Merge branch 'merge' of git://git.secretlab.ca/git/linux-2.6 into merge

43 files changed, 2390 insertions, 929 deletions

diff --git a/Documentation/ABI/testing/debugfs-pktcdvd b/Documentation/ABI/testing/debugfs-pktcdvd
index bf9c16b64c34..cf11736acb76 100644
--- a/Documentation/ABI/testing/debugfs-pktcdvd
+++ b/Documentation/ABI/testing/debugfs-pktcdvd
@@ -1,4 +1,4 @@
-What:           /debug/pktcdvd/pktcdvd[0-7]
+What:           /sys/kernel/debug/pktcdvd/pktcdvd[0-7]
 Date:           Oct. 2006
 KernelVersion:  2.6.20
 Contact:        Thomas Maier <balagi@justmail.de>
@@ -10,10 +10,10 @@ debugfs interface
 The pktcdvd module (packet writing driver) creates
 these files in debugfs:
 
-/debug/pktcdvd/pktcdvd[0-7]/
+/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
     info            (0444) Lots of driver statistics and infos.
 
 Example:
 -------
 
-cat /debug/pktcdvd/pktcdvd0/info
+cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
diff --git a/Documentation/DMA-mapping.txt b/Documentation/DMA-mapping.txt
index b2a4d6d244d9..01f24e94bdb6 100644
--- a/Documentation/DMA-mapping.txt
+++ b/Documentation/DMA-mapping.txt
@@ -136,7 +136,7 @@ exactly why.
 The standard 32-bit addressing PCI device would do something like
 this:
 
-	if (pci_set_dma_mask(pdev, DMA_32BIT_MASK)) {
+	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
@@ -155,9 +155,9 @@ all 64-bits when accessing streaming DMA:
 
 	int using_dac;
 
-	if (!pci_set_dma_mask(pdev, DMA_64BIT_MASK)) {
+	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
-	} else if (!pci_set_dma_mask(pdev, DMA_32BIT_MASK)) {
+	} else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
 		using_dac = 0;
 	} else {
 		printk(KERN_WARNING
@@ -170,14 +170,14 @@ the case would look like this:
 
 	int using_dac, consistent_using_dac;
 
-	if (!pci_set_dma_mask(pdev, DMA_64BIT_MASK)) {
+	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
 	   	consistent_using_dac = 1;
-		pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK);
-	} else if (!pci_set_dma_mask(pdev, DMA_32BIT_MASK)) {
+		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	} else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
 		using_dac = 0;
 		consistent_using_dac = 0;
-		pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK);
+		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
 	} else {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
@@ -192,7 +192,7 @@ check the return value from pci_set_consistent_dma_mask().
 Finally, if your device can only drive the low 24-bits of
 address during PCI bus mastering you might do something like:
 
-	if (pci_set_dma_mask(pdev, DMA_24BIT_MASK)) {
+	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(24))) {
 		printk(KERN_WARNING
 		       "mydev: 24-bit DMA addressing not available.\n");
 		goto ignore_this_device;
@@ -213,7 +213,7 @@ most specific mask.
 
 Here is pseudo-code showing how this might be done:
 
-	#define PLAYBACK_ADDRESS_BITS	DMA_32BIT_MASK
+	#define PLAYBACK_ADDRESS_BITS	DMA_BIT_MASK(32)
 	#define RECORD_ADDRESS_BITS	0x00ffffff
 
 	struct my_sound_card *card;
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index a3a83d38f96f..8918a32c6b3a 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -31,7 +31,7 @@ PS_METHOD	= $(prefer-db2x)
 
 ###
 # The targets that may be used.
-PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs
+PHONY += xmldocs sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs cleandocs
 
 BOOKS := $(addprefix $(obj)/,$(DOCBOOKS))
 xmldocs: $(BOOKS)
@@ -213,11 +213,12 @@ silent_gen_xml = :
 dochelp:
 	@echo  ' Linux kernel internal documentation in different formats:'
 	@echo  '  htmldocs        - HTML'
-	@echo  '  installmandocs  - install man pages generated by mandocs'
-	@echo  '  mandocs         - man pages'
 	@echo  '  pdfdocs         - PDF'
 	@echo  '  psdocs          - Postscript'
 	@echo  '  xmldocs         - XML DocBook'
+	@echo  '  mandocs         - man pages'
+	@echo  '  installmandocs  - install man pages generated by mandocs'
+	@echo  '  cleandocs       - clean all generated DocBook files'
 
