Merge branch 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull the big VFS changes from Al Viro:
 "This one is *big* and changes quite a few things around VFS.  What's in there:

   - the first of two really major architecture changes - death to open
     intents.

     The former is finally there; it was very long in making, but with
     Miklos getting through really hard and messy final push in
     fs/namei.c, we finally have it.  Unlike his variant, this one
     doesn't introduce struct opendata; what we have instead is
     ->atomic_open() taking preallocated struct file * and passing
     everything via its fields.

     Instead of returning struct file *, it returns -E...  on error, 0
     on success and 1 in "deal with it yourself" case (e.g.  symlink
     found on server, etc.).

     See comments before fs/namei.c:atomic_open().  That made a lot of
     goodies finally possible and quite a few are in that pile:
     ->lookup(), ->d_revalidate() and ->create() do not get struct
     nameidata * anymore; ->lookup() and ->d_revalidate() get lookup
     flags instead, ->create() gets "do we want it exclusive" flag.

     With the introduction of new helper (kern_path_locked()) we are rid
     of all struct nameidata instances outside of fs/namei.c; it's still
     visible in namei.h, but not for long.  Come the next cycle,
     declaration will move either to fs/internal.h or to fs/namei.c
     itself.  [me, miklos, hch]

   - The second major change: behaviour of final fput().  Now we have
     __fput() done without any locks held by caller *and* not from deep
     in call stack.

     That obviously lifts a lot of constraints on the locking in there.
     Moreover, it's legal now to call fput() from atomic contexts (which
     has immediately simplified life for aio.c).  We also don't need
     anti-recursion logics in __scm_destroy() anymore.

     There is a price, though - the damn thing has become partially
     asynchronous.  For fput() from normal process we are guaranteed
     that pending __fput() will be done before the caller returns to
     userland, exits or gets stopped for ptrace.

     For kernel threads and atomic contexts it's done via
     schedule_work(), so theoretically we might need a way to make sure
     it's finished; so far only one such place had been found, but there
     might be more.

     There's flush_delayed_fput() (do all pending __fput()) and there's
     __fput_sync() (fput() analog doing __fput() immediately).  I hope
     we won't need them often; see warnings in fs/file_table.c for
     details.  [me, based on task_work series from Oleg merged last
     cycle]

   - sync series from Jan

   - large part of "death to sync_supers()" work from Artem; the only
     bits missing here are exofs and ext4 ones.  As far as I understand,
     those are going via the exofs and ext4 trees resp.; once they are
     in, we can put ->write_super() to the rest, along with the thread
     calling it.

   - preparatory bits from unionmount series (from dhowells).

   - assorted cleanups and fixes all over the place, as usual.

  This is not the last pile for this cycle; there's at least jlayton's
  ESTALE work and fsfreeze series (the latter - in dire need of fixes,
  so I'm not sure it'll make the cut this cycle).  I'll probably throw
  symlink/hardlink restrictions stuff from Kees into the next pile, too.
  Plus there's a lot of misc patches I hadn't thrown into that one -
  it's large enough as it is..."

* 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (127 commits)
  ext4: switch EXT4_IOC_RESIZE_FS to mnt_want_write_file()
  btrfs: switch btrfs_ioctl_balance() to mnt_want_write_file()
  switch dentry_open() to struct path, make it grab references itself
  spufs: shift dget/mntget towards dentry_open()
  zoran: don't bother with struct file * in zoran_map
  ecryptfs: don't reinvent the wheels, please - use struct completion
  don't expose I_NEW inodes via dentry->d_inode
  tidy up namei.c a bit
  unobfuscate follow_up() a bit
  ext3: pass custom EOF to generic_file_llseek_size()
  ext4: use core vfs llseek code for dir seeks
  vfs: allow custom EOF in generic_file_llseek code
  vfs: Avoid unnecessary WB_SYNC_NONE writeback during sys_sync and reorder sync passes
  vfs: Remove unnecessary flushing of block devices
  vfs: Make sys_sync writeout also block device inodes
  vfs: Create function for iterating over block devices
  vfs: Reorder operations during sys_sync
  quota: Move quota syncing to ->sync_fs method
  quota: Split dquot_quota_sync() to writeback and cache flushing part
  vfs: Move noop_backing_dev_info check from sync into writeback
  ...

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.

Documentation/filesystems/porting

@@ -355,12 +355,10 @@ 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 +431,14 @@ 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...

