Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	net/ipv6/route.c

This deals with a merge conflict between the net-next addition of the
inetpeer network namespace ops, and Thomas Graf's bug fix in
2a0c451ade which makes sure we don't
register /proc/net/ipv6_route before it is actually safe to do so.

Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt

@@ -0,0 +1,93 @@
+Pinctrl-based I2C Bus Mux
+
+This binding describes an I2C bus multiplexer that uses pin multiplexing to
+route the I2C signals, and represents the pin multiplexing configuration
+using the pinctrl device tree bindings.
+
+                                 +-----+  +-----+
+                                 | dev |  | dev |
+    +------------------------+   +-----+  +-----+
+    | SoC                    |      |        |
+    |                   /----|------+--------+
+    |   +---+   +------+     | child bus A, on first set of pins
+    |   |I2C|---|Pinmux|     |
+    |   +---+   +------+     | child bus B, on second set of pins
+    |                   \----|------+--------+--------+
+    |                        |      |        |        |
+    +------------------------+  +-----+  +-----+  +-----+
+                                | dev |  | dev |  | dev |
+                                +-----+  +-----+  +-----+
+
+Required properties:
+- compatible: i2c-mux-pinctrl
+- i2c-parent: The phandle of the I2C bus that this multiplexer's master-side
+  port is connected to.
+
+Also required are:
+
+* Standard pinctrl properties that specify the pin mux state for each child
+  bus. See ../pinctrl/pinctrl-bindings.txt.
+
+* Standard I2C mux properties. See mux.txt in this directory.
+
+* I2C child bus nodes. See mux.txt in this directory.
+
+For each named state defined in the pinctrl-names property, an I2C child bus
+will be created. I2C child bus numbers are assigned based on the index into
+the pinctrl-names property.
+
+The only exception is that no bus will be created for a state named "idle". If
+such a state is defined, it must be the last entry in pinctrl-names. For
+example:
+
+	pinctrl-names = "ddc", "pta", "idle"  ->  ddc = bus 0, pta = bus 1
+	pinctrl-names = "ddc", "idle", "pta"  ->  Invalid ("idle" not last)
+	pinctrl-names = "idle", "ddc", "pta"  ->  Invalid ("idle" not last)
+
+Whenever an access is made to a device on a child bus, the relevant pinctrl
+state will be programmed into hardware.
+
+If an idle state is defined, whenever an access is not being made to a device
+on a child bus, the idle pinctrl state will be programmed into hardware.
+
+If an idle state is not defined, the most recently used pinctrl state will be
+left programmed into hardware whenever no access is being made of a device on
+a child bus.
+
+Example:
+
+	i2cmux {
+		compatible = "i2c-mux-pinctrl";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		i2c-parent = <&i2c1>;
+
+		pinctrl-names = "ddc", "pta", "idle";
+		pinctrl-0 = <&state_i2cmux_ddc>;
+		pinctrl-1 = <&state_i2cmux_pta>;
+		pinctrl-2 = <&state_i2cmux_idle>;
+
+		i2c@0 {
+			reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			eeprom {
+				compatible = "eeprom";
+				reg = <0x50>;
+			};
+		};
+
+		i2c@1 {
+			reg = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			eeprom {
+				compatible = "eeprom";
+				reg = <0x50>;
+			};
+		};
+	};
+

Documentation/kernel-parameters.txt

@@ -2543,6 +2543,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	sched_debug	[KNL] Enables verbose scheduler debug messages.
 
+	skew_tick=	[KNL] Offset the periodic timer tick per cpu to mitigate
+			xtime_lock contention on larger systems, and/or RCU lock
+			contention on all systems with CONFIG_MAXSMP set.
+			Format: { "0" | "1" }
+			0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
+			1 -- enable.
+			Note: increases power consumption, thus should only be
+			enabled if running jitter sensitive (HPC/RT) workloads.
+
 	security=	[SECURITY] Choose a security module to enable at boot.
 			If this boot parameter is not specified, only the first
 			security module asking for security registration will be

Documentation/vm/frontswap.txt

@@ -0,0 +1,278 @@
+Frontswap provides a "transcendent memory" interface for swap pages.
+In some environments, dramatic performance savings may be obtained because
+swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk.
+
+(Note, frontswap -- and cleancache (merged at 3.0) -- are the "frontends"
+and the only necessary changes to the core kernel for transcendent memory;
+all other supporting code -- the "backends" -- is implemented as drivers.
+See the LWN.net article "Transcendent memory in a nutshell" for a detailed
+overview of frontswap and related kernel parts:
+https://lwn.net/Articles/454795/ )
+
+Frontswap is so named because it can be thought of as the opposite of
+a "backing" store for a swap device.  The storage is assumed to be
+a synchronous concurrency-safe page-oriented "pseudo-RAM device" conforming
+to the requirements of transcendent memory (such as Xen's "tmem", or
+in-kernel compressed memory, aka "zcache", or future RAM-like devices);
+this pseudo-RAM device is not directly accessible or addressable by the
+kernel and is of unknown and possibly time-varying size.  The driver
+links itself to frontswap by calling frontswap_register_ops to set the
+frontswap_ops funcs appropriately and the functions it provides must
+conform to certain policies as follows:
+
+An "init" prepares the device to receive frontswap pages associated
+with the specified swap device number (aka "type").  A "store" will
+copy the page to transcendent memory and associate it with the type and
+offset associated with the page. A "load" will copy the page, if found,
+from transcendent memory into kernel memory, but will NOT remove the page
+from from transcendent memory.  An "invalidate_page" will remove the page
+from transcendent memory and an "invalidate_area" will remove ALL pages
+associated with the swap type (e.g., like swapoff) and notify the "device"
+to refuse further stores with that swap type.
+
+Once a page is successfully stored, a matching load on the page will normally
+succeed.  So when the kernel finds itself in a situation where it needs
+to swap out a page, it first attempts to use frontswap.  If the store returns
+success, the data has been successfully saved to transcendent memory and
+a disk write and, if the data is later read back, a disk read are avoided.
+If a store returns failure, transcendent memory has rejected the data, and the
+page can be written to swap as usual.
+
+If a backend chooses, frontswap can be configured as a "writethrough
+cache" by calling frontswap_writethrough().  In this mode, the reduction
+in swap device writes is lost (and also a non-trivial performance advantage)
+in order to allow the backend to arbitrarily "reclaim" space used to
+store frontswap pages to more completely manage its memory usage.
+
+Note that if a page is stored and the page already exists in transcendent memory
+(a "duplicate" store), either the store succeeds and the data is overwritten,
+or the store fails AND the page is invalidated.  This ensures stale data may
+never be obtained from frontswap.
+
+If properly configured, monitoring of frontswap is done via debugfs in
+the /sys/kernel/debug/frontswap directory.  The effectiveness of
+frontswap can be measured (across all swap devices) with:
+
+failed_stores	- how many store attempts have failed
+loads		- how many loads were attempted (all should succeed)
+succ_stores	- how many store attempts have succeeded
+invalidates	- how many invalidates were attempted
+
+A backend implementation may provide additional metrics.
+
+FAQ
+
+1) Where's the value?
+
+When a workload starts swapping, performance falls through the floor.
+Frontswap significantly increases performance in many such workloads by
+providing a clean, dynamic interface to read and write swap pages to
+"transcendent memory" that is otherwise not directly addressable to the kernel.
+This interface is ideal when data is transformed to a different form
+and size (such as with compression) or secretly moved (as might be
+useful for write-balancing for some RAM-like devices).  Swap pages (and
+evicted page-cache pages) are a great use for this kind of slower-than-RAM-
+but-much-faster-than-disk "pseudo-RAM device" and the frontswap (and
+cleancache) interface to transcendent memory provides a nice way to read
+and write -- and indirectly "name" -- the pages.
+
+Frontswap -- and cleancache -- with a fairly small impact on the kernel,
+provides a huge amount of flexibility for more dynamic, flexible RAM
+utilization in various system configurations:
+
+In the single kernel case, aka "zcache", pages are compressed and
+stored in local memory, thus increasing the total anonymous pages
+that can be safely kept in RAM.  Zcache essentially trades off CPU
+cycles used in compression/decompression for better memory utilization.
+Benchmarks have shown little or no impact when memory pressure is
+low while providing a significant performance improvement (25%+)
+on some workloads under high memory pressure.
+
+"RAMster" builds on zcache by adding "peer-to-peer" transcendent memory
+support for clustered systems.  Frontswap pages are locally compressed
+as in zcache, but then "remotified" to another system's RAM.  This
+allows RAM to be dynamically load-balanced back-and-forth as needed,
+i.e. when system A is overcommitted, it can swap to system B, and
+vice versa.  RAMster can also be configured as a memory server so
+many servers in a cluster can swap, dynamically as needed, to a single
+server configured with a large amount of RAM... without pre-configuring
+how much of the RAM is available for each of the clients!
+
+In the virtual case, the whole point of virtualization is to statistically
+multiplex physical resources acrosst the varying demands of multiple
+virtual machines.  This is really hard to do with RAM and efforts to do
+it well with no kernel changes have essentially failed (except in some
+well-publicized special-case workloads).
+Specifically, the Xen Transcendent Memory backend allows otherwise
+"fallow" hypervisor-owned RAM to not only be "time-shared" between multiple
+virtual machines, but the pages can be compressed and deduplicated to
+optimize RAM utilization.  And when guest OS's are induced to surrender
+underutilized RAM (e.g. with "selfballooning"), sudden unexpected
+memory pressure may result in swapping; frontswap allows those pages
+to be swapped to and from hypervisor RAM (if overall host system memory
+conditions allow), thus mitigating the potentially awful performance impact
+of unplanned swapping.
+
+A KVM implementation is underway and has been RFC'ed to lkml.  And,
+using frontswap, investigation is also underway on the use of NVM as
+a memory extension technology.
+
+2) Sure there may be performance advantages in some situations, but
+   what's the space/time overhead of frontswap?
+
+If CONFIG_FRONTSWAP is disabled, every frontswap hook compiles into
+nothingness and the only overhead is a few extra bytes per swapon'ed
+swap device.  If CONFIG_FRONTSWAP is enabled but no frontswap "backend"
+registers, there is one extra global variable compared to zero for
+every swap page read or written.  If CONFIG_FRONTSWAP is enabled
+AND a frontswap backend registers AND the backend fails every "store"
+request (i.e. provides no memory despite claiming it might),
+CPU overhead is still negligible -- and since every frontswap fail
+precedes a swap page write-to-disk, the system is highly likely
+to be I/O bound and using a small fraction of a percent of a CPU
+will be irrelevant anyway.
+
+As for space, if CONFIG_FRONTSWAP is enabled AND a frontswap backend
+registers, one bit is allocated for every swap page for every swap
+device that is swapon'd.  This is added to the EIGHT bits (which
+was sixteen until about 2.6.34) that the kernel already allocates
+for every swap page for every swap device that is swapon'd.  (Hugh
+Dickins has observed that frontswap could probably steal one of
+the existing eight bits, but let's worry about that minor optimization
+later.)  For very large swap disks (which are rare) on a standard
+4K pagesize, this is 1MB per 32GB swap.
+
+When swap pages are stored in transcendent memory instead of written
+out to disk, there is a side effect that this may create more memory
+pressure that can potentially outweigh the other advantages.  A
+backend, such as zcache, must implement policies to carefully (but
+dynamically) manage memory limits to ensure this doesn't happen.
+
+3) OK, how about a quick overview of what this frontswap patch does
+   in terms that a kernel hacker can grok?
+
+Let's assume that a frontswap "backend" has registered during
+kernel initialization; this registration indicates that this
+frontswap backend has access to some "memory" that is not directly
+accessible by the kernel.  Exactly how much memory it provides is
+entirely dynamic and random.
+
+Whenever a swap-device is swapon'd frontswap_init() is called,
+passing the swap device number (aka "type") as a parameter.
+This notifies frontswap to expect attempts to "store" swap pages
+associated with that number.
+
+Whenever the swap subsystem is readying a page to write to a swap
+device (c.f swap_writepage()), frontswap_store is called.  Frontswap
+consults with the frontswap backend and if the backend says it does NOT
+have room, frontswap_store returns -1 and the kernel swaps the page
+to the swap device as normal.  Note that the response from the frontswap
+backend is unpredictable to the kernel; it may choose to never accept a
+page, it could accept every ninth page, or it might accept every
+page.  But if the backend does accept a page, the data from the page
+has already been copied and associated with the type and offset,
+and the backend guarantees the persistence of the data.  In this case,
+frontswap sets a bit in the "frontswap_map" for the swap device
+corresponding to the page offset on the swap device to which it would
+otherwise have written the data.
+
+When the swap subsystem needs to swap-in a page (swap_readpage()),
+it first calls frontswap_load() which checks the frontswap_map to
+see if the page was earlier accepted by the frontswap backend.  If
+it was, the page of data is filled from the frontswap backend and
+the swap-in is complete.  If not, the normal swap-in code is
+executed to obtain the page of data from the real swap device.
+
+So every time the frontswap backend accepts a page, a swap device read
+and (potentially) a swap device write are replaced by a "frontswap backend
+store" and (possibly) a "frontswap backend loads", which are presumably much
+faster.
+
+4) Can't frontswap be configured as a "special" swap device that is
+   just higher priority than any real swap device (e.g. like zswap,
+   or maybe swap-over-nbd/NFS)?
+
+No.  First, the existing swap subsystem doesn't allow for any kind of
+swap hierarchy.  Perhaps it could be rewritten to accomodate a hierarchy,
+but this would require fairly drastic changes.  Even if it were
+rewritten, the existing swap subsystem uses the block I/O layer which
+assumes a swap device is fixed size and any page in it is linearly
+addressable.  Frontswap barely touches the existing swap subsystem,
+and works around the constraints of the block I/O subsystem to provide
+a great deal of flexibility and dynamicity.
+
+For example, the acceptance of any swap page by the frontswap backend is
+entirely unpredictable. This is critical to the definition of frontswap
+backends because it grants completely dynamic discretion to the
+backend.  In zcache, one cannot know a priori how compressible a page is.
+"Poorly" compressible pages can be rejected, and "poorly" can itself be
+defined dynamically depending on current memory constraints.
+
+Further, frontswap is entirely synchronous whereas a real swap
+device is, by definition, asynchronous and uses block I/O.  The
+block I/O layer is not only unnecessary, but may perform "optimizations"
+that are inappropriate for a RAM-oriented device including delaying
+the write of some pages for a significant amount of time.  Synchrony is
+required to ensure the dynamicity of the backend and to avoid thorny race
+conditions that would unnecessarily and greatly complicate frontswap
+and/or the block I/O subsystem.  That said, only the initial "store"
+and "load" operations need be synchronous.  A separate asynchronous thread
+is free to manipulate the pages stored by frontswap.  For example,
+the "remotification" thread in RAMster uses standard asynchronous
+kernel sockets to move compressed frontswap pages to a remote machine.
+Similarly, a KVM guest-side implementation could do in-guest compression
+and use "batched" hypercalls.
+
+In a virtualized environment, the dynamicity allows the hypervisor
+(or host OS) to do "intelligent overcommit".  For example, it can
+choose to accept pages only until host-swapping might be imminent,
+then force guests to do their own swapping.
+
+There is a downside to the transcendent memory specifications for
+frontswap:  Since any "store" might fail, there must always be a real
+slot on a real swap device to swap the page.  Thus frontswap must be
+implemented as a "shadow" to every swapon'd device with the potential
+capability of holding every page that the swap device might have held
+and the possibility that it might hold no pages at all.  This means
+that frontswap cannot contain more pages than the total of swapon'd
+swap devices.  For example, if NO swap device is configured on some
+installation, frontswap is useless.  Swapless portable devices
+can still use frontswap but a backend for such devices must configure
+some kind of "ghost" swap device and ensure that it is never used.
+
+5) Why this weird definition about "duplicate stores"?  If a page
+   has been previously successfully stored, can't it always be
+   successfully overwritten?
+
+Nearly always it can, but no, sometimes it cannot.  Consider an example
+where data is compressed and the original 4K page has been compressed
+to 1K.  Now an attempt is made to overwrite the page with data that
+is non-compressible and so would take the entire 4K.  But the backend
+has no more space.  In this case, the store must be rejected.  Whenever
+frontswap rejects a store that would overwrite, it also must invalidate
+the old data and ensure that it is no longer accessible.  Since the
+swap subsystem then writes the new data to the read swap device,
+this is the correct course of action to ensure coherency.
+
+6) What is frontswap_shrink for?
+
+When the (non-frontswap) swap subsystem swaps out a page to a real
+swap device, that page is only taking up low-value pre-allocated disk
+space.  But if frontswap has placed a page in transcendent memory, that
+page may be taking up valuable real estate.  The frontswap_shrink
+routine allows code outside of the swap subsystem to force pages out
+of the memory managed by frontswap and back into kernel-addressable memory.
+For example, in RAMster, a "suction driver" thread will attempt
+to "repatriate" pages sent to a remote machine back to the local machine;
+this is driven using the frontswap_shrink mechanism when memory pressure
+subsides.
+
+7) Why does the frontswap patch create the new include file swapfile.h?
+
+The frontswap code depends on some swap-subsystem-internal data
+structures that have, over the years, moved back and forth between
+static and global.  This seemed a reasonable compromise:  Define
+them as global but declare them in a new include file that isn't
+included by the large number of source files that include swap.h.
+
+Dan Magenheimer, last updated April 9, 2012

