Merge commit '8700c95adb03' into timers/nohz

The full dynticks tree needs the latest RCU and sched upstream updates in order to fix some dependencies. Merge a common upstream merge point that has these updates. Conflicts: include/linux/perf_event.h kernel/rcutree.h kernel/rcutree_plugin.h Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
author: Frederic Weisbecker <fweisbec@gmail.com> 2013-05-02 17:37:49 +0200
committer: Frederic Weisbecker <fweisbec@gmail.com> 2013-05-02 17:54:19 +0200
commit: c032862fba51a3ca504752d3a25186b324c5ce83 (patch)
tree: 955dc2ba4ab3df76ecc2bb780ee84aca04967e8d /fs
parent: fda76e074c7737fc57855dd17c762e50ed526052 (diff)
parent: 8700c95adb033843fc163d112b9d21d4fda78018 (diff)
download: op-kernel-dev-c032862fba51a3ca504752d3a25186b324c5ce83.zip
op-kernel-dev-c032862fba51a3ca504752d3a25186b324c5ce83.tar.gz
176 files changed, 2107 insertions, 855 deletions
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 91dad63..2756dcd 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -365,3 +365,4 @@ struct file_system_type v9fs_fs_type = {
 	.owner = THIS_MODULE,
 	.fs_flags = FS_RENAME_DOES_D_MOVE,
 };
+MODULE_ALIAS_FS("9p");
diff --git a/fs/Makefile b/fs/Makefile
index 9d53192..3b2c767 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -10,7 +10,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		ioctl.o readdir.o select.o fifo.o dcache.o inode.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
-		pnode.o drop_caches.o splice.o sync.o utimes.o \
+		pnode.o splice.o sync.o utimes.o \
 		stack.o fs_struct.o statfs.o
 
 ifeq ($(CONFIG_BLOCK),y)
@@ -49,6 +49,7 @@ obj-$(CONFIG_FS_POSIX_ACL)	+= posix_acl.o xattr_acl.o
 obj-$(CONFIG_NFS_COMMON)	+= nfs_common/
 obj-$(CONFIG_GENERIC_ACL)	+= generic_acl.o
 obj-$(CONFIG_COREDUMP)		+= coredump.o
+obj-$(CONFIG_SYSCTL)		+= drop_caches.o
 
 obj-$(CONFIG_FHANDLE)		+= fhandle.o
 
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index d571229..0ff4bae 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -524,6 +524,7 @@ static struct file_system_type adfs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("adfs");
 
 static int __init init_adfs_fs(void)
 {
diff --git a/fs/affs/super.c b/fs/affs/super.c
index b84dc73..45161a8 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -622,6 +622,7 @@ static struct file_system_type affs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("affs");
 
 static int __init init_affs_fs(void)
 {
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 7c31ec3..c486155 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -45,6 +45,7 @@ struct file_system_type afs_fs_type = {
 	.kill_sb	= afs_kill_super,
 	.fs_flags	= 0,
 };
+MODULE_ALIAS_FS("afs");
 
 static const struct super_operations afs_super_ops = {
 	.statfs		= afs_statfs,
diff --git a/fs/aio.c b/fs/aio.c
index 3f941f2..1dc8786 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1029,9 +1029,9 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
 	spin_unlock(&info->ring_lock);
 
 out:
-	kunmap_atomic(ring);
 	dprintk("leaving aio_read_evt: %d  h%lu t%lu\n", ret,
 		 (unsigned long)ring->head, (unsigned long)ring->tail);
+	kunmap_atomic(ring);
 	return ret;
 }
 
diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c
index cddc74b..b3db517 100644
--- a/fs/autofs4/init.c
+++ b/fs/autofs4/init.c
@@ -26,6 +26,7 @@ static struct file_system_type autofs_fs_type = {
 	.mount		= autofs_mount,
 	.kill_sb	= autofs4_kill_sb,
 };
+MODULE_ALIAS_FS("autofs");
 
 static int __init init_autofs4_fs(void)
 {
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index c8f4e25..8615ee8 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -951,6 +951,7 @@ static struct file_system_type befs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,	
 };
+MODULE_ALIAS_FS("befs");
 
 static int __init
 init_befs_fs(void)
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 737aaa3..5e376bb 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -473,6 +473,7 @@ static struct file_system_type bfs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("bfs");
 
 static int __init init_bfs_fs(void)
 {
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3939829..86af964 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1137,6 +1137,7 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma,
 			goto whole;
 		if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
 			goto whole;
+		return 0;
 	}
 
 	/* Do not dump I/O mapped devices or special mappings */
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index fecbbf3..751df5e 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -720,6 +720,7 @@ static struct file_system_type bm_fs_type = {
 	.mount		= bm_mount,
 	.kill_sb	= kill_litter_super,
 };
+MODULE_ALIAS_FS("binfmt_misc");
 
 static int __init init_misc_binfmt(void)
 {
diff --git a/fs/bio.c b/fs/bio.c
index bb5768f..b96fc6c 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1428,8 +1428,6 @@ void bio_endio(struct bio *bio, int error)
 	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 		error = -EIO;
 
-	trace_block_bio_complete(bio, error);
-
 	if (bio->bi_end_io)
 		bio->bi_end_io(bio, error);
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index aea605c..aae187a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -551,6 +551,7 @@ struct block_device *bdgrab(struct block_device *bdev)
 	ihold(bdev->bd_inode);
 	return bdev;
 }
+EXPORT_SYMBOL(bdgrab);
 
 long nr_blockdev_pages(void)
 {
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index ecd25a1..ca9d8f1 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -651,6 +651,8 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 	if (tree_mod_dont_log(fs_info, NULL))
 		return 0;
 
+	__tree_mod_log_free_eb(fs_info, old_root);
+
 	ret = tree_mod_alloc(fs_info, flags, &tm);
 	if (ret < 0)
 		goto out;
@@ -736,7 +738,7 @@ tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq)
 static noinline void
 tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
 		     struct extent_buffer *src, unsigned long dst_offset,
-		     unsigned long src_offset, int nr_items)
+		     unsigned long src_offset, int nr_items, int log_removal)
 {
 	int ret;
 	int i;
@@ -750,10 +752,12 @@ tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
 	}
 
 	for (i = 0; i < nr_items; i++) {
-		ret = tree_mod_log_insert_key_locked(fs_info, src,
-						     i + src_offset,
-						     MOD_LOG_KEY_REMOVE);
-		BUG_ON(ret < 0);
+		if (log_removal) {
+			ret = tree_mod_log_insert_key_locked(fs_info, src,
+							i + src_offset,
+							MOD_LOG_KEY_REMOVE);
+			BUG_ON(ret < 0);
+		}
 		ret = tree_mod_log_insert_key_locked(fs_info, dst,
 						     i + dst_offset,
 						     MOD_LOG_KEY_ADD);
@@ -927,7 +931,6 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 			ret = btrfs_dec_ref(trans, root, buf, 1, 1);
 			BUG_ON(ret); /* -ENOMEM */
 		}
-		tree_mod_log_free_eb(root->fs_info, buf);
 		clean_tree_block(trans, root, buf);
 		*last_ref = 1;
 	}
@@ -1046,6 +1049,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		btrfs_set_node_ptr_generation(parent, parent_slot,
 					      trans->transid);
 		btrfs_mark_buffer_dirty(parent);
+		tree_mod_log_free_eb(root->fs_info, buf);
 		btrfs_free_tree_block(trans, root, buf, parent_start,
 				      last_ref);
 	}
@@ -1750,7 +1754,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			goto enospc;
 		}
 
-		tree_mod_log_free_eb(root->fs_info, root->node);
 		tree_mod_log_set_root_pointer(root, child);
 		rcu_assign_pointer(root->node, child);
 
@@ -2995,7 +2998,7 @@ static int push_node_left(struct btrfs_trans_handle *trans,
 		push_items = min(src_nritems - 8, push_items);
 
 	tree_mod_log_eb_copy(root->fs_info, dst, src, dst_nritems, 0,
-			     push_items);
+			     push_items, 1);
 	copy_extent_buffer(dst, src,
 			   btrfs_node_key_ptr_offset(dst_nritems),
 			   btrfs_node_key_ptr_offset(0),
@@ -3066,7 +3069,7 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
 				      sizeof(struct btrfs_key_ptr));
 
 	tree_mod_log_eb_copy(root->fs_info, dst, src, 0,
-			     src_nritems - push_items, push_items);
+			     src_nritems - push_items, push_items, 1);
 	copy_extent_buffer(dst, src,
 			   btrfs_node_key_ptr_offset(0),
 			   btrfs_node_key_ptr_offset(src_nritems - push_items),
@@ -3218,12 +3221,18 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	int mid;
 	int ret;
 	u32 c_nritems;
+	int tree_mod_log_removal = 1;
 
 	c = path->nodes[level];
 	WARN_ON(btrfs_header_generation(c) != trans->transid);
 	if (c == root->node) {
 		/* trying to split the root, lets make a new one */
 		ret = insert_new_root(trans, root, path, level + 1);
+		/*
+		 * removal of root nodes has been logged by
+		 * tree_mod_log_set_root_pointer due to locking
+		 */
+		tree_mod_log_removal = 0;
 		if (ret)
 			return ret;
 	} else {
@@ -3261,7 +3270,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 			    (unsigned long)btrfs_header_chunk_tree_uuid(split),
 			    BTRFS_UUID_SIZE);
 
-	tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid);
+	tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid,
+			     tree_mod_log_removal);
 	copy_extent_buffer(split, c,
 			   btrfs_node_key_ptr_offset(0),
 			   btrfs_node_key_ptr_offset(mid),
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 0b278b1..14fce27 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -22,8 +22,9 @@
 #include "disk-io.h"
 #include "transaction.h"
 
-#define BTRFS_DELAYED_WRITEBACK		400
-#define BTRFS_DELAYED_BACKGROUND	100
+#define BTRFS_DELAYED_WRITEBACK		512
+#define BTRFS_DELAYED_BACKGROUND	128
+#define BTRFS_DELAYED_BATCH		16
 
 static struct kmem_cache *delayed_node_cache;
 
@@ -494,6 +495,15 @@ static int __btrfs_add_delayed_deletion_item(struct btrfs_delayed_node *node,
 					BTRFS_DELAYED_DELETION_ITEM);
 }
 
+static void finish_one_item(struct btrfs_delayed_root *delayed_root)
+{
+	int seq = atomic_inc_return(&delayed_root->items_seq);
+	if ((atomic_dec_return(&delayed_root->items) <
+	    BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0) &&
+	    waitqueue_active(&delayed_root->wait))
+		wake_up(&delayed_root->wait);
+}
+
 static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
 {
 	struct rb_root *root;
@@ -512,10 +522,8 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
 
 	rb_erase(&delayed_item->rb_node, root);
 	delayed_item->delayed_node->count--;
-	if (atomic_dec_return(&delayed_root->items) <
-	    BTRFS_DELAYED_BACKGROUND &&
-	    waitqueue_active(&delayed_root->wait))
-		wake_up(&delayed_root->wait);
+
+	finish_one_item(delayed_root);
 }
 
 static void btrfs_release_delayed_item(struct btrfs_delayed_item *item)
@@ -1056,10 +1064,7 @@ static void btrfs_release_delayed_inode(struct btrfs_delayed_node *delayed_node)
 		delayed_node->count--;
 
 		delayed_root = delayed_node->root->fs_info->delayed_root;
-		if (atomic_dec_return(&delayed_root->items) <
-		    BTRFS_DELAYED_BACKGROUND &&
-		    waitqueue_active(&delayed_root->wait))
-			wake_up(&delayed_root->wait);
+		finish_one_item(delayed_root);
 	}
 }
 
@@ -1304,35 +1309,44 @@ void btrfs_remove_delayed_node(struct inode *inode)
 	btrfs_release_delayed_node(delayed_node);
 }
 
-struct btrfs_async_delayed_node {
-	struct btrfs_root *root;
-	struct btrfs_delayed_node *delayed_node;
+struct btrfs_async_delayed_work {
+	struct btrfs_delayed_root *delayed_root;
+	int nr;
 	struct btrfs_work work;
 };
 
-static void btrfs_async_run_delayed_node_done(struct btrfs_work *work)
+static void btrfs_async_run_delayed_root(struct btrfs_work *work)
 {
-	struct btrfs_async_delayed_node *async_node;
+	struct btrfs_async_delayed_work *async_work;
+	struct btrfs_delayed_root *delayed_root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_path *path;
 	struct btrfs_delayed_node *delayed_node = NULL;
 	struct btrfs_root *root;
 	struct btrfs_block_rsv *block_rsv;
-	int need_requeue = 0;
+	int total_done = 0;
 
-	async_node = container_of(work, struct btrfs_async_delayed_node, work);
+	async_work = container_of(work, struct btrfs_async_delayed_work, work);
+	delayed_root = async_work->delayed_root;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		goto out;
-	path->leave_spinning = 1;
 
-	delayed_node = async_node->delayed_node;
+again:
+	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND / 2)
+		goto free_path;
+
+	delayed_node = btrfs_first_prepared_delayed_node(delayed_root);
+	if (!delayed_node)
+		goto free_path;
+
+	path->leave_spinning = 1;
 	root = delayed_node->root;
 
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
-		goto free_path;
+		goto release_path;
 
 	block_rsv = trans->block_rsv;
 	trans->block_rsv = &root->fs_info->delayed_block_rsv;
@@ -1363,57 +1377,47 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work)
 	 * Task1 will sleep until the transaction is commited.
 	 */
 	mutex_lock(&delayed_node->mutex);
-	if (delayed_node->count)
-		need_requeue = 1;
-	else
-		btrfs_dequeue_delayed_node(root->fs_info->delayed_root,
-					   delayed_node);
+	btrfs_dequeue_delayed_node(root->fs_info->delayed_root, delayed_node);
 	mutex_unlock(&delayed_node->mutex);
 
 	trans->block_rsv = block_rsv;
 	btrfs_end_transaction_dmeta(trans, root);
 	btrfs_btree_balance_dirty_nodelay(root);
+
+release_path:
+	btrfs_release_path(path);
+	total_done++;
+
+	btrfs_release_prepared_delayed_node(delayed_node);
+	if (async_work->nr == 0 || total_done < async_work->nr)
+		goto again;
+
 free_path:
 	btrfs_free_path(path);
 out:
-	if (need_requeue)
-		btrfs_requeue_work(&async_node->work);
-	else {
-		btrfs_release_prepared_delayed_node(delayed_node);
-		kfree(async_node);
-	}
+	wake_up(&delayed_root->wait);
+	kfree(async_work);
 }
 
+
 static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
-				     struct btrfs_root *root, int all)
+				     struct btrfs_root *root, int nr)
 {
-	struct btrfs_async_delayed_node *async_node;
-	struct btrfs_delayed_node *curr;
-	int count = 0;
+	struct btrfs_async_delayed_work *async_work;
 
-again:
-	curr = btrfs_first_prepared_delayed_node(delayed_root);
-	if (!curr)
+	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
 		return 0;
 
-	async_node = kmalloc(sizeof(*async_node), GFP_NOFS);
-	if (!async_node) {
-		btrfs_release_prepared_delayed_node(curr);
+	async_work = kmalloc(sizeof(*async_work), GFP_NOFS);
+	if (!async_work)
 		return -ENOMEM;
-	}
-
-	async_node->root = root;
-	async_node->delayed_node = curr;
-
-	async_node->work.func = btrfs_async_run_delayed_node_done;
-	async_node->work.flags = 0;
 
-	btrfs_queue_worker(&root->fs_info->delayed_workers, &async_node->work);
-	count++;
-
-	if (all || count < 4)
-		goto again;
+	async_work->delayed_root = delayed_root;
+	async_work->work.func = btrfs_async_run_delayed_root;
+	async_work->work.flags = 0;
+	async_work->nr = nr;
 
+	btrfs_queue_worker(&root->fs_info->delayed_workers, &async_work->work);
 	return 0;
 }
 
@@ -1424,30 +1428,55 @@ void btrfs_assert_delayed_root_empty(struct btrfs_root *root)
 	WARN_ON(btrfs_first_delayed_node(delayed_root));
 }
 
+static int refs_newer(struct btrfs_delayed_root *delayed_root,
+		      int seq, int count)
+{
+	int val = atomic_read(&delayed_root->items_seq);
+
+	if (val < seq || val >= seq + count)
+		return 1;
+	return 0;
+}
+
 void btrfs_balance_delayed_items(struct btrfs_root *root)
 {
 	struct btrfs_delayed_root *delayed_root;
+	int seq;
 
 	delayed_root = btrfs_get_delayed_root(root);
 
 	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
 		return;
 
+	seq = atomic_read(&delayed_root->items_seq);
+
 	if (atomic_read(&delayed_root->items) >= BTRFS_DELAYED_WRITEBACK) {
 		int ret;
-		ret = btrfs_wq_run_delayed_node(delayed_root, root, 1);
+		DEFINE_WAIT(__wait);
+
+		ret = btrfs_wq_run_delayed_node(delayed_root, root, 0);
 		if (ret)
 			return;
 
-		wait_event_interruptible_timeout(
-				delayed_root->wait,
-				(atomic_read(&delayed_root->items) <
-				 BTRFS_DELAYED_BACKGROUND),
-				HZ);
-		return;
+		while (1) {
+			prepare_to_wait(&delayed_root->wait, &__wait,
+					TASK_INTERRUPTIBLE);
+
+			if (refs_newer(delayed_root, seq,
+				       BTRFS_DELAYED_BATCH) ||
+			    atomic_read(&delayed_root->items) <
+			    BTRFS_DELAYED_BACKGROUND) {
+				break;
+			}
+			if (!signal_pending(current))
+				schedule();
+			else
+				break;
+		}
+		finish_wait(&delayed_root->wait, &__wait);
 	}
 
-	btrfs_wq_run_delayed_node(delayed_root, root, 0);
+	btrfs_wq_run_delayed_node(delayed_root, root, BTRFS_DELAYED_BATCH);
 }
 
 /* Will return 0 or -ENOMEM */
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 78b6ad0..1d5c5f7 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -43,6 +43,7 @@ struct btrfs_delayed_root {
 	 */
 	struct list_head prepare_list;
 	atomic_t items;		/* for delayed items */
+	atomic_t items_seq;	/* for delayed items */
 	int nodes;		/* for delayed nodes */
 	wait_queue_head_t wait;
 };
@@ -86,6 +87,7 @@ static inline void btrfs_init_delayed_root(
 				struct btrfs_delayed_root *delayed_root)
 {
 	atomic_set(&delayed_root->items, 0);
+	atomic_set(&delayed_root->items_seq, 0);
 	delayed_root->nodes = 0;
 	spin_lock_init(&delayed_root->lock);
 	init_waitqueue_head(&delayed_root->wait);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 02369a3..6d19a0a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -62,7 +62,7 @@ static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				      struct btrfs_root *root);
-static void btrfs_destroy_pending_snapshots(struct btrfs_transaction *t);
+static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t);
 static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
 static int btrfs_destroy_marked_extents(struct btrfs_root *root,
 					struct extent_io_tree *dirty_pages,
@@ -1291,6 +1291,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 				      0, objectid, NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
+		leaf = NULL;
 		goto fail;
 	}
 
@@ -1334,11 +1335,16 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 
 	btrfs_tree_unlock(leaf);
 
+	return root;
+
 fail:
-	if (ret)
-		return ERR_PTR(ret);
+	if (leaf) {
+		btrfs_tree_unlock(leaf);
+		free_extent_buffer(leaf);
+	}
+	kfree(root);
 
-	return root;
+	return ERR_PTR(ret);
 }
 
 static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
@@ -3253,7 +3259,7 @@ void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
 	if (btrfs_root_refs(&root->root_item) == 0)
 		synchronize_srcu(&fs_info->subvol_srcu);
 
-	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
 		btrfs_free_log(NULL, root);
 		btrfs_free_log_root_tree(NULL, fs_info);
 	}
@@ -3687,7 +3693,7 @@ int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 	return ret;
 }
 
-static void btrfs_destroy_pending_snapshots(struct btrfs_transaction *t)
+static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t)
 {
 	struct btrfs_pending_snapshot *snapshot;
 	struct list_head splice;
@@ -3700,10 +3706,8 @@ static void btrfs_destroy_pending_snapshots(struct btrfs_transaction *t)
 		snapshot = list_entry(splice.next,
 				      struct btrfs_pending_snapshot,
 				      list);
-
+		snapshot->error = -ECANCELED;
 		list_del_init(&snapshot->list);
-
-		kfree(snapshot);
 	}
 }
 
@@ -3840,6 +3844,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 	cur_trans->blocked = 1;
 	wake_up(&root->fs_info->transaction_blocked_wait);
 
+	btrfs_evict_pending_snapshots(cur_trans);
+
 	cur_trans->blocked = 0;
 	wake_up(&root->fs_info->transaction_wait);
 
@@ -3849,8 +3855,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 	btrfs_destroy_delayed_inodes(root);
 	btrfs_assert_delayed_root_empty(root);
 
-	btrfs_destroy_pending_snapshots(cur_trans);
-
 	btrfs_destroy_marked_extents(root, &cur_trans->dirty_pages,
 				     EXTENT_DIRTY);
 	btrfs_destroy_pinned_extent(root,
@@ -3894,6 +3898,8 @@ int btrfs_cleanup_transaction(struct btrfs_root *root)
 		if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
 			wake_up(&root->fs_info->transaction_blocked_wait);
 
+		btrfs_evict_pending_snapshots(t);
+
 		t->blocked = 0;
 		smp_mb();
 		if (waitqueue_active(&root->fs_info->transaction_wait))
@@ -3907,8 +3913,6 @@ int btrfs_cleanup_transaction(struct btrfs_root *root)
 		btrfs_destroy_delayed_inodes(root);
 		btrfs_assert_delayed_root_empty(root);
 
-		btrfs_destroy_pending_snapshots(t);
-
 		btrfs_destroy_delalloc_inodes(root);
 
 		spin_lock(&root->fs_info->trans_lock);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3e074da..3d55123 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -257,7 +257,8 @@ static int exclude_super_stripes(struct btrfs_root *root,
 		cache->bytes_super += stripe_len;
 		ret = add_excluded_extent(root, cache->key.objectid,
 					  stripe_len);
-		BUG_ON(ret); /* -ENOMEM */
+		if (ret)
+			return ret;
 	}
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
@@ -265,13 +266,17 @@ static int exclude_super_stripes(struct btrfs_root *root,
 		ret = btrfs_rmap_block(&root->fs_info->mapping_tree,
 				       cache->key.objectid, bytenr,
 				       0, &logical, &nr, &stripe_len);
-		BUG_ON(ret); /* -ENOMEM */
+		if (ret)
+			return ret;
 
 		while (nr--) {
 			cache->bytes_super += stripe_len;
 			ret = add_excluded_extent(root, logical[nr],
 						  stripe_len);
-			BUG_ON(ret); /* -ENOMEM */
+			if (ret) {
+				kfree(logical);
+				return ret;
+			}
 		}
 
 		kfree(logical);
@@ -1467,8 +1472,11 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
 	if (ret && !insert) {
 		err = -ENOENT;
 		goto out;
+	} else if (ret) {
+		err = -EIO;
+		WARN_ON(1);
+		goto out;
 	}
-	BUG_ON(ret); /* Corruption */
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
@@ -4435,7 +4443,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	spin_lock(&sinfo->lock);
 	spin_lock(&block_rsv->lock);
 
-	block_rsv->size = num_bytes;
+	block_rsv->size = min_t(u64, num_bytes, 512 * 1024 * 1024);
 
 	num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
 		    sinfo->bytes_reserved + sinfo->bytes_readonly +
@@ -4790,14 +4798,49 @@ out_fail:
 	 * If the inodes csum_bytes is the same as the original
 	 * csum_bytes then we know we haven't raced with any free()ers
 	 * so we can just reduce our inodes csum bytes and carry on.
-	 * Otherwise we have to do the normal free thing to account for
-	 * the case that the free side didn't free up its reserve
-	 * because of this outstanding reservation.
 	 */
-	if (BTRFS_I(inode)->csum_bytes == csum_bytes)
+	if (BTRFS_I(inode)->csum_bytes == csum_bytes) {
 		calc_csum_metadata_size(inode, num_bytes, 0);
-	else
-		to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+	} else {
+		u64 orig_csum_bytes = BTRFS_I(inode)->csum_bytes;
+		u64 bytes;
+
+		/*
+		 * This is tricky, but first we need to figure out how much we
+		 * free'd from any free-ers that occured during this
+		 * reservation, so we reset ->csum_bytes to the csum_bytes
+		 * before we dropped our lock, and then call the free for the
+		 * number of bytes that were freed while we were trying our
+		 * reservation.
+		 */
+		bytes = csum_bytes - BTRFS_I(inode)->csum_bytes;
+		BTRFS_I(inode)->csum_bytes = csum_bytes;
+		to_free = calc_csum_metadata_size(inode, bytes, 0);
+
+
+		/*
+		 * Now we need to see how much we would have freed had we not
+		 * been making this reservation and our ->csum_bytes were not
+		 * artificially inflated.
+		 */
+		BTRFS_I(inode)->csum_bytes = csum_bytes - num_bytes;
+		bytes = csum_bytes - orig_csum_bytes;
+		bytes = calc_csum_metadata_size(inode, bytes, 0);
+
+		/*
+		 * Now reset ->csum_bytes to what it should be.  If bytes is
+		 * more than to_free then we would have free'd more space had we
+		 * not had an artificially high ->csum_bytes, so we need to free
+		 * the remainder.  If bytes is the same or less then we don't
+		 * need to do anything, the other free-ers did the correct
+		 * thing.
+		 */
+		BTRFS_I(inode)->csum_bytes = orig_csum_bytes - num_bytes;
+		if (bytes > to_free)
+			to_free = bytes - to_free;
+		else
+			to_free = 0;
+	}
 	spin_unlock(&BTRFS_I(inode)->lock);
 	if (dropped)
 		to_free += btrfs_calc_trans_metadata_size(root, dropped);
@@ -7944,7 +7987,17 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		 * info has super bytes accounted for, otherwise we'll think
 		 * we have more space than we actually do.
 		 */
-		exclude_super_stripes(root, cache);
+		ret = exclude_super_stripes(root, cache);
+		if (ret) {
+			/*
+			 * We may have excluded something, so call this just in
+			 * case.
+			 */
+			free_excluded_extents(root, cache);
+			kfree(cache->free_space_ctl);
+			kfree(cache);
+			goto error;
+		}
 
 		/*
 		 * check for two cases, either we are full, and therefore
@@ -8086,7 +8139,17 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
-	exclude_super_stripes(root, cache);
+	ret = exclude_super_stripes(root, cache);
+	if (ret) {
+		/*
+		 * We may have excluded something, so call this just in
+		 * case.
+		 */
+		free_excluded_extents(root, cache);
+		kfree(cache->free_space_ctl);
+		kfree(cache);
+		return ret;
+	}
 
 	add_new_free_space(cache, root->fs_info, chunk_offset,
 			   chunk_offset + size);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f173c5a..cdee391 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1257,6 +1257,39 @@ int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 				GFP_NOFS);
 }
 
+int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
+{
+	unsigned long index = start >> PAGE_CACHE_SHIFT;
+	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	struct page *page;
+
+	while (index <= end_index) {
+		page = find_get_page(inode->i_mapping, index);
+		BUG_ON(!page); /* Pages should be in the extent_io_tree */
+		clear_page_dirty_for_io(page);
+		page_cache_release(page);
+		index++;
+	}
+	return 0;
+}
+
+int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
+{
+	unsigned long index = start >> PAGE_CACHE_SHIFT;
+	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	struct page *page;
+
+	while (index <= end_index) {
+		page = find_get_page(inode->i_mapping, index);
+		BUG_ON(!page); /* Pages should be in the extent_io_tree */
+		account_page_redirty(page);
+		__set_page_dirty_nobuffers(page);
+		page_cache_release(page);
+		index++;
+	}
+	return 0;
+}
+
 /*
  * helper function to set both pages and extents in the tree writeback
  */
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 6068a19..258c921 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -325,6 +325,8 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset,
 		      unsigned long *map_len);
 int extent_range_uptodate(struct extent_io_tree *tree,
 			  u64 start, u64 end);
+int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
+int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
 int extent_clear_unlock_delalloc(struct inode *inode,
 				struct extent_io_tree *tree,
 				u64 start, u64 end, struct page *locked_page,
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index ec16020..c4628a2 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -118,9 +118,11 @@ struct btrfs_csum_item *btrfs_lookup_csum(struct btrfs_trans_handle *trans,
 		csums_in_item = btrfs_item_size_nr(leaf, path->slots[0]);
 		csums_in_item /= csum_size;
 
