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: <66945bc6-e567-b5a8-9b4d-2b620cf1bdc5@gmail.com>
Date:   Mon, 15 Aug 2022 15:09:50 +0100
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.11.0
Subject: Re: [RFC net-next v3 23/29] io_uring: allow to pass addr into sendzc
Content-Language: en-US
To:     Stefan Metzmacher <metze@samba.org>, io-uring@vger.kernel.org,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     "David S . Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Jonathan Lemon <jonathan.lemon@gmail.com>,
        Willem de Bruijn <willemb@google.com>,
        Jens Axboe <axboe@kernel.dk>, kernel-team@fb.com
References: <cover.1653992701.git.asml.silence@gmail.com>
 <228d4841af5eeb9a4b73955136559f18cb7e43a0.1653992701.git.asml.silence@gmail.com>
 <cccec667-d762-9bfd-f5a5-1c9fb46df5af@samba.org>
 <56631a36-fec8-9c41-712b-195ad7e4cb9f@gmail.com>
 <4eb0adae-660a-3582-df27-d6c254b97adb@samba.org>
 <db7bbfcd-fdd0-ed8e-3d8e-78d76f278af8@gmail.com>
 <246ef163-5711-01d6-feac-396fc176e14e@samba.org>
 <9edd5970-504c-b088-d2b1-3a2b7ad9b345@gmail.com>
 <f8ec9b9e-80b5-a24f-eb12-4069b7b90bea@samba.org>
From:   Pavel Begunkov <asml.silence@gmail.com>
In-Reply-To: <f8ec9b9e-80b5-a24f-eb12-4069b7b90bea@samba.org>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 8/15/22 14:30, Stefan Metzmacher wrote:
[...]
>>> that causes io_ring_exit_work() to wait for it.> It would be great if you or someone else could explain this in detail
>>> and maybe adding some comments into the code.
>>
>> Almost, the mechanism is absolutely the same as with requests,
>> and notifiers are actually requests for internal purposes.
>>
>> In __io_alloc_req_refill() we grab ctx->refs, which are waited
>> for in io_ring_exit_work(). We usually put requests into a cache,
>> so when a request is complete we don't put the ref and therefore
>> in io_ring_exit_work() we also have a call to io_req_caches_free(),
>> which puts ctx->refs.
> 
> Ok, thanks.
> 
> Would a close() on the ring fd block? I guess not, but the exit_work may block, correct?

Right, close doesn't block, it queues exit_work to get executed async.
exit_work() will wait for ctx->refs and then will free most of
io_uring resources.

> So a process would be a zombie until net released all references?

The userspace process will exit normally, but you can find a kernel
thread (kworker) doing the job.

-- 
Pavel Begunkov