1 files changed, 746 insertions, 110 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 55db6a336f7e..7106932c6f88 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -135,6 +135,9 @@ struct send_queue {
 	struct virtnet_sq_stats stats;
 
 	struct napi_struct napi;
+
+	/* Record whether sq is in reset state. */
+	bool reset;
 };
 
 /* Internal representation of a receive virtqueue */
@@ -169,6 +172,24 @@ struct receive_queue {
 	struct xdp_rxq_info xdp_rxq;
 };
 
+/* This structure can contain rss message with maximum settings for indirection table and keysize
+ * Note, that default structure that describes RSS configuration virtio_net_rss_config
+ * contains same info but can't handle table values.
+ * In any case, structure would be passed to virtio hw through sg_buf split by parts
+ * because table sizes may be differ according to the device configuration.
+ */
+#define VIRTIO_NET_RSS_MAX_KEY_SIZE     40
+#define VIRTIO_NET_RSS_MAX_TABLE_LEN    128
+struct virtio_net_ctrl_rss {
+	u32 hash_types;
+	u16 indirection_table_mask;
+	u16 unclassified_queue;
+	u16 indirection_table[VIRTIO_NET_RSS_MAX_TABLE_LEN];
+	u16 max_tx_vq;
+	u8 hash_key_length;
+	u8 key[VIRTIO_NET_RSS_MAX_KEY_SIZE];
+};
+
 /* Control VQ buffers: protected by the rtnl lock */
 struct control_buf {
 	struct virtio_net_ctrl_hdr hdr;
@@ -178,6 +199,7 @@ struct control_buf {
 	u8 allmulti;
 	__virtio16 vid;
 	__virtio64 offloads;
+	struct virtio_net_ctrl_rss rss;
 };
 
 struct virtnet_info {
@@ -203,9 +225,20 @@ struct virtnet_info {
 	/* I like... big packets and I cannot lie! */
 	bool big_packets;
 
+	/* number of sg entries allocated for big packets */
+	unsigned int big_packets_num_skbfrags;
+
 	/* Host will merge rx buffers for big packets (shake it! shake it!) */
 	bool mergeable_rx_bufs;
 
+	/* Host supports rss and/or hash report */
+	bool has_rss;
+	bool has_rss_hash_report;
+	u8 rss_key_size;
+	u16 rss_indir_table_size;
+	u32 rss_hash_types_supported;
+	u32 rss_hash_types_saved;
+
 	/* Has control virtqueue */
 	bool has_cvq;
 
@@ -215,9 +248,15 @@ struct virtnet_info {
 	/* Packet virtio header size */
 	u8 hdr_len;
 
-	/* Work struct for refilling if we run low on memory. */
+	/* Work struct for delayed refilling if we run low on memory. */
 	struct delayed_work refill;
 
+	/* Is delayed refill enabled? */
+	bool refill_enabled;
+
+	/* The lock to synchronize the access to refill_enabled */
+	spinlock_t refill_lock;
+
 	/* Work struct for config space updates */
 	struct work_struct config_work;
 
@@ -234,6 +273,12 @@ struct virtnet_info {
 	u8 duplex;
 	u32 speed;
 
+	/* Interrupt coalescing settings */
+	u32 tx_usecs;
+	u32 rx_usecs;
+	u32 tx_max_packets;
+	u32 rx_max_packets;
+
 	unsigned long guest_offloads;
 	unsigned long guest_offloads_capable;
 
@@ -242,15 +287,18 @@ struct virtnet_info {
 };
 
 struct padded_vnet_hdr {
-	struct virtio_net_hdr_mrg_rxbuf hdr;
+	struct virtio_net_hdr_v1_hash hdr;
 	/*
 	 * hdr is in a separate sg buffer, and data sg buffer shares same page
 	 * with this header sg. This padding makes next sg 16 byte aligned
 	 * after the header.
 	 */
-	char padding[4];
+	char padding[12];
 };
 
+static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf);
+static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
+
 static bool is_xdp_frame(void *ptr)
 {
 	return (unsigned long)ptr & VIRTIO_XDP_FLAG;
@@ -321,6 +369,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
 	return p;
 }
 
+static void enable_delayed_refill(struct virtnet_info *vi)
+{
+	spin_lock_bh(&vi->refill_lock);
+	vi->refill_enabled = true;
+	spin_unlock_bh(&vi->refill_lock);
+}
+
+static void disable_delayed_refill(struct virtnet_info *vi)
+{
+	spin_lock_bh(&vi->refill_lock);
+	vi->refill_enabled = false;
+	spin_unlock_bh(&vi->refill_lock);
+}
+
 static void virtqueue_napi_schedule(struct napi_struct *napi,
 				    struct virtqueue *vq)
 {
@@ -396,7 +458,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 
 	hdr_len = vi->hdr_len;
 	if (vi->mergeable_rx_bufs)
-		hdr_padded_len = sizeof(*hdr);
+		hdr_padded_len = hdr_len;
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
@@ -733,7 +795,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		pr_debug("%s: rx error: len %u exceeds max size %d\n",
 			 dev->name, len, GOOD_PACKET_LEN);
 		dev->stats.rx_length_errors++;
-		goto err_len;
+		goto err;
 	}
 
 	if (likely(!vi->xdp_enabled)) {
@@ -812,7 +874,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			rcu_read_unlock();
 			goto xdp_xmit;
 		default:
-			bpf_warn_invalid_xdp_action(act);
+			bpf_warn_invalid_xdp_action(vi->dev, xdp_prog, act);
 			fallthrough;
 		case XDP_ABORTED:
 			trace_xdp_exception(vi->dev, xdp_prog, act);
@@ -825,10 +887,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 
 skip_xdp:
 	skb = build_skb(buf, buflen);
-	if (!skb) {
-		put_page(page);
+	if (!skb)
 		goto err;
-	}
 	skb_reserve(skb, headroom - delta);
 	skb_put(skb, len);
 	if (!xdp_prog) {
@@ -839,13 +899,12 @@ skip_xdp:
 	if (metasize)
 		skb_metadata_set(skb, metasize);
 
