Merge branch 'master' into next

author: James Morris <jmorris@namei.org> 2010-03-31 08:39:27 +1100
committer: James Morris <jmorris@namei.org> 2010-03-31 08:39:27 +1100
commit: d25d6fa1a95f465ff1ec4458ca15e30b2c8dffec (patch)
tree: 7362b182dedd825fc762ef7706830837e42943af /Documentation
parent: 225a9be24d799aa16d543c31fb09f0c9ed1d9caa (diff)
parent: 2eaa9cfdf33b8d7fb7aff27792192e0019ae8fc6 (diff)
86 files changed, 3581 insertions, 1434 deletions
diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
new file mode 100644
index 00000000000..49b82cad700
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -0,0 +1,7 @@
+What:		/sys/devices/system/node/nodeX
+Date:		October 2002
+Contact:	Linux Memory Management list <linux-mm@kvack.org>
+Description:
+		When CONFIG_NUMA is enabled, this is a directory containing
+		information on node X such as what CPUs are local to the
+		node.
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index a986e9bbba3..bcebb9eaedc 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/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:
diff --git a/Documentation/PCI/PCI-DMA-mapping.txt b/Documentation/DMA-API-HOWTO.txt
index ecad88d9fe5..52618ab069a 100644
--- a/Documentation/PCI/PCI-DMA-mapping.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -1,12 +1,12 @@
-			Dynamic DMA mapping
-			===================
+		     Dynamic DMA mapping Guide
+		     =========================
 
 		 David S. Miller <davem@redhat.com>
 		 Richard Henderson <rth@cygnus.com>
 		  Jakub Jelinek <jakub@redhat.com>
 
-This document describes the DMA mapping system in terms of the pci_
-API.  For a similar API that works for generic devices, see
+This is a guide to device driver writers on how to use the DMA API
+with example pseudo-code.  For a concise description of the API, see
 DMA-API.txt.
 
 Most of the 64bit platforms have special hardware that translates bus
@@ -26,12 +26,15 @@ mapped only for the time they are actually used and unmapped after the DMA
 transfer.
 
 The following API will work of course even on platforms where no such
-hardware exists, see e.g. arch/x86/include/asm/pci.h for how it is implemented on
-top of the virt_to_bus interface.
+hardware exists.
+
+Note that the DMA API works with any bus independent of the underlying
+microprocessor architecture. You should use the DMA API rather than
+the bus specific DMA API (e.g. pci_dma_*).
 
 First of all, you should make sure
 
-#include <linux/pci.h>
+#include <linux/dma-mapping.h>
 
 is in your driver. This file will obtain for you the definition of the
 dma_addr_t (which can hold any valid DMA address for the platform)
@@ -78,44 +81,43 @@ for you to DMA from/to.
 			DMA addressing limitations
 
 Does your device have any DMA addressing limitations?  For example, is
-your device only capable of driving the low order 24-bits of address
-on the PCI bus for SAC DMA transfers?  If so, you need to inform the
-PCI layer of this fact.
+your device only capable of driving the low order 24-bits of address?
+If so, you need to inform the kernel of this fact.
 
 By default, the kernel assumes that your device can address the full
-32-bits in a SAC cycle.  For a 64-bit DAC capable device, this needs
-to be increased.  And for a device with limitations, as discussed in
-the previous paragraph, it needs to be decreased.
-
-pci_alloc_consistent() by default will return 32-bit DMA addresses.
-PCI-X specification requires PCI-X devices to support 64-bit
-addressing (DAC) for all transactions. And at least one platform (SGI
-SN2) requires 64-bit consistent allocations to operate correctly when
-the IO bus is in PCI-X mode. Therefore, like with pci_set_dma_mask(),
-it's good practice to call pci_set_consistent_dma_mask() to set the
-appropriate mask even if your device only supports 32-bit DMA
-(default) and especially if it's a PCI-X device.
-
-For correct operation, you must interrogate the PCI layer in your
-device probe routine to see if the PCI controller on the machine can
-properly support the DMA addressing limitation your device has.  It is
-good style to do this even if your device holds the default setting,
+32-bits.  For a 64-bit capable device, this needs to be increased.
+And for a device with limitations, as discussed in the previous
+paragraph, it needs to be decreased.
+
+Special note about PCI: PCI-X specification requires PCI-X devices to
+support 64-bit addressing (DAC) for all transactions.  And at least
+one platform (SGI SN2) requires 64-bit consistent allocations to
+operate correctly when the IO bus is in PCI-X mode.
+
+For correct operation, you must interrogate the kernel in your device
+probe routine to see if the DMA controller on the machine can properly
+support the DMA addressing limitation your device has.  It is good
+style to do this even if your device holds the default setting,
 because this shows that you did think about these issues wrt. your
 device.
 
-The query is performed via a call to pci_set_dma_mask():
+The query is performed via a call to dma_set_mask():
 
-	int pci_set_dma_mask(struct pci_dev *pdev, u64 device_mask);
+	int dma_set_mask(struct device *dev, u64 mask);
 
 The query for consistent allocations is performed via a call to
-pci_set_consistent_dma_mask():
+dma_set_coherent_mask():
 
-	int pci_set_consistent_dma_mask(struct pci_dev *pdev, u64 device_mask);
+	int dma_set_coherent_mask(struct device *dev, u64 mask);
 
-Here, pdev is a pointer to the PCI device struct of your device, and
-device_mask is a bit mask describing which bits of a PCI address your
-device supports.  It returns zero if your card can perform DMA
-properly on the machine given the address mask you provided.
+Here, dev is a pointer to the device struct of your device, and mask
+is a bit mask describing which bits of an address your device
+supports.  It returns zero if your card can perform DMA properly on
+the machine given the address mask you provided.  In general, the
+device struct of your device is embedded in the bus specific device
+struct of your device.  For example, a pointer to the device struct of
+your PCI device is pdev->dev (pdev is a pointer to the PCI device
+struct of your device).
 
 If it returns non-zero, your device cannot perform DMA properly on
 this platform, and attempting to do so will result in undefined
@@ -133,31 +135,30 @@ of your driver reports that performance is bad or that the device is not
 even detected, you can ask them for the kernel messages to find out
 exactly why.
 
-The standard 32-bit addressing PCI device would do something like
-this:
+The standard 32-bit addressing device would do something like this:
 
-	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+	if (dma_set_mask(dev, DMA_BIT_MASK(32))) {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
 	}
 
-Another common scenario is a 64-bit capable device.  The approach
-here is to try for 64-bit DAC addressing, but back down to a
-32-bit mask should that fail.  The PCI platform code may fail the
-64-bit mask not because the platform is not capable of 64-bit
-addressing.  Rather, it may fail in this case simply because
-32-bit SAC addressing is done more efficiently than DAC addressing.
-Sparc64 is one platform which behaves in this way.
+Another common scenario is a 64-bit capable device.  The approach here
+is to try for 64-bit addressing, but back down to a 32-bit mask that
+should not fail.  The kernel may fail the 64-bit mask not because the
+platform is not capable of 64-bit addressing.  Rather, it may fail in
+this case simply because 32-bit addressing is done more efficiently
+than 64-bit addressing.  For example, Sparc64 PCI SAC addressing is
+more efficient than DAC addressing.
 
 Here is how you would handle a 64-bit capable device which can drive
 all 64-bits when accessing streaming DMA:
 
 	int using_dac;
 
-	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+	if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
-	} else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+	} else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
 		using_dac = 0;
 	} else {
 		printk(KERN_WARNING
@@ -170,36 +171,36 @@ the case would look like this:
 
 	int using_dac, consistent_using_dac;
 
-	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+	if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
 	   	consistent_using_dac = 1;
-		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	} else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+		dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
+	} else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
 		using_dac = 0;
 		consistent_using_dac = 0;
-		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
 	} else {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
 	}
 
-pci_set_consistent_dma_mask() will always be able to set the same or a
-smaller mask as pci_set_dma_mask(). However for the rare case that a
+dma_set_coherent_mask() will always be able to set the same or a
+smaller mask as dma_set_mask(). However for the rare case that a
 device driver only uses consistent allocations, one would have to
-check the return value from pci_set_consistent_dma_mask().
+check the return value from dma_set_coherent_mask().
 
 Finally, if your device can only drive the low 24-bits of
-address during PCI bus mastering you might do something like:
+address you might do something like:
 
-	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(24))) {
+	if (dma_set_mask(dev, DMA_BIT_MASK(24))) {
 		printk(KERN_WARNING
 		       "mydev: 24-bit DMA addressing not available.\n");
 		goto ignore_this_device;
 	}
 
-When pci_set_dma_mask() is successful, and returns zero, the PCI layer
-saves away this mask you have provided.  The PCI layer will use this
+When dma_set_mask() is successful, and returns zero, the kernel saves
+away this mask you have provided.  The kernel will use this
 information later when you make DMA mappings.
 
 There is a case which we are aware of at this time, which is worth
@@ -208,7 +209,7 @@ functions (for example a sound card provides playback and record
 functions) and the various different functions have _different_
 DMA addressing limitations, you may wish to probe each mask and
 only provide the functionality which the machine can handle.  It
-is important that the last call to pci_set_dma_mask() be for the
+is important that the last call to dma_set_mask() be for the
 most specific mask.
 
 Here is pseudo-code showing how this might be done:
@@ -217,17 +218,17 @@ Here is pseudo-code showing how this might be done:
 	#define RECORD_ADDRESS_BITS	DMA_BIT_MASK(24)
 
 	struct my_sound_card *card;
-	struct pci_dev *pdev;
+	struct device *dev;
 
 	...
-	if (!pci_set_dma_mask(pdev, PLAYBACK_ADDRESS_BITS)) {
+	if (!dma_set_mask(dev, PLAYBACK_ADDRESS_BITS)) {
 		card->playback_enabled = 1;
 	} else {
 		card->playback_enabled = 0;
 		printk(KERN_WARNING "%s: Playback disabled due to DMA limitations.\n",
 		       card->name);
 	}
-	if (!pci_set_dma_mask(pdev, RECORD_ADDRESS_BITS)) {
+	if (!dma_set_mask(dev, RECORD_ADDRESS_BITS)) {
 		card->record_enabled = 1;
 	} else {
 		card->record_enabled = 0;
@@ -252,8 +253,8 @@ There are two types of DMA mappings:
   Think of "consistent" as "synchronous" or "coherent".
 
   The current default is to return consistent memory in the low 32
-  bits of the PCI bus space.  However, for future compatibility you
-  should set the consistent mask even if this default is fine for your
+  bits of the bus space.  However, for future compatibility you should
+  set the consistent mask even if this default is fine for your
   driver.
 
   Good examples of what to use consistent mappings for are:
@@ -285,9 +286,9 @@ There are two types of DMA mappings:
 	     found in PCI bridges (such as by reading a register's value
 	     after writing it).
 
-- Streaming DMA mappings which are usually mapped for one DMA transfer,
-  unmapped right after it (unless you use pci_dma_sync_* below) and for which
-  hardware can optimize for sequential accesses.
+- Streaming DMA mappings which are usually mapped for one DMA
+  transfer, unmapped right after it (unless you use dma_sync_* below)
+  and for which hardware can optimize for sequential accesses.
 
   This of "streaming" as "asynchronous" or "outside the coherency
   domain".
@@ -302,8 +303,8 @@ There are two types of DMA mappings:
   optimizations the hardware allows.  To this end, when using
   such mappings you must be explicit about what you want to happen.
 
-Neither type of DMA mapping has alignment restrictions that come
-from PCI, although some devices may have such restrictions.
+Neither type of DMA mapping has alignment restrictions that come from
+the underlying bus, although some devices may have such restrictions.
 Also, systems with caches that aren't DMA-coherent will work better
 when the underlying buffers don't share cache lines with other data.
 
@@ -315,33 +316,27 @@ you should do:
 
 	dma_addr_t dma_handle;
 
-	cpu_addr = pci_alloc_consistent(pdev, size, &dma_handle);
-
-where pdev is a struct pci_dev *. This may be called in interrupt context.
-You should use dma_alloc_coherent (see DMA-API.txt) for buses
-where devices don't have struct pci_dev (like ISA, EISA).
+	cpu_addr = dma_alloc_coherent(dev, size, &dma_handle, gfp);
 
-This argument is needed because the DMA translations may be bus
-specific (and often is private to the bus which the device is attached
-to).
+where device is a struct device *. This may be called in interrupt
+context with the GFP_ATOMIC flag.
 
 Size is the length of the region you want to allocate, in bytes.
 
 This routine will allocate RAM for that region, so it acts similarly to
 __get_free_pages (but takes size instead of a page order).  If your
 driver needs regions sized smaller than a page, you may prefer using
-the pci_pool interface, described below.
-
-The consistent DMA mapping interfaces, for non-NULL pdev, will by
-default return a DMA address which is SAC (Single Address Cycle)
-addressable.  Even if the device indicates (via PCI dma mask) that it
-may address the upper 32-bits and thus perform DAC cycles, consistent
-allocation will only return > 32-bit PCI addresses for DMA if the
-consistent dma mask has been explicitly changed via
-pci_set_consistent_dma_mask().  This is true of the pci_pool interface
-as well.
-
-pci_alloc_consistent returns two values: the virtual address which you
+the dma_pool interface, described below.
+
+The consistent DMA mapping interfaces, for non-NULL dev, will by
+default return a DMA address which is 32-bit addressable.  Even if the
+device indicates (via DMA mask) that it may address the upper 32-bits,
+consistent allocation will only return > 32-bit addresses for DMA if
+the consistent DMA mask has been explicitly changed via
+dma_set_coherent_mask().  This is true of the dma_pool interface as
+well.
+
+dma_alloc_coherent returns two values: the virtual address which you
 can use to access it from the CPU and dma_handle which you pass to the
 card.
 
@@ -354,54 +349,54 @@ buffer you receive will not cross a 64K boundary.
 
 To unmap and free such a DMA region, you call:
 
-	pci_free_consistent(pdev, size, cpu_addr, dma_handle);
+	dma_free_coherent(dev, size, cpu_addr, dma_handle);
 
-where pdev, size are the same as in the above call and cpu_addr and
-dma_handle are the values pci_alloc_consistent returned to you.
+where dev, size are the same as in the above call and cpu_addr and
+dma_handle are the values dma_alloc_coherent returned to you.
 This function may not be called in interrupt context.
 
 If your driver needs lots of smaller memory regions, you can write
-custom code to subdivide pages returned by pci_alloc_consistent,
-or you can use the pci_pool API to do that.  A pci_pool is like
-a kmem_cache, but it uses pci_alloc_consistent not __get_free_pages.
+custom code to subdivide pages returned by dma_alloc_coherent,
+or you can use the dma_pool API to do that.  A dma_pool is like
+a kmem_cache, but it uses dma_alloc_coherent not __get_free_pages.
 Also, it understands common hardware constraints for alignment,
 like queue heads needing to be aligned on N byte boundaries.
 
-Create a pci_pool like this:
+Create a dma_pool like this:
 
-	struct pci_pool *pool;
+	struct dma_pool *pool;
 
-	pool = pci_pool_create(name, pdev, size, align, alloc);
+	pool = dma_pool_create(name, dev, size, align, alloc);
 
-The "name" is for diagnostics (like a kmem_cache name); pdev and size
+The "name" is for diagnostics (like a kmem_cache name); dev and size
 are as above.  The device's hardware alignment requirement for this
 type of data is "align" (which is expressed in bytes, and must be a
 power of two).  If your device has no boundary crossing restrictions,
 pass 0 for alloc; passing 4096 says memory allocated from this pool
 must not cross 4KByte boundaries (but at that time it may be better to
-go for pci_alloc_consistent directly instead).
+go for dma_alloc_coherent directly instead).
 
-Allocate memory from a pci pool like this:
+Allocate memory from a dma pool like this:
 
-	cpu_addr = pci_pool_alloc(pool, flags, &dma_handle);
+	cpu_addr = dma_pool_alloc(pool, flags, &dma_handle);
 
 flags are SLAB_KERNEL if blocking is permitted (not in_interrupt nor
-holding SMP locks), SLAB_ATOMIC otherwise.  Like pci_alloc_consistent,
+holding SMP locks), SLAB_ATOMIC otherwise.  Like dma_alloc_coherent,
 this returns two values, cpu_addr and dma_handle.
 
-Free memory that was allocated from a pci_pool like this:
+Free memory that was allocated from a dma_pool like this:
 
-	pci_pool_free(pool, cpu_addr, dma_handle);
+	dma_pool_free(pool, cpu_addr, dma_handle);
 
-where pool is what you passed to pci_pool_alloc, and cpu_addr and
-dma_handle are the values pci_pool_alloc returned. This function
+where pool is what you passed to dma_pool_alloc, and cpu_addr and
+dma_handle are the values dma_pool_alloc returned. This function
 may be called in interrupt context.
 
-Destroy a pci_pool by calling:
+Destroy a dma_pool by calling:
 
-	pci_pool_destroy(pool);
+	dma_pool_destroy(pool);
 
-Make sure you've called pci_pool_free for all memory allocated
+Make sure you've called dma_pool_free for all memory allocated
 from a pool before you destroy the pool. This function may not
 be called in interrupt context.
 
@@ -411,15 +406,15 @@ The interfaces described in subsequent portions of this document
 take a DMA direction argument, which is an integer and takes on
 one of the following values:
 
- PCI_DMA_BIDIRECTIONAL
- PCI_DMA_TODEVICE
- PCI_DMA_FROMDEVICE
- PCI_DMA_NONE
+ DMA_BIDIRECTIONAL
+ DMA_TO_DEVICE
+ DMA_FROM_DEVICE
+ DMA_NONE
 
 One should provide the exact DMA direction if you know it.
 
-PCI_DMA_TODEVICE means "from main memory to the PCI device"
-PCI_DMA_FROMDEVICE means "from the PCI device to main memory"
+DMA_TO_DEVICE means "from main memory to the device"
+DMA_FROM_DEVICE means "from the device to main memory"
 It is the direction in which the data moves during the DMA
 transfer.
 
@@ -427,12 +422,12 @@ You are _strongly_ encouraged to specify this as precisely
 as you possibly can.
 
 If you absolutely cannot know the direction of the DMA transfer,
-specify PCI_DMA_BIDIRECTIONAL.  It means that the DMA can go in
+specify DMA_BIDIRECTIONAL.  It means that the DMA can go in
 either direction.  The platform guarantees that you may legally
 specify this, and that it will work, but this may be at the
 cost of performance for example.
 
-The value PCI_DMA_NONE is to be used for debugging.  One can
+The value DMA_NONE is to be used for debugging.  One can
 hold this in a data structure before you come to know the
 precise direction, and this will help catch cases where your
 direction tracking logic has failed to set things up properly.
@@ -442,21 +437,21 @@ potential platform-specific optimizations of such) is for debugging.
 Some platforms actually have a write permission boolean which DMA
 mappings can be marked with, much like page protections in the user
 program address space.  Such platforms can and do report errors in the
-kernel logs when the PCI controller hardware detects violation of the
+kernel logs when the DMA controller hardware detects violation of the
 permission setting.
 
 Only streaming mappings specify a direction, consistent mappings
 implicitly have a direction attribute setting of
-PCI_DMA_BIDIRECTIONAL.
+DMA_BIDIRECTIONAL.
 
 The SCSI subsystem tells you the direction to use in the
 'sc_data_direction' member of the SCSI command your driver is
 working on.
 
 For Networking drivers, it's a rather simple affair.  For transmit
-packets, map/unmap them with the PCI_DMA_TODEVICE direction
+packets, map/unmap them with the DMA_TO_DEVICE direction
 specifier.  For receive packets, just the opposite, map/unmap them
-with the PCI_DMA_FROMDEVICE direction specifier.
+with the DMA_FROM_DEVICE direction specifier.
 
 		  Using Streaming DMA mappings
 
@@ -467,43 +462,43 @@ scatterlist.
 
 To map a single region, you do:
 
-	struct pci_dev *pdev = mydev->pdev;
+	struct device *dev = &my_dev->dev;
 	dma_addr_t dma_handle;
 	void *addr = buffer->ptr;
 	size_t size = buffer->len;
 
-	dma_handle = pci_map_single(pdev, addr, size, direction);
+	dma_handle = dma_map_single(dev, addr, size, direction);
 
 and to unmap it:
 
-	pci_unmap_single(pdev, dma_handle, size, direction);
+	dma_unmap_single(dev, dma_handle, size, direction);
 
-You should call pci_unmap_single when the DMA activity is finished, e.g.
+You should call dma_unmap_single when the DMA activity is finished, e.g.
 from the interrupt which told you that the DMA transfer is done.
 
 Using cpu pointers like this for single mappings has a disadvantage,
 you cannot reference HIGHMEM memory in this way.  Thus, there is a
-map/unmap interface pair akin to pci_{map,unmap}_single.  These
+map/unmap interface pair akin to dma_{map,unmap}_single.  These
 interfaces deal with page/offset pairs instead of cpu pointers.
 Specifically:
 
-	struct pci_dev *pdev = mydev->pdev;
+	struct device *dev = &my_dev->dev;
 	dma_addr_t dma_handle;
 	struct page *page = buffer->page;
 	unsigned long offset = buffer->offset;
 	size_t size = buffer->len;
 
-	dma_handle = pci_map_page(pdev, page, offset, size, direction);
+	dma_handle = dma_map_page(dev, page, offset, size, direction);
 
 	...
 
-	pci_unmap_page(pdev, dma_handle, size, direction);
+	dma_unmap_page(dev, dma_handle, size, direction);
 
 Here, "offset" means byte offset within the given page.
 
 With scatterlists, you map a region gathered from several regions by:
 
-	int i, count = pci_map_sg(pdev, sglist, nents, direction);
+	int i, count = dma_map_sg(dev, sglist, nents, direction);
 	struct scatterlist *sg;
 
 	for_each_sg(sglist, sg, count, i) {
@@ -527,16 +522,16 @@ accessed sg->address and sg->length as shown above.
 
 To unmap a scatterlist, just call:
 
-	pci_unmap_sg(pdev, sglist, nents, direction);
+	dma_unmap_sg(dev, sglist, nents, direction);
 
 Again, make sure DMA activity has already finished.
 
-PLEASE NOTE:  The 'nents' argument to the pci_unmap_sg call must be
-              the _same_ one you passed into the pci_map_sg call,
+PLEASE NOTE:  The 'nents' argument to the dma_unmap_sg call must be
+              the _same_ one you passed into the dma_map_sg call,
 	      it should _NOT_ be the 'count' value _returned_ from the
-              pci_map_sg call.
+              dma_map_sg call.
 
-Every pci_map_{single,sg} call should have its pci_unmap_{single,sg}
+Every dma_map_{single,sg} call should have its dma_unmap_{single,sg}
 counterpart, because the bus address space is a shared resource (although
 in some ports the mapping is per each BUS so less devices contend for the
 same bus address space) and you could render the machine unusable by eating
@@ -547,14 +542,14 @@ the data in between the DMA transfers, the buffer needs to be synced
 properly in order for the cpu and device to see the most uptodate and
 correct copy of the DMA buffer.
 
-So, firstly, just map it with pci_map_{single,sg}, and after each DMA
+So, firstly, just map it with dma_map_{single,sg}, and after each DMA
 transfer call either:
 
-	pci_dma_sync_single_for_cpu(pdev, dma_handle, size, direction);
+	dma_sync_single_for_cpu(dev, dma_handle, size, direction);
 
 or:
 
-	pci_dma_sync_sg_for_cpu(pdev, sglist, nents, direction);
+	dma_sync_sg_for_cpu(dev, sglist, nents, direction);
 
 as appropriate.
 
@@ -562,27 +557,27 @@ Then, if you wish to let the device get at the DMA area again,
 finish accessing the data with the cpu, and then before actually
 giving the buffer to the hardware call either:
 
-	pci_dma_sync_single_for_device(pdev, dma_handle, size, direction);
+	dma_sync_single_for_device(dev, dma_handle, size, direction);
 
 or:
 
-	pci_dma_sync_sg_for_device(dev, sglist, nents, direction);
+	dma_sync_sg_for_device(dev, sglist, nents, direction);
 
 as appropriate.
 
 After the last DMA transfer call one of the DMA unmap routines
-pci_unmap_{single,sg}. If you don't touch the data from the first pci_map_*
-call till pci_unmap_*, then you don't have to call the pci_dma_sync_*
+dma_unmap_{single,sg}. If you don't touch the data from the first dma_map_*
+call till dma_unmap_*, then you don't have to call the dma_sync_*
 routines at all.
 
 Here is pseudo code which shows a situation in which you would need
-to use the pci_dma_sync_*() interfaces.
+to use the dma_sync_*() interfaces.
 
 	my_card_setup_receive_buffer(struct my_card *cp, char *buffer, int len)
 	{
 		dma_addr_t mapping;
 
-		mapping = pci_map_single(cp->pdev, buffer, len, PCI_DMA_FROMDEVICE);
+		mapping = dma_map_single(cp->dev, buffer, len, DMA_FROM_DEVICE);
 
 		cp->rx_buf = buffer;
 		cp->rx_len = len;
@@ -606,25 +601,25 @@ to use the pci_dma_sync_*() interfaces.
 			 * the DMA transfer with the CPU first
 			 * so that we see updated contents.
 			 */
-			pci_dma_sync_single_for_cpu(cp->pdev, cp->rx_dma,
-						    cp->rx_len,
-						    PCI_DMA_FROMDEVICE);
+			dma_sync_single_for_cpu(&cp->dev, cp->rx_dma,
+						cp->rx_len,
+						DMA_FROM_DEVICE);
 
 			/* Now it is safe to examine the buffer. */
 			hp = (struct my_card_header *) cp->rx_buf;
 			if (header_is_ok(hp)) {
-				pci_unmap_single(cp->pdev, cp->rx_dma, cp->rx_len,
-						 PCI_DMA_FROMDEVICE);
+				dma_unmap_single(&cp->dev, cp->rx_dma, cp->rx_len,
+						 DMA_FROM_DEVICE);
 				pass_to_upper_layers(cp->rx_buf);
 				make_and_setup_new_rx_buf(cp);
 			} else {
 				/* Just sync the buffer and give it back
 				 * to the card.
 				 */
-				pci_dma_sync_single_for_device(cp->pdev,
-							       cp->rx_dma,
-							       cp->rx_len,
-							       PCI_DMA_FROMDEVICE);
+				dma_sync_single_for_device(&cp->dev,
+							   cp->rx_dma,
+							   cp->rx_len,
+							   DMA_FROM_DEVICE);
 				give_rx_buf_to_card(cp);
 			}
 		}
@@ -634,19 +629,19 @@ Drivers converted fully to this interface should not use virt_to_bus any
 longer, nor should they use bus_to_virt. Some drivers have to be changed a
 little bit, because there is no longer an equivalent to bus_to_virt in the
 dynamic DMA mapping scheme - you have to always store the DMA addresses
-returned by the pci_alloc_consistent, pci_pool_alloc, and pci_map_single
-calls (pci_map_sg stores them in the scatterlist itself if the platform
+returned by the dma_alloc_coherent, dma_pool_alloc, and dma_map_single
+calls (dma_map_sg stores them in the scatterlist itself if the platform
 supports dynamic DMA mapping in hardware) in your driver structures and/or
 in the card registers.
 
-All PCI drivers should be using these interfaces with no exceptions.
-It is planned to completely remove virt_to_bus() and bus_to_virt() as
+All drivers should be using these interfaces with no exceptions.  It
+is planned to completely remove virt_to_bus() and bus_to_virt() as
 they are entirely deprecated.  Some ports already do not provide these
 as it is impossible to correctly support them.
 
 		Optimizing Unmap State Space Consumption
 
-On many platforms, pci_unmap_{single,page}() is simply a nop.
+On many platforms, dma_unmap_{single,page}() is simply a nop.
 Therefore, keeping track of the mapping address and length is a waste
 of space.  Instead of filling your drivers up with ifdefs and the like
 to "work around" this (which would defeat the whole purpose of a
@@ -655,7 +650,7 @@ portable API) the following facilities are provided.
 Actually, instead of describing the macros one by one, we'll
 transform some example code.
 
