24 files changed, 461 insertions, 112 deletions

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 9a0124a95851..fb3e64d37cb4 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -83,11 +83,9 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans,
 	case ACL_TYPE_ACCESS:
 		name = POSIX_ACL_XATTR_ACCESS;
 		if (acl) {
-			ret = posix_acl_equiv_mode(acl, &inode->i_mode);
-			if (ret < 0)
+			ret = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+			if (ret)
 				return ret;
-			if (ret == 0)
-				acl = NULL;
 		}
 		ret = 0;
 		break;
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 3e36e4adc4a3..9aba42b78253 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -328,8 +328,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
 		list_add_tail(&work->ordered_list, &wq->ordered_list);
 		spin_unlock_irqrestore(&wq->list_lock, flags);
 	}
-	queue_work(wq->normal_wq, &work->normal_work);
 	trace_btrfs_work_queued(work);
+	queue_work(wq->normal_wq, &work->normal_work);
 }
 
 void btrfs_queue_work(struct btrfs_workqueue *wq,
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index d453d62ab0c6..e2f659dc5745 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1417,7 +1417,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			read_extent_buffer(eb, dest + bytes_left,
 					   name_off, name_len);
 		if (eb != eb_in) {
-			btrfs_tree_read_unlock_blocking(eb);
+			if (!path->skip_locking)
+				btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
 		}
 		ret = btrfs_find_item(fs_root, path, parent, 0,
@@ -1437,9 +1438,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		if (eb != eb_in) {
-			atomic_inc(&eb->refs);
-			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			if (!path->skip_locking)
+				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			path->nodes[0] = NULL;
+			path->locks[0] = 0;
 		}
 		btrfs_release_path(path);
 		iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c473c42d7d6c..bae05c5c75ba 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -694,7 +694,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			ret = btrfs_map_bio(root, READ, comp_bio,
 					    mirror_num, 0);
 			if (ret) {
-				bio->bi_error = ret;
+				comp_bio->bi_error = ret;
 				bio_endio(comp_bio);
 			}
 
@@ -723,7 +723,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 	ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0);
 	if (ret) {
-		bio->bi_error = ret;
+		comp_bio->bi_error = ret;
 		bio_endio(comp_bio);
 	}
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 5b8e235c4b6d..0f2b7c622ce3 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1551,6 +1551,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		       trans->transid, root->fs_info->generation);
 
 	if (!should_cow_block(trans, root, buf)) {
+		trans->dirty = true;
 		*cow_ret = buf;
 		return 0;
 	}
@@ -2773,8 +2774,10 @@ again:
 			 * then we don't want to set the path blocking,
 			 * so we test it here
 			 */
-			if (!should_cow_block(trans, root, b))
+			if (!should_cow_block(trans, root, b)) {
+				trans->dirty = true;
 				goto cow_done;
+			}
 
 			/*
 			 * must have write locks on this node and the
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 35489e7129a7..1391f72c28c3 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1572,7 +1572,7 @@ struct btrfs_fs_info {
 
 	spinlock_t delayed_iput_lock;
 	struct list_head delayed_iputs;
-	struct rw_semaphore delayed_iput_sem;
+	struct mutex cleaner_delayed_iput_mutex;
 
 	/* this protects tree_mod_seq_list */
 	spinlock_t tree_mod_seq_lock;
@@ -1770,6 +1770,7 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *qgroup_rescan_workers;
 	struct completion qgroup_rescan_completion;
 	struct btrfs_work qgroup_rescan_work;
+	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
 
 	/* filesystem state */
 	unsigned long fs_state;
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index e0941fbb913c..02b934d0ee65 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1694,7 +1694,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
  *
  */
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list)
+				    struct list_head *ins_list, bool *emitted)
 {
 	struct btrfs_dir_item *di;
 	struct btrfs_delayed_item *curr, *next;
@@ -1738,6 +1738,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 
 		if (over)
 			return 1;
+		*emitted = true;
 	}
 	return 0;
 }
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index f70119f25421..0167853c84ae 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list);
+				    struct list_head *ins_list, bool *emitted);
 
 /* for init */
 int __init btrfs_delayed_inode_init(void);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 974be09e7556..85b207d19aa5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1582,8 +1582,23 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 	ret = get_anon_bdev(&root->anon_dev);
 	if (ret)
 		goto free_writers;
+
+	mutex_lock(&root->objectid_mutex);
+	ret = btrfs_find_highest_objectid(root,
+					&root->highest_objectid);
+	if (ret) {
+		mutex_unlock(&root->objectid_mutex);
+		goto free_root_dev;
+	}
+
+	ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+	mutex_unlock(&root->objectid_mutex);
+
 	return 0;
 
