virtio: wean net driver off NETDEV_TX_BUSY

diff -r 26ba2dd67f46 drivers/net/virtio_net.c
@@ -40,6 +40,9 @@ struct virtnet_info
 	struct virtqueue *rvq, *svq;
 	struct net_device *dev;
 	struct napi_struct napi;
+
+	/* The skb we couldn't send because buffers were full. */
+	struct sk_buff *last_xmit_skb;
 
 	/* Number of input buffers, and max we've ever had. */
 	unsigned int num, max;

@@ -227,17 +230,16 @@ static void free_old_xmit_skbs(struct vi
 	}
 }
 
-static int start_xmit(struct sk_buff *skb, struct net_device *dev)
+static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
 {
-	struct virtnet_info *vi = netdev_priv(dev);
-	int num, err;
+	int num;
 	struct scatterlist sg[2+MAX_SKB_FRAGS];
 	struct virtio_net_hdr *hdr;
 	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", dev->name, skb,
+	pr_debug("%s: xmit %p " MAC_FMT "\n", vi->dev->name, skb,
 		 dest[0], dest[1], dest[2],
 		 dest[3], dest[4], dest[5]);
 

@@ -272,30 +274,50 @@ static int start_xmit(struct sk_buff *sk
 
 	vnet_hdr_to_sg(sg, skb);
 	num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
-	__skb_queue_head(&vi->send, skb);
+
+	return vi->svq->vq_ops->add_buf(vi->svq, sg, num, 0, skb);
+}
+
+static int start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
 
 again:
 	/* Free up any pending old buffers before queueing new ones. */
 	free_old_xmit_skbs(vi);
-	err = vi->svq->vq_ops->add_buf(vi->svq, sg, num, 0, skb);
-	if (err) {
-		pr_debug("%s: virtio not prepared to send\n", dev->name);
-		netif_stop_queue(dev);
 
-		/* Activate callback for using skbs: if this returns false it
-		 * means some were used in the meantime. */
-		if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) {
-			vi->svq->vq_ops->disable_cb(vi->svq);
-			netif_start_queue(dev);
-			goto again;
+	/* If we has a buffer left over from last time, send it now. */
+	if (vi->last_xmit_skb) {
+		if (xmit_skb(vi, vi->last_xmit_skb) != 0) {
+			/* Drop this skb: we only queue one. */
+			kfree_skb(skb);
+			goto stop_queue;
 		}
-		__skb_unlink(skb, &vi->send);
+		vi->last_xmit_skb = NULL;
+	}
 
-		return NETDEV_TX_BUSY;
+	/* Put new one in send queue and do transmit */
+	__skb_queue_head(&vi->send, skb);
+	if (xmit_skb(vi, skb) != 0) {
+		vi->last_xmit_skb = skb;
+		goto stop_queue;
 	}
+done:
 	vi->svq->vq_ops->kick(vi->svq);
+	return NETDEV_TX_OK;
 
-	return 0;
+stop_queue:
+	pr_debug("%s: virtio not prepared to send\n", dev->name);
+	netif_stop_queue(dev);
+
+	/* Activate callback for using skbs: if this returns false it
+	 * means some were used in the meantime. */
+	if (unlikely(!vi->svq->vq_ops->enable_cb(vi->svq))) {
+		vi->svq->vq_ops->disable_cb(vi->svq);
+		netif_start_queue(dev);
+		goto again;
+	}
+	goto done;
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER

diff -r effa8facedf1 drivers/net/virtio_net.c
@@ -381,6 +381,15 @@ static int virtnet_probe(struct virtio_d
 			dev->features |= NETIF_F_TSO | NETIF_F_UFO
 				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
 		}
+		/* Individual feature bits: what can host handle? */
+		if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_HOST_TSO4))
+			dev->features |= NETIF_F_TSO;
+		if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_HOST_TSO6))
+			dev->features |= NETIF_F_TSO6;
+		if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_HOST_ECN))
+			dev->features |= NETIF_F_TSO_ECN;
+		if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_HOST_UFO))
+			dev->features |= NETIF_F_UFO;
 	}
 