-1) Use DECLARE_PCI_UNMAP_{ADDR,LEN} in state saving structures.
+1) Use DEFINE_DMA_UNMAP_{ADDR,LEN} in state saving structures.
    Example, before:
 
 	struct ring_state {
@@ -668,14 +663,11 @@ transform some example code.
 
 	struct ring_state {
 		struct sk_buff *skb;
-		DECLARE_PCI_UNMAP_ADDR(mapping)
-		DECLARE_PCI_UNMAP_LEN(len)
+		DEFINE_DMA_UNMAP_ADDR(mapping);
+		DEFINE_DMA_UNMAP_LEN(len);
 	};
 
-   NOTE: DO NOT put a semicolon at the end of the DECLARE_*()
-         macro.
-
-2) Use pci_unmap_{addr,len}_set to set these values.
+2) Use dma_unmap_{addr,len}_set to set these values.
    Example, before:
 
 	ringp->mapping = FOO;
@@ -683,21 +675,21 @@ transform some example code.
 
    after:
 
-	pci_unmap_addr_set(ringp, mapping, FOO);
-	pci_unmap_len_set(ringp, len, BAR);
+	dma_unmap_addr_set(ringp, mapping, FOO);
+	dma_unmap_len_set(ringp, len, BAR);
 
-3) Use pci_unmap_{addr,len} to access these values.
+3) Use dma_unmap_{addr,len} to access these values.
    Example, before:
 
-	pci_unmap_single(pdev, ringp->mapping, ringp->len,
-			 PCI_DMA_FROMDEVICE);
+	dma_unmap_single(dev, ringp->mapping, ringp->len,
+			 DMA_FROM_DEVICE);
 
    after:
 
-	pci_unmap_single(pdev,
-			 pci_unmap_addr(ringp, mapping),
-			 pci_unmap_len(ringp, len),
-			 PCI_DMA_FROMDEVICE);
+	dma_unmap_single(dev,
+			 dma_unmap_addr(ringp, mapping),
+			 dma_unmap_len(ringp, len),
+			 DMA_FROM_DEVICE);
 
 It really should be self-explanatory.  We treat the ADDR and LEN
 separately, because it is possible for an implementation to only
@@ -732,15 +724,15 @@ to "Closing".
 DMA address space is limited on some architectures and an allocation
 failure can be determined by:
 
-- checking if pci_alloc_consistent returns NULL or pci_map_sg returns 0
+- checking if dma_alloc_coherent returns NULL or dma_map_sg returns 0
 
-- checking the returned dma_addr_t of pci_map_single and pci_map_page
-  by using pci_dma_mapping_error():
+- checking the returned dma_addr_t of dma_map_single and dma_map_page
+  by using dma_mapping_error():
 
 	dma_addr_t dma_handle;
 
-	dma_handle = pci_map_single(pdev, addr, size, direction);
-	if (pci_dma_mapping_error(pdev, dma_handle)) {
+	dma_handle = dma_map_single(dev, addr, size, direction);
+	if (dma_mapping_error(dev, dma_handle)) {
 		/*
 		 * reduce current DMA mapping usage,
 		 * delay and try again later or
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 5aceb88b3f8..05e2ae23686 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -4,20 +4,18 @@
         James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
 
 This document describes the DMA API.  For a more gentle introduction
-phrased in terms of the pci_ equivalents (and actual examples) see
-Documentation/PCI/PCI-DMA-mapping.txt.
+of the API (and actual examples) see
+Documentation/DMA-API-HOWTO.txt.
 
-This API is split into two pieces.  Part I describes the API and the
-corresponding pci_ API.  Part II describes the extensions to the API
-for supporting non-consistent memory machines.  Unless you know that
-your driver absolutely has to support non-consistent platforms (this
-is usually only legacy platforms) you should only use the API
-described in part I.
+This API is split into two pieces.  Part I describes the API.  Part II
+describes the extensions to the API for supporting non-consistent
+memory machines.  Unless you know that your driver absolutely has to
+support non-consistent platforms (this is usually only legacy
+platforms) you should only use the API described in part I.
 
-Part I - pci_ and dma_ Equivalent API 
+Part I - dma_ API
 -------------------------------------
 
-To get the pci_ API, you must #include <linux/pci.h>
 To get the dma_ API, you must #include <linux/dma-mapping.h>
 
 
@@ -27,9 +25,6 @@ Part Ia - Using large dma-coherent buffers
 void *
 dma_alloc_coherent(struct device *dev, size_t size,
 			     dma_addr_t *dma_handle, gfp_t flag)
-void *
-pci_alloc_consistent(struct pci_dev *dev, size_t size,
-			     dma_addr_t *dma_handle)
 
 Consistent memory is memory for which a write by either the device or
 the processor can immediately be read by the processor or device
@@ -53,15 +48,11 @@ The simplest way to do that is to use the dma_pool calls (see below).
 The flag parameter (dma_alloc_coherent only) allows the caller to
 specify the GFP_ flags (see kmalloc) for the allocation (the
 implementation may choose to ignore flags that affect the location of
-the returned memory, like GFP_DMA).  For pci_alloc_consistent, you
-must assume GFP_ATOMIC behaviour.
+the returned memory, like GFP_DMA).
 
 void
 dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
 			   dma_addr_t dma_handle)
-void
-pci_free_consistent(struct pci_dev *dev, size_t size, void *cpu_addr,
-			   dma_addr_t dma_handle)
 
 Free the region of consistent memory you previously allocated.  dev,
 size and dma_handle must all be the same as those passed into the
@@ -89,10 +80,6 @@ for alignment, like queue heads needing to be aligned on N-byte boundaries.
 	dma_pool_create(const char *name, struct device *dev,
 			size_t size, size_t align, size_t alloc);
 
-	struct pci_pool *
-	pci_pool_create(const char *name, struct pci_device *dev,
-			size_t size, size_t align, size_t alloc);
-
 The pool create() routines initialize a pool of dma-coherent buffers
 for use with a given device.  It must be called in a context which
 can sleep.
@@ -108,9 +95,6 @@ from this pool must not cross 4KByte boundaries.
 	void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
 			dma_addr_t *dma_handle);
 
-	void *pci_pool_alloc(struct pci_pool *pool, gfp_t gfp_flags,
-			dma_addr_t *dma_handle);
-
 This allocates memory from the pool; the returned memory will meet the size
 and alignment requirements specified at creation time.  Pass GFP_ATOMIC to
 prevent blocking, or if it's permitted (not in_interrupt, not holding SMP locks),
@@ -122,9 +106,6 @@ pool's device.
 	void dma_pool_free(struct dma_pool *pool, void *vaddr,
 			dma_addr_t addr);
 
-	void pci_pool_free(struct pci_pool *pool, void *vaddr,
-			dma_addr_t addr);
-
 This puts memory back into the pool.  The pool is what was passed to
 the pool allocation routine; the cpu (vaddr) and dma addresses are what
 were returned when that routine allocated the memory being freed.
@@ -132,8 +113,6 @@ were returned when that routine allocated the memory being freed.
 
 	void dma_pool_destroy(struct dma_pool *pool);
 
-	void pci_pool_destroy(struct pci_pool *pool);
-
 The pool destroy() routines free the resources of the pool.  They must be
 called in a context which can sleep.  Make sure you've freed all allocated
 memory back to the pool before you destroy it.
@@ -144,8 +123,6 @@ Part Ic - DMA addressing limitations
 
 int
 dma_supported(struct device *dev, u64 mask)
-int
-pci_dma_supported(struct pci_dev *hwdev, u64 mask)
 
 Checks to see if the device can support DMA to the memory described by
 mask.
@@ -159,8 +136,14 @@ driver writers.
 
 int
 dma_set_mask(struct device *dev, u64 mask)
+
+Checks to see if the mask is possible and updates the device
+parameters if it is.
+
+Returns: 0 if successful and a negative error if not.
+
 int
-pci_set_dma_mask(struct pci_device *dev, u64 mask)
+dma_set_coherent_mask(struct device *dev, u64 mask)
 
 Checks to see if the mask is possible and updates the device
 parameters if it is.
@@ -187,9 +170,6 @@ Part Id - Streaming DMA mappings
 dma_addr_t
 dma_map_single(struct device *dev, void *cpu_addr, size_t size,
 		      enum dma_data_direction direction)
-dma_addr_t
-pci_map_single(struct pci_dev *hwdev, void *cpu_addr, size_t size,
-		      int direction)
 
 Maps a piece of processor virtual memory so it can be accessed by the
 device and returns the physical handle of the memory.
@@ -198,14 +178,10 @@ The direction for both api's may be converted freely by casting.
 However the dma_ API uses a strongly typed enumerator for its
 direction:
 
-DMA_NONE		= PCI_DMA_NONE		no direction (used for
-						debugging)
-DMA_TO_DEVICE		= PCI_DMA_TODEVICE	data is going from the
-						memory to the device
-DMA_FROM_DEVICE		= PCI_DMA_FROMDEVICE	data is coming from
-						the device to the
-						memory
-DMA_BIDIRECTIONAL	= PCI_DMA_BIDIRECTIONAL	direction isn't known
+DMA_NONE		no direction (used for debugging)
+DMA_TO_DEVICE		data is going from the memory to the device
+DMA_FROM_DEVICE		data is coming from the device to the memory
+DMA_BIDIRECTIONAL	direction isn't known
 
 Notes:  Not all memory regions in a machine can be mapped by this
 API.  Further, regions that appear to be physically contiguous in
@@ -268,9 +244,6 @@ cache lines are updated with data that the device may have changed).
 void
 dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 		 enum dma_data_direction direction)
-void
-pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr,
-		 size_t size, int direction)
 
 Unmaps the region previously mapped.  All the parameters passed in
 must be identical to those passed in (and returned) by the mapping
@@ -280,15 +253,9 @@ dma_addr_t
 dma_map_page(struct device *dev, struct page *page,
 		    unsigned long offset, size_t size,
 		    enum dma_data_direction direction)
-dma_addr_t
-pci_map_page(struct pci_dev *hwdev, struct page *page,
-		    unsigned long offset, size_t size, int direction)
 void
 dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
 	       enum dma_data_direction direction)
-void
-pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address,
-	       size_t size, int direction)
 
 API for mapping and unmapping for pages.  All the notes and warnings
 for the other mapping APIs apply here.  Also, although the <offset>
@@ -299,9 +266,6 @@ cache width is.
 int
 dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 
-int
-pci_dma_mapping_error(struct pci_dev *hwdev, dma_addr_t dma_addr)
-
 In some circumstances dma_map_single and dma_map_page will fail to create
 a mapping. A driver can check for these errors by testing the returned
 dma address with dma_mapping_error(). A non-zero return value means the mapping
@@ -311,9 +275,6 @@ reduce current DMA mapping usage or delay and try again later).
 	int
 	dma_map_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction direction)
-	int
-	pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-		int nents, int direction)
 
 Returns: the number of physical segments mapped (this may be shorter
 than <nents> passed in if some elements of the scatter/gather list are
@@ -353,9 +314,6 @@ accessed sg->address and sg->length as shown above.
 	void
 	dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 		int nhwentries, enum dma_data_direction direction)
-	void
-	pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-		int nents, int direction)
 
 Unmap the previously mapped scatter/gather list.  All the parameters
 must be the same as those and passed in to the scatter/gather mapping
@@ -365,21 +323,23 @@ Note: <nents> must be the number you passed in, *not* the number of
 physical entries returned.
 
 void
-dma_sync_single(struct device *dev, dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
+			enum dma_data_direction direction)
 void
-pci_dma_sync_single(struct pci_dev *hwdev, dma_addr_t dma_handle,
-			   size_t size, int direction)
+dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
+			   enum dma_data_direction direction)
 void
-dma_sync_sg(struct device *dev, struct scatterlist *sg, int nelems,
-			  enum dma_data_direction direction)
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+		    enum dma_data_direction direction)
 void
-pci_dma_sync_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-		       int nelems, int direction)
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
+		       enum dma_data_direction direction)
 
-Synchronise a single contiguous or scatter/gather mapping.  All the
-parameters must be the same as those passed into the single mapping
-API.
+Synchronise a single contiguous or scatter/gather mapping for the cpu
+and device. With the sync_sg API, all the parameters must be the same
+as those passed into the single mapping API. With the sync_single API,
+you can use dma_handle and size parameters that aren't identical to
+those passed into the single mapping API to do a partial sync.
 
 Notes:  You must do this:
 
@@ -461,9 +421,9 @@ void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
 Part II - Advanced dma_ usage
 -----------------------------
 
-Warning: These pieces of the DMA API have no PCI equivalent.  They
-should also not be used in the majority of cases, since they cater for
-unlikely corner cases that don't belong in usual drivers.
+Warning: These pieces of the DMA API should not be used in the
+majority of cases, since they cater for unlikely corner cases that
+don't belong in usual drivers.
 
 If you don't understand how cache line coherency works between a
 processor and an I/O device, you should not be using this part of the
@@ -514,16 +474,6 @@ into the width returned by this call.  It will also always be a power
 of two for easy alignment.
 
 void
-dma_sync_single_range(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
-
-Does a partial sync, starting at offset and continuing for size.  You
-must be careful to observe the cache alignment and width when doing
-anything like this.  You must also be extra careful about accessing
-memory you intend to sync partially.
-
-void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction)
 
diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl
index 5e7d84b4850..133cd6c3f3c 100644
--- a/Documentation/DocBook/mtdnand.tmpl
+++ b/Documentation/DocBook/mtdnand.tmpl
@@ -488,7 +488,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 				The ECC bytes must be placed immidiately after the data
 				bytes in order to make the syndrome generator work. This
 				is contrary to the usual layout used by software ECC. The
-				seperation of data and out of band area is not longer
+				separation of data and out of band area is not longer
 				possible. The nand driver code handles this layout and
 				the remaining free bytes in the oob area are managed by 
 				the autoplacement code. Provide a matching oob-layout
@@ -560,7 +560,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 				bad blocks. They have factory marked good blocks. The marker pattern
 				is erased when the block is erased to be reused. So in case of
 				powerloss before writing the pattern back to the chip this block 
-				would be lost and added to the bad blocks. Therefor we scan the 
+				would be lost and added to the bad blocks. Therefore we scan the 
 				chip(s) when we detect them the first time for good blocks and 
 				store this information in a bad block table before erasing any 
 				of the blocks.
@@ -1094,7 +1094,7 @@ in this page</entry>
 		manufacturers specifications. This applies similar to the spare area. 
 	</para>
 	<para>
-		Therefor NAND aware filesystems must either write in page size chunks
+		Therefore NAND aware filesystems must either write in page size chunks
 		or hold a writebuffer to collect smaller writes until they sum up to 
 		pagesize. Available NAND aware filesystems: JFFS2, YAFFS. 		
 	</para>
diff --git a/Documentation/DocBook/v4l/common.xml b/Documentation/DocBook/v4l/common.xml
index c65f0ac9b6e..cea23e1c4fc 100644
--- a/Documentation/DocBook/v4l/common.xml
+++ b/Documentation/DocBook/v4l/common.xml
@@ -1170,7 +1170,7 @@ frames per second. If less than this number of frames is to be
 captured or output, applications can request frame skipping or
 duplicating on the driver side. This is especially useful when using
 the &func-read; or &func-write;, which are not augmented by timestamps
-or sequence counters, and to avoid unneccessary data copying.</para>
+or sequence counters, and to avoid unnecessary data copying.</para>
 
     <para>Finally these ioctls can be used to determine the number of
 buffers used internally by a driver in read/write mode. For
diff --git a/Documentation/DocBook/v4l/vidioc-g-parm.xml b/Documentation/DocBook/v4l/vidioc-g-parm.xml
index 78332d365ce..392aa9e5571 100644
--- a/Documentation/DocBook/v4l/vidioc-g-parm.xml
+++ b/Documentation/DocBook/v4l/vidioc-g-parm.xml
@@ -55,7 +55,7 @@ captured or output, applications can request frame skipping or
 duplicating on the driver side. This is especially useful when using
 the <function>read()</function> or <function>write()</function>, which
 are not augmented by timestamps or sequence counters, and to avoid
-unneccessary data copying.</para>
+unnecessary data copying.</para>
 
     <para>Further these ioctls can be used to determine the number of
 buffers used internally by a driver in read/write mode. For
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 8495fc97039..f5395af88a4 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -221,8 +221,8 @@ branches.  These different branches are:
   - main 2.6.x kernel tree
   - 2.6.x.y -stable kernel tree
   - 2.6.x -git kernel patches
-  - 2.6.x -mm kernel patches
   - subsystem specific kernel trees and patches
+  - the 2.6.x -next kernel tree for integration tests
 
 2.6.x kernel tree
 -----------------
@@ -232,7 +232,7 @@ process is as follows:
   - As soon as a new kernel is released a two weeks window is open,
     during this period of time maintainers can submit big diffs to
     Linus, usually the patches that have already been included in the
-    -mm kernel for a few weeks.  The preferred way to submit big changes
+    -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
     fine.
@@ -293,84 +293,43 @@ daily and represent the current state of Linus' tree.  They are more
 experimental than -rc kernels since they are generated automatically
 without even a cursory glance to see if they are sane.
 
-2.6.x -mm kernel patches
-------------------------
-These are experimental kernel patches released by Andrew Morton.  Andrew
-takes all of the different subsystem kernel trees and patches and mushes
-them together, along with a lot of patches that have been plucked from
-the linux-kernel mailing list.  This tree serves as a proving ground for
-new features and patches.  Once a patch has proved its worth in -mm for
-a while Andrew or the subsystem maintainer pushes it on to Linus for
-inclusion in mainline.
-
-It is heavily encouraged that all new patches get tested in the -mm tree
-before they are sent to Linus for inclusion in the main kernel tree.  Code
-which does not make an appearance in -mm before the opening of the merge
-window will prove hard to merge into the mainline.
-
-These kernels are not appropriate for use on systems that are supposed
-to be stable and they are more risky to run than any of the other
-branches.
-
-If you wish to help out with the kernel development process, please test
-and use these kernel releases and provide feedback to the linux-kernel
-mailing list if you have any problems, and if everything works properly.
-
-In addition to all the other experimental patches, these kernels usually
-also contain any changes in the mainline -git kernels available at the
-time of release.
-
-The -mm kernels are not released on a fixed schedule, but usually a few
--mm kernels are released in between each -rc kernel (1 to 3 is common).
-
 Subsystem Specific kernel trees and patches
 -------------------------------------------
-A number of the different kernel subsystem developers expose their
-development trees so that others can see what is happening in the
-different areas of the kernel.  These trees are pulled into the -mm
-kernel releases as described above.
-
-Here is a list of some of the different kernel trees available:
-  git trees:
-    - Kbuild development tree, Sam Ravnborg <sam@ravnborg.org>
-	git.kernel.org:/pub/scm/linux/kernel/git/sam/kbuild.git
-
-    - ACPI development tree, Len Brown <len.brown@intel.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git
-
-    - Block development tree, Jens Axboe <jens.axboe@oracle.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git
-
-    - DRM development tree, Dave Airlie <airlied@linux.ie>
-	git.kernel.org:/pub/scm/linux/kernel/git/airlied/drm-2.6.git
-
-    - ia64 development tree, Tony Luck <tony.luck@intel.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git
-
-    - infiniband, Roland Dreier <rolandd@cisco.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git
-
-    - libata, Jeff Garzik <jgarzik@pobox.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git
-
-    - network drivers, Jeff Garzik <jgarzik@pobox.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6.git
-
-    - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net>
-	git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
-
-    - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com>
-	git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
-
-    - x86, Ingo Molnar <mingo@elte.hu>
-	git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
-
-  quilt trees:
-    - USB, Driver Core, and I2C, Greg Kroah-Hartman <gregkh@suse.de>
-	kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
+The maintainers of the various kernel subsystems --- and also many
+kernel subsystem developers --- expose their current state of
+development in source repositories.  That way, others can see what is
+happening in the different areas of the kernel.  In areas where
+development is rapid, a developer may be asked to base his submissions
+onto such a subsystem kernel tree so that conflicts between the
+submission and other already ongoing work are avoided.
+
+Most of these repositories are git trees, but there are also other SCMs
+in use, or patch queues being published as quilt series.  Addresses of
+these subsystem repositories are listed in the MAINTAINERS file.  Many
+of them can be browsed at http://git.kernel.org/.
+
+Before a proposed patch is committed to such a subsystem tree, it is
+subject to review which primarily happens on mailing lists (see the
+respective section below).  For several kernel subsystems, this review
+process is tracked with the tool patchwork.  Patchwork offers a web
+interface which shows patch postings, any comments on a patch or
+revisions to it, and maintainers can mark patches as under review,
+accepted, or rejected.  Most of these patchwork sites are listed at
+http://patchwork.kernel.org/ or http://patchwork.ozlabs.org/.
+
+2.6.x -next kernel tree for integration tests
+---------------------------------------------
+Before updates from subsystem trees are merged into the mainline 2.6.x
+tree, they need to be integration-tested.  For this purpose, a special
+testing repository exists into which virtually all subsystem trees are
+pulled on an almost daily basis:
+	http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git
+	http://linux.f-seidel.de/linux-next/pmwiki/
+
+This way, the -next kernel gives a summary outlook onto what will be
+expected to go into the mainline kernel at the next merge period.
+Adventurous testers are very welcome to runtime-test the -next kernel.
 
-  Other kernel trees can be found listed at http://git.kernel.org/ and in
-  the MAINTAINERS file.
 
 Bug Reporting
 -------------
diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt
index bc38283379f..69dd29ed824 100644
--- a/Documentation/IPMI.txt
+++ b/Documentation/IPMI.txt
@@ -365,6 +365,7 @@ You can change this at module load time (for a module) with:
        regshifts=<shift1>,<shift2>,...
        slave_addrs=<addr1>,<addr2>,...
        force_kipmid=<enable1>,<enable2>,...
+       kipmid_max_busy_us=<ustime1>,<ustime2>,...
        unload_when_empty=[0|1]
 
 Each of these except si_trydefaults is a list, the first item for the
@@ -433,6 +434,7 @@ kernel command line as:
        ipmi_si.regshifts=<shift1>,<shift2>,...
        ipmi_si.slave_addrs=<addr1>,<addr2>,...
        ipmi_si.force_kipmid=<enable1>,<enable2>,...
+       ipmi_si.kipmid_max_busy_us=<ustime1>,<ustime2>,...
 
 It works the same as the module parameters of the same names.
 
@@ -450,6 +452,16 @@ force this thread on or off.  If you force it off and don't have
 interrupts, the driver will run VERY slowly.  Don't blame me,
 these interfaces suck.
 
+Unfortunately, this thread can use a lot of CPU depending on the
+interface's performance.  This can waste a lot of CPU and cause
+various issues with detecting idle CPU and using extra power.  To
+avoid this, the kipmid_max_busy_us sets the maximum amount of time, in
+microseconds, that kipmid will spin before sleeping for a tick.  This
+value sets a balance between performance and CPU waste and needs to be
+tuned to your needs.  Maybe, someday, auto-tuning will be added, but
+that's not a simple thing and even the auto-tuning would need to be
+tuned to the user's desired performance.
+
 The driver supports a hot add and remove of interfaces.  This way,
 interfaces can be added or removed after the kernel is up and running.
 This is done using /sys/modules/ipmi_si/parameters/hotmod, which is a
diff --git a/Documentation/Makefile b/Documentation/Makefile
index 94b94573353..6fc7ea1d1f9 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -1,3 +1,3 @@
 obj-m := DocBook/ accounting/ auxdisplay/ connector/ \
-	filesystems/configfs/ ia64/ networking/ \
-	pcmcia/ spi/ video4linux/ vm/ watchdog/src/
+	filesystems/ filesystems/configfs/ ia64/ laptops/ networking/ \
+	pcmcia/ spi/ timers/ video4linux/ vm/ watchdog/src/
diff --git a/Documentation/SubmitChecklist b/Documentation/SubmitChecklist
index 1053a56be3b..8916ca48bc9 100644
--- a/Documentation/SubmitChecklist
+++ b/Documentation/SubmitChecklist
@@ -9,10 +9,14 @@ Documentation/SubmittingPatches and elsewhere regarding submitting Linux
 kernel patches.
 
 
-1: Builds cleanly with applicable or modified CONFIG options =y, =m, and
+1: If you use a facility then #include the file that defines/declares
+   that facility.  Don't depend on other header files pulling in ones
+   that you use.
+
+2: Builds cleanly with applicable or modified CONFIG options =y, =m, and
    =n.  No gcc warnings/errors, no linker warnings/errors.
 
-2: Passes allnoconfig, allmodconfig
+2b: Passes allnoconfig, allmodconfig
 
 3: Builds on multiple CPU architectures by using local cross-compile tools
    or some other build farm.
diff --git a/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt b/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt
index 76b3a11e90b..fa968aa99d6 100644
--- a/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt
+++ b/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt
@@ -14,8 +14,8 @@ Introduction
  how the clocks are arranged. The first implementation used as single
  PLL to feed the ARM, memory and peripherals via a series of dividers
  and muxes and this is the implementation that is documented here. A
- newer version where there is a seperate PLL and clock divider for the
- ARM core is available as a seperate driver.
+ newer version where there is a separate PLL and clock divider for the
+ ARM core is available as a separate driver.
 
 
 Layout
diff --git a/Documentation/arm/Samsung/Overview.txt b/Documentation/arm/Samsung/Overview.txt
new file mode 100644
index 00000000000..7cced1fea9c
--- /dev/null
+++ b/Documentation/arm/Samsung/Overview.txt
@@ -0,0 +1,86 @@
+		Samsung ARM Linux Overview
+		==========================
+
+Introduction
+------------
+
+  The Samsung range of ARM SoCs spans many similar devices, from the initial
+  ARM9 through to the newest ARM cores. This document shows an overview of
+  the current kernel support, how to use it and where to find the code
+  that supports this.
+
+  The currently supported SoCs are:
+
+  - S3C24XX: See Documentation/arm/Samsung-S3C24XX/Overview.txt for full list
+  - S3C64XX: S3C6400 and S3C6410
+  - S5PC6440
+
+  S5PC100 and S5PC110 support is currently being merged
+
+
+S3C24XX Systems
+---------------
+
+  There is still documentation in Documnetation/arm/Samsung-S3C24XX/ which
+  deals with the architecture and drivers specific to these devices.
+
+  See Documentation/arm/Samsung-S3C24XX/Overview.txt for more information
+  on the implementation details and specific support.
+
+
+Configuration
+-------------
+
+  A number of configurations are supplied, as there is no current way of
+  unifying all the SoCs into one kernel.
+
+  s5p6440_defconfig - S5P6440 specific default configuration
+  s5pc100_defconfig - S5PC100 specific default configuration
+
+
+Layout
+------
+
+  The directory layout is currently being restructured, and consists of
+  several platform directories and then the machine specific directories
+  of the CPUs being built for.
+
+  plat-samsung provides the base for all the implementations, and is the
+  last in the line of include directories that are processed for the build
+  specific information. It contains the base clock, GPIO and device definitions
+  to get the system running.
+
+  plat-s3c is the s3c24xx/s3c64xx platform directory, although it is currently
+  involved in other builds this will be phased out once the relevant code is
+  moved elsewhere.
+
+  plat-s3c24xx is for s3c24xx specific builds, see the S3C24XX docs.
+
+  plat-s3c64xx is for the s3c64xx specific bits, see the S3C24XX docs.
+
+  plat-s5p is for s5p specific builds, more to be added.
+
+
+  [ to finish ]
+
+
+Port Contributors
+-----------------
+
+  Ben Dooks (BJD)
+  Vincent Sanders
+  Herbert Potzl
+  Arnaud Patard (RTP)
+  Roc Wu
+  Klaus Fetscher
+  Dimitry Andric
+  Shannon Holland
+  Guillaume Gourat (NexVision)
+  Christer Weinigel (wingel) (Acer N30)
+  Lucas Correia Villa Real (S3C2400 port)
+
+
+Document Author
+---------------
+
+Copyright 2009-2010 Ben Dooks <ben-linux@fluff.org>
diff --git a/Documentation/arm/Samsung/clksrc-change-registers.awk b/Documentation/arm/Samsung/clksrc-change-registers.awk
new file mode 100755
index 00000000000..0c50220851f
--- /dev/null
+++ b/Documentation/arm/Samsung/clksrc-change-registers.awk
@@ -0,0 +1,167 @@
+#!/usr/bin/awk -f
+#
+# Copyright 2010 Ben Dooks <ben-linux@fluff.org>
+#
+# Released under GPLv2
+
+# example usage
+# ./clksrc-change-registers.awk arch/arm/plat-s5pc1xx/include/plat/regs-clock.h < src > dst
+
+function extract_value(s)
+{
+    eqat = index(s, "=")
+    comat = index(s, ",")
+    return substr(s, eqat+2, (comat-eqat)-2)
+}
+
+function remove_brackets(b)
+{
+    return substr(b, 2, length(b)-2)
+}
+
+function splitdefine(l, p)
+{
+    r = split(l, tp)
+
+    p[0] = tp[2]
+    p[1] = remove_brackets(tp[3])
+}
+
+function find_length(f)
+{
+    if (0)
+	printf "find_length " f "\n" > "/dev/stderr"
+
+    if (f ~ /0x1/)
+	return 1
+    else if (f ~ /0x3/)
+	return 2
+    else if (f ~ /0x7/)
+	return 3
+    else if (f ~ /0xf/)
+	return 4
+
+    printf "unknown legnth " f "\n" > "/dev/stderr"
+    exit
+}
+
+function find_shift(s)
+{
+    id = index(s, "<")
+    if (id <= 0) {
+	printf "cannot find shift " s "\n" > "/dev/stderr"
+	exit
+    }
+
+    return substr(s, id+2)
+}
+
+
+BEGIN {
+    if (ARGC < 2) {
+	print "too few arguments" > "/dev/stderr"
+	exit
+    }
+
+# read the header file and find the mask values that we will need
+# to replace and create an associative array of values
+
+    while (getline line < ARGV[1] > 0) {
+	if (line ~ /\#define.*_MASK/ &&
+	    !(line ~ /S5PC100_EPLL_MASK/) &&
+	    !(line ~ /USB_SIG_MASK/)) {
+	    splitdefine(line, fields)
+	    name = fields[0]
+	    if (0)
+		printf "MASK " line "\n" > "/dev/stderr"
+	    dmask[name,0] = find_length(fields[1])
+	    dmask[name,1] = find_shift(fields[1])
+	    if (0)
+		printf "=> '" name "' LENGTH=" dmask[name,0] " SHIFT=" dmask[name,1] "\n" > "/dev/stderr"
+	} else {
+	}
+    }
+
+    delete ARGV[1]
+}
+
+/clksrc_clk.*=.*{/ {
+    shift=""
+    mask=""
+    divshift=""
+    reg_div=""
+    reg_src=""
+    indent=1
+
+    print $0
+
+    for(; indent >= 1;) {
+	if ((getline line) <= 0) {
+	    printf "unexpected end of file" > "/dev/stderr"
+	    exit 1;
+	}
+
+	if (line ~ /\.shift/) {
+	    shift = extract_value(line)
+	} else if (line ~ /\.mask/) {
+	    mask = extract_value(line)
+	} else if (line ~ /\.reg_divider/) {
+	    reg_div = extract_value(line)
+	} else if (line ~ /\.reg_source/) {
+	    reg_src = extract_value(line)
+	} else if (line ~ /\.divider_shift/) {
+	    divshift = extract_value(line)
+	} else if (line ~ /{/) {
+		indent++
+		print line
+	    } else if (line ~ /}/) {
+	    indent--
+
+	    if (indent == 0) {
+		if (0) {
+		    printf "shift '" shift   "' ='" dmask[shift,0] "'\n" > "/dev/stderr"
+		    printf "mask  '" mask    "'\n" > "/dev/stderr"
+		    printf "dshft '" divshift "'\n" > "/dev/stderr"
+		    printf "rdiv  '" reg_div "'\n" > "/dev/stderr"
+		    printf "rsrc  '" reg_src "'\n" > "/dev/stderr"
+		}
+
+		generated = mask
+		sub(reg_src, reg_div, generated)
+
+		if (0) {
+		    printf "/* rsrc " reg_src " */\n"
+		    printf "/* rdiv " reg_div " */\n"
+		    printf "/* shift " shift " */\n"
+		    printf "/* mask " mask " */\n"
+		    printf "/* generated " generated " */\n"
+		}
+
+		if (reg_div != "") {
+		    printf "\t.reg_div = { "
+		    printf ".reg = " reg_div ", "
+		    printf ".shift = " dmask[generated,1] ", "
+		    printf ".size = " dmask[generated,0] ", "
+		    printf "},\n"
+		}
+
+		printf "\t.reg_src = { "
+		printf ".reg = " reg_src ", "
+		printf ".shift = " dmask[mask,1] ", "
+		printf ".size = " dmask[mask,0] ", "
+
+		printf "},\n"
+
+	    }
+
+	    print line
+	} else {
+	    print line
+	}
+
+	if (0)
+	    printf indent ":" line "\n" > "/dev/stderr"
+    }
+}
+
+// && ! /clksrc_clk.*=.*{/ { print $0 }
diff --git a/Documentation/cdrom/ide-cd b/Documentation/cdrom/ide-cd
index 2c558cd6c1e..f4dc9de2694 100644
--- a/Documentation/cdrom/ide-cd
+++ b/Documentation/cdrom/ide-cd
@@ -159,42 +159,7 @@ two arguments:  the CDROM device, and the slot number to which you wish
 to change.  If the slot number is -1, the drive is unloaded.
 