-		if (csum_offset >= csums_in_item) {
+		if (csum_offset == csums_in_item) {
 			ret = -EFBIG;
 			goto fail;
+		} else if (csum_offset > csums_in_item) {
+			goto fail;
 		}
 	}
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item);
@@ -728,7 +730,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	sector_sum = sums->sums;
-	trans->adding_csums = 1;
 again:
 	next_offset = (u64)-1;
 	found_next = 0;
@@ -899,7 +900,6 @@ next_sector:
 		goto again;
 	}
 out:
-	trans->adding_csums = 0;
 	btrfs_free_path(path);
 	return ret;
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index af1d060..ade03e6 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -591,6 +591,7 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 		}
 		compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
 		clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+		clear_bit(EXTENT_FLAG_LOGGING, &flags);
 		remove_extent_mapping(em_tree, em);
 		if (no_splits)
 			goto next;
@@ -2141,6 +2142,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 {
 	struct inode *inode = file_inode(file);
 	struct extent_state *cached_state = NULL;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	u64 cur_offset;
 	u64 last_byte;
 	u64 alloc_start;
@@ -2168,6 +2170,11 @@ static long btrfs_fallocate(struct file *file, int mode,
 	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
 	if (ret)
 		return ret;
+	if (root->fs_info->quota_enabled) {
+		ret = btrfs_qgroup_reserve(root, alloc_end - alloc_start);
+		if (ret)
+			goto out_reserve_fail;
+	}
 
 	/*
 	 * wait for ordered IO before we have any locks.  We'll loop again
@@ -2271,6 +2278,9 @@ static long btrfs_fallocate(struct file *file, int mode,
 			     &cached_state, GFP_NOFS);
 out:
 	mutex_unlock(&inode->i_mutex);
+	if (root->fs_info->quota_enabled)
+		btrfs_qgroup_free(root, alloc_end - alloc_start);
+out_reserve_fail:
 	/* Let go of our reservation. */
 	btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
 	return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c226dae..09c58a3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -353,6 +353,7 @@ static noinline int compress_file_range(struct inode *inode,
 	int i;
 	int will_compress;
 	int compress_type = root->fs_info->compress_type;
+	int redirty = 0;
 
 	/* if this is a small write inside eof, kick off a defrag */
 	if ((end - start + 1) < 16 * 1024 &&
@@ -415,6 +416,17 @@ again:
 		if (BTRFS_I(inode)->force_compress)
 			compress_type = BTRFS_I(inode)->force_compress;
 
+		/*
+		 * we need to call clear_page_dirty_for_io on each
+		 * page in the range.  Otherwise applications with the file
+		 * mmap'd can wander in and change the page contents while
+		 * we are compressing them.
+		 *
+		 * If the compression fails for any reason, we set the pages
+		 * dirty again later on.
+		 */
+		extent_range_clear_dirty_for_io(inode, start, end);
+		redirty = 1;
 		ret = btrfs_compress_pages(compress_type,
 					   inode->i_mapping, start,
 					   total_compressed, pages,
@@ -554,6 +566,8 @@ cleanup_and_bail_uncompressed:
 			__set_page_dirty_nobuffers(locked_page);
 			/* unlocked later on in the async handlers */
 		}
+		if (redirty)
+			extent_range_redirty_for_io(inode, start, end);
 		add_async_extent(async_cow, start, end - start + 1,
 				 0, NULL, 0, BTRFS_COMPRESS_NONE);
 		*num_added += 1;
@@ -1743,8 +1757,10 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
 	struct btrfs_ordered_sum *sum;
 
 	list_for_each_entry(sum, list, list) {
+		trans->adding_csums = 1;
 		btrfs_csum_file_blocks(trans,
 		       BTRFS_I(inode)->root->fs_info->csum_root, sum);
+		trans->adding_csums = 0;
 	}
 	return 0;
 }
@@ -2312,6 +2328,7 @@ again:
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = start;
 
+	path->leave_spinning = 1;
 	if (merge) {
 		struct btrfs_file_extent_item *fi;
 		u64 extent_len;
@@ -2368,6 +2385,7 @@ again:
 
 	btrfs_mark_buffer_dirty(leaf);
 	inode_add_bytes(inode, len);
+	btrfs_release_path(path);
 
 	ret = btrfs_inc_extent_ref(trans, root, new->bytenr,
 			new->disk_len, 0,
@@ -2381,6 +2399,7 @@ again:
 	ret = 1;
 out_free_path:
 	btrfs_release_path(path);
+	path->leave_spinning = 0;
 	btrfs_end_transaction(trans, root);
 out_unlock:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, lock_end,
@@ -3676,11 +3695,9 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 	 * 1 for the dir item
 	 * 1 for the dir index
 	 * 1 for the inode ref
-	 * 1 for the inode ref in the tree log
-	 * 2 for the dir entries in the log
 	 * 1 for the inode
 	 */
-	trans = btrfs_start_transaction(root, 8);
+	trans = btrfs_start_transaction(root, 5);
 	if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
 		return trans;
 
@@ -8124,7 +8141,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * inodes.  So 5 * 2 is 10, plus 1 for the new link, so 11 total items
 	 * should cover the worst case number of items we'll modify.
 	 */
-	trans = btrfs_start_transaction(root, 20);
+	trans = btrfs_start_transaction(root, 11);
 	if (IS_ERR(trans)) {
                 ret = PTR_ERR(trans);
                 goto out_notrans;
@@ -8502,6 +8519,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 	struct btrfs_key ins;
 	u64 cur_offset = start;
 	u64 i_size;
+	u64 cur_bytes;
 	int ret = 0;
 	bool own_trans = true;
 
@@ -8516,8 +8534,9 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 			}
 		}
 
-		ret = btrfs_reserve_extent(trans, root,
-					   min(num_bytes, 256ULL * 1024 * 1024),
+		cur_bytes = min(num_bytes, 256ULL * 1024 * 1024);
+		cur_bytes = max(cur_bytes, min_size);
+		ret = btrfs_reserve_extent(trans, root, cur_bytes,
 					   min_size, 0, *alloc_hint, &ins, 1);
 		if (ret) {
 			if (own_trans)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c83086fd..2c02310 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -527,6 +527,8 @@ fail:
 	if (async_transid) {
 		*async_transid = trans->transid;
 		err = btrfs_commit_transaction_async(trans, root, 1);
+		if (err)
+			err = btrfs_commit_transaction(trans, root);
 	} else {
 		err = btrfs_commit_transaction(trans, root);
 	}
@@ -592,16 +594,14 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		*async_transid = trans->transid;
 		ret = btrfs_commit_transaction_async(trans,
 				     root->fs_info->extent_root, 1);
+		if (ret)
+			ret = btrfs_commit_transaction(trans, root);
 	} else {
 		ret = btrfs_commit_transaction(trans,
 					       root->fs_info->extent_root);
 	}
-	if (ret) {
-		/* cleanup_transaction has freed this for us */
-		if (trans->aborted)
-			pending_snapshot = NULL;
+	if (ret)
 		goto fail;
-	}
 
 	ret = pending_snapshot->error;
 	if (ret)
@@ -2245,13 +2245,6 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 	if (ret)
 		return ret;
 
-	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
-			1)) {
-		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
-		mnt_drop_write_file(file);
-		return -EINVAL;
-	}
-
 	if (btrfs_root_readonly(root)) {
 		ret = -EROFS;
 		goto out;
@@ -2306,7 +2299,6 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 		ret = -EINVAL;
 	}
 out:
-	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
 	mnt_drop_write_file(file);
 	return ret;
 }
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index ca52681..b81e0e9 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -26,7 +26,6 @@
 
 void btrfs_tree_lock(struct extent_buffer *eb);
 void btrfs_tree_unlock(struct extent_buffer *eb);
-int btrfs_try_spin_lock(struct extent_buffer *eb);
 
 void btrfs_tree_read_lock(struct extent_buffer *eb);
 void btrfs_tree_read_unlock(struct extent_buffer *eb);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index dc08d77..005c45d 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -557,6 +557,7 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput)
 	INIT_LIST_HEAD(&splice);
 	INIT_LIST_HEAD(&works);
 
+	mutex_lock(&root->fs_info->ordered_operations_mutex);
 	spin_lock(&root->fs_info->ordered_extent_lock);
 	list_splice_init(&root->fs_info->ordered_extents, &splice);
 	while (!list_empty(&splice)) {
@@ -600,6 +601,7 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput)
 
 		cond_resched();
 	}
+	mutex_unlock(&root->fs_info->ordered_operations_mutex);
 }
 
 /*
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index aee4b1c..b44124d 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1153,7 +1153,7 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans,
 	ret = btrfs_find_all_roots(trans, fs_info, node->bytenr,
 				   sgn > 0 ? node->seq - 1 : node->seq, &roots);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
@@ -1275,7 +1275,6 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans,
 	ret = 0;
 unlock:
 	spin_unlock(&fs_info->qgroup_lock);
-out:
 	ulist_free(roots);
 	ulist_free(tmp);
 
@@ -1525,21 +1524,23 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 
 		if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
 		    qg->reserved + qg->rfer + num_bytes >
-		    qg->max_rfer)
+		    qg->max_rfer) {
 			ret = -EDQUOT;
+			goto out;
+		}
 
 		if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) &&
 		    qg->reserved + qg->excl + num_bytes >
-		    qg->max_excl)
+		    qg->max_excl) {
 			ret = -EDQUOT;
+			goto out;
+		}
 
 		list_for_each_entry(glist, &qg->groups, next_group) {
 			ulist_add(ulist, glist->group->qgroupid,
 				  (uintptr_t)glist->group, GFP_ATOMIC);
 		}
 	}
-	if (ret)
-		goto out;
 
 	/*
 	 * no limits exceeded, now record the reservation into all qgroups
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 50695dc..b67171e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1269,6 +1269,8 @@ static int __update_reloc_root(struct btrfs_root *root, int del)
 	}
 	spin_unlock(&rc->reloc_root_tree.lock);
 
+	if (!node)
+		return 0;
 	BUG_ON((struct btrfs_root *)node->data != root);
 
 	if (!del) {
@@ -2238,13 +2240,28 @@ again:
 }
 
 static noinline_for_stack
+void free_reloc_roots(struct list_head *list)
+{
+	struct btrfs_root *reloc_root;
+
+	while (!list_empty(list)) {
+		reloc_root = list_entry(list->next, struct btrfs_root,
+					root_list);
+		__update_reloc_root(reloc_root, 1);
+		free_extent_buffer(reloc_root->node);
+		free_extent_buffer(reloc_root->commit_root);
+		kfree(reloc_root);
+	}
+}
+
+static noinline_for_stack
 int merge_reloc_roots(struct reloc_control *rc)
 {
 	struct btrfs_root *root;
 	struct btrfs_root *reloc_root;
 	LIST_HEAD(reloc_roots);
 	int found = 0;
-	int ret;
+	int ret = 0;
 again:
 	root = rc->extent_root;
 
@@ -2270,20 +2287,33 @@ again:
 			BUG_ON(root->reloc_root != reloc_root);
 
 			ret = merge_reloc_root(rc, root);
-			BUG_ON(ret);
+			if (ret)
+				goto out;
 		} else {
 			list_del_init(&reloc_root->root_list);
 		}
 		ret = btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0, 1);
-		BUG_ON(ret < 0);
+		if (ret < 0) {
+			if (list_empty(&reloc_root->root_list))
+				list_add_tail(&reloc_root->root_list,
+					      &reloc_roots);
+			goto out;
+		}
 	}
 
 	if (found) {
 		found = 0;
 		goto again;
 	}
+out:
+	if (ret) {
+		btrfs_std_error(root->fs_info, ret);
+		if (!list_empty(&reloc_roots))
+			free_reloc_roots(&reloc_roots);
+	}
+
 	BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
-	return 0;
+	return ret;
 }
 
 static void free_block_list(struct rb_root *blocks)
@@ -2818,8 +2848,10 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 	int err = 0;
 
 	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
+	if (!path) {
+		err = -ENOMEM;
+		goto out_path;
+	}
 
 	rb_node = rb_first(blocks);
 	while (rb_node) {
@@ -2858,10 +2890,11 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 		rb_node = rb_next(rb_node);
 	}
 out:
-	free_block_list(blocks);
 	err = finish_pending_nodes(trans, rc, path, err);
 
 	btrfs_free_path(path);
+out_path:
+	free_block_list(blocks);
 	return err;
 }
 
@@ -3698,7 +3731,15 @@ int prepare_to_relocate(struct reloc_control *rc)
 	set_reloc_control(rc);
 
 	trans = btrfs_join_transaction(rc->extent_root);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans)) {
+		unset_reloc_control(rc);
+		/*
+		 * extent tree is not a ref_cow tree and has no reloc_root to
+		 * cleanup.  And callers are responsible to free the above
+		 * block rsv.
+		 */
+		return PTR_ERR(trans);
+	}
 	btrfs_commit_transaction(trans, rc->extent_root);
 	return 0;
 }
@@ -3730,7 +3771,11 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 	while (1) {
 		progress++;
 		trans = btrfs_start_transaction(rc->extent_root, 0);
-		BUG_ON(IS_ERR(trans));
+		if (IS_ERR(trans)) {
+			err = PTR_ERR(trans);
+			trans = NULL;
+			break;
+		}
 restart:
 		if (update_backref_cache(trans, &rc->backref_cache)) {
 			btrfs_end_transaction(trans, rc->extent_root);
@@ -4264,14 +4309,9 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 out_free:
 	kfree(rc);
 out:
-	while (!list_empty(&reloc_roots)) {
-		reloc_root = list_entry(reloc_roots.next,
-					struct btrfs_root, root_list);
-		list_del(&reloc_root->root_list);
-		free_extent_buffer(reloc_root->node);
-		free_extent_buffer(reloc_root->commit_root);
-		kfree(reloc_root);
-	}
+	if (!list_empty(&reloc_roots))
+		free_reloc_roots(&reloc_roots);
+
 	btrfs_free_path(path);
 
 	if (err == 0) {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 53c3501..85e072b 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -542,7 +542,6 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 	eb = path->nodes[0];
 	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
 	item_size = btrfs_item_size_nr(eb, path->slots[0]);
-	btrfs_release_path(path);
 
 	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		do {
@@ -558,7 +557,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 				ret < 0 ? -1 : ref_level,
 				ret < 0 ? -1 : ref_root);
 		} while (ret != 1);
+		btrfs_release_path(path);
 	} else {
+		btrfs_release_path(path);
 		swarn.path = path;
 		swarn.dev = dev;
 		iterate_extent_inodes(fs_info, found_key.objectid,
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index f7a8b86..c85e7c6 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -3945,12 +3945,10 @@ static int is_extent_unchanged(struct send_ctx *sctx,
 		    found_key.type != key.type) {
 			key.offset += right_len;
 			break;
-		} else {
-			if (found_key.offset != key.offset + right_len) {
-				/* Should really not happen */
-				ret = -EIO;
-				goto out;
-			}
+		}
+		if (found_key.offset != key.offset + right_len) {
+			ret = 0;
+			goto out;
 		}
 		key = found_key;
 	}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 68a29a1..f6b8859 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1558,6 +1558,7 @@ static struct file_system_type btrfs_fs_type = {
 	.kill_sb	= btrfs_kill_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("btrfs");
 
 /*
  * used by btrfsctl to scan devices when no FS is mounted
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index e52da6f..50767bb 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -625,14 +625,13 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
 	btrfs_trans_release_metadata(trans, root);
 	trans->block_rsv = NULL;
-	/*
-	 * the same root has to be passed to start_transaction and
-	 * end_transaction. Subvolume quota depends on this.
-	 */
-	WARN_ON(trans->root != root);
 
 	if (trans->qgroup_reserved) {
-		btrfs_qgroup_free(root, trans->qgroup_reserved);
+		/*
+		 * the same root has to be passed here between start_transaction
+		 * and end_transaction. Subvolume quota depends on this.
+		 */
+		btrfs_qgroup_free(trans->root, trans->qgroup_reserved);
 		trans->qgroup_reserved = 0;
 	}
 
@@ -1052,7 +1051,12 @@ int btrfs_defrag_root(struct btrfs_root *root)
 
 /*
  * new snapshots need to be created at a very specific time in the
- * transaction commit.  This does the actual creation
+ * transaction commit.  This does the actual creation.
+ *
+ * Note:
+ * If the error which may affect the commitment of the current transaction
+ * happens, we should return the error number. If the error which just affect
+ * the creation of the pending snapshots, just return 0.
  */
 static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 				   struct btrfs_fs_info *fs_info,
@@ -1071,7 +1075,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	struct extent_buffer *tmp;
 	struct extent_buffer *old;
 	struct timespec cur_time = CURRENT_TIME;
-	int ret;
+	int ret = 0;
 	u64 to_reserve = 0;
 	u64 index = 0;
 	u64 objectid;
@@ -1080,40 +1084,36 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		ret = pending->error = -ENOMEM;
-		return ret;
+		pending->error = -ENOMEM;
+		return 0;
 	}
 
 	new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
 	if (!new_root_item) {
-		ret = pending->error = -ENOMEM;
+		pending->error = -ENOMEM;
 		goto root_item_alloc_fail;
 	}
 
-	ret = btrfs_find_free_objectid(tree_root, &objectid);
-	if (ret) {
-		pending->error = ret;
+	pending->error = btrfs_find_free_objectid(tree_root, &objectid);
+	if (pending->error)
 		goto no_free_objectid;
-	}
 
 	btrfs_reloc_pre_snapshot(trans, pending, &to_reserve);
 
 	if (to_reserve > 0) {
-		ret = btrfs_block_rsv_add(root, &pending->block_rsv,
-					  to_reserve,
-					  BTRFS_RESERVE_NO_FLUSH);
-		if (ret) {
-			pending->error = ret;
+		pending->error = btrfs_block_rsv_add(root,
+						     &pending->block_rsv,
+						     to_reserve,
+						     BTRFS_RESERVE_NO_FLUSH);
+		if (pending->error)
 			goto no_free_objectid;
-		}
 	}
 
-	ret = btrfs_qgroup_inherit(trans, fs_info, root->root_key.objectid,
-				   objectid, pending->inherit);
-	if (ret) {
-		pending->error = ret;
+	pending->error = btrfs_qgroup_inherit(trans, fs_info,
+					      root->root_key.objectid,
+					      objectid, pending->inherit);
+	if (pending->error)
 		goto no_free_objectid;
-	}
 
 	key.objectid = objectid;
 	key.offset = (u64)-1;
@@ -1141,7 +1141,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 					 dentry->d_name.len, 0);
 	if (dir_item != NULL && !IS_ERR(dir_item)) {
 		pending->error = -EEXIST;
-		goto fail;
+		goto dir_item_existed;
 	} else if (IS_ERR(dir_item)) {
 		ret = PTR_ERR(dir_item);
 		btrfs_abort_transaction(trans, root, ret);
@@ -1272,6 +1272,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
 fail:
+	pending->error = ret;
+dir_item_existed:
 	trans->block_rsv = rsv;
 	trans->bytes_reserved = 0;
 no_free_objectid:
@@ -1287,12 +1289,17 @@ root_item_alloc_fail:
 static noinline int create_pending_snapshots(struct btrfs_trans_handle *trans,
 					     struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_pending_snapshot *pending;
+	struct btrfs_pending_snapshot *pending, *next;
 	struct list_head *head = &trans->transaction->pending_snapshots;
+	int ret = 0;
 
-	list_for_each_entry(pending, head, list)
-		create_pending_snapshot(trans, fs_info, pending);
-	return 0;
+	list_for_each_entry_safe(pending, next, head, list) {
+		list_del(&pending->list);
+		ret = create_pending_snapshot(trans, fs_info, pending);
+		if (ret)
+			break;
+	}
+	return ret;
 }
 
 static void update_super_roots(struct btrfs_root *root)
@@ -1448,6 +1455,13 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans,
 	btrfs_abort_transaction(trans, root, err);
 
 	spin_lock(&root->fs_info->trans_lock);
+
+	if (list_empty(&cur_trans->list)) {
+		spin_unlock(&root->fs_info->trans_lock);
+		btrfs_end_transaction(trans, root);
+		return;
+	}
+
 	list_del_init(&cur_trans->list);
 	if (cur_trans == root->fs_info->running_transaction) {
 		root->fs_info->trans_no_join = 1;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index c7ef569..ef96381 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -317,6 +317,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 	unsigned long src_ptr;
 	unsigned long dst_ptr;
 	int overwrite_root = 0;
+	bool inode_item = key->type == BTRFS_INODE_ITEM_KEY;
 
 	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
 		overwrite_root = 1;
@@ -326,6 +327,9 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 
 	/* look for the key in the destination tree */
 	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+	if (ret < 0)
+		return ret;
+
 	if (ret == 0) {
 		char *src_copy;
 		char *dst_copy;
@@ -367,6 +371,30 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 			return 0;
 		}
 
+		/*
+		 * We need to load the old nbytes into the inode so when we
+		 * replay the extents we've logged we get the right nbytes.
+		 */
+		if (inode_item) {
+			struct btrfs_inode_item *item;
+			u64 nbytes;
+
+			item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+					      struct btrfs_inode_item);
+			nbytes = btrfs_inode_nbytes(path->nodes[0], item);
+			item = btrfs_item_ptr(eb, slot,
+					      struct btrfs_inode_item);
+			btrfs_set_inode_nbytes(eb, item, nbytes);
+		}
+	} else if (inode_item) {
+		struct btrfs_inode_item *item;
+
+		/*
+		 * New inode, set nbytes to 0 so that the nbytes comes out
+		 * properly when we replay the extents.
+		 */
+		item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item);
+		btrfs_set_inode_nbytes(eb, item, 0);
 	}
 insert:
 	btrfs_release_path(path);
@@ -486,7 +514,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	int found_type;
 	u64 extent_end;
 	u64 start = key->offset;
-	u64 saved_nbytes;
+	u64 nbytes = 0;
 	struct btrfs_file_extent_item *item;
 	struct inode *inode = NULL;
 	unsigned long size;
@@ -496,10 +524,19 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	found_type = btrfs_file_extent_type(eb, item);
 
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
-	    found_type == BTRFS_FILE_EXTENT_PREALLOC)
-		extent_end = start + btrfs_file_extent_num_bytes(eb, item);
-	else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
+	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+		nbytes = btrfs_file_extent_num_bytes(eb, item);
+		extent_end = start + nbytes;
+
+		/*
+		 * We don't add to the inodes nbytes if we are prealloc or a
+		 * hole.
+		 */
+		if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
+			nbytes = 0;
+	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		size = btrfs_file_extent_inline_len(eb, item);
+		nbytes = btrfs_file_extent_ram_bytes(eb, item);
 		extent_end = ALIGN(start + size, root->sectorsize);
 	} else {
 		ret = 0;
@@ -548,7 +585,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	saved_nbytes = inode_get_bytes(inode);
 	/* drop any overlapping extents */
 	ret = btrfs_drop_extents(trans, root, inode, start, extent_end, 1);
 	BUG_ON(ret);
@@ -635,7 +671,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		BUG_ON(ret);
 	}
 
-	inode_set_bytes(inode, saved_nbytes);
+	inode_add_bytes(inode, nbytes);
 	ret = btrfs_update_inode(trans, root, inode);
 out:
 	if (inode)
@@ -1382,7 +1418,10 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
 
 	btrfs_release_path(path);
 	if (ret == 0) {
-		btrfs_inc_nlink(inode);
+		if (!inode->i_nlink)
+			set_nlink(inode, 1);
+		else
+			btrfs_inc_nlink(inode);
 		ret = btrfs_update_inode(trans, root, inode);
 	} else if (ret == -EEXIST) {
 		ret = 0;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 35bb2d4..2854c82 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -684,6 +684,12 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 		__btrfs_close_devices(fs_devices);
 		free_fs_devices(fs_devices);
 	}
+	/*
+	 * Wait for rcu kworkers under __btrfs_close_devices
+	 * to finish all blkdev_puts so device is really
+	 * free when umount is done.
+	 */
+	rcu_barrier();
 	return ret;
 }
 
@@ -2379,7 +2385,11 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
 		return ret;
 
 	trans = btrfs_start_transaction(root, 0);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		btrfs_std_error(root->fs_info, ret);
+		return ret;
+	}
 
 	lock_chunks(root);
 
@@ -3050,7 +3060,8 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info)
 
 	unset_balance_control(fs_info);
 	ret = del_balance_item(fs_info->tree_root);
-	BUG_ON(ret);
+	if (ret)
+		btrfs_std_error(fs_info, ret);
 
 	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
 }
@@ -3230,6 +3241,11 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		update_ioctl_balance_args(fs_info, 0, bargs);
 	}
 
+	if ((ret && ret != -ECANCELED && ret != -ENOSPC) ||
+	    balance_need_close(fs_info)) {
+		__cancel_balance(fs_info);
+	}
+
 	wake_up(&fs_info->balance_wait_q);
 
 	return ret;
@@ -4919,7 +4935,18 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 	em = lookup_extent_mapping(em_tree, chunk_start, 1);
 	read_unlock(&em_tree->lock);
 
-	BUG_ON(!em || em->start != chunk_start);
+	if (!em) {
+		printk(KERN_ERR "btrfs: couldn't find em for chunk %Lu\n",
+		       chunk_start);
+		return -EIO;
+	}
+
+	if (em->start != chunk_start) {
+		printk(KERN_ERR "btrfs: bad chunk start, em=%Lu, wanted=%Lu\n",
+		       em->start, chunk_start);
+		free_extent_map(em);
+		return -EIO;
+	}
 	map = (struct map_lookup *)em->bdev;
 
 	length = em->len;
diff --git a/fs/buffer.c b/fs/buffer.c
index b4dcb34..10ef81e 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -865,8 +865,6 @@ try_again:
 
 		/* Link the buffer to its page */
 		set_bh_page(bh, page, offset);
-
-		init_buffer(bh, NULL, NULL);
 	}
 	return head;
 /*
@@ -2949,7 +2947,7 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
 	}
 }
 
-int submit_bh(int rw, struct buffer_head * bh)
+int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 {
 	struct bio *bio;
 	int ret = 0;
@@ -2984,6 +2982,7 @@ int submit_bh(int rw, struct buffer_head * bh)
 
 	bio->bi_end_io = end_bio_bh_io_sync;
 	bio->bi_private = bh;
+	bio->bi_flags |= bio_flags;
 
 	/* Take care of bh's that straddle the end of the device */
 	guard_bh_eod(rw, bio, bh);
@@ -2997,6 +2996,12 @@ int submit_bh(int rw, struct buffer_head * bh)
 	bio_put(bio);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(_submit_bh);
+
+int submit_bh(int rw, struct buffer_head *bh)
+{
+	return _submit_bh(rw, bh, 0);
+}
 EXPORT_SYMBOL(submit_bh);
 
 /**
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 9fe17c6c..6ddc0bc 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -952,6 +952,7 @@ static struct file_system_type ceph_fs_type = {
 	.kill_sb	= ceph_kill_sb,
 	.fs_flags	= FS_RENAME_DOES_D_MOVE,
 };
+MODULE_ALIAS_FS("ceph");
 
 #define _STRINGIFY(x) #x
 #define STRINGIFY(x) _STRINGIFY(x)
diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c
index cfd1ce3..1d36db1 100644
--- a/fs/cifs/asn1.c
+++ b/fs/cifs/asn1.c
@@ -614,53 +614,10 @@ decode_negTokenInit(unsigned char *security_blob, int length,
 		}
 	}
 
-	/* mechlistMIC */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		/* Check if we have reached the end of the blob, but with
-		   no mechListMic (e.g. NTLMSSP instead of KRB5) */
-		if (ctx.error == ASN1_ERR_DEC_EMPTY)
-			goto decode_negtoken_exit;
-		cFYI(1, "Error decoding last part negTokenInit exit3");
-		return 0;
-	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
-		/* tag = 3 indicating mechListMIC */
-		cFYI(1, "Exit 4 cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-		return 0;
-	}
-
-	/* sequence */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, "Error decoding last part negTokenInit exit5");
-		return 0;
-	} else if ((cls != ASN1_UNI) || (con != ASN1_CON)
-		   || (tag != ASN1_SEQ)) {
-		cFYI(1, "cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-	}
-
-	/* sequence of */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, "Error decoding last part negTokenInit exit 7");
-		return 0;
-	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
-		cFYI(1, "Exit 8 cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-		return 0;
-	}
-
-	/* general string */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, "Error decoding last part negTokenInit exit9");
-		return 0;
-	} else if ((cls != ASN1_UNI) || (con != ASN1_PRI)
-		   || (tag != ASN1_GENSTR)) {
-		cFYI(1, "Exit10 cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-		return 0;
-	}
-	cFYI(1, "Need to call asn1_octets_decode() function for %s",
-		ctx.pointer);	/* is this UTF-8 or ASCII? */
-decode_negtoken_exit:
+	/*
+	 * We currently ignore anything at the end of the SPNEGO blob after
+	 * the mechTypes have been parsed, since none of that info is
+	 * used at the moment.
+	 */
 	return 1;
 }
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 1a052c0..345fc89 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -91,6 +91,30 @@ struct workqueue_struct	*cifsiod_wq;
 __u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE];
 #endif
 
