4 files changed, 66 insertions, 40 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 0706d32a61e6..fe7afe225381 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -11,10 +11,8 @@ be able to use diff(1).
 prototypes:
         int (*d_revalidate)(struct dentry *, unsigned int);
         int (*d_weak_revalidate)(struct dentry *, unsigned int);
-        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 *,
+        int (*d_hash)(const struct dentry *, struct qstr *);
+        int (*d_compare)(const struct dentry *, const struct dentry *,
                         unsigned int, const char *, const struct qstr *);
         int (*d_delete)(struct dentry *);
         void (*d_release)(struct dentry *);
@@ -66,6 +64,7 @@ prototypes:
         int (*atomic_open)(struct inode *, struct dentry *,
                                 struct file *, unsigned open_flag,
                                 umode_t create_mode, int *opened);
+        int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 
 locking rules:
         all may block
@@ -93,6 +92,7 @@ removexattr:	yes
 fiemap:         no
 update_time:    no
 atomic_open:    yes
+tmpfile:        no
 
         Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
@@ -189,7 +189,7 @@ prototypes:
                                 loff_t pos, unsigned len, unsigned copied,
                                 struct page *page, void *fsdata);
         sector_t (*bmap)(struct address_space *, sector_t);
-        int (*invalidatepage) (struct page *, unsigned long);
+        void (*invalidatepage) (struct page *, unsigned int, unsigned int);
         int (*releasepage) (struct page *, int);
         void (*freepage)(struct page *);
         int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
@@ -310,8 +310,8 @@ 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
-returns zero on success.  If ->invalidatepage is zero, the kernel uses
+some or all of the buffers from the page when it is being truncated. It
+returns zero on success. If ->invalidatepage is zero, the kernel uses
 block_invalidatepage() instead.
 
         ->releasepage() is called when the kernel is about to try to drop the
@@ -344,25 +344,38 @@ prototypes:
 
 
 locking rules:
-                        file_lock_lock  may block
+                        inode->i_lock   may block
 fl_copy_lock:           yes             no
 fl_release_private:     maybe           no
 
 ----------------------- lock_manager_operations ---------------------------
 prototypes:
         int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
+        unsigned long (*lm_owner_key)(struct file_lock *);
         void (*lm_notify)(struct file_lock *);  /* unblock callback */
         int (*lm_grant)(struct file_lock *, struct file_lock *, int);
         void (*lm_break)(struct file_lock *); /* break_lease callback */
         int (*lm_change)(struct file_lock **, int);
 
 locking rules:
-                        file_lock_lock  may block
-lm_compare_owner:       yes             no
-lm_notify:              yes             no
-lm_grant:               no              no
-lm_break:               yes             no
-lm_change               yes             no
+
+                        inode->i_lock   blocked_lock_lock       may block
+lm_compare_owner:       yes[1]          maybe                   no
+lm_owner_key            yes[1]          yes                     no
+lm_notify:              yes             yes                     no
+lm_grant:               no              no                      no
+lm_break:               yes             no                      no
+lm_change               yes             no                      no
+
+[1]:    ->lm_compare_owner and ->lm_owner_key are generally called with
+*an* inode->i_lock held. It may not be the i_lock of the inode
+associated with either file_lock argument! This is the case with deadlock
+detection, since the code has to chase down the owners of locks that may
+be entirely unrelated to the one on which the lock is being acquired.
+For deadlock detection however, the blocked_lock_lock is also held. The
+fact that these locks are held ensures that the file_locks do not
+disappear out from under you while doing the comparison or generating an
+owner key.
 
 --------------------------- buffer_head -----------------------------------
 prototypes:
@@ -414,7 +427,7 @@ prototypes:
         ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
         ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
         ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
-        int (*readdir) (struct file *, void *, filldir_t);
+        int (*iterate) (struct file *, struct dir_context *);
         unsigned int (*poll) (struct file *, struct poll_table_struct *);
         long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
         long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index bd3c56c67380..b91e2f26b672 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -98,8 +98,13 @@ Cleaning Overhead
 MOUNT OPTIONS
 ================================================================================
 
