From mboxrd@z Thu Jan  1 00:00:00 1970
From: Maxime Coquelin <maxime.coquelin@redhat.com>
Subject: Re: [PATCH v5 2/6] vhost: rewrite enqueue
Date: Mon, 12 Sep 2016 18:26:38 +0200
Message-ID: <09efe45a-16b6-aa0c-f68c-b64dfefd4087@redhat.com>
References: <1471319402-112998-1-git-send-email-zhihong.wang@intel.com>
 <1473392368-84903-1-git-send-email-zhihong.wang@intel.com>
 <1473392368-84903-3-git-send-email-zhihong.wang@intel.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=windows-1252; format=flowed
Content-Transfer-Encoding: 7bit
Cc: yuanhan.liu@linux.intel.com, thomas.monjalon@6wind.com
To: Zhihong Wang <zhihong.wang@intel.com>, dev@dpdk.org
Return-path: <dev-bounces@dpdk.org>
Received: from mx1.redhat.com (mx1.redhat.com [209.132.183.28])
 by dpdk.org (Postfix) with ESMTP id A8F4B532E
 for <dev@dpdk.org>; Mon, 12 Sep 2016 18:26:44 +0200 (CEST)
In-Reply-To: <1473392368-84903-3-git-send-email-zhihong.wang@intel.com>
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>



On 09/09/2016 05:39 AM, Zhihong Wang wrote:
>
> +static inline void __attribute__((always_inline))
> +notify_guest(struct virtio_net *dev, struct vhost_virtqueue *vq)
> +{
>  	rte_smp_wmb();
> -
> -	*(volatile uint16_t *)&vq->used->idx += count;
> -	vq->last_used_idx += count;
> -	vhost_log_used_vring(dev, vq,
> -		offsetof(struct vring_used, idx),
> -		sizeof(vq->used->idx));
> -
> -	/* flush used->idx update before we read avail->flags. */
Please don't remove comments if not justified.
Here the comment is important, as it explains why the barrier is needed.
> +	*(volatile uint16_t *)&vq->used->idx = vq->last_used_idx;
> +	vhost_log_used_vring(dev, vq, offsetof(struct vring_used, idx),
> +			sizeof(vq->used->idx));
>  	rte_mb();
> -
> -	/* Kick the guest if necessary. */
>  	if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
>  			&& (vq->callfd >= 0))
>  		eventfd_write(vq->callfd, (eventfd_t)1);
> -	return count;
>  }