Merge commit 'v2.6.38-rc1' into kbuild/packaging

45 files changed, 2566 insertions, 552 deletions

diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 875d49696b6..8c624a18f67 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
@@ -90,8 +96,6 @@ seq_file.txt
 	- how to use the seq_file API
 sharedsubtree.txt
 	- a description of shared subtrees for namespaces.
-smbfs.txt
-	- info on using filesystems with the SMB protocol (Win 3.11 and NT).
 spufs.txt
 	- info and mount options for the SPU filesystem used on Cell.
 sysfs-pci.txt
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt
index 57e0b80a527..b22abba78fe 100644
--- a/Documentation/filesystems/9p.txt
+++ b/Documentation/filesystems/9p.txt
@@ -37,6 +37,15 @@ For Plan 9 From User Space applications (http://swtch.com/plan9)
 
 	mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER
 
+For server running on QEMU host with virtio transport:
+
+	mount -t 9p -o trans=virtio <mount_tag> /mnt/9
+
+where mount_tag is the tag associated by the server to each of the exported
+mount points. Each 9P export is seen by the client as a virtio device with an
+associated "mount_tag" property. Available mount tags can be
+seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files.
+
 OPTIONS
 =======
 
@@ -47,7 +56,7 @@ OPTIONS
 			fd   	- used passed file descriptors for connection
                                 (see rfdno and wfdno)
 			virtio	- connect to the next virtio channel available
-				(from lguest or KVM with trans_virtio module)
+				(from QEMU with trans_virtio module)
 			rdma	- connect to a specified RDMA channel
 
   uname=name	user name to attempt mount as on the remote server.  The
@@ -85,7 +94,12 @@ OPTIONS
 
   port=n	port to connect to on the remote server
 
-  noextend	force legacy mode (no 9p2000.u semantics)
+  noextend	force legacy mode (no 9p2000.u or 9p2000.L semantics)
+
+  version=name	Select 9P protocol version. Valid options are:
+			9p2000          - Legacy mode (same as noextend)
+			9p2000.u        - Use 9P2000.u protocol
+			9p2000.L        - Use 9P2000.L protocol
 
   dfltuid	attempt to mount as a particular uid
 
@@ -97,7 +111,7 @@ OPTIONS
   		This can be used to share devices/named pipes/sockets between
 		hosts.  This functionality will be expanded in later versions.
 
-  access	there are three access modes.
+  access	there are four access modes.
 			user  = if a user tries to access a file on v9fs
 			        filesystem for the first time, v9fs sends an
 			        attach command (Tattach) for that user.
@@ -106,6 +120,8 @@ OPTIONS
 				the files on the mounted filesystem
 			any   = v9fs does single attach and performs all
 				operations as one user
+			client = ACL based access check on the 9p client
+			         side for access validation
 
   cachetag	cache tag to use the specified persistent cache.
 		cache tags for existing cache sessions can be listed at
@@ -114,7 +130,7 @@ OPTIONS
 RESOURCES
 =========
 
-Our current recommendation is to use Inferno (http://www.vitanuova.com/inferno)
+Our current recommendation is to use Inferno (http://www.vitanuova.com/nferno/index.html)
 as the 9p server.  You can start a 9p server under Inferno by issuing the
 following command:
    ; styxlisten -A tcp!*!564 export '#U*'
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 18b9d0ca063..4471a416c27 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -9,24 +9,30 @@ be able to use diff(1).
 
 --------------------------- dentry_operations --------------------------
 prototypes:
-	int (*d_revalidate)(struct dentry *, int);
-	int (*d_hash) (struct dentry *, struct qstr *);
-	int (*d_compare) (struct dentry *, struct qstr *, struct qstr *);
+	int (*d_revalidate)(struct dentry *, struct nameidata *);
+	int (*d_hash)(const struct dentry *, const struct inode *,
+			struct qstr *);
+	int (*d_compare)(const struct dentry *, const struct inode *,
+			const struct dentry *, const struct inode *,
+			unsigned int, const char *, const struct qstr *);
 	int (*d_delete)(struct dentry *);
 	void (*d_release)(struct dentry *);
 	void (*d_iput)(struct dentry *, struct inode *);
 	char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
+	struct vfsmount *(*d_automount)(struct path *path);
+	int (*d_manage)(struct dentry *, bool);
 
 locking rules:
-	none have BKL
-		dcache_lock	rename_lock	->d_lock	may block
-d_revalidate:	no		no		no		yes
-d_hash		no		no		no		yes
-d_compare:	no		yes		no		no 
-d_delete:	yes		no		yes		no
-d_release:	no		no		no		yes
-d_iput:		no		no		no		yes
+		rename_lock	->d_lock	may block	rcu-walk
+d_revalidate:	no		no		yes (ref-walk)	maybe
+d_hash		no		no		no		maybe
+d_compare:	yes		no		no		maybe
+d_delete:	no		yes		no		no
+d_release:	no		no		yes		no
+d_iput:		no		no		yes		no
 d_dname:	no		no		no		no
+d_automount:	no		no		yes		no
+d_manage:	no		no		yes (ref-walk)	maybe
 
 --------------------------- inode_operations --------------------------- 
 prototypes:
@@ -42,18 +48,22 @@ ata *);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
 	int (*readlink) (struct dentry *, char __user *,int);
-	int (*follow_link) (struct dentry *, struct nameidata *);
+	void * (*follow_link) (struct dentry *, struct nameidata *);
+	void (*put_link) (struct dentry *, struct nameidata *, void *);
 	void (*truncate) (struct inode *);
-	int (*permission) (struct inode *, int, struct nameidata *);
+	int (*permission) (struct inode *, int, unsigned int);
+	int (*check_acl)(struct inode *, int, unsigned int);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
 	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
+	void (*truncate_range)(struct inode *, loff_t, loff_t);
+	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
 
 locking rules:
-	all may block, none have BKL
+	all may block
 		i_mutex(inode)
 lookup:		yes
 create:		yes
@@ -66,19 +76,23 @@ rmdir:		yes (both)	(see below)
 rename:		yes (all)	(see below)
 readlink:	no
 follow_link:	no
+put_link:	no
 truncate:	yes		(see below)
 setattr:	yes
-permission:	no
+permission:	no (may not block if called in rcu-walk mode)
+check_acl:	no
 getattr:	no
 setxattr:	yes
 getxattr:	no
 listxattr:	no
 removexattr:	yes
+truncate_range:	yes
+fiemap:		no
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
 	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
 	->truncate() is never called directly - it's a callback, not a
-method. It's called by vmtruncate() - library function normally used by
+method. It's called by vmtruncate() - deprecated library function used by
 ->setattr(). Locking information above applies to that call (i.e. is
 inherited from ->setattr() - vmtruncate() is used when ATTR_SIZE had been
 passed).
@@ -91,9 +105,9 @@ prototypes:
 	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
 	void (*dirty_inode) (struct inode *);
-	int (*write_inode) (struct inode *, int);
-	void (*drop_inode) (struct inode *);
-	void (*delete_inode) (struct inode *);
+	int (*write_inode) (struct inode *, struct writeback_control *wbc);
+	int (*drop_inode) (struct inode *);
+	void (*evict_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
 	void (*write_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
@@ -101,55 +115,64 @@ prototypes:
 	int (*unfreeze_fs) (struct super_block *);
 	int (*statfs) (struct dentry *, struct kstatfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
-	void (*clear_inode) (struct inode *);
 	void (*umount_begin) (struct super_block *);
 	int (*show_options)(struct seq_file *, struct vfsmount *);
 	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
+	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
 
 locking rules:
-	All may block.
-	None have BKL
+	All may block [not true, see below]
 			s_umount
 alloc_inode:
 destroy_inode:
 dirty_inode:				(must not sleep)
 write_inode:
 drop_inode:				!!!inode_lock!!!
-delete_inode:
+evict_inode:
 put_super:		write
 write_super:		read
 sync_fs:		read
 freeze_fs:		read
 unfreeze_fs:		read
-statfs:			no
-remount_fs:		maybe		(see below)
-clear_inode:
+statfs:			maybe(read)	(see below)
+remount_fs:		write
 umount_begin:		no
 show_options:		no		(namespace_sem)
 quota_read:		no		(see below)
 quota_write:		no		(see below)
-
-->remount_fs() will have the s_umount exclusive lock if it's already mounted.
-When called from get_sb_single, it does NOT have the s_umount lock.
+bdev_try_to_free_page:	no		(see below)
+
+->statfs() has s_umount (shared) when called by ustat(2) (native or
+compat), but that's an accident of bad API; s_umount is used to pin
+the superblock down when we only have dev_t given us by userland to
+identify the superblock.  Everything else (statfs(), fstatfs(), etc.)
+doesn't hold it when calling ->statfs() - superblock is pinned down
+by resolving the pathname passed to syscall.
 ->quota_read() and ->quota_write() functions are both guaranteed to
 be the only ones operating on the quota file by the quota code (via
 dqio_sem) (unless an admin really wants to screw up something and
 writes to quota files with quotas on). For other details about locking
 see also dquot_operations section.
+->bdev_try_to_free_page is called from the ->releasepage handler of
+the block device inode.  See there for more details.
 
 --------------------------- file_system_type ---------------------------
 prototypes:
 	int (*get_sb) (struct file_system_type *, int,
 		       const char *, void *, struct vfsmount *);
+	struct dentry *(*mount) (struct file_system_type *, int,
+		       const char *, void *);
 	void (*kill_sb) (struct super_block *);
 locking rules:
-		may block	BKL
-get_sb		yes		no
-kill_sb		yes		no
+		may block
+get_sb		yes
+mount		yes
+kill_sb		yes
 
 ->get_sb() returns error or 0 with locked superblock attached to the vfsmount
 (exclusive on ->s_umount).
+->mount() returns ERR_PTR or the root dentry.
 ->kill_sb() takes a write-locked superblock, does all shutdown work on it,
 unlocks and drops the reference.
 
@@ -171,28 +194,38 @@ prototypes:
 	sector_t (*bmap)(struct address_space *, sector_t);
 	int (*invalidatepage) (struct page *, unsigned long);
 	int (*releasepage) (struct page *, int);
+	void (*freepage)(struct page *);
 	int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
 			loff_t offset, unsigned long nr_segs);
-	int (*launder_page) (struct page *);
+	int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **,
+				unsigned long *);
+	int (*migratepage)(struct address_space *, struct page *, struct page *);
+	int (*launder_page)(struct page *);
+	int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long);
+	int (*error_remove_page)(struct address_space *, struct page *);
 
 locking rules:
-	All except set_page_dirty may block
-
-			BKL	PageLocked(page)	i_sem
-writepage:		no	yes, unlocks (see below)
-readpage:		no	yes, unlocks
-sync_page:		no	maybe
-writepages:		no
-set_page_dirty		no	no
-readpages:		no
-write_begin:		no	locks the page		yes
-write_end:		no	yes, unlocks		yes
-perform_write:		no	n/a			yes
-bmap:			no
-invalidatepage:		no	yes
-releasepage:		no	yes
-direct_IO:		no
-launder_page:		no	yes
+	All except set_page_dirty and freepage may block
+
+			PageLocked(page)	i_mutex
+writepage:		yes, unlocks (see below)
+readpage:		yes, unlocks
+sync_page:		maybe
+writepages:
+set_page_dirty		no
+readpages:
+write_begin:		locks the page		yes
+write_end:		yes, unlocks		yes
+bmap:
+invalidatepage:		yes
+releasepage:		yes
+freepage:		yes
+direct_IO:
+get_xip_mem:					maybe
+migratepage:		yes (both)
+launder_page:		yes
+is_partially_uptodate:	yes
+error_remove_page:	yes
 
 	->write_begin(), ->write_end(), ->sync_page() and ->readpage()
 may be called from the request handler (/dev/loop).
@@ -272,9 +305,8 @@ under spinlock (it cannot block) and is sometimes called with the page
 not locked.
 
 	->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
-filesystems and by the swapper. The latter will eventually go away. All
-instances do not actually need the BKL. Please, keep it that way and don't
-breed new callers.
+filesystems and by the swapper. The latter will eventually go away.  Please,
+keep it that way and don't breed new callers.
 
 	->invalidatepage() is called when the filesystem must attempt to drop
 some or all of the buffers from the page when it is being truncated.  It
@@ -286,55 +318,44 @@ buffers from the page in preparation for freeing it.  It returns zero to
 indicate that the buffers are (or may be) freeable.  If ->releasepage is zero,
 the kernel assumes that the fs has no private interest in the buffers.
 
+	->freepage() is called when the kernel is done dropping the page
+from the page cache.
+
 	->launder_page() may be called prior to releasing a page if
 it is still found to be dirty. It returns zero if the page was successfully
 cleaned, or an error value if not. Note that in order to prevent the page
 getting mapped back in and redirtied, it needs to be kept locked
 across the entire operation.
 
-	Note: currently almost all instances of address_space methods are
-using BKL for internal serialization and that's one of the worst sources
-of contention. Normally they are calling library functions (in fs/buffer.c)
-and pass foo_get_block() as a callback (on local block-based filesystems,
-indeed). BKL is not needed for library stuff and is usually taken by
-foo_get_block(). It's an overkill, since block bitmaps can be protected by
-internal fs locking and real critical areas are much smaller than the areas
-filesystems protect now.
-
 ----------------------- file_lock_operations ------------------------------
 prototypes:
-	void (*fl_insert)(struct file_lock *);	/* lock insertion callback */
-	void (*fl_remove)(struct file_lock *);	/* lock removal callback */
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
 	void (*fl_release_private)(struct file_lock *);
 
 
 locking rules:
-			BKL	may block
-fl_insert:		yes	no
-fl_remove:		yes	no
-fl_copy_lock:		yes	no
-fl_release_private:	yes	yes
+			file_lock_lock	may block
+fl_copy_lock:		yes		no
+fl_release_private:	maybe		no
 
 ----------------------- lock_manager_operations ---------------------------
 prototypes:
 	int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
 	void (*fl_notify)(struct file_lock *);  /* unblock callback */
-	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
+	int (*fl_grant)(struct file_lock *, struct file_lock *, int);
 	void (*fl_release_private)(struct file_lock *);
 	void (*fl_break)(struct file_lock *); /* break_lease callback */
+	int (*fl_change)(struct file_lock **, int);
 
 locking rules:
-			BKL	may block
-fl_compare_owner:	yes	no
-fl_notify:		yes	no
-fl_copy_lock:		yes	no
-fl_release_private:	yes	yes
-fl_break:		yes	no
-
-	Currently only NFSD and NLM provide instances of this class. None of the
-them block. If you have out-of-tree instances - please, show up. Locking
-in that area will change.
+			file_lock_lock	may block
+fl_compare_owner:	yes		no
+fl_notify:		yes		no
+fl_grant:		no		no
+fl_release_private:	maybe		no
+fl_break:		yes		no
+fl_change		yes		no
+
 --------------------------- buffer_head -----------------------------------
 prototypes:
 	void (*b_end_io)(struct buffer_head *bh, int uptodate);
@@ -347,21 +368,36 @@ call this method upon the IO completion.
 
 --------------------------- block_device_operations -----------------------
 prototypes:
-	int (*open) (struct inode *, struct file *);
-	int (*release) (struct inode *, struct file *);
-	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
+	int (*open) (struct block_device *, fmode_t);
+	int (*release) (struct gendisk *, fmode_t);
+	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
 	int (*media_changed) (struct gendisk *);
+	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
+	int (*getgeo)(struct block_device *, struct hd_geometry *);
+	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 
 locking rules:
-			BKL	bd_sem
-open:			yes	yes
-release:		yes	yes
-ioctl:			yes	no
-media_changed:		no	no
-revalidate_disk:	no	no
+			bd_mutex
+open:			yes
+release:		yes
+ioctl:			no
+compat_ioctl:		no
+direct_access:		no
+media_changed:		no
+unlock_native_capacity:	no
+revalidate_disk:	no
+getgeo:			no
+swap_slot_free_notify:	no	(see below)
+
+media_changed, unlock_native_capacity and revalidate_disk are called only from
+check_disk_change().
+
+swap_slot_free_notify is called with swap_lock and sometimes the page lock
+held.
 
-The last two are called only from check_disk_change().
 
 --------------------------- file_operations -------------------------------
 prototypes:
@@ -372,15 +408,13 @@ prototypes:
 	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	int (*readdir) (struct file *, void *, filldir_t);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
-	int (*ioctl) (struct inode *, struct file *, unsigned int,
-			unsigned long);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *);
 	int (*release) (struct inode *, struct file *);
-	int (*fsync) (struct file *, struct dentry *, int datasync);
+	int (*fsync) (struct file *, int datasync);
 	int (*aio_fsync) (struct kiocb *, int datasync);
 	int (*fasync) (int, struct file *, int);
 	int (*lock) (struct file *, int, struct file_lock *);
@@ -395,54 +429,35 @@ prototypes:
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long,
 			unsigned long, unsigned long, unsigned long);
 	int (*check_flags)(int);
+	int (*flock) (struct file *, int, struct file_lock *);
+	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
+			size_t, unsigned int);
+	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
+			size_t, unsigned int);
+	int (*setlease)(struct file *, long, struct file_lock **);
+	long (*fallocate)(struct file *, int, loff_t, loff_t);
 };
 
 locking rules:
-	All may block.
-			BKL
-llseek:			no	(see below)
-read:			no
-aio_read:		no
-write:			no
-aio_write:		no
-readdir: 		no
-poll:			no
-ioctl:			yes	(see below)
-unlocked_ioctl:		no	(see below)
-compat_ioctl:		no
-mmap:			no
-open:			no
-flush:			no
-release:		no
-fsync:			no	(see below)
-aio_fsync:		no
-fasync:			no
-lock:			yes
-readv:			no
-writev:			no
-sendfile:		no
-sendpage:		no
-get_unmapped_area:	no
-check_flags:		no
+	All may block except for ->setlease.
+	No VFS locks held on entry except for ->fsync and ->setlease.
+
+->fsync() has i_mutex on inode.
+
+->setlease has the file_list_lock held and must not sleep.
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you
 need to acquire and release the appropriate locks in your ->llseek().
 For many filesystems, it is probably safe to acquire the inode
-semaphore.  Note some filesystems (i.e. remote ones) provide no
-protection for i_size so you will need to use the BKL.
-
-Note: ext2_release() was *the* source of contention on fs-intensive
-loads and dropping BKL on ->release() helps to get rid of that (we still
-grab BKL for cases when we close a file that had been opened r/w, but that
-can and should be done using the internal locking with smaller critical areas).
-Current worst offender is ext2_get_block()...
+mutex or just to use i_size_read() instead.
+Note: this does not protect the file->f_pos against concurrent modifications
+since this is something the userspace has to take care about.
 
