Merge branch 'master' into for-2.6.35

Conflicts:
	fs/block_dev.c

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

Documentation/HOWTO

@@ -234,7 +234,7 @@ process is as follows:
     Linus, usually the patches that have already been included in the
     -next kernel for a few weeks.  The preferred way to submit big changes
     is using git (the kernel's source management tool, more information
-    can be found at http://git.or.cz/) but plain patches are also just
+    can be found at http://git-scm.com/) but plain patches are also just
     fine.
   - After two weeks a -rc1 kernel is released it is now possible to push
     only patches that do not include new features that could affect the

Documentation/RCU/NMI-RCU.txt

@@ -34,7 +34,7 @@ NMI handler.
 		cpu = smp_processor_id();
 		++nmi_count(cpu);
 
-		if (!rcu_dereference(nmi_callback)(regs, cpu))
+		if (!rcu_dereference_sched(nmi_callback)(regs, cpu))
 			default_do_nmi(regs);
 
 		nmi_exit();
@@ -47,12 +47,13 @@ function pointer.  If this handler returns zero, do_nmi() invokes the
 default_do_nmi() function to handle a machine-specific NMI.  Finally,
 preemption is restored.
 
-Strictly speaking, rcu_dereference() is not needed, since this code runs
-only on i386, which does not need rcu_dereference() anyway.  However,
-it is a good documentation aid, particularly for anyone attempting to
-do something similar on Alpha.
+In theory, rcu_dereference_sched() is not needed, since this code runs
+only on i386, which in theory does not need rcu_dereference_sched()
+anyway.  However, in practice it is a good documentation aid, particularly
+for anyone attempting to do something similar on Alpha or on systems
+with aggressive optimizing compilers.
 
-Quick Quiz:  Why might the rcu_dereference() be necessary on Alpha,
+Quick Quiz:  Why might the rcu_dereference_sched() be necessary on Alpha,
 	     given that the code referenced by the pointer is read-only?
 
 
@@ -99,17 +100,21 @@ invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.
 
 Answer to Quick Quiz
 
-	Why might the rcu_dereference() be necessary on Alpha, given
+	Why might the rcu_dereference_sched() be necessary on Alpha, given
 	that the code referenced by the pointer is read-only?
 
 	Answer: The caller to set_nmi_callback() might well have
-		initialized some data that is to be used by the
-		new NMI handler.  In this case, the rcu_dereference()
-		would be needed, because otherwise a CPU that received
-		an NMI just after the new handler was set might see
-		the pointer to the new NMI handler, but the old
-		pre-initialized version of the handler's data.
+		initialized some data that is to be used by the new NMI
+		handler.  In this case, the rcu_dereference_sched() would
+		be needed, because otherwise a CPU that received an NMI
+		just after the new handler was set might see the pointer
+		to the new NMI handler, but the old pre-initialized
+		version of the handler's data.
 
-		More important, the rcu_dereference() makes it clear
-		to someone reading the code that the pointer is being
-		protected by RCU.
+		This same sad story can happen on other CPUs when using
+		a compiler with aggressive pointer-value speculation
+		optimizations.
+
+		More important, the rcu_dereference_sched() makes it
+		clear to someone reading the code that the pointer is
+		being protected by RCU-sched.

Documentation/RCU/checklist.txt

@@ -260,7 +260,8 @@ over a rather long period of time, but improvements are always welcome!
 	The reason that it is permissible to use RCU list-traversal
 	primitives when the update-side lock is held is that doing so
 	can be quite helpful in reducing code bloat when common code is
-	shared between readers and updaters.
+	shared between readers and updaters.  Additional primitives
+	are provided for this case, as discussed in lockdep.txt.
 
 10.	Conversely, if you are in an RCU read-side critical section,
 	and you don't hold the appropriate update-side lock, you -must-
@@ -344,8 +345,8 @@ over a rather long period of time, but improvements are always welcome!
 	requiring SRCU's read-side deadlock immunity or low read-side
 	realtime latency.
 
-	Note that, rcu_assign_pointer() and rcu_dereference() relate to
-	SRCU just as they do to other forms of RCU.
+	Note that, rcu_assign_pointer() relates to SRCU just as they do
+	to other forms of RCU.
 
 15.	The whole point of call_rcu(), synchronize_rcu(), and friends
 	is to wait until all pre-existing readers have finished before

Documentation/RCU/lockdep.txt

@@ -32,9 +32,20 @@ checking of rcu_dereference() primitives:
 	srcu_dereference(p, sp):
 		Check for SRCU read-side critical section.
 	rcu_dereference_check(p, c):
-		Use explicit check expression "c".
+		Use explicit check expression "c".  This is useful in
+		code that is invoked by both readers and updaters.
 	rcu_dereference_raw(p)
 		Don't check.  (Use sparingly, if at all.)
+	rcu_dereference_protected(p, c):
+		Use explicit check expression "c", and omit all barriers
+		and compiler constraints.  This is useful when the data
+		structure cannot change, for example, in code that is
+		invoked only by updaters.
+	rcu_access_pointer(p):
+		Return the value of the pointer and omit all barriers,
+		but retain the compiler constraints that prevent duplicating
+		or coalescsing.  This is useful when when testing the
+		value of the pointer itself, for example, against NULL.
 
 The rcu_dereference_check() check expression can be any boolean
 expression, but would normally include one of the rcu_read_lock_held()
@@ -59,7 +70,20 @@ In case (1), the pointer is picked up in an RCU-safe manner for vanilla
 RCU read-side critical sections, in case (2) the ->file_lock prevents
 any change from taking place, and finally, in case (3) the current task
 is the only task accessing the file_struct, again preventing any change
-from taking place.
+from taking place.  If the above statement was invoked only from updater
+code, it could instead be written as follows:
+
+	file = rcu_dereference_protected(fdt->fd[fd],
+					 lockdep_is_held(&files->file_lock) ||
+					 atomic_read(&files->count) == 1);
+
+This would verify cases #2 and #3 above, and furthermore lockdep would
+complain if this was used in an RCU read-side critical section unless one
+of these two cases held.  Because rcu_dereference_protected() omits all
+barriers and compiler constraints, it generates better code than do the
+other flavors of rcu_dereference().  On the other hand, it is illegal
+to use rcu_dereference_protected() if either the RCU-protected pointer
+or the RCU-protected data that it points to can change concurrently.
 
 There are currently only "universal" versions of the rcu_assign_pointer()
 and RCU list-/tree-traversal primitives, which do not (yet) check for

Documentation/RCU/whatisRCU.txt

@@ -840,6 +840,12 @@ SRCU:	Initialization/cleanup
 	init_srcu_struct
 	cleanup_srcu_struct
 
+All:  lockdep-checked RCU-protected pointer access
+
+	rcu_dereference_check
+	rcu_dereference_protected
+	rcu_access_pointer
+
 See the comment headers in the source code (or the docbook generated
 from them) for more information.
 

Documentation/cgroups/cgroups.txt

@@ -235,8 +235,7 @@ containing the following files describing that cgroup:
  - cgroup.procs: list of tgids in the cgroup.  This list is not
    guaranteed to be sorted or free of duplicate tgids, and userspace
    should sort/uniquify the list if this property is required.
-   Writing a tgid into this file moves all threads with that tgid into
-   this cgroup.
+   This is a read-only file, for now.
  - notify_on_release flag: run the release agent on exit?
  - release_agent: the path to use for release notifications (this file
    exists in the top cgroup only)

Documentation/input/multi-touch-protocol.txt

@@ -68,6 +68,22 @@ like:
    SYN_MT_REPORT
    SYN_REPORT
 
+Here is the sequence after lifting one of the fingers:
+
+   ABS_MT_POSITION_X
+   ABS_MT_POSITION_Y
+   SYN_MT_REPORT
+   SYN_REPORT
+
+And here is the sequence after lifting the remaining finger:
+
+   SYN_MT_REPORT
+   SYN_REPORT
+
+If the driver reports one of BTN_TOUCH or ABS_PRESSURE in addition to the
+ABS_MT events, the last SYN_MT_REPORT event may be omitted. Otherwise, the
+last SYN_REPORT will be dropped by the input core, resulting in no
+zero-finger event reaching userland.
 
 Event Semantics
 ---------------
@@ -217,11 +233,6 @@ where examples can be found.
 difference between the contact position and the approaching tool position
 could be used to derive tilt.
 [2] The list can of course be extended.
-[3] The multi-touch X driver is currently in the prototyping stage. At the
-time of writing (April 2009), the MT protocol is not yet merged, and the
-prototype implements finger matching, basic mouse support and two-finger
-scrolling. The project aims at improving the quality of current multi-touch
-functionality available in the Synaptics X driver, and in addition
-implement more advanced gestures.
+[3] Multitouch X driver project: http://bitmath.org/code/multitouch/.
 [4] See the section on event computation.
 [5] See the section on finger tracking.

Documentation/kernel-parameters.txt

@@ -320,11 +320,6 @@ and is between 256 and 4096 characters. It is defined in the file
 	amd_iommu=	[HW,X86-84]
 			Pass parameters to the AMD IOMMU driver in the system.
 			Possible values are:
-			isolate - enable device isolation (each device, as far
-			          as possible, will get its own protection
-			          domain) [default]
-			share - put every device behind one IOMMU into the
-				same protection domain
 			fullflush - enable flushing of IO/TLB entries when
 				    they are unmapped. Otherwise they are
 				    flushed before they will be reused, which
@@ -1199,7 +1194,7 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	libata.force=	[LIBATA] Force configurations.  The format is comma
 			separated list of "[ID:]VAL" where ID is
-			PORT[:DEVICE].  PORT and DEVICE are decimal numbers
+			PORT[.DEVICE].  PORT and DEVICE are decimal numbers
 			matching port, link or device.  Basically, it matches
 			the ATA ID string printed on console by libata.  If
 			the whole ID part is omitted, the last PORT and DEVICE

Documentation/networking/timestamping.txt

@@ -41,11 +41,12 @@ SOF_TIMESTAMPING_SOFTWARE:     return system time stamp generated in
 SOF_TIMESTAMPING_TX/RX determine how time stamps are generated.
 SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the
 following control message:
-    struct scm_timestamping {
+
+struct scm_timestamping {
 	struct timespec systime;
 	struct timespec hwtimetrans;
 	struct timespec hwtimeraw;
-    };
+};
 
 recvmsg() can be used to get this control message for regular incoming
 packets. For send time stamps the outgoing packet is looped back to
@@ -87,7 +88,8 @@ by the network device and will be empty without that support.
 SIOCSHWTSTAMP:
 
 Hardware time stamping must also be initialized for each device driver
-that is expected to do hardware time stamping. The parameter is:
+that is expected to do hardware time stamping. The parameter is defined in
+/include/linux/net_tstamp.h as:
 
 struct hwtstamp_config {
 	int flags;	/* no flags defined right now, must be zero */
@@ -145,36 +147,50 @@ enum {
 	/* PTP v1, UDP, any kind of event packet */
 	HWTSTAMP_FILTER_PTP_V1_L4_EVENT,
 
-        ...
+	/* for the complete list of values, please check
+	 * the include file /include/linux/net_tstamp.h
+	 */
 };
 
 
 DEVICE IMPLEMENTATION
 
 A driver which supports hardware time stamping must support the
-SIOCSHWTSTAMP ioctl. Time stamps for received packets must be stored
-in the skb with skb_hwtstamp_set().
+SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with
+the actual values as described in the section on SIOCSHWTSTAMP.
+
+Time stamps for received packets must be stored in the skb. To get a pointer
+to the shared time stamp structure of the skb call skb_hwtstamps(). Then
+set the time stamps in the structure:
+
+struct skb_shared_hwtstamps {
+	/* hardware time stamp transformed into duration
+	 * since arbitrary point in time
+	 */
+	ktime_t	hwtstamp;
+	ktime_t	syststamp; /* hwtstamp transformed to system time base */
+};
 
 Time stamps for outgoing packets are to be generated as follows:
-- In hard_start_xmit(), check if skb_hwtstamp_check_tx_hardware()
-  returns non-zero. If yes, then the driver is expected
-  to do hardware time stamping.
+- In hard_start_xmit(), check if skb_tx(skb)->hardware is set no-zero.
+  If yes, then the driver is expected to do hardware time stamping.
 - If this is possible for the skb and requested, then declare
-  that the driver is doing the time stamping by calling
-  skb_hwtstamp_tx_in_progress(). A driver not supporting
-  hardware time stamping doesn't do that. A driver must never
-  touch sk_buff::tstamp! It is used to store how time stamping
-  for an outgoing packets is to be done.
+  that the driver is doing the time stamping by setting the field
+  skb_tx(skb)->in_progress non-zero. You might want to keep a pointer
+  to the associated skb for the next step and not free the skb. A driver
+  not supporting hardware time stamping doesn't do that. A driver must
+  never touch sk_buff::tstamp! It is used to store software generated
+  time stamps by the network subsystem.
 - As soon as the driver has sent the packet and/or obtained a
   hardware time stamp for it, it passes the time stamp back by
   calling skb_hwtstamp_tx() with the original skb, the raw
-  hardware time stamp and a handle to the device (necessary
-  to convert the hardware time stamp to system time). If obtaining
-  the hardware time stamp somehow fails, then the driver should
-  not fall back to software time stamping. The rationale is that
-  this would occur at a later time in the processing pipeline
-  than other software time stamping and therefore could lead
-  to unexpected deltas between time stamps.
-- If the driver did not call skb_hwtstamp_tx_in_progress(), then
+  hardware time stamp. skb_hwtstamp_tx() clones the original skb and
+  adds the timestamps, therefore the original skb has to be freed now.
+  If obtaining the hardware time stamp somehow fails, then the driver
+  should not fall back to software time stamping. The rationale is that
+  this would occur at a later time in the processing pipeline than other
+  software time stamping and therefore could lead to unexpected deltas
+  between time stamps.
+- If the driver did not call set skb_tx(skb)->in_progress, then
   dev_hard_start_xmit() checks whether software time stamping
   is wanted as fallback and potentially generates the time stamp.

