>>> @@ -342,13 +1208,14 @@ void ufshpb_suspend(struct ufs_hba *hba)
>>> > struct scsi_device *sdev;
>>> >
>>> > shost_for_each_device(sdev, hba->host) {
>>> > - hpb = sdev->hostdata;
>>> > + hpb = ufshpb_get_hpb_data(sdev);
>>> > if (!hpb)
>>> > continue;
>>> >
>>> > if (ufshpb_get_state(hpb) != HPB_PRESENT)
>>> > continue;
>>> > ufshpb_set_state(hpb, HPB_SUSPEND);
>>> > + ufshpb_cancel_jobs(hpb);
>>>
>>> Here may have a dead lock problem - in the case of runtime suspend,
>>> when ufshpb_suspend() is invoked, all of hba's children scsi devices
>>> are in RPM_SUSPENDED state. When this line tries to cancel a running
>>> map work, i.e. when ufshpb_get_map_req() calls below lines, it will
>>> be stuck at blk_queue_enter().
>>>
>>> req = blk_get_request(hpb->sdev_ufs_lu->request_queue,
>>> REQ_OP_SCSI_IN, 0);
>>>
>>> Please check block layer power management, and see also commit
>>> d55d15a33
>>> ("scsi: block: Do not accept any requests while suspended").
>>
>> I am agree with your comment.
>> How about add BLK_MQ_REQ_NOWAIT flag on blk_get_request() to avoid
>> hang?
>>
>
>That won't work - BLK_MQ_REQ_NOWAIT allows one to fast fail from
>blk_mq_get_tag(),
>but blk_queue_enter() comes before __blk_mq_alloc_request();
>
In blk_queue_enter(), BLK_MQ_REQ_NOWAIT flag can make error than wait rpm
resume. Please refer following code.
int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
{
const bool pm = flags & BLK_MQ_REQ_PM;
while (true) {
bool success = false;
rcu_read_lock();
if (percpu_ref_tryget_live(&q->q_usage_counter)) {
/*
* The code that increments the pm_only counter is
* responsible for ensuring that that counter is
* globally visible before the queue is unfrozen.
*/
if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) ||
!blk_queue_pm_only(q)) {
success = true;
} else {
percpu_ref_put(&q->q_usage_counter);
}
}
rcu_read_unlock();
if (success)
return 0;
if (flags & BLK_MQ_REQ_NOWAIT)
return -EBUSY; <-- out from the function.
Thanks,
Daejun