-err:
 	return skb;
 
 err_xdp:
 	rcu_read_unlock();
 	stats->xdp_drops++;
-err_len:
+err:
 	stats->drops++;
 	put_page(page);
 xdp_xmit:
@@ -981,6 +1040,24 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			 * xdp.data_meta were adjusted
 			 */
 			len = xdp.data_end - xdp.data + vi->hdr_len + metasize;
+
+			/* recalculate headroom if xdp.data or xdp_data_meta
+			 * were adjusted, note that offset should always point
+			 * to the start of the reserved bytes for virtio_net
+			 * header which are followed by xdp.data, that means
+			 * that offset is equal to the headroom (when buf is
+			 * starting at the beginning of the page, otherwise
+			 * there is a base offset inside the page) but it's used
+			 * with a different starting point (buf start) than
+			 * xdp.data (buf start + vnet hdr size). If xdp.data or
+			 * data_meta were adjusted by the xdp prog then the
+			 * headroom size has changed and so has the offset, we
+			 * can use data_hard_start, which points at buf start +
+			 * vnet hdr size, to calculate the new headroom and use
+			 * it later to compute buf start in page_to_skb()
+			 */
+			headroom = xdp.data - xdp.data_hard_start - metasize;
+
 			/* We can only create skb based on xdp_page. */
 			if (unlikely(xdp_page != page)) {
 				rcu_read_unlock();
@@ -988,15 +1065,18 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 				head_skb = page_to_skb(vi, rq, xdp_page, offset,
 						       len, PAGE_SIZE, false,
 						       metasize,
-						       VIRTIO_XDP_HEADROOM);
+						       headroom);
 				return head_skb;
 			}
 			break;
 		case XDP_TX:
 			stats->xdp_tx++;
 			xdpf = xdp_convert_buff_to_frame(&xdp);
-			if (unlikely(!xdpf))
+			if (unlikely(!xdpf)) {
+				if (unlikely(xdp_page != page))
+					put_page(xdp_page);
 				goto err_xdp;
+			}
 			err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
 			if (unlikely(!err)) {
 				xdp_return_frame_rx_napi(xdpf);
@@ -1025,7 +1105,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			rcu_read_unlock();
 			goto xdp_xmit;
 		default:
-			bpf_warn_invalid_xdp_action(act);
+			bpf_warn_invalid_xdp_action(vi->dev, xdp_prog, act);
 			fallthrough;
 		case XDP_ABORTED:
 			trace_xdp_exception(vi->dev, xdp_prog, act);
@@ -1126,6 +1206,35 @@ xdp_xmit:
 	return NULL;
 }
 
+static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash,
+				struct sk_buff *skb)
+{
+	enum pkt_hash_types rss_hash_type;
+
+	if (!hdr_hash || !skb)
+		return;
+
+	switch (__le16_to_cpu(hdr_hash->hash_report)) {
+	case VIRTIO_NET_HASH_REPORT_TCPv4:
+	case VIRTIO_NET_HASH_REPORT_UDPv4:
+	case VIRTIO_NET_HASH_REPORT_TCPv6:
+	case VIRTIO_NET_HASH_REPORT_UDPv6:
+	case VIRTIO_NET_HASH_REPORT_TCPv6_EX:
+	case VIRTIO_NET_HASH_REPORT_UDPv6_EX:
+		rss_hash_type = PKT_HASH_TYPE_L4;
+		break;
+	case VIRTIO_NET_HASH_REPORT_IPv4:
+	case VIRTIO_NET_HASH_REPORT_IPv6:
+	case VIRTIO_NET_HASH_REPORT_IPv6_EX:
+		rss_hash_type = PKT_HASH_TYPE_L3;
+		break;
+	case VIRTIO_NET_HASH_REPORT_NONE:
+	default:
+		rss_hash_type = PKT_HASH_TYPE_NONE;
+	}
+	skb_set_hash(skb, __le32_to_cpu(hdr_hash->hash_value), rss_hash_type);
+}
+
 static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 			void *buf, unsigned int len, void **ctx,
 			unsigned int *xdp_xmit,
@@ -1160,6 +1269,8 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 		return;
 
 	hdr = skb_vnet_hdr(skb);
+	if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report)
+		virtio_skb_set_hash((const struct virtio_net_hdr_v1_hash *)hdr, skb);
 
 	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1223,10 +1334,10 @@ static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq,
 	char *p;
 	int i, err, offset;
 
-	sg_init_table(rq->sg, MAX_SKB_FRAGS + 2);
+	sg_init_table(rq->sg, vi->big_packets_num_skbfrags + 2);
 