Documentation/filesystems/vfs.txt

@@ -341,8 +341,8 @@ 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 +364,9 @@ 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 +479,14 @@ 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
 ========================
 
@@ -891,7 +902,7 @@ 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 +921,11 @@ 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.

arch/powerpc/platforms/cell/spufs/inode.c

@@ -317,28 +317,23 @@ out:
 	return ret;
 }
 
-static int spufs_context_open(struct dentry *dentry, struct vfsmount *mnt)
+static int spufs_context_open(struct path *path)
 {
 	int ret;
 	struct file *filp;
 
 	ret = get_unused_fd();
-	if (ret < 0) {
-		dput(dentry);
-		mntput(mnt);
-		goto out;
-	}
+	if (ret < 0)
+		return ret;
 
-	filp = dentry_open(dentry, mnt, O_RDONLY, current_cred());
+	filp = dentry_open(path, O_RDONLY, current_cred());
 	if (IS_ERR(filp)) {
 		put_unused_fd(ret);
-		ret = PTR_ERR(filp);
-		goto out;
+		return PTR_ERR(filp);
 	}
 
 	filp->f_op = &spufs_context_fops;
 	fd_install(ret, filp);
-out:
 	return ret;
 }
 
@@ -453,6 +448,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 	int affinity;
 	struct spu_gang *gang;
 	struct spu_context *neighbor;
+	struct path path = {.mnt = mnt, .dentry = dentry};
 
 	ret = -EPERM;
 	if ((flags & SPU_CREATE_NOSCHED) &&
@@ -495,11 +491,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 			put_spu_context(neighbor);
 	}
 
-	/*
-	 * get references for dget and mntget, will be released
-	 * in error path of *_open().
-	 */
-	ret = spufs_context_open(dget(dentry), mntget(mnt));
+	ret = spufs_context_open(&path);
 	if (ret < 0) {
 		WARN_ON(spufs_rmdir(inode, dentry));
 		if (affinity)
@@ -556,28 +548,27 @@ out:
 	return ret;
 }
 
-static int spufs_gang_open(struct dentry *dentry, struct vfsmount *mnt)
+static int spufs_gang_open(struct path *path)
 {
 	int ret;
 	struct file *filp;
 
 	ret = get_unused_fd();
-	if (ret < 0) {
-		dput(dentry);
-		mntput(mnt);
-		goto out;
-	}
+	if (ret < 0)
+		return ret;
 
-	filp = dentry_open(dentry, mnt, O_RDONLY, current_cred());
+	/*
+	 * get references for dget and mntget, will be released
+	 * in error path of *_open().
+	 */
+	filp = dentry_open(path, O_RDONLY, current_cred());
 	if (IS_ERR(filp)) {
 		put_unused_fd(ret);
-		ret = PTR_ERR(filp);
-		goto out;
+		return PTR_ERR(filp);
 	}
 
 	filp->f_op = &simple_dir_operations;
 	fd_install(ret, filp);
-out:
 	return ret;
 }
 
@@ -585,17 +576,14 @@ static int spufs_create_gang(struct inode *inode,
 			struct dentry *dentry,
 			struct vfsmount *mnt, umode_t mode)
 {
+	struct path path = {.mnt = mnt, .dentry = dentry};
 	int ret;
 
 	ret = spufs_mkgang(inode, dentry, mode & S_IRWXUGO);
 	if (ret)
 		goto out;
 
-	/*
-	 * get references for dget and mntget, will be released
-	 * in error path of *_open().
-	 */
-	ret = spufs_gang_open(dget(dentry), mntget(mnt));
+	ret = spufs_gang_open(&path);
 	if (ret < 0) {
 		int err = simple_rmdir(inode, dentry);
 		WARN_ON(err);

drivers/base/devtmpfs.c

@@ -227,33 +227,24 @@ static int handle_create(const char *nodename, umode_t mode, struct device *dev)
 
 static int dev_rmdir(const char *name)
 {
-	struct nameidata nd;
+	struct path parent;
 	struct dentry *dentry;
 	int err;
 
-	err = kern_path_parent(name, &nd);
-	if (err)
-		return err;
-
-	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
-	if (!IS_ERR(dentry)) {
-		if (dentry->d_inode) {
-			if (dentry->d_inode->i_private == &thread)
-				err = vfs_rmdir(nd.path.dentry->d_inode,
-						dentry);
-			else
-				err = -EPERM;
-		} else {
-			err = -ENOENT;
-		}
-		dput(dentry);
+	dentry = kern_path_locked(name, &parent);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	if (dentry->d_inode) {
+		if (dentry->d_inode->i_private == &thread)
+			err = vfs_rmdir(parent.dentry->d_inode, dentry);
+		else
+			err = -EPERM;
 	} else {
-		err = PTR_ERR(dentry);
+		err = -ENOENT;
 	}
-
-	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
-	path_put(&nd.path);
+	dput(dentry);
+	mutex_unlock(&parent.dentry->d_inode->i_mutex);
+	path_put(&parent);
 	return err;
 }
 
