public inbox for [email protected]
 help / color / mirror / Atom feed
From: Pavel Begunkov <[email protected]>
To: Hao Xu <[email protected]>, Jens Axboe <[email protected]>
Cc: [email protected], Joseph Qi <[email protected]>
Subject: Re: [PATCH for-5.15] io_uring: fix lacking of protection for compl_nr
Date: Fri, 20 Aug 2021 22:32:05 +0100	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

On 8/20/21 9:39 PM, Hao Xu wrote:
> 在 2021/8/21 上午2:59, Pavel Begunkov 写道:
>> On 8/20/21 7:40 PM, Hao Xu wrote:
>>> coml_nr in ctx_flush_and_put() is not protected by uring_lock, this
>>> may cause problems when accessing it parallelly.
>>
>> Did you hit any problem? It sounds like it should be fine as is:
>>
>> The trick is that it's only responsible to flush requests added
>> during execution of current call to tctx_task_work(), and those
>> naturally synchronised with the current task. All other potentially
>> enqueued requests will be of someone else's responsibility.
>>
>> So, if nobody flushed requests, we're finely in-sync. If we see
>> 0 there, but actually enqueued a request, it means someone
>> actually flushed it after the request had been added.
>>
>> Probably, needs a more formal explanation with happens-before
>> and so.
> I should put more detail in the commit message, the thing is:
> say coml_nr > 0
> 
>   ctx_flush_and put                  other context
>    if (compl_nr)                      get mutex
>                                       coml_nr > 0
>                                       do flush
>                                           coml_nr = 0
>                                       release mutex
>         get mutex
>            do flush (*)
>         release mutex
> 
> in (*) place, we do a bunch of unnecessary works, moreover, we

I wouldn't care about overhead, that shouldn't be much

> call io_cqring_ev_posted() which I think we shouldn't.

IMHO, users should expect spurious io_cqring_ev_posted(),
though there were some eventfd users complaining before, so
for them we can do

if (state->nr) {
    lock();
    if (state->nr) flush();
    unlock();
}

>>> Fixes: d10299e14aae ("io_uring: inline struct io_comp_state")
>>
>> FWIW, it came much earlier than this commit, IIRC
>>
>> commit 2c32395d8111037ae2cb8cab883e80bcdbb70713
>> Author: Pavel Begunkov <[email protected]>
>> Date:   Sun Feb 28 22:04:53 2021 +0000
>>
>>      io_uring: fix __tctx_task_work() ctx race
>>
>>
>>> Signed-off-by: Hao Xu <[email protected]>
>>> ---
>>>   fs/io_uring.c | 7 +++----
>>>   1 file changed, 3 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/fs/io_uring.c b/fs/io_uring.c
>>> index c755efdac71f..420f8dfa5327 100644
>>> --- a/fs/io_uring.c
>>> +++ b/fs/io_uring.c
>>> @@ -2003,11 +2003,10 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx)
>>>   {
>>>       if (!ctx)
>>>           return;
>>> -    if (ctx->submit_state.compl_nr) {
>>> -        mutex_lock(&ctx->uring_lock);
>>> +    mutex_lock(&ctx->uring_lock);
>>> +    if (ctx->submit_state.compl_nr)
>>>           io_submit_flush_completions(ctx);
>>> -        mutex_unlock(&ctx->uring_lock);
>>> -    }
>>> +    mutex_unlock(&ctx->uring_lock);
>>>       percpu_ref_put(&ctx->refs);
>>>   }
>>>  
>>
> 

-- 
Pavel Begunkov

  reply	other threads:[~2021-08-20 21:32 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-20 18:40 [PATCH for-5.15] io_uring: fix lacking of protection for compl_nr Hao Xu
2021-08-20 18:59 ` Pavel Begunkov
2021-08-20 20:39   ` Hao Xu
2021-08-20 21:32     ` Pavel Begunkov [this message]
2021-08-20 22:07       ` Hao Xu
2021-08-20 22:09       ` Jens Axboe
2021-08-20 22:21         ` Hao Xu
2021-08-20 22:28         ` Pavel Begunkov
2021-08-20 22:30           ` Jens Axboe
2021-08-20 22:41             ` Pavel Begunkov
2021-08-20 22:46               ` Jens Axboe
2021-08-20 22:59                 ` Pavel Begunkov
2021-08-21  3:10                   ` Jens Axboe

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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