Documentation/stable_kernel_rules.txt

@@ -18,16 +18,15 @@ Rules on what kind of patches are accepted, and which ones are not, into the
  - It cannot contain any "trivial" fixes in it (spelling changes,
    whitespace cleanups, etc).
  - It must follow the Documentation/SubmittingPatches rules.
- - It or an equivalent fix must already exist in Linus' tree.  Quote the
-   respective commit ID in Linus' tree in your patch submission to -stable.
+ - It or an equivalent fix must already exist in Linus' tree (upstream).
 
 
 Procedure for submitting patches to the -stable tree:
 
  - Send the patch, after verifying that it follows the above rules, to
-   stable@kernel.org.
- - To have the patch automatically included in the stable tree, add the
-   the tag
+   stable@kernel.org.  You must note the upstream commit ID in the changelog
+   of your submission.
+ - To have the patch automatically included in the stable tree, add the tag
      Cc: stable@kernel.org
    in the sign-off area. Once the patch is merged it will be applied to
    the stable tree without anything else needing to be done by the author

MAINTAINERS

@@ -485,8 +485,8 @@ S:	Maintained
 F:	drivers/input/mouse/bcm5974.c
 
 APPLE SMC DRIVER
-M:	Nicolas Boichat <nicolas@boichat.ch>
-L:	mactel-linux-devel@lists.sourceforge.net
+M:	Henrik Rydberg <rydberg@euromail.se>
+L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	drivers/hwmon/applesmc.c
 
@@ -1960,7 +1960,7 @@ F:	lib/kobj*
 
 DRM DRIVERS
 M:	David Airlie <airlied@linux.ie>
-L:	dri-devel@lists.sourceforge.net
+L:	dri-devel@lists.freedesktop.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6.git
 S:	Maintained
 F:	drivers/gpu/drm/
@@ -4791,12 +4791,11 @@ F:	drivers/s390/crypto/
 
 S390 ZFCP DRIVER
 M:	Christof Schmitt <christof.schmitt@de.ibm.com>
-M:	Martin Peschke <mp3@de.ibm.com>
+M:	Swen Schillig <swen@vnet.ibm.com>
 M:	linux390@de.ibm.com
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
-F:	Documentation/s390/zfcpdump.txt
 F:	drivers/s390/scsi/zfcp_*
 
 S390 IUCV NETWORK LAYER

Makefile

@@ -1,8 +1,8 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 34
-EXTRAVERSION = -rc4
-NAME = Man-Eating Seals of Antiquity
+EXTRAVERSION = -rc5
+NAME = Sheep on Meth
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"

arch/arm/configs/n8x0_defconfig

@@ -1058,7 +1058,6 @@ CONFIG_JFFS2_CMODE_PRIORITY=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

arch/arm/configs/omap_zoom2_defconfig

@@ -661,7 +661,7 @@ CONFIG_DEVKMEM=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=32
-CONFIG_SERIAL_8250_RUNTIME_UARTS=4
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y

arch/arm/configs/omap_zoom3_defconfig

@@ -680,7 +680,7 @@ CONFIG_DEVKMEM=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=32
-CONFIG_SERIAL_8250_RUNTIME_UARTS=4
+CONFIG_SERIAL_8250_RUNTIME_UARTS=1
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y

arch/arm/configs/rx51_defconfig

@@ -59,8 +59,6 @@ CONFIG_FAIR_GROUP_SCHED=y
 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=y
@@ -480,7 +478,6 @@ CONFIG_BT_HIDP=m
 # CONFIG_BT_HCIBFUSB is not set
 # CONFIG_BT_HCIVHCI is not set
 # CONFIG_AF_RXRPC is not set
-# CONFIG_PHONET is not set
 CONFIG_WIRELESS=y
 CONFIG_CFG80211=y
 # CONFIG_CFG80211_REG_DEBUG is not set

arch/arm/include/asm/highmem.h

@@ -11,7 +11,11 @@
 
 #define kmap_prot		PAGE_KERNEL
 
-#define flush_cache_kmaps()	flush_cache_all()
+#define flush_cache_kmaps() \
+	do { \
+		if (cache_is_vivt()) \
+			flush_cache_all(); \
+	} while (0)
 
 extern pte_t *pkmap_page_table;
 
@@ -21,11 +25,20 @@ extern void *kmap_high(struct page *page);
 extern void *kmap_high_get(struct page *page);
 extern void kunmap_high(struct page *page);
 
+extern void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte);
+extern void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte);
+
+/*
+ * The following functions are already defined by <linux/highmem.h>
+ * when CONFIG_HIGHMEM is not set.
+ */
+#ifdef CONFIG_HIGHMEM
 extern void *kmap(struct page *page);
 extern void kunmap(struct page *page);
 extern void *kmap_atomic(struct page *page, enum km_type type);
 extern void kunmap_atomic(void *kvaddr, enum km_type type);
 extern void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
 extern struct page *kmap_atomic_to_page(const void *ptr);
+#endif
 
 #endif

arch/arm/include/asm/kmap_types.h

@@ -18,6 +18,7 @@ enum km_type {
 	KM_IRQ1,
 	KM_SOFTIRQ0,
 	KM_SOFTIRQ1,
+	KM_L1_CACHE,
 	KM_L2_CACHE,
 	KM_TYPE_NR
 };

arch/arm/include/asm/ucontext.h

@@ -59,23 +59,22 @@ struct iwmmxt_sigframe {
 #endif /* CONFIG_IWMMXT */
 
 #ifdef CONFIG_VFP
-#if __LINUX_ARM_ARCH__ < 6
-/* For ARM pre-v6, we use fstmiax and fldmiax.  This adds one extra
- * word after the registers, and a word of padding at the end for
- * alignment.  */
 #define VFP_MAGIC		0x56465001
-#define VFP_STORAGE_SIZE	152
-#else
-#define VFP_MAGIC		0x56465002
-#define VFP_STORAGE_SIZE	144
-#endif
 
 struct vfp_sigframe
 {
 	unsigned long		magic;
 	unsigned long		size;
-	union vfp_state		storage;
-};
+	struct user_vfp		ufp;
+	struct user_vfp_exc	ufp_exc;
+} __attribute__((__aligned__(8)));
+
+/*
+ *  8 byte for magic and size, 264 byte for ufp, 12 bytes for ufp_exc,
+ *  4 bytes padding.
+ */
+#define VFP_STORAGE_SIZE	sizeof(struct vfp_sigframe)
+
 #endif /* CONFIG_VFP */
 
 /*
@@ -91,7 +90,7 @@ struct aux_sigframe {
 #ifdef CONFIG_IWMMXT
 	struct iwmmxt_sigframe	iwmmxt;
 #endif
-#if 0 && defined CONFIG_VFP /* Not yet saved.  */
+#ifdef CONFIG_VFP
 	struct vfp_sigframe	vfp;
 #endif
 	/* Something that isn't a valid magic number for any coprocessor.  */

arch/arm/include/asm/user.h

@@ -83,11 +83,21 @@ struct user{
 
 /*
  * User specific VFP registers. If only VFPv2 is present, registers 16 to 31
- * are ignored by the ptrace system call.
+ * are ignored by the ptrace system call and the signal handler.
  */
 struct user_vfp {
 	unsigned long long fpregs[32];
 	unsigned long fpscr;
 };
 
+/*
+ * VFP exception registers exposed to user space during signal delivery.
+ * Fields not relavant to the current VFP architecture are ignored.
+ */
+struct user_vfp_exc {
+	unsigned long	fpexc;
+	unsigned long	fpinst;
+	unsigned long	fpinst2;
+};
+
 #endif /* _ARM_USER_H */

arch/arm/kernel/signal.c

@@ -18,6 +18,7 @@
 #include <asm/cacheflush.h>
 #include <asm/ucontext.h>
 #include <asm/unistd.h>
+#include <asm/vfp.h>
 
 #include "ptrace.h"
 #include "signal.h"
@@ -175,6 +176,90 @@ static int restore_iwmmxt_context(struct iwmmxt_sigframe *frame)
 
 #endif
 
+#ifdef CONFIG_VFP
+
+static int preserve_vfp_context(struct vfp_sigframe __user *frame)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *h = &thread->vfpstate.hard;
+	const unsigned long magic = VFP_MAGIC;
+	const unsigned long size = VFP_STORAGE_SIZE;
+	int err = 0;
+
+	vfp_sync_hwstate(thread);
+	__put_user_error(magic, &frame->magic, err);
+	__put_user_error(size, &frame->size, err);
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_to_user(&frame->ufp.fpregs, &h->fpregs,
+			      sizeof(h->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__put_user_error(h->fpscr, &frame->ufp.fpscr, err);
+
+	/*
+	 * Copy the exception registers.
+	 */
+	__put_user_error(h->fpexc, &frame->ufp_exc.fpexc, err);
+	__put_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
+	__put_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_vfp_context(struct vfp_sigframe __user *frame)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *h = &thread->vfpstate.hard;
+	unsigned long magic;
+	unsigned long size;
+	unsigned long fpexc;
+	int err = 0;
+
+	__get_user_error(magic, &frame->magic, err);
+	__get_user_error(size, &frame->size, err);
+
+	if (err)
+		return -EFAULT;
+	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
+		return -EINVAL;
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_from_user(&h->fpregs, &frame->ufp.fpregs,
+				sizeof(h->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__get_user_error(h->fpscr, &frame->ufp.fpscr, err);
+
+	/*
+	 * Sanitise and restore the exception registers.
+	 */
+	__get_user_error(fpexc, &frame->ufp_exc.fpexc, err);
+	/* Ensure the VFP is enabled. */
+	fpexc |= FPEXC_EN;
+	/* Ensure FPINST2 is invalid and the exception flag is cleared. */
+	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
+	h->fpexc = fpexc;
+
+	__get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
+	__get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
+
+	if (!err)
+		vfp_flush_hwstate(thread);
+
+	return err ? -EFAULT : 0;
+}
+
+#endif
+
 /*
  * Do a signal return; undo the signal stack.  These are aligned to 64-bit.
  */
@@ -233,8 +318,8 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 		err |= restore_iwmmxt_context(&aux->iwmmxt);
 #endif
 #ifdef CONFIG_VFP
-//	if (err == 0)
-//		err |= vfp_restore_state(&sf->aux.vfp);
+	if (err == 0)
+		err |= restore_vfp_context(&aux->vfp);
 #endif
 
 	return err;
@@ -348,8 +433,8 @@ setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs, sigset_t *set)
 		err |= preserve_iwmmxt_context(&aux->iwmmxt);
 #endif
 #ifdef CONFIG_VFP
-//	if (err == 0)
-//		err |= vfp_save_state(&sf->aux.vfp);
+	if (err == 0)
+		err |= preserve_vfp_context(&aux->vfp);
 #endif
 	__put_user_error(0, &aux->end_magic, err);
 

arch/arm/mach-at91/Makefile

@@ -17,7 +17,7 @@ obj-$(CONFIG_ARCH_AT91SAM9G10)	+= at91sam9261.o at91sam926x_time.o at91sam9261_d
 obj-$(CONFIG_ARCH_AT91SAM9263)	+= at91sam9263.o at91sam926x_time.o at91sam9263_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91SAM9RL)	+= at91sam9rl.o at91sam926x_time.o at91sam9rl_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91SAM9G20)	+= at91sam9260.o at91sam926x_time.o at91sam9260_devices.o sam9_smc.o
- obj-$(CONFIG_ARCH_AT91SAM9G45)	+= at91sam9g45.o at91sam926x_time.o at91sam9g45_devices.o sam9_smc.o
+obj-$(CONFIG_ARCH_AT91SAM9G45)	+= at91sam9g45.o at91sam926x_time.o at91sam9g45_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91CAP9)	+= at91cap9.o at91sam926x_time.o at91cap9_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT572D940HF)  += at572d940hf.o at91sam926x_time.o at572d940hf_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91X40)	+= at91x40.o at91x40_time.o

arch/arm/mach-at91/pm_slowclock.S

@@ -175,8 +175,6 @@ ENTRY(at91_slow_clock)
 	orr	r3, r3, #(1 << 29)		/* bit 29 always set */
 	str	r3, [r1, #(AT91_CKGR_PLLAR - AT91_PMC)]
 
-	wait_pllalock
-
 	/* Save PLLB setting and disable it */
 	ldr	r3, [r1, #(AT91_CKGR_PLLBR - AT91_PMC)]
 	str	r3, .saved_pllbr
@@ -184,8 +182,6 @@ ENTRY(at91_slow_clock)
 	mov	r3, #AT91_PMC_PLLCOUNT
 	str	r3, [r1, #(AT91_CKGR_PLLBR - AT91_PMC)]
 
