Merge branch 'master' into for-next

244 files changed, 8470 insertions, 5175 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index 771f457402d4..3db9caa57edc 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -30,15 +30,6 @@ config FS_MBCACHE
 source "fs/reiserfs/Kconfig"
 source "fs/jfs/Kconfig"
 
-config FS_POSIX_ACL
-# Posix ACL utility routines (for now, only ext2/ext3/jfs/reiserfs/nfs4)
-#
-# NOTE: you can implement Posix ACLs without these helpers (XFS does).
-# 	Never use this symbol for ifdefs.
-#
-	bool
-	default n
-
 source "fs/xfs/Kconfig"
 source "fs/gfs2/Kconfig"
 source "fs/ocfs2/Kconfig"
@@ -47,11 +38,19 @@ source "fs/nilfs2/Kconfig"
 
 endif # BLOCK
 
+# Posix ACL utility routines
+#
+# Note: Posix ACLs can be implemented without these helpers.  Never use
+# this symbol for ifdefs in core code.
+#
+config FS_POSIX_ACL
+	def_bool n
+
 config EXPORTFS
 	tristate
 
 config FILE_LOCKING
-	bool "Enable POSIX file locking API" if EMBEDDED
+	bool "Enable POSIX file locking API" if EXPERT
 	default y
 	help
 	  This option enables standard file locking support, required
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index a3bcec75c54a..1c8c6cc6de30 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -289,7 +289,7 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
 	call->server = server;
 
 	INIT_WORK(&call->work, SRXAFSCB_CallBack);
-	schedule_work(&call->work);
+	queue_work(afs_wq, &call->work);
 	return 0;
 }
 
@@ -336,7 +336,7 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call,
 	call->server = server;
 
 	INIT_WORK(&call->work, SRXAFSCB_InitCallBackState);
-	schedule_work(&call->work);
+	queue_work(afs_wq, &call->work);
 	return 0;
 }
 
@@ -367,7 +367,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call,
 	call->server = server;
 
 	INIT_WORK(&call->work, SRXAFSCB_InitCallBackState);
-	schedule_work(&call->work);
+	queue_work(afs_wq, &call->work);
 	return 0;
 }
 
@@ -400,7 +400,7 @@ static int afs_deliver_cb_probe(struct afs_call *call, struct sk_buff *skb,
 	call->state = AFS_CALL_REPLYING;
 
 	INIT_WORK(&call->work, SRXAFSCB_Probe);
-	schedule_work(&call->work);
+	queue_work(afs_wq, &call->work);
 	return 0;
 }
 
@@ -496,7 +496,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb,
 	call->state = AFS_CALL_REPLYING;
 
 	INIT_WORK(&call->work, SRXAFSCB_ProbeUuid);
-	schedule_work(&call->work);
+	queue_work(afs_wq, &call->work);
 	return 0;
 }
 
@@ -580,6 +580,6 @@ static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call,
 	call->state = AFS_CALL_REPLYING;
 
 	INIT_WORK(&call->work, SRXAFSCB_TellMeAboutYourself);
-	schedule_work(&call->work);
+	queue_work(afs_wq, &call->work);
 	return 0;
 }
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index e6a4ab980e31..20c106f24927 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -66,6 +66,7 @@ const struct dentry_operations afs_fs_dentry_operations = {
 	.d_revalidate	= afs_d_revalidate,
 	.d_delete	= afs_d_delete,
 	.d_release	= afs_d_release,
+	.d_automount	= afs_d_automount,
 };
 
 #define AFS_DIR_HASHTBL_SIZE	128
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 0747339011c3..db66c5201474 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -184,7 +184,8 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
 	inode->i_generation	= 0;
 
 	set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags);
-	inode->i_flags |= S_NOATIME;
+	set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+	inode->i_flags |= S_AUTOMOUNT | S_NOATIME;
 	unlock_new_inode(inode);
 	_leave(" = %p", inode);
 	return inode;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index ab6db5abaf53..5a9b6843bac1 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -577,6 +577,7 @@ extern int afs_drop_inode(struct inode *);
 /*
  * main.c
  */
+extern struct workqueue_struct *afs_wq;
 extern struct afs_uuid afs_uuid;
 
 /*
@@ -591,6 +592,7 @@ extern const struct inode_operations afs_mntpt_inode_operations;
 extern const struct inode_operations afs_autocell_inode_operations;
 extern const struct file_operations afs_mntpt_file_operations;
 
+extern struct vfsmount *afs_d_automount(struct path *);
 extern int afs_mntpt_check_symlink(struct afs_vnode *, struct key *);
 extern void afs_mntpt_kill_timer(void);
 
diff --git a/fs/afs/main.c b/fs/afs/main.c
index cfd1cbe25b22..42dd2e499ed8 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -30,6 +30,7 @@ module_param(rootcell, charp, 0);
 MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list");
 
 struct afs_uuid afs_uuid;
+struct workqueue_struct *afs_wq;
 
 /*
  * get a client UUID
@@ -87,10 +88,16 @@ static int __init afs_init(void)
 	if (ret < 0)
 		return ret;
 
+	/* create workqueue */
+	ret = -ENOMEM;
+	afs_wq = alloc_workqueue("afs", 0, 0);
+	if (!afs_wq)
+		return ret;
+
 	/* register the /proc stuff */
 	ret = afs_proc_init();
 	if (ret < 0)
-		return ret;
+		goto error_proc;
 
 #ifdef CONFIG_AFS_FSCACHE
 	/* we want to be able to cache */
@@ -140,6 +147,8 @@ error_cell_init:
 error_cache:
 #endif
 	afs_proc_cleanup();
+error_proc:
+	destroy_workqueue(afs_wq);
 	rcu_barrier();
 	printk(KERN_ERR "kAFS: failed to register: %d\n", ret);
 	return ret;
@@ -163,7 +172,7 @@ static void __exit afs_exit(void)
 	afs_purge_servers();
 	afs_callback_update_kill();
 	afs_vlocation_purge();
-	flush_scheduled_work();
+	destroy_workqueue(afs_wq);
 	afs_cell_purge();
 #ifdef CONFIG_AFS_FSCACHE
 	fscache_unregister_netfs(&afs_cache_netfs);
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 6153417caf57..aa59184151d0 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -24,7 +24,6 @@ static struct dentry *afs_mntpt_lookup(struct inode *dir,
 				       struct dentry *dentry,
 				       struct nameidata *nd);
 static int afs_mntpt_open(struct inode *inode, struct file *file);
-static void *afs_mntpt_follow_link(struct dentry *dentry, struct nameidata *nd);
 static void afs_mntpt_expiry_timed_out(struct work_struct *work);
 
 const struct file_operations afs_mntpt_file_operations = {
@@ -34,13 +33,11 @@ const struct file_operations afs_mntpt_file_operations = {
 
 const struct inode_operations afs_mntpt_inode_operations = {
 	.lookup		= afs_mntpt_lookup,
-	.follow_link	= afs_mntpt_follow_link,
 	.readlink	= page_readlink,
 	.getattr	= afs_getattr,
 };
 
 const struct inode_operations afs_autocell_inode_operations = {
-	.follow_link	= afs_mntpt_follow_link,
 	.getattr	= afs_getattr,
 };
 
@@ -88,6 +85,7 @@ int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
 		_debug("symlink is a mountpoint");
 		spin_lock(&vnode->lock);
 		set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+		vnode->vfs_inode.i_flags |= S_AUTOMOUNT;
 		spin_unlock(&vnode->lock);
 	}
 
@@ -238,52 +236,24 @@ error_no_devname:
 }
 
 /*
- * follow a link from a mountpoint directory, thus causing it to be mounted
+ * handle an automount point
  */
-static void *afs_mntpt_follow_link(struct dentry *dentry, struct nameidata *nd)
+struct vfsmount *afs_d_automount(struct path *path)
 {
 	struct vfsmount *newmnt;
-	int err;
 
-	_enter("%p{%s},{%s:%p{%s},}",
-	       dentry,
-	       dentry->d_name.name,
-	       nd->path.mnt->mnt_devname,
-	       dentry,
-	       nd->path.dentry->d_name.name);
-
-	dput(nd->path.dentry);
-	nd->path.dentry = dget(dentry);
+	_enter("{%s,%s}", path->mnt->mnt_devname, path->dentry->d_name.name);
 
-	newmnt = afs_mntpt_do_automount(nd->path.dentry);
-	if (IS_ERR(newmnt)) {
-		path_put(&nd->path);
-		return (void *)newmnt;
-	}
-
-	mntget(newmnt);
-	err = do_add_mount(newmnt, &nd->path, MNT_SHRINKABLE, &afs_vfsmounts);
-	switch (err) {
-	case 0:
-		path_put(&nd->path);
-		nd->path.mnt = newmnt;
-		nd->path.dentry = dget(newmnt->mnt_root);
-		schedule_delayed_work(&afs_mntpt_expiry_timer,
-				      afs_mntpt_expiry_timeout * HZ);
-		break;
-	case -EBUSY:
-		/* someone else made a mount here whilst we were busy */
-		while (d_mountpoint(nd->path.dentry) &&
-		       follow_down(&nd->path))
-			;
-		err = 0;
-	default:
-		mntput(newmnt);
-		break;
-	}
+	newmnt = afs_mntpt_do_automount(path->dentry);
+	if (IS_ERR(newmnt))
+		return newmnt;
 
-	_leave(" = %d", err);
-	return ERR_PTR(err);
+	mntget(newmnt); /* prevent immediate expiration */
+	mnt_set_expiry(newmnt, &afs_vfsmounts);
+	queue_delayed_work(afs_wq, &afs_mntpt_expiry_timer,
+			   afs_mntpt_expiry_timeout * HZ);
+	_leave(" = %p {%s}", newmnt, newmnt->mnt_devname);
+	return newmnt;
 }
 
 /*
@@ -295,8 +265,8 @@ static void afs_mntpt_expiry_timed_out(struct work_struct *work)
 
 	if (!list_empty(&afs_vfsmounts)) {
 		mark_mounts_for_expiry(&afs_vfsmounts);
-		schedule_delayed_work(&afs_mntpt_expiry_timer,
-				      afs_mntpt_expiry_timeout * HZ);
+		queue_delayed_work(afs_wq, &afs_mntpt_expiry_timer,
+				   afs_mntpt_expiry_timeout * HZ);
 	}
 
 	_leave("");
@@ -310,6 +280,5 @@ void afs_mntpt_kill_timer(void)
 	_enter("");
 
 	ASSERT(list_empty(&afs_vfsmounts));
-	cancel_delayed_work(&afs_mntpt_expiry_timer);
-	flush_scheduled_work();
+	cancel_delayed_work_sync(&afs_mntpt_expiry_timer);
 }
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 654d8fdbf01f..e45a323aebb4 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -410,7 +410,7 @@ static void afs_rx_interceptor(struct sock *sk, unsigned long user_call_ID,
 	if (!call) {
 		/* its an incoming call for our callback service */
 		skb_queue_tail(&afs_incoming_calls, skb);
-		schedule_work(&afs_collect_incoming_call_work);
+		queue_work(afs_wq, &afs_collect_incoming_call_work);
 	} else {
 		/* route the messages directly to the appropriate call */
 		skb_queue_tail(&call->rx_queue, skb);
diff --git a/fs/afs/server.c b/fs/afs/server.c
index 9fdc7fe3a7bc..d59b7516e943 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -238,8 +238,8 @@ void afs_put_server(struct afs_server *server)
 	if (atomic_read(&server->usage) == 0) {
 		list_move_tail(&server->grave, &afs_server_graveyard);
 		server->time_of_death = get_seconds();
-		schedule_delayed_work(&afs_server_reaper,
-				      afs_server_timeout * HZ);
+		queue_delayed_work(afs_wq, &afs_server_reaper,
+				   afs_server_timeout * HZ);
 	}
 	spin_unlock(&afs_server_graveyard_lock);
 	_leave(" [dead]");
@@ -285,10 +285,11 @@ static void afs_reap_server(struct work_struct *work)
 		expiry = server->time_of_death + afs_server_timeout;
 		if (expiry > now) {
 			delay = (expiry - now) * HZ;
-			if (!schedule_delayed_work(&afs_server_reaper, delay)) {
+			if (!queue_delayed_work(afs_wq, &afs_server_reaper,
+						delay)) {
 				cancel_delayed_work(&afs_server_reaper);
-				schedule_delayed_work(&afs_server_reaper,
-						      delay);
+				queue_delayed_work(afs_wq, &afs_server_reaper,
+						   delay);
 			}
 			break;
 		}
@@ -323,5 +324,5 @@ void __exit afs_purge_servers(void)
 {
 	afs_server_timeout = 0;
 	cancel_delayed_work(&afs_server_reaper);
-	schedule_delayed_work(&afs_server_reaper, 0);
+	queue_delayed_work(afs_wq, &afs_server_reaper, 0);
 }
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index 9ac260d1361d..431984d2e372 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -507,8 +507,8 @@ void afs_put_vlocation(struct afs_vlocation *vl)
 		_debug("buried");
 		list_move_tail(&vl->grave, &afs_vlocation_graveyard);
 		vl->time_of_death = get_seconds();
-		schedule_delayed_work(&afs_vlocation_reap,
-				      afs_vlocation_timeout * HZ);
+		queue_delayed_work(afs_wq, &afs_vlocation_reap,
+				   afs_vlocation_timeout * HZ);
 
 		/* suspend updates on this record */
 		if (!list_empty(&vl->update)) {
@@ -561,11 +561,11 @@ static void afs_vlocation_reaper(struct work_struct *work)
 		if (expiry > now) {
 			delay = (expiry - now) * HZ;
 			_debug("delay %lu", delay);
-			if (!schedule_delayed_work(&afs_vlocation_reap,
-						   delay)) {
+			if (!queue_delayed_work(afs_wq, &afs_vlocation_reap,
+						delay)) {
 				cancel_delayed_work(&afs_vlocation_reap);
-				schedule_delayed_work(&afs_vlocation_reap,
-						      delay);
+				queue_delayed_work(afs_wq, &afs_vlocation_reap,
+						   delay);
 			}
 			break;
 		}
@@ -620,7 +620,7 @@ void afs_vlocation_purge(void)
 	destroy_workqueue(afs_vlocation_update_worker);
 
 	cancel_delayed_work(&afs_vlocation_reap);
-	schedule_delayed_work(&afs_vlocation_reap, 0);
+	queue_delayed_work(afs_wq, &afs_vlocation_reap, 0);
 }
 
 /*
diff --git a/fs/aio.c b/fs/aio.c
index 5e00f15c54aa..fc557a3be0a9 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -87,7 +87,7 @@ static int __init aio_setup(void)
 
 	aio_wq = create_workqueue("aio");
 	abe_pool = mempool_create_kmalloc_pool(1, sizeof(struct aio_batch_entry));
-	BUG_ON(!abe_pool);
+	BUG_ON(!aio_wq || !abe_pool);
 
 	pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page));
 
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index cbe57f3c4d89..c5567cb78432 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -233,7 +233,7 @@ static int __init anon_inode_init(void)
 	return 0;
 
 err_mntput:
-	mntput_long(anon_inode_mnt);
+	mntput(anon_inode_mnt);
 err_unregister_filesystem:
 	unregister_filesystem(&anon_inode_fs_type);
 err_exit:
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 0fffe1c24cec..54f923792728 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -88,18 +88,9 @@ struct autofs_info {
 
 	uid_t uid;
 	gid_t gid;
-
-	mode_t	mode;
-	size_t	size;
-
-	void (*free)(struct autofs_info *);
-	union {
-		const char *symlink;
-	} u;
 };
 
 #define AUTOFS_INF_EXPIRING	(1<<0) /* dentry is in the process of expiring */
-#define AUTOFS_INF_MOUNTPOINT	(1<<1) /* mountpoint status for direct expire */
 #define AUTOFS_INF_PENDING	(1<<2) /* dentry pending mount */
 
 struct autofs_wait_queue {
@@ -176,14 +167,7 @@ static inline int autofs4_ispending(struct dentry *dentry)
 	return 0;
 }
 
-static inline void autofs4_copy_atime(struct file *src, struct file *dst)
-{
-	dst->f_path.dentry->d_inode->i_atime =
-		src->f_path.dentry->d_inode->i_atime;
-	return;
-}
-
-struct inode *autofs4_get_inode(struct super_block *, struct autofs_info *);
+struct inode *autofs4_get_inode(struct super_block *, mode_t);
 void autofs4_free_ino(struct autofs_info *);
 
 /* Expiration */
@@ -212,16 +196,89 @@ void autofs_dev_ioctl_exit(void);
 
 extern const struct inode_operations autofs4_symlink_inode_operations;
 extern const struct inode_operations autofs4_dir_inode_operations;
-extern const struct inode_operations autofs4_root_inode_operations;
-extern const struct inode_operations autofs4_indirect_root_inode_operations;
-extern const struct inode_operations autofs4_direct_root_inode_operations;
 extern const struct file_operations autofs4_dir_operations;
 extern const struct file_operations autofs4_root_operations;
+extern const struct dentry_operations autofs4_dentry_operations;
+
+/* VFS automount flags management functions */
+
+static inline void __managed_dentry_set_automount(struct dentry *dentry)
+{
+	dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
+}
+
+static inline void managed_dentry_set_automount(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_set_automount(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_clear_automount(struct dentry *dentry)
+{
+	dentry->d_flags &= ~DCACHE_NEED_AUTOMOUNT;
+}
+
+static inline void managed_dentry_clear_automount(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_clear_automount(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_set_transit(struct dentry *dentry)
+{
+	dentry->d_flags |= DCACHE_MANAGE_TRANSIT;
+}
+
+static inline void managed_dentry_set_transit(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_set_transit(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_clear_transit(struct dentry *dentry)
+{
+	dentry->d_flags &= ~DCACHE_MANAGE_TRANSIT;
+}
+
+static inline void managed_dentry_clear_transit(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_clear_transit(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_set_managed(struct dentry *dentry)
+{
+	dentry->d_flags |= (DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT);
+}
+
+static inline void managed_dentry_set_managed(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_set_managed(dentry);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline void __managed_dentry_clear_managed(struct dentry *dentry)
+{
+	dentry->d_flags &= ~(DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT);
+}
+
+static inline void managed_dentry_clear_managed(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	__managed_dentry_clear_managed(dentry);
+	spin_unlock(&dentry->d_lock);
+}
 
 /* Initializing function */
 
 int autofs4_fill_super(struct super_block *, void *, int);
-struct autofs_info *autofs4_init_ino(struct autofs_info *, struct autofs_sb_info *sbi, mode_t mode);
+struct autofs_info *autofs4_new_ino(struct autofs_sb_info *);
+void autofs4_clean_ino(struct autofs_info *);
 
 /* Queue management functions */
 
@@ -229,19 +286,6 @@ int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify);
 int autofs4_wait_release(struct autofs_sb_info *,autofs_wqt_t,int);
 void autofs4_catatonic_mode(struct autofs_sb_info *);
 
-static inline int autofs4_follow_mount(struct path *path)
-{
-	int res = 0;
-
-	while (d_mountpoint(path->dentry)) {
-		int followed = follow_down(path);
-		if (!followed)
-			break;
-		res = 1;
-	}
-	return res;
-}
-
 static inline u32 autofs4_get_dev(struct autofs_sb_info *sbi)
 {
 	return new_encode_dev(sbi->sb->s_dev);
@@ -294,5 +338,4 @@ static inline void autofs4_del_expiring(struct dentry *dentry)
 	return;
 }
 
-void autofs4_dentry_release(struct dentry *);
 extern void autofs4_kill_sb(struct super_block *);
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index eff9a419469a..1442da4860e5 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -551,7 +551,7 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp,
 
 		err = have_submounts(path.dentry);
 
-		if (follow_down(&path))
+		if (follow_down_one(&path))
 			magic = path.mnt->mnt_sb->s_magic;
 	}
 
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index cc1d01365905..f43100b9662b 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -26,10 +26,6 @@ static inline int autofs4_can_expire(struct dentry *dentry,
 	if (ino == NULL)
 		return 0;
 
-	/* No point expiring a pending mount */
-	if (ino->flags & AUTOFS_INF_PENDING)
-		return 0;
-
 	if (!do_now) {
 		/* Too young to die */
 		if (!timeout || time_after(ino->last_used + timeout, now))
@@ -56,7 +52,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 
 	path_get(&path);
 
-	if (!follow_down(&path))
+	if (!follow_down_one(&path))
 		goto done;
 
 	if (is_autofs4_dentry(path.dentry)) {
@@ -100,7 +96,7 @@ static struct dentry *get_next_positive_dentry(struct dentry *prev,
 	struct dentry *p, *ret;
 
 	if (prev == NULL)
-		return dget(prev);
+		return dget(root);
 
 	spin_lock(&autofs4_lock);
 relock:
@@ -137,7 +133,7 @@ again:
 	spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED);
 	/* Negative dentry - try next */
 	if (!simple_positive(ret)) {
-		spin_unlock(&ret->d_lock);
+		spin_unlock(&p->d_lock);
 		p = ret;
 		goto again;
 	}
@@ -283,6 +279,7 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	unsigned long timeout;
 	struct dentry *root = dget(sb->s_root);
 	int do_now = how & AUTOFS_EXP_IMMEDIATE;
+	struct autofs_info *ino;
 
 	if (!root)
 		return NULL;
@@ -291,19 +288,21 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	timeout = sbi->exp_timeout;
 
 	spin_lock(&sbi->fs_lock);
+	ino = autofs4_dentry_ino(root);
+	/* No point expiring a pending mount */
+	if (ino->flags & AUTOFS_INF_PENDING) {
+		spin_unlock(&sbi->fs_lock);
+		return NULL;
+	}
+	managed_dentry_set_transit(root);
 	if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
 		struct autofs_info *ino = autofs4_dentry_ino(root);
-		if (d_mountpoint(root)) {
-			ino->flags |= AUTOFS_INF_MOUNTPOINT;
-			spin_lock(&root->d_lock);
-			root->d_flags &= ~DCACHE_MOUNTED;
-			spin_unlock(&root->d_lock);
-		}
 		ino->flags |= AUTOFS_INF_EXPIRING;
 		init_completion(&ino->expire_complete);
 		spin_unlock(&sbi->fs_lock);
 		return root;
 	}
+	managed_dentry_clear_transit(root);
 	spin_unlock(&sbi->fs_lock);
 	dput(root);
 
@@ -340,6 +339,10 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	while ((dentry = get_next_positive_dentry(dentry, root))) {
 		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(dentry);
+		/* No point expiring a pending mount */
+		if (ino->flags & AUTOFS_INF_PENDING)
+			goto cont;
+		managed_dentry_set_transit(dentry);
 
 		/*
 		 * Case 1: (i) indirect mount or top level pseudo direct mount
@@ -399,6 +402,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 			}
 		}
 next:
+		managed_dentry_clear_transit(dentry);
+cont:
 		spin_unlock(&sbi->fs_lock);
 	}
 	return NULL;
@@ -479,6 +484,8 @@ int autofs4_expire_run(struct super_block *sb,
 	spin_lock(&sbi->fs_lock);
 	ino = autofs4_dentry_ino(dentry);
 	ino->flags &= ~AUTOFS_INF_EXPIRING;
+	if (!d_unhashed(dentry))
+		managed_dentry_clear_transit(dentry);
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 
@@ -504,18 +511,18 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		ret = autofs4_wait(sbi, dentry, NFY_EXPIRE);
 
 		spin_lock(&sbi->fs_lock);
-		if (ino->flags & AUTOFS_INF_MOUNTPOINT) {
-			spin_lock(&sb->s_root->d_lock);
-			/*
-			 * If we haven't been expired away, then reset
-			 * mounted status.
-			 */
-			if (mnt->mnt_parent != mnt)
-				sb->s_root->d_flags |= DCACHE_MOUNTED;
-			spin_unlock(&sb->s_root->d_lock);
-			ino->flags &= ~AUTOFS_INF_MOUNTPOINT;
-		}
 		ino->flags &= ~AUTOFS_INF_EXPIRING;
+		spin_lock(&dentry->d_lock);
+		if (ret)
+			__managed_dentry_clear_transit(dentry);
+		else {
+			if ((IS_ROOT(dentry) ||
+			    (autofs_type_indirect(sbi->type) &&
+			     IS_ROOT(dentry->d_parent))) &&
+			    !(dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
+				__managed_dentry_set_automount(dentry);
+		}
+		spin_unlock(&dentry->d_lock);
 		complete_all(&ino->expire_complete);
 		spin_unlock(&sbi->fs_lock);
 		dput(dentry);
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index a7bdb9dcac84..180fa2425e49 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -22,77 +22,27 @@
 #include "autofs_i.h"
 #include <linux/module.h>
 
-static void ino_lnkfree(struct autofs_info *ino)
+struct autofs_info *autofs4_new_ino(struct autofs_sb_info *sbi)
 {
-	if (ino->u.symlink) {
-		kfree(ino->u.symlink);
-		ino->u.symlink = NULL;
-	}
-}
-
-struct autofs_info *autofs4_init_ino(struct autofs_info *ino,
-				     struct autofs_sb_info *sbi, mode_t mode)
-{
-	int reinit = 1;
-
-	if (ino == NULL) {
-		reinit = 0;
-		ino = kmalloc(sizeof(*ino), GFP_KERNEL);
-	}
-
-	if (ino == NULL)
-		return NULL;
-
-	if (!reinit) {
-		ino->flags = 0;
-		ino->inode = NULL;
-		ino->dentry = NULL;
-		ino->size = 0;
+	struct autofs_info *ino = kzalloc(sizeof(*ino), GFP_KERNEL);
+	if (ino) {
 		INIT_LIST_HEAD(&ino->active);
-		ino->active_count = 0;
 		INIT_LIST_HEAD(&ino->expiring);
-		atomic_set(&ino->count, 0);
+		ino->last_used = jiffies;
+		ino->sbi = sbi;
 	}
+	return ino;
+}
 
+void autofs4_clean_ino(struct autofs_info *ino)
+{
 	ino->uid = 0;
 	ino->gid = 0;
-	ino->mode = mode;
 	ino->last_used = jiffies;
-
-	ino->sbi = sbi;
-
-	if (reinit && ino->free)
-		(ino->free)(ino);
-
-	memset(&ino->u, 0, sizeof(ino->u));
-
-	ino->free = NULL;
-
-	if (S_ISLNK(mode))
-		ino->free = ino_lnkfree;
-
-	return ino;
 }
 
 void autofs4_free_ino(struct autofs_info *ino)
 {
-	struct autofs_info *p_ino;
-
-	if (ino->dentry) {
-		ino->dentry->d_fsdata = NULL;
-		if (ino->dentry->d_inode) {
-			struct dentry *parent = ino->dentry->d_parent;
-			if (atomic_dec_and_test(&ino->count)) {
-				p_ino = autofs4_dentry_ino(parent);
-				if (p_ino && parent != ino->dentry)
-					atomic_dec(&p_ino->count);
-			}
-			dput(ino->dentry);
-		}
-		ino->dentry = NULL;
-	}
-	if (ino->free)
-		(ino->free)(ino);
 	kfree(ino);
 }
 
@@ -148,9 +98,16 @@ static int autofs4_show_options(struct seq_file *m, struct vfsmount *mnt)
 	return 0;
 }
 
+static void autofs4_evict_inode(struct inode *inode)
+{
+	end_writeback(inode);
+	kfree(inode->i_private);
+}
+
 static const struct super_operations autofs4_sops = {
 	.statfs		= simple_statfs,
 	.show_options	= autofs4_show_options,
+	.evict_inode	= autofs4_evict_inode,
 };
 
 enum {Opt_err, Opt_fd, Opt_uid, Opt_gid, Opt_pgrp, Opt_minproto, Opt_maxproto,
@@ -240,21 +197,6 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid,
 	return (*pipefd < 0);
 }
 
-static struct autofs_info *autofs4_mkroot(struct autofs_sb_info *sbi)
-{
-	struct autofs_info *ino;
-
-	ino = autofs4_init_ino(NULL, sbi, S_IFDIR | 0755);
-	if (!ino)
-		return NULL;
-
-	return ino;
-}
-
-static const struct dentry_operations autofs4_sb_dentry_operations = {
-	.d_release      = autofs4_dentry_release,
-};
-
 int autofs4_fill_super(struct super_block *s, void *data, int silent)
 {
 	struct inode * root_inode;
@@ -292,15 +234,16 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	s->s_blocksize_bits = 10;
 	s->s_magic = AUTOFS_SUPER_MAGIC;
 	s->s_op = &autofs4_sops;
+	s->s_d_op = &autofs4_dentry_operations;
 	s->s_time_gran = 1;
 
 	/*
 	 * Get the root inode and dentry, but defer checking for errors.
 	 */
-	ino = autofs4_mkroot(sbi);
+	ino = autofs4_new_ino(sbi);
 	if (!ino)
 		goto fail_free;
-	root_inode = autofs4_get_inode(s, ino);
+	root_inode = autofs4_get_inode(s, S_IFDIR | 0755);
 	if (!root_inode)
 		goto fail_ino;
 
@@ -309,7 +252,6 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 		goto fail_iput;
 	pipe = NULL;
 
-	d_set_d_op(root, &autofs4_sb_dentry_operations);
 	root->d_fsdata = ino;
 
 	/* Can this call block? */
@@ -320,10 +262,11 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 		goto fail_dput;
 	}
 
+	if (autofs_type_trigger(sbi->type))
+		__managed_dentry_set_managed(root);
+
 	root_inode->i_fop = &autofs4_root_operations;
-	root_inode->i_op = autofs_type_trigger(sbi->type) ?
-			&autofs4_direct_root_inode_operations :
-			&autofs4_indirect_root_inode_operations;
+	root_inode->i_op = &autofs4_dir_inode_operations;
 
 	/* Couldn't this be tested earlier? */
 	if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION ||
@@ -383,16 +326,14 @@ fail_unlock:
 	return -EINVAL;
 }
 
-struct inode *autofs4_get_inode(struct super_block *sb,
-				struct autofs_info *inf)
+struct inode *autofs4_get_inode(struct super_block *sb, mode_t mode)
 {
 	struct inode *inode = new_inode(sb);
 
 	if (inode == NULL)
 		return NULL;
 
-	inf->inode = inode;
-	inode->i_mode = inf->mode;
+	inode->i_mode = mode;
 	if (sb->s_root) {
 		inode->i_uid = sb->s_root->d_inode->i_uid;
 		inode->i_gid = sb->s_root->d_inode->i_gid;
@@ -400,12 +341,11 @@ struct inode *autofs4_get_inode(struct super_block *sb,
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	inode->i_ino = get_next_ino();
 
-	if (S_ISDIR(inf->mode)) {
+	if (S_ISDIR(mode)) {
 		inode->i_nlink = 2;
 		inode->i_op = &autofs4_dir_inode_operations;
 		inode->i_fop = &autofs4_dir_operations;
-	} else if (S_ISLNK(inf->mode)) {
-		inode->i_size = inf->size;
+	} else if (S_ISLNK(mode)) {
 		inode->i_op = &autofs4_symlink_inode_operations;
 	}
 
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 651e4ef563b1..014e7aba3b08 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -35,10 +35,9 @@ static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
 #endif
 static int autofs4_dir_open(struct inode *inode, struct file *file);
 static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
-static void *autofs4_follow_link(struct dentry *, struct nameidata *);
-
-#define TRIGGER_FLAGS   (LOOKUP_CONTINUE | LOOKUP_DIRECTORY)
-#define TRIGGER_INTENTS (LOOKUP_OPEN | LOOKUP_CREATE)
+static struct vfsmount *autofs4_d_automount(struct path *);
+static int autofs4_d_manage(struct dentry *, bool, bool);
+static void autofs4_dentry_release(struct dentry *);
 
 const struct file_operations autofs4_root_operations = {
 	.open		= dcache_dir_open,
@@ -60,7 +59,7 @@ const struct file_operations autofs4_dir_operations = {
 	.llseek		= dcache_dir_lseek,
 };
 
-const struct inode_operations autofs4_indirect_root_inode_operations = {
+const struct inode_operations autofs4_dir_inode_operations = {
 	.lookup		= autofs4_lookup,
 	.unlink		= autofs4_dir_unlink,
 	.symlink	= autofs4_dir_symlink,
@@ -68,20 +67,10 @@ const struct inode_operations autofs4_indirect_root_inode_operations = {
 	.rmdir		= autofs4_dir_rmdir,
 };
 
-const struct inode_operations autofs4_direct_root_inode_operations = {
-	.lookup		= autofs4_lookup,
-	.unlink		= autofs4_dir_unlink,
-	.mkdir		= autofs4_dir_mkdir,
-	.rmdir		= autofs4_dir_rmdir,
-	.follow_link	= autofs4_follow_link,
-};
-
-const struct inode_operations autofs4_dir_inode_operations = {
-	.lookup		= autofs4_lookup,
-	.unlink		= autofs4_dir_unlink,
-	.symlink	= autofs4_dir_symlink,
-	.mkdir		= autofs4_dir_mkdir,
-	.rmdir		= autofs4_dir_rmdir,
+const struct dentry_operations autofs4_dentry_operations = {
+	.d_automount	= autofs4_d_automount,
+	.d_manage	= autofs4_d_manage,
+	.d_release	= autofs4_dentry_release,
 };
 
 static void autofs4_add_active(struct dentry *dentry)
@@ -116,14 +105,6 @@ static void autofs4_del_active(struct dentry *dentry)
 	return;
 }
 
-static unsigned int autofs4_need_mount(unsigned int flags)
-{
-	unsigned int res = 0;
-	if (flags & (TRIGGER_FLAGS | TRIGGER_INTENTS))
-		res = 1;
-	return res;
-}
-
 static int autofs4_dir_open(struct inode *inode, struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
@@ -158,278 +139,27 @@ out:
 	return dcache_dir_open(inode, file);
 }
 
-static int try_to_fill_dentry(struct dentry *dentry, int flags)
-{
-	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
-	int status;
-
-	DPRINTK("dentry=%p %.*s ino=%p",
-		 dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
-
-	/*
-	 * Wait for a pending mount, triggering one if there
-	 * isn't one already
-	 */
-	if (dentry->d_inode == NULL) {
-		DPRINTK("waiting for mount name=%.*s",
-			 dentry->d_name.len, dentry->d_name.name);
-
-		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
-
-		DPRINTK("mount done status=%d", status);
-
-		/* Turn this into a real negative dentry? */
-		if (status == -ENOENT) {
-			spin_lock(&sbi->fs_lock);
-			ino->flags &= ~AUTOFS_INF_PENDING;
-			spin_unlock(&sbi->fs_lock);
-			return status;
-		} else if (status) {
-			/* Return a negative dentry, but leave it "pending" */
-			return status;
-		}
-	/* Trigger mount for path component or follow link */
-	} else if (ino->flags & AUTOFS_INF_PENDING ||
-			autofs4_need_mount(flags)) {
-		DPRINTK("waiting for mount name=%.*s",
-			dentry->d_name.len, dentry->d_name.name);
-
-		spin_lock(&sbi->fs_lock);
-		ino->flags |= AUTOFS_INF_PENDING;
-		spin_unlock(&sbi->fs_lock);
-		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
-
-		DPRINTK("mount done status=%d", status);
-
-		if (status) {
-			spin_lock(&sbi->fs_lock);
-			ino->flags &= ~AUTOFS_INF_PENDING;
-			spin_unlock(&sbi->fs_lock);
-			return status;
-		}
-	}
-
-	/* Initialize expiry counter after successful mount */
-	ino->last_used = jiffies;
-
-	spin_lock(&sbi->fs_lock);
-	ino->flags &= ~AUTOFS_INF_PENDING;
-	spin_unlock(&sbi->fs_lock);
-
-	return 0;
-}
-
-/* For autofs direct mounts the follow link triggers the mount */
-static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
-	int oz_mode = autofs4_oz_mode(sbi);
-	unsigned int lookup_type;
-	int status;
-
-	DPRINTK("dentry=%p %.*s oz_mode=%d nd->flags=%d",
-		dentry, dentry->d_name.len, dentry->d_name.name, oz_mode,
-		nd->flags);
-	/*
-	 * For an expire of a covered direct or offset mount we need
-	 * to break out of follow_down() at the autofs mount trigger
-	 * (d_mounted--), so we can see the expiring flag, and manage
-	 * the blocking and following here until the expire is completed.
-	 */
-	if (oz_mode) {
-		spin_lock(&sbi->fs_lock);
-		if (ino->flags & AUTOFS_INF_EXPIRING) {
-			spin_unlock(&sbi->fs_lock);
-			/* Follow down to our covering mount. */
-			if (!follow_down(&nd->path))
-				goto done;
-			goto follow;
-		}
-		spin_unlock(&sbi->fs_lock);
-		goto done;
-	}
-
-	/* If an expire request is pending everyone must wait. */
-	autofs4_expire_wait(dentry);
-
-	/* We trigger a mount for almost all flags */
-	lookup_type = autofs4_need_mount(nd->flags);
-	spin_lock(&sbi->fs_lock);
-	spin_lock(&autofs4_lock);
-	spin_lock(&dentry->d_lock);
-	if (!(lookup_type || ino->flags & AUTOFS_INF_PENDING)) {
-		spin_unlock(&dentry->d_lock);
-		spin_unlock(&autofs4_lock);
-		spin_unlock(&sbi->fs_lock);
-		goto follow;
-	}
-
-	/*
-	 * If the dentry contains directories then it is an autofs
-	 * multi-mount with no root mount offset. So don't try to
-	 * mount it again.
-	 */
-	if (ino->flags & AUTOFS_INF_PENDING ||
-	    (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs))) {
-		spin_unlock(&dentry->d_lock);
-		spin_unlock(&autofs4_lock);
-		spin_unlock(&sbi->fs_lock);
-
-		status = try_to_fill_dentry(dentry, nd->flags);
-		if (status)
-			goto out_error;
-
-		goto follow;
-	}
-	spin_unlock(&dentry->d_lock);
-	spin_unlock(&autofs4_lock);
-	spin_unlock(&sbi->fs_lock);
-follow:
-	/*
-	 * If there is no root mount it must be an autofs
-	 * multi-mount with no root offset so we don't need
-	 * to follow it.
-	 */
-	if (d_mountpoint(dentry)) {
-		if (!autofs4_follow_mount(&nd->path)) {
-			status = -ENOENT;
-			goto out_error;
-		}
-	}
-
-done:
-	return NULL;
-
-out_error:
-	path_put(&nd->path);
-	return ERR_PTR(status);
-}
-
-/*
- * Revalidate is called on every cache lookup.  Some of those
- * cache lookups may actually happen while the dentry is not
- * yet completely filled in, and revalidate has to delay such
- * lookups..
- */
-static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
+static void autofs4_dentry_release(struct dentry *de)
 {
-	struct inode *dir;
-	struct autofs_sb_info *sbi;
-	int oz_mode;
-	int flags = nd ? nd->flags : 0;
-	int status = 1;
-
-	if (flags & LOOKUP_RCU)
-		return -ECHILD;
-
-	dir = dentry->d_parent->d_inode;
-	sbi = autofs4_sbi(dir->i_sb);
-	oz_mode = autofs4_oz_mode(sbi);
-
-	/* Pending dentry */
-	spin_lock(&sbi->fs_lock);
-	if (autofs4_ispending(dentry)) {
-		/* The daemon never causes a mount to trigger */
-		spin_unlock(&sbi->fs_lock);
-
-		if (oz_mode)
-			return 1;
-
-		/*
-		 * If the directory has gone away due to an expire
-		 * we have been called as ->d_revalidate() and so
-		 * we need to return false and proceed to ->lookup().
-		 */
-		if (autofs4_expire_wait(dentry) == -EAGAIN)
-			return 0;
-
-		/*
-		 * A zero status is success otherwise we have a
-		 * negative error code.
-		 */
-		status = try_to_fill_dentry(dentry, flags);
-		if (status == 0)
-			return 1;
-
-		return status;
-	}
-	spin_unlock(&sbi->fs_lock);
-
-	/* Negative dentry.. invalidate if "old" */
-	if (dentry->d_inode == NULL)
-		return 0;
-
-	/* Check for a non-mountpoint directory with no contents */
-	spin_lock(&autofs4_lock);
-	spin_lock(&dentry->d_lock);
-	if (S_ISDIR(dentry->d_inode->i_mode) &&
-	    !d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
-		DPRINTK("dentry=%p %.*s, emptydir",
-			 dentry, dentry->d_name.len, dentry->d_name.name);
-		spin_unlock(&dentry->d_lock);
-		spin_unlock(&autofs4_lock);
-
-		/* The daemon never causes a mount to trigger */
-		if (oz_mode)
-			return 1;
-
-		/*
-		 * A zero status is success otherwise we have a
-		 * negative error code.
-		 */
-		status = try_to_fill_dentry(dentry, flags);
-		if (status == 0)
-			return 1;
-
-		return status;
-	}
-	spin_unlock(&dentry->d_lock);
-	spin_unlock(&autofs4_lock);
-
-	return 1;
-}
-
-void autofs4_dentry_release(struct dentry *de)
-{
-	struct autofs_info *inf;
+	struct autofs_info *ino = autofs4_dentry_ino(de);
+	struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb);
 
 	DPRINTK("releasing %p", de);
 
-	inf = autofs4_dentry_ino(de);
-	de->d_fsdata = NULL;
-
-	if (inf) {
-		struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb);
-
-		if (sbi) {
-			spin_lock(&sbi->lookup_lock);
-			if (!list_empty(&inf->active))
-				list_del(&inf->active);
-			if (!list_empty(&inf->expiring))
-				list_del(&inf->expiring);
-			spin_unlock(&sbi->lookup_lock);
-		}
-
-		inf->dentry = NULL;
-		inf->inode = NULL;
+	if (!ino)
+		return;
 
-		autofs4_free_ino(inf);
+	if (sbi) {
+		spin_lock(&sbi->lookup_lock);
+		if (!list_empty(&ino->active))
+			list_del(&ino->active);
+		if (!list_empty(&ino->expiring))
+			list_del(&ino->expiring);
+		spin_unlock(&sbi->lookup_lock);
 	}
-}
 
-/* For dentries of directories in the root dir */
-static const struct dentry_operations autofs4_root_dentry_operations = {
-	.d_revalidate	= autofs4_revalidate,
-	.d_release	= autofs4_dentry_release,
-};
-
-/* For other dentries */
-static const struct dentry_operations autofs4_dentry_operations = {
-	.d_revalidate	= autofs4_revalidate,
-	.d_release	= autofs4_dentry_release,
-};
+	autofs4_free_ino(ino);
+}
 
 static struct dentry *autofs4_lookup_active(struct dentry *dentry)
 {
@@ -541,51 +271,246 @@ next:
 	return NULL;
 }
 
+static int autofs4_mount_wait(struct dentry *dentry)
+{
+	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	int status;
+
+	if (ino->flags & AUTOFS_INF_PENDING) {
+		DPRINTK("waiting for mount name=%.*s",
+			dentry->d_name.len, dentry->d_name.name);
+		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
+		DPRINTK("mount wait done status=%d", status);
+		ino->last_used = jiffies;
+		return status;
+	}
+	return 0;
+}
+
+static int do_expire_wait(struct dentry *dentry)
+{
+	struct dentry *expiring;
+
+	expiring = autofs4_lookup_expiring(dentry);
+	if (!expiring)
+		return autofs4_expire_wait(dentry);
+	else {
+		/*
+		 * If we are racing with expire the request might not
+		 * be quite complete, but the directory has been removed
+		 * so it must have been successful, just wait for it.
+		 */
+		autofs4_expire_wait(expiring);
+		autofs4_del_expiring(expiring);
+		dput(expiring);
+	}
+	return 0;
+}
+
+static struct dentry *autofs4_mountpoint_changed(struct path *path)
+{
+	struct dentry *dentry = path->dentry;
+	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+
+	/*
+	 * If this is an indirect mount the dentry could have gone away
+	 * as a result of an expire and a new one created.
+	 */
+	if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
+		struct dentry *parent = dentry->d_parent;
+		struct dentry *new = d_lookup(parent, &dentry->d_name);
+		if (!new)
+			return NULL;
+		dput(path->dentry);
+		path->dentry = new;
+	}
+	return path->dentry;
+}
+
+static struct vfsmount *autofs4_d_automount(struct path *path)
+{
+	struct dentry *dentry = path->dentry;
+	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	int status;
+
+	DPRINTK("dentry=%p %.*s",
+		dentry, dentry->d_name.len, dentry->d_name.name);
+
+	/*
+	 * Someone may have manually umounted this or it was a submount
+	 * that has gone away.
+	 */
+	spin_lock(&dentry->d_lock);
+	if (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
+		if (!(dentry->d_flags & DCACHE_MANAGE_TRANSIT) &&
+		     (dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
+			__managed_dentry_set_transit(path->dentry);
+	}
+	spin_unlock(&dentry->d_lock);
+
+	/* The daemon never triggers a mount. */
+	if (autofs4_oz_mode(sbi))
+		return NULL;
+
+	/*
+	 * If an expire request is pending everyone must wait.
+	 * If the expire fails we're still mounted so continue
+	 * the follow and return. A return of -EAGAIN (which only
+	 * happens with indirect mounts) means the expire completed
+	 * and the directory was removed, so just go ahead and try
+	 * the mount.
+	 */
+	status = do_expire_wait(dentry);
+	if (status && status != -EAGAIN)
+		return NULL;
+
+	/* Callback to the daemon to perform the mount or wait */
+	spin_lock(&sbi->fs_lock);
+	if (ino->flags & AUTOFS_INF_PENDING) {
+		spin_unlock(&sbi->fs_lock);
+		status = autofs4_mount_wait(dentry);
+		if (status)
+			return ERR_PTR(status);
+		spin_lock(&sbi->fs_lock);
+		goto done;
+	}
+
+	/*
+	 * If the dentry is a symlink it's equivalent to a directory
+	 * having d_mountpoint() true, so there's no need to call back
+	 * to the daemon.
+	 */
+	if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode))
+		goto done;
+	if (!d_mountpoint(dentry)) {
+		/*
+		 * It's possible that user space hasn't removed directories
+		 * after umounting a rootless multi-mount, although it
+		 * should. For v5 have_submounts() is sufficient to handle
+		 * this because the leaves of the directory tree under the
+		 * mount never trigger mounts themselves (they have an autofs
+		 * trigger mount mounted on them). But v4 pseudo direct mounts
+		 * do need the leaves to to trigger mounts. In this case we
+		 * have no choice but to use the list_empty() check and
+		 * require user space behave.
+		 */
+		if (sbi->version > 4) {
+			if (have_submounts(dentry))
+				goto done;
+		} else {
+			spin_lock(&dentry->d_lock);
+			if (!list_empty(&dentry->d_subdirs)) {
+				spin_unlock(&dentry->d_lock);
+				goto done;
+			}
+			spin_unlock(&dentry->d_lock);
+		}
+		ino->flags |= AUTOFS_INF_PENDING;
+		spin_unlock(&sbi->fs_lock);
+		status = autofs4_mount_wait(dentry);
+		if (status)
+			return ERR_PTR(status);
+		spin_lock(&sbi->fs_lock);
+		ino->flags &= ~AUTOFS_INF_PENDING;
+	}
+done:
+	if (!(ino->flags & AUTOFS_INF_EXPIRING)) {
+		/*
+		 * Any needed mounting has been completed and the path updated
+		 * so turn this into a normal dentry so we don't continually
+		 * call ->d_automount() and ->d_manage().
+		 */
+		spin_lock(&dentry->d_lock);
+		__managed_dentry_clear_transit(dentry);
+		/*
+		 * Only clear DMANAGED_AUTOMOUNT for rootless multi-mounts and
+		 * symlinks as in all other cases the dentry will be covered by
+		 * an actual mount so ->d_automount() won't be called during
+		 * the follow.
+		 */
+		if ((!d_mountpoint(dentry) &&
+		    !list_empty(&dentry->d_subdirs)) ||
+		    (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)))
+			__managed_dentry_clear_automount(dentry);
+		spin_unlock(&dentry->d_lock);
+	}
+	spin_unlock(&sbi->fs_lock);
+
+	/* Mount succeeded, check if we ended up with a new dentry */
+	dentry = autofs4_mountpoint_changed(path);
+	if (!dentry)
+		return ERR_PTR(-ENOENT);
+
+	return NULL;
+}
+
+int autofs4_d_manage(struct dentry *dentry, bool mounting_here, bool rcu_walk)
+{
+	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+
+	DPRINTK("dentry=%p %.*s",
+		dentry, dentry->d_name.len, dentry->d_name.name);
+
+	/* The daemon never waits. */
+	if (autofs4_oz_mode(sbi) || mounting_here) {
+		if (!d_mountpoint(dentry))
+			return -EISDIR;
+		return 0;
+	}
+
+	/* We need to sleep, so we need pathwalk to be in ref-mode */
+	if (rcu_walk)
+		return -ECHILD;
+
+	/* Wait for pending expires */
+	do_expire_wait(dentry);
+
+	/*
+	 * This dentry may be under construction so wait on mount
+	 * completion.
+	 */
+	return autofs4_mount_wait(dentry);
+}
+
 /* Lookups in the root directory */
 static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 {
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
-	struct dentry *expiring, *active;
-	int oz_mode;
+	struct dentry *active;
 
-	DPRINTK("name = %.*s",
-		dentry->d_name.len, dentry->d_name.name);
+	DPRINTK("name = %.*s", dentry->d_name.len, dentry->d_name.name);
 
 	/* File name too long to exist */
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
 
 	sbi = autofs4_sbi(dir->i_sb);
-	oz_mode = autofs4_oz_mode(sbi);
 
 	DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d",
-		 current->pid, task_pgrp_nr(current), sbi->catatonic, oz_mode);
+		current->pid, task_pgrp_nr(current), sbi->catatonic,
+		autofs4_oz_mode(sbi));
 
 	active = autofs4_lookup_active(dentry);
 	if (active) {
-		dentry = active;
-		ino = autofs4_dentry_ino(dentry);
+		return active;
 	} else {
 		/*
-		 * Mark the dentry incomplete but don't hash it. We do this
-		 * to serialize our inode creation operations (symlink and
-		 * mkdir) which prevents deadlock during the callback to
-		 * the daemon. Subsequent user space lookups for the same
-		 * dentry are placed on the wait queue while the daemon
-		 * itself is allowed passage unresticted so the create
-		 * operation itself can then hash the dentry. Finally,
-		 * we check for the hashed dentry and return the newly
-		 * hashed dentry.
+		 * A dentry that is not within the root can never trigger a
+		 * mount operation, unless the directory already exists, so we
+		 * can return fail immediately.  The daemon however does need
+		 * to create directories within the file system.
 		 */
-		d_set_d_op(dentry, &autofs4_root_dentry_operations);
+		if (!autofs4_oz_mode(sbi) && !IS_ROOT(dentry->d_parent))
+			return ERR_PTR(-ENOENT);
 
-		/*
-		 * And we need to ensure that the same dentry is used for
-		 * all following lookup calls until it is hashed so that
-		 * the dentry flags are persistent throughout the request.
-		 */
-		ino = autofs4_init_ino(NULL, sbi, 0555);
+		/* Mark entries in the root as mount triggers */
+		if (autofs_type_indirect(sbi->type) && IS_ROOT(dentry->d_parent))
+			__managed_dentry_set_managed(dentry);
+
+		ino = autofs4_new_ino(sbi);
 		if (!ino)
 			return ERR_PTR(-ENOMEM);
 
@@ -596,82 +521,6 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
 
 		d_instantiate(dentry, NULL);
 	}
-
-	if (!oz_mode) {
-		mutex_unlock(&dir->i_mutex);
-		expiring = autofs4_lookup_expiring(dentry);
-		if (expiring) {
-			/*
-			 * If we are racing with expire the request might not
-			 * be quite complete but the directory has been removed
-			 * so it must have been successful, so just wait for it.
-			 */
-			autofs4_expire_wait(expiring);
-			autofs4_del_expiring(expiring);
-			dput(expiring);
-		}
-
-		spin_lock(&sbi->fs_lock);
-		ino->flags |= AUTOFS_INF_PENDING;
-		spin_unlock(&sbi->fs_lock);
-		if (dentry->d_op && dentry->d_op->d_revalidate)
-			(dentry->d_op->d_revalidate)(dentry, nd);
-		mutex_lock(&dir->i_mutex);
-	}
-
-	/*
-	 * If we are still pending, check if we had to handle
-	 * a signal. If so we can force a restart..
-	 */
-	if (ino->flags & AUTOFS_INF_PENDING) {
-		/* See if we were interrupted */
-		if (signal_pending(current)) {
-			sigset_t *sigset = &current->pending.signal;
-			if (sigismember (sigset, SIGKILL) ||
-			    sigismember (sigset, SIGQUIT) ||
-			    sigismember (sigset, SIGINT)) {
-			    if (active)
-				dput(active);
-			    return ERR_PTR(-ERESTARTNOINTR);
-			}
-		}
-		if (!oz_mode) {
-			spin_lock(&sbi->fs_lock);
-			ino->flags &= ~AUTOFS_INF_PENDING;
-			spin_unlock(&sbi->fs_lock);
-		}
-	}
-
-	/*
-	 * If this dentry is unhashed, then we shouldn't honour this
-	 * lookup.  Returning ENOENT here doesn't do the right thing
-	 * for all system calls, but it should be OK for the operations
-	 * we permit from an autofs.
-	 */
-	if (!oz_mode && d_unhashed(dentry)) {
-		/*
-		 * A user space application can (and has done in the past)
-		 * remove and re-create this directory during the callback.
-		 * This can leave us with an unhashed dentry, but a
-		 * successful mount!  So we need to perform another
-		 * cached lookup in case the dentry now exists.
-		 */
-		struct dentry *parent = dentry->d_parent;
-		struct dentry *new = d_lookup(parent, &dentry->d_name);
-		if (new != NULL)
-			dentry = new;
-		else
-			dentry = ERR_PTR(-ENOENT);
-
-		if (active)
-			dput(active);
-
-		return dentry;
-	}
-
-	if (active)
-		return active;
-
 	return NULL;
 }
 
@@ -683,6 +532,7 @@ static int autofs4_dir_symlink(struct inode *dir,
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	struct autofs_info *p_ino;
 	struct inode *inode;
+	size_t size = strlen(symname);
 	char *cp;
 
 	DPRINTK("%s <- %.*s", symname,
@@ -691,45 +541,35 @@ static int autofs4_dir_symlink(struct inode *dir,
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
 
-	ino = autofs4_init_ino(ino, sbi, S_IFLNK | 0555);
-	if (!ino)
-		return -ENOMEM;
+	BUG_ON(!ino);
+
+	autofs4_clean_ino(ino);
 
 	autofs4_del_active(dentry);
 
-	ino->size = strlen(symname);
-	cp = kmalloc(ino->size + 1, GFP_KERNEL);
-	if (!cp) {
-		if (!dentry->d_fsdata)
-			kfree(ino);
+	cp = kmalloc(size + 1, GFP_KERNEL);
+	if (!cp)
 		return -ENOMEM;
-	}
 
 	strcpy(cp, symname);
 
-	inode = autofs4_get_inode(dir->i_sb, ino);
+	inode = autofs4_get_inode(dir->i_sb, S_IFLNK | 0555);
 	if (!inode) {
 		kfree(cp);
 		if (!dentry->d_fsdata)
 			kfree(ino);
 		return -ENOMEM;
 	}
+	inode->i_private = cp;
+	inode->i_size = size;
 	d_add(dentry, inode);
 
-	if (dir == dir->i_sb->s_root->d_inode)
-		d_set_d_op(dentry, &autofs4_root_dentry_operations);
-	else
-		d_set_d_op(dentry, &autofs4_dentry_operations);
-
-	dentry->d_fsdata = ino;
-	ino->dentry = dget(dentry);
+	dget(dentry);
 	atomic_inc(&ino->count);
 	p_ino = autofs4_dentry_ino(dentry->d_parent);
 	if (p_ino && dentry->d_parent != dentry)
 		atomic_inc(&p_ino->count);
-	ino->inode = inode;
 
-	ino->u.symlink = cp;
 	dir->i_mtime = CURRENT_TIME;
 
 	return 0;
@@ -782,6 +622,58 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
 	return 0;
 }
 
+/*
+ * Version 4 of autofs provides a pseudo direct mount implementation
+ * that relies on directories at the leaves of a directory tree under
+ * an indirect mount to trigger mounts. To allow for this we need to
+ * set the DMANAGED_AUTOMOUNT and DMANAGED_TRANSIT flags on the leaves
+ * of the directory tree. There is no need to clear the automount flag
+ * following a mount or restore it after an expire because these mounts
+ * are always covered. However, it is neccessary to ensure that these
+ * flags are clear on non-empty directories to avoid unnecessary calls
+ * during path walks.
+ */
+static void autofs_set_leaf_automount_flags(struct dentry *dentry)
+{
+	struct dentry *parent;
+
+	/* root and dentrys in the root are already handled */
+	if (IS_ROOT(dentry->d_parent))
+		return;
+
+	managed_dentry_set_managed(dentry);
+
+	parent = dentry->d_parent;
+	/* only consider parents below dentrys in the root */
+	if (IS_ROOT(parent->d_parent))
+		return;
+	managed_dentry_clear_managed(parent);
+	return;
+}
+
+static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
+{
+	struct list_head *d_child;
+	struct dentry *parent;
+
+	/* flags for dentrys in the root are handled elsewhere */
+	if (IS_ROOT(dentry->d_parent))
+		return;
+
+	managed_dentry_clear_managed(dentry);
+
+	parent = dentry->d_parent;
+	/* only consider parents below dentrys in the root */
+	if (IS_ROOT(parent->d_parent))
+		return;
+	d_child = &dentry->d_u.d_child;
+	/* Set parent managed if it's becoming empty */
+	if (d_child->next == &parent->d_subdirs &&
+	    d_child->prev == &parent->d_subdirs)
+		managed_dentry_set_managed(parent);
+	return;
+}
+
 static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
@@ -809,6 +701,9 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&autofs4_lock);
 
+	if (sbi->version < 5)
+		autofs_clear_leaf_automount_flags(dentry);
+
 	if (atomic_dec_and_test(&ino->count)) {
 		p_ino = autofs4_dentry_ino(dentry->d_parent);
 		if (p_ino && dentry->d_parent != dentry)
@@ -837,32 +732,25 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	DPRINTK("dentry %p, creating %.*s",
 		dentry, dentry->d_name.len, dentry->d_name.name);
 
-	ino = autofs4_init_ino(ino, sbi, S_IFDIR | 0555);
-	if (!ino)
-		return -ENOMEM;
+	BUG_ON(!ino);
+
+	autofs4_clean_ino(ino);
 
 	autofs4_del_active(dentry);
 
-	inode = autofs4_get_inode(dir->i_sb, ino);
-	if (!inode) {
-		if (!dentry->d_fsdata)
-			kfree(ino);
+	inode = autofs4_get_inode(dir->i_sb, S_IFDIR | 0555);
+	if (!inode)
 		return -ENOMEM;
-	}
 	d_add(dentry, inode);
 
-	if (dir == dir->i_sb->s_root->d_inode)
-		d_set_d_op(dentry, &autofs4_root_dentry_operations);
-	else
-		d_set_d_op(dentry, &autofs4_dentry_operations);
+	if (sbi->version < 5)
+		autofs_set_leaf_automount_flags(dentry);
 
-	dentry->d_fsdata = ino;
-	ino->dentry = dget(dentry);
+	dget(dentry);
 	atomic_inc(&ino->count);
 	p_ino = autofs4_dentry_ino(dentry->d_parent);
 	if (p_ino && dentry->d_parent != dentry)
 		atomic_inc(&p_ino->count);
-	ino->inode = inode;
 	inc_nlink(dir);
 	dir->i_mtime = CURRENT_TIME;
 
@@ -944,8 +832,7 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
 int is_autofs4_dentry(struct dentry *dentry)
 {
 	return dentry && dentry->d_inode &&
-		(dentry->d_op == &autofs4_root_dentry_operations ||
-		 dentry->d_op == &autofs4_dentry_operations) &&
+		dentry->d_op == &autofs4_dentry_operations &&
 		dentry->d_fsdata != NULL;
 }
 
diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c
index b4ea82934d2e..f27c094a1919 100644
--- a/fs/autofs4/symlink.c
+++ b/fs/autofs4/symlink.c
@@ -14,8 +14,7 @@
 
 static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
-	nd_set_link(nd, (char *)ino->u.symlink);
+	nd_set_link(nd, dentry->d_inode->i_private);
 	return NULL;
 }
 
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index c5f8459c905e..56010056b2e6 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -309,6 +309,9 @@ static int validate_request(struct autofs_wait_queue **wait,
 	 * completed while we waited on the mutex ...
 	 */
 	if (notify == NFY_MOUNT) {
+		struct dentry *new = NULL;
+		int valid = 1;
+
 		/*
 		 * If the dentry was successfully mounted while we slept
 		 * on the wait queue mutex we can return success. If it
@@ -316,8 +319,20 @@ static int validate_request(struct autofs_wait_queue **wait,
 		 * a multi-mount with no mount at it's base) we can
 		 * continue on and create a new request.
 		 */
+		if (!IS_ROOT(dentry)) {
+			if (dentry->d_inode && d_unhashed(dentry)) {
+				struct dentry *parent = dentry->d_parent;
+				new = d_lookup(parent, &dentry->d_name);
+				if (new)
+					dentry = new;
+			}
+		}
 		if (have_submounts(dentry))
-			return 0;
+			valid = 0;
+
+		if (new)
+			dput(new);
+		return valid;
 	}
 
 	return 1;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index fe3f59c14a02..333a7bb4cb9c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -432,6 +432,9 @@ static void init_once(void *foo)
 	mutex_init(&bdev->bd_mutex);
 	INIT_LIST_HEAD(&bdev->bd_inodes);
 	INIT_LIST_HEAD(&bdev->bd_list);
+#ifdef CONFIG_SYSFS
+	INIT_LIST_HEAD(&bdev->bd_holder_disks);
+#endif
 	inode_init_once(&ei->vfs_inode);
 	/* Initialize mutex for freeze. */
 	mutex_init(&bdev->bd_fsfreeze_mutex);
@@ -779,6 +782,23 @@ static struct block_device *bd_start_claiming(struct block_device *bdev,
 }
 
 #ifdef CONFIG_SYSFS
+struct bd_holder_disk {
+	struct list_head	list;
+	struct gendisk		*disk;
+	int			refcnt;
+};
+
+static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
+						  struct gendisk *disk)
+{
+	struct bd_holder_disk *holder;
+
+	list_for_each_entry(holder, &bdev->bd_holder_disks, list)
+		if (holder->disk == disk)
+			return holder;
+	return NULL;
+}
+
 static int add_symlink(struct kobject *from, struct kobject *to)
 {
 	return sysfs_create_link(from, to, kobject_name(to));
@@ -794,6 +814,8 @@ static void del_symlink(struct kobject *from, struct kobject *to)
  * @bdev: the claimed slave bdev
  * @disk: the holding disk
  *
+ * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
+ *
  * This functions creates the following sysfs symlinks.
  *
  * - from "slaves" directory of the holder @disk to the claimed @bdev
@@ -817,47 +839,83 @@ static void del_symlink(struct kobject *from, struct kobject *to)
  */
 int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 {
+	struct bd_holder_disk *holder;
 	int ret = 0;
 
 	mutex_lock(&bdev->bd_mutex);
 
-	WARN_ON_ONCE(!bdev->bd_holder || bdev->bd_holder_disk);
+	WARN_ON_ONCE(!bdev->bd_holder);
 
 	/* FIXME: remove the following once add_disk() handles errors */
 	if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir))
 		goto out_unlock;
 
-	ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
-	if (ret)
+	holder = bd_find_holder_disk(bdev, disk);
+	if (holder) {
+		holder->refcnt++;
 		goto out_unlock;
+	}
 
-	ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
-	if (ret) {
-		del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+	holder = kzalloc(sizeof(*holder), GFP_KERNEL);
+	if (!holder) {
+		ret = -ENOMEM;
 		goto out_unlock;
 	}
 
-	bdev->bd_holder_disk = disk;
+	INIT_LIST_HEAD(&holder->list);
+	holder->disk = disk;
+	holder->refcnt = 1;
+
+	ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+	if (ret)
+		goto out_free;
+
+	ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
+	if (ret)
+		goto out_del;
+
+	list_add(&holder->list, &bdev->bd_holder_disks);
+	goto out_unlock;
+
+out_del:
+	del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+out_free:
+	kfree(holder);
 out_unlock:
 	mutex_unlock(&bdev->bd_mutex);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(bd_link_disk_holder);
 
-static void bd_unlink_disk_holder(struct block_device *bdev)
+/**
+ * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder()
+ * @bdev: the calimed slave bdev
+ * @disk: the holding disk
+ *
+ * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
+ *
+ * CONTEXT:
+ * Might sleep.
+ */
+void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 {
-	struct gendisk *disk = bdev->bd_holder_disk;
+	struct bd_holder_disk *holder;
 
-	bdev->bd_holder_disk = NULL;
-	if (!disk)
-		return;
+	mutex_lock(&bdev->bd_mutex);
 
-	del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
-	del_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
+	holder = bd_find_holder_disk(bdev, disk);
+
+	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
+		del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+		del_symlink(bdev->bd_part->holder_dir,
+			    &disk_to_dev(disk)->kobj);
+		list_del_init(&holder->list);
+		kfree(holder);
+	}
+
+	mutex_unlock(&bdev->bd_mutex);
 }
-#else
-static inline void bd_unlink_disk_holder(struct block_device *bdev)
-{ }
+EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
 #endif
 
 /**
@@ -1380,7 +1438,6 @@ int blkdev_put(struct block_device *bdev, fmode_t mode)
 		 * unblock evpoll if it was a write holder.
 		 */
 		if (bdev_free) {
-			bd_unlink_disk_holder(bdev);
 			if (bdev->bd_write_holder) {
 				disk_unblock_events(bdev->bd_disk);
 				bdev->bd_write_holder = false;
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 7bb3c020e570..ecb9fd3be143 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -4,6 +4,8 @@ config BTRFS_FS
 	select LIBCRC32C
 	select ZLIB_INFLATE
 	select ZLIB_DEFLATE
+	select LZO_COMPRESS
+	select LZO_DECOMPRESS
 	help
 	  Btrfs is a new filesystem with extents, writable snapshotting,
 	  support for multiple devices and many more features.
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index a35eb36b32fd..31610ea73aec 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -6,5 +6,5 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   transaction.o inode.o file.o tree-defrag.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
-	   export.o tree-log.o acl.o free-space-cache.o zlib.o \
+	   export.o tree-log.o acl.o free-space-cache.o zlib.o lzo.o \
 	   compression.o delayed-ref.o relocation.o
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 6ae2c8cac9d5..9c949348510b 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -37,6 +37,9 @@ static struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 	char *value = NULL;
 	struct posix_acl *acl;
 
+	if (!IS_POSIXACL(inode))
+		return NULL;
+
 	acl = get_cached_acl(inode, type);
 	if (acl != ACL_NOT_CACHED)
 		return acl;
@@ -60,8 +63,10 @@ static struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 		size = __btrfs_getxattr(inode, name, value, size);
 		if (size > 0) {
 			acl = posix_acl_from_xattr(value, size);
-			if (IS_ERR(acl))
+			if (IS_ERR(acl)) {
+				kfree(value);
 				return acl;
+			}
 			set_cached_acl(inode, type, acl);
 		}
 		kfree(value);
@@ -82,6 +87,9 @@ static int btrfs_xattr_acl_get(struct dentry *dentry, const char *name,
 	struct posix_acl *acl;
 	int ret = 0;
 
+	if (!IS_POSIXACL(dentry->d_inode))
+		return -EOPNOTSUPP;
+
 	acl = btrfs_get_acl(dentry->d_inode, type);
 
 	if (IS_ERR(acl))
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 6ad63f17eca0..ccc991c542df 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -157,7 +157,7 @@ struct btrfs_inode {
 	/*
 	 * always compress this one file
 	 */
-	unsigned force_compress:1;
+	unsigned force_compress:4;
 
 	struct inode vfs_inode;
 };
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b50bc4bd5c56..4d2110eafe29 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -62,6 +62,9 @@ struct compressed_bio {
 	/* number of bytes on disk */
 	unsigned long compressed_len;
 
+	/* the compression algorithm for this bio */
+	int compress_type;
+
 	/* number of compressed pages in the array */
 	unsigned long nr_pages;
 
@@ -173,11 +176,12 @@ static void end_compressed_bio_read(struct bio *bio, int err)
 	/* ok, we're the last bio for this extent, lets start
 	 * the decompression.
 	 */
-	ret = btrfs_zlib_decompress_biovec(cb->compressed_pages,
-					cb->start,
-					cb->orig_bio->bi_io_vec,
-					cb->orig_bio->bi_vcnt,
-					cb->compressed_len);
+	ret = btrfs_decompress_biovec(cb->compress_type,
+				      cb->compressed_pages,
+				      cb->start,
+				      cb->orig_bio->bi_io_vec,
+				      cb->orig_bio->bi_vcnt,
+				      cb->compressed_len);
 csum_failed:
 	if (ret)
 		cb->errors = 1;
@@ -558,7 +562,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	u64 em_len;
 	u64 em_start;
 	struct extent_map *em;
-	int ret;
+	int ret = -ENOMEM;
 	u32 *sums;
 
 	tree = &BTRFS_I(inode)->io_tree;
@@ -573,6 +577,9 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 	compressed_len = em->block_len;
 	cb = kmalloc(compressed_bio_size(root, compressed_len), GFP_NOFS);
+	if (!cb)
+		goto out;
+
 	atomic_set(&cb->pending_bios, 0);
 	cb->errors = 0;
 	cb->inode = inode;
@@ -588,17 +595,23 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 	cb->len = uncompressed_len;
 	cb->compressed_len = compressed_len;
+	cb->compress_type = extent_compress_type(bio_flags);
 	cb->orig_bio = bio;
 
 	nr_pages = (compressed_len + PAGE_CACHE_SIZE - 1) /
 				 PAGE_CACHE_SIZE;
-	cb->compressed_pages = kmalloc(sizeof(struct page *) * nr_pages,
+	cb->compressed_pages = kzalloc(sizeof(struct page *) * nr_pages,
 				       GFP_NOFS);
+	if (!cb->compressed_pages)
+		goto fail1;
+
 	bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
 
 	for (page_index = 0; page_index < nr_pages; page_index++) {
 		cb->compressed_pages[page_index] = alloc_page(GFP_NOFS |
 							      __GFP_HIGHMEM);
+		if (!cb->compressed_pages[page_index])
+			goto fail2;
 	}
 	cb->nr_pages = nr_pages;
 
@@ -609,6 +622,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	cb->len = uncompressed_len;
 
 	comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS);
+	if (!comp_bio)
+		goto fail2;
 	comp_bio->bi_private = cb;
 	comp_bio->bi_end_io = end_compressed_bio_read;
 	atomic_inc(&cb->pending_bios);
@@ -676,4 +691,329 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 	bio_put(comp_bio);
 	return 0;
+
+fail2:
+	for (page_index = 0; page_index < nr_pages; page_index++)
+		free_page((unsigned long)cb->compressed_pages[page_index]);
+
+	kfree(cb->compressed_pages);
+fail1:
+	kfree(cb);
+out:
+	free_extent_map(em);
+	return ret;
+}
+
+static struct list_head comp_idle_workspace[BTRFS_COMPRESS_TYPES];
+static spinlock_t comp_workspace_lock[BTRFS_COMPRESS_TYPES];
+static int comp_num_workspace[BTRFS_COMPRESS_TYPES];
+static atomic_t comp_alloc_workspace[BTRFS_COMPRESS_TYPES];
+static wait_queue_head_t comp_workspace_wait[BTRFS_COMPRESS_TYPES];
+
+struct btrfs_compress_op *btrfs_compress_op[] = {
+	&btrfs_zlib_compress,
+	&btrfs_lzo_compress,
+};
+
+int __init btrfs_init_compress(void)
+{
+	int i;
+
+	for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) {
+		INIT_LIST_HEAD(&comp_idle_workspace[i]);
+		spin_lock_init(&comp_workspace_lock[i]);
+		atomic_set(&comp_alloc_workspace[i], 0);
+		init_waitqueue_head(&comp_workspace_wait[i]);
+	}
+	return 0;
+}
+
+/*
+ * this finds an available workspace or allocates a new one
+ * ERR_PTR is returned if things go bad.
+ */
+static struct list_head *find_workspace(int type)
+{
+	struct list_head *workspace;
+	int cpus = num_online_cpus();
+	int idx = type - 1;
+
+	struct list_head *idle_workspace	= &comp_idle_workspace[idx];
+	spinlock_t *workspace_lock		= &comp_workspace_lock[idx];
+	atomic_t *alloc_workspace		= &comp_alloc_workspace[idx];
+	wait_queue_head_t *workspace_wait	= &comp_workspace_wait[idx];
+	int *num_workspace			= &comp_num_workspace[idx];
+again:
+	spin_lock(workspace_lock);
+	if (!list_empty(idle_workspace)) {
+		workspace = idle_workspace->next;
+		list_del(workspace);
+		(*num_workspace)--;
+		spin_unlock(workspace_lock);
+		return workspace;
+
+	}
+	if (atomic_read(alloc_workspace) > cpus) {
+		DEFINE_WAIT(wait);
+
+		spin_unlock(workspace_lock);
+		prepare_to_wait(workspace_wait, &wait, TASK_UNINTERRUPTIBLE);
+		if (atomic_read(alloc_workspace) > cpus && !*num_workspace)
+			schedule();
+		finish_wait(workspace_wait, &wait);
+		goto again;
+	}
+	atomic_inc(alloc_workspace);
+	spin_unlock(workspace_lock);
+
+	workspace = btrfs_compress_op[idx]->alloc_workspace();
+	if (IS_ERR(workspace)) {
+		atomic_dec(alloc_workspace);
+		wake_up(workspace_wait);
+	}
+	return workspace;
+}
+
+/*
+ * put a workspace struct back on the list or free it if we have enough
+ * idle ones sitting around
+ */
+static void free_workspace(int type, struct list_head *workspace)
+{
+	int idx = type - 1;
+	struct list_head *idle_workspace	= &comp_idle_workspace[idx];
+	spinlock_t *workspace_lock		= &comp_workspace_lock[idx];
+	atomic_t *alloc_workspace		= &comp_alloc_workspace[idx];
+	wait_queue_head_t *workspace_wait	= &comp_workspace_wait[idx];
+	int *num_workspace			= &comp_num_workspace[idx];
+
+	spin_lock(workspace_lock);
+	if (*num_workspace < num_online_cpus()) {
+		list_add_tail(workspace, idle_workspace);
+		(*num_workspace)++;
+		spin_unlock(workspace_lock);
+		goto wake;
+	}
+	spin_unlock(workspace_lock);
+
+	btrfs_compress_op[idx]->free_workspace(workspace);
+	atomic_dec(alloc_workspace);
+wake:
+	if (waitqueue_active(workspace_wait))
+		wake_up(workspace_wait);
+}
+
+/*
+ * cleanup function for module exit
+ */
+static void free_workspaces(void)
+{
+	struct list_head *workspace;
+	int i;
+
+	for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) {
+		while (!list_empty(&comp_idle_workspace[i])) {
+			workspace = comp_idle_workspace[i].next;
+			list_del(workspace);
+			btrfs_compress_op[i]->free_workspace(workspace);
+			atomic_dec(&comp_alloc_workspace[i]);
+		}
+	}
+}
+
+/*
+ * given an address space and start/len, compress the bytes.
+ *
+ * pages are allocated to hold the compressed result and stored
+ * in 'pages'
+ *
+ * out_pages is used to return the number of pages allocated.  There
+ * may be pages allocated even if we return an error
+ *
+ * total_in is used to return the number of bytes actually read.  It
+ * may be smaller then len if we had to exit early because we
+ * ran out of room in the pages array or because we cross the
+ * max_out threshold.
+ *
+ * total_out is used to return the total number of compressed bytes
+ *
+ * max_out tells us the max number of bytes that we're allowed to
+ * stuff into pages
+ */
+int btrfs_compress_pages(int type, struct address_space *mapping,
+			 u64 start, unsigned long len,
+			 struct page **pages,
+			 unsigned long nr_dest_pages,
+			 unsigned long *out_pages,
+			 unsigned long *total_in,
+			 unsigned long *total_out,
+			 unsigned long max_out)
+{
+	struct list_head *workspace;
+	int ret;
+
+	workspace = find_workspace(type);
+	if (IS_ERR(workspace))
+		return -1;
+
+	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
+						      start, len, pages,
+						      nr_dest_pages, out_pages,
+						      total_in, total_out,
+						      max_out);
+	free_workspace(type, workspace);
+	return ret;
+}
+
+/*
+ * pages_in is an array of pages with compressed data.
+ *
+ * disk_start is the starting logical offset of this array in the file
+ *
+ * bvec is a bio_vec of pages from the file that we want to decompress into
+ *
+ * vcnt is the count of pages in the biovec
+ *
+ * srclen is the number of bytes in pages_in
+ *
+ * The basic idea is that we have a bio that was created by readpages.
+ * The pages in the bio are for the uncompressed data, and they may not
+ * be contiguous.  They all correspond to the range of bytes covered by
+ * the compressed extent.
+ */
+int btrfs_decompress_biovec(int type, struct page **pages_in, u64 disk_start,
+			    struct bio_vec *bvec, int vcnt, size_t srclen)
+{
+	struct list_head *workspace;
+	int ret;
+
+	workspace = find_workspace(type);
+	if (IS_ERR(workspace))
+		return -ENOMEM;
+
+	ret = btrfs_compress_op[type-1]->decompress_biovec(workspace, pages_in,
+							 disk_start,
+							 bvec, vcnt, srclen);
+	free_workspace(type, workspace);
+	return ret;
+}
+
+/*
+ * a less complex decompression routine.  Our compressed data fits in a
+ * single page, and we want to read a single page out of it.
+ * start_byte tells us the offset into the compressed data we're interested in
+ */
+int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
+		     unsigned long start_byte, size_t srclen, size_t destlen)
+{
+	struct list_head *workspace;
+	int ret;
+
+	workspace = find_workspace(type);
+	if (IS_ERR(workspace))
+		return -ENOMEM;
+
+	ret = btrfs_compress_op[type-1]->decompress(workspace, data_in,
+						  dest_page, start_byte,
+						  srclen, destlen);
+
+	free_workspace(type, workspace);
+	return ret;
+}
+
+void btrfs_exit_compress(void)
+{
+	free_workspaces();
+}
+
+/*
+ * Copy uncompressed data from working buffer to pages.
+ *
+ * buf_start is the byte offset we're of the start of our workspace buffer.
+ *
+ * total_out is the last byte of the buffer
+ */
+int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+			      unsigned long total_out, u64 disk_start,
+			      struct bio_vec *bvec, int vcnt,
+			      unsigned long *page_index,
+			      unsigned long *pg_offset)
+{
+	unsigned long buf_offset;
+	unsigned long current_buf_start;
+	unsigned long start_byte;
+	unsigned long working_bytes = total_out - buf_start;
+	unsigned long bytes;
+	char *kaddr;
+	struct page *page_out = bvec[*page_index].bv_page;
+
+	/*
+	 * start byte is the first byte of the page we're currently
+	 * copying into relative to the start of the compressed data.
+	 */
+	start_byte = page_offset(page_out) - disk_start;
+
+	/* we haven't yet hit data corresponding to this page */
+	if (total_out <= start_byte)
+		return 1;
+
+	/*
+	 * the start of the data we care about is offset into
+	 * the middle of our working buffer
+	 */
+	if (total_out > start_byte && buf_start < start_byte) {
+		buf_offset = start_byte - buf_start;
+		working_bytes -= buf_offset;
+	} else {
+		buf_offset = 0;
+	}
+	current_buf_start = buf_start;
+
+	/* copy bytes from the working buffer into the pages */
+	while (working_bytes > 0) {
+		bytes = min(PAGE_CACHE_SIZE - *pg_offset,
+			    PAGE_CACHE_SIZE - buf_offset);
+		bytes = min(bytes, working_bytes);
+		kaddr = kmap_atomic(page_out, KM_USER0);
+		memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
+		kunmap_atomic(kaddr, KM_USER0);
+		flush_dcache_page(page_out);
+
+		*pg_offset += bytes;
+		buf_offset += bytes;
+		working_bytes -= bytes;
+		current_buf_start += bytes;
+
+		/* check if we need to pick another page */
+		if (*pg_offset == PAGE_CACHE_SIZE) {
+			(*page_index)++;
+			if (*page_index >= vcnt)
+				return 0;
+
+			page_out = bvec[*page_index].bv_page;
+			*pg_offset = 0;
+			start_byte = page_offset(page_out) - disk_start;
+
+			/*
+			 * make sure our new page is covered by this
+			 * working buffer
+			 */
+			if (total_out <= start_byte)
+				return 1;
+
+			/*
+			 * the next page in the biovec might not be adjacent
+			 * to the last page, but it might still be found
+			 * inside this working buffer. bump our offset pointer
+			 */
+			if (total_out > start_byte &&
+			    current_buf_start < start_byte) {
+				buf_offset = start_byte - buf_start;
+				working_bytes = total_out - start_byte;
+				current_buf_start = buf_start + buf_offset;
+			}
+		}
+	}
+
+	return 1;
 }
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 421f5b4aa715..51000174b9d7 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -19,24 +19,27 @@
 #ifndef __BTRFS_COMPRESSION_
 #define __BTRFS_COMPRESSION_
 
-int btrfs_zlib_decompress(unsigned char *data_in,
-			  struct page *dest_page,
-			  unsigned long start_byte,
-			  size_t srclen, size_t destlen);
-int btrfs_zlib_compress_pages(struct address_space *mapping,
-			      u64 start, unsigned long len,
-			      struct page **pages,
-			      unsigned long nr_dest_pages,
-			      unsigned long *out_pages,
-			      unsigned long *total_in,
-			      unsigned long *total_out,
-			      unsigned long max_out);
-int btrfs_zlib_decompress_biovec(struct page **pages_in,
-			      u64 disk_start,
-			      struct bio_vec *bvec,
-			      int vcnt,
-			      size_t srclen);
-void btrfs_zlib_exit(void);
+int btrfs_init_compress(void);
+void btrfs_exit_compress(void);
+
+int btrfs_compress_pages(int type, struct address_space *mapping,
+			 u64 start, unsigned long len,
+			 struct page **pages,
+			 unsigned long nr_dest_pages,
+			 unsigned long *out_pages,
+			 unsigned long *total_in,
+			 unsigned long *total_out,
+			 unsigned long max_out);
+int btrfs_decompress_biovec(int type, struct page **pages_in, u64 disk_start,
+			    struct bio_vec *bvec, int vcnt, size_t srclen);
+int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
+		     unsigned long start_byte, size_t srclen, size_t destlen);
+int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+			      unsigned long total_out, u64 disk_start,
+			      struct bio_vec *bvec, int vcnt,
+			      unsigned long *page_index,
+			      unsigned long *pg_offset);
+
 int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long len, u64 disk_start,
 				  unsigned long compressed_len,
@@ -44,4 +47,37 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long nr_pages);
 int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags);
+
+struct btrfs_compress_op {
+	struct list_head *(*alloc_workspace)(void);
+
+	void (*free_workspace)(struct list_head *workspace);
+
+	int (*compress_pages)(struct list_head *workspace,
+			      struct address_space *mapping,
+			      u64 start, unsigned long len,
+			      struct page **pages,
+			      unsigned long nr_dest_pages,
+			      unsigned long *out_pages,
+			      unsigned long *total_in,
+			      unsigned long *total_out,
+			      unsigned long max_out);
+
+	int (*decompress_biovec)(struct list_head *workspace,
+				 struct page **pages_in,
+				 u64 disk_start,
+				 struct bio_vec *bvec,
+				 int vcnt,
+				 size_t srclen);
+
+	int (*decompress)(struct list_head *workspace,
+			  unsigned char *data_in,
+			  struct page *dest_page,
+			  unsigned long start_byte,
+			  size_t srclen, size_t destlen);
+};
+
+extern struct btrfs_compress_op btrfs_zlib_compress;
+extern struct btrfs_compress_op btrfs_lzo_compress;
+
 #endif
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 9ac171599258..b5baff0dccfe 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -105,6 +105,8 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
 /* this also releases the path */
 void btrfs_free_path(struct btrfs_path *p)
 {
+	if (!p)
+		return;
 	btrfs_release_path(NULL, p);
 	kmem_cache_free(btrfs_path_cachep, p);
 }
@@ -2514,6 +2516,9 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
 	btrfs_assert_tree_locked(path->nodes[1]);
 
 	right = read_node_slot(root, upper, slot + 1);
+	if (right == NULL)
+		return 1;
+
 	btrfs_tree_lock(right);
 	btrfs_set_lock_blocking(right);
 
@@ -2764,6 +2769,9 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 	btrfs_assert_tree_locked(path->nodes[1]);
 
 	left = read_node_slot(root, path->nodes[1], slot - 1);
+	if (left == NULL)
+		return 1;
+
 	btrfs_tree_lock(left);
 	btrfs_set_lock_blocking(left);
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index a142d204b526..2c98b3af6052 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -27,6 +27,7 @@
 #include <linux/backing-dev.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
+#include <linux/kobject.h>
 #include <asm/kmap_types.h>
 #include "extent_io.h"
 #include "extent_map.h"
@@ -294,6 +295,14 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 #define BTRFS_FSID_SIZE 16
 #define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
 #define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
+
+/*
+ * File system states
+ */
+
+/* Errors detected */
+#define BTRFS_SUPER_FLAG_ERROR		(1ULL << 2)
+
 #define BTRFS_SUPER_FLAG_SEEDING	(1ULL << 32)
 #define BTRFS_SUPER_FLAG_METADUMP	(1ULL << 33)
 
@@ -398,13 +407,15 @@ struct btrfs_super_block {
 #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
 #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS	(1ULL << 2)
+#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO	(1ULL << 3)
 
 #define BTRFS_FEATURE_COMPAT_SUPP		0ULL
 #define BTRFS_FEATURE_COMPAT_RO_SUPP		0ULL
 #define BTRFS_FEATURE_INCOMPAT_SUPP			\
 	(BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF |		\
 	 BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL |	\
-	 BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+	 BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS |		\
+	 BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO)
 
 /*
  * A leaf is full of items. offset and size tell us where to find
@@ -551,9 +562,11 @@ struct btrfs_timespec {
 } __attribute__ ((__packed__));
 
 enum btrfs_compression_type {
-	BTRFS_COMPRESS_NONE = 0,
-	BTRFS_COMPRESS_ZLIB = 1,
-	BTRFS_COMPRESS_LAST = 2,
+	BTRFS_COMPRESS_NONE  = 0,
+	BTRFS_COMPRESS_ZLIB  = 1,
+	BTRFS_COMPRESS_LZO   = 2,
+	BTRFS_COMPRESS_TYPES = 2,
+	BTRFS_COMPRESS_LAST  = 3,
 };
 
 struct btrfs_inode_item {
@@ -597,6 +610,8 @@ struct btrfs_dir_item {
 	u8 type;
 } __attribute__ ((__packed__));
 
+#define BTRFS_ROOT_SUBVOL_RDONLY	(1ULL << 0)
+
 struct btrfs_root_item {
 	struct btrfs_inode_item inode;
 	__le64 generation;
@@ -895,7 +910,8 @@ struct btrfs_fs_info {
 	 */
 	u64 last_trans_log_full_commit;
 	u64 open_ioctl_trans;
-	unsigned long mount_opt;
+	unsigned long mount_opt:20;
+	unsigned long compress_type:4;
 	u64 max_inline;
 	u64 alloc_start;
 	struct btrfs_transaction *running_transaction;
@@ -1050,6 +1066,9 @@ struct btrfs_fs_info {
 	unsigned metadata_ratio;
 
 	void *bdev_holder;
+
+	/* filesystem state */
+	u64 fs_state;
 };
 
 /*
@@ -1893,6 +1912,11 @@ BTRFS_SETGET_STACK_FUNCS(root_limit, struct btrfs_root_item, byte_limit, 64);
 BTRFS_SETGET_STACK_FUNCS(root_last_snapshot, struct btrfs_root_item,
 			 last_snapshot, 64);
 
+static inline bool btrfs_root_readonly(struct btrfs_root *root)
+{
+	return root->root_item.flags & BTRFS_ROOT_SUBVOL_RDONLY;
+}
+
 /* struct btrfs_super_block */
 
 BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64);
@@ -2145,6 +2169,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 group_start);
 u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags);
+u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data);
 void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
 int btrfs_check_data_free_space(struct inode *inode, u64 bytes);
@@ -2188,6 +2213,12 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 int btrfs_set_block_group_rw(struct btrfs_root *root,
 			     struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
+u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
+int btrfs_error_unpin_extent_range(struct btrfs_root *root,
+				   u64 start, u64 end);
+int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
+			       u64 num_bytes);
+
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
 		     int level, int *slot);
@@ -2541,6 +2572,14 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
 /* super.c */
 int btrfs_parse_options(struct btrfs_root *root, char *options);
 int btrfs_sync_fs(struct super_block *sb, int wait);
+void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+		     unsigned int line, int errno);
+
+#define btrfs_std_error(fs_info, errno)				\
+do {								\
+	if ((errno))						\
+		__btrfs_std_error((fs_info), __func__, __LINE__, (errno));\
+} while (0)
 
 /* acl.c */
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 51d2e4de34eb..fdce8799b98d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -44,6 +44,20 @@
 static struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
+static void btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
+				    int read_only);
+static int btrfs_destroy_ordered_operations(struct btrfs_root *root);
+static int btrfs_destroy_ordered_extents(struct btrfs_root *root);
+static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
+				      struct btrfs_root *root);
+static int btrfs_destroy_pending_snapshots(struct btrfs_transaction *t);
+static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
+static int btrfs_destroy_marked_extents(struct btrfs_root *root,
+					struct extent_io_tree *dirty_pages,
+					int mark);
+static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
+				       struct extent_io_tree *pinned_extents);
+static int btrfs_cleanup_transaction(struct btrfs_root *root);
 
 /*
  * end_io_wq structs are used to do processing in task context when an IO is
@@ -353,6 +367,10 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
 	WARN_ON(len == 0);
 
 	eb = alloc_extent_buffer(tree, start, len, page, GFP_NOFS);
+	if (eb == NULL) {
+		WARN_ON(1);
+		goto out;
+	}
 	ret = btree_read_extent_buffer_pages(root, eb, start + PAGE_CACHE_SIZE,
 					     btrfs_header_generation(eb));
 	BUG_ON(ret);
@@ -427,6 +445,10 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 	WARN_ON(len == 0);
 
 	eb = alloc_extent_buffer(tree, start, len, page, GFP_NOFS);
+	if (eb == NULL) {
+		ret = -EIO;
+		goto out;
+	}
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != start) {
@@ -1145,6 +1167,7 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
 	}
 	btrfs_free_path(path);
 	if (ret) {
+		kfree(root);
 		if (ret > 0)
 			ret = -ENOENT;
 		return ERR_PTR(ret);
@@ -1527,6 +1550,7 @@ static int transaction_kthread(void *arg)
 		spin_unlock(&root->fs_info->new_trans_lock);
 
 		trans = btrfs_join_transaction(root, 1);
+		BUG_ON(IS_ERR(trans));
 		if (transid == trans->transid) {
 			ret = btrfs_commit_transaction(trans, root);
 			BUG_ON(ret);
@@ -1713,8 +1737,10 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		     fs_info, BTRFS_ROOT_TREE_OBJECTID);
 
 	bh = btrfs_read_dev_super(fs_devices->latest_bdev);
-	if (!bh)
+	if (!bh) {
+		err = -EINVAL;
 		goto fail_iput;
+	}
 
 	memcpy(&fs_info->super_copy, bh->b_data, sizeof(fs_info->super_copy));
 	memcpy(&fs_info->super_for_commit, &fs_info->super_copy,
@@ -1727,6 +1753,11 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	if (!btrfs_super_root(disk_super))
 		goto fail_iput;
 
+	/* check FS state, whether FS is broken. */
+	fs_info->fs_state |= btrfs_super_flags(disk_super);
+
+	btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
+
 	ret = btrfs_parse_options(tree_root, options);
 	if (ret) {
 		err = ret;
@@ -1744,10 +1775,10 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	}
 
 	features = btrfs_super_incompat_flags(disk_super);
-	if (!(features & BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF)) {
-		features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
-		btrfs_set_super_incompat_flags(disk_super, features);
-	}
+	features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
+	if (tree_root->fs_info->compress_type & BTRFS_COMPRESS_LZO)
+		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+	btrfs_set_super_incompat_flags(disk_super, features);
 
 	features = btrfs_super_compat_ro_flags(disk_super) &
 		~BTRFS_FEATURE_COMPAT_RO_SUPP;
@@ -1957,7 +1988,9 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		btrfs_set_opt(fs_info->mount_opt, SSD);
 	}
 
-	if (btrfs_super_log_root(disk_super) != 0) {
+	/* do not make disk changes in broken FS */
+	if (btrfs_super_log_root(disk_super) != 0 &&
+	    !(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) {
 		u64 bytenr = btrfs_super_log_root(disk_super);
 
 		if (fs_devices->rw_devices == 0) {
@@ -2421,10 +2454,14 @@ int btrfs_commit_super(struct btrfs_root *root)
 	up_write(&root->fs_info->cleanup_work_sem);
 
 	trans = btrfs_join_transaction(root, 1);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 	ret = btrfs_commit_transaction(trans, root);
 	BUG_ON(ret);
 	/* run commit again to drop the original snapshot */
 	trans = btrfs_join_transaction(root, 1);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 	btrfs_commit_transaction(trans, root);
 	ret = btrfs_write_and_wait_transaction(NULL, root);
 	BUG_ON(ret);
@@ -2442,8 +2479,28 @@ int close_ctree(struct btrfs_root *root)
 	smp_mb();
 
 	btrfs_put_block_group_cache(fs_info);
+
+	/*
+	 * Here come 2 situations when btrfs is broken to flip readonly:
+	 *
+	 * 1. when btrfs flips readonly somewhere else before
+	 * btrfs_commit_super, sb->s_flags has MS_RDONLY flag,
+	 * and btrfs will skip to write sb directly to keep
+	 * ERROR state on disk.
+	 *
+	 * 2. when btrfs flips readonly just in btrfs_commit_super,
+	 * and in such case, btrfs cannnot write sb via btrfs_commit_super,
+	 * and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag,
+	 * btrfs will cleanup all FS resources first and write sb then.
+	 */
 	if (!(fs_info->sb->s_flags & MS_RDONLY)) {
-		ret =  btrfs_commit_super(root);
+		ret = btrfs_commit_super(root);
+		if (ret)
+			printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
+	}
+
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		ret = btrfs_error_commit_super(root);
 		if (ret)
 			printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
 	}
@@ -2502,6 +2559,8 @@ int close_ctree(struct btrfs_root *root)
 	kfree(fs_info->chunk_root);
 	kfree(fs_info->dev_root);
 	kfree(fs_info->csum_root);
+	kfree(fs_info);
+
 	return 0;
 }
 