-->fasync() is called without BKL protection, and is responsible for
-maintaining the FASYNC bit in filp->f_flags.  Most instances call
-fasync_helper(), which does that maintenance, so it's not normally
-something one needs to worry about.  Return values > 0 will be mapped to
-zero in the VFS layer.
+->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
+Most instances call fasync_helper(), which does that maintenance, so it's
+not normally something one needs to worry about.  Return values > 0 will be
+mapped to zero in the VFS layer.
 
 ->readdir() and ->ioctl() on directories must be changed. Ideally we would
 move ->readdir() to inode_operations and use a separate method for directory
@@ -450,23 +465,11 @@ move ->readdir() to inode_operations and use a separate method for directory
 anything that resembles union-mount we won't have a struct file for all
 components. And there are other reasons why the current interface is a mess...
 
-->ioctl() on regular files is superceded by the ->unlocked_ioctl() that
-doesn't take the BKL.
-
 ->read on directories probably must go away - we should just enforce -EISDIR
 in sys_read() and friends.
 
-->fsync() has i_mutex on inode.
-
 --------------------------- 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 +482,6 @@ 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 +491,6 @@ 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 -----------------------------
@@ -510,12 +502,12 @@ prototypes:
 	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 
 locking rules:
-		BKL	mmap_sem	PageLocked(page)
-open:		no	yes
-close:		no	yes
-fault:		no	yes		can return with page locked
-page_mkwrite:	no	yes		can return with page locked
-access:		no	yes
+		mmap_sem	PageLocked(page)
+open:		yes
+close:		yes
+fault:		yes		can return with page locked
+page_mkwrite:	yes		can return with page locked
+access:		yes
 
 	->fault() is called when a previously not present pte is about
 to be faulted in. The filesystem must find and return the page associated
@@ -542,6 +534,3 @@ VM_IO | VM_PFNMAP VMAs.
 
 (if you break something or notice that it is broken and do not fix it yourself
 - at least put it here)
-
-ipc/shm.c::shm_delete() - may need BKL.
-->read() and ->write() in many drivers are (probably) missing BKL.
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/affs.txt b/Documentation/filesystems/affs.txt
index 2d1524469c2..81ac488e375 100644
--- a/Documentation/filesystems/affs.txt
+++ b/Documentation/filesystems/affs.txt
@@ -216,4 +216,4 @@ due to an incompatibility with the Amiga floppy controller.
 
 If you are interested in an Amiga Emulator for Linux, look at
 
-http://www.freiburg.linux.de/~uae/
+http://web.archive.org/web/*/http://www.freiburg.linux.de/~uae/
diff --git a/Documentation/filesystems/autofs4-mount-control.txt b/Documentation/filesystems/autofs4-mount-control.txt
index 8f78ded4b64..51986bf08a4 100644
--- a/Documentation/filesystems/autofs4-mount-control.txt
+++ b/Documentation/filesystems/autofs4-mount-control.txt
@@ -146,7 +146,7 @@ found to be inadequate, in this case. The Generic Netlink system was
 used for this as raw Netlink would lead to a significant increase in
 complexity. There's no question that the Generic Netlink system is an
 elegant solution for common case ioctl functions but it's not a complete
-replacement probably because it's primary purpose in life is to be a
+replacement probably because its primary purpose in life is to be a
 message bus implementation rather than specifically an ioctl replacement.
 While it would be possible to work around this there is one concern
 that lead to the decision to not use it. This is that the autofs
diff --git a/Documentation/filesystems/befs.txt b/Documentation/filesystems/befs.txt
index 67391a15949..6e49c363938 100644
--- a/Documentation/filesystems/befs.txt
+++ b/Documentation/filesystems/befs.txt
@@ -31,7 +31,7 @@ Current maintainer: Sergey S. Kostyliov <rathamahata@php4.ru>
 
 WHAT IS THIS DRIVER?
 ==================
-This module implements the native filesystem of BeOS <http://www.be.com/>
+This module implements the native filesystem of BeOS http://www.beincorporated.com/ 
 for the linux 2.4.1 and later kernels. Currently it is a read-only
 implementation.
 
@@ -61,7 +61,7 @@ step 2.  Configuration & make kernel
 
 The linux kernel has many compile-time options. Most of them are beyond the
 scope of this document. I suggest the Kernel-HOWTO document as a good general
-reference on this topic. <http://www.linux.com/howto/Kernel-HOWTO.html>
+reference on this topic. http://www.linuxdocs.org/HOWTOs/Kernel-HOWTO-4.html 
 
 However, to use the BeFS module, you must enable it at configure time.
 
diff --git a/Documentation/filesystems/caching/fscache.txt b/Documentation/filesystems/caching/fscache.txt
index a91e2e2095b..770267af5b3 100644
--- a/Documentation/filesystems/caching/fscache.txt
+++ b/Documentation/filesystems/caching/fscache.txt
@@ -343,8 +343,8 @@ This will look something like:
 	[root@andromeda ~]# head /proc/fs/fscache/objects
 	OBJECT   PARENT   STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA       OBJECT_KEY, AUX_DATA
 	======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================
-	   17e4b        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a
-	   1693a        2 ACTV     0   0   0   0  0     0 7b  4 0 8 | NFS.fh           DT  0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a
+	   17e4b        2 ACTV     0   0   0   0  0     0 7b  4 0 0 | NFS.fh           DT  0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a
+	   1693a        2 ACTV     0   0   0   0  0     0 7b  4 0 0 | NFS.fh           DT  0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a
 
 where the first set of columns before the '|' describe the object:
 
@@ -362,7 +362,7 @@ where the first set of columns before the '|' describe the object:
 	EM	Object's event mask
 	EV	Events raised on this object
 	F	Object flags
-	S	Object slow-work work item flags
+	S	Object work item busy state mask (1:pending 2:running)
 
 and the second set of columns describe the object's cookie, if present:
 
@@ -395,8 +395,8 @@ and the following paired letters:
 	w	Show objects that don't have pending writes
 	R	Show objects that have outstanding reads
 	r	Show objects that don't have outstanding reads
-	S	Show objects that have slow work queued
-	s	Show objects that don't have slow work queued
+	S	Show objects that have work queued
+	s	Show objects that don't have work queued
 
 If neither side of a letter pair is given, then both are implied.  For example:
 
diff --git a/Documentation/filesystems/ceph.txt b/Documentation/filesystems/ceph.txt
new file mode 100644
index 00000000000..763d8ebbbeb
--- /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 its 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/configfs/configfs_example_explicit.c b/Documentation/filesystems/configfs/configfs_example_explicit.c
index d428cc9f07f..fd53869f563 100644
--- a/Documentation/filesystems/configfs/configfs_example_explicit.c
+++ b/Documentation/filesystems/configfs/configfs_example_explicit.c
@@ -89,7 +89,7 @@ static ssize_t childless_storeme_write(struct childless *childless,
 	char *p = (char *) page;
 
 	tmp = simple_strtoul(p, &p, 10);
-	if (!p || (*p && (*p != '\n')))
+	if ((*p != '\0') && (*p != '\n'))
 		return -EINVAL;
 
 	if (tmp > INT_MAX)
diff --git a/Documentation/filesystems/dentry-locking.txt b/Documentation/filesystems/dentry-locking.txt
deleted file mode 100644
index 4c0c575a401..00000000000
--- a/Documentation/filesystems/dentry-locking.txt
+++ /dev/null
@@ -1,173 +0,0 @@
-RCU-based dcache locking model
-==============================
-
-On many workloads, the most common operation on dcache is to look up a
-dentry, given a parent dentry and the name of the child. Typically,
-for every open(), stat() etc., the dentry corresponding to the
-pathname will be looked up by walking the tree starting with the first
-component of the pathname and using that dentry along with the next
-component to look up the next level and so on. Since it is a frequent
-operation for workloads like multiuser environments and web servers,
-it is important to optimize this path.
-
-Prior to 2.5.10, dcache_lock was acquired in d_lookup and thus in
-every component during path look-up. Since 2.5.10 onwards, fast-walk
-algorithm changed this by holding the dcache_lock at the beginning and
-walking as many cached path component dentries as possible. This
-significantly decreases the number of acquisition of
-dcache_lock. However it also increases the lock hold time
-significantly and affects performance in large SMP machines. Since
-2.5.62 kernel, dcache has been using a new locking model that uses RCU
-to make dcache look-up lock-free.
-
-The current dcache locking model is not very different from the
-existing dcache locking model. Prior to 2.5.62 kernel, dcache_lock
-protected the hash chain, d_child, d_alias, d_lru lists as well as
-d_inode and several other things like mount look-up. RCU-based changes
-affect only the way the hash chain is protected. For everything else
-the dcache_lock must be taken for both traversing as well as
-updating. The hash chain updates too take the dcache_lock.  The
-significant change is the way d_lookup traverses the hash chain, it
-doesn't acquire the dcache_lock for this and rely on RCU to ensure
-that the dentry has not been *freed*.
-
-
-Dcache locking details
-======================
-
-For many multi-user workloads, open() and stat() on files are very
-frequently occurring operations. Both involve walking of path names to
-find the dentry corresponding to the concerned file. In 2.4 kernel,
-dcache_lock was held during look-up of each path component. Contention
-and cache-line bouncing of this global lock caused significant
-scalability problems. With the introduction of RCU in Linux kernel,
-this was worked around by making the look-up of path components during
-path walking lock-free.
-
-
-Safe lock-free look-up of dcache hash table
-===========================================
-
-Dcache is a complex data structure with the hash table entries also
-linked together in other lists. In 2.4 kernel, dcache_lock protected
-all the lists. We applied RCU only on hash chain walking. The rest of
-the lists are still protected by dcache_lock.  Some of the important
-changes are :
-
-1. The deletion from hash chain is done using hlist_del_rcu() macro
-   which doesn't initialize next pointer of the deleted dentry and
-   this allows us to walk safely lock-free while a deletion is
-   happening.
-
-2. Insertion of a dentry into the hash table is done using
-   hlist_add_head_rcu() which take care of ordering the writes - the
-   writes to the dentry must be visible before the dentry is
-   inserted. This works in conjunction with hlist_for_each_rcu() while
-   walking the hash chain. The only requirement is that all
-   initialization to the dentry must be done before
-   hlist_add_head_rcu() since we don't have dcache_lock protection
-   while traversing the hash chain. This isn't different from the
-   existing code.
-
-3. The dentry looked up without holding dcache_lock by cannot be
-   returned for walking if it is unhashed. It then may have a NULL
-   d_inode or other bogosity since RCU doesn't protect the other
-   fields in the dentry. We therefore use a flag DCACHE_UNHASHED to
-   indicate unhashed dentries and use this in conjunction with a
-   per-dentry lock (d_lock). Once looked up without the dcache_lock,
-   we acquire the per-dentry lock (d_lock) and check if the dentry is
-   unhashed. If so, the look-up is failed. If not, the reference count
-   of the dentry is increased and the dentry is returned.
-
-4. Once a dentry is looked up, it must be ensured during the path walk
-   for that component it doesn't go away. In pre-2.5.10 code, this was
-   done holding a reference to the dentry. dcache_rcu does the same.
-   In some sense, dcache_rcu path walking looks like the pre-2.5.10
-   version.
-
-5. All dentry hash chain updates must take the dcache_lock as well as
-   the per-dentry lock in that order. dput() does this to ensure that
-   a dentry that has just been looked up in another CPU doesn't get
-   deleted before dget() can be done on it.
-
-6. There are several ways to do reference counting of RCU protected
-   objects. One such example is in ipv4 route cache where deferred
-   freeing (using call_rcu()) is done as soon as the reference count
-   goes to zero. This cannot be done in the case of dentries because
-   tearing down of dentries require blocking (dentry_iput()) which
-   isn't supported from RCU callbacks. Instead, tearing down of
-   dentries happen synchronously in dput(), but actual freeing happens
-   later when RCU grace period is over. This allows safe lock-free
-   walking of the hash chains, but a matched dentry may have been
-   partially torn down. The checking of DCACHE_UNHASHED flag with
-   d_lock held detects such dentries and prevents them from being
-   returned from look-up.
-
-
-Maintaining POSIX rename semantics
-==================================
-
-Since look-up of dentries is lock-free, it can race against a
-concurrent rename operation. For example, during rename of file A to
-B, look-up of either A or B must succeed.  So, if look-up of B happens
-after A has been removed from the hash chain but not added to the new
-hash chain, it may fail.  Also, a comparison while the name is being
-written concurrently by a rename may result in false positive matches
-violating rename semantics.  Issues related to race with rename are
-handled as described below :
-
-1. Look-up can be done in two ways - d_lookup() which is safe from
-   simultaneous renames and __d_lookup() which is not.  If
-   __d_lookup() fails, it must be followed up by a d_lookup() to
-   correctly determine whether a dentry is in the hash table or
-   not. d_lookup() protects look-ups using a sequence lock
-   (rename_lock).
-
-2. The name associated with a dentry (d_name) may be changed if a
-   rename is allowed to happen simultaneously. To avoid memcmp() in
-   __d_lookup() go out of bounds due to a rename and false positive
-   comparison, the name comparison is done while holding the
-   per-dentry lock. This prevents concurrent renames during this
-   operation.
-
-3. Hash table walking during look-up may move to a different bucket as
-   the current dentry is moved to a different bucket due to rename.
-   But we use hlists in dcache hash table and they are
-   null-terminated.  So, even if a dentry moves to a different bucket,
-   hash chain walk will terminate. [with a list_head list, it may not
-   since termination is when the list_head in the original bucket is
-   reached].  Since we redo the d_parent check and compare name while
-   holding d_lock, lock-free look-up will not race against d_move().
-
-4. There can be a theoretical race when a dentry keeps coming back to
-   original bucket due to double moves. Due to this look-up may
-   consider that it has never moved and can end up in a infinite loop.
-   But this is not any worse that theoretical livelocks we already
-   have in the kernel.
-
-
-Important guidelines for filesystem developers related to dcache_rcu
-====================================================================
-
-1. Existing dcache interfaces (pre-2.5.62) exported to filesystem
-   don't change. Only dcache internal implementation changes. However
-   filesystems *must not* delete from the dentry hash chains directly
-   using the list macros like allowed earlier. They must use dcache
-   APIs like d_drop() or __d_drop() depending on the situation.
-
-2. d_flags is now protected by a per-dentry lock (d_lock). All access
-   to d_flags must be protected by it.
-
-3. For a hashed dentry, checking of d_count needs to be protected by
-   d_lock.
-
-
-Papers and other documentation on dcache locking
-================================================
-
-1. Scaling dcache with RCU (http://linuxjournal.com/article.php?sid=7124).
-
-2. http://lse.sourceforge.net/locking/dcache/dcache.html
-
-
-
diff --git a/Documentation/filesystems/dlmfs.txt b/Documentation/filesystems/dlmfs.txt
index c50bbb2d52b..1b528b2ad80 100644
--- a/Documentation/filesystems/dlmfs.txt
+++ b/Documentation/filesystems/dlmfs.txt
@@ -47,7 +47,7 @@ You'll want to start heartbeating on a volume which all the nodes in
 your lockspace can access. The easiest way to do this is via
 ocfs2_hb_ctl (distributed with ocfs2-tools). Right now it requires
 that an OCFS2 file system be in place so that it can automatically
-find it's heartbeat area, though it will eventually support heartbeat
+find its heartbeat area, though it will eventually support heartbeat
 against raw disks.
 
 Please see the ocfs2_hb_ctl and mkfs.ocfs2 manual pages distributed
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/ext3.txt b/Documentation/filesystems/ext3.txt
index 867c5b50cb4..272f80d5f96 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -59,8 +59,19 @@ commit=nrsec	(*)	Ext3 can be told to sync all its data and metadata
 			Setting it to very large values will improve
 			performance.
 
-barrier=1		This enables/disables barriers.  barrier=0 disables
-			it, barrier=1 enables it.
+barrier=<0(*)|1>	This enables/disables the use of write barriers in
+barrier			the jbd code.  barrier=0 disables, barrier=1 enables.
+nobarrier	(*)	This also requires an IO stack which can support
+			barriers, and if jbd gets an error on a barrier
+			write, it will disable again with a warning.
+			Write barriers enforce proper on-disk ordering
+			of journal commits, making volatile disk write caches
+			safe to use, at some performance penalty.  If
+			your disks are battery-backed in one way or another,
+			disabling barriers may safely improve performance.
+			The mount options "barrier" and "nobarrier" can
+			also be used to enable or disable barriers, for
+			consistency with other ext3 mount options.
 
 orlov		(*)	This enables the new Orlov block allocator. It is
 			enabled by default.
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index e1def1786e5..6ab9442d7ee 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -353,6 +353,20 @@ noauto_da_alloc		replacing existing files via patterns such as
 			system crashes before the delayed allocation
 			blocks are forced to disk.
 
+noinit_itable		Do not initialize any uninitialized inode table
+			blocks in the background.  This feature may be
+			used by installation CD's so that the install
+			process can complete as quickly as possible; the
+			inode table initialization process would then be
+			deferred until the next time the  file system
+			is unmounted.
+
+init_itable=n		The lazy itable init code will wait n times the
+			number of milliseconds it took to zero out the
+			previous block group's inode table.  This
+			minimizes the impact on the systme performance
+			while file system's inode table is being initialized.
+
 discard		Controls whether ext4 should issue discard/TRIM
 nodiscard(*)		commands to the underlying block device when
 			blocks are freed.  This is useful for SSD devices
diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt
index 606233cd461..1b805a0efbb 100644
--- a/Documentation/filesystems/fiemap.txt
+++ b/Documentation/filesystems/fiemap.txt
@@ -38,7 +38,7 @@ flags, it will return EBADR and the contents of fm_flags will contain
 the set of flags which caused the error. If the kernel is compatible
 with all flags passed, the contents of fm_flags will be unmodified.
 It is up to userspace to determine whether rejection of a particular
-flag is fatal to it's operation. This scheme is intended to allow the
+flag is fatal to its operation. This scheme is intended to allow the
 fiemap interface to grow in the future but without losing
 compatibility with old software.
 
@@ -56,7 +56,7 @@ If this flag is set, the kernel will sync the file before mapping extents.
 
 * FIEMAP_FLAG_XATTR
 If this flag is set, the extents returned will describe the inodes
-extended attribute lookup tree, instead of it's data tree.
+extended attribute lookup tree, instead of its data tree.
 
