Re: [PATCH v7 24/26] virtio_net: support rx/tx queue reset

From: Jason Wang <jasowang@redhat.com>
To: Xuan Zhuo <xuanzhuo@linux.alibaba.com>,
	virtualization@lists.linux-foundation.org,
	netdev@vger.kernel.org
Cc: Jeff Dike <jdike@addtoit.com>,
	Richard Weinberger <richard@nod.at>,
	Anton Ivanov <anton.ivanov@cambridgegreys.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	Hans de Goede <hdegoede@redhat.com>,
	Mark Gross <markgross@kernel.org>,
	Vadim Pasternak <vadimp@nvidia.com>,
	Bjorn Andersson <bjorn.andersson@linaro.org>,
	Mathieu Poirier <mathieu.poirier@linaro.org>,
	Cornelia Huck <cohuck@redhat.com>,
	Halil Pasic <pasic@linux.ibm.com>,
	Heiko Carstens <hca@linux.ibm.com>,
	Vasily Gorbik <gor@linux.ibm.com>,
	Christian Borntraeger <borntraeger@linux.ibm.com>,
	Alexander Gordeev <agordeev@linux.ibm.com>,
	Sven Schnelle <svens@linux.ibm.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Jesper Dangaard Brouer <hawk@kernel.org>,
	John Fastabend <john.fastabend@gmail.com>,
	Johannes Berg <johannes.berg@intel.com>,
	Vincent Whitchurch <vincent.whitchurch@axis.com>,
	linux-um@lists.infradead.org,
	platform-driver-x86@vger.kernel.org,
	linux-remoteproc@vger.kernel.org, linux-s390@vger.kernel.org,
	kvm@vger.kernel.org, bpf@vger.kernel.org
Subject: Re: [PATCH v7 24/26] virtio_net: support rx/tx queue reset
Date: Wed, 9 Mar 2022 17:14:34 +0800	[thread overview]
Message-ID: <7ff78ff8-bdd0-bb5e-1cea-cf1126226feb@redhat.com> (raw)
In-Reply-To: <20220308123518.33800-25-xuanzhuo@linux.alibaba.com>

在 2022/3/8 下午8:35, Xuan Zhuo 写道:
> This patch implements the reset function of the rx, tx queues.
>
> Based on this function, it is possible to modify the ring num of the
> queue. And quickly recycle the buffer in the queue.
>
> In the process of the queue disable, in theory, as long as virtio
> supports queue reset, there will be no exceptions.
>
> However, in the process of the queue enable, there may be exceptions due to
> memory allocation.  In this case, vq is not available, but we still have
> to 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@linux.alibaba.com>
> ---
>   drivers/net/virtio_net.c | 107 +++++++++++++++++++++++++++++++++++++++
>   1 file changed, 107 insertions(+)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 409a8e180918..ffff323dcef0 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -251,6 +251,11 @@ struct padded_vnet_hdr {
>   	char padding[4];
>   };
>   
> +static void virtnet_sq_free_unused_bufs(struct virtnet_info *vi,
> +					struct send_queue *sq);
> +static void virtnet_rq_free_unused_bufs(struct virtnet_info *vi,
> +					struct receive_queue *rq);
> +
>   static bool is_xdp_frame(void *ptr)
>   {
>   	return (unsigned long)ptr & VIRTIO_XDP_FLAG;
> @@ -1369,6 +1374,9 @@ static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
>   {
>   	napi_enable(napi);
>   
> +	if (vq->reset)
> +		return;
> +

Let's WARN_ONCE() here?

