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;
-
-	err = 0;
-	fid = NULL;
-	v9ses = v9fs_inode2v9ses(dir);
-	perm = unixmode2p9mode(v9ses, mode);
-	if (nd)
-		flags = nd->intent.open.flags;
-	else
-		flags = O_RDWR;
+	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
+	u32 perm = unixmode2p9mode(v9ses, mode);
+	struct p9_fid *fid;
 
-	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;
@@ -251,19 +256,23 @@ 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;
 
-	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);
+	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);
+
 	name = (char *) dentry->d_name.name;
 	p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n",
 		 name, flags, omode);
@@ -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);
@@ -55,26 +56,43 @@ affs_put_super(struct super_block *sb)
 	sb->s_fs_info = NULL;
 }
 
-static void
-affs_write_super(struct super_block *sb)
+static int
+affs_sync_fs(struct super_block *sb, int wait)
 {
-	lock_super(sb);
-	if (!(sb->s_flags & MS_RDONLY))
-		affs_commit_super(sb, 1, 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;
 
-	pr_debug("AFFS: write_super() at %lu, clean=2\n", get_seconds());
+	spin_lock(&sbi->work_lock);
+	sbi->work_queued = 0;
+	spin_unlock(&sbi->work_lock);
+
+	affs_commit_super(sb, 1);
 }
 
-static int
-affs_sync_fs(struct super_block *sb, int wait)
+void affs_mark_sb_dirty(struct super_block *sb)
 {
-	lock_super(sb);
-	affs_commit_super(sb, wait, 2);
-	sb->s_dirt = 0;
-	unlock_super(sb);
-	return 0;
+	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;
@@ -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;

fs/afs/dir.c

@@ -20,16 +20,16 @@
 #include "internal.h"
 
 static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
-				 struct nameidata *nd);
+				 unsigned int flags);
 static int afs_dir_open(struct inode *inode, struct file *file);
 static int afs_readdir(struct file *file, void *dirent, filldir_t filldir);
-static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd);
+static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
 static int afs_d_delete(const struct dentry *dentry);
 static void afs_d_release(struct dentry *dentry);
 static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
 				  loff_t fpos, u64 ino, unsigned dtype);
 static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-		      struct nameidata *nd);
+		      bool excl);
 static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
 static int afs_rmdir(struct inode *dir, struct dentry *dentry);
 static int afs_unlink(struct inode *dir, struct dentry *dentry);
@@ -516,7 +516,7 @@ out:
  * look up an entry in a directory
  */
 static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
-				 struct nameidata *nd)
+				 unsigned int flags)
 {
 	struct afs_vnode *vnode;
 	struct afs_fid fid;
@@ -598,7 +598,7 @@ success:
  * - NOTE! the hit can be a negative hit too, so we can't assume we have an
  *   inode
  */
-static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct afs_vnode *vnode, *dir;
 	struct afs_fid uninitialized_var(fid);
@@ -607,7 +607,7 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
 	void *dir_version;
 	int ret;
 
-	if (nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	vnode = AFS_FS_I(dentry->d_inode);
@@ -949,7 +949,7 @@ error:
  * create a regular file on an AFS filesystem
  */
 static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-		      struct nameidata *nd)
+		      bool excl)
 {
 	struct afs_file_status status;
 	struct afs_callback cb;

fs/afs/mntpt.c

@@ -22,7 +22,7 @@
 
 static struct dentry *afs_mntpt_lookup(struct inode *dir,
 				       struct dentry *dentry,
-				       struct nameidata *nd);
+				       unsigned int flags);
 static int afs_mntpt_open(struct inode *inode, struct file *file);
 static void afs_mntpt_expiry_timed_out(struct work_struct *work);
 
@@ -104,7 +104,7 @@ out:
  */
 static struct dentry *afs_mntpt_lookup(struct inode *dir,
 				       struct dentry *dentry,
-				       struct nameidata *nd)
+				       unsigned int flags)
 {
 	_enter("%p,%p{%p{%s},%s}",
 	       dir,

fs/afs/super.c

@@ -395,7 +395,7 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
 	as->volume = vol;
 
 	/* allocate a deviceless superblock */
-	sb = sget(fs_type, afs_test_super, afs_set_super, as);
+	sb = sget(fs_type, afs_test_super, afs_set_super, flags, as);
 	if (IS_ERR(sb)) {
 		ret = PTR_ERR(sb);
 		afs_put_volume(vol);
@@ -406,7 +406,6 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
 	if (!sb->s_root) {
 		/* initial superblock/root creation */
 		_debug("create");
-		sb->s_flags = flags;
 		ret = afs_fill_super(sb, &params);
 		if (ret < 0) {
 			deactivate_locked_super(sb);

fs/aio.c

@@ -56,13 +56,6 @@ static struct kmem_cache	*kioctx_cachep;
 
 static struct workqueue_struct *aio_wq;
 
-/* Used for rare fput completion. */
-static void aio_fput_routine(struct work_struct *);
-static DECLARE_WORK(fput_work, aio_fput_routine);
-
-static DEFINE_SPINLOCK(fput_lock);
-static LIST_HEAD(fput_head);
-
 static void aio_kick_handler(struct work_struct *);
 static void aio_queue_work(struct kioctx *);
 
@@ -479,7 +472,6 @@ static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch)
 {
 	unsigned short allocated, to_alloc;
 	long avail;
-	bool called_fput = false;
 	struct kiocb *req, *n;
 	struct aio_ring *ring;
 
@@ -495,28 +487,11 @@ static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch)
 	if (allocated == 0)
 		goto out;
 
-retry:
 	spin_lock_irq(&ctx->ctx_lock);
 	ring = kmap_atomic(ctx->ring_info.ring_pages[0]);
 
 	avail = aio_ring_avail(&ctx->ring_info, ring) - ctx->reqs_active;
 	BUG_ON(avail < 0);
-	if (avail == 0 && !called_fput) {
-		/*
-		 * Handle a potential starvation case.  It is possible that
-		 * we hold the last reference on a struct file, causing us
-		 * to delay the final fput to non-irq context.  In this case,
-		 * ctx->reqs_active is artificially high.  Calling the fput
-		 * routine here may free up a slot in the event completion
-		 * ring, allowing this allocation to succeed.
-		 */
-		kunmap_atomic(ring);
-		spin_unlock_irq(&ctx->ctx_lock);
-		aio_fput_routine(NULL);
-		called_fput = true;
-		goto retry;
-	}
-
 	if (avail < allocated) {
 		/* Trim back the number of requests. */
 		list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
@@ -570,36 +545,6 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
 		wake_up_all(&ctx->wait);
 }
 
-static void aio_fput_routine(struct work_struct *data)
-{
-	spin_lock_irq(&fput_lock);
-	while (likely(!list_empty(&fput_head))) {
-		struct kiocb *req = list_kiocb(fput_head.next);
-		struct kioctx *ctx = req->ki_ctx;
-
-		list_del(&req->ki_list);
-		spin_unlock_irq(&fput_lock);
-
-		/* Complete the fput(s) */
-		if (req->ki_filp != NULL)
-			fput(req->ki_filp);
-
-		/* Link the iocb into the context's free list */
-		rcu_read_lock();
-		spin_lock_irq(&ctx->ctx_lock);
-		really_put_req(ctx, req);
-		/*
-		 * at that point ctx might've been killed, but actual
-		 * freeing is RCU'd
-		 */
-		spin_unlock_irq(&ctx->ctx_lock);
-		rcu_read_unlock();
-
-		spin_lock_irq(&fput_lock);
-	}
-	spin_unlock_irq(&fput_lock);
-}
-
 /* __aio_put_req
  *	Returns true if this put was the last user of the request.
  */
@@ -618,21 +563,9 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 	req->ki_cancel = NULL;
 	req->ki_retry = NULL;
 
-	/*
-	 * Try to optimize the aio and eventfd file* puts, by avoiding to
-	 * schedule work in case it is not final fput() time. In normal cases,
-	 * we would not be holding the last reference to the file*, so
-	 * this function will be executed w/out any aio kthread wakeup.
-	 */
-	if (unlikely(!fput_atomic(req->ki_filp))) {
-		spin_lock(&fput_lock);
-		list_add(&req->ki_list, &fput_head);
-		spin_unlock(&fput_lock);
-		schedule_work(&fput_work);
-	} else {
-		req->ki_filp = NULL;
-		really_put_req(ctx, req);
-	}
+	fput(req->ki_filp);
+	req->ki_filp = NULL;
+	really_put_req(ctx, req);
 	return 1;
 }
 

fs/attr.c

@@ -171,6 +171,8 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
 	struct timespec now;
 	unsigned int ia_valid = attr->ia_valid;
 
+	WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
+
 	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
 		if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 			return -EPERM;
@@ -250,5 +252,4 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
 
 	return error;
 }
-
 EXPORT_SYMBOL(notify_change);

fs/autofs4/dev-ioctl.c

@@ -257,8 +257,8 @@ static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid)
 		 * corresponding to the autofs fs we want to open.
 		 */
 
-		filp = dentry_open(path.dentry, path.mnt, O_RDONLY,
-				   current_cred());
+		filp = dentry_open(&path, O_RDONLY, current_cred());
+		path_put(&path);
 		if (IS_ERR(filp)) {
 			err = PTR_ERR(filp);
 			goto out;

fs/autofs4/root.c

@@ -32,7 +32,7 @@ static long autofs4_root_ioctl(struct file *,unsigned int,unsigned long);
 static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
 #endif
 static int autofs4_dir_open(struct inode *inode, struct file *file);
-static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
+static struct dentry *autofs4_lookup(struct inode *,struct dentry *, unsigned int);
 static struct vfsmount *autofs4_d_automount(struct path *);
 static int autofs4_d_manage(struct dentry *, bool);
 static void autofs4_dentry_release(struct dentry *);
@@ -458,7 +458,7 @@ int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 }
 
 /* Lookups in the root directory */
-static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;

fs/bad_inode.c

@@ -173,13 +173,13 @@ static const struct file_operations bad_file_ops =
 };
 
 static int bad_inode_create (struct inode *dir, struct dentry *dentry,
-		umode_t mode, struct nameidata *nd)
+		umode_t mode, bool excl)
 {
 	return -EIO;
 }
 
 static struct dentry *bad_inode_lookup(struct inode *dir,
-			struct dentry *dentry, struct nameidata *nd)
+			struct dentry *dentry, unsigned int flags)
 {
 	return ERR_PTR(-EIO);
 }

fs/befs/linuxvfs.c

@@ -34,7 +34,7 @@ static int befs_readdir(struct file *, void *, filldir_t);
 static int befs_get_block(struct inode *, sector_t, struct buffer_head *, int);
 static int befs_readpage(struct file *file, struct page *page);
 static sector_t befs_bmap(struct address_space *mapping, sector_t block);
-static struct dentry *befs_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int);
 static struct inode *befs_iget(struct super_block *, unsigned long);
 static struct inode *befs_alloc_inode(struct super_block *sb);
 static void befs_destroy_inode(struct inode *inode);
@@ -159,7 +159,7 @@ befs_get_block(struct inode *inode, sector_t block,
 }
 
 static struct dentry *
-befs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode = NULL;
 	struct super_block *sb = dir->i_sb;

fs/bfs/dir.c

@@ -85,7 +85,7 @@ const struct file_operations bfs_dir_operations = {
 extern void dump_imap(const char *, struct super_block *);
 
 static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-						struct nameidata *nd)
+						bool excl)
 {
 	int err;
 	struct inode *inode;
@@ -133,7 +133,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 }
 
 static struct dentry *bfs_lookup(struct inode *dir, struct dentry *dentry,
-						struct nameidata *nd)
+						unsigned int flags)
 {
 	struct inode *inode = NULL;
 	struct buffer_head *bh;

fs/block_dev.c

@@ -1710,3 +1710,39 @@ int __invalidate_device(struct block_device *bdev, bool kill_dirty)
 	return res;
 }
 EXPORT_SYMBOL(__invalidate_device);
+
+void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
+{
+	struct inode *inode, *old_inode = NULL;
+
+	spin_lock(&inode_sb_list_lock);
+	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
+		struct address_space *mapping = inode->i_mapping;
+
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
+		    mapping->nrpages == 0) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		__iget(inode);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&inode_sb_list_lock);
+		/*
+		 * We hold a reference to 'inode' so it couldn't have been
+		 * removed from s_inodes list while we dropped the
+		 * inode_sb_list_lock.  We cannot iput the inode now as we can
+		 * be holding the last reference and we cannot iput it under
+		 * inode_sb_list_lock. So we keep the reference and iput it
+		 * later.
+		 */
+		iput(old_inode);
+		old_inode = inode;
+
+		func(I_BDEV(inode), arg);
+
+		spin_lock(&inode_sb_list_lock);
+	}
+	spin_unlock(&inode_sb_list_lock);
+	iput(old_inode);
+}

fs/btrfs/inode.c

@@ -4247,7 +4247,7 @@ static void btrfs_dentry_release(struct dentry *dentry)
 }
 
 static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
-				   struct nameidata *nd)
+				   unsigned int flags)
 {
 	struct dentry *ret;
 
@@ -4893,7 +4893,7 @@ out_unlock:
 }
 
 static int btrfs_create(struct inode *dir, struct dentry *dentry,
-			umode_t mode, struct nameidata *nd)
+			umode_t mode, bool excl)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
@@ -6987,7 +6987,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	struct btrfs_ordered_extent *ordered;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 
-	WARN_ON(!list_empty(&inode->i_dentry));
+	WARN_ON(!hlist_empty(&inode->i_dentry));
 	WARN_ON(inode->i_data.nrpages);
 	WARN_ON(BTRFS_I(inode)->outstanding_extents);
 	WARN_ON(BTRFS_I(inode)->reserved_extents);

fs/btrfs/ioctl.c

@@ -3268,7 +3268,7 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 	if (fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 
-	ret = mnt_want_write(file->f_path.mnt);
+	ret = mnt_want_write_file(file);
 	if (ret)
 		return ret;
 
@@ -3338,7 +3338,7 @@ out_bargs:
 out:
 	mutex_unlock(&fs_info->balance_mutex);
 	mutex_unlock(&fs_info->volume_mutex);
-	mnt_drop_write(file->f_path.mnt);
+	mnt_drop_write_file(file);
 	return ret;
 }
 

fs/btrfs/super.c

@@ -1068,7 +1068,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	}
 
 	bdev = fs_devices->latest_bdev;
-	s = sget(fs_type, btrfs_test_super, btrfs_set_super, fs_info);
+	s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC,
+		 fs_info);
 	if (IS_ERR(s)) {
 		error = PTR_ERR(s);
 		goto error_close_devices;
@@ -1082,7 +1083,6 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	} else {
 		char b[BDEVNAME_SIZE];
 
