Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Merge the BIOS workarounds from 2.6.32, and the swiotlb fallback on failure.

.gitignore

@@ -25,6 +25,7 @@
 *.elf
 *.bin
 *.gz
+*.bz2
 *.lzma
 *.patch
 *.gcno

Documentation/ABI/testing/sysfs-bus-pci-devices-cciss

@@ -31,3 +31,31 @@ Date:		March 2009
 Kernel Version: 2.6.30
 Contact:	iss_storagedev@hp.com
 Description:	A symbolic link to /sys/block/cciss!cXdY
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/rescan
+Date:		August 2009
+Kernel Version:	2.6.31
+Contact:	iss_storagedev@hp.com
+Description:	Kicks of a rescan of the controller to discover logical
+		drive topology changes.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/lunid
+Date:		August 2009
+Kernel Version: 2.6.31
+Contact:	iss_storagedev@hp.com
+Description:	Displays the 8-byte LUN ID used to address logical
+		drive Y of controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/raid_level
+Date:		August 2009
+Kernel Version: 2.6.31
+Contact:	iss_storagedev@hp.com
+Description:	Displays the RAID level of logical drive Y of
+		controller X.
+
+Where:		/sys/bus/pci/devices/<dev>/ccissX/cXdY/usage_count
+Date:		August 2009
+Kernel Version: 2.6.31
+Contact:	iss_storagedev@hp.com
+Description:	Displays the usage count (number of opens) of logical drive Y
+		of controller X.

Documentation/ABI/testing/sysfs-class-usb_host → Documentation/ABI/testing/sysfs-class-uwb_rc-wusbhc

@@ -1,4 +1,4 @@
-What:           /sys/class/usb_host/usb_hostN/wusb_chid
+What:           /sys/class/uwb_rc/uwbN/wusbhc/wusb_chid
 Date:           July 2008
 KernelVersion:  2.6.27
 Contact:        David Vrabel <david.vrabel@csr.com>
@@ -9,7 +9,7 @@ Description:
 
                 Set an all zero CHID to stop the host controller.
 
-What:           /sys/class/usb_host/usb_hostN/wusb_trust_timeout
+What:           /sys/class/uwb_rc/uwbN/wusbhc/wusb_trust_timeout
 Date:           July 2008
 KernelVersion:  2.6.27
 Contact:        David Vrabel <david.vrabel@csr.com>

Documentation/ABI/testing/sysfs-devices-cache_disable

@@ -1,18 +0,0 @@
-What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
-Date:      August 2008
-KernelVersion:	2.6.27
-Contact:	mark.langsdorf@amd.com
-Description:	These files exist in every cpu's cache index directories.
-		There are currently 2 cache_disable_# files in each
-		directory.  Reading from these files on a supported
-		processor will return that cache disable index value
-		for that processor and node.  Writing to one of these
-		files will cause the specificed cache index to be disabled.
-
-		Currently, only AMD Family 10h Processors support cache index
-		disable, and only for their L3 caches.  See the BIOS and
-		Kernel Developer's Guide at
-		http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
-		for formatting information and other details on the
-		cache index disable.
-Users:    joachim.deguara@amd.com

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -0,0 +1,156 @@
+What:		/sys/devices/system/cpu/
+Date:		pre-git history
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:
+		A collection of both global and individual CPU attributes
+
+		Individual CPU attributes are contained in subdirectories
+		named by the kernel's logical CPU number, e.g.:
+
+		/sys/devices/system/cpu/cpu#/
+
+What:		/sys/devices/system/cpu/sched_mc_power_savings
+		/sys/devices/system/cpu/sched_smt_power_savings
+Date:		June 2006
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Discover and adjust the kernel's multi-core scheduler support.
+
+		Possible values are:
+
+		0 - No power saving load balance (default value)
+		1 - Fill one thread/core/package first for long running threads
+		2 - Also bias task wakeups to semi-idle cpu package for power
+		    savings
+
+		sched_mc_power_savings is dependent upon SCHED_MC, which is
+		itself architecture dependent.
+
+		sched_smt_power_savings is dependent upon SCHED_SMT, which
+		is itself architecture dependent.
+
+		The two files are independent of each other. It is possible
+		that one file may be present without the other.
+
+		Introduced by git commit 5c45bf27.
+
+
+What:		/sys/devices/system/cpu/kernel_max
+		/sys/devices/system/cpu/offline
+		/sys/devices/system/cpu/online
+		/sys/devices/system/cpu/possible
+		/sys/devices/system/cpu/present
+Date:		December 2008
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	CPU topology files that describe kernel limits related to
+		hotplug. Briefly:
+
+		kernel_max: the maximum cpu index allowed by the kernel
+		configuration.
+
+		offline: cpus that are not online because they have been
+		HOTPLUGGED off or exceed the limit of cpus allowed by the
+		kernel configuration (kernel_max above).
+
+		online: cpus that are online and being scheduled.
+
+		possible: cpus that have been allocated resources and can be
+		brought online if they are present.
+
+		present: cpus that have been identified as being present in
+		the system.
+
+		See Documentation/cputopology.txt for more information.
+
+
+
+What:		/sys/devices/system/cpu/cpu#/node
+Date:		October 2009
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Discover NUMA node a CPU belongs to
+
+		When CONFIG_NUMA is enabled, a symbolic link that points
+		to the corresponding NUMA node directory.
+
+		For example, the following symlink is created for cpu42
+		in NUMA node 2:
+
+		/sys/devices/system/cpu/cpu42/node2 -> ../../node/node2
+
+
+What:		/sys/devices/system/cpu/cpu#/topology/core_id
+		/sys/devices/system/cpu/cpu#/topology/core_siblings
+		/sys/devices/system/cpu/cpu#/topology/core_siblings_list
+		/sys/devices/system/cpu/cpu#/topology/physical_package_id
+		/sys/devices/system/cpu/cpu#/topology/thread_siblings
+		/sys/devices/system/cpu/cpu#/topology/thread_siblings_list
+Date:		December 2008
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	CPU topology files that describe a logical CPU's relationship
+		to other cores and threads in the same physical package.
+
+		One cpu# directory is created per logical CPU in the system,
+		e.g. /sys/devices/system/cpu/cpu42/.
+
+		Briefly, the files above are:
+
+		core_id: the CPU core ID of cpu#. Typically it is the
+		hardware platform's identifier (rather than the kernel's).
+		The actual value is architecture and platform dependent.
+
+		core_siblings: internal kernel map of cpu#'s hardware threads
+		within the same physical_package_id.
+
+		core_siblings_list: human-readable list of the logical CPU
+		numbers within the same physical_package_id as cpu#.
+
+		physical_package_id: physical package id of cpu#. Typically
+		corresponds to a physical socket number, but the actual value
+		is architecture and platform dependent.
+
+		thread_siblings: internel kernel map of cpu#'s hardware
+		threads within the same core as cpu#
+
+		thread_siblings_list: human-readable list of cpu#'s hardware
+		threads within the same core as cpu#
+
+		See Documentation/cputopology.txt for more information.
+
+
+What:		/sys/devices/system/cpu/cpuidle/current_driver
+		/sys/devices/system/cpu/cpuidle/current_governer_ro
+Date:		September 2007
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Discover cpuidle policy and mechanism
+
+		Various CPUs today support multiple idle levels that are
+		differentiated by varying exit latencies and power
+		consumption during idle.
+
+		Idle policy (governor) is differentiated from idle mechanism
+		(driver)
+
+		current_driver: displays current idle mechanism
+
+		current_governor_ro: displays current idle policy
+
+		See files in Documentation/cpuidle/ for more information.
+
+
+What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
+Date:      August 2008
+KernelVersion:	2.6.27
+Contact:	mark.langsdorf@amd.com
+Description:	These files exist in every cpu's cache index directories.
+		There are currently 2 cache_disable_# files in each
+		directory.  Reading from these files on a supported
+		processor will return that cache disable index value
+		for that processor and node.  Writing to one of these
+		files will cause the specificed cache index to be disabled.
+
+		Currently, only AMD Family 10h Processors support cache index
+		disable, and only for their L3 caches.  See the BIOS and
+		Kernel Developer's Guide at
+		http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
+		for formatting information and other details on the
+		cache index disable.
+Users:    joachim.deguara@amd.com

Documentation/SubmittingPatches

@@ -232,7 +232,7 @@ your e-mail client so that it sends your patches untouched.
 When sending patches to Linus, always follow step #7.
 
 Large changes are not appropriate for mailing lists, and some
-maintainers.  If your patch, uncompressed, exceeds 40 kB in size,
+maintainers.  If your patch, uncompressed, exceeds 300 kB in size,
 it is preferred that you store your patch on an Internet-accessible
 server, and provide instead a URL (link) pointing to your patch.
 

Documentation/arm/tcm.txt

@@ -0,0 +1,147 @@
+ARM TCM (Tightly-Coupled Memory) handling in Linux
+----
+Written by Linus Walleij <linus.walleij@stericsson.com>
+
+Some ARM SoC:s have a so-called TCM (Tightly-Coupled Memory).
+This is usually just a few (4-64) KiB of RAM inside the ARM
+processor.
+
+Due to being embedded inside the CPU The TCM has a
+Harvard-architecture, so there is an ITCM (instruction TCM)
+and a DTCM (data TCM). The DTCM can not contain any
+instructions, but the ITCM can actually contain data.
+The size of DTCM or ITCM is minimum 4KiB so the typical
+minimum configuration is 4KiB ITCM and 4KiB DTCM.
+
+ARM CPU:s have special registers to read out status, physical
+location and size of TCM memories. arch/arm/include/asm/cputype.h
+defines a CPUID_TCM register that you can read out from the
+system control coprocessor. Documentation from ARM can be found
+at http://infocenter.arm.com, search for "TCM Status Register"
+to see documents for all CPUs. Reading this register you can
+determine if ITCM (bit 0) and/or DTCM (bit 16) is present in the
+machine.
+
+There is further a TCM region register (search for "TCM Region
+Registers" at the ARM site) that can report and modify the location
+size of TCM memories at runtime. This is used to read out and modify
+TCM location and size. Notice that this is not a MMU table: you
+actually move the physical location of the TCM around. At the
+place you put it, it will mask any underlying RAM from the
+CPU so it is usually wise not to overlap any physical RAM with
+the TCM.
+
+The TCM memory can then be remapped to another address again using
+the MMU, but notice that the TCM if often used in situations where
+the MMU is turned off. To avoid confusion the current Linux
+implementation will map the TCM 1 to 1 from physical to virtual
+memory in the location specified by the machine.
+
+TCM is used for a few things:
+
+- FIQ and other interrupt handlers that need deterministic
+  timing and cannot wait for cache misses.
+
+- Idle loops where all external RAM is set to self-refresh
+  retention mode, so only on-chip RAM is accessible by
+  the CPU and then we hang inside ITCM waiting for an
+  interrupt.
+
+- Other operations which implies shutting off or reconfiguring
+  the external RAM controller.
+
+There is an interface for using TCM on the ARM architecture
+in <asm/tcm.h>. Using this interface it is possible to:
+
+- Define the physical address and size of ITCM and DTCM.
+
+- Tag functions to be compiled into ITCM.
+
+- Tag data and constants to be allocated to DTCM and ITCM.
+
+- Have the remaining TCM RAM added to a special
+  allocation pool with gen_pool_create() and gen_pool_add()
+  and provice tcm_alloc() and tcm_free() for this
+  memory. Such a heap is great for things like saving
+  device state when shutting off device power domains.
+
+A machine that has TCM memory shall select HAVE_TCM in
+arch/arm/Kconfig for itself, and then the
+rest of the functionality will depend on the physical
+location and size of ITCM and DTCM to be defined in
+mach/memory.h for the machine. Code that needs to use
+TCM shall #include <asm/tcm.h> If the TCM is not located
+at the place given in memory.h it will be moved using
+the TCM Region registers.
+
+Functions to go into itcm can be tagged like this:
+int __tcmfunc foo(int bar);
+
+Variables to go into dtcm can be tagged like this:
+int __tcmdata foo;
+
+Constants can be tagged like this:
+int __tcmconst foo;
+
+To put assembler into TCM just use
+.section ".tcm.text" or .section ".tcm.data"
+respectively.
+
+Example code:
+
+#include <asm/tcm.h>
+
+/* Uninitialized data */
+static u32 __tcmdata tcmvar;
+/* Initialized data */
+static u32 __tcmdata tcmassigned = 0x2BADBABEU;
+/* Constant */
+static const u32 __tcmconst tcmconst = 0xCAFEBABEU;
+
+static void __tcmlocalfunc tcm_to_tcm(void)
+{
+	int i;
+	for (i = 0; i < 100; i++)
+		tcmvar ++;
+}
+
+static void __tcmfunc hello_tcm(void)
+{
+	/* Some abstract code that runs in ITCM */
+	int i;
+	for (i = 0; i < 100; i++) {
+		tcmvar ++;
+	}
+	tcm_to_tcm();
+}
+
+static void __init test_tcm(void)
+{
+	u32 *tcmem;
+	int i;
+
+	hello_tcm();
+	printk("Hello TCM executed from ITCM RAM\n");
+
+	printk("TCM variable from testrun: %u @ %p\n", tcmvar, &tcmvar);
+	tcmvar = 0xDEADBEEFU;
+	printk("TCM variable: 0x%x @ %p\n", tcmvar, &tcmvar);
+
+	printk("TCM assigned variable: 0x%x @ %p\n", tcmassigned, &tcmassigned);
+
+	printk("TCM constant: 0x%x @ %p\n", tcmconst, &tcmconst);
+
+	/* Allocate some TCM memory from the pool */
+	tcmem = tcm_alloc(20);
+	if (tcmem) {
+		printk("TCM Allocated 20 bytes of TCM @ %p\n", tcmem);
+		tcmem[0] = 0xDEADBEEFU;
+		tcmem[1] = 0x2BADBABEU;
+		tcmem[2] = 0xCAFEBABEU;
+		tcmem[3] = 0xDEADBEEFU;
+		tcmem[4] = 0x2BADBABEU;
+		for (i = 0; i < 5; i++)
+			printk("TCM tcmem[%d] = %08x\n", i, tcmem[i]);
+		tcm_free(tcmem, 20);
+	}
+}

Documentation/auxdisplay/cfag12864b-example.c

@@ -194,7 +194,6 @@ static void cfag12864b_blit(void)
  */
 
 #include <stdio.h>
-#include <string.h>
 
 #define EXAMPLES	6
 

Documentation/cgroups/cgroups.txt

@@ -227,7 +227,14 @@ as the path relative to the root of the cgroup file system.
 Each cgroup is represented by a directory in the cgroup file system
 containing the following files describing that cgroup:
 
- - tasks: list of tasks (by pid) attached to that cgroup
+ - tasks: list of tasks (by pid) attached to that cgroup.  This list
+   is not guaranteed to be sorted.  Writing a thread id into this file
+   moves the thread into this 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.
  - 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)
@@ -374,7 +381,7 @@ Now you want to do something with this cgroup.
 
 In this directory you can find several files:
 # ls
-notify_on_release tasks
+cgroup.procs notify_on_release tasks
 (plus whatever files added by the attached subsystems)
 
 Now attach your shell to this cgroup:
@@ -408,6 +415,26 @@ You can attach the current shell task by echoing 0:
 
 # echo 0 > tasks
 
+2.3 Mounting hierarchies by name
+--------------------------------
+
+Passing the name=<x> option when mounting a cgroups hierarchy
+associates the given name with the hierarchy.  This can be used when
+mounting a pre-existing hierarchy, in order to refer to it by name
+rather than by its set of active subsystems.  Each hierarchy is either
+nameless, or has a unique name.
+
+The name should match [\w.-]+
+
+When passing a name=<x> option for a new hierarchy, you need to
+specify subsystems manually; the legacy behaviour of mounting all
+subsystems when none are explicitly specified is not supported when
+you give a subsystem a name.
+
+The name of the subsystem appears as part of the hierarchy description
+in /proc/mounts and /proc/<pid>/cgroups.
+
+
 3. Kernel API
 =============
 
@@ -501,7 +528,7 @@ rmdir() will fail with it. From this behavior, pre_destroy() can be
 called multiple times against a cgroup.
 
 int can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-	       struct task_struct *task)
+	       struct task_struct *task, bool threadgroup)
 (cgroup_mutex held by caller)
 
 Called prior to moving a task into a cgroup; if the subsystem
@@ -509,14 +536,20 @@ returns an error, this will abort the attach operation.  If a NULL
 task is passed, then a successful result indicates that *any*
 unspecified task can be moved into the cgroup. Note that this isn't
 called on a fork. If this method returns 0 (success) then this should
-remain valid while the caller holds cgroup_mutex.
+remain valid while the caller holds cgroup_mutex. If threadgroup is
+true, then a successful result indicates that all threads in the given
+thread's threadgroup can be moved together.
 
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-	    struct cgroup *old_cgrp, struct task_struct *task)
+	    struct cgroup *old_cgrp, struct task_struct *task,
+	    bool threadgroup)
 (cgroup_mutex held by caller)
 
 Called after the task has been attached to the cgroup, to allow any
 post-attachment activity that requires memory allocations or blocking.
+If threadgroup is true, the subsystem should take care of all threads
+in the specified thread's threadgroup. Currently does not support any
+subsystem that might need the old_cgrp for every thread in the group.
 
 void fork(struct cgroup_subsy *ss, struct task_struct *task)
 

Documentation/cgroups/memory.txt

@@ -179,6 +179,9 @@ The reclaim algorithm has not been modified for cgroups, except that
 pages that are selected for reclaiming come from the per cgroup LRU
 list.
 
+NOTE: Reclaim does not work for the root cgroup, since we cannot set any
+limits on the root cgroup.
+
 2. Locking
 
 The memory controller uses the following hierarchy
@@ -210,6 +213,7 @@ We can alter the memory limit:
 NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
 mega or gigabytes.
 NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited).
+NOTE: We cannot set limits on the root cgroup any more.
 
 # cat /cgroups/0/memory.limit_in_bytes
 4194304
@@ -375,7 +379,42 @@ cgroups created below it.
 
 NOTE2: This feature can be enabled/disabled per subtree.
 
-7. TODO
+7. Soft limits
+
+Soft limits allow for greater sharing of memory. The idea behind soft limits
+is to allow control groups to use as much of the memory as needed, provided
+
+a. There is no memory contention
+b. They do not exceed their hard limit
+
+When the system detects memory contention or low memory control groups
+are pushed back to their soft limits. If the soft limit of each control
+group is very high, they are pushed back as much as possible to make
+sure that one control group does not starve the others of memory.
+
+Please note that soft limits is a best effort feature, it comes with
+no guarantees, but it does its best to make sure that when memory is
+heavily contended for, memory is allocated based on the soft limit
+hints/setup. Currently soft limit based reclaim is setup such that
+it gets invoked from balance_pgdat (kswapd).
+
+7.1 Interface
+
+Soft limits can be setup by using the following commands (in this example we
+assume a soft limit of 256 megabytes)
+
+# echo 256M > memory.soft_limit_in_bytes
+
+If we want to change this to 1G, we can at any time use
+
+# echo 1G > memory.soft_limit_in_bytes
+
+NOTE1: Soft limits take effect over a long period of time, since they involve
+       reclaiming memory for balancing between memory cgroups
+NOTE2: It is recommended to set the soft limit always below the hard limit,
+       otherwise the hard limit will take precedence.
+
+8. TODO
 
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first

Documentation/connector/cn_test.c

@@ -34,7 +34,7 @@ static char cn_test_name[] = "cn_test";
 static struct sock *nls;
 static struct timer_list cn_test_timer;
 
-static void cn_test_callback(struct cn_msg *msg)
+static void cn_test_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp)
 {
 	pr_info("%s: %lu: idx=%x, val=%x, seq=%u, ack=%u, len=%d: %s.\n",
 	        __func__, jiffies, msg->id.idx, msg->id.val,

Documentation/connector/connector.txt

@@ -23,7 +23,7 @@ handling, etc...  The Connector driver allows any kernelspace agents to use
 netlink based networking for inter-process communication in a significantly
 easier way:
 
-int cn_add_callback(struct cb_id *id, char *name, void (*callback) (void *));
+int cn_add_callback(struct cb_id *id, char *name, void (*callback) (struct cn_msg *, struct netlink_skb_parms *));
 void cn_netlink_send(struct cn_msg *msg, u32 __group, int gfp_mask);
 
 struct cb_id
@@ -53,15 +53,15 @@ struct cn_msg
 Connector interfaces.
 /*****************************************/
 
-int cn_add_callback(struct cb_id *id, char *name, void (*callback) (void *));
+int cn_add_callback(struct cb_id *id, char *name, void (*callback) (struct cn_msg *, struct netlink_skb_parms *));
 
  Registers new callback with connector core.
 
  struct cb_id *id		- unique connector's user identifier.
 				  It must be registered in connector.h for legal in-kernel users.
  char *name			- connector's callback symbolic name.
- void (*callback) (void *)	- connector's callback.
-				  Argument must be dereferenced to struct cn_msg *.
+ void (*callback) (struct cn..)	- connector's callback.
+				  cn_msg and the sender's credentials
 
 
 void cn_del_callback(struct cb_id *id);

Documentation/cputopology.txt

@@ -1,15 +1,28 @@
 
-Export cpu topology info via sysfs. Items (attributes) are similar
+Export CPU topology info via sysfs. Items (attributes) are similar
 to /proc/cpuinfo.
 
 1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
-represent the physical package id of  cpu X;
+
+	physical package id of cpuX. Typically corresponds to a physical
+	socket number, but the actual value is architecture and platform
+	dependent.
+
 2) /sys/devices/system/cpu/cpuX/topology/core_id:
-represent the cpu core id to cpu X;
+
+	the CPU core ID of cpuX. Typically it is the hardware platform's
+	identifier (rather than the kernel's).  The actual value is
+	architecture and platform dependent.
+
 3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
-represent the thread siblings to cpu X in the same core;
+
+	internel kernel map of cpuX's hardware threads within the same
+	core as cpuX
+
 4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
-represent the thread siblings to cpu X in the same physical package;
+
+	internal kernel map of cpuX's hardware threads within the same
+	physical_package_id.
 
 To implement it in an architecture-neutral way, a new source file,
 drivers/base/topology.c, is to export the 4 attributes.
@@ -32,32 +45,32 @@ not defined by include/asm-XXX/topology.h:
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
 
-Additionally, cpu topology information is provided under
+Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
 
-    kernel_max: the maximum cpu index allowed by the kernel configuration.
+    kernel_max: the maximum CPU index allowed by the kernel configuration.
 		[NR_CPUS-1]
 
-    offline:	cpus that are not online because they have been
+    offline:	CPUs that are not online because they have been
 		HOTPLUGGED off (see cpu-hotplug.txt) or exceed the limit
-		of cpus allowed by the kernel configuration (kernel_max
+		of CPUs allowed by the kernel configuration (kernel_max
 		above). [~cpu_online_mask + cpus >= NR_CPUS]
 
-    online:	cpus that are online and being scheduled [cpu_online_mask]
+    online:	CPUs that are online and being scheduled [cpu_online_mask]
 
-    possible:	cpus that have been allocated resources and can be
+    possible:	CPUs that have been allocated resources and can be
 		brought online if they are present. [cpu_possible_mask]
 
-    present:	cpus that have been identified as being present in the
+    present:	CPUs that have been identified as being present in the
 		system. [cpu_present_mask]
 
 The format for the above output is compatible with cpulist_parse()
 [see <linux/cpumask.h>].  Some examples follow.
 
-In this example, there are 64 cpus in the system but cpus 32-63 exceed
+In this example, there are 64 CPUs in the system but cpus 32-63 exceed
 the kernel max which is limited to 0..31 by the NR_CPUS config option
-being 32.  Note also that cpus 2 and 4-31 are not online but could be
+being 32.  Note also that CPUs 2 and 4-31 are not online but could be
 brought online as they are both present and possible.
 
      kernel_max: 31
@@ -67,8 +80,8 @@ brought online as they are both present and possible.
         present: 0-31
 
 In this example, the NR_CPUS config option is 128, but the kernel was
-started with possible_cpus=144.  There are 4 cpus in the system and cpu2
-was manually taken offline (and is the only cpu that can be brought
+started with possible_cpus=144.  There are 4 CPUs in the system and cpu2
+was manually taken offline (and is the only CPU that can be brought
 online.)
 
      kernel_max: 127
@@ -78,4 +91,4 @@ online.)
         present: 0-3
 
 See cpu-hotplug.txt for the possible_cpus=NUM kernel start parameter
-as well as more information on the various cpumask's.
+as well as more information on the various cpumasks.

Documentation/crypto/async-tx-api.txt

@@ -54,20 +54,23 @@ features surfaced as a result:
 
 3.1 General format of the API:
 struct dma_async_tx_descriptor *
-async_<operation>(<op specific parameters>,
-		  enum async_tx_flags flags,
-        	  struct dma_async_tx_descriptor *dependency,
-        	  dma_async_tx_callback callback_routine,
-		  void *callback_parameter);
+async_<operation>(<op specific parameters>, struct async_submit ctl *submit)
 
 3.2 Supported operations:
-memcpy       - memory copy between a source and a destination buffer
-memset       - fill a destination buffer with a byte value
-xor          - xor a series of source buffers and write the result to a
-	       destination buffer
-xor_zero_sum - xor a series of source buffers and set a flag if the
-	       result is zero.  The implementation attempts to prevent
-	       writes to memory
+memcpy  - memory copy between a source and a destination buffer
+memset  - fill a destination buffer with a byte value
+xor     - xor a series of source buffers and write the result to a
+	  destination buffer
+xor_val - xor a series of source buffers and set a flag if the
+	  result is zero.  The implementation attempts to prevent
+	  writes to memory
+pq	- generate the p+q (raid6 syndrome) from a series of source buffers
+pq_val  - validate that a p and or q buffer are in sync with a given series of
+	  sources
+datap	- (raid6_datap_recov) recover a raid6 data block and the p block
+	  from the given sources
+2data	- (raid6_2data_recov) recover 2 raid6 data blocks from the given
+	  sources
 
 3.3 Descriptor management:
 The return value is non-NULL and points to a 'descriptor' when the operation
@@ -80,8 +83,8 @@ acknowledged by the application before the offload engine driver is allowed to
 recycle (or free) the descriptor.  A descriptor can be acked by one of the
 following methods:
 1/ setting the ASYNC_TX_ACK flag if no child operations are to be submitted
-2/ setting the ASYNC_TX_DEP_ACK flag to acknowledge the parent
-   descriptor of a new operation.
+2/ submitting an unacknowledged descriptor as a dependency to another
+   async_tx call will implicitly set the acknowledged state.
 3/ calling async_tx_ack() on the descriptor.
 