 
 Extent Mapping
@@ -89,7 +89,7 @@ struct fiemap_extent {
 };
 
 All offsets and lengths are in bytes and mirror those on disk.  It is valid
-for an extents logical offset to start before the request or it's logical
+for an extents logical offset to start before the request or its logical
 length to extend past the request.  Unless FIEMAP_EXTENT_NOT_ALIGNED is
 returned, fe_logical, fe_physical, and fe_length will be aligned to the
 block size of the file system.  With the exception of extents flagged as
@@ -125,7 +125,7 @@ been allocated for the file yet.
 
 * FIEMAP_EXTENT_DELALLOC
   - This will also set FIEMAP_EXTENT_UNKNOWN.
-Delayed allocation - while there is data for this extent, it's
+Delayed allocation - while there is data for this extent, its
 physical location has not been allocated yet.
 
 * FIEMAP_EXTENT_ENCODED
@@ -159,7 +159,7 @@ Data is located within a meta data block.
 Data is packed into a block with data from other files.
 
 * FIEMAP_EXTENT_UNWRITTEN
-Unwritten extent - the extent is allocated but it's data has not been
+Unwritten extent - the extent is allocated but its data has not been
 initialized.  This indicates the extent's data will be all zero if read
 through the filesystem but the contents are undefined if read directly from
 the device.
@@ -176,7 +176,7 @@ VFS -> File System Implementation
 
 File systems wishing to support fiemap must implement a ->fiemap callback on
 their inode_operations structure. The fs ->fiemap call is responsible for
-defining it's set of supported fiemap flags, and calling a helper function on
+defining its set of supported fiemap flags, and calling a helper function on
 each discovered extent:
 
 struct inode_operations {
diff --git a/Documentation/filesystems/fuse.txt b/Documentation/filesystems/fuse.txt
index 397a41adb4c..13af4a49e7d 100644
--- a/Documentation/filesystems/fuse.txt
+++ b/Documentation/filesystems/fuse.txt
@@ -91,7 +91,7 @@ Mount options
 'default_permissions'
 
   By default FUSE doesn't check file access permissions, the
-  filesystem is free to implement it's access policy or leave it to
+  filesystem is free to implement its access policy or leave it to
   the underlying file access mechanism (e.g. in case of network
   filesystems).  This option enables permission checking, restricting
   access based on file mode.  It is usually useful together with the
@@ -171,7 +171,7 @@ or may honor them by sending a reply to the _original_ request, with
 the error set to EINTR.
 
 It is also possible that there's a race between processing the
-original request and it's INTERRUPT request.  There are two possibilities:
+original request and its INTERRUPT request.  There are two possibilities:
 
   1) The INTERRUPT request is processed before the original request is
      processed
diff --git a/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.txt
index 5e3ab8f3bef..0b59c020091 100644
--- a/Documentation/filesystems/gfs2.txt
+++ b/Documentation/filesystems/gfs2.txt
@@ -1,7 +1,7 @@
 Global File System
 ------------------
 
-http://sources.redhat.com/cluster/
+http://sources.redhat.com/cluster/wiki/
 
 GFS is a cluster file system. It allows a cluster of computers to
 simultaneously use a block device that is shared between them (with FC,
@@ -36,11 +36,11 @@ GFS2 is not on-disk compatible with previous versions of GFS, but it
 is pretty close.
 
 The following man pages can be found at the URL above:
-  fsck.gfs2	to repair a filesystem
-  gfs2_grow	to expand a filesystem online
-  gfs2_jadd	to add journals to a filesystem online
-  gfs2_tool	to manipulate, examine and tune a filesystem
+  fsck.gfs2		to repair a filesystem
+  gfs2_grow		to expand a filesystem online
+  gfs2_jadd		to add journals to a filesystem online
+  gfs2_tool		to manipulate, examine and tune a filesystem
   gfs2_quota	to examine and change quota values in a filesystem
   gfs2_convert	to convert a gfs filesystem to gfs2 in-place
   mount.gfs2	to help mount(8) mount a filesystem
-  mkfs.gfs2	to make a filesystem
+  mkfs.gfs2		to make a filesystem
diff --git a/Documentation/filesystems/hpfs.txt b/Documentation/filesystems/hpfs.txt
index fa45c3baed9..74630bd504f 100644
--- a/Documentation/filesystems/hpfs.txt
+++ b/Documentation/filesystems/hpfs.txt
@@ -103,7 +103,7 @@ to analyze or change OS2SYS.INI.
 Codepages
 
 HPFS can contain several uppercasing tables for several codepages and each
-file has a pointer to codepage it's name is in. However OS/2 was created in
+file has a pointer to codepage its name is in. However OS/2 was created in
 America where people don't care much about codepages and so multiple codepages
 support is quite buggy. I have Czech OS/2 working in codepage 852 on my disk.
 Once I booted English OS/2 working in cp 850 and I created a file on my 852
diff --git a/Documentation/filesystems/isofs.txt b/Documentation/filesystems/isofs.txt
index 3c367c3b360..ba0a93384de 100644
--- a/Documentation/filesystems/isofs.txt
+++ b/Documentation/filesystems/isofs.txt
@@ -41,7 +41,7 @@ Mount options unique to the isofs filesystem.
   sbsector=xxx  Session begins from sector xxx
 
 Recommended documents about ISO 9660 standard are located at:
-http://www.y-adagio.com/public/standards/iso_cdromr/tocont.htm
+http://www.y-adagio.com/
 ftp://ftp.ecma.ch/ecma-st/Ecma-119.pdf
 Quoting from the PDF "This 2nd Edition of Standard ECMA-119 is technically 
 identical with ISO 9660.", so it is a valid and gratis substitute of the
diff --git a/Documentation/filesystems/logfs.txt b/Documentation/filesystems/logfs.txt
new file mode 100644
index 00000000000..bca42c22a14
--- /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 separated
+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 separate 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
+separate long-living data from short-living data and thereby reduce
+the GC overhead later.  Each type of distinc life expectency (vim) can
+have a separate 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/00-INDEX b/Documentation/filesystems/nfs/00-INDEX
index 2f68cd68876..a57e12411d2 100644
--- a/Documentation/filesystems/nfs/00-INDEX
+++ b/Documentation/filesystems/nfs/00-INDEX
@@ -12,5 +12,9 @@ nfs-rdma.txt
 	- how to install and setup the Linux NFS/RDMA client and server software
 nfsroot.txt
 	- short guide on setting up a diskless box with NFS root filesystem.
+pnfs.txt
+	- short explanation of some of the internals of the pnfs client code
 rpc-cache.txt
 	- introduction to the caching mechanisms in the sunrpc layer.
+idmapper.txt
+	- information for configuring request-keys to be used by idmapper
diff --git a/Documentation/filesystems/nfs/idmapper.txt b/Documentation/filesystems/nfs/idmapper.txt
new file mode 100644
index 00000000000..b9b4192ea8b
--- /dev/null
+++ b/Documentation/filesystems/nfs/idmapper.txt
@@ -0,0 +1,67 @@
+
+=========
+ID Mapper
+=========
+Id mapper is used by NFS to translate user and group ids into names, and to
+translate user and group names into ids.  Part of this translation involves
+performing an upcall to userspace to request the information.  Id mapper will
+user request-key to perform this upcall and cache the result.  The program
+/usr/sbin/nfs.idmap should be called by request-key, and will perform the
+translation and initialize a key with the resulting information.
+
+ NFS_USE_NEW_IDMAPPER must be selected when configuring the kernel to use this
+ feature.
+
+===========
+Configuring
+===========
+The file /etc/request-key.conf will need to be modified so /sbin/request-key can
+direct the upcall.  The following line should be added:
+
+#OP	TYPE	DESCRIPTION	CALLOUT INFO	PROGRAM ARG1 ARG2 ARG3 ...
+#======	=======	===============	===============	===============================
+create	id_resolver	*	*		/usr/sbin/nfs.idmap %k %d 600
+
+This will direct all id_resolver requests to the program /usr/sbin/nfs.idmap.
+The last parameter, 600, defines how many seconds into the future the key will
+expire.  This parameter is optional for /usr/sbin/nfs.idmap.  When the timeout
+is not specified, nfs.idmap will default to 600 seconds.
+
+id mapper uses for key descriptions:
+	  uid:  Find the UID for the given user
+	  gid:  Find the GID for the given group
+	 user:  Find the user  name for the given UID
+	group:  Find the group name for the given GID
+
+You can handle any of these individually, rather than using the generic upcall
+program.  If you would like to use your own program for a uid lookup then you
+would edit your request-key.conf so it look similar to this:
+
+#OP	TYPE	DESCRIPTION	CALLOUT INFO	PROGRAM ARG1 ARG2 ARG3 ...
+#======	=======	===============	===============	===============================
+create	id_resolver	uid:*	*		/some/other/program %k %d 600
+create	id_resolver	*	*		/usr/sbin/nfs.idmap %k %d 600
+
+Notice that the new line was added above the line for the generic program.
+request-key will find the first matching line and corresponding program.  In
+this case, /some/other/program will handle all uid lookups and
+/usr/sbin/nfs.idmap will handle gid, user, and group lookups.
+
+See <file:Documentation/keys-request-keys.txt> for more information about the
+request-key function.
+
+
+=========
+nfs.idmap
+=========
+nfs.idmap is designed to be called by request-key, and should not be run "by
+hand".  This program takes two arguments, a serialized key and a key
+description.  The serialized key is first converted into a key_serial_t, and
+then passed as an argument to keyctl_instantiate (both are part of keyutils.h).
+
+The actual lookups are performed by functions found in nfsidmap.h.  nfs.idmap
+determines the correct function to call by looking at the first part of the
+description string.  For example, a uid lookup description will appear as
+"uid:user@domain".
+
+nfs.idmap will return 0 if the key was instantiated, and non-zero otherwise.
diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index 1bd0d0c0517..04884914a1c 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
@@ -138,7 +137,7 @@ NS*| OPENATTR             | OPT        |              | Section 18.17  |
    | READ                 | REQ        |              | Section 18.22  |
    | READDIR              | REQ        |              | Section 18.23  |
    | READLINK             | OPT        |              | Section 18.24  |
-NS | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
+   | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
    | RELEASE_LOCKOWNER    | MNI        |              | N/A            |
    | REMOVE               | REQ        |              | Section 18.25  |
    | RENAME               | REQ        |              | Section 18.26  |
diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt
index 3ba0b945aaf..90c71c6f0d0 100644
--- a/Documentation/filesystems/nfs/nfsroot.txt
+++ b/Documentation/filesystems/nfs/nfsroot.txt
@@ -124,6 +124,8 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>
 
   <hostname>	Name of the client. May be supplied by autoconfiguration,
   		but its absence will not trigger autoconfiguration.
+		If specified and DHCP is used, the user provided hostname will
+		be carried in the DHCP request to hopefully update DNS record.
 
   		Default: Client IP address is used in ASCII notation.
 
@@ -157,6 +159,28 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>
                 Default: any
 
 
+nfsrootdebug
+
+  This parameter enables debugging messages to appear in the kernel
+  log at boot time so that administrators can verify that the correct
+  NFS mount options, server address, and root path are passed to the
+  NFS client.
+
+
+rdinit=<executable file>
+
+  To specify which file contains the program that starts system
+  initialization, administrators can use this command line parameter.
+  The default value of this parameter is "/init".  If the specified
+  file exists and the kernel can execute it, root filesystem related
+  kernel command line parameters, including `nfsroot=', are ignored.
+
+  A description of the process of mounting the root file system can be
+  found in:
+
+    Documentation/early-userspace/README
+
+
 
 
 3.) Boot Loader
diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt
new file mode 100644
index 00000000000..bc0b9cfe095
--- /dev/null
+++ b/Documentation/filesystems/nfs/pnfs.txt
@@ -0,0 +1,48 @@
+Reference counting in pnfs:
+==========================
+
+The are several inter-related caches.  We have layouts which can
+reference multiple devices, each of which can reference multiple data servers.
+Each data server can be referenced by multiple devices.  Each device
+can be referenced by multiple layouts.  To keep all of this straight,
+we need to reference count.
+
+
+struct pnfs_layout_hdr
+----------------------
+The on-the-wire command LAYOUTGET corresponds to struct
+pnfs_layout_segment, usually referred to by the variable name lseg.
+Each nfs_inode may hold a pointer to a cache of of these layout
+segments in nfsi->layout, of type struct pnfs_layout_hdr.
+
+We reference the header for the inode pointing to it, across each
+outstanding RPC call that references it (LAYOUTGET, LAYOUTRETURN,
+LAYOUTCOMMIT), and for each lseg held within.
+
+Each header is also (when non-empty) put on a list associated with
+struct nfs_client (cl_layouts).  Being put on this list does not bump
+the reference count, as the layout is kept around by the lseg that
+keeps it in the list.
+
+deviceid_cache
+--------------
+lsegs reference device ids, which are resolved per nfs_client and
+layout driver type.  The device ids are held in a RCU cache (struct
+nfs4_deviceid_cache).  The cache itself is referenced across each
+mount.  The entries (struct nfs4_deviceid) themselves are held across
+the lifetime of each lseg referencing them.
+
+RCU is used because the deviceid is basically a write once, read many
+data structure.  The hlist size of 32 buckets needs better
+justification, but seems reasonable given that we can have multiple
+deviceid's per filesystem, and multiple filesystems per nfs_client.
+
+The hash code is copied from the nfsd code base.  A discussion of
+hashing and variations of this algorithm can be found at:
+http://groups.google.com/group/comp.lang.c/browse_thread/thread/9522965e2b8d3809
+
+data server cache
+-----------------
+file driver devices refer to data servers, which are kept in a module
+level cache.  Its reference is held over the lifetime of the deviceid
+pointing to it.
diff --git a/Documentation/filesystems/nfs/rpc-cache.txt b/Documentation/filesystems/nfs/rpc-cache.txt
index 8a382bea680..ebcaaee2161 100644
--- a/Documentation/filesystems/nfs/rpc-cache.txt
+++ b/Documentation/filesystems/nfs/rpc-cache.txt
@@ -185,7 +185,7 @@ failed lookup meant a definite 'no'.
 request/response format
 -----------------------
 
-While each cache is free to use it's own format for requests
+While each cache is free to use its own format for requests
 and responses over channel, the following is recommended as
 appropriate and support routines are available to help:
 Each request or response record should be printable ASCII
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index 839efd8a8a8..d5c0cef38a7 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -49,9 +49,12 @@ Mount options
 NILFS2 supports the following mount options:
 (*) == default
 
-nobarrier		Disables barriers.
-errors=continue(*)	Keep going on a filesystem error.
-errors=remount-ro	Remount the filesystem read-only on an error.
+barrier(*)		This enables/disables the use of write barriers.  This
+nobarrier		requires an IO stack which can support barriers, and
+			if nilfs gets an error on a barrier write, it will
+			disable again with a warning.
+errors=continue		Keep going on a filesystem error.
+errors=remount-ro(*)	Remount the filesystem read-only on an error.
 errors=panic		Panic and halt the machine if an error occurs.
 cp=n			Specify the checkpoint-number of the snapshot to be
 			mounted.  Checkpoints and snapshots are listed by lscp
@@ -74,6 +77,10 @@ norecovery		Disable recovery of the filesystem on mount.
 			This disables every write access on the device for
 			read-only mounts or snapshots.  This option will fail
 			for r/w mounts on an unclean volume.
+discard			This enables/disables the use of discard/TRIM commands.
+nodiscard(*)		The discard/TRIM commands are sent to the underlying
+			block device when blocks are freed.  This is useful
+			for SSD devices and sparse/thinly-provisioned LUNs.
 
 NILFS2 usage
 ============
diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt
index ac2a261c5f7..6ef8cf3bc9a 100644
--- a/Documentation/filesystems/ntfs.txt
+++ b/Documentation/filesystems/ntfs.txt
@@ -457,6 +457,9 @@ ChangeLog
 
 Note, a technical ChangeLog aimed at kernel hackers is in fs/ntfs/ChangeLog.
 
