Merge 3.8-rc5 into staging-next

This resolves a merge issue with a iio driver, and the zram code.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

72 files changed, 875 insertions, 571 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index cfe512fd1caf..780725a463b1 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -68,16 +68,6 @@ source "fs/quota/Kconfig"
 source "fs/autofs4/Kconfig"
 source "fs/fuse/Kconfig"
 
-config CUSE
-	tristate "Character device in Userspace support"
-	depends on FUSE_FS
-	help
-	  This FUSE extension allows character devices to be
-	  implemented in userspace.
-
-	  If you want to develop or use userspace character device
-	  based on CUSE, answer Y or M.
-
 config GENERIC_ACL
 	bool
 	select FS_POSIX_ACL
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 521e9d4424f6..a8b8adc05070 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3997,7 +3997,7 @@ again:
 	 * We make the other tasks wait for the flush only when we can flush
 	 * all things.
 	 */
-	if (ret && flush == BTRFS_RESERVE_FLUSH_ALL) {
+	if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
 		flushing = true;
 		space_info->flush = 1;
 	}
@@ -5560,7 +5560,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 	int empty_cluster = 2 * 1024 * 1024;
 	struct btrfs_space_info *space_info;
 	int loop = 0;
-	int index = 0;
+	int index = __get_raid_index(data);
 	int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
 		RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC;
 	bool found_uncached_bg = false;
@@ -6788,11 +6788,13 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 						       &wc->flags[level]);
 			if (ret < 0) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
+				path->locks[level] = 0;
 				return ret;
 			}
 			BUG_ON(wc->refs[level] == 0);
 			if (wc->refs[level] == 1) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
+				path->locks[level] = 0;
 				return 1;
 			}
 		}
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index f169d6b11d7f..2e8cae63d247 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -171,6 +171,10 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 	if (test_bit(EXTENT_FLAG_COMPRESSED, &prev->flags))
 		return 0;
 
+	if (test_bit(EXTENT_FLAG_LOGGING, &prev->flags) ||
+	    test_bit(EXTENT_FLAG_LOGGING, &next->flags))
+		return 0;
+
 	if (extent_map_end(prev) == next->start &&
 	    prev->flags == next->flags &&
 	    prev->bdev == next->bdev &&
@@ -255,7 +259,8 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
 	if (!em)
 		goto out;
 
-	list_move(&em->list, &tree->modified_extents);
+	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+		list_move(&em->list, &tree->modified_extents);
 	em->generation = gen;
 	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 	em->mod_start = em->start;
@@ -280,6 +285,12 @@ out:
 
 }
 
+void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
+{
+	clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+	try_merge_map(tree, em);
+}
+
 /**
  * add_extent_mapping - add new extent map to the extent tree
  * @tree:	tree to insert new map in
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 922943ce29e8..c6598c89cff8 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -69,6 +69,7 @@ void free_extent_map(struct extent_map *em);
 int __init extent_map_init(void);
 void extent_map_exit(void);
 int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, u64 gen);
+void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em);
 struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len);
 #endif
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index bd38cef42358..94aa53b38721 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -460,8 +460,8 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		if (!contig)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
 
-		if (!contig && (offset >= ordered->file_offset + ordered->len ||
-		    offset < ordered->file_offset)) {
+		if (offset >= ordered->file_offset + ordered->len ||
+		    offset < ordered->file_offset) {
 			unsigned long bytes_left;
 			sums->len = this_sum_bytes;
 			this_sum_bytes = 0;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 77061bf43edb..f76b1fd160d4 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2241,6 +2241,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 	if (lockend <= lockstart)
 		lockend = lockstart + root->sectorsize;
 
+	lockend--;
 	len = lockend - lockstart + 1;
 
 	len = max_t(u64, len, root->sectorsize);
@@ -2307,9 +2308,12 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 					}
 				}
 
-				*offset = start;
-				free_extent_map(em);
-				break;
+				if (!test_bit(EXTENT_FLAG_PREALLOC,
+					      &em->flags)) {
+					*offset = start;
+					free_extent_map(em);
+					break;
+				}
 			}
 		}
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 59ea2e4349c9..0be7a8742a43 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1862,11 +1862,13 @@ int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *info;
-	int ret = 0;
+	int ret;
+	bool re_search = false;
 
 	spin_lock(&ctl->tree_lock);
 
 again:
+	ret = 0;
 	if (!bytes)
 		goto out_lock;
 
@@ -1879,17 +1881,17 @@ again:
 		info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
 					  1, 0);
 		if (!info) {
-			/* the tree logging code might be calling us before we
-			 * have fully loaded the free space rbtree for this
-			 * block group.  So it is possible the entry won't
-			 * be in the rbtree yet at all.  The caching code
-			 * will make sure not to put it in the rbtree if
-			 * the logging code has pinned it.
+			/*
+			 * If we found a partial bit of our free space in a
+			 * bitmap but then couldn't find the other part this may
+			 * be a problem, so WARN about it.
 			 */
+			WARN_ON(re_search);
 			goto out_lock;
 		}
 	}
 
+	re_search = false;
 	if (!info->bitmap) {
 		unlink_free_space(ctl, info);
 		if (offset == info->offset) {
@@ -1935,8 +1937,10 @@ again:
 	}
 
 	ret = remove_from_bitmap(ctl, info, &offset, &bytes);
-	if (ret == -EAGAIN)
+	if (ret == -EAGAIN) {
+		re_search = true;
 		goto again;
+	}
 	BUG_ON(ret); /* logic error */
 out_lock:
 	spin_unlock(&ctl->tree_lock);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 16d9e8e191e6..cc93b23ca352 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -88,7 +88,7 @@ static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFLNK >> S_SHIFT]	= BTRFS_FT_SYMLINK,
 };
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize);
+static int btrfs_setsize(struct inode *inode, struct iattr *attr);
 static int btrfs_truncate(struct inode *inode);
 static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
 static noinline int cow_file_range(struct inode *inode,
@@ -2478,6 +2478,18 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 				continue;
 			}
 			nr_truncate++;
+
+			/* 1 for the orphan item deletion. */
+			trans = btrfs_start_transaction(root, 1);
+			if (IS_ERR(trans)) {
+				ret = PTR_ERR(trans);
+				goto out;
+			}
+			ret = btrfs_orphan_add(trans, inode);
+			btrfs_end_transaction(trans, root);
+			if (ret)
+				goto out;
+
 			ret = btrfs_truncate(inode);
 		} else {
 			nr_unlink++;
@@ -3665,6 +3677,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 				block_end - cur_offset, 0);
 		if (IS_ERR(em)) {
 			err = PTR_ERR(em);
+			em = NULL;
 			break;
 		}
 		last_byte = min(extent_map_end(em), block_end);
@@ -3748,16 +3761,27 @@ next:
 	return err;
 }
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize)
+static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	loff_t oldsize = i_size_read(inode);
+	loff_t newsize = attr->ia_size;
+	int mask = attr->ia_valid;
 	int ret;
 
 	if (newsize == oldsize)
 		return 0;
 
+	/*
+	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
+	 * special case where we need to update the times despite not having
+	 * these flags set.  For all other operations the VFS set these flags
+	 * explicitly if it wants a timestamp update.
+	 */
+	if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
+		inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+
 	if (newsize > oldsize) {
 		truncate_pagecache(inode, oldsize, newsize);
 		ret = btrfs_cont_expand(inode, oldsize, newsize);
@@ -3783,9 +3807,34 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize)
 			set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
 				&BTRFS_I(inode)->runtime_flags);
 
+		/*
+		 * 1 for the orphan item we're going to add
+		 * 1 for the orphan item deletion.
+		 */
+		trans = btrfs_start_transaction(root, 2);
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
+
+		/*
+		 * We need to do this in case we fail at _any_ point during the
+		 * actual truncate.  Once we do the truncate_setsize we could
+		 * invalidate pages which forces any outstanding ordered io to
+		 * be instantly completed which will give us extents that need
+		 * to be truncated.  If we fail to get an orphan inode down we
+		 * could have left over extents that were never meant to live,
+		 * so we need to garuntee from this point on that everything
+		 * will be consistent.
+		 */
+		ret = btrfs_orphan_add(trans, inode);
+		btrfs_end_transaction(trans, root);
+		if (ret)
+			return ret;
+
 		/* we don't support swapfiles, so vmtruncate shouldn't fail */
 		truncate_setsize(inode, newsize);
 		ret = btrfs_truncate(inode);
+		if (ret && inode->i_nlink)
+			btrfs_orphan_del(NULL, inode);
 	}
 
 	return ret;
@@ -3805,7 +3854,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
 		return err;
 
 	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
-		err = btrfs_setsize(inode, attr->ia_size);
+		err = btrfs_setsize(inode, attr);
 		if (err)
 			return err;
 	}
@@ -5572,10 +5621,13 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 		return em;
 	if (em) {
 		/*
-		 * if our em maps to a hole, there might
-		 * actually be delalloc bytes behind it
+		 * if our em maps to
+		 * -  a hole or
+		 * -  a pre-alloc extent,
+		 * there might actually be delalloc bytes behind it.
 		 */
-		if (em->block_start != EXTENT_MAP_HOLE)
+		if (em->block_start != EXTENT_MAP_HOLE &&
+		    !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			return em;
 		else
 			hole_em = em;
@@ -5657,6 +5709,8 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 			 */
 			em->block_start = hole_em->block_start;
 			em->block_len = hole_len;
+			if (test_bit(EXTENT_FLAG_PREALLOC, &hole_em->flags))
+				set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
 		} else {
 			em->start = range_start;
 			em->len = found;
@@ -6915,11 +6969,9 @@ static int btrfs_truncate(struct inode *inode)
 
 	/*
 	 * 1 for the truncate slack space
-	 * 1 for the orphan item we're going to add
-	 * 1 for the orphan item deletion
 	 * 1 for updating the inode.
 	 */
-	trans = btrfs_start_transaction(root, 4);
+	trans = btrfs_start_transaction(root, 2);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
 		goto out;
@@ -6930,12 +6982,6 @@ static int btrfs_truncate(struct inode *inode)
 				      min_size);
 	BUG_ON(ret);
 
-	ret = btrfs_orphan_add(trans, inode);
-	if (ret) {
-		btrfs_end_transaction(trans, root);
-		goto out;
-	}
-
 	/*
 	 * setattr is responsible for setting the ordered_data_close flag,
 	 * but that is only tested during the last file release.  That
@@ -7004,12 +7050,6 @@ static int btrfs_truncate(struct inode *inode)
 		ret = btrfs_orphan_del(trans, inode);
 		if (ret)
 			err = ret;
-	} else if (ret && inode->i_nlink > 0) {
-		/*
-		 * Failed to do the truncate, remove us from the in memory
-		 * orphan list.
-		 */
-		ret = btrfs_orphan_del(NULL, inode);
 	}
 
 	if (trans) {
@@ -7531,41 +7571,61 @@ void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work)
  */
 int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 {
-	struct list_head *head = &root->fs_info->delalloc_inodes;
 	struct btrfs_inode *binode;
 	struct inode *inode;
 	struct btrfs_delalloc_work *work, *next;
 	struct list_head works;
+	struct list_head splice;
 	int ret = 0;
 
 	if (root->fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 
 	INIT_LIST_HEAD(&works);
-
+	INIT_LIST_HEAD(&splice);
+again:
 	spin_lock(&root->fs_info->delalloc_lock);
-	while (!list_empty(head)) {
-		binode = list_entry(head->next, struct btrfs_inode,
+	list_splice_init(&root->fs_info->delalloc_inodes, &splice);
+	while (!list_empty(&splice)) {
+		binode = list_entry(splice.next, struct btrfs_inode,
 				    delalloc_inodes);
+
+		list_del_init(&binode->delalloc_inodes);
+
 		inode = igrab(&binode->vfs_inode);
 		if (!inode)
-			list_del_init(&binode->delalloc_inodes);
+			continue;
+
+		list_add_tail(&binode->delalloc_inodes,
+			      &root->fs_info->delalloc_inodes);
 		spin_unlock(&root->fs_info->delalloc_lock);
-		if (inode) {
-			work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
-			if (!work) {
-				ret = -ENOMEM;
-				goto out;
-			}
-			list_add_tail(&work->list, &works);
-			btrfs_queue_worker(&root->fs_info->flush_workers,
-					   &work->work);
+
+		work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
+		if (unlikely(!work)) {
+			ret = -ENOMEM;
+			goto out;
 		}
+		list_add_tail(&work->list, &works);
+		btrfs_queue_worker(&root->fs_info->flush_workers,
+				   &work->work);
+
 		cond_resched();
 		spin_lock(&root->fs_info->delalloc_lock);
 	}
 	spin_unlock(&root->fs_info->delalloc_lock);
 
+	list_for_each_entry_safe(work, next, &works, list) {
+		list_del_init(&work->list);
+		btrfs_wait_and_free_delalloc_work(work);
+	}
+
+	spin_lock(&root->fs_info->delalloc_lock);
+	if (!list_empty(&root->fs_info->delalloc_inodes)) {
+		spin_unlock(&root->fs_info->delalloc_lock);
+		goto again;
+	}
+	spin_unlock(&root->fs_info->delalloc_lock);
+
 	/* the filemap_flush will queue IO into the worker threads, but
 	 * we have to make sure the IO is actually started and that
 	 * ordered extents get created before we return
@@ -7578,11 +7638,18 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 		    atomic_read(&root->fs_info->async_delalloc_pages) == 0));
 	}
 	atomic_dec(&root->fs_info->async_submit_draining);
+	return 0;
 out:
 	list_for_each_entry_safe(work, next, &works, list) {
 		list_del_init(&work->list);
 		btrfs_wait_and_free_delalloc_work(work);
 	}
+
+	if (!list_empty_careful(&splice)) {
+		spin_lock(&root->fs_info->delalloc_lock);
+		list_splice_tail(&splice, &root->fs_info->delalloc_inodes);
+		spin_unlock(&root->fs_info->delalloc_lock);
+	}
 	return ret;
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4b4516770f05..5b22d45d3c6a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1339,7 +1339,8 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
 			1)) {
 		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
-		return -EINPROGRESS;
+		mnt_drop_write_file(file);
+		return -EINVAL;
 	}
 
 	mutex_lock(&root->fs_info->volume_mutex);
@@ -1362,6 +1363,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		printk(KERN_INFO "btrfs: resizing devid %llu\n",
 		       (unsigned long long)devid);
 	}
+
 	device = btrfs_find_device(root->fs_info, devid, NULL, NULL);
 	if (!device) {
 		printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
@@ -1369,9 +1371,10 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		ret = -EINVAL;
 		goto out_free;
 	}
-	if (device->fs_devices && device->fs_devices->seeding) {
+
+	if (!device->writeable) {
 		printk(KERN_INFO "btrfs: resizer unable to apply on "
-		       "seeding device %llu\n",
+		       "readonly device %llu\n",
 		       (unsigned long long)devid);
 		ret = -EINVAL;
 		goto out_free;
@@ -1443,8 +1446,8 @@ out_free:
 	kfree(vol_args);
 out:
 	mutex_unlock(&root->fs_info->volume_mutex);
-	mnt_drop_write_file(file);
 	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+	mnt_drop_write_file(file);
 	return ret;
 }
 
@@ -2095,13 +2098,13 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		err = inode_permission(inode, MAY_WRITE | MAY_EXEC);
 		if (err)
 			goto out_dput;
-
-		/* check if subvolume may be deleted by a non-root user */
-		err = btrfs_may_delete(dir, dentry, 1);
-		if (err)
-			goto out_dput;
 	}
 
