3 files changed, 68 insertions, 29 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 8e2da1e06e3b..e540a24e5d06 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -9,7 +9,7 @@ be able to use diff(1).
 
 --------------------------- dentry_operations --------------------------
 prototypes:
-        int (*d_revalidate)(struct dentry *, struct nameidata *);
+        int (*d_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 *,
@@ -37,9 +37,8 @@ d_manage:	no		no		yes (ref-walk)	maybe
 
 --------------------------- inode_operations --------------------------- 
 prototypes:
-        int (*create) (struct inode *,struct dentry *,umode_t, struct nameidata *);
-        struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameid
-ata *);
+        int (*create) (struct inode *,struct dentry *,umode_t, bool);
+        struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
         int (*link) (struct dentry *,struct inode *,struct dentry *);
         int (*unlink) (struct inode *,struct dentry *);
         int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -62,6 +61,9 @@ ata *);
         int (*removexattr) (struct dentry *, const char *);
         int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
         void (*update_time)(struct inode *, struct timespec *, int);
+        int (*atomic_open)(struct inode *, struct dentry *,
+                                struct file *, unsigned open_flag,
+                                umode_t create_mode, int *opened);
 
 locking rules:
         all may block
@@ -89,6 +91,7 @@ listxattr:	no
 removexattr:    yes
 fiemap:         no
 update_time:    no
+atomic_open:    yes
 
         Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
@@ -111,7 +114,6 @@ prototypes:
         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);
         int (*freeze_fs) (struct super_block *);
         int (*unfreeze_fs) (struct super_block *);
@@ -133,10 +135,9 @@ write_inode:
 drop_inode:                             !!!inode->i_lock!!!
 evict_inode:
 put_super:              write
-write_super:            read
 sync_fs:                read
-freeze_fs:              read
-unfreeze_fs:            read
+freeze_fs:              write
+unfreeze_fs:            write
 statfs:                 maybe(read)     (see below)
 remount_fs:             write
 umount_begin:           no
@@ -203,6 +204,8 @@ prototypes:
         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 *);
+        int (*swap_activate)(struct file *);
+        int (*swap_deactivate)(struct file *);
 
 locking rules:
         All except set_page_dirty and freepage may block
@@ -226,6 +229,8 @@ migratepage:		yes (both)
 launder_page:           yes
 is_partially_uptodate:  yes
 error_remove_page:      yes
+swap_activate:          no
+swap_deactivate:        no
 
         ->write_begin(), ->write_end(), ->sync_page() and ->readpage()
 may be called from the request handler (/dev/loop).
@@ -327,6 +332,15 @@ 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.
 
+        ->swap_activate will be called with a non-zero argument on
+files backing (non block device backed) swapfiles. A return value
+of zero indicates success, in which case this file can be used for
+backing swapspace. The swapspace operations will be proxied to the
+address space operations.
+
+        ->swap_deactivate() will be called in the sys_swapoff()
+path after ->swap_activate() returned success.
+
 ----------------------- file_lock_operations ------------------------------
 prototypes:
         void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
@@ -343,7 +357,6 @@ prototypes:
         int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
         void (*lm_notify)(struct file_lock *);  /* unblock callback */
         int (*lm_grant)(struct file_lock *, struct file_lock *, int);
-        void (*lm_release_private)(struct file_lock *);
         void (*lm_break)(struct file_lock *); /* break_lease callback */
         int (*lm_change)(struct file_lock **, int);
 
@@ -352,7 +365,6 @@ locking rules:
 lm_compare_owner:       yes             no
 lm_notify:              yes             no
 lm_grant:               no              no
-lm_release_private:     maybe           no
 lm_break:               yes             no
 lm_change               yes             no
 
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 8c91d1057d9a..0742feebc6e2 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -94,9 +94,8 @@ protected.
 ---
 [mandatory]
 
-BKL is also moved from around sb operations.  ->write_super() Is now called 
-without BKL held.  BKL should have been shifted into individual fs sb_op
-functions.  If you don't need it, remove it.  
+BKL is also moved from around sb operations. BKL should have been shifted into
+individual fs sb_op functions.  If you don't need it, remove it.
 
 ---
 [informational]
@@ -355,12 +354,10 @@ protects *all* the dcache state of a given dentry.
 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.
+        Even though i_dentry and i_rcu share storage in a union, we will
+initialize the former in inode_init_always(), so just leave it alone in
+the callback.  It used to be necessary to clean it there, but not anymore
+(starting at 3.2).
 
