--- zzzz-none-000/linux-3.10.107/drivers/net/hyperv/netvsc_drv.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/drivers/net/hyperv/netvsc_drv.c	2021-02-04 17:41:59.000000000 +0000
@@ -11,8 +11,7 @@
  * more details.
  *
  * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
+ * this program; if not, see <http://www.gnu.org/licenses/>.
  *
  * Authors:
  *   Haiyang Zhang <haiyangz@microsoft.com>
@@ -41,13 +40,6 @@
 
 #include "hyperv_net.h"
 
-struct net_device_context {
-	/* point back to our device context */
-	struct hv_device *device_ctx;
-	struct delayed_work dwork;
-	struct work_struct work;
-};
-
 /* Restrict GSO size to account for NVGRE */
 #define NETVSC_GSO_MAX_SIZE	62768
 
@@ -56,6 +48,17 @@
 module_param(ring_size, int, S_IRUGO);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
 
+static int max_num_vrss_chns = 8;
+
+static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
+				NETIF_MSG_LINK | NETIF_MSG_IFUP |
+				NETIF_MSG_IFDOWN | NETIF_MSG_RX_ERR |
+				NETIF_MSG_TX_ERR;
+
+static int debug = -1;
+module_param(debug, int, S_IRUGO);
+MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+
 static void do_set_multicast(struct work_struct *w)
 {
 	struct net_device_context *ndevctx =
@@ -92,8 +95,12 @@
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
 	struct hv_device *device_obj = net_device_ctx->device_ctx;
+	struct netvsc_device *nvdev;
+	struct rndis_device *rdev;
 	int ret = 0;
 
+	netif_carrier_off(net);
+
 	/* Open up the device */
 	ret = rndis_filter_open(device_obj);
 	if (ret != 0) {
@@ -101,7 +108,12 @@
 		return ret;
 	}
 
-	netif_start_queue(net);
+	netif_tx_wake_all_queues(net);
+
+	nvdev = hv_get_drvdata(device_obj);
+	rdev = nvdev->extension;
+	if (!rdev->link_state)
+		netif_carrier_on(net);
 
 	return ret;
 }
@@ -110,112 +122,453 @@
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
 	struct hv_device *device_obj = net_device_ctx->device_ctx;
+	struct netvsc_device *nvdev = hv_get_drvdata(device_obj);
 	int ret;
+	u32 aread, awrite, i, msec = 10, retry = 0, retry_max = 20;
+	struct vmbus_channel *chn;
 
 	netif_tx_disable(net);
 
 	/* Make sure netvsc_set_multicast_list doesn't re-enable filter! */
 	cancel_work_sync(&net_device_ctx->work);
 	ret = rndis_filter_close(device_obj);
-	if (ret != 0)
+	if (ret != 0) {
 		netdev_err(net, "unable to close device (ret %d).\n", ret);
+		return ret;
+	}
+
+	/* Ensure pending bytes in ring are read */
+	while (true) {
+		aread = 0;
+		for (i = 0; i < nvdev->num_chn; i++) {
+			chn = nvdev->chn_table[i];
+			if (!chn)
+				continue;
+
+			hv_get_ringbuffer_availbytes(&chn->inbound, &aread,
+						     &awrite);
+
+			if (aread)
+				break;
+
+			hv_get_ringbuffer_availbytes(&chn->outbound, &aread,
+						     &awrite);
+
+			if (aread)
+				break;
+		}
+
+		retry++;
+		if (retry > retry_max || aread == 0)
+			break;
+
+		msleep(msec);
+
+		if (msec < 1000)
+			msec *= 2;
+	}
+
+	if (aread) {
+		netdev_err(net, "Ring buffer not empty after closing rndis\n");
+		ret = -ETIMEDOUT;
+	}
 
 	return ret;
 }
 
-static void netvsc_xmit_completion(void *context)
+static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
+				int pkt_type)
+{
+	struct rndis_packet *rndis_pkt;
+	struct rndis_per_packet_info *ppi;
+
+	rndis_pkt = &msg->msg.pkt;
+	rndis_pkt->data_offset += ppi_size;
+
+	ppi = (struct rndis_per_packet_info *)((void *)rndis_pkt +
+		rndis_pkt->per_pkt_info_offset + rndis_pkt->per_pkt_info_len);
+
+	ppi->size = ppi_size;
+	ppi->type = pkt_type;
+	ppi->ppi_offset = sizeof(struct rndis_per_packet_info);
+
+	rndis_pkt->per_pkt_info_len += ppi_size;
+
+	return ppi;
+}
+
+static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
+			void *accel_priv, select_queue_fallback_t fallback)
+{
+	struct net_device_context *net_device_ctx = netdev_priv(ndev);
+	struct hv_device *hdev =  net_device_ctx->device_ctx;
+	struct netvsc_device *nvsc_dev = hv_get_drvdata(hdev);
+	u32 hash;
+	u16 q_idx = 0;
+
+	if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1)
+		return 0;
+
+	hash = skb_get_hash(skb);
+	q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
+		ndev->real_num_tx_queues;
+
+	return q_idx;
+}
+
+void netvsc_xmit_completion(void *context)
 {
 	struct hv_netvsc_packet *packet = (struct hv_netvsc_packet *)context;
 	struct sk_buff *skb = (struct sk_buff *)
-		(unsigned long)packet->completion.send.send_completion_tid;
-
-	kfree(packet);
+		(unsigned long)packet->send_completion_tid;
 
