These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

4 files changed, 403 insertions, 51 deletions

diff --git a/kernel/drivers/net/hyperv/hyperv_net.h b/kernel/drivers/net/hyperv/hyperv_net.h
index 41071d32b..5fa98f599 100644
--- a/kernel/drivers/net/hyperv/hyperv_net.h
+++ b/kernel/drivers/net/hyperv/hyperv_net.h
@@ -161,6 +161,8 @@ struct netvsc_device_info {
 	unsigned char mac_adr[ETH_ALEN];
 	bool link_state;	/* 0 - link up, 1 - link down */
 	int  ring_size;
+	u32  max_num_vrss_chns;
+	u32  num_chn;
 };
 
 enum rndis_device_state {
@@ -540,6 +542,29 @@ union nvsp_2_message_uber {
 	struct nvsp_2_free_rxbuf free_rxbuf;
 } __packed;
 
+struct nvsp_4_send_vf_association {
+	/* 1: allocated, serial number is valid. 0: not allocated */
+	u32 allocated;
+
+	/* Serial number of the VF to team with */
+	u32 serial;
+} __packed;
+
+enum nvsp_vm_datapath {
+	NVSP_DATAPATH_SYNTHETIC = 0,
+	NVSP_DATAPATH_VF,
+	NVSP_DATAPATH_MAX
+};
+
+struct nvsp_4_sw_datapath {
+	u32 active_datapath; /* active data path in VM */
+} __packed;
+
+union nvsp_4_message_uber {
+	struct nvsp_4_send_vf_association vf_assoc;
+	struct nvsp_4_sw_datapath active_dp;
+} __packed;
+
 enum nvsp_subchannel_operation {
 	NVSP_SUBCHANNEL_NONE = 0,
 	NVSP_SUBCHANNEL_ALLOCATE,
@@ -577,6 +602,7 @@ union nvsp_all_messages {
 	union nvsp_message_init_uber init_msg;
 	union nvsp_1_message_uber v1_msg;
 	union nvsp_2_message_uber v2_msg;
+	union nvsp_4_message_uber v4_msg;
 	union nvsp_5_message_uber v5_msg;
 } __packed;
 
@@ -588,6 +614,7 @@ struct nvsp_message {
 
 
 #define NETVSC_MTU 65536
+#define NETVSC_MTU_MIN 68
 
 #define NETVSC_RECEIVE_BUFFER_SIZE		(1024*1024*16)	/* 16MB */
 #define NETVSC_RECEIVE_BUFFER_SIZE_LEGACY	(1024*1024*15)  /* 15MB */
@@ -611,6 +638,12 @@ struct multi_send_data {
 	u32 count; /* counter of batched packets */
 };
 
+struct netvsc_stats {
+	u64 packets;
+	u64 bytes;
+	struct u64_stats_sync syncp;
+};
+
 /* The context of the netvsc device  */
 struct net_device_context {
 	/* point back to our device context */
@@ -618,6 +651,9 @@ struct net_device_context {
 	struct delayed_work dwork;
 	struct work_struct work;
 	u32 msg_enable; /* debug level */
+
+	struct netvsc_stats __percpu *tx_stats;
+	struct netvsc_stats __percpu *rx_stats;
 };
 
 /* Per netvsc device */
@@ -660,6 +696,8 @@ struct netvsc_device {
 	u32 send_table[VRSS_SEND_TAB_SIZE];
 	u32 max_chn;
 	u32 num_chn;
+	spinlock_t sc_lock; /* Protects num_sc_offered variable */
+	u32 num_sc_offered;
 	atomic_t queue_sends[NR_CPUS];
 
 	/* Holds rndis device info */
@@ -678,6 +716,11 @@ struct netvsc_device {
 
 	/* The net device context */
 	struct net_device_context *nd_ctx;
+
+	/* 1: allocated, serial number is valid. 0: not allocated */
+	u32 vf_alloc;
+	/* Serial number of the VF to team with */
+	u32 vf_serial;
 };
 
 /* NdisInitialize message */
diff --git a/kernel/drivers/net/hyperv/netvsc.c b/kernel/drivers/net/hyperv/netvsc.c
index ea091bc5f..51e4c0fd0 100644
--- a/kernel/drivers/net/hyperv/netvsc.c
+++ b/kernel/drivers/net/hyperv/netvsc.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/netdevice.h>
 #include <linux/if_ether.h>
+#include <linux/vmalloc.h>
 #include <asm/sync_bitops.h>
 