 3.4 When does the operation execute?
@@ -119,30 +122,42 @@ of an operation.
 Perform a xor->copy->xor operation where each operation depends on the
 result from the previous operation:
 
-void complete_xor_copy_xor(void *param)
+void callback(void *param)
 {
-	printk("complete\n");
+	struct completion *cmp = param;
+
+	complete(cmp);
 }
 
-int run_xor_copy_xor(struct page **xor_srcs,
-		     int xor_src_cnt,
-		     struct page *xor_dest,
-		     size_t xor_len,
-		     struct page *copy_src,
-		     struct page *copy_dest,
-		     size_t copy_len)
+void run_xor_copy_xor(struct page **xor_srcs,
+		      int xor_src_cnt,
+		      struct page *xor_dest,
+		      size_t xor_len,
+		      struct page *copy_src,
+		      struct page *copy_dest,
+		      size_t copy_len)
 {
 	struct dma_async_tx_descriptor *tx;
+	addr_conv_t addr_conv[xor_src_cnt];
+	struct async_submit_ctl submit;
+	addr_conv_t addr_conv[NDISKS];
+	struct completion cmp;
+
+	init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL,
+			  addr_conv);
+	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit)
 
-	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len,
-		       ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL);
-	tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len,
-			  ASYNC_TX_DEP_ACK, tx, NULL, NULL);
-	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len,
-		       ASYNC_TX_XOR_DROP_DST | ASYNC_TX_DEP_ACK | ASYNC_TX_ACK,
-		       tx, complete_xor_copy_xor, NULL);
+	submit->depend_tx = tx;
+	tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len, &submit);
+
+	init_completion(&cmp);
+	init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST | ASYNC_TX_ACK, tx,
+			  callback, &cmp, addr_conv);
+	tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, &submit);
 
 	async_tx_issue_pending_all();
+
+	wait_for_completion(&cmp);
 }
 
 See include/linux/async_tx.h for more information on the flags.  See the

Documentation/debugging-via-ohci1394.txt

@@ -64,14 +64,14 @@ be used to view the printk buffer of a remote machine, even with live update.
 
 Bernhard Kaindl enhanced firescope to support accessing 64-bit machines
 from 32-bit firescope and vice versa:
-- ftp://ftp.suse.de/private/bk/firewire/tools/firescope-0.2.2.tar.bz2
+- http://halobates.de/firewire/firescope-0.2.2.tar.bz2
 
 and he implemented fast system dump (alpha version - read README.txt):
-- ftp://ftp.suse.de/private/bk/firewire/tools/firedump-0.1.tar.bz2
+- http://halobates.de/firewire/firedump-0.1.tar.bz2
 
 There is also a gdb proxy for firewire which allows to use gdb to access
 data which can be referenced from symbols found by gdb in vmlinux:
-- ftp://ftp.suse.de/private/bk/firewire/tools/fireproxy-0.33.tar.bz2
+- http://halobates.de/firewire/fireproxy-0.33.tar.bz2
 
 The latest version of this gdb proxy (fireproxy-0.34) can communicate (not
 yet stable) with kgdb over an memory-based communication module (kgdbom).
@@ -178,7 +178,7 @@ Step-by-step instructions for using firescope with early OHCI initialization:
 
 Notes
 -----
-Documentation and specifications: ftp://ftp.suse.de/private/bk/firewire/docs
+Documentation and specifications: http://halobates.de/firewire/
 
 FireWire is a trademark of Apple Inc. - for more information please refer to:
 http://en.wikipedia.org/wiki/FireWire

Documentation/dontdiff

@@ -65,6 +65,7 @@ aicdb.h*
 asm-offsets.h
 asm_offsets.h
 autoconf.h*
+av_permissions.h
 bbootsect
 bin2c
 binkernel.spec
@@ -95,12 +96,14 @@ docproc
 elf2ecoff
 elfconfig.h*
 fixdep
+flask.h
 fore200e_mkfirm
 fore200e_pca_fw.c*
 gconf
 gen-devlist
 gen_crc32table
 gen_init_cpio
+genheaders
 genksyms
 *_gray256.c
 ihex2fw

Documentation/fb/framebuffer.txt

@@ -312,10 +312,8 @@ and to the following documentation:
 8. Mailing list
 ---------------
 
-There are several frame buffer device related mailing lists at SourceForge:
-  - linux-fbdev-announce@lists.sourceforge.net, for announcements,
-  - linux-fbdev-user@lists.sourceforge.net, for generic user support,
-  - linux-fbdev-devel@lists.sourceforge.net, for project developers.
+There is a frame buffer device related mailing list at kernel.org:
+linux-fbdev@vger.kernel.org.
 
 Point your web browser to http://sourceforge.net/projects/linux-fbdev/ for
 subscription information and archive browsing.

Documentation/feature-removal-schedule.txt

@@ -354,14 +354,6 @@ Who:  Krzysztof Piotr Oledzki <ole@ans.pl>
 
 ---------------------------
 
-What:	fscher and fscpos drivers
-When:	June 2009
-Why:	Deprecated by the new fschmd driver.
-Who:	Hans de Goede <hdegoede@redhat.com>
-	Jean Delvare <khali@linux-fr.org>
-
----------------------------
-
 What:	sysfs ui for changing p4-clockmod parameters
 When:	September 2009
 Why:	See commits 129f8ae9b1b5be94517da76009ea956e89104ce8 and
@@ -426,6 +418,14 @@ When:	2.6.33
 Why:	Should be implemented in userspace, policy daemon.
 Who:	Johannes Berg <johannes@sipsolutions.net>
 
+---------------------------
+
+What:	CONFIG_INOTIFY
+When:	2.6.33
+Why:	last user (audit) will be converted to the newer more generic
+	and more easily maintained fsnotify subsystem
+Who:	Eric Paris <eparis@redhat.com>
+
 ----------------------------
 
 What:	lock_policy_rwsem_* and unlock_policy_rwsem_* will not be
@@ -459,3 +459,33 @@ Why:	OSS sound_core grabs all legacy minors (0-255) of SOUND_MAJOR
 	will also allow making ALSA OSS emulation independent of
 	sound_core.  The dependency will be broken then too.
 Who:	Tejun Heo <tj@kernel.org>
+
+----------------------------
+
+What:	Support for VMware's guest paravirtuliazation technique [VMI] will be
+	dropped.
+When:	2.6.37 or earlier.
+Why:	With the recent innovations in CPU hardware acceleration technologies
+	from Intel and AMD, VMware ran a few experiments to compare these
+	techniques to guest paravirtualization technique on VMware's platform.
+	These hardware assisted virtualization techniques have outperformed the
+	performance benefits provided by VMI in most of the workloads. VMware
+	expects that these hardware features will be ubiquitous in a couple of
+	years, as a result, VMware has started a phased retirement of this
+	feature from the hypervisor. We will be removing this feature from the
+	Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
+	technical reasons (read opportunity to remove major chunk of pvops)
+	arise.
+
+	Please note that VMI has always been an optimization and non-VMI kernels
+	still work fine on VMware's platform.
+	Latest versions of VMware's product which support VMI are,
+	Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
+	releases for these products will continue supporting VMI.
+
+	For more details about VMI retirement take a look at this,
+	http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
+
+Who:	Alok N Kataria <akataria@vmware.com>
+
+----------------------------

Documentation/filesystems/9p.txt

@@ -18,11 +18,11 @@ the 9p client is available in the form of a USENIX paper:
 
 Other applications are described in the following papers:
 	* XCPU & Clustering
-		http://www.xcpu.org/xcpu-talk.pdf
+		http://xcpu.org/papers/xcpu-talk.pdf
 	* KVMFS: control file system for KVM
-		http://www.xcpu.org/kvmfs.pdf
-	* CellFS: A New ProgrammingModel for the Cell BE
-		http://www.xcpu.org/cellfs-talk.pdf
+		http://xcpu.org/papers/kvmfs.pdf
+	* CellFS: A New Programming Model for the Cell BE
+		http://xcpu.org/papers/cellfs-talk.pdf
 	* PROSE I/O: Using 9p to enable Application Partitions
 		http://plan9.escet.urjc.es/iwp9/cready/PROSE_iwp9_2006.pdf
 
@@ -48,6 +48,7 @@ OPTIONS
                                 (see rfdno and wfdno)
 			virtio	- connect to the next virtio channel available
 				(from lguest or KVM with trans_virtio module)
+			rdma	- connect to a specified RDMA channel
 
   uname=name	user name to attempt mount as on the remote server.  The
   		server may override or ignore this value.  Certain user
@@ -59,16 +60,22 @@ OPTIONS
   cache=mode	specifies a caching policy.  By default, no caches are used.
 			loose = no attempts are made at consistency,
                                 intended for exclusive, read-only mounts
+			fscache = use FS-Cache for a persistent, read-only
+				cache backend.
 
   debug=n	specifies debug level.  The debug level is a bitmask.
-  			0x01 = display verbose error messages
-			0x02 = developer debug (DEBUG_CURRENT)
-			0x04 = display 9p trace
-			0x08 = display VFS trace
-			0x10 = display Marshalling debug
-			0x20 = display RPC debug
-			0x40 = display transport debug
-			0x80 = display allocation debug
+			0x01  = display verbose error messages
+			0x02  = developer debug (DEBUG_CURRENT)
+			0x04  = display 9p trace
+			0x08  = display VFS trace
+			0x10  = display Marshalling debug
+			0x20  = display RPC debug
+			0x40  = display transport debug
+			0x80  = display allocation debug
+			0x100 = display protocol message debug
+			0x200 = display Fid debug
+			0x400 = display packet debug
+			0x800 = display fscache tracing debug
 
   rfdno=n	the file descriptor for reading with trans=fd
 
@@ -100,6 +107,10 @@ OPTIONS
 			any   = v9fs does single attach and performs all
 				operations as one user
 
+  cachetag	cache tag to use the specified persistent cache.
+		cache tags for existing cache sessions can be listed at
+		/sys/fs/9p/caches. (applies only to cache=fscache)
+
 RESOURCES
 =========
 
@@ -118,7 +129,7 @@ and export.
 A Linux version of the 9p server is now maintained under the npfs project
 on sourceforge (http://sourceforge.net/projects/npfs).  The currently
 maintained version is the single-threaded version of the server (named spfs)
-available from the same CVS repository.
+available from the same SVN repository.
 
 There are user and developer mailing lists available through the v9fs project
 on sourceforge (http://sourceforge.net/projects/v9fs).
@@ -126,7 +137,8 @@ on sourceforge (http://sourceforge.net/projects/v9fs).
 A stand-alone version of the module (which should build for any 2.6 kernel)
 is available via (http://github.com/ericvh/9p-sac/tree/master)
 
-News and other information is maintained on SWiK (http://swik.net/v9fs).
+News and other information is maintained on SWiK (http://swik.net/v9fs)
+and the Wiki (http://sf.net/apps/mediawiki/v9fs/index.php).
 
 Bug reports may be issued through the kernel.org bugzilla 
 (http://bugzilla.kernel.org)

Documentation/filesystems/caching/fscache.txt

@@ -235,6 +235,7 @@ proc files.
 		neg=N	Number of negative lookups made
 		pos=N	Number of positive lookups made
 		crt=N	Number of objects created by lookup
+		tmo=N	Number of lookups timed out and requeued
 	Updates	n=N	Number of update cookie requests seen
 		nul=N	Number of upd reqs given a NULL parent
 		run=N	Number of upd reqs granted CPU time
@@ -250,8 +251,10 @@ proc files.
 		ok=N	Number of successful alloc reqs
 		wt=N	Number of alloc reqs that waited on lookup completion
 		nbf=N	Number of alloc reqs rejected -ENOBUFS
+		int=N	Number of alloc reqs aborted -ERESTARTSYS
 		ops=N	Number of alloc reqs submitted
 		owt=N	Number of alloc reqs waited for CPU time
+		abt=N	Number of alloc reqs aborted due to object death
 	Retrvls	n=N	Number of retrieval (read) requests seen
 		ok=N	Number of successful retr reqs
 		wt=N	Number of retr reqs that waited on lookup completion
@@ -261,6 +264,7 @@ proc files.
 		oom=N	Number of retr reqs failed -ENOMEM
 		ops=N	Number of retr reqs submitted
 		owt=N	Number of retr reqs waited for CPU time
+		abt=N	Number of retr reqs aborted due to object death
 	Stores	n=N	Number of storage (write) requests seen
 		ok=N	Number of successful store reqs
 		agn=N	Number of store reqs on a page already pending storage
@@ -268,12 +272,37 @@ proc files.
 		oom=N	Number of store reqs failed -ENOMEM
 		ops=N	Number of store reqs submitted
 		run=N	Number of store reqs granted CPU time
+		pgs=N	Number of pages given store req processing time
+		rxd=N	Number of store reqs deleted from tracking tree
+		olm=N	Number of store reqs over store limit
+	VmScan	nos=N	Number of release reqs against pages with no pending store
+		gon=N	Number of release reqs against pages stored by time lock granted
+		bsy=N	Number of release reqs ignored due to in-progress store
+		can=N	Number of page stores cancelled due to release req
 	Ops	pend=N	Number of times async ops added to pending queues
 		run=N	Number of times async ops given CPU time
 		enq=N	Number of times async ops queued for processing
+		can=N	Number of async ops cancelled
+		rej=N	Number of async ops rejected due to object lookup/create failure
 		dfr=N	Number of async ops queued for deferred release
 		rel=N	Number of async ops released
 		gc=N	Number of deferred-release async ops garbage collected
+	CacheOp	alo=N	Number of in-progress alloc_object() cache ops
+		luo=N	Number of in-progress lookup_object() cache ops
+		luc=N	Number of in-progress lookup_complete() cache ops
+		gro=N	Number of in-progress grab_object() cache ops
+		upo=N	Number of in-progress update_object() cache ops
+		dro=N	Number of in-progress drop_object() cache ops
+		pto=N	Number of in-progress put_object() cache ops
+		syn=N	Number of in-progress sync_cache() cache ops
+		atc=N	Number of in-progress attr_changed() cache ops
+		rap=N	Number of in-progress read_or_alloc_page() cache ops
+		ras=N	Number of in-progress read_or_alloc_pages() cache ops
+		alp=N	Number of in-progress allocate_page() cache ops
+		als=N	Number of in-progress allocate_pages() cache ops
+		wrp=N	Number of in-progress write_page() cache ops
+		ucp=N	Number of in-progress uncache_page() cache ops
+		dsp=N	Number of in-progress dissociate_pages() cache ops
 
 
  (*) /proc/fs/fscache/histogram
@@ -299,6 +328,87 @@ proc files.
      jiffy range covered, and the SECS field the equivalent number of seconds.
 
 
+===========
+OBJECT LIST
+===========
+
+If CONFIG_FSCACHE_OBJECT_LIST is enabled, the FS-Cache facility will maintain a
+list of all the objects currently allocated and allow them to be viewed
+through:
+
+	/proc/fs/fscache/objects
+
+This will look something like:
+
+	[root@andromeda ~]# head /proc/fs/fscache/objects
+	OBJECT   PARENT   STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA       OBJECT_KEY, AUX_DATA
+	======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================
+	   17e4b        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a
+	   1693a        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a
+
+where the first set of columns before the '|' describe the object:
+
+	COLUMN	DESCRIPTION
+	=======	===============================================================
+	OBJECT	Object debugging ID (appears as OBJ%x in some debug messages)
+	PARENT	Debugging ID of parent object
+	STAT	Object state
+	CHLDN	Number of child objects of this object
+	OPS	Number of outstanding operations on this object
+	OOP	Number of outstanding child object management operations
+	IPR
+	EX	Number of outstanding exclusive operations
+	READS	Number of outstanding read operations
+	EM	Object's event mask
+	EV	Events raised on this object
+	F	Object flags
+	S	Object slow-work work item flags
+
+and the second set of columns describe the object's cookie, if present:
+
+	COLUMN		DESCRIPTION
+	===============	=======================================================
+	NETFS_COOKIE_DEF Name of netfs cookie definition
+	TY		Cookie type (IX - index, DT - data, hex - special)
+	FL		Cookie flags
+	NETFS_DATA	Netfs private data stored in the cookie
+	OBJECT_KEY	Object key	} 1 column, with separating comma
+	AUX_DATA	Object aux data	} presence may be configured
+
+The data shown may be filtered by attaching the a key to an appropriate keyring
+before viewing the file.  Something like:
+
+		keyctl add user fscache:objlist <restrictions> @s
+
+where <restrictions> are a selection of the following letters:
+
+	K	Show hexdump of object key (don't show if not given)
+	A	Show hexdump of object aux data (don't show if not given)
+
+and the following paired letters:
+
+	C	Show objects that have a cookie
+	c	Show objects that don't have a cookie
+	B	Show objects that are busy
+	b	Show objects that aren't busy
+	W	Show objects that have pending writes
+	w	Show objects that don't have pending writes
+	R	Show objects that have outstanding reads
+	r	Show objects that don't have outstanding reads
+	S	Show objects that have slow work queued
+	s	Show objects that don't have slow work queued
+
+If neither side of a letter pair is given, then both are implied.  For example:
+
+	keyctl add user fscache:objlist KB @s
+
+shows objects that are busy, and lists their object keys, but does not dump
+their auxiliary data.  It also implies "CcWwRrSs", but as 'B' is given, 'b' is
+not implied.
+
+By default all objects and all fields will be shown.
+
+
 =========
 DEBUGGING
 =========

Documentation/filesystems/caching/netfs-api.txt

@@ -641,7 +641,7 @@ data file must be retired (see the relinquish cookie function below).
 
 Furthermore, note that this does not cancel the asynchronous read or write
 operation started by the read/alloc and write functions, so the page
-invalidation and release functions must use:
+invalidation functions must use:
 
 	bool fscache_check_page_write(struct fscache_cookie *cookie,
 				      struct page *page);
@@ -654,6 +654,25 @@ to see if a page is being written to the cache, and:
 to wait for it to finish if it is.
 
 
+When releasepage() is being implemented, a special FS-Cache function exists to
+manage the heuristics of coping with vmscan trying to eject pages, which may
+conflict with the cache trying to write pages to the cache (which may itself
+need to allocate memory):
+
+	bool fscache_maybe_release_page(struct fscache_cookie *cookie,
+					struct page *page,
+					gfp_t gfp);
+
+This takes the netfs cookie, and the page and gfp arguments as supplied to
+releasepage().  It will return false if the page cannot be released yet for
+some reason and if it returns true, the page has been uncached and can now be
+released.
+
+To make a page available for release, this function may wait for an outstanding
+storage request to complete, or it may attempt to cancel the storage request -
+in which case the page will not be stored in the cache this time.
+
+
 ==========================
 INDEX AND DATA FILE UPDATE
 ==========================

Documentation/filesystems/ext3.txt

@@ -123,10 +123,18 @@ resuid=n		The user ID which may use the reserved blocks.
 
 sb=n			Use alternate superblock at this location.
 
-quota
-noquota
-grpquota
-usrquota
+quota			These options are ignored by the filesystem. They
+noquota			are used only by quota tools to recognize volumes
+grpquota		where quota should be turned on. See documentation
+usrquota		in the quota-tools package for more details
+			(http://sourceforge.net/projects/linuxquota).
+
+jqfmt=<quota type>	These options tell filesystem details about quota
+usrjquota=<file>	so that quota information can be properly updated
+grpjquota=<file>	during journal replay. They replace the above
+			quota options. See documentation in the quota-tools
+			package for more details
+			(http://sourceforge.net/projects/linuxquota).
 
 bh		(*)	ext3 associates buffer heads to data pages to
 nobh			(a) cache disk block mapping information

Documentation/filesystems/ext4.txt

@@ -134,9 +134,15 @@ ro                   	Mount filesystem read only. Note that ext4 will
                      	mount options "ro,noload" can be used to prevent
 		     	writes to the filesystem.
 
+journal_checksum	Enable checksumming of the journal transactions.
+			This will allow the recovery code in e2fsck and the
+			kernel to detect corruption in the kernel.  It is a
+			compatible change and will be ignored by older kernels.
+
 journal_async_commit	Commit block can be written to disk without waiting
 			for descriptor blocks. If enabled older kernels cannot
-			mount the device.
+			mount the device. This will enable 'journal_checksum'
+			internally.
 
 journal=update		Update the ext4 file system's journal to the current
 			format.
@@ -282,9 +288,16 @@ stripe=n		Number of filesystem blocks that mballoc will try
 			to use for allocation size and alignment. For RAID5/6
 			systems this should be the number of data
 			disks *  RAID chunk size in file system blocks.
-delalloc	(*)	Deferring block allocation until write-out time.
-nodelalloc		Disable delayed allocation. Blocks are allocation
-			when data is copied from user to page cache.
+
+delalloc	(*)	Defer block allocation until just before ext4
+			writes out the block(s) in question.  This
+			allows ext4 to better allocation decisions
+			more efficiently.
+nodelalloc		Disable delayed allocation.  Blocks are allocated
+			when the data is copied from userspace to the
+			page cache, either via the write(2) system call
+			or when an mmap'ed page which was previously
+			unallocated is written for the first time.
 
 max_batch_time=usec	Maximum amount of time ext4 should wait for
 			additional filesystem operations to be batch

Documentation/filesystems/ocfs2.txt

@@ -20,15 +20,16 @@ Lots of code taken from ext3 and other projects.
 Authors in alphabetical order:
 Joel Becker   <joel.becker@oracle.com>
 Zach Brown    <zach.brown@oracle.com>
-Mark Fasheh   <mark.fasheh@oracle.com>
+Mark Fasheh   <mfasheh@suse.com>
 Kurt Hackel   <kurt.hackel@oracle.com>
+Tao Ma        <tao.ma@oracle.com>
 Sunil Mushran <sunil.mushran@oracle.com>
 Manish Singh  <manish.singh@oracle.com>
+Tiger Yang    <tiger.yang@oracle.com>
 
 Caveats
 =======
 Features which OCFS2 does not support yet:
-	- quotas
 	- Directory change notification (F_NOTIFY)
 	- Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease)
 
@@ -70,7 +71,6 @@ commit=nrsec	(*)	Ocfs2 can be told to sync all its data and metadata
 			performance.
 localalloc=8(*)		Allows custom localalloc size in MB. If the value is too
 			large, the fs will silently revert it to the default.
-			Localalloc is not enabled for local mounts.
 localflocks		This disables cluster aware flock.
 inode64			Indicates that Ocfs2 is allowed to create inodes at
 			any location in the filesystem, including those which

Documentation/filesystems/proc.txt

@@ -1113,7 +1113,6 @@ Table 1-12: Files in /proc/fs/ext4/<devname>
 ..............................................................................
  File            Content                                        
  mb_groups       details of multiblock allocator buddy cache of free blocks
- mb_history      multiblock allocation history
 ..............................................................................
 
 

Documentation/filesystems/sharedsubtree.txt

@@ -4,7 +4,7 @@ Shared Subtrees
 Contents:
 	1) Overview
 	2) Features
-	3) smount command
+	3) Setting mount states
 	4) Use-case
 	5) Detailed semantics
 	6) Quiz
@@ -41,14 +41,14 @@ replicas continue to be exactly same.
 
 	Here is an example:
 
-	Lets say /mnt has a mount that is shared.
+	Let's say /mnt has a mount that is shared.
 	mount --make-shared /mnt
 
-	note: mount command does not yet support the --make-shared flag.
-	I have included a small C program which does the same by executing
-	'smount /mnt shared'
+	Note: mount(8) command now supports the --make-shared flag,
+	so the sample 'smount' program is no longer needed and has been
+	removed.
 
-	#mount --bind /mnt /tmp
+	# mount --bind /mnt /tmp
 	The above command replicates the mount at /mnt to the mountpoint /tmp
 	and the contents of both the mounts remain identical.
 
@@ -58,8 +58,8 @@ replicas continue to be exactly same.
 	#ls /tmp
 	a b c
 
-	Now lets say we mount a device at /tmp/a
-	#mount /dev/sd0  /tmp/a
+	Now let's say we mount a device at /tmp/a
+	# mount /dev/sd0  /tmp/a
 
 	#ls /tmp/a
 	t1 t2 t2
@@ -80,21 +80,20 @@ replicas continue to be exactly same.
 
 	Here is an example:
 
-	Lets say /mnt has a mount which is shared.
-	#mount --make-shared /mnt
+	Let's say /mnt has a mount which is shared.
+	# mount --make-shared /mnt
 
-	Lets bind mount /mnt to /tmp
-	#mount --bind /mnt /tmp
+	Let's bind mount /mnt to /tmp
+	# mount --bind /mnt /tmp
 
 	the new mount at /tmp becomes a shared mount and it is a replica of
 	the mount at /mnt.
 
-	Now lets make the mount at /tmp; a slave of /mnt
-	#mount --make-slave /tmp
-	[or smount /tmp slave]
+	Now let's make the mount at /tmp; a slave of /mnt
+	# mount --make-slave /tmp
 
-	lets mount /dev/sd0 on /mnt/a
-	#mount /dev/sd0 /mnt/a
+	let's mount /dev/sd0 on /mnt/a
+	# mount /dev/sd0 /mnt/a
 
 	#ls /mnt/a
 	t1 t2 t3
@@ -104,9 +103,9 @@ replicas continue to be exactly same.
 
 	Note the mount event has propagated to the mount at /tmp
 
-	However lets see what happens if we mount something on the mount at /tmp
+	However let's see what happens if we mount something on the mount at /tmp
 
-	#mount /dev/sd1 /tmp/b
+	# mount /dev/sd1 /tmp/b
 
 	#ls /tmp/b
 	s1 s2 s3
@@ -124,12 +123,11 @@ replicas continue to be exactly same.
 
 2d) A unbindable mount is a unbindable private mount
 
-	lets say we have a mount at /mnt and we make is unbindable
+	let's say we have a mount at /mnt and we make is unbindable
 
-	#mount --make-unbindable /mnt
-	 [ smount /mnt  unbindable ]
+	# mount --make-unbindable /mnt
 
-	 Lets try to bind mount this mount somewhere else.
+	 Let's try to bind mount this mount somewhere else.
 	 # mount --bind /mnt /tmp
 	 mount: wrong fs type, bad option, bad superblock on /mnt,
 	        or too many mounted file systems
@@ -137,149 +135,15 @@ replicas continue to be exactly same.
 	Binding a unbindable mount is a invalid operation.
 
