110 files changed, 754 insertions, 533 deletions

diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 46ce357ca1ab..410ffd6ceb5f 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -54,9 +54,9 @@ extern struct kmem_cache *v9fs_inode_cache;
 
 struct inode *v9fs_alloc_inode(struct super_block *sb);
 void v9fs_destroy_inode(struct inode *inode);
-struct inode *v9fs_get_inode(struct super_block *sb, int mode);
+struct inode *v9fs_get_inode(struct super_block *sb, int mode, dev_t);
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
-		    struct inode *inode, int mode);
+		    struct inode *inode, int mode, dev_t);
 void v9fs_evict_inode(struct inode *inode);
 ino_t v9fs_qid2ino(struct p9_qid *qid);
 void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *);
@@ -83,4 +83,6 @@ static inline void v9fs_invalidate_inode_attr(struct inode *inode)
 	v9inode->cache_validity |= V9FS_INO_INVALID_ATTR;
 	return;
 }
+
+int v9fs_open_to_dotl_flags(int flags);
 #endif
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 3c173fcc2c5a..62857a810a79 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -65,7 +65,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
 	v9inode = V9FS_I(inode);
 	v9ses = v9fs_inode2v9ses(inode);
 	if (v9fs_proto_dotl(v9ses))
-		omode = file->f_flags;
+		omode = v9fs_open_to_dotl_flags(file->f_flags);
 	else
 		omode = v9fs_uflags2omode(file->f_flags,
 					v9fs_proto_dotu(v9ses));
@@ -169,7 +169,18 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 
 	/* convert posix lock to p9 tlock args */
 	memset(&flock, 0, sizeof(flock));
-	flock.type = fl->fl_type;
+	/* map the lock type */
+	switch (fl->fl_type) {
+	case F_RDLCK:
+		flock.type = P9_LOCK_TYPE_RDLCK;
+		break;
+	case F_WRLCK:
+		flock.type = P9_LOCK_TYPE_WRLCK;
+		break;
+	case F_UNLCK:
+		flock.type = P9_LOCK_TYPE_UNLCK;
+		break;
+	}
 	flock.start = fl->fl_start;
 	if (fl->fl_end == OFFSET_MAX)
 		flock.length = 0;
@@ -245,7 +256,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 
 	/* convert posix lock to p9 tgetlock args */
 	memset(&glock, 0, sizeof(glock));
-	glock.type = fl->fl_type;
+	glock.type  = P9_LOCK_TYPE_UNLCK;
 	glock.start = fl->fl_start;
 	if (fl->fl_end == OFFSET_MAX)
 		glock.length = 0;
@@ -257,17 +268,26 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 	res = p9_client_getlock_dotl(fid, &glock);
 	if (res < 0)
 		return res;
-	if (glock.type != F_UNLCK) {
-		fl->fl_type = glock.type;
+	/* map 9p lock type to os lock type */
+	switch (glock.type) {
+	case P9_LOCK_TYPE_RDLCK:
+		fl->fl_type = F_RDLCK;
+		break;
+	case P9_LOCK_TYPE_WRLCK:
+		fl->fl_type = F_WRLCK;
+		break;
+	case P9_LOCK_TYPE_UNLCK:
+		fl->fl_type = F_UNLCK;
+		break;
+	}
+	if (glock.type != P9_LOCK_TYPE_UNLCK) {
 		fl->fl_start = glock.start;
 		if (glock.length == 0)
 			fl->fl_end = OFFSET_MAX;
 		else
 			fl->fl_end = glock.start + glock.length - 1;
 		fl->fl_pid = glock.proc_id;
-	} else
-		fl->fl_type = F_UNLCK;
-
+	}
 	return res;
 }
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 8bb5507e822f..e3c03db3c788 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -95,15 +95,18 @@ static int unixmode2p9mode(struct v9fs_session_info *v9ses, int mode)
 /**
  * p9mode2unixmode- convert plan9 mode bits to unix mode bits
  * @v9ses: v9fs session information
- * @mode: mode to convert
+ * @stat: p9_wstat from which mode need to be derived
+ * @rdev: major number, minor number in case of device files.
  *
  */
-
-static int p9mode2unixmode(struct v9fs_session_info *v9ses, int mode)
+static int p9mode2unixmode(struct v9fs_session_info *v9ses,
+			   struct p9_wstat *stat, dev_t *rdev)
 {
 	int res;
+	int mode = stat->mode;
 
-	res = mode & 0777;
+	res = mode & S_IALLUGO;
+	*rdev = 0;
 
 	if ((mode & P9_DMDIR) == P9_DMDIR)
 		res |= S_IFDIR;
@@ -116,9 +119,26 @@ static int p9mode2unixmode(struct v9fs_session_info *v9ses, int mode)
 		 && (v9ses->nodev == 0))
 		res |= S_IFIFO;
 	else if ((mode & P9_DMDEVICE) && (v9fs_proto_dotu(v9ses))
-		 && (v9ses->nodev == 0))
-		res |= S_IFBLK;
-	else
+		 && (v9ses->nodev == 0)) {
+		char type = 0, ext[32];
+		int major = -1, minor = -1;
+
+		strncpy(ext, stat->extension, sizeof(ext));
+		sscanf(ext, "%c %u %u", &type, &major, &minor);
+		switch (type) {
+		case 'c':
+			res |= S_IFCHR;
+			break;
+		case 'b':
+			res |= S_IFBLK;
+			break;
+		default:
+			P9_DPRINTK(P9_DEBUG_ERROR,
+				"Unknown special type %c %s\n", type,
+				stat->extension);
+		};
+		*rdev = MKDEV(major, minor);
+	} else
 		res |= S_IFREG;
 
 	if (v9fs_proto_dotu(v9ses)) {
@@ -131,7 +151,6 @@ static int p9mode2unixmode(struct v9fs_session_info *v9ses, int mode)
 		if ((mode & P9_DMSETVTX) == P9_DMSETVTX)
 			res |= S_ISVTX;
 	}
-
 	return res;
 }
 
@@ -242,13 +261,13 @@ void v9fs_destroy_inode(struct inode *inode)
 }
 
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
-		    struct inode *inode, int mode)
+		    struct inode *inode, int mode, dev_t rdev)
 {
 	int err = 0;
 
 	inode_init_owner(inode, NULL, mode);
 	inode->i_blocks = 0;
-	inode->i_rdev = 0;
+	inode->i_rdev = rdev;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	inode->i_mapping->a_ops = &v9fs_addr_operations;
 
@@ -335,7 +354,7 @@ error:
  *
  */
 
-struct inode *v9fs_get_inode(struct super_block *sb, int mode)
+struct inode *v9fs_get_inode(struct super_block *sb, int mode, dev_t rdev)
 {
 	int err;
 	struct inode *inode;
@@ -348,7 +367,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, int mode)
 		P9_EPRINTK(KERN_WARNING, "Problem allocating inode\n");
 		return ERR_PTR(-ENOMEM);
 	}
-	err = v9fs_init_inode(v9ses, inode, mode);
+	err = v9fs_init_inode(v9ses, inode, mode, rdev);
 	if (err) {
 		iput(inode);
 		return ERR_PTR(err);
@@ -435,11 +454,12 @@ void v9fs_evict_inode(struct inode *inode)
 static int v9fs_test_inode(struct inode *inode, void *data)
 {
 	int umode;
+	dev_t rdev;
 	struct v9fs_inode *v9inode = V9FS_I(inode);
 	struct p9_wstat *st = (struct p9_wstat *)data;
 	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode);
 
-	umode = p9mode2unixmode(v9ses, st->mode);
+	umode = p9mode2unixmode(v9ses, st, &rdev);
 	/* don't match inode of different type */
 	if ((inode->i_mode & S_IFMT) != (umode & S_IFMT))
 		return 0;
@@ -473,6 +493,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb,
 				   struct p9_wstat *st,
 				   int new)
 {
+	dev_t rdev;
 	int retval, umode;
 	unsigned long i_ino;
 	struct inode *inode;
@@ -496,8 +517,8 @@ static struct inode *v9fs_qid_iget(struct super_block *sb,
 	 * later.
 	 */
 	inode->i_ino = i_ino;
-	umode = p9mode2unixmode(v9ses, st->mode);
-	retval = v9fs_init_inode(v9ses, inode, umode);
+	umode = p9mode2unixmode(v9ses, st, &rdev);
+	retval = v9fs_init_inode(v9ses, inode, umode, rdev);
 	if (retval)
 		goto error;
 
@@ -532,6 +553,19 @@ v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
 }
 
 /**
+ * v9fs_at_to_dotl_flags- convert Linux specific AT flags to
+ * plan 9 AT flag.
+ * @flags: flags to convert
+ */
+static int v9fs_at_to_dotl_flags(int flags)
+{
+	int rflags = 0;
+	if (flags & AT_REMOVEDIR)
+		rflags |= P9_DOTL_AT_REMOVEDIR;
+	return rflags;
+}
+
+/**
  * v9fs_remove - helper function to remove files and directories
  * @dir: directory inode that is being deleted
  * @dentry:  dentry that is being deleted
@@ -558,7 +592,8 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
 		return retval;
 	}
 	if (v9fs_proto_dotl(v9ses))
-		retval = p9_client_unlinkat(dfid, dentry->d_name.name, flags);
+		retval = p9_client_unlinkat(dfid, dentry->d_name.name,
+					    v9fs_at_to_dotl_flags(flags));
 	if (retval == -EOPNOTSUPP) {
 		/* Try the one based on path */
 		v9fid = v9fs_fid_clone(dentry);
@@ -645,13 +680,11 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 		P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n", err);
 		goto error;
 	}
-	d_instantiate(dentry, inode);
 	err = v9fs_fid_add(dentry, fid);
 	if (err < 0)
 		goto error;
-
+	d_instantiate(dentry, inode);
 	return ofid;
-
 error:
 	if (ofid)
 		p9_client_clunk(ofid);
@@ -792,6 +825,7 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 				      struct nameidata *nameidata)
 {
+	struct dentry *res;
 	struct super_block *sb;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *dfid, *fid;
@@ -823,22 +857,35 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 
 		return ERR_PTR(result);
 	}
-
-	inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
+	/*
+	 * Make sure we don't use a wrong inode due to parallel
+	 * unlink. For cached mode create calls request for new
+	 * inode. But with cache disabled, lookup should do this.
+	 */
+	if (v9ses->cache)
+		inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
+	else
+		inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
 	if (IS_ERR(inode)) {
 		result = PTR_ERR(inode);
 		inode = NULL;
 		goto error;
 	}
-
 	result = v9fs_fid_add(dentry, fid);
 	if (result < 0)
 		goto error_iput;
-
 inst_out:
-	d_add(dentry, inode);
-	return NULL;
-
+	/*
+	 * If we had a rename on the server and a parallel lookup
+	 * for the new name, then make sure we instantiate with
+	 * the new name. ie look up for a/b, while on server somebody
+	 * moved b under k and client parallely did a lookup for
+	 * k/b.
+	 */
+	res = d_materialise_unique(dentry, inode);
+	if (!IS_ERR(res))
+		return res;
+	result = PTR_ERR(res);
 error_iput:
 	iput(inode);
 error:
@@ -1002,7 +1049,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		return PTR_ERR(st);
 
 	v9fs_stat2inode(st, dentry->d_inode, dentry->d_inode->i_sb);
-		generic_fillattr(dentry->d_inode, stat);
+	generic_fillattr(dentry->d_inode, stat);
 
 	p9stat_free(st);
 	kfree(st);
@@ -1086,6 +1133,7 @@ void
 v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
 	struct super_block *sb)
 {
+	mode_t mode;
 	char ext[32];
 	char tag_name[14];
 	unsigned int i_nlink;
@@ -1121,31 +1169,9 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
 				inode->i_nlink = i_nlink;
 		}
 	}
-	inode->i_mode = p9mode2unixmode(v9ses, stat->mode);
-	if ((S_ISBLK(inode->i_mode)) || (S_ISCHR(inode->i_mode))) {
-		char type = 0;
-		int major = -1;
-		int minor = -1;
-
-		strncpy(ext, stat->extension, sizeof(ext));
-		sscanf(ext, "%c %u %u", &type, &major, &minor);
-		switch (type) {
-		case 'c':
-			inode->i_mode &= ~S_IFBLK;
-			inode->i_mode |= S_IFCHR;
-			break;
-		case 'b':
-			break;
-		default:
-			P9_DPRINTK(P9_DEBUG_ERROR,
-				"Unknown special type %c %s\n", type,
-				stat->extension);
-		};
-		inode->i_rdev = MKDEV(major, minor);
-		init_special_inode(inode, inode->i_mode, inode->i_rdev);
-	} else
-		inode->i_rdev = 0;
-
+	mode = stat->mode & S_IALLUGO;
+	mode |= inode->i_mode & ~S_IALLUGO;
+	inode->i_mode = mode;
 	i_size_write(inode, stat->length);
 