-	/* page in rq->sg[MAX_SKB_FRAGS + 1] is list tail */
-	for (i = MAX_SKB_FRAGS + 1; i > 1; --i) {
+	/* page in rq->sg[vi->big_packets_num_skbfrags + 1] is list tail */
+	for (i = vi->big_packets_num_skbfrags + 1; i > 1; --i) {
 		first = get_a_page(rq, gfp);
 		if (!first) {
 			if (list)
@@ -1257,7 +1368,7 @@ static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq,
 
 	/* chain first in list head */
 	first->private = (unsigned long)list;
-	err = virtqueue_add_inbuf(rq->vq, rq->sg, MAX_SKB_FRAGS + 2,
+	err = virtqueue_add_inbuf(rq->vq, rq->sg, vi->big_packets_num_skbfrags + 2,
 				  first, gfp);
 	if (err < 0)
 		give_pages(rq, first);
@@ -1269,7 +1380,8 @@ static unsigned int get_mergeable_buf_len(struct receive_queue *rq,
 					  struct ewma_pkt_len *avg_pkt_len,
 					  unsigned int room)
 {
-	const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	const size_t hdr_len = vi->hdr_len;
 	unsigned int len;
 
 	if (room)
@@ -1453,8 +1565,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	}
 
 	if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
-		if (!try_fill_recv(vi, rq, GFP_ATOMIC))
-			schedule_delayed_work(&vi->refill, 0);
+		if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
+			spin_lock(&vi->refill_lock);
+			if (vi->refill_enabled)
+				schedule_delayed_work(&vi->refill, 0);
+			spin_unlock(&vi->refill_lock);
+		}
 	}
 
 	u64_stats_update_begin(&rq->stats.syncp);
@@ -1527,6 +1643,11 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 		return;
 
 	if (__netif_tx_trylock(txq)) {
+		if (sq->reset) {
+			__netif_tx_unlock(txq);
+			return;
+		}
+
 		do {
 			virtqueue_disable_cb(sq->vq);
 			free_old_xmit_skbs(sq, true);
@@ -1577,6 +1698,8 @@ static int virtnet_open(struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i, err;
 
+	enable_delayed_refill(vi);
+
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (i < vi->curr_queue_pairs)
 			/* Make sure we have some buffers: if oom use wq. */
@@ -1772,6 +1895,70 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
+static int virtnet_rx_resize(struct virtnet_info *vi,
+			     struct receive_queue *rq, u32 ring_num)
+{
+	bool running = netif_running(vi->dev);
+	int err, qindex;
+
+	qindex = rq - vi->rq;
+
+	if (running)
+		napi_disable(&rq->napi);
+
+	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
+	if (err)
+		netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err);
+
+	if (!try_fill_recv(vi, rq, GFP_KERNEL))
+		schedule_delayed_work(&vi->refill, 0);
+
+	if (running)
+		virtnet_napi_enable(rq->vq, &rq->napi);
+	return err;
+}
+
+static int virtnet_tx_resize(struct virtnet_info *vi,
+			     struct send_queue *sq, u32 ring_num)
+{
+	bool running = netif_running(vi->dev);
+	struct netdev_queue *txq;
+	int err, qindex;
+
+	qindex = sq - vi->sq;
+
+	if (running)
+		virtnet_napi_tx_disable(&sq->napi);
+
+	txq = netdev_get_tx_queue(vi->dev, qindex);
+
+	/* 1. wait all ximt complete
+	 * 2. fix the race of netif_stop_subqueue() vs netif_start_subqueue()
+	 */
+	__netif_tx_lock_bh(txq);
+
+	/* Prevent rx poll from accessing sq. */
+	sq->reset = true;
+
+	/* Prevent the upper layer from trying to send packets. */
+	netif_stop_subqueue(vi->dev, qindex);
+
+	__netif_tx_unlock_bh(txq);
+
+	err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf);
+	if (err)
+		netdev_err(vi->dev, "resize tx fail: tx queue index: %d err: %d\n", qindex, err);
+
+	__netif_tx_lock_bh(txq);
+	sq->reset = false;
+	netif_tx_wake_queue(txq);
+	__netif_tx_unlock_bh(txq);
+
+	if (running)
+		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
@@ -1959,6 +2146,8 @@ static int virtnet_close(struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i;
 
+	/* Make sure NAPI doesn't schedule refill work */
+	disable_delayed_refill(vi);
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
 
@@ -2104,7 +2293,7 @@ static void virtnet_set_affinity(struct virtnet_info *vi)
 	stragglers = num_cpu >= vi->curr_queue_pairs ?
 			num_cpu % vi->curr_queue_pairs :
 			0;
-	cpu = cpumask_next(-1, cpu_online_mask);
+	cpu = cpumask_first(cpu_online_mask);
 
 	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		group_size = stride + (i < stragglers ? 1 : 0);
@@ -2174,16 +2363,233 @@ static void virtnet_cpu_notif_remove(struct virtnet_info *vi)
 }
 
 static void virtnet_get_ringparam(struct net_device *dev,
-				struct ethtool_ringparam *ring)
+				  struct ethtool_ringparam *ring,
+				  struct kernel_ethtool_ringparam *kernel_ring,
+				  struct netlink_ext_ack *extack)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 
-	ring->rx_max_pending = virtqueue_get_vring_size(vi->rq[0].vq);
-	ring->tx_max_pending = virtqueue_get_vring_size(vi->sq[0].vq);
-	ring->rx_pending = ring->rx_max_pending;
-	ring->tx_pending = ring->tx_max_pending;
+	ring->rx_max_pending = vi->rq[0].vq->num_max;
+	ring->tx_max_pending = vi->sq[0].vq->num_max;
+	ring->rx_pending = virtqueue_get_vring_size(vi->rq[0].vq);
+	ring->tx_pending = virtqueue_get_vring_size(vi->sq[0].vq);
 }
 
