159 files changed, 1251 insertions, 891 deletions

diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 46ce357ca1a..410ffd6ceb5 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 3c173fcc2c5..62857a810a7 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 8bb5507e822..e3c03db3c78 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 b6c8ed20519..aded79fcd5c 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 feef6cdc1fd..c70251d47ed 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/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 475f9c597cb..326dc08d3e3 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -39,27 +39,17 @@
 
 /* #define DEBUG */
 
-#ifdef DEBUG
-#define DPRINTK(fmt, args...)				\
-do {							\
-	printk(KERN_DEBUG "pid %d: %s: " fmt "\n",	\
-		current->pid, __func__, ##args);	\
-} while (0)
-#else
-#define DPRINTK(fmt, args...) do {} while (0)
-#endif
-
-#define AUTOFS_WARN(fmt, args...)			\
-do {							\
+#define DPRINTK(fmt, ...)				\
+	pr_debug("pid %d: %s: " fmt "\n",		\
+		current->pid, __func__, ##__VA_ARGS__)
+
+#define AUTOFS_WARN(fmt, ...)				\
 	printk(KERN_WARNING "pid %d: %s: " fmt "\n",	\
-		current->pid, __func__, ##args);	\
-} while (0)
+		current->pid, __func__, ##__VA_ARGS__)
 
-#define AUTOFS_ERROR(fmt, args...)			\
-do {							\
+#define AUTOFS_ERROR(fmt, ...)				\
 	printk(KERN_ERR "pid %d: %s: " fmt "\n",	\
-		current->pid, __func__, ##args);	\
-} while (0)
+		current->pid, __func__, ##__VA_ARGS__)
 
 /* Unified info structure.  This is pointed to by both the dentry and
    inode structures.  Each file in the filesystem has an instance of this
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 25435987d6a..e1fbdeef85d 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -104,7 +104,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	size_t pktsz;
 
 	DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d",
-		wq->wait_queue_token, wq->name.len, wq->name.name, type);
+		(unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, type);
 
 	memset(&pkt,0,sizeof pkt); /* For security reasons */
 
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 54b8c28bebc..720d885e8dc 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -474,17 +474,22 @@ befs_follow_link(struct dentry *dentry, struct nameidata *nd)
 		befs_data_stream *data = &befs_ino->i_data.ds;
 		befs_off_t len = data->size;
 
-		befs_debug(sb, "Follow long symlink");
-
-		link = kmalloc(len, GFP_NOFS);
-		if (!link) {
-			link = ERR_PTR(-ENOMEM);
-		} else if (befs_read_lsymlink(sb, data, link, len) != len) {
-			kfree(link);
-			befs_error(sb, "Failed to read entire long symlink");
+		if (len == 0) {
+			befs_error(sb, "Long symlink with illegal length");
 			link = ERR_PTR(-EIO);
 		} else {
-			link[len - 1] = '\0';
+			befs_debug(sb, "Follow long symlink");
+
+			link = kmalloc(len, GFP_NOFS);
+			if (!link) {
+				link = ERR_PTR(-ENOMEM);
+			} else if (befs_read_lsymlink(sb, data, link, len) != len) {
+				kfree(link);
+				befs_error(sb, "Failed to read entire long symlink");
+				link = ERR_PTR(-EIO);
+			} else {
+				link[len - 1] = '\0';
+			}
 		}
 	} else {
 		link = befs_ino->i_data.symlink;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index ff77262e887..95f786ec7f0 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 502b9e98867..d9f99a16edd 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/ctree.h b/fs/btrfs/ctree.h
index 0469263e327..03912c5c6f4 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1415,17 +1415,15 @@ void btrfs_set_##name(struct extent_buffer *eb, type *s, u##bits val);
 #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits)		\
 static inline u##bits btrfs_##name(struct extent_buffer *eb)		\
 {									\
-	type *p = kmap_atomic(eb->first_page, KM_USER0);		\
+	type *p = page_address(eb->first_page);				\
 	u##bits res = le##bits##_to_cpu(p->member);			\
-	kunmap_atomic(p, KM_USER0);					\
 	return res;							\
 }									\
 static inline void btrfs_set_##name(struct extent_buffer *eb,		\
 				    u##bits val)			\
 {									\
-	type *p = kmap_atomic(eb->first_page, KM_USER0);		\
+	type *p = page_address(eb->first_page);				\
 	p->member = cpu_to_le##bits(val);				\
-	kunmap_atomic(p, KM_USER0);					\
 }
 
 #define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits)		\
@@ -2367,8 +2365,8 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
 int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path);
 int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
 int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf);
-int btrfs_drop_snapshot(struct btrfs_root *root,
-			struct btrfs_block_rsv *block_rsv, int update_ref);
+void btrfs_drop_snapshot(struct btrfs_root *root,
+			 struct btrfs_block_rsv *block_rsv, int update_ref);
 int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct extent_buffer *node,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 66bac226944..f5be06a2462 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1782,6 +1782,9 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 
 
 		for (i = 0; i < multi->num_stripes; i++, stripe++) {
+			if (!stripe->dev->can_discard)
+				continue;
+
 			ret = btrfs_issue_discard(stripe->dev->bdev,
 						  stripe->physical,
 						  stripe->length);
@@ -1789,11 +1792,16 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 				discarded_bytes += stripe->length;
 			else if (ret != -EOPNOTSUPP)
 				break;
+
+			/*
+			 * Just in case we get back EOPNOTSUPP for some reason,
+			 * just ignore the return value so we don't screw up
+			 * people calling discard_extent.
+			 */
+			ret = 0;
 		}
 		kfree(multi);
 	}
-	if (discarded_bytes && ret == -EOPNOTSUPP)
-		ret = 0;
 
 	if (actual_bytes)
 		*actual_bytes = discarded_bytes;
@@ -6269,8 +6277,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
  * also make sure backrefs for the shared block and all lower level
  * blocks are properly updated.
  */
-int btrfs_drop_snapshot(struct btrfs_root *root,
-			struct btrfs_block_rsv *block_rsv, int update_ref)
+void btrfs_drop_snapshot(struct btrfs_root *root,
+			 struct btrfs_block_rsv *block_rsv, int update_ref)
 {
 	struct btrfs_path *path;
 	struct btrfs_trans_handle *trans;
@@ -6283,13 +6291,16 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	int level;
 
 	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
+	if (!path) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	wc = kzalloc(sizeof(*wc), GFP_NOFS);
 	if (!wc) {
 		btrfs_free_path(path);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto out;
 	}
 
 	trans = btrfs_start_transaction(tree_root, 0);
@@ -6318,7 +6329,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		path->lowest_level = 0;
 		if (ret < 0) {
 			err = ret;
-			goto out;
+			goto out_free;
 		}
 		WARN_ON(ret > 0);
 
@@ -6425,11 +6436,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		free_extent_buffer(root->commit_root);
 		kfree(root);
 	}
-out:
+out_free:
 	btrfs_end_transaction_throttle(trans, tree_root);
 	kfree(wc);
 	btrfs_free_path(path);
-	return err;
+out:
+	if (err)
+		btrfs_std_error(root->fs_info, err);
+	return;
 }
 
 /*
@@ -6720,6 +6734,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	struct btrfs_space_info *space_info;
 	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
 	struct btrfs_device *device;
+	u64 min_free;
+	u64 dev_min = 1;
+	u64 dev_nr = 0;
+	int index;
 	int full = 0;
 	int ret = 0;
 
@@ -6729,8 +6747,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	if (!block_group)
 		return -1;
 
+	min_free = btrfs_block_group_used(&block_group->item);
+
 	/* no bytes used, we're good */
-	if (!btrfs_block_group_used(&block_group->item))
+	if (!min_free)
 		goto out;
 
 	space_info = block_group->space_info;
@@ -6746,10 +6766,9 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	 * all of the extents from this block group.  If we can, we're good
 	 */
 	if ((space_info->total_bytes != block_group->key.offset) &&
-	   (space_info->bytes_used + space_info->bytes_reserved +
-	    space_info->bytes_pinned + space_info->bytes_readonly +
-	    btrfs_block_group_used(&block_group->item) <
-	    space_info->total_bytes)) {
+	    (space_info->bytes_used + space_info->bytes_reserved +
+	     space_info->bytes_pinned + space_info->bytes_readonly +
+	     min_free < space_info->total_bytes)) {
 		spin_unlock(&space_info->lock);
 		goto out;
 	}
@@ -6766,9 +6785,31 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	if (full)
 		goto out;
 
+	/*
+	 * index:
+	 *      0: raid10
+	 *      1: raid1
+	 *      2: dup
+	 *      3: raid0
+	 *      4: single
+	 */
+	index = get_block_group_index(block_group);
+	if (index == 0) {
+		dev_min = 4;
+		/* Divide by 2 */
+		min_free >>= 1;
+	} else if (index == 1) {
+		dev_min = 2;
+	} else if (index == 2) {
+		/* Multiply by 2 */
+		min_free <<= 1;
+	} else if (index == 3) {
+		dev_min = fs_devices->rw_devices;
+		do_div(min_free, dev_min);
+	}
+
 	mutex_lock(&root->fs_info->chunk_mutex);
 	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
-		u64 min_free = btrfs_block_group_used(&block_group->item);
 		u64 dev_offset;
 
 		/*
@@ -6779,7 +6820,11 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 			ret = find_free_dev_extent(NULL, device, min_free,
 						   &dev_offset, NULL);
 			if (!ret)
+				dev_nr++;
+
+			if (dev_nr >= dev_min)
 				break;
+
 			ret = -1;
 		}
 	}
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index b910694f61e..a1cb7821bec 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 658d66959ab..e4e57d59edb 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -150,6 +150,8 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 	spin_lock(&root->fs_info->defrag_inodes_lock);
 	if (!BTRFS_I(inode)->in_defrag)
 		__btrfs_add_inode_defrag(inode, defrag);
+	else
+		kfree(defrag);
 	spin_unlock(&root->fs_info->defrag_inodes_lock);
 	return 0;
 }
@@ -1034,11 +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;
@@ -1059,7 +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;
@@ -1073,12 +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,
@@ -1090,10 +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;
@@ -1162,6 +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 /
@@ -1204,7 +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);
@@ -1221,12 +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
@@ -1336,6 +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;
@@ -1384,6 +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);
@@ -1638,11 +1652,15 @@ static long btrfs_fallocate(struct file *file, int mode,
 
 	cur_offset = alloc_start;
 	while (1) {
+		u64 actual_end;
+
 		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
 				      alloc_end - cur_offset, 0);
 		BUG_ON(IS_ERR_OR_NULL(em));
 		last_byte = min(extent_map_end(em), alloc_end);
+		actual_end = min_t(u64, extent_map_end(em), offset + len);
 		last_byte = (last_byte + mask) & ~mask;
+
 		if (em->block_start == EXTENT_MAP_HOLE ||
 		    (cur_offset >= inode->i_size &&
 		     !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
@@ -1655,6 +1673,16 @@ static long btrfs_fallocate(struct file *file, int mode,
 				free_extent_map(em);
 				break;
 			}
+		} else if (actual_end > inode->i_size &&
+			   !(mode & FALLOC_FL_KEEP_SIZE)) {
+			/*
+			 * We didn't need to allocate any more space, but we
+			 * still extended the size of the file so we need to
+			 * update i_size.
+			 */
+			inode->i_ctime = CURRENT_TIME;
+			i_size_write(inode, actual_end);
+			btrfs_ordered_update_i_size(inode, actual_end, NULL);
 		}
 		free_extent_map(em);
 
@@ -1797,6 +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);
@@ -1804,10 +1837,14 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
 		}
 	}
 
-	if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
-		return -EINVAL;
-	if (offset > inode->i_sb->s_maxbytes)
-		return -EINVAL;
+	if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) {
+		offset = -EINVAL;
+		goto out;
+	}
+	if (offset > inode->i_sb->s_maxbytes) {
+		offset = -EINVAL;
+		goto out;
+	}
 
 	/* Special lock needed here? */
 	if (offset != file->f_pos) {
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6377713f639..41ac927401d 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;
@@ -1168,9 +1172,9 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 		div64_u64(extent_bytes, (sizeof(struct btrfs_free_space)));
 }
 
-static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
-			      struct btrfs_free_space *info, u64 offset,
-			      u64 bytes)
+static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
+				       struct btrfs_free_space *info,
+				       u64 offset, u64 bytes)
 {
 	unsigned long start, count;
 
@@ -1181,6 +1185,13 @@ static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
 	bitmap_clear(info->bitmap, start, count);
 
 	info->bytes -= bytes;
+}
+
+static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
+			      struct btrfs_free_space *info, u64 offset,
+			      u64 bytes)
+{
+	__bitmap_clear_bits(ctl, info, offset, bytes);
 	ctl->free_space -= bytes;
 }
 
@@ -1984,7 +1995,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
 		return 0;
 
 	ret = search_start;
-	bitmap_clear_bits(ctl, entry, ret, bytes);
+	__bitmap_clear_bits(ctl, entry, ret, bytes);
 
 	return ret;
 }
@@ -2039,7 +2050,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 				continue;
 			}
 		} else {
-
 			ret = entry->offset;
 
 			entry->offset += bytes;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 15fceefbca0..b2d004ad66a 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:
@@ -7354,11 +7364,15 @@ static int btrfs_set_page_dirty(struct page *page)
 static int btrfs_permission(struct inode *inode, int mask)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	umode_t mode = inode->i_mode;
 
-	if (btrfs_root_readonly(root) && (mask & MAY_WRITE))
-		return -EROFS;
-	if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE))
-		return -EACCES;
+	if (mask & MAY_WRITE &&
+	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
+		if (btrfs_root_readonly(root))
+			return -EROFS;
+		if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY)
+			return -EACCES;
+	}
 	return generic_permission(inode, mask);
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 7cf01334994..538f65a79ec 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2177,6 +2177,11 @@ 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 +2225,16 @@ 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) {
@@ -2313,7 +2328,12 @@ 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;
@@ -2321,14 +2341,21 @@ 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,
@@ -2425,7 +2452,6 @@ 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 7dc36fab4af..e24b7964a15 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/tree-log.c b/fs/btrfs/tree-log.c
index babee65f8ed..786639fca06 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -799,14 +799,15 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				  struct extent_buffer *eb, int slot,
 				  struct btrfs_key *key)
 {
-	struct inode *dir;
-	int ret;
 	struct btrfs_inode_ref *ref;
+	struct btrfs_dir_item *di;
+	struct inode *dir;
 	struct inode *inode;
-	char *name;
-	int namelen;
 	unsigned long ref_ptr;
 	unsigned long ref_end;
+	char *name;
+	int namelen;
+	int ret;
 	int search_done = 0;
 