@@ -305,50 +296,43 @@ static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *sta
 
 static int handle_remove(const char *nodename, struct device *dev)
 {
-	struct nameidata nd;
+	struct path parent;
 	struct dentry *dentry;
-	struct kstat stat;
 	int deleted = 1;
 	int err;
 
-	err = kern_path_parent(nodename, &nd);
-	if (err)
-		return err;
+	dentry = kern_path_locked(nodename, &parent);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
 
-	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
-	if (!IS_ERR(dentry)) {
-		if (dentry->d_inode) {
-			err = vfs_getattr(nd.path.mnt, dentry, &stat);
-			if (!err && dev_mynode(dev, dentry->d_inode, &stat)) {
-				struct iattr newattrs;
-				/*
-				 * before unlinking this node, reset permissions
-				 * of possible references like hardlinks
-				 */
-				newattrs.ia_uid = 0;
-				newattrs.ia_gid = 0;
-				newattrs.ia_mode = stat.mode & ~0777;
-				newattrs.ia_valid =
-					ATTR_UID|ATTR_GID|ATTR_MODE;
-				mutex_lock(&dentry->d_inode->i_mutex);
-				notify_change(dentry, &newattrs);
-				mutex_unlock(&dentry->d_inode->i_mutex);
-				err = vfs_unlink(nd.path.dentry->d_inode,
-						 dentry);
-				if (!err || err == -ENOENT)
-					deleted = 1;
-			}
-		} else {
-			err = -ENOENT;
+	if (dentry->d_inode) {
+		struct kstat stat;
+		err = vfs_getattr(parent.mnt, dentry, &stat);
+		if (!err && dev_mynode(dev, dentry->d_inode, &stat)) {
+			struct iattr newattrs;
+			/*
+			 * before unlinking this node, reset permissions
+			 * of possible references like hardlinks
+			 */
+			newattrs.ia_uid = 0;
+			newattrs.ia_gid = 0;
+			newattrs.ia_mode = stat.mode & ~0777;
+			newattrs.ia_valid =
+				ATTR_UID|ATTR_GID|ATTR_MODE;
+			mutex_lock(&dentry->d_inode->i_mutex);
+			notify_change(dentry, &newattrs);
+			mutex_unlock(&dentry->d_inode->i_mutex);
+			err = vfs_unlink(parent.dentry->d_inode, dentry);
+			if (!err || err == -ENOENT)
+				deleted = 1;
 		}
-		dput(dentry);
 	} else {
-		err = PTR_ERR(dentry);
+		err = -ENOENT;
 	}
-	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+	dput(dentry);
+	mutex_unlock(&parent.dentry->d_inode->i_mutex);
 
-	path_put(&nd.path);
+	path_put(&parent);
 	if (deleted && strchr(nodename, '/'))
 		delete_path(nodename);
 	return err;

drivers/media/video/zoran/zoran.h

@@ -172,8 +172,10 @@ struct zoran_jpg_settings {
 	struct v4l2_jpegcompression jpg_comp;	/* JPEG-specific capture settings */
 };
 
+struct zoran_fh;
+
 struct zoran_mapping {
-	struct file *file;
+	struct zoran_fh *fh;
 	int count;
 };
 

drivers/media/video/zoran/zoran_driver.c

@@ -2811,7 +2811,7 @@ static void
 zoran_vm_close (struct vm_area_struct *vma)
 {
 	struct zoran_mapping *map = vma->vm_private_data;
-	struct zoran_fh *fh = map->file->private_data;
+	struct zoran_fh *fh = map->fh;
 	struct zoran *zr = fh->zr;
 	int i;
 
@@ -2938,7 +2938,7 @@ zoran_mmap (struct file           *file,
 		res = -ENOMEM;
 		goto mmap_unlock_and_return;
 	}
-	map->file = file;
+	map->fh = fh;
 	map->count = 1;
 
 	vma->vm_ops = &zoran_vm_ops;

drivers/mtd/mtdsuper.c

@@ -63,7 +63,7 @@ static struct dentry *mount_mtd_aux(struct file_system_type *fs_type, int flags,
 	struct super_block *sb;
 	int ret;
 
-	sb = sget(fs_type, get_sb_mtd_compare, get_sb_mtd_set, mtd);
+	sb = sget(fs_type, get_sb_mtd_compare, get_sb_mtd_set, flags, mtd);
 	if (IS_ERR(sb))
 		goto out_error;
 