+static int virtnet_set_ringparam(struct net_device *dev,
+				 struct ethtool_ringparam *ring,
+				 struct kernel_ethtool_ringparam *kernel_ring,
+				 struct netlink_ext_ack *extack)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	u32 rx_pending, tx_pending;
+	struct receive_queue *rq;
+	struct send_queue *sq;
+	int i, err;
+
+	if (ring->rx_mini_pending || ring->rx_jumbo_pending)
+		return -EINVAL;
+
+	rx_pending = virtqueue_get_vring_size(vi->rq[0].vq);
+	tx_pending = virtqueue_get_vring_size(vi->sq[0].vq);
+
+	if (ring->rx_pending == rx_pending &&
+	    ring->tx_pending == tx_pending)
+		return 0;
+
+	if (ring->rx_pending > vi->rq[0].vq->num_max)
+		return -EINVAL;
+
+	if (ring->tx_pending > vi->sq[0].vq->num_max)
+		return -EINVAL;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		rq = vi->rq + i;
+		sq = vi->sq + i;
+
+		if (ring->tx_pending != tx_pending) {
+			err = virtnet_tx_resize(vi, sq, ring->tx_pending);
+			if (err)
+				return err;
+		}
+
+		if (ring->rx_pending != rx_pending) {
+			err = virtnet_rx_resize(vi, rq, ring->rx_pending);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static bool virtnet_commit_rss_command(struct virtnet_info *vi)
+{
+	struct net_device *dev = vi->dev;
+	struct scatterlist sgs[4];
+	unsigned int sg_buf_size;
+
+	/* prepare sgs */
+	sg_init_table(sgs, 4);
+
+	sg_buf_size = offsetof(struct virtio_net_ctrl_rss, indirection_table);
+	sg_set_buf(&sgs[0], &vi->ctrl->rss, sg_buf_size);
+
+	sg_buf_size = sizeof(uint16_t) * (vi->ctrl->rss.indirection_table_mask + 1);
+	sg_set_buf(&sgs[1], vi->ctrl->rss.indirection_table, sg_buf_size);
+
+	sg_buf_size = offsetof(struct virtio_net_ctrl_rss, key)
+			- offsetof(struct virtio_net_ctrl_rss, max_tx_vq);
+	sg_set_buf(&sgs[2], &vi->ctrl->rss.max_tx_vq, sg_buf_size);
+
+	sg_buf_size = vi->rss_key_size;
+	sg_set_buf(&sgs[3], vi->ctrl->rss.key, sg_buf_size);
+
+	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
+				  vi->has_rss ? VIRTIO_NET_CTRL_MQ_RSS_CONFIG
+				  : VIRTIO_NET_CTRL_MQ_HASH_CONFIG, sgs)) {
+		dev_warn(&dev->dev, "VIRTIONET issue with committing RSS sgs\n");
+		return false;
+	}
+	return true;
+}
+
+static void virtnet_init_default_rss(struct virtnet_info *vi)
+{
+	u32 indir_val = 0;
+	int i = 0;
+
+	vi->ctrl->rss.hash_types = vi->rss_hash_types_supported;
+	vi->rss_hash_types_saved = vi->rss_hash_types_supported;
+	vi->ctrl->rss.indirection_table_mask = vi->rss_indir_table_size
+						? vi->rss_indir_table_size - 1 : 0;
+	vi->ctrl->rss.unclassified_queue = 0;
+
+	for (; i < vi->rss_indir_table_size; ++i) {
+		indir_val = ethtool_rxfh_indir_default(i, vi->curr_queue_pairs);
+		vi->ctrl->rss.indirection_table[i] = indir_val;
+	}
+
+	vi->ctrl->rss.max_tx_vq = vi->curr_queue_pairs;
+	vi->ctrl->rss.hash_key_length = vi->rss_key_size;
+
+	netdev_rss_key_fill(vi->ctrl->rss.key, vi->rss_key_size);
+}
+
+static void virtnet_get_hashflow(const struct virtnet_info *vi, struct ethtool_rxnfc *info)
+{
+	info->data = 0;
+	switch (info->flow_type) {
+	case TCP_V4_FLOW:
+		if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv4) {
+			info->data = RXH_IP_SRC | RXH_IP_DST |
+						 RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		} else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) {
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		}
+		break;
+	case TCP_V6_FLOW:
+		if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv6) {
+			info->data = RXH_IP_SRC | RXH_IP_DST |
+						 RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		} else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) {
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		}
+		break;
+	case UDP_V4_FLOW:
+		if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv4) {
+			info->data = RXH_IP_SRC | RXH_IP_DST |
+						 RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		} else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) {
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		}
+		break;
+	case UDP_V6_FLOW:
+		if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv6) {
+			info->data = RXH_IP_SRC | RXH_IP_DST |
+						 RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		} else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) {
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+		}
+		break;
+	case IPV4_FLOW:
+		if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4)
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+
+		break;
+	case IPV6_FLOW:
+		if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6)
+			info->data = RXH_IP_SRC | RXH_IP_DST;
+
+		break;
+	default:
+		info->data = 0;
+		break;
+	}
+}
+
+static bool virtnet_set_hashflow(struct virtnet_info *vi, struct ethtool_rxnfc *info)
+{
+	u32 new_hashtypes = vi->rss_hash_types_saved;
+	bool is_disable = info->data & RXH_DISCARD;
+	bool is_l4 = info->data == (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3);
+
+	/* supports only 'sd', 'sdfn' and 'r' */
+	if (!((info->data == (RXH_IP_SRC | RXH_IP_DST)) | is_l4 | is_disable))
+		return false;
+
+	switch (info->flow_type) {
+	case TCP_V4_FLOW:
+		new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_TCPv4);
+		if (!is_disable)
+			new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4
+				| (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv4 : 0);
+		break;
+	case UDP_V4_FLOW:
+		new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_UDPv4);
+		if (!is_disable)
+			new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4
+				| (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv4 : 0);
+		break;
+	case IPV4_FLOW:
+		new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv4;
+		if (!is_disable)
+			new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv4;
+		break;
+	case TCP_V6_FLOW:
+		new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_TCPv6);
+		if (!is_disable)
+			new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6
+				| (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv6 : 0);
+		break;
+	case UDP_V6_FLOW:
+		new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_UDPv6);
+		if (!is_disable)
+			new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6
+				| (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv6 : 0);
+		break;
+	case IPV6_FLOW:
+		new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv6;
+		if (!is_disable)
+			new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv6;
+		break;
+	default:
+		/* unsupported flow */
+		return false;
+	}
+
+	/* if unsupported hashtype was set */
+	if (new_hashtypes != (new_hashtypes & vi->rss_hash_types_supported))
+		return false;
+
+	if (new_hashtypes != vi->rss_hash_types_saved) {
+		vi->rss_hash_types_saved = new_hashtypes;
+		vi->ctrl->rss.hash_types = vi->rss_hash_types_saved;
+		if (vi->dev->features & NETIF_F_RXHASH)
+			return virtnet_commit_rss_command(vi);
+	}
+
+	return true;
+}
 