+free_root_dev:
+	free_anon_bdev(root->anon_dev);
 free_writers:
 	btrfs_free_subvolume_writers(root->subv_writers);
 fail:
@@ -1762,7 +1777,6 @@ static int cleaner_kthread(void *arg)
 	int again;
 	struct btrfs_trans_handle *trans;
 
-	set_freezable();
 	do {
 		again = 0;
 
@@ -1782,7 +1796,10 @@ static int cleaner_kthread(void *arg)
 			goto sleep;
 		}
 
+		mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
 		btrfs_run_delayed_iputs(root);
+		mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
+
 		again = btrfs_clean_one_deleted_snapshot(root);
 		mutex_unlock(&root->fs_info->cleaner_mutex);
 
@@ -2259,6 +2276,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
 	fs_info->quota_enabled = 0;
 	fs_info->pending_quota_state = 0;
 	fs_info->qgroup_ulist = NULL;
+	fs_info->qgroup_rescan_running = false;
 	mutex_init(&fs_info->qgroup_rescan_lock);
 }
 
@@ -2542,8 +2560,8 @@ int open_ctree(struct super_block *sb,
 	mutex_init(&fs_info->delete_unused_bgs_mutex);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
+	mutex_init(&fs_info->cleaner_delayed_iput_mutex);
 	seqlock_init(&fs_info->profiles_lock);
-	init_rwsem(&fs_info->delayed_iput_sem);
 
 	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
 	INIT_LIST_HEAD(&fs_info->space_info);
@@ -2668,6 +2686,7 @@ int open_ctree(struct super_block *sb,
 	if (btrfs_check_super_csum(bh->b_data)) {
 		printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
 		err = -EINVAL;
+		brelse(bh);
 		goto fail_alloc;
 	}
 
@@ -2900,6 +2919,18 @@ retry_root_backup:
 	tree_root->commit_root = btrfs_root_node(tree_root);
 	btrfs_set_root_refs(&tree_root->root_item, 1);
 
+	mutex_lock(&tree_root->objectid_mutex);
+	ret = btrfs_find_highest_objectid(tree_root,
+					&tree_root->highest_objectid);
+	if (ret) {
+		mutex_unlock(&tree_root->objectid_mutex);
+		goto recovery_tree_root;
+	}
+
+	ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+	mutex_unlock(&tree_root->objectid_mutex);
+
 	ret = btrfs_read_roots(fs_info, tree_root);
 	if (ret)
 		goto recovery_tree_root;
@@ -3781,7 +3812,7 @@ void close_ctree(struct btrfs_root *root)
 	smp_mb();
 
 	/* wait for the qgroup rescan worker to stop */
-	btrfs_qgroup_wait_for_completion(fs_info);
+	btrfs_qgroup_wait_for_completion(fs_info, false);
 
 	/* wait for the uuid_scan task to finish */
 	down(&fs_info->uuid_tree_rescan_sem);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c4661db2b72a..47cdc6f3390b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4086,8 +4086,10 @@ commit_trans:
 		    !atomic_read(&root->fs_info->open_ioctl_trans)) {
 			need_commit--;
 
-			if (need_commit > 0)
+			if (need_commit > 0) {
+				btrfs_start_delalloc_roots(fs_info, 0, -1);
 				btrfs_wait_ordered_roots(fs_info, -1);
+			}
 
 			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans))
@@ -4100,11 +4102,12 @@ commit_trans:
 				if (ret)
 					return ret;
 				/*
-				 * make sure that all running delayed iput are
-				 * done
+				 * The cleaner kthread might still be doing iput
+				 * operations. Wait for it to finish so that
+				 * more space is released.
 				 */
-				down_write(&root->fs_info->delayed_iput_sem);
-				up_write(&root->fs_info->delayed_iput_sem);
+				mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
+				mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
 				goto again;
 			} else {
 				btrfs_end_transaction(trans, root);
@@ -7853,7 +7856,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
 			 buf->start + buf->len - 1, GFP_NOFS);
 	}
-	trans->blocks_used++;
+	trans->dirty = true;
 	/* this returns a buffer locked for blocking */
 	return buf;
 }
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9abe18763a7f..257bbdcb5df6 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2786,12 +2786,6 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask)
 		btrfs_bio->csum = NULL;
 		btrfs_bio->csum_allocated = NULL;
 		btrfs_bio->end_io = NULL;
-
-#ifdef CONFIG_BLK_CGROUP
-		/* FIXME, put this into bio_clone_bioset */
-		if (bio->bi_css)
-			bio_associate_blkcg(new, bio->bi_css);
-#endif
 	}
 	return new;
 }
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0f09526aa7d9..353f4bae658c 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1526,27 +1526,24 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 
 		reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
 
