Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless

Documentation/ABI/removed/o2cb

@@ -1,6 +1,6 @@
 What:		/sys/o2cb symlink
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	ocfs2-devel@oss.oracle.com
 Description:	This is a symlink: /sys/o2cb to /sys/fs/o2cb. The symlink is
 		removed when new versions of ocfs2-tools which know to look

Documentation/ABI/removed/raw1394

@@ -5,7 +5,7 @@ Description:
 	/dev/raw1394 was a character device file that allowed low-level
 	access to FireWire buses.  Its major drawbacks were its inability
 	to implement sensible device security policies, and its low level
-	of abstraction that required userspace clients do duplicate much
+	of abstraction that required userspace clients to duplicate much
 	of the kernel's ieee1394 core functionality.
 	Replaced by /dev/fw*, i.e. the <linux/firewire-cdev.h> ABI of
 	firewire-core.

Documentation/ABI/testing/evm

@@ -0,0 +1,23 @@
+What:		security/evm
+Date:		March 2011
+Contact:	Mimi Zohar <zohar@us.ibm.com>
+Description:
+		EVM protects a file's security extended attributes(xattrs)
+		against integrity attacks. The initial method maintains an
+		HMAC-sha1 value across the extended attributes, storing the
+		value as the extended attribute 'security.evm'.
+
+		EVM depends on the Kernel Key Retention System to provide it
+		with a trusted/encrypted key for the HMAC-sha1 operation.
+		The key is loaded onto the root's keyring using keyctl.  Until
+		EVM receives notification that the key has been successfully
+		loaded onto the keyring (echo 1 > <securityfs>/evm), EVM
+		can not create or validate the 'security.evm' xattr, but
+		returns INTEGRITY_UNKNOWN.  Loading the key and signaling EVM
+		should be done as early as possible.  Normally this is done
+		in the initramfs, which has already been measured as part
+		of the trusted boot.  For more information on creating and
+		loading existing trusted/encrypted keys, refer to:
+		Documentation/keys-trusted-encrypted.txt.  (A sample dracut
+		patch, which loads the trusted/encrypted key and enables
+		EVM, is available from http://linux-ima.sourceforge.net/#EVM.)

Documentation/ABI/testing/sysfs-bus-bcma

@@ -1,6 +1,6 @@
 What:		/sys/bus/bcma/devices/.../manuf
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	Rafał Miłecki <zajec5@gmail.com>
 Description:
 		Each BCMA core has it's manufacturer id. See
@@ -8,7 +8,7 @@ Description:
 
 What:		/sys/bus/bcma/devices/.../id
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	Rafał Miłecki <zajec5@gmail.com>
 Description:
 		There are a few types of BCMA cores, they can be identified by
@@ -16,7 +16,7 @@ Description:
 
 What:		/sys/bus/bcma/devices/.../rev
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	Rafał Miłecki <zajec5@gmail.com>
 Description:
 		BCMA cores of the same type can still slightly differ depending
@@ -24,7 +24,7 @@ Description:
 
 What:		/sys/bus/bcma/devices/.../class
 Date:		May 2011
-KernelVersion:	2.6.40
+KernelVersion:	3.0
 Contact:	Rafał Miłecki <zajec5@gmail.com>
 Description:
 		Each BCMA core is identified by few fields, including class it

Documentation/ABI/testing/sysfs-bus-pci-drivers-ehci_hcd

@@ -0,0 +1,46 @@
+What:		/sys/bus/pci/drivers/ehci_hcd/.../companion
+		/sys/bus/usb/devices/usbN/../companion
+Date:		January 2007
+KernelVersion:	2.6.21
+Contact:	Alan Stern <stern@rowland.harvard.edu>
+Description:
+		PCI-based EHCI USB controllers (i.e., high-speed USB-2.0
+		controllers) are often implemented along with a set of
+		"companion" full/low-speed USB-1.1 controllers.  When a
+		high-speed device is plugged in, the connection is routed
+		to the EHCI controller; when a full- or low-speed device
+		is plugged in, the connection is routed to the companion
+		controller.
+
+		Sometimes you want to force a high-speed device to connect
+		at full speed, which can be accomplished by forcing the
+		connection to be routed to the companion controller.
+		That's what this file does.  Writing a port number to the
+		file causes connections on that port to be routed to the
+		companion controller, and writing the negative of a port
+		number returns the port to normal operation.
+
+		For example: To force the high-speed device attached to
+		port 4 on bus 2 to run at full speed:
+
+			echo 4 >/sys/bus/usb/devices/usb2/../companion
+
+		To return the port to high-speed operation:
+
+			echo -4 >/sys/bus/usb/devices/usb2/../companion
+
+		Reading the file gives the list of ports currently forced
+		to the companion controller.
+
+		Note: Some EHCI controllers do not have companions; they
+		may contain an internal "transaction translator" or they
+		may be attached directly to a "rate-matching hub".  This
+		mechanism will not work with such controllers.  Also, it
+		cannot be used to force a port on a high-speed hub to
+		connect at full speed.
+
+		Note: When this file was first added, it appeared in a
+		different sysfs directory.  The location given above is
+		correct for 2.6.35 (and probably several earlier kernel
+		versions as well).
+

Documentation/ABI/testing/sysfs-bus-usb

@@ -142,3 +142,18 @@ Description:
 		such devices.
 Users:
 		usb_modeswitch
+
+What:		/sys/bus/usb/devices/.../power/usb2_hardware_lpm
+Date:		September 2011
+Contact:	Andiry Xu <andiry.xu@amd.com>
+Description:
+		If CONFIG_USB_SUSPEND is set and a USB 2.0 lpm-capable device
+		is plugged in to a xHCI host which support link PM, it will
+		perform a LPM test; if the test is passed and host supports
+		USB2 hardware LPM (xHCI 1.0 feature), USB2 hardware LPM will
+		be enabled for the device and the USB device directory will
+		contain a file named power/usb2_hardware_lpm.  The file holds
+		a string value (enable or disable) indicating whether or not
+		USB2 hardware LPM is enabled for the device. Developer can
+		write y/Y/1 or n/N/0 to the file to enable/disable the
+		feature.

Documentation/ABI/testing/sysfs-class-backlight-driver-adp8870

@@ -4,8 +4,8 @@ What:		/sys/class/backlight/<backlight>/l2_bright_max
 What:		/sys/class/backlight/<backlight>/l3_office_max
 What:		/sys/class/backlight/<backlight>/l4_indoor_max
 What:		/sys/class/backlight/<backlight>/l5_dark_max
-Date:		Mai 2011
-KernelVersion:	2.6.40
+Date:		May 2011
+KernelVersion:	3.0
 Contact:	device-drivers-devel@blackfin.uclinux.org
 Description:
 		Control the maximum brightness for <ambient light zone>
@@ -18,8 +18,8 @@ What:		/sys/class/backlight/<backlight>/l2_bright_dim
 What:		/sys/class/backlight/<backlight>/l3_office_dim
 What:		/sys/class/backlight/<backlight>/l4_indoor_dim
 What:		/sys/class/backlight/<backlight>/l5_dark_dim
-Date:		Mai 2011
-KernelVersion:	2.6.40
+Date:		May 2011
+KernelVersion:	3.0
 Contact:	device-drivers-devel@blackfin.uclinux.org
 Description:
 		Control the dim brightness for <ambient light zone>
@@ -29,8 +29,8 @@ Description:
 		this <ambient light zone>.
 
 What:		/sys/class/backlight/<backlight>/ambient_light_level
-Date:		Mai 2011
-KernelVersion:	2.6.40
+Date:		May 2011
+KernelVersion:	3.0
 Contact:	device-drivers-devel@blackfin.uclinux.org
 Description:
 		Get conversion value of the light sensor.
@@ -39,8 +39,8 @@ Description:
 		8000 (max ambient brightness)
 
 What:		/sys/class/backlight/<backlight>/ambient_light_zone
-Date:		Mai 2011
-KernelVersion:	2.6.40
+Date:		May 2011
+KernelVersion:	3.0
 Contact:	device-drivers-devel@blackfin.uclinux.org
 Description:
 		Get/Set current ambient light zone. Reading returns

Documentation/ABI/testing/sysfs-class-devfreq

@@ -0,0 +1,52 @@
+What:		/sys/class/devfreq/.../
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		Provide a place in sysfs for the devfreq objects.
+		This allows accessing various devfreq specific variables.
+		The name of devfreq object denoted as ... is same as the
+		name of device using devfreq.
+
+What:		/sys/class/devfreq/.../governor
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../governor shows the name of the
+		governor used by the corresponding devfreq object.
+
+What:		/sys/class/devfreq/.../cur_freq
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../cur_freq shows the current
+		frequency of the corresponding devfreq object.
+
+What:		/sys/class/devfreq/.../central_polling
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../central_polling shows whether
+		the devfreq ojbect is using devfreq-provided central
+		polling mechanism or not.
+
+What:		/sys/class/devfreq/.../polling_interval
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../polling_interval shows and sets
+		the requested polling interval of the corresponding devfreq
+		object. The values are represented in ms. If the value is
+		less than 1 jiffy, it is considered to be 0, which means
+		no polling. This value is meaningless if the governor is
+		not polling; thus. If the governor is not using
+		devfreq-provided central polling
+		(/sys/class/devfreq/.../central_polling is 0), this value
+		may be useless.
+
+What:		/sys/class/devfreq/.../userspace/set_freq
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../userspace/set_freq shows and
+		sets the requested frequency for the devfreq object if
+		userspace governor is in effect.

Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff

@@ -0,0 +1,7 @@
+What:		/sys/module/hid_logitech/drivers/hid:logitech/<dev>/range.
+Date:		July 2011
+KernelVersion:	3.2
+Contact:	Michal Malý <madcatxster@gmail.com>
+Description:	Display minimum, maximum and current range of the steering
+		wheel. Writing a value within min and max boundaries sets the
+		range of the wheel.

Documentation/DocBook/uio-howto.tmpl

@@ -529,7 +529,7 @@ memory (e.g. allocated with <function>kmalloc()</function>). There's also
 </para></listitem>
 
 <listitem><para>
-<varname>unsigned long addr</varname>: Required if the mapping is used.
+<varname>phys_addr_t addr</varname>: Required if the mapping is used.
 Fill in the address of your memory block. This address is the one that
 appears in sysfs.
 </para></listitem>

Documentation/PCI/pci.txt

@@ -314,7 +314,7 @@ from the PCI device config space. Use the values in the pci_dev structure
 as the PCI "bus address" might have been remapped to a "host physical"
 address by the arch/chip-set specific kernel support.
 
-See Documentation/IO-mapping.txt for how to access device registers
+See Documentation/io-mapping.txt for how to access device registers
 or device memory.
 
 The device driver needs to call pci_request_region() to verify

Documentation/RCU/NMI-RCU.txt

@@ -95,7 +95,7 @@ not to return until all ongoing NMI handlers exit.  It is therefore safe
 to free up the handler's data as soon as synchronize_sched() returns.
 
 Important note: for this to work, the architecture in question must
-invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.
+invoke nmi_enter() and nmi_exit() on NMI entry and exit, respectively.
 
 
 Answer to Quick Quiz

Documentation/RCU/lockdep-splat.txt

@@ -0,0 +1,110 @@
+Lockdep-RCU was added to the Linux kernel in early 2010
+(http://lwn.net/Articles/371986/).  This facility checks for some common
+misuses of the RCU API, most notably using one of the rcu_dereference()
+family to access an RCU-protected pointer without the proper protection.
+When such misuse is detected, an lockdep-RCU splat is emitted.
+
+The usual cause of a lockdep-RCU slat is someone accessing an
+RCU-protected data structure without either (1) being in the right kind of
+RCU read-side critical section or (2) holding the right update-side lock.
+This problem can therefore be serious: it might result in random memory
+overwriting or worse.  There can of course be false positives, this
+being the real world and all that.
+
+So let's look at an example RCU lockdep splat from 3.0-rc5, one that
+has long since been fixed:
+
+===============================
+[ INFO: suspicious RCU usage. ]
+-------------------------------
+block/cfq-iosched.c:2776 suspicious rcu_dereference_protected() usage!
+
+other info that might help us debug this:
+
+
+rcu_scheduler_active = 1, debug_locks = 0
+3 locks held by scsi_scan_6/1552:
+ #0:  (&shost->scan_mutex){+.+.+.}, at: [<ffffffff8145efca>]
+scsi_scan_host_selected+0x5a/0x150
+ #1:  (&eq->sysfs_lock){+.+...}, at: [<ffffffff812a5032>]
+elevator_exit+0x22/0x60
+ #2:  (&(&q->__queue_lock)->rlock){-.-...}, at: [<ffffffff812b6233>]
+cfq_exit_queue+0x43/0x190
+
+stack backtrace:
+Pid: 1552, comm: scsi_scan_6 Not tainted 3.0.0-rc5 #17
+Call Trace:
+ [<ffffffff810abb9b>] lockdep_rcu_dereference+0xbb/0xc0
+ [<ffffffff812b6139>] __cfq_exit_single_io_context+0xe9/0x120
+ [<ffffffff812b626c>] cfq_exit_queue+0x7c/0x190
+ [<ffffffff812a5046>] elevator_exit+0x36/0x60
+ [<ffffffff812a802a>] blk_cleanup_queue+0x4a/0x60
+ [<ffffffff8145cc09>] scsi_free_queue+0x9/0x10
+ [<ffffffff81460944>] __scsi_remove_device+0x84/0xd0
+ [<ffffffff8145dca3>] scsi_probe_and_add_lun+0x353/0xb10
+ [<ffffffff817da069>] ? error_exit+0x29/0xb0
+ [<ffffffff817d98ed>] ? _raw_spin_unlock_irqrestore+0x3d/0x80
+ [<ffffffff8145e722>] __scsi_scan_target+0x112/0x680
+ [<ffffffff812c690d>] ? trace_hardirqs_off_thunk+0x3a/0x3c
+ [<ffffffff817da069>] ? error_exit+0x29/0xb0
+ [<ffffffff812bcc60>] ? kobject_del+0x40/0x40
+ [<ffffffff8145ed16>] scsi_scan_channel+0x86/0xb0
+ [<ffffffff8145f0b0>] scsi_scan_host_selected+0x140/0x150
+ [<ffffffff8145f149>] do_scsi_scan_host+0x89/0x90
+ [<ffffffff8145f170>] do_scan_async+0x20/0x160
+ [<ffffffff8145f150>] ? do_scsi_scan_host+0x90/0x90
+ [<ffffffff810975b6>] kthread+0xa6/0xb0
+ [<ffffffff817db154>] kernel_thread_helper+0x4/0x10
+ [<ffffffff81066430>] ? finish_task_switch+0x80/0x110
+ [<ffffffff817d9c04>] ? retint_restore_args+0xe/0xe
+ [<ffffffff81097510>] ? __init_kthread_worker+0x70/0x70
+ [<ffffffff817db150>] ? gs_change+0xb/0xb
+
+Line 2776 of block/cfq-iosched.c in v3.0-rc5 is as follows:
+
+	if (rcu_dereference(ioc->ioc_data) == cic) {
+
+This form says that it must be in a plain vanilla RCU read-side critical
+section, but the "other info" list above shows that this is not the
+case.  Instead, we hold three locks, one of which might be RCU related.
+And maybe that lock really does protect this reference.  If so, the fix
+is to inform RCU, perhaps by changing __cfq_exit_single_io_context() to
+take the struct request_queue "q" from cfq_exit_queue() as an argument,
+which would permit us to invoke rcu_dereference_protected as follows:
+
+	if (rcu_dereference_protected(ioc->ioc_data,
+				      lockdep_is_held(&q->queue_lock)) == cic) {
+
+With this change, there would be no lockdep-RCU splat emitted if this
+code was invoked either from within an RCU read-side critical section
+or with the ->queue_lock held.  In particular, this would have suppressed
+the above lockdep-RCU splat because ->queue_lock is held (see #2 in the
+list above).
+
+On the other hand, perhaps we really do need an RCU read-side critical
+section.  In this case, the critical section must span the use of the
+return value from rcu_dereference(), or at least until there is some
+reference count incremented or some such.  One way to handle this is to
+add rcu_read_lock() and rcu_read_unlock() as follows:
+
+	rcu_read_lock();
+	if (rcu_dereference(ioc->ioc_data) == cic) {
+		spin_lock(&ioc->lock);
+		rcu_assign_pointer(ioc->ioc_data, NULL);
+		spin_unlock(&ioc->lock);
+	}
+	rcu_read_unlock();
+
+With this change, the rcu_dereference() is always within an RCU
+read-side critical section, which again would have suppressed the
+above lockdep-RCU splat.
+
+But in this particular case, we don't actually deference the pointer
+returned from rcu_dereference().  Instead, that pointer is just compared
+to the cic pointer, which means that the rcu_dereference() can be replaced
+by rcu_access_pointer() as follows:
+
+	if (rcu_access_pointer(ioc->ioc_data) == cic) {
+
+Because it is legal to invoke rcu_access_pointer() without protection,
+this change would also suppress the above lockdep-RCU splat.

Documentation/RCU/lockdep.txt

@@ -32,9 +32,27 @@ checking of rcu_dereference() primitives:
 	srcu_dereference(p, sp):
 		Check for SRCU read-side critical section.
 	rcu_dereference_check(p, c):
-		Use explicit check expression "c".  This is useful in
-		code that is invoked by both readers and updaters.
-	rcu_dereference_raw(p)
+		Use explicit check expression "c" along with
+		rcu_read_lock_held().  This is useful in code that is
+		invoked by both RCU readers and updaters.
+	rcu_dereference_bh_check(p, c):
+		Use explicit check expression "c" along with
+		rcu_read_lock_bh_held().  This is useful in code that
+		is invoked by both RCU-bh readers and updaters.
+	rcu_dereference_sched_check(p, c):
+		Use explicit check expression "c" along with
+		rcu_read_lock_sched_held().  This is useful in code that
+		is invoked by both RCU-sched readers and updaters.
+	srcu_dereference_check(p, c):
+		Use explicit check expression "c" along with
+		srcu_read_lock_held()().  This is useful in code that
+		is invoked by both SRCU readers and updaters.
+	rcu_dereference_index_check(p, c):
+		Use explicit check expression "c", but the caller
+		must supply one of the rcu_read_lock_held() functions.
+		This is useful in code that uses RCU-protected arrays
+		that is invoked by both RCU readers and updaters.
+	rcu_dereference_raw(p):
 		Don't check.  (Use sparingly, if at all.)
 	rcu_dereference_protected(p, c):
 		Use explicit check expression "c", and omit all barriers
@@ -48,13 +66,11 @@ checking of rcu_dereference() primitives:
 		value of the pointer itself, for example, against NULL.
 
 The rcu_dereference_check() check expression can be any boolean
-expression, but would normally include one of the rcu_read_lock_held()
-family of functions and a lockdep expression.  However, any boolean
-expression can be used.  For a moderately ornate example, consider
-the following:
+expression, but would normally include a lockdep expression.  However,
+any boolean expression can be used.  For a moderately ornate example,
+consider the following:
 
 	file = rcu_dereference_check(fdt->fd[fd],
-				     rcu_read_lock_held() ||
 				     lockdep_is_held(&files->file_lock) ||
 				     atomic_read(&files->count) == 1);
 
@@ -62,7 +78,7 @@ This expression picks up the pointer "fdt->fd[fd]" in an RCU-safe manner,
 and, if CONFIG_PROVE_RCU is configured, verifies that this expression
 is used in:
 
-1.	An RCU read-side critical section, or
+1.	An RCU read-side critical section (implicit), or
 2.	with files->file_lock held, or
 3.	on an unshared files_struct.
 

Documentation/RCU/torture.txt

@@ -42,7 +42,7 @@ fqs_holdoff	Holdoff time (in microseconds) between consecutive calls
 fqs_stutter	Wait time (in seconds) between consecutive bursts
 		of calls to force_quiescent_state().
 
-irqreaders	Says to invoke RCU readers from irq level.  This is currently
+irqreader	Says to invoke RCU readers from irq level.  This is currently
 		done via timers.  Defaults to "1" for variants of RCU that
 		permit this.  (Or, more accurately, variants of RCU that do
 		-not- permit this know to ignore this variable.)
@@ -79,19 +79,68 @@ stutter		The length of time to run the test before pausing for this
 		Specifying "stutter=0" causes the test to run continuously
 		without pausing, which is the old default behavior.
 
+test_boost	Whether or not to test the ability of RCU to do priority
+		boosting.  Defaults to "test_boost=1", which performs
+		RCU priority-inversion testing only if the selected
+		RCU implementation supports priority boosting.  Specifying
+		"test_boost=0" never performs RCU priority-inversion
+		testing.  Specifying "test_boost=2" performs RCU
+		priority-inversion testing even if the selected RCU
+		implementation does not support RCU priority boosting,
+		which can be used to test rcutorture's ability to
+		carry out RCU priority-inversion testing.
+
+test_boost_interval
+		The number of seconds in an RCU priority-inversion test
+		cycle.	Defaults to "test_boost_interval=7".  It is
+		usually wise for this value to be relatively prime to
+		the value selected for "stutter".
+
+test_boost_duration
+		The number of seconds to do RCU priority-inversion testing
+		within any given "test_boost_interval".  Defaults to
+		"test_boost_duration=4".
+
 test_no_idle_hz	Whether or not to test the ability of RCU to operate in
 		a kernel that disables the scheduling-clock interrupt to
 		idle CPUs.  Boolean parameter, "1" to test, "0" otherwise.
 		Defaults to omitting this test.
 
-torture_type	The type of RCU to test: "rcu" for the rcu_read_lock() API,
-		"rcu_sync" for rcu_read_lock() with synchronous reclamation,
-		"rcu_bh" for the rcu_read_lock_bh() API, "rcu_bh_sync" for
-		rcu_read_lock_bh() with synchronous reclamation, "srcu" for
-		the "srcu_read_lock()" API, "sched" for the use of
-		preempt_disable() together with synchronize_sched(),
-		and "sched_expedited" for the use of preempt_disable()
-		with synchronize_sched_expedited().
+torture_type	The type of RCU to test, with string values as follows:
+
+		"rcu":  rcu_read_lock(), rcu_read_unlock() and call_rcu().
+
+		"rcu_sync":  rcu_read_lock(), rcu_read_unlock(), and
+			synchronize_rcu().
+
+		"rcu_expedited": rcu_read_lock(), rcu_read_unlock(), and
+			synchronize_rcu_expedited().
+
+		"rcu_bh": rcu_read_lock_bh(), rcu_read_unlock_bh(), and
+			call_rcu_bh().
+
+		"rcu_bh_sync": rcu_read_lock_bh(), rcu_read_unlock_bh(),
+			and synchronize_rcu_bh().
+
+		"rcu_bh_expedited": rcu_read_lock_bh(), rcu_read_unlock_bh(),
+			and synchronize_rcu_bh_expedited().
+
+		"srcu": srcu_read_lock(), srcu_read_unlock() and
+			synchronize_srcu().
+
+		"srcu_expedited": srcu_read_lock(), srcu_read_unlock() and
+			synchronize_srcu_expedited().
+
+		"sched": preempt_disable(), preempt_enable(), and
+			call_rcu_sched().
+
+		"sched_sync": preempt_disable(), preempt_enable(), and
+			synchronize_sched().
+
+		"sched_expedited": preempt_disable(), preempt_enable(), and
+			synchronize_sched_expedited().
+
+		Defaults to "rcu".
 
 verbose		Enable debug printk()s.  Default is disabled.
 
@@ -100,12 +149,12 @@ OUTPUT
 
 The statistics output is as follows:
 
-	rcu-torture: --- Start of test: nreaders=16 stat_interval=0 verbose=0
-	rcu-torture: rtc: 0000000000000000 ver: 1916 tfle: 0 rta: 1916 rtaf: 0 rtf: 1915
-	rcu-torture: Reader Pipe:  1466408 9747 0 0 0 0 0 0 0 0 0
-	rcu-torture: Reader Batch:  1464477 11678 0 0 0 0 0 0 0 0
-	rcu-torture: Free-Block Circulation:  1915 1915 1915 1915 1915 1915 1915 1915 1915 1915 0
-	rcu-torture: --- End of test
+	rcu-torture:--- Start of test: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_no_idle_hz=1 shuffle_interval=3 stutter=5 irqreader=1 fqs_duration=0 fqs_holdoff=0 fqs_stutter=3 test_boost=1/0 test_boost_interval=7 test_boost_duration=4
+	rcu-torture: rtc:           (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0 rtbke: 0 rtbre: 0 rtbf: 0 rtb: 0 nt: 3055767
+	rcu-torture: Reader Pipe:  727860534 34213 0 0 0 0 0 0 0 0 0
+	rcu-torture: Reader Batch:  727877838 17003 0 0 0 0 0 0 0 0 0
+	rcu-torture: Free-Block Circulation:  155440 155440 155440 155440 155440 155440 155440 155440 155440 155440 0
+	rcu-torture:--- End of test: SUCCESS: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_no_idle_hz=1 shuffle_interval=3 stutter=5 irqreader=1 fqs_duration=0 fqs_holdoff=0 fqs_stutter=3 test_boost=1/0 test_boost_interval=7 test_boost_duration=4
 
 The command "dmesg | grep torture:" will extract this information on
 most systems.  On more esoteric configurations, it may be necessary to
@@ -113,26 +162,55 @@ use other commands to access the output of the printk()s used by
 the RCU torture test.  The printk()s use KERN_ALERT, so they should
 be evident.  ;-)
 
+The first and last lines show the rcutorture module parameters, and the
+last line shows either "SUCCESS" or "FAILURE", based on rcutorture's
+automatic determination as to whether RCU operated correctly.
+
 The entries are as follows:
 
 o	"rtc": The hexadecimal address of the structure currently visible
 	to readers.
 