-		s->s_flags = flags | MS_NOSEC;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
 		btrfs_sb(s)->bdev_holder = fs_type;
 		error = btrfs_fill_super(s, fs_devices, data,

fs/cachefiles/namei.c

@@ -567,7 +567,7 @@ lookup_again:
 			if (ret < 0)
 				goto create_error;
 			start = jiffies;
-			ret = vfs_create(dir->d_inode, next, S_IFREG, NULL);
+			ret = vfs_create(dir->d_inode, next, S_IFREG, true);
 			cachefiles_hist(cachefiles_create_histogram, start);
 			if (ret < 0)
 				goto create_error;

fs/cachefiles/rdwr.c

@@ -891,6 +891,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	struct cachefiles_cache *cache;
 	mm_segment_t old_fs;
 	struct file *file;
+	struct path path;
 	loff_t pos, eof;
 	size_t len;
 	void *data;
@@ -916,10 +917,9 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 
 	/* write the page to the backing filesystem and let it store it in its
 	 * own time */
-	dget(object->backer);
-	mntget(cache->mnt);
-	file = dentry_open(object->backer, cache->mnt, O_RDWR,
-			   cache->cache_cred);
+	path.mnt = cache->mnt;
+	path.dentry = object->backer;
+	file = dentry_open(&path, O_RDWR, cache->cache_cred);
 	if (IS_ERR(file)) {
 		ret = PTR_ERR(file);
 	} else {

fs/ceph/dir.c

@@ -576,7 +576,7 @@ static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
  * the MDS so that it gets our 'caps wanted' value in a single op.
  */
 static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
-				  struct nameidata *nd)
+				  unsigned int flags)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -594,14 +594,6 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 	if (err < 0)
 		return ERR_PTR(err);
 
-	/* open (but not create!) intent? */
-	if (nd &&
-	    (nd->flags & LOOKUP_OPEN) &&
-	    !(nd->intent.open.flags & O_CREAT)) {
-		int mode = nd->intent.open.create_mode & ~current->fs->umask;
-		return ceph_lookup_open(dir, dentry, nd, mode, 1);
-	}
-
 	/* can we conclude ENOENT locally? */
 	if (dentry->d_inode == NULL) {
 		struct ceph_inode_info *ci = ceph_inode(dir);
@@ -642,13 +634,51 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 	return dentry;
 }
 
+int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
+		     struct file *file, unsigned flags, umode_t mode,
+		     int *opened)
+{
+	int err;
+	struct dentry *res = NULL;
+
+	if (!(flags & O_CREAT)) {
+		if (dentry->d_name.len > NAME_MAX)
+			return -ENAMETOOLONG;
+
+		err = ceph_init_dentry(dentry);
+		if (err < 0)
+			return err;
+
+		return ceph_lookup_open(dir, dentry, file, flags, mode, opened);
+	}
+
+	if (d_unhashed(dentry)) {
+		res = ceph_lookup(dir, dentry, 0);
+		if (IS_ERR(res))
+			return PTR_ERR(res);
+
+		if (res)
+			dentry = res;
+	}
+
+	/* We don't deal with positive dentries here */
+	if (dentry->d_inode)
+		return finish_no_open(file, res);
+
+	*opened |= FILE_CREATED;
+	err = ceph_lookup_open(dir, dentry, file, flags, mode, opened);
+	dput(res);
+
+	return err;
+}
+
 /*
  * If we do a create but get no trace back from the MDS, follow up with
  * a lookup (the VFS expects us to link up the provided dentry).
  */
 int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
 {
-	struct dentry *result = ceph_lookup(dir, dentry, NULL);
+	struct dentry *result = ceph_lookup(dir, dentry, 0);
 
 	if (result && !IS_ERR(result)) {
 		/*
@@ -700,25 +730,9 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
 }
 
 static int ceph_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-		       struct nameidata *nd)
+		       bool excl)
 {
-	dout("create in dir %p dentry %p name '%.*s'\n",
-	     dir, dentry, dentry->d_name.len, dentry->d_name.name);
-
-	if (ceph_snap(dir) != CEPH_NOSNAP)
-		return -EROFS;
-
-	if (nd) {
-		BUG_ON((nd->flags & LOOKUP_OPEN) == 0);
-		dentry = ceph_lookup_open(dir, dentry, nd, mode, 0);
-		/* hrm, what should i do here if we get aliased? */
-		if (IS_ERR(dentry))
-			return PTR_ERR(dentry);
-		return 0;
-	}
-
-	/* fall back to mknod */
-	return ceph_mknod(dir, dentry, (mode & ~S_IFMT) | S_IFREG, 0);
+	return ceph_mknod(dir, dentry, mode, 0);
 }
 
 static int ceph_symlink(struct inode *dir, struct dentry *dentry,
@@ -1028,12 +1042,12 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
 /*
  * Check if cached dentry can be trusted.
  */
-static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	int valid = 0;
 	struct inode *dir;
 
-	if (nd && nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry,
@@ -1080,7 +1094,7 @@ static void ceph_d_release(struct dentry *dentry)
 }
 
 static int ceph_snapdir_d_revalidate(struct dentry *dentry,
-					  struct nameidata *nd)
+					  unsigned int flags)
 {
 	/*
 	 * Eventually, we'll want to revalidate snapped metadata
@@ -1357,6 +1371,7 @@ const struct inode_operations ceph_dir_iops = {
 	.rmdir = ceph_unlink,
 	.rename = ceph_rename,
 	.create = ceph_create,
+	.atomic_open = ceph_atomic_open,
 };
 
 const struct dentry_operations ceph_dentry_ops = {

fs/ceph/file.c

@@ -213,22 +213,15 @@ out:
  * may_open() fails, the struct *file gets cleaned up (i.e.
  * ceph_release gets called).  So fear not!
  */
-/*
- * flags
- *  path_lookup_open   -> LOOKUP_OPEN
- *  path_lookup_create -> LOOKUP_OPEN|LOOKUP_CREATE
- */
-struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
-				struct nameidata *nd, int mode,
-				int locked_dir)
+int ceph_lookup_open(struct inode *dir, struct dentry *dentry,
+		     struct file *file, unsigned flags, umode_t mode,
+		     int *opened)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
-	struct file *file;
 	struct ceph_mds_request *req;
 	struct dentry *ret;
 	int err;
-	int flags = nd->intent.open.flags;
 
 	dout("ceph_lookup_open dentry %p '%.*s' flags %d mode 0%o\n",
 	     dentry, dentry->d_name.len, dentry->d_name.name, flags, mode);
@@ -236,7 +229,7 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
 	/* do the open */
 	req = prepare_open_request(dir->i_sb, flags, mode);
 	if (IS_ERR(req))
-		return ERR_CAST(req);
+		return PTR_ERR(req);
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	if (flags & O_CREAT) {
@@ -254,14 +247,17 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
 		err = ceph_handle_notrace_create(dir, dentry);
 	if (err)
 		goto out;
-	file = lookup_instantiate_filp(nd, req->r_dentry, ceph_open);
-	if (IS_ERR(file))
-		err = PTR_ERR(file);
+	err = finish_open(file, req->r_dentry, ceph_open, opened);
 out:
 	ret = ceph_finish_lookup(req, dentry, err);
 	ceph_mdsc_put_request(req);
 	dout("ceph_lookup_open result=%p\n", ret);
-	return ret;
+
+	if (IS_ERR(ret))
+		return PTR_ERR(ret);
+
+	dput(ret);
+	return err;
 }
 
 int ceph_release(struct inode *inode, struct file *file)

fs/ceph/super.c

@@ -871,7 +871,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
 
 	if (ceph_test_opt(fsc->client, NOSHARE))
 		compare_super = NULL;
-	sb = sget(fs_type, compare_super, ceph_set_super, fsc);
+	sb = sget(fs_type, compare_super, ceph_set_super, flags, fsc);
 	if (IS_ERR(sb)) {
 		res = ERR_CAST(sb);
 		goto out;

fs/ceph/super.h

@@ -806,9 +806,9 @@ extern int ceph_copy_from_page_vector(struct page **pages,
 				    loff_t off, size_t len);
 extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
 extern int ceph_open(struct inode *inode, struct file *file);
-extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
-				       struct nameidata *nd, int mode,
-				       int locked_dir);
+extern int ceph_lookup_open(struct inode *dir, struct dentry *dentry,
+			     struct file *od, unsigned flags,
+			     umode_t mode, int *opened);
 extern int ceph_release(struct inode *inode, struct file *filp);
 
 /* dir.c */

fs/cifs/cifsfs.c

@@ -257,7 +257,6 @@ cifs_alloc_inode(struct super_block *sb)
 static void cifs_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(cifs_inode_cachep, CIFS_I(inode));
 }
 
@@ -638,7 +637,10 @@ cifs_do_mount(struct file_system_type *fs_type,
 	mnt_data.cifs_sb = cifs_sb;
 	mnt_data.flags = flags;
 
-	sb = sget(fs_type, cifs_match_super, cifs_set_super, &mnt_data);
+	/* BB should we make this contingent on mount parm? */
+	flags |= MS_NODIRATIME | MS_NOATIME;
+
+	sb = sget(fs_type, cifs_match_super, cifs_set_super, flags, &mnt_data);
 	if (IS_ERR(sb)) {
 		root = ERR_CAST(sb);
 		cifs_umount(cifs_sb);
@@ -649,10 +651,6 @@ cifs_do_mount(struct file_system_type *fs_type,
 		cFYI(1, "Use existing superblock");
 		cifs_umount(cifs_sb);
 	} else {
-		sb->s_flags = flags;
-		/* BB should we make this contingent on mount parm? */
-		sb->s_flags |= MS_NODIRATIME | MS_NOATIME;
-
 		rc = cifs_read_super(sb);
 		if (rc) {
 			root = ERR_PTR(rc);
@@ -778,6 +776,7 @@ struct file_system_type cifs_fs_type = {
 };
 const struct inode_operations cifs_dir_inode_ops = {
 	.create = cifs_create,
+	.atomic_open = cifs_atomic_open,
 	.lookup = cifs_lookup,
 	.getattr = cifs_getattr,
 	.unlink = cifs_unlink,

fs/cifs/cifsfs.h

@@ -45,9 +45,12 @@ extern const struct address_space_operations cifs_addr_ops_smallbuf;
 extern const struct inode_operations cifs_dir_inode_ops;
 extern struct inode *cifs_root_iget(struct super_block *);
 extern int cifs_create(struct inode *, struct dentry *, umode_t,
-		       struct nameidata *);
+		       bool excl);
+extern int cifs_atomic_open(struct inode *, struct dentry *,
+			    struct file *, unsigned, umode_t,
+			    int *);
 extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
-				  struct nameidata *);
+				  unsigned int);
 extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
 extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *);
 extern int cifs_mknod(struct inode *, struct dentry *, umode_t, dev_t);

fs/cifs/dir.c

@@ -133,108 +133,141 @@ cifs_bp_rename_retry:
 	return full_path;
 }
 
+/*
+ * Don't allow the separator character in a path component.
+ * The VFS will not allow "/", but "\" is allowed by posix.
+ */
+static int
+check_name(struct dentry *direntry)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
+	int i;
+
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
+		for (i = 0; i < direntry->d_name.len; i++) {
+			if (direntry->d_name.name[i] == '\\') {
+				cFYI(1, "Invalid file name");
+				return -EINVAL;
+			}
+		}
+	}
+	return 0;
+}
+
+
 /* Inode operations in similar order to how they appear in Linux file fs.h */
 
-int
-cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
-		struct nameidata *nd)
+static int cifs_do_create(struct inode *inode, struct dentry *direntry,
+			  int xid, struct tcon_link *tlink, unsigned oflags,
+			  umode_t mode, __u32 *oplock, __u16 *fileHandle,
+			  int *created)
 {
 	int rc = -ENOENT;
-	int xid;
 	int create_options = CREATE_NOT_DIR;
-	__u32 oplock = 0;
-	int oflags;
-	/*
-	 * BB below access is probably too much for mknod to request
-	 *    but we have to do query and setpathinfo so requesting
-	 *    less could fail (unless we want to request getatr and setatr
-	 *    permissions (only).  At least for POSIX we do not have to
-	 *    request so much.
-	 */
-	int desiredAccess = GENERIC_READ | GENERIC_WRITE;
-	__u16 fileHandle;
-	struct cifs_sb_info *cifs_sb;
-	struct tcon_link *tlink;
-	struct cifs_tcon *tcon;
+	int desiredAccess;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_tcon *tcon = tlink_tcon(tlink);
 	char *full_path = NULL;
 	FILE_ALL_INFO *buf = NULL;
 	struct inode *newinode = NULL;
-	int disposition = FILE_OVERWRITE_IF;
-
-	xid = GetXid();
-
-	cifs_sb = CIFS_SB(inode->i_sb);
-	tlink = cifs_sb_tlink(cifs_sb);
-	if (IS_ERR(tlink)) {
-		FreeXid(xid);
-		return PTR_ERR(tlink);
-	}
-	tcon = tlink_tcon(tlink);
+	int disposition;
 
+	*oplock = 0;
 	if (tcon->ses->server->oplocks)
-		oplock = REQ_OPLOCK;
-
-	if (nd)
-		oflags = nd->intent.open.file->f_flags;
-	else
-		oflags = O_RDONLY | O_CREAT;
+		*oplock = REQ_OPLOCK;
 
 	full_path = build_path_from_dentry(direntry);
 	if (full_path == NULL) {
 		rc = -ENOMEM;
-		goto cifs_create_out;
+		goto out;
 	}
 
 	if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) &&
+	    !tcon->broken_posix_open &&
 	    (CIFS_UNIX_POSIX_PATH_OPS_CAP &
 			le64_to_cpu(tcon->fsUnixInfo.Capability))) {
 		rc = cifs_posix_open(full_path, &newinode,
-			inode->i_sb, mode, oflags, &oplock, &fileHandle, xid);
-		/* EIO could indicate that (posix open) operation is not
-		   supported, despite what server claimed in capability
-		   negotiation.  EREMOTE indicates DFS junction, which is not
-		   handled in posix open */
-
-		if (rc == 0) {
-			if (newinode == NULL) /* query inode info */
+			inode->i_sb, mode, oflags, oplock, fileHandle, xid);
+		switch (rc) {
+		case 0:
+			if (newinode == NULL) {
+				/* query inode info */
 				goto cifs_create_get_file_info;
-			else /* success, no need to query */
-				goto cifs_create_set_dentry;
-		} else if ((rc != -EIO) && (rc != -EREMOTE) &&
-			 (rc != -EOPNOTSUPP) && (rc != -EINVAL))
-			goto cifs_create_out;
-		/* else fallthrough to retry, using older open call, this is
-		   case where server does not support this SMB level, and
-		   falsely claims capability (also get here for DFS case
-		   which should be rare for path not covered on files) */
-	}
+			}
+
+			if (!S_ISREG(newinode->i_mode)) {
+				/*
+				 * The server may allow us to open things like
+				 * FIFOs, but the client isn't set up to deal
+				 * with that. If it's not a regular file, just
+				 * close it and proceed as if it were a normal
+				 * lookup.
+				 */
+				CIFSSMBClose(xid, tcon, *fileHandle);
+				goto cifs_create_get_file_info;
+			}
+			/* success, no need to query */
+			goto cifs_create_set_dentry;
+
+		case -ENOENT:
+			goto cifs_create_get_file_info;
+
+		case -EIO:
+		case -EINVAL:
+			/*
+			 * EIO could indicate that (posix open) operation is not
+			 * supported, despite what server claimed in capability
+			 * negotiation.
+			 *
+			 * POSIX open in samba versions 3.3.1 and earlier could
+			 * incorrectly fail with invalid parameter.
+			 */
+			tcon->broken_posix_open = true;
+			break;
+
+		case -EREMOTE:
+		case -EOPNOTSUPP:
+			/*
+			 * EREMOTE indicates DFS junction, which is not handled
+			 * in posix open.  If either that or op not supported
+			 * returned, follow the normal lookup.
+			 */
+			break;
 
