Merge branch 'linus' into timers/core

Reason: Further posix_cpu_timer patches depend on mainline changes

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

Documentation/ABI/testing/sysfs-bus-usb

@@ -160,7 +160,7 @@ Description:
 		match the driver to the device.  For example:
 		# echo "046d c315" > /sys/bus/usb/drivers/foo/remove_id
 
-What:		/sys/bus/usb/device/.../avoid_reset
+What:		/sys/bus/usb/device/.../avoid_reset_quirk
 Date:		December 2009
 Contact:	Oliver Neukum <oliver@neukum.org>
 Description:

Documentation/DocBook/libata.tmpl

@@ -107,10 +107,6 @@ void (*dev_config) (struct ata_port *, struct ata_device *);
 	issue of SET FEATURES - XFER MODE, and prior to operation.
 	</para>
 	<para>
-	Called by ata_device_add() after ata_dev_identify() determines
-	a device is present.
-	</para>
-	<para>
 	This entry may be specified as NULL in ata_port_operations.
 	</para>
 
@@ -154,8 +150,8 @@ unsigned int (*mode_filter) (struct ata_port *, struct ata_device *, unsigned in
 
 	<sect2><title>Taskfile read/write</title>
 	<programlisting>
-void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
-void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
 	</programlisting>
 
 	<para>
@@ -164,36 +160,35 @@ void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
 	hardware registers / DMA buffers, to obtain the current set of
 	taskfile register values.
 	Most drivers for taskfile-based hardware (PIO or MMIO) use
-	ata_tf_load() and ata_tf_read() for these hooks.
+	ata_sff_tf_load() and ata_sff_tf_read() for these hooks.
 	</para>
 
 	</sect2>
 
 	<sect2><title>PIO data read/write</title>
 	<programlisting>
-void (*data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
+void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
 	</programlisting>
 
 	<para>
 All bmdma-style drivers must implement this hook.  This is the low-level
 operation that actually copies the data bytes during a PIO data
 transfer.
-Typically the driver
-will choose one of ata_pio_data_xfer_noirq(), ata_pio_data_xfer(), or
-ata_mmio_data_xfer().
+Typically the driver will choose one of ata_sff_data_xfer_noirq(),
+ata_sff_data_xfer(), or ata_sff_data_xfer32().
 	</para>
 
 	</sect2>
 
 	<sect2><title>ATA command execute</title>
 	<programlisting>
-void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
 	</programlisting>
 
 	<para>
 	causes an ATA command, previously loaded with
 	->tf_load(), to be initiated in hardware.
-	Most drivers for taskfile-based hardware use ata_exec_command()
+	Most drivers for taskfile-based hardware use ata_sff_exec_command()
 	for this hook.
 	</para>
 
@@ -218,8 +213,8 @@ command.
 
 	<sect2><title>Read specific ATA shadow registers</title>
 	<programlisting>
-u8   (*check_status)(struct ata_port *ap);
-u8   (*check_altstatus)(struct ata_port *ap);
+u8   (*sff_check_status)(struct ata_port *ap);
+u8   (*sff_check_altstatus)(struct ata_port *ap);
 	</programlisting>
 
 	<para>
@@ -227,20 +222,14 @@ u8   (*check_altstatus)(struct ata_port *ap);
 	hardware.  On some hardware, reading the Status register has
 	the side effect of clearing the interrupt condition.
 	Most drivers for taskfile-based hardware use
-	ata_check_status() for this hook.
-	</para>
-	<para>
-	Note that because this is called from ata_device_add(), at
-	least a dummy function that clears device interrupts must be
-	provided for all drivers, even if the controller doesn't
-	actually have a taskfile status register.
+	ata_sff_check_status() for this hook.
 	</para>
 
 	</sect2>
 
 	<sect2><title>Select ATA device on bus</title>
 	<programlisting>
-void (*dev_select)(struct ata_port *ap, unsigned int device);
+void (*sff_dev_select)(struct ata_port *ap, unsigned int device);
 	</programlisting>
 
 	<para>
@@ -251,9 +240,7 @@ void (*dev_select)(struct ata_port *ap, unsigned int device);
 	</para>
 	<para>
 	Most drivers for taskfile-based hardware use
-	ata_std_dev_select() for this hook.  Controllers which do not
-	support second drives on a port (such as SATA contollers) will
-	use ata_noop_dev_select().
+	ata_sff_dev_select() for this hook.
 	</para>
 