 	/*
@@ -909,6 +910,25 @@ again:
 	}
 	btrfs_release_path(path);
 
+	/* look for a conflicting sequence number */
+	di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir),
+					 btrfs_inode_ref_index(eb, ref),
+					 name, namelen, 0);
+	if (di && !IS_ERR(di)) {
+		ret = drop_one_dir_item(trans, root, path, dir, di);
+		BUG_ON(ret);
+	}
+	btrfs_release_path(path);
+
+	/* look for a conflicing name */
+	di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir),
+				   name, namelen, 0);
+	if (di && !IS_ERR(di)) {
+		ret = drop_one_dir_item(trans, root, path, dir, di);
+		BUG_ON(ret);
+	}
+	btrfs_release_path(path);
+
 insert:
 	/* insert our name */
 	ret = btrfs_add_link(trans, dir, inode, name, namelen, 0,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 53875ae73ad..f2a4cc79da6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -142,6 +142,7 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 	unsigned long limit;
 	unsigned long last_waited = 0;
 	int force_reg = 0;
+	int sync_pending = 0;
 	struct blk_plug plug;
 
 	/*
@@ -229,6 +230,22 @@ loop_lock:
 
 		BUG_ON(atomic_read(&cur->bi_cnt) == 0);
 
+		/*
+		 * if we're doing the sync list, record that our
+		 * plug has some sync requests on it
+		 *
+		 * If we're doing the regular list and there are
+		 * sync requests sitting around, unplug before
+		 * we add more
+		 */
+		if (pending_bios == &device->pending_sync_bios) {
+			sync_pending = 1;
+		} else if (sync_pending) {
+			blk_finish_plug(&plug);
+			blk_start_plug(&plug);
+			sync_pending = 0;
+		}
+
 		submit_bio(cur->bi_rw, cur);
 		num_run++;
 		batch_run++;
@@ -500,6 +517,9 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 			fs_devices->rw_devices--;
 		}
 
+		if (device->can_discard)
+			fs_devices->num_can_discard--;
+
 		new_device = kmalloc(sizeof(*new_device), GFP_NOFS);
 		BUG_ON(!new_device);
 		memcpy(new_device, device, sizeof(*new_device));
@@ -508,6 +528,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 		new_device->bdev = NULL;
 		new_device->writeable = 0;
 		new_device->in_fs_metadata = 0;
+		new_device->can_discard = 0;
 		list_replace_rcu(&device->dev_list, &new_device->dev_list);
 
 		call_rcu(&device->rcu, free_device);
@@ -547,6 +568,7 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 				fmode_t flags, void *holder)
 {
+	struct request_queue *q;
 	struct block_device *bdev;
 	struct list_head *head = &fs_devices->devices;
 	struct btrfs_device *device;
@@ -603,6 +625,12 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 			seeding = 0;
 		}
 
+		q = bdev_get_queue(bdev);
+		if (blk_queue_discard(q)) {
+			device->can_discard = 1;
+			fs_devices->num_can_discard++;
+		}
+
 		device->bdev = bdev;
 		device->in_fs_metadata = 0;
 		device->mode = flags;
@@ -835,6 +863,7 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
 
 	max_hole_start = search_start;
 	max_hole_size = 0;
+	hole_size = 0;
 
 	if (search_start >= search_end) {
 		ret = -ENOSPC;
@@ -917,7 +946,14 @@ next:
 		cond_resched();
 	}
 
-	hole_size = search_end- search_start;
+	/*
+	 * At this point, search_start should be the end of
+	 * allocated dev extents, and when shrinking the device,
+	 * search_end may be smaller than search_start.
+	 */
+	if (search_end > search_start)
+		hole_size = search_end - search_start;
+
 	if (hole_size > max_hole_size) {
 		max_hole_start = search_start;
 		max_hole_size = hole_size;
@@ -1543,6 +1579,7 @@ error:
 
 int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 {
+	struct request_queue *q;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
 	struct block_device *bdev;
@@ -1612,6 +1649,9 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 
 	lock_chunks(root);
 
+	q = bdev_get_queue(bdev);
+	if (blk_queue_discard(q))
+		device->can_discard = 1;
 	device->writeable = 1;
 	device->work.func = pending_bios_fn;
 	generate_random_uuid(device->uuid);
@@ -1647,6 +1687,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	root->fs_info->fs_devices->num_devices++;
 	root->fs_info->fs_devices->open_devices++;
 	root->fs_info->fs_devices->rw_devices++;
+	if (device->can_discard)
+		root->fs_info->fs_devices->num_can_discard++;
 	root->fs_info->fs_devices->total_rw_bytes += device->total_bytes;
 
 	if (!blk_queue_nonrot(bdev_get_queue(bdev)))
@@ -2413,9 +2455,10 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 			total_avail = device->total_bytes - device->bytes_used;
 		else
 			total_avail = 0;
-		/* avail is off by max(alloc_start, 1MB), but that is the same
-		 * for all devices, so it doesn't hurt the sorting later on
-		 */
+
+		/* If there is no space on this device, skip it. */
+		if (total_avail == 0)
+			continue;
 
 		ret = find_free_dev_extent(trans, device,
 					   max_stripe_size * dev_stripes,
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 7c12d61ae7a..6d866db4e17 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -48,6 +48,7 @@ struct btrfs_device {
 	int writeable;
 	int in_fs_metadata;
 	int missing;
+	int can_discard;
 
 	spinlock_t io_lock;
 
@@ -104,6 +105,7 @@ struct btrfs_fs_devices {
 	u64 rw_devices;
 	u64 missing_devices;
 	u64 total_rw_bytes;
+	u64 num_can_discard;
 	struct block_device *latest_bdev;
 
 	/* all of the devices in the FS, protected by a mutex
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index d733b9cfea3..69565e5fc6a 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 fee028b5332..86c59e16ba7 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 d47c5ec7fb1..88bacaf385d 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/cifs_debug.c b/fs/cifs/cifs_debug.c
index 2fe3cf13b2e..6d40656e1e2 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -176,7 +176,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 
 #ifdef CONFIG_CIFS_STATS2
 			seq_printf(m, " In Send: %d In MaxReq Wait: %d",
-				atomic_read(&server->inSend),
+				atomic_read(&server->in_send),
 				atomic_read(&server->num_waiters));
 #endif
 
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 21de1d6d584..d0f59faefb7 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -991,24 +991,6 @@ struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
 	return pntsd;
 }
 
-static int set_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, __u16 fid,
-		struct cifs_ntsd *pnntsd, u32 acllen)
-{
-	int xid, rc;
-	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
-
-	if (IS_ERR(tlink))
-		return PTR_ERR(tlink);
-
-	xid = GetXid();
-	rc = CIFSSMBSetCIFSACL(xid, tlink_tcon(tlink), fid, pnntsd, acllen);
-	FreeXid(xid);
-	cifs_put_tlink(tlink);
-
-	cFYI(DBG2, "SetCIFSACL rc = %d", rc);
-	return rc;
-}
-
 static int set_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, const char *path,
 		struct cifs_ntsd *pnntsd, u32 acllen)
 {
@@ -1047,18 +1029,10 @@ int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
 				struct inode *inode, const char *path)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-	struct cifsFileInfo *open_file;
-	int rc;
 
 	cFYI(DBG2, "set ACL for %s from mode 0x%x", path, inode->i_mode);
 
-	open_file = find_readable_file(CIFS_I(inode), true);
-	if (!open_file)
-		return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen);
-
-	rc = set_cifs_acl_by_fid(cifs_sb, open_file->netfid, pnntsd, acllen);
-	cifsFileInfo_put(open_file);
-	return rc;
+	return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen);
 }
 
 /* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index e76bfeb6826..30acd22147e 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 f93eb948d07..54b8f1e7da9 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/cifsfs.h b/fs/cifs/cifsfs.h
index cb71dc1f94d..95da8027983 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -125,5 +125,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 extern const struct export_operations cifs_export_ops;
 #endif /* CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "1.74"
+#define CIFS_VERSION   "1.75"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 38ce6d44b14..95dad9d14cf 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -291,7 +291,7 @@ struct TCP_Server_Info {
 	struct fscache_cookie   *fscache; /* client index cache cookie */
 #endif
 #ifdef CONFIG_CIFS_STATS2
-	atomic_t inSend; /* requests trying to send */
+	atomic_t in_send; /* requests trying to send */
 	atomic_t num_waiters;   /* blocked waiting to get in sendrecv */
 #endif
 };
@@ -672,12 +672,54 @@ struct mid_q_entry {
 	bool multiEnd:1;	/* both received */
 };
 
-struct oplock_q_entry {
-	struct list_head qhead;
-	struct inode *pinode;
-	struct cifs_tcon *tcon;
-	__u16 netfid;
-};
+/*	Make code in transport.c a little cleaner by moving
+	update of optional stats into function below */
+#ifdef CONFIG_CIFS_STATS2
+
+static inline void cifs_in_send_inc(struct TCP_Server_Info *server)
+{
+	atomic_inc(&server->in_send);
+}
+
+static inline void cifs_in_send_dec(struct TCP_Server_Info *server)
+{
+	atomic_dec(&server->in_send);
+}
+
+static inline void cifs_num_waiters_inc(struct TCP_Server_Info *server)
+{
+	atomic_inc(&server->num_waiters);
+}
+
+static inline void cifs_num_waiters_dec(struct TCP_Server_Info *server)
+{
+	atomic_dec(&server->num_waiters);
+}
+
+static inline void cifs_save_when_sent(struct mid_q_entry *mid)
+{
+	mid->when_sent = jiffies;
+}
+#else
+static inline void cifs_in_send_inc(struct TCP_Server_Info *server)
+{
+}
+static inline void cifs_in_send_dec(struct TCP_Server_Info *server)
+{
+}
+
+static inline void cifs_num_waiters_inc(struct TCP_Server_Info *server)
+{
+}
+
+static inline void cifs_num_waiters_dec(struct TCP_Server_Info *server)
+{
+}
+
+static inline void cifs_save_when_sent(struct mid_q_entry *mid)
+{
+}
+#endif
 
 /* for pending dnotify requests */
 struct dir_notify_req {
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index aac37d99a48..a80f7bd97b9 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 80c2e3add3a..f4af4cc3750 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;
@@ -2878,7 +2878,8 @@ cleanup_volume_info_contents(struct smb_vol *volume_info)
 	kfree(volume_info->username);
 	kzfree(volume_info->password);
 	kfree(volume_info->UNC);
-	kfree(volume_info->UNCip);
+	if (volume_info->UNCip != volume_info->UNC + 2)
+		kfree(volume_info->UNCip);
 	kfree(volume_info->domainname);
 	kfree(volume_info->iocharset);
 	kfree(volume_info->prepath);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index ae576fbb514..72d448bf96c 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -105,8 +105,8 @@ cifs_bp_rename_retry:
 	}
 	rcu_read_unlock();
 	if (namelen != dfsplen || read_seqretry(&rename_lock, seq)) {
-		cERROR(1, "did not end path lookup where expected namelen is %d",
-			namelen);
+		cFYI(1, "did not end path lookup where expected. namelen=%d "
+			"dfsplen=%d", namelen, dfsplen);
 		/* presumably this is only possible if racing with a rename
 		of one of the parent directories  (we can not lock the dentries
 		above us to prevent this, but retrying should be harmless) */
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index c1b9c4b1073..10ca6b2c26b 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -266,15 +266,11 @@ static int wait_for_free_request(struct TCP_Server_Info *server,
 	while (1) {
 		if (atomic_read(&server->inFlight) >= cifs_max_pending) {
 			spin_unlock(&GlobalMid_Lock);
-#ifdef CONFIG_CIFS_STATS2
-			atomic_inc(&server->num_waiters);
-#endif
+			cifs_num_waiters_inc(server);
 			wait_event(server->request_q,
 				   atomic_read(&server->inFlight)
 				     < cifs_max_pending);
-#ifdef CONFIG_CIFS_STATS2
-			atomic_dec(&server->num_waiters);
-#endif
+			cifs_num_waiters_dec(server);
 			spin_lock(&GlobalMid_Lock);
 		} else {
 			if (server->tcpStatus == CifsExiting) {
@@ -381,15 +377,13 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov,
 	mid->callback = callback;
 	mid->callback_data = cbdata;
 	mid->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
-	atomic_inc(&server->inSend);
-#endif
+
+	cifs_in_send_inc(server);
 	rc = smb_sendv(server, iov, nvec);
-#ifdef CONFIG_CIFS_STATS2
-	atomic_dec(&server->inSend);
-	mid->when_sent = jiffies;
-#endif
+	cifs_in_send_dec(server);
+	cifs_save_when_sent(mid);
 	mutex_unlock(&server->srv_mutex);
+
 	if (rc)
 		goto out_err;
 
@@ -575,14 +569,10 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	}
 
 	midQ->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
-	atomic_inc(&ses->server->inSend);
-#endif
+	cifs_in_send_inc(ses->server);
 	rc = smb_sendv(ses->server, iov, n_vec);
-#ifdef CONFIG_CIFS_STATS2
-	atomic_dec(&ses->server->inSend);
-	midQ->when_sent = jiffies;
-#endif
+	cifs_in_send_dec(ses->server);
+	cifs_save_when_sent(midQ);
 
 	mutex_unlock(&ses->server->srv_mutex);
 
