Re: [Qemu-devel] [net-next RFC PATCH 7/7] virtio-net changes

From: Sasha Levin <levinsasha928@gmail.com>
To: Jason Wang <jasowang@redhat.com>
Cc: mst@redhat.com, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org, davem@davemloft.net,
	krkumar2@in.ibm.com, rusty@rustcorp.com.au,
	qemu-devel@nongnu.org, kvm@vger.kernel.org,
	mirq-linux@rere.qmqm.pl
Subject: Re: [Qemu-devel] [net-next RFC PATCH 7/7] virtio-net changes
Date: Fri, 12 Aug 2011 12:09:16 +0300	[thread overview]
Message-ID: <1313140156.3651.1.camel@lappy> (raw)
In-Reply-To: <20110812015551.31613.13885.stgit@intel-e5620-16-2.englab.nay.redhat.com>

On Fri, 2011-08-12 at 09:55 +0800, Jason Wang wrote:
> From: Krishna Kumar <krkumar2@in.ibm.com>
> 
> Implement mq virtio-net driver.
> 
> Though struct virtio_net_config changes, it works with the old
> qemu since the last element is not accessed unless qemu sets
> VIRTIO_NET_F_MULTIQUEUE.
> 
> Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
> Signed-off-by: Jason Wang <jasowang@redhat.com>
> ---

Could these changes be documented to virtio-spec as well?

>  drivers/net/virtio_net.c   |  578 +++++++++++++++++++++++++++++++-------------
>  include/linux/virtio_net.h |    3 
>  2 files changed, 411 insertions(+), 170 deletions(-)
> 
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 0c7321c..03a199d 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -49,16 +49,48 @@ struct virtnet_stats {
>  	u64 rx_packets;
>  };
>  
> -struct virtnet_info {
> -	struct virtio_device *vdev;
> -	struct virtqueue *rvq, *svq, *cvq;
> -	struct net_device *dev;
> +/* Internal representation of a send virtqueue */
> +struct send_queue {
> +	/* Virtqueue associated with this send _queue */
> +	struct virtqueue *svq;
> +
> +	/* TX: fragments + linear part + virtio header */
> +	struct scatterlist tx_sg[MAX_SKB_FRAGS + 2];
> +};
> +
> +/* Internal representation of a receive virtqueue */
> +struct receive_queue {
> +	/* Virtqueue associated with this receive_queue */
> +	struct virtqueue *rvq;
> +
> +	/* Back pointer to the virtnet_info */
> +	struct virtnet_info *vi;
> +
>  	struct napi_struct napi;
> -	unsigned int status;
>  
>  	/* Number of input buffers, and max we've ever had. */
>  	unsigned int num, max;
>  
> +	/* Work struct for refilling if we run low on memory. */
> +	struct delayed_work refill;
> +
> +	/* Chain pages by the private ptr. */
> +	struct page *pages;
> +
> +	/* RX: fragments + linear part + virtio header */
> +	struct scatterlist rx_sg[MAX_SKB_FRAGS + 2];
> +};
> +
> +struct virtnet_info {
> +	struct send_queue **sq;
> +	struct receive_queue **rq;
> +
> +	int numtxqs; /* # of rxqs/txqs */
> +	struct virtio_device *vdev;
> +	struct virtqueue *cvq;
> +	struct net_device *dev;
> +	unsigned int status;
> +
>  	/* I like... big packets and I cannot lie! */
>  	bool big_packets;
>  
> @@ -67,16 +99,6 @@ struct virtnet_info {
>  
>  	/* Active statistics */
>  	struct virtnet_stats __percpu *stats;
> -
> -	/* Work struct for refilling if we run low on memory. */
> -	struct delayed_work refill;
> -
> -	/* Chain pages by the private ptr. */
> -	struct page *pages;
> -
> -	/* fragments + linear part + virtio header */
> -	struct scatterlist rx_sg[MAX_SKB_FRAGS + 2];
> -	struct scatterlist tx_sg[MAX_SKB_FRAGS + 2];
>  };
>  
>  struct skb_vnet_hdr {
> @@ -106,22 +128,22 @@ static inline struct skb_vnet_hdr *skb_vnet_hdr(struct sk_buff *skb)
>   * private is used to chain pages for big packets, put the whole
>   * most recent used list in the beginning for reuse
>   */
> -static void give_pages(struct virtnet_info *vi, struct page *page)
> +static void give_pages(struct receive_queue *rq, struct page *page)
>  {
>  	struct page *end;
>  
>  	/* Find end of list, sew whole thing into vi->pages. */
>  	for (end = page; end->private; end = (struct page *)end->private);
> -	end->private = (unsigned long)vi->pages;
> -	vi->pages = page;
> +	end->private = (unsigned long)rq->pages;
> +	rq->pages = page;
>  }
>  
> -static struct page *get_a_page(struct virtnet_info *vi, gfp_t gfp_mask)
> +static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
>  {
> -	struct page *p = vi->pages;
> +	struct page *p = rq->pages;
>  
>  	if (p) {
> -		vi->pages = (struct page *)p->private;
> +		rq->pages = (struct page *)p->private;
>  		/* clear private here, it is used to chain pages */