+/*
+ * Bumps refcount for cifs super block.
+ * Note that it should be only called if a referece to VFS super block is
+ * already held, e.g. in open-type syscalls context. Otherwise it can race with
+ * atomic_dec_and_test in deactivate_locked_super.
+ */
+void
+cifs_sb_active(struct super_block *sb)
+{
+	struct cifs_sb_info *server = CIFS_SB(sb);
+
+	if (atomic_inc_return(&server->active) == 1)
+		atomic_inc(&sb->s_active);
+}
+
+void
+cifs_sb_deactive(struct super_block *sb)
+{
+	struct cifs_sb_info *server = CIFS_SB(sb);
+
+	if (atomic_dec_and_test(&server->active))
+		deactivate_super(sb);
+}
+
 static int
 cifs_read_super(struct super_block *sb)
 {
@@ -777,6 +801,7 @@ struct file_system_type cifs_fs_type = {
 	.kill_sb = cifs_kill_sb,
 	/*  .fs_flags */
 };
+MODULE_ALIAS_FS("cifs");
 const struct inode_operations cifs_dir_inode_ops = {
 	.create = cifs_create,
 	.atomic_open = cifs_atomic_open,
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 7163419..0e32c34 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -41,6 +41,10 @@ extern struct file_system_type cifs_fs_type;
 extern const struct address_space_operations cifs_addr_ops;
 extern const struct address_space_operations cifs_addr_ops_smallbuf;
 
+/* Functions related to super block operations */
+extern void cifs_sb_active(struct super_block *sb);
+extern void cifs_sb_deactive(struct super_block *sb);
+
 /* Functions related to inodes */
 extern const struct inode_operations cifs_dir_inode_ops;
 extern struct inode *cifs_root_iget(struct super_block *);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 7353bc5..8e2e799 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1909,12 +1909,12 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
 	} while (rc == -EAGAIN);
 
 	for (i = 0; i < wdata->nr_pages; i++) {
+		unlock_page(wdata->pages[i]);
 		if (rc != 0) {
 			SetPageError(wdata->pages[i]);
 			end_page_writeback(wdata->pages[i]);
 			page_cache_release(wdata->pages[i]);
 		}
-		unlock_page(wdata->pages[i]);
 	}
 
 	mapping_set_error(inode->i_mapping, rc);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 54125e0..21b3a29 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -97,7 +97,7 @@ enum {
 	Opt_user, Opt_pass, Opt_ip,
 	Opt_unc, Opt_domain,
 	Opt_srcaddr, Opt_prefixpath,
-	Opt_iocharset, Opt_sockopt,
+	Opt_iocharset,
 	Opt_netbiosname, Opt_servern,
 	Opt_ver, Opt_vers, Opt_sec, Opt_cache,
 
@@ -202,7 +202,6 @@ static const match_table_t cifs_mount_option_tokens = {
 	{ Opt_srcaddr, "srcaddr=%s" },
 	{ Opt_prefixpath, "prefixpath=%s" },
 	{ Opt_iocharset, "iocharset=%s" },
-	{ Opt_sockopt, "sockopt=%s" },
 	{ Opt_netbiosname, "netbiosname=%s" },
 	{ Opt_servern, "servern=%s" },
 	{ Opt_ver, "ver=%s" },
@@ -1576,14 +1575,24 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			}
 			break;
 		case Opt_blank_pass:
-			vol->password = NULL;
-			break;
-		case Opt_pass:
 			/* passwords have to be handled differently
 			 * to allow the character used for deliminator
 			 * to be passed within them
 			 */
 
+			/*
+			 * Check if this is a case where the  password
+			 * starts with a delimiter
+			 */
+			tmp_end = strchr(data, '=');
+			tmp_end++;
+			if (!(tmp_end < end && tmp_end[1] == delim)) {
+				/* No it is not. Set the password to NULL */
+				vol->password = NULL;
+				break;
+			}
+			/* Yes it is. Drop down to Opt_pass below.*/
+		case Opt_pass:
 			/* Obtain the value string */
 			value = strchr(data, '=');
 			value++;
@@ -1752,19 +1761,6 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			 */
 			cFYI(1, "iocharset set to %s", string);
 			break;
-		case Opt_sockopt:
-			string = match_strdup(args);
-			if (string == NULL)
-				goto out_nomem;
-
-			if (strnicmp(string, "TCP_NODELAY", 11) == 0) {
-				printk(KERN_WARNING "CIFS: the "
-					"sockopt=TCP_NODELAY option has been "
-					"deprecated and will be removed "
-					"in 3.9\n");
-				vol->sockopt_tcp_nodelay = 1;
-			}
-			break;
 		case Opt_netbiosname:
 			string = match_strdup(args);
 			if (string == NULL)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 8c0d855..7a0dd99 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -300,6 +300,8 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
 	mutex_init(&cfile->fh_mutex);
 
+	cifs_sb_active(inode->i_sb);
+
 	/*
 	 * If the server returned a read oplock and we have mandatory brlocks,
 	 * set oplock level to None.
@@ -349,7 +351,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 	struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct super_block *sb = inode->i_sb;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifsLockInfo *li, *tmp;
 	struct cifs_fid fid;
 	struct cifs_pending_open open;
@@ -414,6 +417,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 
 	cifs_put_tlink(cifs_file->tlink);
 	dput(cifs_file->dentry);
+	cifs_sb_deactive(sb);
 	kfree(cifs_file);
 }
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 83f2606..20887bf 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -995,6 +995,15 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
 		return PTR_ERR(tlink);
 	tcon = tlink_tcon(tlink);
 
+	/*
+	 * We cannot rename the file if the server doesn't support
+	 * CAP_INFOLEVEL_PASSTHRU
+	 */
+	if (!(tcon->ses->capabilities & CAP_INFOLEVEL_PASSTHRU)) {
+		rc = -EBUSY;
+		goto out;
+	}
+
 	rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN,
 			 DELETE|FILE_WRITE_ATTRIBUTES, CREATE_NOT_DIR,
 			 &netfid, &oplock, NULL, cifs_sb->local_nls,
@@ -1023,7 +1032,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
 					current->tgid);
 		/* although we would like to mark the file hidden
  		   if that fails we will still try to rename it */
-		if (rc != 0)
+		if (!rc)
 			cifsInode->cifsAttrs = dosattr;
 		else
 			dosattr = origattr; /* since not able to change them */
@@ -1034,7 +1043,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
 				   cifs_sb->mnt_cifs_flags &
 					    CIFS_MOUNT_MAP_SPECIAL_CHR);
 	if (rc != 0) {
-		rc = -ETXTBSY;
+		rc = -EBUSY;
 		goto undo_setattr;
 	}
 
@@ -1053,7 +1062,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
 		if (rc == -ENOENT)
 			rc = 0;
 		else if (rc != 0) {
-			rc = -ETXTBSY;
+			rc = -EBUSY;
 			goto undo_rename;
 		}
 		cifsInode->delete_pending = true;
@@ -1160,15 +1169,13 @@ psx_del_no_retry:
 			cifs_drop_nlink(inode);
 	} else if (rc == -ENOENT) {
 		d_drop(dentry);
-	} else if (rc == -ETXTBSY) {
+	} else if (rc == -EBUSY) {
 		if (server->ops->rename_pending_delete) {
 			rc = server->ops->rename_pending_delete(full_path,
 								dentry, xid);
 			if (rc == 0)
 				cifs_drop_nlink(inode);
 		}
-		if (rc == -ETXTBSY)
-			rc = -EBUSY;
 	} else if ((rc == -EACCES) && (dosattr == 0) && inode) {
 		attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
 		if (attrs == NULL) {
@@ -1509,7 +1516,7 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
 	 * source. Note that cross directory moves do not work with
 	 * rename by filehandle to various Windows servers.
 	 */
-	if (rc == 0 || rc != -ETXTBSY)
+	if (rc == 0 || rc != -EBUSY)
 		goto do_rename_exit;
 
 	/* open-file renames don't work across directories */
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index a82bc51..c0b25b2 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -62,7 +62,7 @@ static const struct smb_to_posix_error mapping_table_ERRDOS[] = {
 	{ERRdiffdevice, -EXDEV},
 	{ERRnofiles, -ENOENT},
 	{ERRwriteprot, -EROFS},
-	{ERRbadshare, -ETXTBSY},
+	{ERRbadshare, -EBUSY},
 	{ERRlock, -EACCES},
 	{ERRunsup, -EINVAL},
 	{ERRnosuchshare, -ENXIO},
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index c9c7aa7..bceffe7 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -744,4 +744,5 @@ struct smb_version_values smb30_values = {
 	.cap_unix = 0,
 	.cap_nt_find = SMB2_NT_FIND,
 	.cap_large_files = SMB2_LARGE_FILES,
+	.oplock_read = SMB2_OPLOCK_LEVEL_II,
 };
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index dada9d0..4dcc0d8 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -329,4 +329,5 @@ struct file_system_type coda_fs_type = {
 	.kill_sb	= kill_anon_super,
 	.fs_flags	= FS_BINARY_MOUNTDATA,
 };
+MODULE_ALIAS_FS("coda");
 
diff --git a/fs/compat.c b/fs/compat.c
index fe40fde..d487985 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -558,6 +558,10 @@ ssize_t compat_rw_copy_check_uvector(int type,
 	}
 	*ret_pointer = iov;
 
+	ret = -EFAULT;
+	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
+		goto out;
+
 	/*
 	 * Single unix specification:
 	 * We should -EINVAL if an element length is not >= 0 and fitting an
@@ -1080,17 +1084,12 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	if (!file->f_op)
 		goto out;
 
-	ret = -EFAULT;
-	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
-		goto out;
-
-	tot_len = compat_rw_copy_check_uvector(type, uvector, nr_segs,
+	ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
 					       UIO_FASTIOV, iovstack, &iov);
-	if (tot_len == 0) {
-		ret = 0;
+	if (ret <= 0)
 		goto out;
-	}
 
+	tot_len = ret;
 	ret = rw_verify_area(type, file, pos, tot_len);
 	if (ret < 0)
 		goto out;
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index aee0a7e..7f26c3c 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -114,6 +114,7 @@ static struct file_system_type configfs_fs_type = {
 	.mount		= configfs_do_mount,
 	.kill_sb	= kill_litter_super,
 };
+MODULE_ALIAS_FS("configfs");
 
 struct dentry *configfs_pin_fs(void)
 {
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 3ceb9ec..35b1c7b 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -573,6 +573,7 @@ static struct file_system_type cramfs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("cramfs");
 
 static int __init init_cramfs_fs(void)
 {
diff --git a/fs/dcache.c b/fs/dcache.c
index fbfae008..e8bc342 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2542,7 +2542,6 @@ static int prepend_path(const struct path *path,
 	bool slash = false;
 	int error = 0;
 
-	br_read_lock(&vfsmount_lock);
 	while (dentry != root->dentry || vfsmnt != root->mnt) {
 		struct dentry * parent;
 
@@ -2572,8 +2571,6 @@ static int prepend_path(const struct path *path,
 	if (!error && !slash)
 		error = prepend(buffer, buflen, "/", 1);
 
-out:
-	br_read_unlock(&vfsmount_lock);
 	return error;
 
 global_root:
@@ -2590,7 +2587,7 @@ global_root:
 		error = prepend(buffer, buflen, "/", 1);
 	if (!error)
 		error = is_mounted(vfsmnt) ? 1 : 2;
-	goto out;
+	return error;
 }
 
 /**
@@ -2617,9 +2614,11 @@ char *__d_path(const struct path *path,
 	int error;
 
 	prepend(&res, &buflen, "\0", 1);
+	br_read_lock(&vfsmount_lock);
 	write_seqlock(&rename_lock);
 	error = prepend_path(path, root, &res, &buflen);
 	write_sequnlock(&rename_lock);
+	br_read_unlock(&vfsmount_lock);
 
 	if (error < 0)
 		return ERR_PTR(error);
@@ -2636,9 +2635,11 @@ char *d_absolute_path(const struct path *path,
 	int error;
 
 	prepend(&res, &buflen, "\0", 1);
+	br_read_lock(&vfsmount_lock);
 	write_seqlock(&rename_lock);
 	error = prepend_path(path, &root, &res, &buflen);
 	write_sequnlock(&rename_lock);
+	br_read_unlock(&vfsmount_lock);
 
 	if (error > 1)
 		error = -EINVAL;
@@ -2702,11 +2703,13 @@ char *d_path(const struct path *path, char *buf, int buflen)
 		return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
 
 	get_fs_root(current->fs, &root);
+	br_read_lock(&vfsmount_lock);
 	write_seqlock(&rename_lock);
 	error = path_with_deleted(path, &root, &res, &buflen);
+	write_sequnlock(&rename_lock);
+	br_read_unlock(&vfsmount_lock);
 	if (error < 0)
 		res = ERR_PTR(error);
-	write_sequnlock(&rename_lock);
 	path_put(&root);
 	return res;
 }
@@ -2830,6 +2833,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 	get_fs_root_and_pwd(current->fs, &root, &pwd);
 
 	error = -ENOENT;
+	br_read_lock(&vfsmount_lock);
 	write_seqlock(&rename_lock);
 	if (!d_unlinked(pwd.dentry)) {
 		unsigned long len;
@@ -2839,6 +2843,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 		prepend(&cwd, &buflen, "\0", 1);
 		error = prepend_path(&pwd, &root, &cwd, &buflen);
 		write_sequnlock(&rename_lock);
+		br_read_unlock(&vfsmount_lock);
 
 		if (error < 0)
 			goto out;
@@ -2859,6 +2864,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 		}
 	} else {
 		write_sequnlock(&rename_lock);
+		br_read_unlock(&vfsmount_lock);
 	}
 
 out:
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 0c4f80b..4888cb3 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -299,6 +299,7 @@ static struct file_system_type debug_fs_type = {
 	.mount =	debug_mount,
 	.kill_sb =	kill_litter_super,
 };
+MODULE_ALIAS_FS("debugfs");
 
 static struct dentry *__create_file(const char *name, umode_t mode,
 				    struct dentry *parent, void *data,
diff --git a/fs/direct-io.c b/fs/direct-io.c
index f853263..cfb816d 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -672,12 +672,6 @@ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio,
 		if (sdio->final_block_in_bio != sdio->cur_page_block ||
 		    cur_offset != bio_next_offset)
 			dio_bio_submit(dio, sdio);
-		/*
-		 * Submit now if the underlying fs is about to perform a
-		 * metadata read
-		 */
-		else if (sdio->boundary)
-			dio_bio_submit(dio, sdio);
 	}
 
 	if (sdio->bio == NULL) {
@@ -737,16 +731,6 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 	    sdio->cur_page_block +
 	    (sdio->cur_page_len >> sdio->blkbits) == blocknr) {
 		sdio->cur_page_len += len;
-
-		/*
-		 * If sdio->boundary then we want to schedule the IO now to
-		 * avoid metadata seeks.
-		 */
-		if (sdio->boundary) {
-			ret = dio_send_cur_page(dio, sdio, map_bh);
-			page_cache_release(sdio->cur_page);
-			sdio->cur_page = NULL;
-		}
 		goto out;
 	}
 
@@ -758,7 +742,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 		page_cache_release(sdio->cur_page);
 		sdio->cur_page = NULL;
 		if (ret)
-			goto out;
+			return ret;
 	}
 
 	page_cache_get(page);		/* It is in dio */
@@ -768,6 +752,16 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 	sdio->cur_page_block = blocknr;
 	sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits;
 out:
+	/*
+	 * If sdio->boundary then we want to schedule the IO now to
+	 * avoid metadata seeks.
+	 */
+	if (sdio->boundary) {
+		ret = dio_send_cur_page(dio, sdio, map_bh);
+		dio_bio_submit(dio, sdio);
+		page_cache_release(sdio->cur_page);
+		sdio->cur_page = NULL;
+	}
 	return ret;
 }
 
@@ -969,7 +963,8 @@ do_holes:
 			this_chunk_bytes = this_chunk_blocks << blkbits;
 			BUG_ON(this_chunk_bytes == 0);
 
-			sdio->boundary = buffer_boundary(map_bh);
+			if (this_chunk_blocks == sdio->blocks_available)
+				sdio->boundary = buffer_boundary(map_bh);
 			ret = submit_page_section(dio, sdio, page,
 						  offset_in_page,
 						  this_chunk_bytes,
diff --git a/fs/ecryptfs/Kconfig b/fs/ecryptfs/Kconfig
index e15ef38..434aa31 100644
--- a/fs/ecryptfs/Kconfig
+++ b/fs/ecryptfs/Kconfig
@@ -12,3 +12,11 @@ config ECRYPT_FS
 
 	  To compile this file system support as a module, choose M here: the
 	  module will be called ecryptfs.
+
+config ECRYPT_FS_MESSAGING
+	bool "Enable notifications for userspace key wrap/unwrap"
+	depends on ECRYPT_FS
+	help
+	  Enables the /dev/ecryptfs entry for use by ecryptfsd. This allows
+	  for userspace to wrap/unwrap file encryption keys by other
+	  backends, like OpenSSL.
diff --git a/fs/ecryptfs/Makefile b/fs/ecryptfs/Makefile
index 2cc9ee4..49678a6 100644
--- a/fs/ecryptfs/Makefile
+++ b/fs/ecryptfs/Makefile
@@ -1,7 +1,10 @@
 #
-# Makefile for the Linux 2.6 eCryptfs
+# Makefile for the Linux eCryptfs
 #
 
 obj-$(CONFIG_ECRYPT_FS) += ecryptfs.o
 
-ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o miscdev.o kthread.o debug.o
+ecryptfs-y := dentry.o file.o inode.o main.o super.o mmap.o read_write.o \
+	      crypto.o keystore.o kthread.o debug.o
+
+ecryptfs-$(CONFIG_ECRYPT_FS_MESSAGING) += messaging.o miscdev.o
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index a7b0c2d..d5c25db 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -301,17 +301,14 @@ int virt_to_scatterlist(const void *addr, int size, struct scatterlist *sg,
 	while (size > 0 && i < sg_size) {
 		pg = virt_to_page(addr);
 		offset = offset_in_page(addr);
-		if (sg)
-			sg_set_page(&sg[i], pg, 0, offset);
+		sg_set_page(&sg[i], pg, 0, offset);
 		remainder_of_page = PAGE_CACHE_SIZE - offset;
 		if (size >= remainder_of_page) {
-			if (sg)
-				sg[i].length = remainder_of_page;
+			sg[i].length = remainder_of_page;
 			addr += remainder_of_page;
 			size -= remainder_of_page;
 		} else {
-			if (sg)
-				sg[i].length = size;
+			sg[i].length = size;
 			addr += size;
 			size = 0;
 		}
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 1b5d9af..bf12ba5 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -45,14 +45,12 @@
 static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *lower_dentry;
-	struct vfsmount *lower_mnt;
 	int rc = 1;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
-	lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
 	if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
 		goto out;
 	rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 7e2c6f5..dd299b3 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -172,6 +172,19 @@ ecryptfs_get_key_payload_data(struct key *key)
 #define ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE 24
 #define ECRYPTFS_ENCRYPTED_DENTRY_NAME_LEN (18 + 1 + 4 + 1 + 32)
 
+#ifdef CONFIG_ECRYPT_FS_MESSAGING
+# define ECRYPTFS_VERSIONING_MASK_MESSAGING (ECRYPTFS_VERSIONING_DEVMISC \
+					     | ECRYPTFS_VERSIONING_PUBKEY)
+#else
+# define ECRYPTFS_VERSIONING_MASK_MESSAGING 0
+#endif
+
+#define ECRYPTFS_VERSIONING_MASK (ECRYPTFS_VERSIONING_PASSPHRASE \
+				  | ECRYPTFS_VERSIONING_PLAINTEXT_PASSTHROUGH \
+				  | ECRYPTFS_VERSIONING_XATTR \
+				  | ECRYPTFS_VERSIONING_MULTKEY \
+				  | ECRYPTFS_VERSIONING_MASK_MESSAGING \
+				  | ECRYPTFS_VERSIONING_FILENAME_ENCRYPTION)
 struct ecryptfs_key_sig {
 	struct list_head crypt_stat_list;
 	char keysig[ECRYPTFS_SIG_SIZE_HEX + 1];
@@ -399,7 +412,9 @@ struct ecryptfs_daemon {
 	struct hlist_node euid_chain;
 };
 
+#ifdef CONFIG_ECRYPT_FS_MESSAGING
 extern struct mutex ecryptfs_daemon_hash_mux;
+#endif
 
 static inline size_t
 ecryptfs_lower_header_size(struct ecryptfs_crypt_stat *crypt_stat)
@@ -610,6 +625,7 @@ int
 ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 		  size_t size, int flags);
 int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode);
+#ifdef CONFIG_ECRYPT_FS_MESSAGING
 int ecryptfs_process_response(struct ecryptfs_daemon *daemon,
 			      struct ecryptfs_message *msg, u32 seq);
 int ecryptfs_send_message(char *data, int data_len,
@@ -618,6 +634,24 @@ int ecryptfs_wait_for_response(struct ecryptfs_msg_ctx *msg_ctx,
 			       struct ecryptfs_message **emsg);
 int ecryptfs_init_messaging(void);
 void ecryptfs_release_messaging(void);
+#else
+static inline int ecryptfs_init_messaging(void)
+{
+	return 0;
+}
+static inline void ecryptfs_release_messaging(void)
+{ }
+static inline int ecryptfs_send_message(char *data, int data_len,
+					struct ecryptfs_msg_ctx **msg_ctx)
+{
+	return -ENOTCONN;
+}
+static inline int ecryptfs_wait_for_response(struct ecryptfs_msg_ctx *msg_ctx,
+					     struct ecryptfs_message **emsg)
+{
+	return -ENOMSG;
+}
+#endif
 
 void
 ecryptfs_write_header_metadata(char *virt,
@@ -655,12 +689,11 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs,
 				     size_t offset_in_page, size_t size,
 				     struct inode *ecryptfs_inode);
 struct page *ecryptfs_get_locked_page(struct inode *inode, loff_t index);
-int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon);
-int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon);
 int ecryptfs_parse_packet_length(unsigned char *data, size_t *size,
 				 size_t *length_size);
 int ecryptfs_write_packet_length(char *dest, size_t size,
 				 size_t *packet_size_length);
+#ifdef CONFIG_ECRYPT_FS_MESSAGING
 int ecryptfs_init_ecryptfs_miscdev(void);
 void ecryptfs_destroy_ecryptfs_miscdev(void);
 int ecryptfs_send_miscdev(char *data, size_t data_size,
@@ -669,6 +702,9 @@ int ecryptfs_send_miscdev(char *data, size_t data_size,
 void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx);
 int
 ecryptfs_spawn_daemon(struct ecryptfs_daemon **daemon, struct file *file);
+int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon);
+int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon);
+#endif
 int ecryptfs_init_kthread(void);
 void ecryptfs_destroy_kthread(void);
 int ecryptfs_privileged_open(struct file **lower_file,
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 53acc9d..63b1f54 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -199,7 +199,6 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 	struct dentry *ecryptfs_dentry = file->f_path.dentry;
 	/* Private value of ecryptfs_dentry allocated in
 	 * ecryptfs_lookup() */
-	struct dentry *lower_dentry;
 	struct ecryptfs_file_info *file_info;
 
 	mount_crypt_stat = &ecryptfs_superblock_to_private(
@@ -222,7 +221,6 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 		rc = -ENOMEM;
 		goto out;
 	}
-	lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
 	crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat;
 	mutex_lock(&crypt_stat->cs_mutex);
 	if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED)) {
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index e0f07fb..5eab400 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -999,8 +999,8 @@ out:
 	return rc;
 }
 
-int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
-			  struct kstat *stat)
+static int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
+				 struct kstat *stat)
 {
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	int rc = 0;
@@ -1021,8 +1021,8 @@ int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
 	return rc;
 }
 
-int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		     struct kstat *stat)
+static int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			    struct kstat *stat)
 {
 	struct kstat lower_stat;
 	int rc;
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 2333203..7d52806 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1150,7 +1150,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	struct ecryptfs_message *msg = NULL;
 	char *auth_tok_sig;
 	char *payload;
-	size_t payload_len;
+	size_t payload_len = 0;
 	int rc;
 
 	rc = ecryptfs_get_auth_tok_sig(&auth_tok_sig, auth_tok);
@@ -1168,7 +1168,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	rc = ecryptfs_send_message(payload, payload_len, &msg_ctx);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error sending message to "
-				"ecryptfsd\n");
+				"ecryptfsd: %d\n", rc);
 		goto out;
 	}
 	rc = ecryptfs_wait_for_response(msg_ctx, &msg);
@@ -1202,8 +1202,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 				  crypt_stat->key_size);
 	}
 out:
-	if (msg)
-		kfree(msg);
+	kfree(msg);
 	return rc;
 }
 
@@ -1989,7 +1988,7 @@ pki_encrypt_session_key(struct key *auth_tok_key,
 	rc = ecryptfs_send_message(payload, payload_len, &msg_ctx);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error sending message to "
-				"ecryptfsd\n");
+				"ecryptfsd: %d\n", rc);
 		goto out;
 	}
 	rc = ecryptfs_wait_for_response(msg_ctx, &msg);
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 4e0886c..e924cf4 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -629,6 +629,7 @@ static struct file_system_type ecryptfs_fs_type = {
 	.kill_sb = ecryptfs_kill_block_super,
 	.fs_flags = 0
 };
+MODULE_ALIAS_FS("ecryptfs");
 
 /**
  * inode_info_init_once
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index 8d7a577..49ff8ea0 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -97,8 +97,7 @@ static void ecryptfs_msg_ctx_free_to_alloc(struct ecryptfs_msg_ctx *msg_ctx)
 void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx)
 {
 	list_move(&(msg_ctx->node), &ecryptfs_msg_ctx_free_list);
-	if (msg_ctx->msg)
-		kfree(msg_ctx->msg);
+	kfree(msg_ctx->msg);
 	msg_ctx->msg = NULL;
 	msg_ctx->state = ECRYPTFS_MSG_CTX_STATE_FREE;
 }
@@ -283,7 +282,7 @@ ecryptfs_send_message_locked(char *data, int data_len, u8 msg_type,
 	int rc;
 
 	rc = ecryptfs_find_daemon_by_euid(&daemon);
-	if (rc || !daemon) {
+	if (rc) {
 		rc = -ENOTCONN;
 		goto out;
 	}
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 412e6ed..e4141f2 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -80,13 +80,6 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file)
 	int rc;
 
 	mutex_lock(&ecryptfs_daemon_hash_mux);
-	rc = try_module_get(THIS_MODULE);
-	if (rc == 0) {
-		rc = -EIO;
-		printk(KERN_ERR "%s: Error attempting to increment module use "
-		       "count; rc = [%d]\n", __func__, rc);
-		goto out_unlock_daemon_list;
-	}
 	rc = ecryptfs_find_daemon_by_euid(&daemon);
 	if (!rc) {
 		rc = -EINVAL;
@@ -96,7 +89,7 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file)
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to spawn daemon; "
 		       "rc = [%d]\n", __func__, rc);
-		goto out_module_put_unlock_daemon_list;
+		goto out_unlock_daemon_list;
 	}
 	mutex_lock(&daemon->mux);
 	if (daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN) {
@@ -108,9 +101,6 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file)
 	atomic_inc(&ecryptfs_num_miscdev_opens);
 out_unlock_daemon:
 	mutex_unlock(&daemon->mux);
-out_module_put_unlock_daemon_list:
-	if (rc)
-		module_put(THIS_MODULE);
 out_unlock_daemon_list:
 	mutex_unlock(&ecryptfs_daemon_hash_mux);
 	return rc;
@@ -147,7 +137,6 @@ ecryptfs_miscdev_release(struct inode *inode, struct file *file)
 		       "bug.\n", __func__, rc);
 		BUG();
 	}
-	module_put(THIS_MODULE);
 	return rc;
 }
 
