache.h"
+
+/*
+ * Do not use this for inspecting *tracked* content.  When path is a
+ * symlink to a directory, we do not want to say it is a directory when
+ * dealing with tracked content in the working tree.
+ */
+static int is_directory(const char *path)
+{
+	struct stat st;
+	return (!stat(path, &st) && S_ISDIR(st.st_mode));
+}
+
+/* We allow "recursive" symbolic links. Only within reason, though. */
+#define MAXDEPTH 5
+
+const char *make_absolute_path(const char *path)
+{
+	static char bufs[2][PATH_MAX + 1], *buf = bufs[0], *next_buf = bufs[1];
+	char cwd[1024] = "";
+	int buf_index = 1, len;
+
+	int depth = MAXDEPTH;
+	char *last_elem = NULL;
+	struct stat st;
+
+	if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX)
+		die ("Too long path: %.*s", 60, path);
+
+	while (depth--) {
+		if (!is_directory(buf)) {
+			char *last_slash = strrchr(buf, '/');
+			if (last_slash) {
+				*last_slash = '\0';
+				last_elem = xstrdup(last_slash + 1);
+			} else {
+				last_elem = xstrdup(buf);
+				*buf = '\0';
+			}
+		}
+
+		if (*buf) {
+			if (!*cwd && !getcwd(cwd, sizeof(cwd)))
+				die ("Could not get current working directory");
+
+			if (chdir(buf))
+				die ("Could not switch to '%s'", buf);
+		}
+		if (!getcwd(buf, PATH_MAX))
+			die ("Could not get current working directory");
+
+		if (last_elem) {
+			int len = strlen(buf);
+			if (len + strlen(last_elem) + 2 > PATH_MAX)
+				die ("Too long path name: '%s/%s'",
+						buf, last_elem);
+			buf[len] = '/';
+			strcpy(buf + len + 1, last_elem);
+			free(last_elem);
+			last_elem = NULL;
+		}
+
+		if (!lstat(buf, &st) && S_ISLNK(st.st_mode)) {
+			len = readlink(buf, next_buf, PATH_MAX);
+			if (len < 0)
+				die ("Invalid symlink: %s", buf);
+			if (PATH_MAX <= len)
+				die("symbolic link too long: %s", buf);
+			next_buf[len] = '\0';
+			buf = next_buf;
+			buf_index = 1 - buf_index;
+			next_buf = bufs[buf_index];
+		} else
+			break;
+	}
+
+	if (*cwd && chdir(cwd))
+		die ("Could not change back to '%s'", cwd);
+
+	return buf;
+}
+
+static const char *get_pwd_cwd(void)
+{
+	static char cwd[PATH_MAX + 1];
+	char *pwd;
+	struct stat cwd_stat, pwd_stat;
+	if (getcwd(cwd, PATH_MAX) == NULL)
+		return NULL;
+	pwd = getenv("PWD");
+	if (pwd && strcmp(pwd, cwd)) {
+		stat(cwd, &cwd_stat);
+		if (!stat(pwd, &pwd_stat) &&
+		    pwd_stat.st_dev == cwd_stat.st_dev &&
+		    pwd_stat.st_ino == cwd_stat.st_ino) {
+			strlcpy(cwd, pwd, PATH_MAX);
+		}
+	}
+	return cwd;
+}
+
+const char *make_nonrelative_path(const char *path)
+{
+	static char buf[PATH_MAX + 1];
+
+	if (is_absolute_path(path)) {
+		if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX)
+			die("Too long path: %.*s", 60, path);
+	} else {
+		const char *cwd = get_pwd_cwd();
+		if (!cwd)
+			die("Cannot determine the current working directory");
+		if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX)
+			die("Too long path: %.*s", 60, path);
+	}
+	return buf;
+}
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
new file mode 100644
index 000000000000..9b3dd2b428df
--- /dev/null
+++ b/tools/perf/util/alias.c
@@ -0,0 +1,77 @@
+#include "cache.h"
+
+static const char *alias_key;
+static char *alias_val;
+
+static int alias_lookup_cb(const char *k, const char *v, void *cb)
+{
+	if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) {
+		if (!v)
+			return config_error_nonbool(k);
+		alias_val = strdup(v);
+		return 0;
+	}
+	return 0;
+}
+
+char *alias_lookup(const char *alias)
+{
+	alias_key = alias;
+	alias_val = NULL;
+	perf_config(alias_lookup_cb, NULL);
+	return alias_val;
+}
+
+int split_cmdline(char *cmdline, const char ***argv)
+{
+	int src, dst, count = 0, size = 16;
+	char quoted = 0;
+
+	*argv = malloc(sizeof(char*) * size);
+
+	/* split alias_string */
+	(*argv)[count++] = cmdline;
+	for (src = dst = 0; cmdline[src];) {
+		char c = cmdline[src];
+		if (!quoted && isspace(c)) {
+			cmdline[dst++] = 0;
+			while (cmdline[++src]
+					&& isspace(cmdline[src]))
+				; /* skip */
+			if (count >= size) {
+				size += 16;
+				*argv = realloc(*argv, sizeof(char*) * size);
+			}
+			(*argv)[count++] = cmdline + dst;
+		} else if (!quoted && (c == '\'' || c == '"')) {
+			quoted = c;
+			src++;
+		} else if (c == quoted) {
+			quoted = 0;
+			src++;
+		} else {
+			if (c == '\\' && quoted != '\'') {
+				src++;
+				c = cmdline[src];
+				if (!c) {
+					free(*argv);
+					*argv = NULL;
+					return error("cmdline ends with \\");
+				}
+			}
+			cmdline[dst++] = c;
+			src++;
+		}
+	}
+
+	cmdline[dst] = 0;
+
+	if (quoted) {
+		free(*argv);
+		*argv = NULL;
+		return error("unclosed quote");
+	}
+
+	return count;
+}
+
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
new file mode 100644
index 000000000000..393d6146d13b
--- /dev/null
+++ b/tools/perf/util/cache.h
@@ -0,0 +1,119 @@
+#ifndef CACHE_H
+#define CACHE_H
+
+#include "util.h"
+#include "strbuf.h"
+
+#define PERF_DIR_ENVIRONMENT "PERF_DIR"
+#define PERF_WORK_TREE_ENVIRONMENT "PERF_WORK_TREE"
+#define DEFAULT_PERF_DIR_ENVIRONMENT ".perf"
+#define DB_ENVIRONMENT "PERF_OBJECT_DIRECTORY"
+#define INDEX_ENVIRONMENT "PERF_INDEX_FILE"
+#define GRAFT_ENVIRONMENT "PERF_GRAFT_FILE"
+#define TEMPLATE_DIR_ENVIRONMENT "PERF_TEMPLATE_DIR"
+#define CONFIG_ENVIRONMENT "PERF_CONFIG"
+#define EXEC_PATH_ENVIRONMENT "PERF_EXEC_PATH"
+#define CEILING_DIRECTORIES_ENVIRONMENT "PERF_CEILING_DIRECTORIES"
+#define PERFATTRIBUTES_FILE ".perfattributes"
+#define INFOATTRIBUTES_FILE "info/attributes"
+#define ATTRIBUTE_MACRO_PREFIX "[attr]"
+
+typedef int (*config_fn_t)(const char *, const char *, void *);
+extern int perf_default_config(const char *, const char *, void *);
+extern int perf_config_from_file(config_fn_t fn, const char *, void *);
+extern int perf_config(config_fn_t fn, void *);
+extern int perf_parse_ulong(const char *, unsigned long *);
+extern int perf_config_int(const char *, const char *);
+extern unsigned long perf_config_ulong(const char *, const char *);
+extern int perf_config_bool_or_int(const char *, const char *, int *);
+extern int perf_config_bool(const char *, const char *);
+extern int perf_config_string(const char **, const char *, const char *);
+extern int perf_config_set(const char *, const char *);
+extern int perf_config_set_multivar(const char *, const char *, const char *, int);
+extern int perf_config_rename_section(const char *, const char *);
+extern const char *perf_etc_perfconfig(void);
+extern int check_repository_format_version(const char *var, const char *value, void *cb);
+extern int perf_config_system(void);
+extern int perf_config_global(void);
+extern int config_error_nonbool(const char *);
+extern const char *config_exclusive_filename;
+
+#define MAX_PERFNAME (1000)
+extern char perf_default_email[MAX_PERFNAME];
+extern char perf_default_name[MAX_PERFNAME];
+extern int user_ident_explicitly_given;
+
+extern const char *perf_log_output_encoding;
+extern const char *perf_mailmap_file;
+
+/* IO helper functions */
+extern void maybe_flush_or_die(FILE *, const char *);
+extern int copy_fd(int ifd, int ofd);
+extern int copy_file(const char *dst, const char *src, int mode);
+extern ssize_t read_in_full(int fd, void *buf, size_t count);
+extern ssize_t write_in_full(int fd, const void *buf, size_t count);
+extern void write_or_die(int fd, const void *buf, size_t count);
+extern int write_or_whine(int fd, const void *buf, size_t count, const char *msg);
+extern int write_or_whine_pipe(int fd, const void *buf, size_t count, const char *msg);
+extern void fsync_or_die(int fd, const char *);
+
+/* pager.c */
+extern void setup_pager(void);
+extern const char *pager_program;
+extern int pager_in_use(void);
+extern int pager_use_color;
+
+extern const char *editor_program;
+extern const char *excludes_file;
+
+char *alias_lookup(const char *alias);
+int split_cmdline(char *cmdline, const char ***argv);
+
+#define alloc_nr(x) (((x)+16)*3/2)
+
+/*
+ * Realloc the buffer pointed at by variable 'x' so that it can hold
+ * at least 'nr' entries; the number of entries currently allocated
+ * is 'alloc', using the standard growing factor alloc_nr() macro.
+ *
+ * DO NOT USE any expression with side-effect for 'x' or 'alloc'.
+ */
+#define ALLOC_GROW(x, nr, alloc) \
+	do { \
+		if ((nr) > alloc) { \
+			if (alloc_nr(alloc) < (nr)) \
+				alloc = (nr); \
+			else \
+				alloc = alloc_nr(alloc); \
+			x = xrealloc((x), alloc * sizeof(*(x))); \
+		} \
+	} while(0)
+
+
+static inline int is_absolute_path(const char *path)
+{
+	return path[0] == '/';
+}
+
+const char *make_absolute_path(const char *path);
+const char *make_nonrelative_path(const char *path);
+const char *make_relative_path(const char *abs, const char *base);
+int normalize_path_copy(char *dst, const char *src);
+int longest_ancestor_length(const char *path, const char *prefix_list);
+char *strip_path_suffix(const char *path, const char *suffix);
+
+extern char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
+extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
+/* perf_mkstemp() - create tmp file honoring TMPDIR variable */
+extern int perf_mkstemp(char *path, size_t len, const char *template);
+
+extern char *mksnpath(char *buf, size_t n, const char *fmt, ...)
+	__attribute__((format (printf, 3, 4)));
+extern char *perf_snpath(char *buf, size_t n, const char *fmt, ...)
+	__attribute__((format (printf, 3, 4)));
+extern char *perf_pathdup(const char *fmt, ...)
+	__attribute__((format (printf, 1, 2)));
+
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+
+#endif /* CACHE_H */
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
new file mode 100644
index 000000000000..9a8c20ccc53e
--- /dev/null
+++ b/tools/perf/util/color.c
@@ -0,0 +1,241 @@
+#include "cache.h"
+#include "color.h"
+
+int perf_use_color_default = -1;
+
+static int parse_color(const char *name, int len)
+{
+	static const char * const color_names[] = {
+		"normal", "black", "red", "green", "yellow",
+		"blue", "magenta", "cyan", "white"
+	};
+	char *end;
+	int i;
+	for (i = 0; i < ARRAY_SIZE(color_names); i++) {
+		const char *str = color_names[i];
+		if (!strncasecmp(name, str, len) && !str[len])
+			return i - 1;
+	}
+	i = strtol(name, &end, 10);
+	if (end - name == len && i >= -1 && i <= 255)
+		return i;
+	return -2;
+}
+
+static int parse_attr(const char *name, int len)
+{
+	static const int attr_values[] = { 1, 2, 4, 5, 7 };
+	static const char * const attr_names[] = {
+		"bold", "dim", "ul", "blink", "reverse"
+	};
+	int i;
+	for (i = 0; i < ARRAY_SIZE(attr_names); i++) {
+		const char *str = attr_names[i];
+		if (!strncasecmp(name, str, len) && !str[len])
+			return attr_values[i];
+	}
+	return -1;
+}
+
+void color_parse(const char *value, const char *var, char *dst)
+{
+	color_parse_mem(value, strlen(value), var, dst);
+}
+
+void color_parse_mem(const char *value, int value_len, const char *var,
+		char *dst)
+{
+	const char *ptr = value;
+	int len = value_len;
+	int attr = -1;
+	int fg = -2;
+	int bg = -2;
+
+	if (!strncasecmp(value, "reset", len)) {
+		strcpy(dst, PERF_COLOR_RESET);
+		return;
+	}
+
+	/* [fg [bg]] [attr] */
+	while (len > 0) {
+		const char *word = ptr;
+		int val, wordlen = 0;
+
+		while (len > 0 && !isspace(word[wordlen])) {
+			wordlen++;
+			len--;
+		}
+
+		ptr = word + wordlen;
+		while (len > 0 && isspace(*ptr)) {
+			ptr++;
+			len--;
+		}
+
+		val = parse_color(word, wordlen);
+		if (val >= -1) {
+			if (fg == -2) {
+				fg = val;
+				continue;
+			}
+			if (bg == -2) {
+				bg = val;
+				continue;
+			}
+			goto bad;
+		}
+		val = parse_attr(word, wordlen);
+		if (val < 0 || attr != -1)
+			goto bad;
+		attr = val;
+	}
+
+	if (attr >= 0 || fg >= 0 || bg >= 0) {
+		int sep = 0;
+
+		*dst++ = '\033';
+		*dst++ = '[';
+		if (attr >= 0) {
+			*dst++ = '0' + attr;
+			sep++;
+		}
+		if (fg >= 0) {
+			if (sep++)
+				*dst++ = ';';
+			if (fg < 8) {
+				*dst++ = '3';
+				*dst++ = '0' + fg;
+			} else {
+				dst += sprintf(dst, "38;5;%d", fg);
+			}
+		}
+		if (bg >= 0) {
+			if (sep++)
+				*dst++ = ';';
+			if (bg < 8) {
+				*dst++ = '4';
+				*dst++ = '0' + bg;
+			} else {
+				dst += sprintf(dst, "48;5;%d", bg);
+			}
+		}
+		*dst++ = 'm';
+	}
+	*dst = 0;
+	return;
+bad:
+	die("bad color value '%.*s' for variable '%s'", value_len, value, var);
+}
+
+int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
+{
+	if (value) {
+		if (!strcasecmp(value, "never"))
+			return 0;
+		if (!strcasecmp(value, "always"))
+			return 1;
+		if (!strcasecmp(value, "auto"))
+			goto auto_color;
+	}
+
+	/* Missing or explicit false to turn off colorization */
+	if (!perf_config_bool(var, value))
+		return 0;
+
+	/* any normal truth value defaults to 'auto' */
+ auto_color:
+	if (stdout_is_tty < 0)
+		stdout_is_tty = isatty(1);
+	if (stdout_is_tty || (pager_in_use() && pager_use_color)) {
+		char *term = getenv("TERM");
+		if (term && strcmp(term, "dumb"))
+			return 1;
+	}
+	return 0;
+}
+
+int perf_color_default_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "color.ui")) {
+		perf_use_color_default = perf_config_colorbool(var, value, -1);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
+static int color_vfprintf(FILE *fp, const char *color, const char *fmt,
+		va_list args, const char *trail)
+{
+	int r = 0;
+
+	/*
+	 * Auto-detect:
+	 */
+	if (perf_use_color_default < 0) {
+		if (isatty(1) || pager_in_use())
+			perf_use_color_default = 1;
+		else
+			perf_use_color_default = 0;
+	}
+
+	if (perf_use_color_default && *color)
+		r += fprintf(fp, "%s", color);
+	r += vfprintf(fp, fmt, args);
+	if (perf_use_color_default && *color)
+		r += fprintf(fp, "%s", PERF_COLOR_RESET);
+	if (trail)
+		r += fprintf(fp, "%s", trail);
+	return r;
+}
+
+
+
+int color_fprintf(FILE *fp, const char *color, const char *fmt, ...)
+{
+	va_list args;
+	int r;
+
+	va_start(args, fmt);
+	r = color_vfprintf(fp, color, fmt, args, NULL);
+	va_end(args);
+	return r;
+}
+
+int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...)
+{
+	va_list args;
+	int r;
+	va_start(args, fmt);
+	r = color_vfprintf(fp, color, fmt, args, "\n");
+	va_end(args);
+	return r;
+}
+
+/*
+ * This function splits the buffer by newlines and colors the lines individually.
+ *
+ * Returns 0 on success.
+ */
+int color_fwrite_lines(FILE *fp, const char *color,
+		size_t count, const char *buf)
+{
+	if (!*color)
+		return fwrite(buf, count, 1, fp) != 1;
+	while (count) {
+		char *p = memchr(buf, '\n', count);
+		if (p != buf && (fputs(color, fp) < 0 ||
+				fwrite(buf, p ? p - buf : count, 1, fp) != 1 ||
+				fputs(PERF_COLOR_RESET, fp) < 0))
+			return -1;
+		if (!p)
+			return 0;
+		if (fputc('\n', fp) < 0)
+			return -1;
+		count -= p + 1 - buf;
+		buf = p + 1;
+	}
+	return 0;
+}
+
+
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
new file mode 100644
index 000000000000..5abfd379582b
--- /dev/null
+++ b/tools/perf/util/color.h
@@ -0,0 +1,36 @@
+#ifndef COLOR_H
+#define COLOR_H
+
+/* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */
+#define COLOR_MAXLEN 24
+
+#define PERF_COLOR_NORMAL	""
+#define PERF_COLOR_RESET	"\033[m"
+#define PERF_COLOR_BOLD		"\033[1m"
+#define PERF_COLOR_RED		"\033[31m"
+#define PERF_COLOR_GREEN	"\033[32m"
+#define PERF_COLOR_YELLOW	"\033[33m"
+#define PERF_COLOR_BLUE		"\033[34m"
+#define PERF_COLOR_MAGENTA	"\033[35m"
+#define PERF_COLOR_CYAN		"\033[36m"
+#define PERF_COLOR_BG_RED	"\033[41m"
+
+/*
+ * This variable stores the value of color.ui
+ */
+extern int perf_use_color_default;
+
+
+/*
+ * Use this instead of perf_default_config if you need the value of color.ui.
+ */
+int perf_color_default_config(const char *var, const char *value, void *cb);
+
+int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty);
+void color_parse(const char *value, const char *var, char *dst);
+void color_parse_mem(const char *value, int len, const char *var, char *dst);
+int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
+int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
+int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
+
+#endif /* COLOR_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
new file mode 100644
index 000000000000..3dd13faa6a27
--- /dev/null
+++ b/tools/perf/util/config.c
@@ -0,0 +1,873 @@
+/*
+ * GIT - The information manager from hell
+ *
+ * Copyright (C) Linus Torvalds, 2005
+ * Copyright (C) Johannes Schindelin, 2005
+ *
+ */
+#include "util.h"
+#include "cache.h"
+#include "exec_cmd.h"
+
+#define MAXNAME (256)
+
+static FILE *config_file;
+static const char *config_file_name;
+static int config_linenr;
+static int config_file_eof;
+
+const char *config_exclusive_filename = NULL;
+
+static int get_next_char(void)
+{
+	int c;
+	FILE *f;
+
+	c = '\n';
+	if ((f = config_file) != NULL) {
+		c = fgetc(f);
+		if (c == '\r') {
+			/* DOS like systems */
+			c = fgetc(f);
+			if (c != '\n') {
+				ungetc(c, f);
+				c = '\r';
+			}
+		}
+		if (c == '\n')
+			config_linenr++;
+		if (c == EOF) {
+			config_file_eof = 1;
+			c = '\n';
+		}
+	}
+	return c;
+}
+
+static char *parse_value(void)
+{
+	static char value[1024];
+	int quote = 0, comment = 0, len = 0, space = 0;
+
+	for (;;) {
+		int c = get_next_char();
+		if (len >= sizeof(value) - 1)
+			return NULL;
+		if (c == '\n') {
+			if (quote)
+				return NULL;
+			value[len] = 0;
+			return value;
+		}
+		if (comment)
+			continue;
+		if (isspace(c) && !quote) {
+			space = 1;
+			continue;
+		}
+		if (!quote) {
+			if (c == ';' || c == '#') {
+				comment = 1;
+				continue;
+			}
+		}
+		if (space) {
+			if (len)
+				value[len++] = ' ';
+			space = 0;
+		}
+		if (c == '\\') {
+			c = get_next_char();
+			switch (c) {
+			case '\n':
+				continue;
+			case 't':
+				c = '\t';
+				break;
+			case 'b':
+				c = '\b';
+				break;
+			case 'n':
+				c = '\n';
+				break;
+			/* Some characters escape as themselves */
+			case '\\': case '"':
+				break;
+			/* Reject unknown escape sequences */
+			default:
+				return NULL;
+			}
+			value[len++] = c;
+			continue;
+		}
+		if (c == '"') {
+			quote = 1-quote;
+			continue;
+		}
+		value[len++] = c;
+	}
+}
+
+static inline int iskeychar(int c)
+{
+	return isalnum(c) || c == '-';
+}
+
+static int get_value(config_fn_t fn, void *data, char *name, unsigned int len)
+{
+	int c;
+	char *value;
+
+	/* Get the full name */
+	for (;;) {
+		c = get_next_char();
+		if (config_file_eof)
+			break;
+		if (!iskeychar(c))
+			break;
+		name[len++] = tolower(c);
+		if (len >= MAXNAME)
+			return -1;
+	}
+	name[len] = 0;
+	while (c == ' ' || c == '\t')
+		c = get_next_char();
+
+	value = NULL;
+	if (c != '\n') {
+		if (c != '=')
+			return -1;
+		value = parse_value();
+		if (!value)
+			return -1;
+	}
+	return fn(name, value, data);
+}
+
+static int get_extended_base_var(char *name, int baselen, int c)
+{
+	do {
+		if (c == '\n')
+			return -1;
+		c = get_next_char();
+	} while (isspace(c));
+
+	/* We require the format to be '[base "extension"]' */
+	if (c != '"')
+		return -1;
+	name[baselen++] = '.';
+
+	for (;;) {
+		int c = get_next_char();
+		if (c == '\n')
+			return -1;
+		if (c == '"')
+			break;
+		if (c == '\\') {
+			c = get_next_char();
+			if (c == '\n')
+				return -1;
+		}
+		name[baselen++] = c;
+		if (baselen > MAXNAME / 2)
+			return -1;
+	}
+
+	/* Final ']' */
+	if (get_next_char() != ']')
+		return -1;
+	return baselen;
+}
+
+static int get_base_var(char *name)
+{
+	int baselen = 0;
+
+	for (;;) {
+		int c = get_next_char();
+		if (config_file_eof)
+			return -1;
+		if (c == ']')
+			return baselen;
+		if (isspace(c))
+			return get_extended_base_var(name, baselen, c);
+		if (!iskeychar(c) && c != '.')
+			return -1;
+		if (baselen > MAXNAME / 2)
+			return -1;
+		name[baselen++] = tolower(c);
+	}
+}
+
+static int perf_parse_file(config_fn_t fn, void *data)
+{
+	int comment = 0;
+	int baselen = 0;
+	static char var[MAXNAME];
+
+	/* U+FEFF Byte Order Mark in UTF8 */
+	static const unsigned char *utf8_bom = (unsigned char *) "\xef\xbb\xbf";
+	const unsigned char *bomptr = utf8_bom;
+
+	for (;;) {
+		int c = get_next_char();
+		if (bomptr && *bomptr) {
+			/* We are at the file beginning; skip UTF8-encoded BOM
+			 * if present. Sane editors won't put this in on their
+			 * own, but e.g. Windows Notepad will do it happily. */
+			if ((unsigned char) c == *bomptr) {
+				bomptr++;
+				continue;
+			} else {
+				/* Do not tolerate partial BOM. */
+				if (bomptr != utf8_bom)
+					break;
+				/* No BOM at file beginning. Cool. */
+				bomptr = NULL;
+			}
+		}
+		if (c == '\n') {
+			if (config_file_eof)
+				return 0;
+			comment = 0;
+			continue;
+		}
+		if (comment || isspace(c))
+			continue;
+		if (c == '#' || c == ';') {
+			comment = 1;
+			continue;
+		}
+		if (c == '[') {
+			baselen = get_base_var(var);
+			if (baselen <= 0)
+				break;
+			var[baselen++] = '.';
+			var[baselen] = 0;
+			continue;
+		}
+		if (!isalpha(c))
+			break;
+		var[baselen] = tolower(c);
+		if (get_value(fn, data, var, baselen+1) < 0)
+			break;
+	}
+	die("bad config file line %d in %s", config_linenr, config_file_name);
+}
+
+static int parse_unit_factor(const char *end, unsigned long *val)
+{
+	if (!*end)
+		return 1;
+	else if (!strcasecmp(end, "k")) {
+		*val *= 1024;
+		return 1;
+	}
+	else if (!strcasecmp(end, "m")) {
+		*val *= 1024 * 1024;
+		return 1;
+	}
+	else if (!strcasecmp(end, "g")) {
+		*val *= 1024 * 1024 * 1024;
+		return 1;
+	}
+	return 0;
+}
+
+static int perf_parse_long(const char *value, long *ret)
+{
+	if (value && *value) {
+		char *end;
+		long val = strtol(value, &end, 0);
+		unsigned long factor = 1;
+		if (!parse_unit_factor(end, &factor))
+			return 0;
+		*ret = val * factor;
+		return 1;
+	}
+	return 0;
+}
+
+int perf_parse_ulong(const char *value, unsigned long *ret)
+{
+	if (value && *value) {
+		char *end;
+		unsigned long val = strtoul(value, &end, 0);
+		if (!parse_unit_factor(end, &val))
+			return 0;
+		*ret = val;
+		return 1;
+	}
+	return 0;
+}
+
+static void die_bad_config(const char *name)
+{
+	if (config_file_name)
+		die("bad config value for '%s' in %s", name, config_file_name);
+	die("bad config value for '%s'", name);
+}
+
+int perf_config_int(const char *name, const char *value)
+{
+	long ret = 0;
+	if (!perf_parse_long(value, &ret))
+		die_bad_config(name);
+	return ret;
+}
+
+unsigned long perf_config_ulong(const char *name, const char *value)
+{
+	unsigned long ret;
+	if (!perf_parse_ulong(value, &ret))
+		die_bad_config(name);
+	return ret;
+}
+
+int perf_config_bool_or_int(const char *name, const char *value, int *is_bool)
+{
+	*is_bool = 1;
+	if (!value)
+		return 1;
+	if (!*value)
+		return 0;
+	if (!strcasecmp(value, "true") || !strcasecmp(value, "yes") || !strcasecmp(value, "on"))
+		return 1;
+	if (!strcasecmp(value, "false") || !strcasecmp(value, "no") || !strcasecmp(value, "off"))
+		return 0;
+	*is_bool = 0;
+	return perf_config_int(name, value);
+}
+
+int perf_config_bool(const char *name, const char *value)
+{
+	int discard;
+	return !!perf_config_bool_or_int(name, value, &discard);
+}
+
+int perf_config_string(const char **dest, const char *var, const char *value)
+{
+	if (!value)
+		return config_error_nonbool(var);
+	*dest = strdup(value);
+	return 0;
+}
+
+static int perf_default_core_config(const char *var, const char *value)
+{
+	/* Add other config variables here and to Documentation/config.txt. */
+	return 0;
+}
+
+int perf_default_config(const char *var, const char *value, void *dummy)
+{
+	if (!prefixcmp(var, "core."))
+		return perf_default_core_config(var, value);
+
+	/* Add other config variables here and to Documentation/config.txt. */
+	return 0;
+}
+
+int perf_config_from_file(config_fn_t fn, const char *filename, void *data)
+{
+	int ret;
+	FILE *f = fopen(filename, "r");
+
+	ret = -1;
+	if (f) {
+		config_file = f;
+		config_file_name = filename;
+		config_linenr = 1;
+		config_file_eof = 0;
+		ret = perf_parse_file(fn, data);
+		fclose(f);
+		config_file_name = NULL;
+	}
+	return ret;
+}
+
+const char *perf_etc_perfconfig(void)
+{
+	static const char *system_wide;
+	if (!system_wide)
+		system_wide = system_path(ETC_PERFCONFIG);
+	return system_wide;
+}
+
+static int perf_env_bool(const char *k, int def)
+{
+	const char *v = getenv(k);
+	return v ? perf_config_bool(k, v) : def;
+}
+
+int perf_config_system(void)
+{
+	return !perf_env_bool("PERF_CONFIG_NOSYSTEM", 0);
+}
+
+int perf_config_global(void)
+{
+	return !perf_env_bool("PERF_CONFIG_NOGLOBAL", 0);
+}
+
+int perf_config(config_fn_t fn, void *data)
+{
+	int ret = 0, found = 0;
+	char *repo_config = NULL;
+	const char *home = NULL;
+
+	/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
+	if (config_exclusive_filename)
+		return perf_config_from_file(fn, config_exclusive_filename, data);
+	if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) {
+		ret += perf_config_from_file(fn, perf_etc_perfconfig(),
+					    data);
+		found += 1;
+	}
+
+	home = getenv("HOME");
+	if (perf_config_global() && home) {
+		char *user_config = strdup(mkpath("%s/.perfconfig", home));
+		if (!access(user_config, R_OK)) {
+			ret += perf_config_from_file(fn, user_config, data);
+			found += 1;
+		}
+		free(user_config);
+	}
+
+	repo_config = perf_pathdup("config");
+	if (!access(repo_config, R_OK)) {
+		ret += perf_config_from_file(fn, repo_config, data);
+		found += 1;
+	}
+	free(repo_config);
+	if (found == 0)
+		return -1;
+	return ret;
+}
+
+/*
+ * Find all the stuff for perf_config_set() below.
+ */
+
+#define MAX_MATCHES 512
+
+static struct {
+	int baselen;
+	char* key;
+	int do_not_match;
+	regex_t* value_regex;
+	int multi_replace;
+	size_t offset[MAX_MATCHES];
+	enum { START, SECTION_SEEN, SECTION_END_SEEN, KEY_SEEN } state;
+	int seen;
+} store;
+
+static int matches(const char* key, const char* value)
+{
+	return !strcmp(key, store.key) &&
+		(store.value_regex == NULL ||
+		 (store.do_not_match ^
+		  !regexec(store.value_regex, value, 0, NULL, 0)));
+}
+
+static int store_aux(const char* key, const char* value, void *cb)
+{
+	const char *ep;
+	size_t section_len;
+
+	switch (store.state) {
+	case KEY_SEEN:
+		if (matches(key, value)) {
+			if (store.seen == 1 && store.multi_replace == 0) {
+				warning("%s has multiple values", key);
+			} else if (store.seen >= MAX_MATCHES) {
+				error("too many matches for %s", key);
+				return 1;
+			}
+
+			store.offset[store.seen] = ftell(config_file);
+			store.seen++;
+		}
+		break;
+	case SECTION_SEEN:
+		/*
+		 * What we are looking for is in store.key (both
+		 * section and var), and its section part is baselen
+		 * long.  We found key (again, both section and var).
+		 * We would want to know if this key is in the same
+		 * section as what we are looking for.  We already
+		 * know we are in the same section as what should
+		 * hold store.key.
+		 */
+		ep = strrchr(key, '.');
+		section_len = ep - key;
+
+		if ((section_len != store.baselen) ||
+		    memcmp(key, store.key, section_len+1)) {
+			store.state = SECTION_END_SEEN;
+			break;
+		}
+
+		/*
+		 * Do not increment matches: this is no match, but we
+		 * just made sure we are in the desired section.
+		 */
+		store.offset[store.seen] = ftell(config_file);
+		/* fallthru */
+	case SECTION_END_SEEN:
+	case START:
+		if (matches(key, value)) {
+			store.offset[store.seen] = ftell(config_file);
+			store.state = KEY_SEEN;
+			store.seen++;
+		} else {
+			if (strrchr(key, '.') - key == store.baselen &&
+			      !strncmp(key, store.key, store.baselen)) {
+					store.state = SECTION_SEEN;
+					store.offset[store.seen] = ftell(config_file);
+			}
+		}
+	}
+	return 0;
+}
+
+static int store_write_section(int fd, const char* key)
+{
+	const char *dot;
+	int i, success;
+	struct strbuf sb = STRBUF_INIT;
+
+	dot = memchr(key, '.', store.baselen);
+	if (dot) {
+		strbuf_addf(&sb, "[%.*s \"", (int)(dot - key), key);
+		for (i = dot - key + 1; i < store.baselen; i++) {
+			if (key[i] == '"' || key[i] == '\\')
+				strbuf_addch(&sb, '\\');
+			strbuf_addch(&sb, key[i]);
+		}
+		strbuf_addstr(&sb, "\"]\n");
+	} else {
+		strbuf_addf(&sb, "[%.*s]\n", store.baselen, key);
+	}
+
+	success = write_in_full(fd, sb.buf, sb.len) == sb.len;
+	strbuf_release(&sb);
+
+	return success;
+}
+
+static int store_write_pair(int fd, const char* key, const char* value)
+{
+	int i, success;
+	int length = strlen(key + store.baselen + 1);
+	const char *quote = "";
+	struct strbuf sb = STRBUF_INIT;
+
+	/*
+	 * Check to see if the value needs to be surrounded with a dq pair.
+	 * Note that problematic characters are always backslash-quoted; this
+	 * check is about not losing leading or trailing SP and strings that
+	 * follow beginning-of-comment characters (i.e. ';' and '#') by the
+	 * configuration parser.
+	 */
+	if (value[0] == ' ')
+		quote = "\"";
+	for (i = 0; value[i]; i++)
+		if (value[i] == ';' || value[i] == '#')
+			quote = "\"";
+	if (i && value[i - 1] == ' ')
+		quote = "\"";
+
+	strbuf_addf(&sb, "\t%.*s = %s",
+		    length, key + store.baselen + 1, quote);
+
+	for (i = 0; value[i]; i++)
+		switch (value[i]) {
+		case '\n':
+			strbuf_addstr(&sb, "\\n");
+			break;
+		case '\t':
+			strbuf_addstr(&sb, "\\t");
+			break;
+		case '"':
+		case '\\':
+			strbuf_addch(&sb, '\\');
+		default:
+			strbuf_addch(&sb, value[i]);
+			break;
+		}
+	strbuf_addf(&sb, "%s\n", quote);
+
+	success = write_in_full(fd, sb.buf, sb.len) == sb.len;
+	strbuf_release(&sb);
+
+	return success;
+}
+
+static ssize_t find_beginning_of_line(const char* contents, size_t size,
+	size_t offset_, int* found_bracket)
+{
+	size_t equal_offset = size, bracket_offset = size;
+	ssize_t offset;
+
+contline:
+	for (offset = offset_-2; offset > 0
+			&& contents[offset] != '\n'; offset--)
+		switch (contents[offset]) {
+			case '=': equal_offset = offset; break;
+			case ']': bracket_offset = offset; break;
+		}
+	if (offset > 0 && contents[offset-1] == '\\') {
+		offset_ = offset;
+		goto contline;
+	}
+	if (bracket_offset < equal_offset) {
+		*found_bracket = 1;
+		offset = bracket_offset+1;
+	} else
+		offset++;
+
+	return offset;
+}
+
+int perf_config_set(const char* key, const char* value)
+{
+	return perf_config_set_multivar(key, value, NULL, 0);
+}
+
+/*
+ * If value==NULL, unset in (remove from) config,
+ * if value_regex!=NULL, disregard key/value pairs where value does not match.
+ * if multi_replace==0, nothing, or only one matching key/value is replaced,
+ *     else all matching key/values (regardless how many) are removed,
+ *     before the new pair is written.
+ *
+ * Returns 0 on success.
+ *
+ * This function does this:
+ *
+ * - it locks the config file by creating ".perf/config.lock"
+ *
+ * - it then parses the config using store_aux() as validator to find
+ *   the position on the key/value pair to replace. If it is to be unset,
+ *   it must be found exactly once.
+ *
+ * - the config file is mmap()ed and the part before the match (if any) is
+ *   written to the lock file, then the changed part and the rest.
+ *
+ * - the config file is removed and the lock file rename()d to it.
+ *
+ */
+int perf_config_set_multivar(const char* key, const char* value,
+	const char* value_regex, int multi_replace)
+{
+	int i, dot;
+	int fd = -1, in_fd;
+	int ret = 0;
+	char* config_filename;
+	const char* last_dot = strrchr(key, '.');
+
+	if (config_exclusive_filename)
+		config_filename = strdup(config_exclusive_filename);
+	else
+		config_filename = perf_pathdup("config");
+
+	/*
+	 * Since "key" actually contains the section name and the real
+	 * key name separated by a dot, we have to know where the dot is.
+	 */
+
+	if (last_dot == NULL) {
+		error("key does not contain a section: %s", key);
+		ret = 2;
+		goto out_free;
+	}
+	store.baselen = last_dot - key;
+
+	store.multi_replace = multi_replace;
+
+	/*
+	 * Validate the key and while at it, lower case it for matching.
+	 */
+	store.key = malloc(strlen(key) + 1);
+	dot = 0;
+	for (i = 0; key[i]; i++) {
+		unsigned char c = key[i];
+		if (c == '.')
+			dot = 1;
+		/* Leave the extended basename untouched.. */
+		if (!dot || i > store.baselen) {
+			if (!iskeychar(c) || (i == store.baselen+1 && !isalpha(c))) {
+				error("invalid key: %s", key);
+				free(store.key);
+				ret = 1;
+				goto out_free;
+			}
+			c = tolower(c);
+		} else if (c == '\n') {
+			error("invalid key (newline): %s", key);
+			free(store.key);
+			ret = 1;
+			goto out_free;
+		}
+		store.key[i] = c;
+	}
+	store.key[i] = 0;
+
+	/*
+	 * If .perf/config does not exist yet, write a minimal version.
+	 */
+	in_fd = open(config_filename, O_RDONLY);
+	if ( in_fd < 0 ) {
+		free(store.key);
+
+		if ( ENOENT != errno ) {
+			error("opening %s: %s", config_filename,
+			      strerror(errno));
+			ret = 3; /* same as "invalid config file" */
+			goto out_free;
+		}
+		/* if nothing to unset, error out */
+		if (value == NULL) {
+			ret = 5;
+			goto out_free;
+		}
+
+		store.key = (char*)key;
+		if (!store_write_section(fd, key) ||
+		    !store_write_pair(fd, key, value))
+			goto write_err_out;
+	} else {
+		struct stat st;
+		char* contents;
+		size_t contents_sz, copy_begin, copy_end;
+		int i, new_line = 0;
+
+		if (value_regex == NULL)
+			store.value_regex = NULL;
+		else {
+			if (value_regex[0] == '!') {
+				store.do_not_match = 1;
+				value_regex++;
+			} else
+				store.do_not_match = 0;
+
+			store.value_regex = (regex_t*)malloc(sizeof(regex_t));
+			if (regcomp(store.value_regex, value_regex,
+					REG_EXTENDED)) {
+				error("invalid pattern: %s", value_regex);
+				free(store.value_regex);
+				ret = 6;
+				goto out_free;
+			}
+		}
+
+		store.offset[0] = 0;
+		store.state = START;
+		store.seen = 0;
+
+		/*
+		 * After this, store.offset will contain the *end* offset
+		 * of the last match, or remain at 0 if no match was found.
+		 * As a side effect, we make sure to transform only a valid
+		 * existing config file.
+		 */
+		if (perf_config_from_file(store_aux, config_filename, NULL)) {
+			error("invalid config file %s", config_filename);
+			free(store.key);
+			if (store.value_regex != NULL) {
+				regfree(store.value_regex);
+				free(store.value_regex);
+			}
+			ret = 3;
+			goto out_free;
+		}
+
+		free(store.key);
+		if (store.value_regex != NULL) {
+			regfree(store.value_regex);
+			free(store.value_regex);
+		}
+
+		/* if nothing to unset, or too many matches, error out */
+		if ((store.seen == 0 && value == NULL) ||
+				(store.seen > 1 && multi_replace == 0)) {
+			ret = 5;
+			goto out_free;
+		}
+
+		fstat(in_fd, &st);
+		contents_sz = xsize_t(st.st_size);
+		contents = mmap(NULL, contents_sz, PROT_READ,
+			MAP_PRIVATE, in_fd, 0);
+		close(in_fd);
+
+		if (store.seen == 0)
+			store.seen = 1;
+
+		for (i = 0, copy_begin = 0; i < store.seen; i++) {
+			if (store.offset[i] == 0) {
+				store.offset[i] = copy_end = contents_sz;
+			} else if (store.state != KEY_SEEN) {
+				copy_end = store.offset[i];
+			} else
+				copy_end = find_beginning_of_line(
+					contents, contents_sz,
+					store.offset[i]-2, &new_line);
+
+			if (copy_end > 0 && contents[copy_end-1] != '\n')
+				new_line = 1;
+
+			/* write the first part of the config */
+			if (copy_end > copy_begin) {
+				if (write_in_full(fd, contents + copy_begin,
+						  copy_end - copy_begin) <
+				    copy_end - copy_begin)
+					goto write_err_out;
+				if (new_line &&
+				    write_in_full(fd, "\n", 1) != 1)
+					goto write_err_out;
+			}
+			copy_begin = store.offset[i];
+		}
+
+		/* write the pair (value == NULL means unset) */
+		if (value != NULL) {
+			if (store.state == START) {
+				if (!store_write_section(fd, key))
+					goto write_err_out;
+			}
+			if (!store_write_pair(fd, key, value))
+				goto write_err_out;
+		}
+
+		/* write the rest of the config */
+		if (copy_begin < contents_sz)
+			if (write_in_full(fd, contents + copy_begin,
+					  contents_sz - copy_begin) <
+			    contents_sz - copy_begin)
+				goto write_err_out;
+
+		munmap(contents, contents_sz);
+	}
+
+	ret = 0;
+
+out_free:
+	free(config_filename);
+	return ret;
+
+write_err_out:
+	goto out_free;
+
+}
+
+/*
+ * Call this to report error for your variable that should not
+ * get a boolean value (i.e. "[my] var" means "true").
+ */
+int config_error_nonbool(const char *var)
+{
+	return error("Missing value for '%s'", var);
+}
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
new file mode 100644
index 000000000000..b90ec004f29c
--- /dev/null
+++ b/tools/perf/util/ctype.c
@@ -0,0 +1,26 @@
+/*
+ * Sane locale-independent, ASCII ctype.
+ *
+ * No surprises, and works with signed and unsigned chars.
+ */
+#include "cache.h"
+
+enum {
+	S = GIT_SPACE,
+	A = GIT_ALPHA,
+	D = GIT_DIGIT,
+	G = GIT_GLOB_SPECIAL,	/* *, ?, [, \\ */
+	R = GIT_REGEX_SPECIAL,	/* $, (, ), +, ., ^, {, | * */
+};
+
+unsigned char sane_ctype[256] = {
+	0, 0, 0, 0, 0, 0, 0, 0, 0, S, S, 0, 0, S, 0, 0,		/*   0.. 15 */
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,		/*  16.. 31 */
+	S, 0, 0, 0, R, 0, 0, 0, R, R, G, R, 0, 0, R, 0,		/*  32.. 47 */
+	D, D, D, D, D, D, D, D, D, D, 0, 0, 0, 0, 0, G,		/*  48.. 63 */
+	0, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A,		/*  64.. 79 */
+	A, A, A, A, A, A, A, A, A, A, A, G, G, 0, R, 0,		/*  80.. 95 */
+	0, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A,		/*  96..111 */
+	A, A, A, A, A, A, A, A, A, A, A, R, R, 0, 0, 0,		/* 112..127 */
+	/* Nothing in the 128.. range */
+};
diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c
new file mode 100644
index 000000000000..275b0ee345f5
--- /dev/null
+++ b/tools/perf/util/environment.c
@@ -0,0 +1,9 @@
+/*
+ * We put all the perf config variables in this same object
+ * file, so that programs can link against the config parser
+ * without having to link against all the rest of perf.
+ */
+#include "cache.h"
+
+const char *pager_program;
+int pager_use_color = 1;
diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c
new file mode 100644
index 000000000000..d39292263153
--- /dev/null
+++ b/tools/perf/util/exec_cmd.c
@@ -0,0 +1,165 @@
+#include "cache.h"
+#include "exec_cmd.h"
+#include "quote.h"
+#define MAX_ARGS	32
+
+extern char **environ;
+static const char *argv_exec_path;
+static const char *argv0_path;
+
+const char *system_path(const char *path)
+{
+#ifdef RUNTIME_PREFIX
+	static const char *prefix;
+#else
+	static const char *prefix = PREFIX;
+#endif
+	struct strbuf d = STRBUF_INIT;
+
+	if (is_absolute_path(path))
+		return path;
+
+#ifdef RUNTIME_PREFIX
+	assert(argv0_path);
+	assert(is_absolute_path(argv0_path));
+
+	if (!prefix &&
+	    !(prefix = strip_path_suffix(argv0_path, PERF_EXEC_PATH)) &&
+	    !(prefix = strip_path_suffix(argv0_path, BINDIR)) &&
+	    !(prefix = strip_path_suffix(argv0_path, "perf"))) {
+		prefix = PREFIX;
+		fprintf(stderr, "RUNTIME_PREFIX requested, "
+				"but prefix computation failed.  "
+				"Using static fallback '%s'.\n", prefix);
+	}
+#endif
+
+	strbuf_addf(&d, "%s/%s", prefix, path);
+	path = strbuf_detach(&d, NULL);
+	return path;
+}
+
+const char *perf_extract_argv0_path(const char *argv0)
+{
+	const char *slash;
+
+	if (!argv0 || !*argv0)
+		return NULL;
+	slash = argv0 + strlen(argv0);
+
+	while (argv0 <= slash && !is_dir_sep(*slash))
+		slash--;
+
+	if (slash >= argv0) {
+		argv0_path = strndup(argv0, slash - argv0);
+		return slash + 1;
+	}
+
+	return argv0;
+}
+
+void perf_set_argv_exec_path(const char *exec_path)
+{
+	argv_exec_path = exec_path;
+	/*
+	 * Propagate this setting to external programs.
+	 */
+	setenv(EXEC_PATH_ENVIRONMENT, exec_path, 1);