+2.1.30:
+	- Fix writev() (it kept writing the first segment over and over again
+	  instead of moving onto subsequent segments).
 2.1.29:
 	- Fix a deadlock when mounting read-write.
 2.1.28:
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index c58b9f5ba00..5393e661169 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -80,3 +80,17 @@ user_xattr	(*)	Enables Extended User Attributes.
 nouser_xattr		Disables Extended User Attributes.
 acl			Enables POSIX Access Control Lists support.
 noacl		(*)	Disables POSIX Access Control Lists support.
+resv_level=2	(*)	Set how agressive allocation reservations will be.
+			Valid values are between 0 (reservations off) to 8
+			(maximum space for reservations).
+dir_resv_level=	(*)	By default, directory reservations will scale with file
+			reservations - users should rarely need to change this
+			value. If allocation reservations are turned off, this
+			option will have no effect.
+coherency=full  (*)	Disallow concurrent O_DIRECT writes, cluster inode
+			lock will be taken to force other nodes drop cache,
+			therefore full cluster coherency is guaranteed even
+			for O_DIRECT writes.
+coherency=buffered	Allow concurrent O_DIRECT writes without EX lock among
+			nodes, which gains high performance at risk of getting
+			stale data on other nodes.
diff --git a/Documentation/filesystems/path-lookup.txt b/Documentation/filesystems/path-lookup.txt
new file mode 100644
index 00000000000..eb59c8b44be
--- /dev/null
+++ b/Documentation/filesystems/path-lookup.txt
@@ -0,0 +1,382 @@
+Path walking and name lookup locking
+====================================
+
+Path resolution is the finding a dentry corresponding to a path name string, by
+performing a path walk. Typically, for every open(), stat() etc., the path name
+will be resolved. Paths are resolved by walking the namespace tree, starting
+with the first component of the pathname (eg. root or cwd) with a known dentry,
+then finding the child of that dentry, which is named the next component in the
+path string. Then repeating the lookup from the child dentry and finding its
+child with the next element, and so on.
+
+Since it is a frequent operation for workloads like multiuser environments and
+web servers, it is important to optimize this code.
+
+Path walking synchronisation history:
+Prior to 2.5.10, dcache_lock was acquired in d_lookup (dcache hash lookup) and
+thus in every component during path look-up. Since 2.5.10 onwards, fast-walk
+algorithm changed this by holding the dcache_lock at the beginning and walking
+as many cached path component dentries as possible. This significantly
+decreases the number of acquisition of dcache_lock. However it also increases
+the lock hold time significantly and affects performance in large SMP machines.
+Since 2.5.62 kernel, dcache has been using a new locking model that uses RCU to
+make dcache look-up lock-free.
+
+All the above algorithms required taking a lock and reference count on the
+dentry that was looked up, so that may be used as the basis for walking the
+next path element. This is inefficient and unscalable. It is inefficient
+because of the locks and atomic operations required for every dentry element
+slows things down. It is not scalable because many parallel applications that
+are path-walk intensive tend to do path lookups starting from a common dentry
+(usually, the root "/" or current working directory). So contention on these
+common path elements causes lock and cacheline queueing.
+
+Since 2.6.38, RCU is used to make a significant part of the entire path walk
+(including dcache look-up) completely "store-free" (so, no locks, atomics, or
+even stores into cachelines of common dentries). This is known as "rcu-walk"
+path walking.
+
+Path walking overview
+=====================
+
+A name string specifies a start (root directory, cwd, fd-relative) and a
+sequence of elements (directory entry names), which together refer to a path in
+the namespace. A path is represented as a (dentry, vfsmount) tuple. The name
+elements are sub-strings, seperated by '/'.
+
+Name lookups will want to find a particular path that a name string refers to
+(usually the final element, or parent of final element). This is done by taking
+the path given by the name's starting point (which we know in advance -- eg.
+current->fs->cwd or current->fs->root) as the first parent of the lookup. Then
+iteratively for each subsequent name element, look up the child of the current
+parent with the given name and if it is not the desired entry, make it the
+parent for the next lookup.
+
+A parent, of course, must be a directory, and we must have appropriate
+permissions on the parent inode to be able to walk into it.
+
+Turning the child into a parent for the next lookup requires more checks and
+procedures. Symlinks essentially substitute the symlink name for the target
+name in the name string, and require some recursive path walking.  Mount points
+must be followed into (thus changing the vfsmount that subsequent path elements
+refer to), switching from the mount point path to the root of the particular
+mounted vfsmount. These behaviours are variously modified depending on the
+exact path walking flags.
+
+Path walking then must, broadly, do several particular things:
+- find the start point of the walk;
+- perform permissions and validity checks on inodes;
+- perform dcache hash name lookups on (parent, name element) tuples;
+- traverse mount points;
+- traverse symlinks;
+- lookup and create missing parts of the path on demand.
+
+Safe store-free look-up of dcache hash table
+============================================
+
+Dcache name lookup
+------------------
+In order to lookup a dcache (parent, name) tuple, we take a hash on the tuple
+and use that to select a bucket in the dcache-hash table. The list of entries
+in that bucket is then walked, and we do a full comparison of each entry
+against our (parent, name) tuple.
+
+The hash lists are RCU protected, so list walking is not serialised with
+concurrent updates (insertion, deletion from the hash). This is a standard RCU
+list application with the exception of renames, which will be covered below.
+
+Parent and name members of a dentry, as well as its membership in the dcache
+hash, and its inode are protected by the per-dentry d_lock spinlock. A
+reference is taken on the dentry (while the fields are verified under d_lock),
+and this stabilises its d_inode pointer and actual inode. This gives a stable
+point to perform the next step of our path walk against.
+
+These members are also protected by d_seq seqlock, although this offers
+read-only protection and no durability of results, so care must be taken when
+using d_seq for synchronisation (see seqcount based lookups, below).
+
+Renames
+-------
+Back to the rename case. In usual RCU protected lists, the only operations that
+will happen to an object is insertion, and then eventually removal from the
+list. The object will not be reused until an RCU grace period is complete.
+This ensures the RCU list traversal primitives can run over the object without
+problems (see RCU documentation for how this works).
+
+However when a dentry is renamed, its hash value can change, requiring it to be
+moved to a new hash list. Allocating and inserting a new alias would be
+expensive and also problematic for directory dentries. Latency would be far to
+high to wait for a grace period after removing the dentry and before inserting
+it in the new hash bucket. So what is done is to insert the dentry into the
+new list immediately.
+
+However, when the dentry's list pointers are updated to point to objects in the
+new list before waiting for a grace period, this can result in a concurrent RCU
+lookup of the old list veering off into the new (incorrect) list and missing
+the remaining dentries on the list.
+
+There is no fundamental problem with walking down the wrong list, because the
+dentry comparisons will never match. However it is fatal to miss a matching
+dentry. So a seqlock is used to detect when a rename has occurred, and so the
+lookup can be retried.
+
+         1      2      3
+        +---+  +---+  +---+
+hlist-->| N-+->| N-+->| N-+->
+head <--+-P |<-+-P |<-+-P |
+        +---+  +---+  +---+
+
+Rename of dentry 2 may require it deleted from the above list, and inserted
+into a new list. Deleting 2 gives the following list.
+
+         1             3
+        +---+         +---+     (don't worry, the longer pointers do not
+hlist-->| N-+-------->| N-+->    impose a measurable performance overhead
+head <--+-P |<--------+-P |      on modern CPUs)
+        +---+         +---+
+          ^      2      ^
+          |    +---+    |
+          |    | N-+----+
+          +----+-P |
+               +---+
+
+This is a standard RCU-list deletion, which leaves the deleted object's
+pointers intact, so a concurrent list walker that is currently looking at
+object 2 will correctly continue to object 3 when it is time to traverse the
+next object.
+
+However, when inserting object 2 onto a new list, we end up with this:
+
+         1             3
+        +---+         +---+
+hlist-->| N-+-------->| N-+->
+head <--+-P |<--------+-P |
+        +---+         +---+
+                 2
+               +---+
+               | N-+---->
+          <----+-P |
+               +---+
+
+Because we didn't wait for a grace period, there may be a concurrent lookup
+still at 2. Now when it follows 2's 'next' pointer, it will walk off into
+another list without ever having checked object 3.
+
+A related, but distinctly different, issue is that of rename atomicity versus
+lookup operations. If a file is renamed from 'A' to 'B', a lookup must only
+find either 'A' or 'B'. So if a lookup of 'A' returns NULL, a subsequent lookup
+of 'B' must succeed (note the reverse is not true).
+
+Between deleting the dentry from the old hash list, and inserting it on the new
+hash list, a lookup may find neither 'A' nor 'B' matching the dentry. The same
+rename seqlock is also used to cover this race in much the same way, by
+retrying a negative lookup result if a rename was in progress.
+
+Seqcount based lookups
+----------------------
+In refcount based dcache lookups, d_lock is used to serialise access to
+the dentry, stabilising it while comparing its name and parent and then
+taking a reference count (the reference count then gives a stable place to
+start the next part of the path walk from).
+
+As explained above, we would like to do path walking without taking locks or
+reference counts on intermediate dentries along the path. To do this, a per
+dentry seqlock (d_seq) is used to take a "coherent snapshot" of what the dentry
+looks like (its name, parent, and inode). That snapshot is then used to start
+the next part of the path walk. When loading the coherent snapshot under d_seq,
+care must be taken to load the members up-front, and use those pointers rather
+than reloading from the dentry later on (otherwise we'd have interesting things
+like d_inode going NULL underneath us, if the name was unlinked).
+
+Also important is to avoid performing any destructive operations (pretty much:
+no non-atomic stores to shared data), and to recheck the seqcount when we are
+"done" with the operation. Retry or abort if the seqcount does not match.
+Avoiding destructive or changing operations means we can easily unwind from
+failure.
+
+What this means is that a caller, provided they are holding RCU lock to
+protect the dentry object from disappearing, can perform a seqcount based
+lookup which does not increment the refcount on the dentry or write to
+it in any way. This returned dentry can be used for subsequent operations,
+provided that d_seq is rechecked after that operation is complete.
+
+Inodes are also rcu freed, so the seqcount lookup dentry's inode may also be
+queried for permissions.
+
+With this two parts of the puzzle, we can do path lookups without taking
+locks or refcounts on dentry elements.
+
+RCU-walk path walking design
+============================
+
+Path walking code now has two distinct modes, ref-walk and rcu-walk. ref-walk
+is the traditional[*] way of performing dcache lookups using d_lock to
+serialise concurrent modifications to the dentry and take a reference count on
+it. ref-walk is simple and obvious, and may sleep, take locks, etc while path
+walking is operating on each dentry. rcu-walk uses seqcount based dentry
+lookups, and can perform lookup of intermediate elements without any stores to
+shared data in the dentry or inode. rcu-walk can not be applied to all cases,
+eg. if the filesystem must sleep or perform non trivial operations, rcu-walk
+must be switched to ref-walk mode.
+
+[*] RCU is still used for the dentry hash lookup in ref-walk, but not the full
+    path walk.
+
+Where ref-walk uses a stable, refcounted ``parent'' to walk the remaining
+path string, rcu-walk uses a d_seq protected snapshot. When looking up a
+child of this parent snapshot, we open d_seq critical section on the child
+before closing d_seq critical section on the parent. This gives an interlocking
+ladder of snapshots to walk down.
+
+
+     proc 101
+      /----------------\
+     / comm:    "vi"    \
+    /  fs.root: dentry0  \
+    \  fs.cwd:  dentry2  /
+     \                  /
+      \----------------/
+
+So when vi wants to open("/home/npiggin/test.c", O_RDWR), then it will
+start from current->fs->root, which is a pinned dentry. Alternatively,
+"./test.c" would start from cwd; both names refer to the same path in
+the context of proc101.
+
+     dentry 0
+    +---------------------+   rcu-walk begins here, we note d_seq, check the
+    | name:    "/"        |   inode's permission, and then look up the next
+    | inode:   10         |   path element which is "home"...
+    | children:"home", ...|
+    +---------------------+
+              |
+     dentry 1 V
+    +---------------------+   ... which brings us here. We find dentry1 via
+    | name:    "home"     |   hash lookup, then note d_seq and compare name
+    | inode:   678        |   string and parent pointer. When we have a match,
+    | children:"npiggin"  |   we now recheck the d_seq of dentry0. Then we
+    +---------------------+   check inode and look up the next element.
+              |
+     dentry2  V
+    +---------------------+   Note: if dentry0 is now modified, lookup is
+    | name:    "npiggin"  |   not necessarily invalid, so we need only keep a
+    | inode:   543        |   parent for d_seq verification, and grandparents
+    | children:"a.c", ... |   can be forgotten.
+    +---------------------+
+              |
+     dentry3  V
+    +---------------------+   At this point we have our destination dentry.
+    | name:    "a.c"      |   We now take its d_lock, verify d_seq of this
+    | inode:   14221      |   dentry. If that checks out, we can increment
+    | children:NULL       |   its refcount because we're holding d_lock.
+    +---------------------+
+
+Taking a refcount on a dentry from rcu-walk mode, by taking its d_lock,
+re-checking its d_seq, and then incrementing its refcount is called
+"dropping rcu" or dropping from rcu-walk into ref-walk mode.
+
+It is, in some sense, a bit of a house of cards. If the seqcount check of the
+parent snapshot fails, the house comes down, because we had closed the d_seq
+section on the grandparent, so we have nothing left to stand on. In that case,
+the path walk must be fully restarted (which we do in ref-walk mode, to avoid
+live locks). It is costly to have a full restart, but fortunately they are
+quite rare.
+
+When we reach a point where sleeping is required, or a filesystem callout
+requires ref-walk, then instead of restarting the walk, we attempt to drop rcu
+at the last known good dentry we have. Avoiding a full restart in ref-walk in
+these cases is fundamental for performance and scalability because blocking
+operations such as creates and unlinks are not uncommon.
+
+The detailed design for rcu-walk is like this:
+* LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk.
+* Take the RCU lock for the entire path walk, starting with the acquiring
+  of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are
+  not required for dentry persistence.
+* synchronize_rcu is called when unregistering a filesystem, so we can
+  access d_ops and i_ops during rcu-walk.
+* Similarly take the vfsmount lock for the entire path walk. So now mnt
+  refcounts are not required for persistence. Also we are free to perform mount
+  lookups, and to assume dentry mount points and mount roots are stable up and
+  down the path.
+* Have a per-dentry seqlock to protect the dentry name, parent, and inode,
+  so we can load this tuple atomically, and also check whether any of its
+  members have changed.
+* Dentry lookups (based on parent, candidate string tuple) recheck the parent
+  sequence after the child is found in case anything changed in the parent
+  during the path walk.
+* inode is also RCU protected so we can load d_inode and use the inode for
+  limited things.
+* i_mode, i_uid, i_gid can be tested for exec permissions during path walk.
+* i_op can be loaded.
+* When the destination dentry is reached, drop rcu there (ie. take d_lock,
+  verify d_seq, increment refcount).
+* If seqlock verification fails anywhere along the path, do a full restart
+  of the path lookup in ref-walk mode. -ECHILD tends to be used (for want of
+  a better errno) to signal an rcu-walk failure.
+
+The cases where rcu-walk cannot continue are:
+* NULL dentry (ie. any uncached path element)
+* Following links
+
+It may be possible eventually to make following links rcu-walk aware.
+
+Uncached path elements will always require dropping to ref-walk mode, at the
+very least because i_mutex needs to be grabbed, and objects allocated.
+
+Final note:
+"store-free" path walking is not strictly store free. We take vfsmount lock
+and refcounts (both of which can be made per-cpu), and we also store to the
+stack (which is essentially CPU-local), and we also have to take locks and
+refcount on final dentry.
+
+The point is that shared data, where practically possible, is not locked
+or stored into. The result is massive improvements in performance and
+scalability of path resolution.
+
+
+Interesting statistics
+======================
+
+The following table gives rcu lookup statistics for a few simple workloads
+(2s12c24t Westmere, debian non-graphical system). Ungraceful are attempts to
+drop rcu that fail due to d_seq failure and requiring the entire path lookup
+again. Other cases are successful rcu-drops that are required before the final
+element, nodentry for missing dentry, revalidate for filesystem revalidate
+routine requiring rcu drop, permission for permission check requiring drop,
+and link for symlink traversal requiring drop.
+
+     rcu-lookups     restart  nodentry          link  revalidate  permission
+bootup     47121           0      4624          1010       10283        7852
+dbench  25386793           0   6778659(26.7%)     55         549        1156
+kbuild   2696672          10     64442(2.3%)  108764(4.0%)     1        1590
+git diff   39605           0        28             2           0         106
+vfstest 24185492        4945    708725(2.9%) 1076136(4.4%)     0        2651
+
+What this shows is that failed rcu-walk lookups, ie. ones that are restarted
+entirely with ref-walk, are quite rare. Even the "vfstest" case which
+specifically has concurrent renames/mkdir/rmdir/ creat/unlink/etc to excercise
+such races is not showing a huge amount of restarts.
+
+Dropping from rcu-walk to ref-walk mean that we have encountered a dentry where
+the reference count needs to be taken for some reason. This is either because
+we have reached the target of the path walk, or because we have encountered a
+condition that can't be resolved in rcu-walk mode.  Ideally, we drop rcu-walk
+only when we have reached the target dentry, so the other statistics show where
+this does not happen.
+
+Note that a graceful drop from rcu-walk mode due to something such as the
+dentry not existing (which can be common) is not necessarily a failure of
+rcu-walk scheme, because some elements of the path may have been walked in
+rcu-walk mode. The further we get from common path elements (such as cwd or
+root), the less contended the dentry is likely to be. The closer we are to
+common path elements, the more likely they will exist in dentry cache.
+
+
+Papers and other documentation on dcache locking
+================================================
+
+1. Scaling dcache with RCU (http://linuxjournal.com/article.php?sid=7124).
+
+2. http://lse.sourceforge.net/locking/dcache/dcache.html
+
+
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index a7e9746ee7e..dfbcd1b00b0 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -216,7 +216,6 @@ had ->revalidate()) add calls in ->follow_link()/->readlink().
 ->d_parent changes are not protected by BKL anymore.  Read access is safe
 if at least one of the following is true:
 	* filesystem has no cross-directory rename()
-	* dcache_lock is held
 	* we know that parent had been locked (e.g. we are looking at
 ->d_parent of ->lookup() argument).
 	* we are called from ->rename().
@@ -273,3 +272,125 @@ it's safe to remove it.  If you don't need it, remove it.
 deliberate; as soon as struct block_device * is propagated in a reasonable
 way by that code fixing will become trivial; until then nothing can be
 done.
+
+[mandatory]
+
+	block truncatation on error exit from ->write_begin, and ->direct_IO
+moved from generic methods (block_write_begin, cont_write_begin,
+nobh_write_begin, blockdev_direct_IO*) to callers.  Take a look at
+ext2_write_failed and callers for an example.
+
+[mandatory]
+
+	->truncate is going away.  The whole truncate sequence needs to be
+implemented in ->setattr, which is now mandatory for filesystems
+implementing on-disk size changes.  Start with a copy of the old inode_setattr
+and vmtruncate, and the reorder the vmtruncate + foofs_vmtruncate sequence to
+be in order of zeroing blocks using block_truncate_page or similar helpers,
+size update and on finally on-disk truncation which should not fail.
+inode_change_ok now includes the size checks for ATTR_SIZE and must be called
+in the beginning of ->setattr unconditionally.
+
+[mandatory]
+
+	->clear_inode() and ->delete_inode() are gone; ->evict_inode() should
+be used instead.  It gets called whenever the inode is evicted, whether it has
+remaining links or not.  Caller does *not* evict the pagecache or inode-associated
+metadata buffers; getting rid of those is responsibility of method, as it had
+been for ->delete_inode().
+	->drop_inode() returns int now; it's called on final iput() with inode_lock
+held and it returns true if filesystems wants the inode to be dropped.  As before,
+generic_drop_inode() is still the default and it's been updated appropriately.
+generic_delete_inode() is also alive and it consists simply of return 1.  Note that
+all actual eviction work is done by caller after ->drop_inode() returns.
+	clear_inode() is gone; use end_writeback() instead.  As before, it must
+be called exactly once on each call of ->evict_inode() (as it used to be for
+each call of ->delete_inode()).  Unlike before, if you are using inode-associated
+metadata buffers (i.e. mark_buffer_dirty_inode()), it's your responsibility to
+call invalidate_inode_buffers() before end_writeback().
+	No async writeback (and thus no calls of ->write_inode()) will happen
+after end_writeback() returns, so actions that should not overlap with ->write_inode()
+(e.g. freeing on-disk inode if i_nlink is 0) ought to be done after that call.
+
+	NOTE: checking i_nlink in the beginning of ->write_inode() and bailing out
+if it's zero is not *and* *never* *had* *been* enough.  Final unlink() and iput()
+may happen while the inode is in the middle of ->write_inode(); e.g. if you blindly
+free the on-disk inode, you may end up doing that while ->write_inode() is writing
+to it.
+
+---
+[mandatory]
+
+	.d_delete() now only advises the dcache as to whether or not to cache
+unreferenced dentries, and is now only called when the dentry refcount goes to
+0. Even on 0 refcount transition, it must be able to tolerate being called 0,
+1, or more times (eg. constant, idempotent).
+
+---
+[mandatory]
+
+	.d_compare() calling convention and locking rules are significantly
+changed. Read updated documentation in Documentation/filesystems/vfs.txt (and
+look at examples of other filesystems) for guidance.
+
+---
+[mandatory]
+
+	.d_hash() calling convention and locking rules are significantly
+changed. Read updated documentation in Documentation/filesystems/vfs.txt (and
+look at examples of other filesystems) for guidance.
+
+---
+[mandatory]
+	dcache_lock is gone, replaced by fine grained locks. See fs/dcache.c
+for details of what locks to replace dcache_lock with in order to protect
+particular things. Most of the time, a filesystem only needs ->d_lock, which
+protects *all* the dcache state of a given dentry.
+
+--
+[mandatory]
+
+	Filesystems must RCU-free their inodes, if they can have been accessed
+via rcu-walk path walk (basically, if the file can have had a path name in the
+vfs namespace).
+
+	i_dentry and i_rcu share storage in a union, and the vfs expects
+i_dentry to be reinitialized before it is freed, so an:
+
+  INIT_LIST_HEAD(&inode->i_dentry);
+
+must be done in the RCU callback.
+
+--
+[recommended]
+	vfs now tries to do path walking in "rcu-walk mode", which avoids
+atomic operations and scalability hazards on dentries and inodes (see
+Documentation/filesystems/path-lookup.txt). d_hash and d_compare changes
+(above) are examples of the changes required to support this. For more complex
+filesystem callbacks, the vfs drops out of rcu-walk mode before the fs call, so
+no changes are required to the filesystem. However, this is costly and loses
+the benefits of rcu-walk mode. We will begin to add filesystem callbacks that
+are rcu-walk aware, shown below. Filesystems should take advantage of this
+where possible.
+
+--
+[mandatory]
+	d_revalidate is a callback that is made on every path element (if
+the filesystem provides it), which requires dropping out of rcu-walk mode. This
+may now be called in rcu-walk mode (nd->flags & LOOKUP_RCU). -ECHILD should be
+returned if the filesystem cannot handle rcu-walk. See
+Documentation/filesystems/vfs.txt for more details.
+
+	permission and check_acl are inode permission checks that are called
+on many or all directory inodes on the way down a path walk (to check for
+exec permission). These must now be rcu-walk aware (flags & IPERM_FLAG_RCU).
+See Documentation/filesystems/vfs.txt for more details.
+ 
+--
+[mandatory]
+	In ->fallocate() you must check the mode option passed in.  If your
+filesystem does not support hole punching (deallocating space in the middle of a
+file) you must return -EOPNOTSUPP if FALLOC_FL_PUNCH_HOLE is set in mode.
+Currently you can only have FALLOC_FL_PUNCH_HOLE with FALLOC_FL_KEEP_SIZE set,
+so the i_size should not change when hole punching, even when puching the end of
+a file off.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 0d07513a67a..23cae6548d3 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -33,7 +33,8 @@ Table of Contents
   2	Modifying System Parameters
 