 	if (skb)
 		dev_kfree_skb_any(skb);
 }
 
+static u32 fill_pg_buf(struct page *page, u32 offset, u32 len,
+			struct hv_page_buffer *pb)
+{
+	int j = 0;
+
+	/* Deal with compund pages by ignoring unused part
+	 * of the page.
+	 */
+	page += (offset >> PAGE_SHIFT);
+	offset &= ~PAGE_MASK;
+
+	while (len > 0) {
+		unsigned long bytes;
+
+		bytes = PAGE_SIZE - offset;
+		if (bytes > len)
+			bytes = len;
+		pb[j].pfn = page_to_pfn(page);
+		pb[j].offset = offset;
+		pb[j].len = bytes;
+
+		offset += bytes;
+		len -= bytes;
+
+		if (offset == PAGE_SIZE && len) {
+			page++;
+			offset = 0;
+			j++;
+		}
+	}
+
+	return j + 1;
+}
+
+static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
+			   struct hv_netvsc_packet *packet)
+{
+	struct hv_page_buffer *pb = packet->page_buf;
+	u32 slots_used = 0;
+	char *data = skb->data;
+	int frags = skb_shinfo(skb)->nr_frags;
+	int i;
+
+	/* The packet is laid out thus:
+	 * 1. hdr: RNDIS header and PPI
+	 * 2. skb linear data
+	 * 3. skb fragment data
+	 */
+	if (hdr != NULL)
+		slots_used += fill_pg_buf(virt_to_page(hdr),
+					offset_in_page(hdr),
+					len, &pb[slots_used]);
+
+	packet->rmsg_size = len;
+	packet->rmsg_pgcnt = slots_used;
+
+	slots_used += fill_pg_buf(virt_to_page(data),
+				offset_in_page(data),
+				skb_headlen(skb), &pb[slots_used]);
+
+	for (i = 0; i < frags; i++) {
+		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+
+		slots_used += fill_pg_buf(skb_frag_page(frag),
+					frag->page_offset,
+					skb_frag_size(frag), &pb[slots_used]);
+	}
+	return slots_used;
+}
+
+static int count_skb_frag_slots(struct sk_buff *skb)
+{
+	int i, frags = skb_shinfo(skb)->nr_frags;
+	int pages = 0;
+
+	for (i = 0; i < frags; i++) {
+		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+		unsigned long size = skb_frag_size(frag);
+		unsigned long offset = frag->page_offset;
+
+		/* Skip unused frames from start of page */
+		offset &= ~PAGE_MASK;
+		pages += PFN_UP(offset + size);
+	}
+	return pages;
+}
+
+static int netvsc_get_slots(struct sk_buff *skb)
+{
+	char *data = skb->data;
+	unsigned int offset = offset_in_page(data);
+	unsigned int len = skb_headlen(skb);
+	int slots;
+	int frag_slots;
+
+	slots = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+	frag_slots = count_skb_frag_slots(skb);
+	return slots + frag_slots;
+}
+
+static u32 get_net_transport_info(struct sk_buff *skb, u32 *trans_off)
+{
+	u32 ret_val = TRANSPORT_INFO_NOT_IP;
+
+	if ((eth_hdr(skb)->h_proto != htons(ETH_P_IP)) &&
+		(eth_hdr(skb)->h_proto != htons(ETH_P_IPV6))) {
+		goto not_ip;
+	}
+
+	*trans_off = skb_transport_offset(skb);
+
+	if ((eth_hdr(skb)->h_proto == htons(ETH_P_IP))) {
+		struct iphdr *iphdr = ip_hdr(skb);
+
+		if (iphdr->protocol == IPPROTO_TCP)
+			ret_val = TRANSPORT_INFO_IPV4_TCP;
+		else if (iphdr->protocol == IPPROTO_UDP)
+			ret_val = TRANSPORT_INFO_IPV4_UDP;
+	} else {
+		if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
+			ret_val = TRANSPORT_INFO_IPV6_TCP;
+		else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
+			ret_val = TRANSPORT_INFO_IPV6_UDP;
+	}
+
+not_ip:
+	return ret_val;
+}
+
 static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct hv_netvsc_packet *packet;
+	struct hv_netvsc_packet *packet = NULL;
 	int ret;
-	unsigned int i, num_pages, npg_data;
-	u32 skb_length = skb->len;
+	unsigned int num_data_pgs;
+	struct rndis_message *rndis_msg;
+	struct rndis_packet *rndis_pkt;
+	u32 rndis_msg_size;
+	bool isvlan;
+	bool linear = false;
+	struct rndis_per_packet_info *ppi;
+	struct ndis_tcp_ip_checksum_info *csum_info;
+	struct ndis_tcp_lso_info *lso_info;
+	int  hdr_offset;
+	u32 net_trans_info;
+	u32 hash;
+	u32 skb_length;
+	u32 pkt_sz;
+	struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT];
+	struct netvsc_stats *tx_stats = this_cpu_ptr(net_device_ctx->tx_stats);
+
+	/* We will atmost need two pages to describe the rndis
+	 * header. We can only transmit MAX_PAGE_BUFFER_COUNT number
+	 * of pages in a single packet. If skb is scattered around
+	 * more pages we try linearizing it.
+	 */
 
