1 files changed, 159 insertions, 105 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index fb5e68ed3ec27..486b5849033dc 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -62,7 +62,8 @@ static const unsigned long guest_offloads[] = {
 	VIRTIO_NET_F_GUEST_UFO,
 	VIRTIO_NET_F_GUEST_CSUM,
 	VIRTIO_NET_F_GUEST_USO4,
-	VIRTIO_NET_F_GUEST_USO6
+	VIRTIO_NET_F_GUEST_USO6,
+	VIRTIO_NET_F_GUEST_HDRLEN
 };
 
 #define GUEST_OFFLOAD_GRO_HW_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
@@ -204,6 +205,8 @@ struct control_buf {
 	__virtio16 vid;
 	__virtio64 offloads;
 	struct virtio_net_ctrl_rss rss;
+	struct virtio_net_ctrl_coal_tx coal_tx;
+	struct virtio_net_ctrl_coal_rx coal_rx;
 };
 
 struct virtnet_info {
@@ -446,7 +449,8 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
 static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct receive_queue *rq,
 				   struct page *page, unsigned int offset,
-				   unsigned int len, unsigned int truesize)
+				   unsigned int len, unsigned int truesize,
+				   unsigned int headroom)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -464,11 +468,11 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
-	buf = p;
+	buf = p - headroom;
 	len -= hdr_len;
 	offset += hdr_padded_len;
 	p += hdr_padded_len;
-	tailroom = truesize - hdr_padded_len - len;
+	tailroom = truesize - headroom  - hdr_padded_len - len;
 
 	shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
@@ -545,6 +549,87 @@ ok:
 	return skb;
 }
 
+static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
+{
+	unsigned int len;
+	unsigned int packets = 0;
+	unsigned int bytes = 0;
+	void *ptr;
+
+	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		if (likely(!is_xdp_frame(ptr))) {
+			struct sk_buff *skb = ptr;
+
+			pr_debug("Sent skb %p\n", skb);
+
+			bytes += skb->len;
+			napi_consume_skb(skb, in_napi);
+		} else {
+			struct xdp_frame *frame = ptr_to_xdp(ptr);
+
+			bytes += xdp_get_frame_len(frame);
+			xdp_return_frame(frame);
+		}
+		packets++;
+	}
+
+	/* Avoid overhead when no packets have been processed
+	 * happens when called speculatively from start_xmit.
+	 */
+	if (!packets)
+		return;
+
+	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.bytes += bytes;
+	sq->stats.packets += packets;
+	u64_stats_update_end(&sq->stats.syncp);
+}
+
+static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
+{
+	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
+		return false;
+	else if (q < vi->curr_queue_pairs)
+		return true;
+	else
+		return false;
+}
+
+static void check_sq_full_and_disable(struct virtnet_info *vi,
+				      struct net_device *dev,
+				      struct send_queue *sq)
+{
+	bool use_napi = sq->napi.weight;
+	int qnum;
+
+	qnum = sq - vi->sq;
+
+	/* If running out of space, stop queue to avoid getting packets that we
+	 * are then unable to transmit.
+	 * An alternative would be to force queuing layer to requeue the skb by
+	 * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be
+	 * returned in a normal path of operation: it means that driver is not
+	 * maintaining the TX queue stop/start state properly, and causes
+	 * the stack to do a non-trivial amount of useless work.
+	 * Since most packets only take 1 or 2 ring slots, stopping the queue
+	 * early means 16 slots are typically wasted.
+	 */
+	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
+		netif_stop_subqueue(dev, qnum);
+		if (use_napi) {
+			if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
+				virtqueue_napi_schedule(&sq->napi, sq->vq);
+		} else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
+			/* More just got used, free them then recheck. */
+			free_old_xmit_skbs(sq, false);
+			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
+				netif_start_subqueue(dev, qnum);
+				virtqueue_disable_cb(sq->vq);
+			}
+		}
+	}
+}
+
 static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 				   struct send_queue *sq,
 				   struct xdp_frame *xdpf)
@@ -686,6 +771,9 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 	ret = nxmit;
 
