X-Git-Url: http://git.efficios.com/?a=blobdiff_plain;f=drivers%2Fnet%2Fvirtio_net.c;h=e6b5d6ef9ea8223868375a0d2f184869b200b447;hb=5c5aa3f13a50881b8f6e529e321bbefb5faec37b;hp=c28d7cb2035b1dbcb5425aaeff55294d3f4eb786;hpb=7f9dce38378f0a4a298e885553d6bb7121376376;p=deliverable%2Flinux.git

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c28d7cb2035b..e6b5d6ef9ea8 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -19,6 +19,7 @@
 //#define DEBUG
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/virtio.h>
 #include <linux/virtio_net.h>
@@ -33,6 +34,7 @@ module_param(gso, bool, 0444);
 
 /* FIXME: MTU in config. */
 #define MAX_PACKET_LEN (ETH_HLEN+ETH_DATA_LEN)
+#define GOOD_COPY_LEN	128
 
 struct virtnet_info
 {
@@ -54,19 +56,50 @@ struct virtnet_info
 	struct tasklet_struct tasklet;
 	bool free_in_tasklet;
 
+	/* I like... big packets and I cannot lie! */
+	bool big_packets;
+
+	/* Host will merge rx buffers for big packets (shake it! shake it!) */
+	bool mergeable_rx_bufs;
+
 	/* Receive & send queues. */
 	struct sk_buff_head recv;
 	struct sk_buff_head send;
+
+	/* Chain pages by the private ptr. */
+	struct page *pages;
 };
 
-static inline struct virtio_net_hdr *skb_vnet_hdr(struct sk_buff *skb)
+static inline void *skb_vnet_hdr(struct sk_buff *skb)
 {
 	return (struct virtio_net_hdr *)skb->cb;
 }
 
-static inline void vnet_hdr_to_sg(struct scatterlist *sg, struct sk_buff *skb)
+static void give_a_page(struct virtnet_info *vi, struct page *page)
 {
-	sg_init_one(sg, skb_vnet_hdr(skb), sizeof(struct virtio_net_hdr));
+	page->private = (unsigned long)vi->pages;
+	vi->pages = page;
+}
+
+static void trim_pages(struct virtnet_info *vi, struct sk_buff *skb)
+{
+	unsigned int i;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+		give_a_page(vi, skb_shinfo(skb)->frags[i].page);
+	skb_shinfo(skb)->nr_frags = 0;
+	skb->data_len = 0;
+}
+
+static struct page *get_a_page(struct virtnet_info *vi, gfp_t gfp_mask)
+{
+	struct page *p = vi->pages;
+
+	if (p)
+		vi->pages = (struct page *)p->private;
+	else
+		p = alloc_page(gfp_mask);
+	return p;
 }
 
 static void skb_xmit_done(struct virtqueue *svq)
@@ -87,18 +120,98 @@ static void skb_xmit_done(struct virtqueue *svq)
 static void receive_skb(struct net_device *dev, struct sk_buff *skb,
 			unsigned len)
 {
+	struct virtnet_info *vi = netdev_priv(dev);
 	struct virtio_net_hdr *hdr = skb_vnet_hdr(skb);
+	int err;
+	int i;
 
 	if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
 		dev->stats.rx_length_errors++;
 		goto drop;
 	}
-	len -= sizeof(struct virtio_net_hdr);
-	BUG_ON(len > MAX_PACKET_LEN);
 
-	skb_trim(skb, len);
+	if (vi->mergeable_rx_bufs) {
+		struct virtio_net_hdr_mrg_rxbuf *mhdr = skb_vnet_hdr(skb);
+		unsigned int copy;
+		char *p = page_address(skb_shinfo(skb)->frags[0].page);
 