MAINTAINERS

@@ -2273,7 +2273,7 @@ F:	include/linux/device-mapper.h
 F:	include/linux/dm-*.h
 
 DIOLAN U2C-12 I2C DRIVER
-M:	Guenter Roeck <guenter.roeck@ericsson.com>
+M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-diolan-u2c.c
@@ -2933,6 +2933,13 @@ F:	Documentation/power/freezing-of-tasks.txt
 F:	include/linux/freezer.h
 F:	kernel/freezer.c
 
+FRONTSWAP API
+M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	mm/frontswap.c
+F:	include/linux/frontswap.h
+
 FS-CACHE: LOCAL CACHING FOR NETWORK FILESYSTEMS
 M:	David Howells <dhowells@redhat.com>
 L:	linux-cachefs@redhat.com
@@ -3141,7 +3148,7 @@ F:	drivers/tty/hvc/
 
 HARDWARE MONITORING
 M:	Jean Delvare <khali@linux-fr.org>
-M:	Guenter Roeck <guenter.roeck@ericsson.com>
+M:	Guenter Roeck <linux@roeck-us.net>
 L:	lm-sensors@lm-sensors.org
 W:	http://www.lm-sensors.org/
 T:	quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-hwmon/
@@ -4099,6 +4106,8 @@ F:	drivers/scsi/53c700*
 LED SUBSYSTEM
 M:	Bryan Wu <bryan.wu@canonical.com>
 M:	Richard Purdie <rpurdie@rpsys.net>
+L:	linux-leds@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/linux-leds.git
 S:	Maintained
 F:	drivers/leds/
 F:	include/linux/leds.h
@@ -4416,6 +4425,13 @@ S:	Orphan
 F:	drivers/video/matrox/matroxfb_*
 F:	include/linux/matroxfb.h
 
+MAX16065 HARDWARE MONITOR DRIVER
+M:	Guenter Roeck <linux@roeck-us.net>
+L:	lm-sensors@lm-sensors.org
+S:	Maintained
+F:	Documentation/hwmon/max16065
+F:	drivers/hwmon/max16065.c
+
 MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 M:	"Hans J. Koch" <hjk@hansjkoch.de>
 L:	lm-sensors@lm-sensors.org
@@ -5154,7 +5170,7 @@ F:	drivers/leds/leds-pca9532.c
 F:	include/linux/leds-pca9532.h
 
 PCA9541 I2C BUS MASTER SELECTOR DRIVER
-M:	Guenter Roeck <guenter.roeck@ericsson.com>
+M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/muxes/i2c-mux-pca9541.c
@@ -5304,7 +5320,7 @@ F:	drivers/video/fb-puv3.c
 F:	drivers/rtc/rtc-puv3.c
 
 PMBUS HARDWARE MONITORING DRIVERS
-M:	Guenter Roeck <guenter.roeck@ericsson.com>
+M:	Guenter Roeck <linux@roeck-us.net>
 L:	lm-sensors@lm-sensors.org
 W:	http://www.lm-sensors.org/
 W:	http://www.roeck-us.net/linux/drivers/
@@ -7299,11 +7315,11 @@ F:	Documentation/DocBook/uio-howto.tmpl
 F:	drivers/uio/
 F:	include/linux/uio*.h
 
-UTIL-LINUX-NG PACKAGE
+UTIL-LINUX PACKAGE
 M:	Karel Zak <kzak@redhat.com>
-L:	util-linux-ng@vger.kernel.org
-W:	http://kernel.org/~kzak/util-linux-ng/
-T:	git git://git.kernel.org/pub/scm/utils/util-linux-ng/util-linux-ng.git
+L:	util-linux@vger.kernel.org
+W:	http://en.wikipedia.org/wiki/Util-linux
+T:	git git://git.kernel.org/pub/scm/utils/util-linux/util-linux.git
 S:	Maintained
 
 UVESAFB DRIVER

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 5
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Saber-toothed Squirrel
 
 # *DOCUMENTATION*

arch/arm/Kconfig

@@ -7,7 +7,6 @@ config ARM
 	select HAVE_IDE if PCI || ISA || PCMCIA
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
-	select CMA if (CPU_V6 || CPU_V6K || CPU_V7)
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION

arch/arm/mach-omap2/display.c

@@ -271,9 +271,9 @@ static struct platform_device *create_simple_dss_pdev(const char *pdev_name,
 		goto err;
 	}
 
-	r = omap_device_register(pdev);
+	r = platform_device_add(pdev);
 	if (r) {
-		pr_err("Could not register omap_device for %s\n", pdev_name);
+		pr_err("Could not register platform_device for %s\n", pdev_name);
 		goto err;
 	}
 

arch/arm/mach-shmobile/Kconfig

@@ -186,6 +186,12 @@ config SH_TIMER_TMU
 	help
 	  This enables build of the TMU timer driver.
 
