4 files changed, 476 insertions, 334 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 4f3afcf92a7c..01017dd88802 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -179,7 +179,7 @@ struct rndis_device {
 
 	u8 hw_mac_adr[ETH_ALEN];
 	u8 rss_key[NETVSC_HASH_KEYLEN];
-	u16 ind_table[ITAB_NUM];
+	u16 rx_table[ITAB_NUM];
 };
 
 
@@ -192,7 +192,7 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 					const struct netvsc_device_info *info);
 int netvsc_alloc_recv_comp_ring(struct netvsc_device *net_device, u32 q_idx);
 void netvsc_device_remove(struct hv_device *device);
-int netvsc_send(struct net_device_context *ndc,
+int netvsc_send(struct net_device *net,
 		struct hv_netvsc_packet *packet,
 		struct rndis_message *rndis_msg,
 		struct hv_page_buffer *page_buffer,
@@ -208,7 +208,6 @@ void netvsc_channel_cb(void *context);
 int netvsc_poll(struct napi_struct *napi, int budget);
 
 void rndis_set_subchannel(struct work_struct *w);
-bool rndis_filter_opened(const struct netvsc_device *nvdev);
 int rndis_filter_open(struct netvsc_device *nvdev);
 int rndis_filter_close(struct netvsc_device *nvdev);
 struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
@@ -659,6 +658,10 @@ struct nvsp_message {
 #define NETVSC_RECEIVE_BUFFER_ID		0xcafe
 #define NETVSC_SEND_BUFFER_ID			0
 
+#define NETVSC_SUPPORTED_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | \
+				      NETIF_F_TSO | NETIF_F_IPV6_CSUM | \
+				      NETIF_F_TSO6)
+
 #define VRSS_SEND_TAB_SIZE 16  /* must be power of 2 */
 #define VRSS_CHANNEL_MAX 64
 #define VRSS_CHANNEL_DEFAULT 8
@@ -734,7 +737,7 @@ struct net_device_context {
 
 	u32 tx_checksum_mask;
 
-	u32 tx_send_table[VRSS_SEND_TAB_SIZE];
+	u32 tx_table[VRSS_SEND_TAB_SIZE];
 
 	/* Ethtool settings */
 	bool udp4_l4_hash;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index a6bafcf55776..4647ecbe6f36 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -89,6 +89,11 @@ static void free_netvsc_device(struct rcu_head *head)
 		= container_of(head, struct netvsc_device, rcu);
 	int i;
 
+	kfree(nvdev->extension);
+	vfree(nvdev->recv_buf);
+	vfree(nvdev->send_buf);
+	kfree(nvdev->send_section_map);
+
 	for (i = 0; i < VRSS_CHANNEL_MAX; i++)
 		vfree(nvdev->chan_table[i].mrc.slots);
 
@@ -100,12 +105,11 @@ static void free_netvsc_device_rcu(struct netvsc_device *nvdev)
 	call_rcu(&nvdev->rcu, free_netvsc_device);
 }
 
-static void netvsc_destroy_buf(struct hv_device *device)
+static void netvsc_revoke_recv_buf(struct hv_device *device,
+				   struct netvsc_device *net_device)
 {
-	struct nvsp_message *revoke_packet;
 	struct net_device *ndev = hv_get_drvdata(device);
-	struct net_device_context *ndc = netdev_priv(ndev);
-	struct netvsc_device *net_device = rtnl_dereference(ndc->nvdev);
+	struct nvsp_message *revoke_packet;
 	int ret;
 
 	/*
@@ -147,28 +151,14 @@ static void netvsc_destroy_buf(struct hv_device *device)
 		}
 		net_device->recv_section_cnt = 0;
 	}
+}
 
-	/* Teardown the gpadl on the vsp end */
-	if (net_device->recv_buf_gpadl_handle) {
-		ret = vmbus_teardown_gpadl(device->channel,
-					   net_device->recv_buf_gpadl_handle);
-
-		/* If we failed here, we might as well return and have a leak
-		 * rather than continue and a bugchk
-		 */
-		if (ret != 0) {
-			netdev_err(ndev,
-				   "unable to teardown receive buffer's gpadl\n");
-			return;
-		}
-		net_device->recv_buf_gpadl_handle = 0;
-	}
-
-	if (net_device->recv_buf) {
-		/* Free up the receive buffer */
-		vfree(net_device->recv_buf);
-		net_device->recv_buf = NULL;
-	}
+static void netvsc_revoke_send_buf(struct hv_device *device,
+				   struct netvsc_device *net_device)
+{
+	struct net_device *ndev = hv_get_drvdata(device);
+	struct nvsp_message *revoke_packet;
+	int ret;
 