@@ -2619,6 +2678,352 @@ out:
 	return 0;
 }
 
+static void btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
+			      int read_only)
+{
+	if (read_only)
+		return;
+
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+		printk(KERN_WARNING "warning: mount fs with errors, "
+		       "running btrfsck is recommended\n");
+}
+
+int btrfs_error_commit_super(struct btrfs_root *root)
+{
+	int ret;
+
+	mutex_lock(&root->fs_info->cleaner_mutex);
+	btrfs_run_delayed_iputs(root);
+	mutex_unlock(&root->fs_info->cleaner_mutex);
+
+	down_write(&root->fs_info->cleanup_work_sem);
+	up_write(&root->fs_info->cleanup_work_sem);
+
+	/* cleanup FS via transaction */
+	btrfs_cleanup_transaction(root);
+
+	ret = write_ctree_super(NULL, root, 0);
+
+	return ret;
+}
+
+static int btrfs_destroy_ordered_operations(struct btrfs_root *root)
+{
+	struct btrfs_inode *btrfs_inode;
+	struct list_head splice;
+
+	INIT_LIST_HEAD(&splice);
+
+	mutex_lock(&root->fs_info->ordered_operations_mutex);
+	spin_lock(&root->fs_info->ordered_extent_lock);
+
+	list_splice_init(&root->fs_info->ordered_operations, &splice);
+	while (!list_empty(&splice)) {
+		btrfs_inode = list_entry(splice.next, struct btrfs_inode,
+					 ordered_operations);
+
+		list_del_init(&btrfs_inode->ordered_operations);
+
+		btrfs_invalidate_inodes(btrfs_inode->root);
+	}
+
+	spin_unlock(&root->fs_info->ordered_extent_lock);
+	mutex_unlock(&root->fs_info->ordered_operations_mutex);
+
+	return 0;
+}
+
+static int btrfs_destroy_ordered_extents(struct btrfs_root *root)
+{
+	struct list_head splice;
+	struct btrfs_ordered_extent *ordered;
+	struct inode *inode;
+
+	INIT_LIST_HEAD(&splice);
+
+	spin_lock(&root->fs_info->ordered_extent_lock);
+
+	list_splice_init(&root->fs_info->ordered_extents, &splice);
+	while (!list_empty(&splice)) {
+		ordered = list_entry(splice.next, struct btrfs_ordered_extent,
+				     root_extent_list);
+
+		list_del_init(&ordered->root_extent_list);
+		atomic_inc(&ordered->refs);
+
+		/* the inode may be getting freed (in sys_unlink path). */
+		inode = igrab(ordered->inode);
+
+		spin_unlock(&root->fs_info->ordered_extent_lock);
+		if (inode)
+			iput(inode);
+
+		atomic_set(&ordered->refs, 1);
+		btrfs_put_ordered_extent(ordered);
+
+		spin_lock(&root->fs_info->ordered_extent_lock);
+	}
+
+	spin_unlock(&root->fs_info->ordered_extent_lock);
+
+	return 0;
+}
+
+static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
+				      struct btrfs_root *root)
+{
+	struct rb_node *node;
+	struct btrfs_delayed_ref_root *delayed_refs;
+	struct btrfs_delayed_ref_node *ref;
+	int ret = 0;
+
+	delayed_refs = &trans->delayed_refs;
+
+	spin_lock(&delayed_refs->lock);
+	if (delayed_refs->num_entries == 0) {
+		printk(KERN_INFO "delayed_refs has NO entry\n");
+		return ret;
+	}
+
+	node = rb_first(&delayed_refs->root);
+	while (node) {
+		ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
+		node = rb_next(node);
+
+		ref->in_tree = 0;
+		rb_erase(&ref->rb_node, &delayed_refs->root);
+		delayed_refs->num_entries--;
+
+		atomic_set(&ref->refs, 1);
+		if (btrfs_delayed_ref_is_head(ref)) {
+			struct btrfs_delayed_ref_head *head;
+
+			head = btrfs_delayed_node_to_head(ref);
+			mutex_lock(&head->mutex);
+			kfree(head->extent_op);
+			delayed_refs->num_heads--;
+			if (list_empty(&head->cluster))
+				delayed_refs->num_heads_ready--;
+			list_del_init(&head->cluster);
+			mutex_unlock(&head->mutex);
+		}
+
+		spin_unlock(&delayed_refs->lock);
+		btrfs_put_delayed_ref(ref);
+
+		cond_resched();
+		spin_lock(&delayed_refs->lock);
+	}
+
+	spin_unlock(&delayed_refs->lock);
+
+	return ret;
+}
+
+static int btrfs_destroy_pending_snapshots(struct btrfs_transaction *t)
+{
+	struct btrfs_pending_snapshot *snapshot;
+	struct list_head splice;
+
+	INIT_LIST_HEAD(&splice);
+
+	list_splice_init(&t->pending_snapshots, &splice);
+
+	while (!list_empty(&splice)) {
+		snapshot = list_entry(splice.next,
+				      struct btrfs_pending_snapshot,
+				      list);
+
+		list_del_init(&snapshot->list);
+
+		kfree(snapshot);
+	}
+
+	return 0;
+}
+
+static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
+{
+	struct btrfs_inode *btrfs_inode;
+	struct list_head splice;
+
+	INIT_LIST_HEAD(&splice);
+
+	list_splice_init(&root->fs_info->delalloc_inodes, &splice);
+
+	spin_lock(&root->fs_info->delalloc_lock);
+
+	while (!list_empty(&splice)) {
+		btrfs_inode = list_entry(splice.next, struct btrfs_inode,
+				    delalloc_inodes);
+
+		list_del_init(&btrfs_inode->delalloc_inodes);
+
+		btrfs_invalidate_inodes(btrfs_inode->root);
+	}
+
+	spin_unlock(&root->fs_info->delalloc_lock);
+
+	return 0;
+}
+
+static int btrfs_destroy_marked_extents(struct btrfs_root *root,
+					struct extent_io_tree *dirty_pages,
+					int mark)
+{
+	int ret;
+	struct page *page;
+	struct inode *btree_inode = root->fs_info->btree_inode;
+	struct extent_buffer *eb;
+	u64 start = 0;
+	u64 end;
+	u64 offset;
+	unsigned long index;
+
+	while (1) {
+		ret = find_first_extent_bit(dirty_pages, start, &start, &end,
+					    mark);
+		if (ret)
+			break;
+
+		clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
+		while (start <= end) {
+			index = start >> PAGE_CACHE_SHIFT;
+			start = (u64)(index + 1) << PAGE_CACHE_SHIFT;
+			page = find_get_page(btree_inode->i_mapping, index);
+			if (!page)
+				continue;
+			offset = page_offset(page);
+
+			spin_lock(&dirty_pages->buffer_lock);
+			eb = radix_tree_lookup(
+			     &(&BTRFS_I(page->mapping->host)->io_tree)->buffer,
+					       offset >> PAGE_CACHE_SHIFT);
+			spin_unlock(&dirty_pages->buffer_lock);
+			if (eb) {
+				ret = test_and_clear_bit(EXTENT_BUFFER_DIRTY,
+							 &eb->bflags);
+				atomic_set(&eb->refs, 1);
+			}
+			if (PageWriteback(page))
+				end_page_writeback(page);
+
+			lock_page(page);
+			if (PageDirty(page)) {
+				clear_page_dirty_for_io(page);
+				spin_lock_irq(&page->mapping->tree_lock);
+				radix_tree_tag_clear(&page->mapping->page_tree,
+							page_index(page),
+							PAGECACHE_TAG_DIRTY);
+				spin_unlock_irq(&page->mapping->tree_lock);
+			}
+
+			page->mapping->a_ops->invalidatepage(page, 0);
+			unlock_page(page);
+		}
+	}
+
+	return ret;
+}
+
+static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
+				       struct extent_io_tree *pinned_extents)
+{
+	struct extent_io_tree *unpin;
+	u64 start;
+	u64 end;
+	int ret;
+
+	unpin = pinned_extents;
+	while (1) {
+		ret = find_first_extent_bit(unpin, 0, &start, &end,
+					    EXTENT_DIRTY);
+		if (ret)
+			break;
+
+		/* opt_discard */
+		ret = btrfs_error_discard_extent(root, start, end + 1 - start);
+
+		clear_extent_dirty(unpin, start, end, GFP_NOFS);
+		btrfs_error_unpin_extent_range(root, start, end);
+		cond_resched();
+	}
+
+	return 0;
+}
+
+static int btrfs_cleanup_transaction(struct btrfs_root *root)
+{
+	struct btrfs_transaction *t;
+	LIST_HEAD(list);
+
+	WARN_ON(1);
+
+	mutex_lock(&root->fs_info->trans_mutex);
+	mutex_lock(&root->fs_info->transaction_kthread_mutex);
+
+	list_splice_init(&root->fs_info->trans_list, &list);
+	while (!list_empty(&list)) {
+		t = list_entry(list.next, struct btrfs_transaction, list);
+		if (!t)
+			break;
+
+		btrfs_destroy_ordered_operations(root);
+
+		btrfs_destroy_ordered_extents(root);
+
+		btrfs_destroy_delayed_refs(t, root);
+
+		btrfs_block_rsv_release(root,
+					&root->fs_info->trans_block_rsv,
+					t->dirty_pages.dirty_bytes);
+
+		/* FIXME: cleanup wait for commit */
+		t->in_commit = 1;
+		t->blocked = 1;
+		if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
+			wake_up(&root->fs_info->transaction_blocked_wait);
+
+		t->blocked = 0;
+		if (waitqueue_active(&root->fs_info->transaction_wait))
+			wake_up(&root->fs_info->transaction_wait);
+		mutex_unlock(&root->fs_info->trans_mutex);
+
+		mutex_lock(&root->fs_info->trans_mutex);
+		t->commit_done = 1;
+		if (waitqueue_active(&t->commit_wait))
+			wake_up(&t->commit_wait);
+		mutex_unlock(&root->fs_info->trans_mutex);
+
+		mutex_lock(&root->fs_info->trans_mutex);
+
+		btrfs_destroy_pending_snapshots(t);
+
+		btrfs_destroy_delalloc_inodes(root);
+
+		spin_lock(&root->fs_info->new_trans_lock);
+		root->fs_info->running_transaction = NULL;
+		spin_unlock(&root->fs_info->new_trans_lock);
+
+		btrfs_destroy_marked_extents(root, &t->dirty_pages,
+					     EXTENT_DIRTY);
+
+		btrfs_destroy_pinned_extent(root,
+					    root->fs_info->pinned_extents);
+
+		t->use_count = 0;
+		list_del_init(&t->list);
+		memset(t, 0, sizeof(*t));
+		kmem_cache_free(btrfs_transaction_cachep, t);
+	}
+
+	mutex_unlock(&root->fs_info->transaction_kthread_mutex);
+	mutex_unlock(&root->fs_info->trans_mutex);
+
+	return 0;
+}
+
 static struct extent_io_ops btree_extent_io_ops = {
 	.write_cache_pages_lock_hook = btree_lock_page_hook,
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 88e825a0bf21..07b20dc2fd95 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -52,6 +52,7 @@ int write_ctree_super(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root, int max_mirrors);
 struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_commit_super(struct btrfs_root *root);
+int btrfs_error_commit_super(struct btrfs_root *root);
 struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 					    u64 bytenr, u32 blocksize);
 struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 9786963b07e5..ff27d7a477b2 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -171,6 +171,8 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 	int ret;
 
 	path = btrfs_alloc_path();
+	if (!path)
+		return ERR_PTR(-ENOMEM);
 
 	if (dir->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
 		key.objectid = root->root_key.objectid;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 227e5815d838..4e7e012ad667 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -320,11 +320,6 @@ static int caching_kthread(void *data)
 	if (!path)
 		return -ENOMEM;
 
-	exclude_super_stripes(extent_root, block_group);
-	spin_lock(&block_group->space_info->lock);
-	block_group->space_info->bytes_readonly += block_group->bytes_super;
-	spin_unlock(&block_group->space_info->lock);
-
 	last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET);
 
 	/*
@@ -467,8 +462,10 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 			cache->cached = BTRFS_CACHE_NO;
 		}
 		spin_unlock(&cache->lock);
-		if (ret == 1)
+		if (ret == 1) {
+			free_excluded_extents(fs_info->extent_root, cache);
 			return 0;
+		}
 	}
 
 	if (load_cache_only)
@@ -3089,7 +3086,7 @@ static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
 	return btrfs_reduce_alloc_profile(root, flags);
 }
 
-static u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
+u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
 {
 	u64 flags;
 
@@ -3161,8 +3158,12 @@ alloc:
 					     bytes + 2 * 1024 * 1024,
 					     alloc_target, 0);
 			btrfs_end_transaction(trans, root);
-			if (ret < 0)
-				return ret;
+			if (ret < 0) {
+				if (ret != -ENOSPC)
+					return ret;
+				else
+					goto commit_trans;
+			}
 
 			if (!data_sinfo) {
 				btrfs_set_inode_space_info(root, inode);
@@ -3173,6 +3174,7 @@ alloc:
 		spin_unlock(&data_sinfo->lock);
 
 		/* commit the current transaction and try again */
+commit_trans:
 		if (!committed && !root->fs_info->open_ioctl_trans) {
 			committed = 1;
 			trans = btrfs_join_transaction(root, 1);
@@ -3339,8 +3341,10 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
 	u64 reserved;
 	u64 max_reclaim;
 	u64 reclaimed = 0;
+	long time_left;
 	int pause = 1;
 	int nr_pages = (2 * 1024 * 1024) >> PAGE_CACHE_SHIFT;
+	int loops = 0;
 
 	block_rsv = &root->fs_info->delalloc_block_rsv;
 	space_info = block_rsv->space_info;
@@ -3353,7 +3357,7 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
 
 	max_reclaim = min(reserved, to_reclaim);
 
-	while (1) {
+	while (loops < 1024) {
 		/* have the flusher threads jump in and do some IO */
 		smp_mb();
 		nr_pages = min_t(unsigned long, nr_pages,
@@ -3361,8 +3365,12 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
 		writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages);
 
 		spin_lock(&space_info->lock);
-		if (reserved > space_info->bytes_reserved)
+		if (reserved > space_info->bytes_reserved) {
+			loops = 0;
 			reclaimed += reserved - space_info->bytes_reserved;
+		} else {
+			loops++;
+		}
 		reserved = space_info->bytes_reserved;
 		spin_unlock(&space_info->lock);
 
@@ -3373,7 +3381,12 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
 			return -EAGAIN;
 
 		__set_current_state(TASK_INTERRUPTIBLE);
-		schedule_timeout(pause);
+		time_left = schedule_timeout(pause);
+
+		/* We were interrupted, exit */
+		if (time_left)
+			break;
+
 		pause <<= 1;
 		if (pause > HZ / 10)
 			pause = HZ / 10;
@@ -3583,8 +3596,20 @@ void block_rsv_release_bytes(struct btrfs_block_rsv *block_rsv,
 
 	if (num_bytes > 0) {
 		if (dest) {
-			block_rsv_add_bytes(dest, num_bytes, 0);
-		} else {
+			spin_lock(&dest->lock);
+			if (!dest->full) {
+				u64 bytes_to_add;
+
+				bytes_to_add = dest->size - dest->reserved;
+				bytes_to_add = min(num_bytes, bytes_to_add);
+				dest->reserved += bytes_to_add;
+				if (dest->reserved >= dest->size)
+					dest->full = 1;
+				num_bytes -= bytes_to_add;
+			}
+			spin_unlock(&dest->lock);
+		}
+		if (num_bytes) {
 			spin_lock(&space_info->lock);
 			space_info->bytes_reserved -= num_bytes;
 			spin_unlock(&space_info->lock);
@@ -3721,11 +3746,6 @@ int btrfs_block_rsv_check(struct btrfs_trans_handle *trans,
 		return 0;
 	}
 
-	WARN_ON(1);
-	printk(KERN_INFO"block_rsv size %llu reserved %llu freed %llu %llu\n",
-		block_rsv->size, block_rsv->reserved,
-		block_rsv->freed[0], block_rsv->freed[1]);
-
 	return -ENOSPC;
 }
 
@@ -4012,6 +4032,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
 
 	num_bytes = ALIGN(num_bytes, root->sectorsize);
 	atomic_dec(&BTRFS_I(inode)->outstanding_extents);
+	WARN_ON(atomic_read(&BTRFS_I(inode)->outstanding_extents) < 0);
 
 	spin_lock(&BTRFS_I(inode)->accounting_lock);
 	nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents);
@@ -5633,6 +5654,7 @@ use_block_rsv(struct btrfs_trans_handle *trans,
 	      struct btrfs_root *root, u32 blocksize)
 {
 	struct btrfs_block_rsv *block_rsv;
+	struct btrfs_block_rsv *global_rsv = &root->fs_info->global_block_rsv;
 	int ret;
 
 	block_rsv = get_block_rsv(trans, root);
@@ -5640,14 +5662,39 @@ use_block_rsv(struct btrfs_trans_handle *trans,
 	if (block_rsv->size == 0) {
 		ret = reserve_metadata_bytes(trans, root, block_rsv,
 					     blocksize, 0);
-		if (ret)
+		/*
+		 * If we couldn't reserve metadata bytes try and use some from
+		 * the global reserve.
+		 */
+		if (ret && block_rsv != global_rsv) {
+			ret = block_rsv_use_bytes(global_rsv, blocksize);
+			if (!ret)
+				return global_rsv;
+			return ERR_PTR(ret);
+		} else if (ret) {
 			return ERR_PTR(ret);
+		}
 		return block_rsv;
 	}
 
 	ret = block_rsv_use_bytes(block_rsv, blocksize);
 	if (!ret)
 		return block_rsv;
+	if (ret) {
+		WARN_ON(1);
+		ret = reserve_metadata_bytes(trans, root, block_rsv, blocksize,
+					     0);
+		if (!ret) {
+			spin_lock(&block_rsv->lock);
+			block_rsv->size += blocksize;
+			spin_unlock(&block_rsv->lock);
+			return block_rsv;
+		} else if (ret && block_rsv != global_rsv) {
+			ret = block_rsv_use_bytes(global_rsv, blocksize);
+			if (!ret)
+				return global_rsv;
+		}
+	}
 
 	return ERR_PTR(-ENOSPC);
 }
@@ -6221,6 +6268,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	BUG_ON(!wc);
 
 	trans = btrfs_start_transaction(tree_root, 0);
+	BUG_ON(IS_ERR(trans));
+
 	if (block_rsv)
 		trans->block_rsv = block_rsv;
 
@@ -6318,6 +6367,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 
 			btrfs_end_transaction_throttle(trans, tree_root);
 			trans = btrfs_start_transaction(tree_root, 0);
+			BUG_ON(IS_ERR(trans));
 			if (block_rsv)
 				trans->block_rsv = block_rsv;
 		}
@@ -6446,6 +6496,8 @@ static noinline int relocate_inode_pages(struct inode *inode, u64 start,
 	int ret = 0;
 
 	ra = kzalloc(sizeof(*ra), GFP_NOFS);
+	if (!ra)
+		return -ENOMEM;
 
 	mutex_lock(&inode->i_mutex);
 	first_index = start >> PAGE_CACHE_SHIFT;
@@ -7477,7 +7529,7 @@ int btrfs_drop_dead_reloc_roots(struct btrfs_root *root)
 		BUG_ON(reloc_root->commit_root != NULL);
 		while (1) {
 			trans = btrfs_join_transaction(root, 1);
-			BUG_ON(!trans);
+			BUG_ON(IS_ERR(trans));
 
 			mutex_lock(&root->fs_info->drop_mutex);
 			ret = btrfs_drop_snapshot(trans, reloc_root);
@@ -7535,7 +7587,7 @@ int btrfs_cleanup_reloc_trees(struct btrfs_root *root)
 
 	if (found) {
 		trans = btrfs_start_transaction(root, 1);
-		BUG_ON(!trans);
+		BUG_ON(IS_ERR(trans));
 		ret = btrfs_commit_transaction(trans, root);
 		BUG_ON(ret);
 	}
@@ -7779,7 +7831,7 @@ static noinline int relocate_one_extent(struct btrfs_root *extent_root,
 
 
 	trans = btrfs_start_transaction(extent_root, 1);
-	BUG_ON(!trans);
+	BUG_ON(IS_ERR(trans));
 
 	if (extent_key->objectid == 0) {
 		ret = del_extent_zero(trans, extent_root, path, extent_key);
@@ -7970,13 +8022,14 @@ static int set_block_group_ro(struct btrfs_block_group_cache *cache)
 
 	if (sinfo->bytes_used + sinfo->bytes_reserved + sinfo->bytes_pinned +
 	    sinfo->bytes_may_use + sinfo->bytes_readonly +
-	    cache->reserved_pinned + num_bytes < sinfo->total_bytes) {
+	    cache->reserved_pinned + num_bytes <= sinfo->total_bytes) {
 		sinfo->bytes_readonly += num_bytes;
 		sinfo->bytes_reserved += cache->reserved_pinned;
 		cache->reserved_pinned = 0;
 		cache->ro = 1;
 		ret = 0;
 	}
+
 	spin_unlock(&cache->lock);
 	spin_unlock(&sinfo->lock);
 	return ret;
@@ -8012,6 +8065,62 @@ out:
 	return ret;
 }
 
+/*
+ * helper to account the unused space of all the readonly block group in the
+ * list. takes mirrors into account.
+ */
+static u64 __btrfs_get_ro_block_group_free_space(struct list_head *groups_list)
+{
+	struct btrfs_block_group_cache *block_group;
+	u64 free_bytes = 0;
+	int factor;
+
+	list_for_each_entry(block_group, groups_list, list) {
+		spin_lock(&block_group->lock);
+
+		if (!block_group->ro) {
+			spin_unlock(&block_group->lock);
+			continue;
+		}
+
+		if (block_group->flags & (BTRFS_BLOCK_GROUP_RAID1 |
+					  BTRFS_BLOCK_GROUP_RAID10 |
+					  BTRFS_BLOCK_GROUP_DUP))
+			factor = 2;
+		else
+			factor = 1;
+
+		free_bytes += (block_group->key.offset -
+			       btrfs_block_group_used(&block_group->item)) *
+			       factor;
+
+		spin_unlock(&block_group->lock);
+	}
+
+	return free_bytes;
+}
+
+/*
+ * helper to account the unused space of all the readonly block group in the
+ * space_info. takes mirrors into account.
+ */
+u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
+{
+	int i;
+	u64 free_bytes = 0;
+
+	spin_lock(&sinfo->lock);
+
+	for(i = 0; i < BTRFS_NR_RAID_TYPES; i++)
+		if (!list_empty(&sinfo->block_groups[i]))
+			free_bytes += __btrfs_get_ro_block_group_free_space(
+						&sinfo->block_groups[i]);
+
+	spin_unlock(&sinfo->lock);
+
+	return free_bytes;
+}
+
 int btrfs_set_block_group_rw(struct btrfs_root *root,
 			      struct btrfs_block_group_cache *cache)
 {
@@ -8092,7 +8201,7 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 	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, max_avail;
+		u64 dev_offset;
 
 		/*
 		 * check to make sure we can actually find a chunk with enough
@@ -8100,7 +8209,7 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
 		 */
 		if (device->total_bytes > device->bytes_used + min_free) {
 			ret = find_free_dev_extent(NULL, device, min_free,
-						   &dev_offset, &max_avail);
+						   &dev_offset, NULL);
 			if (!ret)
 				break;
 			ret = -1;
@@ -8213,6 +8322,13 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		if (block_group->cached == BTRFS_CACHE_STARTED)
 			wait_block_group_cache_done(block_group);
 
+		/*
+		 * We haven't cached this block group, which means we could
+		 * possibly have excluded extents on this block group.
+		 */
+		if (block_group->cached == BTRFS_CACHE_NO)
+			free_excluded_extents(info->extent_root, block_group);
+
 		btrfs_remove_free_space_cache(block_group);
 		btrfs_put_block_group(block_group);
 
@@ -8328,6 +8444,13 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		cache->sectorsize = root->sectorsize;
 
 		/*
+		 * We need to exclude the super stripes now so that the space
+		 * info has super bytes accounted for, otherwise we'll think
+		 * we have more space than we actually do.
+		 */
+		exclude_super_stripes(root, cache);
+
+		/*
 		 * check for two cases, either we are full, and therefore
 		 * don't need to bother with the caching work since we won't
 		 * find any space, or we are empty, and we can just add all
@@ -8335,12 +8458,10 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		 * time, particularly in the full case.
 		 */
 		if (found_key.offset == btrfs_block_group_used(&cache->item)) {
-			exclude_super_stripes(root, cache);
 			cache->last_byte_to_unpin = (u64)-1;
 			cache->cached = BTRFS_CACHE_FINISHED;
 			free_excluded_extents(root, cache);
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
-			exclude_super_stripes(root, cache);
 			cache->last_byte_to_unpin = (u64)-1;
 			cache->cached = BTRFS_CACHE_FINISHED;
 			add_new_free_space(cache, root->fs_info,
@@ -8584,3 +8705,14 @@ out:
 	btrfs_free_path(path);
 	return ret;
 }
+
+int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+{
+	return unpin_extent_range(root, start, end);
+}
+
+int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
+			       u64 num_bytes)
+{
+	return btrfs_discard_extent(root, bytenr, num_bytes);
+}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3e86b9f36507..5e76a474cb7e 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1865,7 +1865,7 @@ static int submit_one_bio(int rw, struct bio *bio, int mirror_num,
 	bio_get(bio);
 
 	if (tree->ops && tree->ops->submit_bio_hook)
-		tree->ops->submit_bio_hook(page->mapping->host, rw, bio,
+		ret = tree->ops->submit_bio_hook(page->mapping->host, rw, bio,
 					   mirror_num, bio_flags, start);
 	else
 		submit_bio(rw, bio);
@@ -1920,6 +1920,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 		nr = bio_get_nr_vecs(bdev);
 
 	bio = btrfs_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH);
+	if (!bio)
+		return -ENOMEM;
 
 	bio_add_page(bio, page, page_size, offset);
 	bio->bi_end_io = end_io_func;
@@ -2028,8 +2030,11 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 		BUG_ON(extent_map_end(em) <= cur);
 		BUG_ON(end < cur);
 
-		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
 			this_bio_flag = EXTENT_BIO_COMPRESSED;
+			extent_set_compress_type(&this_bio_flag,
+						 em->compress_type);
+		}
 
 		iosize = min(extent_map_end(em) - cur, end - cur + 1);
 		cur_end = min(extent_map_end(em) - 1, end);
@@ -2123,7 +2128,7 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	ret = __extent_read_full_page(tree, page, get_extent, &bio, 0,
 				      &bio_flags);
 	if (bio)
-		submit_one_bio(READ, bio, 0, bio_flags);
+		ret = submit_one_bio(READ, bio, 0, bio_flags);
 	return ret;
 }
 
@@ -3072,6 +3077,8 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
 #endif
 
 	eb = kmem_cache_zalloc(extent_buffer_cache, mask);
+	if (eb == NULL)
+		return NULL;
 	eb->start = start;
 	eb->len = len;
 	spin_lock_init(&eb->lock);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 4183c8178f01..7083cfafd061 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -20,8 +20,12 @@
 #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
 #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
 
-/* flags for bio submission */
+/*
+ * flags for bio submission. The high bits indicate the compression
+ * type for this bio
+ */
 #define EXTENT_BIO_COMPRESSED 1
+#define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */
 #define EXTENT_BUFFER_UPTODATE 0
@@ -135,6 +139,17 @@ struct extent_buffer {
 	wait_queue_head_t lock_wq;
 };
 
+static inline void extent_set_compress_type(unsigned long *bio_flags,
+					    int compress_type)
+{
+	*bio_flags |= compress_type << EXTENT_BIO_FLAG_SHIFT;
+}
+
+static inline int extent_compress_type(unsigned long bio_flags)
+{
+	return bio_flags >> EXTENT_BIO_FLAG_SHIFT;
+}
+
 struct extent_map_tree;
 
 static inline struct extent_state *extent_state_next(struct extent_state *state)
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 23cb8da3ff66..b0e1fce12530 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -3,6 +3,7 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
+#include "ctree.h"
 #include "extent_map.h"
 
 
@@ -54,6 +55,7 @@ struct extent_map *alloc_extent_map(gfp_t mask)
 		return em;
 	em->in_tree = 0;
 	em->flags = 0;
+	em->compress_type = BTRFS_COMPRESS_NONE;
 	atomic_set(&em->refs, 1);
 	return em;
 }
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index ab6d74b6e647..28b44dbd1e35 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -26,7 +26,8 @@ struct extent_map {
 	unsigned long flags;
 	struct block_device *bdev;
 	atomic_t refs;
-	int in_tree;
+	unsigned int in_tree:1;
+	unsigned int compress_type:4;
 };
 
 struct extent_map_tree {
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index a562a250ae77..4f19a3e1bf32 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -536,6 +536,8 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 	root = root->fs_info->csum_root;
 
 	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
 
 	while (1) {
 		key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
@@ -548,7 +550,10 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 			if (path->slots[0] == 0)
 				goto out;
 			path->slots[0]--;
+		} else if (ret < 0) {
+			goto out;
 		}
+
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 66836d85763b..c1d3a818731a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -24,6 +24,7 @@
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mpage.h>
+#include <linux/falloc.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/statfs.h>
@@ -224,6 +225,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 
 			split->bdev = em->bdev;
 			split->flags = flags;
+			split->compress_type = em->compress_type;
 			ret = add_extent_mapping(em_tree, split);
 			BUG_ON(ret);
 			free_extent_map(split);
@@ -238,6 +240,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			split->len = em->start + em->len - (start + len);
 			split->bdev = em->bdev;
 			split->flags = flags;
+			split->compress_type = em->compress_type;
 
 			if (compressed) {
 				split->block_len = em->block_len;
@@ -790,8 +793,12 @@ again:
 	for (i = 0; i < num_pages; i++) {
 		pages[i] = grab_cache_page(inode->i_mapping, index + i);
 		if (!pages[i]) {
-			err = -ENOMEM;
-			BUG_ON(1);
+			int c;
+			for (c = i - 1; c >= 0; c--) {
+				unlock_page(pages[c]);
+				page_cache_release(pages[c]);
+			}
+			return -ENOMEM;
 		}
 		wait_on_page_writeback(pages[i]);
 	}
@@ -890,6 +897,17 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	if (err)
 		goto out;
 
+	/*
+	 * If BTRFS flips readonly due to some impossible error
+	 * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR),
+	 * although we have opened a file as writable, we have
+	 * to stop this write operation to ensure FS consistency.
+	 */
+	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		err = -EROFS;
+		goto out;
+	}
+
 	file_update_time(file);
 	BTRFS_I(inode)->sequence++;
 
@@ -932,6 +950,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		     PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
 		     (sizeof(struct page *)));
 	pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
+	if (!pages) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	/* generic_write_checks can change our pos */
 	start_pos = pos;
@@ -970,8 +992,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		size_t write_bytes = min(iov_iter_count(&i),
 					 nrptrs * (size_t)PAGE_CACHE_SIZE -
 					 offset);
-		size_t num_pages = (write_bytes + PAGE_CACHE_SIZE - 1) >>
-					PAGE_CACHE_SHIFT;
+		size_t num_pages = (write_bytes + offset +
+				    PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
 		WARN_ON(num_pages > nrptrs);
 		memset(pages, 0, sizeof(struct page *) * nrptrs);
@@ -1001,8 +1023,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 
 		copied = btrfs_copy_from_user(pos, num_pages,
 					   write_bytes, pages, &i);
-		dirty_pages = (copied + PAGE_CACHE_SIZE - 1) >>
-					PAGE_CACHE_SHIFT;
+		dirty_pages = (copied + offset + PAGE_CACHE_SIZE - 1) >>
+				PAGE_CACHE_SHIFT;
 
 		if (num_pages > dirty_pages) {
 			if (copied > 0)
@@ -1237,6 +1259,117 @@ static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
 	return 0;
 }
 
+static long btrfs_fallocate(struct file *file, int mode,
+			    loff_t offset, loff_t len)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct extent_state *cached_state = NULL;
+	u64 cur_offset;
+	u64 last_byte;
+	u64 alloc_start;
+	u64 alloc_end;
+	u64 alloc_hint = 0;
+	u64 locked_end;
+	u64 mask = BTRFS_I(inode)->root->sectorsize - 1;
+	struct extent_map *em;
+	int ret;
+
+	alloc_start = offset & ~mask;
+	alloc_end =  (offset + len + mask) & ~mask;
+
+	/* We only support the FALLOC_FL_KEEP_SIZE mode */
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
+		return -EOPNOTSUPP;
+
+	/*
+	 * wait for ordered IO before we have any locks.  We'll loop again
+	 * below with the locks held.
+	 */
+	btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start);
+
+	mutex_lock(&inode->i_mutex);
+	ret = inode_newsize_ok(inode, alloc_end);
+	if (ret)
+		goto out;
+
+	if (alloc_start > inode->i_size) {
+		ret = btrfs_cont_expand(inode, alloc_start);
+		if (ret)
+			goto out;
+	}
+
+	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
+	if (ret)
+		goto out;
+
+	locked_end = alloc_end - 1;
+	while (1) {
+		struct btrfs_ordered_extent *ordered;
+
+		/* the extent lock is ordered inside the running
+		 * transaction
+		 */
+		lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
+				 locked_end, 0, &cached_state, GFP_NOFS);
+		ordered = btrfs_lookup_first_ordered_extent(inode,
+							    alloc_end - 1);
+		if (ordered &&
+		    ordered->file_offset + ordered->len > alloc_start &&
+		    ordered->file_offset < alloc_end) {
+			btrfs_put_ordered_extent(ordered);
+			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+					     alloc_start, locked_end,
+					     &cached_state, GFP_NOFS);
+			/*
+			 * we can't wait on the range with the transaction
+			 * running or with the extent lock held
+			 */
+			btrfs_wait_ordered_range(inode, alloc_start,
+						 alloc_end - alloc_start);
+		} else {
+			if (ordered)
+				btrfs_put_ordered_extent(ordered);
+			break;
+		}
+	}
+
+	cur_offset = alloc_start;
+	while (1) {
+		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
+				      alloc_end - cur_offset, 0);
+		BUG_ON(IS_ERR(em) || !em);
+		last_byte = min(extent_map_end(em), alloc_end);
+		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))) {
+			ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
+							last_byte - cur_offset,
+							1 << inode->i_blkbits,
+							offset + len,
+							&alloc_hint);
+			if (ret < 0) {
+				free_extent_map(em);
+				break;
+			}
+		}
+		free_extent_map(em);
+
+		cur_offset = last_byte;
+		if (cur_offset >= alloc_end) {
+			ret = 0;
+			break;
+		}
+	}
+	unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
+			     &cached_state, GFP_NOFS);
+
+	btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
+out:
+	mutex_unlock(&inode->i_mutex);
+	return ret;
+}
+
 const struct file_operations btrfs_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
@@ -1248,6 +1381,7 @@ const struct file_operations btrfs_file_operations = {
 	.open		= generic_file_open,
 	.release	= btrfs_release_file,
 	.fsync		= btrfs_sync_file,
+	.fallocate	= btrfs_fallocate,
 	.unlocked_ioctl	= btrfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= btrfs_ioctl,
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 60d684266959..a0390657451b 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -987,11 +987,18 @@ tree_search_offset(struct btrfs_block_group_cache *block_group,
 	return entry;
 }
 
-static void unlink_free_space(struct btrfs_block_group_cache *block_group,
-			      struct btrfs_free_space *info)
+static inline void
+__unlink_free_space(struct btrfs_block_group_cache *block_group,
+		    struct btrfs_free_space *info)
 {
 	rb_erase(&info->offset_index, &block_group->free_space_offset);
 	block_group->free_extents--;
+}
+
+static void unlink_free_space(struct btrfs_block_group_cache *block_group,
+			      struct btrfs_free_space *info)
+{
+	__unlink_free_space(block_group, info);
 	block_group->free_space -= info->bytes;
 }
 
@@ -1016,14 +1023,18 @@ static void recalculate_thresholds(struct btrfs_block_group_cache *block_group)
 	u64 max_bytes;
 	u64 bitmap_bytes;
 	u64 extent_bytes;
+	u64 size = block_group->key.offset;
 
 	/*
 	 * The goal is to keep the total amount of memory used per 1gb of space
 	 * at or below 32k, so we need to adjust how much memory we allow to be
 	 * used by extent based free space tracking
 	 */
-	max_bytes = MAX_CACHE_BYTES_PER_GIG *
-		(div64_u64(block_group->key.offset, 1024 * 1024 * 1024));
+	if (size < 1024 * 1024 * 1024)
+		max_bytes = MAX_CACHE_BYTES_PER_GIG;
+	else
+		max_bytes = MAX_CACHE_BYTES_PER_GIG *
+			div64_u64(size, 1024 * 1024 * 1024);
 
 	/*
 	 * we want to account for 1 more bitmap than what we have so we can make
@@ -1171,6 +1182,16 @@ static void add_new_bitmap(struct btrfs_block_group_cache *block_group,
 	recalculate_thresholds(block_group);
 }
 
+static void free_bitmap(struct btrfs_block_group_cache *block_group,
+			struct btrfs_free_space *bitmap_info)
+{
+	unlink_free_space(block_group, bitmap_info);
+	kfree(bitmap_info->bitmap);
+	kfree(bitmap_info);
+	block_group->total_bitmaps--;
+	recalculate_thresholds(block_group);
+}
+
 static noinline int remove_from_bitmap(struct btrfs_block_group_cache *block_group,
 			      struct btrfs_free_space *bitmap_info,
 			      u64 *offset, u64 *bytes)
@@ -1195,6 +1216,7 @@ again:
 	 */
 	search_start = *offset;
 	search_bytes = *bytes;
+	search_bytes = min(search_bytes, end - search_start + 1);
 	ret = search_bitmap(block_group, bitmap_info, &search_start,
 			    &search_bytes);
 	BUG_ON(ret < 0 || search_start != *offset);
@@ -1211,13 +1233,8 @@ again:
 
 	if (*bytes) {
 		struct rb_node *next = rb_next(&bitmap_info->offset_index);
-		if (!bitmap_info->bytes) {
-			unlink_free_space(block_group, bitmap_info);
-			kfree(bitmap_info->bitmap);
-			kfree(bitmap_info);
-			block_group->total_bitmaps--;
-			recalculate_thresholds(block_group);
-		}
+		if (!bitmap_info->bytes)
+			free_bitmap(block_group, bitmap_info);
 
 		/*
 		 * no entry after this bitmap, but we still have bytes to
@@ -1250,13 +1267,8 @@ again:
 			return -EAGAIN;
 
 		goto again;
-	} else if (!bitmap_info->bytes) {
-		unlink_free_space(block_group, bitmap_info);
-		kfree(bitmap_info->bitmap);
-		kfree(bitmap_info);
-		block_group->total_bitmaps--;
-		recalculate_thresholds(block_group);
-	}
+	} else if (!bitmap_info->bytes)
+		free_bitmap(block_group, bitmap_info);
 
 	return 0;
 }
@@ -1359,22 +1371,14 @@ out:
 	return ret;
 }
 
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
-			 u64 offset, u64 bytes)
+bool try_merge_free_space(struct btrfs_block_group_cache *block_group,
+			  struct btrfs_free_space *info, bool update_stat)
 {
-	struct btrfs_free_space *right_info = NULL;
-	struct btrfs_free_space *left_info = NULL;
-	struct btrfs_free_space *info = NULL;
-	int ret = 0;
-
-	info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS);
-	if (!info)
-		return -ENOMEM;
-
-	info->offset = offset;
-	info->bytes = bytes;
-
-	spin_lock(&block_group->tree_lock);
+	struct btrfs_free_space *left_info;
+	struct btrfs_free_space *right_info;
+	bool merged = false;
+	u64 offset = info->offset;
+	u64 bytes = info->bytes;
 
 	/*
 	 * first we want to see if there is free space adjacent to the range we
@@ -1388,37 +1392,62 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
 	else
 		left_info = tree_search_offset(block_group, offset - 1, 0, 0);
 
-	/*
-	 * If there was no extent directly to the left or right of this new
-	 * extent then we know we're going to have to allocate a new extent, so
-	 * before we do that see if we need to drop this into a bitmap
-	 */
-	if ((!left_info || left_info->bitmap) &&
-	    (!right_info || right_info->bitmap)) {
-		ret = insert_into_bitmap(block_group, info);
-
-		if (ret < 0) {
-			goto out;
-		} else if (ret) {
-			ret = 0;
-			goto out;
-		}
-	}
-
 	if (right_info && !right_info->bitmap) {
-		unlink_free_space(block_group, right_info);
+		if (update_stat)
+			unlink_free_space(block_group, right_info);
+		else
+			__unlink_free_space(block_group, right_info);
 		info->bytes += right_info->bytes;
 		kfree(right_info);
+		merged = true;
 	}
 
 	if (left_info && !left_info->bitmap &&
 	    left_info->offset + left_info->bytes == offset) {
-		unlink_free_space(block_group, left_info);
+		if (update_stat)
+			unlink_free_space(block_group, left_info);
+		else
+			__unlink_free_space(block_group, left_info);
 		info->offset = left_info->offset;
 		info->bytes += left_info->bytes;
 		kfree(left_info);
+		merged = true;
 	}
 
+	return merged;
+}
+
+int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+			 u64 offset, u64 bytes)
+{
+	struct btrfs_free_space *info;
+	int ret = 0;
+
+	info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS);
+	if (!info)
+		return -ENOMEM;
+
+	info->offset = offset;
+	info->bytes = bytes;
+
+	spin_lock(&block_group->tree_lock);
+
+	if (try_merge_free_space(block_group, info, true))
+		goto link;
+
+	/*
+	 * There was no extent directly to the left or right of this new
+	 * extent then we know we're going to have to allocate a new extent, so
+	 * before we do that see if we need to drop this into a bitmap
+	 */
+	ret = insert_into_bitmap(block_group, info);
+	if (ret < 0) {
+		goto out;
+	} else if (ret) {
+		ret = 0;
+		goto out;
+	}
+link:
 	ret = link_free_space(block_group, info);
 	if (ret)
 		kfree(info);
@@ -1621,6 +1650,7 @@ __btrfs_return_cluster_to_free_space(
 		node = rb_next(&entry->offset_index);
 		rb_erase(&entry->offset_index, &cluster->root);
 		BUG_ON(entry->bitmap);
+		try_merge_free_space(block_group, entry, false);
 		tree_insert_offset(&block_group->free_space_offset,
 				   entry->offset, &entry->offset_index, 0);
 	}
@@ -1685,13 +1715,8 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
 	ret = offset;
 	if (entry->bitmap) {
 		bitmap_clear_bits(block_group, entry, offset, bytes);
-		if (!entry->bytes) {
-			unlink_free_space(block_group, entry);
-			kfree(entry->bitmap);
-			kfree(entry);
-			block_group->total_bitmaps--;
-			recalculate_thresholds(block_group);
-		}
+		if (!entry->bytes)
+			free_bitmap(block_group, entry);
 	} else {
 		unlink_free_space(block_group, entry);
 		entry->offset += bytes;
@@ -1789,6 +1814,8 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
 
 	ret = search_start;
 	bitmap_clear_bits(block_group, entry, ret, bytes);
+	if (entry->bytes == 0)
+		free_bitmap(block_group, entry);
 out:
 	spin_unlock(&cluster->lock);
 	spin_unlock(&block_group->tree_lock);
@@ -1842,15 +1869,26 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 		entry->offset += bytes;
 		entry->bytes -= bytes;
 
-		if (entry->bytes == 0) {
+		if (entry->bytes == 0)
 			rb_erase(&entry->offset_index, &cluster->root);
-			kfree(entry);
-		}
 		break;
 	}
 out:
 	spin_unlock(&cluster->lock);
 
+	if (!ret)
+		return 0;
+
+	spin_lock(&block_group->tree_lock);
+
+	block_group->free_space -= bytes;
+	if (entry->bytes == 0) {
+		block_group->free_extents--;
+		kfree(entry);
+	}
+
+	spin_unlock(&block_group->tree_lock);
+
 	return ret;
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a3798a3aa0d2..bcc461a9695f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -122,10 +122,10 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 	size_t cur_size = size;
 	size_t datasize;
 	unsigned long offset;
-	int use_compress = 0;
+	int compress_type = BTRFS_COMPRESS_NONE;
 
 	if (compressed_size && compressed_pages) {
-		use_compress = 1;
+		compress_type = root->fs_info->compress_type;
 		cur_size = compressed_size;
 	}
 
@@ -159,7 +159,7 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_file_extent_ram_bytes(leaf, ei, size);
 	ptr = btrfs_file_extent_inline_start(ei);
 
-	if (use_compress) {
+	if (compress_type != BTRFS_COMPRESS_NONE) {
 		struct page *cpage;
 		int i = 0;
 		while (compressed_size > 0) {
@@ -176,7 +176,7 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 			compressed_size -= cur_size;
 		}
 		btrfs_set_file_extent_compression(leaf, ei,
-						  BTRFS_COMPRESS_ZLIB);
+						  compress_type);
 	} else {
 		page = find_get_page(inode->i_mapping,
 				     start >> PAGE_CACHE_SHIFT);
@@ -263,6 +263,7 @@ struct async_extent {
 	u64 compressed_size;
 	struct page **pages;
 	unsigned long nr_pages;
+	int compress_type;
 	struct list_head list;
 };
 
@@ -280,7 +281,8 @@ static noinline int add_async_extent(struct async_cow *cow,
 				     u64 start, u64 ram_size,
 				     u64 compressed_size,
 				     struct page **pages,
-				     unsigned long nr_pages)
+				     unsigned long nr_pages,
+				     int compress_type)
 {
 	struct async_extent *async_extent;
 
@@ -290,6 +292,7 @@ static noinline int add_async_extent(struct async_cow *cow,
 	async_extent->compressed_size = compressed_size;
 	async_extent->pages = pages;
 	async_extent->nr_pages = nr_pages;
+	async_extent->compress_type = compress_type;
 	list_add_tail(&async_extent->list, &cow->extents);
 	return 0;
 }
@@ -332,6 +335,7 @@ static noinline int compress_file_range(struct inode *inode,
 	unsigned long max_uncompressed = 128 * 1024;
 	int i;
 	int will_compress;
+	int compress_type = root->fs_info->compress_type;
 
 	actual_end = min_t(u64, isize, end + 1);
 again:
@@ -381,12 +385,16 @@ again:
 		WARN_ON(pages);
 		pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
 
-		ret = btrfs_zlib_compress_pages(inode->i_mapping, start,
-						total_compressed, pages,
-						nr_pages, &nr_pages_ret,
-						&total_in,
-						&total_compressed,
-						max_compressed);
+		if (BTRFS_I(inode)->force_compress)
+			compress_type = BTRFS_I(inode)->force_compress;
+
+		ret = btrfs_compress_pages(compress_type,
+					   inode->i_mapping, start,
+					   total_compressed, pages,
+					   nr_pages, &nr_pages_ret,
+					   &total_in,
+					   &total_compressed,
+					   max_compressed);
 
 		if (!ret) {
 			unsigned long offset = total_compressed &
@@ -408,7 +416,7 @@ again:
 	}
 	if (start == 0) {
 		trans = btrfs_join_transaction(root, 1);
-		BUG_ON(!trans);
+		BUG_ON(IS_ERR(trans));
 		btrfs_set_trans_block_group(trans, inode);
 		trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
@@ -493,7 +501,8 @@ again:
 		 * and will submit them to the elevator.
 		 */
 		add_async_extent(async_cow, start, num_bytes,
-				 total_compressed, pages, nr_pages_ret);
+				 total_compressed, pages, nr_pages_ret,
+				 compress_type);
 
 		if (start + num_bytes < end) {
 			start += num_bytes;
@@ -515,7 +524,8 @@ cleanup_and_bail_uncompressed:
 			__set_page_dirty_nobuffers(locked_page);
 			/* unlocked later on in the async handlers */
 		}
-		add_async_extent(async_cow, start, end - start + 1, 0, NULL, 0);
+		add_async_extent(async_cow, start, end - start + 1,
+				 0, NULL, 0, BTRFS_COMPRESS_NONE);
 		*num_added += 1;
 	}
 
@@ -602,6 +612,7 @@ retry:
 			    GFP_NOFS);
 
 		trans = btrfs_join_transaction(root, 1);
+		BUG_ON(IS_ERR(trans));
 		ret = btrfs_reserve_extent(trans, root,
 					   async_extent->compressed_size,
 					   async_extent->compressed_size,
@@ -640,6 +651,7 @@ retry:
 		em->block_start = ins.objectid;
 		em->block_len = ins.offset;
 		em->bdev = root->fs_info->fs_devices->latest_bdev;
+		em->compress_type = async_extent->compress_type;
 		set_bit(EXTENT_FLAG_PINNED, &em->flags);
 		set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
 
@@ -656,11 +668,13 @@ retry:
 						async_extent->ram_size - 1, 0);
 		}
 
-		ret = btrfs_add_ordered_extent(inode, async_extent->start,
-					       ins.objectid,
-					       async_extent->ram_size,
-					       ins.offset,
-					       BTRFS_ORDERED_COMPRESSED);
+		ret = btrfs_add_ordered_extent_compress(inode,
+						async_extent->start,
+						ins.objectid,
+						async_extent->ram_size,
+						ins.offset,
+						BTRFS_ORDERED_COMPRESSED,
+						async_extent->compress_type);
 		BUG_ON(ret);
 
 		/*
@@ -758,7 +772,7 @@ static noinline int cow_file_range(struct inode *inode,
 
 	BUG_ON(root == root->fs_info->tree_root);
 	trans = btrfs_join_transaction(root, 1);
-	BUG_ON(!trans);
+	BUG_ON(IS_ERR(trans));
 	btrfs_set_trans_block_group(trans, inode);
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
@@ -1036,7 +1050,7 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	} else {
 		trans = btrfs_join_transaction(root, 1);
 	}
-	BUG_ON(!trans);
+	BUG_ON(IS_ERR(trans));
 
 	cow_start = (u64)-1;
 	cur_offset = start;
@@ -1544,6 +1558,7 @@ out:
 out_page:
 	unlock_page(page);
 	page_cache_release(page);
+	kfree(fixup);
 }
 
 /*
@@ -1670,7 +1685,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 	struct btrfs_ordered_extent *ordered_extent = NULL;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct extent_state *cached_state = NULL;
-	int compressed = 0;
+	int compress_type = 0;
 	int ret;
 	bool nolock = false;
 
@@ -1690,7 +1705,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 				trans = btrfs_join_transaction_nolock(root, 1);
 			else
 				trans = btrfs_join_transaction(root, 1);
-			BUG_ON(!trans);
+			BUG_ON(IS_ERR(trans));
 			btrfs_set_trans_block_group(trans, inode);
 			trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 			ret = btrfs_update_inode(trans, root, inode);
@@ -1707,13 +1722,14 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 		trans = btrfs_join_transaction_nolock(root, 1);
 	else
 		trans = btrfs_join_transaction(root, 1);
+	BUG_ON(IS_ERR(trans));
 	btrfs_set_trans_block_group(trans, inode);
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
-		compressed = 1;
+		compress_type = ordered_extent->compress_type;
 	if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
-		BUG_ON(compressed);
+		BUG_ON(compress_type);
 		ret = btrfs_mark_extent_written(trans, inode,
 						ordered_extent->file_offset,
 						ordered_extent->file_offset +
@@ -1727,7 +1743,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 						ordered_extent->disk_len,
 						ordered_extent->len,
 						ordered_extent->len,
-						compressed, 0, 0,
+						compress_type, 0, 0,
 						BTRFS_FILE_EXTENT_REG);
 		unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
 				   ordered_extent->file_offset,
@@ -1829,6 +1845,8 @@ static int btrfs_io_failed_hook(struct bio *failed_bio,
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
 			logical = em->block_start;
 			failrec->bio_flags = EXTENT_BIO_COMPRESSED;
+			extent_set_compress_type(&failrec->bio_flags,
+						 em->compress_type);
 		}
 		failrec->logical = logical;
 		free_extent_map(em);
@@ -2339,6 +2357,7 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 		 */
 		if (is_bad_inode(inode)) {
 			trans = btrfs_start_transaction(root, 0);
+			BUG_ON(IS_ERR(trans));
 			btrfs_orphan_del(trans, inode);
 			btrfs_end_transaction(trans, root);
 			iput(inode);
@@ -2366,6 +2385,7 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 
 	if (root->orphan_block_rsv || root->orphan_item_inserted) {
 		trans = btrfs_join_transaction(root, 1);
+		BUG_ON(IS_ERR(trans));
 		btrfs_end_transaction(trans, root);
 	}
 
@@ -2626,7 +2646,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
-		goto err;
+		goto out;
 	}
 
 	path->leave_spinning = 1;
@@ -2699,9 +2719,10 @@ static int check_path_shared(struct btrfs_root *root,
 	struct extent_buffer *eb;
 	int level;
 	u64 refs = 1;
-	int uninitialized_var(ret);
 
 	for (level = 0; level < BTRFS_MAX_LEVEL; level++) {
+		int ret;
+
 		if (!path->nodes[level])
 			break;
 		eb = path->nodes[level];
@@ -2712,7 +2733,7 @@ static int check_path_shared(struct btrfs_root *root,
 		if (refs > 1)
 			return 1;
 	}
-	return ret; /* XXX callers? */
+	return 0;
 }
 
 /*
@@ -3671,8 +3692,12 @@ static int btrfs_setattr_size(struct inode *inode, struct iattr *attr)
 static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int err;
 
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	err = inode_change_ok(inode, attr);
 	if (err)
 		return err;
@@ -4115,7 +4140,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 	}
 	srcu_read_unlock(&root->fs_info->subvol_srcu, index);
 
-	if (root != sub_root) {
+	if (!IS_ERR(inode) && root != sub_root) {
 		down_read(&root->fs_info->cleanup_work_sem);
 		if (!(inode->i_sb->s_flags & MS_RDONLY))
 			btrfs_orphan_cleanup(sub_root);
@@ -4328,6 +4353,8 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 			trans = btrfs_join_transaction_nolock(root, 1);
 		else
 			trans = btrfs_join_transaction(root, 1);
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
 		btrfs_set_trans_block_group(trans, inode);
 		if (nolock)
 			ret = btrfs_end_transaction_nolock(trans, root);
@@ -4353,6 +4380,7 @@ void btrfs_dirty_inode(struct inode *inode)
 		return;
 
 	trans = btrfs_join_transaction(root, 1);
+	BUG_ON(IS_ERR(trans));
 	btrfs_set_trans_block_group(trans, inode);
 
 	ret = btrfs_update_inode(trans, root, inode);
@@ -4928,8 +4956,10 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	size_t max_size;
 	unsigned long inline_size;
 	unsigned long ptr;
+	int compress_type;
 
 	WARN_ON(pg_offset != 0);
+	compress_type = btrfs_file_extent_compression(leaf, item);
 	max_size = btrfs_file_extent_ram_bytes(leaf, item);
 	inline_size = btrfs_file_extent_inline_item_len(leaf,
 					btrfs_item_nr(leaf, path->slots[0]));
@@ -4939,8 +4969,8 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	read_extent_buffer(leaf, tmp, ptr, inline_size);
 
 	max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size);
-	ret = btrfs_zlib_decompress(tmp, page, extent_offset,
-				    inline_size, max_size);
+	ret = btrfs_decompress(compress_type, tmp, page,
+			       extent_offset, inline_size, max_size);
 	if (ret) {
 		char *kaddr = kmap_atomic(page, KM_USER0);
 		unsigned long copy_size = min_t(u64,
@@ -4982,7 +5012,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_trans_handle *trans = NULL;
-	int compressed;
+	int compress_type;
 
 again:
 	read_lock(&em_tree->lock);
@@ -5041,7 +5071,7 @@ again:
 
 	found_type = btrfs_file_extent_type(leaf, item);
 	extent_start = found_key.offset;
-	compressed = btrfs_file_extent_compression(leaf, item);
+	compress_type = btrfs_file_extent_compression(leaf, item);
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
 		extent_end = extent_start +
@@ -5087,8 +5117,9 @@ again:
 			em->block_start = EXTENT_MAP_HOLE;
 			goto insert;
 		}
-		if (compressed) {
+		if (compress_type != BTRFS_COMPRESS_NONE) {
 			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+			em->compress_type = compress_type;
 			em->block_start = bytenr;
 			em->block_len = btrfs_file_extent_disk_num_bytes(leaf,
 									 item);
@@ -5122,12 +5153,14 @@ again:
 		em->len = (copy_size + root->sectorsize - 1) &
 			~((u64)root->sectorsize - 1);
 		em->orig_start = EXTENT_MAP_INLINE;
-		if (compressed)
+		if (compress_type) {
 			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+			em->compress_type = compress_type;
+		}
 		ptr = btrfs_file_extent_inline_start(item) + extent_offset;
 		if (create == 0 && !PageUptodate(page)) {
-			if (btrfs_file_extent_compression(leaf, item) ==
-			    BTRFS_COMPRESS_ZLIB) {
+			if (btrfs_file_extent_compression(leaf, item) !=
+			    BTRFS_COMPRESS_NONE) {
 				ret = uncompress_inline(path, inode, page,
 							pg_offset,
 							extent_offset, item);
@@ -5152,6 +5185,8 @@ again:
 				em = NULL;
 				btrfs_release_path(root, path);
 				trans = btrfs_join_transaction(root, 1);
+				if (IS_ERR(trans))
+					return ERR_CAST(trans);
 				goto again;
 			}
 			map = kmap(page);
@@ -5256,8 +5291,8 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 	btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
 
 	trans = btrfs_join_transaction(root, 0);
-	if (!trans)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(trans))
+		return ERR_CAST(trans);
 
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
@@ -5481,7 +5516,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		 * while we look for nocow cross refs
 		 */
 		trans = btrfs_join_transaction(root, 0);
-		if (!trans)
+		if (IS_ERR(trans))
 			goto must_cow;
 
 		if (can_nocow_odirect(trans, inode, start, len) == 1) {
@@ -5616,7 +5651,7 @@ again:
 	BUG_ON(!ordered);
 
 	trans = btrfs_join_transaction(root, 1);
-	if (!trans) {
+	if (IS_ERR(trans)) {
 		err = -ENOMEM;
 		goto out;
 	}
@@ -6477,7 +6512,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->ordered_data_close = 0;
 	ei->orphan_meta_reserved = 0;
 	ei->dummy_inode = 0;
-	ei->force_compress = 0;
+	ei->force_compress = BTRFS_COMPRESS_NONE;
 
 	inode = &ei->vfs_inode;
 	extent_map_tree_init(&ei->extent_tree, GFP_NOFS);
@@ -7098,116 +7133,6 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
 					   min_size, actual_len, alloc_hint, trans);
 }
 
-static long btrfs_fallocate(struct inode *inode, int mode,
-			    loff_t offset, loff_t len)
-{
-	struct extent_state *cached_state = NULL;
-	u64 cur_offset;
-	u64 last_byte;
-	u64 alloc_start;
-	u64 alloc_end;
-	u64 alloc_hint = 0;
-	u64 locked_end;
-	u64 mask = BTRFS_I(inode)->root->sectorsize - 1;
-	struct extent_map *em;
-	int ret;
-
-	alloc_start = offset & ~mask;
-	alloc_end =  (offset + len + mask) & ~mask;
-
-	/* We only support the FALLOC_FL_KEEP_SIZE mode */
-	if (mode && (mode != FALLOC_FL_KEEP_SIZE))
-		return -EOPNOTSUPP;
-
-	/*
-	 * wait for ordered IO before we have any locks.  We'll loop again
-	 * below with the locks held.
-	 */
-	btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start);
-
-	mutex_lock(&inode->i_mutex);
-	ret = inode_newsize_ok(inode, alloc_end);
-	if (ret)
-		goto out;
-
-	if (alloc_start > inode->i_size) {
-		ret = btrfs_cont_expand(inode, alloc_start);
-		if (ret)
-			goto out;
-	}
-
-	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
-	if (ret)
-		goto out;
-
-	locked_end = alloc_end - 1;
-	while (1) {
-		struct btrfs_ordered_extent *ordered;
-
-		/* the extent lock is ordered inside the running
-		 * transaction
-		 */
-		lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
-				 locked_end, 0, &cached_state, GFP_NOFS);
-		ordered = btrfs_lookup_first_ordered_extent(inode,
-							    alloc_end - 1);
-		if (ordered &&
-		    ordered->file_offset + ordered->len > alloc_start &&
-		    ordered->file_offset < alloc_end) {
-			btrfs_put_ordered_extent(ordered);
-			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
-					     alloc_start, locked_end,
-					     &cached_state, GFP_NOFS);
-			/*
-			 * we can't wait on the range with the transaction
-			 * running or with the extent lock held
-			 */
-			btrfs_wait_ordered_range(inode, alloc_start,
-						 alloc_end - alloc_start);
-		} else {
-			if (ordered)
-				btrfs_put_ordered_extent(ordered);
-			break;
-		}
-	}
-
-	cur_offset = alloc_start;
-	while (1) {
-		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
-				      alloc_end - cur_offset, 0);
-		BUG_ON(IS_ERR(em) || !em);
-		last_byte = min(extent_map_end(em), alloc_end);
-		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))) {
-			ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
-							last_byte - cur_offset,
-							1 << inode->i_blkbits,
-							offset + len,
-							&alloc_hint);
-			if (ret < 0) {
-				free_extent_map(em);
-				break;
-			}
-		}
-		free_extent_map(em);
-
-		cur_offset = last_byte;
-		if (cur_offset >= alloc_end) {
-			ret = 0;
-			break;
-		}
-	}
-	unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
-			     &cached_state, GFP_NOFS);
-
-	btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
-out:
-	mutex_unlock(&inode->i_mutex);
-	return ret;
-}
-
 static int btrfs_set_page_dirty(struct page *page)
 {
 	return __set_page_dirty_nobuffers(page);
@@ -7215,6 +7140,10 @@ static int btrfs_set_page_dirty(struct page *page)
 
 static int btrfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+
+	if (btrfs_root_readonly(root) && (mask & MAY_WRITE))
+		return -EROFS;
 	if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE))
 		return -EACCES;
 	return generic_permission(inode, mask, flags, btrfs_check_acl);
@@ -7310,7 +7239,6 @@ static const struct inode_operations btrfs_file_inode_operations = {
 	.listxattr      = btrfs_listxattr,
 	.removexattr	= btrfs_removexattr,
 	.permission	= btrfs_permission,
-	.fallocate	= btrfs_fallocate,
 	.fiemap		= btrfs_fiemap,
 };
 static const struct inode_operations btrfs_special_inode_operations = {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index f87552a1d7ea..02d224e8c83f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -147,6 +147,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	unsigned int flags, oldflags;
 	int ret;
 
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	if (copy_from_user(&flags, arg, sizeof(flags)))
 		return -EFAULT;
 
@@ -200,7 +203,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 
 
 	trans = btrfs_join_transaction(root, 1);
-	BUG_ON(!trans);
+	BUG_ON(IS_ERR(trans));
 
 	ret = btrfs_update_inode(trans, root, inode);
 	BUG_ON(ret);
@@ -360,7 +363,8 @@ fail:
 }
 
 static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
-			   char *name, int namelen, u64 *async_transid)
+			   char *name, int namelen, u64 *async_transid,
+			   bool readonly)
 {
 	struct inode *inode;
 	struct dentry *parent;
@@ -378,6 +382,7 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
 	btrfs_init_block_rsv(&pending_snapshot->block_rsv);
 	pending_snapshot->dentry = dentry;
 	pending_snapshot->root = root;
+	pending_snapshot->readonly = readonly;
 
 	trans = btrfs_start_transaction(root->fs_info->extent_root, 5);
 	if (IS_ERR(trans)) {
@@ -509,7 +514,7 @@ static inline int btrfs_may_create(struct inode *dir, struct dentry *child)
 static noinline int btrfs_mksubvol(struct path *parent,
 				   char *name, int namelen,
 				   struct btrfs_root *snap_src,
-				   u64 *async_transid)
+				   u64 *async_transid, bool readonly)
 {
 	struct inode *dir  = parent->dentry->d_inode;
 	struct dentry *dentry;
@@ -541,7 +546,7 @@ static noinline int btrfs_mksubvol(struct path *parent,
 
 	if (snap_src) {
 		error = create_snapshot(snap_src, dentry,
-					name, namelen, async_transid);
+					name, namelen, async_transid, readonly);
 	} else {
 		error = create_subvol(BTRFS_I(dir)->root, dentry,
 				      name, namelen, async_transid);
@@ -638,9 +643,11 @@ static int btrfs_defrag_file(struct file *file,
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	struct page *page;
+	struct btrfs_super_block *disk_super;
 	unsigned long last_index;
 	unsigned long ra_pages = root->fs_info->bdi.ra_pages;
 	unsigned long total_read = 0;
+	u64 features;
 	u64 page_start;
 	u64 page_end;
 	u64 last_len = 0;
@@ -648,6 +655,14 @@ static int btrfs_defrag_file(struct file *file,
 	u64 defrag_end = 0;
 	unsigned long i;
 	int ret;
+	int compress_type = BTRFS_COMPRESS_ZLIB;
+
+	if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
+		if (range->compress_type > BTRFS_COMPRESS_TYPES)
+			return -EINVAL;
+		if (range->compress_type)
+			compress_type = range->compress_type;
+	}
 
 	if (inode->i_size == 0)
 		return 0;
@@ -683,7 +698,7 @@ static int btrfs_defrag_file(struct file *file,
 		total_read++;
 		mutex_lock(&inode->i_mutex);
 		if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
-			BTRFS_I(inode)->force_compress = 1;
+			BTRFS_I(inode)->force_compress = compress_type;
 
 		ret  = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
 		if (ret)
@@ -781,10 +796,17 @@ loop_unlock:
 		atomic_dec(&root->fs_info->async_submit_draining);
 
 		mutex_lock(&inode->i_mutex);
-		BTRFS_I(inode)->force_compress = 0;
+		BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
 		mutex_unlock(&inode->i_mutex);
 	}
 
+	disk_super = &root->fs_info->super_copy;
+	features = btrfs_super_incompat_flags(disk_super);
+	if (range->compress_type == BTRFS_COMPRESS_LZO) {
+		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+		btrfs_set_super_incompat_flags(disk_super, features);
+	}
+
 	return 0;
 
 err_reservations:
@@ -885,6 +907,10 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 
 	if (new_size > old_size) {
 		trans = btrfs_start_transaction(root, 0);
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+			goto out_unlock;
+		}
 		ret = btrfs_grow_device(trans, device, new_size);
 		btrfs_commit_transaction(trans, root);
 	} else {
@@ -901,7 +927,8 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 						    char *name,
 						    unsigned long fd,
 						    int subvol,
-						    u64 *transid)
+						    u64 *transid,
+						    bool readonly)
 {
 	struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
 	struct file *src_file;
@@ -919,7 +946,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 
 	if (subvol) {
 		ret = btrfs_mksubvol(&file->f_path, name, namelen,
-				     NULL, transid);
+				     NULL, transid, readonly);
 	} else {
 		struct inode *src_inode;
 		src_file = fget(fd);
@@ -938,7 +965,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 		}
 		ret = btrfs_mksubvol(&file->f_path, name, namelen,
 				     BTRFS_I(src_inode)->root,
-				     transid);
+				     transid, readonly);
 		fput(src_file);
 	}
 out:
@@ -946,58 +973,139 @@ out:
 }
 
 static noinline int btrfs_ioctl_snap_create(struct file *file,
-					    void __user *arg, int subvol,
-					    int v2)
+					    void __user *arg, int subvol)
 {
-	struct btrfs_ioctl_vol_args *vol_args = NULL;
-	struct btrfs_ioctl_vol_args_v2 *vol_args_v2 = NULL;
-	char *name;
-	u64 fd;
+	struct btrfs_ioctl_vol_args *vol_args;
 	int ret;
 
-	if (v2) {
-		u64 transid = 0;
-		u64 *ptr = NULL;
-
-		vol_args_v2 = memdup_user(arg, sizeof(*vol_args_v2));
-		if (IS_ERR(vol_args_v2))
-			return PTR_ERR(vol_args_v2);
+	vol_args = memdup_user(arg, sizeof(*vol_args));
+	if (IS_ERR(vol_args))
+		return PTR_ERR(vol_args);
+	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 
-		if (vol_args_v2->flags & ~BTRFS_SUBVOL_CREATE_ASYNC) {
-			ret = -EINVAL;
-			goto out;
-		}
+	ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
+					      vol_args->fd, subvol,
+					      NULL, false);
 
-		name = vol_args_v2->name;
-		fd = vol_args_v2->fd;
-		vol_args_v2->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+	kfree(vol_args);
+	return ret;
+}
 
-		if (vol_args_v2->flags & BTRFS_SUBVOL_CREATE_ASYNC)
-			ptr = &transid;
+static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
+					       void __user *arg, int subvol)
+{
+	struct btrfs_ioctl_vol_args_v2 *vol_args;
+	int ret;
+	u64 transid = 0;
+	u64 *ptr = NULL;
+	bool readonly = false;
 
-		ret = btrfs_ioctl_snap_create_transid(file, name, fd,
-						      subvol, ptr);
+	vol_args = memdup_user(arg, sizeof(*vol_args));
+	if (IS_ERR(vol_args))
+		return PTR_ERR(vol_args);
+	vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
 
-		if (ret == 0 && ptr &&
-		    copy_to_user(arg +
-				 offsetof(struct btrfs_ioctl_vol_args_v2,
-					  transid), ptr, sizeof(*ptr)))
-			ret = -EFAULT;
-	} else {
-		vol_args = memdup_user(arg, sizeof(*vol_args));
-		if (IS_ERR(vol_args))
-			return PTR_ERR(vol_args);
-		name = vol_args->name;
-		fd = vol_args->fd;
-		vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
-
-		ret = btrfs_ioctl_snap_create_transid(file, name, fd,
-						      subvol, NULL);
+	if (vol_args->flags &
+	    ~(BTRFS_SUBVOL_CREATE_ASYNC | BTRFS_SUBVOL_RDONLY)) {
+		ret = -EOPNOTSUPP;
+		goto out;
 	}
+
+	if (vol_args->flags & BTRFS_SUBVOL_CREATE_ASYNC)
+		ptr = &transid;
+	if (vol_args->flags & BTRFS_SUBVOL_RDONLY)
+		readonly = true;
+
+	ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
+					      vol_args->fd, subvol,
+					      ptr, readonly);
+
+	if (ret == 0 && ptr &&
+	    copy_to_user(arg +
+			 offsetof(struct btrfs_ioctl_vol_args_v2,
+				  transid), ptr, sizeof(*ptr)))
+		ret = -EFAULT;
 out:
 	kfree(vol_args);
-	kfree(vol_args_v2);
+	return ret;
+}
+
+static noinline int btrfs_ioctl_subvol_getflags(struct file *file,
+						void __user *arg)
+{
+	struct inode *inode = fdentry(file)->d_inode;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	int ret = 0;
+	u64 flags = 0;
+
+	if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID)
+		return -EINVAL;
+
+	down_read(&root->fs_info->subvol_sem);
+	if (btrfs_root_readonly(root))
+		flags |= BTRFS_SUBVOL_RDONLY;
+	up_read(&root->fs_info->subvol_sem);
+
+	if (copy_to_user(arg, &flags, sizeof(flags)))
+		ret = -EFAULT;
+
+	return ret;
+}
+
+static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
+					      void __user *arg)
+{
+	struct inode *inode = fdentry(file)->d_inode;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_trans_handle *trans;
+	u64 root_flags;
+	u64 flags;
+	int ret = 0;
+
+	if (root->fs_info->sb->s_flags & MS_RDONLY)
+		return -EROFS;
+
+	if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID)
+		return -EINVAL;
+
+	if (copy_from_user(&flags, arg, sizeof(flags)))
+		return -EFAULT;
+
+	if (flags & ~BTRFS_SUBVOL_CREATE_ASYNC)
+		return -EINVAL;
+
+	if (flags & ~BTRFS_SUBVOL_RDONLY)
+		return -EOPNOTSUPP;
+
+	down_write(&root->fs_info->subvol_sem);
 
+	/* nothing to do */
+	if (!!(flags & BTRFS_SUBVOL_RDONLY) == btrfs_root_readonly(root))
+		goto out;
+
+	root_flags = btrfs_root_flags(&root->root_item);
+	if (flags & BTRFS_SUBVOL_RDONLY)
+		btrfs_set_root_flags(&root->root_item,
+				     root_flags | BTRFS_ROOT_SUBVOL_RDONLY);
+	else
+		btrfs_set_root_flags(&root->root_item,
+				     root_flags & ~BTRFS_ROOT_SUBVOL_RDONLY);
+
+	trans = btrfs_start_transaction(root, 1);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out_reset;
+	}
+
+	ret = btrfs_update_root(trans, root,
+				&root->root_key, &root->root_item);
+
+	btrfs_commit_transaction(trans, root);
+out_reset:
+	if (ret)
+		btrfs_set_root_flags(&root->root_item, root_flags);
+out:
+	up_write(&root->fs_info->subvol_sem);
 	return ret;
 }
 
@@ -1509,6 +1617,9 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 	struct btrfs_ioctl_defrag_range_args *range;
 	int ret;
 
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	ret = mnt_want_write(file->f_path.mnt);
 	if (ret)
 		return ret;
@@ -1637,6 +1748,9 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
 		return -EINVAL;
 
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	ret = mnt_want_write(file->f_path.mnt);
 	if (ret)
 		return ret;
@@ -1788,7 +1902,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 
 			memcpy(&new_key, &key, sizeof(new_key));
 			new_key.objectid = inode->i_ino;
-			new_key.offset = key.offset + destoff - off;
+			if (off <= key.offset)
+				new_key.offset = key.offset + destoff - off;
+			else
+				new_key.offset = destoff;
 
 			trans = btrfs_start_transaction(root, 1);
 			if (IS_ERR(trans)) {
@@ -1958,6 +2075,10 @@ static long btrfs_ioctl_trans_start(struct file *file)
 	if (file->private_data)
 		goto out;
 
+	ret = -EROFS;
+	if (btrfs_root_readonly(root))
+		goto out;
+
 	ret = mnt_want_write(file->f_path.mnt);
 	if (ret)
 		goto out;
@@ -1968,7 +2089,7 @@ static long btrfs_ioctl_trans_start(struct file *file)
 
 	ret = -ENOMEM;
 	trans = btrfs_start_ioctl_transaction(root, 0);
-	if (!trans)
+	if (IS_ERR(trans))
 		goto out_drop;
 
 	file->private_data = trans;
@@ -2024,9 +2145,9 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
 	path->leave_spinning = 1;
 
 	trans = btrfs_start_transaction(root, 1);
-	if (!trans) {
+	if (IS_ERR(trans)) {
 		btrfs_free_path(path);
-		return -ENOMEM;
+		return PTR_ERR(trans);
 	}
 
 	dir_id = btrfs_super_root_dir(&root->fs_info->super_copy);
@@ -2220,6 +2341,8 @@ static noinline long btrfs_ioctl_start_sync(struct file *file, void __user *argp
 	u64 transid;
 
 	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 	transid = trans->transid;
 	btrfs_commit_transaction_async(trans, root, 0);
 
@@ -2257,13 +2380,17 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case FS_IOC_GETVERSION:
 		return btrfs_ioctl_getversion(file, argp);
 	case BTRFS_IOC_SNAP_CREATE:
-		return btrfs_ioctl_snap_create(file, argp, 0, 0);
+		return btrfs_ioctl_snap_create(file, argp, 0);
 	case BTRFS_IOC_SNAP_CREATE_V2:
-		return btrfs_ioctl_snap_create(file, argp, 0, 1);
+		return btrfs_ioctl_snap_create_v2(file, argp, 0);
 	case BTRFS_IOC_SUBVOL_CREATE:
-		return btrfs_ioctl_snap_create(file, argp, 1, 0);
+		return btrfs_ioctl_snap_create(file, argp, 1);
 	case BTRFS_IOC_SNAP_DESTROY:
 		return btrfs_ioctl_snap_destroy(file, argp);
+	case BTRFS_IOC_SUBVOL_GETFLAGS:
+		return btrfs_ioctl_subvol_getflags(file, argp);
+	case BTRFS_IOC_SUBVOL_SETFLAGS:
+		return btrfs_ioctl_subvol_setflags(file, argp);
 	case BTRFS_IOC_DEFAULT_SUBVOL:
 		return btrfs_ioctl_default_subvol(file, argp);
 	case BTRFS_IOC_DEFRAG:
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index c344d12c646b..8fb382167b13 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -31,6 +31,7 @@ struct btrfs_ioctl_vol_args {
 };
 
 #define BTRFS_SUBVOL_CREATE_ASYNC	(1ULL << 0)
+#define BTRFS_SUBVOL_RDONLY		(1ULL << 1)
 
 #define BTRFS_SUBVOL_NAME_MAX 4039
 struct btrfs_ioctl_vol_args_v2 {
@@ -133,8 +134,15 @@ struct btrfs_ioctl_defrag_range_args {
 	 */
 	__u32 extent_thresh;
 
+	/*
+	 * which compression method to use if turning on compression
+	 * for this defrag operation.  If unspecified, zlib will
+	 * be used
+	 */
+	__u32 compress_type;
+
 	/* spare for later */
-	__u32 unused[5];
+	__u32 unused[4];
 };
 
 struct btrfs_ioctl_space_info {
@@ -193,4 +201,6 @@ struct btrfs_ioctl_space_args {
 #define BTRFS_IOC_WAIT_SYNC  _IOW(BTRFS_IOCTL_MAGIC, 22, __u64)
 #define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \
 				   struct btrfs_ioctl_vol_args_v2)
+#define BTRFS_IOC_SUBVOL_GETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 25, __u64)
+#define BTRFS_IOC_SUBVOL_SETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 26, __u64)
 #endif
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
new file mode 100644
index 000000000000..cc9b450399df
--- /dev/null
+++ b/fs/btrfs/lzo.c
@@ -0,0 +1,420 @@
+/*
+ * Copyright (C) 2008 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/pagemap.h>
+#include <linux/bio.h>
+#include <linux/lzo.h>
+#include "compression.h"
+
+#define LZO_LEN	4
+
+struct workspace {
+	void *mem;
+	void *buf;	/* where compressed data goes */
+	void *cbuf;	/* where decompressed data goes */
+	struct list_head list;
+};
+
+static void lzo_free_workspace(struct list_head *ws)
+{
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
+
+	vfree(workspace->buf);
+	vfree(workspace->cbuf);
+	vfree(workspace->mem);
+	kfree(workspace);
+}
+
+static struct list_head *lzo_alloc_workspace(void)
+{
+	struct workspace *workspace;
+
+	workspace = kzalloc(sizeof(*workspace), GFP_NOFS);
+	if (!workspace)
+		return ERR_PTR(-ENOMEM);
+
+	workspace->mem = vmalloc(LZO1X_MEM_COMPRESS);
+	workspace->buf = vmalloc(lzo1x_worst_compress(PAGE_CACHE_SIZE));
+	workspace->cbuf = vmalloc(lzo1x_worst_compress(PAGE_CACHE_SIZE));
+	if (!workspace->mem || !workspace->buf || !workspace->cbuf)
+		goto fail;
+
+	INIT_LIST_HEAD(&workspace->list);
+
+	return &workspace->list;
+fail:
+	lzo_free_workspace(&workspace->list);
+	return ERR_PTR(-ENOMEM);
+}
+
+static inline void write_compress_length(char *buf, size_t len)
+{
+	__le32 dlen;
+
+	dlen = cpu_to_le32(len);
+	memcpy(buf, &dlen, LZO_LEN);
+}
+
+static inline size_t read_compress_length(char *buf)
+{
+	__le32 dlen;
+
+	memcpy(&dlen, buf, LZO_LEN);
+	return le32_to_cpu(dlen);
+}
+
+static int lzo_compress_pages(struct list_head *ws,
+			      struct address_space *mapping,
+			      u64 start, unsigned long len,
+			      struct page **pages,
+			      unsigned long nr_dest_pages,
+			      unsigned long *out_pages,
+			      unsigned long *total_in,
+			      unsigned long *total_out,
+			      unsigned long max_out)
+{
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	int ret = 0;
+	char *data_in;
+	char *cpage_out;
+	int nr_pages = 0;
+	struct page *in_page = NULL;
+	struct page *out_page = NULL;
+	unsigned long bytes_left;
+
+	size_t in_len;
+	size_t out_len;
+	char *buf;
+	unsigned long tot_in = 0;
+	unsigned long tot_out = 0;
+	unsigned long pg_bytes_left;
+	unsigned long out_offset;
+	unsigned long bytes;
+
+	*out_pages = 0;
+	*total_out = 0;
+	*total_in = 0;
+
+	in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
+	data_in = kmap(in_page);
+
+	/*
+	 * store the size of all chunks of compressed data in
+	 * the first 4 bytes
+	 */
+	out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+	if (out_page == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	cpage_out = kmap(out_page);
+	out_offset = LZO_LEN;
+	tot_out = LZO_LEN;
+	pages[0] = out_page;
+	nr_pages = 1;
+	pg_bytes_left = PAGE_CACHE_SIZE - LZO_LEN;
+
+	/* compress at most one page of data each time */
+	in_len = min(len, PAGE_CACHE_SIZE);
+	while (tot_in < len) {
+		ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf,
+				       &out_len, workspace->mem);
+		if (ret != LZO_E_OK) {
+			printk(KERN_DEBUG "btrfs deflate in loop returned %d\n",
+			       ret);
+			ret = -1;
+			goto out;
+		}
+
+		/* store the size of this chunk of compressed data */
+		write_compress_length(cpage_out + out_offset, out_len);
+		tot_out += LZO_LEN;
+		out_offset += LZO_LEN;
+		pg_bytes_left -= LZO_LEN;
+
+		tot_in += in_len;
+		tot_out += out_len;
+
+		/* copy bytes from the working buffer into the pages */
+		buf = workspace->cbuf;
+		while (out_len) {
+			bytes = min_t(unsigned long, pg_bytes_left, out_len);
+
+			memcpy(cpage_out + out_offset, buf, bytes);
+
+			out_len -= bytes;
+			pg_bytes_left -= bytes;
+			buf += bytes;
+			out_offset += bytes;
+
+			/*
+			 * we need another page for writing out.
+			 *
+			 * Note if there's less than 4 bytes left, we just
+			 * skip to a new page.
+			 */
+			if ((out_len == 0 && pg_bytes_left < LZO_LEN) ||
+			    pg_bytes_left == 0) {
+				if (pg_bytes_left) {
+					memset(cpage_out + out_offset, 0,
+					       pg_bytes_left);
+					tot_out += pg_bytes_left;
+				}
+
+				/* we're done, don't allocate new page */
+				if (out_len == 0 && tot_in >= len)
+					break;
+
+				kunmap(out_page);
+				if (nr_pages == nr_dest_pages) {
+					out_page = NULL;
+					ret = -1;
+					goto out;
+				}
+
+				out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+				if (out_page == NULL) {
+					ret = -ENOMEM;
+					goto out;
+				}
+				cpage_out = kmap(out_page);
+				pages[nr_pages++] = out_page;
+
+				pg_bytes_left = PAGE_CACHE_SIZE;
+				out_offset = 0;
+			}
+		}
+
+		/* we're making it bigger, give up */
+		if (tot_in > 8192 && tot_in < tot_out)
+			goto out;
+
+		/* we're all done */
+		if (tot_in >= len)
+			break;
+
+		if (tot_out > max_out)
+			break;
+
+		bytes_left = len - tot_in;
+		kunmap(in_page);
+		page_cache_release(in_page);
+
+		start += PAGE_CACHE_SIZE;
+		in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
+		data_in = kmap(in_page);
+		in_len = min(bytes_left, PAGE_CACHE_SIZE);
+	}
+
+	if (tot_out > tot_in)
+		goto out;
+
+	/* store the size of all chunks of compressed data */
+	cpage_out = kmap(pages[0]);
+	write_compress_length(cpage_out, tot_out);
+
+	kunmap(pages[0]);
+
+	ret = 0;
+	*total_out = tot_out;
+	*total_in = tot_in;
+out:
+	*out_pages = nr_pages;
+	if (out_page)
+		kunmap(out_page);
+
+	if (in_page) {
+		kunmap(in_page);
+		page_cache_release(in_page);
+	}
+
+	return ret;
+}
+
+static int lzo_decompress_biovec(struct list_head *ws,
+				 struct page **pages_in,
+				 u64 disk_start,
+				 struct bio_vec *bvec,
+				 int vcnt,
+				 size_t srclen)
+{
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	int ret = 0, ret2;
+	char *data_in;
+	unsigned long page_in_index = 0;
+	unsigned long page_out_index = 0;
+	unsigned long total_pages_in = (srclen + PAGE_CACHE_SIZE - 1) /
+					PAGE_CACHE_SIZE;
+	unsigned long buf_start;
+	unsigned long buf_offset = 0;
+	unsigned long bytes;
+	unsigned long working_bytes;
+	unsigned long pg_offset;
+
+	size_t in_len;
+	size_t out_len;
+	unsigned long in_offset;
+	unsigned long in_page_bytes_left;
+	unsigned long tot_in;
+	unsigned long tot_out;
+	unsigned long tot_len;
+	char *buf;
+
+	data_in = kmap(pages_in[0]);
+	tot_len = read_compress_length(data_in);
+
+	tot_in = LZO_LEN;
+	in_offset = LZO_LEN;
+	tot_len = min_t(size_t, srclen, tot_len);
+	in_page_bytes_left = PAGE_CACHE_SIZE - LZO_LEN;
+
+	tot_out = 0;
+	pg_offset = 0;
+
+	while (tot_in < tot_len) {
+		in_len = read_compress_length(data_in + in_offset);
+		in_page_bytes_left -= LZO_LEN;
+		in_offset += LZO_LEN;
+		tot_in += LZO_LEN;
+
+		tot_in += in_len;
+		working_bytes = in_len;
+
+		/* fast path: avoid using the working buffer */
+		if (in_page_bytes_left >= in_len) {
+			buf = data_in + in_offset;
+			bytes = in_len;
+			goto cont;
+		}
+
+		/* copy bytes from the pages into the working buffer */
+		buf = workspace->cbuf;
+		buf_offset = 0;
+		while (working_bytes) {
+			bytes = min(working_bytes, in_page_bytes_left);
+
+			memcpy(buf + buf_offset, data_in + in_offset, bytes);
+			buf_offset += bytes;
+cont:
+			working_bytes -= bytes;
+			in_page_bytes_left -= bytes;
+			in_offset += bytes;
+
+			/* check if we need to pick another page */
+			if ((working_bytes == 0 && in_page_bytes_left < LZO_LEN)
+			    || in_page_bytes_left == 0) {
+				tot_in += in_page_bytes_left;
+
+				if (working_bytes == 0 && tot_in >= tot_len)
+					break;
+
+				kunmap(pages_in[page_in_index]);
+				page_in_index++;
+				if (page_in_index >= total_pages_in) {
+					ret = -1;
+					data_in = NULL;
+					goto done;
+				}
+				data_in = kmap(pages_in[page_in_index]);
+
+				in_page_bytes_left = PAGE_CACHE_SIZE;
+				in_offset = 0;
+			}
+		}
+
+		out_len = lzo1x_worst_compress(PAGE_CACHE_SIZE);
+		ret = lzo1x_decompress_safe(buf, in_len, workspace->buf,
+					    &out_len);
+		if (ret != LZO_E_OK) {
+			printk(KERN_WARNING "btrfs decompress failed\n");
+			ret = -1;
+			break;
+		}
+
+		buf_start = tot_out;
+		tot_out += out_len;
+
+		ret2 = btrfs_decompress_buf2page(workspace->buf, buf_start,
+						 tot_out, disk_start,
+						 bvec, vcnt,
+						 &page_out_index, &pg_offset);
+		if (ret2 == 0)
+			break;
+	}
+done:
+	if (data_in)
+		kunmap(pages_in[page_in_index]);
+	return ret;
+}
+
+static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
+			  struct page *dest_page,
+			  unsigned long start_byte,
+			  size_t srclen, size_t destlen)
+{
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	size_t in_len;
+	size_t out_len;
+	size_t tot_len;
+	int ret = 0;
+	char *kaddr;
+	unsigned long bytes;
+
+	BUG_ON(srclen < LZO_LEN);
+
+	tot_len = read_compress_length(data_in);
+	data_in += LZO_LEN;
+
+	in_len = read_compress_length(data_in);
+	data_in += LZO_LEN;
+
+	out_len = PAGE_CACHE_SIZE;
+	ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
+	if (ret != LZO_E_OK) {
+		printk(KERN_WARNING "btrfs decompress failed!\n");
+		ret = -1;
+		goto out;
+	}
+
+	if (out_len < start_byte) {
+		ret = -1;
+		goto out;
+	}
+
+	bytes = min_t(unsigned long, destlen, out_len - start_byte);
+
+	kaddr = kmap_atomic(dest_page, KM_USER0);
+	memcpy(kaddr, workspace->buf + start_byte, bytes);
+	kunmap_atomic(kaddr, KM_USER0);
+out:
+	return ret;
+}
+
+struct btrfs_compress_op btrfs_lzo_compress = {
+	.alloc_workspace	= lzo_alloc_workspace,
+	.free_workspace		= lzo_free_workspace,
+	.compress_pages		= lzo_compress_pages,
+	.decompress_biovec	= lzo_decompress_biovec,
+	.decompress		= lzo_decompress,
+};
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index ae7737e352c9..083a55477375 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -141,7 +141,7 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
 					  u64 file_offset)
 {
 	struct rb_root *root = &tree->tree;
-	struct rb_node *prev;
+	struct rb_node *prev = NULL;
 	struct rb_node *ret;
 	struct btrfs_ordered_extent *entry;
 
@@ -172,7 +172,7 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
  */
 static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 				      u64 start, u64 len, u64 disk_len,
-				      int type, int dio)
+				      int type, int dio, int compress_type)
 {
 	struct btrfs_ordered_inode_tree *tree;
 	struct rb_node *node;
@@ -189,6 +189,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	entry->disk_len = disk_len;
 	entry->bytes_left = len;
 	entry->inode = inode;
+	entry->compress_type = compress_type;
 	if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE)
 		set_bit(type, &entry->flags);
 
@@ -220,14 +221,25 @@ int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 			     u64 start, u64 len, u64 disk_len, int type)
 {
 	return __btrfs_add_ordered_extent(inode, file_offset, start, len,
-					  disk_len, type, 0);
+					  disk_len, type, 0,
+					  BTRFS_COMPRESS_NONE);
 }
 
 int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
 				 u64 start, u64 len, u64 disk_len, int type)
 {
 	return __btrfs_add_ordered_extent(inode, file_offset, start, len,
-					  disk_len, type, 1);
+					  disk_len, type, 1,
+					  BTRFS_COMPRESS_NONE);
+}
+
+int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
+				      u64 start, u64 len, u64 disk_len,
+				      int type, int compress_type)
+{
+	return __btrfs_add_ordered_extent(inode, file_offset, start, len,
+					  disk_len, type, 0,
+					  compress_type);
 }
 
 /*
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 61dca83119dd..ff1f69aa1883 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -68,7 +68,7 @@ struct btrfs_ordered_sum {
 
 #define BTRFS_ORDERED_NOCOW 2 /* set when we want to write in place */
 
-#define BTRFS_ORDERED_COMPRESSED 3 /* writing a compressed extent */
+#define BTRFS_ORDERED_COMPRESSED 3 /* writing a zlib compressed extent */
 
 #define BTRFS_ORDERED_PREALLOC 4 /* set when writing to prealloced extent */
 
@@ -93,6 +93,9 @@ struct btrfs_ordered_extent {
 	/* flags (described above) */
 	unsigned long flags;
 
+	/* compression algorithm */
+	int compress_type;
+
 	/* reference count */
 	atomic_t refs;
 
@@ -148,6 +151,9 @@ int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 			     u64 start, u64 len, u64 disk_len, int type);
 int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
 				 u64 start, u64 len, u64 disk_len, int type);
+int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
+				      u64 start, u64 len, u64 disk_len,
+				      int type, int compress_type);
 int btrfs_add_ordered_sum(struct inode *inode,
 			  struct btrfs_ordered_extent *entry,
 			  struct btrfs_ordered_sum *sum);
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 0d126be22b63..fb2605d998e9 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -260,6 +260,7 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 #else
 			BUG();
 #endif
+			break;
 		case BTRFS_BLOCK_GROUP_ITEM_KEY:
 			bi = btrfs_item_ptr(l, i,
 					    struct btrfs_block_group_item);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 045c9c2b2d7e..1f5556acb530 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2028,6 +2028,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 
 	while (1) {
 		trans = btrfs_start_transaction(root, 0);
+		BUG_ON(IS_ERR(trans));
 		trans->block_rsv = rc->block_rsv;
 
 		ret = btrfs_block_rsv_check(trans, root, rc->block_rsv,
@@ -2147,6 +2148,12 @@ again:
 	}
 
 	trans = btrfs_join_transaction(rc->extent_root, 1);
+	if (IS_ERR(trans)) {
+		if (!err)
+			btrfs_block_rsv_release(rc->extent_root,
+						rc->block_rsv, num_bytes);
+		return PTR_ERR(trans);
+	}
 
 	if (!err) {
 		if (num_bytes != rc->merging_rsv_size) {
@@ -3222,6 +3229,7 @@ truncate:
 	trans = btrfs_join_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		btrfs_free_path(path);
+		ret = PTR_ERR(trans);
 		goto out;
 	}
 
@@ -3628,6 +3636,7 @@ int prepare_to_relocate(struct reloc_control *rc)
 	set_reloc_control(rc);
 
 	trans = btrfs_join_transaction(rc->extent_root, 1);
+	BUG_ON(IS_ERR(trans));
 	btrfs_commit_transaction(trans, rc->extent_root);
 	return 0;
 }
@@ -3657,6 +3666,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 
 	while (1) {
 		trans = btrfs_start_transaction(rc->extent_root, 0);
+		BUG_ON(IS_ERR(trans));
 
 		if (update_backref_cache(trans, &rc->backref_cache)) {
 			btrfs_end_transaction(trans, rc->extent_root);
@@ -3804,7 +3814,10 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 
 	/* get rid of pinned extents */
 	trans = btrfs_join_transaction(rc->extent_root, 1);
-	btrfs_commit_transaction(trans, rc->extent_root);
+	if (IS_ERR(trans))
+		err = PTR_ERR(trans);
+	else
+		btrfs_commit_transaction(trans, rc->extent_root);
 out_free:
 	btrfs_free_block_rsv(rc->extent_root, rc->block_rsv);
 	btrfs_free_path(path);
@@ -4022,6 +4035,7 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root)
 	int ret;
 
 	trans = btrfs_start_transaction(root->fs_info->tree_root, 0);
+	BUG_ON(IS_ERR(trans));
 
 	memset(&root->root_item.drop_progress, 0,
 		sizeof(root->root_item.drop_progress));
@@ -4125,6 +4139,11 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 	set_reloc_control(rc);
 
 	trans = btrfs_join_transaction(rc->extent_root, 1);
+	if (IS_ERR(trans)) {
+		unset_reloc_control(rc);
+		err = PTR_ERR(trans);
+		goto out_free;
+	}
 
 	rc->merge_reloc_tree = 1;
 
@@ -4154,9 +4173,13 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 	unset_reloc_control(rc);
 
 	trans = btrfs_join_transaction(rc->extent_root, 1);
-	btrfs_commit_transaction(trans, rc->extent_root);
-out:
+	if (IS_ERR(trans))
+		err = PTR_ERR(trans);
+	else
+		btrfs_commit_transaction(trans, rc->extent_root);
+out_free:
 	kfree(rc);
+out:
 	while (!list_empty(&reloc_roots)) {
 		reloc_root = list_entry(reloc_roots.next,
 					struct btrfs_root, root_list);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 22acdaa78ce1..a004008f7d28 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -54,6 +54,90 @@
 
 static const struct super_operations btrfs_super_ops;
 
+static const char *btrfs_decode_error(struct btrfs_fs_info *fs_info, int errno,
+				      char nbuf[16])
+{
+	char *errstr = NULL;
+
+	switch (errno) {
+	case -EIO:
+		errstr = "IO failure";
+		break;
+	case -ENOMEM:
+		errstr = "Out of memory";
+		break;
+	case -EROFS:
+		errstr = "Readonly filesystem";
+		break;
+	default:
+		if (nbuf) {
+			if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
+				errstr = nbuf;
+		}
+		break;
+	}
+
+	return errstr;
+}
+
+static void __save_error_info(struct btrfs_fs_info *fs_info)
+{
+	/*
+	 * today we only save the error info into ram.  Long term we'll
+	 * also send it down to the disk
+	 */
+	fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR;
+}
+
+/* NOTE:
+ *	We move write_super stuff at umount in order to avoid deadlock
+ *	for umount hold all lock.
+ */
+static void save_error_info(struct btrfs_fs_info *fs_info)
+{
+	__save_error_info(fs_info);
+}
+
+/* btrfs handle error by forcing the filesystem readonly */
+static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
+{
+	struct super_block *sb = fs_info->sb;
+
+	if (sb->s_flags & MS_RDONLY)
+		return;
+
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		sb->s_flags |= MS_RDONLY;
+		printk(KERN_INFO "btrfs is forced readonly\n");
+	}
+}
+
+/*
+ * __btrfs_std_error decodes expected errors from the caller and
+ * invokes the approciate error response.
+ */
+void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+		     unsigned int line, int errno)
+{
+	struct super_block *sb = fs_info->sb;
+	char nbuf[16];
+	const char *errstr;
+
+	/*
+	 * Special case: if the error is EROFS, and we're already
+	 * under MS_RDONLY, then it is safe here.
+	 */
+	if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
+		return;
+
+	errstr = btrfs_decode_error(fs_info, errno, nbuf);
+	printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s\n",
+		sb->s_id, function, line, errstr);
+	save_error_info(fs_info);
+
+	btrfs_handle_error(fs_info);
+}
+
 static void btrfs_put_super(struct super_block *sb)
 {
 	struct btrfs_root *root = btrfs_sb(sb);
@@ -69,9 +153,9 @@ enum {
 	Opt_degraded, Opt_subvol, Opt_subvolid, Opt_device, Opt_nodatasum,
 	Opt_nodatacow, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, Opt_ssd,
 	Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress,
-	Opt_compress_force, Opt_notreelog, Opt_ratio, Opt_flushoncommit,
-	Opt_discard, Opt_space_cache, Opt_clear_cache, Opt_err,
-	Opt_user_subvol_rm_allowed,
+	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
+	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
+	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -86,7 +170,9 @@ static match_table_t tokens = {
 	{Opt_alloc_start, "alloc_start=%s"},
 	{Opt_thread_pool, "thread_pool=%d"},
 	{Opt_compress, "compress"},
+	{Opt_compress_type, "compress=%s"},
 	{Opt_compress_force, "compress-force"},
+	{Opt_compress_force_type, "compress-force=%s"},
 	{Opt_ssd, "ssd"},
 	{Opt_ssd_spread, "ssd_spread"},
 	{Opt_nossd, "nossd"},
@@ -112,6 +198,8 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 	char *p, *num, *orig;
 	int intarg;
 	int ret = 0;
+	char *compress_type;
+	bool compress_force = false;
 
 	if (!options)
 		return 0;
@@ -154,14 +242,32 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			btrfs_set_opt(info->mount_opt, NODATACOW);
 			btrfs_set_opt(info->mount_opt, NODATASUM);
 			break;
-		case Opt_compress:
-			printk(KERN_INFO "btrfs: use compression\n");
-			btrfs_set_opt(info->mount_opt, COMPRESS);
-			break;
 		case Opt_compress_force:
-			printk(KERN_INFO "btrfs: forcing compression\n");
-			btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
+		case Opt_compress_force_type:
+			compress_force = true;
+		case Opt_compress:
+		case Opt_compress_type:
+			if (token == Opt_compress ||
+			    token == Opt_compress_force ||
+			    strcmp(args[0].from, "zlib") == 0) {
+				compress_type = "zlib";
+				info->compress_type = BTRFS_COMPRESS_ZLIB;
+			} else if (strcmp(args[0].from, "lzo") == 0) {
+				compress_type = "lzo";
+				info->compress_type = BTRFS_COMPRESS_LZO;
+			} else {
+				ret = -EINVAL;
+				goto out;
+			}
+
 			btrfs_set_opt(info->mount_opt, COMPRESS);
+			if (compress_force) {
+				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
+				pr_info("btrfs: force %s compression\n",
+					compress_type);
+			} else
+				pr_info("btrfs: use %s compression\n",
+					compress_type);
 			break;
 		case Opt_ssd:
 			printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
@@ -277,7 +383,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		struct btrfs_fs_devices **fs_devices)
 {
 	substring_t args[MAX_OPT_ARGS];
-	char *opts, *p;
+	char *opts, *orig, *p;
 	int error = 0;
 	int intarg;
 
@@ -291,6 +397,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 	opts = kstrdup(options, GFP_KERNEL);
 	if (!opts)
 		return -ENOMEM;
+	orig = opts;
 
 	while ((p = strsep(&opts, ",")) != NULL) {
 		int token;
@@ -326,7 +433,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 	}
 
  out_free_opts:
-	kfree(opts);
+	kfree(orig);
  out:
 	/*
 	 * If no subvolume name is specified we use the default one.  Allocate
@@ -517,6 +624,8 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 	btrfs_wait_ordered_extents(root, 0, 0);
 