 
-3) smount command
+3) Setting mount states
 
-	Currently the mount command is not aware of shared subtree features.
-	Work is in progress to add the support in mount ( util-linux package ).
-	Till then use the following program.
+	The mount command (util-linux package) can be used to set mount
+	states:
 
-	------------------------------------------------------------------------
-	//
-	//this code was developed my Miklos Szeredi <miklos@szeredi.hu>
-	//and modified by Ram Pai <linuxram@us.ibm.com>
-	// sample usage:
-	//              smount /tmp shared
-	//
-	#include <stdio.h>
-	#include <stdlib.h>
-	#include <unistd.h>
-	#include <string.h>
-	#include <sys/mount.h>
-	#include <sys/fsuid.h>
-
-	#ifndef MS_REC
-	#define MS_REC		0x4000	/* 16384: Recursive loopback */
-	#endif
-
-	#ifndef MS_SHARED
-	#define MS_SHARED		1<<20	/* Shared */
-	#endif
-
-	#ifndef MS_PRIVATE
-	#define MS_PRIVATE		1<<18	/* Private */
-	#endif
-
-	#ifndef MS_SLAVE
-	#define MS_SLAVE		1<<19	/* Slave */
-	#endif
-
-	#ifndef MS_UNBINDABLE
-	#define MS_UNBINDABLE		1<<17	/* Unbindable */
-	#endif
-
-	int main(int argc, char *argv[])
-	{
-		int type;
-		if(argc != 3) {
-			fprintf(stderr, "usage: %s dir "
-			"<rshared|rslave|rprivate|runbindable|shared|slave"
-			"|private|unbindable>\n" , argv[0]);
-			return 1;
-		}
-
-		fprintf(stdout, "%s %s %s\n", argv[0], argv[1], argv[2]);
-
-		if (strcmp(argv[2],"rshared")==0)
-			type=(MS_SHARED|MS_REC);
-		else if (strcmp(argv[2],"rslave")==0)
-			type=(MS_SLAVE|MS_REC);
-		else if (strcmp(argv[2],"rprivate")==0)
-			type=(MS_PRIVATE|MS_REC);
-		else if (strcmp(argv[2],"runbindable")==0)
-			type=(MS_UNBINDABLE|MS_REC);
-		else if (strcmp(argv[2],"shared")==0)
-			type=MS_SHARED;
-		else if (strcmp(argv[2],"slave")==0)
-			type=MS_SLAVE;
-		else if (strcmp(argv[2],"private")==0)
-			type=MS_PRIVATE;
-		else if (strcmp(argv[2],"unbindable")==0)
-			type=MS_UNBINDABLE;
-		else {
-			fprintf(stderr, "invalid operation: %s\n", argv[2]);
-			return 1;
-		}
-		setfsuid(getuid());
-
-		if(mount("", argv[1], "dontcare", type, "") == -1) {
-			perror("mount");
-			return 1;
-		}
-		return 0;
-	}
-	-----------------------------------------------------------------------
-
-	Copy the above code snippet into smount.c
-	gcc -o smount smount.c
-
-
-	(i) To mark all the mounts under /mnt as shared execute the following
-	command:
-
-	 	smount /mnt rshared
-		the corresponding syntax planned for mount command is
-		mount --make-rshared /mnt
-
-	    just to mark a mount /mnt as shared, execute the following
-	    command:
-	 	smount /mnt shared
-		the corresponding syntax planned for mount command is
-		mount --make-shared /mnt
-
-	(ii) To mark all the shared mounts under /mnt as slave execute the
-	following
-
-	     command:
-		smount /mnt rslave
-		the corresponding syntax planned for mount command is
-		mount --make-rslave /mnt
-
-	    just to mark a mount /mnt as slave, execute the following
-	    command:
-	 	smount /mnt slave
-		the corresponding syntax planned for mount command is
-		mount --make-slave /mnt
-
-	(iii) To mark all the mounts under /mnt as private execute the
-	following command:
-
-		smount /mnt rprivate
-		the corresponding syntax planned for mount command is
-		mount --make-rprivate /mnt
-
-	    just to mark a mount /mnt as private, execute the following
-	    command:
-	 	smount /mnt private
-		the corresponding syntax planned for mount command is
-		mount --make-private /mnt
-
-	      NOTE: by default all the mounts are created as private. But if
-	      you want to change some shared/slave/unbindable  mount as
-	      private at a later point in time, this command can help.
-
-	(iv) To mark all the mounts under /mnt as unbindable execute the
-	following
-
-	     command:
-		smount /mnt runbindable
-		the corresponding syntax planned for mount command is
-		mount --make-runbindable /mnt
-
-	    just to mark a mount /mnt as unbindable, execute the following
-	    command:
-	 	smount /mnt unbindable
-		the corresponding syntax planned for mount command is
-		mount --make-unbindable /mnt
+	mount --make-shared mountpoint
+	mount --make-slave mountpoint
+	mount --make-private mountpoint
+	mount --make-unbindable mountpoint
 
 
 4) Use cases
@@ -350,7 +214,7 @@ replicas continue to be exactly same.
 		mount --rbind / /view/v3
 		mount --rbind / /view/v4
 
-		and if /usr has a versioning filesystem mounted, than that
+		and if /usr has a versioning filesystem mounted, then that
 		mount appears at /view/v1/usr, /view/v2/usr, /view/v3/usr and
 		/view/v4/usr too
 
@@ -390,7 +254,7 @@ replicas continue to be exactly same.
 
 		For example:
 			mount --make-shared /mnt
-			mount --bin /mnt /tmp
+			mount --bind /mnt /tmp
 
 		The mount at /mnt and that at /tmp are both shared and belong
 		to the same peer group. Anything mounted or unmounted under
@@ -558,7 +422,7 @@ replicas continue to be exactly same.
 	then the subtree under the unbindable mount is pruned in the new
 	location.
 
-	eg: lets say we have the following mount tree.
+	eg: let's say we have the following mount tree.
 
 		A
 	      /   \
@@ -566,7 +430,7 @@ replicas continue to be exactly same.
 	     / \ / \
 	     D E F G
 
-	     Lets say all the mount except the mount C in the tree are
+	     Let's say all the mount except the mount C in the tree are
 	     of a type other than unbindable.
 
 	     If this tree is rbound to say Z
@@ -683,13 +547,13 @@ replicas continue to be exactly same.
 	'b' on mounts that receive propagation from mount 'B' and does not have
 	sub-mounts within them are unmounted.
 
-	Example: Lets say 'B1', 'B2', 'B3' are shared mounts that propagate to
+	Example: Let's say 'B1', 'B2', 'B3' are shared mounts that propagate to
 	each other.
 
-	lets say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount
+	let's say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount
 	'B1', 'B2' and 'B3' respectively.
 
-	lets say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on
+	let's say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on
 	mount 'B1', 'B2' and 'B3' respectively.
 
 	if 'C1' is unmounted, all the mounts that are most-recently-mounted on
@@ -710,7 +574,7 @@ replicas continue to be exactly same.
 	A cloned namespace contains all the mounts as that of the parent
 	namespace.
 
-	Lets say 'A' and 'B' are the corresponding mounts in the parent and the
+	Let's say 'A' and 'B' are the corresponding mounts in the parent and the
 	child namespace.
 
 	If 'A' is shared, then 'B' is also shared and 'A' and 'B' propagate to
@@ -759,11 +623,11 @@ replicas continue to be exactly same.
 		mount --make-slave /mnt
 
 		At this point we have the first mount at /tmp and
-		its root dentry is 1. Lets call this mount 'A'
+		its root dentry is 1. Let's call this mount 'A'
 		And then we have a second mount at /tmp1 with root
-		dentry 2. Lets call this mount 'B'
+		dentry 2. Let's call this mount 'B'
 		Next we have a third mount at /mnt with root dentry
-		mnt. Lets call this mount 'C'
+		mnt. Let's call this mount 'C'
 
 		'B' is the slave of 'A' and 'C' is a slave of 'B'
 		A -> B -> C
@@ -794,7 +658,7 @@ replicas continue to be exactly same.
 
 	Q3 Why is unbindable mount needed?
 
-		Lets say we want to replicate the mount tree at multiple
+		Let's say we want to replicate the mount tree at multiple
 		locations within the same subtree.
 
 		if one rbind mounts a tree within the same subtree 'n' times
@@ -803,7 +667,7 @@ replicas continue to be exactly same.
 		mounts. Here is a example.
 
 		step 1:
-		   lets say the root tree has just two directories with
+		   let's say the root tree has just two directories with
 		   one vfsmount.
 				    root
 				   /    \
@@ -875,7 +739,7 @@ replicas continue to be exactly same.
 		Unclonable mounts come in handy here.
 
 		step 1:
-		   lets say the root tree has just two directories with
+		   let's say the root tree has just two directories with
 		   one vfsmount.
 				    root
 				   /    \

Documentation/filesystems/vfat.txt

@@ -102,7 +102,7 @@ shortname=lower|win95|winnt|mixed
 		 winnt: emulate the Windows NT rule for display/create.
 		 mixed: emulate the Windows NT rule for display,
 			emulate the Windows 95 rule for create.
-		 Default setting is `lower'.
+		 Default setting is `mixed'.
 
 tz=UTC        -- Interpret timestamps as UTC rather than local time.
                  This option disables the conversion of timestamps

Documentation/filesystems/vfs.txt

@@ -536,6 +536,7 @@ struct address_space_operations {
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
+	int (*error_remove_page) (struct mapping *mapping, struct page *page);
 };
 
   writepage: called by the VM to write a dirty page to backing store.
@@ -694,6 +695,12 @@ struct address_space_operations {
   	prevent redirtying the page, it is kept locked during the whole
 	operation.
 
+  error_remove_page: normally set to generic_error_remove_page if truncation
+	is ok for this address space. Used for memory failure handling.
+	Setting this implies you deal with pages going away under you,
+	unless you have them locked or reference counts increased.
+
+
 The File Object
 ===============
 

Documentation/flexible-arrays.txt

@@ -1,5 +1,5 @@
 Using flexible arrays in the kernel
-Last updated for 2.6.31
+Last updated for 2.6.32
 Jonathan Corbet <corbet@lwn.net>
 
 Large contiguous memory allocations can be unreliable in the Linux kernel.
@@ -40,6 +40,13 @@ argument is passed directly to the internal memory allocation calls.  With
 the current code, using flags to ask for high memory is likely to lead to
 notably unpleasant side effects.
 
+It is also possible to define flexible arrays at compile time with:
+
+    DEFINE_FLEX_ARRAY(name, element_size, total);
+
+This macro will result in a definition of an array with the given name; the
+element size and total will be checked for validity at compile time.
+
 Storing data into a flexible array is accomplished with a call to:
 
     int flex_array_put(struct flex_array *array, unsigned int element_nr,
@@ -76,16 +83,30 @@ particular element has never been allocated.
 Note that it is possible to get back a valid pointer for an element which
 has never been stored in the array.  Memory for array elements is allocated
 one page at a time; a single allocation could provide memory for several
-adjacent elements.  The flexible array code does not know if a specific
-element has been written; it only knows if the associated memory is
-present.  So a flex_array_get() call on an element which was never stored
-in the array has the potential to return a pointer to random data.  If the
-caller does not have a separate way to know which elements were actually
-stored, it might be wise, at least, to add GFP_ZERO to the flags argument
-to ensure that all elements are zeroed.
-
-There is no way to remove a single element from the array.  It is possible,
-though, to remove all elements with a call to:
+adjacent elements.  Flexible array elements are normally initialized to the
+value FLEX_ARRAY_FREE (defined as 0x6c in <linux/poison.h>), so errors
+involving that number probably result from use of unstored array entries.
+Note that, if array elements are allocated with __GFP_ZERO, they will be
+initialized to zero and this poisoning will not happen.
+
+Individual elements in the array can be cleared with:
+
+    int flex_array_clear(struct flex_array *array, unsigned int element_nr);
+
+This function will set the given element to FLEX_ARRAY_FREE and return
+zero.  If storage for the indicated element is not allocated for the array,
+flex_array_clear() will return -EINVAL instead.  Note that clearing an
+element does not release the storage associated with it; to reduce the
+allocated size of an array, call:
+
+    int flex_array_shrink(struct flex_array *array);
+
+The return value will be the number of pages of memory actually freed.
+This function works by scanning the array for pages containing nothing but
+FLEX_ARRAY_FREE bytes, so (1) it can be expensive, and (2) it will not work
+if the array's pages are allocated with __GFP_ZERO.
+
+It is possible to remove all elements of an array with a call to:
 
     void flex_array_free_parts(struct flex_array *array);
 

Documentation/hwmon/coretemp

@@ -4,7 +4,9 @@ Kernel driver coretemp
 Supported chips:
   * All Intel Core family
     Prefix: 'coretemp'
-    CPUID: family 0x6, models 0xe, 0xf, 0x16, 0x17
+    CPUID: family 0x6, models 0xe (Pentium M DC), 0xf (Core 2 DC 65nm),
+                              0x16 (Core 2 SC 65nm), 0x17 (Penryn 45nm),
+                              0x1a (Nehalem), 0x1c (Atom), 0x1e (Lynnfield)
     Datasheet: Intel 64 and IA-32 Architectures Software Developer's Manual
                Volume 3A: System Programming Guide
                http://softwarecommunity.intel.com/Wiki/Mobility/720.htm

Documentation/hwmon/fscher

@@ -1,169 +0,0 @@
-Kernel driver fscher
-====================
-
-Supported chips:
-  * Fujitsu-Siemens Hermes chip
-    Prefix: 'fscher'
-    Addresses scanned: I2C 0x73
-
-Authors:
-        Reinhard Nissl <rnissl@gmx.de> based on work
-        from Hermann Jung <hej@odn.de>,
-        Frodo Looijaard <frodol@dds.nl>,
-        Philip Edelbrock <phil@netroedge.com>
-
-Description
------------
-
-This driver implements support for the Fujitsu-Siemens Hermes chip. It is
-described in the 'Register Set Specification BMC Hermes based Systemboard'
-from Fujitsu-Siemens.
-
-The Hermes chip implements a hardware-based system management, e.g. for
-controlling fan speed and core voltage. There is also a watchdog counter on
-the chip which can trigger an alarm and even shut the system down.
-
-The chip provides three temperature values (CPU, motherboard and
-auxiliary), three voltage values (+12V, +5V and battery) and three fans
-(power supply, CPU and auxiliary).
-
-Temperatures are measured in degrees Celsius. The resolution is 1 degree.
-
-Fan rotation speeds are reported in RPM (rotations per minute). The value
-can be divided by a programmable divider (1, 2 or 4) which is stored on
-the chip.
-
-Voltage sensors (also known as "in" sensors) report their values in volts.
-
-All values are reported as final values from the driver. There is no need
-for further calculations.
-
-
-Detailed description
---------------------
-
-Below you'll find a single line description of all the bit values. With
-this information, you're able to decode e. g. alarms, wdog, etc. To make
-use of the watchdog, you'll need to set the watchdog time and enable the
-watchdog. After that it is necessary to restart the watchdog time within
-the specified period of time, or a system reset will occur.
-
-* revision
-  READING & 0xff = 0x??: HERMES revision identification
-
-* alarms
-  READING & 0x80 = 0x80: CPU throttling active
-  READING & 0x80 = 0x00: CPU running at full speed
-
-  READING & 0x10 = 0x10: software event (see control:1)
-  READING & 0x10 = 0x00: no software event
-
-  READING & 0x08 = 0x08: watchdog event (see wdog:2)
-  READING & 0x08 = 0x00: no watchdog event
-
-  READING & 0x02 = 0x02: thermal event (see temp*:1)
-  READING & 0x02 = 0x00: no thermal event
-
-  READING & 0x01 = 0x01: fan event (see fan*:1)
-  READING & 0x01 = 0x00: no fan event
-
-  READING & 0x13 ! 0x00: ALERT LED is flashing
-
-* control
-  READING & 0x01 = 0x01: software event
-  READING & 0x01 = 0x00: no software event
-
-  WRITING & 0x01 = 0x01: set software event
-  WRITING & 0x01 = 0x00: clear software event
-
-* watchdog_control
-  READING & 0x80 = 0x80: power off on watchdog event while thermal event
-  READING & 0x80 = 0x00: watchdog power off disabled (just system reset enabled)
-
-  READING & 0x40 = 0x40: watchdog timebase 60 seconds (see also wdog:1)
-  READING & 0x40 = 0x00: watchdog timebase  2 seconds
-
-  READING & 0x10 = 0x10: watchdog enabled
-  READING & 0x10 = 0x00: watchdog disabled
-
-  WRITING & 0x80 = 0x80: enable "power off on watchdog event while thermal event"
-  WRITING & 0x80 = 0x00: disable "power off on watchdog event while thermal event"
-
-  WRITING & 0x40 = 0x40: set watchdog timebase to 60 seconds
-  WRITING & 0x40 = 0x00: set watchdog timebase to  2 seconds
-
-  WRITING & 0x20 = 0x20: disable watchdog
-
-  WRITING & 0x10 = 0x10: enable watchdog / restart watchdog time
-
-* watchdog_state
-  READING & 0x02 = 0x02: watchdog system reset occurred
-  READING & 0x02 = 0x00: no watchdog system reset occurred
-
-  WRITING & 0x02 = 0x02: clear watchdog event
-
-* watchdog_preset
-  READING & 0xff = 0x??: configured watch dog time in units (see wdog:3 0x40)
-
-  WRITING & 0xff = 0x??: configure watch dog time in units
-
-* in*     (0: +5V, 1: +12V, 2: onboard 3V battery)
-  READING: actual voltage value
-
-* temp*_status   (1: CPU sensor, 2: onboard sensor, 3: auxiliary sensor)
-  READING & 0x02 = 0x02: thermal event (overtemperature)
-  READING & 0x02 = 0x00: no thermal event
-
-  READING & 0x01 = 0x01: sensor is working
-  READING & 0x01 = 0x00: sensor is faulty
-
-  WRITING & 0x02 = 0x02: clear thermal event
-
-* temp*_input   (1: CPU sensor, 2: onboard sensor, 3: auxiliary sensor)
-  READING: actual temperature value
-
-* fan*_status   (1: power supply fan, 2: CPU fan, 3: auxiliary fan)
-  READING & 0x04 = 0x04: fan event (fan fault)
-  READING & 0x04 = 0x00: no fan event
-
-  WRITING & 0x04 = 0x04: clear fan event
-
-* fan*_div (1: power supply fan, 2: CPU fan, 3: auxiliary fan)
-  	Divisors 2,4 and 8 are supported, both for reading and writing
-
-* fan*_pwm   (1: power supply fan, 2: CPU fan, 3: auxiliary fan)
-  READING & 0xff = 0x00: fan may be switched off
-  READING & 0xff = 0x01: fan must run at least at minimum speed (supply: 6V)
-  READING & 0xff = 0xff: fan must run at maximum speed (supply: 12V)
-  READING & 0xff = 0x??: fan must run at least at given speed (supply: 6V..12V)
-
-  WRITING & 0xff = 0x00: fan may be switched off
-  WRITING & 0xff = 0x01: fan must run at least at minimum speed (supply: 6V)
-  WRITING & 0xff = 0xff: fan must run at maximum speed (supply: 12V)
-  WRITING & 0xff = 0x??: fan must run at least at given speed (supply: 6V..12V)
-
-* fan*_input   (1: power supply fan, 2: CPU fan, 3: auxiliary fan)
-  READING: actual RPM value
-
-
-Limitations
------------
-
-* Measuring fan speed
-It seems that the chip counts "ripples" (typical fans produce 2 ripples per
-rotation while VERAX fans produce 18) in a 9-bit register. This register is
-read out every second, then the ripple prescaler (2, 4 or 8) is applied and
-the result is stored in the 8 bit output register. Due to the limitation of
-the counting register to 9 bits, it is impossible to measure a VERAX fan
-properly (even with a prescaler of 8). At its maximum speed of 3500 RPM the
-fan produces 1080 ripples per second which causes the counting register to
-overflow twice, leading to only 186 RPM.
-
-* Measuring input voltages
-in2 ("battery") reports the voltage of the onboard lithium battery and not
-+3.3V from the power supply.
-
-* Undocumented features
-Fujitsu-Siemens Computers has not documented all features of the chip so
-far. Their software, System Guard, shows that there are a still some
-features which cannot be controlled by this implementation.

Documentation/hwmon/ltc4215

@@ -22,12 +22,13 @@ Usage Notes
 -----------
 
 This driver does not probe for LTC4215 devices, due to the fact that some
-of the possible addresses are unfriendly to probing. You will need to use
-the "force" parameter to tell the driver where to find the device.
+of the possible addresses are unfriendly to probing. You will have to
+instantiate the devices explicitly.
 
 Example: the following will load the driver for an LTC4215 at address 0x44
 on I2C bus #0:
-$ modprobe ltc4215 force=0,0x44
+$ modprobe ltc4215
+$ echo ltc4215 0x44 > /sys/bus/i2c/devices/i2c-0/new_device
 
 
 Sysfs entries

Documentation/hwmon/ltc4245

@@ -23,12 +23,13 @@ Usage Notes
 -----------
 
 This driver does not probe for LTC4245 devices, due to the fact that some
-of the possible addresses are unfriendly to probing. You will need to use
-the "force" parameter to tell the driver where to find the device.
+of the possible addresses are unfriendly to probing. You will have to
+instantiate the devices explicitly.
 
 Example: the following will load the driver for an LTC4245 at address 0x23
 on I2C bus #1:
-$ modprobe ltc4245 force=1,0x23
+$ modprobe ltc4245
+$ echo ltc4245 0x23 > /sys/bus/i2c/devices/i2c-1/new_device
 
 
 Sysfs entries

Documentation/hwmon/sysfs-interface

@@ -353,10 +353,20 @@ power[1-*]_average		Average power use
 				Unit: microWatt
 				RO
 
-power[1-*]_average_interval	Power use averaging interval
+power[1-*]_average_interval	Power use averaging interval.  A poll
+				notification is sent to this file if the
+				hardware changes the averaging interval.
 				Unit: milliseconds
 				RW
 
+power[1-*]_average_interval_max	Maximum power use averaging interval
+				Unit: milliseconds
+				RO
+
+power[1-*]_average_interval_min	Minimum power use averaging interval
+				Unit: milliseconds
+				RO
+
 power[1-*]_average_highest	Historical average maximum power use
 				Unit: microWatt
 				RO
@@ -365,6 +375,18 @@ power[1-*]_average_lowest	Historical average minimum power use
 				Unit: microWatt
 				RO
 
+power[1-*]_average_max		A poll notification is sent to
+				power[1-*]_average when power use
+				rises above this value.
+				Unit: microWatt
+				RW
+
+power[1-*]_average_min		A poll notification is sent to
+				power[1-*]_average when power use
+				sinks below this value.
+				Unit: microWatt
+				RW
+
 power[1-*]_input		Instantaneous power use
 				Unit: microWatt
 				RO
@@ -381,6 +403,39 @@ power[1-*]_reset_history	Reset input_highest, input_lowest,
 				average_highest and average_lowest.
 				WO
 
+power[1-*]_accuracy		Accuracy of the power meter.
+				Unit: Percent
+				RO
+
+power[1-*]_alarm		1 if the system is drawing more power than the
+				cap allows; 0 otherwise.  A poll notification is
+				sent to this file when the power use exceeds the
+				cap.  This file only appears if the cap is known
+				to be enforced by hardware.
+				RO
+
+power[1-*]_cap			If power use rises above this limit, the
+				system should take action to reduce power use.
+				A poll notification is sent to this file if the
+				cap is changed by the hardware.  The *_cap
+				files only appear if the cap is known to be
+				enforced by hardware.
+				Unit: microWatt
+				RW
+
+power[1-*]_cap_hyst		Margin of hysteresis built around capping and
+				notification.
+				Unit: microWatt
+				RW
+
+power[1-*]_cap_max		Maximum cap that can be set.
+				Unit: microWatt
+				RO
+
+power[1-*]_cap_min		Minimum cap that can be set.
+				Unit: microWatt
+				RO
+
 **********
 * Energy *
 **********

Documentation/i2c/busses/i2c-piix4

@@ -8,7 +8,7 @@ Supported adapters:
     Datasheet: Only available via NDA from ServerWorks
   * ATI IXP200, IXP300, IXP400, SB600, SB700 and SB800 southbridges
     Datasheet: Not publicly available
-  * AMD SB900
+  * AMD Hudson-2
     Datasheet: Not publicly available
   * Standard Microsystems (SMSC) SLC90E66 (Victory66) southbridge
     Datasheet: Publicly available at the SMSC website http://www.smsc.com

Documentation/i2c/instantiating-devices

@@ -188,7 +188,7 @@ segment, the address is sufficient to uniquely identify the device to be
 deleted.
 
 Example:
-# echo eeprom 0x50 > /sys/class/i2c-adapter/i2c-3/new_device
+# echo eeprom 0x50 > /sys/bus/i2c/devices/i2c-3/new_device
 
 While this interface should only be used when in-kernel device declaration
 can't be done, there is a variety of cases where it can be helpful:

Documentation/infiniband/user_mad.txt

@@ -128,8 +128,8 @@ Setting IsSM Capability Bit
   To create the appropriate character device files automatically with
   udev, a rule like
 
-    KERNEL="umad*", NAME="infiniband/%k"
-    KERNEL="issm*", NAME="infiniband/%k"
+    KERNEL=="umad*", NAME="infiniband/%k"
+    KERNEL=="issm*", NAME="infiniband/%k"
 
   can be used.  This will create device nodes named
 

Documentation/infiniband/user_verbs.txt

@@ -58,7 +58,7 @@ Memory pinning
   To create the appropriate character device files automatically with
   udev, a rule like
 
-    KERNEL="uverbs*", NAME="infiniband/%k"
+    KERNEL=="uverbs*", NAME="infiniband/%k"
 
   can be used.  This will create device nodes named
 

Documentation/ioctl/ioctl-number.txt

@@ -135,6 +135,7 @@ Code	Seq#	Include File		Comments
 					<http://mikonos.dia.unisa.it/tcfs>
 'l'	40-7F	linux/udf_fs_i.h	in development:
 					<http://sourceforge.net/projects/linux-udf/>
+'m'	00-09	linux/mmtimer.h
 'm'	all	linux/mtio.h		conflict!
 'm'	all	linux/soundcard.h	conflict!
 'm'	all	linux/synclink.h	conflict!

Documentation/isdn/INTERFACE.CAPI

@@ -60,10 +60,9 @@ open() operation on regular files or character devices.
 
 After a successful return from register_appl(), CAPI messages from the
 application may be passed to the driver for the device via calls to the
-send_message() callback function. The CAPI message to send is stored in the
-data portion of an skb. Conversely, the driver may call Kernel CAPI's
-capi_ctr_handle_message() function to pass a received CAPI message to Kernel
-CAPI for forwarding to an application, specifying its ApplID.
+send_message() callback function. Conversely, the driver may call Kernel
+CAPI's capi_ctr_handle_message() function to pass a received CAPI message to
+Kernel CAPI for forwarding to an application, specifying its ApplID.
 
 Deregistration requests (CAPI operation CAPI_RELEASE) from applications are
 forwarded as calls to the release_appl() callback function, passing the same
@@ -142,6 +141,7 @@ u16  (*send_message)(struct capi_ctr *ctrlr, struct sk_buff *skb)
 	to accepting or queueing the message. Errors occurring during the
 	actual processing of the message should be signaled with an
 	appropriate reply message.
+	May be called in process or interrupt context.
 	Calls to this function are not serialized by Kernel CAPI, ie. it must
 	be prepared to be re-entered.
 