 --
 [recommended]
@@ -433,3 +430,14 @@ release it yourself.
         d_alloc_root() is gone, along with a lot of bugs caused by code
 misusing it.  Replacement: d_make_root(inode).  The difference is,
 d_make_root() drops the reference to inode if dentry allocation fails.  
+
+--
+[mandatory]
+        The witch is dead!  Well, 2/3 of it, anyway.  ->d_revalidate() and
+->lookup() do *not* take struct nameidata anymore; just the flags.
+--
+[mandatory]
+        ->create() doesn't take struct nameidata *; unlike the previous
+two, it gets "is it an O_EXCL or equivalent?" boolean argument.  Note that
+local filesystems can ignore tha argument - they are guaranteed that the
+object doesn't exist.  It's remote/distributed ones that might care...
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index efd23f481704..2ee133e030c3 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -216,7 +216,6 @@ struct super_operations {
         void (*drop_inode) (struct inode *);
         void (*delete_inode) (struct inode *);
         void (*put_super) (struct super_block *);
-        void (*write_super) (struct super_block *);
         int (*sync_fs)(struct super_block *sb, int wait);
         int (*freeze_fs) (struct super_block *);
         int (*unfreeze_fs) (struct super_block *);
@@ -273,9 +272,6 @@ or bottom half).
   put_super: called when the VFS wishes to free the superblock
         (i.e. unmount). This is called with the superblock lock held
 
-  write_super: called when the VFS superblock needs to be written to
-        disc. This method is optional
-
   sync_fs: called when VFS is writing out all dirty data associated with
         a superblock. The second parameter indicates whether the method
         should wait until the write out has been completed. Optional.
@@ -341,8 +337,8 @@ This describes how the VFS can manipulate an inode in your
 filesystem. As of kernel 2.6.22, the following members are defined:
 
 struct inode_operations {
-        int (*create) (struct inode *,struct dentry *, umode_t, struct nameidata *);
-        struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
+        int (*create) (struct inode *,struct dentry *, umode_t, bool);
+        struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
         int (*link) (struct dentry *,struct inode *,struct dentry *);
         int (*unlink) (struct inode *,struct dentry *);
         int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -364,6 +360,9 @@ struct inode_operations {
         ssize_t (*listxattr) (struct dentry *, char *, size_t);
         int (*removexattr) (struct dentry *, const char *);
         void (*update_time)(struct inode *, struct timespec *, int);
+        int (*atomic_open)(struct inode *, struct dentry *,
+                                struct file *, unsigned open_flag,
+                                umode_t create_mode, int *opened);
 };
 
 Again, all methods are called without any locks being held, unless
@@ -476,6 +475,14 @@ otherwise noted.
         an inode.  If this is not defined the VFS will update the inode itself
         and call mark_inode_dirty_sync.
 
+  atomic_open: called on the last component of an open.  Using this optional
+        method the filesystem can look up, possibly create and open the file in
+        one atomic operation.  If it cannot perform this (e.g. the file type
+        turned out to be wrong) it may signal this by returning 1 instead of
+        usual 0 or -ve .  This method is only called if the last
+        component is negative or needs lookup.  Cached positive dentries are
+        still handled by f_op->open().
+
 The Address Space Object
 ========================
 
@@ -581,6 +588,8 @@ struct address_space_operations {
         int (*migratepage) (struct page *, struct page *);
         int (*launder_page) (struct page *);
         int (*error_remove_page) (struct mapping *mapping, struct page *page);
+        int (*swap_activate)(struct file *);
+        int (*swap_deactivate)(struct file *);
 };
 
   writepage: called by the VM to write a dirty page to backing store.
@@ -749,6 +758,16 @@ struct address_space_operations {
         Setting this implies you deal with pages going away under you,
         unless you have them locked or reference counts increased.
 
+  swap_activate: Called when swapon is used on a file to allocate
+        space if necessary and pin the block lookup information in
+        memory. A return value of zero indicates success,
+        in which case this file can be used to back swapspace. The
+        swapspace operations will be proxied to this address space's
+        ->swap_{out,in} methods.
+
+  swap_deactivate: Called during swapoff on files where swap_activate
+        was successful.
+
 
 The File Object
 ===============
@@ -891,7 +910,7 @@ the VFS uses a default. As of kernel 2.6.22, the following members are
 defined:
 
 struct dentry_operations {
-        int (*d_revalidate)(struct dentry *, struct nameidata *);
+        int (*d_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 *,
@@ -910,11 +929,11 @@ struct dentry_operations {
         dcache. Most filesystems leave this as NULL, because all their
         dentries in the dcache are valid
 
-        d_revalidate may be called in rcu-walk mode (nd->flags & LOOKUP_RCU).
+        d_revalidate may be called in rcu-walk mode (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.
+        used without care (because they can change and, in d_inode case, even
+        become NULL under us).
 
         If a situation is encountered that rcu-walk cannot handle, return
         -ECHILD and it will be called again in ref-walk mode.