Merge branch 'misc-4.7' into for-chris-4.7-20160516

fs/btrfs/backref.c

@@ -1991,7 +1991,7 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 
 	ifp = kmalloc(sizeof(*ifp), GFP_NOFS);
 	if (!ifp) {
-		kfree(fspath);
+		vfree(fspath);
 		return ERR_PTR(-ENOMEM);
 	}
 

fs/btrfs/compression.c

@@ -743,8 +743,11 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 static struct {
 	struct list_head idle_ws;
 	spinlock_t ws_lock;
-	int num_ws;
-	atomic_t alloc_ws;
+	/* Number of free workspaces */
+	int free_ws;
+	/* Total number of allocated workspaces */
+	atomic_t total_ws;
+	/* Waiters for a free workspace */
 	wait_queue_head_t ws_wait;
 } btrfs_comp_ws[BTRFS_COMPRESS_TYPES];
 
@@ -758,16 +761,34 @@ void __init btrfs_init_compress(void)
 	int i;
 
 	for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) {
+		struct list_head *workspace;
+
 		INIT_LIST_HEAD(&btrfs_comp_ws[i].idle_ws);
 		spin_lock_init(&btrfs_comp_ws[i].ws_lock);
-		atomic_set(&btrfs_comp_ws[i].alloc_ws, 0);
+		atomic_set(&btrfs_comp_ws[i].total_ws, 0);
 		init_waitqueue_head(&btrfs_comp_ws[i].ws_wait);
+
+		/*
+		 * Preallocate one workspace for each compression type so
+		 * we can guarantee forward progress in the worst case
+		 */
+		workspace = btrfs_compress_op[i]->alloc_workspace();
+		if (IS_ERR(workspace)) {
+			printk(KERN_WARNING
+	"BTRFS: cannot preallocate compression workspace, will try later");
+		} else {
+			atomic_set(&btrfs_comp_ws[i].total_ws, 1);
+			btrfs_comp_ws[i].free_ws = 1;
+			list_add(workspace, &btrfs_comp_ws[i].idle_ws);
+		}
 	}
 }
 
 /*
- * this finds an available workspace or allocates a new one
- * ERR_PTR is returned if things go bad.
+ * This finds an available workspace or allocates a new one.
+ * If it's not possible to allocate a new one, waits until there's one.
+ * Preallocation makes a forward progress guarantees and we do not return
+ * errors.
  */
 static struct list_head *find_workspace(int type)
 {
@@ -777,36 +798,58 @@ static struct list_head *find_workspace(int type)
 
 	struct list_head *idle_ws	= &btrfs_comp_ws[idx].idle_ws;
 	spinlock_t *ws_lock		= &btrfs_comp_ws[idx].ws_lock;
-	atomic_t *alloc_ws		= &btrfs_comp_ws[idx].alloc_ws;
+	atomic_t *total_ws		= &btrfs_comp_ws[idx].total_ws;
 	wait_queue_head_t *ws_wait	= &btrfs_comp_ws[idx].ws_wait;
-	int *num_ws			= &btrfs_comp_ws[idx].num_ws;
+	int *free_ws			= &btrfs_comp_ws[idx].free_ws;
 again:
 	spin_lock(ws_lock);
 	if (!list_empty(idle_ws)) {
 		workspace = idle_ws->next;
 		list_del(workspace);
-		(*num_ws)--;
+		(*free_ws)--;
 		spin_unlock(ws_lock);
 		return workspace;
 
 	}
-	if (atomic_read(alloc_ws) > cpus) {
+	if (atomic_read(total_ws) > cpus) {
 		DEFINE_WAIT(wait);
 
 		spin_unlock(ws_lock);
 		prepare_to_wait(ws_wait, &wait, TASK_UNINTERRUPTIBLE);
-		if (atomic_read(alloc_ws) > cpus && !*num_ws)
+		if (atomic_read(total_ws) > cpus && !*free_ws)
 			schedule();
 		finish_wait(ws_wait, &wait);
 		goto again;
 	}
-	atomic_inc(alloc_ws);
+	atomic_inc(total_ws);
 	spin_unlock(ws_lock);
 
 	workspace = btrfs_compress_op[idx]->alloc_workspace();
 	if (IS_ERR(workspace)) {
-		atomic_dec(alloc_ws);
+		atomic_dec(total_ws);
 		wake_up(ws_wait);
+
+		/*
+		 * Do not return the error but go back to waiting. There's a
+		 * workspace preallocated for each type and the compression
+		 * time is bounded so we get to a workspace eventually. This
+		 * makes our caller's life easier.
+		 *
+		 * To prevent silent and low-probability deadlocks (when the
+		 * initial preallocation fails), check if there are any
+		 * workspaces at all.
+		 */
+		if (atomic_read(total_ws) == 0) {
+			static DEFINE_RATELIMIT_STATE(_rs,
+					/* once per minute */ 60 * HZ,
+					/* no burst */ 1);
+
+			if (__ratelimit(&_rs)) {
+				printk(KERN_WARNING
+			    "no compression workspaces, low memory, retrying");
+			}
+		}
+		goto again;
 	}
 	return workspace;
 }
@@ -820,21 +863,21 @@ static void free_workspace(int type, struct list_head *workspace)
 	int idx = type - 1;
 	struct list_head *idle_ws	= &btrfs_comp_ws[idx].idle_ws;
 	spinlock_t *ws_lock		= &btrfs_comp_ws[idx].ws_lock;
-	atomic_t *alloc_ws		= &btrfs_comp_ws[idx].alloc_ws;
+	atomic_t *total_ws		= &btrfs_comp_ws[idx].total_ws;
 	wait_queue_head_t *ws_wait	= &btrfs_comp_ws[idx].ws_wait;
-	int *num_ws			= &btrfs_comp_ws[idx].num_ws;
+	int *free_ws			= &btrfs_comp_ws[idx].free_ws;
 