-	if (nd) {
-		/* if the file is going to stay open, then we
-		   need to set the desired access properly */
-		desiredAccess = 0;
-		if (OPEN_FMODE(oflags) & FMODE_READ)
-			desiredAccess |= GENERIC_READ; /* is this too little? */
-		if (OPEN_FMODE(oflags) & FMODE_WRITE)
-			desiredAccess |= GENERIC_WRITE;
-
-		if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
-			disposition = FILE_CREATE;
-		else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
-			disposition = FILE_OVERWRITE_IF;
-		else if ((oflags & O_CREAT) == O_CREAT)
-			disposition = FILE_OPEN_IF;
-		else
-			cFYI(1, "Create flag not set in create function");
+		default:
+			goto out;
+		}
+		/*
+		 * fallthrough to retry, using older open call, this is case
+		 * where server does not support this SMB level, and falsely
+		 * claims capability (also get here for DFS case which should be
+		 * rare for path not covered on files)
+		 */
 	}
 
+	desiredAccess = 0;
+	if (OPEN_FMODE(oflags) & FMODE_READ)
+		desiredAccess |= GENERIC_READ; /* is this too little? */
+	if (OPEN_FMODE(oflags) & FMODE_WRITE)
+		desiredAccess |= GENERIC_WRITE;
+
+	disposition = FILE_OVERWRITE_IF;
+	if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
+		disposition = FILE_CREATE;
+	else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
+		disposition = FILE_OVERWRITE_IF;
+	else if ((oflags & O_CREAT) == O_CREAT)
+		disposition = FILE_OPEN_IF;
+	else
+		cFYI(1, "Create flag not set in create function");
+
 	/* BB add processing to set equivalent of mode - e.g. via CreateX with
 	   ACLs */
 
 	buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
 	if (buf == NULL) {
 		rc = -ENOMEM;
-		goto cifs_create_out;
+		goto out;
 	}
 
 	/*
@@ -250,7 +283,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 	if (tcon->ses->capabilities & CAP_NT_SMBS)
 		rc = CIFSSMBOpen(xid, tcon, full_path, disposition,
 			 desiredAccess, create_options,
-			 &fileHandle, &oplock, buf, cifs_sb->local_nls,
+			 fileHandle, oplock, buf, cifs_sb->local_nls,
 			 cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
 	else
 		rc = -EIO; /* no NT SMB support fall into legacy open below */
@@ -259,17 +292,17 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 		/* old server, retry the open legacy style */
 		rc = SMBLegacyOpen(xid, tcon, full_path, disposition,
 			desiredAccess, create_options,
-			&fileHandle, &oplock, buf, cifs_sb->local_nls,
+			fileHandle, oplock, buf, cifs_sb->local_nls,
 			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
 	}
 	if (rc) {
 		cFYI(1, "cifs_create returned 0x%x", rc);
-		goto cifs_create_out;
+		goto out;
 	}
 
 	/* If Open reported that we actually created a file
 	   then we now have to set the mode if possible */
-	if ((tcon->unix_ext) && (oplock & CIFS_CREATE_ACTION)) {
+	if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) {
 		struct cifs_unix_set_info_args args = {
 				.mode	= mode,
 				.ctime	= NO_CHANGE_64,
@@ -278,6 +311,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 				.device	= 0,
 		};
 
+		*created |= FILE_CREATED;
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
 			args.uid = (__u64) current_fsuid();
 			if (inode->i_mode & S_ISGID)
@@ -288,7 +322,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 			args.uid = NO_CHANGE_64;
 			args.gid = NO_CHANGE_64;
 		}
-		CIFSSMBUnixSetFileInfo(xid, tcon, &args, fileHandle,
+		CIFSSMBUnixSetFileInfo(xid, tcon, &args, *fileHandle,
 					current->tgid);
 	} else {
 		/* BB implement mode setting via Windows security
@@ -305,11 +339,11 @@ cifs_create_get_file_info:
 					      inode->i_sb, xid);
 	else {
 		rc = cifs_get_inode_info(&newinode, full_path, buf,
-					 inode->i_sb, xid, &fileHandle);
+					 inode->i_sb, xid, fileHandle);
 		if (newinode) {
 			if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
 				newinode->i_mode = mode;
-			if ((oplock & CIFS_CREATE_ACTION) &&
+			if ((*oplock & CIFS_CREATE_ACTION) &&
 			    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) {
 				newinode->i_uid = current_fsuid();
 				if (inode->i_mode & S_ISGID)
@@ -321,40 +355,139 @@ cifs_create_get_file_info:
 	}
 
 cifs_create_set_dentry:
-	if (rc == 0)
-		d_instantiate(direntry, newinode);
-	else
+	if (rc != 0) {
 		cFYI(1, "Create worked, get_inode_info failed rc = %d", rc);
+		goto out;
+	}
+	d_drop(direntry);
+	d_add(direntry, newinode);
 
-	if (newinode && nd) {
-		struct cifsFileInfo *pfile_info;
-		struct file *filp;
+	/* ENOENT for create?  How weird... */
+	rc = -ENOENT;
+	if (!newinode) {
+		CIFSSMBClose(xid, tcon, *fileHandle);
+		goto out;
+	}
+	rc = 0;
 
-		filp = lookup_instantiate_filp(nd, direntry, generic_file_open);
-		if (IS_ERR(filp)) {
-			rc = PTR_ERR(filp);
-			CIFSSMBClose(xid, tcon, fileHandle);
-			goto cifs_create_out;
-		}
+out:
+	kfree(buf);
+	kfree(full_path);
+	return rc;
+}
 
-		pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock);
-		if (pfile_info == NULL) {
-			fput(filp);
-			CIFSSMBClose(xid, tcon, fileHandle);
-			rc = -ENOMEM;
-		}
-	} else {
+int
+cifs_atomic_open(struct inode *inode, struct dentry *direntry,
+		 struct file *file, unsigned oflags, umode_t mode,
+		 int *opened)
+{
+	int rc;
+	int xid;
+	struct tcon_link *tlink;
+	struct cifs_tcon *tcon;
+	__u16 fileHandle;
+	__u32 oplock;
+	struct file *filp;
+	struct cifsFileInfo *pfile_info;
+
+	/* Posix open is only called (at lookup time) for file create now.  For
+	 * opens (rather than creates), because we do not know if it is a file
+	 * or directory yet, and current Samba no longer allows us to do posix
+	 * open on dirs, we could end up wasting an open call on what turns out
+	 * to be a dir. For file opens, we wait to call posix open till
+	 * cifs_open.  It could be added to atomic_open in the future but the
+	 * performance tradeoff of the extra network request when EISDIR or
+	 * EACCES is returned would have to be weighed against the 50% reduction
+	 * in network traffic in the other paths.
+	 */
+	if (!(oflags & O_CREAT)) {
+		struct dentry *res = cifs_lookup(inode, direntry, 0);
+		if (IS_ERR(res))
+			return PTR_ERR(res);
+
+		return finish_no_open(file, res);
+	}
+
+	rc = check_name(direntry);
+	if (rc)
+		return rc;
+
+	xid = GetXid();
+
+	cFYI(1, "parent inode = 0x%p name is: %s and dentry = 0x%p",
+	     inode, direntry->d_name.name, direntry);
+
+	tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
+	filp = ERR_CAST(tlink);
+	if (IS_ERR(tlink))
+		goto free_xid;
+
+	tcon = tlink_tcon(tlink);
+
+	rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
+			    &oplock, &fileHandle, opened);
+
+	if (rc)
+		goto out;
+
+	rc = finish_open(file, direntry, generic_file_open, opened);
+	if (rc) {
 		CIFSSMBClose(xid, tcon, fileHandle);
+		goto out;
 	}
 
-cifs_create_out:
-	kfree(buf);
-	kfree(full_path);
+	pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock);
+	if (pfile_info == NULL) {
+		CIFSSMBClose(xid, tcon, fileHandle);
+		fput(filp);
+		rc = -ENOMEM;
+	}
+
+out:
 	cifs_put_tlink(tlink);
+free_xid:
 	FreeXid(xid);
 	return rc;
 }
 
+int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
+		bool excl)
+{
+	int rc;
+	int xid = GetXid();
+	/*
+	 * BB below access is probably too much for mknod to request
+	 *    but we have to do query and setpathinfo so requesting
+	 *    less could fail (unless we want to request getatr and setatr
+	 *    permissions (only).  At least for POSIX we do not have to
+	 *    request so much.
+	 */
+	unsigned oflags = O_EXCL | O_CREAT | O_RDWR;
+	struct tcon_link *tlink;
+	__u16 fileHandle;
+	__u32 oplock;
+	int created = FILE_CREATED;
+
+	cFYI(1, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p",
+	     inode, direntry->d_name.name, direntry);
+
+	tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
+	rc = PTR_ERR(tlink);
+	if (IS_ERR(tlink))
+		goto free_xid;
+
+	rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
+			    &oplock, &fileHandle, &created);
+	if (!rc)
+		CIFSSMBClose(xid, tlink_tcon(tlink), fileHandle);
+
+	cifs_put_tlink(tlink);
+free_xid:
+	FreeXid(xid);
+
+	return rc;
+}
+
 int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
 		dev_t device_number)
 {
@@ -488,20 +621,15 @@ mknod_out:
 
 struct dentry *
 cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
-	    struct nameidata *nd)
+	    unsigned int flags)
 {
 	int xid;
 	int rc = 0; /* to get around spurious gcc warning, set to zero here */
-	__u32 oplock;
-	__u16 fileHandle = 0;
-	bool posix_open = false;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
 	struct cifs_tcon *pTcon;
-	struct cifsFileInfo *cfile;
 	struct inode *newInode = NULL;
 	char *full_path = NULL;
-	struct file *filp;
 
 	xid = GetXid();
 
@@ -518,31 +646,9 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	}
 	pTcon = tlink_tcon(tlink);
 
-	oplock = pTcon->ses->server->oplocks ? REQ_OPLOCK : 0;
-
-	/*
-	 * Don't allow the separator character in a path component.
-	 * The VFS will not allow "/", but "\" is allowed by posix.
-	 */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
-		int i;
-		for (i = 0; i < direntry->d_name.len; i++)
-			if (direntry->d_name.name[i] == '\\') {
-				cFYI(1, "Invalid file name");
-				rc = -EINVAL;
-				goto lookup_out;
-			}
-	}
-
-	/*
-	 * O_EXCL: optimize away the lookup, but don't hash the dentry. Let
-	 * the VFS handle the create.
-	 */
-	if (nd && (nd->flags & LOOKUP_EXCL)) {
-		d_instantiate(direntry, NULL);
-		rc = 0;
+	rc = check_name(direntry);
+	if (rc)
 		goto lookup_out;
-	}
 
 	/* can not grab the rename sem here since it would
 	deadlock in the cases (beginning of sys_rename itself)
@@ -560,80 +666,16 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 	}
 	cFYI(1, "Full path: %s inode = 0x%p", full_path, direntry->d_inode);
 
-	/* Posix open is only called (at lookup time) for file create now.
-	 * For opens (rather than creates), because we do not know if it
-	 * is a file or directory yet, and current Samba no longer allows
-	 * us to do posix open on dirs, we could end up wasting an open call
-	 * on what turns out to be a dir. For file opens, we wait to call posix
-	 * open till cifs_open.  It could be added here (lookup) in the future
-	 * but the performance tradeoff of the extra network request when EISDIR
-	 * or EACCES is returned would have to be weighed against the 50%
-	 * reduction in network traffic in the other paths.
-	 */
 	if (pTcon->unix_ext) {
-		if (nd && !(nd->flags & LOOKUP_DIRECTORY) &&
-		     (nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open &&
-		     (nd->intent.open.file->f_flags & O_CREAT)) {
-			rc = cifs_posix_open(full_path, &newInode,
-					parent_dir_inode->i_sb,
-					nd->intent.open.create_mode,
-					nd->intent.open.file->f_flags, &oplock,
-					&fileHandle, xid);
-			/*
-			 * The check below works around a bug in POSIX
-			 * open in samba versions 3.3.1 and earlier where
-			 * open could incorrectly fail with invalid parameter.
-			 * If either that or op not supported returned, follow
-			 * the normal lookup.
-			 */
-			switch (rc) {
-			case 0:
-				/*
-				 * The server may allow us to open things like
-				 * FIFOs, but the client isn't set up to deal
-				 * with that. If it's not a regular file, just
-				 * close it and proceed as if it were a normal
-				 * lookup.
-				 */
-				if (newInode && !S_ISREG(newInode->i_mode)) {
-					CIFSSMBClose(xid, pTcon, fileHandle);
-					break;
-				}
-			case -ENOENT:
-				posix_open = true;
-			case -EOPNOTSUPP:
-				break;
-			default:
-				pTcon->broken_posix_open = true;
-			}
-		}
-		if (!posix_open)
-			rc = cifs_get_inode_info_unix(&newInode, full_path,
-						parent_dir_inode->i_sb, xid);
-	} else
+		rc = cifs_get_inode_info_unix(&newInode, full_path,
+					      parent_dir_inode->i_sb, xid);
+	} else {
 		rc = cifs_get_inode_info(&newInode, full_path, NULL,
 				parent_dir_inode->i_sb, xid, NULL);
+	}
 
 	if ((rc == 0) && (newInode != NULL)) {
 		d_add(direntry, newInode);
-		if (posix_open) {
-			filp = lookup_instantiate_filp(nd, direntry,
-						       generic_file_open);
-			if (IS_ERR(filp)) {
-				rc = PTR_ERR(filp);
-				CIFSSMBClose(xid, pTcon, fileHandle);
-				goto lookup_out;
-			}
-
-			cfile = cifs_new_fileinfo(fileHandle, filp, tlink,
-						  oplock);
-			if (cfile == NULL) {
-				fput(filp);
-				CIFSSMBClose(xid, pTcon, fileHandle);
-				rc = -ENOMEM;
-				goto lookup_out;
-			}
-		}
 		/* since paths are not looked up by component - the parent
 		   directories are presumed to be good here */
 		renew_parental_timestamps(direntry);
@@ -658,9 +700,9 @@ lookup_out:
 }
 
 static int
-cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
+cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
 {
-	if (nd && (nd->flags & LOOKUP_RCU))
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	if (direntry->d_inode) {
@@ -689,7 +731,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
 	 * This may be nfsd (or something), anyway, we can't see the
 	 * intent of this. So, since this can be for creation, drop it.
 	 */
-	if (!nd)
+	if (!flags)
 		return 0;
 
 	/*
@@ -697,7 +739,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
 	 * case sensitive name which is specified by user if this is
 	 * for creation.
 	 */
-	if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+	if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
 		return 0;
 
 	if (time_after(jiffies, direntry->d_time + HZ) || !lookupCacheEnabled)

fs/cifs/inode.c

@@ -800,7 +800,7 @@ cifs_find_inode(struct inode *inode, void *opaque)
 		return 0;
 
 	/* if it's not a directory or has no dentries, then flag it */
-	if (S_ISDIR(inode->i_mode) && !list_empty(&inode->i_dentry))
+	if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry))
 		fattr->cf_flags |= CIFS_FATTR_INO_COLLISION;
 
 	return 1;
@@ -825,9 +825,10 @@ static bool
 inode_has_hashed_dentries(struct inode *inode)
 {
 	struct dentry *dentry;
+	struct hlist_node *p;
 
 	spin_lock(&inode->i_lock);
-	list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
 		if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
 			spin_unlock(&inode->i_lock);
 			return true;

fs/coda/cache.c

@@ -89,17 +89,13 @@ int coda_cache_check(struct inode *inode, int mask)
 /* this won't do any harm: just flag all children */
 static void coda_flag_children(struct dentry *parent, int flag)
 {
-	struct list_head *child;
 	struct dentry *de;
 
 	spin_lock(&parent->d_lock);
-	list_for_each(child, &parent->d_subdirs)
-	{
-		de = list_entry(child, struct dentry, d_u.d_child);
+	list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) {
 		/* don't know what to do with negative dentries */
-		if ( ! de->d_inode ) 
-			continue;
-		coda_flag_inode(de->d_inode, flag);
+		if (de->d_inode ) 
+			coda_flag_inode(de->d_inode, flag);
 	}
 	spin_unlock(&parent->d_lock);
 	return; 

fs/coda/dir.c

@@ -30,8 +30,8 @@
 #include "coda_int.h"
 