 ###
 # Temporary files left by various tools
@@ -235,6 +236,10 @@ clean-files := $(DOCBOOKS) \
 
 clean-dirs := $(patsubst %.xml,%,$(DOCBOOKS)) man
 
+cleandocs:
+	$(Q)rm -f $(call objectify, $(clean-files))
+	$(Q)rm -rf $(call objectify, $(clean-dirs))
+
 # Declare the contents of the .PHONY variable as phony.  We keep that
 # information in a variable se we can use it in if_changed and friends.
 
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index 58c194572c76..d6ac5d61820e 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -259,7 +259,7 @@ X!Earch/x86/kernel/mca_32.c
 !Eblock/blk-tag.c
 !Iblock/blk-tag.c
 !Eblock/blk-integrity.c
-!Iblock/blktrace.c
+!Ikernel/trace/blktrace.c
 !Iblock/genhd.c
 !Eblock/genhd.c
   </chapter>
diff --git a/Documentation/DocBook/writing-an-alsa-driver.tmpl b/Documentation/DocBook/writing-an-alsa-driver.tmpl
index 46b08fef3744..7a2e0e98986a 100644
--- a/Documentation/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/DocBook/writing-an-alsa-driver.tmpl
@@ -1137,8 +1137,8 @@
           if (err < 0)
                   return err;
           /* check PCI availability (28bit DMA) */
-          if (pci_set_dma_mask(pci, DMA_28BIT_MASK) < 0 ||
-              pci_set_consistent_dma_mask(pci, DMA_28BIT_MASK) < 0) {
+          if (pci_set_dma_mask(pci, DMA_BIT_MASK(28)) < 0 ||
+              pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(28)) < 0) {
                   printk(KERN_ERR "error to set 28bit mask DMA\n");
                   pci_disable_device(pci);
                   return -ENXIO;
@@ -1252,8 +1252,8 @@
   err = pci_enable_device(pci);
   if (err < 0)
           return err;
-  if (pci_set_dma_mask(pci, DMA_28BIT_MASK) < 0 ||
-      pci_set_consistent_dma_mask(pci, DMA_28BIT_MASK) < 0) {
+  if (pci_set_dma_mask(pci, DMA_BIT_MASK(28)) < 0 ||
+      pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(28)) < 0) {
           printk(KERN_ERR "error to set 28bit mask DMA\n");
           pci_disable_device(pci);
           return -ENXIO;
diff --git a/Documentation/blockdev/00-INDEX b/Documentation/blockdev/00-INDEX
index 86f054c47013..c08df56dd91b 100644
--- a/Documentation/blockdev/00-INDEX
+++ b/Documentation/blockdev/00-INDEX
@@ -8,6 +8,8 @@ cpqarray.txt
 	- info on using Compaq's SMART2 Intelligent Disk Array Controllers.
 floppy.txt
 	- notes and driver options for the floppy disk driver.
+mflash.txt
+	- info on mGine m(g)flash driver for linux.
 nbd.txt
 	- info on a TCP implementation of a network block device.
 paride.txt
diff --git a/Documentation/blockdev/mflash.txt b/Documentation/blockdev/mflash.txt
new file mode 100644
index 000000000000..1f610ecf698a
--- /dev/null
+++ b/Documentation/blockdev/mflash.txt
@@ -0,0 +1,84 @@
+This document describes m[g]flash support in linux.
+
+Contents
+  1. Overview
+  2. Reserved area configuration
+  3. Example of mflash platform driver registration
+
+1. Overview
+
+Mflash and gflash are embedded flash drive. The only difference is mflash is
+MCP(Multi Chip Package) device. These two device operate exactly same way.
+So the rest mflash repersents mflash and gflash altogether.
+
+Internally, mflash has nand flash and other hardware logics and supports
+2 different operation (ATA, IO) modes. ATA mode doesn't need any new
+driver and currently works well under standard IDE subsystem. Actually it's