 	</sect2>
@@ -441,13 +428,13 @@ void (*irq_clear) (struct ata_port *);
 	to struct ata_host_set.
 	</para>
 	<para>
-	Most legacy IDE drivers use ata_interrupt() for the
+	Most legacy IDE drivers use ata_sff_interrupt() for the
 	irq_handler hook, which scans all ports in the host_set,
 	determines which queued command was active (if any), and calls
-	ata_host_intr(ap,qc).
+	ata_sff_host_intr(ap,qc).
 	</para>
 	<para>
-	Most legacy IDE drivers use ata_bmdma_irq_clear() for the
+	Most legacy IDE drivers use ata_sff_irq_clear() for the
 	irq_clear() hook, which simply clears the interrupt and error
 	flags in the DMA status register.
 	</para>
@@ -496,10 +483,6 @@ void (*host_stop) (struct ata_host_set *host_set);
 	data from port at this time.
 	</para>
 	<para>
-	Many drivers use ata_port_stop() as this hook, which frees the
-	PRD table.
-	</para>
-	<para>
 	->host_stop() is called after all ->port_stop() calls
 have completed.  The hook must finalize hardware shutdown, release DMA
 and other resources, etc.

Documentation/DocBook/tracepoint.tmpl

@@ -16,6 +16,15 @@
      </address>
     </affiliation>
    </author>
+   <author>
+    <firstname>William</firstname>
+    <surname>Cohen</surname>
+    <affiliation>
+     <address>
+      <email>wcohen@redhat.com</email>
+     </address>
+    </affiliation>
+   </author>
   </authorgroup>
 
   <legalnotice>
@@ -91,4 +100,8 @@
 !Iinclude/trace/events/signal.h
   </chapter>
 
+  <chapter id="block">
+   <title>Block IO</title>
+!Iinclude/trace/events/block.h
+  </chapter>
 </book>

Documentation/HOWTO

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

Documentation/RCU/NMI-RCU.txt

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

Documentation/RCU/checklist.txt

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

Documentation/RCU/lockdep.txt

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

Documentation/RCU/whatisRCU.txt

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

Documentation/block/biodoc.txt

@@ -1162,8 +1162,8 @@ where a driver received a request ala this before:
 
 As mentioned, there is no virtual mapping of a bio. For DMA, this is
 not a problem as the driver probably never will need a virtual mapping.
-Instead it needs a bus mapping (pci_map_page for a single segment or
-use blk_rq_map_sg for scatter gather) to be able to ship it to the driver. For
+Instead it needs a bus mapping (dma_map_page for a single segment or
+use dma_map_sg for scatter gather) to be able to ship it to the driver. For
 PIO drivers (or drivers that need to revert to PIO transfer once in a
 while (IDE for example)), where the CPU is doing the actual data
 transfer a virtual mapping is needed. If the driver supports highmem I/O,

Documentation/cgroups/cgroups.txt

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

Documentation/cgroups/memory.txt

@@ -340,7 +340,7 @@ Note:
 5.3 swappiness
   Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
 
-  Following cgroups' swapiness can't be changed.
+  Following cgroups' swappiness can't be changed.
   - root cgroup (uses /proc/sys/vm/swappiness).
   - a cgroup which uses hierarchy and it has child cgroup.
   - a cgroup which uses hierarchy and not the root of hierarchy.