>  		p->private = 0;
>  	} else
> @@ -132,12 +154,13 @@ static struct page *get_a_page(struct virtnet_info *vi, gfp_t gfp_mask)
>  static void skb_xmit_done(struct virtqueue *svq)
>  {
>  	struct virtnet_info *vi = svq->vdev->priv;
> +	int qnum = svq->queue_index / 2; /* RX/TX vqs are allocated in pairs */
>  
>  	/* Suppress further interrupts. */
>  	virtqueue_disable_cb(svq);
>  
>  	/* We were probably waiting for more output buffers. */
> -	netif_wake_queue(vi->dev);
> +	netif_wake_subqueue(vi->dev, qnum);
>  }
>  
>  static void set_skb_frag(struct sk_buff *skb, struct page *page,
> @@ -157,9 +180,10 @@ static void set_skb_frag(struct sk_buff *skb, struct page *page,
>  	*len -= f->size;
>  }
>  
> -static struct sk_buff *page_to_skb(struct virtnet_info *vi,
> +static struct sk_buff *page_to_skb(struct receive_queue *rq,
>  				   struct page *page, unsigned int len)
>  {
> +	struct virtnet_info *vi = rq->vi;
>  	struct sk_buff *skb;
>  	struct skb_vnet_hdr *hdr;
>  	unsigned int copy, hdr_len, offset;
> @@ -202,12 +226,12 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
>  	}
>  
>  	if (page)
> -		give_pages(vi, page);
> +		give_pages(rq, page);
>  
>  	return skb;
>  }
>  
> -static int receive_mergeable(struct virtnet_info *vi, struct sk_buff *skb)
> +static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb)
>  {
>  	struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
>  	struct page *page;
> @@ -221,7 +245,8 @@ static int receive_mergeable(struct virtnet_info *vi, struct sk_buff *skb)
>  			skb->dev->stats.rx_length_errors++;
>  			return -EINVAL;
>  		}
> -		page = virtqueue_get_buf(vi->rvq, &len);
> +
> +		page = virtqueue_get_buf(rq->rvq, &len);
>  		if (!page) {
>  			pr_debug("%s: rx error: %d buffers missing\n",
>  				 skb->dev->name, hdr->mhdr.num_buffers);
> @@ -234,13 +259,14 @@ static int receive_mergeable(struct virtnet_info *vi, struct sk_buff *skb)
>  
>  		set_skb_frag(skb, page, 0, &len);
>  
> -		--vi->num;
> +		--rq->num;
>  	}
>  	return 0;
>  }
>  
> -static void receive_buf(struct net_device *dev, void *buf, unsigned int len)
> +static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
>  {
> +	struct net_device *dev = rq->vi->dev;
>  	struct virtnet_info *vi = netdev_priv(dev);
>  	struct virtnet_stats __percpu *stats = this_cpu_ptr(vi->stats);
>  	struct sk_buff *skb;
> @@ -251,7 +277,7 @@ static void receive_buf(struct net_device *dev, void *buf, unsigned int len)
>  		pr_debug("%s: short packet %i\n", dev->name, len);
>  		dev->stats.rx_length_errors++;
>  		if (vi->mergeable_rx_bufs || vi->big_packets)
> -			give_pages(vi, buf);
> +			give_pages(rq, buf);
>  		else
>  			dev_kfree_skb(buf);
>  		return;
> @@ -263,14 +289,14 @@ static void receive_buf(struct net_device *dev, void *buf, unsigned int len)
>  		skb_trim(skb, len);
>  	} else {
>  		page = buf;
> -		skb = page_to_skb(vi, page, len);
> +		skb = page_to_skb(rq, page, len);
>  		if (unlikely(!skb)) {
>  			dev->stats.rx_dropped++;
> -			give_pages(vi, page);
> +			give_pages(rq, page);
>  			return;
>  		}
>  		if (vi->mergeable_rx_bufs)
> -			if (receive_mergeable(vi, skb)) {
> +			if (receive_mergeable(rq, skb)) {
>  				dev_kfree_skb(skb);
>  				return;
>  			}
> @@ -341,184 +367,200 @@ frame_err:
>  	dev_kfree_skb(skb);
>  }
>  
> -static int add_recvbuf_small(struct virtnet_info *vi, gfp_t gfp)
> +static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp)
>  {
>  	struct sk_buff *skb;
>  	struct skb_vnet_hdr *hdr;
>  	int err;
>  
> -	skb = netdev_alloc_skb_ip_align(vi->dev, MAX_PACKET_LEN);
> +	skb = netdev_alloc_skb_ip_align(rq->vi->dev, MAX_PACKET_LEN);
>  	if (unlikely(!skb))
>  		return -ENOMEM;
>  
>  	skb_put(skb, MAX_PACKET_LEN);
>  
>  	hdr = skb_vnet_hdr(skb);
> -	sg_set_buf(vi->rx_sg, &hdr->hdr, sizeof hdr->hdr);
> +	sg_set_buf(rq->rx_sg, &hdr->hdr, sizeof hdr->hdr);
>  
> -	skb_to_sgvec(skb, vi->rx_sg + 1, 0, skb->len);
> +	skb_to_sgvec(skb, rq->rx_sg + 1, 0, skb->len);
>  
> -	err = virtqueue_add_buf_gfp(vi->rvq, vi->rx_sg, 0, 2, skb, gfp);
> +	err = virtqueue_add_buf_gfp(rq->rvq, rq->rx_sg, 0, 2, skb, gfp);
>  	if (err < 0)
>  		dev_kfree_skb(skb);
>  
>  	return err;
>  }
>  
> -static int add_recvbuf_big(struct virtnet_info *vi, gfp_t gfp)
> +static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp)
>  {
>  	struct page *first, *list = NULL;