 	/* Deal with the send buffer we may have setup.
 	 * If we got a  send section size, it means we received a
@@ -210,7 +200,36 @@ static void netvsc_destroy_buf(struct hv_device *device)
 		}
 		net_device->send_section_cnt = 0;
 	}
-	/* Teardown the gpadl on the vsp end */
+}
+
+static void netvsc_teardown_recv_gpadl(struct hv_device *device,
+				       struct netvsc_device *net_device)
+{
+	struct net_device *ndev = hv_get_drvdata(device);
+	int ret;
+
+	if (net_device->recv_buf_gpadl_handle) {
+		ret = vmbus_teardown_gpadl(device->channel,
+					   net_device->recv_buf_gpadl_handle);
+
+		/* If we failed here, we might as well return and have a leak
+		 * rather than continue and a bugchk
+		 */
+		if (ret != 0) {
+			netdev_err(ndev,
+				   "unable to teardown receive buffer's gpadl\n");
+			return;
+		}
+		net_device->recv_buf_gpadl_handle = 0;
+	}
+}
+
+static void netvsc_teardown_send_gpadl(struct hv_device *device,
+				       struct netvsc_device *net_device)
+{
+	struct net_device *ndev = hv_get_drvdata(device);
+	int ret;
+
 	if (net_device->send_buf_gpadl_handle) {
 		ret = vmbus_teardown_gpadl(device->channel,
 					   net_device->send_buf_gpadl_handle);
@@ -225,12 +244,6 @@ static void netvsc_destroy_buf(struct hv_device *device)
 		}
 		net_device->send_buf_gpadl_handle = 0;
 	}
-	if (net_device->send_buf) {
-		/* Free up the send buffer */
-		vfree(net_device->send_buf);
-		net_device->send_buf = NULL;
-	}
-	kfree(net_device->send_section_map);
 }
 
 int netvsc_alloc_recv_comp_ring(struct netvsc_device *net_device, u32 q_idx)
@@ -425,7 +438,10 @@ static int netvsc_init_buf(struct hv_device *device,
 	goto exit;
 
 cleanup:
-	netvsc_destroy_buf(device);
+	netvsc_revoke_recv_buf(device, net_device);
+	netvsc_revoke_send_buf(device, net_device);
+	netvsc_teardown_recv_gpadl(device, net_device);
+	netvsc_teardown_send_gpadl(device, net_device);
 
 exit:
 	return ret;
@@ -544,11 +560,6 @@ cleanup:
 	return ret;
 }
 
-static void netvsc_disconnect_vsp(struct hv_device *device)
-{
-	netvsc_destroy_buf(device);
-}
-
 /*
  * netvsc_device_remove - Callback when the root bus device is removed
  */
@@ -560,12 +571,24 @@ void netvsc_device_remove(struct hv_device *device)
 		= rtnl_dereference(net_device_ctx->nvdev);
 	int i;
 
-	cancel_work_sync(&net_device->subchan_work);
+	/*
+	 * Revoke receive buffer. If host is pre-Win2016 then tear down
+	 * receive buffer GPADL. Do the same for send buffer.
+	 */
+	netvsc_revoke_recv_buf(device, net_device);
+	if (vmbus_proto_version < VERSION_WIN10)
+		netvsc_teardown_recv_gpadl(device, net_device);
 
-	netvsc_disconnect_vsp(device);
+	netvsc_revoke_send_buf(device, net_device);
+	if (vmbus_proto_version < VERSION_WIN10)
+		netvsc_teardown_send_gpadl(device, net_device);
 