 
-4. Compilation options
-----------------------
-
-There are a few additional options which can be set when compiling the
-driver.  Most people should not need to mess with any of these; they
-are listed here simply for completeness.  A compilation option can be
-enabled by adding a line of the form `#define <option> 1' to the top
-of ide-cd.c.  All these options are disabled by default.
-
-VERBOSE_IDE_CD_ERRORS
-  If this is set, ATAPI error codes will be translated into textual
-  descriptions.  In addition, a dump is made of the command which
-  provoked the error.  This is off by default to save the memory used
-  by the (somewhat long) table of error descriptions.  
-
-STANDARD_ATAPI
-  If this is set, the code needed to deal with certain drives which do
-  not properly implement the ATAPI spec will be disabled.  If you know
-  your drive implements ATAPI properly, you can turn this on to get a
-  slightly smaller kernel.
-
-NO_DOOR_LOCKING
-  If this is set, the driver will never attempt to lock the door of
-  the drive.
-
-CDROM_NBLOCKS_BUFFER
-  This sets the size of the buffer to be used for a CDROMREADAUDIO
-  ioctl.  The default is 8.
-
-TEST
-  This currently enables an additional ioctl which enables a user-mode
-  program to execute an arbitrary packet command.  See the source for
-  details.  This should be left off unless you know what you're doing.
-
-
-5. Common problems
+4. Common problems
 ------------------
 
 This section discusses some common problems encountered when trying to
@@ -371,7 +336,7 @@ f. Data corruption.
     expense of low system performance.
 
 
-6. cdchange.c
+5. cdchange.c
 -------------
 
 /*
diff --git a/Documentation/cgroups/cgroup_event_listener.c b/Documentation/cgroups/cgroup_event_listener.c
new file mode 100644
index 00000000000..8c2bfc4a635
--- /dev/null
+++ b/Documentation/cgroups/cgroup_event_listener.c
@@ -0,0 +1,110 @@
+/*
+ * cgroup_event_listener.c - Simple listener of cgroup events
+ *
+ * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name>
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/eventfd.h>
+
+#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>\n"
+
+int main(int argc, char **argv)
+{
+	int efd = -1;
+	int cfd = -1;
+	int event_control = -1;
+	char event_control_path[PATH_MAX];
+	char line[LINE_MAX];
+	int ret;
+
+	if (argc != 3) {
+		fputs(USAGE_STR, stderr);
+		return 1;
+	}
+
+	cfd = open(argv[1], O_RDONLY);
+	if (cfd == -1) {
+		fprintf(stderr, "Cannot open %s: %s\n", argv[1],
+				strerror(errno));
+		goto out;
+	}
+
+	ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control",
+			dirname(argv[1]));
+	if (ret >= PATH_MAX) {
+		fputs("Path to cgroup.event_control is too long\n", stderr);
+		goto out;
+	}
+
+	event_control = open(event_control_path, O_WRONLY);
+	if (event_control == -1) {
+		fprintf(stderr, "Cannot open %s: %s\n", event_control_path,
+				strerror(errno));
+		goto out;
+	}
+
+	efd = eventfd(0, 0);
+	if (efd == -1) {
+		perror("eventfd() failed");
+		goto out;
+	}
+
+	ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]);
+	if (ret >= LINE_MAX) {
+		fputs("Arguments string is too long\n", stderr);
+		goto out;
+	}
+
+	ret = write(event_control, line, strlen(line) + 1);
+	if (ret == -1) {
+		perror("Cannot write to cgroup.event_control");
+		goto out;
+	}
+
+	while (1) {
+		uint64_t result;
+
+		ret = read(efd, &result, sizeof(result));
+		if (ret == -1) {
+			if (errno == EINTR)
+				continue;
+			perror("Cannot read from eventfd");
+			break;
+		}
+		assert(ret == sizeof(result));
+
+		ret = access(event_control_path, W_OK);
+		if ((ret == -1) && (errno == ENOENT)) {
+				puts("The cgroup seems to have removed.");
+				ret = 0;
+				break;
+		}
+
+		if (ret == -1) {
+			perror("cgroup.event_control "
+					"is not accessable any more");
+			break;
+		}
+
+		printf("%s %s: crossed\n", argv[1], argv[2]);
+	}
+
+out:
+	if (efd >= 0)
+		close(efd);
+	if (event_control >= 0)
+		close(event_control);
+	if (cfd >= 0)
+		close(cfd);
+
+	return (ret != 0);
+}
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 0b33bfe7dde..fd588ff0e29 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -22,6 +22,8 @@ CONTENTS:
 2. Usage Examples and Syntax
   2.1 Basic Usage
   2.2 Attaching processes
+  2.3 Mounting hierarchies by name
+  2.4 Notification API
 3. Kernel API
   3.1 Overview
   3.2 Synchronization
@@ -434,6 +436,25 @@ you give a subsystem a name.
 The name of the subsystem appears as part of the hierarchy description
 in /proc/mounts and /proc/<pid>/cgroups.
 
+2.4 Notification API
+--------------------
+
+There is mechanism which allows to get notifications about changing
+status of a cgroup.
+
+To register new notification handler you need:
+ - create a file descriptor for event notification using eventfd(2);
+ - open a control file to be monitored (e.g. memory.usage_in_bytes);
+ - write "<event_fd> <control_fd> <args>" to cgroup.event_control.
+   Interpretation of args is defined by control file implementation;
+
+eventfd will be woken up by control file implementation or when the
+cgroup is removed.
+
+To unregister notification handler just close eventfd.
+
+NOTE: Support of notifications should be implemented for the control
+file. See documentation for the subsystem.
 
 3. Kernel API
 =============
@@ -488,6 +509,11 @@ Each subsystem should:
 - add an entry in linux/cgroup_subsys.h
 - define a cgroup_subsys object called <name>_subsys
 
+If a subsystem can be compiled as a module, it should also have in its
+module initcall a call to cgroup_load_subsys(), and in its exitcall a
+call to cgroup_unload_subsys(). It should also set its_subsys.module =
+THIS_MODULE in its .c file.
+
 Each subsystem may export the following methods. The only mandatory
 methods are create/destroy. Any others that are null are presumed to
 be successful no-ops.
@@ -536,10 +562,21 @@ returns an error, this will abort the attach operation.  If a NULL
 task is passed, then a successful result indicates that *any*
 unspecified task can be moved into the cgroup. Note that this isn't
 called on a fork. If this method returns 0 (success) then this should
-remain valid while the caller holds cgroup_mutex. If threadgroup is
+remain valid while the caller holds cgroup_mutex and it is ensured that either
+attach() or cancel_attach() will be called in future. If threadgroup is
 true, then a successful result indicates that all threads in the given
 thread's threadgroup can be moved together.
 
+void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+	       struct task_struct *task, bool threadgroup)
+(cgroup_mutex held by caller)
+
+Called when a task attach operation has failed after can_attach() has succeeded.
+A subsystem whose can_attach() has some side-effects should provide this
+function, so that the subsytem can implement a rollback. If not, not necessary.
+This will be called only about subsystems whose can_attach() operation have
+succeeded.
+
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	    struct cgroup *old_cgrp, struct task_struct *task,
 	    bool threadgroup)
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 1d7e9784439..4160df82b3f 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -168,20 +168,20 @@ Each cpuset is represented by a directory in the cgroup file system
 containing (on top of the standard cgroup files) the following
 files describing that cpuset:
 
- - cpus: list of CPUs in that cpuset
- - mems: list of Memory Nodes in that cpuset
- - memory_migrate flag: if set, move pages to cpusets nodes
- - cpu_exclusive flag: is cpu placement exclusive?
- - mem_exclusive flag: is memory placement exclusive?
- - mem_hardwall flag:  is memory allocation hardwalled
- - memory_pressure: measure of how much paging pressure in cpuset
- - memory_spread_page flag: if set, spread page cache evenly on allowed nodes
- - memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes
- - sched_load_balance flag: if set, load balance within CPUs on that cpuset
- - sched_relax_domain_level: the searching range when migrating tasks
+ - cpuset.cpus: list of CPUs in that cpuset
+ - cpuset.mems: list of Memory Nodes in that cpuset
+ - cpuset.memory_migrate flag: if set, move pages to cpusets nodes
+ - cpuset.cpu_exclusive flag: is cpu placement exclusive?
+ - cpuset.mem_exclusive flag: is memory placement exclusive?
+ - cpuset.mem_hardwall flag:  is memory allocation hardwalled
+ - cpuset.memory_pressure: measure of how much paging pressure in cpuset
+ - cpuset.memory_spread_page flag: if set, spread page cache evenly on allowed nodes
+ - cpuset.memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes
+ - cpuset.sched_load_balance flag: if set, load balance within CPUs on that cpuset
+ - cpuset.sched_relax_domain_level: the searching range when migrating tasks
 
 In addition, the root cpuset only has the following file:
- - memory_pressure_enabled flag: compute memory_pressure?
+ - cpuset.memory_pressure_enabled flag: compute memory_pressure?
 
 New cpusets are created using the mkdir system call or shell
 command.  The properties of a cpuset, such as its flags, allowed
@@ -229,7 +229,7 @@ If a cpuset is cpu or mem exclusive, no other cpuset, other than
 a direct ancestor or descendant, may share any of the same CPUs or
 Memory Nodes.
 
-A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled",
+A cpuset that is cpuset.mem_exclusive *or* cpuset.mem_hardwall is "hardwalled",
 i.e. it restricts kernel allocations for page, buffer and other data
 commonly shared by the kernel across multiple users.  All cpusets,
 whether hardwalled or not, restrict allocations of memory for user
@@ -304,15 +304,15 @@ times 1000.
 ---------------------------
 There are two boolean flag files per cpuset that control where the
 kernel allocates pages for the file system buffers and related in
-kernel data structures.  They are called 'memory_spread_page' and
-'memory_spread_slab'.
+kernel data structures.  They are called 'cpuset.memory_spread_page' and
+'cpuset.memory_spread_slab'.
 
-If the per-cpuset boolean flag file 'memory_spread_page' is set, then
+If the per-cpuset boolean flag file 'cpuset.memory_spread_page' is set, then
 the kernel will spread the file system buffers (page cache) evenly
 over all the nodes that the faulting task is allowed to use, instead
 of preferring to put those pages on the node where the task is running.
 
-If the per-cpuset boolean flag file 'memory_spread_slab' is set,
+If the per-cpuset boolean flag file 'cpuset.memory_spread_slab' is set,
 then the kernel will spread some file system related slab caches,
 such as for inodes and dentries evenly over all the nodes that the
 faulting task is allowed to use, instead of preferring to put those
@@ -337,21 +337,21 @@ their containing tasks memory spread settings.  If memory spreading
 is turned off, then the currently specified NUMA mempolicy once again
 applies to memory page allocations.
 
-Both 'memory_spread_page' and 'memory_spread_slab' are boolean flag
+Both 'cpuset.memory_spread_page' and 'cpuset.memory_spread_slab' are boolean flag
 files.  By default they contain "0", meaning that the feature is off
 for that cpuset.  If a "1" is written to that file, then that turns
 the named feature on.
 
 The implementation is simple.
 
-Setting the flag 'memory_spread_page' turns on a per-process flag
+Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag
 PF_SPREAD_PAGE for each task that is in that cpuset or subsequently
 joins that cpuset.  The page allocation calls for the page cache
 is modified to perform an inline check for this PF_SPREAD_PAGE task
 flag, and if set, a call to a new routine cpuset_mem_spread_node()
 returns the node to prefer for the allocation.
 
-Similarly, setting 'memory_spread_slab' turns on the flag
+Similarly, setting 'cpuset.memory_spread_slab' turns on the flag
 PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
 pages from the node returned by cpuset_mem_spread_node().
 
@@ -404,24 +404,24 @@ the following two situations:
     system overhead on those CPUs, including avoiding task load
     balancing if that is not needed.
 
-When the per-cpuset flag "sched_load_balance" is enabled (the default
-setting), it requests that all the CPUs in that cpusets allowed 'cpus'
+When the per-cpuset flag "cpuset.sched_load_balance" is enabled (the default
+setting), it requests that all the CPUs in that cpusets allowed 'cpuset.cpus'
 be contained in a single sched domain, ensuring that load balancing
 can move a task (not otherwised pinned, as by sched_setaffinity)
 from any CPU in that cpuset to any other.
 
-When the per-cpuset flag "sched_load_balance" is disabled, then the
+When the per-cpuset flag "cpuset.sched_load_balance" is disabled, then the
 scheduler will avoid load balancing across the CPUs in that cpuset,
 --except-- in so far as is necessary because some overlapping cpuset
 has "sched_load_balance" enabled.
 
-So, for example, if the top cpuset has the flag "sched_load_balance"
+So, for example, if the top cpuset has the flag "cpuset.sched_load_balance"
 enabled, then the scheduler will have one sched domain covering all
-CPUs, and the setting of the "sched_load_balance" flag in any other
+CPUs, and the setting of the "cpuset.sched_load_balance" flag in any other
 cpusets won't matter, as we're already fully load balancing.
 
 Therefore in the above two situations, the top cpuset flag
-"sched_load_balance" should be disabled, and only some of the smaller,
+"cpuset.sched_load_balance" should be disabled, and only some of the smaller,
 child cpusets have this flag enabled.
 
 When doing this, you don't usually want to leave any unpinned tasks in
@@ -433,7 +433,7 @@ scheduler might not consider the possibility of load balancing that
 task to that underused CPU.
 
 Of course, tasks pinned to a particular CPU can be left in a cpuset
-that disables "sched_load_balance" as those tasks aren't going anywhere
+that disables "cpuset.sched_load_balance" as those tasks aren't going anywhere
 else anyway.
 
 There is an impedance mismatch here, between cpusets and sched domains.
@@ -443,19 +443,19 @@ overlap and each CPU is in at most one sched domain.
 It is necessary for sched domains to be flat because load balancing
 across partially overlapping sets of CPUs would risk unstable dynamics
 that would be beyond our understanding.  So if each of two partially
-overlapping cpusets enables the flag 'sched_load_balance', then we
+overlapping cpusets enables the flag 'cpuset.sched_load_balance', then we
 form a single sched domain that is a superset of both.  We won't move
 a task to a CPU outside it cpuset, but the scheduler load balancing
 code might waste some compute cycles considering that possibility.
 
 This mismatch is why there is not a simple one-to-one relation
-between which cpusets have the flag "sched_load_balance" enabled,
+between which cpusets have the flag "cpuset.sched_load_balance" enabled,
 and the sched domain configuration.  If a cpuset enables the flag, it
 will get balancing across all its CPUs, but if it disables the flag,
 it will only be assured of no load balancing if no other overlapping
 cpuset enables the flag.
 
-If two cpusets have partially overlapping 'cpus' allowed, and only
+If two cpusets have partially overlapping 'cpuset.cpus' allowed, and only
 one of them has this flag enabled, then the other may find its
 tasks only partially load balanced, just on the overlapping CPUs.
 This is just the general case of the top_cpuset example given a few
@@ -468,23 +468,23 @@ load balancing to the other CPUs.
 1.7.1 sched_load_balance implementation details.
 ------------------------------------------------
 
-The per-cpuset flag 'sched_load_balance' defaults to enabled (contrary
+The per-cpuset flag 'cpuset.sched_load_balance' defaults to enabled (contrary
 to most cpuset flags.)  When enabled for a cpuset, the kernel will
 ensure that it can load balance across all the CPUs in that cpuset
 (makes sure that all the CPUs in the cpus_allowed of that cpuset are
 in the same sched domain.)
 
-If two overlapping cpusets both have 'sched_load_balance' enabled,
+If two overlapping cpusets both have 'cpuset.sched_load_balance' enabled,
 then they will be (must be) both in the same sched domain.
 
-If, as is the default, the top cpuset has 'sched_load_balance' enabled,
+If, as is the default, the top cpuset has 'cpuset.sched_load_balance' enabled,
 then by the above that means there is a single sched domain covering
 the whole system, regardless of any other cpuset settings.
 
 The kernel commits to user space that it will avoid load balancing
 where it can.  It will pick as fine a granularity partition of sched
 domains as it can while still providing load balancing for any set
-of CPUs allowed to a cpuset having 'sched_load_balance' enabled.
+of CPUs allowed to a cpuset having 'cpuset.sched_load_balance' enabled.
 
 The internal kernel cpuset to scheduler interface passes from the
 cpuset code to the scheduler code a partition of the load balanced
@@ -495,9 +495,9 @@ all the CPUs that must be load balanced.
 The cpuset code builds a new such partition and passes it to the
 scheduler sched domain setup code, to have the sched domains rebuilt
 as necessary, whenever:
- - the 'sched_load_balance' flag of a cpuset with non-empty CPUs changes,
+ - the 'cpuset.sched_load_balance' flag of a cpuset with non-empty CPUs changes,
  - or CPUs come or go from a cpuset with this flag enabled,
- - or 'sched_relax_domain_level' value of a cpuset with non-empty CPUs
+ - or 'cpuset.sched_relax_domain_level' value of a cpuset with non-empty CPUs
    and with this flag enabled changes,
  - or a cpuset with non-empty CPUs and with this flag enabled is removed,
  - or a cpu is offlined/onlined.
@@ -542,7 +542,7 @@ As the result, task B on CPU X need to wait task A or wait load balance
 on the next tick.  For some applications in special situation, waiting
 1 tick may be too long.
 
-The 'sched_relax_domain_level' file allows you to request changing
+The 'cpuset.sched_relax_domain_level' file allows you to request changing
 this searching range as you like.  This file takes int value which
 indicates size of searching range in levels ideally as follows,
 otherwise initial value -1 that indicates the cpuset has no request.
@@ -559,8 +559,8 @@ The system default is architecture dependent.  The system default
 can be changed using the relax_domain_level= boot parameter.
 
 This file is per-cpuset and affect the sched domain where the cpuset
-belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
-is disabled, then 'sched_relax_domain_level' have no effect since
+belongs to.  Therefore if the flag 'cpuset.sched_load_balance' of a cpuset
+is disabled, then 'cpuset.sched_relax_domain_level' have no effect since
 there is no sched domain belonging the cpuset.
 
 If multiple cpusets are overlapping and hence they form a single sched
@@ -607,9 +607,9 @@ from one cpuset to another, then the kernel will adjust the tasks
 memory placement, as above, the next time that the kernel attempts
 to allocate a page of memory for that task.
 
-If a cpuset has its 'cpus' modified, then each task in that cpuset
+If a cpuset has its 'cpuset.cpus' modified, then each task in that cpuset
 will have its allowed CPU placement changed immediately.  Similarly,
-if a tasks pid is written to another cpusets 'tasks' file, then its
+if a tasks pid is written to another cpusets 'cpuset.tasks' file, then its
 allowed CPU placement is changed immediately.  If such a task had been
 bound to some subset of its cpuset using the sched_setaffinity() call,
 the task will be allowed to run on any CPU allowed in its new cpuset,
@@ -622,8 +622,8 @@ and the processor placement is updated immediately.
 Normally, once a page is allocated (given a physical page
 of main memory) then that page stays on whatever node it
 was allocated, so long as it remains allocated, even if the
-cpusets memory placement policy 'mems' subsequently changes.
-If the cpuset flag file 'memory_migrate' is set true, then when
+cpusets memory placement policy 'cpuset.mems' subsequently changes.
+If the cpuset flag file 'cpuset.memory_migrate' is set true, then when
 tasks are attached to that cpuset, any pages that task had
 allocated to it on nodes in its previous cpuset are migrated
 to the tasks new cpuset. The relative placement of the page within
@@ -631,12 +631,12 @@ the cpuset is preserved during these migration operations if possible.
 For example if the page was on the second valid node of the prior cpuset
 then the page will be placed on the second valid node of the new cpuset.
 
-Also if 'memory_migrate' is set true, then if that cpusets
-'mems' file is modified, pages allocated to tasks in that
-cpuset, that were on nodes in the previous setting of 'mems',
+Also if 'cpuset.memory_migrate' is set true, then if that cpusets
+'cpuset.mems' file is modified, pages allocated to tasks in that
+cpuset, that were on nodes in the previous setting of 'cpuset.mems',
 will be moved to nodes in the new setting of 'mems.'
 Pages that were not in the tasks prior cpuset, or in the cpusets
-prior 'mems' setting, will not be moved.
+prior 'cpuset.mems' setting, will not be moved.
 
 There is an exception to the above.  If hotplug functionality is used
 to remove all the CPUs that are currently assigned to a cpuset,
@@ -678,8 +678,8 @@ and then start a subshell 'sh' in that cpuset:
   cd /dev/cpuset
   mkdir Charlie
   cd Charlie
-  /bin/echo 2-3 > cpus
-  /bin/echo 1 > mems
+  /bin/echo 2-3 > cpuset.cpus
+  /bin/echo 1 > cpuset.mems
   /bin/echo $$ > tasks
   sh
   # The subshell 'sh' is now running in cpuset Charlie
@@ -725,10 +725,13 @@ Now you want to do something with this cpuset.
 
 In this directory you can find several files:
 # ls
-cpu_exclusive  memory_migrate      mems                      tasks
-cpus           memory_pressure     notify_on_release
-mem_exclusive  memory_spread_page  sched_load_balance
-mem_hardwall   memory_spread_slab  sched_relax_domain_level
+cpuset.cpu_exclusive       cpuset.memory_spread_slab
+cpuset.cpus                cpuset.mems
+cpuset.mem_exclusive       cpuset.sched_load_balance
+cpuset.mem_hardwall        cpuset.sched_relax_domain_level
+cpuset.memory_migrate      notify_on_release
+cpuset.memory_pressure     tasks
+cpuset.memory_spread_page
 
 Reading them will give you information about the state of this cpuset:
 the CPUs and Memory Nodes it can use, the processes that are using
@@ -736,13 +739,13 @@ it, its properties.  By writing to these files you can manipulate
 the cpuset.
 
 Set some flags:
-# /bin/echo 1 > cpu_exclusive
+# /bin/echo 1 > cpuset.cpu_exclusive
 
 Add some cpus:
-# /bin/echo 0-7 > cpus
+# /bin/echo 0-7 > cpuset.cpus
 
 Add some mems:
-# /bin/echo 0-7 > mems
+# /bin/echo 0-7 > cpuset.mems
 
 Now attach your shell to this cpuset:
 # /bin/echo $$ > tasks
@@ -774,28 +777,28 @@ echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent
 This is the syntax to use when writing in the cpus or mems files
 in cpuset directories:
 
-# /bin/echo 1-4 > cpus		-> set cpus list to cpus 1,2,3,4
-# /bin/echo 1,2,3,4 > cpus	-> set cpus list to cpus 1,2,3,4
+# /bin/echo 1-4 > cpuset.cpus		-> set cpus list to cpus 1,2,3,4
+# /bin/echo 1,2,3,4 > cpuset.cpus	-> set cpus list to cpus 1,2,3,4
 
 To add a CPU to a cpuset, write the new list of CPUs including the
 CPU to be added. To add 6 to the above cpuset:
 
-# /bin/echo 1-4,6 > cpus	-> set cpus list to cpus 1,2,3,4,6
+# /bin/echo 1-4,6 > cpuset.cpus	-> set cpus list to cpus 1,2,3,4,6
 
 Similarly to remove a CPU from a cpuset, write the new list of CPUs
 without the CPU to be removed.
 
 To remove all the CPUs:
 
-# /bin/echo "" > cpus		-> clear cpus list
+# /bin/echo "" > cpuset.cpus		-> clear cpus list
 
 2.3 Setting flags
 -----------------
 
 The syntax is very simple:
 
-# /bin/echo 1 > cpu_exclusive 	-> set flag 'cpu_exclusive'
-# /bin/echo 0 > cpu_exclusive 	-> unset flag 'cpu_exclusive'
+# /bin/echo 1 > cpuset.cpu_exclusive 	-> set flag 'cpuset.cpu_exclusive'
+# /bin/echo 0 > cpuset.cpu_exclusive 	-> unset flag 'cpuset.cpu_exclusive'
 
 2.4 Attaching processes
 -----------------------
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index 72db89ed060..f7f68b2ac19 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -1,6 +1,6 @@
 Memory Resource Controller(Memcg)  Implementation Memo.
-Last Updated: 2009/1/20
-Base Kernel Version: based on 2.6.29-rc2.
+Last Updated: 2010/2
+Base Kernel Version: based on 2.6.33-rc7-mm(candidate for 34).
 
 Because VM is getting complex (one of reasons is memcg...), memcg's behavior
 is complex. This is a document for memcg's internal behavior.
@@ -337,7 +337,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	race and lock dependency with other cgroup subsystems.
 
 	example)
-	# mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
+	# mount -t cgroup none /cgroup -o cpuset,memory,cpu,devices
 
 	and do task move, mkdir, rmdir etc...under this.
 
@@ -348,7 +348,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 
 	For example, test like following is good.
 	(Shell-A)
-	# mount -t cgroup none /cgroup -t memory
+	# mount -t cgroup none /cgroup -o memory
 	# mkdir /cgroup/test
 	# echo 40M > /cgroup/test/memory.limit_in_bytes
 	# echo 0 > /cgroup/test/tasks
@@ -378,3 +378,42 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	#echo 50M > memory.limit_in_bytes
 	#echo 50M > memory.memsw.limit_in_bytes
 	run 51M of malloc
+
+ 9.9 Move charges at task migration
+	Charges associated with a task can be moved along with task migration.
+
+	(Shell-A)
+	#mkdir /cgroup/A
+	#echo $$ >/cgroup/A/tasks
+	run some programs which uses some amount of memory in /cgroup/A.
+
+	(Shell-B)
+	#mkdir /cgroup/B
+	#echo 1 >/cgroup/B/memory.move_charge_at_immigrate
+	#echo "pid of the program running in group A" >/cgroup/B/tasks
+
+	You can see charges have been moved by reading *.usage_in_bytes or
+	memory.stat of both A and B.
+	See 8.2 of Documentation/cgroups/memory.txt to see what value should be
+	written to move_charge_at_immigrate.
+
+ 9.10 Memory thresholds
+	Memory controler implements memory thresholds using cgroups notification
+	API. You can use Documentation/cgroups/cgroup_event_listener.c to test
+	it.
+
+	(Shell-A) Create cgroup and run event listener
+	# mkdir /cgroup/A
+	# ./cgroup_event_listener /cgroup/A/memory.usage_in_bytes 5M
+
+	(Shell-B) Add task to cgroup and try to allocate and free memory
+	# echo $$ >/cgroup/A/tasks
+	# a="$(dd if=/dev/zero bs=1M count=10)"
+	# a=
+
+	You will see message from cgroup_event_listener every time you cross
+	the thresholds.
+
+	Use /cgroup/A/memory.memsw.usage_in_bytes to test memsw thresholds.
+
+	It's good idea to test root cgroup as well.
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index b871f2552b4..3a6aecd078b 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -182,6 +182,8 @@ list.
 NOTE: Reclaim does not work for the root cgroup, since we cannot set any
 limits on the root cgroup.
 