-o	"ver": The number of times since boot that the rcutw writer task
+o	"ver": The number of times since boot that the RCU writer task
 	has changed the structure visible to readers.
 
 o	"tfle": If non-zero, indicates that the "torture freelist"
-	containing structure to be placed into the "rtc" area is empty.
+	containing structures to be placed into the "rtc" area is empty.
 	This condition is important, since it can fool you into thinking
 	that RCU is working when it is not.  :-/
 
 o	"rta": Number of structures allocated from the torture freelist.
 
 o	"rtaf": Number of allocations from the torture freelist that have
-	failed due to the list being empty.
+	failed due to the list being empty.  It is not unusual for this
+	to be non-zero, but it is bad for it to be a large fraction of
+	the value indicated by "rta".
 
 o	"rtf": Number of frees into the torture freelist.
 
+o	"rtmbe": A non-zero value indicates that rcutorture believes that
+	rcu_assign_pointer() and rcu_dereference() are not working
+	correctly.  This value should be zero.
+
+o	"rtbke": rcutorture was unable to create the real-time kthreads
+	used to force RCU priority inversion.  This value should be zero.
+
+o	"rtbre": Although rcutorture successfully created the kthreads
+	used to force RCU priority inversion, it was unable to set them
+	to the real-time priority level of 1.  This value should be zero.
+
+o	"rtbf": The number of times that RCU priority boosting failed
+	to resolve RCU priority inversion.
+
+o	"rtb": The number of times that rcutorture attempted to force
+	an RCU priority inversion condition.  If you are testing RCU
+	priority boosting via the "test_boost" module parameter, this
+	value should be non-zero.
+
+o	"nt": The number of times rcutorture ran RCU read-side code from
+	within a timer handler.  This value should be non-zero only
+	if you specified the "irqreader" module parameter.
+
 o	"Reader Pipe": Histogram of "ages" of structures seen by readers.
 	If any entries past the first two are non-zero, RCU is broken.
 	And rcutorture prints the error flag string "!!!" to make sure
@@ -162,26 +240,15 @@ o	"Free-Block Circulation": Shows the number of torture structures
 	somehow gets incremented farther than it should.
 
 Different implementations of RCU can provide implementation-specific
-additional information.  For example, SRCU provides the following:
+additional information.  For example, SRCU provides the following
+additional line:
 
-	srcu-torture: rtc: f8cf46a8 ver: 355 tfle: 0 rta: 356 rtaf: 0 rtf: 346 rtmbe: 0
-	srcu-torture: Reader Pipe:  559738 939 0 0 0 0 0 0 0 0 0
-	srcu-torture: Reader Batch:  560434 243 0 0 0 0 0 0 0 0
-	srcu-torture: Free-Block Circulation:  355 354 353 352 351 350 349 348 347 346 0
 	srcu-torture: per-CPU(idx=1): 0(0,1) 1(0,1) 2(0,0) 3(0,1)
 
-The first four lines are similar to those for RCU.  The last line shows
-the per-CPU counter state.  The numbers in parentheses are the values
-of the "old" and "current" counters for the corresponding CPU.  The
-"idx" value maps the "old" and "current" values to the underlying array,
-and is useful for debugging.
-
-Similarly, sched_expedited RCU provides the following:
-
-	sched_expedited-torture: rtc: d0000000016c1880 ver: 1090796 tfle: 0 rta: 1090796 rtaf: 0 rtf: 1090787 rtmbe: 0 nt: 27713319
-	sched_expedited-torture: Reader Pipe:  12660320201 95875 0 0 0 0 0 0 0 0 0
-	sched_expedited-torture: Reader Batch:  12660424885 0 0 0 0 0 0 0 0 0 0
-	sched_expedited-torture: Free-Block Circulation:  1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0
+This line shows the per-CPU counter state.  The numbers in parentheses are
+the values of the "old" and "current" counters for the corresponding CPU.
+The "idx" value maps the "old" and "current" values to the underlying
+array, and is useful for debugging.
 
 
 USAGE

Documentation/RCU/trace.txt

@@ -33,23 +33,23 @@ rcu/rcuboost:
 The output of "cat rcu/rcudata" looks as follows:
 
 rcu_sched:
-  0 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=545/1/0 df=50 of=0 ri=0 ql=163 qs=NRW. kt=0/W/0 ktl=ebc3 b=10 ci=153737 co=0 ca=0
-  1 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=967/1/0 df=58 of=0 ri=0 ql=634 qs=NRW. kt=0/W/1 ktl=58c b=10 ci=191037 co=0 ca=0
-  2 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=1081/1/0 df=175 of=0 ri=0 ql=74 qs=N.W. kt=0/W/2 ktl=da94 b=10 ci=75991 co=0 ca=0
-  3 c=20942 g=20943 pq=1 pqc=20942 qp=1 dt=1846/0/0 df=404 of=0 ri=0 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=72261 co=0 ca=0
-  4 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=369/1/0 df=83 of=0 ri=0 ql=48 qs=N.W. kt=0/W/4 ktl=e0e7 b=10 ci=128365 co=0 ca=0
-  5 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=381/1/0 df=64 of=0 ri=0 ql=169 qs=NRW. kt=0/W/5 ktl=fb2f b=10 ci=164360 co=0 ca=0
-  6 c=20972 g=20973 pq=1 pqc=20972 qp=0 dt=1037/1/0 df=183 of=0 ri=0 ql=62 qs=N.W. kt=0/W/6 ktl=d2ad b=10 ci=65663 co=0 ca=0
-  7 c=20897 g=20897 pq=1 pqc=20896 qp=0 dt=1572/0/0 df=382 of=0 ri=0 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=75006 co=0 ca=0
+  0 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=545/1/0 df=50 of=0 ri=0 ql=163 qs=NRW. kt=0/W/0 ktl=ebc3 b=10 ci=153737 co=0 ca=0
+  1 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=967/1/0 df=58 of=0 ri=0 ql=634 qs=NRW. kt=0/W/1 ktl=58c b=10 ci=191037 co=0 ca=0
+  2 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=1081/1/0 df=175 of=0 ri=0 ql=74 qs=N.W. kt=0/W/2 ktl=da94 b=10 ci=75991 co=0 ca=0
+  3 c=20942 g=20943 pq=1 pgp=20942 qp=1 dt=1846/0/0 df=404 of=0 ri=0 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=72261 co=0 ca=0
+  4 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=369/1/0 df=83 of=0 ri=0 ql=48 qs=N.W. kt=0/W/4 ktl=e0e7 b=10 ci=128365 co=0 ca=0
+  5 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=381/1/0 df=64 of=0 ri=0 ql=169 qs=NRW. kt=0/W/5 ktl=fb2f b=10 ci=164360 co=0 ca=0
+  6 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=1037/1/0 df=183 of=0 ri=0 ql=62 qs=N.W. kt=0/W/6 ktl=d2ad b=10 ci=65663 co=0 ca=0
+  7 c=20897 g=20897 pq=1 pgp=20896 qp=0 dt=1572/0/0 df=382 of=0 ri=0 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=75006 co=0 ca=0
 rcu_bh:
-  0 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=545/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/0 ktl=ebc3 b=10 ci=0 co=0 ca=0
-  1 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=967/1/0 df=3 of=0 ri=1 ql=0 qs=.... kt=0/W/1 ktl=58c b=10 ci=151 co=0 ca=0
-  2 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=1081/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/2 ktl=da94 b=10 ci=0 co=0 ca=0
-  3 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=1846/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=0 co=0 ca=0
-  4 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=369/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/4 ktl=e0e7 b=10 ci=0 co=0 ca=0
-  5 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=381/1/0 df=4 of=0 ri=1 ql=0 qs=.... kt=0/W/5 ktl=fb2f b=10 ci=0 co=0 ca=0
-  6 c=1480 g=1480 pq=1 pqc=1479 qp=0 dt=1037/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/6 ktl=d2ad b=10 ci=0 co=0 ca=0
-  7 c=1474 g=1474 pq=1 pqc=1473 qp=0 dt=1572/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=0 co=0 ca=0
+  0 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=545/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/0 ktl=ebc3 b=10 ci=0 co=0 ca=0
+  1 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=967/1/0 df=3 of=0 ri=1 ql=0 qs=.... kt=0/W/1 ktl=58c b=10 ci=151 co=0 ca=0
+  2 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1081/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/2 ktl=da94 b=10 ci=0 co=0 ca=0
+  3 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1846/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=0 co=0 ca=0
+  4 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=369/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/4 ktl=e0e7 b=10 ci=0 co=0 ca=0
+  5 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=381/1/0 df=4 of=0 ri=1 ql=0 qs=.... kt=0/W/5 ktl=fb2f b=10 ci=0 co=0 ca=0
+  6 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1037/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/6 ktl=d2ad b=10 ci=0 co=0 ca=0
+  7 c=1474 g=1474 pq=1 pgp=1473 qp=0 dt=1572/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=0 co=0 ca=0
 
 The first section lists the rcu_data structures for rcu_sched, the second
 for rcu_bh.  Note that CONFIG_TREE_PREEMPT_RCU kernels will have an
@@ -84,7 +84,7 @@ o	"pq" indicates that this CPU has passed through a quiescent state
 	CPU has not yet reported that fact, (2) some other CPU has not
 	yet reported for this grace period, or (3) both.
 
-o	"pqc" indicates which grace period the last-observed quiescent
+o	"pgp" indicates which grace period the last-observed quiescent
 	state for this CPU corresponds to.  This is important for handling
 	the race between CPU 0 reporting an extended dynticks-idle
 	quiescent state for CPU 1 and CPU 1 suddenly waking up and
@@ -184,10 +184,14 @@ o	"kt" is the per-CPU kernel-thread state.  The digit preceding
 	The number after the final slash is the CPU that the kthread
 	is actually running on.
 
+	This field is displayed only for CONFIG_RCU_BOOST kernels.
+
 o	"ktl" is the low-order 16 bits (in hexadecimal) of the count of
 	the number of times that this CPU's per-CPU kthread has gone
 	through its loop servicing invoke_rcu_cpu_kthread() requests.
 
+	This field is displayed only for CONFIG_RCU_BOOST kernels.
+
 o	"b" is the batch limit for this CPU.  If more than this number
 	of RCU callbacks is ready to invoke, then the remainder will
 	be deferred.

Documentation/blackfin/bfin-gpio-notes.txt

@@ -1,5 +1,5 @@
 /*
- * File:         Documentation/blackfin/bfin-gpio-note.txt
+ * File:         Documentation/blackfin/bfin-gpio-notes.txt
  * Based on:
  * Author:
  *

Documentation/block/biodoc.txt

@@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
+Note: Please refer to Documentation/DMA-API-HOWTO.txt for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 

Documentation/bus-virt-phys-mapping.txt

@@ -1,6 +1,6 @@
 [ NOTE: The virt_to_bus() and bus_to_virt() functions have been
 	superseded by the functionality provided by the PCI DMA interface
-	(see Documentation/PCI/PCI-DMA-mapping.txt).  They continue
+	(see Documentation/DMA-API-HOWTO.txt).  They continue
 	to be documented below for historical purposes, but new code
 	must not use them. --davidm 00/12/12 ]
 

Documentation/cdrom/packet-writing.txt

@@ -109,7 +109,7 @@ this interface. (see http://tom.ist-im-web.de/download/pktcdvd )
 
 For a description of the sysfs interface look into the file:
 
-  Documentation/ABI/testing/sysfs-block-pktcdvd
+  Documentation/ABI/testing/sysfs-class-pktcdvd
 
 
 Using the pktcdvd debugfs interface

Documentation/cpu-freq/governors.txt

@@ -132,7 +132,7 @@ The sampling rate is limited by the HW transition latency:
 transition_latency * 100
 Or by kernel restrictions:
 If CONFIG_NO_HZ is set, the limit is 10ms fixed.
-If CONFIG_NO_HZ is not set or no_hz=off boot parameter is used, the
+If CONFIG_NO_HZ is not set or nohz=off boot parameter is used, the
 limits depend on the CONFIG_HZ option:
 HZ=1000: min=20000us  (20ms)
 HZ=250:  min=80000us  (80ms)

Documentation/development-process/4.Coding

@@ -278,7 +278,7 @@ enabled, a configurable percentage of memory allocations will be made to
 fail; these failures can be restricted to a specific range of code.
 Running with fault injection enabled allows the programmer to see how the
 code responds when things go badly.  See
-Documentation/fault-injection/fault-injection.text for more information on
+Documentation/fault-injection/fault-injection.txt for more information on
 how to use this facility.
 
 Other kinds of errors can be found with the "sparse" static analysis tool.

Documentation/devicetree/bindings/arm/l2cc.txt

@@ -0,0 +1,44 @@
+* ARM L2 Cache Controller
+
+ARM cores often have a separate level 2 cache controller. There are various
+implementations of the L2 cache controller with compatible programming models.
+The ARM L2 cache representation in the device tree should be done as follows:
+
+Required properties:
+
+- compatible : should be one of:
+	"arm,pl310-cache"
+	"arm,l220-cache"
+	"arm,l210-cache"
+- cache-unified : Specifies the cache is a unified cache.
+- cache-level : Should be set to 2 for a level 2 cache.
+- reg : Physical base address and size of cache controller's memory mapped
+  registers.
+
+Optional properties:
+
+- arm,data-latency : Cycles of latency for Data RAM accesses. Specifies 3 cells of
+  read, write and setup latencies. Minimum valid values are 1. Controllers
+  without setup latency control should use a value of 0.
+- arm,tag-latency : Cycles of latency for Tag RAM accesses. Specifies 3 cells of
+  read, write and setup latencies. Controllers without setup latency control
+  should use 0. Controllers without separate read and write Tag RAM latency
+  values should only use the first cell.
+- arm,dirty-latency : Cycles of latency for Dirty RAMs. This is a single cell.
+- arm,filter-ranges : <start length> Starting address and length of window to
+  filter. Addresses in the filter window are directed to the M1 port. Other
+  addresses will go to the M0 port.
+- interrupts : 1 combined interrupt.
+
+Example:
+
+L2: cache-controller {
+        compatible = "arm,pl310-cache";
+        reg = <0xfff12000 0x1000>;
+        arm,data-latency = <1 1 1>;
+        arm,tag-latency = <2 2 2>;
+        arm,filter-latency = <0x80000000 0x8000000>;
+        cache-unified;
+        cache-level = <2>;
+	interrupts = <45>;
+};

Documentation/devicetree/bindings/gpio/led.txt

@@ -8,7 +8,7 @@ node's name represents the name of the corresponding LED.
 
 LED sub-node properties:
 - gpios :  Should specify the LED's GPIO, see "Specifying GPIO information
-  for devices" in Documentation/powerpc/booting-without-of.txt.  Active
+  for devices" in Documentation/devicetree/booting-without-of.txt.  Active
   low LEDs should be indicated using flags in the GPIO specifier.
 - label :  (optional) The label for this LED.  If omitted, the label is
   taken from the node name (excluding the unit address).

Documentation/devicetree/bindings/serial/rs485.txt

@@ -0,0 +1,31 @@
+* RS485 serial communications
+
+The RTS signal is capable of automatically controlling line direction for
+the built-in half-duplex mode.
+The properties described hereafter shall be given to a half-duplex capable
+UART node.
+
+Required properties:
+- rs485-rts-delay: prop-encoded-array <a b> where:
+  * a is the delay beteween rts signal and beginning of data sent in milliseconds.
+      it corresponds to the delay before sending data.
+  * b is the delay between end of data sent and rts signal in milliseconds
+      it corresponds to the delay after sending data and actual release of the line.
+
+Optional properties:
+- linux,rs485-enabled-at-boot-time: empty property telling to enable the rs485
+  feature at boot time. It can be disabled later with proper ioctl.
+- rs485-rx-during-tx: empty property that enables the receiving of data even
+  whilst sending data.
+
+RS485 example for Atmel USART:
+	usart0: serial@fff8c000 {
+		compatible = "atmel,at91sam9260-usart";
+		reg = <0xfff8c000 0x4000>;
+		interrupts = <7>;
+		atmel,use-dma-rx;
+		atmel,use-dma-tx;
+		linux,rs485-enabled-at-boot-time;
+		rs485-rts-delay = <0 200>;		// in milliseconds
+	};
+

Documentation/devicetree/bindings/tty/serial/atmel-usart.txt

@@ -0,0 +1,27 @@
+* Atmel Universal Synchronous Asynchronous Receiver/Transmitter (USART)
+
+Required properties:
+- compatible: Should be "atmel,<chip>-usart"
+  The compatible <chip> indicated will be the first SoC to support an
+  additional mode or an USART new feature.
+- reg: Should contain registers location and length
+- interrupts: Should contain interrupt
+
+Optional properties:
+- atmel,use-dma-rx: use of PDC or DMA for receiving data
+- atmel,use-dma-tx: use of PDC or DMA for transmitting data
+
+<chip> compatible description:
+- at91rm9200:  legacy USART support
+- at91sam9260: generic USART implementation for SAM9 SoCs
+
+Example:
+
+	usart0: serial@fff8c000 {
+		compatible = "atmel,at91sam9260-usart";
+		reg = <0xfff8c000 0x4000>;
+		interrupts = <7>;
+		atmel,use-dma-rx;
+		atmel,use-dma-tx;
+	};
+

Documentation/devicetree/bindings/tty/serial/snps-dw-apb-uart.txt

@@ -0,0 +1,25 @@
+* Synopsys DesignWare ABP UART
+
+Required properties:
+- compatible : "snps,dw-apb-uart"
+- reg : offset and length of the register set for the device.
+- interrupts : should contain uart interrupt.
+- clock-frequency : the input clock frequency for the UART.
+
+Optional properties:
+- reg-shift : quantity to shift the register offsets by.  If this property is
+  not present then the register offsets are not shifted.
+- reg-io-width : the size (in bytes) of the IO accesses that should be
+  performed on the device.  If this property is not present then single byte
+  accesses are used.
+
+Example:
+
+	uart@80230000 {
+		compatible = "snps,dw-apb-uart";
+		reg = <0x80230000 0x100>;
+		clock-frequency = <3686400>;
+		interrupts = <10>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+	};

Documentation/driver-model/binding.txt

@@ -48,10 +48,6 @@ devclass_add_device is called to enumerate the device within the class
 and actually register it with the class, which happens with the
 class's register_dev callback.
 
-NOTE: The device class structures and core routines to manipulate them
-are not in the mainline kernel, so the discussion is still a bit
-speculative. 
-
 