 static void virtnet_get_drvinfo(struct net_device *dev,
 				struct ethtool_drvinfo *info)
@@ -2191,9 +2597,9 @@ static void virtnet_get_drvinfo(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct virtio_device *vdev = vi->vdev;
 
-	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
-	strlcpy(info->version, VIRTNET_DRIVER_VERSION, sizeof(info->version));
-	strlcpy(info->bus_info, virtio_bus_name(vdev), sizeof(info->bus_info));
+	strscpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+	strscpy(info->version, VIRTNET_DRIVER_VERSION, sizeof(info->version));
+	strscpy(info->bus_info, virtio_bus_name(vdev), sizeof(info->bus_info));
 
 }
 
@@ -2343,27 +2749,89 @@ static int virtnet_get_link_ksettings(struct net_device *dev,
 	return 0;
 }
 
+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));
+
+	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
+				  VIRTIO_NET_CTRL_NOTF_COAL_TX_SET,
+				  &sgs_tx))
+		return -EINVAL;
+
+	/* Save parameters */
+	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));
+
+	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
+				  VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
+				  &sgs_rx))
+		return -EINVAL;
+
+	/* Save parameters */
+	vi->rx_usecs = ec->rx_coalesce_usecs;
+	vi->rx_max_packets = ec->rx_max_coalesced_frames;
+
+	return 0;
+}
+
+static int virtnet_coal_params_supported(struct ethtool_coalesce *ec)
+{
+	/* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL
+	 * feature is negotiated.
+	 */
+	if (ec->rx_coalesce_usecs || ec->tx_coalesce_usecs)
+		return -EOPNOTSUPP;
+
+	if (ec->tx_max_coalesced_frames > 1 ||
+	    ec->rx_max_coalesced_frames != 1)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int virtnet_set_coalesce(struct net_device *dev,
 				struct ethtool_coalesce *ec,
 				struct kernel_ethtool_coalesce *kernel_coal,
 				struct netlink_ext_ack *extack)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
-	int i, napi_weight;
-
-	if (ec->tx_max_coalesced_frames > 1 ||
-	    ec->rx_max_coalesced_frames != 1)
-		return -EINVAL;
+	int ret, i, napi_weight;
+	bool update_napi = false;
 
+	/* Can't change NAPI weight if the link is up */
 	napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0;
 	if (napi_weight ^ vi->sq[0].napi.weight) {
 		if (dev->flags & IFF_UP)
 			return -EBUSY;
+		else
+			update_napi = true;
+	}
+
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL))
+		ret = virtnet_send_notf_coal_cmds(vi, ec);
+	else
+		ret = virtnet_coal_params_supported(ec);
+
+	if (ret)
+		return ret;
+
+	if (update_napi) {
 		for (i = 0; i < vi->max_queue_pairs; i++)
 			vi->sq[i].napi.weight = napi_weight;
 	}
 
-	return 0;
+	return ret;
 }
 
 static int virtnet_get_coalesce(struct net_device *dev,
@@ -2371,16 +2839,19 @@ static int virtnet_get_coalesce(struct net_device *dev,
 				struct kernel_ethtool_coalesce *kernel_coal,
 				struct netlink_ext_ack *extack)
 {
-	struct ethtool_coalesce ec_default = {
-		.cmd = ETHTOOL_GCOALESCE,
-		.rx_max_coalesced_frames = 1,
-	};
 	struct virtnet_info *vi = netdev_priv(dev);
 