@@ -703,14 +693,11 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	}
 
 	midQ->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
-	atomic_inc(&ses->server->inSend);
-#endif
+
+	cifs_in_send_inc(ses->server);
 	rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
-#ifdef CONFIG_CIFS_STATS2
-	atomic_dec(&ses->server->inSend);
-	midQ->when_sent = jiffies;
-#endif
+	cifs_in_send_dec(ses->server);
+	cifs_save_when_sent(midQ);
 	mutex_unlock(&ses->server->srv_mutex);
 
 	if (rc < 0)
@@ -843,14 +830,10 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 	}
 
 	midQ->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
-	atomic_inc(&ses->server->inSend);
-#endif
+	cifs_in_send_inc(ses->server);
 	rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
-#ifdef CONFIG_CIFS_STATS2
-	atomic_dec(&ses->server->inSend);
-	midQ->when_sent = jiffies;
-#endif
+	cifs_in_send_dec(ses->server);
+	cifs_save_when_sent(midQ);
 	mutex_unlock(&ses->server->srv_mutex);
 
 	if (rc < 0) {
diff --git a/fs/compat.c b/fs/compat.c
index 0b48d018e38..58b1da45989 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/compat_ioctl.c b/fs/compat_ioctl.c
index 8be086e9abe..51352de88ef 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1003,6 +1003,7 @@ COMPATIBLE_IOCTL(PPPIOCCONNECT)
 COMPATIBLE_IOCTL(PPPIOCDISCONN)
 COMPATIBLE_IOCTL(PPPIOCATTCHAN)
 COMPATIBLE_IOCTL(PPPIOCGCHAN)
+COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS)
 /* PPPOX */
 COMPATIBLE_IOCTL(PPPOEIOCSFWD)
 COMPATIBLE_IOCTL(PPPOEIOCDFWD)
diff --git a/fs/ecryptfs/Kconfig b/fs/ecryptfs/Kconfig
index 1cd6d9d3e29..cc16562654d 100644
--- a/fs/ecryptfs/Kconfig
+++ b/fs/ecryptfs/Kconfig
@@ -1,6 +1,6 @@
 config ECRYPT_FS
 	tristate "eCrypt filesystem layer support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL && KEYS && CRYPTO
+	depends on EXPERIMENTAL && KEYS && CRYPTO && (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n)
 	select CRYPTO_ECB
 	select CRYPTO_CBC
 	select CRYPTO_MD5
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 08a2b52bf56..ac1ad48c237 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1973,7 +1973,7 @@ pki_encrypt_session_key(struct key *auth_tok_key,
 {
 	struct ecryptfs_msg_ctx *msg_ctx = NULL;
 	char *payload = NULL;
-	size_t payload_len;
+	size_t payload_len = 0;
 	struct ecryptfs_message *msg;
 	int rc;
 
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 9f1bb747d77..b4a6befb121 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -175,6 +175,7 @@ enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig,
        ecryptfs_opt_encrypted_view, ecryptfs_opt_fnek_sig,
        ecryptfs_opt_fn_cipher, ecryptfs_opt_fn_cipher_key_bytes,
        ecryptfs_opt_unlink_sigs, ecryptfs_opt_mount_auth_tok_only,
+       ecryptfs_opt_check_dev_ruid,
        ecryptfs_opt_err };
 
 static const match_table_t tokens = {
@@ -191,6 +192,7 @@ static const match_table_t tokens = {
 	{ecryptfs_opt_fn_cipher_key_bytes, "ecryptfs_fn_key_bytes=%u"},
 	{ecryptfs_opt_unlink_sigs, "ecryptfs_unlink_sigs"},
 	{ecryptfs_opt_mount_auth_tok_only, "ecryptfs_mount_auth_tok_only"},
+	{ecryptfs_opt_check_dev_ruid, "ecryptfs_check_dev_ruid"},
 	{ecryptfs_opt_err, NULL}
 };
 
@@ -236,6 +238,7 @@ static void ecryptfs_init_mount_crypt_stat(
  * ecryptfs_parse_options
  * @sb: The ecryptfs super block
  * @options: The options passed to the kernel
+ * @check_ruid: set to 1 if device uid should be checked against the ruid
  *
  * Parse mount options:
  * debug=N 	   - ecryptfs_verbosity level for debug output
@@ -251,7 +254,8 @@ static void ecryptfs_init_mount_crypt_stat(
  *
  * Returns zero on success; non-zero on error
  */
-static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options)
+static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
+				  uid_t *check_ruid)
 {
 	char *p;
 	int rc = 0;
@@ -276,6 +280,8 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options)
 	char *cipher_key_bytes_src;
 	char *fn_cipher_key_bytes_src;
 
+	*check_ruid = 0;
+
 	if (!options) {
 		rc = -EINVAL;
 		goto out;
@@ -380,6 +386,9 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options)
 			mount_crypt_stat->flags |=
 				ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY;
 			break;
+		case ecryptfs_opt_check_dev_ruid:
+			*check_ruid = 1;
+			break;
 		case ecryptfs_opt_err:
 		default:
 			printk(KERN_WARNING
@@ -475,6 +484,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	const char *err = "Getting sb failed";
 	struct inode *inode;
 	struct path path;
+	uid_t check_ruid;
 	int rc;
 
 	sbi = kmem_cache_zalloc(ecryptfs_sb_info_cache, GFP_KERNEL);
@@ -483,7 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	rc = ecryptfs_parse_options(sbi, raw_data);
+	rc = ecryptfs_parse_options(sbi, raw_data, &check_ruid);
 	if (rc) {
 		err = "Error parsing options";
 		goto out;
@@ -521,6 +531,15 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 			"known incompatibilities\n");
 		goto out_free;
 	}
+
+	if (check_ruid && path.dentry->d_inode->i_uid != current_uid()) {
+		rc = -EPERM;
+		printk(KERN_ERR "Mount of device (uid: %d) not owned by "
+		       "requested user (uid: %d)\n",
+		       path.dentry->d_inode->i_uid, current_uid());
+		goto out_free;
+	}
+
 	ecryptfs_set_superblock_lower(s, path.dentry->d_sb);
 	s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
 	s->s_blocksize = path.dentry->d_sb->s_blocksize;
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 85d43096311..3745f7c2b9c 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -39,15 +39,16 @@
 int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data,
 			 loff_t offset, size_t size)
 {
-	struct ecryptfs_inode_info *inode_info;
+	struct file *lower_file;
 	mm_segment_t fs_save;
 	ssize_t rc;
 
-	inode_info = ecryptfs_inode_to_private(ecryptfs_inode);
-	BUG_ON(!inode_info->lower_file);
+	lower_file = ecryptfs_inode_to_private(ecryptfs_inode)->lower_file;
+	if (!lower_file)
+		return -EIO;
 	fs_save = get_fs();
 	set_fs(get_ds());
-	rc = vfs_write(inode_info->lower_file, data, size, &offset);
+	rc = vfs_write(lower_file, data, size, &offset);
 	set_fs(fs_save);
 	mark_inode_dirty_sync(ecryptfs_inode);
 	return rc;
@@ -225,15 +226,16 @@ out:
 int ecryptfs_read_lower(char *data, loff_t offset, size_t size,
 			struct inode *ecryptfs_inode)
 {
-	struct ecryptfs_inode_info *inode_info =
-		ecryptfs_inode_to_private(ecryptfs_inode);
+	struct file *lower_file;
 	mm_segment_t fs_save;
 	ssize_t rc;
 
-	BUG_ON(!inode_info->lower_file);
+	lower_file = ecryptfs_inode_to_private(ecryptfs_inode)->lower_file;
+	if (!lower_file)
+		return -EIO;
 	fs_save = get_fs();
 	set_fs(get_ds());
-	rc = vfs_read(inode_info->lower_file, data, size, &offset);
+	rc = vfs_read(lower_file, data, size, &offset);
 	set_fs(fs_save);
 	return rc;
 }
diff --git a/fs/exec.c b/fs/exec.c
index da80612a35f..25dcbe5fc35 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1459,6 +1459,23 @@ static int do_execve_common(const char *filename,
 	struct files_struct *displaced;
 	bool clear_in_exec;
 	int retval;
+	const struct cred *cred = current_cred();
+
+	/*
+	 * We move the actual failure in case of RLIMIT_NPROC excess from
+	 * set*uid() to execve() because too many poorly written programs
+	 * don't check setuid() return code.  Here we additionally recheck
+	 * whether NPROC limit is still exceeded.
+	 */
+	if ((current->flags & PF_NPROC_EXCEEDED) &&
+	    atomic_read(&cred->user->processes) > rlimit(RLIMIT_NPROC)) {
+		retval = -EAGAIN;
+		goto out_ret;
+	}
+
+	/* We're below the limit (still or again), so we don't want to make
+	 * further execve() calls fail. */
+	current->flags &= ~PF_NPROC_EXCEEDED;
 
 	retval = unshare_files(&displaced);
 	if (retval)
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 04da6acde85..12661e1deed 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 6e18a0b7750..0629e09f651 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)
@@ -2209,9 +2210,11 @@ static int ext3_symlink (struct inode * dir,
 		/*
 		 * For non-fast symlinks, we just allocate inode and put it on
 		 * orphan list in the first transaction => we need bitmap,
-		 * group descriptor, sb, inode block, quota blocks.
+		 * group descriptor, sb, inode block, quota blocks, and
+		 * possibly selinux xattr blocks.
 		 */
-		credits = 4 + EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
+		credits = 4 + EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+			  EXT3_XATTR_TRANS_BLOCKS;
 	} else {
 		/*
 		 * Fast symlink. We have to add entry to directory
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e717dfd2f2b..b7d7bd0f066 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/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index bb85757689b..5802fa1dab1 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -289,10 +289,10 @@ static inline int ext4_should_order_data(struct inode *inode)
 
 static inline int ext4_should_writeback_data(struct inode *inode)
 {
-	if (!S_ISREG(inode->i_mode))
-		return 0;
 	if (EXT4_JOURNAL(inode) == NULL)
 		return 1;
+	if (!S_ISREG(inode->i_mode))
+		return 0;
 	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
 		return 0;
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index b8602cde5b5..0962642119c 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -800,12 +800,17 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retry:
-	if (rw == READ && ext4_should_dioread_nolock(inode))
+	if (rw == READ && ext4_should_dioread_nolock(inode)) {
+		if (unlikely(!list_empty(&ei->i_completed_io_list))) {
+			mutex_lock(&inode->i_mutex);
+			ext4_flush_completed_IO(inode);
+			mutex_unlock(&inode->i_mutex);
+		}
 		ret = __blockdev_direct_IO(rw, iocb, inode,
 				 inode->i_sb->s_bdev, iov,
 				 offset, nr_segs,
 				 ext4_get_block, NULL, NULL, 0);
-	else {
+	} else {
 		ret = blockdev_direct_IO(rw, iocb, inode, iov,
 				 offset, nr_segs, ext4_get_block);
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d47264cafee..986e2388f03 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -120,6 +120,9 @@ void ext4_evict_inode(struct inode *inode)
 	int err;
 
 	trace_ext4_evict_inode(inode);
+
+	ext4_ioend_wait(inode);
+
 	if (inode->i_nlink) {
 		/*
 		 * When journalling data dirty buffers are tracked only in the
@@ -644,7 +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;
@@ -983,6 +986,8 @@ static int ext4_journalled_write_end(struct file *file,
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
 
+	BUG_ON(!ext4_handle_valid(handle));
+
 	if (copied < len) {
 		if (!PageUptodate(page))
 			copied = 0;
@@ -1283,7 +1288,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 			else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
 				err = ext4_bio_write_page(&io_submit, page,
 							  len, mpd->wbc);
-			else
+			else if (buffer_uninit(page_bufs)) {
+				ext4_set_bh_endio(page_bufs, inode);
+				err = block_write_full_page_endio(page,
+					noalloc_get_block_write,
+					mpd->wbc, ext4_end_io_buffer_write);
+			} else
 				err = block_write_full_page(page,
 					noalloc_get_block_write, mpd->wbc);
 
@@ -1699,6 +1709,8 @@ static int __ext4_journalled_writepage(struct page *page,
 		goto out;
 	}
 
+	BUG_ON(!ext4_handle_valid(handle));
+
 	ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
 				do_journal_get_write_access);
 
@@ -2668,8 +2680,15 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
 		goto out;
 	}
 
-	io_end->flag = EXT4_IO_END_UNWRITTEN;
+	/*
+	 * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now,
+	 * but being more careful is always safe for the future change.
+	 */
 	inode = io_end->inode;
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		io_end->flag |= EXT4_IO_END_UNWRITTEN;
+		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+	}
 
 	/* Add the io_end to per-inode completed io list*/
 	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
@@ -3279,7 +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 565a154e22d..1c924faeb6c 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)
@@ -2253,9 +2254,11 @@ static int ext4_symlink(struct inode *dir,
 		/*
 		 * For non-fast symlinks, we just allocate inode and put it on
 		 * orphan list in the first transaction => we need bitmap,
-		 * group descriptor, sb, inode block, quota blocks.
+		 * group descriptor, sb, inode block, quota blocks, and
+		 * possibly selinux xattr blocks.
 		 */
-		credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
+		credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+			  EXT4_XATTR_TRANS_BLOCKS;
 	} else {
 		/*
 		 * Fast symlink. We have to add entry to directory
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 430c401d089..92f38ee13f8 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);
@@ -334,8 +350,10 @@ submit_and_retry:
 	if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
 	    (io_end->pages[io_end->num_io_pages-1] != io_page))
 		goto submit_and_retry;
-	if (buffer_uninit(bh))
-		io->io_end->flag |= EXT4_IO_END_UNWRITTEN;
+	if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		io_end->flag |= EXT4_IO_END_UNWRITTEN;
+		atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+	}
 	io->io_end->size += bh->b_size;
 	io->io_next_block++;
 	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4687fea0c00..44d0c8db223 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -919,7 +919,6 @@ static void ext4_i_callback(struct rcu_head *head)
 
 static void ext4_destroy_inode(struct inode *inode)
 {
-	ext4_ioend_wait(inode);
 	if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
 		ext4_msg(inode->i_sb, KERN_ERR,
 			 "Inode %lu (%p): orphan list check failed!",
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 4ad64732cbc..5efbd5d7701 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -1231,7 +1231,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots,
 	struct super_block *sb = dir->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	struct buffer_head *bh, *prev, *bhs[3]; /* 32*slots (672bytes) */
-	struct msdos_dir_entry *de;
+	struct msdos_dir_entry *uninitialized_var(de);
 	int err, free_slots, i, nr_bhs;
 	loff_t pos, i_pos;
 
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 5942fec22c6..1726d730304 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1188,9 +1188,9 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 out:
 	/* UTF-8 doesn't provide FAT semantics */
 	if (!strcmp(opts->iocharset, "utf8")) {
-		fat_msg(sb, KERN_ERR, "utf8 is not a recommended IO charset"
+		fat_msg(sb, KERN_WARNING, "utf8 is not a recommended IO charset"
 		       " for FAT filesystems, filesystem will be "
-		       "case sensitive!\n");
+		       "case sensitive!");
 	}
 
 	/* If user doesn't specify allow_utime, it's initialized from dmask. */
@@ -1367,6 +1367,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	sbi->free_clusters = -1;	/* Don't know yet */
 	sbi->free_clus_valid = 0;
 	sbi->prev_free = FAT_START_ENT;
+	sb->s_maxbytes = 0xffffffff;
 
 	if (!sbi->fat_length && b->fat32_length) {
 		struct fat_boot_fsinfo *fsinfo;
@@ -1377,8 +1378,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 		sbi->fat_length = le32_to_cpu(b->fat32_length);
 		sbi->root_cluster = le32_to_cpu(b->root_cluster);
 
