@@ -2278,7 +2278,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
goto out;
err = 0;
- while (!err) {
+ while (!err && !btrfs_fs_closing(fs_info)) {
trans = btrfs_start_transaction(fs_info->fs_root, 0);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
@@ -2301,7 +2301,8 @@ out:
btrfs_free_path(path);
mutex_lock(&fs_info->qgroup_rescan_lock);
- fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+ if (!btrfs_fs_closing(fs_info)) {
+ fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
if (err > 0 &&
fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) {
@@ -2330,7 +2331,9 @@ out:
}
btrfs_end_transaction(trans, fs_info->quota_root);
- if (err >= 0) {
+ if (btrfs_fs_closing(fs_info)) {
+ btrfs_info(fs_info, "qgroup scan paused");
+ } else if (err >= 0) {
btrfs_info(fs_info, "qgroup scan completed%s",
err > 0 ? " (inconsistency flag cleared)" : "");
} else {
I was hitting a consistent NULL pointer dereference during shutdown that showed the trace running through end_workqueue_bio(). I traced it back to the endio_meta_workers workqueue being poked after it had already been destroyed. Eventually I found that the root cause was a qgroup rescan that was still in progress while we were stopping all the btrfs workers. Currently we explicitly pause balance and scrub operations in close_ctree(), but we do nothing to stop the qgroup rescan. We should probably be doing the same for qgroup rescan, but that's a much larger change. This small change is good enough to allow me to unmount without crashing. Signed-off-by: Justin Maggard <jmaggard@netgear.com> --- fs/btrfs/qgroup.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)