+config EM_TIMER_STI
+	bool "STI timer driver"
+	default y
+	help
+	  This enables build of the STI timer driver.
+
 endmenu
 
 config SH_CLK_CPG

arch/arm/mm/dma-mapping.c

@@ -268,10 +268,8 @@ static int __init consistent_init(void)
 	unsigned long base = consistent_base;
 	unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
 
-#ifndef CONFIG_ARM_DMA_USE_IOMMU
-	if (cpu_architecture() >= CPU_ARCH_ARMv6)
+	if (IS_ENABLED(CONFIG_CMA) && !IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
 		return 0;
-#endif
 
 	consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
 	if (!consistent_pte) {
@@ -342,7 +340,7 @@ static int __init coherent_init(void)
 	struct page *page;
 	void *ptr;
 
-	if (cpu_architecture() < CPU_ARCH_ARMv6)
+	if (!IS_ENABLED(CONFIG_CMA))
 		return 0;
 
 	ptr = __alloc_from_contiguous(NULL, size, prot, &page);
@@ -704,7 +702,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 
 	if (arch_is_coherent() || nommu())
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
-	else if (cpu_architecture() < CPU_ARCH_ARMv6)
+	else if (!IS_ENABLED(CONFIG_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
 	else if (gfp & GFP_ATOMIC)
 		addr = __alloc_from_pool(dev, size, &page, caller);
@@ -773,7 +771,7 @@ void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 
 	if (arch_is_coherent() || nommu()) {
 		__dma_free_buffer(page, size);
-	} else if (cpu_architecture() < CPU_ARCH_ARMv6) {
+	} else if (!IS_ENABLED(CONFIG_CMA)) {
 		__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {

arch/avr32/kernel/signal.c

@@ -300,7 +300,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, struct thread_info *ti)
 	if ((sysreg_read(SR) & MODE_MASK) == MODE_SUPERVISOR)
 		syscall = 1;
 
-	if (ti->flags & _TIF_SIGPENDING))
+	if (ti->flags & _TIF_SIGPENDING)
 		do_signal(regs, syscall);
 
 	if (ti->flags & _TIF_NOTIFY_RESUME) {

arch/blackfin/kernel/process.c

@@ -173,7 +173,7 @@ asmlinkage int bfin_clone(struct pt_regs *regs)
 	unsigned long newsp;
 
 #ifdef __ARCH_SYNC_CORE_DCACHE
-	if (current->rt.nr_cpus_allowed == num_possible_cpus())
+	if (current->nr_cpus_allowed == num_possible_cpus())
 		set_cpus_allowed_ptr(current, cpumask_of(smp_processor_id()));
 #endif
 

arch/m68k/Kconfig

@@ -7,6 +7,8 @@ config M68K
 	select GENERIC_IRQ_SHOW
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
 	select GENERIC_CPU_DEVICES
+	select GENERIC_STRNCPY_FROM_USER if MMU
+	select GENERIC_STRNLEN_USER if MMU
 	select FPU if MMU
 	select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
 

arch/m68k/include/asm/Kbuild

@@ -1,2 +1,4 @@
 include include/asm-generic/Kbuild.asm
 header-y += cachectl.h
+
+generic-y += word-at-a-time.h

arch/m68k/include/asm/m528xsim.h

@@ -86,7 +86,7 @@
 /*
  *	QSPI module.
  */
-#define	MCFQSPI_IOBASE		(MCF_IPSBAR + 0x340)
+#define	MCFQSPI_BASE		(MCF_IPSBAR + 0x340)
 #define	MCFQSPI_SIZE		0x40
 
 #define	MCFQSPI_CS0		147

arch/m68k/include/asm/uaccess_mm.h

@@ -379,12 +379,15 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n)
 #define copy_from_user(to, from, n)	__copy_from_user(to, from, n)
 #define copy_to_user(to, from, n)	__copy_to_user(to, from, n)
 
-long strncpy_from_user(char *dst, const char __user *src, long count);
-long strnlen_user(const char __user *src, long n);
+#define user_addr_max() \
+	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+
+extern long strncpy_from_user(char *dst, const char __user *src, long count);
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
 unsigned long __clear_user(void __user *to, unsigned long n);
 
 #define clear_user	__clear_user
 
-#define strlen_user(str) strnlen_user(str, 32767)
-
 #endif /* _M68K_UACCESS_H */

arch/m68k/kernel/ptrace.c

@@ -286,7 +286,7 @@ asmlinkage void syscall_trace(void)
 	}
 }
 
-#ifdef CONFIG_COLDFIRE
+#if defined(CONFIG_COLDFIRE) || !defined(CONFIG_MMU)
 asmlinkage int syscall_trace_enter(void)
 {
 	int ret = 0;

arch/m68k/kernel/time.c

@@ -85,7 +85,7 @@ void __init time_init(void)
 	mach_sched_init(timer_interrupt);
 }
 
-#ifdef CONFIG_M68KCLASSIC
+#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
 
 u32 arch_gettimeoffset(void)
 {
@@ -108,4 +108,4 @@ static int __init rtc_init(void)
 
 module_init(rtc_init);
 
-#endif /* CONFIG_M68KCLASSIC */
+#endif /* CONFIG_ARCH_USES_GETTIMEOFFSET */

arch/m68k/lib/uaccess.c

@@ -103,80 +103,6 @@ unsigned long __generic_copy_to_user(void __user *to, const void *from,
 }
 EXPORT_SYMBOL(__generic_copy_to_user);
 
-/*
- * Copy a null terminated string from userspace.
- */
-long strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	char c;
-
-	if (count <= 0)
-		return count;
-
-	asm volatile ("\n"
-		"1:	"MOVES".b	(%2)+,%4\n"
-		"	move.b	%4,(%1)+\n"
-		"	jeq	2f\n"
-		"	subq.l	#1,%3\n"
-		"	jne	1b\n"
-		"2:	sub.l	%3,%0\n"
-		"3:\n"
-		"	.section .fixup,\"ax\"\n"
-		"	.even\n"
-		"10:	move.l	%5,%0\n"
-		"	jra	3b\n"
-		"	.previous\n"
-		"\n"
-		"	.section __ex_table,\"a\"\n"
-		"	.align	4\n"
-		"	.long	1b,10b\n"
-		"	.previous"
-		: "=d" (res), "+a" (dst), "+a" (src), "+r" (count), "=&d" (c)
-		: "i" (-EFAULT), "0" (count));
-
-	return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
- * Return the size of a string (including the ending 0)
- *
- * Return 0 on exception, a value greater than N if too long
- */
-long strnlen_user(const char __user *src, long n)
-{
-	char c;
-	long res;
-
-	asm volatile ("\n"
-		"1:	subq.l	#1,%1\n"
-		"	jmi	3f\n"
-		"2:	"MOVES".b	(%0)+,%2\n"
-		"	tst.b	%2\n"
-		"	jne	1b\n"
-		"	jra	4f\n"
-		"\n"
-		"3:	addq.l	#1,%0\n"
-		"4:	sub.l	%4,%0\n"
-		"5:\n"
-		"	.section .fixup,\"ax\"\n"
-		"	.even\n"
-		"20:	sub.l	%0,%0\n"
-		"	jra	5b\n"
-		"	.previous\n"
-		"\n"
-		"	.section __ex_table,\"a\"\n"
-		"	.align	4\n"
-		"	.long	2b,20b\n"
-		"	.previous\n"
-		: "=&a" (res), "+d" (n), "=&d" (c)
-		: "0" (src), "r" (src));
-
-	return res;
-}
-EXPORT_SYMBOL(strnlen_user);
-
 /*
  * Zero Userspace
  */

arch/m68k/platform/68328/timers.c

@@ -53,6 +53,7 @@
 #endif
 
 static u32 m68328_tick_cnt;
+static irq_handler_t timer_interrupt;
 
 /***************************************************************************/
 
@@ -62,7 +63,7 @@ static irqreturn_t hw_tick(int irq, void *dummy)
 	TSTAT &= 0;
 
 	m68328_tick_cnt += TICKS_PER_JIFFY;
-	return arch_timer_interrupt(irq, dummy);
+	return timer_interrupt(irq, dummy);
 }
 
 /***************************************************************************/
@@ -99,7 +100,7 @@ static struct clocksource m68328_clk = {
 
 /***************************************************************************/
 
-void hw_timer_init(void)
+void hw_timer_init(irq_handler_t handler)
 {
 	/* disable timer 1 */
 	TCTL = 0;
@@ -115,6 +116,7 @@ void hw_timer_init(void)
 	/* Enable timer 1 */
 	TCTL |= TCTL_TEN;
 	clocksource_register_hz(&m68328_clk, TICKS_PER_JIFFY*HZ);
+	timer_interrupt = handler;
 }
 
 /***************************************************************************/

arch/m68k/platform/68360/config.c

@@ -35,6 +35,7 @@ extern void m360_cpm_reset(void);
 #define OSCILLATOR  (unsigned long int)33000000
 #endif
 
+static irq_handler_t timer_interrupt;
 unsigned long int system_clock;
 
 extern QUICC *pquicc;
@@ -52,7 +53,7 @@ static irqreturn_t hw_tick(int irq, void *dummy)
 
   pquicc->timer_ter1 = 0x0002; /* clear timer event */
 
-  return arch_timer_interrupt(irq, dummy);
+  return timer_interrupt(irq, dummy);
 }
 
 static struct irqaction m68360_timer_irq = {
@@ -61,7 +62,7 @@ static struct irqaction m68360_timer_irq = {
 	.handler = hw_tick,
 };
 