+		if (len > PAGE_SIZE)
+			len = PAGE_SIZE;
+		len -= sizeof(struct virtio_net_hdr_mrg_rxbuf);
+
+		memcpy(hdr, p, sizeof(*mhdr));
+		p += sizeof(*mhdr);
+
+		copy = len;
+		if (copy > skb_tailroom(skb))
+			copy = skb_tailroom(skb);
+
+		memcpy(skb_put(skb, copy), p, copy);
+
+		len -= copy;
+
+		if (!len) {
+			give_a_page(vi, skb_shinfo(skb)->frags[0].page);
+			skb_shinfo(skb)->nr_frags--;
+		} else {
+			skb_shinfo(skb)->frags[0].page_offset +=
+				sizeof(*mhdr) + copy;
+			skb_shinfo(skb)->frags[0].size = len;
+			skb->data_len += len;
+			skb->len += len;
+		}
+
+		while (--mhdr->num_buffers) {
+			struct sk_buff *nskb;
+
+			i = skb_shinfo(skb)->nr_frags;
+			if (i >= MAX_SKB_FRAGS) {
+				pr_debug("%s: packet too long %d\n", dev->name,
+					 len);
+				dev->stats.rx_length_errors++;
+				goto drop;
+			}
+
+			nskb = vi->rvq->vq_ops->get_buf(vi->rvq, &len);
+			if (!nskb) {
+				pr_debug("%s: rx error: %d buffers missing\n",
+					 dev->name, mhdr->num_buffers);
+				dev->stats.rx_length_errors++;
+				goto drop;
+			}
+
+			__skb_unlink(nskb, &vi->recv);
+			vi->num--;
+
+			skb_shinfo(skb)->frags[i] = skb_shinfo(nskb)->frags[0];
+			skb_shinfo(nskb)->nr_frags = 0;
+			kfree_skb(nskb);
+
+			if (len > PAGE_SIZE)
+				len = PAGE_SIZE;
+
+			skb_shinfo(skb)->frags[i].size = len;
+			skb_shinfo(skb)->nr_frags++;
+			skb->data_len += len;
+			skb->len += len;
+		}
+	} else {
+		len -= sizeof(struct virtio_net_hdr);
+
+		if (len <= MAX_PACKET_LEN)
+			trim_pages(vi, skb);
+
+		err = pskb_trim(skb, len);
+		if (err) {
+			pr_debug("%s: pskb_trim failed %i %d\n", dev->name,
+				 len, err);
+			dev->stats.rx_dropped++;
+			goto drop;
+		}
+	}
+
+	skb->truesize += skb->data_len;
 	dev->stats.rx_bytes += skb->len;
 	dev->stats.rx_packets++;
 
@@ -156,24 +269,95 @@ drop:
 	dev_kfree_skb(skb);
 }
 
-static void try_fill_recv(struct virtnet_info *vi)
+static void try_fill_recv_maxbufs(struct virtnet_info *vi)
 {
 	struct sk_buff *skb;
 	struct scatterlist sg[2+MAX_SKB_FRAGS];
-	int num, err;
+	int num, err, i;
 
 	sg_init_table(sg, 2+MAX_SKB_FRAGS);
 	for (;;) {
+		struct virtio_net_hdr *hdr;
+
 		skb = netdev_alloc_skb(vi->dev, MAX_PACKET_LEN);
 		if (unlikely(!skb))
 			break;
 
 		skb_put(skb, MAX_PACKET_LEN);
-		vnet_hdr_to_sg(sg, skb);
+
+		hdr = skb_vnet_hdr(skb);
+		sg_init_one(sg, hdr, sizeof(*hdr));
+
+		if (vi->big_packets) {
+			for (i = 0; i < MAX_SKB_FRAGS; i++) {
+				skb_frag_t *f = &skb_shinfo(skb)->frags[i];
+				f->page = get_a_page(vi, GFP_ATOMIC);
+				if (!f->page)
+					break;
+
+				f->page_offset = 0;
+				f->size = PAGE_SIZE;
+
+				skb->data_len += PAGE_SIZE;
+				skb->len += PAGE_SIZE;
+
+				skb_shinfo(skb)->nr_frags++;
+			}
+		}
+
 		num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
 		skb_queue_head(&vi->recv, skb);
 
 		err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, num, skb);
+		if (err) {
+			skb_unlink(skb, &vi->recv);
+			trim_pages(vi, skb);
+			kfree_skb(skb);
+			break;
+		}
+		vi->num++;
+	}
+	if (unlikely(vi->num > vi->max))
+		vi->max = vi->num;
+	vi->rvq->vq_ops->kick(vi->rvq);
+}
+
+static void try_fill_recv(struct virtnet_info *vi)
+{
+	struct sk_buff *skb;
+	struct scatterlist sg[1];
+	int err;
+
+	if (!vi->mergeable_rx_bufs) {
+		try_fill_recv_maxbufs(vi);
+		return;
+	}
+
+	for (;;) {
+		skb_frag_t *f;
+
+		skb = netdev_alloc_skb(vi->dev, GOOD_COPY_LEN + NET_IP_ALIGN);
+		if (unlikely(!skb))
+			break;
+
+		skb_reserve(skb, NET_IP_ALIGN);
+
+		f = &skb_shinfo(skb)->frags[0];
+		f->page = get_a_page(vi, GFP_ATOMIC);
+		if (!f->page) {
+			kfree_skb(skb);
+			break;
+		}
+
+		f->page_offset = 0;
+		f->size = PAGE_SIZE;
+
+		skb_shinfo(skb)->nr_frags++;
+
+		sg_init_one(sg, page_address(f->page), PAGE_SIZE);
+		skb_queue_head(&vi->recv, skb);
+
+		err = vi->rvq->vq_ops->add_buf(vi->rvq, sg, 0, 1, skb);
 		if (err) {
 			skb_unlink(skb, &vi->recv);
 			kfree_skb(skb);
@@ -264,17 +448,14 @@ static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
 {
 	int num, err;
 	struct scatterlist sg[2+MAX_SKB_FRAGS];
-	struct virtio_net_hdr *hdr;
+	struct virtio_net_hdr_mrg_rxbuf *mhdr = skb_vnet_hdr(skb);
+	struct virtio_net_hdr *hdr = skb_vnet_hdr(skb);
 	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
 
 	sg_init_table(sg, 2+MAX_SKB_FRAGS);
 