 	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
 
+	/* And disassociate NAPI context from device */
+	for (i = 0; i < net_device->num_chn; i++)
+		netif_napi_del(&net_device->chan_table[i].napi);
+
 	/*
 	 * At this point, no one should be accessing net_device
 	 * except in here
@@ -575,9 +598,14 @@ void netvsc_device_remove(struct hv_device *device)
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
-	/* And dissassociate NAPI context from device */
-	for (i = 0; i < net_device->num_chn; i++)
-		netif_napi_del(&net_device->chan_table[i].napi);
+	/*
+	 * If host is Win2016 or higher then we do the GPADL tear down
+	 * here after VMBus is closed.
+	*/
+	if (vmbus_proto_version >= VERSION_WIN10) {
+		netvsc_teardown_recv_gpadl(device, net_device);
+		netvsc_teardown_send_gpadl(device, net_device);
+	}
 
 	/* Release all resources */
 	free_netvsc_device_rcu(net_device);
@@ -643,13 +671,18 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 	queue_sends =
 		atomic_dec_return(&net_device->chan_table[q_idx].queue_sends);
 
-	if (net_device->destroy && queue_sends == 0)
-		wake_up(&net_device->wait_drain);
+	if (unlikely(net_device->destroy)) {
+		if (queue_sends == 0)
+			wake_up(&net_device->wait_drain);
+	} else {
+		struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx);
 
-	if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) &&
-	    (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER ||
-	     queue_sends < 1))
-		netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx));
+		if (netif_tx_queue_stopped(txq) &&
+		    (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER ||
+		     queue_sends < 1)) {
+			netif_tx_wake_queue(txq);
+		}
+	}
 }
 
 static void netvsc_send_completion(struct netvsc_device *net_device,
@@ -697,13 +730,13 @@ static u32 netvsc_get_next_send_section(struct netvsc_device *net_device)
 	return NETVSC_INVALID_INDEX;
 }
 
-static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
-				   unsigned int section_index,
-				   u32 pend_size,
-				   struct hv_netvsc_packet *packet,
-				   struct rndis_message *rndis_msg,
-				   struct hv_page_buffer *pb,
-				   struct sk_buff *skb)
+static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
+				    unsigned int section_index,
+				    u32 pend_size,
+				    struct hv_netvsc_packet *packet,
+				    struct rndis_message *rndis_msg,
+				    struct hv_page_buffer *pb,
+				    bool xmit_more)
 {
 	char *start = net_device->send_buf;
 	char *dest = start + (section_index * net_device->send_section_size)
@@ -716,7 +749,8 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		packet->page_buf_cnt;
 
 	/* Add padding */
-	if (skb->xmit_more && remain && !packet->cp_partial) {
+	remain = packet->total_data_buflen & (net_device->pkt_align - 1);
+	if (xmit_more && remain) {
 		padding = net_device->pkt_align - remain;
 		rndis_msg->msg_len += padding;
 		packet->total_data_buflen += padding;
@@ -736,8 +770,6 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		memset(dest, 0, padding);
 		msg_size += padding;
 	}
-
-	return msg_size;
 }
 
 static inline int netvsc_send_pkt(
@@ -825,12 +857,13 @@ static inline void move_pkt_msd(struct hv_netvsc_packet **msd_send,
 }
 
 /* RCU already held by caller */
-int netvsc_send(struct net_device_context *ndev_ctx,
+int netvsc_send(struct net_device *ndev,
 		struct hv_netvsc_packet *packet,
 		struct rndis_message *rndis_msg,
 		struct hv_page_buffer *pb,
 		struct sk_buff *skb)
 {
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	struct netvsc_device *net_device
 		= rcu_dereference_bh(ndev_ctx->nvdev);
 	struct hv_device *device = ndev_ctx->device_ctx;
@@ -841,20 +874,12 @@ int netvsc_send(struct net_device_context *ndev_ctx,
 	struct multi_send_data *msdp;
 	struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL;
 	struct sk_buff *msd_skb = NULL;
-	bool try_batch;
-	bool xmit_more = (skb != NULL) ? skb->xmit_more : false;
+	bool try_batch, xmit_more;
 
 	/* If device is rescinded, return error and packet will get dropped. */
 	if (unlikely(!net_device || net_device->destroy))
 		return -ENODEV;
 