 Driver
 ~~~~~~

Documentation/driver-model/device.txt

@@ -45,33 +45,52 @@ struct device_attribute {
 			 const char *buf, size_t count);
 };
 
-Attributes of devices can be exported via drivers using a simple
-procfs-like interface. 
+Attributes of devices can be exported by a device driver through sysfs.
 
 Please see Documentation/filesystems/sysfs.txt for more information
 on how sysfs works.
 
+As explained in Documentation/kobject.txt, device attributes must be be
+created before the KOBJ_ADD uevent is generated. The only way to realize
+that is by defining an attribute group.
+
 Attributes are declared using a macro called DEVICE_ATTR:
 
 #define DEVICE_ATTR(name,mode,show,store)
 
 Example:
 
-DEVICE_ATTR(power,0644,show_power,store_power);
+static DEVICE_ATTR(type, 0444, show_type, NULL);
+static DEVICE_ATTR(power, 0644, show_power, store_power);
 
-This declares a structure of type struct device_attribute named
-'dev_attr_power'. This can then be added and removed to the device's
-directory using:
+This declares two structures of type struct device_attribute with respective
+names 'dev_attr_type' and 'dev_attr_power'. These two attributes can be
+organized as follows into a group:
 
-int device_create_file(struct device *device, struct device_attribute * entry);
-void device_remove_file(struct device * dev, struct device_attribute * attr);
+static struct attribute *dev_attrs[] = {
+	&dev_attr_type.attr,
+	&dev_attr_power.attr,
+	NULL,
+};
 
-Example:
+static struct attribute_group dev_attr_group = {
+	.attrs = dev_attrs,
+};
+
+static const struct attribute_group *dev_attr_groups[] = {
+	&dev_attr_group,
+	NULL,
+};
+
+This array of groups can then be associated with a device by setting the
+group pointer in struct device before device_register() is invoked:
 
-device_create_file(dev,&dev_attr_power);
-device_remove_file(dev,&dev_attr_power);
+      dev->groups = dev_attr_groups;
+      device_register(dev);
 
-The file name will be 'power' with a mode of 0644 (-rw-r--r--).
+The device_register() function will use the 'groups' pointer to create the
+device attributes and the device_unregister() function will use this pointer
+to remove the device attributes.
 
 Word of warning:  While the kernel allows device_create_file() and
 device_remove_file() to be called on a device at any time, userspace has
@@ -84,24 +103,4 @@ not know about the new attributes.
 This is important for device driver that need to publish additional
 attributes for a device at driver probe time.  If the device driver simply
 calls device_create_file() on the device structure passed to it, then
-userspace will never be notified of the new attributes.  Instead, it should
-probably use class_create() and class->dev_attrs to set up a list of
-desired attributes in the modules_init function, and then in the .probe()
-hook, and then use device_create() to create a new device as a child
-of the probed device.  The new device will generate a new uevent and
-properly advertise the new attributes to userspace.
-
-For example, if a driver wanted to add the following attributes:
-struct device_attribute mydriver_attribs[] = {
-	__ATTR(port_count, 0444, port_count_show),
-	__ATTR(serial_number, 0444, serial_number_show),
-	NULL
-};
-
-Then in the module init function is would do:
-	mydriver_class = class_create(THIS_MODULE, "my_attrs");
-	mydriver_class.dev_attr = mydriver_attribs;
-
-And assuming 'dev' is the struct device passed into the probe hook, the driver
-probe function would do something like:
-	device_create(&mydriver_class, dev, chrdev, &private_data, "my_name");
+userspace will never be notified of the new attributes.

Documentation/filesystems/9p.txt

@@ -92,7 +92,7 @@ OPTIONS
 
   wfdno=n	the file descriptor for writing with trans=fd
 
-  maxdata=n	the number of bytes to use for 9p packet payload (msize)
+  msize=n	the number of bytes to use for 9p packet payload
 
   port=n	port to connect to on the remote server
 

Documentation/filesystems/caching/object.txt

@@ -127,9 +127,9 @@ fscache_enqueue_object()).
 PROVISION OF CPU TIME
 ---------------------
 
-The work to be done by the various states is given CPU time by the threads of
-the slow work facility (see Documentation/slow-work.txt).  This is used in
-preference to the workqueue facility because:
+The work to be done by the various states was given CPU time by the threads of
+the slow work facility.  This was used in preference to the workqueue facility
+because:
 
  (1) Threads may be completely occupied for very long periods of time by a
      particular work item.  These state actions may be doing sequences of

Documentation/filesystems/locks.txt

@@ -53,11 +53,12 @@ fcntl(), with all the problems that implies.
 1.3 Mandatory Locking As A Mount Option
 ---------------------------------------
 
-Mandatory locking, as described in 'Documentation/filesystems/mandatory.txt'
-was prior to this release a general configuration option that was valid for
-all mounted filesystems.  This had a number of inherent dangers, not the
-least of which was the ability to freeze an NFS server by asking it to read
-a file for which a mandatory lock existed.
+Mandatory locking, as described in
+'Documentation/filesystems/mandatory-locking.txt' was prior to this release a
+general configuration option that was valid for all mounted filesystems.  This
+had a number of inherent dangers, not the least of which was the ability to
+freeze an NFS server by asking it to read a file for which a mandatory lock
+existed.
 
 From this release of the kernel, mandatory locking can be turned on and off
 on a per-filesystem basis, using the mount options 'mand' and 'nomand'.

Documentation/filesystems/nfs/idmapper.txt

@@ -47,7 +47,7 @@ request-key will find the first matching line and corresponding program.  In
 this case, /some/other/program will handle all uid lookups and
 /usr/sbin/nfs.idmap will handle gid, user, and group lookups.
 
-See <file:Documentation/security/keys-request-keys.txt> for more information
+See <file:Documentation/security/keys-request-key.txt> for more information
 about the request-key function.
 
 

Documentation/filesystems/pohmelfs/design_notes.txt

@@ -58,8 +58,9 @@ data transfers.
 POHMELFS clients operate with a working set of servers and are capable of balancing read-only
 operations (like lookups or directory listings) between them according to IO priorities.
 Administrators can add or remove servers from the set at run-time via special commands (described
-in Documentation/pohmelfs/info.txt file). Writes are replicated to all servers, which are connected
-with write permission turned on. IO priority and permissions can be changed in run-time.
+in Documentation/filesystems/pohmelfs/info.txt file). Writes are replicated to all servers, which
+are connected with write permission turned on. IO priority and permissions can be changed in
+run-time.
 
 POHMELFS is capable of full data channel encryption and/or strong crypto hashing.
 One can select any kernel supported cipher, encryption mode, hash type and operation mode

Documentation/filesystems/proc.txt

@@ -1263,7 +1263,7 @@ review the kernel documentation in the directory /usr/src/linux/Documentation.
 This chapter  is  heavily  based  on the documentation included in the pre 2.2
 kernels, and became part of it in version 2.2.1 of the Linux kernel.
 
-Please see: Documentation/sysctls/ directory for descriptions of these
+Please see: Documentation/sysctl/ directory for descriptions of these
 entries.
 
 ------------------------------------------------------------------------------

Documentation/filesystems/sysfs.txt

@@ -4,7 +4,7 @@ sysfs - _The_ filesystem for exporting kernel objects.
 Patrick Mochel	<mochel@osdl.org>
 Mike Murphy <mamurph@cs.clemson.edu>
 
-Revised:    15 July 2010
+Revised:    16 August 2011
 Original:   10 January 2003
 
 
@@ -370,3 +370,11 @@ int driver_create_file(struct device_driver *, const struct driver_attribute *);
 void driver_remove_file(struct device_driver *, const struct driver_attribute *);
 
 
+Documentation
+~~~~~~~~~~~~~
+
+The sysfs directory structure and the attributes in each directory define an
+ABI between the kernel and user space. As for any ABI, it is important that
+this ABI is stable and properly documented. All new sysfs attributes must be
+documented in Documentation/ABI. See also Documentation/ABI/README for more
+information.

Documentation/filesystems/vfs.txt

@@ -1053,9 +1053,6 @@ manipulate dentries:
 	and the dentry is returned. The caller must use dput()
 	to free the dentry when it finishes using it.
 
-For further information on dentry locking, please refer to the document
-Documentation/filesystems/dentry-locking.txt.
-
 Mount Options
 =============
 

Documentation/frv/booting.txt

@@ -180,9 +180,3 @@ separated by spaces:
 
       This tells the kernel what program to run initially. By default this is
       /sbin/init, but /sbin/sash or /bin/sh are common alternatives.
-
-  (*) vdc=...
-
-      This option configures the MB93493 companion chip visual display
-      driver. Please see Documentation/frv/mb93493/vdc.txt for more
-      information.

Documentation/hwmon/ad7314

@@ -0,0 +1,25 @@
+Kernel driver ad7314
+====================
+
+Supported chips:
+   * Analog Devices AD7314
+     Prefix: 'ad7314'
+     Datasheet: Publicly available at Analog Devices website.
+   * Analog Devices ADT7301
+     Prefix: 'adt7301'
+     Datasheet: Publicly available at Analog Devices website.
+   * Analog Devices ADT7302
+     Prefix: 'adt7302'
+     Datasheet: Publicly available at Analog Devices website.
+
+Description
+-----------
+
+Driver supports the above parts.  The ad7314 has a 10 bit
+sensor with 1lsb = 0.25 degrees centigrade. The adt7301 and
+adt7302 have 14 bit sensors with 1lsb = 0.03125 degrees centigrade.
+
+Notes
+-----
+
+Currently power down mode is not supported.

Documentation/hwmon/adm1275

@@ -6,6 +6,10 @@ Supported chips:
     Prefix: 'adm1275'
     Addresses scanned: -
     Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1275.pdf
+  * Analog Devices ADM1276
+    Prefix: 'adm1276'
+    Addresses scanned: -
+    Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1276.pdf
 
 Author: Guenter Roeck <guenter.roeck@ericsson.com>
 
@@ -13,13 +17,13 @@ Author: Guenter Roeck <guenter.roeck@ericsson.com>
 Description
 -----------
 
-This driver supports hardware montoring for Analog Devices ADM1275 Hot-Swap
-Controller and Digital Power Monitor.
+This driver supports hardware montoring for Analog Devices ADM1275 and ADM1276
+Hot-Swap Controller and Digital Power Monitor.
 
-The ADM1275 is a hot-swap controller that allows a circuit board to be removed
-from or inserted into a live backplane. It also features current and voltage
-readback via an integrated 12-bit analog-to-digital converter (ADC), accessed
-using a PMBus. interface.
+ADM1275 and ADM1276 are hot-swap controllers that allow a circuit board to be
+removed from or inserted into a live backplane. They also feature current and
+voltage readback via an integrated 12-bit analog-to-digital converter (ADC),
+accessed using a PMBus interface.
 
 The driver is a client driver to the core PMBus driver. Please see
 Documentation/hwmon/pmbus for details on PMBus client drivers.
@@ -48,17 +52,25 @@ attributes are write-only, all other attributes are read-only.
 
 in1_label		"vin1" or "vout1" depending on chip variant and
 			configuration.
-in1_input		Measured voltage. From READ_VOUT register.
-in1_min			Minumum Voltage. From VOUT_UV_WARN_LIMIT register.
-in1_max			Maximum voltage. From VOUT_OV_WARN_LIMIT register.
-in1_min_alarm		Voltage low alarm. From VOLTAGE_UV_WARNING status.
-in1_max_alarm		Voltage high alarm. From VOLTAGE_OV_WARNING status.
+in1_input		Measured voltage.
+in1_min			Minumum Voltage.
+in1_max			Maximum voltage.
+in1_min_alarm		Voltage low alarm.
+in1_max_alarm		Voltage high alarm.
 in1_highest		Historical maximum voltage.
 in1_reset_history	Write any value to reset history.
 
 curr1_label		"iout1"
-curr1_input		Measured current. From READ_IOUT register.
-curr1_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
-curr1_max_alarm		Current high alarm. From IOUT_OC_WARN_LIMIT register.
+curr1_input		Measured current.
+curr1_max		Maximum current.
+curr1_max_alarm		Current high alarm.
+curr1_lcrit		Critical minimum current. Depending on the chip
+			configuration, either curr1_lcrit or curr1_crit is
+			supported, but not both.
+curr1_lcrit_alarm	Critical current low alarm.
+curr1_crit		Critical maximum current. Depending on the chip
+			configuration, either curr1_lcrit or curr1_crit is
+			supported, but not both.
+curr1_crit_alarm	Critical current high alarm.
 curr1_highest		Historical maximum current.
 curr1_reset_history	Write any value to reset history.

Documentation/hwmon/exynos4_tmu

@@ -0,0 +1,81 @@
+Kernel driver exynos4_tmu
+=================
+
+Supported chips:
+* ARM SAMSUNG EXYNOS4 series of SoC
+  Prefix: 'exynos4-tmu'
+  Datasheet: Not publicly available
+
+Authors: Donggeun Kim <dg77.kim@samsung.com>
+
+Description
+-----------
+
+This driver allows to read temperature inside SAMSUNG EXYNOS4 series of SoC.
+
+The chip only exposes the measured 8-bit temperature code value
+through a register.
+Temperature can be taken from the temperature code.
+There are three equations converting from temperature to temperature code.
+
+The three equations are:
+  1. Two point trimming
+	Tc = (T - 25) * (TI2 - TI1) / (85 - 25) + TI1
+
+  2. One point trimming
+	Tc = T + TI1 - 25
+
+  3. No trimming
+	Tc = T + 50
+
+  Tc: Temperature code, T: Temperature,
+  TI1: Trimming info for 25 degree Celsius (stored at TRIMINFO register)
+       Temperature code measured at 25 degree Celsius which is unchanged
+  TI2: Trimming info for 85 degree Celsius (stored at TRIMINFO register)
+       Temperature code measured at 85 degree Celsius which is unchanged
+
+TMU(Thermal Management Unit) in EXYNOS4 generates interrupt
+when temperature exceeds pre-defined levels.
+The maximum number of configurable threshold is four.
+The threshold levels are defined as follows:
+  Level_0: current temperature > trigger_level_0 + threshold
+  Level_1: current temperature > trigger_level_1 + threshold
+  Level_2: current temperature > trigger_level_2 + threshold
+  Level_3: current temperature > trigger_level_3 + threshold
+
+  The threshold and each trigger_level are set
+  through the corresponding registers.
+
+When an interrupt occurs, this driver notify user space of
+one of four threshold levels for the interrupt
+through kobject_uevent_env and sysfs_notify functions.
+Although an interrupt condition for level_0 can be set,
+it is not notified to user space through sysfs_notify function.
+
+Sysfs Interface
+---------------
+name		name of the temperature sensor
+		RO
+
+temp1_input	temperature
+		RO
+
+temp1_max	temperature for level_1 interrupt
+		RO
+
+temp1_crit	temperature for level_2 interrupt
+		RO
+
+temp1_emergency	temperature for level_3 interrupt
+		RO
+
+temp1_max_alarm	alarm for level_1 interrupt
+		RO
+
+temp1_crit_alarm
+		alarm for level_2 interrupt
+		RO
+
+temp1_emergency_alarm
+		alarm for level_3 interrupt
+		RO

Documentation/hwmon/lm75

@@ -12,26 +12,46 @@ Supported chips:
     Addresses scanned: I2C 0x48 - 0x4f
     Datasheet: Publicly available at the National Semiconductor website
                http://www.national.com/
-  * Dallas Semiconductor DS75
-    Prefix: 'lm75'
-    Addresses scanned: I2C 0x48 - 0x4f
-    Datasheet: Publicly available at the Dallas Semiconductor website
-               http://www.maxim-ic.com/
-  * Dallas Semiconductor DS1775
-    Prefix: 'lm75'
-    Addresses scanned: I2C 0x48 - 0x4f
+  * Dallas Semiconductor DS75, DS1775
+    Prefixes: 'ds75', 'ds1775'
+    Addresses scanned: none
     Datasheet: Publicly available at the Dallas Semiconductor website
                http://www.maxim-ic.com/
   * Maxim MAX6625, MAX6626
-    Prefix: 'lm75'
-    Addresses scanned: I2C 0x48 - 0x4b
+    Prefixes: 'max6625', 'max6626'
+    Addresses scanned: none
     Datasheet: Publicly available at the Maxim website
                http://www.maxim-ic.com/
   * Microchip (TelCom) TCN75
     Prefix: 'lm75'
-    Addresses scanned: I2C 0x48 - 0x4f
+    Addresses scanned: none
+    Datasheet: Publicly available at the Microchip website
+               http://www.microchip.com/
+  * Microchip MCP9800, MCP9801, MCP9802, MCP9803
+    Prefix: 'mcp980x'
+    Addresses scanned: none
     Datasheet: Publicly available at the Microchip website
                http://www.microchip.com/
+  * Analog Devices ADT75
+    Prefix: 'adt75'
+    Addresses scanned: none
+    Datasheet: Publicly available at the Analog Devices website
+               http://www.analog.com/adt75
+  * ST Microelectronics STDS75
+    Prefix: 'stds75'
+    Addresses scanned: none
+    Datasheet: Publicly available at the ST website
+               http://www.st.com/internet/analog/product/121769.jsp
+  * Texas Instruments TMP100, TMP101, TMP105, TMP75, TMP175, TMP275
+    Prefixes: 'tmp100', 'tmp101', 'tmp105', 'tmp175', 'tmp75', 'tmp275'
+    Addresses scanned: none
+    Datasheet: Publicly available at the Texas Instruments website
+               http://www.ti.com/product/tmp100
+               http://www.ti.com/product/tmp101
+               http://www.ti.com/product/tmp105
+               http://www.ti.com/product/tmp75
+               http://www.ti.com/product/tmp175
+               http://www.ti.com/product/tmp275
 
 Author: Frodo Looijaard <frodol@dds.nl>
 
@@ -50,21 +70,16 @@ range of -55 to +125 degrees.
 The LM75 only updates its values each 1.5 seconds; reading it more often
 will do no harm, but will return 'old' values.
 
-The LM75 is usually used in combination with LM78-like chips, to measure
-the temperature of the processor(s).
-
-The DS75, DS1775, MAX6625, and MAX6626 are supported as well.
-They are not distinguished from an LM75. While most of these chips
-have three additional bits of accuracy (12 vs. 9 for the LM75),
-the additional bits are not supported. Not only that, but these chips will
-not be detected if not in 9-bit precision mode (use the force parameter if
-needed).
-
-The TCN75 is supported as well, and is not distinguished from an LM75.
+The original LM75 was typically used in combination with LM78-like chips
+on PC motherboards, to measure the temperature of the processor(s). Clones
+are now used in various embedded designs.
 
 The LM75 is essentially an industry standard; there may be other
 LM75 clones not listed here, with or without various enhancements,
-that are supported.
+that are supported. The clones are not detected by the driver, unless
+they reproduce the exact register tricks of the original LM75, and must
+therefore be instantiated explicitly. The specific enhancements (such as
+higher resolution) are not currently supported by the driver.
 
 The LM77 is not supported, contrary to what we pretended for a long time.
 Both chips are simply not compatible, value encoding differs.

Documentation/hwmon/ltc2978

@@ -0,0 +1,103 @@
+Kernel driver ltc2978
+=====================
+
+Supported chips:
+  * Linear Technology LTC2978
+    Prefix: 'ltc2978'
+    Addresses scanned: -
+    Datasheet: http://cds.linear.com/docs/Datasheet/2978fa.pdf
+  * Linear Technology LTC3880
+    Prefix: 'ltc3880'
+    Addresses scanned: -
+    Datasheet: http://cds.linear.com/docs/Datasheet/3880f.pdf
+
+Author: Guenter Roeck <guenter.roeck@ericsson.com>
+
+
+Description
+-----------
+
+The LTC2978 is an octal power supply monitor, supervisor, sequencer and
+margin controller. The LTC3880 is a dual, PolyPhase DC/DC synchronous
+step-down switching regulator controller.
+
+
+Usage Notes
+-----------
+
+This driver does not probe for PMBus devices. You will have to instantiate
+devices explicitly.
+
+Example: the following commands will load the driver for an LTC2978 at address
+0x60 on I2C bus #1:
+
+# modprobe ltc2978
+# echo ltc2978 0x60 > /sys/bus/i2c/devices/i2c-1/new_device
+
+
+Sysfs attributes
+----------------
+
+in1_label		"vin"
+in1_input		Measured input voltage.
+in1_min			Minimum input voltage.
+in1_max			Maximum input voltage.
+in1_lcrit		Critical minimum input voltage.
+in1_crit		Critical maximum input voltage.
+in1_min_alarm		Input voltage low alarm.
+in1_max_alarm		Input voltage high alarm.
+in1_lcrit_alarm		Input voltage critical low alarm.
+in1_crit_alarm		Input voltage critical high alarm.
+in1_lowest		Lowest input voltage. LTC2978 only.
+in1_highest		Highest input voltage.
+in1_reset_history	Reset history. Writing into this attribute will reset
+			history for all attributes.
+
+in[2-9]_label		"vout[1-8]". Channels 3 to 9 on LTC2978 only.
+in[2-9]_input		Measured output voltage.
+in[2-9]_min		Minimum output voltage.
+in[2-9]_max		Maximum output voltage.
+in[2-9]_lcrit		Critical minimum output voltage.
+in[2-9]_crit		Critical maximum output voltage.
+in[2-9]_min_alarm	Output voltage low alarm.
+in[2-9]_max_alarm	Output voltage high alarm.
+in[2-9]_lcrit_alarm	Output voltage critical low alarm.
+in[2-9]_crit_alarm	Output voltage critical high alarm.
+in[2-9]_lowest		Lowest output voltage. LTC2978 only.
+in[2-9]_highest		Lowest output voltage.
+in[2-9]_reset_history	Reset history. Writing into this attribute will reset
+			history for all attributes.
+
+temp[1-3]_input		Measured temperature.
+			On LTC2978, only one temperature measurement is
+			supported and reflects the internal temperature.
+			On LTC3880, temp1 and temp2 report external
+			temperatures, and temp3 reports the internal
+			temperature.
+temp[1-3]_min		Mimimum temperature.
+temp[1-3]_max		Maximum temperature.
+temp[1-3]_lcrit		Critical low temperature.
+temp[1-3]_crit		Critical high temperature.
+temp[1-3]_min_alarm	Chip temperature low alarm.
+temp[1-3]_max_alarm	Chip temperature high alarm.
+temp[1-3]_lcrit_alarm	Chip temperature critical low alarm.
+temp[1-3]_crit_alarm	Chip temperature critical high alarm.
+temp[1-3]_lowest	Lowest measured temperature. LTC2978 only.
+temp[1-3]_highest	Highest measured temperature.
+temp[1-3]_reset_history	Reset history. Writing into this attribute will reset
+			history for all attributes.
+
+power[1-2]_label	"pout[1-2]". LTC3880 only.
+power[1-2]_input	Measured power.
+
+curr1_label		"iin". LTC3880 only.
+curr1_input		Measured input current.
+curr1_max		Maximum input current.
+curr1_max_alarm		Input current high alarm.
+
+curr[2-3]_label		"iout[1-2]". LTC3880 only.
+curr[2-3]_input		Measured input current.
+curr[2-3]_max		Maximum input current.
+curr[2-3]_crit		Critical input current.
+curr[2-3]_max_alarm	Input current high alarm.
+curr[2-3]_crit_alarm	Input current critical high alarm.

Documentation/hwmon/pmbus

@@ -8,11 +8,6 @@ Supported chips:
     Addresses scanned: -
     Datasheet:
  http://archive.ericsson.net/service/internet/picov/get?DocNo=28701-EN/LZT146395
-  * Linear Technology LTC2978
-    Octal PMBus Power Supply Monitor and Controller
-    Prefix: 'ltc2978'
-    Addresses scanned: -
-    Datasheet: http://cds.linear.com/docs/Datasheet/2978fa.pdf
   * ON Semiconductor ADP4000, NCP4200, NCP4208
     Prefixes: 'adp4000', 'ncp4200', 'ncp4208'
     Addresses scanned: -
@@ -20,6 +15,14 @@ Supported chips:
 	http://www.onsemi.com/pub_link/Collateral/ADP4000-D.PDF
 	http://www.onsemi.com/pub_link/Collateral/NCP4200-D.PDF
 	http://www.onsemi.com/pub_link/Collateral/JUNE%202009-%20REV.%200.PDF
+  * Lineage Power
+    Prefixes: 'pdt003', 'pdt006', 'pdt012', 'udt020'
+    Addresses scanned: -
+    Datasheets:
+	http://www.lineagepower.com/oem/pdf/PDT003A0X.pdf
+	http://www.lineagepower.com/oem/pdf/PDT006A0X.pdf
+	http://www.lineagepower.com/oem/pdf/PDT012A0X.pdf
+	http://www.lineagepower.com/oem/pdf/UDT020A0X.pdf
   * Generic PMBus devices
     Prefix: 'pmbus'
     Addresses scanned: -

Documentation/hwmon/pmbus-core

@@ -0,0 +1,283 @@
+PMBus core driver and internal API
+==================================
+
+Introduction
+============
+
+[from pmbus.org] The Power Management Bus (PMBus) is an open standard
+power-management protocol with a fully defined command language that facilitates
+communication with power converters and other devices in a power system. The
+protocol is implemented over the industry-standard SMBus serial interface and
+enables programming, control, and real-time monitoring of compliant power
+conversion products. This flexible and highly versatile standard allows for
+communication between devices based on both analog and digital technologies, and
+provides true interoperability which will reduce design complexity and shorten
+time to market for power system designers. Pioneered by leading power supply and
+semiconductor companies, this open power system standard is maintained and
+promoted by the PMBus Implementers Forum (PMBus-IF), comprising 30+ adopters
+with the objective to provide support to, and facilitate adoption among, users.
+
+Unfortunately, while PMBus commands are standardized, there are no mandatory
+commands, and manufacturers can add as many non-standard commands as they like.
+Also, different PMBUs devices act differently if non-supported commands are
+executed. Some devices return an error, some devices return 0xff or 0xffff and
+set a status error flag, and some devices may simply hang up.
+
+Despite all those difficulties, a generic PMBus device driver is still useful
+and supported since kernel version 2.6.39. However, it was necessary to support
+device specific extensions in addition to the core PMBus driver, since it is
+simply unknown what new device specific functionality PMBus device developers
+come up with next.
+
+To make device specific extensions as scalable as possible, and to avoid having
+to modify the core PMBus driver repeatedly for new devices, the PMBus driver was
+split into core, generic, and device specific code. The core code (in
+pmbus_core.c) provides generic functionality. The generic code (in pmbus.c)
+provides support for generic PMBus devices. Device specific code is responsible
+for device specific initialization and, if needed, maps device specific
+functionality into generic functionality. This is to some degree comparable
+to PCI code, where generic code is augmented as needed with quirks for all kinds
+of devices.
+
+PMBus device capabilities auto-detection
+========================================
+