@@ -471,6 +460,7 @@ out_free:
 
 
 static const struct file_operations ecryptfs_miscdev_fops = {
+	.owner   = THIS_MODULE,
 	.open    = ecryptfs_miscdev_open,
 	.poll    = ecryptfs_miscdev_poll,
 	.read    = ecryptfs_miscdev_read,
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 2002431..c6f57a7 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -33,6 +33,7 @@ static struct file_system_type efs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("efs");
 
 static struct pt_types sgi_pt_types[] = {
 	{0x00,		"SGI vh"},
diff --git a/fs/exec.c b/fs/exec.c
index a96a488..87e731f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -613,7 +613,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		 * when the old and new regions overlap clear from new_end.
 		 */
 		free_pgd_range(&tlb, new_end, old_end, new_end,
-			vma->vm_next ? vma->vm_next->vm_start : 0);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	} else {
 		/*
 		 * otherwise, clean from old_start; this is done to not touch
@@ -622,7 +622,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		 * for the others its just a little faster.
 		 */
 		free_pgd_range(&tlb, old_start, old_end, new_end,
-			vma->vm_next ? vma->vm_next->vm_start : 0);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	}
 	tlb_finish_mmu(&tlb, new_end, old_end);
 
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 5e59280..9d97633 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -1010,6 +1010,7 @@ static struct file_system_type exofs_type = {
 	.mount          = exofs_mount,
 	.kill_sb        = generic_shutdown_super,
 };
+MODULE_ALIAS_FS("exofs");
 
 static int __init init_exofs(void)
 {
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 8f370e01..7cadd82 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -118,7 +118,6 @@ void ext2_free_inode (struct inode * inode)
 	 * as writing the quota to disk may need the lock as well.
 	 */
 	/* Quota is already initialized in iput() */
-	ext2_xattr_delete_inode(inode);
 	dquot_free_inode(inode);
 	dquot_drop(inode);
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index c3881e5..fe60cc1 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -34,6 +34,7 @@
 #include "ext2.h"
 #include "acl.h"
 #include "xip.h"
+#include "xattr.h"
 
 static int __ext2_write_inode(struct inode *inode, int do_sync);
 
@@ -88,6 +89,7 @@ void ext2_evict_inode(struct inode * inode)
 		inode->i_size = 0;
 		if (inode->i_blocks)
 			ext2_truncate_blocks(inode, 0);
+		ext2_xattr_delete_inode(inode);
 	}
 
 	invalidate_inode_buffers(inode);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 7f68c81..2885349 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1536,6 +1536,7 @@ static struct file_system_type ext2_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("ext2");
 
 static int __init init_ext2_fs(void)
 {
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 5546ca2..3dc48cc 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -353,7 +353,7 @@ static struct block_device *ext3_blkdev_get(dev_t dev, struct super_block *sb)
 	return bdev;
 
 fail:
-	ext3_msg(sb, "error: failed to open journal device %s: %ld",
+	ext3_msg(sb, KERN_ERR, "error: failed to open journal device %s: %ld",
 		__bdevname(dev, b), PTR_ERR(bdev));
 
 	return NULL;
@@ -887,7 +887,7 @@ static ext3_fsblk_t get_sb_block(void **data, struct super_block *sb)
 	/*todo: use simple_strtoll with >32bit ext3 */
 	sb_block = simple_strtoul(options, &options, 0);
 	if (*options && *options != ',') {
-		ext3_msg(sb, "error: invalid sb specification: %s",
+		ext3_msg(sb, KERN_ERR, "error: invalid sb specification: %s",
 		       (char *) *data);
 		return 1;
 	}
@@ -2067,7 +2067,6 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 		test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal":
 		test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered":
 		"writeback");
-	sb->s_flags |= MS_SNAP_STABLE;
 
 	return 0;
 
@@ -3068,6 +3067,7 @@ static struct file_system_type ext3_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("ext3");
 
 static int __init init_ext3_fs(void)
 {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4a01ba3..3b83cd6 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -335,9 +335,9 @@ struct ext4_group_desc
  */
 
 struct flex_groups {
-	atomic_t free_inodes;
-	atomic_t free_clusters;
-	atomic_t used_dirs;
+	atomic64_t	free_clusters;
+	atomic_t	free_inodes;
+	atomic_t	used_dirs;
 };
 
 #define EXT4_BG_INODE_UNINIT	0x0001 /* Inode table/bitmap not in use */
@@ -2617,7 +2617,7 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 extern int __init ext4_init_pageio(void);
 extern void ext4_add_complete_io(ext4_io_end_t *io_end);
 extern void ext4_exit_pageio(void);
-extern void ext4_ioend_wait(struct inode *);
+extern void ext4_ioend_shutdown(struct inode *);
 extern void ext4_free_io_end(ext4_io_end_t *io);
 extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
 extern void ext4_end_io_work(struct work_struct *work);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 28dd8ee..9c6d06d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1584,10 +1584,12 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 	unsigned short ext1_ee_len, ext2_ee_len, max_len;
 
 	/*
-	 * Make sure that either both extents are uninitialized, or
-	 * both are _not_.
+	 * Make sure that both extents are initialized. We don't merge
+	 * uninitialized extents so that we can be sure that end_io code has
+	 * the extent that was written properly split out and conversion to
+	 * initialized is trivial.
 	 */
-	if (ext4_ext_is_uninitialized(ex1) ^ ext4_ext_is_uninitialized(ex2))
+	if (ext4_ext_is_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2))
 		return 0;
 
 	if (ext4_ext_is_uninitialized(ex1))
@@ -2923,7 +2925,7 @@ static int ext4_split_extent_at(handle_t *handle,
 {
 	ext4_fsblk_t newblock;
 	ext4_lblk_t ee_block;
-	struct ext4_extent *ex, newex, orig_ex;
+	struct ext4_extent *ex, newex, orig_ex, zero_ex;
 	struct ext4_extent *ex2 = NULL;
 	unsigned int ee_len, depth;
 	int err = 0;
@@ -2943,6 +2945,10 @@ static int ext4_split_extent_at(handle_t *handle,
 	newblock = split - ee_block + ext4_ext_pblock(ex);
 
 	BUG_ON(split < ee_block || split >= (ee_block + ee_len));
+	BUG_ON(!ext4_ext_is_uninitialized(ex) &&
+	       split_flag & (EXT4_EXT_MAY_ZEROOUT |
+			     EXT4_EXT_MARK_UNINIT1 |
+			     EXT4_EXT_MARK_UNINIT2));
 
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
@@ -2990,12 +2996,29 @@ static int ext4_split_extent_at(handle_t *handle,
 	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
 	if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
 		if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
-			if (split_flag & EXT4_EXT_DATA_VALID1)
+			if (split_flag & EXT4_EXT_DATA_VALID1) {
 				err = ext4_ext_zeroout(inode, ex2);
-			else
+				zero_ex.ee_block = ex2->ee_block;
+				zero_ex.ee_len = cpu_to_le16(
+						ext4_ext_get_actual_len(ex2));
+				ext4_ext_store_pblock(&zero_ex,
+						      ext4_ext_pblock(ex2));
+			} else {
 				err = ext4_ext_zeroout(inode, ex);
-		} else
+				zero_ex.ee_block = ex->ee_block;
+				zero_ex.ee_len = cpu_to_le16(
+						ext4_ext_get_actual_len(ex));
+				ext4_ext_store_pblock(&zero_ex,
+						      ext4_ext_pblock(ex));
+			}
+		} else {
 			err = ext4_ext_zeroout(inode, &orig_ex);
+			zero_ex.ee_block = orig_ex.ee_block;
+			zero_ex.ee_len = cpu_to_le16(
+						ext4_ext_get_actual_len(&orig_ex));
+			ext4_ext_store_pblock(&zero_ex,
+					      ext4_ext_pblock(&orig_ex));
+		}
 
 		if (err)
 			goto fix_extent_len;
@@ -3003,6 +3026,12 @@ static int ext4_split_extent_at(handle_t *handle,
 		ex->ee_len = cpu_to_le16(ee_len);
 		ext4_ext_try_to_merge(handle, inode, path, ex);
 		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+		if (err)
+			goto fix_extent_len;
+
+		/* update extent status tree */
+		err = ext4_es_zeroout(inode, &zero_ex);
+
 		goto out;
 	} else if (err)
 		goto fix_extent_len;
@@ -3041,6 +3070,7 @@ static int ext4_split_extent(handle_t *handle,
 	int err = 0;
 	int uninitialized;
 	int split_flag1, flags1;
+	int allocated = map->m_len;
 
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
@@ -3060,20 +3090,29 @@ static int ext4_split_extent(handle_t *handle,
 				map->m_lblk + map->m_len, split_flag1, flags1);
 		if (err)
 			goto out;
+	} else {
+		allocated = ee_len - (map->m_lblk - ee_block);
 	}
-
+	/*
+	 * Update path is required because previous ext4_split_extent_at() may
+	 * result in split of original leaf or extent zeroout.
+	 */
 	ext4_ext_drop_refs(path);
 	path = ext4_ext_find_extent(inode, map->m_lblk, path);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	uninitialized = ext4_ext_is_uninitialized(ex);
+	split_flag1 = 0;
 
 	if (map->m_lblk >= ee_block) {
-		split_flag1 = split_flag & (EXT4_EXT_MAY_ZEROOUT |
-					    EXT4_EXT_DATA_VALID2);
-		if (uninitialized)
+		split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
+		if (uninitialized) {
 			split_flag1 |= EXT4_EXT_MARK_UNINIT1;
-		if (split_flag & EXT4_EXT_MARK_UNINIT2)
-			split_flag1 |= EXT4_EXT_MARK_UNINIT2;
+			split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
+						     EXT4_EXT_MARK_UNINIT2);
+		}
 		err = ext4_split_extent_at(handle, inode, path,
 				map->m_lblk, split_flag1, flags);
 		if (err)
@@ -3082,7 +3121,7 @@ static int ext4_split_extent(handle_t *handle,
 
 	ext4_ext_show_leaf(inode, path);
 out:
-	return err ? err : map->m_len;
+	return err ? err : allocated;
 }
 
 /*
@@ -3137,6 +3176,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
 	allocated = ee_len - (map->m_lblk - ee_block);
+	zero_ex.ee_len = 0;
 
 	trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
 
@@ -3227,13 +3267,16 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 
 	if (EXT4_EXT_MAY_ZEROOUT & split_flag)
 		max_zeroout = sbi->s_extent_max_zeroout_kb >>
-			inode->i_sb->s_blocksize_bits;
+			(inode->i_sb->s_blocksize_bits - 10);
 
 	/* If extent is less than s_max_zeroout_kb, zeroout directly */
 	if (max_zeroout && (ee_len <= max_zeroout)) {
 		err = ext4_ext_zeroout(inode, ex);
 		if (err)
 			goto out;
+		zero_ex.ee_block = ex->ee_block;
+		zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex));
+		ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex));
 
 		err = ext4_ext_get_access(handle, inode, path + depth);
 		if (err)
@@ -3292,6 +3335,9 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		err = allocated;
 
 out:
+	/* If we have gotten a failure, don't zero out status tree */
+	if (!err)
+		err = ext4_es_zeroout(inode, &zero_ex);
 	return err ? err : allocated;
 }
 
@@ -3374,8 +3420,19 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 		"block %llu, max_blocks %u\n", inode->i_ino,
 		  (unsigned long long)ee_block, ee_len);
 
-	/* If extent is larger than requested then split is required */
+	/* If extent is larger than requested it is a clear sign that we still
+	 * have some extent state machine issues left. So extent_split is still
+	 * required.
+	 * TODO: Once all related issues will be fixed this situation should be
+	 * illegal.
+	 */
 	if (ee_block != map->m_lblk || ee_len > map->m_len) {
+#ifdef EXT4_DEBUG
+		ext4_warning("Inode (%ld) finished: extent logical block %llu,"
+			     " len %u; IO logical block %llu, len %u\n",
+			     inode->i_ino, (unsigned long long)ee_block, ee_len,
+			     (unsigned long long)map->m_lblk, map->m_len);
+#endif
 		err = ext4_split_unwritten_extents(handle, inode, map, path,
 						   EXT4_GET_BLOCKS_CONVERT);
 		if (err < 0)
@@ -3626,6 +3683,10 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 						 path, map->m_len);
 		} else
 			err = ret;
+		map->m_flags |= EXT4_MAP_MAPPED;
+		if (allocated > map->m_len)
+			allocated = map->m_len;
+		map->m_len = allocated;
 		goto out2;
 	}
 	/* buffered IO case */
@@ -3675,6 +3736,7 @@ out:
 					allocated - map->m_len);
 		allocated = map->m_len;
 	}
+	map->m_len = allocated;
 
 	/*
 	 * If we have done fallocate with the offset that is already
@@ -4106,9 +4168,6 @@ got_allocated_blocks:
 			}
 		} else {
 			BUG_ON(allocated_clusters < reserved_clusters);
-			/* We will claim quota for all newly allocated blocks.*/
-			ext4_da_update_reserve_space(inode, allocated_clusters,
-							1);
 			if (reserved_clusters < allocated_clusters) {
 				struct ext4_inode_info *ei = EXT4_I(inode);
 				int reservation = allocated_clusters -
@@ -4159,6 +4218,15 @@ got_allocated_blocks:
 				ei->i_reserved_data_blocks += reservation;
 				spin_unlock(&ei->i_block_reservation_lock);
 			}
+			/*
+			 * We will claim quota for all newly allocated blocks.
+			 * We're updating the reserved space *after* the
+			 * correction above so we do not accidentally free
+			 * all the metadata reservation because we might
+			 * actually need it later on.
+			 */
+			ext4_da_update_reserve_space(inode, allocated_clusters,
+							1);
 		}
 	}
 
@@ -4368,8 +4436,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (len <= EXT_UNINIT_MAX_LEN << blkbits)
 		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 
-	/* Prevent race condition between unwritten */
-	ext4_flush_unwritten_io(inode);
 retry:
 	while (ret >= 0 && ret < max_blocks) {
 		map.m_lblk = map.m_lblk + ret;
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 95796a1..fe3337a 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -333,17 +333,27 @@ static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
 static int ext4_es_can_be_merged(struct extent_status *es1,
 				 struct extent_status *es2)
 {
-	if (es1->es_lblk + es1->es_len != es2->es_lblk)
+	if (ext4_es_status(es1) != ext4_es_status(es2))
 		return 0;
 
-	if (ext4_es_status(es1) != ext4_es_status(es2))
+	if (((__u64) es1->es_len) + es2->es_len > 0xFFFFFFFFULL)
 		return 0;
 
-	if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) &&
-	    (ext4_es_pblock(es1) + es1->es_len != ext4_es_pblock(es2)))
+	if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk)
 		return 0;
 
-	return 1;
+	if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) &&
+	    (ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2)))
+		return 1;
+
+	if (ext4_es_is_hole(es1))
+		return 1;
+
+	/* we need to check delayed extent is without unwritten status */
+	if (ext4_es_is_delayed(es1) && !ext4_es_is_unwritten(es1))
+		return 1;
+
+	return 0;
 }
 
 static struct extent_status *
@@ -389,6 +399,179 @@ ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es)
 	return es;
 }
 
+#ifdef ES_AGGRESSIVE_TEST
+static void ext4_es_insert_extent_ext_check(struct inode *inode,
+					    struct extent_status *es)
+{
+	struct ext4_ext_path *path = NULL;
+	struct ext4_extent *ex;
+	ext4_lblk_t ee_block;
+	ext4_fsblk_t ee_start;
+	unsigned short ee_len;
+	int depth, ee_status, es_status;
+
+	path = ext4_ext_find_extent(inode, es->es_lblk, NULL);
+	if (IS_ERR(path))
+		return;
+
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+
+	if (ex) {
+
+		ee_block = le32_to_cpu(ex->ee_block);
+		ee_start = ext4_ext_pblock(ex);
+		ee_len = ext4_ext_get_actual_len(ex);
+
+		ee_status = ext4_ext_is_uninitialized(ex) ? 1 : 0;
+		es_status = ext4_es_is_unwritten(es) ? 1 : 0;
+
+		/*
+		 * Make sure ex and es are not overlap when we try to insert
+		 * a delayed/hole extent.
+		 */
+		if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) {
+			if (in_range(es->es_lblk, ee_block, ee_len)) {
+				pr_warn("ES insert assertation failed for "
+					"inode: %lu we can find an extent "
+					"at block [%d/%d/%llu/%c], but we "
+					"want to add an delayed/hole extent "
+					"[%d/%d/%llu/%llx]\n",
+					inode->i_ino, ee_block, ee_len,
+					ee_start, ee_status ? 'u' : 'w',
+					es->es_lblk, es->es_len,
+					ext4_es_pblock(es), ext4_es_status(es));
+			}
+			goto out;
+		}
+
+		/*
+		 * We don't check ee_block == es->es_lblk, etc. because es
+		 * might be a part of whole extent, vice versa.
+		 */
+		if (es->es_lblk < ee_block ||
+		    ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) {
+			pr_warn("ES insert assertation failed for inode: %lu "
+				"ex_status [%d/%d/%llu/%c] != "
+				"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
+				ee_block, ee_len, ee_start,
+				ee_status ? 'u' : 'w', es->es_lblk, es->es_len,
+				ext4_es_pblock(es), es_status ? 'u' : 'w');
+			goto out;
+		}
+
+		if (ee_status ^ es_status) {
+			pr_warn("ES insert assertation failed for inode: %lu "
+				"ex_status [%d/%d/%llu/%c] != "
+				"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
+				ee_block, ee_len, ee_start,
+				ee_status ? 'u' : 'w', es->es_lblk, es->es_len,
+				ext4_es_pblock(es), es_status ? 'u' : 'w');
+		}
+	} else {
+		/*
+		 * We can't find an extent on disk.  So we need to make sure
+		 * that we don't want to add an written/unwritten extent.
+		 */
+		if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) {
+			pr_warn("ES insert assertation failed for inode: %lu "
+				"can't find an extent at block %d but we want "
+				"to add an written/unwritten extent "
+				"[%d/%d/%llu/%llx]\n", inode->i_ino,
+				es->es_lblk, es->es_lblk, es->es_len,
+				ext4_es_pblock(es), ext4_es_status(es));
+		}
+	}
+out:
+	if (path) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+}
+
+static void ext4_es_insert_extent_ind_check(struct inode *inode,
+					    struct extent_status *es)
+{
+	struct ext4_map_blocks map;
+	int retval;
+
+	/*
+	 * Here we call ext4_ind_map_blocks to lookup a block mapping because
+	 * 'Indirect' structure is defined in indirect.c.  So we couldn't
+	 * access direct/indirect tree from outside.  It is too dirty to define
+	 * this function in indirect.c file.
+	 */
+
+	map.m_lblk = es->es_lblk;
+	map.m_len = es->es_len;
+
+	retval = ext4_ind_map_blocks(NULL, inode, &map, 0);
+	if (retval > 0) {
+		if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) {
+			/*
+			 * We want to add a delayed/hole extent but this
+			 * block has been allocated.
+			 */
+			pr_warn("ES insert assertation failed for inode: %lu "
+				"We can find blocks but we want to add a "
+				"delayed/hole extent [%d/%d/%llu/%llx]\n",
+				inode->i_ino, es->es_lblk, es->es_len,
+				ext4_es_pblock(es), ext4_es_status(es));
+			return;
+		} else if (ext4_es_is_written(es)) {
+			if (retval != es->es_len) {
+				pr_warn("ES insert assertation failed for "
+					"inode: %lu retval %d != es_len %d\n",
+					inode->i_ino, retval, es->es_len);
+				return;
+			}
+			if (map.m_pblk != ext4_es_pblock(es)) {
+				pr_warn("ES insert assertation failed for "
+					"inode: %lu m_pblk %llu != "
+					"es_pblk %llu\n",
+					inode->i_ino, map.m_pblk,
+					ext4_es_pblock(es));
+				return;
+			}
+		} else {
+			/*
+			 * We don't need to check unwritten extent because
+			 * indirect-based file doesn't have it.
+			 */
+			BUG_ON(1);
+		}
+	} else if (retval == 0) {
+		if (ext4_es_is_written(es)) {
+			pr_warn("ES insert assertation failed for inode: %lu "
+				"We can't find the block but we want to add "
+				"an written extent [%d/%d/%llu/%llx]\n",
+				inode->i_ino, es->es_lblk, es->es_len,
+				ext4_es_pblock(es), ext4_es_status(es));
+			return;
+		}
+	}
+}
+
+static inline void ext4_es_insert_extent_check(struct inode *inode,
+					       struct extent_status *es)
+{
+	/*
+	 * We don't need to worry about the race condition because
+	 * caller takes i_data_sem locking.
+	 */
+	BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem));
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		ext4_es_insert_extent_ext_check(inode, es);
+	else
+		ext4_es_insert_extent_ind_check(inode, es);
+}
+#else
+static inline void ext4_es_insert_extent_check(struct inode *inode,
+					       struct extent_status *es)
+{
+}
+#endif
+
 static int __es_insert_extent(struct inode *inode, struct extent_status *newes)
 {
 	struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
@@ -471,6 +654,8 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 	ext4_es_store_status(&newes, status);
 	trace_ext4_es_insert_extent(inode, &newes);
 
+	ext4_es_insert_extent_check(inode, &newes);
+
 	write_lock(&EXT4_I(inode)->i_es_lock);
 	err = __es_remove_extent(inode, lblk, end);
 	if (err != 0)
@@ -669,6 +854,23 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 	return err;
 }
 
+int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex)
+{
+	ext4_lblk_t  ee_block;
+	ext4_fsblk_t ee_pblock;
+	unsigned int ee_len;
+
+	ee_block  = le32_to_cpu(ex->ee_block);
+	ee_len    = ext4_ext_get_actual_len(ex);
+	ee_pblock = ext4_ext_pblock(ex);
+
+	if (ee_len == 0)
+		return 0;
+
+	return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
+				     EXTENT_STATUS_WRITTEN);
+}
+
 static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
 {
 	struct ext4_sb_info *sbi = container_of(shrink,
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index f190dfe..d8e2d4d 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -21,6 +21,12 @@
 #endif
 
 /*
+ * With ES_AGGRESSIVE_TEST defined, the result of es caching will be
+ * checked with old map_block's result.
+ */
+#define ES_AGGRESSIVE_TEST__
+
+/*
  * These flags live in the high bits of extent_status.es_pblk
  */
 #define EXTENT_STATUS_WRITTEN	(1ULL << 63)
@@ -33,6 +39,8 @@
 				 EXTENT_STATUS_DELAYED | \
 				 EXTENT_STATUS_HOLE)
 
+struct ext4_extent;
+
 struct extent_status {
 	struct rb_node rb_node;
 	ext4_lblk_t es_lblk;	/* first logical block extent covers */
@@ -58,6 +66,7 @@ extern void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
 					struct extent_status *es);
 extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 				 struct extent_status *es);
+extern int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex);
 
 static inline int ext4_es_is_written(struct extent_status *es)
 {
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 32fd2b9..6c5bb8d 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -324,8 +324,8 @@ error_return:
 }
 
 struct orlov_stats {
+	__u64 free_clusters;
 	__u32 free_inodes;
-	__u32 free_clusters;
 	__u32 used_dirs;
 };
 
@@ -342,7 +342,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
 
 	if (flex_size > 1) {
 		stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
-		stats->free_clusters = atomic_read(&flex_group[g].free_clusters);
+		stats->free_clusters = atomic64_read(&flex_group[g].free_clusters);
 		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
 		return;
 	}
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index b505a14..a041831 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -1539,9 +1539,9 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode,
 		blk = *i_data;
 		if (level > 0) {
 			ext4_lblk_t first2;
-			bh = sb_bread(inode->i_sb, blk);
+			bh = sb_bread(inode->i_sb, le32_to_cpu(blk));
 			if (!bh) {
-				EXT4_ERROR_INODE_BLOCK(inode, blk,
+				EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk),
 						       "Read failure");
 				return -EIO;
 			}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9ea0cde..b3a5213 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -185,8 +185,6 @@ void ext4_evict_inode(struct inode *inode)
 
 	trace_ext4_evict_inode(inode);
 
-	ext4_ioend_wait(inode);
-
 	if (inode->i_nlink) {
 		/*
 		 * When journalling data dirty buffers are tracked only in the
@@ -207,7 +205,8 @@ void ext4_evict_inode(struct inode *inode)
 		 * don't use page cache.
 		 */
 		if (ext4_should_journal_data(inode) &&
-		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
+		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
+		    inode->i_ino != EXT4_JOURNAL_INO) {
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
@@ -216,6 +215,7 @@ void ext4_evict_inode(struct inode *inode)
 			filemap_write_and_wait(&inode->i_data);
 		}
 		truncate_inode_pages(&inode->i_data, 0);
+		ext4_ioend_shutdown(inode);
 		goto no_delete;
 	}
 
@@ -225,6 +225,7 @@ void ext4_evict_inode(struct inode *inode)
 	if (ext4_should_order_data(inode))
 		ext4_begin_ordered_truncate(inode, 0);
 	truncate_inode_pages(&inode->i_data, 0);
+	ext4_ioend_shutdown(inode);
 
 	if (is_bad_inode(inode))
 		goto no_delete;
@@ -482,6 +483,58 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
 	return num;
 }
 
+#ifdef ES_AGGRESSIVE_TEST
+static void ext4_map_blocks_es_recheck(handle_t *handle,
+				       struct inode *inode,
+				       struct ext4_map_blocks *es_map,
+				       struct ext4_map_blocks *map,
+				       int flags)
+{
+	int retval;
+
+	map->m_flags = 0;
+	/*
+	 * There is a race window that the result is not the same.
+	 * e.g. xfstests #223 when dioread_nolock enables.  The reason
+	 * is that we lookup a block mapping in extent status tree with
+	 * out taking i_data_sem.  So at the time the unwritten extent
+	 * could be converted.
+	 */
+	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
+		down_read((&EXT4_I(inode)->i_data_sem));
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		retval = ext4_ext_map_blocks(handle, inode, map, flags &
+					     EXT4_GET_BLOCKS_KEEP_SIZE);
+	} else {
+		retval = ext4_ind_map_blocks(handle, inode, map, flags &
+					     EXT4_GET_BLOCKS_KEEP_SIZE);
+	}
+	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
+		up_read((&EXT4_I(inode)->i_data_sem));
+	/*
+	 * Clear EXT4_MAP_FROM_CLUSTER and EXT4_MAP_BOUNDARY flag
+	 * because it shouldn't be marked in es_map->m_flags.
+	 */
+	map->m_flags &= ~(EXT4_MAP_FROM_CLUSTER | EXT4_MAP_BOUNDARY);
+
+	/*
+	 * We don't check m_len because extent will be collpased in status
+	 * tree.  So the m_len might not equal.
+	 */
+	if (es_map->m_lblk != map->m_lblk ||
+	    es_map->m_flags != map->m_flags ||
+	    es_map->m_pblk != map->m_pblk) {
+		printk("ES cache assertation failed for inode: %lu "
+		       "es_cached ex [%d/%d/%llu/%x] != "
+		       "found ex [%d/%d/%llu/%x] retval %d flags %x\n",
+		       inode->i_ino, es_map->m_lblk, es_map->m_len,
+		       es_map->m_pblk, es_map->m_flags, map->m_lblk,
+		       map->m_len, map->m_pblk, map->m_flags,
+		       retval, flags);
+	}
+}
+#endif /* ES_AGGRESSIVE_TEST */
+
 /*
  * The ext4_map_blocks() function tries to look up the requested blocks,
  * and returns if the blocks are already mapped.
@@ -509,6 +562,11 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 {
 	struct extent_status es;
 	int retval;
+#ifdef ES_AGGRESSIVE_TEST
+	struct ext4_map_blocks orig_map;
+
+	memcpy(&orig_map, map, sizeof(*map));
+#endif
 
 	map->m_flags = 0;
 	ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
@@ -531,6 +589,10 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		} else {
 			BUG_ON(1);
 		}
+#ifdef ES_AGGRESSIVE_TEST
+		ext4_map_blocks_es_recheck(handle, inode, map,
+					   &orig_map, flags);
+#endif
 		goto found;
 	}
 
@@ -551,6 +613,15 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		int ret;
 		unsigned long long status;
 
+#ifdef ES_AGGRESSIVE_TEST
+		if (retval != map->m_len) {
+			printk("ES len assertation failed for inode: %lu "
+			       "retval %d != map->m_len %d "
+			       "in %s (lookup)\n", inode->i_ino, retval,
+			       map->m_len, __func__);
+		}
+#endif
+
 		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
@@ -643,6 +714,24 @@ found:
 		int ret;
 		unsigned long long status;
 
+#ifdef ES_AGGRESSIVE_TEST
+		if (retval != map->m_len) {
+			printk("ES len assertation failed for inode: %lu "
+			       "retval %d != map->m_len %d "
+			       "in %s (allocation)\n", inode->i_ino, retval,
+			       map->m_len, __func__);
+		}
+#endif
+
+		/*
+		 * If the extent has been zeroed out, we don't need to update
+		 * extent status tree.
+		 */
+		if ((flags & EXT4_GET_BLOCKS_PRE_IO) &&
+		    ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
+			if (ext4_es_is_written(&es))
+				goto has_zeroout;
+		}
 		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
@@ -655,6 +744,7 @@ found:
 			retval = ret;
 	}
 