-	/* Add multipages for skb->data and additional 2 for RNDIS */
-	npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1)
-		>> PAGE_SHIFT) - ((unsigned long)skb->data >> PAGE_SHIFT) + 1;
-	num_pages = skb_shinfo(skb)->nr_frags + npg_data + 2;
-
-	/* Allocate a netvsc packet based on # of frags. */
-	packet = kzalloc(sizeof(struct hv_netvsc_packet) +
-			 (num_pages * sizeof(struct hv_page_buffer)) +
-			 sizeof(struct rndis_filter_packet) +
-			 NDIS_VLAN_PPI_SIZE, GFP_ATOMIC);
-	if (!packet) {
-		/* out of memory, drop packet */
-		netdev_err(net, "unable to allocate hv_netvsc_packet\n");
-
-		dev_kfree_skb(skb);
-		net->stats.tx_dropped++;
-		return NETDEV_TX_OK;
+check_size:
+	skb_length = skb->len;
+	num_data_pgs = netvsc_get_slots(skb) + 2;
+	if (num_data_pgs > MAX_PAGE_BUFFER_COUNT && linear) {
+		net_alert_ratelimited("packet too big: %u pages (%u bytes)\n",
+				      num_data_pgs, skb->len);
+		ret = -EFAULT;
+		goto drop;
+	} else if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) {
+		if (skb_linearize(skb)) {
+			net_alert_ratelimited("failed to linearize skb\n");
+			ret = -ENOMEM;
+			goto drop;
+		}
+		linear = true;
+		goto check_size;
 	}
 
-	packet->vlan_tci = skb->vlan_tci;
+	pkt_sz = sizeof(struct hv_netvsc_packet) + RNDIS_AND_PPI_SIZE;
 
-	packet->extension = (void *)(unsigned long)packet +
-				sizeof(struct hv_netvsc_packet) +
-				    (num_pages * sizeof(struct hv_page_buffer));
+	ret = skb_cow_head(skb, pkt_sz);
+	if (ret) {
+		netdev_err(net, "unable to alloc hv_netvsc_packet\n");
+		ret = -ENOMEM;
+		goto drop;
+	}
+	/* Use the headroom for building up the packet */
+	packet = (struct hv_netvsc_packet *)skb->head;
+
+	packet->status = 0;
+	packet->xmit_more = skb->xmit_more;
+
+	packet->vlan_tci = skb->vlan_tci;
+	packet->page_buf = page_buf;
 
-	/* If the rndis msg goes beyond 1 page, we will add 1 later */
-	packet->page_buf_cnt = num_pages - 1;
+	packet->q_idx = skb_get_queue_mapping(skb);
 
-	/* Initialize it from the skb */
+	packet->is_data_pkt = true;
 	packet->total_data_buflen = skb->len;
 