-	wait_pllblock
-
 	/* Turn off the main oscillator */
 	ldr	r3, [r1, #(AT91_CKGR_MOR - AT91_PMC)]
 	bic	r3, r3, #AT91_PMC_MOSCEN

arch/arm/mach-omap1/timer32k.c

@@ -68,12 +68,6 @@ struct sys_timer omap_timer;
  * ---------------------------------------------------------------------------
  */
 
-#if defined(CONFIG_ARCH_OMAP16XX)
-#define TIMER_32K_SYNCHRONIZED		0xfffbc410
-#else
-#error OMAP 32KHz timer does not currently work on 15XX!
-#endif
-
 /* 16xx specific defines */
 #define OMAP1_32K_TIMER_BASE		0xfffb9000
 #define OMAP1_32K_TIMER_CR		0x08
@@ -150,15 +144,6 @@ static struct clock_event_device clockevent_32k_timer = {
 	.set_mode	= omap_32k_timer_set_mode,
 };
 
-/*
- * The 32KHz synchronized timer is an additional timer on 16xx.
- * It is always running.
- */
-static inline unsigned long omap_32k_sync_timer_read(void)
-{
-	return omap_readl(TIMER_32K_SYNCHRONIZED);
-}
-
 static irqreturn_t omap_32k_timer_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *evt = &clockevent_32k_timer;

arch/arm/mach-omap2/Kconfig

@@ -61,6 +61,8 @@ config MACH_OMAP3_BEAGLE
 config MACH_DEVKIT8000
 	bool "DEVKIT8000 board"
 	depends on ARCH_OMAP3
+	select OMAP_PACKAGE_CUS
+	select OMAP_MUX
 
 config MACH_OMAP_LDP
 	bool "OMAP3 LDP board"

arch/arm/mach-omap2/board-3630sdp.c

@@ -96,6 +96,7 @@ static struct omap_board_mux board_mux[] __initdata = {
 static void __init omap_sdp_init(void)
 {
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBP);
+	omap_serial_init();
 	zoom_peripherals_init();
 	board_smc91x_init();
 	enable_board_wakeup_source();

arch/arm/mach-omap2/board-am3517evm.c

@@ -294,9 +294,9 @@ static struct omap_board_mux board_mux[] __initdata = {
 
 static void __init am3517_evm_init(void)
 {
-	am3517_evm_i2c_init();
-
 	omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
+
+	am3517_evm_i2c_init();
 	platform_add_devices(am3517_evm_devices,
 				ARRAY_SIZE(am3517_evm_devices));
 

arch/arm/mach-omap2/board-devkit8000.c

@@ -50,7 +50,6 @@
 #include <linux/input/matrix_keypad.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
-#include <linux/usb/otg.h>
 #include <linux/dm9000.h>
 #include <linux/interrupt.h>
 
@@ -269,20 +268,6 @@ static int devkit8000_twl_gpio_setup(struct device *dev,
 	devkit8000_vmmc1_supply.dev = mmc[0].dev;
 	devkit8000_vsim_supply.dev = mmc[0].dev;
 
-	/* REVISIT: need ehci-omap hooks for external VBUS
-	 * power switch and overcurrent detect
-	 */
-
-	gpio_request(gpio + 1, "EHCI_nOC");
-	gpio_direction_input(gpio + 1);
-
-	/* TWL4030_GPIO_MAX + 0 == ledA, EHCI nEN_USB_PWR (out, active low) */
-	gpio_request(gpio + TWL4030_GPIO_MAX, "nEN_USB_PWR");
-	gpio_direction_output(gpio + TWL4030_GPIO_MAX, 1);
-
-	/* TWL4030_GPIO_MAX + 1 == ledB, PMU_STAT (out, active low LED) */
-	gpio_leds[2].gpio = gpio + TWL4030_GPIO_MAX + 1;
-
 	return 0;
 }
 
@@ -303,7 +288,7 @@ static struct regulator_consumer_supply devkit8000_vpll2_supplies[] = {
 	.dev		= &devkit8000_lcd_device.dev,
 	},
 	{
-	.supply		= "vdss_dsi",
+	.supply		= "vdds_dsi",
 	.dev		= &devkit8000_dss_device.dev,
 	}
 };
@@ -639,17 +624,21 @@ static struct omap_musb_board_data musb_board_data = {
 static const struct ehci_hcd_omap_platform_data ehci_pdata __initconst = {
 
 	.port_mode[0] = EHCI_HCD_OMAP_MODE_PHY,
-	.port_mode[1] = EHCI_HCD_OMAP_MODE_PHY,
+	.port_mode[1] = EHCI_HCD_OMAP_MODE_UNKNOWN,
 	.port_mode[2] = EHCI_HCD_OMAP_MODE_UNKNOWN,
 
 	.phy_reset  = true,
 	.reset_gpio_port[0]  = -EINVAL,
-	.reset_gpio_port[1]  = 147,
+	.reset_gpio_port[1]  = -EINVAL,
 	.reset_gpio_port[2]  = -EINVAL
 };
 
 static void __init devkit8000_init(void)
 {
+	omap_serial_init();
+
+	omap_dm9000_init();
+
 	devkit8000_i2c_init();
 	platform_add_devices(devkit8000_devices,
 			ARRAY_SIZE(devkit8000_devices));
@@ -659,25 +648,15 @@ static void __init devkit8000_init(void)
 	spi_register_board_info(devkit8000_spi_board_info,
 	ARRAY_SIZE(devkit8000_spi_board_info));
 
-	omap_serial_init();
-
-	omap_dm9000_init();
-
 	devkit8000_ads7846_init();
 
-	omap_mux_init_gpio(170, OMAP_PIN_INPUT);
-
-	gpio_request(170, "DVI_nPD");
-	/* REVISIT leave DVI powered down until it's needed ... */
-	gpio_direction_output(170, true);
-
 	usb_musb_init(&musb_board_data);
 	usb_ehci_init(&ehci_pdata);
 	devkit8000_flash_init();
 
 	/* Ensure SDRC pins are mux'd for self-refresh */
-	omap_mux_init_signal("sdr_cke0", OMAP_PIN_OUTPUT);
-	omap_mux_init_signal("sdr_cke1", OMAP_PIN_OUTPUT);
+	omap_mux_init_signal("sdrc_cke0", OMAP_PIN_OUTPUT);
+	omap_mux_init_signal("sdrc_cke1", OMAP_PIN_OUTPUT);
 }
 
 static void __init devkit8000_map_io(void)

arch/arm/mach-omap2/board-igep0020.c

@@ -458,13 +458,13 @@ static struct omap_musb_board_data musb_board_data = {
 };
 
 static const struct ehci_hcd_omap_platform_data ehci_pdata __initconst = {
-	.port_mode[0] = EHCI_HCD_OMAP_MODE_UNKNOWN,
-	.port_mode[1] = EHCI_HCD_OMAP_MODE_PHY,
+	.port_mode[0] = EHCI_HCD_OMAP_MODE_PHY,
+	.port_mode[1] = EHCI_HCD_OMAP_MODE_UNKNOWN,
 	.port_mode[2] = EHCI_HCD_OMAP_MODE_UNKNOWN,
 
 	.phy_reset = true,
-	.reset_gpio_port[0] = -EINVAL,
-	.reset_gpio_port[1] = IGEP2_GPIO_USBH_NRESET,
+	.reset_gpio_port[0] = IGEP2_GPIO_USBH_NRESET,
+	.reset_gpio_port[1] = -EINVAL,
 	.reset_gpio_port[2] = -EINVAL,
 };
 

arch/arm/mach-omap2/board-n8x0.c

@@ -216,7 +216,7 @@ static void __init n8x0_onenand_init(void) {}
  */
 #define N8X0_SLOT_SWITCH_GPIO	96
 #define N810_EMMC_VSD_GPIO	23
-#define NN810_EMMC_VIO_GPIO	9
+#define N810_EMMC_VIO_GPIO	9
 
 static int n8x0_mmc_switch_slot(struct device *dev, int slot)
 {
@@ -304,10 +304,10 @@ static void n810_set_power_emmc(struct device *dev,
 	if (power_on) {
 		gpio_set_value(N810_EMMC_VSD_GPIO, 1);
 		msleep(1);
-		gpio_set_value(NN810_EMMC_VIO_GPIO, 1);
+		gpio_set_value(N810_EMMC_VIO_GPIO, 1);
 		msleep(1);
 	} else {
-		gpio_set_value(NN810_EMMC_VIO_GPIO, 0);
+		gpio_set_value(N810_EMMC_VIO_GPIO, 0);
 		msleep(50);
 		gpio_set_value(N810_EMMC_VSD_GPIO, 0);
 		msleep(50);
@@ -468,7 +468,7 @@ static void n8x0_mmc_cleanup(struct device *dev)
 
 	if (machine_is_nokia_n810()) {
 		gpio_free(N810_EMMC_VSD_GPIO);
-		gpio_free(NN810_EMMC_VIO_GPIO);
+		gpio_free(N810_EMMC_VIO_GPIO);
 	}
 }
 
@@ -529,7 +529,7 @@ void __init n8x0_mmc_init(void)
 
 	err = gpio_request(N8X0_SLOT_SWITCH_GPIO, "MMC slot switch");
 	if (err)
-		return err;
+		return;
 
 	gpio_direction_output(N8X0_SLOT_SWITCH_GPIO, 0);
 
@@ -537,17 +537,17 @@ void __init n8x0_mmc_init(void)
 		err = gpio_request(N810_EMMC_VSD_GPIO, "MMC slot 2 Vddf");
 		if (err) {
 			gpio_free(N8X0_SLOT_SWITCH_GPIO);
-			return err;
+			return;
 		}
 		gpio_direction_output(N810_EMMC_VSD_GPIO, 0);
 
-		err = gpio_request(NN810_EMMC_VIO_GPIO, "MMC slot 2 Vdd");
+		err = gpio_request(N810_EMMC_VIO_GPIO, "MMC slot 2 Vdd");
 		if (err) {
 			gpio_free(N8X0_SLOT_SWITCH_GPIO);
 			gpio_free(N810_EMMC_VSD_GPIO);
-			return err;
+			return;
 		}
-		gpio_direction_output(NN810_EMMC_VIO_GPIO, 0);
+		gpio_direction_output(N810_EMMC_VIO_GPIO, 0);
 	}
 
 	mmc_data[0] = &mmc1_data;

arch/arm/mach-omap2/board-sdp-flash.c

@@ -253,20 +253,20 @@ void __init sdp_flash_init(struct flash_partitions sdp_partition_info[])
 	}
 
 	if (norcs > GPMC_CS_NUM)
-		printk(KERN_INFO "OneNAND: Unable to find configuration "
-				" in GPMC\n ");
+		printk(KERN_INFO "NOR: Unable to find configuration "
+				"in GPMC\n");
 	else
 		board_nor_init(sdp_partition_info[0], norcs);
 
 	if (onenandcs > GPMC_CS_NUM)
 		printk(KERN_INFO "OneNAND: Unable to find configuration "
-				" in GPMC\n ");
+				"in GPMC\n");
 	else
 		board_onenand_init(sdp_partition_info[1], onenandcs);
 
 	if (nandcs > GPMC_CS_NUM)
 		printk(KERN_INFO "NAND: Unable to find configuration "
-				" in GPMC\n ");
+				"in GPMC\n");
 	else
 		board_nand_init(sdp_partition_info[2], nandcs);
 }

arch/arm/mach-omap2/board-zoom-debugboard.c

@@ -96,7 +96,7 @@ static struct plat_serial8250_port serial_platform_data[] = {
 
 static struct platform_device zoom_debugboard_serial_device = {
 	.name			= "serial8250",
-	.id			= 3,
+	.id			= PLAT8250_DEV_PLATFORM,
 	.dev			= {
 		.platform_data	= serial_platform_data,
 	},

arch/arm/mach-omap2/board-zoom-peripherals.c

@@ -280,7 +280,6 @@ static void enable_board_wakeup_source(void)
 void __init zoom_peripherals_init(void)
 {
 	omap_i2c_init();
-	omap_serial_init();
 	usb_musb_init(&musb_board_data);
 	enable_board_wakeup_source();
 }

arch/arm/mach-omap2/clock3xxx_data.c

@@ -895,7 +895,7 @@ static struct clk dpll4_m4x2_ck = {
 	.ops		= &clkops_omap2_dflt_wait,
 	.parent		= &dpll4_m4_ck,
 	.enable_reg	= OMAP_CM_REGADDR(PLL_MOD, CM_CLKEN),
-	.enable_bit	= OMAP3430_PWRDN_CAM_SHIFT,
+	.enable_bit	= OMAP3430_PWRDN_DSS1_SHIFT,
 	.flags		= INVERT_ENABLE,
 	.clkdm_name	= "dpll4_clkdm",
 	.recalc		= &omap3_clkoutx2_recalc,

arch/arm/mach-omap2/clock44xx_data.c

@@ -2671,10 +2671,10 @@ static struct omap_clk omap44xx_clks[] = {
 	CLK("omap-mcbsp.2",	"ick",				&dummy_ck,	CK_443X),
 	CLK("omap-mcbsp.3",	"ick",				&dummy_ck,	CK_443X),
 	CLK("omap-mcbsp.4",	"ick",				&dummy_ck,	CK_443X),
-	CLK("omap-mcspi.1",	"ick",				&dummy_ck,	CK_443X),
-	CLK("omap-mcspi.2",	"ick",				&dummy_ck,	CK_443X),
-	CLK("omap-mcspi.3",	"ick",				&dummy_ck,	CK_443X),
-	CLK("omap-mcspi.4",	"ick",				&dummy_ck,	CK_443X),
+	CLK("omap2_mcspi.1",	"ick",			&dummy_ck,	CK_443X),
+	CLK("omap2_mcspi.2",	"ick",			&dummy_ck,	CK_443X),
+	CLK("omap2_mcspi.3",	"ick",			&dummy_ck,	CK_443X),
+	CLK("omap2_mcspi.4",	"ick",			&dummy_ck,	CK_443X),
 	CLK(NULL,	"uart1_ick",			&dummy_ck,	CK_443X),
 	CLK(NULL,	"uart2_ick",			&dummy_ck,	CK_443X),
 	CLK(NULL,	"uart3_ick",			&dummy_ck,	CK_443X),

arch/arm/mach-omap2/clockdomain.c

@@ -240,7 +240,7 @@ static void _omap2_clkdm_set_hwsup(struct clockdomain *clkdm, int enable)
 			bits = OMAP24XX_CLKSTCTRL_ENABLE_AUTO;
 		else
 			bits = OMAP24XX_CLKSTCTRL_DISABLE_AUTO;
-	} else if (cpu_is_omap34xx() | cpu_is_omap44xx()) {
+	} else if (cpu_is_omap34xx() || cpu_is_omap44xx()) {
 		if (enable)
 			bits = OMAP34XX_CLKSTCTRL_ENABLE_AUTO;
 		else
@@ -812,7 +812,7 @@ int omap2_clkdm_sleep(struct clockdomain *clkdm)
 		cm_set_mod_reg_bits(OMAP24XX_FORCESTATE,
 			    clkdm->pwrdm.ptr->prcm_offs, OMAP2_PM_PWSTCTRL);
 