+}
+
+
+/* Returns the highest-priority, location to look for perf programs. */
+const char *perf_exec_path(void)
+{
+	const char *env;
+
+	if (argv_exec_path)
+		return argv_exec_path;
+
+	env = getenv(EXEC_PATH_ENVIRONMENT);
+	if (env && *env) {
+		return env;
+	}
+
+	return system_path(PERF_EXEC_PATH);
+}
+
+static void add_path(struct strbuf *out, const char *path)
+{
+	if (path && *path) {
+		if (is_absolute_path(path))
+			strbuf_addstr(out, path);
+		else
+			strbuf_addstr(out, make_nonrelative_path(path));
+
+		strbuf_addch(out, PATH_SEP);
+	}
+}
+
+void setup_path(void)
+{
+	const char *old_path = getenv("PATH");
+	struct strbuf new_path = STRBUF_INIT;
+
+	add_path(&new_path, perf_exec_path());
+	add_path(&new_path, argv0_path);
+
+	if (old_path)
+		strbuf_addstr(&new_path, old_path);
+	else
+		strbuf_addstr(&new_path, "/usr/local/bin:/usr/bin:/bin");
+
+	setenv("PATH", new_path.buf, 1);
+
+	strbuf_release(&new_path);
+}
+
+const char **prepare_perf_cmd(const char **argv)
+{
+	int argc;
+	const char **nargv;
+
+	for (argc = 0; argv[argc]; argc++)
+		; /* just counting */
+	nargv = malloc(sizeof(*nargv) * (argc + 2));
+
+	nargv[0] = "perf";
+	for (argc = 0; argv[argc]; argc++)
+		nargv[argc + 1] = argv[argc];
+	nargv[argc + 1] = NULL;
+	return nargv;
+}
+
+int execv_perf_cmd(const char **argv) {
+	const char **nargv = prepare_perf_cmd(argv);
+
+	/* execvp() can only ever return if it fails */
+	execvp("perf", (char **)nargv);
+
+	free(nargv);
+	return -1;
+}
+
+
+int execl_perf_cmd(const char *cmd,...)
+{
+	int argc;
+	const char *argv[MAX_ARGS + 1];
+	const char *arg;
+	va_list param;
+
+	va_start(param, cmd);
+	argv[0] = cmd;
+	argc = 1;
+	while (argc < MAX_ARGS) {
+		arg = argv[argc++] = va_arg(param, char *);
+		if (!arg)
+			break;
+	}
+	va_end(param);
+	if (MAX_ARGS <= argc)
+		return error("too many args to run %s", cmd);
+
+	argv[argc] = NULL;
+	return execv_perf_cmd(argv);
+}
diff --git a/tools/perf/util/exec_cmd.h b/tools/perf/util/exec_cmd.h
new file mode 100644
index 000000000000..effe25eb1545
--- /dev/null
+++ b/tools/perf/util/exec_cmd.h
@@ -0,0 +1,13 @@
+#ifndef PERF_EXEC_CMD_H
+#define PERF_EXEC_CMD_H
+
+extern void perf_set_argv_exec_path(const char *exec_path);
+extern const char *perf_extract_argv0_path(const char *path);
+extern const char *perf_exec_path(void);
+extern void setup_path(void);
+extern const char **prepare_perf_cmd(const char **argv);
+extern int execv_perf_cmd(const char **argv); /* NULL terminated */
+extern int execl_perf_cmd(const char *cmd, ...);
+extern const char *system_path(const char *path);
+
+#endif /* PERF_EXEC_CMD_H */
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
new file mode 100755
index 000000000000..f06f6fd148f8
--- /dev/null
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -0,0 +1,24 @@
+#!/bin/sh
+
+echo "/* Automatically generated by $0 */
+struct cmdname_help
+{
+    char name[16];
+    char help[80];
+};
+
+static struct cmdname_help common_cmds[] = {"
+
+sed -n -e 's/^perf-\([^ 	]*\)[ 	].* common.*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+     sed -n '
+     /^NAME/,/perf-'"$cmd"'/H
+     ${
+            x
+            s/.*perf-'"$cmd"' - \(.*\)/  {"'"$cmd"'", "\1"},/
+	    p
+     }' "Documentation/perf-$cmd.txt"
+done
+echo "};"
diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
new file mode 100644
index 000000000000..6653f7dd1d78
--- /dev/null
+++ b/tools/perf/util/help.c
@@ -0,0 +1,367 @@
+#include "cache.h"
+#include "../builtin.h"
+#include "exec_cmd.h"
+#include "levenshtein.h"
+#include "help.h"
+
+/* most GUI terminals set COLUMNS (although some don't export it) */
+static int term_columns(void)
+{
+	char *col_string = getenv("COLUMNS");
+	int n_cols;
+
+	if (col_string && (n_cols = atoi(col_string)) > 0)
+		return n_cols;
+
+#ifdef TIOCGWINSZ
+	{
+		struct winsize ws;
+		if (!ioctl(1, TIOCGWINSZ, &ws)) {
+			if (ws.ws_col)
+				return ws.ws_col;
+		}
+	}
+#endif
+
+	return 80;
+}
+
+void add_cmdname(struct cmdnames *cmds, const char *name, int len)
+{
+	struct cmdname *ent = malloc(sizeof(*ent) + len + 1);
+
+	ent->len = len;
+	memcpy(ent->name, name, len);
+	ent->name[len] = 0;
+
+	ALLOC_GROW(cmds->names, cmds->cnt + 1, cmds->alloc);
+	cmds->names[cmds->cnt++] = ent;
+}
+
+static void clean_cmdnames(struct cmdnames *cmds)
+{
+	int i;
+	for (i = 0; i < cmds->cnt; ++i)
+		free(cmds->names[i]);
+	free(cmds->names);
+	cmds->cnt = 0;
+	cmds->alloc = 0;
+}
+
+static int cmdname_compare(const void *a_, const void *b_)
+{
+	struct cmdname *a = *(struct cmdname **)a_;
+	struct cmdname *b = *(struct cmdname **)b_;
+	return strcmp(a->name, b->name);
+}
+
+static void uniq(struct cmdnames *cmds)
+{
+	int i, j;
+
+	if (!cmds->cnt)
+		return;
+
+	for (i = j = 1; i < cmds->cnt; i++)
+		if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name))
+			cmds->names[j++] = cmds->names[i];
+
+	cmds->cnt = j;
+}
+
+void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
+{
+	int ci, cj, ei;
+	int cmp;
+
+	ci = cj = ei = 0;
+	while (ci < cmds->cnt && ei < excludes->cnt) {
+		cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);
+		if (cmp < 0)
+			cmds->names[cj++] = cmds->names[ci++];
+		else if (cmp == 0)
+			ci++, ei++;
+		else if (cmp > 0)
+			ei++;
+	}
+
+	while (ci < cmds->cnt)
+		cmds->names[cj++] = cmds->names[ci++];
+
+	cmds->cnt = cj;
+}
+
+static void pretty_print_string_list(struct cmdnames *cmds, int longest)
+{
+	int cols = 1, rows;
+	int space = longest + 1; /* min 1 SP between words */
+	int max_cols = term_columns() - 1; /* don't print *on* the edge */
+	int i, j;
+
+	if (space < max_cols)
+		cols = max_cols / space;
+	rows = (cmds->cnt + cols - 1) / cols;
+
+	for (i = 0; i < rows; i++) {
+		printf("  ");
+
+		for (j = 0; j < cols; j++) {
+			int n = j * rows + i;
+			int size = space;
+			if (n >= cmds->cnt)
+				break;
+			if (j == cols-1 || n + rows >= cmds->cnt)
+				size = 1;
+			printf("%-*s", size, cmds->names[n]->name);
+		}
+		putchar('\n');
+	}
+}
+
+static int is_executable(const char *name)
+{
+	struct stat st;
+
+	if (stat(name, &st) || /* stat, not lstat */
+	    !S_ISREG(st.st_mode))
+		return 0;
+
+#ifdef __MINGW32__
+	/* cannot trust the executable bit, peek into the file instead */
+	char buf[3] = { 0 };
+	int n;
+	int fd = open(name, O_RDONLY);
+	st.st_mode &= ~S_IXUSR;
+	if (fd >= 0) {
+		n = read(fd, buf, 2);
+		if (n == 2)
+			/* DOS executables start with "MZ" */
+			if (!strcmp(buf, "#!") || !strcmp(buf, "MZ"))
+				st.st_mode |= S_IXUSR;
+		close(fd);
+	}
+#endif
+	return st.st_mode & S_IXUSR;
+}
+
+static void list_commands_in_dir(struct cmdnames *cmds,
+					 const char *path,
+					 const char *prefix)
+{
+	int prefix_len;
+	DIR *dir = opendir(path);
+	struct dirent *de;
+	struct strbuf buf = STRBUF_INIT;
+	int len;
+
+	if (!dir)
+		return;
+	if (!prefix)
+		prefix = "perf-";
+	prefix_len = strlen(prefix);
+
+	strbuf_addf(&buf, "%s/", path);
+	len = buf.len;
+
+	while ((de = readdir(dir)) != NULL) {
+		int entlen;
+
+		if (prefixcmp(de->d_name, prefix))
+			continue;
+
+		strbuf_setlen(&buf, len);
+		strbuf_addstr(&buf, de->d_name);
+		if (!is_executable(buf.buf))
+			continue;
+
+		entlen = strlen(de->d_name) - prefix_len;
+		if (has_extension(de->d_name, ".exe"))
+			entlen -= 4;
+
+		add_cmdname(cmds, de->d_name + prefix_len, entlen);
+	}
+	closedir(dir);
+	strbuf_release(&buf);
+}
+
+void load_command_list(const char *prefix,
+		struct cmdnames *main_cmds,
+		struct cmdnames *other_cmds)
+{
+	const char *env_path = getenv("PATH");
+	const char *exec_path = perf_exec_path();
+
+	if (exec_path) {
+		list_commands_in_dir(main_cmds, exec_path, prefix);
+		qsort(main_cmds->names, main_cmds->cnt,
+		      sizeof(*main_cmds->names), cmdname_compare);
+		uniq(main_cmds);
+	}
+
+	if (env_path) {
+		char *paths, *path, *colon;
+		path = paths = strdup(env_path);
+		while (1) {
+			if ((colon = strchr(path, PATH_SEP)))
+				*colon = 0;
+			if (!exec_path || strcmp(path, exec_path))
+				list_commands_in_dir(other_cmds, path, prefix);
+
+			if (!colon)
+				break;
+			path = colon + 1;
+		}
+		free(paths);
+
+		qsort(other_cmds->names, other_cmds->cnt,
+		      sizeof(*other_cmds->names), cmdname_compare);
+		uniq(other_cmds);
+	}
+	exclude_cmds(other_cmds, main_cmds);
+}
+
+void list_commands(const char *title, struct cmdnames *main_cmds,
+		   struct cmdnames *other_cmds)
+{
+	int i, longest = 0;
+
+	for (i = 0; i < main_cmds->cnt; i++)
+		if (longest < main_cmds->names[i]->len)
+			longest = main_cmds->names[i]->len;
+	for (i = 0; i < other_cmds->cnt; i++)
+		if (longest < other_cmds->names[i]->len)
+			longest = other_cmds->names[i]->len;
+
+	if (main_cmds->cnt) {
+		const char *exec_path = perf_exec_path();
+		printf("available %s in '%s'\n", title, exec_path);
+		printf("----------------");
+		mput_char('-', strlen(title) + strlen(exec_path));
+		putchar('\n');
+		pretty_print_string_list(main_cmds, longest);
+		putchar('\n');
+	}
+
+	if (other_cmds->cnt) {
+		printf("%s available from elsewhere on your $PATH\n", title);
+		printf("---------------------------------------");
+		mput_char('-', strlen(title));
+		putchar('\n');
+		pretty_print_string_list(other_cmds, longest);
+		putchar('\n');
+	}
+}
+
+int is_in_cmdlist(struct cmdnames *c, const char *s)
+{
+	int i;
+	for (i = 0; i < c->cnt; i++)
+		if (!strcmp(s, c->names[i]->name))
+			return 1;
+	return 0;
+}
+
+static int autocorrect;
+static struct cmdnames aliases;
+
+static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "help.autocorrect"))
+		autocorrect = perf_config_int(var,value);
+	/* Also use aliases for command lookup */
+	if (!prefixcmp(var, "alias."))
+		add_cmdname(&aliases, var + 6, strlen(var + 6));
+
+	return perf_default_config(var, value, cb);
+}
+
+static int levenshtein_compare(const void *p1, const void *p2)
+{
+	const struct cmdname *const *c1 = p1, *const *c2 = p2;
+	const char *s1 = (*c1)->name, *s2 = (*c2)->name;
+	int l1 = (*c1)->len;
+	int l2 = (*c2)->len;
+	return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
+}
+
+static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
+{
+	int i;
+	ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);
+
+	for (i = 0; i < old->cnt; i++)
+		cmds->names[cmds->cnt++] = old->names[i];
+	free(old->names);
+	old->cnt = 0;
+	old->names = NULL;
+}
+
+const char *help_unknown_cmd(const char *cmd)
+{
+	int i, n = 0, best_similarity = 0;
+	struct cmdnames main_cmds, other_cmds;
+
+	memset(&main_cmds, 0, sizeof(main_cmds));
+	memset(&other_cmds, 0, sizeof(main_cmds));
+	memset(&aliases, 0, sizeof(aliases));
+
+	perf_config(perf_unknown_cmd_config, NULL);
+
+	load_command_list("perf-", &main_cmds, &other_cmds);
+
+	add_cmd_list(&main_cmds, &aliases);
+	add_cmd_list(&main_cmds, &other_cmds);
+	qsort(main_cmds.names, main_cmds.cnt,
+	      sizeof(main_cmds.names), cmdname_compare);
+	uniq(&main_cmds);
+
+	if (main_cmds.cnt) {
+		/* This reuses cmdname->len for similarity index */
+		for (i = 0; i < main_cmds.cnt; ++i)
+			main_cmds.names[i]->len =
+				levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
+
+		qsort(main_cmds.names, main_cmds.cnt,
+		      sizeof(*main_cmds.names), levenshtein_compare);
+
+		best_similarity = main_cmds.names[0]->len;
+		n = 1;
+		while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
+			++n;
+	}
+
+	if (autocorrect && n == 1) {
+		const char *assumed = main_cmds.names[0]->name;
+
+		main_cmds.names[0] = NULL;
+		clean_cmdnames(&main_cmds);
+		fprintf(stderr, "WARNING: You called a Git program named '%s', "
+			"which does not exist.\n"
+			"Continuing under the assumption that you meant '%s'\n",
+			cmd, assumed);
+		if (autocorrect > 0) {
+			fprintf(stderr, "in %0.1f seconds automatically...\n",
+				(float)autocorrect/10.0);
+			poll(NULL, 0, autocorrect * 100);
+		}
+		return assumed;
+	}
+
+	fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
+
+	if (main_cmds.cnt && best_similarity < 6) {
+		fprintf(stderr, "\nDid you mean %s?\n",
+			n < 2 ? "this": "one of these");
+
+		for (i = 0; i < n; i++)
+			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
+	}
+
+	exit(1);
+}
+
+int cmd_version(int argc, const char **argv, const char *prefix)
+{
+	printf("perf version %s\n", perf_version_string);
+	return 0;
+}
diff --git a/tools/perf/util/help.h b/tools/perf/util/help.h
new file mode 100644
index 000000000000..56bc15406ffc
--- /dev/null
+++ b/tools/perf/util/help.h
@@ -0,0 +1,29 @@
+#ifndef HELP_H
+#define HELP_H
+
+struct cmdnames {
+	int alloc;
+	int cnt;
+	struct cmdname {
+		size_t len; /* also used for similarity index in help.c */
+		char name[FLEX_ARRAY];
+	} **names;
+};
+
+static inline void mput_char(char c, unsigned int num)
+{
+	while(num--)
+		putchar(c);
+}
+
+void load_command_list(const char *prefix,
+		struct cmdnames *main_cmds,
+		struct cmdnames *other_cmds);
+void add_cmdname(struct cmdnames *cmds, const char *name, int len);
+/* Here we require that excludes is a sorted list. */
+void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes);
+int is_in_cmdlist(struct cmdnames *c, const char *s);
+void list_commands(const char *title, struct cmdnames *main_cmds,
+		   struct cmdnames *other_cmds);
+
+#endif /* HELP_H */
diff --git a/tools/perf/util/levenshtein.c b/tools/perf/util/levenshtein.c
new file mode 100644
index 000000000000..e521d1516df6
--- /dev/null
+++ b/tools/perf/util/levenshtein.c
@@ -0,0 +1,84 @@
+#include "cache.h"
+#include "levenshtein.h"
+
+/*
+ * This function implements the Damerau-Levenshtein algorithm to
+ * calculate a distance between strings.
+ *
+ * Basically, it says how many letters need to be swapped, substituted,
+ * deleted from, or added to string1, at least, to get string2.
+ *
+ * The idea is to build a distance matrix for the substrings of both
+ * strings.  To avoid a large space complexity, only the last three rows
+ * are kept in memory (if swaps had the same or higher cost as one deletion
+ * plus one insertion, only two rows would be needed).
+ *
+ * At any stage, "i + 1" denotes the length of the current substring of
+ * string1 that the distance is calculated for.
+ *
+ * row2 holds the current row, row1 the previous row (i.e. for the substring
+ * of string1 of length "i"), and row0 the row before that.
+ *
+ * In other words, at the start of the big loop, row2[j + 1] contains the
+ * Damerau-Levenshtein distance between the substring of string1 of length
+ * "i" and the substring of string2 of length "j + 1".
+ *
+ * All the big loop does is determine the partial minimum-cost paths.
+ *
+ * It does so by calculating the costs of the path ending in characters
+ * i (in string1) and j (in string2), respectively, given that the last
+ * operation is a substition, a swap, a deletion, or an insertion.
+ *
+ * This implementation allows the costs to be weighted:
+ *
+ * - w (as in "sWap")
+ * - s (as in "Substitution")
+ * - a (for insertion, AKA "Add")
+ * - d (as in "Deletion")
+ *
+ * Note that this algorithm calculates a distance _iff_ d == a.
+ */
+int levenshtein(const char *string1, const char *string2,
+		int w, int s, int a, int d)
+{
+	int len1 = strlen(string1), len2 = strlen(string2);
+	int *row0 = malloc(sizeof(int) * (len2 + 1));
+	int *row1 = malloc(sizeof(int) * (len2 + 1));
+	int *row2 = malloc(sizeof(int) * (len2 + 1));
+	int i, j;
+
+	for (j = 0; j <= len2; j++)
+		row1[j] = j * a;
+	for (i = 0; i < len1; i++) {
+		int *dummy;
+
+		row2[0] = (i + 1) * d;
+		for (j = 0; j < len2; j++) {
+			/* substitution */
+			row2[j + 1] = row1[j] + s * (string1[i] != string2[j]);
+			/* swap */
+			if (i > 0 && j > 0 && string1[i - 1] == string2[j] &&
+					string1[i] == string2[j - 1] &&
+					row2[j + 1] > row0[j - 1] + w)
+				row2[j + 1] = row0[j - 1] + w;
+			/* deletion */
+			if (row2[j + 1] > row1[j + 1] + d)
+				row2[j + 1] = row1[j + 1] + d;
+			/* insertion */
+			if (row2[j + 1] > row2[j] + a)
+				row2[j + 1] = row2[j] + a;
+		}
+
+		dummy = row0;
+		row0 = row1;
+		row1 = row2;
+		row2 = dummy;
+	}
+
+	i = row1[len2];
+	free(row0);
+	free(row1);
+	free(row2);
+
+	return i;
+}
diff --git a/tools/perf/util/levenshtein.h b/tools/perf/util/levenshtein.h
new file mode 100644
index 000000000000..0173abeef52c
--- /dev/null
+++ b/tools/perf/util/levenshtein.h
@@ -0,0 +1,8 @@
+#ifndef LEVENSHTEIN_H
+#define LEVENSHTEIN_H
+
+int levenshtein(const char *string1, const char *string2,
+	int swap_penalty, int substition_penalty,
+	int insertion_penalty, int deletion_penalty);
+
+#endif
diff --git a/tools/perf/util/list.h b/tools/perf/util/list.h
new file mode 100644
index 000000000000..e2548e8072cf
--- /dev/null
+++ b/tools/perf/util/list.h
@@ -0,0 +1,603 @@
+#ifndef _LINUX_LIST_H
+#define _LINUX_LIST_H
+/*
+  Copyright (C) Cast of dozens, comes from the Linux kernel
+
+  This program is free software; you can redistribute it and/or modify it
+  under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+*/
+
+#include <stddef.h>
+
+/*
+ * These are non-NULL pointers that will result in page faults
+ * under normal circumstances, used to verify that nobody uses
+ * non-initialized list entries.
+ */
+#define LIST_POISON1 ((void *)0x00100100)
+#define LIST_POISON2 ((void *)0x00200200)
+
+/**
+ * container_of - cast a member of a structure out to the containing structure
+ * @ptr:	the pointer to the member.
+ * @type:	the type of the container struct this is embedded in.
+ * @member:	the name of the member within the struct.
+ *
+ */
+#define container_of(ptr, type, member) ({			\
+        const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
+        (type *)( (char *)__mptr - offsetof(type,member) );})
+
+/*
+ * Simple doubly linked list implementation.
+ *
+ * Some of the internal functions ("__xxx") are useful when
+ * manipulating whole lists rather than single entries, as
+ * sometimes we already know the next/prev entries and we can
+ * generate better code by using them directly rather than
+ * using the generic single-entry routines.
+ */
+
+struct list_head {
+	struct list_head *next, *prev;
+};
+
+#define LIST_HEAD_INIT(name) { &(name), &(name) }
+
+#define LIST_HEAD(name) \
+	struct list_head name = LIST_HEAD_INIT(name)
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+	list->next = list;
+	list->prev = list;
+}
+
+/*
+ * Insert a new entry between two known consecutive entries.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_add(struct list_head *new,
+			      struct list_head *prev,
+			      struct list_head *next)
+{
+	next->prev = new;
+	new->next = next;
+	new->prev = prev;
+	prev->next = new;
+}
+
+/**
+ * list_add - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it after
+ *
+ * Insert a new entry after the specified head.
+ * This is good for implementing stacks.
+ */
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+	__list_add(new, head, head->next);
+}
+
+/**
+ * list_add_tail - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it before
+ *
+ * Insert a new entry before the specified head.
+ * This is useful for implementing queues.
+ */
+static inline void list_add_tail(struct list_head *new, struct list_head *head)
+{
+	__list_add(new, head->prev, head);
+}
+
+/*
+ * Delete a list entry by making the prev/next entries
+ * point to each other.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_del(struct list_head * prev, struct list_head * next)
+{
+	next->prev = prev;
+	prev->next = next;
+}
+
+/**
+ * list_del - deletes entry from list.
+ * @entry: the element to delete from the list.
+ * Note: list_empty on entry does not return true after this, the entry is
+ * in an undefined state.
+ */
+static inline void list_del(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+	entry->next = LIST_POISON1;
+	entry->prev = LIST_POISON2;
+}
+
+/**
+ * list_del_range - deletes range of entries from list.
+ * @beging: first element in the range to delete from the list.
+ * @beging: first element in the range to delete from the list.
+ * Note: list_empty on the range of entries does not return true after this,
+ * the entries is in an undefined state.
+ */
+static inline void list_del_range(struct list_head *begin,
+				  struct list_head *end)
+{
+	begin->prev->next = end->next;
+	end->next->prev = begin->prev;
+}
+
+/**
+ * list_replace - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ * Note: if 'old' was empty, it will be overwritten.
+ */
+static inline void list_replace(struct list_head *old,
+				struct list_head *new)
+{
+	new->next = old->next;
+	new->next->prev = new;
+	new->prev = old->prev;
+	new->prev->next = new;
+}
+
+static inline void list_replace_init(struct list_head *old,
+					struct list_head *new)
+{
+	list_replace(old, new);
+	INIT_LIST_HEAD(old);
+}
+
+/**
+ * list_del_init - deletes entry from list and reinitialize it.
+ * @entry: the element to delete from the list.
+ */
+static inline void list_del_init(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+	INIT_LIST_HEAD(entry);
+}
+
+/**
+ * list_move - delete from one list and add as another's head
+ * @list: the entry to move
+ * @head: the head that will precede our entry
+ */
+static inline void list_move(struct list_head *list, struct list_head *head)
+{
+        __list_del(list->prev, list->next);
+        list_add(list, head);
+}
+
+/**
+ * list_move_tail - delete from one list and add as another's tail
+ * @list: the entry to move
+ * @head: the head that will follow our entry
+ */
+static inline void list_move_tail(struct list_head *list,
+				  struct list_head *head)
+{
+        __list_del(list->prev, list->next);
+        list_add_tail(list, head);
+}
+
+/**
+ * list_is_last - tests whether @list is the last entry in list @head
+ * @list: the entry to test
+ * @head: the head of the list
+ */
+static inline int list_is_last(const struct list_head *list,
+				const struct list_head *head)
+{
+	return list->next == head;
+}
+
+/**
+ * list_empty - tests whether a list is empty
+ * @head: the list to test.
+ */
+static inline int list_empty(const struct list_head *head)
+{
+	return head->next == head;
+}
+
+/**
+ * list_empty_careful - tests whether a list is empty and not being modified
+ * @head: the list to test
+ *
+ * Description:
+ * tests whether a list is empty _and_ checks that no other CPU might be
+ * in the process of modifying either member (next or prev)
+ *
+ * NOTE: using list_empty_careful() without synchronization
+ * can only be safe if the only activity that can happen
+ * to the list entry is list_del_init(). Eg. it cannot be used
+ * if another CPU could re-list_add() it.
+ */
+static inline int list_empty_careful(const struct list_head *head)
+{
+	struct list_head *next = head->next;
+	return (next == head) && (next == head->prev);
+}
+
+static inline void __list_splice(struct list_head *list,
+				 struct list_head *head)
+{
+	struct list_head *first = list->next;
+	struct list_head *last = list->prev;
+	struct list_head *at = head->next;
+
+	first->prev = head;
+	head->next = first;
+
+	last->next = at;
+	at->prev = last;
+}
+
+/**
+ * list_splice - join two lists
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice(struct list_head *list, struct list_head *head)
+{
+	if (!list_empty(list))
+		__list_splice(list, head);
+}
+
+/**
+ * list_splice_init - join two lists and reinitialise the emptied list.
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_init(struct list_head *list,
+				    struct list_head *head)
+{
+	if (!list_empty(list)) {
+		__list_splice(list, head);
+		INIT_LIST_HEAD(list);
+	}
+}
+
+/**
+ * list_entry - get the struct for this entry
+ * @ptr:	the &struct list_head pointer.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_entry(ptr, type, member) \
+	container_of(ptr, type, member)
+
+/**
+ * list_first_entry - get the first element from a list
+ * @ptr:       the list head to take the element from.
+ * @type:      the type of the struct this is embedded in.
+ * @member:    the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_first_entry(ptr, type, member) \
+	list_entry((ptr)->next, type, member)
+
+/**
+ * list_for_each	-	iterate over a list
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ */
+#define list_for_each(pos, head) \
+	for (pos = (head)->next; pos != (head); \
+        	pos = pos->next)
+
+/**
+ * __list_for_each	-	iterate over a list
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ *
+ * This variant differs from list_for_each() in that it's the
+ * simplest possible list iteration code, no prefetching is done.
+ * Use this for code that knows the list to be very short (empty
+ * or 1 entry) most of the time.
+ */
+#define __list_for_each(pos, head) \
+	for (pos = (head)->next; pos != (head); pos = pos->next)
+
+/**
+ * list_for_each_prev	-	iterate over a list backwards
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ */
+#define list_for_each_prev(pos, head) \
+	for (pos = (head)->prev; pos != (head); \
+        	pos = pos->prev)
+
+/**
+ * list_for_each_safe - iterate over a list safe against removal of list entry
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @n:		another &struct list_head to use as temporary storage
+ * @head:	the head for your list.
+ */
+#define list_for_each_safe(pos, n, head) \
+	for (pos = (head)->next, n = pos->next; pos != (head); \
+		pos = n, n = pos->next)
+
+/**
+ * list_for_each_entry	-	iterate over list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_for_each_entry(pos, head, member)				\
+	for (pos = list_entry((head)->next, typeof(*pos), member);	\
+	     &pos->member != (head); 	\
+	     pos = list_entry(pos->member.next, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_reverse - iterate backwards over list of given type.
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_for_each_entry_reverse(pos, head, member)			\
+	for (pos = list_entry((head)->prev, typeof(*pos), member);	\
+	     &pos->member != (head); 	\
+	     pos = list_entry(pos->member.prev, typeof(*pos), member))
+
+/**
+ * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue
+ * @pos:	the type * to use as a start point
+ * @head:	the head of the list
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Prepares a pos entry for use as a start point in list_for_each_entry_continue.
+ */
+#define list_prepare_entry(pos, head, member) \
+	((pos) ? : list_entry(head, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_continue - continue iteration over list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue(pos, head, member) 		\
+	for (pos = list_entry(pos->member.next, typeof(*pos), member);	\
+	     &pos->member != (head);	\
+	     pos = list_entry(pos->member.next, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_from - iterate over list of given type from the current point
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Iterate over list of given type, continuing from current position.
+ */
+#define list_for_each_entry_from(pos, head, member) 			\
+	for (; &pos->member != (head);	\
+	     pos = list_entry(pos->member.next, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_for_each_entry_safe(pos, n, head, member)			\
+	for (pos = list_entry((head)->next, typeof(*pos), member),	\
+		n = list_entry(pos->member.next, typeof(*pos), member);	\
+	     &pos->member != (head); 					\
+	     pos = n, n = list_entry(n->member.next, typeof(*n), member))
+
+/**
+ * list_for_each_entry_safe_continue
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Iterate over list of given type, continuing after current point,
+ * safe against removal of list entry.
+ */
+#define list_for_each_entry_safe_continue(pos, n, head, member) 		\
+	for (pos = list_entry(pos->member.next, typeof(*pos), member), 		\
+		n = list_entry(pos->member.next, typeof(*pos), member);		\
+	     &pos->member != (head);						\
+	     pos = n, n = list_entry(n->member.next, typeof(*n), member))
+
+/**
+ * list_for_each_entry_safe_from
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Iterate over list of given type from current point, safe against
+ * removal of list entry.
+ */
+#define list_for_each_entry_safe_from(pos, n, head, member) 			\
+	for (n = list_entry(pos->member.next, typeof(*pos), member);		\
+	     &pos->member != (head);						\
+	     pos = n, n = list_entry(n->member.next, typeof(*n), member))
+
+/**
+ * list_for_each_entry_safe_reverse
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Iterate backwards over list of given type, safe against removal
+ * of list entry.
+ */
+#define list_for_each_entry_safe_reverse(pos, n, head, member)		\
+	for (pos = list_entry((head)->prev, typeof(*pos), member),	\
+		n = list_entry(pos->member.prev, typeof(*pos), member);	\
+	     &pos->member != (head); 					\
+	     pos = n, n = list_entry(n->member.prev, typeof(*n), member))
+
+/*
+ * Double linked lists with a single pointer list head.
+ * Mostly useful for hash tables where the two pointer list head is
+ * too wasteful.
+ * You lose the ability to access the tail in O(1).
+ */
+
+struct hlist_head {
+	struct hlist_node *first;
+};
+
+struct hlist_node {
+	struct hlist_node *next, **pprev;
+};
+
+#define HLIST_HEAD_INIT { .first = NULL }
+#define HLIST_HEAD(name) struct hlist_head name = {  .first = NULL }
+#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL)
+static inline void INIT_HLIST_NODE(struct hlist_node *h)
+{
+	h->next = NULL;
+	h->pprev = NULL;
+}
+
+static inline int hlist_unhashed(const struct hlist_node *h)
+{
+	return !h->pprev;
+}
+
+static inline int hlist_empty(const struct hlist_head *h)
+{
+	return !h->first;
+}
+
+static inline void __hlist_del(struct hlist_node *n)
+{
+	struct hlist_node *next = n->next;
+	struct hlist_node **pprev = n->pprev;
+	*pprev = next;
+	if (next)
+		next->pprev = pprev;
+}
+
+static inline void hlist_del(struct hlist_node *n)
+{
+	__hlist_del(n);
+	n->next = LIST_POISON1;
+	n->pprev = LIST_POISON2;
+}
+
+static inline void hlist_del_init(struct hlist_node *n)
+{
+	if (!hlist_unhashed(n)) {
+		__hlist_del(n);
+		INIT_HLIST_NODE(n);
+	}
+}
+
+static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
+{
+	struct hlist_node *first = h->first;
+	n->next = first;
+	if (first)
+		first->pprev = &n->next;
+	h->first = n;
+	n->pprev = &h->first;
+}
+
+/* next must be != NULL */
+static inline void hlist_add_before(struct hlist_node *n,
+					struct hlist_node *next)
+{
+	n->pprev = next->pprev;
+	n->next = next;
+	next->pprev = &n->next;
+	*(n->pprev) = n;
+}
+
+static inline void hlist_add_after(struct hlist_node *n,
+					struct hlist_node *next)
+{
+	next->next = n->next;
+	n->next = next;
+	next->pprev = &n->next;
+
+	if(next->next)
+		next->next->pprev  = &next->next;
+}
+
+#define hlist_entry(ptr, type, member) container_of(ptr,type,member)
+
+#define hlist_for_each(pos, head) \
+	for (pos = (head)->first; pos; \
+	     pos = pos->next)
+
+#define hlist_for_each_safe(pos, n, head) \
+	for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
+	     pos = n)
+
+/**
+ * hlist_for_each_entry	- iterate over list of given type
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry(tpos, pos, head, member)			 \
+	for (pos = (head)->first;					 \
+	     pos && 			 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = pos->next)
+
+/**
+ * hlist_for_each_entry_continue - iterate over a hlist continuing after current point
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_continue(tpos, pos, member)		 \
+	for (pos = (pos)->next;						 \
+	     pos && 			 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = pos->next)
+
+/**
+ * hlist_for_each_entry_from - iterate over a hlist continuing from current point
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_from(tpos, pos, member)			 \
+	for (; pos && 			 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = pos->next)
+
+/**
+ * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @n:		another &struct hlist_node to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_safe(tpos, pos, n, head, member) 		 \
+	for (pos = (head)->first;					 \
+	     pos && ({ n = pos->next; 1; }) && 				 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = n)
+
+#endif
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
new file mode 100644
index 000000000000..a28bccae5458
--- /dev/null
+++ b/tools/perf/util/pager.c
@@ -0,0 +1,99 @@
+#include "cache.h"
+#include "run-command.h"
+#include "sigchain.h"
+
+/*
+ * This is split up from the rest of git so that we can do
+ * something different on Windows.
+ */
+
+static int spawned_pager;
+
+#ifndef __MINGW32__
+static void pager_preexec(void)
+{
+	/*
+	 * Work around bug in "less" by not starting it until we
+	 * have real input
+	 */
+	fd_set in;
+
+	FD_ZERO(&in);
+	FD_SET(0, &in);
+	select(1, &in, NULL, &in, NULL);
+
+	setenv("LESS", "FRSX", 0);
+}
+#endif
+
+static const char *pager_argv[] = { "sh", "-c", NULL, NULL };
+static struct child_process pager_process;
+
+static void wait_for_pager(void)
+{
+	fflush(stdout);
+	fflush(stderr);
+	/* signal EOF to pager */
+	close(1);
+	close(2);
+	finish_command(&pager_process);
+}
+
+static void wait_for_pager_signal(int signo)
+{
+	wait_for_pager();
+	sigchain_pop(signo);
+	raise(signo);
+}
+
+void setup_pager(void)
+{
+	const char *pager = getenv("PERF_PAGER");
+
+	if (!isatty(1))
+		return;
+	if (!pager) {
+		if (!pager_program)
+			perf_config(perf_default_config, NULL);
+		pager = pager_program;
+	}
+	if (!pager)
+		pager = getenv("PAGER");
+	if (!pager)
+		pager = "less";
+	else if (!*pager || !strcmp(pager, "cat"))
+		return;
+
+	spawned_pager = 1; /* means we are emitting to terminal */
+
+	/* spawn the pager */
+	pager_argv[2] = pager;
+	pager_process.argv = pager_argv;
+	pager_process.in = -1;
+#ifndef __MINGW32__
+	pager_process.preexec_cb = pager_preexec;
+#endif
+	if (start_command(&pager_process))
+		return;
+
+	/* original process continues, but writes to the pipe */
+	dup2(pager_process.in, 1);
+	if (isatty(2))
+		dup2(pager_process.in, 2);
+	close(pager_process.in);
+
+	/* this makes sure that the parent terminates after the pager */
+	sigchain_push_common(wait_for_pager_signal);
+	atexit(wait_for_pager);
+}
+
+int pager_in_use(void)
+{
+	const char *env;
+
+	if (spawned_pager)
+		return 1;
+
+	env = getenv("PERF_PAGER_IN_USE");
+	return env ? perf_config_bool("PERF_PAGER_IN_USE", env) : 0;
+}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
new file mode 100644
index 000000000000..9d5f1ca50e6f
--- /dev/null
+++ b/tools/perf/util/parse-events.c
@@ -0,0 +1,316 @@
+
+#include "../perf.h"
+#include "util.h"
+#include "parse-options.h"
+#include "parse-events.h"
+#include "exec_cmd.h"
+#include "string.h"
+
+extern char *strcasestr(const char *haystack, const char *needle);
+
+int					nr_counters;
+
+struct perf_counter_attr		attrs[MAX_COUNTERS];
+
+struct event_symbol {
+	__u8	type;
+	__u64	config;
+	char	*symbol;
+};
+
+#define C(x, y) .type = PERF_TYPE_##x, .config = PERF_COUNT_##y
+#define CR(x, y) .type = PERF_TYPE_##x, .config = y
+
+static struct event_symbol event_symbols[] = {
+  { C(HARDWARE, HW_CPU_CYCLES),		"cpu-cycles",		},
+  { C(HARDWARE, HW_CPU_CYCLES),		"cycles",		},
+  { C(HARDWARE, HW_INSTRUCTIONS),	"instructions",		},
+  { C(HARDWARE, HW_CACHE_REFERENCES),	"cache-references",	},
+  { C(HARDWARE, HW_CACHE_MISSES),	"cache-misses",		},
+  { C(HARDWARE, HW_BRANCH_INSTRUCTIONS),"branch-instructions",	},
+  { C(HARDWARE, HW_BRANCH_INSTRUCTIONS),"branches",		},
+  { C(HARDWARE, HW_BRANCH_MISSES),	"branch-misses",	},
+  { C(HARDWARE, HW_BUS_CYCLES),		"bus-cycles",		},
+
+  { C(SOFTWARE, SW_CPU_CLOCK),		"cpu-clock",		},
+  { C(SOFTWARE, SW_TASK_CLOCK),		"task-clock",		},
+  { C(SOFTWARE, SW_PAGE_FAULTS),	"page-faults",		},
+  { C(SOFTWARE, SW_PAGE_FAULTS),	"faults",		},
+  { C(SOFTWARE, SW_PAGE_FAULTS_MIN),	"minor-faults",		},
+  { C(SOFTWARE, SW_PAGE_FAULTS_MAJ),	"major-faults",		},
+  { C(SOFTWARE, SW_CONTEXT_SWITCHES),	"context-switches",	},
+  { C(SOFTWARE, SW_CONTEXT_SWITCHES),	"cs",			},
+  { C(SOFTWARE, SW_CPU_MIGRATIONS),	"cpu-migrations",	},
+  { C(SOFTWARE, SW_CPU_MIGRATIONS),	"migrations",		},
+};
+
+#define __PERF_COUNTER_FIELD(config, name) \
+	((config & PERF_COUNTER_##name##_MASK) >> PERF_COUNTER_##name##_SHIFT)
+
+#define PERF_COUNTER_RAW(config)	__PERF_COUNTER_FIELD(config, RAW)
+#define PERF_COUNTER_CONFIG(config)	__PERF_COUNTER_FIELD(config, CONFIG)
+#define PERF_COUNTER_TYPE(config)	__PERF_COUNTER_FIELD(config, TYPE)
+#define PERF_COUNTER_ID(config)		__PERF_COUNTER_FIELD(config, EVENT)
+
+static char *hw_event_names[] = {
+	"cycles",
+	"instructions",
+	"cache-references",
+	"cache-misses",
+	"branches",
+	"branch-misses",
+	"bus-cycles",
+};
+
+static char *sw_event_names[] = {
+	"cpu-clock-ticks",
+	"task-clock-ticks",
+	"page-faults",
+	"context-switches",
+	"CPU-migrations",
+	"minor-faults",
+	"major-faults",
+};
+
+#define MAX_ALIASES 8
+
+static char *hw_cache [][MAX_ALIASES] = {
+	{ "L1-data"		, "l1-d", "l1d", "l1"				},
+	{ "L1-instruction"	, "l1-i", "l1i"					},
+	{ "L2"			, "l2"						},
+	{ "Data-TLB"		, "dtlb", "d-tlb"				},
+	{ "Instruction-TLB"	, "itlb", "i-tlb"				},
+	{ "Branch"		, "bpu" , "btb", "bpc"				},
+};
+
+static char *hw_cache_op [][MAX_ALIASES] = {
+	{ "Load"		, "read"					},
+	{ "Store"		, "write"					},
+	{ "Prefetch"		, "speculative-read", "speculative-load"	},
+};
+
+static char *hw_cache_result [][MAX_ALIASES] = {
+	{ "Reference"		, "ops", "access"				},
+	{ "Miss"								},
+};
+
+char *event_name(int counter)
+{
+	__u64 config = attrs[counter].config;
+	int type = attrs[counter].type;
+	static char buf[32];
+
+	if (attrs[counter].type == PERF_TYPE_RAW) {
+		sprintf(buf, "raw 0x%llx", config);
+		return buf;
+	}
+
+	switch (type) {
+	case PERF_TYPE_HARDWARE:
+		if (config < PERF_COUNT_HW_MAX)
+			return hw_event_names[config];
+		return "unknown-hardware";
+
+	case PERF_TYPE_HW_CACHE: {
+		__u8 cache_type, cache_op, cache_result;
+		static char name[100];
+
+		cache_type   = (config >>  0) & 0xff;
+		if (cache_type > PERF_COUNT_HW_CACHE_MAX)
+			return "unknown-ext-hardware-cache-type";
+
+		cache_op     = (config >>  8) & 0xff;
+		if (cache_op > PERF_COUNT_HW_CACHE_OP_MAX)
+			return "unknown-ext-hardware-cache-op";
+
+		cache_result = (config >> 16) & 0xff;
+		if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX)
+			return "unknown-ext-hardware-cache-result";
+
+		sprintf(name, "%s-Cache-%s-%ses",
+			hw_cache[cache_type][0],
+			hw_cache_op[cache_op][0],
+			hw_cache_result[cache_result][0]);
+
+		return name;
+	}
+
+	case PERF_TYPE_SOFTWARE:
+		if (config < PERF_COUNT_SW_MAX)
+			return sw_event_names[config];
+		return "unknown-software";
+
+	default:
+		break;
+	}
+
+	return "unknown";
+}
+
+static int parse_aliases(const char *str, char *names[][MAX_ALIASES], int size)
+{
+	int i, j;
+
+	for (i = 0; i < size; i++) {
+		for (j = 0; j < MAX_ALIASES; j++) {
+			if (!names[i][j])
+				break;
+			if (strcasestr(str, names[i][j]))
+				return i;
+		}
+	}
+
+	return -1;
+}
+
+static int parse_generic_hw_symbols(const char *str, struct perf_counter_attr *attr)
+{
+	int cache_type = -1, cache_op = 0, cache_result = 0;
+
+	cache_type = parse_aliases(str, hw_cache, PERF_COUNT_HW_CACHE_MAX);
+	/*
+	 * No fallback - if we cannot get a clear cache type
+	 * then bail out:
+	 */
+	if (cache_type == -1)
+		return -EINVAL;
+
+	cache_op = parse_aliases(str, hw_cache_op, PERF_COUNT_HW_CACHE_OP_MAX);
+	/*
+	 * Fall back to reads:
+	 */
+	if (cache_op == -1)