+	/* check if subvolume may be deleted by a user */
+	err = btrfs_may_delete(dir, dentry, 1);
+	if (err)
+		goto out_dput;
+
 	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
 		err = -EINVAL;
 		goto out_dput;
@@ -2183,19 +2186,20 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 	struct btrfs_ioctl_defrag_range_args *range;
 	int ret;
 
-	if (btrfs_root_readonly(root))
-		return -EROFS;
+	ret = mnt_want_write_file(file);
+	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");
-		return -EINPROGRESS;
+		mnt_drop_write_file(file);
+		return -EINVAL;
 	}
-	ret = mnt_want_write_file(file);
-	if (ret) {
-		atomic_set(&root->fs_info->mutually_exclusive_operation_running,
-			   0);
-		return ret;
+
+	if (btrfs_root_readonly(root)) {
+		ret = -EROFS;
+		goto out;
 	}
 
 	switch (inode->i_mode & S_IFMT) {
@@ -2247,8 +2251,8 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 		ret = -EINVAL;
 	}
 out:
-	mnt_drop_write_file(file);
 	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+	mnt_drop_write_file(file);
 	return ret;
 }
 
@@ -2263,7 +2267,7 @@ static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg)
 	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
 			1)) {
 		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
-		return -EINPROGRESS;
+		return -EINVAL;
 	}
 
 	mutex_lock(&root->fs_info->volume_mutex);
@@ -2300,7 +2304,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 			1)) {
 		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
 		mnt_drop_write_file(file);
-		return -EINPROGRESS;
+		return -EINVAL;
 	}
 
 	mutex_lock(&root->fs_info->volume_mutex);
@@ -2316,8 +2320,8 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	kfree(vol_args);
 out:
 	mutex_unlock(&root->fs_info->volume_mutex);
-	mnt_drop_write_file(file);
 	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+	mnt_drop_write_file(file);
 	return ret;
 }
 
@@ -3437,8 +3441,8 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_ioctl_balance_args *bargs;
 	struct btrfs_balance_control *bctl;
+	bool need_unlock; /* for mut. excl. ops lock */
 	int ret;
-	int need_to_clear_lock = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -3447,14 +3451,61 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 	if (ret)
 		return ret;
 
-	mutex_lock(&fs_info->volume_mutex);
+again:
+	if (!atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+		mutex_lock(&fs_info->volume_mutex);
+		mutex_lock(&fs_info->balance_mutex);
+		need_unlock = true;
+		goto locked;
+	}
+
+	/*
+	 * mut. excl. ops lock is locked.  Three possibilites:
+	 *   (1) some other op is running
+	 *   (2) balance is running
+	 *   (3) balance is paused -- special case (think resume)
+	 */
 	mutex_lock(&fs_info->balance_mutex);
+	if (fs_info->balance_ctl) {
+		/* this is either (2) or (3) */
+		if (!atomic_read(&fs_info->balance_running)) {
+			mutex_unlock(&fs_info->balance_mutex);
+			if (!mutex_trylock(&fs_info->volume_mutex))
+				goto again;
+			mutex_lock(&fs_info->balance_mutex);
+
+			if (fs_info->balance_ctl &&
+			    !atomic_read(&fs_info->balance_running)) {
+				/* this is (3) */
+				need_unlock = false;
+				goto locked;
+			}
+
+			mutex_unlock(&fs_info->balance_mutex);
+			mutex_unlock(&fs_info->volume_mutex);
+			goto again;
+		} else {
+			/* this is (2) */
+			mutex_unlock(&fs_info->balance_mutex);
+			ret = -EINPROGRESS;
+			goto out;
+		}
+	} else {
+		/* this is (1) */
+		mutex_unlock(&fs_info->balance_mutex);
+		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+locked:
+	BUG_ON(!atomic_read(&fs_info->mutually_exclusive_operation_running));
 
 	if (arg) {
 		bargs = memdup_user(arg, sizeof(*bargs));
 		if (IS_ERR(bargs)) {
 			ret = PTR_ERR(bargs);
-			goto out;
+			goto out_unlock;
 		}
 
 		if (bargs->flags & BTRFS_BALANCE_RESUME) {
@@ -3474,13 +3525,10 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 		bargs = NULL;
 	}
 
-	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
-			1)) {
-		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
+	if (fs_info->balance_ctl) {
 		ret = -EINPROGRESS;
 		goto out_bargs;
 	}
-	need_to_clear_lock = 1;
 
 	bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
 	if (!bctl) {
@@ -3501,11 +3549,17 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 	}
 
 do_balance:
-	ret = btrfs_balance(bctl, bargs);
 	/*
-	 * bctl is freed in __cancel_balance or in free_fs_info if
-	 * restriper was paused all the way until unmount
+	 * Ownership of bctl and mutually_exclusive_operation_running
+	 * goes to to btrfs_balance.  bctl is freed in __cancel_balance,
+	 * or, if restriper was paused all the way until unmount, in
+	 * free_fs_info.  mutually_exclusive_operation_running is
+	 * cleared in __cancel_balance.
 	 */
+	need_unlock = false;
+
+	ret = btrfs_balance(bctl, bargs);
+
 	if (arg) {
 		if (copy_to_user(arg, bargs, sizeof(*bargs)))
 			ret = -EFAULT;
@@ -3513,12 +3567,12 @@ do_balance:
 
 out_bargs:
 	kfree(bargs);
-out:
-	if (need_to_clear_lock)
-		atomic_set(&root->fs_info->mutually_exclusive_operation_running,
-			   0);
+out_unlock:
 	mutex_unlock(&fs_info->balance_mutex);
 	mutex_unlock(&fs_info->volume_mutex);
+	if (need_unlock)
+		atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+out:
 	mnt_drop_write_file(file);
 	return ret;
 }
@@ -3698,6 +3752,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 		goto drop_write;
 	}
 
+	if (!sa->qgroupid) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index fe9d02c45f8e..a5c856234323 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -379,6 +379,13 @@ next1:
 
 		ret = add_relation_rb(fs_info, found_key.objectid,
 				      found_key.offset);
+		if (ret == -ENOENT) {
+			printk(KERN_WARNING
+				"btrfs: orphan qgroup relation 0x%llx->0x%llx\n",
+				(unsigned long long)found_key.objectid,
+				(unsigned long long)found_key.offset);
+			ret = 0;	/* ignore the error */
+		}
 		if (ret)
 			goto out;
 next2:
@@ -956,17 +963,28 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info, u64 qgroupid)
 {
 	struct btrfs_root *quota_root;
+	struct btrfs_qgroup *qgroup;
 	int ret = 0;
 
 	quota_root = fs_info->quota_root;
 	if (!quota_root)
 		return -EINVAL;
 
+	/* check if there are no relations to this qgroup */
+	spin_lock(&fs_info->qgroup_lock);
+	qgroup = find_qgroup_rb(fs_info, qgroupid);
+	if (qgroup) {
+		if (!list_empty(&qgroup->groups) || !list_empty(&qgroup->members)) {
+			spin_unlock(&fs_info->qgroup_lock);
+			return -EBUSY;
+		}
+	}
+	spin_unlock(&fs_info->qgroup_lock);
+
 	ret = del_qgroup_item(trans, quota_root, qgroupid);
 
 	spin_lock(&fs_info->qgroup_lock);
 	del_qgroup_rb(quota_root->fs_info, qgroupid);
-
 	spin_unlock(&fs_info->qgroup_lock);
 
 	return ret;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 54454542ad40..321b7fb4e441 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1814,8 +1814,10 @@ static int name_cache_insert(struct send_ctx *sctx,
 			(unsigned long)nce->ino);
 	if (!nce_head) {
 		nce_head = kmalloc(sizeof(*nce_head), GFP_NOFS);
-		if (!nce_head)
+		if (!nce_head) {
+			kfree(nce);
 			return -ENOMEM;
+		}
 		INIT_LIST_HEAD(nce_head);
 
 		ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 99545df1b86c..d8982e9601d3 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -267,7 +267,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 			     function, line, errstr);
 		return;
 	}
-	trans->transaction->aborted = errno;
+	ACCESS_ONCE(trans->transaction->aborted) = errno;
 	__btrfs_std_error(root->fs_info, function, line, errno, NULL);
 }
 /*
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 87fac9a21ea5..f15494699f3b 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1468,7 +1468,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 		goto cleanup_transaction;
 	}
 
-	if (cur_trans->aborted) {
+	/* Stop the commit early if ->aborted is set */
+	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
 		goto cleanup_transaction;
 	}
@@ -1574,6 +1575,11 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	wait_event(cur_trans->writer_wait,
 		   atomic_read(&cur_trans->num_writers) == 1);
 
+	/* ->aborted might be set after the previous check, so check it */
+	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
+		ret = cur_trans->aborted;
+		goto cleanup_transaction;
+	}
 	/*
 	 * the reloc mutex makes sure that we stop
 	 * the balancing code from coming in and moving
@@ -1657,6 +1663,17 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 		goto cleanup_transaction;
 	}
 
+	/*
+	 * The tasks which save the space cache and inode cache may also
+	 * update ->aborted, check it.
+	 */
+	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
+		ret = cur_trans->aborted;
+		mutex_unlock(&root->fs_info->tree_log_mutex);
+		mutex_unlock(&root->fs_info->reloc_mutex);
+		goto cleanup_transaction;
+	}
+
 	btrfs_prepare_extent_commit(trans, root);
 
 	cur_trans = root->fs_info->running_transaction;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 83186c7e45d4..9027bb1e7466 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3357,6 +3357,11 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	if (skip_csum)
 		return 0;
 
+	if (em->compress_type) {
+		csum_offset = 0;
+		csum_len = block_len;
+	}
+
 	/* block start is already adjusted for the file extent offset. */
 	ret = btrfs_lookup_csums_range(log->fs_info->csum_root,
 				       em->block_start + csum_offset,
@@ -3410,13 +3415,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 		em = list_entry(extents.next, struct extent_map, list);
 
 		list_del_init(&em->list);
-		clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
 
 		/*
 		 * If we had an error we just need to delete everybody from our
 		 * private list.
 		 */
 		if (ret) {
+			clear_em_logging(tree, em);
 			free_extent_map(em);
 			continue;
 		}
@@ -3424,8 +3429,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 		write_unlock(&tree->lock);
 
 		ret = log_one_extent(trans, inode, root, em, path);
-		free_extent_map(em);
 		write_lock(&tree->lock);
+		clear_em_logging(tree, em);
+		free_extent_map(em);
 	}
 	WARN_ON(!list_empty(&extents));
 	write_unlock(&tree->lock);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5cce6aa74012..15f6efdf6463 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1431,7 +1431,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		}
 	} else {
 		ret = btrfs_get_bdev_and_sb(device_path,
-					    FMODE_READ | FMODE_EXCL,
+					    FMODE_WRITE | FMODE_EXCL,
 					    root->fs_info->bdev_holder, 0,
 					    &bdev, &bh);
 		if (ret)
@@ -2614,7 +2614,14 @@ static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
 	cache = btrfs_lookup_block_group(fs_info, chunk_offset);
 	chunk_used = btrfs_block_group_used(&cache->item);
 
-	user_thresh = div_factor_fine(cache->key.offset, bargs->usage);
+	if (bargs->usage == 0)
+		user_thresh = 0;
+	else if (bargs->usage > 100)
+		user_thresh = cache->key.offset;
+	else
+		user_thresh = div_factor_fine(cache->key.offset,
+					      bargs->usage);
+
 	if (chunk_used < user_thresh)
 		ret = 0;
 
@@ -2959,6 +2966,8 @@ 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);
+
+	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
 }
 
 void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
@@ -3138,8 +3147,10 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 out:
 	if (bctl->flags & BTRFS_BALANCE_RESUME)
 		__cancel_balance(fs_info);
-	else
+	else {
 		kfree(bctl);
+		atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+	}
 	return ret;
 }
 
@@ -3156,7 +3167,6 @@ static int balance_kthread(void *data)
 		ret = btrfs_balance(fs_info->balance_ctl, NULL);
 	}
 
-	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
 	mutex_unlock(&fs_info->balance_mutex);
 	mutex_unlock(&fs_info->volume_mutex);
 
@@ -3179,7 +3189,6 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
 		return 0;
 	}
 
-	WARN_ON(atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1));
 	tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
 	if (IS_ERR(tsk))
 		return PTR_ERR(tsk);
@@ -3233,6 +3242,8 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
 	btrfs_balance_sys(leaf, item, &disk_bargs);
 	btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
 
+	WARN_ON(atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1));
+
 	mutex_lock(&fs_info->volume_mutex);
 	mutex_lock(&fs_info->balance_mutex);
 
@@ -3496,7 +3507,7 @@ struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	{ 1, 1, 2, 2, 2, 2 /* raid1 */ },
 	{ 1, 2, 1, 1, 1, 2 /* dup */ },
 	{ 1, 1, 0, 2, 1, 1 /* raid0 */ },
-	{ 1, 1, 0, 1, 1, 1 /* single */ },
+	{ 1, 1, 1, 1, 1, 1 /* single */ },
 };
 
 static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
diff --git a/fs/buffer.c b/fs/buffer.c
index c017a2dfb909..7a75c3e0fd58 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2935,6 +2935,7 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
 		void *kaddr = kmap_atomic(bh->b_page);
 		memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes);
 		kunmap_atomic(kaddr);
+		flush_dcache_page(bh->b_page);
 	}
 }
 
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index ce5cbd717bfc..210fce2df308 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -226,6 +226,8 @@ compose_mount_options_out:
 compose_mount_options_err:
 	kfree(mountdata);
 	mountdata = ERR_PTR(rc);
+	kfree(*devname);
+	*devname = NULL;
 	goto compose_mount_options_out;
 }
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index f653835d067b..de7f9168a118 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -228,7 +228,6 @@ cifs_alloc_inode(struct super_block *sb)
 	cifs_set_oplock_level(cifs_inode, 0);
 	cifs_inode->delete_pending = false;
 	cifs_inode->invalid_mapping = false;
-	cifs_inode->leave_pages_clean = false;
 	cifs_inode->vfs_inode.i_blkbits = 14;  /* 2**14 = CIFS_MAX_MSGSIZE */
 	cifs_inode->server_eof = 0;
 	cifs_inode->uniqueid = 0;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index aea1eec64911..e6899cea1c35 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -386,6 +386,7 @@ struct smb_version_values {
 	unsigned int	cap_unix;
 	unsigned int	cap_nt_find;
 	unsigned int	cap_large_files;
+	unsigned int	oplock_read;
 };
 
 #define HEADER_SIZE(server) (server->vals->header_size)
@@ -1030,7 +1031,6 @@ struct cifsInodeInfo {
 	bool clientCanCacheAll;		/* read and writebehind oplock */
 	bool delete_pending;		/* DELETE_ON_CLOSE is set */
 	bool invalid_mapping;		/* pagecache is invalid */
-	bool leave_pages_clean;	/* protected by i_mutex, not set pages dirty */
 	unsigned long time;		/* jiffies of last update of inode */
 	u64  server_eof;		/* current file size on server -- protected by i_lock */
 	u64  uniqueid;			/* server inode number */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 17c3643e5950..12b3da39733b 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1917,7 +1917,7 @@ srcip_matches(struct sockaddr *srcaddr, struct sockaddr *rhs)
 	}
 	case AF_INET6: {
 		struct sockaddr_in6 *saddr6 = (struct sockaddr_in6 *)srcaddr;
-		struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)&rhs;
+		struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)rhs;
 		return ipv6_addr_equal(&saddr6->sin6_addr, &vaddr6->sin6_addr);
 	}
 	default:
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0a6677ba212b..8ea6ca50a665 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -238,6 +238,23 @@ out:
 	return rc;
 }
 
