dm kcopyd: always complete failed jobs

This patch fixes a problem in dm-kcopyd that may leave jobs in
complete queue indefinitely in the event of backing storage failure.

This behavior has been observed while running 100% write file fio
workload against an XFS volume created on top of a dm-zoned target
device. If the underlying storage of dm-zoned goes to offline state
under I/O, kcopyd sometimes never issues the end copy callback and
dm-zoned reclaim work hangs indefinitely waiting for that completion.

This behavior was traced down to the error handling code in
process_jobs() function that places the failed job to complete_jobs
queue, but doesn't wake up the job handler. In case of backing device
failure, all outstanding jobs may end up going to complete_jobs queue
via this code path and then stay there forever because there are no
more successful I/O jobs to wake up the job handler.

This patch adds a wake() call to always wake up kcopyd job wait queue
for all I/O jobs that fail before dm_io() gets called for that job.

The patch also sets the write error status in all sub jobs that are
failed because their master job has failed.

Fixes: b73c67c2cbb00 ("dm kcopyd: add sequential write feature")
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

1 files changed, 4 insertions, 1 deletions

diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index df2011de7be2..1bbe4a34ef4c 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -566,8 +566,10 @@ static int run_io_job(struct kcopyd_job *job)
 	 * no point in continuing.
 	 */
 	if (test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags) &&
-	    job->master_job->write_err)
+	    job->master_job->write_err) {
+		job->write_err = job->master_job->write_err;
 		return -EIO;
+	}
 
 	io_job_start(job->kc->throttle);
 
@@ -619,6 +621,7 @@ static int process_jobs(struct list_head *jobs, struct dm_kcopyd_client *kc,
 			else
 				job->read_err = 1;
 			push(&kc->complete_jobs, job);
+			wake(kc);
 			break;
 		}