 	/* not real number of blocks, but 512 byte ones ... */
@@ -1411,6 +1437,8 @@ v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev)
 
 int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
 {
+	int umode;
+	dev_t rdev;
 	loff_t i_size;
 	struct p9_wstat *st;
 	struct v9fs_session_info *v9ses;
@@ -1419,6 +1447,12 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
 	st = p9_client_stat(fid);
 	if (IS_ERR(st))
 		return PTR_ERR(st);
+	/*
+	 * Don't update inode if the file type is different
+	 */
+	umode = p9mode2unixmode(v9ses, st, &rdev);
+	if ((inode->i_mode & S_IFMT) != (umode & S_IFMT))
+		goto out;
 
 	spin_lock(&inode->i_lock);
 	/*
@@ -1430,6 +1464,7 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
 	if (v9ses->cache)
 		inode->i_size = i_size;
 	spin_unlock(&inode->i_lock);
+out:
 	p9stat_free(st);
 	kfree(st);
 	return 0;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index b6c8ed205192..aded79fcd5cf 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -153,7 +153,8 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
 	 * later.
 	 */
 	inode->i_ino = i_ino;
-	retval = v9fs_init_inode(v9ses, inode, st->st_mode);
+	retval = v9fs_init_inode(v9ses, inode,
+				 st->st_mode, new_decode_dev(st->st_rdev));
 	if (retval)
 		goto error;
 
@@ -190,6 +191,58 @@ v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid,
 	return inode;
 }
 
+struct dotl_openflag_map {
+	int open_flag;
+	int dotl_flag;
+};
+
+static int v9fs_mapped_dotl_flags(int flags)
+{
+	int i;
+	int rflags = 0;
+	struct dotl_openflag_map dotl_oflag_map[] = {
+		{ O_CREAT,	P9_DOTL_CREATE },
+		{ O_EXCL,	P9_DOTL_EXCL },
+		{ O_NOCTTY,	P9_DOTL_NOCTTY },
+		{ O_TRUNC,	P9_DOTL_TRUNC },
+		{ O_APPEND,	P9_DOTL_APPEND },
+		{ O_NONBLOCK,	P9_DOTL_NONBLOCK },
+		{ O_DSYNC,	P9_DOTL_DSYNC },
+		{ FASYNC,	P9_DOTL_FASYNC },
+		{ O_DIRECT,	P9_DOTL_DIRECT },
+		{ O_LARGEFILE,	P9_DOTL_LARGEFILE },
+		{ O_DIRECTORY,	P9_DOTL_DIRECTORY },
+		{ O_NOFOLLOW,	P9_DOTL_NOFOLLOW },
+		{ O_NOATIME,	P9_DOTL_NOATIME },
+		{ O_CLOEXEC,	P9_DOTL_CLOEXEC },
+		{ O_SYNC,	P9_DOTL_SYNC},
+	};
+	for (i = 0; i < ARRAY_SIZE(dotl_oflag_map); i++) {
+		if (flags & dotl_oflag_map[i].open_flag)
+			rflags |= dotl_oflag_map[i].dotl_flag;
+	}
+	return rflags;
+}
+
+/**
+ * v9fs_open_to_dotl_flags- convert Linux specific open flags to
+ * plan 9 open flag.
+ * @flags: flags to convert
+ */
+int v9fs_open_to_dotl_flags(int flags)
+{
+	int rflags = 0;
+
+	/*
+	 * We have same bits for P9_DOTL_READONLY, P9_DOTL_WRONLY
+	 * and P9_DOTL_NOACCESS
+	 */
+	rflags |= flags & O_ACCMODE;
+	rflags |= v9fs_mapped_dotl_flags(flags);
+
+	return rflags;
+}
+
 /**
  * v9fs_vfs_create_dotl - VFS hook to create files for 9P2000.L protocol.
  * @dir: directory inode that is being created
@@ -258,7 +311,8 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode,
 			   "Failed to get acl values in creat %d\n", err);
 		goto error;
 	}
-	err = p9_client_create_dotl(ofid, name, flags, mode, gid, &qid);
+	err = p9_client_create_dotl(ofid, name, v9fs_open_to_dotl_flags(flags),
+				    mode, gid, &qid);
 	if (err < 0) {
 		P9_DPRINTK(P9_DEBUG_VFS,
 				"p9_client_open_dotl failed in creat %d\n",
@@ -281,10 +335,10 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode,
 		P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n", err);
 		goto error;
 	}
-	d_instantiate(dentry, inode);
 	err = v9fs_fid_add(dentry, fid);
 	if (err < 0)
 		goto error;
+	d_instantiate(dentry, inode);
 
 	/* Now set the ACL based on the default value */
 	v9fs_set_create_acl(dentry, &dacl, &pacl);
@@ -403,10 +457,10 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 				err);
 			goto error;
 		}
-		d_instantiate(dentry, inode);
 		err = v9fs_fid_add(dentry, fid);
 		if (err < 0)
 			goto error;
+		d_instantiate(dentry, inode);
 		fid = NULL;
 	} else {
 		/*
@@ -414,7 +468,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 		 * inode with stat. We need to get an inode
 		 * so that we can set the acl with dentry
 		 */
-		inode = v9fs_get_inode(dir->i_sb, mode);
+		inode = v9fs_get_inode(dir->i_sb, mode, 0);
 		if (IS_ERR(inode)) {
 			err = PTR_ERR(inode);
 			goto error;
@@ -540,6 +594,7 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
 void
 v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode)
 {
+	mode_t mode;
 	struct v9fs_inode *v9inode = V9FS_I(inode);
 
 	if ((stat->st_result_mask & P9_STATS_BASIC) == P9_STATS_BASIC) {
@@ -552,11 +607,10 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode)
 		inode->i_uid = stat->st_uid;
 		inode->i_gid = stat->st_gid;
 		inode->i_nlink = stat->st_nlink;
-		inode->i_mode = stat->st_mode;
-		inode->i_rdev = new_decode_dev(stat->st_rdev);
 
-		if ((S_ISBLK(inode->i_mode)) || (S_ISCHR(inode->i_mode)))
-			init_special_inode(inode, inode->i_mode, inode->i_rdev);
+		mode = stat->st_mode & S_IALLUGO;
+		mode |= inode->i_mode & ~S_IALLUGO;
+		inode->i_mode = mode;
 
 		i_size_write(inode, stat->st_size);
 		inode->i_blocks = stat->st_blocks;
@@ -657,14 +711,14 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
 					err);
 			goto error;
 		}
-		d_instantiate(dentry, inode);
 		err = v9fs_fid_add(dentry, fid);
 		if (err < 0)
 			goto error;
+		d_instantiate(dentry, inode);
 		fid = NULL;
 	} else {
 		/* Not in cached mode. No need to populate inode with stat */
-		inode = v9fs_get_inode(dir->i_sb, S_IFLNK);
+		inode = v9fs_get_inode(dir->i_sb, S_IFLNK, 0);
 		if (IS_ERR(inode)) {
 			err = PTR_ERR(inode);
 			goto error;
@@ -810,17 +864,17 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int omode,
 				err);
 			goto error;
 		}
-		d_instantiate(dentry, inode);
 		err = v9fs_fid_add(dentry, fid);
 		if (err < 0)
 			goto error;
+		d_instantiate(dentry, inode);
 		fid = NULL;
 	} else {
 		/*
 		 * Not in cached mode. No need to populate inode with stat.
 		 * socket syscall returns a fd, so we need instantiate
 		 */
-		inode = v9fs_get_inode(dir->i_sb, mode);
+		inode = v9fs_get_inode(dir->i_sb, mode, rdev);
 		if (IS_ERR(inode)) {
 			err = PTR_ERR(inode);
 			goto error;
@@ -886,6 +940,11 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
 	st = p9_client_getattr_dotl(fid, P9_STATS_ALL);
 	if (IS_ERR(st))
 		return PTR_ERR(st);
+	/*
+	 * Don't update inode if the file type is different
+	 */
+	if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT))
+		goto out;
 
 	spin_lock(&inode->i_lock);
 	/*
@@ -897,6 +956,7 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
 	if (v9ses->cache)
 		inode->i_size = i_size;
 	spin_unlock(&inode->i_lock);
+out:
 	kfree(st);
 	return 0;
 }
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index feef6cdc1fd2..c70251d47ed1 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -149,7 +149,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 	else
 		sb->s_d_op = &v9fs_dentry_operations;
 
-	inode = v9fs_get_inode(sb, S_IFDIR | mode);
+	inode = v9fs_get_inode(sb, S_IFDIR | mode, 0);
 	if (IS_ERR(inode)) {
 		retval = PTR_ERR(inode);
 		goto release_sb;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index ff77262e887c..95f786ec7f08 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1429,6 +1429,11 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		WARN_ON_ONCE(bdev->bd_holders);
 		sync_blockdev(bdev);
 		kill_bdev(bdev);
+		/* ->release can cause the old bdi to disappear,
+		 * so must switch it out first
+		 */
+		bdev_inode_switch_bdi(bdev->bd_inode,
+					&default_backing_dev_info);
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
@@ -1442,8 +1447,6 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		disk_put_part(bdev->bd_part);
 		bdev->bd_part = NULL;
 		bdev->bd_disk = NULL;
-		bdev_inode_switch_bdi(bdev->bd_inode,
-					&default_backing_dev_info);
 		if (bdev != bdev->bd_contains)
 			victim = bdev->bd_contains;
 		bdev->bd_contains = NULL;
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 502b9e988679..d9f99a16edd6 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -176,7 +176,11 @@ static inline u64 btrfs_ino(struct inode *inode)
 {
 	u64 ino = BTRFS_I(inode)->location.objectid;
 
-	if (ino <= BTRFS_FIRST_FREE_OBJECTID)
+	/*
+	 * !ino: btree_inode
+	 * type == BTRFS_ROOT_ITEM_KEY: subvol dir
+	 */
+	if (!ino || BTRFS_I(inode)->location.type == BTRFS_ROOT_ITEM_KEY)
 		ino = inode->i_ino;
 	return ino;
 }
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index b910694f61ed..a1cb7821becd 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -183,8 +183,10 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	 * read from the commit root and sidestep a nasty deadlock
 	 * between reading the free space cache and updating the csum tree.
 	 */
-	if (btrfs_is_free_space_inode(root, inode))
+	if (btrfs_is_free_space_inode(root, inode)) {
 		path->search_commit_root = 1;
+		path->skip_locking = 1;
+	}
 
 	disk_bytenr = (u64)bio->bi_sector << 9;
 	if (dio)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e7872e485f13..e4e57d59edb7 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1036,11 +1036,13 @@ out:
  * on error we return an unlocked page and the error value
  * on success we return a locked page and 0
  */
-static int prepare_uptodate_page(struct page *page, u64 pos)
+static int prepare_uptodate_page(struct page *page, u64 pos,
+				 bool force_uptodate)
 {
 	int ret = 0;
 
-	if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) {
+	if (((pos & (PAGE_CACHE_SIZE - 1)) || force_uptodate) &&
+	    !PageUptodate(page)) {
 		ret = btrfs_readpage(NULL, page);
 		if (ret)
 			return ret;
@@ -1061,7 +1063,7 @@ static int prepare_uptodate_page(struct page *page, u64 pos)
 static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
 			 struct page **pages, size_t num_pages,
 			 loff_t pos, unsigned long first_index,
-			 size_t write_bytes)
+			 size_t write_bytes, bool force_uptodate)
 {
 	struct extent_state *cached_state = NULL;
 	int i;
@@ -1075,12 +1077,6 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
 	start_pos = pos & ~((u64)root->sectorsize - 1);
 	last_pos = ((u64)index + num_pages) << PAGE_CACHE_SHIFT;
 
-	if (start_pos > inode->i_size) {
-		err = btrfs_cont_expand(inode, i_size_read(inode), start_pos);
-		if (err)
-			return err;
-	}
-
 again:
 	for (i = 0; i < num_pages; i++) {
 		pages[i] = find_or_create_page(inode->i_mapping, index + i,
@@ -1092,10 +1088,11 @@ again:
 		}
 
 		if (i == 0)
-			err = prepare_uptodate_page(pages[i], pos);
+			err = prepare_uptodate_page(pages[i], pos,
+						    force_uptodate);
 		if (i == num_pages - 1)
 			err = prepare_uptodate_page(pages[i],
-						    pos + write_bytes);
+						    pos + write_bytes, false);
 		if (err) {
 			page_cache_release(pages[i]);
 			faili = i - 1;
@@ -1164,6 +1161,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	size_t num_written = 0;
 	int nrptrs;
 	int ret = 0;
+	bool force_page_uptodate = false;
 
 	nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
 		     PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
@@ -1206,7 +1204,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		 * contents of pages from loop to loop
 		 */
 		ret = prepare_pages(root, file, pages, num_pages,
-				    pos, first_index, write_bytes);
+				    pos, first_index, write_bytes,
+				    force_page_uptodate);
 		if (ret) {
 			btrfs_delalloc_release_space(inode,
 					num_pages << PAGE_CACHE_SHIFT);
@@ -1223,12 +1222,15 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		if (copied < write_bytes)
 			nrptrs = 1;
 
-		if (copied == 0)
+		if (copied == 0) {
+			force_page_uptodate = true;
 			dirty_pages = 0;
-		else
+		} else {
+			force_page_uptodate = false;
 			dirty_pages = (copied + offset +
 				       PAGE_CACHE_SIZE - 1) >>
 				       PAGE_CACHE_SHIFT;
+		}
 
 		/*
 		 * If we had a short copy we need to release the excess delaloc
@@ -1338,6 +1340,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	struct inode *inode = fdentry(file)->d_inode;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	loff_t *ppos = &iocb->ki_pos;
+	u64 start_pos;
 	ssize_t num_written = 0;
 	ssize_t err = 0;
 	size_t count, ocount;
@@ -1386,6 +1389,15 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	file_update_time(file);
 	BTRFS_I(inode)->sequence++;
 
