On 04/05/2020 09:38, Ming Lei wrote:
[67.602937] refcount_warn_saturate+0x6c/0x13c
[67.607369] aio_complete_rw+0x350/0x384
[67.611279] blkdev_bio_end_io+0xc4/0x12c
[67.615276] bio_endio+0x104/0x130
[67.618665] blk_update_request+0x98/0x37c
[67.622748] blk_mq_end_request+0x24/0x138
[67.626831] blk_mq_resubmit_end_rq+0x40/0x58
[67.631174] __blk_mq_end_request+0xb0/0x10c
[67.635432] scsi_end_request+0xdc/0x20c
Looks an old issue, I believe the following patch can fix the issue:
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 12dee4ecd5cc..3fc79d4b2fe0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2415,6 +2415,10 @@ static void blk_mq_resubmit_rq(struct request *rq)
nrq->bio = rq->bio;
nrq->biotail = rq->biotail;
+ /* Now all bios ownership is transfered to 'nrq' */
+ rq->bio = rq->biotail = NULL;
+ rq->__data_len = 0;
+
if (blk_insert_cloned_request(nrq->q, nrq) != BLK_STS_OK)
blk_mq_request_bypass_insert(nrq, false, true);
}
ok, looks much better.
I'll test this a bit more now.
cheers