-	/* Start filling in the page buffers starting after RNDIS buffer. */
-	packet->page_buf[1].pfn = virt_to_phys(skb->data) >> PAGE_SHIFT;
-	packet->page_buf[1].offset
-		= (unsigned long)skb->data & (PAGE_SIZE - 1);
-	if (npg_data == 1)
-		packet->page_buf[1].len = skb_headlen(skb);
+	packet->rndis_msg = (struct rndis_message *)((unsigned long)packet +
+				sizeof(struct hv_netvsc_packet));
+
+	memset(packet->rndis_msg, 0, RNDIS_AND_PPI_SIZE);
+
+	/* Set the completion routine */
+	packet->send_completion = netvsc_xmit_completion;
+	packet->send_completion_ctx = packet;
+	packet->send_completion_tid = (unsigned long)skb;
+
+	isvlan = packet->vlan_tci & VLAN_TAG_PRESENT;
+
+	/* Add the rndis header */
+	rndis_msg = packet->rndis_msg;
+	rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
+	rndis_msg->msg_len = packet->total_data_buflen;
+	rndis_pkt = &rndis_msg->msg.pkt;
+	rndis_pkt->data_offset = sizeof(struct rndis_packet);
+	rndis_pkt->data_len = packet->total_data_buflen;
+	rndis_pkt->per_pkt_info_offset = sizeof(struct rndis_packet);
+
+	rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet);
+
+	hash = skb_get_hash_raw(skb);
+	if (hash != 0 && net->real_num_tx_queues > 1) {
+		rndis_msg_size += NDIS_HASH_PPI_SIZE;
+		ppi = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
+				    NBL_HASH_VALUE);
+		*(u32 *)((void *)ppi + ppi->ppi_offset) = hash;
+	}
+
+	if (isvlan) {
+		struct ndis_pkt_8021q_info *vlan;
+
+		rndis_msg_size += NDIS_VLAN_PPI_SIZE;
+		ppi = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
+					IEEE_8021Q_INFO);
+		vlan = (struct ndis_pkt_8021q_info *)((void *)ppi +
+						ppi->ppi_offset);
+		vlan->vlanid = packet->vlan_tci & VLAN_VID_MASK;
+		vlan->pri = (packet->vlan_tci & VLAN_PRIO_MASK) >>
+				VLAN_PRIO_SHIFT;
+	}
+
+	net_trans_info = get_net_transport_info(skb, &hdr_offset);
+	if (net_trans_info == TRANSPORT_INFO_NOT_IP)
+		goto do_send;
+
+	/*
+	 * Setup the sendside checksum offload only if this is not a
+	 * GSO packet.
+	 */
+	if (skb_is_gso(skb))
+		goto do_lso;
+
+	if ((skb->ip_summed == CHECKSUM_NONE) ||
+	    (skb->ip_summed == CHECKSUM_UNNECESSARY))
+		goto do_send;
+
+	rndis_msg_size += NDIS_CSUM_PPI_SIZE;
+	ppi = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
+			    TCPIP_CHKSUM_PKTINFO);
+
+	csum_info = (struct ndis_tcp_ip_checksum_info *)((void *)ppi +
+			ppi->ppi_offset);
+
+	if (net_trans_info & (INFO_IPV4 << 16))
+		csum_info->transmit.is_ipv4 = 1;
 	else
-		packet->page_buf[1].len = PAGE_SIZE
-			- packet->page_buf[1].offset;
+		csum_info->transmit.is_ipv6 = 1;
 
-	for (i = 2; i <= npg_data; i++) {
-		packet->page_buf[i].pfn = virt_to_phys(skb->data
-			+ PAGE_SIZE * (i-1)) >> PAGE_SHIFT;
-		packet->page_buf[i].offset = 0;
-		packet->page_buf[i].len = PAGE_SIZE;
-	}
-	if (npg_data > 1)
-		packet->page_buf[npg_data].len = (((unsigned long)skb->data
-			+ skb_headlen(skb) - 1) & (PAGE_SIZE - 1)) + 1;
-
-	/* Additional fragments are after SKB data */
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		const skb_frag_t *f = &skb_shinfo(skb)->frags[i];
-
-		packet->page_buf[i+npg_data+1].pfn =
-			page_to_pfn(skb_frag_page(f));
-		packet->page_buf[i+npg_data+1].offset = f->page_offset;
-		packet->page_buf[i+npg_data+1].len = skb_frag_size(f);
+	if (net_trans_info & INFO_TCP) {
+		csum_info->transmit.tcp_checksum = 1;
+		csum_info->transmit.tcp_header_offset = hdr_offset;
+	} else if (net_trans_info & INFO_UDP) {
+		/* UDP checksum offload is not supported on ws2008r2.
+		 * Furthermore, on ws2012 and ws2012r2, there are some
+		 * issues with udp checksum offload from Linux guests.
+		 * (these are host issues).
+		 * For now compute the checksum here.
+		 */
+		struct udphdr *uh;
+		u16 udp_len;
+
+		ret = skb_cow_head(skb, 0);
+		if (ret)
+			goto drop;
+
+		uh = udp_hdr(skb);
+		udp_len = ntohs(uh->len);
+		uh->check = 0;
+		uh->check = csum_tcpudp_magic(ip_hdr(skb)->saddr,
+					      ip_hdr(skb)->daddr,
+					      udp_len, IPPROTO_UDP,
+					      csum_partial(uh, udp_len, 0));
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		csum_info->transmit.udp_checksum = 0;
 	}
+	goto do_send;
 