 #include "hyperv_net.h"
@@ -227,13 +228,18 @@ static int netvsc_init_buf(struct hv_device *device)
 	struct netvsc_device *net_device;
 	struct nvsp_message *init_packet;
 	struct net_device *ndev;
+	int node;
 
 	net_device = get_outbound_net_device(device);
 	if (!net_device)
 		return -ENODEV;
 	ndev = net_device->ndev;
 
-	net_device->recv_buf = vzalloc(net_device->recv_buf_size);
+	node = cpu_to_node(device->channel->target_cpu);
+	net_device->recv_buf = vzalloc_node(net_device->recv_buf_size, node);
+	if (!net_device->recv_buf)
+		net_device->recv_buf = vzalloc(net_device->recv_buf_size);
+
 	if (!net_device->recv_buf) {
 		netdev_err(ndev, "unable to allocate receive "
 			"buffer of size %d\n", net_device->recv_buf_size);
@@ -321,7 +327,9 @@ static int netvsc_init_buf(struct hv_device *device)
 
 	/* Now setup the send buffer.
 	 */
-	net_device->send_buf = vzalloc(net_device->send_buf_size);
+	net_device->send_buf = vzalloc_node(net_device->send_buf_size, node);
+	if (!net_device->send_buf)
+		net_device->send_buf = vzalloc(net_device->send_buf_size);
 	if (!net_device->send_buf) {
 		netdev_err(ndev, "unable to allocate send "
 			   "buffer of size %d\n", net_device->send_buf_size);
@@ -445,13 +453,16 @@ static int negotiate_nvsp_ver(struct hv_device *device,
 	if (nvsp_ver == NVSP_PROTOCOL_VERSION_1)
 		return 0;
 
-	/* NVSPv2 only: Send NDIS config */
+	/* NVSPv2 or later: Send NDIS config */
 	memset(init_packet, 0, sizeof(struct nvsp_message));
 	init_packet->hdr.msg_type = NVSP_MSG2_TYPE_SEND_NDIS_CONFIG;
 	init_packet->msg.v2_msg.send_ndis_config.mtu = net_device->ndev->mtu +
 						       ETH_HLEN;
 	init_packet->msg.v2_msg.send_ndis_config.capability.ieee8021q = 1;
 
+	if (nvsp_ver >= NVSP_PROTOCOL_VERSION_5)
+		init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1;
+
 	ret = vmbus_sendpacket(device->channel, init_packet,
 				sizeof(struct nvsp_message),
 				(unsigned long)init_packet,
@@ -743,6 +754,7 @@ static inline int netvsc_send_pkt(
 	u64 req_id;
 	int ret;
 	struct hv_page_buffer *pgbuf;
+	u32 ring_avail = hv_ringbuf_avail_percent(&out_channel->outbound);
 
 	nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
 	if (packet->is_data_pkt) {
@@ -769,32 +781,42 @@ static inline int netvsc_send_pkt(
 	if (out_channel->rescind)
 		return -ENODEV;
 
+	/*
+	 * It is possible that once we successfully place this packet
+	 * on the ringbuffer, we may stop the queue. In that case, we want
+	 * to notify the host independent of the xmit_more flag. We don't
+	 * need to be precise here; in the worst case we may signal the host
+	 * unnecessarily.
+	 */
+	if (ring_avail < (RING_AVAIL_PERCENT_LOWATER + 1))
+		packet->xmit_more = false;
+
 	if (packet->page_buf_cnt) {
 		pgbuf = packet->cp_partial ? packet->page_buf +
 			packet->rmsg_pgcnt : packet->page_buf;
-		ret = vmbus_sendpacket_pagebuffer(out_channel,
-						  pgbuf,
-						  packet->page_buf_cnt,
-						  &nvmsg,
-						  sizeof(struct nvsp_message),
-						  req_id);
+		ret = vmbus_sendpacket_pagebuffer_ctl(out_channel,
+						      pgbuf,
+						      packet->page_buf_cnt,
+						      &nvmsg,
+						      sizeof(struct nvsp_message),
+						      req_id,
+						      VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
+						      !packet->xmit_more);
 	} else {
-		ret = vmbus_sendpacket(
-				out_channel, &nvmsg,
-				sizeof(struct nvsp_message),
-				req_id,
-				VM_PKT_DATA_INBAND,
-				VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+		ret = vmbus_sendpacket_ctl(out_channel, &nvmsg,
+					   sizeof(struct nvsp_message),
+					   req_id,
+					   VM_PKT_DATA_INBAND,
+					   VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
+					   !packet->xmit_more);
 	}
 