+has_zeroout:
 	up_write((&EXT4_I(inode)->i_data_sem));
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
 		int ret = check_block_validity(inode, map);
@@ -1216,6 +1306,55 @@ static int ext4_journalled_write_end(struct file *file,
 }
 
 /*
+ * Reserve a metadata for a single block located at lblock
+ */
+static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
+{
+	int retries = 0;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned int md_needed;
+	ext4_lblk_t save_last_lblock;
+	int save_len;
+
+	/*
+	 * recalculate the amount of metadata blocks to reserve
+	 * in order to allocate nrblocks
+	 * worse case is one extent per block
+	 */
+repeat:
+	spin_lock(&ei->i_block_reservation_lock);
+	/*
+	 * ext4_calc_metadata_amount() has side effects, which we have
+	 * to be prepared undo if we fail to claim space.
+	 */
+	save_len = ei->i_da_metadata_calc_len;
+	save_last_lblock = ei->i_da_metadata_calc_last_lblock;
+	md_needed = EXT4_NUM_B2C(sbi,
+				 ext4_calc_metadata_amount(inode, lblock));
+	trace_ext4_da_reserve_space(inode, md_needed);
+
+	/*
+	 * We do still charge estimated metadata to the sb though;
+	 * we cannot afford to run out of free blocks.
+	 */
+	if (ext4_claim_free_clusters(sbi, md_needed, 0)) {
+		ei->i_da_metadata_calc_len = save_len;
+		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
+		spin_unlock(&ei->i_block_reservation_lock);
+		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+			cond_resched();
+			goto repeat;
+		}
+		return -ENOSPC;
+	}
+	ei->i_reserved_meta_blocks += md_needed;
+	spin_unlock(&ei->i_block_reservation_lock);
+
+	return 0;       /* success */
+}
+
+/*
  * Reserve a single cluster located at lblock
  */
 static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
@@ -1263,7 +1402,7 @@ repeat:
 		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
 		spin_unlock(&ei->i_block_reservation_lock);
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
-			yield();
+			cond_resched();
 			goto repeat;
 		}
 		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
@@ -1768,6 +1907,11 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 	struct extent_status es;
 	int retval;
 	sector_t invalid_block = ~((sector_t) 0xffff);
+#ifdef ES_AGGRESSIVE_TEST
+	struct ext4_map_blocks orig_map;
+
+	memcpy(&orig_map, map, sizeof(*map));
+#endif
 
 	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
 		invalid_block = ~0;
@@ -1809,6 +1953,9 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		else
 			BUG_ON(1);
 
+#ifdef ES_AGGRESSIVE_TEST
+		ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
+#endif
 		return retval;
 	}
 
@@ -1843,8 +1990,11 @@ add_delayed:
 		 * XXX: __block_prepare_write() unmaps passed block,
 		 * is it OK?
 		 */
-		/* If the block was allocated from previously allocated cluster,
-		 * then we dont need to reserve it again. */
+		/*
+		 * If the block was allocated from previously allocated cluster,
+		 * then we don't need to reserve it again. However we still need
+		 * to reserve metadata for every block we're going to write.
+		 */
 		if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
 			ret = ext4_da_reserve_space(inode, iblock);
 			if (ret) {
@@ -1852,6 +2002,13 @@ add_delayed:
 				retval = ret;
 				goto out_unlock;
 			}
+		} else {
+			ret = ext4_da_reserve_metadata(inode, iblock);
+			if (ret) {
+				/* not enough space to reserve */
+				retval = ret;
+				goto out_unlock;
+			}
 		}
 
 		ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
@@ -1873,6 +2030,15 @@ add_delayed:
 		int ret;
 		unsigned long long status;
 
+#ifdef ES_AGGRESSIVE_TEST
+		if (retval != map->m_len) {
+			printk("ES len assertation failed for inode: %lu "
+			       "retval %d != map->m_len %d "
+			       "in %s (lookup)\n", inode->i_ino, retval,
+			       map->m_len, __func__);
+		}
+#endif
+
 		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
@@ -2908,8 +3074,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 
 	trace_ext4_releasepage(page);
 
-	WARN_ON(PageChecked(page));
-	if (!page_has_buffers(page))
+	/* Page has dirty journalled data -> cannot release */
+	if (PageChecked(page))
 		return 0;
 	if (journal)
 		return jbd2_journal_try_to_free_buffers(journal, page, wait);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 7bb713a..ee6614bd 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2804,8 +2804,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi,
 							  ac->ac_b_ex.fe_group);
-		atomic_sub(ac->ac_b_ex.fe_len,
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_sub(ac->ac_b_ex.fe_len,
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
 	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -3692,11 +3692,7 @@ repeat:
 	if (free < needed && busy) {
 		busy = 0;
 		ext4_unlock_group(sb, group);
-		/*
-		 * Yield the CPU here so that we don't get soft lockup
-		 * in non preempt case.
-		 */
-		yield();
+		cond_resched();
 		goto repeat;
 	}
 
@@ -4246,7 +4242,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 			ext4_claim_free_clusters(sbi, ar->len, ar->flags)) {
 
 			/* let others to free the space */
-			yield();
+			cond_resched();
 			ar->len = ar->len >> 1;
 		}
 		if (!ar->len) {
@@ -4464,7 +4460,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	struct buffer_head *bitmap_bh = NULL;
 	struct super_block *sb = inode->i_sb;
 	struct ext4_group_desc *gdp;
-	unsigned long freed = 0;
 	unsigned int overflow;
 	ext4_grpblk_t bit;
 	struct buffer_head *gd_bh;
@@ -4666,14 +4661,12 @@ do_more:
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(count_clusters,
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_add(count_clusters,
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
 	ext4_mb_unload_buddy(&e4b);
 
-	freed += count;
-
 	if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
 		dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
 
@@ -4811,8 +4804,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(EXT4_NUM_B2C(sbi, blocks_freed),
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_add(EXT4_NUM_B2C(sbi, blocks_freed),
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
 	ext4_mb_unload_buddy(&e4b);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 4e81d47..33e1c08 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -32,16 +32,18 @@
  */
 static inline int
 get_ext_path(struct inode *inode, ext4_lblk_t lblock,
-		struct ext4_ext_path **path)
+		struct ext4_ext_path **orig_path)
 {
 	int ret = 0;
+	struct ext4_ext_path *path;
 
-	*path = ext4_ext_find_extent(inode, lblock, *path);
-	if (IS_ERR(*path)) {
-		ret = PTR_ERR(*path);
-		*path = NULL;
-	} else if ((*path)[ext_depth(inode)].p_ext == NULL)
+	path = ext4_ext_find_extent(inode, lblock, *orig_path);
+	if (IS_ERR(path))
+		ret = PTR_ERR(path);
+	else if (path[ext_depth(inode)].p_ext == NULL)
 		ret = -ENODATA;
+	else
+		*orig_path = path;
 
 	return ret;
 }
@@ -611,24 +613,25 @@ mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
 {
 	struct ext4_ext_path *path = NULL;
 	struct ext4_extent *ext;
+	int ret = 0;
 	ext4_lblk_t last = from + count;
 	while (from < last) {
 		*err = get_ext_path(inode, from, &path);
 		if (*err)
-			return 0;
+			goto out;
 		ext = path[ext_depth(inode)].p_ext;
-		if (!ext) {
-			ext4_ext_drop_refs(path);
-			return 0;
-		}
-		if (uninit != ext4_ext_is_uninitialized(ext)) {
-			ext4_ext_drop_refs(path);
-			return 0;
-		}
+		if (uninit != ext4_ext_is_uninitialized(ext))
+			goto out;
 		from += ext4_ext_get_actual_len(ext);
 		ext4_ext_drop_refs(path);
 	}
-	return 1;
+	ret = 1;
+out:
+	if (path) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+	return ret;
 }
 
 /**
@@ -666,6 +669,14 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
 	int replaced_count = 0;
 	int dext_alen;
 
+	*err = ext4_es_remove_extent(orig_inode, from, count);
+	if (*err)
+		goto out;
+
+	*err = ext4_es_remove_extent(donor_inode, from, count);
+	if (*err)
+		goto out;
+
 	/* Get the original extent for the block "orig_off" */
 	*err = get_ext_path(orig_inode, orig_off, &orig_path);
 	if (*err)
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 809b310..047a6de 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -50,11 +50,21 @@ void ext4_exit_pageio(void)
 	kmem_cache_destroy(io_page_cachep);
 }
 
-void ext4_ioend_wait(struct inode *inode)
+/*
+ * This function is called by ext4_evict_inode() to make sure there is
+ * no more pending I/O completion work left to do.
+ */
+void ext4_ioend_shutdown(struct inode *inode)
 {
 	wait_queue_head_t *wq = ext4_ioend_wq(inode);
 
 	wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
+	/*
+	 * We need to make sure the work structure is finished being
+	 * used before we let the inode get destroyed.
+	 */
+	if (work_pending(&EXT4_I(inode)->i_unwritten_work))
+		cancel_work_sync(&EXT4_I(inode)->i_unwritten_work);
 }
 
 static void put_io_page(struct ext4_io_page *io_page)
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index b2c8ee5..c169477 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1360,8 +1360,8 @@ static void ext4_update_super(struct super_block *sb,
 	    sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group;
 		flex_group = ext4_flex_group(sbi, group_data[0].group);
-		atomic_add(EXT4_NUM_B2C(sbi, free_blocks),
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_add(EXT4_NUM_B2C(sbi, free_blocks),
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 		atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
 			   &sbi->s_flex_groups[flex_group].free_inodes);
 	}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 5e6c878..5d6d5357 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -90,6 +90,8 @@ static struct file_system_type ext2_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("ext2");
+MODULE_ALIAS("ext2");
 #define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
 #else
 #define IS_EXT2_SB(sb) (0)
@@ -104,6 +106,8 @@ static struct file_system_type ext3_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("ext3");
+MODULE_ALIAS("ext3");
 #define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
 #else
 #define IS_EXT3_SB(sb) (0)
@@ -1923,8 +1927,8 @@ static int ext4_fill_flex_info(struct super_block *sb)
 		flex_group = ext4_flex_group(sbi, i);
 		atomic_add(ext4_free_inodes_count(sb, gdp),
 			   &sbi->s_flex_groups[flex_group].free_inodes);
-		atomic_add(ext4_free_group_clusters(sb, gdp),
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_add(ext4_free_group_clusters(sb, gdp),
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 		atomic_add(ext4_used_dirs_count(sb, gdp),
 			   &sbi->s_flex_groups[flex_group].used_dirs);
 	}
@@ -5152,7 +5156,6 @@ static inline int ext2_feature_set_ok(struct super_block *sb)
 		return 0;
 	return 1;
 }
-MODULE_ALIAS("ext2");
 #else
 static inline void register_as_ext2(void) { }
 static inline void unregister_as_ext2(void) { }
@@ -5185,7 +5188,6 @@ static inline int ext3_feature_set_ok(struct super_block *sb)
 		return 0;
 	return 1;
 }
-MODULE_ALIAS("ext3");
 #else
 static inline void register_as_ext3(void) { }
 static inline void unregister_as_ext3(void) { }
@@ -5199,6 +5201,7 @@ static struct file_system_type ext4_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("ext4");
 
 static int __init ext4_init_feat_adverts(void)
 {
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 8c11764..fea6e58 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -687,6 +687,7 @@ static struct file_system_type f2fs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("f2fs");
 
 static int __init init_inodecache(void)
 {
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 165012e..7a6f02c 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -964,6 +964,29 @@ int fat_scan(struct inode *dir, const unsigned char *name,
 }
 EXPORT_SYMBOL_GPL(fat_scan);
 
+/*
+ * Scans a directory for a given logstart.
+ * Returns an error code or zero.
+ */
+int fat_scan_logstart(struct inode *dir, int i_logstart,
+		      struct fat_slot_info *sinfo)
+{
+	struct super_block *sb = dir->i_sb;
+
+	sinfo->slot_off = 0;
+	sinfo->bh = NULL;
+	while (fat_get_short_entry(dir, &sinfo->slot_off, &sinfo->bh,
+				   &sinfo->de) >= 0) {
+		if (fat_get_start(MSDOS_SB(sb), sinfo->de) == i_logstart) {
+			sinfo->slot_off -= sizeof(*sinfo->de);
+			sinfo->nr_slots = 1;
+			sinfo->i_pos = fat_make_i_pos(sb, sinfo->bh, sinfo->de);
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
 static int __fat_remove_entries(struct inode *dir, loff_t pos, int nr_slots)
 {
 	struct super_block *sb = dir->i_sb;
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index e9cc3f0..21664fc 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -23,6 +23,9 @@
 #define FAT_ERRORS_PANIC	2      /* panic on error */
 #define FAT_ERRORS_RO		3      /* remount r/o on error */
 
+#define FAT_NFS_STALE_RW	1      /* NFS RW support, can cause ESTALE */
+#define FAT_NFS_NOSTALE_RO	2      /* NFS RO support, no ESTALE issue */
+
 struct fat_mount_options {
 	kuid_t fs_uid;
 	kgid_t fs_gid;
@@ -34,6 +37,7 @@ struct fat_mount_options {
 	unsigned short shortname;  /* flags for shortname display/create rule */
 	unsigned char name_check;  /* r = relaxed, n = normal, s = strict */
 	unsigned char errors;	   /* On error: continue, panic, remount-ro */
+	unsigned char nfs;	  /* NFS support: nostale_ro, stale_rw */
 	unsigned short allow_utime;/* permission for setting the [am]time */
 	unsigned quiet:1,          /* set = fake successful chmods and chowns */
 		 showexec:1,       /* set = only set x bit for com/exe/bat */
@@ -48,8 +52,7 @@ struct fat_mount_options {
 		 usefree:1,	   /* Use free_clusters for FAT32 */
 		 tz_set:1,	   /* Filesystem timestamps' offset set */
 		 rodir:1,	   /* allow ATTR_RO for directory */
-		 discard:1,	   /* Issue discard requests on deletions */
-		 nfs:1;		   /* Do extra work needed for NFS export */
+		 discard:1;	   /* Issue discard requests on deletions */
 };
 
 #define FAT_HASH_BITS	8
@@ -72,6 +75,7 @@ struct msdos_sb_info {
 	unsigned long root_cluster;   /* first cluster of the root directory */
 	unsigned long fsinfo_sector;  /* sector number of FAT32 fsinfo */
 	struct mutex fat_lock;
+	struct mutex nfs_build_inode_lock;
 	struct mutex s_lock;
 	unsigned int prev_free;      /* previously allocated cluster number */
 	unsigned int free_clusters;  /* -1 if undefined */
@@ -215,6 +219,27 @@ static inline sector_t fat_clus_to_blknr(struct msdos_sb_info *sbi, int clus)
 		+ sbi->data_start;
 }
 
+static inline void fat_get_blknr_offset(struct msdos_sb_info *sbi,
+				loff_t i_pos, sector_t *blknr, int *offset)
+{
+	*blknr = i_pos >> sbi->dir_per_block_bits;
+	*offset = i_pos & (sbi->dir_per_block - 1);
+}
+
+static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi,
+					struct inode *inode)
+{
+	loff_t i_pos;
+#if BITS_PER_LONG == 32
+	spin_lock(&sbi->inode_hash_lock);
+#endif
+	i_pos = MSDOS_I(inode)->i_pos;
+#if BITS_PER_LONG == 32
+	spin_unlock(&sbi->inode_hash_lock);
+#endif
+	return i_pos;
+}
+
 static inline void fat16_towchar(wchar_t *dst, const __u8 *src, size_t len)
 {
 #ifdef __BIG_ENDIAN
@@ -271,6 +296,8 @@ extern int fat_dir_empty(struct inode *dir);
 extern int fat_subdirs(struct inode *dir);
 extern int fat_scan(struct inode *dir, const unsigned char *name,
 		    struct fat_slot_info *sinfo);
+extern int fat_scan_logstart(struct inode *dir, int i_logstart,
+			     struct fat_slot_info *sinfo);
 extern int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh,
 				struct msdos_dir_entry **de);
 extern int fat_alloc_new_dir(struct inode *dir, struct timespec *ts);
@@ -348,6 +375,7 @@ extern struct inode *fat_build_inode(struct super_block *sb,
 extern int fat_sync_inode(struct inode *inode);
 extern int fat_fill_super(struct super_block *sb, void *data, int silent,
 			  int isvfat, void (*setup)(struct super_block *));
+extern int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de);
 
 extern int fat_flush_inodes(struct super_block *sb, struct inode *i1,
 			    struct inode *i2);
@@ -382,12 +410,8 @@ int fat_cache_init(void);
 void fat_cache_destroy(void);
 
 /* fat/nfs.c */
-struct fid;
-extern struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid,
-				       int fh_len, int fh_type);
-extern struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid,
-				       int fh_len, int fh_type);
-extern struct dentry *fat_get_parent(struct dentry *child_dir);
+extern const struct export_operations fat_export_ops;
+extern const struct export_operations fat_export_ops_nostale;
 
 /* helper for printk */
 typedef unsigned long long	llu;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 3978f8c..b0b632e 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -306,6 +306,11 @@ int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	struct inode *inode = dentry->d_inode;
 	generic_fillattr(inode, stat);
 	stat->blksize = MSDOS_SB(inode->i_sb)->cluster_size;
+
+	if (MSDOS_SB(inode->i_sb)->options.nfs == FAT_NFS_NOSTALE_RO) {
+		/* Use i_pos for ino. This is used as fileid of nfs. */
+		stat->ino = fat_i_pos_read(MSDOS_SB(inode->i_sb), inode);
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fat_getattr);
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index acf6e47..4ff9016 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -18,7 +18,6 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/buffer_head.h>
-#include <linux/exportfs.h>
 #include <linux/mount.h>
 #include <linux/vfs.h>
 #include <linux/parser.h>
@@ -385,7 +384,7 @@ static int fat_calc_dir_size(struct inode *inode)
 }
 
 /* doesn't deal with root inode */
-static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
+int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
 	int error;
@@ -444,12 +443,25 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 	return 0;
 }
 
+static inline void fat_lock_build_inode(struct msdos_sb_info *sbi)
+{
+	if (sbi->options.nfs == FAT_NFS_NOSTALE_RO)
+		mutex_lock(&sbi->nfs_build_inode_lock);
+}
+
+static inline void fat_unlock_build_inode(struct msdos_sb_info *sbi)
+{
+	if (sbi->options.nfs == FAT_NFS_NOSTALE_RO)
+		mutex_unlock(&sbi->nfs_build_inode_lock);
+}
+
 struct inode *fat_build_inode(struct super_block *sb,
 			struct msdos_dir_entry *de, loff_t i_pos)
 {
 	struct inode *inode;
 	int err;
 
+	fat_lock_build_inode(MSDOS_SB(sb));
 	inode = fat_iget(sb, i_pos);
 	if (inode)
 		goto out;
@@ -469,6 +481,7 @@ struct inode *fat_build_inode(struct super_block *sb,
 	fat_attach(inode, i_pos);
 	insert_inode_hash(inode);
 out:
+	fat_unlock_build_inode(MSDOS_SB(sb));
 	return inode;
 }
 
@@ -655,20 +668,6 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0;
 }
 
-static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi,
-				    struct inode *inode)
-{
-	loff_t i_pos;
-#if BITS_PER_LONG == 32
-	spin_lock(&sbi->inode_hash_lock);
-#endif
-	i_pos = MSDOS_I(inode)->i_pos;
-#if BITS_PER_LONG == 32
-	spin_unlock(&sbi->inode_hash_lock);
-#endif
-	return i_pos;
-}
-
 static int __fat_write_inode(struct inode *inode, int wait)
 {
 	struct super_block *sb = inode->i_sb;
@@ -676,7 +675,8 @@ static int __fat_write_inode(struct inode *inode, int wait)
 	struct buffer_head *bh;
 	struct msdos_dir_entry *raw_entry;
 	loff_t i_pos;
-	int err;
+	sector_t blocknr;
+	int err, offset;
 
 	if (inode->i_ino == MSDOS_ROOT_INO)
 		return 0;
@@ -686,7 +686,8 @@ retry:
 	if (!i_pos)
 		return 0;
 
-	bh = sb_bread(sb, i_pos >> sbi->dir_per_block_bits);
+	fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset);
+	bh = sb_bread(sb, blocknr);
 	if (!bh) {
 		fat_msg(sb, KERN_ERR, "unable to read inode block "
 		       "for updating (i_pos %lld)", i_pos);
@@ -699,8 +700,7 @@ retry:
 		goto retry;
 	}
 
-	raw_entry = &((struct msdos_dir_entry *) (bh->b_data))
-	    [i_pos & (sbi->dir_per_block - 1)];
+	raw_entry = &((struct msdos_dir_entry *) (bh->b_data))[offset];
 	if (S_ISDIR(inode->i_mode))
 		raw_entry->size = 0;
 	else
@@ -761,12 +761,6 @@ static const struct super_operations fat_sops = {
 	.show_options	= fat_show_options,
 };
 
-static const struct export_operations fat_export_ops = {
-	.fh_to_dentry	= fat_fh_to_dentry,
-	.fh_to_parent	= fat_fh_to_parent,
-	.get_parent	= fat_get_parent,
-};
-
 static int fat_show_options(struct seq_file *m, struct dentry *root)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(root->d_sb);
@@ -814,8 +808,6 @@ static int fat_show_options(struct seq_file *m, struct dentry *root)
 		seq_puts(m, ",usefree");
 	if (opts->quiet)
 		seq_puts(m, ",quiet");
-	if (opts->nfs)
-		seq_puts(m, ",nfs");
 	if (opts->showexec)
 		seq_puts(m, ",showexec");
 	if (opts->sys_immutable)
@@ -849,6 +841,10 @@ static int fat_show_options(struct seq_file *m, struct dentry *root)
 		seq_puts(m, ",errors=panic");
 	else
 		seq_puts(m, ",errors=remount-ro");
+	if (opts->nfs == FAT_NFS_NOSTALE_RO)
+		seq_puts(m, ",nfs=nostale_ro");
+	else if (opts->nfs)
+		seq_puts(m, ",nfs=stale_rw");
 	if (opts->discard)
 		seq_puts(m, ",discard");
 
@@ -865,7 +861,7 @@ enum {
 	Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
 	Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont,
 	Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_time_offset,
-	Opt_err,
+	Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err,
 };
 
 static const match_table_t fat_tokens = {
@@ -895,7 +891,9 @@ static const match_table_t fat_tokens = {
 	{Opt_err_panic, "errors=panic"},
 	{Opt_err_ro, "errors=remount-ro"},
 	{Opt_discard, "discard"},
-	{Opt_nfs, "nfs"},
+	{Opt_nfs_stale_rw, "nfs"},
+	{Opt_nfs_stale_rw, "nfs=stale_rw"},
+	{Opt_nfs_nostale_ro, "nfs=nostale_ro"},
 	{Opt_obsolete, "conv=binary"},
 	{Opt_obsolete, "conv=text"},
 	{Opt_obsolete, "conv=auto"},
@@ -1092,6 +1090,12 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 		case Opt_err_ro:
 			opts->errors = FAT_ERRORS_RO;
 			break;
+		case Opt_nfs_stale_rw:
+			opts->nfs = FAT_NFS_STALE_RW;
+			break;
+		case Opt_nfs_nostale_ro:
+			opts->nfs = FAT_NFS_NOSTALE_RO;
+			break;
 
 		/* msdos specific */
 		case Opt_dots:
@@ -1150,9 +1154,6 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 		case Opt_discard:
 			opts->discard = 1;
 			break;
-		case Opt_nfs:
-			opts->nfs = 1;
-			break;
 
 		/* obsolete mount options */
 		case Opt_obsolete:
@@ -1183,6 +1184,10 @@ out:
 		opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH);
 	if (opts->unicode_xlate)
 		opts->utf8 = 0;
+	if (opts->nfs == FAT_NFS_NOSTALE_RO) {
+		sb->s_flags |= MS_RDONLY;
+		sb->s_export_op = &fat_export_ops_nostale;
+	}
 
 	return 0;
 }
@@ -1193,7 +1198,7 @@ static int fat_read_root(struct inode *inode)
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	int error;
 
-	MSDOS_I(inode)->i_pos = 0;
+	MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO;
 	inode->i_uid = sbi->options.fs_uid;
 	inode->i_gid = sbi->options.fs_gid;
 	inode->i_version++;
@@ -1256,6 +1261,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	sb->s_magic = MSDOS_SUPER_MAGIC;
 	sb->s_op = &fat_sops;
 	sb->s_export_op = &fat_export_ops;
+	mutex_init(&sbi->nfs_build_inode_lock);
 	ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL,
 			     DEFAULT_RATELIMIT_BURST);
 
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index e2cfda9..081b759 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -668,6 +668,7 @@ static struct file_system_type msdos_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("msdos");
 
 static int __init init_msdos_fs(void)
 {
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index ac959d6..2da9520 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -1073,6 +1073,7 @@ static struct file_system_type vfat_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("vfat");
 
 static int __init init_vfat_fs(void)
 {
diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c
index 499c104..93e1493 100644
--- a/fs/fat/nfs.c
+++ b/fs/fat/nfs.c
@@ -14,6 +14,18 @@
 #include <linux/exportfs.h>
 #include "fat.h"
 
+struct fat_fid {
+	u32 i_gen;
+	u32 i_pos_low;
+	u16 i_pos_hi;
+	u16 parent_i_pos_hi;
+	u32 parent_i_pos_low;
+	u32 parent_i_gen;
+};
+
+#define FAT_FID_SIZE_WITHOUT_PARENT 3
+#define FAT_FID_SIZE_WITH_PARENT (sizeof(struct fat_fid)/sizeof(u32))
+
 /**
  * Look up a directory inode given its starting cluster.
  */
@@ -38,63 +50,252 @@ static struct inode *fat_dget(struct super_block *sb, int i_logstart)
 	return inode;
 }
 
-static struct inode *fat_nfs_get_inode(struct super_block *sb,
-				       u64 ino, u32 generation)
+static struct inode *fat_ilookup(struct super_block *sb, u64 ino, loff_t i_pos)
 {
-	struct inode *inode;
+	if (MSDOS_SB(sb)->options.nfs == FAT_NFS_NOSTALE_RO)
+		return fat_iget(sb, i_pos);
 
-	if ((ino < MSDOS_ROOT_INO) || (ino == MSDOS_FSINFO_INO))
-		return NULL;
+	else {
+		if ((ino < MSDOS_ROOT_INO) || (ino == MSDOS_FSINFO_INO))
+			return NULL;
+		return ilookup(sb, ino);
+	}
+}
+
+static struct inode *__fat_nfs_get_inode(struct super_block *sb,
+				       u64 ino, u32 generation, loff_t i_pos)
+{
+	struct inode *inode = fat_ilookup(sb, ino, i_pos);
 
-	inode = ilookup(sb, ino);
 	if (inode && generation && (inode->i_generation != generation)) {
 		iput(inode);
 		inode = NULL;
 	}
+	if (inode == NULL && MSDOS_SB(sb)->options.nfs == FAT_NFS_NOSTALE_RO) {
+		struct buffer_head *bh = NULL;
+		struct msdos_dir_entry *de ;
+		sector_t blocknr;
+		int offset;
+		fat_get_blknr_offset(MSDOS_SB(sb), i_pos, &blocknr, &offset);
+		bh = sb_bread(sb, blocknr);
+		if (!bh) {
+			fat_msg(sb, KERN_ERR,
+				"unable to read block(%llu) for building NFS inode",
+				(llu)blocknr);
+			return inode;
+		}
+		de = (struct msdos_dir_entry *)bh->b_data;
+		/* If a file is deleted on server and client is not updated
+		 * yet, we must not build the inode upon a lookup call.
+		 */
+		if (IS_FREE(de[offset].name))
+			inode = NULL;
+		else
+			inode = fat_build_inode(sb, &de[offset], i_pos);
+		brelse(bh);
+	}
 
 	return inode;
 }
 
+static struct inode *fat_nfs_get_inode(struct super_block *sb,
+				       u64 ino, u32 generation)
+{
+
+	return __fat_nfs_get_inode(sb, ino, generation, 0);
+}
+
+static int
+fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp,
+		      struct inode *parent)
+{
+	int len = *lenp;
+	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+	struct fat_fid *fid = (struct fat_fid *) fh;
+	loff_t i_pos;
+	int type = FILEID_FAT_WITHOUT_PARENT;
+
+	if (parent) {
+		if (len < FAT_FID_SIZE_WITH_PARENT) {
+			*lenp = FAT_FID_SIZE_WITH_PARENT;
+			return FILEID_INVALID;
+		}
+	} else {
+		if (len < FAT_FID_SIZE_WITHOUT_PARENT) {
+			*lenp = FAT_FID_SIZE_WITHOUT_PARENT;
+			return FILEID_INVALID;
+		}
+	}
+
+	i_pos = fat_i_pos_read(sbi, inode);
+	*lenp = FAT_FID_SIZE_WITHOUT_PARENT;
+	fid->i_gen = inode->i_generation;
+	fid->i_pos_low = i_pos & 0xFFFFFFFF;
+	fid->i_pos_hi = (i_pos >> 32) & 0xFFFF;
+	if (parent) {
+		i_pos = fat_i_pos_read(sbi, parent);
+		fid->parent_i_pos_hi = (i_pos >> 32) & 0xFFFF;
+		fid->parent_i_pos_low = i_pos & 0xFFFFFFFF;
+		fid->parent_i_gen = parent->i_generation;
+		type = FILEID_FAT_WITH_PARENT;
+		*lenp = FAT_FID_SIZE_WITH_PARENT;
+	}
+
+	return type;
+}
+
 /**
  * Map a NFS file handle to a corresponding dentry.
  * The dentry may or may not be connected to the filesystem root.
  */
-struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid,
+static struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid,
 				int fh_len, int fh_type)
 {
 	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
 				    fat_nfs_get_inode);
 }
 