-		if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
-					     BTRFS_INODE_PREALLOC)) {
-			ret = check_can_nocow(inode, pos, &write_bytes);
-			if (ret < 0)
-				break;
-			if (ret > 0) {
-				/*
-				 * For nodata cow case, no need to reserve
-				 * data space.
-				 */
-				only_release_metadata = true;
-				/*
-				 * our prealloc extent may be smaller than
-				 * write_bytes, so scale down.
-				 */
-				num_pages = DIV_ROUND_UP(write_bytes + offset,
-							 PAGE_CACHE_SIZE);
-				reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
-				goto reserve_metadata;
-			}
+		if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+					      BTRFS_INODE_PREALLOC)) &&
+		    check_can_nocow(inode, pos, &write_bytes) > 0) {
+			/*
+			 * For nodata cow case, no need to reserve
+			 * data space.
+			 */
+			only_release_metadata = true;
+			/*
+			 * our prealloc extent may be smaller than
+			 * write_bytes, so scale down.
+			 */
+			num_pages = DIV_ROUND_UP(write_bytes + offset,
+						 PAGE_CACHE_SIZE);
+			reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+			goto reserve_metadata;
 		}
+
 		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
 		if (ret < 0)
 			break;
@@ -1885,7 +1882,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
  */
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
-	struct dentry *dentry = file->f_path.dentry;
+	struct dentry *dentry = file_dentry(file);
 	struct inode *inode = d_inode(dentry);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 767a6056ac45..07573dc1614a 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -515,7 +515,7 @@ out:
 	return ret;
 }
 
-static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -555,13 +555,6 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
 	int ret;
 	mutex_lock(&root->objectid_mutex);
 
-	if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) {
-		ret = btrfs_find_highest_objectid(root,
-						  &root->highest_objectid);
-		if (ret)
-			goto out;
-	}
-
 	if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
 		ret = -ENOSPC;
 		goto out;
diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h
index ddb347bfee23..c8e864b2d530 100644
--- a/fs/btrfs/inode-map.h
+++ b/fs/btrfs/inode-map.h
@@ -9,5 +9,6 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 			 struct btrfs_trans_handle *trans);
 
 int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
 
 #endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a70c5790f8f5..4bc9dbf29a73 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3142,8 +3142,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
 	if (empty)
 		return;
 
-	down_read(&fs_info->delayed_iput_sem);
-
 	spin_lock(&fs_info->delayed_iput_lock);
 	list_splice_init(&fs_info->delayed_iputs, &list);
 	spin_unlock(&fs_info->delayed_iput_lock);
@@ -3154,8 +3152,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
 		iput(delayed->inode);
 		kfree(delayed);
 	}
-
-	up_read(&root->fs_info->delayed_iput_sem);
 }
 
 /*
@@ -5741,6 +5737,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	char *name_ptr;
 	int name_len;
 	int is_curr = 0;	/* ctx->pos points to the current index? */
+	bool emitted;
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -5769,6 +5766,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (ret < 0)
 		goto err;
 
+	emitted = false;
 	while (1) {
 		leaf = path->nodes[0];
 		slot = path->slots[0];
@@ -5848,6 +5846,7 @@ skip:
 
 			if (over)
 				goto nopos;
+			emitted = true;
 			di_len = btrfs_dir_name_len(leaf, di) +
 				 btrfs_dir_data_len(leaf, di) + sizeof(*di);
 			di_cur += di_len;
@@ -5860,11 +5859,20 @@ next:
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		if (is_curr)
 			ctx->pos++;
-		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
 		if (ret)
 			goto nopos;
 	}
 
+	/*
+	 * If we haven't emitted any dir entry, we must not touch ctx->pos as
+	 * it was was set to the termination value in previous call. We assume
+	 * that "." and ".." were emitted if we reach this point and set the
+	 * termination value as well for an empty directory.
+	 */
+	if (ctx->pos > 2 && !emitted)
+		goto nopos;
+
 	/* Reached end of directory/root. Bump pos past the last item. */
 	ctx->pos++;
 
@@ -6481,7 +6489,7 @@ out_unlock_inode:
 static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		      struct dentry *dentry)
 {
-	struct btrfs_trans_handle *trans;
+	struct btrfs_trans_handle *trans = NULL;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = d_inode(old_dentry);
 	u64 index;
@@ -6507,6 +6515,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	trans = btrfs_start_transaction(root, 5);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
+		trans = NULL;
 		goto fail;
 	}
 