 /* dir inode-ops */
-static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, struct nameidata *nd);
-static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, struct nameidata *nd);
+static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, bool excl);
+static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, unsigned int flags);
 static int coda_link(struct dentry *old_dentry, struct inode *dir_inode, 
 		     struct dentry *entry);
 static int coda_unlink(struct inode *dir_inode, struct dentry *entry);
@@ -46,7 +46,7 @@ static int coda_rename(struct inode *old_inode, struct dentry *old_dentry,
 static int coda_readdir(struct file *file, void *buf, filldir_t filldir);
 
 /* dentry ops */
-static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd);
+static int coda_dentry_revalidate(struct dentry *de, unsigned int flags);
 static int coda_dentry_delete(const struct dentry *);
 
 /* support routines */
@@ -94,7 +94,7 @@ const struct file_operations coda_dir_operations = {
 
 /* inode operations for directories */
 /* access routines: lookup, readlink, permission */
-static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, struct nameidata *nd)
+static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsigned int flags)
 {
 	struct super_block *sb = dir->i_sb;
 	const char *name = entry->d_name.name;
@@ -188,7 +188,7 @@ static inline void coda_dir_drop_nlink(struct inode *dir)
 }
 
 /* creation routines: create, mknod, mkdir, link, symlink */
-static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, struct nameidata *nd)
+static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool excl)
 {
 	int error;
 	const char *name=de->d_name.name;
@@ -536,12 +536,12 @@ out:
 }
 
 /* called when a cache lookup succeeds */
-static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd)
+static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
 {
 	struct inode *inode;
 	struct coda_inode_info *cii;
 
-	if (nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	inode = de->d_inode;

fs/configfs/dir.c

@@ -442,7 +442,7 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den
 
 static struct dentry * configfs_lookup(struct inode *dir,
 				       struct dentry *dentry,
-				       struct nameidata *nd)
+				       unsigned int flags)
 {
 	struct configfs_dirent * parent_sd = dentry->d_parent->d_fsdata;
 	struct configfs_dirent * sd;

fs/cramfs/inode.c

@@ -417,7 +417,7 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 /*
  * Lookup and fill in the inode data..
  */
-static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	unsigned int offset = 0;
 	struct inode *inode = NULL;

fs/dcache.c

@@ -218,7 +218,7 @@ static void __d_free(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
 
-	WARN_ON(!list_empty(&dentry->d_alias));
+	WARN_ON(!hlist_unhashed(&dentry->d_alias));
 	if (dname_external(dentry))
 		kfree(dentry->d_name.name);
 	kmem_cache_free(dentry_cache, dentry); 
@@ -267,7 +267,7 @@ static void dentry_iput(struct dentry * dentry)
 	struct inode *inode = dentry->d_inode;
 	if (inode) {
 		dentry->d_inode = NULL;
-		list_del_init(&dentry->d_alias);
+		hlist_del_init(&dentry->d_alias);
 		spin_unlock(&dentry->d_lock);
 		spin_unlock(&inode->i_lock);
 		if (!inode->i_nlink)
@@ -291,7 +291,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
 {
 	struct inode *inode = dentry->d_inode;
 	dentry->d_inode = NULL;
-	list_del_init(&dentry->d_alias);
+	hlist_del_init(&dentry->d_alias);
 	dentry_rcuwalk_barrier(dentry);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
@@ -699,10 +699,11 @@ EXPORT_SYMBOL(dget_parent);
 static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
 {
 	struct dentry *alias, *discon_alias;
+	struct hlist_node *p;
 
 again:
 	discon_alias = NULL;
-	list_for_each_entry(alias, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
 		spin_lock(&alias->d_lock);
  		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
 			if (IS_ROOT(alias) &&
@@ -737,7 +738,7 @@ struct dentry *d_find_alias(struct inode *inode)
 {
 	struct dentry *de = NULL;
 
-	if (!list_empty(&inode->i_dentry)) {
+	if (!hlist_empty(&inode->i_dentry)) {
 		spin_lock(&inode->i_lock);
 		de = __d_find_alias(inode, 0);
 		spin_unlock(&inode->i_lock);
@@ -753,9 +754,10 @@ EXPORT_SYMBOL(d_find_alias);
 void d_prune_aliases(struct inode *inode)
 {
 	struct dentry *dentry;
+	struct hlist_node *p;
 restart:
 	spin_lock(&inode->i_lock);
-	list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!dentry->d_count) {
 			__dget_dlock(dentry);
@@ -977,7 +979,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 			inode = dentry->d_inode;
 			if (inode) {
 				dentry->d_inode = NULL;
-				list_del_init(&dentry->d_alias);
+				hlist_del_init(&dentry->d_alias);
 				if (dentry->d_op && dentry->d_op->d_iput)
 					dentry->d_op->d_iput(dentry, inode);
 				else
@@ -1312,7 +1314,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	INIT_HLIST_BL_NODE(&dentry->d_hash);
 	INIT_LIST_HEAD(&dentry->d_lru);
 	INIT_LIST_HEAD(&dentry->d_subdirs);
-	INIT_LIST_HEAD(&dentry->d_alias);
+	INIT_HLIST_NODE(&dentry->d_alias);
 	INIT_LIST_HEAD(&dentry->d_u.d_child);
 	d_set_d_op(dentry, dentry->d_sb->s_d_op);
 
@@ -1400,7 +1402,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	if (inode) {
 		if (unlikely(IS_AUTOMOUNT(inode)))
 			dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
-		list_add(&dentry->d_alias, &inode->i_dentry);
+		hlist_add_head(&dentry->d_alias, &inode->i_dentry);
 	}
 	dentry->d_inode = inode;
 	dentry_rcuwalk_barrier(dentry);
@@ -1425,7 +1427,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
  
 void d_instantiate(struct dentry *entry, struct inode * inode)
 {
-	BUG_ON(!list_empty(&entry->d_alias));
+	BUG_ON(!hlist_unhashed(&entry->d_alias));
 	if (inode)
 		spin_lock(&inode->i_lock);
 	__d_instantiate(entry, inode);
@@ -1458,13 +1460,14 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry,
 	int len = entry->d_name.len;
 	const char *name = entry->d_name.name;
 	unsigned int hash = entry->d_name.hash;
+	struct hlist_node *p;
 
 	if (!inode) {
 		__d_instantiate(entry, NULL);
 		return NULL;
 	}
 
-	list_for_each_entry(alias, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
 		/*
 		 * Don't need alias->d_lock here, because aliases with
 		 * d_parent == entry->d_parent are not subject to name or
@@ -1490,7 +1493,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
 {
 	struct dentry *result;
 
-	BUG_ON(!list_empty(&entry->d_alias));
+	BUG_ON(!hlist_unhashed(&entry->d_alias));
 
 	if (inode)
 		spin_lock(&inode->i_lock);
@@ -1531,9 +1534,9 @@ static struct dentry * __d_find_any_alias(struct inode *inode)
 {
 	struct dentry *alias;
 
-	if (list_empty(&inode->i_dentry))
+	if (hlist_empty(&inode->i_dentry))
 		return NULL;
-	alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias);
+	alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
 	__dget(alias);
 	return alias;
 }
@@ -1607,7 +1610,7 @@ struct dentry *d_obtain_alias(struct inode *inode)
 	spin_lock(&tmp->d_lock);
 	tmp->d_inode = inode;
 	tmp->d_flags |= DCACHE_DISCONNECTED;
-	list_add(&tmp->d_alias, &inode->i_dentry);
+	hlist_add_head(&tmp->d_alias, &inode->i_dentry);
 	hlist_bl_lock(&tmp->d_sb->s_anon);
 	hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
 	hlist_bl_unlock(&tmp->d_sb->s_anon);
@@ -2384,14 +2387,13 @@ static struct dentry *__d_unalias(struct inode *inode,
 		struct dentry *dentry, struct dentry *alias)
 {
 	struct mutex *m1 = NULL, *m2 = NULL;
-	struct dentry *ret;
+	struct dentry *ret = ERR_PTR(-EBUSY);
 
 	/* If alias and dentry share a parent, then no extra locks required */
 	if (alias->d_parent == dentry->d_parent)
 		goto out_unalias;
 
 	/* See lock_rename() */
-	ret = ERR_PTR(-EBUSY);
 	if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
 		goto out_err;
 	m1 = &dentry->d_sb->s_vfs_rename_mutex;
@@ -2399,8 +2401,10 @@ static struct dentry *__d_unalias(struct inode *inode,
 		goto out_err;
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
-	__d_move(alias, dentry);
-	ret = alias;
+	if (likely(!d_mountpoint(alias))) {
+		__d_move(alias, dentry);
+		ret = alias;
+	}
 out_err:
 	spin_unlock(&inode->i_lock);
 	if (m2)
@@ -2622,7 +2626,7 @@ global_root:
 	if (!slash)
 		error = prepend(buffer, buflen, "/", 1);
 	if (!error)
-		error = real_mount(vfsmnt)->mnt_ns ? 1 : 2;
+		error = is_mounted(vfsmnt) ? 1 : 2;
 	goto out;
 }
 

fs/debugfs/inode.c

@@ -54,13 +54,12 @@ static struct inode *debugfs_get_inode(struct super_block *sb, umode_t mode, dev
 			break;
 		case S_IFLNK:
 			inode->i_op = &debugfs_link_operations;
-			inode->i_fop = fops;
 			inode->i_private = data;
 			break;
 		case S_IFDIR:
 			inode->i_op = &simple_dir_inode_operations;
-			inode->i_fop = fops ? fops : &simple_dir_operations;
-			inode->i_private = data;
+			inode->i_fop = &simple_dir_operations;
+			inode->i_private = NULL;
 
 			/* directory inodes start off with i_nlink == 2
 			 * (for "." entry) */
@@ -91,13 +90,12 @@ static int debugfs_mknod(struct inode *dir, struct dentry *dentry,
 	return error;
 }
 
-static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode,
-			 void *data, const struct file_operations *fops)
+static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	int res;
 
 	mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR;
-	res = debugfs_mknod(dir, dentry, mode, 0, data, fops);
+	res = debugfs_mknod(dir, dentry, mode, 0, NULL, NULL);
 	if (!res) {
 		inc_nlink(dir);
 		fsnotify_mkdir(dir, dentry);
@@ -106,10 +104,10 @@ static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode,
 }
 
 static int debugfs_link(struct inode *dir, struct dentry *dentry, umode_t mode,
-			void *data, const struct file_operations *fops)
+			void *data)
 {
 	mode = (mode & S_IALLUGO) | S_IFLNK;
-	return debugfs_mknod(dir, dentry, mode, 0, data, fops);
+	return debugfs_mknod(dir, dentry, mode, 0, data, NULL);
 }
 
 static int debugfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
@@ -293,13 +291,19 @@ static struct file_system_type debug_fs_type = {
 	.kill_sb =	kill_litter_super,
 };
 
-static int debugfs_create_by_name(const char *name, umode_t mode,
-				  struct dentry *parent,
-				  struct dentry **dentry,
-				  void *data,
-				  const struct file_operations *fops)
+struct dentry *__create_file(const char *name, umode_t mode,
+				   struct dentry *parent, void *data,
+				   const struct file_operations *fops)
 {
-	int error = 0;
+	struct dentry *dentry = NULL;
+	int error;
+
+	pr_debug("debugfs: creating file '%s'\n",name);
+
+	error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
+			      &debugfs_mount_count);
+	if (error)
+		goto exit;
 
 	/* If the parent is not specified, we create it in the root.
 	 * We need the root dentry to do this, which is in the super 
@@ -309,30 +313,35 @@ static int debugfs_create_by_name(const char *name, umode_t mode,
 	if (!parent)
 		parent = debugfs_mount->mnt_root;
 
-	*dentry = NULL;
+	dentry = NULL;
 	mutex_lock(&parent->d_inode->i_mutex);
-	*dentry = lookup_one_len(name, parent, strlen(name));
-	if (!IS_ERR(*dentry)) {
+	dentry = lookup_one_len(name, parent, strlen(name));
+	if (!IS_ERR(dentry)) {
 		switch (mode & S_IFMT) {
 		case S_IFDIR:
-			error = debugfs_mkdir(parent->d_inode, *dentry, mode,
-					      data, fops);
+			error = debugfs_mkdir(parent->d_inode, dentry, mode);
+					      
 			break;
 		case S_IFLNK:
-			error = debugfs_link(parent->d_inode, *dentry, mode,
-					     data, fops);
+			error = debugfs_link(parent->d_inode, dentry, mode,
+					     data);
 			break;
 		default:
-			error = debugfs_create(parent->d_inode, *dentry, mode,
+			error = debugfs_create(parent->d_inode, dentry, mode,
 					       data, fops);
 			break;
 		}
-		dput(*dentry);
+		dput(dentry);
 	} else
-		error = PTR_ERR(*dentry);
+		error = PTR_ERR(dentry);
 	mutex_unlock(&parent->d_inode->i_mutex);
 
-	return error;
+	if (error) {
+		dentry = NULL;
+		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+	}
+exit:
+	return dentry;
 }
 
 /**
@@ -365,25 +374,15 @@ struct dentry *debugfs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops)
 {
-	struct dentry *dentry = NULL;
-	int error;
-
-	pr_debug("debugfs: creating file '%s'\n",name);
-
-	error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
-			      &debugfs_mount_count);
-	if (error)
-		goto exit;
-
-	error = debugfs_create_by_name(name, mode, parent, &dentry,
-				       data, fops);
-	if (error) {
-		dentry = NULL;
-		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
-		goto exit;
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+	case 0:
+		break;
+	default:
+		BUG();
 	}
-exit:
-	return dentry;
+
+	return __create_file(name, mode, parent, data, fops);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_file);
 
@@ -407,8 +406,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_file);
  */
 struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
 {
-	return debugfs_create_file(name, 
-				   S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
+	return __create_file(name, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
 				   parent, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_dir);
@@ -446,8 +444,7 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 	if (!link)
 		return NULL;
 
-	result = debugfs_create_file(name, S_IFLNK | S_IRWXUGO, parent, link,
-				     NULL);
+	result = __create_file(name, S_IFLNK | S_IRWXUGO, parent, link, NULL);
 	if (!result)
 		kfree(link);
 	return result;

fs/devpts/inode.c

@@ -439,15 +439,15 @@ static struct dentry *devpts_mount(struct file_system_type *fs_type,
 		return ERR_PTR(error);
 
 	if (opts.newinstance)
-		s = sget(fs_type, NULL, set_anon_super, NULL);
+		s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	else
-		s = sget(fs_type, compare_init_pts_sb, set_anon_super, NULL);
+		s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags,
+			 NULL);
 
 	if (IS_ERR(s))
 		return ERR_CAST(s);
 
 	if (!s->s_root) {
-		s->s_flags = flags;
 		error = devpts_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
 		if (error)
 			goto out_undo_sget;

fs/direct-io.c

@@ -1258,7 +1258,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	 */
 	BUG_ON(retval == -EIOCBQUEUED);
 	if (dio->is_async && retval == 0 && dio->result &&
-	    ((rw & READ) || (dio->result == sdio.size)))
+	    ((rw == READ) || (dio->result == sdio.size)))
 		retval = -EIOCBQUEUED;
 
 	if (retval != -EIOCBQUEUED)

fs/ecryptfs/dentry.c

@@ -32,7 +32,7 @@
 /**
  * ecryptfs_d_revalidate - revalidate an ecryptfs dentry
  * @dentry: The ecryptfs dentry
- * @nd: The associated nameidata
+ * @flags: lookup flags
  *
  * Called when the VFS needs to revalidate a dentry. This
  * is called whenever a name lookup finds a dentry in the
@@ -42,32 +42,20 @@
  * Returns 1 if valid, 0 otherwise.
  *
  */
-static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *lower_dentry;
 	struct vfsmount *lower_mnt;
-	struct dentry *dentry_save = NULL;
-	struct vfsmount *vfsmount_save = NULL;
 	int rc = 1;
 