+static bool
+cifs_has_mand_locks(struct cifsInodeInfo *cinode)
+{
+	struct cifs_fid_locks *cur;
+	bool has_locks = false;
+
+	down_read(&cinode->lock_sem);
+	list_for_each_entry(cur, &cinode->llist, llist) {
+		if (!list_empty(&cur->locks)) {
+			has_locks = true;
+			break;
+		}
+	}
+	up_read(&cinode->lock_sem);
+	return has_locks;
+}
+
 struct cifsFileInfo *
 cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 		  struct tcon_link *tlink, __u32 oplock)
@@ -248,6 +265,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	struct cifsFileInfo *cfile;
 	struct cifs_fid_locks *fdlocks;
 	struct cifs_tcon *tcon = tlink_tcon(tlink);
+	struct TCP_Server_Info *server = tcon->ses->server;
 
 	cfile = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL);
 	if (cfile == NULL)
@@ -276,12 +294,22 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
 	mutex_init(&cfile->fh_mutex);
 
+	/*
+	 * If the server returned a read oplock and we have mandatory brlocks,
+	 * set oplock level to None.
+	 */
+	if (oplock == server->vals->oplock_read &&
+						cifs_has_mand_locks(cinode)) {
+		cFYI(1, "Reset oplock val from read to None due to mand locks");
+		oplock = 0;
+	}
+
 	spin_lock(&cifs_file_list_lock);
-	if (fid->pending_open->oplock != CIFS_OPLOCK_NO_CHANGE)
+	if (fid->pending_open->oplock != CIFS_OPLOCK_NO_CHANGE && oplock)
 		oplock = fid->pending_open->oplock;
 	list_del(&fid->pending_open->olist);
 
-	tlink_tcon(tlink)->ses->server->ops->set_fid(cfile, fid, oplock);
+	server->ops->set_fid(cfile, fid, oplock);
 
 	list_add(&cfile->tlist, &tcon->openFileList);
 	/* if readable file instance put first in list*/
@@ -1422,6 +1450,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 	struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
+	struct inode *inode = cfile->dentry->d_inode;
 
 	if (posix_lck) {
 		int posix_lock_type;
@@ -1459,6 +1488,21 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 		if (!rc)
 			goto out;
 
+		/*
+		 * Windows 7 server can delay breaking lease from read to None
+		 * if we set a byte-range lock on a file - break it explicitly
+		 * before sending the lock to the server to be sure the next
+		 * read won't conflict with non-overlapted locks due to
+		 * pagereading.
+		 */
+		if (!CIFS_I(inode)->clientCanCacheAll &&
+					CIFS_I(inode)->clientCanCacheRead) {
+			cifs_invalidate_mapping(inode);
+			cFYI(1, "Set no oplock for inode=%p due to mand locks",
+			     inode);
+			CIFS_I(inode)->clientCanCacheRead = false;
+		}
+
 		rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
 					    type, 1, 0, wait_flag);
 		if (rc) {
@@ -2103,15 +2147,7 @@ static int cifs_write_end(struct file *file, struct address_space *mapping,
 	} else {
 		rc = copied;
 		pos += copied;
-		/*
-		 * When we use strict cache mode and cifs_strict_writev was run
-		 * with level II oplock (indicated by leave_pages_clean field of
-		 * CIFS_I(inode)), we can leave pages clean - cifs_strict_writev
-		 * sent the data to the server itself.
-		 */
-		if (!CIFS_I(inode)->leave_pages_clean ||
-		    !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO))
-			set_page_dirty(page);
+		set_page_dirty(page);
 	}
 
 	if (rc > 0) {
@@ -2462,8 +2498,8 @@ ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
 }
 
 static ssize_t
-cifs_pagecache_writev(struct kiocb *iocb, const struct iovec *iov,
-		      unsigned long nr_segs, loff_t pos, bool cache_ex)
+cifs_writev(struct kiocb *iocb, const struct iovec *iov,
+	    unsigned long nr_segs, loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
 	struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
@@ -2485,12 +2521,8 @@ cifs_pagecache_writev(struct kiocb *iocb, const struct iovec *iov,
 				     server->vals->exclusive_lock_type, NULL,
 				     CIFS_WRITE_OP)) {
 		mutex_lock(&inode->i_mutex);
-		if (!cache_ex)
-			cinode->leave_pages_clean = true;
 		rc = __generic_file_aio_write(iocb, iov, nr_segs,
-					      &iocb->ki_pos);
-		if (!cache_ex)
-			cinode->leave_pages_clean = false;
+					       &iocb->ki_pos);
 		mutex_unlock(&inode->i_mutex);
 	}
 
@@ -2517,60 +2549,32 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
 	struct cifsFileInfo *cfile = (struct cifsFileInfo *)
 						iocb->ki_filp->private_data;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
-	ssize_t written, written2;
-	/*
-	 * We need to store clientCanCacheAll here to prevent race
-	 * conditions - this value can be changed during an execution
-	 * of generic_file_aio_write. For CIFS it can be changed from
-	 * true to false only, but for SMB2 it can be changed both from
-	 * true to false and vice versa. So, we can end up with a data
-	 * stored in the cache, not marked dirty and not sent to the
-	 * server if this value changes its state from false to true
-	 * after cifs_write_end.
-	 */
-	bool cache_ex = cinode->clientCanCacheAll;
-	bool cache_read = cinode->clientCanCacheRead;
-	int rc;
-	loff_t saved_pos;
+	ssize_t written;
 
-	if (cache_ex) {
+	if (cinode->clientCanCacheAll) {
 		if (cap_unix(tcon->ses) &&
-		    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0) &&
-		    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(
-						tcon->fsUnixInfo.Capability)))
+		(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))
+		    && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
 			return generic_file_aio_write(iocb, iov, nr_segs, pos);
-		return cifs_pagecache_writev(iocb, iov, nr_segs, pos, cache_ex);
+		return cifs_writev(iocb, iov, nr_segs, pos);
 	}
-
 	/*
-	 * For files without exclusive oplock in strict cache mode we need to
-	 * write the data to the server exactly from the pos to pos+len-1 rather
-	 * than flush all affected pages because it may cause a error with
-	 * mandatory locks on these pages but not on the region from pos to
-	 * ppos+len-1.
+	 * For non-oplocked files in strict cache mode we need to write the data
+	 * to the server exactly from the pos to pos+len-1 rather than flush all
+	 * affected pages because it may cause a error with mandatory locks on
+	 * these pages but not on the region from pos to ppos+len-1.
 	 */
 	written = cifs_user_writev(iocb, iov, nr_segs, pos);
-	if (!cache_read || written <= 0)
-		return written;
-
-	saved_pos = iocb->ki_pos;
-	iocb->ki_pos = pos;
-	/* we have a read oplock - need to store a data in the page cache */
-	if (cap_unix(tcon->ses) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0) &&
-	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(
-					tcon->fsUnixInfo.Capability)))
-		written2 = generic_file_aio_write(iocb, iov, nr_segs, pos);
-	else
-		written2 = cifs_pagecache_writev(iocb, iov, nr_segs, pos,
-						 cache_ex);
-	/* errors occured during writing - invalidate the page cache */
-	if (written2 < 0) {
-		rc = cifs_invalidate_mapping(inode);
-		if (rc)
-			written = (ssize_t)rc;
-		else
-			iocb->ki_pos = saved_pos;
+	if (written > 0 && cinode->clientCanCacheRead) {
+		/*
+		 * Windows 7 server can delay breaking level2 oplock if a write
+		 * request comes - break it on the client to prevent reading
+		 * an old data.
+		 */
+		cifs_invalidate_mapping(inode);
+		cFYI(1, "Set no oplock for inode=%p after a write operation",
+		     inode);
+		cinode->clientCanCacheRead = false;
 	}
 	return written;
 }
@@ -3577,6 +3581,13 @@ void cifs_oplock_break(struct work_struct *work)
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	int rc = 0;
 
+	if (!cinode->clientCanCacheAll && cinode->clientCanCacheRead &&
+						cifs_has_mand_locks(cinode)) {
+		cFYI(1, "Reset oplock to None for inode=%p due to mand locks",
+		     inode);
+		cinode->clientCanCacheRead = false;
+	}
+
 	if (inode && S_ISREG(inode->i_mode)) {
 		if (cinode->clientCanCacheRead)
 			break_lease(inode, O_RDONLY);
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index a5d234c8d5d9..47bc5a87f94e 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -53,6 +53,13 @@ send_nt_cancel(struct TCP_Server_Info *server, void *buf,
 		mutex_unlock(&server->srv_mutex);
 		return rc;
 	}
+
+	/*
+	 * The response to this call was already factored into the sequence
+	 * number when the call went out, so we must adjust it back downward
+	 * after signing here.
+	 */
+	--server->sequence_number;
 	rc = smb_send(server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
 	mutex_unlock(&server->srv_mutex);
 
@@ -952,4 +959,5 @@ struct smb_version_values smb1_values = {
 	.cap_unix = CAP_UNIX,
 	.cap_nt_find = CAP_NT_SMBS | CAP_NT_FIND,
 	.cap_large_files = CAP_LARGE_FILES,
+	.oplock_read = OPLOCK_READ,
 };
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index d79de7bc4435..c9c7aa7ed966 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -708,6 +708,7 @@ struct smb_version_values smb20_values = {
 	.cap_unix = 0,
 	.cap_nt_find = SMB2_NT_FIND,
 	.cap_large_files = SMB2_LARGE_FILES,
+	.oplock_read = SMB2_OPLOCK_LEVEL_II,
 };
 
 struct smb_version_values smb21_values = {
@@ -725,6 +726,7 @@ struct smb_version_values smb21_values = {
 	.cap_unix = 0,
 	.cap_nt_find = SMB2_NT_FIND,
 	.cap_large_files = SMB2_LARGE_FILES,
+	.oplock_read = SMB2_OPLOCK_LEVEL_II,
 };
 
 struct smb_version_values smb30_values = {
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 76d974c952fe..1a528680ec5a 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -144,9 +144,6 @@ smb_send_kvec(struct TCP_Server_Info *server, struct kvec *iov, size_t n_vec,
 
 	*sent = 0;
 
-	if (ssocket == NULL)
-		return -ENOTSOCK; /* BB eventually add reconnect code here */
-
 	smb_msg.msg_name = (struct sockaddr *) &server->dstaddr;
 	smb_msg.msg_namelen = sizeof(struct sockaddr);
 	smb_msg.msg_control = NULL;
@@ -291,6 +288,9 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 	struct socket *ssocket = server->ssocket;
 	int val = 1;
 
+	if (ssocket == NULL)
+		return -ENOTSOCK;
+
 	cFYI(1, "Sending smb: smb_len=%u", smb_buf_length);
 	dump_smb(iov[0].iov_base, iov[0].iov_len);
 
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 153bb1e42e63..a5f12b7e228d 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -176,7 +176,7 @@ static int debugfs_parse_options(char *data, struct debugfs_mount_opts *opts)
 			opts->uid = uid;
 			break;
 		case Opt_gid:
-			if (match_octal(&args[0], &option))
+			if (match_int(&args[0], &option))
 				return -EINVAL;
 			gid = make_kgid(current_user_ns(), option);
 			if (!gid_valid(gid))
diff --git a/fs/exec.c b/fs/exec.c
index 18c45cac368f..20df02c1cc70 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -434,8 +434,9 @@ static int count(struct user_arg_ptr argv, int max)
 			if (IS_ERR(p))
 				return -EFAULT;
 
-			if (i++ >= max)
+			if (i >= max)
 				return -E2BIG;
+			++i;
 
 			if (fatal_signal_pending(current))
 				return -ERESTARTNOHAND;
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 0a475c881852..987358740cb9 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -41,6 +41,7 @@ config EXT4_USE_FOR_EXT23
 
 config EXT4_FS_POSIX_ACL
 	bool "Ext4 POSIX Access Control Lists"
+	depends on EXT4_FS
 	select FS_POSIX_ACL
 	help
 	  POSIX Access Control Lists (ACLs) support permissions for users and
@@ -53,6 +54,7 @@ config EXT4_FS_POSIX_ACL
 
 config EXT4_FS_SECURITY
 	bool "Ext4 Security Labels"
+	depends on EXT4_FS
 	help
 	  Security labels support alternative access control models
 	  implemented by security modules like SELinux.  This option
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 8990165346ee..f9ed946a448e 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -722,7 +722,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
 			ext4_warning(dir->i_sb, "Node failed checksum");
 			brelse(bh);
 			*err = ERR_BAD_DX_DIR;
-			goto fail;
+			goto fail2;
 		}
 		set_buffer_verified(bh);
 
@@ -2368,7 +2368,6 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir,
 	}
 
 	inode->i_size = EXT4_I(inode)->i_disksize = blocksize;
-	dir_block = ext4_bread(handle, inode, 0, 1, &err);
 	if (!(dir_block = ext4_bread(handle, inode, 0, 1, &err))) {
 		if (!err) {
 			err = -EIO;
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index e95b94945d5f..137af4255da6 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -191,15 +191,14 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
 		retval = f2fs_getxattr(inode, name_index, "", value, retval);
 	}
 
-	if (retval < 0) {
-		if (retval == -ENODATA)
-			acl = NULL;
-		else
-			acl = ERR_PTR(retval);
-	} else {
+	if (retval > 0)
 		acl = f2fs_acl_from_disk(value, retval);
-	}
+	else if (retval == -ENODATA)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
 	kfree(value);
+
 	if (!IS_ERR(acl))
 		set_cached_acl(inode, type, acl);
 
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 6ef36c37e2be..ff3c8439af87 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -214,7 +214,6 @@ retry:
 		goto retry;
 	}
 	new->ino = ino;
-	INIT_LIST_HEAD(&new->list);
 
 	/* add new_oentry into list which is sorted by inode number */
 	if (orphan) {
@@ -772,7 +771,7 @@ void init_orphan_info(struct f2fs_sb_info *sbi)
 	sbi->n_orphans = 0;
 }
 
-int create_checkpoint_caches(void)
+int __init create_checkpoint_caches(void)
 {
 	orphan_entry_slab = f2fs_kmem_cache_create("f2fs_orphan_entry",
 			sizeof(struct orphan_inode_entry), NULL);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 655aeabc1dd4..7bd22a201125 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -16,6 +16,7 @@
 #include <linux/backing-dev.h>
 #include <linux/blkdev.h>
 #include <linux/bio.h>
+#include <linux/prefetch.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -546,6 +547,15 @@ redirty_out:
 
 #define MAX_DESIRED_PAGES_WP	4096
 
+static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
+			void *data)
+{
+	struct address_space *mapping = data;
+	int ret = mapping->a_ops->writepage(page, wbc);
+	mapping_set_error(mapping, ret);
+	return ret;
+}
+
 static int f2fs_write_data_pages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
@@ -562,7 +572,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 
 	if (!S_ISDIR(inode->i_mode))
 		mutex_lock(&sbi->writepages);
-	ret = generic_writepages(mapping, wbc);
+	ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
 	if (!S_ISDIR(inode->i_mode))
 		mutex_unlock(&sbi->writepages);
 	f2fs_submit_bio(sbi, DATA, (wbc->sync_mode == WB_SYNC_ALL));
@@ -688,6 +698,11 @@ static int f2fs_set_data_page_dirty(struct page *page)
 	return 0;
 }
 