+Note2: When panic_on_oom is set to "2", the whole system will panic.
+
 2. Locking
 
 The memory controller uses the following hierarchy
@@ -262,10 +264,12 @@ some of the pages cached in the cgroup (page cache pages).
 4.2 Task migration
 
 When a task migrates from one cgroup to another, it's charge is not
-carried forward. The pages allocated from the original cgroup still
+carried forward by default. The pages allocated from the original cgroup still
 remain charged to it, the charge is dropped when the page is freed or
 reclaimed.
 
+Note: You can move charges of a task along with task migration. See 8.
+
 4.3 Removing a cgroup
 
 A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
@@ -336,7 +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.
@@ -377,7 +381,8 @@ The feature can be disabled by
 NOTE1: Enabling/disabling will fail if the cgroup already has other
 cgroups created below it.
 
-NOTE2: This feature can be enabled/disabled per subtree.
+NOTE2: When panic_on_oom is set to "2", the whole system will panic in
+case of an oom event in any cgroup.
 
 7. Soft limits
 
@@ -414,7 +419,76 @@ NOTE1: Soft limits take effect over a long period of time, since they involve
 NOTE2: It is recommended to set the soft limit always below the hard limit,
        otherwise the hard limit will take precedence.
 
-8. TODO
+8. Move charges at task migration
+
+Users can move charges associated with a task along with task migration, that
+is, uncharge task's pages from the old cgroup and charge them to the new cgroup.
+This feature is not supported in !CONFIG_MMU environments because of lack of
+page tables.
+
+8.1 Interface
+
+This feature is disabled by default. It can be enabled(and disabled again) by
+writing to memory.move_charge_at_immigrate of the destination cgroup.
+
+If you want to enable it:
+
+# echo (some positive value) > memory.move_charge_at_immigrate
+
+Note: Each bits of move_charge_at_immigrate has its own meaning about what type
+      of charges should be moved. See 8.2 for details.
+Note: Charges are moved only when you move mm->owner, IOW, a leader of a thread
+      group.
+Note: If we cannot find enough space for the task in the destination cgroup, we
+      try to make space by reclaiming memory. Task migration may fail if we
+      cannot make enough space.
+Note: It can take several seconds if you move charges in giga bytes order.
+
+And if you want disable it again:
+
+# echo 0 > memory.move_charge_at_immigrate
+
+8.2 Type of charges which can be move
+
+Each bits of move_charge_at_immigrate has its own meaning about what type of
+charges should be moved.
+
+  bit | what type of charges would be moved ?
+ -----+------------------------------------------------------------------------
+   0  | A charge of an anonymous page(or swap of it) used by the target task.
+      | Those pages and swaps must be used only by the target task. You must
+      | enable Swap Extension(see 2.4) to enable move of swap charges.
+
+Note: Those pages and swaps must be charged to the old cgroup.
+Note: More type of pages(e.g. file cache, shmem,) will be supported by other
+      bits in future.
+
+8.3 TODO
+
+- Add support for other types of pages(e.g. file cache, shmem, etc.).
+- Implement madvise(2) to let users decide the vma to be moved or not to be
+  moved.
+- All of moving charge operations are done under cgroup_mutex. It's not good
+  behavior to hold the mutex too long, so we may need some trick.
+
+9. Memory thresholds
+
+Memory controler implements memory thresholds using cgroups notification
+API (see cgroups.txt). It allows to register multiple memory and memsw
+thresholds and gets notifications when it crosses.
+
+To register a threshold application need:
+ - create an eventfd using eventfd(2);
+ - open memory.usage_in_bytes or memory.memsw.usage_in_bytes;
+ - write string like "<event_fd> <memory.usage_in_bytes> <threshold>" to
+   cgroup.event_control.
+
+Application will be notified through eventfd when memory usage crosses
+threshold in any direction.
+
+It's applicable for root and non-root cgroup.
+
+10. TODO
 
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first
diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt
new file mode 100644
index 00000000000..8117e5bf606
--- /dev/null
+++ b/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.
diff --git a/Documentation/console/console.txt b/Documentation/console/console.txt
index 877a1b26cc3..926cf1b5e63 100644
--- a/Documentation/console/console.txt
+++ b/Documentation/console/console.txt
@@ -74,7 +74,7 @@ driver takes over the consoles vacated by the driver. Binding, on the other
 hand, will bind the driver to the consoles that are currently occupied by a
 system driver.
 
-NOTE1: Binding and binding must be selected in Kconfig. It's under:
+NOTE1: Binding and unbinding must be selected in Kconfig. It's under:
 
 Device Drivers -> Character devices -> Support for binding and unbinding
 console drivers
diff --git a/Documentation/cpu-freq/pcc-cpufreq.txt b/Documentation/cpu-freq/pcc-cpufreq.txt
new file mode 100644
index 00000000000..9e3c3b33514
--- /dev/null
+++ b/Documentation/cpu-freq/pcc-cpufreq.txt
@@ -0,0 +1,207 @@
+/*
+ *  pcc-cpufreq.txt - PCC interface documentation
+ *
+ *  Copyright (C) 2009 Red Hat, Matthew Garrett <mjg@redhat.com>
+ *  Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ *      Nagananda Chumbalkar <nagananda.chumbalkar@hp.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or NON
+ *  INFRINGEMENT. See the GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+
+			Processor Clocking Control Driver
+			---------------------------------
+
+Contents:
+---------
+1.	Introduction
+1.1	PCC interface
+1.1.1   Get Average Frequency
+1.1.2	Set Desired Frequency
+1.2	Platforms affected
+2.	Driver and /sys details
+2.1	scaling_available_frequencies
+2.2	cpuinfo_transition_latency
+2.3	cpuinfo_cur_freq
+2.4	related_cpus
+3.	Caveats
+
+1. Introduction:
+----------------
+Processor Clocking Control (PCC) is an interface between the platform
+firmware and OSPM. It is a mechanism for coordinating processor
+performance (ie: frequency) between the platform firmware and the OS.
+
+The PCC driver (pcc-cpufreq) allows OSPM to take advantage of the PCC
+interface.
+
+OS utilizes the PCC interface to inform platform firmware what frequency the
+OS wants for a logical processor. The platform firmware attempts to achieve
+the requested frequency. If the request for the target frequency could not be
+satisfied by platform firmware, then it usually means that power budget
+conditions are in place, and "power capping" is taking place.
+
+1.1 PCC interface:
+------------------
+The complete PCC specification is available here:
+http://www.acpica.org/download/Processor-Clocking-Control-v1p0.pdf
+
+PCC relies on a shared memory region that provides a channel for communication
+between the OS and platform firmware. PCC also implements a "doorbell" that
+is used by the OS to inform the platform firmware that a command has been
+sent.
+
+The ACPI PCCH() method is used to discover the location of the PCC shared
+memory region. The shared memory region header contains the "command" and
+"status" interface. PCCH() also contains details on how to access the platform
+doorbell.
+
+The following commands are supported by the PCC interface:
+* Get Average Frequency
+* Set Desired Frequency
+
+The ACPI PCCP() method is implemented for each logical processor and is
+used to discover the offsets for the input and output buffers in the shared
+memory region.
+
+When PCC mode is enabled, the platform will not expose processor performance
+or throttle states (_PSS, _TSS and related ACPI objects) to OSPM. Therefore,
+the native P-state driver (such as acpi-cpufreq for Intel, powernow-k8 for
+AMD) will not load.
+
+However, OSPM remains in control of policy. The governor (eg: "ondemand")
+computes the required performance for each processor based on server workload.
+The PCC driver fills in the command interface, and the input buffer and
+communicates the request to the platform firmware. The platform firmware is
+responsible for delivering the requested performance.
+
+Each PCC command is "global" in scope and can affect all the logical CPUs in
+the system. Therefore, PCC is capable of performing "group" updates. With PCC
+the OS is capable of getting/setting the frequency of all the logical CPUs in
+the system with a single call to the BIOS.
+
+1.1.1 Get Average Frequency:
+----------------------------
+This command is used by the OSPM to query the running frequency of the
+processor since the last time this command was completed. The output buffer
+indicates the average unhalted frequency of the logical processor expressed as
+a percentage of the nominal (ie: maximum) CPU frequency. The output buffer
+also signifies if the CPU frequency is limited by a power budget condition.
+
+1.1.2 Set Desired Frequency:
+----------------------------
+This command is used by the OSPM to communicate to the platform firmware the
+desired frequency for a logical processor. The output buffer is currently
+ignored by OSPM. The next invocation of "Get Average Frequency" will inform
+OSPM if the desired frequency was achieved or not.
+
+1.2 Platforms affected:
+-----------------------
+The PCC driver will load on any system where the platform firmware:
+* supports the PCC interface, and the associated PCCH() and PCCP() methods
+* assumes responsibility for managing the hardware clocking controls in order
+to deliver the requested processor performance
+
+Currently, certain HP ProLiant platforms implement the PCC interface. On those
+platforms PCC is the "default" choice.
+
+However, it is possible to disable this interface via a BIOS setting. In
+such an instance, as is also the case on platforms where the PCC interface
+is not implemented, the PCC driver will fail to load silently.
+
+2. Driver and /sys details:
+---------------------------
+When the driver loads, it merely prints the lowest and the highest CPU
+frequencies supported by the platform firmware.
+
+The PCC driver loads with a message such as:
+pcc-cpufreq: (v1.00.00) driver loaded with frequency limits: 1600 MHz, 2933
+MHz
+
+This means that the OPSM can request the CPU to run at any frequency in
+between the limits (1600 MHz, and 2933 MHz) specified in the message.
+
+Internally, there is no need for the driver to convert the "target" frequency
+to a corresponding P-state.
+
+The VERSION number for the driver will be of the format v.xy.ab.
+eg: 1.00.02
+   ----- --
+    |    |
+    |    -- this will increase with bug fixes/enhancements to the driver
+    |-- this is the version of the PCC specification the driver adheres to
+
+
+The following is a brief discussion on some of the fields exported via the
+/sys filesystem and how their values are affected by the PCC driver:
+
+2.1 scaling_available_frequencies:
+----------------------------------
+scaling_available_frequencies is not created in /sys. No intermediate
+frequencies need to be listed because the BIOS will try to achieve any
+frequency, within limits, requested by the governor. A frequency does not have
+to be strictly associated with a P-state.
+
+2.2 cpuinfo_transition_latency:
+-------------------------------
+The cpuinfo_transition_latency field is 0. The PCC specification does
+not include a field to expose this value currently.
+
+2.3 cpuinfo_cur_freq:
+---------------------
+A) Often cpuinfo_cur_freq will show a value different than what is declared
+in the scaling_available_frequencies or scaling_cur_freq, or scaling_max_freq.
+This is due to "turbo boost" available on recent Intel processors. If certain
+conditions are met the BIOS can achieve a slightly higher speed than requested
+by OSPM. An example:
+
+scaling_cur_freq	: 2933000
+cpuinfo_cur_freq	: 3196000
+
+B) There is a round-off error associated with the cpuinfo_cur_freq value.
+Since the driver obtains the current frequency as a "percentage" (%) of the
+nominal frequency from the BIOS, sometimes, the values displayed by
+scaling_cur_freq and cpuinfo_cur_freq may not match. An example:
+
+scaling_cur_freq	: 1600000
+cpuinfo_cur_freq	: 1583000
+
+In this example, the nominal frequency is 2933 MHz. The driver obtains the
+current frequency, cpuinfo_cur_freq, as 54% of the nominal frequency:
+
+	54% of 2933 MHz = 1583 MHz
+
+Nominal frequency is the maximum frequency of the processor, and it usually
+corresponds to the frequency of the P0 P-state.
+
+2.4 related_cpus:
+-----------------
+The related_cpus field is identical to affected_cpus.
+
+affected_cpus	: 4
+related_cpus	: 4
+
+Currently, the PCC driver does not evaluate _PSD. The platforms that support
+PCC do not implement SW_ALL. So OSPM doesn't need to perform any coordination
+to ensure that the same frequency is requested of all dependent CPUs.
+
+3. Caveats:
+-----------
+The "cpufreq_stats" module in its present form cannot be loaded and
+expected to work with the PCC driver. Since the "cpufreq_stats" module
+provides information wrt each P-state, it is not applicable to the PCC driver.
diff --git a/Documentation/device-mapper/snapshot.txt b/Documentation/device-mapper/snapshot.txt
index e3a77b21513..0d5bc46dc16 100644
--- a/Documentation/device-mapper/snapshot.txt
+++ b/Documentation/device-mapper/snapshot.txt
@@ -122,3 +122,47 @@ volumeGroup-base: 0 2097152 snapshot-merge 254:11 254:12 P 16
 brw-------  1 root root 254, 11 29 ago 18:15 /dev/mapper/volumeGroup-base-real
 brw-------  1 root root 254, 12 29 ago 18:16 /dev/mapper/volumeGroup-base-cow
 brw-------  1 root root 254, 10 29 ago 18:16 /dev/mapper/volumeGroup-base
+
+
+How to determine when a merging is complete
+===========================================
+The snapshot-merge and snapshot status lines end with:
+  <sectors_allocated>/<total_sectors> <metadata_sectors>
+
+Both <sectors_allocated> and <total_sectors> include both data and metadata.
+During merging, the number of sectors allocated gets smaller and
+smaller.  Merging has finished when the number of sectors holding data
+is zero, in other words <sectors_allocated> == <metadata_sectors>.
+
+Here is a practical example (using a hybrid of lvm and dmsetup commands):
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
+  snap    volumeGroup swi-a- 1.00g base  18.97
+
+# dmsetup status volumeGroup-snap
+0 8388608 snapshot 397896/2097152 1560
+                                  ^^^^ metadata sectors
+
+# lvconvert --merge -b volumeGroup/snap
+  Merging of volume snap started.
+
+# lvs volumeGroup/snap
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup Owi-a- 4.00g          17.23
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 281688/2097152 1104
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 180480/2097152 712
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 16/2097152 16
+
+Merging has finished.
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
diff --git a/Documentation/driver-model/platform.txt b/Documentation/driver-model/platform.txt
index 2e2c2ea90ce..41f41632ee5 100644
--- a/Documentation/driver-model/platform.txt
+++ b/Documentation/driver-model/platform.txt
@@ -192,7 +192,7 @@ command line. This will execute all matching early_param() callbacks.
 User specified early platform devices will be registered at this point.
 For the early serial console case the user can specify port on the
 kernel command line as "earlyprintk=serial.0" where "earlyprintk" is
-the class string, "serial" is the name of the platfrom driver and
+the class string, "serial" is the name of the platform driver and
 0 is the platform device id. If the id is -1 then the dot and the
 id can be omitted.
 
diff --git a/Documentation/eisa.txt b/Documentation/eisa.txt
index 60e361ba08c..f297fc1202a 100644
--- a/Documentation/eisa.txt
+++ b/Documentation/eisa.txt
@@ -171,7 +171,7 @@ device.
 virtual_root.force_probe :
 
 Force the probing code to probe EISA slots even when it cannot find an
-EISA compliant mainboard (nothing appears on slot 0). Defaultd to 0
+EISA compliant mainboard (nothing appears on slot 0). Defaults to 0
 (don't force), and set to 1 (force probing) when either
 CONFIG_ALPHA_JENSEN or CONFIG_EISA_VLB_PRIMING are set.
 
diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt
index a618efab7b1..945ff3fda43 100644
--- a/Documentation/email-clients.txt
+++ b/Documentation/email-clients.txt
@@ -216,26 +216,14 @@ Works.  Use "Insert file..." or external editor.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Gmail (Web GUI)
 
-If you just have to use Gmail to send patches, it CAN be made to work.  It
-requires a bit of external help, though.
-
-The first problem is that Gmail converts tabs to spaces.  This will
-totally break your patches.  To prevent this, you have to use a different
-editor.  There is a firefox extension called "ViewSourceWith"
-(https://addons.mozilla.org/en-US/firefox/addon/394) which allows you to
-edit any text box in the editor of your choice.  Configure it to launch
-your favorite editor.  When you want to send a patch, use this technique.
-Once you have crafted your messsage + patch, save and exit the editor,
-which should reload the Gmail edit box.  GMAIL WILL PRESERVE THE TABS.
-Hoorah.  Apparently you can cut-n-paste literal tabs, but Gmail will
-convert those to spaces upon sending!
-
-The second problem is that Gmail converts tabs to spaces on replies.  If
-you reply to a patch, don't expect to be able to apply it as a patch.
-
-The last problem is that Gmail will base64-encode any message that has a
-non-ASCII character.  That includes things like European names.  Be aware.
-
-Gmail is not convenient for lkml patches, but CAN be made to work.
+Does not work for sending patches.
+
+Gmail web client converts tabs to spaces automatically.
+
+At the same time it wraps lines every 78 chars with CRLF style line breaks
+although tab2space problem can be solved with external editor.
+
+Another problem is that Gmail will base64-encode any message that has a
+non-ASCII character. That includes things like European names.
 
                                 ###
diff --git a/Documentation/fault-injection/provoke-crashes.txt b/Documentation/fault-injection/provoke-crashes.txt
new file mode 100644
index 00000000000..7a9d3d81525
--- /dev/null
+++ b/Documentation/fault-injection/provoke-crashes.txt
@@ -0,0 +1,38 @@
+The lkdtm module provides an interface to crash or injure the kernel at
+predefined crashpoints to evaluate the reliability of crash dumps obtained
+using different dumping solutions. The module uses KPROBEs to instrument
+crashing points, but can also crash the kernel directly without KRPOBE
+support.
+
+
+You can provide the way either through module arguments when inserting
+the module, or through a debugfs interface.
+
+Usage: insmod lkdtm.ko [recur_count={>0}] cpoint_name=<> cpoint_type=<>
+				[cpoint_count={>0}]
+
+  recur_count : Recursion level for the stack overflow test. Default is 10.
+
+  cpoint_name : Crash point where the kernel is to be crashed. It can be
+	 one of INT_HARDWARE_ENTRY, INT_HW_IRQ_EN, INT_TASKLET_ENTRY,
+	 FS_DEVRW, MEM_SWAPOUT, TIMERADD, SCSI_DISPATCH_CMD,
+	 IDE_CORE_CP, DIRECT
+
+  cpoint_type : Indicates the action to be taken on hitting the crash point.
+     It can be one of PANIC, BUG, EXCEPTION, LOOP, OVERFLOW,
+     CORRUPT_STACK, UNALIGNED_LOAD_STORE_WRITE, OVERWRITE_ALLOCATION,
+     WRITE_AFTER_FREE,
+
+  cpoint_count : Indicates the number of times the crash point is to be hit
+    to trigger an action. The default is 10.
+
+You can also induce failures by mounting debugfs and writing the type to
+<mountpoint>/provoke-crash/<crashpoint>. E.g.,
+
+  mount -t debugfs debugfs /mnt
+  echo EXCEPTION > /mnt/provoke-crash/INT_HARDWARE_ENTRY
+
+
+A special file is `DIRECT' which will induce the crash directly without
+KPROBE instrumentation. This mode is the only one available when the module
+is built on a kernel without KPROBEs support.
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 73ef30dbe61..ed511af0f79 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -117,19 +117,25 @@ Who:	Mauro Carvalho Chehab <mchehab@infradead.org>
 ---------------------------
 
 What:	PCMCIA control ioctl (needed for pcmcia-cs [cardmgr, cardctl])
-When:	November 2005
+When:	2.6.35/2.6.36
 Files:	drivers/pcmcia/: pcmcia_ioctl.c
 Why:	With the 16-bit PCMCIA subsystem now behaving (almost) like a
 	normal hotpluggable bus, and with it using the default kernel
 	infrastructure (hotplug, driver core, sysfs) keeping the PCMCIA
 	control ioctl needed by cardmgr and cardctl from pcmcia-cs is
-	unnecessary, and makes further cleanups and integration of the
+	unnecessary and potentially harmful (it does not provide for
+	proper locking), and makes further cleanups and integration of the
 	PCMCIA subsystem into the Linux kernel device driver model more
 	difficult. The features provided by cardmgr and cardctl are either
 	handled by the kernel itself now or are available in the new
 	pcmciautils package available at
 	http://kernel.org/pub/linux/utils/kernel/pcmcia/
-Who:	Dominik Brodowski <linux@brodo.de>
+
+	For all architectures except ARM, the associated config symbol
+	has been removed from kernel 2.6.34; for ARM, it will be likely
+	be removed from kernel 2.6.35. The actual code will then likely
+	be removed from kernel 2.6.36.
+Who:	Dominik Brodowski <linux@dominikbrodowski.net>
 
 ---------------------------
 
@@ -443,12 +449,6 @@ Who:	Alok N Kataria <akataria@vmware.com>
 
 ----------------------------
 
-What:	adt7473 hardware monitoring driver
-When:	February 2010
-Why:	Obsoleted by the adt7475 driver.
-Who:	Jean Delvare <khali@linux-fr.org>
-
----------------------------
 What:	Support for lcd_switch and display_get in asus-laptop driver
 When:	March 2010
 Why:	These two features use non-standard interfaces. There are the
@@ -550,3 +550,42 @@ Why:	udev fully replaces this special file system that only contains CAPI
 	NCCI TTY device nodes. User space (pppdcapiplugin) works without
 	noticing the difference.
 Who:	Jan Kiszka <jan.kiszka@web.de>
+
+----------------------------
+
+What:	KVM memory aliases support
+When:	July 2010
+Why:	Memory aliasing support is used for speeding up guest vga access
+	through the vga windows.
+
+	Modern userspace no longer uses this feature, so it's just bitrotted
+	code and can be removed with no impact.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:	KVM kernel-allocated memory slots
+When:	July 2010
+Why:	Since 2.6.25, kvm supports user-allocated memory slots, which are
+	much more flexible than kernel-allocated slots.  All current userspace
+	supports the newer interface and this code can be removed with no
+	impact.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:	KVM paravirt mmu host support
+When:	January 2011
+Why:	The paravirt mmu host support is slower than non-paravirt mmu, both
+	on newer and older hardware.  It is already not exposed to the guest,
+	and kept only for live migration purposes.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What: 	"acpi=ht" boot option
+When:	2.6.35
+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>
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 875d49696b6..4303614b5ad 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/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
@@ -32,6 +34,8 @@ dlmfs.txt
 	- info on the userspace interface to the OCFS2 DLM.
 dnotify.txt
 	- info about directory notification in Linux.
+dnotify_test.c
+	- example program for dnotify
 ecryptfs.txt
 	- docs on eCryptfs: stacked cryptographic filesystem for Linux.
 exofs.txt
@@ -62,6 +66,8 @@ jfs.txt
 	- info and mount options for the JFS filesystem.
 locks.txt
 	- info on file locking implementations, flock() vs. fcntl(), etc.
+logfs.txt
+	- info on the LogFS flash filesystem.
 mandatory-locking.txt
 	- info on the Linux implementation of Sys V mandatory file locking.
 ncpfs.txt
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 18b9d0ca063..06bbbed7120 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -460,13 +460,6 @@ in sys_read() and friends.
 
 --------------------------- dquot_operations -------------------------------
 prototypes:
-	int (*initialize) (struct inode *, int);
-	int (*drop) (struct inode *);
-	int (*alloc_space) (struct inode *, qsize_t, int);
-	int (*alloc_inode) (const struct inode *, unsigned long);
-	int (*free_space) (struct inode *, qsize_t);
-	int (*free_inode) (const struct inode *, unsigned long);
-	int (*transfer) (struct inode *, struct iattr *);
 	int (*write_dquot) (struct dquot *);
 	int (*acquire_dquot) (struct dquot *);
 	int (*release_dquot) (struct dquot *);
@@ -479,13 +472,6 @@ a proper locking wrt the filesystem and call the generic quota operations.
 What filesystem should expect from the generic quota functions:
 
 		FS recursion	Held locks when called
-initialize:	yes		maybe dqonoff_sem
-drop:		yes		-
-alloc_space:	->mark_dirty()	-
-alloc_inode:	->mark_dirty()	-
-free_space:	->mark_dirty()	-
-free_inode:	->mark_dirty()	-
-transfer:	yes		-
 write_dquot:	yes		dqonoff_sem or dqptr_sem
 acquire_dquot:	yes		dqonoff_sem or dqptr_sem
 release_dquot:	yes		dqonoff_sem or dqptr_sem
@@ -495,10 +481,6 @@ write_info:	yes		dqonoff_sem
 FS recursion means calling ->quota_read() and ->quota_write() from superblock
 operations.
 
-->alloc_space(), ->alloc_inode(), ->free_space(), ->free_inode() are called
-only directly by the filesystem and do not call any fs functions only
-the ->mark_dirty() operation.
-
 More details about quota locking can be found in fs/dquot.c.
 
 --------------------------- vm_operations_struct -----------------------------
diff --git a/Documentation/filesystems/Makefile b/Documentation/filesystems/Makefile
new file mode 100644
index 00000000000..a5dd114da14
--- /dev/null
+++ b/Documentation/filesystems/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := dnotify_test
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/filesystems/ceph.txt b/Documentation/filesystems/ceph.txt
new file mode 100644
index 00000000000..0660c9f5dee
--- /dev/null
+++ b/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
diff --git a/Documentation/filesystems/dnotify.txt b/Documentation/filesystems/dnotify.txt
index 9f5d338ddbb..6baf88f4685 100644
--- a/Documentation/filesystems/dnotify.txt
+++ b/Documentation/filesystems/dnotify.txt
@@ -62,38 +62,9 @@ disabled, fcntl(fd, F_NOTIFY, ...) will return -EINVAL.
 
 Example
 -------
+See Documentation/filesystems/dnotify_test.c for an example.
 