+For generic PMBus devices, code in pmbus.c attempts to auto-detect all supported
+PMBus commands. Auto-detection is somewhat limited, since there are simply too
+many variables to consider. For example, it is almost impossible to autodetect
+which PMBus commands are paged and which commands are replicated across all
+pages (see the PMBus specification for details on multi-page PMBus devices).
+
+For this reason, it often makes sense to provide a device specific driver if not
+all commands can be auto-detected. The data structures in this driver can be
+used to inform the core driver about functionality supported by individual
+chips.
+
+Some commands are always auto-detected. This applies to all limit commands
+(lcrit, min, max, and crit attributes) as well as associated alarm attributes.
+Limits and alarm attributes are auto-detected because there are simply too many
+possible combinations to provide a manual configuration interface.
+
+PMBus internal API
+==================
+
+The API between core and device specific PMBus code is defined in
+drivers/hwmon/pmbus/pmbus.h. In addition to the internal API, pmbus.h defines
+standard PMBus commands and virtual PMBus commands.
+
+Standard PMBus commands
+-----------------------
+
+Standard PMBus commands (commands values 0x00 to 0xff) are defined in the PMBUs
+specification.
+
+Virtual PMBus commands
+----------------------
+
+Virtual PMBus commands are provided to enable support for non-standard
+functionality which has been implemented by several chip vendors and is thus
+desirable to support.
+
+Virtual PMBus commands start with command value 0x100 and can thus easily be
+distinguished from standard PMBus commands (which can not have values larger
+than 0xff). Support for virtual PMBus commands is device specific and thus has
+to be implemented in device specific code.
+
+Virtual commands are named PMBUS_VIRT_xxx and start with PMBUS_VIRT_BASE. All
+virtual commands are word sized.
+
+There are currently two types of virtual commands.
+
+- READ commands are read-only; writes are either ignored or return an error.
+- RESET commands are read/write. Reading reset registers returns zero
+  (used for detection), writing any value causes the associated history to be
+  reset.
+
+Virtual commands have to be handled in device specific driver code. Chip driver
+code returns non-negative values if a virtual command is supported, or a
+negative error code if not. The chip driver may return -ENODATA or any other
+Linux error code in this case, though an error code other than -ENODATA is
+handled more efficiently and thus preferred. Either case, the calling PMBus
+core code will abort if the chip driver returns an error code when reading
+or writing virtual registers (in other words, the PMBus core code will never
+send a virtual command to a chip).
+
+PMBus driver information
+------------------------
+
+PMBus driver information, defined in struct pmbus_driver_info, is the main means
+for device specific drivers to pass information to the core PMBus driver.
+Specifically, it provides the following information.
+
+- For devices supporting its data in Direct Data Format, it provides coefficients
+  for converting register values into normalized data. This data is usually
+  provided by chip manufacturers in device datasheets.
+- Supported chip functionality can be provided to the core driver. This may be
+  necessary for chips which react badly if non-supported commands are executed,
+  and/or to speed up device detection and initialization.
+- Several function entry points are provided to support overriding and/or
+  augmenting generic command execution. This functionality can be used to map
+  non-standard PMBus commands to standard commands, or to augment standard
+  command return values with device specific information.
+
+  API functions
+  -------------
+
+  Functions provided by chip driver
+  ---------------------------------
+
+  All functions return the command return value (read) or zero (write) if
+  successful. A return value of -ENODATA indicates that there is no manufacturer
+  specific command, but that a standard PMBus command may exist. Any other
+  negative return value indicates that the commands does not exist for this
+  chip, and that no attempt should be made to read or write the standard
+  command.
+
+  As mentioned above, an exception to this rule applies to virtual commands,
+  which  _must_ be handled in driver specific code. See "Virtual PMBus Commands"
+  above for more details.
+
+  Command execution in the core PMBus driver code is as follows.
+
+	if (chip_access_function) {
+		status = chip_access_function();
+		if (status != -ENODATA)
+			return status;
+	}
+	if (command >= PMBUS_VIRT_BASE)	/* For word commands/registers only */
+		return -EINVAL;
+	return generic_access();
+
+  Chip drivers may provide pointers to the following functions in struct
+  pmbus_driver_info. All functions are optional.
+
+  int (*read_byte_data)(struct i2c_client *client, int page, int reg);
+
+  Read byte from page <page>, register <reg>.
+  <page> may be -1, which means "current page".
+
+  int (*read_word_data)(struct i2c_client *client, int page, int reg);
+
+  Read word from page <page>, register <reg>.
+
+  int (*write_word_data)(struct i2c_client *client, int page, int reg,
+		         u16 word);
+
+  Write word to page <page>, register <reg>.
+
+  int (*write_byte)(struct i2c_client *client, int page, u8 value);
+
+  Write byte to page <page>, register <reg>.
+  <page> may be -1, which means "current page".
+
+  int (*identify)(struct i2c_client *client, struct pmbus_driver_info *info);
+
+  Determine supported PMBus functionality. This function is only necessary
+  if a chip driver supports multiple chips, and the chip functionality is not
+  pre-determined. It is currently only used by the generic pmbus driver
+  (pmbus.c).
+
+  Functions exported by core driver
+  ---------------------------------
+
+  Chip drivers are expected to use the following functions to read or write
+  PMBus registers. Chip drivers may also use direct I2C commands. If direct I2C
+  commands are used, the chip driver code must not directly modify the current
+  page, since the selected page is cached in the core driver and the core driver
+  will assume that it is selected. Using pmbus_set_page() to select a new page
+  is mandatory.
+
+  int pmbus_set_page(struct i2c_client *client, u8 page);
+
+  Set PMBus page register to <page> for subsequent commands.
+
+  int pmbus_read_word_data(struct i2c_client *client, u8 page, u8 reg);
+
+  Read word data from <page>, <reg>. Similar to i2c_smbus_read_word_data(), but
+  selects page first.
+
+  int pmbus_write_word_data(struct i2c_client *client, u8 page, u8 reg,
+			    u16 word);
+
+  Write word data to <page>, <reg>. Similar to i2c_smbus_write_word_data(), but
+  selects page first.
+
+  int pmbus_read_byte_data(struct i2c_client *client, int page, u8 reg);
+
+  Read byte data from <page>, <reg>. Similar to i2c_smbus_read_byte_data(), but
+  selects page first. <page> may be -1, which means "current page".
+
+  int pmbus_write_byte(struct i2c_client *client, int page, u8 value);
+
+  Write byte data to <page>, <reg>. Similar to i2c_smbus_write_byte(), but
+  selects page first. <page> may be -1, which means "current page".
+
+  void pmbus_clear_faults(struct i2c_client *client);
+
+  Execute PMBus "Clear Fault" command on all chip pages.
+  This function calls the device specific write_byte function if defined.
+  Therefore, it must _not_ be called from that function.
+
+  bool pmbus_check_byte_register(struct i2c_client *client, int page, int reg);
+
+  Check if byte register exists. Return true if the register exists, false
+  otherwise.
+  This function calls the device specific write_byte function if defined to
+  obtain the chip status. Therefore, it must _not_ be called from that function.
+
+  bool pmbus_check_word_register(struct i2c_client *client, int page, int reg);
+
+  Check if word register exists. Return true if the register exists, false
+  otherwise.
+  This function calls the device specific write_byte function if defined to
+  obtain the chip status. Therefore, it must _not_ be called from that function.
+
+  int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id,
+                     struct pmbus_driver_info *info);
+
+  Execute probe function. Similar to standard probe function for other drivers,
+  with the pointer to struct pmbus_driver_info as additional argument. Calls
+  identify function if supported. Must only be called from device probe
+  function.
+
+  void pmbus_do_remove(struct i2c_client *client);
+
+  Execute driver remove function. Similar to standard driver remove function.
+
+  const struct pmbus_driver_info
+	*pmbus_get_driver_info(struct i2c_client *client);
+
+  Return pointer to struct pmbus_driver_info as passed to pmbus_do_probe().
+
+
+PMBus driver platform data
+==========================
+
+PMBus platform data is defined in include/linux/i2c/pmbus.h. Platform data
+currently only provides a flag field with a single bit used.
+
+#define PMBUS_SKIP_STATUS_CHECK (1 << 0)
+
+struct pmbus_platform_data {
+        u32 flags;              /* Device specific flags */
+};
+
+
+Flags
+-----
+
+PMBUS_SKIP_STATUS_CHECK
+
+During register detection, skip checking the status register for
+communication or command errors.
+
+Some PMBus chips respond with valid data when trying to read an unsupported
+register. For such chips, checking the status register is mandatory when
+trying to determine if a chip register exists or not.
+Other PMBus chips don't support the STATUS_CML register, or report
+communication errors for no explicable reason. For such chips, checking the
+status register must be disabled.
+
+Some i2c controllers do not support single-byte commands (write commands with
+no data, i2c_smbus_write_byte()). With such controllers, clearing the status
+register is impossible, and the PMBUS_SKIP_STATUS_CHECK flag must be set.

Documentation/hwmon/zl6100

@@ -0,0 +1,125 @@
+Kernel driver zl6100
+====================
+
+Supported chips:
+  * Intersil / Zilker Labs ZL2004
+    Prefix: 'zl2004'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6847.pdf
+  * Intersil / Zilker Labs ZL2006
+    Prefix: 'zl2006'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6850.pdf
+  * Intersil / Zilker Labs ZL2008
+    Prefix: 'zl2008'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6859.pdf
+  * Intersil / Zilker Labs ZL2105
+    Prefix: 'zl2105'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6851.pdf
+  * Intersil / Zilker Labs ZL2106
+    Prefix: 'zl2106'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6852.pdf
+  * Intersil / Zilker Labs ZL6100
+    Prefix: 'zl6100'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6876.pdf
+  * Intersil / Zilker Labs ZL6105
+    Prefix: 'zl6105'
+    Addresses scanned: -
+    Datasheet: http://www.intersil.com/data/fn/fn6906.pdf
+
+Author: Guenter Roeck <guenter.roeck@ericsson.com>
+
+
+Description
+-----------
+
+This driver supports hardware montoring for Intersil / Zilker Labs ZL6100 and
+compatible digital DC-DC controllers.
+
+The driver is a client driver to the core PMBus driver. Please see
+Documentation/hwmon/pmbus and Documentation.hwmon/pmbus-core for details
+on PMBus client drivers.
+
+
+Usage Notes
+-----------
+
+This driver does not auto-detect devices. You will have to instantiate the
+devices explicitly. Please see Documentation/i2c/instantiating-devices for
+details.
+
+WARNING: Do not access chip registers using the i2cdump command, and do not use
+any of the i2ctools commands on a command register used to save and restore
+configuration data (0x11, 0x12, 0x15, 0x16, and 0xf4). The chips supported by
+this driver interpret any access to those command registers (including read
+commands) as request to execute the command in question. Unless write accesses
+to those registers are protected, this may result in power loss, board resets,
+and/or Flash corruption. Worst case, your board may turn into a brick.
+
+
+Platform data support
+---------------------
+
+The driver supports standard PMBus driver platform data.
+
+
+Module parameters
+-----------------
+
+delay
+-----
+
+Some Intersil/Zilker Labs DC-DC controllers require a minimum interval between
+I2C bus accesses. According to Intersil, the minimum interval is 2 ms, though
+1 ms appears to be sufficient and has not caused any problems in testing.
+The problem is known to affect ZL6100, ZL2105, and ZL2008. It is known not to
+affect ZL2004 and ZL6105. The driver automatically sets the interval to 1 ms
+except for ZL2004 and ZL6105. To enable manual override, the driver provides a
+writeable module parameter, 'delay', which can be used to set the interval to
+a value between 0 and 65,535 microseconds.
+
+
+Sysfs entries
+-------------
+
+The following attributes are supported. Limits are read-write; all other
+attributes are read-only.
+
+in1_label		"vin"
+in1_input		Measured input voltage.
+in1_min			Minimum input voltage.
+in1_max			Maximum input voltage.
+in1_lcrit		Critical minumum input voltage.
+in1_crit		Critical maximum input voltage.
+in1_min_alarm		Input voltage low alarm.
+in1_max_alarm		Input voltage high alarm.
+in1_lcrit_alarm		Input voltage critical low alarm.
+in1_crit_alarm		Input voltage critical high alarm.
+
+in2_label		"vout1"
+in2_input		Measured output voltage.
+in2_lcrit		Critical minumum output Voltage.
+in2_crit		Critical maximum output voltage.
+in2_lcrit_alarm		Critical output voltage critical low alarm.
+in2_crit_alarm		Critical output voltage critical high alarm.
+
+curr1_label		"iout1"
+curr1_input		Measured output current.
+curr1_lcrit		Critical minimum output current.
+curr1_crit		Critical maximum output current.
+curr1_lcrit_alarm	Output current critical low alarm.
+curr1_crit_alarm	Output current critical high alarm.
+
+temp[12]_input		Measured temperature.
+temp[12]_min		Minimum temperature.
+temp[12]_max		Maximum temperature.
+temp[12]_lcrit		Critical low temperature.
+temp[12]_crit		Critical high temperature.
+temp[12]_min_alarm	Chip temperature low alarm.
+temp[12]_max_alarm	Chip temperature high alarm.
+temp[12]_lcrit_alarm	Chip temperature critical low alarm.
+temp[12]_crit_alarm	Chip temperature critical high alarm.

Documentation/input/input.txt

@@ -111,7 +111,7 @@ LCDs and many other purposes.
 
  The monitor and speaker controls should be easy to add to the hid/input
 interface, but for the UPSs and LCDs it doesn't make much sense. For this,
-the hiddev interface was designed. See Documentation/usb/hiddev.txt
+the hiddev interface was designed. See Documentation/hid/hiddev.txt
 for more information about it.
 
   The usage of the usbhid module is very simple, it takes no parameters,

Documentation/kernel-docs.txt

@@ -300,7 +300,7 @@
        
      * Title: "The Kernel Hacking HOWTO"
        Author: Various Talented People, and Rusty.
-       Location: in kernel tree, Documentation/DocBook/kernel-hacking/
+       Location: in kernel tree, Documentation/DocBook/kernel-hacking.tmpl
        (must be built as "make {htmldocs | psdocs | pdfdocs})
        Keywords: HOWTO, kernel contexts, deadlock, locking, modules,
        symbols, return conventions.
@@ -351,7 +351,7 @@
        
      * Title: "Linux Kernel Locking HOWTO"
        Author: Various Talented People, and Rusty.
-       Location: in kernel tree, Documentation/DocBook/kernel-locking/
+       Location: in kernel tree, Documentation/DocBook/kernel-locking.tmpl
        (must be built as "make {htmldocs | psdocs | pdfdocs})
        Keywords: locks, locking, spinlock, semaphore, atomic, race
        condition, bottom halves, tasklets, softirqs.

Documentation/kernel-parameters.txt

@@ -49,6 +49,7 @@ parameter is applicable:
 	EDD	BIOS Enhanced Disk Drive Services (EDD) is enabled
 	EFI	EFI Partitioning (GPT) is enabled
 	EIDE	EIDE/ATAPI support is enabled.
+	EVM	Extended Verification Module
 	FB	The frame buffer device is enabled.
 	FTRACE	Function tracing enabled.
 	GCOV	GCOV profiling is enabled.
@@ -163,7 +164,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			rsdt -- prefer RSDT over (default) XSDT
 			copy_dsdt -- copy DSDT to memory
 
-			See also Documentation/power/pm.txt, pci=noacpi
+			See also Documentation/power/runtime_pm.txt, pci=noacpi
 
 	acpi_rsdp=	[ACPI,EFI,KEXEC]
 			Pass the RSDP address to the kernel, mostly used
@@ -319,7 +320,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
-			See also Documentation/kernel/input/joystick.txt
+			See also Documentation/input/joystick.txt
 
 	analog.map=	[HW,JOY] Analog joystick and gamepad support
 			Specifies type or capabilities of an analog joystick
@@ -408,7 +409,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	bttv.radio=	Most important insmod options are available as
 			kernel args too.
 	bttv.pll=	See Documentation/video4linux/bttv/Insmod-options
-	bttv.tuner=	and Documentation/video4linux/bttv/CARDLIST
+	bttv.tuner=
 
 	bulk_remove=off	[PPC]  This parameter disables the use of the pSeries
 			firmware feature for flushing multiple hpte entries
@@ -724,7 +725,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	elevator=	[IOSCHED]
 			Format: {"cfq" | "deadline" | "noop"}
-			See Documentation/block/as-iosched.txt and
+			See Documentation/block/cfq-iosched.txt and
 			Documentation/block/deadline-iosched.txt for details.
 
 	elfcorehdr=	[IA-64,PPC,SH,X86]
@@ -760,12 +761,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			This option is obsoleted by the "netdev=" option, which
 			has equivalent usage. See its documentation for details.
 
+	evm=		[EVM]
+			Format: { "fix" }
+			Permit 'security.evm' to be updated regardless of
+			current integrity status.
+
 	failslab=
 	fail_page_alloc=
 	fail_make_request=[KNL]
 			General fault injection mechanism.
 			Format: <interval>,<probability>,<space>,<times>
-			See also /Documentation/fault-injection/.
+			See also Documentation/fault-injection/.
 
 	floppy=		[HW]
 			See Documentation/blockdev/floppy.txt.
@@ -1014,10 +1020,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			has the capability. With this option, super page will
 			not be supported.
 	intremap=	[X86-64, Intel-IOMMU]
-			Format: { on (default) | off | nosid }
 			on	enable Interrupt Remapping (default)
 			off	disable Interrupt Remapping
 			nosid	disable Source ID checking
+			no_x2apic_optout
+				BIOS x2APIC opt-out request will be ignored
 
 	inttest=	[IA-64]
 
@@ -2240,6 +2247,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			in <PAGE_SIZE> units (needed only for swap files).
 			See  Documentation/power/swsusp-and-swap-files.txt
 
+	resumedelay=	[HIBERNATION] Delay (in seconds) to pause before attempting to
+			read the resume files
+
+	resumewait	[HIBERNATION] Wait (indefinitely) for resume device to show up.
+			Useful for devices that are detected asynchronously
+			(e.g. USB and MMC devices).
+
 	hibernate=	[HIBERNATION]
 		noresume	Don't check if there's a hibernation image
 				present during boot.
@@ -2375,7 +2389,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Format: <integer>
 
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
-			See Documentation/sonypi.txt
+			See Documentation/laptops/sonypi.txt
 
 	specialix=	[HW,SERIAL] Specialix multi-serial port adapter
 			See Documentation/serial/specialix.txt.

Documentation/laptops/thinkpad-acpi.txt

@@ -736,7 +736,7 @@ status as "unknown". The available commands are:
 sysfs notes:
 
 The ThinkLight sysfs interface is documented by the LED class
-documentation, in Documentation/leds-class.txt.  The ThinkLight LED name
+documentation, in Documentation/leds/leds-class.txt.  The ThinkLight LED name
 is "tpacpi::thinklight".
 
 Due to limitations in the sysfs LED class, if the status of the ThinkLight
@@ -833,7 +833,7 @@ All of the above can be turned on and off and can be made to blink.
 sysfs notes:
 
 The ThinkPad LED sysfs interface is described in detail by the LED class
-documentation, in Documentation/leds-class.txt.
+documentation, in Documentation/leds/leds-class.txt.
 
 The LEDs are named (in LED ID order, from 0 to 12):
 "tpacpi::power", "tpacpi:orange:batt", "tpacpi:green:batt",

Documentation/media-framework.txt

@@ -9,8 +9,8 @@ Introduction
 ------------
 
 The media controller API is documented in DocBook format in
-Documentation/DocBook/v4l/media-controller.xml. This document will focus on
-the kernel-side implementation of the media framework.
+Documentation/DocBook/media/v4l/media-controller.xml. This document will focus
+on the kernel-side implementation of the media framework.
 
 
 Abstract media device model

Documentation/memory-barriers.txt

@@ -438,7 +438,7 @@ There are certain things that the Linux kernel memory barriers do not guarantee:
 	[*] For information on bus mastering DMA and coherency please read:
 
 	    Documentation/PCI/pci.txt
-	    Documentation/PCI/PCI-DMA-mapping.txt
+	    Documentation/DMA-API-HOWTO.txt
 	    Documentation/DMA-API.txt
 
 

Documentation/networking/LICENSE.qlcnic

@@ -1,61 +1,22 @@
-Copyright (c) 2009-2010 QLogic Corporation
+Copyright (c) 2009-2011 QLogic Corporation
 QLogic Linux qlcnic NIC Driver
 
-This program includes a device driver for Linux 2.6 that may be
-distributed with QLogic hardware specific firmware binary file.
 You may modify and redistribute the device driver code under the
 GNU General Public License (a copy of which is attached hereto as
 Exhibit A) published by the Free Software Foundation (version 2).
 
-You may redistribute the hardware specific firmware binary file
-under the following terms:
-
-       1. Redistribution of source code (only if applicable),
-          must retain the above copyright notice, this list of
-          conditions and the following disclaimer.
-
-       2. Redistribution in binary form must reproduce the above
-          copyright notice, this list of conditions and the
-          following disclaimer in the documentation and/or other
-          materials provided with the distribution.
-
-       3. The name of QLogic Corporation may not be used to
-          endorse or promote products derived from this software
-          without specific prior written permission
-
-REGARDLESS OF WHAT LICENSING MECHANISM IS USED OR APPLICABLE,
-THIS PROGRAM IS PROVIDED BY QLOGIC CORPORATION "AS IS'' AND ANY
-EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
-PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR
-BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
-TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
-ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
-OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.
-
-USER ACKNOWLEDGES AND AGREES THAT USE OF THIS PROGRAM WILL NOT
-CREATE OR GIVE GROUNDS FOR A LICENSE BY IMPLICATION, ESTOPPEL, OR
-OTHERWISE IN ANY INTELLECTUAL PROPERTY RIGHTS (PATENT, COPYRIGHT,
-TRADE SECRET, MASK WORK, OR OTHER PROPRIETARY RIGHT) EMBODIED IN
-ANY OTHER QLOGIC HARDWARE OR SOFTWARE EITHER SOLELY OR IN
-COMBINATION WITH THIS PROGRAM.
-
 
 EXHIBIT A
 
-                   GNU GENERAL PUBLIC LICENSE
-                      Version 2, June 1991
+		    GNU GENERAL PUBLIC LICENSE
+		       Version 2, June 1991
 
  Copyright (C) 1989, 1991 Free Software Foundation, Inc.
  51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
  Everyone is permitted to copy and distribute verbatim copies
  of this license document, but changing it is not allowed.
 
-                           Preamble
+			    Preamble
 
   The licenses for most software are designed to take away your
 freedom to share and change it.  By contrast, the GNU General Public
@@ -105,7 +66,7 @@ patent must be licensed for everyone's free use or not licensed at all.
   The precise terms and conditions for copying, distribution and
 modification follow.
 
-                   GNU GENERAL PUBLIC LICENSE
+		    GNU GENERAL PUBLIC LICENSE
    TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
 
   0. This License applies to any program or other work which contains
@@ -304,7 +265,7 @@ make exceptions for this.  Our decision will be guided by the two goals
 of preserving the free status of all derivatives of our free software and
 of promoting the sharing and reuse of software generally.
 
-                           NO WARRANTY
+			    NO WARRANTY
 
   11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
 FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN

Documentation/networking/scaling.txt

@@ -73,7 +73,7 @@ of queues to IRQs can be determined from /proc/interrupts. By default,
 an IRQ may be handled on any CPU. Because a non-negligible part of packet
 processing takes place in receive interrupt handling, it is advantageous
 to spread receive interrupts between CPUs. To manually adjust the IRQ
-affinity of each interrupt see Documentation/IRQ-affinity. Some systems
+affinity of each interrupt see Documentation/IRQ-affinity.txt. Some systems
 will be running irqbalance, a daemon that dynamically optimizes IRQ
 assignments and as a result may override any manual settings.
 

Documentation/pinctrl.txt

@@ -0,0 +1,950 @@
+PINCTRL (PIN CONTROL) subsystem
+This document outlines the pin control subsystem in Linux
+
+This subsystem deals with:
+
+- Enumerating and naming controllable pins
+
+- Multiplexing of pins, pads, fingers (etc) see below for details
+
+The intention is to also deal with:
+
+- Software-controlled biasing and driving mode specific pins, such as
+  pull-up/down, open drain etc, load capacitance configuration when controlled
+  by software, etc.
+
+
+Top-level interface
+===================
+
+Definition of PIN CONTROLLER:
+
+- A pin controller is a piece of hardware, usually a set of registers, that
+  can control PINs. It may be able to multiplex, bias, set load capacitance,
+  set drive strength etc for individual pins or groups of pins.
+
+Definition of PIN:
+
+- PINS are equal to pads, fingers, balls or whatever packaging input or
+  output line you want to control and these are denoted by unsigned integers
+  in the range 0..maxpin. This numberspace is local to each PIN CONTROLLER, so
+  there may be several such number spaces in a system. This pin space may
+  be sparse - i.e. there may be gaps in the space with numbers where no
+  pin exists.
+
+When a PIN CONTROLLER is instatiated, it will register a descriptor to the