 	/* Configuration may specify what MAC to use.  Otherwise random. */

diff -r effa8facedf1 include/linux/virtio_net.h
@@ -6,9 +6,18 @@
 #define VIRTIO_ID_NET	1
 
 /* The feature bitmap for virtio net */
-#define VIRTIO_NET_F_CSUM	0	/* Can handle pkts w/ partial csum */
+#define VIRTIO_NET_F_CSUM	0	/* Host handles pkts w/ partial csum */
+#define VIRTIO_NET_F_GUEST_CSUM	1	/* Guest handles pkts w/ partial csum */
 #define VIRTIO_NET_F_MAC	5	/* Host has given MAC address. */
-#define VIRTIO_NET_F_GSO	6	/* Can handle pkts w/ any GSO type */
+#define VIRTIO_NET_F_GSO	6	/* Host handles pkts w/ any GSO type */
+#define VIRTIO_NET_F_GUEST_TSO4	7	/* Guest can handle TSOv4 in. */
+#define VIRTIO_NET_F_GUEST_TSO6	8	/* Guest can handle TSOv6 in. */
+#define VIRTIO_NET_F_GUEST_ECN	9	/* Guest can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_GUEST_UFO	10	/* Guest can handle UFO in. */
+#define VIRTIO_NET_F_HOST_TSO4	11	/* Host can handle TSOv4 in. */
+#define VIRTIO_NET_F_HOST_TSO6	12	/* Host can handle TSOv6 in. */
+#define VIRTIO_NET_F_HOST_ECN	13	/* Host can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_HOST_UFO	14	/* Host can handle UFO in. */
 
 struct virtio_net_config
 {

diff -r effa8facedf1 drivers/net/virtio_net.c
@@ -381,6 +381,15 @@ static int virtnet_probe(struct virtio_d
 			dev->features |= NETIF_F_TSO | NETIF_F_UFO
 				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
 		}
+		/* Individual feature bits: what can host handle? */
+		if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_HOST_TSO4))
+			dev->features |= NETIF_F_TSO;
+		if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_HOST_TSO6))
+			dev->features |= NETIF_F_TSO6;
+		if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_HOST_ECN))
+			dev->features |= NETIF_F_TSO_ECN;
+		if (gso && vdev->config->feature(vdev, VIRTIO_NET_F_HOST_UFO))
+			dev->features |= NETIF_F_UFO;
 	}
 
 	/* Configuration may specify what MAC to use.  Otherwise random. */

diff -r effa8facedf1 include/linux/virtio_net.h
@@ -6,9 +6,18 @@
 #define VIRTIO_ID_NET	1
 
 /* The feature bitmap for virtio net */
-#define VIRTIO_NET_F_CSUM	0	/* Can handle pkts w/ partial csum */
+#define VIRTIO_NET_F_CSUM	0	/* Host handles pkts w/ partial csum */
+#define VIRTIO_NET_F_GUEST_CSUM	1	/* Guest handles pkts w/ partial csum */
 #define VIRTIO_NET_F_MAC	5	/* Host has given MAC address. */
-#define VIRTIO_NET_F_GSO	6	/* Can handle pkts w/ any GSO type */
+#define VIRTIO_NET_F_GSO	6	/* Host handles pkts w/ any GSO type */
+#define VIRTIO_NET_F_GUEST_TSO4	7	/* Guest can handle TSOv4 in. */
+#define VIRTIO_NET_F_GUEST_TSO6	8	/* Guest can handle TSOv6 in. */
+#define VIRTIO_NET_F_GUEST_ECN	9	/* Guest can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_GUEST_UFO	10	/* Guest can handle UFO in. */
+#define VIRTIO_NET_F_HOST_TSO4	11	/* Host can handle TSOv4 in. */
+#define VIRTIO_NET_F_HOST_TSO6	12	/* Host can handle TSOv6 in. */
+#define VIRTIO_NET_F_HOST_ECN	13	/* Host can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_HOST_UFO	14	/* Host can handle UFO in. */
 
 struct virtio_net_config
 {

@@ -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>

@@ -352,6 +353,22 @@ static int virtnet_close(struct net_devi
 	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,
+};
+
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int err;