   3	Per-Process Parameters
-  3.1	/proc/<pid>/oom_adj - Adjust the oom-killer score
+  3.1	/proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
+								score
   3.2	/proc/<pid>/oom_score - Display current oom-killer score
   3.3	/proc/<pid>/io - Display the IO accounting fields
   3.4	/proc/<pid>/coredump_filter - Core dump filtering settings
@@ -73,9 +74,9 @@ contact Bodo  Bauer  at  bb@ricochet.net.  We'll  be happy to add them to this
 document.
 
 The   latest   version    of   this   document   is    available   online   at
-http://skaro.nightcrawler.com/~bb/Docs/Proc as HTML version.
+http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html
 
-If  the above  direction does  not works  for you,  ypu could  try the  kernel
+If  the above  direction does  not works  for you,  you could  try the  kernel
 mailing  list  at  linux-kernel@vger.kernel.org  and/or try  to  reach  me  at
 comandante@zaralinux.com.
 
@@ -135,6 +136,7 @@ Table 1-1: Process specific entries in /proc
  statm		Process memory status information
  status		Process status in human readable form
  wchan		If CONFIG_KALLSYMS is set, a pre-decoded wchan
+ pagemap	Page table
  stack		Report full stack trace, enable via CONFIG_STACKTRACE
  smaps		a extension based on maps, showing the memory consumption of
 		each mapping
@@ -164,6 +166,7 @@ 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 +191,13 @@ 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 +222,7 @@ 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
@@ -297,7 +307,7 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
   cgtime        guest time of the task children in jiffies
 ..............................................................................
 
-The /proc/PID/map file containing the currently mapped memory regions and
+The /proc/PID/maps file containing the currently mapped memory regions and
 their access permissions.
 
 The format is:
@@ -308,7 +318,7 @@ address           perms offset  dev   inode      pathname
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0          [threadstack:001ff4b4]
+a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
@@ -344,7 +354,6 @@ is not associated with a file:
  [stack]                  = the stack of the main process
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
- [threadstack:xxxxxxxx]   = the stack of the thread, xxxxxxxx is the stack size
 
  or if empty, the mapping is anonymous.
 
@@ -362,17 +371,25 @@ Shared_Dirty:          0 kB
 Private_Clean:         0 kB
 Private_Dirty:         0 kB
 Referenced:          892 kB
+Anonymous:             0 kB
 Swap:                  0 kB
 KernelPageSize:        4 kB
 MMUPageSize:           4 kB
-
-The first  of these lines shows  the same information  as is displayed for the
-mapping in /proc/PID/maps.  The remaining lines show  the size of the mapping,
-the amount of the mapping that is currently resident in RAM, the "proportional
-set size” (divide each shared page by the number of processes sharing it), the
-number of clean and dirty shared pages in the mapping, and the number of clean
-and dirty private pages in the mapping.  The "Referenced" indicates the amount
-of memory currently marked as referenced or accessed.
+Locked:              374 kB
+
+The first of these lines shows the same information as is displayed for the
+mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
+(size), the amount of the mapping that is currently resident in RAM (RSS), the
+process' proportional share of this mapping (PSS), the number of clean and
+dirty private pages in the mapping.  Note that even a page which is part of a
+MAP_SHARED mapping, but has only a single pte mapped, i.e.  is currently used
+by only one process, is accounted as private and not as shared.  "Referenced"
+indicates the amount of memory currently marked as referenced or accessed.
+"Anonymous" shows the amount of memory that does not belong to any file.  Even
+a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
+and a page is modified, the file page is replaced by a private anonymous copy.
+"Swap" shows how much would-be-anonymous memory is also used, but out on
+swap.
 
 This file is only present if the CONFIG_MMU kernel configuration option is
 enabled.
@@ -389,6 +406,9 @@ To clear the bits for the file mapped pages associated with the process
     > echo 3 > /proc/PID/clear_refs
 Any other value written to /proc/PID/clear_refs will have no effect.
 
+The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
+using /proc/kpageflags and number of times a page is mapped using
+/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
 
 1.2 Kernel data
 ---------------
@@ -430,6 +450,7 @@ 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)
@@ -557,6 +578,10 @@ The default_smp_affinity mask applies to all non-active IRQs, which are the
 IRQs which have not yet been allocated/activated, and hence which lack a
 /proc/irq/[0-9]* directory.
 
+The node file on an SMP system shows the node to which the device using the IRQ
+reports itself as being attached. This hardware locality information does not
+include information about any possible driver locality preference.
+
 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
 profiler. Default value is ffffffff (all cpus).
 
@@ -584,7 +609,7 @@ 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 +619,48 @@ 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:
@@ -604,6 +671,8 @@ varies by architecture and compile options.  The following is from a
 
 > cat /proc/meminfo
 
+The "Locked" indicates whether the mapping is locked in memory or not.
+
 
 MemTotal:     16344972 kB
 MemFree:      13634064 kB
@@ -914,7 +983,7 @@ your system and how much traffic was routed over those devices:
   ...] 1375103    17405    0    0    0     0       0          0 
   ...] 1703981     5535    0    0    0     3       0          0 
 
-In addition, each Channel Bond interface has it's own directory.  For
+In addition, each Channel Bond interface has its own directory.  For
 example, the bond0 device will have a directory called /proc/net/bond0/.
 It will contain information that is specific to that bond, such as the
 current slaves of the bond, the link status of the slaves, and how
@@ -1115,6 +1184,30 @@ Table 1-12: Files in /proc/fs/ext4/<devname>
  mb_groups       details of multiblock allocator buddy cache of free blocks
 ..............................................................................
 
+2.0 /proc/consoles
+------------------
+Shows registered system console lines.
+
+To see which character device lines are currently used for the system console
+/dev/console, you may simply look into the file /proc/consoles:
+
+  > cat /proc/consoles
+  tty0                 -WU (ECp)       4:7
+  ttyS0                -W- (Ep)        4:64
+
+The columns are:
+
+  device               name of the device
+  operations           R = can do read operations
+                       W = can do write operations
+                       U = can do unblank
+  flags                E = it is enabled
+                       C = it is prefered console
+                       B = it is primary boot console
+                       p = it is used for printk buffer
+                       b = it is not a TTY but a Braille device
+                       a = it is safe to use when cpu is offline
+  major:minor          major and minor number of the device separated by a colon
 
 ------------------------------------------------------------------------------
 Summary
@@ -1180,42 +1273,68 @@ of the kernel.
 CHAPTER 3: PER-PROCESS PARAMETERS
 ------------------------------------------------------------------------------
 
-3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
-------------------------------------------------------
-
-This file can be used to adjust the score used to select which processes
-should be killed in an  out-of-memory  situation.  Giving it a high score will
-increase the likelihood of this process being killed by the oom-killer.  Valid
-values are in the range -16 to +15, plus the special value -17, which disables
-oom-killing altogether for this process.
-
-The process to be killed in an out-of-memory situation is selected among all others
-based on its badness score. This value equals the original memory size of the process
-and is then updated according to its CPU time (utime + stime) and the
-run time (uptime - start time). The longer it runs the smaller is the score.
-Badness score is divided by the square root of the CPU time and then by
-the double square root of the run time.
-
-Swapped out tasks are killed first. Half of each child's memory size is added to
-the parent's score if they do not share the same memory. Thus forking servers
-are the prime candidates to be killed. Having only one 'hungry' child will make
-parent less preferable than the child.
-
-/proc/<pid>/oom_score shows process' current badness score.
-
-The following heuristics are then applied:
- * if the task was reniced, its score doubles
- * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE
- 	or CAP_SYS_RAWIO) have their score divided by 4
- * if oom condition happened in one cpuset and checked process does not belong
- 	to it, its score is divided by 8
- * the resulting score is multiplied by two to the power of oom_adj, i.e.
-	points <<= oom_adj when it is positive and
-	points >>= -(oom_adj) otherwise
-
-The task with the highest badness score is then selected and its children
-are killed, process itself will be killed in an OOM situation when it does
-not have children or some of them disabled oom like described above.
+3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
+--------------------------------------------------------------------------------
+
+These file can be used to adjust the badness heuristic used to select which
+process gets killed in out of memory conditions.
+
+The badness heuristic assigns a value to each candidate task ranging from 0
+(never kill) to 1000 (always kill) to determine which process is targeted.  The
+units are roughly a proportion along that range of allowed memory the process
+may allocate from based on an estimation of its current memory and swap use.
+For example, if a task is using all allowed memory, its badness score will be
+1000.  If it is using half of its allowed memory, its score will be 500.
+
+There is an additional factor included in the badness score: root
+processes are given 3% extra memory over other tasks.
+
+The amount of "allowed" memory depends on the context in which the oom killer
+was called.  If it is due to the memory assigned to the allocating task's cpuset
+being exhausted, the allowed memory represents the set of mems assigned to that
+cpuset.  If it is due to a mempolicy's node(s) being exhausted, the allowed
+memory represents the set of mempolicy nodes.  If it is due to a memory
+limit (or swap limit) being reached, the allowed memory is that configured
+limit.  Finally, if it is due to the entire system being out of memory, the
+allowed memory represents all allocatable resources.
+
+The value of /proc/<pid>/oom_score_adj is added to the badness score before it
+is used to determine which task to kill.  Acceptable values range from -1000
+(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX).  This allows userspace to
+polarize the preference for oom killing either by always preferring a certain
+task or completely disabling it.  The lowest possible value, -1000, is
+equivalent to disabling oom killing entirely for that task since it will always
+report a badness score of 0.
+
+Consequently, it is very simple for userspace to define the amount of memory to
+consider for each task.  Setting a /proc/<pid>/oom_score_adj value of +500, for
+example, is roughly equivalent to allowing the remainder of tasks sharing the
+same system, cpuset, mempolicy, or memory controller resources to use at least
+50% more memory.  A value of -500, on the other hand, would be roughly
+equivalent to discounting 50% of the task's allowed memory from being considered
+as scoring against the task.
+
+For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
+be used to tune the badness score.  Its acceptable values range from -16
+(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
+(OOM_DISABLE) to disable oom killing entirely for that task.  Its value is
+scaled linearly with /proc/<pid>/oom_score_adj.
+
+Writing to /proc/<pid>/oom_score_adj or /proc/<pid>/oom_adj will change the
+other with its scaled value.
+
+The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
+value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
+requires CAP_SYS_RESOURCE.
+
+NOTICE: /proc/<pid>/oom_adj is deprecated and will be removed, please see
+Documentation/feature-removal-schedule.txt.
+
+Caveat: when a parent task is selected, the oom killer will sacrifice any first
+generation children with seperate address spaces instead, if possible.  This
+avoids servers and important system daemons from being killed and loses the
+minimal amount of work.
+
 
 3.2 /proc/<pid>/oom_score - Display current oom-killer score
 -------------------------------------------------------------
@@ -1311,7 +1430,7 @@ been accounted as having caused 1MB of write.
 In other words: The number of bytes which this process caused to not happen,
 by truncating pagecache. A task can cause "negative" IO too. If this task
 truncates some dirty pagecache, some IO which another task has been accounted
-for (in it's write_bytes) will not be happening. We _could_ just subtract that
+for (in its write_bytes) will not be happening. We _could_ just subtract that
 from the truncating task's write_bytes, but there is information loss in doing
 that.
 
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
index 23a181074f9..4ede421c968 100644
--- a/Documentation/filesystems/sharedsubtree.txt
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -62,10 +62,10 @@ replicas continue to be exactly same.
 	# mount /dev/sd0  /tmp/a
 
 	#ls /tmp/a
-	t1 t2 t2
+	t1 t2 t3
 
 	#ls /mnt/a
-	t1 t2 t2
+	t1 t2 t3
 
 	Note that the mount has propagated to the mount at /mnt as well.
 
@@ -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/smbfs.txt b/Documentation/filesystems/smbfs.txt
deleted file mode 100644
index f673ef0de0f..00000000000
--- a/Documentation/filesystems/smbfs.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-Smbfs is a filesystem that implements the SMB protocol, which is the
-protocol used by Windows for Workgroups, Windows 95 and Windows NT.
-Smbfs was inspired by Samba, the program written by Andrew Tridgell
-that turns any Unix host into a file server for DOS or Windows clients.
-
-Smbfs is a SMB client, but uses parts of samba for it's operation. For
-more info on samba, including documentation, please go to
-http://www.samba.org/ and then on to your nearest mirror.
diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.txt
index b324c033035..66699afd66c 100644
--- a/Documentation/filesystems/squashfs.txt
+++ b/Documentation/filesystems/squashfs.txt
@@ -2,7 +2,7 @@ SQUASHFS 4.0 FILESYSTEM
 =======================
 
 Squashfs is a compressed read-only filesystem for Linux.
-It uses zlib compression to compress files, inodes and directories.
+It uses zlib/lzo compression to compress files, inodes and directories.
 Inodes in the system are very small and all blocks are packed to minimise
 data overhead. Block sizes greater than 4K are supported up to a maximum
 of 1Mbytes (default block size 128K).
@@ -38,7 +38,8 @@ Hard link support:		yes			no
 Real inode numbers:		yes			no
 32-bit uids/gids:		yes			no
 File creation time:		yes			no
-Xattr and ACL support:		no			no
+Xattr support:			yes			no
+ACL support:			no			no
 
 Squashfs compresses data, inodes and directories.  In addition, inode and
 directory data are highly compacted, and packed on byte boundaries.  Each
@@ -58,7 +59,7 @@ obtained from this site also.
 3. SQUASHFS FILESYSTEM DESIGN
 -----------------------------
 
-A squashfs filesystem consists of seven parts, packed together on a byte
+A squashfs filesystem consists of a maximum of eight parts, packed together on a byte
 alignment:
 
 	 ---------------
@@ -80,6 +81,9 @@ alignment:
 	|---------------|
 	|    uid/gid	|
 	|  lookup table	|
+	|---------------|
+	|     xattr     |
+	|     table	|
 	 ---------------
 
 Compressed data blocks are written to the filesystem as files are read from
@@ -192,6 +196,26 @@ This table is stored compressed into metadata blocks.  A second index table is
 used to locate these.  This second index table for speed of access (and because
 it is small) is read at mount time and cached in memory.
 
+3.7 Xattr table
+---------------
+
+The xattr table contains extended attributes for each inode.  The xattrs
+for each inode are stored in a list, each list entry containing a type,
+name and value field.  The type field encodes the xattr prefix
+("user.", "trusted." etc) and it also encodes how the name/value fields
+should be interpreted.  Currently the type indicates whether the value
+is stored inline (in which case the value field contains the xattr value),
+or if it is stored out of line (in which case the value field stores a
+reference to where the actual value is stored).  This allows large values
+to be stored out of line improving scanning and lookup performance and it
+also allows values to be de-duplicated, the value being stored once, and
+all other occurences holding an out of line reference to that value.
+
+The xattr lists are packed into compressed 8K metadata blocks.
+To reduce overhead in inodes, rather than storing the on-disk
+location of the xattr list inside each inode, a 32-bit xattr id
+is stored.  This xattr id is mapped into the location of the xattr
+list using a second xattr id lookup table.
 
 4. TODOS AND OUTSTANDING ISSUES
 -------------------------------
@@ -199,9 +223,7 @@ it is small) is read at mount time and cached in memory.
 4.1 Todo list
 -------------
 
-Implement Xattr and ACL support.  The Squashfs 4.0 filesystem layout has hooks
-for these but the code has not been written.  Once the code has been written
-the existing layout should not require modification.
+Implement ACL support.
 