+	start_pos = round_down(pos, root->sectorsize);
+	if (start_pos > i_size_read(inode)) {
+		err = btrfs_cont_expand(inode, i_size_read(inode), start_pos);
+		if (err) {
+			mutex_unlock(&inode->i_mutex);
+			goto out;
+		}
+	}
+
 	if (unlikely(file->f_flags & O_DIRECT)) {
 		num_written = __btrfs_direct_write(iocb, iov, nr_segs,
 						   pos, ppos, count, ocount);
@@ -1813,6 +1825,11 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
 		goto out;
 	case SEEK_DATA:
 	case SEEK_HOLE:
+		if (offset >= i_size_read(inode)) {
+			mutex_unlock(&inode->i_mutex);
+			return -ENXIO;
+		}
+
 		ret = find_desired_extent(inode, &offset, origin);
 		if (ret) {
 			mutex_unlock(&inode->i_mutex);
@@ -1821,11 +1838,11 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
 	}
 
 	if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) {
-		ret = -EINVAL;
+		offset = -EINVAL;
 		goto out;
 	}
 	if (offset > inode->i_sb->s_maxbytes) {
-		ret = -EINVAL;
+		offset = -EINVAL;
 		goto out;
 	}
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6a265b9f85f2..41ac927401d0 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -190,9 +190,11 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root,
 				    struct btrfs_path *path,
 				    struct inode *inode)
 {
+	struct btrfs_block_rsv *rsv;
 	loff_t oldsize;
 	int ret = 0;
 
+	rsv = trans->block_rsv;
 	trans->block_rsv = root->orphan_block_rsv;
 	ret = btrfs_block_rsv_check(trans, root,
 				    root->orphan_block_rsv,
@@ -210,6 +212,8 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root,
 	 */
 	ret = btrfs_truncate_inode_items(trans, root, inode,
 					 0, BTRFS_EXTENT_DATA_KEY);
+
+	trans->block_rsv = rsv;
 	if (ret) {
 		WARN_ON(1);
 		return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0ccc7438ad34..b2d004ad66a0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1786,7 +1786,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 			  &ordered_extent->list);
 
 	ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
-	if (!ret) {
+	if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
 		ret = btrfs_update_inode(trans, root, inode);
 		BUG_ON(ret);
 	}
@@ -3510,15 +3510,19 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 			err = btrfs_drop_extents(trans, inode, cur_offset,
 						 cur_offset + hole_size,
 						 &hint_byte, 1);
-			if (err)
+			if (err) {
+				btrfs_end_transaction(trans, root);
 				break;
+			}
 
 			err = btrfs_insert_file_extent(trans, root,
 					btrfs_ino(inode), cur_offset, 0,
 					0, hole_size, 0, hole_size,
 					0, 0, 0);
-			if (err)
+			if (err) {
+				btrfs_end_transaction(trans, root);
 				break;
+			}
 
 			btrfs_drop_extent_cache(inode, hole_start,
 					last_byte - 1, 0);
@@ -3952,7 +3956,6 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			 struct btrfs_root *root, int *new)
 {
 	struct inode *inode;
-	int bad_inode = 0;
 
 	inode = btrfs_iget_locked(s, location->objectid, root);
 	if (!inode)
@@ -3968,15 +3971,12 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			if (new)
 				*new = 1;
 		} else {
-			bad_inode = 1;
+			unlock_new_inode(inode);
+			iput(inode);
+			inode = ERR_PTR(-ESTALE);
 		}
 	}
 
-	if (bad_inode) {
-		iput(inode);
-		inode = ERR_PTR(-ESTALE);
-	}
-
 	return inode;
 }
 
@@ -4018,7 +4018,8 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		memcpy(&location, dentry->d_fsdata, sizeof(struct btrfs_key));
 		kfree(dentry->d_fsdata);
 		dentry->d_fsdata = NULL;
-		d_clear_need_lookup(dentry);
+		/* This thing is hashed, drop it for now */
+		d_drop(dentry);
 	} else {
 		ret = btrfs_inode_by_name(dir, dentry, &location);
 	}
@@ -4085,7 +4086,15 @@ static void btrfs_dentry_release(struct dentry *dentry)
 static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
 				   struct nameidata *nd)
 {
-	return d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry);
+	struct dentry *ret;
+
+	ret = d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry);
+	if (unlikely(d_need_lookup(dentry))) {
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
+		spin_unlock(&dentry->d_lock);
+	}
+	return ret;
 }
 
 unsigned char btrfs_filetype_table[] = {
@@ -4125,7 +4134,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 
 	/* special case for "." */
 	if (filp->f_pos == 0) {
-		over = filldir(dirent, ".", 1, 1, btrfs_ino(inode), DT_DIR);
+		over = filldir(dirent, ".", 1,
+			       filp->f_pos, btrfs_ino(inode), DT_DIR);
 		if (over)
 			return 0;
 		filp->f_pos = 1;
@@ -4134,7 +4144,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 	if (filp->f_pos == 1) {
 		u64 pino = parent_ino(filp->f_path.dentry);
 		over = filldir(dirent, "..", 2,
-			       2, pino, DT_DIR);
+			       filp->f_pos, pino, DT_DIR);
 		if (over)
 			return 0;
 		filp->f_pos = 2;
@@ -5823,7 +5833,7 @@ again:
 
 	add_pending_csums(trans, inode, ordered->file_offset, &ordered->list);
 	ret = btrfs_ordered_update_i_size(inode, 0, ordered);
-	if (!ret)
+	if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags))
 		btrfs_update_inode(trans, root, inode);
 	ret = 0;
 out_unlock:
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 970977aab224..dae5dfe41ba5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1047,7 +1047,16 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 	if (!max_to_defrag)
 		max_to_defrag = last_index - 1;
 
-	while (i <= last_index && defrag_count < max_to_defrag) {
+	/*
+	 * make writeback starts from i, so the defrag range can be
+	 * written sequentially.
+	 */
+	if (i < inode->i_mapping->writeback_index)
+		inode->i_mapping->writeback_index = i;
+
+	while (i <= last_index && defrag_count < max_to_defrag &&
+	       (i < (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+		PAGE_CACHE_SHIFT)) {
 		/*
 		 * make sure we stop running if someone unmounts
 		 * the FS
@@ -2177,6 +2186,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	if (!(src_file->f_mode & FMODE_READ))
 		goto out_fput;
 
+	/* don't make the dst file partly checksummed */
+	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+	    (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
+		goto out_fput;
+
 	ret = -EISDIR;
 	if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
 		goto out_fput;
@@ -2220,6 +2234,16 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	    !IS_ALIGNED(destoff, bs))
 		goto out_unlock;
 
+	if (destoff > inode->i_size) {
+		ret = btrfs_cont_expand(inode, inode->i_size, destoff);
+		if (ret)
+			goto out_unlock;
+	}
+
+	/* truncate page cache pages from target inode range */
+	truncate_inode_pages_range(&inode->i_data, destoff,
+				   PAGE_CACHE_ALIGN(destoff + len) - 1);
+
 	/* do any pending delalloc/csum calc on src, one way or
 	   another, and lock file content */
 	while (1) {
@@ -2236,10 +2260,6 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 		btrfs_wait_ordered_range(src, off, len);
 	}
 
-	/* truncate page cache pages from target inode range */
-	truncate_inode_pages_range(&inode->i_data, off,
-				   ALIGN(off + len, PAGE_CACHE_SIZE) - 1);
-
 	/* clone data */
 	key.objectid = btrfs_ino(src);
 	key.type = BTRFS_EXTENT_DATA_KEY;
@@ -2317,7 +2337,12 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 			else
 				new_key.offset = destoff;
 
-			trans = btrfs_start_transaction(root, 1);
+			/*
+			 * 1 - adjusting old extent (we may have to split it)
+			 * 1 - add new extent
+			 * 1 - inode update
+			 */
+			trans = btrfs_start_transaction(root, 3);
 			if (IS_ERR(trans)) {
 				ret = PTR_ERR(trans);
 				goto out;
@@ -2325,14 +2350,21 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 
 			if (type == BTRFS_FILE_EXTENT_REG ||
 			    type == BTRFS_FILE_EXTENT_PREALLOC) {
+				/*
+				 *    a  | --- range to clone ---|  b
+				 * | ------------- extent ------------- |
+				 */
+
+				/* substract range b */
+				if (key.offset + datal > off + len)
+					datal = off + len - key.offset;
+
+				/* substract range a */
 				if (off > key.offset) {
 					datao += off - key.offset;
 					datal -= off - key.offset;
 				}
 
-				if (key.offset + datal > off + len)
-					datal = off + len - key.offset;
-
 				ret = btrfs_drop_extents(trans, inode,
 							 new_key.offset,
 							 new_key.offset + datal,
@@ -2429,7 +2461,6 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 			if (endoff > inode->i_size)
 				btrfs_i_size_write(inode, endoff);
 
-			BTRFS_I(inode)->flags = BTRFS_I(src)->flags;
 			ret = btrfs_update_inode(trans, root, inode);
 			BUG_ON(ret);
 			btrfs_end_transaction(trans, root);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 7dc36fab4afc..e24b7964a155 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -884,6 +884,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	struct btrfs_root *tree_root = fs_info->tree_root;
 	struct btrfs_root *root = pending->root;
 	struct btrfs_root *parent_root;
+	struct btrfs_block_rsv *rsv;
 	struct inode *parent_inode;
 	struct dentry *parent;
 	struct dentry *dentry;
@@ -895,6 +896,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	u64 objectid;
 	u64 root_flags;
 
+	rsv = trans->block_rsv;
+
 	new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
 	if (!new_root_item) {
 		pending->error = -ENOMEM;
@@ -1002,6 +1005,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_orphan_post_snapshot(trans, pending);
 fail:
 	kfree(new_root_item);
+	trans->block_rsv = rsv;
 	btrfs_block_rsv_release(root, &pending->block_rsv, (u64)-1);
 	return 0;
 }
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index d733b9cfea34..69565e5fc6a0 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -116,6 +116,12 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		if (ret)
 			goto out;
 		btrfs_release_path(path);
+
+		/*
+		 * remove the attribute
+		 */
+		if (!value)
+			goto out;
 	}
 
 again:
@@ -158,6 +164,9 @@ out:
 	return ret;
 }
 
+/*
+ * @value: "" makes the attribute to empty, NULL removes it
+ */
 int __btrfs_setxattr(struct btrfs_trans_handle *trans,
 		     struct inode *inode, const char *name,
 		     const void *value, size_t size, int flags)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index fee028b5332e..86c59e16ba74 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1595,7 +1595,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
 		r = build_dentry_path(rdentry, ppath, pathlen, ino, freepath);
 		dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen,
 		     *ppath);
-	} else if (rpath) {
+	} else if (rpath || rino) {
 		*ino = rino;
 		*ppath = rpath;
 		*pathlen = strlen(rpath);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index d47c5ec7fb1f..88bacaf385d9 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -813,8 +813,8 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
 	fsc = create_fs_client(fsopt, opt);
 	if (IS_ERR(fsc)) {
 		res = ERR_CAST(fsc);
-		kfree(fsopt);
-		kfree(opt);
+		destroy_mount_options(fsopt);
+		ceph_destroy_options(opt);
 		goto out_final;
 	}
 
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index e76bfeb68267..30acd22147e1 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -351,9 +351,7 @@ static int
 build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp)
 {
 	unsigned int dlen;
-	unsigned int wlen;
-	unsigned int size = 6 * sizeof(struct ntlmssp2_name);
-	__le64  curtime;
+	unsigned int size = 2 * sizeof(struct ntlmssp2_name);
 	char *defdmname = "WORKGROUP";
 	unsigned char *blobptr;
 	struct ntlmssp2_name *attrptr;
@@ -365,15 +363,14 @@ build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	}
 
 	dlen = strlen(ses->domainName);
-	wlen = strlen(ses->server->hostname);
 
-	/* The length of this blob is a size which is
-	 * six times the size of a structure which holds name/size +
-	 * two times the unicode length of a domain name +
-	 * two times the unicode length of a server name +
-	 * size of a timestamp (which is 8 bytes).
+	/*
+	 * The length of this blob is two times the size of a
+	 * structure (av pair) which holds name/size
+	 * ( for NTLMSSP_AV_NB_DOMAIN_NAME followed by NTLMSSP_AV_EOL ) +
+	 * unicode length of a netbios domain name
 	 */
-	ses->auth_key.len = size + 2 * (2 * dlen) + 2 * (2 * wlen) + 8;
+	ses->auth_key.len = size + 2 * dlen;
 	ses->auth_key.response = kzalloc(ses->auth_key.len, GFP_KERNEL);
 	if (!ses->auth_key.response) {
 		ses->auth_key.len = 0;
@@ -384,44 +381,15 @@ build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	blobptr = ses->auth_key.response;
 	attrptr = (struct ntlmssp2_name *) blobptr;
 
+	/*
+	 * As defined in MS-NTLM 3.3.2, just this av pair field
+	 * is sufficient as part of the temp
+	 */
 	attrptr->type = cpu_to_le16(NTLMSSP_AV_NB_DOMAIN_NAME);
 	attrptr->length = cpu_to_le16(2 * dlen);
 	blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name);
 	cifs_strtoUCS((__le16 *)blobptr, ses->domainName, dlen, nls_cp);
 