-		sb->s_maxbytes = 0xffffffff;
-
 		/* MC - if info_sector is 0, don't multiply by 0 */
 		sbi->fsinfo_sector = le16_to_cpu(b->info_sector);
 		if (sbi->fsinfo_sector == 0)
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 640fc229df1..5cb8614508c 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 d480d9af46c..594f07a81c2 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 c6aa2d4b851..cf6db0a9321 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 38f84cd48b6..add96f6ffda 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 85c62923ee2..59864643436 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 747238cd9f9..be29858900f 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 3bc073a4cf8..079587e5384 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 42e8d23bc04..0e8bb13381e 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 c106ca22e81..d24a9b666a2 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 10e515a0d45..7daf4b852d1 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 87b6e0421c1..ec889538e5a 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 73920d555c8..ec7924696a1 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/jfs/jfs_umount.c b/fs/jfs/jfs_umount.c
index adcf92d3b60..7971f37534a 100644
--- a/fs/jfs/jfs_umount.c
+++ b/fs/jfs/jfs_umount.c
@@ -68,7 +68,7 @@ int jfs_umount(struct super_block *sb)
 		/*
 		 * Wait for outstanding transactions to be written to log:
 		 */
-		jfs_flush_journal(log, 1);
+		jfs_flush_journal(log, 2);
 
 	/*
 	 * close fileset inode allocation map (aka fileset inode)
@@ -146,7 +146,7 @@ int jfs_umount_rw(struct super_block *sb)
 	 *
 	 * remove file system from log active file system list.
 	 */
-	jfs_flush_journal(log, 1);
+	jfs_flush_journal(log, 2);
 
 	/*
 	 * Make sure all metadata makes it to disk
diff --git a/fs/namei.c b/fs/namei.c
index 2826db35dc2..0b3138de2a3 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 22bfe8273c6..b4febb29d3b 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/Kconfig b/fs/nfs/Kconfig
index be020771c6b..dbcd82126ae 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -79,12 +79,9 @@ config NFS_V4_1
 	depends on NFS_FS && NFS_V4 && EXPERIMENTAL
 	select SUNRPC_BACKCHANNEL
 	select PNFS_FILE_LAYOUT
-	select PNFS_BLOCK
-	select MD
-	select BLK_DEV_DM
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
-	  (RFC 5661 and RFC 5663) in the kernel's NFS client.
+	  (RFC 5661) in the kernel's NFS client.
 
 	  If unsure, say N.
 
@@ -93,16 +90,13 @@ config PNFS_FILE_LAYOUT
 
 config PNFS_BLOCK
 	tristate
+	depends on NFS_FS && NFS_V4_1 && BLK_DEV_DM
+	default m
 
 config PNFS_OBJLAYOUT
-	tristate "Provide support for the pNFS Objects Layout Driver for NFSv4.1 pNFS (EXPERIMENTAL)"
+	tristate
 	depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
-	help
-	  Say M here if you want your pNFS client to support the Objects Layout Driver.
-	  Requires the SCSI osd initiator library (SCSI_OSD_INITIATOR) and
-	  upper level driver (SCSI_OSD_ULD).
-
-	  If unsure, say N.
+	default m
 
 config ROOT_NFS
 	bool "Root file system on NFS"
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index e56564d2ef9..9561c8fc8bd 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -36,6 +36,7 @@
 #include <linux/namei.h>
 #include <linux/bio.h>		/* struct bio */
 #include <linux/buffer_head.h>	/* various write calls */
+#include <linux/prefetch.h>
 
 #include "blocklayout.h"
 
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index b257383bb56..07df5f1d85e 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -38,6 +38,7 @@ enum nfs4_callback_opnum {
 struct cb_process_state {
 	__be32			drc_status;
 	struct nfs_client	*clp;
+	int			slotid;
 };
 
 struct cb_compound_hdr_arg {
@@ -166,7 +167,6 @@ extern unsigned nfs4_callback_layoutrecall(
 	void *dummy, struct cb_process_state *cps);
 
 extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
-extern void nfs4_cb_take_slot(struct nfs_client *clp);
 
 struct cb_devicenotifyitem {
 	uint32_t		cbd_notify_type;
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 74780f9f852..43926add945 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -348,7 +348,7 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 	/* Normal */
 	if (likely(args->csa_sequenceid == slot->seq_nr + 1)) {
 		slot->seq_nr++;
-		return htonl(NFS4_OK);
+		goto out_ok;
 	}
 
 	/* Replay */
@@ -367,11 +367,14 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 	/* Wraparound */
 	if (args->csa_sequenceid == 1 && (slot->seq_nr + 1) == 0) {
 		slot->seq_nr = 1;
-		return htonl(NFS4_OK);
+		goto out_ok;
 	}
 
 	/* Misordered request */
 	return htonl(NFS4ERR_SEQ_MISORDERED);
+out_ok:
+	tbl->highest_used_slotid = args->csa_slotid;
+	return htonl(NFS4_OK);
 }
 
 /*
@@ -433,26 +436,37 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 			      struct cb_sequenceres *res,
 			      struct cb_process_state *cps)
 {
+	struct nfs4_slot_table *tbl;
 	struct nfs_client *clp;
 	int i;
 	__be32 status = htonl(NFS4ERR_BADSESSION);
 
-	cps->clp = NULL;
-
 	clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid);
 	if (clp == NULL)
 		goto out;
 
+	tbl = &clp->cl_session->bc_slot_table;
+
+	spin_lock(&tbl->slot_tbl_lock);
 	/* state manager is resetting the session */
 	if (test_bit(NFS4_SESSION_DRAINING, &clp->cl_session->session_state)) {
-		status = NFS4ERR_DELAY;
+		spin_unlock(&tbl->slot_tbl_lock);
+		status = htonl(NFS4ERR_DELAY);
+		/* Return NFS4ERR_BADSESSION if we're draining the session
+		 * in order to reset it.
+		 */
+		if (test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
+			status = htonl(NFS4ERR_BADSESSION);
 		goto out;
 	}
 
 	status = validate_seqid(&clp->cl_session->bc_slot_table, args);
+	spin_unlock(&tbl->slot_tbl_lock);
 	if (status)
 		goto out;
 
+	cps->slotid = args->csa_slotid;
+
 	/*
 	 * Check for pending referring calls.  If a match is found, a
 	 * related callback was received before the response to the original
@@ -469,7 +483,6 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	res->csr_slotid = args->csa_slotid;
 	res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
 	res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
-	nfs4_cb_take_slot(clp);
 
 out:
 	cps->clp = clp; /* put in nfs4_callback_compound */
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index c6c86a77e04..918ad647afe 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -754,26 +754,15 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
 	 * Let the state manager know callback processing done.
 	 * A single slot, so highest used slotid is either 0 or -1
 	 */
-	tbl->highest_used_slotid--;
+	tbl->highest_used_slotid = -1;
 	nfs4_check_drain_bc_complete(session);
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
-static void nfs4_cb_free_slot(struct nfs_client *clp)
+static void nfs4_cb_free_slot(struct cb_process_state *cps)
 {
-	if (clp && clp->cl_session)
-		nfs4_callback_free_slot(clp->cl_session);
-}
-
-/* A single slot, so highest used slotid is either 0 or -1 */
-void nfs4_cb_take_slot(struct nfs_client *clp)
-{
-	struct nfs4_slot_table *tbl = &clp->cl_session->bc_slot_table;
-
-	spin_lock(&tbl->slot_tbl_lock);
-	tbl->highest_used_slotid++;
-	BUG_ON(tbl->highest_used_slotid != 0);
-	spin_unlock(&tbl->slot_tbl_lock);
+	if (cps->slotid != -1)
+		nfs4_callback_free_slot(cps->clp->cl_session);
 }
 
 #else /* CONFIG_NFS_V4_1 */
@@ -784,7 +773,7 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
 	return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
 }
 
-static void nfs4_cb_free_slot(struct nfs_client *clp)
+static void nfs4_cb_free_slot(struct cb_process_state *cps)
 {
 }
 #endif /* CONFIG_NFS_V4_1 */
@@ -866,6 +855,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	struct cb_process_state cps = {
 		.drc_status = 0,
 		.clp = NULL,
+		.slotid = -1,
 	};
 	unsigned int nops = 0;
 
@@ -906,7 +896,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 
 	*hdr_res.status = status;
 	*hdr_res.nops = htonl(nops);
-	nfs4_cb_free_slot(cps.clp);
+	nfs4_cb_free_slot(&cps);
 	nfs_put_client(cps.clp);
 	dprintk("%s: done, status = %u\n", __func__, ntohl(status));
 	return rpc_success;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 1ec1a85fa71..3e93e9a1bee 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 8c77039e7a8..4700fae1ada 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 df8e7f3ca56..dc484c0eae7 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 72ab97ef3d6..39914be40b0 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/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 9383ca7245b..d0cda12fddc 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -479,7 +479,6 @@ static int _io_check(struct objio_state *ios, bool is_write)
 	for (i = 0; i <  ios->numdevs; i++) {
 		struct osd_sense_info osi;
 		struct osd_request *or = ios->per_dev[i].or;
-		unsigned dev;
 		int ret;
 
 		if (!or)
@@ -500,9 +499,8 @@ static int _io_check(struct objio_state *ios, bool is_write)
 
 			continue; /* we recovered */
 		}
-		dev = ios->per_dev[i].dev;
-		objlayout_io_set_result(&ios->ol_state, dev,
-					&ios->layout->comps[dev].oc_object_id,
+		objlayout_io_set_result(&ios->ol_state, i,
+					&ios->layout->comps[i].oc_object_id,
 					osd_pri_2_pnfs_err(osi.osd_err_pri),
 					ios->per_dev[i].offset,
 					ios->per_dev[i].length,
@@ -589,22 +587,19 @@ static void _calc_stripe_info(struct objio_state *ios, u64 file_offset,
 }
 
 static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
-		unsigned pgbase, struct _objio_per_comp *per_dev, int cur_len,
+		unsigned pgbase, struct _objio_per_comp *per_dev, int len,
 		gfp_t gfp_flags)
 {
 	unsigned pg = *cur_pg;
+	int cur_len = len;
 	struct request_queue *q =
 			osd_request_queue(_io_od(ios, per_dev->dev));
 
-	per_dev->length += cur_len;
-
 	if (per_dev->bio == NULL) {
-		unsigned stripes = ios->layout->num_comps /
-						     ios->layout->mirrors_p1;
-		unsigned pages_in_stripe = stripes *
+		unsigned pages_in_stripe = ios->layout->group_width *
 				      (ios->layout->stripe_unit / PAGE_SIZE);
 		unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) /
-				    stripes;
+				    ios->layout->group_width;
 
 		if (BIO_MAX_PAGES_KMALLOC < bio_size)
 			bio_size = BIO_MAX_PAGES_KMALLOC;
@@ -632,6 +627,7 @@ static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
 	}
 	BUG_ON(cur_len);
 
+	per_dev->length += len;
 	*cur_pg = pg;
 	return 0;
 }
@@ -650,7 +646,7 @@ static int _prepare_one_group(struct objio_state *ios, u64 length,
 	int ret = 0;
 
 	while (length) {
-		struct _objio_per_comp *per_dev = &ios->per_dev[dev];
+		struct _objio_per_comp *per_dev = &ios->per_dev[dev - first_dev];
 		unsigned cur_len, page_off = 0;
 
 		if (!per_dev->length) {
@@ -670,8 +666,8 @@ static int _prepare_one_group(struct objio_state *ios, u64 length,
 				cur_len = stripe_unit;
 			}
 
-			if (max_comp < dev)
-				max_comp = dev;
+			if (max_comp < dev - first_dev)
+				max_comp = dev - first_dev;
 		} else {
 			cur_len = stripe_unit;
 		}
@@ -806,7 +802,7 @@ static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
 	struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
 	unsigned dev = per_dev->dev;
 	struct pnfs_osd_object_cred *cred =
-			&ios->layout->comps[dev];
+			&ios->layout->comps[cur_comp];
 	struct osd_obj_id obj = {
 		.partition = cred->oc_object_id.oid_partition_id,
 		.id = cred->oc_object_id.oid_object_id,
@@ -904,7 +900,7 @@ static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
 	for (; cur_comp < last_comp; ++cur_comp, ++dev) {
 		struct osd_request *or = NULL;
 		struct pnfs_osd_object_cred *cred =
-					&ios->layout->comps[dev];
+					&ios->layout->comps[cur_comp];
 		struct osd_obj_id obj = {
 			.partition = cred->oc_object_id.oid_partition_id,
 			.id = cred->oc_object_id.oid_object_id,
diff --git a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
index 16fc758e912..b3918f7ac34 100644
--- a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
+++ b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
@@ -170,6 +170,9 @@ int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
 	p = _osd_xdr_decode_data_map(p, &layout->olo_map);
 	layout->olo_comps_index = be32_to_cpup(p++);
 	layout->olo_num_comps = be32_to_cpup(p++);
+	dprintk("%s: olo_comps_index=%d olo_num_comps=%d\n", __func__,
+		layout->olo_comps_index, layout->olo_num_comps);
+
 	iter->total_comps = layout->olo_num_comps;
 	return 0;
 }
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index b961ceac66b..5b19b6aabe1 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 b39b37f8091..c9bd2a6b7d4 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 25b6a887adb..5afaa58a863 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 b34bdb25490..10b6be3ca28 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 ba5316ffac6..78a3aa83c7e 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 45174b53437..feb361e252a 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 75bb316529d..427a4e82a58 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 a907de565db..a907de565db 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 f7c8f7a9ea6..f7c8f7a9ea6 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 ff6a19873e5..ff6a19873e5 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 387e695a184..387e695a184 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 b83f76b6d41..b83f76b6d41 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 4732d71262c..4732d71262c 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 53ec3ea9a62..d8b11b7f94a 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 b6c4b3795c4..b6c4b3795c4 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 6530769a999..4805f009f92 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -103,7 +103,7 @@ typedef struct xfs_agf {
 /* disk block (xfs_daddr_t) in the AG */
 #define XFS_AGF_DADDR(mp)	((xfs_daddr_t)(1 << (mp)->m_sectbb_log))
 #define	XFS_AGF_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_AGF_DADDR(mp))
-#define	XFS_BUF_TO_AGF(bp)	((xfs_agf_t *)XFS_BUF_PTR(bp))
+#define	XFS_BUF_TO_AGF(bp)	((xfs_agf_t *)((bp)->b_addr))
 
 extern int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
@@ -156,7 +156,7 @@ typedef struct xfs_agi {
 /* disk block (xfs_daddr_t) in the AG */
 #define XFS_AGI_DADDR(mp)	((xfs_daddr_t)(2 << (mp)->m_sectbb_log))
 #define	XFS_AGI_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_AGI_DADDR(mp))
-#define	XFS_BUF_TO_AGI(bp)	((xfs_agi_t *)XFS_BUF_PTR(bp))
+#define	XFS_BUF_TO_AGI(bp)	((xfs_agi_t *)((bp)->b_addr))
 
 extern int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
 				xfs_agnumber_t agno, struct xfs_buf **bpp);
@@ -168,7 +168,7 @@ extern int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
 #define XFS_AGFL_DADDR(mp)	((xfs_daddr_t)(3 << (mp)->m_sectbb_log))
 #define	XFS_AGFL_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_AGFL_DADDR(mp))
 #define XFS_AGFL_SIZE(mp)	((mp)->m_sb.sb_sectsize / sizeof(xfs_agblock_t))
-#define	XFS_BUF_TO_AGFL(bp)	((xfs_agfl_t *)XFS_BUF_PTR(bp))
+#define	XFS_BUF_TO_AGFL(bp)	((xfs_agfl_t *)((bp)->b_addr))
 
 typedef struct xfs_agfl {
 	__be32		agfl_bno[1];	/* actually XFS_AGFL_SIZE(mp) */
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 1e00b3ef627..bdd9cb54d63 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -451,8 +451,7 @@ xfs_alloc_read_agfl(
 			XFS_FSS_TO_BB(mp, 1), 0, &bp);
 	if (error)
 		return error;
-	ASSERT(bp);
-	ASSERT(!XFS_BUF_GETERROR(bp));
+	ASSERT(!xfs_buf_geterror(bp));
 	XFS_BUF_SET_VTYPE_REF(bp, B_FS_AGFL, XFS_AGFL_REF);
 	*bpp = bp;
 	return 0;
@@ -2116,7 +2115,7 @@ xfs_read_agf(
 	if (!*bpp)
 		return 0;
 