-	/* Set the completion routine */
-	packet->completion.send.send_completion = netvsc_xmit_completion;
-	packet->completion.send.send_completion_ctx = packet;
-	packet->completion.send.send_completion_tid = (unsigned long)skb;
+do_lso:
+	rndis_msg_size += NDIS_LSO_PPI_SIZE;
+	ppi = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
+			    TCP_LARGESEND_PKTINFO);
+
+	lso_info = (struct ndis_tcp_lso_info *)((void *)ppi +
+			ppi->ppi_offset);
+
+	lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE;
+	if (net_trans_info & (INFO_IPV4 << 16)) {
+		lso_info->lso_v2_transmit.ip_version =
+			NDIS_TCP_LARGE_SEND_OFFLOAD_IPV4;
+		ip_hdr(skb)->tot_len = 0;
+		ip_hdr(skb)->check = 0;
+		tcp_hdr(skb)->check =
+		~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+				   ip_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
+	} else {
+		lso_info->lso_v2_transmit.ip_version =
+			NDIS_TCP_LARGE_SEND_OFFLOAD_IPV6;
+		ipv6_hdr(skb)->payload_len = 0;
+		tcp_hdr(skb)->check =
+		~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+				&ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
+	}
+	lso_info->lso_v2_transmit.tcp_header_offset = hdr_offset;
+	lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size;
+
+do_send:
+	/* Start filling in the page buffers with the rndis hdr */
+	rndis_msg->msg_len += rndis_msg_size;
+	packet->total_data_buflen = rndis_msg->msg_len;
+	packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size,
+					       skb, packet);
 
-	ret = rndis_filter_send(net_device_ctx->device_ctx,
-				  packet);
+	ret = netvsc_send(net_device_ctx->device_ctx, packet);
+
+drop:
 	if (ret == 0) {
-		net->stats.tx_bytes += skb_length;
-		net->stats.tx_packets++;
+		u64_stats_update_begin(&tx_stats->syncp);
+		tx_stats->packets++;
+		tx_stats->bytes += skb_length;
+		u64_stats_update_end(&tx_stats->syncp);
 	} else {
-		kfree(packet);
 		if (ret != -EAGAIN) {
 			dev_kfree_skb_any(skb);
 			net->stats.tx_dropped++;
@@ -229,28 +582,42 @@
  * netvsc_linkstatus_callback - Link up/down notification
  */
 void netvsc_linkstatus_callback(struct hv_device *device_obj,
-				       unsigned int status)
+				struct rndis_message *resp)
 {
+	struct rndis_indicate_status *indicate = &resp->msg.indicate_status;
 	struct net_device *net;
 	struct net_device_context *ndev_ctx;
 	struct netvsc_device *net_device;
+	struct rndis_device *rdev;
 
 	net_device = hv_get_drvdata(device_obj);
-	net = net_device->ndev;
+	rdev = net_device->extension;
 
-	if (!net) {
-		netdev_err(net, "got link status but net device "
-				"not initialized yet\n");
+	switch (indicate->status) {
+	case RNDIS_STATUS_MEDIA_CONNECT:
+		rdev->link_state = false;
+		break;
+	case RNDIS_STATUS_MEDIA_DISCONNECT:
+		rdev->link_state = true;
+		break;
+	case RNDIS_STATUS_NETWORK_CHANGE:
+		rdev->link_change = true;
+		break;
+	default:
 		return;
 	}
 
-	if (status == 1) {
-		netif_carrier_on(net);
-		ndev_ctx = netdev_priv(net);
+	net = net_device->ndev;
+
+	if (!net || net->reg_state != NETREG_REGISTERED)
+		return;
+
+	ndev_ctx = netdev_priv(net);
+	if (!rdev->link_state) {
 		schedule_delayed_work(&ndev_ctx->dwork, 0);
 		schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20));
 	} else {
-		netif_carrier_off(net);
+		schedule_delayed_work(&ndev_ctx->dwork, 0);
 	}
 }
 
@@ -259,18 +626,21 @@
  * "wire" on the specified device.
  */
 int netvsc_recv_callback(struct hv_device *device_obj,
-				struct hv_netvsc_packet *packet)
+				struct hv_netvsc_packet *packet,
+				struct ndis_tcp_ip_checksum_info *csum_info)
 {
 	struct net_device *net;
+	struct net_device_context *net_device_ctx;
 	struct sk_buff *skb;
+	struct netvsc_stats *rx_stats;
 
 	net = ((struct netvsc_device *)hv_get_drvdata(device_obj))->ndev;
-	if (!net) {
-		netdev_err(net, "got receive callback but net device"
-			" not initialized yet\n");
+	if (!net || net->reg_state != NETREG_REGISTERED) {
 		packet->status = NVSP_STAT_FAIL;
 		return 0;
 	}
+	net_device_ctx = netdev_priv(net);
+	rx_stats = this_cpu_ptr(net_device_ctx->rx_stats);
 