@@ -371,6 +389,7 @@ static int virtnet_probe(struct virtio_d
 #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? */

@@ -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>

@@ -352,6 +353,22 @@ static int virtnet_close(struct net_devi
 	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,
+};
+
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int err;

@@ -371,6 +389,7 @@ static int virtnet_probe(struct virtio_d
 #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? */

@@ -77,6 +77,7 @@ static void receive_skb(struct net_devic
 			unsigned len)
 {
 	struct virtio_net_hdr *hdr = skb_vnet_hdr(skb);
+	int err;
 
 	if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);

@@ -84,9 +85,15 @@ static void receive_skb(struct net_devic
 		goto drop;
 	}
 	len -= sizeof(struct virtio_net_hdr);
-	BUG_ON(len > MAX_PACKET_LEN);
 
-	skb_trim(skb, len);
+	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;
+
 	skb->protocol = eth_type_trans(skb, dev);
 	pr_debug("Receiving skb proto 0x%04x len %i type %i\n",
 		 ntohs(skb->protocol), skb->len, skb->pkt_type);

@@ -147,7 +154,7 @@ static void try_fill_recv(struct virtnet
 {
 	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 (;;) {

@@ -157,6 +164,24 @@ static void try_fill_recv(struct virtnet
 
 		skb_put(skb, MAX_PACKET_LEN);
 		vnet_hdr_to_sg(sg, skb);
+
+		if (vi->dev->features & NETIF_F_LRO) {
+			for (i = 0; i < MAX_SKB_FRAGS; i++) {
+				skb_frag_t *f = &skb_shinfo(skb)->frags[i];
+				f->page = alloc_page(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);
 

@@ -411,6 +436,12 @@ static int virtnet_probe(struct virtio_d
 			dev->features |= NETIF_F_UFO;
 	}
 
+	/* 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))
+		dev->features |= NETIF_F_LRO;
+
 	/* Configuration may specify what MAC to use.  Otherwise random. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) {
 		vdev->config->get(vdev,

@@ -504,7 +535,8 @@ static unsigned int features[] = {
 static unsigned int features[] = {
 	VIRTIO_NET_F_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_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. */
 };
 
 static struct virtio_driver virtio_net = {

@@ -77,6 +77,7 @@ static void receive_skb(struct net_devic
 			unsigned len)
 {
 	struct virtio_net_hdr *hdr = skb_vnet_hdr(skb);
+	int err;
 
 	if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);

@@ -84,9 +85,15 @@ static void receive_skb(struct net_devic
 		goto drop;
 	}
 	len -= sizeof(struct virtio_net_hdr);
-	BUG_ON(len > MAX_PACKET_LEN);
 
-	skb_trim(skb, len);
+	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;
+
 	skb->protocol = eth_type_trans(skb, dev);
 	pr_debug("Receiving skb proto 0x%04x len %i type %i\n",
 		 ntohs(skb->protocol), skb->len, skb->pkt_type);

@@ -147,7 +154,7 @@ static void try_fill_recv(struct virtnet
 {
 	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 (;;) {

@@ -157,6 +164,24 @@ static void try_fill_recv(struct virtnet
 
 		skb_put(skb, MAX_PACKET_LEN);
 		vnet_hdr_to_sg(sg, skb);
+
+		if (vi->dev->features & NETIF_F_LRO) {
+			for (i = 0; i < MAX_SKB_FRAGS; i++) {
+				skb_frag_t *f = &skb_shinfo(skb)->frags[i];
+				f->page = alloc_page(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);
 

@@ -411,6 +436,12 @@ static int virtnet_probe(struct virtio_d
 			dev->features |= NETIF_F_UFO;
 	}
 
+	/* 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))
+		dev->features |= NETIF_F_LRO;
+
 	/* Configuration may specify what MAC to use.  Otherwise random. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) {
 		vdev->config->get(vdev,

@@ -504,7 +535,8 @@ static unsigned int features[] = {
 static unsigned int features[] = {
 	VIRTIO_NET_F_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_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. */
 };
 
 static struct virtio_driver virtio_net = {