@@ -154,7 +154,8 @@ read_proc_t *ctr_read_proc
 	system entry, /proc/capi/controllers/<n>; will be called with a
 	pointer to the device's capi_ctr structure as the last (data) argument
 
-Note: Callback functions are never called in interrupt context.
+Note: Callback functions except send_message() are never called in interrupt
+context.
 
 - to be filled in before calling capi_ctr_ready():
 
@@ -171,14 +172,40 @@ u8 serial[CAPI_SERIAL_LEN]
 	value to return for CAPI_GET_SERIAL
 
 
-4.3 The _cmsg Structure
+4.3 SKBs
+
+CAPI messages are passed between Kernel CAPI and the driver via send_message()
+and capi_ctr_handle_message(), stored in the data portion of a socket buffer
+(skb).  Each skb contains a single CAPI message coded according to the CAPI 2.0
+standard.
+
+For the data transfer messages, DATA_B3_REQ and DATA_B3_IND, the actual
+payload data immediately follows the CAPI message itself within the same skb.
+The Data and Data64 parameters are not used for processing. The Data64
+parameter may be omitted by setting the length field of the CAPI message to 22
+instead of 30.
+
+
+4.4 The _cmsg Structure
 
 (declared in <linux/isdn/capiutil.h>)
 
 The _cmsg structure stores the contents of a CAPI 2.0 message in an easily
-accessible form. It contains members for all possible CAPI 2.0 parameters, of
-which only those appearing in the message type currently being processed are
-actually used. Unused members should be set to zero.
+accessible form. It contains members for all possible CAPI 2.0 parameters,
+including subparameters of the Additional Info and B Protocol structured
+parameters, with the following exceptions:
+
+* second Calling party number (CONNECT_IND)
+
+* Data64 (DATA_B3_REQ and DATA_B3_IND)
+
+* Sending complete (subparameter of Additional Info, CONNECT_REQ and INFO_REQ)
+
+* Global Configuration (subparameter of B Protocol, CONNECT_REQ, CONNECT_RESP
+  and SELECT_B_PROTOCOL_REQ)
+
+Only those parameters appearing in the message type currently being processed
+are actually used. Unused members should be set to zero.
 
 Members are named after the CAPI 2.0 standard names of the parameters they
 represent. See <linux/isdn/capiutil.h> for the exact spelling. Member data
@@ -190,18 +217,19 @@ u16         for CAPI parameters of type 'word'
 
 u32         for CAPI parameters of type 'dword'
 
-_cstruct    for CAPI parameters of type 'struct' not containing any
-	    variably-sized (struct) subparameters (eg. 'Called Party Number')
+_cstruct    for CAPI parameters of type 'struct'
 	    The member is a pointer to a buffer containing the parameter in
 	    CAPI encoding (length + content). It may also be NULL, which will
 	    be taken to represent an empty (zero length) parameter.
+	    Subparameters are stored in encoded form within the content part.
 
-_cmstruct   for CAPI parameters of type 'struct' containing 'struct'
-	    subparameters ('Additional Info' and 'B Protocol')
+_cmstruct   alternative representation for CAPI parameters of type 'struct'
+	    (used only for the 'Additional Info' and 'B Protocol' parameters)
 	    The representation is a single byte containing one of the values:
-	    CAPI_DEFAULT: the parameter is empty
-	    CAPI_COMPOSE: the values of the subparameters are stored
-	    individually in the corresponding _cmsg structure members
+	    CAPI_DEFAULT: The parameter is empty/absent.
+	    CAPI_COMPOSE: The parameter is present.
+	    Subparameter values are stored individually in the corresponding
+	    _cmsg structure members.
 
 Functions capi_cmsg2message() and capi_message2cmsg() are provided to convert
 messages between their transport encoding described in the CAPI 2.0 standard
@@ -297,3 +325,26 @@ char *capi_cmd2str(u8 Command, u8 Subcommand)
 	be NULL if the command/subcommand is not one of those defined in the
 	CAPI 2.0 standard.
 
+
+7. Debugging
+
+The module kernelcapi has a module parameter showcapimsgs controlling some
+debugging output produced by the module. It can only be set when the module is
+loaded, via a parameter "showcapimsgs=<n>" to the modprobe command, either on
+the command line or in the configuration file.
+
+If the lowest bit of showcapimsgs is set, kernelcapi logs controller and
+application up and down events.
+
+In addition, every registered CAPI controller has an associated traceflag
+parameter controlling how CAPI messages sent from and to tha controller are
+logged. The traceflag parameter is initialized with the value of the
+showcapimsgs parameter when the controller is registered, but can later be
+changed via the MANUFACTURER_REQ command KCAPI_CMD_TRACE.
+
+If the value of traceflag is non-zero, CAPI messages are logged.
+DATA_B3 messages are only logged if the value of traceflag is > 2.
+
+If the lowest bit of traceflag is set, only the command/subcommand and message
+length are logged. Otherwise, kernelcapi logs a readable representation of
+the entire message.

Documentation/kbuild/kbuild.txt

@@ -65,6 +65,22 @@ INSTALL_PATH
 INSTALL_PATH specifies where to place the updated kernel and system map
 images. Default is /boot, but you can set it to other values.
 
+INSTALLKERNEL
+--------------------------------------------------
+Install script called when using "make install".
+The default name is "installkernel".
+
+The script will be called with the following arguments:
+    $1 - kernel version
+    $2 - kernel image file
+    $3 - kernel map file
+    $4 - default install path (use root directory if blank)
+
+The implmentation of "make install" is architecture specific
+and it may differ from the above.
+
+INSTALLKERNEL is provided to enable the possibility to
+specify a custom installer when cross compiling a kernel.
 
 MODLIB
 --------------------------------------------------

Documentation/kbuild/makefiles.txt

@@ -18,6 +18,7 @@ This document describes the Linux kernel Makefiles.
 	   --- 3.9 Dependency tracking
 	   --- 3.10 Special Rules
 	   --- 3.11 $(CC) support functions
+	   --- 3.12 $(LD) support functions
 
 	=== 4 Host Program support
 	   --- 4.1 Simple Host Program
@@ -435,14 +436,14 @@ more details, with real examples.
 	The second argument is optional, and if supplied will be used
 	if first argument is not supported.
 
-    ld-option
-	ld-option is used to check if $(CC) when used to link object files
+    cc-ldoption
+	cc-ldoption is used to check if $(CC) when used to link object files
 	supports the given option.  An optional second option may be
 	specified if first option are not supported.
 
 	Example:
 		#arch/i386/kernel/Makefile
-		vsyscall-flags += $(call ld-option, -Wl$(comma)--hash-style=sysv)
+		vsyscall-flags += $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 
 	In the above example, vsyscall-flags will be assigned the option
 	-Wl$(comma)--hash-style=sysv if it is supported by $(CC).
@@ -570,6 +571,19 @@ more details, with real examples.
 			endif
 		endif
 
+--- 3.12 $(LD) support functions
+
+    ld-option
+	ld-option is used to check if $(LD) supports the supplied option.
+	ld-option takes two options as arguments.
+	The second argument is an optional option that can be used if the
+	first option is not supported by $(LD).
+
+	Example:
+		#Makefile
+		LDFLAGS_vmlinux += $(call really-ld-option, -X)
+
+
 === 4 Host Program support
 
 Kbuild supports building executables on the host for use during the

Documentation/kernel-parameters.txt

@@ -85,7 +85,6 @@ parameter is applicable:
 	PPT	Parallel port support is enabled.
 	PS2	Appropriate PS/2 support is enabled.
 	RAM	RAM disk support is enabled.
-	ROOTPLUG The example Root Plug LSM is enabled.
 	S390	S390 architecture is enabled.
 	SCSI	Appropriate SCSI support is enabled.
 			A lot of drivers has their options described inside of
@@ -671,6 +670,7 @@ and is between 256 and 4096 characters. It is defined in the file
 	earlyprintk=	[X86,SH,BLACKFIN]
 			earlyprintk=vga
 			earlyprintk=serial[,ttySn[,baudrate]]
+			earlyprintk=ttySn[,baudrate]
 			earlyprintk=dbgp[debugController#]
 
 			Append ",keep" to not disable it when the real console
@@ -2163,15 +2163,6 @@ and is between 256 and 4096 characters. It is defined in the file
 			Useful for devices that are detected asynchronously
 			(e.g. USB and MMC devices).
 
-	root_plug.vendor_id=
-			[ROOTPLUG] Override the default vendor ID
-
-	root_plug.product_id=
-			[ROOTPLUG] Override the default product ID
-
-	root_plug.debug=
-			[ROOTPLUG] Enable debugging output
-
 	rw		[KNL] Mount root device read-write on boot
 
 	S		[KNL] Run init in single mode

Documentation/laptops/thinkpad-acpi.txt

@@ -199,18 +199,22 @@ kind to allow it (and it often doesn't!).
 
 Not all bits in the mask can be modified.  Not all bits that can be
 modified do anything.  Not all hot keys can be individually controlled
-by the mask.  Some models do not support the mask at all, and in those
-models, hot keys cannot be controlled individually.  The behaviour of
-the mask is, therefore, highly dependent on the ThinkPad model.
+by the mask.  Some models do not support the mask at all.  The behaviour
+of the mask is, therefore, highly dependent on the ThinkPad model.
+
+The driver will filter out any unmasked hotkeys, so even if the firmware
+doesn't allow disabling an specific hotkey, the driver will not report
+events for unmasked hotkeys.
 
 Note that unmasking some keys prevents their default behavior.  For
 example, if Fn+F5 is unmasked, that key will no longer enable/disable
-Bluetooth by itself.
+Bluetooth by itself in firmware.
 
-Note also that not all Fn key combinations are supported through ACPI.
-For example, on the X40, the brightness, volume and "Access IBM" buttons
-do not generate ACPI events even with this driver.  They *can* be used
-through the "ThinkPad Buttons" utility, see http://www.nongnu.org/tpb/
+Note also that not all Fn key combinations are supported through ACPI
+depending on the ThinkPad model and firmware version.  On those
+ThinkPads, it is still possible to support some extra hotkeys by
+polling the "CMOS NVRAM" at least 10 times per second.  The driver
+attempts to enables this functionality automatically when required.
 
 procfs notes:
 
@@ -255,18 +259,11 @@ sysfs notes:
 		1: does nothing
 
 	hotkey_mask:
-		bit mask to enable driver-handling (and depending on
+		bit mask to enable reporting (and depending on
 		the firmware, ACPI event generation) for each hot key
 		(see above).  Returns the current status of the hot keys
 		mask, and allows one to modify it.
 
-		Note: when NVRAM polling is active, the firmware mask
-		will be different from the value returned by
-		hotkey_mask.  The driver will retain enabled bits for
-		hotkeys that are under NVRAM polling even if the
-		firmware refuses them, and will not set these bits on
-		the firmware hot key mask.
-
 	hotkey_all_mask:
 		bit mask that should enable event reporting for all
 		supported hot keys, when echoed to hotkey_mask above.
@@ -279,7 +276,8 @@ sysfs notes:
 		bit mask that should enable event reporting for all
 		supported hot keys, except those which are always
 		handled by the firmware anyway.  Echo it to
-		hotkey_mask above, to use.
+		hotkey_mask above, to use.  This is the default mask
+		used by the driver.
 
 	hotkey_source_mask:
 		bit mask that selects which hot keys will the driver
@@ -287,9 +285,10 @@ sysfs notes:
 		based on the capabilities reported by the ACPI firmware,
 		but it can be overridden at runtime.
 
-		Hot keys whose bits are set in both hotkey_source_mask
-		and also on hotkey_mask are polled for in NVRAM.  Only a
-		few hot keys are available through CMOS NVRAM polling.
+		Hot keys whose bits are set in hotkey_source_mask are
+		polled for in NVRAM, and reported as hotkey events if
+		enabled in hotkey_mask.  Only a few hot keys are
+		available through CMOS NVRAM polling.
 
 		Warning: when in NVRAM mode, the volume up/down/mute
 		keys are synthesized according to changes in the mixer,
@@ -525,6 +524,7 @@ compatibility purposes when hotkey_report_mode is set to 1.
 0x2305		System is waking up from suspend to eject bay
 0x2404		System is waking up from hibernation to undock
 0x2405		System is waking up from hibernation to eject bay
+0x5010		Brightness level changed/control event
 
 The above events are never propagated by the driver.
 
@@ -532,7 +532,6 @@ The above events are never propagated by the driver.
 0x4003		Undocked (see 0x2x04), can sleep again
 0x500B		Tablet pen inserted into its storage bay
 0x500C		Tablet pen removed from its storage bay
-0x5010		Brightness level changed (newer Lenovo BIOSes)
 
 The above events are propagated by the driver.
 
@@ -621,6 +620,8 @@ For Lenovo models *with* ACPI backlight control:
 2. Do *NOT* load up ACPI video, enable the hotkeys in thinkpad-acpi,
    and map them to KEY_BRIGHTNESS_UP and KEY_BRIGHTNESS_DOWN.  Process
    these keys on userspace somehow (e.g. by calling xbacklight).
+   The driver will do this automatically if it detects that ACPI video
+   has been disabled.
 
 
 Bluetooth
@@ -1459,3 +1460,8 @@ Sysfs interface changelog:
 0x020400:	Marker for 16 LEDs support.  Also, LEDs that are known
 		to not exist in a given model are not registered with
 		the LED sysfs class anymore.
+
+0x020500:	Updated hotkey driver, hotkey_mask is always available
+		and it is always able to disable hot keys.  Very old
+		thinkpads are properly supported.  hotkey_bios_mask
+		is deprecated and marked for removal.

Documentation/lguest/lguest.c

@@ -42,7 +42,6 @@
 #include <signal.h>
 #include "linux/lguest_launcher.h"
 #include "linux/virtio_config.h"
-#include <linux/virtio_ids.h>
 #include "linux/virtio_net.h"
 #include "linux/virtio_blk.h"
 #include "linux/virtio_console.h"

Documentation/i2c/chips/max6875 → Documentation/misc-devices/max6875

@@ -42,10 +42,12 @@ General Remarks
 
 Valid addresses for the MAX6875 are 0x50 and 0x52.
 Valid addresses for the MAX6874 are 0x50, 0x52, 0x54 and 0x56.
-The driver does not probe any address, so you must force the address.
+The driver does not probe any address, so you explicitly instantiate the
+devices.
 
 Example:
-$ modprobe max6875 force=0,0x50
+$ modprobe max6875
+$ echo max6875 0x50 > /sys/bus/i2c/devices/i2c-0/new_device
 
 The MAX6874/MAX6875 ignores address bit 0, so this driver attaches to multiple
 addresses.  For example, for address 0x50, it also reserves 0x51.

Documentation/networking/pktgen.txt

@@ -90,6 +90,11 @@ Examples:
  pgset "dstmac 00:00:00:00:00:00"    sets MAC destination address
  pgset "srcmac 00:00:00:00:00:00"    sets MAC source address
 
+ pgset "queue_map_min 0" Sets the min value of tx queue interval
+ pgset "queue_map_max 7" Sets the max value of tx queue interval, for multiqueue devices
+                         To select queue 1 of a given device,
+                         use queue_map_min=1 and queue_map_max=1
+
  pgset "src_mac_count 1" Sets the number of MACs we'll range through.  
                          The 'minimum' MAC is what you set with srcmac.
 
@@ -101,6 +106,9 @@ Examples:
                               IPDST_RND, UDPSRC_RND,
                               UDPDST_RND, MACSRC_RND, MACDST_RND 
                               MPLS_RND, VID_RND, SVID_RND
+                              QUEUE_MAP_RND # queue map random
+                              QUEUE_MAP_CPU # queue map mirrors smp_processor_id()
+
 
  pgset "udp_src_min 9"   set UDP source port min, If < udp_src_max, then
                          cycle through the port range.

Documentation/networking/timestamping/timestamping.c

@@ -381,7 +381,7 @@ int main(int argc, char **argv)
 	memset(&hwtstamp, 0, sizeof(hwtstamp));
 	strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name));
 	hwtstamp.ifr_data = (void *)&hwconfig;
-	memset(&hwconfig, 0, sizeof(&hwconfig));
+	memset(&hwconfig, 0, sizeof(hwconfig));
 	hwconfig.tx_type =
 		(so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ?
 		HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;

Documentation/pcmcia/driver-changes.txt

@@ -1,5 +1,17 @@
 This file details changes in 2.6 which affect PCMCIA card driver authors:
 
+* no cs_error / CS_CHECK / CONFIG_PCMCIA_DEBUG (as of 2.6.33)
+   Instead of the cs_error() callback or the CS_CHECK() macro, please use
+   Linux-style checking of return values, and -- if necessary -- debug
+   messages using "dev_dbg()" or "pr_debug()".
+
+* New CIS tuple access (as of 2.6.33)
+   Instead of pcmcia_get_{first,next}_tuple(), pcmcia_get_tuple_data() and
+   pcmcia_parse_tuple(), a driver shall use "pcmcia_get_tuple()" if it is
+   only interested in one (raw) tuple, or "pcmcia_loop_tuple()" if it is
+   interested in all tuples of one type. To decode the MAC from CISTPL_FUNCE,
+   a new helper "pcmcia_get_mac_from_cis()" was added.
+
 * New configuration loop helper (as of 2.6.28)
    By calling pcmcia_loop_config(), a driver can iterate over all available
    configuration options. During a driver's probe() phase, one doesn't need

Documentation/power/power_supply_class.txt

@@ -76,6 +76,11 @@ STATUS - this attribute represents operating status (charging, full,
 discharging (i.e. powering a load), etc.). This corresponds to
 BATTERY_STATUS_* values, as defined in battery.h.
 
+CHARGE_TYPE - batteries can typically charge at different rates.
+This defines trickle and fast charges.  For batteries that
+are already charged or discharging, 'n/a' can be displayed (or
+'unknown', if the status is not known).
+
 HEALTH - represents health of the battery, values corresponds to
 POWER_SUPPLY_HEALTH_*, defined in battery.h.
 
@@ -108,6 +113,8 @@ relative, time-based measurements.
 ENERGY_FULL, ENERGY_EMPTY - same as above but for energy.
 
 CAPACITY - capacity in percents.
+CAPACITY_LEVEL - capacity level. This corresponds to
+POWER_SUPPLY_CAPACITY_LEVEL_*.
 
 TEMP - temperature of the power supply.
 TEMP_AMBIENT - ambient temperature.

Documentation/powerpc/dts-bindings/mtd-physmap.txt

@@ -1,18 +1,19 @@
-CFI or JEDEC memory-mapped NOR flash
+CFI or JEDEC memory-mapped NOR flash, MTD-RAM (NVRAM...)
 
 Flash chips (Memory Technology Devices) are often used for solid state
 file systems on embedded devices.
 
- - compatible : should contain the specific model of flash chip(s)
-   used, if known, followed by either "cfi-flash" or "jedec-flash"
- - reg : Address range(s) of the flash chip(s)
+ - compatible : should contain the specific model of mtd chip(s)
+   used, if known, followed by either "cfi-flash", "jedec-flash"
+   or "mtd-ram".
+ - reg : Address range(s) of the mtd chip(s)
    It's possible to (optionally) define multiple "reg" tuples so that
-   non-identical NOR chips can be described in one flash node.
- - bank-width : Width (in bytes) of the flash bank.  Equal to the
+   non-identical chips can be described in one node.
+ - bank-width : Width (in bytes) of the bank.  Equal to the
    device width times the number of interleaved chips.
- - device-width : (optional) Width of a single flash chip.  If
+ - device-width : (optional) Width of a single mtd chip.  If
    omitted, assumed to be equal to 'bank-width'.
- - #address-cells, #size-cells : Must be present if the flash has
+ - #address-cells, #size-cells : Must be present if the device has
    sub-nodes representing partitions (see below).  In this case
    both #address-cells and #size-cells must be equal to 1.
 
@@ -22,24 +23,24 @@ are defined:
  - vendor-id : Contains the flash chip's vendor id (1 byte).
  - device-id : Contains the flash chip's device id (1 byte).
 
-In addition to the information on the flash bank itself, the
+In addition to the information on the mtd bank itself, the
 device tree may optionally contain additional information
-describing partitions of the flash address space.  This can be
+describing partitions of the address space.  This can be
 used on platforms which have strong conventions about which
-portions of the flash are used for what purposes, but which don't
+portions of a flash are used for what purposes, but which don't
 use an on-flash partition table such as RedBoot.
 
-Each partition is represented as a sub-node of the flash device.
+Each partition is represented as a sub-node of the mtd device.
 Each node's name represents the name of the corresponding
-partition of the flash device.
+partition of the mtd device.
 
 Flash partitions
- - reg : The partition's offset and size within the flash bank.
- - label : (optional) The label / name for this flash partition.
+ - reg : The partition's offset and size within the mtd bank.
+ - label : (optional) The label / name for this partition.
    If omitted, the label is taken from the node name (excluding
    the unit address).
  - read-only : (optional) This parameter, if present, is a hint to
-   Linux that this flash partition should only be mounted
+   Linux that this partition should only be mounted
    read-only.  This is usually used for flash partitions
    containing early-boot firmware images or data which should not
    be clobbered.
@@ -78,3 +79,12 @@ Here an example with multiple "reg" tuples:
 			reg = <0 0x04000000>;
 		};
 	};
+
+An example using SRAM:
+
+	sram@2,0 {
+		compatible = "samsung,k6f1616u6a", "mtd-ram";
+		reg = <2 0 0x00200000>;
+		bank-width = <2>;
+	};
+

Documentation/scsi/hptiop.txt

@@ -3,6 +3,25 @@ HIGHPOINT ROCKETRAID 3xxx/4xxx ADAPTER DRIVER (hptiop)
 Controller Register Map
 -------------------------
 
+For RR44xx Intel IOP based adapters, the controller IOP is accessed via PCI BAR0 and BAR2:
+
+     BAR0 offset    Register
+            0x11C5C Link Interface IRQ Set
+            0x11C60 Link Interface IRQ Clear
+
+     BAR2 offset    Register
+            0x10    Inbound Message Register 0
+            0x14    Inbound Message Register 1
+            0x18    Outbound Message Register 0
+            0x1C    Outbound Message Register 1
+            0x20    Inbound Doorbell Register
+            0x24    Inbound Interrupt Status Register
+            0x28    Inbound Interrupt Mask Register
+            0x30    Outbound Interrupt Status Register
+            0x34    Outbound Interrupt Mask Register
+            0x40    Inbound Queue Port
+            0x44    Outbound Queue Port
+
 For Intel IOP based adapters, the controller IOP is accessed via PCI BAR0:
 
      BAR0 offset    Register
@@ -93,7 +112,7 @@ The driver exposes following sysfs attributes:
 
 
 -----------------------------------------------------------------------------
-Copyright (C) 2006-2007 HighPoint Technologies, Inc. All Rights Reserved.
+Copyright (C) 2006-2009 HighPoint Technologies, Inc. All Rights Reserved.
 
   This file is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of

Documentation/slow-work.txt

@@ -41,6 +41,13 @@ expand files, provided the time taken to do so isn't too long.
 Operations of both types may sleep during execution, thus tying up the thread
 loaned to it.
 
+A further class of work item is available, based on the slow work item class:
+
+ (*) Delayed slow work items.
+
+These are slow work items that have a timer to defer queueing of the item for
+a while.
+
 
 THREAD-TO-CLASS ALLOCATION
 --------------------------
@@ -64,9 +71,11 @@ USING SLOW WORK ITEMS
 Firstly, a module or subsystem wanting to make use of slow work items must
 register its interest:
 
-	 int ret = slow_work_register_user();
+	 int ret = slow_work_register_user(struct module *module);
 
-This will return 0 if successful, or a -ve error upon failure.
+This will return 0 if successful, or a -ve error upon failure.  The module
+pointer should be the module interested in using this facility (almost
+certainly THIS_MODULE).
 
 
 Slow work items may then be set up by:
@@ -91,6 +100,10 @@ Slow work items may then be set up by:
 
 	slow_work_init(&myitem, &myitem_ops);
 
+     or:
+
+	delayed_slow_work_init(&myitem, &myitem_ops);
+
      or:
 
 	vslow_work_init(&myitem, &myitem_ops);
@@ -102,15 +115,92 @@ A suitably set up work item can then be enqueued for processing:
 	int ret = slow_work_enqueue(&myitem);
 
 This will return a -ve error if the thread pool is unable to gain a reference
-on the item, 0 otherwise.
+on the item, 0 otherwise, or (for delayed work):
+
+	int ret = delayed_slow_work_enqueue(&myitem, my_jiffy_delay);
 
 
 The items are reference counted, so there ought to be no need for a flush
-operation.  When all a module's slow work items have been processed, and the
+operation.  But as the reference counting is optional, means to cancel
+existing work items are also included:
+
+	cancel_slow_work(&myitem);
+	cancel_delayed_slow_work(&myitem);
+
+can be used to cancel pending work.  The above cancel function waits for
+existing work to have been executed (or prevent execution of them, depending
+on timing).
+
+
+When all a module's slow work items have been processed, and the
 module has no further interest in the facility, it should unregister its
 interest:
 
-	slow_work_unregister_user();
+	slow_work_unregister_user(struct module *module);
+
+The module pointer is used to wait for all outstanding work items for that
+module before completing the unregistration.  This prevents the put_ref() code
+from being taken away before it completes.  module should almost certainly be
+THIS_MODULE.
+
+
+================
+HELPER FUNCTIONS
+================
+
+The slow-work facility provides a function by which it can be determined
+whether or not an item is queued for later execution:
+
+	bool queued = slow_work_is_queued(struct slow_work *work);
+
+If it returns false, then the item is not on the queue (it may be executing
+with a requeue pending).  This can be used to work out whether an item on which
+another depends is on the queue, thus allowing a dependent item to be queued
+after it.
+
+If the above shows an item on which another depends not to be queued, then the
+owner of the dependent item might need to wait.  However, to avoid locking up
+the threads unnecessarily be sleeping in them, it can make sense under some
+circumstances to return the work item to the queue, thus deferring it until
+some other items have had a chance to make use of the yielded thread.
+
+To yield a thread and defer an item, the work function should simply enqueue
+the work item again and return.  However, this doesn't work if there's nothing
+actually on the queue, as the thread just vacated will jump straight back into
+the item's work function, thus busy waiting on a CPU.
+
+Instead, the item should use the thread to wait for the dependency to go away,
+but rather than using schedule() or schedule_timeout() to sleep, it should use
+the following function:
+
+	bool requeue = slow_work_sleep_till_thread_needed(
+			struct slow_work *work,
+			signed long *_timeout);
+
+This will add a second wait and then sleep, such that it will be woken up if
+either something appears on the queue that could usefully make use of the
+thread - and behind which this item can be queued, or if the event the caller
+set up to wait for happens.  True will be returned if something else appeared
+on the queue and this work function should perhaps return, of false if
+something else woke it up.  The timeout is as for schedule_timeout().
+
+For example:
+
+	wq = bit_waitqueue(&my_flags, MY_BIT);
+	init_wait(&wait);
+	requeue = false;
+	do {
+		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
+		if (!test_bit(MY_BIT, &my_flags))
+			break;
+		requeue = slow_work_sleep_till_thread_needed(&my_work,
+							     &timeout);
+	} while (timeout > 0 && !requeue);
+	finish_wait(wq, &wait);
+	if (!test_bit(MY_BIT, &my_flags)
+		goto do_my_thing;
+	if (requeue)
+		return; // to slow_work
 
 
 ===============
@@ -118,7 +208,8 @@ ITEM OPERATIONS
 ===============
 
 Each work item requires a table of operations of type struct slow_work_ops.
-All members are required:
+Only ->execute() is required; the getting and putting of a reference and the
+describing of an item are all optional.
 