 	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 	ret = btrfs_commit_transaction(trans, root);
 	return ret;
 }
@@ -655,6 +764,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 		}
 
 		btrfs_close_devices(fs_devices);
+		kfree(fs_info);
+		kfree(tree_root);
 	} else {
 		char b[BDEVNAME_SIZE];
 
@@ -753,6 +864,127 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	return 0;
 }
 
+/*
+ * The helper to calc the free space on the devices that can be used to store
+ * file data.
+ */
+static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_device_info *devices_info;
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_device *device;
+	u64 skip_space;
+	u64 type;
+	u64 avail_space;
+	u64 used_space;
+	u64 min_stripe_size;
+	int min_stripes = 1;
+	int i = 0, nr_devices;
+	int ret;
+
+	nr_devices = fs_info->fs_devices->rw_devices;
+	BUG_ON(!nr_devices);
+
+	devices_info = kmalloc(sizeof(*devices_info) * nr_devices,
+			       GFP_NOFS);
+	if (!devices_info)
+		return -ENOMEM;
+
+	/* calc min stripe number for data space alloction */
+	type = btrfs_get_alloc_profile(root, 1);
+	if (type & BTRFS_BLOCK_GROUP_RAID0)
+		min_stripes = 2;
+	else if (type & BTRFS_BLOCK_GROUP_RAID1)
+		min_stripes = 2;
+	else if (type & BTRFS_BLOCK_GROUP_RAID10)
+		min_stripes = 4;
+
+	if (type & BTRFS_BLOCK_GROUP_DUP)
+		min_stripe_size = 2 * BTRFS_STRIPE_LEN;
+	else
+		min_stripe_size = BTRFS_STRIPE_LEN;
+
+	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
+		if (!device->in_fs_metadata)
+			continue;
+
+		avail_space = device->total_bytes - device->bytes_used;
+
+		/* align with stripe_len */
+		do_div(avail_space, BTRFS_STRIPE_LEN);
+		avail_space *= BTRFS_STRIPE_LEN;
+
+		/*
+		 * In order to avoid overwritting the superblock on the drive,
+		 * btrfs starts at an offset of at least 1MB when doing chunk
+		 * allocation.
+		 */
+		skip_space = 1024 * 1024;
+
+		/* user can set the offset in fs_info->alloc_start. */
+		if (fs_info->alloc_start + BTRFS_STRIPE_LEN <=
+		    device->total_bytes)
+			skip_space = max(fs_info->alloc_start, skip_space);
+
+		/*
+		 * btrfs can not use the free space in [0, skip_space - 1],
+		 * we must subtract it from the total. In order to implement
+		 * it, we account the used space in this range first.
+		 */
+		ret = btrfs_account_dev_extents_size(device, 0, skip_space - 1,
+						     &used_space);
+		if (ret) {
+			kfree(devices_info);
+			return ret;
+		}
+
+		/* calc the free space in [0, skip_space - 1] */
+		skip_space -= used_space;
+
+		/*
+		 * we can use the free space in [0, skip_space - 1], subtract
+		 * it from the total.
+		 */
+		if (avail_space && avail_space >= skip_space)
+			avail_space -= skip_space;
+		else
+			avail_space = 0;
+
+		if (avail_space < min_stripe_size)
+			continue;
+
+		devices_info[i].dev = device;
+		devices_info[i].max_avail = avail_space;
+
+		i++;
+	}
+
+	nr_devices = i;
+
+	btrfs_descending_sort_devices(devices_info, nr_devices);
+
+	i = nr_devices - 1;
+	avail_space = 0;
+	while (nr_devices >= min_stripes) {
+		if (devices_info[i].max_avail >= min_stripe_size) {
+			int j;
+			u64 alloc_size;
+
+			avail_space += devices_info[i].max_avail * min_stripes;
+			alloc_size = devices_info[i].max_avail;
+			for (j = i + 1 - min_stripes; j <= i; j++)
+				devices_info[j].max_avail -= alloc_size;
+		}
+		i--;
+		nr_devices--;
+	}
+
+	kfree(devices_info);
+	*free_bytes = avail_space;
+	return 0;
+}
+
 static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct btrfs_root *root = btrfs_sb(dentry->d_sb);
@@ -760,17 +992,21 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct list_head *head = &root->fs_info->space_info;
 	struct btrfs_space_info *found;
 	u64 total_used = 0;
-	u64 total_used_data = 0;
+	u64 total_free_data = 0;
 	int bits = dentry->d_sb->s_blocksize_bits;
 	__be32 *fsid = (__be32 *)root->fs_info->fsid;
+	int ret;
 
+	/* holding chunk_muext to avoid allocating new chunks */
+	mutex_lock(&root->fs_info->chunk_mutex);
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
-		if (found->flags & (BTRFS_BLOCK_GROUP_METADATA |
-				    BTRFS_BLOCK_GROUP_SYSTEM))
-			total_used_data += found->disk_total;
-		else
-			total_used_data += found->disk_used;
+		if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
+			total_free_data += found->disk_total - found->disk_used;
+			total_free_data -=
+				btrfs_account_ro_block_groups_free_space(found);
+		}
+
 		total_used += found->disk_used;
 	}
 	rcu_read_unlock();
@@ -778,9 +1014,17 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = BTRFS_NAME_LEN;
 	buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits;
 	buf->f_bfree = buf->f_blocks - (total_used >> bits);
-	buf->f_bavail = buf->f_blocks - (total_used_data >> bits);
 	buf->f_bsize = dentry->d_sb->s_blocksize;
 	buf->f_type = BTRFS_SUPER_MAGIC;
+	buf->f_bavail = total_free_data;
+	ret = btrfs_calc_avail_data_space(root, &total_free_data);
+	if (ret) {
+		mutex_unlock(&root->fs_info->chunk_mutex);
+		return ret;
+	}
+	buf->f_bavail += total_free_data;
+	buf->f_bavail = buf->f_bavail >> bits;
+	mutex_unlock(&root->fs_info->chunk_mutex);
 
 	/* We treat it as constant endianness (it doesn't matter _which_)
 	   because we want the fsid to come out the same whether mounted
@@ -897,10 +1141,14 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		return err;
 
-	err = btrfs_init_cachep();
+	err = btrfs_init_compress();
 	if (err)
 		goto free_sysfs;
 
+	err = btrfs_init_cachep();
+	if (err)
+		goto free_compress;
+
 	err = extent_io_init();
 	if (err)
 		goto free_cachep;
@@ -928,6 +1176,8 @@ free_extent_io:
 	extent_io_exit();
 free_cachep:
 	btrfs_destroy_cachep();
+free_compress:
+	btrfs_exit_compress();
 free_sysfs:
 	btrfs_exit_sysfs();
 	return err;
@@ -942,7 +1192,7 @@ static void __exit exit_btrfs_fs(void)
 	unregister_filesystem(&btrfs_fs_type);
 	btrfs_exit_sysfs();
 	btrfs_cleanup_fs_uuids();
-	btrfs_zlib_exit();
+	btrfs_exit_compress();
 }
 
 module_init(init_btrfs_fs)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index f50e931fc217..3d73c8d93bbb 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -181,6 +181,9 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 	struct btrfs_trans_handle *h;
 	struct btrfs_transaction *cur_trans;
 	int ret;
+
+	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+		return ERR_PTR(-EROFS);
 again:
 	h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
 	if (!h)
@@ -910,6 +913,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	u64 to_reserve = 0;
 	u64 index = 0;
 	u64 objectid;
+	u64 root_flags;
 
 	new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
 	if (!new_root_item) {
@@ -967,6 +971,13 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
 	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
 
+	root_flags = btrfs_root_flags(new_root_item);
+	if (pending->readonly)
+		root_flags |= BTRFS_ROOT_SUBVOL_RDONLY;
+	else
+		root_flags &= ~BTRFS_ROOT_SUBVOL_RDONLY;
+	btrfs_set_root_flags(new_root_item, root_flags);
+
 	old = btrfs_lock_root_node(root);
 	btrfs_cow_block(trans, root, old, NULL, 0, &old);
 	btrfs_set_lock_blocking(old);
@@ -1150,6 +1161,11 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 	INIT_DELAYED_WORK(&ac->work, do_async_commit);
 	ac->root = root;
 	ac->newtrans = btrfs_join_transaction(root, 0);
+	if (IS_ERR(ac->newtrans)) {
+		int err = PTR_ERR(ac->newtrans);
+		kfree(ac);
+		return err;
+	}
 
 	/* take transaction reference */
 	mutex_lock(&root->fs_info->trans_mutex);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index f104b57ad4ef..229a594cacd5 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -62,6 +62,7 @@ struct btrfs_pending_snapshot {
 	struct btrfs_block_rsv block_rsv;
 	/* extra metadata reseration for relocation */
 	int error;
+	bool readonly;
 	struct list_head list;
 };
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 054744ac5719..a4bbb854dfd2 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -338,6 +338,12 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 		}
 		dst_copy = kmalloc(item_size, GFP_NOFS);
 		src_copy = kmalloc(item_size, GFP_NOFS);
+		if (!dst_copy || !src_copy) {
+			btrfs_release_path(root, path);
+			kfree(dst_copy);
+			kfree(src_copy);
+			return -ENOMEM;
+		}
 
 		read_extent_buffer(eb, src_copy, src_ptr, item_size);
 
@@ -665,6 +671,9 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 	btrfs_dir_item_key_to_cpu(leaf, di, &location);
 	name_len = btrfs_dir_name_len(leaf, di);
 	name = kmalloc(name_len, GFP_NOFS);
+	if (!name)
+		return -ENOMEM;
+
 	read_extent_buffer(leaf, name, (unsigned long)(di + 1), name_len);
 	btrfs_release_path(root, path);
 
@@ -744,6 +753,9 @@ static noinline int backref_in_log(struct btrfs_root *log,
 	int match = 0;
 
 	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
 	ret = btrfs_search_slot(NULL, log, key, path, 0, 0);
 	if (ret != 0)
 		goto out;
@@ -967,6 +979,8 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 	key.offset = (u64)-1;
 
 	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
 
 	while (1) {
 		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
@@ -1178,6 +1192,9 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 
 	name_len = btrfs_dir_name_len(eb, di);
 	name = kmalloc(name_len, GFP_NOFS);
+	if (!name)
+		return -ENOMEM;
+
 	log_type = btrfs_dir_type(eb, di);
 	read_extent_buffer(eb, name, (unsigned long)(di + 1),
 		   name_len);
@@ -1692,6 +1709,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 		root_owner = btrfs_header_owner(parent);
 
 		next = btrfs_find_create_tree_block(root, bytenr, blocksize);
+		if (!next)
+			return -ENOMEM;
 
 		if (*level == 1) {
 			wc->process_func(root, next, wc, ptr_gen);
@@ -2032,6 +2051,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		wait_log_commit(trans, log_root_tree,
 				log_root_tree->log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
+		ret = 0;
 		goto out;
 	}
 	atomic_set(&log_root_tree->log_commit[index2], 1);
@@ -2096,7 +2116,7 @@ out:
 	smp_mb();
 	if (waitqueue_active(&root->log_commit_wait[index1]))
 		wake_up(&root->log_commit_wait[index1]);
-	return 0;
+	return ret;
 }
 
 static void free_log_tree(struct btrfs_trans_handle *trans,
@@ -2194,6 +2214,9 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 
 	log = root->log_root;
 	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
 	di = btrfs_lookup_dir_item(trans, log, path, dir->i_ino,
 				   name, name_len, -1);
 	if (IS_ERR(di)) {
@@ -2594,6 +2617,9 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 
 	ins_data = kmalloc(nr * sizeof(struct btrfs_key) +
 			   nr * sizeof(u32), GFP_NOFS);
+	if (!ins_data)
+		return -ENOMEM;
+
 	ins_sizes = (u32 *)ins_data;
 	ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32));
 
@@ -2725,7 +2751,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	log = root->log_root;
 
 	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
 	dst_path = btrfs_alloc_path();
+	if (!dst_path) {
+		btrfs_free_path(path);
+		return -ENOMEM;
+	}
 
 	min_key.objectid = inode->i_ino;
 	min_key.type = BTRFS_INODE_ITEM_KEY;
@@ -3080,6 +3112,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
 	BUG_ON(!path);
 
 	trans = btrfs_start_transaction(fs_info->tree_root, 0);
+	BUG_ON(IS_ERR(trans));
 
 	wc.trans = trans;
 	wc.pin = 1;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1718e1a5c320..2636a051e4b2 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -22,6 +22,7 @@
 #include <linux/blkdev.h>
 #include <linux/random.h>
 #include <linux/iocontext.h>
+#include <linux/capability.h>
 #include <asm/div64.h>
 #include "compat.h"
 #include "ctree.h"
@@ -600,8 +601,10 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		set_blocksize(bdev, 4096);
 
 		bh = btrfs_read_dev_super(bdev);
-		if (!bh)
+		if (!bh) {
+			ret = -EINVAL;
 			goto error_close;
+		}
 
 		disk_super = (struct btrfs_super_block *)bh->b_data;
 		devid = btrfs_stack_device_id(&disk_super->dev_item);
@@ -703,7 +706,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 		goto error_close;
 	bh = btrfs_read_dev_super(bdev);
 	if (!bh) {
-		ret = -EIO;
+		ret = -EINVAL;
 		goto error_close;
 	}
 	disk_super = (struct btrfs_super_block *)bh->b_data;
@@ -729,59 +732,167 @@ error:
 	return ret;
 }
 
+/* helper to account the used device space in the range */
+int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
+				   u64 end, u64 *length)
+{
+	struct btrfs_key key;
+	struct btrfs_root *root = device->dev_root;
+	struct btrfs_dev_extent *dev_extent;
+	struct btrfs_path *path;
+	u64 extent_end;
+	int ret;
+	int slot;
+	struct extent_buffer *l;
+
+	*length = 0;
+
+	if (start >= device->total_bytes)
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+	path->reada = 2;
+
+	key.objectid = device->devid;
+	key.offset = start;
+	key.type = BTRFS_DEV_EXTENT_KEY;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	if (ret > 0) {
+		ret = btrfs_previous_item(root, path, key.objectid, key.type);
+		if (ret < 0)
+			goto out;
+	}
+
+	while (1) {
+		l = path->nodes[0];
+		slot = path->slots[0];
+		if (slot >= btrfs_header_nritems(l)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret == 0)
+				continue;
+			if (ret < 0)
+				goto out;
+
+			break;
+		}
+		btrfs_item_key_to_cpu(l, &key, slot);
+
+		if (key.objectid < device->devid)
+			goto next;
+
+		if (key.objectid > device->devid)
+			break;
+
+		if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY)
+			goto next;
+
+		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
+		extent_end = key.offset + btrfs_dev_extent_length(l,
+								  dev_extent);
+		if (key.offset <= start && extent_end > end) {
+			*length = end - start + 1;
+			break;
+		} else if (key.offset <= start && extent_end > start)
+			*length += extent_end - start;
+		else if (key.offset > start && extent_end <= end)
+			*length += extent_end - key.offset;
+		else if (key.offset > start && key.offset <= end) {
+			*length += end - key.offset + 1;
+			break;
+		} else if (key.offset > end)
+			break;
+
+next:
+		path->slots[0]++;
+	}
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 /*
+ * find_free_dev_extent - find free space in the specified device
+ * @trans:	transaction handler
+ * @device:	the device which we search the free space in
+ * @num_bytes:	the size of the free space that we need
+ * @start:	store the start of the free space.
+ * @len:	the size of the free space. that we find, or the size of the max
+ * 		free space if we don't find suitable free space
+ *
  * this uses a pretty simple search, the expectation is that it is
  * called very infrequently and that a given device has a small number
  * of extents
+ *
+ * @start is used to store the start of the free space if we find. But if we
+ * don't find suitable free space, it will be used to store the start position
+ * of the max free space.
+ *
+ * @len is used to store the size of the free space that we find.
+ * But if we don't find suitable free space, it is used to store the size of
+ * the max free space.
  */
 int find_free_dev_extent(struct btrfs_trans_handle *trans,
 			 struct btrfs_device *device, u64 num_bytes,
-			 u64 *start, u64 *max_avail)
+			 u64 *start, u64 *len)
 {
 	struct btrfs_key key;
 	struct btrfs_root *root = device->dev_root;
-	struct btrfs_dev_extent *dev_extent = NULL;
+	struct btrfs_dev_extent *dev_extent;
 	struct btrfs_path *path;
-	u64 hole_size = 0;
-	u64 last_byte = 0;
-	u64 search_start = 0;
+	u64 hole_size;
+	u64 max_hole_start;
+	u64 max_hole_size;
+	u64 extent_end;
+	u64 search_start;
 	u64 search_end = device->total_bytes;
 	int ret;
-	int slot = 0;
-	int start_found;
+	int slot;
 	struct extent_buffer *l;
 
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-	path->reada = 2;
-	start_found = 0;
-
 	/* FIXME use last free of some kind */
 
 	/* we don't want to overwrite the superblock on the drive,
 	 * so we make sure to start at an offset of at least 1MB
 	 */
-	search_start = max((u64)1024 * 1024, search_start);
+	search_start = 1024 * 1024;
 
-	if (root->fs_info->alloc_start + num_bytes <= device->total_bytes)
+	if (root->fs_info->alloc_start + num_bytes <= search_end)
 		search_start = max(root->fs_info->alloc_start, search_start);
 
+	max_hole_start = search_start;
+	max_hole_size = 0;
+
+	if (search_start >= search_end) {
+		ret = -ENOSPC;
+		goto error;
+	}
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto error;
+	}
+	path->reada = 2;
+
 	key.objectid = device->devid;
 	key.offset = search_start;
 	key.type = BTRFS_DEV_EXTENT_KEY;
+
 	ret = btrfs_search_slot(trans, root, &key, path, 0, 0);
 	if (ret < 0)
-		goto error;
+		goto out;
 	if (ret > 0) {
 		ret = btrfs_previous_item(root, path, key.objectid, key.type);
 		if (ret < 0)
-			goto error;
-		if (ret > 0)
-			start_found = 1;
+			goto out;
 	}
-	l = path->nodes[0];
-	btrfs_item_key_to_cpu(l, &key, path->slots[0]);
+
 	while (1) {
 		l = path->nodes[0];
 		slot = path->slots[0];
@@ -790,24 +901,9 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
 			if (ret == 0)
 				continue;
 			if (ret < 0)
-				goto error;
-no_more_items:
-			if (!start_found) {
-				if (search_start >= search_end) {
-					ret = -ENOSPC;
-					goto error;
-				}
-				*start = search_start;
-				start_found = 1;
-				goto check_pending;
-			}
-			*start = last_byte > search_start ?
-				last_byte : search_start;
-			if (search_end <= *start) {
-				ret = -ENOSPC;
-				goto error;
-			}
-			goto check_pending;
+				goto out;
+
+			break;
 		}
 		btrfs_item_key_to_cpu(l, &key, slot);
 
@@ -815,48 +911,62 @@ no_more_items:
 			goto next;
 
 		if (key.objectid > device->devid)
-			goto no_more_items;
+			break;
 
-		if (key.offset >= search_start && key.offset > last_byte &&
-		    start_found) {
-			if (last_byte < search_start)
-				last_byte = search_start;
-			hole_size = key.offset - last_byte;
+		if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY)
+			goto next;
 
-			if (hole_size > *max_avail)
-				*max_avail = hole_size;
+		if (key.offset > search_start) {
+			hole_size = key.offset - search_start;
 
-			if (key.offset > last_byte &&
-			    hole_size >= num_bytes) {
-				*start = last_byte;
-				goto check_pending;
+			if (hole_size > max_hole_size) {
+				max_hole_start = search_start;
+				max_hole_size = hole_size;
+			}
+
+			/*
+			 * If this free space is greater than which we need,
+			 * it must be the max free space that we have found
+			 * until now, so max_hole_start must point to the start
+			 * of this free space and the length of this free space
+			 * is stored in max_hole_size. Thus, we return
+			 * max_hole_start and max_hole_size and go back to the
+			 * caller.
+			 */
+			if (hole_size >= num_bytes) {
+				ret = 0;
+				goto out;
 			}
 		}
-		if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY)
-			goto next;
 
-		start_found = 1;
 		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
-		last_byte = key.offset + btrfs_dev_extent_length(l, dev_extent);
+		extent_end = key.offset + btrfs_dev_extent_length(l,
+								  dev_extent);
+		if (extent_end > search_start)
+			search_start = extent_end;
 next:
 		path->slots[0]++;
 		cond_resched();
 	}
-check_pending:
-	/* we have to make sure we didn't find an extent that has already
-	 * been allocated by the map tree or the original allocation
-	 */
-	BUG_ON(*start < search_start);
 
-	if (*start + num_bytes > search_end) {
-		ret = -ENOSPC;
-		goto error;
+	hole_size = search_end- search_start;
+	if (hole_size > max_hole_size) {
+		max_hole_start = search_start;
+		max_hole_size = hole_size;
 	}
-	/* check for pending inserts here */
-	ret = 0;
 
-error:
+	/* See above. */
+	if (hole_size < num_bytes)
+		ret = -ENOSPC;
+	else
+		ret = 0;
+
+out:
 	btrfs_free_path(path);
+error:
+	*start = max_hole_start;
+	if (len)
+		*len = max_hole_size;
 	return ret;
 }
 
@@ -1103,6 +1213,10 @@ static int btrfs_rm_dev_item(struct btrfs_root *root,
 		return -ENOMEM;
 
 	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans)) {
+		btrfs_free_path(path);
+		return PTR_ERR(trans);
+	}
 	key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
 	key.type = BTRFS_DEV_ITEM_KEY;
 	key.offset = device->devid;
@@ -1196,7 +1310,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		set_blocksize(bdev, 4096);
 		bh = btrfs_read_dev_super(bdev);
 		if (!bh) {
-			ret = -EIO;
+			ret = -EINVAL;
 			goto error_close;
 		}
 		disk_super = (struct btrfs_super_block *)bh->b_data;
@@ -1496,6 +1610,12 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	}
 
 	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans)) {
+		kfree(device);
+		ret = PTR_ERR(trans);
+		goto error;
+	}
+
 	lock_chunks(root);
 
 	device->writeable = 1;
@@ -1763,7 +1883,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
 		return ret;
 
 	trans = btrfs_start_transaction(root, 0);
-	BUG_ON(!trans);
+	BUG_ON(IS_ERR(trans));
 
 	lock_chunks(root);
 
@@ -1916,6 +2036,9 @@ int btrfs_balance(struct btrfs_root *dev_root)
 	if (dev_root->fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	mutex_lock(&dev_root->fs_info->volume_mutex);
 	dev_root = dev_root->fs_info->dev_root;
 
@@ -1934,7 +2057,7 @@ int btrfs_balance(struct btrfs_root *dev_root)
 		BUG_ON(ret);
 
 		trans = btrfs_start_transaction(dev_root, 0);
-		BUG_ON(!trans);
+		BUG_ON(IS_ERR(trans));
 
 		ret = btrfs_grow_device(trans, device, old_size);
 		BUG_ON(ret);
@@ -2100,6 +2223,11 @@ again:
 
 	/* Shrinking succeeded, else we would be at "done". */
 	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto done;
+	}
+
 	lock_chunks(root);
 
 	device->disk_total_bytes = new_size;
@@ -2154,66 +2282,67 @@ static noinline u64 chunk_bytes_by_type(u64 type, u64 calc_size,
 		return calc_size * num_stripes;
 }
 
-static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *extent_root,
-			       struct map_lookup **map_ret,
-			       u64 *num_bytes, u64 *stripe_size,
-			       u64 start, u64 type)
+/* Used to sort the devices by max_avail(descending sort) */
+int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2)
 {
-	struct btrfs_fs_info *info = extent_root->fs_info;
-	struct btrfs_device *device = NULL;
-	struct btrfs_fs_devices *fs_devices = info->fs_devices;
-	struct list_head *cur;
-	struct map_lookup *map = NULL;
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
-	struct list_head private_devs;
-	int min_stripe_size = 1 * 1024 * 1024;
-	u64 calc_size = 1024 * 1024 * 1024;
-	u64 max_chunk_size = calc_size;
-	u64 min_free;
-	u64 avail;
-	u64 max_avail = 0;
-	u64 dev_offset;
-	int num_stripes = 1;
-	int min_stripes = 1;
-	int sub_stripes = 0;
-	int looped = 0;
-	int ret;
-	int index;
-	int stripe_len = 64 * 1024;
+	if (((struct btrfs_device_info *)dev_info1)->max_avail >
+	    ((struct btrfs_device_info *)dev_info2)->max_avail)
+		return -1;
+	else if (((struct btrfs_device_info *)dev_info1)->max_avail <
+		 ((struct btrfs_device_info *)dev_info2)->max_avail)
+		return 1;
+	else
+		return 0;
+}
 
-	if ((type & BTRFS_BLOCK_GROUP_RAID1) &&
-	    (type & BTRFS_BLOCK_GROUP_DUP)) {
-		WARN_ON(1);
-		type &= ~BTRFS_BLOCK_GROUP_DUP;
-	}
-	if (list_empty(&fs_devices->alloc_list))
-		return -ENOSPC;
+static int __btrfs_calc_nstripes(struct btrfs_fs_devices *fs_devices, u64 type,
+				 int *num_stripes, int *min_stripes,
+				 int *sub_stripes)
+{
+	*num_stripes = 1;
+	*min_stripes = 1;
+	*sub_stripes = 0;
 
 	if (type & (BTRFS_BLOCK_GROUP_RAID0)) {
-		num_stripes = fs_devices->rw_devices;
-		min_stripes = 2;
+		*num_stripes = fs_devices->rw_devices;
+		*min_stripes = 2;
 	}
 	if (type & (BTRFS_BLOCK_GROUP_DUP)) {
-		num_stripes = 2;
-		min_stripes = 2;
+		*num_stripes = 2;
+		*min_stripes = 2;
 	}
 	if (type & (BTRFS_BLOCK_GROUP_RAID1)) {
 		if (fs_devices->rw_devices < 2)
 			return -ENOSPC;
-		num_stripes = 2;
-		min_stripes = 2;
+		*num_stripes = 2;
+		*min_stripes = 2;
 	}
 	if (type & (BTRFS_BLOCK_GROUP_RAID10)) {
-		num_stripes = fs_devices->rw_devices;
-		if (num_stripes < 4)
+		*num_stripes = fs_devices->rw_devices;
+		if (*num_stripes < 4)
 			return -ENOSPC;
-		num_stripes &= ~(u32)1;
-		sub_stripes = 2;
-		min_stripes = 4;
+		*num_stripes &= ~(u32)1;
+		*sub_stripes = 2;
+		*min_stripes = 4;
 	}
 
+	return 0;
+}
+
+static u64 __btrfs_calc_stripe_size(struct btrfs_fs_devices *fs_devices,
+				    u64 proposed_size, u64 type,
+				    int num_stripes, int small_stripe)
+{
+	int min_stripe_size = 1 * 1024 * 1024;
+	u64 calc_size = proposed_size;
+	u64 max_chunk_size = calc_size;
+	int ncopies = 1;
+
+	if (type & (BTRFS_BLOCK_GROUP_RAID1 |
+		    BTRFS_BLOCK_GROUP_DUP |
+		    BTRFS_BLOCK_GROUP_RAID10))
+		ncopies = 2;
+
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
 		max_chunk_size = 10 * calc_size;
 		min_stripe_size = 64 * 1024 * 1024;
@@ -2230,51 +2359,209 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	max_chunk_size = min(div_factor(fs_devices->total_rw_bytes, 1),
 			     max_chunk_size);
 
-again:
-	max_avail = 0;
-	if (!map || map->num_stripes != num_stripes) {
-		kfree(map);
-		map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
-		if (!map)
-			return -ENOMEM;
-		map->num_stripes = num_stripes;
-	}
-
-	if (calc_size * num_stripes > max_chunk_size) {
-		calc_size = max_chunk_size;
+	if (calc_size * num_stripes > max_chunk_size * ncopies) {
+		calc_size = max_chunk_size * ncopies;
 		do_div(calc_size, num_stripes);
-		do_div(calc_size, stripe_len);
-		calc_size *= stripe_len;
+		do_div(calc_size, BTRFS_STRIPE_LEN);
+		calc_size *= BTRFS_STRIPE_LEN;
 	}
 
 	/* we don't want tiny stripes */
-	if (!looped)
+	if (!small_stripe)
 		calc_size = max_t(u64, min_stripe_size, calc_size);
 
 	/*
-	 * we're about to do_div by the stripe_len so lets make sure
+	 * we're about to do_div by the BTRFS_STRIPE_LEN so lets make sure
 	 * we end up with something bigger than a stripe
 	 */
-	calc_size = max_t(u64, calc_size, stripe_len * 4);
+	calc_size = max_t(u64, calc_size, BTRFS_STRIPE_LEN);
+
+	do_div(calc_size, BTRFS_STRIPE_LEN);
+	calc_size *= BTRFS_STRIPE_LEN;
+
+	return calc_size;
+}
+
+static struct map_lookup *__shrink_map_lookup_stripes(struct map_lookup *map,
+						      int num_stripes)
+{
+	struct map_lookup *new;
+	size_t len = map_lookup_size(num_stripes);
+
+	BUG_ON(map->num_stripes < num_stripes);
+
+	if (map->num_stripes == num_stripes)
+		return map;
+
+	new = kmalloc(len, GFP_NOFS);
+	if (!new) {
+		/* just change map->num_stripes */
+		map->num_stripes = num_stripes;
+		return map;
+	}
+
+	memcpy(new, map, len);
+	new->num_stripes = num_stripes;
+	kfree(map);
+	return new;
+}
+
+/*
+ * helper to allocate device space from btrfs_device_info, in which we stored
+ * max free space information of every device. It is used when we can not
+ * allocate chunks by default size.
+ *
+ * By this helper, we can allocate a new chunk as larger as possible.
+ */
+static int __btrfs_alloc_tiny_space(struct btrfs_trans_handle *trans,
+				    struct btrfs_fs_devices *fs_devices,
+				    struct btrfs_device_info *devices,
+				    int nr_device, u64 type,
+				    struct map_lookup **map_lookup,
+				    int min_stripes, u64 *stripe_size)
+{
+	int i, index, sort_again = 0;
+	int min_devices = min_stripes;
+	u64 max_avail, min_free;
+	struct map_lookup *map = *map_lookup;
+	int ret;
+
+	if (nr_device < min_stripes)
+		return -ENOSPC;
+
+	btrfs_descending_sort_devices(devices, nr_device);
+
+	max_avail = devices[0].max_avail;
+	if (!max_avail)
+		return -ENOSPC;
+
+	for (i = 0; i < nr_device; i++) {
+		/*
+		 * if dev_offset = 0, it means the free space of this device
+		 * is less than what we need, and we didn't search max avail
+		 * extent on this device, so do it now.
+		 */
+		if (!devices[i].dev_offset) {
+			ret = find_free_dev_extent(trans, devices[i].dev,
+						   max_avail,
+						   &devices[i].dev_offset,
+						   &devices[i].max_avail);
+			if (ret != 0 && ret != -ENOSPC)
+				return ret;
+			sort_again = 1;
+		}
+	}
+
+	/* we update the max avail free extent of each devices, sort again */
+	if (sort_again)
+		btrfs_descending_sort_devices(devices, nr_device);
+
+	if (type & BTRFS_BLOCK_GROUP_DUP)
+		min_devices = 1;
+
+	if (!devices[min_devices - 1].max_avail)
+		return -ENOSPC;
+
+	max_avail = devices[min_devices - 1].max_avail;
+	if (type & BTRFS_BLOCK_GROUP_DUP)
+		do_div(max_avail, 2);
+
+	max_avail = __btrfs_calc_stripe_size(fs_devices, max_avail, type,
+					     min_stripes, 1);
+	if (type & BTRFS_BLOCK_GROUP_DUP)
+		min_free = max_avail * 2;
+	else
+		min_free = max_avail;
+
+	if (min_free > devices[min_devices - 1].max_avail)
+		return -ENOSPC;
+
+	map = __shrink_map_lookup_stripes(map, min_stripes);
+	*stripe_size = max_avail;
+
+	index = 0;
+	for (i = 0; i < min_stripes; i++) {
+		map->stripes[i].dev = devices[index].dev;
+		map->stripes[i].physical = devices[index].dev_offset;
+		if (type & BTRFS_BLOCK_GROUP_DUP) {
+			i++;
+			map->stripes[i].dev = devices[index].dev;
+			map->stripes[i].physical = devices[index].dev_offset +
+						   max_avail;
+		}
+		index++;
+	}
+	*map_lookup = map;
 
-	do_div(calc_size, stripe_len);
-	calc_size *= stripe_len;
+	return 0;
+}
+
+static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *extent_root,
+			       struct map_lookup **map_ret,
+			       u64 *num_bytes, u64 *stripe_size,
+			       u64 start, u64 type)
+{
+	struct btrfs_fs_info *info = extent_root->fs_info;
+	struct btrfs_device *device = NULL;
+	struct btrfs_fs_devices *fs_devices = info->fs_devices;
+	struct list_head *cur;
+	struct map_lookup *map;
+	struct extent_map_tree *em_tree;
+	struct extent_map *em;
+	struct btrfs_device_info *devices_info;
+	struct list_head private_devs;
+	u64 calc_size = 1024 * 1024 * 1024;
+	u64 min_free;
+	u64 avail;
+	u64 dev_offset;
+	int num_stripes;
+	int min_stripes;
+	int sub_stripes;
+	int min_devices;	/* the min number of devices we need */
+	int i;
+	int ret;
+	int index;
+
+	if ((type & BTRFS_BLOCK_GROUP_RAID1) &&
+	    (type & BTRFS_BLOCK_GROUP_DUP)) {
+		WARN_ON(1);
+		type &= ~BTRFS_BLOCK_GROUP_DUP;
+	}
+	if (list_empty(&fs_devices->alloc_list))
+		return -ENOSPC;
+
+	ret = __btrfs_calc_nstripes(fs_devices, type, &num_stripes,
+				    &min_stripes, &sub_stripes);
+	if (ret)
+		return ret;
+
+	devices_info = kzalloc(sizeof(*devices_info) * fs_devices->rw_devices,
+			       GFP_NOFS);
+	if (!devices_info)
+		return -ENOMEM;
+
+	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
+	if (!map) {
+		ret = -ENOMEM;
+		goto error;
+	}
+	map->num_stripes = num_stripes;
 
 	cur = fs_devices->alloc_list.next;
 	index = 0;
+	i = 0;
 
-	if (type & BTRFS_BLOCK_GROUP_DUP)
+	calc_size = __btrfs_calc_stripe_size(fs_devices, calc_size, type,
+					     num_stripes, 0);
+
+	if (type & BTRFS_BLOCK_GROUP_DUP) {
 		min_free = calc_size * 2;
-	else
+		min_devices = 1;
+	} else {
 		min_free = calc_size;
-
-	/*
-	 * we add 1MB because we never use the first 1MB of the device, unless
-	 * we've looped, then we are likely allocating the maximum amount of
-	 * space left already
-	 */
-	if (!looped)
-		min_free += 1024 * 1024;
+		min_devices = min_stripes;
+	}
 
 	INIT_LIST_HEAD(&private_devs);
 	while (index < num_stripes) {
@@ -2287,27 +2574,39 @@ again:
 		cur = cur->next;
 
 		if (device->in_fs_metadata && avail >= min_free) {
-			ret = find_free_dev_extent(trans, device,
-						   min_free, &dev_offset,
-						   &max_avail);
+			ret = find_free_dev_extent(trans, device, min_free,
+						   &devices_info[i].dev_offset,
+						   &devices_info[i].max_avail);
 			if (ret == 0) {
 				list_move_tail(&device->dev_alloc_list,
 					       &private_devs);
 				map->stripes[index].dev = device;
-				map->stripes[index].physical = dev_offset;
+				map->stripes[index].physical =
+						devices_info[i].dev_offset;
 				index++;
 				if (type & BTRFS_BLOCK_GROUP_DUP) {
 					map->stripes[index].dev = device;
 					map->stripes[index].physical =
-						dev_offset + calc_size;
+						devices_info[i].dev_offset +
+						calc_size;
 					index++;
 				}
-			}
-		} else if (device->in_fs_metadata && avail > max_avail)
-			max_avail = avail;
+			} else if (ret != -ENOSPC)
+				goto error;
+
+			devices_info[i].dev = device;
+			i++;
+		} else if (device->in_fs_metadata &&
+			   avail >= BTRFS_STRIPE_LEN) {
+			devices_info[i].dev = device;
+			devices_info[i].max_avail = avail;
+			i++;
+		}
+
 		if (cur == &fs_devices->alloc_list)
 			break;
 	}
+
 	list_splice(&private_devs, &fs_devices->alloc_list);
 	if (index < num_stripes) {
 		if (index >= min_stripes) {
@@ -2316,34 +2615,36 @@ again:
 				num_stripes /= sub_stripes;
 				num_stripes *= sub_stripes;
 			}
-			looped = 1;
-			goto again;
-		}
-		if (!looped && max_avail > 0) {
-			looped = 1;
-			calc_size = max_avail;
-			goto again;
+
+			map = __shrink_map_lookup_stripes(map, num_stripes);
+		} else if (i >= min_devices) {
+			ret = __btrfs_alloc_tiny_space(trans, fs_devices,
+						       devices_info, i, type,
+						       &map, min_stripes,
+						       &calc_size);
+			if (ret)
+				goto error;
+		} else {
+			ret = -ENOSPC;
+			goto error;
 		}
-		kfree(map);
-		return -ENOSPC;
 	}
 	map->sector_size = extent_root->sectorsize;
-	map->stripe_len = stripe_len;
-	map->io_align = stripe_len;
-	map->io_width = stripe_len;
+	map->stripe_len = BTRFS_STRIPE_LEN;
+	map->io_align = BTRFS_STRIPE_LEN;
+	map->io_width = BTRFS_STRIPE_LEN;
 	map->type = type;
-	map->num_stripes = num_stripes;
 	map->sub_stripes = sub_stripes;
 
 	*map_ret = map;
 	*stripe_size = calc_size;
 	*num_bytes = chunk_bytes_by_type(type, calc_size,
-					 num_stripes, sub_stripes);
+					 map->num_stripes, sub_stripes);
 
 	em = alloc_extent_map(GFP_NOFS);
 	if (!em) {
-		kfree(map);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto error;
 	}
 	em->bdev = (struct block_device *)map;
 	em->start = start;
@@ -2376,7 +2677,13 @@ again:
 		index++;
 	}
 
+	kfree(devices_info);
 	return 0;
+
+error:
+	kfree(map);
+	kfree(devices_info);
+	return ret;
 }
 
 static int __finish_chunk_alloc(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1be781079450..7fb59d45fe8c 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -20,8 +20,11 @@
 #define __BTRFS_VOLUMES_
 
 #include <linux/bio.h>
+#include <linux/sort.h>
 #include "async-thread.h"
 
+#define BTRFS_STRIPE_LEN	(64 * 1024)
+
 struct buffer_head;
 struct btrfs_pending_bios {
 	struct bio *head;
@@ -136,6 +139,30 @@ struct btrfs_multi_bio {
 	struct btrfs_bio_stripe stripes[];
 };
 
+struct btrfs_device_info {
+	struct btrfs_device *dev;
+	u64 dev_offset;
+	u64 max_avail;
+};
+
+/* Used to sort the devices by max_avail(descending sort) */
+int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2);
+
+/*
+ * sort the devices by max_avail, in which max free extent size of each device
+ * is stored.(Descending Sort)
+ */
+static inline void btrfs_descending_sort_devices(
+					struct btrfs_device_info *devices,
+					size_t nr_devices)
+{
+	sort(devices, nr_devices, sizeof(struct btrfs_device_info),
+	     btrfs_cmp_device_free_bytes, NULL);
+}
+
+int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
+				   u64 end, u64 *length);
+
 #define btrfs_multi_bio_size(n) (sizeof(struct btrfs_multi_bio) + \
 			    (sizeof(struct btrfs_bio_stripe) * (n)))
 
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 698fdd2c739c..a5776531dc2b 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -316,6 +316,15 @@ ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
 int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 		   size_t size, int flags)
 {
+	struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root;
+
+	/*
+	 * The permission on security.* and system.* is not checked
+	 * in permission().
+	 */
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	/*
 	 * If this is a request for a synthetic attribute in the system.*
 	 * namespace use the generic infrastructure to resolve a handler
@@ -336,6 +345,15 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 
 int btrfs_removexattr(struct dentry *dentry, const char *name)
 {
+	struct btrfs_root *root = BTRFS_I(dentry->d_inode)->root;
+
+	/*
+	 * The permission on security.* and system.* is not checked
+	 * in permission().
+	 */
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	/*
 	 * If this is a request for a synthetic attribute in the system.*
 	 * namespace use the generic infrastructure to resolve a handler
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index b9cd5445f71c..f5ec2d44150d 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -32,15 +32,6 @@
 #include <linux/bio.h>
 #include "compression.h"
 
-/* Plan: call deflate() with avail_in == *sourcelen,
-	avail_out = *dstlen - 12 and flush == Z_FINISH.
-	If it doesn't manage to finish,	call it again with
-	avail_in == 0 and avail_out set to the remaining 12
-	bytes for it to clean up.
-   Q: Is 12 bytes sufficient?
-*/
-#define STREAM_END_SPACE 12
-
 struct workspace {
 	z_stream inf_strm;
 	z_stream def_strm;
@@ -48,152 +39,51 @@ struct workspace {
 	struct list_head list;
 };
 
-static LIST_HEAD(idle_workspace);
-static DEFINE_SPINLOCK(workspace_lock);
-static unsigned long num_workspace;
-static atomic_t alloc_workspace = ATOMIC_INIT(0);
-static DECLARE_WAIT_QUEUE_HEAD(workspace_wait);
+static void zlib_free_workspace(struct list_head *ws)
+{
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
-/*
- * this finds an available zlib workspace or allocates a new one
- * NULL or an ERR_PTR is returned if things go bad.
- */
-static struct workspace *find_zlib_workspace(void)
+	vfree(workspace->def_strm.workspace);
+	vfree(workspace->inf_strm.workspace);
+	kfree(workspace->buf);
+	kfree(workspace);
+}
+
+static struct list_head *zlib_alloc_workspace(void)
 {
 	struct workspace *workspace;
-	int ret;
-	int cpus = num_online_cpus();
-
-again:
-	spin_lock(&workspace_lock);
-	if (!list_empty(&idle_workspace)) {
-		workspace = list_entry(idle_workspace.next, struct workspace,
-				       list);
-		list_del(&workspace->list);
-		num_workspace--;
-		spin_unlock(&workspace_lock);
-		return workspace;
 
-	}
-	spin_unlock(&workspace_lock);
-	if (atomic_read(&alloc_workspace) > cpus) {
-		DEFINE_WAIT(wait);
-		prepare_to_wait(&workspace_wait, &wait, TASK_UNINTERRUPTIBLE);
-		if (atomic_read(&alloc_workspace) > cpus)
-			schedule();
-		finish_wait(&workspace_wait, &wait);
-		goto again;
-	}
-	atomic_inc(&alloc_workspace);
 	workspace = kzalloc(sizeof(*workspace), GFP_NOFS);
-	if (!workspace) {
-		ret = -ENOMEM;
-		goto fail;
-	}
+	if (!workspace)
+		return ERR_PTR(-ENOMEM);
 
 	workspace->def_strm.workspace = vmalloc(zlib_deflate_workspacesize());
-	if (!workspace->def_strm.workspace) {
-		ret = -ENOMEM;
-		goto fail;
-	}
 	workspace->inf_strm.workspace = vmalloc(zlib_inflate_workspacesize());
-	if (!workspace->inf_strm.workspace) {
-		ret = -ENOMEM;
-		goto fail_inflate;
-	}
 	workspace->buf = kmalloc(PAGE_CACHE_SIZE, GFP_NOFS);
-	if (!workspace->buf) {
-		ret = -ENOMEM;
-		goto fail_kmalloc;
-	}
-	return workspace;
-
-fail_kmalloc:
-	vfree(workspace->inf_strm.workspace);
-fail_inflate:
-	vfree(workspace->def_strm.workspace);
-fail:
-	kfree(workspace);
-	atomic_dec(&alloc_workspace);
-	wake_up(&workspace_wait);
-	return ERR_PTR(ret);
-}
-
-/*
- * put a workspace struct back on the list or free it if we have enough
- * idle ones sitting around
- */
-static int free_workspace(struct workspace *workspace)
-{
-	spin_lock(&workspace_lock);
-	if (num_workspace < num_online_cpus()) {
-		list_add_tail(&workspace->list, &idle_workspace);
-		num_workspace++;
-		spin_unlock(&workspace_lock);
-		if (waitqueue_active(&workspace_wait))
-			wake_up(&workspace_wait);
-		return 0;
-	}
-	spin_unlock(&workspace_lock);
-	vfree(workspace->def_strm.workspace);
-	vfree(workspace->inf_strm.workspace);
-	kfree(workspace->buf);
-	kfree(workspace);
+	if (!workspace->def_strm.workspace ||
+	    !workspace->inf_strm.workspace || !workspace->buf)
+		goto fail;
 
-	atomic_dec(&alloc_workspace);
-	if (waitqueue_active(&workspace_wait))
-		wake_up(&workspace_wait);
-	return 0;
-}
+	INIT_LIST_HEAD(&workspace->list);
 
-/*
- * cleanup function for module exit
- */
-static void free_workspaces(void)
-{
-	struct workspace *workspace;
-	while (!list_empty(&idle_workspace)) {
-		workspace = list_entry(idle_workspace.next, struct workspace,
-				       list);
-		list_del(&workspace->list);
-		vfree(workspace->def_strm.workspace);
-		vfree(workspace->inf_strm.workspace);
-		kfree(workspace->buf);
-		kfree(workspace);
-		atomic_dec(&alloc_workspace);
-	}
+	return &workspace->list;
+fail:
+	zlib_free_workspace(&workspace->list);
+	return ERR_PTR(-ENOMEM);
 }
 
-/*
- * given an address space and start/len, compress the bytes.
- *
- * pages are allocated to hold the compressed result and stored
- * in 'pages'
- *
- * out_pages is used to return the number of pages allocated.  There
- * may be pages allocated even if we return an error
- *
- * total_in is used to return the number of bytes actually read.  It
- * may be smaller then len if we had to exit early because we
- * ran out of room in the pages array or because we cross the
- * max_out threshold.
- *
- * total_out is used to return the total number of compressed bytes
- *
- * max_out tells us the max number of bytes that we're allowed to
- * stuff into pages
- */
-int btrfs_zlib_compress_pages(struct address_space *mapping,
-			      u64 start, unsigned long len,
-			      struct page **pages,
-			      unsigned long nr_dest_pages,
-			      unsigned long *out_pages,
-			      unsigned long *total_in,
-			      unsigned long *total_out,
-			      unsigned long max_out)
+static int zlib_compress_pages(struct list_head *ws,
+			       struct address_space *mapping,
+			       u64 start, unsigned long len,
+			       struct page **pages,
+			       unsigned long nr_dest_pages,
+			       unsigned long *out_pages,
+			       unsigned long *total_in,
+			       unsigned long *total_out,
+			       unsigned long max_out)
 {
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret;
-	struct workspace *workspace;
 	char *data_in;
 	char *cpage_out;
 	int nr_pages = 0;
@@ -205,10 +95,6 @@ int btrfs_zlib_compress_pages(struct address_space *mapping,
 	*total_out = 0;
 	*total_in = 0;
 
-	workspace = find_zlib_workspace();
-	if (IS_ERR(workspace))
-		return -1;
-
 	if (Z_OK != zlib_deflateInit(&workspace->def_strm, 3)) {
 		printk(KERN_WARNING "deflateInit failed\n");
 		ret = -1;
@@ -222,6 +108,10 @@ int btrfs_zlib_compress_pages(struct address_space *mapping,
 	data_in = kmap(in_page);
 
 	out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+	if (out_page == NULL) {
+		ret = -1;
+		goto out;
+	}
 	cpage_out = kmap(out_page);
 	pages[0] = out_page;
 	nr_pages = 1;
@@ -260,6 +150,10 @@ int btrfs_zlib_compress_pages(struct address_space *mapping,
 				goto out;
 			}
 			out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+			if (out_page == NULL) {
+				ret = -1;
+				goto out;
+			}
 			cpage_out = kmap(out_page);
 			pages[nr_pages] = out_page;
 			nr_pages++;
@@ -314,55 +208,26 @@ out:
 		kunmap(in_page);
 		page_cache_release(in_page);
 	}
-	free_workspace(workspace);
 	return ret;
 }
 
-/*
- * pages_in is an array of pages with compressed data.
- *
- * disk_start is the starting logical offset of this array in the file
- *
- * bvec is a bio_vec of pages from the file that we want to decompress into
- *
- * vcnt is the count of pages in the biovec
- *
- * srclen is the number of bytes in pages_in
- *
- * The basic idea is that we have a bio that was created by readpages.
- * The pages in the bio are for the uncompressed data, and they may not
- * be contiguous.  They all correspond to the range of bytes covered by
- * the compressed extent.
- */
-int btrfs_zlib_decompress_biovec(struct page **pages_in,
-			      u64 disk_start,
-			      struct bio_vec *bvec,
-			      int vcnt,
-			      size_t srclen)
+static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
+				  u64 disk_start,
+				  struct bio_vec *bvec,
+				  int vcnt,
+				  size_t srclen)
 {
-	int ret = 0;
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	int ret = 0, ret2;
 	int wbits = MAX_WBITS;
-	struct workspace *workspace;
 	char *data_in;
 	size_t total_out = 0;
-	unsigned long page_bytes_left;
 	unsigned long page_in_index = 0;
 	unsigned long page_out_index = 0;
-	struct page *page_out;
 	unsigned long total_pages_in = (srclen + PAGE_CACHE_SIZE - 1) /
 					PAGE_CACHE_SIZE;
 	unsigned long buf_start;
-	unsigned long buf_offset;
-	unsigned long bytes;
-	unsigned long working_bytes;
 	unsigned long pg_offset;
-	unsigned long start_byte;
-	unsigned long current_buf_start;
-	char *kaddr;
-
-	workspace = find_zlib_workspace();
-	if (IS_ERR(workspace))
-		return -ENOMEM;
 
 	data_in = kmap(pages_in[page_in_index]);
 	workspace->inf_strm.next_in = data_in;
@@ -372,8 +237,6 @@ int btrfs_zlib_decompress_biovec(struct page **pages_in,
 	workspace->inf_strm.total_out = 0;
 	workspace->inf_strm.next_out = workspace->buf;
 	workspace->inf_strm.avail_out = PAGE_CACHE_SIZE;
-	page_out = bvec[page_out_index].bv_page;
-	page_bytes_left = PAGE_CACHE_SIZE;
 	pg_offset = 0;
 
 	/* If it's deflate, and it's got no preset dictionary, then
@@ -389,107 +252,29 @@ int btrfs_zlib_decompress_biovec(struct page **pages_in,
 
 	if (Z_OK != zlib_inflateInit2(&workspace->inf_strm, wbits)) {
 		printk(KERN_WARNING "inflateInit failed\n");
-		ret = -1;
-		goto out;
+		return -1;
 	}
 	while (workspace->inf_strm.total_in < srclen) {
 		ret = zlib_inflate(&workspace->inf_strm, Z_NO_FLUSH);
 		if (ret != Z_OK && ret != Z_STREAM_END)
 			break;
-		/*
-		 * buf start is the byte offset we're of the start of
-		 * our workspace buffer
-		 */
-		buf_start = total_out;
 
-		/* total_out is the last byte of the workspace buffer */
+		buf_start = total_out;
 		total_out = workspace->inf_strm.total_out;
 
-		working_bytes = total_out - buf_start;
-
-		/*
-		 * start byte is the first byte of the page we're currently
-		 * copying into relative to the start of the compressed data.
-		 */
-		start_byte = page_offset(page_out) - disk_start;
-
-		if (working_bytes == 0) {
-			/* we didn't make progress in this inflate
-			 * call, we're done
-			 */
-			if (ret != Z_STREAM_END)
-				ret = -1;
+		/* we didn't make progress in this inflate call, we're done */
+		if (buf_start == total_out)
 			break;
-		}
 
-		/* we haven't yet hit data corresponding to this page */
-		if (total_out <= start_byte)
-			goto next;
-
-		/*
-		 * the start of the data we care about is offset into
-		 * the middle of our working buffer
-		 */
-		if (total_out > start_byte && buf_start < start_byte) {
-			buf_offset = start_byte - buf_start;
-			working_bytes -= buf_offset;
-		} else {
-			buf_offset = 0;
-		}
-		current_buf_start = buf_start;
-
-		/* copy bytes from the working buffer into the pages */
-		while (working_bytes > 0) {
-			bytes = min(PAGE_CACHE_SIZE - pg_offset,
-				    PAGE_CACHE_SIZE - buf_offset);
-			bytes = min(bytes, working_bytes);
-			kaddr = kmap_atomic(page_out, KM_USER0);
-			memcpy(kaddr + pg_offset, workspace->buf + buf_offset,
-			       bytes);
-			kunmap_atomic(kaddr, KM_USER0);
-			flush_dcache_page(page_out);
-
-			pg_offset += bytes;
-			page_bytes_left -= bytes;
-			buf_offset += bytes;
-			working_bytes -= bytes;
-			current_buf_start += bytes;
-
-			/* check if we need to pick another page */
-			if (page_bytes_left == 0) {
-				page_out_index++;
-				if (page_out_index >= vcnt) {
-					ret = 0;
-					goto done;
-				}
-
-				page_out = bvec[page_out_index].bv_page;
-				pg_offset = 0;
-				page_bytes_left = PAGE_CACHE_SIZE;
-				start_byte = page_offset(page_out) - disk_start;
-
-				/*
-				 * make sure our new page is covered by this
-				 * working buffer
-				 */
-				if (total_out <= start_byte)
-					goto next;
-
-				/* the next page in the biovec might not
-				 * be adjacent to the last page, but it
-				 * might still be found inside this working
-				 * buffer.  bump our offset pointer
-				 */
-				if (total_out > start_byte &&
-				    current_buf_start < start_byte) {
-					buf_offset = start_byte - buf_start;
-					working_bytes = total_out - start_byte;
-					current_buf_start = buf_start +
-						buf_offset;
-				}
-			}
+		ret2 = btrfs_decompress_buf2page(workspace->buf, buf_start,
+						 total_out, disk_start,
+						 bvec, vcnt,
+						 &page_out_index, &pg_offset);
+		if (ret2 == 0) {
+			ret = 0;
+			goto done;
 		}
-next:
+
 		workspace->inf_strm.next_out = workspace->buf;
 		workspace->inf_strm.avail_out = PAGE_CACHE_SIZE;
 
@@ -516,35 +301,21 @@ done:
 	zlib_inflateEnd(&workspace->inf_strm);
 	if (data_in)
 		kunmap(pages_in[page_in_index]);
-out:
-	free_workspace(workspace);
 	return ret;
 }
 
-/*
- * a less complex decompression routine.  Our compressed data fits in a
- * single page, and we want to read a single page out of it.
- * start_byte tells us the offset into the compressed data we're interested in
- */
-int btrfs_zlib_decompress(unsigned char *data_in,
-			  struct page *dest_page,
-			  unsigned long start_byte,
-			  size_t srclen, size_t destlen)
+static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
+			   struct page *dest_page,
+			   unsigned long start_byte,
+			   size_t srclen, size_t destlen)
 {
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
 	int wbits = MAX_WBITS;
-	struct workspace *workspace;
 	unsigned long bytes_left = destlen;
 	unsigned long total_out = 0;
 	char *kaddr;
 
-	if (destlen > PAGE_CACHE_SIZE)
-		return -ENOMEM;
-
-	workspace = find_zlib_workspace();
-	if (IS_ERR(workspace))
-		return -ENOMEM;
-
 	workspace->inf_strm.next_in = data_in;
 	workspace->inf_strm.avail_in = srclen;
 	workspace->inf_strm.total_in = 0;
@@ -565,8 +336,7 @@ int btrfs_zlib_decompress(unsigned char *data_in,
 
 	if (Z_OK != zlib_inflateInit2(&workspace->inf_strm, wbits)) {
 		printk(KERN_WARNING "inflateInit failed\n");
-		ret = -1;
-		goto out;
+		return -1;
 	}
 
 	while (bytes_left > 0) {
@@ -616,12 +386,13 @@ next:
 		ret = 0;
 
 	zlib_inflateEnd(&workspace->inf_strm);
-out:
-	free_workspace(workspace);
 	return ret;
 }
 
-void btrfs_zlib_exit(void)
-{
-    free_workspaces();
-}
+struct btrfs_compress_op btrfs_zlib_compress = {
+	.alloc_workspace	= zlib_alloc_workspace,
+	.free_workspace		= zlib_free_workspace,
+	.compress_pages		= zlib_compress_pages,
+	.decompress_biovec	= zlib_decompress_biovec,
+	.decompress		= zlib_decompress,
+};
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 60d27bc9eb83..6b61ded701e1 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1560,9 +1560,10 @@ retry_locked:
 		/* NOTE: no side-effects allowed, until we take s_mutex */
 
 		revoking = cap->implemented & ~cap->issued;
-		if (revoking)
-			dout(" mds%d revoking %s\n", cap->mds,
-			     ceph_cap_string(revoking));
+		dout(" mds%d cap %p issued %s implemented %s revoking %s\n",
+		     cap->mds, cap, ceph_cap_string(cap->issued),
+		     ceph_cap_string(cap->implemented),
+		     ceph_cap_string(revoking));
 
 		if (cap == ci->i_auth_cap &&
 		    (cap->issued & CEPH_CAP_FILE_WR)) {
@@ -1658,6 +1659,8 @@ ack:
 
 		if (cap == ci->i_auth_cap && ci->i_dirty_caps)
 			flushing = __mark_caps_flushing(inode, session);
+		else
+			flushing = 0;
 
 		mds = cap->mds;  /* remember mds, so we don't repeat */
 		sent++;
@@ -1940,6 +1943,35 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 	}
 }
 
+static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc,
+				     struct ceph_mds_session *session,
+				     struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_cap *cap;
+	int delayed = 0;
+
+	spin_lock(&inode->i_lock);
+	cap = ci->i_auth_cap;
+	dout("kick_flushing_inode_caps %p flushing %s flush_seq %lld\n", inode,
+	     ceph_cap_string(ci->i_flushing_caps), ci->i_cap_flush_seq);
+	__ceph_flush_snaps(ci, &session, 1);
+	if (ci->i_flushing_caps) {
+		delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
+				     __ceph_caps_used(ci),
+				     __ceph_caps_wanted(ci),
+				     cap->issued | cap->implemented,
+				     ci->i_flushing_caps, NULL);
+		if (delayed) {
+			spin_lock(&inode->i_lock);
+			__cap_delay_requeue(mdsc, ci);
+			spin_unlock(&inode->i_lock);
+		}
+	} else {
+		spin_unlock(&inode->i_lock);
+	}
+}
+
 
 /*
  * Take references to capabilities we hold, so that we don't release
@@ -2687,7 +2719,7 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
 	ceph_add_cap(inode, session, cap_id, -1,
 		     issued, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH,
 		     NULL /* no caps context */);
-	try_flush_caps(inode, session, NULL);
+	kick_flushing_inode_caps(mdsc, session, inode);
 	up_read(&mdsc->snap_rwsem);
 
 	/* make sure we re-request max_size, if necessary */
@@ -2785,8 +2817,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	case CEPH_CAP_OP_IMPORT:
 		handle_cap_import(mdsc, inode, h, session,
 				  snaptrace, snaptrace_len);
-		ceph_check_caps(ceph_inode(inode), CHECK_CAPS_NODELAY,
-				session);
+		ceph_check_caps(ceph_inode(inode), 0, session);
 		goto done_unlocked;
 	}
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e835eff551e3..5625463aa479 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -710,10 +710,6 @@ static int fill_inode(struct inode *inode,
 			ci->i_ceph_flags |= CEPH_I_COMPLETE;
 			ci->i_max_offset = 2;
 		}
-
-		/* it may be better to set st_size in getattr instead? */
-		if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), RBYTES))
-			inode->i_size = ci->i_rbytes;
 		break;
 	default:
 		pr_err("fill_inode %llx.%llx BAD mode 0%o\n",
@@ -1819,7 +1815,11 @@ int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		else
 			stat->dev = 0;
 		if (S_ISDIR(inode->i_mode)) {
-			stat->size = ci->i_rbytes;
+			if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb),
+						RBYTES))
+				stat->size = ci->i_rbytes;
+			else
+				stat->size = ci->i_files + ci->i_subdirs;
 			stat->blocks = 0;
 			stat->blksize = 65536;
 		}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 1e30d194a8e3..a1ee8fa3a8e7 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -693,9 +693,11 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				dout("choose_mds %p %llx.%llx "
 				     "frag %u mds%d (%d/%d)\n",
 				     inode, ceph_vinop(inode),
-				     frag.frag, frag.mds,
+				     frag.frag, mds,
 				     (int)r, frag.ndist);
-				return mds;
+				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
+				    CEPH_MDS_STATE_ACTIVE)
+					return mds;
 			}
 
 			/* since this file/dir wasn't known to be
@@ -708,7 +710,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				dout("choose_mds %p %llx.%llx "
 				     "frag %u mds%d (auth)\n",
 				     inode, ceph_vinop(inode), frag.frag, mds);
-				return mds;
+				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
+				    CEPH_MDS_STATE_ACTIVE)
+					return mds;
 			}
 		}
 	}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index bf6f0f34082a..9c5085465a63 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -290,6 +290,8 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 
         fsopt->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
         fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
+	fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
+	fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
         fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
         fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
         fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 6e12a6ba5f79..8c9eba6ef9df 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -219,6 +219,7 @@ static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct ceph_inode_xattr *xattr = NULL;
+	int name_len = strlen(name);
 	int c;
 
 	p = &ci->i_xattrs.index.rb_node;
@@ -226,6 +227,8 @@ static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
 		parent = *p;
 		xattr = rb_entry(parent, struct ceph_inode_xattr, node);
 		c = strncmp(name, xattr->name, xattr->name_len);
+		if (c == 0 && name_len > xattr->name_len)
+			c = 1;
 		if (c < 0)
 			p = &(*p)->rb_left;
 		else if (c > 0)
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index ee45648b0d1a..7cb0f7f847e4 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -3,6 +3,7 @@ config CIFS
 	depends on INET
 	select NLS
 	select CRYPTO
+	select CRYPTO_MD4
 	select CRYPTO_MD5
 	select CRYPTO_HMAC
 	select CRYPTO_ARC4
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index 43b19dd39191..d87558448e3d 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -5,7 +5,7 @@ obj-$(CONFIG_CIFS) += cifs.o
 
 cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \
 	  link.o misc.o netmisc.o smbdes.o smbencrypt.o transport.o asn1.o \
-	  md4.o md5.o cifs_unicode.o nterr.o xattr.o cifsencrypt.o \
+	  cifs_unicode.o nterr.o xattr.o cifsencrypt.o \
 	  readdir.o ioctl.o sess.o export.o
 
 cifs-$(CONFIG_CIFS_ACL) += cifsacl.o
diff --git a/fs/cifs/README b/fs/cifs/README
index 46af99ab3614..fe1683590828 100644
--- a/fs/cifs/README
+++ b/fs/cifs/README
@@ -452,6 +452,11 @@ A partial list of the supported mount options follows:
 		if oplock (caching token) is granted and held. Note that
 		direct allows write operations larger than page size
 		to be sent to the server.
+  strictcache   Use for switching on strict cache mode. In this mode the
+		client read from the cache all the time it has Oplock Level II,
+		otherwise - read from the server. All written data are stored
+		in the cache, but if the client doesn't have Exclusive Oplock,
+		it writes the data to the server.
   acl   	Allow setfacl and getfacl to manage posix ACLs if server
 		supports them.  (default)
   noacl 	Do not allow setfacl and getfacl calls on this mount
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index ede98300a8cd..65829d32128c 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -79,11 +79,11 @@ void cifs_dump_mids(struct TCP_Server_Info *server)
 	spin_lock(&GlobalMid_Lock);
 	list_for_each(tmp, &server->pending_mid_q) {
 		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-		cERROR(1, "State: %d Cmd: %d Pid: %d Tsk: %p Mid %d",
+		cERROR(1, "State: %d Cmd: %d Pid: %d Cbdata: %p Mid %d",
 			mid_entry->midState,
 			(int)mid_entry->command,
 			mid_entry->pid,
-			mid_entry->tsk,
+			mid_entry->callback_data,
 			mid_entry->mid);
 #ifdef CONFIG_CIFS_STATS2
 		cERROR(1, "IsLarge: %d buf: %p time rcv: %ld now: %ld",
@@ -218,11 +218,11 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 				mid_entry = list_entry(tmp3, struct mid_q_entry,
 					qhead);
 				seq_printf(m, "\tState: %d com: %d pid:"
-						" %d tsk: %p mid %d\n",
+						" %d cbdata: %p mid %d\n",
 						mid_entry->midState,
 						(int)mid_entry->command,
 						mid_entry->pid,
-						mid_entry->tsk,
+						mid_entry->callback_data,
 						mid_entry->mid);
 			}
 			spin_unlock(&GlobalMid_Lock);
@@ -331,7 +331,7 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
 				atomic_read(&totSmBufAllocCount));
 #endif /* CONFIG_CIFS_STATS2 */
 
-	seq_printf(m, "Operations (MIDs): %d\n", midCount.counter);
+	seq_printf(m, "Operations (MIDs): %d\n", atomic_read(&midCount));
 	seq_printf(m,
 		"\n%d session %d share reconnects\n",
 		tcpSesReconnectCount.counter, tconInfoReconnectCount.counter);
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index c68a056f27fd..0a265ad9e426 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -255,35 +255,6 @@ static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb,
 
 }
 
-static int add_mount_helper(struct vfsmount *newmnt, struct nameidata *nd,
-				struct list_head *mntlist)
-{
-	/* stolen from afs code */
-	int err;
-
-	mntget(newmnt);
-	err = do_add_mount(newmnt, &nd->path, nd->path.mnt->mnt_flags | MNT_SHRINKABLE, mntlist);
-	switch (err) {
-	case 0:
-		path_put(&nd->path);
-		nd->path.mnt = newmnt;
-		nd->path.dentry = dget(newmnt->mnt_root);
-		schedule_delayed_work(&cifs_dfs_automount_task,
-				      cifs_dfs_mountpoint_expiry_timeout);
-		break;
-	case -EBUSY:
-		/* someone else made a mount here whilst we were busy */
-		while (d_mountpoint(nd->path.dentry) &&
-		       follow_down(&nd->path))
-			;
-		err = 0;
-	default:
-		mntput(newmnt);
-		break;
-	}
-	return err;
-}
-
 static void dump_referral(const struct dfs_info3_param *ref)
 {
 	cFYI(1, "DFS: ref path: %s", ref->path_name);
@@ -293,27 +264,23 @@ static void dump_referral(const struct dfs_info3_param *ref)
 				ref->path_consumed);
 }
 
-
-static void*
-cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
+/*
+ * Create a vfsmount that we can automount
+ */
+static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 {
 	struct dfs_info3_param *referrals = NULL;
 	unsigned int num_referrals = 0;
 	struct cifs_sb_info *cifs_sb;
 	struct cifsSesInfo *ses;
-	char *full_path = NULL;
+	char *full_path;
 	int xid, i;
-	int rc = 0;
-	struct vfsmount *mnt = ERR_PTR(-ENOENT);
+	int rc;
+	struct vfsmount *mnt;
 	struct tcon_link *tlink;
 
 	cFYI(1, "in %s", __func__);
-	BUG_ON(IS_ROOT(dentry));
-
-	xid = GetXid();
-
-	dput(nd->path.dentry);
-	nd->path.dentry = dget(dentry);
+	BUG_ON(IS_ROOT(mntpt));
 
 	/*
 	 * The MSDFS spec states that paths in DFS referral requests and
@@ -321,66 +288,83 @@ cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
 	 * the double backslashes usually used in the UNC. This function
 	 * gives us the latter, so we must adjust the result.
 	 */
-	full_path = build_path_from_dentry(dentry);
-	if (full_path == NULL) {
-		rc = -ENOMEM;
-		goto out_err;
-	}
+	mnt = ERR_PTR(-ENOMEM);
+	full_path = build_path_from_dentry(mntpt);
+	if (full_path == NULL)
+		goto cdda_exit;
 
-	cifs_sb = CIFS_SB(dentry->d_inode->i_sb);
+	cifs_sb = CIFS_SB(mntpt->d_inode->i_sb);
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink)) {
-		rc = PTR_ERR(tlink);
-		goto out_err;
+		mnt = ERR_CAST(tlink);
+		goto free_full_path;
 	}
 	ses = tlink_tcon(tlink)->ses;
 
+	xid = GetXid();
 	rc = get_dfs_path(xid, ses, full_path + 1, cifs_sb->local_nls,
 		&num_referrals, &referrals,
 		cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+	FreeXid(xid);
 
 	cifs_put_tlink(tlink);
 
+	mnt = ERR_PTR(-ENOENT);
 	for (i = 0; i < num_referrals; i++) {
 		int len;
-		dump_referral(referrals+i);
+		dump_referral(referrals + i);
 		/* connect to a node */
 		len = strlen(referrals[i].node_name);
 		if (len < 2) {
 			cERROR(1, "%s: Net Address path too short: %s",
 					__func__, referrals[i].node_name);
-			rc = -EINVAL;
-			goto out_err;
+			mnt = ERR_PTR(-EINVAL);
+			break;
 		}
 		mnt = cifs_dfs_do_refmount(cifs_sb,
 				full_path, referrals + i);
 		cFYI(1, "%s: cifs_dfs_do_refmount:%s , mnt:%p", __func__,
 					referrals[i].node_name, mnt);
-
-		/* complete mount procedure if we accured submount */
 		if (!IS_ERR(mnt))
-			break;
+			goto success;
 	}
 
-	/* we need it cause for() above could exit without valid submount */
-	rc = PTR_ERR(mnt);
-	if (IS_ERR(mnt))
-		goto out_err;
+	/* no valid submounts were found; return error from get_dfs_path() by
+	 * preference */
+	if (rc != 0)
+		mnt = ERR_PTR(rc);
 
-	rc = add_mount_helper(mnt, nd, &cifs_dfs_automount_list);
-
-out:
-	FreeXid(xid);
+success:
 	free_dfs_info_array(referrals, num_referrals);
+free_full_path:
 	kfree(full_path);
+cdda_exit:
 	cFYI(1, "leaving %s" , __func__);
-	return ERR_PTR(rc);
-out_err:
-	path_put(&nd->path);
-	goto out;
+	return mnt;
+}
+
+/*
+ * Attempt to automount the referral
+ */
+struct vfsmount *cifs_dfs_d_automount(struct path *path)
+{
+	struct vfsmount *newmnt;
+
+	cFYI(1, "in %s", __func__);
+
+	newmnt = cifs_dfs_do_automount(path->dentry);
+	if (IS_ERR(newmnt)) {
+		cFYI(1, "leaving %s [automount failed]" , __func__);
+		return newmnt;
+	}
+
+	mntget(newmnt); /* prevent immediate expiration */
+	mnt_set_expiry(newmnt, &cifs_dfs_automount_list);
+	schedule_delayed_work(&cifs_dfs_automount_task,
+			      cifs_dfs_mountpoint_expiry_timeout);
+	cFYI(1, "leaving %s [ok]" , __func__);
+	return newmnt;
 }
 
 const struct inode_operations cifs_dfs_referral_inode_operations = {
-	.follow_link = cifs_dfs_follow_mountpoint,
 };
-
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index 7852cd677051..ac51cd2d33ae 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -40,6 +40,7 @@
 #define CIFS_MOUNT_FSCACHE	0x8000 /* local caching enabled */
 #define CIFS_MOUNT_MF_SYMLINKS	0x10000 /* Minshall+French Symlinks enabled */
 #define CIFS_MOUNT_MULTIUSER	0x20000 /* multiuser mount */
+#define CIFS_MOUNT_STRICT_IO	0x40000 /* strict cache mode */
 
 struct cifs_sb_info {
 	struct rb_root tlink_tree;
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 430f510a1720..fc0fd4fde306 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -44,10 +44,14 @@ cifs_ucs2_bytes(const __le16 *from, int maxbytes,
 	int charlen, outlen = 0;
 	int maxwords = maxbytes / 2;
 	char tmp[NLS_MAX_CHARSET_SIZE];
+	__u16 ftmp;
 
-	for (i = 0; i < maxwords && from[i]; i++) {
-		charlen = codepage->uni2char(le16_to_cpu(from[i]), tmp,
-					     NLS_MAX_CHARSET_SIZE);
+	for (i = 0; i < maxwords; i++) {
+		ftmp = get_unaligned_le16(&from[i]);
+		if (ftmp == 0)
+			break;
+
+		charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE);
 		if (charlen > 0)
 			outlen += charlen;
 		else
@@ -58,9 +62,9 @@ cifs_ucs2_bytes(const __le16 *from, int maxbytes,
 }
 
 /*
- * cifs_mapchar - convert a little-endian char to proper char in codepage
+ * cifs_mapchar - convert a host-endian char to proper char in codepage
  * @target - where converted character should be copied
- * @src_char - 2 byte little-endian source character
+ * @src_char - 2 byte host-endian source character
  * @cp - codepage to which character should be converted
  * @mapchar - should character be mapped according to mapchars mount option?
  *
@@ -69,7 +73,7 @@ cifs_ucs2_bytes(const __le16 *from, int maxbytes,
  * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
  */
 static int
-cifs_mapchar(char *target, const __le16 src_char, const struct nls_table *cp,
+cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp,
 	     bool mapchar)
 {
 	int len = 1;
@@ -82,7 +86,7 @@ cifs_mapchar(char *target, const __le16 src_char, const struct nls_table *cp,
 	 *     build_path_from_dentry are modified, as they use slash as
 	 *     separator.
 	 */
-	switch (le16_to_cpu(src_char)) {
+	switch (src_char) {
 	case UNI_COLON:
 		*target = ':';
 		break;
@@ -109,8 +113,7 @@ out:
 	return len;
 
 cp_convert:
-	len = cp->uni2char(le16_to_cpu(src_char), target,
-			   NLS_MAX_CHARSET_SIZE);
+	len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE);
 	if (len <= 0) {
 		*target = '?';
 		len = 1;
@@ -149,6 +152,7 @@ cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
 	int nullsize = nls_nullsize(codepage);
 	int fromwords = fromlen / 2;
 	char tmp[NLS_MAX_CHARSET_SIZE];
+	__u16 ftmp;
 
 	/*
 	 * because the chars can be of varying widths, we need to take care
@@ -158,19 +162,23 @@ cifs_from_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
 	 */
 	safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);
 
-	for (i = 0; i < fromwords && from[i]; i++) {
+	for (i = 0; i < fromwords; i++) {
+		ftmp = get_unaligned_le16(&from[i]);
+		if (ftmp == 0)
+			break;
+
 		/*
 		 * check to see if converting this character might make the
 		 * conversion bleed into the null terminator
 		 */
 		if (outlen >= safelen) {
-			charlen = cifs_mapchar(tmp, from[i], codepage, mapchar);
+			charlen = cifs_mapchar(tmp, ftmp, codepage, mapchar);
 			if ((outlen + charlen) > (tolen - nullsize))
 				break;
 		}
 
 		/* put converted char into 'to' buffer */
-		charlen = cifs_mapchar(&to[outlen], from[i], codepage, mapchar);
+		charlen = cifs_mapchar(&to[outlen], ftmp, codepage, mapchar);
 		outlen += charlen;
 	}
 
@@ -193,24 +201,21 @@ cifs_strtoUCS(__le16 *to, const char *from, int len,
 {
 	int charlen;
 	int i;
-	wchar_t *wchar_to = (wchar_t *)to; /* needed to quiet sparse */
+	wchar_t wchar_to; /* needed to quiet sparse */
 
 	for (i = 0; len && *from; i++, from += charlen, len -= charlen) {
-
-		/* works for 2.4.0 kernel or later */
-		charlen = codepage->char2uni(from, len, &wchar_to[i]);
+		charlen = codepage->char2uni(from, len, &wchar_to);
 		if (charlen < 1) {
-			cERROR(1, "strtoUCS: char2uni of %d returned %d",
-				(int)*from, charlen);
+			cERROR(1, "strtoUCS: char2uni of 0x%x returned %d",
+				*from, charlen);
 			/* A question mark */
-			to[i] = cpu_to_le16(0x003f);
+			wchar_to = 0x003f;
 			charlen = 1;
-		} else
-			to[i] = cpu_to_le16(wchar_to[i]);
-
+		}
+		put_unaligned_le16(wchar_to, &to[i]);
 	}
 
-	to[i] = 0;
+	put_unaligned_le16(0, &to[i]);
 	return i;
 }
 
@@ -252,3 +257,79 @@ cifs_strndup_from_ucs(const char *src, const int maxlen, const bool is_unicode,
 	return dst;
 }
 
+/*
+ * Convert 16 bit Unicode pathname to wire format from string in current code
+ * page. Conversion may involve remapping up the six characters that are
+ * only legal in POSIX-like OS (if they are present in the string). Path
+ * names are little endian 16 bit Unicode on the wire
+ */
+int
+cifsConvertToUCS(__le16 *target, const char *source, int maxlen,
+		 const struct nls_table *cp, int mapChars)
+{
+	int i, j, charlen;
+	int len_remaining = maxlen;
+	char src_char;
+	__u16 temp;
+
+	if (!mapChars)
+		return cifs_strtoUCS(target, source, PATH_MAX, cp);
+
+	for (i = 0, j = 0; i < maxlen; j++) {
+		src_char = source[i];
+		switch (src_char) {
+		case 0:
+			put_unaligned_le16(0, &target[j]);
+			goto ctoUCS_out;
+		case ':':
+			temp = UNI_COLON;
+			break;
+		case '*':
+			temp = UNI_ASTERIK;
+			break;
+		case '?':
+			temp = UNI_QUESTION;
+			break;
+		case '<':
+			temp = UNI_LESSTHAN;
+			break;
+		case '>':
+			temp = UNI_GRTRTHAN;
+			break;
+		case '|':
+			temp = UNI_PIPE;
+			break;
+		/*
+		 * FIXME: We can not handle remapping backslash (UNI_SLASH)
+		 * until all the calls to build_path_from_dentry are modified,
+		 * as they use backslash as separator.
+		 */
+		default:
+			charlen = cp->char2uni(source+i, len_remaining,
+						&temp);
+			/*
+			 * if no match, use question mark, which at least in
+			 * some cases serves as wild card
+			 */
+			if (charlen < 1) {
+				temp = 0x003f;
+				charlen = 1;
+			}
+			len_remaining -= charlen;
+			/*
+			 * character may take more than one byte in the source
+			 * string, but will take exactly two bytes in the
+			 * target string
+			 */
+			i += charlen;
+			continue;
+		}
+		put_unaligned_le16(temp, &target[j]);
+		i++; /* move to next char in source string */
+		len_remaining--;
+	}
+
+ctoUCS_out:
+	return i;
+}
+
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index a437ec391a01..beeebf194234 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -41,9 +41,12 @@ static struct cifs_wksid wksidarr[NUM_WK_SIDS] = {
 ;
 
 
-/* security id for everyone */
+/* security id for everyone/world system group */
 static const struct cifs_sid sid_everyone = {
 	1, 1, {0, 0, 0, 0, 0, 1}, {0} };
+/* security id for Authenticated Users system group */
+static const struct cifs_sid sid_authusers = {
+	1, 1, {0, 0, 0, 0, 0, 5}, {11} };
 /* group users */
 static const struct cifs_sid sid_user = {1, 2 , {0, 0, 0, 0, 0, 5}, {} };
 
@@ -365,10 +368,14 @@ static void parse_dacl(struct cifs_acl *pdacl, char *end_of_acl,
 	if (num_aces  > 0) {
 		umode_t user_mask = S_IRWXU;
 		umode_t group_mask = S_IRWXG;
-		umode_t other_mask = S_IRWXO;
+		umode_t other_mask = S_IRWXU | S_IRWXG | S_IRWXO;
 
 		ppace = kmalloc(num_aces * sizeof(struct cifs_ace *),
 				GFP_KERNEL);
+		if (!ppace) {
+			cERROR(1, "DACL memory allocation error");
+			return;
+		}
 
 		for (i = 0; i < num_aces; ++i) {
 			ppace[i] = (struct cifs_ace *) (acl_base + acl_size);
@@ -390,6 +397,12 @@ static void parse_dacl(struct cifs_acl *pdacl, char *end_of_acl,
 						     ppace[i]->type,
 						     &fattr->cf_mode,
 						     &other_mask);
+			if (compare_sids(&(ppace[i]->sid), &sid_authusers))
+				access_flags_to_mode(ppace[i]->access_req,
+						     ppace[i]->type,
+						     &fattr->cf_mode,
+						     &other_mask);
+
 
 /*			memcpy((void *)(&(cifscred->aces[i])),
 				(void *)ppace[i],
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 66f3d50d0676..a51585f9852b 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -24,7 +24,6 @@
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifs_debug.h"
-#include "md5.h"
 #include "cifs_unicode.h"
 #include "cifsproto.h"
 #include "ntlmssp.h"
@@ -37,11 +36,6 @@
 /* Note that the smb header signature field on input contains the
 	sequence number before this function is called */
 
-extern void mdfour(unsigned char *out, unsigned char *in, int n);
-extern void E_md4hash(const unsigned char *passwd, unsigned char *p16);
-extern void SMBencrypt(unsigned char *passwd, const unsigned char *c8,
-		       unsigned char *p24);
-
 static int cifs_calculate_signature(const struct smb_hdr *cifs_pdu,
 				struct TCP_Server_Info *server, char *signature)
 {
@@ -234,6 +228,7 @@ int cifs_verify_signature(struct smb_hdr *cifs_pdu,
 /* first calculate 24 bytes ntlm response and then 16 byte session key */
 int setup_ntlm_response(struct cifsSesInfo *ses)
 {
+	int rc = 0;
 	unsigned int temp_len = CIFS_SESS_KEY_SIZE + CIFS_AUTH_RESP_SIZE;
 	char temp_key[CIFS_SESS_KEY_SIZE];
 
@@ -247,13 +242,26 @@ int setup_ntlm_response(struct cifsSesInfo *ses)
 	}
 	ses->auth_key.len = temp_len;
 
-	SMBNTencrypt(ses->password, ses->server->cryptkey,
+	rc = SMBNTencrypt(ses->password, ses->server->cryptkey,
 			ses->auth_key.response + CIFS_SESS_KEY_SIZE);
+	if (rc) {
+		cFYI(1, "%s Can't generate NTLM response, error: %d",
+			__func__, rc);
+		return rc;
+	}
 
-	E_md4hash(ses->password, temp_key);
-	mdfour(ses->auth_key.response, temp_key, CIFS_SESS_KEY_SIZE);
+	rc = E_md4hash(ses->password, temp_key);
+	if (rc) {
+		cFYI(1, "%s Can't generate NT hash, error: %d", __func__, rc);
+		return rc;
+	}
 
-	return 0;
+	rc = mdfour(ses->auth_key.response, temp_key, CIFS_SESS_KEY_SIZE);
+	if (rc)
+		cFYI(1, "%s Can't generate NTLM session key, error: %d",
+			__func__, rc);
+
+	return rc;
 }
 
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
@@ -649,9 +657,10 @@ calc_seckey(struct cifsSesInfo *ses)
 	get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE);
 
 	tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
-	if (!tfm_arc4 || IS_ERR(tfm_arc4)) {
+	if (IS_ERR(tfm_arc4)) {
+		rc = PTR_ERR(tfm_arc4);
 		cERROR(1, "could not allocate crypto API arc4\n");
-		return PTR_ERR(tfm_arc4);
+		return rc;
 	}
 
 	desc.tfm = tfm_arc4;
@@ -700,14 +709,13 @@ cifs_crypto_shash_allocate(struct TCP_Server_Info *server)
 	unsigned int size;
 
 	server->secmech.hmacmd5 = crypto_alloc_shash("hmac(md5)", 0, 0);
-	if (!server->secmech.hmacmd5 ||
-			IS_ERR(server->secmech.hmacmd5)) {
+	if (IS_ERR(server->secmech.hmacmd5)) {
 		cERROR(1, "could not allocate crypto hmacmd5\n");
 		return PTR_ERR(server->secmech.hmacmd5);
 	}
 
 	server->secmech.md5 = crypto_alloc_shash("md5", 0, 0);
-	if (!server->secmech.md5 || IS_ERR(server->secmech.md5)) {
+	if (IS_ERR(server->secmech.md5)) {
 		cERROR(1, "could not allocate crypto md5\n");
 		rc = PTR_ERR(server->secmech.md5);
 		goto crypto_allocate_md5_fail;
diff --git a/fs/cifs/cifsencrypt.h b/fs/cifs/cifsencrypt.h
deleted file mode 100644
index 15d2ec006474..000000000000
--- a/fs/cifs/cifsencrypt.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- *   fs/cifs/cifsencrypt.h
- *
- *   Copyright (c) International Business Machines  Corp., 2005
- *   Author(s): Steve French (sfrench@us.ibm.com)
- *
- *   Externs for misc. small encryption routines
- *   so we do not have to put them in cifsproto.h
- *
- *   This library is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU Lesser General Public License as published
- *   by the Free Software Foundation; either version 2.1 of the License, or
- *   (at your option) any later version.
- *
- *   This library is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
- *   the GNU Lesser General Public License for more details.
- *
- *   You should have received a copy of the GNU Lesser General Public License
- *   along with this library; if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-/* md4.c */
-extern void mdfour(unsigned char *out, unsigned char *in, int n);
-/* smbdes.c */
-extern void E_P16(unsigned char *p14, unsigned char *p16);
-extern void E_P24(unsigned char *p21, const unsigned char *c8,
-		  unsigned char *p24);
-
-
-
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index d9f652a522a6..f2970136d17d 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -77,7 +77,11 @@ unsigned int cifs_max_pending = CIFS_MAX_REQ;
 module_param(cifs_max_pending, int, 0);
 MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server. "
 				   "Default: 50 Range: 2 to 256");
-
+unsigned short echo_retries = 5;
+module_param(echo_retries, ushort, 0644);
+MODULE_PARM_DESC(echo_retries, "Number of echo attempts before giving up and "
+			       "reconnecting server. Default: 5. 0 means "
+			       "never reconnect.");
 extern mempool_t *cifs_sm_req_poolp;
 extern mempool_t *cifs_req_poolp;
 extern mempool_t *cifs_mid_poolp;
@@ -596,10 +600,17 @@ static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 {
 	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
 	ssize_t written;
+	int rc;
 
 	written = generic_file_aio_write(iocb, iov, nr_segs, pos);
-	if (!CIFS_I(inode)->clientCanCacheAll)
-		filemap_fdatawrite(inode->i_mapping);
+
+	if (CIFS_I(inode)->clientCanCacheAll)
+		return written;
+
+	rc = filemap_fdatawrite(inode->i_mapping);
+	if (rc)
+		cFYI(1, "cifs_file_aio_write: %d rc on %p inode", rc, inode);
+
 	return written;
 }
 
@@ -729,6 +740,25 @@ const struct file_operations cifs_file_ops = {
 	.setlease = cifs_setlease,
 };
 
+const struct file_operations cifs_file_strict_ops = {
+	.read = do_sync_read,
+	.write = do_sync_write,
+	.aio_read = cifs_strict_readv,
+	.aio_write = cifs_strict_writev,
+	.open = cifs_open,
+	.release = cifs_close,
+	.lock = cifs_lock,
+	.fsync = cifs_strict_fsync,
+	.flush = cifs_flush,
+	.mmap = cifs_file_strict_mmap,
+	.splice_read = generic_file_splice_read,
+	.llseek = cifs_llseek,
+#ifdef CONFIG_CIFS_POSIX
+	.unlocked_ioctl	= cifs_ioctl,
+#endif /* CONFIG_CIFS_POSIX */
+	.setlease = cifs_setlease,
+};
+
 const struct file_operations cifs_file_direct_ops = {
 	/* no aio, no readv -
 	   BB reevaluate whether they can be done with directio, no cache */
@@ -747,6 +777,7 @@ const struct file_operations cifs_file_direct_ops = {
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
 };
+
 const struct file_operations cifs_file_nobrl_ops = {
 	.read = do_sync_read,
 	.write = do_sync_write,
@@ -765,6 +796,24 @@ const struct file_operations cifs_file_nobrl_ops = {
 	.setlease = cifs_setlease,
 };
 
+const struct file_operations cifs_file_strict_nobrl_ops = {
+	.read = do_sync_read,
+	.write = do_sync_write,
+	.aio_read = cifs_strict_readv,
+	.aio_write = cifs_strict_writev,
+	.open = cifs_open,
+	.release = cifs_close,
+	.fsync = cifs_strict_fsync,
+	.flush = cifs_flush,
+	.mmap = cifs_file_strict_mmap,
+	.splice_read = generic_file_splice_read,
+	.llseek = cifs_llseek,
+#ifdef CONFIG_CIFS_POSIX
+	.unlocked_ioctl	= cifs_ioctl,
+#endif /* CONFIG_CIFS_POSIX */
+	.setlease = cifs_setlease,
+};
+
 const struct file_operations cifs_file_direct_nobrl_ops = {
 	/* no mmap, no aio, no readv -
 	   BB reevaluate whether they can be done with directio, no cache */
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 897b2b2b28b5..4a3330235d55 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -61,6 +61,7 @@ extern int cifs_rename(struct inode *, struct dentry *, struct inode *,
 		       struct dentry *);
 extern int cifs_revalidate_file(struct file *filp);
 extern int cifs_revalidate_dentry(struct dentry *);
+extern void cifs_invalidate_mapping(struct inode *inode);
 extern int cifs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern int cifs_setattr(struct dentry *, struct iattr *);
 
@@ -72,19 +73,27 @@ extern const struct inode_operations cifs_dfs_referral_inode_operations;
 /* Functions related to files and directories */
 extern const struct file_operations cifs_file_ops;
 extern const struct file_operations cifs_file_direct_ops; /* if directio mnt */
-extern const struct file_operations cifs_file_nobrl_ops;
-extern const struct file_operations cifs_file_direct_nobrl_ops; /* no brlocks */
+extern const struct file_operations cifs_file_strict_ops; /* if strictio mnt */
+extern const struct file_operations cifs_file_nobrl_ops; /* no brlocks */
+extern const struct file_operations cifs_file_direct_nobrl_ops;
+extern const struct file_operations cifs_file_strict_nobrl_ops;
 extern int cifs_open(struct inode *inode, struct file *file);
 extern int cifs_close(struct inode *inode, struct file *file);
 extern int cifs_closedir(struct inode *inode, struct file *file);
 extern ssize_t cifs_user_read(struct file *file, char __user *read_data,
-			 size_t read_size, loff_t *poffset);
+			      size_t read_size, loff_t *poffset);
+extern ssize_t cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov,
+				 unsigned long nr_segs, loff_t pos);
 extern ssize_t cifs_user_write(struct file *file, const char __user *write_data,
-			 size_t write_size, loff_t *poffset);
+			       size_t write_size, loff_t *poffset);
+extern ssize_t cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
+				  unsigned long nr_segs, loff_t pos);
 extern int cifs_lock(struct file *, int, struct file_lock *);
 extern int cifs_fsync(struct file *, int);
+extern int cifs_strict_fsync(struct file *, int);
 extern int cifs_flush(struct file *, fl_owner_t id);
 extern int cifs_file_mmap(struct file * , struct vm_area_struct *);
+extern int cifs_file_strict_mmap(struct file * , struct vm_area_struct *);
 extern const struct file_operations cifs_dir_ops;
 extern int cifs_dir_open(struct inode *inode, struct file *file);
 extern int cifs_readdir(struct file *file, void *direntry, filldir_t filldir);
@@ -93,6 +102,12 @@ extern int cifs_readdir(struct file *file, void *direntry, filldir_t filldir);
 extern const struct dentry_operations cifs_dentry_ops;
 extern const struct dentry_operations cifs_ci_dentry_ops;
 
+#ifdef CONFIG_CIFS_DFS_UPCALL
+extern struct vfsmount *cifs_dfs_d_automount(struct path *path);
+#else
+#define cifs_dfs_d_automount NULL
+#endif
+
 /* Functions related to symlinks */
 extern void *cifs_follow_link(struct dentry *direntry, struct nameidata *nd);
 extern void cifs_put_link(struct dentry *direntry,
@@ -112,5 +127,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 extern const struct export_operations cifs_export_ops;
 #endif /* EXPERIMENTAL */
 
-#define CIFS_VERSION   "1.68"
+#define CIFS_VERSION   "1.70"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 606ca8bb7102..17afb0fbcaed 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -161,46 +161,41 @@ struct TCP_Server_Info {
 	int srv_count; /* reference counter */
 	/* 15 character server name + 0x20 16th byte indicating type = srv */
 	char server_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL];
+	enum statusEnum tcpStatus; /* what we think the status is */
 	char *hostname; /* hostname portion of UNC string */
 	struct socket *ssocket;
 	struct sockaddr_storage dstaddr;
 	struct sockaddr_storage srcaddr; /* locally bind to this IP */
+#ifdef CONFIG_NET_NS
+	struct net *net;
+#endif
 	wait_queue_head_t response_q;
 	wait_queue_head_t request_q; /* if more than maxmpx to srvr must block*/
 	struct list_head pending_mid_q;
-	void *Server_NlsInfo;	/* BB - placeholder for future NLS info  */
-	unsigned short server_codepage;	/* codepage for the server    */
-	enum protocolEnum protocolType;
-	char versionMajor;
-	char versionMinor;
-	bool svlocal:1;			/* local server or remote */
 	bool noblocksnd;		/* use blocking sendmsg */
 	bool noautotune;		/* do not autotune send buf sizes */
 	bool tcp_nodelay;
 	atomic_t inFlight;  /* number of requests on the wire to server */
-#ifdef CONFIG_CIFS_STATS2
-	atomic_t inSend; /* requests trying to send */
-	atomic_t num_waiters;   /* blocked waiting to get in sendrecv */
-#endif
-	enum statusEnum tcpStatus; /* what we think the status is */
 	struct mutex srv_mutex;
 	struct task_struct *tsk;
 	char server_GUID[16];
 	char secMode;
+	bool session_estab; /* mark when very first sess is established */
+	u16 dialect; /* dialect index that server chose */
 	enum securityEnum secType;
 	unsigned int maxReq;	/* Clients should submit no more */
 	/* than maxReq distinct unanswered SMBs to the server when using  */
 	/* multiplexed reads or writes */
 	unsigned int maxBuf;	/* maxBuf specifies the maximum */
 	/* message size the server can send or receive for non-raw SMBs */
+	/* maxBuf is returned by SMB NegotiateProtocol so maxBuf is only 0 */
+	/* when socket is setup (and during reconnect) before NegProt sent */
 	unsigned int max_rw;	/* maxRw specifies the maximum */
 	/* message size the server can send or receive for */
 	/* SMB_COM_WRITE_RAW or SMB_COM_READ_RAW. */
 	unsigned int max_vcs;	/* maximum number of smb sessions, at least
 				   those that can be specified uniquely with
 				   vcnumbers */
-	char sessid[4];		/* unique token id for this session */
-	/* (returned on Negotiate */
 	int capabilities; /* allow selective disabling of caps by smb sess */
 	int timeAdj;  /* Adjust for difference in server time zone in sec */
 	__u16 CurrentMid;         /* multiplex id - rotating counter */
@@ -210,20 +205,53 @@ struct TCP_Server_Info {
 	__u32 sequence_number; /* for signing, protected by srv_mutex */
 	struct session_key session_key;
 	unsigned long lstrp; /* when we got last response from this server */
-	u16 dialect; /* dialect index that server chose */
 	struct cifs_secmech secmech; /* crypto sec mech functs, descriptors */
 	/* extended security flavors that server supports */
+	bool	sec_ntlmssp;		/* supports NTLMSSP */
+	bool	sec_kerberosu2u;	/* supports U2U Kerberos */
 	bool	sec_kerberos;		/* supports plain Kerberos */
 	bool	sec_mskerberos;		/* supports legacy MS Kerberos */
-	bool	sec_kerberosu2u;	/* supports U2U Kerberos */
-	bool	sec_ntlmssp;		/* supports NTLMSSP */
-	bool session_estab; /* mark when very first sess is established */
+	struct delayed_work	echo; /* echo ping workqueue job */
 #ifdef CONFIG_CIFS_FSCACHE
 	struct fscache_cookie   *fscache; /* client index cache cookie */
 #endif
+#ifdef CONFIG_CIFS_STATS2
+	atomic_t inSend; /* requests trying to send */
+	atomic_t num_waiters;   /* blocked waiting to get in sendrecv */
+#endif
 };
 
 /*
+ * Macros to allow the TCP_Server_Info->net field and related code to drop out
+ * when CONFIG_NET_NS isn't set.
+ */
+
+#ifdef CONFIG_NET_NS
+
+static inline struct net *cifs_net_ns(struct TCP_Server_Info *srv)
+{
+	return srv->net;
+}
+
+static inline void cifs_set_net_ns(struct TCP_Server_Info *srv, struct net *net)
+{
+	srv->net = net;
+}
+
+#else
+
+static inline struct net *cifs_net_ns(struct TCP_Server_Info *srv)
+{
+	return &init_net;
+}
+
+static inline void cifs_set_net_ns(struct TCP_Server_Info *srv, struct net *net)
+{
+}
+
+#endif
+
+/*
  * Session structure.  One of these for each uid session with a particular host
  */
 struct cifsSesInfo {
@@ -446,11 +474,11 @@ struct cifsInodeInfo {
 	/* BB add in lists for dirty pages i.e. write caching info for oplock */
 	struct list_head openFileList;
 	__u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */
-	unsigned long time;	/* jiffies of last update/check of inode */
-	bool clientCanCacheRead:1;	/* read oplock */
-	bool clientCanCacheAll:1;	/* read and writebehind oplock */
-	bool delete_pending:1;		/* DELETE_ON_CLOSE is set */
-	bool invalid_mapping:1;		/* pagecache is invalid */
+	bool clientCanCacheRead;	/* read oplock */
+	bool clientCanCacheAll;		/* read and writebehind oplock */
+	bool delete_pending;		/* DELETE_ON_CLOSE is set */
+	bool invalid_mapping;		/* pagecache is invalid */
+	unsigned long time;		/* jiffies of last update of inode */
 	u64  server_eof;		/* current file size on server */
 	u64  uniqueid;			/* server inode number */
 	u64  createtime;		/* creation time on server */
@@ -508,6 +536,18 @@ static inline void cifs_stats_bytes_read(struct cifsTconInfo *tcon,
 