>  	char *p;
>  	int i, err, offset;
>  
> -	/* page in vi->rx_sg[MAX_SKB_FRAGS + 1] is list tail */
> +	/* page in rq->rx_sg[MAX_SKB_FRAGS + 1] is list tail */
>  	for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
> -		first = get_a_page(vi, gfp);
> +		first = get_a_page(rq, gfp);
>  		if (!first) {
>  			if (list)
> -				give_pages(vi, list);
> +				give_pages(rq, list);
>  			return -ENOMEM;
>  		}
> -		sg_set_buf(&vi->rx_sg[i], page_address(first), PAGE_SIZE);
> +		sg_set_buf(&rq->rx_sg[i], page_address(first), PAGE_SIZE);
>  
>  		/* chain new page in list head to match sg */
>  		first->private = (unsigned long)list;
>  		list = first;
>  	}
>  
> -	first = get_a_page(vi, gfp);
> +	first = get_a_page(rq, gfp);
>  	if (!first) {
> -		give_pages(vi, list);
> +		give_pages(rq, list);
>  		return -ENOMEM;
>  	}
>  	p = page_address(first);
>  
> -	/* vi->rx_sg[0], vi->rx_sg[1] share the same page */
> -	/* a separated vi->rx_sg[0] for virtio_net_hdr only due to QEMU bug */
> -	sg_set_buf(&vi->rx_sg[0], p, sizeof(struct virtio_net_hdr));
> +	/* rq->rx_sg[0], rq->rx_sg[1] share the same page */
> +	/* a separated rq->rx_sg[0] for virtio_net_hdr only due to QEMU bug */
> +	sg_set_buf(&rq->rx_sg[0], p, sizeof(struct virtio_net_hdr));
>  
> -	/* vi->rx_sg[1] for data packet, from offset */
> +	/* rq->rx_sg[1] for data packet, from offset */
>  	offset = sizeof(struct padded_vnet_hdr);
> -	sg_set_buf(&vi->rx_sg[1], p + offset, PAGE_SIZE - offset);
> +	sg_set_buf(&rq->rx_sg[1], p + offset, PAGE_SIZE - offset);
>  
>  	/* chain first in list head */
>  	first->private = (unsigned long)list;
> -	err = virtqueue_add_buf_gfp(vi->rvq, vi->rx_sg, 0, MAX_SKB_FRAGS + 2,
> +	err = virtqueue_add_buf_gfp(rq->rvq, rq->rx_sg, 0, MAX_SKB_FRAGS + 2,
>  				    first, gfp);
>  	if (err < 0)
> -		give_pages(vi, first);
> +		give_pages(rq, first);
>  
>  	return err;
>  }
>  
> -static int add_recvbuf_mergeable(struct virtnet_info *vi, gfp_t gfp)
> +static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
>  {
>  	struct page *page;
>  	int err;
>  
> -	page = get_a_page(vi, gfp);
> +	page = get_a_page(rq, gfp);
>  	if (!page)
>  		return -ENOMEM;
>  
> -	sg_init_one(vi->rx_sg, page_address(page), PAGE_SIZE);
> +	sg_init_one(rq->rx_sg, page_address(page), PAGE_SIZE);
>  
> -	err = virtqueue_add_buf_gfp(vi->rvq, vi->rx_sg, 0, 1, page, gfp);
> +	err = virtqueue_add_buf_gfp(rq->rvq, rq->rx_sg, 0, 1, page, gfp);
>  	if (err < 0)
> -		give_pages(vi, page);
> +		give_pages(rq, page);
>  
>  	return err;
>  }
>  
>  /* Returns false if we couldn't fill entirely (OOM). */
> -static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp)
> +static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
>  {
> +	struct virtnet_info *vi = rq->vi;
>  	int err;
>  	bool oom;
>  
>  	do {
>  		if (vi->mergeable_rx_bufs)
> -			err = add_recvbuf_mergeable(vi, gfp);
> +			err = add_recvbuf_mergeable(rq, gfp);
>  		else if (vi->big_packets)
> -			err = add_recvbuf_big(vi, gfp);
> +			err = add_recvbuf_big(rq, gfp);
>  		else
> -			err = add_recvbuf_small(vi, gfp);
> +			err = add_recvbuf_small(rq, gfp);
>  
>  		oom = err == -ENOMEM;
>  		if (err < 0)
>  			break;
> -		++vi->num;
> +		++rq->num;
>  	} while (err > 0);
> -	if (unlikely(vi->num > vi->max))
> -		vi->max = vi->num;
> -	virtqueue_kick(vi->rvq);
> +	if (unlikely(rq->num > rq->max))
> +		rq->max = rq->num;
> +	virtqueue_kick(rq->rvq);
>  	return !oom;
>  }
>  
>  static void skb_recv_done(struct virtqueue *rvq)
>  {
> +	int qnum = rvq->queue_index / 2; /* RX/TX vqs are allocated in pairs */
>  	struct virtnet_info *vi = rvq->vdev->priv;
> +	struct napi_struct *napi = &vi->rq[qnum]->napi;
> +
>  	/* Schedule NAPI, Suppress further interrupts if successful. */
> -	if (napi_schedule_prep(&vi->napi)) {
> +	if (napi_schedule_prep(napi)) {
>  		virtqueue_disable_cb(rvq);
> -		__napi_schedule(&vi->napi);
> +		__napi_schedule(napi);
>  	}
>  }
>  
> -static void virtnet_napi_enable(struct virtnet_info *vi)
> +static void virtnet_napi_enable(struct receive_queue *rq)
>  {
> -	napi_enable(&vi->napi);
> +	napi_enable(&rq->napi);
>  
>  	/* If all buffers were filled by other side before we napi_enabled, we
>  	 * won't get another interrupt, so process any outstanding packets
>  	 * now.  virtnet_poll wants re-enable the queue, so we disable here.