@@ -74,8 +74,6 @@ static struct dentry *mount_mtd_aux(struct file_system_type *fs_type, int flags,
 	pr_debug("MTDSB: New superblock for device %d (\"%s\")\n",
 	      mtd->index, mtd->name);
 
-	sb->s_flags = flags;
-
 	ret = fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
 	if (ret < 0) {
 		deactivate_locked_super(sb);

fs/9p/v9fs.h

@@ -144,7 +144,7 @@ extern void v9fs_session_close(struct v9fs_session_info *v9ses);
 extern void v9fs_session_cancel(struct v9fs_session_info *v9ses);
 extern void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses);
 extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
-			struct nameidata *nameidata);
+			unsigned int flags);
 extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d);
 extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
 extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,

fs/9p/vfs_dentry.c

@@ -100,13 +100,13 @@ static void v9fs_dentry_release(struct dentry *dentry)
 	}
 }
 
-static int v9fs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct p9_fid *fid;
 	struct inode *inode;
 	struct v9fs_inode *v9inode;
 
-	if (nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	inode = dentry->d_inode;

fs/9p/vfs_inode.c

@@ -712,88 +712,34 @@ error:
 }
 
 /**
- * v9fs_vfs_create - VFS hook to create files
+ * v9fs_vfs_create - VFS hook to create a regular file
+ *
+ * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open().  This is only called
+ * for mknod(2).
+ *
  * @dir: directory inode that is being created
  * @dentry:  dentry that is being deleted
  * @mode: create permissions
- * @nd: path information
  *
  */
 
 static int
 v9fs_vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-		struct nameidata *nd)
+		bool excl)
 {
-	int err;
-	u32 perm;
-	int flags;
-	struct file *filp;
-	struct v9fs_inode *v9inode;
-	struct v9fs_session_info *v9ses;
-	struct p9_fid *fid, *inode_fid;
+	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
+	u32 perm = unixmode2p9mode(v9ses, mode);
+	struct p9_fid *fid;
 
-	err = 0;
-	fid = NULL;
-	v9ses = v9fs_inode2v9ses(dir);
-	perm = unixmode2p9mode(v9ses, mode);
-	if (nd)
-		flags = nd->intent.open.flags;
-	else
-		flags = O_RDWR;
-
-	fid = v9fs_create(v9ses, dir, dentry, NULL, perm,
-				v9fs_uflags2omode(flags,
-						v9fs_proto_dotu(v9ses)));
-	if (IS_ERR(fid)) {
-		err = PTR_ERR(fid);
-		fid = NULL;
-		goto error;
-	}
+	/* P9_OEXCL? */
+	fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_ORDWR);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
 
 	v9fs_invalidate_inode_attr(dir);
-	/* if we are opening a file, assign the open fid to the file */
-	if (nd) {
-		v9inode = V9FS_I(dentry->d_inode);
-		mutex_lock(&v9inode->v_mutex);
-		if (v9ses->cache && !v9inode->writeback_fid &&
-		    ((flags & O_ACCMODE) != O_RDONLY)) {
-			/*
-			 * clone a fid and add it to writeback_fid
-			 * we do it during open time instead of
-			 * page dirty time via write_begin/page_mkwrite
-			 * because we want write after unlink usecase
-			 * to work.
-			 */
-			inode_fid = v9fs_writeback_fid(dentry);
-			if (IS_ERR(inode_fid)) {
-				err = PTR_ERR(inode_fid);
-				mutex_unlock(&v9inode->v_mutex);
-				goto error;
-			}
-			v9inode->writeback_fid = (void *) inode_fid;
-		}
-		mutex_unlock(&v9inode->v_mutex);
-		filp = lookup_instantiate_filp(nd, dentry, generic_file_open);
-		if (IS_ERR(filp)) {
-			err = PTR_ERR(filp);
-			goto error;
-		}
-
-		filp->private_data = fid;
-#ifdef CONFIG_9P_FSCACHE
-		if (v9ses->cache)
-			v9fs_cache_inode_set_cookie(dentry->d_inode, filp);
-#endif
-	} else
-		p9_client_clunk(fid);
+	p9_client_clunk(fid);
 
 	return 0;
-
-error:
-	if (fid)
-		p9_client_clunk(fid);
-
-	return err;
 }
 
 /**
@@ -839,7 +785,7 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
  */
 
 struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
-				      struct nameidata *nameidata)
+				      unsigned int flags)
 {
 	struct dentry *res;
 	struct super_block *sb;
@@ -849,8 +795,8 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	char *name;
 	int result = 0;
 