  (*) Get a reference on an item:
 
@@ -148,6 +239,16 @@ All members are required:
      This should perform the work required of the item.  It may sleep, it may
      perform disk I/O and it may wait for locks.
 
+ (*) View an item through /proc:
+
+	void (*desc)(struct slow_work *work, struct seq_file *m);
+
+     If supplied, this should print to 'm' a small string describing the work
+     the item is to do.  This should be no more than about 40 characters, and
+     shouldn't include a newline character.
+
+     See the 'Viewing executing and queued items' section below.
+
 
 ==================
 POOL CONFIGURATION
@@ -172,3 +273,50 @@ The slow-work thread pool has a number of configurables:
      is bounded to between 1 and one fewer than the number of active threads.
      This ensures there is always at least one thread that can process very
      slow work items, and always at least one thread that won't.
+
+
+==================================
+VIEWING EXECUTING AND QUEUED ITEMS
+==================================
+
+If CONFIG_SLOW_WORK_DEBUG is enabled, a debugfs file is made available:
+
+	/sys/kernel/debug/slow_work/runqueue
+
+through which the list of work items being executed and the queues of items to
+be executed may be viewed.  The owner of a work item is given the chance to
+add some information of its own.
+
+The contents look something like the following:
+
+    THR PID   ITEM ADDR        FL MARK  DESC
+    === ===== ================ == ===== ==========
+      0  3005 ffff880023f52348  a 952ms FSC: OBJ17d3: LOOK
+      1  3006 ffff880024e33668  2 160ms FSC: OBJ17e5 OP60d3b: Write1/Store fl=2
+      2  3165 ffff8800296dd180  a 424ms FSC: OBJ17e4: LOOK
+      3  4089 ffff8800262c8d78  a 212ms FSC: OBJ17ea: CRTN
+      4  4090 ffff88002792bed8  2 388ms FSC: OBJ17e8 OP60d36: Write1/Store fl=2
+      5  4092 ffff88002a0ef308  2 388ms FSC: OBJ17e7 OP60d2e: Write1/Store fl=2
+      6  4094 ffff88002abaf4b8  2 132ms FSC: OBJ17e2 OP60d4e: Write1/Store fl=2
+      7  4095 ffff88002bb188e0  a 388ms FSC: OBJ17e9: CRTN
+    vsq     - ffff880023d99668  1 308ms FSC: OBJ17e0 OP60f91: Write1/EnQ fl=2
+    vsq     - ffff8800295d1740  1 212ms FSC: OBJ16be OP4d4b6: Write1/EnQ fl=2
+    vsq     - ffff880025ba3308  1 160ms FSC: OBJ179a OP58dec: Write1/EnQ fl=2
+    vsq     - ffff880024ec83e0  1 160ms FSC: OBJ17ae OP599f2: Write1/EnQ fl=2
+    vsq     - ffff880026618e00  1 160ms FSC: OBJ17e6 OP60d33: Write1/EnQ fl=2
+    vsq     - ffff880025a2a4b8  1 132ms FSC: OBJ16a2 OP4d583: Write1/EnQ fl=2
+    vsq     - ffff880023cbe6d8  9 212ms FSC: OBJ17eb: LOOK
+    vsq     - ffff880024d37590  9 212ms FSC: OBJ17ec: LOOK
+    vsq     - ffff880027746cb0  9 212ms FSC: OBJ17ed: LOOK
+    vsq     - ffff880024d37ae8  9 212ms FSC: OBJ17ee: LOOK
+    vsq     - ffff880024d37cb0  9 212ms FSC: OBJ17ef: LOOK
+    vsq     - ffff880025036550  9 212ms FSC: OBJ17f0: LOOK
+    vsq     - ffff8800250368e0  9 212ms FSC: OBJ17f1: LOOK
+    vsq     - ffff880025036aa8  9 212ms FSC: OBJ17f2: LOOK
+
+In the 'THR' column, executing items show the thread they're occupying and
+queued threads indicate which queue they're on.  'PID' shows the process ID of
+a slow-work thread that's executing something.  'FL' shows the work item flags.
+'MARK' indicates how long since an item was queued or began executing.  Lastly,
+the 'DESC' column permits the owner of an item to give some information.
+

Documentation/sound/alsa/ALSA-Configuration.txt

@@ -522,7 +522,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
     pcm_devs       - Number of PCM devices assigned to each card
                      (default = 1, up to 4)
     pcm_substreams - Number of PCM substreams assigned to each PCM
-                     (default = 8, up to 16)
+                     (default = 8, up to 128)
     hrtimer        - Use hrtimer (=1, default) or system timer (=0)
     fake_buffer    - Fake buffer allocations (default = 1)
 

Documentation/sound/alsa/HD-Audio-Models.txt

@@ -209,6 +209,7 @@ AD1884A / AD1883 / AD1984A / AD1984B
   laptop	laptop with HP jack sensing
   mobile	mobile devices with HP jack sensing
   thinkpad	Lenovo Thinkpad X300
+  touchsmart	HP Touchsmart
 
 AD1884
 ======
@@ -358,6 +359,7 @@ STAC9227/9228/9229/927x
   5stack-no-fp	D965 5stack without front panel
   dell-3stack	Dell Dimension E520
   dell-bios	Fixes with Dell BIOS setup
+  volknob	Fixes with volume-knob widget 0x24
   auto		BIOS setup (default)
 
 STAC92HD71B*

Documentation/sysctl/fs.txt

@@ -96,13 +96,16 @@ handles that the Linux kernel will allocate. When you get lots
 of error messages about running out of file handles, you might
 want to increase this limit.
 
-The three values in file-nr denote the number of allocated
-file handles, the number of unused file handles and the maximum
-number of file handles. When the allocated file handles come
-close to the maximum, but the number of unused file handles is
-significantly greater than 0, you've encountered a peak in your 
-usage of file handles and you don't need to increase the maximum.
-
+Historically, the three values in file-nr denoted the number of
+allocated file handles, the number of allocated but unused file
+handles, and the maximum number of file handles. Linux 2.6 always
+reports 0 as the number of free file handles -- this is not an
+error, it just means that the number of allocated file handles
+exactly matches the number of used file handles.
+
+Attempts to allocate more file descriptors than file-max are
+reported with printk, look for "VFS: file-max limit <number>
+reached".
 ==============================================================
 
 nr_open:

Documentation/sysctl/kernel.txt

@@ -22,6 +22,7 @@ show up in /proc/sys/kernel:
 - callhome		     [ S390 only ]
 - auto_msgmni
 - core_pattern
+- core_pipe_limit
 - core_uses_pid
 - ctrl-alt-del
 - dentry-state
@@ -135,6 +136,27 @@ core_pattern is used to specify a core dumpfile pattern name.
 
 ==============================================================
 
+core_pipe_limit:
+
+This sysctl is only applicable when core_pattern is configured to pipe core
+files to user space helper a (when the first character of core_pattern is a '|',
+see above).  When collecting cores via a pipe to an application, it is
+occasionally usefull for the collecting application to gather data about the
+crashing process from its /proc/pid directory.  In order to do this safely, the
+kernel must wait for the collecting process to exit, so as not to remove the
+crashing processes proc files prematurely.  This in turn creates the possibility
+that a misbehaving userspace collecting process can block the reaping of a
+crashed process simply by never exiting.  This sysctl defends against that.  It
+defines how many concurrent crashing processes may be piped to user space
+applications in parallel.  If this value is exceeded, then those crashing
+processes above that value are noted via the kernel log and their cores are
+skipped.  0 is a special value, indicating that unlimited processes may be
+captured in parallel, but that no waiting will take place (i.e. the collecting
+process is not guaranteed access to /proc/<crahing pid>/).  This value defaults
+to 0.
+
+==============================================================
+
 core_uses_pid:
 
 The default coredump filename is "core".  By setting

Documentation/sysctl/vm.txt

@@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/vm:
 - legacy_va_layout
 - lowmem_reserve_ratio
 - max_map_count
+- memory_failure_early_kill
+- memory_failure_recovery
 - min_free_kbytes
 - min_slab_ratio
 - min_unmapped_ratio
@@ -53,7 +55,6 @@ Currently, these files are in /proc/sys/vm:
 - vfs_cache_pressure
 - zone_reclaim_mode
 
-
 ==============================================================
 
 block_dump
@@ -275,6 +276,44 @@ e.g., up to one or two maps per allocation.
 
 The default value is 65536.
 
+=============================================================
+
+memory_failure_early_kill:
+
+Control how to kill processes when uncorrected memory error (typically
+a 2bit error in a memory module) is detected in the background by hardware
+that cannot be handled by the kernel. In some cases (like the page
+still having a valid copy on disk) the kernel will handle the failure
+transparently without affecting any applications. But if there is
+no other uptodate copy of the data it will kill to prevent any data
+corruptions from propagating.
+
+1: Kill all processes that have the corrupted and not reloadable page mapped
+as soon as the corruption is detected.  Note this is not supported
+for a few types of pages, like kernel internally allocated data or
+the swap cache, but works for the majority of user pages.
+
+0: Only unmap the corrupted page from all processes and only kill a process
+who tries to access it.
+
+The kill is done using a catchable SIGBUS with BUS_MCEERR_AO, so processes can
+handle this if they want to.
+
+This is only active on architectures/platforms with advanced machine
+check handling and depends on the hardware capabilities.
+
+Applications can override this setting individually with the PR_MCE_KILL prctl
+
+==============================================================
+
+memory_failure_recovery
+
+Enable memory failure recovery (when supported by the platform)
+
+1: Attempt recovery.
+
+0: Always panic on a memory failure.
+
 ==============================================================
 
 min_free_kbytes:

Documentation/thermal/sysfs-api.txt

@@ -1,5 +1,5 @@
 Generic Thermal Sysfs driver How To
-=========================
+===================================
 
 Written by Sujith Thomas <sujith.thomas@intel.com>, Zhang Rui <rui.zhang@intel.com>
 
@@ -10,20 +10,20 @@ Copyright (c)  2008 Intel Corporation
 
 0. Introduction
 
-The generic thermal sysfs provides a set of interfaces for thermal zone devices (sensors)
-and thermal cooling devices (fan, processor...) to register with the thermal management
-solution and to be a part of it.
+The generic thermal sysfs provides a set of interfaces for thermal zone
+devices (sensors) and thermal cooling devices (fan, processor...) to register
+with the thermal management solution and to be a part of it.
 
-This how-to focuses on enabling new thermal zone and cooling devices to participate
-in thermal management.
-This solution is platform independent and any type of thermal zone devices and
-cooling devices should be able to make use of the infrastructure.
+This how-to focuses on enabling new thermal zone and cooling devices to
+participate in thermal management.
+This solution is platform independent and any type of thermal zone devices
+and cooling devices should be able to make use of the infrastructure.
 
-The main task of the thermal sysfs driver is to expose thermal zone attributes as well
-as cooling device attributes to the user space.
-An intelligent thermal management application can make decisions based on inputs
-from thermal zone attributes (the current temperature and trip point temperature)
-and throttle appropriate devices.
+The main task of the thermal sysfs driver is to expose thermal zone attributes
+as well as cooling device attributes to the user space.
+An intelligent thermal management application can make decisions based on
+inputs from thermal zone attributes (the current temperature and trip point
+temperature) and throttle appropriate devices.
 
 [0-*]	denotes any positive number starting from 0
 [1-*]	denotes any positive number starting from 1
@@ -31,77 +31,77 @@ and throttle appropriate devices.
 1. thermal sysfs driver interface functions
 
 1.1 thermal zone device interface
-1.1.1 struct thermal_zone_device *thermal_zone_device_register(char *name, int trips,
-				void *devdata, struct thermal_zone_device_ops *ops)
-
-	This interface function adds a new thermal zone device (sensor) to
-	/sys/class/thermal folder as thermal_zone[0-*].
-	It tries to bind all the thermal cooling devices registered at the same time.
-
-	name: the thermal zone name.
-	trips: the total number of trip points this thermal zone supports.
-	devdata: device private data
-	ops: thermal zone device call-backs.
-		.bind: bind the thermal zone device with a thermal cooling device.
-		.unbind: unbind the thermal zone device with a thermal cooling device.
-		.get_temp: get the current temperature of the thermal zone.
-		.get_mode: get the current mode (user/kernel) of the thermal zone.
-			   "kernel" means thermal management is done in kernel.
-			   "user" will prevent kernel thermal driver actions upon trip points
-			   so that user applications can take charge of thermal management.
-		.set_mode: set the mode (user/kernel) of the thermal zone.
-		.get_trip_type: get the type of certain trip point.
-		.get_trip_temp: get the temperature above which the certain trip point
-				will be fired.
+1.1.1 struct thermal_zone_device *thermal_zone_device_register(char *name,
+		int trips, void *devdata, struct thermal_zone_device_ops *ops)
+
+    This interface function adds a new thermal zone device (sensor) to
+    /sys/class/thermal folder as thermal_zone[0-*]. It tries to bind all the
+    thermal cooling devices registered at the same time.
+
+    name: the thermal zone name.
+    trips: the total number of trip points this thermal zone supports.
+    devdata: device private data
+    ops: thermal zone device call-backs.
+	.bind: bind the thermal zone device with a thermal cooling device.
+	.unbind: unbind the thermal zone device with a thermal cooling device.
+	.get_temp: get the current temperature of the thermal zone.
+	.get_mode: get the current mode (user/kernel) of the thermal zone.
+	    - "kernel" means thermal management is done in kernel.
+	    - "user" will prevent kernel thermal driver actions upon trip points
+	      so that user applications can take charge of thermal management.
+	.set_mode: set the mode (user/kernel) of the thermal zone.
+	.get_trip_type: get the type of certain trip point.
+	.get_trip_temp: get the temperature above which the certain trip point
+			will be fired.
 
 1.1.2 void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 
-	This interface function removes the thermal zone device.
-	It deletes the corresponding entry form /sys/class/thermal folder and unbind all
-	the thermal cooling devices it uses.
+    This interface function removes the thermal zone device.
+    It deletes the corresponding entry form /sys/class/thermal folder and
+    unbind all the thermal cooling devices it uses.
 
 1.2 thermal cooling device interface
 1.2.1 struct thermal_cooling_device *thermal_cooling_device_register(char *name,
-					void *devdata, struct thermal_cooling_device_ops *)
-
-	This interface function adds a new thermal cooling device (fan/processor/...) to
-	/sys/class/thermal/ folder as cooling_device[0-*].
-	It tries to bind itself to all the thermal zone devices register at the same time.
-	name: the cooling device name.
-	devdata: device private data.
-	ops: thermal cooling devices call-backs.
-		.get_max_state: get the Maximum throttle state of the cooling device.
-		.get_cur_state: get the Current throttle state of the cooling device.
-		.set_cur_state: set the Current throttle state of the cooling device.
+		void *devdata, struct thermal_cooling_device_ops *)
+
+    This interface function adds a new thermal cooling device (fan/processor/...)
+    to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
+    to all the thermal zone devices register at the same time.
+    name: the cooling device name.
+    devdata: device private data.
+    ops: thermal cooling devices call-backs.
+	.get_max_state: get the Maximum throttle state of the cooling device.
+	.get_cur_state: get the Current throttle state of the cooling device.
+	.set_cur_state: set the Current throttle state of the cooling device.
 
 1.2.2 void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
 
-	This interface function remove the thermal cooling device.
-	It deletes the corresponding entry form /sys/class/thermal folder and unbind
-	itself from all	the thermal zone devices using it.
+    This interface function remove the thermal cooling device.
+    It deletes the corresponding entry form /sys/class/thermal folder and
+    unbind itself from all the thermal zone devices using it.
 
 1.3 interface for binding a thermal zone device with a thermal cooling device
 1.3.1 int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
-			int trip, struct thermal_cooling_device *cdev);
+		int trip, struct thermal_cooling_device *cdev);
 
-	This interface function bind a thermal cooling device to the certain trip point
-	of a thermal zone device.
-	This function is usually called in the thermal zone device .bind callback.
-	tz: the thermal zone device
-	cdev: thermal cooling device
-	trip: indicates which trip point the cooling devices is associated with
-		 in this thermal zone.
+    This interface function bind a thermal cooling device to the certain trip
+    point of a thermal zone device.
+    This function is usually called in the thermal zone device .bind callback.
+    tz: the thermal zone device
+    cdev: thermal cooling device
+    trip: indicates which trip point the cooling devices is associated with
+	  in this thermal zone.
 
 1.3.2 int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz,
-				int trip, struct thermal_cooling_device *cdev);
+		int trip, struct thermal_cooling_device *cdev);
 
-	This interface function unbind a thermal cooling device from the certain trip point
-	of a thermal zone device.
-	This function is usually called in the thermal zone device .unbind callback.
-	tz: the thermal zone device
-	cdev: thermal cooling device
-	trip: indicates which trip point the cooling devices is associated with
-		in this thermal zone.
+    This interface function unbind a thermal cooling device from the certain
+    trip point of a thermal zone device. This function is usually called in
+    the thermal zone device .unbind callback.
+    tz: the thermal zone device
+    cdev: thermal cooling device
+    trip: indicates which trip point the cooling devices is associated with
+	  in this thermal zone.
 
 2. sysfs attributes structure
 
@@ -114,153 +114,166 @@ if hwmon is compiled in or built as a module.
 
 Thermal zone device sys I/F, created once it's registered:
 /sys/class/thermal/thermal_zone[0-*]:
-	|-----type:			Type of the thermal zone
-	|-----temp:			Current temperature
-	|-----mode:			Working mode of the thermal zone
-	|-----trip_point_[0-*]_temp:	Trip point temperature
-	|-----trip_point_[0-*]_type:	Trip point type
+    |---type:			Type of the thermal zone
+    |---temp:			Current temperature
+    |---mode:			Working mode of the thermal zone
+    |---trip_point_[0-*]_temp:	Trip point temperature
+    |---trip_point_[0-*]_type:	Trip point type
 
 Thermal cooling device sys I/F, created once it's registered:
 /sys/class/thermal/cooling_device[0-*]:
-	|-----type :			Type of the cooling device(processor/fan/...)
-	|-----max_state:		Maximum cooling state of the cooling device
-	|-----cur_state:		Current cooling state of the cooling device
+    |---type:			Type of the cooling device(processor/fan/...)
+    |---max_state:		Maximum cooling state of the cooling device
+    |---cur_state:		Current cooling state of the cooling device
 
 
-These two dynamic attributes are created/removed in pairs.
-They represent the relationship between a thermal zone and its associated cooling device.
-They are created/removed for each
-thermal_zone_bind_cooling_device/thermal_zone_unbind_cooling_device successful execution.
+Then next two dynamic attributes are created/removed in pairs. They represent
+the relationship between a thermal zone and its associated cooling device.
+They are created/removed for each successful execution of
+thermal_zone_bind_cooling_device/thermal_zone_unbind_cooling_device.
 
-/sys/class/thermal/thermal_zone[0-*]
-	|-----cdev[0-*]:		The [0-*]th cooling device in the current thermal zone
-	|-----cdev[0-*]_trip_point:	Trip point that cdev[0-*] is associated with
+/sys/class/thermal/thermal_zone[0-*]:
+    |---cdev[0-*]:		[0-*]th cooling device in current thermal zone
+    |---cdev[0-*]_trip_point:	Trip point that cdev[0-*] is associated with
 
 Besides the thermal zone device sysfs I/F and cooling device sysfs I/F,
-the generic thermal driver also creates a hwmon sysfs I/F for each _type_ of
-thermal zone device. E.g. the generic thermal driver registers one hwmon class device
-and build the associated hwmon sysfs I/F for all the registered ACPI thermal zones.
+the generic thermal driver also creates a hwmon sysfs I/F for each _type_
+of thermal zone device. E.g. the generic thermal driver registers one hwmon
+class device and build the associated hwmon sysfs I/F for all the registered
+ACPI thermal zones.
+
 /sys/class/hwmon/hwmon[0-*]:
-	|-----name:			The type of the thermal zone devices.
-	|-----temp[1-*]_input:		The current temperature of thermal zone [1-*].
-	|-----temp[1-*]_critical:	The critical trip point of thermal zone [1-*].
+    |---name:			The type of the thermal zone devices
+    |---temp[1-*]_input:	The current temperature of thermal zone [1-*]
+    |---temp[1-*]_critical:	The critical trip point of thermal zone [1-*]
+
 Please read Documentation/hwmon/sysfs-interface for additional information.
 
 ***************************
 * Thermal zone attributes *
 ***************************
 
-type				Strings which represent the thermal zone type.
-				This is given by thermal zone driver as part of registration.
-				Eg: "acpitz" indicates it's an ACPI thermal device.
-				In order to keep it consistent with hwmon sys attribute,
-				this should be a short, lowercase string,
-				not containing spaces nor dashes.
-				RO
-				Required
-
-temp				Current temperature as reported by thermal zone (sensor)
-				Unit: millidegree Celsius
-				RO
-				Required
-
-mode				One of the predefined values in [kernel, user]
-				This file gives information about the algorithm
-				that is currently managing the thermal zone.
-				It can be either default kernel based algorithm
-				or user space application.
-				RW
-				Optional
-				kernel	= Thermal management in kernel thermal zone driver.
-				user	= Preventing kernel thermal zone driver actions upon
-					  trip points so that user application can take full
-					  charge of the thermal management.
-
-trip_point_[0-*]_temp		The temperature above which trip point will be fired
-				Unit: millidegree Celsius
-				RO
-				Optional
-
-trip_point_[0-*]_type 		Strings which indicate the type of the trip point
-				E.g. it can be one of critical, hot, passive,
-				    active[0-*] for ACPI thermal zone.
-				RO
-				Optional
-
-cdev[0-*]			Sysfs link to the thermal cooling device node where the sys I/F
-				for cooling device throttling control represents.
-				RO
-				Optional
-
-cdev[0-*]_trip_point		The trip point with which cdev[0-*] is associated in this thermal zone
-				-1 means the cooling device is not associated with any trip point.
-				RO
-				Optional
-
-******************************
-* Cooling device  attributes *
-******************************
-
-type				String which represents the type of device
-				eg: For generic ACPI: this should be "Fan",
-				"Processor" or "LCD"
-				eg. For memory controller device on intel_menlow platform:
-				this should be "Memory controller"
-				RO
-				Required
-
-max_state			The maximum permissible cooling state of this cooling device.
-				RO
-				Required
-
-cur_state			The current cooling state of this cooling device.
-				the value can any integer numbers between 0 and max_state,
-				cur_state == 0 means no cooling
-				cur_state == max_state means the maximum cooling.
-				RW
-				Required
+type
+	Strings which represent the thermal zone type.
+	This is given by thermal zone driver as part of registration.
+	E.g: "acpitz" indicates it's an ACPI thermal device.
+	In order to keep it consistent with hwmon sys attribute; this should
+	be a short, lowercase string, not containing spaces nor dashes.
+	RO, Required
+
+temp
+	Current temperature as reported by thermal zone (sensor).
+	Unit: millidegree Celsius
+	RO, Required
+
+mode
+	One of the predefined values in [kernel, user].
+	This file gives information about the algorithm that is currently
+	managing the thermal zone. It can be either default kernel based
+	algorithm or user space application.
+	kernel	= Thermal management in kernel thermal zone driver.
+	user	= Preventing kernel thermal zone driver actions upon
+		  trip points so that user application can take full
+		  charge of the thermal management.
+	RW, Optional
+
+trip_point_[0-*]_temp
+	The temperature above which trip point will be fired.
+	Unit: millidegree Celsius
+	RO, Optional
+
+trip_point_[0-*]_type
+	Strings which indicate the type of the trip point.
+	E.g. it can be one of critical, hot, passive, active[0-*] for ACPI
+	thermal zone.
+	RO, Optional
+
+cdev[0-*]
+	Sysfs link to the thermal cooling device node where the sys I/F
+	for cooling device throttling control represents.
+	RO, Optional
+
+cdev[0-*]_trip_point
+	The trip point with which cdev[0-*] is associated in this thermal
+	zone; -1 means the cooling device is not associated with any trip
+	point.
+	RO, Optional
+
+passive
+	Attribute is only present for zones in which the passive cooling
+	policy is not supported by native thermal driver. Default is zero
+	and can be set to a temperature (in millidegrees) to enable a
+	passive trip point for the zone. Activation is done by polling with
+	an interval of 1 second.
+	Unit: millidegrees Celsius
+	RW, Optional
+
+*****************************
+* Cooling device attributes *
+*****************************
+
+type
+	String which represents the type of device, e.g:
+	- for generic ACPI: should be "Fan", "Processor" or "LCD"
+	- for memory controller device on intel_menlow platform:
+	  should be "Memory controller".
+	RO, Required
+
+max_state
+	The maximum permissible cooling state of this cooling device.
+	RO, Required
+
+cur_state
+	The current cooling state of this cooling device.
+	The value can any integer numbers between 0 and max_state:
+	- cur_state == 0 means no cooling
+	- cur_state == max_state means the maximum cooling.
+	RW, Required
 
 3. A simple implementation
 
-ACPI thermal zone may support multiple trip points like critical/hot/passive/active.
-If an ACPI thermal zone supports critical, passive, active[0] and active[1] at the same time,
-it may register itself as a thermal_zone_device (thermal_zone1) with 4 trip points in all.
-It has one processor and one fan, which are both registered as thermal_cooling_device.
-If the processor is listed in _PSL method, and the fan is listed in _AL0 method,
-the sys I/F structure will be built like this:
+ACPI thermal zone may support multiple trip points like critical, hot,
+passive, active. If an ACPI thermal zone supports critical, passive,
+active[0] and active[1] at the same time, it may register itself as a
+thermal_zone_device (thermal_zone1) with 4 trip points in all.
+It has one processor and one fan, which are both registered as
+thermal_cooling_device.
+
+If the processor is listed in _PSL method, and the fan is listed in _AL0
+method, the sys I/F structure will be built like this:
 