-	#define _GNU_SOURCE	/* needed to get the defines */
-	#include <fcntl.h>	/* in glibc 2.2 this has the needed
-					   values defined */
-	#include <signal.h>
-	#include <stdio.h>
-	#include <unistd.h>
-
-	static volatile int event_fd;
-
-	static void handler(int sig, siginfo_t *si, void *data)
-	{
-		event_fd = si->si_fd;
-	}
-
-	int main(void)
-	{
-		struct sigaction act;
-		int fd;
-
-		act.sa_sigaction = handler;
-		sigemptyset(&act.sa_mask);
-		act.sa_flags = SA_SIGINFO;
-		sigaction(SIGRTMIN + 1, &act, NULL);
-
-		fd = open(".", O_RDONLY);
-		fcntl(fd, F_SETSIG, SIGRTMIN + 1);
-		fcntl(fd, F_NOTIFY, DN_MODIFY|DN_CREATE|DN_MULTISHOT);
-		/* we will now be notified if any of the files
-		   in "." is modified or new files are created */
-		while (1) {
-			pause();
-			printf("Got event on fd=%d\n", event_fd);
-		}
-	}
+NOTE
+----
+Beginning with Linux 2.6.13, dnotify has been replaced by inotify.
+See Documentation/filesystems/inotify.txt for more information on it.
diff --git a/Documentation/filesystems/dnotify_test.c b/Documentation/filesystems/dnotify_test.c
new file mode 100644
index 00000000000..8b37b4a1e18
--- /dev/null
+++ b/Documentation/filesystems/dnotify_test.c
@@ -0,0 +1,34 @@
+#define _GNU_SOURCE	/* needed to get the defines */
+#include <fcntl.h>	/* in glibc 2.2 this has the needed
+				   values defined */
+#include <signal.h>
+#include <stdio.h>
+#include <unistd.h>
+
+static volatile int event_fd;
+
+static void handler(int sig, siginfo_t *si, void *data)
+{
+	event_fd = si->si_fd;
+}
+
+int main(void)
+{
+	struct sigaction act;
+	int fd;
+
+	act.sa_sigaction = handler;
+	sigemptyset(&act.sa_mask);
+	act.sa_flags = SA_SIGINFO;
+	sigaction(SIGRTMIN + 1, &act, NULL);
+
+	fd = open(".", O_RDONLY);
+	fcntl(fd, F_SETSIG, SIGRTMIN + 1);
+	fcntl(fd, F_NOTIFY, DN_MODIFY|DN_CREATE|DN_MULTISHOT);
+	/* we will now be notified if any of the files
+	   in "." is modified or new files are created */
+	while (1) {
+		pause();
+		printf("Got event on fd=%d\n", event_fd);
+	}
+}
diff --git a/Documentation/filesystems/logfs.txt b/Documentation/filesystems/logfs.txt
new file mode 100644
index 00000000000..e64c94ba401
--- /dev/null
+++ b/Documentation/filesystems/logfs.txt
@@ -0,0 +1,241 @@
+
+The LogFS Flash Filesystem
+==========================
+
+Specification
+=============
+
+Superblocks
+-----------
+
+Two superblocks exist at the beginning and end of the filesystem.
+Each superblock is 256 Bytes large, with another 3840 Bytes reserved
+for future purposes, making a total of 4096 Bytes.
+
+Superblock locations may differ for MTD and block devices.  On MTD the
+first non-bad block contains a superblock in the first 4096 Bytes and
+the last non-bad block contains a superblock in the last 4096 Bytes.
+On block devices, the first 4096 Bytes of the device contain the first
+superblock and the last aligned 4096 Byte-block contains the second
+superblock.
+
+For the most part, the superblocks can be considered read-only.  They
+are written only to correct errors detected within the superblocks,
+move the journal and change the filesystem parameters through tunefs.
+As a result, the superblock does not contain any fields that require
+constant updates, like the amount of free space, etc.
+
+Segments
+--------
+
+The space in the device is split up into equal-sized segments.
+Segments are the primary write unit of LogFS.  Within each segments,
+writes happen from front (low addresses) to back (high addresses.  If
+only a partial segment has been written, the segment number, the
+current position within and optionally a write buffer are stored in
+the journal.
+
+Segments are erased as a whole.  Therefore Garbage Collection may be
+required to completely free a segment before doing so.
+
+Journal
+--------
+
+The journal contains all global information about the filesystem that
+is subject to frequent change.  At mount time, it has to be scanned
+for the most recent commit entry, which contains a list of pointers to
+all currently valid entries.
+
+Object Store
+------------
+
+All space except for the superblocks and journal is part of the object
+store.  Each segment contains a segment header and a number of
+objects, each consisting of the object header and the payload.
+Objects are either inodes, directory entries (dentries), file data
+blocks or indirect blocks.
+
+Levels
+------
+
+Garbage collection (GC) may fail if all data is written
+indiscriminately.  One requirement of GC is that data is seperated
+roughly according to the distance between the tree root and the data.
+Effectively that means all file data is on level 0, indirect blocks
+are on levels 1, 2, 3 4 or 5 for 1x, 2x, 3x, 4x or 5x indirect blocks,
+respectively.  Inode file data is on level 6 for the inodes and 7-11
+for indirect blocks.
+
+Each segment contains objects of a single level only.  As a result,
+each level requires its own seperate segment to be open for writing.
+
+Inode File
+----------
+
+All inodes are stored in a special file, the inode file.  Single
+exception is the inode file's inode (master inode) which for obvious
+reasons is stored in the journal instead.  Instead of data blocks, the
+leaf nodes of the inode files are inodes.
+
+Aliases
+-------
+
+Writes in LogFS are done by means of a wandering tree.  A naïve
+implementation would require that for each write or a block, all
+parent blocks are written as well, since the block pointers have
+changed.  Such an implementation would not be very efficient.
+
+In LogFS, the block pointer changes are cached in the journal by means
+of alias entries.  Each alias consists of its logical address - inode
+number, block index, level and child number (index into block) - and
+the changed data.  Any 8-byte word can be changes in this manner.
+
+Currently aliases are used for block pointers, file size, file used
+bytes and the height of an inodes indirect tree.
+
+Segment Aliases
+---------------
+
+Related to regular aliases, these are used to handle bad blocks.
+Initially, bad blocks are handled by moving the affected segment
+content to a spare segment and noting this move in the journal with a
+segment alias, a simple (to, from) tupel.  GC will later empty this
+segment and the alias can be removed again.  This is used on MTD only.
+
+Vim
+---
+
+By cleverly predicting the life time of data, it is possible to
+seperate long-living data from short-living data and thereby reduce
+the GC overhead later.  Each type of distinc life expectency (vim) can
+have a seperate segment open for writing.  Each (level, vim) tupel can
+be open just once.  If an open segment with unknown vim is encountered
+at mount time, it is closed and ignored henceforth.
+
+Indirect Tree
+-------------
+
+Inodes in LogFS are similar to FFS-style filesystems with direct and
+indirect block pointers.  One difference is that LogFS uses a single
+indirect pointer that can be either a 1x, 2x, etc. indirect pointer.
+A height field in the inode defines the height of the indirect tree
+and thereby the indirection of the pointer.
+
+Another difference is the addressing of indirect blocks.  In LogFS,
+the first 16 pointers in the first indirect block are left empty,
+corresponding to the 16 direct pointers in the inode.  In ext2 (maybe
+others as well) the first pointer in the first indirect block
+corresponds to logical block 12, skipping the 12 direct pointers.
+So where ext2 is using arithmetic to better utilize space, LogFS keeps
+arithmetic simple and uses compression to save space.
+
+Compression
+-----------
+
+Both file data and metadata can be compressed.  Compression for file
+data can be enabled with chattr +c and disabled with chattr -c.  Doing
+so has no effect on existing data, but new data will be stored
+accordingly.  New inodes will inherit the compression flag of the
+parent directory.
+
+Metadata is always compressed.  However, the space accounting ignores
+this and charges for the uncompressed size.  Failing to do so could
+result in GC failures when, after moving some data, indirect blocks
+compress worse than previously.  Even on a 100% full medium, GC may
+not consume any extra space, so the compression gains are lost space
+to the user.
+
+However, they are not lost space to the filesystem internals.  By
+cheating the user for those bytes, the filesystem gained some slack
+space and GC will run less often and faster.
+
+Garbage Collection and Wear Leveling
+------------------------------------
+
+Garbage collection is invoked whenever the number of free segments
+falls below a threshold.  The best (known) candidate is picked based
+on the least amount of valid data contained in the segment.  All
+remaining valid data is copied elsewhere, thereby invalidating it.
+
+The GC code also checks for aliases and writes then back if their
+number gets too large.
+
+Wear leveling is done by occasionally picking a suboptimal segment for
+garbage collection.  If a stale segments erase count is significantly
+lower than the active segments' erase counts, it will be picked.  Wear
+leveling is rate limited, so it will never monopolize the device for
+more than one segment worth at a time.
+
+Values for "occasionally", "significantly lower" are compile time
+constants.
+
+Hashed directories
+------------------
+
+To satisfy efficient lookup(), directory entries are hashed and
+located based on the hash.  In order to both support large directories
+and not be overly inefficient for small directories, several hash
+tables of increasing size are used.  For each table, the hash value
+modulo the table size gives the table index.
+
+Tables sizes are chosen to limit the number of indirect blocks with a
+fully populated table to 0, 1, 2 or 3 respectively.  So the first
+table contains 16 entries, the second 512-16, etc.
+
+The last table is special in several ways.  First its size depends on
+the effective 32bit limit on telldir/seekdir cookies.  Since logfs
+uses the upper half of the address space for indirect blocks, the size
+is limited to 2^31.  Secondly the table contains hash buckets with 16
+entries each.
+
+Using single-entry buckets would result in birthday "attacks".  At
+just 2^16 used entries, hash collisions would be likely (P >= 0.5).
+My math skills are insufficient to do the combinatorics for the 17x
+collisions necessary to overflow a bucket, but testing showed that in
+10,000 runs the lowest directory fill before a bucket overflow was
+188,057,130 entries with an average of 315,149,915 entries.  So for
+directory sizes of up to a million, bucket overflows should be
+virtually impossible under normal circumstances.
+
+With carefully chosen filenames, it is obviously possible to cause an
+overflow with just 21 entries (4 higher tables + 16 entries + 1).  So
+there may be a security concern if a malicious user has write access
+to a directory.
+
+Open For Discussion
+===================
+
+Device Address Space
+--------------------
+
+A device address space is used for caching.  Both block devices and
+MTD provide functions to either read a single page or write a segment.
+Partial segments may be written for data integrity, but where possible
+complete segments are written for performance on simple block device
+flash media.
+
+Meta Inodes
+-----------
+
+Inodes are stored in the inode file, which is just a regular file for
+most purposes.  At umount time, however, the inode file needs to
+remain open until all dirty inodes are written.  So
+generic_shutdown_super() may not close this inode, but shouldn't
+complain about remaining inodes due to the inode file either.  Same
+goes for mapping inode of the device address space.
+
+Currently logfs uses a hack that essentially copies part of fs/inode.c
+code over.  A general solution would be preferred.
+
+Indirect block mapping
+----------------------
+
+With compression, the block device (or mapping inode) cannot be used
+to cache indirect blocks.  Some other place is required.  Currently
+logfs uses the top half of each inode's address space.  The low 8TB
+(on 32bit) are filled with file data, the high 8TB are used for
+indirect blocks.
+
+One problem is that 16TB files created on 64bit systems actually have
+data in the top 8TB.  But files >16TB would cause problems anyway, so
+only the limit has changed.
diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index 1bd0d0c0517..6a53a84afc7 100644
--- a/Documentation/filesystems/nfs/nfs41-server.txt
+++ b/Documentation/filesystems/nfs/nfs41-server.txt
@@ -17,8 +17,7 @@ kernels must turn 4.1 on or off *before* turning support for version 4
 on or off; rpc.nfsd does this correctly.)
 
 The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
-on the latest NFSv4.1 Internet Draft:
-http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
+on RFC 5661.
 
 From the many new features in NFSv4.1 the current implementation
 focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
@@ -44,7 +43,7 @@ interoperability problems with future clients.  Known issues:
 	  trunking, but this is a mandatory feature, and its use is
 	  recommended to clients in a number of places.  (E.g. to ensure
 	  timely renewal in case an existing connection's retry timeouts
-	  have gotten too long; see section 8.3 of the draft.)
+	  have gotten too long; see section 8.3 of the RFC.)
 	  Therefore, lack of this feature may cause future clients to
 	  fail.
 	- Incomplete backchannel support: incomplete backchannel gss
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 0d07513a67a..a4f30faa4f1 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -164,6 +164,7 @@ read the file /proc/PID/status:
   VmExe:        68 kB
   VmLib:      1412 kB
   VmPTE:        20 kb
+  VmSwap:        0 kB
   Threads:        1
   SigQ:   0/28578
   SigPnd: 0000000000000000
@@ -188,7 +189,13 @@ memory usage. Its seven fields are explained in Table 1-3.  The stat file
 contains details information about the process itself.  Its fields are
 explained in Table 1-4.
 
-Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
+(for SMP CONFIG users)
+For making accounting scalable, RSS related information are handled in
+asynchronous manner and the vaule may not be very precise. To see a precise
+snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
+It's slow but very precise.
+
+Table 1-2: Contents of the status files (as of 2.6.30-rc7)
 ..............................................................................
  Field                       Content
  Name                        filename of the executable
@@ -213,6 +220,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
  VmExe                       size of text segment
  VmLib                       size of shared library code
  VmPTE                       size of page table entries
+ VmSwap                      size of swap usage (the number of referred swapents)
  Threads                     number of threads
  SigQ                        number of signals queued/max. number for queue
  SigPnd                      bitmap of pending signals for the thread
@@ -430,6 +438,7 @@ Table 1-5: Kernel info in /proc
  modules     List of loaded modules                            
  mounts      Mounted filesystems                               
  net         Networking info (see text)                        
+ pagetypeinfo Additional page allocator information (see text)  (2.5)
  partitions  Table of partitions known to the system           
  pci	     Deprecated info of PCI bus (new way -> /proc/bus/pci/,
              decoupled by lspci					(2.4)
@@ -584,7 +593,7 @@ Node 0, zone      DMA      0      4      5      4      4      3 ...
 Node 0, zone   Normal      1      0      0      1    101      8 ...
 Node 0, zone  HighMem      2      0      0      1      1      0 ...
 
-Memory fragmentation is a problem under some workloads, and buddyinfo is a 
+External fragmentation is a problem under some workloads, and buddyinfo is a
 useful tool for helping diagnose these problems.  Buddyinfo will give you a 
 clue as to how big an area you can safely allocate, or why a previous
 allocation failed.
@@ -594,6 +603,48 @@ available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 
 available in ZONE_NORMAL, etc... 
 
+More information relevant to external fragmentation can be found in
+pagetypeinfo.
+
+> cat /proc/pagetypeinfo
+Page block order: 9
+Pages per block:  512
+
+Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
+Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
+Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
+Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
+Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
+Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
+Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
+Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
+Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+
+Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
+Node 0, zone      DMA            2            0            5            1            0
+Node 0, zone    DMA32           41            6          967            2            0
+
+Fragmentation avoidance in the kernel works by grouping pages of different
+migrate types into the same contiguous regions of memory called page blocks.
+A page block is typically the size of the default hugepage size e.g. 2MB on
+X86-64. By keeping pages grouped based on their ability to move, the kernel
+can reclaim pages within a page block to satisfy a high-order allocation.
+
+The pagetypinfo begins with information on the size of a page block. It
+then gives the same type of information as buddyinfo except broken down
+by migrate-type and finishes with details on how many page blocks of each
+type exist.
+
+If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
+from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
+make an estimate of the likely number of huge pages that can be allocated
+at a given point in time. All the "Movable" blocks should be allocatable
+unless memory has been mlock()'d. Some of the Reclaimable blocks should
+also be allocatable although a lot of filesystem metadata may have to be
+reclaimed to achieve this.
+
 ..............................................................................
 
 meminfo:
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
index 23a181074f9..fc0e39af43c 100644
--- a/Documentation/filesystems/sharedsubtree.txt
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -837,6 +837,9 @@ replicas continue to be exactly same.
 	 individual lists does not affect propagation or the way propagation
 	 tree is modified by operations.
 
+	All vfsmounts in a peer group have the same ->mnt_master.  If it is
+	non-NULL, they form a contiguous (ordered) segment of slave list.
+
 	A example propagation tree looks as shown in the figure below.
 	[ NOTE: Though it looks like a forest, if we consider all the shared
 	mounts as a conceptual entity called 'pnode', it becomes a tree]
@@ -874,8 +877,19 @@ replicas continue to be exactly same.
 
 	NOTE: The propagation tree is orthogonal to the mount tree.
 
+8B Locking:
+
+	->mnt_share, ->mnt_slave, ->mnt_slave_list, ->mnt_master are protected
+	by namespace_sem (exclusive for modifications, shared for reading).
+
+	Normally we have ->mnt_flags modifications serialized by vfsmount_lock.
+	There are two exceptions: do_add_mount() and clone_mnt().
+	The former modifies a vfsmount that has not been visible in any shared
+	data structures yet.
+	The latter holds namespace_sem and the only references to vfsmount
+	are in lists that can't be traversed without namespace_sem.
 
-8B Algorithm:
+8C Algorithm:
 
 	The crux of the implementation resides in rbind/move operation.
 
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index 3015da0c6b2..fe09a2cb185 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/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
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index 1866c27eec6..c2c6e9b39bb 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -253,6 +253,70 @@ pin setup (e.g. controlling which pin the GPIO uses, pullup/pulldown).
 Also note that it's your responsibility to have stopped using a GPIO
 before you free it.
 
+Considering in most cases GPIOs are actually configured right after they
+are claimed, three additional calls are defined:
+
+	/* request a single GPIO, with initial configuration specified by
+	 * 'flags', identical to gpio_request() wrt other arguments and
+	 * return value
+	 */
+	int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
+
+	/* request multiple GPIOs in a single call
+	 */
+	int gpio_request_array(struct gpio *array, size_t num);
+
+	/* release multiple GPIOs in a single call
+	 */
+	void gpio_free_array(struct gpio *array, size_t num);
+
+where 'flags' is currently defined to specify the following properties:
+
+	* GPIOF_DIR_IN		- to configure direction as input
+	* GPIOF_DIR_OUT		- to configure direction as output
+
+	* GPIOF_INIT_LOW	- as output, set initial level to LOW
+	* GPIOF_INIT_HIGH	- as output, set initial level to HIGH
+
+since GPIOF_INIT_* are only valid when configured as output, so group valid
+combinations as:
+
+	* GPIOF_IN		- configure as input
+	* GPIOF_OUT_INIT_LOW	- configured as output, initial level LOW
+	* GPIOF_OUT_INIT_HIGH	- configured as output, initial level HIGH
+
+In the future, these flags can be extended to support more properties such
+as open-drain status.
+
+Further more, to ease the claim/release of multiple GPIOs, 'struct gpio' is
+introduced to encapsulate all three fields as:
+
+	struct gpio {
+		unsigned	gpio;
+		unsigned long	flags;
+		const char	*label;
+	};
+
+A typical example of usage:
+
+	static struct gpio leds_gpios[] = {
+		{ 32, GPIOF_OUT_INIT_HIGH, "Power LED" }, /* default to ON */
+		{ 33, GPIOF_OUT_INIT_LOW,  "Green LED" }, /* default to OFF */
+		{ 34, GPIOF_OUT_INIT_LOW,  "Red LED"   }, /* default to OFF */
+		{ 35, GPIOF_OUT_INIT_LOW,  "Blue LED"  }, /* default to OFF */
+		{ ... },
+	};
+
+	err = gpio_request_one(31, GPIOF_IN, "Reset Button");
+	if (err)
+		...
+
+	err = gpio_request_array(leds_gpios, ARRAY_SIZE(leds_gpios));
+	if (err)
+		...
+
+	gpio_free_array(leds_gpios, ARRAY_SIZE(leds_gpios));
+
 
 GPIOs mapped to IRQs
 --------------------
diff --git a/Documentation/hwmon/abituguru b/Documentation/hwmon/abituguru
index 87ffa0f5ec7..5eb3b9d5f0d 100644
--- a/Documentation/hwmon/abituguru
+++ b/Documentation/hwmon/abituguru
@@ -30,7 +30,7 @@ Supported chips:
 	   bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1
 	   You may also need to specify the fan_sensors option for these boards
 	   fan_sensors=5
-	2) There is a seperate abituguru3 driver for these motherboards,
+	2) There is a separate abituguru3 driver for these motherboards,
 	   the abituguru (without the 3 !) driver will not work on these
 	   motherboards (and visa versa)!
 
diff --git a/Documentation/hwmon/adt7411 b/Documentation/hwmon/adt7411
new file mode 100644
index 00000000000..1632960f974
--- /dev/null
+++ b/Documentation/hwmon/adt7411
@@ -0,0 +1,42 @@
+Kernel driver adt7411
+=====================
+
+Supported chips:
+  * Analog Devices ADT7411
+    Prefix: 'adt7411'
+    Addresses scanned: 0x48, 0x4a, 0x4b
+    Datasheet: Publicly available at the Analog Devices website
+
+Author: Wolfram Sang (based on adt7470 by Darrick J. Wong)
+
+Description
+-----------
+
+This driver implements support for the Analog Devices ADT7411 chip. There may
+be other chips that implement this interface.
+
+The ADT7411 can use an I2C/SMBus compatible 2-wire interface or an
+SPI-compatible 4-wire interface. It provides a 10-bit analog to digital
+converter which measures 1 temperature, vdd and 8 input voltages. It has an
+internal temperature sensor, but an external one can also be connected (one
+loses 2 inputs then). There are high- and low-limit registers for all inputs.
+
+Check the datasheet for details.
+
+sysfs-Interface
+---------------
+
+in0_input	- vdd voltage input
+in[1-8]_input	- analog 1-8 input
+temp1_input	- temperature input
+
+Besides standard interfaces, this driver adds (0 = off, 1 = on):
+
+  adc_ref_vdd	- Use vdd as reference instead of 2.25 V
+  fast_sampling	- Sample at 22.5 kHz instead of 1.4 kHz, but drop filters
+  no_average	- Turn off averaging over 16 samples
+
+Notes
+-----
+
+SPI, external temperature sensor and limit registers are not supported yet.
diff --git a/Documentation/hwmon/adt7473 b/Documentation/hwmon/adt7473
deleted file mode 100644
index 446612bd1fb..00000000000
--- a/Documentation/hwmon/adt7473
+++ /dev/null
@@ -1,74 +0,0 @@
-Kernel driver adt7473
-======================
-
-Supported chips:
-  * Analog Devices ADT7473
-    Prefix: 'adt7473'
-    Addresses scanned: I2C 0x2C, 0x2D, 0x2E
-    Datasheet: Publicly available at the Analog Devices website
-
-Author: Darrick J. Wong
-
-This driver is depreacted, please use the adt7475 driver instead.
-
-Description
------------
-
-This driver implements support for the Analog Devices ADT7473 chip family.
-
-The ADT7473 uses the 2-wire interface compatible with the SMBUS 2.0
-specification. Using an analog to digital converter it measures three (3)
-temperatures and two (2) voltages. It has four (4) 16-bit counters for
-measuring fan speed. There are three (3) PWM outputs that can be used
-to control fan speed.
-
-A sophisticated control system for the PWM outputs is designed into the
-ADT7473 that allows fan speed to be adjusted automatically based on any of the
-three temperature sensors. Each PWM output is individually adjustable and
-programmable. Once configured, the ADT7473 will adjust the PWM outputs in
-response to the measured temperatures without further host intervention.
-This feature can also be disabled for manual control of the PWM's.
-
-Each of the measured inputs (voltage, temperature, fan speed) has
-corresponding high/low limit values. The ADT7473 will signal an ALARM if
-any measured value exceeds either limit.
-
-The ADT7473 samples all inputs continuously. The driver will not read
-the registers more often than once every other second. Further,
-configuration data is only read once per minute.
-
-Special Features
-----------------
-
-The ADT7473 have a 10-bit ADC and can therefore measure temperatures
-with 0.25 degC resolution. Temperature readings can be configured either
-for twos complement format or "Offset 64" format, wherein 63 is subtracted
-from the raw value to get the temperature value.
-
-The Analog Devices datasheet is very detailed and describes a procedure for
-determining an optimal configuration for the automatic PWM control.
-
-Configuration Notes
--------------------
-
-Besides standard interfaces driver adds the following:
-
-* PWM Control
-
-* pwm#_auto_point1_pwm and temp#_auto_point1_temp and
-* pwm#_auto_point2_pwm and temp#_auto_point2_temp -
-
-point1: Set the pwm speed at a lower temperature bound.
-point2: Set the pwm speed at a higher temperature bound.
-
-The ADT7473 will scale the pwm between the lower and higher pwm speed when
-the temperature is between the two temperature boundaries.  PWM values range
-from 0 (off) to 255 (full speed).  Fan speed will be set to maximum when the
-temperature sensor associated with the PWM control exceeds temp#_max.
-
-Notes
------
-
-The NVIDIA binary driver presents an ADT7473 chip via an on-card i2c bus.
-Unfortunately, they fail to set the i2c adapter class, so this driver may
-fail to find the chip until the nvidia driver is patched.
diff --git a/Documentation/hwmon/asc7621 b/Documentation/hwmon/asc7621
new file mode 100644
index 00000000000..7287be7e1f2
--- /dev/null
+++ b/Documentation/hwmon/asc7621
@@ -0,0 +1,296 @@
+Kernel driver asc7621
+==================
+
+Supported chips:
+    Andigilog aSC7621 and aSC7621a
+    Prefix: 'asc7621'
+    Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+    Datasheet: http://www.fairview5.com/linux/asc7621/asc7621.pdf
+
+Author:
+		George Joseph
+
+Description provided by Dave Pivin @ Andigilog:
+
+Andigilog has both the PECI and pre-PECI versions of the Heceta-6, as
+Intel calls them. Heceta-6e has high frequency PWM and Heceta-6p has
+added PECI and a 4th thermal zone. The Andigilog aSC7611 is the
+Heceta-6e part and aSC7621 is the Heceta-6p part. They are both in
+volume production, shipping to Intel and their subs.
+
+We have enhanced both parts relative to the governing Intel
+specification. First enhancement is temperature reading resolution. We
+have used registers below 20h for vendor-specific functions in addition
+to those in the Intel-specified vendor range.
+
+Our conversion process produces a result that is reported as two bytes.
+The fan speed control uses this finer value to produce a "step-less" fan
+PWM output. These two bytes are "read-locked" to guarantee that once a
+high or low byte is read, the other byte is locked-in until after the
+next read of any register. So to get an atomic reading, read high or low
+byte, then the very next read should be the opposite byte. Our data
+sheet says 10-bits of resolution, although you may find the lower bits
+are active, they are not necessarily reliable or useful externally. We
+chose not to mask them.
+
+We employ significant filtering that is user tunable as described in the
+data sheet. Our temperature reports and fan PWM outputs are very smooth
+when compared to the competition, in addition to the higher resolution
+temperature reports. The smoother PWM output does not require user
+intervention.
+
+We offer GPIO features on the former VID pins. These are open-drain
+outputs or inputs and may be used as general purpose I/O or as alarm
+outputs that are based on temperature limits. These are in 19h and 1Ah.
+
+We offer flexible mapping of temperature readings to thermal zones. Any
+temperature may be mapped to any zone, which has a default assignment
+that follows Intel's specs.
+
+Since there is a fan to zone assignment that allows for the "hotter" of
+a set of zones to control the PWM of an individual fan, but there is no
+indication to the user, we have added an indicator that shows which zone
+is currently controlling the PWM for a given fan. This is in register
+00h.
+
+Both remote diode temperature readings may be given an offset value such
+that the reported reading as well as the temperature used to determine
+PWM may be offset for system calibration purposes.
+
+PECI Extended configuration allows for having more than two domains per
+PECI address and also provides an enabling function for each PECI
+address. One could use our flexible zone assignment to have a zone
+assigned to up to 4 PECI addresses. This is not possible in the default
+Intel configuration. This would be useful in multi-CPU systems with
+individual fans on each that would benefit from individual fan control.
+This is in register 0Eh.
+
+The tachometer measurement system is flexible and able to adapt to many
+fan types. We can also support pulse-stretched PWM so that 3-wire fans
+may be used. These characteristics are in registers 04h to 07h.
+
+Finally, we have added a tach disable function that turns off the tach
+measurement system for individual tachs in order to save power. That is
+in register 75h.
+
+--
+aSC7621 Product Description
+
+The aSC7621 has a two wire digital interface compatible with SMBus 2.0.
+Using a 10-bit ADC, the aSC7621 measures the temperature of two remote diode
+connected transistors as well as its own die. Support for Platform
+Environmental Control Interface (PECI) is included.
+
+Using temperature information from these four zones, an automatic fan speed
+control algorithm is employed to minimize acoustic impact while achieving
+recommended CPU temperature under varying operational loads.
+
+To set fan speed, the aSC7621 has three independent pulse width modulation
+(PWM) outputs that are controlled by one, or a combination of three,
+temperature zones. Both high- and low-frequency PWM ranges are supported.
+
+The aSC7621 also includes a digital filter that can be invoked to smooth
+temperature readings for better control of fan speed and minimum acoustic
+impact.
+
+The aSC7621 has tachometer inputs to measure fan speed on up to four fans.
+Limit and status registers for all measured values are included to alert
+the system host that any measurements are outside of programmed limits
+via status registers.
+
+System voltages of VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard power are
+monitored efficiently with internal scaling resistors.
+
+Features
+- Supports PECI interface and monitors internal and remote thermal diodes
+- 2-wire, SMBus 2.0 compliant, serial interface
+- 10-bit ADC
+- Monitors VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard/processor supplies
+- Programmable autonomous fan control based on temperature readings
+- Noise filtering of temperature reading for fan speed control
+- 0.25C digital temperature sensor resolution
+- 3 PWM fan speed control outputs for 2-, 3- or 4-wire fans and up to 4 fan
+	tachometer inputs
+- Enhanced measured temperature to Temperature Zone assignment.
+- Provides high and low PWM frequency ranges
+- 3 GPIO pins for custom use
+- 24-Lead QSOP package
+
+Configuration Notes
+===================
+
+Except where noted below, the sysfs entries created by this driver follow
+the standards defined in "sysfs-interface".
+
+temp1_source
+	0 	(default) peci_legacy = 0, Remote 1 Temperature
+			peci_legacy = 1, PECI Processor Temperature 0
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7  PECI Processor Temperature 3
+
+temp2_source
+	0 	(default) Internal Temperature
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7 	PECI Processor Temperature 3
+
+temp3_source
+	0 	(default) Remote 2 Temperature
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7 	PECI Processor Temperature 3
+
+temp4_source
+	0 	(default) peci_legacy = 0, PECI Processor Temperature 0
+			peci_legacy = 1, Remote 1 Temperature
+	1 	Remote 1 Temperature
+	2 	Remote 2 Temperature
+	3 	Internal Temperature
+	4 	PECI Processor Temperature 0
+	5 	PECI Processor Temperature 1
+	6 	PECI Processor Temperature 2
+	7 	PECI Processor Temperature 3
+
+temp[1-4]_smoothing_enable
+temp[1-4]_smoothing_time
+	Smooths spikes in temp readings caused by noise.
+	Valid values in milliseconds are:
+	35000
+	17600
+	11800
+	 7000
+	 4400
+	 3000
+	 1600
+	  800
+
+temp[1-4]_crit
+	When the corresponding zone temperature reaches this value,
+	ALL pwm outputs will got to 100%.
+
+temp[5-8]_input
+temp[5-8]_enable
+	The aSC7621 can also read temperatures provided by the processor
+	via the PECI bus.  Usually these are "core" temps and are relative
+	to the point where the automatic thermal control circuit starts
+	throttling.  This means that these are usually negative numbers.
+
+pwm[1-3]_enable
+	0		Fan off.
+	1		Fan on manual control.
+	2		Fan on automatic control and will run at the minimum pwm
+				if the temperature for the zone is below the minimum.
+	3		Fan on automatic control but will be off if the temperature
+				for the zone is below the minimum.
+	4-254	Ignored.
+	255		Fan on full.
+
+pwm[1-3]_auto_channels
+	Bitmap as described in sysctl-interface with the following
+	exceptions...
+	Only the following combination of zones (and their corresponding masks)
+	are valid:
+	1
+	2
+	3
+	2,3
+	1,2,3
+	4
+	1,2,3,4
+
+	Special values:
+	0			Disabled.
+	16		Fan on manual control.
+	31		Fan on full.
+
+
+pwm[1-3]_invert
+	When set, inverts the meaning of pwm[1-3].
+	i.e.  when pwm = 0, the fan will be on full and
+	when pwm = 255 the fan will be off.
+
+pwm[1-3]_freq
+	PWM frequency in Hz
+	Valid values in Hz are:
+
+	10
+	15
+	23
+	30  (default)
+	38
+	47
+	62
+	94
+	23000
+	24000
+	25000
+	26000
+	27000
+	28000
+	29000
+	30000
+
+	Setting any other value will be ignored.
+
+peci_enable
+	Enables or disables PECI
+
+peci_avg
+	Input filter average time.
+
+	0 	0 Sec. (no Smoothing) (default)
+	1 	0.25 Sec.
+	2 	0.5 Sec.
+	3 	1.0 Sec.
+	4 	2.0 Sec.
+	5 	4.0 Sec.
+	6 	8.0 Sec.
+	7 	0.0 Sec.
+
+peci_legacy
+
+	0	Standard Mode (default)
+		Remote Diode 1 reading is associated with
+		Temperature Zone 1, PECI is associated with
+		Zone 4
+
+	1	Legacy Mode
+		PECI is associated with Temperature Zone 1,
+		Remote Diode 1 is associated with Zone 4
+
+peci_diode
+	Diode filter
+
+	0	0.25 Sec.
+	1 	1.1 Sec.
+	2 	2.4 Sec.  (default)
+	3 	3.4 Sec.
+	4 	5.0 Sec.
+	5 	6.8 Sec.
+	6 	10.2 Sec.
+	7 	16.4 Sec.
+
+peci_4domain
+	Four domain enable
+
+	0 	1 or 2 Domains for enabled processors (default)
+	1 	3 or 4 Domains for enabled processors
+
+peci_domain
+	Domain
+
+	0 	Processor contains a single domain (0) 	 (default)
+	1 	Processor contains two domains (0,1)
diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87
index f9ba96c0ac4..8d08bf0d38e 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87
@@ -5,31 +5,23 @@ Supported chips:
   * IT8705F
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8705F_V.0.4.1.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8712F
     Prefix: 'it8712'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/Errata%20V0.1%20for%20IT8712F%20V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.3.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8716F/IT8726F
     Prefix: 'it8716'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8716F_V0.3.ZIP
-               http://www.ite.com.tw/product_info/file/pc/IT8726F_V0.3.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8718F
     Prefix: 'it8718'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0.2.zip
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0%203_(for%20C%20version).zip
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8720F
     Prefix: 'it8720'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Not yet publicly available.
+    Datasheet: Not publicly available
   * SiS950   [clone of IT8705F]
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -136,6 +128,10 @@ registers are read whenever any data is read (unless it is less than 1.5
 seconds since the last update). This means that you can easily miss
 once-only alarms.
 
