Merge git://git.kernel.org/pub/scm/linux/kernel/git/josef/btrfs-next.git for-chris into for-linus

16 files changed, 370 insertions, 119 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d133edfcd44..85b8454d960 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 fff2c28497b..9759911dd34 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 &&
@@ -256,7 +260,8 @@ 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;
@@ -281,6 +286,13 @@ out:
 
 }
 
+void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
+{
+	clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+	if (em->in_tree)
+		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 922943ce29e..c6598c89cff 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 bd38cef4235..94aa53b3872 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 20452c110d7..b06d289f998 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -293,15 +293,24 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	struct btrfs_key key;
 	struct btrfs_ioctl_defrag_range_args range;
 	int num_defrag;
+	int index;
+	int ret;
 
 	/* get the inode */
 	key.objectid = defrag->root;
 	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
 	key.offset = (u64)-1;
+
+	index = srcu_read_lock(&fs_info->subvol_srcu);
+
 	inode_root = btrfs_read_fs_root_no_name(fs_info, &key);
 	if (IS_ERR(inode_root)) {
-		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-		return PTR_ERR(inode_root);
+		ret = PTR_ERR(inode_root);
+		goto cleanup;
+	}
+	if (btrfs_root_refs(&inode_root->root_item) == 0) {
+		ret = -ENOENT;
+		goto cleanup;
 	}
 
 	key.objectid = defrag->ino;
@@ -309,9 +318,10 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
 	if (IS_ERR(inode)) {
-		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-		return PTR_ERR(inode);
+		ret = PTR_ERR(inode);
+		goto cleanup;
 	}
+	srcu_read_unlock(&fs_info->subvol_srcu, index);
 
 	/* do a chunk of defrag */
 	clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
@@ -346,6 +356,10 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 
 	iput(inode);
 	return 0;
+cleanup:
+	srcu_read_unlock(&fs_info->subvol_srcu, index);
+	kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
+	return ret;
 }
 
 /*
@@ -1595,9 +1609,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		if (err < 0 && num_written > 0)
 			num_written = err;
 	}
-out:
+
 	if (sync)
 		atomic_dec(&BTRFS_I(inode)->sync_writers);
+out:
 	sb_end_write(inode->i_sb);
 	current->backing_dev_info = NULL;
 	return num_written ? num_written : err;
@@ -2242,6 +2257,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
 	if (lockend <= lockstart)
 		lockend = lockstart + root->sectorsize;
 
+	lockend--;
 	len = lockend - lockstart + 1;
 
 	len = max_t(u64, len, root->sectorsize);
@@ -2308,9 +2324,12 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int origin)
 					}
 				}
 
-				*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 59ea2e4349c..0be7a8742a4 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 67ed24ae86b..ca7ace7b7b5 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;
 	}
@@ -5586,10 +5635,13 @@ 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;
@@ -5671,6 +5723,8 @@ 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;
@@ -6929,11 +6983,9 @@ 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;
@@ -6944,12 +6996,6 @@ 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
@@ -7018,12 +7064,6 @@ 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) {
@@ -7545,41 +7585,61 @@ 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
@@ -7592,11 +7652,18 @@ 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 7624212ae92..afbf3ac2079 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/ordered-data.c b/fs/btrfs/ordered-data.c
index f1073129704..e5ed5672960 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -836,9 +836,16 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 	 * if the disk i_size is already at the inode->i_size, or
 	 * this ordered extent is inside the disk i_size, we're done
 	 */
-	if (disk_i_size == i_size || offset <= disk_i_size) {
+	if (disk_i_size == i_size)
+		goto out;
+
+	/*
+	 * We still need to update disk_i_size if outstanding_isize is greater
+	 * than disk_i_size.
+	 */
+	if (offset <= disk_i_size &&
+	    (!ordered || ordered->outstanding_isize <= disk_i_size))
 		goto out;
-	}
 