-void hw_timer_init(void)
+void hw_timer_init(irq_handler_t handler)
 {
   unsigned char prescaler;
   unsigned short tgcr_save;
@@ -94,6 +95,8 @@ void hw_timer_init(void)
 
   pquicc->timer_ter1 = 0x0003; /* clear timer events */
 
+  timer_interrupt = handler;
+
   /* enable timer 1 interrupt in CIMR */
   setup_irq(CPMVEC_TIMER1, &m68360_timer_irq);
 

arch/parisc/Makefile

@@ -21,6 +21,7 @@ KBUILD_DEFCONFIG := default_defconfig
 
 NM		= sh $(srctree)/arch/parisc/nm
 CHECKFLAGS	+= -D__hppa__=1
+LIBGCC		= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 
 MACHINE		:= $(shell uname -m)
 ifeq ($(MACHINE),parisc*)
@@ -79,7 +80,7 @@ kernel-y			:= mm/ kernel/ math-emu/
 kernel-$(CONFIG_HPUX)		+= hpux/
 
 core-y	+= $(addprefix arch/parisc/, $(kernel-y))
-libs-y	+= arch/parisc/lib/ `$(CC) -print-libgcc-file-name`
+libs-y	+= arch/parisc/lib/ $(LIBGCC)
 
 drivers-$(CONFIG_OPROFILE)		+= arch/parisc/oprofile/
 

arch/parisc/include/asm/Kbuild

@@ -1,3 +1,4 @@
 include include/asm-generic/Kbuild.asm
 
 header-y += pdc.h
+generic-y += word-at-a-time.h

arch/parisc/include/asm/bug.h

@@ -1,6 +1,8 @@
 #ifndef _PARISC_BUG_H
 #define _PARISC_BUG_H
 
+#include <linux/kernel.h>	/* for BUGFLAG_TAINT */
+
 /*
  * Tell the user there is some problem.
  * The offending file and line are encoded in the __bug_table section.

arch/powerpc/kernel/module_32.c

@@ -176,8 +176,8 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr,
 
 static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
 {
-	if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16)
-	    && entry->jump[1] == 0x396b0000 + (val & 0xffff))
+	if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16)
+	    && entry->jump[1] == 0x398c0000 + (val & 0xffff))
 		return 1;
 	return 0;
 }
@@ -204,10 +204,9 @@ static uint32_t do_plt_call(void *location,
 		entry++;
 	}
 
-	/* Stolen from Paul Mackerras as well... */
-	entry->jump[0] = 0x3d600000+((val+0x8000)>>16);	/* lis r11,sym@ha */
-	entry->jump[1] = 0x396b0000 + (val&0xffff);	/* addi r11,r11,sym@l*/
-	entry->jump[2] = 0x7d6903a6;			/* mtctr r11 */
+	entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */
+	entry->jump[1] = 0x398c0000 + (val&0xffff);     /* addi r12,r12,sym@l*/
+	entry->jump[2] = 0x7d8903a6;                    /* mtctr r12 */
 	entry->jump[3] = 0x4e800420;			/* bctr */
 
 	DEBUGP("Initialized plt for 0x%x at %p\n", val, entry);

arch/powerpc/kernel/time.c

@@ -475,6 +475,7 @@ void timer_interrupt(struct pt_regs * regs)
 	struct pt_regs *old_regs;
 	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
 	struct clock_event_device *evt = &__get_cpu_var(decrementers);
+	u64 now;
 
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
@@ -509,9 +510,16 @@ void timer_interrupt(struct pt_regs * regs)
 		irq_work_run();
 	}
 
+	now = get_tb_or_rtc();
+	if (now >= *next_tb) {
 		*next_tb = ~(u64)0;
 		if (evt->event_handler)
 			evt->event_handler(evt);
+	} else {
+		now = *next_tb - now;
+		if (now <= DECREMENTER_MAX)
+			set_dec((int)now);
+	}
 
 #ifdef CONFIG_PPC64
 	/* collect purr register values often, for accurate calculations */

arch/sh/Kconfig

@@ -32,6 +32,8 @@ config SUPERH
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
 	  and consumer electronics; it was also used in the Sega Dreamcast

arch/sh/Makefile

@@ -9,6 +9,12 @@
 # License.  See the file "COPYING" in the main directory of this archive
 # for more details.
 #
+ifneq ($(SUBARCH),$(ARCH))
+  ifeq ($(CROSS_COMPILE),)
+    CROSS_COMPILE := $(call cc-cross-prefix, $(UTS_MACHINE)-linux-  $(UTS_MACHINE)-linux-gnu-  $(UTS_MACHINE)-unknown-linux-gnu-)
+  endif
+endif
+
 isa-y					:= any
 isa-$(CONFIG_SH_DSP)			:= sh
 isa-$(CONFIG_CPU_SH2)			:= sh2
@@ -106,19 +112,13 @@ LDFLAGS_vmlinux		+= --defsym phys_stext=_stext-$(CONFIG_PAGE_OFFSET) \
 KBUILD_DEFCONFIG	:= cayman_defconfig
 endif
 
-ifneq ($(SUBARCH),$(ARCH))
-  ifeq ($(CROSS_COMPILE),)
-    CROSS_COMPILE := $(call cc-cross-prefix, $(UTS_MACHINE)-linux-  $(UTS_MACHINE)-linux-gnu-  $(UTS_MACHINE)-unknown-linux-gnu-)
-  endif
-endif
-
 ifdef CONFIG_CPU_LITTLE_ENDIAN
 ld-bfd			:= elf32-$(UTS_MACHINE)-linux
-LDFLAGS_vmlinux		+= --defsym 'jiffies=jiffies_64' --oformat $(ld-bfd)
+LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64 --oformat $(ld-bfd)
 LDFLAGS			+= -EL
 else
 ld-bfd			:= elf32-$(UTS_MACHINE)big-linux
-LDFLAGS_vmlinux		+= --defsym 'jiffies=jiffies_64+4' --oformat $(ld-bfd)
+LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64+4 --oformat $(ld-bfd)
 LDFLAGS			+= -EB
 endif
 

arch/sh/include/asm/Kbuild

@@ -1,5 +1,39 @@
 include include/asm-generic/Kbuild.asm
 
+generic-y += bitsperlong.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += delay.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += fcntl.h
+generic-y += ioctl.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += mman.h
+generic-y += msgbuf.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += shmbuf.h
+generic-y += siginfo.h
+generic-y += sizes.h
+generic-y += socket.h
+generic-y += statfs.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += ucontext.h
+generic-y += xor.h
+
 header-y += cachectl.h
 header-y += cpu-features.h
 header-y += hw_breakpoint.h

arch/sh/include/asm/bitsperlong.h

@@ -1 +0,0 @@
-#include <asm-generic/bitsperlong.h>

arch/sh/include/asm/cputime.h

@@ -1,6 +0,0 @@
-#ifndef __SH_CPUTIME_H
-#define __SH_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __SH_CPUTIME_H */

arch/sh/include/asm/current.h

@@ -1 +0,0 @@
-#include <asm-generic/current.h>

arch/sh/include/asm/delay.h

@@ -1 +0,0 @@
-#include <asm-generic/delay.h>

arch/sh/include/asm/div64.h

@@ -1 +0,0 @@
-#include <asm-generic/div64.h>

arch/sh/include/asm/emergency-restart.h

@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */

arch/sh/include/asm/errno.h

@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_ERRNO_H
-#define __ASM_SH_ERRNO_H
-
-#include <asm-generic/errno.h>
-
-#endif /* __ASM_SH_ERRNO_H */

arch/sh/include/asm/fcntl.h

@@ -1 +0,0 @@
-#include <asm-generic/fcntl.h>

arch/sh/include/asm/ioctl.h

@@ -1 +0,0 @@
-#include <asm-generic/ioctl.h>

arch/sh/include/asm/ipcbuf.h

@@ -1 +0,0 @@
-#include <asm-generic/ipcbuf.h>

arch/sh/include/asm/irq_regs.h

@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>

arch/sh/include/asm/kvm_para.h

@@ -1 +0,0 @@
-#include <asm-generic/kvm_para.h>

arch/sh/include/asm/local.h

@@ -1,7 +0,0 @@
-#ifndef __ASM_SH_LOCAL_H
-#define __ASM_SH_LOCAL_H
-
-#include <asm-generic/local.h>
-
-#endif /* __ASM_SH_LOCAL_H */
-

arch/sh/include/asm/local64.h

@@ -1 +0,0 @@
-#include <asm-generic/local64.h>

arch/sh/include/asm/mman.h

@@ -1 +0,0 @@
-#include <asm-generic/mman.h>

arch/sh/include/asm/msgbuf.h

@@ -1 +0,0 @@
-#include <asm-generic/msgbuf.h>

arch/sh/include/asm/param.h

@@ -1 +0,0 @@
-#include <asm-generic/param.h>

arch/sh/include/asm/parport.h

@@ -1 +0,0 @@
-#include <asm-generic/parport.h>

arch/sh/include/asm/percpu.h

@@ -1,6 +0,0 @@
-#ifndef __ARCH_SH_PERCPU
-#define __ARCH_SH_PERCPU
-
-#include <asm-generic/percpu.h>
-
-#endif /* __ARCH_SH_PERCPU */

arch/sh/include/asm/poll.h

@@ -1 +0,0 @@
-#include <asm-generic/poll.h>

arch/sh/include/asm/resource.h

@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_RESOURCE_H
-#define __ASM_SH_RESOURCE_H
-
-#include <asm-generic/resource.h>
-
-#endif /* __ASM_SH_RESOURCE_H */

arch/sh/include/asm/scatterlist.h

@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_SCATTERLIST_H
-#define __ASM_SH_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* __ASM_SH_SCATTERLIST_H */

arch/sh/include/asm/sembuf.h

@@ -1 +0,0 @@
-#include <asm-generic/sembuf.h>

arch/sh/include/asm/serial.h

@@ -1 +0,0 @@
-#include <asm-generic/serial.h>

arch/sh/include/asm/shmbuf.h

@@ -1 +0,0 @@
-#include <asm-generic/shmbuf.h>

arch/sh/include/asm/siginfo.h

@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_SIGINFO_H
-#define __ASM_SH_SIGINFO_H
-
-#include <asm-generic/siginfo.h>
-
-#endif /* __ASM_SH_SIGINFO_H */

arch/sh/include/asm/sizes.h

@@ -1 +0,0 @@
-#include <asm-generic/sizes.h>

arch/sh/include/asm/socket.h

@@ -1 +0,0 @@
-#include <asm-generic/socket.h>

arch/sh/include/asm/statfs.h

@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_STATFS_H
-#define __ASM_SH_STATFS_H
-
-#include <asm-generic/statfs.h>
-
-#endif /* __ASM_SH_STATFS_H */

arch/sh/include/asm/termbits.h

@@ -1 +0,0 @@
-#include <asm-generic/termbits.h>

arch/sh/include/asm/termios.h

@@ -1 +0,0 @@
-#include <asm-generic/termios.h>

arch/sh/include/asm/uaccess.h

@@ -25,6 +25,8 @@
 	(__chk_user_ptr(addr),		\
 	 __access_ok((unsigned long __force)(addr), (size)))
 