-	blobptr += 2 * dlen;
-	attrptr = (struct ntlmssp2_name *) blobptr;
-
-	attrptr->type = cpu_to_le16(NTLMSSP_AV_NB_COMPUTER_NAME);
-	attrptr->length = cpu_to_le16(2 * wlen);
-	blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name);
-	cifs_strtoUCS((__le16 *)blobptr, ses->server->hostname, wlen, nls_cp);
-
-	blobptr += 2 * wlen;
-	attrptr = (struct ntlmssp2_name *) blobptr;
-
-	attrptr->type = cpu_to_le16(NTLMSSP_AV_DNS_DOMAIN_NAME);
-	attrptr->length = cpu_to_le16(2 * dlen);
-	blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name);
-	cifs_strtoUCS((__le16 *)blobptr, ses->domainName, dlen, nls_cp);
-
-	blobptr += 2 * dlen;
-	attrptr = (struct ntlmssp2_name *) blobptr;
-
-	attrptr->type = cpu_to_le16(NTLMSSP_AV_DNS_COMPUTER_NAME);
-	attrptr->length = cpu_to_le16(2 * wlen);
-	blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name);
-	cifs_strtoUCS((__le16 *)blobptr, ses->server->hostname, wlen, nls_cp);
-
-	blobptr += 2 * wlen;
-	attrptr = (struct ntlmssp2_name *) blobptr;
-
-	attrptr->type = cpu_to_le16(NTLMSSP_AV_TIMESTAMP);
-	attrptr->length = cpu_to_le16(sizeof(__le64));
-	blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name);
-	curtime = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
-	memcpy(blobptr, &curtime, sizeof(__le64));
-
 	return 0;
 }
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index f93eb948d071..54b8f1e7da94 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -548,6 +548,12 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 		struct inode *dir = dentry->d_inode;
 		struct dentry *child;
 
+		if (!dir) {
+			dput(dentry);
+			dentry = ERR_PTR(-ENOENT);
+			break;
+		}
+
 		/* skip separators */
 		while (*s == sep)
 			s++;
@@ -563,10 +569,6 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 		mutex_unlock(&dir->i_mutex);
 		dput(dentry);
 		dentry = child;
-		if (!dentry->d_inode) {
-			dput(dentry);
-			dentry = ERR_PTR(-ENOENT);
-		}
 	} while (!IS_ERR(dentry));
 	_FreeXid(xid);
 	kfree(full_path);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index aac37d99a487..a80f7bd97b90 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -4079,7 +4079,8 @@ int CIFSFindNext(const int xid, struct cifs_tcon *tcon,
 	T2_FNEXT_RSP_PARMS *parms;
 	char *response_data;
 	int rc = 0;
-	int bytes_returned, name_len;
+	int bytes_returned;
+	unsigned int name_len;
 	__u16 params, byte_count;
 
 	cFYI(1, "In FindNext");
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 633c246b6775..71beb0201970 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1298,7 +1298,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			/* ignore */
 		} else if (strnicmp(data, "guest", 5) == 0) {
 			/* ignore */
-		} else if (strnicmp(data, "rw", 2) == 0) {
+		} else if (strnicmp(data, "rw", 2) == 0 && strlen(data) == 2) {
 			/* ignore */
 		} else if (strnicmp(data, "ro", 2) == 0) {
 			/* ignore */
@@ -1401,7 +1401,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			vol->server_ino = 1;
 		} else if (strnicmp(data, "noserverino", 9) == 0) {
 			vol->server_ino = 0;
-		} else if (strnicmp(data, "rwpidforward", 4) == 0) {
+		} else if (strnicmp(data, "rwpidforward", 12) == 0) {
 			vol->rwpidforward = 1;
 		} else if (strnicmp(data, "cifsacl", 7) == 0) {
 			vol->cifs_acl = 1;
@@ -2018,7 +2018,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 		warned_on_ntlm = true;
 		cERROR(1, "default security mechanism requested.  The default "
 			"security mechanism will be upgraded from ntlm to "
-			"ntlmv2 in kernel release 3.1");
+			"ntlmv2 in kernel release 3.2");
 	}
 	ses->overrideSecFlg = volume_info->secFlg;
 
diff --git a/fs/compat.c b/fs/compat.c
index 0b48d018e38a..58b1da459893 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1675,11 +1675,6 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 }
 #endif /* HAVE_SET_RESTORE_SIGMASK */
 
-long asmlinkage compat_sys_nfsservctl(int cmd, void *notused, void *notused2)
-{
-	return sys_ni_syscall();
-}
-
 #ifdef CONFIG_EPOLL
 
 #ifdef HAVE_SET_RESTORE_SIGMASK
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 04da6acde85d..12661e1deedd 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1134,7 +1134,7 @@ struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode,
 		return bh;
 	if (buffer_uptodate(bh))
 		return bh;
-	ll_rw_block(READ_META, 1, &bh);
+	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return bh;
@@ -2807,7 +2807,7 @@ make_io:
 		trace_ext3_load_inode(inode);
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(READ_META, bh);
+		submit_bh(READ | REQ_META | REQ_PRIO, bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			ext3_error(inode->i_sb, "ext3_get_inode_loc",
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 5571708b6a58..0629e09f6511 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -922,7 +922,8 @@ restart:
 				bh = ext3_getblk(NULL, dir, b++, 0, &err);
 				bh_use[ra_max] = bh;
 				if (bh)
-					ll_rw_block(READ_META, 1, &bh);
+					ll_rw_block(READ | REQ_META | REQ_PRIO,
+						    1, &bh);
 			}
 		}
 		if ((bh = bh_use[ra_ptr++]) == NULL)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e717dfd2f2b4..b7d7bd0f066e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -175,6 +175,7 @@ struct mpage_da_data {
  */
 #define	EXT4_IO_END_UNWRITTEN	0x0001
 #define EXT4_IO_END_ERROR	0x0002
+#define EXT4_IO_END_QUEUED	0x0004
 
 struct ext4_io_page {
 	struct page	*p_page;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c4da98a959ae..986e2388f031 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -121,9 +121,6 @@ void ext4_evict_inode(struct inode *inode)
 
 	trace_ext4_evict_inode(inode);
 
-	mutex_lock(&inode->i_mutex);
-	ext4_flush_completed_IO(inode);
-	mutex_unlock(&inode->i_mutex);
 	ext4_ioend_wait(inode);
 
 	if (inode->i_nlink) {
@@ -650,7 +647,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
 		return bh;
 	if (buffer_uptodate(bh))
 		return bh;
-	ll_rw_block(READ_META, 1, &bh);
+	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return bh;
@@ -3301,7 +3298,7 @@ make_io:
 		trace_ext4_load_inode(inode);
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(READ_META, bh);
+		submit_bh(READ | REQ_META | REQ_PRIO, bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			EXT4_ERROR_INODE_BLOCK(inode, block,
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index f8068c7bae9f..1c924faeb6c8 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -922,7 +922,8 @@ restart:
 				bh = ext4_getblk(NULL, dir, b++, 0, &err);
 				bh_use[ra_max] = bh;
 				if (bh)
-					ll_rw_block(READ_META, 1, &bh);
+					ll_rw_block(READ | REQ_META | REQ_PRIO,
+						    1, &bh);
 			}
 		}
 		if ((bh = bh_use[ra_ptr++]) == NULL)
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 78839af7ce29..92f38ee13f8a 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -142,7 +142,23 @@ static void ext4_end_io_work(struct work_struct *work)
 	unsigned long		flags;
 	int			ret;
 
-	mutex_lock(&inode->i_mutex);
+	if (!mutex_trylock(&inode->i_mutex)) {
+		/*
+		 * Requeue the work instead of waiting so that the work
+		 * items queued after this can be processed.
+		 */
+		queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
+		/*
+		 * To prevent the ext4-dio-unwritten thread from keeping
+		 * requeueing end_io requests and occupying cpu for too long,
+		 * yield the cpu if it sees an end_io request that has already
+		 * been requeued.
+		 */
+		if (io->flag & EXT4_IO_END_QUEUED)
+			yield();
+		io->flag |= EXT4_IO_END_QUEUED;
+		return;
+	}
 	ret = ext4_end_io_nolock(io);
 	if (ret < 0) {
 		mutex_unlock(&inode->i_mutex);
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 640fc229df10..5cb8614508c3 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -258,10 +258,14 @@ void fuse_queue_forget(struct fuse_conn *fc, struct fuse_forget_link *forget,
 	forget->forget_one.nlookup = nlookup;
 
 	spin_lock(&fc->lock);
-	fc->forget_list_tail->next = forget;
-	fc->forget_list_tail = forget;
-	wake_up(&fc->waitq);
-	kill_fasync(&fc->fasync, SIGIO, POLL_IN);
+	if (fc->connected) {
+		fc->forget_list_tail->next = forget;
+		fc->forget_list_tail = forget;
+		wake_up(&fc->waitq);
+		kill_fasync(&fc->fasync, SIGIO, POLL_IN);
+	} else {
+		kfree(forget);
+	}
 	spin_unlock(&fc->lock);
 }
 
@@ -1358,6 +1362,10 @@ static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
 	if (outarg.namelen > FUSE_NAME_MAX)
 		goto err;
 
+	err = -EINVAL;
+	if (size != sizeof(outarg) + outarg.namelen + 1)
+		goto err;
+
 	name.name = buf;
 	name.len = outarg.namelen;
 	err = fuse_copy_one(cs, buf, outarg.namelen + 1);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index d480d9af46c9..594f07a81c28 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/compat.h>
+#include <linux/swap.h>
 
 static const struct file_operations fuse_direct_io_file_operations;
 
@@ -245,6 +246,12 @@ void fuse_release_common(struct file *file, int opcode)
 	req = ff->reserved_req;
 	fuse_prepare_release(ff, file->f_flags, opcode);
 
+	if (ff->flock) {
+		struct fuse_release_in *inarg = &req->misc.release.in;
+		inarg->release_flags |= FUSE_RELEASE_FLOCK_UNLOCK;
+		inarg->lock_owner = fuse_lock_owner_id(ff->fc,
+						       (fl_owner_t) file);
+	}
 	/* Hold vfsmount and dentry until release is finished */
 	path_get(&file->f_path);
 	req->misc.release.path = file->f_path;
@@ -755,18 +762,6 @@ static size_t fuse_send_write(struct fuse_req *req, struct file *file,
 	return req->misc.write.out.size;
 }
 
-static int fuse_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
-			struct page **pagep, void **fsdata)
-{
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-
-	*pagep = grab_cache_page_write_begin(mapping, index, flags);
-	if (!*pagep)
-		return -ENOMEM;
-	return 0;
-}
-
 void fuse_write_update_size(struct inode *inode, loff_t pos)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
@@ -779,62 +774,6 @@ void fuse_write_update_size(struct inode *inode, loff_t pos)
 	spin_unlock(&fc->lock);
 }
 
-static int fuse_buffered_write(struct file *file, struct inode *inode,
-			       loff_t pos, unsigned count, struct page *page)
-{
-	int err;
-	size_t nres;
-	struct fuse_conn *fc = get_fuse_conn(inode);
-	unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
-	struct fuse_req *req;
-
-	if (is_bad_inode(inode))
-		return -EIO;
-
-	/*
-	 * Make sure writepages on the same page are not mixed up with
-	 * plain writes.
-	 */
-	fuse_wait_on_page_writeback(inode, page->index);
-
-	req = fuse_get_req(fc);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
-
-	req->in.argpages = 1;
-	req->num_pages = 1;
-	req->pages[0] = page;
-	req->page_offset = offset;
-	nres = fuse_send_write(req, file, pos, count, NULL);
-	err = req->out.h.error;
-	fuse_put_request(fc, req);
-	if (!err && !nres)
-		err = -EIO;
-	if (!err) {
-		pos += nres;
-		fuse_write_update_size(inode, pos);
-		if (count == PAGE_CACHE_SIZE)
-			SetPageUptodate(page);
-	}
-	fuse_invalidate_attr(inode);
-	return err ? err : nres;
-}
-
-static int fuse_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
-{
-	struct inode *inode = mapping->host;
-	int res = 0;
-
-	if (copied)
-		res = fuse_buffered_write(file, inode, pos, copied, page);
-
-	unlock_page(page);
-	page_cache_release(page);
-	return res;
-}
-
 static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
 				    struct inode *inode, loff_t pos,
 				    size_t count)
@@ -908,6 +847,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 		pagefault_enable();
 		flush_dcache_page(page);
 
+		mark_page_accessed(page);
+
 		if (!tmp) {
 			unlock_page(page);
 			page_cache_release(page);
@@ -1559,11 +1500,14 @@ static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl)
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	int err;
 
-	if (fc->no_lock) {
+	if (fc->no_flock) {
 		err = flock_lock_file_wait(file, fl);
 	} else {
+		struct fuse_file *ff = file->private_data;
+
 		/* emulate flock with POSIX locks */
 		fl->fl_owner = (fl_owner_t) file;
+		ff->flock = true;
 		err = fuse_setlk(file, fl, 1);
 	}
 
@@ -2201,8 +2145,6 @@ static const struct address_space_operations fuse_file_aops  = {
 	.readpage	= fuse_readpage,
 	.writepage	= fuse_writepage,
 	.launder_page	= fuse_launder_page,
-	.write_begin	= fuse_write_begin,
-	.write_end	= fuse_write_end,
 	.readpages	= fuse_readpages,
 	.set_page_dirty	= __set_page_dirty_nobuffers,
 	.bmap		= fuse_bmap,
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index c6aa2d4b8517..cf6db0a93219 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -135,6 +135,9 @@ struct fuse_file {
 
 	/** Wait queue head for poll */
 	wait_queue_head_t poll_wait;
+
+	/** Has flock been performed on this file? */
+	bool flock:1;
 };
 
 /** One input argument of a request */
@@ -448,7 +451,7 @@ struct fuse_conn {
 	/** Is removexattr not implemented by fs? */
 	unsigned no_removexattr:1;
 