-	pr_debug("%s: xmit %p " MAC_FMT "\n", vi->dev->name, skb,
-		 dest[0], dest[1], dest[2],
-		 dest[3], dest[4], dest[5]);
+	pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
 
-	/* Encode metadata header at front. */
-	hdr = skb_vnet_hdr(skb);
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
 		hdr->csum_start = skb->csum_start - skb_headroom(skb);
@@ -302,7 +483,14 @@ static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
 		hdr->gso_size = hdr->hdr_len = 0;
 	}
 
-	vnet_hdr_to_sg(sg, skb);
+	mhdr->num_buffers = 0;
+
+	/* Encode metadata header at front. */
+	if (vi->mergeable_rx_bufs)
+		sg_init_one(sg, mhdr, sizeof(*mhdr));
+	else
+		sg_init_one(sg, hdr, sizeof(*hdr));
+
 	num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
 
 	err = vi->svq->vq_ops->add_buf(vi->svq, sg, num, 0, skb);
@@ -335,16 +523,11 @@ again:
 	free_old_xmit_skbs(vi);
 
 	/* If we has a buffer left over from last time, send it now. */
-	if (unlikely(vi->last_xmit_skb)) {
-		if (xmit_skb(vi, vi->last_xmit_skb) != 0) {
-			/* Drop this skb: we only queue one. */
-			vi->dev->stats.tx_dropped++;
-			kfree_skb(skb);
-			skb = NULL;
-			goto stop_queue;
-		}
-		vi->last_xmit_skb = NULL;
-	}
+	if (unlikely(vi->last_xmit_skb) &&
+	    xmit_skb(vi, vi->last_xmit_skb) != 0)
+		goto stop_queue;
+
+	vi->last_xmit_skb = NULL;
 
 	/* Put new one in send queue and do transmit */
 	if (likely(skb)) {
@@ -370,6 +553,11 @@ stop_queue:
 		netif_start_queue(dev);
 		goto again;
 	}
+	if (skb) {
+		/* Drop this skb: we only queue one. */
+		vi->dev->stats.tx_dropped++;
+		kfree_skb(skb);
+	}
 	goto done;
 }
 
@@ -408,6 +596,23 @@ static int virtnet_close(struct net_device *dev)
 	return 0;
 }
 
+static int virtnet_set_tx_csum(struct net_device *dev, u32 data)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	struct virtio_device *vdev = vi->vdev;
+
+	if (data && !virtio_has_feature(vdev, VIRTIO_NET_F_CSUM))
+		return -ENOSYS;
+
+	return ethtool_op_set_tx_hw_csum(dev, data);
+}
+
+static struct ethtool_ops virtnet_ethtool_ops = {
+	.set_tx_csum = virtnet_set_tx_csum,
+	.set_sg = ethtool_op_set_sg,
+	.set_tso = ethtool_op_set_tso,
+};
+
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int err;
@@ -427,6 +632,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	dev->poll_controller = virtnet_netpoll;
 #endif
+	SET_ETHTOOL_OPS(dev, &virtnet_ethtool_ops);
 	SET_NETDEV_DEV(dev, &vdev->dev);
 
 	/* Do we support "hardware" checksums? */
@@ -462,11 +668,21 @@ static int virtnet_probe(struct virtio_device *vdev)
 	vi->dev = dev;
 	vi->vdev = vdev;
 	vdev->priv = vi;
+	vi->pages = NULL;
 
 	/* If they give us a callback when all buffers are done, we don't need
 	 * the timer. */
 	vi->free_in_tasklet = virtio_has_feature(vdev,VIRTIO_F_NOTIFY_ON_EMPTY);
 
+	/* If we can receive ANY GSO packets, we must allocate large ones. */
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4)
+	    || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6)
+	    || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+		vi->big_packets = true;
+
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
+		vi->mergeable_rx_bufs = true;
+
 	/* We expect two virtqueues, receive then send. */
 	vi->rvq = vdev->config->find_vq(vdev, 0, skb_recv_done);
 	if (IS_ERR(vi->rvq)) {
@@ -541,6 +757,10 @@ static void virtnet_remove(struct virtio_device *vdev)
 	vdev->config->del_vq(vi->svq);
 	vdev->config->del_vq(vi->rvq);
 	unregister_netdev(vi->dev);
+
+	while (vi->pages)
+		__free_pages(get_a_page(vi, GFP_KERNEL), 0);
+
 	free_netdev(vi->dev);
 }
 
@@ -553,7 +773,10 @@ static unsigned int features[] = {
 	VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM,
 	VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC,
 	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6,
-	VIRTIO_NET_F_HOST_ECN, VIRTIO_F_NOTIFY_ON_EMPTY,
+	VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
+	VIRTIO_NET_F_GUEST_ECN, /* We don't yet handle UFO input. */
+	VIRTIO_NET_F_MRG_RXBUF,
+	VIRTIO_F_NOTIFY_ON_EMPTY,
 };
 
 static struct virtio_driver virtio_net = {