+Out-of-limit readings can also result in beeping, if the chip is properly
+wired and configured. Beeping can be enabled or disabled per sensor type
+(temperatures, voltages and fans.)
+
 The IT87xx only updates its values each 1.5 seconds; reading it more often
 will do no harm, but will return 'old' values.
 
@@ -150,11 +146,38 @@ Fan speed control
 -----------------
 
 The fan speed control features are limited to manual PWM mode. Automatic
-"Smart Guardian" mode control handling is not implemented. However
-if you want to go for "manual mode" just write 1 to pwmN_enable.
+"Smart Guardian" mode control handling is only implemented for older chips
+(see below.) However if you want to go for "manual mode" just write 1 to
+pwmN_enable.
 
 If you are only able to control the fan speed with very small PWM values,
 try lowering the PWM base frequency (pwm1_freq). Depending on the fan,
 it may give you a somewhat greater control range. The same frequency is
 used to drive all fan outputs, which is why pwm2_freq and pwm3_freq are
 read-only.
+
+
+Automatic fan speed control (old interface)
+-------------------------------------------
+
+The driver supports the old interface to automatic fan speed control
+which is implemented by IT8705F chips up to revision F and IT8712F
+chips up to revision G.
+
+This interface implements 4 temperature vs. PWM output trip points.
+The PWM output of trip point 4 is always the maximum value (fan running
+at full speed) while the PWM output of the other 3 trip points can be
+freely chosen. The temperature of all 4 trip points can be freely chosen.
+Additionally, trip point 1 has an hysteresis temperature attached, to
+prevent fast switching between fan on and off.
+
+The chip automatically computes the PWM output value based on the input
+temperature, based on this simple rule: if the temperature value is
+between trip point N and trip point N+1 then the PWM output value is
+the one of trip point N. The automatic control mode is less flexible
+than the manual control mode, but it reacts faster, is more robust and
+doesn't use CPU cycles.
+
+Trip points must be set properly before switching to automatic fan speed
+control mode. The driver will perform basic integrity checks before
+actually switching to automatic control mode.
diff --git a/Documentation/hwmon/lm90 b/Documentation/hwmon/lm90
index 93d8e3d5515..6a03dd4bcc9 100644
--- a/Documentation/hwmon/lm90
+++ b/Documentation/hwmon/lm90
@@ -84,6 +84,10 @@ Supported chips:
     Addresses scanned: I2C 0x4c
     Datasheet: Publicly available at the Maxim website
                http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3500
+  * Winbond/Nuvoton W83L771AWG/ASG
+    Prefix: 'w83l771'
+    Addresses scanned: I2C 0x4c
+    Datasheet: Not publicly available, can be requested from Nuvoton
 
 
 Author: Jean Delvare <khali@linux-fr.org>
@@ -147,6 +151,12 @@ MAX6680 and MAX6681:
   * Selectable address
   * Remote sensor type selection
 
+W83L771AWG/ASG
+  * The AWG and ASG variants only differ in package format.
+  * Filter and alert configuration register at 0xBF
+  * Diode ideality factor configuration (remote sensor) at 0xE3
+  * Moving average (depending on conversion rate)
+
 All temperature values are given in degrees Celsius. Resolution
 is 1.0 degree for the local temperature, 0.125 degree for the remote
 temperature, except for the MAX6657, MAX6658 and MAX6659 which have a
@@ -163,6 +173,18 @@ The lm90 driver will not update its values more frequently than every
 other second; reading them more often will do no harm, but will return
 'old' values.
 
+SMBus Alert Support
+-------------------
+
+This driver has basic support for SMBus alert. When an alert is received,
+the status register is read and the faulty temperature channel is logged.
+
+The Analog Devices chips (ADM1032 and ADT7461) do not implement the SMBus
+alert protocol properly so additional care is needed: the ALERT output is
+disabled when an alert is received, and is re-enabled only when the alarm
+is gone. Otherwise the chip would block alerts from other chips in the bus
+as long as the alarm is active.
+
 PEC Support
 -----------
 
diff --git a/Documentation/init.txt b/Documentation/init.txt
new file mode 100644
index 00000000000..535ad5e82b9
--- /dev/null
+++ b/Documentation/init.txt
@@ -0,0 +1,49 @@
+Explaining the dreaded "No init found." boot hang message
+=========================================================
+
+OK, so you've got this pretty unintuitive message (currently located
+in init/main.c) and are wondering what the H*** went wrong.
+Some high-level reasons for failure (listed roughly in order of execution)
+to load the init binary are:
+A) Unable to mount root FS
+B) init binary doesn't exist on rootfs
+C) broken console device
+D) binary exists but dependencies not available
+E) binary cannot be loaded
+
+Detailed explanations:
+0) Set "debug" kernel parameter (in bootloader config file or CONFIG_CMDLINE)
+   to get more detailed kernel messages.
+A) make sure you have the correct root FS type
+   (and root= kernel parameter points to the correct partition),
+   required drivers such as storage hardware (such as SCSI or USB!)
+   and filesystem (ext3, jffs2 etc.) are builtin (alternatively as modules,
+   to be pre-loaded by an initrd)
+C) Possibly a conflict in console= setup --> initial console unavailable.
+   E.g. some serial consoles are unreliable due to serial IRQ issues (e.g.
+   missing interrupt-based configuration).
+   Try using a different console= device or e.g. netconsole= .
+D) e.g. required library dependencies of the init binary such as
+   /lib/ld-linux.so.2 missing or broken. Use readelf -d <INIT>|grep NEEDED
+   to find out which libraries are required.
+E) make sure the binary's architecture matches your hardware.
+   E.g. i386 vs. x86_64 mismatch, or trying to load x86 on ARM hardware.
+   In case you tried loading a non-binary file here (shell script?),
+   you should make sure that the script specifies an interpreter in its shebang
+   header line (#!/...) that is fully working (including its library
+   dependencies). And before tackling scripts, better first test a simple
+   non-script binary such as /bin/sh and confirm its successful execution.
+   To find out more, add code to init/main.c to display kernel_execve()s
+   return values.
+
+Please extend this explanation whenever you find new failure causes
+(after all loading the init binary is a CRITICAL and hard transition step
+which needs to be made as painless as possible), then submit patch to LKML.
+Further TODOs:
+- Implement the various run_init_process() invocations via a struct array
+  which can then store the kernel_execve() result value and on failure
+  log it all by iterating over _all_ results (very important usability fix).
+- try to make the implementation itself more helpful in general,
+  e.g. by providing additional error messages at affected places.
+
+Andreas Mohr <andi at lisas period de>
diff --git a/Documentation/input/rotary-encoder.txt b/Documentation/input/rotary-encoder.txt
index 3a6aec40c0b..8b4129de1d2 100644
--- a/Documentation/input/rotary-encoder.txt
+++ b/Documentation/input/rotary-encoder.txt
@@ -75,7 +75,7 @@ and the number of steps or will clamp at the maximum and zero depending on
 the configuration.
 
 Because GPIO to IRQ mapping is platform specific, this information must
-be given in seperately to the driver. See the example below.
+be given in separately to the driver. See the example below.
 
 ---------<snip>---------
 
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 35c9b51d20e..dd5806f4fcc 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -291,6 +291,7 @@ Code  Seq#(hex)	Include File		Comments
 0x92	00-0F	drivers/usb/mon/mon_bin.c
 0x93	60-7F	linux/auto_fs.h
 0x94	all	fs/btrfs/ioctl.h
+0x97	00-7F	fs/ceph/ioctl.h		Ceph file system
 0x99	00-0F				537-Addinboard driver
 					<mailto:buk@buks.ipn.de>
 0xA0	all	linux/sdp/sdp.h		Industrial Device Project
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e0df679c390..23f95eaf7c0 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -201,10 +201,6 @@ and is between 256 and 4096 characters. It is defined in the file
 			acpi_display_output=video
 			See above.
 
-	acpi_early_pdc_eval	[HW,ACPI] Evaluate processor _PDC methods
-				early. Needed on some platforms to properly
-				initialize the EC.
-
 	acpi_irq_balance [HW,ACPI]
 			ACPI will balance active IRQs
 			default in APIC mode
@@ -2844,6 +2840,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			default x2apic cluster mode on platforms
 			supporting x2apic.
 
+	x86_mrst_timer= [X86-32,APBT]
+			Choose timer option for x86 Moorestown MID platform.
+			Two valid options are apbt timer only and lapic timer
+			plus one apbt timer for broadcast timer.
+			x86_mrst_timer=apbt_only | lapic_and_apbt
+
 	xd=		[HW,XT] Original XT pre-IDE (RLL encoded) disks.
 	xd_geo=		See header of drivers/block/xd.c.
 
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index c79ab996dad..3ab2472509c 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -59,37 +59,56 @@ nice to have in other objects.  The C language does not allow for the
 direct expression of inheritance, so other techniques - such as structure
 embedding - must be used.
 
-So, for example, the UIO code has a structure that defines the memory
-region associated with a uio device:
+(As an aside, for those familiar with the kernel linked list implementation,
+this is analogous as to how "list_head" structs are rarely useful on
+their own, but are invariably found embedded in the larger objects of
+interest.)
 
-struct uio_mem {
+So, for example, the UIO code in drivers/uio/uio.c has a structure that
+defines the memory region associated with a uio device:
+
+    struct uio_map {
 	struct kobject kobj;
-	unsigned long addr;
-	unsigned long size;
-	int memtype;
-	void __iomem *internal_addr;
-};
+	struct uio_mem *mem;
+    };
 
-If you have a struct uio_mem structure, finding its embedded kobject is
+If you have a struct uio_map structure, finding its embedded kobject is
 just a matter of using the kobj member.  Code that works with kobjects will
 often have the opposite problem, however: given a struct kobject pointer,
 what is the pointer to the containing structure?  You must avoid tricks
 (such as assuming that the kobject is at the beginning of the structure)
 and, instead, use the container_of() macro, found in <linux/kernel.h>:
 
-	container_of(pointer, type, member)
+    container_of(pointer, type, member)
+
+where:
+
+  * "pointer" is the pointer to the embedded kobject,
+  * "type" is the type of the containing structure, and
+  * "member" is the name of the structure field to which "pointer" points.
+
+The return value from container_of() is a pointer to the corresponding
+container type. So, for example, a pointer "kp" to a struct kobject
+embedded *within* a struct uio_map could be converted to a pointer to the
+*containing* uio_map structure with:
+
+    struct uio_map *u_map = container_of(kp, struct uio_map, kobj);
+
+For convenience, programmers often define a simple macro for "back-casting"
+kobject pointers to the containing type.  Exactly this happens in the
+earlier drivers/uio/uio.c, as you can see here:
+
+    struct uio_map {
+        struct kobject kobj;
+        struct uio_mem *mem;
+    };
 
-where pointer is the pointer to the embedded kobject, type is the type of
-the containing structure, and member is the name of the structure field to
-which pointer points.  The return value from container_of() is a pointer to
-the given type. So, for example, a pointer "kp" to a struct kobject
-embedded within a struct uio_mem could be converted to a pointer to the
-containing uio_mem structure with:
+    #define to_map(map) container_of(map, struct uio_map, kobj)
 
-    struct uio_mem *u_mem = container_of(kp, struct uio_mem, kobj);
+where the macro argument "map" is a pointer to the struct kobject in
+question.  That macro is subsequently invoked with:
 
-Programmers often define a simple macro for "back-casting" kobject pointers
-to the containing type.
+    struct uio_map *map = to_map(kobj);
 
 
 Initialization of kobjects
@@ -266,7 +285,7 @@ kobj_type:
 
     struct kobj_type {
 	    void (*release)(struct kobject *);
-	    struct sysfs_ops	*sysfs_ops;
+	    const struct sysfs_ops *sysfs_ops;
 	    struct attribute	**default_attrs;
     };
 
@@ -387,4 +406,5 @@ called, and the objects in the former circle release each other.
 Example code to copy from
 
 For a more complete example of using ksets and kobjects properly, see the
-sample/kobject/kset-example.c code.
+example programs samples/kobject/{kobject-example.c,kset-example.c},
+which will be built as loadable modules if you select CONFIG_SAMPLE_KOBJECT.
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 053037a1fe6..2f9115c0ae6 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -1,6 +1,7 @@
 Title	: Kernel Probes (Kprobes)
 Authors	: Jim Keniston <jkenisto@us.ibm.com>
-	: Prasanna S Panchamukhi <prasanna@in.ibm.com>
+	: Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
+	: Masami Hiramatsu <mhiramat@redhat.com>
 
 CONTENTS
 
@@ -15,6 +16,7 @@ CONTENTS
 9. Jprobes Example
 10. Kretprobes Example
 Appendix A: The kprobes debugfs interface
+Appendix B: The kprobes sysctl interface
 
 1. Concepts: Kprobes, Jprobes, Return Probes
 
@@ -42,13 +44,13 @@ registration/unregistration of a group of *probes. These functions
 can speed up unregistration process when you have to unregister
 a lot of probes at once.
 
-The next three subsections explain how the different types of
-probes work.  They explain certain things that you'll need to
-know in order to make the best use of Kprobes -- e.g., the
-difference between a pre_handler and a post_handler, and how
-to use the maxactive and nmissed fields of a kretprobe.  But
-if you're in a hurry to start using Kprobes, you can skip ahead
-to section 2.
+The next four subsections explain how the different types of
+probes work and how jump optimization works.  They explain certain
+things that you'll need to know in order to make the best use of
+Kprobes -- e.g., the difference between a pre_handler and
+a post_handler, and how to use the maxactive and nmissed fields of
+a kretprobe.  But if you're in a hurry to start using Kprobes, you
+can skip ahead to section 2.
 
 1.1 How Does a Kprobe Work?
 
@@ -161,13 +163,125 @@ In case probed function is entered but there is no kretprobe_instance
 object available, then in addition to incrementing the nmissed count,
 the user entry_handler invocation is also skipped.
 
+1.4 How Does Jump Optimization Work?
+
+If you configured your kernel with CONFIG_OPTPROBES=y (currently
+this option is supported on x86/x86-64, non-preemptive kernel) and
+the "debug.kprobes_optimization" kernel parameter is set to 1 (see
+sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
+instruction instead of a breakpoint instruction at each probepoint.
+
+1.4.1 Init a Kprobe
+
+When a probe is registered, before attempting this optimization,
+Kprobes inserts an ordinary, breakpoint-based kprobe at the specified
+address. So, even if it's not possible to optimize this particular
+probepoint, there'll be a probe there.
+
+1.4.2 Safety Check
+
+Before optimizing a probe, Kprobes performs the following safety checks:
+
+- Kprobes verifies that the region that will be replaced by the jump
+instruction (the "optimized region") lies entirely within one function.
+(A jump instruction is multiple bytes, and so may overlay multiple
+instructions.)
+
+- Kprobes analyzes the entire function and verifies that there is no
+jump into the optimized region.  Specifically:
+  - the function contains no indirect jump;
+  - the function contains no instruction that causes an exception (since
+  the fixup code triggered by the exception could jump back into the
+  optimized region -- Kprobes checks the exception tables to verify this);
+  and
+  - there is no near jump to the optimized region (other than to the first
+  byte).
+
+- For each instruction in the optimized region, Kprobes verifies that
+the instruction can be executed out of line.
+
+1.4.3 Preparing Detour Buffer
+
+Next, Kprobes prepares a "detour" buffer, which contains the following
+instruction sequence:
+- code to push the CPU's registers (emulating a breakpoint trap)
+- a call to the trampoline code which calls user's probe handlers.
+- code to restore registers
+- the instructions from the optimized region
+- a jump back to the original execution path.
+
+1.4.4 Pre-optimization
+
+After preparing the detour buffer, Kprobes verifies that none of the
+following situations exist:
+- The probe has either a break_handler (i.e., it's a jprobe) or a
+post_handler.
+- Other instructions in the optimized region are probed.
+- The probe is disabled.
+In any of the above cases, Kprobes won't start optimizing the probe.
+Since these are temporary situations, Kprobes tries to start
+optimizing it again if the situation is changed.
+
+If the kprobe can be optimized, Kprobes enqueues the kprobe to an
+optimizing list, and kicks the kprobe-optimizer workqueue to optimize
+it.  If the to-be-optimized probepoint is hit before being optimized,
+Kprobes returns control to the original instruction path by setting
+the CPU's instruction pointer to the copied code in the detour buffer
+-- thus at least avoiding the single-step.
+
+1.4.5 Optimization
+
+The Kprobe-optimizer doesn't insert the jump instruction immediately;
+rather, it calls synchronize_sched() for safety first, because it's
+possible for a CPU to be interrupted in the middle of executing the
+optimized region(*).  As you know, synchronize_sched() can ensure
+that all interruptions that were active when synchronize_sched()
+was called are done, but only if CONFIG_PREEMPT=n.  So, this version
+of kprobe optimization supports only kernels with CONFIG_PREEMPT=n.(**)
+
+After that, the Kprobe-optimizer calls stop_machine() to replace
+the optimized region with a jump instruction to the detour buffer,
+using text_poke_smp().
+
+1.4.6 Unoptimization
+
+When an optimized kprobe is unregistered, disabled, or blocked by
+another kprobe, it will be unoptimized.  If this happens before
+the optimization is complete, the kprobe is just dequeued from the
+optimized list.  If the optimization has been done, the jump is
+replaced with the original code (except for an int3 breakpoint in
+the first byte) by using text_poke_smp().
+
+(*)Please imagine that the 2nd instruction is interrupted and then
+the optimizer replaces the 2nd instruction with the jump *address*
+while the interrupt handler is running. When the interrupt
+returns to original address, there is no valid instruction,
+and it causes an unexpected result.
+
+(**)This optimization-safety checking may be replaced with the
+stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y
+kernel.
+
+NOTE for geeks:
+The jump optimization changes the kprobe's pre_handler behavior.
+Without optimization, the pre_handler can change the kernel's execution
+path by changing regs->ip and returning 1.  However, when the probe
+is optimized, that modification is ignored.  Thus, if you want to
+tweak the kernel's execution path, you need to suppress optimization,
+using one of the following techniques:
+- Specify an empty function for the kprobe's post_handler or break_handler.
+ or
+- Config CONFIG_OPTPROBES=n.
+ or
+- Execute 'sysctl -w debug.kprobes_optimization=n'
+
 2. Architectures Supported
 
 Kprobes, jprobes, and return probes are implemented on the following
 architectures:
 
-- i386
-- x86_64 (AMD-64, EM64T)
+- i386 (Supports jump optimization)
+- x86_64 (AMD-64, EM64T) (Supports jump optimization)
 - ppc64
 - ia64 (Does not support probes on instruction slot1.)
 - sparc64 (Return probes not yet implemented.)
@@ -193,6 +307,10 @@ it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
 so you can use "objdump -d -l vmlinux" to see the source-to-object
 code mapping.
 
+If you want to reduce probing overhead, set "Kprobes jump optimization
+support" (CONFIG_OPTPROBES) to "y". You can find this option under the
+"Kprobes" line.
+
 4. API Reference
 
 The Kprobes API includes a "register" function and an "unregister"
@@ -389,7 +507,10 @@ the probe which has been registered.
 
 Kprobes allows multiple probes at the same address.  Currently,
 however, there cannot be multiple jprobes on the same function at
-the same time.
+the same time.  Also, a probepoint for which there is a jprobe or
+a post_handler cannot be optimized.  So if you install a jprobe,
+or a kprobe with a post_handler, at an optimized probepoint, the
+probepoint will be unoptimized automatically.
 
 In general, you can install a probe anywhere in the kernel.
 In particular, you can probe interrupt handlers.  Known exceptions
@@ -453,6 +574,38 @@ reason, Kprobes doesn't support return probes (or kprobes or jprobes)
 on the x86_64 version of __switch_to(); the registration functions
 return -EINVAL.
 
+On x86/x86-64, since the Jump Optimization of Kprobes modifies
+instructions widely, there are some limitations to optimization. To
+explain it, we introduce some terminology. Imagine a 3-instruction
+sequence consisting of a two 2-byte instructions and one 3-byte
+instruction.
+
+        IA
+         |
+[-2][-1][0][1][2][3][4][5][6][7]
+        [ins1][ins2][  ins3 ]
+	[<-     DCR       ->]
+	   [<- JTPR ->]
+
+ins1: 1st Instruction
+ins2: 2nd Instruction
+ins3: 3rd Instruction
+IA:  Insertion Address
+JTPR: Jump Target Prohibition Region
+DCR: Detoured Code Region
+
+The instructions in DCR are copied to the out-of-line buffer
+of the kprobe, because the bytes in DCR are replaced by
+a 5-byte jump instruction. So there are several limitations.
+
+a) The instructions in DCR must be relocatable.
+b) The instructions in DCR must not include a call instruction.
+c) JTPR must not be targeted by any jump or call instruction.
+d) DCR must not straddle the border betweeen functions.
+
+Anyway, these limitations are checked by the in-kernel instruction
+decoder, so you don't need to worry about that.
+
 6. Probe Overhead
 
 On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
@@ -476,6 +629,19 @@ k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07
 ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
 k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
 
+6.1 Optimized Probe Overhead
+
+Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to
+process. Here are sample overhead figures (in usec) for x86 architectures.
+k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,
+r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.
+
+i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33
+
+x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30
+
 7. TODO
 
 a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
@@ -523,7 +689,8 @@ is also specified. Following columns show probe status. If the probe is on
 a virtual address that is no longer valid (module init sections, module
 virtual addresses that correspond to modules that've been unloaded),
 such probes are marked with [GONE]. If the probe is temporarily disabled,
-such probes are marked with [DISABLED].
+such probes are marked with [DISABLED]. If the probe is optimized, it is
+marked with [OPTIMIZED].
 
 /sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
 
@@ -533,3 +700,19 @@ registered probes will be disarmed, till such time a "1" is echoed to this
 file. Note that this knob just disarms and arms all kprobes and doesn't
 change each probe's disabling state. This means that disabled kprobes (marked
 [DISABLED]) will be not enabled if you turn ON all kprobes by this knob.
+
+
+Appendix B: The kprobes sysctl interface
+
+/proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF.
+
+When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides
+a knob to globally and forcibly turn jump optimization (see section
+1.4) ON or OFF. By default, jump optimization is allowed (ON).
+If you echo "0" to this file or set "debug.kprobes_optimization" to
+0 via sysctl, all optimized probes will be unoptimized, and any new
+probes registered after that will not be optimized.  Note that this
+knob *changes* the optimized state. This means that optimized probes
+(marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be
+removed). If the knob is turned on, they will be optimized again.
+
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index 2811e452f75..c6416a39816 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -23,12 +23,12 @@ of a virtual machine.  The ioctls belong to three classes
    Only run vcpu ioctls from the same thread that was used to create the
    vcpu.
 
