All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sagi Grimberg <sagi@grimberg.me>
To: Ming Lei <ming.lei@redhat.com>, Chao Leng <lengchao@huawei.com>
Cc: Yi Zhang <yi.zhang@redhat.com>, Jens Axboe <axboe@kernel.dk>,
	linux-block@vger.kernel.org, Keith Busch <kbusch@kernel.org>,
	linux-nvme@lists.infradead.org, Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH] block: re-introduce blk_mq_complete_request_sync
Date: Tue, 13 Oct 2020 15:31:18 -0700	[thread overview]
Message-ID: <0b5bfc44-d925-960d-b2a2-d0ba88b51111@grimberg.me> (raw)
In-Reply-To: <20201012081306.GB556731@T590>


>>>>>> -- 
>>>>>> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
>>>>>> index 629b025685d1..46428ff0b0fc 100644
>>>>>> --- a/drivers/nvme/host/tcp.c
>>>>>> +++ b/drivers/nvme/host/tcp.c
>>>>>> @@ -2175,7 +2175,7 @@ static void nvme_tcp_complete_timed_out(struct request *rq)
>>>>>>          /* fence other contexts that may complete the command */
>>>>>>          mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
>>>>>>          nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
>>>>>> -       if (!blk_mq_request_completed(rq)) {
>>>>>> +       if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
>>>>>>                  nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
>>>>>>                  blk_mq_complete_request_sync(rq);
>>>>>>          }
>> This may just reduce the probability. The concurrency of timeout and teardown will cause the same request
>> be treated repeatly, this is not we expected.
> 
> That is right, not like SCSI, NVME doesn't apply atomic request completion, so
> request may be completed/freed from both timeout & nvme_cancel_request().
> 
> .teardown_lock still may cover the race with Sagi's patch because teardown
> actually cancels requests in sync style.
> 
>> In the teardown process, after quiesced queues delete the timer and cancel the timeout work maybe a better option.
> 
> Seems better solution, given it is aligned with NVME PCI's reset
> handling. nvme_sync_queues() may be called in nvme_tcp_teardown_io_queues() to
> avoid this race.

We can't call nvme_sync_queues, that flushes the timeout work that is
serializing with the teardown, it will deadlock.

WARNING: multiple messages have this Message-ID (diff)
From: Sagi Grimberg <sagi@grimberg.me>
To: Ming Lei <ming.lei@redhat.com>, Chao Leng <lengchao@huawei.com>
Cc: Jens Axboe <axboe@kernel.dk>, Yi Zhang <yi.zhang@redhat.com>,
	linux-nvme@lists.infradead.org, linux-block@vger.kernel.org,
	Keith Busch <kbusch@kernel.org>, Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH] block: re-introduce blk_mq_complete_request_sync
Date: Tue, 13 Oct 2020 15:31:18 -0700	[thread overview]
Message-ID: <0b5bfc44-d925-960d-b2a2-d0ba88b51111@grimberg.me> (raw)
In-Reply-To: <20201012081306.GB556731@T590>


>>>>>> -- 
>>>>>> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
>>>>>> index 629b025685d1..46428ff0b0fc 100644
>>>>>> --- a/drivers/nvme/host/tcp.c
>>>>>> +++ b/drivers/nvme/host/tcp.c
>>>>>> @@ -2175,7 +2175,7 @@ static void nvme_tcp_complete_timed_out(struct request *rq)
>>>>>>          /* fence other contexts that may complete the command */
>>>>>>          mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
>>>>>>          nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
>>>>>> -       if (!blk_mq_request_completed(rq)) {
>>>>>> +       if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
>>>>>>                  nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
>>>>>>                  blk_mq_complete_request_sync(rq);
>>>>>>          }
>> This may just reduce the probability. The concurrency of timeout and teardown will cause the same request
>> be treated repeatly, this is not we expected.
> 
> That is right, not like SCSI, NVME doesn't apply atomic request completion, so
> request may be completed/freed from both timeout & nvme_cancel_request().
> 
> .teardown_lock still may cover the race with Sagi's patch because teardown
> actually cancels requests in sync style.
> 
>> In the teardown process, after quiesced queues delete the timer and cancel the timeout work maybe a better option.
> 
> Seems better solution, given it is aligned with NVME PCI's reset
> handling. nvme_sync_queues() may be called in nvme_tcp_teardown_io_queues() to
> avoid this race.

We can't call nvme_sync_queues, that flushes the timeout work that is
serializing with the teardown, it will deadlock.

_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  parent reply	other threads:[~2020-10-13 22:31 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-08 21:37 [PATCH] block: re-introduce blk_mq_complete_request_sync Sagi Grimberg
2020-10-08 21:37 ` Sagi Grimberg
2020-10-09  4:39 ` Ming Lei
2020-10-09  4:39   ` Ming Lei
2020-10-09  5:03   ` Yi Zhang
2020-10-09  5:03     ` Yi Zhang
2020-10-09  8:09     ` Sagi Grimberg
2020-10-09  8:09       ` Sagi Grimberg
2020-10-09 13:55       ` Yi Zhang
2020-10-09 13:55         ` Yi Zhang
2020-10-09 18:29         ` Sagi Grimberg
2020-10-09 18:29           ` Sagi Grimberg
2020-10-10  6:08           ` Yi Zhang
2020-10-10  6:08             ` Yi Zhang
2020-10-12  3:59             ` Chao Leng
2020-10-12  3:59               ` Chao Leng
2020-10-12  8:13               ` Ming Lei
2020-10-12  8:13                 ` Ming Lei
2020-10-12  9:06                 ` Chao Leng
2020-10-12  9:06                   ` Chao Leng
2020-10-13 22:36                   ` Sagi Grimberg
2020-10-13 22:36                     ` Sagi Grimberg
2020-10-14  1:08                     ` Ming Lei
2020-10-14  1:08                       ` Ming Lei
2020-10-14  1:37                       ` Chao Leng
2020-10-14  1:37                         ` Chao Leng
2020-10-14  2:02                         ` Ming Lei
2020-10-14  2:02                           ` Ming Lei
2020-10-14  2:32                           ` Chao Leng
2020-10-14  2:32                             ` Chao Leng
2020-10-14  2:41                           ` Chao Leng
2020-10-14  2:41                             ` Chao Leng
2020-10-14  3:34                       ` Ming Lei
2020-10-14  3:34                         ` Ming Lei
2020-10-14  9:39                         ` Chao Leng
2020-10-14  9:39                           ` Chao Leng
2020-10-14  9:56                           ` Ming Lei
2020-10-14  9:56                             ` Ming Lei
2020-10-15  6:05                             ` Chao Leng
2020-10-15  6:05                               ` Chao Leng
2020-10-15  7:50                               ` Ming Lei
2020-10-15  7:50                                 ` Ming Lei
2020-10-15 10:05                                 ` Chao Leng
2020-10-15 10:05                                   ` Chao Leng
2020-10-14  1:32                     ` Chao Leng
2020-10-14  1:32                       ` Chao Leng
2020-10-13 22:31                 ` Sagi Grimberg [this message]
2020-10-13 22:31                   ` Sagi Grimberg
2020-10-14  1:25                   ` Chao Leng
2020-10-14  1:25                     ` Chao Leng
2020-10-09  8:11   ` Sagi Grimberg
2020-10-09  8:11     ` Sagi Grimberg

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=0b5bfc44-d925-960d-b2a2-d0ba88b51111@grimberg.me \
    --to=sagi@grimberg.me \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=lengchao@huawei.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=ming.lei@redhat.com \
    --cc=yi.zhang@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.