Merge branch 'linux-2.6' into for-2.6.24

[linux-2.6-omap-h63xx.git] / Documentation / filesystems / Locking

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 790ef6fbe495914f94ea351e92834d9fb206f80c..f0f825808ca463023d815b3d38679851b55a6ff6 100644 (file)
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -15,6 +15,7 @@ prototypes:
        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);
 
 locking rules:
        none have BKL
@@ -25,6 +26,7 @@ d_compare:    no              yes             no              no
 d_delete:      yes             no              yes             no
 d_release:     no              no              no              yes
 d_iput:                no              no              no              yes
+d_dname:       no              no              no              no
 
 --------------------------- inode_operations --------------------------- 
 prototypes:
@@ -52,7 +54,7 @@ ata *);
 
 locking rules:
        all may block, none have BKL
-               i_sem(inode)
+               i_mutex(inode)
 lookup:                yes
 create:                yes
 link:          yes (both)
@@ -72,7 +74,7 @@ setxattr:     yes
 getxattr:      no
 listxattr:     no
 removexattr:   yes
-       Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_sem on
+       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
@@ -171,6 +173,7 @@ prototypes:
        int (*releasepage) (struct page *, int);
        int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
                        loff_t offset, unsigned long nr_segs);
+       int (*launder_page) (struct page *);
 
 locking rules:
        All except set_page_dirty may block
@@ -188,6 +191,7 @@ bmap:                       yes
 invalidatepage:                no      yes
 releasepage:           no      yes
 direct_IO:             no
+launder_page:          no      yes
 
        ->prepare_write(), ->commit_write(), ->sync_page() and ->readpage()
 may be called from the request handler (/dev/loop).
@@ -281,6 +285,12 @@ 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.
 
+       ->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)
@@ -451,7 +461,7 @@ 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_sem on inode.
+->fsync() has i_mutex on inode.
 
 --------------------------- dquot_operations -------------------------------
 prototypes:
@@ -500,13 +510,24 @@ More details about quota locking can be found in fs/dquot.c.
 prototypes:
        void (*open)(struct vm_area_struct*);
        void (*close)(struct vm_area_struct*);
+       int (*fault)(struct vm_area_struct*, struct vm_fault *);
        struct page *(*nopage)(struct vm_area_struct*, unsigned long, int *);
+       int (*page_mkwrite)(struct vm_area_struct *, struct page *);
 
 locking rules:
-               BKL     mmap_sem
+               BKL     mmap_sem        PageLocked(page)
 open:          no      yes
 close:         no      yes
+fault:         no      yes
 nopage:                no      yes
+page_mkwrite:  no      yes             no
+
+       ->page_mkwrite() is called when a previously read-only page is
+about to become writeable. The file system is responsible for
+protecting against truncate races. Once appropriate action has been
+taking to lock out truncate, the page range should be verified to be
+within i_size. The page mapping should also be checked that it is not
+NULL.
 
 ================================================================================
                        Dubious stuff