[PATCH 5.7 103/120] scsi: core: Run queue in case of I/O resource contention failure

From: Greg Kroah-Hartman
Date: Mon Aug 03 2020 - 08:25:45 EST


From: Ming Lei <ming.lei@xxxxxxxxxx>

[ Upstream commit 3f0dcfbcd2e162fc0a11c1f59b7acd42ee45f126 ]

I/O requests may be held in scheduler queue because of resource contention.
The starvation scenario was handled properly in the regular completion
path but we failed to account for it during I/O submission. This lead to
the hang captured below. Make sure we run the queue when resource
contention is encountered in the submission path.

[ 39.054963] scsi 13:0:0:0: rejecting I/O to dead device
[ 39.058700] scsi 13:0:0:0: rejecting I/O to dead device
[ 39.087855] sd 13:0:0:1: [sdd] Synchronizing SCSI cache
[ 39.088909] scsi 13:0:0:1: rejecting I/O to dead device
[ 39.095351] scsi 13:0:0:1: rejecting I/O to dead device
[ 39.096962] scsi 13:0:0:1: rejecting I/O to dead device
[ 247.021859] INFO: task scsi-stress-rem:813 blocked for more than 122 seconds.
[ 247.023258] Not tainted 5.8.0-rc2 #8
[ 247.024069] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 247.025331] scsi-stress-rem D 0 813 802 0x00004000
[ 247.025334] Call Trace:
[ 247.025354] __schedule+0x504/0x55f
[ 247.027987] schedule+0x72/0xa8
[ 247.027991] blk_mq_freeze_queue_wait+0x63/0x8c
[ 247.027994] ? do_wait_intr_irq+0x7a/0x7a
[ 247.027996] blk_cleanup_queue+0x4b/0xc9
[ 247.028000] __scsi_remove_device+0xf6/0x14e
[ 247.028002] scsi_remove_device+0x21/0x2b
[ 247.029037] sdev_store_delete+0x58/0x7c
[ 247.029041] kernfs_fop_write+0x10d/0x14f
[ 247.031281] vfs_write+0xa2/0xdf
[ 247.032670] ksys_write+0x6b/0xb3
[ 247.032673] do_syscall_64+0x56/0x82
[ 247.034053] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 247.034059] RIP: 0033:0x7f69f39e9008
[ 247.036330] Code: Bad RIP value.
[ 247.036331] RSP: 002b:00007ffdd8116498 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[ 247.037613] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f69f39e9008
[ 247.039714] RDX: 0000000000000002 RSI: 000055cde92a0ab0 RDI: 0000000000000001
[ 247.039715] RBP: 000055cde92a0ab0 R08: 000000000000000a R09: 00007f69f3a79e80
[ 247.039716] R10: 000000000000000a R11: 0000000000000246 R12: 00007f69f3abb780
[ 247.039717] R13: 0000000000000002 R14: 00007f69f3ab6740 R15: 0000000000000002

Link: https://lore.kernel.org/r/20200720025435.812030-1-ming.lei@xxxxxxxxxx
Cc: linux-block@xxxxxxxxxxxxxxx
Cc: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Bart Van Assche <bvanassche@xxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/scsi/scsi_lib.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b8b4366f12001..887b6a47f5dac 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -564,6 +564,15 @@ static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd)
scsi_uninit_cmd(cmd);
}

+static void scsi_run_queue_async(struct scsi_device *sdev)
+{
+ if (scsi_target(sdev)->single_lun ||
+ !list_empty(&sdev->host->starved_list))
+ kblockd_schedule_work(&sdev->requeue_work);
+ else
+ blk_mq_run_hw_queues(sdev->request_queue, true);
+}
+
/* Returns false when no more bytes to process, true if there are more */
static bool scsi_end_request(struct request *req, blk_status_t error,
unsigned int bytes)
@@ -608,11 +617,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error,

__blk_mq_end_request(req, error);

- if (scsi_target(sdev)->single_lun ||
- !list_empty(&sdev->host->starved_list))
- kblockd_schedule_work(&sdev->requeue_work);
- else
- blk_mq_run_hw_queues(q, true);
+ scsi_run_queue_async(sdev);

percpu_ref_put(&q->q_usage_counter);
return false;
@@ -1706,6 +1711,7 @@ out_put_budget:
*/
if (req->rq_flags & RQF_DONTPREP)
scsi_mq_uninit_cmd(cmd);
+ scsi_run_queue_async(sdev);
break;
}
return ret;
--
2.25.1