-	ASSERT(!XFS_BUF_GETERROR(*bpp));
+	ASSERT(!(*bpp)->b_error);
 	agf = XFS_BUF_TO_AGF(*bpp);
 
 	/*
@@ -2168,7 +2167,7 @@ xfs_alloc_read_agf(
 		return error;
 	if (!*bpp)
 		return 0;
-	ASSERT(!XFS_BUF_GETERROR(*bpp));
+	ASSERT(!(*bpp)->b_error);
 
 	agf = XFS_BUF_TO_AGF(*bpp);
 	pag = xfs_perag_get(mp, agno);
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/xfs_aops.c
index 63e971e2b83..8c37dde4c52 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 71f721e1a71..71f721e1a71 100644
--- a/fs/xfs/linux-2.6/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index cbae424fe1b..160bcdc34a6 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -2121,8 +2121,7 @@ xfs_attr_rmtval_set(xfs_da_args_t *args)
 
 		bp = xfs_buf_get(mp->m_ddev_targp, dblkno, blkcnt,
 				 XBF_LOCK | XBF_DONT_BLOCK);
-		ASSERT(bp);
-		ASSERT(!XFS_BUF_GETERROR(bp));
+		ASSERT(!xfs_buf_geterror(bp));
 
 		tmp = (valuelen < XFS_BUF_SIZE(bp)) ? valuelen :
 							XFS_BUF_SIZE(bp);
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index ab3e5c6c464..452a291383a 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -3383,8 +3383,7 @@ xfs_bmap_local_to_extents(
 		ASSERT(args.len == 1);
 		*firstblock = args.fsbno;
 		bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
-		memcpy((char *)XFS_BUF_PTR(bp), ifp->if_u1.if_data,
-			ifp->if_bytes);
+		memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
 		xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
 		xfs_bmap_forkoff_reset(args.mp, ip, whichfork);
 		xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index cabf4b5604a..2b9fd385e27 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -275,8 +275,7 @@ xfs_btree_dup_cursor(
 				return error;
 			}
 			new->bc_bufs[i] = bp;
-			ASSERT(bp);
-			ASSERT(!XFS_BUF_GETERROR(bp));
+			ASSERT(!xfs_buf_geterror(bp));
 		} else
 			new->bc_bufs[i] = NULL;
 	}
@@ -467,8 +466,7 @@ xfs_btree_get_bufl(
 	ASSERT(fsbno != NULLFSBLOCK);
 	d = XFS_FSB_TO_DADDR(mp, fsbno);
 	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
-	ASSERT(bp);
-	ASSERT(!XFS_BUF_GETERROR(bp));
+	ASSERT(!xfs_buf_geterror(bp));
 	return bp;
 }
 
@@ -491,8 +489,7 @@ xfs_btree_get_bufs(
 	ASSERT(agbno != NULLAGBLOCK);
 	d = XFS_AGB_TO_DADDR(mp, agno, agbno);
 	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
-	ASSERT(bp);
-	ASSERT(!XFS_BUF_GETERROR(bp));
+	ASSERT(!xfs_buf_geterror(bp));
 	return bp;
 }
 
@@ -632,7 +629,7 @@ xfs_btree_read_bufl(
 			mp->m_bsize, lock, &bp))) {
 		return error;
 	}
-	ASSERT(!bp || !XFS_BUF_GETERROR(bp));
+	ASSERT(!xfs_buf_geterror(bp));
 	if (bp)
 		XFS_BUF_SET_VTYPE_REF(bp, B_FS_MAP, refval);
 	*bpp = bp;
@@ -973,8 +970,7 @@ xfs_btree_get_buf_block(
 	*bpp = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d,
 				 mp->m_bsize, flags);
 
-	ASSERT(*bpp);
-	ASSERT(!XFS_BUF_GETERROR(*bpp));
+	ASSERT(!xfs_buf_geterror(*bpp));
 
 	*block = XFS_BUF_TO_BLOCK(*bpp);
 	return 0;
@@ -1006,8 +1002,7 @@ xfs_btree_read_buf_block(
 	if (error)
 		return error;
 
-	ASSERT(*bpp != NULL);
-	ASSERT(!XFS_BUF_GETERROR(*bpp));
+	ASSERT(!xfs_buf_geterror(*bpp));
 
 	xfs_btree_set_refs(cur, *bpp);
 	*block = XFS_BUF_TO_BLOCK(*bpp);
diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h
index 8d05a6a46ce..5b240de104c 100644
--- a/fs/xfs/xfs_btree.h
+++ b/fs/xfs/xfs_btree.h
@@ -262,7 +262,7 @@ typedef struct xfs_btree_cur
 /*
  * Convert from buffer to btree block header.
  */
-#define	XFS_BUF_TO_BLOCK(bp)	((struct xfs_btree_block *)XFS_BUF_PTR(bp))
+#define	XFS_BUF_TO_BLOCK(bp)	((struct xfs_btree_block *)((bp)->b_addr))
 
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/xfs_buf.c
index d1fe74506c4..c57836dc778 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -596,7 +596,7 @@ _xfs_buf_read(
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
 
 	status = xfs_buf_iorequest(bp);
-	if (status || XFS_BUF_ISERROR(bp) || (flags & XBF_ASYNC))
+	if (status || bp->b_error || (flags & XBF_ASYNC))
 		return status;
 	return xfs_buf_iowait(bp);
 }
@@ -679,7 +679,6 @@ xfs_buf_read_uncached(
 	/* set up the buffer for a read IO */
 	XFS_BUF_SET_ADDR(bp, daddr);
 	XFS_BUF_READ(bp);
-	XFS_BUF_BUSY(bp);
 
 	xfsbdstrat(mp, bp);
 	error = xfs_buf_iowait(bp);
@@ -1069,7 +1068,7 @@ xfs_bioerror(
 	/*
 	 * No need to wait until the buffer is unpinned, we aren't flushing it.
 	 */
-	XFS_BUF_ERROR(bp, EIO);
+	xfs_buf_ioerror(bp, EIO);
 
 	/*
 	 * We're calling xfs_buf_ioend, so delete XBF_DONE flag.
@@ -1094,7 +1093,7 @@ STATIC int
 xfs_bioerror_relse(
 	struct xfs_buf	*bp)
 {
-	int64_t		fl = XFS_BUF_BFLAGS(bp);
+	int64_t		fl = bp->b_flags;
 	/*
 	 * No need to wait until the buffer is unpinned.
 	 * We aren't flushing it.
@@ -1115,7 +1114,7 @@ xfs_bioerror_relse(
 		 * There's no reason to mark error for
 		 * ASYNC buffers.
 		 */
-		XFS_BUF_ERROR(bp, EIO);
+		xfs_buf_ioerror(bp, EIO);
 		XFS_BUF_FINISH_IOWAIT(bp);
 	} else {
 		xfs_buf_relse(bp);
@@ -1324,7 +1323,7 @@ xfs_buf_offset(
 	struct page		*page;
 
 	if (bp->b_flags & XBF_MAPPED)
-		return XFS_BUF_PTR(bp) + offset;
+		return bp->b_addr + offset;
 
 	offset += bp->b_offset;
 	page = bp->b_pages[offset >> PAGE_SHIFT];
@@ -1484,7 +1483,7 @@ xfs_setsize_buftarg_flags(
 	if (set_blocksize(btp->bt_bdev, sectorsize)) {
 		xfs_warn(btp->bt_mount,
 			"Cannot set_blocksize to %u on device %s\n",
-			sectorsize, XFS_BUFTARG_NAME(btp));
+			sectorsize, xfs_buf_target_name(btp));
 		return EINVAL;
 	}
 
@@ -1681,7 +1680,7 @@ xfs_buf_delwri_split(
 	list_for_each_entry_safe(bp, n, dwq, b_list) {
 		ASSERT(bp->b_flags & XBF_DELWRI);
 
-		if (!XFS_BUF_ISPINNED(bp) && xfs_buf_trylock(bp)) {
+		if (!xfs_buf_ispinned(bp) && xfs_buf_trylock(bp)) {
 			if (!force &&
 			    time_before(jiffies, bp->b_queuetime + age)) {
 				xfs_buf_unlock(bp);
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/xfs_buf.h
index 6a83b46b4bc..620972b8094 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -228,11 +228,15 @@ extern void xfs_buf_delwri_promote(xfs_buf_t *);
 extern int xfs_buf_init(void);
 extern void xfs_buf_terminate(void);
 
-#define xfs_buf_target_name(target)	\
-	({ char __b[BDEVNAME_SIZE]; bdevname((target)->bt_bdev, __b); __b; })
+static inline const char *
+xfs_buf_target_name(struct xfs_buftarg *target)
+{
+	static char __b[BDEVNAME_SIZE];
+
+	return bdevname(target->bt_bdev, __b);
+}
 
 
-#define XFS_BUF_BFLAGS(bp)	((bp)->b_flags)
 #define XFS_BUF_ZEROFLAGS(bp) \
 	((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI| \
 			    XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
@@ -251,23 +255,14 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNDELAYWRITE(bp)	xfs_buf_delwri_dequeue(bp)
 #define XFS_BUF_ISDELAYWRITE(bp)	((bp)->b_flags & XBF_DELWRI)
 
-#define XFS_BUF_ERROR(bp,no)	xfs_buf_ioerror(bp,no)
-#define XFS_BUF_GETERROR(bp)	xfs_buf_geterror(bp)
-#define XFS_BUF_ISERROR(bp)	(xfs_buf_geterror(bp) ? 1 : 0)
-
 #define XFS_BUF_DONE(bp)	((bp)->b_flags |= XBF_DONE)
 #define XFS_BUF_UNDONE(bp)	((bp)->b_flags &= ~XBF_DONE)
 #define XFS_BUF_ISDONE(bp)	((bp)->b_flags & XBF_DONE)
 
-#define XFS_BUF_BUSY(bp)	do { } while (0)
-#define XFS_BUF_UNBUSY(bp)	do { } while (0)
-#define XFS_BUF_ISBUSY(bp)	(1)
-
 #define XFS_BUF_ASYNC(bp)	((bp)->b_flags |= XBF_ASYNC)
 #define XFS_BUF_UNASYNC(bp)	((bp)->b_flags &= ~XBF_ASYNC)
 #define XFS_BUF_ISASYNC(bp)	((bp)->b_flags & XBF_ASYNC)
 
-#define XFS_BUF_HOLD(bp)	xfs_buf_hold(bp)
 #define XFS_BUF_READ(bp)	((bp)->b_flags |= XBF_READ)
 #define XFS_BUF_UNREAD(bp)	((bp)->b_flags &= ~XBF_READ)
 #define XFS_BUF_ISREAD(bp)	((bp)->b_flags & XBF_READ)
@@ -276,10 +271,6 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_UNWRITE(bp)	((bp)->b_flags &= ~XBF_WRITE)
 #define XFS_BUF_ISWRITE(bp)	((bp)->b_flags & XBF_WRITE)
 
-#define XFS_BUF_SET_START(bp)			do { } while (0)
-
-#define XFS_BUF_PTR(bp)			(xfs_caddr_t)((bp)->b_addr)
-#define XFS_BUF_SET_PTR(bp, val, cnt)	xfs_buf_associate_memory(bp, val, cnt)
 #define XFS_BUF_ADDR(bp)		((bp)->b_bn)
 #define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_bn = (xfs_daddr_t)(bno))
 #define XFS_BUF_OFFSET(bp)		((bp)->b_file_offset)
@@ -299,14 +290,13 @@ xfs_buf_set_ref(
 #define XFS_BUF_SET_VTYPE_REF(bp, type, ref)	xfs_buf_set_ref(bp, ref)
 #define XFS_BUF_SET_VTYPE(bp, type)		do { } while (0)
 
-#define XFS_BUF_ISPINNED(bp)	atomic_read(&((bp)->b_pin_count))
+static inline int xfs_buf_ispinned(struct xfs_buf *bp)
+{
+	return atomic_read(&bp->b_pin_count);
+}
 
 #define XFS_BUF_FINISH_IOWAIT(bp)	complete(&bp->b_iowait);
 