 	if (ret == 0) {
 		atomic_inc(&net_device->num_outstanding_sends);
 		atomic_inc(&net_device->queue_sends[q_idx]);
 
-		if (hv_ringbuf_avail_percent(&out_channel->outbound) <
-			RING_AVAIL_PERCENT_LOWATER) {
-			netif_tx_stop_queue(netdev_get_tx_queue(
-					    ndev, q_idx));
+		if (ring_avail < RING_AVAIL_PERCENT_LOWATER) {
+			netif_tx_stop_queue(netdev_get_tx_queue(ndev, q_idx));
 
 			if (atomic_read(&net_device->
 				queue_sends[q_idx]) < 1)
@@ -1045,11 +1067,10 @@ static void netvsc_receive(struct netvsc_device *net_device,
 
 
 static void netvsc_send_table(struct hv_device *hdev,
-			      struct vmpacket_descriptor *vmpkt)
+			      struct nvsp_message *nvmsg)
 {
 	struct netvsc_device *nvscdev;
 	struct net_device *ndev;
-	struct nvsp_message *nvmsg;
 	int i;
 	u32 count, *tab;
 
@@ -1058,12 +1079,6 @@ static void netvsc_send_table(struct hv_device *hdev,
 		return;
 	ndev = nvscdev->ndev;
 
-	nvmsg = (struct nvsp_message *)((unsigned long)vmpkt +
-					(vmpkt->offset8 << 3));
-
-	if (nvmsg->hdr.msg_type != NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE)
-		return;
-
 	count = nvmsg->msg.v5_msg.send_table.count;
 	if (count != VRSS_SEND_TAB_SIZE) {
 		netdev_err(ndev, "Received wrong send-table size:%u\n", count);
@@ -1077,6 +1092,28 @@ static void netvsc_send_table(struct hv_device *hdev,
 		nvscdev->send_table[i] = tab[i];
 }
 
+static void netvsc_send_vf(struct netvsc_device *nvdev,
+			   struct nvsp_message *nvmsg)
+{
+	nvdev->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated;
+	nvdev->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial;
+}
+
+static inline void netvsc_receive_inband(struct hv_device *hdev,
+					 struct netvsc_device *nvdev,
+					 struct nvsp_message *nvmsg)
+{
+	switch (nvmsg->hdr.msg_type) {
+	case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE:
+		netvsc_send_table(hdev, nvmsg);
+		break;
+
+	case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION:
+		netvsc_send_vf(nvdev, nvmsg);
+		break;
+	}
+}
+
 void netvsc_channel_cb(void *context)
 {
 	int ret;
@@ -1089,6 +1126,7 @@ void netvsc_channel_cb(void *context)
 	unsigned char *buffer;
 	int bufferlen = NETVSC_PACKET_SIZE;
 	struct net_device *ndev;
+	struct nvsp_message *nvmsg;
 
 	if (channel->primary_channel != NULL)
 		device = channel->primary_channel->device_obj;
@@ -1107,6 +1145,8 @@ void netvsc_channel_cb(void *context)
 		if (ret == 0) {
 			if (bytes_recvd > 0) {
 				desc = (struct vmpacket_descriptor *)buffer;
+				nvmsg = (struct nvsp_message *)((unsigned long)
+					 desc + (desc->offset8 << 3));
 				switch (desc->type) {
 				case VM_PKT_COMP:
 					netvsc_send_completion(net_device,
@@ -1119,7 +1159,9 @@ void netvsc_channel_cb(void *context)
 					break;
 
 				case VM_PKT_DATA_INBAND:
-					netvsc_send_table(device, desc);
+					netvsc_receive_inband(device,
+							      net_device,
+							      nvmsg);
 					break;
 
 				default:
diff --git a/kernel/drivers/net/hyperv/netvsc_drv.c b/kernel/drivers/net/hyperv/netvsc_drv.c
index 5993c7e2d..409b48e1e 100644
--- a/kernel/drivers/net/hyperv/netvsc_drv.c
+++ b/kernel/drivers/net/hyperv/netvsc_drv.c
@@ -46,6 +46,8 @@ static int ring_size = 128;
 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 |
@@ -104,7 +106,7 @@ static int netvsc_open(struct net_device *net)
 		return ret;
 	}
 