+static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
+{
+	return generic_block_bmap(mapping, block, get_data_block_ro);
+}
+
 const struct address_space_operations f2fs_dblock_aops = {
 	.readpage	= f2fs_read_data_page,
 	.readpages	= f2fs_read_data_pages,
@@ -699,4 +714,5 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.invalidatepage	= f2fs_invalidate_data_page,
 	.releasepage	= f2fs_release_data_page,
 	.direct_IO	= f2fs_direct_IO,
+	.bmap		= f2fs_bmap,
 };
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 0e0380a588ad..c8c37307b326 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -26,6 +26,7 @@
 
 static LIST_HEAD(f2fs_stat_list);
 static struct dentry *debugfs_root;
+static DEFINE_MUTEX(f2fs_stat_mutex);
 
 static void update_general_status(struct f2fs_sb_info *sbi)
 {
@@ -180,18 +181,14 @@ static int stat_show(struct seq_file *s, void *v)
 	int i = 0;
 	int j;
 
+	mutex_lock(&f2fs_stat_mutex);
 	list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) {
 
-		mutex_lock(&si->stat_lock);
-		if (!si->sbi) {
-			mutex_unlock(&si->stat_lock);
-			continue;
-		}
 		update_general_status(si->sbi);
 
 		seq_printf(s, "\n=====[ partition info. #%d ]=====\n", i++);
-		seq_printf(s, "[SB: 1] [CP: 2] [NAT: %d] [SIT: %d] ",
-			   si->nat_area_segs, si->sit_area_segs);
+		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
+			   si->sit_area_segs, si->nat_area_segs);
 		seq_printf(s, "[SSA: %d] [MAIN: %d",
 			   si->ssa_area_segs, si->main_area_segs);
 		seq_printf(s, "(OverProv:%d Resv:%d)]\n\n",
@@ -286,8 +283,8 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n",
 				(si->base_mem + si->cache_mem) >> 10,
 				si->base_mem >> 10, si->cache_mem >> 10);
-		mutex_unlock(&si->stat_lock);
 	}
+	mutex_unlock(&f2fs_stat_mutex);
 	return 0;
 }
 
@@ -303,7 +300,7 @@ static const struct file_operations stat_fops = {
 	.release = single_release,
 };
 
-static int init_stats(struct f2fs_sb_info *sbi)
+int f2fs_build_stats(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_stat_info *si;
@@ -313,9 +310,6 @@ static int init_stats(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 	si = sbi->stat_info;
-	mutex_init(&si->stat_lock);
-	list_add_tail(&si->stat_list, &f2fs_stat_list);
-
 	si->all_area_segs = le32_to_cpu(raw_super->segment_count);
 	si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit);
 	si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat);
@@ -325,21 +319,11 @@ static int init_stats(struct f2fs_sb_info *sbi)
 	si->main_area_zones = si->main_area_sections /
 				le32_to_cpu(raw_super->secs_per_zone);
 	si->sbi = sbi;
-	return 0;
-}
 
-int f2fs_build_stats(struct f2fs_sb_info *sbi)
-{
-	int retval;
-
-	retval = init_stats(sbi);
-	if (retval)
-		return retval;
-
-	if (!debugfs_root)
-		debugfs_root = debugfs_create_dir("f2fs", NULL);
+	mutex_lock(&f2fs_stat_mutex);
+	list_add_tail(&si->stat_list, &f2fs_stat_list);
+	mutex_unlock(&f2fs_stat_mutex);
 
-	debugfs_create_file("status", S_IRUGO, debugfs_root, NULL, &stat_fops);
 	return 0;
 }
 
@@ -347,14 +331,22 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_stat_info *si = sbi->stat_info;
 
+	mutex_lock(&f2fs_stat_mutex);
 	list_del(&si->stat_list);
-	mutex_lock(&si->stat_lock);
-	si->sbi = NULL;
-	mutex_unlock(&si->stat_lock);
+	mutex_unlock(&f2fs_stat_mutex);
+
 	kfree(sbi->stat_info);
 }
 
-void destroy_root_stats(void)
+void __init f2fs_create_root_stats(void)
+{
+	debugfs_root = debugfs_create_dir("f2fs", NULL);
+	if (debugfs_root)
+		debugfs_create_file("status", S_IRUGO, debugfs_root,
+					 NULL, &stat_fops);
+}
+
+void f2fs_destroy_root_stats(void)
 {
 	debugfs_remove_recursive(debugfs_root);
 	debugfs_root = NULL;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index b4e24f32b54e..989980e16d0b 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -11,6 +11,7 @@
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include "f2fs.h"
+#include "node.h"
 #include "acl.h"
 
 static unsigned long dir_blocks(struct inode *inode)
@@ -74,7 +75,7 @@ static unsigned long dir_block_index(unsigned int level, unsigned int idx)
 	return bidx;
 }
 
-static bool early_match_name(const char *name, int namelen,
+static bool early_match_name(const char *name, size_t namelen,
 			f2fs_hash_t namehash, struct f2fs_dir_entry *de)
 {
 	if (le16_to_cpu(de->name_len) != namelen)
@@ -87,7 +88,7 @@ static bool early_match_name(const char *name, int namelen,
 }
 
 static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
-			const char *name, int namelen, int *max_slots,
+			const char *name, size_t namelen, int *max_slots,
 			f2fs_hash_t namehash, struct page **res_page)
 {
 	struct f2fs_dir_entry *de;
@@ -126,7 +127,7 @@ found:
 }
 
 static struct f2fs_dir_entry *find_in_level(struct inode *dir,
-		unsigned int level, const char *name, int namelen,
+		unsigned int level, const char *name, size_t namelen,
 			f2fs_hash_t namehash, struct page **res_page)
 {
 	int s = GET_DENTRY_SLOTS(namelen);
@@ -181,7 +182,7 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 			struct qstr *child, struct page **res_page)
 {
 	const char *name = child->name;
-	int namelen = child->len;
+	size_t namelen = child->len;
 	unsigned long npages = dir_blocks(dir);
 	struct f2fs_dir_entry *de = NULL;
 	f2fs_hash_t name_hash;
@@ -308,6 +309,7 @@ static int init_inode_metadata(struct inode *inode, struct dentry *dentry)
 		ipage = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
 		if (IS_ERR(ipage))
 			return PTR_ERR(ipage);
+		set_cold_node(inode, ipage);
 		init_dent_inode(dentry, ipage);
 		f2fs_put_page(ipage, 1);
 	}
@@ -381,7 +383,7 @@ int f2fs_add_link(struct dentry *dentry, struct inode *inode)
 	struct inode *dir = dentry->d_parent->d_inode;
 	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
 	const char *name = dentry->d_name.name;
-	int namelen = dentry->d_name.len;
+	size_t namelen = dentry->d_name.len;
 	struct page *dentry_page = NULL;
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	int slots = GET_DENTRY_SLOTS(namelen);
@@ -501,7 +503,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	}
 
 	if (inode) {
-		inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+		inode->i_ctime = CURRENT_TIME;
 		drop_nlink(inode);
 		if (S_ISDIR(inode->i_mode)) {
 			drop_nlink(inode);
@@ -540,13 +542,13 @@ int f2fs_make_empty(struct inode *inode, struct inode *parent)
 
 	de = &dentry_blk->dentry[0];
 	de->name_len = cpu_to_le16(1);
-	de->hash_code = 0;
+	de->hash_code = f2fs_dentry_hash(".", 1);
 	de->ino = cpu_to_le32(inode->i_ino);
 	memcpy(dentry_blk->filename[0], ".", 1);
 	set_de_type(de, inode);
 
 	de = &dentry_blk->dentry[1];
-	de->hash_code = 0;
+	de->hash_code = f2fs_dentry_hash("..", 2);
 	de->name_len = cpu_to_le16(2);
 	de->ino = cpu_to_le32(parent->i_ino);
 	memcpy(dentry_blk->filename[1], "..", 2);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index a18d63db2fb6..c8e2d751ef9c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -211,11 +211,11 @@ struct dnode_of_data {
 static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
 		struct page *ipage, struct page *npage, nid_t nid)
 {
+	memset(dn, 0, sizeof(*dn));
 	dn->inode = inode;
 	dn->inode_page = ipage;
 	dn->node_page = npage;
 	dn->nid = nid;
-	dn->inode_page_locked = 0;
 }
 
 /*
@@ -877,11 +877,13 @@ bool f2fs_empty_dir(struct inode *);
  * super.c
  */
 int f2fs_sync_fs(struct super_block *, int);
+extern __printf(3, 4)
+void f2fs_msg(struct super_block *, const char *, const char *, ...);
 
 /*
  * hash.c
  */
-f2fs_hash_t f2fs_dentry_hash(const char *, int);
+f2fs_hash_t f2fs_dentry_hash(const char *, size_t);
 
 /*
  * node.c
@@ -912,7 +914,7 @@ int restore_node_summary(struct f2fs_sb_info *, unsigned int,
 void flush_nat_entries(struct f2fs_sb_info *);
 int build_node_manager(struct f2fs_sb_info *);
 void destroy_node_manager(struct f2fs_sb_info *);
-int create_node_manager_caches(void);
+int __init create_node_manager_caches(void);
 void destroy_node_manager_caches(void);
 
 /*
@@ -964,7 +966,7 @@ void sync_dirty_dir_inodes(struct f2fs_sb_info *);
 void block_operations(struct f2fs_sb_info *);
 void write_checkpoint(struct f2fs_sb_info *, bool, bool);
 void init_orphan_info(struct f2fs_sb_info *);
-int create_checkpoint_caches(void);
+int __init create_checkpoint_caches(void);
 void destroy_checkpoint_caches(void);
 
 /*
@@ -984,9 +986,9 @@ int do_write_data_page(struct page *);
 int start_gc_thread(struct f2fs_sb_info *);
 void stop_gc_thread(struct f2fs_sb_info *);
 block_t start_bidx_of_node(unsigned int);
-int f2fs_gc(struct f2fs_sb_info *, int);
+int f2fs_gc(struct f2fs_sb_info *);
 void build_gc_manager(struct f2fs_sb_info *);
-int create_gc_caches(void);
+int __init create_gc_caches(void);
 void destroy_gc_caches(void);
 
 /*
@@ -1058,7 +1060,8 @@ struct f2fs_stat_info {
 
 int f2fs_build_stats(struct f2fs_sb_info *);
 void f2fs_destroy_stats(struct f2fs_sb_info *);
-void destroy_root_stats(void);
+void __init f2fs_create_root_stats(void);
+void f2fs_destroy_root_stats(void);
 #else
 #define stat_inc_call_count(si)
 #define stat_inc_seg_count(si, type)
@@ -1068,7 +1071,8 @@ void destroy_root_stats(void);
 
 static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
 static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
-static inline void destroy_root_stats(void) { }
+static inline void __init f2fs_create_root_stats(void) { }
+static inline void f2fs_destroy_root_stats(void) { }
 #endif
 
 extern const struct file_operations f2fs_dir_operations;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index f9e085dfb1f0..3191b52aafb0 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -96,8 +96,9 @@ out:
 }
 
 static const struct vm_operations_struct f2fs_file_vm_ops = {
-	.fault        = filemap_fault,
-	.page_mkwrite = f2fs_vm_page_mkwrite,
+	.fault		= filemap_fault,
+	.page_mkwrite	= f2fs_vm_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 };
 
 static int need_to_sync_dir(struct f2fs_sb_info *sbi, struct inode *inode)
@@ -137,6 +138,9 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (ret)
 		return ret;
 
+	/* guarantee free sections for fsync */
+	f2fs_balance_fs(sbi);
+
 	mutex_lock(&inode->i_mutex);
 
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
@@ -160,15 +164,17 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (need_to_sync_dir(sbi, inode))
 		need_cp = true;
 
-	f2fs_write_inode(inode, NULL);
-
 	if (need_cp) {
 		/* all the dirty node pages should be flushed for POR */
 		ret = f2fs_sync_fs(inode->i_sb, 1);
 		clear_inode_flag(F2FS_I(inode), FI_NEED_CP);
 	} else {
-		while (sync_node_pages(sbi, inode->i_ino, &wbc) == 0)
-			f2fs_write_inode(inode, NULL);
+		/* if there is no written node page, write its inode page */
+		while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
+			ret = f2fs_write_inode(inode, NULL);
+			if (ret)
+				goto out;
+		}
 		filemap_fdatawait_range(sbi->node_inode->i_mapping,
 							0, LONG_MAX);
 	}
@@ -405,6 +411,8 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 		struct dnode_of_data dn;
 		struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
+		f2fs_balance_fs(sbi);
+
 		mutex_lock_op(sbi, DATA_TRUNC);
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
 		err = get_dnode_of_data(&dn, index, RDONLY_NODE);
@@ -532,7 +540,6 @@ static long f2fs_fallocate(struct file *file, int mode,
 				loff_t offset, loff_t len)
 {
 	struct inode *inode = file->f_path.dentry->d_inode;
-	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	long ret;
 
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
@@ -543,7 +550,10 @@ static long f2fs_fallocate(struct file *file, int mode,
 	else
 		ret = expand_inode_data(inode, offset, len, mode);
 
-	f2fs_balance_fs(sbi);
+	if (!ret) {
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		mark_inode_dirty(inode);
+	}
 	return ret;
 }
 
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 644aa3808273..c386910dacc5 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -78,7 +78,7 @@ static int gc_thread_func(void *data)
 
 		sbi->bg_gc++;
 
-		if (f2fs_gc(sbi, 1) == GC_NONE)
+		if (f2fs_gc(sbi) == GC_NONE)
 			wait_ms = GC_THREAD_NOGC_SLEEP_TIME;
 		else if (wait_ms == GC_THREAD_NOGC_SLEEP_TIME)
 			wait_ms = GC_THREAD_MAX_SLEEP_TIME;
@@ -390,9 +390,7 @@ next_step:
 		}
 
 		err = check_valid_map(sbi, segno, off);
-		if (err == GC_ERROR)
-			return err;
-		else if (err == GC_NEXT)
+		if (err == GC_NEXT)
 			continue;
 
 		if (initial) {
@@ -426,32 +424,30 @@ next_step:
 }
 
 /*
- * Calculate start block index that this node page contains
+ * Calculate start block index indicating the given node offset.
+ * Be careful, caller should give this node offset only indicating direct node
+ * blocks. If any node offsets, which point the other types of node blocks such
+ * as indirect or double indirect node blocks, are given, it must be a caller's
+ * bug.
  */
 block_t start_bidx_of_node(unsigned int node_ofs)
 {
-	block_t start_bidx;
-	unsigned int bidx, indirect_blks;
-	int dec;
+	unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
+	unsigned int bidx;
 
-	indirect_blks = 2 * NIDS_PER_BLOCK + 4;
+	if (node_ofs == 0)
+		return 0;
 