-	} else if (cpu_is_omap34xx() | cpu_is_omap44xx()) {
+	} else if (cpu_is_omap34xx() || cpu_is_omap44xx()) {
 
 		u32 bits = (OMAP34XX_CLKSTCTRL_FORCE_SLEEP <<
 			 __ffs(clkdm->clktrctrl_mask));
@@ -856,7 +856,7 @@ int omap2_clkdm_wakeup(struct clockdomain *clkdm)
 		cm_clear_mod_reg_bits(OMAP24XX_FORCESTATE,
 			      clkdm->pwrdm.ptr->prcm_offs, OMAP2_PM_PWSTCTRL);
 
-	} else if (cpu_is_omap34xx() | cpu_is_omap44xx()) {
+	} else if (cpu_is_omap34xx() || cpu_is_omap44xx()) {
 
 		u32 bits = (OMAP34XX_CLKSTCTRL_FORCE_WAKEUP <<
 			 __ffs(clkdm->clktrctrl_mask));

arch/arm/mach-omap2/devices.c

@@ -726,7 +726,7 @@ void __init omap2_init_mmc(struct omap_mmc_platform_data **mmc_data,
 			if (!cpu_is_omap44xx())
 				return;
 			base = OMAP4_MMC5_BASE + OMAP4_MMC_REG_OFFSET;
-			irq = OMAP44XX_IRQ_MMC4;
+			irq = OMAP44XX_IRQ_MMC5;
 			break;
 		default:
 			continue;

arch/arm/mach-omap2/gpmc-nand.c

@@ -39,6 +39,9 @@ static int omap2_nand_gpmc_retime(void)
 	struct gpmc_timings t;
 	int err;
 
+	if (!gpmc_nand_data->gpmc_t)
+		return 0;
+
 	memset(&t, 0, sizeof(t));
 	t.sync_clk = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->sync_clk);
 	t.cs_on = gpmc_round_ns_to_ticks(gpmc_nand_data->gpmc_t->cs_on);

arch/arm/mach-omap2/include/mach/entry-macro.S

@@ -52,7 +52,7 @@ omap_irq_base:	.word	0
 
 		mrc	p15, 0, \tmp, c0, c0, 0	@ get processor revision
 		and	\tmp, \tmp, #0x000f0000	@ only check architecture
-		cmp	\tmp, #0x00060000	@ is v6?
+		cmp	\tmp, #0x00070000	@ is v6?
 		beq	2400f			@ found v6 so it's omap24xx
 		mrc	p15, 0, \tmp, c0, c0, 0	@ get processor revision
 		and	\tmp, \tmp, #0x000000f0	@ check cortex 8 or 9

arch/arm/mach-omap2/omap-headsmp.S

@@ -33,7 +33,7 @@
 ENTRY(omap_secondary_startup)
 hold:	ldr	r12,=0x103
 	dsb
-	smc				@ read from AuxCoreBoot0
+	smc	#0			@ read from AuxCoreBoot0
 	mov	r0, r0, lsr #9
 	mrc	p15, 0, r4, c0, c0, 5
 	and	r4, r4, #0x0f
@@ -52,7 +52,7 @@ ENTRY(omap_modify_auxcoreboot0)
 	stmfd   sp!, {r1-r12, lr}
 	ldr	r12, =0x104
 	dsb
-	smc
+	smc	#0
 	ldmfd   sp!, {r1-r12, pc}
 END(omap_modify_auxcoreboot0)
 
@@ -60,6 +60,6 @@ ENTRY(omap_auxcoreboot_addr)
 	stmfd   sp!, {r2-r12, lr}
 	ldr	r12, =0x105
 	dsb
-	smc
+	smc	#0
 	ldmfd   sp!, {r2-r12, pc}
 END(omap_auxcoreboot_addr)

arch/arm/mach-omap2/omap44xx-smc.S

@@ -27,6 +27,6 @@ ENTRY(omap_smc1)
 	mov	r12, r0
 	mov 	r0, r1
 	dsb
-	smc
+	smc	#0
 	ldmfd   sp!, {r2-r12, pc}
 END(omap_smc1)

arch/arm/mach-omap2/omap_hwmod.c

@@ -1511,6 +1511,9 @@ struct powerdomain *omap_hwmod_get_pwrdm(struct omap_hwmod *oh)
 		c = oh->slaves[oh->_mpu_port_index]->_clk;
 	}
 
+	if (!c->clkdm)
+		return NULL;
+
 	return c->clkdm->pwrdm.ptr;
 
 }

arch/arm/mach-omap2/powerdomain.c

@@ -222,7 +222,7 @@ void pwrdm_init(struct powerdomain **pwrdm_list)
 {
 	struct powerdomain **p = NULL;
 
-	if (cpu_is_omap24xx() | cpu_is_omap34xx()) {
+	if (cpu_is_omap24xx() || cpu_is_omap34xx()) {
 		pwrstctrl_reg_offs = OMAP2_PM_PWSTCTRL;
 		pwrstst_reg_offs = OMAP2_PM_PWSTST;
 	} else if (cpu_is_omap44xx()) {

arch/arm/mach-omap2/prcm.c

@@ -123,7 +123,7 @@ struct omap3_prcm_regs prcm_context;
 u32 omap_prcm_get_reset_sources(void)
 {
 	/* XXX This presumably needs modification for 34XX */
-	if (cpu_is_omap24xx() | cpu_is_omap34xx())
+	if (cpu_is_omap24xx() || cpu_is_omap34xx())
 		return prm_read_mod_reg(WKUP_MOD, OMAP2_RM_RSTST) & 0x7f;
 	if (cpu_is_omap44xx())
 		return prm_read_mod_reg(WKUP_MOD, OMAP4_RM_RSTST) & 0x7f;
@@ -157,7 +157,7 @@ void omap_prcm_arch_reset(char mode, const char *cmd)
 	else
 		WARN_ON(1);
 
-	if (cpu_is_omap24xx() | cpu_is_omap34xx())
+	if (cpu_is_omap24xx() || cpu_is_omap34xx())
 		prm_set_mod_reg_bits(OMAP_RST_DPLL3, prcm_offs,
 						 OMAP2_RM_RSTCTRL);
 	if (cpu_is_omap44xx())

arch/arm/mach-omap2/serial.c

@@ -115,7 +115,6 @@ static struct plat_serial8250_port serial_platform_data2[] = {
 	}
 };
 
-#if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_ARCH_OMAP4)
 static struct plat_serial8250_port serial_platform_data3[] = {
 	{
 		.irq		= 70,
@@ -128,23 +127,12 @@ static struct plat_serial8250_port serial_platform_data3[] = {
 	}
 };
 
-static inline void omap2_set_globals_uart4(struct omap_globals *omap2_globals)
-{
-	serial_platform_data3[0].mapbase = omap2_globals->uart4_phys;
-}
-#else
-static inline void omap2_set_globals_uart4(struct omap_globals *omap2_globals)
-{
-}
-#endif
-
 void __init omap2_set_globals_uart(struct omap_globals *omap2_globals)
 {
 	serial_platform_data0[0].mapbase = omap2_globals->uart1_phys;
 	serial_platform_data1[0].mapbase = omap2_globals->uart2_phys;
 	serial_platform_data2[0].mapbase = omap2_globals->uart3_phys;
-	if (cpu_is_omap3630() || cpu_is_omap44xx())
-		omap2_set_globals_uart4(omap2_globals);
+	serial_platform_data3[0].mapbase = omap2_globals->uart4_phys;
 }
 
 static inline unsigned int __serial_read_reg(struct uart_port *up,
@@ -550,7 +538,7 @@ static ssize_t sleep_timeout_store(struct device *dev,
 	unsigned int value;
 
 	if (sscanf(buf, "%u", &value) != 1) {
-		printk(KERN_ERR "sleep_timeout_store: Invalid value\n");
+		dev_err(dev, "sleep_timeout_store: Invalid value\n");
 		return -EINVAL;
 	}
 
@@ -664,27 +652,33 @@ void __init omap_serial_early_init(void)
 		struct device *dev = &pdev->dev;
 		struct plat_serial8250_port *p = dev->platform_data;
 
+		/* Don't map zero-based physical address */
+		if (p->mapbase == 0) {
+			dev_warn(dev, "no physical address for uart#%d,"
+				 " so skipping early_init...\n", i);
+			continue;
+		}
 		/*
 		 * Module 4KB + L4 interconnect 4KB
 		 * Static mapping, never released
 		 */
 		p->membase = ioremap(p->mapbase, SZ_8K);
 		if (!p->membase) {
-			printk(KERN_ERR "ioremap failed for uart%i\n", i + 1);
+			dev_err(dev, "ioremap failed for uart%i\n", i + 1);
 			continue;
 		}
 
 		sprintf(name, "uart%d_ick", i + 1);
 		uart->ick = clk_get(NULL, name);
 		if (IS_ERR(uart->ick)) {
-			printk(KERN_ERR "Could not get uart%d_ick\n", i + 1);
+			dev_err(dev, "Could not get uart%d_ick\n", i + 1);
 			uart->ick = NULL;
 		}
 
 		sprintf(name, "uart%d_fck", i+1);
 		uart->fck = clk_get(NULL, name);
 		if (IS_ERR(uart->fck)) {
-			printk(KERN_ERR "Could not get uart%d_fck\n", i + 1);
+			dev_err(dev, "Could not get uart%d_fck\n", i + 1);
 			uart->fck = NULL;
 		}
 
@@ -727,6 +721,13 @@ void __init omap_serial_init_port(int port)
 	pdev = &uart->pdev;
 	dev = &pdev->dev;
 
+	/* Don't proceed if there's no clocks available */
+	if (unlikely(!uart->ick || !uart->fck)) {
+		WARN(1, "%s: can't init uart%d, no clocks available\n",
+		     kobject_name(&dev->kobj), port);
+		return;
+	}
+
 	omap_uart_enable_clocks(uart);
 
 	omap_uart_reset(uart);

arch/arm/mm/copypage-v6.c

@@ -41,13 +41,6 @@ static void v6_copy_user_highpage_nonaliasing(struct page *to,
 	kfrom = kmap_atomic(from, KM_USER0);
 	kto = kmap_atomic(to, KM_USER1);
 	copy_page(kto, kfrom);
-#ifdef CONFIG_HIGHMEM
-	/*
-	 * kmap_atomic() doesn't set the page virtual address, and
-	 * kunmap_atomic() takes care of cache flushing already.
-	 */
-	if (page_address(to) != NULL)
-#endif
 	__cpuc_flush_dcache_area(kto, PAGE_SIZE);
 	kunmap_atomic(kto, KM_USER1);
 	kunmap_atomic(kfrom, KM_USER0);

arch/arm/mm/dma-mapping.c

@@ -464,6 +464,11 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 				vaddr += offset;
 				op(vaddr, len, dir);
 				kunmap_high(page);
+			} else if (cache_is_vipt()) {
+				pte_t saved_pte;
+				vaddr = kmap_high_l1_vipt(page, &saved_pte);
+				op(vaddr + offset, len, dir);
+				kunmap_high_l1_vipt(page, saved_pte);
 			}
 		} else {
 			vaddr = page_address(page) + offset;

arch/arm/mm/flush.c

@@ -13,6 +13,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
+#include <asm/highmem.h>
 #include <asm/smp_plat.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
@@ -152,21 +153,25 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 
 void __flush_dcache_page(struct address_space *mapping, struct page *page)
 {
-	void *addr = page_address(page);
-
 	/*
 	 * Writeback any data associated with the kernel mapping of this
 	 * page.  This ensures that data in the physical page is mutually
 	 * coherent with the kernels mapping.
 	 */
-#ifdef CONFIG_HIGHMEM
-	/*
-	 * kmap_atomic() doesn't set the page virtual address, and
-	 * kunmap_atomic() takes care of cache flushing already.
-	 */
-	if (addr)
-#endif
+	if (!PageHighMem(page)) {
+		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+	} else {
+		void *addr = kmap_high_get(page);
+		if (addr) {
 			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+			kunmap_high(page);
+		} else if (cache_is_vipt()) {
+			pte_t saved_pte;
+			addr = kmap_high_l1_vipt(page, &saved_pte);
+			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+			kunmap_high_l1_vipt(page, saved_pte);
+		}
+	}
 