+one chip SSD. IO mode is ATA-like custom mode for the host that doesn't have
+IDE interface.
+
+Followings are brief descriptions about IO mode.
+A. IO mode based on ATA protocol and uses some custom command. (read confirm,
+write confirm)
+B. IO mode uses SRAM bus interface.
+C. IO mode supports 4kB boot area, so host can boot from mflash.
+
+2. Reserved area configuration
+If host boot from mflash, usually needs raw area for boot loader image. All of
+the mflash's block device operation will be taken this value as start offset.
+Note that boot loader's size of reserved area and kernel configuration value
+must be same.
+
+3. Example of mflash platform driver registration
+Working mflash is very straight forward. Adding platform device stuff to board
+configuration file is all. Here is some pseudo example.
+
+static struct mg_drv_data mflash_drv_data = {
+	/* If you want to polling driver set to 1 */
+	.use_polling = 0,
+	/* device attribution */
+	.dev_attr = MG_BOOT_DEV
+};
+
+static struct resource mg_mflash_rsc[] = {
+	/* Base address of mflash */
+	[0] = {
+		.start = 0x08000000,
+		.end = 0x08000000 + SZ_64K - 1,
+		.flags = IORESOURCE_MEM
+	},
+	/* mflash interrupt pin */
+	[1] = {
+		.start = IRQ_GPIO(84),
+		.end = IRQ_GPIO(84),
+		.flags = IORESOURCE_IRQ
+	},
+	/* mflash reset pin */
+	[2] = {
+		.start = 43,
+		.end = 43,
+		.name = MG_RST_PIN,
+		.flags = IORESOURCE_IO
+	},
+	/* mflash reset-out pin
+	 * If you use mflash as storage device (i.e. other than MG_BOOT_DEV),
+	 * should assign this */
+	[3] = {
+		.start = 51,
+		.end = 51,
+		.name = MG_RSTOUT_PIN,
+		.flags = IORESOURCE_IO
+	}
+};
+
+static struct platform_device mflash_dev = {
+	.name = MG_DEV_NAME,
+	.id = -1,
+	.dev = {
+		.platform_data = &mflash_drv_data,
+	},
+	.num_resources = ARRAY_SIZE(mg_mflash_rsc),
+	.resource = mg_mflash_rsc
+};
+
+platform_device_register(&mflash_dev);
diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt
index bb775fbe43d7..8b930946c52a 100644
--- a/Documentation/cgroups/cpuacct.txt
+++ b/Documentation/cgroups/cpuacct.txt
@@ -30,3 +30,21 @@ The above steps create a new group g1 and move the current shell
 process (bash) into it. CPU time consumed by this bash and its children
 can be obtained from g1/cpuacct.usage and the same is accumulated in
 /cgroups/cpuacct.usage also.
+
+cpuacct.stat file lists a few statistics which further divide the
+CPU time obtained by the cgroup into user and system times. Currently
+the following statistics are supported:
+
+user: Time spent by tasks of the cgroup in user mode.
+system: Time spent by tasks of the cgroup in kernel mode.
+
+user and system are in USER_HZ unit.
+
+cpuacct controller uses percpu_counter interface to collect user and
+system times. This has two side effects:
+
+- It is theoretically possible to see wrong values for user and system times.
+  This is because percpu_counter_read() on 32bit systems isn't safe
+  against concurrent writes.
+- It is possible to see slightly outdated values for user and system times
+  due to the batch processing nature of percpu_counter.
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index a98a7fe7aabb..1a608877b14e 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -6,15 +6,14 @@ used here with the memory controller that is used in hardware.
 