@@ -6540,9 +6549,10 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		btrfs_log_new_name(trans, inode, NULL, parent);
 	}
 
-	btrfs_end_transaction(trans, root);
 	btrfs_balance_delayed_items(root);
 fail:
+	if (trans)
+		btrfs_end_transaction(trans, root);
 	if (drop_inode) {
 		inode_dec_link_count(inode);
 		iput(inode);
@@ -7985,6 +7995,7 @@ static void btrfs_endio_direct_read(struct bio *bio)
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 
 	if (io_bio->end_io)
@@ -8030,6 +8041,7 @@ out_test:
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 	bio_put(bio);
 }
@@ -8534,15 +8546,28 @@ int btrfs_readpage(struct file *file, struct page *page)
 static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
 {
 	struct extent_io_tree *tree;
-
+	struct inode *inode = page->mapping->host;
+	int ret;
 
 	if (current->flags & PF_MEMALLOC) {
 		redirty_page_for_writepage(wbc, page);
 		unlock_page(page);
 		return 0;
 	}
+
+	/*
+	 * If we are under memory pressure we will call this directly from the
+	 * VM, we need to make sure we have the inode referenced for the ordered
+	 * extent.  If not just return like we didn't do anything.
+	 */
+	if (!igrab(inode)) {
+		redirty_page_for_writepage(wbc, page);
+		return AOP_WRITEPAGE_ACTIVATE;
+	}
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
-	return extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+	ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+	btrfs_add_delayed_iput(inode);
+	return ret;
 }
 
 static int btrfs_writepages(struct address_space *mapping,
@@ -9636,9 +9661,11 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	/*
 	 * 2 items for inode item and ref
 	 * 2 items for dir items
+	 * 1 item for updating parent inode item
+	 * 1 item for the inline extent item
 	 * 1 item for xattr if selinux is on
 	 */
-	trans = btrfs_start_transaction(root, 5);
+	trans = btrfs_start_transaction(root, 7);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index da94138eb85e..a7e18dbadf74 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -568,6 +568,10 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 	}
 
+	mutex_lock(&new_root->objectid_mutex);
+	new_root->highest_objectid = new_dirid;
+	mutex_unlock(&new_root->objectid_mutex);
+
 	/*
 	 * insert the directory item
 	 */
@@ -1615,6 +1619,9 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 	int namelen;
 	int ret = 0;
 
+	if (!S_ISDIR(file_inode(file)->i_mode))
+		return -ENOTDIR;
+
 	ret = mnt_want_write_file(file);
 	if (ret)
 		goto out;
@@ -1644,7 +1651,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 
 		src_inode = file_inode(src.file);
 		if (src_inode->i_sb != file_inode(file)->i_sb) {
-			btrfs_info(BTRFS_I(src_inode)->root->fs_info,
+			btrfs_info(BTRFS_I(file_inode(file))->root->fs_info,
 				   "Snapshot src from another FS");
 			ret = -EXDEV;
 		} else if (!inode_owner_or_capable(src_inode)) {
@@ -1672,6 +1679,9 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
 	struct btrfs_ioctl_vol_args *vol_args;
 	int ret;
 
+	if (!S_ISDIR(file_inode(file)->i_mode))
+		return -ENOTDIR;
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
@@ -1695,6 +1705,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 	bool readonly = false;
 	struct btrfs_qgroup_inherit *inherit = NULL;
 
+	if (!S_ISDIR(file_inode(file)->i_mode))
+		return -ENOTDIR;
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
@@ -2341,6 +2354,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	int ret;
 	int err = 0;
 
+	if (!S_ISDIR(dir->i_mode))
+		return -ENOTDIR;
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
@@ -2782,24 +2798,29 @@ out:
 static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
 {
 	struct page *page;
-	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
 	page = grab_cache_page(inode->i_mapping, index);
 	if (!page)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (!PageUptodate(page)) {
-		if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
-						 0))
-			return NULL;
+		int ret;
+
+		ret = btrfs_readpage(NULL, page);
+		if (ret)
+			return ERR_PTR(ret);
 		lock_page(page);
 		if (!PageUptodate(page)) {
 			unlock_page(page);
 			page_cache_release(page);
-			return NULL;
+			return ERR_PTR(-EIO);
+		}
+		if (page->mapping != inode->i_mapping) {
+			unlock_page(page);
+			page_cache_release(page);
+			return ERR_PTR(-EAGAIN);
 		}
 	}
-	unlock_page(page);
 