 4.2 Squashfs internal cache
 ---------------------------
diff --git a/Documentation/filesystems/sysfs-pci.txt b/Documentation/filesystems/sysfs-pci.txt
index 85354b32d73..74eaac26f8b 100644
--- a/Documentation/filesystems/sysfs-pci.txt
+++ b/Documentation/filesystems/sysfs-pci.txt
@@ -39,7 +39,7 @@ files, each with their own function.
        local_cpus	   nearby CPU mask (cpumask, ro)
        remove		   remove device from kernel's list (ascii, wo)
        resource		   PCI resource host addresses (ascii, ro)
-       resource0..N	   PCI resource N, if present (binary, mmap)
+       resource0..N	   PCI resource N, if present (binary, mmap, rw[1])
        resource0_wc..N_wc  PCI WC map resource N, if prefetchable (binary, mmap)
        rom		   PCI ROM resource, if present (binary, ro)
        subsystem_device	   PCI subsystem device (ascii, ro)
@@ -54,13 +54,16 @@ files, each with their own function.
   binary - file contains binary data
   cpumask - file contains a cpumask type
 
+[1] rw for RESOURCE_IO (I/O port) regions only
+
 The read only files are informational, writes to them will be ignored, with
 the exception of the 'rom' file.  Writable files can be used to perform
 actions on the device (e.g. changing config space, detaching a device).
 mmapable files are available via an mmap of the file at offset 0 and can be
 used to do actual device programming from userspace.  Note that some platforms
 don't support mmapping of certain resources, so be sure to check the return
-value from any attempted mmap.
+value from any attempted mmap.  The most notable of these are I/O port
+resources, which also provide read/write access.
 
 The 'enable' file provides a counter that indicates how many times the device 
 has been enabled.  If the 'enable' file currently returns '4', and a '1' is
diff --git a/Documentation/filesystems/sysfs-tagging.txt b/Documentation/filesystems/sysfs-tagging.txt
new file mode 100644
index 00000000000..caaaf1266d8
--- /dev/null
+++ b/Documentation/filesystems/sysfs-tagging.txt
@@ -0,0 +1,42 @@
+Sysfs tagging
+-------------
+
+(Taken almost verbatim from Eric Biederman's netns tagging patch
+commit msg)
+
+The problem.  Network devices show up in sysfs and with the network
+namespace active multiple devices with the same name can show up in
+the same directory, ouch!
+
+To avoid that problem and allow existing applications in network
+namespaces to see the same interface that is currently presented in
+sysfs, sysfs now has tagging directory support.
+
+By using the network namespace pointers as tags to separate out the
+the sysfs directory entries we ensure that we don't have conflicts
+in the directories and applications only see a limited set of
+the network devices.
+
+Each sysfs directory entry may be tagged with zero or one
+namespaces.  A sysfs_dirent is augmented with a void *s_ns.  If a
+directory entry is tagged, then sysfs_dirent->s_flags will have a
+flag between KOBJ_NS_TYPE_NONE and KOBJ_NS_TYPES, and s_ns will
+point to the namespace to which it belongs.
+
+Each sysfs superblock's sysfs_super_info contains an array void
+*ns[KOBJ_NS_TYPES].  When a a task in a tagging namespace
+kobj_nstype first mounts sysfs, a new superblock is created.  It
+will be differentiated from other sysfs mounts by having its
+s_fs_info->ns[kobj_nstype] set to the new namespace.  Note that
+through bind mounting and mounts propagation, a task can easily view
+the contents of other namespaces' sysfs mounts.  Therefore, when a
+namespace exits, it will call kobj_ns_exit() to invalidate any
+sysfs_dirent->s_ns pointers pointing to it.
+
+Users of this interface:
+- define a type in the kobj_ns_type enumeration.
+- call kobj_ns_type_register() with its kobj_ns_type_operations which has
+  - current_ns() which returns current's namespace
+  - netlink_ns() which returns a socket's namespace
+  - initial_ns() which returns the initial namesapce
+- call kobj_ns_exit() when an individual tag is no longer valid
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index 931c806642c..5d1335faec2 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/Documentation/filesystems/sysfs.txt
@@ -4,7 +4,7 @@ sysfs - _The_ filesystem for exporting kernel objects.
 Patrick Mochel	<mochel@osdl.org>
 Mike Murphy <mamurph@cs.clemson.edu>
 
-Revised:    22 February 2009
+Revised:    15 July 2010
 Original:   10 January 2003
 
 
@@ -124,7 +124,7 @@ show and store methods of the attribute owners.
 
 struct sysfs_ops {
         ssize_t (*show)(struct kobject *, struct attribute *, char *);
-        ssize_t (*store)(struct kobject *, struct attribute *, const char *);
+        ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t);
 };
 
 [ Subsystems should have already defined a struct kobj_type as a
@@ -139,18 +139,22 @@ calls the associated methods.
 
 To illustrate:
 
+#define to_dev(obj) container_of(obj, struct device, kobj)
 #define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr)
-#define to_dev(d) container_of(d, struct device, kobj)
 
-static ssize_t
-dev_attr_show(struct kobject * kobj, struct attribute * attr, char * buf)
+static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr,
+                             char *buf)
 {
-        struct device_attribute * dev_attr = to_dev_attr(attr);
-        struct device * dev = to_dev(kobj);
-        ssize_t ret = 0;
+        struct device_attribute *dev_attr = to_dev_attr(attr);
+        struct device *dev = to_dev(kobj);
+        ssize_t ret = -EIO;
 
         if (dev_attr->show)
-                ret = dev_attr->show(dev, buf);
+                ret = dev_attr->show(dev, dev_attr, buf);
+        if (ret >= (ssize_t)PAGE_SIZE) {
+                print_symbol("dev_attr_show: %s returned bad count\n",
+                                (unsigned long)dev_attr->show);
+        }
         return ret;
 }
 
@@ -163,10 +167,9 @@ To read or write attributes, show() or store() methods must be
 specified when declaring the attribute. The method types should be as
 simple as those defined for device attributes:
 
-ssize_t (*show)(struct device * dev, struct device_attribute * attr,
-                char * buf);
-ssize_t (*store)(struct device * dev, struct device_attribute * attr,
-                 const char * buf);
+ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf);
+ssize_t (*store)(struct device *dev, struct device_attribute *attr,
+                 const char *buf, size_t count);
 
 IOW, they should take only an object, an attribute, and a buffer as parameters.
 
@@ -209,8 +212,8 @@ Other notes:
 
 - show() should always use snprintf(). 
 
-- store() should return the number of bytes used from the buffer. This
-  can be done using strlen().
+- store() should return the number of bytes used from the buffer. If the
+  entire buffer has been used, just return the count argument.
 
 - show() or store() can always return errors. If a bad value comes
   through, be sure to return an error.
@@ -223,15 +226,18 @@ Other notes:
 
 A very simple (and naive) implementation of a device attribute is:
 
-static ssize_t show_name(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t show_name(struct device *dev, struct device_attribute *attr,
+                         char *buf)
 {
 	return snprintf(buf, PAGE_SIZE, "%s\n", dev->name);
 }
 
-static ssize_t store_name(struct device * dev, const char * buf)
+static ssize_t store_name(struct device *dev, struct device_attribute *attr,
+                          const char *buf, size_t count)
 {
-	sscanf(buf, "%20s", dev->name);
-	return strnlen(buf, PAGE_SIZE);
+        snprintf(dev->name, sizeof(dev->name), "%.*s",
+                 (int)min(count, sizeof(dev->name) - 1), buf);
+	return count;
 }
 
 static DEVICE_ATTR(name, S_IRUGO, show_name, store_name);
@@ -327,7 +333,7 @@ Structure:
 struct bus_attribute {
         struct attribute        attr;
         ssize_t (*show)(struct bus_type *, char * buf);
-        ssize_t (*store)(struct bus_type *, const char * buf);
+        ssize_t (*store)(struct bus_type *, const char * buf, size_t count);
 };
 
 Declaring:
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index 3015da0c6b2..98ef5512415 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -82,21 +82,31 @@ 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
 largest node numbers in the range.  For example, mpol=bind:0-3,5,7,9-15
 
+A memory policy with a valid NodeList will be saved, as specified, for
+use at file creation time.  When a task allocates a file in the file
+system, the mount option memory policy will be applied with a NodeList,
+if any, modified by the calling task's cpuset constraints
+[See Documentation/cgroups/cpusets.txt] and any optional flags, listed
+below.  If the resulting NodeLists is the empty set, the effective memory
+policy for the file will revert to "default" policy.
+
 NUMA memory allocation policies have optional flags that can be used in
 conjunction with their modes.  These optional flags can be specified
 when tmpfs is mounted by appending them to the mode before the NodeList.
 See Documentation/vm/numa_memory_policy.txt for a list of all available
-memory allocation policy mode flags.
+memory allocation policy mode flags and their effect on memory policy.
 
 	=static		is equivalent to	MPOL_F_STATIC_NODES
 	=relative	is equivalent to	MPOL_F_RELATIVE_NODES
@@ -134,3 +144,5 @@ 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/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index eed520fd0c8..ead764b2728 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -165,7 +165,8 @@ TEST SUITE
 If you plan to make any modifications to the vfat filesystem, please
 get the test suite that comes with the vfat distribution at
 
-  http://bmrc.berkeley.edu/people/chaffee/vfat.html
+  http://web.archive.org/web/*/http://bmrc.berkeley.edu/
+  people/chaffee/vfat.html
 
 This tests quite a few parts of the vfat filesystem and additional
 tests for new features or untested features would be appreciated.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 3de2f32edd9..94cf97b901d 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -72,7 +72,7 @@ structure (this is the kernel-side implementation of file
 descriptors). The freshly allocated file structure is initialized with
 a pointer to the dentry and a set of file operation member functions.
 These are taken from the inode data. The open() file method is then
-called so the specific filesystem implementation can do it's work. You
+called so the specific filesystem implementation can do its work. You
 can see that this is another switch performed by the VFS. The file
 structure is placed into the file descriptor table for the process.
 
@@ -325,7 +325,8 @@ struct inode_operations {
         void * (*follow_link) (struct dentry *, struct nameidata *);
         void (*put_link) (struct dentry *, struct nameidata *, void *);
 	void (*truncate) (struct inode *);
-	int (*permission) (struct inode *, int, struct nameidata *);
+	int (*permission) (struct inode *, int, unsigned int);
+	int (*check_acl)(struct inode *, int, unsigned int);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
@@ -401,14 +402,26 @@ otherwise noted.
   	started might not be in the page cache at the end of the
   	walk).
 
-  truncate: called by the VFS to change the size of a file.  The
+  truncate: Deprecated. This will not be called if ->setsize is defined.
+	Called by the VFS to change the size of a file.  The
  	i_size field of the inode is set to the desired size by the
  	VFS before this method is called.  This method is called by
  	the truncate(2) system call and related functionality.
 
+	Note: ->truncate and vmtruncate are deprecated. Do not add new
+	instances/calls of these. Filesystems should be converted to do their
+	truncate sequence via ->setattr().
+
   permission: called by the VFS to check for access rights on a POSIX-like
   	filesystem.
 
+	May be called in rcu-walk mode (flags & IPERM_FLAG_RCU). If in rcu-walk
+        mode, the filesystem must check the permission without blocking or
+	storing to the inode.
+
+	If a situation is encountered that rcu-walk cannot handle, return
+	-ECHILD and it will be called again in ref-walk mode.
+
   setattr: called by the VFS to set attributes for a file. This method
   	is called by chmod(2) and related system calls.
 
@@ -529,6 +542,7 @@ struct address_space_operations {
 	sector_t (*bmap)(struct address_space *, sector_t);
 	int (*invalidatepage) (struct page *, unsigned long);
 	int (*releasepage) (struct page *, int);
+	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
 			loff_t offset, unsigned long nr_segs);
 	struct page* (*get_xip_page)(struct address_space *, sector_t,
@@ -655,11 +669,10 @@ struct address_space_operations {
   releasepage: releasepage is called on PagePrivate pages to indicate
         that the page should be freed if possible.  ->releasepage
         should remove any private data from the page and clear the
-        PagePrivate flag.  It may also remove the page from the
-        address_space.  If this fails for some reason, it may indicate
-        failure with a 0 return value.
-	This is used in two distinct though related cases.  The first
-        is when the VM finds a clean page with no active users and
+        PagePrivate flag. If releasepage() fails for some reason, it must
+	indicate failure with a 0 return value.
+	releasepage() is used in two distinct though related cases.  The
+	first is when the VM finds a clean page with no active users and
         wants to make it a free page.  If ->releasepage succeeds, the
         page will be removed from the address_space and become free.
 
@@ -674,6 +687,12 @@ struct address_space_operations {
         need to ensure this.  Possibly it can clear the PageUptodate
         bit if it cannot free private data yet.
 
+  freepage: freepage is called once the page is no longer visible in
+        the page cache in order to allow the cleanup of any private
+	data. Since it may be called by the memory reclaimer, it
+	should not assume that the original address_space mapping still
+	exists, and it should not block.
+
   direct_IO: called by the generic read/write routines to perform
         direct_IO - that is IO requests which bypass the page cache
         and transfer data directly between the storage and the
@@ -722,14 +741,13 @@ struct file_operations {
 	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	int (*readdir) (struct file *, void *, filldir_t);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
-	int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *);
 	int (*release) (struct inode *, struct file *);
-	int (*fsync) (struct file *, struct dentry *, int datasync);
+	int (*fsync) (struct file *, int datasync);
 	int (*aio_fsync) (struct kiocb *, int datasync);
 	int (*fasync) (int, struct file *, int);
 	int (*lock) (struct file *, int, struct file_lock *);
@@ -763,10 +781,7 @@ otherwise noted.
 	activity on this file and (optionally) go to sleep until there
 	is activity. Called by the select(2) and poll(2) system calls
 
-  ioctl: called by the ioctl(2) system call
-
-  unlocked_ioctl: called by the ioctl(2) system call. Filesystems that do not
-  	require the BKL should use this method instead of the ioctl() above.
+  unlocked_ioctl: called by the ioctl(2) system call.
 
   compat_ioctl: called by the ioctl(2) system call when 32 bit system calls
  	 are used on 64 bit kernels.
@@ -840,12 +855,17 @@ defined:
 
 struct dentry_operations {
 	int (*d_revalidate)(struct dentry *, struct nameidata *);
-	int (*d_hash) (struct dentry *, struct qstr *);
-	int (*d_compare) (struct dentry *, struct qstr *, struct qstr *);
-	int (*d_delete)(struct dentry *);
+	int (*d_hash)(const struct dentry *, const struct inode *,
+			struct qstr *);
+	int (*d_compare)(const struct dentry *, const struct inode *,
+			const struct dentry *, const struct inode *,
+			unsigned int, const char *, const struct qstr *);
+	int (*d_delete)(const struct dentry *);
 	void (*d_release)(struct dentry *);
 	void (*d_iput)(struct dentry *, struct inode *);
 	char *(*d_dname)(struct dentry *, char *, int);
+	struct vfsmount *(*d_automount)(struct path *);
+	int (*d_manage)(struct dentry *, bool, bool);
 };
 
   d_revalidate: called when the VFS needs to revalidate a dentry. This
@@ -853,13 +873,45 @@ struct dentry_operations {
 	dcache. Most filesystems leave this as NULL, because all their
 	dentries in the dcache are valid
 
-  d_hash: called when the VFS adds a dentry to the hash table
+	d_revalidate may be called in rcu-walk mode (nd->flags & LOOKUP_RCU).
+	If in rcu-walk mode, the filesystem must revalidate the dentry without
+	blocking or storing to the dentry, d_parent and d_inode should not be
+	used without care (because they can go NULL), instead nd->inode should
+	be used.
+
+	If a situation is encountered that rcu-walk cannot handle, return
+	-ECHILD and it will be called again in ref-walk mode.
 
-  d_compare: called when a dentry should be compared with another
+  d_hash: called when the VFS adds a dentry to the hash table. The first
+	dentry passed to d_hash is the parent directory that the name is
+	to be hashed into. The inode is the dentry's inode.
 
-  d_delete: called when the last reference to a dentry is
-	deleted. This means no-one is using the dentry, however it is
-	still valid and in the dcache
+	Same locking and synchronisation rules as d_compare regarding
+	what is safe to dereference etc.
+
+  d_compare: called to compare a dentry name with a given name. The first
+	dentry is the parent of the dentry to be compared, the second is
+	the parent's inode, then the dentry and inode (may be NULL) of the
+	child dentry. len and name string are properties of the dentry to be
+	compared. qstr is the name to compare it with.
+
+	Must be constant and idempotent, and should not take locks if
+	possible, and should not or store into the dentry or inodes.
+	Should not dereference pointers outside the dentry or inodes without
+	lots of care (eg.  d_parent, d_inode, d_name should not be used).
+
+	However, our vfsmount is pinned, and RCU held, so the dentries and
+	inodes won't disappear, neither will our sb or filesystem module.
+	->i_sb and ->d_sb may be used.
+
+	It is a tricky calling convention because it needs to be called under
+	"rcu-walk", ie. without any locks or references on things.
+
+  d_delete: called when the last reference to a dentry is dropped and the
+	dcache is deciding whether or not to cache it. Return 1 to delete
+	immediately, or 0 to cache the dentry. Default is NULL which means to
+	always cache a reachable dentry. d_delete must be constant and
+	idempotent.
 
   d_release: called when a dentry is really deallocated
 
@@ -880,6 +932,47 @@ struct dentry_operations {
 	at the end of the buffer, and returns a pointer to the first char.
 	dynamic_dname() helper function is provided to take care of this.
 
