1 files changed, 44 insertions, 17 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ec3a874165de..2ec3b8ac8fa3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -558,6 +558,8 @@ static int btrfs_free_stale_devices(const char *path,
 	struct btrfs_device *device, *tmp_device;
 	int ret = 0;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	if (path)
 		ret = -ENOENT;
 
@@ -988,11 +990,12 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 	struct btrfs_device *orig_dev;
 	int ret = 0;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	fs_devices = alloc_fs_devices(orig->fsid, NULL);
 	if (IS_ERR(fs_devices))
 		return fs_devices;
 
-	mutex_lock(&orig->device_list_mutex);
 	fs_devices->total_devices = orig->total_devices;
 
 	list_for_each_entry(orig_dev, &orig->devices, dev_list) {
@@ -1024,10 +1027,8 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		device->fs_devices = fs_devices;
 		fs_devices->num_devices++;
 	}
-	mutex_unlock(&orig->device_list_mutex);
 	return fs_devices;
 error:
-	mutex_unlock(&orig->device_list_mutex);
 	free_fs_devices(fs_devices);
 	return ERR_PTR(ret);
 }
@@ -1136,6 +1137,19 @@ static void btrfs_close_one_device(struct btrfs_device *device)
 	atomic_set(&device->dev_stats_ccnt, 0);
 	extent_io_tree_release(&device->alloc_state);
 
+	/*
+	 * Reset the flush error record. We might have a transient flush error
+	 * in this mount, and if so we aborted the current transaction and set
+	 * the fs to an error state, guaranteeing no super blocks can be further
+	 * committed. However that error might be transient and if we unmount the
+	 * filesystem and mount it again, we should allow the mount to succeed
+	 * (btrfs_check_rw_degradable() should not fail) - if after mounting the
+	 * filesystem again we still get flush errors, then we will again abort
+	 * any transaction and set the error state, guaranteeing no commits of
+	 * unsafe super blocks.
+	 */
+	device->last_flush_error = 0;
+
 	/* Verify the device is back in a pristine state  */
 	ASSERT(!test_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state));
 	ASSERT(!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state));
@@ -1869,15 +1883,17 @@ out:
  * Function to update ctime/mtime for a given device path.
  * Mainly used for ctime/mtime based probe like libblkid.
  */
-static void update_dev_time(const char *path_name)
+static void update_dev_time(struct block_device *bdev)
 {
-	struct file *filp;
+	struct inode *inode = bdev->bd_inode;
+	struct timespec64 now;
 
-	filp = filp_open(path_name, O_RDWR, 0);
-	if (IS_ERR(filp))
+	/* Shouldn't happen but just in case. */
+	if (!inode)
 		return;
-	file_update_time(filp);
-	filp_close(filp, NULL);
+
+	now = current_time(inode);
+	generic_update_time(inode, &now, S_MTIME | S_CTIME);
 }
 
 static int btrfs_rm_dev_item(struct btrfs_device *device)
@@ -2053,11 +2069,11 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 	btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
 	/* Update ctime/mtime for device path for libblkid */
-	update_dev_time(device_path);
+	update_dev_time(bdev);
 }
 
 int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
-		    u64 devid)
+		    u64 devid, struct block_device **bdev, fmode_t *mode)
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *cur_devices;
@@ -2171,15 +2187,26 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 	mutex_unlock(&fs_devices->device_list_mutex);
 
 	/*
-	 * at this point, the device is zero sized and detached from
-	 * the devices list.  All that's left is to zero out the old
-	 * supers and free the device.
+	 * At this point, the device is zero sized and detached from the
+	 * devices list.  All that's left is to zero out the old supers and
+	 * free the device.
+	 *
+	 * We cannot call btrfs_close_bdev() here because we're holding the sb
+	 * write lock, and blkdev_put() will pull in the ->open_mutex on the
+	 * block device and it's dependencies.  Instead just flush the device
+	 * and let the caller do the final blkdev_put.
 	 */
-	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state))
+	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 		btrfs_scratch_superblocks(fs_info, device->bdev,
 					  device->name->str);
+		if (device->bdev) {
+			sync_blockdev(device->bdev);
+			invalidate_bdev(device->bdev);
+		}
+	}
 
-	btrfs_close_bdev(device);
+	*bdev = device->bdev;
+	*mode = device->mode;
 	synchronize_rcu();
 	btrfs_free_device(device);
 
@@ -2706,7 +2733,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	btrfs_forget_devices(device_path);
 
 	/* Update ctime/mtime for blkid or udev */
-	update_dev_time(device_path);
+	update_dev_time(bdev);
 
 	return ret;