-2. File descritpors
+2. File descriptors
 
 The kvm API is centered around file descriptors.  An initial
 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
 can be used to issue system ioctls.  A KVM_CREATE_VM ioctl on this
-handle will create a VM file descripror which can be used to issue VM
+handle will create a VM file descriptor which can be used to issue VM
 ioctls.  A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
 and return a file descriptor pointing to it.  Finally, ioctls on a vcpu
 fd can be used to control the vcpu, including the important task of
@@ -643,7 +643,7 @@ Type: vm ioctl
 Parameters: struct kvm_clock_data (in)
 Returns: 0 on success, -1 on error
 
-Sets the current timestamp of kvmclock to the valued specific in its parameter.
+Sets the current timestamp of kvmclock to the value specified in its parameter.
 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
@@ -795,11 +795,11 @@ Unused.
 			__u64 data_offset; /* relative to kvm_run start */
 		} io;
 
-If exit_reason is KVM_EXIT_IO_IN or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_IO, then the vcpu has
 executed a port I/O instruction which could not be satisfied by kvm.
 data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
 where kvm expects application code to place the data for the next
-KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a patcked array.
+KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.
 
 		struct {
 			struct kvm_debug_exit_arch arch;
@@ -815,7 +815,7 @@ Unused.
 			__u8  is_write;
 		} mmio;
 
-If exit_reason is KVM_EXIT_MMIO or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_MMIO, then the vcpu has
 executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.
diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX
index ee5692b26dd..fa688538e75 100644
--- a/Documentation/laptops/00-INDEX
+++ b/Documentation/laptops/00-INDEX
@@ -2,6 +2,12 @@
 	- This file
 acer-wmi.txt
 	- information on the Acer Laptop WMI Extras driver.
+asus-laptop.txt
+	- information on the Asus Laptop Extras driver.
+disk-shock-protection.txt
+	- information on hard disk shock protection.
+dslm.c
+	- Simple Disk Sleep Monitor program
 laptop-mode.txt
 	- how to conserve battery power using laptop-mode.
 sony-laptop.txt
diff --git a/Documentation/laptops/Makefile b/Documentation/laptops/Makefile
new file mode 100644
index 00000000000..5cb144af3c0
--- /dev/null
+++ b/Documentation/laptops/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := dslm
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/laptops/dslm.c b/Documentation/laptops/dslm.c
new file mode 100644
index 00000000000..72ff290c5fc
--- /dev/null
+++ b/Documentation/laptops/dslm.c
@@ -0,0 +1,166 @@
+/*
+ * dslm.c
+ * Simple Disk Sleep Monitor
+ *  by Bartek Kania
+ * Licenced under the GPL
+ */
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <time.h>
+#include <string.h>
+#include <signal.h>
+#include <sys/ioctl.h>
+#include <linux/hdreg.h>
+
+#ifdef DEBUG
+#define D(x) x
+#else
+#define D(x)
+#endif
+
+int endit = 0;
+
+/* Check if the disk is in powersave-mode
+ * Most of the code is stolen from hdparm.
+ * 1 = active, 0 = standby/sleep, -1 = unknown */
+static int check_powermode(int fd)
+{
+    unsigned char args[4] = {WIN_CHECKPOWERMODE1,0,0,0};
+    int state;
+
+    if (ioctl(fd, HDIO_DRIVE_CMD, &args)
+	&& (args[0] = WIN_CHECKPOWERMODE2) /* try again with 0x98 */
+	&& ioctl(fd, HDIO_DRIVE_CMD, &args)) {
+	if (errno != EIO || args[0] != 0 || args[1] != 0) {
+	    state = -1; /* "unknown"; */
+	} else
+	    state = 0; /* "sleeping"; */
+    } else {
+	state = (args[2] == 255) ? 1 : 0;
+    }
+    D(printf(" drive state is:  %d\n", state));
+
+    return state;
+}
+
+static char *state_name(int i)
+{
+    if (i == -1) return "unknown";
+    if (i == 0) return "sleeping";
+    if (i == 1) return "active";
+
+    return "internal error";
+}
+
+static char *myctime(time_t time)
+{
+    char *ts = ctime(&time);
+    ts[strlen(ts) - 1] = 0;
+
+    return ts;
+}
+
+static void measure(int fd)
+{
+    time_t start_time;
+    int last_state;
+    time_t last_time;
+    int curr_state;
+    time_t curr_time = 0;
+    time_t time_diff;
+    time_t active_time = 0;
+    time_t sleep_time = 0;
+    time_t unknown_time = 0;
+    time_t total_time = 0;
+    int changes = 0;
+    float tmp;
+
+    printf("Starting measurements\n");
+
+    last_state = check_powermode(fd);
+    start_time = last_time = time(0);
+    printf("  System is in state %s\n\n", state_name(last_state));
+
+    while(!endit) {
+	sleep(1);
+	curr_state = check_powermode(fd);
+
+	if (curr_state != last_state || endit) {
+	    changes++;
+	    curr_time = time(0);
+	    time_diff = curr_time - last_time;
+
+	    if (last_state == 1) active_time += time_diff;
+	    else if (last_state == 0) sleep_time += time_diff;
+	    else unknown_time += time_diff;
+
+	    last_state = curr_state;
+	    last_time = curr_time;
+
+	    printf("%s: State-change to %s\n", myctime(curr_time),
+		   state_name(curr_state));
+	}
+    }
+    changes--; /* Compensate for SIGINT */
+
+    total_time = time(0) - start_time;
+    printf("\nTotal running time:  %lus\n", curr_time - start_time);
+    printf(" State changed %d times\n", changes);
+
+    tmp = (float)sleep_time / (float)total_time * 100;
+    printf(" Time in sleep state:   %lus (%.2f%%)\n", sleep_time, tmp);
+    tmp = (float)active_time / (float)total_time * 100;
+    printf(" Time in active state:  %lus (%.2f%%)\n", active_time, tmp);
+    tmp = (float)unknown_time / (float)total_time * 100;
+    printf(" Time in unknown state: %lus (%.2f%%)\n", unknown_time, tmp);
+}
+
+static void ender(int s)
+{
+    endit = 1;
+}
+
+static void usage(void)
+{
+    puts("usage: dslm [-w <time>] <disk>");
+    exit(0);
+}
+
+int main(int argc, char **argv)
+{
+    int fd;
+    char *disk = 0;
+    int settle_time = 60;
+
+    /* Parse the simple command-line */
+    if (argc == 2)
+	disk = argv[1];
+    else if (argc == 4) {
+	settle_time = atoi(argv[2]);
+	disk = argv[3];
+    } else
+	usage();
+
+    if (!(fd = open(disk, O_RDONLY|O_NONBLOCK))) {
+	printf("Can't open %s, because: %s\n", disk, strerror(errno));
+	exit(-1);
+    }
+
+    if (settle_time) {
+	printf("Waiting %d seconds for the system to settle down to "
+	       "'normal'\n", settle_time);
+	sleep(settle_time);
+    } else
+	puts("Not waiting for system to settle down");
+
+    signal(SIGINT, ender);
+
+    measure(fd);
+
+    close(fd);
+
+    return 0;
+}
diff --git a/Documentation/laptops/laptop-mode.txt b/Documentation/laptops/laptop-mode.txt
index eeedee11c8c..2c3c3509302 100644
--- a/Documentation/laptops/laptop-mode.txt
+++ b/Documentation/laptops/laptop-mode.txt
@@ -779,172 +779,4 @@ Monitoring tool
 ---------------
 
 Bartek Kania submitted this, it can be used to measure how much time your disk
-spends spun up/down.
-
----------------------------dslm.c BEGIN-----------------------------------------
-/*
- * Simple Disk Sleep Monitor
- *  by Bartek Kania
- * Licenced under the GPL
- */
-#include <unistd.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <fcntl.h>
-#include <errno.h>
-#include <time.h>
-#include <string.h>
-#include <signal.h>
-#include <sys/ioctl.h>
-#include <linux/hdreg.h>
-
-#ifdef DEBUG
-#define D(x) x
-#else
-#define D(x)
-#endif
-
-int endit = 0;
-
-/* Check if the disk is in powersave-mode
- * Most of the code is stolen from hdparm.
- * 1 = active, 0 = standby/sleep, -1 = unknown */
-int check_powermode(int fd)
-{
-    unsigned char args[4] = {WIN_CHECKPOWERMODE1,0,0,0};
-    int state;
-
-    if (ioctl(fd, HDIO_DRIVE_CMD, &args)
-	&& (args[0] = WIN_CHECKPOWERMODE2) /* try again with 0x98 */
-	&& ioctl(fd, HDIO_DRIVE_CMD, &args)) {
-	if (errno != EIO || args[0] != 0 || args[1] != 0) {
-	    state = -1; /* "unknown"; */
-	} else
-	    state = 0; /* "sleeping"; */
-    } else {
-	state = (args[2] == 255) ? 1 : 0;
-    }
-    D(printf(" drive state is:  %d\n", state));
-
-    return state;
-}
-
-char *state_name(int i)
-{
-    if (i == -1) return "unknown";
-    if (i == 0) return "sleeping";
-    if (i == 1) return "active";
-
-    return "internal error";
-}
-
-char *myctime(time_t time)
-{
-    char *ts = ctime(&time);
-    ts[strlen(ts) - 1] = 0;
-
-    return ts;
-}
-
-void measure(int fd)
-{
-    time_t start_time;
-    int last_state;
-    time_t last_time;
-    int curr_state;
-    time_t curr_time = 0;
-    time_t time_diff;
-    time_t active_time = 0;
-    time_t sleep_time = 0;
-    time_t unknown_time = 0;
-    time_t total_time = 0;
-    int changes = 0;
-    float tmp;
-
-    printf("Starting measurements\n");
-
-    last_state = check_powermode(fd);
-    start_time = last_time = time(0);
-    printf("  System is in state %s\n\n", state_name(last_state));
-
-    while(!endit) {
-	sleep(1);
-	curr_state = check_powermode(fd);
-
-	if (curr_state != last_state || endit) {
-	    changes++;
-	    curr_time = time(0);
-	    time_diff = curr_time - last_time;
-
-	    if (last_state == 1) active_time += time_diff;
-	    else if (last_state == 0) sleep_time += time_diff;
-	    else unknown_time += time_diff;
-
-	    last_state = curr_state;
-	    last_time = curr_time;
-
-	    printf("%s: State-change to %s\n", myctime(curr_time),
-		   state_name(curr_state));
-	}
-    }
-    changes--; /* Compensate for SIGINT */
-
-    total_time = time(0) - start_time;
-    printf("\nTotal running time:  %lus\n", curr_time - start_time);
-    printf(" State changed %d times\n", changes);
-
-    tmp = (float)sleep_time / (float)total_time * 100;
-    printf(" Time in sleep state:   %lus (%.2f%%)\n", sleep_time, tmp);
-    tmp = (float)active_time / (float)total_time * 100;
-    printf(" Time in active state:  %lus (%.2f%%)\n", active_time, tmp);
-    tmp = (float)unknown_time / (float)total_time * 100;
-    printf(" Time in unknown state: %lus (%.2f%%)\n", unknown_time, tmp);
-}
-
-void ender(int s)
-{
-    endit = 1;
-}
-
-void usage()
-{
-    puts("usage: dslm [-w <time>] <disk>");
-    exit(0);
-}
-
-int main(int argc, char **argv)
-{
-    int fd;
-    char *disk = 0;
-    int settle_time = 60;
-
-    /* Parse the simple command-line */
-    if (argc == 2)
-	disk = argv[1];
-    else if (argc == 4) {
-	settle_time = atoi(argv[2]);
-	disk = argv[3];
-    } else
-	usage();
-
-    if (!(fd = open(disk, O_RDONLY|O_NONBLOCK))) {
-	printf("Can't open %s, because: %s\n", disk, strerror(errno));
-	exit(-1);
-    }
-
-    if (settle_time) {
-	printf("Waiting %d seconds for the system to settle down to "
-	       "'normal'\n", settle_time);
-	sleep(settle_time);
-    } else
-	puts("Not waiting for system to settle down");
-
-    signal(SIGINT, ender);
-
-    measure(fd);
-
-    close(fd);
-
-    return 0;
-}
----------------------------dslm.c END-------------------------------------------
+spends spun up/down.  See Documentation/laptops/dslm.c
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 7f5809eddee..631ad2f1b22 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -3,6 +3,7 @@
 			 ============================
 
 By: David Howells <dhowells@redhat.com>
+    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
 Contents:
 
@@ -60,6 +61,10 @@ Contents:
 
      - And then there's the Alpha.
 
+ (*) Example uses.
+
+     - Circular buffers.
+
  (*) References.
 
 
@@ -2226,6 +2231,21 @@ The Alpha defines the Linux kernel's memory barrier model.
 See the subsection on "Cache Coherency" above.
 
 
+============
+EXAMPLE USES
+============
+
+CIRCULAR BUFFERS
+----------------
+
+Memory barriers can be used to implement circular buffering without the need
+of a lock to serialise the producer with the consumer.  See:
+
+	Documentation/circular-buffers.txt
+
+for details.
+
+
 ==========
 REFERENCES
 ==========
diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile
index 6d8af1ac56c..5aba7a33aee 100644
--- a/Documentation/networking/Makefile
+++ b/Documentation/networking/Makefile
@@ -6,3 +6,5 @@ hostprogs-y := ifenslave
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
+
+obj-m := timestamping/
diff --git a/Documentation/networking/skfp.txt b/Documentation/networking/skfp.txt
index abfddf81e34..203ec66c9fb 100644
--- a/Documentation/networking/skfp.txt
+++ b/Documentation/networking/skfp.txt
@@ -68,7 +68,7 @@ Compaq adapters (not tested):
 =======================
 
 From v2.01 on, the driver is integrated in the linux kernel sources.
-Therefor, the installation is the same as for any other adapter
+Therefore, the installation is the same as for any other adapter
 supported by the kernel.
 Refer to the manual of your distribution about the installation
 of network adapters.
diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile
index 2a1489fdc03..e79973443e9 100644
--- a/Documentation/networking/timestamping/Makefile
+++ b/Documentation/networking/timestamping/Makefile
@@ -1,6 +1,13 @@
-CPPFLAGS = -I../../../include
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
 
-timestamping: timestamping.c
+# List of programs to build
+hostprogs-y := timestamping
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+
+HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include
 
 clean:
 	rm -f timestamping
diff --git a/Documentation/networking/timestamping/timestamping.c b/Documentation/networking/timestamping/timestamping.c
index a7936fe8444..8ba82bfe6a3 100644
--- a/Documentation/networking/timestamping/timestamping.c
+++ b/Documentation/networking/timestamping/timestamping.c
@@ -41,9 +41,9 @@
 #include <arpa/inet.h>
 #include <net/if.h>
 
-#include "asm/types.h"
-#include "linux/net_tstamp.h"
-#include "linux/errqueue.h"
+#include <asm/types.h>
+#include <linux/net_tstamp.h>
+#include <linux/errqueue.h>
 
 #ifndef SO_TIMESTAMPING
 # define SO_TIMESTAMPING         37
@@ -164,7 +164,7 @@ static void printpacket(struct msghdr *msg, int res,
 
 	gettimeofday(&now, 0);
 
-	printf("%ld.%06ld: received %s data, %d bytes from %s, %d bytes control messages\n",
+	printf("%ld.%06ld: received %s data, %d bytes from %s, %zu bytes control messages\n",
 	       (long)now.tv_sec, (long)now.tv_usec,
 	       (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular",
 	       res,
@@ -173,7 +173,7 @@ static void printpacket(struct msghdr *msg, int res,
 	for (cmsg = CMSG_FIRSTHDR(msg);
 	     cmsg;
 	     cmsg = CMSG_NXTHDR(msg, cmsg)) {
-		printf("   cmsg len %d: ", cmsg->cmsg_len);
+		printf("   cmsg len %zu: ", cmsg->cmsg_len);
 		switch (cmsg->cmsg_level) {
 		case SOL_SOCKET:
 			printf("SOL_SOCKET ");
@@ -370,7 +370,7 @@ int main(int argc, char **argv)
 	}
 
 	sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP);
-	if (socket < 0)
+	if (sock < 0)
 		bail("socket");
 
 	memset(&device, 0, sizeof(device));
diff --git a/Documentation/pnp.txt b/Documentation/pnp.txt
index a327db67782..763e4659bf1 100644
--- a/Documentation/pnp.txt
+++ b/Documentation/pnp.txt
@@ -57,7 +57,7 @@ PC standard floppy disk controller
 # cat resources
 DISABLED
 
-- Notice the string "DISABLED".  THis means the device is not active.
+- Notice the string "DISABLED".  This means the device is not active.
 
 3.) check the device's possible configurations (optional)
 # cat options
@@ -139,7 +139,7 @@ Plug and Play but it is planned to be in the near future.
 
 Requirements for a Linux PnP protocol:
 1.) the protocol must use EISA IDs
-2.) the protocol must inform the PnP Layer of a devices current configuration
+2.) the protocol must inform the PnP Layer of a device's current configuration
 - the ability to set resources is optional but preferred.
 
 The following are PnP protocol related functions:
@@ -158,7 +158,7 @@ pnp_remove_device
 - automatically will free mem used by the device and related structures
 
 pnp_add_id
-- adds a EISA ID to the list of supported IDs for the specified device
+- adds an EISA ID to the list of supported IDs for the specified device
 
 For more information consult the source of a protocol such as
 /drivers/pnp/pnpbios/core.c.
@@ -167,7 +167,7 @@ For more information consult the source of a protocol such as
 
 Linux Plug and Play Drivers
 ---------------------------
-	This section contains information for linux PnP driver developers.
+	This section contains information for Linux PnP driver developers.
 
 The New Way
 ...........
@@ -235,11 +235,10 @@ static int __init serial8250_pnp_init(void)
 The Old Way
 ...........
 
-a series of compatibility functions have been created to make it easy to convert 
-
+A series of compatibility functions have been created to make it easy to convert
 ISAPNP drivers.  They should serve as a temporary solution only.
 
-they are as follows:
+They are as follows:
 
 struct pnp_card *pnp_find_card(unsigned short vendor,
 				 unsigned short device,
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 356fd86f4ea..55b859b3bc7 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -224,6 +224,12 @@ defined in include/linux/pm.h:
       RPM_SUSPENDED, which means that each device is initially regarded by the
       PM core as 'suspended', regardless of its real hardware status
 
+  unsigned int runtime_auto;
+    - if set, indicates that the user space has allowed the device driver to
+      power manage the device at run time via the /sys/devices/.../power/control
+      interface; it may only be modified with the help of the pm_runtime_allow()
+      and pm_runtime_forbid() helper functions
+
 All of the above fields are members of the 'power' member of 'struct device'.
 
 4. Run-time PM Device Helper Functions
@@ -250,7 +256,7 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       to suspend the device again in future
 
   int pm_runtime_resume(struct device *dev);
-    - execute the subsystem-leve resume callback for the device; returns 0 on
+    - execute the subsystem-level resume callback for the device; returns 0 on
       success, 1 if the device's run-time PM status was already 'active' or
       error code on failure, where -EAGAIN means it may be safe to attempt to
       resume the device again in future, but 'power.runtime_error' should be
@@ -329,6 +335,20 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       'power.runtime_error' is set or 'power.disable_depth' is greater than
       zero)
 
+  bool pm_runtime_suspended(struct device *dev);
+    - return true if the device's runtime PM status is 'suspended', or false
+      otherwise
+
+  void pm_runtime_allow(struct device *dev);
+    - set the power.runtime_auto flag for the device and decrease its usage
+      counter (used by the /sys/devices/.../power/control interface to
+      effectively allow the device to be power managed at run time)
+
+  void pm_runtime_forbid(struct device *dev);
+    - unset the power.runtime_auto flag for the device and increase its usage
+      counter (used by the /sys/devices/.../power/control interface to
+      effectively prevent the device from being power managed at run time)
+
 It is safe to execute the following helper functions from interrupt context:
 
 pm_request_idle()
@@ -382,6 +402,18 @@ may be desirable to suspend the device as soon as ->probe() or ->remove() has
 finished, so the PM core uses pm_runtime_idle_sync() to invoke the
 subsystem-level idle callback for the device at that time.
 
+The user space can effectively disallow the driver of the device to power manage
+it at run time by changing the value of its /sys/devices/.../power/control
+attribute to "on", which causes pm_runtime_forbid() to be called.  In principle,
+this mechanism may also be used by the driver to effectively turn off the
+run-time power management of the device until the user space turns it on.
+Namely, during the initialization the driver can make sure that the run-time PM
+status of the device is 'active' and call pm_runtime_forbid().  It should be
+noted, however, that if the user space has already intentionally changed the
+value of /sys/devices/.../power/control to "auto" to allow the driver to power
+manage the device at run time, the driver may confuse it by using
+pm_runtime_forbid() this way.
+
 6. Run-time PM and System Sleep
 
 Run-time PM and system sleep (i.e., system suspend and hibernation, also known
@@ -431,3 +463,64 @@ The PM core always increments the run-time usage counter before calling the
 ->prepare() callback and decrements it after calling the ->complete() callback.
 Hence disabling run-time PM temporarily like this will not cause any run-time
 suspend callbacks to be lost.
+
+7. Generic subsystem callbacks
+
+Subsystems may wish to conserve code space by using the set of generic power
+management callbacks provided by the PM core, defined in
+driver/base/power/generic_ops.c:
+
+  int pm_generic_runtime_idle(struct device *dev);
+    - invoke the ->runtime_idle() callback provided by the driver of this
+      device, if defined, and call pm_runtime_suspend() for this device if the
+      return value is 0 or the callback is not defined
+
+  int pm_generic_runtime_suspend(struct device *dev);
+    - invoke the ->runtime_suspend() callback provided by the driver of this
+      device and return its result, or return -EINVAL if not defined
+
+  int pm_generic_runtime_resume(struct device *dev);
+    - invoke the ->runtime_resume() callback provided by the driver of this
+      device and return its result, or return -EINVAL if not defined
+
+  int pm_generic_suspend(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->suspend()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_resume(struct device *dev);
+    - invoke the ->resume() callback provided by the driver of this device and,
+      if successful, change the device's runtime PM status to 'active'
+
+  int pm_generic_freeze(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->freeze()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_thaw(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->thaw()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_poweroff(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->poweroff()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_restore(struct device *dev);
+    - invoke the ->restore() callback provided by the driver of this device and,
+      if successful, change the device's runtime PM status to 'active'
+
+These functions can be assigned to the ->runtime_idle(), ->runtime_suspend(),
+->runtime_resume(), ->suspend(), ->resume(), ->freeze(), ->thaw(), ->poweroff(),
+or ->restore() callback pointers in the subsystem-level dev_pm_ops structures.
+
+If a subsystem wishes to use all of them at the same time, it can simply assign
+the GENERIC_SUBSYS_PM_OPS macro, defined in include/linux/pm.h, to its
+dev_pm_ops structure pointer.
+
+Device drivers that wish to use the same function as a system suspend, freeze,
+poweroff and run-time suspend callback, and similarly for system resume, thaw,
+restore, and run-time resume, can achieve this with the help of the
+UNIVERSAL_DEV_PM_OPS macro defined in include/linux/pm.h (possibly setting its
+last argument to NULL).
diff --git a/Documentation/powerpc/dts-bindings/fsl/dma.txt b/Documentation/powerpc/dts-bindings/fsl/dma.txt
index 0732cdd05ba..2a4b4bce611 100644
--- a/Documentation/powerpc/dts-bindings/fsl/dma.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/dma.txt
@@ -44,21 +44,29 @@ Example:
 			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
 			cell-index = <0>;
 			reg = <0 0x80>;
+			interrupt-parent = <&ipic>;
+			interrupts = <71 8>;
 		};
 		dma-channel@80 {
 			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
 			cell-index = <1>;
 			reg = <0x80 0x80>;
+			interrupt-parent = <&ipic>;
+			interrupts = <71 8>;
 		};
 		dma-channel@100 {
 			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
 			cell-index = <2>;
 			reg = <0x100 0x80>;
+			interrupt-parent = <&ipic>;
+			interrupts = <71 8>;
 		};
 		dma-channel@180 {
 			compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
 			cell-index = <3>;
 			reg = <0x180 0x80>;
+			interrupt-parent = <&ipic>;
+			interrupts = <71 8>;
 		};
 	};
 
diff --git a/Documentation/powerpc/dts-bindings/fsl/i2c.txt b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
index b6d2e21474f..50da2031058 100644
--- a/Documentation/powerpc/dts-bindings/fsl/i2c.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
@@ -2,15 +2,14 @@
 
 Required properties :
 
- - device_type : Should be "i2c"
  - reg : Offset and length of the register set for the device
+ - compatible : should be "fsl,CHIP-i2c" where CHIP is the name of a
+   compatible processor, e.g. mpc8313, mpc8543, mpc8544, mpc5121,
+   mpc5200 or mpc5200b. For the mpc5121, an additional node
+   "fsl,mpc5121-i2c-ctrl" is required as shown in the example below.
 
 Recommended properties :
 
- - compatible : compatibility list with 2 entries, the first should
-   be "fsl,CHIP-i2c" where CHIP is the name of a compatible processor,
-   e.g. mpc8313, mpc8543, mpc8544, mpc5200 or mpc5200b. The second one
-   should be "fsl-i2c".
  - interrupts : <a b> where a is the interrupt number and b is a
    field that represents an encoding of the sense and level
    information for the interrupt.  This should be encoded based on
@@ -24,25 +23,40 @@ Recommended properties :
 
 Examples :
 
+	/* MPC5121 based board */
+	i2c@1740 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "fsl,mpc5121-i2c", "fsl-i2c";
+		reg = <0x1740 0x20>;
+		interrupts = <11 0x8>;
+		interrupt-parent = <&ipic>;
+		clock-frequency = <100000>;
+	};
+
+	i2ccontrol@1760 {
+		compatible = "fsl,mpc5121-i2c-ctrl";
+		reg = <0x1760 0x8>;
+	};
+
+	/* MPC5200B based board */
 	i2c@3d00 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "fsl,mpc5200b-i2c","fsl,mpc5200-i2c","fsl-i2c";
-		cell-index = <0>;
 		reg = <0x3d00 0x40>;
 		interrupts = <2 15 0>;
 		interrupt-parent = <&mpc5200_pic>;
 		fsl,preserve-clocking;
 	};
 
+	/* MPC8544 base board */
 	i2c@3100 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		cell-index = <1>;
 		compatible = "fsl,mpc8544-i2c", "fsl-i2c";
 		reg = <0x3100 0x100>;
 		interrupts = <43 2>;
 		interrupt-parent = <&mpic>;
 		clock-frequency = <400000>;
 	};
-
diff --git a/Documentation/s390/kvm.txt b/Documentation/s390/kvm.txt
index 6f5ceb0f09f..85f3280d7ef 100644
--- a/Documentation/s390/kvm.txt
+++ b/Documentation/s390/kvm.txt
@@ -102,7 +102,7 @@ args:		unsigned long
 see also:	include/linux/kvm.h
 This ioctl stores the state of the cpu at the guest real address given as
 argument, unless one of the following values defined in include/linux/kvm.h
-is given as arguement:
+is given as argument:
 KVM_S390_STORE_STATUS_NOADDR - the CPU stores its status to the save area in
 absolute lowcore as defined by the principles of operation
 KVM_S390_STORE_STATUS_PREFIXED - the CPU stores its status to the save area in
diff --git a/Documentation/scsi/ChangeLog.lpfc b/Documentation/scsi/ChangeLog.lpfc
index ff19a52fe00..2ffc1148eb9 100644
--- a/Documentation/scsi/ChangeLog.lpfc
+++ b/Documentation/scsi/ChangeLog.lpfc
@@ -989,8 +989,8 @@ Changes from 20040709 to 20040716
 	* Remove redundant port_cmp != 2 check in if
 	  (!port_cmp) { .... if (port_cmp != 2).... }
 	* Clock changes: removed struct clk_data and timerList.
-	* Clock changes: seperate nodev_tmo and els_retry_delay into 2
-	  seperate timers and convert to 1 argument changed
+	* Clock changes: separate nodev_tmo and els_retry_delay into 2
+	  separate timers and convert to 1 argument changed
 	  LPFC_NODE_FARP_PEND_t to struct lpfc_node_farp_pend convert
 	  ipfarp_tmo to 1 argument convert target struct tmofunc and
 	  rtplunfunc to 1 argument * cr_count, cr_delay and
@@ -1514,7 +1514,7 @@ Changes from 20040402 to 20040409
 	* Remove unused elxclock declaration in elx_sli.h.
 	* Since everywhere IOCB_ENTRY is used, the return value is cast,
 	  move the cast into the macro.
-	* Split ioctls out into seperate files
+	* Split ioctls out into separate files
 
 Changes from 20040326 to 20040402
 
@@ -1534,7 +1534,7 @@ Changes from 20040326 to 20040402
 	* Unused variable cleanup
 	* Use Linux list macros for DMABUF_t
 	* Break up ioctls into 3 sections, dfc, util, hbaapi
-	  rearranged code so this could be easily seperated into a
+	  rearranged code so this could be easily separated into a
 	  differnet module later All 3 are currently turned on by
 	  defines in lpfc_ioctl.c LPFC_DFC_IOCTL, LPFC_UTIL_IOCTL,
 	  LPFC_HBAAPI_IOCTL
@@ -1551,7 +1551,7 @@ Changes from 20040326 to 20040402
 	  started by lpfc_online().  lpfc_offline() only stopped
 	  els_timeout routine.  It now stops all timeout routines
 	  associated with that hba.
-	* Replace seperate next and prev pointers in struct
+	* Replace separate next and prev pointers in struct
 	  lpfc_bindlist with list_head type.  In elxHBA_t, replace
 	  fc_nlpbind_start and _end with fc_nlpbind_list and use
 	  list_head macros to access it.
diff --git a/Documentation/serial/tty.txt b/Documentation/serial/tty.txt
index 5e5349a4fcd..7c900507279 100644
--- a/Documentation/serial/tty.txt
+++ b/Documentation/serial/tty.txt
@@ -105,6 +105,10 @@ write_wakeup()	-	May be called at any point between open and close.
 			is permitted to call the driver write method from
 			this function. In such a situation defer it.
 
+dcd_change()	-	Report to the tty line the current DCD pin status
+			changes and the relative timestamp. The timestamp
+			can be NULL.
+
 
 Driver Access
 
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 33df82e3a39..bfcbbf88c44 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -1812,7 +1812,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   Module snd-ua101
   ----------------
 
-    Module for the Edirol UA-101 audio/MIDI interface.
+    Module for the Edirol UA-101/UA-1000 audio/MIDI interfaces.
 
     This module supports multiple devices, autoprobe and hotplugging.
 
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index fc5790d36cd..6c7d18c53f8 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -573,11 +573,14 @@ Because other nodes' memory may be free. This means system total status
 may be not fatal yet.
 
 If this is set to 2, the kernel panics compulsorily even on the
-above-mentioned.
+above-mentioned. Even oom happens under memory cgroup, the whole
+system panics.
 
 The default value is 0.
 1 and 2 are for failover of clustering. Please select either
 according to your policy of failover.
+panic_on_oom=2+kdump gives you very strong tool to investigate
+why oom happens. You can get snapshot.
 
 =============================================================
 
diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX
index 397dc35e132..a9248da5cdb 100644
--- a/Documentation/timers/00-INDEX
+++ b/Documentation/timers/00-INDEX
@@ -4,6 +4,8 @@ highres.txt
 	- High resolution timers and dynamic ticks design notes
 hpet.txt
 	- High Precision Event Timer Driver for Linux
+hpet_example.c
+	- sample hpet timer test program
 hrtimers.txt
 	- subsystem for high-resolution kernel timers
 timer_stats.txt
diff --git a/Documentation/timers/Makefile b/Documentation/timers/Makefile
new file mode 100644
index 00000000000..c85625f4ab2
--- /dev/null
+++ b/Documentation/timers/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := hpet_example
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt
index 16d25e6b5a0..767392ffd31 100644
--- a/Documentation/timers/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -26,274 +26,5 @@ initialization.  An example of this initialization can be found in
 arch/x86/kernel/hpet.c.
 