-	if (nd && nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
 	if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
 		goto out;
-	if (nd) {
-		dentry_save = nd->path.dentry;
-		vfsmount_save = nd->path.mnt;
-		nd->path.dentry = lower_dentry;
-		nd->path.mnt = lower_mnt;
-	}
-	rc = lower_dentry->d_op->d_revalidate(lower_dentry, nd);
-	if (nd) {
-		nd->path.dentry = dentry_save;
-		nd->path.mnt = vfsmount_save;
-	}
+	rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
 	if (dentry->d_inode) {
 		struct inode *lower_inode =
 			ecryptfs_inode_to_lower(dentry->d_inode);

fs/ecryptfs/ecryptfs_kernel.h

@@ -550,20 +550,6 @@ extern struct kmem_cache *ecryptfs_key_record_cache;
 extern struct kmem_cache *ecryptfs_key_sig_cache;
 extern struct kmem_cache *ecryptfs_global_auth_tok_cache;
 extern struct kmem_cache *ecryptfs_key_tfm_cache;
-extern struct kmem_cache *ecryptfs_open_req_cache;
-
-struct ecryptfs_open_req {
-#define ECRYPTFS_REQ_PROCESSED 0x00000001
-#define ECRYPTFS_REQ_DROPPED   0x00000002
-#define ECRYPTFS_REQ_ZOMBIE    0x00000004
-	u32 flags;
-	struct file **lower_file;
-	struct dentry *lower_dentry;
-	struct vfsmount *lower_mnt;
-	wait_queue_head_t wait;
-	struct mutex mux;
-	struct list_head kthread_ctl_list;
-};
 
 struct inode *ecryptfs_get_inode(struct inode *lower_inode,
 				 struct super_block *sb);

fs/ecryptfs/inode.c

@@ -173,7 +173,7 @@ ecryptfs_do_create(struct inode *directory_inode,
 		inode = ERR_CAST(lower_dir_dentry);
 		goto out;
 	}
-	rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, NULL);
+	rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, true);
 	if (rc) {
 		printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
 		       "rc = [%d]\n", __func__, rc);
@@ -240,7 +240,6 @@ out:
  * @dir: The inode of the directory in which to create the file.
  * @dentry: The eCryptfs dentry
  * @mode: The mode of the new file.
- * @nd: nameidata
  *
  * Creates a new file.
  *
@@ -248,7 +247,7 @@ out:
  */
 static int
 ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
-		umode_t mode, struct nameidata *nd)
+		umode_t mode, bool excl)
 {
 	struct inode *ecryptfs_inode;
 	int rc;
@@ -270,8 +269,8 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
 		iput(ecryptfs_inode);
 		goto out;
 	}
-	d_instantiate(ecryptfs_dentry, ecryptfs_inode);
 	unlock_new_inode(ecryptfs_inode);
+	d_instantiate(ecryptfs_dentry, ecryptfs_inode);
 out:
 	return rc;
 }
@@ -374,7 +373,7 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
  */
 static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 				      struct dentry *ecryptfs_dentry,
-				      struct nameidata *ecryptfs_nd)
+				      unsigned int flags)
 {
 	char *encrypted_and_encoded_name = NULL;
 	size_t encrypted_and_encoded_name_size;

fs/ecryptfs/kthread.c

@@ -27,7 +27,12 @@
 #include <linux/mount.h>
 #include "ecryptfs_kernel.h"
 
-struct kmem_cache *ecryptfs_open_req_cache;
+struct ecryptfs_open_req {
+	struct file **lower_file;
+	struct path path;
+	struct completion done;
+	struct list_head kthread_ctl_list;
+};
 
 static struct ecryptfs_kthread_ctl {
 #define ECRYPTFS_KTHREAD_ZOMBIE 0x00000001
@@ -67,18 +72,10 @@ static int ecryptfs_threadfn(void *ignored)
 			req = list_first_entry(&ecryptfs_kthread_ctl.req_list,
 					       struct ecryptfs_open_req,
 					       kthread_ctl_list);
-			mutex_lock(&req->mux);
 			list_del(&req->kthread_ctl_list);
-			if (!(req->flags & ECRYPTFS_REQ_ZOMBIE)) {
-				dget(req->lower_dentry);
-				mntget(req->lower_mnt);
-				(*req->lower_file) = dentry_open(
-					req->lower_dentry, req->lower_mnt,
-					(O_RDWR | O_LARGEFILE), current_cred());
-				req->flags |= ECRYPTFS_REQ_PROCESSED;
-			}
-			wake_up(&req->wait);
-			mutex_unlock(&req->mux);
+			*req->lower_file = dentry_open(&req->path,
+				(O_RDWR | O_LARGEFILE), current_cred());
+			complete(&req->done);
 		}
 		mutex_unlock(&ecryptfs_kthread_ctl.mux);
 	}
@@ -111,10 +108,9 @@ void ecryptfs_destroy_kthread(void)
 	ecryptfs_kthread_ctl.flags |= ECRYPTFS_KTHREAD_ZOMBIE;
 	list_for_each_entry(req, &ecryptfs_kthread_ctl.req_list,
 			    kthread_ctl_list) {
-		mutex_lock(&req->mux);
-		req->flags |= ECRYPTFS_REQ_ZOMBIE;
-		wake_up(&req->wait);
-		mutex_unlock(&req->mux);
+		list_del(&req->kthread_ctl_list);
+		*req->lower_file = ERR_PTR(-EIO);
+		complete(&req->done);
 	}
 	mutex_unlock(&ecryptfs_kthread_ctl.mux);
 	kthread_stop(ecryptfs_kthread);
@@ -136,34 +132,26 @@ int ecryptfs_privileged_open(struct file **lower_file,
 			     struct vfsmount *lower_mnt,
 			     const struct cred *cred)
 {
-	struct ecryptfs_open_req *req;
+	struct ecryptfs_open_req req;
 	int flags = O_LARGEFILE;
 	int rc = 0;
 
+	init_completion(&req.done);
+	req.lower_file = lower_file;
+	req.path.dentry = lower_dentry;
+	req.path.mnt = lower_mnt;
+
 	/* Corresponding dput() and mntput() are done when the
 	 * lower file is fput() when all eCryptfs files for the inode are
 	 * released. */
-	dget(lower_dentry);
-	mntget(lower_mnt);
 	flags |= IS_RDONLY(lower_dentry->d_inode) ? O_RDONLY : O_RDWR;
-	(*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred);
+	(*lower_file) = dentry_open(&req.path, flags, cred);
 	if (!IS_ERR(*lower_file))
 		goto out;
 	if ((flags & O_ACCMODE) == O_RDONLY) {
 		rc = PTR_ERR((*lower_file));
 		goto out;
 	}
-	req = kmem_cache_alloc(ecryptfs_open_req_cache, GFP_KERNEL);
-	if (!req) {
-		rc = -ENOMEM;
-		goto out;
-	}
-	mutex_init(&req->mux);
-	req->lower_file = lower_file;
-	req->lower_dentry = lower_dentry;
-	req->lower_mnt = lower_mnt;
-	init_waitqueue_head(&req->wait);
-	req->flags = 0;
 	mutex_lock(&ecryptfs_kthread_ctl.mux);
 	if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
 		rc = -EIO;
@@ -171,27 +159,14 @@ int ecryptfs_privileged_open(struct file **lower_file,
 		printk(KERN_ERR "%s: We are in the middle of shutting down; "
 		       "aborting privileged request to open lower file\n",
 			__func__);
-		goto out_free;
+		goto out;
 	}
-	list_add_tail(&req->kthread_ctl_list, &ecryptfs_kthread_ctl.req_list);
+	list_add_tail(&req.kthread_ctl_list, &ecryptfs_kthread_ctl.req_list);
 	mutex_unlock(&ecryptfs_kthread_ctl.mux);
 	wake_up(&ecryptfs_kthread_ctl.wait);
-	wait_event(req->wait, (req->flags != 0));
-	mutex_lock(&req->mux);
-	BUG_ON(req->flags == 0);
-	if (req->flags & ECRYPTFS_REQ_DROPPED
-	    || req->flags & ECRYPTFS_REQ_ZOMBIE) {
-		rc = -EIO;
-		printk(KERN_WARNING "%s: Privileged open request dropped\n",
-		       __func__);
-		goto out_unlock;
-	}
-	if (IS_ERR(*req->lower_file))
-		rc = PTR_ERR(*req->lower_file);
-out_unlock:
-	mutex_unlock(&req->mux);
-out_free:
-	kmem_cache_free(ecryptfs_open_req_cache, req);
+	wait_for_completion(&req.done);
+	if (IS_ERR(*lower_file))
+		rc = PTR_ERR(*lower_file);
 out:
 	return rc;
 }

fs/ecryptfs/main.c

@@ -499,13 +499,12 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	s = sget(fs_type, NULL, set_anon_super, NULL);
+	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s)) {
 		rc = PTR_ERR(s);
 		goto out;
 	}
 
-	s->s_flags = flags;
 	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
 	if (rc)
 		goto out1;
@@ -682,11 +681,6 @@ static struct ecryptfs_cache_info {
 		.name = "ecryptfs_key_tfm_cache",
 		.size = sizeof(struct ecryptfs_key_tfm),
 	},
-	{
-		.cache = &ecryptfs_open_req_cache,
-		.name = "ecryptfs_open_req_cache",
-		.size = sizeof(struct ecryptfs_open_req),
-	},
 };
 
 static void ecryptfs_free_kmem_caches(void)

fs/efs/efs.h

@@ -129,7 +129,7 @@ extern struct inode *efs_iget(struct super_block *, unsigned long);
 extern efs_block_t efs_map_block(struct inode *, efs_block_t);
 extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int);
 
-extern struct dentry *efs_lookup(struct inode *, struct dentry *, struct nameidata *);
+extern struct dentry *efs_lookup(struct inode *, struct dentry *, unsigned int);
 extern struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 		int fh_len, int fh_type);
 extern struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid,

fs/efs/namei.c

@@ -58,7 +58,8 @@ static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len)
 	return(0);
 }
 
-struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) {
+struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
 	efs_ino_t inodenum;
 	struct inode *inode = NULL;
 

fs/exofs/namei.c

@@ -46,7 +46,7 @@ static inline int exofs_add_nondir(struct dentry *dentry, struct inode *inode)
 }
 
 static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry,
-				   struct nameidata *nd)
+				   unsigned int flags)
 {
 	struct inode *inode;
 	ino_t ino;
@@ -60,7 +60,7 @@ static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry,
 }
 
 static int exofs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-			 struct nameidata *nd)
+			 bool excl)
 {
 	struct inode *inode = exofs_new_inode(dir, mode);
 	int err = PTR_ERR(inode);

fs/exportfs/expfs.c

@@ -19,19 +19,19 @@
 #define dprintk(fmt, args...) do{}while(0)
 
 
-static int get_name(struct vfsmount *mnt, struct dentry *dentry, char *name,
-		struct dentry *child);
+static int get_name(const struct path *path, char *name, struct dentry *child);
 
 
 static int exportfs_get_name(struct vfsmount *mnt, struct dentry *dir,
 		char *name, struct dentry *child)
 {
 	const struct export_operations *nop = dir->d_sb->s_export_op;
+	struct path path = {.mnt = mnt, .dentry = dir};
 
 	if (nop->get_name)
 		return nop->get_name(dir, name, child);
 	else
-		return get_name(mnt, dir, name, child);
+		return get_name(&path, name, child);
 }
 
 /*
@@ -44,13 +44,14 @@ find_acceptable_alias(struct dentry *result,
 {
 	struct dentry *dentry, *toput = NULL;
 	struct inode *inode;
+	struct hlist_node *p;
 
 	if (acceptable(context, result))
 		return result;
 
 	inode = result->d_inode;
 	spin_lock(&inode->i_lock);
-	list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+	hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
 		dget(dentry);
 		spin_unlock(&inode->i_lock);
 		if (toput)
@@ -248,11 +249,10 @@ static int filldir_one(void * __buf, const char * name, int len,
  * calls readdir on the parent until it finds an entry with
  * the same inode number as the child, and returns that.
  */
-static int get_name(struct vfsmount *mnt, struct dentry *dentry,
-		char *name, struct dentry *child)
+static int get_name(const struct path *path, char *name, struct dentry *child)
 {
 	const struct cred *cred = current_cred();
-	struct inode *dir = dentry->d_inode;
+	struct inode *dir = path->dentry->d_inode;
 	int error;
 	struct file *file;
 	struct getdents_callback buffer;
@@ -266,7 +266,7 @@ static int get_name(struct vfsmount *mnt, struct dentry *dentry,
 	/*
 	 * Open the directory ...
 	 */
-	file = dentry_open(dget(dentry), mntget(mnt), O_RDONLY, cred);
+	file = dentry_open(path, O_RDONLY, cred);
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out;

fs/ext2/namei.c

@@ -41,8 +41,8 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 {
 	int err = ext2_add_link(dentry, inode);
 	if (!err) {
-		d_instantiate(dentry, inode);
 		unlock_new_inode(inode);
+		d_instantiate(dentry, inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
@@ -55,7 +55,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
  * Methods themselves.
  */
 
-static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
 {
 	struct inode * inode;
 	ino_t ino;
@@ -94,7 +94,7 @@ struct dentry *ext2_get_parent(struct dentry *child)
  * If the create succeeds, we fill in the inode information
  * with d_instantiate(). 
  */
-static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, struct nameidata *nd)
+static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl)
 {
 	struct inode *inode;
 
@@ -242,8 +242,8 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 	if (err)
 		goto out_fail;
 
-	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	d_instantiate(dentry, inode);
 out:
 	return err;
 

fs/ext2/super.c

@@ -1184,6 +1184,12 @@ static int ext2_sync_fs(struct super_block *sb, int wait)
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 	struct ext2_super_block *es = EXT2_SB(sb)->s_es;
 
