btrfs: scrub: move scrub_setup_ctx allocation out of device_list_mutex

[ Upstream commit 0e94c4f ]

The scrub context is allocated with GFP_KERNEL and called from
btrfs_scrub_dev under the fs_info::device_list_mutex. This is not safe
regarding reclaim that could try to flush filesystem data in order to
get the memory. And the device_list_mutex is held during superblock
commit, so this would cause a lockup.

Move the alocation and initialization before any changes that require
the mutex.

Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

fs/btrfs/scrub.c

@@ -3837,29 +3837,36 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		return -EINVAL;
 	}
 
+	/* Allocate outside of device_list_mutex */
+	sctx = scrub_setup_ctx(fs_info, is_dev_replace);
+	if (IS_ERR(sctx))
+		return PTR_ERR(sctx);
 
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	dev = btrfs_find_device(fs_info, devid, NULL, NULL);
 	if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) &&
 		     !is_dev_replace)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_free_ctx;
 	}
 
 	if (!is_dev_replace && !readonly &&
 	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable",
 				rcu_str_deref(dev->name));
-		return -EROFS;
+		ret = -EROFS;
+		goto out_free_ctx;
 	}
 
 	mutex_lock(&fs_info->scrub_lock);
 	if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
 	    test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &dev->dev_state)) {
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		return -EIO;
+		ret = -EIO;
+		goto out_free_ctx;
 	}
 
 	btrfs_dev_replace_read_lock(&fs_info->dev_replace);
@@ -3869,24 +3876,18 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		btrfs_dev_replace_read_unlock(&fs_info->dev_replace);
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		return -EINPROGRESS;
+		ret = -EINPROGRESS;
+		goto out_free_ctx;
 	}
 	btrfs_dev_replace_read_unlock(&fs_info->dev_replace);
 
 	ret = scrub_workers_get(fs_info, is_dev_replace);
 	if (ret) {
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		return ret;
+		goto out_free_ctx;
 	}
 
-	sctx = scrub_setup_ctx(fs_info, is_dev_replace);
-	if (IS_ERR(sctx)) {
-		mutex_unlock(&fs_info->scrub_lock);
-		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		scrub_workers_put(fs_info);
-		return PTR_ERR(sctx);
-	}
 	sctx->readonly = readonly;
 	dev->scrub_ctx = sctx;
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
@@ -3939,6 +3940,11 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 
 	scrub_put_ctx(sctx);
 
+	return ret;
+
+out_free_ctx:
+	scrub_free_ctx(sctx);
+
 	return ret;
 }