 	/* Allocate a skb - TODO direct I/O to pages? */
 	skb = netdev_alloc_skb_ip_align(net, packet->total_data_buflen);
@@ -288,13 +658,28 @@
 		packet->total_data_buflen);
 
 	skb->protocol = eth_type_trans(skb, net);
-	skb->ip_summed = CHECKSUM_NONE;
+	if (csum_info) {
+		/* We only look at the IP checksum here.
+		 * Should we be dropping the packet if checksum
+		 * failed? How do we deal with other checksums - TCP/UDP?
+		 */
+		if (csum_info->receive.ip_checksum_succeeded)
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		else
+			skb->ip_summed = CHECKSUM_NONE;
+	}
+
 	if (packet->vlan_tci & VLAN_TAG_PRESENT)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 				       packet->vlan_tci);
 
-	net->stats.rx_packets++;
-	net->stats.rx_bytes += packet->total_data_buflen;
+	skb_record_rx_queue(skb, packet->channel->
+			    offermsg.offer.sub_channel_index);
+
+	u64_stats_update_begin(&rx_stats->syncp);
+	rx_stats->packets++;
+	rx_stats->bytes += packet->total_data_buflen;
+	u64_stats_update_end(&rx_stats->syncp);
 
 	/*
 	 * Pass the skb back up. Network stack will deallocate the skb when it
@@ -310,10 +695,120 @@
 			       struct ethtool_drvinfo *info)
 {
 	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
-	strlcpy(info->version, HV_DRV_VERSION, sizeof(info->version));
 	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
 }
 
+static void netvsc_get_channels(struct net_device *net,
+				struct ethtool_channels *channel)
+{
+	struct net_device_context *net_device_ctx = netdev_priv(net);
+	struct hv_device *dev = net_device_ctx->device_ctx;
+	struct netvsc_device *nvdev = hv_get_drvdata(dev);
+
+	if (nvdev) {
+		channel->max_combined	= nvdev->max_chn;
+		channel->combined_count = nvdev->num_chn;
+	}
+}
+
+static int netvsc_set_channels(struct net_device *net,
+			       struct ethtool_channels *channels)
+{
+	struct net_device_context *net_device_ctx = netdev_priv(net);
+	struct hv_device *dev = net_device_ctx->device_ctx;
+	struct netvsc_device *nvdev = hv_get_drvdata(dev);
+	struct netvsc_device_info device_info;
+	u32 num_chn;
+	u32 max_chn;
+	int ret = 0;
+	bool recovering = false;
+
+	if (!nvdev || nvdev->destroy)
+		return -ENODEV;
+
+	num_chn = nvdev->num_chn;
+	max_chn = min_t(u32, nvdev->max_chn, num_online_cpus());
+
+	if (nvdev->nvsp_version < NVSP_PROTOCOL_VERSION_5) {
+		pr_info("vRSS unsupported before NVSP Version 5\n");
+		return -EINVAL;
+	}
+
+	/* We do not support rx, tx, or other */
+	if (!channels ||
+	    channels->rx_count ||
+	    channels->tx_count ||
+	    channels->other_count ||
+	    (channels->combined_count < 1))
+		return -EINVAL;
+
+	if (channels->combined_count > max_chn) {
+		pr_info("combined channels too high, using %d\n", max_chn);
+		channels->combined_count = max_chn;
+	}
+
+	ret = netvsc_close(net);
+	if (ret)
+		goto out;
+
+ do_set:
+	nvdev->start_remove = true;
+	rndis_filter_device_remove(dev);
+
+	nvdev->num_chn = channels->combined_count;
+
+	net_device_ctx->device_ctx = dev;
+	hv_set_drvdata(dev, net);
+
+	memset(&device_info, 0, sizeof(device_info));
+	device_info.num_chn = nvdev->num_chn; /* passed to RNDIS */
+	device_info.ring_size = ring_size;
+	device_info.max_num_vrss_chns = max_num_vrss_chns;
+
+	ret = rndis_filter_device_add(dev, &device_info);
+	if (ret) {
+		if (recovering) {
+			netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
+			return ret;
+		}
+		goto recover;
+	}
+
+	nvdev = hv_get_drvdata(dev);
+
+	ret = netif_set_real_num_tx_queues(net, nvdev->num_chn);
+	if (ret) {
+		if (recovering) {
+			netdev_err(net, "could not set tx queue count (ret %d)\n", ret);
+			return ret;
+		}
+		goto recover;
+	}
+
+	ret = netif_set_real_num_rx_queues(net, nvdev->num_chn);
+	if (ret) {
+		if (recovering) {
+			netdev_err(net, "could not set rx queue count (ret %d)\n", ret);
+			return ret;
+		}
+		goto recover;
+	}
+
+ out:
+	netvsc_open(net);
+
+	return ret;
+
+ recover:
+	/* If the above failed, we attempt to recover through the same
+	 * process but with the original number of channels.
+	 */
+	netdev_err(net, "could not set channels, recovering\n");
+	recovering = true;
+	channels->combined_count = num_chn;
+	goto do_set;
+}
+
 static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 {
 	struct net_device_context *ndevctx = netdev_priv(ndev);
@@ -321,32 +816,81 @@
 	struct netvsc_device *nvdev = hv_get_drvdata(hdev);
 	struct netvsc_device_info device_info;
 	int limit = ETH_DATA_LEN;
+	int ret = 0;
 
 	if (nvdev == NULL || nvdev->destroy)
 		return -ENODEV;
 
