Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
Message-ID: <d68381cf-a9fc-33b8-8a9c-ff8485ba8d19@gmail.com>
Date:   Fri, 6 May 2022 18:19:42 +0100
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.8.1
Subject: Re: [PATCH 3/5] io_uring: let fast poll support multishot
Content-Language: en-US
To:     Hao Xu <haoxu.linux@gmail.com>, io-uring@vger.kernel.org
Cc:     Jens Axboe <axboe@kernel.dk>, linux-kernel@vger.kernel.org
References: <20220506070102.26032-1-haoxu.linux@gmail.com>
 <20220506070102.26032-4-haoxu.linux@gmail.com>
From:   Pavel Begunkov <asml.silence@gmail.com>
In-Reply-To: <20220506070102.26032-4-haoxu.linux@gmail.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 5/6/22 08:01, Hao Xu wrote:
> From: Hao Xu <howeyxu@tencent.com>
> 
> For operations like accept, multishot is a useful feature, since we can
> reduce a number of accept sqe. Let's integrate it to fast poll, it may
> be good for other operations in the future.
> 
> Signed-off-by: Hao Xu <howeyxu@tencent.com>
> ---
>   fs/io_uring.c | 41 ++++++++++++++++++++++++++---------------
>   1 file changed, 26 insertions(+), 15 deletions(-)
> 
> diff --git a/fs/io_uring.c b/fs/io_uring.c
> index 8ebb1a794e36..d33777575faf 100644
> --- a/fs/io_uring.c
> +++ b/fs/io_uring.c
> @@ -5952,7 +5952,7 @@ static void io_poll_remove_entries(struct io_kiocb *req)
>    * either spurious wakeup or multishot CQE is served. 0 when it's done with
>    * the request, then the mask is stored in req->cqe.res.
>    */
> -static int io_poll_check_events(struct io_kiocb *req, bool locked)
> +static int io_poll_check_events(struct io_kiocb *req, bool *locked)
>   {
>   	struct io_ring_ctx *ctx = req->ctx;
>   	int v;
> @@ -5981,17 +5981,26 @@ static int io_poll_check_events(struct io_kiocb *req, bool locked)
>   
>   		/* multishot, just fill an CQE and proceed */
>   		if (req->cqe.res && !(req->apoll_events & EPOLLONESHOT)) {
> -			__poll_t mask = mangle_poll(req->cqe.res & req->apoll_events);
> -			bool filled;
> -
> -			spin_lock(&ctx->completion_lock);
> -			filled = io_fill_cqe_aux(ctx, req->cqe.user_data, mask,
> -						 IORING_CQE_F_MORE);
> -			io_commit_cqring(ctx);
> -			spin_unlock(&ctx->completion_lock);
> -			if (unlikely(!filled))
> -				return -ECANCELED;
> -			io_cqring_ev_posted(ctx);
> +			if (req->flags & REQ_F_APOLL_MULTISHOT) {
> +				io_tw_lock(req->ctx, locked);
> +				if (likely(!(req->task->flags & PF_EXITING)))
> +					io_queue_sqe(req);

That looks dangerous, io_queue_sqe() usually takes the request ownership
and doesn't expect that someone, i.e. io_poll_check_events(), may still be
actively using it.

E.g. io_accept() fails on fd < 0, return an error,
io_queue_sqe() -> io_queue_async() -> io_req_complete_failed()
kills it. Then io_poll_check_events() and polling in general
carry on using the freed request => UAF. Didn't look at it
too carefully, but there might other similar cases.


> +				else
> +					return -EFAULT;
> +			} else {
> +				__poll_t mask = mangle_poll(req->cqe.res &
> +							    req->apoll_events);
> +				bool filled;
> +
> +				spin_lock(&ctx->completion_lock);
> +				filled = io_fill_cqe_aux(ctx, req->cqe.user_data,
> +							 mask, IORING_CQE_F_MORE);
> +				io_commit_cqring(ctx);
> +				spin_unlock(&ctx->completion_lock);
> +				if (unlikely(!filled))
> +					return -ECANCELED;
> +				io_cqring_ev_posted(ctx);
> +			}
>   		} else if (req->cqe.res) {
>   			return 0;
>   		}
> @@ -6010,7 +6019,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked)
>   	struct io_ring_ctx *ctx = req->ctx;
>   	int ret;
>   
> -	ret = io_poll_check_events(req, *locked);
> +	ret = io_poll_check_events(req, locked);
>   	if (ret > 0)
>   		return;
>   
> @@ -6035,7 +6044,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked)
>   	struct io_ring_ctx *ctx = req->ctx;
>   	int ret;
>   
> -	ret = io_poll_check_events(req, *locked);
> +	ret = io_poll_check_events(req, locked);
>   	if (ret > 0)
>   		return;
>   
> @@ -6275,7 +6284,7 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
>   	struct io_ring_ctx *ctx = req->ctx;
>   	struct async_poll *apoll;
>   	struct io_poll_table ipt;
> -	__poll_t mask = EPOLLONESHOT | POLLERR | POLLPRI;
> +	__poll_t mask = POLLERR | POLLPRI;
>   	int ret;
>   
>   	if (!def->pollin && !def->pollout)
> @@ -6284,6 +6293,8 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
>   		return IO_APOLL_ABORTED;
>   	if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED)
>   		return IO_APOLL_ABORTED;
> +	if (!(req->flags & REQ_F_APOLL_MULTISHOT))
> +		mask |= EPOLLONESHOT;
>   
>   	if (def->pollin) {
>   		mask |= POLLIN | POLLRDNORM;

-- 
Pavel Begunkov