+pin control framework, and this descriptor contains an array of pin descriptors
+describing the pins handled by this specific pin controller.
+
+Here is an example of a PGA (Pin Grid Array) chip seen from underneath:
+
+        A   B   C   D   E   F   G   H
+
+   8    o   o   o   o   o   o   o   o
+
+   7    o   o   o   o   o   o   o   o
+
+   6    o   o   o   o   o   o   o   o
+
+   5    o   o   o   o   o   o   o   o
+
+   4    o   o   o   o   o   o   o   o
+
+   3    o   o   o   o   o   o   o   o
+
+   2    o   o   o   o   o   o   o   o
+
+   1    o   o   o   o   o   o   o   o
+
+To register a pin controller and name all the pins on this package we can do
+this in our driver:
+
+#include <linux/pinctrl/pinctrl.h>
+
+const struct pinctrl_pin_desc __refdata foo_pins[] = {
+      PINCTRL_PIN(0, "A1"),
+      PINCTRL_PIN(1, "A2"),
+      PINCTRL_PIN(2, "A3"),
+      ...
+      PINCTRL_PIN(61, "H6"),
+      PINCTRL_PIN(62, "H7"),
+      PINCTRL_PIN(63, "H8"),
+};
+
+static struct pinctrl_desc foo_desc = {
+	.name = "foo",
+	.pins = foo_pins,
+	.npins = ARRAY_SIZE(foo_pins),
+	.maxpin = 63,
+	.owner = THIS_MODULE,
+};
+
+int __init foo_probe(void)
+{
+	struct pinctrl_dev *pctl;
+
+	pctl = pinctrl_register(&foo_desc, <PARENT>, NULL);
+	if (IS_ERR(pctl))
+		pr_err("could not register foo pin driver\n");
+}
+
+Pins usually have fancier names than this. You can find these in the dataheet
+for your chip. Notice that the core pinctrl.h file provides a fancy macro
+called PINCTRL_PIN() to create the struct entries. As you can see I enumerated
+the pins from 0 in the upper left corner to 63 in the lower right corner,
+this enumeration was arbitrarily chosen, in practice you need to think
+through your numbering system so that it matches the layout of registers
+and such things in your driver, or the code may become complicated. You must
+also consider matching of offsets to the GPIO ranges that may be handled by
+the pin controller.
+
+For a padring with 467 pads, as opposed to actual pins, I used an enumeration
+like this, walking around the edge of the chip, which seems to be industry
+standard too (all these pads had names, too):
+
+
+     0 ..... 104
+   466        105
+     .        .
+     .        .
+   358        224
+    357 .... 225
+
+
+Pin groups
+==========
+
+Many controllers need to deal with groups of pins, so the pin controller
+subsystem has a mechanism for enumerating groups of pins and retrieving the
+actual enumerated pins that are part of a certain group.
+
+For example, say that we have a group of pins dealing with an SPI interface
+on { 0, 8, 16, 24 }, and a group of pins dealing with an I2C interface on pins
+on { 24, 25 }.
+
+These two groups are presented to the pin control subsystem by implementing
+some generic pinctrl_ops like this:
+
+#include <linux/pinctrl/pinctrl.h>
+
+struct foo_group {
+	const char *name;
+	const unsigned int *pins;
+	const unsigned num_pins;
+};
+
+static unsigned int spi0_pins[] = { 0, 8, 16, 24 };
+static unsigned int i2c0_pins[] = { 24, 25 };
+
+static const struct foo_group foo_groups[] = {
+	{
+		.name = "spi0_grp",
+		.pins = spi0_pins,
+		.num_pins = ARRAY_SIZE(spi0_pins),
+	},
+	{
+		.name = "i2c0_grp",
+		.pins = i2c0_pins,
+		.num_pins = ARRAY_SIZE(i2c0_pins),
+	},
+};
+
+
+static int foo_list_groups(struct pinctrl_dev *pctldev, unsigned selector)
+{
+	if (selector >= ARRAY_SIZE(foo_groups))
+		return -EINVAL;
+	return 0;
+}
+
+static const char *foo_get_group_name(struct pinctrl_dev *pctldev,
+				       unsigned selector)
+{
+	return foo_groups[selector].name;
+}
+
+static int foo_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector,
+			       unsigned ** const pins,
+			       unsigned * const num_pins)
+{
+	*pins = (unsigned *) foo_groups[selector].pins;
+	*num_pins = foo_groups[selector].num_pins;
+	return 0;
+}
+
+static struct pinctrl_ops foo_pctrl_ops = {
+	.list_groups = foo_list_groups,
+	.get_group_name = foo_get_group_name,
+	.get_group_pins = foo_get_group_pins,
+};
+
+
+static struct pinctrl_desc foo_desc = {
+       ...
+       .pctlops = &foo_pctrl_ops,
+};
+
+The pin control subsystem will call the .list_groups() function repeatedly
+beginning on 0 until it returns non-zero to determine legal selectors, then
+it will call the other functions to retrieve the name and pins of the group.
+Maintaining the data structure of the groups is up to the driver, this is
+just a simple example - in practice you may need more entries in your group
+structure, for example specific register ranges associated with each group
+and so on.
+
+
+Interaction with the GPIO subsystem
+===================================
+
+The GPIO drivers may want to perform operations of various types on the same
+physical pins that are also registered as pin controller pins.
+
+Since the pin controller subsystem have its pinspace local to the pin
+controller we need a mapping so that the pin control subsystem can figure out
+which pin controller handles control of a certain GPIO pin. Since a single
+pin controller may be muxing several GPIO ranges (typically SoCs that have
+one set of pins but internally several GPIO silicon blocks, each modeled as
+a struct gpio_chip) any number of GPIO ranges can be added to a pin controller
+instance like this:
+
+struct gpio_chip chip_a;
+struct gpio_chip chip_b;
+
+static struct pinctrl_gpio_range gpio_range_a = {
+	.name = "chip a",
+	.id = 0,
+	.base = 32,
+	.npins = 16,
+	.gc = &chip_a;
+};
+
+static struct pinctrl_gpio_range gpio_range_a = {
+	.name = "chip b",
+	.id = 0,
+	.base = 48,
+	.npins = 8,
+	.gc = &chip_b;
+};
+
+
+{
+	struct pinctrl_dev *pctl;
+	...
+	pinctrl_add_gpio_range(pctl, &gpio_range_a);
+	pinctrl_add_gpio_range(pctl, &gpio_range_b);
+}
+
+So this complex system has one pin controller handling two different
+GPIO chips. Chip a has 16 pins and chip b has 8 pins. They are mapped in
+the global GPIO pin space at:
+
+chip a: [32 .. 47]
+chip b: [48 .. 55]
+
+When GPIO-specific functions in the pin control subsystem are called, these
+ranges will be used to look up the apropriate pin controller by inspecting
+and matching the pin to the pin ranges across all controllers. When a
+pin controller handling the matching range is found, GPIO-specific functions
+will be called on that specific pin controller.
+
+For all functionalities dealing with pin biasing, pin muxing etc, the pin
+controller subsystem will subtract the range's .base offset from the passed
+in gpio pin number, and pass that on to the pin control driver, so the driver
+will get an offset into its handled number range. Further it is also passed
+the range ID value, so that the pin controller knows which range it should
+deal with.
+
+For example: if a user issues pinctrl_gpio_set_foo(50), the pin control
+subsystem will find that the second range on this pin controller matches,
+subtract the base 48 and call the
+pinctrl_driver_gpio_set_foo(pinctrl, range, 2) where the latter function has
+this signature:
+
+int pinctrl_driver_gpio_set_foo(struct pinctrl_dev *pctldev,
+    struct pinctrl_gpio_range *rangeid,
+    unsigned offset);
+
+Now the driver knows that we want to do some GPIO-specific operation on the
+second GPIO range handled by "chip b", at offset 2 in that specific range.
+
+(If the GPIO subsystem is ever refactored to use a local per-GPIO controller
+pin space, this mapping will need to be augmented accordingly.)
+
+
+PINMUX interfaces
+=================
+
+These calls use the pinmux_* naming prefix.  No other calls should use that
+prefix.
+
+
+What is pinmuxing?
+==================
+
+PINMUX, also known as padmux, ballmux, alternate functions or mission modes
+is a way for chip vendors producing some kind of electrical packages to use
+a certain physical pin (ball, pad, finger, etc) for multiple mutually exclusive
+functions, depending on the application. By "application" in this context
+we usually mean a way of soldering or wiring the package into an electronic
+system, even though the framework makes it possible to also change the function
+at runtime.
+
+Here is an example of a PGA (Pin Grid Array) chip seen from underneath:
+
+        A   B   C   D   E   F   G   H
+      +---+
+   8  | o | o   o   o   o   o   o   o
+      |   |
+   7  | o | o   o   o   o   o   o   o
+      |   |
+   6  | o | o   o   o   o   o   o   o
+      +---+---+
+   5  | o | o | o   o   o   o   o   o
+      +---+---+               +---+
+   4    o   o   o   o   o   o | o | o
+                              |   |
+   3    o   o   o   o   o   o | o | o
+                              |   |
+   2    o   o   o   o   o   o | o | o
+      +-------+-------+-------+---+---+
+   1  | o   o | o   o | o   o | o | o |
+      +-------+-------+-------+---+---+
+
+This is not tetris. The game to think of is chess. Not all PGA/BGA packages
+are chessboard-like, big ones have "holes" in some arrangement according to
+different design patterns, but we're using this as a simple example. Of the
+pins you see some will be taken by things like a few VCC and GND to feed power
+to the chip, and quite a few will be taken by large ports like an external
+memory interface. The remaining pins will often be subject to pin multiplexing.
+
+The example 8x8 PGA package above will have pin numbers 0 thru 63 assigned to
+its physical pins. It will name the pins { A1, A2, A3 ... H6, H7, H8 } using
+pinctrl_register_pins() and a suitable data set as shown earlier.
+
+In this 8x8 BGA package the pins { A8, A7, A6, A5 } can be used as an SPI port
+(these are four pins: CLK, RXD, TXD, FRM). In that case, pin B5 can be used as
+some general-purpose GPIO pin. However, in another setting, pins { A5, B5 } can
+be used as an I2C port (these are just two pins: SCL, SDA). Needless to say,
+we cannot use the SPI port and I2C port at the same time. However in the inside
+of the package the silicon performing the SPI logic can alternatively be routed
+out on pins { G4, G3, G2, G1 }.
+
+On the botton row at { A1, B1, C1, D1, E1, F1, G1, H1 } we have something
+special - it's an external MMC bus that can be 2, 4 or 8 bits wide, and it will
+consume 2, 4 or 8 pins respectively, so either { A1, B1 } are taken or
+{ A1, B1, C1, D1 } or all of them. If we use all 8 bits, we cannot use the SPI
+port on pins { G4, G3, G2, G1 } of course.
+
+This way the silicon blocks present inside the chip can be multiplexed "muxed"
+out on different pin ranges. Often contemporary SoC (systems on chip) will
+contain several I2C, SPI, SDIO/MMC, etc silicon blocks that can be routed to
+different pins by pinmux settings.
+
+Since general-purpose I/O pins (GPIO) are typically always in shortage, it is
+common to be able to use almost any pin as a GPIO pin if it is not currently
+in use by some other I/O port.
+
+
+Pinmux conventions
+==================
+
+The purpose of the pinmux functionality in the pin controller subsystem is to
+abstract and provide pinmux settings to the devices you choose to instantiate
+in your machine configuration. It is inspired by the clk, GPIO and regulator
+subsystems, so devices will request their mux setting, but it's also possible
+to request a single pin for e.g. GPIO.
+
+Definitions:
+
+- FUNCTIONS can be switched in and out by a driver residing with the pin
+  control subsystem in the drivers/pinctrl/* directory of the kernel. The
+  pin control driver knows the possible functions. In the example above you can
+  identify three pinmux functions, one for spi, one for i2c and one for mmc.
+
+- FUNCTIONS are assumed to be enumerable from zero in a one-dimensional array.
+  In this case the array could be something like: { spi0, i2c0, mmc0 }
+  for the three available functions.
+
+- FUNCTIONS have PIN GROUPS as defined on the generic level - so a certain
+  function is *always* associated with a certain set of pin groups, could
+  be just a single one, but could also be many. In the example above the
+  function i2c is associated with the pins { A5, B5 }, enumerated as
+  { 24, 25 } in the controller pin space.
+
+  The Function spi is associated with pin groups { A8, A7, A6, A5 }
+  and { G4, G3, G2, G1 }, which are enumerated as { 0, 8, 16, 24 } and
+  { 38, 46, 54, 62 } respectively.
+
+  Group names must be unique per pin controller, no two groups on the same
+  controller may have the same name.
+
+- The combination of a FUNCTION and a PIN GROUP determine a certain function
+  for a certain set of pins. The knowledge of the functions and pin groups
+  and their machine-specific particulars are kept inside the pinmux driver,
+  from the outside only the enumerators are known, and the driver core can:
+
+  - Request the name of a function with a certain selector (>= 0)
+  - A list of groups associated with a certain function
+  - Request that a certain group in that list to be activated for a certain
+    function
+
+  As already described above, pin groups are in turn self-descriptive, so
+  the core will retrieve the actual pin range in a certain group from the
+  driver.
+
+- FUNCTIONS and GROUPS on a certain PIN CONTROLLER are MAPPED to a certain
+  device by the board file, device tree or similar machine setup configuration
+  mechanism, similar to how regulators are connected to devices, usually by
+  name. Defining a pin controller, function and group thus uniquely identify
+  the set of pins to be used by a certain device. (If only one possible group
+  of pins is available for the function, no group name need to be supplied -
+  the core will simply select the first and only group available.)
+
+  In the example case we can define that this particular machine shall
+  use device spi0 with pinmux function fspi0 group gspi0 and i2c0 on function
+  fi2c0 group gi2c0, on the primary pin controller, we get mappings
+  like these:
+
+  {
+    {"map-spi0", spi0, pinctrl0, fspi0, gspi0},
+    {"map-i2c0", i2c0, pinctrl0, fi2c0, gi2c0}
+  }
+
+  Every map must be assigned a symbolic name, pin controller and function.
+  The group is not compulsory - if it is omitted the first group presented by
+  the driver as applicable for the function will be selected, which is
+  useful for simple cases.
+
+  The device name is present in map entries tied to specific devices. Maps
+  without device names are referred to as SYSTEM pinmuxes, such as can be taken
+  by the machine implementation on boot and not tied to any specific device.
+
+  It is possible to map several groups to the same combination of device,
+  pin controller and function. This is for cases where a certain function on
+  a certain pin controller may use different sets of pins in different
+  configurations.
+
+- PINS for a certain FUNCTION using a certain PIN GROUP on a certain
+  PIN CONTROLLER are provided on a first-come first-serve basis, so if some
+  other device mux setting or GPIO pin request has already taken your physical
+  pin, you will be denied the use of it. To get (activate) a new setting, the
+  old one has to be put (deactivated) first.
+
+Sometimes the documentation and hardware registers will be oriented around
+pads (or "fingers") rather than pins - these are the soldering surfaces on the
+silicon inside the package, and may or may not match the actual number of
+pins/balls underneath the capsule. Pick some enumeration that makes sense to
+you. Define enumerators only for the pins you can control if that makes sense.
+
+Assumptions:
+
+We assume that the number possible function maps to pin groups is limited by
+the hardware. I.e. we assume that there is no system where any function can be
+mapped to any pin, like in a phone exchange. So the available pins groups for
+a certain function will be limited to a few choices (say up to eight or so),
+not hundreds or any amount of choices. This is the characteristic we have found
+by inspecting available pinmux hardware, and a necessary assumption since we
+expect pinmux drivers to present *all* possible function vs pin group mappings
+to the subsystem.
+
+
+Pinmux drivers
+==============
+
+The pinmux core takes care of preventing conflicts on pins and calling
+the pin controller driver to execute different settings.
+
+It is the responsibility of the pinmux driver to impose further restrictions
+(say for example infer electronic limitations due to load etc) to determine
+whether or not the requested function can actually be allowed, and in case it
+is possible to perform the requested mux setting, poke the hardware so that
+this happens.
+
+Pinmux drivers are required to supply a few callback functions, some are
+optional. Usually the enable() and disable() functions are implemented,
+writing values into some certain registers to activate a certain mux setting
+for a certain pin.
+
+A simple driver for the above example will work by setting bits 0, 1, 2, 3 or 4
+into some register named MUX to select a certain function with a certain
+group of pins would work something like this:
+
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+
+struct foo_group {
+	const char *name;
+	const unsigned int *pins;
+	const unsigned num_pins;
+};
+
+static const unsigned spi0_0_pins[] = { 0, 8, 16, 24 };
+static const unsigned spi0_1_pins[] = { 38, 46, 54, 62 };
+static const unsigned i2c0_pins[] = { 24, 25 };
+static const unsigned mmc0_1_pins[] = { 56, 57 };
+static const unsigned mmc0_2_pins[] = { 58, 59 };
+static const unsigned mmc0_3_pins[] = { 60, 61, 62, 63 };
+
+static const struct foo_group foo_groups[] = {
+	{
+		.name = "spi0_0_grp",
+		.pins = spi0_0_pins,
+		.num_pins = ARRAY_SIZE(spi0_0_pins),
+	},
+	{
+		.name = "spi0_1_grp",
+		.pins = spi0_1_pins,
+		.num_pins = ARRAY_SIZE(spi0_1_pins),
+	},
+	{
+		.name = "i2c0_grp",
+		.pins = i2c0_pins,
+		.num_pins = ARRAY_SIZE(i2c0_pins),
+	},
+	{
+		.name = "mmc0_1_grp",
+		.pins = mmc0_1_pins,
+		.num_pins = ARRAY_SIZE(mmc0_1_pins),
+	},
+	{
+		.name = "mmc0_2_grp",
+		.pins = mmc0_2_pins,
+		.num_pins = ARRAY_SIZE(mmc0_2_pins),
+	},
+	{
+		.name = "mmc0_3_grp",
+		.pins = mmc0_3_pins,
+		.num_pins = ARRAY_SIZE(mmc0_3_pins),
+	},
+};
+
+
+static int foo_list_groups(struct pinctrl_dev *pctldev, unsigned selector)
+{
+	if (selector >= ARRAY_SIZE(foo_groups))
+		return -EINVAL;
+	return 0;
+}
+
+static const char *foo_get_group_name(struct pinctrl_dev *pctldev,
+				       unsigned selector)
+{
+	return foo_groups[selector].name;
+}
+
+static int foo_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector,
+			       unsigned ** const pins,
+			       unsigned * const num_pins)
+{
+	*pins = (unsigned *) foo_groups[selector].pins;
+	*num_pins = foo_groups[selector].num_pins;
+	return 0;
+}
+
+static struct pinctrl_ops foo_pctrl_ops = {
+	.list_groups = foo_list_groups,
+	.get_group_name = foo_get_group_name,
+	.get_group_pins = foo_get_group_pins,
+};
+
+struct foo_pmx_func {
+	const char *name;
+	const char * const *groups;
+	const unsigned num_groups;
+};
+
+static const char * const spi0_groups[] = { "spi0_1_grp" };
+static const char * const i2c0_groups[] = { "i2c0_grp" };
+static const char * const mmc0_groups[] = { "mmc0_1_grp", "mmc0_2_grp",
+					"mmc0_3_grp" };
+
+static const struct foo_pmx_func foo_functions[] = {
+	{
+		.name = "spi0",
+		.groups = spi0_groups,
+		.num_groups = ARRAY_SIZE(spi0_groups),
+	},
+	{
+		.name = "i2c0",
+		.groups = i2c0_groups,
+		.num_groups = ARRAY_SIZE(i2c0_groups),
+	},
+	{
+		.name = "mmc0",
+		.groups = mmc0_groups,
+		.num_groups = ARRAY_SIZE(mmc0_groups),
+	},
+};
+
+int foo_list_funcs(struct pinctrl_dev *pctldev, unsigned selector)
+{
+	if (selector >= ARRAY_SIZE(foo_functions))
+		return -EINVAL;
+	return 0;
+}
+
+const char *foo_get_fname(struct pinctrl_dev *pctldev, unsigned selector)
+{
+	return myfuncs[selector].name;
+}
+
+static int foo_get_groups(struct pinctrl_dev *pctldev, unsigned selector,
+			  const char * const **groups,
+			  unsigned * const num_groups)
+{
+	*groups = foo_functions[selector].groups;
+	*num_groups = foo_functions[selector].num_groups;
+	return 0;
+}
+
+int foo_enable(struct pinctrl_dev *pctldev, unsigned selector,
+		unsigned group)
+{
+	u8 regbit = (1 << group);
+
+	writeb((readb(MUX)|regbit), MUX)
+	return 0;
+}
+
+int foo_disable(struct pinctrl_dev *pctldev, unsigned selector,
+		unsigned group)
+{
+	u8 regbit = (1 << group);
+
+	writeb((readb(MUX) & ~(regbit)), MUX)
+	return 0;
+}
+
+struct pinmux_ops foo_pmxops = {
+	.list_functions = foo_list_funcs,
+	.get_function_name = foo_get_fname,
+	.get_function_groups = foo_get_groups,
+	.enable = foo_enable,
+	.disable = foo_disable,
+};
+
+/* Pinmux operations are handled by some pin controller */
+static struct pinctrl_desc foo_desc = {
+	...
+	.pctlops = &foo_pctrl_ops,
+	.pmxops = &foo_pmxops,
+};
+
+In the example activating muxing 0 and 1 at the same time setting bits
+0 and 1, uses one pin in common so they would collide.
+
+The beauty of the pinmux subsystem is that since it keeps track of all
+pins and who is using them, it will already have denied an impossible
+request like that, so the driver does not need to worry about such
+things - when it gets a selector passed in, the pinmux subsystem makes
+sure no other device or GPIO assignment is already using the selected
+pins. Thus bits 0 and 1 in the control register will never be set at the
+same time.
+
+All the above functions are mandatory to implement for a pinmux driver.
+
+
+Pinmux interaction with the GPIO subsystem
+==========================================
+
+The function list could become long, especially if you can convert every
+individual pin into a GPIO pin independent of any other pins, and then try
+the approach to define every pin as a function.
+
+In this case, the function array would become 64 entries for each GPIO
+setting and then the device functions.
+
+For this reason there is an additional function a pinmux driver can implement
+to enable only GPIO on an individual pin: .gpio_request_enable(). The same
+.free() function as for other functions is assumed to be usable also for
+GPIO pins.
+
+This function will pass in the affected GPIO range identified by the pin
+controller core, so you know which GPIO pins are being affected by the request
+operation.
+
+Alternatively it is fully allowed to use named functions for each GPIO
+pin, the pinmux_request_gpio() will attempt to obtain the function "gpioN"
+where "N" is the global GPIO pin number if no special GPIO-handler is
+registered.
+
+
+Pinmux board/machine configuration
+==================================
+
+Boards and machines define how a certain complete running system is put
+together, including how GPIOs and devices are muxed, how regulators are
+constrained and how the clock tree looks. Of course pinmux settings are also
+part of this.
+
+A pinmux config for a machine looks pretty much like a simple regulator
+configuration, so for the example array above we want to enable i2c and
+spi on the second function mapping:
+
+#include <linux/pinctrl/machine.h>
+
+static struct pinmux_map pmx_mapping[] = {
+	{
+		.ctrl_dev_name = "pinctrl.0",
+		.function = "spi0",
+		.dev_name = "foo-spi.0",
+	},
+	{
+		.ctrl_dev_name = "pinctrl.0",
+		.function = "i2c0",
+		.dev_name = "foo-i2c.0",
+	},
+	{
+		.ctrl_dev_name = "pinctrl.0",
+		.function = "mmc0",
+		.dev_name = "foo-mmc.0",
+	},
+};
+
+The dev_name here matches to the unique device name that can be used to look
+up the device struct (just like with clockdev or regulators). The function name
+must match a function provided by the pinmux driver handling this pin range.
+
+As you can see we may have several pin controllers on the system and thus
+we need to specify which one of them that contain the functions we wish
+to map. The map can also use struct device * directly, so there is no
+inherent need to use strings to specify .dev_name or .ctrl_dev_name, these
+are for the situation where you do not have a handle to the struct device *,
+for example if they are not yet instantiated or cumbersome to obtain.
+
+You register this pinmux mapping to the pinmux subsystem by simply:
+
+       ret = pinmux_register_mappings(&pmx_mapping, ARRAY_SIZE(pmx_mapping));
+
+Since the above construct is pretty common there is a helper macro to make
+it even more compact which assumes you want to use pinctrl.0 and position
+0 for mapping, for example:
+
+static struct pinmux_map pmx_mapping[] = {
+       PINMUX_MAP_PRIMARY("I2CMAP", "i2c0", "foo-i2c.0"),
+};
+
+
+Complex mappings
+================
+
+As it is possible to map a function to different groups of pins an optional
+.group can be specified like this:
+
+...
+{
+	.name = "spi0-pos-A",
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "spi0",
+	.group = "spi0_0_grp",
+	.dev_name = "foo-spi.0",
+},
+{
+	.name = "spi0-pos-B",
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "spi0",
+	.group = "spi0_1_grp",
+	.dev_name = "foo-spi.0",
+},
+...
+
+This example mapping is used to switch between two positions for spi0 at
+runtime, as described further below under the heading "Runtime pinmuxing".
+
+Further it is possible to match several groups of pins to the same function
+for a single device, say for example in the mmc0 example above, where you can
+additively expand the mmc0 bus from 2 to 4 to 8 pins. If we want to use all
+three groups for a total of 2+2+4 = 8 pins (for an 8-bit MMC bus as is the
+case), we define a mapping like this:
+
+...
+{
+	.name "2bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_0_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "4bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_0_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "4bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_1_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "8bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_0_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "8bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_1_grp",
+	.dev_name = "foo-mmc.0",
+},
+{
+	.name "8bit"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "mmc0",
+	.group = "mmc0_2_grp",
+	.dev_name = "foo-mmc.0",
+},
+...
+
+The result of grabbing this mapping from the device with something like
+this (see next paragraph):
+
+	pmx = pinmux_get(&device, "8bit");
+
+Will be that you activate all the three bottom records in the mapping at
+once. Since they share the same name, pin controller device, funcion and
+device, and since we allow multiple groups to match to a single device, they
+all get selected, and they all get enabled and disable simultaneously by the