-	/** Are file locking primitives not implemented by fs? */
+	/** Are posix file locking primitives not implemented by fs? */
 	unsigned no_lock:1;
 
 	/** Is access not implemented by fs? */
@@ -472,6 +475,9 @@ struct fuse_conn {
 	/** Don't apply umask to creation modes */
 	unsigned dont_mask:1;
 
+	/** Are BSD file locking primitives not implemented by fs? */
+	unsigned no_flock:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 38f84cd48b67..add96f6ffda5 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -71,7 +71,7 @@ struct fuse_mount_data {
 	unsigned blksize;
 };
 
-struct fuse_forget_link *fuse_alloc_forget()
+struct fuse_forget_link *fuse_alloc_forget(void)
 {
 	return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL);
 }
@@ -809,6 +809,13 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 				fc->async_read = 1;
 			if (!(arg->flags & FUSE_POSIX_LOCKS))
 				fc->no_lock = 1;
+			if (arg->minor >= 17) {
+				if (!(arg->flags & FUSE_FLOCK_LOCKS))
+					fc->no_flock = 1;
+			} else {
+				if (!(arg->flags & FUSE_POSIX_LOCKS))
+					fc->no_flock = 1;
+			}
 			if (arg->flags & FUSE_ATOMIC_O_TRUNC)
 				fc->atomic_o_trunc = 1;
 			if (arg->minor >= 9) {
@@ -823,6 +830,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 		} else {
 			ra_pages = fc->max_read / PAGE_CACHE_SIZE;
 			fc->no_lock = 1;
+			fc->no_flock = 1;
 		}
 
 		fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
@@ -843,7 +851,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 	arg->minor = FUSE_KERNEL_MINOR_VERSION;
 	arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
 	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
-		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK;
+		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
+		FUSE_FLOCK_LOCKS;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 85c62923ee29..598646434362 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -624,9 +624,9 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
 	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
-		submit_bh(WRITE_SYNC | REQ_META, bh);
+		submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
 	else
-		submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
+		submit_bh(WRITE_FLUSH_FUA | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
 
 	if (!buffer_uptodate(bh))
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 747238cd9f96..be29858900f6 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -37,7 +37,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
 {
 	struct buffer_head *bh, *head;
 	int nr_underway = 0;
-	int write_op = REQ_META |
+	int write_op = REQ_META | REQ_PRIO |
 		(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
 
 	BUG_ON(!PageLocked(page));
@@ -225,7 +225,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	}
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
-	submit_bh(READ_SYNC | REQ_META, bh);
+	submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh);
 	if (!(flags & DIO_WAIT))
 		return 0;
 
@@ -435,7 +435,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
 	if (buffer_uptodate(first_bh))
 		goto out;
 	if (!buffer_locked(first_bh))
-		ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh);
+		ll_rw_block(READ_SYNC | REQ_META | REQ_PRIO, 1, &first_bh);
 
 	dblock++;
 	extlen--;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 3bc073a4cf82..079587e53849 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -224,7 +224,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent)
 
 	bio->bi_end_io = end_bio_io_page;
 	bio->bi_private = page;
-	submit_bio(READ_SYNC | REQ_META, bio);
+	submit_bio(READ_SYNC | REQ_META | REQ_PRIO, bio);
 	wait_on_page_locked(page);
 	bio_put(bio);
 	if (!PageUptodate(page)) {
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 42e8d23bc047..0e8bb13381e4 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -709,7 +709,7 @@ get_a_page:
 		set_buffer_uptodate(bh);
 
 	if (!buffer_uptodate(bh)) {
-		ll_rw_block(READ_META, 1, &bh);
+		ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh))
 			goto unlock_out;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index c106ca22e812..d24a9b666a23 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -344,6 +344,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	struct inode *root, *inode;
 	struct qstr str;
 	struct nls_table *nls = NULL;
+	u64 last_fs_block, last_fs_page;
 	int err;
 
 	err = -EINVAL;
@@ -399,9 +400,13 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sbi->rsrc_clump_blocks)
 		sbi->rsrc_clump_blocks = 1;
 
-	err = generic_check_addressable(sbi->alloc_blksz_shift,
-					sbi->total_blocks);
-	if (err) {
+	err = -EFBIG;
+	last_fs_block = sbi->total_blocks - 1;
+	last_fs_page = (last_fs_block << sbi->alloc_blksz_shift) >>
+			PAGE_CACHE_SHIFT;
+
+	if ((last_fs_block > (sector_t)(~0ULL) >> (sbi->alloc_blksz_shift - 9)) ||
+	    (last_fs_page > (pgoff_t)(~0ULL))) {
 		printk(KERN_ERR "hfs: filesystem size too large.\n");
 		goto out_free_vhdr;
 	}
@@ -525,8 +530,8 @@ out_close_cat_tree:
 out_close_ext_tree:
 	hfs_btree_close(sbi->ext_tree);
 out_free_vhdr:
-	kfree(sbi->s_vhdr);
-	kfree(sbi->s_backup_vhdr);
+	kfree(sbi->s_vhdr_buf);
+	kfree(sbi->s_backup_vhdr_buf);
 out_unload_nls:
 	unload_nls(sbi->nls);
 	unload_nls(nls);
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 10e515a0d452..7daf4b852d1c 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -272,9 +272,9 @@ reread:
 	return 0;
 
 out_free_backup_vhdr:
-	kfree(sbi->s_backup_vhdr);
+	kfree(sbi->s_backup_vhdr_buf);
 out_free_vhdr:
-	kfree(sbi->s_vhdr);
+	kfree(sbi->s_vhdr_buf);
 out:
 	return error;
 }
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 87b6e0421c12..ec889538e5a6 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -491,6 +491,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
 			inode->i_op = &page_symlink_inode_operations;
 			break;
 		}
+		lockdep_annotate_inode_mutex_key(inode);
 	}
 	return inode;
 }
diff --git a/fs/inode.c b/fs/inode.c
index 73920d555c88..ec7924696a13 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -848,16 +848,9 @@ struct inode *new_inode(struct super_block *sb)
 }
 EXPORT_SYMBOL(new_inode);
 
-/**
- * unlock_new_inode - clear the I_NEW state and wake up any waiters
- * @inode:	new inode to unlock
- *
- * Called when the inode is fully initialised to clear the new state of the
- * inode and wake up anyone waiting for the inode to finish initialisation.
- */
-void unlock_new_inode(struct inode *inode)
-{
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
+void lockdep_annotate_inode_mutex_key(struct inode *inode)
+{
 	if (S_ISDIR(inode->i_mode)) {
 		struct file_system_type *type = inode->i_sb->s_type;
 
@@ -873,7 +866,20 @@ void unlock_new_inode(struct inode *inode)
 					  &type->i_mutex_dir_key);
 		}
 	}
+}
+EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key);
 #endif
+
+/**
+ * unlock_new_inode - clear the I_NEW state and wake up any waiters
+ * @inode:	new inode to unlock
+ *
+ * Called when the inode is fully initialised to clear the new state of the
+ * inode and wake up anyone waiting for the inode to finish initialisation.
+ */
+void unlock_new_inode(struct inode *inode)
+{
+	lockdep_annotate_inode_mutex_key(inode);
 	spin_lock(&inode->i_lock);
 	WARN_ON(!(inode->i_state & I_NEW));
 	inode->i_state &= ~I_NEW;
diff --git a/fs/namei.c b/fs/namei.c
index 2826db35dc25..0b3138de2a3b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -721,31 +721,22 @@ static int follow_automount(struct path *path, unsigned flags,
 	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
 		return -EREMOTE;
 
-	/* We don't want to mount if someone supplied AT_NO_AUTOMOUNT
-	 * and this is the terminal part of the path.
+	/* We don't want to mount if someone's just doing a stat -
+	 * unless they're stat'ing a directory and appended a '/' to
+	 * the name.
+	 *
+	 * We do, however, want to mount if someone wants to open or
+	 * create a file of any type under the mountpoint, wants to
+	 * traverse through the mountpoint or wants to open the
+	 * mounted directory.  Also, autofs may mark negative dentries
+	 * as being automount points.  These will need the attentions
+	 * of the daemon to instantiate them before they can be used.
 	 */
-	if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_PARENT))
-		return -EISDIR; /* we actually want to stop here */
+	if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
+		     LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
+	    path->dentry->d_inode)
+		return -EISDIR;
 
-	/*
-	 * We don't want to mount if someone's just doing a stat and they've
-	 * set AT_SYMLINK_NOFOLLOW - unless they're stat'ing a directory and
-	 * appended a '/' to the name.
-	 */
-	if (!(flags & LOOKUP_FOLLOW)) {
-		/* We do, however, want to mount if someone wants to open or
-		 * create a file of any type under the mountpoint, wants to
-		 * traverse through the mountpoint or wants to open the mounted
-		 * directory.
-		 * Also, autofs may mark negative dentries as being automount
-		 * points.  These will need the attentions of the daemon to
-		 * instantiate them before they can be used.
-		 */
-		if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
-			     LOOKUP_OPEN | LOOKUP_CREATE)) &&
-		    path->dentry->d_inode)
-			return -EISDIR;
-	}
 	current->total_link_count++;
 	if (current->total_link_count >= 40)
 		return -ELOOP;
@@ -2619,6 +2610,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (!dir->i_op->rmdir)
 		return -EPERM;
 
+	dget(dentry);
 	mutex_lock(&dentry->d_inode->i_mutex);
 
 	error = -EBUSY;
@@ -2639,6 +2631,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 
 out:
 	mutex_unlock(&dentry->d_inode->i_mutex);
+	dput(dentry);
 	if (!error)
 		d_delete(dentry);
 	return error;
@@ -3028,6 +3021,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
 	if (error)
 		return error;
 
+	dget(new_dentry);
 	if (target)
 		mutex_lock(&target->i_mutex);
 
@@ -3048,6 +3042,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
 out:
 	if (target)
 		mutex_unlock(&target->i_mutex);
+	dput(new_dentry);
 	if (!error)
 		if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
 			d_move(old_dentry,new_dentry);
diff --git a/fs/namespace.c b/fs/namespace.c
index 22bfe8273c68..b4febb29d3bb 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1757,7 +1757,7 @@ static int do_loopback(struct path *path, char *old_name,
 		return err;
 	if (!old_name || !*old_name)
 		return -EINVAL;
-	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
+	err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
 	if (err)
 		return err;
 
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 1ec1a85fa71c..3e93e9a1bee1 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -56,6 +56,9 @@ enum nfs4_session_state {
 	NFS4_SESSION_DRAINING,
 };
 
+#define NFS4_RENEW_TIMEOUT		0x01
+#define NFS4_RENEW_DELEGATION_CB	0x02
+
 struct nfs4_minor_version_ops {
 	u32	minor_version;
 
@@ -225,7 +228,7 @@ struct nfs4_state_recovery_ops {
 };
 
 struct nfs4_state_maintenance_ops {
-	int (*sched_state_renewal)(struct nfs_client *, struct rpc_cred *);
+	int (*sched_state_renewal)(struct nfs_client *, struct rpc_cred *, unsigned);
 	struct rpc_cred * (*get_state_renewal_cred_locked)(struct nfs_client *);
 	int (*renew_lease)(struct nfs_client *, struct rpc_cred *);
 };
@@ -237,8 +240,6 @@ extern const struct inode_operations nfs4_dir_inode_operations;
 extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
 extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred);
-extern int nfs4_proc_async_renew(struct nfs_client *, struct rpc_cred *);
-extern int nfs4_proc_renew(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc);
@@ -349,6 +350,7 @@ extern void nfs4_close_sync(struct nfs4_state *, fmode_t);
 extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
 extern void nfs4_schedule_lease_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
+extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
 extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 extern void nfs41_handle_recall_slot(struct nfs_client *clp);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8c77039e7a81..4700fae1ada0 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3374,9 +3374,13 @@ static void nfs4_renew_done(struct rpc_task *task, void *calldata)
 
 	if (task->tk_status < 0) {
 		/* Unless we're shutting down, schedule state recovery! */
-		if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) != 0)
+		if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) == 0)
+			return;
+		if (task->tk_status != NFS4ERR_CB_PATH_DOWN) {
 			nfs4_schedule_lease_recovery(clp);
-		return;
+			return;
+		}
+		nfs4_schedule_path_down_recovery(clp);
 	}
 	do_renew_lease(clp, timestamp);
 }
@@ -3386,7 +3390,7 @@ static const struct rpc_call_ops nfs4_renew_ops = {
 	.rpc_release = nfs4_renew_release,
 };
 
-int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred)
+static int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags)
 {
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_RENEW],
@@ -3395,9 +3399,11 @@ int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred)
 	};
 	struct nfs4_renewdata *data;
 
+	if (renew_flags == 0)
+		return 0;
 	if (!atomic_inc_not_zero(&clp->cl_count))
 		return -EIO;
-	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	data = kmalloc(sizeof(*data), GFP_NOFS);
 	if (data == NULL)
 		return -ENOMEM;
 	data->client = clp;
@@ -3406,7 +3412,7 @@ int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred)
 			&nfs4_renew_ops, data);
 }
 
-int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
+static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_RENEW],
@@ -5504,11 +5510,13 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_
 	return rpc_run_task(&task_setup_data);
 }
 
-static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cred)
+static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags)
 {
 	struct rpc_task *task;
 	int ret = 0;
 