>  	 * We synchronize against interrupts via NAPI_STATE_SCHED */
> -	if (napi_schedule_prep(&vi->napi)) {
> -		virtqueue_disable_cb(vi->rvq);
> -		__napi_schedule(&vi->napi);
> +	if (napi_schedule_prep(&rq->napi)) {
> +		virtqueue_disable_cb(rq->rvq);
> +		__napi_schedule(&rq->napi);
>  	}
>  }
>  
> +static void virtnet_napi_enable_all_queues(struct virtnet_info *vi)
> +{
> +	int i;
> +
> +	for (i = 0; i < vi->numtxqs; i++)
> +		virtnet_napi_enable(vi->rq[i]);
> +}
> +
>  static void refill_work(struct work_struct *work)
>  {
> -	struct virtnet_info *vi;
> +	struct napi_struct *napi;
> +	struct receive_queue *rq;
>  	bool still_empty;
>  
> -	vi = container_of(work, struct virtnet_info, refill.work);
> -	napi_disable(&vi->napi);
> -	still_empty = !try_fill_recv(vi, GFP_KERNEL);
> -	virtnet_napi_enable(vi);
> +	rq = container_of(work, struct receive_queue, refill.work);
> +	napi = &rq->napi;
> +
> +	napi_disable(napi);
> +	still_empty = !try_fill_recv(rq, GFP_KERNEL);
> +	virtnet_napi_enable(rq);
>  
>  	/* In theory, this can happen: if we don't get any buffers in
>  	 * we will *never* try to fill again. */
>  	if (still_empty)
> -		schedule_delayed_work(&vi->refill, HZ/2);
> +		schedule_delayed_work(&rq->refill, HZ/2);
>  }
>  
>  static int virtnet_poll(struct napi_struct *napi, int budget)
>  {
> -	struct virtnet_info *vi = container_of(napi, struct virtnet_info, napi);
> +	struct receive_queue *rq = container_of(napi, struct receive_queue,
> +						napi);
>  	void *buf;
>  	unsigned int len, received = 0;
>  
>  again:
>  	while (received < budget &&
> -	       (buf = virtqueue_get_buf(vi->rvq, &len)) != NULL) {
> -		receive_buf(vi->dev, buf, len);
> -		--vi->num;
> +	       (buf = virtqueue_get_buf(rq->rvq, &len)) != NULL) {
> +		receive_buf(rq, buf, len);
> +		--rq->num;
>  		received++;
>  	}
>  
> -	if (vi->num < vi->max / 2) {
> -		if (!try_fill_recv(vi, GFP_ATOMIC))
> -			schedule_delayed_work(&vi->refill, 0);
> +	if (rq->num < rq->max / 2) {
> +		if (!try_fill_recv(rq, GFP_ATOMIC))
> +			schedule_delayed_work(&rq->refill, 0);
>  	}
>  
>  	/* Out of packets? */
>  	if (received < budget) {
>  		napi_complete(napi);
> -		if (unlikely(!virtqueue_enable_cb(vi->rvq)) &&
> +		if (unlikely(!virtqueue_enable_cb(rq->rvq)) &&
>  		    napi_schedule_prep(napi)) {
> -			virtqueue_disable_cb(vi->rvq);
> +			virtqueue_disable_cb(rq->rvq);
>  			__napi_schedule(napi);
>  			goto again;
>  		}
> @@ -527,13 +569,14 @@ again:
>  	return received;
>  }
>  
> -static unsigned int free_old_xmit_skbs(struct virtnet_info *vi)
> +static unsigned int free_old_xmit_skbs(struct virtnet_info *vi,
> +				       struct virtqueue *svq)
>  {
>  	struct sk_buff *skb;
>  	unsigned int len, tot_sgs = 0;
>  	struct virtnet_stats __percpu *stats = this_cpu_ptr(vi->stats);
>  
> -	while ((skb = virtqueue_get_buf(vi->svq, &len)) != NULL) {
> +	while ((skb = virtqueue_get_buf(svq, &len)) != NULL) {
>  		pr_debug("Sent skb %p\n", skb);
>  
>  		u64_stats_update_begin(&stats->syncp);
> @@ -547,7 +590,8 @@ static unsigned int free_old_xmit_skbs(struct virtnet_info *vi)
>  	return tot_sgs;
>  }
>  
> -static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
> +static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb,
> +		    struct virtqueue *svq, struct scatterlist *tx_sg)
>  {
>  	struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