+pinmux core.
+
+
+Pinmux requests from drivers
+============================
+
+Generally it is discouraged to let individual drivers get and enable pinmuxes.
+So if possible, handle the pinmuxes in platform code or some other place where
+you have access to all the affected struct device * pointers. In some cases
+where a driver needs to switch between different mux mappings at runtime
+this is not possible.
+
+A driver may request a certain mux to be activated, usually just the default
+mux like this:
+
+#include <linux/pinctrl/pinmux.h>
+
+struct foo_state {
+       struct pinmux *pmx;
+       ...
+};
+
+foo_probe()
+{
+	/* Allocate a state holder named "state" etc */
+	struct pinmux pmx;
+
+	pmx = pinmux_get(&device, NULL);
+	if IS_ERR(pmx)
+		return PTR_ERR(pmx);
+	pinmux_enable(pmx);
+
+	state->pmx = pmx;
+}
+
+foo_remove()
+{
+	pinmux_disable(state->pmx);
+	pinmux_put(state->pmx);
+}
+
+If you want to grab a specific mux mapping and not just the first one found for
+this device you can specify a specific mapping name, for example in the above
+example the second i2c0 setting: pinmux_get(&device, "spi0-pos-B");
+
+This get/enable/disable/put sequence can just as well be handled by bus drivers
+if you don't want each and every driver to handle it and you know the
+arrangement on your bus.
+
+The semantics of the get/enable respective disable/put is as follows:
+
+- pinmux_get() is called in process context to reserve the pins affected with
+  a certain mapping and set up the pinmux core and the driver. It will allocate
+  a struct from the kernel memory to hold the pinmux state.
+
+- pinmux_enable()/pinmux_disable() is quick and can be called from fastpath
+  (irq context) when you quickly want to set up/tear down the hardware muxing
+  when running a device driver. Usually it will just poke some values into a
+  register.
+
+- pinmux_disable() is called in process context to tear down the pin requests
+  and release the state holder struct for the mux setting.
+
+Usually the pinmux core handled the get/put pair and call out to the device
+drivers bookkeeping operations, like checking available functions and the
+associated pins, whereas the enable/disable pass on to the pin controller
+driver which takes care of activating and/or deactivating the mux setting by
+quickly poking some registers.
+
+The pins are allocated for your device when you issue the pinmux_get() call,
+after this you should be able to see this in the debugfs listing of all pins.
+
+
+System pinmux hogging
+=====================
+
+A system pinmux map entry, i.e. a pinmux setting that does not have a device
+associated with it, can be hogged by the core when the pin controller is
+registered. This means that the core will attempt to call pinmux_get() and
+pinmux_enable() on it immediately after the pin control device has been
+registered.
+
+This is enabled by simply setting the .hog_on_boot field in the map to true,
+like this:
+
+{
+	.name "POWERMAP"
+	.ctrl_dev_name = "pinctrl.0",
+	.function = "power_func",
+	.hog_on_boot = true,
+},
+
+Since it may be common to request the core to hog a few always-applicable
+mux settings on the primary pin controller, there is a convenience macro for
+this:
+
+PINMUX_MAP_PRIMARY_SYS_HOG("POWERMAP", "power_func")
+
+This gives the exact same result as the above construction.
+
+
+Runtime pinmuxing
+=================
+
+It is possible to mux a certain function in and out at runtime, say to move
+an SPI port from one set of pins to another set of pins. Say for example for
+spi0 in the example above, we expose two different groups of pins for the same
+function, but with different named in the mapping as described under
+"Advanced mapping" above. So we have two mappings named "spi0-pos-A" and
+"spi0-pos-B".
+
+This snippet first muxes the function in the pins defined by group A, enables
+it, disables and releases it, and muxes it in on the pins defined by group B:
+
+foo_switch()
+{
+	struct pinmux pmx;
+
+	/* Enable on position A */
+	pmx = pinmux_get(&device, "spi0-pos-A");
+	if IS_ERR(pmx)
+		return PTR_ERR(pmx);
+	pinmux_enable(pmx);
+
+	/* This releases the pins again */
+	pinmux_disable(pmx);
+	pinmux_put(pmx);
+
+	/* Enable on position B */
+	pmx = pinmux_get(&device, "spi0-pos-B");
+	if IS_ERR(pmx)
+		return PTR_ERR(pmx);
+	pinmux_enable(pmx);
+	...
+}
+
+The above has to be done from process context.

Documentation/power/00-INDEX

@@ -26,6 +26,8 @@ s2ram.txt
 	- How to get suspend to ram working (and debug it when it isn't)
 states.txt
 	- System power management states
+suspend-and-cpuhotplug.txt
+	- Explains the interaction between Suspend-to-RAM (S3) and CPU hotplug
 swsusp-and-swap-files.txt
 	- Using swap files with software suspend (to disk)
 swsusp-dmcrypt.txt

Documentation/power/basic-pm-debugging.txt

@@ -173,7 +173,7 @@ kernel messages using the serial console.  This may provide you with some
 information about the reasons of the suspend (resume) failure.  Alternatively,
 it may be possible to use a FireWire port for debugging with firescope
 (ftp://ftp.firstfloor.org/pub/ak/firescope/).  On x86 it is also possible to
-use the PM_TRACE mechanism documented in Documentation/s2ram.txt .
+use the PM_TRACE mechanism documented in Documentation/power/s2ram.txt .
 
 2. Testing suspend to RAM (STR)
 
@@ -201,3 +201,27 @@ case, you may be able to search for failing drivers by following the procedure
 analogous to the one described in section 1.  If you find some failing drivers,
 you will have to unload them every time before an STR transition (ie. before
 you run s2ram), and please report the problems with them.
+
+There is a debugfs entry which shows the suspend to RAM statistics. Here is an
+example of its output.
+	# mount -t debugfs none /sys/kernel/debug
+	# cat /sys/kernel/debug/suspend_stats
+	success: 20
+	fail: 5
+	failed_freeze: 0
+	failed_prepare: 0
+	failed_suspend: 5
+	failed_suspend_noirq: 0
+	failed_resume: 0
+	failed_resume_noirq: 0
+	failures:
+	  last_failed_dev:	alarm
+				adc
+	  last_failed_errno:	-16
+				-16
+	  last_failed_step:	suspend
+				suspend
+Field success means the success number of suspend to RAM, and field fail means
+the failure number. Others are the failure number of different steps of suspend
+to RAM. suspend_stats just lists the last 2 failed devices, error number and
+failed step of suspend.

Documentation/power/devices.txt

@@ -152,7 +152,9 @@ try to use its wakeup mechanism.  device_set_wakeup_enable() affects this flag;
 for the most part drivers should not change its value.  The initial value of
 should_wakeup is supposed to be false for the majority of devices; the major
 exceptions are power buttons, keyboards, and Ethernet adapters whose WoL
-(wake-on-LAN) feature has been set up with ethtool.
+(wake-on-LAN) feature has been set up with ethtool.  It should also default
+to true for devices that don't generate wakeup requests on their own but merely
+forward wakeup requests from one bus to another (like PCI bridges).
 
 Whether or not a device is capable of issuing wakeup events is a hardware
 matter, and the kernel is responsible for keeping track of it.  By contrast,
@@ -279,10 +281,6 @@ When the system goes into the standby or memory sleep state, the phases are:
 	time.)  Unlike the other suspend-related phases, during the prepare
 	phase the device tree is traversed top-down.
 
-	In addition to that, if device drivers need to allocate additional
-	memory to be able to hadle device suspend correctly, that should be
-	done in the prepare phase.
-
 	After the prepare callback method returns, no new children may be
 	registered below the device.  The method may also prepare the device or
 	driver in some way for the upcoming system power transition (for

Documentation/power/pm_qos_interface.txt

@@ -4,14 +4,19 @@ This interface provides a kernel and user mode interface for registering
 performance expectations by drivers, subsystems and user space applications on
 one of the parameters.
 
-Currently we have {cpu_dma_latency, network_latency, network_throughput} as the
-initial set of pm_qos parameters.
+Two different PM QoS frameworks are available:
+1. PM QoS classes for cpu_dma_latency, network_latency, network_throughput.
+2. the per-device PM QoS framework provides the API to manage the per-device latency
+constraints.
 
 Each parameters have defined units:
  * latency: usec
  * timeout: usec
  * throughput: kbs (kilo bit / sec)
 
+
+1. PM QoS framework
+
 The infrastructure exposes multiple misc device nodes one per implemented
 parameter.  The set of parameters implement is defined by pm_qos_power_init()
 and pm_qos_params.h.  This is done because having the available parameters
@@ -23,14 +28,18 @@ an aggregated target value.  The aggregated target value is updated with
 changes to the request list or elements of the list.  Typically the
 aggregated target value is simply the max or min of the request values held
 in the parameter list elements.
+Note: the aggregated target value is implemented as an atomic variable so that
+reading the aggregated value does not require any locking mechanism.
+
 
 From kernel mode the use of this interface is simple:
 
-handle = pm_qos_add_request(param_class, target_value):
-Will insert an element into the list for that identified PM_QOS class with the
+void pm_qos_add_request(handle, param_class, target_value):
+Will insert an element into the list for that identified PM QoS class with the
 target value.  Upon change to this list the new target is recomputed and any
 registered notifiers are called only if the target value is now different.
-Clients of pm_qos need to save the returned handle.
+Clients of pm_qos need to save the returned handle for future use in other
+pm_qos API functions.
 
 void pm_qos_update_request(handle, new_target_value):
 Will update the list element pointed to by the handle with the new target value
@@ -42,6 +51,20 @@ Will remove the element.  After removal it will update the aggregate target and
 call the notification tree if the target was changed as a result of removing
 the request.
 
+int pm_qos_request(param_class):
+Returns the aggregated value for a given PM QoS class.
+
+int pm_qos_request_active(handle):
+Returns if the request is still active, i.e. it has not been removed from a
+PM QoS class constraints list.
+
+int pm_qos_add_notifier(param_class, notifier):
+Adds a notification callback function to the PM QoS class. The callback is
+called when the aggregated value for the PM QoS class is changed.
+
+int pm_qos_remove_notifier(int param_class, notifier):
+Removes the notification callback function for the PM QoS class.
+
 
 From user mode:
 Only processes can register a pm_qos request.  To provide for automatic
@@ -63,4 +86,63 @@ To remove the user mode request for a target value simply close the device
 node.
 
 
+2. PM QoS per-device latency framework
+
+For each device a list of performance requests is maintained along with
+an aggregated target value.  The aggregated target value is updated with
+changes to the request list or elements of the list.  Typically the
+aggregated target value is simply the max or min of the request values held
+in the parameter list elements.
+Note: the aggregated target value is implemented as an atomic variable so that
+reading the aggregated value does not require any locking mechanism.
+
+
+From kernel mode the use of this interface is the following:
+
+int dev_pm_qos_add_request(device, handle, value):
+Will insert an element into the list for that identified device with the
+target value.  Upon change to this list the new target is recomputed and any
+registered notifiers are called only if the target value is now different.
+Clients of dev_pm_qos need to save the handle for future use in other
+dev_pm_qos API functions.
+
+int dev_pm_qos_update_request(handle, new_value):
+Will update the list element pointed to by the handle with the new target value
+and recompute the new aggregated target, calling the notification trees if the
+target is changed.
+
+int dev_pm_qos_remove_request(handle):
+Will remove the element.  After removal it will update the aggregate target and
+call the notification trees if the target was changed as a result of removing
+the request.
+
+s32 dev_pm_qos_read_value(device):
+Returns the aggregated value for a given device's constraints list.
+
+
+Notification mechanisms:
+The per-device PM QoS framework has 2 different and distinct notification trees:
+a per-device notification tree and a global notification tree.
+
+int dev_pm_qos_add_notifier(device, notifier):
+Adds a notification callback function for the device.
+The callback is called when the aggregated value of the device constraints list
+is changed.
+
+int dev_pm_qos_remove_notifier(device, notifier):
+Removes the notification callback function for the device.
+
+int dev_pm_qos_add_global_notifier(notifier):
+Adds a notification callback function in the global notification tree of the
+framework.
+The callback is called when the aggregated value for any device is changed.
+
+int dev_pm_qos_remove_global_notifier(notifier):
+Removes the notification callback function from the global notification tree
+of the framework.
+
+
+From user mode:
+No API for user space access to the per-device latency constraints is provided
+yet - still under discussion.
 

Documentation/power/runtime_pm.txt

@@ -43,13 +43,18 @@ struct dev_pm_ops {
 	...
 };
 
-The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks are
-executed by the PM core for either the device type, or the class (if the device
-type's struct dev_pm_ops object does not exist), or the bus type (if the
-device type's and class' struct dev_pm_ops objects do not exist) of the given
-device (this allows device types to override callbacks provided by bus types or
-classes if necessary).  The bus type, device type and class callbacks are
-referred to as subsystem-level callbacks in what follows.
+The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks
+are executed by the PM core for either the power domain, or the device type
+(if the device power domain's struct dev_pm_ops does not exist), or the class
+(if the device power domain's and type's struct dev_pm_ops object does not
+exist), or the bus type (if the device power domain's, type's and class'
+struct dev_pm_ops objects do not exist) of the given device, so the priority
+order of callbacks from high to low is that power domain callbacks, device
+type callbacks, class callbacks and bus type callbacks, and the high priority
+one will take precedence over low priority one. The bus type, device type and
+class callbacks are referred to as subsystem-level callbacks in what follows,
+and generally speaking, the power domain callbacks are used for representing
+power domains within a SoC.
 
 By default, the callbacks are always invoked in process context with interrupts
 enabled.  However, subsystems can use the pm_runtime_irq_safe() helper function
@@ -477,12 +482,14 @@ pm_runtime_autosuspend_expiration()
 If pm_runtime_irq_safe() has been called for a device then the following helper
 functions may also be used in interrupt context:
 
+pm_runtime_idle()
 pm_runtime_suspend()
 pm_runtime_autosuspend()
 pm_runtime_resume()
 pm_runtime_get_sync()
 pm_runtime_put_sync()
 pm_runtime_put_sync_suspend()
+pm_runtime_put_sync_autosuspend()
 
 5. Runtime PM Initialization, Device Probing and Removal
 

Documentation/power/suspend-and-cpuhotplug.txt

@@ -0,0 +1,275 @@
+Interaction of Suspend code (S3) with the CPU hotplug infrastructure
+
+     (C) 2011 Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
+
+
+I. How does the regular CPU hotplug code differ from how the Suspend-to-RAM
+   infrastructure uses it internally? And where do they share common code?
+
+Well, a picture is worth a thousand words... So ASCII art follows :-)
+
+[This depicts the current design in the kernel, and focusses only on the
+interactions involving the freezer and CPU hotplug and also tries to explain
+the locking involved. It outlines the notifications involved as well.
+But please note that here, only the call paths are illustrated, with the aim
+of describing where they take different paths and where they share code.
+What happens when regular CPU hotplug and Suspend-to-RAM race with each other
+is not depicted here.]
+
+On a high level, the suspend-resume cycle goes like this:
+
+|Freeze| -> |Disable nonboot| -> |Do suspend| -> |Enable nonboot| -> |Thaw |
+|tasks |    |     cpus      |    |          |    |     cpus     |    |tasks|
+
+
+More details follow:
+
+                                Suspend call path
+                                -----------------
+
+                                  Write 'mem' to
+                                /sys/power/state
+                                    syfs file
+                                        |
+                                        v
+                               Acquire pm_mutex lock
+                                        |
+                                        v
+                             Send PM_SUSPEND_PREPARE
+                                   notifications
+                                        |
+                                        v
+                                   Freeze tasks
+                                        |
+                                        |
+                                        v
+                              disable_nonboot_cpus()
+                                   /* start */
+                                        |
+                                        v
+                            Acquire cpu_add_remove_lock
+                                        |
+                                        v
+                             Iterate over CURRENTLY
+                                   online CPUs
+                                        |
+                                        |
+                                        |                ----------
+                                        v                          | L
+             ======>               _cpu_down()                     |
+            |              [This takes cpuhotplug.lock             |
+  Common    |               before taking down the CPU             |
+   code     |               and releases it when done]             | O
+            |            While it is at it, notifications          |
+            |            are sent when notable events occur,       |
+             ======>     by running all registered callbacks.      |
+                                        |                          | O
+                                        |                          |
+                                        |                          |
+                                        v                          |
+                            Note down these cpus in                | P
+                                frozen_cpus mask         ----------
+                                        |
+                                        v
+                           Disable regular cpu hotplug
+                        by setting cpu_hotplug_disabled=1
+                                        |
+                                        v
+                            Release cpu_add_remove_lock
+                                        |
+                                        v
+                       /* disable_nonboot_cpus() complete */
+                                        |
+                                        v
+                                   Do suspend
+
+
+
+Resuming back is likewise, with the counterparts being (in the order of
+execution during resume):
+* enable_nonboot_cpus() which involves:
+   |  Acquire cpu_add_remove_lock
+   |  Reset cpu_hotplug_disabled to 0, thereby enabling regular cpu hotplug
+   |  Call _cpu_up() [for all those cpus in the frozen_cpus mask, in a loop]
+   |  Release cpu_add_remove_lock
+   v
+
+* thaw tasks
+* send PM_POST_SUSPEND notifications
+* Release pm_mutex lock.
+
+
+It is to be noted here that the pm_mutex lock is acquired at the very
+beginning, when we are just starting out to suspend, and then released only
+after the entire cycle is complete (i.e., suspend + resume).
+
+
+
+                          Regular CPU hotplug call path
+                          -----------------------------
+
+                                Write 0 (or 1) to
+                       /sys/devices/system/cpu/cpu*/online
+                                    sysfs file
+                                        |
+                                        |
+                                        v
+                                    cpu_down()
+                                        |
+                                        v
+                           Acquire cpu_add_remove_lock
+                                        |
+                                        v
+                          If cpu_hotplug_disabled is 1
+                                return gracefully
+                                        |
+                                        |
+                                        v
+             ======>                _cpu_down()
+            |              [This takes cpuhotplug.lock
+  Common    |               before taking down the CPU
+   code     |               and releases it when done]
+            |            While it is at it, notifications
+            |           are sent when notable events occur,
+             ======>    by running all registered callbacks.
+                                        |
+                                        |
+                                        v
+                          Release cpu_add_remove_lock
+                               [That's it!, for
+                              regular CPU hotplug]
+
+
+
+So, as can be seen from the two diagrams (the parts marked as "Common code"),
+regular CPU hotplug and the suspend code path converge at the _cpu_down() and
+_cpu_up() functions. They differ in the arguments passed to these functions,
+in that during regular CPU hotplug, 0 is passed for the 'tasks_frozen'
+argument. But during suspend, since the tasks are already frozen by the time
+the non-boot CPUs are offlined or onlined, the _cpu_*() functions are called
+with the 'tasks_frozen' argument set to 1.
+[See below for some known issues regarding this.]
+
+
+Important files and functions/entry points:
+------------------------------------------
+
+kernel/power/process.c : freeze_processes(), thaw_processes()
+kernel/power/suspend.c : suspend_prepare(), suspend_enter(), suspend_finish()
+kernel/cpu.c: cpu_[up|down](), _cpu_[up|down](), [disable|enable]_nonboot_cpus()
+
+
+
+II. What are the issues involved in CPU hotplug?
+    -------------------------------------------
+
+There are some interesting situations involving CPU hotplug and microcode
+update on the CPUs, as discussed below:
+
+[Please bear in mind that the kernel requests the microcode images from
+userspace, using the request_firmware() function defined in
+drivers/base/firmware_class.c]
+
+
+a. When all the CPUs are identical:
+
+   This is the most common situation and it is quite straightforward: we want
+   to apply the same microcode revision to each of the CPUs.
+   To give an example of x86, the collect_cpu_info() function defined in
+   arch/x86/kernel/microcode_core.c helps in discovering the type of the CPU
+   and thereby in applying the correct microcode revision to it.
+   But note that the kernel does not maintain a common microcode image for the
+   all CPUs, in order to handle case 'b' described below.
+
+
+b. When some of the CPUs are different than the rest:
+
+   In this case since we probably need to apply different microcode revisions
+   to different CPUs, the kernel maintains a copy of the correct microcode
+   image for each CPU (after appropriate CPU type/model discovery using
+   functions such as collect_cpu_info()).
+
+
+c. When a CPU is physically hot-unplugged and a new (and possibly different
+   type of) CPU is hot-plugged into the system:
+
+   In the current design of the kernel, whenever a CPU is taken offline during
+   a regular CPU hotplug operation, upon receiving the CPU_DEAD notification
+   (which is sent by the CPU hotplug code), the microcode update driver's
+   callback for that event reacts by freeing the kernel's copy of the
+   microcode image for that CPU.
+
+   Hence, when a new CPU is brought online, since the kernel finds that it
+   doesn't have the microcode image, it does the CPU type/model discovery
+   afresh and then requests the userspace for the appropriate microcode image
+   for that CPU, which is subsequently applied.
+
+   For example, in x86, the mc_cpu_callback() function (which is the microcode
+   update driver's callback registered for CPU hotplug events) calls
+   microcode_update_cpu() which would call microcode_init_cpu() in this case,
+   instead of microcode_resume_cpu() when it finds that the kernel doesn't
+   have a valid microcode image. This ensures that the CPU type/model
+   discovery is performed and the right microcode is applied to the CPU after
+   getting it from userspace.
+
+
+d. Handling microcode update during suspend/hibernate:
+
+   Strictly speaking, during a CPU hotplug operation which does not involve
+   physically removing or inserting CPUs, the CPUs are not actually powered
+   off during a CPU offline. They are just put to the lowest C-states possible.
+   Hence, in such a case, it is not really necessary to re-apply microcode
+   when the CPUs are brought back online, since they wouldn't have lost the
+   image during the CPU offline operation.
+
+   This is the usual scenario encountered during a resume after a suspend.
+   However, in the case of hibernation, since all the CPUs are completely
+   powered off, during restore it becomes necessary to apply the microcode
+   images to all the CPUs.
+
+   [Note that we don't expect someone to physically pull out nodes and insert
+   nodes with a different type of CPUs in-between a suspend-resume or a
+   hibernate/restore cycle.]
+
+   In the current design of the kernel however, during a CPU offline operation
+   as part of the suspend/hibernate cycle (the CPU_DEAD_FROZEN notification),