Documentation/circular-buffers.txt

@@ -0,0 +1,234 @@
+			       ================
+			       CIRCULAR BUFFERS
+			       ================
+
+By: David Howells <dhowells@redhat.com>
+    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+
+Linux provides a number of features that can be used to implement circular
+buffering.  There are two sets of such features:
+
+ (1) Convenience functions for determining information about power-of-2 sized
+     buffers.
+
+ (2) Memory barriers for when the producer and the consumer of objects in the
+     buffer don't want to share a lock.
+
+To use these facilities, as discussed below, there needs to be just one
+producer and just one consumer.  It is possible to handle multiple producers by
+serialising them, and to handle multiple consumers by serialising them.
+
+
+Contents:
+
+ (*) What is a circular buffer?
+
+ (*) Measuring power-of-2 buffers.
+
+ (*) Using memory barriers with circular buffers.
+     - The producer.
+     - The consumer.
+
+
+==========================
+WHAT IS A CIRCULAR BUFFER?
+==========================
+
+First of all, what is a circular buffer?  A circular buffer is a buffer of
+fixed, finite size into which there are two indices:
+
+ (1) A 'head' index - the point at which the producer inserts items into the
+     buffer.
+
+ (2) A 'tail' index - the point at which the consumer finds the next item in
+     the buffer.
+
+Typically when the tail pointer is equal to the head pointer, the buffer is
+empty; and the buffer is full when the head pointer is one less than the tail
+pointer.
+
+The head index is incremented when items are added, and the tail index when
+items are removed.  The tail index should never jump the head index, and both
+indices should be wrapped to 0 when they reach the end of the buffer, thus
+allowing an infinite amount of data to flow through the buffer.
+
+Typically, items will all be of the same unit size, but this isn't strictly
+required to use the techniques below.  The indices can be increased by more
+than 1 if multiple items or variable-sized items are to be included in the
+buffer, provided that neither index overtakes the other.  The implementer must
+be careful, however, as a region more than one unit in size may wrap the end of
+the buffer and be broken into two segments.
+
+
+============================
+MEASURING POWER-OF-2 BUFFERS
+============================
+
+Calculation of the occupancy or the remaining capacity of an arbitrarily sized
+circular buffer would normally be a slow operation, requiring the use of a
+modulus (divide) instruction.  However, if the buffer is of a power-of-2 size,
+then a much quicker bitwise-AND instruction can be used instead.
+
+Linux provides a set of macros for handling power-of-2 circular buffers.  These
+can be made use of by:
+
+	#include <linux/circ_buf.h>
+
+The macros are:
+
+ (*) Measure the remaining capacity of a buffer:
+
+	CIRC_SPACE(head_index, tail_index, buffer_size);
+
+     This returns the amount of space left in the buffer[1] into which items
+     can be inserted.
+
+
+ (*) Measure the maximum consecutive immediate space in a buffer:
+
+	CIRC_SPACE_TO_END(head_index, tail_index, buffer_size);
+
+     This returns the amount of consecutive space left in the buffer[1] into
+     which items can be immediately inserted without having to wrap back to the
+     beginning of the buffer.
+
+
+ (*) Measure the occupancy of a buffer:
+
+	CIRC_CNT(head_index, tail_index, buffer_size);
+
+     This returns the number of items currently occupying a buffer[2].
+
+
+ (*) Measure the non-wrapping occupancy of a buffer:
+
+	CIRC_CNT_TO_END(head_index, tail_index, buffer_size);
+
+     This returns the number of consecutive items[2] that can be extracted from
+     the buffer without having to wrap back to the beginning of the buffer.
+
+
+Each of these macros will nominally return a value between 0 and buffer_size-1,
+however:
+
+ [1] CIRC_SPACE*() are intended to be used in the producer.  To the producer
+     they will return a lower bound as the producer controls the head index,
+     but the consumer may still be depleting the buffer on another CPU and
+     moving the tail index.
+
+     To the consumer it will show an upper bound as the producer may be busy
+     depleting the space.
+
+ [2] CIRC_CNT*() are intended to be used in the consumer.  To the consumer they
+     will return a lower bound as the consumer controls the tail index, but the
+     producer may still be filling the buffer on another CPU and moving the
+     head index.
+
+     To the producer it will show an upper bound as the consumer may be busy
+     emptying the buffer.
+
+ [3] To a third party, the order in which the writes to the indices by the
+     producer and consumer become visible cannot be guaranteed as they are
+     independent and may be made on different CPUs - so the result in such a
+     situation will merely be a guess, and may even be negative.
+
+
+===========================================
+USING MEMORY BARRIERS WITH CIRCULAR BUFFERS
+===========================================
+
+By using memory barriers in conjunction with circular buffers, you can avoid
+the need to:
+
+ (1) use a single lock to govern access to both ends of the buffer, thus
+     allowing the buffer to be filled and emptied at the same time; and
+
+ (2) use atomic counter operations.
+
+There are two sides to this: the producer that fills the buffer, and the
+consumer that empties it.  Only one thing should be filling a buffer at any one
+time, and only one thing should be emptying a buffer at any one time, but the
+two sides can operate simultaneously.
+
+
+THE PRODUCER
+------------
+
+The producer will look something like this:
+
+	spin_lock(&producer_lock);
+
+	unsigned long head = buffer->head;
+	unsigned long tail = ACCESS_ONCE(buffer->tail);
+
+	if (CIRC_SPACE(head, tail, buffer->size) >= 1) {
+		/* insert one item into the buffer */
+		struct item *item = buffer[head];
+
+		produce_item(item);
+
+		smp_wmb(); /* commit the item before incrementing the head */
+
+		buffer->head = (head + 1) & (buffer->size - 1);
+
+		/* wake_up() will make sure that the head is committed before
+		 * waking anyone up */
+		wake_up(consumer);
+	}
+
+	spin_unlock(&producer_lock);
+
+This will instruct the CPU that the contents of the new item must be written
+before the head index makes it available to the consumer and then instructs the
+CPU that the revised head index must be written before the consumer is woken.
+
+Note that wake_up() doesn't have to be the exact mechanism used, but whatever
+is used must guarantee a (write) memory barrier between the update of the head
+index and the change of state of the consumer, if a change of state occurs.
+
+
+THE CONSUMER
+------------
+
+The consumer will look something like this:
+
+	spin_lock(&consumer_lock);
+
+	unsigned long head = ACCESS_ONCE(buffer->head);
+	unsigned long tail = buffer->tail;
+
+	if (CIRC_CNT(head, tail, buffer->size) >= 1) {
+		/* read index before reading contents at that index */
+		smp_read_barrier_depends();
+
+		/* extract one item from the buffer */
+		struct item *item = buffer[tail];
+
+		consume_item(item);
+
+		smp_mb(); /* finish reading descriptor before incrementing tail */
+
+		buffer->tail = (tail + 1) & (buffer->size - 1);
+	}
+
+	spin_unlock(&consumer_lock);
+
+This will instruct the CPU to make sure the index is up to date before reading
+the new item, and then it shall make sure the CPU has finished reading the item
+before it writes the new tail pointer, which will erase the item.
+
+
+Note the use of ACCESS_ONCE() in both algorithms to read the opposition index.
+This prevents the compiler from discarding and reloading its cached value -
+which some compilers will do across smp_read_barrier_depends().  This isn't
+strictly needed if you can be sure that the opposition index will _only_ be
+used the once.
+
+
+===============
+FURTHER READING
+===============
+
+See also Documentation/memory-barriers.txt for a description of Linux's memory
+barrier facilities.