+  d_automount: called when an automount dentry is to be traversed (optional).
+	This should create a new VFS mount record and return the record to the
+	caller.  The caller is supplied with a path parameter giving the
+	automount directory to describe the automount target and the parent
+	VFS mount record to provide inheritable mount parameters.  NULL should
+	be returned if someone else managed to make the automount first.  If
+	the vfsmount creation failed, then an error code should be returned.
+	If -EISDIR is returned, then the directory will be treated as an
+	ordinary directory and returned to pathwalk to continue walking.
+
+	If a vfsmount is returned, the caller will attempt to mount it on the
+	mountpoint and will remove the vfsmount from its expiration list in
+	the case of failure.  The vfsmount should be returned with 2 refs on
+	it to prevent automatic expiration - the caller will clean up the
+	additional ref.
+
+	This function is only used if DCACHE_NEED_AUTOMOUNT is set on the
+	dentry.  This is set by __d_instantiate() if S_AUTOMOUNT is set on the
+	inode being added.
+
+  d_manage: called to allow the filesystem to manage the transition from a
+	dentry (optional).  This allows autofs, for example, to hold up clients
+	waiting to explore behind a 'mountpoint' whilst letting the daemon go
+	past and construct the subtree there.  0 should be returned to let the
+	calling process continue.  -EISDIR can be returned to tell pathwalk to
+	use this directory as an ordinary directory and to ignore anything
+	mounted on it and not to check the automount flag.  Any other error
+	code will abort pathwalk completely.
+
+	If the 'mounting_here' parameter is true, then namespace_sem is being
+	held by the caller and the function should not initiate any mounts or
+	unmounts that it will then wait for.
+
+	If the 'rcu_walk' parameter is true, then the caller is doing a
+	pathwalk in RCU-walk mode.  Sleeping is not permitted in this mode,
+	and the caller can be asked to leave it and call again by returing
+	-ECHILD.
+
+	This function is only used if DCACHE_MANAGE_TRANSIT is set on the
+	dentry being transited from.
+
 Example :
 
 static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)
@@ -903,14 +996,11 @@ manipulate dentries:
 	the usage count)
 
   dput: close a handle for a dentry (decrements the usage count). If
-	the usage count drops to 0, the "d_delete" method is called
-	and the dentry is placed on the unused list if the dentry is
-	still in its parents hash list. Putting the dentry on the
-	unused list just means that if the system needs some RAM, it
-	goes through the unused list of dentries and deallocates them.
-	If the dentry has already been unhashed and the usage count
-	drops to 0, in this case the dentry is deallocated after the
-	"d_delete" method is called
+	the usage count drops to 0, and the dentry is still in its
+	parent's hash, the "d_delete" method is called to check whether
+	it should be cached. If it should not be cached, or if the dentry
+	is not hashed, it is deleted. Otherwise cached dentries are put
+	into an LRU list to be reclaimed on memory shortage.
 
