Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <ac5f5152-f9e4-8e83-642b-73c2620ce7c0@gmail.com>
Date:   Thu, 3 Feb 2022 19:00:39 +0000
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.5.0
Subject: Re: [External] Re: [PATCH v3 2/3] io_uring: avoid ring quiesce while
 registering/unregistering eventfd
Content-Language: en-US
To:     Jens Axboe <axboe@kernel.dk>,
        Usama Arif <usama.arif@bytedance.com>,
        io-uring@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     fam.zheng@bytedance.com
References: <20220203174108.668549-1-usama.arif@bytedance.com>
 <20220203174108.668549-3-usama.arif@bytedance.com>
 <ffa271c7-3f49-2b5a-b67e-3bb1b052ee4e@kernel.dk>
 <877d54b9-5baa-f0b5-23fe-25aef78e37c4@bytedance.com>
 <dc6bb53f-19cc-ee23-2137-6e27396f7d57@kernel.dk>
From:   Pavel Begunkov <asml.silence@gmail.com>
In-Reply-To: <dc6bb53f-19cc-ee23-2137-6e27396f7d57@kernel.dk>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Precedence: bulk

On 2/3/22 18:29, Jens Axboe wrote:
> On 2/3/22 11:26 AM, Usama Arif wrote:
>> Hmm, maybe i didn't understand you and Pavel correctly. Are you
>> suggesting to do the below diff over patch 3? I dont think that would be
>> correct, as it is possible that just after checking if ctx->io_ev_fd is
>> present unregister can be called by another thread and set ctx->io_ev_fd
>> to NULL that would cause a NULL pointer exception later? In the current
>> patch, the check of whether ev_fd exists happens as the first thing
>> after rcu_read_lock and the rcu_read_lock are extremely cheap i believe.
> 
> They are cheap, but they are still noticeable at high requests/sec
> rates. So would be best to avoid them.
> 
> And yes it's obviously racy, there's the potential to miss an eventfd
> notification if it races with registering an eventfd descriptor. But
> that's not really a concern, as if you register with inflight IO
> pending, then that always exists just depending on timing. The only
> thing I care about here is that it's always _safe_. Hence something ala
> what you did below is totally fine, as we're re-evaluating under rcu
> protection.

Indeed, the patch doesn't have any formal guarantees for propagation
to already inflight requests, so this extra unsynchronised check
doesn't change anything.

I'm still more сurious why we need RCU and extra complexity when
apparently there is no use case for that. If it's only about
initial initialisation, then as I described there is a much
simpler approach.

-- 
Pavel Begunkov