+	if (!is_xdp_raw_buffer_queue(vi, sq - vi->sq))
+		check_sq_full_and_disable(vi, dev, sq);
+
 	if (flags & XDP_XMIT_FLUSH) {
 		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq))
 			kicks = 1;
@@ -729,8 +817,13 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 				       int page_off,
 				       unsigned int *len)
 {
-	struct page *page = alloc_page(GFP_ATOMIC);
+	int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	struct page *page;
+
+	if (page_off + *len + tailroom > PAGE_SIZE)
+		return NULL;
 
+	page = alloc_page(GFP_ATOMIC);
 	if (!page)
 		return NULL;
 
@@ -738,7 +831,6 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 	page_off += *len;
 
 	while (--*num_buf) {
-		int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 		unsigned int buflen;
 		void *buf;
 		int off;
@@ -925,7 +1017,7 @@ static struct sk_buff *receive_big(struct net_device *dev,
 {
 	struct page *page = buf;
 	struct sk_buff *skb =
-		page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
+		page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, 0);
 
 	stats->bytes += len - vi->hdr_len;
 	if (unlikely(!skb))
@@ -1188,9 +1280,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 
 		switch (act) {
 		case XDP_PASS:
+			head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz);
+			if (unlikely(!head_skb))
+				goto err_xdp_frags;
+
 			if (unlikely(xdp_page != page))
 				put_page(page);
-			head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz);
 			rcu_read_unlock();
 			return head_skb;
 		case XDP_TX:
@@ -1248,7 +1343,7 @@ err_xdp_frags:
 	rcu_read_unlock();
 
 skip_xdp:
-	head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
+	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, headroom);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
@@ -1714,52 +1809,6 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	return stats.packets;
 }
 
-static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
-{
-	unsigned int len;
-	unsigned int packets = 0;
-	unsigned int bytes = 0;
-	void *ptr;
-
-	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		if (likely(!is_xdp_frame(ptr))) {
-			struct sk_buff *skb = ptr;
-
-			pr_debug("Sent skb %p\n", skb);
-
-			bytes += skb->len;
-			napi_consume_skb(skb, in_napi);
-		} else {
-			struct xdp_frame *frame = ptr_to_xdp(ptr);
-
-			bytes += xdp_get_frame_len(frame);
-			xdp_return_frame(frame);
-		}
-		packets++;
-	}
-
-	/* Avoid overhead when no packets have been processed
-	 * happens when called speculatively from start_xmit.
-	 */
-	if (!packets)
-		return;
-
-	u64_stats_update_begin(&sq->stats.syncp);
-	sq->stats.bytes += bytes;
-	sq->stats.packets += packets;
-	u64_stats_update_end(&sq->stats.syncp);
-}
-
-static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
-{
-	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
-		return false;
-	else if (q < vi->curr_queue_pairs)
-		return true;
-	else
-		return false;
-}
-
 static void virtnet_poll_cleantx(struct receive_queue *rq)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
@@ -1821,6 +1870,38 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	return received;
 }
 
+static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
+{
+	virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
+	napi_disable(&vi->rq[qp_index].napi);
+	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
+}
+
+static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
+{
+	struct net_device *dev = vi->dev;
+	int err;
+
+	err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index,
+			       vi->rq[qp_index].napi.napi_id);
+	if (err < 0)
+		return err;
+
+	err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq,
+					 MEM_TYPE_PAGE_SHARED, NULL);
+	if (err < 0)
+		goto err_xdp_reg_mem_model;
+
+	virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
+	virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
+
+	return 0;
+
+err_xdp_reg_mem_model:
+	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
+	return err;
+}
+
 static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -1834,22 +1915,20 @@ static int virtnet_open(struct net_device *dev)
 			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
 				schedule_delayed_work(&vi->refill, 0);
 