 	spin_lock(ws_lock);
-	if (*num_ws < num_online_cpus()) {
+	if (*free_ws < num_online_cpus()) {
 		list_add(workspace, idle_ws);
-		(*num_ws)++;
+		(*free_ws)++;
 		spin_unlock(ws_lock);
 		goto wake;
 	}
 	spin_unlock(ws_lock);
 
 	btrfs_compress_op[idx]->free_workspace(workspace);
-	atomic_dec(alloc_ws);
+	atomic_dec(total_ws);
 wake:
 	/*
 	 * Make sure counter is updated before we wake up waiters.
@@ -857,7 +900,7 @@ static void free_workspaces(void)
 			workspace = btrfs_comp_ws[i].idle_ws.next;
 			list_del(workspace);
 			btrfs_compress_op[i]->free_workspace(workspace);
-			atomic_dec(&btrfs_comp_ws[i].alloc_ws);
+			atomic_dec(&btrfs_comp_ws[i].total_ws);
 		}
 	}
 }
@@ -894,8 +937,6 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 	int ret;
 
 	workspace = find_workspace(type);
-	if (IS_ERR(workspace))
-		return PTR_ERR(workspace);
 
 	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
 						      start, len, pages,
@@ -930,8 +971,6 @@ static int btrfs_decompress_biovec(int type, struct page **pages_in,
 	int ret;
 
 	workspace = find_workspace(type);
-	if (IS_ERR(workspace))
-		return PTR_ERR(workspace);
 
 	ret = btrfs_compress_op[type-1]->decompress_biovec(workspace, pages_in,
 							 disk_start,
@@ -952,8 +991,6 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 	int ret;
 
 	workspace = find_workspace(type);
-	if (IS_ERR(workspace))
-		return PTR_ERR(workspace);
 
 	ret = btrfs_compress_op[type-1]->decompress(workspace, data_in,
 						  dest_page, start_byte,

fs/btrfs/ctree.h

@@ -4122,6 +4122,7 @@ void btrfs_test_inode_set_ops(struct inode *inode);
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int btrfs_ioctl_get_supported_features(void __user *arg);
 void btrfs_update_iflags(struct inode *inode);
 void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);

fs/btrfs/disk-io.c

@@ -2517,6 +2517,7 @@ int open_ctree(struct super_block *sb,
 	int num_backups_tried = 0;
 	int backup_index = 0;
 	int max_active;
+	bool cleaner_mutex_locked = false;
 
 	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
@@ -2997,6 +2998,13 @@ int open_ctree(struct super_block *sb,
 		goto fail_sysfs;
 	}
 
+	/*
+	 * Hold the cleaner_mutex thread here so that we don't block
+	 * for a long time on btrfs_recover_relocation.  cleaner_kthread
+	 * will wait for us to finish mounting the filesystem.
+	 */
+	mutex_lock(&fs_info->cleaner_mutex);
+	cleaner_mutex_locked = true;
 	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
 					       "btrfs-cleaner");
 	if (IS_ERR(fs_info->cleaner_kthread))
@@ -3056,10 +3064,8 @@ int open_ctree(struct super_block *sb,
 		ret = btrfs_cleanup_fs_roots(fs_info);
 		if (ret)
 			goto fail_qgroup;
-
-		mutex_lock(&fs_info->cleaner_mutex);
+		/* We locked cleaner_mutex before creating cleaner_kthread. */
 		ret = btrfs_recover_relocation(tree_root);
-		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret < 0) {
 			printk(KERN_WARNING
 			       "BTRFS: failed to recover relocation\n");
@@ -3067,6 +3073,8 @@ int open_ctree(struct super_block *sb,
 			goto fail_qgroup;
 		}
 	}
+	mutex_unlock(&fs_info->cleaner_mutex);
+	cleaner_mutex_locked = false;
 
 	location.objectid = BTRFS_FS_TREE_OBJECTID;
 	location.type = BTRFS_ROOT_ITEM_KEY;
@@ -3180,6 +3188,10 @@ int open_ctree(struct super_block *sb,
 	filemap_write_and_wait(fs_info->btree_inode->i_mapping);
 
 fail_sysfs:
+	if (cleaner_mutex_locked) {
+		mutex_unlock(&fs_info->cleaner_mutex);
+		cleaner_mutex_locked = false;
+	}
 	btrfs_sysfs_remove_mounted(fs_info);
 
 fail_fsdev_sysfs:

fs/btrfs/extent-tree.c

@@ -4620,7 +4620,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
 
 	/* Calc the number of the pages we need flush for space reservation */
 	items = calc_reclaim_items_nr(root, to_reclaim);
-	to_reclaim = items * EXTENT_SIZE_PER_ITEM;
+	to_reclaim = (u64)items * EXTENT_SIZE_PER_ITEM;
 
 	trans = (struct btrfs_trans_handle *)current->journal_info;
 	block_rsv = &root->fs_info->delalloc_block_rsv;

fs/btrfs/extent_io.c

@@ -3200,14 +3200,10 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	return ret;
 }
 
-static noinline void update_nr_written(struct page *page,
-				      struct writeback_control *wbc,
-				      unsigned long nr_written)
+static void update_nr_written(struct page *page, struct writeback_control *wbc,
+			      unsigned long nr_written)
 {
 	wbc->nr_to_write -= nr_written;
-	if (wbc->range_cyclic || (wbc->nr_to_write > 0 &&
-	    wbc->range_start == 0 && wbc->range_end == LLONG_MAX))
-		page->mapping->writeback_index = page->index + nr_written;
 }
 
 /*
@@ -3920,12 +3916,13 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 	struct inode *inode = mapping->host;
 	int ret = 0;
 	int done = 0;
-	int err = 0;
 	int nr_to_write_done = 0;
 	struct pagevec pvec;
 	int nr_pages;
 	pgoff_t index;
 	pgoff_t end;		/* Inclusive */
+	pgoff_t done_index;
+	int range_whole = 0;
 	int scanned = 0;
 	int tag;
 
@@ -3948,6 +3945,8 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 	} else {
 		index = wbc->range_start >> PAGE_SHIFT;
 		end = wbc->range_end >> PAGE_SHIFT;
+		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+			range_whole = 1;
 		scanned = 1;
 	}
 	if (wbc->sync_mode == WB_SYNC_ALL)
@@ -3957,6 +3956,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 retry:
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		tag_pages_for_writeback(mapping, index, end);
+	done_index = index;
 	while (!done && !nr_to_write_done && (index <= end) &&
 	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
 			min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
@@ -3966,6 +3966,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
+			done_index = page->index;
 			/*
 			 * At this point we hold neither mapping->tree_lock nor
 			 * lock on the page itself: the page may be truncated or
@@ -4007,8 +4008,20 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 				unlock_page(page);
 				ret = 0;
 			}
-			if (!err && ret < 0)
-				err = ret;
+			if (ret < 0) {
+				/*
+				 * done_index is set past this page,
+				 * so media errors will not choke
+				 * background writeout for the entire
+				 * file. This has consequences for
+				 * range_cyclic semantics (ie. it may
+				 * not be suitable for data integrity
+				 * writeout).
+				 */
+				done_index = page->index + 1;
+				done = 1;
+				break;
+			}
 
 			/*
 			 * the filesystem may choose to bump up nr_to_write.
@@ -4020,7 +4033,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 		pagevec_release(&pvec);
 		cond_resched();
 	}
-	if (!scanned && !done && !err) {
+	if (!scanned && !done) {
 		/*
 		 * We hit the last page and there is more work to be done: wrap
 		 * back to the start of the file
@@ -4029,8 +4042,12 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 		index = 0;
 		goto retry;
 	}
+
+	if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
+		mapping->writeback_index = done_index;
+
 	btrfs_add_delayed_iput(inode);
-	return err;
+	return ret;
 }
 
 static void flush_epd_write_bio(struct extent_page_data *epd)

fs/btrfs/file.c

@@ -1696,7 +1696,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			btrfs_end_write_no_snapshoting(root);
 			btrfs_delalloc_release_metadata(inode, release_bytes);
 		} else {
-			btrfs_delalloc_release_space(inode, pos, release_bytes);
+			btrfs_delalloc_release_space(inode,
+						round_down(pos, root->sectorsize),
+						release_bytes);
 		}
 	}
 
@@ -2956,7 +2958,7 @@ const struct file_operations btrfs_file_operations = {
 	.fallocate	= btrfs_fallocate,
 	.unlocked_ioctl	= btrfs_ioctl,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl	= btrfs_ioctl,
+	.compat_ioctl	= btrfs_compat_ioctl,
 #endif
 	.copy_file_range = btrfs_copy_file_range,
 	.clone_file_range = btrfs_clone_file_range,

fs/btrfs/inode.c

@@ -10184,7 +10184,7 @@ static const struct file_operations btrfs_dir_file_operations = {
 	.iterate	= btrfs_real_readdir,
 	.unlocked_ioctl	= btrfs_ioctl,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl	= btrfs_ioctl,
+	.compat_ioctl	= btrfs_compat_ioctl,
 #endif
 	.release        = btrfs_release_file,
 	.fsync		= btrfs_sync_file,

fs/btrfs/ioctl.c

@@ -439,7 +439,7 @@ static noinline int create_subvol(struct inode *dir,
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_key key;
-	struct btrfs_root_item root_item;
+	struct btrfs_root_item *root_item;
 	struct btrfs_inode_item *inode_item;
 	struct extent_buffer *leaf;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
@@ -455,16 +455,22 @@ static noinline int create_subvol(struct inode *dir,
 	u64 qgroup_reserved;
 	uuid_le new_uuid;
 
+	root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
+	if (!root_item)
+		return -ENOMEM;
+
 	ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
 	if (ret)
-		return ret;
+		goto fail_free;
 
 	/*
 	 * Don't create subvolume whose level is not zero. Or qgroup will be
 	 * screwed up since it assume subvolme qgroup's level to be 0.
 	 */
-	if (btrfs_qgroup_level(objectid))
-		return -ENOSPC;
+	if (btrfs_qgroup_level(objectid)) {
+		ret = -ENOSPC;
+		goto fail_free;
+	}
 
 	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
 	/*
@@ -474,14 +480,14 @@ static noinline int create_subvol(struct inode *dir,
 	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
 					       8, &qgroup_reserved, false);
 	if (ret)
-		return ret;
+		goto fail_free;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		btrfs_subvolume_release_metadata(root, &block_rsv,
 						 qgroup_reserved);
-		return ret;
+		goto fail_free;
 	}
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
@@ -509,47 +515,45 @@ static noinline int create_subvol(struct inode *dir,
 			    BTRFS_UUID_SIZE);
 	btrfs_mark_buffer_dirty(leaf);
 
-	memset(&root_item, 0, sizeof(root_item));
-
-	inode_item = &root_item.inode;
+	inode_item = &root_item->inode;
 	btrfs_set_stack_inode_generation(inode_item, 1);
 	btrfs_set_stack_inode_size(inode_item, 3);
 	btrfs_set_stack_inode_nlink(inode_item, 1);
 	btrfs_set_stack_inode_nbytes(inode_item, root->nodesize);
 	btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
 
-	btrfs_set_root_flags(&root_item, 0);
-	btrfs_set_root_limit(&root_item, 0);
+	btrfs_set_root_flags(root_item, 0);
+	btrfs_set_root_limit(root_item, 0);
 	btrfs_set_stack_inode_flags(inode_item, BTRFS_INODE_ROOT_ITEM_INIT);
 
-	btrfs_set_root_bytenr(&root_item, leaf->start);
-	btrfs_set_root_generation(&root_item, trans->transid);
-	btrfs_set_root_level(&root_item, 0);
-	btrfs_set_root_refs(&root_item, 1);
-	btrfs_set_root_used(&root_item, leaf->len);
-	btrfs_set_root_last_snapshot(&root_item, 0);
+	btrfs_set_root_bytenr(root_item, leaf->start);
+	btrfs_set_root_generation(root_item, trans->transid);
+	btrfs_set_root_level(root_item, 0);
+	btrfs_set_root_refs(root_item, 1);
+	btrfs_set_root_used(root_item, leaf->len);
+	btrfs_set_root_last_snapshot(root_item, 0);
 
-	btrfs_set_root_generation_v2(&root_item,
-			btrfs_root_generation(&root_item));
+	btrfs_set_root_generation_v2(root_item,
+			btrfs_root_generation(root_item));
 	uuid_le_gen(&new_uuid);
-	memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE);
-	btrfs_set_stack_timespec_sec(&root_item.otime, cur_time.tv_sec);
-	btrfs_set_stack_timespec_nsec(&root_item.otime, cur_time.tv_nsec);
-	root_item.ctime = root_item.otime;
-	btrfs_set_root_ctransid(&root_item, trans->transid);
-	btrfs_set_root_otransid(&root_item, trans->transid);
+	memcpy(root_item->uuid, new_uuid.b, BTRFS_UUID_SIZE);
+	btrfs_set_stack_timespec_sec(&root_item->otime, cur_time.tv_sec);
+	btrfs_set_stack_timespec_nsec(&root_item->otime, cur_time.tv_nsec);
+	root_item->ctime = root_item->otime;
+	btrfs_set_root_ctransid(root_item, trans->transid);
+	btrfs_set_root_otransid(root_item, trans->transid);
 
 	btrfs_tree_unlock(leaf);
 	free_extent_buffer(leaf);
 	leaf = NULL;
 
-	btrfs_set_root_dirid(&root_item, new_dirid);
+	btrfs_set_root_dirid(root_item, new_dirid);
 
 	key.objectid = objectid;
 	key.offset = 0;
 	key.type = BTRFS_ROOT_ITEM_KEY;
 	ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
-				&root_item);
+				root_item);
 	if (ret)
 		goto fail;
 
@@ -601,12 +605,13 @@ static noinline int create_subvol(struct inode *dir,
 	BUG_ON(ret);
 
 	ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
-				  root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
+				  root_item->uuid, BTRFS_UUID_KEY_SUBVOL,
 				  objectid);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
 
 fail:
+	kfree(root_item);
 	trans->block_rsv = NULL;
 	trans->bytes_reserved = 0;
 	btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
@@ -629,6 +634,10 @@ static noinline int create_subvol(struct inode *dir,
 		d_instantiate(dentry, inode);
 	}
 	return ret;
+
+fail_free:
+	kfree(root_item);
+	return ret;
 }
 
 static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root)
@@ -2680,32 +2689,31 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	if (ret)
 		return ret;
 
-	vol_args = memdup_user(arg, sizeof(*vol_args));
-	if (IS_ERR(vol_args)) {
-		ret = PTR_ERR(vol_args);
-		goto err_drop;
-	}
-
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
-
 	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
 			1)) {
 		ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
+		goto out_drop_write;
+	}
+
+	vol_args = memdup_user(arg, sizeof(*vol_args));
+	if (IS_ERR(vol_args)) {
+		ret = PTR_ERR(vol_args);
 		goto out;
 	}
 
+	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 	mutex_lock(&root->fs_info->volume_mutex);
 	ret = btrfs_rm_device(root, vol_args->name);
 	mutex_unlock(&root->fs_info->volume_mutex);
-	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
 
 	if (!ret)
 		btrfs_info(root->fs_info, "disk deleted %s",vol_args->name);
-
-out:
 	kfree(vol_args);
-err_drop:
+out:
+	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+out_drop_write:
 	mnt_drop_write_file(file);
+
 	return ret;
 }
 
@@ -3468,13 +3476,16 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	u64 last_dest_end = destoff;
 
 	ret = -ENOMEM;
-	buf = vmalloc(root->nodesize);
-	if (!buf)
-		return ret;
+	buf = kmalloc(root->nodesize, GFP_KERNEL | __GFP_NOWARN);
+	if (!buf) {
+		buf = vmalloc(root->nodesize);
+		if (!buf)
+			return ret;
+	}
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		vfree(buf);
+		kvfree(buf);
 		return ret;
 	}
 
@@ -3775,7 +3786,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 
 out:
 	btrfs_free_path(path);
-	vfree(buf);
+	kvfree(buf);
 	return ret;
 }
 
@@ -5394,9 +5405,15 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
 	if (ret)
 		return ret;
 
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+
 	trans = btrfs_start_transaction(root, 0);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out_drop_write;
+	}
 
 	spin_lock(&root->fs_info->super_lock);
 	newflags = btrfs_super_compat_flags(super_block);
@@ -5415,7 +5432,11 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
 	btrfs_set_super_incompat_flags(super_block, newflags);
 	spin_unlock(&root->fs_info->super_lock);
 
-	return btrfs_commit_transaction(trans, root);
+	ret = btrfs_commit_transaction(trans, root);
+out_drop_write:
+	mnt_drop_write_file(file);
+
+	return ret;
 }
 
 long btrfs_ioctl(struct file *file, unsigned int
@@ -5552,3 +5573,24 @@ long btrfs_ioctl(struct file *file, unsigned int
 
 	return -ENOTTY;
 }
+
+#ifdef CONFIG_COMPAT
+long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case FS_IOC32_GETFLAGS:
+		cmd = FS_IOC_GETFLAGS;
+		break;
+	case FS_IOC32_SETFLAGS:
+		cmd = FS_IOC_SETFLAGS;
+		break;
+	case FS_IOC32_GETVERSION:
+		cmd = FS_IOC_GETVERSION;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif

fs/btrfs/scrub.c

@@ -1350,7 +1350,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 		recover->bbio = bbio;
 		recover->map_length = mapped_length;
 
-		BUG_ON(page_index >= SCRUB_PAGES_PER_RD_BIO);
+		BUG_ON(page_index >= SCRUB_MAX_PAGES_PER_BLOCK);
 
 		nmirrors = min(scrub_nr_raid_mirrors(bbio), BTRFS_MAX_MIRRORS);
 
@@ -2127,6 +2127,8 @@ static void scrub_missing_raid56_end_io(struct bio *bio)
 	if (bio->bi_error)
 		sblock->no_io_error_seen = 0;
 
+	bio_put(bio);
+
 	btrfs_queue_work(fs_info->scrub_workers, &sblock->work);
 }
 
@@ -2860,7 +2862,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 	int extent_mirror_num;
 	int stop_loop = 0;
 
-	nsectors = map->stripe_len / root->sectorsize;
+	nsectors = div_u64(map->stripe_len, root->sectorsize);
 	bitmap_len = scrub_calc_parity_bitmap_len(nsectors);
 	sparity = kzalloc(sizeof(struct scrub_parity) + 2 * bitmap_len,
 			  GFP_NOFS);
@@ -3070,7 +3072,6 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	int slot;
 	u64 nstripes;
 	struct extent_buffer *l;
-	struct btrfs_key key;
 	u64 physical;
 	u64 logical;
 	u64 logic_end;
@@ -3079,7 +3080,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	int mirror_num;
 	struct reada_control *reada1;
 	struct reada_control *reada2;
-	struct btrfs_key key_start;
+	struct btrfs_key key;
 	struct btrfs_key key_end;
 	u64 increment = map->stripe_len;
 	u64 offset;
@@ -3158,21 +3159,21 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	scrub_blocked_if_needed(fs_info);
 
 	/* FIXME it might be better to start readahead at commit root */
-	key_start.objectid = logical;
-	key_start.type = BTRFS_EXTENT_ITEM_KEY;
-	key_start.offset = (u64)0;
+	key.objectid = logical;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = (u64)0;
 	key_end.objectid = logic_end;
 	key_end.type = BTRFS_METADATA_ITEM_KEY;
 	key_end.offset = (u64)-1;
-	reada1 = btrfs_reada_add(root, &key_start, &key_end);
+	reada1 = btrfs_reada_add(root, &key, &key_end);
 
-	key_start.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
-	key_start.type = BTRFS_EXTENT_CSUM_KEY;
-	key_start.offset = logical;
+	key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
+	key.type = BTRFS_EXTENT_CSUM_KEY;
+	key.offset = logical;
 	key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
 	key_end.type = BTRFS_EXTENT_CSUM_KEY;
 	key_end.offset = logic_end;
-	reada2 = btrfs_reada_add(csum_root, &key_start, &key_end);
+	reada2 = btrfs_reada_add(csum_root, &key, &key_end);
 
 	if (!IS_ERR(reada1))
 		btrfs_reada_wait(reada1);

fs/btrfs/send.c

@@ -5939,6 +5939,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 	u32 i;
 	u64 *clone_sources_tmp = NULL;
 	int clone_sources_to_rollback = 0;
+	unsigned alloc_size;
 	int sort_clone_roots = 0;
 	int index;
 
@@ -5978,6 +5979,12 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 		goto out;
 	}
 
+	if (arg->clone_sources_count >
+	    ULLONG_MAX / sizeof(*arg->clone_sources)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (!access_ok(VERIFY_READ, arg->clone_sources,
 			sizeof(*arg->clone_sources) *
 			arg->clone_sources_count)) {
@@ -6022,40 +6029,53 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 	sctx->clone_roots_cnt = arg->clone_sources_count;
 
 	sctx->send_max_size = BTRFS_SEND_BUF_SIZE;
-	sctx->send_buf = vmalloc(sctx->send_max_size);
+	sctx->send_buf = kmalloc(sctx->send_max_size, GFP_KERNEL | __GFP_NOWARN);
 	if (!sctx->send_buf) {
-		ret = -ENOMEM;
-		goto out;
+		sctx->send_buf = vmalloc(sctx->send_max_size);
+		if (!sctx->send_buf) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
-	sctx->read_buf = vmalloc(BTRFS_SEND_READ_SIZE);
+	sctx->read_buf = kmalloc(BTRFS_SEND_READ_SIZE, GFP_KERNEL | __GFP_NOWARN);
 	if (!sctx->read_buf) {
-		ret = -ENOMEM;
-		goto out;
+		sctx->read_buf = vmalloc(BTRFS_SEND_READ_SIZE);
+		if (!sctx->read_buf) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
 	sctx->pending_dir_moves = RB_ROOT;
 	sctx->waiting_dir_moves = RB_ROOT;
 	sctx->orphan_dirs = RB_ROOT;
 
-	sctx->clone_roots = vzalloc(sizeof(struct clone_root) *
-			(arg->clone_sources_count + 1));
+	alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1);
+
+	sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN);
 	if (!sctx->clone_roots) {
-		ret = -ENOMEM;
-		goto out;
+		sctx->clone_roots = vzalloc(alloc_size);
+		if (!sctx->clone_roots) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
+	alloc_size = arg->clone_sources_count * sizeof(*arg->clone_sources);
+
 	if (arg->clone_sources_count) {
-		clone_sources_tmp = vmalloc(arg->clone_sources_count *
-				sizeof(*arg->clone_sources));
+		clone_sources_tmp = kmalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN);
 		if (!clone_sources_tmp) {
-			ret = -ENOMEM;
-			goto out;
+			clone_sources_tmp = vmalloc(alloc_size);
+			if (!clone_sources_tmp) {
+				ret = -ENOMEM;
+				goto out;
+			}
 		}
 
 		ret = copy_from_user(clone_sources_tmp, arg->clone_sources,
-				arg->clone_sources_count *
-				sizeof(*arg->clone_sources));
+				alloc_size);
 		if (ret) {
 			ret = -EFAULT;
 			goto out;
@@ -6089,7 +6109,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 			sctx->clone_roots[i].root = clone_root;
 			clone_sources_to_rollback = i + 1;
 		}
-		vfree(clone_sources_tmp);
+		kvfree(clone_sources_tmp);
 		clone_sources_tmp = NULL;
 	}
 
@@ -6207,15 +6227,15 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 		btrfs_root_dec_send_in_progress(sctx->parent_root);
 
 	kfree(arg);
-	vfree(clone_sources_tmp);
+	kvfree(clone_sources_tmp);
 
 	if (sctx) {
 		if (sctx->send_filp)
 			fput(sctx->send_filp);
 
-		vfree(sctx->clone_roots);
-		vfree(sctx->send_buf);
-		vfree(sctx->read_buf);
+		kvfree(sctx->clone_roots);
+		kvfree(sctx->send_buf);
+		kvfree(sctx->read_buf);
 
 		name_cache_free(sctx);
 

fs/btrfs/super.c

@@ -2051,6 +2051,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	int ret;
 	u64 thresh = 0;
+	int mixed = 0;
 
 	/*
 	 * holding chunk_muext to avoid allocating new chunks, holding
@@ -2076,8 +2077,17 @@ 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;
+
+		/*
+		 * Metadata in mixed block goup profiles are accounted in data
+		 */
+		if (!mixed && found->flags & BTRFS_BLOCK_GROUP_METADATA) {
+			if (found->flags & BTRFS_BLOCK_GROUP_DATA)
+				mixed = 1;
+			else
+				total_free_meta += found->disk_total -
+					found->disk_used;
+		}
 
 		total_used += found->disk_used;
 	}
@@ -2090,7 +2100,11 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	/* Account global block reserve as used, it's in logical size already */
 	spin_lock(&block_rsv->lock);
-	buf->f_bfree -= block_rsv->size >> bits;
+	/* Mixed block groups accounting is not byte-accurate, avoid overflow */
+	if (buf->f_bfree >= block_rsv->size >> bits)
+		buf->f_bfree -= block_rsv->size >> bits;
+	else
+		buf->f_bfree = 0;
 	spin_unlock(&block_rsv->lock);
 
 	buf->f_bavail = div_u64(total_free_data, factor);
@@ -2115,7 +2129,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	 */
 	thresh = 4 * 1024 * 1024;
 
-	if (total_free_meta - thresh < block_rsv->size)
+	if (!mixed && total_free_meta - thresh < block_rsv->size)
 		buf->f_bavail = 0;
 
 	buf->f_type = BTRFS_SUPER_MAGIC;

fs/btrfs/sysfs.c

@@ -120,6 +120,9 @@ static ssize_t btrfs_feature_attr_store(struct kobject *kobj,
 	if (!fs_info)
 		return -EPERM;
 
+	if (fs_info->sb->s_flags & MS_RDONLY)
+		return -EROFS;
+
 	ret = kstrtoul(skip_spaces(buf), 0, &val);
 	if (ret)
 		return ret;
@@ -364,7 +367,13 @@ static ssize_t btrfs_label_show(struct kobject *kobj,
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 	char *label = fs_info->super_copy->label;
-	return snprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label);
+	ssize_t ret;
+
+	spin_lock(&fs_info->super_lock);
+	ret = snprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label);
+	spin_unlock(&fs_info->super_lock);
+
+	return ret;
 }
 
 static ssize_t btrfs_label_store(struct kobject *kobj,
@@ -374,6 +383,9 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 	size_t p_len;
 
+	if (!fs_info)
+		return -EPERM;
+
 	if (fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 

fs/btrfs/transaction.c

@@ -311,10 +311,11 @@ static noinline int join_transaction(struct btrfs_root *root, unsigned int type)
  * when the transaction commits
  */
 static int record_root_in_trans(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root)
+			       struct btrfs_root *root,
+			       int force)
 {
-	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
-	    root->last_trans < trans->transid) {
+	if ((test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+	    root->last_trans < trans->transid) || force) {
 		WARN_ON(root == root->fs_info->extent_root);
 		WARN_ON(root->commit_root != root->node);
 
@@ -331,7 +332,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 		smp_wmb();
 
 		spin_lock(&root->fs_info->fs_roots_radix_lock);
-		if (root->last_trans == trans->transid) {
+		if (root->last_trans == trans->transid && !force) {
 			spin_unlock(&root->fs_info->fs_roots_radix_lock);
 			return 0;
 		}
@@ -402,7 +403,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 		return 0;
 
 	mutex_lock(&root->fs_info->reloc_mutex);
-	record_root_in_trans(trans, root);
+	record_root_in_trans(trans, root, 0);
 	mutex_unlock(&root->fs_info->reloc_mutex);
 
 	return 0;
@@ -1310,6 +1311,97 @@ int btrfs_defrag_root(struct btrfs_root *root)
 	return ret;
 }
 
+/* Bisesctability fixup, remove in 4.8 */
+#ifndef btrfs_std_error
+#define btrfs_std_error btrfs_handle_fs_error
+#endif
+
+/*
+ * Do all special snapshot related qgroup dirty hack.
+ *
+ * Will do all needed qgroup inherit and dirty hack like switch commit
+ * roots inside one transaction and write all btree into disk, to make
+ * qgroup works.
+ */
+static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *src,
+				   struct btrfs_root *parent,
+				   struct btrfs_qgroup_inherit *inherit,
+				   u64 dst_objectid)
+{
+	struct btrfs_fs_info *fs_info = src->fs_info;
+	int ret;
+
+	/*
+	 * Save some performance in the case that qgroups are not
+	 * enabled. If this check races with the ioctl, rescan will
+	 * kick in anyway.
+	 */
+	mutex_lock(&fs_info->qgroup_ioctl_lock);
+	if (!fs_info->quota_enabled) {
+		mutex_unlock(&fs_info->qgroup_ioctl_lock);
+		return 0;
+	}
+	mutex_unlock(&fs_info->qgroup_ioctl_lock);
+
+	/*
+	 * We are going to commit transaction, see btrfs_commit_transaction()
+	 * comment for reason locking tree_log_mutex
+	 */
+	mutex_lock(&fs_info->tree_log_mutex);
+
+	ret = commit_fs_roots(trans, src);
+	if (ret)
+		goto out;
+	ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
+	if (ret < 0)
+		goto out;
+	ret = btrfs_qgroup_account_extents(trans, fs_info);
+	if (ret < 0)
+		goto out;
+
+	/* Now qgroup are all updated, we can inherit it to new qgroups */
+	ret = btrfs_qgroup_inherit(trans, fs_info,
+				   src->root_key.objectid, dst_objectid,
+				   inherit);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * Now we do a simplified commit transaction, which will:
+	 * 1) commit all subvolume and extent tree
+	 *    To ensure all subvolume and extent tree have a valid
+	 *    commit_root to accounting later insert_dir_item()
+	 * 2) write all btree blocks onto disk
+	 *    This is to make sure later btree modification will be cowed
+	 *    Or commit_root can be populated and cause wrong qgroup numbers
+	 * In this simplified commit, we don't really care about other trees
+	 * like chunk and root tree, as they won't affect qgroup.
+	 * And we don't write super to avoid half committed status.
+	 */
+	ret = commit_cowonly_roots(trans, src);
+	if (ret)
+		goto out;
+	switch_commit_roots(trans->transaction, fs_info);
+	ret = btrfs_write_and_wait_transaction(trans, src);
+	if (ret)
+		btrfs_std_error(fs_info, ret,
+			"Error while writing out transaction for qgroup");
+
+out:
+	mutex_unlock(&fs_info->tree_log_mutex);
+
+	/*
+	 * Force parent root to be updated, as we recorded it before so its
+	 * last_trans == cur_transid.
+	 * Or it won't be committed again onto disk after later
+	 * insert_dir_item()
+	 */
+	if (!ret)
+		record_root_in_trans(trans, parent, 1);
+	return ret;
+}
+
 /*
  * new snapshots need to be created at a very specific time in the
  * transaction commit.  This does the actual creation.
@@ -1383,7 +1475,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	dentry = pending->dentry;
 	parent_inode = pending->dir;
 	parent_root = BTRFS_I(parent_inode)->root;
-	record_root_in_trans(trans, parent_root);
+	record_root_in_trans(trans, parent_root, 0);
 
 	cur_time = current_fs_time(parent_inode->i_sb);
 
@@ -1420,7 +1512,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	record_root_in_trans(trans, root);
+	record_root_in_trans(trans, root, 0);
 	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
 	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
 	btrfs_check_and_init_root_item(new_root_item);
@@ -1516,6 +1608,17 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
+	/*
+	 * Do special qgroup accounting for snapshot, as we do some qgroup
+	 * snapshot hack to do fast snapshot.
+	 * To co-operate with that hack, we do hack again.
+	 * Or snapshot will be greatly slowed down by a subtree qgroup rescan
+	 */
+	ret = qgroup_account_snapshot(trans, root, parent_root,
+				      pending->inherit, objectid);
+	if (ret < 0)
+		goto fail;
+
 	ret = btrfs_insert_dir_item(trans, parent_root,
 				    dentry->d_name.name, dentry->d_name.len,
 				    parent_inode, &key,
@@ -1559,23 +1662,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	/*
-	 * account qgroup counters before qgroup_inherit()
-	 */
-	ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
-	if (ret)
-		goto fail;
-	ret = btrfs_qgroup_account_extents(trans, fs_info);
-	if (ret)
-		goto fail;
-	ret = btrfs_qgroup_inherit(trans, fs_info,
-				   root->root_key.objectid,
-				   objectid, pending->inherit);
-	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
-		goto fail;
-	}
-
 fail:
 	pending->error = ret;
 dir_item_existed:

fs/btrfs/volumes.c

@@ -1972,11 +1972,8 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
 	if (srcdev->missing)
 		fs_devices->missing_devices--;
 
-	if (srcdev->writeable) {
+	if (srcdev->writeable)
 		fs_devices->rw_devices--;
-		/* zero out the old super if it is writable */
-		btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
-	}
 
 	if (srcdev->bdev)
 		fs_devices->open_devices--;
@@ -1987,6 +1984,10 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_fs_devices *fs_devices = srcdev->fs_devices;
 
+	if (srcdev->writeable) {
+		/* zero out the old super if it is writable */
+		btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
+	}
 	call_rcu(&srcdev->rcu, free_device);
 
 	/*
@@ -2024,10 +2025,9 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 
 	btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
 
-	if (tgtdev->bdev) {
-		btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+	if (tgtdev->bdev)
 		fs_info->fs_devices->open_devices--;
-	}
+
 	fs_info->fs_devices->num_devices--;
 
 	next_device = list_entry(fs_info->fs_devices->devices.next,
@@ -2038,10 +2038,18 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		fs_info->fs_devices->latest_bdev = next_device->bdev;
 	list_del_rcu(&tgtdev->dev_list);
 
-	call_rcu(&tgtdev->rcu, free_device);
-
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 	mutex_unlock(&uuid_mutex);
+
+	/*
+	 * The update_dev_time() with in btrfs_scratch_superblocks()
+	 * may lead to a call to btrfs_show_devname() which will try
+	 * to hold device_list_mutex. And here this device
+	 * is already out of device list, so we don't have to hold
+	 * the device_list_mutex lock.
+	 */
+	btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+	call_rcu(&tgtdev->rcu, free_device);
 }
 
 static int btrfs_find_device_by_path(struct btrfs_root *root, char *device_path,
@@ -3402,6 +3410,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	u32 count_meta = 0;
 	u32 count_sys = 0;
 	int chunk_reserved = 0;
+	u64 bytes_used = 0;
 
 	/* step one make some room on all the devices */
 	devices = &fs_info->fs_devices->devices;
@@ -3540,7 +3549,13 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 			goto loop;
 		}
 
-		if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) && !chunk_reserved) {
+		ASSERT(fs_info->data_sinfo);
+		spin_lock(&fs_info->data_sinfo->lock);
+		bytes_used = fs_info->data_sinfo->bytes_used;
+		spin_unlock(&fs_info->data_sinfo->lock);
+
+		if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) &&
+		    !chunk_reserved && !bytes_used) {
 			trans = btrfs_start_transaction(chunk_root, 0);
 			if (IS_ERR(trans)) {
 				mutex_unlock(&fs_info->delete_unused_bgs_mutex);
@@ -3693,10 +3708,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		num_devices--;
 	}
 	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
-	allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-	if (num_devices == 1)
-		allowed |= BTRFS_BLOCK_GROUP_DUP;
-	else if (num_devices > 1)
+	allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE | BTRFS_BLOCK_GROUP_DUP;
+	if (num_devices > 1)
 		allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
 	if (num_devices > 2)
 		allowed |= BTRFS_BLOCK_GROUP_RAID5;
@@ -5278,7 +5291,15 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 	stripe_nr = div64_u64(stripe_nr, stripe_len);
 
 	stripe_offset = stripe_nr * stripe_len;
-	BUG_ON(offset < stripe_offset);
+	if (offset < stripe_offset) {
+		btrfs_crit(fs_info, "stripe math has gone wrong, "
+			   "stripe_offset=%llu, offset=%llu, start=%llu, "
+			   "logical=%llu, stripe_len=%llu",
+			   stripe_offset, offset, em->start, logical,
+			   stripe_len);
+		free_extent_map(em);
+		return -EINVAL;
+	}
 
 	/* stripe_offset is the offset of this block in its stripe*/
 	stripe_offset = offset - stripe_offset;
@@ -5519,7 +5540,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 				&stripe_index);
 		mirror_num = stripe_index + 1;
 	}
-	BUG_ON(stripe_index >= map->num_stripes);
+	if (stripe_index >= map->num_stripes) {
+		btrfs_crit(fs_info, "stripe index math went horribly wrong, "
+			   "got stripe_index=%u, num_stripes=%u",
+			   stripe_index, map->num_stripes);
+		ret = -EINVAL;
+		goto out;
+	}
 
 	num_alloc_stripes = num_stripes;
 	if (dev_replace_is_ongoing) {
@@ -6242,7 +6269,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 			"invalid chunk length %llu", length);
 		return -EIO;
 	}
-	if (!is_power_of_2(stripe_len)) {
+	if (!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN) {
 		btrfs_err(root->fs_info, "invalid chunk stripe length: %llu",
 			  stripe_len);
 		return -EIO;

fs/btrfs/volumes.h

@@ -347,7 +347,7 @@ struct map_lookup {
 	u64 type;
 	int io_align;
 	int io_width;
-	int stripe_len;
+	u64 stripe_len;
 	int sector_size;
 	int num_stripes;
 	int sub_stripes;