+	/*
+	 * Write quota structures to quota file, sync_blockdev() will write
+	 * them to disk later
+	 */
+	dquot_writeback_dquots(sb, -1);
+
 	spin_lock(&sbi->s_lock);
 	if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) {
 		ext2_debug("setting valid to 0\n");

fs/ext3/dir.c

@@ -300,10 +300,11 @@ loff_t ext3_dir_llseek(struct file *file, loff_t offset, int origin)
 {
 	struct inode *inode = file->f_mapping->host;
 	int dx_dir = is_dx_dir(inode);
+	loff_t htree_max = ext3_get_htree_eof(file);
 
 	if (likely(dx_dir))
 		return generic_file_llseek_size(file, offset, origin,
-					        ext3_get_htree_eof(file));
+					        htree_max, htree_max);
 	else
 		return generic_file_llseek(file, offset, origin);
 }

fs/ext3/namei.c

@@ -1011,7 +1011,7 @@ errout:
 	return NULL;
 }
 
-static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
 {
 	struct inode * inode;
 	struct ext3_dir_entry_2 * de;
@@ -1671,8 +1671,8 @@ static int ext3_add_nondir(handle_t *handle,
 	int err = ext3_add_entry(handle, dentry, inode);
 	if (!err) {
 		ext3_mark_inode_dirty(handle, inode);
-		d_instantiate(dentry, inode);
 		unlock_new_inode(inode);
+		d_instantiate(dentry, inode);
 		return 0;
 	}
 	drop_nlink(inode);
@@ -1690,7 +1690,7 @@ static int ext3_add_nondir(handle_t *handle,
  * with d_instantiate().
  */
 static int ext3_create (struct inode * dir, struct dentry * dentry, umode_t mode,
-		struct nameidata *nd)
+		bool excl)
 {
 	handle_t *handle;
 	struct inode * inode;
@@ -1836,8 +1836,8 @@ out_clear_inode:
 	if (err)
 		goto out_clear_inode;
 
-	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	d_instantiate(dentry, inode);
 out_stop:
 	brelse(dir_block);
 	ext3_journal_stop(handle);

fs/ext3/super.c

@@ -2526,6 +2526,11 @@ static int ext3_sync_fs(struct super_block *sb, int wait)
 	tid_t target;
 
 	trace_ext3_sync_fs(sb, wait);
+	/*
+	 * Writeback quota in non-journalled quota case - journalled quota has
+	 * no dirty dquots
+	 */
+	dquot_writeback_dquots(sb, -1);
 	if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) {
 		if (wait)
 			log_wait_commit(EXT3_SB(sb)->s_journal, target);

fs/ext4/dir.c

@@ -324,74 +324,27 @@ static inline loff_t ext4_get_htree_eof(struct file *filp)
 
 
 /*
- * ext4_dir_llseek() based on generic_file_llseek() to handle both
- * non-htree and htree directories, where the "offset" is in terms
- * of the filename hash value instead of the byte offset.
+ * ext4_dir_llseek() calls generic_file_llseek_size to handle htree
+ * directories, where the "offset" is in terms of the filename hash
+ * value instead of the byte offset.
  *
- * NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX)
- *       will be invalid once the directory was converted into a dx directory
+ * Because we may return a 64-bit hash that is well beyond offset limits,
+ * we need to pass the max hash as the maximum allowable offset in
+ * the htree directory case.
+ *
+ * For non-htree, ext4_llseek already chooses the proper max offset.
  */
 loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin)
 {
 	struct inode *inode = file->f_mapping->host;
-	loff_t ret = -EINVAL;
 	int dx_dir = is_dx_dir(inode);
+	loff_t htree_max = ext4_get_htree_eof(file);
 
-	mutex_lock(&inode->i_mutex);
-
-	/* NOTE: relative offsets with dx directories might not work
-	 *       as expected, as it is difficult to figure out the
-	 *       correct offset between dx hashes */
-
-	switch (origin) {
-	case SEEK_END:
-		if (unlikely(offset > 0))
-			goto out_err; /* not supported for directories */
-
-		/* so only negative offsets are left, does that have a
-		 * meaning for directories at all? */
-		if (dx_dir)
-			offset += ext4_get_htree_eof(file);
-		else
-			offset += inode->i_size;
-		break;
-	case SEEK_CUR:
-		/*
-		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
-		 * position-querying operation.  Avoid rewriting the "same"
-		 * f_pos value back to the file because a concurrent read(),
-		 * write() or lseek() might have altered it
-		 */
-		if (offset == 0) {
-			offset = file->f_pos;
-			goto out_ok;
-		}
-
-		offset += file->f_pos;
-		break;
-	}
-
-	if (unlikely(offset < 0))
-		goto out_err;
-
-	if (!dx_dir) {
-		if (offset > inode->i_sb->s_maxbytes)
-			goto out_err;
-	} else if (offset > ext4_get_htree_eof(file))
-		goto out_err;
-
-	/* Special lock needed here? */
-	if (offset != file->f_pos) {
-		file->f_pos = offset;
-		file->f_version = 0;
-	}
-
-out_ok:
-	ret = offset;
-out_err:
-	mutex_unlock(&inode->i_mutex);
-
-	return ret;
+	if (likely(dx_dir))
+		return generic_file_llseek_size(file, offset, origin,
+						    htree_max, htree_max);
+	else
+		return ext4_llseek(file, offset, origin);
 }
 
 /*

fs/ext4/file.c

@@ -211,9 +211,9 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 }
 
 /*
- * ext4_llseek() copied from generic_file_llseek() to handle both
- * block-mapped and extent-mapped maxbytes values. This should
- * otherwise be identical with generic_file_llseek().
+ * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
+ * by calling generic_file_llseek_size() with the appropriate maxbytes
+ * value for each.
  */
 loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
 {
@@ -225,7 +225,8 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
 	else
 		maxbytes = inode->i_sb->s_maxbytes;
 
-	return generic_file_llseek_size(file, offset, origin, maxbytes);
+	return generic_file_llseek_size(file, offset, origin,
+					maxbytes, i_size_read(inode));
 }
 
 const struct file_operations ext4_file_operations = {

fs/ext4/fsync.c

@@ -135,14 +135,7 @@ static int ext4_sync_parent(struct inode *inode)
 	inode = igrab(inode);
 	while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
 		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
-		dentry = NULL;
-		spin_lock(&inode->i_lock);
-		if (!list_empty(&inode->i_dentry)) {
-			dentry = list_first_entry(&inode->i_dentry,
-						  struct dentry, d_alias);
-			dget(dentry);
-		}
-		spin_unlock(&inode->i_lock);
+		dentry = d_find_any_alias(inode);
 		if (!dentry)
 			break;
 		next = igrab(dentry->d_parent->d_inode);
@@ -232,7 +225,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	if (!journal) {
 		ret = __sync_inode(inode, datasync);
-		if (!ret && !list_empty(&inode->i_dentry))
+		if (!ret && !hlist_empty(&inode->i_dentry))
 			ret = ext4_sync_parent(inode);
 		goto out;
 	}

fs/ext4/ioctl.c

@@ -389,7 +389,7 @@ group_add_out:
 		if (err)
 			return err;
 
-		err = mnt_want_write(filp->f_path.mnt);
+		err = mnt_want_write_file(filp);
 		if (err)
 			goto resizefs_out;
 
@@ -401,7 +401,7 @@ group_add_out:
 		}
 		if (err == 0)
 			err = err2;
-		mnt_drop_write(filp->f_path.mnt);
+		mnt_drop_write_file(filp);
 resizefs_out:
 		ext4_resize_end(sb);
 		return err;

fs/ext4/namei.c

@@ -1312,7 +1312,7 @@ errout:
 	return NULL;
 }
 
-static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	struct ext4_dir_entry_2 *de;
@@ -2072,8 +2072,8 @@ static int ext4_add_nondir(handle_t *handle,
 	int err = ext4_add_entry(handle, dentry, inode);
 	if (!err) {
 		ext4_mark_inode_dirty(handle, inode);
-		d_instantiate(dentry, inode);
 		unlock_new_inode(inode);
+		d_instantiate(dentry, inode);
 		return 0;
 	}
 	drop_nlink(inode);
@@ -2091,7 +2091,7 @@ static int ext4_add_nondir(handle_t *handle,
  * with d_instantiate().
  */
 static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-		       struct nameidata *nd)
+		       bool excl)
 {
 	handle_t *handle;
 	struct inode *inode;
@@ -2249,8 +2249,8 @@ out_clear_inode:
 	err = ext4_mark_inode_dirty(handle, dir);
 	if (err)
 		goto out_clear_inode;
-	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	d_instantiate(dentry, inode);
 out_stop:
 	brelse(dir_block);
 	ext4_journal_stop(handle);

fs/ext4/super.c

@@ -4325,6 +4325,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 
 	trace_ext4_sync_fs(sb, wait);
 	flush_workqueue(sbi->dio_unwritten_wq);
+	/*
+	 * Writeback quota in non-journalled quota case - journalled quota has
+	 * no dirty dquots
+	 */
+	dquot_writeback_dquots(sb, -1);
 	if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
 		if (wait)
 			jbd2_log_wait_commit(sbi->s_journal, target);

fs/fat/namei_msdos.c

@@ -201,7 +201,7 @@ static const struct dentry_operations msdos_dentry_operations = {
 
 /***** Get inode using directory and name */
 static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
-				   struct nameidata *nd)
+				   unsigned int flags)
 {
 	struct super_block *sb = dir->i_sb;
 	struct fat_slot_info sinfo;
@@ -265,7 +265,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name,
 
 /***** Create a file */
 static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-			struct nameidata *nd)
+			bool excl)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = NULL;

fs/fat/namei_vfat.c

@@ -41,9 +41,9 @@ static int vfat_revalidate_shortname(struct dentry *dentry)
 	return ret;
 }
 
-static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int vfat_revalidate(struct dentry *dentry, unsigned int flags)
 {
-	if (nd && nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	/* This is not negative dentry. Always valid. */
@@ -52,9 +52,9 @@ static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd)
 	return vfat_revalidate_shortname(dentry);
 }
 
-static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd)
+static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags)
 {
-	if (nd && nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	/*
@@ -74,7 +74,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd)
 	 * This may be nfsd (or something), anyway, we can't see the
 	 * intent of this. So, since this can be for creation, drop it.
 	 */
-	if (!nd)
+	if (!flags)
 		return 0;
 
 	/*
@@ -82,7 +82,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd)
 	 * case sensitive name which is specified by user if this is
 	 * for creation.
 	 */
-	if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+	if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
 		return 0;
 
 	return vfat_revalidate_shortname(dentry);
@@ -714,7 +714,7 @@ static int vfat_d_anon_disconn(struct dentry *dentry)
 }
 
 static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
-				  struct nameidata *nd)
+				  unsigned int flags)
 {
 	struct super_block *sb = dir->i_sb;
 	struct fat_slot_info sinfo;
@@ -772,7 +772,7 @@ error:
 }
 
 static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-		       struct nameidata *nd)
+		       bool excl)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode;

fs/file_table.c

@@ -23,6 +23,8 @@
 #include <linux/lglock.h>
 #include <linux/percpu_counter.h>
 #include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/task_work.h>
 #include <linux/ima.h>
 
 #include <linux/atomic.h>
@@ -251,7 +253,6 @@ static void __fput(struct file *file)
 	}
 	fops_put(file->f_op);
 	put_pid(file->f_owner.pid);
-	file_sb_list_del(file);
 	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_dec(inode);
 	if (file->f_mode & FMODE_WRITE)
@@ -263,10 +264,77 @@ static void __fput(struct file *file)
 	mntput(mnt);
 }
 
+static DEFINE_SPINLOCK(delayed_fput_lock);
+static LIST_HEAD(delayed_fput_list);
+static void delayed_fput(struct work_struct *unused)
+{
+	LIST_HEAD(head);
+	spin_lock_irq(&delayed_fput_lock);
+	list_splice_init(&delayed_fput_list, &head);
+	spin_unlock_irq(&delayed_fput_lock);
+	while (!list_empty(&head)) {
+		struct file *f = list_first_entry(&head, struct file, f_u.fu_list);
+		list_del_init(&f->f_u.fu_list);
+		__fput(f);
+	}
+}
+
+static void ____fput(struct callback_head *work)
+{
+	__fput(container_of(work, struct file, f_u.fu_rcuhead));
+}
+
+/*
+ * If kernel thread really needs to have the final fput() it has done
+ * to complete, call this.  The only user right now is the boot - we
+ * *do* need to make sure our writes to binaries on initramfs has
+ * not left us with opened struct file waiting for __fput() - execve()
+ * won't work without that.  Please, don't add more callers without
+ * very good reasons; in particular, never call that with locks
+ * held and never call that from a thread that might need to do
+ * some work on any kind of umount.
+ */
+void flush_delayed_fput(void)
+{
+	delayed_fput(NULL);
+}
+
+static DECLARE_WORK(delayed_fput_work, delayed_fput);
+
 void fput(struct file *file)
 {
-	if (atomic_long_dec_and_test(&file->f_count))
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		struct task_struct *task = current;
+		file_sb_list_del(file);
+		if (unlikely(in_interrupt() || task->flags & PF_KTHREAD)) {
+			unsigned long flags;
+			spin_lock_irqsave(&delayed_fput_lock, flags);
+			list_add(&file->f_u.fu_list, &delayed_fput_list);
+			schedule_work(&delayed_fput_work);
+			spin_unlock_irqrestore(&delayed_fput_lock, flags);
+			return;
+		}
+		init_task_work(&file->f_u.fu_rcuhead, ____fput);
+		task_work_add(task, &file->f_u.fu_rcuhead, true);
+	}
+}
+
+/*
+ * synchronous analog of fput(); for kernel threads that might be needed
+ * in some umount() (and thus can't use flush_delayed_fput() without
+ * risking deadlocks), need to wait for completion of __fput() and know
+ * for this specific struct file it won't involve anything that would
+ * need them.  Use only if you really need it - at the very least,
+ * don't blindly convert fput() by kernel thread to that.
+ */
+void __fput_sync(struct file *file)
+{
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		struct task_struct *task = current;
+		file_sb_list_del(file);
+		BUG_ON(!(task->flags & PF_KTHREAD));
 		__fput(file);
+	}
 }
 
 EXPORT_SYMBOL(fput);
@@ -483,10 +551,8 @@ void mark_files_ro(struct super_block *sb)
 {
 	struct file *f;
 
-retry:
 	lg_global_lock(&files_lglock);
 	do_file_list_for_each_entry(sb, f) {
-		struct vfsmount *mnt;
 		if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
 		       continue;
 		if (!file_count(f))
@@ -499,12 +565,7 @@ retry:
 		if (file_check_writeable(f) != 0)
 			continue;
 		file_release_write(f);
-		mnt = mntget(f->f_path.mnt);
-		/* This can sleep, so we can't hold the spinlock. */
-		lg_global_unlock(&files_lglock);
-		mnt_drop_write(mnt);
-		mntput(mnt);
-		goto retry;
+		mnt_drop_write_file(f);
 	} while_file_list_for_each_entry;
 	lg_global_unlock(&files_lglock);
 }

fs/freevxfs/vxfs_lookup.c

@@ -48,7 +48,7 @@
 #define VXFS_BLOCK_PER_PAGE(sbp)  ((PAGE_CACHE_SIZE / (sbp)->s_blocksize))
 
 
-static struct dentry *	vxfs_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry *	vxfs_lookup(struct inode *, struct dentry *, unsigned int);
 static int		vxfs_readdir(struct file *, void *, filldir_t);
 
 const struct inode_operations vxfs_dir_inode_ops = {
@@ -203,7 +203,7 @@ vxfs_inode_by_name(struct inode *dip, struct dentry *dp)
  *   in the return pointer.
  */
 static struct dentry *
-vxfs_lookup(struct inode *dip, struct dentry *dp, struct nameidata *nd)
+vxfs_lookup(struct inode *dip, struct dentry *dp, unsigned int flags)
 {
 	struct inode		*ip = NULL;
 	ino_t			ino;

fs/fs-writeback.c

@@ -1315,6 +1315,8 @@ void writeback_inodes_sb_nr(struct super_block *sb,
 		.reason			= reason,
 	};
 