 	/*
 	 * If this is a page cache page, and we have an aliasing VIPT cache,

arch/arm/mm/highmem.c

@@ -79,6 +79,7 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 	unsigned int idx = type + KM_TYPE_NR * smp_processor_id();
 
 	if (kvaddr >= (void *)FIXADDR_START) {
+		if (cache_is_vivt())
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
 #ifdef CONFIG_DEBUG_HIGHMEM
 		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
@@ -124,3 +125,87 @@ struct page *kmap_atomic_to_page(const void *ptr)
 	pte = TOP_PTE(vaddr);
 	return pte_page(*pte);
 }
+
+#ifdef CONFIG_CPU_CACHE_VIPT
+
+#include <linux/percpu.h>
+
+/*
+ * The VIVT cache of a highmem page is always flushed before the page
+ * is unmapped. Hence unmapped highmem pages need no cache maintenance
+ * in that case.
+ *
+ * However unmapped pages may still be cached with a VIPT cache, and
+ * it is not possible to perform cache maintenance on them using physical
+ * addresses unfortunately.  So we have no choice but to set up a temporary
+ * virtual mapping for that purpose.
+ *
+ * Yet this VIPT cache maintenance may be triggered from DMA support
+ * functions which are possibly called from interrupt context. As we don't
+ * want to keep interrupt disabled all the time when such maintenance is
+ * taking place, we therefore allow for some reentrancy by preserving and
+ * restoring the previous fixmap entry before the interrupted context is
+ * resumed.  If the reentrancy depth is 0 then there is no need to restore
+ * the previous fixmap, and leaving the current one in place allow it to
+ * be reused the next time without a TLB flush (common with DMA).
+ */
+
+static DEFINE_PER_CPU(int, kmap_high_l1_vipt_depth);
+
+void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte)
+{
+	unsigned int idx, cpu = smp_processor_id();
+	int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
+	unsigned long vaddr, flags;
+	pte_t pte, *ptep;
+
+	idx = KM_L1_CACHE + KM_TYPE_NR * cpu;
+	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+	ptep = TOP_PTE(vaddr);
+	pte = mk_pte(page, kmap_prot);
+
+	if (!in_interrupt())
+		preempt_disable();
+
+	raw_local_irq_save(flags);
+	(*depth)++;
+	if (pte_val(*ptep) == pte_val(pte)) {
+		*saved_pte = pte;
+	} else {
+		*saved_pte = *ptep;
+		set_pte_ext(ptep, pte, 0);
+		local_flush_tlb_kernel_page(vaddr);
+	}
+	raw_local_irq_restore(flags);
+
+	return (void *)vaddr;
+}
+
+void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte)
+{
+	unsigned int idx, cpu = smp_processor_id();
+	int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
+	unsigned long vaddr, flags;
+	pte_t pte, *ptep;
+
+	idx = KM_L1_CACHE + KM_TYPE_NR * cpu;
+	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+	ptep = TOP_PTE(vaddr);
+	pte = mk_pte(page, kmap_prot);
+
+	BUG_ON(pte_val(*ptep) != pte_val(pte));
+	BUG_ON(*depth <= 0);
+
+	raw_local_irq_save(flags);
+	(*depth)--;
+	if (*depth != 0 && pte_val(pte) != pte_val(saved_pte)) {
+		set_pte_ext(ptep, saved_pte, 0);
+		local_flush_tlb_kernel_page(vaddr);
+	}
+	raw_local_irq_restore(flags);
+
+	if (!in_interrupt())
+		preempt_enable();
+}
+
+#endif  /* CONFIG_CPU_CACHE_VIPT */

arch/arm/mm/mmu.c

@@ -1054,10 +1054,12 @@ void setup_mm_for_reboot(char mode)
 	pgd_t *pgd;
 	int i;
 
-	if (current->mm && current->mm->pgd)
-		pgd = current->mm->pgd;
-	else
-		pgd = init_mm.pgd;
+	/*
+	 * We need to access to user-mode page tables here. For kernel threads
+	 * we don't have any user-mode mappings so we use the context that we
+	 * "borrowed".
+	 */
+	pgd = current->active_mm->pgd;
 
 	base_pmdval = PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | PMD_TYPE_SECT;
 	if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale())

arch/arm/plat-omap/common.c

@@ -44,9 +44,6 @@
 
 #define NO_LENGTH_CHECK 0xffffffff
 
-unsigned char omap_bootloader_tag[512];
-int omap_bootloader_tag_len;
-
 struct omap_board_config_kernel *omap_board_config;
 int omap_board_config_size;
 
@@ -100,10 +97,17 @@ EXPORT_SYMBOL(omap_get_var_config);
 
 #include <linux/clocksource.h>
 
+/*
+ * offset_32k holds the init time counter value. It is then subtracted
+ * from every counter read to achieve a counter that counts time from the
+ * kernel boot (needed for sched_clock()).
+ */
+static u32 offset_32k __read_mostly;
+
 #ifdef CONFIG_ARCH_OMAP16XX
 static cycle_t omap16xx_32k_read(struct clocksource *cs)
 {
-	return omap_readl(OMAP16XX_TIMER_32K_SYNCHRONIZED);
+	return omap_readl(OMAP16XX_TIMER_32K_SYNCHRONIZED) - offset_32k;
 }
 #else
 #define omap16xx_32k_read	NULL
@@ -112,7 +116,7 @@ static cycle_t omap16xx_32k_read(struct clocksource *cs)
 #ifdef CONFIG_ARCH_OMAP2420
 static cycle_t omap2420_32k_read(struct clocksource *cs)
 {
-	return omap_readl(OMAP2420_32KSYNCT_BASE + 0x10);
+	return omap_readl(OMAP2420_32KSYNCT_BASE + 0x10) - offset_32k;
 }
 #else
 #define omap2420_32k_read	NULL
@@ -121,7 +125,7 @@ static cycle_t omap2420_32k_read(struct clocksource *cs)
 #ifdef CONFIG_ARCH_OMAP2430
 static cycle_t omap2430_32k_read(struct clocksource *cs)
 {
-	return omap_readl(OMAP2430_32KSYNCT_BASE + 0x10);
+	return omap_readl(OMAP2430_32KSYNCT_BASE + 0x10) - offset_32k;
 }
 #else
 #define omap2430_32k_read	NULL
@@ -130,7 +134,7 @@ static cycle_t omap2430_32k_read(struct clocksource *cs)
 #ifdef CONFIG_ARCH_OMAP3
 static cycle_t omap34xx_32k_read(struct clocksource *cs)
 {
-	return omap_readl(OMAP3430_32KSYNCT_BASE + 0x10);
+	return omap_readl(OMAP3430_32KSYNCT_BASE + 0x10) - offset_32k;
 }
 #else
 #define omap34xx_32k_read	NULL
@@ -139,7 +143,7 @@ static cycle_t omap34xx_32k_read(struct clocksource *cs)
 #ifdef CONFIG_ARCH_OMAP4
 static cycle_t omap44xx_32k_read(struct clocksource *cs)
 {
-	return omap_readl(OMAP4430_32KSYNCT_BASE + 0x10);
+	return omap_readl(OMAP4430_32KSYNCT_BASE + 0x10) - offset_32k;
 }
 #else
 #define omap44xx_32k_read	NULL
@@ -227,6 +231,8 @@ static int __init omap_init_clocksource_32k(void)
 		clocksource_32k.mult = clocksource_hz2mult(32768,
 					    clocksource_32k.shift);
 
+		offset_32k = clocksource_32k.read(&clocksource_32k);
+
 		if (clocksource_register(&clocksource_32k))
 			printk(err, clocksource_32k.name);
 	}

arch/arm/plat-omap/dma.c

@@ -937,6 +937,15 @@ void omap_start_dma(int lch)
 {
 	u32 l;
 
+	/*
+	 * The CPC/CDAC register needs to be initialized to zero
+	 * before starting dma transfer.
+	 */
+	if (cpu_is_omap15xx())
+		dma_write(0, CPC(lch));
+	else
+		dma_write(0, CDAC(lch));
+
 	if (!omap_dma_in_1510_mode() && dma_chan[lch].next_lch != -1) {
 		int next_lch, cur_lch;
 		char dma_chan_link_map[OMAP_DMA4_LOGICAL_DMA_CH_COUNT];

arch/arm/plat-omap/gpio.c

@@ -798,7 +798,7 @@ static int _set_gpio_triggering(struct gpio_bank *bank, int gpio, int trigger)
 	case METHOD_MPUIO:
 		reg += OMAP_MPUIO_GPIO_INT_EDGE;
 		l = __raw_readl(reg);
-		if (trigger & IRQ_TYPE_EDGE_BOTH)
+		if ((trigger & IRQ_TYPE_SENSE_MASK) == IRQ_TYPE_EDGE_BOTH)
 			bank->toggle_mask |= 1 << gpio;
 		if (trigger & IRQ_TYPE_EDGE_RISING)
 			l |= 1 << gpio;
@@ -812,7 +812,7 @@ static int _set_gpio_triggering(struct gpio_bank *bank, int gpio, int trigger)
 	case METHOD_GPIO_1510:
 		reg += OMAP1510_GPIO_INT_CONTROL;
 		l = __raw_readl(reg);
-		if (trigger & IRQ_TYPE_EDGE_BOTH)
+		if ((trigger & IRQ_TYPE_SENSE_MASK) == IRQ_TYPE_EDGE_BOTH)
 			bank->toggle_mask |= 1 << gpio;
 		if (trigger & IRQ_TYPE_EDGE_RISING)
 			l |= 1 << gpio;
@@ -846,7 +846,7 @@ static int _set_gpio_triggering(struct gpio_bank *bank, int gpio, int trigger)
 	case METHOD_GPIO_7XX:
 		reg += OMAP7XX_GPIO_INT_CONTROL;
 		l = __raw_readl(reg);
-		if (trigger & IRQ_TYPE_EDGE_BOTH)
+		if ((trigger & IRQ_TYPE_SENSE_MASK) == IRQ_TYPE_EDGE_BOTH)
 			bank->toggle_mask |= 1 << gpio;
 		if (trigger & IRQ_TYPE_EDGE_RISING)
 			l |= 1 << gpio;

arch/arm/plat-omap/include/plat/irqs.h

@@ -345,8 +345,6 @@
 #define INT_34XX_MMC3_IRQ	94
 #define INT_34XX_GPT12_IRQ	95
 
-#define	INT_34XX_BENCH_MPU_EMUL	3
-
 #define INT_35XX_HECC0_IRQ		24
 #define INT_35XX_HECC1_IRQ		28
 #define INT_35XX_EMAC_C0_RXTHRESH_IRQ	67

arch/arm/plat-omap/include/plat/mcbsp.h

@@ -59,7 +59,7 @@
 #define OMAP44XX_MCBSP1_BASE	0x49022000
 #define OMAP44XX_MCBSP2_BASE	0x49024000
 #define OMAP44XX_MCBSP3_BASE	0x49026000
-#define OMAP44XX_MCBSP4_BASE	0x48074000
+#define OMAP44XX_MCBSP4_BASE	0x48096000
 
 #if defined(CONFIG_ARCH_OMAP15XX) || defined(CONFIG_ARCH_OMAP16XX) || defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850)
 

arch/arm/plat-omap/include/plat/nand.h

@@ -29,4 +29,11 @@ struct omap_nand_platform_data {
 /* size (4 KiB) for IO mapping */
 #define	NAND_IO_SIZE	SZ_4K
 
+#if defined(CONFIG_MTD_NAND_OMAP2) || defined(CONFIG_MTD_NAND_OMAP2_MODULE)
 extern int gpmc_nand_init(struct omap_nand_platform_data *d);
+#else
+static inline int gpmc_nand_init(struct omap_nand_platform_data *d)
+{
+	return 0;
+}
+#endif

arch/arm/plat-omap/include/plat/omap44xx.h

@@ -32,7 +32,7 @@
 #define OMAP4430_PRM_BASE		0x4a306000
 #define OMAP44XX_GPMC_BASE		0x50000000
 #define OMAP443X_SCM_BASE		0x4a002000
-#define OMAP443X_CTRL_BASE		OMAP443X_SCM_BASE
+#define OMAP443X_CTRL_BASE		0x4a100000
 #define OMAP44XX_IC_BASE		0x48200000
 #define OMAP44XX_IVA_INTC_BASE		0x40000000
 #define IRQ_SIR_IRQ			0x0040

arch/arm/plat-omap/include/plat/omap_hwmod.h

@@ -294,8 +294,8 @@ struct omap_hwmod_class_sysconfig {
 	u16 rev_offs;
 	u16 sysc_offs;
 	u16 syss_offs;
+	u16 sysc_flags;
 	u8 idlemodes;
-	u8 sysc_flags;
 	u8 clockact;
 	struct omap_hwmod_sysc_fields *sysc_fields;
 };

arch/arm/vfp/vfpmodule.c

@@ -428,26 +428,6 @@ static void vfp_pm_init(void)
 static inline void vfp_pm_init(void) { }
 #endif /* CONFIG_PM */
 