+static struct dentry *fat_fh_to_dentry_nostale(struct super_block *sb,
+					       struct fid *fh, int fh_len,
+					       int fh_type)
+{
+	struct inode *inode = NULL;
+	struct fat_fid *fid = (struct fat_fid *)fh;
+	loff_t i_pos;
+
+	switch (fh_type) {
+	case FILEID_FAT_WITHOUT_PARENT:
+		if (fh_len < FAT_FID_SIZE_WITHOUT_PARENT)
+			return NULL;
+		break;
+	case FILEID_FAT_WITH_PARENT:
+		if (fh_len < FAT_FID_SIZE_WITH_PARENT)
+			return NULL;
+		break;
+	default:
+		return NULL;
+	}
+	i_pos = fid->i_pos_hi;
+	i_pos = (i_pos << 32) | (fid->i_pos_low);
+	inode = __fat_nfs_get_inode(sb, 0, fid->i_gen, i_pos);
+
+	return d_obtain_alias(inode);
+}
+
 /*
  * Find the parent for a file specified by NFS handle.
  * This requires that the handle contain the i_ino of the parent.
  */
-struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid,
+static struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid,
 				int fh_len, int fh_type)
 {
 	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
 				    fat_nfs_get_inode);
 }
 
+static struct dentry *fat_fh_to_parent_nostale(struct super_block *sb,
+					       struct fid *fh, int fh_len,
+					       int fh_type)
+{
+	struct inode *inode = NULL;
+	struct fat_fid *fid = (struct fat_fid *)fh;
+	loff_t i_pos;
+
+	if (fh_len < FAT_FID_SIZE_WITH_PARENT)
+		return NULL;
+
+	switch (fh_type) {
+	case FILEID_FAT_WITH_PARENT:
+		i_pos = fid->parent_i_pos_hi;
+		i_pos = (i_pos << 32) | (fid->parent_i_pos_low);
+		inode = __fat_nfs_get_inode(sb, 0, fid->parent_i_gen, i_pos);
+		break;
+	}
+
+	return d_obtain_alias(inode);
+}
+
+/*
+ * Rebuild the parent for a directory that is not connected
+ *  to the filesystem root
+ */
+static
+struct inode *fat_rebuild_parent(struct super_block *sb, int parent_logstart)
+{
+	int search_clus, clus_to_match;
+	struct msdos_dir_entry *de;
+	struct inode *parent = NULL;
+	struct inode *dummy_grand_parent = NULL;
+	struct fat_slot_info sinfo;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	sector_t blknr = fat_clus_to_blknr(sbi, parent_logstart);
+	struct buffer_head *parent_bh = sb_bread(sb, blknr);
+	if (!parent_bh) {
+		fat_msg(sb, KERN_ERR,
+			"unable to read cluster of parent directory");
+		return NULL;
+	}
+
+	de = (struct msdos_dir_entry *) parent_bh->b_data;
+	clus_to_match = fat_get_start(sbi, &de[0]);
+	search_clus = fat_get_start(sbi, &de[1]);
+
+	dummy_grand_parent = fat_dget(sb, search_clus);
+	if (!dummy_grand_parent) {
+		dummy_grand_parent = new_inode(sb);
+		if (!dummy_grand_parent) {
+			brelse(parent_bh);
+			return parent;
+		}
+
+		dummy_grand_parent->i_ino = iunique(sb, MSDOS_ROOT_INO);
+		fat_fill_inode(dummy_grand_parent, &de[1]);
+		MSDOS_I(dummy_grand_parent)->i_pos = -1;
+	}
+
+	if (!fat_scan_logstart(dummy_grand_parent, clus_to_match, &sinfo))
+		parent = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
+
+	brelse(parent_bh);
+	iput(dummy_grand_parent);
+
+	return parent;
+}
+
 /*
  * Find the parent for a directory that is not currently connected to
  * the filesystem root.
  *
  * On entry, the caller holds child_dir->d_inode->i_mutex.
  */
-struct dentry *fat_get_parent(struct dentry *child_dir)
+static struct dentry *fat_get_parent(struct dentry *child_dir)
 {
 	struct super_block *sb = child_dir->d_sb;
 	struct buffer_head *bh = NULL;
 	struct msdos_dir_entry *de;
 	struct inode *parent_inode = NULL;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 
 	if (!fat_get_dotdot_entry(child_dir->d_inode, &bh, &de)) {
-		int parent_logstart = fat_get_start(MSDOS_SB(sb), de);
+		int parent_logstart = fat_get_start(sbi, de);
 		parent_inode = fat_dget(sb, parent_logstart);
+		if (!parent_inode && sbi->options.nfs == FAT_NFS_NOSTALE_RO)
+			parent_inode = fat_rebuild_parent(sb, parent_logstart);
 	}
 	brelse(bh);
 
 	return d_obtain_alias(parent_inode);
 }
+
+const struct export_operations fat_export_ops = {
+	.fh_to_dentry   = fat_fh_to_dentry,
+	.fh_to_parent   = fat_fh_to_parent,
+	.get_parent     = fat_get_parent,
+};
+
+const struct export_operations fat_export_ops_nostale = {
+	.encode_fh      = fat_encode_fh_nostale,
+	.fh_to_dentry   = fat_fh_to_dentry_nostale,
+	.fh_to_parent   = fat_fh_to_parent_nostale,
+	.get_parent     = fat_get_parent,
+};
diff --git a/fs/filesystems.c b/fs/filesystems.c
index da165f6..92567d9 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -273,7 +273,7 @@ struct file_system_type *get_fs_type(const char *name)
 	int len = dot ? dot - name : strlen(name);
 
 	fs = __get_fs_type(name, len);
-	if (!fs && (request_module("%.*s", len, name) == 0))
+	if (!fs && (request_module("fs-%.*s", len, name) == 0))
 		fs = __get_fs_type(name, len);
 
 	if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) {
diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c
index fed2c8a..e37eb27 100644
--- a/fs/freevxfs/vxfs_super.c
+++ b/fs/freevxfs/vxfs_super.c
@@ -52,7 +52,6 @@ MODULE_AUTHOR("Christoph Hellwig");
 MODULE_DESCRIPTION("Veritas Filesystem (VxFS) driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
-MODULE_ALIAS("vxfs"); /* makes mount -t vxfs autoload the module */
 
 
 static void		vxfs_put_super(struct super_block *);
@@ -258,6 +257,8 @@ static struct file_system_type vxfs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("vxfs"); /* makes mount -t vxfs autoload the module */
+MODULE_ALIAS("vxfs");
 
 static int __init
 vxfs_init(void)
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 8179e8b..40d13c7 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -287,5 +287,5 @@ const struct file_operations fscache_stats_fops = {
 	.open		= fscache_stats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release        = single_release,
 };
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index b7978b9f..a0b0855 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -341,6 +341,7 @@ static struct file_system_type fuse_ctl_fs_type = {
 	.mount		= fuse_ctl_mount,
 	.kill_sb	= fuse_ctl_kill_sb,
 };
+MODULE_ALIAS_FS("fusectl");
 
 int __init fuse_ctl_init(void)
 {
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index df00993..137185c 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1117,6 +1117,7 @@ static struct file_system_type fuse_fs_type = {
 	.mount		= fuse_mount,
 	.kill_sb	= fuse_kill_sb_anon,
 };
+MODULE_ALIAS_FS("fuse");
 
 #ifdef CONFIG_BLOCK
 static struct dentry *fuse_mount_blk(struct file_system_type *fs_type,
@@ -1146,6 +1147,7 @@ static struct file_system_type fuseblk_fs_type = {
 	.kill_sb	= fuse_kill_sb_blk,
 	.fs_flags	= FS_REQUIRES_DEV | FS_HAS_SUBTYPE,
 };
+MODULE_ALIAS_FS("fuseblk");
 
 static inline int register_fuseblk(void)
 {
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 019f45e..d79c2da 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -923,8 +923,11 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 		cmd = F_SETLK;
 		fl->fl_type = F_UNLCK;
 	}
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
+		if (fl->fl_type == F_UNLCK)
+			posix_lock_file_wait(file, fl);
 		return -EIO;
+	}
 	if (IS_GETLK(cmd))
 		return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl);
 	else if (fl->fl_type == F_UNLCK)
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 156e42e..5c29216 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -588,6 +588,7 @@ struct lm_lockstruct {
 	struct dlm_lksb ls_control_lksb; /* control_lock */
 	char ls_control_lvb[GDLM_LVB_SIZE]; /* control_lock lvb */
 	struct completion ls_sync_wait; /* {control,mounted}_{lock,unlock} */
+	char *ls_lvb_bits;
 
 	spinlock_t ls_recover_spin; /* protects following fields */
 	unsigned long ls_recover_flags; /* DFL_ */
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 9802de0..c8423d6 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -483,12 +483,8 @@ static void control_lvb_write(struct lm_lockstruct *ls, uint32_t lvb_gen,
 
 static int all_jid_bits_clear(char *lvb)
 {
-	int i;
-	for (i = JID_BITMAP_OFFSET; i < GDLM_LVB_SIZE; i++) {
-		if (lvb[i])
-			return 0;
-	}
-	return 1;
+	return !memchr_inv(lvb + JID_BITMAP_OFFSET, 0,
+			GDLM_LVB_SIZE - JID_BITMAP_OFFSET);
 }
 
 static void sync_wait_cb(void *arg)
@@ -580,7 +576,6 @@ static void gfs2_control_func(struct work_struct *work)
 {
 	struct gfs2_sbd *sdp = container_of(work, struct gfs2_sbd, sd_control_work.work);
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
-	char lvb_bits[GDLM_LVB_SIZE];
 	uint32_t block_gen, start_gen, lvb_gen, flags;
 	int recover_set = 0;
 	int write_lvb = 0;
@@ -634,7 +629,7 @@ static void gfs2_control_func(struct work_struct *work)
 		return;
 	}
 
-	control_lvb_read(ls, &lvb_gen, lvb_bits);
+	control_lvb_read(ls, &lvb_gen, ls->ls_lvb_bits);
 
 	spin_lock(&ls->ls_recover_spin);
 	if (block_gen != ls->ls_recover_block ||
@@ -664,10 +659,10 @@ static void gfs2_control_func(struct work_struct *work)
 
 			ls->ls_recover_result[i] = 0;
 
-			if (!test_bit_le(i, lvb_bits + JID_BITMAP_OFFSET))
+			if (!test_bit_le(i, ls->ls_lvb_bits + JID_BITMAP_OFFSET))
 				continue;
 
-			__clear_bit_le(i, lvb_bits + JID_BITMAP_OFFSET);
+			__clear_bit_le(i, ls->ls_lvb_bits + JID_BITMAP_OFFSET);
 			write_lvb = 1;
 		}
 	}
@@ -691,7 +686,7 @@ static void gfs2_control_func(struct work_struct *work)
 				continue;
 			if (ls->ls_recover_submit[i] < start_gen) {
 				ls->ls_recover_submit[i] = 0;
-				__set_bit_le(i, lvb_bits + JID_BITMAP_OFFSET);
+				__set_bit_le(i, ls->ls_lvb_bits + JID_BITMAP_OFFSET);
 			}
 		}
 		/* even if there are no bits to set, we need to write the
@@ -705,7 +700,7 @@ static void gfs2_control_func(struct work_struct *work)
 	spin_unlock(&ls->ls_recover_spin);
 
 	if (write_lvb) {
-		control_lvb_write(ls, start_gen, lvb_bits);
+		control_lvb_write(ls, start_gen, ls->ls_lvb_bits);
 		flags = DLM_LKF_CONVERT | DLM_LKF_VALBLK;
 	} else {
 		flags = DLM_LKF_CONVERT;
@@ -725,7 +720,7 @@ static void gfs2_control_func(struct work_struct *work)
 	 */
 
 	for (i = 0; i < recover_size; i++) {
-		if (test_bit_le(i, lvb_bits + JID_BITMAP_OFFSET)) {
+		if (test_bit_le(i, ls->ls_lvb_bits + JID_BITMAP_OFFSET)) {
 			fs_info(sdp, "recover generation %u jid %d\n",
 				start_gen, i);
 			gfs2_recover_set(sdp, i);
@@ -758,7 +753,6 @@ static void gfs2_control_func(struct work_struct *work)
 static int control_mount(struct gfs2_sbd *sdp)
 {
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
-	char lvb_bits[GDLM_LVB_SIZE];
 	uint32_t start_gen, block_gen, mount_gen, lvb_gen;
 	int mounted_mode;
 	int retries = 0;
@@ -857,7 +851,7 @@ locks_done:
 	 * lvb_gen will be non-zero.
 	 */
 
-	control_lvb_read(ls, &lvb_gen, lvb_bits);
+	control_lvb_read(ls, &lvb_gen, ls->ls_lvb_bits);
 
 	if (lvb_gen == 0xFFFFFFFF) {
 		/* special value to force mount attempts to fail */
@@ -887,7 +881,7 @@ locks_done:
 	 * and all lvb bits to be clear (no pending journal recoveries.)
 	 */
 
-	if (!all_jid_bits_clear(lvb_bits)) {
+	if (!all_jid_bits_clear(ls->ls_lvb_bits)) {
 		/* journals need recovery, wait until all are clear */
 		fs_info(sdp, "control_mount wait for journal recovery\n");
 		goto restart;
@@ -949,7 +943,6 @@ static int dlm_recovery_wait(void *word)
 static int control_first_done(struct gfs2_sbd *sdp)
 {
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
-	char lvb_bits[GDLM_LVB_SIZE];
 	uint32_t start_gen, block_gen;
 	int error;
 
@@ -991,8 +984,8 @@ restart:
 	memset(ls->ls_recover_result, 0, ls->ls_recover_size*sizeof(uint32_t));
 	spin_unlock(&ls->ls_recover_spin);
 
-	memset(lvb_bits, 0, sizeof(lvb_bits));
-	control_lvb_write(ls, start_gen, lvb_bits);
+	memset(ls->ls_lvb_bits, 0, GDLM_LVB_SIZE);
+	control_lvb_write(ls, start_gen, ls->ls_lvb_bits);
 
 	error = mounted_lock(sdp, DLM_LOCK_PR, DLM_LKF_CONVERT);
 	if (error)
@@ -1022,6 +1015,12 @@ static int set_recover_size(struct gfs2_sbd *sdp, struct dlm_slot *slots,
 	uint32_t old_size, new_size;
 	int i, max_jid;
 
+	if (!ls->ls_lvb_bits) {
+		ls->ls_lvb_bits = kzalloc(GDLM_LVB_SIZE, GFP_NOFS);
+		if (!ls->ls_lvb_bits)
+			return -ENOMEM;
+	}
+
 	max_jid = 0;
 	for (i = 0; i < num_slots; i++) {
 		if (max_jid < slots[i].slot - 1)
@@ -1057,6 +1056,7 @@ static int set_recover_size(struct gfs2_sbd *sdp, struct dlm_slot *slots,
 
 static void free_recover_size(struct lm_lockstruct *ls)
 {
+	kfree(ls->ls_lvb_bits);
 	kfree(ls->ls_recover_submit);
 	kfree(ls->ls_recover_result);
 	ls->ls_recover_submit = NULL;
@@ -1205,6 +1205,7 @@ static int gdlm_mount(struct gfs2_sbd *sdp, const char *table)
 	ls->ls_recover_size = 0;
 	ls->ls_recover_submit = NULL;
 	ls->ls_recover_result = NULL;
+	ls->ls_lvb_bits = NULL;
 
 	error = set_recover_size(sdp, NULL, 0);
 	if (error)
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 1b612be..60ede2a 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -20,6 +20,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/quotaops.h>
 #include <linux/lockdep.h>
+#include <linux/module.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -1425,6 +1426,7 @@ struct file_system_type gfs2_fs_type = {
 	.kill_sb = gfs2_kill_sb,
 	.owner = THIS_MODULE,
 };
+MODULE_ALIAS_FS("gfs2");
 
 struct file_system_type gfs2meta_fs_type = {
 	.name = "gfs2meta",
@@ -1432,4 +1434,4 @@ struct file_system_type gfs2meta_fs_type = {
 	.mount = gfs2_mount_meta,
 	.owner = THIS_MODULE,
 };
-
+MODULE_ALIAS_FS("gfs2meta");
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index d1f51fd..5a51265 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -576,7 +576,7 @@ int gfs2_rs_alloc(struct gfs2_inode *ip)
 	RB_CLEAR_NODE(&ip->i_res->rs_node);
 out:
 	up_write(&ip->i_rw_mutex);
-	return 0;
+	return error;
 }
 
 static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs)
@@ -1181,12 +1181,9 @@ int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
 			     const struct gfs2_bitmap *bi, unsigned minlen, u64 *ptrimmed)
 {
 	struct super_block *sb = sdp->sd_vfs;
-	struct block_device *bdev = sb->s_bdev;
-	const unsigned int sects_per_blk = sdp->sd_sb.sb_bsize /
-					   bdev_logical_block_size(sb->s_bdev);
 	u64 blk;
 	sector_t start = 0;
-	sector_t nr_sects = 0;
+	sector_t nr_blks = 0;
 	int rv;
 	unsigned int x;
 	u32 trimmed = 0;
@@ -1206,35 +1203,34 @@ int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
 		if (diff == 0)
 			continue;
 		blk = offset + ((bi->bi_start + x) * GFS2_NBBY);
-		blk *= sects_per_blk; /* convert to sectors */
 		while(diff) {
 			if (diff & 1) {
-				if (nr_sects == 0)
+				if (nr_blks == 0)
 					goto start_new_extent;
-				if ((start + nr_sects) != blk) {
-					if (nr_sects >= minlen) {
-						rv = blkdev_issue_discard(bdev,
-							start, nr_sects,
+				if ((start + nr_blks) != blk) {
+					if (nr_blks >= minlen) {
+						rv = sb_issue_discard(sb,
+							start, nr_blks,
 							GFP_NOFS, 0);
 						if (rv)
 							goto fail;
-						trimmed += nr_sects;
+						trimmed += nr_blks;
 					}
-					nr_sects = 0;
+					nr_blks = 0;
 start_new_extent:
 					start = blk;
 				}
-				nr_sects += sects_per_blk;
+				nr_blks++;
 			}
 			diff >>= 2;
-			blk += sects_per_blk;
+			blk++;
 		}
 	}
-	if (nr_sects >= minlen) {
-		rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, 0);
+	if (nr_blks >= minlen) {
+		rv = sb_issue_discard(sb, start, nr_blks, GFP_NOFS, 0);
 		if (rv)
 			goto fail;
-		trimmed += nr_sects;
+		trimmed += nr_blks;
 	}
 	if (ptrimmed)
 		*ptrimmed = trimmed;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index e93ddaa..bbaaa8a 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -466,6 +466,7 @@ static struct file_system_type hfs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("hfs");
 
 static void hfs_init_once(void *p)
 {
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index a94f0f7..fe0a762 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -533,7 +533,7 @@ void hfsplus_file_truncate(struct inode *inode)
 		struct address_space *mapping = inode->i_mapping;
 		struct page *page;
 		void *fsdata;
-		u32 size = inode->i_size;
+		loff_t size = inode->i_size;
 
 		res = pagecache_write_begin(NULL, mapping, size, 0,
 						AOP_FLAG_UNINTERRUPTIBLE,
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 974c26f..7b87284 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -654,6 +654,7 @@ static struct file_system_type hfsplus_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("hfsplus");
 
 static void hfsplus_init_once(void *p)
 {
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index fbabb90..0f6e52d 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -845,15 +845,8 @@ int hostfs_setattr(struct dentry *dentry, struct iattr *attr)
 		return err;
 
 	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode)) {
-		int error;
-
-		error = inode_newsize_ok(inode, attr->ia_size);
-		if (error)
-			return error;
-
+	    attr->ia_size != i_size_read(inode))
 		truncate_setsize(inode, attr->ia_size);
-	}
 
 	setattr_copy(inode, attr);
 	mark_inode_dirty(inode);
@@ -993,6 +986,7 @@ static struct file_system_type hostfs_type = {
 	.kill_sb	= hostfs_kill_sb,
 	.fs_flags 	= 0,
 };
+MODULE_ALIAS_FS("hostfs");
 
 static int __init init_hostfs(void)
 {
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index a307622..a0617e7 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -688,6 +688,7 @@ static struct file_system_type hpfs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("hpfs");
 
 static int __init init_hpfs_fs(void)
 {
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index 74f5570..126d3c2 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -748,6 +748,7 @@ static struct file_system_type hppfs_type = {
 	.kill_sb	= kill_anon_super,
 	.fs_flags 	= 0,
 };
+MODULE_ALIAS_FS("hppfs");
 
 static int __init init_hppfs(void)
 {
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 7f94e0c..523464e 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -110,7 +110,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	 * way when do_mmap_pgoff unwinds (may be important on powerpc
 	 * and ia64).
 	 */
-	vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
 	vma->vm_ops = &hugetlb_vm_ops;
 
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
@@ -896,6 +896,7 @@ static struct file_system_type hugetlbfs_fs_type = {
 	.mount		= hugetlbfs_mount,
 	.kill_sb	= kill_litter_super,
 };
+MODULE_ALIAS_FS("hugetlbfs");
 
 static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
 
diff --git a/fs/inode.c b/fs/inode.c
index f5f7c06..a898b3d 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -725,7 +725,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan)
 		 * inode to the back of the list so we don't spin on it.
 		 */
 		if (!spin_trylock(&inode->i_lock)) {
-			list_move_tail(&inode->i_lru, &sb->s_inode_lru);
+			list_move(&inode->i_lru, &sb->s_inode_lru);
 			continue;
 		}
 
diff --git a/fs/internal.h b/fs/internal.h
index 507141f..4be7823 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -125,3 +125,8 @@ extern int invalidate_inodes(struct super_block *, bool);
  * dcache.c
  */
 extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
+
+/*
+ * read_write.c
+ */
+extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 67ce52507..d9b8aeb 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -1556,6 +1556,8 @@ static struct file_system_type iso9660_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("iso9660");
+MODULE_ALIAS("iso9660");
 
 static int __init init_iso9660_fs(void)
 {
@@ -1593,5 +1595,3 @@ static void __exit exit_iso9660_fs(void)
 module_init(init_iso9660_fs)
 module_exit(exit_iso9660_fs)
 MODULE_LICENSE("GPL");
-/* Actual filesystem name is iso9660, as requested in filesystems.c */
-MODULE_ALIAS("iso9660");
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 86b39b1..11bb11f 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -162,8 +162,17 @@ static void journal_do_submit_data(struct buffer_head **wbuf, int bufs,
 
 	for (i = 0; i < bufs; i++) {
 		wbuf[i]->b_end_io = end_buffer_write_sync;
-		/* We use-up our safety reference in submit_bh() */
-		submit_bh(write_op, wbuf[i]);
+		/*
+		 * Here we write back pagecache data that may be mmaped. Since
+		 * we cannot afford to clean the page and set PageWriteback
+		 * here due to lock ordering (page lock ranks above transaction
+		 * start), the data can change while IO is in flight. Tell the
+		 * block layer it should bounce the bio pages if stable data
+		 * during write is required.
+		 *
+		 * We use up our safety reference in submit_bh().
+		 */
+		_submit_bh(write_op, wbuf[i], 1 << BIO_SNAP_STABLE);
 	}
 }
 
@@ -667,7 +676,17 @@ start_journal_io:
 				clear_buffer_dirty(bh);
 				set_buffer_uptodate(bh);
 				bh->b_end_io = journal_end_buffer_io_sync;
-				submit_bh(write_op, bh);
+				/*
+				 * In data=journal mode, here we can end up
+				 * writing pagecache data that might be
+				 * mmapped. Since we can't afford to clean the
+				 * page and set PageWriteback (see the comment
+				 * near the other use of _submit_bh()), the
+				 * data can change while the write is in
+				 * flight.  Tell the block layer to bounce the
+				 * bio pages if stable pages are required.
+				 */
+				_submit_bh(write_op, bh, 1 << BIO_SNAP_STABLE);
 			}
 			cond_resched();
 
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index 81cc7ea..865c430 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -310,8 +310,6 @@ int journal_write_metadata_buffer(transaction_t *transaction,
 
 	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
 	/* keep subsequent assertions sane */
-	new_bh->b_state = 0;
-	init_buffer(new_bh, NULL, NULL);
 	atomic_set(&new_bh->b_count, 1);
 	new_jh = journal_add_journal_head(new_bh);	/* This sleeps */
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index ed10991..8b220f1 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -367,8 +367,6 @@ retry_alloc:
 	}
 
 	/* keep subsequent assertions sane */
-	new_bh->b_state = 0;
-	init_buffer(new_bh, NULL, NULL);
 	atomic_set(&new_bh->b_count, 1);
 	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */
 
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index d6ee5ae..325bc01 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1065,9 +1065,12 @@ out:
 void jbd2_journal_set_triggers(struct buffer_head *bh,
 			       struct jbd2_buffer_trigger_type *type)
 {
-	struct journal_head *jh = bh2jh(bh);
+	struct journal_head *jh = jbd2_journal_grab_journal_head(bh);
 
+	if (WARN_ON(!jh))
+		return;
 	jh->b_triggers = type;
+	jbd2_journal_put_journal_head(jh);
 }
 
 void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data,
@@ -1119,17 +1122,18 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 {
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal = transaction->t_journal;
-	struct journal_head *jh = bh2jh(bh);
+	struct journal_head *jh;
 	int ret = 0;
 
-	jbd_debug(5, "journal_head %p\n", jh);
-	JBUFFER_TRACE(jh, "entry");
 	if (is_handle_aborted(handle))
 		goto out;
-	if (!buffer_jbd(bh)) {
+	jh = jbd2_journal_grab_journal_head(bh);
+	if (!jh) {
 		ret = -EUCLEAN;
 		goto out;
 	}
+	jbd_debug(5, "journal_head %p\n", jh);
+	JBUFFER_TRACE(jh, "entry");
 
 	jbd_lock_bh_state(bh);
 
@@ -1220,6 +1224,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	spin_unlock(&journal->j_list_lock);
 out_unlock_bh:
 	jbd_unlock_bh_state(bh);
+	jbd2_journal_put_journal_head(jh);
 out:
 	JBUFFER_TRACE(jh, "exit");
 	WARN_ON(ret);	/* All errors are bugs, so dump the stack */
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index d3d8799..0defb1c 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -356,6 +356,7 @@ static struct file_system_type jffs2_fs_type = {
 	.mount =	jffs2_mount,
 	.kill_sb =	jffs2_kill_sb,
 };
+MODULE_ALIAS_FS("jffs2");
 
 static int __init init_jffs2_fs(void)
 {
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 060ba63..2003e83 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -833,6 +833,7 @@ static struct file_system_type jfs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("jfs");
 
 static void init_once(void *foo)
 {
diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index 345c24b..5436029 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -608,6 +608,7 @@ static struct file_system_type logfs_fs_type = {
 	.fs_flags	= FS_REQUIRES_DEV,
 
 };
+MODULE_ALIAS_FS("logfs");
 
 static int __init logfs_init(void)
 {
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 99541cc..df12249 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -660,6 +660,7 @@ static struct file_system_type minix_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("minix");
 
 static int __init init_minix_fs(void)
 {
diff --git a/fs/namei.c b/fs/namei.c
index 961bc12..57ae9c8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -689,8 +689,6 @@ void nd_jump_link(struct nameidata *nd, struct path *path)
 	nd->path = *path;
 	nd->inode = nd->path.dentry->d_inode;
 	nd->flags |= LOOKUP_JUMPED;
-
-	BUG_ON(nd->inode->i_op->follow_link);
 }
 
 static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
diff --git a/fs/namespace.c b/fs/namespace.c
index 50ca17d..341d3f5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -798,6 +798,10 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	}
 