+		cache_op = PERF_COUNT_HW_CACHE_OP_READ;
+
+	cache_result = parse_aliases(str, hw_cache_result,
+					PERF_COUNT_HW_CACHE_RESULT_MAX);
+	/*
+	 * Fall back to accesses:
+	 */
+	if (cache_result == -1)
+		cache_result = PERF_COUNT_HW_CACHE_RESULT_ACCESS;
+
+	attr->config = cache_type | (cache_op << 8) | (cache_result << 16);
+	attr->type = PERF_TYPE_HW_CACHE;
+
+	return 0;
+}
+
+/*
+ * Each event can have multiple symbolic names.
+ * Symbolic names are (almost) exactly matched.
+ */
+static int parse_event_symbols(const char *str, struct perf_counter_attr *attr)
+{
+	__u64 config, id;
+	int type;
+	unsigned int i;
+	const char *sep, *pstr;
+
+	if (str[0] == 'r' && hex2u64(str + 1, &config) > 0) {
+		attr->type = PERF_TYPE_RAW;
+		attr->config = config;
+
+		return 0;
+	}
+
+	pstr = str;
+	sep = strchr(pstr, ':');
+	if (sep) {
+		type = atoi(pstr);
+		pstr = sep + 1;
+		id = atoi(pstr);
+		sep = strchr(pstr, ':');
+		if (sep) {
+			pstr = sep + 1;
+			if (strchr(pstr, 'k'))
+				attr->exclude_user = 1;
+			if (strchr(pstr, 'u'))
+				attr->exclude_kernel = 1;
+		}
+		attr->type = type;
+		attr->config = id;
+
+		return 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(event_symbols); i++) {
+		if (!strncmp(str, event_symbols[i].symbol,
+			     strlen(event_symbols[i].symbol))) {
+
+			attr->type = event_symbols[i].type;
+			attr->config = event_symbols[i].config;
+
+			return 0;
+		}
+	}
+
+	return parse_generic_hw_symbols(str, attr);
+}
+
+int parse_events(const struct option *opt, const char *str, int unset)
+{
+	struct perf_counter_attr attr;
+	int ret;
+
+	memset(&attr, 0, sizeof(attr));
+again:
+	if (nr_counters == MAX_COUNTERS)
+		return -1;
+
+	ret = parse_event_symbols(str, &attr);
+	if (ret < 0)
+		return ret;
+
+	attrs[nr_counters] = attr;
+	nr_counters++;
+
+	str = strstr(str, ",");
+	if (str) {
+		str++;
+		goto again;
+	}
+
+	return 0;
+}
+
+static const char * const event_type_descriptors[] = {
+	"",
+	"Hardware event",
+	"Software event",
+	"Tracepoint event",
+	"Hardware cache event",
+};
+
+/*
+ * Print the help text for the event symbols:
+ */
+void print_events(void)
+{
+	struct event_symbol *syms = event_symbols;
+	unsigned int i, type, prev_type = -1;
+
+	fprintf(stderr, "\n");
+	fprintf(stderr, "List of pre-defined events (to be used in -e):\n");
+
+	for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
+		type = syms->type + 1;
+		if (type > ARRAY_SIZE(event_type_descriptors))
+			type = 0;
+
+		if (type != prev_type)
+			fprintf(stderr, "\n");
+
+		fprintf(stderr, "  %-30s [%s]\n", syms->symbol,
+			event_type_descriptors[type]);
+
+		prev_type = type;
+	}
+
+	fprintf(stderr, "\n");
+	fprintf(stderr, "  %-30s [raw hardware event descriptor]\n",
+		"rNNN");
+	fprintf(stderr, "\n");
+
+	exit(129);
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
new file mode 100644
index 000000000000..e3d552908e60
--- /dev/null
+++ b/tools/perf/util/parse-events.h
@@ -0,0 +1,17 @@
+
+/*
+ * Parse symbolic events/counts passed in as options:
+ */
+
+extern int			nr_counters;
+
+extern struct perf_counter_attr attrs[MAX_COUNTERS];
+
+extern char *event_name(int ctr);
+
+extern int parse_events(const struct option *opt, const char *str, int unset);
+
+#define EVENTS_HELP_MAX (128*1024)
+
+extern void print_events(void);
+
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
new file mode 100644
index 000000000000..b3affb1658d2
--- /dev/null
+++ b/tools/perf/util/parse-options.c
@@ -0,0 +1,508 @@
+#include "util.h"
+#include "parse-options.h"
+#include "cache.h"
+
+#define OPT_SHORT 1
+#define OPT_UNSET 2
+
+static int opterror(const struct option *opt, const char *reason, int flags)
+{
+	if (flags & OPT_SHORT)
+		return error("switch `%c' %s", opt->short_name, reason);
+	if (flags & OPT_UNSET)
+		return error("option `no-%s' %s", opt->long_name, reason);
+	return error("option `%s' %s", opt->long_name, reason);
+}
+
+static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt,
+		   int flags, const char **arg)
+{
+	if (p->opt) {
+		*arg = p->opt;
+		p->opt = NULL;
+	} else if (p->argc == 1 && (opt->flags & PARSE_OPT_LASTARG_DEFAULT)) {
+		*arg = (const char *)opt->defval;
+	} else if (p->argc > 1) {
+		p->argc--;
+		*arg = *++p->argv;
+	} else
+		return opterror(opt, "requires a value", flags);
+	return 0;
+}
+
+static int get_value(struct parse_opt_ctx_t *p,
+		     const struct option *opt, int flags)
+{
+	const char *s, *arg = NULL;
+	const int unset = flags & OPT_UNSET;
+
+	if (unset && p->opt)
+		return opterror(opt, "takes no value", flags);
+	if (unset && (opt->flags & PARSE_OPT_NONEG))
+		return opterror(opt, "isn't available", flags);
+
+	if (!(flags & OPT_SHORT) && p->opt) {
+		switch (opt->type) {
+		case OPTION_CALLBACK:
+			if (!(opt->flags & PARSE_OPT_NOARG))
+				break;
+			/* FALLTHROUGH */
+		case OPTION_BOOLEAN:
+		case OPTION_BIT:
+		case OPTION_SET_INT:
+		case OPTION_SET_PTR:
+			return opterror(opt, "takes no value", flags);
+		default:
+			break;
+		}
+	}
+
+	switch (opt->type) {
+	case OPTION_BIT:
+		if (unset)
+			*(int *)opt->value &= ~opt->defval;
+		else
+			*(int *)opt->value |= opt->defval;
+		return 0;
+
+	case OPTION_BOOLEAN:
+		*(int *)opt->value = unset ? 0 : *(int *)opt->value + 1;
+		return 0;
+
+	case OPTION_SET_INT:
+		*(int *)opt->value = unset ? 0 : opt->defval;
+		return 0;
+
+	case OPTION_SET_PTR:
+		*(void **)opt->value = unset ? NULL : (void *)opt->defval;
+		return 0;
+
+	case OPTION_STRING:
+		if (unset)
+			*(const char **)opt->value = NULL;
+		else if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
+			*(const char **)opt->value = (const char *)opt->defval;
+		else
+			return get_arg(p, opt, flags, (const char **)opt->value);
+		return 0;
+
+	case OPTION_CALLBACK:
+		if (unset)
+			return (*opt->callback)(opt, NULL, 1) ? (-1) : 0;
+		if (opt->flags & PARSE_OPT_NOARG)
+			return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
+			return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
+		if (get_arg(p, opt, flags, &arg))
+			return -1;
+		return (*opt->callback)(opt, arg, 0) ? (-1) : 0;
+
+	case OPTION_INTEGER:
+		if (unset) {
+			*(int *)opt->value = 0;
+			return 0;
+		}
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+			*(int *)opt->value = opt->defval;
+			return 0;
+		}
+		if (get_arg(p, opt, flags, &arg))
+			return -1;
+		*(int *)opt->value = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return opterror(opt, "expects a numerical value", flags);
+		return 0;
+
+	case OPTION_LONG:
+		if (unset) {
+			*(long *)opt->value = 0;
+			return 0;
+		}
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+			*(long *)opt->value = opt->defval;
+			return 0;
+		}
+		if (get_arg(p, opt, flags, &arg))
+			return -1;
+		*(long *)opt->value = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return opterror(opt, "expects a numerical value", flags);
+		return 0;
+
+	default:
+		die("should not happen, someone must be hit on the forehead");
+	}
+}
+
+static int parse_short_opt(struct parse_opt_ctx_t *p, const struct option *options)
+{
+	for (; options->type != OPTION_END; options++) {
+		if (options->short_name == *p->opt) {
+			p->opt = p->opt[1] ? p->opt + 1 : NULL;
+			return get_value(p, options, OPT_SHORT);
+		}
+	}
+	return -2;
+}
+
+static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
+                          const struct option *options)
+{
+	const char *arg_end = strchr(arg, '=');
+	const struct option *abbrev_option = NULL, *ambiguous_option = NULL;
+	int abbrev_flags = 0, ambiguous_flags = 0;
+
+	if (!arg_end)
+		arg_end = arg + strlen(arg);
+
+	for (; options->type != OPTION_END; options++) {
+		const char *rest;
+		int flags = 0;
+
+		if (!options->long_name)
+			continue;
+
+		rest = skip_prefix(arg, options->long_name);
+		if (options->type == OPTION_ARGUMENT) {
+			if (!rest)
+				continue;
+			if (*rest == '=')
+				return opterror(options, "takes no value", flags);
+			if (*rest)
+				continue;
+			p->out[p->cpidx++] = arg - 2;
+			return 0;
+		}
+		if (!rest) {
+			/* abbreviated? */
+			if (!strncmp(options->long_name, arg, arg_end - arg)) {
+is_abbreviated:
+				if (abbrev_option) {
+					/*
+					 * If this is abbreviated, it is
+					 * ambiguous. So when there is no
+					 * exact match later, we need to
+					 * error out.
+					 */
+					ambiguous_option = abbrev_option;
+					ambiguous_flags = abbrev_flags;
+				}
+				if (!(flags & OPT_UNSET) && *arg_end)
+					p->opt = arg_end + 1;
+				abbrev_option = options;
+				abbrev_flags = flags;
+				continue;
+			}
+			/* negated and abbreviated very much? */
+			if (!prefixcmp("no-", arg)) {
+				flags |= OPT_UNSET;
+				goto is_abbreviated;
+			}
+			/* negated? */
+			if (strncmp(arg, "no-", 3))
+				continue;
+			flags |= OPT_UNSET;
+			rest = skip_prefix(arg + 3, options->long_name);
+			/* abbreviated and negated? */
+			if (!rest && !prefixcmp(options->long_name, arg + 3))
+				goto is_abbreviated;
+			if (!rest)
+				continue;
+		}
+		if (*rest) {
+			if (*rest != '=')
+				continue;
+			p->opt = rest + 1;
+		}
+		return get_value(p, options, flags);
+	}
+
+	if (ambiguous_option)
+		return error("Ambiguous option: %s "
+			"(could be --%s%s or --%s%s)",
+			arg,
+			(ambiguous_flags & OPT_UNSET) ?  "no-" : "",
+			ambiguous_option->long_name,
+			(abbrev_flags & OPT_UNSET) ?  "no-" : "",
+			abbrev_option->long_name);
+	if (abbrev_option)
+		return get_value(p, abbrev_option, abbrev_flags);
+	return -2;
+}
+
+static void check_typos(const char *arg, const struct option *options)
+{
+	if (strlen(arg) < 3)
+		return;
+
+	if (!prefixcmp(arg, "no-")) {
+		error ("did you mean `--%s` (with two dashes ?)", arg);
+		exit(129);
+	}
+
+	for (; options->type != OPTION_END; options++) {
+		if (!options->long_name)
+			continue;
+		if (!prefixcmp(options->long_name, arg)) {
+			error ("did you mean `--%s` (with two dashes ?)", arg);
+			exit(129);
+		}
+	}
+}
+
+void parse_options_start(struct parse_opt_ctx_t *ctx,
+			 int argc, const char **argv, int flags)
+{
+	memset(ctx, 0, sizeof(*ctx));
+	ctx->argc = argc - 1;
+	ctx->argv = argv + 1;
+	ctx->out  = argv;
+	ctx->cpidx = ((flags & PARSE_OPT_KEEP_ARGV0) != 0);
+	ctx->flags = flags;
+	if ((flags & PARSE_OPT_KEEP_UNKNOWN) &&
+	    (flags & PARSE_OPT_STOP_AT_NON_OPTION))
+		die("STOP_AT_NON_OPTION and KEEP_UNKNOWN don't go together");
+}
+
+static int usage_with_options_internal(const char * const *,
+				       const struct option *, int);
+
+int parse_options_step(struct parse_opt_ctx_t *ctx,
+		       const struct option *options,
+		       const char * const usagestr[])
+{
+	int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
+
+	/* we must reset ->opt, unknown short option leave it dangling */
+	ctx->opt = NULL;
+
+	for (; ctx->argc; ctx->argc--, ctx->argv++) {
+		const char *arg = ctx->argv[0];
+
+		if (*arg != '-' || !arg[1]) {
+			if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION)
+				break;
+			ctx->out[ctx->cpidx++] = ctx->argv[0];
+			continue;
+		}
+
+		if (arg[1] != '-') {
+			ctx->opt = arg + 1;
+			if (internal_help && *ctx->opt == 'h')
+				return parse_options_usage(usagestr, options);
+			switch (parse_short_opt(ctx, options)) {
+			case -1:
+				return parse_options_usage(usagestr, options);
+			case -2:
+				goto unknown;
+			}
+			if (ctx->opt)
+				check_typos(arg + 1, options);
+			while (ctx->opt) {
+				if (internal_help && *ctx->opt == 'h')
+					return parse_options_usage(usagestr, options);
+				switch (parse_short_opt(ctx, options)) {
+				case -1:
+					return parse_options_usage(usagestr, options);
+				case -2:
+					/* fake a short option thing to hide the fact that we may have
+					 * started to parse aggregated stuff
+					 *
+					 * This is leaky, too bad.
+					 */
+					ctx->argv[0] = strdup(ctx->opt - 1);
+					*(char *)ctx->argv[0] = '-';
+					goto unknown;
+				}
+			}
+			continue;
+		}
+
+		if (!arg[2]) { /* "--" */
+			if (!(ctx->flags & PARSE_OPT_KEEP_DASHDASH)) {
+				ctx->argc--;
+				ctx->argv++;
+			}
+			break;
+		}
+
+		if (internal_help && !strcmp(arg + 2, "help-all"))
+			return usage_with_options_internal(usagestr, options, 1);
+		if (internal_help && !strcmp(arg + 2, "help"))
+			return parse_options_usage(usagestr, options);
+		switch (parse_long_opt(ctx, arg + 2, options)) {
+		case -1:
+			return parse_options_usage(usagestr, options);
+		case -2:
+			goto unknown;
+		}
+		continue;
+unknown:
+		if (!(ctx->flags & PARSE_OPT_KEEP_UNKNOWN))
+			return PARSE_OPT_UNKNOWN;
+		ctx->out[ctx->cpidx++] = ctx->argv[0];
+		ctx->opt = NULL;
+	}
+	return PARSE_OPT_DONE;
+}
+
+int parse_options_end(struct parse_opt_ctx_t *ctx)
+{
+	memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out));
+	ctx->out[ctx->cpidx + ctx->argc] = NULL;
+	return ctx->cpidx + ctx->argc;
+}
+
+int parse_options(int argc, const char **argv, const struct option *options,
+		  const char * const usagestr[], int flags)
+{
+	struct parse_opt_ctx_t ctx;
+
+	parse_options_start(&ctx, argc, argv, flags);
+	switch (parse_options_step(&ctx, options, usagestr)) {
+	case PARSE_OPT_HELP:
+		exit(129);
+	case PARSE_OPT_DONE:
+		break;
+	default: /* PARSE_OPT_UNKNOWN */
+		if (ctx.argv[0][1] == '-') {
+			error("unknown option `%s'", ctx.argv[0] + 2);
+		} else {
+			error("unknown switch `%c'", *ctx.opt);
+		}
+		usage_with_options(usagestr, options);
+	}
+
+	return parse_options_end(&ctx);
+}
+
+#define USAGE_OPTS_WIDTH 24
+#define USAGE_GAP         2
+
+int usage_with_options_internal(const char * const *usagestr,
+				const struct option *opts, int full)
+{
+	if (!usagestr)
+		return PARSE_OPT_HELP;
+
+	fprintf(stderr, "\n usage: %s\n", *usagestr++);
+	while (*usagestr && **usagestr)
+		fprintf(stderr, "    or: %s\n", *usagestr++);
+	while (*usagestr) {
+		fprintf(stderr, "%s%s\n",
+				**usagestr ? "    " : "",
+				*usagestr);
+		usagestr++;
+	}
+
+	if (opts->type != OPTION_GROUP)
+		fputc('\n', stderr);
+
+	for (; opts->type != OPTION_END; opts++) {
+		size_t pos;
+		int pad;
+
+		if (opts->type == OPTION_GROUP) {
+			fputc('\n', stderr);
+			if (*opts->help)
+				fprintf(stderr, "%s\n", opts->help);
+			continue;
+		}
+		if (!full && (opts->flags & PARSE_OPT_HIDDEN))
+			continue;
+
+		pos = fprintf(stderr, "    ");
+		if (opts->short_name)
+			pos += fprintf(stderr, "-%c", opts->short_name);
+		if (opts->long_name && opts->short_name)
+			pos += fprintf(stderr, ", ");
+		if (opts->long_name)
+			pos += fprintf(stderr, "--%s", opts->long_name);
+
+		switch (opts->type) {
+		case OPTION_ARGUMENT:
+			break;
+		case OPTION_INTEGER:
+			if (opts->flags & PARSE_OPT_OPTARG)
+				if (opts->long_name)
+					pos += fprintf(stderr, "[=<n>]");
+				else
+					pos += fprintf(stderr, "[<n>]");
+			else
+				pos += fprintf(stderr, " <n>");
+			break;
+		case OPTION_CALLBACK:
+			if (opts->flags & PARSE_OPT_NOARG)
+				break;
+			/* FALLTHROUGH */
+		case OPTION_STRING:
+			if (opts->argh) {
+				if (opts->flags & PARSE_OPT_OPTARG)
+					if (opts->long_name)
+						pos += fprintf(stderr, "[=<%s>]", opts->argh);
+					else
+						pos += fprintf(stderr, "[<%s>]", opts->argh);
+				else
+					pos += fprintf(stderr, " <%s>", opts->argh);
+			} else {
+				if (opts->flags & PARSE_OPT_OPTARG)
+					if (opts->long_name)
+						pos += fprintf(stderr, "[=...]");
+					else
+						pos += fprintf(stderr, "[...]");
+				else
+					pos += fprintf(stderr, " ...");
+			}
+			break;
+		default: /* OPTION_{BIT,BOOLEAN,SET_INT,SET_PTR} */
+			break;
+		}
+
+		if (pos <= USAGE_OPTS_WIDTH)
+			pad = USAGE_OPTS_WIDTH - pos;
+		else {
+			fputc('\n', stderr);
+			pad = USAGE_OPTS_WIDTH;
+		}
+		fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
+	}
+	fputc('\n', stderr);
+
+	return PARSE_OPT_HELP;
+}
+
+void usage_with_options(const char * const *usagestr,
+			const struct option *opts)
+{
+	usage_with_options_internal(usagestr, opts, 0);
+	exit(129);
+}
+
+int parse_options_usage(const char * const *usagestr,
+			const struct option *opts)
+{
+	return usage_with_options_internal(usagestr, opts, 0);
+}
+
+
+int parse_opt_verbosity_cb(const struct option *opt, const char *arg,
+			   int unset)
+{
+	int *target = opt->value;
+
+	if (unset)
+		/* --no-quiet, --no-verbose */
+		*target = 0;
+	else if (opt->short_name == 'v') {
+		if (*target >= 0)
+			(*target)++;
+		else
+			*target = 1;
+	} else {
+		if (*target <= 0)
+			(*target)--;
+		else
+			*target = -1;
+	}
+	return 0;
+}
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
new file mode 100644
index 000000000000..a1039a6ce0eb
--- /dev/null
+++ b/tools/perf/util/parse-options.h
@@ -0,0 +1,174 @@
+#ifndef PARSE_OPTIONS_H
+#define PARSE_OPTIONS_H
+
+enum parse_opt_type {
+	/* special types */
+	OPTION_END,
+	OPTION_ARGUMENT,
+	OPTION_GROUP,
+	/* options with no arguments */
+	OPTION_BIT,
+	OPTION_BOOLEAN, /* _INCR would have been a better name */
+	OPTION_SET_INT,
+	OPTION_SET_PTR,
+	/* options with arguments (usually) */
+	OPTION_STRING,
+	OPTION_INTEGER,
+	OPTION_LONG,
+	OPTION_CALLBACK,
+};
+
+enum parse_opt_flags {
+	PARSE_OPT_KEEP_DASHDASH = 1,
+	PARSE_OPT_STOP_AT_NON_OPTION = 2,
+	PARSE_OPT_KEEP_ARGV0 = 4,
+	PARSE_OPT_KEEP_UNKNOWN = 8,
+	PARSE_OPT_NO_INTERNAL_HELP = 16,
+};
+
+enum parse_opt_option_flags {
+	PARSE_OPT_OPTARG  = 1,
+	PARSE_OPT_NOARG   = 2,
+	PARSE_OPT_NONEG   = 4,
+	PARSE_OPT_HIDDEN  = 8,
+	PARSE_OPT_LASTARG_DEFAULT = 16,
+};
+
+struct option;
+typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
+
+/*
+ * `type`::
+ *   holds the type of the option, you must have an OPTION_END last in your
+ *   array.
+ *
+ * `short_name`::
+ *   the character to use as a short option name, '\0' if none.
+ *
+ * `long_name`::
+ *   the long option name, without the leading dashes, NULL if none.
+ *
+ * `value`::
+ *   stores pointers to the values to be filled.
+ *
+ * `argh`::
+ *   token to explain the kind of argument this option wants. Keep it
+ *   homogenous across the repository.
+ *
+ * `help`::
+ *   the short help associated to what the option does.
+ *   Must never be NULL (except for OPTION_END).
+ *   OPTION_GROUP uses this pointer to store the group header.
+ *
+ * `flags`::
+ *   mask of parse_opt_option_flags.
+ *   PARSE_OPT_OPTARG: says that the argument is optionnal (not for BOOLEANs)
+ *   PARSE_OPT_NOARG: says that this option takes no argument, for CALLBACKs
+ *   PARSE_OPT_NONEG: says that this option cannot be negated
+ *   PARSE_OPT_HIDDEN this option is skipped in the default usage, showed in
+ *                    the long one.
+ *
+ * `callback`::
+ *   pointer to the callback to use for OPTION_CALLBACK.
+ *
+ * `defval`::
+ *   default value to fill (*->value) with for PARSE_OPT_OPTARG.
+ *   OPTION_{BIT,SET_INT,SET_PTR} store the {mask,integer,pointer} to put in
+ *   the value when met.
+ *   CALLBACKS can use it like they want.
+ */
+struct option {
+	enum parse_opt_type type;
+	int short_name;
+	const char *long_name;
+	void *value;
+	const char *argh;
+	const char *help;
+
+	int flags;
+	parse_opt_cb *callback;
+	intptr_t defval;
+};
+
+#define OPT_END()                   { OPTION_END }
+#define OPT_ARGUMENT(l, h)          { OPTION_ARGUMENT, 0, (l), NULL, NULL, (h) }
+#define OPT_GROUP(h)                { OPTION_GROUP, 0, NULL, NULL, NULL, (h) }
+#define OPT_BIT(s, l, v, h, b)      { OPTION_BIT, (s), (l), (v), NULL, (h), 0, NULL, (b) }
+#define OPT_BOOLEAN(s, l, v, h)     { OPTION_BOOLEAN, (s), (l), (v), NULL, (h) }
+#define OPT_SET_INT(s, l, v, h, i)  { OPTION_SET_INT, (s), (l), (v), NULL, (h), 0, NULL, (i) }
+#define OPT_SET_PTR(s, l, v, h, p)  { OPTION_SET_PTR, (s), (l), (v), NULL, (h), 0, NULL, (p) }
+#define OPT_INTEGER(s, l, v, h)     { OPTION_INTEGER, (s), (l), (v), NULL, (h) }
+#define OPT_LONG(s, l, v, h)        { OPTION_LONG, (s), (l), (v), NULL, (h) }
+#define OPT_STRING(s, l, v, a, h)   { OPTION_STRING,  (s), (l), (v), (a), (h) }
+#define OPT_DATE(s, l, v, h) \
+	{ OPTION_CALLBACK, (s), (l), (v), "time",(h), 0, \
+	  parse_opt_approxidate_cb }
+#define OPT_CALLBACK(s, l, v, a, h, f) \
+	{ OPTION_CALLBACK, (s), (l), (v), (a), (h), 0, (f) }
+
+/* parse_options() will filter out the processed options and leave the
+ * non-option argments in argv[].
+ * Returns the number of arguments left in argv[].
+ */
+extern int parse_options(int argc, const char **argv,
+                         const struct option *options,
+                         const char * const usagestr[], int flags);
+
+extern NORETURN void usage_with_options(const char * const *usagestr,
+                                        const struct option *options);
+
+/*----- incremantal advanced APIs -----*/
+
+enum {
+	PARSE_OPT_HELP = -1,
+	PARSE_OPT_DONE,
+	PARSE_OPT_UNKNOWN,
+};
+
+/*
+ * It's okay for the caller to consume argv/argc in the usual way.
+ * Other fields of that structure are private to parse-options and should not
+ * be modified in any way.
+ */
+struct parse_opt_ctx_t {
+	const char **argv;
+	const char **out;
+	int argc, cpidx;
+	const char *opt;
+	int flags;
+};
+
+extern int parse_options_usage(const char * const *usagestr,
+			       const struct option *opts);
+
+extern void parse_options_start(struct parse_opt_ctx_t *ctx,
+				int argc, const char **argv, int flags);
+
+extern int parse_options_step(struct parse_opt_ctx_t *ctx,
+			      const struct option *options,
+			      const char * const usagestr[]);
+
+extern int parse_options_end(struct parse_opt_ctx_t *ctx);
+
+
+/*----- some often used options -----*/
+extern int parse_opt_abbrev_cb(const struct option *, const char *, int);
+extern int parse_opt_approxidate_cb(const struct option *, const char *, int);
+extern int parse_opt_verbosity_cb(const struct option *, const char *, int);
+
+#define OPT__VERBOSE(var)  OPT_BOOLEAN('v', "verbose", (var), "be verbose")
+#define OPT__QUIET(var)    OPT_BOOLEAN('q', "quiet",   (var), "be quiet")
+#define OPT__VERBOSITY(var) \
+	{ OPTION_CALLBACK, 'v', "verbose", (var), NULL, "be more verbose", \
+	  PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 }, \
+	{ OPTION_CALLBACK, 'q', "quiet", (var), NULL, "be more quiet", \
+	  PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 }
+#define OPT__DRY_RUN(var)  OPT_BOOLEAN('n', "dry-run", (var), "dry run")
+#define OPT__ABBREV(var)  \
+	{ OPTION_CALLBACK, 0, "abbrev", (var), "n", \
+	  "use <n> digits to display SHA-1s", \
+	  PARSE_OPT_OPTARG, &parse_opt_abbrev_cb, 0 }
+
+extern const char *parse_options_fix_filename(const char *prefix, const char *file);
+
+#endif
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
new file mode 100644
index 000000000000..a501a40dd2cb
--- /dev/null
+++ b/tools/perf/util/path.c
@@ -0,0 +1,353 @@
+/*
+ * I'm tired of doing "vsnprintf()" etc just to open a
+ * file, so here's a "return static buffer with printf"
+ * interface for paths.
+ *
+ * It's obviously not thread-safe. Sue me. But it's quite
+ * useful for doing things like
+ *
+ *   f = open(mkpath("%s/%s.perf", base, name), O_RDONLY);
+ *
+ * which is what it's designed for.
+ */
+#include "cache.h"
+
+static char bad_path[] = "/bad-path/";
+/*
+ * Two hacks:
+ */
+
+static char *get_perf_dir(void)
+{
+	return ".";
+}
+
+size_t strlcpy(char *dest, const char *src, size_t size)
+{
+	size_t ret = strlen(src);
+
+	if (size) {
+		size_t len = (ret >= size) ? size - 1 : ret;
+		memcpy(dest, src, len);
+		dest[len] = '\0';
+	}
+	return ret;
+}
+
+
+static char *get_pathname(void)
+{
+	static char pathname_array[4][PATH_MAX];
+	static int index;
+	return pathname_array[3 & ++index];
+}
+
+static char *cleanup_path(char *path)
+{
+	/* Clean it up */
+	if (!memcmp(path, "./", 2)) {
+		path += 2;
+		while (*path == '/')
+			path++;
+	}
+	return path;
+}
+
+char *mksnpath(char *buf, size_t n, const char *fmt, ...)
+{
+	va_list args;
+	unsigned len;
+
+	va_start(args, fmt);
+	len = vsnprintf(buf, n, fmt, args);
+	va_end(args);
+	if (len >= n) {
+		strlcpy(buf, bad_path, n);
+		return buf;
+	}
+	return cleanup_path(buf);
+}
+
+static char *perf_vsnpath(char *buf, size_t n, const char *fmt, va_list args)
+{
+	const char *perf_dir = get_perf_dir();
+	size_t len;
+
+	len = strlen(perf_dir);
+	if (n < len + 1)
+		goto bad;
+	memcpy(buf, perf_dir, len);
+	if (len && !is_dir_sep(perf_dir[len-1]))
+		buf[len++] = '/';
+	len += vsnprintf(buf + len, n - len, fmt, args);
+	if (len >= n)
+		goto bad;
+	return cleanup_path(buf);
+bad:
+	strlcpy(buf, bad_path, n);
+	return buf;
+}
+
+char *perf_snpath(char *buf, size_t n, const char *fmt, ...)
+{
+	va_list args;
+	va_start(args, fmt);
+	(void)perf_vsnpath(buf, n, fmt, args);
+	va_end(args);
+	return buf;
+}
+
+char *perf_pathdup(const char *fmt, ...)
+{
+	char path[PATH_MAX];
+	va_list args;
+	va_start(args, fmt);
+	(void)perf_vsnpath(path, sizeof(path), fmt, args);
+	va_end(args);
+	return xstrdup(path);
+}
+
+char *mkpath(const char *fmt, ...)
+{
+	va_list args;
+	unsigned len;
+	char *pathname = get_pathname();
+
+	va_start(args, fmt);
+	len = vsnprintf(pathname, PATH_MAX, fmt, args);
+	va_end(args);
+	if (len >= PATH_MAX)
+		return bad_path;
+	return cleanup_path(pathname);
+}
+
+char *perf_path(const char *fmt, ...)
+{
+	const char *perf_dir = get_perf_dir();
+	char *pathname = get_pathname();
+	va_list args;
+	unsigned len;
+
+	len = strlen(perf_dir);
+	if (len > PATH_MAX-100)
+		return bad_path;
+	memcpy(pathname, perf_dir, len);
+	if (len && perf_dir[len-1] != '/')
+		pathname[len++] = '/';
+	va_start(args, fmt);
+	len += vsnprintf(pathname + len, PATH_MAX - len, fmt, args);
+	va_end(args);
+	if (len >= PATH_MAX)
+		return bad_path;
+	return cleanup_path(pathname);
+}
+
+
+/* perf_mkstemp() - create tmp file honoring TMPDIR variable */
+int perf_mkstemp(char *path, size_t len, const char *template)
+{
+	const char *tmp;
+	size_t n;
+
+	tmp = getenv("TMPDIR");
+	if (!tmp)
+		tmp = "/tmp";
+	n = snprintf(path, len, "%s/%s", tmp, template);
+	if (len <= n) {
+		errno = ENAMETOOLONG;
+		return -1;
+	}
+	return mkstemp(path);
+}
+
+
+const char *make_relative_path(const char *abs, const char *base)
+{
+	static char buf[PATH_MAX + 1];
+	int baselen;
+	if (!base)
+		return abs;
+	baselen = strlen(base);
+	if (prefixcmp(abs, base))
+		return abs;
+	if (abs[baselen] == '/')
+		baselen++;
+	else if (base[baselen - 1] != '/')
+		return abs;
+	strcpy(buf, abs + baselen);
+	return buf;
+}
+
+/*
+ * It is okay if dst == src, but they should not overlap otherwise.
+ *
+ * Performs the following normalizations on src, storing the result in dst:
+ * - Ensures that components are separated by '/' (Windows only)
+ * - Squashes sequences of '/'.
+ * - Removes "." components.
+ * - Removes ".." components, and the components the precede them.
+ * Returns failure (non-zero) if a ".." component appears as first path
+ * component anytime during the normalization. Otherwise, returns success (0).
+ *
+ * Note that this function is purely textual.  It does not follow symlinks,
+ * verify the existence of the path, or make any system calls.
+ */
+int normalize_path_copy(char *dst, const char *src)
+{
+	char *dst0;
+
+	if (has_dos_drive_prefix(src)) {
+		*dst++ = *src++;
+		*dst++ = *src++;
+	}
+	dst0 = dst;
+
+	if (is_dir_sep(*src)) {
+		*dst++ = '/';
+		while (is_dir_sep(*src))
+			src++;
+	}
+
+	for (;;) {
+		char c = *src;
+
+		/*
+		 * A path component that begins with . could be
+		 * special:
+		 * (1) "." and ends   -- ignore and terminate.
+		 * (2) "./"           -- ignore them, eat slash and continue.
+		 * (3) ".." and ends  -- strip one and terminate.
+		 * (4) "../"          -- strip one, eat slash and continue.
+		 */
+		if (c == '.') {
+			if (!src[1]) {
+				/* (1) */
+				src++;
+			} else if (is_dir_sep(src[1])) {
+				/* (2) */
+				src += 2;
+				while (is_dir_sep(*src))
+					src++;
+				continue;
+			} else if (src[1] == '.') {
+				if (!src[2]) {
+					/* (3) */
+					src += 2;
+					goto up_one;
+				} else if (is_dir_sep(src[2])) {
+					/* (4) */
+					src += 3;
+					while (is_dir_sep(*src))
+						src++;
+					goto up_one;
+				}
+			}
+		}
+
+		/* copy up to the next '/', and eat all '/' */
+		while ((c = *src++) != '\0' && !is_dir_sep(c))
+			*dst++ = c;
+		if (is_dir_sep(c)) {
+			*dst++ = '/';
+			while (is_dir_sep(c))
+				c = *src++;
+			src--;
+		} else if (!c)
+			break;
+		continue;
+
+	up_one:
+		/*
+		 * dst0..dst is prefix portion, and dst[-1] is '/';
+		 * go up one level.
+		 */
+		dst--;	/* go to trailing '/' */
+		if (dst <= dst0)
+			return -1;
+		/* Windows: dst[-1] cannot be backslash anymore */
+		while (dst0 < dst && dst[-1] != '/')
+			dst--;
+	}
+	*dst = '\0';
+	return 0;
+}
+
+/*
+ * path = Canonical absolute path
+ * prefix_list = Colon-separated list of absolute paths
+ *
+ * Determines, for each path in prefix_list, whether the "prefix" really
+ * is an ancestor directory of path.  Returns the length of the longest
+ * ancestor directory, excluding any trailing slashes, or -1 if no prefix
+ * is an ancestor.  (Note that this means 0 is returned if prefix_list is
+ * "/".) "/foo" is not considered an ancestor of "/foobar".  Directories
+ * are not considered to be their own ancestors.  path must be in a
+ * canonical form: empty components, or "." or ".." components are not
+ * allowed.  prefix_list may be null, which is like "".
+ */
+int longest_ancestor_length(const char *path, const char *prefix_list)
+{
+	char buf[PATH_MAX+1];
+	const char *ceil, *colon;
+	int len, max_len = -1;
+
+	if (prefix_list == NULL || !strcmp(path, "/"))
+		return -1;
+
+	for (colon = ceil = prefix_list; *colon; ceil = colon+1) {
+		for (colon = ceil; *colon && *colon != PATH_SEP; colon++);
+		len = colon - ceil;
+		if (len == 0 || len > PATH_MAX || !is_absolute_path(ceil))
+			continue;
+		strlcpy(buf, ceil, len+1);
+		if (normalize_path_copy(buf, buf) < 0)
+			continue;
+		len = strlen(buf);
+		if (len > 0 && buf[len-1] == '/')
+			buf[--len] = '\0';
+
+		if (!strncmp(path, buf, len) &&
+		    path[len] == '/' &&
+		    len > max_len) {
+			max_len = len;
+		}
+	}
+
+	return max_len;
+}
+
+/* strip arbitrary amount of directory separators at end of path */
+static inline int chomp_trailing_dir_sep(const char *path, int len)
+{
+	while (len && is_dir_sep(path[len - 1]))
+		len--;
+	return len;
+}
+
+/*
+ * If path ends with suffix (complete path components), returns the
+ * part before suffix (sans trailing directory separators).
+ * Otherwise returns NULL.
+ */
+char *strip_path_suffix(const char *path, const char *suffix)
+{
+	int path_len = strlen(path), suffix_len = strlen(suffix);
+
+	while (suffix_len) {
+		if (!path_len)
+			return NULL;
+
+		if (is_dir_sep(path[path_len - 1])) {
+			if (!is_dir_sep(suffix[suffix_len - 1]))
+				return NULL;
+			path_len = chomp_trailing_dir_sep(path, path_len);
+			suffix_len = chomp_trailing_dir_sep(suffix, suffix_len);
+		}
+		else if (path[--path_len] != suffix[--suffix_len])
+			return NULL;
+	}
+
+	if (path_len && !is_dir_sep(path[path_len - 1]))
+		return NULL;
+	return xstrndup(path, chomp_trailing_dir_sep(path, path_len));
+}
diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c
new file mode 100644
index 000000000000..f18c5212bc92
--- /dev/null
+++ b/tools/perf/util/quote.c
@@ -0,0 +1,481 @@
+#include "cache.h"
+#include "quote.h"
+
+int quote_path_fully = 1;
+
+/* Help to copy the thing properly quoted for the shell safety.
+ * any single quote is replaced with '\'', any exclamation point
+ * is replaced with '\!', and the whole thing is enclosed in a
+ *
+ * E.g.
+ *  original     sq_quote     result
+ *  name     ==> name      ==> 'name'
+ *  a b      ==> a b       ==> 'a b'
+ *  a'b      ==> a'\''b    ==> 'a'\''b'
+ *  a!b      ==> a'\!'b    ==> 'a'\!'b'
+ */
+static inline int need_bs_quote(char c)
+{
+	return (c == '\'' || c == '!');
+}
+
+void sq_quote_buf(struct strbuf *dst, const char *src)
+{
+	char *to_free = NULL;
+
+	if (dst->buf == src)
+		to_free = strbuf_detach(dst, NULL);
+
+	strbuf_addch(dst, '\'');
+	while (*src) {
+		size_t len = strcspn(src, "'!");
+		strbuf_add(dst, src, len);
+		src += len;
+		while (need_bs_quote(*src)) {
+			strbuf_addstr(dst, "'\\");
+			strbuf_addch(dst, *src++);
+			strbuf_addch(dst, '\'');
+		}
+	}
+	strbuf_addch(dst, '\'');
+	free(to_free);
+}
+
+void sq_quote_print(FILE *stream, const char *src)
+{
+	char c;
+
+	fputc('\'', stream);
+	while ((c = *src++)) {
+		if (need_bs_quote(c)) {
+			fputs("'\\", stream);
+			fputc(c, stream);
+			fputc('\'', stream);
+		} else {
+			fputc(c, stream);
+		}
+	}
+	fputc('\'', stream);
+}
+
+void sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen)
+{
+	int i;
+
+	/* Copy into destination buffer. */
+	strbuf_grow(dst, 255);
+	for (i = 0; argv[i]; ++i) {
+		strbuf_addch(dst, ' ');
+		sq_quote_buf(dst, argv[i]);
+		if (maxlen && dst->len > maxlen)
+			die("Too many or long arguments");
+	}
+}
+
+char *sq_dequote_step(char *arg, char **next)
+{
+	char *dst = arg;
+	char *src = arg;
+	char c;
+
+	if (*src != '\'')
+		return NULL;
+	for (;;) {
+		c = *++src;
+		if (!c)
+			return NULL;
+		if (c != '\'') {
+			*dst++ = c;
+			continue;
+		}
+		/* We stepped out of sq */
+		switch (*++src) {
+		case '\0':
+			*dst = 0;
+			if (next)
+				*next = NULL;
+			return arg;
+		case '\\':
+			c = *++src;
+			if (need_bs_quote(c) && *++src == '\'') {
+				*dst++ = c;
+				continue;
+			}
+		/* Fallthrough */
+		default:
+			if (!next || !isspace(*src))
+				return NULL;
+			do {
+				c = *++src;
+			} while (isspace(c));
+			*dst = 0;
+			*next = src;
+			return arg;
+		}
+	}
+}
+
+char *sq_dequote(char *arg)
+{
+	return sq_dequote_step(arg, NULL);
+}
+
+int sq_dequote_to_argv(char *arg, const char ***argv, int *nr, int *alloc)
+{
+	char *next = arg;
+
+	if (!*arg)
+		return 0;
+	do {
+		char *dequoted = sq_dequote_step(next, &next);
+		if (!dequoted)
+			return -1;
+		ALLOC_GROW(*argv, *nr + 1, *alloc);
+		(*argv)[(*nr)++] = dequoted;
+	} while (next);
+
+	return 0;
+}
+
+/* 1 means: quote as octal
+ * 0 means: quote as octal if (quote_path_fully)
+ * -1 means: never quote
+ * c: quote as "\\c"
+ */
+#define X8(x)   x, x, x, x, x, x, x, x
+#define X16(x)  X8(x), X8(x)
+static signed char const sq_lookup[256] = {
+	/*           0    1    2    3    4    5    6    7 */
+	/* 0x00 */   1,   1,   1,   1,   1,   1,   1, 'a',
+	/* 0x08 */ 'b', 't', 'n', 'v', 'f', 'r',   1,   1,
+	/* 0x10 */ X16(1),
+	/* 0x20 */  -1,  -1, '"',  -1,  -1,  -1,  -1,  -1,
+	/* 0x28 */ X16(-1), X16(-1), X16(-1),
+	/* 0x58 */  -1,  -1,  -1,  -1,'\\',  -1,  -1,  -1,
+	/* 0x60 */ X16(-1), X8(-1),
+	/* 0x78 */  -1,  -1,  -1,  -1,  -1,  -1,  -1,   1,
+	/* 0x80 */ /* set to 0 */
+};
+
+static inline int sq_must_quote(char c)
+{
+	return sq_lookup[(unsigned char)c] + quote_path_fully > 0;
+}
+
+/* returns the longest prefix not needing a quote up to maxlen if positive.
+   This stops at the first \0 because it's marked as a character needing an
+   escape */
+static size_t next_quote_pos(const char *s, ssize_t maxlen)
+{
+	size_t len;
+	if (maxlen < 0) {
+		for (len = 0; !sq_must_quote(s[len]); len++);
+	} else {
+		for (len = 0; len < maxlen && !sq_must_quote(s[len]); len++);
+	}
+	return len;
+}
+
+/*
+ * C-style name quoting.
+ *
+ * (1) if sb and fp are both NULL, inspect the input name and counts the
+ *     number of bytes that are needed to hold c_style quoted version of name,
+ *     counting the double quotes around it but not terminating NUL, and
+ *     returns it.
+ *     However, if name does not need c_style quoting, it returns 0.
+ *
+ * (2) if sb or fp are not NULL, it emits the c_style quoted version
+ *     of name, enclosed with double quotes if asked and needed only.
+ *     Return value is the same as in (1).
+ */
+static size_t quote_c_style_counted(const char *name, ssize_t maxlen,
+                                    struct strbuf *sb, FILE *fp, int no_dq)
+{
+#undef EMIT
+#define EMIT(c)                                 \
+	do {                                        \
+		if (sb) strbuf_addch(sb, (c));          \
+		if (fp) fputc((c), fp);                 \
+		count++;                                \
+	} while (0)
+#define EMITBUF(s, l)                           \
+	do {                                        \
+		int __ret;				\
+		if (sb) strbuf_add(sb, (s), (l));       \
+		if (fp) __ret = fwrite((s), (l), 1, fp);        \
+		count += (l);                           \
+	} while (0)
+
+	size_t len, count = 0;
+	const char *p = name;
+
+	for (;;) {
+		int ch;
+
+		len = next_quote_pos(p, maxlen);
+		if (len == maxlen || !p[len])
+			break;
+
+		if (!no_dq && p == name)
+			EMIT('"');
+
+		EMITBUF(p, len);
+		EMIT('\\');
+		p += len;
+		ch = (unsigned char)*p++;
+		if (sq_lookup[ch] >= ' ') {
+			EMIT(sq_lookup[ch]);
+		} else {
+			EMIT(((ch >> 6) & 03) + '0');
+			EMIT(((ch >> 3) & 07) + '0');
+			EMIT(((ch >> 0) & 07) + '0');
+		}
+	}
+
+	EMITBUF(p, len);
+	if (p == name)   /* no ending quote needed */
+		return 0;
+
+	if (!no_dq)
+		EMIT('"');
+	return count;
+}
+
+size_t quote_c_style(const char *name, struct strbuf *sb, FILE *fp, int nodq)
+{
+	return quote_c_style_counted(name, -1, sb, fp, nodq);
+}
+
+void quote_two_c_style(struct strbuf *sb, const char *prefix, const char *path, int nodq)
+{
+	if (quote_c_style(prefix, NULL, NULL, 0) ||
+	    quote_c_style(path, NULL, NULL, 0)) {
+		if (!nodq)
+			strbuf_addch(sb, '"');
+		quote_c_style(prefix, sb, NULL, 1);
+		quote_c_style(path, sb, NULL, 1);
+		if (!nodq)
+			strbuf_addch(sb, '"');
+	} else {
+		strbuf_addstr(sb, prefix);
+		strbuf_addstr(sb, path);
+	}
+}
+
+void write_name_quoted(const char *name, FILE *fp, int terminator)
+{
+	if (terminator) {
+		quote_c_style(name, NULL, fp, 0);
+	} else {
+		fputs(name, fp);
+	}
+	fputc(terminator, fp);
+}
+
+extern void write_name_quotedpfx(const char *pfx, size_t pfxlen,
+                                 const char *name, FILE *fp, int terminator)
+{
+	int needquote = 0;
+
+	if (terminator) {
+		needquote = next_quote_pos(pfx, pfxlen) < pfxlen
+			|| name[next_quote_pos(name, -1)];
+	}
+	if (needquote) {
+		fputc('"', fp);
+		quote_c_style_counted(pfx, pfxlen, NULL, fp, 1);
+		quote_c_style(name, NULL, fp, 1);
+		fputc('"', fp);
+	} else {
+		int ret;
+
+		ret = fwrite(pfx, pfxlen, 1, fp);
+		fputs(name, fp);
+	}
+	fputc(terminator, fp);
+}
+
+/* quote path as relative to the given prefix */
+char *quote_path_relative(const char *in, int len,
+			  struct strbuf *out, const char *prefix)
+{
+	int needquote;
+
+	if (len < 0)
+		len = strlen(in);
+
+	/* "../" prefix itself does not need quoting, but "in" might. */
+	needquote = next_quote_pos(in, len) < len;
+	strbuf_setlen(out, 0);
+	strbuf_grow(out, len);
+
+	if (needquote)
+		strbuf_addch(out, '"');
+	if (prefix) {
+		int off = 0;
+		while (prefix[off] && off < len && prefix[off] == in[off])
+			if (prefix[off] == '/') {
+				prefix += off + 1;
+				in += off + 1;
+				len -= off + 1;
+				off = 0;
+			} else
+				off++;
+
+		for (; *prefix; prefix++)
+			if (*prefix == '/')
+				strbuf_addstr(out, "../");
+	}
+
+	quote_c_style_counted (in, len, out, NULL, 1);
+
+	if (needquote)
+		strbuf_addch(out, '"');
+	if (!out->len)
+		strbuf_addstr(out, "./");
+
+	return out->buf;
+}
+
+/*
+ * C-style name unquoting.
+ *
+ * Quoted should point at the opening double quote.
+ * + Returns 0 if it was able to unquote the string properly, and appends the
+ *   result in the strbuf `sb'.
+ * + Returns -1 in case of error, and doesn't touch the strbuf. Though note