-	start_bidx = 1;
-	if (node_ofs == 0) {
-		start_bidx = 0;
-	} else if (node_ofs <= 2) {
+	if (node_ofs <= 2) {
 		bidx = node_ofs - 1;
 	} else if (node_ofs <= indirect_blks) {
-		dec = (node_ofs - 4) / (NIDS_PER_BLOCK + 1);
+		int dec = (node_ofs - 4) / (NIDS_PER_BLOCK + 1);
 		bidx = node_ofs - 2 - dec;
 	} else {
-		dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
+		int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
 		bidx = node_ofs - 5 - dec;
 	}
-
-	if (start_bidx)
-		start_bidx = bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE;
-	return start_bidx;
+	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE;
 }
 
 static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
@@ -556,9 +552,7 @@ next_step:
 		}
 
 		err = check_valid_map(sbi, segno, off);
-		if (err == GC_ERROR)
-			goto stop;
-		else if (err == GC_NEXT)
+		if (err == GC_NEXT)
 			continue;
 
 		if (phase == 0) {
@@ -568,9 +562,7 @@ next_step:
 
 		/* Get an inode by ino with checking validity */
 		err = check_dnode(sbi, entry, &dni, start_addr + off, &nofs);
-		if (err == GC_ERROR)
-			goto stop;
-		else if (err == GC_NEXT)
+		if (err == GC_NEXT)
 			continue;
 
 		if (phase == 1) {
@@ -663,62 +655,44 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
 	return ret;
 }
 
-int f2fs_gc(struct f2fs_sb_info *sbi, int nGC)
+int f2fs_gc(struct f2fs_sb_info *sbi)
 {
-	unsigned int segno;
-	int old_free_secs, cur_free_secs;
-	int gc_status, nfree;
 	struct list_head ilist;
+	unsigned int segno, i;
 	int gc_type = BG_GC;
+	int gc_status = GC_NONE;
 
 	INIT_LIST_HEAD(&ilist);
 gc_more:
-	nfree = 0;
-	gc_status = GC_NONE;
+	if (!(sbi->sb->s_flags & MS_ACTIVE))
+		goto stop;
 
 	if (has_not_enough_free_secs(sbi))
-		old_free_secs = reserved_sections(sbi);
-	else
-		old_free_secs = free_sections(sbi);
-
-	while (sbi->sb->s_flags & MS_ACTIVE) {
-		int i;
-		if (has_not_enough_free_secs(sbi))
-			gc_type = FG_GC;
+		gc_type = FG_GC;
 
-		cur_free_secs = free_sections(sbi) + nfree;
+	if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
+		goto stop;
 
-		/* We got free space successfully. */
-		if (nGC < cur_free_secs - old_free_secs)
-			break;
-
-		if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
+	for (i = 0; i < sbi->segs_per_sec; i++) {
+		/*
+		 * do_garbage_collect will give us three gc_status:
+		 * GC_ERROR, GC_DONE, and GC_BLOCKED.
+		 * If GC is finished uncleanly, we have to return
+		 * the victim to dirty segment list.
+		 */
+		gc_status = do_garbage_collect(sbi, segno + i, &ilist, gc_type);
+		if (gc_status != GC_DONE)
 			break;
-
-		for (i = 0; i < sbi->segs_per_sec; i++) {
-			/*
-			 * do_garbage_collect will give us three gc_status:
-			 * GC_ERROR, GC_DONE, and GC_BLOCKED.
-			 * If GC is finished uncleanly, we have to return
-			 * the victim to dirty segment list.
-			 */
-			gc_status = do_garbage_collect(sbi, segno + i,
-					&ilist, gc_type);
-			if (gc_status != GC_DONE)
-				goto stop;
-			nfree++;
-		}
 	}
-stop:
-	if (has_not_enough_free_secs(sbi) || gc_status == GC_BLOCKED) {
+	if (has_not_enough_free_secs(sbi)) {
 		write_checkpoint(sbi, (gc_status == GC_BLOCKED), false);
-		if (nfree)
+		if (has_not_enough_free_secs(sbi))
 			goto gc_more;
 	}
+stop:
 	mutex_unlock(&sbi->gc_mutex);
 
 	put_gc_inode(&ilist);
-	BUG_ON(!list_empty(&ilist));
 	return gc_status;
 }
 
@@ -727,7 +701,7 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
 	DIRTY_I(sbi)->v_ops = &default_v_ops;
 }
 
-int create_gc_caches(void)
+int __init create_gc_caches(void)
 {
 	winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes",
 			sizeof(struct inode_entry), NULL);
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index a60f04200f8b..6eb8d269b53b 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -42,7 +42,7 @@ static void TEA_transform(unsigned int buf[4], unsigned int const in[])
 	buf[1] += b1;
 }
 
-static void str2hashbuf(const char *msg, int len, unsigned int *buf, int num)
+static void str2hashbuf(const char *msg, size_t len, unsigned int *buf, int num)
 {
 	unsigned pad, val;
 	int i;
@@ -69,13 +69,17 @@ static void str2hashbuf(const char *msg, int len, unsigned int *buf, int num)
 		*buf++ = pad;
 }
 
-f2fs_hash_t f2fs_dentry_hash(const char *name, int len)
+f2fs_hash_t f2fs_dentry_hash(const char *name, size_t len)
 {
-	__u32 hash, minor_hash;
+	__u32 hash;
 	f2fs_hash_t f2fs_hash;
 	const char *p;
 	__u32 in[8], buf[4];
 
+	if ((len <= 2) && (name[0] == '.') &&
+		(name[1] == '.' || name[1] == '\0'))
+		return 0;
+
 	/* Initialize the default seed for the hash checksum functions */
 	buf[0] = 0x67452301;
 	buf[1] = 0xefcdab89;
@@ -83,15 +87,15 @@ f2fs_hash_t f2fs_dentry_hash(const char *name, int len)
 	buf[3] = 0x10325476;
 
 	p = name;
-	while (len > 0) {
+	while (1) {
 		str2hashbuf(p, len, in, 4);
 		TEA_transform(buf, in);
-		len -= 16;
 		p += 16;
+		if (len <= 16)
+			break;
+		len -= 16;
 	}
 	hash = buf[0];
-	minor_hash = buf[1];
-
 	f2fs_hash = cpu_to_le32(hash & ~F2FS_HASH_COL_BIT);
 	return f2fs_hash;
 }
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index df5fb381ebf1..794241777322 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -203,6 +203,7 @@ void update_inode(struct inode *inode, struct page *node_page)
 	ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
 	ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
 	ri->i_generation = cpu_to_le32(inode->i_generation);
+	set_cold_node(inode, node_page);
 	set_page_dirty(node_page);
 }
 
@@ -216,6 +217,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 			inode->i_ino == F2FS_META_INO(sbi))
 		return 0;
 
+	if (wbc)
+		f2fs_balance_fs(sbi);
+
 	node_page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page))
 		return PTR_ERR(node_page);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 89b7675dc377..1a49b881bac0 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -77,8 +77,8 @@ fail:
 
 static int is_multimedia_file(const unsigned char *s, const char *sub)
 {
-	int slen = strlen(s);
-	int sublen = strlen(sub);
+	size_t slen = strlen(s);
+	size_t sublen = strlen(sub);
 	int ret;
 
 	if (sublen > slen)
@@ -123,6 +123,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	nid_t ino = 0;
 	int err;
 
+	f2fs_balance_fs(sbi);
+
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -144,8 +146,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	if (!sbi->por_doing)
 		d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
-
-	f2fs_balance_fs(sbi);
 	return 0;
 out:
 	clear_nlink(inode);
@@ -163,6 +163,8 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	int err;
 
+	f2fs_balance_fs(sbi);
+
 	inode->i_ctime = CURRENT_TIME;
 	atomic_inc(&inode->i_count);
 
@@ -172,8 +174,6 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 		goto out;
 
 	d_instantiate(dentry, inode);
-
-	f2fs_balance_fs(sbi);
 	return 0;
 out:
 	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
@@ -223,6 +223,8 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 	struct page *page;
 	int err = -ENOENT;
 
+	f2fs_balance_fs(sbi);
+
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
 	if (!de)
 		goto fail;
@@ -238,7 +240,6 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 
 	/* In order to evict this inode,  we set it dirty */
 	mark_inode_dirty(inode);
-	f2fs_balance_fs(sbi);
 fail:
 	return err;
 }
@@ -249,9 +250,11 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	struct super_block *sb = dir->i_sb;
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct inode *inode;
-	unsigned symlen = strlen(symname) + 1;
+	size_t symlen = strlen(symname) + 1;
 	int err;
 
+	f2fs_balance_fs(sbi);
+
 	inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -268,9 +271,6 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
-
-	f2fs_balance_fs(sbi);
-
 	return err;
 out:
 	clear_nlink(inode);
@@ -286,6 +286,8 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct inode *inode;
 	int err;
 
+	f2fs_balance_fs(sbi);
+
 	inode = f2fs_new_inode(dir, S_IFDIR | mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -305,7 +307,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
 
-	f2fs_balance_fs(sbi);
 	return 0;
 
 out_fail:
@@ -336,6 +337,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	if (!new_valid_dev(rdev))
 		return -EINVAL;
 
+	f2fs_balance_fs(sbi);
+
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -350,9 +353,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	alloc_nid_done(sbi, inode->i_ino);
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
-
-	f2fs_balance_fs(sbi);
-
 	return 0;
 out:
 	clear_nlink(inode);
@@ -376,6 +376,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct f2fs_dir_entry *new_entry;
 	int err = -ENOENT;
 
+	f2fs_balance_fs(sbi);
+
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry)
 		goto out;
@@ -441,8 +443,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 
 	mutex_unlock_op(sbi, RENAME);
-
-	f2fs_balance_fs(sbi);
 	return 0;
 
 out_dir:
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 19870361497e..9bda63c9c166 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -484,12 +484,14 @@ static void truncate_node(struct dnode_of_data *dn)
 	struct node_info ni;
 
 	get_node_info(sbi, dn->nid, &ni);
+	if (dn->inode->i_blocks == 0) {
+		BUG_ON(ni.blk_addr != NULL_ADDR);
+		goto invalidate;
+	}
 	BUG_ON(ni.blk_addr == NULL_ADDR);
 
-	if (ni.blk_addr != NULL_ADDR)
-		invalidate_blocks(sbi, ni.blk_addr);
-
 	/* Deallocate node address */
+	invalidate_blocks(sbi, ni.blk_addr);
 	dec_valid_node_count(sbi, dn->inode, 1);
 	set_node_addr(sbi, &ni, NULL_ADDR);
 
@@ -499,7 +501,7 @@ static void truncate_node(struct dnode_of_data *dn)
 	} else {
 		sync_inode_page(dn);
 	}
-
+invalidate:
 	clear_node_page_dirty(dn->node_page);
 	F2FS_SET_SB_DIRT(sbi);
 
@@ -768,20 +770,12 @@ int remove_inode_page(struct inode *inode)
 		dn.inode_page_locked = 1;
 		truncate_node(&dn);
 	}
-	if (inode->i_blocks == 1) {
-		/* inernally call f2fs_put_page() */
-		set_new_dnode(&dn, inode, page, page, ino);
-		truncate_node(&dn);
-	} else if (inode->i_blocks == 0) {
-		struct node_info ni;
-		get_node_info(sbi, inode->i_ino, &ni);
 
-		/* called after f2fs_new_inode() is failed */
-		BUG_ON(ni.blk_addr != NULL_ADDR);
-		f2fs_put_page(page, 1);
-	} else {
-		BUG();
-	}
+	/* 0 is possible, after f2fs_new_inode() is failed */
+	BUG_ON(inode->i_blocks != 0 && inode->i_blocks != 1);
+	set_new_dnode(&dn, inode, page, page, ino);
+	truncate_node(&dn);
+
 	mutex_unlock_op(sbi, NODE_TRUNC);
 	return 0;
 }
@@ -834,17 +828,18 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs)
 		goto fail;
 	}
 	set_node_addr(sbi, &new_ni, NEW_ADDR);
+	set_cold_node(dn->inode, page);
 
 	dn->node_page = page;
 	sync_inode_page(dn);
 	set_page_dirty(page);
-	set_cold_node(dn->inode, page);
 	if (ofs == 0)
 		inc_valid_inode_count(sbi);
 
 	return page;
 
 fail:
+	clear_node_page_dirty(page);
 	f2fs_put_page(page, 1);
 	return ERR_PTR(err);
 }
@@ -1093,7 +1088,6 @@ static int f2fs_write_node_page(struct page *page,
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
 	nid_t nid;
-	unsigned int nofs;
 	block_t new_addr;
 	struct node_info ni;
 
@@ -1110,7 +1104,6 @@ static int f2fs_write_node_page(struct page *page,
 
 	/* get old block addr of this node page */
 	nid = nid_of_node(page);
-	nofs = ofs_of_node(page);
 	BUG_ON(page->index != nid);
 
 	get_node_info(sbi, nid, &ni);
@@ -1131,6 +1124,12 @@ static int f2fs_write_node_page(struct page *page,
 	return 0;
 }
 
+/*
+ * It is very important to gather dirty pages and write at once, so that we can
+ * submit a big bio without interfering other data writes.
+ * Be default, 512 pages (2MB), a segment size, is quite reasonable.
+ */
+#define COLLECT_DIRTY_NODES	512
 static int f2fs_write_node_pages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
@@ -1138,17 +1137,16 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	struct block_device *bdev = sbi->sb->s_bdev;
 	long nr_to_write = wbc->nr_to_write;
 
-	if (wbc->for_kupdate)
-		return 0;
-
-	if (get_pages(sbi, F2FS_DIRTY_NODES) == 0)
-		return 0;
-
+	/* First check balancing cached NAT entries */
 	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK)) {
 		write_checkpoint(sbi, false, false);
 		return 0;
 	}
 
+	/* collect a number of dirty node pages and write together */
+	if (get_pages(sbi, F2FS_DIRTY_NODES) < COLLECT_DIRTY_NODES)
+		return 0;
+
 	/* if mounting is failed, skip writing node pages */
 	wbc->nr_to_write = bio_get_nr_vecs(bdev);
 	sync_node_pages(sbi, 0, wbc);
@@ -1571,7 +1569,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 		nid_t nid;
 		struct f2fs_nat_entry raw_ne;
 		int offset = -1;
-		block_t old_blkaddr, new_blkaddr;
+		block_t new_blkaddr;
 
 		ne = list_entry(cur, struct nat_entry, list);
 		nid = nat_get_nid(ne);
@@ -1585,7 +1583,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 		offset = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 1);
 		if (offset >= 0) {
 			raw_ne = nat_in_journal(sum, offset);
-			old_blkaddr = le32_to_cpu(raw_ne.block_addr);
 			goto flush_now;
 		}
 to_nat_page:
@@ -1607,7 +1604,6 @@ to_nat_page:
 
 		BUG_ON(!nat_blk);
 		raw_ne = nat_blk->entries[nid - start_nid];
-		old_blkaddr = le32_to_cpu(raw_ne.block_addr);
 flush_now:
 		new_blkaddr = nat_get_blkaddr(ne);
 
@@ -1741,7 +1737,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 	kfree(nm_i);
 }
 
-int create_node_manager_caches(void)
+int __init create_node_manager_caches(void)
 {
 	nat_entry_slab = f2fs_kmem_cache_create("nat_entry",
 			sizeof(struct nat_entry), NULL);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index b07e9b6ef376..f42e4060b399 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -67,7 +67,7 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
 		kunmap(page);
 		f2fs_put_page(page, 0);
 	} else {
-		f2fs_add_link(&dent, inode);
+		err = f2fs_add_link(&dent, inode);
 	}
 	iput(dir);
 out:
@@ -144,14 +144,14 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 				goto out;
 			}
 
