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;
Date:   Mon, 23 May 2022 10:12:44 -0400
From:   Josef Bacik <josef@toxicpanda.com>
To:     Yu Kuai <yukuai3@huawei.com>
Cc:     axboe@kernel.dk, ming.lei@redhat.com, linux-block@vger.kernel.org,
        nbd@other.debian.org, linux-kernel@vger.kernel.org,
        yi.zhang@huawei.com
Subject: Re: [PATCH -next v3 3/6] nbd: don't clear 'NBD_CMD_INFLIGHT' flag if
 request is not completed
Message-ID: <YouWXEcyoBNUXLb7@localhost.localdomain>
References: <20220521073749.3146892-1-yukuai3@huawei.com>
 <20220521073749.3146892-4-yukuai3@huawei.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20220521073749.3146892-4-yukuai3@huawei.com>
Precedence: bulk

On Sat, May 21, 2022 at 03:37:46PM +0800, Yu Kuai wrote:
> Otherwise io will hung because request will only be completed if the
> cmd has the flag 'NBD_CMD_INFLIGHT'.
> 
> Fixes: 07175cb1baf4 ("nbd: make sure request completion won't concurrent")
> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
> ---
>  drivers/block/nbd.c | 18 ++++++++++++++----
>  1 file changed, 14 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
> index 2ee1e376d5c4..a0d0910dae2a 100644
> --- a/drivers/block/nbd.c
> +++ b/drivers/block/nbd.c
> @@ -403,13 +403,14 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
>  	if (!mutex_trylock(&cmd->lock))
>  		return BLK_EH_RESET_TIMER;
>  
> -	if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
> +	if (!test_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
>  		mutex_unlock(&cmd->lock);
>  		return BLK_EH_DONE;
>  	}
>  
>  	if (!refcount_inc_not_zero(&nbd->config_refs)) {
>  		cmd->status = BLK_STS_TIMEOUT;
> +		__clear_bit(NBD_CMD_INFLIGHT, &cmd->flags);
>  		mutex_unlock(&cmd->lock);
>  		goto done;
>  	}
> @@ -478,6 +479,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
>  	dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out\n");
>  	set_bit(NBD_RT_TIMEDOUT, &config->runtime_flags);
>  	cmd->status = BLK_STS_IOERR;
> +	__clear_bit(NBD_CMD_INFLIGHT, &cmd->flags);
>  	mutex_unlock(&cmd->lock);
>  	sock_shutdown(nbd);
>  	nbd_config_put(nbd);
> @@ -745,7 +747,7 @@ static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index,
>  	cmd = blk_mq_rq_to_pdu(req);
>  
>  	mutex_lock(&cmd->lock);
> -	if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
> +	if (!test_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
>  		dev_err(disk_to_dev(nbd->disk), "Suspicious reply %d (status %u flags %lu)",
>  			tag, cmd->status, cmd->flags);
>  		ret = -ENOENT;
> @@ -854,8 +856,16 @@ static void recv_work(struct work_struct *work)
>  		}
>  
>  		rq = blk_mq_rq_from_pdu(cmd);
> -		if (likely(!blk_should_fake_timeout(rq->q)))
> -			blk_mq_complete_request(rq);
> +		if (likely(!blk_should_fake_timeout(rq->q))) {
> +			bool complete;
> +
> +			mutex_lock(&cmd->lock);
> +			complete = __test_and_clear_bit(NBD_CMD_INFLIGHT,
> +							&cmd->flags);
> +			mutex_unlock(&cmd->lock);
> +			if (complete)
> +				blk_mq_complete_request(rq);
> +		}

I'd rather this be handled in nbd_handle_reply.  We should return with it
cleared if it's ready to be completed.  Thanks,

Josef