 #endif
 
+struct mid_q_entry;
+
+/*
+ * This is the prototype for the mid callback function. When creating one,
+ * take special care to avoid deadlocks. Things to bear in mind:
+ *
+ * - it will be called by cifsd
+ * - the GlobalMid_Lock will be held
+ * - the mid will be removed from the pending_mid_q list
+ */
+typedef void (mid_callback_t)(struct mid_q_entry *mid);
+
 /* one of these for every pending CIFS request to the server */
 struct mid_q_entry {
 	struct list_head qhead;	/* mids waiting on reply from this server */
@@ -519,7 +559,8 @@ struct mid_q_entry {
 	unsigned long when_sent; /* time when smb send finished */
 	unsigned long when_received; /* when demux complete (taken off wire) */
 #endif
-	struct task_struct *tsk;	/* task waiting for response */
+	mid_callback_t *callback; /* call completion callback */
+	void *callback_data;	  /* general purpose pointer for callback */
 	struct smb_hdr *resp_buf;	/* response buffer */
 	int midState;	/* wish this were enum but can not pass to wait_event */
 	__u8 command;	/* smb command code */
@@ -613,7 +654,7 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
 #define   MID_REQUEST_SUBMITTED 2
 #define   MID_RESPONSE_RECEIVED 4
 #define   MID_RETRY_NEEDED      8 /* session closed while this request out */
-#define   MID_NO_RESP_NEEDED 0x10
+#define   MID_RESPONSE_MALFORMED 0x10
 
 /* Types of response buffer returned from SendReceive2 */
 #define   CIFS_NO_BUFFER        0    /* Response buffer not returned */
@@ -622,12 +663,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
 #define   CIFS_IOVEC            4    /* array of response buffers */
 
 /* Type of Request to SendReceive2 */
-#define   CIFS_STD_OP	        0    /* normal request timeout */
-#define   CIFS_LONG_OP          1    /* long op (up to 45 sec, oplock time) */
-#define   CIFS_VLONG_OP         2    /* sloow op - can take up to 180 seconds */
-#define   CIFS_BLOCKING_OP      4    /* operation can block */
-#define   CIFS_ASYNC_OP         8    /* do not wait for response */
-#define   CIFS_TIMEOUT_MASK 0x00F    /* only one of 5 above set in req */
+#define   CIFS_BLOCKING_OP      1    /* operation can block */
+#define   CIFS_ASYNC_OP         2    /* do not wait for response */
+#define   CIFS_TIMEOUT_MASK 0x003    /* only one of above set in req */
 #define   CIFS_LOG_ERROR    0x010    /* log NT STATUS if non-zero */
 #define   CIFS_LARGE_BUF_OP 0x020    /* large request buffer */
 #define   CIFS_NO_RESP      0x040    /* no response buffer required */
@@ -790,6 +828,9 @@ GLOBAL_EXTERN unsigned int cifs_min_rcv;    /* min size of big ntwrk buf pool */
 GLOBAL_EXTERN unsigned int cifs_min_small;  /* min size of small buf pool */
 GLOBAL_EXTERN unsigned int cifs_max_pending; /* MAX requests at once to server*/
 
+/* reconnect after this many failed echo attempts */
+GLOBAL_EXTERN unsigned short echo_retries;
+
 void cifs_oplock_break(struct work_struct *work);
 void cifs_oplock_break_get(struct cifsFileInfo *cfile);
 void cifs_oplock_break_put(struct cifsFileInfo *cfile);
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index de36b09763a8..b5c8cc5d7a7f 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -23,6 +23,7 @@
 #define _CIFSPDU_H
 
 #include <net/sock.h>
+#include <asm/unaligned.h>
 #include "smbfsctl.h"
 
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
@@ -50,6 +51,7 @@
 #define SMB_COM_SETATTR               0x09 /* trivial response */
 #define SMB_COM_LOCKING_ANDX          0x24 /* trivial response */
 #define SMB_COM_COPY                  0x29 /* trivial rsp, fail filename ignrd*/
+#define SMB_COM_ECHO                  0x2B /* echo request */
 #define SMB_COM_OPEN_ANDX             0x2D /* Legacy open for old servers */
 #define SMB_COM_READ_ANDX             0x2E
 #define SMB_COM_WRITE_ANDX            0x2F
@@ -425,11 +427,49 @@ struct smb_hdr {
 	__u16 Mid;
 	__u8 WordCount;
 } __attribute__((packed));
-/* given a pointer to an smb_hdr retrieve the value of byte count */
-#define BCC(smb_var) (*(__u16 *)((char *)(smb_var) + sizeof(struct smb_hdr) + (2 * (smb_var)->WordCount)))
-#define BCC_LE(smb_var) (*(__le16 *)((char *)(smb_var) + sizeof(struct smb_hdr) + (2 * (smb_var)->WordCount)))
+
+/* given a pointer to an smb_hdr retrieve a char pointer to the byte count */
+#define BCC(smb_var) ((unsigned char *)(smb_var) + sizeof(struct smb_hdr) + \
+			 (2 * (smb_var)->WordCount))
+
 /* given a pointer to an smb_hdr retrieve the pointer to the byte area */
-#define pByteArea(smb_var) ((unsigned char *)(smb_var) + sizeof(struct smb_hdr) + (2 * (smb_var)->WordCount) + 2)
+#define pByteArea(smb_var) (BCC(smb_var) + 2)
+
+/* get the converted ByteCount for a SMB packet and return it */
+static inline __u16
+get_bcc(struct smb_hdr *hdr)
+{
+	__u16 *bc_ptr = (__u16 *)BCC(hdr);
+
+	return get_unaligned(bc_ptr);
+}
+
+/* get the unconverted ByteCount for a SMB packet and return it */
+static inline __u16
+get_bcc_le(struct smb_hdr *hdr)
+{
+	__le16 *bc_ptr = (__le16 *)BCC(hdr);
+
+	return get_unaligned_le16(bc_ptr);
+}
+
+/* set the ByteCount for a SMB packet in host-byte order */
+static inline void
+put_bcc(__u16 count, struct smb_hdr *hdr)
+{
+	__u16 *bc_ptr = (__u16 *)BCC(hdr);
+
+	put_unaligned(count, bc_ptr);
+}
+
+/* set the ByteCount for a SMB packet in little-endian */
+static inline void
+put_bcc_le(__u16 count, struct smb_hdr *hdr)
+{
+	__le16 *bc_ptr = (__le16 *)BCC(hdr);
+
+	put_unaligned_le16(count, bc_ptr);
+}
 
 /*
  * Computer Name Length (since Netbios name was length 16 with last byte 0x20)
@@ -760,6 +800,20 @@ typedef struct smb_com_tconx_rsp_ext {
  *
  */
 
+typedef struct smb_com_echo_req {
+	struct	smb_hdr hdr;
+	__le16	EchoCount;
+	__le16	ByteCount;
+	char	Data[1];
+} __attribute__((packed)) ECHO_REQ;
+
+typedef struct smb_com_echo_rsp {
+	struct	smb_hdr hdr;
+	__le16	SequenceNumber;
+	__le16	ByteCount;
+	char	Data[1];
+} __attribute__((packed)) ECHO_RSP;
+
 typedef struct smb_com_logoff_andx_req {
 	struct smb_hdr hdr;	/* wct = 2 */
 	__u8 AndXCommand;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index e6d1481b16c1..8096f27ad9a8 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -61,6 +61,12 @@ extern char *cifs_compose_mount_options(const char *sb_mountdata,
 		const char *fullpath, const struct dfs_info3_param *ref,
 		char **devname);
 /* extern void renew_parental_timestamps(struct dentry *direntry);*/
+extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer,
+					struct TCP_Server_Info *server);
+extern void DeleteMidQEntry(struct mid_q_entry *midEntry);
+extern int cifs_call_async(struct TCP_Server_Info *server,
+			   struct smb_hdr *in_buf, mid_callback_t *callback,
+			   void *cbdata);
 extern int SendReceive(const unsigned int /* xid */ , struct cifsSesInfo *,
 			struct smb_hdr * /* input */ ,
 			struct smb_hdr * /* out */ ,
@@ -79,6 +85,8 @@ extern int checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length);
 extern bool is_valid_oplock_break(struct smb_hdr *smb,
 				  struct TCP_Server_Info *);
 extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof);
+extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
+			    unsigned int bytes_written);
 extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, bool);
 extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool);
 extern unsigned int smbCalcSize(struct smb_hdr *ptr);
@@ -347,12 +355,13 @@ extern int CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
 			const __u16 netfid, const __u64 len,
 			const __u64 offset, const __u32 numUnlock,
 			const __u32 numLock, const __u8 lockType,
-			const bool waitFlag);
+			const bool waitFlag, const __u8 oplock_level);
 extern int CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon,
 			const __u16 smb_file_id, const int get_flag,
 			const __u64 len, struct file_lock *,
 			const __u16 lock_type, const bool waitFlag);
 extern int CIFSSMBTDis(const int xid, struct cifsTconInfo *tcon);
+extern int CIFSSMBEcho(struct TCP_Server_Info *server);
 extern int CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses);
 
 extern struct cifsSesInfo *sesInfoAlloc(void);
@@ -366,7 +375,7 @@ extern int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *,
 extern int cifs_verify_signature(struct smb_hdr *,
 				 struct TCP_Server_Info *server,
 				__u32 expected_sequence_number);
-extern void SMBNTencrypt(unsigned char *, unsigned char *, unsigned char *);
+extern int SMBNTencrypt(unsigned char *, unsigned char *, unsigned char *);
 extern int setup_ntlm_response(struct cifsSesInfo *);
 extern int setup_ntlmv2_rsp(struct cifsSesInfo *, const struct nls_table *);
 extern int cifs_crypto_shash_allocate(struct TCP_Server_Info *);
@@ -416,4 +425,11 @@ extern bool CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr);
 extern int CIFSCheckMFSymlink(struct cifs_fattr *fattr,
 		const unsigned char *path,
 		struct cifs_sb_info *cifs_sb, int xid);
+extern int mdfour(unsigned char *, unsigned char *, int);
+extern int E_md4hash(const unsigned char *passwd, unsigned char *p16);
+extern void SMBencrypt(unsigned char *passwd, const unsigned char *c8,
+			unsigned char *p24);
+extern void E_P16(unsigned char *p14, unsigned char *p16);
+extern void E_P24(unsigned char *p21, const unsigned char *c8,
+			unsigned char *p24);
 #endif			/* _CIFSPROTO_H */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 2f6795e524d3..904aa47e3515 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -136,9 +136,6 @@ cifs_reconnect_tcon(struct cifsTconInfo *tcon, int smb_command)
 		}
 	}
 
-	if (ses->status == CifsExiting)
-		return -EIO;
-
 	/*
 	 * Give demultiplex thread up to 10 seconds to reconnect, should be
 	 * greater than cifs socket timeout which is 7 seconds
@@ -156,7 +153,7 @@ cifs_reconnect_tcon(struct cifsTconInfo *tcon, int smb_command)
 		 * retrying until process is killed or server comes
 		 * back on-line
 		 */
-		if (!tcon->retry || ses->status == CifsExiting) {
+		if (!tcon->retry) {
 			cFYI(1, "gave up waiting on reconnect in smb_init");
 			return -EHOSTDOWN;
 		}
@@ -331,37 +328,35 @@ smb_init_no_reconnect(int smb_command, int wct, struct cifsTconInfo *tcon,
 
 static int validate_t2(struct smb_t2_rsp *pSMB)
 {
-	int rc = -EINVAL;
-	int total_size;
-	char *pBCC;
+	unsigned int total_size;
+
+	/* check for plausible wct */
+	if (pSMB->hdr.WordCount < 10)
+		goto vt2_err;
 
-	/* check for plausible wct, bcc and t2 data and parm sizes */
 	/* check for parm and data offset going beyond end of smb */
-	if (pSMB->hdr.WordCount >= 10) {
-		if ((le16_to_cpu(pSMB->t2_rsp.ParameterOffset) <= 1024) &&
-		   (le16_to_cpu(pSMB->t2_rsp.DataOffset) <= 1024)) {
-			/* check that bcc is at least as big as parms + data */
-			/* check that bcc is less than negotiated smb buffer */
-			total_size = le16_to_cpu(pSMB->t2_rsp.ParameterCount);
-			if (total_size < 512) {
-				total_size +=
-					le16_to_cpu(pSMB->t2_rsp.DataCount);
-				/* BCC le converted in SendReceive */
-				pBCC = (pSMB->hdr.WordCount * 2) +
-					sizeof(struct smb_hdr) +
-					(char *)pSMB;
-				if ((total_size <= (*(u16 *)pBCC)) &&
-				   (total_size <
-					CIFSMaxBufSize+MAX_CIFS_HDR_SIZE)) {
-					return 0;
-				}
-			}
-		}
-	}
+	if (get_unaligned_le16(&pSMB->t2_rsp.ParameterOffset) > 1024 ||
+	    get_unaligned_le16(&pSMB->t2_rsp.DataOffset) > 1024)
+		goto vt2_err;
+
+	/* check that bcc is at least as big as parms + data */
+	/* check that bcc is less than negotiated smb buffer */
+	total_size = get_unaligned_le16(&pSMB->t2_rsp.ParameterCount);
+	if (total_size >= 512)
+		goto vt2_err;
+
+	total_size += get_unaligned_le16(&pSMB->t2_rsp.DataCount);
+	if (total_size > get_bcc(&pSMB->hdr) ||
+	    total_size >= CIFSMaxBufSize + MAX_CIFS_HDR_SIZE)
+		goto vt2_err;
+
+	return 0;
+vt2_err:
 	cifs_dump_mem("Invalid transact2 SMB: ", (char *)pSMB,
 		sizeof(struct smb_t2_rsp) + 16);
-	return rc;
+	return -EINVAL;
 }
+
 int
 CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 {
@@ -452,7 +447,6 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 		server->maxBuf = min((__u32)le16_to_cpu(rsp->MaxBufSize),
 				(__u32)CIFSMaxBufSize + MAX_CIFS_HDR_SIZE);
 		server->max_vcs = le16_to_cpu(rsp->MaxNumberVcs);
-		GETU32(server->sessid) = le32_to_cpu(rsp->SessionKey);
 		/* even though we do not use raw we might as well set this
 		accurately, in case we ever find a need for it */
 		if ((le16_to_cpu(rsp->RawMode) & RAW_ENABLE) == RAW_ENABLE) {
@@ -566,7 +560,6 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 			(__u32) CIFSMaxBufSize + MAX_CIFS_HDR_SIZE);
 	server->max_rw = le32_to_cpu(pSMBr->MaxRawSize);
 	cFYI(DBG2, "Max buf = %d", ses->server->maxBuf);
-	GETU32(ses->server->sessid) = le32_to_cpu(pSMBr->SessionKey);
 	server->capabilities = le32_to_cpu(pSMBr->Capabilities);
 	server->timeAdj = (int)(__s16)le16_to_cpu(pSMBr->ServerTimeZone);
 	server->timeAdj *= 60;
@@ -706,6 +699,53 @@ CIFSSMBTDis(const int xid, struct cifsTconInfo *tcon)
 	return rc;
 }
 
+/*
+ * This is a no-op for now. We're not really interested in the reply, but
+ * rather in the fact that the server sent one and that server->lstrp
+ * gets updated.
+ *
+ * FIXME: maybe we should consider checking that the reply matches request?
+ */
+static void
+cifs_echo_callback(struct mid_q_entry *mid)
+{
+	struct TCP_Server_Info *server = mid->callback_data;
+
+	DeleteMidQEntry(mid);
+	atomic_dec(&server->inFlight);
+	wake_up(&server->request_q);
+}
+
+int
+CIFSSMBEcho(struct TCP_Server_Info *server)
+{
+	ECHO_REQ *smb;
+	int rc = 0;
+
+	cFYI(1, "In echo request");
+
+	rc = small_smb_init(SMB_COM_ECHO, 0, NULL, (void **)&smb);
+	if (rc)
+		return rc;
+
+	/* set up echo request */
+	smb->hdr.Tid = cpu_to_le16(0xffff);
+	smb->hdr.WordCount = 1;
+	put_unaligned_le16(1, &smb->EchoCount);
+	put_bcc_le(1, &smb->hdr);
+	smb->Data[0] = 'a';
+	smb->hdr.smb_buf_length += 3;
+
+	rc = cifs_call_async(server, (struct smb_hdr *)smb,
+				cifs_echo_callback, server);
+	if (rc)
+		cFYI(1, "Echo request failed: %d", rc);
+
+	cifs_small_buf_release(smb);
+
+	return rc;
+}
+
 int
 CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses)
 {
@@ -1193,7 +1233,7 @@ OldOpenRetry:
 	pSMB->ByteCount = cpu_to_le16(count);
 	/* long_op set to 1 to allow for oplock break timeouts */
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
-			(struct smb_hdr *)pSMBr, &bytes_returned, CIFS_LONG_OP);
+			(struct smb_hdr *)pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_opens);
 	if (rc) {
 		cFYI(1, "Error in Open = %d", rc);
@@ -1306,7 +1346,7 @@ openRetry:
 	pSMB->ByteCount = cpu_to_le16(count);
 	/* long_op set to 1 to allow for oplock break timeouts */
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
-			(struct smb_hdr *)pSMBr, &bytes_returned, CIFS_LONG_OP);
+			(struct smb_hdr *)pSMBr, &bytes_returned, 0);
 	cifs_stats_inc(&tcon->num_opens);
 	if (rc) {
 		cFYI(1, "Error in Open = %d", rc);
@@ -1388,7 +1428,7 @@ CIFSSMBRead(const int xid, struct cifsTconInfo *tcon, const int netfid,
 	iov[0].iov_base = (char *)pSMB;
 	iov[0].iov_len = pSMB->hdr.smb_buf_length + 4;
 	rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovecs */,
-			 &resp_buf_type, CIFS_STD_OP | CIFS_LOG_ERROR);
+			 &resp_buf_type, CIFS_LOG_ERROR);
 	cifs_stats_inc(&tcon->num_reads);
 	pSMBr = (READ_RSP *)iov[0].iov_base;
 	if (rc) {
@@ -1663,7 +1703,8 @@ int
 CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
 	    const __u16 smb_file_id, const __u64 len,
 	    const __u64 offset, const __u32 numUnlock,
-	    const __u32 numLock, const __u8 lockType, const bool waitFlag)
+	    const __u32 numLock, const __u8 lockType,
+	    const bool waitFlag, const __u8 oplock_level)
 {
 	int rc = 0;
 	LOCK_REQ *pSMB = NULL;
@@ -1691,6 +1732,7 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
 	pSMB->NumberOfLocks = cpu_to_le16(numLock);
 	pSMB->NumberOfUnlocks = cpu_to_le16(numUnlock);
 	pSMB->LockType = lockType;
+	pSMB->OplockLevel = oplock_level;
 	pSMB->AndXCommand = 0xFF;	/* none */
 	pSMB->Fid = smb_file_id; /* netfid stays le */
 
@@ -3087,7 +3129,7 @@ CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid,
 	iov[0].iov_len = pSMB->hdr.smb_buf_length + 4;
 
 	rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovec */, &buf_type,
-			 CIFS_STD_OP);
+			 0);
 	cifs_stats_inc(&tcon->num_acl_get);
 	if (rc) {
 		cFYI(1, "Send error in QuerySecDesc = %d", rc);
@@ -4869,7 +4911,6 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size,
 		   __u16 fid, __u32 pid_of_opener, bool SetAllocation)
 {
 	struct smb_com_transaction2_sfi_req *pSMB  = NULL;
-	char *data_offset;
 	struct file_end_of_file_info *parm_data;
 	int rc = 0;
 	__u16 params, param_offset, offset, byte_count, count;
@@ -4893,8 +4934,6 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size,
 	param_offset = offsetof(struct smb_com_transaction2_sfi_req, Fid) - 4;
 	offset = param_offset + params;
 
-	data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
-
 	count = sizeof(struct file_end_of_file_info);
 	pSMB->MaxParameterCount = cpu_to_le16(2);
 	/* BB find exact max SMB PDU from sess structure BB */
@@ -5562,7 +5601,7 @@ QAllEAsRetry:
 	}
 
 	/* make sure list_len doesn't go past end of SMB */
-	end_of_smb = (char *)pByteArea(&pSMBr->hdr) + BCC(&pSMBr->hdr);
+	end_of_smb = (char *)pByteArea(&pSMBr->hdr) + get_bcc(&pSMBr->hdr);
 	if ((char *)ea_response_data + list_len > end_of_smb) {
 		cFYI(1, "EA list appears to go beyond SMB");
 		rc = -EIO;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a65d311d163a..8d6c17ab593d 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -52,8 +52,8 @@
 #define CIFS_PORT 445
 #define RFC1001_PORT 139
 
-extern void SMBNTencrypt(unsigned char *passwd, unsigned char *c8,
-			 unsigned char *p24);
+/* SMB echo "timeout" -- FIXME: tunable? */
+#define SMB_ECHO_INTERVAL (60 * HZ)
 
 extern mempool_t *cifs_req_poolp;
 
@@ -84,6 +84,7 @@ struct smb_vol {
 	bool no_xattr:1;   /* set if xattr (EA) support should be disabled*/
 	bool server_ino:1; /* use inode numbers from server ie UniqueId */
 	bool direct_io:1;
+	bool strict_io:1; /* strict cache behavior */
 	bool remap:1;      /* set to remap seven reserved chars in filenames */
 	bool posix_paths:1; /* unset to not ask for posix pathnames. */
 	bool no_linux_ext:1;
@@ -152,6 +153,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 
 	/* before reconnecting the tcp session, mark the smb session (uid)
 		and the tid bad so they are not used until reconnected */
+	cFYI(1, "%s: marking sessions and tcons for reconnect", __func__);
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &server->smb_ses_list) {
 		ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list);
@@ -163,7 +165,9 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		}
 	}
 	spin_unlock(&cifs_tcp_ses_lock);
+
 	/* do not want to be sending data on a socket we are freeing */
+	cFYI(1, "%s: tearing down socket", __func__);
 	mutex_lock(&server->srv_mutex);
 	if (server->ssocket) {
 		cFYI(1, "State: 0x%x Flags: 0x%lx", server->ssocket->state,
@@ -180,22 +184,20 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	kfree(server->session_key.response);
 	server->session_key.response = NULL;
 	server->session_key.len = 0;
+	server->lstrp = jiffies;
+	mutex_unlock(&server->srv_mutex);
 
+	/* mark submitted MIDs for retry and issue callback */
+	cFYI(1, "%s: issuing mid callbacks", __func__);
 	spin_lock(&GlobalMid_Lock);
-	list_for_each(tmp, &server->pending_mid_q) {
-		mid_entry = list_entry(tmp, struct
-					mid_q_entry,
-					qhead);
-		if (mid_entry->midState == MID_REQUEST_SUBMITTED) {
-				/* Mark other intransit requests as needing
-				   retry so we do not immediately mark the
-				   session bad again (ie after we reconnect
-				   below) as they timeout too */
+	list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
+		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
+		if (mid_entry->midState == MID_REQUEST_SUBMITTED)
 			mid_entry->midState = MID_RETRY_NEEDED;
-		}
+		list_del_init(&mid_entry->qhead);
+		mid_entry->callback(mid_entry);
 	}
 	spin_unlock(&GlobalMid_Lock);
-	mutex_unlock(&server->srv_mutex);
 
 	while ((server->tcpStatus != CifsExiting) &&
 	       (server->tcpStatus != CifsGood)) {
@@ -212,10 +214,9 @@ cifs_reconnect(struct TCP_Server_Info *server)
 			if (server->tcpStatus != CifsExiting)
 				server->tcpStatus = CifsGood;
 			spin_unlock(&GlobalMid_Lock);
-	/*		atomic_set(&server->inFlight,0);*/
-			wake_up(&server->response_q);
 		}
 	}
+
 	return rc;
 }
 
@@ -229,9 +230,8 @@ cifs_reconnect(struct TCP_Server_Info *server)
 static int check2ndT2(struct smb_hdr *pSMB, unsigned int maxBufSize)
 {
 	struct smb_t2_rsp *pSMBt;
-	int total_data_size;
-	int data_in_this_rsp;
 	int remaining;
+	__u16 total_data_size, data_in_this_rsp;
 
 	if (pSMB->Command != SMB_COM_TRANSACTION2)
 		return 0;
@@ -245,8 +245,8 @@ static int check2ndT2(struct smb_hdr *pSMB, unsigned int maxBufSize)
 
 	pSMBt = (struct smb_t2_rsp *)pSMB;
 
-	total_data_size = le16_to_cpu(pSMBt->t2_rsp.TotalDataCount);
-	data_in_this_rsp = le16_to_cpu(pSMBt->t2_rsp.DataCount);
+	total_data_size = get_unaligned_le16(&pSMBt->t2_rsp.TotalDataCount);
+	data_in_this_rsp = get_unaligned_le16(&pSMBt->t2_rsp.DataCount);
 
 	remaining = total_data_size - data_in_this_rsp;
 
@@ -272,21 +272,18 @@ static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB)
 {
 	struct smb_t2_rsp *pSMB2 = (struct smb_t2_rsp *)psecond;
 	struct smb_t2_rsp *pSMBt  = (struct smb_t2_rsp *)pTargetSMB;
-	int total_data_size;
-	int total_in_buf;
-	int remaining;
-	int total_in_buf2;
 	char *data_area_of_target;
 	char *data_area_of_buf2;
-	__u16 byte_count;
+	int remaining;
+	__u16 byte_count, total_data_size, total_in_buf, total_in_buf2;
 
-	total_data_size = le16_to_cpu(pSMBt->t2_rsp.TotalDataCount);
+	total_data_size = get_unaligned_le16(&pSMBt->t2_rsp.TotalDataCount);
 
-	if (total_data_size != le16_to_cpu(pSMB2->t2_rsp.TotalDataCount)) {
+	if (total_data_size !=
+	    get_unaligned_le16(&pSMB2->t2_rsp.TotalDataCount))
 		cFYI(1, "total data size of primary and secondary t2 differ");
-	}
 
-	total_in_buf = le16_to_cpu(pSMBt->t2_rsp.DataCount);
+	total_in_buf = get_unaligned_le16(&pSMBt->t2_rsp.DataCount);
 
 	remaining = total_data_size - total_in_buf;
 
@@ -296,28 +293,28 @@ static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB)
 	if (remaining == 0) /* nothing to do, ignore */
 		return 0;
 
-	total_in_buf2 = le16_to_cpu(pSMB2->t2_rsp.DataCount);
+	total_in_buf2 = get_unaligned_le16(&pSMB2->t2_rsp.DataCount);
 	if (remaining < total_in_buf2) {
 		cFYI(1, "transact2 2nd response contains too much data");
 	}
 
 	/* find end of first SMB data area */
 	data_area_of_target = (char *)&pSMBt->hdr.Protocol +
-				le16_to_cpu(pSMBt->t2_rsp.DataOffset);
+				get_unaligned_le16(&pSMBt->t2_rsp.DataOffset);
 	/* validate target area */
 
-	data_area_of_buf2 = (char *) &pSMB2->hdr.Protocol +
-					le16_to_cpu(pSMB2->t2_rsp.DataOffset);
+	data_area_of_buf2 = (char *)&pSMB2->hdr.Protocol +
+				get_unaligned_le16(&pSMB2->t2_rsp.DataOffset);
 
 	data_area_of_target += total_in_buf;
 
 	/* copy second buffer into end of first buffer */
 	memcpy(data_area_of_target, data_area_of_buf2, total_in_buf2);
 	total_in_buf += total_in_buf2;
-	pSMBt->t2_rsp.DataCount = cpu_to_le16(total_in_buf);
-	byte_count = le16_to_cpu(BCC_LE(pTargetSMB));
+	put_unaligned_le16(total_in_buf, &pSMBt->t2_rsp.DataCount);
+	byte_count = get_bcc_le(pTargetSMB);
 	byte_count += total_in_buf2;
-	BCC_LE(pTargetSMB) = cpu_to_le16(byte_count);
+	put_bcc_le(byte_count, pTargetSMB);
 
 	byte_count = pTargetSMB->smb_buf_length;
 	byte_count += total_in_buf2;
@@ -331,7 +328,31 @@ static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB)
 		return 0; /* we are done */
 	} else /* more responses to go */
 		return 1;
+}
+
+static void
+cifs_echo_request(struct work_struct *work)
+{
+	int rc;
+	struct TCP_Server_Info *server = container_of(work,
+					struct TCP_Server_Info, echo.work);
+
+	/*
+	 * We cannot send an echo until the NEGOTIATE_PROTOCOL request is
+	 * done, which is indicated by maxBuf != 0. Also, no need to ping if
+	 * we got a response recently
+	 */
+	if (server->maxBuf == 0 ||
+	    time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
+		goto requeue_echo;
+
+	rc = CIFSSMBEcho(server);
+	if (rc)
+		cFYI(1, "Unable to send echo request to server: %s",
+			server->hostname);
 
+requeue_echo:
+	queue_delayed_work(system_nrt_wq, &server->echo, SMB_ECHO_INTERVAL);
 }
 
 static int
@@ -345,8 +366,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server)
 	struct msghdr smb_msg;
 	struct kvec iov;
 	struct socket *csocket = server->ssocket;
-	struct list_head *tmp;
-	struct cifsSesInfo *ses;
+	struct list_head *tmp, *tmp2;
 	struct task_struct *task_to_wake = NULL;
 	struct mid_q_entry *mid_entry;
 	char temp;
@@ -399,7 +419,20 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server)
 		smb_msg.msg_control = NULL;
 		smb_msg.msg_controllen = 0;
 		pdu_length = 4; /* enough to get RFC1001 header */
+
 incomplete_rcv:
+		if (echo_retries > 0 &&
+		    time_after(jiffies, server->lstrp +
+					(echo_retries * SMB_ECHO_INTERVAL))) {
+			cERROR(1, "Server %s has not responded in %d seconds. "
+				  "Reconnecting...", server->hostname,
+				  (echo_retries * SMB_ECHO_INTERVAL / HZ));
+			cifs_reconnect(server);
+			csocket = server->ssocket;
+			wake_up(&server->response_q);
+			continue;
+		}
+
 		length =
 		    kernel_recvmsg(csocket, &smb_msg,
 				&iov, 1, pdu_length, 0 /* BB other flags? */);
@@ -550,25 +583,36 @@ incomplete_rcv:
 		else if (reconnect == 1)
 			continue;
 
-		length += 4; /* account for rfc1002 hdr */
+		total_read += 4; /* account for rfc1002 hdr */
 
+		dump_smb(smb_buffer, total_read);
 
-		dump_smb(smb_buffer, length);
-		if (checkSMB(smb_buffer, smb_buffer->Mid, total_read+4)) {
-			cifs_dump_mem("Bad SMB: ", smb_buffer, 48);
-			continue;
-		}
+		/*
+		 * We know that we received enough to get to the MID as we
+		 * checked the pdu_length earlier. Now check to see
+		 * if the rest of the header is OK. We borrow the length
+		 * var for the rest of the loop to avoid a new stack var.
+		 *
+		 * 48 bytes is enough to display the header and a little bit
+		 * into the payload for debugging purposes.
+		 */
+		length = checkSMB(smb_buffer, smb_buffer->Mid, total_read);
+		if (length != 0)
+			cifs_dump_mem("Bad SMB: ", smb_buffer,
+					min_t(unsigned int, total_read, 48));
 
+		mid_entry = NULL;
+		server->lstrp = jiffies;
 
-		task_to_wake = NULL;
 		spin_lock(&GlobalMid_Lock);
-		list_for_each(tmp, &server->pending_mid_q) {
+		list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
 			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
 
 			if ((mid_entry->mid == smb_buffer->Mid) &&
 			    (mid_entry->midState == MID_REQUEST_SUBMITTED) &&
 			    (mid_entry->command == smb_buffer->Command)) {
-				if (check2ndT2(smb_buffer,server->maxBuf) > 0) {
+				if (length == 0 &&
+				   check2ndT2(smb_buffer, server->maxBuf) > 0) {
 					/* We have a multipart transact2 resp */
 					isMultiRsp = true;
 					if (mid_entry->resp_buf) {
@@ -603,20 +647,24 @@ incomplete_rcv:
 				mid_entry->resp_buf = smb_buffer;
 				mid_entry->largeBuf = isLargeBuf;
 multi_t2_fnd:
-				task_to_wake = mid_entry->tsk;
-				mid_entry->midState = MID_RESPONSE_RECEIVED;
+				if (length == 0)
+					mid_entry->midState =
+							MID_RESPONSE_RECEIVED;
+				else
+					mid_entry->midState =
+							MID_RESPONSE_MALFORMED;
 #ifdef CONFIG_CIFS_STATS2
 				mid_entry->when_received = jiffies;
 #endif
-				/* so we do not time out requests to  server
-				which is still responding (since server could
-				be busy but not dead) */
-				server->lstrp = jiffies;
+				list_del_init(&mid_entry->qhead);
+				mid_entry->callback(mid_entry);
 				break;
 			}
+			mid_entry = NULL;
 		}
 		spin_unlock(&GlobalMid_Lock);
-		if (task_to_wake) {
+
+		if (mid_entry != NULL) {
 			/* Was previous buf put in mpx struct for multi-rsp? */
 			if (!isMultiRsp) {
 				/* smb buffer will be freed by user thread */
@@ -625,11 +673,13 @@ multi_t2_fnd:
 				else
 					smallbuf = NULL;
 			}
-			wake_up_process(task_to_wake);
+		} else if (length != 0) {
+			/* response sanity checks failed */
+			continue;
 		} else if (!is_valid_oplock_break(smb_buffer, server) &&
 			   !isMultiRsp) {
 			cERROR(1, "No task to wake, unknown frame received! "
-				   "NumMids %d", midCount.counter);
+				   "NumMids %d", atomic_read(&midCount));
 			cifs_dump_mem("Received Data is: ", (char *)smb_buffer,
 				      sizeof(struct smb_hdr));
 #ifdef CONFIG_CIFS_DEBUG2
@@ -677,44 +727,16 @@ multi_t2_fnd:
 	if (smallbuf) /* no sense logging a debug message if NULL */
 		cifs_small_buf_release(smallbuf);
 
-	/*
-	 * BB: we shouldn't have to do any of this. It shouldn't be
-	 * possible to exit from the thread with active SMB sessions
-	 */
-	spin_lock(&cifs_tcp_ses_lock);
-	if (list_empty(&server->pending_mid_q)) {
-		/* loop through server session structures attached to this and
-		    mark them dead */
-		list_for_each(tmp, &server->smb_ses_list) {
-			ses = list_entry(tmp, struct cifsSesInfo,
-					 smb_ses_list);
-			ses->status = CifsExiting;
-			ses->server = NULL;
-		}
-		spin_unlock(&cifs_tcp_ses_lock);
-	} else {
-		/* although we can not zero the server struct pointer yet,
-		since there are active requests which may depnd on them,
-		mark the corresponding SMB sessions as exiting too */
-		list_for_each(tmp, &server->smb_ses_list) {
-			ses = list_entry(tmp, struct cifsSesInfo,
-					 smb_ses_list);
-			ses->status = CifsExiting;
-		}
-
+	if (!list_empty(&server->pending_mid_q)) {
 		spin_lock(&GlobalMid_Lock);
-		list_for_each(tmp, &server->pending_mid_q) {
-		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-			if (mid_entry->midState == MID_REQUEST_SUBMITTED) {
-				cFYI(1, "Clearing Mid 0x%x - waking up ",
+		list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
+			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
+			cFYI(1, "Clearing Mid 0x%x - issuing callback",
 					 mid_entry->mid);
-				task_to_wake = mid_entry->tsk;
-				if (task_to_wake)
-					wake_up_process(task_to_wake);
-			}
+			list_del_init(&mid_entry->qhead);
+			mid_entry->callback(mid_entry);
 		}
 		spin_unlock(&GlobalMid_Lock);
-		spin_unlock(&cifs_tcp_ses_lock);
 		/* 1/8th of sec is more than enough time for them to exit */
 		msleep(125);
 	}
@@ -732,18 +754,6 @@ multi_t2_fnd:
 		coming home not much else we can do but free the memory */
 	}
 
-	/* last chance to mark ses pointers invalid
-	if there are any pointing to this (e.g
-	if a crazy root user tried to kill cifsd
-	kernel thread explicitly this might happen) */
-	/* BB: This shouldn't be necessary, see above */
-	spin_lock(&cifs_tcp_ses_lock);
-	list_for_each(tmp, &server->smb_ses_list) {
-		ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list);
-		ses->server = NULL;
-	}
-	spin_unlock(&cifs_tcp_ses_lock);
-
 	kfree(server->hostname);
 	task_to_wake = xchg(&server->tsk, NULL);
 	kfree(server);
@@ -1113,6 +1123,8 @@ cifs_parse_mount_options(char *options, const char *devname,
 		} else if (!strnicmp(data, "uid", 3) && value && *value) {
 			vol->linux_uid = simple_strtoul(value, &value, 0);
 			uid_specified = true;
+		} else if (!strnicmp(data, "cruid", 5) && value && *value) {
+			vol->cred_uid = simple_strtoul(value, &value, 0);
 		} else if (!strnicmp(data, "forceuid", 8)) {
 			override_uid = 1;
 		} else if (!strnicmp(data, "noforceuid", 10)) {
@@ -1353,6 +1365,8 @@ cifs_parse_mount_options(char *options, const char *devname,
 			vol->direct_io = 1;
 		} else if (strnicmp(data, "forcedirectio", 13) == 0) {
 			vol->direct_io = 1;
+		} else if (strnicmp(data, "strictcache", 11) == 0) {
+			vol->strict_io = 1;
 		} else if (strnicmp(data, "noac", 4) == 0) {
 			printk(KERN_WARNING "CIFS: Mount option noac not "
 				"supported. Instead set "
@@ -1577,6 +1591,9 @@ cifs_find_tcp_session(struct sockaddr *addr, struct smb_vol *vol)
 
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
+		if (!net_eq(cifs_net_ns(server), current->nsproxy->net_ns))
+			continue;
+
 		if (!match_address(server, addr,
 				   (struct sockaddr *)&vol->srcaddr))
 			continue;
@@ -1607,9 +1624,13 @@ cifs_put_tcp_session(struct TCP_Server_Info *server)
 		return;
 	}
 
+	put_net(cifs_net_ns(server));
+
 	list_del_init(&server->tcp_ses_list);
 	spin_unlock(&cifs_tcp_ses_lock);
 
+	cancel_delayed_work_sync(&server->echo);
+
 	spin_lock(&GlobalMid_Lock);
 	server->tcpStatus = CifsExiting;
 	spin_unlock(&GlobalMid_Lock);
@@ -1679,6 +1700,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 		goto out_err;
 	}
 
+	cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns));
 	tcp_ses->hostname = extract_hostname(volume_info->UNC);
 	if (IS_ERR(tcp_ses->hostname)) {
 		rc = PTR_ERR(tcp_ses->hostname);
@@ -1699,8 +1721,10 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 		volume_info->target_rfc1001_name, RFC1001_NAME_LEN_WITH_NULL);
 	tcp_ses->session_estab = false;
 	tcp_ses->sequence_number = 0;
+	tcp_ses->lstrp = jiffies;
 	INIT_LIST_HEAD(&tcp_ses->tcp_ses_list);
 	INIT_LIST_HEAD(&tcp_ses->smb_ses_list);
+	INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request);
 
 	/*
 	 * at this point we are the only ones with the pointer
@@ -1749,11 +1773,16 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 
 	cifs_fscache_get_client_cookie(tcp_ses);
 
+	/* queue echo request delayed work */
+	queue_delayed_work(system_nrt_wq, &tcp_ses->echo, SMB_ECHO_INTERVAL);
+
 	return tcp_ses;
 
 out_err_crypto_release:
 	cifs_crypto_shash_release(tcp_ses);
 
+	put_net(cifs_net_ns(tcp_ses));
+
 out_err:
 	if (tcp_ses) {
 		if (!IS_ERR(tcp_ses->hostname))
@@ -2265,8 +2294,8 @@ generic_ip_connect(struct TCP_Server_Info *server)
 	}
 
 	if (socket == NULL) {
-		rc = sock_create_kern(sfamily, SOCK_STREAM,
-				      IPPROTO_TCP, &socket);
+		rc = __sock_create(cifs_net_ns(server), sfamily, SOCK_STREAM,
+				   IPPROTO_TCP, &socket, 1);
 		if (rc < 0) {
 			cERROR(1, "Error %d creating socket", rc);
 			server->ssocket = NULL;
@@ -2578,6 +2607,8 @@ static void setup_cifs_sb(struct smb_vol *pvolume_info,
 	if (pvolume_info->multiuser)
 		cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_MULTIUSER |
 					    CIFS_MOUNT_NO_PERM);
+	if (pvolume_info->strict_io)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_STRICT_IO;
 	if (pvolume_info->direct_io) {
 		cFYI(1, "mounting share using direct i/o");
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO;
@@ -2934,8 +2965,8 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 	TCONX_RSP *pSMBr;
 	unsigned char *bcc_ptr;
 	int rc = 0;
-	int length, bytes_left;
-	__u16 count;
+	int length;
+	__u16 bytes_left, count;
 
 	if (ses == NULL)
 		return -EIO;
@@ -2963,7 +2994,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 		bcc_ptr++;              /* skip password */
 		/* already aligned so no need to do it below */
 	} else {
-		pSMB->PasswordLength = cpu_to_le16(CIFS_SESS_KEY_SIZE);
+		pSMB->PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE);
 		/* BB FIXME add code to fail this if NTLMv2 or Kerberos
 		   specified as required (when that support is added to
 		   the vfs in the future) as only NTLM or the much
@@ -2979,9 +3010,10 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 					 bcc_ptr);
 		else
 #endif /* CIFS_WEAK_PW_HASH */
-		SMBNTencrypt(tcon->password, ses->server->cryptkey, bcc_ptr);
+		rc = SMBNTencrypt(tcon->password, ses->server->cryptkey,
+					bcc_ptr);
 
-		bcc_ptr += CIFS_SESS_KEY_SIZE;
+		bcc_ptr += CIFS_AUTH_RESP_SIZE;
 		if (ses->capabilities & CAP_UNICODE) {
 			/* must align unicode strings */
 			*bcc_ptr = 0; /* null byte password */
@@ -3019,7 +3051,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 	pSMB->ByteCount = cpu_to_le16(count);
 
 	rc = SendReceive(xid, ses, smb_buffer, smb_buffer_response, &length,
-			 CIFS_STD_OP);
+			 0);
 
 	/* above now done in SendReceive */
 	if ((rc == 0) && (tcon != NULL)) {
@@ -3029,7 +3061,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 		tcon->need_reconnect = false;
 		tcon->tid = smb_buffer_response->Tid;
 		bcc_ptr = pByteArea(smb_buffer_response);
-		bytes_left = BCC(smb_buffer_response);
+		bytes_left = get_bcc(smb_buffer_response);
 		length = strnlen(bcc_ptr, bytes_left - 2);
 		if (smb_buffer->Flags2 & SMBFLG2_UNICODE)
 			is_unicode = true;
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 1e95dd635632..dd5f22918c33 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -675,6 +675,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
 
 const struct dentry_operations cifs_dentry_ops = {
 	.d_revalidate = cifs_d_revalidate,
+	.d_automount = cifs_dfs_d_automount,
 /* d_delete:       cifs_d_delete,      */ /* not needed except for debugging */
 };
 
@@ -711,4 +712,5 @@ const struct dentry_operations cifs_ci_dentry_ops = {
 	.d_revalidate = cifs_d_revalidate,
 	.d_hash = cifs_ci_hash,
 	.d_compare = cifs_ci_compare,
+	.d_automount = cifs_dfs_d_automount,
 };
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index d843631c028d..e964b1cd5dd0 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -287,6 +287,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 	struct inode *inode = cifs_file->dentry->d_inode;
 	struct cifsTconInfo *tcon = tlink_tcon(cifs_file->tlink);
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifsLockInfo *li, *tmp;
 
 	spin_lock(&cifs_file_list_lock);
@@ -302,6 +303,13 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 	if (list_empty(&cifsi->openFileList)) {
 		cFYI(1, "closing last open instance for inode %p",
 			cifs_file->dentry->d_inode);
+
+		/* in strict cache mode we need invalidate mapping on the last
+		   close  because it may cause a error when we open this file
+		   again and get at least level II oplock */
+		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
+			CIFS_I(inode)->invalid_mapping = true;
+
 		cifs_set_oplock_level(cifsi, 0);
 	}
 	spin_unlock(&cifs_file_list_lock);
@@ -338,7 +346,6 @@ int cifs_open(struct inode *inode, struct file *file)
 	struct cifsTconInfo *tcon;
 	struct tcon_link *tlink;
 	struct cifsFileInfo *pCifsFile = NULL;
-	struct cifsInodeInfo *pCifsInode;
 	char *full_path = NULL;
 	bool posix_open_ok = false;
 	__u16 netfid;
@@ -353,8 +360,6 @@ int cifs_open(struct inode *inode, struct file *file)
 	}
 	tcon = tlink_tcon(tlink);
 
-	pCifsInode = CIFS_I(file->f_path.dentry->d_inode);
-
 	full_path = build_path_from_dentry(file->f_path.dentry);
 	if (full_path == NULL) {
 		rc = -ENOMEM;
@@ -726,12 +731,12 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
 
 		/* BB we could chain these into one lock request BB */
 		rc = CIFSSMBLock(xid, tcon, netfid, length, pfLock->fl_start,
-				 0, 1, lockType, 0 /* wait flag */ );
+				 0, 1, lockType, 0 /* wait flag */, 0);
 		if (rc == 0) {
 			rc = CIFSSMBLock(xid, tcon, netfid, length,
 					 pfLock->fl_start, 1 /* numUnlock */ ,
 					 0 /* numLock */ , lockType,
-					 0 /* wait flag */ );
+					 0 /* wait flag */, 0);
 			pfLock->fl_type = F_UNLCK;
 			if (rc != 0)
 				cERROR(1, "Error unlocking previously locked "
@@ -748,13 +753,13 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
 				rc = CIFSSMBLock(xid, tcon, netfid, length,
 					pfLock->fl_start, 0, 1,
 					lockType | LOCKING_ANDX_SHARED_LOCK,
-					0 /* wait flag */);
+					0 /* wait flag */, 0);
 				if (rc == 0) {
 					rc = CIFSSMBLock(xid, tcon, netfid,
 						length, pfLock->fl_start, 1, 0,
 						lockType |
 						LOCKING_ANDX_SHARED_LOCK,
-						0 /* wait flag */);
+						0 /* wait flag */, 0);
 					pfLock->fl_type = F_RDLCK;
 					if (rc != 0)
 						cERROR(1, "Error unlocking "
@@ -797,8 +802,8 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
 
 		if (numLock) {
 			rc = CIFSSMBLock(xid, tcon, netfid, length,
-					pfLock->fl_start,
-					0, numLock, lockType, wait_flag);
+					 pfLock->fl_start, 0, numLock, lockType,
+					 wait_flag, 0);
 
 			if (rc == 0) {
 				/* For Windows locks we must store them. */
@@ -818,9 +823,9 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
 						(pfLock->fl_start + length) >=
 						(li->offset + li->length)) {
 					stored_rc = CIFSSMBLock(xid, tcon,
-							netfid,
-							li->length, li->offset,
-							1, 0, li->type, false);
+							netfid, li->length,
+							li->offset, 1, 0,
+							li->type, false, 0);
 					if (stored_rc)
 						rc = stored_rc;
 					else {
@@ -839,31 +844,8 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
 	return rc;
 }
 
-/*
- * Set the timeout on write requests past EOF. For some servers (Windows)
- * these calls can be very long.
- *
- * If we're writing >10M past the EOF we give a 180s timeout. Anything less
- * than that gets a 45s timeout. Writes not past EOF get 15s timeouts.
- * The 10M cutoff is totally arbitrary. A better scheme for this would be
- * welcome if someone wants to suggest one.
- *
- * We may be able to do a better job with this if there were some way to
- * declare that a file should be sparse.
- */
-static int
-cifs_write_timeout(struct cifsInodeInfo *cifsi, loff_t offset)
-{
-	if (offset <= cifsi->server_eof)
-		return CIFS_STD_OP;
-	else if (offset > (cifsi->server_eof + (10 * 1024 * 1024)))
-		return CIFS_VLONG_OP;
-	else
-		return CIFS_LONG_OP;
-}
-
 /* update the file size (if needed) after a write */
-static void
+void
 cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
 		      unsigned int bytes_written)
 {
@@ -882,7 +864,7 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data,
 	unsigned int total_written;
 	struct cifs_sb_info *cifs_sb;
 	struct cifsTconInfo *pTcon;
-	int xid, long_op;
+	int xid;
 	struct cifsFileInfo *open_file;
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 
@@ -903,7 +885,6 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data,
 
 	xid = GetXid();
 
-	long_op = cifs_write_timeout(cifsi, *poffset);
 	for (total_written = 0; write_size > total_written;
 	     total_written += bytes_written) {
 		rc = -EAGAIN;
@@ -931,7 +912,7 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data,
 				min_t(const int, cifs_sb->wsize,
 				      write_size - total_written),
 				*poffset, &bytes_written,
-				NULL, write_data + total_written, long_op);
+				NULL, write_data + total_written, 0);
 		}
 		if (rc || (bytes_written == 0)) {
 			if (total_written)
@@ -944,8 +925,6 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data,
 			cifs_update_eof(cifsi, *poffset, bytes_written);
 			*poffset += bytes_written;
 		}
-		long_op = CIFS_STD_OP; /* subsequent writes fast -
-				    15 seconds is plenty */
 	}
 
 	cifs_stats_bytes_written(pTcon, total_written);
@@ -974,7 +953,7 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file,
 	unsigned int total_written;
 	struct cifs_sb_info *cifs_sb;
 	struct cifsTconInfo *pTcon;
-	int xid, long_op;
+	int xid;
 	struct dentry *dentry = open_file->dentry;
 	struct cifsInodeInfo *cifsi = CIFS_I(dentry->d_inode);
 
@@ -987,7 +966,6 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file,
 
 	xid = GetXid();
 
-	long_op = cifs_write_timeout(cifsi, *poffset);
 	for (total_written = 0; write_size > total_written;
 	     total_written += bytes_written) {
 		rc = -EAGAIN;
@@ -1017,7 +995,7 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file,
 				rc = CIFSSMBWrite2(xid, pTcon,
 						open_file->netfid, len,
 						*poffset, &bytes_written,
-						iov, 1, long_op);
+						iov, 1, 0);
 			} else
 				rc = CIFSSMBWrite(xid, pTcon,
 					 open_file->netfid,
@@ -1025,7 +1003,7 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file,
 					       write_size - total_written),
 					 *poffset, &bytes_written,
 					 write_data + total_written,
-					 NULL, long_op);
+					 NULL, 0);
 		}
 		if (rc || (bytes_written == 0)) {
 			if (total_written)
@@ -1038,8 +1016,6 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file,
 			cifs_update_eof(cifsi, *poffset, bytes_written);
 			*poffset += bytes_written;
 		}
-		long_op = CIFS_STD_OP; /* subsequent writes fast -
-				    15 seconds is plenty */
 	}
 
 	cifs_stats_bytes_written(pTcon, total_written);
@@ -1167,7 +1143,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
 	char *write_data;
 	int rc = -EFAULT;
 	int bytes_written = 0;
-	struct cifs_sb_info *cifs_sb;
 	struct inode *inode;
 	struct cifsFileInfo *open_file;
 
@@ -1175,7 +1150,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
 		return -EFAULT;
 
 	inode = page->mapping->host;
-	cifs_sb = CIFS_SB(inode->i_sb);
 
 	offset += (loff_t)from;
 	write_data = kmap(page);
@@ -1239,7 +1213,7 @@ static int cifs_writepages(struct address_space *mapping,
 	struct pagevec pvec;
 	int rc = 0;
 	int scanned = 0;
-	int xid, long_op;
+	int xid;
 
 	cifs_sb = CIFS_SB(mapping->host->i_sb);
 
@@ -1377,43 +1351,67 @@ retry:
 				break;
 		}
 		if (n_iov) {
+retry_write:
 			open_file = find_writable_file(CIFS_I(mapping->host),
 							false);
 			if (!open_file) {
 				cERROR(1, "No writable handles for inode");
 				rc = -EBADF;
 			} else {
-				long_op = cifs_write_timeout(cifsi, offset);
 				rc = CIFSSMBWrite2(xid, tcon, open_file->netfid,
 						   bytes_to_write, offset,
 						   &bytes_written, iov, n_iov,
-						   long_op);
+						   0);
 				cifsFileInfo_put(open_file);
-				cifs_update_eof(cifsi, offset, bytes_written);
 			}
 
-			if (rc || bytes_written < bytes_to_write) {
-				cERROR(1, "Write2 ret %d, wrote %d",
-					  rc, bytes_written);
-				mapping_set_error(mapping, rc);
-			} else {
+			cFYI(1, "Write2 rc=%d, wrote=%u", rc, bytes_written);
+
+			/*
+			 * For now, treat a short write as if nothing got
+			 * written. A zero length write however indicates
+			 * ENOSPC or EFBIG. We have no way to know which
+			 * though, so call it ENOSPC for now. EFBIG would
+			 * get translated to AS_EIO anyway.
+			 *
+			 * FIXME: make it take into account the data that did
+			 *	  get written
+			 */
+			if (rc == 0) {
+				if (bytes_written == 0)
+					rc = -ENOSPC;
+				else if (bytes_written < bytes_to_write)
+					rc = -EAGAIN;
+			}
+
+			/* retry on data-integrity flush */
+			if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN)
+				goto retry_write;
+
+			/* fix the stats and EOF */
+			if (bytes_written > 0) {
 				cifs_stats_bytes_written(tcon, bytes_written);
+				cifs_update_eof(cifsi, offset, bytes_written);
 			}
 
 			for (i = 0; i < n_iov; i++) {
 				page = pvec.pages[first + i];
-				/* Should we also set page error on
-				success rc but too little data written? */
-				/* BB investigate retry logic on temporary
-				server crash cases and how recovery works
-				when page marked as error */
-				if (rc)
+				/* on retryable write error, redirty page */
+				if (rc == -EAGAIN)
+					redirty_page_for_writepage(wbc, page);
+				else if (rc != 0)
 					SetPageError(page);
 				kunmap(page);
 				unlock_page(page);
 				end_page_writeback(page);
 				page_cache_release(page);
 			}
+
+			if (rc != -EAGAIN)
+				mapping_set_error(mapping, rc);
+			else
+				rc = 0;
+
 			if ((wbc->nr_to_write -= n_iov) <= 0)
 				done = 1;
 			index = next;
@@ -1525,27 +1523,47 @@ static int cifs_write_end(struct file *file, struct address_space *mapping,
 	return rc;
 }
 
-int cifs_fsync(struct file *file, int datasync)
+int cifs_strict_fsync(struct file *file, int datasync)
 {
 	int xid;
 	int rc = 0;
 	struct cifsTconInfo *tcon;
 	struct cifsFileInfo *smbfile = file->private_data;
 	struct inode *inode = file->f_path.dentry->d_inode;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 
 	xid = GetXid();
 
 	cFYI(1, "Sync file - name: %s datasync: 0x%x",
 		file->f_path.dentry->d_name.name, datasync);
 
-	rc = filemap_write_and_wait(inode->i_mapping);
-	if (rc == 0) {
-		struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	if (!CIFS_I(inode)->clientCanCacheRead)
+		cifs_invalidate_mapping(inode);
 
-		tcon = tlink_tcon(smbfile->tlink);
-		if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC))
-			rc = CIFSSMBFlush(xid, tcon, smbfile->netfid);
-	}
+	tcon = tlink_tcon(smbfile->tlink);
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC))
+		rc = CIFSSMBFlush(xid, tcon, smbfile->netfid);
+
+	FreeXid(xid);
+	return rc;
+}
+
+int cifs_fsync(struct file *file, int datasync)
+{
+	int xid;
+	int rc = 0;
+	struct cifsTconInfo *tcon;
+	struct cifsFileInfo *smbfile = file->private_data;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+
+	xid = GetXid();
+
+	cFYI(1, "Sync file - name: %s datasync: 0x%x",
+		file->f_path.dentry->d_name.name, datasync);
+
+	tcon = tlink_tcon(smbfile->tlink);
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC))
+		rc = CIFSSMBFlush(xid, tcon, smbfile->netfid);
 
 	FreeXid(xid);
 	return rc;
@@ -1596,42 +1614,244 @@ int cifs_flush(struct file *file, fl_owner_t id)
 	return rc;
 }
 
-ssize_t cifs_user_read(struct file *file, char __user *read_data,
-	size_t read_size, loff_t *poffset)
+static int
+cifs_write_allocate_pages(struct page **pages, unsigned long num_pages)
 {
-	int rc = -EACCES;
+	int rc = 0;
+	unsigned long i;
+
+	for (i = 0; i < num_pages; i++) {
+		pages[i] = alloc_page(__GFP_HIGHMEM);
+		if (!pages[i]) {
+			/*
+			 * save number of pages we have already allocated and
+			 * return with ENOMEM error
+			 */
+			num_pages = i;
+			rc = -ENOMEM;
+			goto error;
+		}
+	}
+
+	return rc;
+
+error:
+	for (i = 0; i < num_pages; i++)
+		put_page(pages[i]);
+	return rc;
+}
+
+static inline
+size_t get_numpages(const size_t wsize, const size_t len, size_t *cur_len)
+{
+	size_t num_pages;
+	size_t clen;
+
+	clen = min_t(const size_t, len, wsize);
+	num_pages = clen / PAGE_CACHE_SIZE;
+	if (clen % PAGE_CACHE_SIZE)
+		num_pages++;
+
+	if (cur_len)
+		*cur_len = clen;
+
+	return num_pages;
+}
+
+static ssize_t
+cifs_iovec_write(struct file *file, const struct iovec *iov,
+		 unsigned long nr_segs, loff_t *poffset)
+{
+	unsigned int written;
+	unsigned long num_pages, npages, i;
+	size_t copied, len, cur_len;
+	ssize_t total_written = 0;
+	struct kvec *to_send;
+	struct page **pages;
+	struct iov_iter it;
+	struct inode *inode;
+	struct cifsFileInfo *open_file;
+	struct cifsTconInfo *pTcon;
+	struct cifs_sb_info *cifs_sb;
+	int xid, rc;
+
+	len = iov_length(iov, nr_segs);
+	if (!len)
+		return 0;
+
+	rc = generic_write_checks(file, poffset, &len, 0);
+	if (rc)
+		return rc;
+
+	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
+	num_pages = get_numpages(cifs_sb->wsize, len, &cur_len);
+
+	pages = kmalloc(sizeof(struct pages *)*num_pages, GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
+	to_send = kmalloc(sizeof(struct kvec)*(num_pages + 1), GFP_KERNEL);
+	if (!to_send) {
+		kfree(pages);
+		return -ENOMEM;
+	}
+
+	rc = cifs_write_allocate_pages(pages, num_pages);
+	if (rc) {
+		kfree(pages);
+		kfree(to_send);
+		return rc;
+	}
+
+	xid = GetXid();
+	open_file = file->private_data;
+	pTcon = tlink_tcon(open_file->tlink);
+	inode = file->f_path.dentry->d_inode;
+
+	iov_iter_init(&it, iov, nr_segs, len, 0);
+	npages = num_pages;
+
+	do {
+		size_t save_len = cur_len;
+		for (i = 0; i < npages; i++) {
+			copied = min_t(const size_t, cur_len, PAGE_CACHE_SIZE);
+			copied = iov_iter_copy_from_user(pages[i], &it, 0,
+							 copied);
+			cur_len -= copied;
+			iov_iter_advance(&it, copied);
+			to_send[i+1].iov_base = kmap(pages[i]);
+			to_send[i+1].iov_len = copied;
+		}
+
+		cur_len = save_len - cur_len;
+
+		do {
+			if (open_file->invalidHandle) {
+				rc = cifs_reopen_file(open_file, false);
+				if (rc != 0)
+					break;
+			}
+			rc = CIFSSMBWrite2(xid, pTcon, open_file->netfid,
+					   cur_len, *poffset, &written,
+					   to_send, npages, 0);
+		} while (rc == -EAGAIN);
+
+		for (i = 0; i < npages; i++)
+			kunmap(pages[i]);
+
+		if (written) {
+			len -= written;
+			total_written += written;
+			cifs_update_eof(CIFS_I(inode), *poffset, written);
+			*poffset += written;
+		} else if (rc < 0) {
+			if (!total_written)
+				total_written = rc;
+			break;
+		}
+
+		/* get length and number of kvecs of the next write */
+		npages = get_numpages(cifs_sb->wsize, len, &cur_len);
+	} while (len > 0);
+
+	if (total_written > 0) {
+		spin_lock(&inode->i_lock);
+		if (*poffset > inode->i_size)
+			i_size_write(inode, *poffset);
+		spin_unlock(&inode->i_lock);
+	}
+
+	cifs_stats_bytes_written(pTcon, total_written);
+	mark_inode_dirty_sync(inode);
+
+	for (i = 0; i < num_pages; i++)
+		put_page(pages[i]);
+	kfree(to_send);
+	kfree(pages);
+	FreeXid(xid);
+	return total_written;
+}
+
+static ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
+				unsigned long nr_segs, loff_t pos)
+{
+	ssize_t written;
+	struct inode *inode;
+
+	inode = iocb->ki_filp->f_path.dentry->d_inode;
+
+	/*
+	 * BB - optimize the way when signing is disabled. We can drop this
+	 * extra memory-to-memory copying and use iovec buffers for constructing
+	 * write request.
+	 */
+
+	written = cifs_iovec_write(iocb->ki_filp, iov, nr_segs, &pos);
+	if (written > 0) {
+		CIFS_I(inode)->invalid_mapping = true;
+		iocb->ki_pos = pos;
+	}
+
+	return written;
+}
+
+ssize_t cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
+			   unsigned long nr_segs, loff_t pos)
+{
+	struct inode *inode;
+
+	inode = iocb->ki_filp->f_path.dentry->d_inode;
+
+	if (CIFS_I(inode)->clientCanCacheAll)
+		return generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+	/*
+	 * In strict cache mode we need to write the data to the server exactly
+	 * from the pos to pos+len-1 rather than flush all affected pages
+	 * because it may cause a error with mandatory locks on these pages but
+	 * not on the region from pos to ppos+len-1.
+	 */
+
+	return cifs_user_writev(iocb, iov, nr_segs, pos);
+}
+
+static ssize_t
+cifs_iovec_read(struct file *file, const struct iovec *iov,
+		 unsigned long nr_segs, loff_t *poffset)
+{
+	int rc;
+	int xid;
+	ssize_t total_read;
 	unsigned int bytes_read = 0;
-	unsigned int total_read = 0;
-	unsigned int current_read_size;
+	size_t len, cur_len;
+	int iov_offset = 0;
 	struct cifs_sb_info *cifs_sb;
 	struct cifsTconInfo *pTcon;
-	int xid;
 	struct cifsFileInfo *open_file;
-	char *smb_read_data;
-	char __user *current_offset;
 	struct smb_com_read_rsp *pSMBr;
+	char *read_data;
+
+	if (!nr_segs)
+		return 0;
+
+	len = iov_length(iov, nr_segs);
+	if (!len)
+		return 0;
 
 	xid = GetXid();
 	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
 
-	if (file->private_data == NULL) {
-		rc = -EBADF;
-		FreeXid(xid);
-		return rc;
-	}
 	open_file = file->private_data;
 	pTcon = tlink_tcon(open_file->tlink);
 
 	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
 		cFYI(1, "attempting read on write only file instance");
 
-	for (total_read = 0, current_offset = read_data;
-	     read_size > total_read;
-	     total_read += bytes_read, current_offset += bytes_read) {
-		current_read_size = min_t(const int, read_size - total_read,
-					  cifs_sb->rsize);
+	for (total_read = 0; total_read < len; total_read += bytes_read) {
+		cur_len = min_t(const size_t, len - total_read, cifs_sb->rsize);
 		rc = -EAGAIN;
-		smb_read_data = NULL;
+		read_data = NULL;
+
 		while (rc == -EAGAIN) {
 			int buf_type = CIFS_NO_BUFFER;
 			if (open_file->invalidHandle) {
@@ -1639,27 +1859,25 @@ ssize_t cifs_user_read(struct file *file, char __user *read_data,
 				if (rc != 0)
 					break;
 			}
-			rc = CIFSSMBRead(xid, pTcon,
-					 open_file->netfid,
-					 current_read_size, *poffset,
-					 &bytes_read, &smb_read_data,
-					 &buf_type);
-			pSMBr = (struct smb_com_read_rsp *)smb_read_data;
-			if (smb_read_data) {
-				if (copy_to_user(current_offset,
-						smb_read_data +
-						4 /* RFC1001 length field */ +
-						le16_to_cpu(pSMBr->DataOffset),
-						bytes_read))
+			rc = CIFSSMBRead(xid, pTcon, open_file->netfid,
+					 cur_len, *poffset, &bytes_read,
+					 &read_data, &buf_type);
+			pSMBr = (struct smb_com_read_rsp *)read_data;
+			if (read_data) {
+				char *data_offset = read_data + 4 +
+						le16_to_cpu(pSMBr->DataOffset);
+				if (memcpy_toiovecend(iov, data_offset,
+						      iov_offset, bytes_read))
 					rc = -EFAULT;
-
 				if (buf_type == CIFS_SMALL_BUFFER)
-					cifs_small_buf_release(smb_read_data);
+					cifs_small_buf_release(read_data);
 				else if (buf_type == CIFS_LARGE_BUFFER)
-					cifs_buf_release(smb_read_data);
-				smb_read_data = NULL;
+					cifs_buf_release(read_data);
+				read_data = NULL;
+				iov_offset += bytes_read;
 			}
 		}
+
 		if (rc || (bytes_read == 0)) {
 			if (total_read) {
 				break;
@@ -1672,13 +1890,57 @@ ssize_t cifs_user_read(struct file *file, char __user *read_data,
 			*poffset += bytes_read;
 		}
 	}
+
 	FreeXid(xid);
 	return total_read;
 }
 
+ssize_t cifs_user_read(struct file *file, char __user *read_data,
+		       size_t read_size, loff_t *poffset)
+{
+	struct iovec iov;
+	iov.iov_base = read_data;
+	iov.iov_len = read_size;
+
+	return cifs_iovec_read(file, &iov, 1, poffset);
+}
+
+static ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov,
+			       unsigned long nr_segs, loff_t pos)
+{
+	ssize_t read;
+
+	read = cifs_iovec_read(iocb->ki_filp, iov, nr_segs, &pos);
+	if (read > 0)
+		iocb->ki_pos = pos;
+
+	return read;
+}
+
+ssize_t cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov,
+			  unsigned long nr_segs, loff_t pos)
+{
+	struct inode *inode;
+
+	inode = iocb->ki_filp->f_path.dentry->d_inode;
+
+	if (CIFS_I(inode)->clientCanCacheRead)
+		return generic_file_aio_read(iocb, iov, nr_segs, pos);
+
+	/*
+	 * In strict cache mode we need to read from the server all the time
+	 * if we don't have level II oplock because the server can delay mtime
+	 * change - so we can't make a decision about inode invalidating.
+	 * And we can also fail with pagereading if there are mandatory locks
+	 * on pages affected by this read but not on the region from pos to
+	 * pos+len-1.
+	 */
+
+	return cifs_user_readv(iocb, iov, nr_segs, pos);
+}
 
 static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size,
-	loff_t *poffset)
+			 loff_t *poffset)
 {
 	int rc = -EACCES;
 	unsigned int bytes_read = 0;
@@ -1746,6 +2008,21 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size,
 	return total_read;
 }
 
+int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int rc, xid;
+	struct inode *inode = file->f_path.dentry->d_inode;
+
+	xid = GetXid();
+
+	if (!CIFS_I(inode)->clientCanCacheRead)
+		cifs_invalidate_mapping(inode);
+
+	rc = generic_file_mmap(file, vma);
+	FreeXid(xid);
+	return rc;
+}
+
 int cifs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	int rc, xid;
@@ -2192,7 +2469,8 @@ void cifs_oplock_break(struct work_struct *work)
 	 */
 	if (!cfile->oplock_break_cancelled) {
 		rc = CIFSSMBLock(0, tlink_tcon(cfile->tlink), cfile->netfid, 0,
-				 0, 0, 0, LOCKING_ANDX_OPLOCK_RELEASE, false);
+				 0, 0, 0, LOCKING_ANDX_OPLOCK_RELEASE, false,
+				 cinode->clientCanCacheRead ? 1 : 0);
 		cFYI(1, "Oplock release rc = %d", rc);
 	}
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index b06b60620240..8852470b4fbb 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -32,7 +32,7 @@
 #include "fscache.h"
 
 
-static void cifs_set_ops(struct inode *inode, const bool is_dfs_referral)
+static void cifs_set_ops(struct inode *inode)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 
@@ -44,13 +44,17 @@ static void cifs_set_ops(struct inode *inode, const bool is_dfs_referral)
 				inode->i_fop = &cifs_file_direct_nobrl_ops;
 			else
 				inode->i_fop = &cifs_file_direct_ops;
+		} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
+			if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+				inode->i_fop = &cifs_file_strict_nobrl_ops;
+			else
+				inode->i_fop = &cifs_file_strict_ops;
 		} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
 			inode->i_fop = &cifs_file_nobrl_ops;
 		else { /* not direct, send byte range locks */
 			inode->i_fop = &cifs_file_ops;
 		}
 
-
 		/* check if server can support readpages */
 		if (cifs_sb_master_tcon(cifs_sb)->ses->server->maxBuf <
 				PAGE_CACHE_SIZE + MAX_CIFS_HDR_SIZE)
@@ -60,7 +64,7 @@ static void cifs_set_ops(struct inode *inode, const bool is_dfs_referral)
 		break;
 	case S_IFDIR:
 #ifdef CONFIG_CIFS_DFS_UPCALL
-		if (is_dfs_referral) {
+		if (IS_AUTOMOUNT(inode)) {
 			inode->i_op = &cifs_dfs_referral_inode_operations;
 		} else {
 #else /* NO DFS support, treat as a directory */
@@ -167,7 +171,9 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 	}
 	spin_unlock(&inode->i_lock);
 
-	cifs_set_ops(inode, fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL);
+	if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL)
+		inode->i_flags |= S_AUTOMOUNT;
+	cifs_set_ops(inode);
 }
 
 void
@@ -1677,7 +1683,7 @@ cifs_inode_needs_reval(struct inode *inode)
 /*
  * Zap the cache. Called when invalid_mapping flag is set.
  */
-static void
+void
 cifs_invalidate_mapping(struct inode *inode)
 {
 	int rc;
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 306769de2fb5..e8804d373404 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -28,7 +28,6 @@
 #include "cifsproto.h"
 #include "cifs_debug.h"
 #include "cifs_fs_sb.h"
-#include "md5.h"
 
 #define CIFS_MF_SYMLINK_LEN_OFFSET (4+1)
 #define CIFS_MF_SYMLINK_MD5_OFFSET (CIFS_MF_SYMLINK_LEN_OFFSET+(4+1))
@@ -47,6 +46,45 @@
 	md5_hash[12], md5_hash[13], md5_hash[14], md5_hash[15]
 
 static int
+symlink_hash(unsigned int link_len, const char *link_str, u8 *md5_hash)
+{
+	int rc;
+	unsigned int size;
+	struct crypto_shash *md5;
+	struct sdesc *sdescmd5;
+
+	md5 = crypto_alloc_shash("md5", 0, 0);
+	if (IS_ERR(md5)) {
+		rc = PTR_ERR(md5);
+		cERROR(1, "%s: Crypto md5 allocation error %d\n", __func__, rc);
+		return rc;
+	}
+	size = sizeof(struct shash_desc) + crypto_shash_descsize(md5);
+	sdescmd5 = kmalloc(size, GFP_KERNEL);
+	if (!sdescmd5) {
+		rc = -ENOMEM;
+		cERROR(1, "%s: Memory allocation failure\n", __func__);
+		goto symlink_hash_err;
+	}
+	sdescmd5->shash.tfm = md5;
+	sdescmd5->shash.flags = 0x0;
+
+	rc = crypto_shash_init(&sdescmd5->shash);
+	if (rc) {
+		cERROR(1, "%s: Could not init md5 shash\n", __func__);
+		goto symlink_hash_err;
+	}
+	crypto_shash_update(&sdescmd5->shash, link_str, link_len);
+	rc = crypto_shash_final(&sdescmd5->shash, md5_hash);
+
+symlink_hash_err:
+	crypto_free_shash(md5);
+	kfree(sdescmd5);
+
+	return rc;
+}
+
+static int
 CIFSParseMFSymlink(const u8 *buf,
 		   unsigned int buf_len,
 		   unsigned int *_link_len,
@@ -56,7 +94,6 @@ CIFSParseMFSymlink(const u8 *buf,
 	unsigned int link_len;
 	const char *md5_str1;
 	const char *link_str;
-	struct MD5Context md5_ctx;
 	u8 md5_hash[16];
 	char md5_str2[34];
 
@@ -70,9 +107,11 @@ CIFSParseMFSymlink(const u8 *buf,
 	if (rc != 1)
 		return -EINVAL;
 
-	cifs_MD5_init(&md5_ctx);
-	cifs_MD5_update(&md5_ctx, (const u8 *)link_str, link_len);
-	cifs_MD5_final(md5_hash, &md5_ctx);
+	rc = symlink_hash(link_len, link_str, md5_hash);
+	if (rc) {
+		cFYI(1, "%s: MD5 hash failure: %d\n", __func__, rc);
+		return rc;
+	}
 
 	snprintf(md5_str2, sizeof(md5_str2),
 		 CIFS_MF_SYMLINK_MD5_FORMAT,
@@ -94,9 +133,9 @@ CIFSParseMFSymlink(const u8 *buf,
 static int
 CIFSFormatMFSymlink(u8 *buf, unsigned int buf_len, const char *link_str)
 {
+	int rc;
 	unsigned int link_len;
 	unsigned int ofs;
-	struct MD5Context md5_ctx;
 	u8 md5_hash[16];
 
 	if (buf_len != CIFS_MF_SYMLINK_FILE_SIZE)
@@ -107,9 +146,11 @@ CIFSFormatMFSymlink(u8 *buf, unsigned int buf_len, const char *link_str)
 	if (link_len > CIFS_MF_SYMLINK_LINK_MAXLEN)
 		return -ENAMETOOLONG;
 
-	cifs_MD5_init(&md5_ctx);
-	cifs_MD5_update(&md5_ctx, (const u8 *)link_str, link_len);
-	cifs_MD5_final(md5_hash, &md5_ctx);
+	rc = symlink_hash(link_len, link_str, md5_hash);
+	if (rc) {
+		cFYI(1, "%s: MD5 hash failure: %d\n", __func__, rc);
+		return rc;
+	}
 
 	snprintf(buf, buf_len,
 		 CIFS_MF_SYMLINK_LEN_FORMAT CIFS_MF_SYMLINK_MD5_FORMAT,
diff --git a/fs/cifs/md4.c b/fs/cifs/md4.c
deleted file mode 100644
index a725c2609d67..000000000000
--- a/fs/cifs/md4.c
+++ /dev/null
@@ -1,205 +0,0 @@
-/*
-   Unix SMB/Netbios implementation.
-   Version 1.9.
-   a implementation of MD4 designed for use in the SMB authentication protocol
-   Copyright (C) Andrew Tridgell 1997-1998.
-   Modified by Steve French (sfrench@us.ibm.com) 2002-2003
-
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 2 of the License, or
-   (at your option) any later version.
-
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-
-   You should have received a copy of the GNU General Public License
-   along with this program; if not, write to the Free Software
-   Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-*/
-#include <linux/module.h>
-#include <linux/fs.h>
-#include "cifsencrypt.h"
-
-/* NOTE: This code makes no attempt to be fast! */
-
-static __u32
-F(__u32 X, __u32 Y, __u32 Z)
-{
-	return (X & Y) | ((~X) & Z);
-}
-
-static __u32
-G(__u32 X, __u32 Y, __u32 Z)
-{
-	return (X & Y) | (X & Z) | (Y & Z);
-}
-
-static __u32
-H(__u32 X, __u32 Y, __u32 Z)
-{
-	return X ^ Y ^ Z;
-}
-
-static __u32
-lshift(__u32 x, int s)
-{
-	x &= 0xFFFFFFFF;
-	return ((x << s) & 0xFFFFFFFF) | (x >> (32 - s));
-}
-
-#define ROUND1(a,b,c,d,k,s) (*a) = lshift((*a) + F(*b,*c,*d) + X[k], s)
-#define ROUND2(a,b,c,d,k,s) (*a) = lshift((*a) + G(*b,*c,*d) + X[k] + (__u32)0x5A827999,s)
-#define ROUND3(a,b,c,d,k,s) (*a) = lshift((*a) + H(*b,*c,*d) + X[k] + (__u32)0x6ED9EBA1,s)
-
-/* this applies md4 to 64 byte chunks */
-static void
-mdfour64(__u32 *M, __u32 *A, __u32 *B, __u32 *C, __u32 *D)
-{
-	int j;
-	__u32 AA, BB, CC, DD;
-	__u32 X[16];
-
-
-	for (j = 0; j < 16; j++)
-		X[j] = M[j];
-
-	AA = *A;
-	BB = *B;
-	CC = *C;
-	DD = *D;
-
-	ROUND1(A, B, C, D, 0, 3);
-	ROUND1(D, A, B, C, 1, 7);
-	ROUND1(C, D, A, B, 2, 11);
-	ROUND1(B, C, D, A, 3, 19);
-	ROUND1(A, B, C, D, 4, 3);
-	ROUND1(D, A, B, C, 5, 7);
-	ROUND1(C, D, A, B, 6, 11);
-	ROUND1(B, C, D, A, 7, 19);
-	ROUND1(A, B, C, D, 8, 3);
-	ROUND1(D, A, B, C, 9, 7);
-	ROUND1(C, D, A, B, 10, 11);
-	ROUND1(B, C, D, A, 11, 19);
-	ROUND1(A, B, C, D, 12, 3);
-	ROUND1(D, A, B, C, 13, 7);
-	ROUND1(C, D, A, B, 14, 11);
-	ROUND1(B, C, D, A, 15, 19);
-
-	ROUND2(A, B, C, D, 0, 3);
-	ROUND2(D, A, B, C, 4, 5);
-	ROUND2(C, D, A, B, 8, 9);
-	ROUND2(B, C, D, A, 12, 13);
-	ROUND2(A, B, C, D, 1, 3);
-	ROUND2(D, A, B, C, 5, 5);
-	ROUND2(C, D, A, B, 9, 9);
-	ROUND2(B, C, D, A, 13, 13);
-	ROUND2(A, B, C, D, 2, 3);
-	ROUND2(D, A, B, C, 6, 5);
-	ROUND2(C, D, A, B, 10, 9);
-	ROUND2(B, C, D, A, 14, 13);
-	ROUND2(A, B, C, D, 3, 3);
-	ROUND2(D, A, B, C, 7, 5);
-	ROUND2(C, D, A, B, 11, 9);
-	ROUND2(B, C, D, A, 15, 13);
-
-	ROUND3(A, B, C, D, 0, 3);
-	ROUND3(D, A, B, C, 8, 9);
-	ROUND3(C, D, A, B, 4, 11);
-	ROUND3(B, C, D, A, 12, 15);
-	ROUND3(A, B, C, D, 2, 3);
-	ROUND3(D, A, B, C, 10, 9);
-	ROUND3(C, D, A, B, 6, 11);
-	ROUND3(B, C, D, A, 14, 15);
-	ROUND3(A, B, C, D, 1, 3);
-	ROUND3(D, A, B, C, 9, 9);
-	ROUND3(C, D, A, B, 5, 11);
-	ROUND3(B, C, D, A, 13, 15);
-	ROUND3(A, B, C, D, 3, 3);
-	ROUND3(D, A, B, C, 11, 9);
-	ROUND3(C, D, A, B, 7, 11);
-	ROUND3(B, C, D, A, 15, 15);
-
-	*A += AA;
-	*B += BB;
-	*C += CC;
-	*D += DD;
-
-	*A &= 0xFFFFFFFF;
-	*B &= 0xFFFFFFFF;
-	*C &= 0xFFFFFFFF;
-	*D &= 0xFFFFFFFF;
-
-	for (j = 0; j < 16; j++)
-		X[j] = 0;
-}
-
-static void
-copy64(__u32 *M, unsigned char *in)
-{
-	int i;
-
-	for (i = 0; i < 16; i++)
-		M[i] = (in[i * 4 + 3] << 24) | (in[i * 4 + 2] << 16) |
-		    (in[i * 4 + 1] << 8) | (in[i * 4 + 0] << 0);
-}
-
-static void
-copy4(unsigned char *out, __u32 x)
-{
-	out[0] = x & 0xFF;
-	out[1] = (x >> 8) & 0xFF;
-	out[2] = (x >> 16) & 0xFF;
-	out[3] = (x >> 24) & 0xFF;
-}
-
-/* produce a md4 message digest from data of length n bytes */
-void
-mdfour(unsigned char *out, unsigned char *in, int n)
-{
-	unsigned char buf[128];
-	__u32 M[16];
-	__u32 b = n * 8;
-	int i;
-	__u32 A = 0x67452301;
-	__u32 B = 0xefcdab89;
-	__u32 C = 0x98badcfe;
-	__u32 D = 0x10325476;
-
-	while (n > 64) {
-		copy64(M, in);
-		mdfour64(M, &A, &B, &C, &D);
-		in += 64;
-		n -= 64;
-	}
-
-	for (i = 0; i < 128; i++)
-		buf[i] = 0;
-	memcpy(buf, in, n);
-	buf[n] = 0x80;
-
-	if (n <= 55) {
-		copy4(buf + 56, b);
-		copy64(M, buf);
-		mdfour64(M, &A, &B, &C, &D);
-	} else {
-		copy4(buf + 120, b);
-		copy64(M, buf);
-		mdfour64(M, &A, &B, &C, &D);
-		copy64(M, buf + 64);
-		mdfour64(M, &A, &B, &C, &D);
-	}
-
-	for (i = 0; i < 128; i++)
-		buf[i] = 0;
-	copy64(M, buf);
-
-	copy4(out, A);
-	copy4(out + 4, B);
-	copy4(out + 8, C);
-	copy4(out + 12, D);
-
-	A = B = C = D = 0;
-}
diff --git a/fs/cifs/md5.c b/fs/cifs/md5.c
deleted file mode 100644
index 98b66a54c319..000000000000
--- a/fs/cifs/md5.c
+++ /dev/null
@@ -1,366 +0,0 @@
-/*
- * This code implements the MD5 message-digest algorithm.
- * The algorithm is due to Ron Rivest.  This code was
- * written by Colin Plumb in 1993, no copyright is claimed.
- * This code is in the public domain; do with it what you wish.
- *
- * Equivalent code is available from RSA Data Security, Inc.
- * This code has been tested against that, and is equivalent,
- * except that you don't need to include two pages of legalese
- * with every copy.
- *
- * To compute the message digest of a chunk of bytes, declare an
- * MD5Context structure, pass it to cifs_MD5_init, call cifs_MD5_update as
- * needed on buffers full of bytes, and then call cifs_MD5_final, which
- * will fill a supplied 16-byte array with the digest.
- */
-
-/* This code slightly modified to fit into Samba by
-   abartlet@samba.org Jun 2001
-   and to fit the cifs vfs by
-   Steve French sfrench@us.ibm.com */
-
-#include <linux/string.h>
-#include "md5.h"
-
-static void MD5Transform(__u32 buf[4], __u32 const in[16]);
-
-/*
- * Note: this code is harmless on little-endian machines.
- */
-static void
-byteReverse(unsigned char *buf, unsigned longs)
-{
-	__u32 t;
-	do {
-		t = (__u32) ((unsigned) buf[3] << 8 | buf[2]) << 16 |
-		    ((unsigned) buf[1] << 8 | buf[0]);
-		*(__u32 *) buf = t;
-		buf += 4;
-	} while (--longs);
-}
-
-/*
- * Start MD5 accumulation.  Set bit count to 0 and buffer to mysterious
- * initialization constants.
- */
-void
-cifs_MD5_init(struct MD5Context *ctx)
-{
-	ctx->buf[0] = 0x67452301;
-	ctx->buf[1] = 0xefcdab89;
-	ctx->buf[2] = 0x98badcfe;
-	ctx->buf[3] = 0x10325476;
-
-	ctx->bits[0] = 0;
-	ctx->bits[1] = 0;
-}
-
-/*
- * Update context to reflect the concatenation of another buffer full
- * of bytes.
- */
-void
-cifs_MD5_update(struct MD5Context *ctx, unsigned char const *buf, unsigned len)
-{
-	register __u32 t;
-
-	/* Update bitcount */
-
-	t = ctx->bits[0];
-	if ((ctx->bits[0] = t + ((__u32) len << 3)) < t)
-		ctx->bits[1]++;	/* Carry from low to high */
-	ctx->bits[1] += len >> 29;
-
-	t = (t >> 3) & 0x3f;	/* Bytes already in shsInfo->data */
-
-	/* Handle any leading odd-sized chunks */
-
-	if (t) {
-		unsigned char *p = (unsigned char *) ctx->in + t;
-
-		t = 64 - t;
-		if (len < t) {
-			memmove(p, buf, len);
-			return;
-		}
-		memmove(p, buf, t);
-		byteReverse(ctx->in, 16);
-		MD5Transform(ctx->buf, (__u32 *) ctx->in);
-		buf += t;
-		len -= t;
-	}
-	/* Process data in 64-byte chunks */
-
-	while (len >= 64) {
-		memmove(ctx->in, buf, 64);
-		byteReverse(ctx->in, 16);
-		MD5Transform(ctx->buf, (__u32 *) ctx->in);
-		buf += 64;
-		len -= 64;
-	}
-
-	/* Handle any remaining bytes of data. */
-
-	memmove(ctx->in, buf, len);
-}
-
-/*
- * Final wrapup - pad to 64-byte boundary with the bit pattern
- * 1 0* (64-bit count of bits processed, MSB-first)
- */
-void
-cifs_MD5_final(unsigned char digest[16], struct MD5Context *ctx)
-{
-	unsigned int count;
-	unsigned char *p;
-
-	/* Compute number of bytes mod 64 */
-	count = (ctx->bits[0] >> 3) & 0x3F;
-
-	/* Set the first char of padding to 0x80.  This is safe since there is
-	   always at least one byte free */
-	p = ctx->in + count;
-	*p++ = 0x80;
-
-	/* Bytes of padding needed to make 64 bytes */
-	count = 64 - 1 - count;
-
-	/* Pad out to 56 mod 64 */
-	if (count < 8) {
-		/* Two lots of padding:  Pad the first block to 64 bytes */
-		memset(p, 0, count);
-		byteReverse(ctx->in, 16);
-		MD5Transform(ctx->buf, (__u32 *) ctx->in);
-
-		/* Now fill the next block with 56 bytes */
-		memset(ctx->in, 0, 56);
-	} else {
-		/* Pad block to 56 bytes */
-		memset(p, 0, count - 8);
-	}
-	byteReverse(ctx->in, 14);
-
-	/* Append length in bits and transform */
-	((__u32 *) ctx->in)[14] = ctx->bits[0];
-	((__u32 *) ctx->in)[15] = ctx->bits[1];
-
-	MD5Transform(ctx->buf, (__u32 *) ctx->in);
-	byteReverse((unsigned char *) ctx->buf, 4);
-	memmove(digest, ctx->buf, 16);
-	memset(ctx, 0, sizeof(*ctx));	/* In case it's sensitive */
-}
-
-/* The four core functions - F1 is optimized somewhat */
-
-/* #define F1(x, y, z) (x & y | ~x & z) */
-#define F1(x, y, z) (z ^ (x & (y ^ z)))
-#define F2(x, y, z) F1(z, x, y)
-#define F3(x, y, z) (x ^ y ^ z)
-#define F4(x, y, z) (y ^ (x | ~z))
-
-/* This is the central step in the MD5 algorithm. */
-#define MD5STEP(f, w, x, y, z, data, s) \
-	(w += f(x, y, z) + data,  w = w<<s | w>>(32-s),  w += x)
-
-/*
- * The core of the MD5 algorithm, this alters an existing MD5 hash to
- * reflect the addition of 16 longwords of new data.  cifs_MD5_update blocks
- * the data and converts bytes into longwords for this routine.
- */
-static void
-MD5Transform(__u32 buf[4], __u32 const in[16])
-{
-	register __u32 a, b, c, d;
-
-	a = buf[0];
-	b = buf[1];
-	c = buf[2];
-	d = buf[3];
-
-	MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
-	MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
-	MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
-	MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
-	MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
-	MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
-	MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
-	MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
-	MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
-	MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
-	MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
-	MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
-	MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
-	MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
-	MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
-	MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
-
-	MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
-	MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
-	MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
-	MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
-	MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
-	MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
-	MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
-	MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
-	MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
-	MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
-	MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
-	MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
-	MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
-	MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
-	MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
-	MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
-
-	MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
-	MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
-	MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
-	MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
-	MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
-	MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
-	MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
-	MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
-	MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
-	MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
-	MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
-	MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
-	MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
-	MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
-	MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
-	MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
-
-	MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
-	MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
-	MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
-	MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
-	MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
-	MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
-	MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
-	MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
-	MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
-	MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
-	MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
-	MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
-	MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
-	MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
-	MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
-	MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
-
-	buf[0] += a;
-	buf[1] += b;
-	buf[2] += c;
-	buf[3] += d;
-}
-
-#if 0   /* currently unused */
-/***********************************************************************
- the rfc 2104 version of hmac_md5 initialisation.
-***********************************************************************/
-static void
-hmac_md5_init_rfc2104(unsigned char *key, int key_len,
-		      struct HMACMD5Context *ctx)
-{
-	int i;
-
-	/* if key is longer than 64 bytes reset it to key=MD5(key) */
-	if (key_len > 64) {
-		unsigned char tk[16];
-		struct MD5Context tctx;
-
-		cifs_MD5_init(&tctx);
-		cifs_MD5_update(&tctx, key, key_len);
-		cifs_MD5_final(tk, &tctx);
-
-		key = tk;
-		key_len = 16;
-	}
-
-	/* start out by storing key in pads */
-	memset(ctx->k_ipad, 0, sizeof(ctx->k_ipad));
-	memset(ctx->k_opad, 0, sizeof(ctx->k_opad));
-	memcpy(ctx->k_ipad, key, key_len);
-	memcpy(ctx->k_opad, key, key_len);
-
-	/* XOR key with ipad and opad values */
-	for (i = 0; i < 64; i++) {
-		ctx->k_ipad[i] ^= 0x36;
-		ctx->k_opad[i] ^= 0x5c;
-	}
-
-	cifs_MD5_init(&ctx->ctx);
-	cifs_MD5_update(&ctx->ctx, ctx->k_ipad, 64);
-}
-#endif
-
-/***********************************************************************
- the microsoft version of hmac_md5 initialisation.
-***********************************************************************/
-void
-hmac_md5_init_limK_to_64(const unsigned char *key, int key_len,
-			 struct HMACMD5Context *ctx)
-{
-	int i;
-
-	/* if key is longer than 64 bytes truncate it */
-	if (key_len > 64)
-		key_len = 64;
-
-	/* start out by storing key in pads */
-	memset(ctx->k_ipad, 0, sizeof(ctx->k_ipad));
-	memset(ctx->k_opad, 0, sizeof(ctx->k_opad));
-	memcpy(ctx->k_ipad, key, key_len);
-	memcpy(ctx->k_opad, key, key_len);
-
-	/* XOR key with ipad and opad values */
-	for (i = 0; i < 64; i++) {
-		ctx->k_ipad[i] ^= 0x36;
-		ctx->k_opad[i] ^= 0x5c;
-	}
-
-	cifs_MD5_init(&ctx->ctx);
-	cifs_MD5_update(&ctx->ctx, ctx->k_ipad, 64);
-}
-
-/***********************************************************************
- update hmac_md5 "inner" buffer
-***********************************************************************/
-void
-hmac_md5_update(const unsigned char *text, int text_len,
-		struct HMACMD5Context *ctx)
-{
-	cifs_MD5_update(&ctx->ctx, text, text_len);	/* then text of datagram */
-}
-
-/***********************************************************************
- finish off hmac_md5 "inner" buffer and generate outer one.
-***********************************************************************/
-void
-hmac_md5_final(unsigned char *digest, struct HMACMD5Context *ctx)
-{
-	struct MD5Context ctx_o;
-
-	cifs_MD5_final(digest, &ctx->ctx);
-
-	cifs_MD5_init(&ctx_o);
-	cifs_MD5_update(&ctx_o, ctx->k_opad, 64);
-	cifs_MD5_update(&ctx_o, digest, 16);
-	cifs_MD5_final(digest, &ctx_o);
-}
-
-/***********************************************************
- single function to calculate an HMAC MD5 digest from data.
- use the microsoft hmacmd5 init method because the key is 16 bytes.
-************************************************************/
-#if 0 /* currently unused */
-static void
-hmac_md5(unsigned char key[16], unsigned char *data, int data_len,
-	 unsigned char *digest)
-{
-	struct HMACMD5Context ctx;
-	hmac_md5_init_limK_to_64(key, 16, &ctx);
-	if (data_len != 0)
-		hmac_md5_update(data, data_len, &ctx);
-
-	hmac_md5_final(digest, &ctx);
-}
-#endif
diff --git a/fs/cifs/md5.h b/fs/cifs/md5.h
deleted file mode 100644
index 6fba8cb402fd..000000000000
--- a/fs/cifs/md5.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#ifndef MD5_H
-#define MD5_H
-#ifndef HEADER_MD5_H
-/* Try to avoid clashes with OpenSSL */
-#define HEADER_MD5_H
-#endif
-
-struct MD5Context {
-	__u32 buf[4];
-	__u32 bits[2];
-	unsigned char in[64];
-};
-#endif				/* !MD5_H */
-
-#ifndef _HMAC_MD5_H
-struct HMACMD5Context {
-	struct MD5Context ctx;
-	unsigned char k_ipad[65];
-	unsigned char k_opad[65];
-};
-#endif				/* _HMAC_MD5_H */
-
-void cifs_MD5_init(struct MD5Context *context);
-void cifs_MD5_update(struct MD5Context *context, unsigned char const *buf,
-			unsigned len);
-void cifs_MD5_final(unsigned char digest[16], struct MD5Context *context);
-
-/* The following definitions come from lib/hmacmd5.c  */
-
-/* void hmac_md5_init_rfc2104(unsigned char *key, int key_len,
-			struct HMACMD5Context *ctx);*/
-void hmac_md5_init_limK_to_64(const unsigned char *key, int key_len,
-			struct HMACMD5Context *ctx);
-void hmac_md5_update(const unsigned char *text, int text_len,
-			struct HMACMD5Context *ctx);
-void hmac_md5_final(unsigned char *digest, struct HMACMD5Context *ctx);
-/* void hmac_md5(unsigned char key[16], unsigned char *data, int data_len,
-			unsigned char *digest);*/
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 43f10281bc19..2a930a752a78 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -236,10 +236,7 @@ __u16 GetNextMid(struct TCP_Server_Info *server)
 {
 	__u16 mid = 0;
 	__u16 last_mid;
-	int   collision;
-
-	if (server == NULL)
-		return mid;
+	bool collision;
 
 	spin_lock(&GlobalMid_Lock);
 	last_mid = server->CurrentMid; /* we do not want to loop forever */
@@ -252,24 +249,38 @@ __u16 GetNextMid(struct TCP_Server_Info *server)
 	(and it would also have to have been a request that
 	 did not time out) */
 	while (server->CurrentMid != last_mid) {
-		struct list_head *tmp;
 		struct mid_q_entry *mid_entry;
+		unsigned int num_mids;
 
-		collision = 0;
+		collision = false;
 		if (server->CurrentMid == 0)
 			server->CurrentMid++;
 
-		list_for_each(tmp, &server->pending_mid_q) {
-			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-
-			if ((mid_entry->mid == server->CurrentMid) &&
-			    (mid_entry->midState == MID_REQUEST_SUBMITTED)) {
+		num_mids = 0;
+		list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) {
+			++num_mids;
+			if (mid_entry->mid == server->CurrentMid &&
+			    mid_entry->midState == MID_REQUEST_SUBMITTED) {
 				/* This mid is in use, try a different one */
-				collision = 1;
+				collision = true;
 				break;
 			}
 		}
-		if (collision == 0) {
+
+		/*
+		 * if we have more than 32k mids in the list, then something
+		 * is very wrong. Possibly a local user is trying to DoS the
+		 * box by issuing long-running calls and SIGKILL'ing them. If
+		 * we get to 2^16 mids then we're in big trouble as this
+		 * function could loop forever.
+		 *
+		 * Go ahead and assign out the mid in this situation, but force
+		 * an eventual reconnect to clean out the pending_mid_q.
+		 */
+		if (num_mids > 32768)
+			server->tcpStatus = CifsNeedReconnect;
+
+		if (!collision) {
 			mid = server->CurrentMid;
 			break;
 		}
@@ -381,29 +392,31 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
 }
 
 static int
-checkSMBhdr(struct smb_hdr *smb, __u16 mid)
+check_smb_hdr(struct smb_hdr *smb, __u16 mid)
 {
-	/* Make sure that this really is an SMB, that it is a response,
-	   and that the message ids match */
-	if ((*(__le32 *) smb->Protocol == cpu_to_le32(0x424d53ff)) &&
-		(mid == smb->Mid)) {
-		if (smb->Flags & SMBFLG_RESPONSE)
-			return 0;
-		else {
-		/* only one valid case where server sends us request */
-			if (smb->Command == SMB_COM_LOCKING_ANDX)
-				return 0;
-			else
-				cERROR(1, "Received Request not response");
-		}
-	} else { /* bad signature or mid */
-		if (*(__le32 *) smb->Protocol != cpu_to_le32(0x424d53ff))
-			cERROR(1, "Bad protocol string signature header %x",
-				*(unsigned int *) smb->Protocol);
-		if (mid != smb->Mid)
-			cERROR(1, "Mids do not match");
+	/* does it have the right SMB "signature" ? */
+	if (*(__le32 *) smb->Protocol != cpu_to_le32(0x424d53ff)) {
+		cERROR(1, "Bad protocol string signature header 0x%x",
+			*(unsigned int *)smb->Protocol);
+		return 1;
 	}
-	cERROR(1, "bad smb detected. The Mid=%d", smb->Mid);
+
+	/* Make sure that message ids match */
+	if (mid != smb->Mid) {
+		cERROR(1, "Mids do not match. received=%u expected=%u",
+			smb->Mid, mid);
+		return 1;
+	}
+
+	/* if it's a response then accept */
+	if (smb->Flags & SMBFLG_RESPONSE)
+		return 0;
+
+	/* only one valid case where server sends us request */
+	if (smb->Command == SMB_COM_LOCKING_ANDX)
+		return 0;
+
+	cERROR(1, "Server sent request, not response. mid=%u", smb->Mid);
 	return 1;
 }
 