-			INIT_LIST_HEAD(&entry->list);
-			list_add_tail(&entry->list, head);
-
 			entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
 			if (IS_ERR(entry->inode)) {
 				err = PTR_ERR(entry->inode);
+				kmem_cache_free(fsync_entry_slab, entry);
 				goto out;
 			}
+
+			list_add_tail(&entry->list, head);
 			entry->blkaddr = blkaddr;
 		}
 		if (IS_INODE(page)) {
@@ -173,10 +173,9 @@ out:
 static void destroy_fsync_dnodes(struct f2fs_sb_info *sbi,
 					struct list_head *head)
 {
-	struct list_head *this;
-	struct fsync_inode_entry *entry;
-	list_for_each(this, head) {
-		entry = list_entry(this, struct fsync_inode_entry, list);
+	struct fsync_inode_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, head, list) {
 		iput(entry->inode);
 		list_del(&entry->list);
 		kmem_cache_free(fsync_entry_slab, entry);
@@ -228,6 +227,9 @@ static void check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 
 	/* Deallocate previous index in the node page */
 	inode = f2fs_iget_nowait(sbi->sb, ino);
+	if (IS_ERR(inode))
+		return;
+
 	truncate_hole(inode, bidx, bidx + 1);
 	iput(inode);
 }
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 1b26e4ea1016..4b0099066582 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -12,57 +12,26 @@
 #include <linux/f2fs_fs.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/prefetch.h>
 #include <linux/vmalloc.h>
 
 #include "f2fs.h"
 #include "segment.h"
 #include "node.h"
 
-static int need_to_flush(struct f2fs_sb_info *sbi)
-{
-	unsigned int pages_per_sec = (1 << sbi->log_blocks_per_seg) *
-			sbi->segs_per_sec;
-	int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1)
-		>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
-	int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1)
-		>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
-
-	if (sbi->por_doing)
-		return 0;
-
-	if (free_sections(sbi) <= (node_secs + 2 * dent_secs +
-						reserved_sections(sbi)))
-		return 1;
-	return 0;
-}
-
 /*
  * This function balances dirty node and dentry pages.
  * In addition, it controls garbage collection.
  */
 void f2fs_balance_fs(struct f2fs_sb_info *sbi)
 {
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = LONG_MAX,
-		.for_reclaim = 0,
-	};
-
-	if (sbi->por_doing)
-		return;
-
 	/*
-	 * We should do checkpoint when there are so many dirty node pages
-	 * with enough free segments. After then, we should do GC.
+	 * We should do GC or end up with checkpoint, if there are so many dirty
+	 * dir/node pages without enough free segments.
 	 */
-	if (need_to_flush(sbi)) {
-		sync_dirty_dir_inodes(sbi);
-		sync_node_pages(sbi, 0, &wbc);
-	}
-
 	if (has_not_enough_free_secs(sbi)) {
 		mutex_lock(&sbi->gc_mutex);
-		f2fs_gc(sbi, 1);
+		f2fs_gc(sbi);
 	}
 }
 
@@ -631,7 +600,6 @@ static void f2fs_end_io_write(struct bio *bio, int err)
 			if (page->mapping)
 				set_bit(AS_EIO, &page->mapping->flags);
 			set_ckpt_flags(p->sbi->ckpt, CP_ERROR_FLAG);
-			set_page_dirty(page);
 		}
 		end_page_writeback(page);
 		dec_page_count(p->sbi, F2FS_WRITEBACK);
@@ -791,11 +759,10 @@ static int __get_segment_type(struct page *page, enum page_type p_type)
 		return __get_segment_type_2(page, p_type);
 	case 4:
 		return __get_segment_type_4(page, p_type);
-	case 6:
-		return __get_segment_type_6(page, p_type);
-	default:
-		BUG();
 	}
+	/* NR_CURSEG_TYPE(6) logs by default */
+	BUG_ON(sbi->active_logs != NR_CURSEG_TYPE);
+	return __get_segment_type_6(page, p_type);
 }
 
 static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
@@ -1608,7 +1575,6 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < NR_DIRTY_TYPE; i++) {
 		dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL);
-		dirty_i->nr_dirty[i] = 0;
 		if (!dirty_i->dirty_segmap[i])
 			return -ENOMEM;
 	}
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 0948405af6f5..66a288a52fd3 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -459,7 +459,20 @@ static inline int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
 
 static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi)
 {
-	return free_sections(sbi) <= reserved_sections(sbi);
+	unsigned int pages_per_sec = (1 << sbi->log_blocks_per_seg) *
+			sbi->segs_per_sec;
+	int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1)
+			>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+	int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1)
+			>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+
+	if (sbi->por_doing)
+		return false;
+
+	if (free_sections(sbi) <= (node_secs + 2 * dent_secs +
+						reserved_sections(sbi)))
+		return true;
+	return false;
 }
 
 static inline int utilization(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 13867322cf5a..37fad04c8669 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -53,6 +53,18 @@ static match_table_t f2fs_tokens = {
 	{Opt_err, NULL},
 };
 
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
+	va_end(args);
+}
+
 static void init_once(void *foo)
 {
 	struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;
@@ -119,15 +131,16 @@ static void f2fs_put_super(struct super_block *sb)
 int f2fs_sync_fs(struct super_block *sb, int sync)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	int ret = 0;
 
 	if (!sbi->s_dirty && !get_pages(sbi, F2FS_DIRTY_NODES))
 		return 0;
 
 	if (sync)
 		write_checkpoint(sbi, false, false);
+	else
+		f2fs_balance_fs(sbi);
 
-	return ret;
+	return 0;
 }
 
 static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -148,8 +161,8 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
 	buf->f_bavail = user_block_count - valid_user_blocks(sbi);
 
-	buf->f_files = valid_inode_count(sbi);
-	buf->f_ffree = sbi->total_node_count - valid_node_count(sbi);
+	buf->f_files = sbi->total_node_count;
+	buf->f_ffree = sbi->total_node_count - valid_inode_count(sbi);
 
 	buf->f_namelen = F2FS_MAX_NAME_LEN;
 	buf->f_fsid.val[0] = (u32)id;
@@ -248,7 +261,8 @@ static const struct export_operations f2fs_export_ops = {
 	.get_parent = f2fs_get_parent,
 };
 
-static int parse_options(struct f2fs_sb_info *sbi, char *options)
+static int parse_options(struct super_block *sb, struct f2fs_sb_info *sbi,
+				char *options)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *p;
@@ -287,7 +301,8 @@ static int parse_options(struct f2fs_sb_info *sbi, char *options)
 			break;
 #else
 		case Opt_nouser_xattr:
-			pr_info("nouser_xattr options not supported\n");
+			f2fs_msg(sb, KERN_INFO,
+				"nouser_xattr options not supported");
 			break;
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
@@ -296,13 +311,13 @@ static int parse_options(struct f2fs_sb_info *sbi, char *options)
 			break;
 #else
 		case Opt_noacl:
-			pr_info("noacl options not supported\n");
+			f2fs_msg(sb, KERN_INFO, "noacl options not supported");
 			break;
 #endif
 		case Opt_active_logs:
 			if (args->from && match_int(args, &arg))
 				return -EINVAL;
-			if (arg != 2 && arg != 4 && arg != 6)
+			if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE)
 				return -EINVAL;
 			sbi->active_logs = arg;
 			break;
@@ -310,8 +325,9 @@ static int parse_options(struct f2fs_sb_info *sbi, char *options)
 			set_opt(sbi, DISABLE_EXT_IDENTIFY);
 			break;
 		default:
-			pr_err("Unrecognized mount option \"%s\" or missing value\n",
-					p);
+			f2fs_msg(sb, KERN_ERR,
+				"Unrecognized mount option \"%s\" or missing value",
+				p);
 			return -EINVAL;
 		}
 	}
@@ -338,23 +354,36 @@ static loff_t max_file_size(unsigned bits)
 	return result;
 }
 
-static int sanity_check_raw_super(struct f2fs_super_block *raw_super)
+static int sanity_check_raw_super(struct super_block *sb,
+			struct f2fs_super_block *raw_super)
 {
 	unsigned int blocksize;
 
-	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic))
+	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
+		f2fs_msg(sb, KERN_INFO,
+			"Magic Mismatch, valid(0x%x) - read(0x%x)",
+			F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
 		return 1;
+	}
 
 	/* Currently, support only 4KB block size */
 	blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
-	if (blocksize != PAGE_CACHE_SIZE)
+	if (blocksize != PAGE_CACHE_SIZE) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid blocksize (%u), supports only 4KB\n",
+			blocksize);
 		return 1;
+	}
 	if (le32_to_cpu(raw_super->log_sectorsize) !=
-					F2FS_LOG_SECTOR_SIZE)
+					F2FS_LOG_SECTOR_SIZE) {
+		f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
 		return 1;
+	}
 	if (le32_to_cpu(raw_super->log_sectors_per_block) !=
-					F2FS_LOG_SECTORS_PER_BLOCK)
+					F2FS_LOG_SECTORS_PER_BLOCK) {
+		f2fs_msg(sb, KERN_INFO, "Invalid log sectors per block");
 		return 1;
+	}
 	return 0;
 }
 
@@ -414,14 +443,17 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sbi)
 		return -ENOMEM;
 
-	/* set a temporary block size */
-	if (!sb_set_blocksize(sb, F2FS_BLKSIZE))
+	/* set a block size */
+	if (!sb_set_blocksize(sb, F2FS_BLKSIZE)) {
+		f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
 		goto free_sbi;
+	}
 
 	/* read f2fs raw super block */
 	raw_super_buf = sb_bread(sb, 0);
 	if (!raw_super_buf) {
 		err = -EIO;
+		f2fs_msg(sb, KERN_ERR, "unable to read superblock");
 		goto free_sbi;
 	}
 	raw_super = (struct f2fs_super_block *)
@@ -439,12 +471,14 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	set_opt(sbi, POSIX_ACL);
 #endif
 	/* parse mount options */
-	if (parse_options(sbi, (char *)data))
+	if (parse_options(sb, sbi, (char *)data))
 		goto free_sb_buf;
 
 	/* sanity checking of raw super */
-	if (sanity_check_raw_super(raw_super))
+	if (sanity_check_raw_super(sb, raw_super)) {
+		f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem");
 		goto free_sb_buf;
+	}
 
 	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
 	sb->s_max_links = F2FS_LINK_MAX;
@@ -478,18 +512,23 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	/* get an inode for meta space */
 	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
 	if (IS_ERR(sbi->meta_inode)) {
+		f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
 		err = PTR_ERR(sbi->meta_inode);
 		goto free_sb_buf;
 	}
 
 	err = get_valid_checkpoint(sbi);
-	if (err)
+	if (err) {
+		f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
 		goto free_meta_inode;
+	}
 
 	/* sanity checking of checkpoint */
 	err = -EINVAL;
-	if (sanity_check_ckpt(raw_super, sbi->ckpt))
+	if (sanity_check_ckpt(raw_super, sbi->ckpt)) {
+		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
 		goto free_cp;
+	}
 
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
@@ -503,38 +542,41 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	INIT_LIST_HEAD(&sbi->dir_inode_list);
 	spin_lock_init(&sbi->dir_inode_lock);
 
-	/* init super block */
-	if (!sb_set_blocksize(sb, sbi->blocksize))
-		goto free_cp;
-
 	init_orphan_info(sbi);
 
 	/* setup f2fs internal modules */
 	err = build_segment_manager(sbi);
-	if (err)
+	if (err) {
+		f2fs_msg(sb, KERN_ERR,
+			"Failed to initialize F2FS segment manager");
 		goto free_sm;
+	}
 	err = build_node_manager(sbi);
-	if (err)
+	if (err) {
+		f2fs_msg(sb, KERN_ERR,
+			"Failed to initialize F2FS node manager");
 		goto free_nm;
+	}
 
 	build_gc_manager(sbi);
 
 	/* get an inode for node space */
 	sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
 	if (IS_ERR(sbi->node_inode)) {
+		f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
 		err = PTR_ERR(sbi->node_inode);
 		goto free_nm;
 	}
 
 	/* if there are nt orphan nodes free them */
 	err = -EINVAL;
-	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) &&
-				recover_orphan_inodes(sbi))
+	if (recover_orphan_inodes(sbi))
 		goto free_node_inode;
 
 	/* read root inode and dentry */
 	root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
 	if (IS_ERR(root)) {
+		f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
 		err = PTR_ERR(root);
 		goto free_node_inode;
 	}
@@ -548,8 +590,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/* recover fsynced data */
-	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) &&
-				!test_opt(sbi, DISABLE_ROLL_FORWARD))
+	if (!test_opt(sbi, DISABLE_ROLL_FORWARD))
 		recover_fsync_data(sbi);
 
 	/* After POR, we can run background GC thread */
@@ -599,7 +640,7 @@ static struct file_system_type f2fs_fs_type = {
 	.fs_flags	= FS_REQUIRES_DEV,
 };
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
 			sizeof(struct f2fs_inode_info), NULL);
@@ -634,14 +675,17 @@ static int __init init_f2fs_fs(void)
 	err = create_checkpoint_caches();
 	if (err)
 		goto fail;
-	return register_filesystem(&f2fs_fs_type);
+	err = register_filesystem(&f2fs_fs_type);
+	if (err)
+		goto fail;
+	f2fs_create_root_stats();
 fail:
 	return err;
 }
 
 static void __exit exit_f2fs_fs(void)
 {
-	destroy_root_stats();
+	f2fs_destroy_root_stats();
 	unregister_filesystem(&f2fs_fs_type);
 	destroy_checkpoint_caches();
 	destroy_gc_caches();
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 7d52e8dc0c59..8038c0496504 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -208,7 +208,7 @@ int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
 	struct page *page;
 	void *base_addr;
 	int error = 0, found = 0;
-	int value_len, name_len;
+	size_t value_len, name_len;
 
 	if (name == NULL)
 		return -EINVAL;
@@ -304,7 +304,8 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 	struct f2fs_xattr_entry *here, *last;
 	struct page *page;
 	void *base_addr;
-	int error, found, free, name_len, newsize;
+	int error, found, free, newsize;
+	size_t name_len;
 	char *pval;
 
 	if (name == NULL)
@@ -317,6 +318,8 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 	if (name_len > 255 || value_len > MAX_VALUE_LEN)
 		return -ERANGE;
 
+	f2fs_balance_fs(sbi);
+
 	mutex_lock_op(sbi, NODE_NEW);
 	if (!fi->i_xattr_nid) {
 		/* Allocate new attribute block */
diff --git a/fs/file.c b/fs/file.c
index 15cb8618e95d..2b3570b7caeb 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -490,7 +490,7 @@ void exit_files(struct task_struct *tsk)
 	}
 }
 
-static void __devinit fdtable_defer_list_init(int cpu)
+static void fdtable_defer_list_init(int cpu)
 {
 	struct fdtable_defer *fddef = &per_cpu(fdtable_defer_list, cpu);
 	spin_lock_init(&fddef->lock);
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 0cf160a94eda..1b2f6c2c3aaf 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -4,12 +4,24 @@ config FUSE_FS
 	  With FUSE it is possible to implement a fully functional filesystem
 	  in a userspace program.
 