 /sys/class/thermal:
 
 |thermal_zone1:
-	|-----type:			acpitz
-	|-----temp:			37000
-	|-----mode:			kernel
-	|-----trip_point_0_temp:	100000
-	|-----trip_point_0_type:	critical
-	|-----trip_point_1_temp:	80000
-	|-----trip_point_1_type:	passive
-	|-----trip_point_2_temp:	70000
-	|-----trip_point_2_type:	active0
-	|-----trip_point_3_temp:	60000
-	|-----trip_point_3_type:	active1
-	|-----cdev0:			--->/sys/class/thermal/cooling_device0
-	|-----cdev0_trip_point:		1	/* cdev0 can be used for passive */
-	|-----cdev1:			--->/sys/class/thermal/cooling_device3
-	|-----cdev1_trip_point:		2	/* cdev1 can be used for active[0]*/
+    |---type:			acpitz
+    |---temp:			37000
+    |---mode:			kernel
+    |---trip_point_0_temp:	100000
+    |---trip_point_0_type:	critical
+    |---trip_point_1_temp:	80000
+    |---trip_point_1_type:	passive
+    |---trip_point_2_temp:	70000
+    |---trip_point_2_type:	active0
+    |---trip_point_3_temp:	60000
+    |---trip_point_3_type:	active1
+    |---cdev0:			--->/sys/class/thermal/cooling_device0
+    |---cdev0_trip_point:	1	/* cdev0 can be used for passive */
+    |---cdev1:			--->/sys/class/thermal/cooling_device3
+    |---cdev1_trip_point:	2	/* cdev1 can be used for active[0]*/
 
 |cooling_device0:
-	|-----type:			Processor
-	|-----max_state:		8
-	|-----cur_state:		0
+    |---type:			Processor
+    |---max_state:		8
+    |---cur_state:		0
 
 |cooling_device3:
-	|-----type:			Fan
-	|-----max_state:		2
-	|-----cur_state:		0
+    |---type:			Fan
+    |---max_state:		2
+    |---cur_state:		0
 
 /sys/class/hwmon:
 
 |hwmon0:
-	|-----name:			acpitz
-	|-----temp1_input:		37000
-	|-----temp1_crit:		100000
+    |---name:			acpitz
+    |---temp1_input:		37000
+    |---temp1_crit:		100000

Documentation/trace/ftrace.txt

@@ -1231,6 +1231,7 @@ something like this simple program:
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <string.h>
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
@@ -1265,6 +1266,7 @@ const char *find_debugfs(void)
                return NULL;
        }
 
+       strcat(debugfs, "/tracing/");
        debugfs_found = 1;
 
        return debugfs;

Documentation/vm/.gitignore

@@ -1 +1,2 @@
+page-types
 slabinfo

Documentation/vm/hwpoison.txt

@@ -0,0 +1,136 @@
+What is hwpoison?
+
+Upcoming Intel CPUs have support for recovering from some memory errors
+(``MCA recovery''). This requires the OS to declare a page "poisoned",
+kill the processes associated with it and avoid using it in the future.
+
+This patchkit implements the necessary infrastructure in the VM.
+
+To quote the overview comment:
+
+ * High level machine check handler. Handles pages reported by the
+ * hardware as being corrupted usually due to a 2bit ECC memory or cache
+ * failure.
+ *
+ * This focusses on pages detected as corrupted in the background.
+ * When the current CPU tries to consume corruption the currently
+ * running process can just be killed directly instead. This implies
+ * that if the error cannot be handled for some reason it's safe to
+ * just ignore it because no corruption has been consumed yet. Instead
+ * when that happens another machine check will happen.
+ *
+ * Handles page cache pages in various states. The tricky part
+ * here is that we can access any page asynchronous to other VM
+ * users, because memory failures could happen anytime and anywhere,
+ * possibly violating some of their assumptions. This is why this code
+ * has to be extremely careful. Generally it tries to use normal locking
+ * rules, as in get the standard locks, even if that means the
+ * error handling takes potentially a long time.
+ *
+ * Some of the operations here are somewhat inefficient and have non
+ * linear algorithmic complexity, because the data structures have not
+ * been optimized for this case. This is in particular the case
+ * for the mapping from a vma to a process. Since this case is expected
+ * to be rare we hope we can get away with this.
+
+The code consists of a the high level handler in mm/memory-failure.c,
+a new page poison bit and various checks in the VM to handle poisoned
+pages.
+
+The main target right now is KVM guests, but it works for all kinds
+of applications. KVM support requires a recent qemu-kvm release.
+
+For the KVM use there was need for a new signal type so that
+KVM can inject the machine check into the guest with the proper
+address. This in theory allows other applications to handle
+memory failures too. The expection is that near all applications
+won't do that, but some very specialized ones might.
+
+---
+
+There are two (actually three) modi memory failure recovery can be in:
+
+vm.memory_failure_recovery sysctl set to zero:
+	All memory failures cause a panic. Do not attempt recovery.
+	(on x86 this can be also affected by the tolerant level of the
+	MCE subsystem)
+
+early kill
+	(can be controlled globally and per process)
+	Send SIGBUS to the application as soon as the error is detected
+	This allows applications who can process memory errors in a gentle
+	way (e.g. drop affected object)
+	This is the mode used by KVM qemu.
+
+late kill
+	Send SIGBUS when the application runs into the corrupted page.
+	This is best for memory error unaware applications and default
+	Note some pages are always handled as late kill.
+
+---
+
+User control:
+
+vm.memory_failure_recovery
+	See sysctl.txt
+
+vm.memory_failure_early_kill
+	Enable early kill mode globally
+
+PR_MCE_KILL
+	Set early/late kill mode/revert to system default
+	arg1: PR_MCE_KILL_CLEAR: Revert to system default
+	arg1: PR_MCE_KILL_SET: arg2 defines thread specific mode
+		PR_MCE_KILL_EARLY: Early kill
+		PR_MCE_KILL_LATE:  Late kill
+		PR_MCE_KILL_DEFAULT: Use system global default
+PR_MCE_KILL_GET
+	return current mode
+
+
+---
+
+Testing:
+
+madvise(MADV_POISON, ....)
+	(as root)
+	Poison a page in the process for testing
+
+
+hwpoison-inject module through debugfs
+	/sys/debug/hwpoison/corrupt-pfn
+
+Inject hwpoison fault at PFN echoed into this file
+
+
+Architecture specific MCE injector
+
+x86 has mce-inject, mce-test
+
+Some portable hwpoison test programs in mce-test, see blow.
+
+---
+
+References:
+
+http://halobates.de/mce-lc09-2.pdf
+	Overview presentation from LinuxCon 09
+
+git://git.kernel.org/pub/scm/utils/cpu/mce/mce-test.git
+	Test suite (hwpoison specific portable tests in tsrc)
+
+git://git.kernel.org/pub/scm/utils/cpu/mce/mce-inject.git
+	x86 specific injector
+
+
+---
+
+Limitations:
+
+- Not all page types are supported and never will. Most kernel internal
+objects cannot be recovered, only LRU pages for now.
+- Right now hugepage support is missing.
+
+---
+Andi Kleen, Oct 2009
+

Documentation/vm/ksm.txt

@@ -52,15 +52,15 @@ The KSM daemon is controlled by sysfs files in /sys/kernel/mm/ksm/,
 readable by all but writable only by root:
 
 max_kernel_pages - set to maximum number of kernel pages that KSM may use
-                   e.g. "echo 2000 > /sys/kernel/mm/ksm/max_kernel_pages"
+                   e.g. "echo 100000 > /sys/kernel/mm/ksm/max_kernel_pages"
                    Value 0 imposes no limit on the kernel pages KSM may use;
                    but note that any process using MADV_MERGEABLE can cause
                    KSM to allocate these pages, unswappable until it exits.
-                   Default: 2000 (chosen for demonstration purposes)
+                   Default: quarter of memory (chosen to not pin too much)
 
 pages_to_scan    - how many present pages to scan before ksmd goes to sleep
-                   e.g. "echo 200 > /sys/kernel/mm/ksm/pages_to_scan"
-                   Default: 200 (chosen for demonstration purposes)
+                   e.g. "echo 100 > /sys/kernel/mm/ksm/pages_to_scan"
+                   Default: 100 (chosen for demonstration purposes)
 
 sleep_millisecs  - how many milliseconds ksmd should sleep before next scan
                    e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
@@ -70,7 +70,8 @@ run              - set 0 to stop ksmd from running but keep merged pages,
                    set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
                    set 2 to stop ksmd and unmerge all pages currently merged,
                          but leave mergeable areas registered for next run
-                   Default: 1 (for immediate use by apps which register)
+                   Default: 0 (must be changed to 1 to activate KSM,
+                               except if CONFIG_SYSFS is disabled)
 
 The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/:
 
@@ -86,4 +87,4 @@ pages_volatile embraces several different kinds of activity, but a high
 proportion there would also indicate poor use of madvise MADV_MERGEABLE.
 
 Izik Eidus,
-Hugh Dickins, 30 July 2009
+Hugh Dickins, 24 Sept 2009

Documentation/vm/locking

@@ -80,7 +80,7 @@ Note: PTL can also be used to guarantee that no new clones using the
 mm start up ... this is a loose form of stability on mm_users. For
 example, it is used in copy_mm to protect against a racing tlb_gather_mmu
 single address space optimization, so that the zap_page_range (from
-vmtruncate) does not lose sending ipi's to cloned threads that might 
+truncate) does not lose sending ipi's to cloned threads that might
 be spawned underneath it and go to user mode to drag in pte's into tlbs.
 
 swap_lock

Documentation/vm/page-types.c

@@ -2,9 +2,13 @@
  * page-types: Tool for querying page flags
  *
  * Copyright (C) 2009 Intel corporation
- * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com>
+ *
+ * Authors: Wu Fengguang <fengguang.wu@intel.com>
+ *
+ * Released under the General Public License (GPL).
  */
 
+#define _LARGEFILE64_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -13,11 +17,32 @@
 #include <string.h>
 #include <getopt.h>
 #include <limits.h>
+#include <assert.h>
 #include <sys/types.h>
 #include <sys/errno.h>
 #include <sys/fcntl.h>
 
 
+/*
+ * pagemap kernel ABI bits
+ */
+
+#define PM_ENTRY_BYTES      sizeof(uint64_t)
+#define PM_STATUS_BITS      3
+#define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
+#define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
+#define PM_STATUS(nr)       (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
+#define PM_PSHIFT_BITS      6
+#define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
+#define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
+#define PM_PSHIFT(x)        (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
+#define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
+
+#define PM_PRESENT          PM_STATUS(4LL)
+#define PM_SWAP             PM_STATUS(2LL)
+
+
 /*
  * kernel page flags
  */
@@ -47,7 +72,9 @@
 #define KPF_COMPOUND_TAIL	16
 #define KPF_HUGE		17
 #define KPF_UNEVICTABLE		18
+#define KPF_HWPOISON		19
 #define KPF_NOPAGE		20
+#define KPF_KSM			21
 
 /* [32-] kernel hacking assistances */
 #define KPF_RESERVED		32
@@ -94,7 +121,9 @@ static char *page_flag_names[] = {
 	[KPF_COMPOUND_TAIL]	= "T:compound_tail",
 	[KPF_HUGE]		= "G:huge",
 	[KPF_UNEVICTABLE]	= "u:unevictable",
+	[KPF_HWPOISON]		= "X:hwpoison",
 	[KPF_NOPAGE]		= "n:nopage",
+	[KPF_KSM]		= "x:ksm",
 
 	[KPF_RESERVED]		= "r:reserved",
 	[KPF_MLOCKED]		= "m:mlocked",
@@ -126,6 +155,11 @@ static int		nr_addr_ranges;
 static unsigned long	opt_offset[MAX_ADDR_RANGES];
 static unsigned long	opt_size[MAX_ADDR_RANGES];
 
+#define MAX_VMAS	10240
+static int		nr_vmas;
+static unsigned long	pg_start[MAX_VMAS];
+static unsigned long	pg_end[MAX_VMAS];
+
 #define MAX_BIT_FILTERS	64
 static int		nr_bit_filters;
 static uint64_t		opt_mask[MAX_BIT_FILTERS];
@@ -133,9 +167,15 @@ static uint64_t		opt_bits[MAX_BIT_FILTERS];
 
 static int		page_size;
 
-#define PAGES_BATCH	(64 << 10)	/* 64k pages */
+static int		pagemap_fd;
 static int		kpageflags_fd;
-static uint64_t		kpageflags_buf[KPF_BYTES * PAGES_BATCH];
+
+static int		opt_hwpoison;
+static int		opt_unpoison;
+
+static char		*hwpoison_debug_fs = "/debug/hwpoison";
+static int		hwpoison_inject_fd;
+static int		hwpoison_forget_fd;
 
 #define HASH_SHIFT	13
 #define HASH_SIZE	(1 << HASH_SHIFT)
@@ -158,6 +198,11 @@ static uint64_t 	page_flags[HASH_SIZE];
 	type __min2 = (y);			\
 	__min1 < __min2 ? __min1 : __min2; })
 
+#define max_t(type, x, y) ({			\
+	type __max1 = (x);			\
+	type __max2 = (y);			\
+	__max1 > __max2 ? __max1 : __max2; })
+
 static unsigned long pages2mb(unsigned long pages)
 {
 	return (pages * page_size) >> 20;
@@ -173,6 +218,74 @@ static void fatal(const char *x, ...)
 	exit(EXIT_FAILURE);
 }
 
+static int checked_open(const char *pathname, int flags)
+{
+	int fd = open(pathname, flags);
+
+	if (fd < 0) {
+		perror(pathname);
+		exit(EXIT_FAILURE);
+	}
+
+	return fd;
+}
+
+/*
+ * pagemap/kpageflags routines
+ */
+
+static unsigned long do_u64_read(int fd, char *name,
+				 uint64_t *buf,
+				 unsigned long index,
+				 unsigned long count)
+{
+	long bytes;
+
+	if (index > ULONG_MAX / 8)
+		fatal("index overflow: %lu\n", index);
+
+	if (lseek(fd, index * 8, SEEK_SET) < 0) {
+		perror(name);
+		exit(EXIT_FAILURE);
+	}
+
+	bytes = read(fd, buf, count * 8);
+	if (bytes < 0) {
+		perror(name);
+		exit(EXIT_FAILURE);
+	}
+	if (bytes % 8)
+		fatal("partial read: %lu bytes\n", bytes);
+
+	return bytes / 8;
+}
+
+static unsigned long kpageflags_read(uint64_t *buf,
+				     unsigned long index,
+				     unsigned long pages)
+{
+	return do_u64_read(kpageflags_fd, PROC_KPAGEFLAGS, buf, index, pages);
+}
+
+static unsigned long pagemap_read(uint64_t *buf,
+				  unsigned long index,
+				  unsigned long pages)
+{
+	return do_u64_read(pagemap_fd, "/proc/pid/pagemap", buf, index, pages);
+}
+
+static unsigned long pagemap_pfn(uint64_t val)
+{
+	unsigned long pfn;
+
+	if (val & PM_PRESENT)
+		pfn = PM_PFRAME(val);
+	else
+		pfn = 0;
+
+	return pfn;
+}
+
 
 /*
  * page flag names
@@ -221,29 +334,39 @@ static char *page_flag_longname(uint64_t flags)
  * page list and summary
  */
 
-static void show_page_range(unsigned long offset, uint64_t flags)
+static void show_page_range(unsigned long voffset,
+			    unsigned long offset, uint64_t flags)
 {
 	static uint64_t      flags0;
+	static unsigned long voff;
 	static unsigned long index;
 	static unsigned long count;
 
-	if (flags == flags0 && offset == index + count) {
+	if (flags == flags0 && offset == index + count &&
+	    (!opt_pid || voffset == voff + count)) {
 		count++;
 		return;
 	}
 
-	if (count)
-		printf("%lu\t%lu\t%s\n",
+	if (count) {
+		if (opt_pid)
+			printf("%lx\t", voff);
+		printf("%lx\t%lx\t%s\n",
 				index, count, page_flag_name(flags0));
+	}
 
 	flags0 = flags;
 	index  = offset;
+	voff   = voffset;
 	count  = 1;
 }
 
-static void show_page(unsigned long offset, uint64_t flags)
+static void show_page(unsigned long voffset,
+		      unsigned long offset, uint64_t flags)
 {
-	printf("%lu\t%s\n", offset, page_flag_name(flags));
+	if (opt_pid)
+		printf("%lx\t", voffset);
+	printf("%lx\t%s\n", offset, page_flag_name(flags));
 }
 
 static void show_summary(void)
@@ -320,6 +443,62 @@ static uint64_t well_known_flags(uint64_t flags)
 	return flags;
 }
 
+static uint64_t kpageflags_flags(uint64_t flags)
+{
+	flags = expand_overloaded_flags(flags);
+
+	if (!opt_raw)
+		flags = well_known_flags(flags);
+
+	return flags;
+}
+
+/*
+ * page actions
+ */
+
+static void prepare_hwpoison_fd(void)
+{
+	char buf[100];
+
+	if (opt_hwpoison && !hwpoison_inject_fd) {
+		sprintf(buf, "%s/corrupt-pfn", hwpoison_debug_fs);
+		hwpoison_inject_fd = checked_open(buf, O_WRONLY);
+	}
+
+	if (opt_unpoison && !hwpoison_forget_fd) {
+		sprintf(buf, "%s/renew-pfn", hwpoison_debug_fs);
+		hwpoison_forget_fd = checked_open(buf, O_WRONLY);
+	}
+}
+
+static int hwpoison_page(unsigned long offset)
+{
+	char buf[100];
+	int len;
+
+	len = sprintf(buf, "0x%lx\n", offset);
+	len = write(hwpoison_inject_fd, buf, len);
+	if (len < 0) {
+		perror("hwpoison inject");
+		return len;
+	}
+	return 0;
+}
+
+static int unpoison_page(unsigned long offset)
+{
+	char buf[100];
+	int len;
+
+	len = sprintf(buf, "0x%lx\n", offset);
+	len = write(hwpoison_forget_fd, buf, len);
+	if (len < 0) {
+		perror("hwpoison forget");
+		return len;
+	}
+	return 0;
+}
 
 /*
  * page frame walker
@@ -352,73 +531,124 @@ static int hash_slot(uint64_t flags)
 	exit(EXIT_FAILURE);
 }
 
-static void add_page(unsigned long offset, uint64_t flags)
+static void add_page(unsigned long voffset,
+		     unsigned long offset, uint64_t flags)
 {
-	flags = expand_overloaded_flags(flags);
-
-	if (!opt_raw)
-		flags = well_known_flags(flags);
+	flags = kpageflags_flags(flags);
 
 	if (!bit_mask_ok(flags))
 		return;
 
+	if (opt_hwpoison)
+		hwpoison_page(offset);
+	if (opt_unpoison)
+		unpoison_page(offset);
+
 	if (opt_list == 1)
-		show_page_range(offset, flags);
+		show_page_range(voffset, offset, flags);
 	else if (opt_list == 2)
-		show_page(offset, flags);
+		show_page(voffset, offset, flags);
 
 	nr_pages[hash_slot(flags)]++;
 	total_pages++;
 }
 
-static void walk_pfn(unsigned long index, unsigned long count)
+#define KPAGEFLAGS_BATCH	(64 << 10)	/* 64k pages */
+static void walk_pfn(unsigned long voffset,
+		     unsigned long index,
+		     unsigned long count)
 {
+	uint64_t buf[KPAGEFLAGS_BATCH];
 	unsigned long batch;
-	unsigned long n;
+	unsigned long pages;
 	unsigned long i;
 
-	if (index > ULONG_MAX / KPF_BYTES)
-		fatal("index overflow: %lu\n", index);
+	while (count) {
+		batch = min_t(unsigned long, count, KPAGEFLAGS_BATCH);
+		pages = kpageflags_read(buf, index, batch);
+		if (pages == 0)
+			break;
+
+		for (i = 0; i < pages; i++)
+			add_page(voffset + i, index + i, buf[i]);
+
+		index += pages;
+		count -= pages;
+	}
+}
 
-	lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET);
+#define PAGEMAP_BATCH	(64 << 10)
+static void walk_vma(unsigned long index, unsigned long count)
+{
+	uint64_t buf[PAGEMAP_BATCH];
+	unsigned long batch;
+	unsigned long pages;
+	unsigned long pfn;
+	unsigned long i;
 
 	while (count) {
-		batch = min_t(unsigned long, count, PAGES_BATCH);
-		n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES);
-		if (n == 0)
+		batch = min_t(unsigned long, count, PAGEMAP_BATCH);
+		pages = pagemap_read(buf, index, batch);
+		if (pages == 0)
 			break;
-		if (n < 0) {
-			perror(PROC_KPAGEFLAGS);
-			exit(EXIT_FAILURE);
+
+		for (i = 0; i < pages; i++) {
+			pfn = pagemap_pfn(buf[i]);
+			if (pfn)
+				walk_pfn(index + i, pfn, 1);
 		}
 
-		if (n % KPF_BYTES != 0)
-			fatal("partial read: %lu bytes\n", n);
-		n = n / KPF_BYTES;
+		index += pages;
+		count -= pages;
+	}
+}
+
+static void walk_task(unsigned long index, unsigned long count)
+{
+	const unsigned long end = index + count;
+	unsigned long start;
+	int i = 0;
+
+	while (index < end) {
 
-		for (i = 0; i < n; i++)
-			add_page(index + i, kpageflags_buf[i]);
+		while (pg_end[i] <= index)
+			if (++i >= nr_vmas)
+				return;
+		if (pg_start[i] >= end)
+			return;
 
-		index += batch;
-		count -= batch;
+		start = max_t(unsigned long, pg_start[i], index);
+		index = min_t(unsigned long, pg_end[i], end);
+
+		assert(start < index);
+		walk_vma(start, index - start);
 	}
 }
 
+static void add_addr_range(unsigned long offset, unsigned long size)
+{
+	if (nr_addr_ranges >= MAX_ADDR_RANGES)
+		fatal("too many addr ranges\n");
+
+	opt_offset[nr_addr_ranges] = offset;
+	opt_size[nr_addr_ranges] = min_t(unsigned long, size, ULONG_MAX-offset);
+	nr_addr_ranges++;
+}
+
 static void walk_addr_ranges(void)
 {
 	int i;
 
-	kpageflags_fd = open(PROC_KPAGEFLAGS, O_RDONLY);
-	if (kpageflags_fd < 0) {
-		perror(PROC_KPAGEFLAGS);
-		exit(EXIT_FAILURE);
-	}
+	kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY);
 
 	if (!nr_addr_ranges)
-		walk_pfn(0, ULONG_MAX);
+		add_addr_range(0, ULONG_MAX);
 
 	for (i = 0; i < nr_addr_ranges; i++)
-		walk_pfn(opt_offset[i], opt_size[i]);
+		if (!opt_pid)
+			walk_pfn(0, opt_offset[i], opt_size[i]);
+		else
+			walk_task(opt_offset[i], opt_size[i]);
 
 	close(kpageflags_fd);
 }
@@ -446,20 +676,22 @@ static void usage(void)
 "            -r|--raw                  Raw mode, for kernel developers\n"
 "            -a|--addr    addr-spec    Walk a range of pages\n"
 "            -b|--bits    bits-spec    Walk pages with specified bits\n"
-#if 0 /* planned features */
 "            -p|--pid     pid          Walk process address space\n"
+#if 0 /* planned features */
 "            -f|--file    filename     Walk file address space\n"
 #endif
 "            -l|--list                 Show page details in ranges\n"
 "            -L|--list-each            Show page details one by one\n"
 "            -N|--no-summary           Don't show summay info\n"
+"            -X|--hwpoison             hwpoison pages\n"
+"            -x|--unpoison             unpoison pages\n"
 "            -h|--help                 Show this usage message\n"
 "addr-spec:\n"
 "            N                         one page at offset N (unit: pages)\n"
 "            N+M                       pages range from N to N+M-1\n"
 "            N,M                       pages range from N to M-1\n"
 "            N,                        pages range from N to end\n"
-"            ,M                        pages range from 0 to M\n"
+"            ,M                        pages range from 0 to M-1\n"
 "bits-spec:\n"
 "            bit1,bit2                 (flags & (bit1|bit2)) != 0\n"
 "            bit1,bit2=bit1            (flags & (bit1|bit2)) == bit1\n"
@@ -496,21 +728,53 @@ static unsigned long long parse_number(const char *str)
 
 static void parse_pid(const char *str)
 {
+	FILE *file;
+	char buf[5000];
+
 	opt_pid = parse_number(str);
-}
 
-static void parse_file(const char *name)
-{
+	sprintf(buf, "/proc/%d/pagemap", opt_pid);
+	pagemap_fd = checked_open(buf, O_RDONLY);
+
+	sprintf(buf, "/proc/%d/maps", opt_pid);
+	file = fopen(buf, "r");
+	if (!file) {
+		perror(buf);
+		exit(EXIT_FAILURE);
+	}
+
+	while (fgets(buf, sizeof(buf), file) != NULL) {
+		unsigned long vm_start;
+		unsigned long vm_end;
+		unsigned long long pgoff;
+		int major, minor;
+		char r, w, x, s;
+		unsigned long ino;
+		int n;
+
+		n = sscanf(buf, "%lx-%lx %c%c%c%c %llx %x:%x %lu",
+			   &vm_start,
+			   &vm_end,
+			   &r, &w, &x, &s,
+			   &pgoff,
+			   &major, &minor,
+			   &ino);
+		if (n < 10) {
+			fprintf(stderr, "unexpected line: %s\n", buf);
+			continue;
+		}
+		pg_start[nr_vmas] = vm_start / page_size;
+		pg_end[nr_vmas] = vm_end / page_size;
+		if (++nr_vmas >= MAX_VMAS) {
+			fprintf(stderr, "too many VMAs\n");
+			break;
+		}
+	}
+	fclose(file);
 }
 
-static void add_addr_range(unsigned long offset, unsigned long size)
+static void parse_file(const char *name)
 {
-	if (nr_addr_ranges >= MAX_ADDR_RANGES)
-		fatal("too much addr ranges\n");
-
-	opt_offset[nr_addr_ranges] = offset;
-	opt_size[nr_addr_ranges] = size;
-	nr_addr_ranges++;
 }
 
 static void parse_addr_range(const char *optarg)
@@ -630,6 +894,8 @@ static struct option opts[] = {
 	{ "list"      , 0, NULL, 'l' },
 	{ "list-each" , 0, NULL, 'L' },
 	{ "no-summary", 0, NULL, 'N' },
+	{ "hwpoison"  , 0, NULL, 'X' },
+	{ "unpoison"  , 0, NULL, 'x' },
 	{ "help"      , 0, NULL, 'h' },
 	{ NULL        , 0, NULL, 0 }
 };
@@ -641,7 +907,7 @@ int main(int argc, char *argv[])
 	page_size = getpagesize();
 
 	while ((c = getopt_long(argc, argv,
-				"rp:f:a:b:lLNh", opts, NULL)) != -1) {
+				"rp:f:a:b:lLNXxh", opts, NULL)) != -1) {
 		switch (c) {
 		case 'r':
 			opt_raw = 1;
@@ -667,6 +933,14 @@ int main(int argc, char *argv[])
 		case 'N':
 			opt_no_summary = 1;
 			break;
+		case 'X':
+			opt_hwpoison = 1;
+			prepare_hwpoison_fd();
+			break;
+		case 'x':
+			opt_unpoison = 1;
+			prepare_hwpoison_fd();
+			break;
 		case 'h':
 			usage();
 			exit(0);
@@ -676,15 +950,17 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	if (opt_list && opt_pid)
+		printf("voffset\t");
 	if (opt_list == 1)
-		printf("offset\tcount\tflags\n");
+		printf("offset\tlen\tflags\n");
 	if (opt_list == 2)
 		printf("offset\tflags\n");
 
 	walk_addr_ranges();
 
 	if (opt_list == 1)
-		show_page_range(0, 0);  /* drain the buffer */
+		show_page_range(0, 0, 0);  /* drain the buffer */
 
 	if (opt_no_summary)
 		return 0;

Documentation/vm/pagemap.txt

@@ -57,7 +57,9 @@ There are three components to pagemap:
     16. COMPOUND_TAIL
     16. HUGE
     18. UNEVICTABLE
+    19. HWPOISON
     20. NOPAGE
+    21. KSM
 
 Short descriptions to the page flags:
 
@@ -86,9 +88,15 @@ Short descriptions to the page flags:
 17. HUGE
     this is an integral part of a HugeTLB page
 
+19. HWPOISON
+    hardware detected memory corruption on this page: don't touch the data!
+
 20. NOPAGE
     no page frame exists at the requested address
 
+21. KSM
+    identical memory pages dynamically shared between one or more processes
+
     [IO related page flags]
  1. ERROR     IO error occurred
  3. UPTODATE  page has up-to-date data

Documentation/w1/masters/ds2482

@@ -24,8 +24,8 @@ General Remarks
 
 Valid addresses are 0x18, 0x19, 0x1a, and 0x1b.
 However, the device cannot be detected without writing to the i2c bus, so no
-detection is done.
-You should force the device address.
+detection is done. You should instantiate the device explicitly.
 