+#define user_addr_max()	(current_thread_info()->addr_limit.seg)
+
 /*
  * Uh, these should become the main single-value transfer routines ...
  * They automatically use the right size if we just have the right
@@ -100,6 +102,11 @@ struct __large_struct { unsigned long buf[100]; };
 # include "uaccess_64.h"
 #endif
 
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
 /* Generic arbitrary sized copy.  */
 /* Return the number of bytes NOT copied */
 __kernel_size_t __copy_user(void *to, const void *from, __kernel_size_t n);
@@ -137,37 +144,6 @@ __kernel_size_t __clear_user(void *addr, __kernel_size_t size);
 	__cl_size;							\
 })
 
-/**
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst:   Destination address, in kernel space.  This buffer must be at
- *         least @count bytes long.
- * @src:   Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-#define strncpy_from_user(dest,src,count)				\
-({									\
-	unsigned long __sfu_src = (unsigned long)(src);			\
-	int __sfu_count = (int)(count);					\
-	long __sfu_res = -EFAULT;					\
-									\
-	if (__access_ok(__sfu_src, __sfu_count))			\
-		__sfu_res = __strncpy_from_user((unsigned long)(dest),	\
-				__sfu_src, __sfu_count);		\
-									\
-	__sfu_res;							\
-})
-
 static inline unsigned long
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
@@ -192,43 +168,6 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
 	return __copy_size;
 }
 
-/**
- * strnlen_user: - Get the size of a string in user space.
- * @s: The string to measure.
- * @n: The maximum valid length
- *
- * Context: User context only.  This function may sleep.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- * If the string is too long, returns a value greater than @n.
- */
-static inline long strnlen_user(const char __user *s, long n)
-{
-	if (!__addr_ok(s))
-		return 0;
-	else
-		return __strnlen_user(s, n);
-}
-
-/**
- * strlen_user: - Get the size of a string in user space.
- * @str: The string to measure.
- *
- * Context: User context only.  This function may sleep.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- *
- * If there is a limit on the length of a valid string, you may wish to
- * consider using strnlen_user() instead.
- */
-#define strlen_user(str)	strnlen_user(str, ~0UL >> 1)
-
 /*
  * The exception table consists of pairs of addresses: the first is the
  * address of an instruction that is allowed to fault, and the second is

arch/sh/include/asm/uaccess_32.h

@@ -170,79 +170,4 @@ __asm__ __volatile__( \
 
 extern void __put_user_unknown(void);
 
-static inline int
-__strncpy_from_user(unsigned long __dest, unsigned long __user __src, int __count)
-{
-	__kernel_size_t res;
-	unsigned long __dummy, _d, _s, _c;
-
-	__asm__ __volatile__(
-		"9:\n"
-		"mov.b	@%2+, %1\n\t"
-		"cmp/eq	#0, %1\n\t"
-		"bt/s	2f\n"
-		"1:\n"
-		"mov.b	%1, @%3\n\t"
-		"dt	%4\n\t"
-		"bf/s	9b\n\t"
-		" add	#1, %3\n\t"
-		"2:\n\t"
-		"sub	%4, %0\n"
-		"3:\n"
-		".section .fixup,\"ax\"\n"
-		"4:\n\t"
-		"mov.l	5f, %1\n\t"
-		"jmp	@%1\n\t"
-		" mov	%9, %0\n\t"
-		".balign 4\n"
-		"5:	.long 3b\n"
-		".previous\n"
-		".section __ex_table,\"a\"\n"
-		"	.balign 4\n"
-		"	.long 9b,4b\n"
-		".previous"
-		: "=r" (res), "=&z" (__dummy), "=r" (_s), "=r" (_d), "=r"(_c)
-		: "0" (__count), "2" (__src), "3" (__dest), "4" (__count),
-		  "i" (-EFAULT)
-		: "memory", "t");
-
-	return res;
-}
-
-/*
- * Return the size of a string (including the ending 0 even when we have
- * exceeded the maximum string length).
- */
-static inline long __strnlen_user(const char __user *__s, long __n)
-{
-	unsigned long res;
-	unsigned long __dummy;
-
-	__asm__ __volatile__(
-		"1:\t"
-		"mov.b	@(%0,%3), %1\n\t"
-		"cmp/eq	%4, %0\n\t"
-		"bt/s	2f\n\t"
-		" add	#1, %0\n\t"
-		"tst	%1, %1\n\t"
-		"bf	1b\n\t"
-		"2:\n"
-		".section .fixup,\"ax\"\n"
-		"3:\n\t"
-		"mov.l	4f, %1\n\t"
-		"jmp	@%1\n\t"
-		" mov	#0, %0\n"
-		".balign 4\n"
-		"4:	.long 2b\n"
-		".previous\n"
-		".section __ex_table,\"a\"\n"
-		"	.balign 4\n"
-		"	.long 1b,3b\n"
-		".previous"
-		: "=z" (res), "=&r" (__dummy)
-		: "0" (0), "r" (__s), "r" (__n)
-		: "t");
-	return res;
-}
-
 #endif /* __ASM_SH_UACCESS_32_H */

arch/sh/include/asm/uaccess_64.h

@@ -84,8 +84,4 @@ extern long __put_user_asm_l(void *, long);
 extern long __put_user_asm_q(void *, long);
 extern void __put_user_unknown(void);
 
-extern long __strnlen_user(const char *__s, long __n);
-extern int __strncpy_from_user(unsigned long __dest,
-	       unsigned long __user __src, int __count);
-
 #endif /* __ASM_SH_UACCESS_64_H */

arch/sh/include/asm/ucontext.h

@@ -1 +0,0 @@
-#include <asm-generic/ucontext.h>

arch/sh/include/asm/word-at-a-time.h

@@ -0,0 +1,53 @@
+#ifndef __ASM_SH_WORD_AT_A_TIME_H
+#define __ASM_SH_WORD_AT_A_TIME_H
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+# include <asm-generic/word-at-a-time.h>
+#else
+/*
+ * Little-endian version cribbed from x86.
+ */
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	long a = (0x0ff0001+mask) >> 23;
+	/* Fix the 1 for 00 case */
+	return a & mask;
+}
+
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	return count_masked_bytes(mask);
+}
+#endif
+
+#endif

arch/sh/include/asm/xor.h

@@ -1 +0,0 @@
-#include <asm-generic/xor.h>

arch/sh/include/cpu-sh2a/cpu/ubc.h

@@ -1,28 +0,0 @@
-/*
- * 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 */

arch/sh/kernel/cpu/sh5/entry.S

@@ -1568,86 +1568,6 @@ ___clear_user_exit:
 
 #endif /* CONFIG_MMU */
 
-/*
- * int __strncpy_from_user(unsigned long __dest, unsigned long __src,
- *			   int __count)
- *
- * Inputs:
- * (r2)  target address
- * (r3)  source address
- * (r4)  maximum size in bytes
- *
- * Ouputs:
- * (*r2) copied data
- * (r2)  -EFAULT (in case of faulting)
- *       copied data (otherwise)
- */
-	.global	__strncpy_from_user
-__strncpy_from_user:
-	pta	___strncpy_from_user1, tr0
-	pta	___strncpy_from_user_done, tr1
-	or	r4, ZERO, r5		/* r5 = original count */
-	beq/u	r4, r63, tr1		/* early exit if r4==0 */
-	movi	-(EFAULT), r6		/* r6 = reply, no real fixup */
-	or	ZERO, ZERO, r7		/* r7 = data, clear top byte of data */
-
-___strncpy_from_user1:
-	ld.b	r3, 0, r7		/* Fault address: only in reading */
-	st.b	r2, 0, r7
-	addi	r2, 1, r2
-	addi	r3, 1, r3
-	beq/u	ZERO, r7, tr1
-	addi	r4, -1, r4		/* return real number of copied bytes */
-	bne/l	ZERO, r4, tr0
-
-___strncpy_from_user_done:
-	sub	r5, r4, r6		/* If done, return copied */
-
-___strncpy_from_user_exit:
-	or	r6, ZERO, r2
-	ptabs	LINK, tr0
-	blink	tr0, ZERO
-
-/*
- * extern long __strnlen_user(const char *__s, long __n)
- *
- * Inputs:
- * (r2)  source address
- * (r3)  source size in bytes
- *
- * Ouputs:
- * (r2)  -EFAULT (in case of faulting)
- *       string length (otherwise)
- */
-	.global	__strnlen_user
-__strnlen_user:
-	pta	___strnlen_user_set_reply, tr0
-	pta	___strnlen_user1, tr1
-	or	ZERO, ZERO, r5		/* r5 = counter */
-	movi	-(EFAULT), r6		/* r6 = reply, no real fixup */
-	or	ZERO, ZERO, r7		/* r7 = data, clear top byte of data */
-	beq	r3, ZERO, tr0
-
-___strnlen_user1:
-	ldx.b	r2, r5, r7		/* Fault address: only in reading */
-	addi	r3, -1, r3		/* No real fixup */
-	addi	r5, 1, r5
-	beq	r3, ZERO, tr0
-	bne	r7, ZERO, tr1
-! The line below used to be active.  This meant led to a junk byte lying between each pair
-! of entries in the argv & envp structures in memory.  Whilst the program saw the right data
-! via the argv and envp arguments to main, it meant the 'flat' representation visible through
-! /proc/$pid/cmdline was corrupt, causing trouble with ps, for example.
-!	addi	r5, 1, r5		/* Include '\0' */
-
-___strnlen_user_set_reply:
-	or	r5, ZERO, r6		/* If done, return counter */
-
-___strnlen_user_exit:
-	or	r6, ZERO, r2
-	ptabs	LINK, tr0
-	blink	tr0, ZERO
-
 /*
  * extern long __get_user_asm_?(void *val, long addr)
  *
@@ -1982,8 +1902,6 @@ asm_uaccess_start:
 	.long	___copy_user2, ___copy_user_exit
 	.long	___clear_user1, ___clear_user_exit
 #endif
-	.long	___strncpy_from_user1, ___strncpy_from_user_exit
-	.long	___strnlen_user1, ___strnlen_user_exit
 	.long	___get_user_asm_b1, ___get_user_asm_b_exit
 	.long	___get_user_asm_w1, ___get_user_asm_w_exit
 	.long	___get_user_asm_l1, ___get_user_asm_l_exit

arch/sh/kernel/process.c

@@ -4,6 +4,7 @@
 #include <linux/sched.h>
 #include <linux/export.h>
 #include <linux/stackprotector.h>
+#include <asm/fpu.h>
 
 struct kmem_cache *task_xstate_cachep = NULL;
 unsigned int xstate_size;

arch/sh/kernel/process_64.c

@@ -33,6 +33,7 @@
 #include <asm/switch_to.h>
 
 struct task_struct *last_task_used_math = NULL;
+struct pt_regs fake_swapper_regs = { 0, };
 
 void show_regs(struct pt_regs *regs)
 {

arch/sh/kernel/sh_ksyms_64.c

@@ -32,8 +32,6 @@ EXPORT_SYMBOL(__get_user_asm_b);
 EXPORT_SYMBOL(__get_user_asm_w);
 EXPORT_SYMBOL(__get_user_asm_l);
 EXPORT_SYMBOL(__get_user_asm_q);
-EXPORT_SYMBOL(__strnlen_user);
-EXPORT_SYMBOL(__strncpy_from_user);
 EXPORT_SYMBOL(__clear_user);
 EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(__copy_user);

arch/tile/include/asm/thread_info.h

@@ -91,11 +91,6 @@ extern void smp_nap(void);
 /* Enable interrupts racelessly and nap forever: helper for cpu_idle(). */
 extern void _cpu_idle(void);
 