+	if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
+		return 0;
 	task = _nfs41_proc_sequence(clp, cred);
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index df8e7f3ca56d..dc484c0eae7f 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -60,6 +60,7 @@ nfs4_renew_state(struct work_struct *work)
 	struct rpc_cred *cred;
 	long lease;
 	unsigned long last, now;
+	unsigned renew_flags = 0;
 
 	ops = clp->cl_mvops->state_renewal_ops;
 	dprintk("%s: start\n", __func__);
@@ -72,18 +73,23 @@ nfs4_renew_state(struct work_struct *work)
 	last = clp->cl_last_renewal;
 	now = jiffies;
 	/* Are we close to a lease timeout? */
-	if (time_after(now, last + lease/3)) {
+	if (time_after(now, last + lease/3))
+		renew_flags |= NFS4_RENEW_TIMEOUT;
+	if (nfs_delegations_present(clp))
+		renew_flags |= NFS4_RENEW_DELEGATION_CB;
+
+	if (renew_flags != 0) {
 		cred = ops->get_state_renewal_cred_locked(clp);
 		spin_unlock(&clp->cl_lock);
 		if (cred == NULL) {
-			if (!nfs_delegations_present(clp)) {
+			if (!(renew_flags & NFS4_RENEW_DELEGATION_CB)) {
 				set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
 				goto out;
 			}
 			nfs_expire_all_delegations(clp);
 		} else {
 			/* Queue an asynchronous RENEW. */
-			ops->sched_state_renewal(clp, cred);
+			ops->sched_state_renewal(clp, cred, renew_flags);
 			put_rpccred(cred);
 			goto out_exp;
 		}
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 72ab97ef3d61..39914be40b03 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1038,6 +1038,12 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp)
 	nfs4_schedule_state_manager(clp);
 }
 
+void nfs4_schedule_path_down_recovery(struct nfs_client *clp)
+{
+	nfs_handle_cb_pathdown(clp);
+	nfs4_schedule_state_manager(clp);
+}
+
 static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
 {
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index b961ceac66b4..5b19b6aabe18 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2035,9 +2035,6 @@ static inline void nfs_initialise_sb(struct super_block *sb)
 		sb->s_blocksize = nfs_block_bits(server->wsize,
 						 &sb->s_blocksize_bits);
 
-	if (server->flags & NFS_MOUNT_NOAC)
-		sb->s_flags |= MS_SYNCHRONOUS;
-
 	sb->s_bdi = &server->backing_dev_info;
 
 	nfs_super_set_maxbytes(sb, server->maxfilesize);
@@ -2249,6 +2246,10 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	if (server->flags & NFS_MOUNT_UNSHARED)
 		compare_super = NULL;
 
+	/* -o noac implies -o sync */
+	if (server->flags & NFS_MOUNT_NOAC)
+		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+
 	/* Get a superblock - note that we may end up sharing one that already exists */
 	s = sget(fs_type, compare_super, nfs_set_super, &sb_mntdata);
 	if (IS_ERR(s)) {
@@ -2361,6 +2362,10 @@ nfs_xdev_mount(struct file_system_type *fs_type, int flags,
 	if (server->flags & NFS_MOUNT_UNSHARED)
 		compare_super = NULL;
 
+	/* -o noac implies -o sync */
+	if (server->flags & NFS_MOUNT_NOAC)
+		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+
 	/* Get a superblock - note that we may end up sharing one that already exists */
 	s = sget(&nfs_fs_type, compare_super, nfs_set_super, &sb_mntdata);
 	if (IS_ERR(s)) {
@@ -2628,6 +2633,10 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags,
 	if (server->flags & NFS4_MOUNT_UNSHARED)
 		compare_super = NULL;
 
+	/* -o noac implies -o sync */
+	if (server->flags & NFS_MOUNT_NOAC)
+		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+
 	/* Get a superblock - note that we may end up sharing one that already exists */
 	s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata);
 	if (IS_ERR(s)) {
@@ -2789,7 +2798,7 @@ static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
 		goto out_put_mnt_ns;
 
 	ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt,
-			export_path, LOOKUP_FOLLOW, &path);
+			export_path, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
 
 	nfs_referral_loop_unprotect();
 	put_mnt_ns(ns_private);
@@ -2916,6 +2925,10 @@ nfs4_xdev_mount(struct file_system_type *fs_type, int flags,
 	if (server->flags & NFS4_MOUNT_UNSHARED)
 		compare_super = NULL;
 
+	/* -o noac implies -o sync */
+	if (server->flags & NFS_MOUNT_NOAC)
+		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+
 	/* Get a superblock - note that we may end up sharing one that already exists */
 	s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata);
 	if (IS_ERR(s)) {
@@ -3003,6 +3016,10 @@ nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags,
 	if (server->flags & NFS4_MOUNT_UNSHARED)
 		compare_super = NULL;
 
+	/* -o noac implies -o sync */
+	if (server->flags & NFS_MOUNT_NOAC)
+		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+
 	/* Get a superblock - note that we may end up sharing one that already exists */
 	s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata);
 	if (IS_ERR(s)) {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index b39b37f80913..c9bd2a6b7d4b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -958,7 +958,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head
 		if (!data)
 			goto out_bad;
 		data->pagevec[0] = page;
-		nfs_write_rpcsetup(req, data, wsize, offset, desc->pg_ioflags);
+		nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags);
 		list_add(&data->list, res);
 		requests++;
 		nbytes -= len;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 25b6a887adb9..5afaa58a8630 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -877,30 +877,54 @@ struct numa_maps_private {
 	struct numa_maps md;
 };
 
-static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty)
+static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
+			unsigned long nr_pages)
 {
 	int count = page_mapcount(page);
 
-	md->pages++;
+	md->pages += nr_pages;
 	if (pte_dirty || PageDirty(page))
-		md->dirty++;
+		md->dirty += nr_pages;
 
 	if (PageSwapCache(page))
-		md->swapcache++;
+		md->swapcache += nr_pages;
 
 	if (PageActive(page) || PageUnevictable(page))
-		md->active++;
+		md->active += nr_pages;
 
 	if (PageWriteback(page))
-		md->writeback++;
+		md->writeback += nr_pages;
 
 	if (PageAnon(page))
-		md->anon++;
+		md->anon += nr_pages;
 
 	if (count > md->mapcount_max)
 		md->mapcount_max = count;
 
-	md->node[page_to_nid(page)]++;
+	md->node[page_to_nid(page)] += nr_pages;
+}
+
+static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
+		unsigned long addr)
+{
+	struct page *page;
+	int nid;
+
+	if (!pte_present(pte))
+		return NULL;
+
+	page = vm_normal_page(vma, addr, pte);
+	if (!page)
+		return NULL;
+
+	if (PageReserved(page))
+		return NULL;
+
+	nid = page_to_nid(page);
+	if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
+		return NULL;
+
+	return page;
 }
 
 static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
@@ -912,26 +936,32 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *pte;
 
 	md = walk->private;
-	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
-	do {
-		struct page *page;
-		int nid;
+	spin_lock(&walk->mm->page_table_lock);
+	if (pmd_trans_huge(*pmd)) {
+		if (pmd_trans_splitting(*pmd)) {
+			spin_unlock(&walk->mm->page_table_lock);
+			wait_split_huge_page(md->vma->anon_vma, pmd);
+		} else {
+			pte_t huge_pte = *(pte_t *)pmd;
+			struct page *page;
 
-		if (!pte_present(*pte))
-			continue;
+			page = can_gather_numa_stats(huge_pte, md->vma, addr);
+			if (page)
+				gather_stats(page, md, pte_dirty(huge_pte),
+						HPAGE_PMD_SIZE/PAGE_SIZE);
+			spin_unlock(&walk->mm->page_table_lock);
+			return 0;
+		}
+	} else {
+		spin_unlock(&walk->mm->page_table_lock);
+	}
 
-		page = vm_normal_page(md->vma, addr, *pte);
+	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	do {
+		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
 		if (!page)
 			continue;
-
-		if (PageReserved(page))
-			continue;
-
-		nid = page_to_nid(page);
-		if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
-			continue;
-
-		gather_stats(page, md, pte_dirty(*pte));
+		gather_stats(page, md, pte_dirty(*pte), 1);
 
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	pte_unmap_unlock(orig_pte, ptl);
@@ -952,7 +982,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 		return 0;
 
 	md = walk->private;
-	gather_stats(page, md, pte_dirty(*pte));
+	gather_stats(page, md, pte_dirty(*pte), 1);
 	return 0;
 }
 
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index b34bdb25490c..10b6be3ca280 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -355,7 +355,7 @@ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
 	 * resolution (think about autofs) and thus deadlocks could arise.
 	 */
 	if (cmds == Q_QUOTAON) {
-		ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW, &path);
+		ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
 		if (ret)
 			pathp = ERR_PTR(ret);
 		else
diff --git a/fs/stat.c b/fs/stat.c
index ba5316ffac61..78a3aa83c7ea 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -81,8 +81,6 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 
 	if (!(flag & AT_SYMLINK_NOFOLLOW))
 		lookup_flags |= LOOKUP_FOLLOW;
-	if (flag & AT_NO_AUTOMOUNT)
-		lookup_flags |= LOOKUP_NO_AUTOMOUNT;
 	if (flag & AT_EMPTY_PATH)
 		lookup_flags |= LOOKUP_EMPTY;
 
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index 45174b534377..feb361e252ac 100644
--- a/fs/ubifs/debug.h
+++ b/fs/ubifs/debug.h
@@ -335,9 +335,9 @@ void dbg_debugfs_exit_fs(struct ubifs_info *c);
 #define DBGKEY(key)  ((char *)(key))
 #define DBGKEY1(key) ((char *)(key))
 
-#define ubifs_dbg_msg(fmt, ...) do {               \
-	if (0)                                     \
-		pr_debug(fmt "\n", ##__VA_ARGS__); \
+#define ubifs_dbg_msg(fmt, ...) do {                        \
+	if (0)                                              \
+		printk(KERN_DEBUG fmt "\n", ##__VA_ARGS__); \
 } while (0)
 
 #define dbg_dump_stack()
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 75bb316529dd..427a4e82a588 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -16,44 +16,53 @@
 # Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 #
 
-ccflags-y := -I$(src) -I$(src)/linux-2.6
-ccflags-$(CONFIG_XFS_DEBUG) += -g
+ccflags-y += -I$(src)			# needed for trace events
 
-XFS_LINUX := linux-2.6
+ccflags-$(CONFIG_XFS_DEBUG) += -g
 
 obj-$(CONFIG_XFS_FS)		+= xfs.o
 
-xfs-y				+= linux-2.6/xfs_trace.o
-
-xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix quota/, \
-				   xfs_dquot.o \
-				   xfs_dquot_item.o \
-				   xfs_trans_dquot.o \
-				   xfs_qm_syscalls.o \
-				   xfs_qm_bhv.o \
-				   xfs_qm.o)
-xfs-$(CONFIG_XFS_QUOTA)		+= linux-2.6/xfs_quotaops.o
-
-ifeq ($(CONFIG_XFS_QUOTA),y)
-xfs-$(CONFIG_PROC_FS)		+= quota/xfs_qm_stats.o
-endif
-
-xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o
-xfs-$(CONFIG_XFS_POSIX_ACL)	+= $(XFS_LINUX)/xfs_acl.o
-xfs-$(CONFIG_PROC_FS)		+= $(XFS_LINUX)/xfs_stats.o
-xfs-$(CONFIG_SYSCTL)		+= $(XFS_LINUX)/xfs_sysctl.o
-xfs-$(CONFIG_COMPAT)		+= $(XFS_LINUX)/xfs_ioctl32.o
+# this one should be compiled first, as the tracing macros can easily blow up
+xfs-y				+= xfs_trace.o
 
+# highlevel code
+xfs-y				+= xfs_aops.o \
+				   xfs_bit.o \
+				   xfs_buf.o \
+				   xfs_dfrag.o \
+				   xfs_discard.o \
+				   xfs_error.o \
+				   xfs_export.o \
+				   xfs_file.o \
+				   xfs_filestream.o \
+				   xfs_fsops.o \
+				   xfs_fs_subr.o \
+				   xfs_globals.o \
+				   xfs_iget.o \
+				   xfs_ioctl.o \
+				   xfs_iomap.o \
+				   xfs_iops.o \
+				   xfs_itable.o \
+				   xfs_message.o \
+				   xfs_mru_cache.o \
+				   xfs_super.o \
+				   xfs_sync.o \
+				   xfs_xattr.o \
+				   xfs_rename.o \
+				   xfs_rw.o \
+				   xfs_utils.o \
+				   xfs_vnodeops.o \
+				   kmem.o \
+				   uuid.o
 