+ *   that this function will allocate memory in the strbuf, so calling
+ *   strbuf_release is mandatory whichever result unquote_c_style returns.
+ *
+ * Updates endp pointer to point at one past the ending double quote if given.
+ */
+int unquote_c_style(struct strbuf *sb, const char *quoted, const char **endp)
+{
+	size_t oldlen = sb->len, len;
+	int ch, ac;
+
+	if (*quoted++ != '"')
+		return -1;
+
+	for (;;) {
+		len = strcspn(quoted, "\"\\");
+		strbuf_add(sb, quoted, len);
+		quoted += len;
+
+		switch (*quoted++) {
+		  case '"':
+			if (endp)
+				*endp = quoted;
+			return 0;
+		  case '\\':
+			break;
+		  default:
+			goto error;
+		}
+
+		switch ((ch = *quoted++)) {
+		case 'a': ch = '\a'; break;
+		case 'b': ch = '\b'; break;
+		case 'f': ch = '\f'; break;
+		case 'n': ch = '\n'; break;
+		case 'r': ch = '\r'; break;
+		case 't': ch = '\t'; break;
+		case 'v': ch = '\v'; break;
+
+		case '\\': case '"':
+			break; /* verbatim */
+
+		/* octal values with first digit over 4 overflow */
+		case '0': case '1': case '2': case '3':
+					ac = ((ch - '0') << 6);
+			if ((ch = *quoted++) < '0' || '7' < ch)
+				goto error;
+					ac |= ((ch - '0') << 3);
+			if ((ch = *quoted++) < '0' || '7' < ch)
+				goto error;
+					ac |= (ch - '0');
+					ch = ac;
+					break;
+				default:
+			goto error;
+			}
+		strbuf_addch(sb, ch);
+		}
+
+  error:
+	strbuf_setlen(sb, oldlen);
+	return -1;
+}
+
+/* quoting as a string literal for other languages */
+
+void perl_quote_print(FILE *stream, const char *src)
+{
+	const char sq = '\'';
+	const char bq = '\\';
+	char c;
+
+	fputc(sq, stream);
+	while ((c = *src++)) {
+		if (c == sq || c == bq)
+			fputc(bq, stream);
+		fputc(c, stream);
+	}
+	fputc(sq, stream);
+}
+
+void python_quote_print(FILE *stream, const char *src)
+{
+	const char sq = '\'';
+	const char bq = '\\';
+	const char nl = '\n';
+	char c;
+
+	fputc(sq, stream);
+	while ((c = *src++)) {
+		if (c == nl) {
+			fputc(bq, stream);
+			fputc('n', stream);
+			continue;
+		}
+		if (c == sq || c == bq)
+			fputc(bq, stream);
+		fputc(c, stream);
+	}
+	fputc(sq, stream);
+}
+
+void tcl_quote_print(FILE *stream, const char *src)
+{
+	char c;
+
+	fputc('"', stream);
+	while ((c = *src++)) {
+		switch (c) {
+		case '[': case ']':
+		case '{': case '}':
+		case '$': case '\\': case '"':
+			fputc('\\', stream);
+		default:
+			fputc(c, stream);
+			break;
+		case '\f':
+			fputs("\\f", stream);
+			break;
+		case '\r':
+			fputs("\\r", stream);
+			break;
+		case '\n':
+			fputs("\\n", stream);
+			break;
+		case '\t':
+			fputs("\\t", stream);
+			break;
+		case '\v':
+			fputs("\\v", stream);
+			break;
+		}
+	}
+	fputc('"', stream);
+}
diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h
new file mode 100644
index 000000000000..5dfad89816db
--- /dev/null
+++ b/tools/perf/util/quote.h
@@ -0,0 +1,68 @@
+#ifndef QUOTE_H
+#define QUOTE_H
+
+#include <stddef.h>
+#include <stdio.h>
+
+/* Help to copy the thing properly quoted for the shell safety.
+ * any single quote is replaced with '\'', any exclamation point
+ * is replaced with '\!', and the whole thing is enclosed in a
+ * single quote pair.
+ *
+ * For example, if you are passing the result to system() as an
+ * argument:
+ *
+ * sprintf(cmd, "foobar %s %s", sq_quote(arg0), sq_quote(arg1))
+ *
+ * would be appropriate.  If the system() is going to call ssh to
+ * run the command on the other side:
+ *
+ * sprintf(cmd, "git-diff-tree %s %s", sq_quote(arg0), sq_quote(arg1));
+ * sprintf(rcmd, "ssh %s %s", sq_util/quote.host), sq_quote(cmd));
+ *
+ * Note that the above examples leak memory!  Remember to free result from
+ * sq_quote() in a real application.
+ *
+ * sq_quote_buf() writes to an existing buffer of specified size; it
+ * will return the number of characters that would have been written
+ * excluding the final null regardless of the buffer size.
+ */
+
+extern void sq_quote_print(FILE *stream, const char *src);
+
+extern void sq_quote_buf(struct strbuf *, const char *src);
+extern void sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
+
+/* This unwraps what sq_quote() produces in place, but returns
+ * NULL if the input does not look like what sq_quote would have
+ * produced.
+ */
+extern char *sq_dequote(char *);
+
+/*
+ * Same as the above, but can be used to unwrap many arguments in the
+ * same string separated by space. "next" is changed to point to the
+ * next argument that should be passed as first parameter. When there
+ * is no more argument to be dequoted, "next" is updated to point to NULL.
+ */
+extern char *sq_dequote_step(char *arg, char **next);
+extern int sq_dequote_to_argv(char *arg, const char ***argv, int *nr, int *alloc);
+
+extern int unquote_c_style(struct strbuf *, const char *quoted, const char **endp);
+extern size_t quote_c_style(const char *name, struct strbuf *, FILE *, int no_dq);
+extern void quote_two_c_style(struct strbuf *, const char *, const char *, int);
+
+extern void write_name_quoted(const char *name, FILE *, int terminator);
+extern void write_name_quotedpfx(const char *pfx, size_t pfxlen,
+                                 const char *name, FILE *, int terminator);
+
+/* quote path as relative to the given prefix */
+char *quote_path_relative(const char *in, int len,
+			  struct strbuf *out, const char *prefix);
+
+/* quoting as a string literal for other languages */
+extern void perl_quote_print(FILE *stream, const char *src);
+extern void python_quote_print(FILE *stream, const char *src);
+extern void tcl_quote_print(FILE *stream, const char *src);
+
+#endif
diff --git a/tools/perf/util/rbtree.c b/tools/perf/util/rbtree.c
new file mode 100644
index 000000000000..b15ba9c7cb3f
--- /dev/null
+++ b/tools/perf/util/rbtree.c
@@ -0,0 +1,383 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/lib/rbtree.c
+*/
+
+#include "rbtree.h"
+
+static void __rb_rotate_left(struct rb_node *node, struct rb_root *root)
+{
+	struct rb_node *right = node->rb_right;
+	struct rb_node *parent = rb_parent(node);
+
+	if ((node->rb_right = right->rb_left))
+		rb_set_parent(right->rb_left, node);
+	right->rb_left = node;
+
+	rb_set_parent(right, parent);
+
+	if (parent)
+	{
+		if (node == parent->rb_left)
+			parent->rb_left = right;
+		else
+			parent->rb_right = right;
+	}
+	else
+		root->rb_node = right;
+	rb_set_parent(node, right);
+}
+
+static void __rb_rotate_right(struct rb_node *node, struct rb_root *root)
+{
+	struct rb_node *left = node->rb_left;
+	struct rb_node *parent = rb_parent(node);
+
+	if ((node->rb_left = left->rb_right))
+		rb_set_parent(left->rb_right, node);
+	left->rb_right = node;
+
+	rb_set_parent(left, parent);
+
+	if (parent)
+	{
+		if (node == parent->rb_right)
+			parent->rb_right = left;
+		else
+			parent->rb_left = left;
+	}
+	else
+		root->rb_node = left;
+	rb_set_parent(node, left);
+}
+
+void rb_insert_color(struct rb_node *node, struct rb_root *root)
+{
+	struct rb_node *parent, *gparent;
+
+	while ((parent = rb_parent(node)) && rb_is_red(parent))
+	{
+		gparent = rb_parent(parent);
+
+		if (parent == gparent->rb_left)
+		{
+			{
+				register struct rb_node *uncle = gparent->rb_right;
+				if (uncle && rb_is_red(uncle))
+				{
+					rb_set_black(uncle);
+					rb_set_black(parent);
+					rb_set_red(gparent);
+					node = gparent;
+					continue;
+				}
+			}
+
+			if (parent->rb_right == node)
+			{
+				register struct rb_node *tmp;
+				__rb_rotate_left(parent, root);
+				tmp = parent;
+				parent = node;
+				node = tmp;
+			}
+
+			rb_set_black(parent);
+			rb_set_red(gparent);
+			__rb_rotate_right(gparent, root);
+		} else {
+			{
+				register struct rb_node *uncle = gparent->rb_left;
+				if (uncle && rb_is_red(uncle))
+				{
+					rb_set_black(uncle);
+					rb_set_black(parent);
+					rb_set_red(gparent);
+					node = gparent;
+					continue;
+				}
+			}
+
+			if (parent->rb_left == node)
+			{
+				register struct rb_node *tmp;
+				__rb_rotate_right(parent, root);
+				tmp = parent;
+				parent = node;
+				node = tmp;
+			}
+
+			rb_set_black(parent);
+			rb_set_red(gparent);
+			__rb_rotate_left(gparent, root);
+		}
+	}
+
+	rb_set_black(root->rb_node);
+}
+
+static void __rb_erase_color(struct rb_node *node, struct rb_node *parent,
+			     struct rb_root *root)
+{
+	struct rb_node *other;
+
+	while ((!node || rb_is_black(node)) && node != root->rb_node)
+	{
+		if (parent->rb_left == node)
+		{
+			other = parent->rb_right;
+			if (rb_is_red(other))
+			{
+				rb_set_black(other);
+				rb_set_red(parent);
+				__rb_rotate_left(parent, root);
+				other = parent->rb_right;
+			}
+			if ((!other->rb_left || rb_is_black(other->rb_left)) &&
+			    (!other->rb_right || rb_is_black(other->rb_right)))
+			{
+				rb_set_red(other);
+				node = parent;
+				parent = rb_parent(node);
+			}
+			else
+			{
+				if (!other->rb_right || rb_is_black(other->rb_right))
+				{
+					rb_set_black(other->rb_left);
+					rb_set_red(other);
+					__rb_rotate_right(other, root);
+					other = parent->rb_right;
+				}
+				rb_set_color(other, rb_color(parent));
+				rb_set_black(parent);
+				rb_set_black(other->rb_right);
+				__rb_rotate_left(parent, root);
+				node = root->rb_node;
+				break;
+			}
+		}
+		else
+		{
+			other = parent->rb_left;
+			if (rb_is_red(other))
+			{
+				rb_set_black(other);
+				rb_set_red(parent);
+				__rb_rotate_right(parent, root);
+				other = parent->rb_left;
+			}
+			if ((!other->rb_left || rb_is_black(other->rb_left)) &&
+			    (!other->rb_right || rb_is_black(other->rb_right)))
+			{
+				rb_set_red(other);
+				node = parent;
+				parent = rb_parent(node);
+			}
+			else
+			{
+				if (!other->rb_left || rb_is_black(other->rb_left))
+				{
+					rb_set_black(other->rb_right);
+					rb_set_red(other);
+					__rb_rotate_left(other, root);
+					other = parent->rb_left;
+				}
+				rb_set_color(other, rb_color(parent));
+				rb_set_black(parent);
+				rb_set_black(other->rb_left);
+				__rb_rotate_right(parent, root);
+				node = root->rb_node;
+				break;
+			}
+		}
+	}
+	if (node)
+		rb_set_black(node);
+}
+
+void rb_erase(struct rb_node *node, struct rb_root *root)
+{
+	struct rb_node *child, *parent;
+	int color;
+
+	if (!node->rb_left)
+		child = node->rb_right;
+	else if (!node->rb_right)
+		child = node->rb_left;
+	else
+	{
+		struct rb_node *old = node, *left;
+
+		node = node->rb_right;
+		while ((left = node->rb_left) != NULL)
+			node = left;
+		child = node->rb_right;
+		parent = rb_parent(node);
+		color = rb_color(node);
+
+		if (child)
+			rb_set_parent(child, parent);
+		if (parent == old) {
+			parent->rb_right = child;
+			parent = node;
+		} else
+			parent->rb_left = child;
+
+		node->rb_parent_color = old->rb_parent_color;
+		node->rb_right = old->rb_right;
+		node->rb_left = old->rb_left;
+
+		if (rb_parent(old))
+		{
+			if (rb_parent(old)->rb_left == old)
+				rb_parent(old)->rb_left = node;
+			else
+				rb_parent(old)->rb_right = node;
+		} else
+			root->rb_node = node;
+
+		rb_set_parent(old->rb_left, node);
+		if (old->rb_right)
+			rb_set_parent(old->rb_right, node);
+		goto color;
+	}
+
+	parent = rb_parent(node);
+	color = rb_color(node);
+
+	if (child)
+		rb_set_parent(child, parent);
+	if (parent)
+	{
+		if (parent->rb_left == node)
+			parent->rb_left = child;
+		else
+			parent->rb_right = child;
+	}
+	else
+		root->rb_node = child;
+
+ color:
+	if (color == RB_BLACK)
+		__rb_erase_color(child, parent, root);
+}
+
+/*
+ * This function returns the first node (in sort order) of the tree.
+ */
+struct rb_node *rb_first(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_left)
+		n = n->rb_left;
+	return n;
+}
+
+struct rb_node *rb_last(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_right)
+		n = n->rb_right;
+	return n;
+}
+
+struct rb_node *rb_next(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (rb_parent(node) == node)
+		return NULL;
+
+	/* If we have a right-hand child, go down and then left as far
+	   as we can. */
+	if (node->rb_right) {
+		node = node->rb_right; 
+		while (node->rb_left)
+			node=node->rb_left;
+		return (struct rb_node *)node;
+	}
+
+	/* No right-hand children.  Everything down and left is
+	   smaller than us, so any 'next' node must be in the general
+	   direction of our parent. Go up the tree; any time the
+	   ancestor is a right-hand child of its parent, keep going
+	   up. First time it's a left-hand child of its parent, said
+	   parent is our 'next' node. */
+	while ((parent = rb_parent(node)) && node == parent->rb_right)
+		node = parent;
+
+	return parent;
+}
+
+struct rb_node *rb_prev(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (rb_parent(node) == node)
+		return NULL;
+
+	/* If we have a left-hand child, go down and then right as far
+	   as we can. */
+	if (node->rb_left) {
+		node = node->rb_left; 
+		while (node->rb_right)
+			node=node->rb_right;
+		return (struct rb_node *)node;
+	}
+
+	/* No left-hand children. Go up till we find an ancestor which
+	   is a right-hand child of its parent */
+	while ((parent = rb_parent(node)) && node == parent->rb_left)
+		node = parent;
+
+	return parent;
+}
+
+void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+		     struct rb_root *root)
+{
+	struct rb_node *parent = rb_parent(victim);
+
+	/* Set the surrounding nodes to point to the replacement */
+	if (parent) {
+		if (victim == parent->rb_left)
+			parent->rb_left = new;
+		else
+			parent->rb_right = new;
+	} else {
+		root->rb_node = new;
+	}
+	if (victim->rb_left)
+		rb_set_parent(victim->rb_left, new);
+	if (victim->rb_right)
+		rb_set_parent(victim->rb_right, new);
+
+	/* Copy the pointers/colour from the victim to the replacement */
+	*new = *victim;
+}
diff --git a/tools/perf/util/rbtree.h b/tools/perf/util/rbtree.h
new file mode 100644
index 000000000000..6bdc488a47fb
--- /dev/null
+++ b/tools/perf/util/rbtree.h
@@ -0,0 +1,171 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/include/linux/rbtree.h
+
+  To use rbtrees you'll have to implement your own insert and search cores.
+  This will avoid us to use callbacks and to drop drammatically performances.
+  I know it's not the cleaner way,  but in C (not in C++) to get
+  performances and genericity...
+
+  Some example of insert and search follows here. The search is a plain
+  normal search over an ordered tree. The insert instead must be implemented
+  int two steps: as first thing the code must insert the element in
+  order as a red leaf in the tree, then the support library function
+  rb_insert_color() must be called. Such function will do the
+  not trivial work to rebalance the rbtree if necessary.
+
+-----------------------------------------------------------------------
+static inline struct page * rb_search_page_cache(struct inode * inode,
+						 unsigned long offset)
+{
+	struct rb_node * n = inode->i_rb_page_cache.rb_node;
+	struct page * page;
+
+	while (n)
+	{
+		page = rb_entry(n, struct page, rb_page_cache);
+
+		if (offset < page->offset)
+			n = n->rb_left;
+		else if (offset > page->offset)
+			n = n->rb_right;
+		else
+			return page;
+	}
+	return NULL;
+}
+
+static inline struct page * __rb_insert_page_cache(struct inode * inode,
+						   unsigned long offset,
+						   struct rb_node * node)
+{
+	struct rb_node ** p = &inode->i_rb_page_cache.rb_node;
+	struct rb_node * parent = NULL;
+	struct page * page;
+
+	while (*p)
+	{
+		parent = *p;
+		page = rb_entry(parent, struct page, rb_page_cache);
+
+		if (offset < page->offset)
+			p = &(*p)->rb_left;
+		else if (offset > page->offset)
+			p = &(*p)->rb_right;
+		else
+			return page;
+	}
+
+	rb_link_node(node, parent, p);
+
+	return NULL;
+}
+
+static inline struct page * rb_insert_page_cache(struct inode * inode,
+						 unsigned long offset,
+						 struct rb_node * node)
+{
+	struct page * ret;
+	if ((ret = __rb_insert_page_cache(inode, offset, node)))
+		goto out;
+	rb_insert_color(node, &inode->i_rb_page_cache);
+ out:
+	return ret;
+}
+-----------------------------------------------------------------------
+*/
+
+#ifndef	_LINUX_RBTREE_H
+#define	_LINUX_RBTREE_H
+
+#include <stddef.h>
+
+/**
+ * container_of - cast a member of a structure out to the containing structure
+ * @ptr:	the pointer to the member.
+ * @type:	the type of the container struct this is embedded in.
+ * @member:	the name of the member within the struct.
+ *
+ */
+#define container_of(ptr, type, member) ({			\
+	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
+	(type *)( (char *)__mptr - offsetof(type,member) );})
+
+struct rb_node
+{
+	unsigned long  rb_parent_color;
+#define	RB_RED		0
+#define	RB_BLACK	1
+	struct rb_node *rb_right;
+	struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+    /* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root
+{
+	struct rb_node *rb_node;
+};
+
+
+#define rb_parent(r)   ((struct rb_node *)((r)->rb_parent_color & ~3))
+#define rb_color(r)   ((r)->rb_parent_color & 1)
+#define rb_is_red(r)   (!rb_color(r))
+#define rb_is_black(r) rb_color(r)
+#define rb_set_red(r)  do { (r)->rb_parent_color &= ~1; } while (0)
+#define rb_set_black(r)  do { (r)->rb_parent_color |= 1; } while (0)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+	rb->rb_parent_color = (rb->rb_parent_color & 3) | (unsigned long)p;
+}
+static inline void rb_set_color(struct rb_node *rb, int color)
+{
+	rb->rb_parent_color = (rb->rb_parent_color & ~1) | color;
+}
+
+#define RB_ROOT	(struct rb_root) { NULL, }
+#define	rb_entry(ptr, type, member) container_of(ptr, type, member)
+
+#define RB_EMPTY_ROOT(root)	((root)->rb_node == NULL)
+#define RB_EMPTY_NODE(node)	(rb_parent(node) == node)
+#define RB_CLEAR_NODE(node)	(rb_set_parent(node, node))
+
+extern void rb_insert_color(struct rb_node *, struct rb_root *);
+extern void rb_erase(struct rb_node *, struct rb_root *);
+
+/* Find logical next and previous nodes in a tree */
+extern struct rb_node *rb_next(const struct rb_node *);
+extern struct rb_node *rb_prev(const struct rb_node *);
+extern struct rb_node *rb_first(const struct rb_root *);
+extern struct rb_node *rb_last(const struct rb_root *);
+
+/* Fast replacement of a single node without remove/rebalance/add/rebalance */
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, 
+			    struct rb_root *root);
+
+static inline void rb_link_node(struct rb_node * node, struct rb_node * parent,
+				struct rb_node ** rb_link)
+{
+	node->rb_parent_color = (unsigned long )parent;
+	node->rb_left = node->rb_right = NULL;
+
+	*rb_link = node;
+}
+
+#endif	/* _LINUX_RBTREE_H */
diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c
new file mode 100644
index 000000000000..b2f5e854f40a
--- /dev/null
+++ b/tools/perf/util/run-command.c
@@ -0,0 +1,395 @@
+#include "cache.h"
+#include "run-command.h"
+#include "exec_cmd.h"
+
+static inline void close_pair(int fd[2])
+{
+	close(fd[0]);
+	close(fd[1]);
+}
+
+static inline void dup_devnull(int to)
+{
+	int fd = open("/dev/null", O_RDWR);
+	dup2(fd, to);
+	close(fd);
+}
+
+int start_command(struct child_process *cmd)
+{
+	int need_in, need_out, need_err;
+	int fdin[2], fdout[2], fderr[2];
+
+	/*
+	 * In case of errors we must keep the promise to close FDs
+	 * that have been passed in via ->in and ->out.
+	 */
+
+	need_in = !cmd->no_stdin && cmd->in < 0;
+	if (need_in) {
+		if (pipe(fdin) < 0) {
+			if (cmd->out > 0)
+				close(cmd->out);
+			return -ERR_RUN_COMMAND_PIPE;
+		}
+		cmd->in = fdin[1];
+	}
+
+	need_out = !cmd->no_stdout
+		&& !cmd->stdout_to_stderr
+		&& cmd->out < 0;
+	if (need_out) {
+		if (pipe(fdout) < 0) {
+			if (need_in)
+				close_pair(fdin);
+			else if (cmd->in)
+				close(cmd->in);
+			return -ERR_RUN_COMMAND_PIPE;
+		}
+		cmd->out = fdout[0];
+	}
+
+	need_err = !cmd->no_stderr && cmd->err < 0;
+	if (need_err) {
+		if (pipe(fderr) < 0) {
+			if (need_in)
+				close_pair(fdin);
+			else if (cmd->in)
+				close(cmd->in);
+			if (need_out)
+				close_pair(fdout);
+			else if (cmd->out)
+				close(cmd->out);
+			return -ERR_RUN_COMMAND_PIPE;
+		}
+		cmd->err = fderr[0];
+	}
+
+#ifndef __MINGW32__
+	fflush(NULL);
+	cmd->pid = fork();
+	if (!cmd->pid) {
+		if (cmd->no_stdin)
+			dup_devnull(0);
+		else if (need_in) {
+			dup2(fdin[0], 0);
+			close_pair(fdin);
+		} else if (cmd->in) {
+			dup2(cmd->in, 0);
+			close(cmd->in);
+		}
+
+		if (cmd->no_stderr)
+			dup_devnull(2);
+		else if (need_err) {
+			dup2(fderr[1], 2);
+			close_pair(fderr);
+		}
+
+		if (cmd->no_stdout)
+			dup_devnull(1);
+		else if (cmd->stdout_to_stderr)
+			dup2(2, 1);
+		else if (need_out) {
+			dup2(fdout[1], 1);
+			close_pair(fdout);
+		} else if (cmd->out > 1) {
+			dup2(cmd->out, 1);
+			close(cmd->out);
+		}
+
+		if (cmd->dir && chdir(cmd->dir))
+			die("exec %s: cd to %s failed (%s)", cmd->argv[0],
+			    cmd->dir, strerror(errno));
+		if (cmd->env) {
+			for (; *cmd->env; cmd->env++) {
+				if (strchr(*cmd->env, '='))
+					putenv((char*)*cmd->env);
+				else
+					unsetenv(*cmd->env);
+			}
+		}
+		if (cmd->preexec_cb)
+			cmd->preexec_cb();
+		if (cmd->perf_cmd) {
+			execv_perf_cmd(cmd->argv);
+		} else {
+			execvp(cmd->argv[0], (char *const*) cmd->argv);
+		}
+		exit(127);
+	}
+#else
+	int s0 = -1, s1 = -1, s2 = -1;	/* backups of stdin, stdout, stderr */
+	const char **sargv = cmd->argv;
+	char **env = environ;
+
+	if (cmd->no_stdin) {
+		s0 = dup(0);
+		dup_devnull(0);
+	} else if (need_in) {
+		s0 = dup(0);
+		dup2(fdin[0], 0);
+	} else if (cmd->in) {
+		s0 = dup(0);
+		dup2(cmd->in, 0);
+	}
+
+	if (cmd->no_stderr) {
+		s2 = dup(2);
+		dup_devnull(2);
+	} else if (need_err) {
+		s2 = dup(2);
+		dup2(fderr[1], 2);
+	}
+
+	if (cmd->no_stdout) {
+		s1 = dup(1);
+		dup_devnull(1);
+	} else if (cmd->stdout_to_stderr) {
+		s1 = dup(1);
+		dup2(2, 1);
+	} else if (need_out) {
+		s1 = dup(1);
+		dup2(fdout[1], 1);
+	} else if (cmd->out > 1) {
+		s1 = dup(1);
+		dup2(cmd->out, 1);
+	}
+
+	if (cmd->dir)
+		die("chdir in start_command() not implemented");
+	if (cmd->env) {
+		env = copy_environ();
+		for (; *cmd->env; cmd->env++)
+			env = env_setenv(env, *cmd->env);
+	}
+
+	if (cmd->perf_cmd) {
+		cmd->argv = prepare_perf_cmd(cmd->argv);
+	}
+
+	cmd->pid = mingw_spawnvpe(cmd->argv[0], cmd->argv, env);
+
+	if (cmd->env)
+		free_environ(env);
+	if (cmd->perf_cmd)
+		free(cmd->argv);
+
+	cmd->argv = sargv;
+	if (s0 >= 0)
+		dup2(s0, 0), close(s0);
+	if (s1 >= 0)
+		dup2(s1, 1), close(s1);
+	if (s2 >= 0)
+		dup2(s2, 2), close(s2);
+#endif
+
+	if (cmd->pid < 0) {
+		int err = errno;
+		if (need_in)
+			close_pair(fdin);
+		else if (cmd->in)
+			close(cmd->in);
+		if (need_out)
+			close_pair(fdout);
+		else if (cmd->out)
+			close(cmd->out);
+		if (need_err)
+			close_pair(fderr);
+		return err == ENOENT ?
+			-ERR_RUN_COMMAND_EXEC :
+			-ERR_RUN_COMMAND_FORK;
+	}
+
+	if (need_in)
+		close(fdin[0]);
+	else if (cmd->in)
+		close(cmd->in);
+
+	if (need_out)
+		close(fdout[1]);
+	else if (cmd->out)
+		close(cmd->out);
+
+	if (need_err)
+		close(fderr[1]);
+
+	return 0;
+}
+
+static int wait_or_whine(pid_t pid)
+{
+	for (;;) {
+		int status, code;
+		pid_t waiting = waitpid(pid, &status, 0);
+
+		if (waiting < 0) {
+			if (errno == EINTR)
+				continue;
+			error("waitpid failed (%s)", strerror(errno));
+			return -ERR_RUN_COMMAND_WAITPID;
+		}
+		if (waiting != pid)
+			return -ERR_RUN_COMMAND_WAITPID_WRONG_PID;
+		if (WIFSIGNALED(status))
+			return -ERR_RUN_COMMAND_WAITPID_SIGNAL;
+
+		if (!WIFEXITED(status))
+			return -ERR_RUN_COMMAND_WAITPID_NOEXIT;
+		code = WEXITSTATUS(status);
+		switch (code) {
+		case 127:
+			return -ERR_RUN_COMMAND_EXEC;
+		case 0:
+			return 0;
+		default:
+			return -code;
+		}
+	}
+}
+
+int finish_command(struct child_process *cmd)
+{
+	return wait_or_whine(cmd->pid);
+}
+
+int run_command(struct child_process *cmd)
+{
+	int code = start_command(cmd);
+	if (code)
+		return code;
+	return finish_command(cmd);
+}
+
+static void prepare_run_command_v_opt(struct child_process *cmd,
+				      const char **argv,
+				      int opt)
+{
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->argv = argv;
+	cmd->no_stdin = opt & RUN_COMMAND_NO_STDIN ? 1 : 0;
+	cmd->perf_cmd = opt & RUN_PERF_CMD ? 1 : 0;
+	cmd->stdout_to_stderr = opt & RUN_COMMAND_STDOUT_TO_STDERR ? 1 : 0;
+}
+
+int run_command_v_opt(const char **argv, int opt)
+{
+	struct child_process cmd;
+	prepare_run_command_v_opt(&cmd, argv, opt);
+	return run_command(&cmd);
+}
+
+int run_command_v_opt_cd_env(const char **argv, int opt, const char *dir, const char *const *env)
+{
+	struct child_process cmd;
+	prepare_run_command_v_opt(&cmd, argv, opt);
+	cmd.dir = dir;
+	cmd.env = env;
+	return run_command(&cmd);
+}
+
+#ifdef __MINGW32__
+static __stdcall unsigned run_thread(void *data)
+{
+	struct async *async = data;
+	return async->proc(async->fd_for_proc, async->data);
+}
+#endif
+
+int start_async(struct async *async)
+{
+	int pipe_out[2];
+
+	if (pipe(pipe_out) < 0)
+		return error("cannot create pipe: %s", strerror(errno));
+	async->out = pipe_out[0];
+
+#ifndef __MINGW32__
+	/* Flush stdio before fork() to avoid cloning buffers */
+	fflush(NULL);
+
+	async->pid = fork();
+	if (async->pid < 0) {
+		error("fork (async) failed: %s", strerror(errno));
+		close_pair(pipe_out);
+		return -1;
+	}
+	if (!async->pid) {
+		close(pipe_out[0]);
+		exit(!!async->proc(pipe_out[1], async->data));
+	}
+	close(pipe_out[1]);
+#else
+	async->fd_for_proc = pipe_out[1];
+	async->tid = (HANDLE) _beginthreadex(NULL, 0, run_thread, async, 0, NULL);
+	if (!async->tid) {
+		error("cannot create thread: %s", strerror(errno));
+		close_pair(pipe_out);
+		return -1;
+	}
+#endif
+	return 0;
+}
+
+int finish_async(struct async *async)
+{
+#ifndef __MINGW32__
+	int ret = 0;
+
+	if (wait_or_whine(async->pid))
+		ret = error("waitpid (async) failed");
+#else
+	DWORD ret = 0;
+	if (WaitForSingleObject(async->tid, INFINITE) != WAIT_OBJECT_0)
+		ret = error("waiting for thread failed: %lu", GetLastError());
+	else if (!GetExitCodeThread(async->tid, &ret))
+		ret = error("cannot get thread exit code: %lu", GetLastError());
+	CloseHandle(async->tid);
+#endif
+	return ret;
+}
+
+int run_hook(const char *index_file, const char *name, ...)
+{
+	struct child_process hook;
+	const char **argv = NULL, *env[2];
+	char index[PATH_MAX];
+	va_list args;
+	int ret;
+	size_t i = 0, alloc = 0;
+
+	if (access(perf_path("hooks/%s", name), X_OK) < 0)
+		return 0;
+
+	va_start(args, name);
+	ALLOC_GROW(argv, i + 1, alloc);
+	argv[i++] = perf_path("hooks/%s", name);
+	while (argv[i-1]) {
+		ALLOC_GROW(argv, i + 1, alloc);
+		argv[i++] = va_arg(args, const char *);
+	}
+	va_end(args);
+
+	memset(&hook, 0, sizeof(hook));
+	hook.argv = argv;
+	hook.no_stdin = 1;
+	hook.stdout_to_stderr = 1;
+	if (index_file) {
+		snprintf(index, sizeof(index), "PERF_INDEX_FILE=%s", index_file);
+		env[0] = index;
+		env[1] = NULL;
+		hook.env = env;
+	}
+
+	ret = start_command(&hook);
+	free(argv);
+	if (ret) {
+		warning("Could not spawn %s", argv[0]);
+		return ret;
+	}
+	ret = finish_command(&hook);
+	if (ret == -ERR_RUN_COMMAND_WAITPID_SIGNAL)
+		warning("%s exited due to uncaught signal", argv[0]);
+
+	return ret;
+}
diff --git a/tools/perf/util/run-command.h b/tools/perf/util/run-command.h
new file mode 100644
index 000000000000..328289f23669
--- /dev/null
+++ b/tools/perf/util/run-command.h
@@ -0,0 +1,93 @@
+#ifndef RUN_COMMAND_H
+#define RUN_COMMAND_H
+
+enum {
+	ERR_RUN_COMMAND_FORK = 10000,
+	ERR_RUN_COMMAND_EXEC,
+	ERR_RUN_COMMAND_PIPE,
+	ERR_RUN_COMMAND_WAITPID,
+	ERR_RUN_COMMAND_WAITPID_WRONG_PID,
+	ERR_RUN_COMMAND_WAITPID_SIGNAL,
+	ERR_RUN_COMMAND_WAITPID_NOEXIT,
+};
+#define IS_RUN_COMMAND_ERR(x) (-(x) >= ERR_RUN_COMMAND_FORK)
+
+struct child_process {
+	const char **argv;
+	pid_t pid;
+	/*
+	 * Using .in, .out, .err:
+	 * - Specify 0 for no redirections (child inherits stdin, stdout,
+	 *   stderr from parent).
+	 * - Specify -1 to have a pipe allocated as follows:
+	 *     .in: returns the writable pipe end; parent writes to it,
+	 *          the readable pipe end becomes child's stdin
+	 *     .out, .err: returns the readable pipe end; parent reads from
+	 *          it, the writable pipe end becomes child's stdout/stderr
+	 *   The caller of start_command() must close the returned FDs
+	 *   after it has completed reading from/writing to it!
+	 * - Specify > 0 to set a channel to a particular FD as follows:
+	 *     .in: a readable FD, becomes child's stdin
+	 *     .out: a writable FD, becomes child's stdout/stderr
+	 *     .err > 0 not supported
+	 *   The specified FD is closed by start_command(), even in case
+	 *   of errors!
+	 */
+	int in;
+	int out;
+	int err;
+	const char *dir;
+	const char *const *env;
+	unsigned no_stdin:1;
+	unsigned no_stdout:1;
+	unsigned no_stderr:1;
+	unsigned perf_cmd:1; /* if this is to be perf sub-command */
+	unsigned stdout_to_stderr:1;
+	void (*preexec_cb)(void);
+};
+
+int start_command(struct child_process *);
+int finish_command(struct child_process *);
+int run_command(struct child_process *);
+
+extern int run_hook(const char *index_file, const char *name, ...);
+
+#define RUN_COMMAND_NO_STDIN 1
+#define RUN_PERF_CMD	     2	/*If this is to be perf sub-command */
+#define RUN_COMMAND_STDOUT_TO_STDERR 4
+int run_command_v_opt(const char **argv, int opt);
+
+/*
+ * env (the environment) is to be formatted like environ: "VAR=VALUE".
+ * To unset an environment variable use just "VAR".
+ */
+int run_command_v_opt_cd_env(const char **argv, int opt, const char *dir, const char *const *env);
+
+/*
+ * The purpose of the following functions is to feed a pipe by running
+ * a function asynchronously and providing output that the caller reads.
+ *
+ * It is expected that no synchronization and mutual exclusion between
+ * the caller and the feed function is necessary so that the function
+ * can run in a thread without interfering with the caller.
+ */
+struct async {
+	/*
+	 * proc writes to fd and closes it;
+	 * returns 0 on success, non-zero on failure
+	 */
+	int (*proc)(int fd, void *data);
+	void *data;
+	int out;	/* caller reads from here and closes it */
+#ifndef __MINGW32__
+	pid_t pid;
+#else
+	HANDLE tid;
+	int fd_for_proc;
+#endif
+};
+
+int start_async(struct async *async);
+int finish_async(struct async *async);
+
+#endif
diff --git a/tools/perf/util/sigchain.c b/tools/perf/util/sigchain.c
new file mode 100644
index 000000000000..1118b99e57d3
--- /dev/null
+++ b/tools/perf/util/sigchain.c
@@ -0,0 +1,52 @@
+#include "sigchain.h"
+#include "cache.h"
+
+#define SIGCHAIN_MAX_SIGNALS 32
+
+struct sigchain_signal {
+	sigchain_fun *old;
+	int n;
+	int alloc;
+};
+static struct sigchain_signal signals[SIGCHAIN_MAX_SIGNALS];
+
+static void check_signum(int sig)
+{
+	if (sig < 1 || sig >= SIGCHAIN_MAX_SIGNALS)
+		die("BUG: signal out of range: %d", sig);
+}
+
+int sigchain_push(int sig, sigchain_fun f)
+{
+	struct sigchain_signal *s = signals + sig;
+	check_signum(sig);
+
+	ALLOC_GROW(s->old, s->n + 1, s->alloc);
+	s->old[s->n] = signal(sig, f);
+	if (s->old[s->n] == SIG_ERR)
+		return -1;
+	s->n++;
+	return 0;
+}
+
+int sigchain_pop(int sig)
+{
+	struct sigchain_signal *s = signals + sig;
+	check_signum(sig);
+	if (s->n < 1)
+		return 0;
+
+	if (signal(sig, s->old[s->n - 1]) == SIG_ERR)
+		return -1;
+	s->n--;
+	return 0;
+}
+
+void sigchain_push_common(sigchain_fun f)
+{
+	sigchain_push(SIGINT, f);
+	sigchain_push(SIGHUP, f);
+	sigchain_push(SIGTERM, f);
+	sigchain_push(SIGQUIT, f);
+	sigchain_push(SIGPIPE, f);
+}
diff --git a/tools/perf/util/sigchain.h b/tools/perf/util/sigchain.h
new file mode 100644
index 000000000000..618083bce0c6
--- /dev/null
+++ b/tools/perf/util/sigchain.h
@@ -0,0 +1,11 @@
+#ifndef SIGCHAIN_H
+#define SIGCHAIN_H
+
+typedef void (*sigchain_fun)(int);
+
+int sigchain_push(int sig, sigchain_fun f);
+int sigchain_pop(int sig);
+
+void sigchain_push_common(sigchain_fun f);
+
+#endif /* SIGCHAIN_H */
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
new file mode 100644
index 000000000000..eaba09306802
--- /dev/null
+++ b/tools/perf/util/strbuf.c
@@ -0,0 +1,359 @@
+#include "cache.h"
+
+int prefixcmp(const char *str, const char *prefix)
+{
+	for (; ; str++, prefix++)
+		if (!*prefix)
+			return 0;
+		else if (*str != *prefix)
+			return (unsigned char)*prefix - (unsigned char)*str;
+}
+
+/*
+ * Used as the default ->buf value, so that people can always assume
+ * buf is non NULL and ->buf is NUL terminated even for a freshly
+ * initialized strbuf.
+ */
+char strbuf_slopbuf[1];
+
+void strbuf_init(struct strbuf *sb, size_t hint)
+{
+	sb->alloc = sb->len = 0;
+	sb->buf = strbuf_slopbuf;
+	if (hint)
+		strbuf_grow(sb, hint);
+}
+
+void strbuf_release(struct strbuf *sb)
+{
+	if (sb->alloc) {
+		free(sb->buf);
+		strbuf_init(sb, 0);
+	}
+}
+
+char *strbuf_detach(struct strbuf *sb, size_t *sz)
+{
+	char *res = sb->alloc ? sb->buf : NULL;
+	if (sz)
+		*sz = sb->len;
+	strbuf_init(sb, 0);
+	return res;
+}
+
+void strbuf_attach(struct strbuf *sb, void *buf, size_t len, size_t alloc)
+{
+	strbuf_release(sb);
+	sb->buf   = buf;
+	sb->len   = len;
+	sb->alloc = alloc;
+	strbuf_grow(sb, 0);
+	sb->buf[sb->len] = '\0';
+}
+
+void strbuf_grow(struct strbuf *sb, size_t extra)
+{
+	if (sb->len + extra + 1 <= sb->len)
+		die("you want to use way too much memory");
+	if (!sb->alloc)
+		sb->buf = NULL;
+	ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc);
+}
+
+void strbuf_trim(struct strbuf *sb)
+{
+	char *b = sb->buf;
+	while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1]))
+		sb->len--;
+	while (sb->len > 0 && isspace(*b)) {
+		b++;
+		sb->len--;
+	}
+	memmove(sb->buf, b, sb->len);
+	sb->buf[sb->len] = '\0';
+}
+void strbuf_rtrim(struct strbuf *sb)
+{
+	while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1]))
+		sb->len--;
+	sb->buf[sb->len] = '\0';
+}
+
+void strbuf_ltrim(struct strbuf *sb)
+{
+	char *b = sb->buf;
+	while (sb->len > 0 && isspace(*b)) {
+		b++;
+		sb->len--;
+	}
+	memmove(sb->buf, b, sb->len);
+	sb->buf[sb->len] = '\0';
+}
+
+void strbuf_tolower(struct strbuf *sb)
+{
+	int i;
+	for (i = 0; i < sb->len; i++)
+		sb->buf[i] = tolower(sb->buf[i]);
+}
+
+struct strbuf **strbuf_split(const struct strbuf *sb, int delim)
+{
+	int alloc = 2, pos = 0;
+	char *n, *p;
+	struct strbuf **ret;
+	struct strbuf *t;
+
+	ret = calloc(alloc, sizeof(struct strbuf *));
+	p = n = sb->buf;
+	while (n < sb->buf + sb->len) {
+		int len;
+		n = memchr(n, delim, sb->len - (n - sb->buf));
+		if (pos + 1 >= alloc) {
+			alloc = alloc * 2;
+			ret = realloc(ret, sizeof(struct strbuf *) * alloc);
+		}
+		if (!n)
+			n = sb->buf + sb->len - 1;
+		len = n - p + 1;
+		t = malloc(sizeof(struct strbuf));
+		strbuf_init(t, len);
+		strbuf_add(t, p, len);
+		ret[pos] = t;
+		ret[++pos] = NULL;
+		p = ++n;
+	}
+	return ret;
+}
+
+void strbuf_list_free(struct strbuf **sbs)
+{
+	struct strbuf **s = sbs;
+
+	while (*s) {
+		strbuf_release(*s);
+		free(*s++);
+	}
+	free(sbs);
+}
+
+int strbuf_cmp(const struct strbuf *a, const struct strbuf *b)
+{
+	int len = a->len < b->len ? a->len: b->len;
+	int cmp = memcmp(a->buf, b->buf, len);
+	if (cmp)
+		return cmp;
+	return a->len < b->len ? -1: a->len != b->len;
+}
+
+void strbuf_splice(struct strbuf *sb, size_t pos, size_t len,
+				   const void *data, size_t dlen)
+{
+	if (pos + len < pos)
+		die("you want to use way too much memory");
+	if (pos > sb->len)
+		die("`pos' is too far after the end of the buffer");
+	if (pos + len > sb->len)
+		die("`pos + len' is too far after the end of the buffer");
+
+	if (dlen >= len)
+		strbuf_grow(sb, dlen - len);
+	memmove(sb->buf + pos + dlen,
+			sb->buf + pos + len,
+			sb->len - pos - len);
+	memcpy(sb->buf + pos, data, dlen);
+	strbuf_setlen(sb, sb->len + dlen - len);
+}
+
+void strbuf_insert(struct strbuf *sb, size_t pos, const void *data, size_t len)
+{
+	strbuf_splice(sb, pos, 0, data, len);
+}
+
+void strbuf_remove(struct strbuf *sb, size_t pos, size_t len)
+{
+	strbuf_splice(sb, pos, len, NULL, 0);
+}
+
+void strbuf_add(struct strbuf *sb, const void *data, size_t len)
+{
+	strbuf_grow(sb, len);
+	memcpy(sb->buf + sb->len, data, len);
+	strbuf_setlen(sb, sb->len + len);
+}
+
+void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len)
+{
+	strbuf_grow(sb, len);
+	memcpy(sb->buf + sb->len, sb->buf + pos, len);
+	strbuf_setlen(sb, sb->len + len);
+}
+
+void strbuf_addf(struct strbuf *sb, const char *fmt, ...)
+{
+	int len;
+	va_list ap;
+
+	if (!strbuf_avail(sb))
+		strbuf_grow(sb, 64);
+	va_start(ap, fmt);
+	len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
+	va_end(ap);
+	if (len < 0)
+		die("your vsnprintf is broken");
+	if (len > strbuf_avail(sb)) {
+		strbuf_grow(sb, len);
+		va_start(ap, fmt);
+		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
+		va_end(ap);
+		if (len > strbuf_avail(sb)) {
+			die("this should not happen, your snprintf is broken");
+		}
+	}
+	strbuf_setlen(sb, sb->len + len);
+}
+
+void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn,
+		   void *context)
+{
+	for (;;) {
+		const char *percent;
+		size_t consumed;
+
+		percent = strchrnul(format, '%');
+		strbuf_add(sb, format, percent - format);
+		if (!*percent)
+			break;
+		format = percent + 1;
+
+		consumed = fn(sb, format, context);
+		if (consumed)
+			format += consumed;
+		else
+			strbuf_addch(sb, '%');
+	}
+}
+
+size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder,
+		void *context)
+{
+	struct strbuf_expand_dict_entry *e = context;
+	size_t len;
+
+	for (; e->placeholder && (len = strlen(e->placeholder)); e++) {
+		if (!strncmp(placeholder, e->placeholder, len)) {
+			if (e->value)
+				strbuf_addstr(sb, e->value);
+			return len;
+		}
+	}
+	return 0;
+}
+
+size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f)
+{
+	size_t res;
+	size_t oldalloc = sb->alloc;
+
+	strbuf_grow(sb, size);
+	res = fread(sb->buf + sb->len, 1, size, f);
+	if (res > 0)
+		strbuf_setlen(sb, sb->len + res);
+	else if (res < 0 && oldalloc == 0)
+		strbuf_release(sb);
+	return res;
+}
+
+ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint)
+{
+	size_t oldlen = sb->len;
+	size_t oldalloc = sb->alloc;
+
+	strbuf_grow(sb, hint ? hint : 8192);
+	for (;;) {
+		ssize_t cnt;
+
+		cnt = read(fd, sb->buf + sb->len, sb->alloc - sb->len - 1);
+		if (cnt < 0) {
+			if (oldalloc == 0)
+				strbuf_release(sb);
+			else
+				strbuf_setlen(sb, oldlen);
+			return -1;
+		}
+		if (!cnt)
+			break;
+		sb->len += cnt;
+		strbuf_grow(sb, 8192);
+	}
+
+	sb->buf[sb->len] = '\0';
+	return sb->len - oldlen;
+}
+
+#define STRBUF_MAXLINK (2*PATH_MAX)
+
+int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint)
+{
+	size_t oldalloc = sb->alloc;
+
+	if (hint < 32)
+		hint = 32;
+
+	while (hint < STRBUF_MAXLINK) {
+		int len;
+
+		strbuf_grow(sb, hint);
+		len = readlink(path, sb->buf, hint);
+		if (len < 0) {
+			if (errno != ERANGE)
+				break;
+		} else if (len < hint) {
+			strbuf_setlen(sb, len);
+			return 0;
+		}
+
+		/* .. the buffer was too small - try again */
+		hint *= 2;
+	}
+	if (oldalloc == 0)
+		strbuf_release(sb);
+	return -1;
+}
+
+int strbuf_getline(struct strbuf *sb, FILE *fp, int term)
+{
+	int ch;
+
+	strbuf_grow(sb, 0);
+	if (feof(fp))
+		return EOF;
+
+	strbuf_reset(sb);
+	while ((ch = fgetc(fp)) != EOF) {
+		if (ch == term)
+			break;
+		strbuf_grow(sb, 1);
+		sb->buf[sb->len++] = ch;
+	}
+	if (ch == EOF && sb->len == 0)
+		return EOF;
+
+	sb->buf[sb->len] = '\0';
+	return 0;
+}
+
+int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint)