 Salient features
 
-a. Enable control of both RSS (mapped) and Page Cache (unmapped) pages
+a. Enable control of Anonymous, Page Cache (mapped and unmapped) and
+   Swap Cache memory pages.
 b. The infrastructure allows easy addition of other types of memory to control
 c. Provides *zero overhead* for non memory controller users
 d. Provides a double LRU: global memory pressure causes reclaim from the
    global LRU; a cgroup on hitting a limit, reclaims from the per
    cgroup LRU
 
-NOTE: Swap Cache (unmapped) is not accounted now.
-
 Benefits and Purpose of the memory controller
 
 The memory controller isolates the memory behaviour of a group of tasks
@@ -290,34 +289,44 @@ will be charged as a new owner of it.
   moved to the parent. If you want to avoid that, force_empty will be useful.
 
 5.2 stat file
-  memory.stat file includes following statistics (now)
-	cache			- # of pages from page-cache and shmem.
-	rss			- # of pages from anonymous memory.
-	pgpgin			- # of event of charging
-	pgpgout			- # of event of uncharging
-	active_anon		- # of pages on active lru of anon, shmem.
-	inactive_anon 		- # of pages on active lru of anon, shmem
-	active_file		- # of pages on active lru of file-cache
-	inactive_file		- # of pages on inactive lru of file cache
-	unevictable		- # of pages cannot be reclaimed.(mlocked etc)
-
-	Below is depend on CONFIG_DEBUG_VM.
-	inactive_ratio		- VM internal parameter. (see mm/page_alloc.c)
-	recent_rotated_anon	- VM internal parameter. (see mm/vmscan.c)
-	recent_rotated_file	- VM internal parameter. (see mm/vmscan.c)
-	recent_scanned_anon 	- VM internal parameter. (see mm/vmscan.c)
-	recent_scanned_file 	- VM internal parameter. (see mm/vmscan.c)
-
-  Memo:
+
+memory.stat file includes following statistics
+
+cache		- # of bytes of page cache memory.
+rss		- # of bytes of anonymous and swap cache memory.
+pgpgin		- # of pages paged in (equivalent to # of charging events).
+pgpgout		- # of pages paged out (equivalent to # of uncharging events).
+active_anon	- # of bytes of anonymous and  swap cache memory on active
+		  lru list.
+inactive_anon	- # of bytes of anonymous memory and swap cache memory on
+		  inactive lru list.
+active_file	- # of bytes of file-backed memory on active lru list.
+inactive_file	- # of bytes of file-backed memory on inactive lru list.
+unevictable	- # of bytes of memory that cannot be reclaimed (mlocked etc).
+
+The following additional stats are dependent on CONFIG_DEBUG_VM.
+
+inactive_ratio		- VM internal parameter. (see mm/page_alloc.c)
+recent_rotated_anon	- VM internal parameter. (see mm/vmscan.c)
+recent_rotated_file	- VM internal parameter. (see mm/vmscan.c)
+recent_scanned_anon	- VM internal parameter. (see mm/vmscan.c)
+recent_scanned_file	- VM internal parameter. (see mm/vmscan.c)
+
+Memo:
 	recent_rotated means recent frequency of lru rotation.
 	recent_scanned means recent # of scans to lru.
 	showing for better debug please see the code for meanings.
 
+Note:
+	Only anonymous and swap cache memory is listed as part of 'rss' stat.
+	This should not be confused with the true 'resident set size' or the
+	amount of physical memory used by the cgroup. Per-cgroup rss
+	accounting is not done yet.
 
 5.3 swappiness
   Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
 
-  Following cgroup's swapiness can't be changed.
+  Following cgroups' swapiness 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.
diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
index f196ac1d7d25..95b24d766eab 100644
--- a/Documentation/cgroups/resource_counter.txt
+++ b/Documentation/cgroups/resource_counter.txt
@@ -47,13 +47,18 @@ to work with it.
 
 2. Basic accounting routines
 
- a. void res_counter_init(struct res_counter *rc)
+ a. void res_counter_init(struct res_counter *rc,
+				struct res_counter *rc_parent)
 
  	Initializes the resource counter. As usual, should be the first
 	routine called for a new counter.
 
- b. int res_counter_charge[_locked]
-			(struct res_counter *rc, unsigned long val)
+	The struct res_counter *parent can be used to define a hierarchical
+	child -> parent relationship directly in the res_counter structure,
+	NULL can be used to define no relationship.
+
+ c. int res_counter_charge(struct res_counter *rc, unsigned long val,
+				struct res_counter **limit_fail_at)
 
 	When a resource is about to be allocated it has to be accounted
 	with the appropriate resource counter (controller should determine
@@ -67,15 +72,25 @@ to work with it.
 	  * if the charging is performed first, then it should be uncharged
 	    on error path (if the one is called).
 
- c. void res_counter_uncharge[_locked]
+	If the charging fails and a hierarchical dependency exists, the
+	limit_fail_at parameter is set to the particular res_counter element
+	where the charging failed.
+
+ d. int res_counter_charge_locked
+			(struct res_counter *rc, unsigned long val)
+
+	The same as res_counter_charge(), but it must not acquire/release the
+	res_counter->lock internally (it must be called with res_counter->lock
+	held).
+
+ e. void res_counter_uncharge[_locked]
 			(struct res_counter *rc, unsigned long val)
 
 	When a resource is released (freed) it should be de-accounted
 	from the resource counter it was accounted to.  This is called
 	"uncharging".
 