 	return page;
 }
@@ -2811,17 +2832,31 @@ static int gather_extent_pages(struct inode *inode, struct page **pages,
 	pgoff_t index = off >> PAGE_CACHE_SHIFT;
 
 	for (i = 0; i < num_pages; i++) {
+again:
 		pages[i] = extent_same_get_page(inode, index + i);
-		if (!pages[i])
-			return -ENOMEM;
+		if (IS_ERR(pages[i])) {
+			int err = PTR_ERR(pages[i]);
+
+			if (err == -EAGAIN)
+				goto again;
+			pages[i] = NULL;
+			return err;
+		}
 	}
 	return 0;
 }
 
-static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+static int lock_extent_range(struct inode *inode, u64 off, u64 len,
+			     bool retry_range_locking)
 {
-	/* do any pending delalloc/csum calc on src, one way or
-	   another, and lock file content */
+	/*
+	 * Do any pending delalloc/csum calculations on inode, one way or
+	 * another, and lock file content.
+	 * The locking order is:
+	 *
+	 *   1) pages
+	 *   2) range in the inode's io tree
+	 */
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
@@ -2839,8 +2874,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 		unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
+		if (!retry_range_locking)
+			return -EAGAIN;
 		btrfs_wait_ordered_range(inode, off, len);
 	}
+	return 0;
 }
 
 static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
@@ -2865,15 +2903,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
 	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
 }
 
-static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
-				     struct inode *inode2, u64 loff2, u64 len)
+static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+				    struct inode *inode2, u64 loff2, u64 len,
+				    bool retry_range_locking)
 {
+	int ret;
+
 	if (inode1 < inode2) {
 		swap(inode1, inode2);
 		swap(loff1, loff2);
 	}
-	lock_extent_range(inode1, loff1, len);
-	lock_extent_range(inode2, loff2, len);
+	ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
+	if (ret)
+		return ret;
+	ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
+	if (ret)
+		unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
+			      loff1 + len - 1);
+	return ret;
 }
 
 struct cmp_pages {
@@ -2889,11 +2936,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
 
 	for (i = 0; i < cmp->num_pages; i++) {
 		pg = cmp->src_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 		pg = cmp->dst_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 	}
 	kfree(cmp->src_pages);
 	kfree(cmp->dst_pages);
@@ -2954,6 +3005,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
 
 		src_page = cmp->src_pages[i];
 		dst_page = cmp->dst_pages[i];
+		ASSERT(PageLocked(src_page));
+		ASSERT(PageLocked(dst_page));
 
 		addr = kmap_atomic(src_page);
 		dst_addr = kmap_atomic(dst_page);
@@ -3066,14 +3119,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		goto out_unlock;
 	}
 
+again:
 	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
 	if (ret)
 		goto out_unlock;
 
 	if (same_inode)
-		lock_extent_range(src, same_lock_start, same_lock_len);
+		ret = lock_extent_range(src, same_lock_start, same_lock_len,
+					false);
 	else
-		btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+		ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len,
+					       false);
+	/*
+	 * If one of the inodes has dirty pages in the respective range or
+	 * ordered extents, we need to flush dellaloc and wait for all ordered
+	 * extents in the range. We must unlock the pages and the ranges in the
+	 * io trees to avoid deadlocks when flushing delalloc (requires locking
+	 * pages) and when waiting for ordered extents to complete (they require
+	 * range locking).
+	 */
+	if (ret == -EAGAIN) {
+		/*
+		 * Ranges in the io trees already unlocked. Now unlock all
+		 * pages before waiting for all IO to complete.
+		 */
+		btrfs_cmp_data_free(&cmp);
+		if (same_inode) {
+			btrfs_wait_ordered_range(src, same_lock_start,
+						 same_lock_len);
+		} else {
+			btrfs_wait_ordered_range(src, loff, len);
+			btrfs_wait_ordered_range(dst, dst_loff, len);
+		}
+		goto again;
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		btrfs_cmp_data_free(&cmp);
+		return ret;
+	}
 
 	/* pass original length for comparison so we stay within i_size */
 	ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
@@ -3895,9 +3980,15 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 		u64 lock_start = min_t(u64, off, destoff);
 		u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
 
-		lock_extent_range(src, lock_start, lock_len);
+		ret = lock_extent_range(src, lock_start, lock_len, true);
 	} else {
-		btrfs_double_extent_lock(src, off, inode, destoff, len);
+		ret = btrfs_double_extent_lock(src, off, inode, destoff, len,
+					       true);
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		goto out_unlock;
 	}
 