@@ -448,7 +461,7 @@ checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length)
 		return 1;
 	}
 
-	if (checkSMBhdr(smb, mid))
+	if (check_smb_hdr(smb, mid))
 		return 1;
 	clc_len = smbCalcSize_LE(smb);
 
@@ -465,25 +478,26 @@ checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length)
 			if (((4 + len) & 0xFFFF) == (clc_len & 0xFFFF))
 				return 0; /* bcc wrapped */
 		}
-		cFYI(1, "Calculated size %d vs length %d mismatch for mid %d",
+		cFYI(1, "Calculated size %u vs length %u mismatch for mid=%u",
 				clc_len, 4 + len, smb->Mid);
-		/* Windows XP can return a few bytes too much, presumably
-		an illegal pad, at the end of byte range lock responses
-		so we allow for that three byte pad, as long as actual
-		received length is as long or longer than calculated length */
-		/* We have now had to extend this more, since there is a
-		case in which it needs to be bigger still to handle a
-		malformed response to transact2 findfirst from WinXP when
-		access denied is returned and thus bcc and wct are zero
-		but server says length is 0x21 bytes too long as if the server
-		forget to reset the smb rfc1001 length when it reset the
-		wct and bcc to minimum size and drop the t2 parms and data */
-		if ((4+len > clc_len) && (len <= clc_len + 512))
-			return 0;
-		else {
-			cERROR(1, "RFC1001 size %d bigger than SMB for Mid=%d",
+
+		if (4 + len < clc_len) {
+			cERROR(1, "RFC1001 size %u smaller than SMB for mid=%u",
 					len, smb->Mid);
 			return 1;
+		} else if (len > clc_len + 512) {
+			/*
+			 * Some servers (Windows XP in particular) send more
+			 * data than the lengths in the SMB packet would
+			 * indicate on certain calls (byte range locks and
+			 * trans2 find first calls in particular). While the
+			 * client can handle such a frame by ignoring the
+			 * trailing data, we choose limit the amount of extra
+			 * data to 512 bytes.
+			 */
+			cERROR(1, "RFC1001 size %u more than 512 bytes larger "
+				  "than SMB for mid=%u", len, smb->Mid);
+			return 1;
 		}
 	}
 	return 0;
@@ -571,7 +585,7 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
 				pCifsInode = CIFS_I(netfile->dentry->d_inode);
 
 				cifs_set_oplock_level(pCifsInode,
-						      pSMB->OplockLevel);
+					pSMB->OplockLevel ? OPLOCK_READ : 0);
 				/*
 				 * cifs_oplock_break_put() can't be called
 				 * from here.  Get reference after queueing
@@ -637,77 +651,6 @@ dump_smb(struct smb_hdr *smb_buf, int smb_buf_length)
 	return;
 }
 
-/* Convert 16 bit Unicode pathname to wire format from string in current code
-   page.  Conversion may involve remapping up the seven characters that are
-   only legal in POSIX-like OS (if they are present in the string). Path
-   names are little endian 16 bit Unicode on the wire */
-int
-cifsConvertToUCS(__le16 *target, const char *source, int maxlen,
-		 const struct nls_table *cp, int mapChars)
-{
-	int i, j, charlen;
-	int len_remaining = maxlen;
-	char src_char;
-	__u16 temp;
-
-	if (!mapChars)
-		return cifs_strtoUCS(target, source, PATH_MAX, cp);
-
-	for (i = 0, j = 0; i < maxlen; j++) {
-		src_char = source[i];
-		switch (src_char) {
-			case 0:
-				target[j] = 0;
-				goto ctoUCS_out;
-			case ':':
-				target[j] = cpu_to_le16(UNI_COLON);
-				break;
-			case '*':
-				target[j] = cpu_to_le16(UNI_ASTERIK);
-				break;
-			case '?':
-				target[j] = cpu_to_le16(UNI_QUESTION);
-				break;
-			case '<':
-				target[j] = cpu_to_le16(UNI_LESSTHAN);
-				break;
-			case '>':
-				target[j] = cpu_to_le16(UNI_GRTRTHAN);
-				break;
-			case '|':
-				target[j] = cpu_to_le16(UNI_PIPE);
-				break;
-			/* BB We can not handle remapping slash until
-			   all the calls to build_path_from_dentry
-			   are modified, as they use slash as separator BB */
-			/* case '\\':
-				target[j] = cpu_to_le16(UNI_SLASH);
-				break;*/
-			default:
-				charlen = cp->char2uni(source+i,
-					len_remaining, &temp);
-				/* if no match, use question mark, which
-				at least in some cases servers as wild card */
-				if (charlen < 1) {
-					target[j] = cpu_to_le16(0x003f);
-					charlen = 1;
-				} else
-					target[j] = cpu_to_le16(temp);
-				len_remaining -= charlen;
-				/* character may take more than one byte in the
-				   the source string, but will take exactly two
-				   bytes in the target string */
-				i += charlen;
-				continue;
-		}
-		i++; /* move to next char in source string */
-		len_remaining--;
-	}
-
-ctoUCS_out:
-	return i;
-}
-
 void
 cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb)
 {
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index 9aad47a2d62f..8d9189f64477 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -899,8 +899,8 @@ map_smb_to_linux_error(struct smb_hdr *smb, int logErr)
 	}
 	/* else ERRHRD class errors or junk  - return EIO */
 
-	cFYI(1, "Mapping smb error code %d to POSIX err %d",
-		 smberrcode, rc);
+	cFYI(1, "Mapping smb error code 0x%x to POSIX err %d",
+		 le32_to_cpu(smb->Status.CifsError), rc);
 
 	/* generic corrective action e.g. reconnect SMB session on
 	 * ERRbaduid could be added */
@@ -916,14 +916,14 @@ unsigned int
 smbCalcSize(struct smb_hdr *ptr)
 {
 	return (sizeof(struct smb_hdr) + (2 * ptr->WordCount) +
-		2 /* size of the bcc field */ + BCC(ptr));
+		2 /* size of the bcc field */ + get_bcc(ptr));
 }
 
 unsigned int
 smbCalcSize_LE(struct smb_hdr *ptr)
 {
 	return (sizeof(struct smb_hdr) + (2 * ptr->WordCount) +
-		2 /* size of the bcc field */ + le16_to_cpu(BCC_LE(ptr)));
+		2 /* size of the bcc field */ + get_bcc_le(ptr));
 }
 
 /* The following are taken from fs/ntfs/util.c */
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 7f25cc3d2256..f8e4cd2a7912 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -764,7 +764,6 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir)
 {
 	int rc = 0;
 	int xid, i;
-	struct cifs_sb_info *cifs_sb;
 	struct cifsTconInfo *pTcon;
 	struct cifsFileInfo *cifsFile = NULL;
 	char *current_entry;
@@ -775,8 +774,6 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir)
 
 	xid = GetXid();
 
-	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
-
 	/*
 	 * Ensure FindFirst doesn't fail before doing filldir() for '.' and
 	 * '..'. Otherwise we won't be able to notify VFS in case of failure.
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index eb746486e49e..1adc9625a344 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -277,7 +277,7 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses,
 }
 
 static void
-decode_unicode_ssetup(char **pbcc_area, int bleft, struct cifsSesInfo *ses,
+decode_unicode_ssetup(char **pbcc_area, __u16 bleft, struct cifsSesInfo *ses,
 		      const struct nls_table *nls_cp)
 {
 	int len;
@@ -323,7 +323,7 @@ decode_unicode_ssetup(char **pbcc_area, int bleft, struct cifsSesInfo *ses,
 	return;
 }
 
-static int decode_ascii_ssetup(char **pbcc_area, int bleft,
+static int decode_ascii_ssetup(char **pbcc_area, __u16 bleft,
 			       struct cifsSesInfo *ses,
 			       const struct nls_table *nls_cp)
 {
@@ -575,12 +575,11 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses,
 	char *str_area;
 	SESSION_SETUP_ANDX *pSMB;
 	__u32 capabilities;
-	int count;
+	__u16 count;
 	int resp_buf_type;
 	struct kvec iov[3];
 	enum securityEnum type;
-	__u16 action;
-	int bytes_remaining;
+	__u16 action, bytes_remaining;
 	struct key *spnego_key = NULL;
 	__le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */
 	u16 blob_len;
@@ -876,10 +875,10 @@ ssetup_ntlmssp_authenticate:
 	count = iov[1].iov_len + iov[2].iov_len;
 	smb_buf->smb_buf_length += count;
 
-	BCC_LE(smb_buf) = cpu_to_le16(count);
+	put_bcc_le(count, smb_buf);
 
 	rc = SendReceive2(xid, ses, iov, 3 /* num_iovecs */, &resp_buf_type,
-			  CIFS_STD_OP /* not long */ | CIFS_LOG_ERROR);
+			  CIFS_LOG_ERROR);
 	/* SMB request buf freed in SendReceive2 */
 
 	pSMB = (SESSION_SETUP_ANDX *)iov[0].iov_base;
@@ -910,7 +909,7 @@ ssetup_ntlmssp_authenticate:
 	cFYI(1, "UID = %d ", ses->Suid);
 	/* response can have either 3 or 4 word count - Samba sends 3 */
 	/* and lanman response is 3 */
-	bytes_remaining = BCC(smb_buf);
+	bytes_remaining = get_bcc(smb_buf);
 	bcc_ptr = pByteArea(smb_buf);
 
 	if (smb_buf->WordCount == 4) {
diff --git a/fs/cifs/smbdes.c b/fs/cifs/smbdes.c
index b6b6dcb500bf..04721485925d 100644
--- a/fs/cifs/smbdes.c
+++ b/fs/cifs/smbdes.c
@@ -45,7 +45,6 @@
    up with a different answer to the one above)
 */
 #include <linux/slab.h>
-#include "cifsencrypt.h"
 #define uchar unsigned char
 
 static uchar perm1[56] = { 57, 49, 41, 33, 25, 17, 9,
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 192ea51af20f..b5041c849981 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -32,9 +32,8 @@
 #include "cifs_unicode.h"
 #include "cifspdu.h"
 #include "cifsglob.h"
-#include "md5.h"
 #include "cifs_debug.h"
-#include "cifsencrypt.h"
+#include "cifsproto.h"
 
 #ifndef false
 #define false 0
@@ -48,14 +47,58 @@
 #define SSVALX(buf,pos,val) (CVAL(buf,pos)=(val)&0xFF,CVAL(buf,pos+1)=(val)>>8)
 #define SSVAL(buf,pos,val) SSVALX((buf),(pos),((__u16)(val)))
 
-/*The following definitions come from  libsmb/smbencrypt.c  */
+/* produce a md4 message digest from data of length n bytes */
+int
+mdfour(unsigned char *md4_hash, unsigned char *link_str, int link_len)
+{
+	int rc;
+	unsigned int size;
+	struct crypto_shash *md4;
+	struct sdesc *sdescmd4;
+
+	md4 = crypto_alloc_shash("md4", 0, 0);
+	if (IS_ERR(md4)) {
+		rc = PTR_ERR(md4);
+		cERROR(1, "%s: Crypto md4 allocation error %d\n", __func__, rc);
+		return rc;
+	}
+	size = sizeof(struct shash_desc) + crypto_shash_descsize(md4);
+	sdescmd4 = kmalloc(size, GFP_KERNEL);
+	if (!sdescmd4) {
+		rc = -ENOMEM;
+		cERROR(1, "%s: Memory allocation failure\n", __func__);
+		goto mdfour_err;
+	}
+	sdescmd4->shash.tfm = md4;
+	sdescmd4->shash.flags = 0x0;
+
+	rc = crypto_shash_init(&sdescmd4->shash);
+	if (rc) {
+		cERROR(1, "%s: Could not init md4 shash\n", __func__);
+		goto mdfour_err;
+	}
+	crypto_shash_update(&sdescmd4->shash, link_str, link_len);
+	rc = crypto_shash_final(&sdescmd4->shash, md4_hash);
 
-void SMBencrypt(unsigned char *passwd, const unsigned char *c8,
-		unsigned char *p24);
-void E_md4hash(const unsigned char *passwd, unsigned char *p16);
-static void SMBOWFencrypt(unsigned char passwd[16], const unsigned char *c8,
-		   unsigned char p24[24]);
-void SMBNTencrypt(unsigned char *passwd, unsigned char *c8, unsigned char *p24);
+mdfour_err:
+	crypto_free_shash(md4);
+	kfree(sdescmd4);
+
+	return rc;
+}
+
+/* Does the des encryption from the NT or LM MD4 hash. */
+static void
+SMBOWFencrypt(unsigned char passwd[16], const unsigned char *c8,
+	      unsigned char p24[24])
+{
+	unsigned char p21[21];
+
+	memset(p21, '\0', 21);
+
+	memcpy(p21, passwd, 16);
+	E_P24(p21, c8, p24);
+}
 
 /*
    This implements the X/Open SMB password encryption
@@ -118,9 +161,10 @@ _my_mbstowcs(__u16 *dst, const unsigned char *src, int len)
  * Creates the MD4 Hash of the users password in NT UNICODE.
  */
 
-void
+int
 E_md4hash(const unsigned char *passwd, unsigned char *p16)
 {
+	int rc;
 	int len;
 	__u16 wpwd[129];
 
@@ -139,8 +183,10 @@ E_md4hash(const unsigned char *passwd, unsigned char *p16)
 	/* Calculate length in bytes */
 	len = _my_wcslen(wpwd) * sizeof(__u16);
 
-	mdfour(p16, (unsigned char *) wpwd, len);
+	rc = mdfour(p16, (unsigned char *) wpwd, len);
 	memset(wpwd, 0, 129 * 2);
+
+	return rc;
 }
 
 #if 0 /* currently unused */
@@ -212,19 +258,6 @@ ntv2_owf_gen(const unsigned char owf[16], const char *user_n,
 }
 #endif
 
-/* Does the des encryption from the NT or LM MD4 hash. */
-static void
-SMBOWFencrypt(unsigned char passwd[16], const unsigned char *c8,
-	      unsigned char p24[24])
-{
-	unsigned char p21[21];
-
-	memset(p21, '\0', 21);
-
-	memcpy(p21, passwd, 16);
-	E_P24(p21, c8, p24);
-}
-
 /* Does the des encryption from the FIRST 8 BYTES of the NT or LM MD4 hash. */
 #if 0 /* currently unused */
 static void
@@ -242,16 +275,21 @@ NTLMSSPOWFencrypt(unsigned char passwd[8],
 #endif
 
 /* Does the NT MD4 hash then des encryption. */
-
-void
+int
 SMBNTencrypt(unsigned char *passwd, unsigned char *c8, unsigned char *p24)
 {
+	int rc;
 	unsigned char p21[21];
 
 	memset(p21, '\0', 21);
 
-	E_md4hash(passwd, p21);
+	rc = E_md4hash(passwd, p21);
+	if (rc) {
+		cFYI(1, "%s Can't generate NT hash, error: %d", __func__, rc);
+		return rc;
+	}
 	SMBOWFencrypt(p21, c8, p24);
+	return rc;
 }
 
 
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 59ca81b16919..46d8756f2b24 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -36,7 +36,13 @@
 
 extern mempool_t *cifs_mid_poolp;
 
-static struct mid_q_entry *
+static void
+wake_up_task(struct mid_q_entry *mid)
+{
+	wake_up_process(mid->callback_data);
+}
+
+struct mid_q_entry *
 AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 {
 	struct mid_q_entry *temp;
@@ -58,28 +64,28 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 	/*	do_gettimeofday(&temp->when_sent);*/ /* easier to use jiffies */
 		/* when mid allocated can be before when sent */
 		temp->when_alloc = jiffies;
-		temp->tsk = current;
+
+		/*
+		 * The default is for the mid to be synchronous, so the
+		 * default callback just wakes up the current task.
+		 */
+		temp->callback = wake_up_task;
+		temp->callback_data = current;
 	}
 
-	spin_lock(&GlobalMid_Lock);
-	list_add_tail(&temp->qhead, &server->pending_mid_q);
 	atomic_inc(&midCount);
 	temp->midState = MID_REQUEST_ALLOCATED;
-	spin_unlock(&GlobalMid_Lock);
 	return temp;
 }
 
-static void
+void
 DeleteMidQEntry(struct mid_q_entry *midEntry)
 {
 #ifdef CONFIG_CIFS_STATS2
 	unsigned long now;
 #endif
-	spin_lock(&GlobalMid_Lock);
 	midEntry->midState = MID_FREE;
-	list_del(&midEntry->qhead);
 	atomic_dec(&midCount);
-	spin_unlock(&GlobalMid_Lock);
 	if (midEntry->largeBuf)
 		cifs_buf_release(midEntry->resp_buf);
 	else
@@ -103,6 +109,16 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 	mempool_free(midEntry, cifs_mid_poolp);
 }
 
+static void
+delete_mid(struct mid_q_entry *mid)
+{
+	spin_lock(&GlobalMid_Lock);
+	list_del(&mid->qhead);
+	spin_unlock(&GlobalMid_Lock);
+
+	DeleteMidQEntry(mid);
+}
+
 static int
 smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
 {
@@ -220,9 +236,9 @@ smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
 		server->tcpStatus = CifsNeedReconnect;
 	}
 
-	if (rc < 0) {
+	if (rc < 0 && rc != -EINTR)
 		cERROR(1, "Error %d sending data on socket to server", rc);
-	} else
+	else
 		rc = 0;
 
 	/* Don't want to modify the buffer as a
@@ -244,31 +260,31 @@ smb_send(struct TCP_Server_Info *server, struct smb_hdr *smb_buffer,
 	return smb_sendv(server, &iov, 1);
 }
 
-static int wait_for_free_request(struct cifsSesInfo *ses, const int long_op)
+static int wait_for_free_request(struct TCP_Server_Info *server,
+				 const int long_op)
 {
 	if (long_op == CIFS_ASYNC_OP) {
 		/* oplock breaks must not be held up */
-		atomic_inc(&ses->server->inFlight);
+		atomic_inc(&server->inFlight);
 		return 0;
 	}
 
 	spin_lock(&GlobalMid_Lock);
 	while (1) {
-		if (atomic_read(&ses->server->inFlight) >=
-				cifs_max_pending){
+		if (atomic_read(&server->inFlight) >= cifs_max_pending) {
 			spin_unlock(&GlobalMid_Lock);
 #ifdef CONFIG_CIFS_STATS2
-			atomic_inc(&ses->server->num_waiters);
+			atomic_inc(&server->num_waiters);
 #endif
-			wait_event(ses->server->request_q,
-				   atomic_read(&ses->server->inFlight)
+			wait_event(server->request_q,
+				   atomic_read(&server->inFlight)
 				     < cifs_max_pending);
 #ifdef CONFIG_CIFS_STATS2
-			atomic_dec(&ses->server->num_waiters);
+			atomic_dec(&server->num_waiters);
 #endif
 			spin_lock(&GlobalMid_Lock);
 		} else {
-			if (ses->server->tcpStatus == CifsExiting) {
+			if (server->tcpStatus == CifsExiting) {
 				spin_unlock(&GlobalMid_Lock);
 				return -ENOENT;
 			}
@@ -278,7 +294,7 @@ static int wait_for_free_request(struct cifsSesInfo *ses, const int long_op)
 
 			/* update # of requests on the wire to server */
 			if (long_op != CIFS_BLOCKING_OP)
-				atomic_inc(&ses->server->inFlight);
+				atomic_inc(&server->inFlight);
 			spin_unlock(&GlobalMid_Lock);
 			break;
 		}
@@ -308,53 +324,85 @@ static int allocate_mid(struct cifsSesInfo *ses, struct smb_hdr *in_buf,
 	*ppmidQ = AllocMidQEntry(in_buf, ses->server);
 	if (*ppmidQ == NULL)
 		return -ENOMEM;
+	spin_lock(&GlobalMid_Lock);
+	list_add_tail(&(*ppmidQ)->qhead, &ses->server->pending_mid_q);
+	spin_unlock(&GlobalMid_Lock);
 	return 0;
 }
 
-static int wait_for_response(struct cifsSesInfo *ses,
-			struct mid_q_entry *midQ,
-			unsigned long timeout,
-			unsigned long time_to_wait)
+static int
+wait_for_response(struct TCP_Server_Info *server, struct mid_q_entry *midQ)
 {
-	unsigned long curr_timeout;
+	int error;
 
-	for (;;) {
-		curr_timeout = timeout + jiffies;
-		wait_event_timeout(ses->server->response_q,
-			midQ->midState != MID_REQUEST_SUBMITTED, timeout);
+	error = wait_event_killable(server->response_q,
+				    midQ->midState != MID_REQUEST_SUBMITTED);
+	if (error < 0)
+		return -ERESTARTSYS;
 
-		if (time_after(jiffies, curr_timeout) &&
-			(midQ->midState == MID_REQUEST_SUBMITTED) &&
-			((ses->server->tcpStatus == CifsGood) ||
-			 (ses->server->tcpStatus == CifsNew))) {
+	return 0;
+}
 
-			unsigned long lrt;
 
-			/* We timed out. Is the server still
-			   sending replies ? */
-			spin_lock(&GlobalMid_Lock);
-			lrt = ses->server->lstrp;
-			spin_unlock(&GlobalMid_Lock);
+/*
+ * Send a SMB request and set the callback function in the mid to handle
+ * the result. Caller is responsible for dealing with timeouts.
+ */
+int
+cifs_call_async(struct TCP_Server_Info *server, struct smb_hdr *in_buf,
+		mid_callback_t *callback, void *cbdata)
+{
+	int rc;
+	struct mid_q_entry *mid;
 
-			/* Calculate time_to_wait past last receive time.
-			 Although we prefer not to time out if the
-			 server is still responding - we will time
-			 out if the server takes more than 15 (or 45
-			 or 180) seconds to respond to this request
-			 and has not responded to any request from
-			 other threads on the client within 10 seconds */
-			lrt += time_to_wait;
-			if (time_after(jiffies, lrt)) {
-				/* No replies for time_to_wait. */
-				cERROR(1, "server not responding");
-				return -1;
-			}
-		} else {
-			return 0;
-		}
+	rc = wait_for_free_request(server, CIFS_ASYNC_OP);
+	if (rc)
+		return rc;
+
+	/* enable signing if server requires it */
+	if (server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
+		in_buf->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
+
+	mutex_lock(&server->srv_mutex);
+	mid = AllocMidQEntry(in_buf, server);
+	if (mid == NULL) {
+		mutex_unlock(&server->srv_mutex);
+		return -ENOMEM;
 	}
-}
 
+	/* put it on the pending_mid_q */
+	spin_lock(&GlobalMid_Lock);
+	list_add_tail(&mid->qhead, &server->pending_mid_q);
+	spin_unlock(&GlobalMid_Lock);
+
+	rc = cifs_sign_smb(in_buf, server, &mid->sequence_number);
+	if (rc) {
+		mutex_unlock(&server->srv_mutex);
+		goto out_err;
+	}
+
+	mid->callback = callback;
+	mid->callback_data = cbdata;
+	mid->midState = MID_REQUEST_SUBMITTED;
+#ifdef CONFIG_CIFS_STATS2
+	atomic_inc(&server->inSend);
+#endif
+	rc = smb_send(server, in_buf, in_buf->smb_buf_length);
+#ifdef CONFIG_CIFS_STATS2
+	atomic_dec(&server->inSend);
+	mid->when_sent = jiffies;
+#endif
+	mutex_unlock(&server->srv_mutex);
+	if (rc)
+		goto out_err;
+
+	return rc;
+out_err:
+	delete_mid(mid);
+	atomic_dec(&server->inFlight);
+	wake_up(&server->request_q);
+	return rc;
+}
 
 /*
  *
@@ -382,6 +430,84 @@ SendReceiveNoRsp(const unsigned int xid, struct cifsSesInfo *ses,
 	return rc;
 }
 
+static int
+sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
+{
+	int rc = 0;
+
+	cFYI(1, "%s: cmd=%d mid=%d state=%d", __func__, mid->command,
+		mid->mid, mid->midState);
+
+	spin_lock(&GlobalMid_Lock);
+	/* ensure that it's no longer on the pending_mid_q */
+	list_del_init(&mid->qhead);
+
+	switch (mid->midState) {
+	case MID_RESPONSE_RECEIVED:
+		spin_unlock(&GlobalMid_Lock);
+		return rc;
+	case MID_REQUEST_SUBMITTED:
+		/* socket is going down, reject all calls */
+		if (server->tcpStatus == CifsExiting) {
+			cERROR(1, "%s: canceling mid=%d cmd=0x%x state=%d",
+			       __func__, mid->mid, mid->command, mid->midState);
+			rc = -EHOSTDOWN;
+			break;
+		}
+	case MID_RETRY_NEEDED:
+		rc = -EAGAIN;
+		break;
+	case MID_RESPONSE_MALFORMED:
+		rc = -EIO;
+		break;
+	default:
+		cERROR(1, "%s: invalid mid state mid=%d state=%d", __func__,
+			mid->mid, mid->midState);
+		rc = -EIO;
+	}
+	spin_unlock(&GlobalMid_Lock);
+
+	DeleteMidQEntry(mid);
+	return rc;
+}
+
+/*
+ * An NT cancel request header looks just like the original request except:
+ *
+ * The Command is SMB_COM_NT_CANCEL
+ * The WordCount is zeroed out
+ * The ByteCount is zeroed out
+ *
+ * This function mangles an existing request buffer into a
+ * SMB_COM_NT_CANCEL request and then sends it.
+ */
+static int
+send_nt_cancel(struct TCP_Server_Info *server, struct smb_hdr *in_buf,
+		struct mid_q_entry *mid)
+{
+	int rc = 0;
+
+	/* -4 for RFC1001 length and +2 for BCC field */
+	in_buf->smb_buf_length = sizeof(struct smb_hdr) - 4  + 2;
+	in_buf->Command = SMB_COM_NT_CANCEL;
+	in_buf->WordCount = 0;
+	put_bcc_le(0, in_buf);
+
+	mutex_lock(&server->srv_mutex);
+	rc = cifs_sign_smb(in_buf, server, &mid->sequence_number);
+	if (rc) {
+		mutex_unlock(&server->srv_mutex);
+		return rc;
+	}
+	rc = smb_send(server, in_buf, in_buf->smb_buf_length);
+	mutex_unlock(&server->srv_mutex);
+
+	cFYI(1, "issued NT_CANCEL for mid %u, rc = %d",
+		in_buf->Mid, rc);
+
+	return rc;
+}
+
 int
 SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
 	     struct kvec *iov, int n_vec, int *pRespBufType /* ret */,
@@ -390,7 +516,6 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
 	int rc = 0;
 	int long_op;
 	unsigned int receive_len;
-	unsigned long timeout;
 	struct mid_q_entry *midQ;
 	struct smb_hdr *in_buf = iov[0].iov_base;
 
@@ -413,7 +538,7 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
 	   to the same server. We may make this configurable later or
 	   use ses->maxReq */
 
-	rc = wait_for_free_request(ses, long_op);
+	rc = wait_for_free_request(ses->server, long_op);
 	if (rc) {
 		cifs_small_buf_release(in_buf);
 		return rc;
@@ -452,70 +577,41 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
 #endif
 
 	mutex_unlock(&ses->server->srv_mutex);
-	cifs_small_buf_release(in_buf);
 
-	if (rc < 0)
-		goto out;
-
-	if (long_op == CIFS_STD_OP)
-		timeout = 15 * HZ;
-	else if (long_op == CIFS_VLONG_OP) /* e.g. slow writes past EOF */
-		timeout = 180 * HZ;
-	else if (long_op == CIFS_LONG_OP)
-		timeout = 45 * HZ; /* should be greater than
-			servers oplock break timeout (about 43 seconds) */
-	else if (long_op == CIFS_ASYNC_OP)
-		goto out;
-	else if (long_op == CIFS_BLOCKING_OP)
-		timeout = 0x7FFFFFFF; /*  large, but not so large as to wrap */
-	else {
-		cERROR(1, "unknown timeout flag %d", long_op);
-		rc = -EIO;
+	if (rc < 0) {
+		cifs_small_buf_release(in_buf);
 		goto out;
 	}
 
-	/* wait for 15 seconds or until woken up due to response arriving or
-	   due to last connection to this server being unmounted */
-	if (signal_pending(current)) {
-		/* if signal pending do not hold up user for full smb timeout
-		but we still give response a chance to complete */
-		timeout = 2 * HZ;
+	if (long_op == CIFS_ASYNC_OP) {
+		cifs_small_buf_release(in_buf);
+		goto out;
 	}
 
-	/* No user interrupts in wait - wreaks havoc with performance */
-	wait_for_response(ses, midQ, timeout, 10 * HZ);
-
-	spin_lock(&GlobalMid_Lock);
-
-	if (midQ->resp_buf == NULL) {
-		cERROR(1, "No response to cmd %d mid %d",
-			midQ->command, midQ->mid);
+	rc = wait_for_response(ses->server, midQ);
+	if (rc != 0) {
+		send_nt_cancel(ses->server, in_buf, midQ);
+		spin_lock(&GlobalMid_Lock);
 		if (midQ->midState == MID_REQUEST_SUBMITTED) {
-			if (ses->server->tcpStatus == CifsExiting)
-				rc = -EHOSTDOWN;
-			else {
-				ses->server->tcpStatus = CifsNeedReconnect;
-				midQ->midState = MID_RETRY_NEEDED;
-			}
-		}
-
-		if (rc != -EHOSTDOWN) {
-			if (midQ->midState == MID_RETRY_NEEDED) {
-				rc = -EAGAIN;
-				cFYI(1, "marking request for retry");
-			} else {
-				rc = -EIO;
-			}
+			midQ->callback = DeleteMidQEntry;
+			spin_unlock(&GlobalMid_Lock);
+			cifs_small_buf_release(in_buf);
+			atomic_dec(&ses->server->inFlight);
+			wake_up(&ses->server->request_q);
+			return rc;
 		}
 		spin_unlock(&GlobalMid_Lock);
-		DeleteMidQEntry(midQ);
-		/* Update # of requests on wire to server */
+	}
+
+	cifs_small_buf_release(in_buf);
+
+	rc = sync_mid_result(midQ, ses->server);
+	if (rc != 0) {
 		atomic_dec(&ses->server->inFlight);
 		wake_up(&ses->server->request_q);
 		return rc;
 	}
 
-	spin_unlock(&GlobalMid_Lock);
 	receive_len = midQ->resp_buf->smb_buf_length;
 
 	if (receive_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
@@ -559,19 +655,18 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
 		if (receive_len >= sizeof(struct smb_hdr) - 4
 		    /* do not count RFC1001 header */  +
 		    (2 * midQ->resp_buf->WordCount) + 2 /* bcc */ )
-			BCC(midQ->resp_buf) =
-				le16_to_cpu(BCC_LE(midQ->resp_buf));
+			put_bcc(get_bcc_le(midQ->resp_buf), midQ->resp_buf);
 		if ((flags & CIFS_NO_RESP) == 0)
 			midQ->resp_buf = NULL;  /* mark it so buf will
 						   not be freed by
-						   DeleteMidQEntry */
+						   delete_mid */
 	} else {
 		rc = -EIO;
 		cFYI(1, "Bad MID state?");
 	}
 
 out:
-	DeleteMidQEntry(midQ);
+	delete_mid(midQ);
 	atomic_dec(&ses->server->inFlight);
 	wake_up(&ses->server->request_q);
 
@@ -585,7 +680,6 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses,
 {
 	int rc = 0;
 	unsigned int receive_len;
-	unsigned long timeout;
 	struct mid_q_entry *midQ;
 
 	if (ses == NULL) {
@@ -610,7 +704,7 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses,
 		return -EIO;
 	}
 
-	rc = wait_for_free_request(ses, long_op);
+	rc = wait_for_free_request(ses->server, long_op);
 	if (rc)
 		return rc;
 
@@ -649,64 +743,31 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses,
 	if (rc < 0)
 		goto out;
 
-	if (long_op == CIFS_STD_OP)
-		timeout = 15 * HZ;
-	/* wait for 15 seconds or until woken up due to response arriving or
-	   due to last connection to this server being unmounted */
-	else if (long_op == CIFS_ASYNC_OP)
-		goto out;
-	else if (long_op == CIFS_VLONG_OP) /* writes past EOF can be slow */
-		timeout = 180 * HZ;
-	else if (long_op == CIFS_LONG_OP)
-		timeout = 45 * HZ; /* should be greater than
-			servers oplock break timeout (about 43 seconds) */
-	else if (long_op == CIFS_BLOCKING_OP)
-		timeout = 0x7FFFFFFF; /* large but no so large as to wrap */
-	else {
-		cERROR(1, "unknown timeout flag %d", long_op);
-		rc = -EIO;
+	if (long_op == CIFS_ASYNC_OP)
 		goto out;
-	}
-
-	if (signal_pending(current)) {
-		/* if signal pending do not hold up user for full smb timeout
-		but we still give response a chance to complete */
-		timeout = 2 * HZ;
-	}
-
-	/* No user interrupts in wait - wreaks havoc with performance */
-	wait_for_response(ses, midQ, timeout, 10 * HZ);
 
-	spin_lock(&GlobalMid_Lock);
-	if (midQ->resp_buf == NULL) {
-		cERROR(1, "No response for cmd %d mid %d",
-			  midQ->command, midQ->mid);
+	rc = wait_for_response(ses->server, midQ);
+	if (rc != 0) {
+		send_nt_cancel(ses->server, in_buf, midQ);
+		spin_lock(&GlobalMid_Lock);
 		if (midQ->midState == MID_REQUEST_SUBMITTED) {
-			if (ses->server->tcpStatus == CifsExiting)
-				rc = -EHOSTDOWN;
-			else {
-				ses->server->tcpStatus = CifsNeedReconnect;
-				midQ->midState = MID_RETRY_NEEDED;
-			}
-		}
-
-		if (rc != -EHOSTDOWN) {
-			if (midQ->midState == MID_RETRY_NEEDED) {
-				rc = -EAGAIN;
-				cFYI(1, "marking request for retry");
-			} else {
-				rc = -EIO;
-			}
+			/* no longer considered to be "in-flight" */
+			midQ->callback = DeleteMidQEntry;
+			spin_unlock(&GlobalMid_Lock);
+			atomic_dec(&ses->server->inFlight);
+			wake_up(&ses->server->request_q);
+			return rc;
 		}
 		spin_unlock(&GlobalMid_Lock);
-		DeleteMidQEntry(midQ);
-		/* Update # of requests on wire to server */
+	}
+
+	rc = sync_mid_result(midQ, ses->server);
+	if (rc != 0) {
 		atomic_dec(&ses->server->inFlight);
 		wake_up(&ses->server->request_q);
 		return rc;
 	}
 
-	spin_unlock(&GlobalMid_Lock);
 	receive_len = midQ->resp_buf->smb_buf_length;
 
 	if (receive_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
@@ -748,43 +809,20 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses,
 		if (receive_len >= sizeof(struct smb_hdr) - 4
 		    /* do not count RFC1001 header */  +
 		    (2 * out_buf->WordCount) + 2 /* bcc */ )
-			BCC(out_buf) = le16_to_cpu(BCC_LE(out_buf));
+			put_bcc(get_bcc_le(midQ->resp_buf), midQ->resp_buf);
 	} else {
 		rc = -EIO;
 		cERROR(1, "Bad MID state?");
 	}
 
 out:
-	DeleteMidQEntry(midQ);
+	delete_mid(midQ);
 	atomic_dec(&ses->server->inFlight);
 	wake_up(&ses->server->request_q);
 
 	return rc;
 }
 
-/* Send an NT_CANCEL SMB to cause the POSIX blocking lock to return. */
-
-static int
-send_nt_cancel(struct cifsTconInfo *tcon, struct smb_hdr *in_buf,
-		struct mid_q_entry *midQ)
-{
-	int rc = 0;
-	struct cifsSesInfo *ses = tcon->ses;
-	__u16 mid = in_buf->Mid;
-
-	header_assemble(in_buf, SMB_COM_NT_CANCEL, tcon, 0);
-	in_buf->Mid = mid;
-	mutex_lock(&ses->server->srv_mutex);
-	rc = cifs_sign_smb(in_buf, ses->server, &midQ->sequence_number);
-	if (rc) {
-		mutex_unlock(&ses->server->srv_mutex);
-		return rc;
-	}
-	rc = smb_send(ses->server, in_buf, in_buf->smb_buf_length);
-	mutex_unlock(&ses->server->srv_mutex);
-	return rc;
-}
-
 /* We send a LOCKINGX_CANCEL_LOCK to cause the Windows
    blocking lock to return. */
 
@@ -807,7 +845,7 @@ send_lock_cancel(const unsigned int xid, struct cifsTconInfo *tcon,
 	pSMB->hdr.Mid = GetNextMid(ses->server);
 
 	return SendReceive(xid, ses, in_buf, out_buf,
-			&bytes_returned, CIFS_STD_OP);
+			&bytes_returned, 0);
 }
 
 int
@@ -845,7 +883,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
 		return -EIO;
 	}
 
-	rc = wait_for_free_request(ses, CIFS_BLOCKING_OP);
+	rc = wait_for_free_request(ses->server, CIFS_BLOCKING_OP);
 	if (rc)
 		return rc;
 
@@ -863,7 +901,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
 
 	rc = cifs_sign_smb(in_buf, ses->server, &midQ->sequence_number);
 	if (rc) {
-		DeleteMidQEntry(midQ);
+		delete_mid(midQ);
 		mutex_unlock(&ses->server->srv_mutex);
 		return rc;
 	}
@@ -880,7 +918,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
 	mutex_unlock(&ses->server->srv_mutex);
 
 	if (rc < 0) {
-		DeleteMidQEntry(midQ);
+		delete_mid(midQ);
 		return rc;
 	}
 
@@ -899,10 +937,9 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
 		if (in_buf->Command == SMB_COM_TRANSACTION2) {
 			/* POSIX lock. We send a NT_CANCEL SMB to cause the
 			   blocking lock to return. */
-
-			rc = send_nt_cancel(tcon, in_buf, midQ);
+			rc = send_nt_cancel(ses->server, in_buf, midQ);
 			if (rc) {
-				DeleteMidQEntry(midQ);
+				delete_mid(midQ);
 				return rc;
 			}
 		} else {
@@ -914,47 +951,33 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
 			/* If we get -ENOLCK back the lock may have
 			   already been removed. Don't exit in this case. */
 			if (rc && rc != -ENOLCK) {
-				DeleteMidQEntry(midQ);
+				delete_mid(midQ);
 				return rc;
 			}
 		}
 
-		/* Wait 5 seconds for the response. */
-		if (wait_for_response(ses, midQ, 5 * HZ, 5 * HZ) == 0) {
-			/* We got the response - restart system call. */
-			rstart = 1;
-		}
-	}
-
-	spin_lock(&GlobalMid_Lock);
-	if (midQ->resp_buf) {
-		spin_unlock(&GlobalMid_Lock);
-		receive_len = midQ->resp_buf->smb_buf_length;
-	} else {
-		cERROR(1, "No response for cmd %d mid %d",
-			  midQ->command, midQ->mid);
-		if (midQ->midState == MID_REQUEST_SUBMITTED) {
-			if (ses->server->tcpStatus == CifsExiting)
-				rc = -EHOSTDOWN;
-			else {
-				ses->server->tcpStatus = CifsNeedReconnect;
-				midQ->midState = MID_RETRY_NEEDED;
+		rc = wait_for_response(ses->server, midQ);
+		if (rc) {
+			send_nt_cancel(ses->server, in_buf, midQ);
+			spin_lock(&GlobalMid_Lock);
+			if (midQ->midState == MID_REQUEST_SUBMITTED) {
+				/* no longer considered to be "in-flight" */
+				midQ->callback = DeleteMidQEntry;
+				spin_unlock(&GlobalMid_Lock);
+				return rc;
 			}
+			spin_unlock(&GlobalMid_Lock);
 		}
 
-		if (rc != -EHOSTDOWN) {
-			if (midQ->midState == MID_RETRY_NEEDED) {
-				rc = -EAGAIN;
-				cFYI(1, "marking request for retry");
-			} else {
-				rc = -EIO;
-			}
-		}
-		spin_unlock(&GlobalMid_Lock);
-		DeleteMidQEntry(midQ);
-		return rc;
+		/* We got the response - restart system call. */
+		rstart = 1;
 	}
 
+	rc = sync_mid_result(midQ, ses->server);
+	if (rc != 0)
+		return rc;
+
+	receive_len = midQ->resp_buf->smb_buf_length;
 	if (receive_len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) {
 		cERROR(1, "Frame too large received.  Length: %d  Xid: %d",
 			receive_len, xid);
@@ -998,10 +1021,10 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
 	if (receive_len >= sizeof(struct smb_hdr) - 4
 	    /* do not count RFC1001 header */  +
 	    (2 * out_buf->WordCount) + 2 /* bcc */ )
-		BCC(out_buf) = le16_to_cpu(BCC_LE(out_buf));
+		put_bcc(get_bcc_le(out_buf), out_buf);
 
 out:
-	DeleteMidQEntry(midQ);
+	delete_mid(midQ);
 	if (rstart && rc == -EACCES)
 		return -ERESTARTSYS;
 	return rc;
diff --git a/fs/compat.c b/fs/compat.c
index eb1740ac8c0a..f6fd0a00e6cc 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -257,7 +257,7 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *
 }
 
 /*
- * The following statfs calls are copies of code from fs/open.c and
+ * The following statfs calls are copies of code from fs/statfs.c and
  * should be checked against those from time to time
  */
 asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf)
@@ -320,7 +320,9 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat
 	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
 	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
 	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
-	    __put_user(kbuf->f_frsize, &ubuf->f_frsize))
+	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
+	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
+	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
 		return -EFAULT;
 	return 0;
 }
@@ -597,10 +599,8 @@ ssize_t compat_rw_copy_check_uvector(int type,
 	if (nr_segs > fast_segs) {
 		ret = -ENOMEM;
 		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
-		if (iov == NULL) {
-			*ret_pointer = fast_pointer;
+		if (iov == NULL)
 			goto out;
-		}
 	}
 	*ret_pointer = iov;
 
diff --git a/fs/configfs/Kconfig b/fs/configfs/Kconfig
index 13587cc97a0b..9febcdefdfdc 100644
--- a/fs/configfs/Kconfig
+++ b/fs/configfs/Kconfig
@@ -1,8 +1,8 @@
 config CONFIGFS_FS
 	tristate "Userspace-driven configuration filesystem"
-	depends on SYSFS
+	select SYSFS
 	help
-	  configfs is a ram-based filesystem that provides the converse
+	  configfs is a RAM-based filesystem that provides the converse
 	  of sysfs's functionality. Where sysfs is a filesystem-based
 	  view of kernel objects, configfs is a filesystem-based manager
 	  of kernel objects, or config_items.
diff --git a/fs/dcache.c b/fs/dcache.c
index 0c6d5c549d84..2a6bd9a4ae97 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -176,6 +176,7 @@ static void d_free(struct dentry *dentry)
 
 /**
  * dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
+ * @dentry: the target dentry
  * After this call, in-progress rcu-walk path lookup will fail. This
  * should be called after unhashing, and after changing d_inode (if
  * the dentry has not already been unhashed).
@@ -281,6 +282,7 @@ static void dentry_lru_move_tail(struct dentry *dentry)
 /**
  * d_kill - kill dentry and return parent
  * @dentry: dentry to kill
+ * @parent: parent dentry
  *
  * The dentry must already be unhashed and removed from the LRU.
  *
@@ -1357,8 +1359,8 @@ EXPORT_SYMBOL(d_alloc_name);
 
 void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 {
-	BUG_ON(dentry->d_op);
-	BUG_ON(dentry->d_flags & (DCACHE_OP_HASH	|
+	WARN_ON_ONCE(dentry->d_op);
+	WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH	|
 				DCACHE_OP_COMPARE	|
 				DCACHE_OP_REVALIDATE	|
 				DCACHE_OP_DELETE ));
@@ -1380,8 +1382,11 @@ EXPORT_SYMBOL(d_set_d_op);
 static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 {
 	spin_lock(&dentry->d_lock);
-	if (inode)
+	if (inode) {
+		if (unlikely(IS_AUTOMOUNT(inode)))
+			dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
 		list_add(&dentry->d_alias, &inode->i_dentry);
+	}
 	dentry->d_inode = inode;
 	dentry_rcuwalk_barrier(dentry);
 	spin_unlock(&dentry->d_lock);
@@ -1970,7 +1975,7 @@ out:
 /**
  * d_validate - verify dentry provided from insecure source (deprecated)
  * @dentry: The dentry alleged to be valid child of @dparent
- * @parent: The parent dentry (known to be valid)
+ * @dparent: The parent dentry (known to be valid)
  *
  * An insecure source has sent us a dentry, here we verify it and dget() it.
  * This is used by ncpfs in its readdir implementation.
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 8201c2558d85..dcb5577cde1d 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -325,12 +325,16 @@ void dio_end_io(struct bio *bio, int error)
 }
 EXPORT_SYMBOL_GPL(dio_end_io);
 
-static int
+static void
 dio_bio_alloc(struct dio *dio, struct block_device *bdev,
 		sector_t first_sector, int nr_vecs)
 {
 	struct bio *bio;
 
+	/*
+	 * bio_alloc() is guaranteed to return a bio when called with
+	 * __GFP_WAIT and we request a valid number of vectors.
+	 */
 	bio = bio_alloc(GFP_KERNEL, nr_vecs);
 
 	bio->bi_bdev = bdev;
@@ -342,7 +346,6 @@ dio_bio_alloc(struct dio *dio, struct block_device *bdev,
 
 	dio->bio = bio;
 	dio->logical_offset_in_bio = dio->cur_page_fs_offset;
-	return 0;
 }
 
 /*
@@ -583,8 +586,9 @@ static int dio_new_bio(struct dio *dio, sector_t start_sector)
 		goto out;
 	sector = start_sector << (dio->blkbits - 9);
 	nr_pages = min(dio->pages_in_io, bio_get_nr_vecs(dio->map_bh.b_bdev));
+	nr_pages = min(nr_pages, BIO_MAX_PAGES);
 	BUG_ON(nr_pages <= 0);
-	ret = dio_bio_alloc(dio, dio->map_bh.b_bdev, sector, nr_pages);
+	dio_bio_alloc(dio, dio->map_bh.b_bdev, sector, nr_pages);
 	dio->boundary = 0;
 out:
 	return ret;
diff --git a/fs/dlm/Kconfig b/fs/dlm/Kconfig
index 2dbb422e8116..1897eb1b4b6a 100644
--- a/fs/dlm/Kconfig
+++ b/fs/dlm/Kconfig
@@ -1,8 +1,7 @@
 menuconfig DLM
 	tristate "Distributed Lock Manager (DLM)"
 	depends on EXPERIMENTAL && INET
-	depends on SYSFS && (IPV6 || IPV6=n)
-	select CONFIGFS_FS
+	depends on SYSFS && CONFIGFS_FS && (IPV6 || IPV6=n)
 	select IP_SCTP
 	help
 	A general purpose distributed lock manager for kernel or userspace
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 9c64ae9e4c1a..2d8c87b951c2 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1468,15 +1468,13 @@ static void work_stop(void)
 
 static int work_start(void)
 {
-	recv_workqueue = alloc_workqueue("dlm_recv", WQ_MEM_RECLAIM |
-					 WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+	recv_workqueue = create_singlethread_workqueue("dlm_recv");
 	if (!recv_workqueue) {
 		log_print("can't start dlm_recv");
 		return -ENOMEM;
 	}
 
-	send_workqueue = alloc_workqueue("dlm_send", WQ_MEM_RECLAIM |
-					 WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+	send_workqueue = create_singlethread_workqueue("dlm_send");
 	if (!send_workqueue) {
 		log_print("can't start dlm_send");
 		destroy_workqueue(recv_workqueue);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index cbadc1bee6e7..bfd8b680e648 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -348,7 +348,7 @@ static int encrypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 	BUG_ON(!crypt_stat || !crypt_stat->tfm
 	       || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED));
 	if (unlikely(ecryptfs_verbosity > 0)) {
-		ecryptfs_printk(KERN_DEBUG, "Key size [%d]; key:\n",
+		ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n",
 				crypt_stat->key_size);
 		ecryptfs_dump_hex(crypt_stat->key,
 				  crypt_stat->key_size);
@@ -413,10 +413,9 @@ static int ecryptfs_encrypt_extent(struct page *enc_extent_page,
 	rc = ecryptfs_derive_iv(extent_iv, crypt_stat,
 				(extent_base + extent_offset));
 	if (rc) {
-		ecryptfs_printk(KERN_ERR, "Error attempting to "
-				"derive IV for extent [0x%.16x]; "
-				"rc = [%d]\n", (extent_base + extent_offset),
-				rc);
+		ecryptfs_printk(KERN_ERR, "Error attempting to derive IV for "
+			"extent [0x%.16llx]; rc = [%d]\n",
+			(unsigned long long)(extent_base + extent_offset), rc);
 		goto out;
 	}
 	if (unlikely(ecryptfs_verbosity > 0)) {
@@ -443,9 +442,9 @@ static int ecryptfs_encrypt_extent(struct page *enc_extent_page,
 	}
 	rc = 0;
 	if (unlikely(ecryptfs_verbosity > 0)) {
-		ecryptfs_printk(KERN_DEBUG, "Encrypt extent [0x%.16x]; "
-				"rc = [%d]\n", (extent_base + extent_offset),
-				rc);
+		ecryptfs_printk(KERN_DEBUG, "Encrypt extent [0x%.16llx]; "
+			"rc = [%d]\n",
+			(unsigned long long)(extent_base + extent_offset), rc);
 		ecryptfs_printk(KERN_DEBUG, "First 8 bytes after "
 				"encryption:\n");
 		ecryptfs_dump_hex((char *)(page_address(enc_extent_page)), 8);
@@ -540,10 +539,9 @@ static int ecryptfs_decrypt_extent(struct page *page,
 	rc = ecryptfs_derive_iv(extent_iv, crypt_stat,
 				(extent_base + extent_offset));
 	if (rc) {
-		ecryptfs_printk(KERN_ERR, "Error attempting to "
-				"derive IV for extent [0x%.16x]; "
-				"rc = [%d]\n", (extent_base + extent_offset),
-				rc);
+		ecryptfs_printk(KERN_ERR, "Error attempting to derive IV for "
+			"extent [0x%.16llx]; rc = [%d]\n",
+			(unsigned long long)(extent_base + extent_offset), rc);
 		goto out;
 	}
 	if (unlikely(ecryptfs_verbosity > 0)) {
@@ -571,9 +569,9 @@ static int ecryptfs_decrypt_extent(struct page *page,
 	}
 	rc = 0;
 	if (unlikely(ecryptfs_verbosity > 0)) {
-		ecryptfs_printk(KERN_DEBUG, "Decrypt extent [0x%.16x]; "
-				"rc = [%d]\n", (extent_base + extent_offset),
-				rc);
+		ecryptfs_printk(KERN_DEBUG, "Decrypt extent [0x%.16llx]; "
+			"rc = [%d]\n",
+			(unsigned long long)(extent_base + extent_offset), rc);
 		ecryptfs_printk(KERN_DEBUG, "First 8 bytes after "
 				"decryption:\n");
 		ecryptfs_dump_hex((char *)(page_address(page)
@@ -780,7 +778,7 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat)
 	}
 	ecryptfs_printk(KERN_DEBUG,
 			"Initializing cipher [%s]; strlen = [%d]; "
-			"key_size_bits = [%d]\n",
+			"key_size_bits = [%zd]\n",
 			crypt_stat->cipher, (int)strlen(crypt_stat->cipher),
 			crypt_stat->key_size << 3);
 	if (crypt_stat->tfm) {
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 413a3c48f0bb..dbc84ed96336 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -192,7 +192,6 @@ ecryptfs_get_key_payload_data(struct key *key)
 		(((struct user_key_payload*)key->payload.data)->data);
 }
 
-#define ECRYPTFS_SUPER_MAGIC 0xf15f
 #define ECRYPTFS_MAX_KEYSET_SIZE 1024
 #define ECRYPTFS_MAX_CIPHER_NAME_SIZE 32
 #define ECRYPTFS_MAX_NUM_ENC_KEYS 64
@@ -584,6 +583,7 @@ ecryptfs_set_dentry_lower_mnt(struct dentry *dentry, struct vfsmount *lower_mnt)
 
 #define ecryptfs_printk(type, fmt, arg...) \
         __ecryptfs_printk(type "%s: " fmt, __func__, ## arg);
+__attribute__ ((format(printf, 1, 2)))
 void __ecryptfs_printk(const char *fmt, ...);
 
 extern const struct file_operations ecryptfs_main_fops;
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 91da02987bff..81e10e6a9443 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -47,7 +47,7 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
 				const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos)
 {
-	int rc;
+	ssize_t rc;
 	struct dentry *lower_dentry;
 	struct vfsmount *lower_vfsmount;
 	struct file *file = iocb->ki_filp;
@@ -191,18 +191,16 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 				      | ECRYPTFS_ENCRYPTED);
 	}
 	mutex_unlock(&crypt_stat->cs_mutex);
-	if (!ecryptfs_inode_to_private(inode)->lower_file) {
-		rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
-		if (rc) {
-			printk(KERN_ERR "%s: Error attempting to initialize "
-			       "the persistent file for the dentry with name "
-			       "[%s]; rc = [%d]\n", __func__,
-			       ecryptfs_dentry->d_name.name, rc);
-			goto out_free;
-		}
+	rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
+	if (rc) {
+		printk(KERN_ERR "%s: Error attempting to initialize "
+			"the persistent file for the dentry with name "
+			"[%s]; rc = [%d]\n", __func__,
+			ecryptfs_dentry->d_name.name, rc);
+		goto out_free;
 	}
-	if ((ecryptfs_inode_to_private(inode)->lower_file->f_flags & O_RDONLY)
-	    && !(file->f_flags & O_RDONLY)) {
+	if ((ecryptfs_inode_to_private(inode)->lower_file->f_flags & O_ACCMODE)
+	    == O_RDONLY && (file->f_flags & O_ACCMODE) != O_RDONLY) {
 		rc = -EPERM;
 		printk(KERN_WARNING "%s: Lower persistent file is RO; eCryptfs "
 		       "file must hence be opened RO\n", __func__);
@@ -243,9 +241,9 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 		}
 	}
 	mutex_unlock(&crypt_stat->cs_mutex);
-	ecryptfs_printk(KERN_DEBUG, "inode w/ addr = [0x%p], i_ino = [0x%.16x] "
-			"size: [0x%.16x]\n", inode, inode->i_ino,
-			i_size_read(inode));
+	ecryptfs_printk(KERN_DEBUG, "inode w/ addr = [0x%p], i_ino = "
+			"[0x%.16lx] size: [0x%.16llx]\n", inode, inode->i_ino,
+			(unsigned long long)i_size_read(inode));
 	goto out;
 out_free:
 	kmem_cache_free(ecryptfs_file_info_cache,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 64ff02330752..bd33f87a1907 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -185,15 +185,13 @@ static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
 				"context; rc = [%d]\n", rc);
 		goto out;
 	}
-	if (!ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->lower_file) {
-		rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
-		if (rc) {
-			printk(KERN_ERR "%s: Error attempting to initialize "
-			       "the persistent file for the dentry with name "
-			       "[%s]; rc = [%d]\n", __func__,
-			       ecryptfs_dentry->d_name.name, rc);
-			goto out;
-		}
+	rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
+	if (rc) {
+		printk(KERN_ERR "%s: Error attempting to initialize "
+			"the persistent file for the dentry with name "
+			"[%s]; rc = [%d]\n", __func__,
+			ecryptfs_dentry->d_name.name, rc);
+		goto out;
 	}
 	rc = ecryptfs_write_metadata(ecryptfs_dentry);
 	if (rc) {
@@ -302,15 +300,13 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
 		rc = -ENOMEM;
 		goto out;
 	}
-	if (!ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->lower_file) {
-		rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
-		if (rc) {
-			printk(KERN_ERR "%s: Error attempting to initialize "
-			       "the persistent file for the dentry with name "
-			       "[%s]; rc = [%d]\n", __func__,
-			       ecryptfs_dentry->d_name.name, rc);
-			goto out_free_kmem;
-		}
+	rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
+	if (rc) {
+		printk(KERN_ERR "%s: Error attempting to initialize "
+			"the persistent file for the dentry with name "
+			"[%s]; rc = [%d]\n", __func__,
+			ecryptfs_dentry->d_name.name, rc);
+		goto out_free_kmem;
 	}
 	crypt_stat = &ecryptfs_inode_to_private(
 					ecryptfs_dentry->d_inode)->crypt_stat;
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index b1f6858a5223..c1436cff6f2d 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -59,7 +59,7 @@ static int process_request_key_err(long err_code)
 		break;
 	default:
 		ecryptfs_printk(KERN_WARNING, "Unknown error code: "
-				"[0x%.16x]\n", err_code);
+				"[0x%.16lx]\n", err_code);
 		rc = -EINVAL;
 	}
 	return rc;
@@ -130,7 +130,7 @@ int ecryptfs_write_packet_length(char *dest, size_t size,
 	} else {
 		rc = -EINVAL;
 		ecryptfs_printk(KERN_WARNING,
-				"Unsupported packet size: [%d]\n", size);
+				"Unsupported packet size: [%zd]\n", size);
 	}
 	return rc;
 }
@@ -1672,7 +1672,7 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	       auth_tok->session_key.decrypted_key_size);
 	crypt_stat->flags |= ECRYPTFS_KEY_VALID;
 	if (unlikely(ecryptfs_verbosity > 0)) {
-		ecryptfs_printk(KERN_DEBUG, "FEK of size [%d]:\n",
+		ecryptfs_printk(KERN_DEBUG, "FEK of size [%zd]:\n",
 				crypt_stat->key_size);
 		ecryptfs_dump_hex(crypt_stat->key,
 				  crypt_stat->key_size);
@@ -1754,7 +1754,7 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat,
 			if (ECRYPTFS_SIG_SIZE != tag_11_contents_size) {
 				ecryptfs_printk(KERN_ERR, "Expected "
 						"signature of size [%d]; "
-						"read size [%d]\n",
+						"read size [%zd]\n",
 						ECRYPTFS_SIG_SIZE,
 						tag_11_contents_size);
 				rc = -EIO;
@@ -1787,8 +1787,8 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat,
 			goto out_wipe_list;
 			break;
 		default:
-			ecryptfs_printk(KERN_DEBUG, "No packet at offset "
-					"[%d] of the file header; hex value of "
+			ecryptfs_printk(KERN_DEBUG, "No packet at offset [%zd] "
+					"of the file header; hex value of "
 					"character is [0x%.2x]\n", i, src[i]);
 			next_packet_is_auth_tok_packet = 0;
 		}
@@ -1864,8 +1864,8 @@ found_matching_auth_tok:
 				"session key for authentication token with sig "
 				"[%.*s]; rc = [%d]. Removing auth tok "
 				"candidate from the list and searching for "
-				"the next match.\n", candidate_auth_tok_sig,
-				ECRYPTFS_SIG_SIZE_HEX, rc);
+				"the next match.\n", ECRYPTFS_SIG_SIZE_HEX,
+				candidate_auth_tok_sig,	rc);
 		list_for_each_entry_safe(auth_tok_list_item,
 					 auth_tok_list_item_tmp,
 					 &auth_tok_list, list) {
@@ -2168,7 +2168,7 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 	if (encrypted_session_key_valid) {
 		ecryptfs_printk(KERN_DEBUG, "encrypted_session_key_valid != 0; "
 				"using auth_tok->session_key.encrypted_key, "
-				"where key_rec->enc_key_size = [%d]\n",
+				"where key_rec->enc_key_size = [%zd]\n",
 				key_rec->enc_key_size);
 		memcpy(key_rec->enc_key,
 		       auth_tok->session_key.encrypted_key,
@@ -2198,7 +2198,7 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 	if (rc < 1 || rc > 2) {
 		ecryptfs_printk(KERN_ERR, "Error generating scatterlist "
 				"for crypt_stat session key; expected rc = 1; "
-				"got rc = [%d]. key_rec->enc_key_size = [%d]\n",
+				"got rc = [%d]. key_rec->enc_key_size = [%zd]\n",
 				rc, key_rec->enc_key_size);
 		rc = -ENOMEM;
 		goto out;
@@ -2209,7 +2209,7 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		ecryptfs_printk(KERN_ERR, "Error generating scatterlist "
 				"for crypt_stat encrypted session key; "
 				"expected rc = 1; got rc = [%d]. "
-				"key_rec->enc_key_size = [%d]\n", rc,
+				"key_rec->enc_key_size = [%zd]\n", rc,
 				key_rec->enc_key_size);
 		rc = -ENOMEM;
 		goto out;
@@ -2224,7 +2224,7 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	rc = 0;
-	ecryptfs_printk(KERN_DEBUG, "Encrypting [%d] bytes of the key\n",
+	ecryptfs_printk(KERN_DEBUG, "Encrypting [%zd] bytes of the key\n",
 			crypt_stat->key_size);
 	rc = crypto_blkcipher_encrypt(&desc, dst_sg, src_sg,
 				      (*key_rec).enc_key_size);
@@ -2235,7 +2235,7 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 	}
 	ecryptfs_printk(KERN_DEBUG, "This should be the encrypted key:\n");
 	if (ecryptfs_verbosity > 0) {
-		ecryptfs_printk(KERN_DEBUG, "EFEK of size [%d]:\n",
+		ecryptfs_printk(KERN_DEBUG, "EFEK of size [%zd]:\n",
 				key_rec->enc_key_size);
 		ecryptfs_dump_hex(key_rec->enc_key,
 				  key_rec->enc_key_size);
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 9ed476906327..758323a0f09a 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -36,6 +36,7 @@
 #include <linux/parser.h>
 #include <linux/fs_stack.h>
 #include <linux/slab.h>
+#include <linux/magic.h>
 #include "ecryptfs_kernel.h"
 
 /**
@@ -141,13 +142,12 @@ int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
 	return rc;
 }
 
-static inode *ecryptfs_get_inode(struct inode *lower_inode,
+static struct inode *ecryptfs_get_inode(struct inode *lower_inode,
 		       struct super_block *sb)
 {
 	struct inode *inode;
 	int rc = 0;
 
-	lower_inode = lower_dentry->d_inode;
 	if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb)) {
 		rc = -EXDEV;
 		goto out;
@@ -202,7 +202,7 @@ int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
 {
 	struct inode *lower_inode = lower_dentry->d_inode;
 	struct inode *inode = ecryptfs_get_inode(lower_inode, sb);
-	if (IS_ERR(inode)
+	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 	if (flags & ECRYPTFS_INTERPOSE_FLAG_D_ADD)
 		d_add(dentry, inode);
@@ -565,6 +565,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	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;
+	s->s_magic = ECRYPTFS_SUPER_MAGIC;
 
 	inode = ecryptfs_get_inode(path.dentry->d_inode, s);
 	rc = PTR_ERR(inode);
@@ -809,9 +810,10 @@ static int __init ecryptfs_init(void)
 		ecryptfs_printk(KERN_ERR, "The eCryptfs extent size is "
 				"larger than the host's page size, and so "
 				"eCryptfs cannot run on this system. The "
-				"default eCryptfs extent size is [%d] bytes; "
-				"the page size is [%d] bytes.\n",
-				ECRYPTFS_DEFAULT_EXTENT_SIZE, PAGE_CACHE_SIZE);
+				"default eCryptfs extent size is [%u] bytes; "
+				"the page size is [%lu] bytes.\n",
+				ECRYPTFS_DEFAULT_EXTENT_SIZE,
+				(unsigned long)PAGE_CACHE_SIZE);
 		goto out;
 	}
 	rc = ecryptfs_init_kmem_caches();
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index b1d82756544b..cc64fca89f8d 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -65,7 +65,7 @@ static int ecryptfs_writepage(struct page *page, struct writeback_control *wbc)
 	rc = ecryptfs_encrypt_page(page);
 	if (rc) {
 		ecryptfs_printk(KERN_WARNING, "Error encrypting "
-				"page (upper index [0x%.16x])\n", page->index);
+				"page (upper index [0x%.16lx])\n", page->index);
 		ClearPageUptodate(page);
 		goto out;
 	}
@@ -237,7 +237,7 @@ out:
 		ClearPageUptodate(page);
 	else
 		SetPageUptodate(page);
-	ecryptfs_printk(KERN_DEBUG, "Unlocking page with index = [0x%.16x]\n",
+	ecryptfs_printk(KERN_DEBUG, "Unlocking page with index = [0x%.16lx]\n",
 			page->index);
 	unlock_page(page);
 	return rc;
@@ -290,6 +290,7 @@ static int ecryptfs_write_begin(struct file *file,
 		return -ENOMEM;
 	*pagep = page;
 
+	prev_page_end_size = ((loff_t)index << PAGE_CACHE_SHIFT);
 	if (!PageUptodate(page)) {
 		struct ecryptfs_crypt_stat *crypt_stat =
 			&ecryptfs_inode_to_private(mapping->host)->crypt_stat;
@@ -335,18 +336,23 @@ static int ecryptfs_write_begin(struct file *file,
 				SetPageUptodate(page);
 			}
 		} else {
-			rc = ecryptfs_decrypt_page(page);
-			if (rc) {
-				printk(KERN_ERR "%s: Error decrypting page "
-				       "at index [%ld]; rc = [%d]\n",
-				       __func__, page->index, rc);
-				ClearPageUptodate(page);
-				goto out;
+			if (prev_page_end_size
+			    >= i_size_read(page->mapping->host)) {
+				zero_user(page, 0, PAGE_CACHE_SIZE);
+			} else {
+				rc = ecryptfs_decrypt_page(page);
+				if (rc) {
+					printk(KERN_ERR "%s: Error decrypting "
+					       "page at index [%ld]; "
+					       "rc = [%d]\n",
+					       __func__, page->index, rc);
+					ClearPageUptodate(page);
+					goto out;
+				}
 			}
 			SetPageUptodate(page);
 		}
 	}
-	prev_page_end_size = ((loff_t)index << PAGE_CACHE_SHIFT);
 	/* If creating a page or more of holes, zero them out via truncate.
 	 * Note, this will increase i_size. */
 	if (index != 0) {
@@ -488,7 +494,7 @@ static int ecryptfs_write_end(struct file *file,
 	} else
 		ecryptfs_printk(KERN_DEBUG, "Not a new file\n");
 	ecryptfs_printk(KERN_DEBUG, "Calling fill_zeros_to_end_of_page"
-			"(page w/ index = [0x%.16x], to = [%d])\n", index, to);
+			"(page w/ index = [0x%.16lx], to = [%d])\n", index, to);
 	if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
 		rc = ecryptfs_write_lower_page_segment(ecryptfs_inode, page, 0,
 						       to);
@@ -503,19 +509,20 @@ static int ecryptfs_write_end(struct file *file,
 	rc = fill_zeros_to_end_of_page(page, to);
 	if (rc) {
 		ecryptfs_printk(KERN_WARNING, "Error attempting to fill "
-			"zeros in page with index = [0x%.16x]\n", index);
+			"zeros in page with index = [0x%.16lx]\n", index);
 		goto out;
 	}
 	rc = ecryptfs_encrypt_page(page);
 	if (rc) {
 		ecryptfs_printk(KERN_WARNING, "Error encrypting page (upper "
-				"index [0x%.16x])\n", index);
+				"index [0x%.16lx])\n", index);
 		goto out;
 	}
 	if (pos + copied > i_size_read(ecryptfs_inode)) {
 		i_size_write(ecryptfs_inode, pos + copied);
 		ecryptfs_printk(KERN_DEBUG, "Expanded file size to "
-				"[0x%.16x]\n", i_size_read(ecryptfs_inode));
+			"[0x%.16llx]\n",
+			(unsigned long long)i_size_read(ecryptfs_inode));
 	}
 	rc = ecryptfs_write_inode_size_to_metadata(ecryptfs_inode);
 	if (rc)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index cc8a9b7d6064..267d0ada4541 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1114,6 +1114,17 @@ static int ep_send_events(struct eventpoll *ep,
 	return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
 }
 
+static inline struct timespec ep_set_mstimeout(long ms)
+{
+	struct timespec now, ts = {
+		.tv_sec = ms / MSEC_PER_SEC,
+		.tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC),
+	};
+
+	ktime_get_ts(&now);
+	return timespec_add_safe(now, ts);
+}
+
 static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		   int maxevents, long timeout)
 {
@@ -1121,12 +1132,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	unsigned long flags;
 	long slack;
 	wait_queue_t wait;
-	struct timespec end_time;
 	ktime_t expires, *to = NULL;
 
 	if (timeout > 0) {
-		ktime_get_ts(&end_time);
-		timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC);
+		struct timespec end_time = ep_set_mstimeout(timeout);
+
 		slack = select_estimate_accuracy(&end_time);
 		to = &expires;
 		*to = timespec_to_ktime(end_time);
diff --git a/fs/exec.c b/fs/exec.c
index c62efcb959c7..52a447d9b6ab 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -120,7 +120,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 		goto out;
 
 	file = do_filp_open(AT_FDCWD, tmp,
-				O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0,
+				O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
 				MAY_READ | MAY_EXEC | MAY_OPEN);
 	putname(tmp);
 	error = PTR_ERR(file);
@@ -723,7 +723,7 @@ struct file *open_exec(const char *name)
 	int err;
 
 	file = do_filp_open(AT_FDCWD, name,
-				O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0,
+				O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
 				MAY_EXEC | MAY_OPEN);
 	if (IS_ERR(file))
 		goto out;
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 42685424817b..a7555238c41a 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1030,7 +1030,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
 		memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
 	}
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &exofs_file_inode_operations;
 		inode->i_fop = &exofs_file_operations;
@@ -1131,7 +1130,6 @@ struct inode *exofs_new_inode(struct inode *dir, int mode)
 
 	sbi = sb->s_fs_info;
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	sb->s_dirt = 1;
 	inode_init_owner(inode, dir, mode);
 	inode->i_ino = sbi->s_nextid++;
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 7aa767d4f06f..85c8cc8f2473 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -754,7 +754,7 @@ static int ext3_release_dquot(struct dquot *dquot);
 static int ext3_mark_dquot_dirty(struct dquot *dquot);
 static int ext3_write_info(struct super_block *sb, int type);
 static int ext3_quota_on(struct super_block *sb, int type, int format_id,
-				char *path);
+			 struct path *path);
 static int ext3_quota_on_mount(struct super_block *sb, int type);
 static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data,
 			       size_t len, loff_t off);
@@ -2877,27 +2877,20 @@ static int ext3_quota_on_mount(struct super_block *sb, int type)
  * Standard function to be called on quota_on
  */
 static int ext3_quota_on(struct super_block *sb, int type, int format_id,
-			 char *name)
+			 struct path *path)
 {
 	int err;
-	struct path path;
 
 	if (!test_opt(sb, QUOTA))
 		return -EINVAL;
 
-	err = kern_path(name, LOOKUP_FOLLOW, &path);
-	if (err)
-		return err;
-
 	/* Quotafile not on the same filesystem? */
-	if (path.mnt->mnt_sb != sb) {
-		path_put(&path);
+	if (path->mnt->mnt_sb != sb)
 		return -EXDEV;
-	}
 	/* Journaling quota? */
 	if (EXT3_SB(sb)->s_qf_names[type]) {
 		/* Quotafile not of fs root? */
-		if (path.dentry->d_parent != sb->s_root)
+		if (path->dentry->d_parent != sb->s_root)
 			ext3_msg(sb, KERN_WARNING,
 				"warning: Quota file not on filesystem root. "
 				"Journaled quota will not work.");
@@ -2907,7 +2900,7 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id,
 	 * When we journal data on quota file, we have to flush journal to see
 	 * all updates to the file when we bypass pagecache...
 	 */
-	if (ext3_should_journal_data(path.dentry->d_inode)) {
+	if (ext3_should_journal_data(path->dentry->d_inode)) {
 		/*
 		 * We don't need to lock updates but journal_flush() could
 		 * otherwise be livelocked...
@@ -2915,15 +2908,11 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id,
 		journal_lock_updates(EXT3_SB(sb)->s_journal);
 		err = journal_flush(EXT3_SB(sb)->s_journal);
 		journal_unlock_updates(EXT3_SB(sb)->s_journal);
-		if (err) {
-			path_put(&path);
+		if (err)
 			return err;
-		}
 	}
 
-	err = dquot_quota_on_path(sb, type, format_id, &path);
-	path_put(&path);
-	return err;
+	return dquot_quota_on(sb, type, format_id, path);
 }
 
 /* Read data from quotafile - avoid pagecache and such because we cannot afford
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1de65f572033..3aa0b72b3b94 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -848,6 +848,7 @@ struct ext4_inode_info {
 	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
 	/* current io_end structure for async DIO write*/
 	ext4_io_end_t *cur_aio_dio;
+	atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */
 
 	spinlock_t i_block_reservation_lock;
 
@@ -2065,7 +2066,7 @@ extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 extern void ext4_ext_truncate(struct inode *);
 extern void ext4_ext_init(struct super_block *);
 extern void ext4_ext_release(struct super_block *);
-extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
+extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
 			  ssize_t len);
@@ -2119,6 +2120,15 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
 
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
 
+/* For ioend & aio unwritten conversion wait queues */
+#define EXT4_WQ_HASH_SZ		37
+#define ext4_ioend_wq(v)   (&ext4__ioend_wq[((unsigned long)(v)) %\
+					    EXT4_WQ_HASH_SZ])
+#define ext4_aio_mutex(v)  (&ext4__aio_mutex[((unsigned long)(v)) %\
+					     EXT4_WQ_HASH_SZ])
+extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
 #endif	/* __KERNEL__ */
 
 #endif	/* _EXT4_H */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 6b90b6825d32..686240e89df1 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3174,9 +3174,10 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 		 * that this IO needs to convertion to written when IO is
 		 * completed
 		 */
-		if (io)
+		if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
 			io->flag = EXT4_IO_END_UNWRITTEN;
-		else
+			atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+		} else
 			ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 		if (ext4_should_dioread_nolock(inode))
 			map->m_flags |= EXT4_MAP_UNINIT;
@@ -3463,9 +3464,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		 * that we need to perform convertion when IO is done.
 		 */
 		if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
-			if (io)
+			if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
 				io->flag = EXT4_IO_END_UNWRITTEN;
-			else
+				atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+			} else
 				ext4_set_inode_state(inode,
 						     EXT4_STATE_DIO_UNWRITTEN);
 		}
@@ -3627,14 +3629,15 @@ static void ext4_falloc_update_inode(struct inode *inode,
 }
 
 /*
- * preallocate space for a file. This implements ext4's fallocate inode
+ * preallocate space for a file. This implements ext4's fallocate file
  * operation, which gets called from sys_fallocate system call.
  * For block-mapped files, posix_fallocate should fall back to the method
  * of writing zeroes to the required new blocks (the same behavior which is
  * expected for file systems which do not support fallocate() system call).
  */
-long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
+long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
+	struct inode *inode = file->f_path.dentry->d_inode;
 	handle_t *handle;
 	loff_t new_size;
 	unsigned int max_blocks;
@@ -3645,7 +3648,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 	unsigned int credits, blkbits = inode->i_blkbits;
 
 	/* We only support the FALLOC_FL_KEEP_SIZE mode */
-	if (mode && (mode != FALLOC_FL_KEEP_SIZE))
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
 		return -EOPNOTSUPP;
 
 	/*
@@ -3655,10 +3658,6 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return -EOPNOTSUPP;
 
-	/* preallocation to directories is currently not supported */
-	if (S_ISDIR(inode->i_mode))
-		return -ENODEV;
-
 	map.m_lblk = offset >> blkbits;
 	/*
 	 * We can't just convert len to max_blocks because
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index bb003dc9ffff..7b80d543b89e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -55,11 +55,47 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static void ext4_aiodio_wait(struct inode *inode)
+{
+	wait_queue_head_t *wq = ext4_ioend_wq(inode);
+
+	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0));
+}
+
+/*
+ * This tests whether the IO in question is block-aligned or not.
+ * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
+ * are converted to written only after the IO is complete.  Until they are
+ * mapped, these blocks appear as holes, so dio_zero_block() will assume that
+ * it needs to zero out portions of the start and/or end block.  If 2 AIO
+ * threads are at work on the same unwritten block, they must be synchronized
+ * or one thread will zero the other's data, causing corruption.
+ */
+static int
+ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
+		   unsigned long nr_segs, loff_t pos)
+{
+	struct super_block *sb = inode->i_sb;
+	int blockmask = sb->s_blocksize - 1;
+	size_t count = iov_length(iov, nr_segs);
+	loff_t final_size = pos + count;
+
+	if (pos >= inode->i_size)
+		return 0;
+
+	if ((pos & blockmask) || (final_size & blockmask))
+		return 1;
+
+	return 0;
+}
+
 static ssize_t
 ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos)
 {
 	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+	int unaligned_aio = 0;
+	int ret;
 
 	/*
 	 * If we have encountered a bitmap-format file, the size limit
@@ -78,9 +114,31 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
 					      sbi->s_bitmap_maxbytes - pos);
 		}
+	} else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
+		   !is_sync_kiocb(iocb))) {
+		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+	}
+
+	/* Unaligned direct AIO must be serialized; see comment above */
+	if (unaligned_aio) {
+		static unsigned long unaligned_warn_time;
+
+		/* Warn about this once per day */
+		if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
+			ext4_msg(inode->i_sb, KERN_WARNING,
+				 "Unaligned AIO/DIO on inode %ld by %s; "
+				 "performance will be poor.",
+				 inode->i_ino, current->comm);
+		mutex_lock(ext4_aio_mutex(inode));
+		ext4_aiodio_wait(inode);
 	}
 
-	return generic_file_aio_write(iocb, iov, nr_segs, pos);
+	ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+	if (unaligned_aio)
+		mutex_unlock(ext4_aio_mutex(inode));
+
+	return ret;
 }
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
@@ -210,6 +268,7 @@ const struct file_operations ext4_file_operations = {
 	.fsync		= ext4_sync_file,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= generic_file_splice_write,
+	.fallocate	= ext4_fallocate,
 };
 
 const struct inode_operations ext4_file_inode_operations = {
@@ -223,7 +282,6 @@ const struct inode_operations ext4_file_inode_operations = {
 	.removexattr	= generic_removexattr,
 #endif
 	.check_acl	= ext4_check_acl,
-	.fallocate	= ext4_fallocate,
 	.fiemap		= ext4_fiemap,
 };
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 851f49b2f9d2..d1fe09aea73d 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -342,10 +342,15 @@ static struct kmem_cache *ext4_free_ext_cachep;
 /* We create slab caches for groupinfo data structures based on the
  * superblock block size.  There will be one per mounted filesystem for
  * each unique s_blocksize_bits */
-#define NR_GRPINFO_CACHES	\
-	(EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE + 1)
+#define NR_GRPINFO_CACHES 8
 static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES];
 
+static const char *ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = {
+	"ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k",
+	"ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k",
+	"ext4_groupinfo_64k", "ext4_groupinfo_128k"
+};
+
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group);
 static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
@@ -2414,6 +2419,55 @@ err_freesgi:
 	return -ENOMEM;
 }
 
+static void ext4_groupinfo_destroy_slabs(void)
+{
+	int i;
+
+	for (i = 0; i < NR_GRPINFO_CACHES; i++) {
+		if (ext4_groupinfo_caches[i])
+			kmem_cache_destroy(ext4_groupinfo_caches[i]);
+		ext4_groupinfo_caches[i] = NULL;
+	}
+}
+
+static int ext4_groupinfo_create_slab(size_t size)
+{
+	static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex);
+	int slab_size;
+	int blocksize_bits = order_base_2(size);
+	int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
+	struct kmem_cache *cachep;
+
+	if (cache_index >= NR_GRPINFO_CACHES)
+		return -EINVAL;
+
+	if (unlikely(cache_index < 0))
+		cache_index = 0;
+
+	mutex_lock(&ext4_grpinfo_slab_create_mutex);
+	if (ext4_groupinfo_caches[cache_index]) {
+		mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+		return 0;	/* Already created */
+	}
+
+	slab_size = offsetof(struct ext4_group_info,
+				bb_counters[blocksize_bits + 2]);
+
+	cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index],
+					slab_size, 0, SLAB_RECLAIM_ACCOUNT,
+					NULL);
+
+	mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+	if (!cachep) {
+		printk(KERN_EMERG "EXT4: no memory for groupinfo slab cache\n");
+		return -ENOMEM;
+	}
+
+	ext4_groupinfo_caches[cache_index] = cachep;
+
+	return 0;
+}
+
 int ext4_mb_init(struct super_block *sb, int needs_recovery)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2421,9 +2475,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	unsigned offset;
 	unsigned max;
 	int ret;
-	int cache_index;
-	struct kmem_cache *cachep;
-	char *namep = NULL;
 
 	i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets);
 
@@ -2440,30 +2491,9 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 		goto out;
 	}
 
-	cache_index = sb->s_blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
-	cachep = ext4_groupinfo_caches[cache_index];
-	if (!cachep) {
-		char name[32];
-		int len = offsetof(struct ext4_group_info,
-					bb_counters[sb->s_blocksize_bits + 2]);
-
-		sprintf(name, "ext4_groupinfo_%d", sb->s_blocksize_bits);
-		namep = kstrdup(name, GFP_KERNEL);
-		if (!namep) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		/* Need to free the kmem_cache_name() when we
-		 * destroy the slab */
-		cachep = kmem_cache_create(namep, len, 0,
-					     SLAB_RECLAIM_ACCOUNT, NULL);
-		if (!cachep) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		ext4_groupinfo_caches[cache_index] = cachep;
-	}
+	ret = ext4_groupinfo_create_slab(sb->s_blocksize);
+	if (ret < 0)
+		goto out;
 
 	/* order 0 is regular bitmap */
 	sbi->s_mb_maxs[0] = sb->s_blocksize << 3;
@@ -2520,7 +2550,6 @@ out:
 	if (ret) {
 		kfree(sbi->s_mb_offsets);
 		kfree(sbi->s_mb_maxs);
-		kfree(namep);
 	}
 	return ret;
 }
@@ -2734,7 +2763,6 @@ int __init ext4_init_mballoc(void)
 
 void ext4_exit_mballoc(void)
 {
-	int i;
 	/*
 	 * Wait for completion of call_rcu()'s on ext4_pspace_cachep
 	 * before destroying the slab cache.
@@ -2743,15 +2771,7 @@ void ext4_exit_mballoc(void)
 	kmem_cache_destroy(ext4_pspace_cachep);
 	kmem_cache_destroy(ext4_ac_cachep);
 	kmem_cache_destroy(ext4_free_ext_cachep);
-
-	for (i = 0; i < NR_GRPINFO_CACHES; i++) {
-		struct kmem_cache *cachep = ext4_groupinfo_caches[i];
-		if (cachep) {
-			char *name = (char *)kmem_cache_name(cachep);
-			kmem_cache_destroy(cachep);
-			kfree(name);
-		}
-	}
+	ext4_groupinfo_destroy_slabs();
 	ext4_remove_debugfs_entry();
 }
 
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 7270dcfca92a..955cc309142f 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -32,14 +32,8 @@
 
 static struct kmem_cache *io_page_cachep, *io_end_cachep;
 
-#define WQ_HASH_SZ		37
-#define to_ioend_wq(v)	(&ioend_wq[((unsigned long)v) % WQ_HASH_SZ])
-static wait_queue_head_t ioend_wq[WQ_HASH_SZ];
-
 int __init ext4_init_pageio(void)
 {
-	int i;
-
 	io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT);
 	if (io_page_cachep == NULL)
 		return -ENOMEM;
@@ -48,9 +42,6 @@ int __init ext4_init_pageio(void)
 		kmem_cache_destroy(io_page_cachep);
 		return -ENOMEM;
 	}
-	for (i = 0; i < WQ_HASH_SZ; i++)
-		init_waitqueue_head(&ioend_wq[i]);
-
 	return 0;
 }
 
@@ -62,7 +53,7 @@ void ext4_exit_pageio(void)
 
 void ext4_ioend_wait(struct inode *inode)
 {
-	wait_queue_head_t *wq = to_ioend_wq(inode);
+	wait_queue_head_t *wq = ext4_ioend_wq(inode);
 
 	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
 }
@@ -87,7 +78,7 @@ void ext4_free_io_end(ext4_io_end_t *io)
 	for (i = 0; i < io->num_io_pages; i++)
 		put_io_page(io->pages[i]);
 	io->num_io_pages = 0;
-	wq = to_ioend_wq(io->inode);
+	wq = ext4_ioend_wq(io->inode);
 	if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
 	    waitqueue_active(wq))
 		wake_up_all(wq);
@@ -102,6 +93,7 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
 	struct inode *inode = io->inode;
 	loff_t offset = io->offset;
 	ssize_t size = io->size;
+	wait_queue_head_t *wq;
 	int ret = 0;
 
 	ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
@@ -126,7 +118,16 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
 	if (io->iocb)
 		aio_complete(io->iocb, io->result, 0);
 	/* clear the DIO AIO unwritten flag */
-	io->flag &= ~EXT4_IO_END_UNWRITTEN;
+	if (io->flag & EXT4_IO_END_UNWRITTEN) {
+		io->flag &= ~EXT4_IO_END_UNWRITTEN;
+		/* Wake up anyone waiting on unwritten extent conversion */
+		wq = ext4_ioend_wq(io->inode);
+		if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) &&
+		    waitqueue_active(wq)) {
+			wake_up_all(wq);
+		}
+	}
+
 	return ret;
 }
 
@@ -190,6 +191,7 @@ static void ext4_end_bio(struct bio *bio, int error)
 	struct inode *inode;
 	unsigned long flags;
 	int i;
+	sector_t bi_sector = bio->bi_sector;
 
 	BUG_ON(!io_end);
 	bio->bi_private = NULL;
@@ -207,9 +209,7 @@ static void ext4_end_bio(struct bio *bio, int error)
 		if (error)
 			SetPageError(page);
 		BUG_ON(!head);
-		if (head->b_size == PAGE_CACHE_SIZE)
-			clear_buffer_dirty(head);
-		else {
+		if (head->b_size != PAGE_CACHE_SIZE) {
 			loff_t offset;
 			loff_t io_end_offset = io_end->offset + io_end->size;
 
@@ -221,7 +221,6 @@ static void ext4_end_bio(struct bio *bio, int error)
 					if (error)
 						buffer_io_error(bh);
 
-					clear_buffer_dirty(bh);
 				}
 				if (buffer_delay(bh))
 					partial_write = 1;
@@ -257,7 +256,7 @@ static void ext4_end_bio(struct bio *bio, int error)
 			     (unsigned long long) io_end->offset,
 			     (long) io_end->size,
 			     (unsigned long long)
-			     bio->bi_sector >> (inode->i_blkbits - 9));
+			     bi_sector >> (inode->i_blkbits - 9));
 	}
 
 	/* Add the io_end to per-inode completed io list*/
@@ -380,6 +379,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 
 	blocksize = 1 << inode->i_blkbits;
 
+	BUG_ON(!PageLocked(page));
 	BUG_ON(PageWriteback(page));
 	set_page_writeback(page);
 	ClearPageError(page);
@@ -397,12 +397,14 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	for (bh = head = page_buffers(page), block_start = 0;
 	     bh != head || !block_start;
 	     block_start = block_end, bh = bh->b_this_page) {
+
 		block_end = block_start + blocksize;
 		if (block_start >= len) {
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
 			continue;
 		}
+		clear_buffer_dirty(bh);
 		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
 		if (ret) {
 			/*
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index cb10a06775e4..f6a318f836b2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -77,6 +77,7 @@ static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
 		       const char *dev_name, void *data);
 static void ext4_destroy_lazyinit_thread(void);
 static void ext4_unregister_li_request(struct super_block *sb);
+static void ext4_clear_request_list(void);
 
 #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
 static struct file_system_type ext3_fs_type = {
@@ -832,6 +833,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_sync_tid = 0;
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_ioend_count, 0);
+	atomic_set(&ei->i_aiodio_unwritten, 0);
 
 	return &ei->vfs_inode;
 }
@@ -1161,7 +1163,7 @@ static int ext4_release_dquot(struct dquot *dquot);
 static int ext4_mark_dquot_dirty(struct dquot *dquot);
 static int ext4_write_info(struct super_block *sb, int type);
 static int ext4_quota_on(struct super_block *sb, int type, int format_id,
-				char *path);
+			 struct path *path);
 static int ext4_quota_off(struct super_block *sb, int type);
 static int ext4_quota_on_mount(struct super_block *sb, int type);
 static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
@@ -2716,6 +2718,8 @@ static void ext4_unregister_li_request(struct super_block *sb)
 	mutex_unlock(&ext4_li_info->li_list_mtx);
 }
 
+static struct task_struct *ext4_lazyinit_task;
+
 /*
  * This is the function where ext4lazyinit thread lives. It walks
  * through the request list searching for next scheduled filesystem.
@@ -2784,6 +2788,10 @@ cont_thread:
 		if (time_before(jiffies, next_wakeup))
 			schedule();
 		finish_wait(&eli->li_wait_daemon, &wait);
+		if (kthread_should_stop()) {
+			ext4_clear_request_list();
+			goto exit_thread;
+		}
 	}
 
 exit_thread:
@@ -2808,6 +2816,7 @@ exit_thread:
 	wake_up(&eli->li_wait_task);
 
 	kfree(ext4_li_info);
+	ext4_lazyinit_task = NULL;
 	ext4_li_info = NULL;
 	mutex_unlock(&ext4_li_mtx);
 
@@ -2830,11 +2839,10 @@ static void ext4_clear_request_list(void)
 
 static int ext4_run_lazyinit_thread(void)
 {
-	struct task_struct *t;
-
-	t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
-	if (IS_ERR(t)) {
-		int err = PTR_ERR(t);
+	ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread,
+					 ext4_li_info, "ext4lazyinit");
+	if (IS_ERR(ext4_lazyinit_task)) {
+		int err = PTR_ERR(ext4_lazyinit_task);
 		ext4_clear_request_list();
 		del_timer_sync(&ext4_li_info->li_timer);
 		kfree(ext4_li_info);
@@ -2985,16 +2993,10 @@ static void ext4_destroy_lazyinit_thread(void)
 	 * If thread exited earlier
 	 * there's nothing to be done.
 	 */
-	if (!ext4_li_info)
+	if (!ext4_li_info || !ext4_lazyinit_task)
 		return;
 
-	ext4_clear_request_list();
-
-	while (ext4_li_info->li_task) {
-		wake_up(&ext4_li_info->li_wait_daemon);
-		wait_event(ext4_li_info->li_wait_task,
-			   ext4_li_info->li_task == NULL);
-	}
+	kthread_stop(ext4_lazyinit_task);
 }
 
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
@@ -4558,27 +4560,20 @@ static int ext4_quota_on_mount(struct super_block *sb, int type)
  * Standard function to be called on quota_on
  */
 static int ext4_quota_on(struct super_block *sb, int type, int format_id,
-			 char *name)
+			 struct path *path)
 {
 	int err;
-	struct path path;
 
 	if (!test_opt(sb, QUOTA))
 		return -EINVAL;
 
-	err = kern_path(name, LOOKUP_FOLLOW, &path);
-	if (err)
-		return err;
-
 	/* Quotafile not on the same filesystem? */
-	if (path.mnt->mnt_sb != sb) {
-		path_put(&path);
+	if (path->mnt->mnt_sb != sb)
 		return -EXDEV;
-	}
 	/* Journaling quota? */
 	if (EXT4_SB(sb)->s_qf_names[type]) {
 		/* Quotafile not in fs root? */
-		if (path.dentry->d_parent != sb->s_root)
+		if (path->dentry->d_parent != sb->s_root)
 			ext4_msg(sb, KERN_WARNING,
 				"Quota file not on filesystem root. "
 				"Journaled quota will not work");
@@ -4589,7 +4584,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 	 * all updates to the file when we bypass pagecache...
 	 */
 	if (EXT4_SB(sb)->s_journal &&
-	    ext4_should_journal_data(path.dentry->d_inode)) {
+	    ext4_should_journal_data(path->dentry->d_inode)) {
 		/*
 		 * We don't need to lock updates but journal_flush() could
 		 * otherwise be livelocked...
@@ -4597,15 +4592,11 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
 		err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
-		if (err) {
-			path_put(&path);
+		if (err)
 			return err;
-		}
 	}
 
-	err = dquot_quota_on_path(sb, type, format_id, &path);
-	path_put(&path);
-	return err;
+	return dquot_quota_on(sb, type, format_id, path);
 }
 
 static int ext4_quota_off(struct super_block *sb, int type)
@@ -4779,7 +4770,7 @@ static struct file_system_type ext4_fs_type = {
 	.fs_flags	= FS_REQUIRES_DEV,
 };
 
-int __init ext4_init_feat_adverts(void)
+static int __init ext4_init_feat_adverts(void)
 {
 	struct ext4_features *ef;
 	int ret = -ENOMEM;
@@ -4803,23 +4794,44 @@ out:
 	return ret;
 }
 
+static void ext4_exit_feat_adverts(void)
+{
+	kobject_put(&ext4_feat->f_kobj);
+	wait_for_completion(&ext4_feat->f_kobj_unregister);
+	kfree(ext4_feat);
+}
+
+/* Shared across all ext4 file systems */
+wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
 static int __init ext4_init_fs(void)
 {
-	int err;
+	int i, err;
 
 	ext4_check_flag_values();
+
+	for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
+		mutex_init(&ext4__aio_mutex[i]);
+		init_waitqueue_head(&ext4__ioend_wq[i]);
+	}
+
 	err = ext4_init_pageio();
 	if (err)
 		return err;
 	err = ext4_init_system_zone();
 	if (err)
-		goto out5;
+		goto out7;
 	ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
 	if (!ext4_kset)
-		goto out4;
+		goto out6;
 	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
+	if (!ext4_proc_root)
+		goto out5;
 
 	err = ext4_init_feat_adverts();
+	if (err)
+		goto out4;
 
 	err = ext4_init_mballoc();
 	if (err)
@@ -4849,12 +4861,14 @@ out1:
 out2:
 	ext4_exit_mballoc();
 out3:
-	kfree(ext4_feat);
+	ext4_exit_feat_adverts();
+out4:
 	remove_proc_entry("fs/ext4", NULL);
+out5:
 	kset_unregister(ext4_kset);
-out4:
+out6:
 	ext4_exit_system_zone();
-out5:
+out7:
 	ext4_exit_pageio();
 	return err;
 }
@@ -4868,6 +4882,7 @@ static void __exit ext4_exit_fs(void)
 	destroy_inodecache();
 	ext4_exit_xattr();
 	ext4_exit_mballoc();
+	ext4_exit_feat_adverts();
 	remove_proc_entry("fs/ext4", NULL);
 	kset_unregister(ext4_kset);
 	ext4_exit_system_zone();
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ecc8b3954ed6..cb1026181bdc 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -815,7 +815,7 @@ static int __init fcntl_init(void)
 		__O_SYNC	| O_DSYNC	| FASYNC	|
 		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
 		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		FMODE_EXEC
+		__FMODE_EXEC
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/file_table.c b/fs/file_table.c
index c3dee381f1b4..eb36b6b17e26 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -125,13 +125,13 @@ struct file *get_empty_filp(void)
 		goto fail;
 
 	percpu_counter_inc(&nr_files);
+	f->f_cred = get_cred(cred);
 	if (security_file_alloc(f))
 		goto fail_sec;
 
 	INIT_LIST_HEAD(&f->f_u.fu_list);
 	atomic_long_set(&f->f_count, 1);
 	rwlock_init(&f->f_owner.lock);
-	f->f_cred = get_cred(cred);
 	spin_lock_init(&f->f_lock);
 	eventpoll_init_file(f);
 	/* f->f_version: 0 */
@@ -311,7 +311,7 @@ struct file *fget_light(unsigned int fd, int *fput_needed)
 	struct files_struct *files = current->files;
 
 	*fput_needed = 0;
-	if (likely((atomic_read(&files->count) == 1))) {
+	if (atomic_read(&files->count) == 1) {
 		file = fcheck_files(files, fd);
 	} else {
 		rcu_read_lock();
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3d06ccc953aa..59c6e4956786 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -84,13 +84,9 @@ static inline struct inode *wb_inode(struct list_head *head)
 	return list_entry(head, struct inode, i_wb_list);
 }
 
-static void bdi_queue_work(struct backing_dev_info *bdi,
-		struct wb_writeback_work *work)
+/* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
+static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
 {
-	trace_writeback_queue(bdi, work);
-
-	spin_lock_bh(&bdi->wb_lock);
-	list_add_tail(&work->list, &bdi->work_list);
 	if (bdi->wb.task) {
 		wake_up_process(bdi->wb.task);
 	} else {
@@ -98,15 +94,26 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
 		 * The bdi thread isn't there, wake up the forker thread which
 		 * will create and run it.
 		 */
-		trace_writeback_nothread(bdi, work);
 		wake_up_process(default_backing_dev_info.wb.task);
 	}
+}
+
+static void bdi_queue_work(struct backing_dev_info *bdi,
+			   struct wb_writeback_work *work)
+{
+	trace_writeback_queue(bdi, work);
+
+	spin_lock_bh(&bdi->wb_lock);
+	list_add_tail(&work->list, &bdi->work_list);
+	if (!bdi->wb.task)
+		trace_writeback_nothread(bdi, work);
+	bdi_wakeup_flusher(bdi);
 	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
 __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
-		bool range_cyclic, bool for_background)
+		      bool range_cyclic)
 {
 	struct wb_writeback_work *work;
 
