DMARC-Filter: OpenDMARC Filter v1.3.2 mx1.redhat.com 27B3E7E9DE
Subject: Re: [PATCH net-next 8/8] vhost_net: use lockless peeking for skb
 array during busy polling
To: "Michael S. Tsirkin" <mst@redhat.com>
References: <1490069087-4783-1-git-send-email-jasowang@redhat.com>
 <1490069087-4783-9-git-send-email-jasowang@redhat.com>
 <20170329150538-mutt-send-email-mst@kernel.org>
 <104c0c1f-e2fd-f5d0-0aae-c308d1f1373c@redhat.com>
 <20170330053315-mutt-send-email-mst@kernel.org>
Cc: kvm@vger.kernel.org, virtualization@lists.linux-foundation.org,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org
From: Jason Wang <jasowang@redhat.com>
Message-ID: <50124a4d-ff2c-95cf-58c6-fdfc55747c0f@redhat.com>
Date: Thu, 30 Mar 2017 11:53:15 +0800
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101
 Thunderbird/45.8.0
MIME-Version: 1.0
In-Reply-To: <20170330053315-mutt-send-email-mst@kernel.org>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2086
Lines: 57


On 2017年03月30日 10:33, Michael S. Tsirkin wrote:
> On Thu, Mar 30, 2017 at 10:16:15AM +0800, Jason Wang wrote:
>>
>> On 2017年03月29日 20:07, Michael S. Tsirkin wrote:
>>> On Tue, Mar 21, 2017 at 12:04:47PM +0800, Jason Wang wrote:
>>>> For the socket that exports its skb array, we can use lockless polling
>>>> to avoid touching spinlock during busy polling.
>>>>
>>>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>>>> ---
>>>>    drivers/vhost/net.c | 7 +++++--
>>>>    1 file changed, 5 insertions(+), 2 deletions(-)
>>>>
>>>> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
>>>> index 53f09f2..41153a3 100644
>>>> --- a/drivers/vhost/net.c
>>>> +++ b/drivers/vhost/net.c
>>>> @@ -551,10 +551,13 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk)
>>>>    	return len;
>>>>    }
>>>> -static int sk_has_rx_data(struct sock *sk)
>>>> +static int sk_has_rx_data(struct vhost_net_virtqueue *rvq, struct sock *sk)
>>>>    {
>>>>    	struct socket *sock = sk->sk_socket;
>>>> +	if (rvq->rx_array)
>>>> +		return !__skb_array_empty(rvq->rx_array);
>>>> +
>>>>    	if (sock->ops->peek_len)
>>>>    		return sock->ops->peek_len(sock);
>>> I don't see which patch adds __skb_array_empty.
>> This is not something new, it was introduced by ad69f35d1dc0a ("skb_array:
>> array based FIFO for skbs").
>>
>> Thanks
> Same comment about a compiler barrier applies then.

Ok, rethink about this, since skb_array could be resized, using lockless 
version seems wrong.

For the comment of using compiler barrier, caller 
(vhost_net_rx_peek_head_len) uses cpu_relax(). But I haven't figured out 
why a compiler barrier is needed here. Could you please explain?

Thanks

>
>>>> @@ -579,7 +582,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net,
>>>>    		endtime = busy_clock() + vq->busyloop_timeout;
>>>>    		while (vhost_can_busy_poll(&net->dev, endtime) &&
>>>> -		       !sk_has_rx_data(sk) &&
>>>> +		       !sk_has_rx_data(rvq, sk) &&
>>>>    		       vhost_vq_avail_empty(&net->dev, vq))
>>>>    			cpu_relax();
>>>> -- 
>>>> 2.7.4