-#define XFS_BUF_SET_TARGET(bp, target)	((bp)->b_target = (target))
-#define XFS_BUF_TARGET(bp)		((bp)->b_target)
-#define XFS_BUFTARG_NAME(target)	xfs_buf_target_name(target)
-
 static inline void xfs_buf_relse(xfs_buf_t *bp)
 {
 	xfs_buf_unlock(bp);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 88492916c3d..cac2ecfa674 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -124,9 +124,9 @@ xfs_buf_item_log_check(
 
 	bp = bip->bli_buf;
 	ASSERT(XFS_BUF_COUNT(bp) > 0);
-	ASSERT(XFS_BUF_PTR(bp) != NULL);
+	ASSERT(bp->b_addr != NULL);
 	orig = bip->bli_orig;
-	buffer = XFS_BUF_PTR(bp);
+	buffer = bp->b_addr;
 	for (x = 0; x < XFS_BUF_COUNT(bp); x++) {
 		if (orig[x] != buffer[x] && !btst(bip->bli_logged, x)) {
 			xfs_emerg(bp->b_mount,
@@ -371,7 +371,6 @@ xfs_buf_item_pin(
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 
-	ASSERT(XFS_BUF_ISBUSY(bip->bli_buf));
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
 	       (bip->bli_flags & XFS_BLI_STALE));
@@ -479,13 +478,13 @@ xfs_buf_item_trylock(
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
 
-	if (XFS_BUF_ISPINNED(bp))
+	if (xfs_buf_ispinned(bp))
 		return XFS_ITEM_PINNED;
 	if (!xfs_buf_trylock(bp))
 		return XFS_ITEM_LOCKED;
 
 	/* take a reference to the buffer.  */
-	XFS_BUF_HOLD(bp);
+	xfs_buf_hold(bp);
 
 	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
 	trace_xfs_buf_item_trylock(bip);
@@ -726,7 +725,7 @@ xfs_buf_item_init(
 	 * to have logged.
 	 */
 	bip->bli_orig = (char *)kmem_alloc(XFS_BUF_COUNT(bp), KM_SLEEP);
-	memcpy(bip->bli_orig, XFS_BUF_PTR(bp), XFS_BUF_COUNT(bp));
+	memcpy(bip->bli_orig, bp->b_addr, XFS_BUF_COUNT(bp));
 	bip->bli_logged = (char *)kmem_zalloc(XFS_BUF_COUNT(bp) / NBBY, KM_SLEEP);
 #endif
 
@@ -895,7 +894,6 @@ xfs_buf_attach_iodone(
 {
 	xfs_log_item_t	*head_lip;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(xfs_buf_islocked(bp));
 
 	lip->li_cb = cb;
@@ -960,7 +958,7 @@ xfs_buf_iodone_callbacks(
 	static ulong		lasttime;
 	static xfs_buftarg_t	*lasttarg;
 
-	if (likely(!XFS_BUF_GETERROR(bp)))
+	if (likely(!xfs_buf_geterror(bp)))
 		goto do_callbacks;
 
 	/*
@@ -973,14 +971,14 @@ xfs_buf_iodone_callbacks(
 		goto do_callbacks;
 	}
 
-	if (XFS_BUF_TARGET(bp) != lasttarg ||
+	if (bp->b_target != lasttarg ||
 	    time_after(jiffies, (lasttime + 5*HZ))) {
 		lasttime = jiffies;
 		xfs_alert(mp, "Device %s: metadata write error block 0x%llx",
-			XFS_BUFTARG_NAME(XFS_BUF_TARGET(bp)),
+			xfs_buf_target_name(bp->b_target),
 		      (__uint64_t)XFS_BUF_ADDR(bp));
 	}
-	lasttarg = XFS_BUF_TARGET(bp);
+	lasttarg = bp->b_target;
 
 	/*
 	 * If the write was asynchronous then no one will be looking for the
@@ -991,12 +989,11 @@ xfs_buf_iodone_callbacks(
 	 * around.
 	 */
 	if (XFS_BUF_ISASYNC(bp)) {
-		XFS_BUF_ERROR(bp, 0); /* errno of 0 unsets the flag */
+		xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
 
 		if (!XFS_BUF_ISSTALE(bp)) {
 			XFS_BUF_DELAYWRITE(bp);
 			XFS_BUF_DONE(bp);
-			XFS_BUF_SET_START(bp);
 		}
 		ASSERT(bp->b_iodone != NULL);
 		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
@@ -1013,7 +1010,6 @@ xfs_buf_iodone_callbacks(
 	XFS_BUF_UNDELAYWRITE(bp);
 
 	trace_xfs_buf_error_relse(bp, _RET_IP_);
-	xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
 
 do_callbacks:
 	xfs_buf_do_callbacks(bp);
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 5bfcb8779f9..ee9d5427fcd 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -2050,7 +2050,7 @@ xfs_da_do_buf(
 		case 0:
 			bp = xfs_trans_get_buf(trans, mp->m_ddev_targp,
 				mappedbno, nmapped, 0);
-			error = bp ? XFS_BUF_GETERROR(bp) : XFS_ERROR(EIO);
+			error = bp ? bp->b_error : XFS_ERROR(EIO);
 			break;
 		case 1:
 		case 2:
@@ -2268,7 +2268,7 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps)
 		dabuf->nbuf = 1;
 		bp = bps[0];
 		dabuf->bbcount = (short)BTOBB(XFS_BUF_COUNT(bp));
-		dabuf->data = XFS_BUF_PTR(bp);
+		dabuf->data = bp->b_addr;
 		dabuf->bps[0] = bp;
 	} else {
 		dabuf->nbuf = nbuf;
@@ -2279,7 +2279,7 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps)
 		dabuf->data = kmem_alloc(BBTOB(dabuf->bbcount), KM_SLEEP);
 		for (i = off = 0; i < nbuf; i++, off += XFS_BUF_COUNT(bp)) {
 			bp = bps[i];
-			memcpy((char *)dabuf->data + off, XFS_BUF_PTR(bp),
+			memcpy((char *)dabuf->data + off, bp->b_addr,
 				XFS_BUF_COUNT(bp));
 		}
 	}
@@ -2302,8 +2302,8 @@ xfs_da_buf_clean(xfs_dabuf_t *dabuf)
 		for (i = off = 0; i < dabuf->nbuf;
 				i++, off += XFS_BUF_COUNT(bp)) {
 			bp = dabuf->bps[i];
-			memcpy(XFS_BUF_PTR(bp), (char *)dabuf->data + off,
-				XFS_BUF_COUNT(bp));
+			memcpy(bp->b_addr, dabuf->data + off,
+						XFS_BUF_COUNT(bp));
 		}
 	}
 }
@@ -2340,7 +2340,7 @@ xfs_da_log_buf(xfs_trans_t *tp, xfs_dabuf_t *dabuf, uint first, uint last)
 
 	ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]);
 	if (dabuf->nbuf == 1) {
-		ASSERT(dabuf->data == (void *)XFS_BUF_PTR(dabuf->bps[0]));
+		ASSERT(dabuf->data == dabuf->bps[0]->b_addr);
 		xfs_trans_log_buf(tp, dabuf->bps[0], first, last);
 		return;
 	}
diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h
index dffba9ba0db..a3721633abc 100644
--- a/fs/xfs/xfs_dinode.h
+++ b/fs/xfs/xfs_dinode.h
@@ -148,7 +148,7 @@ typedef enum xfs_dinode_fmt {
 		be32_to_cpu((dip)->di_nextents) : \
 		be16_to_cpu((dip)->di_anextents))
 
-#define	XFS_BUF_TO_DINODE(bp)	((xfs_dinode_t *)XFS_BUF_PTR(bp))
+#define	XFS_BUF_TO_DINODE(bp)	((xfs_dinode_t *)((bp)->b_addr))
 
 /*
  * For block and character special files the 32bit dev_t is stored at the
diff --git a/fs/xfs/linux-2.6/xfs_discard.c b/fs/xfs/xfs_discard.c
index 244e797dae3..244e797dae3 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 344879aea64..344879aea64 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 837f31158d4..db62959bed1 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -318,10 +318,9 @@ xfs_qm_init_dquot_blk(
 	int		curid, i;
 
 	ASSERT(tp);
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(xfs_buf_islocked(bp));
 
-	d = (xfs_dqblk_t *)XFS_BUF_PTR(bp);
+	d = bp->b_addr;
 
 	/*
 	 * ID of the first dquot in the block - id's are zero based.
@@ -403,7 +402,7 @@ xfs_qm_dqalloc(
 			       dqp->q_blkno,
 			       mp->m_quotainfo->qi_dqchunklen,
 			       0);
-	if (!bp || (error = XFS_BUF_GETERROR(bp)))
+	if (!bp || (error = xfs_buf_geterror(bp)))
 		goto error1;
 	/*
 	 * Make a chunk of dquots out of this buffer and log
@@ -534,13 +533,12 @@ xfs_qm_dqtobp(
 			return XFS_ERROR(error);
 	}
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(xfs_buf_islocked(bp));
 
 	/*
 	 * calculate the location of the dquot inside the buffer.
 	 */
-	ddq = (struct xfs_disk_dquot *)(XFS_BUF_PTR(bp) + dqp->q_bufoffset);
+	ddq = bp->b_addr + dqp->q_bufoffset;
 
 	/*
 	 * A simple sanity check in case we got a corrupted dquot...
@@ -553,7 +551,6 @@ xfs_qm_dqtobp(
 			xfs_trans_brelse(tp, bp);
 			return XFS_ERROR(EIO);
 		}
-		XFS_BUF_BUSY(bp); /* We dirtied this */
 	}
 
 	*O_bpp = bp;
@@ -622,7 +619,6 @@ xfs_qm_dqread(
 	 * this particular dquot was repaired. We still aren't afraid to
 	 * brelse it because we have the changes incore.
 	 */
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(xfs_buf_islocked(bp));
 	xfs_trans_brelse(tp, bp);
 
@@ -1204,7 +1200,7 @@ xfs_qm_dqflush(
 	/*
 	 * Calculate the location of the dquot inside the buffer.
 	 */
-	ddqp = (struct xfs_disk_dquot *)(XFS_BUF_PTR(bp) + dqp->q_bufoffset);
+	ddqp = bp->b_addr + dqp->q_bufoffset;
 
 	/*
 	 * A simple sanity check in case we got a corrupted dquot..
@@ -1240,7 +1236,7 @@ xfs_qm_dqflush(
 	 * If the buffer is pinned then push on the log so we won't
 	 * get stuck waiting in the write for too long.
 	 */
-	if (XFS_BUF_ISPINNED(bp)) {
+	if (xfs_buf_ispinned(bp)) {
 		trace_xfs_dqflush_force(dqp);
 		xfs_log_force(mp, 0);
 	}
@@ -1447,7 +1443,7 @@ xfs_qm_dqflock_pushbuf_wait(
 		goto out_lock;
 
 	if (XFS_BUF_ISDELAYWRITE(bp)) {
-		if (XFS_BUF_ISPINNED(bp))
+		if (xfs_buf_ispinned(bp))
 			xfs_log_force(mp, 0);
 		xfs_buf_delwri_promote(bp);
 		wake_up_process(bp->b_target->bt_task);
diff --git a/fs/xfs/quota/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index 34b7e945dbf..34b7e945dbf 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 9e0e2fa3f2c..9e0e2fa3f2c 100644
--- a/fs/xfs/quota/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
diff --git a/fs/xfs/quota/xfs_dquot_item.h b/fs/xfs/xfs_dquot_item.h
index 5acae2ada70..5acae2ada70 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 75e5d322e48..75e5d322e48 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 3272b6ae7a3..3272b6ae7a3 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 7f7b42469ea..7f7b42469ea 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 ed88ed16811..ed88ed16811 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 76e81cff70b..76e81cff70b 100644
--- a/fs/xfs/linux-2.6/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index dd5628bd8d0..9f24ec28283 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -202,8 +202,7 @@ xfs_ialloc_inode_init(
 		fbuf = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
 					 mp->m_bsize * blks_per_cluster,
 					 XBF_LOCK);
-		ASSERT(fbuf);
-		ASSERT(!XFS_BUF_GETERROR(fbuf));
+		ASSERT(!xfs_buf_geterror(fbuf));
 
 		/*
 		 * Initialize all inodes in this buffer and then log them.
@@ -1486,7 +1485,7 @@ xfs_read_agi(
 	if (error)
 		return error;
 
-	ASSERT(*bpp && !XFS_BUF_GETERROR(*bpp));
+	ASSERT(!xfs_buf_geterror(*bpp));
 	agi = XFS_BUF_TO_AGI(*bpp);
 
 	/*
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 2fcca4b03ed..0239a7c7c88 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2473,7 +2473,7 @@ cluster_corrupt_out:
 		if (bp->b_iodone) {
 			XFS_BUF_UNDONE(bp);
 			XFS_BUF_STALE(bp);
-			XFS_BUF_ERROR(bp,EIO);
+			xfs_buf_ioerror(bp, EIO);
 			xfs_buf_ioend(bp, 0);
 		} else {
 			XFS_BUF_STALE(bp);
@@ -2585,7 +2585,7 @@ xfs_iflush(
 	 * If the buffer is pinned then push on the log now so we won't
 	 * get stuck waiting in the write for too long.
 	 */
-	if (XFS_BUF_ISPINNED(bp))
+	if (xfs_buf_ispinned(bp))
 		xfs_log_force(mp, 0);
 
 	/*
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index f7ce7debe14..f7ce7debe14 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 d56173b34a2..d56173b34a2 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 54e623bfbb8..54e623bfbb8 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 80f4060e897..80f4060e897 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 b9c172b3fbb..673704fab74 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 ef41c92ce66..ef41c92ce66 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 d42f814e4d3..1e8a45e74c3 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>
@@ -78,14 +77,14 @@
 #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/xfs_log.c b/fs/xfs/xfs_log.c
index 06ff8437ed8..3a8d4f66d70 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -878,7 +878,7 @@ xlog_iodone(xfs_buf_t *bp)
 	/*
 	 * Race to shutdown the filesystem if we see an error.
 	 */
-	if (XFS_TEST_ERROR((XFS_BUF_GETERROR(bp)), l->l_mp,
+	if (XFS_TEST_ERROR((xfs_buf_geterror(bp)), l->l_mp,
 			XFS_ERRTAG_IODONE_IOERR, XFS_RANDOM_IODONE_IOERR)) {
 		xfs_ioerror_alert("xlog_iodone", l->l_mp, bp, XFS_BUF_ADDR(bp));
 		XFS_BUF_STALE(bp);
@@ -1051,7 +1051,6 @@ xlog_alloc_log(xfs_mount_t	*mp,
 	if (!bp)
 		goto out_free_log;
 	bp->b_iodone = xlog_iodone;
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(xfs_buf_islocked(bp));
 	log->l_xbuf = bp;
 
@@ -1108,7 +1107,6 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		iclog->ic_callback_tail = &(iclog->ic_callback);
 		iclog->ic_datap = (char *)iclog->ic_data + log->l_iclog_hsize;
 