 	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
@@ -5042,7 +5133,7 @@ static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	return btrfs_qgroup_wait_for_completion(root->fs_info);
+	return btrfs_qgroup_wait_for_completion(root->fs_info, true);
 }
 
 static long _btrfs_ioctl_set_received_subvol(struct file *file,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5279fdae7142..bcc965ed5fa1 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -995,7 +995,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 		goto out;
 	fs_info->quota_enabled = 0;
 	fs_info->pending_quota_state = 0;
-	btrfs_qgroup_wait_for_completion(fs_info);
+	btrfs_qgroup_wait_for_completion(fs_info, false);
 	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
 	fs_info->quota_root = NULL;
@@ -2283,6 +2283,10 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 	int err = -ENOMEM;
 	int ret = 0;
 
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	fs_info->qgroup_rescan_running = true;
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
+
 	path = btrfs_alloc_path();
 	if (!path)
 		goto out;
@@ -2349,6 +2353,9 @@ out:
 	}
 
 done:
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	fs_info->qgroup_rescan_running = false;
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
 	complete_all(&fs_info->qgroup_rescan_completion);
 }
 
@@ -2467,20 +2474,26 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info)
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+				     bool interruptible)
 {
 	int running;
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
 	spin_lock(&fs_info->qgroup_lock);
-	running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+	running = fs_info->qgroup_rescan_running;
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
-	if (running)
+	if (!running)
+		return 0;
+
+	if (interruptible)
 		ret = wait_for_completion_interruptible(
 					&fs_info->qgroup_rescan_completion);
+	else
+		wait_for_completion(&fs_info->qgroup_rescan_completion);
 
 	return ret;
 }
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index ecb2c143ef75..3d73e4c9c7df 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -46,7 +46,8 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
 void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+				     bool interruptible);
 int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
 			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
 int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7cf8509deda7..2c849b08a91b 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
 		set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
 
 		err = btrfs_insert_fs_root(root->fs_info, root);
+		/*
+		 * The root might have been inserted already, as before we look
+		 * for orphan roots, log replay might have happened, which
+		 * triggers a transaction commit and qgroup accounting, which
+		 * in turn reads and inserts fs roots while doing backref
+		 * walking.
+		 */
+		if (err == -EEXIST)
+			err = 0;
 		if (err) {
-			BUG_ON(err == -EEXIST);
 			btrfs_free_fs_root(root);
 			break;
 		}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 355a458cba1a..63a6152be04b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1469,7 +1469,21 @@ static int read_symlink(struct btrfs_root *root,
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret);
+	if (ret) {
+		/*
+		 * An empty symlink inode. Can happen in rare error paths when
+		 * creating a symlink (transaction committed before the inode
+		 * eviction handler removed the symlink inode items and a crash
+		 * happened in between or the subvol was snapshoted in between).
+		 * Print an informative message to dmesg/syslog so that the user
+		 * can delete the symlink.
+		 */
+		btrfs_err(root->fs_info,
+			  "Found empty symlink inode %llu at root %llu",
+			  ino, root->root_key.objectid);
+		ret = -EIO;
+		goto out;
+	}
 
 	ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
 			struct btrfs_file_extent_item);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 24154e422945..5d34a062ca4f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -239,7 +239,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 	trans->aborted = errno;
 	/* Nothing used. The other threads that have joined this
 	 * transaction may be able to continue. */
-	if (!trans->blocks_used && list_empty(&trans->new_bgs)) {
+	if (!trans->dirty && list_empty(&trans->new_bgs)) {
 		const char *errstr;
 
 		errstr = btrfs_decode_error(errno);
@@ -1956,6 +1956,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
  * there are other factors that may change the result (like a new metadata
  * chunk).
  *
+ * If metadata is exhausted, f_bavail will be 0.
+ *
  * FIXME: not accurate for mixed block groups, total and free/used are ok,
  * available appears slightly larger.
  */
@@ -1967,11 +1969,13 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct btrfs_space_info *found;
 	u64 total_used = 0;
 	u64 total_free_data = 0;
+	u64 total_free_meta = 0;
 	int bits = dentry->d_sb->s_blocksize_bits;
 	__be32 *fsid = (__be32 *)fs_info->fsid;
 	unsigned factor = 1;
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	int ret;
+	u64 thresh = 0;
 
 	/*
 	 * holding chunk_muext to avoid allocating new chunks, holding
@@ -1997,6 +2001,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 				}
 			}
 		}
+		if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
+			total_free_meta += found->disk_total - found->disk_used;
 
 		total_used += found->disk_used;
 	}
@@ -2019,6 +2025,24 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail += div_u64(total_free_data, factor);
 	buf->f_bavail = buf->f_bavail >> bits;
 