-/*
- * Synchronise the hardware VFP state of a thread other than current with the
- * saved one. This function is used by the ptrace mechanism.
- */
-#ifdef CONFIG_SMP
-void vfp_sync_hwstate(struct thread_info *thread)
-{
-}
-
-void vfp_flush_hwstate(struct thread_info *thread)
-{
-	/*
-	 * On SMP systems, the VFP state is automatically saved at every
-	 * context switch. We mark the thread VFP state as belonging to a
-	 * non-existent CPU so that the saved one will be reloaded when
-	 * needed.
-	 */
-	thread->vfpstate.hard.cpu = NR_CPUS;
-}
-#else
 void vfp_sync_hwstate(struct thread_info *thread)
 {
 	unsigned int cpu = get_cpu();
@@ -490,9 +470,18 @@ void vfp_flush_hwstate(struct thread_info *thread)
 		last_VFP_context[cpu] = NULL;
 	}
 
+#ifdef CONFIG_SMP
+	/*
+	 * For SMP we still have to take care of the case where the thread
+	 * migrates to another CPU and then back to the original CPU on which
+	 * the last VFP user is still the same thread. Mark the thread VFP
+	 * state as belonging to a non-existent CPU so that the saved one will
+	 * be reloaded in the above case.
+	 */
+	thread->vfpstate.hard.cpu = NR_CPUS;
+#endif
 	put_cpu();
 }
-#endif
 
 #include <linux/smp.h>
 

arch/avr32/kernel/ptrace.c

@@ -28,7 +28,7 @@ static struct pt_regs *get_user_regs(struct task_struct *tsk)
 				  THREAD_SIZE - sizeof(struct pt_regs));
 }
 
-static void user_enable_single_step(struct task_struct *tsk)
+void user_enable_single_step(struct task_struct *tsk)
 {
 	pr_debug("user_enable_single_step: pid=%u, PC=0x%08lx, SR=0x%08lx\n",
 		 tsk->pid, task_pt_regs(tsk)->pc, task_pt_regs(tsk)->sr);

arch/ia64/kvm/kvm-ia64.c

@@ -1802,7 +1802,8 @@ static int kvm_ia64_sync_dirty_log(struct kvm *kvm,
 {
 	struct kvm_memory_slot *memslot;
 	int r, i;
-	long n, base;
+	long base;
+	unsigned long n;
 	unsigned long *dirty_bitmap = (unsigned long *)(kvm->arch.vm_base +
 			offsetof(struct kvm_vm_data, kvm_mem_dirty_log));
 
@@ -1815,7 +1816,7 @@ static int kvm_ia64_sync_dirty_log(struct kvm *kvm,
 	if (!memslot->dirty_bitmap)
 		goto out;
 
-	n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+	n = kvm_dirty_bitmap_bytes(memslot);
 	base = memslot->base_gfn / BITS_PER_LONG;
 
 	for (i = 0; i < n/sizeof(long); ++i) {
@@ -1831,7 +1832,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 		struct kvm_dirty_log *log)
 {
 	int r;
-	int n;
+	unsigned long n;
 	struct kvm_memory_slot *memslot;
 	int is_dirty = 0;
 
@@ -1850,7 +1851,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	if (is_dirty) {
 		kvm_flush_remote_tlbs(kvm);
 		memslot = &kvm->memslots->memslots[log->slot];
-		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+		n = kvm_dirty_bitmap_bytes(memslot);
 		memset(memslot->dirty_bitmap, 0, n);
 	}
 	r = 0;

arch/m68k/include/asm/atomic_mm.h

@@ -148,14 +148,18 @@ static inline int atomic_xchg(atomic_t *v, int new)
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
 	char c;
-	__asm__ __volatile__("subl %2,%1; seq %0" : "=d" (c), "+m" (*v): "g" (i));
+	__asm__ __volatile__("subl %2,%1; seq %0"
+			     : "=d" (c), "+m" (*v)
+			     : "id" (i));
 	return c != 0;
 }
 
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
 	char c;
-	__asm__ __volatile__("addl %2,%1; smi %0" : "=d" (c), "+m" (*v): "g" (i));
+	__asm__ __volatile__("addl %2,%1; smi %0"
+			     : "=d" (c), "+m" (*v)
+			     : "id" (i));
 	return c != 0;
 }
 

arch/m68k/include/asm/mcfuart.h

@@ -212,5 +212,10 @@ struct mcf_platform_uart {
 #define	MCFUART_URF_RXS		0xc0		/* Receiver status */
 #endif
 
+#if defined(CONFIG_M5272)
+#define MCFUART_TXFIFOSIZE	25
+#else
+#define MCFUART_TXFIFOSIZE	1
+#endif
 /****************************************************************************/
 #endif	/* mcfuart_h */

arch/m68k/include/asm/sigcontext.h

@@ -17,13 +17,11 @@ struct sigcontext {
 #ifndef __uClinux__
 # ifdef __mcoldfire__
 	unsigned long  sc_fpregs[2][2];	/* room for two fp registers */
-	unsigned long  sc_fpcntl[3];
-	unsigned char  sc_fpstate[16+6*8];
 # else
 	unsigned long  sc_fpregs[2*3];  /* room for two fp registers */
+# endif
 	unsigned long  sc_fpcntl[3];
 	unsigned char  sc_fpstate[216];
-# endif
 #endif
 };
 

arch/m68knommu/Makefile

@@ -94,7 +94,7 @@ cflags-$(CONFIG_M520x)		:= $(call cc-option,-mcpu=5208,-m5200)
 cflags-$(CONFIG_M523x)		:= $(call cc-option,-mcpu=523x,-m5307)
 cflags-$(CONFIG_M5249)		:= $(call cc-option,-mcpu=5249,-m5200)
 cflags-$(CONFIG_M5271)		:= $(call cc-option,-mcpu=5271,-m5307)
-cflags-$(CONFIG_M5272)		:= $(call cc-option,-mcpu=5271,-m5200)
+cflags-$(CONFIG_M5272)		:= $(call cc-option,-mcpu=5272,-m5307)
 cflags-$(CONFIG_M5275)		:= $(call cc-option,-mcpu=5275,-m5307)
 cflags-$(CONFIG_M528x)		:= $(call cc-option,-m528x,-m5307)
 cflags-$(CONFIG_M5307)		:= $(call cc-option,-m5307,-m5200)

arch/m68knommu/kernel/entry.S

@@ -145,6 +145,6 @@ ENTRY(ret_from_user_signal)
 	trap #0
 
 ENTRY(ret_from_user_rt_signal)
-	move #__NR_rt_sigreturn,%d0
+	movel #__NR_rt_sigreturn,%d0
 	trap #0
 

arch/m68knommu/platform/68360/ints.c

@@ -107,7 +107,6 @@ void init_IRQ(void)
 	_ramvec[vba+CPMVEC_PIO_PC7]     = inthandler;  /* pio - pc7 */
 	_ramvec[vba+CPMVEC_PIO_PC6]     = inthandler;  /* pio - pc6 */
 	_ramvec[vba+CPMVEC_TIMER3]      = inthandler;  /* timer 3 */
-	_ramvec[vba+CPMVEC_RISCTIMER]   = inthandler;  /* reserved */
 	_ramvec[vba+CPMVEC_PIO_PC5]     = inthandler;  /* pio - pc5 */
 	_ramvec[vba+CPMVEC_PIO_PC4]     = inthandler;  /* pio - pc4 */
 	_ramvec[vba+CPMVEC_RESERVED2]   = inthandler;  /* reserved */

arch/powerpc/kvm/book3s.c

@@ -1004,7 +1004,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	struct kvm_vcpu *vcpu;
 	ulong ga, ga_end;
 	int is_dirty = 0;
-	int r, n;
+	int r;
+	unsigned long n;
 
 	mutex_lock(&kvm->slots_lock);
 
@@ -1022,7 +1023,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 		kvm_for_each_vcpu(n, vcpu, kvm)
 			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
 
-		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+		n = kvm_dirty_bitmap_bytes(memslot);
 		memset(memslot->dirty_bitmap, 0, n);
 	}
 

arch/s390/include/asm/vdso.h

@@ -29,6 +29,7 @@ struct vdso_data {
 	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x30 */
 	__u32 tz_dsttime;		/* Type of dst correction	0x34 */
 	__u32 ectg_available;
+	__u32 ntp_mult;			/* NTP adjusted multiplier	0x3C */
 };
 
 struct vdso_per_cpu_data {

arch/s390/kernel/asm-offsets.c

@@ -61,6 +61,7 @@ int main(void)
 	DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
 	DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest));
 	DEFINE(__VDSO_ECTG_OK, offsetof(struct vdso_data, ectg_available));
+	DEFINE(__VDSO_NTP_MULT, offsetof(struct vdso_data, ntp_mult));
 	DEFINE(__VDSO_ECTG_BASE, offsetof(struct vdso_per_cpu_data, ectg_timer_base));
 	DEFINE(__VDSO_ECTG_USER, offsetof(struct vdso_per_cpu_data, ectg_user_time));
 	/* constants used by the vdso */

arch/s390/kernel/swsusp_asm64.S

@@ -256,6 +256,9 @@ restore_registers:
 	lghi	%r2,0
 	brasl	%r14,arch_set_page_states
 
+	/* Reinitialize the channel subsystem */
+	brasl	%r14,channel_subsystem_reinit
+
 	/* Return 0 */
 	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
 	lghi	%r2,0

arch/s390/kernel/time.c

@@ -221,6 +221,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
 	vdso_data->xtime_clock_nsec = wall_time->tv_nsec;
 	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
 	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
+	vdso_data->ntp_mult = mult;
 	smp_wmb();
 	++vdso_data->tb_update_count;
 }

arch/s390/kernel/vdso32/clock_gettime.S

@@ -38,13 +38,13 @@ __kernel_clock_gettime:
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,2f
 	ahi	%r0,-1
-2:	mhi	%r0,1000			/* cyc2ns(clock,cycle_delta) */
+2:	ms	%r0,__VDSO_NTP_MULT(%r5)	/* cyc2ns(clock,cycle_delta) */
 	lr	%r2,%r0
-	lhi	%r0,1000
+	l	%r0,__VDSO_NTP_MULT(%r5)
 	ltr	%r1,%r1
 	mr	%r0,%r0
 	jnm	3f
-	ahi	%r0,1000
+	a	%r0,__VDSO_NTP_MULT(%r5)
 3:	alr	%r0,%r2
 	srdl	%r0,12
 	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
@@ -86,13 +86,13 @@ __kernel_clock_gettime:
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,12f
 	ahi	%r0,-1
-12:	mhi	%r0,1000			/* cyc2ns(clock,cycle_delta) */
+12:	ms	%r0,__VDSO_NTP_MULT(%r5)	/* cyc2ns(clock,cycle_delta) */
 	lr	%r2,%r0
-	lhi	%r0,1000
+	l	%r0,__VDSO_NTP_MULT(%r5)
 	ltr	%r1,%r1
 	mr	%r0,%r0
 	jnm	13f
-	ahi	%r0,1000
+	a	%r0,__VDSO_NTP_MULT(%r5)
 13:	alr	%r0,%r2
 	srdl	%r0,12
 	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */

arch/s390/kernel/vdso32/gettimeofday.S

@@ -35,13 +35,13 @@ __kernel_gettimeofday:
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,3f
 	ahi	%r0,-1
-3:	mhi	%r0,1000			/* cyc2ns(clock,cycle_delta) */
+3:	ms	%r0,__VDSO_NTP_MULT(%r5)	/* cyc2ns(clock,cycle_delta) */
 	st	%r0,24(%r15)
-	lhi	%r0,1000
+	l	%r0,__VDSO_NTP_MULT(%r5)
 	ltr	%r1,%r1
 	mr	%r0,%r0
 	jnm	4f
-	ahi	%r0,1000
+	a	%r0,__VDSO_NTP_MULT(%r5)
 4:	al	%r0,24(%r15)
 	srdl	%r0,12
 	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */

arch/s390/kernel/vdso64/clock_gettime.S

@@ -36,7 +36,7 @@ __kernel_clock_gettime:
 	stck	48(%r15)			/* Store TOD clock */
 	lg	%r1,48(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	mghi	%r1,1000
+	msgf	%r1,__VDSO_NTP_MULT(%r5)	/*  * NTP adjustment */
 	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
 	lg	%r0,__VDSO_XTIME_SEC(%r5)
@@ -64,7 +64,7 @@ __kernel_clock_gettime:
 	stck	48(%r15)			/* Store TOD clock */
 	lg	%r1,48(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	mghi	%r1,1000
+	msgf	%r1,__VDSO_NTP_MULT(%r5)	/*  * NTP adjustment */
 	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
 	lg	%r0,__VDSO_XTIME_SEC(%r5)

arch/s390/kernel/vdso64/gettimeofday.S

@@ -31,7 +31,7 @@ __kernel_gettimeofday:
 	stck	48(%r15)			/* Store TOD clock */
 	lg	%r1,48(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	mghi	%r1,1000
+	msgf	%r1,__VDSO_NTP_MULT(%r5)	/*  * NTP adjustment */
 	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime.tv_nsec */
 	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* xtime.tv_sec */

arch/sparc/Kconfig

@@ -37,6 +37,9 @@ config SPARC64
 	def_bool 64BIT
 	select ARCH_SUPPORTS_MSI
 	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_GRAPH_FP_TEST
+	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_LMB

arch/sparc/Kconfig.debug

@@ -19,13 +19,10 @@ config DEBUG_DCFLUSH
 	bool "D-cache flush debugging"
 	depends on SPARC64 && DEBUG_KERNEL
 