-	/* We may race with netvsc_connect_vsp()/netvsc_init_buf() and get
-	 * here before the negotiation with the host is finished and
-	 * send_section_map may not be allocated yet.
-	 */
-	if (unlikely(!net_device->send_section_map))
-		return -EAGAIN;
-
 	nvchan = &net_device->chan_table[packet->q_idx];
 	packet->send_buf_index = NETVSC_INVALID_INDEX;
 	packet->cp_partial = false;
@@ -862,10 +887,8 @@ int netvsc_send(struct net_device_context *ndev_ctx,
 	/* Send control message directly without accessing msd (Multi-Send
 	 * Data) field which may be changed during data packet processing.
 	 */
-	if (!skb) {
-		cur_send = packet;
-		goto send_now;
-	}
+	if (!skb)
+		return netvsc_send_pkt(device, packet, net_device, pb, skb);
 
 	/* batch packets in send buffer if possible */
 	msdp = &nvchan->msd;
@@ -893,10 +916,17 @@ int netvsc_send(struct net_device_context *ndev_ctx,
 		}
 	}
 
+	/* Keep aggregating only if stack says more data is coming
+	 * and not doing mixed modes send and not flow blocked
+	 */
+	xmit_more = skb->xmit_more &&
+		!packet->cp_partial &&
+		!netif_xmit_stopped(netdev_get_tx_queue(ndev, packet->q_idx));
+
 	if (section_index != NETVSC_INVALID_INDEX) {
 		netvsc_copy_to_send_buf(net_device,
 					section_index, msd_len,
-					packet, rndis_msg, pb, skb);
+					packet, rndis_msg, pb, xmit_more);
 
 		packet->send_buf_index = section_index;
 
@@ -916,7 +946,7 @@ int netvsc_send(struct net_device_context *ndev_ctx,
 		if (msdp->skb)
 			dev_consume_skb_any(msdp->skb);
 
-		if (xmit_more && !packet->cp_partial) {
+		if (xmit_more) {
 			msdp->skb = skb;
 			msdp->pkt = packet;
 			msdp->count++;
@@ -942,7 +972,6 @@ int netvsc_send(struct net_device_context *ndev_ctx,
 		}
 	}
 
-send_now:
 	if (cur_send)
 		ret = netvsc_send_pkt(device, cur_send, net_device, pb, skb);
 
@@ -1107,7 +1136,7 @@ static void netvsc_send_table(struct hv_device *hdev,
 		      nvmsg->msg.v5_msg.send_table.offset);
 
 	for (i = 0; i < count; i++)
-		net_device_ctx->tx_send_table[i] = tab[i];
+		net_device_ctx->tx_table[i] = tab[i];
 }
 
 static void netvsc_send_vf(struct net_device_context *net_device_ctx,
@@ -1206,9 +1235,10 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 	if (send_recv_completions(ndev, net_device, nvchan) == 0 &&
 	    work_done < budget &&
 	    napi_complete_done(napi, work_done) &&
-	    hv_end_read(&channel->inbound)) {
+	    hv_end_read(&channel->inbound) &&
+	    napi_schedule_prep(napi)) {
 		hv_begin_read(&channel->inbound);
-		napi_reschedule(napi);
+		__napi_schedule(napi);
 	}
 
 	/* Driver may overshoot since multiple packets per descriptor */
@@ -1231,7 +1261,7 @@ void netvsc_channel_cb(void *context)
 		/* disable interupts from host */
 		hv_begin_read(rbi);
 
-		__napi_schedule(&nvchan->napi);
+		__napi_schedule_irqoff(&nvchan->napi);
 	}
 }
 
@@ -1252,6 +1282,9 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 	if (!net_device)
 		return ERR_PTR(-ENOMEM);
 
+	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
+		net_device_ctx->tx_table[i] = 0;
+
 	net_device->ring_size = ring_size;
 
 	/* Because the device uses NAPI, all the interrupt batching and
@@ -1286,7 +1319,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 			 net_device->chan_table);
 
 	if (ret != 0) {
-		netif_napi_del(&net_device->chan_table[0].napi);
 		netdev_err(ndev, "unable to open channel: %d\n", ret);
 		goto cleanup;
 	}
@@ -1296,11 +1328,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 
 	napi_enable(&net_device->chan_table[0].napi);
 
-	/* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is
-	 * populated.
-	 */
-	rcu_assign_pointer(net_device_ctx->nvdev, net_device);
-
 	/* Connect with the NetVsp */
 	ret = netvsc_connect_vsp(device, net_device, device_info);
 	if (ret != 0) {
@@ -1309,6 +1336,11 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 		goto close;
 	}
 