+# code shared with libxfs
 xfs-y				+= xfs_alloc.o \
 				   xfs_alloc_btree.o \
 				   xfs_attr.o \
 				   xfs_attr_leaf.o \
-				   xfs_bit.o \
 				   xfs_bmap.o \
 				   xfs_bmap_btree.o \
 				   xfs_btree.o \
-				   xfs_buf_item.o \
 				   xfs_da_btree.o \
 				   xfs_dir2.o \
 				   xfs_dir2_block.o \
@@ -61,49 +70,37 @@ xfs-y				+= xfs_alloc.o \
 				   xfs_dir2_leaf.o \
 				   xfs_dir2_node.o \
 				   xfs_dir2_sf.o \
-				   xfs_error.o \
-				   xfs_extfree_item.o \
-				   xfs_filestream.o \
-				   xfs_fsops.o \
 				   xfs_ialloc.o \
 				   xfs_ialloc_btree.o \
-				   xfs_iget.o \
 				   xfs_inode.o \
-				   xfs_inode_item.o \
-				   xfs_iomap.o \
-				   xfs_itable.o \
-				   xfs_dfrag.o \
-				   xfs_log.o \
-				   xfs_log_cil.o \
 				   xfs_log_recover.o \
 				   xfs_mount.o \
-				   xfs_mru_cache.o \
-				   xfs_rename.o \
-				   xfs_trans.o \
+				   xfs_trans.o
+
+# low-level transaction/log code
+xfs-y				+= xfs_log.o \
+				   xfs_log_cil.o \
+				   xfs_buf_item.o \
+				   xfs_extfree_item.o \
+				   xfs_inode_item.o \
 				   xfs_trans_ail.o \
 				   xfs_trans_buf.o \
 				   xfs_trans_extfree.o \
 				   xfs_trans_inode.o \
-				   xfs_utils.o \
-				   xfs_vnodeops.o \
-				   xfs_rw.o
-
-# Objects in linux/
-xfs-y				+= $(addprefix $(XFS_LINUX)/, \
-				   kmem.o \
-				   xfs_aops.o \
-				   xfs_buf.o \
-				   xfs_discard.o \
-				   xfs_export.o \
-				   xfs_file.o \
-				   xfs_fs_subr.o \
-				   xfs_globals.o \
-				   xfs_ioctl.o \
-				   xfs_iops.o \
-				   xfs_message.o \
-				   xfs_super.o \
-				   xfs_sync.o \
-				   xfs_xattr.o)
 
-# Objects in support/
-xfs-y				+= support/uuid.o
+# optional features
+xfs-$(CONFIG_XFS_QUOTA)		+= xfs_dquot.o \
+				   xfs_dquot_item.o \
+				   xfs_trans_dquot.o \
+				   xfs_qm_syscalls.o \
+				   xfs_qm_bhv.o \
+				   xfs_qm.o \
+				   xfs_quotaops.o
+ifeq ($(CONFIG_XFS_QUOTA),y)
+xfs-$(CONFIG_PROC_FS)		+= xfs_qm_stats.o
+endif
+xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o
+xfs-$(CONFIG_XFS_POSIX_ACL)	+= xfs_acl.o
+xfs-$(CONFIG_PROC_FS)		+= xfs_stats.o
+xfs-$(CONFIG_SYSCTL)		+= xfs_sysctl.o
+xfs-$(CONFIG_COMPAT)		+= xfs_ioctl32.o
diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/kmem.c
index a907de565db3..a907de565db3 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/kmem.c
diff --git a/fs/xfs/linux-2.6/kmem.h b/fs/xfs/kmem.h
index f7c8f7a9ea6d..f7c8f7a9ea6d 100644
--- a/fs/xfs/linux-2.6/kmem.h
+++ b/fs/xfs/kmem.h
diff --git a/fs/xfs/linux-2.6/mrlock.h b/fs/xfs/mrlock.h
index ff6a19873e5c..ff6a19873e5c 100644
--- a/fs/xfs/linux-2.6/mrlock.h
+++ b/fs/xfs/mrlock.h
diff --git a/fs/xfs/linux-2.6/time.h b/fs/xfs/time.h
index 387e695a184c..387e695a184c 100644
--- a/fs/xfs/linux-2.6/time.h
+++ b/fs/xfs/time.h
diff --git a/fs/xfs/support/uuid.c b/fs/xfs/uuid.c
index b83f76b6d410..b83f76b6d410 100644
--- a/fs/xfs/support/uuid.c
+++ b/fs/xfs/uuid.c
diff --git a/fs/xfs/support/uuid.h b/fs/xfs/uuid.h
index 4732d71262cc..4732d71262cc 100644
--- a/fs/xfs/support/uuid.h
+++ b/fs/xfs/uuid.h
diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h
index 53ec3ea9a625..d8b11b7f94aa 100644
--- a/fs/xfs/xfs.h
+++ b/fs/xfs/xfs.h
@@ -24,5 +24,6 @@
 #define XFS_BUF_LOCK_TRACKING 1
 #endif
 
-#include <linux-2.6/xfs_linux.h>
+#include "xfs_linux.h"
+
 #endif	/* __XFS_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/xfs_acl.c
index b6c4b3795c4a..b6c4b3795c4a 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/xfs_aops.c
index 63e971e2b837..8c37dde4c521 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1300,6 +1300,7 @@ xfs_end_io_direct_write(
 	bool			is_async)
 {
 	struct xfs_ioend	*ioend = iocb->private;
+	struct inode		*inode = ioend->io_inode;
 
 	/*
 	 * blockdev_direct_IO can return an error even after the I/O
@@ -1331,7 +1332,7 @@ xfs_end_io_direct_write(
 	}
 
 	/* XXX: probably should move into the real I/O completion handler */
-	inode_dio_done(ioend->io_inode);
+	inode_dio_done(inode);
 }
 
 STATIC ssize_t
diff --git a/fs/xfs/linux-2.6/xfs_aops.h b/fs/xfs/xfs_aops.h
index 71f721e1a71f..71f721e1a71f 100644
--- a/fs/xfs/linux-2.6/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/xfs_buf.c
index c57836dc778f..c57836dc778f 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/xfs_buf.h
index 620972b8094d..620972b8094d 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index cac2ecfa6746..ef43fce519a1 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -629,7 +629,7 @@ xfs_buf_item_push(
  * the xfsbufd to get this buffer written. We have to unlock the buffer
  * to allow the xfsbufd to write it, too.
  */
-STATIC void
+STATIC bool
 xfs_buf_item_pushbuf(
 	struct xfs_log_item	*lip)
 {
@@ -643,6 +643,7 @@ xfs_buf_item_pushbuf(
 
 	xfs_buf_delwri_promote(bp);
 	xfs_buf_relse(bp);
+	return true;
 }
 
 STATIC void
diff --git a/fs/xfs/linux-2.6/xfs_discard.c b/fs/xfs/xfs_discard.c
index 244e797dae32..244e797dae32 100644
--- a/fs/xfs/linux-2.6/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
diff --git a/fs/xfs/linux-2.6/xfs_discard.h b/fs/xfs/xfs_discard.h
index 344879aea646..344879aea646 100644
--- a/fs/xfs/linux-2.6/xfs_discard.h
+++ b/fs/xfs/xfs_discard.h
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index db62959bed13..db62959bed13 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
diff --git a/fs/xfs/quota/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index 34b7e945dbfa..34b7e945dbfa 100644
--- a/fs/xfs/quota/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
diff --git a/fs/xfs/quota/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index 9e0e2fa3f2c8..bb3f71d236d2 100644
--- a/fs/xfs/quota/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -183,13 +183,14 @@ xfs_qm_dqunpin_wait(
  * search the buffer cache can be a time consuming thing, and AIL lock is a
  * spinlock.
  */
-STATIC void
+STATIC bool
 xfs_qm_dquot_logitem_pushbuf(
 	struct xfs_log_item	*lip)
 {
 	struct xfs_dq_logitem	*qlip = DQUOT_ITEM(lip);
 	struct xfs_dquot	*dqp = qlip->qli_dquot;
 	struct xfs_buf		*bp;
+	bool			ret = true;
 
 	ASSERT(XFS_DQ_IS_LOCKED(dqp));
 
@@ -201,17 +202,20 @@ xfs_qm_dquot_logitem_pushbuf(
 	if (completion_done(&dqp->q_flush) ||
 	    !(lip->li_flags & XFS_LI_IN_AIL)) {
 		xfs_dqunlock(dqp);
-		return;
+		return true;
 	}
 
 	bp = xfs_incore(dqp->q_mount->m_ddev_targp, qlip->qli_format.qlf_blkno,
 			dqp->q_mount->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK);
 	xfs_dqunlock(dqp);
 	if (!bp)
-		return;
+		return true;
 	if (XFS_BUF_ISDELAYWRITE(bp))
 		xfs_buf_delwri_promote(bp);
+	if (xfs_buf_ispinned(bp))
+		ret = false;
 	xfs_buf_relse(bp);
+	return ret;
 }
 
 /*
diff --git a/fs/xfs/quota/xfs_dquot_item.h b/fs/xfs/xfs_dquot_item.h
index 5acae2ada70b..5acae2ada70b 100644
--- a/fs/xfs/quota/xfs_dquot_item.h
+++ b/fs/xfs/xfs_dquot_item.h
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/xfs_export.c
index 75e5d322e48f..75e5d322e48f 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/xfs_export.c
diff --git a/fs/xfs/linux-2.6/xfs_export.h b/fs/xfs/xfs_export.h
index 3272b6ae7a35..3272b6ae7a35 100644
--- a/fs/xfs/linux-2.6/xfs_export.h
+++ b/fs/xfs/xfs_export.h
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/xfs_file.c
index 7f7b42469ea7..7f7b42469ea7 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/xfs_file.c
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/xfs_fs_subr.c
index ed88ed16811c..ed88ed16811c 100644
--- a/fs/xfs/linux-2.6/xfs_fs_subr.c
+++ b/fs/xfs/xfs_fs_subr.c
diff --git a/fs/xfs/linux-2.6/xfs_globals.c b/fs/xfs/xfs_globals.c
index 76e81cff70b9..76e81cff70b9 100644
--- a/fs/xfs/linux-2.6/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 588406dc6a35..836ad80d4f2b 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -708,13 +708,14 @@ xfs_inode_item_committed(
  * marked delayed write. If that's the case, we'll promote it and that will
  * allow the caller to write the buffer by triggering the xfsbufd to run.
  */
-STATIC void
+STATIC bool
 xfs_inode_item_pushbuf(
 	struct xfs_log_item	*lip)
 {
 	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
 	struct xfs_inode	*ip = iip->ili_inode;
 	struct xfs_buf		*bp;
+	bool			ret = true;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
 
@@ -725,7 +726,7 @@ xfs_inode_item_pushbuf(
 	if (completion_done(&ip->i_flush) ||
 	    !(lip->li_flags & XFS_LI_IN_AIL)) {
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-		return;
+		return true;
 	}
 
 	bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno,
@@ -733,10 +734,13 @@ xfs_inode_item_pushbuf(
 
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 	if (!bp)
-		return;
+		return true;
 	if (XFS_BUF_ISDELAYWRITE(bp))
 		xfs_buf_delwri_promote(bp);
+	if (xfs_buf_ispinned(bp))
+		ret = false;
 	xfs_buf_relse(bp);
+	return ret;
 }
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index f7ce7debe14c..f7ce7debe14c 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index d56173b34a2a..d56173b34a2a 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index 54e623bfbb85..54e623bfbb85 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h
index 80f4060e8970..80f4060e8970 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.h
+++ b/fs/xfs/xfs_ioctl32.h
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/xfs_iops.c
index b9c172b3fbbe..673704fab748 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -70,9 +70,8 @@ xfs_synchronize_times(
 }
 
 /*
- * If the linux inode is valid, mark it dirty.
- * Used when committing a dirty inode into a transaction so that
- * the inode will get written back by the linux code
+ * If the linux inode is valid, mark it dirty, else mark the dirty state
+ * in the XFS inode to make sure we pick it up when reclaiming the inode.
  */
 void
 xfs_mark_inode_dirty_sync(
@@ -82,6 +81,10 @@ xfs_mark_inode_dirty_sync(
 
 	if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
 		mark_inode_dirty_sync(inode);
+	else {
+		barrier();
+		ip->i_update_core = 1;
+	}
 }
 
 void
@@ -92,6 +95,11 @@ xfs_mark_inode_dirty(
 
 	if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
 		mark_inode_dirty(inode);
+	else {
+		barrier();
+		ip->i_update_core = 1;
+	}
+
 }
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_iops.h b/fs/xfs/xfs_iops.h
index ef41c92ce66e..ef41c92ce66e 100644
--- a/fs/xfs/linux-2.6/xfs_iops.h
+++ b/fs/xfs/xfs_iops.h
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/xfs_linux.h
index d42f814e4d35..828662f70d64 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -32,13 +32,12 @@
 # define XFS_BIG_INUMS	0
 #endif
 
-#include <xfs_types.h>
+#include "xfs_types.h"
 
-#include <kmem.h>
-#include <mrlock.h>
-#include <time.h>
-
-#include <support/uuid.h>
+#include "kmem.h"
+#include "mrlock.h"
+#include "time.h"
+#include "uuid.h"
 
 #include <linux/semaphore.h>
 #include <linux/mm.h>
@@ -69,6 +68,8 @@
 #include <linux/ctype.h>
 #include <linux/writeback.h>
 #include <linux/capability.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
 #include <linux/list_sort.h>
 
 #include <asm/page.h>
@@ -78,14 +79,14 @@
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
-#include <xfs_vnode.h>
-#include <xfs_stats.h>
-#include <xfs_sysctl.h>
-#include <xfs_iops.h>
-#include <xfs_aops.h>
-#include <xfs_super.h>
-#include <xfs_buf.h>
-#include <xfs_message.h>
+#include "xfs_vnode.h"
+#include "xfs_stats.h"
+#include "xfs_sysctl.h"
+#include "xfs_iops.h"
+#include "xfs_aops.h"
+#include "xfs_super.h"
+#include "xfs_buf.h"
+#include "xfs_message.h"
 