 	/*
 	 * walk backward from this ordered extent to disk_i_size.
@@ -870,7 +877,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 			break;
 		if (test->file_offset >= i_size)
 			break;
-		if (test->file_offset >= disk_i_size) {
+		if (entry_end(test) > disk_i_size) {
 			/*
 			 * we don't update disk_i_size now, so record this
 			 * undealt i_size. Or we will not know the real
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index fe9d02c45f8..a5c85623432 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/scrub.c b/fs/btrfs/scrub.c
index bdbb94f245c..67783e03d12 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -580,20 +580,29 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 	int corrected = 0;
 	struct btrfs_key key;
 	struct inode *inode = NULL;
+	struct btrfs_fs_info *fs_info;
 	u64 end = offset + PAGE_SIZE - 1;
 	struct btrfs_root *local_root;
+	int srcu_index;
 
 	key.objectid = root;
 	key.type = BTRFS_ROOT_ITEM_KEY;
 	key.offset = (u64)-1;
-	local_root = btrfs_read_fs_root_no_name(fixup->root->fs_info, &key);
-	if (IS_ERR(local_root))
+
+	fs_info = fixup->root->fs_info;
+	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
+	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
+	if (IS_ERR(local_root)) {
+		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 		return PTR_ERR(local_root);
+	}
 
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.objectid = inum;
 	key.offset = 0;
-	inode = btrfs_iget(fixup->root->fs_info->sb, &key, local_root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
@@ -606,7 +615,6 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 	}
 
 	if (PageUptodate(page)) {
-		struct btrfs_fs_info *fs_info;
 		if (PageDirty(page)) {
 			/*
 			 * we need to write the data to the defect sector. the
@@ -3180,18 +3188,25 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx)
 	u64 physical_for_dev_replace;
 	u64 len;
 	struct btrfs_fs_info *fs_info = nocow_ctx->sctx->dev_root->fs_info;
+	int srcu_index;
 
 	key.objectid = root;
 	key.type = BTRFS_ROOT_ITEM_KEY;
 	key.offset = (u64)-1;
+
+	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
 	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-	if (IS_ERR(local_root))
+	if (IS_ERR(local_root)) {
+		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 		return PTR_ERR(local_root);
+	}
 
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.objectid = inum;
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 54454542ad4..321b7fb4e44 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 99545df1b86..d8982e9601d 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 87fac9a21ea..fc03aa60b68 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -333,12 +333,14 @@ start_transaction(struct btrfs_root *root, u64 num_items, int type,
 					  &root->fs_info->trans_block_rsv,
 					  num_bytes, flush);
 		if (ret)
-			return ERR_PTR(ret);
+			goto reserve_fail;
 	}
 again:
 	h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
-	if (!h)
-		return ERR_PTR(-ENOMEM);
+	if (!h) {
+		ret = -ENOMEM;
+		goto alloc_fail;
+	}
 
 	/*
 	 * If we are JOIN_NOLOCK we're already committing a transaction and
@@ -365,11 +367,7 @@ again:
 	if (ret < 0) {
 		/* We must get the transaction if we are JOIN_NOLOCK. */
 		BUG_ON(type == TRANS_JOIN_NOLOCK);
-
-		if (type < TRANS_JOIN_NOLOCK)
-			sb_end_intwrite(root->fs_info->sb);
-		kmem_cache_free(btrfs_trans_handle_cachep, h);
-		return ERR_PTR(ret);
+		goto join_fail;
 	}
 
 	cur_trans = root->fs_info->running_transaction;
@@ -410,6 +408,19 @@ got_it:
 	if (!current->journal_info && type != TRANS_USERSPACE)
 		current->journal_info = h;
 	return h;
+
+join_fail:
+	if (type < TRANS_JOIN_NOLOCK)
+		sb_end_intwrite(root->fs_info->sb);
+	kmem_cache_free(btrfs_trans_handle_cachep, h);
+alloc_fail:
+	if (num_bytes)
+		btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv,
+					num_bytes);
+reserve_fail:
+	if (qgroup_reserved)
+		btrfs_qgroup_free(root, qgroup_reserved);
+	return ERR_PTR(ret);
 }
 
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
@@ -1468,7 +1479,8 @@ 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 +1586,11 @@ 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 +1674,17 @@ 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 83186c7e45d..9027bb1e746 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 485a5423e3c..5cbb7f4b167 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)
@@ -2615,7 +2615,14 @@ 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;
 
@@ -2960,6 +2967,8 @@ 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,
@@ -3139,8 +3148,10 @@ 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;
 }
 
@@ -3157,7 +3168,6 @@ 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);
 
@@ -3180,7 +3190,6 @@ 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);
@@ -3234,6 +3243,8 @@ 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);
 
@@ -3497,7 +3508,7 @@ 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,