-	memcpy(ec, &ec_default, sizeof(ec_default));
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) {
+		ec->rx_coalesce_usecs = vi->rx_usecs;
+		ec->tx_coalesce_usecs = vi->tx_usecs;
+		ec->tx_max_coalesced_frames = vi->tx_max_packets;
+		ec->rx_max_coalesced_frames = vi->rx_max_packets;
+	} else {
+		ec->rx_max_coalesced_frames = 1;
 
-	if (vi->sq[0].napi.weight)
-		ec->tx_max_coalesced_frames = 1;
+		if (vi->sq[0].napi.weight)
+			ec->tx_max_coalesced_frames = 1;
+	}
 
 	return 0;
 }
@@ -2412,11 +2883,99 @@ static void virtnet_update_settings(struct virtnet_info *vi)
 		vi->duplex = duplex;
 }
 
+static u32 virtnet_get_rxfh_key_size(struct net_device *dev)
+{
+	return ((struct virtnet_info *)netdev_priv(dev))->rss_key_size;
+}
+
+static u32 virtnet_get_rxfh_indir_size(struct net_device *dev)
+{
+	return ((struct virtnet_info *)netdev_priv(dev))->rss_indir_table_size;
+}
+
+static int virtnet_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	int i;
+
+	if (indir) {
+		for (i = 0; i < vi->rss_indir_table_size; ++i)
+			indir[i] = vi->ctrl->rss.indirection_table[i];
+	}
+
+	if (key)
+		memcpy(key, vi->ctrl->rss.key, vi->rss_key_size);
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+
+	return 0;
+}
+
+static int virtnet_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	int i;
+
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (indir) {
+		for (i = 0; i < vi->rss_indir_table_size; ++i)
+			vi->ctrl->rss.indirection_table[i] = indir[i];
+	}
+	if (key)
+		memcpy(vi->ctrl->rss.key, key, vi->rss_key_size);
+
+	virtnet_commit_rss_command(vi);
+
+	return 0;
+}
+
+static int virtnet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	int rc = 0;
+
+	switch (info->cmd) {
+	case ETHTOOL_GRXRINGS:
+		info->data = vi->curr_queue_pairs;
+		break;
+	case ETHTOOL_GRXFH:
+		virtnet_get_hashflow(vi, info);
+		break;
+	default:
+		rc = -EOPNOTSUPP;
+	}
+
+	return rc;
+}
+
+static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	int rc = 0;
+
+	switch (info->cmd) {
+	case ETHTOOL_SRXFH:
+		if (!virtnet_set_hashflow(vi, info))
+			rc = -EINVAL;
+
+		break;
+	default:
+		rc = -EOPNOTSUPP;
+	}
+
+	return rc;
+}
+
 static const struct ethtool_ops virtnet_ethtool_ops = {
-	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES,
+	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES |
+		ETHTOOL_COALESCE_USECS,
 	.get_drvinfo = virtnet_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = virtnet_get_ringparam,
+	.set_ringparam = virtnet_set_ringparam,
 	.get_strings = virtnet_get_strings,
 	.get_sset_count = virtnet_get_sset_count,
 	.get_ethtool_stats = virtnet_get_ethtool_stats,
@@ -2427,12 +2986,17 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
 	.set_link_ksettings = virtnet_set_link_ksettings,
 	.set_coalesce = virtnet_set_coalesce,
 	.get_coalesce = virtnet_get_coalesce,
+	.get_rxfh_key_size = virtnet_get_rxfh_key_size,
+	.get_rxfh_indir_size = virtnet_get_rxfh_indir_size,
+	.get_rxfh = virtnet_get_rxfh,
+	.set_rxfh = virtnet_set_rxfh,
+	.get_rxnfc = virtnet_get_rxnfc,
+	.set_rxnfc = virtnet_set_rxnfc,
 };
 
 static void virtnet_freeze_down(struct virtio_device *vdev)
 {
 	struct virtnet_info *vi = vdev->priv;
-	int i;
 
 	/* Make sure no work handler is accessing the device */
 	flush_work(&vi->config_work);
@@ -2440,14 +3004,8 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	netif_tx_lock_bh(vi->dev);
 	netif_device_detach(vi->dev);
 	netif_tx_unlock_bh(vi->dev);
-	cancel_delayed_work_sync(&vi->refill);
-
-	if (netif_running(vi->dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			napi_disable(&vi->rq[i].napi);
-			virtnet_napi_tx_disable(&vi->sq[i].napi);
-		}
-	}
+	if (netif_running(vi->dev))
+		virtnet_close(vi->dev);
 }
 
 static int init_vqs(struct virtnet_info *vi);
@@ -2455,7 +3013,7 @@ static int init_vqs(struct virtnet_info *vi);
 static int virtnet_restore_up(struct virtio_device *vdev)
 {
 	struct virtnet_info *vi = vdev->priv;
-	int err, i;
+	int err;
 
 	err = init_vqs(vi);
 	if (err)
@@ -2463,16 +3021,12 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	if (netif_running(vi->dev)) {
-		for (i = 0; i < vi->curr_queue_pairs; i++)
-			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
-				schedule_delayed_work(&vi->refill, 0);
+	enable_delayed_refill(vi);
 