-/* Switch boot idle thread to a freshly-allocated stack and free old stack. */
-extern void cpu_idle_on_new_stack(struct thread_info *old_ti,
-				  unsigned long new_sp,
-				  unsigned long new_ss10);
-
 #else /* __ASSEMBLY__ */
 
 /*

arch/tile/kernel/entry.S

@@ -68,20 +68,6 @@ STD_ENTRY(KBacktraceIterator_init_current)
 	jrp lr   /* keep backtracer happy */
 	STD_ENDPROC(KBacktraceIterator_init_current)
 
-/*
- * Reset our stack to r1/r2 (sp and ksp0+cpu respectively), then
- * free the old stack (passed in r0) and re-invoke cpu_idle().
- * We update sp and ksp0 simultaneously to avoid backtracer warnings.
- */
-STD_ENTRY(cpu_idle_on_new_stack)
-	{
-	 move sp, r1
-	 mtspr SPR_SYSTEM_SAVE_K_0, r2
-	}
-	jal free_thread_info
-	j cpu_idle
-	STD_ENDPROC(cpu_idle_on_new_stack)
-
 /* Loop forever on a nap during SMP boot. */
 STD_ENTRY(smp_nap)
 	nap

arch/tile/kernel/setup.c

@@ -29,6 +29,7 @@
 #include <linux/smp.h>
 #include <linux/timex.h>
 #include <linux/hugetlb.h>
+#include <linux/start_kernel.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/cacheflush.h>

arch/x86/boot/header.S

@@ -94,8 +94,8 @@ bs_die:
 
 	.section ".bsdata", "a"
 bugger_off_msg:
-	.ascii	"Direct booting from floppy is no longer supported.\r\n"
-	.ascii	"Please use a boot loader program instead.\r\n"
+	.ascii	"Direct floppy boot is not supported. "
+	.ascii	"Use a boot loader program instead.\r\n"
 	.ascii	"\n"
 	.ascii	"Remove disk and press any key to reboot ...\r\n"
 	.byte	0
@@ -111,7 +111,7 @@ coff_header:
 #else
 	.word	0x8664				# x86-64
 #endif
-	.word	2				# nr_sections
+	.word	3				# nr_sections
 	.long	0 				# TimeDateStamp
 	.long	0				# PointerToSymbolTable
 	.long	1				# NumberOfSymbols
@@ -158,8 +158,8 @@ extra_header_fields:
 #else
 	.quad	0				# ImageBase
 #endif
-	.long	0x1000				# SectionAlignment
-	.long	0x200				# FileAlignment
+	.long	0x20				# SectionAlignment
+	.long	0x20				# FileAlignment
 	.word	0				# MajorOperatingSystemVersion
 	.word	0				# MinorOperatingSystemVersion
 	.word	0				# MajorImageVersion
@@ -200,8 +200,10 @@ extra_header_fields:
 
 	# Section table
 section_table:
-	.ascii	".text"
-	.byte	0
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".setup"
 	.byte	0
 	.byte	0
 	.long	0
@@ -217,9 +219,8 @@ section_table:
 
 	#
 	# The EFI application loader requires a relocation section
-	# because EFI applications must be relocatable. But since
-	# we don't need the loader to fixup any relocs for us, we
-	# just create an empty (zero-length) .reloc section header.
+	# because EFI applications must be relocatable. The .reloc
+	# offset & size fields are filled in by build.c.
 	#
 	.ascii	".reloc"
 	.byte	0
@@ -233,6 +234,25 @@ section_table:
 	.word	0				# NumberOfRelocations
 	.word	0				# NumberOfLineNumbers
 	.long	0x42100040			# Characteristics (section flags)
+
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".text"
+	.byte	0
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0x0				# startup_{32,64}
+	.long	0				# Size of initialized data
+						# on disk
+	.long	0x0				# startup_{32,64}
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0x60500020			# Characteristics (section flags)
+
 #endif /* CONFIG_EFI_STUB */
 
 	# Kernel attributes; used by setup.  This is part 1 of the

arch/x86/boot/tools/build.c

@@ -50,6 +50,8 @@ typedef unsigned int   u32;
 u8 buf[SETUP_SECT_MAX*512];
 int is_big_kernel;
 
+#define PECOFF_RELOC_RESERVE 0x20
+
 /*----------------------------------------------------------------------*/
 
 static const u32 crctab32[] = {
@@ -133,11 +135,103 @@ static void usage(void)
 	die("Usage: build setup system [> image]");
 }
 
+#ifdef CONFIG_EFI_STUB
+
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+	unsigned int pe_header;
+	unsigned short num_sections;
+	u8 *section;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+	num_sections = get_unaligned_le16(&buf[pe_header + 6]);
+
+#ifdef CONFIG_X86_32
+	section = &buf[pe_header + 0xa8];
+#else
+	section = &buf[pe_header + 0xb8];
+#endif
+
+	while (num_sections > 0) {
+		if (strncmp((char*)section, section_name, 8) == 0) {
+			/* section header size field */
+			put_unaligned_le32(size, section + 0x8);
+
+			/* section header vma field */
+			put_unaligned_le32(offset, section + 0xc);
+
+			/* section header 'size of initialised data' field */
+			put_unaligned_le32(size, section + 0x10);
+
+			/* section header 'file offset' field */
+			put_unaligned_le32(offset, section + 0x14);
+
+			break;
+		}
+		section += 0x28;
+		num_sections--;
+	}
+}
+
+static void update_pecoff_setup_and_reloc(unsigned int size)
+{
+	u32 setup_offset = 0x200;
+	u32 reloc_offset = size - PECOFF_RELOC_RESERVE;
+	u32 setup_size = reloc_offset - setup_offset;
+
+	update_pecoff_section_header(".setup", setup_offset, setup_size);
+	update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
+
+	/*
+	 * Modify .reloc section contents with a single entry. The
+	 * relocation is applied to offset 10 of the relocation section.
+	 */
+	put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
+	put_unaligned_le32(10, &buf[reloc_offset + 4]);
+}
+
+static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
+{
+	unsigned int pe_header;
+	unsigned int text_sz = file_sz - text_start;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+
+	/* Size of image */
+	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
+
+	/*
+	 * Size of code: Subtract the size of the first sector (512 bytes)
+	 * which includes the header.
+	 */
+	put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]);
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Address of entry point.
+	 *
+	 * The EFI stub entry point is +16 bytes from the start of
+	 * the .text section.
+	 */
+	put_unaligned_le32(text_start + 16, &buf[pe_header + 0x28]);
+#else
+	/*
+	 * Address of entry point. startup_32 is at the beginning and
+	 * the 64-bit entry point (startup_64) is always 512 bytes
+	 * after. The EFI stub entry point is 16 bytes after that, as
+	 * the first instruction allows legacy loaders to jump over
+	 * the EFI stub initialisation
+	 */
+	put_unaligned_le32(text_start + 528, &buf[pe_header + 0x28]);
+#endif /* CONFIG_X86_32 */
+
+	update_pecoff_section_header(".text", text_start, text_sz);
+}
+
+#endif /* CONFIG_EFI_STUB */
+
 int main(int argc, char ** argv)
 {
-#ifdef CONFIG_EFI_STUB
-	unsigned int file_sz, pe_header;
-#endif
 	unsigned int i, sz, setup_sectors;
 	int c;
 	u32 sys_size;
@@ -163,6 +257,12 @@ int main(int argc, char ** argv)
 		die("Boot block hasn't got boot flag (0xAA55)");
 	fclose(file);
 
+#ifdef CONFIG_EFI_STUB
+	/* Reserve 0x20 bytes for .reloc section */
+	memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+	c += PECOFF_RELOC_RESERVE;
+#endif
+
 	/* Pad unused space with zeros */
 	setup_sectors = (c + 511) / 512;
 	if (setup_sectors < SETUP_SECT_MIN)
@@ -170,6 +270,10 @@ int main(int argc, char ** argv)
 	i = setup_sectors*512;
 	memset(buf+c, 0, i-c);
 
+#ifdef CONFIG_EFI_STUB
+	update_pecoff_setup_and_reloc(i);
+#endif
+
 	/* Set the default root device */
 	put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
 
@@ -194,66 +298,8 @@ int main(int argc, char ** argv)
 	put_unaligned_le32(sys_size, &buf[0x1f4]);
 
 #ifdef CONFIG_EFI_STUB
-	file_sz = sz + i + ((sys_size * 16) - sz);
-
-	pe_header = get_unaligned_le32(&buf[0x3c]);
-
-	/* Size of image */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
-	/*
-	 * Subtract the size of the first section (512 bytes) which
-	 * includes the header and .reloc section. The remaining size
-	 * is that of the .text section.
-	 */
-	file_sz -= 512;
-
-	/* Size of code */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0x1c]);
-
-#ifdef CONFIG_X86_32
-	/*
-	 * Address of entry point.
-	 *
-	 * The EFI stub entry point is +16 bytes from the start of
-	 * the .text section.
-	 */
-	put_unaligned_le32(i + 16, &buf[pe_header + 0x28]);
-
-	/* .text size */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]);
-
-	/* .text vma */
-	put_unaligned_le32(0x200, &buf[pe_header + 0xb4]);
-
-	/* .text size of initialised data */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0xb8]);
-
-	/* .text file offset */
-	put_unaligned_le32(0x200, &buf[pe_header + 0xbc]);
-#else
-	/*
-	 * Address of entry point. startup_32 is at the beginning and
-	 * the 64-bit entry point (startup_64) is always 512 bytes
-	 * after. The EFI stub entry point is 16 bytes after that, as
-	 * the first instruction allows legacy loaders to jump over
-	 * the EFI stub initialisation
-	 */
-	put_unaligned_le32(i + 528, &buf[pe_header + 0x28]);
-
-	/* .text size */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]);
-
-	/* .text vma */
-	put_unaligned_le32(0x200, &buf[pe_header + 0xc4]);
-
-	/* .text size of initialised data */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0xc8]);
-
-	/* .text file offset */
-	put_unaligned_le32(0x200, &buf[pe_header + 0xcc]);
-#endif /* CONFIG_X86_32 */
-#endif /* CONFIG_EFI_STUB */
+	update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+#endif
 
 	crc = partial_crc32(buf, i, crc);
 	if (fwrite(buf, 1, i, stdout) != i)

arch/x86/crypto/aesni-intel_asm.S

@@ -2460,10 +2460,12 @@ ENTRY(aesni_cbc_dec)
 	pxor IN3, STATE4
 	movaps IN4, IV
 #else
-	pxor (INP), STATE2
-	pxor 0x10(INP), STATE3
 	pxor IN1, STATE4
 	movaps IN2, IV
+	movups (INP), IN1
+	pxor IN1, STATE2
+	movups 0x10(INP), IN2
+	pxor IN2, STATE3
 #endif
 	movups STATE1, (OUTP)
 	movups STATE2, 0x10(OUTP)

arch/x86/include/asm/nmi.h

@@ -54,6 +54,20 @@ struct nmiaction {
 	__register_nmi_handler((t), &fn##_na);	\
 })
 