-background_gc_off      Turn off cleaning operations, namely garbage collection,
-                       triggered in background when I/O subsystem is idle.
+background_gc=%s       Turn on/off cleaning operations, namely garbage
+                       collection, triggered in background when I/O subsystem is
+                       idle. If background_gc=on, it will turn on the garbage
+                       collection and if background_gc=off, garbage collection
+                       will be truned off.
+                       Default value for this option is on. So garbage
+                       collection is on by default.
 disable_roll_forward   Disable the roll-forward recovery routine
 discard                Issue discard/TRIM commands when a segment is cleaned.
 no_heap                Disable heap-style segment allocation which finds free
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 4db22f6491e0..206a1bdc7321 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -445,3 +445,9 @@ object doesn't exist.  It's remote/distributed ones that might care...
 [mandatory]
         FS_REVAL_DOT is gone; if you used to have it, add ->d_weak_revalidate()
 in your dentry operations instead.
+--
+[mandatory]
+        vfs_readdir() is gone; switch to iterate_dir() instead
+--
+[mandatory]
+        ->readdir() is gone now; switch to ->iterate()
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index bc4b06b3160a..1f0ba30ae47e 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -360,6 +360,8 @@ struct inode_operations {
         int (*removexattr) (struct dentry *, const char *);
         void (*update_time)(struct inode *, struct timespec *, int);
         int (*atomic_open)(struct inode *, struct dentry *,
+        int (*tmpfile) (struct inode *, struct dentry *, umode_t);
+} ____cacheline_aligned;
                                 struct file *, unsigned open_flag,
                                 umode_t create_mode, int *opened);
 };
@@ -472,6 +474,9 @@ otherwise noted.
         component is negative or needs lookup.  Cached positive dentries are
         still handled by f_op->open().
 
+  tmpfile: called in the end of O_TMPFILE open().  Optional, equivalent to
+        atomically creating, opening and unlinking a file in given directory.
+
 The Address Space Object
 ========================
 
@@ -549,7 +554,7 @@ struct address_space_operations
 -------------------------------
 
 This describes how the VFS can manipulate mapping of a file to page cache in
-your filesystem. As of kernel 2.6.22, the following members are defined:
+your filesystem. The following members are defined:
 
 struct address_space_operations {
         int (*writepage)(struct page *page, struct writeback_control *wbc);
@@ -566,7 +571,7 @@ struct address_space_operations {
                                 loff_t pos, unsigned len, unsigned copied,
                                 struct page *page, void *fsdata);
         sector_t (*bmap)(struct address_space *, sector_t);
-        int (*invalidatepage) (struct page *, unsigned long);
+        void (*invalidatepage) (struct page *, unsigned int, unsigned int);
         int (*releasepage) (struct page *, int);
         void (*freepage)(struct page *);
         ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
@@ -685,14 +690,14 @@ struct address_space_operations {
   invalidatepage: If a page has PagePrivate set, then invalidatepage
         will be called when part or all of the page is to be removed
         from the address space.  This generally corresponds to either a
-        truncation or a complete invalidation of the address space
-        (in the latter case 'offset' will always be 0).
-        Any private data associated with the page should be updated
-        to reflect this truncation.  If offset is 0, then
-        the private data should be released, because the page
-        must be able to be completely discarded.  This may be done by
-        calling the ->releasepage function, but in this case the
-        release MUST succeed.
+        truncation, punch hole  or a complete invalidation of the address
+        space (in the latter case 'offset' will always be 0 and 'length'
+        will be PAGE_CACHE_SIZE). Any private data associated with the page
+        should be updated to reflect this truncation.  If offset is 0 and
+        length is PAGE_CACHE_SIZE, then the private data should be released,
+        because the page must be able to be completely discarded.  This may
+        be done by calling the ->releasepage function, but in this case the
+        release MUST succeed.
 
   releasepage: releasepage is called on PagePrivate pages to indicate
         that the page should be freed if possible.  ->releasepage
@@ -777,7 +782,7 @@ struct file_operations {
         ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
         ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
         ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
-        int (*readdir) (struct file *, void *, filldir_t);
+        int (*iterate) (struct file *, struct dir_context *);
         unsigned int (*poll) (struct file *, struct poll_table_struct *);
         long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
         long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
@@ -815,7 +820,7 @@ otherwise noted.
 
   aio_write: called by io_submit(2) and other asynchronous I/O operations
 
-  readdir: called when the VFS needs to read the directory contents
+  iterate: called when the VFS needs to read the directory contents
 
   poll: called by the VFS when a process wants to check if there is
         activity on this file and (optionally) go to sleep until there
@@ -901,10 +906,8 @@ defined:
 struct dentry_operations {
         int (*d_revalidate)(struct dentry *, unsigned int);
         int (*d_weak_revalidate)(struct dentry *, unsigned int);
-        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 *,
+        int (*d_hash)(const struct dentry *, struct qstr *);
+        int (*d_compare)(const struct dentry *, const struct dentry *,
                         unsigned int, const char *, const struct qstr *);
         int (*d_delete)(const struct dentry *);
         void (*d_release)(struct dentry *);
@@ -949,25 +952,24 @@ struct dentry_operations {
 
   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.
+        to be hashed into.
 
         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.
+        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
+        possible, and should not or store into the dentry.
+        Should not dereference pointers outside the dentry 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.
+        ->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.