>  	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
> @@ -585,12 +629,12 @@ static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
>  
>  	/* Encode metadata header at front. */
>  	if (vi->mergeable_rx_bufs)
> -		sg_set_buf(vi->tx_sg, &hdr->mhdr, sizeof hdr->mhdr);
> +		sg_set_buf(tx_sg, &hdr->mhdr, sizeof hdr->mhdr);
>  	else
> -		sg_set_buf(vi->tx_sg, &hdr->hdr, sizeof hdr->hdr);
> +		sg_set_buf(tx_sg, &hdr->hdr, sizeof hdr->hdr);
>  
> -	hdr->num_sg = skb_to_sgvec(skb, vi->tx_sg + 1, 0, skb->len) + 1;
> -	return virtqueue_add_buf(vi->svq, vi->tx_sg, hdr->num_sg,
> +	hdr->num_sg = skb_to_sgvec(skb, tx_sg + 1, 0, skb->len) + 1;
> +	return virtqueue_add_buf(svq, tx_sg, hdr->num_sg,
>  					0, skb);
>  }
>  
> @@ -598,31 +642,34 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
>  {
>  	struct virtnet_info *vi = netdev_priv(dev);
>  	int capacity;
> +	int qnum = skb_get_queue_mapping(skb);
> +	struct virtqueue *svq = vi->sq[qnum]->svq;
>  
>  	/* Free up any pending old buffers before queueing new ones. */
> -	free_old_xmit_skbs(vi);
> +	free_old_xmit_skbs(vi, svq);
>  
>  	/* Try to transmit */
> -	capacity = xmit_skb(vi, skb);
> +	capacity = xmit_skb(vi, skb, svq, vi->sq[qnum]->tx_sg);
>  
>  	/* This can happen with OOM and indirect buffers. */
>  	if (unlikely(capacity < 0)) {
>  		if (net_ratelimit()) {
>  			if (likely(capacity == -ENOMEM)) {
>  				dev_warn(&dev->dev,
> -					 "TX queue failure: out of memory\n");
> +					 "TXQ (%d) failure: out of memory\n",
> +					 qnum);
>  			} else {
>  				dev->stats.tx_fifo_errors++;
>  				dev_warn(&dev->dev,
> -					 "Unexpected TX queue failure: %d\n",
> -					 capacity);
> +					 "Unexpected TXQ (%d) failure: %d\n",
> +					 qnum, capacity);
>  			}
>  		}
>  		dev->stats.tx_dropped++;
>  		kfree_skb(skb);
>  		return NETDEV_TX_OK;
>  	}
> -	virtqueue_kick(vi->svq);
> +	virtqueue_kick(svq);
>  
>  	/* Don't wait up for transmitted skbs to be freed. */
>  	skb_orphan(skb);
> @@ -631,13 +678,13 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
>  	/* Apparently nice girls don't return TX_BUSY; stop the queue
>  	 * before it gets out of hand.  Naturally, this wastes entries. */
>  	if (capacity < 2+MAX_SKB_FRAGS) {
> -		netif_stop_queue(dev);
> -		if (unlikely(!virtqueue_enable_cb_delayed(vi->svq))) {
> +		netif_stop_subqueue(dev, qnum);
> +		if (unlikely(!virtqueue_enable_cb_delayed(svq))) {
>  			/* More just got used, free them then recheck. */
> -			capacity += free_old_xmit_skbs(vi);
> +			capacity += free_old_xmit_skbs(vi, svq);
>  			if (capacity >= 2+MAX_SKB_FRAGS) {
> -				netif_start_queue(dev);
> -				virtqueue_disable_cb(vi->svq);
> +				netif_start_subqueue(dev, qnum);
> +				virtqueue_disable_cb(svq);
>  			}
>  		}
>  	}
> @@ -700,8 +747,10 @@ static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev,
>  static void virtnet_netpoll(struct net_device *dev)
>  {
>  	struct virtnet_info *vi = netdev_priv(dev);
> +	int i;
>  
> -	napi_schedule(&vi->napi);
> +	for (i = 0; i < vi->numtxqs; i++)
> +		napi_schedule(&vi->rq[i]->napi);
>  }
>  #endif
>  
> @@ -709,7 +758,7 @@ static int virtnet_open(struct net_device *dev)
>  {
>  	struct virtnet_info *vi = netdev_priv(dev);
>  
> -	virtnet_napi_enable(vi);
> +	virtnet_napi_enable_all_queues(vi);
>  	return 0;
>  }
>  
> @@ -761,8 +810,10 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