@@ -126,7 +133,6 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work->sync_mode	= WB_SYNC_NONE;
 	work->nr_pages	= nr_pages;
 	work->range_cyclic = range_cyclic;
-	work->for_background = for_background;
 
 	bdi_queue_work(bdi, work);
 }
@@ -144,7 +150,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
  */
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
 {
-	__bdi_start_writeback(bdi, nr_pages, true, false);
+	__bdi_start_writeback(bdi, nr_pages, true);
 }
 
 /**
@@ -152,13 +158,21 @@ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
  * @bdi: the backing device to write from
  *
  * Description:
- *   This does WB_SYNC_NONE background writeback. The IO is only
- *   started when this function returns, we make no guarentees on
- *   completion. Caller need not hold sb s_umount semaphore.
+ *   This makes sure WB_SYNC_NONE background writeback happens. When
+ *   this function returns, it is only guaranteed that for given BDI
+ *   some IO is happening if we are over background dirty threshold.
+ *   Caller need not hold sb s_umount semaphore.
  */
 void bdi_start_background_writeback(struct backing_dev_info *bdi)
 {
-	__bdi_start_writeback(bdi, LONG_MAX, true, true);
+	/*
+	 * We just wake up the flusher thread. It will perform background
+	 * writeback as soon as there is no other work to do.
+	 */
+	trace_writeback_wake_background(bdi);
+	spin_lock_bh(&bdi->wb_lock);
+	bdi_wakeup_flusher(bdi);
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 /*
@@ -616,6 +630,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 	};
 	unsigned long oldest_jif;
 	long wrote = 0;
+	long write_chunk;
 	struct inode *inode;
 
 	if (wbc.for_kupdate) {
@@ -628,6 +643,24 @@ static long wb_writeback(struct bdi_writeback *wb,
 		wbc.range_end = LLONG_MAX;
 	}
 
+	/*
+	 * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
+	 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
+	 * here avoids calling into writeback_inodes_wb() more than once.
+	 *
+	 * The intended call sequence for WB_SYNC_ALL writeback is:
+	 *
+	 *      wb_writeback()
+	 *          __writeback_inodes_sb()     <== called only once
+	 *              write_cache_pages()     <== called once for each inode
+	 *                   (quickly) tag currently dirty pages
+	 *                   (maybe slowly) sync all tagged pages
+	 */
+	if (wbc.sync_mode == WB_SYNC_NONE)
+		write_chunk = MAX_WRITEBACK_PAGES;
+	else
+		write_chunk = LONG_MAX;
+
 	wbc.wb_start = jiffies; /* livelock avoidance */
 	for (;;) {
 		/*
@@ -637,6 +670,16 @@ static long wb_writeback(struct bdi_writeback *wb,
 			break;
 
 		/*
+		 * Background writeout and kupdate-style writeback may
+		 * run forever. Stop them if there is other work to do
+		 * so that e.g. sync can proceed. They'll be restarted
+		 * after the other works are all done.
+		 */
+		if ((work->for_background || work->for_kupdate) &&
+		    !list_empty(&wb->bdi->work_list))
+			break;
+
+		/*
 		 * For background writeout, stop when we are below the
 		 * background dirty threshold
 		 */
@@ -644,7 +687,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 			break;
 
 		wbc.more_io = 0;
-		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;
 
 		trace_wbc_writeback_start(&wbc, wb->bdi);
@@ -654,8 +697,8 @@ static long wb_writeback(struct bdi_writeback *wb,
 			writeback_inodes_wb(wb, &wbc);
 		trace_wbc_writeback_written(&wbc, wb->bdi);
 
-		work->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
-		wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+		work->nr_pages -= write_chunk - wbc.nr_to_write;
+		wrote += write_chunk - wbc.nr_to_write;
 
 		/*
 		 * If we consumed everything, see if we have more
@@ -670,7 +713,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		/*
 		 * Did we write something? Try for more
 		 */
-		if (wbc.nr_to_write < MAX_WRITEBACK_PAGES)
+		if (wbc.nr_to_write < write_chunk)
 			continue;
 		/*
 		 * Nothing written. Wait for some inode to
@@ -718,6 +761,23 @@ static unsigned long get_nr_dirty_pages(void)
 		get_nr_dirty_inodes();
 }
 
+static long wb_check_background_flush(struct bdi_writeback *wb)
+{
+	if (over_bground_thresh()) {
+
+		struct wb_writeback_work work = {
+			.nr_pages	= LONG_MAX,
+			.sync_mode	= WB_SYNC_NONE,
+			.for_background	= 1,
+			.range_cyclic	= 1,
+		};
+
+		return wb_writeback(wb, &work);
+	}
+
+	return 0;
+}
+
 static long wb_check_old_data_flush(struct bdi_writeback *wb)
 {
 	unsigned long expired;
@@ -787,6 +847,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 	 * Check for periodic writeback, kupdated() style
 	 */
 	wrote += wb_check_old_data_flush(wb);
+	wrote += wb_check_background_flush(wb);
 	clear_bit(BDI_writeback_running, &wb->bdi->state);
 
 	return wrote;
@@ -873,7 +934,7 @@ void wakeup_flusher_threads(long nr_pages)
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
 		if (!bdi_has_dirty_io(bdi))
 			continue;
-		__bdi_start_writeback(bdi, nr_pages, false, false);
+		__bdi_start_writeback(bdi, nr_pages, false);
 	}
 	rcu_read_unlock();
 }
@@ -1164,7 +1225,7 @@ EXPORT_SYMBOL(writeback_inodes_sb_nr_if_idle);
  * @sb: the superblock
  *
  * This function writes and waits on any dirty inode belonging to this
- * super_block. The number of pages synced is returned.
+ * super_block.
  */
 void sync_inodes_sb(struct super_block *sb)
 {
@@ -1242,11 +1303,11 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc)
 EXPORT_SYMBOL(sync_inode);
 
 /**
- * sync_inode - write an inode to disk
+ * sync_inode_metadata - write an inode to disk
  * @inode: the inode to sync
  * @wait: wait for I/O to complete.
  *
- * Write an inode to disk and adjust it's dirty state after completion.
+ * Write an inode to disk and adjust its dirty state after completion.
  *
  * Note: only writes the actual inode, no associated data or other metadata.
  */
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 68ca487bedb1..78b519c13536 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -4,6 +4,19 @@
 #include <linux/path.h>
 #include <linux/slab.h>
 #include <linux/fs_struct.h>
+#include "internal.h"
+
+static inline void path_get_longterm(struct path *path)
+{
+	path_get(path);
+	mnt_make_longterm(path->mnt);
+}
+
+static inline void path_put_longterm(struct path *path)
+{
+	mnt_make_shortterm(path->mnt);
+	path_put(path);
+}
 
 /*
  * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
@@ -17,11 +30,11 @@ void set_fs_root(struct fs_struct *fs, struct path *path)
 	write_seqcount_begin(&fs->seq);
 	old_root = fs->root;
 	fs->root = *path;
-	path_get_long(path);
+	path_get_longterm(path);
 	write_seqcount_end(&fs->seq);
 	spin_unlock(&fs->lock);
 	if (old_root.dentry)
-		path_put_long(&old_root);
+		path_put_longterm(&old_root);
 }
 
 /*
@@ -36,12 +49,12 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path)
 	write_seqcount_begin(&fs->seq);
 	old_pwd = fs->pwd;
 	fs->pwd = *path;
-	path_get_long(path);
+	path_get_longterm(path);
 	write_seqcount_end(&fs->seq);
 	spin_unlock(&fs->lock);
 
 	if (old_pwd.dentry)
-		path_put_long(&old_pwd);
+		path_put_longterm(&old_pwd);
 }
 
 void chroot_fs_refs(struct path *old_root, struct path *new_root)
@@ -59,13 +72,13 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 			write_seqcount_begin(&fs->seq);
 			if (fs->root.dentry == old_root->dentry
 			    && fs->root.mnt == old_root->mnt) {
-				path_get_long(new_root);
+				path_get_longterm(new_root);
 				fs->root = *new_root;
 				count++;
 			}
 			if (fs->pwd.dentry == old_root->dentry
 			    && fs->pwd.mnt == old_root->mnt) {
-				path_get_long(new_root);
+				path_get_longterm(new_root);
 				fs->pwd = *new_root;
 				count++;
 			}
@@ -76,13 +89,13 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
 	while (count--)
-		path_put_long(old_root);
+		path_put_longterm(old_root);
 }
 
 void free_fs_struct(struct fs_struct *fs)
 {
-	path_put_long(&fs->root);
-	path_put_long(&fs->pwd);
+	path_put_longterm(&fs->root);
+	path_put_longterm(&fs->pwd);
 	kmem_cache_free(fs_cachep, fs);
 }
 
@@ -118,9 +131,9 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
 
 		spin_lock(&old->lock);
 		fs->root = old->root;
-		path_get_long(&fs->root);
+		path_get_longterm(&fs->root);
 		fs->pwd = old->pwd;
-		path_get_long(&fs->pwd);
+		path_get_longterm(&fs->pwd);
 		spin_unlock(&old->lock);
 	}
 	return fs;
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index b9f34eaede09..48a18f184d50 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -101,7 +101,7 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 		object->n_ops++;
 		object->n_exclusive++;	/* reads and writes must wait */
 
-		if (object->n_ops > 0) {
+		if (object->n_ops > 1) {
 			atomic_inc(&op->usage);
 			list_add_tail(&op->pend_link, &object->pending_ops);
 			fscache_stat(&fscache_n_op_pend);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index fca6689e12e6..7cfdcb913363 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -19,6 +19,8 @@
 #include <linux/fs.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/ext2_fs.h>
+#include <linux/falloc.h>
+#include <linux/swap.h>
 #include <linux/crc32.h>
 #include <linux/writeback.h>
 #include <asm/uaccess.h>
@@ -610,6 +612,260 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	return generic_file_aio_write(iocb, iov, nr_segs, pos);
 }
 
+static void empty_write_end(struct page *page, unsigned from,
+			   unsigned to)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+
+	page_zero_new_buffers(page, from, to);
+	flush_dcache_page(page);
+	mark_page_accessed(page);
+
+	if (!gfs2_is_writeback(ip))
+		gfs2_page_add_databufs(ip, page, from, to);
+
+	block_commit_write(page, from, to);
+}
+
+static int write_empty_blocks(struct page *page, unsigned from, unsigned to)
+{
+	unsigned start, end, next;
+	struct buffer_head *bh, *head;
+	int error;
+
+	if (!page_has_buffers(page)) {
+		error = __block_write_begin(page, from, to - from, gfs2_block_map);
+		if (unlikely(error))
+			return error;
+
+		empty_write_end(page, from, to);
+		return 0;
+	}
+
+	bh = head = page_buffers(page);
+	next = end = 0;
+	while (next < from) {
+		next += bh->b_size;
+		bh = bh->b_this_page;
+	}
+	start = next;
+	do {
+		next += bh->b_size;
+		if (buffer_mapped(bh)) {
+			if (end) {
+				error = __block_write_begin(page, start, end - start,
+							    gfs2_block_map);
+				if (unlikely(error))
+					return error;
+				empty_write_end(page, start, end);
+				end = 0;
+			}
+			start = next;
+		}
+		else
+			end = next;
+		bh = bh->b_this_page;
+	} while (next < to);
+
+	if (end) {
+		error = __block_write_begin(page, start, end - start, gfs2_block_map);
+		if (unlikely(error))
+			return error;
+		empty_write_end(page, start, end);
+	}
+
+	return 0;
+}
+
+static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
+			   int mode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct buffer_head *dibh;
+	int error;
+	u64 start = offset >> PAGE_CACHE_SHIFT;
+	unsigned int start_offset = offset & ~PAGE_CACHE_MASK;
+	u64 end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+	pgoff_t curr;
+	struct page *page;
+	unsigned int end_offset = (offset + len) & ~PAGE_CACHE_MASK;
+	unsigned int from, to;
+
+	if (!end_offset)
+		end_offset = PAGE_CACHE_SIZE;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (unlikely(error))
+		goto out;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+
+	if (gfs2_is_stuffed(ip)) {
+		error = gfs2_unstuff_dinode(ip, NULL);
+		if (unlikely(error))
+			goto out;
+	}
+
+	curr = start;
+	offset = start << PAGE_CACHE_SHIFT;
+	from = start_offset;
+	to = PAGE_CACHE_SIZE;
+	while (curr <= end) {
+		page = grab_cache_page_write_begin(inode->i_mapping, curr,
+						   AOP_FLAG_NOFS);
+		if (unlikely(!page)) {
+			error = -ENOMEM;
+			goto out;
+		}
+
+		if (curr == end)
+			to = end_offset;
+		error = write_empty_blocks(page, from, to);
+		if (!error && offset + to > inode->i_size &&
+		    !(mode & FALLOC_FL_KEEP_SIZE)) {
+			i_size_write(inode, offset + to);
+		}
+		unlock_page(page);
+		page_cache_release(page);
+		if (error)
+			goto out;
+		curr++;
+		offset += PAGE_CACHE_SIZE;
+		from = 0;
+	}
+
+	gfs2_dinode_out(ip, dibh->b_data);
+	mark_inode_dirty(inode);
+
+	brelse(dibh);
+
+out:
+	return error;
+}
+
+static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len,
+			    unsigned int *data_blocks, unsigned int *ind_blocks)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	unsigned int max_blocks = ip->i_alloc->al_rgd->rd_free_clone;
+	unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1);
+
+	for (tmp = max_data; tmp > sdp->sd_diptrs;) {
+		tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
+		max_data -= tmp;
+	}
+	/* This calculation isn't the exact reverse of gfs2_write_calc_reserve,
+	   so it might end up with fewer data blocks */
+	if (max_data <= *data_blocks)
+		return;
+	*data_blocks = max_data;
+	*ind_blocks = max_blocks - max_data;
+	*len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift;
+	if (*len > max) {
+		*len = max;
+		gfs2_write_calc_reserv(ip, max, data_blocks, ind_blocks);
+	}
+}
+
+static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
+			   loff_t len)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
+	loff_t bytes, max_bytes;
+	struct gfs2_alloc *al;
+	int error;
+	loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
+	next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
+
+	/* We only support the FALLOC_FL_KEEP_SIZE mode */
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
+		return -EOPNOTSUPP;
+
+	offset = (offset >> sdp->sd_sb.sb_bsize_shift) <<
+		 sdp->sd_sb.sb_bsize_shift;
+
+	len = next - offset;
+	bytes = sdp->sd_max_rg_data * sdp->sd_sb.sb_bsize / 2;
+	if (!bytes)
+		bytes = UINT_MAX;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+	error = gfs2_glock_nq(&ip->i_gh);
+	if (unlikely(error))
+		goto out_uninit;
+
+	if (!gfs2_write_alloc_required(ip, offset, len))
+		goto out_unlock;
+
+	while (len > 0) {
+		if (len < bytes)
+			bytes = len;
+		al = gfs2_alloc_get(ip);
+		if (!al) {
+			error = -ENOMEM;
+			goto out_unlock;
+		}
+
+		error = gfs2_quota_lock_check(ip);
+		if (error)
+			goto out_alloc_put;
+
+retry:
+		gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);
+
+		al->al_requested = data_blocks + ind_blocks;
+		error = gfs2_inplace_reserve(ip);
+		if (error) {
+			if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) {
+				bytes >>= 1;
+				goto retry;
+			}
+			goto out_qunlock;
+		}
+		max_bytes = bytes;
+		calc_max_reserv(ip, len, &max_bytes, &data_blocks, &ind_blocks);
+		al->al_requested = data_blocks + ind_blocks;
+
+		rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA +
+			  RES_RG_HDR + gfs2_rg_blocks(al);
+		if (gfs2_is_jdata(ip))
+			rblocks += data_blocks ? data_blocks : 1;
+
+		error = gfs2_trans_begin(sdp, rblocks,
+					 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
+		if (error)
+			goto out_trans_fail;
+
+		error = fallocate_chunk(inode, offset, max_bytes, mode);
+		gfs2_trans_end(sdp);
+
+		if (error)
+			goto out_trans_fail;
+
+		len -= max_bytes;
+		offset += max_bytes;
+		gfs2_inplace_release(ip);
+		gfs2_quota_unlock(ip);
+		gfs2_alloc_put(ip);
+	}
+	goto out_unlock;
+
+out_trans_fail:
+	gfs2_inplace_release(ip);
+out_qunlock:
+	gfs2_quota_unlock(ip);
+out_alloc_put:
+	gfs2_alloc_put(ip);
+out_unlock:
+	gfs2_glock_dq(&ip->i_gh);
+out_uninit:
+	gfs2_holder_uninit(&ip->i_gh);
+	return error;
+}
+
 #ifdef CONFIG_GFS2_FS_LOCKING_DLM
 
 /**
@@ -765,6 +1021,7 @@ const struct file_operations gfs2_file_fops = {
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= generic_file_splice_write,
 	.setlease	= gfs2_setlease,
+	.fallocate	= gfs2_fallocate,
 };
 
 const struct file_operations gfs2_dir_fops = {
@@ -794,6 +1051,7 @@ const struct file_operations gfs2_file_fops_nolock = {
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= generic_file_splice_write,
 	.setlease	= generic_setlease,
+	.fallocate	= gfs2_fallocate,
 };
 
 const struct file_operations gfs2_dir_fops_nolock = {
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 2232b3c780bd..7aa7d4f8984a 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -74,16 +74,14 @@ static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr)
 }
 
 /**
- * GFS2 lookup code fills in vfs inode contents based on info obtained
- * from directory entry inside gfs2_inode_lookup(). This has caused issues
- * with NFS code path since its get_dentry routine doesn't have the relevant
- * directory entry when gfs2_inode_lookup() is invoked. Part of the code
- * segment inside gfs2_inode_lookup code needs to get moved around.
+ * gfs2_set_iop - Sets inode operations
+ * @inode: The inode with correct i_mode filled in
  *
- * Clears I_NEW as well.
- **/
+ * GFS2 lookup code fills in vfs inode contents based on info obtained
+ * from directory entry inside gfs2_inode_lookup().
+ */
 
-void gfs2_set_iop(struct inode *inode)
+static void gfs2_set_iop(struct inode *inode)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	umode_t mode = inode->i_mode;
@@ -106,8 +104,6 @@ void gfs2_set_iop(struct inode *inode)
 		inode->i_op = &gfs2_file_iops;
 		init_special_inode(inode, inode->i_mode, inode->i_rdev);
 	}
-
-	unlock_new_inode(inode);
 }
 
 /**
@@ -119,10 +115,8 @@ void gfs2_set_iop(struct inode *inode)
  * Returns: A VFS inode, or an error
  */
 
-struct inode *gfs2_inode_lookup(struct super_block *sb,
-				unsigned int type,
-				u64 no_addr,
-				u64 no_formal_ino)
+struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
+				u64 no_addr, u64 no_formal_ino)
 {
 	struct inode *inode;
 	struct gfs2_inode *ip;
@@ -152,51 +146,37 @@ struct inode *gfs2_inode_lookup(struct super_block *sb,
 		error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
 		if (unlikely(error))
 			goto fail_iopen;
-		ip->i_iopen_gh.gh_gl->gl_object = ip;
 
+		ip->i_iopen_gh.gh_gl->gl_object = ip;
 		gfs2_glock_put(io_gl);
 		io_gl = NULL;
 
-		if ((type == DT_UNKNOWN) && (no_formal_ino == 0))
-			goto gfs2_nfsbypass;
-
-		inode->i_mode = DT2IF(type);
-
-		/*
-		 * We must read the inode in order to work out its type in
-		 * this case. Note that this doesn't happen often as we normally
-		 * know the type beforehand. This code path only occurs during
-		 * unlinked inode recovery (where it is safe to do this glock,
-		 * which is not true in the general case).
-		 */
 		if (type == DT_UNKNOWN) {
-			struct gfs2_holder gh;
-			error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-			if (unlikely(error))
-				goto fail_glock;
-			/* Inode is now uptodate */
-			gfs2_glock_dq_uninit(&gh);
+			/* Inode glock must be locked already */
+			error = gfs2_inode_refresh(GFS2_I(inode));
+			if (error)
+				goto fail_refresh;
+		} else {
+			inode->i_mode = DT2IF(type);
 		}
 
 		gfs2_set_iop(inode);
+		unlock_new_inode(inode);
 	}
 
-gfs2_nfsbypass:
 	return inode;
-fail_glock:
-	gfs2_glock_dq(&ip->i_iopen_gh);
+
+fail_refresh:
+	ip->i_iopen_gh.gh_gl->gl_object = NULL;
+	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 fail_iopen:
 	if (io_gl)
 		gfs2_glock_put(io_gl);
 fail_put:
-	if (inode->i_state & I_NEW)
-		ip->i_gl->gl_object = NULL;
+	ip->i_gl->gl_object = NULL;
 	gfs2_glock_put(ip->i_gl);
 fail:
-	if (inode->i_state & I_NEW)
-		iget_failed(inode);
-	else
-		iput(inode);
+	iget_failed(inode);
 	return ERR_PTR(error);
 }
 
@@ -221,14 +201,6 @@ struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
 	if (IS_ERR(inode))
 		goto fail;
 
-	error = gfs2_inode_refresh(GFS2_I(inode));
-	if (error)
-		goto fail_iput;
-
-	/* Pick up the works we bypass in gfs2_inode_lookup */
-	if (inode->i_state & I_NEW) 
-		gfs2_set_iop(inode);
-
 	/* Two extra checks for NFS only */
 	if (no_formal_ino) {
 		error = -ESTALE;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 732a183efdb3..3e00a66e7cbd 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -96,7 +96,6 @@ err:
 	return -EIO;
 }
 
-extern void gfs2_set_iop(struct inode *inode);
 extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
 				       u64 no_addr, u64 no_formal_ino);
 extern struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 040b5a2e6556..d8b26ac2e20b 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -18,8 +18,6 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
 #include <linux/fiemap.h>
-#include <linux/swap.h>
-#include <linux/falloc.h>
 #include <asm/uaccess.h>
 
 #include "gfs2.h"
@@ -1257,261 +1255,6 @@ static int gfs2_removexattr(struct dentry *dentry, const char *name)
 	return ret;
 }
 
-static void empty_write_end(struct page *page, unsigned from,
-			   unsigned to)
-{
-	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
-
-	page_zero_new_buffers(page, from, to);
-	flush_dcache_page(page);
-	mark_page_accessed(page);
-
-	if (!gfs2_is_writeback(ip))
-		gfs2_page_add_databufs(ip, page, from, to);
-
-	block_commit_write(page, from, to);
-}
-
-
-static int write_empty_blocks(struct page *page, unsigned from, unsigned to)
-{
-	unsigned start, end, next;
-	struct buffer_head *bh, *head;
-	int error;
-
-	if (!page_has_buffers(page)) {
-		error = __block_write_begin(page, from, to - from, gfs2_block_map);
-		if (unlikely(error))
-			return error;
-
-		empty_write_end(page, from, to);
-		return 0;
-	}
-
-	bh = head = page_buffers(page);
-	next = end = 0;
-	while (next < from) {
-		next += bh->b_size;
-		bh = bh->b_this_page;
-	}
-	start = next;
-	do {
-		next += bh->b_size;
-		if (buffer_mapped(bh)) {
-			if (end) {
-				error = __block_write_begin(page, start, end - start,
-							    gfs2_block_map);
-				if (unlikely(error))
-					return error;
-				empty_write_end(page, start, end);
-				end = 0;
-			}
-			start = next;
-		}
-		else
-			end = next;
-		bh = bh->b_this_page;
-	} while (next < to);
-
-	if (end) {
-		error = __block_write_begin(page, start, end - start, gfs2_block_map);
-		if (unlikely(error))
-			return error;
-		empty_write_end(page, start, end);
-	}
-
-	return 0;
-}
-
-static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
-			   int mode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct buffer_head *dibh;
-	int error;
-	u64 start = offset >> PAGE_CACHE_SHIFT;
-	unsigned int start_offset = offset & ~PAGE_CACHE_MASK;
-	u64 end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
-	pgoff_t curr;
-	struct page *page;
-	unsigned int end_offset = (offset + len) & ~PAGE_CACHE_MASK;
-	unsigned int from, to;
-
-	if (!end_offset)
-		end_offset = PAGE_CACHE_SIZE;
-
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (unlikely(error))
-		goto out;
-
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-
-	if (gfs2_is_stuffed(ip)) {
-		error = gfs2_unstuff_dinode(ip, NULL);
-		if (unlikely(error))
-			goto out;
-	}
-
-	curr = start;
-	offset = start << PAGE_CACHE_SHIFT;
-	from = start_offset;
-	to = PAGE_CACHE_SIZE;
-	while (curr <= end) {
-		page = grab_cache_page_write_begin(inode->i_mapping, curr,
-						   AOP_FLAG_NOFS);
-		if (unlikely(!page)) {
-			error = -ENOMEM;
-			goto out;
-		}
-
-		if (curr == end)
-			to = end_offset;
-		error = write_empty_blocks(page, from, to);
-		if (!error && offset + to > inode->i_size &&
-		    !(mode & FALLOC_FL_KEEP_SIZE)) {
-			i_size_write(inode, offset + to);
-		}
-		unlock_page(page);
-		page_cache_release(page);
-		if (error)
-			goto out;
-		curr++;
-		offset += PAGE_CACHE_SIZE;
-		from = 0;
-	}
-
-	gfs2_dinode_out(ip, dibh->b_data);
-	mark_inode_dirty(inode);
-
-	brelse(dibh);
-
-out:
-	return error;
-}
-
-static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len,
-			    unsigned int *data_blocks, unsigned int *ind_blocks)
-{
-	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned int max_blocks = ip->i_alloc->al_rgd->rd_free_clone;
-	unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1);
-
-	for (tmp = max_data; tmp > sdp->sd_diptrs;) {
-		tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
-		max_data -= tmp;
-	}
-	/* This calculation isn't the exact reverse of gfs2_write_calc_reserve,
-	   so it might end up with fewer data blocks */
-	if (max_data <= *data_blocks)
-		return;
-	*data_blocks = max_data;
-	*ind_blocks = max_blocks - max_data;
-	*len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift;
-	if (*len > max) {
-		*len = max;
-		gfs2_write_calc_reserv(ip, max, data_blocks, ind_blocks);
-	}
-}
-
-static long gfs2_fallocate(struct inode *inode, int mode, loff_t offset,
-			   loff_t len)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_inode *ip = GFS2_I(inode);
-	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
-	loff_t bytes, max_bytes;
-	struct gfs2_alloc *al;
-	int error;
-	loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
-	next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
-
-	/* We only support the FALLOC_FL_KEEP_SIZE mode */
-	if (mode && (mode != FALLOC_FL_KEEP_SIZE))
-		return -EOPNOTSUPP;
-
-	offset = (offset >> sdp->sd_sb.sb_bsize_shift) <<
-		 sdp->sd_sb.sb_bsize_shift;
-
-	len = next - offset;
-	bytes = sdp->sd_max_rg_data * sdp->sd_sb.sb_bsize / 2;
-	if (!bytes)
-		bytes = UINT_MAX;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
-	error = gfs2_glock_nq(&ip->i_gh);
-	if (unlikely(error))
-		goto out_uninit;
-
-	if (!gfs2_write_alloc_required(ip, offset, len))
-		goto out_unlock;
-
-	while (len > 0) {
-		if (len < bytes)
-			bytes = len;
-		al = gfs2_alloc_get(ip);
-		if (!al) {
-			error = -ENOMEM;
-			goto out_unlock;
-		}
-
-		error = gfs2_quota_lock_check(ip);
-		if (error)
-			goto out_alloc_put;
-
-retry:
-		gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);
-
-		al->al_requested = data_blocks + ind_blocks;
-		error = gfs2_inplace_reserve(ip);
-		if (error) {
-			if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) {
-				bytes >>= 1;
-				goto retry;
-			}
-			goto out_qunlock;
-		}
-		max_bytes = bytes;
-		calc_max_reserv(ip, len, &max_bytes, &data_blocks, &ind_blocks);
-		al->al_requested = data_blocks + ind_blocks;
-
-		rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA +
-			  RES_RG_HDR + gfs2_rg_blocks(al);
-		if (gfs2_is_jdata(ip))
-			rblocks += data_blocks ? data_blocks : 1;
-
-		error = gfs2_trans_begin(sdp, rblocks,
-					 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
-		if (error)
-			goto out_trans_fail;
-
-		error = fallocate_chunk(inode, offset, max_bytes, mode);
-		gfs2_trans_end(sdp);
-
-		if (error)
-			goto out_trans_fail;
-
-		len -= max_bytes;
-		offset += max_bytes;
-		gfs2_inplace_release(ip);
-		gfs2_quota_unlock(ip);
-		gfs2_alloc_put(ip);
-	}
-	goto out_unlock;
-
-out_trans_fail:
-	gfs2_inplace_release(ip);
-out_qunlock:
-	gfs2_quota_unlock(ip);
-out_alloc_put:
-	gfs2_alloc_put(ip);
-out_unlock:
-	gfs2_glock_dq(&ip->i_gh);
-out_uninit:
-	gfs2_holder_uninit(&ip->i_gh);
-	return error;
-}
-
-
 static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		       u64 start, u64 len)
 {
@@ -1562,7 +1305,6 @@ const struct inode_operations gfs2_file_iops = {
 	.getxattr = gfs2_getxattr,
 	.listxattr = gfs2_listxattr,
 	.removexattr = gfs2_removexattr,
-	.fallocate = gfs2_fallocate,
 	.fiemap = gfs2_fiemap,
 };
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 16c2ecac7eb7..ec73ed70bae1 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1336,6 +1336,7 @@ static void gfs2_evict_inode(struct inode *inode)
 	if (error)
 		goto out_truncate;
 
+	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 	gfs2_glock_dq_wait(&ip->i_iopen_gh);
 	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
 	error = gfs2_glock_nq(&ip->i_iopen_gh);
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 52a0bcaa7b6d..b1991a2a08e0 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -397,8 +397,8 @@ int hfsplus_file_extend(struct inode *inode)
 	u32 start, len, goal;
 	int res;
 
-	if (sbi->total_blocks - sbi->free_blocks + 8 >
-			sbi->alloc_file->i_size * 8) {
+	if (sbi->alloc_file->i_size * 8 <
+	    sbi->total_blocks - sbi->free_blocks + 8) {
 		/* extend alloc file */
 		printk(KERN_ERR "hfs: extend alloc file! "
 				"(%llu,%u,%u)\n",
diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c
index d66ad113b1cc..40ad88c12c64 100644
--- a/fs/hfsplus/part_tbl.c
+++ b/fs/hfsplus/part_tbl.c
@@ -134,7 +134,7 @@ int hfs_part_find(struct super_block *sb,
 	res = hfsplus_submit_bio(sb->s_bdev, *part_start + HFS_PMAP_BLK,
 				 data, READ);
 	if (res)
-		return res;
+		goto out;
 
 	switch (be16_to_cpu(*((__be16 *)data))) {
 	case HFS_OLD_PMAP_MAGIC:
@@ -147,7 +147,7 @@ int hfs_part_find(struct super_block *sb,
 		res = -ENOENT;
 		break;
 	}
-
+out:
 	kfree(data);
 	return res;
 }
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 9a3b4795f43c..b49b55584c84 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -338,20 +338,22 @@ 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;
-	int err = -EINVAL;
+	int err;
 
+	err = -EINVAL;
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
-		return -ENOMEM;
+		goto out;
 
 	sb->s_fs_info = sbi;
 	mutex_init(&sbi->alloc_mutex);
 	mutex_init(&sbi->vh_mutex);
 	hfsplus_fill_defaults(sbi);
+
+	err = -EINVAL;
 	if (!hfsplus_parse_options(data, sbi)) {
 		printk(KERN_ERR "hfs: unable to parse mount options\n");
-		err = -EINVAL;
-		goto cleanup;
+		goto out_unload_nls;
 	}
 
 	/* temporarily use utf8 to correctly find the hidden dir below */
@@ -359,16 +361,14 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->nls = load_nls("utf8");
 	if (!sbi->nls) {
 		printk(KERN_ERR "hfs: unable to load nls for utf8\n");
-		err = -EINVAL;
-		goto cleanup;
+		goto out_unload_nls;
 	}
 
 	/* Grab the volume header */
 	if (hfsplus_read_wrapper(sb)) {
 		if (!silent)
 			printk(KERN_WARNING "hfs: unable to find HFS+ superblock\n");
-		err = -EINVAL;
-		goto cleanup;
+		goto out_unload_nls;
 	}
 	vhdr = sbi->s_vhdr;
 
@@ -377,7 +377,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	if (be16_to_cpu(vhdr->version) < HFSPLUS_MIN_VERSION ||
 	    be16_to_cpu(vhdr->version) > HFSPLUS_CURRENT_VERSION) {
 		printk(KERN_ERR "hfs: wrong filesystem version\n");
-		goto cleanup;
+		goto out_free_vhdr;
 	}
 	sbi->total_blocks = be32_to_cpu(vhdr->total_blocks);
 	sbi->free_blocks = be32_to_cpu(vhdr->free_blocks);
@@ -421,19 +421,19 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID);
 	if (!sbi->ext_tree) {
 		printk(KERN_ERR "hfs: failed to load extents file\n");
-		goto cleanup;
+		goto out_free_vhdr;
 	}
 	sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID);
 	if (!sbi->cat_tree) {
 		printk(KERN_ERR "hfs: failed to load catalog file\n");
-		goto cleanup;
+		goto out_close_ext_tree;
 	}
 
 	inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID);
 	if (IS_ERR(inode)) {
 		printk(KERN_ERR "hfs: failed to load allocation file\n");
 		err = PTR_ERR(inode);
-		goto cleanup;
+		goto out_close_cat_tree;
 	}
 	sbi->alloc_file = inode;
 
@@ -442,14 +442,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	if (IS_ERR(root)) {
 		printk(KERN_ERR "hfs: failed to load root directory\n");
 		err = PTR_ERR(root);
-		goto cleanup;
-	}
-	sb->s_d_op = &hfsplus_dentry_operations;
-	sb->s_root = d_alloc_root(root);
-	if (!sb->s_root) {
-		iput(root);
-		err = -ENOMEM;
-		goto cleanup;
+		goto out_put_alloc_file;
 	}
 
 	str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1;
@@ -459,46 +452,69 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
 		hfs_find_exit(&fd);
 		if (entry.type != cpu_to_be16(HFSPLUS_FOLDER))
-			goto cleanup;
+			goto out_put_root;
 		inode = hfsplus_iget(sb, be32_to_cpu(entry.folder.id));
 		if (IS_ERR(inode)) {
 			err = PTR_ERR(inode);
-			goto cleanup;
+			goto out_put_root;
 		}
 		sbi->hidden_dir = inode;
 	} else
 		hfs_find_exit(&fd);
 
-	if (sb->s_flags & MS_RDONLY)
-		goto out;
+	if (!(sb->s_flags & MS_RDONLY)) {
+		/*
+		 * H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused
+		 * all three are registered with Apple for our use
+		 */
+		vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION);
+		vhdr->modify_date = hfsp_now2mt();
+		be32_add_cpu(&vhdr->write_count, 1);
+		vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT);
+		vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT);
+		hfsplus_sync_fs(sb, 1);
 
-	/* H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused
-	 * all three are registered with Apple for our use
-	 */
-	vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION);
-	vhdr->modify_date = hfsp_now2mt();
-	be32_add_cpu(&vhdr->write_count, 1);
-	vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT);
-	vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT);
-	hfsplus_sync_fs(sb, 1);
-
-	if (!sbi->hidden_dir) {
-		mutex_lock(&sbi->vh_mutex);
-		sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
-		hfsplus_create_cat(sbi->hidden_dir->i_ino, sb->s_root->d_inode,
-				   &str, sbi->hidden_dir);
-		mutex_unlock(&sbi->vh_mutex);
-
-		hfsplus_mark_inode_dirty(sbi->hidden_dir, HFSPLUS_I_CAT_DIRTY);
+		if (!sbi->hidden_dir) {
+			mutex_lock(&sbi->vh_mutex);
+			sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
+			hfsplus_create_cat(sbi->hidden_dir->i_ino, root, &str,
+					   sbi->hidden_dir);
+			mutex_unlock(&sbi->vh_mutex);
+
+			hfsplus_mark_inode_dirty(sbi->hidden_dir,
+						 HFSPLUS_I_CAT_DIRTY);
+		}
 	}
-out:
+
+	sb->s_d_op = &hfsplus_dentry_operations;
+	sb->s_root = d_alloc_root(root);
+	if (!sb->s_root) {
+		err = -ENOMEM;
+		goto out_put_hidden_dir;
+	}
+
 	unload_nls(sbi->nls);
 	sbi->nls = nls;
 	return 0;
 
-cleanup:
-	hfsplus_put_super(sb);
+out_put_hidden_dir:
+	iput(sbi->hidden_dir);
+out_put_root:
+	iput(sbi->alloc_file);
+out_put_alloc_file:
+	iput(sbi->alloc_file);
+out_close_cat_tree:
+	hfs_btree_close(sbi->cat_tree);
+out_close_ext_tree:
+	hfs_btree_close(sbi->ext_tree);
+out_free_vhdr:
+	kfree(sbi->s_vhdr);
+	kfree(sbi->s_backup_vhdr);
+out_unload_nls:
+	unload_nls(sbi->nls);
 	unload_nls(nls);
+	kfree(sbi);
+out:
 	return err;
 }
 
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 196231794f64..3031d81f5f0f 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -167,7 +167,7 @@ reread:
 		break;
 	case cpu_to_be16(HFSP_WRAP_MAGIC):
 		if (!hfsplus_read_mdb(sbi->s_vhdr, &wd))
-			goto out;
+			goto out_free_backup_vhdr;
 		wd.ablk_size >>= HFSPLUS_SECTOR_SHIFT;
 		part_start += wd.ablk_start + wd.embed_start * wd.ablk_size;
 		part_size = wd.embed_count * wd.ablk_size;
@@ -179,7 +179,7 @@ reread:
 		 * (should do this only for cdrom/loop though)
 		 */
 		if (hfs_part_find(sb, &part_start, &part_size))
-			goto out;
+			goto out_free_backup_vhdr;
 		goto reread;
 	}
 
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 56f0da1cfd10..1ae35baa539e 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -281,7 +281,7 @@ int hpfs_setattr(struct dentry *dentry, struct iattr *attr)
 	    attr->ia_size != i_size_read(inode)) {
 		error = vmtruncate(inode, attr->ia_size);
 		if (error)
-			return error;
+			goto out_unlock;
 	}
 
 	setattr_copy(inode, attr);
diff --git a/fs/internal.h b/fs/internal.h
index 9687c2ee2735..0663568b1247 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -70,6 +70,10 @@ extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
 extern void release_mounts(struct list_head *);
 extern void umount_tree(struct vfsmount *, int, struct list_head *);
 extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
+extern int finish_automount(struct vfsmount *, struct path *);
+
+extern void mnt_make_longterm(struct vfsmount *);
+extern void mnt_make_shortterm(struct vfsmount *);
 
 extern void __init mnt_init(void);
 
diff --git a/fs/ioctl.c b/fs/ioctl.c
index d6cc16476620..1eebeb72b202 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -86,7 +86,7 @@ int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
 			    u64 phys, u64 len, u32 flags)
 {
 	struct fiemap_extent extent;
-	struct fiemap_extent *dest = fieinfo->fi_extents_start;
+	struct fiemap_extent __user *dest = fieinfo->fi_extents_start;
 
 	/* only count the extents */
 	if (fieinfo->fi_extents_max == 0) {
@@ -173,6 +173,7 @@ static int fiemap_check_ranges(struct super_block *sb,
 static int ioctl_fiemap(struct file *filp, unsigned long arg)
 {
 	struct fiemap fiemap;
+	struct fiemap __user *ufiemap = (struct fiemap __user *) arg;
 	struct fiemap_extent_info fieinfo = { 0, };
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct super_block *sb = inode->i_sb;
@@ -182,8 +183,7 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
 	if (!inode->i_op->fiemap)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
-			   sizeof(struct fiemap)))
+	if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap)))
 		return -EFAULT;
 
 	if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
@@ -196,7 +196,7 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
 
 	fieinfo.fi_flags = fiemap.fm_flags;
 	fieinfo.fi_extents_max = fiemap.fm_extent_count;
-	fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));
+	fieinfo.fi_extents_start = ufiemap->fm_extents;
 
 	if (fiemap.fm_extent_count != 0 &&
 	    !access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
@@ -209,7 +209,7 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
 	error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
 	fiemap.fm_flags = fieinfo.fi_flags;
 	fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
-	if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
+	if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap)))
 		error = -EFAULT;
 
 	return error;
@@ -273,6 +273,13 @@ int __generic_block_fiemap(struct inode *inode,
 		len = isize;
 	}
 
+	/*
+	 * Some filesystems can't deal with being asked to map less than
+	 * blocksize, so make sure our len is at least block length.
+	 */
+	if (logical_to_blk(inode, len) == 0)
+		len = blk_to_logical(inode, 1);
+
 	start_blk = logical_to_blk(inode, start);
 	last_blk = logical_to_blk(inode, start + len - 1);
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 9e4686900f18..97e73469b2c4 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -473,7 +473,8 @@ int __jbd2_log_space_left(journal_t *journal)
 }
 
 /*
- * Called under j_state_lock.  Returns true if a transaction commit was started.
+ * Called with j_state_lock locked for writing.
+ * Returns true if a transaction commit was started.
  */
 int __jbd2_log_start_commit(journal_t *journal, tid_t target)
 {
@@ -520,11 +521,13 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
 {
 	transaction_t *transaction = NULL;
 	tid_t tid;
+	int need_to_start = 0;
 
 	read_lock(&journal->j_state_lock);
 	if (journal->j_running_transaction && !current->journal_info) {
 		transaction = journal->j_running_transaction;
-		__jbd2_log_start_commit(journal, transaction->t_tid);
+		if (!tid_geq(journal->j_commit_request, transaction->t_tid))
+			need_to_start = 1;
 	} else if (journal->j_committing_transaction)
 		transaction = journal->j_committing_transaction;
 
@@ -535,6 +538,8 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
 
 	tid = transaction->t_tid;
 	read_unlock(&journal->j_state_lock);
+	if (need_to_start)
+		jbd2_log_start_commit(journal, tid);
 	jbd2_log_wait_commit(journal, tid);
 	return 1;
 }
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index faad2bd787c7..1d1191050f99 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -117,10 +117,10 @@ static inline void update_t_max_wait(transaction_t *transaction)
 static int start_this_handle(journal_t *journal, handle_t *handle,
 			     int gfp_mask)
 {
-	transaction_t *transaction;
-	int needed;
-	int nblocks = handle->h_buffer_credits;
-	transaction_t *new_transaction = NULL;
+	transaction_t	*transaction, *new_transaction = NULL;
+	tid_t		tid;
+	int		needed, need_to_start;
+	int		nblocks = handle->h_buffer_credits;
 
 	if (nblocks > journal->j_max_transaction_buffers) {
 		printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
@@ -222,8 +222,11 @@ repeat:
 		atomic_sub(nblocks, &transaction->t_outstanding_credits);
 		prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
 				TASK_UNINTERRUPTIBLE);
-		__jbd2_log_start_commit(journal, transaction->t_tid);
+		tid = transaction->t_tid;
+		need_to_start = !tid_geq(journal->j_commit_request, tid);
 		read_unlock(&journal->j_state_lock);
+		if (need_to_start)
+			jbd2_log_start_commit(journal, tid);
 		schedule();
 		finish_wait(&journal->j_wait_transaction_locked, &wait);
 		goto repeat;
@@ -442,7 +445,8 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
 {
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal = transaction->t_journal;
-	int ret;
+	tid_t		tid;
+	int		need_to_start, ret;
 
 	/* If we've had an abort of any type, don't even think about
 	 * actually doing the restart! */
@@ -465,8 +469,11 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
 	spin_unlock(&transaction->t_handle_lock);
 
 	jbd_debug(2, "restarting handle %p\n", handle);
-	__jbd2_log_start_commit(journal, transaction->t_tid);
+	tid = transaction->t_tid;
+	need_to_start = !tid_geq(journal->j_commit_request, tid);
 	read_unlock(&journal->j_state_lock);
+	if (need_to_start)
+		jbd2_log_start_commit(journal, tid);
 
 	lock_map_release(&handle->h_lockdep_map);
 	handle->h_buffer_credits = nblocks;
diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c
index 85c6be2db02f..3005ec4520ad 100644
--- a/fs/jffs2/build.c
+++ b/fs/jffs2/build.c
@@ -336,14 +336,13 @@ int jffs2_do_mount_fs(struct jffs2_sb_info *c)
 	size = sizeof(struct jffs2_eraseblock) * c->nr_blocks;
 #ifndef __ECOS
 	if (jffs2_blocks_use_vmalloc(c))
-		c->blocks = vmalloc(size);
+		c->blocks = vzalloc(size);
 	else
 #endif
-		c->blocks = kmalloc(size, GFP_KERNEL);
+		c->blocks = kzalloc(size, GFP_KERNEL);
 	if (!c->blocks)
 		return -ENOMEM;
 
-	memset(c->blocks, 0, size);
 	for (i=0; i<c->nr_blocks; i++) {
 		INIT_LIST_HEAD(&c->blocks[i].list);
 		c->blocks[i].offset = i * c->sector_size;
diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h
index f864005de64c..0bc6a6c80a56 100644
--- a/fs/jffs2/jffs2_fs_sb.h
+++ b/fs/jffs2/jffs2_fs_sb.h
@@ -144,4 +144,4 @@ struct jffs2_sb_info {
 	void *os_priv;
 };
 
-#endif /* _JFFS2_FB_SB */
+#endif /* _JFFS2_FS_SB */
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index 9b572ca40a49..4f9cc0482949 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -151,7 +151,7 @@ static int do_verify_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_dat
 		JFFS2_ERROR("node CRC failed at %#08x, read=%#08x, calc=%#08x\n",
 			    offset, je32_to_cpu(rx.hdr_crc), crc);
 		xd->flags |= JFFS2_XFLAGS_INVALID;
-		return EIO;
+		return -EIO;
 	}
 	totlen = PAD(sizeof(rx) + rx.name_len + 1 + je16_to_cpu(rx.value_len));
 	if (je16_to_cpu(rx.magic) != JFFS2_MAGIC_BITMASK
@@ -167,7 +167,7 @@ static int do_verify_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_dat
 			    je32_to_cpu(rx.xid), xd->xid,
 			    je32_to_cpu(rx.version), xd->version);
 		xd->flags |= JFFS2_XFLAGS_INVALID;
-		return EIO;
+		return -EIO;
 	}
 	xd->xprefix = rx.xprefix;
 	xd->name_len = rx.name_len;
@@ -230,7 +230,7 @@ static int do_load_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum
 			      ref_offset(xd->node), xd->data_crc, crc);
 		kfree(data);
 		xd->flags |= JFFS2_XFLAGS_INVALID;
-		return EIO;
+		return -EIO;
 	}
 
 	xd->flags |= JFFS2_XFLAGS_HOT;
@@ -268,7 +268,7 @@ static int load_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *x
 	if (xd->xname)
 		return 0;
 	if (xd->flags & JFFS2_XFLAGS_INVALID)
-		return EIO;
+		return -EIO;
 	if (unlikely(is_xattr_datum_unchecked(c, xd)))
 		rc = do_verify_xattr_datum(c, xd);
 	if (!rc)
@@ -460,7 +460,7 @@ static int verify_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref
 	if (crc != je32_to_cpu(rr.node_crc)) {
 		JFFS2_ERROR("node CRC failed at %#08x, read=%#08x, calc=%#08x\n",
 			    offset, je32_to_cpu(rr.node_crc), crc);
-		return EIO;
+		return -EIO;
 	}
 	if (je16_to_cpu(rr.magic) != JFFS2_MAGIC_BITMASK
 	    || je16_to_cpu(rr.nodetype) != JFFS2_NODETYPE_XREF
@@ -470,7 +470,7 @@ static int verify_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref
 			    offset, je16_to_cpu(rr.magic), JFFS2_MAGIC_BITMASK,
 			    je16_to_cpu(rr.nodetype), JFFS2_NODETYPE_XREF,
 			    je32_to_cpu(rr.totlen), PAD(sizeof(rr)));
-		return EIO;
+		return -EIO;
 	}
 	ref->ino = je32_to_cpu(rr.ino);
 	ref->xid = je32_to_cpu(rr.xid);
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 5f1bcb2f06f3..b7c99bfb3da6 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -520,7 +520,7 @@ static struct nlm_host *next_host_state(struct hlist_head *cache,
 					struct nsm_handle *nsm,
 					const struct nlm_reboot *info)
 {
-	struct nlm_host *host = NULL;
+	struct nlm_host *host;
 	struct hlist_head *chain;
 	struct hlist_node *pos;
 
@@ -532,12 +532,13 @@ static struct nlm_host *next_host_state(struct hlist_head *cache,
 			host->h_state++;
 
 			nlm_get_host(host);
-			goto out;
+			mutex_unlock(&nlm_host_mutex);
+			return host;
 		}
 	}
-out:
+
 	mutex_unlock(&nlm_host_mutex);
-	return host;
+	return NULL;
 }
 
 /**
diff --git a/fs/locks.c b/fs/locks.c
index 08415b2a6d36..0f3998291f78 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -444,15 +444,9 @@ static void lease_release_private_callback(struct file_lock *fl)
 	fl->fl_file->f_owner.signum = 0;
 }
 
-static int lease_mylease_callback(struct file_lock *fl, struct file_lock *try)
-{
-	return fl->fl_file == try->fl_file;
-}
-
 static const struct lock_manager_operations lease_manager_ops = {
 	.fl_break = lease_break_callback,
 	.fl_release_private = lease_release_private_callback,
-	.fl_mylease = lease_mylease_callback,
 	.fl_change = lease_modify,
 };
 
@@ -1405,7 +1399,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 	for (before = &inode->i_flock;
 			((fl = *before) != NULL) && IS_LEASE(fl);
 			before = &fl->fl_next) {
-		if (lease->fl_lmops->fl_mylease(fl, lease))
+		if (fl->fl_file == filp)
 			my_before = before;
 		else if (fl->fl_type == (F_INPROGRESS | F_UNLCK))
 			/*
diff --git a/fs/mpage.c b/fs/mpage.c
index fd56ca2ea556..d78455a81ec9 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -40,7 +40,7 @@
  * status of that page is hard.  See end_buffer_async_read() for the details.
  * There is no point in duplicating all that complexity.
  */
-static void mpage_end_io_read(struct bio *bio, int err)
+static void mpage_end_io(struct bio *bio, int err)
 {
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
@@ -50,44 +50,29 @@ static void mpage_end_io_read(struct bio *bio, int err)
 
 		if (--bvec >= bio->bi_io_vec)
 			prefetchw(&bvec->bv_page->flags);
-
-		if (uptodate) {
-			SetPageUptodate(page);
-		} else {
-			ClearPageUptodate(page);
-			SetPageError(page);
-		}
-		unlock_page(page);
-	} while (bvec >= bio->bi_io_vec);
-	bio_put(bio);
-}
-
-static void mpage_end_io_write(struct bio *bio, int err)
-{
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-
-	do {
-		struct page *page = bvec->bv_page;
-
-		if (--bvec >= bio->bi_io_vec)
-			prefetchw(&bvec->bv_page->flags);
-
-		if (!uptodate){
-			SetPageError(page);
-			if (page->mapping)
-				set_bit(AS_EIO, &page->mapping->flags);
+		if (bio_data_dir(bio) == READ) {
+			if (uptodate) {
+				SetPageUptodate(page);
+			} else {
+				ClearPageUptodate(page);
+				SetPageError(page);
+			}
+			unlock_page(page);
+		} else { /* bio_data_dir(bio) == WRITE */
+			if (!uptodate) {
+				SetPageError(page);
+				if (page->mapping)
+					set_bit(AS_EIO, &page->mapping->flags);
+			}
+			end_page_writeback(page);
 		}
-		end_page_writeback(page);
 	} while (bvec >= bio->bi_io_vec);
 	bio_put(bio);
 }
 
 static struct bio *mpage_bio_submit(int rw, struct bio *bio)
 {
-	bio->bi_end_io = mpage_end_io_read;
-	if (rw == WRITE)
-		bio->bi_end_io = mpage_end_io_write;
+	bio->bi_end_io = mpage_end_io;
 	submit_bio(rw, bio);
 	return NULL;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 0b14f6910fc6..ec4b2d0190a8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -368,18 +368,6 @@ void path_get(struct path *path)
 EXPORT_SYMBOL(path_get);
 
 /**
- * path_get_long - get a long reference to a path
- * @path: path to get the reference to
- *
- * Given a path increment the reference count to the dentry and the vfsmount.
- */
-void path_get_long(struct path *path)
-{
-	mntget_long(path->mnt);
-	dget(path->dentry);
-}
-
-/**
  * path_put - put a reference to a path
  * @path: path to put the reference to
  *
@@ -393,18 +381,6 @@ void path_put(struct path *path)
 EXPORT_SYMBOL(path_put);
 
 /**
- * path_put_long - put a long reference to a path
- * @path: path to put the reference to
- *
- * Given a path decrement the reference count to the dentry and the vfsmount.
- */
-void path_put_long(struct path *path)
-{
-	dput(path->dentry);
-	mntput_long(path->mnt);
-}
-
-/**
  * nameidata_drop_rcu - drop this nameidata out of rcu-walk
  * @nd: nameidata pathwalk data to drop
  * Returns: 0 on success, -ECHILD on failure
@@ -479,6 +455,14 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry
 	struct fs_struct *fs = current->fs;
 	struct dentry *parent = nd->path.dentry;
 
+	/*
+	 * It can be possible to revalidate the dentry that we started
+	 * the path walk with. force_reval_path may also revalidate the
+	 * dentry already committed to the nameidata.
+	 */
+	if (unlikely(parent == dentry))
+		return nameidata_drop_rcu(nd);
+
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 	if (nd->root.mnt) {
 		spin_lock(&fs->lock);
@@ -577,12 +561,23 @@ static inline int nameidata_drop_rcu_last_maybe(struct nameidata *nd)
  */
 void release_open_intent(struct nameidata *nd)
 {
-	if (nd->intent.open.file->f_path.dentry == NULL)
-		put_filp(nd->intent.open.file);
-	else
-		fput(nd->intent.open.file);
+	struct file *file = nd->intent.open.file;
+
+	if (file && !IS_ERR(file)) {
+		if (file->f_path.dentry == NULL)
+			put_filp(file);
+		else
+			fput(file);
+	}
 }
 
+/*
+ * Call d_revalidate and handle filesystems that request rcu-walk
+ * to be dropped. This may be called and return in rcu-walk mode,
+ * regardless of success or error. If -ECHILD is returned, the caller
+ * must return -ECHILD back up the path walk stack so path walk may
+ * be restarted in ref-walk mode.
+ */
 static int d_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
 	int status;
@@ -673,6 +668,9 @@ force_reval_path(struct path *path, struct nameidata *nd)
 		return 0;
 
 	if (!status) {
+		/* Don't d_invalidate in rcu-walk mode */
+		if (nameidata_drop_rcu(nd))
+			return -ECHILD;
 		d_invalidate(dentry);
 		status = -ESTALE;
 	}
@@ -761,7 +759,8 @@ static void path_put_conditional(struct path *path, struct nameidata *nd)
 		mntput(path->mnt);
 }
 
-static inline void path_to_nameidata(struct path *path, struct nameidata *nd)
+static inline void path_to_nameidata(const struct path *path,
+					struct nameidata *nd)
 {
 	if (!(nd->flags & LOOKUP_RCU)) {
 		dput(nd->path.dentry);
@@ -773,20 +772,16 @@ static inline void path_to_nameidata(struct path *path, struct nameidata *nd)
 }
 
 static __always_inline int
-__do_follow_link(struct path *path, struct nameidata *nd, void **p)
+__do_follow_link(const struct path *link, struct nameidata *nd, void **p)
 {
 	int error;
-	struct dentry *dentry = path->dentry;
+	struct dentry *dentry = link->dentry;
 
-	touch_atime(path->mnt, dentry);
+	touch_atime(link->mnt, dentry);
 	nd_set_link(nd, NULL);
 
-	if (path->mnt != nd->path.mnt) {
-		path_to_nameidata(path, nd);
-		nd->inode = nd->path.dentry->d_inode;
-		dget(dentry);
-	}
-	mntget(path->mnt);
+	if (link->mnt == nd->path.mnt)
+		mntget(link->mnt);
 
 	nd->last_type = LAST_BIND;
 	*p = dentry->d_inode->i_op->follow_link(dentry, nd);
@@ -877,54 +872,148 @@ int follow_up(struct path *path)
 }
 
 /*
- * serialization is taken care of in namespace.c
+ * Perform an automount
+ * - return -EISDIR to tell follow_managed() to stop and return the path we
+ *   were called with.
  */
-static void __follow_mount_rcu(struct nameidata *nd, struct path *path,
-				struct inode **inode)
+static int follow_automount(struct path *path, unsigned flags,
+			    bool *need_mntput)
 {
-	while (d_mountpoint(path->dentry)) {
-		struct vfsmount *mounted;
-		mounted = __lookup_mnt(path->mnt, path->dentry, 1);
-		if (!mounted)
-			return;
-		path->mnt = mounted;
-		path->dentry = mounted->mnt_root;
-		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
-		*inode = path->dentry->d_inode;
+	struct vfsmount *mnt;
+	int err;
+
+	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.
+	 */
+	if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_CONTINUE))
+		return -EISDIR; /* we actually want to stop here */
+
+	/* We want to mount if someone is trying to open/create a file of any
+	 * type under the mountpoint, wants to traverse through the mountpoint
+	 * or wants to open the mounted directory.
+	 *
+	 * 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) &&
+	    !(flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY |
+		       LOOKUP_OPEN | LOOKUP_CREATE)))
+		return -EISDIR;
+
+	current->total_link_count++;
+	if (current->total_link_count >= 40)
+		return -ELOOP;
+
+	mnt = path->dentry->d_op->d_automount(path);
+	if (IS_ERR(mnt)) {
+		/*
+		 * The filesystem is allowed to return -EISDIR here to indicate
+		 * it doesn't want to automount.  For instance, autofs would do
+		 * this so that its userspace daemon can mount on this dentry.
+		 *
+		 * However, we can only permit this if it's a terminal point in
+		 * the path being looked up; if it wasn't then the remainder of
+		 * the path is inaccessible and we should say so.
+		 */
+		if (PTR_ERR(mnt) == -EISDIR && (flags & LOOKUP_CONTINUE))
+			return -EREMOTE;
+		return PTR_ERR(mnt);
 	}
-}
 
-static int __follow_mount(struct path *path)
-{
-	int res = 0;
-	while (d_mountpoint(path->dentry)) {
-		struct vfsmount *mounted = lookup_mnt(path);
-		if (!mounted)
-			break;
+	if (!mnt) /* mount collision */
+		return 0;
+
+	err = finish_automount(mnt, path);
+
+	switch (err) {
+	case -EBUSY:
+		/* Someone else made a mount here whilst we were busy */
+		return 0;
+	case 0:
 		dput(path->dentry);
-		if (res)
+		if (*need_mntput)
 			mntput(path->mnt);
-		path->mnt = mounted;
-		path->dentry = dget(mounted->mnt_root);
-		res = 1;
+		path->mnt = mnt;
+		path->dentry = dget(mnt->mnt_root);
+		*need_mntput = true;
+		return 0;
+	default:
+		return err;
 	}
-	return res;
+
 }
 
-static void follow_mount(struct path *path)
+/*
+ * Handle a dentry that is managed in some way.
+ * - Flagged for transit management (autofs)
+ * - Flagged as mountpoint
+ * - Flagged as automount point
+ *
+ * This may only be called in refwalk mode.
+ *
+ * Serialization is taken care of in namespace.c
+ */
+static int follow_managed(struct path *path, unsigned flags)
 {
-	while (d_mountpoint(path->dentry)) {
-		struct vfsmount *mounted = lookup_mnt(path);
-		if (!mounted)
-			break;
-		dput(path->dentry);
-		mntput(path->mnt);
-		path->mnt = mounted;
-		path->dentry = dget(mounted->mnt_root);
+	unsigned managed;
+	bool need_mntput = false;
+	int ret;
+
+	/* Given that we're not holding a lock here, we retain the value in a
+	 * local variable for each dentry as we look at it so that we don't see
+	 * the components of that value change under us */
+	while (managed = ACCESS_ONCE(path->dentry->d_flags),
+	       managed &= DCACHE_MANAGED_DENTRY,
+	       unlikely(managed != 0)) {
+		/* Allow the filesystem to manage the transit without i_mutex
+		 * being held. */
+		if (managed & DCACHE_MANAGE_TRANSIT) {
+			BUG_ON(!path->dentry->d_op);
+			BUG_ON(!path->dentry->d_op->d_manage);
+			ret = path->dentry->d_op->d_manage(path->dentry,
+							   false, false);
+			if (ret < 0)
+				return ret == -EISDIR ? 0 : ret;
+		}
+
+		/* Transit to a mounted filesystem. */
+		if (managed & DCACHE_MOUNTED) {
+			struct vfsmount *mounted = lookup_mnt(path);
+			if (mounted) {
+				dput(path->dentry);
+				if (need_mntput)
+					mntput(path->mnt);
+				path->mnt = mounted;
+				path->dentry = dget(mounted->mnt_root);
+				need_mntput = true;
+				continue;
+			}
+
+			/* Something is mounted on this dentry in another
+			 * namespace and/or whatever was mounted there in this
+			 * namespace got unmounted before we managed to get the
+			 * vfsmount_lock */
+		}
+
+		/* Handle an automount point */
+		if (managed & DCACHE_NEED_AUTOMOUNT) {
+			ret = follow_automount(path, flags, &need_mntput);
+			if (ret < 0)
+				return ret == -EISDIR ? 0 : ret;
+			continue;
+		}
+
+		/* We didn't change the current path point */
+		break;
 	}
+	return 0;
 }
 
-int follow_down(struct path *path)
+int follow_down_one(struct path *path)
 {
 	struct vfsmount *mounted;
 
@@ -939,13 +1028,41 @@ int follow_down(struct path *path)
 	return 0;
 }
 
+/*
+ * Skip to top of mountpoint pile in rcuwalk mode.  We abort the rcu-walk if we
+ * meet a managed dentry and we're not walking to "..".  True is returned to
+ * continue, false to abort.
+ */
+static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
+			       struct inode **inode, bool reverse_transit)
+{
+	while (d_mountpoint(path->dentry)) {
+		struct vfsmount *mounted;
+		if (unlikely(path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) &&
+		    !reverse_transit &&
+		    path->dentry->d_op->d_manage(path->dentry, false, true) < 0)
+			return false;
+		mounted = __lookup_mnt(path->mnt, path->dentry, 1);
+		if (!mounted)
+			break;
+		path->mnt = mounted;
+		path->dentry = mounted->mnt_root;
+		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
+		*inode = path->dentry->d_inode;
+	}
+
+	if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
+		return reverse_transit;
+	return true;
+}
+
 static int follow_dotdot_rcu(struct nameidata *nd)
 {
 	struct inode *inode = nd->inode;
 
 	set_root_rcu(nd);
 
-	while(1) {
+	while (1) {
 		if (nd->path.dentry == nd->root.dentry &&
 		    nd->path.mnt == nd->root.mnt) {
 			break;
@@ -968,12 +1085,80 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 		inode = nd->path.dentry->d_inode;
 	}
-	__follow_mount_rcu(nd, &nd->path, &inode);
+	__follow_mount_rcu(nd, &nd->path, &inode, true);
 	nd->inode = inode;
 
 	return 0;
 }
 
+/*
+ * Follow down to the covering mount currently visible to userspace.  At each
+ * point, the filesystem owning that dentry may be queried as to whether the
+ * caller is permitted to proceed or not.
+ *
+ * Care must be taken as namespace_sem may be held (indicated by mounting_here
+ * being true).
+ */
+int follow_down(struct path *path, bool mounting_here)
+{
+	unsigned managed;
+	int ret;
+
+	while (managed = ACCESS_ONCE(path->dentry->d_flags),
+	       unlikely(managed & DCACHE_MANAGED_DENTRY)) {
+		/* Allow the filesystem to manage the transit without i_mutex
+		 * being held.
+		 *
+		 * We indicate to the filesystem if someone is trying to mount
+		 * something here.  This gives autofs the chance to deny anyone
+		 * other than its daemon the right to mount on its
+		 * superstructure.
+		 *
+		 * The filesystem may sleep at this point.
+		 */
+		if (managed & DCACHE_MANAGE_TRANSIT) {
+			BUG_ON(!path->dentry->d_op);
+			BUG_ON(!path->dentry->d_op->d_manage);
+			ret = path->dentry->d_op->d_manage(
+				path->dentry, mounting_here, false);
+			if (ret < 0)
+				return ret == -EISDIR ? 0 : ret;
+		}
+
+		/* Transit to a mounted filesystem. */
+		if (managed & DCACHE_MOUNTED) {
+			struct vfsmount *mounted = lookup_mnt(path);
+			if (!mounted)
+				break;
+			dput(path->dentry);
+			mntput(path->mnt);
+			path->mnt = mounted;
+			path->dentry = dget(mounted->mnt_root);
+			continue;
+		}
+
+		/* Don't handle automount points here */
+		break;
+	}
+	return 0;
+}
+
+/*
+ * Skip to top of mountpoint pile in refwalk mode for follow_dotdot()
+ */
+static void follow_mount(struct path *path)
+{
+	while (d_mountpoint(path->dentry)) {
+		struct vfsmount *mounted = lookup_mnt(path);
+		if (!mounted)
+			break;
+		dput(path->dentry);
+		mntput(path->mnt);
+		path->mnt = mounted;
+		path->dentry = dget(mounted->mnt_root);
+	}
+}
+
 static void follow_dotdot(struct nameidata *nd)
 {
 	set_root(nd);
@@ -1038,12 +1223,14 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 	struct vfsmount *mnt = nd->path.mnt;
 	struct dentry *dentry, *parent = nd->path.dentry;
 	struct inode *dir;
+	int err;
+
 	/*
 	 * See if the low-level filesystem might want
 	 * to use its own hash..
 	 */
 	if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
-		int err = parent->d_op->d_hash(parent, nd->inode, name);
+		err = parent->d_op->d_hash(parent, nd->inode, name);
 		if (err < 0)
 			return err;
 	}
@@ -1070,22 +1257,30 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
 		nd->seq = seq;
 		if (dentry->d_flags & DCACHE_OP_REVALIDATE)
 			goto need_revalidate;
+done2:
 		path->mnt = mnt;
 		path->dentry = dentry;
-		__follow_mount_rcu(nd, path, inode);
-	} else {
-		dentry = __d_lookup(parent, name);
-		if (!dentry)
-			goto need_lookup;
+		if (likely(__follow_mount_rcu(nd, path, inode, false)))
+			return 0;
+		if (nameidata_drop_rcu(nd))
+			return -ECHILD;
+		/* fallthru */
+	}
+	dentry = __d_lookup(parent, name);
+	if (!dentry)
+		goto need_lookup;
 found:
-		if (dentry->d_flags & DCACHE_OP_REVALIDATE)
-			goto need_revalidate;
+	if (dentry->d_flags & DCACHE_OP_REVALIDATE)
+		goto need_revalidate;
 done:
-		path->mnt = mnt;
-		path->dentry = dentry;
-		__follow_mount(path);
-		*inode = path->dentry->d_inode;
-	}
+	path->mnt = mnt;
+	path->dentry = dentry;
+	err = follow_managed(path, nd->flags);
+	if (unlikely(err < 0)) {
+		path_put_conditional(path, nd);
+		return err;
+	}
+	*inode = path->dentry->d_inode;
 	return 0;
 
 need_lookup:
@@ -1124,6 +1319,8 @@ need_revalidate:
 		goto need_lookup;
 	if (IS_ERR(dentry))
 		goto fail;
+	if (nd->flags & LOOKUP_RCU)
+		goto done2;
 	goto done;
 
 fail:
@@ -1131,17 +1328,6 @@ fail:
 }
 
 /*
- * This is a temporary kludge to deal with "automount" symlinks; proper
- * solution is to trigger them on follow_mount(), so that do_lookup()
- * would DTRT.  To be killed before 2.6.34-final.
- */
-static inline int follow_on_final(struct inode *inode, unsigned lookup_flags)
-{
-	return inode && unlikely(inode->i_op->follow_link) &&
-		((lookup_flags & LOOKUP_FOLLOW) || S_ISDIR(inode->i_mode));
-}
-
-/*
  * Name resolution.
  * This is the basic name resolution function, turning a pathname into
  * the final dentry. We expect 'base' to be positive and a directory.
@@ -1279,7 +1465,8 @@ last_component:
 		err = do_lookup(nd, &this, &next, &inode);
 		if (err)
 			break;
-		if (follow_on_final(inode, lookup_flags)) {
+		if (inode && unlikely(inode->i_op->follow_link) &&
+		    (lookup_flags & LOOKUP_FOLLOW)) {
 			if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry))
 				return -ECHILD;
 			BUG_ON(inode != next.dentry->d_inode);
@@ -2082,8 +2269,6 @@ static struct file *finish_open(struct nameidata *nd,
 	return filp;
 
 exit:
-	if (!IS_ERR(nd->intent.open.file))
-		release_open_intent(nd);
 	path_put(&nd->path);
 	return ERR_PTR(error);
 }
@@ -2105,11 +2290,13 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 		dir = nd->path.dentry;
 	case LAST_DOT:
 		if (need_reval_dot(dir)) {
-			error = d_revalidate(nd->path.dentry, nd);
-			if (!error)
-				error = -ESTALE;
-			if (error < 0)
+			int status = d_revalidate(nd->path.dentry, nd);
+			if (!status)
+				status = -ESTALE;
+			if (status < 0) {
+				error = status;
 				goto exit;
+			}
 		}
 		/* fallthrough */
 	case LAST_ROOT:
@@ -2179,11 +2366,9 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (open_flag & O_EXCL)
 		goto exit_dput;
 
-	if (__follow_mount(path)) {
-		error = -ELOOP;
-		if (open_flag & O_NOFOLLOW)
-			goto exit_dput;
-	}
+	error = follow_managed(path, nd->flags);
+	if (error < 0)
+		goto exit_dput;
 
 	error = -ENOENT;
 	if (!path->dentry->d_inode)
@@ -2206,8 +2391,6 @@ exit_mutex_unlock:
 exit_dput:
 	path_put_conditional(path, nd);
 exit:
-	if (!IS_ERR(nd->intent.open.file))
-		release_open_intent(nd);
 	path_put(&nd->path);
 	return ERR_PTR(error);
 }
@@ -2294,6 +2477,7 @@ struct file *do_filp_open(int dfd, const char *pathname,
 	}
 	audit_inode(pathname, nd.path.dentry);
 	filp = finish_open(&nd, open_flag, acc_mode);
+	release_open_intent(&nd);
 	return filp;
 
 creat:
@@ -2328,11 +2512,11 @@ reval:
 	nd.flags = flags;
 	filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
 	while (unlikely(!filp)) { /* trailing symlink */
-		struct path holder;
+		struct path link = path;
+		struct inode *linki = link.dentry->d_inode;
 		void *cookie;
 		error = -ELOOP;
-		/* S_ISDIR part is a temporary automount kludge */
-		if (!(nd.flags & LOOKUP_FOLLOW) && !S_ISDIR(nd.inode->i_mode))
+		if (!(nd.flags & LOOKUP_FOLLOW))
 			goto exit_dput;
 		if (count++ == 32)
 			goto exit_dput;
@@ -2348,29 +2532,29 @@ reval:
 		 * just set LAST_BIND.
 		 */
 		nd.flags |= LOOKUP_PARENT;
-		error = security_inode_follow_link(path.dentry, &nd);
+		error = security_inode_follow_link(link.dentry, &nd);
 		if (error)
 			goto exit_dput;
-		error = __do_follow_link(&path, &nd, &cookie);
+		error = __do_follow_link(&link, &nd, &cookie);
 		if (unlikely(error)) {
-			if (!IS_ERR(cookie) && nd.inode->i_op->put_link)
-				nd.inode->i_op->put_link(path.dentry, &nd, cookie);
+			if (!IS_ERR(cookie) && linki->i_op->put_link)
+				linki->i_op->put_link(link.dentry, &nd, cookie);
 			/* nd.path had been dropped */
-			nd.path = path;
+			nd.path = link;
 			goto out_path;
 		}
-		holder = path;
 		nd.flags &= ~LOOKUP_PARENT;
 		filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
-		if (nd.inode->i_op->put_link)
-			nd.inode->i_op->put_link(holder.dentry, &nd, cookie);
-		path_put(&holder);
+		if (linki->i_op->put_link)
+			linki->i_op->put_link(link.dentry, &nd, cookie);
+		path_put(&link);
 	}
 out:
 	if (nd.root.mnt)
 		path_put(&nd.root);
 	if (filp == ERR_PTR(-ESTALE) && !(flags & LOOKUP_REVAL))
 		goto reval;
+	release_open_intent(&nd);
 	return filp;
 
 exit_dput:
@@ -2378,8 +2562,6 @@ exit_dput:
 out_path:
 	path_put(&nd.path);
 out_filp:
-	if (!IS_ERR(nd.intent.open.file))
-		release_open_intent(&nd);
 	filp = ERR_PTR(error);
 	goto out;
 }
@@ -3392,6 +3574,7 @@ const struct inode_operations page_symlink_inode_operations = {
 };
 
 EXPORT_SYMBOL(user_path_at);
+EXPORT_SYMBOL(follow_down_one);
 EXPORT_SYMBOL(follow_down);
 EXPORT_SYMBOL(follow_up);
 EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
diff --git a/fs/namespace.c b/fs/namespace.c
index 3ddfd9046c44..7b0b95371696 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -183,7 +183,7 @@ static inline void mnt_dec_count(struct vfsmount *mnt)
 unsigned int mnt_get_count(struct vfsmount *mnt)
 {
 #ifdef CONFIG_SMP
-	unsigned int count = atomic_read(&mnt->mnt_longrefs);
+	unsigned int count = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
@@ -217,7 +217,7 @@ struct vfsmount *alloc_vfsmnt(const char *name)
 		if (!mnt->mnt_pcp)
 			goto out_free_devname;
 
-		atomic_set(&mnt->mnt_longrefs, 1);
+		this_cpu_add(mnt->mnt_pcp->mnt_count, 1);
 #else
 		mnt->mnt_count = 1;
 		mnt->mnt_writers = 0;
@@ -611,6 +611,21 @@ static void attach_mnt(struct vfsmount *mnt, struct path *path)
 	list_add_tail(&mnt->mnt_child, &path->mnt->mnt_mounts);
 }
 
+static inline void __mnt_make_longterm(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+	atomic_inc(&mnt->mnt_longterm);
+#endif
+}
+
+/* needs vfsmount lock for write */
+static inline void __mnt_make_shortterm(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+	atomic_dec(&mnt->mnt_longterm);
+#endif
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -624,8 +639,11 @@ static void commit_tree(struct vfsmount *mnt)
 	BUG_ON(parent == mnt);
 
 	list_add_tail(&head, &mnt->mnt_list);
-	list_for_each_entry(m, &head, mnt_list)
+	list_for_each_entry(m, &head, mnt_list) {
 		m->mnt_ns = n;
+		__mnt_make_longterm(m);
+	}
+
 	list_splice(&head, n->list.prev);
 
 	list_add_tail(&mnt->mnt_hash, mount_hashtable +
@@ -734,51 +752,30 @@ static inline void mntfree(struct vfsmount *mnt)
 	deactivate_super(sb);
 }
 
-#ifdef CONFIG_SMP
-static inline void __mntput(struct vfsmount *mnt, int longrefs)
+static void mntput_no_expire(struct vfsmount *mnt)
 {
-	if (!longrefs) {
 put_again:
-		br_read_lock(vfsmount_lock);
-		if (likely(atomic_read(&mnt->mnt_longrefs))) {
-			mnt_dec_count(mnt);
-			br_read_unlock(vfsmount_lock);
-			return;
-		}
+#ifdef CONFIG_SMP
+	br_read_lock(vfsmount_lock);
+	if (likely(atomic_read(&mnt->mnt_longterm))) {
+		mnt_dec_count(mnt);
 		br_read_unlock(vfsmount_lock);
-	} else {
-		BUG_ON(!atomic_read(&mnt->mnt_longrefs));
-		if (atomic_add_unless(&mnt->mnt_longrefs, -1, 1))
-			return;
+		return;
 	}
+	br_read_unlock(vfsmount_lock);
 
 	br_write_lock(vfsmount_lock);
-	if (!longrefs)
-		mnt_dec_count(mnt);
-	else
-		atomic_dec(&mnt->mnt_longrefs);
+	mnt_dec_count(mnt);
 	if (mnt_get_count(mnt)) {
 		br_write_unlock(vfsmount_lock);
 		return;
 	}
-	if (unlikely(mnt->mnt_pinned)) {
-		mnt_add_count(mnt, mnt->mnt_pinned + 1);
-		mnt->mnt_pinned = 0;
-		br_write_unlock(vfsmount_lock);
-		acct_auto_close_mnt(mnt);
-		goto put_again;
-	}
-	br_write_unlock(vfsmount_lock);
-	mntfree(mnt);
-}
 #else
-static inline void __mntput(struct vfsmount *mnt, int longrefs)
-{
-put_again:
 	mnt_dec_count(mnt);
 	if (likely(mnt_get_count(mnt)))
 		return;
 	br_write_lock(vfsmount_lock);
+#endif
 	if (unlikely(mnt->mnt_pinned)) {
 		mnt_add_count(mnt, mnt->mnt_pinned + 1);
 		mnt->mnt_pinned = 0;
@@ -789,12 +786,6 @@ put_again:
 	br_write_unlock(vfsmount_lock);
 	mntfree(mnt);
 }
-#endif
-
-static void mntput_no_expire(struct vfsmount *mnt)
-{
-	__mntput(mnt, 0);
-}
 
 void mntput(struct vfsmount *mnt)
 {
@@ -802,7 +793,7 @@ void mntput(struct vfsmount *mnt)
 		/* avoid cacheline pingpong, hope gcc doesn't get "smart" */
 		if (unlikely(mnt->mnt_expiry_mark))
 			mnt->mnt_expiry_mark = 0;
-		__mntput(mnt, 0);
+		mntput_no_expire(mnt);
 	}
 }
 EXPORT_SYMBOL(mntput);
@@ -815,33 +806,6 @@ struct vfsmount *mntget(struct vfsmount *mnt)
 }
 EXPORT_SYMBOL(mntget);
 
-void mntput_long(struct vfsmount *mnt)
-{
-#ifdef CONFIG_SMP
-	if (mnt) {
-		/* avoid cacheline pingpong, hope gcc doesn't get "smart" */
-		if (unlikely(mnt->mnt_expiry_mark))
-			mnt->mnt_expiry_mark = 0;
-		__mntput(mnt, 1);
-	}
-#else
-	mntput(mnt);
-#endif
-}
-EXPORT_SYMBOL(mntput_long);
-
-struct vfsmount *mntget_long(struct vfsmount *mnt)
-{
-#ifdef CONFIG_SMP
-	if (mnt)
-		atomic_inc(&mnt->mnt_longrefs);
-	return mnt;
-#else
-	return mntget(mnt);
-#endif
-}
-EXPORT_SYMBOL(mntget_long);
-
 void mnt_pin(struct vfsmount *mnt)
 {
 	br_write_lock(vfsmount_lock);
@@ -1216,7 +1180,7 @@ void release_mounts(struct list_head *head)
 			dput(dentry);
 			mntput(m);
 		}
-		mntput_long(mnt);
+		mntput(mnt);
 	}
 }
 
@@ -1226,19 +1190,21 @@ void release_mounts(struct list_head *head)
  */
 void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
 {
+	LIST_HEAD(tmp_list);
 	struct vfsmount *p;
 
 	for (p = mnt; p; p = next_mnt(p, mnt))
-		list_move(&p->mnt_hash, kill);
+		list_move(&p->mnt_hash, &tmp_list);
 
 	if (propagate)
-		propagate_umount(kill);
+		propagate_umount(&tmp_list);
 
-	list_for_each_entry(p, kill, mnt_hash) {
+	list_for_each_entry(p, &tmp_list, mnt_hash) {
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
 		p->mnt_ns = NULL;
+		__mnt_make_shortterm(p);
 		list_del_init(&p->mnt_child);
 		if (p->mnt_parent != p) {
 			p->mnt_parent->mnt_ghosts++;
@@ -1246,6 +1212,7 @@ void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
 		}
 		change_mnt_propagation(p, MS_PRIVATE);
 	}
+	list_splice(&tmp_list, kill);
 }
 
 static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts);
@@ -1844,9 +1811,10 @@ static int do_move_mount(struct path *path, char *old_name)
 		return err;
 
 	down_write(&namespace_sem);
-	while (d_mountpoint(path->dentry) &&
-	       follow_down(path))
-		;
+	err = follow_down(path, true);
+	if (err < 0)
+		goto out;
+
 	err = -EINVAL;
 	if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
 		goto out;
@@ -1904,6 +1872,8 @@ out:
 	return err;
 }
 
+static int do_add_mount(struct vfsmount *, struct path *, int);
+
 /*
  * create a new mount for userspace and request it to be added into the
  * namespace's tree
@@ -1912,6 +1882,7 @@ static int do_new_mount(struct path *path, char *type, int flags,
 			int mnt_flags, char *name, void *data)
 {
 	struct vfsmount *mnt;
+	int err;
 
 	if (!type)
 		return -EINVAL;
@@ -1924,15 +1895,47 @@ static int do_new_mount(struct path *path, char *type, int flags,
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
 
-	return do_add_mount(mnt, path, mnt_flags, NULL);
+	err = do_add_mount(mnt, path, mnt_flags);
+	if (err)
+		mntput(mnt);
+	return err;
+}
+
+int finish_automount(struct vfsmount *m, struct path *path)
+{
+	int err;
+	/* The new mount record should have at least 2 refs to prevent it being
+	 * expired before we get a chance to add it
+	 */
+	BUG_ON(mnt_get_count(m) < 2);
+
+	if (m->mnt_sb == path->mnt->mnt_sb &&
+	    m->mnt_root == path->dentry) {
+		err = -ELOOP;
+		goto fail;
+	}
+
+	err = do_add_mount(m, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
+	if (!err)
+		return 0;
+fail:
+	/* remove m from any expiration list it may be on */
+	if (!list_empty(&m->mnt_expire)) {
+		down_write(&namespace_sem);
+		br_write_lock(vfsmount_lock);
+		list_del_init(&m->mnt_expire);
+		br_write_unlock(vfsmount_lock);
+		up_write(&namespace_sem);
+	}
+	mntput(m);
+	mntput(m);
+	return err;
 }
 
 /*
  * add a mount into a namespace's mount tree
- * - provide the option of adding the new mount to an expiration list
  */
-int do_add_mount(struct vfsmount *newmnt, struct path *path,
-		 int mnt_flags, struct list_head *fslist)
+static int do_add_mount(struct vfsmount *newmnt, struct path *path, int mnt_flags)
 {
 	int err;
 
@@ -1940,9 +1943,10 @@ int do_add_mount(struct vfsmount *newmnt, struct path *path,
 
 	down_write(&namespace_sem);
 	/* Something was mounted here while we slept */
-	while (d_mountpoint(path->dentry) &&
-	       follow_down(path))
-		;
+	err = follow_down(path, true);
+	if (err < 0)
+		goto unlock;
+
 	err = -EINVAL;
 	if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
 		goto unlock;
@@ -1958,22 +1962,29 @@ int do_add_mount(struct vfsmount *newmnt, struct path *path,
 		goto unlock;
 
 	newmnt->mnt_flags = mnt_flags;
-	if ((err = graft_tree(newmnt, path)))
-		goto unlock;
-
-	if (fslist) /* add to the specified expiration list */
-		list_add_tail(&newmnt->mnt_expire, fslist);
-
-	up_write(&namespace_sem);
-	return 0;
+	err = graft_tree(newmnt, path);
 
 unlock:
 	up_write(&namespace_sem);
-	mntput_long(newmnt);
 	return err;
 }
 
-EXPORT_SYMBOL_GPL(do_add_mount);
+/**
+ * mnt_set_expiry - Put a mount on an expiration list
+ * @mnt: The mount to list.
+ * @expiry_list: The list to add the mount to.
+ */
+void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list)
+{
+	down_write(&namespace_sem);
+	br_write_lock(vfsmount_lock);
+
+	list_add_tail(&mnt->mnt_expire, expiry_list);
+
+	br_write_unlock(vfsmount_lock);
+	up_write(&namespace_sem);
+}
+EXPORT_SYMBOL(mnt_set_expiry);
 
 /*
  * process a list of expirable mountpoints with the intent of discarding any
@@ -2262,6 +2273,22 @@ static struct mnt_namespace *alloc_mnt_ns(void)
 	return new_ns;
 }
 
+void mnt_make_longterm(struct vfsmount *mnt)
+{
+	__mnt_make_longterm(mnt);
+}
+
+void mnt_make_shortterm(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+	if (atomic_add_unless(&mnt->mnt_longterm, -1, 1))
+		return;
+	br_write_lock(vfsmount_lock);
+	atomic_dec(&mnt->mnt_longterm);
+	br_write_unlock(vfsmount_lock);
+#endif
+}
+
 /*
  * Allocate a new namespace structure and populate it with contents
  * copied from the namespace of the passed in task structure.
@@ -2299,14 +2326,19 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	q = new_ns->root;
 	while (p) {
 		q->mnt_ns = new_ns;
+		__mnt_make_longterm(q);
 		if (fs) {
 			if (p == fs->root.mnt) {
+				fs->root.mnt = mntget(q);
+				__mnt_make_longterm(q);
+				mnt_make_shortterm(p);
 				rootmnt = p;
-				fs->root.mnt = mntget_long(q);
 			}
 			if (p == fs->pwd.mnt) {
+				fs->pwd.mnt = mntget(q);
+				__mnt_make_longterm(q);
+				mnt_make_shortterm(p);
 				pwdmnt = p;
-				fs->pwd.mnt = mntget_long(q);
 			}
 		}
 		p = next_mnt(p, mnt_ns->root);
@@ -2315,9 +2347,9 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	up_write(&namespace_sem);
 
 	if (rootmnt)
-		mntput_long(rootmnt);
+		mntput(rootmnt);
 	if (pwdmnt)
-		mntput_long(pwdmnt);
+		mntput(pwdmnt);
 
 	return new_ns;
 }
@@ -2350,6 +2382,7 @@ struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt)
 	new_ns = alloc_mnt_ns();
 	if (!IS_ERR(new_ns)) {
 		mnt->mnt_ns = new_ns;
+		__mnt_make_longterm(mnt);
 		new_ns->root = mnt;
 		list_add(&new_ns->list, &new_ns->root->mnt_list);
 	}
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 199016528fcb..e3d294269058 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -135,33 +135,6 @@ out_err:
 
 #if defined(CONFIG_NFS_V4_1)
 /*
- *  * CB_SEQUENCE operations will fail until the callback sessionid is set.
- *   */
-int nfs4_set_callback_sessionid(struct nfs_client *clp)
-{
-	struct svc_serv *serv = clp->cl_rpcclient->cl_xprt->bc_serv;
-	struct nfs4_sessionid *bc_sid;
-
-	if (!serv->sv_bc_xprt)
-		return -EINVAL;
-
-	/* on success freed in xprt_free */
-	bc_sid = kmalloc(sizeof(struct nfs4_sessionid), GFP_KERNEL);
-	if (!bc_sid)
-		return -ENOMEM;
-	memcpy(bc_sid->data, &clp->cl_session->sess_id.data,
-		NFS4_MAX_SESSIONID_LEN);
-	spin_lock_bh(&serv->sv_cb_lock);
-	serv->sv_bc_xprt->xpt_bc_sid = bc_sid;
-	spin_unlock_bh(&serv->sv_cb_lock);
-	dprintk("%s set xpt_bc_sid=%u:%u:%u:%u for sv_bc_xprt %p\n", __func__,
-		((u32 *)bc_sid->data)[0], ((u32 *)bc_sid->data)[1],
-		((u32 *)bc_sid->data)[2], ((u32 *)bc_sid->data)[3],
-		serv->sv_bc_xprt);
-	return 0;
-}
-
-/*
  * The callback service for NFSv4.1 callbacks
  */
 static int
@@ -266,10 +239,6 @@ static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
 		struct nfs_callback_data *cb_info)
 {
 }
-int nfs4_set_callback_sessionid(struct nfs_client *clp)
-{
-	return 0;
-}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -359,78 +328,58 @@ void nfs_callback_down(int minorversion)
 	mutex_unlock(&nfs_callback_mutex);
 }
 
-static int check_gss_callback_principal(struct nfs_client *clp,
-					struct svc_rqst *rqstp)
+/* Boolean check of RPC_AUTH_GSS principal */
+int
+check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
 {
 	struct rpc_clnt *r = clp->cl_rpcclient;
 	char *p = svc_gss_principal(rqstp);
 
+	if (rqstp->rq_authop->flavour != RPC_AUTH_GSS)
+		return 1;
+
 	/* No RPC_AUTH_GSS on NFSv4.1 back channel yet */
 	if (clp->cl_minorversion != 0)
-		return SVC_DROP;
+		return 0;
 	/*
 	 * It might just be a normal user principal, in which case
 	 * userspace won't bother to tell us the name at all.
 	 */
 	if (p == NULL)
-		return SVC_DENIED;
+		return 0;
 
 	/* Expect a GSS_C_NT_HOSTBASED_NAME like "nfs@serverhostname" */
 
 	if (memcmp(p, "nfs@", 4) != 0)
-		return SVC_DENIED;
+		return 0;
 	p += 4;
 	if (strcmp(p, r->cl_server) != 0)
-		return SVC_DENIED;
-	return SVC_OK;
+		return 0;
+	return 1;
 }
 
-/* pg_authenticate method helper */
-static struct nfs_client *nfs_cb_find_client(struct svc_rqst *rqstp)
-{
-	struct nfs4_sessionid *sessionid = bc_xprt_sid(rqstp);
-	int is_cb_compound = rqstp->rq_proc == CB_COMPOUND ? 1 : 0;
-
-	dprintk("--> %s rq_proc %d\n", __func__, rqstp->rq_proc);
-	if (svc_is_backchannel(rqstp))
-		/* Sessionid (usually) set after CB_NULL ping */
-		return nfs4_find_client_sessionid(svc_addr(rqstp), sessionid,
-						  is_cb_compound);
-	else
-		/* No callback identifier in pg_authenticate */
-		return nfs4_find_client_no_ident(svc_addr(rqstp));
-}
-
-/* pg_authenticate method for nfsv4 callback threads. */
+/*
+ * pg_authenticate method for nfsv4 callback threads.
+ *
+ * The authflavor has been negotiated, so an incorrect flavor is a server
+ * bug. Drop packets with incorrect authflavor.
+ *
+ * All other checking done after NFS decoding where the nfs_client can be
+ * found in nfs4_callback_compound
+ */
 static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 {
-	struct nfs_client *clp;
-	RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
-	int ret = SVC_OK;
-
-	/* Don't talk to strangers */
-	clp = nfs_cb_find_client(rqstp);
-	if (clp == NULL)
-		return SVC_DROP;
-
-	dprintk("%s: %s NFSv4 callback!\n", __func__,
-			svc_print_addr(rqstp, buf, sizeof(buf)));
-
 	switch (rqstp->rq_authop->flavour) {
-		case RPC_AUTH_NULL:
-			if (rqstp->rq_proc != CB_NULL)
-				ret = SVC_DENIED;
-			break;
-		case RPC_AUTH_UNIX:
-			break;
-		case RPC_AUTH_GSS:
-			ret = check_gss_callback_principal(clp, rqstp);
-			break;
-		default:
-			ret = SVC_DENIED;
+	case RPC_AUTH_NULL:
+		if (rqstp->rq_proc != CB_NULL)
+			return SVC_DROP;
+		break;
+	case RPC_AUTH_GSS:
+		/* No RPC_AUTH_GSS support yet in NFSv4.1 */
+		 if (svc_is_backchannel(rqstp))
+			return SVC_DROP;
 	}
-	nfs_put_client(clp);
-	return ret;
+	return SVC_OK;
 }
 
 /*
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index d3b44f9bd747..46d93ce7311b 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -7,6 +7,7 @@
  */
 #ifndef __LINUX_FS_NFS_CALLBACK_H
 #define __LINUX_FS_NFS_CALLBACK_H
+#include <linux/sunrpc/svc.h>
 
 #define NFS4_CALLBACK 0x40000000
 #define NFS4_CALLBACK_XDRSIZE 2048
@@ -37,7 +38,6 @@ enum nfs4_callback_opnum {
 struct cb_process_state {
 	__be32			drc_status;
 	struct nfs_client	*clp;
-	struct nfs4_sessionid	*svc_sid; /* v4.1 callback service sessionid */
 };
 
 struct cb_compound_hdr_arg {
@@ -168,7 +168,7 @@ extern unsigned nfs4_callback_layoutrecall(
 extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
 extern void nfs4_cb_take_slot(struct nfs_client *clp);
 #endif /* CONFIG_NFS_V4_1 */
-
+extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *);
 extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
 				    struct cb_getattrres *res,
 				    struct cb_process_state *cps);
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 4bb91cb2620d..89587573fe50 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -373,17 +373,11 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 {
 	struct nfs_client *clp;
 	int i;
-	__be32 status;
+	__be32 status = htonl(NFS4ERR_BADSESSION);
 
 	cps->clp = NULL;
 
-	status = htonl(NFS4ERR_BADSESSION);
-	/* Incoming session must match the callback session */
-	if (memcmp(&args->csa_sessionid, cps->svc_sid, NFS4_MAX_SESSIONID_LEN))
-		goto out;
-
-	clp = nfs4_find_client_sessionid(args->csa_addr,
-					 &args->csa_sessionid, 1);
+	clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid);
 	if (clp == NULL)
 		goto out;
 
@@ -414,9 +408,9 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
 	res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
 	nfs4_cb_take_slot(clp);
-	cps->clp = clp; /* put in nfs4_callback_compound */
 
 out:
+	cps->clp = clp; /* put in nfs4_callback_compound */
 	for (i = 0; i < args->csa_nrclists; i++)
 		kfree(args->csa_rclists[i].rcl_refcalls);
 	kfree(args->csa_rclists);
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 23112c263f81..14e0f9371d14 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -794,10 +794,9 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 
 	if (hdr_arg.minorversion == 0) {
 		cps.clp = nfs4_find_client_ident(hdr_arg.cb_ident);
-		if (!cps.clp)
+		if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
 			return rpc_drop_reply;
-	} else
-		cps.svc_sid = bc_xprt_sid(rqstp);
+	}
 
 	hdr_res.taglen = hdr_arg.taglen;
 	hdr_res.tag = hdr_arg.tag;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 192f2f860265..bd3ca32879e7 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1206,16 +1206,11 @@ nfs4_find_client_ident(int cb_ident)
  * For CB_COMPOUND calls, find a client by IP address, protocol version,
  * minorversion, and sessionID
  *
- * CREATE_SESSION triggers a CB_NULL ping from servers. The callback service
- * sessionid can only be set after the CREATE_SESSION return, so a CB_NULL
- * can arrive before the callback sessionid is set. For CB_NULL calls,
- * find a client by IP address protocol version, and minorversion.
- *
  * Returns NULL if no such client
  */
 struct nfs_client *
 nfs4_find_client_sessionid(const struct sockaddr *addr,
-			   struct nfs4_sessionid *sid, int is_cb_compound)
+			   struct nfs4_sessionid *sid)
 {
 	struct nfs_client *clp;
 
@@ -1227,9 +1222,9 @@ nfs4_find_client_sessionid(const struct sockaddr *addr,
 		if (!nfs4_has_session(clp))
 			continue;
 
-		/* Match sessionid unless cb_null call*/
-		if (is_cb_compound && (memcmp(clp->cl_session->sess_id.data,
-		    sid->data, NFS4_MAX_SESSIONID_LEN) != 0))
+		/* Match sessionid*/
+		if (memcmp(clp->cl_session->sess_id.data,
+		    sid->data, NFS4_MAX_SESSIONID_LEN) != 0)
 			continue;
 
 		atomic_inc(&clp->cl_count);
@@ -1244,7 +1239,7 @@ nfs4_find_client_sessionid(const struct sockaddr *addr,
 
 struct nfs_client *
 nfs4_find_client_sessionid(const struct sockaddr *addr,
-			   struct nfs4_sessionid *sid, int is_cb_compound)
+			   struct nfs4_sessionid *sid)
 {
 	return NULL;
 }
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 364e4328f392..bbbc6bf5cb2e 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -23,8 +23,6 @@
 
 static void nfs_do_free_delegation(struct nfs_delegation *delegation)
 {
-	if (delegation->cred)
-		put_rpccred(delegation->cred);
 	kfree(delegation);
 }
 
@@ -37,6 +35,10 @@ static void nfs_free_delegation_callback(struct rcu_head *head)
 
 static void nfs_free_delegation(struct nfs_delegation *delegation)
 {
+	if (delegation->cred) {
+		put_rpccred(delegation->cred);
+		delegation->cred = NULL;
+	}
 	call_rcu(&delegation->rcu, nfs_free_delegation_callback);
 }
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 95b081bc9e25..2c3eb33b904d 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -970,7 +970,7 @@ int nfs_lookup_verify_inode(struct inode *inode, struct nameidata *nd)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 
-	if (test_bit(NFS_INO_MOUNTPOINT, &NFS_I(inode)->flags))
+	if (IS_AUTOMOUNT(inode))
 		return 0;
 	if (nd != NULL) {
 		/* VFS wants an on-the-wire revalidation */
@@ -1173,6 +1173,7 @@ const struct dentry_operations nfs_dentry_operations = {
 	.d_revalidate	= nfs_lookup_revalidate,
 	.d_delete	= nfs_dentry_delete,
 	.d_iput		= nfs_dentry_iput,
+	.d_automount	= nfs_d_automount,
 };
 
 static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
@@ -1246,6 +1247,7 @@ const struct dentry_operations nfs4_dentry_operations = {
 	.d_revalidate	= nfs_open_revalidate,
 	.d_delete	= nfs_dentry_delete,
 	.d_iput		= nfs_dentry_iput,
+	.d_automount	= nfs_d_automount,
 };
 