-		ASSERT(XFS_BUF_ISBUSY(iclog->ic_bp));
 		ASSERT(xfs_buf_islocked(iclog->ic_bp));
 		init_waitqueue_head(&iclog->ic_force_wait);
 		init_waitqueue_head(&iclog->ic_write_wait);
@@ -1248,7 +1246,7 @@ xlog_bdstrat(
 	struct xlog_in_core	*iclog = bp->b_fspriv;
 
 	if (iclog->ic_state & XLOG_STATE_IOERROR) {
-		XFS_BUF_ERROR(bp, EIO);
+		xfs_buf_ioerror(bp, EIO);
 		XFS_BUF_STALE(bp);
 		xfs_buf_ioend(bp, 0);
 		/*
@@ -1355,7 +1353,6 @@ xlog_sync(xlog_t		*log,
 	XFS_BUF_SET_COUNT(bp, count);
 	bp->b_fspriv = iclog;
 	XFS_BUF_ZEROFLAGS(bp);
-	XFS_BUF_BUSY(bp);
 	XFS_BUF_ASYNC(bp);
 	bp->b_flags |= XBF_SYNCIO;
 
@@ -1398,16 +1395,15 @@ xlog_sync(xlog_t		*log,
 	if (split) {
 		bp = iclog->ic_log->l_xbuf;
 		XFS_BUF_SET_ADDR(bp, 0);	     /* logical 0 */
-		XFS_BUF_SET_PTR(bp, (xfs_caddr_t)((__psint_t)&(iclog->ic_header)+
-					    (__psint_t)count), split);
+		xfs_buf_associate_memory(bp,
+				(char *)&iclog->ic_header + count, split);
 		bp->b_fspriv = iclog;
 		XFS_BUF_ZEROFLAGS(bp);
-		XFS_BUF_BUSY(bp);
 		XFS_BUF_ASYNC(bp);
 		bp->b_flags |= XBF_SYNCIO;
 		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
 			bp->b_flags |= XBF_FUA;
-		dptr = XFS_BUF_PTR(bp);
+		dptr = bp->b_addr;
 		/*
 		 * Bump the cycle numbers at the start of each block
 		 * since this part of the buffer is at the start of
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 052a2c0ec5f..a199dbcee7d 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -147,7 +147,7 @@ xlog_align(
 	xfs_daddr_t	offset = blk_no & ((xfs_daddr_t)log->l_sectBBsize - 1);
 
 	ASSERT(BBTOB(offset + nbblks) <= XFS_BUF_SIZE(bp));
-	return XFS_BUF_PTR(bp) + BBTOB(offset);
+	return bp->b_addr + BBTOB(offset);
 }
 
 
@@ -178,9 +178,7 @@ xlog_bread_noalign(
 
 	XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
 	XFS_BUF_READ(bp);
-	XFS_BUF_BUSY(bp);
 	XFS_BUF_SET_COUNT(bp, BBTOB(nbblks));
-	XFS_BUF_SET_TARGET(bp, log->l_mp->m_logdev_targp);
 
 	xfsbdstrat(log->l_mp, bp);
 	error = xfs_buf_iowait(bp);
@@ -220,18 +218,18 @@ xlog_bread_offset(
 	xfs_buf_t	*bp,
 	xfs_caddr_t	offset)
 {
-	xfs_caddr_t	orig_offset = XFS_BUF_PTR(bp);
+	xfs_caddr_t	orig_offset = bp->b_addr;
 	int		orig_len = bp->b_buffer_length;
 	int		error, error2;
 
-	error = XFS_BUF_SET_PTR(bp, offset, BBTOB(nbblks));
+	error = xfs_buf_associate_memory(bp, offset, BBTOB(nbblks));
 	if (error)
 		return error;
 
 	error = xlog_bread_noalign(log, blk_no, nbblks, bp);
 
 	/* must reset buffer pointer even on error */
-	error2 = XFS_BUF_SET_PTR(bp, orig_offset, orig_len);
+	error2 = xfs_buf_associate_memory(bp, orig_offset, orig_len);
 	if (error)
 		return error;
 	return error2;
@@ -266,11 +264,9 @@ xlog_bwrite(
 
 	XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
 	XFS_BUF_ZEROFLAGS(bp);
-	XFS_BUF_BUSY(bp);
-	XFS_BUF_HOLD(bp);
+	xfs_buf_hold(bp);
 	xfs_buf_lock(bp);
 	XFS_BUF_SET_COUNT(bp, BBTOB(nbblks));
-	XFS_BUF_SET_TARGET(bp, log->l_mp->m_logdev_targp);
 
 	if ((error = xfs_bwrite(log->l_mp, bp)))
 		xfs_ioerror_alert("xlog_bwrite", log->l_mp,
@@ -360,7 +356,7 @@ STATIC void
 xlog_recover_iodone(
 	struct xfs_buf	*bp)
 {
-	if (XFS_BUF_GETERROR(bp)) {
+	if (bp->b_error) {
 		/*
 		 * We're not going to bother about retrying
 		 * this during recovery. One strike!
@@ -1262,7 +1258,7 @@ xlog_write_log_records(
 		 */
 		ealign = round_down(end_block, sectbb);
 		if (j == 0 && (start_block + endcount > ealign)) {
-			offset = XFS_BUF_PTR(bp) + BBTOB(ealign - start_block);
+			offset = bp->b_addr + BBTOB(ealign - start_block);
 			error = xlog_bread_offset(log, ealign, sectbb,
 							bp, offset);
 			if (error)
@@ -2135,15 +2131,16 @@ xlog_recover_buffer_pass2(
 
 	bp = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len,
 			  buf_flags);
-	if (XFS_BUF_ISERROR(bp)) {
+	if (!bp)
+		return XFS_ERROR(ENOMEM);
+	error = bp->b_error;
+	if (error) {
 		xfs_ioerror_alert("xlog_recover_do..(read#1)", mp,
 				  bp, buf_f->blf_blkno);
-		error = XFS_BUF_GETERROR(bp);
 		xfs_buf_relse(bp);
 		return error;
 	}
 
-	error = 0;
 	if (buf_f->blf_flags & XFS_BLF_INODE_BUF) {
 		error = xlog_recover_do_inode_buffer(mp, item, bp, buf_f);
 	} else if (buf_f->blf_flags &
@@ -2227,14 +2224,17 @@ xlog_recover_inode_pass2(
 
 	bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len,
 			  XBF_LOCK);
-	if (XFS_BUF_ISERROR(bp)) {
+	if (!bp) {
+		error = ENOMEM;
+		goto error;
+	}
+	error = bp->b_error;
+	if (error) {
 		xfs_ioerror_alert("xlog_recover_do..(read#2)", mp,
 				  bp, in_f->ilf_blkno);
-		error = XFS_BUF_GETERROR(bp);
 		xfs_buf_relse(bp);
 		goto error;
 	}
-	error = 0;
 	ASSERT(in_f->ilf_fields & XFS_ILOG_CORE);
 	dip = (xfs_dinode_t *)xfs_buf_offset(bp, in_f->ilf_boffset);
 
@@ -3437,7 +3437,7 @@ xlog_do_recovery_pass(
 			/*
 			 * Check for header wrapping around physical end-of-log
 			 */
-			offset = XFS_BUF_PTR(hbp);
+			offset = hbp->b_addr;
 			split_hblks = 0;
 			wrapped_hblks = 0;
 			if (blk_no + hblks <= log->l_logBBsize) {
@@ -3497,7 +3497,7 @@ xlog_do_recovery_pass(
 			} else {
 				/* This log record is split across the
 				 * physical end of log */
-				offset = XFS_BUF_PTR(dbp);
+				offset = dbp->b_addr;
 				split_bblks = 0;
 				if (blk_no != log->l_logBBsize) {
 					/* some data is before the physical
diff --git a/fs/xfs/linux-2.6/xfs_message.c b/fs/xfs/xfs_message.c
index bd672def95a..bd672def95a 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 7fb7ea00767..7fb7ea00767 100644
--- a/fs/xfs/linux-2.6/xfs_message.h
+++ b/fs/xfs/xfs_message.h
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 092e16ae4d9..0081657ad98 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1615,7 +1615,7 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
 		XFS_BUF_UNDELAYWRITE(sbp);
 		XFS_BUF_WRITE(sbp);
 		XFS_BUF_UNASYNC(sbp);
-		ASSERT(XFS_BUF_TARGET(sbp) == mp->m_ddev_targp);
+		ASSERT(sbp->b_target == mp->m_ddev_targp);
 		xfsbdstrat(mp, sbp);
 		error = xfs_buf_iowait(sbp);
 		if (error)
@@ -1938,7 +1938,7 @@ xfs_getsb(
 		xfs_buf_lock(bp);
 	}
 
-	XFS_BUF_HOLD(bp);
+	xfs_buf_hold(bp);
 	ASSERT(XFS_BUF_ISDONE(bp));
 	return bp;
 }
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/xfs_qm.c
index 46e54ad9a2d..9a0aa76facd 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1240,7 +1240,7 @@ xfs_qm_reset_dqcounts(
 	do_div(j, sizeof(xfs_dqblk_t));
 	ASSERT(mp->m_quotainfo->qi_dqperchunk == j);
 #endif
-	ddq = (xfs_disk_dquot_t *)XFS_BUF_PTR(bp);
+	ddq = bp->b_addr;
 	for (j = 0; j < mp->m_quotainfo->qi_dqperchunk; j++) {
 		/*
 		 * Do a sanity check, and if needed, repair the dqblk. Don't
diff --git a/fs/xfs/quota/xfs_qm.h b/fs/xfs/xfs_qm.h
index 43b9abe1052..43b9abe1052 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 a0a829addca..a0a829addca 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 8671a0b3264..8671a0b3264 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 5b964fc0dc0..5b964fc0dc0 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 609246f42e6..609246f42e6 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 94a3d927d71..94a3d927d71 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 29b9d642e93..7e76f537abb 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/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 8f76fdff4f4..35561a511b5 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -168,7 +168,7 @@ error_cancel:
 				xfs_trans_cancel(tp, cancelflags);
 				goto error;
 			}
-			memset(XFS_BUF_PTR(bp), 0, mp->m_sb.sb_blocksize);
+			memset(bp->b_addr, 0, mp->m_sb.sb_blocksize);
 			xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1);
 			/*
 			 * Commit the transaction.
@@ -883,7 +883,7 @@ xfs_rtbuf_get(
 	if (error) {
 		return error;
 	}
-	ASSERT(bp && !XFS_BUF_GETERROR(bp));
+	ASSERT(!xfs_buf_geterror(bp));
 	*bpp = bp;
 	return 0;
 }
@@ -943,7 +943,7 @@ xfs_rtcheck_range(
 	if (error) {
 		return error;
 	}
-	bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+	bufp = bp->b_addr;
 	/*
 	 * Compute the starting word's address, and starting bit.
 	 */
@@ -994,7 +994,7 @@ xfs_rtcheck_range(
 			if (error) {
 				return error;
 			}
-			b = bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+			b = bufp = bp->b_addr;
 			word = 0;
 		} else {
 			/*
@@ -1040,7 +1040,7 @@ xfs_rtcheck_range(
 			if (error) {
 				return error;
 			}
-			b = bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+			b = bufp = bp->b_addr;
 			word = 0;
 		} else {
 			/*
@@ -1158,7 +1158,7 @@ xfs_rtfind_back(
 	if (error) {
 		return error;
 	}
-	bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+	bufp = bp->b_addr;
 	/*
 	 * Get the first word's index & point to it.
 	 */
@@ -1210,7 +1210,7 @@ xfs_rtfind_back(
 			if (error) {
 				return error;
 			}
-			bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+			bufp = bp->b_addr;
 			word = XFS_BLOCKWMASK(mp);
 			b = &bufp[word];
 		} else {
@@ -1256,7 +1256,7 @@ xfs_rtfind_back(
 			if (error) {
 				return error;
 			}
-			bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+			bufp = bp->b_addr;
 			word = XFS_BLOCKWMASK(mp);
 			b = &bufp[word];
 		} else {
@@ -1333,7 +1333,7 @@ xfs_rtfind_forw(
 	if (error) {
 		return error;
 	}
-	bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+	bufp = bp->b_addr;
 	/*
 	 * Get the first word's index & point to it.
 	 */
@@ -1384,7 +1384,7 @@ xfs_rtfind_forw(
 			if (error) {
 				return error;
 			}
-			b = bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+			b = bufp = bp->b_addr;
 			word = 0;
 		} else {
 			/*
@@ -1429,7 +1429,7 @@ xfs_rtfind_forw(
 			if (error) {
 				return error;
 			}
-			b = bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+			b = bufp = bp->b_addr;
 			word = 0;
 		} else {
 			/*
@@ -1649,7 +1649,7 @@ xfs_rtmodify_range(
 	if (error) {
 		return error;
 	}
-	bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+	bufp = bp->b_addr;
 	/*
 	 * Compute the starting word's address, and starting bit.
 	 */
@@ -1694,7 +1694,7 @@ xfs_rtmodify_range(
 			if (error) {
 				return error;
 			}
-			first = b = bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+			first = b = bufp = bp->b_addr;
 			word = 0;
 		} else {
 			/*
@@ -1734,7 +1734,7 @@ xfs_rtmodify_range(
 			if (error) {
 				return error;
 			}
-			first = b = bufp = (xfs_rtword_t *)XFS_BUF_PTR(bp);
+			first = b = bufp = bp->b_addr;
 			word = 0;
 		} else {
 			/*
@@ -1832,8 +1832,8 @@ xfs_rtmodify_summary(
 	 */
 	sp = XFS_SUMPTR(mp, bp, so);
 	*sp += delta;
-	xfs_trans_log_buf(tp, bp, (uint)((char *)sp - (char *)XFS_BUF_PTR(bp)),
-		(uint)((char *)sp - (char *)XFS_BUF_PTR(bp) + sizeof(*sp) - 1));
+	xfs_trans_log_buf(tp, bp, (uint)((char *)sp - (char *)bp->b_addr),
+		(uint)((char *)sp - (char *)bp->b_addr + sizeof(*sp) - 1));
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index 09e1f4f35e9..f7f3a359c1c 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -47,7 +47,7 @@ struct xfs_trans;
 #define	XFS_SUMOFFSTOBLOCK(mp,s)	\
 	(((s) * (uint)sizeof(xfs_suminfo_t)) >> (mp)->m_sb.sb_blocklog)
 #define	XFS_SUMPTR(mp,bp,so)	\
-	((xfs_suminfo_t *)((char *)XFS_BUF_PTR(bp) + \
+	((xfs_suminfo_t *)((bp)->b_addr + \
 		(((so) * (uint)sizeof(xfs_suminfo_t)) & XFS_BLOCKMASK(mp))))
 