>  static int virtnet_close(struct net_device *dev)
>  {
>  	struct virtnet_info *vi = netdev_priv(dev);
> +	int i;
>  
> -	napi_disable(&vi->napi);
> +	for (i = 0; i < vi->numtxqs; i++)
> +		napi_disable(&vi->rq[i]->napi);
>  
>  	return 0;
>  }
> @@ -919,10 +970,10 @@ static void virtnet_update_status(struct virtnet_info *vi)
>  
>  	if (vi->status & VIRTIO_NET_S_LINK_UP) {
>  		netif_carrier_on(vi->dev);
> -		netif_wake_queue(vi->dev);
> +		netif_tx_wake_all_queues(vi->dev);
>  	} else {
>  		netif_carrier_off(vi->dev);
> -		netif_stop_queue(vi->dev);
> +		netif_tx_stop_all_queues(vi->dev);
>  	}
>  }
>  
> @@ -933,18 +984,222 @@ static void virtnet_config_changed(struct virtio_device *vdev)
>  	virtnet_update_status(vi);
>  }
>  
> +static void free_receive_bufs(struct virtnet_info *vi)
> +{
> +	int i;
> +
> +	for (i = 0; i < vi->numtxqs; i++) {
> +		BUG_ON(vi->rq[i] == NULL);
> +		while (vi->rq[i]->pages)
> +			__free_pages(get_a_page(vi->rq[i], GFP_KERNEL), 0);
> +	}
> +}
> +
> +/* Free memory allocated for send and receive queues */
> +static void free_rq_sq(struct virtnet_info *vi)
> +{
> +	int i;
> +
> +	if (vi->rq) {
> +		for (i = 0; i < vi->numtxqs; i++)
> +			kfree(vi->rq[i]);
> +		kfree(vi->rq);
> +	}
> +
> +	if (vi->sq) {
> +		for (i = 0; i < vi->numtxqs; i++)
> +			kfree(vi->sq[i]);
> +		kfree(vi->sq);
> +	}
> +}
> +
> +static void free_unused_bufs(struct virtnet_info *vi)
> +{
> +	void *buf;
> +	int i;
> +
> +	for (i = 0; i < vi->numtxqs; i++) {
> +		struct virtqueue *svq = vi->sq[i]->svq;
> +
> +		while (1) {
> +			buf = virtqueue_detach_unused_buf(svq);
> +			if (!buf)
> +				break;
> +			dev_kfree_skb(buf);
> +		}
> +	}
> +
> +	for (i = 0; i < vi->numtxqs; i++) {
> +		struct virtqueue *rvq = vi->rq[i]->rvq;
> +
> +		while (1) {
> +			buf = virtqueue_detach_unused_buf(rvq);
> +			if (!buf)
> +				break;
> +			if (vi->mergeable_rx_bufs || vi->big_packets)
> +				give_pages(vi->rq[i], buf);
> +			else
> +				dev_kfree_skb(buf);
> +			--vi->rq[i]->num;
> +		}
> +		BUG_ON(vi->rq[i]->num != 0);
> +	}
> +}
> +
> +#define MAX_DEVICE_NAME		16
> +static int initialize_vqs(struct virtnet_info *vi, int numtxqs)
> +{
> +	vq_callback_t **callbacks;
> +	struct virtqueue **vqs;
> +	int i, err = -ENOMEM;
> +	int totalvqs;
> +	char **names;
> +
> +	/* Allocate receive queues */
> +	vi->rq = kcalloc(numtxqs, sizeof(*vi->rq), GFP_KERNEL);
> +	if (!vi->rq)
> +		goto out;
> +	for (i = 0; i < numtxqs; i++) {
> +		vi->rq[i] = kzalloc(sizeof(*vi->rq[i]), GFP_KERNEL);
> +		if (!vi->rq[i])
> +			goto out;
> +	}
> +
> +	/* Allocate send queues */
> +	vi->sq = kcalloc(numtxqs, sizeof(*vi->sq), GFP_KERNEL);
> +	if (!vi->sq)
> +		goto out;
> +	for (i = 0; i < numtxqs; i++) {
> +		vi->sq[i] = kzalloc(sizeof(*vi->sq[i]), GFP_KERNEL);
> +		if (!vi->sq[i])
> +			goto out;
> +	}
> +
> +	/* setup initial receive and send queue parameters */
> +	for (i = 0; i < numtxqs; i++) {
> +		vi->rq[i]->vi = vi;
> +		vi->rq[i]->pages = NULL;
> +		INIT_DELAYED_WORK(&vi->rq[i]->refill, refill_work);
> +		netif_napi_add(vi->dev, &vi->rq[i]->napi, virtnet_poll,
> +			       napi_weight);
> +
> +		sg_init_table(vi->rq[i]->rx_sg, ARRAY_SIZE(vi->rq[i]->rx_sg));
> +		sg_init_table(vi->sq[i]->tx_sg, ARRAY_SIZE(vi->sq[i]->tx_sg));
> +	}
> +
> +	/*
> +	 * We expect 1 RX virtqueue followed by 1 TX virtqueues, followed
> +	 * by the same 'numtxqs-1' times, and optionally one control virtqueue.