-	p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p nameidata: %p\n",
-		 dir, dentry->d_name.name, dentry, nameidata);
+	p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p flags: %x\n",
+		 dir, dentry->d_name.name, dentry, flags);
 
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -910,6 +856,86 @@ error:
 	return ERR_PTR(result);
 }
 
+static int
+v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
+		     struct file *file, unsigned flags, umode_t mode,
+		     int *opened)
+{
+	int err;
+	u32 perm;
+	struct v9fs_inode *v9inode;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid, *inode_fid;
+	struct dentry *res = NULL;
+
+	if (d_unhashed(dentry)) {
+		res = v9fs_vfs_lookup(dir, dentry, 0);
+		if (IS_ERR(res))
+			return PTR_ERR(res);
+
+		if (res)
+			dentry = res;
+	}
+
+	/* Only creates */
+	if (!(flags & O_CREAT) || dentry->d_inode)
+		return finish_no_open(file, res);
+
+	err = 0;
+	fid = NULL;
+	v9ses = v9fs_inode2v9ses(dir);
+	perm = unixmode2p9mode(v9ses, mode);
+	fid = v9fs_create(v9ses, dir, dentry, NULL, perm,
+				v9fs_uflags2omode(flags,
+						v9fs_proto_dotu(v9ses)));
+	if (IS_ERR(fid)) {
+		err = PTR_ERR(fid);
+		fid = NULL;
+		goto error;
+	}
+
+	v9fs_invalidate_inode_attr(dir);
+	v9inode = V9FS_I(dentry->d_inode);
+	mutex_lock(&v9inode->v_mutex);
+	if (v9ses->cache && !v9inode->writeback_fid &&
+	    ((flags & O_ACCMODE) != O_RDONLY)) {
+		/*
+		 * clone a fid and add it to writeback_fid
+		 * we do it during open time instead of
+		 * page dirty time via write_begin/page_mkwrite
+		 * because we want write after unlink usecase
+		 * to work.
+		 */
+		inode_fid = v9fs_writeback_fid(dentry);
+		if (IS_ERR(inode_fid)) {
+			err = PTR_ERR(inode_fid);
+			mutex_unlock(&v9inode->v_mutex);
+			goto error;
+		}
+		v9inode->writeback_fid = (void *) inode_fid;
+	}
+	mutex_unlock(&v9inode->v_mutex);
+	err = finish_open(file, dentry, generic_file_open, opened);
+	if (err)
+		goto error;
+
+	file->private_data = fid;
+#ifdef CONFIG_9P_FSCACHE
+	if (v9ses->cache)
+		v9fs_cache_inode_set_cookie(dentry->d_inode, file);
+#endif
+
+	*opened |= FILE_CREATED;
+out:
+	dput(res);
+	return err;
+
+error:
+	if (fid)
+		p9_client_clunk(fid);
+	goto out;
+}
+
 /**
  * v9fs_vfs_unlink - VFS unlink hook to delete an inode
  * @i:  inode that is being unlinked
@@ -1488,6 +1514,7 @@ out:
 static const struct inode_operations v9fs_dir_inode_operations_dotu = {
 	.create = v9fs_vfs_create,
 	.lookup = v9fs_vfs_lookup,
+	.atomic_open = v9fs_vfs_atomic_open,
 	.symlink = v9fs_vfs_symlink,
 	.link = v9fs_vfs_link,
 	.unlink = v9fs_vfs_unlink,
@@ -1502,6 +1529,7 @@ static const struct inode_operations v9fs_dir_inode_operations_dotu = {
 static const struct inode_operations v9fs_dir_inode_operations = {
 	.create = v9fs_vfs_create,
 	.lookup = v9fs_vfs_lookup,
+	.atomic_open = v9fs_vfs_atomic_open,
 	.unlink = v9fs_vfs_unlink,
 	.mkdir = v9fs_vfs_mkdir,
 	.rmdir = v9fs_vfs_rmdir,

fs/9p/vfs_inode_dotl.c

@@ -230,20 +230,25 @@ int v9fs_open_to_dotl_flags(int flags)
  * @dir: directory inode that is being created
  * @dentry:  dentry that is being deleted
  * @mode: create permissions
- * @nd: path information
  *
  */
 