 	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+	/* Don't allow unprivileged users to change mount flags */
+	if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
+		mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+
 	atomic_inc(&sb->s_active);
 	mnt->mnt.mnt_sb = sb;
 	mnt->mnt.mnt_root = dget(root);
@@ -1686,7 +1690,7 @@ static int do_loopback(struct path *path, const char *old_name,
 
 	if (IS_ERR(mnt)) {
 		err = PTR_ERR(mnt);
-		goto out;
+		goto out2;
 	}
 
 	err = graft_tree(mnt, path);
@@ -1713,6 +1717,9 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
 	if (readonly_request == __mnt_is_readonly(mnt))
 		return 0;
 
+	if (mnt->mnt_flags & MNT_LOCK_READONLY)
+		return -EPERM;
+
 	if (readonly_request)
 		error = mnt_make_readonly(real_mount(mnt));
 	else
@@ -2339,7 +2346,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	/* First pass: copy the tree topology */
 	copy_flags = CL_COPY_ALL | CL_EXPIRE;
 	if (user_ns != mnt_ns->user_ns)
-		copy_flags |= CL_SHARED_TO_SLAVE;
+		copy_flags |= CL_SHARED_TO_SLAVE | CL_UNPRIVILEGED;
 	new = copy_tree(old, old->mnt.mnt_root, copy_flags);
 	if (IS_ERR(new)) {
 		up_write(&namespace_sem);
@@ -2732,6 +2739,51 @@ bool our_mnt(struct vfsmount *mnt)
 	return check_mnt(real_mount(mnt));
 }
 
+bool current_chrooted(void)
+{
+	/* Does the current process have a non-standard root */
+	struct path ns_root;
+	struct path fs_root;
+	bool chrooted;
+
+	/* Find the namespace root */
+	ns_root.mnt = &current->nsproxy->mnt_ns->root->mnt;
+	ns_root.dentry = ns_root.mnt->mnt_root;
+	path_get(&ns_root);
+	while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root))
+		;
+
+	get_fs_root(current->fs, &fs_root);
+
+	chrooted = !path_equal(&fs_root, &ns_root);
+
+	path_put(&fs_root);
+	path_put(&ns_root);
+
+	return chrooted;
+}
+
+void update_mnt_policy(struct user_namespace *userns)
+{
+	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	struct mount *mnt;
+
+	down_read(&namespace_sem);
+	list_for_each_entry(mnt, &ns->list, mnt_list) {
+		switch (mnt->mnt.mnt_sb->s_magic) {
+		case SYSFS_MAGIC:
+			userns->may_mount_sysfs = true;
+			break;
+		case PROC_SUPER_MAGIC:
+			userns->may_mount_proc = true;
+			break;
+		}
+		if (userns->may_mount_sysfs && userns->may_mount_proc)
+			break;
+	}
+	up_read(&namespace_sem);
+}
+
 static void *mntns_get(struct task_struct *task)
 {
 	struct mnt_namespace *ns = NULL;
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 7dafd6899..26910c8 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -1051,6 +1051,7 @@ static struct file_system_type ncp_fs_type = {
 	.kill_sb	= kill_anon_super,
 	.fs_flags	= FS_BINARY_MOUNTDATA,
 };
+MODULE_ALIAS_FS("ncpfs");
 
 static int __init init_ncp_fs(void)
 {
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
index 737d839..6fc7b5c 100644
--- a/fs/nfs/blocklayout/blocklayoutdm.c
+++ b/fs/nfs/blocklayout/blocklayoutdm.c
@@ -55,7 +55,8 @@ static void dev_remove(struct net *net, dev_t dev)
 
 	bl_pipe_msg.bl_wq = &nn->bl_wq;
 	memset(msg, 0, sizeof(*msg));
-	msg->data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
+	msg->len = sizeof(bl_msg) + bl_msg.totallen;
+	msg->data = kzalloc(msg->len, GFP_NOFS);
 	if (!msg->data)
 		goto out;
 
@@ -66,7 +67,6 @@ static void dev_remove(struct net *net, dev_t dev)
 	memcpy(msg->data, &bl_msg, sizeof(bl_msg));
 	dataptr = (uint8_t *) msg->data;
 	memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request));
-	msg->len = sizeof(bl_msg) + bl_msg.totallen;
 
 	add_wait_queue(&nn->bl_wq, &wq);
 	if (rpc_queue_upcall(nn->bl_device_pipe, msg) < 0) {
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index dc0f98d..c516da5 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -726,9 +726,9 @@ out1:
 	return ret;
 }
 
-static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data)
+static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data, size_t datalen)
 {
-	return key_instantiate_and_link(key, data, strlen(data) + 1,
+	return key_instantiate_and_link(key, data, datalen,
 					id_resolver_cache->thread_keyring,
 					authkey);
 }
@@ -738,6 +738,7 @@ static int nfs_idmap_read_and_verify_message(struct idmap_msg *im,
 		struct key *key, struct key *authkey)
 {
 	char id_str[NFS_UINT_MAXLEN];
+	size_t len;
 	int ret = -ENOKEY;
 
 	/* ret = -ENOKEY */
@@ -747,13 +748,15 @@ static int nfs_idmap_read_and_verify_message(struct idmap_msg *im,
 	case IDMAP_CONV_NAMETOID:
 		if (strcmp(upcall->im_name, im->im_name) != 0)
 			break;
-		sprintf(id_str, "%d", im->im_id);
-		ret = nfs_idmap_instantiate(key, authkey, id_str);
+		/* Note: here we store the NUL terminator too */
+		len = sprintf(id_str, "%d", im->im_id) + 1;
+		ret = nfs_idmap_instantiate(key, authkey, id_str, len);
 		break;
 	case IDMAP_CONV_IDTONAME:
 		if (upcall->im_id != im->im_id)
 			break;
-		ret = nfs_idmap_instantiate(key, authkey, im->im_name);
+		len = strlen(im->im_name);
+		ret = nfs_idmap_instantiate(key, authkey, im->im_name, len);
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index ac4fc9a..66b6664 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -300,7 +300,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
 			   struct rpc_cred *cred)
 {
 	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
-	struct nfs_client *pos, *n, *prev = NULL;
+	struct nfs_client *pos, *prev = NULL;
 	struct nfs4_setclientid_res clid = {
 		.clientid	= new->cl_clientid,
 		.confirm	= new->cl_confirm,
@@ -308,10 +308,23 @@ int nfs40_walk_client_list(struct nfs_client *new,
 	int status = -NFS4ERR_STALE_CLIENTID;
 
 	spin_lock(&nn->nfs_client_lock);
-	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
 		/* If "pos" isn't marked ready, we can't trust the
 		 * remaining fields in "pos" */
-		if (pos->cl_cons_state < NFS_CS_READY)
+		if (pos->cl_cons_state > NFS_CS_READY) {
+			atomic_inc(&pos->cl_count);
+			spin_unlock(&nn->nfs_client_lock);
+
+			if (prev)
+				nfs_put_client(prev);
+			prev = pos;
+
+			status = nfs_wait_client_init_complete(pos);
+			spin_lock(&nn->nfs_client_lock);
+			if (status < 0)
+				continue;
+		}
+		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
 
 		if (pos->rpc_ops != new->rpc_ops)
@@ -423,16 +436,16 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			   struct rpc_cred *cred)
 {
 	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
-	struct nfs_client *pos, *n, *prev = NULL;
+	struct nfs_client *pos, *prev = NULL;
 	int status = -NFS4ERR_STALE_CLIENTID;
 
 	spin_lock(&nn->nfs_client_lock);
-	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
 		/* If "pos" isn't marked ready, we can't trust the
 		 * remaining fields in "pos", especially the client
 		 * ID and serverowner fields.  Wait for CREATE_SESSION
 		 * to finish. */
-		if (pos->cl_cons_state < NFS_CS_READY) {
+		if (pos->cl_cons_state > NFS_CS_READY) {
 			atomic_inc(&pos->cl_count);
 			spin_unlock(&nn->nfs_client_lock);
 
@@ -440,18 +453,17 @@ int nfs41_walk_client_list(struct nfs_client *new,
 				nfs_put_client(prev);
 			prev = pos;
 
-			nfs4_schedule_lease_recovery(pos);
 			status = nfs_wait_client_init_complete(pos);
-			if (status < 0) {
-				nfs_put_client(pos);
-				spin_lock(&nn->nfs_client_lock);
-				continue;
+			if (status == 0) {
+				nfs4_schedule_lease_recovery(pos);
+				status = nfs4_wait_clnt_recover(pos);
 			}
-			status = pos->cl_cons_state;
 			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
 				continue;
 		}
+		if (pos->cl_cons_state != NFS_CS_READY)
+			continue;
 
 		if (pos->rpc_ops != new->rpc_ops)
 			continue;
@@ -469,17 +481,18 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			continue;
 
 		atomic_inc(&pos->cl_count);
-		spin_unlock(&nn->nfs_client_lock);
+		*result = pos;
+		status = 0;
 		dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
 			__func__, pos, atomic_read(&pos->cl_count));
-
-		*result = pos;
-		return 0;
+		break;
 	}
 
 	/* No matching nfs_client found. */
 	spin_unlock(&nn->nfs_client_lock);
 	dprintk("NFS: <-- %s status = %d\n", __func__, status);
+	if (prev)
+		nfs_put_client(prev);
 	return status;
 }
 #endif	/* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 49eeb04..4fb234d 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -129,7 +129,6 @@ static void filelayout_fenceme(struct inode *inode, struct pnfs_layout_hdr *lo)
 {
 	if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
 		return;
-	clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags);
 	pnfs_return_layout(inode);
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b2671cb..0ad025e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1046,6 +1046,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 		/* Save the delegation */
 		nfs4_stateid_copy(&stateid, &delegation->stateid);
 		rcu_read_unlock();
+		nfs_release_seqid(opendata->o_arg.seqid);
 		ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode);
 		if (ret != 0)
 			goto out;
@@ -2632,7 +2633,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	int status;
 
 	if (pnfs_ld_layoutret_on_setattr(inode))
-		pnfs_return_layout(inode);
+		pnfs_commit_and_return_layout(inode);
 
 	nfs_fattr_init(fattr);
 	
@@ -6416,22 +6417,8 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 static void nfs4_layoutcommit_release(void *calldata)
 {
 	struct nfs4_layoutcommit_data *data = calldata;
-	struct pnfs_layout_segment *lseg, *tmp;
-	unsigned long *bitlock = &NFS_I(data->args.inode)->flags;
 
 	pnfs_cleanup_layoutcommit(data);
-	/* Matched by references in pnfs_set_layoutcommit */
-	list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) {
-		list_del_init(&lseg->pls_lc_list);
-		if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT,
-				       &lseg->pls_flags))
-			pnfs_put_lseg(lseg);
-	}
-
-	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
-	smp_mb__after_clear_bit();
-	wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
-
 	put_rpccred(data->cred);
 	kfree(data);
 }
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 6ace365..d41a351 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1886,7 +1886,13 @@ again:
 			status = PTR_ERR(clnt);
 			break;
 		}
-		clp->cl_rpcclient = clnt;
+		/* Note: this is safe because we haven't yet marked the
+		 * client as ready, so we are the only user of
+		 * clp->cl_rpcclient
+		 */
+		clnt = xchg(&clp->cl_rpcclient, clnt);
+		rpc_shutdown_client(clnt);
+		clnt = clp->cl_rpcclient;
 		goto again;
 
 	case -NFS4ERR_MINOR_VERS_MISMATCH:
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 48ac5aa..4bdffe0 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -417,6 +417,16 @@ should_free_lseg(struct pnfs_layout_range *lseg_range,
 	       lo_seg_intersecting(lseg_range, recall_range);
 }
 
+static bool pnfs_lseg_dec_and_remove_zero(struct pnfs_layout_segment *lseg,
+		struct list_head *tmp_list)
+{
+	if (!atomic_dec_and_test(&lseg->pls_refcount))
+		return false;
+	pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
+	list_add(&lseg->pls_list, tmp_list);
+	return true;
+}
+
 /* Returns 1 if lseg is removed from list, 0 otherwise */
 static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
 			     struct list_head *tmp_list)
@@ -430,11 +440,8 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
 		 */
 		dprintk("%s: lseg %p ref %d\n", __func__, lseg,
 			atomic_read(&lseg->pls_refcount));
-		if (atomic_dec_and_test(&lseg->pls_refcount)) {
-			pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
-			list_add(&lseg->pls_list, tmp_list);
+		if (pnfs_lseg_dec_and_remove_zero(lseg, tmp_list))
 			rv = 1;
-		}
 	}
 	return rv;
 }
@@ -777,6 +784,21 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	return lseg;
 }
 
+static void pnfs_clear_layoutcommit(struct inode *inode,
+		struct list_head *head)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct pnfs_layout_segment *lseg, *tmp;
+
+	if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+		return;
+	list_for_each_entry_safe(lseg, tmp, &nfsi->layout->plh_segs, pls_list) {
+		if (!test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+			continue;
+		pnfs_lseg_dec_and_remove_zero(lseg, head);
+	}
+}
+
 /*
  * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
  * when the layout segment list is empty.
@@ -808,6 +830,7 @@ _pnfs_return_layout(struct inode *ino)
 	/* Reference matched in nfs4_layoutreturn_release */
 	pnfs_get_layout_hdr(lo);
 	empty = list_empty(&lo->plh_segs);
+	pnfs_clear_layoutcommit(ino, &tmp_list);
 	pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
 	/* Don't send a LAYOUTRETURN if list was initially empty */
 	if (empty) {
@@ -820,8 +843,6 @@ _pnfs_return_layout(struct inode *ino)
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 
-	WARN_ON(test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags));
-
 	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
 	if (unlikely(lrp == NULL)) {
 		status = -ENOMEM;
@@ -845,6 +866,33 @@ out:
 }
 EXPORT_SYMBOL_GPL(_pnfs_return_layout);
 
+int
+pnfs_commit_and_return_layout(struct inode *inode)
+{
+	struct pnfs_layout_hdr *lo;
+	int ret;
+
+	spin_lock(&inode->i_lock);
+	lo = NFS_I(inode)->layout;
+	if (lo == NULL) {
+		spin_unlock(&inode->i_lock);
+		return 0;
+	}
+	pnfs_get_layout_hdr(lo);
+	/* Block new layoutgets and read/write to ds */
+	lo->plh_block_lgets++;
+	spin_unlock(&inode->i_lock);
+	filemap_fdatawait(inode->i_mapping);
+	ret = pnfs_layoutcommit_inode(inode, true);
+	if (ret == 0)
+		ret = _pnfs_return_layout(inode);
+	spin_lock(&inode->i_lock);
+	lo->plh_block_lgets--;
+	spin_unlock(&inode->i_lock);
+	pnfs_put_layout_hdr(lo);
+	return ret;
+}
+
 bool pnfs_roc(struct inode *ino)
 {
 	struct pnfs_layout_hdr *lo;
@@ -1458,7 +1506,6 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data)
 	dprintk("pnfs write error = %d\n", hdr->pnfs_error);
 	if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
 	    PNFS_LAYOUTRET_ON_ERROR) {
-		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
 		pnfs_return_layout(hdr->inode);
 	}
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
@@ -1613,7 +1660,6 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
 	dprintk("pnfs read error = %d\n", hdr->pnfs_error);
 	if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
 	    PNFS_LAYOUTRET_ON_ERROR) {
-		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
 		pnfs_return_layout(hdr->inode);
 	}
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
@@ -1746,11 +1792,27 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 
 	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
 		if (lseg->pls_range.iomode == IOMODE_RW &&
-		    test_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+		    test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
 			list_add(&lseg->pls_lc_list, listp);
 	}
 }
 
+static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *listp)
+{
+	struct pnfs_layout_segment *lseg, *tmp;
+	unsigned long *bitlock = &NFS_I(inode)->flags;
+
+	/* Matched by references in pnfs_set_layoutcommit */
+	list_for_each_entry_safe(lseg, tmp, listp, pls_lc_list) {
+		list_del_init(&lseg->pls_lc_list);
+		pnfs_put_lseg(lseg);
+	}
+
+	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
+	smp_mb__after_clear_bit();
+	wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+}
+
 void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
 {
 	pnfs_layout_io_set_failed(lseg->pls_layout, lseg->pls_range.iomode);
@@ -1795,6 +1857,7 @@ void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
 
 	if (nfss->pnfs_curr_ld->cleanup_layoutcommit)
 		nfss->pnfs_curr_ld->cleanup_layoutcommit(data);
+	pnfs_list_write_lseg_done(data->args.inode, &data->lseg_list);
 }
 
 /*
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 94ba804..f5f8a47 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -219,6 +219,7 @@ void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
+int pnfs_commit_and_return_layout(struct inode *);
 void pnfs_ld_write_done(struct nfs_write_data *);
 void pnfs_ld_read_done(struct nfs_read_data *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
@@ -407,6 +408,11 @@ static inline int pnfs_return_layout(struct inode *ino)
 	return 0;
 }
 
+static inline int pnfs_commit_and_return_layout(struct inode *inode)
+{
+	return 0;
+}
+
 static inline bool
 pnfs_ld_layoutret_on_setattr(struct inode *inode)
 {
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 17b32b7..2f8a29d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -294,6 +294,7 @@ struct file_system_type nfs_fs_type = {
 	.kill_sb	= nfs_kill_super,
 	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
 };
+MODULE_ALIAS_FS("nfs");
 EXPORT_SYMBOL_GPL(nfs_fs_type);
 
 struct file_system_type nfs_xdev_fs_type = {
@@ -333,6 +334,8 @@ struct file_system_type nfs4_fs_type = {
 	.kill_sb	= nfs_kill_super,
 	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
 };
+MODULE_ALIAS_FS("nfs4");
+MODULE_ALIAS("nfs4");
 EXPORT_SYMBOL_GPL(nfs4_fs_type);
 
 static int __init register_nfs4_fs(void)
@@ -2717,6 +2720,5 @@ module_param(send_implementation_id, ushort, 0644);
 MODULE_PARM_DESC(send_implementation_id,
 		"Send implementation ID with NFSv4.1 exchange_id");
 MODULE_PARM_DESC(nfs4_unique_id, "nfs_client_id4 uniquifier string");
-MODULE_ALIAS("nfs4");
 
 #endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 16d39c6..417c848 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -230,42 +230,10 @@ static void nfs4_file_put_access(struct nfs4_file *fp, int oflag)
 		__nfs4_file_put_access(fp, oflag);
 }
 
-static inline int get_new_stid(struct nfs4_stid *stid)
-{
-	static int min_stateid = 0;
-	struct idr *stateids = &stid->sc_client->cl_stateids;
-	int new_stid;
-	int error;
-
-	error = idr_get_new_above(stateids, stid, min_stateid, &new_stid);
-	/*
-	 * Note: the necessary preallocation was done in
-	 * nfs4_alloc_stateid().  The idr code caps the number of
-	 * preallocations that can exist at a time, but the state lock
-	 * prevents anyone from using ours before we get here:
-	 */
-	WARN_ON_ONCE(error);
-	/*
-	 * It shouldn't be a problem to reuse an opaque stateid value.
-	 * I don't think it is for 4.1.  But with 4.0 I worry that, for
-	 * example, a stray write retransmission could be accepted by
-	 * the server when it should have been rejected.  Therefore,
-	 * adopt a trick from the sctp code to attempt to maximize the
-	 * amount of time until an id is reused, by ensuring they always
-	 * "increase" (mod INT_MAX):
-	 */
-
-	min_stateid = new_stid+1;
-	if (min_stateid == INT_MAX)
-		min_stateid = 0;
-	return new_stid;
-}
-
 static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct
 kmem_cache *slab)
 {
 	struct idr *stateids = &cl->cl_stateids;
-	static int min_stateid = 0;
 	struct nfs4_stid *stid;
 	int new_id;
 
@@ -273,9 +241,8 @@ kmem_cache *slab)
 	if (!stid)
 		return NULL;
 
-	if (!idr_pre_get(stateids, GFP_KERNEL))
-		goto out_free;
-	if (idr_get_new_above(stateids, stid, min_stateid, &new_id))
+	new_id = idr_alloc_cyclic(stateids, stid, 0, 0, GFP_KERNEL);
+	if (new_id < 0)
 		goto out_free;
 	stid->sc_client = cl;
 	stid->sc_type = 0;
@@ -293,10 +260,6 @@ kmem_cache *slab)
 	 * amount of time until an id is reused, by ensuring they always
 	 * "increase" (mod INT_MAX):
 	 */
-
-	min_stateid = new_id+1;
-	if (min_stateid == INT_MAX)
-		min_stateid = 0;
 	return stid;
 out_free:
 	kfree(stid);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0116886..a272007 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -264,7 +264,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		iattr->ia_valid |= ATTR_SIZE;
 	}
 	if (bmval[0] & FATTR4_WORD0_ACL) {
-		int nace;
+		u32 nace;
 		struct nfs4_ace *ace;
 
 		READ_BUF(4); len += 4;
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 62c1ee1..ca05f6d 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -102,7 +102,8 @@ nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
 {
 	if (rp->c_type == RC_REPLBUFF)
 		kfree(rp->c_replvec.iov_base);
-	hlist_del(&rp->c_hash);
+	if (!hlist_unhashed(&rp->c_hash))
+		hlist_del(&rp->c_hash);
 	list_del(&rp->c_lru);
 	--num_drc_entries;
 	kmem_cache_free(drc_slab, rp);
@@ -118,6 +119,10 @@ nfsd_reply_cache_free(struct svc_cacherep *rp)
 
 int nfsd_reply_cache_init(void)
 {
+	INIT_LIST_HEAD(&lru_head);
+	max_drc_entries = nfsd_cache_size_limit();
+	num_drc_entries = 0;
+
 	register_shrinker(&nfsd_reply_cache_shrinker);
 	drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep),
 					0, 0, NULL);
@@ -128,10 +133,6 @@ int nfsd_reply_cache_init(void)
 	if (!cache_hash)
 		goto out_nomem;
 
-	INIT_LIST_HEAD(&lru_head);
-	max_drc_entries = nfsd_cache_size_limit();
-	num_drc_entries = 0;
-
 	return 0;
 out_nomem:
 	printk(KERN_ERR "nfsd: failed to allocate reply cache\n");
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 13a21c8..f33455b 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1090,6 +1090,7 @@ static struct file_system_type nfsd_fs_type = {
 	.mount		= nfsd_mount,
 	.kill_sb	= nfsd_umount,
 };
+MODULE_ALIAS_FS("nfsd");
 
 #ifdef CONFIG_PROC_FS
 static int create_proc_exports_entry(void)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 2a7eb53..2b2e2396 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1013,6 +1013,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	int			host_err;
 	int			stable = *stablep;
 	int			use_wgather;
+	loff_t			pos = offset;
 
 	dentry = file->f_path.dentry;
 	inode = dentry->d_inode;
@@ -1025,7 +1026,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 
 	/* Write the data. */
 	oldfs = get_fs(); set_fs(KERNEL_DS);
-	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
+	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos);
 	set_fs(oldfs);
 	if (host_err < 0)
 		goto out_nfserr;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 3c991dc..c7d1f9f 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1361,6 +1361,7 @@ struct file_system_type nilfs_fs_type = {
 	.kill_sb  = kill_block_super,
 	.fs_flags = FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("nilfs2");
 
 static void nilfs_inode_init_once(void *obj)
 {
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index e0f7c12..8562bd3 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -359,7 +359,6 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns
 }
 
 static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock,
-			      int *last_wd,
 			      struct inotify_inode_mark *i_mark)
 {
 	int ret;
@@ -367,11 +366,10 @@ static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock,
 	idr_preload(GFP_KERNEL);
 	spin_lock(idr_lock);
 
-	ret = idr_alloc(idr, i_mark, *last_wd + 1, 0, GFP_NOWAIT);
+	ret = idr_alloc_cyclic(idr, i_mark, 1, 0, GFP_NOWAIT);
 	if (ret >= 0) {
 		/* we added the mark to the idr, take a reference */
 		i_mark->wd = ret;
-		*last_wd = i_mark->wd;
 		fsnotify_get_mark(&i_mark->fsn_mark);
 	}
 
@@ -638,8 +636,7 @@ static int inotify_new_watch(struct fsnotify_group *group,
 	if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
 		goto out_err;
 
-	ret = inotify_add_to_idr(idr, idr_lock, &group->inotify_data.last_wd,
-				 tmp_i_mark);
+	ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
 	if (ret)
 		goto out_err;
 
@@ -697,7 +694,6 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 
 	spin_lock_init(&group->inotify_data.idr_lock);
 	idr_init(&group->inotify_data.idr);
-	group->inotify_data.last_wd = 0;
 	group->inotify_data.user = get_current_user();
 
 	if (atomic_inc_return(&group->inotify_data.user->inotify_devs) >
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 4a8289f8..82650d5 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -3079,6 +3079,7 @@ static struct file_system_type ntfs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("ntfs");
 
 /* Stable names for the slab caches. */
 static const char ntfs_index_ctx_cache_name[] = "ntfs_index_ctx_cache";
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index eeac97b..b3fdd1a 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1498,10 +1498,8 @@ leave:
 
 	dlm_put(dlm);
 	if (ret < 0) {
-		if (buf)
-			kfree(buf);
-		if (item)
-			kfree(item);
+		kfree(buf);
+		kfree(item);
 		mlog_errno(ret);
 	}
 
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 4c5fc8d..12bafb7 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -640,6 +640,7 @@ static struct file_system_type dlmfs_fs_type = {
 	.mount		= dlmfs_mount,
 	.kill_sb	= kill_litter_super,
 };
+MODULE_ALIAS_FS("ocfs2_dlmfs");
 
 static int __init init_dlmfs_fs(void)
 {
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 752f0b2..0c60ef2 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -101,13 +101,6 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 	if (!S_ISDIR(inode->i_mode))
 		flags &= ~OCFS2_DIRSYNC_FL;
 
-	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
-	if (IS_ERR(handle)) {
-		status = PTR_ERR(handle);
-		mlog_errno(status);
-		goto bail_unlock;
-	}
-
 	oldflags = ocfs2_inode->ip_attr;
 	flags = flags & mask;
 	flags |= oldflags & ~mask;
@@ -120,7 +113,14 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 	if ((oldflags & OCFS2_IMMUTABLE_FL) || ((flags ^ oldflags) &
 		(OCFS2_APPEND_FL | OCFS2_IMMUTABLE_FL))) {
 		if (!capable(CAP_LINUX_IMMUTABLE))
-			goto bail_commit;
+			goto bail_unlock;
+	}
+
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		mlog_errno(status);
+		goto bail_unlock;
 	}
 
 	ocfs2_inode->ip_attr = flags;
@@ -130,8 +130,8 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 	if (status < 0)
 		mlog_errno(status);
 
-bail_commit:
 	ocfs2_commit_trans(osb, handle);
+
 bail_unlock:
 	ocfs2_inode_unlock(inode, 1);
 bail:
@@ -706,8 +706,10 @@ int ocfs2_info_handle_freefrag(struct inode *inode,
 
 	o2info_set_request_filled(&oiff->iff_req);
 
-	if (o2info_to_user(*oiff, req))
+	if (o2info_to_user(*oiff, req)) {
+		status = -EFAULT;
 		goto bail;
+	}
 
 	status = 0;
 bail:
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 9f8dcad..f1fc172 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -471,7 +471,7 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
 	int ret, goal_bit = 0;
 
 	struct buffer_head *gd_bh = NULL;
-	struct ocfs2_group_desc *bg = NULL;
+	struct ocfs2_group_desc *bg;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int c_to_b = 1 << (osb->s_clustersize_bits -
 					inode->i_sb->s_blocksize_bits);
@@ -482,13 +482,6 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
 	range->me_goal = ocfs2_block_to_cluster_start(inode->i_sb,
 						      range->me_goal);
 	/*
-	 * moving goal is not allowd to start with a group desc blok(#0 blk)
-	 * let's compromise to the latter cluster.
-	 */
-	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
-		range->me_goal += c_to_b;
-
-	/*
 	 * validate goal sits within global_bitmap, and return the victim
 	 * group desc
 	 */
@@ -502,6 +495,13 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
 	bg = (struct ocfs2_group_desc *)gd_bh->b_data;
 
