Date:   Wed, 13 Apr 2022 16:00:18 +0800
From:   Jason Wang <jasowang@...hat.com>
To:     Xuan Zhuo <xuanzhuo@...ux.alibaba.com>,
        virtualization@...ts.linux-foundation.org
Cc:     Jeff Dike <jdike@...toit.com>, Richard Weinberger <richard@....at>,
        Anton Ivanov <anton.ivanov@...bridgegreys.com>,
        "Michael S. Tsirkin" <mst@...hat.com>,
        "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        Hans de Goede <hdegoede@...hat.com>,
        Mark Gross <markgross@...nel.org>,
        Vadim Pasternak <vadimp@...dia.com>,
        Bjorn Andersson <bjorn.andersson@...aro.org>,
        Mathieu Poirier <mathieu.poirier@...aro.org>,
        Cornelia Huck <cohuck@...hat.com>,
        Halil Pasic <pasic@...ux.ibm.com>,
        Heiko Carstens <hca@...ux.ibm.com>,
        Vasily Gorbik <gor@...ux.ibm.com>,
        Christian Borntraeger <borntraeger@...ux.ibm.com>,
        Alexander Gordeev <agordeev@...ux.ibm.com>,
        Sven Schnelle <svens@...ux.ibm.com>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Jesper Dangaard Brouer <hawk@...nel.org>,
        John Fastabend <john.fastabend@...il.com>,
        Johannes Berg <johannes.berg@...el.com>,
        Vincent Whitchurch <vincent.whitchurch@...s.com>,
        linux-um@...ts.infradead.org, netdev@...r.kernel.org,
        platform-driver-x86@...r.kernel.org,
        linux-remoteproc@...r.kernel.org, linux-s390@...r.kernel.org,
        kvm@...r.kernel.org, bpf@...r.kernel.org
Subject: Re: [PATCH v9 31/32] virtio_net: support rx/tx queue resize


在 2022/4/6 上午11:43, Xuan Zhuo 写道:
> This patch implements the resize function of the rx, tx queues.
> Based on this function, it is possible to modify the ring num of the
> queue.
>
> There may be an exception during the resize process, the resize may
> fail, or the vq can no longer be used. Either way, we must execute
> napi_enable(). Because napi_disable is similar to a lock, napi_enable
> must be called after calling napi_disable.
>
> Signed-off-by: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
> ---
>   drivers/net/virtio_net.c | 81 ++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 81 insertions(+)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index b8bf00525177..ba6859f305f7 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -251,6 +251,9 @@ struct padded_vnet_hdr {
>   	char padding[4];
>   };
>   
> +static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
> +static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
> +
>   static bool is_xdp_frame(void *ptr)
>   {
>   	return (unsigned long)ptr & VIRTIO_XDP_FLAG;
> @@ -1369,6 +1372,15 @@ static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
>   {
>   	napi_enable(napi);
>   
> +	/* Check if vq is in reset state. The normal reset/resize process will
> +	 * be protected by napi. However, the protection of napi is only enabled
> +	 * during the operation, and the protection of napi will end after the
> +	 * operation is completed. If re-enable fails during the process, vq
> +	 * will remain unavailable with reset state.
> +	 */
> +	if (vq->reset)
> +		return;


I don't get when could we hit this condition.


> +
>   	/* If all buffers were filled by other side before we napi_enabled, we
>   	 * won't get another interrupt, so process any outstanding packets now.
>   	 * Call local_bh_enable after to trigger softIRQ processing.
> @@ -1413,6 +1425,15 @@ static void refill_work(struct work_struct *work)
>   		struct receive_queue *rq = &vi->rq[i];
>   
>   		napi_disable(&rq->napi);
> +
> +		/* Check if vq is in reset state. See more in
> +		 * virtnet_napi_enable()
> +		 */
> +		if (rq->vq->reset) {
> +			virtnet_napi_enable(rq->vq, &rq->napi);
> +			continue;
> +		}


Can we do something similar in virtnet_close() by canceling the work?


> +
>   		still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
>   		virtnet_napi_enable(rq->vq, &rq->napi);
>   
> @@ -1523,6 +1544,10 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
>   	if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index))
>   		return;
>   
> +	/* Check if vq is in reset state. See more in virtnet_napi_enable() */
> +	if (sq->vq->reset)
> +		return;


We've disabled TX napi, any chance we can still hit this?


> +
>   	if (__netif_tx_trylock(txq)) {
>   		do {
>   			virtqueue_disable_cb(sq->vq);
> @@ -1769,6 +1794,62 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
>   	return NETDEV_TX_OK;
>   }
>   
> +static int virtnet_rx_resize(struct virtnet_info *vi,
> +			     struct receive_queue *rq, u32 ring_num)
> +{
> +	int err;
> +
> +	napi_disable(&rq->napi);
> +
> +	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
> +	if (err)
> +		goto err;
> +
> +	if (!try_fill_recv(vi, rq, GFP_KERNEL))
> +		schedule_delayed_work(&vi->refill, 0);
> +
> +	virtnet_napi_enable(rq->vq, &rq->napi);
> +	return 0;
> +
> +err:
> +	netdev_err(vi->dev,
> +		   "reset rx reset vq fail: rx queue index: %td err: %d\n",
> +		   rq - vi->rq, err);
> +	virtnet_napi_enable(rq->vq, &rq->napi);
> +	return err;
> +}
> +
> +static int virtnet_tx_resize(struct virtnet_info *vi,
> +			     struct send_queue *sq, u32 ring_num)
> +{
> +	struct netdev_queue *txq;
> +	int err, qindex;
> +
> +	qindex = sq - vi->sq;
> +
> +	virtnet_napi_tx_disable(&sq->napi);
> +
> +	txq = netdev_get_tx_queue(vi->dev, qindex);
> +	__netif_tx_lock_bh(txq);
> +	netif_stop_subqueue(vi->dev, qindex);
> +	__netif_tx_unlock_bh(txq);
> +
> +	err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf);
> +	if (err)
> +		goto err;
> +
> +	netif_start_subqueue(vi->dev, qindex);
> +	virtnet_napi_tx_enable(vi, sq->vq, &sq->napi);
> +	return 0;
> +
> +err:


I guess we can still start the queue in this case? (Since we don't 
change the queue if resize fails).


> +	netdev_err(vi->dev,
> +		   "reset tx reset vq fail: tx queue index: %td err: %d\n",
> +		   sq - vi->sq, err);
> +	virtnet_napi_tx_enable(vi, sq->vq, &sq->napi);
> +	return err;
> +}
> +
>   /*
>    * Send command via the control virtqueue and check status.  Commands
>    * supported by the hypervisor, as indicated by feature bits, should

Powered by blists - more mailing lists