Documentation/connector/cn_test.c

@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/skbuff.h>
+#include <linux/slab.h>
 #include <linux/timer.h>
 
 #include <linux/connector.h>

Documentation/fb/efifb.txt

@@ -1,9 +1,9 @@
 
-What is imacfb?
+What is efifb?
 ===============
 
 This is a generic EFI platform driver for Intel based Apple computers.
-Imacfb is only for EFI booted Intel Macs.
+efifb is only for EFI booted Intel Macs.
 
 Supported Hardware
 ==================
@@ -16,16 +16,16 @@ MacMini
 How to use it?
 ==============
 
-Imacfb does not have any kind of autodetection of your machine.
+efifb does not have any kind of autodetection of your machine.
 You have to add the following kernel parameters in your elilo.conf:
 	Macbook :
-		video=imacfb:macbook
+		video=efifb:macbook
 	MacMini :
-		video=imacfb:mini
+		video=efifb:mini
 	Macbook Pro 15", iMac 17" :
-		video=imacfb:i17
+		video=efifb:i17
 	Macbook Pro 17", iMac 20" :
-		video=imacfb:i20
+		video=efifb:i20
 
 --
 Edgar Hucek <gimli@dark-green.com>

Documentation/feature-removal-schedule.txt

@@ -599,3 +599,26 @@ Why:	Useful in 2003, implementation is a hack.
 	Generally invoked by accident today.
 	Seen as doing more harm than good.
 Who:	Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:	video4linux /dev/vtx teletext API support
+When:	2.6.35
+Files:	drivers/media/video/saa5246a.c drivers/media/video/saa5249.c
+	include/linux/videotext.h
+Why:	The vtx device nodes have been superseded by vbi device nodes
+	for many years. No applications exist that use the vtx support.
+	Of the two i2c drivers that actually support this API the saa5249
+	has been impossible to use for a year now and no known hardware
+	that supports this device exists. The saa5246a is theoretically
+	supported by the old mxb boards, but it never actually worked.
+
+	In summary: there is no hardware that can use this API and there
+	are no applications actually implementing this API.
+
+	The vtx support still reserves minors 192-223 and we would really
+	like to reuse those for upcoming new functionality. In the unlikely
+	event that new hardware appears that wants to use the functionality
+	provided by the vtx API, then that functionality should be build
+	around the sliced VBI API instead.
+Who:	Hans Verkuil <hverkuil@xs4all.nl>