-	netif_tx_start_all_queues(net);
+	netif_tx_wake_all_queues(net);
 
 	nvdev = hv_get_drvdata(device_obj);
 	rdev = nvdev->extension;
@@ -118,15 +120,56 @@ static int netvsc_close(struct net_device *net)
 {
 	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;
 }
@@ -196,12 +239,12 @@ static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb)
 	struct flow_keys flow;
 	int data_len;
 
-	if (!skb_flow_dissect(skb, &flow) ||
-	    !(flow.n_proto == htons(ETH_P_IP) ||
-	      flow.n_proto == htons(ETH_P_IPV6)))
+	if (!skb_flow_dissect_flow_keys(skb, &flow, 0) ||
+	    !(flow.basic.n_proto == htons(ETH_P_IP) ||
+	      flow.basic.n_proto == htons(ETH_P_IPV6)))
 		return false;
 
-	if (flow.ip_proto == IPPROTO_TCP)
+	if (flow.basic.ip_proto == IPPROTO_TCP)
 		data_len = 12;
 	else
 		data_len = 8;
@@ -391,7 +434,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	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
@@ -580,8 +623,10 @@ do_send:
 
 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 {
 		if (ret != -EAGAIN) {
 			dev_kfree_skb_any(skb);
@@ -644,13 +689,17 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 				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 || 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);
@@ -686,8 +735,10 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	skb_record_rx_queue(skb, packet->channel->
 			    offermsg.offer.sub_channel_index);
 
-	net->stats.rx_packets++;
-	net->stats.rx_bytes += packet->total_data_buflen;
+	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
@@ -719,6 +770,104 @@ static void netvsc_get_channels(struct net_device *net,
 	}
 }
 
+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);
@@ -726,6 +875,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	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;
@@ -733,26 +883,73 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
 		limit = NETVSC_MTU - ETH_HLEN;
 
-	/* Hyper-V hosts don't support MTU < ETH_DATA_LEN (1500) */
-	if (mtu < ETH_DATA_LEN || 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_tx_wake_all_queues(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)
 {
@@ -793,6 +990,7 @@ 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 = {
@@ -804,6 +1002,7 @@ static const struct net_device_ops device_ops = {
 	.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
@@ -855,6 +1054,14 @@ static void netvsc_link_change(struct work_struct *w)
 		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)
@@ -883,6 +1090,18 @@ static int netvsc_probe(struct hv_device *dev,
 		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_link_change);
 	INIT_WORK(&net_device_ctx->work, do_set_multicast);
@@ -905,11 +1124,13 @@ static int netvsc_probe(struct hv_device *dev,
 	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);
-		free_netdev(net);
+		netvsc_free_netdev(net);
 		hv_set_drvdata(dev, NULL);
 		return ret;
 	}
@@ -923,7 +1144,7 @@ static int netvsc_probe(struct hv_device *dev,
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
 		rndis_filter_device_remove(dev);
-		free_netdev(net);
+		netvsc_free_netdev(net);
 	} else {
 		schedule_delayed_work(&net_device_ctx->dwork, 0);
 	}
@@ -962,7 +1183,7 @@ static int netvsc_remove(struct hv_device *dev)
 	 */
 	rndis_filter_device_remove(dev);
 
-	free_netdev(net);
+	netvsc_free_netdev(net);
 	return 0;
 }
 
diff --git a/kernel/drivers/net/hyperv/rndis_filter.c b/kernel/drivers/net/hyperv/rndis_filter.c
index 9118cea91..5931a799a 100644
--- a/kernel/drivers/net/hyperv/rndis_filter.c
+++ b/kernel/drivers/net/hyperv/rndis_filter.c
@@ -27,6 +27,7 @@
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/nls.h>
+#include <linux/vmalloc.h>
 