 #ifdef __BIG_ENDIAN
 #define XFS_NATIVE_HOST 1
diff --git a/fs/xfs/linux-2.6/xfs_message.c b/fs/xfs/xfs_message.c
index bd672def95ac..bd672def95ac 100644
--- a/fs/xfs/linux-2.6/xfs_message.c
+++ b/fs/xfs/xfs_message.c
diff --git a/fs/xfs/linux-2.6/xfs_message.h b/fs/xfs/xfs_message.h
index 7fb7ea007672..7fb7ea007672 100644
--- a/fs/xfs/linux-2.6/xfs_message.h
+++ b/fs/xfs/xfs_message.h
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/xfs_qm.c
index 9a0aa76facdf..9a0aa76facdf 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
diff --git a/fs/xfs/quota/xfs_qm.h b/fs/xfs/xfs_qm.h
index 43b9abe1052c..43b9abe1052c 100644
--- a/fs/xfs/quota/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index a0a829addca9..a0a829addca9 100644
--- a/fs/xfs/quota/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
diff --git a/fs/xfs/quota/xfs_qm_stats.c b/fs/xfs/xfs_qm_stats.c
index 8671a0b32644..8671a0b32644 100644
--- a/fs/xfs/quota/xfs_qm_stats.c
+++ b/fs/xfs/xfs_qm_stats.c
diff --git a/fs/xfs/quota/xfs_qm_stats.h b/fs/xfs/xfs_qm_stats.h
index 5b964fc0dc09..5b964fc0dc09 100644
--- a/fs/xfs/quota/xfs_qm_stats.h
+++ b/fs/xfs/xfs_qm_stats.h
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 609246f42e6c..609246f42e6c 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
diff --git a/fs/xfs/quota/xfs_quota_priv.h b/fs/xfs/xfs_quota_priv.h
index 94a3d927d716..94a3d927d716 100644
--- a/fs/xfs/quota/xfs_quota_priv.h
+++ b/fs/xfs/xfs_quota_priv.h
diff --git a/fs/xfs/linux-2.6/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 29b9d642e93d..7e76f537abb7 100644
--- a/fs/xfs/linux-2.6/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -25,7 +25,7 @@
 #include "xfs_trans.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
-#include "quota/xfs_qm.h"
+#include "xfs_qm.h"
 #include <linux/quota.h>
 
 
diff --git a/fs/xfs/linux-2.6/xfs_stats.c b/fs/xfs/xfs_stats.c
index 76fdc5861932..76fdc5861932 100644
--- a/fs/xfs/linux-2.6/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
diff --git a/fs/xfs/linux-2.6/xfs_stats.h b/fs/xfs/xfs_stats.h
index 736854b1ca1a..736854b1ca1a 100644
--- a/fs/xfs/linux-2.6/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/xfs_super.c
index 9a72dda58bd0..5cf06b85fd9d 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -356,6 +356,8 @@ xfs_parseargs(
 			mp->m_flags |= XFS_MOUNT_DELAYLOG;
 		} else if (!strcmp(this_char, MNTOPT_NODELAYLOG)) {
 			mp->m_flags &= ~XFS_MOUNT_DELAYLOG;
+			xfs_warn(mp,
+	"nodelaylog is deprecated and will be removed in Linux 3.3");
 		} else if (!strcmp(this_char, MNTOPT_DISCARD)) {
 			mp->m_flags |= XFS_MOUNT_DISCARD;
 		} else if (!strcmp(this_char, MNTOPT_NODISCARD)) {
@@ -877,33 +879,17 @@ xfs_log_inode(
 	struct xfs_trans	*tp;
 	int			error;
 
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
 	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
-
 	if (error) {
 		xfs_trans_cancel(tp, 0);
-		/* we need to return with the lock hold shared */
-		xfs_ilock(ip, XFS_ILOCK_SHARED);
 		return error;
 	}
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-	/*
-	 * Note - it's possible that we might have pushed ourselves out of the
-	 * way during trans_reserve which would flush the inode.  But there's
-	 * no guarantee that the inode buffer has actually gone out yet (it's
-	 * delwri).  Plus the buffer could be pinned anyway if it's part of
-	 * an inode in another recent transaction.  So we play it safe and
-	 * fire off the transaction anyway.
-	 */
-	xfs_trans_ijoin(tp, ip);
+	xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	error = xfs_trans_commit(tp, 0);
-	xfs_ilock_demote(ip, XFS_ILOCK_EXCL);
-
-	return error;
+	return xfs_trans_commit(tp, 0);
 }
 
 STATIC int
@@ -918,7 +904,9 @@ xfs_fs_write_inode(
 	trace_xfs_write_inode(ip);
 
 	if (XFS_FORCED_SHUTDOWN(mp))
-		return XFS_ERROR(EIO);
+		return -XFS_ERROR(EIO);
+	if (!ip->i_update_core)
+		return 0;
 
 	if (wbc->sync_mode == WB_SYNC_ALL) {
 		/*
@@ -929,12 +917,10 @@ xfs_fs_write_inode(
 		 * of synchronous log foces dramatically.
 		 */
 		xfs_ioend_wait(ip);
-		xfs_ilock(ip, XFS_ILOCK_SHARED);
-		if (ip->i_update_core) {
-			error = xfs_log_inode(ip);
-			if (error)
-				goto out_unlock;
-		}
+		error = xfs_log_inode(ip);
+		if (error)
+			goto out;
+		return 0;
 	} else {
 		/*
 		 * We make this non-blocking if the inode is contended, return
@@ -1666,24 +1652,13 @@ xfs_init_workqueues(void)
 	 */
 	xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_CPU_INTENSIVE, 8);
 	if (!xfs_syncd_wq)
-		goto out;
-
-	xfs_ail_wq = alloc_workqueue("xfsail", WQ_CPU_INTENSIVE, 8);
-	if (!xfs_ail_wq)
-		goto out_destroy_syncd;
-
+		return -ENOMEM;
 	return 0;
-
-out_destroy_syncd:
-	destroy_workqueue(xfs_syncd_wq);
-out:
-	return -ENOMEM;
 }
 
 STATIC void
 xfs_destroy_workqueues(void)
 {
-	destroy_workqueue(xfs_ail_wq);
 	destroy_workqueue(xfs_syncd_wq);
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/xfs_super.h
index 50a3266c999e..50a3266c999e 100644
--- a/fs/xfs/linux-2.6/xfs_super.h
+++ b/fs/xfs/xfs_super.h
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/xfs_sync.c
index 4604f90f86a3..4604f90f86a3 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/xfs_sync.h
index 941202e7ac6e..941202e7ac6e 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/xfs_sync.h
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index ee2d2adaa438..ee2d2adaa438 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index b9937d450f8e..b9937d450f8e 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.h
+++ b/fs/xfs/xfs_sysctl.h
diff --git a/fs/xfs/linux-2.6/xfs_trace.c b/fs/xfs/xfs_trace.c
index 88d25d4aa56e..9010ce885e6a 100644
--- a/fs/xfs/linux-2.6/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -43,8 +43,8 @@
 #include "xfs_quota.h"
 #include "xfs_iomap.h"
 #include "xfs_aops.h"
-#include "quota/xfs_dquot_item.h"
-#include "quota/xfs_dquot.h"
+#include "xfs_dquot_item.h"
+#include "xfs_dquot.h"
 #include "xfs_log_recover.h"
 #include "xfs_inode_item.h"
 
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/xfs_trace.h
index 690fc7a7bd72..690fc7a7bd72 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 06a9759b6352..53597f4db9b5 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -350,7 +350,7 @@ typedef struct xfs_item_ops {
 	void (*iop_unlock)(xfs_log_item_t *);
 	xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t);
 	void (*iop_push)(xfs_log_item_t *);
-	void (*iop_pushbuf)(xfs_log_item_t *);
+	bool (*iop_pushbuf)(xfs_log_item_t *);
 	void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
 } xfs_item_ops_t;
 
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index c15aa29fa169..3a1e7ca54c2d 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -28,8 +28,6 @@
 #include "xfs_trans_priv.h"
 #include "xfs_error.h"
 
-struct workqueue_struct	*xfs_ail_wq;	/* AIL workqueue */
-
 #ifdef DEBUG
 /*
  * Check that the list is sorted as it should be.
@@ -356,16 +354,10 @@ xfs_ail_delete(
 	xfs_trans_ail_cursor_clear(ailp, lip);
 }
 
-/*
- * xfs_ail_worker does the work of pushing on the AIL. It will requeue itself
- * to run at a later time if there is more work to do to complete the push.
- */
-STATIC void
-xfs_ail_worker(
-	struct work_struct	*work)
+static long
+xfsaild_push(
+	struct xfs_ail		*ailp)
 {
-	struct xfs_ail		*ailp = container_of(to_delayed_work(work),
-					struct xfs_ail, xa_work);
 	xfs_mount_t		*mp = ailp->xa_mount;
 	struct xfs_ail_cursor	cur;
 	xfs_log_item_t		*lip;
@@ -427,8 +419,13 @@ xfs_ail_worker(
 
 		case XFS_ITEM_PUSHBUF:
 			XFS_STATS_INC(xs_push_ail_pushbuf);
-			IOP_PUSHBUF(lip);
-			ailp->xa_last_pushed_lsn = lsn;
+
+			if (!IOP_PUSHBUF(lip)) {
+				stuck++;
+				flush_log = 1;
+			} else {
+				ailp->xa_last_pushed_lsn = lsn;
+			}
 			push_xfsbufd = 1;
 			break;
 
@@ -440,7 +437,6 @@ xfs_ail_worker(
 
 		case XFS_ITEM_LOCKED:
 			XFS_STATS_INC(xs_push_ail_locked);
-			ailp->xa_last_pushed_lsn = lsn;
 			stuck++;
 			break;
 
@@ -501,20 +497,6 @@ out_done:
 		/* We're past our target or empty, so idle */
 		ailp->xa_last_pushed_lsn = 0;
 
-		/*
-		 * We clear the XFS_AIL_PUSHING_BIT first before checking
-		 * whether the target has changed. If the target has changed,
-		 * this pushes the requeue race directly onto the result of the
-		 * atomic test/set bit, so we are guaranteed that either the
-		 * the pusher that changed the target or ourselves will requeue
-		 * the work (but not both).
-		 */
-		clear_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags);
-		smp_rmb();
-		if (XFS_LSN_CMP(ailp->xa_target, target) == 0 ||
-		    test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags))
-			return;
-
 		tout = 50;
 	} else if (XFS_LSN_CMP(lsn, target) >= 0) {
 		/*
@@ -537,9 +519,30 @@ out_done:
 		tout = 20;
 	}
 
-	/* There is more to do, requeue us.  */
-	queue_delayed_work(xfs_syncd_wq, &ailp->xa_work,
-					msecs_to_jiffies(tout));
+	return tout;
+}
+
+static int
+xfsaild(
+	void		*data)
+{
+	struct xfs_ail	*ailp = data;
+	long		tout = 0;	/* milliseconds */
+
+	while (!kthread_should_stop()) {
+		if (tout && tout <= 20)
+			__set_current_state(TASK_KILLABLE);
+		else
+			__set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(tout ?
+				 msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT);
+
+		try_to_freeze();
+
+		tout = xfsaild_push(ailp);
+	}
+
+	return 0;
 }
 
 /*
@@ -574,8 +577,9 @@ xfs_ail_push(
 	 */
 	smp_wmb();
 	xfs_trans_ail_copy_lsn(ailp, &ailp->xa_target, &threshold_lsn);
-	if (!test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags))
-		queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, 0);
+	smp_wmb();
+
+	wake_up_process(ailp->xa_task);
 }
 
 /*
@@ -813,9 +817,18 @@ xfs_trans_ail_init(
 	INIT_LIST_HEAD(&ailp->xa_ail);
 	INIT_LIST_HEAD(&ailp->xa_cursors);
 	spin_lock_init(&ailp->xa_lock);
-	INIT_DELAYED_WORK(&ailp->xa_work, xfs_ail_worker);
+
+	ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s",
+			ailp->xa_mount->m_fsname);
+	if (IS_ERR(ailp->xa_task))
+		goto out_free_ailp;
+
 	mp->m_ail = ailp;
 	return 0;
+
+out_free_ailp:
+	kmem_free(ailp);
+	return ENOMEM;
 }
 
 void
@@ -824,6 +837,6 @@ xfs_trans_ail_destroy(
 {
 	struct xfs_ail	*ailp = mp->m_ail;
 
-	cancel_delayed_work_sync(&ailp->xa_work);
+	kthread_stop(ailp->xa_task);
 	kmem_free(ailp);
 }
diff --git a/fs/xfs/quota/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 4d00ee67792d..4d00ee67792d 100644
--- a/fs/xfs/quota/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 212946b97239..22750b5e4a8f 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -64,23 +64,17 @@ struct xfs_ail_cursor {
  */
 struct xfs_ail {
 	struct xfs_mount	*xa_mount;
+	struct task_struct	*xa_task;
 	struct list_head	xa_ail;
 	xfs_lsn_t		xa_target;
 	struct list_head	xa_cursors;
 	spinlock_t		xa_lock;
-	struct delayed_work	xa_work;
 	xfs_lsn_t		xa_last_pushed_lsn;
-	unsigned long		xa_flags;
 };
 
-#define XFS_AIL_PUSHING_BIT	0
-
 /*
  * From xfs_trans_ail.c
  */
-
-extern struct workqueue_struct	*xfs_ail_wq;	/* AIL workqueue */
-
 void	xfs_trans_ail_update_bulk(struct xfs_ail *ailp,
 				struct xfs_ail_cursor *cur,
 				struct xfs_log_item **log_items, int nr_items,
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/xfs_vnode.h
index 7c220b4227bc..7c220b4227bc 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/xfs_vnode.h
diff --git a/fs/xfs/linux-2.6/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 87d3e03878c8..87d3e03878c8 100644
--- a/fs/xfs/linux-2.6/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c