-	  There's also companion library: libfuse.  This library along with
-	  utilities is available from the FUSE homepage:
+	  There's also a companion library: libfuse2.  This library is available
+	  from the FUSE homepage:
 	  <http://fuse.sourceforge.net/>
+	  although chances are your distribution already has that library
+	  installed if you've installed the "fuse" package itself.
 
 	  See <file:Documentation/filesystems/fuse.txt> for more information.
 	  See <file:Documentation/Changes> for needed library/utility version.
 
 	  If you want to develop a userspace FS, or if you want to use
 	  a filesystem based on FUSE, answer Y or M.
+
+config CUSE
+	tristate "Character device in Userspace support"
+	depends on FUSE_FS
+	help
+	  This FUSE extension allows character devices to be
+	  implemented in userspace.
+
+	  If you want to develop or use a userspace character device
+	  based on CUSE, answer Y or M.
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index ee8d55042298..e397b675b029 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -45,7 +45,6 @@
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/spinlock.h>
 #include <linux/stat.h>
 #include <linux/module.h>
 
@@ -63,7 +62,7 @@ struct cuse_conn {
 	bool			unrestricted_ioctl;
 };
 
-static DEFINE_SPINLOCK(cuse_lock);		/* protects cuse_conntbl */
+static DEFINE_MUTEX(cuse_lock);		/* protects registration */
 static struct list_head cuse_conntbl[CUSE_CONNTBL_LEN];
 static struct class *cuse_class;
 
@@ -114,14 +113,14 @@ static int cuse_open(struct inode *inode, struct file *file)
 	int rc;
 
 	/* look up and get the connection */
-	spin_lock(&cuse_lock);
+	mutex_lock(&cuse_lock);
 	list_for_each_entry(pos, cuse_conntbl_head(devt), list)
 		if (pos->dev->devt == devt) {
 			fuse_conn_get(&pos->fc);
 			cc = pos;
 			break;
 		}
-	spin_unlock(&cuse_lock);
+	mutex_unlock(&cuse_lock);
 
 	/* dead? */
 	if (!cc)
@@ -267,7 +266,7 @@ static int cuse_parse_one(char **pp, char *end, char **keyp, char **valp)
 static int cuse_parse_devinfo(char *p, size_t len, struct cuse_devinfo *devinfo)
 {
 	char *end = p + len;
-	char *key, *val;
+	char *uninitialized_var(key), *uninitialized_var(val);
 	int rc;
 
 	while (true) {
@@ -305,14 +304,14 @@ static void cuse_gendev_release(struct device *dev)
  */
 static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 {
-	struct cuse_conn *cc = fc_to_cc(fc);
+	struct cuse_conn *cc = fc_to_cc(fc), *pos;
 	struct cuse_init_out *arg = req->out.args[0].value;
 	struct page *page = req->pages[0];
 	struct cuse_devinfo devinfo = { };
 	struct device *dev;
 	struct cdev *cdev;
 	dev_t devt;
-	int rc;
+	int rc, i;
 
 	if (req->out.h.error ||
 	    arg->major != FUSE_KERNEL_VERSION || arg->minor < 11) {
@@ -356,15 +355,24 @@ static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 	dev_set_drvdata(dev, cc);
 	dev_set_name(dev, "%s", devinfo.name);
 
+	mutex_lock(&cuse_lock);
+
+	/* make sure the device-name is unique */
+	for (i = 0; i < CUSE_CONNTBL_LEN; ++i) {
+		list_for_each_entry(pos, &cuse_conntbl[i], list)
+			if (!strcmp(dev_name(pos->dev), dev_name(dev)))
+				goto err_unlock;
+	}
+
 	rc = device_add(dev);
 	if (rc)
-		goto err_device;
+		goto err_unlock;
 
 	/* register cdev */
 	rc = -ENOMEM;
 	cdev = cdev_alloc();
 	if (!cdev)
-		goto err_device;
+		goto err_unlock;
 
 	cdev->owner = THIS_MODULE;
 	cdev->ops = &cuse_frontend_fops;
@@ -377,9 +385,8 @@ static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 	cc->cdev = cdev;
 
 	/* make the device available */
-	spin_lock(&cuse_lock);
 	list_add(&cc->list, cuse_conntbl_head(devt));
-	spin_unlock(&cuse_lock);
+	mutex_unlock(&cuse_lock);
 
 	/* announce device availability */
 	dev_set_uevent_suppress(dev, 0);
@@ -391,7 +398,8 @@ out:
 
 err_cdev:
 	cdev_del(cdev);
-err_device:
+err_unlock:
+	mutex_unlock(&cuse_lock);
 	put_device(dev);
 err_region:
 	unregister_chrdev_region(devt, 1);
@@ -520,9 +528,9 @@ static int cuse_channel_release(struct inode *inode, struct file *file)
 	int rc;
 
 	/* remove from the conntbl, no more access from this point on */
-	spin_lock(&cuse_lock);
+	mutex_lock(&cuse_lock);
 	list_del_init(&cc->list);
-	spin_unlock(&cuse_lock);
+	mutex_unlock(&cuse_lock);
 
 	/* remove device */
 	if (cc->dev)
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index c16335315e5d..e83351aa5bad 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -692,8 +692,6 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 	struct page *oldpage = *pagep;
 	struct page *newpage;
 	struct pipe_buffer *buf = cs->pipebufs;
-	struct address_space *mapping;
-	pgoff_t index;
 
 	unlock_request(cs->fc, cs->req);
 	fuse_copy_finish(cs);
@@ -724,9 +722,6 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 	if (fuse_check_page(newpage) != 0)
 		goto out_fallback_unlock;
 
-	mapping = oldpage->mapping;
-	index = oldpage->index;
-
 	/*
 	 * This is a new and locked page, it shouldn't be mapped or
 	 * have any special flags on it
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e21d4d8f87e3..f3ab824fa302 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2177,8 +2177,8 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	return ret;
 }
 
-long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
-			    loff_t length)
+static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
+				loff_t length)
 {
 	struct fuse_file *ff = file->private_data;
 	struct fuse_conn *fc = ff->fc;
@@ -2213,7 +2213,6 @@ long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(fuse_file_fallocate);
 
 static const struct file_operations fuse_file_operations = {
 	.llseek		= fuse_file_llseek,
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 8dad6b093716..b906ed17a839 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -241,6 +241,7 @@ static u32 make_flags(struct gfs2_glock *gl, const unsigned int gfs_flags,
 
 static void gfs2_reverse_hex(char *c, u64 value)
 {
+	*c = '0';
 	while (value) {
 		*c-- = hex_asc[value & 0x0f];
 		value >>= 4;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 37ee061d899e..b7eff078fe90 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -350,10 +350,14 @@ static u32 gfs2_free_extlen(const struct gfs2_rbm *rrbm, u32 len)
 		BUG_ON(len < chunk_size);
 		len -= chunk_size;
 		block = gfs2_rbm_to_block(&rbm);
-		gfs2_rbm_from_block(&rbm, block + chunk_size);
-		n_unaligned = 3;
-		if (ptr)
+		if (gfs2_rbm_from_block(&rbm, block + chunk_size)) {
+			n_unaligned = 0;
 			break;
+		}
+		if (ptr) {
+			n_unaligned = 3;
+			break;
+		}
 		n_unaligned = len & 3;
 	}
 
@@ -557,22 +561,20 @@ void gfs2_free_clones(struct gfs2_rgrpd *rgd)
  */
 int gfs2_rs_alloc(struct gfs2_inode *ip)
 {
-	struct gfs2_blkreserv *res;
+	int error = 0;
 
+	down_write(&ip->i_rw_mutex);
 	if (ip->i_res)
-		return 0;
-
-	res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS);
-	if (!res)
-		return -ENOMEM;
+		goto out;
 
-	RB_CLEAR_NODE(&res->rs_node);
+	ip->i_res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS);
+	if (!ip->i_res) {
+		error = -ENOMEM;
+		goto out;
+	}
 
-	down_write(&ip->i_rw_mutex);
-	if (ip->i_res)
-		kmem_cache_free(gfs2_rsrv_cachep, res);
-	else
-		ip->i_res = res;
+	RB_CLEAR_NODE(&ip->i_res->rs_node);
+out:
 	up_write(&ip->i_rw_mutex);
 	return 0;
 }
@@ -1424,6 +1426,9 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
 		rs->rs_free = extlen;
 		rs->rs_inum = ip->i_no_addr;
 		rs_insert(ip);
+	} else {
+		if (goal == rgd->rd_last_alloc + rgd->rd_data0)
+			rgd->rd_last_alloc = 0;
 	}
 }
 
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index a2862339323b..81cc7eaff863 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -446,7 +446,8 @@ int __log_start_commit(journal_t *journal, tid_t target)
 	 * currently running transaction (if it exists).  Otherwise,
 	 * the target tid must be an old one.
 	 */
-	if (journal->j_running_transaction &&
+	if (journal->j_commit_request != target &&
+	    journal->j_running_transaction &&
 	    journal->j_running_transaction->t_tid == target) {
 		/*
 		 * We want a new commit: OK, mark the request and wakeup the
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index c89b26bc9759..264d1aa935f2 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -206,7 +206,7 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 
 		list_for_each_entry(lo, &server->layouts, plh_layouts) {
 			ino = igrab(lo->plh_inode);
-			if (ino)
+			if (!ino)
 				continue;
 			spin_lock(&ino->i_lock);
 			/* Is this layout in the process of being freed? */
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 32e6c53520e2..1b2d7eb93796 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2153,12 +2153,16 @@ static int nfs_open_permission_mask(int openflags)
 {
 	int mask = 0;
 
-	if ((openflags & O_ACCMODE) != O_WRONLY)
-		mask |= MAY_READ;
-	if ((openflags & O_ACCMODE) != O_RDONLY)
-		mask |= MAY_WRITE;
-	if (openflags & __FMODE_EXEC)
-		mask |= MAY_EXEC;
+	if (openflags & __FMODE_EXEC) {
+		/* ONLY check exec rights */
+		mask = MAY_EXEC;
+	} else {
+		if ((openflags & O_ACCMODE) != O_WRONLY)
+			mask |= MAY_READ;
+		if ((openflags & O_ACCMODE) != O_RDONLY)
+			mask |= MAY_WRITE;
+	}
+
 	return mask;
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5d864fb36578..cf747ef86650 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1626,7 +1626,8 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
 
 static int nfs4_opendata_access(struct rpc_cred *cred,
 				struct nfs4_opendata *opendata,
-				struct nfs4_state *state, fmode_t fmode)
+				struct nfs4_state *state, fmode_t fmode,
+				int openflags)
 {
 	struct nfs_access_entry cache;
 	u32 mask;
@@ -1638,11 +1639,14 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
 
 	mask = 0;
 	/* don't check MAY_WRITE - a newly created file may not have
-	 * write mode bits, but POSIX allows the creating process to write */
-	if (fmode & FMODE_READ)
-		mask |= MAY_READ;
-	if (fmode & FMODE_EXEC)
-		mask |= MAY_EXEC;
+	 * write mode bits, but POSIX allows the creating process to write.
+	 * use openflags to check for exec, because fmode won't
+	 * always have FMODE_EXEC set when file open for exec. */
+	if (openflags & __FMODE_EXEC) {
+		/* ONLY check for exec rights */
+		mask = MAY_EXEC;
+	} else if (fmode & FMODE_READ)
+		mask = MAY_READ;
 
 	cache.cred = cred;
 	cache.jiffies = jiffies;
@@ -1896,7 +1900,7 @@ static int _nfs4_do_open(struct inode *dir,
 	if (server->caps & NFS_CAP_POSIX_LOCK)
 		set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
 
-	status = nfs4_opendata_access(cred, opendata, state, fmode);
+	status = nfs4_opendata_access(cred, opendata, state, fmode, flags);
 	if (status != 0)
 		goto err_opendata_put;
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index e7165d915362..d00260b08103 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -254,7 +254,7 @@ static void
 pnfs_layout_set_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit)
 {
 	lo->plh_retry_timestamp = jiffies;
-	if (test_and_set_bit(fail_bit, &lo->plh_flags))
+	if (!test_and_set_bit(fail_bit, &lo->plh_flags))
 		atomic_inc(&lo->plh_refcount);
 }
 
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index b6bdb18e892c..a5e5d9899d56 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -91,12 +91,16 @@ void nfs_readdata_release(struct nfs_read_data *rdata)
 	put_nfs_open_context(rdata->args.context);
 	if (rdata->pages.pagevec != rdata->pages.page_array)
 		kfree(rdata->pages.pagevec);
-	if (rdata != &read_header->rpc_data)
-		kfree(rdata);
-	else
+	if (rdata == &read_header->rpc_data) {
 		rdata->header = NULL;
+		rdata = NULL;
+	}
 	if (atomic_dec_and_test(&hdr->refcnt))
 		hdr->completion_ops->completion(hdr);
+	/* Note: we only free the rpc_task after callbacks are done.
+	 * See the comment in rpc_free_task() for why
+	 */
+	kfree(rdata);
 }
 EXPORT_SYMBOL_GPL(nfs_readdata_release);
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index c25cadf8f8c4..2e7e8c878e5d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1152,7 +1152,7 @@ static int nfs_get_option_str(substring_t args[], char **option)
 {
 	kfree(*option);
 	*option = match_strdup(args);
-	return !option;
+	return !*option;
 }
 
 static int nfs_get_option_ul(substring_t args[], unsigned long *option)
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index b673be31590e..c483cc50b82e 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -126,12 +126,16 @@ void nfs_writedata_release(struct nfs_write_data *wdata)
 	put_nfs_open_context(wdata->args.context);
 	if (wdata->pages.pagevec != wdata->pages.page_array)
 		kfree(wdata->pages.pagevec);
-	if (wdata != &write_header->rpc_data)
-		kfree(wdata);
-	else
+	if (wdata == &write_header->rpc_data) {
 		wdata->header = NULL;
+		wdata = NULL;
+	}
 	if (atomic_dec_and_test(&hdr->refcnt))
 		hdr->completion_ops->completion(hdr);
+	/* Note: we only free the rpc_task after callbacks are done.
+	 * See the comment in rpc_free_task() for why
+	 */
+	kfree(wdata);
 }
 EXPORT_SYMBOL_GPL(nfs_writedata_release);
 
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index f883e7e74305..7003e5266f25 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -291,9 +291,8 @@ static void ramoops_free_przs(struct ramoops_context *cxt)
 	kfree(cxt->przs);
 }
 
-static int __devinit ramoops_init_przs(struct device *dev,
-				       struct ramoops_context *cxt,
-				       phys_addr_t *paddr, size_t dump_mem_sz)
+static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
+			     phys_addr_t *paddr, size_t dump_mem_sz)
 {
 	int err = -ENOMEM;
 	int i;
@@ -336,10 +335,9 @@ fail_prz:
 	return err;
 }
 
-static int __devinit ramoops_init_prz(struct device *dev,
-				      struct ramoops_context *cxt,
-				      struct persistent_ram_zone **prz,
-				      phys_addr_t *paddr, size_t sz, u32 sig)
+static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
+			    struct persistent_ram_zone **prz,
+			    phys_addr_t *paddr, size_t sz, u32 sig)
 {
 	if (!sz)
 		return 0;
@@ -367,7 +365,7 @@ static int __devinit ramoops_init_prz(struct device *dev,
 	return 0;
 }
 
-static int __devinit ramoops_probe(struct platform_device *pdev)
+static int ramoops_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct ramoops_platform_data *pdata = pdev->dev.platform_data;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index eecd2a8a84dd..0306303be372 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -390,8 +390,8 @@ static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size,
 	return 0;
 }
 