-	if (nvdev->nvsp_version == NVSP_PROTOCOL_VERSION_2)
-		limit = NETVSC_MTU;
+	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
+		limit = NETVSC_MTU - ETH_HLEN;
 
-	if (mtu < 68 || mtu > limit)
+	if (mtu < NETVSC_MTU_MIN || mtu > limit)
 		return -EINVAL;
 
+	ret = netvsc_close(ndev);
+	if (ret)
+		goto out;
+
 	nvdev->start_remove = true;
-	cancel_work_sync(&ndevctx->work);
-	netif_tx_disable(ndev);
 	rndis_filter_device_remove(hdev);
 
 	ndev->mtu = mtu;
 
 	ndevctx->device_ctx = hdev;
 	hv_set_drvdata(hdev, ndev);
+
+	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
+	device_info.num_chn = nvdev->num_chn;
+	device_info.max_num_vrss_chns = max_num_vrss_chns;
 	rndis_filter_device_add(hdev, &device_info);
-	netif_wake_queue(ndev);
 
-	return 0;
+out:
+	netvsc_open(ndev);
+
+	return ret;
 }
 
+static struct rtnl_link_stats64 *netvsc_get_stats64(struct net_device *net,
+						    struct rtnl_link_stats64 *t)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(net);
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct netvsc_stats *tx_stats = per_cpu_ptr(ndev_ctx->tx_stats,
+							    cpu);
+		struct netvsc_stats *rx_stats = per_cpu_ptr(ndev_ctx->rx_stats,
+							    cpu);
+		u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&tx_stats->syncp);
+			tx_packets = tx_stats->packets;
+			tx_bytes = tx_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start));
+
+		do {
+			start = u64_stats_fetch_begin_irq(&rx_stats->syncp);
+			rx_packets = rx_stats->packets;
+			rx_bytes = rx_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start));
+
+		t->tx_bytes	+= tx_bytes;
+		t->tx_packets	+= tx_packets;
+		t->rx_bytes	+= rx_bytes;
+		t->rx_packets	+= rx_packets;
+	}
+
+	t->tx_dropped	= net->stats.tx_dropped;
+	t->tx_errors	= net->stats.tx_dropped;
+
+	t->rx_dropped	= net->stats.rx_dropped;
+	t->rx_errors	= net->stats.rx_errors;
+
+	return t;
+}
 
 static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
 {
@@ -374,10 +918,20 @@
 	return err;
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void netvsc_poll_controller(struct net_device *net)
+{
+	/* As netvsc_start_xmit() works synchronous we don't have to
+	 * trigger anything here.
+	 */
+}
+#endif
 
 static const struct ethtool_ops ethtool_ops = {
 	.get_drvinfo	= netvsc_get_drvinfo,
 	.get_link	= ethtool_op_get_link,
+	.get_channels   = netvsc_get_channels,
+	.set_channels   = netvsc_set_channels,
 };
 
 static const struct net_device_ops device_ops = {
@@ -388,6 +942,11 @@
 	.ndo_change_mtu =		netvsc_change_mtu,
 	.ndo_validate_addr =		eth_validate_addr,
 	.ndo_set_mac_address =		netvsc_set_mac_addr,
+	.ndo_select_queue =		netvsc_select_queue,
+	.ndo_get_stats64 =		netvsc_get_stats64,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller =		netvsc_poll_controller,
+#endif
 };
 
 /*
@@ -396,19 +955,54 @@
  * current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, add
  * another netif_notify_peers() into a delayed work, otherwise GARP packet
  * will not be sent after quick migration, and cause network disconnection.
+ * Also, we update the carrier status here.
  */
-static void netvsc_send_garp(struct work_struct *w)
+static void netvsc_link_change(struct work_struct *w)
 {
 	struct net_device_context *ndev_ctx;
 	struct net_device *net;
 	struct netvsc_device *net_device;
+	struct rndis_device *rdev;
+	bool notify, refresh = false;
+	char *argv[] = { "/etc/init.d/network", "restart", NULL };
+	char *envp[] = { "HOME=/", "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL };
+
+	rtnl_lock();
 
 	ndev_ctx = container_of(w, struct net_device_context, dwork.work);
 	net_device = hv_get_drvdata(ndev_ctx->device_ctx);
+	rdev = net_device->extension;
 	net = net_device->ndev;
-	netdev_notify_peers(net);
+
+	if (rdev->link_state) {
+		netif_carrier_off(net);
+		notify = false;
+	} else {
+		netif_carrier_on(net);
+		notify = true;
+		if (rdev->link_change) {
+			rdev->link_change = false;
+			refresh = true;
+		}
+	}
+
+	rtnl_unlock();
+
+	if (refresh)
+		call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+
+	if (notify)
+		netdev_notify_peers(net);
 }
 