+/*
+ * For special handlers that register/unregister in the
+ * init section only.  This should be considered rare.
+ */
+#define register_nmi_handler_initonly(t, fn, fg, n)		\
+({							\
+	static struct nmiaction fn##_na __initdata = {		\
+		.handler = (fn),			\
+		.name = (n),				\
+		.flags = (fg),				\
+	};						\
+	__register_nmi_handler((t), &fn##_na);	\
+})
+
 int __register_nmi_handler(unsigned int, struct nmiaction *);
 
 void unregister_nmi_handler(unsigned int, const char *);

arch/x86/include/asm/uaccess.h

@@ -34,8 +34,7 @@
 
 #define user_addr_max() (current_thread_info()->addr_limit.seg)
 #define __addr_ok(addr) 	\
-	((unsigned long __force)(addr) <		\
-	 (current_thread_info()->addr_limit.seg))
+	((unsigned long __force)(addr) < user_addr_max())
 
 /*
  * Test whether a block of memory is a valid user space address.
@@ -47,14 +46,14 @@
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
 
-#define __range_not_ok(addr, size)					\
+#define __range_not_ok(addr, size, limit)				\
 ({									\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
 	    : "=&r" (flag), "=r" (roksum)				\
 	    : "1" (addr), "g" ((long)(size)),				\
-	      "rm" (current_thread_info()->addr_limit.seg));		\
+	      "rm" (limit));						\
 	flag;								\
 })
 
@@ -77,7 +76,8 @@
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
  */
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+	(likely(__range_not_ok(addr, size, user_addr_max()) == 0))
 
 /*
  * The exception table consists of pairs of addresses relative to the

arch/x86/include/asm/uv/uv_bau.h

@@ -149,7 +149,6 @@
 /* 4 bits of software ack period */
 #define UV2_ACK_MASK			0x7UL
 #define UV2_ACK_UNITS_SHFT		3
-#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT
 #define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
 
 /*

arch/x86/kernel/aperture_64.c

@@ -20,7 +20,6 @@
 #include <linux/bitops.h>
 #include <linux/ioport.h>
 #include <linux/suspend.h>
-#include <linux/kmemleak.h>
 #include <asm/e820.h>
 #include <asm/io.h>
 #include <asm/iommu.h>
@@ -95,11 +94,6 @@ static u32 __init allocate_aperture(void)
 		return 0;
 	}
 	memblock_reserve(addr, aper_size);
-	/*
-	 * Kmemleak should not scan this block as it may not be mapped via the
-	 * kernel direct mapping.
-	 */
-	kmemleak_ignore(phys_to_virt(addr));
 	printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
 			aper_size >> 10, addr);
 	insert_aperture_resource((u32)addr, aper_size);

arch/x86/kernel/apic/io_apic.c

@@ -1195,7 +1195,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
 	BUG_ON(!cfg->vector);
 
 	vector = cfg->vector;
-	for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+	for_each_cpu(cpu, cfg->domain)
 		per_cpu(vector_irq, cpu)[vector] = -1;
 
 	cfg->vector = 0;
@@ -1203,7 +1203,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
 
 	if (likely(!cfg->move_in_progress))
 		return;
-	for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+	for_each_cpu(cpu, cfg->old_domain) {
 		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
 								vector++) {
 			if (per_cpu(vector_irq, cpu)[vector] != irq)

arch/x86/kernel/cpu/mcheck/mce.c

@@ -1274,7 +1274,7 @@ static void mce_timer_fn(unsigned long data)
 	 */
 	iv = __this_cpu_read(mce_next_interval);
 	if (mce_notify_irq())
-		iv = max(iv, (unsigned long) HZ/100);
+		iv = max(iv / 2, (unsigned long) HZ/100);
 	else
 		iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
 	__this_cpu_write(mce_next_interval, iv);
@@ -1557,7 +1557,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 static void __mcheck_cpu_init_timer(void)
 {
 	struct timer_list *t = &__get_cpu_var(mce_timer);
-	unsigned long iv = __this_cpu_read(mce_next_interval);
+	unsigned long iv = check_interval * HZ;
 
 	setup_timer(t, mce_timer_fn, smp_processor_id());
 

arch/x86/kernel/cpu/perf_event.c

@@ -1496,6 +1496,7 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
 		if (!cpuc->shared_regs)
 			goto error;
 	}
+	cpuc->is_fake = 1;
 	return cpuc;
 error:
 	free_fake_cpuc(cpuc);
@@ -1756,6 +1757,12 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
 }
 
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+	return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
 #ifdef CONFIG_COMPAT
 
 #include <asm/compat.h>
@@ -1780,7 +1787,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if (bytes != sizeof(frame))
 			break;
 
-		if (fp < compat_ptr(regs->sp))
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);
@@ -1826,7 +1833,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		if (bytes != sizeof(frame))
 			break;
 
-		if ((unsigned long)fp < regs->sp)
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);

arch/x86/kernel/cpu/perf_event.h

@@ -117,6 +117,7 @@ struct cpu_hw_events {
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
 
 	unsigned int		group_flag;
+	int			is_fake;
 
 	/*
 	 * Intel DebugStore bits
@@ -364,6 +365,7 @@ struct x86_pmu {
 	int		pebs_record_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
+	void		(*pebs_aliases)(struct perf_event *event);
 
 	/*
 	 * Intel LBR

arch/x86/kernel/cpu/perf_event_intel.c

@@ -1119,27 +1119,33 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
-static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
+static int intel_alt_er(int idx)
 {
 	if (!(x86_pmu.er_flags & ERF_HAS_RSP_1))
-		return false;
+		return idx;
 
-	if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) {
-		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-		event->hw.config |= 0x01bb;
-		event->hw.extra_reg.idx = EXTRA_REG_RSP_1;
-		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
-	} else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) {
-		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-		event->hw.config |= 0x01b7;
-		event->hw.extra_reg.idx = EXTRA_REG_RSP_0;
-		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
+	if (idx == EXTRA_REG_RSP_0)
+		return EXTRA_REG_RSP_1;
+
+	if (idx == EXTRA_REG_RSP_1)
+		return EXTRA_REG_RSP_0;
+
+	return idx;
 }
 
-	if (event->hw.extra_reg.idx == orig_idx)
-		return false;
+static void intel_fixup_er(struct perf_event *event, int idx)
+{
+	event->hw.extra_reg.idx = idx;
 
-	return true;
+	if (idx == EXTRA_REG_RSP_0) {
+		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
+		event->hw.config |= 0x01b7;
+		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
+	} else if (idx == EXTRA_REG_RSP_1) {
+		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
+		event->hw.config |= 0x01bb;
+		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
+	}
 }
 
 /*
@@ -1157,14 +1163,18 @@ __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
 	struct event_constraint *c = &emptyconstraint;
 	struct er_account *era;
 	unsigned long flags;
-	int orig_idx = reg->idx;
+	int idx = reg->idx;
 
-	/* already allocated shared msr */
-	if (reg->alloc)
+	/*
+	 * reg->alloc can be set due to existing state, so for fake cpuc we
+	 * need to ignore this, otherwise we might fail to allocate proper fake
+	 * state for this extra reg constraint. Also see the comment below.
+	 */
+	if (reg->alloc && !cpuc->is_fake)
 		return NULL; /* call x86_get_event_constraint() */
 
 again:
-	era = &cpuc->shared_regs->regs[reg->idx];
+	era = &cpuc->shared_regs->regs[idx];
 	/*
 	 * we use spin_lock_irqsave() to avoid lockdep issues when
 	 * passing a fake cpuc
@@ -1173,6 +1183,29 @@ again:
 
 	if (!atomic_read(&era->ref) || era->config == reg->config) {
 
+		/*
+		 * If its a fake cpuc -- as per validate_{group,event}() we
+		 * shouldn't touch event state and we can avoid doing so
+		 * since both will only call get_event_constraints() once
+		 * on each event, this avoids the need for reg->alloc.
+		 *
+		 * Not doing the ER fixup will only result in era->reg being
+		 * wrong, but since we won't actually try and program hardware
+		 * this isn't a problem either.
+		 */
+		if (!cpuc->is_fake) {
+			if (idx != reg->idx)
+				intel_fixup_er(event, idx);
+
+			/*
+			 * x86_schedule_events() can call get_event_constraints()
+			 * multiple times on events in the case of incremental
+			 * scheduling(). reg->alloc ensures we only do the ER
+			 * allocation once.
+			 */
+			reg->alloc = 1;
+		}
+
 		/* lock in msr value */
 		era->config = reg->config;
 		era->reg = reg->reg;
@@ -1180,18 +1213,18 @@ again:
 		/* one more user */
 		atomic_inc(&era->ref);
 
-		/* no need to reallocate during incremental event scheduling */
-		reg->alloc = 1;
-
 		/*
 		 * need to call x86_get_event_constraint()
 		 * to check if associated event has constraints
 		 */
 		c = NULL;
-	} else if (intel_try_alt_er(event, orig_idx)) {
+	} else {
+		idx = intel_alt_er(idx);
+		if (idx != reg->idx) {
 			raw_spin_unlock_irqrestore(&era->lock, flags);
 			goto again;
 		}
+	}
 	raw_spin_unlock_irqrestore(&era->lock, flags);
 
 	return c;
@@ -1204,11 +1237,14 @@ __intel_shared_reg_put_constraints(struct cpu_hw_events *cpuc,
 	struct er_account *era;
 