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
-					       &vi->sq[i].napi);
-		}
+	if (netif_running(vi->dev)) {
+		err = virtnet_open(vi->dev);
+		if (err)
+			return err;
 	}
 
 	netif_tx_lock_bh(vi->dev);
@@ -2679,6 +3233,16 @@ static int virtnet_set_features(struct net_device *dev,
 		vi->guest_offloads = offloads;
 	}
 
+	if ((dev->features ^ features) & NETIF_F_RXHASH) {
+		if (features & NETIF_F_RXHASH)
+			vi->ctrl->rss.hash_types = vi->rss_hash_types_saved;
+		else
+			vi->ctrl->rss.hash_types = VIRTIO_NET_HASH_REPORT_NONE;
+
+		if (!virtnet_commit_rss_command(vi))
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -2694,7 +3258,7 @@ static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue)
 
 	netdev_err(dev, "TX timeout on queue: %u, sq: %s, vq: 0x%x, name: %s, %u usecs ago\n",
 		   txqueue, sq->name, sq->vq->index, sq->vq->name,
-		   jiffies_to_usecs(jiffies - txq->trans_start));
+		   jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start)));
 }
 
 static const struct net_device_ops virtnet_netdev = {
@@ -2805,6 +3369,27 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 			put_page(vi->rq[i].alloc_frag.page);
 }
 
+static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
+{
+	if (!is_xdp_frame(buf))
+		dev_kfree_skb(buf);
+	else
+		xdp_return_frame(ptr_to_xdp(buf));
+}
+
+static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf)
+{
+	struct virtnet_info *vi = vq->vdev->priv;
+	int i = vq2rxq(vq);
+
+	if (vi->mergeable_rx_bufs)
+		put_page(virt_to_head_page(buf));
+	else if (vi->big_packets)
+		give_pages(&vi->rq[i], buf);
+	else
+		put_page(virt_to_head_page(buf));
+}
+
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
@@ -2812,26 +3397,14 @@ static void free_unused_bufs(struct virtnet_info *vi)
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->sq[i].vq;
-		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (!is_xdp_frame(buf))
-				dev_kfree_skb(buf);
-			else
-				xdp_return_frame(ptr_to_xdp(buf));
-		}
+		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
+			virtnet_sq_free_unused_buf(vq, buf);
 	}
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->rq[i].vq;
-
-		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (vi->mergeable_rx_bufs) {
-				put_page(virt_to_head_page(buf));
-			} else if (vi->big_packets) {
-				give_pages(&vi->rq[i], buf);
-			} else {
-				put_page(virt_to_head_page(buf));
-			}
-		}
+		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
+			virtnet_rq_free_unused_buf(vq, buf);
 	}
 }
 
@@ -2852,7 +3425,7 @@ static void virtnet_del_vqs(struct virtnet_info *vi)
  */
 static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqueue *vq)
 {
-	const unsigned int hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+	const unsigned int hdr_len = vi->hdr_len;
 	unsigned int rq_size = virtqueue_get_vring_size(vq);
 	unsigned int packet_len = vi->big_packets ? IP_MAX_MTU : vi->dev->max_mtu;
 	unsigned int buf_len = hdr_len + ETH_HLEN + VLAN_HLEN + packet_len;
@@ -2967,10 +3540,11 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 	INIT_DELAYED_WORK(&vi->refill, refill_work);
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		vi->rq[i].pages = NULL;
-		netif_napi_add(vi->dev, &vi->rq[i].napi, virtnet_poll,
-			       napi_weight);
-		netif_tx_napi_add(vi->dev, &vi->sq[i].napi, virtnet_poll_tx,
-				  napi_tx ? napi_weight : 0);
+		netif_napi_add_weight(vi->dev, &vi->rq[i].napi, virtnet_poll,
+				      napi_weight);
+		netif_napi_add_tx_weight(vi->dev, &vi->sq[i].napi,
+					 virtnet_poll_tx,
+					 napi_tx ? napi_weight : 0);
 
 		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
 		ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len);
@@ -3073,6 +3647,12 @@ static bool virtnet_validate_features(struct virtio_device *vdev)
 			     "VIRTIO_NET_F_CTRL_VQ") ||
 	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_MQ, "VIRTIO_NET_F_CTRL_VQ") ||
 	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR,
+			     "VIRTIO_NET_F_CTRL_VQ") ||
+	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_RSS,
+			     "VIRTIO_NET_F_CTRL_VQ") ||
+	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_HASH_REPORT,
+			     "VIRTIO_NET_F_CTRL_VQ") ||
+	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_NOTF_COAL,
 			     "VIRTIO_NET_F_CTRL_VQ"))) {
 		return false;
 	}
@@ -3105,21 +3685,44 @@ static int virtnet_validate(struct virtio_device *vdev)
 	return 0;
 }
 