+static void netvsc_free_netdev(struct net_device *netdev)
+{
+	struct net_device_context *net_device_ctx = netdev_priv(netdev);
+
+	free_percpu(net_device_ctx->tx_stats);
+	free_percpu(net_device_ctx->rx_stats);
+	free_netdev(netdev);
+}
 
 static int netvsc_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
@@ -416,53 +1010,87 @@
 	struct net_device *net = NULL;
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device_info device_info;
+	struct netvsc_device *nvdev;
 	int ret;
+	u32 max_needed_headroom;
 
-	net = alloc_etherdev(sizeof(struct net_device_context));
+	net = alloc_etherdev_mq(sizeof(struct net_device_context),
+				num_online_cpus());
 	if (!net)
 		return -ENOMEM;
 
-	/* Set initial state */
+	max_needed_headroom = sizeof(struct hv_netvsc_packet) +
+			      RNDIS_AND_PPI_SIZE;
+
 	netif_carrier_off(net);
 
 	net_device_ctx = netdev_priv(net);
 	net_device_ctx->device_ctx = dev;
+	net_device_ctx->msg_enable = netif_msg_init(debug, default_msg);
+	if (netif_msg_probe(net_device_ctx))
+		netdev_dbg(net, "netvsc msg_enable: %d\n",
+			   net_device_ctx->msg_enable);
+
+	net_device_ctx->tx_stats = netdev_alloc_pcpu_stats(struct netvsc_stats);
+	if (!net_device_ctx->tx_stats) {
+		free_netdev(net);
+		return -ENOMEM;
+	}
+	net_device_ctx->rx_stats = netdev_alloc_pcpu_stats(struct netvsc_stats);
+	if (!net_device_ctx->rx_stats) {
+		free_percpu(net_device_ctx->tx_stats);
+		free_netdev(net);
+		return -ENOMEM;
+	}
+
 	hv_set_drvdata(dev, net);
-	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_send_garp);
+	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
 	INIT_WORK(&net_device_ctx->work, do_set_multicast);
 
 	net->netdev_ops = &device_ops;
 
-	/* TODO: Add GSO and Checksum offload */
-	net->hw_features = 0;
-	net->features = NETIF_F_HW_VLAN_CTAG_TX;
+	net->hw_features = NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_IP_CSUM |
+				NETIF_F_TSO;
+	net->features = NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_SG | NETIF_F_RXCSUM |
+			NETIF_F_IP_CSUM | NETIF_F_TSO;
 
-	SET_ETHTOOL_OPS(net, &ethtool_ops);
+	net->ethtool_ops = &ethtool_ops;
 	SET_NETDEV_DEV(net, &dev->device);
-	netif_set_gso_max_size(net, NETVSC_GSO_MAX_SIZE);
 
-	ret = register_netdev(net);
-	if (ret != 0) {
-		pr_err("Unable to register netdev.\n");
-		free_netdev(net);
-		goto out;
-	}
+	/*
+	 * Request additional head room in the skb.
+	 * We will use this space to build the rndis
+	 * heaser and other state we need to maintain.
+	 */
+	net->needed_headroom = max_needed_headroom;
 
 	/* Notify the netvsc driver of the new device */
+	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
+	device_info.max_num_vrss_chns = max_num_vrss_chns;
 	ret = rndis_filter_device_add(dev, &device_info);
 	if (ret != 0) {
 		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
-		unregister_netdev(net);
-		free_netdev(net);
+		netvsc_free_netdev(net);
 		hv_set_drvdata(dev, NULL);
 		return ret;
 	}
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
-	netif_carrier_on(net);
+	nvdev = hv_get_drvdata(dev);
+	netif_set_real_num_tx_queues(net, nvdev->num_chn);
+	netif_set_real_num_rx_queues(net, nvdev->num_chn);
+	netif_set_gso_max_size(net, NETVSC_GSO_MAX_SIZE);
+
+	ret = register_netdev(net);
+	if (ret != 0) {
+		pr_err("Unable to register netdev.\n");
+		rndis_filter_device_remove(dev);
+		netvsc_free_netdev(net);
+	} else {
+		schedule_delayed_work(&net_device_ctx->dwork, 0);
+	}
 
-out:
 	return ret;
 }
 
@@ -497,7 +1125,7 @@
 	 */
 	rndis_filter_device_remove(dev);
 
-	free_netdev(net);
+	netvsc_free_netdev(net);
 	return 0;
 }
 
@@ -533,7 +1161,6 @@
 }
 
 MODULE_LICENSE("GPL");
-MODULE_VERSION(HV_DRV_VERSION);
 MODULE_DESCRIPTION("Microsoft Hyper-V network driver");
 
 module_init(netvsc_drv_init);