 	/*
-	 * only put constraint if extra reg was actually
-	 * allocated. Also takes care of event which do
-	 * not use an extra shared reg
+	 * Only put constraint if extra reg was actually allocated. Also takes
+	 * care of event which do not use an extra shared reg.
+	 *
+	 * Also, if this is a fake cpuc we shouldn't touch any event state
+	 * (reg->alloc) and we don't care about leaving inconsistent cpuc state
+	 * either since it'll be thrown out.
 	 */
-	if (!reg->alloc)
+	if (!reg->alloc || cpuc->is_fake)
 		return;
 
 	era = &cpuc->shared_regs->regs[reg->idx];
@@ -1300,15 +1336,9 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 	intel_put_shared_regs_event_constraints(cpuc, event);
 }
 
-static int intel_pmu_hw_config(struct perf_event *event)
+static void intel_pebs_aliases_core2(struct perf_event *event)
 {
-	int ret = x86_pmu_hw_config(event);
-
-	if (ret)
-		return ret;
-
-	if (event->attr.precise_ip &&
-	    (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
 		/*
 		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
 		 * (0x003c) so that we can use it with PEBS.
@@ -1329,10 +1359,48 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		 */
 		u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
 
+		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+		event->hw.config = alt_config;
+	}
+}
+
+static void intel_pebs_aliases_snb(struct perf_event *event)
+{
+	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+		/*
+		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+		 * (0x003c) so that we can use it with PEBS.
+		 *
+		 * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+		 * PEBS capable. However we can use UOPS_RETIRED.ALL
+		 * (0x01c2), which is a PEBS capable event, to get the same
+		 * count.
+		 *
+		 * UOPS_RETIRED.ALL counts the number of cycles that retires
+		 * CNTMASK micro-ops. By setting CNTMASK to a value (16)
+		 * larger than the maximum number of micro-ops that can be
+		 * retired per cycle (4) and then inverting the condition, we
+		 * count all cycles that retire 16 or less micro-ops, which
+		 * is every cycle.
+		 *
+		 * Thereby we gain a PEBS capable cycle counter.
+		 */
+		u64 alt_config = X86_CONFIG(.event=0xc2, .umask=0x01, .inv=1, .cmask=16);
 
 		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
 		event->hw.config = alt_config;
 	}
+}
+
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
+		x86_pmu.pebs_aliases(event);
 
 	if (intel_pmu_needs_lbr_smpl(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
@@ -1607,6 +1675,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.max_period		= (1ULL << 31) - 1,
 	.get_event_constraints	= intel_get_event_constraints,
 	.put_event_constraints	= intel_put_event_constraints,
+	.pebs_aliases		= intel_pebs_aliases_core2,
 
 	.format_attrs		= intel_arch3_formats_attr,
 
@@ -1840,8 +1909,9 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
-		x86_add_quirk(intel_sandybridge_quirk);
 	case 45: /* SandyBridge, "Romely-EP" */
+		x86_add_quirk(intel_sandybridge_quirk);
+	case 58: /* IvyBridge */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -1849,6 +1919,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
 		x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -400,14 +400,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */

arch/x86/kernel/kvmclock.c

@@ -120,11 +120,6 @@ bool kvm_check_and_clear_guest_paused(void)
 	bool ret = false;
 	struct pvclock_vcpu_time_info *src;
 
-	/*
-	 * per_cpu() is safe here because this function is only called from
-	 * timer functions where preemption is already disabled.
-	 */
-	WARN_ON(!in_atomic());
 	src = &__get_cpu_var(hv_clock);
 	if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
 		__this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED);

arch/x86/kernel/nmi_selftest.c

@@ -42,7 +42,7 @@ static int __init nmi_unk_cb(unsigned int val, struct pt_regs *regs)
 static void __init init_nmi_testsuite(void)
 {
 	/* trap all the unknown NMIs we may generate */
-	register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+	register_nmi_handler_initonly(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
 }
 
 static void __init cleanup_nmi_testsuite(void)
@@ -64,7 +64,7 @@ static void __init test_nmi_ipi(struct cpumask *mask)
 {
 	unsigned long timeout;
 
-	if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+	if (register_nmi_handler_initonly(NMI_LOCAL, test_nmi_ipi_callback,
 				 NMI_FLAG_FIRST, "nmi_selftest")) {
 		nmi_fail = FAILURE;
 		return;

arch/x86/kernel/reboot.c

@@ -639,9 +639,11 @@ void native_machine_shutdown(void)
 	set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
 
 	/*
-	 * O.K Now that I'm on the appropriate processor,
-	 * stop all of the others.
+	 * O.K Now that I'm on the appropriate processor, stop all of the
+	 * others. Also disable the local irq to not receive the per-cpu
+	 * timer interrupt which may trigger scheduler's load balance.
 	 */
+	local_irq_disable();
 	stop_other_cpus();
 #endif
 

arch/x86/kernel/smpboot.c

@@ -382,6 +382,15 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		if ((i == cpu) || (has_mc && match_llc(c, o)))
 			link_mask(llc_shared, cpu, i);
 
+	}
+
+	/*
+	 * This needs a separate iteration over the cpus because we rely on all
+	 * cpu_sibling_mask links to be set-up.
+	 */
+	for_each_cpu(i, cpu_sibling_setup_mask) {
+		o = &cpu_data(i);
+
 		if ((i == cpu) || (has_mc && match_mc(c, o))) {
 			link_mask(core, cpu, i);
 
@@ -410,14 +419,6 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 /* maps the cpu to the sched domain representing multi-core */
 const struct cpumask *cpu_coregroup_mask(int cpu)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-	/*
-	 * For perf, we return last level cache shared map.
-	 * And for power savings, we return cpu_core_map
-	 */
-	if (!(cpu_has(c, X86_FEATURE_AMD_DCM)))
-		return cpu_core_mask(cpu);
-	else
 	return cpu_llc_shared_mask(cpu);
 }
 

arch/x86/lib/usercopy.c

@@ -8,6 +8,7 @@
 #include <linux/module.h>
 
 #include <asm/word-at-a-time.h>
+#include <linux/sched.h>
 
 /*
  * best effort, GUP based copy_from_user() that is NMI-safe
@@ -21,6 +22,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	void *map;
 	int ret;
 
+	if (__range_not_ok(from, n, TASK_SIZE) == 0)
+		return len;
+
 	do {
 		ret = __get_user_pages_fast(addr, 1, 0, &page);
 		if (!ret)

arch/x86/lib/x86-opcode-map.txt

@@ -28,7 +28,7 @@
 #  - (66): the last prefix is 0x66
 #  - (F3): the last prefix is 0xF3
 #  - (F2): the last prefix is 0xF2
-#
+#  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
 
 Table: one byte opcode
 Referrer:
@@ -515,12 +515,12 @@ b4: LFS Gv,Mp
 b5: LGS Gv,Mp
 b6: MOVZX Gv,Eb
 b7: MOVZX Gv,Ew
-b8: JMPE | POPCNT Gv,Ev (F3)
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
 b9: Grp10 (1A)
 ba: Grp8 Ev,Ib (1A)
 bb: BTC Ev,Gv
-bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
 be: MOVSX Gv,Eb
 bf: MOVSX Gv,Ew
 # 0x0f 0xc0-0xcf

arch/x86/mm/init.c

@@ -62,6 +62,7 @@ static void __init find_early_table_space(struct map_range *mr, unsigned long en
 		extra += PMD_SIZE;
 #endif
 		/* The first 2/4M doesn't use large pages. */
+		if (mr->start < PMD_SIZE)
 			extra += mr->end - mr->start;
 
 		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;

arch/x86/mm/srat.c

@@ -176,6 +176,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		return;
 	}
 
+	node_set(node, numa_nodes_parsed);
+
 	printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
 	       node, pxm,
 	       (unsigned long long) start, (unsigned long long) end - 1);

arch/x86/platform/mrst/mrst.c

@@ -782,7 +782,7 @@ BLOCKING_NOTIFIER_HEAD(intel_scu_notifier);
 EXPORT_SYMBOL_GPL(intel_scu_notifier);
 
 /* Called by IPC driver */
-void intel_scu_devices_create(void)
+void __devinit intel_scu_devices_create(void)
 {
 	int i;
 

arch/x86/platform/uv/tlb_uv.c

@@ -1295,7 +1295,6 @@ static void __init enable_timeouts(void)
 		 */
 		mmr_image |= (1L << SOFTACK_MSHIFT);
 		if (is_uv2_hub()) {
-			mmr_image &= ~(1L << UV2_LEG_SHFT);
 			mmr_image |= (1L << UV2_EXT_SHFT);
 		}
 		write_mmr_misc_control(pnode, mmr_image);

arch/x86/tools/gen-insn-attr-x86.awk

@@ -66,9 +66,10 @@ BEGIN {
 	rex_expr = "^REX(\\.[XRWB]+)*"
 	fpu_expr = "^ESC" # TODO
 
-	lprefix1_expr = "\\(66\\)"
+	lprefix1_expr = "\\((66|!F3)\\)"
 	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\(F2\\)"
+	lprefix3_expr = "\\((F2|!F3)\\)"
+	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
 	# All opcodes starting with lower-case 'v' or with (v1) superscript
@@ -333,13 +334,16 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 		if (match(ext, lprefix1_expr)) {
 			lptable1[idx] = add_flags(lptable1[idx],flags)
 			variant = "INAT_VARIANT"
-		} else if (match(ext, lprefix2_expr)) {
+		}
+		if (match(ext, lprefix2_expr)) {
 			lptable2[idx] = add_flags(lptable2[idx],flags)
 			variant = "INAT_VARIANT"
-		} else if (match(ext, lprefix3_expr)) {
+		}
+		if (match(ext, lprefix3_expr)) {
 			lptable3[idx] = add_flags(lptable3[idx],flags)
 			variant = "INAT_VARIANT"
-		} else {
+		}
+		if (!match(ext, lprefix_expr)){
 			table[idx] = add_flags(table[idx],flags)
 		}
 	}

arch/xtensa/include/asm/syscall.h

@@ -31,5 +31,5 @@ asmlinkage long sys_pselect6(int n, fd_set __user *inp, fd_set __user *outp,
 asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
 	struct timespec __user *tsp, const sigset_t __user *sigmask,
 	size_t sigsetsize);
-
-
+asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset,
+		size_t sigsetsize);

arch/xtensa/kernel/signal.c

@@ -493,7 +493,7 @@ static void do_signal(struct pt_regs *regs)
 		if (ret)
 			return;
 
-		signal_delivered(signr, info, ka, regs, 0);
+		signal_delivered(signr, &info, &ka, regs, 0);
 		if (current->ptrace & PT_SINGLESTEP)
 			task_pt_regs(current)->icountlevel = 1;
 

drivers/acpi/Kconfig

@@ -208,7 +208,7 @@ config ACPI_IPMI
 
 config ACPI_HOTPLUG_CPU
 	bool
-	depends on ACPI_PROCESSOR && HOTPLUG_CPU
+	depends on EXPERIMENTAL && ACPI_PROCESSOR && HOTPLUG_CPU
 	select ACPI_CONTAINER
 	default y