linux-kernel - Re: [PATCH v2 0/2] Optimise io

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <79fa9cc2-e0cc-922f-89d3-9ace59abb2e8@gmail.com>
Date:   Tue, 24 Sep 2019 20:33:26 +0300
From:   Pavel Begunkov <asml.silence@...il.com>
To:     Jens Axboe <axboe@...nel.dk>, Peter Zijlstra <peterz@...radead.org>
Cc:     Ingo Molnar <mingo@...nel.org>, Ingo Molnar <mingo@...hat.com>,
        linux-block@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 0/2] Optimise io_uring completion waiting

On 24/09/2019 16:13, Jens Axboe wrote:
> On 9/24/19 5:23 AM, Pavel Begunkov wrote:
>>> Yep that should do it, and saves 8 bytes of stack as well.
>>>
>>> BTW, did you test my patch, this one or the previous? Just curious if it
>>> worked for you.
>>>
>> Not yet, going to do that tonight
> 
> Thanks! For reference, the final version is below. There was still a
> signal mishap in there, now it should all be correct afaict.
> 
> 
> diff --git a/fs/io_uring.c b/fs/io_uring.c
> index 9b84232e5cc4..d2a86164d520 100644
> --- a/fs/io_uring.c
> +++ b/fs/io_uring.c
> @@ -2768,6 +2768,38 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
>  	return submit;
>  }
>  
> +struct io_wait_queue {
> +	struct wait_queue_entry wq;
> +	struct io_ring_ctx *ctx;
> +	unsigned to_wait;
> +	unsigned nr_timeouts;
> +};
> +
> +static inline bool io_should_wake(struct io_wait_queue *iowq)
> +{
> +	struct io_ring_ctx *ctx = iowq->ctx;
> +
> +	/*
> +	 * Wake up if we have enough events, or if a timeout occured since we
> +	 * started waiting. For timeouts, we always want to return to userspace,
> +	 * regardless of event count.
> +	 */
> +	return io_cqring_events(ctx->rings) >= iowq->to_wait ||
> +			atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
> +}
> +
> +static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
> +			    int wake_flags, void *key)
> +{
> +	struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue,
> +							wq);
> +
> +	if (!io_should_wake(iowq))
> +		return -1;

It would try to schedule only the first task in the wait list. Is that the
semantic you want?
E.g. for waiters=[32,8] and nr_events == 8, io_wake_function() returns
after @32, and won't wake up the second one. 

> +
> +	return autoremove_wake_function(curr, mode, wake_flags, key);
> +}
> +
>  /*
>   * Wait until events become available, if we don't already have some. The
>   * application must reap them itself, as they reside on the shared cq ring.
> @@ -2775,8 +2807,16 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
>  static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
>  			  const sigset_t __user *sig, size_t sigsz)
>  {
> +	struct io_wait_queue iowq = {
> +		.wq = {
> +			.private	= current,
> +			.func		= io_wake_function,
> +			.entry		= LIST_HEAD_INIT(iowq.wq.entry),
> +		},
> +		.ctx		= ctx,
> +		.to_wait	= min_events,
> +	};
>  	struct io_rings *rings = ctx->rings;
> -	unsigned nr_timeouts;
>  	int ret;
>  
>  	if (io_cqring_events(rings) >= min_events)
> @@ -2795,15 +2835,20 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
>  			return ret;
>  	}
>  
> -	nr_timeouts = atomic_read(&ctx->cq_timeouts);
> -	/*
> -	 * Return if we have enough events, or if a timeout occured since
> -	 * we started waiting. For timeouts, we always want to return to
> -	 * userspace.
> -	 */
> -	ret = wait_event_interruptible(ctx->wait,
> -				io_cqring_events(rings) >= min_events ||
> -				atomic_read(&ctx->cq_timeouts) != nr_timeouts);
> +	iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
> +	do {
> +		prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
> +						TASK_INTERRUPTIBLE);
> +		if (io_should_wake(&iowq))
> +			break;
> +		schedule();
> +		if (signal_pending(current)) {
> +			ret = -ERESTARTSYS;
> +			break;
> +		}
> +	} while (1);
> +	finish_wait(&ctx->wait, &iowq.wq);
> +
>  	restore_saved_sigmask_unless(ret == -ERESTARTSYS);
>  	if (ret == -ERESTARTSYS)
>  		ret = -EINTR;
> 

-- 
Yours sincerely,
Pavel Begunkov



Download attachment "signature.asc" of type "application/pgp-signature" (834 bytes)