 /*
@@ -1406,11 +1408,15 @@ no_open:
 static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
 	struct dentry *parent = NULL;
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode;
 	struct inode *dir;
 	struct nfs_open_context *ctx;
 	int openflags, ret = 0;
 
+	if (nd->flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	inode = dentry->d_inode;
 	if (!is_atomic_open(nd) || d_mountpoint(dentry))
 		goto no_open;
 
@@ -1579,6 +1585,7 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
 {
 	struct iattr attr;
 	int error;
+	int open_flags = 0;
 
 	dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
 			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
@@ -1586,7 +1593,10 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
 	attr.ia_mode = mode;
 	attr.ia_valid = ATTR_MODE;
 
-	error = NFS_PROTO(dir)->create(dir, dentry, &attr, 0, NULL);
+	if ((nd->flags & LOOKUP_CREATE) != 0)
+		open_flags = nd->intent.open.flags;
+
+	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, NULL);
 	if (error != 0)
 		goto out_err;
 	return 0;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index e6ace0d93c71..9943a75bb6d1 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -407,15 +407,18 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 		pos += vec->iov_len;
 	}
 
+	/*
+	 * If no bytes were started, return the error, and let the
+	 * generic layer handle the completion.
+	 */
+	if (requested_bytes == 0) {
+		nfs_direct_req_release(dreq);
+		return result < 0 ? result : -EIO;
+	}
+
 	if (put_dreq(dreq))
 		nfs_direct_complete(dreq);
-
-	if (requested_bytes != 0)
-		return 0;
-
-	if (result < 0)
-		return result;
-	return -EIO;
+	return 0;
 }
 
 static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
@@ -841,15 +844,18 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 		pos += vec->iov_len;
 	}
 
+	/*
+	 * If no bytes were started, return the error, and let the
+	 * generic layer handle the completion.
+	 */
+	if (requested_bytes == 0) {
+		nfs_direct_req_release(dreq);
+		return result < 0 ? result : -EIO;
+	}
+
 	if (put_dreq(dreq))
 		nfs_direct_write_complete(dreq, dreq->inode);
-
-	if (requested_bytes != 0)
-		return 0;
-
-	if (result < 0)
-		return result;
-	return -EIO;
+	return 0;
 }
 
 static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index ce00b704452c..1cc600e77bb4 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -300,7 +300,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 				else
 					inode->i_op = &nfs_mountpoint_inode_operations;
 				inode->i_fop = NULL;
-				set_bit(NFS_INO_MOUNTPOINT, &nfsi->flags);
+				inode->i_flags |= S_AUTOMOUNT;
 			}
 		} else if (S_ISLNK(inode->i_mode))
 			inode->i_op = &nfs_symlink_inode_operations;
@@ -881,9 +881,10 @@ out:
 	return ret;
 }
 
-static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
+static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
+	unsigned long ret = 0;
 
 	if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
 			&& (fattr->valid & NFS_ATTR_FATTR_CHANGE)
@@ -891,25 +892,32 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		nfsi->change_attr = fattr->change_attr;
 		if (S_ISDIR(inode->i_mode))
 			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+		ret |= NFS_INO_INVALID_ATTR;
 	}
 	/* If we have atomic WCC data, we may update some attributes */
 	if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME)
 			&& (fattr->valid & NFS_ATTR_FATTR_CTIME)
-			&& timespec_equal(&inode->i_ctime, &fattr->pre_ctime))
-			memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
+			&& timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) {
+		memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
+		ret |= NFS_INO_INVALID_ATTR;
+	}
 
 	if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME)
 			&& (fattr->valid & NFS_ATTR_FATTR_MTIME)
 			&& timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
-			memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
-			if (S_ISDIR(inode->i_mode))
-				nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
+		if (S_ISDIR(inode->i_mode))
+			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+		ret |= NFS_INO_INVALID_ATTR;
 	}
 	if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
 			&& (fattr->valid & NFS_ATTR_FATTR_SIZE)
 			&& i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size)
-			&& nfsi->npages == 0)
-			i_size_write(inode, nfs_size_to_loff_t(fattr->size));
+			&& nfsi->npages == 0) {
+		i_size_write(inode, nfs_size_to_loff_t(fattr->size));
+		ret |= NFS_INO_INVALID_ATTR;
+	}
+	return ret;
 }
 
 /**
@@ -1208,7 +1216,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	/* Update the fsid? */
 	if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) &&
 			!nfs_fsid_equal(&server->fsid, &fattr->fsid) &&
-			!test_bit(NFS_INO_MOUNTPOINT, &nfsi->flags))
+			!IS_AUTOMOUNT(inode))
 		server->fsid = fattr->fsid;
 
 	/*
@@ -1223,7 +1231,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			| NFS_INO_REVAL_PAGECACHE);
 
 	/* Do atomic weak cache consistency updates */
-	nfs_wcc_update_inode(inode, fattr);
+	invalid |= nfs_wcc_update_inode(inode, fattr);
 
 	/* More cache consistency checks */
 	if (fattr->valid & NFS_ATTR_FATTR_CHANGE) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index bfa3a34af801..cf9fdbdabc67 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -133,8 +133,7 @@ extern void nfs_put_client(struct nfs_client *);
 extern struct nfs_client *nfs4_find_client_no_ident(const struct sockaddr *);
 extern struct nfs_client *nfs4_find_client_ident(int);
 extern struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *,
-			   int);
+nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *);
 extern struct nfs_server *nfs_create_server(
 					const struct nfs_parsed_mount_data *,
 					struct nfs_fh *);
@@ -252,6 +251,7 @@ extern char *nfs_path(const char *base,
 		      const struct dentry *droot,
 		      const struct dentry *dentry,
 		      char *buffer, ssize_t buflen);
+extern struct vfsmount *nfs_d_automount(struct path *path);
 
 /* getroot.c */
 extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *);
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 74aaf3963c10..f32b8603dca8 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -97,9 +97,8 @@ Elong:
 }
 
 /*
- * nfs_follow_mountpoint - handle crossing a mountpoint on the server
- * @dentry - dentry of mountpoint
- * @nd - nameidata info
+ * nfs_d_automount - Handle crossing a mountpoint on the server
+ * @path - The mountpoint
  *
  * When we encounter a mountpoint on the server, we want to set up
  * a mountpoint on the client too, to prevent inode numbers from
@@ -109,87 +108,65 @@ Elong:
  * situation, and that different filesystems may want to use
  * different security flavours.
  */
-static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
+struct vfsmount *nfs_d_automount(struct path *path)
 {
 	struct vfsmount *mnt;
-	struct nfs_server *server = NFS_SERVER(dentry->d_inode);
+	struct nfs_server *server = NFS_SERVER(path->dentry->d_inode);
 	struct dentry *parent;
 	struct nfs_fh *fh = NULL;
 	struct nfs_fattr *fattr = NULL;
 	int err;
 
-	dprintk("--> nfs_follow_mountpoint()\n");
+	dprintk("--> nfs_d_automount()\n");
 
-	err = -ESTALE;
-	if (IS_ROOT(dentry))
-		goto out_err;
+	mnt = ERR_PTR(-ESTALE);
+	if (IS_ROOT(path->dentry))
+		goto out_nofree;
 
-	err = -ENOMEM;
+	mnt = ERR_PTR(-ENOMEM);
 	fh = nfs_alloc_fhandle();
 	fattr = nfs_alloc_fattr();
 	if (fh == NULL || fattr == NULL)
-		goto out_err;
+		goto out;
 
 	dprintk("%s: enter\n", __func__);
-	dput(nd->path.dentry);
-	nd->path.dentry = dget(dentry);
 
-	/* Look it up again */
-	parent = dget_parent(nd->path.dentry);
+	/* Look it up again to get its attributes */
+	parent = dget_parent(path->dentry);
 	err = server->nfs_client->rpc_ops->lookup(parent->d_inode,
-						  &nd->path.dentry->d_name,
+						  &path->dentry->d_name,
 						  fh, fattr);
 	dput(parent);
-	if (err != 0)
-		goto out_err;
+	if (err != 0) {
+		mnt = ERR_PTR(err);
+		goto out;
+	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
-		mnt = nfs_do_refmount(nd->path.mnt, nd->path.dentry);
+		mnt = nfs_do_refmount(path->mnt, path->dentry);
 	else
-		mnt = nfs_do_submount(nd->path.mnt, nd->path.dentry, fh,
-				      fattr);
-	err = PTR_ERR(mnt);
+		mnt = nfs_do_submount(path->mnt, path->dentry, fh, fattr);
 	if (IS_ERR(mnt))
-		goto out_err;
+		goto out;
 
-	mntget(mnt);
-	err = do_add_mount(mnt, &nd->path, nd->path.mnt->mnt_flags|MNT_SHRINKABLE,
-			   &nfs_automount_list);
-	if (err < 0) {
-		mntput(mnt);
-		if (err == -EBUSY)
-			goto out_follow;
-		goto out_err;
-	}
-	path_put(&nd->path);
-	nd->path.mnt = mnt;
-	nd->path.dentry = dget(mnt->mnt_root);
+	dprintk("%s: done, success\n", __func__);
+	mntget(mnt); /* prevent immediate expiration */
+	mnt_set_expiry(mnt, &nfs_automount_list);
 	schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
+
 out:
 	nfs_free_fattr(fattr);
 	nfs_free_fhandle(fh);
-	dprintk("%s: done, returned %d\n", __func__, err);
-
-	dprintk("<-- nfs_follow_mountpoint() = %d\n", err);
-	return ERR_PTR(err);
-out_err:
-	path_put(&nd->path);
-	goto out;
-out_follow:
-	while (d_mountpoint(nd->path.dentry) &&
-	       follow_down(&nd->path))
-		;
-	err = 0;
-	goto out;
+out_nofree:
+	dprintk("<-- nfs_follow_mountpoint() = %p\n", mnt);
+	return mnt;
 }
 
 const struct inode_operations nfs_mountpoint_inode_operations = {
-	.follow_link	= nfs_follow_mountpoint,
 	.getattr	= nfs_getattr,
 };
 
 const struct inode_operations nfs_referral_inode_operations = {
-	.follow_link	= nfs_follow_mountpoint,
 };
 
 static void nfs_expire_automounts(struct work_struct *work)
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 9f88c5f4c7e2..274342771655 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -311,8 +311,8 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 	if (!nfs_server_capable(inode, NFS_CAP_ACLS))
 		goto out;
 
-	/* We are doing this here, because XDR marshalling can only
-	   return -ENOMEM. */
+	/* We are doing this here because XDR marshalling does not
+	 * return any results, it BUGs. */
 	status = -ENOSPC;
 	if (acl != NULL && acl->a_count > NFS_ACL_MAX_ENTRIES)
 		goto out;
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 01c5e8b1941d..183c6b123d0f 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1328,10 +1328,13 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req,
 
 	encode_nfs_fh3(xdr, NFS_FH(args->inode));
 	encode_uint32(xdr, args->mask);
+
+	base = req->rq_slen;
 	if (args->npages != 0)
 		xdr_write_pages(xdr, args->pages, 0, args->len);
+	else
+		xdr_reserve_space(xdr, NFS_ACL_INLINE_BUFSIZE);
 
-	base = req->rq_slen;
 	error = nfsacl_encode(xdr->buf, base, args->inode,
 			    (args->mask & NFS_ACL) ?
 			    args->acl_access : NULL, 1, 0);
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 51fe64ace55a..f5c9b125e8cc 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -214,7 +214,7 @@ decode_and_add_ds(__be32 **pp, struct inode *inode)
 
 	/* ipv6 length plus port is legal */
 	if (rlen > INET6_ADDRSTRLEN + 8) {
-		dprintk("%s Invalid address, length %d\n", __func__,
+		dprintk("%s: Invalid address, length %d\n", __func__,
 			rlen);
 		goto out_err;
 	}
@@ -225,6 +225,11 @@ decode_and_add_ds(__be32 **pp, struct inode *inode)
 	/* replace the port dots with dashes for the in4_pton() delimiter*/
 	for (i = 0; i < 2; i++) {
 		char *res = strrchr(buf, '.');
+		if (!res) {
+			dprintk("%s: Failed finding expected dots in port\n",
+				__func__);
+			goto out_free;
+		}
 		*res = '-';
 	}
 
@@ -240,7 +245,7 @@ decode_and_add_ds(__be32 **pp, struct inode *inode)
 	port = htons((tmp[0] << 8) | (tmp[1]));
 
 	ds = nfs4_pnfs_ds_add(inode, ip_addr, port);
-	dprintk("%s Decoded address and port %s\n", __func__, buf);
+	dprintk("%s: Decoded address and port %s\n", __func__, buf);
 out_free:
 	kfree(buf);
 out_err:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 9d992b0346e3..78936a8f40ab 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -50,6 +50,7 @@
 #include <linux/module.h>
 #include <linux/sunrpc/bc_xprt.h>
 #include <linux/xattr.h>
+#include <linux/utsname.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
@@ -4572,27 +4573,16 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 	*p = htonl((u32)clp->cl_boot_time.tv_nsec);
 	args.verifier = &verifier;
 
-	while (1) {
-		args.id_len = scnprintf(args.id, sizeof(args.id),
-					"%s/%s %u",
-					clp->cl_ipaddr,
-					rpc_peeraddr2str(clp->cl_rpcclient,
-							 RPC_DISPLAY_ADDR),
-					clp->cl_id_uniquifier);
-
-		status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
-
-		if (status != -NFS4ERR_CLID_INUSE)
-			break;
-
-		if (signalled())
-			break;
-
-		if (++clp->cl_id_uniquifier == 0)
-			break;
-	}
+	args.id_len = scnprintf(args.id, sizeof(args.id),
+				"%s/%s.%s/%u",
+				clp->cl_ipaddr,
+				init_utsname()->nodename,
+				init_utsname()->domainname,
+				clp->cl_rpcclient->cl_auth->au_flavor);
 
-	status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
+	status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
+	if (!status)
+		status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
 	dprintk("<-- %s status= %d\n", __func__, status);
 	return status;
 }
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 2336d532cf66..e6742b57a04c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -232,12 +232,6 @@ int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 	status = nfs4_proc_create_session(clp);
 	if (status != 0)
 		goto out;
-	status = nfs4_set_callback_sessionid(clp);
-	if (status != 0) {
-		printk(KERN_WARNING "Sessionid not set. No callback service\n");
-		nfs_callback_down(1);
-		status = 0;
-	}
 	nfs41_setup_state_renewal(clp);
 	nfs_mark_client_ready(clp, NFS_CS_READY);
 out:
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 2ab8e5cb8f59..4e2c168b6ee9 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -6086,11 +6086,11 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	__be32 *p = xdr_inline_decode(xdr, 4);
 	if (unlikely(!p))
 		goto out_overflow;
-	if (!ntohl(*p++)) {
+	if (*p == xdr_zero) {
 		p = xdr_inline_decode(xdr, 4);
 		if (unlikely(!p))
 			goto out_overflow;
-		if (!ntohl(*p++))
+		if (*p == xdr_zero)
 			return -EAGAIN;
 		entry->eof = 1;
 		return -EBADCOOKIE;
@@ -6101,7 +6101,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		goto out_overflow;
 	entry->prev_cookie = entry->cookie;
 	p = xdr_decode_hyper(p, &entry->cookie);
-	entry->len = ntohl(*p++);
+	entry->len = be32_to_cpup(p);
 
 	p = xdr_inline_decode(xdr, entry->len);
 	if (unlikely(!p))
@@ -6132,9 +6132,6 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	if (entry->fattr->valid & NFS_ATTR_FATTR_TYPE)
 		entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
 
-	if (verify_attr_len(xdr, p, len) < 0)
-		goto out_overflow;
-
 	return 0;
 
 out_overflow:
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index bc4089769735..1b1bc1a0fb0a 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -951,7 +951,7 @@ pnfs_put_deviceid_cache(struct nfs_client *clp)
 {
 	struct pnfs_deviceid_cache *local = clp->cl_devid_cache;
 
-	dprintk("--> %s cl_devid_cache %p\n", __func__, clp->cl_devid_cache);
+	dprintk("--> %s ({%d})\n", __func__, atomic_read(&local->dc_ref));
 	if (atomic_dec_and_lock(&local->dc_ref, &clp->cl_lock)) {
 		int i;
 		/* Verify cache is empty */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 10d648ea128b..c8278f4046cb 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -932,7 +932,7 @@ out_bad:
 	while (!list_empty(&list)) {
 		data = list_entry(list.next, struct nfs_write_data, pages);
 		list_del(&data->pages);
-		nfs_writedata_release(data);
+		nfs_writedata_free(data);
 	}
 	nfs_redirty_request(req);
 	return -ENOMEM;
diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c
index fc1c52571c03..84c27d69d421 100644
--- a/fs/nfs_common/nfsacl.c
+++ b/fs/nfs_common/nfsacl.c
@@ -42,6 +42,11 @@ struct nfsacl_encode_desc {
 	gid_t gid;
 };
 
+struct nfsacl_simple_acl {
+	struct posix_acl acl;
+	struct posix_acl_entry ace[4];
+};
+
 static int
 xdr_nfsace_encode(struct xdr_array2_desc *desc, void *elem)
 {
@@ -72,9 +77,20 @@ xdr_nfsace_encode(struct xdr_array2_desc *desc, void *elem)
 	return 0;
 }
 
-unsigned int
-nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
-	      struct posix_acl *acl, int encode_entries, int typeflag)
+/**
+ * nfsacl_encode - Encode an NFSv3 ACL
+ *
+ * @buf: destination xdr_buf to contain XDR encoded ACL
+ * @base: byte offset in xdr_buf where XDR'd ACL begins
+ * @inode: inode of file whose ACL this is
+ * @acl: posix_acl to encode
+ * @encode_entries: whether to encode ACEs as well
+ * @typeflag: ACL type: NFS_ACL_DEFAULT or zero
+ *
+ * Returns size of encoded ACL in bytes or a negative errno value.
+ */
+int nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
+		  struct posix_acl *acl, int encode_entries, int typeflag)
 {
 	int entries = (acl && acl->a_count) ? max_t(int, acl->a_count, 4) : 0;
 	struct nfsacl_encode_desc nfsacl_desc = {
@@ -88,17 +104,22 @@ nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
 		.uid = inode->i_uid,
 		.gid = inode->i_gid,
 	};
+	struct nfsacl_simple_acl aclbuf;
 	int err;
-	struct posix_acl *acl2 = NULL;
 
 	if (entries > NFS_ACL_MAX_ENTRIES ||
 	    xdr_encode_word(buf, base, entries))
 		return -EINVAL;
 	if (encode_entries && acl && acl->a_count == 3) {
-		/* Fake up an ACL_MASK entry. */
-		acl2 = posix_acl_alloc(4, GFP_KERNEL);
-		if (!acl2)
-			return -ENOMEM;
+		struct posix_acl *acl2 = &aclbuf.acl;
+
+		/* Avoid the use of posix_acl_alloc().  nfsacl_encode() is
+		 * invoked in contexts where a memory allocation failure is
+		 * fatal.  Fortunately this fake ACL is small enough to
+		 * construct on the stack. */
+		memset(acl2, 0, sizeof(acl2));
+		posix_acl_init(acl2, 4);
+
 		/* Insert entries in canonical order: other orders seem
 		 to confuse Solaris VxFS. */
 		acl2->a_entries[0] = acl->a_entries[0];  /* ACL_USER_OBJ */
@@ -109,8 +130,6 @@ nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
 		nfsacl_desc.acl = acl2;
 	}
 	err = xdr_encode_array2(buf, base + 4, &nfsacl_desc.desc);
-	if (acl2)
-		posix_acl_release(acl2);
 	if (!err)
 		err = 8 + nfsacl_desc.desc.elem_size *
 			  nfsacl_desc.desc.array_len;
@@ -224,9 +243,18 @@ posix_acl_from_nfsacl(struct posix_acl *acl)
 	return 0;
 }
 
-unsigned int
-nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt,
-	      struct posix_acl **pacl)
+/**
+ * nfsacl_decode - Decode an NFSv3 ACL
+ *
+ * @buf: xdr_buf containing XDR'd ACL data to decode
+ * @base: byte offset in xdr_buf where XDR'd ACL begins
+ * @aclcnt: count of ACEs in decoded posix_acl
+ * @pacl: buffer in which to place decoded posix_acl
+ *
+ * Returns the length of the decoded ACL in bytes, or a negative errno value.
+ */
+int nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt,
+		  struct posix_acl **pacl)
 {
 	struct nfsacl_decode_desc nfsacl_desc = {
 		.desc = {
diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h
new file mode 100644
index 000000000000..34e5c40af5ef
--- /dev/null
+++ b/fs/nfsd/acl.h
@@ -0,0 +1,59 @@
+/*
+ *  Common NFSv4 ACL handling definitions.
+ *
+ *  Copyright (c) 2002 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef LINUX_NFS4_ACL_H
+#define LINUX_NFS4_ACL_H
+
+#include <linux/posix_acl.h>
+
+/* Maximum ACL we'll accept from client; chosen (somewhat arbitrarily) to
+ * fit in a page: */
+#define NFS4_ACL_MAX 170
+
+struct nfs4_acl *nfs4_acl_new(int);
+int nfs4_acl_get_whotype(char *, u32);
+int nfs4_acl_write_who(int who, char *p);
+int nfs4_acl_permission(struct nfs4_acl *acl, uid_t owner, gid_t group,
+		                        uid_t who, u32 mask);
+
+#define NFS4_ACL_TYPE_DEFAULT	0x01
+#define NFS4_ACL_DIR		0x02
+#define NFS4_ACL_OWNER		0x04
+
+struct nfs4_acl *nfs4_acl_posix_to_nfsv4(struct posix_acl *,
+				struct posix_acl *, unsigned int flags);
+int nfs4_acl_nfsv4_to_posix(struct nfs4_acl *, struct posix_acl **,
+				struct posix_acl **, unsigned int flags);
+
+#endif /* LINUX_NFS4_ACL_H */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index c0fcb7ab7f6d..8b31e5f8795d 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1,4 +1,3 @@
-#define MSNFS	/* HACK HACK */
 /*
  * NFS exporting and validation.
  *
@@ -1444,9 +1443,6 @@ static struct flags {
 	{ NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}},
 	{ NFSEXP_NOAUTHNLM, {"insecure_locks", ""}},
 	{ NFSEXP_V4ROOT, {"v4root", ""}},
-#ifdef MSNFS
-	{ NFSEXP_MSNFS, {"msnfs", ""}},
-#endif
 	{ 0, {"", ""}}
 };
 
diff --git a/fs/nfsd/idmap.h b/fs/nfsd/idmap.h
new file mode 100644
index 000000000000..2f3be1321534
--- /dev/null
+++ b/fs/nfsd/idmap.h
@@ -0,0 +1,62 @@
+/*
+ *  Mapping of UID to name and vice versa.
+ *
+ *  Copyright (c) 2002, 2003 The Regents of the University of
+ *  Michigan.  All rights reserved.
+> *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef LINUX_NFSD_IDMAP_H
+#define LINUX_NFSD_IDMAP_H
+
+#include <linux/in.h>
+#include <linux/sunrpc/svc.h>
+
+/* XXX from linux/nfs_idmap.h */
+#define IDMAP_NAMESZ 128
+
+#ifdef CONFIG_NFSD_V4
+int nfsd_idmap_init(void);
+void nfsd_idmap_shutdown(void);
+#else
+static inline int nfsd_idmap_init(void)
+{
+	return 0;
+}
+static inline void nfsd_idmap_shutdown(void)
+{
+}
+#endif
+
+__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, __u32 *);
+__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, __u32 *);
+int nfsd_map_uid_to_name(struct svc_rqst *, __u32, char *);
+int nfsd_map_gid_to_name(struct svc_rqst *, __u32, char *);
+
+#endif /* LINUX_NFSD_IDMAP_H */
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 5b7e3021e06b..2247fc91d5e9 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -151,10 +151,10 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
 
-	dprintk("nfsd: READ(3) %s %lu bytes at %lu\n",
+	dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n",
 				SVCFH_fmt(&argp->fh),
 				(unsigned long) argp->count,
-				(unsigned long) argp->offset);
+				(unsigned long long) argp->offset);
 
 	/* Obtain buffer pointer for payload.
 	 * 1 (status) + 22 (post_op_attr) + 1 (count) + 1 (eof)
@@ -191,10 +191,10 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
 	__be32	nfserr;
 	unsigned long cnt = argp->len;
 
-	dprintk("nfsd: WRITE(3)    %s %d bytes at %ld%s\n",
+	dprintk("nfsd: WRITE(3)    %s %d bytes at %Lu%s\n",
 				SVCFH_fmt(&argp->fh),
 				argp->len,
-				(unsigned long) argp->offset,
+				(unsigned long long) argp->offset,
 				argp->stable? " stable" : "");
 
 	fh_copy(&resp->fh, &argp->fh);
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index e48052615159..ad88f1c0a4c3 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -36,7 +36,7 @@
 
 #include <linux/slab.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs4_acl.h>
+#include "acl.h"
 
 
 /* mode bit translations: */
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 21a63da305ff..3be975e18919 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -628,10 +628,8 @@ static int max_cb_time(void)
 	return max(nfsd4_lease/10, (time_t)1) * HZ;
 }
 
-/* Reference counting, callback cleanup, etc., all look racy as heck.
- * And why is cl_cb_set an atomic? */
 
-int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
+static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
 {
 	struct rpc_timeout	timeparms = {
 		.to_initval	= max_cb_time(),
@@ -641,6 +639,7 @@ int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
 		.net		= &init_net,
 		.address	= (struct sockaddr *) &conn->cb_addr,
 		.addrsize	= conn->cb_addrlen,
+		.saddress	= (struct sockaddr *) &conn->cb_saddr,
 		.timeout	= &timeparms,
 		.program	= &cb_program,
 		.version	= 0,
@@ -657,6 +656,10 @@ int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
 		args.protocol = XPRT_TRANSPORT_TCP;
 		clp->cl_cb_ident = conn->cb_ident;
 	} else {
+		if (!conn->cb_xprt)
+			return -EINVAL;
+		clp->cl_cb_conn.cb_xprt = conn->cb_xprt;
+		clp->cl_cb_session = ses;
 		args.bc_xprt = conn->cb_xprt;
 		args.prognumber = clp->cl_cb_session->se_cb_prog;
 		args.protocol = XPRT_TRANSPORT_BC_TCP;
@@ -679,14 +682,20 @@ static void warn_no_callback_path(struct nfs4_client *clp, int reason)
 		(int)clp->cl_name.len, clp->cl_name.data, reason);
 }
 
+static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason)
+{
+	clp->cl_cb_state = NFSD4_CB_DOWN;
+	warn_no_callback_path(clp, reason);
+}
+
 static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null);
 
 	if (task->tk_status)
-		warn_no_callback_path(clp, task->tk_status);
+		nfsd4_mark_cb_down(clp, task->tk_status);
 	else
-		atomic_set(&clp->cl_cb_set, 1);
+		clp->cl_cb_state = NFSD4_CB_UP;
 }
 
 static const struct rpc_call_ops nfsd4_cb_probe_ops = {
@@ -709,6 +718,11 @@ int set_callback_cred(void)
 
 static struct workqueue_struct *callback_wq;
 
+static void run_nfsd4_cb(struct nfsd4_callback *cb)
+{
+	queue_work(callback_wq, &cb->cb_work);
+}
+
 static void do_probe_callback(struct nfs4_client *clp)
 {
 	struct nfsd4_callback *cb = &clp->cl_cb_null;
@@ -723,7 +737,7 @@ static void do_probe_callback(struct nfs4_client *clp)
 
 	cb->cb_ops = &nfsd4_cb_probe_ops;
 
-	queue_work(callback_wq, &cb->cb_work);
+	run_nfsd4_cb(cb);
 }
 
 /*
@@ -732,14 +746,21 @@ static void do_probe_callback(struct nfs4_client *clp)
  */
 void nfsd4_probe_callback(struct nfs4_client *clp)
 {
+	/* XXX: atomicity?  Also, should we be using cl_cb_flags? */
+	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
 	set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags);
 	do_probe_callback(clp);
 }
 
-void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
+void nfsd4_probe_callback_sync(struct nfs4_client *clp)
 {
-	BUG_ON(atomic_read(&clp->cl_cb_set));
+	nfsd4_probe_callback(clp);
+	flush_workqueue(callback_wq);
+}
 
+void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
+{
+	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
 	spin_lock(&clp->cl_lock);
 	memcpy(&clp->cl_cb_conn, conn, sizeof(struct nfs4_cb_conn));
 	spin_unlock(&clp->cl_lock);
@@ -750,24 +771,14 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
  * If the slot is available, then mark it busy.  Otherwise, set the
  * thread for sleeping on the callback RPC wait queue.
  */
-static int nfsd41_cb_setup_sequence(struct nfs4_client *clp,
-		struct rpc_task *task)
+static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task)
 {
-	u32 *ptr = (u32 *)clp->cl_cb_session->se_sessionid.data;
-	int status = 0;
-
-	dprintk("%s: %u:%u:%u:%u\n", __func__,
-		ptr[0], ptr[1], ptr[2], ptr[3]);
-
 	if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
 		rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
 		dprintk("%s slot is busy\n", __func__);
-		status = -EAGAIN;
-		goto out;
+		return false;
 	}
-out:
-	dprintk("%s status=%d\n", __func__, status);
-	return status;
+	return true;
 }
 
 /*
@@ -780,20 +791,19 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
 	struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall);
 	struct nfs4_client *clp = dp->dl_client;
 	u32 minorversion = clp->cl_minorversion;
-	int status = 0;
 
 	cb->cb_minorversion = minorversion;
 	if (minorversion) {
-		status = nfsd41_cb_setup_sequence(clp, task);
-		if (status) {
-			if (status != -EAGAIN) {
-				/* terminate rpc task */
-				task->tk_status = status;
-				task->tk_action = NULL;
-			}
+		if (!nfsd41_cb_get_slot(clp, task))
 			return;
-		}
 	}
+	spin_lock(&clp->cl_lock);
+	if (list_empty(&cb->cb_per_client)) {
+		/* This is the first call, not a restart */
+		cb->cb_done = false;
+		list_add(&cb->cb_per_client, &clp->cl_callbacks);
+	}
+	spin_unlock(&clp->cl_lock);
 	rpc_call_start(task);
 }
 
@@ -829,15 +839,18 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
 
 	nfsd4_cb_done(task, calldata);
 
-	if (current_rpc_client == NULL) {
-		/* We're shutting down; give up. */
-		/* XXX: err, or is it ok just to fall through
-		 * and rpc_restart_call? */
+	if (current_rpc_client != task->tk_client) {
+		/* We're shutting down or changing cl_cb_client; leave
+		 * it to nfsd4_process_cb_update to restart the call if
+		 * necessary. */
 		return;
 	}
 
+	if (cb->cb_done)
+		return;
 	switch (task->tk_status) {
 	case 0:
+		cb->cb_done = true;
 		return;
 	case -EBADHANDLE:
 	case -NFS4ERR_BAD_STATEID:
@@ -846,32 +859,30 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
 		break;
 	default:
 		/* Network partition? */
-		atomic_set(&clp->cl_cb_set, 0);
-		warn_no_callback_path(clp, task->tk_status);
-		if (current_rpc_client != task->tk_client) {
-			/* queue a callback on the new connection: */
-			atomic_inc(&dp->dl_count);
-			nfsd4_cb_recall(dp);
-			return;
-		}
+		nfsd4_mark_cb_down(clp, task->tk_status);
 	}
 	if (dp->dl_retries--) {
 		rpc_delay(task, 2*HZ);
 		task->tk_status = 0;
 		rpc_restart_call_prepare(task);
 		return;
-	} else {
-		atomic_set(&clp->cl_cb_set, 0);
-		warn_no_callback_path(clp, task->tk_status);
 	}
+	nfsd4_mark_cb_down(clp, task->tk_status);
+	cb->cb_done = true;
 }
 
 static void nfsd4_cb_recall_release(void *calldata)
 {
 	struct nfsd4_callback *cb = calldata;
+	struct nfs4_client *clp = cb->cb_clp;
 	struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall);
 
-	nfs4_put_delegation(dp);
+	if (cb->cb_done) {
+		spin_lock(&clp->cl_lock);
+		list_del(&cb->cb_per_client);
+		spin_unlock(&clp->cl_lock);
+		nfs4_put_delegation(dp);
+	}
 }
 
 static const struct rpc_call_ops nfsd4_cb_recall_ops = {
@@ -906,16 +917,33 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
 	flush_workqueue(callback_wq);
 }
 
-void nfsd4_release_cb(struct nfsd4_callback *cb)
+static void nfsd4_release_cb(struct nfsd4_callback *cb)
 {
 	if (cb->cb_ops->rpc_release)
 		cb->cb_ops->rpc_release(cb);
 }
 
-void nfsd4_process_cb_update(struct nfsd4_callback *cb)
+/* requires cl_lock: */
+static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp)
+{
+	struct nfsd4_session *s;
+	struct nfsd4_conn *c;
+
+	list_for_each_entry(s, &clp->cl_sessions, se_perclnt) {
+		list_for_each_entry(c, &s->se_conns, cn_persession) {
+			if (c->cn_flags & NFS4_CDFC4_BACK)
+				return c;
+		}
+	}
+	return NULL;
+}
+
+static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 {
 	struct nfs4_cb_conn conn;
 	struct nfs4_client *clp = cb->cb_clp;
+	struct nfsd4_session *ses = NULL;
+	struct nfsd4_conn *c;
 	int err;
 
 	/*
@@ -926,6 +954,10 @@ void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 		rpc_shutdown_client(clp->cl_cb_client);
 		clp->cl_cb_client = NULL;
 	}
+	if (clp->cl_cb_conn.cb_xprt) {
+		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
+		clp->cl_cb_conn.cb_xprt = NULL;
+	}
 	if (test_bit(NFSD4_CLIENT_KILL, &clp->cl_cb_flags))
 		return;
 	spin_lock(&clp->cl_lock);
@@ -936,11 +968,22 @@ void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 	BUG_ON(!clp->cl_cb_flags);
 	clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags);
 	memcpy(&conn, &cb->cb_clp->cl_cb_conn, sizeof(struct nfs4_cb_conn));
+	c = __nfsd4_find_backchannel(clp);
+	if (c) {
+		svc_xprt_get(c->cn_xprt);
+		conn.cb_xprt = c->cn_xprt;
+		ses = c->cn_session;
+	}
 	spin_unlock(&clp->cl_lock);
 
-	err = setup_callback_client(clp, &conn);
-	if (err)
+	err = setup_callback_client(clp, &conn, ses);
+	if (err) {
 		warn_no_callback_path(clp, err);
+		return;
+	}
+	/* Yay, the callback channel's back! Restart any callbacks: */
+	list_for_each_entry(cb, &clp->cl_callbacks, cb_per_client)
+		run_nfsd4_cb(cb);
 }
 
 void nfsd4_do_callback_rpc(struct work_struct *w)
@@ -965,10 +1008,11 @@ void nfsd4_do_callback_rpc(struct work_struct *w)
 void nfsd4_cb_recall(struct nfs4_delegation *dp)
 {
 	struct nfsd4_callback *cb = &dp->dl_recall;
+	struct nfs4_client *clp = dp->dl_client;
 
 	dp->dl_retries = 1;
 	cb->cb_op = dp;
-	cb->cb_clp = dp->dl_client;
+	cb->cb_clp = clp;
 	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL];
 	cb->cb_msg.rpc_argp = cb;
 	cb->cb_msg.rpc_resp = cb;
@@ -977,5 +1021,8 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
 	cb->cb_ops = &nfsd4_cb_recall_ops;
 	dp->dl_retries = 1;
 
-	queue_work(callback_wq, &dp->dl_recall.cb_work);
+	INIT_LIST_HEAD(&cb->cb_per_client);
+	cb->cb_done = true;
+
+	run_nfsd4_cb(&dp->dl_recall);
 }
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index f0695e815f0e..6d2c397d458b 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -33,10 +33,11 @@
  */
 
 #include <linux/module.h>
-#include <linux/nfsd_idmap.h>
 #include <linux/seq_file.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include "idmap.h"
+#include "nfsd.h"
 
 /*
  * Cache entry
@@ -514,7 +515,7 @@ rqst_authname(struct svc_rqst *rqstp)
 	return clp->name;
 }
 
-static int
+static __be32
 idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen,
 		uid_t *id)
 {
@@ -524,15 +525,15 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen
 	int ret;
 
 	if (namelen + 1 > sizeof(key.name))
-		return -EINVAL;
+		return nfserr_badowner;
 	memcpy(key.name, name, namelen);
 	key.name[namelen] = '\0';
 	strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
 	ret = idmap_lookup(rqstp, nametoid_lookup, &key, &nametoid_cache, &item);
 	if (ret == -ENOENT)
-		ret = -ESRCH; /* nfserr_badname */
+		return nfserr_badowner;
 	if (ret)
-		return ret;
+		return nfserrno(ret);
 	*id = item->id;
 	cache_put(&item->h, &nametoid_cache);
 	return 0;
@@ -560,14 +561,14 @@ idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
 	return ret;
 }
 
-int
+__be32
 nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 		__u32 *id)
 {
 	return idmap_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, id);
 }
 
-int
+__be32
 nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 		__u32 *id)
 {
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 0cdfd022bb7b..db52546143d1 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -604,9 +604,7 @@ nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status;
 }
 
-static __be32
-nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	      void *arg)
+static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 {
 	struct svc_fh tmp_fh;
 	__be32 ret;
@@ -615,13 +613,19 @@ nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	ret = exp_pseudoroot(rqstp, &tmp_fh);
 	if (ret)
 		return ret;
-	if (tmp_fh.fh_dentry == cstate->current_fh.fh_dentry) {
+	if (tmp_fh.fh_dentry == fh->fh_dentry) {
 		fh_put(&tmp_fh);
 		return nfserr_noent;
 	}
 	fh_put(&tmp_fh);
-	return nfsd_lookup(rqstp, &cstate->current_fh,
-			   "..", 2, &cstate->current_fh);
+	return nfsd_lookup(rqstp, fh, "..", 2, fh);
+}
+
+static __be32
+nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	      void *arg)
+{
+	return nfsd4_do_lookupp(rqstp, &cstate->current_fh);
 }
 
 static __be32
@@ -769,10 +773,36 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	} else
 		secinfo->si_exp = exp;
 	dput(dentry);
+	if (cstate->minorversion)
+		/* See rfc 5661 section 2.6.3.1.1.8 */
+		fh_put(&cstate->current_fh);
 	return err;
 }
 
 static __be32
+nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	      struct nfsd4_secinfo_no_name *sin)
+{
+	__be32 err;
+
+	switch (sin->sin_style) {
+	case NFS4_SECINFO_STYLE4_CURRENT_FH:
+		break;
+	case NFS4_SECINFO_STYLE4_PARENT:
+		err = nfsd4_do_lookupp(rqstp, &cstate->current_fh);
+		if (err)
+			return err;
+		break;
+	default:
+		return nfserr_inval;
+	}
+	exp_get(cstate->current_fh.fh_export);
+	sin->sin_exp = cstate->current_fh.fh_export;
+	fh_put(&cstate->current_fh);
+	return nfs_ok;
+}
+
+static __be32
 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	      struct nfsd4_setattr *setattr)
 {
@@ -974,8 +1004,8 @@ static const char *nfsd4_op_name(unsigned opnum);
  * Also note, enforced elsewhere:
  *	- SEQUENCE other than as first op results in
  *	  NFS4ERR_SEQUENCE_POS. (Enforced in nfsd4_sequence().)
- *	- BIND_CONN_TO_SESSION must be the only op in its compound
- *	  (Will be enforced in nfsd4_bind_conn_to_session().)
+ *	- BIND_CONN_TO_SESSION must be the only op in its compound.
+ *	  (Enforced in nfsd4_bind_conn_to_session().)
  *	- DESTROY_SESSION must be the final operation in a compound, if
  *	  sessionid's in SEQUENCE and DESTROY_SESSION are the same.
  *	  (Enforced in nfsd4_destroy_session().)
@@ -1126,10 +1156,6 @@ encode_op:
 
 		nfsd4_increment_op_stats(op->opnum);
 	}
-	if (!rqstp->rq_usedeferral && status == nfserr_dropit) {
-		dprintk("%s Dropit - send NFS4ERR_DELAY\n", __func__);
-		status = nfserr_jukebox;
-	}
 
 	resp->cstate.status = status;
 	fh_put(&resp->cstate.current_fh);
@@ -1300,6 +1326,11 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
 		.op_name = "OP_EXCHANGE_ID",
 	},
+	[OP_BIND_CONN_TO_SESSION] = {
+		.op_func = (nfsd4op_func)nfsd4_bind_conn_to_session,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_BIND_CONN_TO_SESSION",
+	},
 	[OP_CREATE_SESSION] = {
 		.op_func = (nfsd4op_func)nfsd4_create_session,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
@@ -1320,6 +1351,10 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_flags = ALLOWED_WITHOUT_FH,
 		.op_name = "OP_RECLAIM_COMPLETE",
 	},
+	[OP_SECINFO_NO_NAME] = {
+		.op_func = (nfsd4op_func)nfsd4_secinfo_no_name,
+		.op_name = "OP_SECINFO_NO_NAME",
+	},
 };
 
 static const char *nfsd4_op_name(unsigned opnum)
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 7e26caab2a26..ffb59ef6f82f 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -302,7 +302,6 @@ purge_old(struct dentry *parent, struct dentry *child)
 {
 	int status;
 
-	/* note: we currently use this path only for minorversion 0 */
 	if (nfs4_has_reclaimed_state(child->d_name.name, false))
 		return 0;
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index fbd18c3074bb..d98d0213285d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -230,7 +230,8 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f
 	dp->dl_client = clp;
 	get_nfs4_file(fp);
 	dp->dl_file = fp;
-	nfs4_file_get_access(fp, O_RDONLY);
+	dp->dl_vfs_file = find_readable_file(fp);
+	get_file(dp->dl_vfs_file);
 	dp->dl_flock = NULL;
 	dp->dl_type = type;
 	dp->dl_stateid.si_boot = boot_time;
@@ -252,6 +253,7 @@ nfs4_put_delegation(struct nfs4_delegation *dp)
 	if (atomic_dec_and_test(&dp->dl_count)) {
 		dprintk("NFSD: freeing dp %p\n",dp);
 		put_nfs4_file(dp->dl_file);
+		fput(dp->dl_vfs_file);
 		kmem_cache_free(deleg_slab, dp);
 		num_delegations--;
 	}
@@ -265,12 +267,10 @@ nfs4_put_delegation(struct nfs4_delegation *dp)
 static void
 nfs4_close_delegation(struct nfs4_delegation *dp)
 {
-	struct file *filp = find_readable_file(dp->dl_file);
-
 	dprintk("NFSD: close_delegation dp %p\n",dp);
+	/* XXX: do we even need this check?: */
 	if (dp->dl_flock)
-		vfs_setlease(filp, F_UNLCK, &dp->dl_flock);
-	nfs4_file_put_access(dp->dl_file, O_RDONLY);
+		vfs_setlease(dp->dl_vfs_file, F_UNLCK, &dp->dl_flock);
 }
 
 /* Called under the state lock. */
@@ -642,6 +642,7 @@ static void nfsd4_conn_lost(struct svc_xpt_user *u)
 		free_conn(c);
 	}
 	spin_unlock(&clp->cl_lock);
+	nfsd4_probe_callback(clp);
 }
 
 static struct nfsd4_conn *alloc_conn(struct svc_rqst *rqstp, u32 flags)
@@ -679,15 +680,12 @@ static int nfsd4_register_conn(struct nfsd4_conn *conn)
 	return register_xpt_user(conn->cn_xprt, &conn->cn_xpt_user);
 }
 
-static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses)
+static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses, u32 dir)
 {
 	struct nfsd4_conn *conn;
-	u32 flags = NFS4_CDFC4_FORE;
 	int ret;
 
-	if (ses->se_flags & SESSION4_BACK_CHAN)
-		flags |= NFS4_CDFC4_BACK;
-	conn = alloc_conn(rqstp, flags);
+	conn = alloc_conn(rqstp, dir);
 	if (!conn)
 		return nfserr_jukebox;
 	nfsd4_hash_conn(conn, ses);
@@ -698,6 +696,17 @@ static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses)
 	return nfs_ok;
 }
 
+static __be32 nfsd4_new_conn_from_crses(struct svc_rqst *rqstp, struct nfsd4_session *ses)
+{
+	u32 dir = NFS4_CDFC4_FORE;
+
+	if (ses->se_flags & SESSION4_BACK_CHAN)
+		dir |= NFS4_CDFC4_BACK;
+
+	return nfsd4_new_conn(rqstp, ses, dir);
+}
+
+/* must be called under client_lock */
 static void nfsd4_del_conns(struct nfsd4_session *s)
 {
 	struct nfs4_client *clp = s->se_client;
@@ -749,6 +758,8 @@ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct n
 	 */
 	slotsize = nfsd4_sanitize_slot_size(fchan->maxresp_cached);
 	numslots = nfsd4_get_drc_mem(slotsize, fchan->maxreqs);
+	if (numslots < 1)
+		return NULL;
 
 	new = alloc_session(slotsize, numslots);
 	if (!new) {
@@ -769,25 +780,30 @@ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct n
 	idx = hash_sessionid(&new->se_sessionid);
 	spin_lock(&client_lock);
 	list_add(&new->se_hash, &sessionid_hashtbl[idx]);
+	spin_lock(&clp->cl_lock);
 	list_add(&new->se_perclnt, &clp->cl_sessions);
+	spin_unlock(&clp->cl_lock);
 	spin_unlock(&client_lock);
 
-	status = nfsd4_new_conn(rqstp, new);
+	status = nfsd4_new_conn_from_crses(rqstp, new);
 	/* whoops: benny points out, status is ignored! (err, or bogus) */
 	if (status) {
 		free_session(&new->se_ref);
 		return NULL;
 	}
-	if (!clp->cl_cb_session && (cses->flags & SESSION4_BACK_CHAN)) {
+	if (cses->flags & SESSION4_BACK_CHAN) {
 		struct sockaddr *sa = svc_addr(rqstp);
-
-		clp->cl_cb_session = new;
-		clp->cl_cb_conn.cb_xprt = rqstp->rq_xprt;
-		svc_xprt_get(rqstp->rq_xprt);
+		/*
+		 * This is a little silly; with sessions there's no real
+		 * use for the callback address.  Use the peer address
+		 * as a reasonable default for now, but consider fixing
+		 * the rpc client not to require an address in the
+		 * future:
+		 */
 		rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa);
 		clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa);
-		nfsd4_probe_callback(clp);
 	}
+	nfsd4_probe_callback(clp);
 	return new;
 }
 
@@ -817,7 +833,9 @@ static void
 unhash_session(struct nfsd4_session *ses)
 {
 	list_del(&ses->se_hash);
+	spin_lock(&ses->se_client->cl_lock);
 	list_del(&ses->se_perclnt);
+	spin_unlock(&ses->se_client->cl_lock);
 }
 
 /* must be called under the client_lock */
@@ -923,8 +941,10 @@ unhash_client_locked(struct nfs4_client *clp)
 
 	mark_client_expired(clp);
 	list_del(&clp->cl_lru);
+	spin_lock(&clp->cl_lock);
 	list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
 		list_del_init(&ses->se_hash);
+	spin_unlock(&clp->cl_lock);
 }
 
 static void
@@ -1051,12 +1071,13 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir,
 
 	memcpy(clp->cl_recdir, recdir, HEXDIR_LEN);
 	atomic_set(&clp->cl_refcount, 0);
-	atomic_set(&clp->cl_cb_set, 0);
+	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
 	INIT_LIST_HEAD(&clp->cl_idhash);
 	INIT_LIST_HEAD(&clp->cl_strhash);
 	INIT_LIST_HEAD(&clp->cl_openowners);
 	INIT_LIST_HEAD(&clp->cl_delegations);
 	INIT_LIST_HEAD(&clp->cl_lru);
+	INIT_LIST_HEAD(&clp->cl_callbacks);
 	spin_lock_init(&clp->cl_lock);
 	INIT_WORK(&clp->cl_cb_null.cb_work, nfsd4_do_callback_rpc);
 	clp->cl_time = get_seconds();
@@ -1132,54 +1153,55 @@ find_unconfirmed_client(clientid_t *clid)
 	return NULL;
 }
 
-/*
- * Return 1 iff clp's clientid establishment method matches the use_exchange_id
- * parameter. Matching is based on the fact the at least one of the
- * EXCHGID4_FLAG_USE_{NON_PNFS,PNFS_MDS,PNFS_DS} flags must be set for v4.1
- *
- * FIXME: we need to unify the clientid namespaces for nfsv4.x
- * and correctly deal with client upgrade/downgrade in EXCHANGE_ID
- * and SET_CLIENTID{,_CONFIRM}
- */
-static inline int
-match_clientid_establishment(struct nfs4_client *clp, bool use_exchange_id)
+static bool clp_used_exchangeid(struct nfs4_client *clp)
 {
-	bool has_exchange_flags = (clp->cl_exchange_flags != 0);
-	return use_exchange_id == has_exchange_flags;
-}
+	return clp->cl_exchange_flags != 0;
+} 
 
 static struct nfs4_client *
-find_confirmed_client_by_str(const char *dname, unsigned int hashval,
-			     bool use_exchange_id)
+find_confirmed_client_by_str(const char *dname, unsigned int hashval)
 {
 	struct nfs4_client *clp;
 
 	list_for_each_entry(clp, &conf_str_hashtbl[hashval], cl_strhash) {
-		if (same_name(clp->cl_recdir, dname) &&
-		    match_clientid_establishment(clp, use_exchange_id))
+		if (same_name(clp->cl_recdir, dname))
 			return clp;
 	}
 	return NULL;
 }
 
 static struct nfs4_client *
-find_unconfirmed_client_by_str(const char *dname, unsigned int hashval,
-			       bool use_exchange_id)
+find_unconfirmed_client_by_str(const char *dname, unsigned int hashval)
 {
 	struct nfs4_client *clp;
 
 	list_for_each_entry(clp, &unconf_str_hashtbl[hashval], cl_strhash) {
-		if (same_name(clp->cl_recdir, dname) &&
-		    match_clientid_establishment(clp, use_exchange_id))
+		if (same_name(clp->cl_recdir, dname))
 			return clp;
 	}
 	return NULL;
 }
 
+static void rpc_svcaddr2sockaddr(struct sockaddr *sa, unsigned short family, union svc_addr_u *svcaddr)
+{
+	switch (family) {
+	case AF_INET:
+		((struct sockaddr_in *)sa)->sin_family = AF_INET;
+		((struct sockaddr_in *)sa)->sin_addr = svcaddr->addr;
+		return;
+	case AF_INET6:
+		((struct sockaddr_in6 *)sa)->sin6_family = AF_INET6;
+		((struct sockaddr_in6 *)sa)->sin6_addr = svcaddr->addr6;
+		return;
+	}
+}
+
 static void
-gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid)
+gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_rqst *rqstp)
 {
 	struct nfs4_cb_conn *conn = &clp->cl_cb_conn;
+	struct sockaddr	*sa = svc_addr(rqstp);
+	u32 scopeid = rpc_get_scope_id(sa);
 	unsigned short expected_family;
 
 	/* Currently, we only support tcp and tcp6 for the callback channel */
@@ -1205,6 +1227,7 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid)
 
 	conn->cb_prog = se->se_callback_prog;
 	conn->cb_ident = se->se_callback_ident;
+	rpc_svcaddr2sockaddr((struct sockaddr *)&conn->cb_saddr, expected_family, &rqstp->rq_daddr);
 	return;
 out_err:
 	conn->cb_addr.ss_family = AF_UNSPEC;
@@ -1344,7 +1367,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 	case SP4_NONE:
 		break;
 	case SP4_SSV:
-		return nfserr_encr_alg_unsupp;
+		return nfserr_serverfault;
 	default:
 		BUG();				/* checked by xdr code */
 	case SP4_MACH_CRED:
@@ -1361,8 +1384,12 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 	nfs4_lock_state();
 	status = nfs_ok;
 
-	conf = find_confirmed_client_by_str(dname, strhashval, true);
+	conf = find_confirmed_client_by_str(dname, strhashval);
 	if (conf) {
+		if (!clp_used_exchangeid(conf)) {
+			status = nfserr_clid_inuse; /* XXX: ? */
+			goto out;
+		}
 		if (!same_verf(&verf, &conf->cl_verifier)) {
 			/* 18.35.4 case 8 */
 			if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) {
@@ -1403,7 +1430,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 		goto out;
 	}
 
-	unconf  = find_unconfirmed_client_by_str(dname, strhashval, true);
+	unconf  = find_unconfirmed_client_by_str(dname, strhashval);
 	if (unconf) {
 		/*
 		 * Possible retry or client restart.  Per 18.35.4 case 4,
@@ -1560,6 +1587,8 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 	status = nfs_ok;
 	memcpy(cr_ses->sessionid.data, new->se_sessionid.data,
 	       NFS4_MAX_SESSIONID_LEN);
+	memcpy(&cr_ses->fore_channel, &new->se_fchannel,
+		sizeof(struct nfsd4_channel_attrs));
 	cs_slot->sl_seqid++;
 	cr_ses->seqid = cs_slot->sl_seqid;
 
@@ -1581,6 +1610,45 @@ static bool nfsd4_last_compound_op(struct svc_rqst *rqstp)
 	return argp->opcnt == resp->opcnt;
 }
 
+static __be32 nfsd4_map_bcts_dir(u32 *dir)
+{
+	switch (*dir) {
+	case NFS4_CDFC4_FORE:
+	case NFS4_CDFC4_BACK:
+		return nfs_ok;
+	case NFS4_CDFC4_FORE_OR_BOTH:
+	case NFS4_CDFC4_BACK_OR_BOTH:
+		*dir = NFS4_CDFC4_BOTH;
+		return nfs_ok;
+	};
+	return nfserr_inval;
+}
+
+__be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
+		     struct nfsd4_compound_state *cstate,
+		     struct nfsd4_bind_conn_to_session *bcts)
+{
+	__be32 status;
+
+	if (!nfsd4_last_compound_op(rqstp))
+		return nfserr_not_only_op;
+	spin_lock(&client_lock);
+	cstate->session = find_in_sessionid_hashtbl(&bcts->sessionid);
+	/* Sorta weird: we only need the refcnt'ing because new_conn acquires
+	 * client_lock iself: */
+	if (cstate->session) {
+		nfsd4_get_session(cstate->session);
+		atomic_inc(&cstate->session->se_client->cl_refcount);
+	}
+	spin_unlock(&client_lock);
+	if (!cstate->session)
+		return nfserr_badsession;
+
+	status = nfsd4_map_bcts_dir(&bcts->dir);
+	nfsd4_new_conn(rqstp, cstate->session, bcts->dir);
+	return nfs_ok;
+}
+
 static bool nfsd4_compound_in_session(struct nfsd4_session *session, struct nfs4_sessionid *sid)
 {
 	if (!session)
@@ -1619,8 +1687,7 @@ nfsd4_destroy_session(struct svc_rqst *r,
 	spin_unlock(&client_lock);
 
 	nfs4_lock_state();
-	/* wait for callbacks */
-	nfsd4_shutdown_callback(ses->se_client);
+	nfsd4_probe_callback_sync(ses->se_client);
 	nfs4_unlock_state();
 
 	nfsd4_del_conns(ses);
@@ -1733,8 +1800,12 @@ nfsd4_sequence(struct svc_rqst *rqstp,
 out:
 	/* Hold a session reference until done processing the compound. */
 	if (cstate->session) {
+		struct nfs4_client *clp = session->se_client;
+
 		nfsd4_get_session(cstate->session);
-		atomic_inc(&session->se_client->cl_refcount);
+		atomic_inc(&clp->cl_refcount);
+		if (clp->cl_cb_state == NFSD4_CB_DOWN)
+			seq->status_flags |= SEQ4_STATUS_CB_PATH_DOWN;
 	}
 	kfree(conn);
 	spin_unlock(&client_lock);
@@ -1775,7 +1846,6 @@ __be32
 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		  struct nfsd4_setclientid *setclid)
 {
-	struct sockaddr		*sa = svc_addr(rqstp);
 	struct xdr_netobj 	clname = { 
 		.len = setclid->se_namelen,
 		.data = setclid->se_name,
@@ -1801,10 +1871,12 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	strhashval = clientstr_hashval(dname);
 
 	nfs4_lock_state();
-	conf = find_confirmed_client_by_str(dname, strhashval, false);
+	conf = find_confirmed_client_by_str(dname, strhashval);
 	if (conf) {
 		/* RFC 3530 14.2.33 CASE 0: */
 		status = nfserr_clid_inuse;
+		if (clp_used_exchangeid(conf))
+			goto out;
 		if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) {
 			char addr_str[INET6_ADDRSTRLEN];
 			rpc_ntop((struct sockaddr *) &conf->cl_addr, addr_str,
@@ -1819,7 +1891,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * has a description of SETCLIENTID request processing consisting
 	 * of 5 bullet points, labeled as CASE0 - CASE4 below.
 	 */
-	unconf = find_unconfirmed_client_by_str(dname, strhashval, false);
+	unconf = find_unconfirmed_client_by_str(dname, strhashval);
 	status = nfserr_resource;
 	if (!conf) {
 		/*
@@ -1876,7 +1948,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * for consistent minorversion use throughout:
 	 */
 	new->cl_minorversion = 0;
-	gen_callback(new, setclid, rpc_get_scope_id(sa));
+	gen_callback(new, setclid, rqstp);
 	add_to_unconfirmed(new, strhashval);
 	setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot;
 	setclid->se_clientid.cl_id = new->cl_clientid.cl_id;
@@ -1935,7 +2007,6 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 		if (!same_creds(&conf->cl_cred, &unconf->cl_cred))
 			status = nfserr_clid_inuse;
 		else {
-			atomic_set(&conf->cl_cb_set, 0);
 			nfsd4_change_callback(conf, &unconf->cl_cb_conn);
 			nfsd4_probe_callback(conf);
 			expire_client(unconf);
@@ -1964,7 +2035,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 			unsigned int hash =
 				clientstr_hashval(unconf->cl_recdir);
 			conf = find_confirmed_client_by_str(unconf->cl_recdir,
-							    hash, false);
+							    hash);
 			if (conf) {
 				nfsd4_remove_clid_dir(conf);
 				expire_client(conf);
@@ -2300,41 +2371,6 @@ void nfsd_break_deleg_cb(struct file_lock *fl)
 	nfsd4_cb_recall(dp);
 }
 
-/*
- * The file_lock is being reapd.
- *
- * Called by locks_free_lock() with lock_flocks() held.
- */
-static
-void nfsd_release_deleg_cb(struct file_lock *fl)
-{
-	struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
-
-	dprintk("NFSD nfsd_release_deleg_cb: fl %p dp %p dl_count %d\n", fl,dp, atomic_read(&dp->dl_count));
-
-	if (!(fl->fl_flags & FL_LEASE) || !dp)
-		return;
-	dp->dl_flock = NULL;
-}
-
-/*
- * Called from setlease() with lock_flocks() held
- */
-static
-int nfsd_same_client_deleg_cb(struct file_lock *onlist, struct file_lock *try)
-{
-	struct nfs4_delegation *onlistd =
-		(struct nfs4_delegation *)onlist->fl_owner;
-	struct nfs4_delegation *tryd =
-		(struct nfs4_delegation *)try->fl_owner;
-
-	if (onlist->fl_lmops != try->fl_lmops)
-		return 0;
-
-	return onlistd->dl_client == tryd->dl_client;
-}
-
-
 static
 int nfsd_change_deleg_cb(struct file_lock **onlist, int arg)
 {
@@ -2346,8 +2382,6 @@ int nfsd_change_deleg_cb(struct file_lock **onlist, int arg)
 
 static const struct lock_manager_operations nfsd_lease_mng_ops = {
 	.fl_break = nfsd_break_deleg_cb,
-	.fl_release_private = nfsd_release_deleg_cb,
-	.fl_mylease = nfsd_same_client_deleg_cb,
 	.fl_change = nfsd_change_deleg_cb,
 };
 
@@ -2514,8 +2548,6 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file
 	if (!fp->fi_fds[oflag]) {
 		status = nfsd_open(rqstp, cur_fh, S_IFREG, access,
 			&fp->fi_fds[oflag]);
-		if (status == nfserr_dropit)
-			status = nfserr_jukebox;
 		if (status)
 			return status;
 	}
@@ -2596,6 +2628,19 @@ nfs4_set_claim_prev(struct nfsd4_open *open)
 	open->op_stateowner->so_client->cl_firststate = 1;
 }
 
+/* Should we give out recallable state?: */
+static bool nfsd4_cb_channel_good(struct nfs4_client *clp)
+{
+	if (clp->cl_cb_state == NFSD4_CB_UP)
+		return true;
+	/*
+	 * In the sessions case, since we don't have to establish a
+	 * separate connection for callbacks, we assume it's OK
+	 * until we hear otherwise:
+	 */
+	return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
+}
+
 /*
  * Attempt to hand out a delegation.
  */
@@ -2604,10 +2649,11 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
 {
 	struct nfs4_delegation *dp;
 	struct nfs4_stateowner *sop = stp->st_stateowner;
-	int cb_up = atomic_read(&sop->so_client->cl_cb_set);
+	int cb_up;
 	struct file_lock *fl;
 	int status, flag = 0;
 
+	cb_up = nfsd4_cb_channel_good(sop->so_client);
 	flag = NFS4_OPEN_DELEGATE_NONE;
 	open->op_recall = 0;
 	switch (open->op_claim_type) {
@@ -2655,7 +2701,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
 	dp->dl_flock = fl;
 
 	/* vfs_setlease checks to see if delegation should be handed out.
-	 * the lock_manager callbacks fl_mylease and fl_change are used
+	 * the lock_manager callback fl_change is used
 	 */
 	if ((status = vfs_setlease(fl->fl_file, fl->fl_type, &fl))) {
 		dprintk("NFSD: setlease failed [%d], no delegation\n", status);
@@ -2794,7 +2840,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	renew_client(clp);
 	status = nfserr_cb_path_down;
 	if (!list_empty(&clp->cl_delegations)
-			&& !atomic_read(&clp->cl_cb_set))
+			&& clp->cl_cb_state != NFSD4_CB_UP)
 		goto out;
 	status = nfs_ok;
 out:
@@ -3081,9 +3127,10 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
 		if (status)
 			goto out;
 		renew_client(dp->dl_client);
-		if (filpp)
+		if (filpp) {
 			*filpp = find_readable_file(dp->dl_file);
-		BUG_ON(!*filpp);
+			BUG_ON(!*filpp);
+		}
 	} else { /* open or lock stateid */
 		stp = find_stateid(stateid, flags);
 		if (!stp)
@@ -4107,7 +4154,7 @@ nfs4_has_reclaimed_state(const char *name, bool use_exchange_id)
 	unsigned int strhashval = clientstr_hashval(name);
 	struct nfs4_client *clp;
 
-	clp = find_confirmed_client_by_str(name, strhashval, use_exchange_id);
+	clp = find_confirmed_client_by_str(name, strhashval);
 	return clp ? 1 : 0;
 }
 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index f35a94a04026..956629b9cdc9 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -44,13 +44,14 @@
 #include <linux/namei.h>
 #include <linux/statfs.h>
 #include <linux/utsname.h>
-#include <linux/nfsd_idmap.h>
-#include <linux/nfs4_acl.h>
 #include <linux/sunrpc/svcauth_gss.h>
 
+#include "idmap.h"
+#include "acl.h"
 #include "xdr4.h"
 #include "vfs.h"
 
+
 #define NFSDDBG_FACILITY		NFSDDBG_XDR
 
 /*
@@ -288,17 +289,17 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 			len += XDR_QUADLEN(dummy32) << 2;
 			READMEM(buf, dummy32);
 			ace->whotype = nfs4_acl_get_whotype(buf, dummy32);
-			host_err = 0;
+			status = nfs_ok;
 			if (ace->whotype != NFS4_ACL_WHO_NAMED)
 				ace->who = 0;
 			else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
-				host_err = nfsd_map_name_to_gid(argp->rqstp,
+				status = nfsd_map_name_to_gid(argp->rqstp,
 						buf, dummy32, &ace->who);
 			else
-				host_err = nfsd_map_name_to_uid(argp->rqstp,
+				status = nfsd_map_name_to_uid(argp->rqstp,
 						buf, dummy32, &ace->who);
-			if (host_err)
-				goto out_nfserr;
+			if (status)
+				return status;
 		}
 	} else
 		*acl = NULL;
@@ -420,6 +421,21 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access
 	DECODE_TAIL;
 }
 
+static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts)
+{
+	DECODE_HEAD;
+	u32 dummy;
+
+	READ_BUF(NFS4_MAX_SESSIONID_LEN + 8);
+	COPYMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
+	READ32(bcts->dir);
+	/* XXX: Perhaps Tom Tucker could help us figure out how we
+	 * should be using ctsa_use_conn_in_rdma_mode: */
+	READ32(dummy);
+
+	DECODE_TAIL;
+}
+
 static __be32
 nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close)
 {
@@ -847,6 +863,17 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp,
 }
 
 static __be32
+nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp,
+		     struct nfsd4_secinfo_no_name *sin)
+{
+	DECODE_HEAD;
+
+	READ_BUF(4);
+	READ32(sin->sin_style);
+	DECODE_TAIL;
+}
+
+static __be32
 nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr)
 {
 	__be32 status;
@@ -1005,7 +1032,7 @@ static __be32
 nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 			 struct nfsd4_exchange_id *exid)
 {
-	int dummy;
+	int dummy, tmp;
 	DECODE_HEAD;
 
 	READ_BUF(NFS4_VERIFIER_SIZE);
@@ -1053,15 +1080,23 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 
 		/* ssp_hash_algs<> */
 		READ_BUF(4);
-		READ32(dummy);
-		READ_BUF(dummy);
-		p += XDR_QUADLEN(dummy);
+		READ32(tmp);
+		while (tmp--) {
+			READ_BUF(4);
+			READ32(dummy);
+			READ_BUF(dummy);
+			p += XDR_QUADLEN(dummy);
+		}
 
 		/* ssp_encr_algs<> */
 		READ_BUF(4);
-		READ32(dummy);
-		READ_BUF(dummy);
-		p += XDR_QUADLEN(dummy);
+		READ32(tmp);
+		while (tmp--) {
+			READ_BUF(4);
+			READ32(dummy);
+			READ_BUF(dummy);
+			p += XDR_QUADLEN(dummy);
+		}
 
 		/* ssp_window and ssp_num_gss_handles */
 		READ_BUF(8);
@@ -1339,7 +1374,7 @@ static nfsd4_dec nfsd41_dec_ops[] = {
 
 	/* new operations for NFSv4.1 */
 	[OP_BACKCHANNEL_CTL]	= (nfsd4_dec)nfsd4_decode_notsupp,
-	[OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session,
 	[OP_EXCHANGE_ID]	= (nfsd4_dec)nfsd4_decode_exchange_id,
 	[OP_CREATE_SESSION]	= (nfsd4_dec)nfsd4_decode_create_session,
 	[OP_DESTROY_SESSION]	= (nfsd4_dec)nfsd4_decode_destroy_session,
@@ -1350,7 +1385,7 @@ static nfsd4_dec nfsd41_dec_ops[] = {
 	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_notsupp,
-	[OP_SECINFO_NO_NAME]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_SECINFO_NO_NAME]	= (nfsd4_dec)nfsd4_decode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_dec)nfsd4_decode_sequence,
 	[OP_SET_SSV]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_TEST_STATEID]	= (nfsd4_dec)nfsd4_decode_notsupp,
@@ -2309,8 +2344,6 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
 	case nfserr_resource:
 		nfserr = nfserr_toosmall;
 		goto fail;
-	case nfserr_dropit:
-		goto fail;
 	case nfserr_noent:
 		goto skip_entry;
 	default:
@@ -2365,6 +2398,21 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
 	return nfserr;
 }
 
+static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts)
+{
+	__be32 *p;
+
+	if (!nfserr) {
+		RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 8);
+		WRITEMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
+		WRITE32(bcts->dir);
+		/* XXX: ? */
+		WRITE32(0);
+		ADJUST_ARGS();
+	}
+	return nfserr;
+}
+
 static __be32
 nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close)
 {
@@ -2826,11 +2874,10 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
 }
 
 static __be32
-nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
-		     struct nfsd4_secinfo *secinfo)
+nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
+			 __be32 nfserr,struct svc_export *exp)
 {
 	int i = 0;
-	struct svc_export *exp = secinfo->si_exp;
 	u32 nflavs;
 	struct exp_flavor_info *flavs;
 	struct exp_flavor_info def_flavs[2];
@@ -2892,6 +2939,20 @@ out:
 	return nfserr;
 }
 
+static __be32
+nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
+		     struct nfsd4_secinfo *secinfo)
+{
+	return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->si_exp);
+}
+
+static __be32
+nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
+		     struct nfsd4_secinfo_no_name *secinfo)
+{
+	return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->sin_exp);
+}
+
 /*
  * The SETATTR encode routine is special -- it always encodes a bitmap,
  * regardless of the error status.
@@ -3076,13 +3137,9 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr,
 	WRITE32(seq->seqid);
 	WRITE32(seq->slotid);
 	WRITE32(seq->maxslots);
-	/*
-	 * FIXME: for now:
-	 *   target_maxslots = maxslots
-	 *   status_flags = 0
-	 */
+	/* For now: target_maxslots = maxslots */
 	WRITE32(seq->maxslots);
-	WRITE32(0);
+	WRITE32(seq->status_flags);
 
 	ADJUST_ARGS();
 	resp->cstate.datap = p; /* DRC cache data pointer */
@@ -3143,7 +3200,7 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 
 	/* NFSv4.1 operations */
 	[OP_BACKCHANNEL_CTL]	= (nfsd4_enc)nfsd4_encode_noop,
-	[OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_noop,
+	[OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_bind_conn_to_session,
 	[OP_EXCHANGE_ID]	= (nfsd4_enc)nfsd4_encode_exchange_id,
 	[OP_CREATE_SESSION]	= (nfsd4_enc)nfsd4_encode_create_session,
 	[OP_DESTROY_SESSION]	= (nfsd4_enc)nfsd4_encode_destroy_session,
@@ -3154,7 +3211,7 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_noop,
-	[OP_SECINFO_NO_NAME]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_SECINFO_NO_NAME]	= (nfsd4_enc)nfsd4_encode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_enc)nfsd4_encode_sequence,
 	[OP_SET_SSV]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_TEST_STATEID]	= (nfsd4_enc)nfsd4_encode_noop,
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 4514ebbee4d6..33b3e2b06779 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -8,12 +8,12 @@
 #include <linux/namei.h>
 #include <linux/ctype.h>
 
-#include <linux/nfsd_idmap.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfsd/syscall.h>
 #include <linux/lockd/lockd.h>
 #include <linux/sunrpc/clnt.h>
 
+#include "idmap.h"
 #include "nfsd.h"
 #include "cache.h"
 
@@ -127,6 +127,7 @@ static ssize_t nfsctl_transaction_write(struct file *file, const char __user *bu
 
 static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos)
 {
+#ifdef CONFIG_NFSD_DEPRECATED
 	static int warned;
 	if (file->f_dentry->d_name.name[0] == '.' && !warned) {
 		printk(KERN_INFO
@@ -135,6 +136,7 @@ static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size
 		       current->comm, file->f_dentry->d_name.name);
 		warned = 1;
 	}
+#endif
 	if (! file->private_data) {
 		/* An attempt to read a transaction file without writing
 		 * causes a 0-byte write so that the file can return
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 6b641cf2c19a..7ecfa2420307 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -158,6 +158,7 @@ void		nfsd_lockd_shutdown(void);
 #define	nfserr_attrnotsupp	cpu_to_be32(NFSERR_ATTRNOTSUPP)
 #define	nfserr_bad_xdr		cpu_to_be32(NFSERR_BAD_XDR)
 #define	nfserr_openmode		cpu_to_be32(NFSERR_OPENMODE)
+#define	nfserr_badowner		cpu_to_be32(NFSERR_BADOWNER)
 #define	nfserr_locks_held	cpu_to_be32(NFSERR_LOCKS_HELD)
 #define	nfserr_op_illegal	cpu_to_be32(NFSERR_OP_ILLEGAL)
 #define	nfserr_grace		cpu_to_be32(NFSERR_GRACE)
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 08e17264784b..e15dc45fc5ec 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -735,9 +735,9 @@ nfserrno (int errno)
 		{ nfserr_stale, -ESTALE },
 		{ nfserr_jukebox, -ETIMEDOUT },
 		{ nfserr_jukebox, -ERESTARTSYS },
-		{ nfserr_dropit, -EAGAIN },
-		{ nfserr_dropit, -ENOMEM },
-		{ nfserr_badname, -ESRCH },
+		{ nfserr_jukebox, -EAGAIN },
+		{ nfserr_jukebox, -EWOULDBLOCK },
+		{ nfserr_jukebox, -ENOMEM },
 		{ nfserr_io, -ETXTBSY },
 		{ nfserr_notsupp, -EOPNOTSUPP },
 		{ nfserr_toosmall, -ETOOSMALL },
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 2bae1d86f5f2..18743c4d8bca 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -608,7 +608,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	/* Now call the procedure handler, and encode NFS status. */
 	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
-	if (nfserr == nfserr_dropit) {
+	if (nfserr == nfserr_dropit || rqstp->rq_dropme) {
 		dprintk("nfsd: Dropping request; may be revisited later\n");
 		nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
 		return 0;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 39adc27b0685..3074656ba7bf 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -68,10 +68,12 @@ typedef struct {
 struct nfsd4_callback {
 	void *cb_op;
 	struct nfs4_client *cb_clp;
+	struct list_head cb_per_client;
 	u32 cb_minorversion;
 	struct rpc_message cb_msg;
 	const struct rpc_call_ops *cb_ops;
 	struct work_struct cb_work;
+	bool cb_done;
 };
 
 struct nfs4_delegation {
@@ -81,6 +83,7 @@ struct nfs4_delegation {
 	atomic_t		dl_count;       /* ref count */
 	struct nfs4_client	*dl_client;
 	struct nfs4_file	*dl_file;
+	struct file		*dl_vfs_file;
 	struct file_lock	*dl_flock;
 	u32			dl_type;
 	time_t			dl_time;
@@ -95,6 +98,7 @@ struct nfs4_delegation {
 struct nfs4_cb_conn {
 	/* SETCLIENTID info */
 	struct sockaddr_storage	cb_addr;
+	struct sockaddr_storage	cb_saddr;
 	size_t			cb_addrlen;
 	u32                     cb_prog; /* used only in 4.0 case;
 					    per-session otherwise */
@@ -146,6 +150,11 @@ struct nfsd4_create_session {
 	u32				gid;
 };
 
+struct nfsd4_bind_conn_to_session {
+	struct nfs4_sessionid		sessionid;
+	u32				dir;
+};
+
 /* The single slot clientid cache structure */
 struct nfsd4_clid_slot {
 	u32				sl_seqid;
@@ -235,9 +244,13 @@ struct nfs4_client {
 	unsigned long		cl_cb_flags;
 	struct rpc_clnt		*cl_cb_client;
 	u32			cl_cb_ident;
-	atomic_t		cl_cb_set;
+#define NFSD4_CB_UP		0
+#define NFSD4_CB_UNKNOWN	1
+#define NFSD4_CB_DOWN		2
+	int			cl_cb_state;
 	struct nfsd4_callback	cl_cb_null;
 	struct nfsd4_session	*cl_cb_session;
+	struct list_head	cl_callbacks; /* list of in-progress callbacks */
 
 	/* for all client information that callback code might need: */
 	spinlock_t		cl_lock;
@@ -454,6 +467,7 @@ extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
 extern void nfs4_free_stateowner(struct kref *kref);
 extern int set_callback_cred(void);
 extern void nfsd4_probe_callback(struct nfs4_client *clp);
+extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
 extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
 extern void nfsd4_do_callback_rpc(struct work_struct *);
 extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 230b79fbf005..641117f2188d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1,4 +1,3 @@
-#define MSNFS	/* HACK HACK */
 /*
  * File operations used by nfsd. Some of these have been ripped from
  * other parts of the kernel because they weren't exported, others
@@ -35,8 +34,8 @@
 #endif /* CONFIG_NFSD_V3 */
 
 #ifdef CONFIG_NFSD_V4
-#include <linux/nfs4_acl.h>
-#include <linux/nfsd_idmap.h>
+#include "acl.h"
+#include "idmap.h"
 #endif /* CONFIG_NFSD_V4 */
 
 #include "nfsd.h"
@@ -88,8 +87,9 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 			    .dentry = dget(dentry)};
 	int err = 0;
 
-	while (d_mountpoint(path.dentry) && follow_down(&path))
-		;
+	err = follow_down(&path, false);
+	if (err < 0)
+		goto out;
 
 	exp2 = rqst_exp_get_by_name(rqstp, &path);
 	if (IS_ERR(exp2)) {
@@ -273,6 +273,13 @@ out:
 	return err;
 }
 
+static int nfsd_break_lease(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+	return break_lease(inode, O_WRONLY | O_NONBLOCK);
+}
+
 /*
  * Commit metadata changes to stable storage.
  */
@@ -375,16 +382,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 				goto out;
 		}
 
-		/*
-		 * If we are changing the size of the file, then
-		 * we need to break all leases.
-		 */
-		host_err = break_lease(inode, O_WRONLY | O_NONBLOCK);
-		if (host_err == -EWOULDBLOCK)
-			host_err = -ETIMEDOUT;
-		if (host_err) /* ENOMEM or EWOULDBLOCK */
-			goto out_nfserr;
-
 		host_err = get_write_access(inode);
 		if (host_err)
 			goto out_nfserr;
@@ -425,7 +422,11 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 
 	err = nfserr_notsync;
 	if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
+		host_err = nfsd_break_lease(inode);
+		if (host_err)
+			goto out_nfserr;
 		fh_lock(fhp);
+
 		host_err = notify_change(dentry, iap);
 		err = nfserrno(host_err);
 		fh_unlock(fhp);
@@ -752,8 +753,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	 */
 	if (!(access & NFSD_MAY_NOT_BREAK_LEASE))
 		host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0));
-	if (host_err == -EWOULDBLOCK)
-		host_err = -ETIMEDOUT;
 	if (host_err) /* NOMEM or WOULDBLOCK */
 		goto out_nfserr;
 
@@ -874,15 +873,6 @@ static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
 	return __splice_from_pipe(pipe, sd, nfsd_splice_actor);
 }
 
-static inline int svc_msnfs(struct svc_fh *ffhp)
-{
-#ifdef MSNFS
-	return (ffhp->fh_export->ex_flags & NFSEXP_MSNFS);
-#else
-	return 0;
-#endif
-}
-
 static __be32
 nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
               loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
@@ -895,9 +885,6 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	err = nfserr_perm;
 	inode = file->f_path.dentry->d_inode;
 
-	if (svc_msnfs(fhp) && !lock_may_read(inode, offset, *count))
-		goto out;
-
 	if (file->f_op->splice_read && rqstp->rq_splice_ok) {
 		struct splice_desc sd = {
 			.len		= 0,
@@ -922,7 +909,6 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 		fsnotify_access(file);
 	} else 
 		err = nfserrno(host_err);
-out:
 	return err;
 }
 
@@ -987,14 +973,6 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	int			stable = *stablep;
 	int			use_wgather;
 
-#ifdef MSNFS
-	err = nfserr_perm;
-
-	if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
-		(!lock_may_write(file->f_path.dentry->d_inode, offset, *cnt)))
-		goto out;
-#endif
-
 	dentry = file->f_path.dentry;
 	inode = dentry->d_inode;
 	exp   = fhp->fh_export;
@@ -1045,7 +1023,6 @@ out_nfserr:
 		err = 0;
 	else
 		err = nfserrno(host_err);
-out:
 	return err;
 }
 
@@ -1665,6 +1642,12 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		err = nfserrno(host_err);
 		goto out_dput;
 	}
+	err = nfserr_noent;
+	if (!dold->d_inode)
+		goto out_drop_write;
+	host_err = nfsd_break_lease(dold->d_inode);
+	if (host_err)
+		goto out_drop_write;
 	host_err = vfs_link(dold, dirp, dnew);
 	if (!host_err) {
 		err = nfserrno(commit_metadata(ffhp));
@@ -1676,6 +1659,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		else
 			err = nfserrno(host_err);
 	}
+out_drop_write:
 	mnt_drop_write(tfhp->fh_export->ex_path.mnt);
 out_dput:
 	dput(dnew);
@@ -1750,12 +1734,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	if (ndentry == trap)
 		goto out_dput_new;
 
-	if (svc_msnfs(ffhp) &&
-		((odentry->d_count > 1) || (ndentry->d_count > 1))) {
-			host_err = -EPERM;
-			goto out_dput_new;
-	}
-
 	host_err = -EXDEV;
 	if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt)
 		goto out_dput_new;
@@ -1763,15 +1741,17 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	if (host_err)
 		goto out_dput_new;
 
+	host_err = nfsd_break_lease(odentry->d_inode);
+	if (host_err)
+		goto out_drop_write;
 	host_err = vfs_rename(fdir, odentry, tdir, ndentry);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);
 		if (!host_err)
 			host_err = commit_metadata(ffhp);
 	}
-
+out_drop_write:
 	mnt_drop_write(ffhp->fh_export->ex_path.mnt);
-
  out_dput_new:
 	dput(ndentry);
  out_dput_old:
@@ -1834,18 +1814,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (host_err)
 		goto out_nfserr;
 
-	if (type != S_IFDIR) { /* It's UNLINK */
-#ifdef MSNFS
-		if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
-			(rdentry->d_count > 1)) {
-			host_err = -EPERM;
-		} else
-#endif
+	host_err = nfsd_break_lease(rdentry->d_inode);
+	if (host_err)
+		goto out_put;
+	if (type != S_IFDIR)
 		host_err = vfs_unlink(dirp, rdentry);
-	} else { /* It's RMDIR */
+	else
 		host_err = vfs_rmdir(dirp, rdentry);
-	}
-
+out_put:
 	dput(rdentry);
 
 	if (!host_err)
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 60fce3dc5cb5..366401e1a536 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -311,6 +311,11 @@ struct nfsd4_secinfo {
 	struct svc_export *si_exp;			/* response */
 };
 
+struct nfsd4_secinfo_no_name {
+	u32 sin_style;					/* request */
+	struct svc_export *sin_exp;			/* response */
+};
+
 struct nfsd4_setattr {
 	stateid_t	sa_stateid;         /* request */
 	u32		sa_bmval[3];        /* request */
@@ -373,8 +378,8 @@ struct nfsd4_sequence {
 	u32			cachethis;		/* request */
 #if 0
 	u32			target_maxslots;	/* response */
-	u32			status_flags;		/* response */
 #endif /* not yet */
+	u32			status_flags;		/* response */
 };
 
 struct nfsd4_destroy_session {
@@ -422,6 +427,7 @@ struct nfsd4_op {
 
 		/* NFSv4.1 */
 		struct nfsd4_exchange_id	exchange_id;
+		struct nfsd4_bind_conn_to_session bind_conn_to_session;
 		struct nfsd4_create_session	create_session;
 		struct nfsd4_destroy_session	destroy_session;
 		struct nfsd4_sequence		sequence;
@@ -518,6 +524,7 @@ extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
 		struct nfsd4_sequence *seq);
 extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, struct nfsd4_exchange_id *);
+extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *);
 extern __be32 nfsd4_create_session(struct svc_rqst *,
 		struct nfsd4_compound_state *,
 		struct nfsd4_create_session *);
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 0994f6a76c07..58fd707174e1 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -704,7 +704,8 @@ skip_mount_setup:
 	sbp[0]->s_state =
 		cpu_to_le16(le16_to_cpu(sbp[0]->s_state) & ~NILFS_VALID_FS);
 	/* synchronize sbp[1] with sbp[0] */
-	memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
+	if (sbp[1])
+		memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
 	return nilfs_commit_super(sbi, NILFS_SB_COMMIT_ALL);
 }
 
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index b572b6727181..326e7475a22a 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -1,7 +1,7 @@
 /**
  * mft.c - NTFS kernel mft record operations. Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2006 Anton Altaparmakov
+ * Copyright (c) 2001-2011 Anton Altaparmakov and Tuxera Inc.
  * Copyright (c) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -2576,6 +2576,8 @@ mft_rec_already_initialized:
 	flush_dcache_page(page);
 	SetPageUptodate(page);
 	if (base_ni) {
+		MFT_RECORD *m_tmp;
+
 		/*
 		 * Setup the base mft record in the extent mft record.  This
 		 * completes initialization of the allocated extent mft record
@@ -2588,11 +2590,11 @@ mft_rec_already_initialized:
 		 * attach it to the base inode @base_ni and map, pin, and lock
 		 * its, i.e. the allocated, mft record.
 		 */
-		m = map_extent_mft_record(base_ni, bit, &ni);
-		if (IS_ERR(m)) {
+		m_tmp = map_extent_mft_record(base_ni, bit, &ni);
+		if (IS_ERR(m_tmp)) {
 			ntfs_error(vol->sb, "Failed to map allocated extent "
 					"mft record 0x%llx.", (long long)bit);
-			err = PTR_ERR(m);
+			err = PTR_ERR(m_tmp);
 			/* Set the mft record itself not in use. */
 			m->flags &= cpu_to_le16(
 					~le16_to_cpu(MFT_RECORD_IN_USE));
@@ -2603,6 +2605,7 @@ mft_rec_already_initialized:
 			ntfs_unmap_page(page);
 			goto undo_mftbmp_alloc;
 		}
+		BUG_ON(m != m_tmp);
 		/*
 		 * Make sure the allocated mft record is written out to disk.
 		 * No need to set the inode dirty because the caller is going
diff --git a/fs/ocfs2/Kconfig b/fs/ocfs2/Kconfig
index ab152c00cd3a..77a8de5f7119 100644
--- a/fs/ocfs2/Kconfig
+++ b/fs/ocfs2/Kconfig
@@ -1,7 +1,6 @@
 config OCFS2_FS
 	tristate "OCFS2 file system support"
-	depends on NET && SYSFS
-	select CONFIGFS_FS
+	depends on NET && SYSFS && CONFIGFS_FS
 	select JBD2
 	select CRC32
 	select QUOTA
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 63e3fca266e0..a6651956482e 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1989,20 +1989,20 @@ int ocfs2_change_file_space(struct file *file, unsigned int cmd,
 	return __ocfs2_change_file_space(file, inode, file->f_pos, cmd, sr, 0);
 }
 
-static long ocfs2_fallocate(struct inode *inode, int mode, loff_t offset,
+static long ocfs2_fallocate(struct file *file, int mode, loff_t offset,
 			    loff_t len)
 {
+	struct inode *inode = file->f_path.dentry->d_inode;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct ocfs2_space_resv sr;
 	int change_size = 1;
 	int cmd = OCFS2_IOC_RESVSP64;
 
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
 	if (!ocfs2_writes_unwritten_extents(osb))
 		return -EOPNOTSUPP;
 
-	if (S_ISDIR(inode->i_mode))
-		return -ENODEV;
-
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		change_size = 0;
 
@@ -2610,7 +2610,6 @@ const struct inode_operations ocfs2_file_iops = {
 	.getxattr	= generic_getxattr,
 	.listxattr	= ocfs2_listxattr,
 	.removexattr	= generic_removexattr,
-	.fallocate	= ocfs2_fallocate,
 	.fiemap		= ocfs2_fiemap,
 };
 
@@ -2642,6 +2641,7 @@ const struct file_operations ocfs2_fops = {
 	.flock		= ocfs2_flock,
 	.splice_read	= ocfs2_file_splice_read,
 	.splice_write	= ocfs2_file_splice_write,
+	.fallocate	= ocfs2_fallocate,
 };
 
 const struct file_operations ocfs2_dops = {
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 06d1f749ca89..38f986d2447e 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -993,8 +993,7 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
 }
 
 /* Handle quota on quotactl */
-static int ocfs2_quota_on(struct super_block *sb, int type, int format_id,
-			  char *path)
+static int ocfs2_quota_on(struct super_block *sb, int type, int format_id)
 {
 	unsigned int feature[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
 					     OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
@@ -1013,7 +1012,7 @@ static int ocfs2_quota_off(struct super_block *sb, int type)
 }
 
 static const struct quotactl_ops ocfs2_quotactl_ops = {
-	.quota_on	= ocfs2_quota_on,
+	.quota_on_meta	= ocfs2_quota_on,
 	.quota_off	= ocfs2_quota_off,
 	.quota_sync	= dquot_quota_sync,
 	.get_info	= dquot_get_dqinfo,
diff --git a/fs/open.c b/fs/open.c
index 5b6ef7e2859e..5a2c6ebc22b5 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -255,10 +255,10 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
 		return -EFBIG;
 
-	if (!inode->i_op->fallocate)
+	if (!file->f_op->fallocate)
 		return -EOPNOTSUPP;
 
-	return inode->i_op->fallocate(inode, mode, offset, len);
+	return file->f_op->fallocate(file, mode, offset, len);
 }
 
 SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len)
@@ -790,6 +790,8 @@ struct file *nameidata_to_filp(struct nameidata *nd)
 
 	/* Pick up the filp from the open intent */
 	filp = nd->intent.open.file;
+	nd->intent.open.file = NULL;
+
 	/* Has the filesystem initialised the file for us? */
 	if (filp->f_path.dentry == NULL) {
 		path_get(&nd->path);
diff --git a/fs/pipe.c b/fs/pipe.c
index e2e95fb46a1e..da42f7db50de 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -441,7 +441,7 @@ redo:
 			break;
 		}
 		if (do_wakeup) {
-			wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT);
+			wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT | POLLWRNORM);
  			kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 		}
 		pipe_wait(pipe);
@@ -450,7 +450,7 @@ redo:
 
 	/* Signal writers asynchronously that there is more room. */
 	if (do_wakeup) {
-		wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT);
+		wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT | POLLWRNORM);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
 	if (ret > 0)
@@ -612,7 +612,7 @@ redo2:
 			break;
 		}
 		if (do_wakeup) {
-			wake_up_interruptible_sync_poll(&pipe->wait, POLLIN);
+			wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM);
 			kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 			do_wakeup = 0;
 		}
@@ -623,7 +623,7 @@ redo2:
 out:
 	mutex_unlock(&inode->i_mutex);
 	if (do_wakeup) {
-		wake_up_interruptible_sync_poll(&pipe->wait, POLLIN);
+		wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM);
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 	}
 	if (ret > 0)
@@ -715,7 +715,7 @@ pipe_release(struct inode *inode, int decr, int decw)
 	if (!pipe->readers && !pipe->writers) {
 		free_pipe_info(inode);
 	} else {
-		wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLOUT);
+		wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM | POLLERR | POLLHUP);
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
@@ -1292,7 +1292,7 @@ static int __init init_pipe_fs(void)
 static void __exit exit_pipe_fs(void)
 {
 	unregister_filesystem(&pipe_fs_type);
-	mntput_long(pipe_mnt);
+	mntput(pipe_mnt);
 }
 
 fs_initcall(init_pipe_fs);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 39df95a0ec25..b1cf6bf4b41d 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -22,6 +22,7 @@
 
 #include <linux/errno.h>
 
+EXPORT_SYMBOL(posix_acl_init);
 EXPORT_SYMBOL(posix_acl_alloc);
 EXPORT_SYMBOL(posix_acl_clone);
 EXPORT_SYMBOL(posix_acl_valid);
@@ -32,6 +33,16 @@ EXPORT_SYMBOL(posix_acl_chmod_masq);
 EXPORT_SYMBOL(posix_acl_permission);
 
 /*
+ * Init a fresh posix_acl
+ */
+void
+posix_acl_init(struct posix_acl *acl, int count)
+{
+	atomic_set(&acl->a_refcount, 1);
+	acl->a_count = count;
+}
+
+/*
  * Allocate a new ACL with the specified number of entries.
  */
 struct posix_acl *
@@ -40,10 +51,8 @@ posix_acl_alloc(int count, gfp_t flags)
 	const size_t size = sizeof(struct posix_acl) +
 	                    count * sizeof(struct posix_acl_entry);
 	struct posix_acl *acl = kmalloc(size, flags);
-	if (acl) {
-		atomic_set(&acl->a_refcount, 1);
-		acl->a_count = count;
-	}
+	if (acl)
+		posix_acl_init(acl, count);
 	return acl;
 }
 
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 6a0068841d96..15af6222f8a4 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -1,5 +1,5 @@
 config PROC_FS
-	bool "/proc file system support" if EMBEDDED
+	bool "/proc file system support" if EXPERT
 	default y
 	help
 	  This is a virtual file system providing information about the status
@@ -40,7 +40,7 @@ config PROC_VMCORE
         Exports the dump image of crashed kernel in ELF format.
 
 config PROC_SYSCTL
-	bool "Sysctl support (/proc/sys)" if EMBEDDED
+	bool "Sysctl support (/proc/sys)" if EXPERT
 	depends on PROC_FS
 	select SYSCTL
 	default y
@@ -61,7 +61,7 @@ config PROC_SYSCTL
 config PROC_PAGE_MONITOR
  	default y
 	depends on PROC_FS && MMU
-	bool "Enable /proc page monitoring" if EMBEDDED
+	bool "Enable /proc page monitoring" if EXPERT
  	help
 	  Various /proc files exist to monitor process memory utilization:
 	  /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 93f1cdd5d3d7..9d096e82b201 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1151,7 +1151,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 		goto err_task_lock;
 	}
 
-	if (oom_score_adj < task->signal->oom_score_adj &&
+	if (oom_score_adj < task->signal->oom_score_adj_min &&
 			!capable(CAP_SYS_RESOURCE)) {
 		err = -EACCES;
 		goto err_sighand;
@@ -1164,6 +1164,8 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 			atomic_dec(&task->mm->oom_disable_count);
 	}
 	task->signal->oom_score_adj = oom_score_adj;
+	if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
+		task->signal->oom_score_adj_min = oom_score_adj;
 	/*
 	 * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is
 	 * always attainable.
diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c
index eafc22ab1fdd..b701eaa482bf 100644
--- a/fs/proc/consoles.c
+++ b/fs/proc/consoles.c
@@ -67,7 +67,7 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 	struct console *con;
 	loff_t off = 0;
 
-	acquire_console_sem();
+	console_lock();
 	for_each_console(con)
 		if (off++ == *pos)
 			break;
@@ -84,7 +84,7 @@ static void *c_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void c_stop(struct seq_file *m, void *v)
 {
-	release_console_sem();
+	console_unlock();
 }
 
 static const struct seq_operations consoles_op = {
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index a65239cfd97e..ed257d141568 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -101,6 +101,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #ifdef CONFIG_MEMORY_FAILURE
 		"HardwareCorrupted: %5lu kB\n"
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		"AnonHugePages:  %8lu kB\n"
+#endif
 		,
 		K(i.totalram),
 		K(i.freeram),
@@ -128,7 +131,12 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		K(i.freeswap),
 		K(global_page_state(NR_FILE_DIRTY)),
 		K(global_page_state(NR_WRITEBACK)),
-		K(global_page_state(NR_ANON_PAGES)),
+		K(global_page_state(NR_ANON_PAGES)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		  + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
+		  HPAGE_PMD_NR
+#endif
+		  ),
 		K(global_page_state(NR_FILE_MAPPED)),
 		K(global_page_state(NR_SHMEM)),
 		K(global_page_state(NR_SLAB_RECLAIMABLE) +
@@ -151,6 +159,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #ifdef CONFIG_MEMORY_FAILURE
 		,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10)
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
+		   HPAGE_PMD_NR)
+#endif
 		);
 
 	hugetlb_report_meminfo(m);
diff --git a/fs/proc/page.c b/fs/proc/page.c
index b06c674624e6..6d8e6a9e93ab 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -116,15 +116,17 @@ u64 stable_page_flags(struct page *page)
 	if (PageHuge(page))
 		u |= 1 << KPF_HUGE;
 
-	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
-
 	/*
-	 * Caveats on high order pages:
-	 * PG_buddy will only be set on the head page; SLUB/SLQB do the same
-	 * for PG_slab; SLOB won't set PG_slab at all on compound pages.
+	 * Caveats on high order pages: page->_count will only be set
+	 * -1 on the head page; SLUB/SLQB do the same for PG_slab;
+	 * SLOB won't set PG_slab at all on compound pages.
 	 */
+	if (PageBuddy(page))
+		u |= 1 << KPF_BUDDY;
+
+	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
+
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
-	u |= kpf_copy_bit(k, KPF_BUDDY,		PG_buddy);
 
 	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
 	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c3755bd8dd3e..60b914860f81 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -418,7 +418,8 @@ static int show_smap(struct seq_file *m, void *v)
 		   "Anonymous:      %8lu kB\n"
 		   "Swap:           %8lu kB\n"
 		   "KernelPageSize: %8lu kB\n"
-		   "MMUPageSize:    %8lu kB\n",
+		   "MMUPageSize:    %8lu kB\n"
+		   "Locked:         %8lu kB\n",
 		   (vma->vm_end - vma->vm_start) >> 10,
 		   mss.resident >> 10,
 		   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
@@ -430,7 +431,9 @@ static int show_smap(struct seq_file *m, void *v)
 		   mss.anonymous >> 10,
 		   mss.swap >> 10,
 		   vma_kernel_pagesize(vma) >> 10,
-		   vma_mmu_pagesize(vma) >> 10);
+		   vma_mmu_pagesize(vma) >> 10,
+		   (vma->vm_flags & VM_LOCKED) ?
+			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
 
 	if (m->count < m->size)  /* vma is copied successfully */
 		m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 84becd3e4772..a2a622e079f0 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2189,8 +2189,8 @@ int dquot_resume(struct super_block *sb, int type)
 }
 EXPORT_SYMBOL(dquot_resume);
 
-int dquot_quota_on_path(struct super_block *sb, int type, int format_id,
-		      struct path *path)
+int dquot_quota_on(struct super_block *sb, int type, int format_id,
+		   struct path *path)
 {
 	int error = security_quota_on(path->dentry);
 	if (error)
@@ -2204,20 +2204,6 @@ int dquot_quota_on_path(struct super_block *sb, int type, int format_id,
 					     DQUOT_LIMITS_ENABLED);
 	return error;
 }
-EXPORT_SYMBOL(dquot_quota_on_path);
-
-int dquot_quota_on(struct super_block *sb, int type, int format_id, char *name)
-{
-	struct path path;
-	int error;
-
-	error = kern_path(name, LOOKUP_FOLLOW, &path);
-	if (!error) {
-		error = dquot_quota_on_path(sb, type, format_id, &path);
-		path_put(&path);
-	}
-	return error;
-}
 EXPORT_SYMBOL(dquot_quota_on);
 
 /*
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index b299961e1edb..b34bdb25490c 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -64,18 +64,15 @@ static int quota_sync_all(int type)
 }
 
 static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id,
-		         void __user *addr)
+		         struct path *path)
 {
-	char *pathname;
-	int ret = -ENOSYS;
-
-	pathname = getname(addr);
-	if (IS_ERR(pathname))
-		return PTR_ERR(pathname);
-	if (sb->s_qcop->quota_on)
-		ret = sb->s_qcop->quota_on(sb, type, id, pathname);
-	putname(pathname);
-	return ret;
+	if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta)
+		return -ENOSYS;
+	if (sb->s_qcop->quota_on_meta)
+		return sb->s_qcop->quota_on_meta(sb, type, id);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+	return sb->s_qcop->quota_on(sb, type, id, path);
 }
 
 static int quota_getfmt(struct super_block *sb, int type, void __user *addr)
@@ -241,7 +238,7 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 
 /* Copy parameters and call proper function */
 static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
-		       void __user *addr)
+		       void __user *addr, struct path *path)
 {
 	int ret;
 
@@ -256,7 +253,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 
 	switch (cmd) {
 	case Q_QUOTAON:
-		return quota_quotaon(sb, type, cmd, id, addr);
+		return quota_quotaon(sb, type, cmd, id, path);
 	case Q_QUOTAOFF:
 		if (!sb->s_qcop->quota_off)
 			return -ENOSYS;
@@ -335,6 +332,7 @@ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
 {
 	uint cmds, type;
 	struct super_block *sb = NULL;
+	struct path path, *pathp = NULL;
 	int ret;
 
 	cmds = cmd >> SUBCMDSHIFT;
@@ -351,12 +349,27 @@ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
 		return -ENODEV;
 	}
 
+	/*
+	 * Path for quotaon has to be resolved before grabbing superblock
+	 * because that gets s_umount sem which is also possibly needed by path
+	 * resolution (think about autofs) and thus deadlocks could arise.
+	 */
+	if (cmds == Q_QUOTAON) {
+		ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW, &path);
+		if (ret)
+			pathp = ERR_PTR(ret);
+		else
+			pathp = &path;
+	}
+
 	sb = quotactl_block(special);
 	if (IS_ERR(sb))
 		return PTR_ERR(sb);
 
-	ret = do_quotactl(sb, type, cmds, id, addr);
+	ret = do_quotactl(sb, type, cmds, id, addr, pathp);
 
 	drop_super(sb);
+	if (pathp && !IS_ERR(pathp))
+		path_put(pathp);
 	return ret;
 }
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 2575682a9ead..0aab04f46827 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -632,7 +632,7 @@ static int reiserfs_acquire_dquot(struct dquot *);
 static int reiserfs_release_dquot(struct dquot *);
 static int reiserfs_mark_dquot_dirty(struct dquot *);
 static int reiserfs_write_info(struct super_block *, int);
-static int reiserfs_quota_on(struct super_block *, int, int, char *);
+static int reiserfs_quota_on(struct super_block *, int, int, struct path *);
 
 static const struct dquot_operations reiserfs_quota_operations = {
 	.write_dquot = reiserfs_write_dquot,
@@ -2048,25 +2048,21 @@ static int reiserfs_quota_on_mount(struct super_block *sb, int type)
  * Standard function to be called on quota_on
  */
 static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
-			     char *name)
+			     struct path *path)
 {
 	int err;
-	struct path path;
 	struct inode *inode;
 	struct reiserfs_transaction_handle th;
 
 	if (!(REISERFS_SB(sb)->s_mount_opt & (1 << REISERFS_QUOTA)))
 		return -EINVAL;
 
-	err = kern_path(name, LOOKUP_FOLLOW, &path);
-	if (err)
-		return err;
 	/* Quotafile not on the same filesystem? */
-	if (path.mnt->mnt_sb != sb) {
+	if (path->mnt->mnt_sb != sb) {
 		err = -EXDEV;
 		goto out;
 	}
-	inode = path.dentry->d_inode;
+	inode = path->dentry->d_inode;
 	/* We must not pack tails for quota files on reiserfs for quota IO to work */
 	if (!(REISERFS_I(inode)->i_flags & i_nopack_mask)) {
 		err = reiserfs_unpack(inode, NULL);
@@ -2082,7 +2078,7 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 	/* Journaling quota? */
 	if (REISERFS_SB(sb)->s_qf_names[type]) {
 		/* Quotafile not of fs root? */
-		if (path.dentry->d_parent != sb->s_root)
+		if (path->dentry->d_parent != sb->s_root)
 			reiserfs_warning(sb, "super-6521",
 				 "Quota file not on filesystem root. "
 				 "Journalled quota will not work.");
@@ -2101,9 +2097,8 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 		if (err)
 			goto out;
 	}
-	err = dquot_quota_on_path(sb, type, format_id, &path);
+	err = dquot_quota_on(sb, type, format_id, path);
 out:
-	path_put(&path);
 	return err;
 }
 
diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig
index e5f63da64d04..aa68a8a31518 100644
--- a/fs/squashfs/Kconfig
+++ b/fs/squashfs/Kconfig
@@ -29,7 +29,6 @@ config SQUASHFS
 config SQUASHFS_XATTR
 	bool "Squashfs XATTR support"
 	depends on SQUASHFS
-	default n
 	help
 	  Saying Y here includes support for extended attributes (xattrs).
 	  Xattrs are name:value pairs associated with inodes by
@@ -40,7 +39,6 @@ config SQUASHFS_XATTR
 config SQUASHFS_LZO
 	bool "Include support for LZO compressed file systems"
 	depends on SQUASHFS
-	default n
 	select LZO_DECOMPRESS
 	help
 	  Saying Y here includes support for reading Squashfs file systems
@@ -53,10 +51,24 @@ config SQUASHFS_LZO
 
 	  If unsure, say N.
 