+{
+	int fd, len;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return -1;
+	len = strbuf_read(sb, fd, hint);
+	close(fd);
+	if (len < 0)
+		return -1;
+
+	return len;
+}
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
new file mode 100644
index 000000000000..9ee908a3ec5d
--- /dev/null
+++ b/tools/perf/util/strbuf.h
@@ -0,0 +1,137 @@
+#ifndef STRBUF_H
+#define STRBUF_H
+
+/*
+ * Strbuf's can be use in many ways: as a byte array, or to store arbitrary
+ * long, overflow safe strings.
+ *
+ * Strbufs has some invariants that are very important to keep in mind:
+ *
+ * 1. the ->buf member is always malloc-ed, hence strbuf's can be used to
+ *    build complex strings/buffers whose final size isn't easily known.
+ *
+ *    It is NOT legal to copy the ->buf pointer away.
+ *    `strbuf_detach' is the operation that detachs a buffer from its shell
+ *    while keeping the shell valid wrt its invariants.
+ *
+ * 2. the ->buf member is a byte array that has at least ->len + 1 bytes
+ *    allocated. The extra byte is used to store a '\0', allowing the ->buf
+ *    member to be a valid C-string. Every strbuf function ensure this
+ *    invariant is preserved.
+ *
+ *    Note that it is OK to "play" with the buffer directly if you work it
+ *    that way:
+ *
+ *    strbuf_grow(sb, SOME_SIZE);
+ *       ... Here, the memory array starting at sb->buf, and of length
+ *       ... strbuf_avail(sb) is all yours, and you are sure that
+ *       ... strbuf_avail(sb) is at least SOME_SIZE.
+ *    strbuf_setlen(sb, sb->len + SOME_OTHER_SIZE);
+ *
+ *    Of course, SOME_OTHER_SIZE must be smaller or equal to strbuf_avail(sb).
+ *
+ *    Doing so is safe, though if it has to be done in many places, adding the
+ *    missing API to the strbuf module is the way to go.
+ *
+ *    XXX: do _not_ assume that the area that is yours is of size ->alloc - 1
+ *         even if it's true in the current implementation. Alloc is somehow a
+ *         "private" member that should not be messed with.
+ */
+
+#include <assert.h>
+
+extern char strbuf_slopbuf[];
+struct strbuf {
+	size_t alloc;
+	size_t len;
+	char *buf;
+};
+
+#define STRBUF_INIT  { 0, 0, strbuf_slopbuf }
+
+/*----- strbuf life cycle -----*/
+extern void strbuf_init(struct strbuf *, size_t);
+extern void strbuf_release(struct strbuf *);
+extern char *strbuf_detach(struct strbuf *, size_t *);
+extern void strbuf_attach(struct strbuf *, void *, size_t, size_t);
+static inline void strbuf_swap(struct strbuf *a, struct strbuf *b) {
+	struct strbuf tmp = *a;
+	*a = *b;
+	*b = tmp;
+}
+
+/*----- strbuf size related -----*/
+static inline size_t strbuf_avail(const struct strbuf *sb) {
+	return sb->alloc ? sb->alloc - sb->len - 1 : 0;
+}
+
+extern void strbuf_grow(struct strbuf *, size_t);
+
+static inline void strbuf_setlen(struct strbuf *sb, size_t len) {
+	if (!sb->alloc)
+		strbuf_grow(sb, 0);
+	assert(len < sb->alloc);
+	sb->len = len;
+	sb->buf[len] = '\0';
+}
+#define strbuf_reset(sb)  strbuf_setlen(sb, 0)
+
+/*----- content related -----*/
+extern void strbuf_trim(struct strbuf *);
+extern void strbuf_rtrim(struct strbuf *);
+extern void strbuf_ltrim(struct strbuf *);
+extern int strbuf_cmp(const struct strbuf *, const struct strbuf *);
+extern void strbuf_tolower(struct strbuf *);
+
+extern struct strbuf **strbuf_split(const struct strbuf *, int delim);
+extern void strbuf_list_free(struct strbuf **);
+
+/*----- add data in your buffer -----*/
+static inline void strbuf_addch(struct strbuf *sb, int c) {
+	strbuf_grow(sb, 1);
+	sb->buf[sb->len++] = c;
+	sb->buf[sb->len] = '\0';
+}
+
+extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t);
+extern void strbuf_remove(struct strbuf *, size_t pos, size_t len);
+
+/* splice pos..pos+len with given data */
+extern void strbuf_splice(struct strbuf *, size_t pos, size_t len,
+                          const void *, size_t);
+
+extern void strbuf_add(struct strbuf *, const void *, size_t);
+static inline void strbuf_addstr(struct strbuf *sb, const char *s) {
+	strbuf_add(sb, s, strlen(s));
+}
+static inline void strbuf_addbuf(struct strbuf *sb, const struct strbuf *sb2) {
+	strbuf_add(sb, sb2->buf, sb2->len);
+}
+extern void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len);
+
+typedef size_t (*expand_fn_t) (struct strbuf *sb, const char *placeholder, void *context);
+extern void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn, void *context);
+struct strbuf_expand_dict_entry {
+	const char *placeholder;
+	const char *value;
+};
+extern size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder, void *context);
+
+__attribute__((format(printf,2,3)))
+extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
+
+extern size_t strbuf_fread(struct strbuf *, size_t, FILE *);
+/* XXX: if read fails, any partial read is undone */
+extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint);
+extern int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint);
+extern int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint);
+
+extern int strbuf_getline(struct strbuf *, FILE *, int);
+
+extern void stripspace(struct strbuf *buf, int skip_comments);
+extern int launch_editor(const char *path, struct strbuf *buffer, const char *const *env);
+
+extern int strbuf_branchname(struct strbuf *sb, const char *name);
+extern int strbuf_check_branch_ref(struct strbuf *sb, const char *name);
+
+#endif /* STRBUF_H */
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
new file mode 100644
index 000000000000..ec33c0c7f4e2
--- /dev/null
+++ b/tools/perf/util/string.c
@@ -0,0 +1,34 @@
+#include "string.h"
+
+static int hex(char ch)
+{
+	if ((ch >= '0') && (ch <= '9'))
+		return ch - '0';
+	if ((ch >= 'a') && (ch <= 'f'))
+		return ch - 'a' + 10;
+	if ((ch >= 'A') && (ch <= 'F'))
+		return ch - 'A' + 10;
+	return -1;
+}
+
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+int hex2u64(const char *ptr, __u64 *long_val)
+{
+	const char *p = ptr;
+	*long_val = 0;
+
+	while (*p) {
+		const int hex_val = hex(*p);
+
+		if (hex_val < 0)
+			break;
+
+		*long_val = (*long_val << 4) | hex_val;
+		p++;
+	}
+
+	return p - ptr;
+}
diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h
new file mode 100644
index 000000000000..72812c1c9a7a
--- /dev/null
+++ b/tools/perf/util/string.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_STRING_H_
+#define _PERF_STRING_H_
+
+#include <linux/types.h>
+
+int hex2u64(const char *ptr, __u64 *val);
+
+#endif
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
new file mode 100644
index 000000000000..49a55f813712
--- /dev/null
+++ b/tools/perf/util/symbol.c
@@ -0,0 +1,641 @@
+#include "util.h"
+#include "../perf.h"
+#include "string.h"
+#include "symbol.h"
+
+#include <libelf.h>
+#include <gelf.h>
+#include <elf.h>
+
+const char *sym_hist_filter;
+
+static struct symbol *symbol__new(__u64 start, __u64 len,
+				  const char *name, unsigned int priv_size,
+				  __u64 obj_start, int verbose)
+{
+	size_t namelen = strlen(name) + 1;
+	struct symbol *self = calloc(1, priv_size + sizeof(*self) + namelen);
+
+	if (!self)
+		return NULL;
+
+	if (verbose >= 2)
+		printf("new symbol: %016Lx [%08lx]: %s, hist: %p, obj_start: %p\n",
+			(__u64)start, (unsigned long)len, name, self->hist, (void *)(unsigned long)obj_start);
+
+	self->obj_start= obj_start;
+	self->hist = NULL;
+	self->hist_sum = 0;
+
+	if (sym_hist_filter && !strcmp(name, sym_hist_filter))
+		self->hist = calloc(sizeof(__u64), len);
+
+	if (priv_size) {
+		memset(self, 0, priv_size);
+		self = ((void *)self) + priv_size;
+	}
+	self->start = start;
+	self->end   = start + len - 1;
+	memcpy(self->name, name, namelen);
+
+	return self;
+}
+
+static void symbol__delete(struct symbol *self, unsigned int priv_size)
+{
+	free(((void *)self) - priv_size);
+}
+
+static size_t symbol__fprintf(struct symbol *self, FILE *fp)
+{
+	return fprintf(fp, " %llx-%llx %s\n",
+		       self->start, self->end, self->name);
+}
+
+struct dso *dso__new(const char *name, unsigned int sym_priv_size)
+{
+	struct dso *self = malloc(sizeof(*self) + strlen(name) + 1);
+
+	if (self != NULL) {
+		strcpy(self->name, name);
+		self->syms = RB_ROOT;
+		self->sym_priv_size = sym_priv_size;
+		self->find_symbol = dso__find_symbol;
+	}
+
+	return self;
+}
+
+static void dso__delete_symbols(struct dso *self)
+{
+	struct symbol *pos;
+	struct rb_node *next = rb_first(&self->syms);
+
+	while (next) {
+		pos = rb_entry(next, struct symbol, rb_node);
+		next = rb_next(&pos->rb_node);
+		rb_erase(&pos->rb_node, &self->syms);
+		symbol__delete(pos, self->sym_priv_size);
+	}
+}
+
+void dso__delete(struct dso *self)
+{
+	dso__delete_symbols(self);
+	free(self);
+}
+
+static void dso__insert_symbol(struct dso *self, struct symbol *sym)
+{
+	struct rb_node **p = &self->syms.rb_node;
+	struct rb_node *parent = NULL;
+	const __u64 ip = sym->start;
+	struct symbol *s;
+
+	while (*p != NULL) {
+		parent = *p;
+		s = rb_entry(parent, struct symbol, rb_node);
+		if (ip < s->start)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&sym->rb_node, parent, p);
+	rb_insert_color(&sym->rb_node, &self->syms);
+}
+
+struct symbol *dso__find_symbol(struct dso *self, __u64 ip)
+{
+	struct rb_node *n;
+
+	if (self == NULL)
+		return NULL;
+
+	n = self->syms.rb_node;
+
+	while (n) {
+		struct symbol *s = rb_entry(n, struct symbol, rb_node);
+
+		if (ip < s->start)
+			n = n->rb_left;
+		else if (ip > s->end)
+			n = n->rb_right;
+		else
+			return s;
+	}
+
+	return NULL;
+}
+
+size_t dso__fprintf(struct dso *self, FILE *fp)
+{
+	size_t ret = fprintf(fp, "dso: %s\n", self->name);
+
+	struct rb_node *nd;
+	for (nd = rb_first(&self->syms); nd; nd = rb_next(nd)) {
+		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
+		ret += symbol__fprintf(pos, fp);
+	}
+
+	return ret;
+}
+
+static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int verbose)
+{
+	struct rb_node *nd, *prevnd;
+	char *line = NULL;
+	size_t n;
+	FILE *file = fopen("/proc/kallsyms", "r");
+
+	if (file == NULL)
+		goto out_failure;
+
+	while (!feof(file)) {
+		__u64 start;
+		struct symbol *sym;
+		int line_len, len;
+		char symbol_type;
+
+		line_len = getline(&line, &n, file);
+		if (line_len < 0)
+			break;
+
+		if (!line)
+			goto out_failure;
+
+		line[--line_len] = '\0'; /* \n */
+
+		len = hex2u64(line, &start);
+
+		len++;
+		if (len + 2 >= line_len)
+			continue;
+
+		symbol_type = toupper(line[len]);
+		/*
+		 * We're interested only in code ('T'ext)
+		 */
+		if (symbol_type != 'T' && symbol_type != 'W')
+			continue;
+		/*
+		 * Well fix up the end later, when we have all sorted.
+		 */
+		sym = symbol__new(start, 0xdead, line + len + 2,
+				  self->sym_priv_size, 0, verbose);
+
+		if (sym == NULL)
+			goto out_delete_line;
+
+		if (filter && filter(self, sym))
+			symbol__delete(sym, self->sym_priv_size);
+		else
+			dso__insert_symbol(self, sym);
+	}
+
+	/*
+	 * Now that we have all sorted out, just set the ->end of all
+	 * symbols
+	 */
+	prevnd = rb_first(&self->syms);
+
+	if (prevnd == NULL)
+		goto out_delete_line;
+
+	for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
+		struct symbol *prev = rb_entry(prevnd, struct symbol, rb_node),
+			      *curr = rb_entry(nd, struct symbol, rb_node);
+
+		prev->end = curr->start - 1;
+		prevnd = nd;
+	}
+
+	free(line);
+	fclose(file);
+
+	return 0;
+
+out_delete_line:
+	free(line);
+out_failure:
+	return -1;
+}
+
+static int dso__load_perf_map(struct dso *self, symbol_filter_t filter, int verbose)
+{
+	char *line = NULL;
+	size_t n;
+	FILE *file;
+	int nr_syms = 0;
+
+	file = fopen(self->name, "r");
+	if (file == NULL)
+		goto out_failure;
+
+	while (!feof(file)) {
+		__u64 start, size;
+		struct symbol *sym;
+		int line_len, len;
+
+		line_len = getline(&line, &n, file);
+		if (line_len < 0)
+			break;
+
+		if (!line)
+			goto out_failure;
+
+		line[--line_len] = '\0'; /* \n */
+
+		len = hex2u64(line, &start);
+
+		len++;
+		if (len + 2 >= line_len)
+			continue;
+
+		len += hex2u64(line + len, &size);
+
+		len++;
+		if (len + 2 >= line_len)
+			continue;
+
+		sym = symbol__new(start, size, line + len,
+				  self->sym_priv_size, start, verbose);
+
+		if (sym == NULL)
+			goto out_delete_line;
+
+		if (filter && filter(self, sym))
+			symbol__delete(sym, self->sym_priv_size);
+		else {
+			dso__insert_symbol(self, sym);
+			nr_syms++;
+		}
+	}
+
+	free(line);
+	fclose(file);
+
+	return nr_syms;
+
+out_delete_line:
+	free(line);
+out_failure:
+	return -1;
+}
+
+/**
+ * elf_symtab__for_each_symbol - iterate thru all the symbols
+ *
+ * @self: struct elf_symtab instance to iterate
+ * @index: uint32_t index
+ * @sym: GElf_Sym iterator
+ */
+#define elf_symtab__for_each_symbol(syms, nr_syms, index, sym) \
+	for (index = 0, gelf_getsym(syms, index, &sym);\
+	     index < nr_syms; \
+	     index++, gelf_getsym(syms, index, &sym))
+
+static inline uint8_t elf_sym__type(const GElf_Sym *sym)
+{
+	return GELF_ST_TYPE(sym->st_info);
+}
+
+static inline int elf_sym__is_function(const GElf_Sym *sym)
+{
+	return elf_sym__type(sym) == STT_FUNC &&
+	       sym->st_name != 0 &&
+	       sym->st_shndx != SHN_UNDEF &&
+	       sym->st_size != 0;
+}
+
+static inline const char *elf_sym__name(const GElf_Sym *sym,
+					const Elf_Data *symstrs)
+{
+	return symstrs->d_buf + sym->st_name;
+}
+
+static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+				    GElf_Shdr *shp, const char *name,
+				    size_t *index)
+{
+	Elf_Scn *sec = NULL;
+	size_t cnt = 1;
+
+	while ((sec = elf_nextscn(elf, sec)) != NULL) {
+		char *str;
+
+		gelf_getshdr(sec, shp);
+		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
+		if (!strcmp(name, str)) {
+			if (index)
+				*index = cnt;
+			break;
+		}
+		++cnt;
+	}
+
+	return sec;
+}
+
+#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
+	for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \
+	     idx < nr_entries; \
+	     ++idx, pos = gelf_getrel(reldata, idx, &pos_mem))
+
+#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \
+	for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \
+	     idx < nr_entries; \
+	     ++idx, pos = gelf_getrela(reldata, idx, &pos_mem))
+
+static int dso__synthesize_plt_symbols(struct  dso *self, Elf *elf,
+				       GElf_Ehdr *ehdr, Elf_Scn *scn_dynsym,
+				       GElf_Shdr *shdr_dynsym,
+				       size_t dynsym_idx, int verbose)
+{
+	uint32_t nr_rel_entries, idx;
+	GElf_Sym sym;
+	__u64 plt_offset;
+	GElf_Shdr shdr_plt;
+	struct symbol *f;
+	GElf_Shdr shdr_rel_plt;
+	Elf_Data *reldata, *syms, *symstrs;
+	Elf_Scn *scn_plt_rel, *scn_symstrs;
+	char sympltname[1024];
+	int nr = 0, symidx;
+
+	scn_plt_rel = elf_section_by_name(elf, ehdr, &shdr_rel_plt,
+					  ".rela.plt", NULL);
+	if (scn_plt_rel == NULL) {
+		scn_plt_rel = elf_section_by_name(elf, ehdr, &shdr_rel_plt,
+						  ".rel.plt", NULL);
+		if (scn_plt_rel == NULL)
+			return 0;
+	}
+
+	if (shdr_rel_plt.sh_link != dynsym_idx)
+		return 0;
+
+	if (elf_section_by_name(elf, ehdr, &shdr_plt, ".plt", NULL) == NULL)
+		return 0;
+
+	/*
+	 * Fetch the relocation section to find the indexes to the GOT
+	 * and the symbols in the .dynsym they refer to.
+	 */
+	reldata = elf_getdata(scn_plt_rel, NULL);
+	if (reldata == NULL)
+		return -1;
+
+	syms = elf_getdata(scn_dynsym, NULL);
+	if (syms == NULL)
+		return -1;
+
+	scn_symstrs = elf_getscn(elf, shdr_dynsym->sh_link);
+	if (scn_symstrs == NULL)
+		return -1;
+
+	symstrs = elf_getdata(scn_symstrs, NULL);
+	if (symstrs == NULL)
+		return -1;
+
+	nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize;
+	plt_offset = shdr_plt.sh_offset;
+
+	if (shdr_rel_plt.sh_type == SHT_RELA) {
+		GElf_Rela pos_mem, *pos;
+
+		elf_section__for_each_rela(reldata, pos, pos_mem, idx,
+					   nr_rel_entries) {
+			symidx = GELF_R_SYM(pos->r_info);
+			plt_offset += shdr_plt.sh_entsize;
+			gelf_getsym(syms, symidx, &sym);
+			snprintf(sympltname, sizeof(sympltname),
+				 "%s@plt", elf_sym__name(&sym, symstrs));
+
+			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+					sympltname, self->sym_priv_size, 0, verbose);
+			if (!f)
+				return -1;
+
+			dso__insert_symbol(self, f);
+			++nr;
+		}
+	} else if (shdr_rel_plt.sh_type == SHT_REL) {
+		GElf_Rel pos_mem, *pos;
+		elf_section__for_each_rel(reldata, pos, pos_mem, idx,
+					  nr_rel_entries) {
+			symidx = GELF_R_SYM(pos->r_info);
+			plt_offset += shdr_plt.sh_entsize;
+			gelf_getsym(syms, symidx, &sym);
+			snprintf(sympltname, sizeof(sympltname),
+				 "%s@plt", elf_sym__name(&sym, symstrs));
+
+			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+					sympltname, self->sym_priv_size, 0, verbose);
+			if (!f)
+				return -1;
+
+			dso__insert_symbol(self, f);
+			++nr;
+		}
+	} else {
+		/*
+		 * TODO: There are still one more shdr_rel_plt.sh_type
+		 * I have to investigate, but probably should be ignored.
+		 */
+	}
+
+	return nr;
+}
+
+static int dso__load_sym(struct dso *self, int fd, const char *name,
+			 symbol_filter_t filter, int verbose)
+{
+	Elf_Data *symstrs;
+	uint32_t nr_syms;
+	int err = -1;
+	uint32_t index;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	Elf_Data *syms;
+	GElf_Sym sym;
+	Elf_Scn *sec, *sec_dynsym;
+	Elf *elf;
+	size_t dynsym_idx;
+	int nr = 0;
+
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (elf == NULL) {
+		if (verbose)
+			fprintf(stderr, "%s: cannot read %s ELF file.\n",
+				__func__, name);
+		goto out_close;
+	}
+
+	if (gelf_getehdr(elf, &ehdr) == NULL) {
+		if (verbose)
+			fprintf(stderr, "%s: cannot get elf header.\n", __func__);
+		goto out_elf_end;
+	}
+
+	/*
+	 * We need to check if we have a .dynsym, so that we can handle the
+	 * .plt, synthesizing its symbols, that aren't on the symtabs (be it
+	 * .dynsym or .symtab)
+	 */
+	sec_dynsym = elf_section_by_name(elf, &ehdr, &shdr,
+					 ".dynsym", &dynsym_idx);
+	if (sec_dynsym != NULL) {
+		nr = dso__synthesize_plt_symbols(self, elf, &ehdr,
+						 sec_dynsym, &shdr,
+						 dynsym_idx, verbose);
+		if (nr < 0)
+			goto out_elf_end;
+	}
+
+	/*
+	 * But if we have a full .symtab (that is a superset of .dynsym) we
+	 * should add the symbols not in the .dynsyn
+	 */
+	sec = elf_section_by_name(elf, &ehdr, &shdr, ".symtab", NULL);
+	if (sec == NULL) {
+		if (sec_dynsym == NULL)
+			goto out_elf_end;
+
+		sec = sec_dynsym;
+		gelf_getshdr(sec, &shdr);
+	}
+
+	syms = elf_getdata(sec, NULL);
+	if (syms == NULL)
+		goto out_elf_end;
+
+	sec = elf_getscn(elf, shdr.sh_link);
+	if (sec == NULL)
+		goto out_elf_end;
+
+	symstrs = elf_getdata(sec, NULL);
+	if (symstrs == NULL)
+		goto out_elf_end;
+
+	nr_syms = shdr.sh_size / shdr.sh_entsize;
+
+	memset(&sym, 0, sizeof(sym));
+
+	elf_symtab__for_each_symbol(syms, nr_syms, index, sym) {
+		struct symbol *f;
+		__u64 obj_start;
+
+		if (!elf_sym__is_function(&sym))
+			continue;
+
+		sec = elf_getscn(elf, sym.st_shndx);
+		if (!sec)
+			goto out_elf_end;
+
+		gelf_getshdr(sec, &shdr);
+		obj_start = sym.st_value;
+
+		sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+
+		f = symbol__new(sym.st_value, sym.st_size,
+				elf_sym__name(&sym, symstrs),
+				self->sym_priv_size, obj_start, verbose);
+		if (!f)
+			goto out_elf_end;
+
+		if (filter && filter(self, f))
+			symbol__delete(f, self->sym_priv_size);
+		else {
+			dso__insert_symbol(self, f);
+			nr++;
+		}
+	}
+
+	err = nr;
+out_elf_end:
+	elf_end(elf);
+out_close:
+	return err;
+}
+
+int dso__load(struct dso *self, symbol_filter_t filter, int verbose)
+{
+	int size = strlen(self->name) + sizeof("/usr/lib/debug%s.debug");
+	char *name = malloc(size);
+	int variant = 0;
+	int ret = -1;
+	int fd;
+
+	if (!name)
+		return -1;
+
+	if (strncmp(self->name, "/tmp/perf-", 10) == 0)
+		return dso__load_perf_map(self, filter, verbose);
+
+more:
+	do {
+		switch (variant) {
+		case 0: /* Fedora */
+			snprintf(name, size, "/usr/lib/debug%s.debug", self->name);
+			break;
+		case 1: /* Ubuntu */
+			snprintf(name, size, "/usr/lib/debug%s", self->name);
+			break;
+		case 2: /* Sane people */
+			snprintf(name, size, "%s", self->name);
+			break;
+
+		default:
+			goto out;
+		}
+		variant++;
+
+		fd = open(name, O_RDONLY);
+	} while (fd < 0);
+
+	ret = dso__load_sym(self, fd, name, filter, verbose);
+	close(fd);
+
+	/*
+	 * Some people seem to have debuginfo files _WITHOUT_ debug info!?!?
+	 */
+	if (!ret)
+		goto more;
+
+out:
+	free(name);
+	return ret;
+}
+
+static int dso__load_vmlinux(struct dso *self, const char *vmlinux,
+			     symbol_filter_t filter, int verbose)
+{
+	int err, fd = open(vmlinux, O_RDONLY);
+
+	if (fd < 0)
+		return -1;
+
+	err = dso__load_sym(self, fd, vmlinux, filter, verbose);
+	close(fd);
+
+	return err;
+}
+
+int dso__load_kernel(struct dso *self, const char *vmlinux,
+		     symbol_filter_t filter, int verbose)
+{
+	int err = -1;
+
+	if (vmlinux)
+		err = dso__load_vmlinux(self, vmlinux, filter, verbose);
+
+	if (err)
+		err = dso__load_kallsyms(self, filter, verbose);
+
+	return err;
+}
+
+void symbol__init(void)
+{
+	elf_version(EV_CURRENT);
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
new file mode 100644
index 000000000000..0d1292bd8270
--- /dev/null
+++ b/tools/perf/util/symbol.h
@@ -0,0 +1,47 @@
+#ifndef _PERF_SYMBOL_
+#define _PERF_SYMBOL_ 1
+
+#include <linux/types.h>
+#include "list.h"
+#include "rbtree.h"
+
+struct symbol {
+	struct rb_node	rb_node;
+	__u64		start;
+	__u64		end;
+	__u64		obj_start;
+	__u64		hist_sum;
+	__u64		*hist;
+	char		name[0];
+};
+
+struct dso {
+	struct list_head node;
+	struct rb_root	 syms;
+	unsigned int	 sym_priv_size;
+	struct symbol    *(*find_symbol)(struct dso *, __u64 ip);
+	char		 name[0];
+};
+
+const char *sym_hist_filter;
+
+typedef int (*symbol_filter_t)(struct dso *self, struct symbol *sym);
+
+struct dso *dso__new(const char *name, unsigned int sym_priv_size);
+void dso__delete(struct dso *self);
+
+static inline void *dso__sym_priv(struct dso *self, struct symbol *sym)
+{
+	return ((void *)sym) - self->sym_priv_size;
+}
+
+struct symbol *dso__find_symbol(struct dso *self, __u64 ip);
+
+int dso__load_kernel(struct dso *self, const char *vmlinux,
+		     symbol_filter_t filter, int verbose);
+int dso__load(struct dso *self, symbol_filter_t filter, int verbose);
+
+size_t dso__fprintf(struct dso *self, FILE *fp);
+
+void symbol__init(void);
+#endif /* _PERF_SYMBOL_ */
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
new file mode 100644
index 000000000000..e16bf9a707e8
--- /dev/null
+++ b/tools/perf/util/usage.c
@@ -0,0 +1,80 @@
+/*
+ * GIT - The information manager from hell
+ *
+ * Copyright (C) Linus Torvalds, 2005
+ */
+#include "util.h"
+
+static void report(const char *prefix, const char *err, va_list params)
+{
+	char msg[1024];
+	vsnprintf(msg, sizeof(msg), err, params);
+	fprintf(stderr, " %s%s\n", prefix, msg);
+}
+
+static NORETURN void usage_builtin(const char *err)
+{
+	fprintf(stderr, "\n Usage: %s\n", err);
+	exit(129);
+}
+
+static NORETURN void die_builtin(const char *err, va_list params)
+{
+	report(" Fatal: ", err, params);
+	exit(128);
+}
+
+static void error_builtin(const char *err, va_list params)
+{
+	report(" Error: ", err, params);
+}
+
+static void warn_builtin(const char *warn, va_list params)
+{
+	report(" Warning: ", warn, params);
+}
+
+/* If we are in a dlopen()ed .so write to a global variable would segfault
+ * (ugh), so keep things static. */
+static void (*usage_routine)(const char *err) NORETURN = usage_builtin;
+static void (*die_routine)(const char *err, va_list params) NORETURN = die_builtin;
+static void (*error_routine)(const char *err, va_list params) = error_builtin;
+static void (*warn_routine)(const char *err, va_list params) = warn_builtin;
+
+void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN)
+{
+	die_routine = routine;
+}
+
+void usage(const char *err)
+{
+	usage_routine(err);
+}
+
+void die(const char *err, ...)
+{
+	va_list params;
+
+	va_start(params, err);
+	die_routine(err, params);
+	va_end(params);
+}
+
+int error(const char *err, ...)
+{
+	va_list params;
+
+	va_start(params, err);
+	error_routine(err, params);
+	va_end(params);
+	return -1;
+}
+
+void warning(const char *warn, ...)
+{
+	va_list params;
+
+	va_start(params, warn);
+	warn_routine(warn, params);
+	va_end(params);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
new file mode 100644
index 000000000000..76590a16c271
--- /dev/null
+++ b/tools/perf/util/util.h
@@ -0,0 +1,410 @@
+#ifndef GIT_COMPAT_UTIL_H
+#define GIT_COMPAT_UTIL_H
+
+#define _FILE_OFFSET_BITS 64
+
+#ifndef FLEX_ARRAY
+/*
+ * See if our compiler is known to support flexible array members.
+ */
+#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)
+# define FLEX_ARRAY /* empty */
+#elif defined(__GNUC__)
+# if (__GNUC__ >= 3)
+#  define FLEX_ARRAY /* empty */
+# else
+#  define FLEX_ARRAY 0 /* older GNU extension */
+# endif
+#endif
+
+/*
+ * Otherwise, default to safer but a bit wasteful traditional style
+ */
+#ifndef FLEX_ARRAY
+# define FLEX_ARRAY 1
+#endif
+#endif
+
+#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
+
+#ifdef __GNUC__
+#define TYPEOF(x) (__typeof__(x))
+#else
+#define TYPEOF(x)
+#endif
+
+#define MSB(x, bits) ((x) & TYPEOF(x)(~0ULL << (sizeof(x) * 8 - (bits))))
+#define HAS_MULTI_BITS(i)  ((i) & ((i) - 1))  /* checks if an integer has more than 1 bit set */
+
+/* Approximation of the length of the decimal representation of this type. */
+#define decimal_length(x)	((int)(sizeof(x) * 2.56 + 0.5) + 1)
+
+#if !defined(__APPLE__) && !defined(__FreeBSD__)  && !defined(__USLC__) && !defined(_M_UNIX)
+#define _XOPEN_SOURCE 600 /* glibc2 and AIX 5.3L need 500, OpenBSD needs 600 for S_ISLNK() */
+#define _XOPEN_SOURCE_EXTENDED 1 /* AIX 5.3L needs this */
+#endif
+#define _ALL_SOURCE 1
+#define _GNU_SOURCE 1
+#define _BSD_SOURCE 1
+
+#include <unistd.h>
+#include <stdio.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+#include <errno.h>
+#include <limits.h>
+#include <sys/param.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <sys/time.h>
+#include <time.h>
+#include <signal.h>
+#include <fnmatch.h>
+#include <assert.h>
+#include <regex.h>
+#include <utime.h>
+#ifndef __MINGW32__
+#include <sys/wait.h>
+#include <sys/poll.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#ifndef NO_SYS_SELECT_H
+#include <sys/select.h>
+#endif
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <arpa/inet.h>
+#include <netdb.h>
+#include <pwd.h>
+#include <inttypes.h>
+#if defined(__CYGWIN__)
+#undef _XOPEN_SOURCE
+#include <grp.h>
+#define _XOPEN_SOURCE 600
+#include "compat/cygwin.h"
+#else
+#undef _ALL_SOURCE /* AIX 5.3L defines a struct list with _ALL_SOURCE. */
+#include <grp.h>
+#define _ALL_SOURCE 1
+#endif
+#else 	/* __MINGW32__ */
+/* pull in Windows compatibility stuff */
+#include "compat/mingw.h"
+#endif	/* __MINGW32__ */
+
+#ifndef NO_ICONV
+#include <iconv.h>
+#endif
+
+#ifndef NO_OPENSSL
+#include <openssl/ssl.h>
+#include <openssl/err.h>
+#endif
+
+/* On most systems <limits.h> would have given us this, but
+ * not on some systems (e.g. GNU/Hurd).
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
+#ifndef PRIuMAX
+#define PRIuMAX "llu"
+#endif
+
+#ifndef PRIu32
+#define PRIu32 "u"
+#endif
+
+#ifndef PRIx32
+#define PRIx32 "x"
+#endif
+
+#ifndef PATH_SEP
+#define PATH_SEP ':'
+#endif
+
+#ifndef STRIP_EXTENSION
+#define STRIP_EXTENSION ""
+#endif
+
+#ifndef has_dos_drive_prefix
+#define has_dos_drive_prefix(path) 0
+#endif
+
+#ifndef is_dir_sep
+#define is_dir_sep(c) ((c) == '/')
+#endif
+
+#ifdef __GNUC__
+#define NORETURN __attribute__((__noreturn__))
+#else
+#define NORETURN
+#ifndef __attribute__
+#define __attribute__(x)
+#endif
+#endif
+
+/* General helper functions */
+extern void usage(const char *err) NORETURN;
+extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
+extern int error(const char *err, ...) __attribute__((format (printf, 1, 2)));
+extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)));
+
+extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
+
+extern int prefixcmp(const char *str, const char *prefix);
+extern time_t tm_to_time_t(const struct tm *tm);
+
+static inline const char *skip_prefix(const char *str, const char *prefix)
+{
+	size_t len = strlen(prefix);
+	return strncmp(str, prefix, len) ? NULL : str + len;
+}
+
+#if defined(NO_MMAP) || defined(USE_WIN32_MMAP)
+
+#ifndef PROT_READ
+#define PROT_READ 1
+#define PROT_WRITE 2
+#define MAP_PRIVATE 1
+#define MAP_FAILED ((void*)-1)
+#endif
+
+#define mmap git_mmap
+#define munmap git_munmap
+extern void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t offset);
+extern int git_munmap(void *start, size_t length);
+
+#else /* NO_MMAP || USE_WIN32_MMAP */
+
+#include <sys/mman.h>
+
+#endif /* NO_MMAP || USE_WIN32_MMAP */
+
+#ifdef NO_MMAP
+
+/* This value must be multiple of (pagesize * 2) */
+#define DEFAULT_PACKED_GIT_WINDOW_SIZE (1 * 1024 * 1024)
+
+#else /* NO_MMAP */
+
+/* This value must be multiple of (pagesize * 2) */
+#define DEFAULT_PACKED_GIT_WINDOW_SIZE \
+	(sizeof(void*) >= 8 \
+		?  1 * 1024 * 1024 * 1024 \
+		: 32 * 1024 * 1024)
+
+#endif /* NO_MMAP */
+
+#ifdef NO_ST_BLOCKS_IN_STRUCT_STAT
+#define on_disk_bytes(st) ((st).st_size)
+#else
+#define on_disk_bytes(st) ((st).st_blocks * 512)
+#endif
+
+#define DEFAULT_PACKED_GIT_LIMIT \
+	((1024L * 1024L) * (sizeof(void*) >= 8 ? 8192 : 256))
+
+#ifdef NO_PREAD
+#define pread git_pread
+extern ssize_t git_pread(int fd, void *buf, size_t count, off_t offset);
+#endif
+/*
+ * Forward decl that will remind us if its twin in cache.h changes.
+ * This function is used in compat/pread.c.  But we can't include
+ * cache.h there.
+ */
+extern ssize_t read_in_full(int fd, void *buf, size_t count);
+
+#ifdef NO_SETENV
+#define setenv gitsetenv
+extern int gitsetenv(const char *, const char *, int);
+#endif
+
+#ifdef NO_MKDTEMP
+#define mkdtemp gitmkdtemp
+extern char *gitmkdtemp(char *);
+#endif
+
+#ifdef NO_UNSETENV
+#define unsetenv gitunsetenv
+extern void gitunsetenv(const char *);
+#endif
+
+#ifdef NO_STRCASESTR
+#define strcasestr gitstrcasestr
+extern char *gitstrcasestr(const char *haystack, const char *needle);
+#endif
+
+#ifdef NO_STRLCPY
+#define strlcpy gitstrlcpy
+extern size_t gitstrlcpy(char *, const char *, size_t);
+#endif
+
+#ifdef NO_STRTOUMAX
+#define strtoumax gitstrtoumax
+extern uintmax_t gitstrtoumax(const char *, char **, int);
+#endif
+
+#ifdef NO_HSTRERROR
+#define hstrerror githstrerror
+extern const char *githstrerror(int herror);
+#endif
+
+#ifdef NO_MEMMEM
+#define memmem gitmemmem
+void *gitmemmem(const void *haystack, size_t haystacklen,
+                const void *needle, size_t needlelen);
+#endif
+
+#ifdef FREAD_READS_DIRECTORIES
+#ifdef fopen
+#undef fopen
+#endif
+#define fopen(a,b) git_fopen(a,b)
+extern FILE *git_fopen(const char*, const char*);
+#endif
+
+#ifdef SNPRINTF_RETURNS_BOGUS
+#define snprintf git_snprintf
+extern int git_snprintf(char *str, size_t maxsize,
+			const char *format, ...);
+#define vsnprintf git_vsnprintf
+extern int git_vsnprintf(char *str, size_t maxsize,
+			 const char *format, va_list ap);
+#endif
+
+#ifdef __GLIBC_PREREQ
+#if __GLIBC_PREREQ(2, 1)
+#define HAVE_STRCHRNUL
+#endif
+#endif
+
+#ifndef HAVE_STRCHRNUL
+#define strchrnul gitstrchrnul
+static inline char *gitstrchrnul(const char *s, int c)
+{
+	while (*s && *s != c)
+		s++;
+	return (char *)s;
+}
+#endif
+
+/*
+ * Wrappers:
+ */
+extern char *xstrdup(const char *str);
+extern void *xmalloc(size_t size);
+extern void *xmemdupz(const void *data, size_t len);
+extern char *xstrndup(const char *str, size_t len);
+extern void *xrealloc(void *ptr, size_t size);
+extern void *xcalloc(size_t nmemb, size_t size);
+extern void *xmmap(void *start, size_t length, int prot, int flags, int fd, off_t offset);
+extern ssize_t xread(int fd, void *buf, size_t len);
+extern ssize_t xwrite(int fd, const void *buf, size_t len);
+extern int xdup(int fd);
+extern FILE *xfdopen(int fd, const char *mode);
+extern int xmkstemp(char *template);
+
+static inline size_t xsize_t(off_t len)
+{
+	return (size_t)len;
+}
+
+static inline int has_extension(const char *filename, const char *ext)
+{
+	size_t len = strlen(filename);
+	size_t extlen = strlen(ext);
+	return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
+}
+
+/* Sane ctype - no locale, and works with signed chars */
+#undef isascii
+#undef isspace
+#undef isdigit
+#undef isalpha
+#undef isalnum
+#undef tolower
+#undef toupper
+extern unsigned char sane_ctype[256];
+#define GIT_SPACE 0x01
+#define GIT_DIGIT 0x02
+#define GIT_ALPHA 0x04
+#define GIT_GLOB_SPECIAL 0x08
+#define GIT_REGEX_SPECIAL 0x10
+#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0)
+#define isascii(x) (((x) & ~0x7f) == 0)
+#define isspace(x) sane_istest(x,GIT_SPACE)
+#define isdigit(x) sane_istest(x,GIT_DIGIT)
+#define isalpha(x) sane_istest(x,GIT_ALPHA)
+#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
+#define is_glob_special(x) sane_istest(x,GIT_GLOB_SPECIAL)
+#define is_regex_special(x) sane_istest(x,GIT_GLOB_SPECIAL | GIT_REGEX_SPECIAL)
+#define tolower(x) sane_case((unsigned char)(x), 0x20)
+#define toupper(x) sane_case((unsigned char)(x), 0)
+
+static inline int sane_case(int x, int high)
+{
+	if (sane_istest(x, GIT_ALPHA))
+		x = (x & ~0x20) | high;
+	return x;
+}
+
+static inline int strtoul_ui(char const *s, int base, unsigned int *result)
+{
+	unsigned long ul;
+	char *p;
+
+	errno = 0;
+	ul = strtoul(s, &p, base);
+	if (errno || *p || p == s || (unsigned int) ul != ul)
+		return -1;
+	*result = ul;
+	return 0;
+}
+
+static inline int strtol_i(char const *s, int base, int *result)
+{
+	long ul;
+	char *p;
+
+	errno = 0;
+	ul = strtol(s, &p, base);
+	if (errno || *p || p == s || (int) ul != ul)
+		return -1;
+	*result = ul;
+	return 0;
+}
+
+#ifdef INTERNAL_QSORT
+void git_qsort(void *base, size_t nmemb, size_t size,
+	       int(*compar)(const void *, const void *));
+#define qsort git_qsort
+#endif
+
+#ifndef DIR_HAS_BSD_GROUP_SEMANTICS
+# define FORCE_DIR_SET_GID S_ISGID
+#else
+# define FORCE_DIR_SET_GID 0
+#endif
+
+#ifdef NO_NSEC
+#undef USE_NSEC
+#define ST_CTIME_NSEC(st) 0
+#define ST_MTIME_NSEC(st) 0
+#else
+#ifdef USE_ST_TIMESPEC
+#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctimespec.tv_nsec))
+#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtimespec.tv_nsec))
+#else
+#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctim.tv_nsec))
+#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtim.tv_nsec))
+#endif
+#endif
+
+#endif
diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c
new file mode 100644
index 000000000000..6350d65f6d9e
--- /dev/null
+++ b/tools/perf/util/wrapper.c
@@ -0,0 +1,206 @@
+/*
+ * Various trivial helper wrappers around standard functions
+ */
+#include "cache.h"
+
+/*
+ * There's no pack memory to release - but stay close to the Git
+ * version so wrap this away:
+ */
+static inline void release_pack_memory(size_t size, int flag)
+{
+}
+
+char *xstrdup(const char *str)
+{
+	char *ret = strdup(str);
+	if (!ret) {
+		release_pack_memory(strlen(str) + 1, -1);
+		ret = strdup(str);
+		if (!ret)
+			die("Out of memory, strdup failed");
+	}
+	return ret;
+}
+
+void *xmalloc(size_t size)
+{
+	void *ret = malloc(size);
+	if (!ret && !size)
+		ret = malloc(1);
+	if (!ret) {
+		release_pack_memory(size, -1);
+		ret = malloc(size);
+		if (!ret && !size)
+			ret = malloc(1);
+		if (!ret)
+			die("Out of memory, malloc failed");
+	}
+#ifdef XMALLOC_POISON
+	memset(ret, 0xA5, size);
+#endif
+	return ret;
+}
+
+/*
+ * xmemdupz() allocates (len + 1) bytes of memory, duplicates "len" bytes of
+ * "data" to the allocated memory, zero terminates the allocated memory,
+ * and returns a pointer to the allocated memory. If the allocation fails,
+ * the program dies.
+ */
+void *xmemdupz(const void *data, size_t len)
+{
+	char *p = xmalloc(len + 1);
+	memcpy(p, data, len);
+	p[len] = '\0';
+	return p;
+}
+
+char *xstrndup(const char *str, size_t len)
+{
+	char *p = memchr(str, '\0', len);
+	return xmemdupz(str, p ? p - str : len);
+}
+
+void *xrealloc(void *ptr, size_t size)
+{
+	void *ret = realloc(ptr, size);
+	if (!ret && !size)
+		ret = realloc(ptr, 1);
+	if (!ret) {
+		release_pack_memory(size, -1);
+		ret = realloc(ptr, size);
+		if (!ret && !size)
+			ret = realloc(ptr, 1);
+		if (!ret)
+			die("Out of memory, realloc failed");
+	}
+	return ret;
+}
+
+void *xcalloc(size_t nmemb, size_t size)
+{
+	void *ret = calloc(nmemb, size);
+	if (!ret && (!nmemb || !size))
+		ret = calloc(1, 1);
+	if (!ret) {
+		release_pack_memory(nmemb * size, -1);
+		ret = calloc(nmemb, size);
+		if (!ret && (!nmemb || !size))
+			ret = calloc(1, 1);
+		if (!ret)
+			die("Out of memory, calloc failed");
+	}
+	return ret;
+}
+
+void *xmmap(void *start, size_t length,
+	int prot, int flags, int fd, off_t offset)
+{
+	void *ret = mmap(start, length, prot, flags, fd, offset);
+	if (ret == MAP_FAILED) {
+		if (!length)
+			return NULL;
+		release_pack_memory(length, fd);
+		ret = mmap(start, length, prot, flags, fd, offset);
+		if (ret == MAP_FAILED)
+			die("Out of memory? mmap failed: %s", strerror(errno));
+	}
+	return ret;
+}
+
+/*
+ * xread() is the same a read(), but it automatically restarts read()
+ * operations with a recoverable error (EAGAIN and EINTR). xread()
+ * DOES NOT GUARANTEE that "len" bytes is read even if the data is available.
+ */
+ssize_t xread(int fd, void *buf, size_t len)
+{
+	ssize_t nr;
+	while (1) {
+		nr = read(fd, buf, len);
+		if ((nr < 0) && (errno == EAGAIN || errno == EINTR))
+			continue;
+		return nr;
+	}
+}
+
+/*
+ * xwrite() is the same a write(), but it automatically restarts write()
+ * operations with a recoverable error (EAGAIN and EINTR). xwrite() DOES NOT
+ * GUARANTEE that "len" bytes is written even if the operation is successful.
+ */
+ssize_t xwrite(int fd, const void *buf, size_t len)
+{
+	ssize_t nr;
+	while (1) {
+		nr = write(fd, buf, len);
+		if ((nr < 0) && (errno == EAGAIN || errno == EINTR))
+			continue;
+		return nr;
+	}
+}
+
+ssize_t read_in_full(int fd, void *buf, size_t count)
+{
+	char *p = buf;
+	ssize_t total = 0;
+
+	while (count > 0) {
+		ssize_t loaded = xread(fd, p, count);
+		if (loaded <= 0)
+			return total ? total : loaded;
+		count -= loaded;
+		p += loaded;
+		total += loaded;
+	}
+
+	return total;
+}
+
+ssize_t write_in_full(int fd, const void *buf, size_t count)
+{
+	const char *p = buf;
+	ssize_t total = 0;
+
+	while (count > 0) {
+		ssize_t written = xwrite(fd, p, count);
+		if (written < 0)
+			return -1;
+		if (!written) {
+			errno = ENOSPC;
+			return -1;
+		}
+		count -= written;
+		p += written;
+		total += written;
+	}
+
+	return total;
+}
+
+int xdup(int fd)
+{
+	int ret = dup(fd);
+	if (ret < 0)
+		die("dup failed: %s", strerror(errno));
+	return ret;
+}
+
+FILE *xfdopen(int fd, const char *mode)
+{
+	FILE *stream = fdopen(fd, mode);
+	if (stream == NULL)
+		die("Out of memory? fdopen failed: %s", strerror(errno));
+	return stream;
+}
+
+int xmkstemp(char *template)
+{
+	int fd;
+
+	fd = mkstemp(template);
+	if (fd < 0)
+		die("Unable to create temporary file: %s", strerror(errno));
+	return fd;
+}
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index c3b99def9cbc..1eddae94bab3 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -85,7 +85,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 
 static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
 {
-	union ioapic_redir_entry *pent;
+	union kvm_ioapic_redirect_entry *pent;
 	int injected = -1;
 