> +	 */
> +	totalvqs = numtxqs * 2 +
> +		   virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ);
> +
> +	/* Allocate space for find_vqs parameters */
> +	vqs = kmalloc(totalvqs * sizeof(*vqs), GFP_KERNEL);
> +	callbacks = kmalloc(totalvqs * sizeof(*callbacks), GFP_KERNEL);
> +	names = kzalloc(totalvqs * sizeof(*names), GFP_KERNEL);
> +	if (!vqs || !callbacks || !names)
> +		goto free_params;
> +
> +#if 1
> +	/* Allocate/initialize parameters for recv/send virtqueues */
> +	for (i = 0; i < numtxqs * 2; i++) {
> +		names[i] = kmalloc(MAX_DEVICE_NAME * sizeof(*names[i]),
> +				   GFP_KERNEL);
> +		if (!names[i])
> +			goto free_params;
> +
> +		if (!(i & 1)) {		/* RX */
> +			callbacks[i] = skb_recv_done;
> +			sprintf(names[i], "input.%d", i / 2);
> +		} else {
> +			callbacks[i] = skb_xmit_done;
> +			sprintf(names[i], "output.%d", i / 2);
> +		}
> +	}
> +
> +	/* Parameters for control virtqueue, if any */
> +	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
> +		callbacks[i] = NULL;
> +		names[i] = "control";
> +	}
> +#else
> +	/* Allocate/initialize parameters for recv virtqueues */
> +	for (i = 0; i < numtxqs * 2; i += 2) {
> +		callbacks[i] = skb_recv_done;
> +		names[i] = kmalloc(MAX_DEVICE_NAME * sizeof(*names[i]),
> +				   GFP_KERNEL);
> +		if (!names[i])
> +			goto free_params;
> +		sprintf(names[i], "input.%d", i / 2);
> +	}
> +
> +	/* Allocate/initialize parameters for send virtqueues */
> +	for (i = 1; i < numtxqs * 2; i += 2) {
> +		callbacks[i] = skb_xmit_done;
> +		names[i] = kmalloc(MAX_DEVICE_NAME * sizeof(*names[i]),
> +				   GFP_KERNEL);
> +		if (!names[i])
> +			goto free_params;
> +		sprintf(names[i], "output.%d", i / 2);
> +	}
> +
> +	/* Parameters for control virtqueue, if any */
> +	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
> +		callbacks[i - 1] = NULL;
> +		names[i - 1] = "control";
> +	}
> +#endif
> +
> +	err = vi->vdev->config->find_vqs(vi->vdev, totalvqs, vqs, callbacks,
> +					 (const char **)names);
> +	if (err)
> +		goto free_params;
> +
> +	/* Assign the allocated vqs alternatively for RX/TX */
> +	for (i = 0; i < numtxqs * 2; i += 2) {
> +		vi->rq[i/2]->rvq = vqs[i];
> +		vi->sq[i/2]->svq = vqs[i + 1];
> +	}
> +
> +	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ))
> +		vi->cvq = vqs[i];
> +
> +free_params:
> +	if (names) {
> +		for (i = 0; i < numtxqs * 2; i++)
> +			kfree(names[i]);
> +		kfree(names);
> +	}
> +
> +	kfree(callbacks);
> +	kfree(vqs);
> +
> +out:
> +	if (err)
> +		free_rq_sq(vi);
> +
> +	return err;
> +}
> +
>  static int virtnet_probe(struct virtio_device *vdev)
>  {
> -	int err;
> +	int i, err;
> +	u16 numtxqs;
> +	u16 num_queue_pairs = 2;
>  	struct net_device *dev;
>  	struct virtnet_info *vi;
> -	struct virtqueue *vqs[3];
> -	vq_callback_t *callbacks[] = { skb_recv_done, skb_xmit_done, NULL};
> -	const char *names[] = { "input", "output", "control" };
> -	int nvqs;
> +
> +	/* Find if host supports MULTIQUEUE */
> +	err = virtio_config_val(vdev, VIRTIO_NET_F_MULTIQUEUE,
> +				offsetof(struct virtio_net_config,
> +				num_queue_pairs), &num_queue_pairs);
> +	numtxqs = num_queue_pairs / 2;
> +	if (!numtxqs)
> +		numtxqs = 1;
>  
>  	/* Allocate ourselves a network device with room for our info */
> -	dev = alloc_etherdev(sizeof(struct virtnet_info));
> +	dev = alloc_etherdev_mq(sizeof(struct virtnet_info), numtxqs);
>  	if (!dev)
>  		return -ENOMEM;
>  
> @@ -991,19 +1246,14 @@ static int virtnet_probe(struct virtio_device *vdev)
>  
>  	/* Set up our device-specific information */
>  	vi = netdev_priv(dev);
> -	netif_napi_add(dev, &vi->napi, virtnet_poll, napi_weight);
>  	vi->dev = dev;
>  	vi->vdev = vdev;
>  	vdev->priv = vi;
> -	vi->pages = NULL;
>  	vi->stats = alloc_percpu(struct virtnet_stats);
>  	err = -ENOMEM;
>  	if (vi->stats == NULL)
>  		goto free;
> -
> -	INIT_DELAYED_WORK(&vi->refill, refill_work);
> -	sg_init_table(vi->rx_sg, ARRAY_SIZE(vi->rx_sg));
> -	sg_init_table(vi->tx_sg, ARRAY_SIZE(vi->tx_sg));
> +	vi->numtxqs = numtxqs;
>  
>  	/* If we can receive ANY GSO packets, we must allocate large ones. */
>  	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
> @@ -1014,23 +1264,14 @@ static int virtnet_probe(struct virtio_device *vdev)
>  	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
>  		vi->mergeable_rx_bufs = true;
>  
> -	/* We expect two virtqueues, receive then send,
> -	 * and optionally control. */
> -	nvqs = virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ? 3 : 2;
> -
> -	err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
> +	/* Initialize our rx/tx queue parameters, and invoke find_vqs */