+	/* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is
+	 * populated.
+	 */
+	rcu_assign_pointer(net_device_ctx->nvdev, net_device);
+
 	return net_device;
 
 close:
@@ -1319,6 +1351,7 @@ close:
 	vmbus_close(device->channel);
 
 cleanup:
+	netif_napi_del(&net_device->chan_table[0].napi);
 	free_netvsc_device(&net_device->rcu);
 
 	return ERR_PTR(ret);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c849de3cb046..3a7241c8713c 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -45,7 +45,10 @@
 
 #include "hyperv_net.h"
 
-#define RING_SIZE_MIN		64
+#define RING_SIZE_MIN	64
+#define RETRY_US_LO	5000
+#define RETRY_US_HI	10000
+#define RETRY_MAX	2000	/* >10 sec */
 
 #define LINKCHANGE_INT (2 * HZ)
 #define VF_TAKEOVER_INT (HZ / 10)
@@ -63,12 +66,43 @@ static int debug = -1;
 module_param(debug, int, S_IRUGO);
 MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
 
-static void netvsc_set_multicast_list(struct net_device *net)
+static void netvsc_change_rx_flags(struct net_device *net, int change)
 {
-	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
+	struct net_device_context *ndev_ctx = netdev_priv(net);
+	struct net_device *vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
+	int inc;
+
+	if (!vf_netdev)
+		return;
+
+	if (change & IFF_PROMISC) {
+		inc = (net->flags & IFF_PROMISC) ? 1 : -1;
+		dev_set_promiscuity(vf_netdev, inc);
+	}
+
+	if (change & IFF_ALLMULTI) {
+		inc = (net->flags & IFF_ALLMULTI) ? 1 : -1;
+		dev_set_allmulti(vf_netdev, inc);
+	}
+}
 
-	rndis_filter_update(nvdev);
+static void netvsc_set_rx_mode(struct net_device *net)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(net);
+	struct net_device *vf_netdev;
+	struct netvsc_device *nvdev;
+
+	rcu_read_lock();
+	vf_netdev = rcu_dereference(ndev_ctx->vf_netdev);
+	if (vf_netdev) {
+		dev_uc_sync(vf_netdev, net);
+		dev_mc_sync(vf_netdev, net);
+	}
+
+	nvdev = rcu_dereference(ndev_ctx->nvdev);
+	if (nvdev)
+		rndis_filter_update(nvdev);
+	rcu_read_unlock();
 }
 
 static int netvsc_open(struct net_device *net)
@@ -88,10 +122,7 @@ static int netvsc_open(struct net_device *net)
 		return ret;
 	}
 
-	netif_tx_wake_all_queues(net);
-
 	rdev = nvdev->extension;
-
 	if (!rdev->link_state)
 		netif_carrier_on(net);
 
@@ -109,36 +140,25 @@ static int netvsc_open(struct net_device *net)
 	return 0;
 }
 
-static int netvsc_close(struct net_device *net)
+static int netvsc_wait_until_empty(struct netvsc_device *nvdev)
 {
-	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct net_device *vf_netdev
-		= rtnl_dereference(net_device_ctx->vf_netdev);
-	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
-	int ret = 0;
-	u32 aread, i, msec = 10, retry = 0, retry_max = 20;
-	struct vmbus_channel *chn;
-
-	netif_tx_disable(net);
-
-	/* No need to close rndis filter if it is removed already */
-	if (!nvdev)
-		goto out;
-
-	ret = rndis_filter_close(nvdev);
-	if (ret != 0) {
-		netdev_err(net, "unable to close device (ret %d).\n", ret);
-		return ret;
-	}
+	unsigned int retry = 0;
+	int i;
 
 	/* Ensure pending bytes in ring are read */
-	while (true) {
-		aread = 0;
+	for (;;) {
+		u32 aread = 0;
+
 		for (i = 0; i < nvdev->num_chn; i++) {
-			chn = nvdev->chan_table[i].channel;
+			struct vmbus_channel *chn
+				= nvdev->chan_table[i].channel;
+
 			if (!chn)
 				continue;
 
+			/* make sure receive not running now */
+			napi_synchronize(&nvdev->chan_table[i].napi);
+
 			aread = hv_get_bytes_to_read(&chn->inbound);
 			if (aread)
 				break;
@@ -148,22 +168,40 @@ static int netvsc_close(struct net_device *net)
 				break;
 		}
 