-$ modprobe ds2482 force=0,0x18
+$ modprobe ds2482
+$ echo ds2482 0x18 > /sys/bus/i2c/devices/i2c-0/new_device
 

MAINTAINERS

@@ -65,43 +65,51 @@ trivial patch so apply some common sense.
 
 8.	Happy hacking.
 
-		-----------------------------------
-
-Maintainers List (try to look for most precise areas first)
+Descriptions of section entries:
+
+	P: Person (obsolete)
+	M: Mail patches to: FullName <address@domain>
+	L: Mailing list that is relevant to this area
+	W: Web-page with status/info
+	T: SCM tree type and location.  Type is one of: git, hg, quilt, stgit.
+	S: Status, one of the following:
+	   Supported:	Someone is actually paid to look after this.
+	   Maintained:	Someone actually looks after it.
+	   Odd Fixes:	It has a maintainer but they don't have time to do
+			much other than throw the odd patch in. See below..
+	   Orphan:	No current maintainer [but maybe you could take the
+			role as you write your new code].
+	   Obsolete:	Old code. Something tagged obsolete generally means
+			it has been replaced by a better system and you
+			should be using that.
+	F: Files and directories with wildcard patterns.
+	   A trailing slash includes all files and subdirectory files.
+	   F:	drivers/net/	all files in and below drivers/net
+	   F:	drivers/net/*	all files in drivers/net, but not below
+	   F:	*/net/*		all files in "any top level directory"/net
+	   One pattern per line.  Multiple F: lines acceptable.
+	X: Files and directories that are NOT maintained, same rules as F:
+	   Files exclusions are tested before file matches.
+	   Can be useful for excluding a specific subdirectory, for instance:
+	   F:	net/
+	   X:	net/ipv6/
+	   matches all files in and below net excluding net/ipv6/
+	K: Keyword perl extended regex pattern to match content in a
+	   patch or file.  For instance:
+	   K: of_get_profile
+	      matches patches or files that contain "of_get_profile"
+	   K: \b(printk|pr_(info|err))\b
+	      matches patches or files that contain one or more of the words
+	      printk, pr_info or pr_err
+	   One regex pattern per line.  Multiple K: lines acceptable.
 
 Note: For the hard of thinking, this list is meant to remain in alphabetical
 order. If you could add yourselves to it in alphabetical order that would be
 so much easier [Ed]
 
-P: Person (obsolete)
-M: Mail patches to: FullName <address@domain>
-L: Mailing list that is relevant to this area
-W: Web-page with status/info
-T: SCM tree type and location.  Type is one of: git, hg, quilt, stgit.
-S: Status, one of the following:
-
-	Supported:	Someone is actually paid to look after this.
-	Maintained:	Someone actually looks after it.
-	Odd Fixes:	It has a maintainer but they don't have time to do
-			much other than throw the odd patch in. See below..
-	Orphan:		No current maintainer [but maybe you could take the
-			role as you write your new code].
-	Obsolete:	Old code. Something tagged obsolete generally means
-			it has been replaced by a better system and you
-			should be using that.
+Maintainers List (try to look for most precise areas first)
 
-F: Files and directories with wildcard patterns.
-   A trailing slash includes all files and subdirectory files.
-	F:	drivers/net/	all files in and below drivers/net
-	F:	drivers/net/*	all files in drivers/net, but not below
-	F:	*/net/*		all files in "any top level directory"/net
-   One pattern per line.  Multiple F: lines acceptable.
-X: Files and directories that are NOT maintained, same rules as F:
-   Files exclusions are tested before file matches.
-   Can be useful for excluding a specific subdirectory, for instance:
-	F:	net/
-	X:	net/ipv6/
-   matches all files in and below net excluding net/ipv6/
+		-----------------------------------
 
 3C505 NETWORK DRIVER
 M:	Philip Blundell <philb@gnu.org>
@@ -174,7 +182,7 @@ M:	Ron Minnich <rminnich@sandia.gov>
 M:	Latchesar Ionkov <lucho@ionkov.net>
 L:	v9fs-developer@lists.sourceforge.net
 W:	http://swik.net/v9fs
-T:	git git://git.kernel.org/pub/scm/linux/kernel/ericvh/v9fs.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs.git
 S:	Maintained
 F:	Documentation/filesystems/9p.txt
 F:	fs/9p/
@@ -257,11 +265,12 @@ W:	http://www.lesswatts.org/projects/acpi/
 S:	Supported
 F:	drivers/acpi/fan.c
 
-ACPI PCI HOTPLUG DRIVER
-M:	Kristen Carlson Accardi <kristen.c.accardi@intel.com>
-L:	linux-pci@vger.kernel.org
+ACPI PROCESSOR AGGREGATOR DRIVER
+M:	Shaohua Li <shaohua.li@intel.com>
+L:	linux-acpi@vger.kernel.org
+W:	http://www.lesswatts.org/projects/acpi/
 S:	Supported
-F:	drivers/pci/hotplug/acpi*
+F:	drivers/acpi/acpi_pad.c
 
 ACPI THERMAL DRIVER
 M:	Zhang Rui <rui.zhang@intel.com>
@@ -503,10 +512,32 @@ W:	http://www.arm.linux.org.uk/
 S:	Maintained
 F:	arch/arm/
 
+ARM PRIMECELL AACI PL041 DRIVER
+M:	Russell King <linux@arm.linux.org.uk>
+S:	Maintained
+F:	sound/arm/aaci.*
+
+ARM PRIMECELL CLCD PL110 DRIVER
+M:	Russell King <linux@arm.linux.org.uk>
+S:	Maintained
+F:	drivers/video/amba-clcd.*
+
+ARM PRIMECELL KMI PL050 DRIVER
+M:	Russell King <linux@arm.linux.org.uk>
+S:	Maintained
+F:	drivers/input/serio/ambakmi.*
+F:	include/linux/amba/kmi.h
+
 ARM PRIMECELL MMCI PL180/1 DRIVER
 S:	Orphan
 F:	drivers/mmc/host/mmci.*
 
+ARM PRIMECELL BUS SUPPORT
+M:	Russell King <linux@arm.linux.org.uk>
+S:	Maintained
+F:	drivers/amba/
+F:	include/linux/amba/bus.h
+
 ARM/ADI ROADRUNNER MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -576,6 +607,11 @@ M:	Mike Rapoport <mike@compulab.co.il>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
+ARM/CONTEC MICRO9 MACHINE SUPPORT
+M:	Hubert Feurstein <hubert.feurstein@contec.at>
+S:	Maintained
+F:	arch/arm/mach-ep93xx/micro9.c
+
 ARM/CORGI MACHINE SUPPORT
 M:	Richard Purdie <rpurdie@rpsys.net>
 S:	Maintained
@@ -652,24 +688,24 @@ ARM/INTEL IOP32X ARM ARCHITECTURE
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Maintained
 
 ARM/INTEL IOP33X ARM ARCHITECTURE
 M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Maintained
 
 ARM/INTEL IOP13XX ARM ARCHITECTURE
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Maintained
 
 ARM/INTEL IQ81342EX MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Maintained
 
 ARM/INTEL IXP2000 ARM ARCHITECTURE
 M:	Lennert Buytenhek <kernel@wantstofly.org>
@@ -686,11 +722,18 @@ M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
+ARM/INTEL IXP4XX ARM ARCHITECTURE
+M:	Imre Kaloz <kaloz@openwrt.org>
+M:	Krzysztof Halasa <khc@pm.waw.pl>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/mach-ixp4xx/
+
 ARM/INTEL XSC3 (MANZANO) ARM CORE
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Maintained
 
 ARM/IP FABRICS DOUBLE ESPRESSO MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
@@ -739,20 +782,37 @@ M:	Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
 M:	Dirk Opfer <dirk@opfer-online.de>
 S:	Maintained
 
-ARM/PALMTX,PALMT5,PALMLD,PALMTE2 SUPPORT
+ARM/PALMTX,PALMT5,PALMLD,PALMTE2,PALMTC SUPPORT
 M:	Marek Vasut <marek.vasut@gmail.com>
+L:	linux-arm-kernel@lists.infradead.org
 W:	http://hackndev.com
 S:	Maintained
+F:	arch/arm/mach-pxa/include/mach/palmtx.h
+F:	arch/arm/mach-pxa/palmtx.c
+F:	arch/arm/mach-pxa/include/mach/palmt5.h
+F:	arch/arm/mach-pxa/palmt5.c
+F:	arch/arm/mach-pxa/include/mach/palmld.h
+F:	arch/arm/mach-pxa/palmld.c
+F:	arch/arm/mach-pxa/include/mach/palmte2.h
+F:	arch/arm/mach-pxa/palmte2.c
+F:	arch/arm/mach-pxa/include/mach/palmtc.h
+F:	arch/arm/mach-pxa/palmtc.c
 
 ARM/PALM TREO 680 SUPPORT
 M:	Tomas Cech <sleep_walker@suse.cz>
+L:	linux-arm-kernel@lists.infradead.org
 W:	http://hackndev.com
 S:	Maintained
+F:	arch/arm/mach-pxa/include/mach/treo680.h
+F:	arch/arm/mach-pxa/treo680.c
 
 ARM/PALMZ72 SUPPORT
 M:	Sergey Lapin <slapin@ossfans.org>
+L:	linux-arm-kernel@lists.infradead.org
 W:	http://hackndev.com
 S:	Maintained
+F:	arch/arm/mach-pxa/include/mach/palmz72.h
+F:	arch/arm/mach-pxa/palmz72.c
 
 ARM/PLEB SUPPORT
 M:	Peter Chubb <pleb@gelato.unsw.edu.au>
@@ -868,7 +928,6 @@ M:	Karol Kozimor <sziwan@users.sourceforge.net>
 L:	acpi4asus-user@lists.sourceforge.net
 W:	http://acpi4asus.sf.net
 S:	Maintained
-F:	arch/x86/kernel/acpi/boot.c
 F:	drivers/platform/x86/asus_acpi.c
 
 ASUS ASB100 HARDWARE MONITOR DRIVER
@@ -962,7 +1021,7 @@ F:	drivers/net/atlx/
 
 ATM
 M:	Chas Williams <chas@cmf.nrl.navy.mil>
-L:	linux-atm-general@lists.sourceforge.net (subscribers-only)
+L:	linux-atm-general@lists.sourceforge.net (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
 W:	http://linux-atm.sourceforge.net
 S:	Maintained
@@ -990,7 +1049,7 @@ F:	drivers/serial/atmel_serial.c
 
 ATMEL LCDFB DRIVER
 M:	Nicolas Ferre <nicolas.ferre@atmel.com>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/atmel_lcdfb.c
 F:	include/video/atmel_lcdc.h
@@ -1206,6 +1265,12 @@ L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/tg3.*
 
+BROCADE BFA FC SCSI DRIVER
+M:	Jing Huang <huangj@brocade.com>
+L:	linux-scsi@vger.kernel.org
+S:	Supported
+F:	drivers/scsi/bfa/
+
 BSG (block layer generic sg v4 driver)
 M:	FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
 L:	linux-scsi@vger.kernel.org
@@ -1443,6 +1508,7 @@ F:	mm/*cgroup*
 
 CORETEMP HARDWARE MONITORING DRIVER
 M:	Rudolf Marek <r.marek@assembler.cz>
+M:	Huaxu Wan <huaxu.wan@intel.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/coretemp
@@ -2033,7 +2099,7 @@ S:	Maintained
 F:	fs/*
 
 FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER
-M:	Riku Voipio <riku.vipio@iki.fi>
+M:	Riku Voipio <riku.voipio@iki.fi>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	drivers/hwmon/f75375s.c
@@ -2069,7 +2135,7 @@ F:	drivers/net/wan/dlci.c
 F:	drivers/net/wan/sdla.c
 
 FRAMEBUFFER LAYER
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 W:	http://linux-fbdev.sourceforge.net/
 S:	Orphan
 F:	Documentation/fb/
@@ -2092,7 +2158,7 @@ F:	drivers/i2c/busses/i2c-cpm.c
 
 FREESCALE IMX / MXC FRAMEBUFFER DRIVER
 M:	Sascha Hauer <kernel@pengutronix.de>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/plat-mxc/include/mach/imxfb.h
@@ -2114,7 +2180,7 @@ S:	Supported
 F:	arch/powerpc/sysdev/qe_lib/
 F:	arch/powerpc/include/asm/*qe.h
 
-FREESCALE USB PERIPHERIAL DRIVERS
+FREESCALE USB PERIPHERAL DRIVERS
 M:	Li Yang <leoli@freescale.com>
 L:	linux-usb@vger.kernel.org
 L:	linuxppc-dev@ozlabs.org
@@ -2165,18 +2231,6 @@ F:	Documentation/filesystems/caching/
 F:	fs/fscache/
 F:	include/linux/fscache*.h
 
-TRACING
-M:	Steven Rostedt <rostedt@goodmis.org>
-M:	Frederic Weisbecker <fweisbec@gmail.com>
-M:	Ingo Molnar <mingo@redhat.com>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git tracing/core
-S:	Maintained
-F:	Documentation/trace/ftrace.txt
-F:	arch/*/*/*/ftrace.h
-F:	arch/*/kernel/ftrace.c
-F:	include/*/ftrace.h include/trace/ include/linux/trace*.h
-F:	kernel/trace/
-
 FUJITSU FR-V (FRV) PORT
 M:	David Howells <dhowells@redhat.com>
 S:	Maintained
@@ -2235,9 +2289,8 @@ S:	Maintained
 F:	include/asm-generic
 
 GENERIC UIO DRIVER FOR PCI DEVICES
-M:	Michael S. Tsirkin <mst@redhat.com>
+M:	"Michael S. Tsirkin" <mst@redhat.com>
 L:	kvm@vger.kernel.org
-L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	drivers/uio/uio_pci_generic.c
 
@@ -2281,6 +2334,13 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git
 S:	Maintained
 F:	drivers/media/video/gspca/finepix.c
 
+GSPCA GL860 SUBDRIVER
+M:	Olivier Lorin <o.lorin@laposte.net>
+L:	linux-media@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git
+S:	Maintained
+F:	drivers/media/video/gspca/gl860/
+
 GSPCA M5602 SUBDRIVER
 M:	Erik Andren <erik.andren@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -2324,7 +2384,9 @@ S:	Orphan
 F:	drivers/hwmon/
 
 HARDWARE RANDOM NUMBER GENERATOR CORE
-S:	Orphan
+M:	Matt Mackall <mpm@selenic.com>
+M:	Herbert Xu <herbert@gondor.apana.org.au>
+S:	Odd fixes
 F:	Documentation/hw_random.txt
 F:	drivers/char/hw_random/
 F:	include/linux/hw_random.h
@@ -2500,8 +2562,7 @@ S:	Maintained
 F:	Documentation/i2c/
 F:	drivers/i2c/
 F:	include/linux/i2c.h
-F:	include/linux/i2c-dev.h
-F:	include/linux/i2c-id.h
+F:	include/linux/i2c-*.h
 
 I2C-TINY-USB DRIVER
 M:	Till Harbaum <till@harbaum.org>
@@ -2576,6 +2637,7 @@ L:	linux1394-devel@lists.sourceforge.net
 W:	http://www.linux1394.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394-2.6.git
 S:	Maintained
+F:	Documentation/debugging-via-ohci1394.txt
 F:	drivers/ieee1394/
 
 IEEE 1394 RAW I/O DRIVER
@@ -2601,7 +2663,7 @@ S:	Supported
 F:	security/integrity/ima/
 
 IMS TWINTURBO FRAMEBUFFER DRIVER
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Orphan
 F:	drivers/video/imsttfb.c
 
@@ -2636,14 +2698,14 @@ F:	drivers/input/
 
 INTEL FRAMEBUFFER DRIVER (excluding 810 and 815)
 M:	Sylvain Meyer <sylvain.meyer@worldonline.fr>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/fb/intelfb.txt
 F:	drivers/video/intelfb/
 
 INTEL 810/815 FRAMEBUFFER DRIVER
 M:	Antonino Daplas <adaplas@gmail.com>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/i810/
 
@@ -2675,7 +2737,7 @@ F:	include/linux/intel-iommu.h
 
 INTEL IOP-ADMA DMA DRIVER
 M:	Dan Williams <dan.j.williams@intel.com>
-S:	Supported
+S:	Maintained
 F:	drivers/dma/iop-adma.c
 
 INTEL IXP4XX QMGR, NPE, ETHERNET and HSS SUPPORT
@@ -2789,7 +2851,7 @@ F:	drivers/infiniband/hw/ipath/
 
 IPMI SUBSYSTEM
 M:	Corey Minyard <minyard@acm.org>
-L:	openipmi-developer@lists.sourceforge.net
+L:	openipmi-developer@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://openipmi.sourceforge.net/
 S:	Supported
 F:	Documentation/IPMI.txt
@@ -2953,19 +3015,16 @@ S:	Maintained
 F:	fs/autofs4/
 
 KERNEL BUILD
-M:	Sam Ravnborg <sam@ravnborg.org>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild-next.git
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild-fixes.git
 L:	linux-kbuild@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	Documentation/kbuild/
 F:	Makefile
 F:	scripts/Makefile.*
 
 KERNEL JANITORS
 L:	kernel-janitors@vger.kernel.org
-W:	http://www.kerneljanitors.org/
-S:	Maintained
+W:	http://janitor.kernelnewbies.org/
+S:	Odd Fixes
 
 KERNEL NFSD, SUNRPC, AND LOCKD SERVERS
 M:	"J. Bruce Fields" <bfields@fieldses.org>
@@ -3050,9 +3109,13 @@ F:	kernel/kgdb.c
 
 KMEMCHECK
 M:	Vegard Nossum <vegardno@ifi.uio.no>
-P	Pekka Enberg
-M:	penberg@cs.helsinki.fi
+M:	Pekka Enberg <penberg@cs.helsinki.fi>
 S:	Maintained
+F:	Documentation/kmemcheck.txt
+F:	arch/x86/include/asm/kmemcheck.h
+F:	arch/x86/mm/kmemcheck/
+F:	include/linux/kmemcheck.h
+F:	mm/kmemcheck.c
 
 KMEMLEAK
 M:	Catalin Marinas <catalin.marinas@arm.com>
@@ -3353,7 +3416,7 @@ S:	Supported
 
 MATROX FRAMEBUFFER DRIVER
 M:	Petr Vandrovec <vandrove@vc.cvut.cz>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/matrox/matroxfb_*
 F:	include/linux/matroxfb.h
@@ -3582,7 +3645,7 @@ L:	netfilter@vger.kernel.org
 L:	coreteam@netfilter.org
 W:	http://www.netfilter.org/
 W:	http://www.iptables.org/
-T:	git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-2.6.git
 S:	Supported
 F:	include/linux/netfilter*
 F:	include/linux/netfilter/
@@ -3616,11 +3679,20 @@ F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
 F:	include/linux/nbd.h
 
+NETWORK DROP MONITOR
+M:	Neil Horman <nhorman@tuxdriver.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+W:	https://fedorahosted.org/dropwatch/
+F:	net/core/drop_monitor.c
+
 NETWORKING [GENERAL]
 M:	"David S. Miller" <davem@davemloft.net>
 L:	netdev@vger.kernel.org
 W:	http://www.linuxfoundation.org/en/Net
+W:	http://patchwork.ozlabs.org/project/netdev/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6.git
 S:	Maintained
 F:	net/
 F:	include/net/
@@ -3731,13 +3803,13 @@ F:	fs/ntfs/
 
 NVIDIA (rivafb and nvidiafb) FRAMEBUFFER DRIVER
 M:	Antonino Daplas <adaplas@gmail.com>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/riva/
 F:	drivers/video/nvidia/
 
 OMAP SUPPORT
-M:	"Tony Lindgren <tony@atomide.com>" <tony@atomide.com>
+M:	Tony Lindgren <tony@atomide.com>
 L:	linux-omap@vger.kernel.org
 W:	http://www.muru.com/linux/omap/
 W:	http://linux.omap.com/
@@ -3766,7 +3838,7 @@ F:	sound/soc/omap/
 
 OMAP FRAMEBUFFER SUPPORT
 M:	Imre Deak <imre.deak@nokia.com>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 L:	linux-omap@vger.kernel.org
 S:	Maintained
 F:	drivers/video/omap/
@@ -3842,6 +3914,15 @@ S:	Maintained
 F:	Documentation/i2c/busses/i2c-ocores
 F:	drivers/i2c/busses/i2c-ocores.c
 
+OPEN FIRMWARE AND FLATTENED DEVICE TREE
+M:	Grant Likely <grant.likely@secretlab.ca>
+L:	devicetree-discuss@lists.ozlabs.org
+W:	http://fdt.secretlab.ca
+S:	Maintained
+F:	drivers/of
+F:	include/linux/of*.h
+K:	of_get_property
+
 OPROFILE
 M:	Robert Richter <robert.richter@amd.com>
 L:	oprofile-list@lists.sf.net
@@ -3946,6 +4027,7 @@ F:	drivers/block/paride/
 PARISC ARCHITECTURE
 M:	Kyle McMartin <kyle@mcmartin.ca>
 M:	Helge Deller <deller@gmx.de>
+M:	"James E.J. Bottomley" <jejb@parisc-linux.org>
 L:	linux-parisc@vger.kernel.org
 W:	http://www.parisc-linux.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kyle/parisc-2.6.git
@@ -3996,11 +4078,11 @@ F:	Documentation/PCI/
 F:	drivers/pci/
 F:	include/linux/pci*
 
-PCIE HOTPLUG DRIVER
-M:	Kristen Carlson Accardi <kristen.c.accardi@intel.com>
+PCI HOTPLUG
+M:	Jesse Barnes <jbarnes@virtuousgeek.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
-F:	drivers/pci/pcie/
+F:	drivers/pci/hotplug
 
 PCMCIA SUBSYSTEM
 P:	Linux PCMCIA Team
@@ -4029,6 +4111,13 @@ M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
 M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@elte.hu>
 S:	Supported
+F:	kernel/perf_event.c
+F:	include/linux/perf_event.h
+F:	arch/*/*/kernel/perf_event.c
+F:	arch/*/include/asm/perf_event.h
+F:	arch/*/lib/perf_event.c
+F:	arch/*/kernel/perf_callchain.c
+F:	tools/perf/
 
 PERSONALITY HANDLING
 M:	Christoph Hellwig <hch@infradead.org>
@@ -4255,21 +4344,23 @@ F:	include/linux/qnxtypes.h
 
 RADEON FRAMEBUFFER DISPLAY DRIVER
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/aty/radeon*
 F:	include/linux/radeonfb.h
 
 RAGE128 FRAMEBUFFER DISPLAY DRIVER
 M:	Paul Mackerras <paulus@samba.org>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/aty/aty128fb.c
 
 RALINK RT2X00 WIRELESS LAN DRIVER
 P:	rt2x00 project
+M:	Ivo van Doorn <IvDoorn@gmail.com>
+M:	Gertjan van Wingerde <gwingerde@gmail.com>
 L:	linux-wireless@vger.kernel.org
-L:	users@rt2x00.serialmonkey.com
+L:	users@rt2x00.serialmonkey.com (moderated for non-subscribers)
 W:	http://rt2x00.serialmonkey.com/
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ivd/rt2x00.git
@@ -4355,7 +4446,7 @@ RFKILL
 M:	Johannes Berg <johannes@sipsolutions.net>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-F	Documentation/rfkill.txt
+F:	Documentation/rfkill.txt
 F:	net/rfkill/
 
 RISCOM8 DRIVER
@@ -4399,7 +4490,7 @@ F:	drivers/net/wireless/rtl818x/rtl8187*
 
 S3 SAVAGE FRAMEBUFFER DRIVER
 M:	Antonino Daplas <adaplas@gmail.com>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/savage/
 
@@ -4478,12 +4569,11 @@ F:	kernel/sched*
 F:	include/linux/sched.h
 
 SCORE ARCHITECTURE
-P:	Chen Liqin
-M:	liqin.chen@sunplusct.com
-P:	Lennox Wu
-M:	lennox.wu@gmail.com
+M:	Chen Liqin <liqin.chen@sunplusct.com>
+M:	Lennox Wu <lennox.wu@gmail.com>
 W:	http://www.sunplusct.com
 S:	Supported
+F:	arch/score/
 