Documentation/filesystems/00-INDEX

@@ -16,6 +16,8 @@ befs.txt
 	- information about the BeOS filesystem for Linux.
 bfs.txt
 	- info for the SCO UnixWare Boot Filesystem (BFS).
+ceph.txt
+	- info for the Ceph Distributed File System
 cifs.txt
 	- description of the CIFS filesystem.
 coda.txt

Documentation/filesystems/9p.txt

@@ -37,6 +37,15 @@ For Plan 9 From User Space applications (http://swtch.com/plan9)
 
 	mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER
 
+For server running on QEMU host with virtio transport:
+
+	mount -t 9p -o trans=virtio <mount_tag> /mnt/9
+
+where mount_tag is the tag associated by the server to each of the exported
+mount points. Each 9P export is seen by the client as a virtio device with an
+associated "mount_tag" property. Available mount tags can be
+seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files.
+
 OPTIONS
 =======
 
@@ -47,7 +56,7 @@ OPTIONS
 			fd   	- used passed file descriptors for connection
                                 (see rfdno and wfdno)
 			virtio	- connect to the next virtio channel available
-				(from lguest or KVM with trans_virtio module)
+				(from QEMU with trans_virtio module)
 			rdma	- connect to a specified RDMA channel
 
   uname=name	user name to attempt mount as on the remote server.  The
@@ -85,7 +94,12 @@ OPTIONS
 
   port=n	port to connect to on the remote server
 
-  noextend	force legacy mode (no 9p2000.u semantics)
+  noextend	force legacy mode (no 9p2000.u or 9p2000.L semantics)
+
+  version=name	Select 9P protocol version. Valid options are:
+			9p2000          - Legacy mode (same as noextend)
+			9p2000.u        - Use 9P2000.u protocol
+			9p2000.L        - Use 9P2000.L protocol
 