+	/*
+	 * We calculate the remaining metadata space minus global reserve. If
+	 * this is (supposedly) smaller than zero, there's no space. But this
+	 * does not hold in practice, the exhausted state happens where's still
+	 * some positive delta. So we apply some guesswork and compare the
+	 * delta to a 4M threshold.  (Practically observed delta was ~2M.)
+	 *
+	 * We probably cannot calculate the exact threshold value because this
+	 * depends on the internal reservations requested by various
+	 * operations, so some operations that consume a few metadata will
+	 * succeed even if the Avail is zero. But this is better than the other
+	 * way around.
+	 */
+	thresh = 4 * 1024 * 1024;
+
+	if (total_free_meta - thresh < block_rsv->size)
+		buf->f_bavail = 0;
+
 	buf->f_type = BTRFS_SUPER_MAGIC;
 	buf->f_bsize = dentry->d_sb->s_blocksize;
 	buf->f_namelen = BTRFS_NAME_LEN;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 64c8221b6165..1e872923ec2c 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -110,7 +110,6 @@ struct btrfs_trans_handle {
 	u64 chunk_bytes_reserved;
 	unsigned long use_count;
 	unsigned long blocks_reserved;
-	unsigned long blocks_used;
 	unsigned long delayed_ref_updates;
 	struct btrfs_transaction *transaction;
 	struct btrfs_block_rsv *block_rsv;
@@ -121,6 +120,7 @@ struct btrfs_trans_handle {
 	bool can_flush_pending_bgs;
 	bool reloc_reserved;
 	bool sync;
+	bool dirty;
 	unsigned int type;
 	/*
 	 * this root is only needed to validate that the root passed to
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 323e12cc9d2f..1415f6d58633 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2850,6 +2850,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 	if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
 		blk_finish_plug(&plug);
+		list_del_init(&root_log_ctx.list);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = root_log_ctx.log_ret;
 		goto out;
@@ -4406,6 +4407,127 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+/*
+ * When we are logging a new inode X, check if it doesn't have a reference that
+ * matches the reference from some other inode Y created in a past transaction
+ * and that was renamed in the current transaction. If we don't do this, then at
+ * log replay time we can lose inode Y (and all its files if it's a directory):
+ *
+ * mkdir /mnt/x
+ * echo "hello world" > /mnt/x/foobar
+ * sync
+ * mv /mnt/x /mnt/y
+ * mkdir /mnt/x                 # or touch /mnt/x
+ * xfs_io -c fsync /mnt/x
+ * <power fail>
+ * mount fs, trigger log replay
+ *
+ * After the log replay procedure, we would lose the first directory and all its
+ * files (file foobar).
+ * For the case where inode Y is not a directory we simply end up losing it:
+ *
+ * echo "123" > /mnt/foo
+ * sync
+ * mv /mnt/foo /mnt/bar
+ * echo "abc" > /mnt/foo
+ * xfs_io -c fsync /mnt/foo
+ * <power fail>
+ *
+ * We also need this for cases where a snapshot entry is replaced by some other
+ * entry (file or directory) otherwise we end up with an unreplayable log due to
+ * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as
+ * if it were a regular entry:
+ *
+ * mkdir /mnt/x
+ * btrfs subvolume snapshot /mnt /mnt/x/snap
+ * btrfs subvolume delete /mnt/x/snap
+ * rmdir /mnt/x
+ * mkdir /mnt/x
+ * fsync /mnt/x or fsync some new file inside it
+ * <power fail>
+ *
+ * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in
+ * the same transaction.
+ */
+static int btrfs_check_ref_name_override(struct extent_buffer *eb,
+					 const int slot,
+					 const struct btrfs_key *key,
+					 struct inode *inode)
+{
+	int ret;
+	struct btrfs_path *search_path;
+	char *name = NULL;
+	u32 name_len = 0;
+	u32 item_size = btrfs_item_size_nr(eb, slot);
+	u32 cur_offset = 0;
+	unsigned long ptr = btrfs_item_ptr_offset(eb, slot);
+
+	search_path = btrfs_alloc_path();
+	if (!search_path)
+		return -ENOMEM;
+	search_path->search_commit_root = 1;
+	search_path->skip_locking = 1;
+
+	while (cur_offset < item_size) {
+		u64 parent;
+		u32 this_name_len;
+		u32 this_len;
+		unsigned long name_ptr;
+		struct btrfs_dir_item *di;
+
+		if (key->type == BTRFS_INODE_REF_KEY) {
+			struct btrfs_inode_ref *iref;
+
+			iref = (struct btrfs_inode_ref *)(ptr + cur_offset);
+			parent = key->offset;
+			this_name_len = btrfs_inode_ref_name_len(eb, iref);
+			name_ptr = (unsigned long)(iref + 1);
+			this_len = sizeof(*iref) + this_name_len;
+		} else {
+			struct btrfs_inode_extref *extref;
+
+			extref = (struct btrfs_inode_extref *)(ptr +
+							       cur_offset);
+			parent = btrfs_inode_extref_parent(eb, extref);
+			this_name_len = btrfs_inode_extref_name_len(eb, extref);
+			name_ptr = (unsigned long)&extref->name;
+			this_len = sizeof(*extref) + this_name_len;
+		}
+
+		if (this_name_len > name_len) {
+			char *new_name;
+
+			new_name = krealloc(name, this_name_len, GFP_NOFS);
+			if (!new_name) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			name_len = this_name_len;
+			name = new_name;
+		}
+
+		read_extent_buffer(eb, name, name_ptr, this_name_len);
+		di = btrfs_lookup_dir_item(NULL, BTRFS_I(inode)->root,
+					   search_path, parent,
+					   name, this_name_len, 0);
+		if (di && !IS_ERR(di)) {
+			ret = 1;
+			goto out;
+		} else if (IS_ERR(di)) {
+			ret = PTR_ERR(di);
+			goto out;
+		}
+		btrfs_release_path(search_path);
+
+		cur_offset += this_len;
+	}
+	ret = 0;
+out:
+	btrfs_free_path(search_path);
+	kfree(name);
+	return ret;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -4578,6 +4700,22 @@ again:
 		if (min_key.type == BTRFS_INODE_ITEM_KEY)
 			need_log_inode_item = false;
 