> +	err = initialize_vqs(vi, numtxqs);
>  	if (err)
>  		goto free_stats;
>  
> -	vi->rvq = vqs[0];
> -	vi->svq = vqs[1];
> -
> -	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)) {
> -		vi->cvq = vqs[2];
> -
> -		if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
> -			dev->features |= NETIF_F_HW_VLAN_FILTER;
> -	}
> +	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) &&
> +	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN))
> +		dev->features |= NETIF_F_HW_VLAN_FILTER;
>  
>  	err = register_netdev(dev);
>  	if (err) {
> @@ -1039,14 +1280,21 @@ static int virtnet_probe(struct virtio_device *vdev)
>  	}
>  
>  	/* Last of all, set up some receive buffers. */
> -	try_fill_recv(vi, GFP_KERNEL);
> -
> -	/* If we didn't even get one input buffer, we're useless. */
> -	if (vi->num == 0) {
> -		err = -ENOMEM;
> -		goto unregister;
> +	for (i = 0; i < numtxqs; i++) {
> +		try_fill_recv(vi->rq[i], GFP_KERNEL);
> +
> +		/* If we didn't even get one input buffer, we're useless. */
> +		if (vi->rq[i]->num == 0) {
> +			if (i)
> +				free_unused_bufs(vi);
> +			err = -ENOMEM;
> +			goto free_recv_bufs;
> +		}
>  	}
>  
> +	dev_info(&dev->dev, "(virtio-net) Allocated %d RX & TX vq's\n",
> +		 numtxqs);
> +
>  	/* Assume link up if device can't report link status,
>  	   otherwise get link status from config. */
>  	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
> @@ -1057,61 +1305,51 @@ static int virtnet_probe(struct virtio_device *vdev)
>  		netif_carrier_on(dev);
>  	}
>  
> -	pr_debug("virtnet: registered device %s\n", dev->name);
> +	pr_debug("virtnet: registered device %s with %d RX and TX vq's\n",
> +		 dev->name, numtxqs);
>  	return 0;
>  
> -unregister:
> +free_recv_bufs:
> +	free_receive_bufs(vi);
>  	unregister_netdev(dev);
> -	cancel_delayed_work_sync(&vi->refill);
> +
>  free_vqs:
> +	for (i = 0; i < numtxqs; i++)
> +		cancel_delayed_work_sync(&vi->rq[i]->refill);
>  	vdev->config->del_vqs(vdev);
> +	free_rq_sq(vi);
> +
>  free_stats:
>  	free_percpu(vi->stats);
> +
>  free:
>  	free_netdev(dev);
>  	return err;
>  }
>  
> -static void free_unused_bufs(struct virtnet_info *vi)
> -{
> -	void *buf;
> -	while (1) {
> -		buf = virtqueue_detach_unused_buf(vi->svq);
> -		if (!buf)
> -			break;
> -		dev_kfree_skb(buf);
> -	}
> -	while (1) {
> -		buf = virtqueue_detach_unused_buf(vi->rvq);
> -		if (!buf)
> -			break;
> -		if (vi->mergeable_rx_bufs || vi->big_packets)
> -			give_pages(vi, buf);
> -		else
> -			dev_kfree_skb(buf);
> -		--vi->num;
> -	}
> -	BUG_ON(vi->num != 0);
> -}
> -
>  static void __devexit virtnet_remove(struct virtio_device *vdev)
>  {
>  	struct virtnet_info *vi = vdev->priv;
> +	int i;
>  
>  	/* Stop all the virtqueues. */
>  	vdev->config->reset(vdev);
>  
> 
>  	unregister_netdev(vi->dev);
> -	cancel_delayed_work_sync(&vi->refill);
> +
> +	for (i = 0; i < vi->numtxqs; i++)
> +		cancel_delayed_work_sync(&vi->rq[i]->refill);
>  
>  	/* Free unused buffers in both send and recv, if any. */
>  	free_unused_bufs(vi);
>  
>  	vdev->config->del_vqs(vi->vdev);
>  
> -	while (vi->pages)
> -		__free_pages(get_a_page(vi, GFP_KERNEL), 0);
> +	free_receive_bufs(vi);
> +
> +	/* Free memory for send and receive queues */
> +	free_rq_sq(vi);
>  
>  	free_percpu(vi->stats);
>  	free_netdev(vi->dev);
> @@ -1129,7 +1367,7 @@ static unsigned int features[] = {
>  	VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
>  	VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
>  	VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
> -	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
> +	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, VIRTIO_NET_F_MULTIQUEUE,
>  };
>  
>  static struct virtio_driver virtio_net_driver = {
> diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
> index 970d5a2..fa85ac3 100644
> --- a/include/linux/virtio_net.h
> +++ b/include/linux/virtio_net.h
> @@ -49,6 +49,7 @@
>  #define VIRTIO_NET_F_CTRL_RX	18	/* Control channel RX mode support */
>  #define VIRTIO_NET_F_CTRL_VLAN	19	/* Control channel VLAN filtering */
>  #define VIRTIO_NET_F_CTRL_RX_EXTRA 20	/* Extra RX mode control support */
> +#define VIRTIO_NET_F_MULTIQUEUE	21	/* Device supports multiple TXQ/RXQ */
>  
>  #define VIRTIO_NET_S_LINK_UP	1	/* Link is up */
>  
> @@ -57,6 +58,8 @@ struct virtio_net_config {
>  	__u8 mac[6];
>  	/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
>  	__u16 status;
> +	/* total number of RX/TX queues */
> +	__u16 num_queue_pairs;
>  } __attribute__((packed));
>  
>  /* This is the first element of the scatter-gather list.  If you don't
> 
> 

-- 

Sasha.