>   	/* 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 +1421,10 @@ static void refill_work(struct work_struct *work)
>   		struct receive_queue *rq = &vi->rq[i];
>   
>   		napi_disable(&rq->napi);
> +		if (rq->vq->reset) {
> +			virtnet_napi_enable(rq->vq, &rq->napi);
> +			continue;
> +		}

This seems racy and it's a hint that we need sync with the refill work 
during reset like what we did in virtnet_close():

         /* Make sure refill_work doesn't re-enable napi! */
         cancel_delayed_work_sync(&vi->refill);

>   		still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
>   		virtnet_napi_enable(rq->vq, &rq->napi);
>   
> @@ -1523,6 +1535,9 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
>   	if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index))
>   		return;
>   
> +	if (sq->vq->reset)
> +		return;

It looks to me we'd better either WARN or just remove this. Since it 
looks like a workaround for the un-synchronized NAPI somehow.

> +
>   	if (__netif_tx_trylock(txq)) {
>   		do {
>   			virtqueue_disable_cb(sq->vq);
> @@ -1769,6 +1784,98 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
>   	return NETDEV_TX_OK;
>   }
>   
> +static int virtnet_rx_vq_reset(struct virtnet_info *vi,
> +			       struct receive_queue *rq, u32 ring_num)

It's better to rename this as virtnet_rx_resize().

> +{
> +	int err;
> +
> +	/* stop napi */
> +	napi_disable(&rq->napi);
> +

Here, as discussed above, we need synchronize with the refill work.

> +	/* reset the queue */
> +	err = virtio_reset_vq(rq->vq);
> +	if (err)
> +		goto err;

Btw, most comment of this function seems useless since code already 
explain themselves.

> +
> +	/* free bufs */
> +	virtnet_rq_free_unused_bufs(vi, rq);
> +
> +	/* reset vring. */
> +	err = virtqueue_reset_vring(rq->vq, ring_num);
> +	if (err)
> +		goto err;
> +
> +	/* enable reset queue */
> +	err = virtio_enable_resetq(rq->vq);
> +	if (err)
> +		goto err;
> +
> +	/* fill recv */
> +	if (!try_fill_recv(vi, rq, GFP_KERNEL))
> +		schedule_delayed_work(&vi->refill, 0);
> +
> +	/* enable napi */
> +	virtnet_napi_enable(rq->vq, &rq->napi);
> +	return 0;
> +
> +err:
> +	netdev_err(vi->dev,
> +		   "reset rx reset vq fail: rx queue index: %ld err: %d\n",
> +		   rq - vi->rq, err);
> +	virtnet_napi_enable(rq->vq, &rq->napi);
> +	return err;
> +}
> +
> +static int virtnet_tx_vq_reset(struct virtnet_info *vi,
> +			       struct send_queue *sq, u32 ring_num)
> +{

It looks to me it's better to rename this as "virtnet_rx_resize()"

> +	struct netdev_queue *txq;
> +	int err, qindex;
> +
> +	qindex = sq - vi->sq;
> +
> +	txq = netdev_get_tx_queue(vi->dev, qindex);
> +	__netif_tx_lock_bh(txq);
> +
> +	/* stop tx queue and napi */
> +	netif_stop_subqueue(vi->dev, qindex);
> +	virtnet_napi_tx_disable(&sq->napi);

There's no need to hold tx lock for napi disable.

Thanks

> +
> +	__netif_tx_unlock_bh(txq);
> +
> +	/* reset the queue */
> +	err = virtio_reset_vq(sq->vq);
> +	if (err) {
> +		netif_start_subqueue(vi->dev, qindex);
> +		goto err;
> +	}
> +
> +	/* free bufs */
> +	virtnet_sq_free_unused_bufs(vi, sq);
> +
> +	/* reset vring. */
> +	err = virtqueue_reset_vring(sq->vq, ring_num);
> +	if (err)
> +		goto err;
> +
> +	/* enable reset queue */
> +	err = virtio_enable_resetq(sq->vq);
> +	if (err)
> +		goto err;
> +
> +	/* start tx queue and napi */
> +	netif_start_subqueue(vi->dev, qindex);
> +	virtnet_napi_tx_enable(vi, sq->vq, &sq->napi);
> +	return 0;
> +
> +err:
> +	netdev_err(vi->dev,
> +		   "reset tx reset vq fail: tx queue index: %ld 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