 The driver provides a userspace API which resembles the API found in the
-RTC driver framework.  An example user space program is provided below.
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <fcntl.h>
-#include <string.h>
-#include <memory.h>
-#include <malloc.h>
-#include <time.h>
-#include <ctype.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-#include <signal.h>
-#include <fcntl.h>
-#include <errno.h>
-#include <sys/time.h>
-#include <linux/hpet.h>
-
-
-extern void hpet_open_close(int, const char **);
-extern void hpet_info(int, const char **);
-extern void hpet_poll(int, const char **);
-extern void hpet_fasync(int, const char **);
-extern void hpet_read(int, const char **);
-
-#include <sys/poll.h>
-#include <sys/ioctl.h>
-#include <signal.h>
-
-struct hpet_command {
-	char		*command;
-	void		(*func)(int argc, const char ** argv);
-} hpet_command[] = {
-	{
-		"open-close",
-		hpet_open_close
-	},
-	{
-		"info",
-		hpet_info
-	},
-	{
-		"poll",
-		hpet_poll
-	},
-	{
-		"fasync",
-		hpet_fasync
-	},
-};
-
-int
-main(int argc, const char ** argv)
-{
-	int	i;
-
-	argc--;
-	argv++;
-
-	if (!argc) {
-		fprintf(stderr, "-hpet: requires command\n");
-		return -1;
-	}
-
-
-	for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++)
-		if (!strcmp(argv[0], hpet_command[i].command)) {
-			argc--;
-			argv++;
-			fprintf(stderr, "-hpet: executing %s\n",
-				hpet_command[i].command);
-			hpet_command[i].func(argc, argv);
-			return 0;
-		}
-
-	fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]);
-
-	return -1;
-}
-
-void
-hpet_open_close(int argc, const char **argv)
-{
-	int	fd;
-
-	if (argc != 1) {
-		fprintf(stderr, "hpet_open_close: device-name\n");
-		return;
-	}
-
-	fd = open(argv[0], O_RDONLY);
-	if (fd < 0)
-		fprintf(stderr, "hpet_open_close: open failed\n");
-	else
-		close(fd);
-
-	return;
-}
-
-void
-hpet_info(int argc, const char **argv)
-{
-}
-
-void
-hpet_poll(int argc, const char **argv)
-{
-	unsigned long		freq;
-	int			iterations, i, fd;
-	struct pollfd		pfd;
-	struct hpet_info	info;
-	struct timeval		stv, etv;
-	struct timezone		tz;
-	long			usec;
-
-	if (argc != 3) {
-		fprintf(stderr, "hpet_poll: device-name freq iterations\n");
-		return;
-	}
-
-	freq = atoi(argv[1]);
-	iterations = atoi(argv[2]);
-
-	fd = open(argv[0], O_RDONLY);
-
-	if (fd < 0) {
-		fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]);
-		return;
-	}
-
-	if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
-		fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n");
-		goto out;
-	}
-
-	if (ioctl(fd, HPET_INFO, &info) < 0) {
-		fprintf(stderr, "hpet_poll: failed to get info\n");
-		goto out;
-	}
-
-	fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags);
-
-	if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
-		fprintf(stderr, "hpet_poll: HPET_EPI failed\n");
-		goto out;
-	}
-
-	if (ioctl(fd, HPET_IE_ON, 0) < 0) {
-		fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n");
-		goto out;
-	}
-
-	pfd.fd = fd;
-	pfd.events = POLLIN;
-
-	for (i = 0; i < iterations; i++) {
-		pfd.revents = 0;
-		gettimeofday(&stv, &tz);
-		if (poll(&pfd, 1, -1) < 0)
-			fprintf(stderr, "hpet_poll: poll failed\n");
-		else {
-			long 	data;
-
-			gettimeofday(&etv, &tz);
-			usec = stv.tv_sec * 1000000 + stv.tv_usec;
-			usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec;
-
-			fprintf(stderr,
-				"hpet_poll: expired time = 0x%lx\n", usec);
-
-			fprintf(stderr, "hpet_poll: revents = 0x%x\n",
-				pfd.revents);
-
-			if (read(fd, &data, sizeof(data)) != sizeof(data)) {
-				fprintf(stderr, "hpet_poll: read failed\n");
-			}
-			else
-				fprintf(stderr, "hpet_poll: data 0x%lx\n",
-					data);
-		}
-	}
-
-out:
-	close(fd);
-	return;
-}
-
-static int hpet_sigio_count;
-
-static void
-hpet_sigio(int val)
-{
-	fprintf(stderr, "hpet_sigio: called\n");
-	hpet_sigio_count++;
-}
-
-void
-hpet_fasync(int argc, const char **argv)
-{
-	unsigned long		freq;
-	int			iterations, i, fd, value;
-	sig_t			oldsig;
-	struct hpet_info	info;
-
-	hpet_sigio_count = 0;
-	fd = -1;
-
-	if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) {
-		fprintf(stderr, "hpet_fasync: failed to set signal handler\n");
-		return;
-	}
-
-	if (argc != 3) {
-		fprintf(stderr, "hpet_fasync: device-name freq iterations\n");
-		goto out;
-	}
-
-	fd = open(argv[0], O_RDONLY);
-
-	if (fd < 0) {
-		fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]);
-		return;
-	}
-
-
-	if ((fcntl(fd, F_SETOWN, getpid()) == 1) ||
-		((value = fcntl(fd, F_GETFL)) == 1) ||
-		(fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) {
-		fprintf(stderr, "hpet_fasync: fcntl failed\n");
-		goto out;
-	}
-
-	freq = atoi(argv[1]);
-	iterations = atoi(argv[2]);
-
-	if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
-		fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n");
-		goto out;
-	}
-
-	if (ioctl(fd, HPET_INFO, &info) < 0) {
-		fprintf(stderr, "hpet_fasync: failed to get info\n");
-		goto out;
-	}
-
-	fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags);
-
-	if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
-		fprintf(stderr, "hpet_fasync: HPET_EPI failed\n");
-		goto out;
-	}
-
-	if (ioctl(fd, HPET_IE_ON, 0) < 0) {
-		fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n");
-		goto out;
-	}
-
-	for (i = 0; i < iterations; i++) {
-		(void) pause();
-		fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count);
-	}
-
-out:
-	signal(SIGIO, oldsig);
-
-	if (fd >= 0)
-		close(fd);
-
-	return;
-}
+RTC driver framework.  An example user space program is provided in
+file:Documentation/timers/hpet_example.c
diff --git a/Documentation/timers/hpet_example.c b/Documentation/timers/hpet_example.c
new file mode 100644
index 00000000000..f9ce2d9fdfd
--- /dev/null
+++ b/Documentation/timers/hpet_example.c
@@ -0,0 +1,269 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <memory.h>
+#include <malloc.h>
+#include <time.h>
+#include <ctype.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <signal.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <sys/time.h>
+#include <linux/hpet.h>
+
+
+extern void hpet_open_close(int, const char **);
+extern void hpet_info(int, const char **);
+extern void hpet_poll(int, const char **);
+extern void hpet_fasync(int, const char **);
+extern void hpet_read(int, const char **);
+
+#include <sys/poll.h>
+#include <sys/ioctl.h>
+#include <signal.h>
+
+struct hpet_command {
+	char		*command;
+	void		(*func)(int argc, const char ** argv);
+} hpet_command[] = {
+	{
+		"open-close",
+		hpet_open_close
+	},
+	{
+		"info",
+		hpet_info
+	},
+	{
+		"poll",
+		hpet_poll
+	},
+	{
+		"fasync",
+		hpet_fasync
+	},
+};
+
+int
+main(int argc, const char ** argv)
+{
+	int	i;
+
+	argc--;
+	argv++;
+
+	if (!argc) {
+		fprintf(stderr, "-hpet: requires command\n");
+		return -1;
+	}
+
+
+	for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++)
+		if (!strcmp(argv[0], hpet_command[i].command)) {
+			argc--;
+			argv++;
+			fprintf(stderr, "-hpet: executing %s\n",
+				hpet_command[i].command);
+			hpet_command[i].func(argc, argv);
+			return 0;
+		}
+
+	fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]);
+
+	return -1;
+}
+
+void
+hpet_open_close(int argc, const char **argv)
+{
+	int	fd;
+
+	if (argc != 1) {
+		fprintf(stderr, "hpet_open_close: device-name\n");
+		return;
+	}
+
+	fd = open(argv[0], O_RDONLY);
+	if (fd < 0)
+		fprintf(stderr, "hpet_open_close: open failed\n");
+	else
+		close(fd);
+
+	return;
+}
+
+void
+hpet_info(int argc, const char **argv)
+{
+}
+
+void
+hpet_poll(int argc, const char **argv)
+{
+	unsigned long		freq;
+	int			iterations, i, fd;
+	struct pollfd		pfd;
+	struct hpet_info	info;
+	struct timeval		stv, etv;
+	struct timezone		tz;
+	long			usec;
+
+	if (argc != 3) {
+		fprintf(stderr, "hpet_poll: device-name freq iterations\n");
+		return;
+	}
+
+	freq = atoi(argv[1]);
+	iterations = atoi(argv[2]);
+
+	fd = open(argv[0], O_RDONLY);
+
+	if (fd < 0) {
+		fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]);
+		return;
+	}
+
+	if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
+		fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n");
+		goto out;
+	}
+
+	if (ioctl(fd, HPET_INFO, &info) < 0) {
+		fprintf(stderr, "hpet_poll: failed to get info\n");
+		goto out;
+	}
+
+	fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags);
+
+	if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
+		fprintf(stderr, "hpet_poll: HPET_EPI failed\n");
+		goto out;
+	}
+
+	if (ioctl(fd, HPET_IE_ON, 0) < 0) {
+		fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n");
+		goto out;
+	}
+
+	pfd.fd = fd;
+	pfd.events = POLLIN;
+
+	for (i = 0; i < iterations; i++) {
+		pfd.revents = 0;
+		gettimeofday(&stv, &tz);
+		if (poll(&pfd, 1, -1) < 0)
+			fprintf(stderr, "hpet_poll: poll failed\n");
+		else {
+			long 	data;
+
+			gettimeofday(&etv, &tz);
+			usec = stv.tv_sec * 1000000 + stv.tv_usec;
+			usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec;
+
+			fprintf(stderr,
+				"hpet_poll: expired time = 0x%lx\n", usec);
+
+			fprintf(stderr, "hpet_poll: revents = 0x%x\n",
+				pfd.revents);
+
+			if (read(fd, &data, sizeof(data)) != sizeof(data)) {
+				fprintf(stderr, "hpet_poll: read failed\n");
+			}
+			else
+				fprintf(stderr, "hpet_poll: data 0x%lx\n",
+					data);
+		}
+	}
+
+out:
+	close(fd);
+	return;
+}
+
+static int hpet_sigio_count;
+
+static void
+hpet_sigio(int val)
+{
+	fprintf(stderr, "hpet_sigio: called\n");
+	hpet_sigio_count++;
+}
+
+void
+hpet_fasync(int argc, const char **argv)
+{
+	unsigned long		freq;
+	int			iterations, i, fd, value;
+	sig_t			oldsig;
+	struct hpet_info	info;
+
+	hpet_sigio_count = 0;
+	fd = -1;
+
+	if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) {
+		fprintf(stderr, "hpet_fasync: failed to set signal handler\n");
+		return;
+	}
+
+	if (argc != 3) {
+		fprintf(stderr, "hpet_fasync: device-name freq iterations\n");
+		goto out;
+	}
+
+	fd = open(argv[0], O_RDONLY);
+
+	if (fd < 0) {
+		fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]);
+		return;
+	}
+
+
+	if ((fcntl(fd, F_SETOWN, getpid()) == 1) ||
+		((value = fcntl(fd, F_GETFL)) == 1) ||
+		(fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) {
+		fprintf(stderr, "hpet_fasync: fcntl failed\n");
+		goto out;
+	}
+
+	freq = atoi(argv[1]);
+	iterations = atoi(argv[2]);
+
+	if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
+		fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n");
+		goto out;
+	}
+
+	if (ioctl(fd, HPET_INFO, &info) < 0) {
+		fprintf(stderr, "hpet_fasync: failed to get info\n");
+		goto out;
+	}
+
+	fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags);
+
+	if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
+		fprintf(stderr, "hpet_fasync: HPET_EPI failed\n");
+		goto out;
+	}
+
+	if (ioctl(fd, HPET_IE_ON, 0) < 0) {
+		fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n");
+		goto out;
+	}
+
+	for (i = 0; i < iterations; i++) {
+		(void) pause();
+		fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count);
+	}
+
+out:
+	signal(SIGIO, oldsig);
+
+	if (fd >= 0)
+		close(fd);
+
+	return;
+}
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index bab3040da54..03485bfbd79 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -1588,7 +1588,7 @@ module author does not need to worry about it.
 
 When tracing is enabled, kstop_machine is called to prevent
 races with the CPUS executing code being modified (which can
-cause the CPU to do undesireable things), and the nops are
+cause the CPU to do undesirable things), and the nops are
 patched back to calls. But this time, they do not call mcount
 (which is just a function stub). They now call into the ftrace
 infrastructure.
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index e57d6a9dd32..dca82d7c83d 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -4,23 +4,35 @@ active_mm.txt
 	- An explanation from Linus about tsk->active_mm vs tsk->mm.
 balance
 	- various information on memory balancing.
+hugepage-mmap.c
+	- Example app using huge page memory with the mmap system call.
+hugepage-shm.c
+	- Example app using huge page memory with Sys V shared memory system calls.
 hugetlbpage.txt
 	- a brief summary of hugetlbpage support in the Linux kernel.
+hwpoison.txt
+	- explains what hwpoison is
 ksm.txt
 	- how to use the Kernel Samepage Merging feature.
 locking
 	- info on how locking and synchronization is done in the Linux vm code.
+map_hugetlb.c
+	- an example program that uses the MAP_HUGETLB mmap flag.
 numa
 	- information about NUMA specific code in the Linux vm.
 numa_memory_policy.txt
 	- documentation of concepts and APIs of the 2.6 memory policy support.
 overcommit-accounting
 	- description of the Linux kernels overcommit handling modes.
+page-types.c
+	- Tool for querying page flags
 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.
-map_hugetlb.c
-	- an example program that uses the MAP_HUGETLB mmap flag.
+unevictable-lru.txt
+	- Unevictable LRU infrastructure
diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile
index 5bd269b3731..9dcff328b96 100644
--- a/Documentation/vm/Makefile
+++ b/Documentation/vm/Makefile
@@ -2,7 +2,7 @@
 obj- := dummy.o
 
 # List of programs to build
-hostprogs-y := slabinfo page-types
+hostprogs-y := slabinfo page-types hugepage-mmap hugepage-shm map_hugetlb
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
diff --git a/Documentation/vm/hugepage-mmap.c b/Documentation/vm/hugepage-mmap.c
new file mode 100644
index 00000000000..db0dd9a33d5
--- /dev/null
+++ b/Documentation/vm/hugepage-mmap.c
@@ -0,0 +1,91 @@
+/*
+ * hugepage-mmap:
+ *
+ * Example of using huge page memory in a user application using the mmap
+ * system call.  Before running this application, make sure that the
+ * administrator has mounted the hugetlbfs filesystem (on some directory
+ * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
+ * example, the app is requesting memory of size 256MB that is backed by
+ * huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages.  That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required.  If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#define FILE_NAME "/mnt/hugepagefile"
+#define LENGTH (256UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define FLAGS (MAP_SHARED | MAP_FIXED)
+#else
+#define ADDR (void *)(0x0UL)
+#define FLAGS (MAP_SHARED)
+#endif
+
+static void check_bytes(char *addr)
+{
+	printf("First hex is %x\n", *((unsigned int *)addr));
+}
+
+static void write_bytes(char *addr)
+{
+	unsigned long i;
+
+	for (i = 0; i < LENGTH; i++)
+		*(addr + i) = (char)i;
+}
+
+static void read_bytes(char *addr)
+{
+	unsigned long i;
+
+	check_bytes(addr);
+	for (i = 0; i < LENGTH; i++)
+		if (*(addr + i) != (char)i) {
+			printf("Mismatch at %lu\n", i);
+			break;
+		}
+}
+
+int main(void)
+{
+	void *addr;
+	int fd;
+
+	fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
+	if (fd < 0) {
+		perror("Open failed");
+		exit(1);
+	}
+
+	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		unlink(FILE_NAME);
+		exit(1);
+	}
+
+	printf("Returned address is %p\n", addr);
+	check_bytes(addr);
+	write_bytes(addr);
+	read_bytes(addr);
+
+	munmap(addr, LENGTH);
+	close(fd);
+	unlink(FILE_NAME);
+
+	return 0;
+}
diff --git a/Documentation/vm/hugepage-shm.c b/Documentation/vm/hugepage-shm.c
new file mode 100644
index 00000000000..07956d8592c
--- /dev/null
+++ b/Documentation/vm/hugepage-shm.c
@@ -0,0 +1,98 @@
+/*
+ * hugepage-shm:
+ *
+ * Example of using huge page memory in a user application using Sys V shared
+ * memory system calls.  In this example the app is requesting 256MB of
+ * memory that is backed by huge pages.  The application uses the flag
+ * SHM_HUGETLB in the shmget system call to inform the kernel that it is
+ * requesting huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages.  That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required.  If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ *
+ * Note: The default shared memory limit is quite low on many kernels,
+ * you may need to increase it via:
+ *
+ * echo 268435456 > /proc/sys/kernel/shmmax
+ *
+ * This will increase the maximum size per shared memory segment to 256MB.
+ * The other limit that you will hit eventually is shmall which is the
+ * total amount of shared memory in pages. To set it to 16GB on a system
+ * with a 4kB pagesize do:
+ *
+ * echo 4194304 > /proc/sys/kernel/shmall
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <sys/mman.h>
+
+#ifndef SHM_HUGETLB
+#define SHM_HUGETLB 04000
+#endif
+
+#define LENGTH (256UL*1024*1024)
+
+#define dprintf(x)  printf(x)
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define SHMAT_FLAGS (SHM_RND)
+#else
+#define ADDR (void *)(0x0UL)
+#define SHMAT_FLAGS (0)
+#endif
+
+int main(void)
+{
+	int shmid;
+	unsigned long i;
+	char *shmaddr;
+
+	if ((shmid = shmget(2, LENGTH,
+			    SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) {
+		perror("shmget");
+		exit(1);
+	}
+	printf("shmid: 0x%x\n", shmid);
+
+	shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS);
+	if (shmaddr == (char *)-1) {
+		perror("Shared memory attach failure");
+		shmctl(shmid, IPC_RMID, NULL);
+		exit(2);
+	}
+	printf("shmaddr: %p\n", shmaddr);
+
+	dprintf("Starting the writes:\n");
+	for (i = 0; i < LENGTH; i++) {
+		shmaddr[i] = (char)(i);
+		if (!(i % (1024 * 1024)))
+			dprintf(".");
+	}
+	dprintf("\n");
+
+	dprintf("Starting the Check...");
+	for (i = 0; i < LENGTH; i++)
+		if (shmaddr[i] != (char)i)
+			printf("\nIndex %lu mismatched\n", i);
+	dprintf("Done.\n");
+
+	if (shmdt((const void *)shmaddr) != 0) {
+		perror("Detach failure");
+		shmctl(shmid, IPC_RMID, NULL);
+		exit(3);
+	}
+
+	shmctl(shmid, IPC_RMID, NULL);
+
+	return 0;
+}
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index bc31636973e..457634c1e03 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -299,176 +299,11 @@ map_hugetlb.c.
 *******************************************************************
 
 /*
- * Example of using huge page memory in a user application using Sys V shared
- * memory system calls.  In this example the app is requesting 256MB of
- * memory that is backed by huge pages.  The application uses the flag
- * SHM_HUGETLB in the shmget system call to inform the kernel that it is
- * requesting huge pages.
- *
- * For the ia64 architecture, the Linux kernel reserves Region number 4 for
- * huge pages.  That means that if one requires a fixed address, a huge page
- * aligned address starting with 0x800000... will be required.  If a fixed
- * address is not required, the kernel will select an address in the proper
- * range.
- * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
- *
- * Note: The default shared memory limit is quite low on many kernels,
- * you may need to increase it via:
- *
- * echo 268435456 > /proc/sys/kernel/shmmax
- *
- * This will increase the maximum size per shared memory segment to 256MB.
- * The other limit that you will hit eventually is shmall which is the
- * total amount of shared memory in pages. To set it to 16GB on a system
- * with a 4kB pagesize do:
- *
- * echo 4194304 > /proc/sys/kernel/shmall
+ * hugepage-shm:  see Documentation/vm/hugepage-shm.c
  */
-#include <stdlib.h>
-#include <stdio.h>
-#include <sys/types.h>
-#include <sys/ipc.h>
-#include <sys/shm.h>
-#include <sys/mman.h>
-
-#ifndef SHM_HUGETLB
-#define SHM_HUGETLB 04000
-#endif
-
-#define LENGTH (256UL*1024*1024)
-
-#define dprintf(x)  printf(x)
-
-#define ADDR (void *)(0x0UL)	/* let kernel choose address */
-#define SHMAT_FLAGS (0)
-
-int main(void)
-{
-	int shmid;
-	unsigned long i;
-	char *shmaddr;
-
-	if ((shmid = shmget(2, LENGTH,
-			    SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) {
-		perror("shmget");
-		exit(1);
-	}
-	printf("shmid: 0x%x\n", shmid);
-
-	shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS);
-	if (shmaddr == (char *)-1) {
-		perror("Shared memory attach failure");
-		shmctl(shmid, IPC_RMID, NULL);
-		exit(2);
-	}
-	printf("shmaddr: %p\n", shmaddr);
-
-	dprintf("Starting the writes:\n");
-	for (i = 0; i < LENGTH; i++) {
-		shmaddr[i] = (char)(i);
-		if (!(i % (1024 * 1024)))
-			dprintf(".");
-	}
-	dprintf("\n");
-
-	dprintf("Starting the Check...");
-	for (i = 0; i < LENGTH; i++)
-		if (shmaddr[i] != (char)i)
-			printf("\nIndex %lu mismatched\n", i);
-	dprintf("Done.\n");
-
-	if (shmdt((const void *)shmaddr) != 0) {
-		perror("Detach failure");
-		shmctl(shmid, IPC_RMID, NULL);
-		exit(3);
-	}
-
-	shmctl(shmid, IPC_RMID, NULL);
-
-	return 0;
-}
 
 *******************************************************************
 
 /*
- * Example of using huge page memory in a user application using the mmap
- * system call.  Before running this application, make sure that the
- * administrator has mounted the hugetlbfs filesystem (on some directory
- * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
- * example, the app is requesting memory of size 256MB that is backed by
- * huge pages.
- *
- * For the ia64 architecture, the Linux kernel reserves Region number 4 for
- * huge pages.  That means that if one requires a fixed address, a huge page
- * aligned address starting with 0x800000... will be required.  If a fixed
- * address is not required, the kernel will select an address in the proper
- * range.
- * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ * hugepage-mmap:  see Documentation/vm/hugepage-mmap.c
  */
-#include <stdlib.h>
-#include <stdio.h>
-#include <unistd.h>
-#include <sys/mman.h>
-#include <fcntl.h>
-
-#define FILE_NAME "/mnt/hugepagefile"
-#define LENGTH (256UL*1024*1024)
-#define PROTECTION (PROT_READ | PROT_WRITE)
-
-#define ADDR (void *)(0x0UL)	/* let kernel choose address */
-#define FLAGS (MAP_SHARED)
-
-void check_bytes(char *addr)
-{
-	printf("First hex is %x\n", *((unsigned int *)addr));
-}
-
-void write_bytes(char *addr)
-{
-	unsigned long i;
-
-	for (i = 0; i < LENGTH; i++)
-		*(addr + i) = (char)i;
-}
-
-void read_bytes(char *addr)
-{
-	unsigned long i;
-
-	check_bytes(addr);
-	for (i = 0; i < LENGTH; i++)
-		if (*(addr + i) != (char)i) {
-			printf("Mismatch at %lu\n", i);
-			break;
-		}
-}
-
-int main(void)
-{
-	void *addr;
-	int fd;
-
-	fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
-	if (fd < 0) {
-		perror("Open failed");
-		exit(1);
-	}
-
-	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
-	if (addr == MAP_FAILED) {
-		perror("mmap");
-		unlink(FILE_NAME);
-		exit(1);
-	}
-
-	printf("Returned address is %p\n", addr);
-	check_bytes(addr);
-	write_bytes(addr);
-	read_bytes(addr);
-
-	munmap(addr, LENGTH);
-	close(fd);
-	unlink(FILE_NAME);
-
-	return 0;
-}
diff --git a/Documentation/vm/map_hugetlb.c b/Documentation/vm/map_hugetlb.c
index e2bdae37f49..9969c7d9f98 100644
--- a/Documentation/vm/map_hugetlb.c
+++ b/Documentation/vm/map_hugetlb.c
@@ -31,12 +31,12 @@
 #define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
 #endif
 
-void check_bytes(char *addr)
+static void check_bytes(char *addr)
 {
 	printf("First hex is %x\n", *((unsigned int *)addr));
 }
 
-void write_bytes(char *addr)
+static void write_bytes(char *addr)
 {
 	unsigned long i;
 
@@ -44,7 +44,7 @@ void write_bytes(char *addr)
 		*(addr + i) = (char)i;
 }
 
-void read_bytes(char *addr)
+static void read_bytes(char *addr)
 {
 	unsigned long i;
 
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index b37300edf27..07375e73981 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -41,6 +41,7 @@ Possible debug options are
 	P		Poisoning (object and padding)
 	U		User tracking (free and alloc)
 	T		Trace (please only use on single slabs)
+	A		Toggle failslab filter mark for the cache
 	O		Switch debugging off for caches that would have
 			caused higher minimum slab orders
 	-		Switch all debugging off (useful if the kernel is
diff --git a/Documentation/volatile-considered-harmful.txt b/Documentation/volatile-considered-harmful.txt
index 991c26a6ef6..db0cb228d64 100644
--- a/Documentation/volatile-considered-harmful.txt
+++ b/Documentation/volatile-considered-harmful.txt
@@ -63,9 +63,9 @@ way to perform a busy wait is:
         cpu_relax();
 
 The cpu_relax() call can lower CPU power consumption or yield to a
-hyperthreaded twin processor; it also happens to serve as a memory barrier,
-so, once again, volatile is unnecessary.  Of course, busy-waiting is
-generally an anti-social act to begin with.
+hyperthreaded twin processor; it also happens to serve as a compiler
+barrier, so, once again, volatile is unnecessary.  Of course, busy-
+waiting is generally an anti-social act to begin with.
 
 There are still a few rare situations where volatile makes sense in the
 kernel:
diff --git a/Documentation/voyager.txt b/Documentation/voyager.txt
deleted file mode 100644
index 2749af552cd..00000000000
--- a/Documentation/voyager.txt
+++ /dev/null
@@ -1,95 +0,0 @@
-Running Linux on the Voyager Architecture
-=========================================
-
-For full details and current project status, see
-
-http://www.hansenpartnership.com/voyager
-
-The voyager architecture was designed by NCR in the mid 80s to be a
-fully SMP capable RAS computing architecture built around intel's 486
-chip set.  The voyager came in three levels of architectural
-sophistication: 3,4 and 5 --- 1 and 2 never made it out of prototype.
-The linux patches support only the Level 5 voyager architecture (any
-machine class 3435 and above).
-
-The Voyager Architecture
-------------------------
-
-Voyager machines consist of a Baseboard with a 386 diagnostic
-processor, a Power Supply Interface (PSI) a Primary and possibly
-Secondary Microchannel bus and between 2 and 20 voyager slots.  The
-voyager slots can be populated with memory and cpu cards (up to 4GB
-memory and from 1 486 to 32 Pentium Pro processors).  Internally, the
-voyager has a dual arbitrated system bus and a configuration and test
-bus (CAT).  The voyager bus speed is 40MHz.  Therefore (since all
-voyager cards are dual ported for each system bus) the maximum
-transfer rate is 320Mb/s but only if you have your slot configuration
-tuned (only memory cards can communicate with both busses at once, CPU
-cards utilise them one at a time).
-
-Voyager SMP
------------
-
-Since voyager was the first intel based SMP system, it is slightly
-more primitive than the Intel IO-APIC approach to SMP.  Voyager allows
-arbitrary interrupt routing (including processor affinity routing) of
-all 16 PC type interrupts.  However it does this by using a modified
-5259 master/slave chip set instead of an APIC bus.  Additionally,
-voyager supports Cross Processor Interrupts (CPI) equivalent to the
-APIC IPIs.  There are two routed voyager interrupt lines provided to
-each slot.
-
-Processor Cards
----------------
-
-These come in single, dyadic and quad configurations (the quads are
-problematic--see later).  The maximum configuration is 8 quad cards
-for 32 way SMP.
-
-Quad Processors
----------------
-
-Because voyager only supplies two interrupt lines to each Processor
-card, the Quad processors have to be configured (and Bootstrapped) in
-as a pair of Master/Slave processors.
-
-In fact, most Quad cards only accept one VIC interrupt line, so they
-have one interrupt handling processor (called the VIC extended
-processor) and three non-interrupt handling processors.
-
-Current Status
---------------
-
-The System will boot on Mono, Dyad and Quad cards.  There was
-originally a Quad boot problem which has been fixed by proper gdt
-alignment in the initial boot loader.  If you still cannot get your
-voyager system to boot, email me at:
-
-<J.E.J.Bottomley@HansenPartnership.com>
-
-
-The Quad cards now support using the separate Quad CPI vectors instead
-of going through the VIC mailbox system.
-
-The Level 4 architecture (3430 and 3360 Machines) should also work
-fine.
-
-Dump Switch
------------
-
-The voyager dump switch sends out a broadcast NMI which the voyager
-code intercepts and does a task dump.
-
-Power Switch
-------------
-
-The front panel power switch is intercepted by the kernel and should
-cause a system shutdown and power off.
-
-A Note About Mixed CPU Systems
-------------------------------
-
-Linux isn't designed to handle mixed CPU systems very well.  In order
-to get everything going you *must* make sure that your lowest
-capability CPU is used for booting.  Also, mixing CPU classes
-(e.g. 486 and 586) is really not going to work very well at all.
author	James Morris <jmorris@namei.org>	2010-03-31 08:39:27 +1100
committer	James Morris <jmorris@namei.org>	2010-03-31 08:39:27 +1100
commit	d25d6fa1a95f465ff1ec4458ca15e30b2c8dffec (patch)
tree	7362b182dedd825fc762ef7706830837e42943af /Documentation
parent	225a9be24d799aa16d543c31fb09f0c9ed1d9caa (diff)
parent	2eaa9cfdf33b8d7fb7aff27792192e0019ae8fc6 (diff)