-config STACK_DEBUG
-	bool "Stack Overflow Detection Support"
-
 config MCOUNT
 	bool
 	depends on SPARC64
-	depends on STACK_DEBUG || FUNCTION_TRACER
+	depends on FUNCTION_TRACER
 	default y
 
 config FRAME_POINTER

arch/sparc/include/asm/cpudata_64.h

@@ -17,7 +17,7 @@ typedef struct {
 	unsigned int	__nmi_count;
 	unsigned long	clock_tick;	/* %tick's per second */
 	unsigned long	__pad;
-	unsigned int	__pad1;
+	unsigned int	irq0_irqs;
 	unsigned int	__pad2;
 
 	/* Dcache line 2, rarely used */

arch/sparc/include/asm/irqflags_64.h

@@ -76,9 +76,26 @@ static inline int raw_irqs_disabled(void)
  */
 static inline unsigned long __raw_local_irq_save(void)
 {
-	unsigned long flags = __raw_local_save_flags();
+	unsigned long flags, tmp;
 
-	raw_local_irq_disable();
+	/* Disable interrupts to PIL_NORMAL_MAX unless we already
+	 * are using PIL_NMI, in which case PIL_NMI is retained.
+	 *
+	 * The only values we ever program into the %pil are 0,
+	 * PIL_NORMAL_MAX and PIL_NMI.
+	 *
+	 * Since PIL_NMI is the largest %pil value and all bits are
+	 * set in it (0xf), it doesn't matter what PIL_NORMAL_MAX
+	 * actually is.
+	 */
+	__asm__ __volatile__(
+		"rdpr	%%pil, %0\n\t"
+		"or	%0, %2, %1\n\t"
+		"wrpr	%1, 0x0, %%pil"
+		: "=r" (flags), "=r" (tmp)
+		: "i" (PIL_NORMAL_MAX)
+		: "memory"
+	);
 
 	return flags;
 }

arch/sparc/include/asm/thread_info_64.h

@@ -111,7 +111,7 @@ struct thread_info {
 #define THREAD_SHIFT PAGE_SHIFT
 #endif /* PAGE_SHIFT == 13 */
 
-#define PREEMPT_ACTIVE		0x4000000
+#define PREEMPT_ACTIVE		0x10000000
 
 /*
  * macros/functions for gaining access to the thread information structure

arch/sparc/kernel/Makefile

@@ -13,6 +13,14 @@ extra-y     += init_task.o
 CPPFLAGS_vmlinux.lds := -Usparc -m$(BITS)
 extra-y              += vmlinux.lds
 
+ifdef CONFIG_FUNCTION_TRACER
+# Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_ftrace.o := -pg
+CFLAGS_REMOVE_time_$(BITS).o := -pg
+CFLAGS_REMOVE_perf_event.o := -pg
+CFLAGS_REMOVE_pcr.o := -pg
+endif
+
 obj-$(CONFIG_SPARC32)   += entry.o wof.o wuf.o
 obj-$(CONFIG_SPARC32)   += etrap_32.o
 obj-$(CONFIG_SPARC32)   += rtrap_32.o
@@ -85,7 +93,7 @@ obj-$(CONFIG_KGDB)        += kgdb_$(BITS).o
 
 
 obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
-CFLAGS_REMOVE_ftrace.o := -pg
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 
 obj-$(CONFIG_EARLYFB) += btext.o
 obj-$(CONFIG_STACKTRACE)     += stacktrace.o

arch/sparc/kernel/ftrace.c

@@ -13,7 +13,7 @@ static const u32 ftrace_nop = 0x01000000;
 
 static u32 ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
-	static u32 call;
+	u32 call;
 	s32 off;
 
 	off = ((s32)addr - (s32)ip);
@@ -91,3 +91,61 @@ int __init ftrace_dyn_arch_init(void *data)
 	return 0;
 }
 #endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+	u32 old, new;
+
+	old = *(u32 *) &ftrace_graph_call;
+	new = ftrace_call_replace(ip, (unsigned long) &ftrace_graph_caller);
+	return ftrace_modify_code(ip, old, new);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+	u32 old, new;
+
+	old = *(u32 *) &ftrace_graph_call;
+	new = ftrace_call_replace(ip, (unsigned long) &ftrace_stub);
+
+	return ftrace_modify_code(ip, old, new);
+}
+
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+unsigned long prepare_ftrace_return(unsigned long parent,
+				    unsigned long self_addr,
+				    unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long) &return_to_handler;
+	struct ftrace_graph_ent trace;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return parent + 8UL;
+
+	if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
+				     frame_pointer) == -EBUSY)
+		return parent + 8UL;
+
+	trace.func = self_addr;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		current->curr_ret_stack--;
+		return parent + 8UL;
+	}
+
+	return return_hooker;
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */

arch/sparc/kernel/irq_64.c

@@ -20,7 +20,9 @@
 #include <linux/delay.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/ftrace.h>
 #include <linux/irq.h>
+#include <linux/kmemleak.h>
 
 #include <asm/ptrace.h>
 #include <asm/processor.h>
@@ -45,6 +47,7 @@
 
 #include "entry.h"
 #include "cpumap.h"
+#include "kstack.h"
 
 #define NUM_IVECS	(IMAP_INR + 1)
 
@@ -647,6 +650,14 @@ unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
 	bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC);
 	if (unlikely(!bucket))
 		return 0;
+
+	/* The only reference we store to the IRQ bucket is
+	 * by physical address which kmemleak can't see, tell
+	 * it that this object explicitly is not a leak and
+	 * should be scanned.
+	 */
+	kmemleak_not_leak(bucket);
+
 	__flush_dcache_range((unsigned long) bucket,
 			     ((unsigned long) bucket +
 			      sizeof(struct ino_bucket)));
@@ -703,25 +714,7 @@ void ack_bad_irq(unsigned int virt_irq)
 void *hardirq_stack[NR_CPUS];
 void *softirq_stack[NR_CPUS];
 
-static __attribute__((always_inline)) void *set_hardirq_stack(void)
-{
-	void *orig_sp, *sp = hardirq_stack[smp_processor_id()];
-
-	__asm__ __volatile__("mov %%sp, %0" : "=r" (orig_sp));
-	if (orig_sp < sp ||
-	    orig_sp > (sp + THREAD_SIZE)) {
-		sp += THREAD_SIZE - 192 - STACK_BIAS;
-		__asm__ __volatile__("mov %0, %%sp" : : "r" (sp));
-	}
-
-	return orig_sp;
-}
-static __attribute__((always_inline)) void restore_hardirq_stack(void *orig_sp)
-{
-	__asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp));
-}
-
-void handler_irq(int irq, struct pt_regs *regs)
+void __irq_entry handler_irq(int irq, struct pt_regs *regs)
 {
 	unsigned long pstate, bucket_pa;
 	struct pt_regs *old_regs;

arch/sparc/kernel/kgdb_64.c

@@ -5,6 +5,7 @@
 
 #include <linux/kgdb.h>
 #include <linux/kdebug.h>
+#include <linux/ftrace.h>
 
 #include <asm/kdebug.h>
 #include <asm/ptrace.h>
@@ -108,7 +109,7 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 }
 
 #ifdef CONFIG_SMP
-void smp_kgdb_capture_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_kgdb_capture_client(int irq, struct pt_regs *regs)
 {
 	unsigned long flags;
 

arch/sparc/kernel/kstack.h

@@ -61,4 +61,23 @@ check_magic:
 
 }
 
+static inline __attribute__((always_inline)) void *set_hardirq_stack(void)
+{
+	void *orig_sp, *sp = hardirq_stack[smp_processor_id()];
+
+	__asm__ __volatile__("mov %%sp, %0" : "=r" (orig_sp));
+	if (orig_sp < sp ||
+	    orig_sp > (sp + THREAD_SIZE)) {
+		sp += THREAD_SIZE - 192 - STACK_BIAS;
+		__asm__ __volatile__("mov %0, %%sp" : : "r" (sp));
+	}
+
+	return orig_sp;
+}
+
+static inline __attribute__((always_inline)) void restore_hardirq_stack(void *orig_sp)
+{
+	__asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp));
+}
+
 #endif /* _KSTACK_H */

arch/sparc/kernel/nmi.c

@@ -23,6 +23,8 @@
 #include <asm/ptrace.h>
 #include <asm/pcr.h>
 
+#include "kstack.h"
+
 /* We don't have a real NMI on sparc64, but we can fake one
  * up using profiling counter overflow interrupts and interrupt
  * levels.
@@ -92,7 +94,7 @@ static void die_nmi(const char *str, struct pt_regs *regs, int do_panic)
 notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 {
 	unsigned int sum, touched = 0;
-	int cpu = smp_processor_id();
+	void *orig_sp;
 
 	clear_softint(1 << irq);
 
@@ -100,13 +102,15 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 
 	nmi_enter();
 
+	orig_sp = set_hardirq_stack();
+
 	if (notify_die(DIE_NMI, "nmi", regs, 0,
 		       pt_regs_trap_type(regs), SIGINT) == NOTIFY_STOP)
 		touched = 1;
 	else
 		pcr_ops->write(PCR_PIC_PRIV);
 
-	sum = kstat_irqs_cpu(0, cpu);
+	sum = local_cpu_data().irq0_irqs;
 	if (__get_cpu_var(nmi_touch)) {
 		__get_cpu_var(nmi_touch) = 0;
 		touched = 1;
@@ -125,6 +129,8 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 		pcr_ops->write(pcr_enable);
 	}
 
+	restore_hardirq_stack(orig_sp);
+
 	nmi_exit();
 }
 

arch/sparc/kernel/pci_common.c

@@ -371,14 +371,19 @@ static void pci_register_iommu_region(struct pci_pbm_info *pbm)
 		struct resource *rp = kzalloc(sizeof(*rp), GFP_KERNEL);
 
 		if (!rp) {
-			prom_printf("Cannot allocate IOMMU resource.\n");
-			prom_halt();
+			pr_info("%s: Cannot allocate IOMMU resource.\n",
+				pbm->name);
+			return;
 		}
 		rp->name = "IOMMU";
 		rp->start = pbm->mem_space.start + (unsigned long) vdma[0];
 		rp->end = rp->start + (unsigned long) vdma[1] - 1UL;
 		rp->flags = IORESOURCE_BUSY;
-		request_resource(&pbm->mem_space, rp);
+		if (request_resource(&pbm->mem_space, rp)) {
+			pr_info("%s: Unable to request IOMMU resource.\n",
+				pbm->name);
+			kfree(rp);
+		}
 	}
 }
 

arch/sparc/kernel/pcr.c

@@ -8,6 +8,7 @@
 #include <linux/irq.h>
 
 #include <linux/perf_event.h>
+#include <linux/ftrace.h>
 
 #include <asm/pil.h>
 #include <asm/pcr.h>
@@ -34,7 +35,7 @@ unsigned int picl_shift;
  * Therefore in such situations we defer the work by signalling
  * a lower level cpu IRQ.
  */
-void deferred_pcr_work_irq(int irq, struct pt_regs *regs)
+void __irq_entry deferred_pcr_work_irq(int irq, struct pt_regs *regs)
 {
 	struct pt_regs *old_regs;
 

arch/sparc/kernel/rtrap_64.S

@@ -130,7 +130,17 @@ rtrap_xcall:
 		 nop
 		call			trace_hardirqs_on
 		 nop
-		wrpr			%l4, %pil
+		/* Do not actually set the %pil here.  We will do that
+		 * below after we clear PSTATE_IE in the %pstate register.
+		 * If we re-enable interrupts here, we can recurse down
+		 * the hardirq stack potentially endlessly, causing a
+		 * stack overflow.
+		 *
+		 * It is tempting to put this test and trace_hardirqs_on
+		 * call at the 'rt_continue' label, but that will not work
+		 * as that path hits unconditionally and we do not want to
+		 * execute this in NMI return paths, for example.
+		 */
 #endif
 rtrap_no_irq_enable:
 		andcc			%l1, TSTATE_PRIV, %l3

arch/sparc/kernel/smp_64.c

@@ -22,6 +22,7 @@
 #include <linux/profile.h>
 #include <linux/bootmem.h>
 #include <linux/vmalloc.h>
+#include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/slab.h>
 
@@ -823,13 +824,13 @@ void arch_send_call_function_single_ipi(int cpu)
 		      &cpumask_of_cpu(cpu));
 }
 
-void smp_call_function_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
 	generic_smp_call_function_interrupt();
 }
 
-void smp_call_function_single_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
 	generic_smp_call_function_single_interrupt();
@@ -965,7 +966,7 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	put_cpu();
 }
 
-void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
 {
 	struct mm_struct *mm;
 	unsigned long flags;
@@ -1149,7 +1150,7 @@ void smp_release(void)
  */
 extern void prom_world(int);
 
-void smp_penguin_jailcell(int irq, struct pt_regs *regs)
+void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
 