 SCSI CDROM DRIVER
 M:	Jens Axboe <axboe@kernel.dk>
@@ -4556,27 +4646,27 @@ S:	Maintained
 F:	drivers/mmc/host/sdricoh_cs.c
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) DRIVER
-S:     Orphan
-L:     linux-mmc@vger.kernel.org
-F:     drivers/mmc/host/sdhci.*
+S:	Orphan
+L:	linux-mmc@vger.kernel.org
+F:	drivers/mmc/host/sdhci.*
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE, OPEN FIRMWARE BINDINGS (SDHCI-OF)
 M:	Anton Vorontsov <avorontsov@ru.mvista.com>
 L:	linuxppc-dev@ozlabs.org
-L:     linux-mmc@vger.kernel.org
+L:	linux-mmc@vger.kernel.org
 S:	Maintained
-F:     drivers/mmc/host/sdhci-of.*
+F:	drivers/mmc/host/sdhci-of.*
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) SAMSUNG DRIVER
 M:	Ben Dooks <ben-linux@fluff.org>
-L:     linux-mmc@vger.kernel.org
+L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/sdhci-s3c.c
 
 SECURITY SUBSYSTEM
 M:	James Morris <jmorris@namei.org>
 L:	linux-security-module@vger.kernel.org (suggested Cc:)
-T:	git git://www.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6.git
 W:	http://security.wiki.kernel.org/
 S:	Supported
 F:	security/
@@ -4611,6 +4701,13 @@ F:	drivers/ata/
 F:	include/linux/ata.h
 F:	include/linux/libata.h
 
+SERVER ENGINES 10Gbps iSCSI - BladeEngine 2 DRIVER
+M:	Jayamohan Kallickal <jayamohank@serverengines.com>
+L:	linux-scsi@vger.kernel.org
+W:	http://www.serverengines.com
+S:	Supported
+F:	drivers/scsi/be2iscsi/
+
 SERVER ENGINES 10Gbps NIC - BladeEngine 2 DRIVER
 M:	Sathya Perla <sathyap@serverengines.com>
 M:	Subbu Seetharaman <subbus@serverengines.com>
@@ -4663,15 +4760,8 @@ F:	drivers/serial/serial_lh7a40x.c
 F:	drivers/usb/gadget/lh7a40*
 F:	drivers/usb/host/ohci-lh7a40*
 
-SHPC HOTPLUG DRIVER
-M:	Kristen Carlson Accardi <kristen.c.accardi@intel.com>
-L:	linux-pci@vger.kernel.org
-S:	Supported
-F:	drivers/pci/hotplug/shpchp*
-
 SIMPLE FIRMWARE INTERFACE (SFI)
-P:	Len Brown
-M:	lenb@kernel.org
+M:	Len Brown <lenb@kernel.org>
 L:	sfi-devel@simplefirmware.org
 W:	http://simplefirmware.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-sfi-2.6.git
@@ -4680,7 +4770,6 @@ F:	arch/x86/kernel/*sfi*
 F:	drivers/sfi/
 F:	include/linux/sfi*.h
 
-
 SIMTEC EB110ATX (Chalice CATS)
 P:	Ben Dooks
 M:	Vincent Sanders <support@simtec.co.uk>
@@ -5120,6 +5209,20 @@ L:	tpmdd-devel@lists.sourceforge.net (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/char/tpm/
 
+TRACING
+M:	Steven Rostedt <rostedt@goodmis.org>
+M:	Frederic Weisbecker <fweisbec@gmail.com>
+M:	Ingo Molnar <mingo@redhat.com>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git tracing/core
+S:	Maintained
+F:	Documentation/trace/ftrace.txt
+F:	arch/*/*/*/ftrace.h
+F:	arch/*/kernel/ftrace.c
+F:	include/*/ftrace.h
+F:	include/linux/trace*.h
+F:	include/trace/
+F:	kernel/trace/
+
 TRIVIAL PATCHES
 M:	Jiri Kosina <trivial@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial.git
@@ -5550,7 +5653,7 @@ S:	Maintained
 
 UVESAFB DRIVER
 M:	Michal Januszewski <spock@gentoo.org>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 W:	http://dev.gentoo.org/~spock/projects/uvesafb/
 S:	Maintained
 F:	Documentation/fb/uvesafb.txt
@@ -5583,7 +5686,7 @@ F:	drivers/mmc/host/via-sdmmc.c
 VIA UNICHROME(PRO)/CHROME9 FRAMEBUFFER DRIVER
 M:	Joseph Chan <JosephChan@via.com.tw>
 M:	Scott Fang <ScottFang@viatech.com.cn>
-L:	linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/via/
 
@@ -5608,6 +5711,13 @@ S:	Maintained
 F:	drivers/vlynq/vlynq.c
 F:	include/linux/vlynq.h
 
+VMWARE VMXNET3 ETHERNET DRIVER
+M:	Shreyas Bhatewara <sbhatewara@vmware.com>
+M:	"VMware, Inc." <pv-drivers@vmware.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/vmxnet3/
+
 VOLTAGE AND CURRENT REGULATOR FRAMEWORK
 M:	Liam Girdwood <lrg@slimlogic.co.uk>
 M:	Mark Brown <broonie@opensource.wolfsonmicro.com>
@@ -5679,8 +5789,7 @@ S:	Maintained
 F:	drivers/scsi/wd7000.c
 
 WINBOND CIR DRIVER
-P:	David Härdeman
-M:	david@hardeman.nu
+M:	David Härdeman <david@hardeman.nu>
 S:	Maintained
 F:	drivers/input/misc/winbond-cir.c
 
@@ -5737,9 +5846,7 @@ F:	drivers/input/touchscreen/*wm97*
 F:	include/linux/wm97xx.h
 
 WOLFSON MICROELECTRONICS PMIC DRIVERS
-P:	Mark Brown
-M:	broonie@opensource.wolfsonmicro.com
-L:	linux-kernel@vger.kernel.org
+M:	Mark Brown <broonie@opensource.wolfsonmicro.com>
 T:	git git://opensource.wolfsonmicro.com/linux-2.6-audioplus
 W:	http://opensource.wolfsonmicro.com/node/8
 S:	Supported

Makefile

@@ -1,6 +1,6 @@
 VERSION = 2
 PATCHLEVEL = 6
-SUBLEVEL = 31
+SUBLEVEL = 32
 EXTRAVERSION =
 NAME = Man-Eating Seals of Antiquity
 
@@ -221,7 +221,7 @@ CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \
 
 HOSTCC       = gcc
 HOSTCXX      = g++
-HOSTCFLAGS   = -Wall -Wstrict-prototypes -O2 -fomit-frame-pointer
+HOSTCFLAGS   = -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 -fomit-frame-pointer
 HOSTCXXFLAGS = -O2
 
 # Decide whether to build built-in, modular, or both.
@@ -315,6 +315,7 @@ OBJCOPY		= $(CROSS_COMPILE)objcopy
 OBJDUMP		= $(CROSS_COMPILE)objdump
 AWK		= awk
 GENKSYMS	= scripts/genksyms/genksyms
+INSTALLKERNEL  := installkernel
 DEPMOD		= /sbin/depmod
 KALLSYMS	= scripts/kallsyms
 PERL		= perl
@@ -353,7 +354,8 @@ KERNELVERSION = $(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION)
 
 export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION
 export ARCH SRCARCH CONFIG_SHELL HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP MAKE AWK GENKSYMS PERL UTS_MACHINE
+export CPP AR NM STRIP OBJCOPY OBJDUMP
+export MAKE AWK GENKSYMS INSTALLKERNEL PERL UTS_MACHINE
 export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
 
 export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS
@@ -571,6 +573,9 @@ KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 # revert to pre-gcc-4.4 behaviour of .eh_frame
 KBUILD_CFLAGS	+= $(call cc-option,-fno-dwarf2-cfi-asm)
 
+# conserve stack if available
+KBUILD_CFLAGS   += $(call cc-option,-fconserve-stack)
+
 # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
 # But warn user when we do so
 warn-assign = \
@@ -591,12 +596,12 @@ endif
 
 # Use --build-id when available.
 LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\
-			      $(call ld-option, -Wl$(comma)--build-id,))
+			      $(call cc-ldoption, -Wl$(comma)--build-id,))
 LDFLAGS_MODULE += $(LDFLAGS_BUILD_ID)
 LDFLAGS_vmlinux += $(LDFLAGS_BUILD_ID)
 
 ifeq ($(CONFIG_STRIP_ASM_SYMS),y)
-LDFLAGS_vmlinux	+= -X
+LDFLAGS_vmlinux	+= $(call ld-option, -X,)
 endif
 
 # Default kernel image to build when no specific target is given.
@@ -980,11 +985,6 @@ prepare0: archprepare FORCE
 # All the preparing..
 prepare: prepare0
 
-# Leave this as default for preprocessing vmlinux.lds.S, which is now
-# done in arch/$(ARCH)/kernel/Makefile
-
-export CPPFLAGS_vmlinux.lds += -P -C -U$(ARCH)
-
 # The asm symlink changes when $(ARCH) changes.
 # Detect this and ask user to run make mrproper
 # If asm is a stale symlink (point to dir that does not exist) remove it

arch/alpha/boot/tools/objstrip.c

@@ -35,7 +35,7 @@
 const char * prog_name;
 
 
-void
+static void
 usage (void)
 {
     fprintf(stderr,

arch/alpha/include/asm/smp.h

@@ -47,7 +47,7 @@ extern struct cpuinfo_alpha cpu_data[NR_CPUS];
 extern int smp_num_cpus;
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #else /* CONFIG_SMP */
 

arch/alpha/include/asm/thread_info.h

@@ -50,32 +50,35 @@ struct thread_info {
 register struct thread_info *__current_thread_info __asm__("$8");
 #define current_thread_info()  __current_thread_info
 
+#endif /* __ASSEMBLY__ */
+
 /* Thread information allocation.  */
 #define THREAD_SIZE_ORDER 1
 #define THREAD_SIZE (2*PAGE_SIZE)
 
-#endif /* __ASSEMBLY__ */
-
 #define PREEMPT_ACTIVE		0x40000000
 
 /*
  * Thread information flags:
  * - these are process state flags and used from assembly
- * - pending work-to-be-done flags come first to fit in and immediate operand.
+ * - pending work-to-be-done flags come first and must be assigned to be
+ *   within bits 0 to 7 to fit in and immediate operand.
+ * - ALPHA_UAC_SHIFT below must be kept consistent with the unaligned
+ *   control flags.
  *
  * TIF_SYSCALL_TRACE is known to be 0 via blbs.
  */
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
-#define TIF_SIGPENDING		1	/* signal pending */
-#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_POLLING_NRFLAG	3	/* poll_idle is polling NEED_RESCHED */
-#define TIF_DIE_IF_KERNEL	4	/* dik recursion lock */
-#define TIF_UAC_NOPRINT		5	/* see sysinfo.h */
-#define TIF_UAC_NOFIX		6
-#define TIF_UAC_SIGBUS		7
-#define TIF_MEMDIE		8
-#define TIF_RESTORE_SIGMASK	9	/* restore signal mask in do_signal */
-#define TIF_NOTIFY_RESUME	10	/* callback before returning to user */
+#define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
+#define TIF_SIGPENDING		2	/* signal pending */
+#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
+#define TIF_POLLING_NRFLAG	8	/* poll_idle is polling NEED_RESCHED */
+#define TIF_DIE_IF_KERNEL	9	/* dik recursion lock */
+#define TIF_UAC_NOPRINT		10	/* see sysinfo.h */
+#define TIF_UAC_NOFIX		11
+#define TIF_UAC_SIGBUS		12
+#define TIF_MEMDIE		13
+#define TIF_RESTORE_SIGMASK	14	/* restore signal mask in do_signal */
 #define TIF_FREEZE		16	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -94,7 +97,7 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define _TIF_ALLWORK_MASK	(_TIF_WORK_MASK		\
 				 | _TIF_SYSCALL_TRACE)
 
-#define ALPHA_UAC_SHIFT		6
+#define ALPHA_UAC_SHIFT		10
 #define ALPHA_UAC_MASK		(1 << TIF_UAC_NOPRINT | 1 << TIF_UAC_NOFIX | \
 				 1 << TIF_UAC_SIGBUS)
 

arch/alpha/include/asm/topology.h

@@ -22,23 +22,6 @@ static inline int cpu_to_node(int cpu)
 	return node;
 }
 
-static inline cpumask_t node_to_cpumask(int node)
-{
-	cpumask_t node_cpu_mask = CPU_MASK_NONE;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if (cpu_to_node(cpu) == node)
-			cpu_set(cpu, node_cpu_mask);
-	}
-
-#ifdef DEBUG_NUMA
-	printk("node %d: cpu_mask: %016lx\n", node, node_cpu_mask);
-#endif
-
-	return node_cpu_mask;
-}
-
 extern struct cpumask node_to_cpumask_map[];
 /* FIXME: This is dumb, recalculating every time.  But simple. */
 static const struct cpumask *cpumask_of_node(int node)
@@ -55,7 +38,6 @@ static const struct cpumask *cpumask_of_node(int node)
 	return &node_to_cpumask_map[node];
 }
 
-#define pcibus_to_cpumask(bus)	(cpu_online_map)
 #define cpumask_of_pcibus(bus)	(cpu_online_mask)
 
 #endif /* !CONFIG_NUMA */

arch/alpha/kernel/core_marvel.c

@@ -1016,7 +1016,7 @@ marvel_agp_bind_memory(alpha_agp_info *agp, off_t pg_start, struct agp_memory *m
 {
 	struct marvel_agp_aperture *aper = agp->aperture.sysdata;
 	return iommu_bind(aper->arena, aper->pg_start + pg_start, 
-			  mem->page_count, mem->memory);
+			  mem->page_count, mem->pages);
 }
 
 static int 
@@ -1103,6 +1103,8 @@ marvel_agp_info(void)
 	 * Allocate the info structure.
 	 */
 	agp = kmalloc(sizeof(*agp), GFP_KERNEL);
+	if (!agp)
+		return NULL;
 
 	/*
 	 * Fill it in.

arch/alpha/kernel/core_titan.c

@@ -680,7 +680,7 @@ titan_agp_bind_memory(alpha_agp_info *agp, off_t pg_start, struct agp_memory *me
 {
 	struct titan_agp_aperture *aper = agp->aperture.sysdata;
 	return iommu_bind(aper->arena, aper->pg_start + pg_start, 
-			  mem->page_count, mem->memory);
+			  mem->page_count, mem->pages);
 }
 
 static int 
@@ -757,6 +757,8 @@ titan_agp_info(void)
 	 * Allocate the info structure.
 	 */
 	agp = kmalloc(sizeof(*agp), GFP_KERNEL);
+	if (!agp)
+		return NULL;
 
 	/*
 	 * Fill it in.

arch/alpha/kernel/init_task.c

@@ -13,6 +13,5 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
 struct task_struct init_task = INIT_TASK(init_task);
 EXPORT_SYMBOL(init_task);
 
-union thread_union init_thread_union
-	__attribute__((section(".data.init_thread")))
-	= { INIT_THREAD_INFO(init_task) };
+union thread_union init_thread_union __init_task_data =
+	{ INIT_THREAD_INFO(init_task) };

arch/alpha/kernel/irq.c

@@ -92,7 +92,7 @@ show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[irq].chip->typename);
+		seq_printf(p, " %14s", irq_desc[irq].chip->name);
 		seq_printf(p, "  %c%s",
 			(action->flags & IRQF_DISABLED)?'+':' ',
 			action->name);

arch/alpha/kernel/irq_alpha.c

@@ -228,7 +228,7 @@ struct irqaction timer_irqaction = {
 };
 
 static struct irq_chip rtc_irq_type = {
-	.typename	= "RTC",
+	.name		= "RTC",
 	.startup	= rtc_startup,
 	.shutdown	= rtc_enable_disable,
 	.enable		= rtc_enable_disable,

arch/alpha/kernel/irq_i8259.c

@@ -84,7 +84,7 @@ i8259a_end_irq(unsigned int irq)
 }
 
 struct irq_chip i8259a_irq_type = {
-	.typename	= "XT-PIC",
+	.name		= "XT-PIC",
 	.startup	= i8259a_startup_irq,
 	.shutdown	= i8259a_disable_irq,
 	.enable		= i8259a_enable_irq,

arch/alpha/kernel/irq_pyxis.c

@@ -71,7 +71,7 @@ pyxis_mask_and_ack_irq(unsigned int irq)
 }
 
 static struct irq_chip pyxis_irq_type = {
-	.typename	= "PYXIS",
+	.name		= "PYXIS",
 	.startup	= pyxis_startup_irq,
 	.shutdown	= pyxis_disable_irq,
 	.enable		= pyxis_enable_irq,

arch/alpha/kernel/irq_srm.c

@@ -49,7 +49,7 @@ srm_end_irq(unsigned int irq)
 
 /* Handle interrupts from the SRM, assuming no additional weirdness.  */
 static struct irq_chip srm_irq_type = {
-	.typename	= "SRM",
+	.name		= "SRM",
 	.startup	= srm_startup_irq,
 	.shutdown	= srm_disable_irq,
 	.enable		= srm_enable_irq,

arch/alpha/kernel/pci_impl.h

@@ -198,7 +198,7 @@ extern unsigned long size_for_memory(unsigned long max);
 
 extern int iommu_reserve(struct pci_iommu_arena *, long, long);
 extern int iommu_release(struct pci_iommu_arena *, long, long);
-extern int iommu_bind(struct pci_iommu_arena *, long, long, unsigned long *);
+extern int iommu_bind(struct pci_iommu_arena *, long, long, struct page **);
 extern int iommu_unbind(struct pci_iommu_arena *, long, long);
 
 

arch/alpha/kernel/pci_iommu.c

@@ -876,7 +876,7 @@ iommu_release(struct pci_iommu_arena *arena, long pg_start, long pg_count)
 
 int
 iommu_bind(struct pci_iommu_arena *arena, long pg_start, long pg_count, 
-	   unsigned long *physaddrs)
+	   struct page **pages)
 {
 	unsigned long flags;
 	unsigned long *ptes;
@@ -896,7 +896,7 @@ iommu_bind(struct pci_iommu_arena *arena, long pg_start, long pg_count,
 	}
 		
 	for(i = 0, j = pg_start; i < pg_count; i++, j++)
-		ptes[j] = mk_iommu_pte(physaddrs[i]);
+		ptes[j] = mk_iommu_pte(page_to_phys(pages[i]));
 
 	spin_unlock_irqrestore(&arena->lock, flags);
 

arch/alpha/kernel/process.c

@@ -19,7 +19,6 @@
 #include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/user.h>
-#include <linux/utsname.h>
 #include <linux/time.h>
 #include <linux/major.h>
 #include <linux/stat.h>

arch/alpha/kernel/smp.c

@@ -548,16 +548,16 @@ setup_profiling_timer(unsigned int multiplier)
 
 
 static void
-send_ipi_message(cpumask_t to_whom, enum ipi_message_type operation)
+send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
 {
 	int i;
 
 	mb();
-	for_each_cpu_mask(i, to_whom)
+	for_each_cpu(i, to_whom)
 		set_bit(operation, &ipi_data[i].bits);
 
 	mb();
-	for_each_cpu_mask(i, to_whom)
+	for_each_cpu(i, to_whom)
 		wripir(i);
 }
 
@@ -624,7 +624,7 @@ smp_send_reschedule(int cpu)
 		printk(KERN_WARNING
 		       "smp_send_reschedule: Sending IPI to self.\n");
 #endif
-	send_ipi_message(cpumask_of_cpu(cpu), IPI_RESCHEDULE);
+	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
 void
@@ -636,17 +636,17 @@ smp_send_stop(void)
 	if (hard_smp_processor_id() != boot_cpu_id)
 		printk(KERN_WARNING "smp_send_stop: Not on boot cpu.\n");
 #endif
-	send_ipi_message(to_whom, IPI_CPU_STOP);
+	send_ipi_message(&to_whom, IPI_CPU_STOP);
 }
 
-void arch_send_call_function_ipi(cpumask_t mask)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	send_ipi_message(mask, IPI_CALL_FUNC);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_ipi_message(cpumask_of_cpu(cpu), IPI_CALL_FUNC_SINGLE);
+	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
 static void

arch/alpha/kernel/sys_alcor.c

@@ -90,7 +90,7 @@ alcor_end_irq(unsigned int irq)
 }
 
 static struct irq_chip alcor_irq_type = {
-	.typename	= "ALCOR",
+	.name		= "ALCOR",
 	.startup	= alcor_startup_irq,
 	.shutdown	= alcor_disable_irq,
 	.enable		= alcor_enable_irq,

arch/alpha/kernel/sys_cabriolet.c

@@ -72,7 +72,7 @@ cabriolet_end_irq(unsigned int irq)
 }
 
 static struct irq_chip cabriolet_irq_type = {
-	.typename	= "CABRIOLET",
+	.name		= "CABRIOLET",
 	.startup	= cabriolet_startup_irq,
 	.shutdown	= cabriolet_disable_irq,
 	.enable		= cabriolet_enable_irq,

arch/alpha/kernel/sys_dp264.c

@@ -199,7 +199,7 @@ clipper_set_affinity(unsigned int irq, const struct cpumask *affinity)
 }
 
 static struct irq_chip dp264_irq_type = {
-	.typename	= "DP264",
+	.name		= "DP264",
 	.startup	= dp264_startup_irq,
 	.shutdown	= dp264_disable_irq,
 	.enable		= dp264_enable_irq,
@@ -210,7 +210,7 @@ static struct irq_chip dp264_irq_type = {
 };
 
 static struct irq_chip clipper_irq_type = {
-	.typename	= "CLIPPER",
+	.name		= "CLIPPER",
 	.startup	= clipper_startup_irq,
 	.shutdown	= clipper_disable_irq,
 	.enable		= clipper_enable_irq,

arch/alpha/kernel/sys_eb64p.c

@@ -70,7 +70,7 @@ eb64p_end_irq(unsigned int irq)
 }
 
 static struct irq_chip eb64p_irq_type = {
-	.typename	= "EB64P",
+	.name		= "EB64P",
 	.startup	= eb64p_startup_irq,
 	.shutdown	= eb64p_disable_irq,
 	.enable		= eb64p_enable_irq,

arch/alpha/kernel/sys_eiger.c

@@ -81,7 +81,7 @@ eiger_end_irq(unsigned int irq)
 }
 
 static struct irq_chip eiger_irq_type = {
-	.typename	= "EIGER",
+	.name		= "EIGER",
 	.startup	= eiger_startup_irq,
 	.shutdown	= eiger_disable_irq,
 	.enable		= eiger_enable_irq,

arch/alpha/kernel/sys_jensen.c

@@ -119,7 +119,7 @@ jensen_local_end(unsigned int irq)
 }
 
 static struct irq_chip jensen_local_irq_type = {
-	.typename	= "LOCAL",
+	.name		= "LOCAL",
 	.startup	= jensen_local_startup,
 	.shutdown	= jensen_local_shutdown,
 	.enable		= jensen_local_enable,

arch/alpha/kernel/sys_marvel.c

@@ -170,7 +170,7 @@ marvel_irq_noop_return(unsigned int irq)
 }
 
 static struct irq_chip marvel_legacy_irq_type = {
-	.typename	= "LEGACY",
+	.name		= "LEGACY",
 	.startup	= marvel_irq_noop_return,
 	.shutdown	= marvel_irq_noop,
 	.enable		= marvel_irq_noop,
@@ -180,7 +180,7 @@ static struct irq_chip marvel_legacy_irq_type = {
 };
 
 static struct irq_chip io7_lsi_irq_type = {
-	.typename	= "LSI",
+	.name		= "LSI",
 	.startup	= io7_startup_irq,
 	.shutdown	= io7_disable_irq,
 	.enable		= io7_enable_irq,
@@ -190,7 +190,7 @@ static struct irq_chip io7_lsi_irq_type = {
 };
 
 static struct irq_chip io7_msi_irq_type = {
-	.typename	= "MSI",
+	.name		= "MSI",
 	.startup	= io7_startup_irq,
 	.shutdown	= io7_disable_irq,
 	.enable		= io7_enable_irq,

arch/alpha/kernel/sys_mikasa.c

@@ -69,7 +69,7 @@ mikasa_end_irq(unsigned int irq)
 }
 
 static struct irq_chip mikasa_irq_type = {
-	.typename	= "MIKASA",
+	.name		= "MIKASA",
 	.startup	= mikasa_startup_irq,
 	.shutdown	= mikasa_disable_irq,
 	.enable		= mikasa_enable_irq,

arch/alpha/kernel/sys_noritake.c

@@ -74,7 +74,7 @@ noritake_end_irq(unsigned int irq)
 }
 
 static struct irq_chip noritake_irq_type = {
-	.typename	= "NORITAKE",
+	.name		= "NORITAKE",
 	.startup	= noritake_startup_irq,
 	.shutdown	= noritake_disable_irq,
 	.enable		= noritake_enable_irq,

arch/alpha/kernel/sys_rawhide.c

@@ -136,7 +136,7 @@ rawhide_end_irq(unsigned int irq)
 }
 
 static struct irq_chip rawhide_irq_type = {
-	.typename	= "RAWHIDE",
+	.name		= "RAWHIDE",
 	.startup	= rawhide_startup_irq,
 	.shutdown	= rawhide_disable_irq,
 	.enable		= rawhide_enable_irq,

arch/alpha/kernel/sys_ruffian.c

@@ -66,7 +66,7 @@ ruffian_init_irq(void)
 	common_init_isa_dma();
 }
 
-#define RUFFIAN_LATCH	((PIT_TICK_RATE + HZ / 2) / HZ)
+#define RUFFIAN_LATCH	DIV_ROUND_CLOSEST(PIT_TICK_RATE, HZ)
 
 static void __init
 ruffian_init_rtc(void)

arch/alpha/kernel/sys_rx164.c

@@ -73,7 +73,7 @@ rx164_end_irq(unsigned int irq)
 }
 
 static struct irq_chip rx164_irq_type = {
-	.typename	= "RX164",
+	.name		= "RX164",
 	.startup	= rx164_startup_irq,
 	.shutdown	= rx164_disable_irq,
 	.enable		= rx164_enable_irq,

arch/alpha/kernel/sys_sable.c

@@ -502,7 +502,7 @@ sable_lynx_mask_and_ack_irq(unsigned int irq)
 }
 
 static struct irq_chip sable_lynx_irq_type = {
-	.typename	= "SABLE/LYNX",
+	.name		= "SABLE/LYNX",
 	.startup	= sable_lynx_startup_irq,
 	.shutdown	= sable_lynx_disable_irq,
 	.enable		= sable_lynx_enable_irq,

arch/alpha/kernel/sys_takara.c

@@ -75,7 +75,7 @@ takara_end_irq(unsigned int irq)
 }
 
 static struct irq_chip takara_irq_type = {
-	.typename	= "TAKARA",
+	.name		= "TAKARA",
 	.startup	= takara_startup_irq,
 	.shutdown	= takara_disable_irq,
 	.enable		= takara_enable_irq,