All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Hannes Reinecke <hare@suse.de>
Cc: Chao Leng <lengchao@huawei.com>,
	linux-nvme@lists.infradead.org, axboe@kernel.dk,
	linux-block@vger.kernel.org, sagi@grimberg.me, axboe@fb.com,
	kbusch@kernel.org, hch@lst.de
Subject: Re: [PATCH v3 3/5] nvme-fabrics: avoid double request completion for nvmf_fail_nonready_command
Date: Thu, 21 Jan 2021 10:00:12 +0100	[thread overview]
Message-ID: <20210121090012.GA27342@lst.de> (raw)
In-Reply-To: <fda1fdb8-8a9d-2e95-4d08-8d8ee1df450d@suse.de>

On Thu, Jan 21, 2021 at 09:58:37AM +0100, Hannes Reinecke wrote:
> On 1/21/21 8:03 AM, Chao Leng wrote:
>> When reconnect, the request may be completed with NVME_SC_HOST_PATH_ERROR
>> in nvmf_fail_nonready_command. The state of request will be changed to
>> MQ_RQ_IN_FLIGHT before call nvme_complete_rq. If free the request
>> asynchronously such as in nvme_submit_user_cmd, in extreme scenario
>> the request may be completed again in tear down process.
>> nvmf_fail_nonready_command do not need calling blk_mq_start_request
>> before complete the request. nvmf_fail_nonready_command should set
>> the state of request to MQ_RQ_COMPLETE before complete the request.
>>
>
> So what you are saying is that there is a race condition between
> blk_mq_start_request()
> and
> nvme_complete_request()

Between those to a teardwon that cancels all requests can come in.

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Hannes Reinecke <hare@suse.de>
Cc: axboe@kernel.dk, axboe@fb.com, sagi@grimberg.me,
	linux-nvme@lists.infradead.org, linux-block@vger.kernel.org,
	Chao Leng <lengchao@huawei.com>,
	kbusch@kernel.org, hch@lst.de
Subject: Re: [PATCH v3 3/5] nvme-fabrics: avoid double request completion for nvmf_fail_nonready_command
Date: Thu, 21 Jan 2021 10:00:12 +0100	[thread overview]
Message-ID: <20210121090012.GA27342@lst.de> (raw)
In-Reply-To: <fda1fdb8-8a9d-2e95-4d08-8d8ee1df450d@suse.de>

On Thu, Jan 21, 2021 at 09:58:37AM +0100, Hannes Reinecke wrote:
> On 1/21/21 8:03 AM, Chao Leng wrote:
>> When reconnect, the request may be completed with NVME_SC_HOST_PATH_ERROR
>> in nvmf_fail_nonready_command. The state of request will be changed to
>> MQ_RQ_IN_FLIGHT before call nvme_complete_rq. If free the request
>> asynchronously such as in nvme_submit_user_cmd, in extreme scenario
>> the request may be completed again in tear down process.
>> nvmf_fail_nonready_command do not need calling blk_mq_start_request
>> before complete the request. nvmf_fail_nonready_command should set
>> the state of request to MQ_RQ_COMPLETE before complete the request.
>>
>
> So what you are saying is that there is a race condition between
> blk_mq_start_request()
> and
> nvme_complete_request()

Between those to a teardwon that cancels all requests can come in.

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

  reply	other threads:[~2021-01-21  9:01 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-21  7:03 [PATCH v3 0/5] avoid double request completion and IO error Chao Leng
2021-01-21  7:03 ` Chao Leng
2021-01-21  7:03 ` [PATCH v3 1/5] blk-mq: introduce blk_mq_set_request_complete Chao Leng
2021-01-21  7:03   ` Chao Leng
2021-01-21  8:40   ` Christoph Hellwig
2021-01-21  8:40     ` Christoph Hellwig
2021-01-22  1:46     ` Chao Leng
2021-01-22  1:46       ` Chao Leng
2021-01-21  7:03 ` [PATCH v3 2/5] nvme-core: introduce complete failed request Chao Leng
2021-01-21  7:03   ` Chao Leng
2021-01-21  8:41   ` Christoph Hellwig
2021-01-21  8:41     ` Christoph Hellwig
2021-01-22  1:46     ` Chao Leng
2021-01-22  1:46       ` Chao Leng
2021-01-21  7:03 ` [PATCH v3 3/5] nvme-fabrics: avoid double request completion for nvmf_fail_nonready_command Chao Leng
2021-01-21  7:03   ` Chao Leng
2021-01-21  8:58   ` Hannes Reinecke
2021-01-21  8:58     ` Hannes Reinecke
2021-01-21  9:00     ` Christoph Hellwig [this message]
2021-01-21  9:00       ` Christoph Hellwig
2021-01-21  9:27       ` Hannes Reinecke
2021-01-21  9:27         ` Hannes Reinecke
2021-01-22  1:50         ` Chao Leng
2021-01-22  1:50           ` Chao Leng
2021-01-22  1:48     ` Chao Leng
2021-01-22  1:48       ` Chao Leng
2021-01-21  7:03 ` [PATCH v3 4/5] nvme-rdma: avoid IO error for nvme native multipath Chao Leng
2021-01-21  7:03   ` Chao Leng
2021-01-21  7:03 ` [PATCH v3 5/5] nvme-fc: " Chao Leng
2021-01-21  7:03   ` Chao Leng

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=20210121090012.GA27342@lst.de \
    --to=hch@lst.de \
    --cc=axboe@fb.com \
    --cc=axboe@kernel.dk \
    --cc=hare@suse.de \
    --cc=kbusch@kernel.org \
    --cc=lengchao@huawei.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=sagi@grimberg.me \
    /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.