 	pent = &ioapic->redirtbl[idx];
@@ -142,149 +142,40 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 	}
 }
 
-static int ioapic_inj_irq(struct kvm_ioapic *ioapic,
-			   struct kvm_vcpu *vcpu,
-			   u8 vector, u8 trig_mode, u8 delivery_mode)
-{
-	ioapic_debug("irq %d trig %d deliv %d\n", vector, trig_mode,
-		     delivery_mode);
-
-	ASSERT((delivery_mode == IOAPIC_FIXED) ||
-	       (delivery_mode == IOAPIC_LOWEST_PRIORITY));
-
-	return kvm_apic_set_irq(vcpu, vector, trig_mode);
-}
-
-static void ioapic_inj_nmi(struct kvm_vcpu *vcpu)
-{
-	kvm_inject_nmi(vcpu);
-	kvm_vcpu_kick(vcpu);
-}
-
-u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest,
-				    u8 dest_mode)
-{
-	u32 mask = 0;
-	int i;
-	struct kvm *kvm = ioapic->kvm;
-	struct kvm_vcpu *vcpu;
-
-	ioapic_debug("dest %d dest_mode %d\n", dest, dest_mode);
-
-	if (dest_mode == 0) {	/* Physical mode. */
-		if (dest == 0xFF) {	/* Broadcast. */
-			for (i = 0; i < KVM_MAX_VCPUS; ++i)
-				if (kvm->vcpus[i] && kvm->vcpus[i]->arch.apic)
-					mask |= 1 << i;
-			return mask;
-		}
-		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			vcpu = kvm->vcpus[i];
-			if (!vcpu)
-				continue;
-			if (kvm_apic_match_physical_addr(vcpu->arch.apic, dest)) {
-				if (vcpu->arch.apic)
-					mask = 1 << i;
-				break;
-			}
-		}
-	} else if (dest != 0)	/* Logical mode, MDA non-zero. */
-		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			vcpu = kvm->vcpus[i];
-			if (!vcpu)
-				continue;
-			if (vcpu->arch.apic &&
-			    kvm_apic_match_logical_addr(vcpu->arch.apic, dest))
-				mask |= 1 << vcpu->vcpu_id;
-		}
-	ioapic_debug("mask %x\n", mask);
-	return mask;
-}
-
 static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 {
-	u8 dest = ioapic->redirtbl[irq].fields.dest_id;
-	u8 dest_mode = ioapic->redirtbl[irq].fields.dest_mode;
-	u8 delivery_mode = ioapic->redirtbl[irq].fields.delivery_mode;
-	u8 vector = ioapic->redirtbl[irq].fields.vector;
-	u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode;
-	u32 deliver_bitmask;
-	struct kvm_vcpu *vcpu;
-	int vcpu_id, r = -1;
+	union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
+	struct kvm_lapic_irq irqe;
 