-		retry++;
-		if (retry > retry_max || aread == 0)
-			break;
+		if (aread == 0)
+			return 0;
 
-		msleep(msec);
+		if (++retry > RETRY_MAX)
+			return -ETIMEDOUT;
 
-		if (msec < 1000)
-			msec *= 2;
+		usleep_range(RETRY_US_LO, RETRY_US_HI);
 	}
+}
 
-	if (aread) {
-		netdev_err(net, "Ring buffer not empty after closing rndis\n");
-		ret = -ETIMEDOUT;
+static int netvsc_close(struct net_device *net)
+{
+	struct net_device_context *net_device_ctx = netdev_priv(net);
+	struct net_device *vf_netdev
+		= rtnl_dereference(net_device_ctx->vf_netdev);
+	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
+	int ret;
+
+	netif_tx_disable(net);
+
+	/* No need to close rndis filter if it is removed already */
+	if (!nvdev)
+		return 0;
+
+	ret = rndis_filter_close(nvdev);
+	if (ret != 0) {
+		netdev_err(net, "unable to close device (ret %d).\n", ret);
+		return ret;
 	}
 
-out:
+	ret = netvsc_wait_until_empty(nvdev);
+	if (ret)
+		netdev_err(net, "Ring buffer not empty after closing rndis\n");
+
 	if (vf_netdev)
 		dev_close(vf_netdev);
 
@@ -234,8 +272,8 @@ static inline int netvsc_get_tx_queue(struct net_device *ndev,
 	struct sock *sk = skb->sk;
 	int q_idx;
 
-	q_idx = ndc->tx_send_table[netvsc_get_hash(skb, ndc) &
-				   (VRSS_SEND_TAB_SIZE - 1)];
+	q_idx = ndc->tx_table[netvsc_get_hash(skb, ndc) &
+			      (VRSS_SEND_TAB_SIZE - 1)];
 
 	/* If queue index changed record the new value */
 	if (q_idx != old_idx &&
@@ -284,8 +322,19 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	rcu_read_lock();
 	vf_netdev = rcu_dereference(ndc->vf_netdev);
 	if (vf_netdev) {
-		txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0;
-		qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
+		const struct net_device_ops *vf_ops = vf_netdev->netdev_ops;
+
+		if (vf_ops->ndo_select_queue)
+			txq = vf_ops->ndo_select_queue(vf_netdev, skb,
+						       accel_priv, fallback);
+		else
+			txq = fallback(vf_netdev, skb);
+
+		/* Record the queue selected by VF so that it can be
+		 * used for common case where VF has more queues than
+		 * the synthetic device.
+		 */
+		qdisc_skb_cb(skb)->slave_dev_queue_mapping = txq;
 	} else {
 		txq = netvsc_pick_tx(ndev, skb);
 	}
@@ -614,7 +663,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
 
-	ret = netvsc_send(net_device_ctx, packet, rndis_msg, pb, skb);
+	ret = netvsc_send(net, packet, rndis_msg, pb, skb);
 	if (likely(ret == 0))
 		return NETDEV_TX_OK;
 
@@ -810,16 +859,81 @@ static void netvsc_get_channels(struct net_device *net,
 	}
 }
 
+static int netvsc_detach(struct net_device *ndev,
+			 struct netvsc_device *nvdev)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct hv_device *hdev = ndev_ctx->device_ctx;
+	int ret;
+
+	/* Don't try continuing to try and setup sub channels */
+	if (cancel_work_sync(&nvdev->subchan_work))
+		nvdev->num_chn = 1;
+
+	/* If device was up (receiving) then shutdown */
+	if (netif_running(ndev)) {
+		netif_tx_disable(ndev);
+
+		ret = rndis_filter_close(nvdev);
+		if (ret) {
+			netdev_err(ndev,
+				   "unable to close device (ret %d).\n", ret);
+			return ret;
+		}
+
+		ret = netvsc_wait_until_empty(nvdev);
+		if (ret) {
+			netdev_err(ndev,
+				   "Ring buffer not empty after closing rndis\n");
+			return ret;
+		}
+	}
+
+	netif_device_detach(ndev);
+
+	rndis_filter_device_remove(hdev, nvdev);
+
+	return 0;
+}
+
+static int netvsc_attach(struct net_device *ndev,
+			 struct netvsc_device_info *dev_info)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct hv_device *hdev = ndev_ctx->device_ctx;
+	struct netvsc_device *nvdev;
+	struct rndis_device *rdev;
+	int ret;
+
+	nvdev = rndis_filter_device_add(hdev, dev_info);
+	if (IS_ERR(nvdev))
+		return PTR_ERR(nvdev);
+
+	/* Note: enable and attach happen when sub-channels setup */
+
+	netif_carrier_off(ndev);
+
+	if (netif_running(ndev)) {
+		ret = rndis_filter_open(nvdev);
+		if (ret)
+			return ret;
+
+		rdev = nvdev->extension;
+		if (!rdev->link_state)
+			netif_carrier_on(ndev);
+	}
+
+	return 0;
+}
+
 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 = rtnl_dereference(net_device_ctx->nvdev);
 	unsigned int orig, count = channels->combined_count;
 	struct netvsc_device_info device_info;
-	bool was_opened;
-	int ret = 0;
+	int ret;
 