   dfltuid	attempt to mount as a particular uid
 

Documentation/filesystems/ceph.txt

@@ -0,0 +1,140 @@
+Ceph Distributed File System
+============================
+
+Ceph is a distributed network file system designed to provide good
+performance, reliability, and scalability.
+
+Basic features include:
+
+ * POSIX semantics
+ * Seamless scaling from 1 to many thousands of nodes
+ * High availability and reliability.  No single point of failure.
+ * N-way replication of data across storage nodes
+ * Fast recovery from node failures
+ * Automatic rebalancing of data on node addition/removal
+ * Easy deployment: most FS components are userspace daemons
+
+Also,
+ * Flexible snapshots (on any directory)
+ * Recursive accounting (nested files, directories, bytes)
+
+In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely
+on symmetric access by all clients to shared block devices, Ceph
+separates data and metadata management into independent server
+clusters, similar to Lustre.  Unlike Lustre, however, metadata and
+storage nodes run entirely as user space daemons.  Storage nodes
+utilize btrfs to store data objects, leveraging its advanced features
+(checksumming, metadata replication, etc.).  File data is striped
+across storage nodes in large chunks to distribute workload and
+facilitate high throughputs.  When storage nodes fail, data is
+re-replicated in a distributed fashion by the storage nodes themselves
+(with some minimal coordination from a cluster monitor), making the
+system extremely efficient and scalable.
+
+Metadata servers effectively form a large, consistent, distributed
+in-memory cache above the file namespace that is extremely scalable,
+dynamically redistributes metadata in response to workload changes,
+and can tolerate arbitrary (well, non-Byzantine) node failures.  The
+metadata server takes a somewhat unconventional approach to metadata
+storage to significantly improve performance for common workloads.  In
+particular, inodes with only a single link are embedded in
+directories, allowing entire directories of dentries and inodes to be
+loaded into its cache with a single I/O operation.  The contents of
+extremely large directories can be fragmented and managed by
+independent metadata servers, allowing scalable concurrent access.
+
+The system offers automatic data rebalancing/migration when scaling
+from a small cluster of just a few nodes to many hundreds, without
+requiring an administrator carve the data set into static volumes or
+go through the tedious process of migrating data between servers.
+When the file system approaches full, new nodes can be easily added
+and things will "just work."
+
+Ceph includes flexible snapshot mechanism that allows a user to create
+a snapshot on any subdirectory (and its nested contents) in the
+system.  Snapshot creation and deletion are as simple as 'mkdir
+.snap/foo' and 'rmdir .snap/foo'.
+
+Ceph also provides some recursive accounting on directories for nested
+files and bytes.  That is, a 'getfattr -d foo' on any directory in the
+system will reveal the total number of nested regular files and
+subdirectories, and a summation of all nested file sizes.  This makes
+the identification of large disk space consumers relatively quick, as
+no 'du' or similar recursive scan of the file system is required.
+
+
+Mount Syntax
+============
+
+The basic mount syntax is:
+
+ # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt
+
+You only need to specify a single monitor, as the client will get the
+full list when it connects.  (However, if the monitor you specify
+happens to be down, the mount won't succeed.)  The port can be left
+off if the monitor is using the default.  So if the monitor is at
+1.2.3.4,
+
+ # mount -t ceph 1.2.3.4:/ /mnt/ceph
+
+is sufficient.  If /sbin/mount.ceph is installed, a hostname can be
+used instead of an IP address.
+
+
+
+Mount Options
+=============
+
+  ip=A.B.C.D[:N]
+	Specify the IP and/or port the client should bind to locally.
+	There is normally not much reason to do this.  If the IP is not
+	specified, the client's IP address is determined by looking at the
+	address it's connection to the monitor originates from.
+
+  wsize=X
+	Specify the maximum write size in bytes.  By default there is no
+	maximum.  Ceph will normally size writes based on the file stripe
+	size.
+
+  rsize=X
+	Specify the maximum readahead.
+
+  mount_timeout=X
+	Specify the timeout value for mount (in seconds), in the case
+	of a non-responsive Ceph file system.  The default is 30
+	seconds.
+
+  rbytes
+	When stat() is called on a directory, set st_size to 'rbytes',
+	the summation of file sizes over all files nested beneath that
+	directory.  This is the default.
+
+  norbytes
+	When stat() is called on a directory, set st_size to the
+	number of entries in that directory.
+
+  nocrc
+	Disable CRC32C calculation for data writes.  If set, the storage node
+	must rely on TCP's error correction to detect data corruption
+	in the data payload.
+
+  noasyncreaddir
+	Disable client's use its local cache to satisfy	readdir
+	requests.  (This does not change correctness; the client uses
+	cached metadata only when a lease or capability ensures it is
+	valid.)
+
+
+More Information
+================
+
+For more information on Ceph, see the home page at
+	http://ceph.newdream.net/
+
+The Linux kernel client source tree is available at
+	git://ceph.newdream.net/git/ceph-client.git
+	git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+
+and the source for the full system is at
+	git://ceph.newdream.net/git/ceph.git

Documentation/filesystems/tmpfs.txt

@@ -82,11 +82,13 @@ tmpfs has a mount option to set the NUMA memory allocation policy for
 all files in that instance (if CONFIG_NUMA is enabled) - which can be
 adjusted on the fly via 'mount -o remount ...'
 
-mpol=default             prefers to allocate memory from the local node
+mpol=default             use the process allocation policy
+                         (see set_mempolicy(2))
 mpol=prefer:Node         prefers to allocate memory from the given Node
 mpol=bind:NodeList       allocates memory only from nodes in NodeList
 mpol=interleave          prefers to allocate from each node in turn
 mpol=interleave:NodeList allocates from each node of NodeList in turn
+mpol=local		 prefers to allocate memory from the local node
 
 NodeList format is a comma-separated list of decimal numbers and ranges,
 a range being two hyphen-separated decimal numbers, the smallest and
@@ -134,3 +136,5 @@ Author:
    Christoph Rohland <cr@sap.com>, 1.12.01
 Updated:
    Hugh Dickins, 4 June 2007
+Updated:
+   KOSAKI Motohiro, 16 Mar 2010