+   the existing copy of microcode image in the kernel is not freed up.
+   And during the CPU online operations (during resume/restore), since the
+   kernel finds that it already has copies of the microcode images for all the
+   CPUs, it just applies them to the CPUs, avoiding any re-discovery of CPU
+   type/model and the need for validating whether the microcode revisions are
+   right for the CPUs or not (due to the above assumption that physical CPU
+   hotplug will not be done in-between suspend/resume or hibernate/restore
+   cycles).
+
+
+III. Are there any known problems when regular CPU hotplug and suspend race
+     with each other?
+
+Yes, they are listed below:
+
+1. When invoking regular CPU hotplug, the 'tasks_frozen' argument passed to
+   the _cpu_down() and _cpu_up() functions is *always* 0.
+   This might not reflect the true current state of the system, since the
+   tasks could have been frozen by an out-of-band event such as a suspend
+   operation in progress. Hence, it will lead to wrong notifications being
+   sent during the cpu online/offline events (eg, CPU_ONLINE notification
+   instead of CPU_ONLINE_FROZEN) which in turn will lead to execution of
+   inappropriate code by the callbacks registered for such CPU hotplug events.
+
+2. If a regular CPU hotplug stress test happens to race with the freezer due
+   to a suspend operation in progress at the same time, then we could hit the
+   situation described below:
+
+    * A regular cpu online operation continues its journey from userspace
+      into the kernel, since the freezing has not yet begun.
+    * Then freezer gets to work and freezes userspace.
+    * If cpu online has not yet completed the microcode update stuff by now,
+      it will now start waiting on the frozen userspace in the
+      TASK_UNINTERRUPTIBLE state, in order to get the microcode image.
+    * Now the freezer continues and tries to freeze the remaining tasks. But
+      due to this wait mentioned above, the freezer won't be able to freeze
+      the cpu online hotplug task and hence freezing of tasks fails.
+
+   As a result of this task freezing failure, the suspend operation gets
+   aborted.

Documentation/power/userland-swsusp.txt

@@ -77,7 +77,8 @@ SNAPSHOT_SET_SWAP_AREA - set the resume partition and the offset (in <PAGE_SIZE>
 	resume_swap_area, as defined in kernel/power/suspend_ioctls.h,
 	containing the resume device specification and the offset); for swap
 	partitions the offset is always 0, but it is different from zero for
-	swap files (see Documentation/swsusp-and-swap-files.txt for details).
+	swap files (see Documentation/power/swsusp-and-swap-files.txt for
+	details).
 
 SNAPSHOT_PLATFORM_SUPPORT - enable/disable the hibernation platform support,
 	depending on the argument value (enable, if the argument is nonzero)

Documentation/rfkill.txt

@@ -117,5 +117,4 @@ The contents of these variables corresponds to the "name", "state" and
 "type" sysfs files explained above.
 
 
-For further details consult Documentation/ABI/stable/dev-rfkill and
-Documentation/ABI/stable/sysfs-class-rfkill.
+For further details consult Documentation/ABI/stable/sysfs-class-rfkill.

Documentation/scheduler/sched-bwc.txt

@@ -0,0 +1,122 @@
+CFS Bandwidth Control
+=====================
+
+[ This document only discusses CPU bandwidth control for SCHED_NORMAL.
+  The SCHED_RT case is covered in Documentation/scheduler/sched-rt-group.txt ]
+
+CFS bandwidth control is a CONFIG_FAIR_GROUP_SCHED extension which allows the
+specification of the maximum CPU bandwidth available to a group or hierarchy.
+
+The bandwidth allowed for a group is specified using a quota and period. Within
+each given "period" (microseconds), a group is allowed to consume only up to
+"quota" microseconds of CPU time.  When the CPU bandwidth consumption of a
+group exceeds this limit (for that period), the tasks belonging to its
+hierarchy will be throttled and are not allowed to run again until the next
+period.
+
+A group's unused runtime is globally tracked, being refreshed with quota units
+above at each period boundary.  As threads consume this bandwidth it is
+transferred to cpu-local "silos" on a demand basis.  The amount transferred
+within each of these updates is tunable and described as the "slice".
+
+Management
+----------
+Quota and period are managed within the cpu subsystem via cgroupfs.
+
+cpu.cfs_quota_us: the total available run-time within a period (in microseconds)
+cpu.cfs_period_us: the length of a period (in microseconds)
+cpu.stat: exports throttling statistics [explained further below]
+
+The default values are:
+	cpu.cfs_period_us=100ms
+	cpu.cfs_quota=-1
+
+A value of -1 for cpu.cfs_quota_us indicates that the group does not have any
+bandwidth restriction in place, such a group is described as an unconstrained
+bandwidth group.  This represents the traditional work-conserving behavior for
+CFS.
+
+Writing any (valid) positive value(s) will enact the specified bandwidth limit.
+The minimum quota allowed for the quota or period is 1ms.  There is also an
+upper bound on the period length of 1s.  Additional restrictions exist when
+bandwidth limits are used in a hierarchical fashion, these are explained in
+more detail below.
+
+Writing any negative value to cpu.cfs_quota_us will remove the bandwidth limit
+and return the group to an unconstrained state once more.
+
+Any updates to a group's bandwidth specification will result in it becoming
+unthrottled if it is in a constrained state.
+
+System wide settings
+--------------------
+For efficiency run-time is transferred between the global pool and CPU local
+"silos" in a batch fashion.  This greatly reduces global accounting pressure
+on large systems.  The amount transferred each time such an update is required
+is described as the "slice".
+
+This is tunable via procfs:
+	/proc/sys/kernel/sched_cfs_bandwidth_slice_us (default=5ms)
+
+Larger slice values will reduce transfer overheads, while smaller values allow
+for more fine-grained consumption.
+
+Statistics
+----------
+A group's bandwidth statistics are exported via 3 fields in cpu.stat.
+
+cpu.stat:
+- nr_periods: Number of enforcement intervals that have elapsed.
+- nr_throttled: Number of times the group has been throttled/limited.
+- throttled_time: The total time duration (in nanoseconds) for which entities
+  of the group have been throttled.
+
+This interface is read-only.
+
+Hierarchical considerations
+---------------------------
+The interface enforces that an individual entity's bandwidth is always
+attainable, that is: max(c_i) <= C. However, over-subscription in the
+aggregate case is explicitly allowed to enable work-conserving semantics
+within a hierarchy.
+  e.g. \Sum (c_i) may exceed C
+[ Where C is the parent's bandwidth, and c_i its children ]
+
+
+There are two ways in which a group may become throttled:
+	a. it fully consumes its own quota within a period
+	b. a parent's quota is fully consumed within its period
+
+In case b) above, even though the child may have runtime remaining it will not
+be allowed to until the parent's runtime is refreshed.
+
+Examples
+--------
+1. Limit a group to 1 CPU worth of runtime.
+
+	If period is 250ms and quota is also 250ms, the group will get
+	1 CPU worth of runtime every 250ms.
+
+	# echo 250000 > cpu.cfs_quota_us /* quota = 250ms */
+	# echo 250000 > cpu.cfs_period_us /* period = 250ms */
+
+2. Limit a group to 2 CPUs worth of runtime on a multi-CPU machine.
+
+	With 500ms period and 1000ms quota, the group can get 2 CPUs worth of
+	runtime every 500ms.
+
+	# echo 1000000 > cpu.cfs_quota_us /* quota = 1000ms */
+	# echo 500000 > cpu.cfs_period_us /* period = 500ms */
+
+	The larger period here allows for increased burst capacity.
+
+3. Limit a group to 20% of 1 CPU.
+
+	With 50ms period, 10ms quota will be equivalent to 20% of 1 CPU.
+
+	# echo 10000 > cpu.cfs_quota_us /* quota = 10ms */
+	# echo 50000 > cpu.cfs_period_us /* period = 50ms */
+
+	By using a small period here we are ensuring a consistent latency
+	response at the expense of burst capacity.
+

Documentation/scsi/aic7xxx_old.txt

@@ -444,7 +444,7 @@ linux-1.1.x and fairly stable since linux-1.2.x, and are also in FreeBSD
   Kernel Compile options
   ------------------------------
     The various kernel compile time options for this driver are now fairly
-    well documented in the file Documentation/Configure.help.  In order to
+    well documented in the file drivers/scsi/Kconfig.  In order to
     see this documentation, you need to use one of the advanced configuration
     programs (menuconfig and xconfig).  If you are using the "make menuconfig"
     method of configuring your kernel, then you would simply highlight the

Documentation/scsi/scsi_mid_low_api.txt

@@ -55,11 +55,6 @@ or in the same directory as the C source code. For example to find a url
 about the USB mass storage driver see the 
 /usr/src/linux/drivers/usb/storage directory.
 
-The Linux kernel source Documentation/DocBook/scsidrivers.tmpl file
-refers to this file. With the appropriate DocBook tool-set, this permits
-users to generate html, ps and pdf renderings of information within this
-file (e.g. the interface functions).
-
 Driver structure
 ================
 Traditionally an LLD for the SCSI subsystem has been at least two files in

Documentation/security/keys-trusted-encrypted.txt

@@ -156,4 +156,5 @@ Load an encrypted key "evm" from saved blob:
 Other uses for trusted and encrypted keys, such as for disk and file encryption
 are anticipated.  In particular the new format 'ecryptfs' has been defined in
 in order to use encrypted keys to mount an eCryptfs filesystem.  More details
-about the usage can be found in the file 'Documentation/keys-ecryptfs.txt'.
+about the usage can be found in the file
+'Documentation/security/keys-ecryptfs.txt'.

Documentation/serial/serial-rs485.txt

@@ -28,6 +28,10 @@
    RS485 communications. This data structure is used to set and configure RS485
    parameters in the platform data and in ioctls.
 
+   The device tree can also provide RS485 boot time parameters (see [2]
+   for bindings). The driver is in charge of filling this data structure from
+   the values given by the device tree.
+
    Any driver for devices capable of working both as RS232 and RS485 should
    provide at least the following ioctls:
 
@@ -104,6 +108,9 @@
 	rs485conf.flags |= SER_RS485_RTS_AFTER_SEND;
 	rs485conf.delay_rts_after_send = ...;
 
+	/* Set this flag if you want to receive data even whilst sending data */
+	rs485conf.flags |= SER_RS485_RX_DURING_TX;
+
 	if (ioctl (fd, TIOCSRS485, &rs485conf) < 0) {
 		/* Error handling. See errno. */
 	}
@@ -118,3 +125,4 @@
 5. REFERENCES
 
  [1]	include/linux/serial.h
+ [2]	Documentation/devicetree/bindings/serial/rs485.txt

Documentation/sound/oss/PAS16

@@ -60,8 +60,7 @@ With PAS16 you can use two audio device files at the same time. /dev/dsp (and
 
 The new stuff for 2.3.99 and later
 ============================================================================
-The following configuration options from Documentation/Configure.help
-are relevant to configuring the PAS16:
+The following configuration options are relevant to configuring the PAS16:
 
 Sound card support
 CONFIG_SOUND

Documentation/spi/pxa2xx

@@ -2,7 +2,7 @@ PXA2xx SPI on SSP driver HOWTO
 ===================================================
 This a mini howto on the pxa2xx_spi driver.  The driver turns a PXA2xx
 synchronous serial port into a SPI master controller
-(see Documentation/spi/spi_summary). The driver has the following features
+(see Documentation/spi/spi-summary). The driver has the following features
 
 - Support for any PXA2xx SSP
 - SSP PIO and SSP DMA data transfers.
@@ -85,7 +85,7 @@ Declaring Slave Devices
 -----------------------
 Typically each SPI slave (chip) is defined in the arch/.../mach-*/board-*.c
 using the "spi_board_info" structure found in "linux/spi/spi.h". See
-"Documentation/spi/spi_summary" for additional information.
+"Documentation/spi/spi-summary" for additional information.
 
 Each slave device attached to the PXA must provide slave specific configuration
 information via the structure "pxa2xx_spi_chip" found in

Documentation/stable_kernel_rules.txt

@@ -24,10 +24,10 @@ Rules on what kind of patches are accepted, and which ones are not, into the
 Procedure for submitting patches to the -stable tree:
 
  - Send the patch, after verifying that it follows the above rules, to
-   stable@kernel.org.  You must note the upstream commit ID in the changelog
-   of your submission.
+   stable@vger.kernel.org.  You must note the upstream commit ID in the
+   changelog of your submission.
  - To have the patch automatically included in the stable tree, add the tag
-     Cc: stable@kernel.org
+     Cc: stable@vger.kernel.org
    in the sign-off area. Once the patch is merged it will be applied to
    the stable tree without anything else needing to be done by the author
    or subsystem maintainer.
@@ -35,10 +35,10 @@ Procedure for submitting patches to the -stable tree:
    cherry-picked than this can be specified in the following format in
    the sign-off area:
 
-     Cc: <stable@kernel.org> # .32.x: a1f84a3: sched: Check for idle
-     Cc: <stable@kernel.org> # .32.x: 1b9508f: sched: Rate-limit newidle
-     Cc: <stable@kernel.org> # .32.x: fd21073: sched: Fix affinity logic
-     Cc: <stable@kernel.org> # .32.x
+     Cc: <stable@vger.kernel.org> # .32.x: a1f84a3: sched: Check for idle
+     Cc: <stable@vger.kernel.org> # .32.x: 1b9508f: sched: Rate-limit newidle
+     Cc: <stable@vger.kernel.org> # .32.x: fd21073: sched: Fix affinity logic
+     Cc: <stable@vger.kernel.org> # .32.x
     Signed-off-by: Ingo Molnar <mingo@elte.hu>
 
    The tag sequence has the meaning of:

Documentation/timers/highres.txt

@@ -30,7 +30,7 @@ hrtimer base infrastructure
 ---------------------------
 
 The hrtimer base infrastructure was merged into the 2.6.16 kernel. Details of
-the base implementation are covered in Documentation/hrtimers/hrtimer.txt. See
+the base implementation are covered in Documentation/timers/hrtimers.txt. See
 also figure #2 (OLS slides p. 15)
 
 The main differences to the timer wheel, which holds the armed timer_list type

Documentation/usb/dma.txt

@@ -7,7 +7,7 @@ API OVERVIEW
 
 The big picture is that USB drivers can continue to ignore most DMA issues,
 though they still must provide DMA-ready buffers (see
-Documentation/PCI/PCI-DMA-mapping.txt).  That's how they've worked through
+Documentation/DMA-API-HOWTO.txt).  That's how they've worked through
 the 2.4 (and earlier) kernels.
 
 OR:  they can now be DMA-aware.
@@ -57,7 +57,7 @@ and effects like cache-trashing can impose subtle penalties.
   force a consistent memory access ordering by using memory barriers.  It's
   not using a streaming DMA mapping, so it's good for small transfers on
   systems where the I/O would otherwise thrash an IOMMU mapping.  (See
-  Documentation/PCI/PCI-DMA-mapping.txt for definitions of "coherent" and
+  Documentation/DMA-API-HOWTO.txt for definitions of "coherent" and
   "streaming" DMA mappings.)
 
   Asking for 1/Nth of a page (as well as asking for N pages) is reasonably
@@ -88,7 +88,7 @@ WORKING WITH EXISTING BUFFERS
 Existing buffers aren't usable for DMA without first being mapped into the
 DMA address space of the device.  However, most buffers passed to your
 driver can safely be used with such DMA mapping.  (See the first section
-of Documentation/PCI/PCI-DMA-mapping.txt, titled "What memory is DMA-able?")
+of Documentation/DMA-API-HOWTO.txt, titled "What memory is DMA-able?")
 
 - When you're using scatterlists, you can map everything at once.  On some
   systems, this kicks in an IOMMU and turns the scatterlists into single

Documentation/usb/dwc3.txt

@@ -0,0 +1,45 @@
+
+ TODO
+~~~~~~
+Please pick something while reading :)
+
+- Convert interrupt handler to per-ep-thread-irq
+
+  As it turns out some DWC3-commands ~1ms to complete. Currently we spin
+  until the command completes which is bad.
+
+  Implementation idea:
+  - dwc core implements a demultiplexing irq chip for interrupts per
+    endpoint. The interrupt numbers are allocated during probe and belong
+    to the device. If MSI provides per-endpoint interrupt this dummy
+    interrupt chip can be replaced with "real" interrupts.
+  - interrupts are requested / allocated on usb_ep_enable() and removed on
+    usb_ep_disable(). Worst case are 32 interrupts, the lower limit is two
+    for ep0/1.
+  - dwc3_send_gadget_ep_cmd() will sleep in wait_for_completion_timeout()
+    until the command completes.
+  - the interrupt handler is split into the following pieces:
+    - primary handler of the device
+      goes through every event and calls generic_handle_irq() for event
+      it. On return from generic_handle_irq() in acknowledges the event
+      counter so interrupt goes away (eventually).
+
+    - threaded handler of the device
+      none
+
+    - primary handler of the EP-interrupt
+      reads the event and tries to process it. Everything that requries
+      sleeping is handed over to the Thread. The event is saved in an
+      per-endpoint data-structure.
+      We probably have to pay attention not to process events once we
+      handed something to thread so we don't process event X prio Y
+      where X > Y.
+
+    - threaded handler of the EP-interrupt
+      handles the remaining EP work which might sleep such as waiting
+      for command completion.
+
+  Latency:
+   There should be no increase in latency since the interrupt-thread has a
+   high priority and will be run before an average task in user land
+   (except the user changed priorities).

Documentation/usb/power-management.txt

@@ -439,10 +439,10 @@ cause autosuspends to fail with -EBUSY if the driver needs to use the
 device.
 
 External suspend calls should never be allowed to fail in this way,
-only autosuspend calls.  The driver can tell them apart by checking
-the PM_EVENT_AUTO bit in the message.event argument to the suspend
-method; this bit will be set for internal PM events (autosuspend) and
-clear for external PM events.
+only autosuspend calls.  The driver can tell them apart by applying
+the PMSG_IS_AUTO() macro to the message argument to the suspend
+method; it will return True for internal PM events (autosuspend) and
+False for external PM events.
 
 
 	Mutual exclusion
@@ -487,3 +487,29 @@ succeed, it may still remain active and thus cause the system to
 resume as soon as the system suspend is complete.  Or the remote
 wakeup may fail and get lost.  Which outcome occurs depends on timing
 and on the hardware and firmware design.
+
+
+	xHCI hardware link PM
+	---------------------
+
+xHCI host controller provides hardware link power management to usb2.0
+(xHCI 1.0 feature) and usb3.0 devices which support link PM. By
+enabling hardware LPM, the host can automatically put the device into
+lower power state(L1 for usb2.0 devices, or U1/U2 for usb3.0 devices),
+which state device can enter and resume very quickly.
+
+The user interface for controlling USB2 hardware LPM is located in the
+power/ subdirectory of each USB device's sysfs directory, that is, in
+/sys/bus/usb/devices/.../power/ where "..." is the device's ID. The
+relevant attribute files is usb2_hardware_lpm.
+
+	power/usb2_hardware_lpm
+
+		When a USB2 device which support LPM is plugged to a
+		xHCI host root hub which support software LPM, the
+		host will run a software LPM test for it; if the device
+		enters L1 state and resume successfully and the host
+		supports USB2 hardware LPM, this file will show up and
+		driver will enable hardware LPM	for the device. You
+		can write y/Y/1 or n/N/0 to the file to	enable/disable
+		USB2 hardware LPM manually. This is for	test purpose mainly.

Documentation/virtual/lguest/lguest.c

@@ -436,7 +436,7 @@ static unsigned long load_bzimage(int fd)
 
 	/*
 	 * Go back to the start of the file and read the header.  It should be
-	 * a Linux boot header (see Documentation/x86/i386/boot.txt)
+	 * a Linux boot header (see Documentation/x86/boot.txt)
 	 */
 	lseek(fd, 0, SEEK_SET);
 	read(fd, &boot, sizeof(boot));

Documentation/vm/00-INDEX

@@ -30,8 +30,6 @@ page_migration
 	- description of page migration in NUMA systems.
 pagemap.txt
 	- pagemap, from the userspace perspective
-slabinfo.c
-	- source code for a tool to get reports about slabs.
 slub.txt
 	- a short users guide for SLUB.
 unevictable-lru.txt

Documentation/vm/numa

@@ -109,11 +109,11 @@ to improve NUMA locality using various CPU affinity command line interfaces,
 such as taskset(1) and numactl(1), and program interfaces such as
 sched_setaffinity(2).  Further, one can modify the kernel's default local
 allocation behavior using Linux NUMA memory policy.
-[see Documentation/vm/numa_memory_policy.]
+[see Documentation/vm/numa_memory_policy.txt.]
 
 System administrators can restrict the CPUs and nodes' memories that a non-
 privileged user can specify in the scheduling or NUMA commands and functions
-using control groups and CPUsets.  [see Documentation/cgroups/CPUsets.txt]
+using control groups and CPUsets.  [see Documentation/cgroups/cpusets.txt]
 
 On architectures that do not hide memoryless nodes, Linux will include only
 zones [nodes] with memory in the zonelists.  This means that for a memoryless

Documentation/vm/slub.txt

@@ -17,7 +17,7 @@ data and perform operation on the slabs. By default slabinfo only lists
 slabs that have data in them. See "slabinfo -h" for more options when
 running the command. slabinfo can be compiled with
 
-gcc -o slabinfo Documentation/vm/slabinfo.c
+gcc -o slabinfo tools/slub/slabinfo.c
 
 Some of the modes of operation of slabinfo require that slub debugging
 be enabled on the command line. F.e. no tracking information will be

Documentation/zh_CN/SubmitChecklist

@@ -1,109 +0,0 @@
-Chinese translated version of Documentation/SubmitChecklist
-
-If you have any comment or update to the content, please contact the
-original document maintainer directly.  However, if you have a problem
-communicating in English you can also ask the Chinese maintainer for
-help.  Contact the Chinese maintainer if this translation is outdated
-or if there is a problem with the translation.
-
-Chinese maintainer: Harry Wei <harryxiyou@gmail.com>
----------------------------------------------------------------------
-Documentation/SubmitChecklist 的中文翻译
-
-如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
-交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
-译存在问题，请联系中文版维护者。
-
-中文版维护者： 贾威威 Harry Wei <harryxiyou@gmail.com>
-中文版翻译者： 贾威威 Harry Wei <harryxiyou@gmail.com>
-中文版校译者： 贾威威 Harry Wei <harryxiyou@gmail.com>
-
-
-以下为正文
----------------------------------------------------------------------
-Linux内核提交清单
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-这里有一些内核开发者应该做的基本事情，如果他们想看到自己的内核补丁提交
-被接受的更快。
-
-这些都是超出Documentation/SubmittingPatches文档里所提供的以及其他
-关于提交Linux内核补丁的说明。
-
-1：如果你使用了一个功能那么就#include定义/声明那个功能的那个文件。
-   不要依靠其他间接引入定义/声明那个功能的头文件。
-
-2：构建简洁适用或者更改CONFIG选项 =y，=m，或者=n。
-   不要有编译警告/错误， 不要有链接警告/错误。
-
-2b：通过 allnoconfig, allmodconfig
-
-2c：当使用 0=builddir 成功地构建
-
-3：通过使用本地交叉编译工具或者其他一些构建产所，在多CPU框架上构建。
-
-4：ppc64 是一个很好的检查交叉编译的框架，因为它往往把‘unsigned long’
-   当64位值来使用。
-
-5：按照Documentation/CodingStyle文件里的详细描述，检查你补丁的整体风格。
-   使用补丁风格检查琐碎的违规(scripts/checkpatch.pl)，审核员优先提交。
-   你应该调整遗留在你补丁中的所有违规。
-
-6：任何更新或者改动CONFIG选项都不能打乱配置菜单。
-
-7：所有的Kconfig选项更新都要有说明文字。
-
-8：已经认真地总结了相关的Kconfig组合。这是很难通过测试做好的--脑力在这里下降。
-
-9：检查具有简洁性。
-
-10：使用'make checkstack'和'make namespacecheck'检查，然后修改所找到的问题。
-    注意：堆栈检查不会明确地出现问题，但是任何的一个函数在堆栈上使用多于512字节
-    都要准备修改。
-
-11：包含kernel-doc到全局内核APIs文件。（不要求静态的函数，但是包含也无所谓。）
-    使用'make htmldocs'或者'make mandocs'来检查kernel-doc，然后修改任何
-    发现的问题。
-
-12：已经通过CONFIG_PREEMPT, CONFIG_DEBUG_PREEMPT,
-    CONFIG_DEBUG_SLAB, CONFIG_DEBUG_PAGEALLOC, CONFIG_DEBUG_MUTEXES,
-    CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_ATOMIC_SLEEP测试，并且同时都
-    使能。
-
-13：已经都构建并且使用或者不使用 CONFIG_SMP 和 CONFIG_PREEMPT测试执行时间。
-
-14：如果补丁影响IO/Disk，等等：已经通过使用或者不使用 CONFIG_LBDAF 测试。
-
-15：所有的codepaths已经行使所有lockdep启用功能。
-
-16：所有的/proc记录更新都要作成文件放在Documentation/目录下。
-
-17：所有的内核启动参数更新都被记录到Documentation/kernel-parameters.txt文件中。
-
-18：所有的模块参数更新都用MODULE_PARM_DESC()记录。
-
-19：所有的用户空间接口更新都被记录到Documentation/ABI/。查看Documentation/ABI/README
-    可以获得更多的信息。改变用户空间接口的补丁应该被邮件抄送给linux-api@vger.kernel.org。
-
-20：检查它是不是都通过`make headers_check'。
-
-21：已经通过至少引入slab和page-allocation失败检查。查看Documentation/fault-injection/。
-
-22：新加入的源码已经通过`gcc -W'（使用"make EXTRA_CFLAGS=-W"）编译。这样将产生很多烦恼，
-    但是对于寻找漏洞很有益处，例如:"warning: comparison between signed and unsigned"。
-
-23：当它被合并到-mm补丁集后再测试，用来确定它是否还和补丁队列中的其他补丁一起工作以及在VM，VFS
-    和其他子系统中各个变化。
-
-24：所有的内存屏障{e.g., barrier(), rmb(), wmb()}需要在源代码中的一个注释来解释他们都是干什么的
-    以及原因。
-
-25：如果有任何输入输出控制的补丁被添加，也要更新Documentation/ioctl/ioctl-number.txt。
-
-26：如果你的更改代码依靠或者使用任何的内核APIs或者与下面的kconfig符号有关系的功能，你就要
-    使用相关的kconfig符号关闭， and/or =m（如果选项提供）[在同一时间不是所用的都启用，仅仅各个或者自由
-    组合他们]：
-
-    CONFIG_SMP, CONFIG_SYSFS, CONFIG_PROC_FS, CONFIG_INPUT, CONFIG_PCI,
-    CONFIG_BLOCK, CONFIG_PM, CONFIG_HOTPLUG, CONFIG_MAGIC_SYSRQ,
-    CONFIG_NET, CONFIG_INET=n (后一个使用 CONFIG_NET=y)

MAINTAINERS

@@ -2144,6 +2144,14 @@ M:	Matthew Garrett <mjg59@srcf.ucam.org>
 S:	Maintained
 F:	drivers/platform/x86/dell-wmi.c
 
+DESIGNWARE USB3 DRD IP DRIVER
+M:	Felipe Balbi <balbi@ti.com>
+L:	linux-usb@vger.kernel.org
+L:	linux-omap@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
+S:	Maintained
+F:	drivers/usb/dwc3/
+
 DEVICE NUMBER REGISTRY
 M:	Torben Mathiasen <device@lanana.org>
 W:	http://lanana.org/docs/device-list/index.html
@@ -2302,6 +2310,12 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/wan/dscc4.c
 
+DYNAMIC DEBUG
+M:	Jason Baron <jbaron@redhat.com>
+S:	Maintained
+F:	lib/dynamic_debug.c
+F:	include/linux/dynamic_debug.h
+
 DZ DECSTATION DZ11 SERIAL DRIVER
 M:	"Maciej W. Rozycki" <macro@linux-mips.org>
 S:	Maintained
@@ -2560,6 +2574,11 @@ S:	Maintained
 F:	Documentation/filesystems/ext4.txt
 F:	fs/ext4/
 
+Extended Verification Module (EVM)
+M:	Mimi Zohar <zohar@us.ibm.com>
+S:	Supported
+F:	security/integrity/evm/
+
 F71805F HARDWARE MONITORING DRIVER
 M:	Jean Delvare <khali@linux-fr.org>
 L:	lm-sensors@lm-sensors.org
@@ -2741,7 +2760,7 @@ F:	fs/freevxfs/
 FREEZER
 M:	Pavel Machek <pavel@ucw.cz>
 M:	"Rafael J. Wysocki" <rjw@sisk.pl>