+	if (sb->s_bdi == &noop_backing_dev_info)
+		return;
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 	bdi_queue_work(sb->s_bdi, &work);
 	wait_for_completion(&done);
@@ -1398,6 +1400,9 @@ void sync_inodes_sb(struct super_block *sb)
 		.reason		= WB_REASON_SYNC,
 	};
 
+	/* Nothing to do? */
+	if (sb->s_bdi == &noop_backing_dev_info)
+		return;
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
 	bdi_queue_work(sb->s_bdi, &work);

fs/fs_struct.c

@@ -6,18 +6,6 @@
 #include <linux/fs_struct.h>
 #include "internal.h"
 
-static inline void path_get_longterm(struct path *path)
-{
-	path_get(path);
-	mnt_make_longterm(path->mnt);
-}
-
-static inline void path_put_longterm(struct path *path)
-{
-	mnt_make_shortterm(path->mnt);
-	path_put(path);
-}
-
 /*
  * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
  * It can block.
@@ -26,7 +14,7 @@ void set_fs_root(struct fs_struct *fs, struct path *path)
 {
 	struct path old_root;
 
-	path_get_longterm(path);
+	path_get(path);
 	spin_lock(&fs->lock);
 	write_seqcount_begin(&fs->seq);
 	old_root = fs->root;
@@ -34,7 +22,7 @@ void set_fs_root(struct fs_struct *fs, struct path *path)
 	write_seqcount_end(&fs->seq);
 	spin_unlock(&fs->lock);
 	if (old_root.dentry)
-		path_put_longterm(&old_root);
+		path_put(&old_root);
 }
 
 /*
@@ -45,7 +33,7 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path)
 {
 	struct path old_pwd;
 
-	path_get_longterm(path);
+	path_get(path);
 	spin_lock(&fs->lock);
 	write_seqcount_begin(&fs->seq);
 	old_pwd = fs->pwd;
@@ -54,7 +42,7 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path)
 	spin_unlock(&fs->lock);
 
 	if (old_pwd.dentry)
-		path_put_longterm(&old_pwd);
+		path_put(&old_pwd);
 }
 
 static inline int replace_path(struct path *p, const struct path *old, const struct path *new)
@@ -84,7 +72,7 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 			write_seqcount_end(&fs->seq);
 			while (hits--) {
 				count++;
-				path_get_longterm(new_root);
+				path_get(new_root);
 			}
 			spin_unlock(&fs->lock);
 		}
@@ -92,13 +80,13 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
 	while (count--)
-		path_put_longterm(old_root);
+		path_put(old_root);
 }
 
 void free_fs_struct(struct fs_struct *fs)
 {
-	path_put_longterm(&fs->root);
-	path_put_longterm(&fs->pwd);
+	path_put(&fs->root);
+	path_put(&fs->pwd);
 	kmem_cache_free(fs_cachep, fs);
 }
 
@@ -132,9 +120,9 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
 
 		spin_lock(&old->lock);
 		fs->root = old->root;
-		path_get_longterm(&fs->root);
+		path_get(&fs->root);
 		fs->pwd = old->pwd;
-		path_get_longterm(&fs->pwd);
+		path_get(&fs->pwd);
 		spin_unlock(&old->lock);
 	}
 	return fs;

fs/fuse/dir.c

@@ -154,7 +154,7 @@ u64 fuse_get_attr_version(struct fuse_conn *fc)
  * the lookup once more.  If the lookup results in the same inode,
  * then refresh the attributes, timeouts and mark the dentry valid.
  */
-static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
+static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
 {
 	struct inode *inode;
 
@@ -174,7 +174,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
 		if (!inode)
 			return 0;
 
-		if (nd && (nd->flags & LOOKUP_RCU))
+		if (flags & LOOKUP_RCU)
 			return -ECHILD;
 
 		fc = get_fuse_conn(inode);
@@ -249,7 +249,7 @@ static struct dentry *fuse_d_add_directory(struct dentry *entry,
 		/* This tries to shrink the subtree below alias */
 		fuse_invalidate_entry(alias);
 		dput(alias);
-		if (!list_empty(&inode->i_dentry))
+		if (!hlist_empty(&inode->i_dentry))
 			return ERR_PTR(-EBUSY);
 	} else {
 		dput(alias);
@@ -316,7 +316,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
 }
 
 static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
-				  struct nameidata *nd)
+				  unsigned int flags)
 {
 	int err;
 	struct fuse_entry_out outarg;
@@ -370,7 +370,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
  * 'mknod' + 'open' requests.
  */
 static int fuse_create_open(struct inode *dir, struct dentry *entry,
-			    umode_t mode, struct nameidata *nd)
+			    struct file *file, unsigned flags,
+			    umode_t mode, int *opened)
 {
 	int err;
 	struct inode *inode;
@@ -381,15 +382,11 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	struct fuse_open_out outopen;
 	struct fuse_entry_out outentry;
 	struct fuse_file *ff;
-	struct file *file;
-	int flags = nd->intent.open.flags;
-
-	if (fc->no_create)
-		return -ENOSYS;
 
 	forget = fuse_alloc_forget();
+	err = -ENOMEM;
 	if (!forget)
-		return -ENOMEM;
+		goto out_err;
 
 	req = fuse_get_req(fc);
 	err = PTR_ERR(req);
@@ -428,11 +425,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	req->out.args[1].value = &outopen;
 	fuse_request_send(fc, req);
 	err = req->out.h.error;
-	if (err) {
-		if (err == -ENOSYS)
-			fc->no_create = 1;
+	if (err)
 		goto out_free_ff;
-	}
 
 	err = -EIO;
 	if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid))
@@ -448,28 +442,74 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 		flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
 		fuse_sync_release(ff, flags);
 		fuse_queue_forget(fc, forget, outentry.nodeid, 1);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto out_err;
 	}
 	kfree(forget);
 	d_instantiate(entry, inode);
 	fuse_change_entry_timeout(entry, &outentry);
 	fuse_invalidate_attr(dir);
-	file = lookup_instantiate_filp(nd, entry, generic_file_open);
-	if (IS_ERR(file)) {
+	err = finish_open(file, entry, generic_file_open, opened);
+	if (err) {
 		fuse_sync_release(ff, flags);
-		return PTR_ERR(file);
+	} else {
+		file->private_data = fuse_file_get(ff);
+		fuse_finish_open(inode, file);
 	}
-	file->private_data = fuse_file_get(ff);
-	fuse_finish_open(inode, file);
-	return 0;
+	return err;
 
- out_free_ff:
+out_free_ff:
 	fuse_file_free(ff);
- out_put_request:
+out_put_request:
 	fuse_put_request(fc, req);
- out_put_forget_req:
+out_put_forget_req:
 	kfree(forget);
+out_err:
+	return err;
+}
+
+static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
+static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
+			    struct file *file, unsigned flags,
+			    umode_t mode, int *opened)
+{
+	int err;
+	struct fuse_conn *fc = get_fuse_conn(dir);
+	struct dentry *res = NULL;
+
+	if (d_unhashed(entry)) {
+		res = fuse_lookup(dir, entry, 0);
+		if (IS_ERR(res))
+			return PTR_ERR(res);
+
+		if (res)
+			entry = res;
+	}
+
+	if (!(flags & O_CREAT) || entry->d_inode)
+		goto no_open;
+
+	/* Only creates */
+	*opened |= FILE_CREATED;
+
+	if (fc->no_create)
+		goto mknod;
+
+	err = fuse_create_open(dir, entry, file, flags, mode, opened);
+	if (err == -ENOSYS) {
+		fc->no_create = 1;
+		goto mknod;
+	}
+out_dput:
+	dput(res);
 	return err;
+
+mknod:
+	err = fuse_mknod(dir, entry, mode, 0);
+	if (err)
+		goto out_dput;
+no_open:
+	return finish_no_open(file, res);
 }
 
 /*
@@ -571,14 +611,8 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode,
 }
 
 static int fuse_create(struct inode *dir, struct dentry *entry, umode_t mode,
-		       struct nameidata *nd)
+		       bool excl)
 {
-	if (nd) {
-		int err = fuse_create_open(dir, entry, mode, nd);
-		if (err != -ENOSYS)
-			return err;
-		/* Fall back on mknod */
-	}
 	return fuse_mknod(dir, entry, mode, 0);
 }
 
@@ -1646,6 +1680,7 @@ static const struct inode_operations fuse_dir_inode_operations = {
 	.link		= fuse_link,
 	.setattr	= fuse_setattr,
 	.create		= fuse_create,
+	.atomic_open	= fuse_atomic_open,
 	.mknod		= fuse_mknod,
 	.permission	= fuse_permission,
 	.getattr	= fuse_getattr,

fs/gfs2/dentry.c

@@ -25,7 +25,7 @@
 /**
  * gfs2_drevalidate - Check directory lookup consistency
  * @dentry: the mapping to check
- * @nd:
+ * @flags: lookup flags
  *
  * Check to make sure the lookup necessary to arrive at this inode from its
  * parent is still good.
@@ -33,7 +33,7 @@
  * Returns: 1 if the dentry is ok, 0 if it isn't
  */
 
-static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
+static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *parent;
 	struct gfs2_sbd *sdp;
@@ -44,7 +44,7 @@ static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
 	int error;
 	int had_lock = 0;
 
-	if (nd && nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	parent = dget_parent(dentry);

fs/gfs2/inode.c

@@ -755,11 +755,8 @@ fail:
  */
 
 static int gfs2_create(struct inode *dir, struct dentry *dentry,
-		       umode_t mode, struct nameidata *nd)
+		       umode_t mode, bool excl)
 {
-	int excl = 0;
-	if (nd && (nd->flags & LOOKUP_EXCL))
-		excl = 1;
 	return gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
@@ -775,7 +772,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
  */
 
 static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
-				  struct nameidata *nd)
+				  unsigned int flags)
 {
 	struct inode *inode = gfs2_lookupi(dir, &dentry->d_name, 0);
 	if (inode && !IS_ERR(inode)) {

fs/gfs2/ops_fstype.c

@@ -1286,7 +1286,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 		error = -EBUSY;
 		goto error_bdev;
 	}
-	s = sget(fs_type, test_gfs2_super, set_gfs2_super, bdev);
+	s = sget(fs_type, test_gfs2_super, set_gfs2_super, flags, bdev);
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	error = PTR_ERR(s);
 	if (IS_ERR(s))
@@ -1316,7 +1316,6 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 	} else {
 		char b[BDEVNAME_SIZE];
 
-		s->s_flags = flags;
 		s->s_mode = mode;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
 		sb_set_blocksize(s, block_size(bdev));
@@ -1360,7 +1359,7 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type,
 		       dev_name, error);
 		return ERR_PTR(error);
 	}
-	s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super,
+	s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, flags,
 		 path.dentry->d_inode->i_sb->s_bdev);
 	path_put(&path);
 	if (IS_ERR(s)) {

fs/gfs2/quota.c

@@ -1108,7 +1108,7 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
 	}
 }
 
-int gfs2_quota_sync(struct super_block *sb, int type, int wait)
+int gfs2_quota_sync(struct super_block *sb, int type)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_quota_data **qda;
@@ -1154,7 +1154,7 @@ int gfs2_quota_sync(struct super_block *sb, int type, int wait)
 
 static int gfs2_quota_sync_timeo(struct super_block *sb, int type)
 {
-	return gfs2_quota_sync(sb, type, 0);
+	return gfs2_quota_sync(sb, type);
 }
 
 int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id)

fs/gfs2/quota.h

@@ -26,7 +26,7 @@ extern int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid);
 extern void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
 			      u32 uid, u32 gid);
 
-extern int gfs2_quota_sync(struct super_block *sb, int type, int wait);
+extern int gfs2_quota_sync(struct super_block *sb, int type);
 extern int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id);
 
 extern int gfs2_quota_init(struct gfs2_sbd *sdp);

fs/gfs2/super.c

@@ -838,7 +838,7 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 	int error;
 
 	flush_workqueue(gfs2_delete_workqueue);
-	gfs2_quota_sync(sdp->sd_vfs, 0, 1);
+	gfs2_quota_sync(sdp->sd_vfs, 0);
 	gfs2_statfs_sync(sdp->sd_vfs, 0);
 
 	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
@@ -952,6 +952,8 @@ restart:
 static int gfs2_sync_fs(struct super_block *sb, int wait)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
+
+	gfs2_quota_sync(sb, -1);
 	if (wait && sdp)
 		gfs2_log_flush(sdp, NULL);
 	return 0;

fs/gfs2/sys.c

@@ -168,7 +168,7 @@ static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf,
 	if (simple_strtol(buf, NULL, 0) != 1)
 		return -EINVAL;
 
-	gfs2_quota_sync(sdp->sd_vfs, 0, 1);
+	gfs2_quota_sync(sdp->sd_vfs, 0);
 	return len;
 }
 

fs/hfs/dir.c

@@ -18,7 +18,7 @@
  * hfs_lookup()
  */
 static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry,
-				 struct nameidata *nd)
+				 unsigned int flags)
 {
 	hfs_cat_rec rec;
 	struct hfs_find_data fd;
@@ -187,7 +187,7 @@ static int hfs_dir_release(struct inode *inode, struct file *file)
  * the directory and the name (and its length) of the new file.
  */
 static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-		      struct nameidata *nd)
+		      bool excl)
 {
 	struct inode *inode;
 	int res;

fs/hfs/extent.c

@@ -432,7 +432,7 @@ out:
 		if (inode->i_ino < HFS_FIRSTUSER_CNID)
 			set_bit(HFS_FLG_ALT_MDB_DIRTY, &HFS_SB(sb)->flags);
 		set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags);
-		sb->s_dirt = 1;
+		hfs_mark_mdb_dirty(sb);
 	}
 	return res;
 

fs/hfs/hfs_fs.h

@@ -14,6 +14,7 @@
 #include <linux/mutex.h>
 #include <linux/buffer_head.h>
 #include <linux/fs.h>
+#include <linux/workqueue.h>
 
 #include <asm/byteorder.h>
 #include <asm/uaccess.h>
@@ -137,16 +138,15 @@ struct hfs_sb_info {
 	gid_t s_gid;				/* The gid of all files */
 
 	int session, part;
-
 	struct nls_table *nls_io, *nls_disk;
-
 	struct mutex bitmap_lock;
-
 	unsigned long flags;
-
 	u16 blockoffset;
-
 	int fs_div;
+	struct super_block *sb;
+	int work_queued;		/* non-zero delayed work is queued */
+	struct delayed_work mdb_work;	/* MDB flush delayed work */
+	spinlock_t work_lock;		/* protects mdb_work and work_queued */
 };
 
 #define HFS_FLG_BITMAP_DIRTY	0
@@ -226,6 +226,9 @@ extern int hfs_compare_dentry(const struct dentry *parent,
 extern void hfs_asc2mac(struct super_block *, struct hfs_name *, struct qstr *);
 extern int hfs_mac2asc(struct super_block *, char *, const struct hfs_name *);
 
+/* super.c */
+extern void hfs_mark_mdb_dirty(struct super_block *sb);
+
 extern struct timezone sys_tz;
 
 /*
@@ -253,7 +256,7 @@ static inline const char *hfs_mdb_name(struct super_block *sb)
 static inline void hfs_bitmap_dirty(struct super_block *sb)
 {
 	set_bit(HFS_FLG_BITMAP_DIRTY, &HFS_SB(sb)->flags);
-	sb->s_dirt = 1;
+	hfs_mark_mdb_dirty(sb);
 }
 