 	/*
+	 * moving goal is not allowd to start with a group desc blok(#0 blk)
+	 * let's compromise to the latter cluster.
+	 */
+	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
+		range->me_goal += c_to_b;
+
+	/*
 	 * movement is not gonna cross two groups.
 	 */
 	if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
@@ -1057,42 +1057,40 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp)
 
 	struct inode *inode = file_inode(filp);
 	struct ocfs2_move_extents range;
-	struct ocfs2_move_extents_context *context = NULL;
+	struct ocfs2_move_extents_context *context;
+
+	if (!argp)
+		return -EINVAL;
 
 	status = mnt_want_write_file(filp);
 	if (status)
 		return status;
 
 	if ((!S_ISREG(inode->i_mode)) || !(filp->f_mode & FMODE_WRITE))
-		goto out;
+		goto out_drop;
 
 	if (inode->i_flags & (S_IMMUTABLE|S_APPEND)) {
 		status = -EPERM;
-		goto out;
+		goto out_drop;
 	}
 
 	context = kzalloc(sizeof(struct ocfs2_move_extents_context), GFP_NOFS);
 	if (!context) {
 		status = -ENOMEM;
 		mlog_errno(status);
-		goto out;
+		goto out_drop;
 	}
 
 	context->inode = inode;
 	context->file = filp;
 
-	if (argp) {
-		if (copy_from_user(&range, argp, sizeof(range))) {
-			status = -EFAULT;
-			goto out;
-		}
-	} else {
-		status = -EINVAL;
-		goto out;
+	if (copy_from_user(&range, argp, sizeof(range))) {
+		status = -EFAULT;
+		goto out_free;
 	}
 
 	if (range.me_start > i_size_read(inode))
-		goto out;
+		goto out_free;
 
 	if (range.me_start + range.me_len > i_size_read(inode))
 			range.me_len = i_size_read(inode) - range.me_start;
@@ -1124,25 +1122,24 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp)
 
 		status = ocfs2_validate_and_adjust_move_goal(inode, &range);
 		if (status)
-			goto out;
+			goto out_copy;
 	}
 
 	status = ocfs2_move_extents(context);
 	if (status)
 		mlog_errno(status);
-out:
+out_copy:
 	/*
 	 * movement/defragmentation may end up being partially completed,
 	 * that's the reason why we need to return userspace the finished
 	 * length and new_offset even if failure happens somewhere.
 	 */
-	if (argp) {
-		if (copy_to_user(argp, &range, sizeof(range)))
-			status = -EFAULT;
-	}
+	if (copy_to_user(argp, &range, sizeof(range)))
+		status = -EFAULT;
 
+out_free:
 	kfree(context);
-
+out_drop:
 	mnt_drop_write_file(filp);
 
 	return status;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 9b6910d..01b8516 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1266,6 +1266,7 @@ static struct file_system_type ocfs2_fs_type = {
 	.fs_flags       = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
 	.next           = NULL
 };
+MODULE_ALIAS_FS("ocfs2");
 
 static int ocfs2_check_set_options(struct super_block *sb,
 				   struct mount_options *options)
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index 25d715c..d8b0afd 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -572,6 +572,7 @@ static struct file_system_type omfs_fs_type = {
 	.kill_sb = kill_block_super,
 	.fs_flags = FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("omfs");
 
 static int __init init_omfs_fs(void)
 {
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index ae47fa7..75885ff 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -432,6 +432,7 @@ static struct file_system_type openprom_fs_type = {
 	.mount		= openprom_mount,
 	.kill_sb	= kill_anon_super,
 };
+MODULE_ALIAS_FS("openpromfs");
 
 static void op_inode_init_once(void *data)
 {
diff --git a/fs/pipe.c b/fs/pipe.c
index 64a494c..2234f3f 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -863,6 +863,9 @@ pipe_rdwr_open(struct inode *inode, struct file *filp)
 {
 	int ret = -ENOENT;
 
+	if (!(filp->f_mode & (FMODE_READ|FMODE_WRITE)))
+		return -EINVAL;
+
 	mutex_lock(&inode->i_mutex);
 
 	if (inode->i_pipe) {
diff --git a/fs/pnode.c b/fs/pnode.c
index 3e000a5..8b29d21 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -9,6 +9,7 @@
 #include <linux/mnt_namespace.h>
 #include <linux/mount.h>
 #include <linux/fs.h>
+#include <linux/nsproxy.h>
 #include "internal.h"
 #include "pnode.h"
 
@@ -220,6 +221,7 @@ static struct mount *get_source(struct mount *dest,
 int propagate_mnt(struct mount *dest_mnt, struct dentry *dest_dentry,
 		    struct mount *source_mnt, struct list_head *tree_list)
 {
+	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
 	struct mount *m, *child;
 	int ret = 0;
 	struct mount *prev_dest_mnt = dest_mnt;
@@ -237,6 +239,10 @@ int propagate_mnt(struct mount *dest_mnt, struct dentry *dest_dentry,
 
 		source =  get_source(m, prev_dest_mnt, prev_src_mnt, &type);
 
+		/* Notice when we are propagating across user namespaces */
+		if (m->mnt_ns->user_ns != user_ns)
+			type |= CL_UNPRIVILEGED;
+
 		child = copy_tree(source, source->mnt.mnt_root, type);
 		if (IS_ERR(child)) {
 			ret = PTR_ERR(child);
diff --git a/fs/pnode.h b/fs/pnode.h
index 19b853a3..a0493d5 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -23,6 +23,7 @@
 #define CL_MAKE_SHARED 		0x08
 #define CL_PRIVATE 		0x10
 #define CL_SHARED_TO_SLAVE	0x20
+#define CL_UNPRIVILEGED		0x40
 
 static inline void set_mnt_shared(struct mount *mnt)
 {
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 712f24d..ab30716 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -5,7 +5,7 @@
 obj-y   += proc.o
 
 proc-y			:= nommu.o task_nommu.o
-proc-$(CONFIG_MMU)	:= mmu.o task_mmu.o
+proc-$(CONFIG_MMU)	:= task_mmu.o
 
 proc-y       += inode.o root.o base.o generic.o array.o \
 		fd.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index f7ed9ee..cbd0f1b 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -143,6 +143,7 @@ static const char * const task_state_array[] = {
 	"x (dead)",		/*  64 */
 	"K (wakekill)",		/* 128 */
 	"W (waking)",		/* 256 */
+	"P (parked)",		/* 512 */
 };
 
 static inline const char *get_task_state(struct task_struct *tsk)
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 4b3b3ff..21e1a8f 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -755,37 +755,8 @@ void pde_put(struct proc_dir_entry *pde)
 		free_proc_entry(pde);
 }
 
-/*
- * Remove a /proc entry and free it if it's not currently in use.
- */
-void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+static void entry_rundown(struct proc_dir_entry *de)
 {
-	struct proc_dir_entry **p;
-	struct proc_dir_entry *de = NULL;
-	const char *fn = name;
-	unsigned int len;
-
-	spin_lock(&proc_subdir_lock);
-	if (__xlate_proc_name(name, &parent, &fn) != 0) {
-		spin_unlock(&proc_subdir_lock);
-		return;
-	}
-	len = strlen(fn);
-
-	for (p = &parent->subdir; *p; p=&(*p)->next ) {
-		if (proc_match(len, fn, *p)) {
-			de = *p;
-			*p = de->next;
-			de->next = NULL;
-			break;
-		}
-	}
-	spin_unlock(&proc_subdir_lock);
-	if (!de) {
-		WARN(1, "name '%s'\n", name);
-		return;
-	}
-
 	spin_lock(&de->pde_unload_lock);
 	/*
 	 * Stop accepting new callers into module. If you're
@@ -817,6 +788,40 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 		spin_lock(&de->pde_unload_lock);
 	}
 	spin_unlock(&de->pde_unload_lock);
+}
+
+/*
+ * Remove a /proc entry and free it if it's not currently in use.
+ */
+void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry **p;
+	struct proc_dir_entry *de = NULL;
+	const char *fn = name;
+	unsigned int len;
+
+	spin_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		spin_unlock(&proc_subdir_lock);
+		return;
+	}
+	len = strlen(fn);
+
+	for (p = &parent->subdir; *p; p=&(*p)->next ) {
+		if (proc_match(len, fn, *p)) {
+			de = *p;
+			*p = de->next;
+			de->next = NULL;
+			break;
+		}
+	}
+	spin_unlock(&proc_subdir_lock);
+	if (!de) {
+		WARN(1, "name '%s'\n", name);
+		return;
+	}
+
+	entry_rundown(de);
 
 	if (S_ISDIR(de->mode))
 		parent->nlink--;
@@ -827,3 +832,57 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 	pde_put(de);
 }
 EXPORT_SYMBOL(remove_proc_entry);
+
+int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry **p;
+	struct proc_dir_entry *root = NULL, *de, *next;
+	const char *fn = name;
+	unsigned int len;
+
+	spin_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		spin_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	len = strlen(fn);
+
+	for (p = &parent->subdir; *p; p=&(*p)->next ) {
+		if (proc_match(len, fn, *p)) {
+			root = *p;
+			*p = root->next;
+			root->next = NULL;
+			break;
+		}
+	}
+	if (!root) {
+		spin_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	de = root;
+	while (1) {
+		next = de->subdir;
+		if (next) {
+			de->subdir = next->next;
+			next->next = NULL;
+			de = next;
+			continue;
+		}
+		spin_unlock(&proc_subdir_lock);
+
+		entry_rundown(de);
+		next = de->parent;
+		if (S_ISDIR(de->mode))
+			next->nlink--;
+		de->nlink = 0;
+		if (de == root)
+			break;
+		pde_put(de);
+
+		spin_lock(&proc_subdir_lock);
+		de = next;
+	}
+	pde_put(root);
+	return 0;
+}
+EXPORT_SYMBOL(remove_proc_subtree);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index a86aebc..869116c 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -446,9 +446,10 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
 
 struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
-	struct inode *inode = iget_locked(sb, de->low_ino);
+	struct inode *inode = new_inode_pseudo(sb);
 
-	if (inode && (inode->i_state & I_NEW)) {
+	if (inode) {
+		inode->i_ino = de->low_ino;
 		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 		PROC_I(inode)->pde = de;
 
@@ -476,7 +477,6 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 				inode->i_fop = de->proc_fops;
 			}
 		}
-		unlock_new_inode(inode);
 	} else
 	       pde_put(de);
 	return inode;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 85ff3a4..7571035 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -30,24 +30,6 @@ extern int proc_net_init(void);
 static inline int proc_net_init(void) { return 0; }
 #endif
 
-struct vmalloc_info {
-	unsigned long	used;
-	unsigned long	largest_chunk;
-};
-
-#ifdef CONFIG_MMU
-#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
-extern void get_vmalloc_info(struct vmalloc_info *vmi);
-#else
-
-#define VMALLOC_TOTAL 0UL
-#define get_vmalloc_info(vmi)			\
-do {						\
-	(vmi)->used = 0;			\
-	(vmi)->largest_chunk = 0;		\
-} while(0)
-#endif
-
 extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task);
 extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index eda6f01..f6a13f4 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -15,6 +15,7 @@
 #include <linux/capability.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
+#include <linux/notifier.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/printk.h>
@@ -564,7 +565,6 @@ static const struct file_operations proc_kcore_operations = {
 	.llseek		= default_llseek,
 };
 
-#ifdef CONFIG_MEMORY_HOTPLUG
 /* just remember that we have to update kcore */
 static int __meminit kcore_callback(struct notifier_block *self,
 				    unsigned long action, void *arg)
@@ -578,8 +578,11 @@ static int __meminit kcore_callback(struct notifier_block *self,
 	}
 	return NOTIFY_OK;
 }
-#endif
 
+static struct notifier_block kcore_callback_nb __meminitdata = {
+	.notifier_call = kcore_callback,
+	.priority = 0,
+};
 
 static struct kcore_list kcore_vmalloc;
 
@@ -631,7 +634,7 @@ static int __init proc_kcore_init(void)
 	add_modules_range();
 	/* Store direct-map area from physical memory map */
 	kcore_update_ram();
-	hotplug_memory_notifier(kcore_callback, 0);
+	register_hotmemory_notifier(&kcore_callback_nb);
 
 	return 0;
 }
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 1efaaa1..5aa847a 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -11,6 +11,7 @@
 #include <linux/swap.h>
 #include <linux/vmstat.h>
 #include <linux/atomic.h>
+#include <linux/vmalloc.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include "internal.h"
diff --git a/fs/proc/mmu.c b/fs/proc/mmu.c
deleted file mode 100644
index 8ae221d..0000000
--- a/fs/proc/mmu.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/* mmu.c: mmu memory info files
- *
- * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * 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.
- */
-#include <linux/spinlock.h>
-#include <linux/vmalloc.h>
-#include <linux/highmem.h>
-#include <asm/pgtable.h>
-#include "internal.h"
-
-void get_vmalloc_info(struct vmalloc_info *vmi)
-{
-	struct vm_struct *vma;
-	unsigned long free_area_size;
-	unsigned long prev_end;
-
-	vmi->used = 0;
-
-	if (!vmlist) {
-		vmi->largest_chunk = VMALLOC_TOTAL;
-	}
-	else {
-		vmi->largest_chunk = 0;
-
-		prev_end = VMALLOC_START;
-
-		read_lock(&vmlist_lock);
-
-		for (vma = vmlist; vma; vma = vma->next) {
-			unsigned long addr = (unsigned long) vma->addr;
-
-			/*
-			 * Some archs keep another range for modules in vmlist
-			 */
-			if (addr < VMALLOC_START)
-				continue;
-			if (addr >= VMALLOC_END)
-				break;
-
-			vmi->used += vma->size;
-
-			free_area_size = addr - prev_end;
-			if (vmi->largest_chunk < free_area_size)
-				vmi->largest_chunk = free_area_size;
-
-			prev_end = vma->size + addr;
-		}
-
-		if (VMALLOC_END - prev_end > vmi->largest_chunk)
-			vmi->largest_chunk = VMALLOC_END - prev_end;
-
-		read_unlock(&vmlist_lock);
-	}
-}
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index b7a4719..66b51c0 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -118,7 +118,7 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
 	struct super_block *sb = inode->i_sb;
 	struct proc_inode *ei = PROC_I(inode);
 	struct task_struct *task;
-	struct dentry *ns_dentry;
+	struct path ns_path;
 	void *error = ERR_PTR(-EACCES);
 
 	task = get_proc_task(inode);
@@ -128,14 +128,14 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto out_put_task;
 
-	ns_dentry = proc_ns_get_dentry(sb, task, ei->ns_ops);
-	if (IS_ERR(ns_dentry)) {
-		error = ERR_CAST(ns_dentry);
+	ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns_ops);
+	if (IS_ERR(ns_path.dentry)) {
+		error = ERR_CAST(ns_path.dentry);
 		goto out_put_task;
 	}
 
-	dput(nd->path.dentry);
-	nd->path.dentry = ns_dentry;
+	ns_path.mnt = mntget(nd->path.mnt);
+	nd_jump_link(nd, &ns_path);
 	error = NULL;
 
 out_put_task:
diff --git a/fs/proc/root.c b/fs/proc/root.c
index c6e9fac..9c7fab1 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
+#include <linux/user_namespace.h>
 #include <linux/mount.h>
 #include <linux/pid_namespace.h>
 #include <linux/parser.h>
@@ -108,6 +109,9 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 	} else {
 		ns = task_active_pid_ns(current);
 		options = data;
+
+		if (!current_user_ns()->may_mount_proc)
+			return ERR_PTR(-EPERM);
 	}
 
 	sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 43098bb..2e8caa6 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -412,6 +412,7 @@ static struct file_system_type qnx4_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("qnx4");
 
 static int __init init_qnx4_fs(void)
 {
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 57199a5..8d941ed 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -672,6 +672,7 @@ static struct file_system_type qnx6_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("qnx6");
 
 static int __init init_qnx6_fs(void)
 {
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 05ae3c9..3e64169 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1439,8 +1439,11 @@ static void __dquot_initialize(struct inode *inode, int type)
 			 * did a write before quota was turned on
 			 */
 			rsv = inode_get_rsv_space(inode);
-			if (unlikely(rsv))
+			if (unlikely(rsv)) {
+				spin_lock(&dq_data_lock);
 				dquot_resv_space(inode->i_dquot[cnt], rsv);
+				spin_unlock(&dq_data_lock);
+			}
 		}
 	}
 out_err:
diff --git a/fs/read_write.c b/fs/read_write.c
index a698eff..7a64891 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -17,6 +17,7 @@
 #include <linux/splice.h>
 #include <linux/compat.h>
 #include "read_write.h"
+#include "internal.h"
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -127,7 +128,7 @@ EXPORT_SYMBOL(generic_file_llseek_size);
  *
  * This is a generic implemenation of ->llseek useable for all normal local
  * filesystems.  It just updates the file offset to the value specified by
- * @offset and @whence under i_mutex.
+ * @offset and @whence.
  */
 loff_t generic_file_llseek(struct file *file, loff_t offset, int whence)
 {
@@ -417,6 +418,33 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof
 
 EXPORT_SYMBOL(do_sync_write);
 
+ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos)
+{
+	mm_segment_t old_fs;
+	const char __user *p;
+	ssize_t ret;
+
+	if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
+		return -EINVAL;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	p = (__force const char __user *)buf;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	if (file->f_op->write)
+		ret = file->f_op->write(file, p, count, pos);
+	else
+		ret = do_sync_write(file, p, count, pos);
+	set_fs(old_fs);
+	if (ret > 0) {
+		fsnotify_modify(file);
+		add_wchar(current, ret);
+	}
+	inc_syscw(current);
+	return ret;
+}
+
 ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
 {
 	ssize_t ret;
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 418bdc3..f8a23c3 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1147,8 +1147,7 @@ static int reiserfs_parse_options(struct super_block *s, char *options,	/* strin
 							 "on filesystem root.");
 					return 0;
 				}
-				qf_names[qtype] =
-				    kmalloc(strlen(arg) + 1, GFP_KERNEL);
+				qf_names[qtype] = kstrdup(arg, GFP_KERNEL);
 				if (!qf_names[qtype]) {
 					reiserfs_warning(s, "reiserfs-2502",
 							 "not enough memory "
@@ -1156,7 +1155,6 @@ static int reiserfs_parse_options(struct super_block *s, char *options,	/* strin
 							 "quotafile name.");
 					return 0;
 				}
-				strcpy(qf_names[qtype], arg);
 				if (qtype == USRQUOTA)
 					*mount_options |= 1 << REISERFS_USRQUOTA;
 				else
@@ -2434,6 +2432,7 @@ struct file_system_type reiserfs_fs_type = {
 	.kill_sb = reiserfs_kill_sb,
 	.fs_flags = FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("reiserfs");
 
 MODULE_DESCRIPTION("ReiserFS journaled filesystem");
 MODULE_AUTHOR("Hans Reiser <reiser@namesys.com>");
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index c196369..4cce1d9 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -187,8 +187,8 @@ fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset,
 	if (dbuf->count == ARRAY_SIZE(dbuf->dentries))
 		return -ENOSPC;
 
-	if (name[0] == '.' && (name[1] == '\0' ||
-			       (name[1] == '.' && name[2] == '\0')))
+	if (name[0] == '.' && (namelen < 2 ||
+			       (namelen == 2 && name[1] == '.')))
 		return 0;
 
 	dentry = lookup_one_len(name, dbuf->xadir, namelen);
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 7e8d3a8..15cbc41e 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -599,6 +599,7 @@ static struct file_system_type romfs_fs_type = {
 	.kill_sb	= romfs_kill_sb,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("romfs");
 
 /*
  * inode storage initialiser
diff --git a/fs/splice.c b/fs/splice.c
index 718bd00..29e394e 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -31,6 +31,7 @@
 #include <linux/security.h>
 #include <linux/gfp.h>
 #include <linux/socket.h>
+#include "internal.h"
 
 /*
  * Attempt to steal a page from a pipe buffer. This should perhaps go into
@@ -1048,9 +1049,10 @@ static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 {
 	int ret;
 	void *data;
+	loff_t tmp = sd->pos;
 
 	data = buf->ops->map(pipe, buf, 0);
-	ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
+	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
 	buf->ops->unmap(pipe, buf, data);
 
 	return ret;
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 260e392..60553a9 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -489,6 +489,7 @@ static struct file_system_type squashfs_fs_type = {
 	.kill_sb = kill_block_super,
 	.fs_flags = FS_REQUIRES_DEV
 };
+MODULE_ALIAS_FS("squashfs");
 
 static const struct super_operations squashfs_super_ops = {
 	.alloc_inode = squashfs_alloc_inode,
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 2fbdff6..e8e0e71 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -165,21 +165,8 @@ struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
 	if (unlikely(!sd))
 		return NULL;
 
-	while (1) {
-		int v, t;
-
-		v = atomic_read(&sd->s_active);
-		if (unlikely(v < 0))
-			return NULL;
-
-		t = atomic_cmpxchg(&sd->s_active, v, v + 1);
-		if (likely(t == v))
-			break;
-		if (t < 0)
-			return NULL;
-
-		cpu_relax();
-	}
+	if (!atomic_inc_unless_negative(&sd->s_active))
+		return NULL;
 
 	if (likely(!ignore_lockdep(sd)))
 		rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_);
@@ -281,6 +268,10 @@ void release_sysfs_dirent(struct sysfs_dirent * sd)
 	 */
 	parent_sd = sd->s_parent;
 
+	WARN(!(sd->s_flags & SYSFS_FLAG_REMOVED),
+		"sysfs: free using entry: %s/%s\n",
+		parent_sd ? parent_sd->s_name : "", sd->s_name);
+
 	if (sysfs_type(sd) == SYSFS_KOBJ_LINK)
 		sysfs_put(sd->s_symlink.target_sd);
 	if (sysfs_type(sd) & SYSFS_COPY_NAME)
@@ -399,7 +390,7 @@ struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
 
 	sd->s_name = name;
 	sd->s_mode = mode;
-	sd->s_flags = type;
+	sd->s_flags = type | SYSFS_FLAG_REMOVED;
 
 	return sd;
 
@@ -479,6 +470,9 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 		ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
 	}
 
+	/* Mark the entry added into directory tree */
+	sd->s_flags &= ~SYSFS_FLAG_REMOVED;
+
 	return 0;
 }
 
@@ -1012,6 +1006,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	enum kobj_ns_type type;
 	const void *ns;
 	ino_t ino;
+	loff_t off;
 
 	type = sysfs_ns_type(parent_sd);
 	ns = sysfs_info(dentry->d_sb)->ns[type];
@@ -1020,6 +1015,8 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 		ino = parent_sd->s_ino;
 		if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
+		else
+			return 0;
 	}
 	if (filp->f_pos == 1) {
 		if (parent_sd->s_parent)
@@ -1028,8 +1025,11 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 			ino = parent_sd->s_ino;
 		if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
+		else
+			return 0;
 	}
 	mutex_lock(&sysfs_mutex);
+	off = filp->f_pos;
 	for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos);
 	     pos;
 	     pos = sysfs_dir_next_pos(ns, parent_sd, filp->f_pos, pos)) {
@@ -1041,27 +1041,43 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 		len = strlen(name);
 		ino = pos->s_ino;
 		type = dt_type(pos);
-		filp->f_pos = pos->s_hash;
+		off = filp->f_pos = pos->s_hash;
 		filp->private_data = sysfs_get(pos);
 
 		mutex_unlock(&sysfs_mutex);
-		ret = filldir(dirent, name, len, filp->f_pos, ino, type);
+		ret = filldir(dirent, name, len, off, ino, type);
 		mutex_lock(&sysfs_mutex);
 		if (ret < 0)
 			break;
 	}
 	mutex_unlock(&sysfs_mutex);
-	if ((filp->f_pos > 1) && !pos) { /* EOF */
-		filp->f_pos = INT_MAX;
+
+	/* don't reference last entry if its refcount is dropped */
+	if (!pos) {
 		filp->private_data = NULL;
+
+		/* EOF and not changed as 0 or 1 in read/write path */
+		if (off == filp->f_pos && off > 1)
+			filp->f_pos = INT_MAX;
 	}
 	return 0;
 }
 
+static loff_t sysfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file_inode(file);
+	loff_t ret;
+
+	mutex_lock(&inode->i_mutex);
+	ret = generic_file_llseek(file, offset, whence);
+	mutex_unlock(&inode->i_mutex);
+
+	return ret;
+}
 
 const struct file_operations sysfs_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= sysfs_readdir,
 	.release	= sysfs_dir_release,
-	.llseek		= generic_file_llseek,
+	.llseek		= sysfs_dir_llseek,
 };
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 8d924b5..afd8327 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
+#include <linux/user_namespace.h>
 
 #include "sysfs.h"
 
@@ -111,6 +112,9 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	struct super_block *sb;
 	int error;
 
+	if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs)
+		return ERR_PTR(-EPERM);
+
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return ERR_PTR(-ENOMEM);
diff --git a/fs/sysv/super.c b/fs/sysv/super.c
index a38e87b..d0c6a00 100644
--- a/fs/sysv/super.c
+++ b/fs/sysv/super.c
@@ -545,6 +545,7 @@ static struct file_system_type sysv_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("sysv");
 
 static struct file_system_type v7_fs_type = {
 	.owner		= THIS_MODULE,
@@ -553,6 +554,8 @@ static struct file_system_type v7_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("v7");
+MODULE_ALIAS("v7");
 
 static int __init init_sysv_fs(void)
 {
@@ -586,5 +589,4 @@ static void __exit exit_sysv_fs(void)
 
 module_init(init_sysv_fs)
 module_exit(exit_sysv_fs)
-MODULE_ALIAS("v7");
 MODULE_LICENSE("GPL");
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index ddc0f6a..f21acf0 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1568,6 +1568,12 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 	c->remounting_rw = 1;
 	c->ro_mount = 0;
 
+	if (c->space_fixup) {
+		err = ubifs_fixup_free_space(c);
+		if (err)
+			return err;
+	}
+
 	err = check_free_space(c);
 	if (err)
 		goto out;
@@ -1684,12 +1690,6 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 		err = dbg_check_space_info(c);
 	}
 
-	if (c->space_fixup) {
-		err = ubifs_fixup_free_space(c);
-		if (err)
-			goto out;
-	}
-
 	mutex_unlock(&c->umount_mutex);
 	return err;
 
@@ -2174,6 +2174,7 @@ static struct file_system_type ubifs_fs_type = {
 	.mount   = ubifs_mount,
 	.kill_sb = kill_ubifs_super,
 };
+MODULE_ALIAS_FS("ubifs");
 
 /*
  * Inode slab cache constructor.
diff --git a/fs/udf/super.c b/fs/udf/super.c
index bc5b30a..9ac4057 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -118,6 +118,7 @@ static struct file_system_type udf_fstype = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("udf");
 
 static struct kmem_cache *udf_inode_cachep;
 
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index dc8e3a8..329f2f5 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1500,6 +1500,7 @@ static struct file_system_type ufs_fs_type = {
 	.kill_sb	= kill_block_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("ufs");
 
 static int __init init_ufs_fs(void)
 {
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 4e8f0df..8459b5d 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1334,6 +1334,12 @@ _xfs_buf_ioapply(
 	int		size;
 	int		i;
 
+	/*
+	 * Make sure we capture only current IO errors rather than stale errors
+	 * left over from previous use of the buffer (e.g. failed readahead).
+	 */
+	bp->b_error = 0;
+
 	if (bp->b_flags & XBF_WRITE) {
 		if (bp->b_flags & XBF_SYNCIO)
 			rw = WRITE_SYNC;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 912d83d..5a30dd8 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -325,7 +325,7 @@ xfs_iomap_eof_want_preallocate(
  * rather than falling short due to things like stripe unit/width alignment of
  * real extents.
  */
-STATIC int
+STATIC xfs_fsblock_t
 xfs_iomap_eof_prealloc_initial_size(
 	struct xfs_mount	*mp,
 	struct xfs_inode	*ip,
@@ -413,7 +413,7 @@ xfs_iomap_prealloc_size(
 		 * have a large file on a small filesystem and the above
 		 * lowspace thresholds are smaller than MAXEXTLEN.
 		 */
-		while (alloc_blocks >= freesp)
+		while (alloc_blocks && alloc_blocks >= freesp)
 			alloc_blocks >>= 4;
 	}
 
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index c407121..ea341ce 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1561,6 +1561,7 @@ static struct file_system_type xfs_fs_type = {
 	.kill_sb		= kill_block_super,
 	.fs_flags		= FS_REQUIRES_DEV,
 };
+MODULE_ALIAS_FS("xfs");
 
 STATIC int __init
 xfs_init_zones(void)
author	Frederic Weisbecker <fweisbec@gmail.com>	2013-05-02 17:37:49 +0200
committer	Frederic Weisbecker <fweisbec@gmail.com>	2013-05-02 17:54:19 +0200
commit	c032862fba51a3ca504752d3a25186b324c5ce83 (patch)
tree	955dc2ba4ab3df76ecc2bb780ee84aca04967e8d /fs
parent	fda76e074c7737fc57855dd17c762e50ed526052 (diff)
parent	8700c95adb033843fc163d112b9d21d4fda78018 (diff)
download	op-kernel-dev-c032862fba51a3ca504752d3a25186b324c5ce83.zip op-kernel-dev-c032862fba51a3ca504752d3a25186b324c5ce83.tar.gz