From mboxrd@z Thu Jan  1 00:00:00 1970
From: Jens Freimann <jfreimann@redhat.com>
Subject: Re: [PATCH 07/14] net/virtio: implement transmit path
 for packed queues
Date: Tue, 13 Feb 2018 10:10:18 +0100
Message-ID: <20180213091018.ygsbkg5weguumhpm@dhcp-192-241.str.redhat.com>
References: <20180129141143.13437-1-jfreimann@redhat.com>
 <20180129141143.13437-8-jfreimann@redhat.com>
 <c095c8f3-8445-2cec-ff87-3b8d4c4325be@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii; format=flowed
Cc: dev@dpdk.org, tiwei.bie@intel.com, yliu@fridaylinux.org,
 maxime.coquelin@redhat.com, mst@redhat.com
To: Jason Wang <jasowang@redhat.com>
Return-path: <dev-bounces@dpdk.org>
Received: from mx1.redhat.com (mx3-rdu2.redhat.com [66.187.233.73])
 by dpdk.org (Postfix) with ESMTP id 8D15B11D4
 for <dev@dpdk.org>; Tue, 13 Feb 2018 10:10:20 +0100 (CET)
Content-Disposition: inline
In-Reply-To: <c095c8f3-8445-2cec-ff87-3b8d4c4325be@redhat.com>
List-Id: DPDK patches and discussions <dev.dpdk.org>
List-Unsubscribe: <https://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: <https://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 Mon, Feb 12, 2018 at 09:16:27PM +0800, Jason Wang wrote:
>
>
>On 2018???01???29??? 22:11, Jens Freimann wrote:
>>+/* Cleanup from completed transmits. */
>>+static void
>>+virtio_xmit_cleanup(struct virtqueue *vq)
>>+{
>>+	uint16_t idx;
>>+	uint16_t size = vq->vq_nentries;
>>+	struct vring_desc_1_1 *desc = vq->vq_ring.desc_1_1;
>>+
>>+	idx = vq->vq_used_cons_idx & (size - 1);
>>+	while (desc_is_used(&desc[idx]) &&
>>+	       vq->vq_free_cnt < size) {
>>+		while (desc[idx].flags & VRING_DESC_F_NEXT) {
>>+			vq->vq_free_cnt++;
>>+			idx = ++vq->vq_used_cons_idx & (size - 1);
>>+		}
>>+		vq->vq_free_cnt++;
>>+		idx = ++vq->vq_used_cons_idx & (size - 1);
>>+	}
>>+}
>
>This looks like a violation of the spec. In 2.6.6 Next Flag: 
>Descriptor Chaining. It said:
>
>"VIRTQ_DESC_F_NEXT is reserved in used descriptors, and should be 
>ignored by drivers."

I think you are right. I will rework this bit.
>
>(Looking at the device implementation, it was in fact an in order 
>device which is said to be no in the cover).

Looking into this as well.

Thanks for the review!

regards,
Jens