-		err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id);
+		err = virtnet_enable_queue_pair(vi, i);
 		if (err < 0)
-			return err;
-
-		err = xdp_rxq_info_reg_mem_model(&vi->rq[i].xdp_rxq,
-						 MEM_TYPE_PAGE_SHARED, NULL);
-		if (err < 0) {
-			xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
-			return err;
-		}
-
-		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-		virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi);
+			goto err_enable_qp;
 	}
 
 	return 0;
+
+err_enable_qp:
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
+
+	for (i--; i >= 0; i--)
+		virtnet_disable_queue_pair(vi, i);
+	return err;
 }
 
 static int virtnet_poll_tx(struct napi_struct *napi, int budget)
@@ -1989,30 +2068,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		nf_reset_ct(skb);
 	}
 
-	/* If running out of space, stop queue to avoid getting packets that we
-	 * are then unable to transmit.
-	 * An alternative would be to force queuing layer to requeue the skb by
-	 * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be
-	 * returned in a normal path of operation: it means that driver is not
-	 * maintaining the TX queue stop/start state properly, and causes
-	 * the stack to do a non-trivial amount of useless work.
-	 * Since most packets only take 1 or 2 ring slots, stopping the queue
-	 * early means 16 slots are typically wasted.
-	 */
-	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
-		netif_stop_subqueue(dev, qnum);
-		if (use_napi) {
-			if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
-				virtqueue_napi_schedule(&sq->napi, sq->vq);
-		} else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
-			/* More just got used, free them then recheck. */
-			free_old_xmit_skbs(sq, false);
-			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
-				netif_start_subqueue(dev, qnum);
-				virtqueue_disable_cb(sq->vq);
-			}
-		}
-	}
+	check_sq_full_and_disable(vi, dev, sq);
 
 	if (kick || netif_xmit_stopped(txq)) {
 		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
@@ -2281,11 +2337,8 @@ static int virtnet_close(struct net_device *dev)
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
 
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		virtnet_napi_tx_disable(&vi->sq[i].napi);
-		napi_disable(&vi->rq[i].napi);
-		xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
-	}
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		virtnet_disable_queue_pair(vi, i);
 
 	return 0;
 }
@@ -2883,12 +2936,10 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 				       struct ethtool_coalesce *ec)
 {
 	struct scatterlist sgs_tx, sgs_rx;
-	struct virtio_net_ctrl_coal_tx coal_tx;
-	struct virtio_net_ctrl_coal_rx coal_rx;
 
-	coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs);
-	coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames);
-	sg_init_one(&sgs_tx, &coal_tx, sizeof(coal_tx));
+	vi->ctrl->coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs);
+	vi->ctrl->coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames);
+	sg_init_one(&sgs_tx, &vi->ctrl->coal_tx, sizeof(vi->ctrl->coal_tx));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
 				  VIRTIO_NET_CTRL_NOTF_COAL_TX_SET,
@@ -2899,9 +2950,9 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 	vi->tx_usecs = ec->tx_coalesce_usecs;
 	vi->tx_max_packets = ec->tx_max_coalesced_frames;
 
-	coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs);
-	coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames);
-	sg_init_one(&sgs_rx, &coal_rx, sizeof(coal_rx));
+	vi->ctrl->coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs);
+	vi->ctrl->coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames);
+	sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
 				  VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
@@ -3536,12 +3587,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
 		struct virtqueue *vq = vi->sq[i].vq;
 		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
 			virtnet_sq_free_unused_buf(vq, buf);
+		cond_resched();
 	}
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->rq[i].vq;
 		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
 			virtnet_rq_free_unused_buf(vq, buf);
+		cond_resched();
 	}
 }
 
@@ -4213,7 +4266,8 @@ static struct virtio_device_id id_table[] = {
 	VIRTIO_NET_F_CTRL_MAC_ADDR, \
 	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
 	VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \
-	VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL
+	VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL, \
+	VIRTIO_NET_F_GUEST_HDRLEN
 
 static unsigned int features[] = {
 	VIRTNET_FEATURES,