@@ -1365,7 +1366,7 @@ void smp_send_reschedule(int cpu)
 		      &cpumask_of_cpu(cpu));
 }
 
-void smp_receive_signal_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
 }

arch/sparc/kernel/time_64.c

@@ -35,6 +35,7 @@
 #include <linux/clocksource.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/ftrace.h>
 
 #include <asm/oplib.h>
 #include <asm/timer.h>
@@ -717,7 +718,7 @@ static struct clock_event_device sparc64_clockevent = {
 };
 static DEFINE_PER_CPU(struct clock_event_device, sparc64_events);
 
-void timer_interrupt(int irq, struct pt_regs *regs)
+void __irq_entry timer_interrupt(int irq, struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	unsigned long tick_mask = tick_ops->softint_mask;
@@ -728,6 +729,7 @@ void timer_interrupt(int irq, struct pt_regs *regs)
 
 	irq_enter();
 
+	local_cpu_data().irq0_irqs++;
 	kstat_incr_irqs_this_cpu(0, irq_to_desc(0));
 
 	if (unlikely(!evt->event_handler)) {

arch/sparc/kernel/traps_64.c

@@ -2203,27 +2203,6 @@ void dump_stack(void)
 
 EXPORT_SYMBOL(dump_stack);
 
-static inline int is_kernel_stack(struct task_struct *task,
-				  struct reg_window *rw)
-{
-	unsigned long rw_addr = (unsigned long) rw;
-	unsigned long thread_base, thread_end;
-
-	if (rw_addr < PAGE_OFFSET) {
-		if (task != &init_task)
-			return 0;
-	}
-
-	thread_base = (unsigned long) task_stack_page(task);
-	thread_end = thread_base + sizeof(union thread_union);
-	if (rw_addr >= thread_base &&
-	    rw_addr < thread_end &&
-	    !(rw_addr & 0x7UL))
-		return 1;
-
-	return 0;
-}
-
 static inline struct reg_window *kernel_stack_up(struct reg_window *rw)
 {
 	unsigned long fp = rw->ins[6];
@@ -2252,6 +2231,7 @@ void die_if_kernel(char *str, struct pt_regs *regs)
 	show_regs(regs);
 	add_taint(TAINT_DIE);
 	if (regs->tstate & TSTATE_PRIV) {
+		struct thread_info *tp = current_thread_info();
 		struct reg_window *rw = (struct reg_window *)
 			(regs->u_regs[UREG_FP] + STACK_BIAS);
 
@@ -2259,8 +2239,8 @@ void die_if_kernel(char *str, struct pt_regs *regs)
 		 * find some badly aligned kernel stack.
 		 */
 		while (rw &&
-		       count++ < 30&&
-		       is_kernel_stack(current, rw)) {
+		       count++ < 30 &&
+		       kstack_valid(tp, (unsigned long) rw)) {
 			printk("Caller[%016lx]: %pS\n", rw->ins[7],
 			       (void *) rw->ins[7]);
 

arch/sparc/kernel/unaligned_64.c

@@ -50,7 +50,7 @@ static inline enum direction decode_direction(unsigned int insn)
 }
 
 /* 16 = double-word, 8 = extra-word, 4 = word, 2 = half-word */
-static inline int decode_access_size(unsigned int insn)
+static inline int decode_access_size(struct pt_regs *regs, unsigned int insn)
 {
 	unsigned int tmp;
 
@@ -66,7 +66,7 @@ static inline int decode_access_size(unsigned int insn)
 		return 2;
 	else {
 		printk("Impossible unaligned trap. insn=%08x\n", insn);
-		die_if_kernel("Byte sized unaligned access?!?!", current_thread_info()->kregs);
+		die_if_kernel("Byte sized unaligned access?!?!", regs);
 
 		/* GCC should never warn that control reaches the end
 		 * of this function without returning a value because
@@ -286,7 +286,7 @@ static void log_unaligned(struct pt_regs *regs)
 asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 {
 	enum direction dir = decode_direction(insn);
-	int size = decode_access_size(insn);
+	int size = decode_access_size(regs, insn);
 	int orig_asi, asi;
 
 	current_thread_info()->kern_una_regs = regs;

arch/sparc/kernel/vmlinux.lds.S

@@ -46,11 +46,16 @@ SECTIONS
 		SCHED_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
+		IRQENTRY_TEXT
 		*(.gnu.warning)
 	} = 0
 	_etext = .;
 
 	RO_DATA(PAGE_SIZE)
+
+	/* Start of data section */
+	_sdata = .;
+
 	.data1 : {
 		*(.data1)
 	}

arch/sparc/lib/mcount.S

@@ -7,26 +7,11 @@
 
 #include <linux/linkage.h>
 
-#include <asm/ptrace.h>
-#include <asm/thread_info.h>
-
 /*
  * This is the main variant and is called by C code.  GCC's -pg option
  * automatically instruments every C function with a call to this.
  */
 
-#ifdef CONFIG_STACK_DEBUG
-
-#define OVSTACKSIZE	4096		/* lets hope this is enough */
-
-	.data
-	.align		8
-panicstring:
-	.asciz		"Stack overflow\n"
-	.align		8
-ovstack:
-	.skip		OVSTACKSIZE
-#endif
 	.text
 	.align		32
 	.globl		_mcount
@@ -35,84 +20,48 @@ ovstack:
 	.type		mcount,#function
 _mcount:
 mcount:
-#ifdef CONFIG_STACK_DEBUG
-	/*
-	 * Check whether %sp is dangerously low.
-	 */
-	ldub		[%g6 + TI_FPDEPTH], %g1
-	srl		%g1, 1, %g3
-	add		%g3, 1, %g3
-	sllx		%g3, 8, %g3			! each fpregs frame is 256b
-	add		%g3, 192, %g3
-	add		%g6, %g3, %g3			! where does task_struct+frame end?
-	sub		%g3, STACK_BIAS, %g3
-	cmp		%sp, %g3
-	bg,pt		%xcc, 1f
-	 nop
-	lduh		[%g6 + TI_CPU], %g1
-	sethi		%hi(hardirq_stack), %g3
-	or		%g3, %lo(hardirq_stack), %g3
-	sllx		%g1, 3, %g1
-	ldx		[%g3 + %g1], %g7
-	sub		%g7, STACK_BIAS, %g7
-	cmp		%sp, %g7
-	bleu,pt		%xcc, 2f
-	 sethi		%hi(THREAD_SIZE), %g3
-	add		%g7, %g3, %g7
-	cmp		%sp, %g7
-	blu,pn		%xcc, 1f
-2:	 sethi		%hi(softirq_stack), %g3
-	or		%g3, %lo(softirq_stack), %g3
-	ldx		[%g3 + %g1], %g7
-	sub		%g7, STACK_BIAS, %g7
-	cmp		%sp, %g7
-	bleu,pt		%xcc, 3f
-	 sethi		%hi(THREAD_SIZE), %g3
-	add		%g7, %g3, %g7
-	cmp		%sp, %g7
-	blu,pn		%xcc, 1f
-	 nop
-	/* If we are already on ovstack, don't hop onto it
-	 * again, we are already trying to output the stack overflow
-	 * message.
-	 */
-3:	sethi		%hi(ovstack), %g7		! cant move to panic stack fast enough
-	 or		%g7, %lo(ovstack), %g7
-	add		%g7, OVSTACKSIZE, %g3
-	sub		%g3, STACK_BIAS + 192, %g3
-	sub		%g7, STACK_BIAS, %g7
-	cmp		%sp, %g7
-	blu,pn		%xcc, 2f
-	 cmp		%sp, %g3
-	bleu,pn		%xcc, 1f
-	 nop
-2:	mov		%g3, %sp
-	sethi		%hi(panicstring), %g3
-	call		prom_printf
-	 or		%g3, %lo(panicstring), %o0
-	call		prom_halt
-	 nop
-1:
-#endif
 #ifdef CONFIG_FUNCTION_TRACER
 #ifdef CONFIG_DYNAMIC_FTRACE
-	mov		%o7, %o0
-	.globl		mcount_call
-mcount_call:
-	call		ftrace_stub
-	 mov		%o0, %o7
+	/* Do nothing, the retl/nop below is all we need.  */
 #else
+	sethi		%hi(function_trace_stop), %g1
+	lduw		[%g1 + %lo(function_trace_stop)], %g2
+	brnz,pn		%g2, 2f
 	 sethi		%hi(ftrace_trace_function), %g1
 	sethi		%hi(ftrace_stub), %g2
 	ldx		[%g1 + %lo(ftrace_trace_function)], %g1
 	or		%g2, %lo(ftrace_stub), %g2
 	cmp		%g1, %g2
 	be,pn		%icc, 1f
-	 mov		%i7, %o1
-	jmpl		%g1, %g0
-	 mov		%o7, %o0
+	 mov		%i7, %g3
+	save		%sp, -176, %sp
+	mov		%g3, %o1
+	jmpl		%g1, %o7
+	 mov		%i7, %o0
+	ret
+	 restore
 	/* not reached */
 1:
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	sethi		%hi(ftrace_graph_return), %g1
+	ldx		[%g1 + %lo(ftrace_graph_return)], %g3
+	cmp		%g2, %g3
+	bne,pn		%xcc, 5f
+	 sethi		%hi(ftrace_graph_entry_stub), %g2
+	sethi		%hi(ftrace_graph_entry), %g1
+	or		%g2, %lo(ftrace_graph_entry_stub), %g2
+	ldx		[%g1 + %lo(ftrace_graph_entry)], %g1
+	cmp		%g1, %g2
+	be,pt		%xcc, 2f
+	 nop
+5:	mov		%i7, %g2
+	mov		%fp, %g3
+	save		%sp, -176, %sp
+	mov		%g2, %l0
+	ba,pt		%xcc, ftrace_graph_caller
+	 mov		%g3, %l1
+#endif
+2:
 #endif
 #endif
 	retl
@@ -131,14 +80,50 @@ ftrace_stub:
 	.globl		ftrace_caller
 	.type		ftrace_caller,#function
 ftrace_caller:
-	mov		%i7, %o1
-	mov		%o7, %o0
+	sethi		%hi(function_trace_stop), %g1
+	mov		%i7, %g2
+	lduw		[%g1 + %lo(function_trace_stop)], %g1
+	brnz,pn		%g1, ftrace_stub
+	 mov		%fp, %g3
+	save		%sp, -176, %sp
+	mov		%g2, %o1
+	mov		%g2, %l0
+	mov		%g3, %l1
 	.globl		ftrace_call
 ftrace_call:
 	call		ftrace_stub
-	 mov		%o0, %o7
-	retl
+	 mov		%i7, %o0
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.globl		ftrace_graph_call
+ftrace_graph_call:
+	call		ftrace_stub
 	 nop
+#endif
+	ret
+	 restore
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.size		ftrace_graph_call,.-ftrace_graph_call
+#endif
+	.size		ftrace_call,.-ftrace_call
 	.size		ftrace_caller,.-ftrace_caller
 #endif
 #endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	mov		%l0, %o0
+	mov		%i7, %o1
+	call		prepare_ftrace_return
+	 mov		%l1, %o2
+	ret
+	 restore	%o0, -8, %i7
+END(ftrace_graph_caller)
+
+ENTRY(return_to_handler)
+	save		%sp, -176, %sp
+	call		ftrace_return_to_handler
+	 mov		%fp, %o0
+	jmpl		%o0 + 8, %g0
+	 restore
+END(return_to_handler)
+#endif

arch/um/drivers/line.c

@@ -6,6 +6,7 @@
 #include "linux/irqreturn.h"
 #include "linux/kd.h"
 #include "linux/sched.h"
+#include "linux/slab.h"
 #include "chan_kern.h"
 #include "irq_kern.h"
 #include "irq_user.h"

arch/um/os-Linux/helper.c

@@ -8,7 +8,6 @@
 #include <errno.h>
 #include <sched.h>
 #include <linux/limits.h>
-#include <linux/slab.h>
 #include <sys/socket.h>
 #include <sys/wait.h>
 #include "kern_constants.h"

arch/x86/ia32/ia32entry.S

@@ -626,7 +626,7 @@ ia32_sys_call_table:
 	.quad stub32_sigreturn
 	.quad stub32_clone		/* 120 */
 	.quad sys_setdomainname
-	.quad sys_uname
+	.quad sys_newuname
 	.quad sys_modify_ldt
 	.quad compat_sys_adjtimex
 	.quad sys32_mprotect		/* 125 */

arch/x86/include/asm/amd_iommu_types.h

@@ -21,6 +21,7 @@
 #define _ASM_X86_AMD_IOMMU_TYPES_H
 
 #include <linux/types.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 
@@ -140,6 +141,7 @@
 
 /* constants to configure the command buffer */
 #define CMD_BUFFER_SIZE    8192
+#define CMD_BUFFER_UNINITIALIZED 1
 #define CMD_BUFFER_ENTRIES 512
 #define MMIO_CMD_SIZE_SHIFT 56
 #define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
@@ -237,6 +239,7 @@ struct protection_domain {
 	struct list_head list;  /* for list of all protection domains */
 	struct list_head dev_list; /* List of all devices in this domain */
 	spinlock_t lock;	/* mostly used to lock the page table*/
+	struct mutex api_lock;	/* protect page tables in the iommu-api path */
 	u16 id;			/* the domain id written to the device table */
 	int mode;		/* paging mode (0-6 levels) */
 	u64 *pt_root;		/* page table root pointer */