 #include "hyperv_net.h"
 
@@ -983,9 +984,16 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 	struct netvsc_device *nvscdev;
 	u16 chn_index = new_sc->offermsg.offer.sub_channel_index;
 	int ret;
+	unsigned long flags;
 
 	nvscdev = hv_get_drvdata(new_sc->primary_channel->device_obj);
 
+	spin_lock_irqsave(&nvscdev->sc_lock, flags);
+	nvscdev->num_sc_offered--;
+	spin_unlock_irqrestore(&nvscdev->sc_lock, flags);
+	if (nvscdev->num_sc_offered == 0)
+		complete(&nvscdev->channel_init_wait);
+
 	if (chn_index >= nvscdev->num_chn)
 		return;
 
@@ -1013,6 +1021,11 @@ int rndis_filter_device_add(struct hv_device *dev,
 	struct ndis_recv_scale_cap rsscap;
 	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	u32 mtu, size;
+	u32 num_rss_qs;
+	u32 sc_delta;
+	const struct cpumask *node_cpu_mask;
+	u32 num_possible_rss_qs;
+	unsigned long flags;
 
 	rndis_device = get_rndis_device();
 	if (!rndis_device)
@@ -1035,6 +1048,8 @@ int rndis_filter_device_add(struct hv_device *dev,
 	net_device->max_chn = 1;
 	net_device->num_chn = 1;
 
+	spin_lock_init(&net_device->sc_lock);
+
 	net_device->extension = rndis_device;
 	rndis_device->net_dev = net_device;
 
@@ -1050,7 +1065,7 @@ int rndis_filter_device_add(struct hv_device *dev,
 	ret = rndis_filter_query_device(rndis_device,
 					RNDIS_OID_GEN_MAXIMUM_FRAME_SIZE,
 					&mtu, &size);
-	if (ret == 0 && size == sizeof(u32))
+	if (ret == 0 && size == sizeof(u32) && mtu < net_device->ndev->mtu)
 		net_device->ndev->mtu = mtu;
 
 	/* Get the mac address */
@@ -1100,9 +1115,26 @@ int rndis_filter_device_add(struct hv_device *dev,
 	if (ret || rsscap.num_recv_que < 2)
 		goto out;
 
+	num_rss_qs = min(device_info->max_num_vrss_chns, rsscap.num_recv_que);
+
 	net_device->max_chn = rsscap.num_recv_que;
-	net_device->num_chn = (num_online_cpus() < rsscap.num_recv_que) ?
-			       num_online_cpus() : rsscap.num_recv_que;
+
+	/*
+	 * We will limit the VRSS channels to the number CPUs in the NUMA node
+	 * the primary channel is currently bound to.
+	 */
+	node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu));
+	num_possible_rss_qs = cpumask_weight(node_cpu_mask);
+
+	/* We will use the given number of channels if available. */
+	if (device_info->num_chn && device_info->num_chn < net_device->max_chn)
+		net_device->num_chn = device_info->num_chn;
+	else
+		net_device->num_chn = min(num_possible_rss_qs, num_rss_qs);
+
+	num_rss_qs = net_device->num_chn - 1;
+	net_device->num_sc_offered = num_rss_qs;
+
 	if (net_device->num_chn == 1)
 		goto out;
 
@@ -1144,11 +1176,25 @@ int rndis_filter_device_add(struct hv_device *dev,
 
 	ret = rndis_filter_set_rss_param(rndis_device, net_device->num_chn);
 
+	/*
+	 * Wait for the host to send us the sub-channel offers.
+	 */
+	spin_lock_irqsave(&net_device->sc_lock, flags);
+	sc_delta = num_rss_qs - (net_device->num_chn - 1);
+	net_device->num_sc_offered -= sc_delta;
+	spin_unlock_irqrestore(&net_device->sc_lock, flags);
+
+	while (net_device->num_sc_offered != 0) {
+		t = wait_for_completion_timeout(&net_device->channel_init_wait, 10*HZ);
+		if (t == 0)
+			WARN(1, "Netvsc: Waiting for sub-channel processing");
+	}
 out:
 	if (ret) {
 		net_device->max_chn = 1;
 		net_device->num_chn = 1;
 	}
+
 	return 0; /* return 0 because primary channel can be used alone */
 
 err_dev_remv: