Btrfs: fix use-after-free problem of the device during device replace

The problem is:
	Task0(device scan task)		Task1(device replace task)
	scan_one_device()
	mutex_lock(&uuid_mutex)
	device = find_device()
					mutex_lock(&device_list_mutex)
					lock_chunk()
					rm_and_free_source_device
					unlock_chunk()
					mutex_unlock(&device_list_mutex)
	check device

Destroying the target device if device replace fails also has the same problem.

We fix this problem by locking uuid_mutex during destroying source device or
target device, just like the device remove operation.

It is a temporary solution, we can fix this problem and make the code more
clear by atomic counter in the future.

Signed-off-by: Miao Xie <[email protected]>
Signed-off-by: Chris Mason <[email protected]>

Author: Miao Xie

fs/btrfs/dev-replace.c

@@ -509,6 +509,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	ret = btrfs_commit_transaction(trans, root);
 	WARN_ON(ret);
 
+	mutex_lock(&uuid_mutex);
 	/* keep away write_all_supers() during the finishing procedure */
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	mutex_lock(&root->fs_info->chunk_mutex);
@@ -536,6 +537,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		btrfs_dev_replace_unlock(dev_replace);
 		mutex_unlock(&root->fs_info->chunk_mutex);
 		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+		mutex_unlock(&uuid_mutex);
 		if (tgt_device)
 			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
@@ -591,6 +593,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	 */
 	mutex_unlock(&root->fs_info->chunk_mutex);
 	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&uuid_mutex);
 
 	/* write back the superblocks */
 	trans = btrfs_start_transaction(root, 0);

fs/btrfs/volumes.c

@@ -50,7 +50,7 @@ static void __btrfs_reset_dev_stats(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
 
-static DEFINE_MUTEX(uuid_mutex);
+DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
 
 static void lock_chunks(struct btrfs_root *root)
@@ -1867,6 +1867,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_device *next_device;
 
+	mutex_lock(&uuid_mutex);
 	WARN_ON(!tgtdev);
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	if (tgtdev->bdev) {
@@ -1886,6 +1887,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	call_rcu(&tgtdev->rcu, free_device);
 
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&uuid_mutex);
 }
 
 static int btrfs_find_device_by_path(struct btrfs_root *root, char *device_path,

fs/btrfs/volumes.h

@@ -24,6 +24,8 @@
 #include <linux/btrfs.h>
 #include "async-thread.h"
 
+extern struct mutex uuid_mutex;
+
 #define BTRFS_STRIPE_LEN	(64 * 1024)
 
 struct buffer_head;