+config SQUASHFS_XZ
+	bool "Include support for XZ compressed file systems"
+	depends on SQUASHFS
+	select XZ_DEC
+	help
+	  Saying Y here includes support for reading Squashfs file systems
+	  compressed with XZ compresssion.  XZ gives better compression than
+	  the default zlib compression, at the expense of greater CPU and
+	  memory overhead.
+
+	  XZ is not the standard compression used in Squashfs and so most
+	  file systems will be readable without selecting this option.
+
+	  If unsure, say N.
+
 config SQUASHFS_EMBEDDED
 	bool "Additional option for memory-constrained systems"
 	depends on SQUASHFS
-	default n
 	help
 	  Saying Y here allows you to specify cache size.
 
diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile
index 7672bac8d328..cecf2bea07af 100644
--- a/fs/squashfs/Makefile
+++ b/fs/squashfs/Makefile
@@ -7,3 +7,4 @@ squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o
 squashfs-y += namei.o super.o symlink.o zlib_wrapper.o decompressor.o
 squashfs-$(CONFIG_SQUASHFS_XATTR) += xattr.o xattr_id.o
 squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o
+squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 653c030eb840..8ab48bc2fa7d 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -34,7 +34,6 @@
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
 #include "squashfs.h"
 #include "decompressor.h"
 
@@ -64,6 +63,14 @@ static struct buffer_head *get_block_length(struct super_block *sb,
 		*length = (unsigned char) bh->b_data[*offset] |
 			(unsigned char) bh->b_data[*offset + 1] << 8;
 		*offset += 2;
+
+		if (*offset == msblk->devblksize) {
+			put_bh(bh);
+			bh = sb_bread(sb, ++(*cur_index));
+			if (bh == NULL)
+				return NULL;
+			*offset = 0;
+		}
 	}
 
 	return bh;
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 57314bee9059..26b15ae34d6f 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -55,7 +55,6 @@
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
 #include "squashfs.h"
 
 /*
diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
index 24af9ce9722f..a5940e54c4dd 100644
--- a/fs/squashfs/decompressor.c
+++ b/fs/squashfs/decompressor.c
@@ -27,7 +27,6 @@
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
 #include "decompressor.h"
 #include "squashfs.h"
 
@@ -41,23 +40,26 @@ static const struct squashfs_decompressor squashfs_lzma_unsupported_comp_ops = {
 };
 
 #ifndef CONFIG_SQUASHFS_LZO
-static const struct squashfs_decompressor squashfs_lzo_unsupported_comp_ops = {
+static const struct squashfs_decompressor squashfs_lzo_comp_ops = {
 	NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0
 };
 #endif
 
+#ifndef CONFIG_SQUASHFS_XZ
+static const struct squashfs_decompressor squashfs_xz_comp_ops = {
+	NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0
+};
+#endif
+
 static const struct squashfs_decompressor squashfs_unknown_comp_ops = {
 	NULL, NULL, NULL, 0, "unknown", 0
 };
 
 static const struct squashfs_decompressor *decompressor[] = {
 	&squashfs_zlib_comp_ops,
-	&squashfs_lzma_unsupported_comp_ops,
-#ifdef CONFIG_SQUASHFS_LZO
 	&squashfs_lzo_comp_ops,
-#else
-	&squashfs_lzo_unsupported_comp_ops,
-#endif
+	&squashfs_xz_comp_ops,
+	&squashfs_lzma_unsupported_comp_ops,
 	&squashfs_unknown_comp_ops
 };
 
diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h
index 7425f80783f6..3b305a70f7aa 100644
--- a/fs/squashfs/decompressor.h
+++ b/fs/squashfs/decompressor.h
@@ -52,4 +52,13 @@ static inline int squashfs_decompress(struct squashfs_sb_info *msblk,
 	return msblk->decompressor->decompress(msblk, buffer, bh, b, offset,
 		length, srclength, pages);
 }
+
+#ifdef CONFIG_SQUASHFS_XZ
+extern const struct squashfs_decompressor squashfs_xz_comp_ops;
+#endif
+
+#ifdef CONFIG_SQUASHFS_LZO
+extern const struct squashfs_decompressor squashfs_lzo_comp_ops;
+#endif
+
 #endif
diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c
index 7c90bbd6879d..7eef571443c6 100644
--- a/fs/squashfs/fragment.c
+++ b/fs/squashfs/fragment.c
@@ -39,7 +39,6 @@
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
 #include "squashfs.h"
 
 /*
diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c
index b7f64bcd2b70..d8f32452638e 100644
--- a/fs/squashfs/id.c
+++ b/fs/squashfs/id.c
@@ -37,7 +37,6 @@
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
 #include "squashfs.h"
 
 /*
diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c
index 5d87789bf1c1..7da759e34c52 100644
--- a/fs/squashfs/lzo_wrapper.c
+++ b/fs/squashfs/lzo_wrapper.c
@@ -29,7 +29,6 @@
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
 #include "squashfs.h"
 #include "decompressor.h"
 
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index 5d45569d5f72..ba729d808876 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -27,11 +27,6 @@
 
 #define WARNING(s, args...)	pr_warning("SQUASHFS: "s, ## args)
 
-static inline struct squashfs_inode_info *squashfs_i(struct inode *inode)
-{
-	return list_entry(inode, struct squashfs_inode_info, vfs_inode);
-}
-
 /* block.c */
 extern int squashfs_read_data(struct super_block *, void **, u64, int, u64 *,
 				int, int);
@@ -104,6 +99,3 @@ extern const struct xattr_handler *squashfs_xattr_handlers[];
 
 /* zlib_wrapper.c */
 extern const struct squashfs_decompressor squashfs_zlib_comp_ops;
-
-/* lzo_wrapper.c */
-extern const struct squashfs_decompressor squashfs_lzo_comp_ops;
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index c5137fc9ab11..39533feffd6d 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -238,6 +238,7 @@ struct meta_index {
 #define ZLIB_COMPRESSION	1
 #define LZMA_COMPRESSION	2
 #define LZO_COMPRESSION		3
+#define XZ_COMPRESSION		4
 
 struct squashfs_super_block {
 	__le32			s_magic;
diff --git a/fs/squashfs/squashfs_fs_i.h b/fs/squashfs/squashfs_fs_i.h
index d3e3a37f28a1..359baefc01fc 100644
--- a/fs/squashfs/squashfs_fs_i.h
+++ b/fs/squashfs/squashfs_fs_i.h
@@ -45,4 +45,10 @@ struct squashfs_inode_info {
 	};
 	struct inode	vfs_inode;
 };
+
+
+static inline struct squashfs_inode_info *squashfs_i(struct inode *inode)
+{
+	return list_entry(inode, struct squashfs_inode_info, vfs_inode);
+}
 #endif
diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c
index d33be5dd6c32..05385dbe1465 100644
--- a/fs/squashfs/xattr_id.c
+++ b/fs/squashfs/xattr_id.c
@@ -32,7 +32,6 @@
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
 #include "squashfs.h"
 #include "xattr.h"
 
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
new file mode 100644
index 000000000000..c4eb40018256
--- /dev/null
+++ b/fs/squashfs/xz_wrapper.c
@@ -0,0 +1,147 @@
+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2,
+ * or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * xz_wrapper.c
+ */
+
+
+#include <linux/mutex.h>
+#include <linux/buffer_head.h>
+#include <linux/slab.h>
+#include <linux/xz.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+#include "decompressor.h"
+
+struct squashfs_xz {
+	struct xz_dec *state;
+	struct xz_buf buf;
+};
+
+static void *squashfs_xz_init(struct squashfs_sb_info *msblk)
+{
+	int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE);
+
+	struct squashfs_xz *stream = kmalloc(sizeof(*stream), GFP_KERNEL);
+	if (stream == NULL)
+		goto failed;
+
+	stream->state = xz_dec_init(XZ_PREALLOC, block_size);
+	if (stream->state == NULL)
+		goto failed;
+
+	return stream;
+
+failed:
+	ERROR("Failed to allocate xz workspace\n");
+	kfree(stream);
+	return NULL;
+}
+
+
+static void squashfs_xz_free(void *strm)
+{
+	struct squashfs_xz *stream = strm;
+
+	if (stream) {
+		xz_dec_end(stream->state);
+		kfree(stream);
+	}
+}
+
+
+static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer,
+	struct buffer_head **bh, int b, int offset, int length, int srclength,
+	int pages)
+{
+	enum xz_ret xz_err;
+	int avail, total = 0, k = 0, page = 0;
+	struct squashfs_xz *stream = msblk->stream;
+
+	mutex_lock(&msblk->read_data_mutex);
+
+	xz_dec_reset(stream->state);
+	stream->buf.in_pos = 0;
+	stream->buf.in_size = 0;
+	stream->buf.out_pos = 0;
+	stream->buf.out_size = PAGE_CACHE_SIZE;
+	stream->buf.out = buffer[page++];
+
+	do {
+		if (stream->buf.in_pos == stream->buf.in_size && k < b) {
+			avail = min(length, msblk->devblksize - offset);
+			length -= avail;
+			wait_on_buffer(bh[k]);
+			if (!buffer_uptodate(bh[k]))
+				goto release_mutex;
+
+			stream->buf.in = bh[k]->b_data + offset;
+			stream->buf.in_size = avail;
+			stream->buf.in_pos = 0;
+			offset = 0;
+		}
+
+		if (stream->buf.out_pos == stream->buf.out_size
+							&& page < pages) {
+			stream->buf.out = buffer[page++];
+			stream->buf.out_pos = 0;
+			total += PAGE_CACHE_SIZE;
+		}
+
+		xz_err = xz_dec_run(stream->state, &stream->buf);
+
+		if (stream->buf.in_pos == stream->buf.in_size && k < b)
+			put_bh(bh[k++]);
+	} while (xz_err == XZ_OK);
+
+	if (xz_err != XZ_STREAM_END) {
+		ERROR("xz_dec_run error, data probably corrupt\n");
+		goto release_mutex;
+	}
+
+	if (k < b) {
+		ERROR("xz_uncompress error, input remaining\n");
+		goto release_mutex;
+	}
+
+	total += stream->buf.out_pos;
+	mutex_unlock(&msblk->read_data_mutex);
+	return total;
+
+release_mutex:
+	mutex_unlock(&msblk->read_data_mutex);
+
+	for (; k < b; k++)
+		put_bh(bh[k]);
+
+	return -EIO;
+}
+
+const struct squashfs_decompressor squashfs_xz_comp_ops = {
+	.init = squashfs_xz_init,
+	.free = squashfs_xz_free,
+	.decompress = squashfs_xz_uncompress,
+	.id = XZ_COMPRESSION,
+	.name = "xz",
+	.supported = 1
+};
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index 7a603874e483..4661ae2b1cec 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -29,7 +29,6 @@
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
 #include "squashfs.h"
 #include "decompressor.h"
 
@@ -66,8 +65,8 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer,
 	struct buffer_head **bh, int b, int offset, int length, int srclength,
 	int pages)
 {
-	int zlib_err = 0, zlib_init = 0;
-	int avail, bytes, k = 0, page = 0;
+	int zlib_err, zlib_init = 0;
+	int k = 0, page = 0;
 	z_stream *stream = msblk->stream;
 
 	mutex_lock(&msblk->read_data_mutex);
@@ -75,21 +74,14 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer,
 	stream->avail_out = 0;
 	stream->avail_in = 0;
 
-	bytes = length;
 	do {
 		if (stream->avail_in == 0 && k < b) {
-			avail = min(bytes, msblk->devblksize - offset);
-			bytes -= avail;
+			int avail = min(length, msblk->devblksize - offset);
+			length -= avail;
 			wait_on_buffer(bh[k]);
 			if (!buffer_uptodate(bh[k]))
 				goto release_mutex;
 
-			if (avail == 0) {
-				offset = 0;
-				put_bh(bh[k++]);
-				continue;
-			}
-
 			stream->next_in = bh[k]->b_data + offset;
 			stream->avail_in = avail;
 			offset = 0;
@@ -128,6 +120,11 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer,
 		goto release_mutex;
 	}
 
+	if (k < b) {
+		ERROR("zlib_uncompress error, data remaining\n");
+		goto release_mutex;
+	}
+
 	length = stream->total_out;
 	mutex_unlock(&msblk->read_data_mutex);
 	return length;
diff --git a/fs/stat.c b/fs/stat.c
index 12e90e213900..d5c61cf2b703 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -75,11 +75,13 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 	int error = -EINVAL;
 	int lookup_flags = 0;
 
-	if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
+	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) != 0)
 		goto out;
 
 	if (!(flag & AT_SYMLINK_NOFOLLOW))
 		lookup_flags |= LOOKUP_FOLLOW;
+	if (flag & AT_NO_AUTOMOUNT)
+		lookup_flags |= LOOKUP_NO_AUTOMOUNT;
 
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
diff --git a/fs/super.c b/fs/super.c
index 4f6a3571a634..7e9dd4cc2c01 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -177,6 +177,11 @@ void deactivate_locked_super(struct super_block *s)
 	struct file_system_type *fs = s->s_type;
 	if (atomic_dec_and_test(&s->s_active)) {
 		fs->kill_sb(s);
+		/*
+		 * We need to call rcu_barrier so all the delayed rcu free
+		 * inodes are flushed before we release the fs module.
+		 */
+		rcu_barrier();
 		put_filesystem(fs);
 		put_super(s);
 	} else {
@@ -1141,7 +1146,7 @@ static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
 	return mnt;
 
  err:
-	mntput_long(mnt);
+	mntput(mnt);
 	return ERR_PTR(err);
 }
 
diff --git a/fs/sysfs/Kconfig b/fs/sysfs/Kconfig
index f4b67588b9d6..8c41feacbac5 100644
--- a/fs/sysfs/Kconfig
+++ b/fs/sysfs/Kconfig
@@ -1,5 +1,5 @@
 config SYSFS
-	bool "sysfs file system support" if EMBEDDED
+	bool "sysfs file system support" if EXPERT
 	default y
 	help
 	The sysfs filesystem is a virtual filesystem that the kernel uses to
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 0dce969d6cad..faca44997099 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -98,6 +98,7 @@ 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 \
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 92f1f2acc6ab..ac1c7e8378dd 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -896,7 +896,6 @@ xfs_buf_rele(
 	trace_xfs_buf_rele(bp, _RET_IP_);
 
 	if (!pag) {
-		ASSERT(!bp->b_relse);
 		ASSERT(list_empty(&bp->b_lru));
 		ASSERT(RB_EMPTY_NODE(&bp->b_rbnode));
 		if (atomic_dec_and_test(&bp->b_hold))
@@ -908,11 +907,7 @@ xfs_buf_rele(
 
 	ASSERT(atomic_read(&bp->b_hold) > 0);
 	if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
-		if (bp->b_relse) {
-			atomic_inc(&bp->b_hold);
-			spin_unlock(&pag->pag_buf_lock);
-			bp->b_relse(bp);
-		} else if (!(bp->b_flags & XBF_STALE) &&
+		if (!(bp->b_flags & XBF_STALE) &&
 			   atomic_read(&bp->b_lru_ref)) {
 			xfs_buf_lru_add(bp);
 			spin_unlock(&pag->pag_buf_lock);
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index a76c2428faff..cbe65950e524 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -152,8 +152,6 @@ typedef struct xfs_buftarg {
 
 struct xfs_buf;
 typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
-typedef void (*xfs_buf_relse_t)(struct xfs_buf *);
-typedef int (*xfs_buf_bdstrat_t)(struct xfs_buf *);
 
 #define XB_PAGES	2
 
@@ -183,7 +181,6 @@ typedef struct xfs_buf {
 	void			*b_addr;	/* virtual address of buffer */
 	struct work_struct	b_iodone_work;
 	xfs_buf_iodone_t	b_iodone;	/* I/O completion function */
-	xfs_buf_relse_t		b_relse;	/* releasing function */
 	struct completion	b_iowait;	/* queue for I/O waiters */
 	void			*b_fspriv;
 	void			*b_fspriv2;
@@ -323,7 +320,6 @@ void xfs_buf_stale(struct xfs_buf *bp);
 #define XFS_BUF_FSPRIVATE2(bp, type)		((type)(bp)->b_fspriv2)
 #define XFS_BUF_SET_FSPRIVATE2(bp, val)		((bp)->b_fspriv2 = (void*)(val))
 #define XFS_BUF_SET_START(bp)			do { } while (0)
-#define XFS_BUF_SET_BRELSE_FUNC(bp, func)	((bp)->b_relse = (func))
 
 #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)
@@ -360,8 +356,7 @@ xfs_buf_set_ref(
 
 static inline void xfs_buf_relse(xfs_buf_t *bp)
 {
-	if (!bp->b_relse)
-		xfs_buf_unlock(bp);
+	xfs_buf_unlock(bp);
 	xfs_buf_rele(bp);
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_discard.c b/fs/xfs/linux-2.6/xfs_discard.c
new file mode 100644
index 000000000000..05201ae719e5
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_discard.c
@@ -0,0 +1,191 @@
+/*
+ * Copyright (C) 2010 Red Hat, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include "xfs.h"
+#include "xfs_sb.h"
+#include "xfs_inum.h"
+#include "xfs_log.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_quota.h"
+#include "xfs_trans.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_btree.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_error.h"
+#include "xfs_discard.h"
+#include "xfs_trace.h"
+
+STATIC int
+xfs_trim_extents(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_fsblock_t		start,
+	xfs_fsblock_t		len,
+	xfs_fsblock_t		minlen,
+	__uint64_t		*blocks_trimmed)
+{
+	struct block_device	*bdev = mp->m_ddev_targp->bt_bdev;
+	struct xfs_btree_cur	*cur;
+	struct xfs_buf		*agbp;
+	struct xfs_perag	*pag;
+	int			error;
+	int			i;
+
+	pag = xfs_perag_get(mp, agno);
+
+	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	if (error || !agbp)
+		goto out_put_perag;
+
+	cur = xfs_allocbt_init_cursor(mp, NULL, agbp, agno, XFS_BTNUM_CNT);
+
+	/*
+	 * Force out the log.  This means any transactions that might have freed
+	 * space before we took the AGF buffer lock are now on disk, and the
+	 * volatile disk cache is flushed.
+	 */
+	xfs_log_force(mp, XFS_LOG_SYNC);
+
+	/*
+	 * Look up the longest btree in the AGF and start with it.
+	 */
+	error = xfs_alloc_lookup_le(cur, 0,
+				    XFS_BUF_TO_AGF(agbp)->agf_longest, &i);
+	if (error)
+		goto out_del_cursor;
+
+	/*
+	 * Loop until we are done with all extents that are large
+	 * enough to be worth discarding.
+	 */
+	while (i) {
+		xfs_agblock_t fbno;
+		xfs_extlen_t flen;
+
+		error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
+		if (error)
+			goto out_del_cursor;
+		XFS_WANT_CORRUPTED_GOTO(i == 1, out_del_cursor);
+		ASSERT(flen <= XFS_BUF_TO_AGF(agbp)->agf_longest);
+
+		/*
+		 * Too small?  Give up.
+		 */
+		if (flen < minlen) {
+			trace_xfs_discard_toosmall(mp, agno, fbno, flen);
+			goto out_del_cursor;
+		}
+
+		/*
+		 * If the extent is entirely outside of the range we are
+		 * supposed to discard skip it.  Do not bother to trim
+		 * down partially overlapping ranges for now.
+		 */
+		if (XFS_AGB_TO_FSB(mp, agno, fbno) + flen < start ||
+		    XFS_AGB_TO_FSB(mp, agno, fbno) >= start + len) {
+			trace_xfs_discard_exclude(mp, agno, fbno, flen);
+			goto next_extent;
+		}
+
+		/*
+		 * If any blocks in the range are still busy, skip the
+		 * discard and try again the next time.
+		 */
+		if (xfs_alloc_busy_search(mp, agno, fbno, flen)) {
+			trace_xfs_discard_busy(mp, agno, fbno, flen);
+			goto next_extent;
+		}
+
+		trace_xfs_discard_extent(mp, agno, fbno, flen);
+		error = -blkdev_issue_discard(bdev,
+				XFS_AGB_TO_DADDR(mp, agno, fbno),
+				XFS_FSB_TO_BB(mp, flen),
+				GFP_NOFS, 0);
+		if (error)
+			goto out_del_cursor;
+		*blocks_trimmed += flen;
+
+next_extent:
+		error = xfs_btree_decrement(cur, 0, &i);
+		if (error)
+			goto out_del_cursor;
+	}
+
+out_del_cursor:
+	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_buf_relse(agbp);
+out_put_perag:
+	xfs_perag_put(pag);
+	return error;
+}
+
+int
+xfs_ioc_trim(
+	struct xfs_mount		*mp,
+	struct fstrim_range __user	*urange)
+{
+	struct request_queue	*q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
+	unsigned int		granularity = q->limits.discard_granularity;
+	struct fstrim_range	range;
+	xfs_fsblock_t		start, len, minlen;
+	xfs_agnumber_t		start_agno, end_agno, agno;
+	__uint64_t		blocks_trimmed = 0;
+	int			error, last_error = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -XFS_ERROR(EPERM);
+	if (copy_from_user(&range, urange, sizeof(range)))
+		return -XFS_ERROR(EFAULT);
+
+	/*
+	 * Truncating down the len isn't actually quite correct, but using
+	 * XFS_B_TO_FSB would mean we trivially get overflows for values
+	 * of ULLONG_MAX or slightly lower.  And ULLONG_MAX is the default
+	 * used by the fstrim application.  In the end it really doesn't
+	 * matter as trimming blocks is an advisory interface.
+	 */
+	start = XFS_B_TO_FSBT(mp, range.start);
+	len = XFS_B_TO_FSBT(mp, range.len);
+	minlen = XFS_B_TO_FSB(mp, max_t(u64, granularity, range.minlen));
+
+	start_agno = XFS_FSB_TO_AGNO(mp, start);
+	if (start_agno >= mp->m_sb.sb_agcount)
+		return -XFS_ERROR(EINVAL);
+
+	end_agno = XFS_FSB_TO_AGNO(mp, start + len);
+	if (end_agno >= mp->m_sb.sb_agcount)
+		end_agno = mp->m_sb.sb_agcount - 1;
+
+	for (agno = start_agno; agno <= end_agno; agno++) {
+		error = -xfs_trim_extents(mp, agno, start, len, minlen,
+					  &blocks_trimmed);
+		if (error)
+			last_error = error;
+	}
+
+	if (last_error)
+		return last_error;
+
+	range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
+	if (copy_to_user(urange, &range, sizeof(range)))
+		return -XFS_ERROR(EFAULT);
+	return 0;
+}
diff --git a/fs/xfs/linux-2.6/xfs_discard.h b/fs/xfs/linux-2.6/xfs_discard.h
new file mode 100644
index 000000000000..e82b6dd3e127
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_discard.h
@@ -0,0 +1,8 @@
+#ifndef XFS_DISCARD_H
+#define XFS_DISCARD_H 1
+
+struct fstrim_range;
+
+extern int	xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *);
+
+#endif /* XFS_DISCARD_H */
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index ba8ad422a165..a55c1b46b219 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -37,10 +37,45 @@
 #include "xfs_trace.h"
 
 #include <linux/dcache.h>
+#include <linux/falloc.h>
 
 static const struct vm_operations_struct xfs_file_vm_ops;
 
 /*
+ * Locking primitives for read and write IO paths to ensure we consistently use
+ * and order the inode->i_mutex, ip->i_lock and ip->i_iolock.
+ */
+static inline void
+xfs_rw_ilock(
+	struct xfs_inode	*ip,
+	int			type)
+{
+	if (type & XFS_IOLOCK_EXCL)
+		mutex_lock(&VFS_I(ip)->i_mutex);
+	xfs_ilock(ip, type);
+}
+
+static inline void
+xfs_rw_iunlock(
+	struct xfs_inode	*ip,
+	int			type)
+{
+	xfs_iunlock(ip, type);
+	if (type & XFS_IOLOCK_EXCL)
+		mutex_unlock(&VFS_I(ip)->i_mutex);
+}
+
+static inline void
+xfs_rw_ilock_demote(
+	struct xfs_inode	*ip,
+	int			type)
+{
+	xfs_ilock_demote(ip, type);
+	if (type & XFS_IOLOCK_EXCL)
+		mutex_unlock(&VFS_I(ip)->i_mutex);
+}
+
+/*
  *	xfs_iozero
  *
  *	xfs_iozero clears the specified range of buffer supplied,
@@ -262,22 +297,21 @@ xfs_file_aio_read(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if (unlikely(ioflags & IO_ISDIRECT))
-		mutex_lock(&inode->i_mutex);
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
-
 	if (unlikely(ioflags & IO_ISDIRECT)) {
+		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
+
 		if (inode->i_mapping->nrpages) {
 			ret = -xfs_flushinval_pages(ip,
 					(iocb->ki_pos & PAGE_CACHE_MASK),
 					-1, FI_REMAPF_LOCKED);
+			if (ret) {
+				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
+				return ret;
+			}
 		}
-		mutex_unlock(&inode->i_mutex);
-		if (ret) {
-			xfs_iunlock(ip, XFS_IOLOCK_SHARED);
-			return ret;
-		}
-	}
+		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+	} else
+		xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
 
 	trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
 
@@ -285,7 +319,7 @@ xfs_file_aio_read(
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
-	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }
 
@@ -309,7 +343,7 @@ xfs_file_splice_read(
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
 
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
 
 	trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
 
@@ -317,10 +351,61 @@ xfs_file_splice_read(
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
-	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
+	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }
 
+STATIC void
+xfs_aio_write_isize_update(
+	struct inode	*inode,
+	loff_t		*ppos,
+	ssize_t		bytes_written)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	xfs_fsize_t		isize = i_size_read(inode);
+
+	if (bytes_written > 0)
+		XFS_STATS_ADD(xs_write_bytes, bytes_written);
+
+	if (unlikely(bytes_written < 0 && bytes_written != -EFAULT &&
+					*ppos > isize))
+		*ppos = isize;
+
+	if (*ppos > ip->i_size) {
+		xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
+		if (*ppos > ip->i_size)
+			ip->i_size = *ppos;
+		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
+	}
+}
+
+/*
+ * If this was a direct or synchronous I/O that failed (such as ENOSPC) then
+ * part of the I/O may have been written to disk before the error occured.  In
+ * this case the on-disk file size may have been adjusted beyond the in-memory
+ * file size and now needs to be truncated back.
+ */
+STATIC void
+xfs_aio_write_newsize_update(
+	struct xfs_inode	*ip)
+{
+	if (ip->i_new_size) {
+		xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
+		ip->i_new_size = 0;
+		if (ip->i_d.di_size > ip->i_size)
+			ip->i_d.di_size = ip->i_size;
+		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
+	}
+}
+
+/*
+ * xfs_file_splice_write() does not use xfs_rw_ilock() because
+ * generic_file_splice_write() takes the i_mutex itself. This, in theory,
+ * couuld cause lock inversions between the aio_write path and the splice path
+ * if someone is doing concurrent splice(2) based writes and write(2) based
+ * writes to the same inode. The only real way to fix this is to re-implement
+ * the generic code here with correct locking orders.
+ */
 STATIC ssize_t
 xfs_file_splice_write(
 	struct pipe_inode_info	*pipe,
@@ -331,7 +416,7 @@ xfs_file_splice_write(
 {
 	struct inode		*inode = outfilp->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	xfs_fsize_t		isize, new_size;
+	xfs_fsize_t		new_size;
 	int			ioflags = 0;
 	ssize_t			ret;
 
@@ -355,27 +440,9 @@ xfs_file_splice_write(
 	trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
 
 	ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
-	if (ret > 0)
-		XFS_STATS_ADD(xs_write_bytes, ret);
-
-	isize = i_size_read(inode);
-	if (unlikely(ret < 0 && ret != -EFAULT && *ppos > isize))
-		*ppos = isize;
-
-	if (*ppos > ip->i_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		if (*ppos > ip->i_size)
-			ip->i_size = *ppos;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
 
-	if (ip->i_new_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		ip->i_new_size = 0;
-		if (ip->i_d.di_size > ip->i_size)
-			ip->i_d.di_size = ip->i_size;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
+	xfs_aio_write_isize_update(inode, ppos, ret);
+	xfs_aio_write_newsize_update(ip);
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	return ret;
 }
@@ -562,247 +629,314 @@ out_lock:
 	return error;
 }
 
+/*
+ * Common pre-write limit and setup checks.
+ *
+ * Returns with iolock held according to @iolock.
+ */
 STATIC ssize_t
-xfs_file_aio_write(
-	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos)
+xfs_file_aio_write_checks(
+	struct file		*file,
+	loff_t			*pos,
+	size_t			*count,
+	int			*iolock)
 {
-	struct file		*file = iocb->ki_filp;
-	struct address_space	*mapping = file->f_mapping;
-	struct inode		*inode = mapping->host;
+	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	ssize_t			ret = 0, error = 0;
-	int			ioflags = 0;
-	xfs_fsize_t		isize, new_size;
-	int			iolock;
-	size_t			ocount = 0, count;
-	int			need_i_mutex;
+	xfs_fsize_t		new_size;
+	int			error = 0;
 
-	XFS_STATS_INC(xs_write_calls);
+	error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
+	if (error) {
+		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
+		*iolock = 0;
+		return error;
+	}
 
-	BUG_ON(iocb->ki_pos != pos);
+	new_size = *pos + *count;
+	if (new_size > ip->i_size)
+		ip->i_new_size = new_size;
 
-	if (unlikely(file->f_flags & O_DIRECT))
-		ioflags |= IO_ISDIRECT;
-	if (file->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
+	if (likely(!(file->f_mode & FMODE_NOCMTIME)))
+		file_update_time(file);
+
+	/*
+	 * If the offset is beyond the size of the file, we need to zero any
+	 * blocks that fall between the existing EOF and the start of this
+	 * write.
+	 */
+	if (*pos > ip->i_size)
+		error = -xfs_zero_eof(ip, *pos, ip->i_size);
 
-	error = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
+	xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
 	if (error)
 		return error;
 
-	count = ocount;
-	if (count == 0)
-		return 0;
-
-	xfs_wait_for_freeze(mp, SB_FREEZE_WRITE);
+	/*
+	 * If we're writing the file then make sure to clear the setuid and
+	 * setgid bits if the process is not being run by root.  This keeps
+	 * people from modifying setuid and setgid binaries.
+	 */
+	return file_remove_suid(file);
 
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
+}
 
-relock:
-	if (ioflags & IO_ISDIRECT) {
-		iolock = XFS_IOLOCK_SHARED;
-		need_i_mutex = 0;
-	} else {
-		iolock = XFS_IOLOCK_EXCL;
-		need_i_mutex = 1;
-		mutex_lock(&inode->i_mutex);
+/*
+ * xfs_file_dio_aio_write - handle direct IO writes
+ *
+ * Lock the inode appropriately to prepare for and issue a direct IO write.
+ * By separating it from the buffered write path we remove all the tricky to
+ * follow locking changes and looping.
+ *
+ * If there are cached pages or we're extending the file, we need IOLOCK_EXCL
+ * until we're sure the bytes at the new EOF have been zeroed and/or the cached
+ * pages are flushed out.
+ *
+ * In most cases the direct IO writes will be done holding IOLOCK_SHARED
+ * allowing them to be done in parallel with reads and other direct IO writes.
+ * However, if the IO is not aligned to filesystem blocks, the direct IO layer
+ * needs to do sub-block zeroing and that requires serialisation against other
+ * direct IOs to the same block. In this case we need to serialise the
+ * submission of the unaligned IOs so that we don't get racing block zeroing in
+ * the dio layer.  To avoid the problem with aio, we also need to wait for
+ * outstanding IOs to complete so that unwritten extent conversion is completed
+ * before we try to map the overlapping block. This is currently implemented by
+ * hitting it with a big hammer (i.e. xfs_ioend_wait()).
+ *
+ * Returns with locks held indicated by @iolock and errors indicated by
+ * negative return values.
+ */
+STATIC ssize_t
+xfs_file_dio_aio_write(
+	struct kiocb		*iocb,
+	const struct iovec	*iovp,
+	unsigned long		nr_segs,
+	loff_t			pos,
+	size_t			ocount,
+	int			*iolock)
+{
+	struct file		*file = iocb->ki_filp;
+	struct address_space	*mapping = file->f_mapping;
+	struct inode		*inode = mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	ssize_t			ret = 0;
+	size_t			count = ocount;
+	int			unaligned_io = 0;
+	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
+					mp->m_rtdev_targp : mp->m_ddev_targp;
+
+	*iolock = 0;
+	if ((pos & target->bt_smask) || (count & target->bt_smask))
+		return -XFS_ERROR(EINVAL);
+
+	if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
+		unaligned_io = 1;
+
+	if (unaligned_io || mapping->nrpages || pos > ip->i_size)
+		*iolock = XFS_IOLOCK_EXCL;
+	else
+		*iolock = XFS_IOLOCK_SHARED;
+	xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+
+	ret = xfs_file_aio_write_checks(file, &pos, &count, iolock);
+	if (ret)
+		return ret;
+
+	if (mapping->nrpages) {
+		WARN_ON(*iolock != XFS_IOLOCK_EXCL);
+		ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
+							FI_REMAPF_LOCKED);
+		if (ret)
+			return ret;
 	}
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
-
-start:
-	error = -generic_write_checks(file, &pos, &count,
-					S_ISBLK(inode->i_mode));
-	if (error) {
-		xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
-		goto out_unlock_mutex;
+	/*
+	 * If we are doing unaligned IO, wait for all other IO to drain,
+	 * otherwise demote the lock if we had to flush cached pages
+	 */
+	if (unaligned_io)
+		xfs_ioend_wait(ip);
+	else if (*iolock == XFS_IOLOCK_EXCL) {
+		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+		*iolock = XFS_IOLOCK_SHARED;
 	}
 
-	if (ioflags & IO_ISDIRECT) {
-		xfs_buftarg_t	*target =
-			XFS_IS_REALTIME_INODE(ip) ?
-				mp->m_rtdev_targp : mp->m_ddev_targp;
+	trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
+	ret = generic_file_direct_write(iocb, iovp,
+			&nr_segs, pos, &iocb->ki_pos, count, ocount);
 
-		if ((pos & target->bt_smask) || (count & target->bt_smask)) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
-			return XFS_ERROR(-EINVAL);
-		}
+	/* No fallback to buffered IO on errors for XFS. */
+	ASSERT(ret < 0 || ret == count);
+	return ret;
+}
 
-		if (!need_i_mutex && (mapping->nrpages || pos > ip->i_size)) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
-			iolock = XFS_IOLOCK_EXCL;
-			need_i_mutex = 1;
-			mutex_lock(&inode->i_mutex);
-			xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
-			goto start;
-		}
-	}
+STATIC ssize_t
+xfs_file_buffered_aio_write(
+	struct kiocb		*iocb,
+	const struct iovec	*iovp,
+	unsigned long		nr_segs,
+	loff_t			pos,
+	size_t			ocount,
+	int			*iolock)
+{
+	struct file		*file = iocb->ki_filp;
+	struct address_space	*mapping = file->f_mapping;
+	struct inode		*inode = mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	ssize_t			ret;
+	int			enospc = 0;
+	size_t			count = ocount;
 
-	new_size = pos + count;
-	if (new_size > ip->i_size)
-		ip->i_new_size = new_size;
+	*iolock = XFS_IOLOCK_EXCL;
+	xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
 
-	if (likely(!(ioflags & IO_INVIS)))
-		file_update_time(file);
+	ret = xfs_file_aio_write_checks(file, &pos, &count, iolock);
+	if (ret)
+		return ret;
 
+	/* We can write back this queue in page reclaim */
+	current->backing_dev_info = mapping->backing_dev_info;
+
+write_retry:
+	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
+	ret = generic_file_buffered_write(iocb, iovp, nr_segs,
+			pos, &iocb->ki_pos, count, ret);
 	/*
-	 * If the offset is beyond the size of the file, we have a couple
-	 * of things to do. First, if there is already space allocated
-	 * we need to either create holes or zero the disk or ...
-	 *
-	 * If there is a page where the previous size lands, we need
-	 * to zero it out up to the new size.
+	 * if we just got an ENOSPC, flush the inode now we aren't holding any
+	 * page locks and retry *once*
 	 */
-
-	if (pos > ip->i_size) {
-		error = xfs_zero_eof(ip, pos, ip->i_size);
-		if (error) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			goto out_unlock_internal;
-		}
+	if (ret == -ENOSPC && !enospc) {
+		ret = -xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
+		if (ret)
+			return ret;
+		enospc = 1;
+		goto write_retry;
 	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	current->backing_dev_info = NULL;
+	return ret;
+}
 
-	/*
-	 * If we're writing the file then make sure to clear the
-	 * setuid and setgid bits if the process is not being run
-	 * by root.  This keeps people from modifying setuid and
-	 * setgid binaries.
-	 */
-	error = -file_remove_suid(file);
-	if (unlikely(error))
-		goto out_unlock_internal;
+STATIC ssize_t
+xfs_file_aio_write(
+	struct kiocb		*iocb,
+	const struct iovec	*iovp,
+	unsigned long		nr_segs,
+	loff_t			pos)
+{
+	struct file		*file = iocb->ki_filp;
+	struct address_space	*mapping = file->f_mapping;
+	struct inode		*inode = mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	ssize_t			ret;
+	int			iolock;
+	size_t			ocount = 0;
 
-	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	XFS_STATS_INC(xs_write_calls);
 
-	if ((ioflags & IO_ISDIRECT)) {
-		if (mapping->nrpages) {
-			WARN_ON(need_i_mutex == 0);
-			error = xfs_flushinval_pages(ip,
-					(pos & PAGE_CACHE_MASK),
-					-1, FI_REMAPF_LOCKED);
-			if (error)
-				goto out_unlock_internal;
-		}
+	BUG_ON(iocb->ki_pos != pos);
 
-		if (need_i_mutex) {
-			/* demote the lock now the cached pages are gone */
-			xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
-			mutex_unlock(&inode->i_mutex);
+	ret = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
+	if (ret)
+		return ret;
 
-			iolock = XFS_IOLOCK_SHARED;
-			need_i_mutex = 0;
-		}
+	if (ocount == 0)
+		return 0;
 
-		trace_xfs_file_direct_write(ip, count, iocb->ki_pos, ioflags);
-		ret = generic_file_direct_write(iocb, iovp,
-				&nr_segs, pos, &iocb->ki_pos, count, ocount);
+	xfs_wait_for_freeze(ip->i_mount, SB_FREEZE_WRITE);
 
-		/*
-		 * direct-io write to a hole: fall through to buffered I/O
-		 * for completing the rest of the request.
-		 */
-		if (ret >= 0 && ret != count) {
-			XFS_STATS_ADD(xs_write_bytes, ret);
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
 
-			pos += ret;
-			count -= ret;
+	if (unlikely(file->f_flags & O_DIRECT))
+		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos,
+						ocount, &iolock);
+	else
+		ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos,
+						ocount, &iolock);
 
-			ioflags &= ~IO_ISDIRECT;
-			xfs_iunlock(ip, iolock);
-			goto relock;
-		}
-	} else {
-		int enospc = 0;
-		ssize_t ret2 = 0;
+	xfs_aio_write_isize_update(inode, &iocb->ki_pos, ret);
 
-write_retry:
-		trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, ioflags);
-		ret2 = generic_file_buffered_write(iocb, iovp, nr_segs,
-				pos, &iocb->ki_pos, count, ret);
-		/*
-		 * if we just got an ENOSPC, flush the inode now we
-		 * aren't holding any page locks and retry *once*
-		 */
-		if (ret2 == -ENOSPC && !enospc) {
-			error = xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
-			if (error)
-				goto out_unlock_internal;
-			enospc = 1;
-			goto write_retry;
-		}
-		ret = ret2;
-	}
+	if (ret <= 0)
+		goto out_unlock;
 
-	current->backing_dev_info = NULL;
+	/* Handle various SYNC-type writes */
+	if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
+		loff_t end = pos + ret - 1;
+		int error, error2;
 
-	isize = i_size_read(inode);
-	if (unlikely(ret < 0 && ret != -EFAULT && iocb->ki_pos > isize))
-		iocb->ki_pos = isize;
+		xfs_rw_iunlock(ip, iolock);
+		error = filemap_write_and_wait_range(mapping, pos, end);
+		xfs_rw_ilock(ip, iolock);
 
-	if (iocb->ki_pos > ip->i_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		if (iocb->ki_pos > ip->i_size)
-			ip->i_size = iocb->ki_pos;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		error2 = -xfs_file_fsync(file,
+					 (file->f_flags & __O_SYNC) ? 0 : 1);
+		if (error)
+			ret = error;
+		else if (error2)
+			ret = error2;
 	}
 
-	error = -ret;
-	if (ret <= 0)
-		goto out_unlock_internal;
+out_unlock:
+	xfs_aio_write_newsize_update(ip);
+	xfs_rw_iunlock(ip, iolock);
+	return ret;
+}
 
-	XFS_STATS_ADD(xs_write_bytes, ret);
+STATIC long
+xfs_file_fallocate(
+	struct file	*file,
+	int		mode,
+	loff_t		offset,
+	loff_t		len)
+{
+	struct inode	*inode = file->f_path.dentry->d_inode;
+	long		error;
+	loff_t		new_size = 0;
+	xfs_flock64_t	bf;
+	xfs_inode_t	*ip = XFS_I(inode);
+	int		cmd = XFS_IOC_RESVSP;
 
-	/* Handle various SYNC-type writes */
-	if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
-		loff_t end = pos + ret - 1;
-		int error2;
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
 
-		xfs_iunlock(ip, iolock);
-		if (need_i_mutex)
-			mutex_unlock(&inode->i_mutex);
+	bf.l_whence = 0;
+	bf.l_start = offset;
+	bf.l_len = len;
 
-		error2 = filemap_write_and_wait_range(mapping, pos, end);
-		if (!error)
-			error = error2;
-		if (need_i_mutex)
-			mutex_lock(&inode->i_mutex);
-		xfs_ilock(ip, iolock);
+	xfs_ilock(ip, XFS_IOLOCK_EXCL);
 
-		error2 = -xfs_file_fsync(file,
-					 (file->f_flags & __O_SYNC) ? 0 : 1);
-		if (!error)
-			error = error2;
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		cmd = XFS_IOC_UNRESVSP;
+
+	/* check the new inode size is valid before allocating */
+	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+	    offset + len > i_size_read(inode)) {
+		new_size = offset + len;
+		error = inode_newsize_ok(inode, new_size);
+		if (error)
+			goto out_unlock;
 	}
 
- out_unlock_internal:
-	if (ip->i_new_size) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		ip->i_new_size = 0;
-		/*
-		 * If this was a direct or synchronous I/O that failed (such
-		 * as ENOSPC) then part of the I/O may have been written to
-		 * disk before the error occured.  In this case the on-disk
-		 * file size may have been adjusted beyond the in-memory file
-		 * size and now needs to be truncated back.
-		 */
-		if (ip->i_d.di_size > ip->i_size)
-			ip->i_d.di_size = ip->i_size;
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	error = -xfs_change_file_space(ip, cmd, &bf, 0, XFS_ATTR_NOLOCK);
+	if (error)
+		goto out_unlock;
+
+	/* Change file size if needed */
+	if (new_size) {
+		struct iattr iattr;
+
+		iattr.ia_valid = ATTR_SIZE;
+		iattr.ia_size = new_size;
+		error = -xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
 	}
-	xfs_iunlock(ip, iolock);
- out_unlock_mutex:
-	if (need_i_mutex)
-		mutex_unlock(&inode->i_mutex);
-	return -error;
+
+out_unlock:
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	return error;
 }
 
+
 STATIC int
 xfs_file_open(
 	struct inode	*inode,
@@ -921,6 +1055,7 @@ const struct file_operations xfs_file_operations = {
 	.open		= xfs_file_open,
 	.release	= xfs_file_release,
 	.fsync		= xfs_file_fsync,
+	.fallocate	= xfs_file_fallocate,
 };
 
 const struct file_operations xfs_dir_file_operations = {
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index ad442d9e392e..f5e2a19e0f8e 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -39,6 +39,7 @@
 #include "xfs_dfrag.h"
 #include "xfs_fsops.h"
 #include "xfs_vnodeops.h"
+#include "xfs_discard.h"
 #include "xfs_quota.h"
 #include "xfs_inode_item.h"
 #include "xfs_export.h"
@@ -984,10 +985,22 @@ xfs_ioctl_setattr(
 
 		/*
 		 * Extent size must be a multiple of the appropriate block
-		 * size, if set at all.
+		 * size, if set at all. It must also be smaller than the
+		 * maximum extent size supported by the filesystem.
+		 *
+		 * Also, for non-realtime files, limit the extent size hint to
+		 * half the size of the AGs in the filesystem so alignment
+		 * doesn't result in extents larger than an AG.
 		 */
 		if (fa->fsx_extsize != 0) {
-			xfs_extlen_t	size;
+			xfs_extlen_t    size;
+			xfs_fsblock_t   extsize_fsb;
+
+			extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
+			if (extsize_fsb > MAXEXTLEN) {
+				code = XFS_ERROR(EINVAL);
+				goto error_return;
+			}
 
 			if (XFS_IS_REALTIME_INODE(ip) ||
 			    ((mask & FSX_XFLAGS) &&
@@ -996,6 +1009,10 @@ xfs_ioctl_setattr(
 				       mp->m_sb.sb_blocklog;
 			} else {
 				size = mp->m_sb.sb_blocksize;
+				if (extsize_fsb > mp->m_sb.sb_agblocks / 2) {
+					code = XFS_ERROR(EINVAL);
+					goto error_return;
+				}
 			}
 
 			if (fa->fsx_extsize % size) {
@@ -1294,6 +1311,8 @@ xfs_file_ioctl(
 	trace_xfs_file_ioctl(ip);
 
 	switch (cmd) {
+	case FITRIM:
+		return xfs_ioc_trim(mp, arg);
 	case XFS_IOC_ALLOCSP:
 	case XFS_IOC_FREESP:
 	case XFS_IOC_RESVSP:
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index da54403633b6..bd5727852fd6 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -46,7 +46,6 @@
 #include <linux/namei.h>
 #include <linux/posix_acl.h>
 #include <linux/security.h>
-#include <linux/falloc.h>
 #include <linux/fiemap.h>
 #include <linux/slab.h>
 
@@ -505,61 +504,6 @@ xfs_vn_setattr(
 	return -xfs_setattr(XFS_I(dentry->d_inode), iattr, 0);
 }
 
-STATIC long
-xfs_vn_fallocate(
-	struct inode	*inode,
-	int		mode,
-	loff_t		offset,
-	loff_t		len)
-{
-	long		error;
-	loff_t		new_size = 0;
-	xfs_flock64_t	bf;
-	xfs_inode_t	*ip = XFS_I(inode);
-	int		cmd = XFS_IOC_RESVSP;
-
-	/* preallocation on directories not yet supported */
-	error = -ENODEV;
-	if (S_ISDIR(inode->i_mode))
-		goto out_error;
-
-	bf.l_whence = 0;
-	bf.l_start = offset;
-	bf.l_len = len;
-
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
-	if (mode & FALLOC_FL_PUNCH_HOLE)
-		cmd = XFS_IOC_UNRESVSP;
-
-	/* check the new inode size is valid before allocating */
-	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-	    offset + len > i_size_read(inode)) {
-		new_size = offset + len;
-		error = inode_newsize_ok(inode, new_size);
-		if (error)
-			goto out_unlock;
-	}
-
-	error = -xfs_change_file_space(ip, cmd, &bf, 0, XFS_ATTR_NOLOCK);
-	if (error)
-		goto out_unlock;
-
-	/* Change file size if needed */
-	if (new_size) {
-		struct iattr iattr;
-
-		iattr.ia_valid = ATTR_SIZE;
-		iattr.ia_size = new_size;
-		error = -xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
-	}
-
-out_unlock:
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-out_error:
-	return error;
-}
-
 #define XFS_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
 
 /*
@@ -653,7 +597,6 @@ static const struct inode_operations xfs_inode_operations = {
 	.getxattr		= generic_getxattr,
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
-	.fallocate		= xfs_vn_fallocate,
 	.fiemap			= xfs_vn_fiemap,
 };
 
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index bd07f7339366..9731898083ae 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -1414,7 +1414,7 @@ xfs_fs_freeze(
 
 	xfs_save_resvblks(mp);
 	xfs_quiesce_attr(mp);
-	return -xfs_fs_log_dummy(mp, SYNC_WAIT);
+	return -xfs_fs_log_dummy(mp);
 }
 
 STATIC int
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index a02480de9759..e22f0057d21f 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -362,7 +362,7 @@ xfs_quiesce_data(
 
 	/* mark the log as covered if needed */
 	if (xfs_log_need_covered(mp))
-		error2 = xfs_fs_log_dummy(mp, SYNC_WAIT);
+		error2 = xfs_fs_log_dummy(mp);
 
 	/* flush data-only devices */
 	if (mp->m_rtdev_targp)
@@ -503,13 +503,14 @@ xfs_sync_worker(
 	int		error;
 
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-		xfs_log_force(mp, 0);
-		xfs_reclaim_inodes(mp, 0);
 		/* dgc: errors ignored here */
-		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
 		if (mp->m_super->s_frozen == SB_UNFROZEN &&
 		    xfs_log_need_covered(mp))
-			error = xfs_fs_log_dummy(mp, 0);
+			error = xfs_fs_log_dummy(mp);
+		else
+			xfs_log_force(mp, 0);
+		xfs_reclaim_inodes(mp, 0);
+		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
 	}
 	mp->m_sync_seq++;
 	wake_up(&mp->m_wait_single_sync_task);
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index 7bb5092d6ae4..ee3cee097e7e 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -18,6 +18,7 @@
 #include "xfs.h"
 #include <linux/sysctl.h>
 #include <linux/proc_fs.h>
+#include "xfs_error.h"
 
 static struct ctl_table_header *xfs_table_header;
 
@@ -51,6 +52,26 @@ xfs_stats_clear_proc_handler(
 
 	return ret;
 }
+
+STATIC int
+xfs_panic_mask_proc_handler(
+	ctl_table	*ctl,
+	int		write,
+	void		__user *buffer,
+	size_t		*lenp,
+	loff_t		*ppos)
+{
+	int		ret, *valp = ctl->data;
+
+	ret = proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+	if (!ret && write) {
+		xfs_panic_mask = *valp;
+#ifdef DEBUG
+		xfs_panic_mask |= (XFS_PTAG_SHUTDOWN_CORRUPT | XFS_PTAG_LOGRES);
+#endif
+	}
+	return ret;
+}
 #endif /* CONFIG_PROC_FS */
 
 static ctl_table xfs_table[] = {
@@ -77,7 +98,7 @@ static ctl_table xfs_table[] = {
 		.data		= &xfs_params.panic_mask.val,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= xfs_panic_mask_proc_handler,
 		.extra1		= &xfs_params.panic_mask.min,
 		.extra2		= &xfs_params.panic_mask.max
 	},
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index 647af2a2e7aa..2d0bcb479075 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -1759,6 +1759,39 @@ DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_recover);
 DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_cancel);
 DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_skip);
 
+DECLARE_EVENT_CLASS(xfs_discard_class,
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+		 xfs_agblock_t agbno, xfs_extlen_t len),
+	TP_ARGS(mp, agno, agbno, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, agbno)
+		__field(xfs_extlen_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->agno = agno;
+		__entry->agbno = agbno;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d agno %u agbno %u len %u\n",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agbno,
+		  __entry->len)
+)
+
+#define DEFINE_DISCARD_EVENT(name) \
+DEFINE_EVENT(xfs_discard_class, name, \
+	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+		 xfs_agblock_t agbno, xfs_extlen_t len), \
+	TP_ARGS(mp, agno, agbno, len))
+DEFINE_DISCARD_EVENT(xfs_discard_extent);
+DEFINE_DISCARD_EVENT(xfs_discard_toosmall);
+DEFINE_DISCARD_EVENT(xfs_discard_exclude);
+DEFINE_DISCARD_EVENT(xfs_discard_busy);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index f8e854b4fde8..206a2815ced6 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -1863,12 +1863,14 @@ xfs_qm_dqreclaim_one(void)
 	xfs_dquot_t	*dqpout;
 	xfs_dquot_t	*dqp;
 	int		restarts;
+	int		startagain;
 
 	restarts = 0;
 	dqpout = NULL;
 
 	/* lockorder: hashchainlock, freelistlock, mplistlock, dqlock, dqflock */
-startagain:
+again:
+	startagain = 0;
 	mutex_lock(&xfs_Gqm->qm_dqfrlist_lock);
 
 	list_for_each_entry(dqp, &xfs_Gqm->qm_dqfrlist, q_freelist) {
@@ -1885,13 +1887,10 @@ startagain:
 			ASSERT(! (dqp->dq_flags & XFS_DQ_INACTIVE));
 
 			trace_xfs_dqreclaim_want(dqp);
-
-			xfs_dqunlock(dqp);
-			mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock);
-			if (++restarts >= XFS_QM_RECLAIM_MAX_RESTARTS)
-				return NULL;
 			XQM_STATS_INC(xqmstats.xs_qm_dqwants);
-			goto startagain;
+			restarts++;
+			startagain = 1;
+			goto dqunlock;
 		}
 
 		/*
@@ -1906,23 +1905,20 @@ startagain:
 			ASSERT(list_empty(&dqp->q_mplist));
 			list_del_init(&dqp->q_freelist);
 			xfs_Gqm->qm_dqfrlist_cnt--;
-			xfs_dqunlock(dqp);
 			dqpout = dqp;
 			XQM_STATS_INC(xqmstats.xs_qm_dqinact_reclaims);
-			break;
+			goto dqunlock;
 		}
 
 		ASSERT(dqp->q_hash);
 		ASSERT(!list_empty(&dqp->q_mplist));
 
 		/*
-		 * Try to grab the flush lock. If this dquot is in the process of
-		 * getting flushed to disk, we don't want to reclaim it.
+		 * Try to grab the flush lock. If this dquot is in the process
+		 * of getting flushed to disk, we don't want to reclaim it.
 		 */
-		if (!xfs_dqflock_nowait(dqp)) {
-			xfs_dqunlock(dqp);
-			continue;
-		}
+		if (!xfs_dqflock_nowait(dqp))
+			goto dqunlock;
 
 		/*
 		 * We have the flush lock so we know that this is not in the
@@ -1944,8 +1940,7 @@ startagain:
 				xfs_fs_cmn_err(CE_WARN, mp,
 			"xfs_qm_dqreclaim: dquot %p flush failed", dqp);
 			}
-			xfs_dqunlock(dqp); /* dqflush unlocks dqflock */
-			continue;
+			goto dqunlock;
 		}
 
 		/*
@@ -1967,13 +1962,8 @@ startagain:
 		 */
 		if (!mutex_trylock(&mp->m_quotainfo->qi_dqlist_lock)) {
 			restarts++;
-			mutex_unlock(&dqp->q_hash->qh_lock);
-			xfs_dqfunlock(dqp);
-			xfs_dqunlock(dqp);
-			mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock);
-			if (restarts++ >= XFS_QM_RECLAIM_MAX_RESTARTS)
-				return NULL;
-			goto startagain;
+			startagain = 1;
+			goto qhunlock;
 		}
 
 		ASSERT(dqp->q_nrefs == 0);
@@ -1986,14 +1976,20 @@ startagain:
 		xfs_Gqm->qm_dqfrlist_cnt--;
 		dqpout = dqp;
 		mutex_unlock(&mp->m_quotainfo->qi_dqlist_lock);
+qhunlock:
 		mutex_unlock(&dqp->q_hash->qh_lock);
 dqfunlock:
 		xfs_dqfunlock(dqp);
+dqunlock:
 		xfs_dqunlock(dqp);
 		if (dqpout)
 			break;
 		if (restarts >= XFS_QM_RECLAIM_MAX_RESTARTS)
-			return NULL;
+			break;
+		if (startagain) {
+			mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock);
+			goto again;
+		}
 	}
 	mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock);
 	return dqpout;
diff --git a/fs/xfs/support/debug.c b/fs/xfs/support/debug.c
index 975aa10e1a47..0df88897ef84 100644
--- a/fs/xfs/support/debug.c
+++ b/fs/xfs/support/debug.c
@@ -25,86 +25,78 @@
 #include "xfs_mount.h"
 #include "xfs_error.h"
 
-static char		message[1024];	/* keep it off the stack */
-static DEFINE_SPINLOCK(xfs_err_lock);
-
-/* Translate from CE_FOO to KERN_FOO, err_level(CE_FOO) == KERN_FOO */
-#define XFS_MAX_ERR_LEVEL	7
-#define XFS_ERR_MASK		((1 << 3) - 1)
-static const char * const	err_level[XFS_MAX_ERR_LEVEL+1] =
-					{KERN_EMERG, KERN_ALERT, KERN_CRIT,
-					 KERN_ERR, KERN_WARNING, KERN_NOTICE,
-					 KERN_INFO, KERN_DEBUG};
-
 void
-cmn_err(register int level, char *fmt, ...)
+cmn_err(
+	const char	*lvl,
+	const char	*fmt,
+	...)
 {
-	char	*fp = fmt;
-	int	len;
-	ulong	flags;
-	va_list	ap;
-
-	level &= XFS_ERR_MASK;
-	if (level > XFS_MAX_ERR_LEVEL)
-		level = XFS_MAX_ERR_LEVEL;
-	spin_lock_irqsave(&xfs_err_lock,flags);
-	va_start(ap, fmt);
-	if (*fmt == '!') fp++;
-	len = vsnprintf(message, sizeof(message), fp, ap);
-	if (len >= sizeof(message))
-		len = sizeof(message) - 1;
-	if (message[len-1] == '\n')
-		message[len-1] = 0;
-	printk("%s%s\n", err_level[level], message);
-	va_end(ap);
-	spin_unlock_irqrestore(&xfs_err_lock,flags);
-	BUG_ON(level == CE_PANIC);
+	struct va_format vaf;
+	va_list		args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk("%s%pV", lvl, &vaf);
+	va_end(args);
+
+	BUG_ON(strncmp(lvl, KERN_EMERG, strlen(KERN_EMERG)) == 0);
 }
 
 void
-xfs_fs_vcmn_err(
-	int			level,
+xfs_fs_cmn_err(
+	const char		*lvl,
 	struct xfs_mount	*mp,
-	char			*fmt,
-	va_list			ap)
+	const char		*fmt,
+	...)
 {
-	unsigned long		flags;
-	int			len = 0;
+	struct va_format	vaf;
+	va_list			args;
 
-	level &= XFS_ERR_MASK;
-	if (level > XFS_MAX_ERR_LEVEL)
-		level = XFS_MAX_ERR_LEVEL;
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
 
-	spin_lock_irqsave(&xfs_err_lock,flags);
+	printk("%sFilesystem %s: %pV", lvl, mp->m_fsname, &vaf);
+	va_end(args);
 
-	if (mp) {
-		len = sprintf(message, "Filesystem \"%s\": ", mp->m_fsname);
+	BUG_ON(strncmp(lvl, KERN_EMERG, strlen(KERN_EMERG)) == 0);
+}
+
+/* All callers to xfs_cmn_err use CE_ALERT, so don't bother testing lvl */
+void
+xfs_cmn_err(
+	int			panic_tag,
+	const char		*lvl,
+	struct xfs_mount	*mp,
+	const char		*fmt,
+	...)
+{
+	struct va_format	vaf;
+	va_list			args;
+	int			do_panic = 0;
 
-		/*
-		 * Skip the printk if we can't print anything useful
-		 * due to an over-long device name.
-		 */
-		if (len >= sizeof(message))
-			goto out;
+	if (xfs_panic_mask && (xfs_panic_mask & panic_tag)) {
+		printk(KERN_ALERT "XFS: Transforming an alert into a BUG.");
+		do_panic = 1;
 	}
 
-	len = vsnprintf(message + len, sizeof(message) - len, fmt, ap);
-	if (len >= sizeof(message))
-		len = sizeof(message) - 1;
-	if (message[len-1] == '\n')
-		message[len-1] = 0;
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
 
-	printk("%s%s\n", err_level[level], message);
- out:
-	spin_unlock_irqrestore(&xfs_err_lock,flags);
+	printk(KERN_ALERT "Filesystem %s: %pV", mp->m_fsname, &vaf);
+	va_end(args);
 
-	BUG_ON(level == CE_PANIC);
+	BUG_ON(do_panic);
 }
 
 void
 assfail(char *expr, char *file, int line)
 {
-	printk("Assertion failed: %s, file: %s, line: %d\n", expr, file, line);
+	printk(KERN_CRIT "Assertion failed: %s, file: %s, line: %d\n", expr,
+	       file, line);
 	BUG();
 }
 
diff --git a/fs/xfs/support/debug.h b/fs/xfs/support/debug.h
index d2d20462fd4f..05699f67d475 100644
--- a/fs/xfs/support/debug.h
+++ b/fs/xfs/support/debug.h
@@ -20,15 +20,22 @@
 
 #include <stdarg.h>
 
-#define CE_DEBUG        7               /* debug        */
-#define CE_CONT         6               /* continuation */
-#define CE_NOTE         5               /* notice       */
-#define CE_WARN         4               /* warning      */
-#define CE_ALERT        1               /* alert        */
-#define CE_PANIC        0               /* panic        */
-
-extern void cmn_err(int, char *, ...)
-	__attribute__ ((format (printf, 2, 3)));
+struct xfs_mount;
+
+#define CE_DEBUG        KERN_DEBUG
+#define CE_CONT         KERN_INFO
+#define CE_NOTE         KERN_NOTICE
+#define CE_WARN         KERN_WARNING
+#define CE_ALERT        KERN_ALERT
+#define CE_PANIC        KERN_EMERG
+
+void cmn_err(const char *lvl, const char *fmt, ...)
+		__attribute__ ((format (printf, 2, 3)));
+void xfs_fs_cmn_err( const char *lvl, struct xfs_mount *mp,
+		const char *fmt, ...) __attribute__ ((format (printf, 3, 4)));
+void xfs_cmn_err( int panic_tag, const char *lvl, struct xfs_mount *mp,
+		const char *fmt, ...) __attribute__ ((format (printf, 4, 5)));
+
 extern void assfail(char *expr, char *f, int l);
 
 #define ASSERT_ALWAYS(expr)	\
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index fa8723f5870a..f3227984a9bf 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -41,10 +41,6 @@
 #define	XFSA_FIXUP_BNO_OK	1
 #define	XFSA_FIXUP_CNT_OK	2
 
-static int
-xfs_alloc_busy_search(struct xfs_mount *mp, xfs_agnumber_t agno,
-		    xfs_agblock_t bno, xfs_extlen_t len);
-
 /*
  * Prototypes for per-ag allocation routines
  */
@@ -94,7 +90,7 @@ xfs_alloc_lookup_ge(
  * Lookup the first record less than or equal to [bno, len]
  * in the btree given by cur.
  */
-STATIC int				/* error */
+int					/* error */
 xfs_alloc_lookup_le(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	xfs_agblock_t		bno,	/* starting block of extent */
@@ -127,7 +123,7 @@ xfs_alloc_update(
 /*
  * Get the data from the pointed-to record.
  */
-STATIC int				/* error */
+int					/* error */
 xfs_alloc_get_rec(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	xfs_agblock_t		*bno,	/* output: starting block of extent */
@@ -2615,7 +2611,7 @@ restart:
  * will require a synchronous transaction, but it can still be
  * used to distinguish between a partial or exact match.
  */
-static int
+int
 xfs_alloc_busy_search(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 895009a97271..d0b3bc72005b 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -19,6 +19,7 @@
 #define	__XFS_ALLOC_H__
 
 struct xfs_buf;
+struct xfs_btree_cur;
 struct xfs_mount;
 struct xfs_perag;
 struct xfs_trans;
@@ -74,6 +75,22 @@ typedef unsigned int xfs_alloctype_t;
 #define XFS_ALLOC_SET_ASIDE(mp)  (4 + ((mp)->m_sb.sb_agcount * 4))
 
 /*
+ * When deciding how much space to allocate out of an AG, we limit the
+ * allocation maximum size to the size the AG. However, we cannot use all the
+ * blocks in the AG - some are permanently used by metadata. These
+ * blocks are generally:
+ *	- the AG superblock, AGF, AGI and AGFL
+ *	- the AGF (bno and cnt) and AGI btree root blocks
+ *	- 4 blocks on the AGFL according to XFS_ALLOC_SET_ASIDE() limits
+ *
+ * The AG headers are sector sized, so the amount of space they take up is
+ * dependent on filesystem geometry. The others are all single blocks.
+ */
+#define XFS_ALLOC_AG_MAX_USABLE(mp)	\
+	((mp)->m_sb.sb_agblocks - XFS_BB_TO_FSB(mp, XFS_FSS_TO_BB(mp, 4)) - 7)
+
+
+/*
  * Argument structure for xfs_alloc routines.
  * This is turned into a structure to avoid having 20 arguments passed
  * down several levels of the stack.
@@ -118,16 +135,16 @@ xfs_alloc_longest_free_extent(struct xfs_mount *mp,
 		struct xfs_perag *pag);
 
 #ifdef __KERNEL__
-
 void
-xfs_alloc_busy_insert(xfs_trans_t *tp,
-		xfs_agnumber_t agno,
-		xfs_agblock_t bno,
-		xfs_extlen_t len);
+xfs_alloc_busy_insert(struct xfs_trans *tp, xfs_agnumber_t agno,
+	xfs_agblock_t bno, xfs_extlen_t len);
 
 void
 xfs_alloc_busy_clear(struct xfs_mount *mp, struct xfs_busy_extent *busyp);
 
+int
+xfs_alloc_busy_search(struct xfs_mount *mp, xfs_agnumber_t agno,
+	xfs_agblock_t bno, xfs_extlen_t len);
 #endif	/* __KERNEL__ */
 
 /*
@@ -205,4 +222,18 @@ xfs_free_extent(
 	xfs_fsblock_t	bno,	/* starting block number of extent */
 	xfs_extlen_t	len);	/* length of extent */
 
+int					/* error */
+xfs_alloc_lookup_le(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* starting block of extent */
+	xfs_extlen_t		len,	/* length of extent */
+	int			*stat);	/* success/failure */
+
+int					/* error */
+xfs_alloc_get_rec(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		*bno,	/* output: starting block of extent */
+	xfs_extlen_t		*len,	/* output: length of extent */
+	int			*stat);	/* output: success/failure */
+
 #endif	/* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 4111cd3966c7..dc3afd7739ff 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -1038,17 +1038,34 @@ xfs_bmap_add_extent_delay_real(
 		 * Filling in the middle part of a previous delayed allocation.
 		 * Contiguity is impossible here.
 		 * This case is avoided almost all the time.
+		 *
+		 * We start with a delayed allocation:
+		 *
+		 * +ddddddddddddddddddddddddddddddddddddddddddddddddddddddd+
+		 *  PREV @ idx
+		 *
+	         * and we are allocating:
+		 *                     +rrrrrrrrrrrrrrrrr+
+		 *			      new
+		 *
+		 * and we set it up for insertion as:
+		 * +ddddddddddddddddddd+rrrrrrrrrrrrrrrrr+ddddddddddddddddd+
+		 *                            new
+		 *  PREV @ idx          LEFT              RIGHT
+		 *                      inserted at idx + 1
 		 */
 		temp = new->br_startoff - PREV.br_startoff;
-		trace_xfs_bmap_pre_update(ip, idx, 0, _THIS_IP_);
-		xfs_bmbt_set_blockcount(ep, temp);
-		r[0] = *new;
-		r[1].br_state = PREV.br_state;
-		r[1].br_startblock = 0;
-		r[1].br_startoff = new_endoff;
 		temp2 = PREV.br_startoff + PREV.br_blockcount - new_endoff;
-		r[1].br_blockcount = temp2;
-		xfs_iext_insert(ip, idx + 1, 2, &r[0], state);
+		trace_xfs_bmap_pre_update(ip, idx, 0, _THIS_IP_);
+		xfs_bmbt_set_blockcount(ep, temp);	/* truncate PREV */
+		LEFT = *new;
+		RIGHT.br_state = PREV.br_state;
+		RIGHT.br_startblock = nullstartblock(
+				(int)xfs_bmap_worst_indlen(ip, temp2));
+		RIGHT.br_startoff = new_endoff;
+		RIGHT.br_blockcount = temp2;
+		/* insert LEFT (r[0]) and RIGHT (r[1]) at the same time */
+		xfs_iext_insert(ip, idx + 1, 2, &LEFT, state);
 		ip->i_df.if_lastex = idx + 1;
 		ip->i_d.di_nextents++;
 		if (cur == NULL)
@@ -2430,7 +2447,7 @@ xfs_bmap_btalloc_nullfb(
 		startag = ag = 0;
 
 	pag = xfs_perag_get(mp, ag);
-	while (*blen < ap->alen) {
+	while (*blen < args->maxlen) {
 		if (!pag->pagf_init) {
 			error = xfs_alloc_pagf_init(mp, args->tp, ag,
 						    XFS_ALLOC_FLAG_TRYLOCK);
@@ -2452,7 +2469,7 @@ xfs_bmap_btalloc_nullfb(
 			notinit = 1;
 
 		if (xfs_inode_is_filestream(ap->ip)) {
-			if (*blen >= ap->alen)
+			if (*blen >= args->maxlen)
 				break;
 
 			if (ap->userdata) {
@@ -2498,14 +2515,14 @@ xfs_bmap_btalloc_nullfb(
 	 * If the best seen length is less than the request
 	 * length, use the best as the minimum.
 	 */
-	else if (*blen < ap->alen)
+	else if (*blen < args->maxlen)
 		args->minlen = *blen;
 	/*
-	 * Otherwise we've seen an extent as big as alen,
+	 * Otherwise we've seen an extent as big as maxlen,
 	 * use that as the minimum.
 	 */
 	else
-		args->minlen = ap->alen;
+		args->minlen = args->maxlen;
 
 	/*
 	 * set the failure fallback case to look in the selected
@@ -2573,7 +2590,9 @@ xfs_bmap_btalloc(
 	args.tp = ap->tp;
 	args.mp = mp;
 	args.fsbno = ap->rval;
-	args.maxlen = MIN(ap->alen, mp->m_sb.sb_agblocks);
+
+	/* Trim the allocation back to the maximum an AG can fit. */
+	args.maxlen = MIN(ap->alen, XFS_ALLOC_AG_MAX_USABLE(mp));
 	args.firstblock = ap->firstblock;
 	blen = 0;
 	if (nullfb) {
@@ -2621,7 +2640,7 @@ xfs_bmap_btalloc(
 			/*
 			 * Adjust for alignment
 			 */
-			if (blen > args.alignment && blen <= ap->alen)
+			if (blen > args.alignment && blen <= args.maxlen)
 				args.minlen = blen - args.alignment;
 			args.minalignslop = 0;
 		} else {
@@ -2640,7 +2659,7 @@ xfs_bmap_btalloc(
 			 * of minlen+alignment+slop doesn't go up
 			 * between the calls.
 			 */
-			if (blen > mp->m_dalign && blen <= ap->alen)
+			if (blen > mp->m_dalign && blen <= args.maxlen)
 				nextminlen = blen - mp->m_dalign;
 			else
 				nextminlen = args.minlen;
@@ -4485,6 +4504,16 @@ xfs_bmapi(
 				/* Figure out the extent size, adjust alen */
 				extsz = xfs_get_extsz_hint(ip);
 				if (extsz) {
+					/*
+					 * make sure we don't exceed a single
+					 * extent length when we align the
+					 * extent by reducing length we are
+					 * going to allocate by the maximum
+					 * amount extent size aligment may
+					 * require.
+					 */
+					alen = XFS_FILBLKS_MIN(len,
+						   MAXEXTLEN - (2 * extsz - 1));
 					error = xfs_bmap_extsize_align(mp,
 							&got, &prev, extsz,
 							rt, eof,
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index ed2b65f3f8b9..6f8c21ce0d6d 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -141,7 +141,6 @@ xfs_buf_item_log_check(
 #define		xfs_buf_item_log_check(x)
 #endif
 
-STATIC void	xfs_buf_error_relse(xfs_buf_t *bp);
 STATIC void	xfs_buf_do_callbacks(struct xfs_buf *bp);
 
 /*
@@ -428,13 +427,15 @@ xfs_buf_item_unpin(
 
 		if (remove) {
 			/*
-			 * We have to remove the log item from the transaction
-			 * as we are about to release our reference to the
-			 * buffer.  If we don't, the unlock that occurs later
-			 * in xfs_trans_uncommit() will ry to reference the
+			 * If we are in a transaction context, we have to
+			 * remove the log item from the transaction as we are
+			 * about to release our reference to the buffer.  If we
+			 * don't, the unlock that occurs later in
+			 * xfs_trans_uncommit() will try to reference the
 			 * buffer which we no longer have a hold on.
 			 */
-			xfs_trans_del_item(lip);
+			if (lip->li_desc)
+				xfs_trans_del_item(lip);
 
 			/*
 			 * Since the transaction no longer refers to the buffer,
@@ -959,128 +960,76 @@ xfs_buf_do_callbacks(
  */
 void
 xfs_buf_iodone_callbacks(
-	xfs_buf_t	*bp)
+	struct xfs_buf		*bp)
 {
-	xfs_log_item_t	*lip;
-	static ulong	lasttime;
-	static xfs_buftarg_t *lasttarg;
-	xfs_mount_t	*mp;
+	struct xfs_log_item	*lip = bp->b_fspriv;
+	struct xfs_mount	*mp = lip->li_mountp;
+	static ulong		lasttime;
+	static xfs_buftarg_t	*lasttarg;
 
-	ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);
-	lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
+	if (likely(!XFS_BUF_GETERROR(bp)))
+		goto do_callbacks;
 
-	if (XFS_BUF_GETERROR(bp) != 0) {
-		/*
-		 * If we've already decided to shutdown the filesystem
-		 * because of IO errors, there's no point in giving this
-		 * a retry.
-		 */
-		mp = lip->li_mountp;
-		if (XFS_FORCED_SHUTDOWN(mp)) {
-			ASSERT(XFS_BUF_TARGET(bp) == mp->m_ddev_targp);
-			XFS_BUF_SUPER_STALE(bp);
-			trace_xfs_buf_item_iodone(bp, _RET_IP_);
-			xfs_buf_do_callbacks(bp);
-			XFS_BUF_SET_FSPRIVATE(bp, NULL);
-			XFS_BUF_CLR_IODONE_FUNC(bp);
-			xfs_buf_ioend(bp, 0);
-			return;
-		}
+	/*
+	 * If we've already decided to shutdown the filesystem because of
+	 * I/O errors, there's no point in giving this a retry.
+	 */
+	if (XFS_FORCED_SHUTDOWN(mp)) {
+		XFS_BUF_SUPER_STALE(bp);
+		trace_xfs_buf_item_iodone(bp, _RET_IP_);
+		goto do_callbacks;
+	}
 
-		if ((XFS_BUF_TARGET(bp) != lasttarg) ||
-		    (time_after(jiffies, (lasttime + 5*HZ)))) {
-			lasttime = jiffies;
-			cmn_err(CE_ALERT, "Device %s, XFS metadata write error"
-					" block 0x%llx in %s",
-				XFS_BUFTARG_NAME(XFS_BUF_TARGET(bp)),
-			      (__uint64_t)XFS_BUF_ADDR(bp), mp->m_fsname);
-		}
-		lasttarg = XFS_BUF_TARGET(bp);
+	if (XFS_BUF_TARGET(bp) != lasttarg ||
+	    time_after(jiffies, (lasttime + 5*HZ))) {
+		lasttime = jiffies;
+		cmn_err(CE_ALERT, "Device %s, XFS metadata write error"
+				" block 0x%llx in %s",
+			XFS_BUFTARG_NAME(XFS_BUF_TARGET(bp)),
+		      (__uint64_t)XFS_BUF_ADDR(bp), mp->m_fsname);
+	}
+	lasttarg = XFS_BUF_TARGET(bp);
 
-		if (XFS_BUF_ISASYNC(bp)) {
-			/*
-			 * If the write was asynchronous then noone will be
-			 * looking for the error.  Clear the error state
-			 * and write the buffer out again delayed write.
-			 *
-			 * XXXsup This is OK, so long as we catch these
-			 * before we start the umount; we don't want these
-			 * DELWRI metadata bufs to be hanging around.
-			 */
-			XFS_BUF_ERROR(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(XFS_BUF_IODONE_FUNC(bp));
-			trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
-			xfs_buf_relse(bp);
-		} else {
-			/*
-			 * If the write of the buffer was not asynchronous,
-			 * then we want to make sure to return the error
-			 * to the caller of bwrite().  Because of this we
-			 * cannot clear the B_ERROR state at this point.
-			 * Instead we install a callback function that
-			 * will be called when the buffer is released, and
-			 * that routine will clear the error state and
-			 * set the buffer to be written out again after
-			 * some delay.
-			 */
-			/* We actually overwrite the existing b-relse
-			   function at times, but we're gonna be shutting down
-			   anyway. */
-			XFS_BUF_SET_BRELSE_FUNC(bp,xfs_buf_error_relse);
+	/*
+	 * If the write was asynchronous then noone will be looking for the
+	 * error.  Clear the error state and write the buffer out again.
+	 *
+	 * During sync or umount we'll write all pending buffers again
+	 * synchronous, which will catch these errors if they keep hanging
+	 * around.
+	 */
+	if (XFS_BUF_ISASYNC(bp)) {
+		XFS_BUF_ERROR(bp, 0); /* errno of 0 unsets the flag */
+
+		if (!XFS_BUF_ISSTALE(bp)) {
+			XFS_BUF_DELAYWRITE(bp);
 			XFS_BUF_DONE(bp);
-			XFS_BUF_FINISH_IOWAIT(bp);
+			XFS_BUF_SET_START(bp);
 		}
+		ASSERT(XFS_BUF_IODONE_FUNC(bp));
+		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
+		xfs_buf_relse(bp);
 		return;
 	}
 
-	xfs_buf_do_callbacks(bp);
-	XFS_BUF_SET_FSPRIVATE(bp, NULL);
-	XFS_BUF_CLR_IODONE_FUNC(bp);
-	xfs_buf_ioend(bp, 0);
-}
-
-/*
- * This is a callback routine attached to a buffer which gets an error
- * when being written out synchronously.
- */
-STATIC void
-xfs_buf_error_relse(
-	xfs_buf_t	*bp)
-{
-	xfs_log_item_t	*lip;
-	xfs_mount_t	*mp;
-
-	lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
-	mp = (xfs_mount_t *)lip->li_mountp;
-	ASSERT(XFS_BUF_TARGET(bp) == mp->m_ddev_targp);
-
+	/*
+	 * If the write of the buffer was synchronous, we want to make
+	 * sure to return the error to the caller of xfs_bwrite().
+	 */
 	XFS_BUF_STALE(bp);
 	XFS_BUF_DONE(bp);
 	XFS_BUF_UNDELAYWRITE(bp);
-	XFS_BUF_ERROR(bp,0);
 
 	trace_xfs_buf_error_relse(bp, _RET_IP_);
+	xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
 
-	if (! XFS_FORCED_SHUTDOWN(mp))
-		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
-	/*
-	 * We have to unpin the pinned buffers so do the
-	 * callbacks.
-	 */
+do_callbacks:
 	xfs_buf_do_callbacks(bp);
 	XFS_BUF_SET_FSPRIVATE(bp, NULL);
 	XFS_BUF_CLR_IODONE_FUNC(bp);
-	XFS_BUF_SET_BRELSE_FUNC(bp,NULL);
-	xfs_buf_relse(bp);
+	xfs_buf_ioend(bp, 0);
 }
 
-
 /*
  * This is the iodone() function for buffers which have been
  * logged.  It is called when they are eventually flushed out.
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index c78cc6a3d87c..4c7db74a05f7 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -152,37 +152,6 @@ xfs_errortag_clearall(xfs_mount_t *mp, int loud)
 }
 #endif /* DEBUG */
 
-
-void
-xfs_fs_cmn_err(int level, xfs_mount_t *mp, char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	xfs_fs_vcmn_err(level, mp, fmt, ap);
-	va_end(ap);
-}
-
-void
-xfs_cmn_err(int panic_tag, int level, xfs_mount_t *mp, char *fmt, ...)
-{
-	va_list ap;
-
-#ifdef DEBUG
-	xfs_panic_mask |= (XFS_PTAG_SHUTDOWN_CORRUPT | XFS_PTAG_LOGRES);
-#endif
-
-	if (xfs_panic_mask && (xfs_panic_mask & panic_tag)
-	    && (level & CE_ALERT)) {
-		level &= ~CE_ALERT;
-		level |= CE_PANIC;
-		cmn_err(CE_ALERT, "XFS: Transforming an alert into a BUG.");
-	}
-	va_start(ap, fmt);
-	xfs_fs_vcmn_err(level, mp, fmt, ap);
-	va_end(ap);
-}
-
 void
 xfs_error_report(
 	const char		*tag,
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index f338847f80b8..10dce5475f02 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -136,8 +136,8 @@ extern int xfs_error_test(int, int *, char *, int, char *, unsigned long);
 	 xfs_error_test((tag), (mp)->m_fixedfsid, "expr", __LINE__, __FILE__, \
 			(rf))))
 
-extern int xfs_errortag_add(int error_tag, xfs_mount_t *mp);
-extern int xfs_errortag_clearall(xfs_mount_t *mp, int loud);
+extern int xfs_errortag_add(int error_tag, struct xfs_mount *mp);
+extern int xfs_errortag_clearall(struct xfs_mount *mp, int loud);
 #else
 #define XFS_TEST_ERROR(expr, mp, tag, rf)	(expr)
 #define xfs_errortag_add(tag, mp)		(ENOSYS)
@@ -162,21 +162,15 @@ extern int xfs_errortag_clearall(xfs_mount_t *mp, int loud);
 
 struct xfs_mount;
 
-extern void xfs_fs_vcmn_err(int level, struct xfs_mount *mp,
-		char *fmt, va_list ap)
-	__attribute__ ((format (printf, 3, 0)));
-extern void xfs_cmn_err(int panic_tag, int level, struct xfs_mount *mp,
-			char *fmt, ...)
-	__attribute__ ((format (printf, 4, 5)));
-extern void xfs_fs_cmn_err(int level, struct xfs_mount *mp, char *fmt, ...)
-	__attribute__ ((format (printf, 3, 4)));
-
 extern void xfs_hex_dump(void *p, int length);
 
 #define xfs_fs_repair_cmn_err(level, mp, fmt, args...) \
 	xfs_fs_cmn_err(level, mp, fmt "  Unmount and run xfs_repair.", ## args)
 
 #define xfs_fs_mount_cmn_err(f, fmt, args...) \
-	((f & XFS_MFSI_QUIET)? (void)0 : cmn_err(CE_WARN, "XFS: " fmt, ## args))
+	do { \
+		if (!(f & XFS_MFSI_QUIET)) 	\
+			cmn_err(CE_WARN, "XFS: " fmt, ## args); \
+	} while (0)
 
 #endif	/* __XFS_ERROR_H__ */
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 75f2ef60e579..d22e62623437 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -138,7 +138,8 @@ xfs_efi_item_unpin(
 
 	if (remove) {
 		ASSERT(!(lip->li_flags & XFS_LI_IN_AIL));
-		xfs_trans_del_item(lip);
+		if (lip->li_desc)
+			xfs_trans_del_item(lip);
 		xfs_efi_item_free(efip);
 		return;
 	}
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index f56d30e8040c..cec89dd5d7d2 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -612,12 +612,13 @@ out:
  *
  * We cannot use an inode here for this - that will push dirty state back up
  * into the VFS and then periodic inode flushing will prevent log covering from
- * making progress. Hence we log a field in the superblock instead.
+ * making progress. Hence we log a field in the superblock instead and use a
+ * synchronous transaction to ensure the superblock is immediately unpinned
+ * and can be written back.
  */
 int
 xfs_fs_log_dummy(
-	xfs_mount_t	*mp,
-	int		flags)
+	xfs_mount_t	*mp)
 {
 	xfs_trans_t	*tp;
 	int		error;
@@ -632,8 +633,7 @@ xfs_fs_log_dummy(
 
 	/* log the UUID because it is an unchanging field */
 	xfs_mod_sb(tp, XFS_SB_UUID);
-	if (flags & SYNC_WAIT)
-		xfs_trans_set_sync(tp);
+	xfs_trans_set_sync(tp);
 	return xfs_trans_commit(tp, 0);
 }
 
diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h
index a786c5212c1e..1b6a98b66886 100644
--- a/fs/xfs/xfs_fsops.h
+++ b/fs/xfs/xfs_fsops.h
@@ -25,6 +25,6 @@ extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt);
 extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval,
 				xfs_fsop_resblks_t *outval);
 extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags);
-extern int xfs_fs_log_dummy(xfs_mount_t *mp, int flags);
+extern int xfs_fs_log_dummy(struct xfs_mount *mp);
 
 #endif	/* __XFS_FSOPS_H__ */
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 55582bd66659..8a0f044750c3 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -337,7 +337,12 @@ xfs_iomap_prealloc_size(
 		int shift = 0;
 		int64_t freesp;
 
-		alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size);
+		/*
+		 * rounddown_pow_of_two() returns an undefined result
+		 * if we pass in alloc_blocks = 0. Hence the "+ 1" to
+		 * ensure we always pass in a non-zero value.
+		 */
+		alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size) + 1;
 		alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN,
 					rounddown_pow_of_two(alloc_blocks));
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 0bf24b11d0c4..ae6fef1ff563 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -377,7 +377,7 @@ xfs_log_mount(
 		cmn_err(CE_NOTE, "XFS mounting filesystem %s", mp->m_fsname);
 	else {
 		cmn_err(CE_NOTE,
-			"!Mounting filesystem \"%s\" in no-recovery mode.  Filesystem will be inconsistent.",
+			"Mounting filesystem \"%s\" in no-recovery mode.  Filesystem will be inconsistent.",
 			mp->m_fsname);
 		ASSERT(mp->m_flags & XFS_MOUNT_RDONLY);
 	}
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 916eb7db14d9..3bd3291ef8d2 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -191,7 +191,7 @@ void	  xfs_log_ticket_put(struct xlog_ticket *ticket);
 
 xlog_tid_t xfs_log_get_trans_ident(struct xfs_trans *tp);
 
-int	xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp,
+void	xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp,
 				struct xfs_log_vec *log_vector,
 				xfs_lsn_t *commit_lsn, int flags);
 bool	xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 9dc8125d04e5..9ca59be08977 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -543,7 +543,7 @@ xlog_cil_push(
 
 	error = xlog_write(log, &lvhdr, tic, &ctx->start_lsn, NULL, 0);
 	if (error)
-		goto out_abort;
+		goto out_abort_free_ticket;
 
 	/*
 	 * now that we've written the checkpoint into the log, strictly
@@ -569,8 +569,9 @@ restart:
 	}
 	spin_unlock(&cil->xc_cil_lock);
 
+	/* xfs_log_done always frees the ticket on error. */
 	commit_lsn = xfs_log_done(log->l_mp, tic, &commit_iclog, 0);
-	if (error || commit_lsn == -1)
+	if (commit_lsn == -1)
 		goto out_abort;
 
 	/* attach all the transactions w/ busy extents to iclog */
@@ -600,6 +601,8 @@ out_free_ticket:
 	kmem_free(new_ctx);
 	return 0;
 
+out_abort_free_ticket:
+	xfs_log_ticket_put(tic);
 out_abort:
 	xlog_cil_committed(ctx, XFS_LI_ABORTED);
 	return XFS_ERROR(EIO);
@@ -622,7 +625,7 @@ out_abort:
  * background commit, returns without it held once background commits are
  * allowed again.
  */
-int
+void
 xfs_log_commit_cil(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
@@ -637,11 +640,6 @@ xfs_log_commit_cil(
 	if (flags & XFS_TRANS_RELEASE_LOG_RES)
 		log_flags = XFS_LOG_REL_PERM_RESERV;
 
-	if (XLOG_FORCED_SHUTDOWN(log)) {
-		xlog_cil_free_logvec(log_vector);
-		return XFS_ERROR(EIO);
-	}
-
 	/*
 	 * do all the hard work of formatting items (including memory
 	 * allocation) outside the CIL context lock. This prevents stalling CIL
@@ -701,7 +699,6 @@ xfs_log_commit_cil(
 	 */
 	if (push)
 		xlog_cil_push(log, 0);
-	return 0;
 }
 
 /*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 204d8e5fa7fa..aa0ebb776903 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3800,7 +3800,7 @@ xlog_recover_finish(
 		log->l_flags &= ~XLOG_RECOVERY_NEEDED;
 	} else {
 		cmn_err(CE_DEBUG,
-			"!Ending clean XFS mount for filesystem: %s\n",
+			"Ending clean XFS mount for filesystem: %s\n",
 			log->l_mp->m_fsname);
 	}
 	return 0;
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index f80a067a4658..76922793f64f 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1137,7 +1137,7 @@ out_undo_fdblocks:
 	if (blkdelta)
 		xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, -blkdelta, rsvd);
 out:
-	ASSERT(error = 0);
+	ASSERT(error == 0);
 	return;
 }
 
@@ -1446,6 +1446,14 @@ xfs_log_item_batch_insert(
  * Bulk operation version of xfs_trans_committed that takes a log vector of
  * items to insert into the AIL. This uses bulk AIL insertion techniques to
  * minimise lock traffic.
+ *
+ * If we are called with the aborted flag set, it is because a log write during
+ * a CIL checkpoint commit has failed. In this case, all the items in the
+ * checkpoint have already gone through IOP_COMMITED and IOP_UNLOCK, which
+ * means that checkpoint commit abort handling is treated exactly the same
+ * as an iclog write error even though we haven't started any IO yet. Hence in
+ * this case all we need to do is IOP_COMMITTED processing, followed by an
+ * IOP_UNPIN(aborted) call.
  */
 void
 xfs_trans_committed_bulk(
@@ -1472,6 +1480,16 @@ xfs_trans_committed_bulk(
 		if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)
 			continue;
 
+		/*
+		 * if we are aborting the operation, no point in inserting the
+		 * object into the AIL as we are in a shutdown situation.
+		 */
+		if (aborted) {
+			ASSERT(XFS_FORCED_SHUTDOWN(ailp->xa_mount));
+			IOP_UNPIN(lip, 1);
+			continue;
+		}
+
 		if (item_lsn != commit_lsn) {
 
 			/*
@@ -1503,20 +1521,24 @@ xfs_trans_committed_bulk(
 }
 
 /*
- * Called from the trans_commit code when we notice that
- * the filesystem is in the middle of a forced shutdown.
+ * Called from the trans_commit code when we notice that the filesystem is in
+ * the middle of a forced shutdown.
+ *
+ * When we are called here, we have already pinned all the items in the
+ * transaction. However, neither IOP_COMMITTING or IOP_UNLOCK has been called
+ * so we can simply walk the items in the transaction, unpin them with an abort
+ * flag and then free the items. Note that unpinning the items can result in
+ * them being freed immediately, so we need to use a safe list traversal method
+ * here.
  */
 STATIC void
 xfs_trans_uncommit(
 	struct xfs_trans	*tp,
 	uint			flags)
 {
-	struct xfs_log_item_desc *lidp;
+	struct xfs_log_item_desc *lidp, *n;
 
-	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
-		/*
-		 * Unpin all but those that aren't dirty.
-		 */
+	list_for_each_entry_safe(lidp, n, &tp->t_items, lid_trans) {
 		if (lidp->lid_flags & XFS_LID_DIRTY)
 			IOP_UNPIN(lidp->lid_item, 1);
 	}
@@ -1733,7 +1755,6 @@ xfs_trans_commit_cil(
 	int			flags)
 {
 	struct xfs_log_vec	*log_vector;
-	int			error;
 
 	/*
 	 * Get each log item to allocate a vector structure for
@@ -1744,9 +1765,7 @@ xfs_trans_commit_cil(
 	if (!log_vector)
 		return ENOMEM;
 
-	error = xfs_log_commit_cil(mp, tp, log_vector, commit_lsn, flags);
-	if (error)
-		return error;
+	xfs_log_commit_cil(mp, tp, log_vector, commit_lsn, flags);
 
 	current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
 	xfs_trans_free(tp);