+		if ((min_key.type == BTRFS_INODE_REF_KEY ||
+		     min_key.type == BTRFS_INODE_EXTREF_KEY) &&
+		    BTRFS_I(inode)->generation == trans->transid) {
+			ret = btrfs_check_ref_name_override(path->nodes[0],
+							    path->slots[0],
+							    &min_key, inode);
+			if (ret < 0) {
+				err = ret;
+				goto out_unlock;
+			} else if (ret > 0) {
+				err = 1;
+				btrfs_set_log_full_commit(root->fs_info, trans);
+				goto out_unlock;
+			}
+		}
+
 		/* Skip xattrs, we log them later with btrfs_log_all_xattrs() */
 		if (min_key.type == BTRFS_XATTR_ITEM_KEY) {
 			if (ins_nr == 0)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a23399e8e3ab..9c62a6f9757a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -232,6 +232,7 @@ static struct btrfs_device *__alloc_device(void)
 	spin_lock_init(&dev->reada_lock);
 	atomic_set(&dev->reada_in_flight, 0);
 	atomic_set(&dev->dev_stats_ccnt, 0);
+	btrfs_device_data_ordered_init(dev);
 	INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 	INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 
@@ -1257,6 +1258,15 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction,
 	int ret;
 	int slot;
 	struct extent_buffer *l;
+	u64 min_search_start;
+
+	/*
+	 * We don't want to overwrite the superblock on the drive nor any area
+	 * used by the boot loader (grub for example), so we make sure to start
+	 * at an offset of at least 1MB.
+	 */
+	min_search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
+	search_start = max(search_start, min_search_start);
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -1397,18 +1407,9 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
 			 struct btrfs_device *device, u64 num_bytes,
 			 u64 *start, u64 *len)
 {
-	struct btrfs_root *root = device->dev_root;
-	u64 search_start;
-
 	/* FIXME use last free of some kind */
-
-	/*
-	 * we don't want to overwrite the superblock on the drive,
-	 * so we make sure to start at an offset of at least 1MB
-	 */
-	search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
 	return find_free_dev_extent_start(trans->transaction, device,
-					  num_bytes, search_start, start, len);
+					  num_bytes, 0, start, len);
 }
 
 static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
@@ -6512,6 +6513,14 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 				goto out_short_read;
 
 			num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+			if (!num_stripes) {
+				printk(KERN_ERR
+	    "BTRFS: invalid number of stripes %u in sys_array at offset %u\n",
+					num_stripes, cur_offset);
+				ret = -EIO;
+				break;
+			}
+
 			len = btrfs_chunk_item_size(num_stripes);
 			if (cur_offset + len > array_size)
 				goto out_short_read;