 	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
 		     "vector=%x trig_mode=%x\n",
-		     dest, dest_mode, delivery_mode, vector, trig_mode);
+		     entry->fields.dest, entry->fields.dest_mode,
+		     entry->fields.delivery_mode, entry->fields.vector,
+		     entry->fields.trig_mode);
 
-	deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic, dest,
-							  dest_mode);
-	if (!deliver_bitmask) {
-		ioapic_debug("no target on destination\n");
-		return 0;
-	}
+	irqe.dest_id = entry->fields.dest_id;
+	irqe.vector = entry->fields.vector;
+	irqe.dest_mode = entry->fields.dest_mode;
+	irqe.trig_mode = entry->fields.trig_mode;
+	irqe.delivery_mode = entry->fields.delivery_mode << 8;
+	irqe.level = 1;
+	irqe.shorthand = 0;
 
-	switch (delivery_mode) {
-	case IOAPIC_LOWEST_PRIORITY:
-		vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector,
-				deliver_bitmask);
 #ifdef CONFIG_X86
-		if (irq == 0)
-			vcpu = ioapic->kvm->vcpus[0];
-#endif
-		if (vcpu != NULL)
-			r = ioapic_inj_irq(ioapic, vcpu, vector,
-				       trig_mode, delivery_mode);
-		else
-			ioapic_debug("null lowest prio vcpu: "
-				     "mask=%x vector=%x delivery_mode=%x\n",
-				     deliver_bitmask, vector, IOAPIC_LOWEST_PRIORITY);
-		break;
-	case IOAPIC_FIXED:
-#ifdef CONFIG_X86
-		if (irq == 0)
-			deliver_bitmask = 1;
-#endif
-		for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) {
-			if (!(deliver_bitmask & (1 << vcpu_id)))
-				continue;
-			deliver_bitmask &= ~(1 << vcpu_id);
-			vcpu = ioapic->kvm->vcpus[vcpu_id];
-			if (vcpu) {
-				if (r < 0)
-					r = 0;
-				r += ioapic_inj_irq(ioapic, vcpu, vector,
-					       trig_mode, delivery_mode);
-			}
-		}
-		break;
-	case IOAPIC_NMI:
-		for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) {
-			if (!(deliver_bitmask & (1 << vcpu_id)))
-				continue;
-			deliver_bitmask &= ~(1 << vcpu_id);
-			vcpu = ioapic->kvm->vcpus[vcpu_id];
-			if (vcpu) {
-				ioapic_inj_nmi(vcpu);
-				r = 1;
-			}
-			else
-				ioapic_debug("NMI to vcpu %d failed\n",
-						vcpu->vcpu_id);
-		}
-		break;
-	default:
-		printk(KERN_WARNING "Unsupported delivery mode %d\n",
-		       delivery_mode);
-		break;
+	/* Always delivery PIT interrupt to vcpu 0 */
+	if (irq == 0) {
+		irqe.dest_mode = 0; /* Physical mode. */
+		irqe.dest_id = ioapic->kvm->vcpus[0]->vcpu_id;
 	}
-	return r;
+#endif
+	return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
 }
 