+static bool virtnet_check_guest_gso(const struct virtnet_info *vi)
+{
+	return virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) ||
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO);
+}
+
+static void virtnet_set_big_packets(struct virtnet_info *vi, const int mtu)
+{
+	bool guest_gso = virtnet_check_guest_gso(vi);
+
+	/* If device can receive ANY guest GSO packets, regardless of mtu,
+	 * allocate packets of maximum size, otherwise limit it to only
+	 * mtu size worth only.
+	 */
+	if (mtu > ETH_DATA_LEN || guest_gso) {
+		vi->big_packets = true;
+		vi->big_packets_num_skbfrags = guest_gso ? MAX_SKB_FRAGS : DIV_ROUND_UP(mtu, PAGE_SIZE);
+	}
+}
+
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int i, err = -ENOMEM;
 	struct net_device *dev;
 	struct virtnet_info *vi;
 	u16 max_queue_pairs;
-	int mtu;
+	int mtu = 0;
 
-	/* Find if host supports multiqueue virtio_net device */
-	err = virtio_cread_feature(vdev, VIRTIO_NET_F_MQ,
-				   struct virtio_net_config,
-				   max_virtqueue_pairs, &max_queue_pairs);
+	/* Find if host supports multiqueue/rss virtio_net device */
+	max_queue_pairs = 1;
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_MQ) || virtio_has_feature(vdev, VIRTIO_NET_F_RSS))
+		max_queue_pairs =
+		     virtio_cread16(vdev, offsetof(struct virtio_net_config, max_virtqueue_pairs));
 
 	/* We need at least 2 queue's */
-	if (err || max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
+	if (max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN ||
 	    max_queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX ||
 	    !virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
 		max_queue_pairs = 1;
@@ -3196,19 +3799,45 @@ static int virtnet_probe(struct virtio_device *vdev)
 	vdev->priv = vi;
 
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
-
-	/* 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) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
-		vi->big_packets = true;
+	spin_lock_init(&vi->refill_lock);
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
 		vi->mergeable_rx_bufs = true;
 
-	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) ||
-	    virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) {
+		vi->rx_usecs = 0;
+		vi->tx_usecs = 0;
+		vi->tx_max_packets = 0;
+		vi->rx_max_packets = 0;
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT))
+		vi->has_rss_hash_report = true;
+
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS))
+		vi->has_rss = true;
+
+	if (vi->has_rss || vi->has_rss_hash_report) {
+		vi->rss_indir_table_size =
+			virtio_cread16(vdev, offsetof(struct virtio_net_config,
+				rss_max_indirection_table_length));
+		vi->rss_key_size =
+			virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size));
+
+		vi->rss_hash_types_supported =
+		    virtio_cread32(vdev, offsetof(struct virtio_net_config, supported_hash_types));
+		vi->rss_hash_types_supported &=
+				~(VIRTIO_NET_RSS_HASH_TYPE_IP_EX |
+				  VIRTIO_NET_RSS_HASH_TYPE_TCP_EX |
+				  VIRTIO_NET_RSS_HASH_TYPE_UDP_EX);
+
+		dev->hw_features |= NETIF_F_RXHASH;
+	}
+
+	if (vi->has_rss_hash_report)
+		vi->hdr_len = sizeof(struct virtio_net_hdr_v1_hash);
+	else if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) ||
+		 virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
 		vi->hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
 	else
 		vi->hdr_len = sizeof(struct virtio_net_hdr);
@@ -3237,12 +3866,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 		dev->mtu = mtu;
 		dev->max_mtu = mtu;
-
-		/* TODO: size buffers correctly in this case. */
-		if (dev->mtu > ETH_DATA_LEN)
-			vi->big_packets = true;
 	}
 
+	virtnet_set_big_packets(vi, mtu);
+
 	if (vi->any_header_sg)
 		dev->needed_headroom = vi->hdr_len;
 
@@ -3275,14 +3902,23 @@ static int virtnet_probe(struct virtio_device *vdev)
 		}
 	}
 
-	err = register_netdev(dev);
+	if (vi->has_rss || vi->has_rss_hash_report)
+		virtnet_init_default_rss(vi);
+
+	/* serialize netdev register + virtio_device_ready() with ndo_open() */
+	rtnl_lock();
+
+	err = register_netdevice(dev);
 	if (err) {
 		pr_debug("virtio_net: registering device failed\n");
+		rtnl_unlock();
 		goto free_failover;
 	}
 
 	virtio_device_ready(vdev);
 
+	rtnl_unlock();
+
 	err = virtnet_cpu_notif_add(vi);
 	if (err) {
 		pr_debug("virtio_net: registering cpu notifier failed\n");
@@ -3313,7 +3949,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	return 0;
 
 free_unregister_netdev:
-	vi->vdev->config->reset(vdev);
+	virtio_reset_device(vdev);
 
 	unregister_netdev(dev);
 free_failover:
@@ -3329,7 +3965,7 @@ free:
 
 static void remove_vq_common(struct virtnet_info *vi)
 {
-	vi->vdev->config->reset(vi->vdev);
+	virtio_reset_device(vi->vdev);
 
 	/* Free unused buffers in both send and recv, if any. */
 	free_unused_bufs(vi);
@@ -3406,7 +4042,8 @@ static struct virtio_device_id id_table[] = {
 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
 	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_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \
+	VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL
 
 static unsigned int features[] = {
 	VIRTNET_FEATURES,
@@ -3450,8 +4087,7 @@ static __init int virtio_net_driver_init(void)
 				      NULL, virtnet_cpu_dead);
 	if (ret)
 		goto err_dead;
-
-        ret = register_virtio_driver(&virtio_net_driver);
+	ret = register_virtio_driver(&virtio_net_driver);
 	if (ret)
 		goto err_virtio;
 	return 0;