-    The _locked routines imply that the res_counter->lock is taken.
-
+	The _locked routines imply that the res_counter->lock is taken.
 
  2.1 Other accounting routines
 
diff --git a/Documentation/devices.txt b/Documentation/devices.txt
index 327de1624759..53d64d382343 100644
--- a/Documentation/devices.txt
+++ b/Documentation/devices.txt
@@ -3,7 +3,7 @@
 
 	     Maintained by Alan Cox <device@lanana.org>
 
-		      Last revised: 29 November 2006
+		      Last revised: 6th April 2009
 
 This list is the Linux Device List, the official registry of allocated
 device numbers and /dev directory nodes for the Linux operating
@@ -2797,6 +2797,10 @@ Your cooperation is appreciated.
 		 206 = /dev/ttySC1		SC26xx serial port 1
 		 207 = /dev/ttySC2		SC26xx serial port 2
 		 208 = /dev/ttySC3		SC26xx serial port 3
+		 209 = /dev/ttyMAX0		MAX3100 serial port 0
+		 210 = /dev/ttyMAX1		MAX3100 serial port 1
+		 211 = /dev/ttyMAX2		MAX3100 serial port 2
+		 212 = /dev/ttyMAX3		MAX3100 serial port 3
 
 205 char	Low-density serial ports (alternate device)
 		  0 = /dev/culu0		Callout device for ttyLU0
diff --git a/Documentation/fb/uvesafb.txt b/Documentation/fb/uvesafb.txt
index 7ac3c4078ff9..eefdd91d298a 100644
--- a/Documentation/fb/uvesafb.txt
+++ b/Documentation/fb/uvesafb.txt
@@ -59,7 +59,8 @@ Accepted options:
 ypan    Enable display panning using the VESA protected mode
         interface.  The visible screen is just a window of the
         video memory, console scrolling is done by changing the
-        start of the window.  Available on x86 only.
+        start of the window.  This option is available on x86
+        only and is the default option on that architecture.
 
 ywrap   Same as ypan, but assumes your gfx board can wrap-around
         the video memory (i.e. starts reading from top if it
@@ -67,7 +68,7 @@ ywrap   Same as ypan, but assumes your gfx board can wrap-around
         Available on x86 only.
 
 redraw  Scroll by redrawing the affected part of the screen, this
-        is the safe (and slow) default.
+        is the default on non-x86.
 
 (If you're using uvesafb as a module, the above three options are
  used a parameter of the scroll option, e.g. scroll=ypan.)
@@ -182,7 +183,7 @@ from the Video BIOS if you set pixclock to 0 in fb_var_screeninfo.
 
 --
  Michal Januszewski <spock@gentoo.org>
- Last updated: 2007-06-16
+ Last updated: 2009-03-30
 
  Documentation of the uvesafb options is loosely based on vesafb.txt.
 
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 39246fc11257..de491a3e2313 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -354,7 +354,8 @@ Who:  Krzysztof Piotr Oledzki <ole@ans.pl>
 