   d_drop: this unhashes a dentry from its parents hash list. A
 	subsequent call to dput() will deallocate the dentry if its
diff --git a/Documentation/filesystems/xfs-delayed-logging-design.txt b/Documentation/filesystems/xfs-delayed-logging-design.txt
new file mode 100644
index 00000000000..7445bf335da
--- /dev/null
+++ b/Documentation/filesystems/xfs-delayed-logging-design.txt
@@ -0,0 +1,800 @@
+XFS Delayed Logging Design
+--------------------------
+
+Introduction to Re-logging in XFS
+---------------------------------
+
+XFS logging is a combination of logical and physical logging. Some objects,
+such as inodes and dquots, are logged in logical format where the details
+logged are made up of the changes to in-core structures rather than on-disk
+structures. Other objects - typically buffers - have their physical changes
+logged. The reason for these differences is to reduce the amount of log space
+required for objects that are frequently logged. Some parts of inodes are more
+frequently logged than others, and inodes are typically more frequently logged
+than any other object (except maybe the superblock buffer) so keeping the
+amount of metadata logged low is of prime importance.
+
+The reason that this is such a concern is that XFS allows multiple separate
+modifications to a single object to be carried in the log at any given time.
+This allows the log to avoid needing to flush each change to disk before
+recording a new change to the object. XFS does this via a method called
+"re-logging". Conceptually, this is quite simple - all it requires is that any
+new change to the object is recorded with a *new copy* of all the existing
+changes in the new transaction that is written to the log.
+
+That is, if we have a sequence of changes A through to F, and the object was
+written to disk after change D, we would see in the log the following series
+of transactions, their contents and the log sequence number (LSN) of the
+transaction:
+
+	Transaction		Contents	LSN
+	   A			   A		   X
+	   B			  A+B		  X+n
+	   C			 A+B+C		 X+n+m
+	   D			A+B+C+D		X+n+m+o
+	    <object written to disk>
+	   E			   E		   Y (> X+n+m+o)
+	   F			  E+F		  Yٍ+p
+
+In other words, each time an object is relogged, the new transaction contains
+the aggregation of all the previous changes currently held only in the log.
+
+This relogging technique also allows objects to be moved forward in the log so
+that an object being relogged does not prevent the tail of the log from ever
+moving forward.  This can be seen in the table above by the changing
+(increasing) LSN of each subsquent transaction - the LSN is effectively a
+direct encoding of the location in the log of the transaction.
+
+This relogging is also used to implement long-running, multiple-commit
+transactions.  These transaction are known as rolling transactions, and require
+a special log reservation known as a permanent transaction reservation. A
+typical example of a rolling transaction is the removal of extents from an
+inode which can only be done at a rate of two extents per transaction because
+of reservation size limitations. Hence a rolling extent removal transaction
+keeps relogging the inode and btree buffers as they get modified in each
+removal operation. This keeps them moving forward in the log as the operation
+progresses, ensuring that current operation never gets blocked by itself if the
+log wraps around.
+
+Hence it can be seen that the relogging operation is fundamental to the correct
+working of the XFS journalling subsystem. From the above description, most
+people should be able to see why the XFS metadata operations writes so much to
+the log - repeated operations to the same objects write the same changes to
+the log over and over again. Worse is the fact that objects tend to get
+dirtier as they get relogged, so each subsequent transaction is writing more
+metadata into the log.
+
+Another feature of the XFS transaction subsystem is that most transactions are
+asynchronous. That is, they don't commit to disk until either a log buffer is
+filled (a log buffer can hold multiple transactions) or a synchronous operation
+forces the log buffers holding the transactions to disk. This means that XFS is
+doing aggregation of transactions in memory - batching them, if you like - to
+minimise the impact of the log IO on transaction throughput.
+
+The limitation on asynchronous transaction throughput is the number and size of
+log buffers made available by the log manager. By default there are 8 log
+buffers available and the size of each is 32kB - the size can be increased up
+to 256kB by use of a mount option.
+
+Effectively, this gives us the maximum bound of outstanding metadata changes
+that can be made to the filesystem at any point in time - if all the log
+buffers are full and under IO, then no more transactions can be committed until
+the current batch completes. It is now common for a single current CPU core to
+be to able to issue enough transactions to keep the log buffers full and under
+IO permanently. Hence the XFS journalling subsystem can be considered to be IO
+bound.
+
+Delayed Logging: Concepts
+-------------------------
+
+The key thing to note about the asynchronous logging combined with the
+relogging technique XFS uses is that we can be relogging changed objects
+multiple times before they are committed to disk in the log buffers. If we
+return to the previous relogging example, it is entirely possible that
+transactions A through D are committed to disk in the same log buffer.
+
+That is, a single log buffer may contain multiple copies of the same object,
+but only one of those copies needs to be there - the last one "D", as it
+contains all the changes from the previous changes. In other words, we have one
+necessary copy in the log buffer, and three stale copies that are simply
+wasting space. When we are doing repeated operations on the same set of
+objects, these "stale objects" can be over 90% of the space used in the log
+buffers. It is clear that reducing the number of stale objects written to the
+log would greatly reduce the amount of metadata we write to the log, and this
+is the fundamental goal of delayed logging.
+
+From a conceptual point of view, XFS is already doing relogging in memory (where
+memory == log buffer), only it is doing it extremely inefficiently. It is using
+logical to physical formatting to do the relogging because there is no
+infrastructure to keep track of logical changes in memory prior to physically
+formatting the changes in a transaction to the log buffer. Hence we cannot avoid
+accumulating stale objects in the log buffers.
+
+Delayed logging is the name we've given to keeping and tracking transactional
+changes to objects in memory outside the log buffer infrastructure. Because of
+the relogging concept fundamental to the XFS journalling subsystem, this is
+actually relatively easy to do - all the changes to logged items are already
+tracked in the current infrastructure. The big problem is how to accumulate
+them and get them to the log in a consistent, recoverable manner.
+Describing the problems and how they have been solved is the focus of this
+document.
+
+One of the key changes that delayed logging makes to the operation of the
+journalling subsystem is that it disassociates the amount of outstanding
+metadata changes from the size and number of log buffers available. In other
+words, instead of there only being a maximum of 2MB of transaction changes not
+written to the log at any point in time, there may be a much greater amount
+being accumulated in memory. Hence the potential for loss of metadata on a
+crash is much greater than for the existing logging mechanism.
+
+It should be noted that this does not change the guarantee that log recovery
+will result in a consistent filesystem. What it does mean is that as far as the
+recovered filesystem is concerned, there may be many thousands of transactions
+that simply did not occur as a result of the crash. This makes it even more
+important that applications that care about their data use fsync() where they
+need to ensure application level data integrity is maintained.
+
+It should be noted that delayed logging is not an innovative new concept that
+warrants rigorous proofs to determine whether it is correct or not. The method
+of accumulating changes in memory for some period before writing them to the
+log is used effectively in many filesystems including ext3 and ext4. Hence
+no time is spent in this document trying to convince the reader that the
+concept is sound. Instead it is simply considered a "solved problem" and as
+such implementing it in XFS is purely an exercise in software engineering.
+
+The fundamental requirements for delayed logging in XFS are simple:
+
+	1. Reduce the amount of metadata written to the log by at least
+	   an order of magnitude.
+	2. Supply sufficient statistics to validate Requirement #1.
+	3. Supply sufficient new tracing infrastructure to be able to debug
+	   problems with the new code.
+	4. No on-disk format change (metadata or log format).
+	5. Enable and disable with a mount option.
+	6. No performance regressions for synchronous transaction workloads.
+
+Delayed Logging: Design
+-----------------------
+
+Storing Changes
+
+The problem with accumulating changes at a logical level (i.e. just using the
+existing log item dirty region tracking) is that when it comes to writing the
+changes to the log buffers, we need to ensure that the object we are formatting
+is not changing while we do this. This requires locking the object to prevent
+concurrent modification. Hence flushing the logical changes to the log would
+require us to lock every object, format them, and then unlock them again.
+
+This introduces lots of scope for deadlocks with transactions that are already
+running. For example, a transaction has object A locked and modified, but needs
+the delayed logging tracking lock to commit the transaction. However, the
+flushing thread has the delayed logging tracking lock already held, and is
+trying to get the lock on object A to flush it to the log buffer. This appears
+to be an unsolvable deadlock condition, and it was solving this problem that
+was the barrier to implementing delayed logging for so long.
+
+The solution is relatively simple - it just took a long time to recognise it.
+Put simply, the current logging code formats the changes to each item into an
+vector array that points to the changed regions in the item. The log write code
+simply copies the memory these vectors point to into the log buffer during
+transaction commit while the item is locked in the transaction. Instead of
+using the log buffer as the destination of the formatting code, we can use an
+allocated memory buffer big enough to fit the formatted vector.
+
+If we then copy the vector into the memory buffer and rewrite the vector to
+point to the memory buffer rather than the object itself, we now have a copy of
+the changes in a format that is compatible with the log buffer writing code.
+that does not require us to lock the item to access. This formatting and
+rewriting can all be done while the object is locked during transaction commit,
+resulting in a vector that is transactionally consistent and can be accessed
+without needing to lock the owning item.
+
+Hence we avoid the need to lock items when we need to flush outstanding
+asynchronous transactions to the log. The differences between the existing
+formatting method and the delayed logging formatting can be seen in the
+diagram below.
+
+Current format log vector:
+
+Object    +---------------------------------------------+
+Vector 1      +----+
+Vector 2                    +----+
+Vector 3                                   +----------+
+
+After formatting:
+
+Log Buffer    +-V1-+-V2-+----V3----+
+
+Delayed logging vector:
+
+Object    +---------------------------------------------+
+Vector 1      +----+
+Vector 2                    +----+
+Vector 3                                   +----------+
+
+After formatting:
+
+Memory Buffer +-V1-+-V2-+----V3----+
+Vector 1      +----+
+Vector 2           +----+
+Vector 3                +----------+
+
+The memory buffer and associated vector need to be passed as a single object,
+but still need to be associated with the parent object so if the object is
+relogged we can replace the current memory buffer with a new memory buffer that
+contains the latest changes.
+
+The reason for keeping the vector around after we've formatted the memory
+buffer is to support splitting vectors across log buffer boundaries correctly.
+If we don't keep the vector around, we do not know where the region boundaries
+are in the item, so we'd need a new encapsulation method for regions in the log
+buffer writing (i.e. double encapsulation). This would be an on-disk format
+change and as such is not desirable.  It also means we'd have to write the log
+region headers in the formatting stage, which is problematic as there is per
+region state that needs to be placed into the headers during the log write.
+
+Hence we need to keep the vector, but by attaching the memory buffer to it and
+rewriting the vector addresses to point at the memory buffer we end up with a
+self-describing object that can be passed to the log buffer write code to be
+handled in exactly the same manner as the existing log vectors are handled.
+Hence we avoid needing a new on-disk format to handle items that have been
+relogged in memory.
+
+
+Tracking Changes
+
+Now that we can record transactional changes in memory in a form that allows
+them to be used without limitations, we need to be able to track and accumulate
+them so that they can be written to the log at some later point in time.  The
+log item is the natural place to store this vector and buffer, and also makes sense
+to be the object that is used to track committed objects as it will always
+exist once the object has been included in a transaction.
+
+The log item is already used to track the log items that have been written to
+the log but not yet written to disk. Such log items are considered "active"
+and as such are stored in the Active Item List (AIL) which is a LSN-ordered
+double linked list. Items are inserted into this list during log buffer IO
+completion, after which they are unpinned and can be written to disk. An object
+that is in the AIL can be relogged, which causes the object to be pinned again
+and then moved forward in the AIL when the log buffer IO completes for that
+transaction.
+
+Essentially, this shows that an item that is in the AIL can still be modified
+and relogged, so any tracking must be separate to the AIL infrastructure. As
+such, we cannot reuse the AIL list pointers for tracking committed items, nor
+can we store state in any field that is protected by the AIL lock. Hence the
+committed item tracking needs it's own locks, lists and state fields in the log
+item.
+
+Similar to the AIL, tracking of committed items is done through a new list
+called the Committed Item List (CIL).  The list tracks log items that have been
+committed and have formatted memory buffers attached to them. It tracks objects
+in transaction commit order, so when an object is relogged it is removed from
+it's place in the list and re-inserted at the tail. This is entirely arbitrary
+and done to make it easy for debugging - the last items in the list are the
+ones that are most recently modified. Ordering of the CIL is not necessary for
+transactional integrity (as discussed in the next section) so the ordering is
+done for convenience/sanity of the developers.
+
+
+Delayed Logging: Checkpoints
+
+When we have a log synchronisation event, commonly known as a "log force",
+all the items in the CIL must be written into the log via the log buffers.
+We need to write these items in the order that they exist in the CIL, and they
+need to be written as an atomic transaction. The need for all the objects to be
+written as an atomic transaction comes from the requirements of relogging and
+log replay - all the changes in all the objects in a given transaction must
+either be completely replayed during log recovery, or not replayed at all. If
+a transaction is not replayed because it is not complete in the log, then
+no later transactions should be replayed, either.
+
+To fulfill this requirement, we need to write the entire CIL in a single log
+transaction. Fortunately, the XFS log code has no fixed limit on the size of a
+transaction, nor does the log replay code. The only fundamental limit is that
+the transaction cannot be larger than just under half the size of the log.  The
+reason for this limit is that to find the head and tail of the log, there must
+be at least one complete transaction in the log at any given time. If a
+transaction is larger than half the log, then there is the possibility that a
+crash during the write of a such a transaction could partially overwrite the
+only complete previous transaction in the log. This will result in a recovery
+failure and an inconsistent filesystem and hence we must enforce the maximum
+size of a checkpoint to be slightly less than a half the log.
+
+Apart from this size requirement, a checkpoint transaction looks no different
+to any other transaction - it contains a transaction header, a series of
+formatted log items and a commit record at the tail. From a recovery
+perspective, the checkpoint transaction is also no different - just a lot
+bigger with a lot more items in it. The worst case effect of this is that we
+might need to tune the recovery transaction object hash size.
+
+Because the checkpoint is just another transaction and all the changes to log
+items are stored as log vectors, we can use the existing log buffer writing
+code to write the changes into the log. To do this efficiently, we need to
+minimise the time we hold the CIL locked while writing the checkpoint
+transaction. The current log write code enables us to do this easily with the
+way it separates the writing of the transaction contents (the log vectors) from
+the transaction commit record, but tracking this requires us to have a
+per-checkpoint context that travels through the log write process through to
+checkpoint completion.
+
+Hence a checkpoint has a context that tracks the state of the current
+checkpoint from initiation to checkpoint completion. A new context is initiated
+at the same time a checkpoint transaction is started. That is, when we remove
+all the current items from the CIL during a checkpoint operation, we move all
+those changes into the current checkpoint context. We then initialise a new
+context and attach that to the CIL for aggregation of new transactions.
+
+This allows us to unlock the CIL immediately after transfer of all the
+committed items and effectively allow new transactions to be issued while we
+are formatting the checkpoint into the log. It also allows concurrent
+checkpoints to be written into the log buffers in the case of log force heavy
+workloads, just like the existing transaction commit code does. This, however,
+requires that we strictly order the commit records in the log so that
+checkpoint sequence order is maintained during log replay.
+
+To ensure that we can be writing an item into a checkpoint transaction at
+the same time another transaction modifies the item and inserts the log item
+into the new CIL, then checkpoint transaction commit code cannot use log items
+to store the list of log vectors that need to be written into the transaction.
+Hence log vectors need to be able to be chained together to allow them to be
+detatched from the log items. That is, when the CIL is flushed the memory
+buffer and log vector attached to each log item needs to be attached to the
+checkpoint context so that the log item can be released. In diagrammatic form,
+the CIL would look like this before the flush:
+
+	CIL Head
+	   |
+	   V
+	Log Item <-> log vector 1	-> memory buffer
+	   |				-> vector array
+	   V
+	Log Item <-> log vector 2	-> memory buffer
+	   |				-> vector array
+	   V
+	......
+	   |
+	   V
+	Log Item <-> log vector N-1	-> memory buffer
+	   |				-> vector array
+	   V
+	Log Item <-> log vector N	-> memory buffer
+					-> vector array
+
+And after the flush the CIL head is empty, and the checkpoint context log
+vector list would look like:
+
+	Checkpoint Context
+	   |
+	   V
+	log vector 1	-> memory buffer
+	   |		-> vector array
+	   |		-> Log Item
+	   V
+	log vector 2	-> memory buffer
+	   |		-> vector array
+	   |		-> Log Item
+	   V
+	......
+	   |
+	   V
+	log vector N-1	-> memory buffer
+	   |		-> vector array
+	   |		-> Log Item
+	   V
+	log vector N	-> memory buffer
+			-> vector array
+			-> Log Item
+
+Once this transfer is done, the CIL can be unlocked and new transactions can
+start, while the checkpoint flush code works over the log vector chain to
+commit the checkpoint.
+
+Once the checkpoint is written into the log buffers, the checkpoint context is
+attached to the log buffer that the commit record was written to along with a
+completion callback. Log IO completion will call that callback, which can then
+run transaction committed processing for the log items (i.e. insert into AIL
+and unpin) in the log vector chain and then free the log vector chain and
+checkpoint context.
+
+Discussion Point: I am uncertain as to whether the log item is the most
+efficient way to track vectors, even though it seems like the natural way to do
+it. The fact that we walk the log items (in the CIL) just to chain the log
+vectors and break the link between the log item and the log vector means that
+we take a cache line hit for the log item list modification, then another for
+the log vector chaining. If we track by the log vectors, then we only need to
+break the link between the log item and the log vector, which means we should
+dirty only the log item cachelines. Normally I wouldn't be concerned about one
+vs two dirty cachelines except for the fact I've seen upwards of 80,000 log
+vectors in one checkpoint transaction. I'd guess this is a "measure and
+compare" situation that can be done after a working and reviewed implementation
+is in the dev tree....
+
+Delayed Logging: Checkpoint Sequencing
+
+One of the key aspects of the XFS transaction subsystem is that it tags
+committed transactions with the log sequence number of the transaction commit.
+This allows transactions to be issued asynchronously even though there may be
+future operations that cannot be completed until that transaction is fully
+committed to the log. In the rare case that a dependent operation occurs (e.g.
+re-using a freed metadata extent for a data extent), a special, optimised log
+force can be issued to force the dependent transaction to disk immediately.
+
+To do this, transactions need to record the LSN of the commit record of the
+transaction. This LSN comes directly from the log buffer the transaction is
+written into. While this works just fine for the existing transaction
+mechanism, it does not work for delayed logging because transactions are not
+written directly into the log buffers. Hence some other method of sequencing
+transactions is required.
+
+As discussed in the checkpoint section, delayed logging uses per-checkpoint
+contexts, and as such it is simple to assign a sequence number to each
+checkpoint. Because the switching of checkpoint contexts must be done
+atomically, it is simple to ensure that each new context has a monotonically
+increasing sequence number assigned to it without the need for an external
+atomic counter - we can just take the current context sequence number and add
+one to it for the new context.
+
+Then, instead of assigning a log buffer LSN to the transaction commit LSN
+during the commit, we can assign the current checkpoint sequence. This allows
+operations that track transactions that have not yet completed know what
+checkpoint sequence needs to be committed before they can continue. As a
+result, the code that forces the log to a specific LSN now needs to ensure that
+the log forces to a specific checkpoint.
+
+To ensure that we can do this, we need to track all the checkpoint contexts
+that are currently committing to the log. When we flush a checkpoint, the
+context gets added to a "committing" list which can be searched. When a
+checkpoint commit completes, it is removed from the committing list. Because
+the checkpoint context records the LSN of the commit record for the checkpoint,
+we can also wait on the log buffer that contains the commit record, thereby
+using the existing log force mechanisms to execute synchronous forces.
+
+It should be noted that the synchronous forces may need to be extended with
+mitigation algorithms similar to the current log buffer code to allow
+aggregation of multiple synchronous transactions if there are already
+synchronous transactions being flushed. Investigation of the performance of the
+current design is needed before making any decisions here.
+
+The main concern with log forces is to ensure that all the previous checkpoints
+are also committed to disk before the one we need to wait for. Therefore we
+need to check that all the prior contexts in the committing list are also
+complete before waiting on the one we need to complete. We do this
+synchronisation in the log force code so that we don't need to wait anywhere
+else for such serialisation - it only matters when we do a log force.
+
+The only remaining complexity is that a log force now also has to handle the
+case where the forcing sequence number is the same as the current context. That
+is, we need to flush the CIL and potentially wait for it to complete. This is a
+simple addition to the existing log forcing code to check the sequence numbers
+and push if required. Indeed, placing the current sequence checkpoint flush in
+the log force code enables the current mechanism for issuing synchronous
+transactions to remain untouched (i.e. commit an asynchronous transaction, then
+force the log at the LSN of that transaction) and so the higher level code
+behaves the same regardless of whether delayed logging is being used or not.
+
+Delayed Logging: Checkpoint Log Space Accounting
+
+The big issue for a checkpoint transaction is the log space reservation for the
+transaction. We don't know how big a checkpoint transaction is going to be
+ahead of time, nor how many log buffers it will take to write out, nor the
+number of split log vector regions are going to be used. We can track the
+amount of log space required as we add items to the commit item list, but we
+still need to reserve the space in the log for the checkpoint.
+
+A typical transaction reserves enough space in the log for the worst case space
+usage of the transaction. The reservation accounts for log record headers,
+transaction and region headers, headers for split regions, buffer tail padding,
+etc. as well as the actual space for all the changed metadata in the
+transaction. While some of this is fixed overhead, much of it is dependent on
+the size of the transaction and the number of regions being logged (the number
+of log vectors in the transaction).
+
+An example of the differences would be logging directory changes versus logging
+inode changes. If you modify lots of inode cores (e.g. chmod -R g+w *), then
+there are lots of transactions that only contain an inode core and an inode log
+format structure. That is, two vectors totaling roughly 150 bytes. If we modify
+10,000 inodes, we have about 1.5MB of metadata to write in 20,000 vectors. Each
+vector is 12 bytes, so the total to be logged is approximately 1.75MB. In
+comparison, if we are logging full directory buffers, they are typically 4KB
+each, so we in 1.5MB of directory buffers we'd have roughly 400 buffers and a
+buffer format structure for each buffer - roughly 800 vectors or 1.51MB total
+space.  From this, it should be obvious that a static log space reservation is
+not particularly flexible and is difficult to select the "optimal value" for
+all workloads.
+
+Further, if we are going to use a static reservation, which bit of the entire
+reservation does it cover? We account for space used by the transaction
+reservation by tracking the space currently used by the object in the CIL and
+then calculating the increase or decrease in space used as the object is
+relogged. This allows for a checkpoint reservation to only have to account for
+log buffer metadata used such as log header records.
+
+However, even using a static reservation for just the log metadata is
+problematic. Typically log record headers use at least 16KB of log space per
+1MB of log space consumed (512 bytes per 32k) and the reservation needs to be
+large enough to handle arbitrary sized checkpoint transactions. This
+reservation needs to be made before the checkpoint is started, and we need to
+be able to reserve the space without sleeping.  For a 8MB checkpoint, we need a
+reservation of around 150KB, which is a non-trivial amount of space.
+
+A static reservation needs to manipulate the log grant counters - we can take a
+permanent reservation on the space, but we still need to make sure we refresh
+the write reservation (the actual space available to the transaction) after
+every checkpoint transaction completion. Unfortunately, if this space is not
+available when required, then the regrant code will sleep waiting for it.
+
+The problem with this is that it can lead to deadlocks as we may need to commit
+checkpoints to be able to free up log space (refer back to the description of
+rolling transactions for an example of this).  Hence we *must* always have
+space available in the log if we are to use static reservations, and that is
+very difficult and complex to arrange. It is possible to do, but there is a
+simpler way.
+
+The simpler way of doing this is tracking the entire log space used by the
+items in the CIL and using this to dynamically calculate the amount of log
+space required by the log metadata. If this log metadata space changes as a
+result of a transaction commit inserting a new memory buffer into the CIL, then
+the difference in space required is removed from the transaction that causes
+the change. Transactions at this level will *always* have enough space
+available in their reservation for this as they have already reserved the
+maximal amount of log metadata space they require, and such a delta reservation
+will always be less than or equal to the maximal amount in the reservation.
+
+Hence we can grow the checkpoint transaction reservation dynamically as items
+are added to the CIL and avoid the need for reserving and regranting log space
+up front. This avoids deadlocks and removes a blocking point from the
+checkpoint flush code.
+
+As mentioned early, transactions can't grow to more than half the size of the
+log. Hence as part of the reservation growing, we need to also check the size
+of the reservation against the maximum allowed transaction size. If we reach
+the maximum threshold, we need to push the CIL to the log. This is effectively
+a "background flush" and is done on demand. This is identical to
+a CIL push triggered by a log force, only that there is no waiting for the
+checkpoint commit to complete. This background push is checked and executed by
+transaction commit code.
+
+If the transaction subsystem goes idle while we still have items in the CIL,
+they will be flushed by the periodic log force issued by the xfssyncd. This log
+force will push the CIL to disk, and if the transaction subsystem stays idle,
+allow the idle log to be covered (effectively marked clean) in exactly the same
+manner that is done for the existing logging method. A discussion point is
+whether this log force needs to be done more frequently than the current rate
+which is once every 30s.
+
+
+Delayed Logging: Log Item Pinning
+
+Currently log items are pinned during transaction commit while the items are
+still locked. This happens just after the items are formatted, though it could
+be done any time before the items are unlocked. The result of this mechanism is
+that items get pinned once for every transaction that is committed to the log
+buffers. Hence items that are relogged in the log buffers will have a pin count
+for every outstanding transaction they were dirtied in. When each of these
+transactions is completed, they will unpin the item once. As a result, the item
+only becomes unpinned when all the transactions complete and there are no
+pending transactions. Thus the pinning and unpinning of a log item is symmetric
+as there is a 1:1 relationship with transaction commit and log item completion.
+
+For delayed logging, however, we have an assymetric transaction commit to
+completion relationship. Every time an object is relogged in the CIL it goes
+through the commit process without a corresponding completion being registered.
+That is, we now have a many-to-one relationship between transaction commit and
+log item completion. The result of this is that pinning and unpinning of the
+log items becomes unbalanced if we retain the "pin on transaction commit, unpin
+on transaction completion" model.
+
+To keep pin/unpin symmetry, the algorithm needs to change to a "pin on
+insertion into the CIL, unpin on checkpoint completion". In other words, the
+pinning and unpinning becomes symmetric around a checkpoint context. We have to
+pin the object the first time it is inserted into the CIL - if it is already in
+the CIL during a transaction commit, then we do not pin it again. Because there
+can be multiple outstanding checkpoint contexts, we can still see elevated pin
+counts, but as each checkpoint completes the pin count will retain the correct
+value according to it's context.
+
+Just to make matters more slightly more complex, this checkpoint level context
+for the pin count means that the pinning of an item must take place under the
+CIL commit/flush lock. If we pin the object outside this lock, we cannot
+guarantee which context the pin count is associated with. This is because of
+the fact pinning the item is dependent on whether the item is present in the
+current CIL or not. If we don't pin the CIL first before we check and pin the
+object, we have a race with CIL being flushed between the check and the pin
+(or not pinning, as the case may be). Hence we must hold the CIL flush/commit
+lock to guarantee that we pin the items correctly.
+
+Delayed Logging: Concurrent Scalability
+
+A fundamental requirement for the CIL is that accesses through transaction
+commits must scale to many concurrent commits. The current transaction commit
+code does not break down even when there are transactions coming from 2048
+processors at once. The current transaction code does not go any faster than if
+there was only one CPU using it, but it does not slow down either.
+
+As a result, the delayed logging transaction commit code needs to be designed
+for concurrency from the ground up. It is obvious that there are serialisation
+points in the design - the three important ones are:
+
+	1. Locking out new transaction commits while flushing the CIL
+	2. Adding items to the CIL and updating item space accounting
+	3. Checkpoint commit ordering
+
+Looking at the transaction commit and CIL flushing interactions, it is clear
+that we have a many-to-one interaction here. That is, the only restriction on
+the number of concurrent transactions that can be trying to commit at once is
+the amount of space available in the log for their reservations. The practical
+limit here is in the order of several hundred concurrent transactions for a
+128MB log, which means that it is generally one per CPU in a machine.
+
+The amount of time a transaction commit needs to hold out a flush is a
+relatively long period of time - the pinning of log items needs to be done
+while we are holding out a CIL flush, so at the moment that means it is held
+across the formatting of the objects into memory buffers (i.e. while memcpy()s
+are in progress). Ultimately a two pass algorithm where the formatting is done
+separately to the pinning of objects could be used to reduce the hold time of
+the transaction commit side.
+
+Because of the number of potential transaction commit side holders, the lock
+really needs to be a sleeping lock - if the CIL flush takes the lock, we do not
+want every other CPU in the machine spinning on the CIL lock. Given that
+flushing the CIL could involve walking a list of tens of thousands of log
+items, it will get held for a significant time and so spin contention is a
+significant concern. Preventing lots of CPUs spinning doing nothing is the
+main reason for choosing a sleeping lock even though nothing in either the
+transaction commit or CIL flush side sleeps with the lock held.
+
+It should also be noted that CIL flushing is also a relatively rare operation
+compared to transaction commit for asynchronous transaction workloads - only
+time will tell if using a read-write semaphore for exclusion will limit
+transaction commit concurrency due to cache line bouncing of the lock on the
+read side.
+
+The second serialisation point is on the transaction commit side where items
+are inserted into the CIL. Because transactions can enter this code
+concurrently, the CIL needs to be protected separately from the above
+commit/flush exclusion. It also needs to be an exclusive lock but it is only
+held for a very short time and so a spin lock is appropriate here. It is
+possible that this lock will become a contention point, but given the short
+hold time once per transaction I think that contention is unlikely.
+
+The final serialisation point is the checkpoint commit record ordering code
+that is run as part of the checkpoint commit and log force sequencing. The code
+path that triggers a CIL flush (i.e. whatever triggers the log force) will enter
+an ordering loop after writing all the log vectors into the log buffers but
+before writing the commit record. This loop walks the list of committing
+checkpoints and needs to block waiting for checkpoints to complete their commit
+record write. As a result it needs a lock and a wait variable. Log force
+sequencing also requires the same lock, list walk, and blocking mechanism to
+ensure completion of checkpoints.
+
+These two sequencing operations can use the mechanism even though the
+events they are waiting for are different. The checkpoint commit record
+sequencing needs to wait until checkpoint contexts contain a commit LSN
+(obtained through completion of a commit record write) while log force
+sequencing needs to wait until previous checkpoint contexts are removed from
+the committing list (i.e. they've completed). A simple wait variable and
+broadcast wakeups (thundering herds) has been used to implement these two
+serialisation queues. They use the same lock as the CIL, too. If we see too
+much contention on the CIL lock, or too many context switches as a result of
+the broadcast wakeups these operations can be put under a new spinlock and
+given separate wait lists to reduce lock contention and the number of processes
+woken by the wrong event.
+
+
+Lifecycle Changes
+
+The existing log item life cycle is as follows:
+
+	1. Transaction allocate
+	2. Transaction reserve
+	3. Lock item
+	4. Join item to transaction
+		If not already attached,
+			Allocate log item
+			Attach log item to owner item
+		Attach log item to transaction
+	5. Modify item
+		Record modifications in log item
+	6. Transaction commit
+		Pin item in memory
+		Format item into log buffer
+		Write commit LSN into transaction
+		Unlock item
+		Attach transaction to log buffer
+
+	<log buffer IO dispatched>
+	<log buffer IO completes>
+
+	7. Transaction completion
+		Mark log item committed
+		Insert log item into AIL
+			Write commit LSN into log item
+		Unpin log item
+	8. AIL traversal
+		Lock item
+		Mark log item clean
+		Flush item to disk
+
+	<item IO completion>
+
+	9. Log item removed from AIL
+		Moves log tail
+		Item unlocked
+
+Essentially, steps 1-6 operate independently from step 7, which is also
+independent of steps 8-9. An item can be locked in steps 1-6 or steps 8-9
+at the same time step 7 is occurring, but only steps 1-6 or 8-9 can occur
+at the same time. If the log item is in the AIL or between steps 6 and 7
+and steps 1-6 are re-entered, then the item is relogged. Only when steps 8-9
+are entered and completed is the object considered clean.
+
+With delayed logging, there are new steps inserted into the life cycle:
+
+	1. Transaction allocate
+	2. Transaction reserve
+	3. Lock item
+	4. Join item to transaction
+		If not already attached,
+			Allocate log item
+			Attach log item to owner item
+		Attach log item to transaction
+	5. Modify item
+		Record modifications in log item
+	6. Transaction commit
+		Pin item in memory if not pinned in CIL
+		Format item into log vector + buffer
+		Attach log vector and buffer to log item
+		Insert log item into CIL
+		Write CIL context sequence into transaction
+		Unlock item
+
+	<next log force>
+
+	7. CIL push
+		lock CIL flush
+		Chain log vectors and buffers together
+		Remove items from CIL
+		unlock CIL flush
+		write log vectors into log
+		sequence commit records
+		attach checkpoint context to log buffer
+
+	<log buffer IO dispatched>
+	<log buffer IO completes>
+
+	8. Checkpoint completion
+		Mark log item committed
+		Insert item into AIL
+			Write commit LSN into log item
+		Unpin log item
+	9. AIL traversal
+		Lock item
+		Mark log item clean
+		Flush item to disk
+	<item IO completion>
+	10. Log item removed from AIL
+		Moves log tail
+		Item unlocked
+
+From this, it can be seen that the only life cycle differences between the two
+logging methods are in the middle of the life cycle - they still have the same
+beginning and end and execution constraints. The only differences are in the
+commiting of the log items to the log itself and the completion processing.
+Hence delayed logging should not introduce any constraints on log item
+behaviour, allocation or freeing that don't already exist.
+
+As a result of this zero-impact "insertion" of delayed logging infrastructure
+and the design of the internal structures to avoid on disk format changes, we
+can basically switch between delayed logging and the existing mechanism with a
+mount option. Fundamentally, there is no reason why the log manager would not
+be able to swap methods automatically and transparently depending on load
+characteristics, but this should not be necessary if delayed logging works as
+designed.
+
+Roadmap:
+
+2.6.39 Switch default mount option to use delayed logging
+	=> should be roughly 12 months after initial merge
+	=> enough time to shake out remaining problems before next round of
+	   enterprise distro kernel rebases
diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt
index 9878f50d6ed..7bff3e4f35d 100644
--- a/Documentation/filesystems/xfs.txt
+++ b/Documentation/filesystems/xfs.txt
@@ -131,17 +131,6 @@ When mounting an XFS filesystem, the following options are accepted.
 	Don't check for double mounted file systems using the file system uuid.
 	This is useful to mount LVM snapshot volumes.
 
-  osyncisosync
-	Make O_SYNC writes implement true O_SYNC.  WITHOUT this option,
-	Linux XFS behaves as if an "osyncisdsync" option is used,
-	which will make writes to files opened with the O_SYNC flag set
-	behave as if the O_DSYNC flag had been used instead.
-	This can result in better performance without compromising
-	data safety.
-	However if this option is not in effect, timestamp updates from
-	O_SYNC writes can be lost if the system crashes.
-	If timestamp updates are critical, use the osyncisosync option.
-
   uquota/usrquota/uqnoenforce/quota
 	User disk quota accounting enabled, and limits (optionally)
 	enforced.  Refer to xfs_quota(8) for further details.