 #define sb_bread512(sb, sec, data) ({			\

fs/hfs/inode.c

@@ -220,7 +220,7 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, umode_t mode)
 	insert_inode_hash(inode);
 	mark_inode_dirty(inode);
 	set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags);
-	sb->s_dirt = 1;
+	hfs_mark_mdb_dirty(sb);
 
 	return inode;
 }
@@ -235,7 +235,7 @@ void hfs_delete_inode(struct inode *inode)
 		if (HFS_I(inode)->cat_key.ParID == cpu_to_be32(HFS_ROOT_CNID))
 			HFS_SB(sb)->root_dirs--;
 		set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags);
-		sb->s_dirt = 1;
+		hfs_mark_mdb_dirty(sb);
 		return;
 	}
 	HFS_SB(sb)->file_count--;
@@ -248,7 +248,7 @@ void hfs_delete_inode(struct inode *inode)
 		}
 	}
 	set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags);
-	sb->s_dirt = 1;
+	hfs_mark_mdb_dirty(sb);
 }
 
 void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext,
@@ -489,7 +489,7 @@ out:
 }
 
 static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
-				      struct nameidata *nd)
+				      unsigned int flags)
 {
 	struct inode *inode = NULL;
 	hfs_cat_rec rec;
@@ -644,13 +644,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 
 	/* sync the superblock to buffers */
 	sb = inode->i_sb;
-	if (sb->s_dirt) {
-		lock_super(sb);
-		sb->s_dirt = 0;
-		if (!(sb->s_flags & MS_RDONLY))
-			hfs_mdb_commit(sb);
-		unlock_super(sb);
-	}
+	flush_delayed_work_sync(&HFS_SB(sb)->mdb_work);
 	/* .. finally sync the buffers to disk */
 	err = sync_blockdev(sb->s_bdev);
 	if (!ret)

fs/hfs/mdb.c

@@ -260,6 +260,10 @@ void hfs_mdb_commit(struct super_block *sb)
 {
 	struct hfs_mdb *mdb = HFS_SB(sb)->mdb;
 
+	if (sb->s_flags & MS_RDONLY)
+		return;
+
+	lock_buffer(HFS_SB(sb)->mdb_bh);
 	if (test_and_clear_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags)) {
 		/* These parameters may have been modified, so write them back */
 		mdb->drLsMod = hfs_mtime();
@@ -283,9 +287,13 @@ void hfs_mdb_commit(struct super_block *sb)
 				     &mdb->drXTFlSize, NULL);
 		hfs_inode_write_fork(HFS_SB(sb)->cat_tree->inode, mdb->drCTExtRec,
 				     &mdb->drCTFlSize, NULL);
+
+		lock_buffer(HFS_SB(sb)->alt_mdb_bh);
 		memcpy(HFS_SB(sb)->alt_mdb, HFS_SB(sb)->mdb, HFS_SECTOR_SIZE);
 		HFS_SB(sb)->alt_mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT);
 		HFS_SB(sb)->alt_mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT);
+		unlock_buffer(HFS_SB(sb)->alt_mdb_bh);
+
 		mark_buffer_dirty(HFS_SB(sb)->alt_mdb_bh);
 		sync_dirty_buffer(HFS_SB(sb)->alt_mdb_bh);
 	}
@@ -308,7 +316,11 @@ void hfs_mdb_commit(struct super_block *sb)
 				break;
 			}
 			len = min((int)sb->s_blocksize - off, size);
+
+			lock_buffer(bh);
 			memcpy(bh->b_data + off, ptr, len);
+			unlock_buffer(bh);
+
 			mark_buffer_dirty(bh);
 			brelse(bh);
 			block++;
@@ -317,6 +329,7 @@ void hfs_mdb_commit(struct super_block *sb)
 			size -= len;
 		}
 	}
+	unlock_buffer(HFS_SB(sb)->mdb_bh);
 }
 
 void hfs_mdb_close(struct super_block *sb)

fs/hfs/super.c

@@ -29,43 +29,9 @@ static struct kmem_cache *hfs_inode_cachep;
 
 MODULE_LICENSE("GPL");
 
-/*
- * hfs_write_super()
- *
- * Description:
- *   This function is called by the VFS only. When the filesystem
- *   is mounted r/w it updates the MDB on disk.
- * Input Variable(s):
- *   struct super_block *sb: Pointer to the hfs superblock
- * Output Variable(s):
- *   NONE
- * Returns:
- *   void
- * Preconditions:
- *   'sb' points to a "valid" (struct super_block).
- * Postconditions:
- *   The MDB is marked 'unsuccessfully unmounted' by clearing bit 8 of drAtrb
- *   (hfs_put_super() must set this flag!). Some MDB fields are updated
- *   and the MDB buffer is written to disk by calling hfs_mdb_commit().
- */
-static void hfs_write_super(struct super_block *sb)
-{
-	lock_super(sb);
-	sb->s_dirt = 0;
-
-	/* sync everything to the buffers */
-	if (!(sb->s_flags & MS_RDONLY))
-		hfs_mdb_commit(sb);
-	unlock_super(sb);
-}
-
 static int hfs_sync_fs(struct super_block *sb, int wait)
 {
-	lock_super(sb);
 	hfs_mdb_commit(sb);
-	sb->s_dirt = 0;
-	unlock_super(sb);
-
 	return 0;
 }
 
@@ -78,13 +44,44 @@ static int hfs_sync_fs(struct super_block *sb, int wait)
  */
 static void hfs_put_super(struct super_block *sb)
 {
-	if (sb->s_dirt)
-		hfs_write_super(sb);
+	cancel_delayed_work_sync(&HFS_SB(sb)->mdb_work);
 	hfs_mdb_close(sb);
 	/* release the MDB's resources */
 	hfs_mdb_put(sb);
 }
 
+static void flush_mdb(struct work_struct *work)
+{
+	struct hfs_sb_info *sbi;
+	struct super_block *sb;
+
+	sbi = container_of(work, struct hfs_sb_info, mdb_work.work);
+	sb = sbi->sb;
+
+	spin_lock(&sbi->work_lock);
+	sbi->work_queued = 0;
+	spin_unlock(&sbi->work_lock);
+
+	hfs_mdb_commit(sb);
+}
+
+void hfs_mark_mdb_dirty(struct super_block *sb)
+{
+	struct hfs_sb_info *sbi = HFS_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->mdb_work, delay);
+		sbi->work_queued = 1;
+	}
+	spin_unlock(&sbi->work_lock);
+}
+
 /*
  * hfs_statfs()
  *
@@ -184,7 +181,6 @@ static const struct super_operations hfs_super_operations = {
 	.write_inode	= hfs_write_inode,
 	.evict_inode	= hfs_evict_inode,
 	.put_super	= hfs_put_super,
-	.write_super	= hfs_write_super,
 	.sync_fs	= hfs_sync_fs,
 	.statfs		= hfs_statfs,
 	.remount_fs     = hfs_remount,
@@ -387,7 +383,10 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sbi)
 		return -ENOMEM;
 
+	sbi->sb = sb;
 	sb->s_fs_info = sbi;
+	spin_lock_init(&sbi->work_lock);
+	INIT_DELAYED_WORK(&sbi->mdb_work, flush_mdb);
 
 	res = -EINVAL;
 	if (!parse_options((char *)data, sbi)) {

fs/hfs/sysdep.c

@@ -13,12 +13,12 @@
 
 /* dentry case-handling: just lowercase everything */
 
-static int hfs_revalidate_dentry(struct dentry *dentry, struct nameidata *nd)
+static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	int diff;
 
-	if (nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	inode = dentry->d_inode;

fs/hfsplus/bitmap.c

@@ -153,7 +153,7 @@ done:
 	kunmap(page);
 	*max = offset + (curr - pptr) * 32 + i - start;
 	sbi->free_blocks -= *max;
-	sb->s_dirt = 1;
+	hfsplus_mark_mdb_dirty(sb);
 	dprint(DBG_BITMAP, "-> %u,%u\n", start, *max);
 out:
 	mutex_unlock(&sbi->alloc_mutex);
@@ -228,7 +228,7 @@ out:
 	set_page_dirty(page);
 	kunmap(page);
 	sbi->free_blocks += len;
-	sb->s_dirt = 1;
+	hfsplus_mark_mdb_dirty(sb);
 	mutex_unlock(&sbi->alloc_mutex);
 
 	return 0;

fs/hfsplus/dir.c

@@ -25,7 +25,7 @@ static inline void hfsplus_instantiate(struct dentry *dentry,
 
 /* Find the entry inside dir named dentry->d_name */
 static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
-				     struct nameidata *nd)
+				     unsigned int flags)
 {
 	struct inode *inode = NULL;
 	struct hfs_find_data fd;
@@ -316,7 +316,7 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
 	inode->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(inode);
 	sbi->file_count++;
-	dst_dir->i_sb->s_dirt = 1;
+	hfsplus_mark_mdb_dirty(dst_dir->i_sb);
 out:
 	mutex_unlock(&sbi->vh_mutex);
 	return res;
@@ -465,7 +465,7 @@ out:
 }
 
 static int hfsplus_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-			  struct nameidata *nd)
+			  bool excl)
 {
 	return hfsplus_mknod(dir, dentry, mode, 0);
 }

fs/hfsplus/hfsplus_fs.h

@@ -153,8 +153,11 @@ struct hfsplus_sb_info {
 	gid_t gid;
 
 	int part, session;
-
 	unsigned long flags;
+
+	int work_queued;               /* non-zero delayed work is queued */
+	struct delayed_work sync_work; /* FS sync delayed work */
+	spinlock_t work_lock;          /* protects sync_work and work_queued */
 };
 
 #define HFSPLUS_SB_WRITEBACKUP	0
@@ -428,7 +431,7 @@ int hfsplus_show_options(struct seq_file *, struct dentry *);
 
 /* super.c */
 struct inode *hfsplus_iget(struct super_block *, unsigned long);
-int hfsplus_sync_fs(struct super_block *sb, int wait);
+void hfsplus_mark_mdb_dirty(struct super_block *sb);
 
 /* tables.c */
 extern u16 hfsplus_case_fold_table[];

fs/hfsplus/inode.c

@@ -168,7 +168,7 @@ const struct dentry_operations hfsplus_dentry_operations = {
 };
 
 static struct dentry *hfsplus_file_lookup(struct inode *dir,
-		struct dentry *dentry, struct nameidata *nd)
+		struct dentry *dentry, unsigned int flags)
 {
 	struct hfs_find_data fd;
 	struct super_block *sb = dir->i_sb;
@@ -431,7 +431,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode)
 		sbi->file_count++;
 	insert_inode_hash(inode);
 	mark_inode_dirty(inode);
-	sb->s_dirt = 1;
+	hfsplus_mark_mdb_dirty(sb);
 
 	return inode;
 }
@@ -442,7 +442,7 @@ void hfsplus_delete_inode(struct inode *inode)
 
 	if (S_ISDIR(inode->i_mode)) {
 		HFSPLUS_SB(sb)->folder_count--;
-		sb->s_dirt = 1;
+		hfsplus_mark_mdb_dirty(sb);
 		return;
 	}
 	HFSPLUS_SB(sb)->file_count--;
@@ -455,7 +455,7 @@ void hfsplus_delete_inode(struct inode *inode)
 		inode->i_size = 0;
 		hfsplus_file_truncate(inode);
 	}
-	sb->s_dirt = 1;
+	hfsplus_mark_mdb_dirty(sb);
 }
 
 void hfsplus_inode_read_fork(struct inode *inode, struct hfsplus_fork_raw *fork)

fs/hfsplus/super.c

@@ -124,7 +124,7 @@ static int hfsplus_system_write_inode(struct inode *inode)
 
 	if (fork->total_size != cpu_to_be64(inode->i_size)) {
 		set_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags);
-		inode->i_sb->s_dirt = 1;
+		hfsplus_mark_mdb_dirty(inode->i_sb);
 	}
 	hfsplus_inode_write_fork(inode, fork);
 	if (tree)
@@ -161,7 +161,7 @@ static void hfsplus_evict_inode(struct inode *inode)
 	}
 }
 
-int hfsplus_sync_fs(struct super_block *sb, int wait)
+static int hfsplus_sync_fs(struct super_block *sb, int wait)
 {
 	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct hfsplus_vh *vhdr = sbi->s_vhdr;
@@ -171,9 +171,7 @@ int hfsplus_sync_fs(struct super_block *sb, int wait)
 	if (!wait)
 		return 0;
 
-	dprint(DBG_SUPER, "hfsplus_write_super\n");
-
-	sb->s_dirt = 0;
+	dprint(DBG_SUPER, "hfsplus_sync_fs\n");
 
 	/*
 	 * Explicitly write out the special metadata inodes.
@@ -226,12 +224,34 @@ out:
 	return error;
 }
 
-static void hfsplus_write_super(struct super_block *sb)
+static void delayed_sync_fs(struct work_struct *work)
 {
-	if (!(sb->s_flags & MS_RDONLY))
-		hfsplus_sync_fs(sb, 1);
-	else
-		sb->s_dirt = 0;
+	struct hfsplus_sb_info *sbi;
+
+	sbi = container_of(work, struct hfsplus_sb_info, sync_work.work);
+
+	spin_lock(&sbi->work_lock);
+	sbi->work_queued = 0;
+	spin_unlock(&sbi->work_lock);
+
+	hfsplus_sync_fs(sbi->alloc_file->i_sb, 1);
+}
+
+void hfsplus_mark_mdb_dirty(struct super_block *sb)
+{
+	struct hfsplus_sb_info *sbi = HFSPLUS_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->sync_work, delay);
+		sbi->work_queued = 1;
+	}
+	spin_unlock(&sbi->work_lock);
 }
 
 static void hfsplus_put_super(struct super_block *sb)
@@ -240,8 +260,7 @@ static void hfsplus_put_super(struct super_block *sb)
 
 	dprint(DBG_SUPER, "hfsplus_put_super\n");
 
-	if (!sb->s_fs_info)
-		return;
+	cancel_delayed_work_sync(&sbi->sync_work);
 
 	if (!(sb->s_flags & MS_RDONLY) && sbi->s_vhdr) {
 		struct hfsplus_vh *vhdr = sbi->s_vhdr;
@@ -328,7 +347,6 @@ static const struct super_operations hfsplus_sops = {
 	.write_inode	= hfsplus_write_inode,
 	.evict_inode	= hfsplus_evict_inode,
 	.put_super	= hfsplus_put_super,
-	.write_super	= hfsplus_write_super,
 	.sync_fs	= hfsplus_sync_fs,
 	.statfs		= hfsplus_statfs,
 	.remount_fs	= hfsplus_remount,
@@ -355,6 +373,8 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_fs_info = sbi;
 	mutex_init(&sbi->alloc_mutex);
 	mutex_init(&sbi->vh_mutex);
+	spin_lock_init(&sbi->work_lock);
+	INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
 	hfsplus_fill_defaults(sbi);
 
 	err = -EINVAL;

fs/hostfs/hostfs_kern.c

@@ -553,7 +553,7 @@ static int read_name(struct inode *ino, char *name)
 }
 
 int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-		  struct nameidata *nd)
+		  bool excl)
 {
 	struct inode *inode;
 	char *name;
@@ -595,7 +595,7 @@ int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 }
 
 struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
-			     struct nameidata *nd)
+			     unsigned int flags)
 {
 	struct inode *inode;
 	char *name;

fs/hpfs/dir.c

@@ -189,7 +189,7 @@ out:
  *	      to tell read_inode to read fnode or not.
  */
 
-struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	const unsigned char *name = dentry->d_name.name;
 	unsigned len = dentry->d_name.len;