 static int
 v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
-		struct nameidata *nd)
+		bool excl)
+{
+	return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0);
+}
+
+static int
+v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
+			  struct file *file, unsigned flags, umode_t omode,
+			  int *opened)
 {
 	int err = 0;
 	gid_t gid;
-	int flags;
 	umode_t mode;
 	char *name = NULL;
-	struct file *filp;
 	struct p9_qid qid;
 	struct inode *inode;
 	struct p9_fid *fid = NULL;
@@ -251,18 +256,22 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 	struct p9_fid *dfid, *ofid, *inode_fid;
 	struct v9fs_session_info *v9ses;
 	struct posix_acl *pacl = NULL, *dacl = NULL;
+	struct dentry *res = NULL;
+
+	if (d_unhashed(dentry)) {
+		res = v9fs_vfs_lookup(dir, dentry, 0);
+		if (IS_ERR(res))
+			return PTR_ERR(res);
+
+		if (res)
+			dentry = res;
+	}
+
+	/* Only creates */
+	if (!(flags & O_CREAT) || dentry->d_inode)
+		return finish_no_open(file, res);
 
 	v9ses = v9fs_inode2v9ses(dir);
-	if (nd)
-		flags = nd->intent.open.flags;
-	else {
-		/*
-		 * create call without LOOKUP_OPEN is due
-		 * to mknod of regular files. So use mknod
-		 * operation.
-		 */
-		return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0);
-	}
 
 	name = (char *) dentry->d_name.name;
 	p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n",
@@ -272,7 +281,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 	if (IS_ERR(dfid)) {
 		err = PTR_ERR(dfid);
 		p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
-		return err;
+		goto out;
 	}
 
 	/* clone a fid to use for creation */
@@ -280,7 +289,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 	if (IS_ERR(ofid)) {
 		err = PTR_ERR(ofid);
 		p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
-		return err;
+		goto out;
 	}
 
 	gid = v9fs_get_fsgid_for_create(dir);
@@ -345,17 +354,18 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 	}
 	mutex_unlock(&v9inode->v_mutex);
 	/* Since we are opening a file, assign the open fid to the file */
-	filp = lookup_instantiate_filp(nd, dentry, generic_file_open);
-	if (IS_ERR(filp)) {
-		err = PTR_ERR(filp);
+	err = finish_open(file, dentry, generic_file_open, opened);
+	if (err)
 		goto err_clunk_old_fid;
-	}
-	filp->private_data = ofid;
+	file->private_data = ofid;
 #ifdef CONFIG_9P_FSCACHE
 	if (v9ses->cache)
-		v9fs_cache_inode_set_cookie(inode, filp);
+		v9fs_cache_inode_set_cookie(inode, file);
 #endif
-	return 0;
+	*opened |= FILE_CREATED;
+out:
+	dput(res);
+	return err;
 
 error:
 	if (fid)
@@ -364,7 +374,7 @@ err_clunk_old_fid:
 	if (ofid)
 		p9_client_clunk(ofid);
 	v9fs_set_create_acl(NULL, &dacl, &pacl);
-	return err;
+	goto out;
 }
 
 /**
@@ -982,6 +992,7 @@ out:
 
 const struct inode_operations v9fs_dir_inode_operations_dotl = {
 	.create = v9fs_vfs_create_dotl,
+	.atomic_open = v9fs_vfs_atomic_open_dotl,
 	.lookup = v9fs_vfs_lookup,
 	.link = v9fs_vfs_link_dotl,
 	.symlink = v9fs_vfs_symlink_dotl,

fs/9p/vfs_super.c

@@ -89,7 +89,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 	if (v9ses->cache)
 		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_CACHE_SIZE;
 
-	sb->s_flags = flags | MS_ACTIVE | MS_DIRSYNC | MS_NOATIME;
+	sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME;
 	if (!v9ses->cache)
 		sb->s_flags |= MS_SYNCHRONOUS;
 
@@ -137,7 +137,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 		goto close_session;
 	}
 
-	sb = sget(fs_type, NULL, v9fs_set_super, v9ses);
+	sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses);
 	if (IS_ERR(sb)) {
 		retval = PTR_ERR(sb);
 		goto clunk_fid;

fs/adfs/dir.c

@@ -266,7 +266,7 @@ const struct dentry_operations adfs_dentry_operations = {
 };
 
 static struct dentry *
-adfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+adfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode = NULL;
 	struct object_info obj;

fs/adfs/super.c

@@ -246,7 +246,6 @@ static struct inode *adfs_alloc_inode(struct super_block *sb)
 static void adfs_i_callback(struct rcu_head *head)
 {
 	struct inode *inode = container_of(head, struct inode, i_rcu);
-	INIT_LIST_HEAD(&inode->i_dentry);
 	kmem_cache_free(adfs_inode_cachep, ADFS_I(inode));
 }
 

fs/affs/affs.h

@@ -3,6 +3,7 @@
 #include <linux/buffer_head.h>
 #include <linux/amigaffs.h>
 #include <linux/mutex.h>
+#include <linux/workqueue.h>
 