 	/* We do not support separate count for rx, tx, or other */
 	if (count == 0 ||
@@ -836,9 +950,6 @@ static int netvsc_set_channels(struct net_device *net,
 		return -EINVAL;
 
 	orig = nvdev->num_chn;
-	was_opened = rndis_filter_opened(nvdev);
-	if (was_opened)
-		rndis_filter_close(nvdev);
 
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.num_chn = count;
@@ -848,28 +959,17 @@ static int netvsc_set_channels(struct net_device *net,
 	device_info.recv_sections = nvdev->recv_section_cnt;
 	device_info.recv_section_size = nvdev->recv_section_size;
 
-	rndis_filter_device_remove(dev, nvdev);
+	ret = netvsc_detach(net, nvdev);
+	if (ret)
+		return ret;
 
-	nvdev = rndis_filter_device_add(dev, &device_info);
-	if (IS_ERR(nvdev)) {
-		ret = PTR_ERR(nvdev);
+	ret = netvsc_attach(net, &device_info);
+	if (ret) {
 		device_info.num_chn = orig;
-		nvdev = rndis_filter_device_add(dev, &device_info);
-
-		if (IS_ERR(nvdev)) {
-			netdev_err(net, "restoring channel setting failed: %ld\n",
-				   PTR_ERR(nvdev));
-			return ret;
-		}
+		if (netvsc_attach(net, &device_info))
+			netdev_err(net, "restoring channel setting failed\n");
 	}
 
-	if (was_opened)
-		rndis_filter_open(nvdev);
-
-	/* We may have missed link change notifications */
-	net_device_ctx->last_reconfig = 0;
-	schedule_delayed_work(&net_device_ctx->dwork, 0);
-
 	return ret;
 }
 
@@ -936,10 +1036,8 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	struct net_device_context *ndevctx = netdev_priv(ndev);
 	struct net_device *vf_netdev = rtnl_dereference(ndevctx->vf_netdev);
 	struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
-	struct hv_device *hdev = ndevctx->device_ctx;
 	int orig_mtu = ndev->mtu;
 	struct netvsc_device_info device_info;
-	bool was_opened;
 	int ret = 0;
 
 	if (!nvdev || nvdev->destroy)
@@ -952,11 +1050,6 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 			return ret;
 	}
 
-	netif_device_detach(ndev);
-	was_opened = rndis_filter_opened(nvdev);
-	if (was_opened)
-		rndis_filter_close(nvdev);
-
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
 	device_info.num_chn = nvdev->num_chn;
@@ -965,35 +1058,27 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	device_info.recv_sections = nvdev->recv_section_cnt;
 	device_info.recv_section_size = nvdev->recv_section_size;
 
-	rndis_filter_device_remove(hdev, nvdev);
+	ret = netvsc_detach(ndev, nvdev);
+	if (ret)
+		goto rollback_vf;
 
 	ndev->mtu = mtu;
 