-static int __devinit persistent_ram_post_init(struct persistent_ram_zone *prz,
-					      u32 sig, int ecc_size)
+static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig,
+				    int ecc_size)
 {
 	int ret;
 
@@ -443,9 +443,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz)
 	kfree(prz);
 }
 
-struct persistent_ram_zone * __devinit persistent_ram_new(phys_addr_t start,
-							  size_t size, u32 sig,
-							  int ecc_size)
+struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
+					       u32 sig, int ecc_size)
 {
 	struct persistent_ram_zone *prz;
 	int ret = -ENOMEM;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 9d863fb501f9..f2bc3dfd0b88 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -296,7 +296,7 @@ EXPORT_SYMBOL(seq_read);
  *	seq_lseek -	->llseek() method for sequential files.
  *	@file: the file in question
  *	@offset: new position
- *	@origin: 0 for absolute, 1 for relative position
+ *	@whence: 0 for absolute, 1 for relative position
  *
  *	Ready-made ->f_op->llseek()
  */
diff --git a/fs/splice.c b/fs/splice.c
index 8890604e3fcd..6909d89d0da5 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -696,8 +696,10 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
 		return -EINVAL;
 
 	more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0;
-	if (sd->len < sd->total_len)
+
+	if (sd->len < sd->total_len && pipe->nrbufs > 1)
 		more |= MSG_SENDPAGE_NOTLAST;
+
 	return file->f_op->sendpage(file, buf->page, buf->offset,
 				    sd->len, &pos, more);
 }
diff --git a/fs/udf/super.c b/fs/udf/super.c
index d44fb568abe1..e9be396a558d 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -307,7 +307,8 @@ static void udf_sb_free_partitions(struct super_block *sb)
 {
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	int i;
-
+	if (sbi->s_partmaps == NULL)
+		return;
 	for (i = 0; i < sbi->s_partitions; i++)
 		udf_free_partition(&sbi->s_partmaps[i]);
 	kfree(sbi->s_partmaps);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 26673a0b20e7..56d1614760cf 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -175,7 +175,7 @@ xfs_buf_get_maps(
 	bp->b_map_count = map_count;
 
 	if (map_count == 1) {
-		bp->b_maps = &bp->b_map;
+		bp->b_maps = &bp->__b_map;
 		return 0;
 	}
 
@@ -193,7 +193,7 @@ static void
 xfs_buf_free_maps(
 	struct xfs_buf	*bp)
 {
-	if (bp->b_maps != &bp->b_map) {
+	if (bp->b_maps != &bp->__b_map) {
 		kmem_free(bp->b_maps);
 		bp->b_maps = NULL;
 	}
@@ -377,8 +377,8 @@ xfs_buf_allocate_memory(
 	}
 
 use_alloc_page:
-	start = BBTOB(bp->b_map.bm_bn) >> PAGE_SHIFT;
-	end = (BBTOB(bp->b_map.bm_bn + bp->b_length) + PAGE_SIZE - 1)
+	start = BBTOB(bp->b_maps[0].bm_bn) >> PAGE_SHIFT;
+	end = (BBTOB(bp->b_maps[0].bm_bn + bp->b_length) + PAGE_SIZE - 1)
 								>> PAGE_SHIFT;
 	page_count = end - start;
 	error = _xfs_buf_get_pages(bp, page_count, flags);
@@ -640,7 +640,7 @@ _xfs_buf_read(
 	xfs_buf_flags_t		flags)
 {
 	ASSERT(!(flags & XBF_WRITE));
-	ASSERT(bp->b_map.bm_bn != XFS_BUF_DADDR_NULL);
+	ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL);
 
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
@@ -1709,7 +1709,7 @@ xfs_buf_cmp(
 	struct xfs_buf	*bp = container_of(b, struct xfs_buf, b_list);
 	xfs_daddr_t		diff;
 
-	diff = ap->b_map.bm_bn - bp->b_map.bm_bn;
+	diff = ap->b_maps[0].bm_bn - bp->b_maps[0].bm_bn;
 	if (diff < 0)
 		return -1;
 	if (diff > 0)
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 23f5642480bb..433a12ed7b17 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -151,7 +151,7 @@ typedef struct xfs_buf {
 	struct page		**b_pages;	/* array of page pointers */
 	struct page		*b_page_array[XB_PAGES]; /* inline pages */
 	struct xfs_buf_map	*b_maps;	/* compound buffer map */
-	struct xfs_buf_map	b_map;		/* inline compound buffer map */
+	struct xfs_buf_map	__b_map;	/* inline compound buffer map */
 	int			b_map_count;
 	int			b_io_length;	/* IO size in BBs */
 	atomic_t		b_pin_count;	/* pin count */
@@ -330,8 +330,8 @@ void xfs_buf_stale(struct xfs_buf *bp);
  * In future, uncached buffers will pass the block number directly to the io
  * request function and hence these macros will go away at that point.
  */
-#define XFS_BUF_ADDR(bp)		((bp)->b_map.bm_bn)
-#define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_map.bm_bn = (xfs_daddr_t)(bno))
+#define XFS_BUF_ADDR(bp)		((bp)->b_maps[0].bm_bn)
+#define XFS_BUF_SET_ADDR(bp, bno)	((bp)->b_maps[0].bm_bn = (xfs_daddr_t)(bno))
 
 static inline void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
 {
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index becf4a97efc6..77b09750e92c 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -71,7 +71,7 @@ xfs_buf_item_log_debug(
 		chunk_num = byte >> XFS_BLF_SHIFT;
 		word_num = chunk_num >> BIT_TO_WORD_SHIFT;
 		bit_num = chunk_num & (NBWORD - 1);
-		wordp = &(bip->bli_format.blf_data_map[word_num]);
+		wordp = &(bip->__bli_format.blf_data_map[word_num]);
 		bit_set = *wordp & (1 << bit_num);
 		ASSERT(bit_set);
 		byte++;
@@ -237,7 +237,7 @@ xfs_buf_item_size(
 		 * cancel flag in it.
 		 */
 		trace_xfs_buf_item_size_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 		return bip->bli_format_count;
 	}
 
@@ -278,7 +278,7 @@ xfs_buf_item_format_segment(
 	uint		buffer_offset;
 
 	/* copy the flags across from the base format item */
-	blfp->blf_flags = bip->bli_format.blf_flags;
+	blfp->blf_flags = bip->__bli_format.blf_flags;
 
 	/*
 	 * Base size is the actual size of the ondisk structure - it reflects
@@ -287,6 +287,17 @@ xfs_buf_item_format_segment(
 	 */
 	base_size = offsetof(struct xfs_buf_log_format, blf_data_map) +
 			(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
+
+	nvecs = 0;
+	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+	if (!(bip->bli_flags & XFS_BLI_STALE) && first_bit == -1) {
+		/*
+		 * If the map is not be dirty in the transaction, mark
+		 * the size as zero and do not advance the vector pointer.
+		 */
+		goto out;
+	}
+
 	vecp->i_addr = blfp;
 	vecp->i_len = base_size;
 	vecp->i_type = XLOG_REG_TYPE_BFORMAT;
@@ -301,15 +312,13 @@ xfs_buf_item_format_segment(
 		 */
 		trace_xfs_buf_item_format_stale(bip);
 		ASSERT(blfp->blf_flags & XFS_BLF_CANCEL);
-		blfp->blf_size = nvecs;
-		return vecp;
+		goto out;
 	}
 
 	/*
 	 * Fill in an iovec for each set of contiguous chunks.
 	 */
-	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
-	ASSERT(first_bit != -1);
+
 	last_bit = first_bit;
 	nbits = 1;
 	for (;;) {
@@ -371,7 +380,8 @@ xfs_buf_item_format_segment(
 			nbits++;
 		}
 	}
-	bip->bli_format.blf_size = nvecs;
+out:
+	blfp->blf_size = nvecs;
 	return vecp;
 }
 
@@ -405,7 +415,7 @@ xfs_buf_item_format(
 	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
 		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
 		      xfs_log_item_in_current_chkpt(lip)))
-			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
+			bip->__bli_format.blf_flags |= XFS_BLF_INODE_BUF;
 		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
 	}
 
@@ -485,7 +495,7 @@ xfs_buf_item_unpin(
 		ASSERT(bip->bli_flags & XFS_BLI_STALE);
 		ASSERT(xfs_buf_islocked(bp));
 		ASSERT(XFS_BUF_ISSTALE(bp));
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 
 		trace_xfs_buf_item_unpin_stale(bip);
 
@@ -601,7 +611,7 @@ xfs_buf_item_unlock(
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
-	int			aborted;
+	int			aborted, clean, i;
 	uint			hold;
 
 	/* Clear the buffer's association with this transaction. */
@@ -631,7 +641,7 @@ xfs_buf_item_unlock(
 	 */
 	if (bip->bli_flags & XFS_BLI_STALE) {
 		trace_xfs_buf_item_unlock_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 		if (!aborted) {
 			atomic_dec(&bip->bli_refcount);
 			return;
@@ -644,8 +654,15 @@ xfs_buf_item_unlock(
 	 * If the buf item isn't tracking any data, free it, otherwise drop the
 	 * reference we hold to it.
 	 */
-	if (xfs_bitmap_empty(bip->bli_format.blf_data_map,
-			     bip->bli_format.blf_map_size))
+	clean = 1;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
+			     bip->bli_formats[i].blf_map_size)) {
+			clean = 0;
+			break;
+		}
+	}
+	if (clean)
 		xfs_buf_item_relse(bp);
 	else
 		atomic_dec(&bip->bli_refcount);
@@ -716,7 +733,7 @@ xfs_buf_item_get_format(
 	bip->bli_format_count = count;
 
 	if (count == 1) {
-		bip->bli_formats = &bip->bli_format;
+		bip->bli_formats = &bip->__bli_format;
 		return 0;
 	}
 
@@ -731,7 +748,7 @@ STATIC void
 xfs_buf_item_free_format(
 	struct xfs_buf_log_item	*bip)
 {
-	if (bip->bli_formats != &bip->bli_format) {
+	if (bip->bli_formats != &bip->__bli_format) {
 		kmem_free(bip->bli_formats);
 		bip->bli_formats = NULL;
 	}
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index 6850f49f4af3..16def435944a 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -104,7 +104,7 @@ typedef struct xfs_buf_log_item {
 #endif
 	int			bli_format_count;	/* count of headers */
 	struct xfs_buf_log_format *bli_formats;	/* array of in-log header ptrs */
-	struct xfs_buf_log_format bli_format;	/* embedded in-log header */
+	struct xfs_buf_log_format __bli_format;	/* embedded in-log header */
 } xfs_buf_log_item_t;
 
 void	xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 7536faaa61e7..12afe07a91d7 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -355,10 +355,12 @@ xfs_dir2_block_addname(
 	/*
 	 * If need to compact the leaf entries, do it now.
 	 */
-	if (compact)
+	if (compact) {
 		xfs_dir2_block_compact(tp, bp, hdr, btp, blp, &needlog,
 				      &lfloghigh, &lfloglow);
-	else if (btp->stale) {
+		/* recalculate blp post-compaction */
+		blp = xfs_dir2_block_leaf_p(btp);
+	} else if (btp->stale) {
 		/*
 		 * Set leaf logging boundaries to impossible state.
 		 * For the no-stale case they're set explicitly.
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 5f53e75409b8..8a59f8546552 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -784,11 +784,11 @@ xfs_qm_scall_getquota(
 	     (XFS_IS_OQUOTA_ENFORCED(mp) &&
 			(dst->d_flags & (FS_PROJ_QUOTA | FS_GROUP_QUOTA)))) &&
 	    dst->d_id != 0) {
-		if (((int) dst->d_bcount > (int) dst->d_blk_softlimit) &&
+		if ((dst->d_bcount > dst->d_blk_softlimit) &&
 		    (dst->d_blk_softlimit > 0)) {
 			ASSERT(dst->d_btimer != 0);
 		}
-		if (((int) dst->d_icount > (int) dst->d_ino_softlimit) &&
+		if ((dst->d_icount > dst->d_ino_softlimit) &&
 		    (dst->d_ino_softlimit > 0)) {
 			ASSERT(dst->d_itimer != 0);
 		}
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 4fc17d479d42..3edf5dbee001 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -93,7 +93,7 @@ _xfs_trans_bjoin(
 	xfs_buf_item_init(bp, tp->t_mountp);
 	bip = bp->b_fspriv;
 	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_CANCEL));
+	ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
 	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
 	if (reset_recur)
 		bip->bli_recur = 0;
@@ -432,7 +432,7 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 	bip = bp->b_fspriv;
 	ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
 	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_CANCEL));
+	ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 
 	trace_xfs_trans_brelse(bip);
@@ -519,7 +519,7 @@ xfs_trans_bhold(xfs_trans_t	*tp,
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_CANCEL));
+	ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 
 	bip->bli_flags |= XFS_BLI_HOLD;
@@ -539,7 +539,7 @@ xfs_trans_bhold_release(xfs_trans_t	*tp,
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
 	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_CANCEL));
+	ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 	ASSERT(bip->bli_flags & XFS_BLI_HOLD);
 
@@ -598,7 +598,7 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 		bip->bli_flags &= ~XFS_BLI_STALE;
 		ASSERT(XFS_BUF_ISSTALE(bp));
 		XFS_BUF_UNSTALE(bp);
-		bip->bli_format.blf_flags &= ~XFS_BLF_CANCEL;
+		bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL;
 	}
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
@@ -643,6 +643,7 @@ xfs_trans_binval(
 	xfs_buf_t	*bp)
 {
 	xfs_buf_log_item_t	*bip = bp->b_fspriv;
+	int			i;
 
 	ASSERT(bp->b_transp == tp);
 	ASSERT(bip != NULL);
@@ -657,8 +658,8 @@ xfs_trans_binval(
 		 */
 		ASSERT(XFS_BUF_ISSTALE(bp));
 		ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY)));
-		ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_INODE_BUF));
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_INODE_BUF));
+		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 		ASSERT(bip->bli_item.li_desc->lid_flags & XFS_LID_DIRTY);
 		ASSERT(tp->t_flags & XFS_TRANS_DIRTY);
 		return;
@@ -668,10 +669,12 @@ xfs_trans_binval(
 
 	bip->bli_flags |= XFS_BLI_STALE;
 	bip->bli_flags &= ~(XFS_BLI_INODE_BUF | XFS_BLI_LOGGED | XFS_BLI_DIRTY);
-	bip->bli_format.blf_flags &= ~XFS_BLF_INODE_BUF;
-	bip->bli_format.blf_flags |= XFS_BLF_CANCEL;
-	memset((char *)(bip->bli_format.blf_data_map), 0,
-	      (bip->bli_format.blf_map_size * sizeof(uint)));
+	bip->__bli_format.blf_flags &= ~XFS_BLF_INODE_BUF;
+	bip->__bli_format.blf_flags |= XFS_BLF_CANCEL;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		memset(bip->bli_formats[i].blf_data_map, 0,
+		       (bip->bli_formats[i].blf_map_size * sizeof(uint)));
+	}
 	bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
 	tp->t_flags |= XFS_TRANS_DIRTY;
 }
@@ -775,5 +778,5 @@ xfs_trans_dquot_buf(
 	       type == XFS_BLF_GDQUOT_BUF);
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 
-	bip->bli_format.blf_flags |= type;
+	bip->__bli_format.blf_flags |= type;
 }