 #define	XFS_BITTOBLOCK(mp,bi)	((bi) >> (mp)->m_blkbit_log)
diff --git a/fs/xfs/xfs_rw.c b/fs/xfs/xfs_rw.c
index d6d6fdfe942..c96a8a05ac0 100644
--- a/fs/xfs/xfs_rw.c
+++ b/fs/xfs/xfs_rw.c
@@ -104,9 +104,9 @@ xfs_ioerror_alert(
 	xfs_alert(mp,
 		 "I/O error occurred: meta-data dev %s block 0x%llx"
 		 "       (\"%s\") error %d buf count %zd",
-		XFS_BUFTARG_NAME(XFS_BUF_TARGET(bp)),
+		xfs_buf_target_name(bp->b_target),
 		(__uint64_t)blkno, func,
-		XFS_BUF_GETERROR(bp), XFS_BUF_COUNT(bp));
+		bp->b_error, XFS_BUF_COUNT(bp));
 }
 
 /*
@@ -137,8 +137,8 @@ xfs_read_buf(
 	bp = xfs_buf_read(target, blkno, len, flags);
 	if (!bp)
 		return XFS_ERROR(EIO);
-	error = XFS_BUF_GETERROR(bp);
-	if (bp && !error && !XFS_FORCED_SHUTDOWN(mp)) {
+	error = bp->b_error;
+	if (!error && !XFS_FORCED_SHUTDOWN(mp)) {
 		*bpp = bp;
 	} else {
 		*bpp = NULL;
diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h
index 1eb2ba58681..cb6ae715814 100644
--- a/fs/xfs/xfs_sb.h
+++ b/fs/xfs/xfs_sb.h
@@ -509,7 +509,7 @@ static inline int xfs_sb_version_hasprojid32bit(xfs_sb_t *sbp)
 
 #define XFS_SB_DADDR		((xfs_daddr_t)0) /* daddr in filesystem/ag */
 #define	XFS_SB_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_SB_DADDR)
-#define XFS_BUF_TO_SBP(bp)	((xfs_dsb_t *)XFS_BUF_PTR(bp))
+#define XFS_BUF_TO_SBP(bp)	((xfs_dsb_t *)((bp)->b_addr))
 
 #define	XFS_HDR_BLOCK(mp,d)	((xfs_agblock_t)XFS_BB_TO_FSBT(mp,d))
 #define	XFS_DADDR_TO_FSB(mp,d)	XFS_AGB_TO_FSB(mp, \
diff --git a/fs/xfs/linux-2.6/xfs_stats.c b/fs/xfs/xfs_stats.c
index 76fdc586193..76fdc586193 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 736854b1ca1..736854b1ca1 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 9a72dda58bd..2366c54cc4f 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
diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/xfs_super.h
index 50a3266c999..50a3266c999 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 e4c938afb91..4604f90f86a 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -332,7 +332,7 @@ xfs_sync_fsdata(
 	 * between there and here.
 	 */
 	bp = xfs_getsb(mp, 0);
-	if (XFS_BUF_ISPINNED(bp))
+	if (xfs_buf_ispinned(bp))
 		xfs_log_force(mp, 0);
 
 	return xfs_bwrite(mp, bp);
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/xfs_sync.h
index 941202e7ac6..941202e7ac6 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 ee2d2adaa43..ee2d2adaa43 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 b9937d450f8..b9937d450f8 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 88d25d4aa56..9010ce885e6 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 690fc7a7bd7..690fc7a7bd7 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 43233e92f0f..c15aa29fa16 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -299,7 +299,7 @@ xfs_trans_ail_cursor_last(
  * Splice the log item list into the AIL at the given LSN. We splice to the
  * tail of the given LSN to maintain insert order for push traversals. The
  * cursor is optional, allowing repeated updates to the same LSN to avoid
- * repeated traversals.
+ * repeated traversals.  This should not be called with an empty list.
  */
 static void
 xfs_ail_splice(
@@ -308,50 +308,39 @@ xfs_ail_splice(
 	struct list_head	*list,
 	xfs_lsn_t		lsn)
 {
-	struct xfs_log_item	*lip = cur ? cur->item : NULL;
-	struct xfs_log_item	*next_lip;
+	struct xfs_log_item	*lip;
+
+	ASSERT(!list_empty(list));
 
 	/*
-	 * Get a new cursor if we don't have a placeholder or the existing one
-	 * has been invalidated.
+	 * Use the cursor to determine the insertion point if one is
+	 * provided.  If not, or if the one we got is not valid,
+	 * find the place in the AIL where the items belong.
 	 */
-	if (!lip || (__psint_t)lip & 1) {
+	lip = cur ? cur->item : NULL;
+	if (!lip || (__psint_t) lip & 1)
 		lip = __xfs_trans_ail_cursor_last(ailp, lsn);
 
-		if (!lip) {
-			/* The list is empty, so just splice and return.  */
-			if (cur)
-				cur->item = NULL;
-			list_splice(list, &ailp->xa_ail);
-			return;
-		}
-	}
+	/*
+	 * If a cursor is provided, we know we're processing the AIL
+	 * in lsn order, and future items to be spliced in will
+	 * follow the last one being inserted now.  Update the
+	 * cursor to point to that last item, now while we have a
+	 * reliable pointer to it.
+	 */
+	if (cur)
+		cur->item = list_entry(list->prev, struct xfs_log_item, li_ail);
 
 	/*
-	 * Our cursor points to the item we want to insert _after_, so we have
-	 * to update the cursor to point to the end of the list we are splicing
-	 * in so that it points to the correct location for the next splice.
-	 * i.e. before the splice
-	 *
-	 *  lsn -> lsn -> lsn + x -> lsn + x ...
-	 *          ^
-	 *          | cursor points here
-	 *
-	 * After the splice we have:
-	 *
-	 *  lsn -> lsn -> lsn -> lsn -> .... -> lsn -> lsn + x -> lsn + x ...
-	 *          ^                            ^
-	 *          | cursor points here         | needs to move here
-	 *
-	 * So we set the cursor to the last item in the list to be spliced
-	 * before we execute the splice, resulting in the cursor pointing to
-	 * the correct item after the splice occurs.
+	 * Finally perform the splice.  Unless the AIL was empty,
+	 * lip points to the item in the AIL _after_ which the new
+	 * items should go.  If lip is null the AIL was empty, so
+	 * the new items go at the head of the AIL.
 	 */
-	if (cur) {
-		next_lip = list_entry(list->prev, struct xfs_log_item, li_ail);
-		cur->item = next_lip;
-	}
-	list_splice(list, &lip->li_ail);
+	if (lip)
+		list_splice(list, &lip->li_ail);
+	else
+		list_splice(list, &ailp->xa_ail);
 }
 
 /*
@@ -682,6 +671,7 @@ xfs_trans_ail_update_bulk(
 	int			i;
 	LIST_HEAD(tmp);
 
+	ASSERT(nr_items > 0);		/* Not required, but true. */
 	mlip = xfs_ail_min(ailp);
 
 	for (i = 0; i < nr_items; i++) {
@@ -701,7 +691,8 @@ xfs_trans_ail_update_bulk(
 		list_add(&lip->li_ail, &tmp);
 	}
 
-	xfs_ail_splice(ailp, cur, &tmp, lsn);
+	if (!list_empty(&tmp))
+		xfs_ail_splice(ailp, cur, &tmp, lsn);
 
 	if (!mlip_changed) {
 		spin_unlock(&ailp->xa_lock);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 15584fc3ed7..137e2b9e294 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -54,7 +54,7 @@ xfs_trans_buf_item_match(
 	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
 		blip = (struct xfs_buf_log_item *)lidp->lid_item;
 		if (blip->bli_item.li_type == XFS_LI_BUF &&
-		    XFS_BUF_TARGET(blip->bli_buf) == target &&
+		    blip->bli_buf->b_target == target &&
 		    XFS_BUF_ADDR(blip->bli_buf) == blkno &&
 		    XFS_BUF_COUNT(blip->bli_buf) == len)
 			return blip->bli_buf;
@@ -80,7 +80,6 @@ _xfs_trans_bjoin(
 {
 	struct xfs_buf_log_item	*bip;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(bp->b_transp == NULL);
 
 	/*
@@ -194,7 +193,7 @@ xfs_trans_get_buf(xfs_trans_t	*tp,
 		return NULL;
 	}
 
-	ASSERT(!XFS_BUF_GETERROR(bp));
+	ASSERT(!bp->b_error);
 
 	_xfs_trans_bjoin(tp, bp, 1);
 	trace_xfs_trans_get_buf(bp->b_fspriv);
@@ -293,10 +292,10 @@ xfs_trans_read_buf(
 			return (flags & XBF_TRYLOCK) ?
 					EAGAIN : XFS_ERROR(ENOMEM);
 
-		if (XFS_BUF_GETERROR(bp) != 0) {
+		if (bp->b_error) {
+			error = bp->b_error;
 			xfs_ioerror_alert("xfs_trans_read_buf", mp,
 					  bp, blkno);
-			error = XFS_BUF_GETERROR(bp);
 			xfs_buf_relse(bp);
 			return error;
 		}
@@ -330,7 +329,7 @@ xfs_trans_read_buf(
 		ASSERT(xfs_buf_islocked(bp));
 		ASSERT(bp->b_transp == tp);
 		ASSERT(bp->b_fspriv != NULL);
-		ASSERT((XFS_BUF_ISERROR(bp)) == 0);
+		ASSERT(!bp->b_error);
 		if (!(XFS_BUF_ISDONE(bp))) {
 			trace_xfs_trans_read_buf_io(bp, _RET_IP_);
 			ASSERT(!XFS_BUF_ISASYNC(bp));
@@ -386,10 +385,9 @@ xfs_trans_read_buf(
 		return (flags & XBF_TRYLOCK) ?
 					0 : XFS_ERROR(ENOMEM);
 	}
-	if (XFS_BUF_GETERROR(bp) != 0) {
-	    XFS_BUF_SUPER_STALE(bp);
-		error = XFS_BUF_GETERROR(bp);
-
+	if (bp->b_error) {
+		error = bp->b_error;
+		XFS_BUF_SUPER_STALE(bp);
 		xfs_ioerror_alert("xfs_trans_read_buf", mp,
 				  bp, blkno);
 		if (tp->t_flags & XFS_TRANS_DIRTY)
@@ -430,7 +428,7 @@ shutdown_abort:
 	if (XFS_BUF_ISSTALE(bp) && XFS_BUF_ISDELAYWRITE(bp))
 		xfs_notice(mp, "about to pop assert, bp == 0x%p", bp);
 #endif
-	ASSERT((XFS_BUF_BFLAGS(bp) & (XBF_STALE|XBF_DELWRI)) !=
+	ASSERT((bp->b_flags & (XBF_STALE|XBF_DELWRI)) !=
 				     (XBF_STALE|XBF_DELWRI));
 
 	trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
@@ -581,7 +579,6 @@ xfs_trans_bhold(xfs_trans_t	*tp,
 {
 	xfs_buf_log_item_t	*bip = bp->b_fspriv;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
@@ -602,7 +599,6 @@ xfs_trans_bhold_release(xfs_trans_t	*tp,
 {
 	xfs_buf_log_item_t	*bip = bp->b_fspriv;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
@@ -631,7 +627,6 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 {
 	xfs_buf_log_item_t	*bip = bp->b_fspriv;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT((first <= last) && (last < XFS_BUF_COUNT(bp)));
@@ -702,7 +697,6 @@ xfs_trans_binval(
 {
 	xfs_buf_log_item_t	*bip = bp->b_fspriv;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
@@ -774,7 +768,6 @@ xfs_trans_inode_buf(
 {
 	xfs_buf_log_item_t	*bip = bp->b_fspriv;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
@@ -798,7 +791,6 @@ xfs_trans_stale_inode_buf(
 {
 	xfs_buf_log_item_t	*bip = bp->b_fspriv;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
@@ -823,7 +815,6 @@ xfs_trans_inode_alloc_buf(
 {
 	xfs_buf_log_item_t	*bip = bp->b_fspriv;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
@@ -851,7 +842,6 @@ xfs_trans_dquot_buf(
 {
 	xfs_buf_log_item_t	*bip = bp->b_fspriv;
 
-	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT(type == XFS_BLF_UDQUOT_BUF ||
diff --git a/fs/xfs/quota/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 4d00ee67792..4d00ee67792 100644
--- a/fs/xfs/quota/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/xfs_vnode.h
index 7c220b4227b..7c220b4227b 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/xfs_vnode.h
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 9322e13f0c6..51fc429527b 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -83,7 +83,9 @@ xfs_readlink_bmap(
 
 		bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt),
 				  XBF_LOCK | XBF_MAPPED | XBF_DONT_BLOCK);
-		error = XFS_BUF_GETERROR(bp);
+		if (!bp)
+			return XFS_ERROR(ENOMEM);
+		error = bp->b_error;
 		if (error) {
 			xfs_ioerror_alert("xfs_readlink",
 				  ip->i_mount, bp, XFS_BUF_ADDR(bp));
@@ -94,7 +96,7 @@ xfs_readlink_bmap(
 			byte_cnt = pathlen;
 		pathlen -= byte_cnt;
 
-		memcpy(link, XFS_BUF_PTR(bp), byte_cnt);
+		memcpy(link, bp->b_addr, byte_cnt);
 		xfs_buf_relse(bp);
 	}
 
@@ -1648,13 +1650,13 @@ xfs_symlink(
 			byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
 			bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
 					       BTOBB(byte_cnt), 0);
-			ASSERT(bp && !XFS_BUF_GETERROR(bp));
+			ASSERT(!xfs_buf_geterror(bp));
 			if (pathlen < byte_cnt) {
 				byte_cnt = pathlen;
 			}
 			pathlen -= byte_cnt;
 
-			memcpy(XFS_BUF_PTR(bp), cur_chunk, byte_cnt);
+			memcpy(bp->b_addr, cur_chunk, byte_cnt);
 			cur_chunk += byte_cnt;
 
 			xfs_trans_log_buf(tp, bp, 0, byte_cnt - 1);
@@ -1999,7 +2001,7 @@ xfs_zero_remaining_bytes(
 					  mp, bp, XFS_BUF_ADDR(bp));
 			break;
 		}
-		memset(XFS_BUF_PTR(bp) +
+		memset(bp->b_addr +
 			(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
 		      0, lastoffset - offset + 1);
 		XFS_BUF_UNDONE(bp);
diff --git a/fs/xfs/linux-2.6/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 87d3e03878c..87d3e03878c 100644
--- a/fs/xfs/linux-2.6/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c