 int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 {
 	u32 old_irr = ioapic->irr;
 	u32 mask = 1 << irq;
-	union ioapic_redir_entry entry;
+	union kvm_ioapic_redirect_entry entry;
 	int ret = 1;
 
 	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
@@ -305,7 +196,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin,
 				    int trigger_mode)
 {
-	union ioapic_redir_entry *ent;
+	union kvm_ioapic_redirect_entry *ent;
 
 	ent = &ioapic->redirtbl[pin];
 
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index a34bd5e6436b..7080b713c160 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -40,22 +40,7 @@ struct kvm_ioapic {
 	u32 id;
 	u32 irr;
 	u32 pad;
-	union ioapic_redir_entry {
-		u64 bits;
-		struct {
-			u8 vector;
-			u8 delivery_mode:3;
-			u8 dest_mode:1;
-			u8 delivery_status:1;
-			u8 polarity:1;
-			u8 remote_irr:1;
-			u8 trig_mode:1;
-			u8 mask:1;
-			u8 reserve:7;
-			u8 reserved[4];
-			u8 dest_id;
-		} fields;
-	} redirtbl[IOAPIC_NUM_PINS];
+	union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
 	void (*ack_notifier)(void *opaque, int irq);
@@ -79,13 +64,13 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
 	return kvm->arch.vioapic;
 }
 
-struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
-				       unsigned long bitmap);
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+		int short_hand, int dest, int dest_mode);
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
 void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode);
 int kvm_ioapic_init(struct kvm *kvm);
 int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
 void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
-u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest,
-				u8 dest_mode);
-
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq);
 #endif
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 4c4037503600..15147583abd1 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -39,11 +39,16 @@ int kvm_iommu_map_pages(struct kvm *kvm,
 	pfn_t pfn;
 	int i, r = 0;
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
+	int flags;
 
 	/* check if iommu exists and in use */
 	if (!domain)
 		return 0;
 
+	flags = IOMMU_READ | IOMMU_WRITE;
+	if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
+		flags |= IOMMU_CACHE;
+
 	for (i = 0; i < npages; i++) {
 		/* check if already mapped */
 		if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn)))
@@ -53,8 +58,7 @@ int kvm_iommu_map_pages(struct kvm *kvm,
 		r = iommu_map_range(domain,
 				    gfn_to_gpa(gfn),
 				    pfn_to_hpa(pfn),
-				    PAGE_SIZE,
-				    IOMMU_READ | IOMMU_WRITE);
+				    PAGE_SIZE, flags);
 		if (r) {
 			printk(KERN_ERR "kvm_iommu_map_address:"
 			       "iommu failed to map pfn=%lx\n", pfn);
@@ -88,7 +92,7 @@ int kvm_assign_device(struct kvm *kvm,
 {
 	struct pci_dev *pdev = NULL;
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	int r;
+	int r, last_flags;
 
 	/* check if iommu exists and in use */
 	if (!domain)
@@ -107,12 +111,29 @@ int kvm_assign_device(struct kvm *kvm,
 		return r;
 	}
 
+	last_flags = kvm->arch.iommu_flags;
+	if (iommu_domain_has_cap(kvm->arch.iommu_domain,
+				 IOMMU_CAP_CACHE_COHERENCY))
+		kvm->arch.iommu_flags |= KVM_IOMMU_CACHE_COHERENCY;
+
+	/* Check if need to update IOMMU page table for guest memory */
+	if ((last_flags ^ kvm->arch.iommu_flags) ==
+			KVM_IOMMU_CACHE_COHERENCY) {
+		kvm_iommu_unmap_memslots(kvm);
+		r = kvm_iommu_map_memslots(kvm);
+		if (r)
+			goto out_unmap;
+	}
+
 	printk(KERN_DEBUG "assign device: host bdf = %x:%x:%x\n",
 		assigned_dev->host_busnr,
 		PCI_SLOT(assigned_dev->host_devfn),
 		PCI_FUNC(assigned_dev->host_devfn));
 
 	return 0;
+out_unmap:
+	kvm_iommu_unmap_memslots(kvm);
+	return r;
 }
 
 int kvm_deassign_device(struct kvm *kvm,
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 864ac5483baa..a8bd466d00cc 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -22,6 +22,9 @@
 #include <linux/kvm_host.h>
 
 #include <asm/msidef.h>
+#ifdef CONFIG_IA64
+#include <asm/iosapic.h>
+#endif
 
 #include "irq.h"
 
@@ -43,55 +46,71 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level);
 }
 
+inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
+{
+#ifdef CONFIG_IA64
+	return irq->delivery_mode ==
+		(IOSAPIC_LOWEST_PRIORITY << IOSAPIC_DELIVERY_SHIFT);
+#else
+	return irq->delivery_mode == APIC_DM_LOWEST;
+#endif
+}
+
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq)
+{
+	int i, r = -1;
+	struct kvm_vcpu *vcpu, *lowest = NULL;
+
+	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
+			kvm_is_dm_lowest_prio(irq))
+		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
+
+	for (i = 0; i < KVM_MAX_VCPUS; i++) {
+		vcpu = kvm->vcpus[i];
+
+		if (!vcpu || !kvm_apic_present(vcpu))
+			continue;
+
+		if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
+					irq->dest_id, irq->dest_mode))
+			continue;
+
+		if (!kvm_is_dm_lowest_prio(irq)) {
+			if (r < 0)
+				r = 0;
+			r += kvm_apic_set_irq(vcpu, irq);
+		} else {
+			if (!lowest)
+				lowest = vcpu;
+			else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
+				lowest = vcpu;
+		}
+	}
+
+	if (lowest)
+		r = kvm_apic_set_irq(lowest, irq);
+
+	return r;
+}
+
 static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 		       struct kvm *kvm, int level)
 {
-	int vcpu_id, r = -1;
-	struct kvm_vcpu *vcpu;
-	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
-	int dest_id = (e->msi.address_lo & MSI_ADDR_DEST_ID_MASK)
-			>> MSI_ADDR_DEST_ID_SHIFT;
-	int vector = (e->msi.data & MSI_DATA_VECTOR_MASK)
-			>> MSI_DATA_VECTOR_SHIFT;
-	int dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT,
-				(unsigned long *)&e->msi.address_lo);
-	int trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT,
-				(unsigned long *)&e->msi.data);
-	int delivery_mode = test_bit(MSI_DATA_DELIVERY_MODE_SHIFT,
-				(unsigned long *)&e->msi.data);
-	u32 deliver_bitmask;
+	struct kvm_lapic_irq irq;
 
-	BUG_ON(!ioapic);
+	irq.dest_id = (e->msi.address_lo &
+			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+	irq.vector = (e->msi.data &
+			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
+	irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+	irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
+	irq.delivery_mode = e->msi.data & 0x700;
+	irq.level = 1;
+	irq.shorthand = 0;
 
-	deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic,
-				dest_id, dest_mode);
-	/* IOAPIC delivery mode value is the same as MSI here */
-	switch (delivery_mode) {
-	case IOAPIC_LOWEST_PRIORITY:
-		vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector,
-				deliver_bitmask);
-		if (vcpu != NULL)
-			r = kvm_apic_set_irq(vcpu, vector, trig_mode);
-		else
-			printk(KERN_INFO "kvm: null lowest priority vcpu!\n");
-		break;
-	case IOAPIC_FIXED:
-		for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) {
-			if (!(deliver_bitmask & (1 << vcpu_id)))
-				continue;
-			deliver_bitmask &= ~(1 << vcpu_id);
-			vcpu = ioapic->kvm->vcpus[vcpu_id];
-			if (vcpu) {
-				if (r < 0)
-					r = 0;
-				r += kvm_apic_set_irq(vcpu, vector, trig_mode);
-			}
-		}
-		break;
-	default:
-		break;
-	}
-	return r;
+	/* TODO Deal with RH bit of MSI message address */
+	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
 /* This should be called with the kvm->lock mutex held
@@ -252,7 +271,7 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 			delta = 8;
 			break;
 		case KVM_IRQCHIP_IOAPIC:
-				e->set = kvm_set_ioapic_irq;
+			e->set = kvm_set_ioapic_irq;
 			break;
 		default:
 			goto out;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 4d0dd390aa50..764554350ed8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -41,6 +41,8 @@
 #include <linux/pagemap.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -60,9 +62,6 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
-static int msi2intx = 1;
-module_param(msi2intx, bool, 0);
-
 DEFINE_SPINLOCK(kvm_lock);
 LIST_HEAD(vm_list);
 
@@ -95,38 +94,96 @@ static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *h
 	return NULL;
 }
 
+static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
+				    *assigned_dev, int irq)
+{
+	int i, index;
+	struct msix_entry *host_msix_entries;
+
+	host_msix_entries = assigned_dev->host_msix_entries;
+
+	index = -1;
+	for (i = 0; i < assigned_dev->entries_nr; i++)
+		if (irq == host_msix_entries[i].vector) {
+			index = i;
+			break;
+		}
+	if (index < 0) {
+		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
+		return 0;
+	}
+
+	return index;
+}
+
 static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev;
+	struct kvm *kvm;
+	int irq, i;
 
 	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
 				    interrupt_work);
+	kvm = assigned_dev->kvm;
 
 	/* This is taken to safely inject irq inside the guest. When
 	 * the interrupt injection (or the ioapic code) uses a
 	 * finer-grained lock, update this
 	 */
-	mutex_lock(&assigned_dev->kvm->lock);
-	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
-		    assigned_dev->guest_irq, 1);
-
-	if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI) {
-		enable_irq(assigned_dev->host_irq);
-		assigned_dev->host_irq_disabled = false;
+	mutex_lock(&kvm->lock);
+	spin_lock_irq(&assigned_dev->assigned_dev_lock);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		struct kvm_guest_msix_entry *guest_entries =
+			assigned_dev->guest_msix_entries;
+		for (i = 0; i < assigned_dev->entries_nr; i++) {
+			if (!(guest_entries[i].flags &
+					KVM_ASSIGNED_MSIX_PENDING))
+				continue;
+			guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING;
+			kvm_set_irq(assigned_dev->kvm,
+				    assigned_dev->irq_source_id,
+				    guest_entries[i].vector, 1);
+			irq = assigned_dev->host_msix_entries[i].vector;
+			if (irq != 0)
+				enable_irq(irq);
+			assigned_dev->host_irq_disabled = false;
+		}
+	} else {
+		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+			    assigned_dev->guest_irq, 1);
+		if (assigned_dev->irq_requested_type &
+				KVM_DEV_IRQ_GUEST_MSI) {
+			enable_irq(assigned_dev->host_irq);
+			assigned_dev->host_irq_disabled = false;
+		}
 	}
+
+	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
 	mutex_unlock(&assigned_dev->kvm->lock);
 }
 
 static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
 {
+	unsigned long flags;
 	struct kvm_assigned_dev_kernel *assigned_dev =
 		(struct kvm_assigned_dev_kernel *) dev_id;
 
+	spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		int index = find_index_from_host_irq(assigned_dev, irq);
+		if (index < 0)
+			goto out;
+		assigned_dev->guest_msix_entries[index].flags |=
+			KVM_ASSIGNED_MSIX_PENDING;
+	}
+
 	schedule_work(&assigned_dev->interrupt_work);
 
 	disable_irq_nosync(irq);
 	assigned_dev->host_irq_disabled = true;
 
+out:
+	spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);
 	return IRQ_HANDLED;
 }
 
@@ -134,6 +191,7 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
 static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 {
 	struct kvm_assigned_dev_kernel *dev;
+	unsigned long flags;
 
 	if (kian->gsi == -1)
 		return;
@@ -146,28 +204,30 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 	/* The guest irq may be shared so this ack may be
 	 * from another device.
 	 */
+	spin_lock_irqsave(&dev->assigned_dev_lock, flags);
 	if (dev->host_irq_disabled) {
 		enable_irq(dev->host_irq);
 		dev->host_irq_disabled = false;
 	}
+	spin_unlock_irqrestore(&dev->assigned_dev_lock, flags);
 }
 
-/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
-static void kvm_free_assigned_irq(struct kvm *kvm,
-				  struct kvm_assigned_dev_kernel *assigned_dev)
+static void deassign_guest_irq(struct kvm *kvm,
+			       struct kvm_assigned_dev_kernel *assigned_dev)
 {
-	if (!irqchip_in_kernel(kvm))
-		return;
-
 	kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier);
+	assigned_dev->ack_notifier.gsi = -1;
 
 	if (assigned_dev->irq_source_id != -1)
 		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
 	assigned_dev->irq_source_id = -1;
+	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK);
+}
 
-	if (!assigned_dev->irq_requested_type)
-		return;
-
+/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
+static void deassign_host_irq(struct kvm *kvm,
+			      struct kvm_assigned_dev_kernel *assigned_dev)
+{
 	/*
 	 * In kvm_free_device_irq, cancel_work_sync return true if:
 	 * 1. work is scheduled, and then cancelled.
@@ -184,17 +244,64 @@ static void kvm_free_assigned_irq(struct kvm *kvm,
 	 * now, the kvm state is still legal for probably we also have to wait
 	 * interrupt_work done.
 	 */
-	disable_irq_nosync(assigned_dev->host_irq);
-	cancel_work_sync(&assigned_dev->interrupt_work);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		int i;
+		for (i = 0; i < assigned_dev->entries_nr; i++)
+			disable_irq_nosync(assigned_dev->
+					   host_msix_entries[i].vector);
 
-	free_irq(assigned_dev->host_irq, (void *)assigned_dev);
+		cancel_work_sync(&assigned_dev->interrupt_work);
 
-	if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
-		pci_disable_msi(assigned_dev->dev);
+		for (i = 0; i < assigned_dev->entries_nr; i++)
+			free_irq(assigned_dev->host_msix_entries[i].vector,
+				 (void *)assigned_dev);
 
-	assigned_dev->irq_requested_type = 0;
+		assigned_dev->entries_nr = 0;
+		kfree(assigned_dev->host_msix_entries);
+		kfree(assigned_dev->guest_msix_entries);
+		pci_disable_msix(assigned_dev->dev);
+	} else {
+		/* Deal with MSI and INTx */
+		disable_irq_nosync(assigned_dev->host_irq);
+		cancel_work_sync(&assigned_dev->interrupt_work);
+
+		free_irq(assigned_dev->host_irq, (void *)assigned_dev);
+
+		if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
+			pci_disable_msi(assigned_dev->dev);
+	}
+
+	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK);
 }
 
+static int kvm_deassign_irq(struct kvm *kvm,
+			    struct kvm_assigned_dev_kernel *assigned_dev,
+			    unsigned long irq_requested_type)
+{
+	unsigned long guest_irq_type, host_irq_type;
+
+	if (!irqchip_in_kernel(kvm))
+		return -EINVAL;
+	/* no irq assignment to deassign */
+	if (!assigned_dev->irq_requested_type)
+		return -ENXIO;
+
+	host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK;
+	guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK;
+
+	if (host_irq_type)
+		deassign_host_irq(kvm, assigned_dev);
+	if (guest_irq_type)
+		deassign_guest_irq(kvm, assigned_dev);
+
+	return 0;
+}
+
+static void kvm_free_assigned_irq(struct kvm *kvm,
+				  struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type);
+}
 
 static void kvm_free_assigned_device(struct kvm *kvm,
 				     struct kvm_assigned_dev_kernel
@@ -226,191 +333,245 @@ void kvm_free_all_assigned_devices(struct kvm *kvm)
 	}
 }
 
-static int assigned_device_update_intx(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *adev,
-			struct kvm_assigned_irq *airq)
+static int assigned_device_enable_host_intx(struct kvm *kvm,
+					    struct kvm_assigned_dev_kernel *dev)
 {
-	adev->guest_irq = airq->guest_irq;
-	adev->ack_notifier.gsi = airq->guest_irq;
-
-	if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_INTX)
-		return 0;
-
-	if (irqchip_in_kernel(kvm)) {
-		if (!msi2intx &&
-		    (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)) {
-			free_irq(adev->host_irq, (void *)adev);
-			pci_disable_msi(adev->dev);
-		}
-
-		if (!capable(CAP_SYS_RAWIO))
-			return -EPERM;
-
-		if (airq->host_irq)
-			adev->host_irq = airq->host_irq;
-		else
-			adev->host_irq = adev->dev->irq;
-
-		/* Even though this is PCI, we don't want to use shared
-		 * interrupts. Sharing host devices with guest-assigned devices
-		 * on the same interrupt line is not a happy situation: there
-		 * are going to be long delays in accepting, acking, etc.
-		 */
-		if (request_irq(adev->host_irq, kvm_assigned_dev_intr,
-				0, "kvm_assigned_intx_device", (void *)adev))
-			return -EIO;
-	}
-
-	adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_INTX |
-				   KVM_ASSIGNED_DEV_HOST_INTX;
+	dev->host_irq = dev->dev->irq;
+	/* Even though this is PCI, we don't want to use shared
+	 * interrupts. Sharing host devices with guest-assigned devices
+	 * on the same interrupt line is not a happy situation: there
+	 * are going to be long delays in accepting, acking, etc.
+	 */
+	if (request_irq(dev->host_irq, kvm_assigned_dev_intr,
+			0, "kvm_assigned_intx_device", (void *)dev))
+		return -EIO;
 	return 0;
 }
 
-#ifdef CONFIG_X86
-static int assigned_device_update_msi(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *adev,
-			struct kvm_assigned_irq *airq)
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_host_msi(struct kvm *kvm,
+					   struct kvm_assigned_dev_kernel *dev)
 {
 	int r;
 
-	adev->guest_irq = airq->guest_irq;
-	if (airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI) {
-		/* x86 don't care upper address of guest msi message addr */
-		adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_MSI;
-		adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_INTX;
-		adev->ack_notifier.gsi = -1;
-	} else if (msi2intx) {
-		adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_INTX;
-		adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_MSI;
-		adev->ack_notifier.gsi = airq->guest_irq;
-	} else {
-		/*
-		 * Guest require to disable device MSI, we disable MSI and
-		 * re-enable INTx by default again. Notice it's only for
-		 * non-msi2intx.
-		 */
-		assigned_device_update_intx(kvm, adev, airq);
-		return 0;
+	if (!dev->dev->msi_enabled) {
+		r = pci_enable_msi(dev->dev);
+		if (r)
+			return r;
 	}
 
-	if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
-		return 0;
-
-	if (irqchip_in_kernel(kvm)) {
-		if (!msi2intx) {
-			if (adev->irq_requested_type &
-					KVM_ASSIGNED_DEV_HOST_INTX)
-				free_irq(adev->host_irq, (void *)adev);
-
-			r = pci_enable_msi(adev->dev);
-			if (r)
-				return r;
-		}
-
-		adev->host_irq = adev->dev->irq;
-		if (request_irq(adev->host_irq, kvm_assigned_dev_intr, 0,
-				"kvm_assigned_msi_device", (void *)adev))
-			return -EIO;
+	dev->host_irq = dev->dev->irq;
+	if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0,
+			"kvm_assigned_msi_device", (void *)dev)) {
+		pci_disable_msi(dev->dev);
+		return -EIO;
 	}
 
-	if (!msi2intx)
-		adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_MSI;
-
-	adev->irq_requested_type |= KVM_ASSIGNED_DEV_HOST_MSI;
 	return 0;
 }
 #endif
 
-static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
-				   struct kvm_assigned_irq
-				   *assigned_irq)
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_host_msix(struct kvm *kvm,
+					    struct kvm_assigned_dev_kernel *dev)
 {
-	int r = 0;
+	int i, r = -EINVAL;
+
+	/* host_msix_entries and guest_msix_entries should have been
+	 * initialized */
+	if (dev->entries_nr == 0)
+		return r;
+
+	r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr);
+	if (r)
+		return r;
+
+	for (i = 0; i < dev->entries_nr; i++) {
+		r = request_irq(dev->host_msix_entries[i].vector,
+				kvm_assigned_dev_intr, 0,
+				"kvm_assigned_msix_device",
+				(void *)dev);
+		/* FIXME: free requested_irq's on failure */
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+
+#endif
+
+static int assigned_device_enable_guest_intx(struct kvm *kvm,
+				struct kvm_assigned_dev_kernel *dev,
+				struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = irq->guest_irq;
+	return 0;
+}
+
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_guest_msi(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *dev,
+			struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = -1;
+	return 0;
+}
+#endif
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_guest_msix(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *dev,
+			struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = -1;
+	return 0;
+}
+#endif
+
+static int assign_host_irq(struct kvm *kvm,
+			   struct kvm_assigned_dev_kernel *dev,
+			   __u32 host_irq_type)
+{
+	int r = -EEXIST;
+
+	if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
+		return r;
+
+	switch (host_irq_type) {
+	case KVM_DEV_IRQ_HOST_INTX:
+		r = assigned_device_enable_host_intx(kvm, dev);
+		break;
+#ifdef __KVM_HAVE_MSI
+	case KVM_DEV_IRQ_HOST_MSI:
+		r = assigned_device_enable_host_msi(kvm, dev);
+		break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+	case KVM_DEV_IRQ_HOST_MSIX:
+		r = assigned_device_enable_host_msix(kvm, dev);
+		break;
+#endif
+	default:
+		r = -EINVAL;
+	}
+
+	if (!r)
+		dev->irq_requested_type |= host_irq_type;
+
+	return r;
+}
+
+static int assign_guest_irq(struct kvm *kvm,
+			    struct kvm_assigned_dev_kernel *dev,
+			    struct kvm_assigned_irq *irq,
+			    unsigned long guest_irq_type)
+{
+	int id;
+	int r = -EEXIST;
+
+	if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK)
+		return r;
+
+	id = kvm_request_irq_source_id(kvm);
+	if (id < 0)
+		return id;
+
+	dev->irq_source_id = id;
+
+	switch (guest_irq_type) {
+	case KVM_DEV_IRQ_GUEST_INTX:
+		r = assigned_device_enable_guest_intx(kvm, dev, irq);
+		break;
+#ifdef __KVM_HAVE_MSI
+	case KVM_DEV_IRQ_GUEST_MSI:
+		r = assigned_device_enable_guest_msi(kvm, dev, irq);
+		break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+	case KVM_DEV_IRQ_GUEST_MSIX:
+		r = assigned_device_enable_guest_msix(kvm, dev, irq);
+		break;
+#endif
+	default:
+		r = -EINVAL;
+	}
+
+	if (!r) {
+		dev->irq_requested_type |= guest_irq_type;
+		kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
+	} else
+		kvm_free_irq_source_id(kvm, dev->irq_source_id);
+
+	return r;
+}
+
+/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */
+static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
+				   struct kvm_assigned_irq *assigned_irq)
+{
+	int r = -EINVAL;
+	struct kvm_assigned_dev_kernel *match;
+	unsigned long host_irq_type, guest_irq_type;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	if (!irqchip_in_kernel(kvm))
+		return r;
+
+	mutex_lock(&kvm->lock);
+	r = -ENODEV;
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_irq->assigned_dev_id);
+	if (!match)
+		goto out;
+
+	host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK);
+	guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK);
+
+	r = -EINVAL;
+	/* can only assign one type at a time */
+	if (hweight_long(host_irq_type) > 1)
+		goto out;
+	if (hweight_long(guest_irq_type) > 1)
+		goto out;
+	if (host_irq_type == 0 && guest_irq_type == 0)
+		goto out;
+
+	r = 0;
+	if (host_irq_type)
+		r = assign_host_irq(kvm, match, host_irq_type);
+	if (r)
+		goto out;
+
+	if (guest_irq_type)
+		r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type);
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
+					 struct kvm_assigned_irq
+					 *assigned_irq)
+{
+	int r = -ENODEV;
 	struct kvm_assigned_dev_kernel *match;
-	u32 current_flags = 0, changed_flags;
 
 	mutex_lock(&kvm->lock);
 
 	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
 				      assigned_irq->assigned_dev_id);
-	if (!match) {
-		mutex_unlock(&kvm->lock);
-		return -EINVAL;
-	}
-
-	if (!match->irq_requested_type) {
-		INIT_WORK(&match->interrupt_work,
-				kvm_assigned_dev_interrupt_work_handler);
-		if (irqchip_in_kernel(kvm)) {
-			/* Register ack nofitier */
-			match->ack_notifier.gsi = -1;
-			match->ack_notifier.irq_acked =
-					kvm_assigned_dev_ack_irq;
-			kvm_register_irq_ack_notifier(kvm,
-					&match->ack_notifier);
-
-			/* Request IRQ source ID */
-			r = kvm_request_irq_source_id(kvm);
-			if (r < 0)
-				goto out_release;
-			else
-				match->irq_source_id = r;
-
-#ifdef CONFIG_X86
-			/* Determine host device irq type, we can know the
-			 * result from dev->msi_enabled */
-			if (msi2intx)
-				pci_enable_msi(match->dev);
-#endif
-		}
-	}
-
-	if ((match->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) &&
-		 (match->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI))
-		current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSI;
-
-	changed_flags = assigned_irq->flags ^ current_flags;
-
-	if ((changed_flags & KVM_DEV_IRQ_ASSIGN_MSI_ACTION) ||
-	    (msi2intx && match->dev->msi_enabled)) {
-#ifdef CONFIG_X86
-		r = assigned_device_update_msi(kvm, match, assigned_irq);
-		if (r) {
-			printk(KERN_WARNING "kvm: failed to enable "
-					"MSI device!\n");
-			goto out_release;
-		}
-#else
-		r = -ENOTTY;
-#endif
-	} else if (assigned_irq->host_irq == 0 && match->dev->irq == 0) {
-		/* Host device IRQ 0 means don't support INTx */
-		if (!msi2intx) {
-			printk(KERN_WARNING
-			       "kvm: wait device to enable MSI!\n");
-			r = 0;
-		} else {
-			printk(KERN_WARNING
-			       "kvm: failed to enable MSI device!\n");
-			r = -ENOTTY;
-			goto out_release;
-		}
-	} else {
-		/* Non-sharing INTx mode */
-		r = assigned_device_update_intx(kvm, match, assigned_irq);
-		if (r) {
-			printk(KERN_WARNING "kvm: failed to enable "
-					"INTx device!\n");
-			goto out_release;
-		}
-	}
+	if (!match)
+		goto out;
 
+	r = kvm_deassign_irq(kvm, match, assigned_irq->flags);
+out:
 	mutex_unlock(&kvm->lock);
 	return r;
-out_release:
-	mutex_unlock(&kvm->lock);
-	kvm_free_assigned_device(kvm, match);
-	return r;
 }
 
 static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
@@ -427,7 +588,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 				      assigned_dev->assigned_dev_id);
 	if (match) {
 		/* device already assigned */
-		r = -EINVAL;
+		r = -EEXIST;
 		goto out;
 	}
 
@@ -464,8 +625,12 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	match->host_devfn = assigned_dev->devfn;
 	match->flags = assigned_dev->flags;
 	match->dev = dev;
+	spin_lock_init(&match->assigned_dev_lock);
 	match->irq_source_id = -1;
 	match->kvm = kvm;
+	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
+	INIT_WORK(&match->interrupt_work,
+		  kvm_assigned_dev_interrupt_work_handler);
 
 	list_add(&match->list, &kvm->arch.assigned_dev_head);
 
@@ -878,6 +1043,8 @@ static void kvm_destroy_vm(struct kvm *kvm)
 #endif
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
+#else
+	kvm_arch_flush_shadow(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
 	mmdrop(mm);
@@ -919,9 +1086,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 {
 	int r;
 	gfn_t base_gfn;
-	unsigned long npages;
-	int largepages;
-	unsigned long i;
+	unsigned long npages, ugfn;
+	unsigned long largepages, i;
 	struct kvm_memory_slot *memslot;
 	struct kvm_memory_slot old, new;
 
@@ -1010,6 +1176,14 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			new.lpage_info[0].write_count = 1;
 		if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE)
 			new.lpage_info[largepages-1].write_count = 1;
+		ugfn = new.userspace_addr >> PAGE_SHIFT;
+		/*
+		 * If the gfn and userspace address are not aligned wrt each
+		 * other, disable large page support for this slot
+		 */
+		if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1))
+			for (i = 0; i < largepages; ++i)
+				new.lpage_info[i].write_count = 1;
 	}
 
 	/* Allocate page dirty bitmap if needed */
@@ -1043,8 +1217,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	kvm_free_physmem_slot(&old, npages ? &new : NULL);
 	/* Slot deletion case: we have to update the current slot */
+	spin_lock(&kvm->mmu_lock);
 	if (!npages)
 		*memslot = old;
+	spin_unlock(&kvm->mmu_lock);
 #ifdef CONFIG_DMAR
 	/* map the pages in iommu page table */
 	r = kvm_iommu_map_pages(kvm, base_gfn, npages);
@@ -1454,12 +1630,14 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	for (;;) {
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
-		if (kvm_cpu_has_interrupt(vcpu) ||
-		    kvm_cpu_has_pending_timer(vcpu) ||
-		    kvm_arch_vcpu_runnable(vcpu)) {
+		if ((kvm_arch_interrupt_allowed(vcpu) &&
+					kvm_cpu_has_interrupt(vcpu)) ||
+				kvm_arch_vcpu_runnable(vcpu)) {
 			set_bit(KVM_REQ_UNHALT, &vcpu->requests);
 			break;
 		}
+		if (kvm_cpu_has_pending_timer(vcpu))
+			break;
 		if (signal_pending(current))
 			break;
 
@@ -1593,6 +1771,88 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
 	return 0;
 }
 
+#ifdef __KVM_HAVE_MSIX
+static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
+				    struct kvm_assigned_msix_nr *entry_nr)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *adev;
+
+	mutex_lock(&kvm->lock);
+
+	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      entry_nr->assigned_dev_id);
+	if (!adev) {
+		r = -EINVAL;
+		goto msix_nr_out;
+	}
+
+	if (adev->entries_nr == 0) {
+		adev->entries_nr = entry_nr->entry_nr;
+		if (adev->entries_nr == 0 ||
+		    adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) {
+			r = -EINVAL;
+			goto msix_nr_out;
+		}
+
+		adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
+						entry_nr->entry_nr,
+						GFP_KERNEL);
+		if (!adev->host_msix_entries) {
+			r = -ENOMEM;
+			goto msix_nr_out;
+		}
+		adev->guest_msix_entries = kzalloc(
+				sizeof(struct kvm_guest_msix_entry) *
+				entry_nr->entry_nr, GFP_KERNEL);
+		if (!adev->guest_msix_entries) {
+			kfree(adev->host_msix_entries);
+			r = -ENOMEM;
+			goto msix_nr_out;
+		}
+	} else /* Not allowed set MSI-X number twice */
+		r = -EINVAL;
+msix_nr_out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
+				       struct kvm_assigned_msix_entry *entry)
+{
+	int r = 0, i;
+	struct kvm_assigned_dev_kernel *adev;
+
+	mutex_lock(&kvm->lock);
+
+	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      entry->assigned_dev_id);
+
+	if (!adev) {
+		r = -EINVAL;
+		goto msix_entry_out;
+	}
+
+	for (i = 0; i < adev->entries_nr; i++)
+		if (adev->guest_msix_entries[i].vector == 0 ||
+		    adev->guest_msix_entries[i].entry == entry->entry) {
+			adev->guest_msix_entries[i].entry = entry->entry;
+			adev->guest_msix_entries[i].vector = entry->gsi;
+			adev->host_msix_entries[i].entry = entry->entry;
+			break;
+		}
+	if (i == adev->entries_nr) {
+		r = -ENOSPC;
+		goto msix_entry_out;
+	}
+
+msix_entry_out:
+	mutex_unlock(&kvm->lock);
+
+	return r;
+}
+#endif
+
 static long kvm_vcpu_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -1864,6 +2124,11 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 	case KVM_ASSIGN_IRQ: {
+		r = -EOPNOTSUPP;
+		break;
+	}
+#ifdef KVM_CAP_ASSIGN_DEV_IRQ
+	case KVM_ASSIGN_DEV_IRQ: {
 		struct kvm_assigned_irq assigned_irq;
 
 		r = -EFAULT;
@@ -1874,6 +2139,18 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out;
 		break;
 	}
+	case KVM_DEASSIGN_DEV_IRQ: {
+		struct kvm_assigned_irq assigned_irq;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+			goto out;
+		r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq);
+		if (r)
+			goto out;
+		break;
+	}
+#endif
 #endif
 #ifdef KVM_CAP_DEVICE_DEASSIGNMENT
 	case KVM_DEASSIGN_PCI_DEVICE: {
@@ -1917,7 +2194,29 @@ static long kvm_vm_ioctl(struct file *filp,
 		vfree(entries);
 		break;
 	}
+#ifdef __KVM_HAVE_MSIX
+	case KVM_ASSIGN_SET_MSIX_NR: {
+		struct kvm_assigned_msix_nr entry_nr;
+		r = -EFAULT;
+		if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
+			goto out;
+		r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_ASSIGN_SET_MSIX_ENTRY: {
+		struct kvm_assigned_msix_entry entry;
+		r = -EFAULT;
+		if (copy_from_user(&entry, argp, sizeof entry))
+			goto out;
+		r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
+		if (r)
+			goto out;
+		break;
+	}
 #endif
+#endif /* KVM_CAP_IRQ_ROUTING */
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -2112,15 +2411,15 @@ EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot);
 static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 		      void *v)
 {
-	if (val == SYS_RESTART) {
-		/*
-		 * Some (well, at least mine) BIOSes hang on reboot if
-		 * in vmx root mode.
-		 */
-		printk(KERN_INFO "kvm: exiting hardware virtualization\n");
-		kvm_rebooting = true;
-		on_each_cpu(hardware_disable, NULL, 1);
-	}
+	/*
+	 * Some (well, at least mine) BIOSes hang on reboot if
+	 * in vmx root mode.
+	 *
+	 * And Intel TXT required VMX off for all cpu when system shutdown.
+	 */
+	printk(KERN_INFO "kvm: exiting hardware virtualization\n");
+	kvm_rebooting = true;
+	on_each_cpu(hardware_disable, NULL, 1);
 	return NOTIFY_OK;
 }
 
@@ -2305,7 +2604,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 		r = -ENOMEM;
 		goto out_free_0;
 	}
-	cpumask_clear(cpus_hardware_enabled);
 
 	r = kvm_arch_hardware_setup();
 	if (r < 0)
@@ -2354,9 +2652,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 
 	kvm_preempt_ops.sched_in = kvm_sched_in;
 	kvm_preempt_ops.sched_out = kvm_sched_out;
-#ifndef CONFIG_X86
-	msi2intx = 0;
-#endif
 
 	return 0;