 /* AmigaOS allows file names with up to 30 characters length.
  * Names longer than that will be silently truncated. If you
@@ -100,6 +101,10 @@ struct affs_sb_info {
 	char *s_prefix;			/* Prefix for volumes and assigns. */
 	char s_volume[32];		/* Volume prefix for absolute symlinks. */
 	spinlock_t symlink_lock;	/* protects the previous two */
+	struct super_block *sb;		/* the VFS superblock object */
+	int work_queued;		/* non-zero delayed work is queued */
+	struct delayed_work sb_work;	/* superblock flush delayed work */
+	spinlock_t work_lock;		/* protects sb_work and work_queued */
 };
 
 #define SF_INTL		0x0001		/* International filesystem. */
@@ -120,6 +125,8 @@ static inline struct affs_sb_info *AFFS_SB(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
+void affs_mark_sb_dirty(struct super_block *sb);
+
 /* amigaffs.c */
 
 extern int	affs_insert_hash(struct inode *inode, struct buffer_head *bh);
@@ -146,9 +153,9 @@ extern void	affs_free_bitmap(struct super_block *sb);
 /* namei.c */
 
 extern int	affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len);
-extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *);
+extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int);
 extern int	affs_unlink(struct inode *dir, struct dentry *dentry);
-extern int	affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *);
+extern int	affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool);
 extern int	affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
 extern int	affs_rmdir(struct inode *dir, struct dentry *dentry);
 extern int	affs_link(struct dentry *olddentry, struct inode *dir,

fs/affs/amigaffs.c

@@ -122,22 +122,16 @@ affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh)
 }
 
 static void
-affs_fix_dcache(struct dentry *dentry, u32 entry_ino)
+affs_fix_dcache(struct inode *inode, u32 entry_ino)
 {
-	struct inode *inode = dentry->d_inode;
-	void *data = dentry->d_fsdata;
-	struct list_head *head, *next;
-
+	struct dentry *dentry;
+	struct hlist_node *p;
 	spin_lock(&inode->i_lock);
-	head = &inode->i_dentry;
-	next = head->next;
-	while (next != head) {
-		dentry = list_entry(next, struct dentry, d_alias);
+	hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
 		if (entry_ino == (u32)(long)dentry->d_fsdata) {
-			dentry->d_fsdata = data;
+			dentry->d_fsdata = (void *)inode->i_ino;
 			break;
 		}
-		next = next->next;
 	}
 	spin_unlock(&inode->i_lock);
 }
@@ -177,7 +171,11 @@ affs_remove_link(struct dentry *dentry)
 		}
 
 		affs_lock_dir(dir);
-		affs_fix_dcache(dentry, link_ino);
+		/*
+		 * if there's a dentry for that block, make it
+		 * refer to inode itself.
+		 */
+		affs_fix_dcache(inode, link_ino);
 		retval = affs_remove_hash(dir, link_bh);
 		if (retval) {
 			affs_unlock_dir(dir);

fs/affs/bitmap.c

@@ -103,7 +103,7 @@ affs_free_block(struct super_block *sb, u32 block)
 	*(__be32 *)bh->b_data = cpu_to_be32(tmp - mask);
 
 	mark_buffer_dirty(bh);
-	sb->s_dirt = 1;
+	affs_mark_sb_dirty(sb);
 	bm->bm_free++;
 
 	mutex_unlock(&sbi->s_bmlock);
@@ -248,7 +248,7 @@ find_bit:
 	*(__be32 *)bh->b_data = cpu_to_be32(tmp + mask);
 
 	mark_buffer_dirty(bh);
-	sb->s_dirt = 1;
+	affs_mark_sb_dirty(sb);
 
 	mutex_unlock(&sbi->s_bmlock);
 

fs/affs/namei.c

@@ -211,7 +211,7 @@ affs_find_entry(struct inode *dir, struct dentry *dentry)
 }
 
 struct dentry *
-affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	struct super_block *sb = dir->i_sb;
 	struct buffer_head *bh;
@@ -255,7 +255,7 @@ affs_unlink(struct inode *dir, struct dentry *dentry)
 }
 
 int
-affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd)
+affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode	*inode;

fs/affs/super.c

@@ -17,6 +17,7 @@
 #include <linux/magic.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/writeback.h>
 #include "affs.h"
 
 extern struct timezone sys_tz;
@@ -25,15 +26,17 @@ static int affs_statfs(struct dentry *dentry, struct kstatfs *buf);
 static int affs_remount (struct super_block *sb, int *flags, char *data);
 
 static void
-affs_commit_super(struct super_block *sb, int wait, int clean)
+affs_commit_super(struct super_block *sb, int wait)
 {
 	struct affs_sb_info *sbi = AFFS_SB(sb);
 	struct buffer_head *bh = sbi->s_root_bh;
 	struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh);
 