 ---------------------------
 
-What:	i2c_attach_client(), i2c_detach_client(), i2c_driver->detach_client()
+What:	i2c_attach_client(), i2c_detach_client(), i2c_driver->detach_client(),
+	i2c_adapter->client_register(), i2c_adapter->client_unregister
 When:	2.6.30
 Check:	i2c_attach_client i2c_detach_client
 Why:	Deprecated by the new (standard) device driver binding model. Use
@@ -427,3 +428,12 @@ Why:	In 2.6.27, the semantics of /sys/bus/pci/slots was redefined to
 	After a reasonable transition period, we will remove the legacy
 	fakephp interface.
 Who:	Alex Chiang <achiang@hp.com>
+
+---------------------------
+
+What:	i2c-voodoo3 driver
+When:	October 2009
+Why:	Superseded by tdfxfb. I2C/DDC support used to live in a separate
+	driver but this caused driver conflicts.
+Who:	Jean Delvare <khali@linux-fr.org>
+	Krzysztof Helt <krzysztof.h1@wp.pl>
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 52cd611277a3..8dd6db76171d 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -68,6 +68,8 @@ ncpfs.txt
 	- info on Novell Netware(tm) filesystem using NCP protocol.
 nfsroot.txt
 	- short guide on setting up a diskless box with NFS root filesystem.
+nilfs2.txt
+	- info and mount options for the NILFS2 filesystem.
 ntfs.txt
 	- info and mount options for the NTFS filesystem (Windows NT).
 ocfs2.txt
diff --git a/Documentation/filesystems/knfsd-stats.txt b/Documentation/filesystems/knfsd-stats.txt
new file mode 100644
index 000000000000..64ced5149d37
--- /dev/null
+++ b/Documentation/filesystems/knfsd-stats.txt
@@ -0,0 +1,159 @@
+
+Kernel NFS Server Statistics
+============================
+
+This document describes the format and semantics of the statistics
+which the kernel NFS server makes available to userspace.  These
+statistics are available in several text form pseudo files, each of
+which is described separately below.
+
+In most cases you don't need to know these formats, as the nfsstat(8)
+program from the nfs-utils distribution provides a helpful command-line
+interface for extracting and printing them.
+
+All the files described here are formatted as a sequence of text lines,
+separated by newline '\n' characters.  Lines beginning with a hash
+'#' character are comments intended for humans and should be ignored
+by parsing routines.  All other lines contain a sequence of fields
+separated by whitespace.
+
+/proc/fs/nfsd/pool_stats
+------------------------
+
+This file is available in kernels from 2.6.30 onwards, if the
+/proc/fs/nfsd filesystem is mounted (it almost always should be).
+
+The first line is a comment which describes the fields present in
+all the other lines.  The other lines present the following data as
+a sequence of unsigned decimal numeric fields.  One line is shown
+for each NFS thread pool.
+
+All counters are 64 bits wide and wrap naturally.  There is no way
+to zero these counters, instead applications should do their own
+rate conversion.
+
+pool
+	The id number of the NFS thread pool to which this line applies.
+	This number does not change.
+
+	Thread pool ids are a contiguous set of small integers starting
+	at zero.  The maximum value depends on the thread pool mode, but
+	currently cannot be larger than the number of CPUs in the system.
+	Note that in the default case there will be a single thread pool
+	which contains all the nfsd threads and all the CPUs in the system,
+	and thus this file will have a single line with a pool id of "0".
+
+packets-arrived
+	Counts how many NFS packets have arrived.  More precisely, this
+	is the number of times that the network stack has notified the
+	sunrpc server layer that new data may be available on a transport
+	(e.g. an NFS or UDP socket or an NFS/RDMA endpoint).
+
+	Depending on the NFS workload patterns and various network stack
+	effects (such as Large Receive Offload) which can combine packets
+	on the wire, this may be either more or less than the number
+	of NFS calls received (which statistic is available elsewhere).
+	However this is a more accurate and less workload-dependent measure
+	of how much CPU load is being placed on the sunrpc server layer
+	due to NFS network traffic.
+
+sockets-enqueued
+	Counts how many times an NFS transport is enqueued to wait for
+	an nfsd thread to service it, i.e. no nfsd thread was considered
+	available.
+
+	The circumstance this statistic tracks indicates that there was NFS
+	network-facing work to be done but it couldn't be done immediately,
+	thus introducing a small delay in servicing NFS calls.  The ideal
+	rate of change for this counter is zero; significantly non-zero
+	values may indicate a performance limitation.
+
+	This can happen either because there are too few nfsd threads in the
+	thread pool for the NFS workload (the workload is thread-limited),
+	or because the NFS workload needs more CPU time than is available in
+	the thread pool (the workload is CPU-limited).  In the former case,
+	configuring more nfsd threads will probably improve the performance
+	of the NFS workload.  In the latter case, the sunrpc server layer is
+	already choosing not to wake idle nfsd threads because there are too
+	many nfsd threads which want to run but cannot, so configuring more
+	nfsd threads will make no difference whatsoever.  The overloads-avoided
+	statistic (see below) can be used to distinguish these cases.
+
+threads-woken
+	Counts how many times an idle nfsd thread is woken to try to
+	receive some data from an NFS transport.
+
+	This sta