From: Pavel Begunkov <asml.silence@gmail.com>
To: Jens Axboe <axboe@kernel.dk>,
io-uring@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/4] io_uring: fix hanging iopoll in case of -EAGAIN
Date: Tue, 23 Jun 2020 14:57:38 +0300 [thread overview]
Message-ID: <6714cb8f-894c-9ff1-7b3a-4f86d7dbe52a@gmail.com> (raw)
In-Reply-To: <e05fc48b-684d-2980-3986-47a77af403e0@kernel.dk>
On 23/06/2020 05:18, Jens Axboe wrote:
> On 6/22/20 8:07 PM, Jens Axboe wrote:
>> On 6/22/20 4:16 PM, Pavel Begunkov wrote:
>>> io_do_iopoll() won't do anything with a request unless
>>> req->iopoll_completed is set. So io_complete_rw_iopoll() has to set
>>> it, otherwise io_do_iopoll() will poll a file again and again even
>>> though the request of interest was completed long ago.
>>
>> I need to look at this again, because with this change, I previously
>> got various use-after-free. I haven't seen any issues with it, but
>> I agree, from a quick look that I'm not quite sure how it's currently
>> not causing hangs. Yet I haven't seen any, with targeted -EAGAIN
>> testing.
Can io_complete_rw_iopoll() get -EAGAIN after being successfully enqueued
(i.e. EIOCBQUEUED)? It's reliably fails for me, because my hacked nullblk
_can_ (i.e. probabilistically returns BLK_STS_AGAIN from ->iopoll()).
>
> Ah I think I know what it is - if we run into:
>
> if (req->result == -EAGAIN)
> return -EAGAIN
>
> in io_issue_sqe() and race with it, we'll reissue twice potentially.
> So the above isn't quite enough, we'll need something a bit broader.
I see, I'll deal with it.
--
Pavel Begunkov
next prev parent reply other threads:[~2020-06-23 11:59 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-22 22:16 [PATCH 0/4] iopoll fixes + cleanups Pavel Begunkov
2020-06-22 22:16 ` [PATCH 1/4] io_uring: fix hanging iopoll in case of -EAGAIN Pavel Begunkov
2020-06-23 2:07 ` Jens Axboe
2020-06-23 2:18 ` Jens Axboe
2020-06-23 11:57 ` Pavel Begunkov [this message]
2020-06-23 19:01 ` Jens Axboe
2020-06-24 16:56 ` Pavel Begunkov
2020-06-22 22:16 ` [PATCH 2/4] io_uring: handle EAGAIN iopoll Pavel Begunkov
2020-06-30 4:01 ` kernel test robot
2020-06-22 22:16 ` [PATCH 3/4] io-wq: compact io-wq flags numbers Pavel Begunkov
2020-06-22 22:16 ` [PATCH 4/4] io-wq: return next work from ->do_work() directly Pavel Begunkov
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=6714cb8f-894c-9ff1-7b3a-4f86d7dbe52a@gmail.com \
--to=asml.silence@gmail.com \
--cc=axboe@kernel.dk \
--cc=io-uring@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).