-	tail->bm_flag = cpu_to_be32(clean);
+	lock_buffer(bh);
 	secs_to_datestamp(get_seconds(), &tail->disk_change);
 	affs_fix_checksum(sb, bh);
+	unlock_buffer(bh);
+
 	mark_buffer_dirty(bh);
 	if (wait)
 		sync_dirty_buffer(bh);
@@ -45,9 +48,7 @@ affs_put_super(struct super_block *sb)
 	struct affs_sb_info *sbi = AFFS_SB(sb);
 	pr_debug("AFFS: put_super()\n");
 
-	if (!(sb->s_flags & MS_RDONLY) && sb->s_dirt)
-		affs_commit_super(sb, 1, 1);
-
+	cancel_delayed_work_sync(&sbi->sb_work);
 	kfree(sbi->s_prefix);
 	affs_free_bitmap(sb);
 	affs_brelse(sbi->s_root_bh);
@@ -55,28 +56,45 @@ affs_put_super(struct super_block *sb)
 	sb->s_fs_info = NULL;
 }
 
-static void
-affs_write_super(struct super_block *sb)
-{
-	lock_super(sb);
-	if (!(sb->s_flags & MS_RDONLY))
-		affs_commit_super(sb, 1, 2);
-	sb->s_dirt = 0;
-	unlock_super(sb);
-
-	pr_debug("AFFS: write_super() at %lu, clean=2\n", get_seconds());
-}
-
 static int
 affs_sync_fs(struct super_block *sb, int wait)
 {
-	lock_super(sb);
-	affs_commit_super(sb, wait, 2);
-	sb->s_dirt = 0;
-	unlock_super(sb);
+	affs_commit_super(sb, wait);
 	return 0;
 }
 
+static void flush_superblock(struct work_struct *work)
+{
+	struct affs_sb_info *sbi;
+	struct super_block *sb;
+
+	sbi = container_of(work, struct affs_sb_info, sb_work.work);
+	sb = sbi->sb;
+
+	spin_lock(&sbi->work_lock);
+	sbi->work_queued = 0;
+	spin_unlock(&sbi->work_lock);
+
+	affs_commit_super(sb, 1);
+}
+
+void affs_mark_sb_dirty(struct super_block *sb)
+{
+	struct affs_sb_info *sbi = AFFS_SB(sb);
+	unsigned long delay;
+
+	if (sb->s_flags & MS_RDONLY)
+	       return;
+
+	spin_lock(&sbi->work_lock);
+	if (!sbi->work_queued) {
+	       delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+	       queue_delayed_work(system_long_wq, &sbi->sb_work, delay);
+	       sbi->work_queued = 1;
+	}
+	spin_unlock(&sbi->work_lock);
+}
+
 static struct kmem_cache * affs_inode_cachep;
 
 static struct inode *affs_alloc_inode(struct super_block *sb)
@@ -138,7 +156,6 @@ static const struct super_operations affs_sops = {
 	.write_inode	= affs_write_inode,
 	.evict_inode	= affs_evict_inode,
 	.put_super	= affs_put_super,
-	.write_super	= affs_write_super,
 	.sync_fs	= affs_sync_fs,
 	.statfs		= affs_statfs,
 	.remount_fs	= affs_remount,
@@ -305,8 +322,11 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 
 	sb->s_fs_info = sbi;
+	sbi->sb = sb;
 	mutex_init(&sbi->s_bmlock);
 	spin_lock_init(&sbi->symlink_lock);
+	spin_lock_init(&sbi->work_lock);
+	INIT_DELAYED_WORK(&sbi->sb_work, flush_superblock);
 
 	if (!parse_options(data,&uid,&gid,&i,&reserved,&root_block,
 				&blocksize,&sbi->s_prefix,
@@ -531,6 +551,7 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 		return -EINVAL;
 	}
 
+	flush_delayed_work_sync(&sbi->sb_work);
 	replace_mount_options(sb, new_opts);
 
 	sbi->s_flags = mount_flags;
@@ -549,10 +570,9 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
 
-	if (*flags & MS_RDONLY) {
-		affs_write_super(sb);
+	if (*flags & MS_RDONLY)
 		affs_free_bitmap(sb);
-	} else
+	else
 		res = affs_init_bitmap(sb, flags);
 
 	return res;