-L:	linux-pm@lists.linux-foundation.org
+L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	Documentation/power/freezing-of-tasks.txt
 F:	include/linux/freezer.h
@@ -3003,7 +3022,7 @@ F:	drivers/video/hgafb.c
 HIBERNATION (aka Software Suspend, aka swsusp)
 M:	Pavel Machek <pavel@ucw.cz>
 M:	"Rafael J. Wysocki" <rjw@sisk.pl>
-L:	linux-pm@lists.linux-foundation.org
+L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	arch/x86/power/
 F:	drivers/base/power/
@@ -3198,7 +3217,7 @@ F:	drivers/ide/ide-cd*
 
 IDLE-I7300
 M:	Andy Henroid <andrew.d.henroid@intel.com>
-L:	linux-pm@lists.linux-foundation.org
+L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	drivers/idle/i7300_idle.c
 
@@ -3281,7 +3300,7 @@ F:	firmware/isci/
 
 INTEL IDLE DRIVER
 M:	Len Brown <lenb@kernel.org>
-L:	linux-pm@lists.linux-foundation.org
+L:	linux-pm@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-idle-2.6.git
 S:	Supported
 F:	drivers/idle/intel_idle.c
@@ -3322,7 +3341,7 @@ M:	David Woodhouse <dwmw2@infradead.org>
 L:	iommu@lists.linux-foundation.org
 T:	git git://git.infradead.org/iommu-2.6.git
 S:	Supported
-F:	drivers/pci/intel-iommu.c
+F:	drivers/iommu/intel-iommu.c
 F:	include/linux/intel-iommu.h
 
 INTEL IOP-ADMA DMA DRIVER
@@ -3378,7 +3397,7 @@ F:	drivers/net/ethernet/intel/
 
 INTEL MRST PMU DRIVER
 M:	Len Brown <len.brown@intel.com>
-L:	linux-pm@lists.linux-foundation.org
+L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	arch/x86/platform/mrst/pmu.*
 
@@ -4069,7 +4088,7 @@ S:	Maintained
 
 M32R ARCHITECTURE
 M:	Hirokazu Takata <takata@linux-m32r.org>
-L:	linux-m32r@ml.linux-m32r.org
+L:	linux-m32r@ml.linux-m32r.org (moderated for non-subscribers)
 L:	linux-m32r-ja@ml.linux-m32r.org (in Japanese)
 W:	http://www.linux-m32r.org/
 S:	Maintained
@@ -4238,7 +4257,7 @@ F:	include/mtd/
 
 MICROBLAZE ARCHITECTURE
 M:	Michal Simek <monstr@monstr.eu>
-L:	microblaze-uclinux@itee.uq.edu.au
+L:	microblaze-uclinux@itee.uq.edu.au (moderated for non-subscribers)
 W:	http://www.monstr.eu/fdt/
 T:	git git://git.monstr.eu/linux-2.6-microblaze.git
 S:	Supported
@@ -4753,7 +4772,7 @@ K:	of_match_table
 OPENRISC ARCHITECTURE
 M:	Jonas Bonn <jonas@southpole.se>
 W:	http://openrisc.net
-L:	linux@lists.openrisc.net
+L:	linux@lists.openrisc.net (moderated for non-subscribers)
 S:	Maintained
 T:	git git://openrisc.net/~jonas/linux
 F:	arch/openrisc
@@ -5023,6 +5042,11 @@ L:	linux-mtd@lists.infradead.org
 S:	Maintained
 F:	drivers/mtd/devices/phram.c
 
+PIN CONTROL SUBSYSTEM
+M:	Linus Walleij <linus.walleij@linaro.org>
+S:	Maintained
+F:	drivers/pinmux/
+
 PKTCDVD DRIVER
 M:	Peter Osterlund <petero2@telia.com>
 S:	Maintained
@@ -6147,7 +6171,7 @@ S:	Maintained
 
 STAGING SUBSYSTEM
 M:	Greg Kroah-Hartman <gregkh@suse.de>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging.git
 L:	devel@driverdev.osuosl.org
 S:	Maintained
 F:	drivers/staging/
@@ -6188,6 +6212,11 @@ M:	David Rowe <david@rowetel.com>
 S:	Odd Fixes
 F:	drivers/staging/echo/
 
+STAGING - ET131X NETWORK DRIVER
+M:	Mark Einon <mark.einon@gmail.com>
+S:	Odd Fixes
+F:	drivers/staging/et131x/
+
 STAGING - FLARION FT1000 DRIVERS
 M:	Marek Belisko <marek.belisko@gmail.com>
 S:	Odd Fixes
@@ -6216,6 +6245,13 @@ W:	http://www.lirc.org/
 S:	Odd Fixes
 F:	drivers/staging/lirc/
 
+STAGING - NVIDIA COMPLIANT EMBEDDED CONTROLLER INTERFACE (nvec)
+M:	Julian Andres Klode <jak@jak-linux.org>
+M:	Marc Dietrich <marvin24@gmx.de>
+L:	ac100@lists.launchpad.net (moderated for non-subscribers)
+S:	Maintained
+F:	drivers/staging/nvec/
+
 STAGING - OLPC SECONDARY DISPLAY CONTROLLER (DCON)
 M:	Andres Salomon <dilinger@queued.net>
 M:	Chris Ball <cjb@laptop.org>
@@ -6314,7 +6350,7 @@ SUSPEND TO RAM
 M:	Len Brown <len.brown@intel.com>
 M:	Pavel Machek <pavel@ucw.cz>
 M:	"Rafael J. Wysocki" <rjw@sisk.pl>
-L:	linux-pm@lists.linux-foundation.org
+L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	Documentation/power/
 F:	arch/x86/kernel/acpi/
@@ -6455,7 +6491,7 @@ L:	tomoyo-users-en@lists.sourceforge.jp (subscribers-only, for users in English)
 L:	tomoyo-dev@lists.sourceforge.jp (subscribers-only, for developers in Japanese)
 L:	tomoyo-users@lists.sourceforge.jp (subscribers-only, for users in Japanese)
 W:	http://tomoyo.sourceforge.jp/
-T:	quilt http://svn.sourceforge.jp/svnroot/tomoyo/trunk/2.4.x/tomoyo-lsm/patches/
+T:	quilt http://svn.sourceforge.jp/svnroot/tomoyo/trunk/2.5.x/tomoyo-lsm/patches/
 S:	Maintained
 F:	security/tomoyo/
 
@@ -7150,6 +7186,12 @@ L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	drivers/scsi/wd7000.c
 
+WIIMOTE HID DRIVER
+M:	David Herrmann <dh.herrmann@googlemail.com>
+L:	linux-input@vger.kernel.org
+S:	Maintained
+F:	drivers/hid/hid-wiimote*
+
 WINBOND CIR DRIVER
 M:	David Härdeman <david@hardeman.nu>
 S:	Maintained

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc10
+EXTRAVERSION =
 NAME = "Divemaster Edition"
 
 # *DOCUMENTATION*

arch/alpha/include/asm/fcntl.h

@@ -51,8 +51,6 @@
 #define F_EXLCK		16	/* or 3 */
 #define F_SHLCK		32	/* or 4 */
 
-#define F_INPROGRESS	64
-
 #include <asm-generic/fcntl.h>
 
 #endif

arch/alpha/kernel/srm_env.c

@@ -4,9 +4,8 @@
  *
  * (C) 2001,2002,2006 by Jan-Benedict Glaw <jbglaw@lug-owl.de>
  *
- * This driver is at all a modified version of Erik Mouw's
- * Documentation/DocBook/procfs_example.c, so: thank
- * you, Erik! He can be reached via email at
+ * This driver is a modified version of Erik Mouw's example proc
+ * interface, so: thank you, Erik! He can be reached via email at
  * <J.A.K.Mouw@its.tudelft.nl>. It is based on an idea
  * provided by DEC^WCompaq^WIntel's "Jumpstart" CD. They
  * included a patch like this as well. Thanks for idea!

arch/arm/Kconfig

@@ -3,7 +3,7 @@ config ARM
 	default y
 	select HAVE_AOUT
 	select HAVE_DMA_API_DEBUG
-	select HAVE_IDE
+	select HAVE_IDE if PCI || ISA || PCMCIA
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
@@ -195,7 +195,8 @@ config VECTORS_BASE
 	  The base address of exception vectors.
 
 config ARM_PATCH_PHYS_VIRT
-	bool "Patch physical to virtual translations at runtime"
+	bool "Patch physical to virtual translations at runtime" if EMBEDDED
+	default y
 	depends on !XIP_KERNEL && MMU
 	depends on !ARCH_REALVIEW || !SPARSEMEM
 	help
@@ -204,16 +205,16 @@ config ARM_PATCH_PHYS_VIRT
 	  kernel in system memory.
 
 	  This can only be used with non-XIP MMU kernels where the base
-	  of physical memory is at a 16MB boundary, or theoretically 64K
-	  for the MSM machine class.
+	  of physical memory is at a 16MB boundary.
+
+	  Only disable this option if you know that you do not require
+	  this feature (eg, building a kernel for a single machine) and
+	  you need to shrink the kernel to the minimal size.
 
-config ARM_PATCH_PHYS_VIRT_16BIT
+
+config GENERIC_BUG
 	def_bool y
-	depends on ARM_PATCH_PHYS_VIRT && ARCH_MSM
-	help
-	  This option extends the physical to virtual translation patching
-	  to allow physical memory down to a theoretical minimum of 64K
-	  boundaries.
+	depends on BUG
 
 source "init/Kconfig"
 
@@ -301,7 +302,6 @@ config ARCH_AT91
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_CLK
 	select CLKDEV_LOOKUP
-	select ARM_PATCH_PHYS_VIRT if MMU
 	help
 	  This enables support for systems based on the Atmel AT91RM9200,
 	  AT91SAM9 and AT91CAP9 processors.
@@ -346,7 +346,6 @@ config ARCH_GEMINI
 config ARCH_PRIMA2
 	bool "CSR SiRFSoC PRIMA2 ARM Cortex A9 Platform"
 	select CPU_V7
-	select GENERIC_TIME
 	select NO_IOPORT
 	select GENERIC_CLOCKEVENTS
 	select CLKDEV_LOOKUP
@@ -385,6 +384,7 @@ config ARCH_FOOTBRIDGE
 	select CPU_SA110
 	select FOOTBRIDGE
 	select GENERIC_CLOCKEVENTS
+	select HAVE_IDE
 	help
 	  Support for systems based on the DC21285 companion chip
 	  ("FootBridge"), such as the Simtec CATS and the Rebel NetWinder.
@@ -519,7 +519,6 @@ config ARCH_LPC32XX
 	select ARM_AMBA
 	select USB_ARCH_HAS_OHCI
 	select CLKDEV_LOOKUP
-	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	help
 	  Support for the NXP LPC32XX family of processors
@@ -598,7 +597,6 @@ config ARCH_TEGRA
 	bool "NVIDIA Tegra"
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
-	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
 	select HAVE_CLK
@@ -631,6 +629,8 @@ config ARCH_PXA
 	select SPARSE_IRQ
 	select AUTO_ZRELADDR
 	select MULTI_IRQ_HANDLER
+	select ARM_CPU_SUSPEND if PM
+	select HAVE_IDE
 	help
 	  Support for Intel/Marvell's PXA2xx/PXA3xx processor line.
 
@@ -671,6 +671,7 @@ config ARCH_RPC
 	select NO_IOPORT
 	select ARCH_SPARSEMEM_ENABLE
 	select ARCH_USES_GETTIMEOFFSET
+	select HAVE_IDE
 	help
 	  On the Acorn Risc-PC, Linux can support the internal IDE disk and
 	  CD-ROM interface, serial and parallel port, and the floppy drive.
@@ -689,6 +690,7 @@ config ARCH_SA1100
 	select HAVE_SCHED_CLOCK
 	select TICK_ONESHOT
 	select ARCH_REQUIRE_GPIOLIB
+	select HAVE_IDE
 	help
 	  Support for StrongARM 11x0 based boards.
 
@@ -722,7 +724,6 @@ config ARCH_S3C64XX
 	select ARCH_REQUIRE_GPIOLIB
 	select SAMSUNG_CLKSRC
 	select SAMSUNG_IRQ_VIC_TIMER
-	select SAMSUNG_IRQ_UART
 	select S3C_GPIO_TRACK
 	select S3C_GPIO_PULL_UPDOWN
 	select S3C_GPIO_CFG_S3C24XX
@@ -910,7 +911,6 @@ config ARCH_VT8500
 config ARCH_ZYNQ
 	bool "Xilinx Zynq ARM Cortex A9 Platform"
 	select CPU_V7
-	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	select CLKDEV_LOOKUP
 	select ARM_GIC
@@ -1375,6 +1375,7 @@ config SMP
 		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \
 		 ARCH_EXYNOS4 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || \
 		 ARCH_MSM_SCORPIONMP || ARCH_SHMOBILE
+	depends on MMU
 	select USE_GENERIC_SMP_HELPERS
 	select HAVE_ARM_SCU if !ARCH_MSM_SCORPIONMP
 	help
@@ -1388,7 +1389,7 @@ config SMP
 	  processor machines. On a single processor machine, the kernel will
 	  run faster if you say N here.
 
-	  See also <file:Documentation/i386/IO-APIC.txt>,
+	  See also <file:Documentation/x86/i386/IO-APIC.txt>,
 	  <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at
 	  <http://tldp.org/HOWTO/SMP-HOWTO.html>.
 
@@ -1407,6 +1408,31 @@ config SMP_ON_UP
 
 	  If you don't know what to do here, say Y.
 
+config ARM_CPU_TOPOLOGY
+	bool "Support cpu topology definition"
+	depends on SMP && CPU_V7
+	default y
+	help
+	  Support ARM cpu topology definition. The MPIDR register defines
+	  affinity between processors which is then used to describe the cpu
+	  topology of an ARM System.
+
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
 config HAVE_ARM_SCU
 	bool
 	help
@@ -1482,6 +1508,7 @@ config THUMB2_KERNEL
 	depends on CPU_V7 && !CPU_V6 && !CPU_V6K && EXPERIMENTAL
 	select AEABI
 	select ARM_ASM_UNIFIED
+	select ARM_UNWIND
 	help
 	  By enabling this option, the kernel will be compiled in
 	  Thumb-2 mode. A compiler/assembler that understand the unified
@@ -2101,6 +2128,9 @@ config ARCH_SUSPEND_POSSIBLE
 		CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE
 	def_bool y
 
+config ARM_CPU_SUSPEND
+	def_bool PM_SLEEP
+
 endmenu
 
 source "net/Kconfig"

arch/arm/Kconfig.debug

@@ -65,13 +65,71 @@ config DEBUG_USER
 
 # These options are only for real kernel hackers who want to get their hands dirty.
 config DEBUG_LL
-	bool "Kernel low-level debugging functions"
+	bool "Kernel low-level debugging functions (read help!)"
 	depends on DEBUG_KERNEL
 	help
 	  Say Y here to include definitions of printascii, printch, printhex
 	  in the kernel.  This is helpful if you are debugging code that
 	  executes before the console is initialized.
 
+	  Note that selecting this option will limit the kernel to a single
+	  UART definition, as specified below. Attempting to boot the kernel
+	  image on a different platform *will not work*, so this option should
+	  not be enabled for kernels that are intended to be portable.
+
+choice
+	prompt "Kernel low-level debugging port"
+	depends on DEBUG_LL
+
+	config DEBUG_LL_UART_NONE
+		bool "No low-level debugging UART"
+		help
+		  Say Y here if your platform doesn't provide a UART option
+		  below. This relies on your platform choosing the right UART
+		  definition internally in order for low-level debugging to
+		  work.
+
+	config DEBUG_ICEDCC
+		bool "Kernel low-level debugging via EmbeddedICE DCC channel"
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the EmbeddedICE macrocell's DCC channel using
+		  co-processor 14. This is known to work on the ARM9 style ICE
+		  channel and on the XScale with the PEEDI.
+
+		  Note that the system will appear to hang during boot if there
+		  is nothing connected to read from the DCC.
+
+	config DEBUG_FOOTBRIDGE_COM1
+		bool "Kernel low-level debugging messages via footbridge 8250 at PCI COM1"
+		depends on FOOTBRIDGE
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the 8250 at PCI COM1.
+
+	config DEBUG_DC21285_PORT
+		bool "Kernel low-level debugging messages via footbridge serial port"
+		depends on FOOTBRIDGE
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the serial port in the DC21285 (Footbridge).
+
+	config DEBUG_CLPS711X_UART1
+		bool "Kernel low-level debugging messages via UART1"
+		depends on ARCH_CLPS711X
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the first serial port on these devices.
+
+	config DEBUG_CLPS711X_UART2
+		bool "Kernel low-level debugging messages via UART2"
+		depends on ARCH_CLPS711X
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the second serial port on these devices.
+
+endchoice
+
 config EARLY_PRINTK
 	bool "Early printk"
 	depends on DEBUG_LL
@@ -80,43 +138,14 @@ config EARLY_PRINTK
 	  kernel low-level debugging functions. Add earlyprintk to your
 	  kernel parameters to enable this console.
 
-config DEBUG_ICEDCC
-	bool "Kernel low-level debugging via EmbeddedICE DCC channel"
-	depends on DEBUG_LL
-	help
-	  Say Y here if you want the debug print routines to direct their
-	  output to the EmbeddedICE macrocell's DCC channel using
-	  co-processor 14. This is known to work on the ARM9 style ICE
-	  channel and on the XScale with the PEEDI.
-
-	  It does include a timeout to ensure that the system does not
-	  totally freeze when there is nothing connected to read.
-
 config OC_ETM
 	bool "On-chip ETM and ETB"
-	select ARM_AMBA
+	depends on ARM_AMBA
 	help
 	  Enables the on-chip embedded trace macrocell and embedded trace
 	  buffer driver that will allow you to collect traces of the
 	  kernel code.
 
-config DEBUG_DC21285_PORT
-	bool "Kernel low-level debugging messages via footbridge serial port"
-	depends on DEBUG_LL && FOOTBRIDGE
-	help
-	  Say Y here if you want the debug print routines to direct their
-	  output to the serial port in the DC21285 (Footbridge). Saying N
-	  will cause the debug messages to appear on the first 16550
-	  serial port.
-
-config DEBUG_CLPS711X_UART2
-	bool "Kernel low-level debugging messages via UART2"
-	depends on DEBUG_LL && ARCH_CLPS711X
-	help
-	  Say Y here if you want the debug print routines to direct their
-	  output to the second serial port on these devices.  Saying N will
-	  cause the debug messages to appear on the first serial port.
-
 config DEBUG_S3C_UART
 	depends on PLAT_SAMSUNG
 	int "S3C UART to use for low-level debug"

arch/arm/Makefile

@@ -128,6 +128,9 @@ textofs-$(CONFIG_PM_H1940)      := 0x00108000
 ifeq ($(CONFIG_ARCH_SA1100),y)
 textofs-$(CONFIG_SA1111) := 0x00208000
 endif
+textofs-$(CONFIG_ARCH_MSM7X30) := 0x00208000
+textofs-$(CONFIG_ARCH_MSM8X60) := 0x00208000
+textofs-$(CONFIG_ARCH_MSM8960) := 0x00208000
 
 # Machine directory name.  This list is sorted alphanumerically
 # by CONFIG_* macro name.

arch/arm/boot/Makefile

@@ -78,7 +78,16 @@ endif
 
 $(obj)/uImage: STARTADDR=$(LOADADDR)
 
+check_for_multiple_loadaddr = \
+if [ $(words $(LOADADDR)) -gt 1 ]; then \
+	echo 'multiple load addresses: $(LOADADDR)'; \
+	echo 'This is incompatible with uImages'; \
+	echo 'Specify LOADADDR on the commandline to build an uImage'; \
+	false; \
+fi
+
 $(obj)/uImage:	$(obj)/zImage FORCE
+	@$(check_for_multiple_loadaddr)
 	$(call if_changed,uimage)
 	@echo '  Image $@ is ready'
 

arch/arm/boot/compressed/Makefile

@@ -139,8 +139,16 @@ bad_syms=$$($(CROSS_COMPILE)nm $@ | sed -n 's/^.\{8\} [bc] \(.*\)/\1/p') && \
   ( echo "following symbols must have non local/private scope:" >&2; \
     echo "$$bad_syms" >&2; rm -f $@; false )
 
+check_for_multiple_zreladdr = \
+if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \
+	echo 'multiple zreladdrs: $(ZRELADDR)'; \
+	echo 'This needs CONFIG_AUTO_ZRELADDR to be set'; \
+	false; \
+fi
+
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
 	 	$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) FORCE
+	@$(check_for_multiple_zreladdr)
 	$(call if_changed,ld)
 	@$(check_for_bad_syms)
 

arch/arm/common/gic.c

@@ -33,7 +33,7 @@
 #include <asm/mach/irq.h>
 #include <asm/hardware/gic.h>
 
-static DEFINE_SPINLOCK(irq_controller_lock);
+static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 
 /* Address of GIC 0 CPU interface */
 void __iomem *gic_cpu_base_addr __read_mostly;
@@ -82,30 +82,30 @@ static void gic_mask_irq(struct irq_data *d)
 {
 	u32 mask = 1 << (d->irq % 32);
 
-	spin_lock(&irq_controller_lock);
+	raw_spin_lock(&irq_controller_lock);
 	writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_CLEAR + (gic_irq(d) / 32) * 4);
 	if (gic_arch_extn.irq_mask)
 		gic_arch_extn.irq_mask(d);
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 }
 
 static void gic_unmask_irq(struct irq_data *d)
 {
 	u32 mask = 1 << (d->irq % 32);
 
-	spin_lock(&irq_controller_lock);
+	raw_spin_lock(&irq_controller_lock);
 	if (gic_arch_extn.irq_unmask)
 		gic_arch_extn.irq_unmask(d);
 	writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_SET + (gic_irq(d) / 32) * 4);
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 }
 
 static void gic_eoi_irq(struct irq_data *d)
 {
 	if (gic_arch_extn.irq_eoi) {
-		spin_lock(&irq_controller_lock);
+		raw_spin_lock(&irq_controller_lock);
 		gic_arch_extn.irq_eoi(d);
-		spin_unlock(&irq_controller_lock);
+		raw_spin_unlock(&irq_controller_lock);
 	}
 
 	writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_EOI);
@@ -129,7 +129,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
 		return -EINVAL;
 
-	spin_lock(&irq_controller_lock);
+	raw_spin_lock(&irq_controller_lock);
 
 	if (gic_arch_extn.irq_set_type)
 		gic_arch_extn.irq_set_type(d, type);
@@ -154,7 +154,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	if (enabled)
 		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
 
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 
 	return 0;
 }
@@ -180,12 +180,12 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 		return -EINVAL;
 
 	mask = 0xff << shift;
-	bit = 1 << (cpu + shift);
+	bit = 1 << (cpu_logical_map(cpu) + shift);
 
-	spin_lock(&irq_controller_lock);
+	raw_spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
 	writel_relaxed(val | bit, reg);
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 
 	return IRQ_SET_MASK_OK;
 }
@@ -215,9 +215,9 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 
 	chained_irq_enter(chip, desc);
 
-	spin_lock(&irq_controller_lock);
+	raw_spin_lock(&irq_controller_lock);
 	status = readl_relaxed(chip_data->cpu_base + GIC_CPU_INTACK);
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 
 	gic_irq = (status & 0x3ff);
 	if (gic_irq == 1023)
@@ -259,9 +259,15 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	unsigned int irq_start)
 {
 	unsigned int gic_irqs, irq_limit, i;
+	u32 cpumask;
 	void __iomem *base = gic->dist_base;
-	u32 cpumask = 1 << smp_processor_id();
+	u32 cpu = 0;
 
+#ifdef CONFIG_SMP
+	cpu = cpu_logical_map(smp_processor_id());
+#endif
+
+	cpumask = 1 << cpu;
 	cpumask |= cpumask << 8;
 	cpumask |= cpumask << 16;
 
@@ -382,7 +388,12 @@ void __cpuinit gic_enable_ppi(unsigned int irq)
 #ifdef CONFIG_SMP
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
-	unsigned long map = *cpus_addr(*mask);
+	int cpu;
+	unsigned long map = 0;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
 
 	/*
 	 * Ensure that stores to Normal memory are visible to the

arch/arm/common/pl330.c

@@ -1546,7 +1546,7 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
 
 		/* Start the next */
 	case PL330_OP_START:
-		if (!_start(thrd))
+		if (!_thrd_active(thrd) && !_start(thrd))
 			ret = -EIO;
 		break;
 

arch/arm/common/vic.c

@@ -346,7 +346,8 @@ void __init vic_init(void __iomem *base, unsigned int irq_start,
 
 	/* Identify which VIC cell this one is, by reading the ID */
 	for (i = 0; i < 4; i++) {
-		u32 addr = ((u32)base & PAGE_MASK) + 0xfe0 + (i * 4);
+		void __iomem *addr;
+		addr = (void __iomem *)((u32)base & PAGE_MASK) + 0xfe0 + (i * 4);
 		cellid |= (readl(addr) & 0xff) << (8 * i);
 	}
 	vendor = (cellid >> 12) & 0xff;

arch/arm/configs/integrator_defconfig

@@ -1,5 +1,6 @@
 CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
+CONFIG_TINY_RCU=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -8,20 +9,29 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_INTEGRATOR=y
 CONFIG_ARCH_INTEGRATOR_AP=y
+CONFIG_ARCH_INTEGRATOR_CP=y
 CONFIG_CPU_ARM720T=y
 CONFIG_CPU_ARM920T=y
+CONFIG_CPU_ARM922T=y
+CONFIG_CPU_ARM926T=y
+CONFIG_CPU_ARM1020=y
+CONFIG_CPU_ARM1022=y
+CONFIG_CPU_ARM1026=y
 CONFIG_PCI=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=y
+CONFIG_AEABI=y
 CONFIG_LEDS=y
 CONFIG_LEDS_CPU=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp mem=32M"
+CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp"
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_FPE_NWFPE=y
-CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -32,7 +42,6 @@ CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
 CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_AFS_PARTS=y
 CONFIG_MTD_CHAR=y
@@ -40,6 +49,7 @@ CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_ADV_OPTIONS=y
 CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_PHYSMAP=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
@@ -56,6 +66,8 @@ CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_MATROX=y
 CONFIG_FB_MATROX_MILLENIUM=y
 CONFIG_FB_MATROX_MYSTIQUE=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL030=y
 CONFIG_EXT2_FS=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
@@ -68,4 +80,3 @@ CONFIG_NFSD_V3=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_ERRORS=y

arch/arm/include/asm/Kbuild

@@ -1,3 +1,20 @@
 include include/asm-generic/Kbuild.asm
 
 header-y += hwcap.h
+
+generic-y += auxvec.h
+generic-y += bitsperlong.h
+generic-y += cputime.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += ioctl.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += resource.h
+generic-y += sections.h
+generic-y += siginfo.h
+generic-y += sizes.h

arch/arm/include/asm/auxvec.h

@@ -1,4 +0,0 @@
-#ifndef __ASMARM_AUXVEC_H
-#define __ASMARM_AUXVEC_H
-
-#endif

arch/arm/include/asm/bitsperlong.h

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

arch/arm/include/asm/bug.h

@@ -3,21 +3,58 @@
 
 
 #ifdef CONFIG_BUG
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-extern void __bug(const char *file, int line) __attribute__((noreturn));
-
-/* give file/line information */
-#define BUG()		__bug(__FILE__, __LINE__)
 
+/*
+ * Use a suitable undefined instruction to use for ARM/Thumb2 bug handling.
+ * We need to be careful not to conflict with those used by other modules and
+ * the register_undef_hook() system.
+ */
+#ifdef CONFIG_THUMB2_KERNEL
+#define BUG_INSTR_VALUE 0xde02
+#define BUG_INSTR_TYPE ".hword "
 #else
+#define BUG_INSTR_VALUE 0xe7f001f2
+#define BUG_INSTR_TYPE ".word "
+#endif
 
-/* this just causes an oops */
-#define BUG()		do { *(int *)0 = 0; } while (1)
 
-#endif
+#define BUG() _BUG(__FILE__, __LINE__, BUG_INSTR_VALUE)
+#define _BUG(file, line, value) __BUG(file, line, value)
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+/*
+ * The extra indirection is to ensure that the __FILE__ string comes through
+ * OK. Many version of gcc do not support the asm %c parameter which would be
+ * preferable to this unpleasantness. We use mergeable string sections to
+ * avoid multiple copies of the string appearing in the kernel image.
+ */
+
+#define __BUG(__file, __line, __value)				\
+do {								\
+	BUILD_BUG_ON(sizeof(struct bug_entry) != 12);		\
+	asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n"	\
+		".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
+		"2:\t.asciz " #__file "\n" 			\
+		".popsection\n" 				\
+		".pushsection __bug_table,\"a\"\n"		\
+		"3:\t.word 1b, 2b\n"				\
+		"\t.hword " #__line ", 0\n"			\
+		".popsection");					\
+	unreachable();						\
+} while (0)
+
+#else  /* not CONFIG_DEBUG_BUGVERBOSE */
+
+#define __BUG(__file, __line, __value)				\
+do {								\
+	asm volatile(BUG_INSTR_TYPE #__value);			\
+	unreachable();						\
+} while (0)
+#endif  /* CONFIG_DEBUG_BUGVERBOSE */
 
 #define HAVE_ARCH_BUG
-#endif
+#endif  /* CONFIG_BUG */
 
 #include <asm-generic/bug.h>
 

arch/arm/include/asm/cachetype.h

@@ -7,6 +7,7 @@
 #define CACHEID_VIPT			(CACHEID_VIPT_ALIASING|CACHEID_VIPT_NONALIASING)
 #define CACHEID_ASID_TAGGED		(1 << 3)
 #define CACHEID_VIPT_I_ALIASING		(1 << 4)
+#define CACHEID_PIPT			(1 << 5)
 
 extern unsigned int cacheid;
 
@@ -16,6 +17,7 @@ extern unsigned int cacheid;
 #define cache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_ALIASING)
 #define icache_is_vivt_asid_tagged()	cacheid_is(CACHEID_ASID_TAGGED)
 #define icache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_I_ALIASING)
+#define icache_is_pipt()		cacheid_is(CACHEID_PIPT)
 
 /*
  * __LINUX_ARM_ARCH__ is the minimum supported CPU architecture
@@ -26,7 +28,8 @@ extern unsigned int cacheid;
 #if __LINUX_ARM_ARCH__ >= 7
 #define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING |\
 				 CACHEID_ASID_TAGGED |\
-				 CACHEID_VIPT_I_ALIASING)
+				 CACHEID_VIPT_I_ALIASING |\
+				 CACHEID_PIPT)
 #elif __LINUX_ARM_ARCH__ >= 6
 #define	__CACHEID_ARCH_MIN	(~CACHEID_VIVT)
 #else

arch/arm/include/asm/cputime.h

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

arch/arm/include/asm/cputype.h

@@ -8,6 +8,7 @@
 #define CPUID_CACHETYPE	1
 #define CPUID_TCM	2
 #define CPUID_TLBTYPE	3
+#define CPUID_MPIDR	5
 
 #define CPUID_EXT_PFR0	"c1, 0"
 #define CPUID_EXT_PFR1	"c1, 1"
@@ -70,6 +71,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
 	return read_cpuid(CPUID_TCM);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mpidr(void)
+{
+	return read_cpuid(CPUID_MPIDR);
+}
+
 /*
  * Intel's XScale3 core supports some v6 features (supersections, L2)
  * but advertises itself as v5 as it does not support the v6 ISA.  For