-	nvdev = rndis_filter_device_add(hdev, &device_info);
-	if (IS_ERR(nvdev)) {
-		ret = PTR_ERR(nvdev);
-
-		/* Attempt rollback to original MTU */
-		ndev->mtu = orig_mtu;
-		nvdev = rndis_filter_device_add(hdev, &device_info);
-
-		if (vf_netdev)
-			dev_set_mtu(vf_netdev, orig_mtu);
-
-		if (IS_ERR(nvdev)) {
-			netdev_err(ndev, "restoring mtu failed: %ld\n",
-				   PTR_ERR(nvdev));
-			return ret;
-		}
-	}
+	ret = netvsc_attach(ndev, &device_info);
+	if (ret)
+		goto rollback;
 
-	if (was_opened)
-		rndis_filter_open(nvdev);
+	return 0;
 
-	netif_device_attach(ndev);
+rollback:
+	/* Attempt rollback to original MTU */
+	ndev->mtu = orig_mtu;
 
-	/* We may have missed link change notifications */
-	schedule_delayed_work(&ndevctx->dwork, 0);
+	if (netvsc_attach(ndev, &device_info))
+		netdev_err(ndev, "restoring mtu failed\n");
+rollback_vf:
+	if (vf_netdev)
+		dev_set_mtu(vf_netdev, orig_mtu);
 
 	return ret;
 }
@@ -1378,7 +1463,7 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	rndis_dev = ndev->extension;
 	if (indir) {
 		for (i = 0; i < ITAB_NUM; i++)
-			indir[i] = rndis_dev->ind_table[i];
+			indir[i] = rndis_dev->rx_table[i];
 	}
 
 	if (key)
@@ -1408,7 +1493,7 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
 				return -EINVAL;
 
 		for (i = 0; i < ITAB_NUM; i++)
-			rndis_dev->ind_table[i] = indir[i];
+			rndis_dev->rx_table[i] = indir[i];
 	}
 
 	if (!key) {
@@ -1459,11 +1544,9 @@ static int netvsc_set_ringparam(struct net_device *ndev,
 {
 	struct net_device_context *ndevctx = netdev_priv(ndev);
 	struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
-	struct hv_device *hdev = ndevctx->device_ctx;
 	struct netvsc_device_info device_info;
 	struct ethtool_ringparam orig;
 	u32 new_tx, new_rx;
-	bool was_opened;
 	int ret = 0;
 
 	if (!nvdev || nvdev->destroy)
@@ -1489,34 +1572,18 @@ static int netvsc_set_ringparam(struct net_device *ndev,
 	device_info.recv_sections = new_rx;
 	device_info.recv_section_size = nvdev->recv_section_size;
 
-	netif_device_detach(ndev);
-	was_opened = rndis_filter_opened(nvdev);
-	if (was_opened)
-		rndis_filter_close(nvdev);
-
-	rndis_filter_device_remove(hdev, nvdev);
-
-	nvdev = rndis_filter_device_add(hdev, &device_info);
-	if (IS_ERR(nvdev)) {
-		ret = PTR_ERR(nvdev);
+	ret = netvsc_detach(ndev, nvdev);
+	if (ret)
+		return ret;
 
+	ret = netvsc_attach(ndev, &device_info);
+	if (ret) {
 		device_info.send_sections = orig.tx_pending;
 		device_info.recv_sections = orig.rx_pending;
-		nvdev = rndis_filter_device_add(hdev, &device_info);
-		if (IS_ERR(nvdev)) {
-			netdev_err(ndev, "restoring ringparam failed: %ld\n",
-				   PTR_ERR(nvdev));
-			return ret;
-		}
-	}
 
-	if (was_opened)
-		rndis_filter_open(nvdev);
-	netif_device_attach(ndev);
-
-	/* We may have missed link change notifications */
-	ndevctx->last_reconfig = 0;
-	schedule_delayed_work(&ndevctx->dwork, 0);
+		if (netvsc_attach(ndev, &device_info))
+			netdev_err(ndev, "restoring ringparam failed");
+	}
 
 	return ret;
 }
@@ -1546,7 +1613,8 @@ static const struct net_device_ops device_ops = {
 	.ndo_open =			netvsc_open,
 	.ndo_stop =			netvsc_close,
 	.ndo_start_xmit =		netvsc_start_xmit,
-	.ndo_set_rx_mode =		netvsc_set_multicast_list,
+	.ndo_change_rx_flags =		netvsc_change_rx_flags,
+	.ndo_set_rx_mode =		netvsc_set_rx_mode,
 	.ndo_change_mtu =		netvsc_change_mtu,
 	.ndo_validate_addr =		eth_validate_addr,
 	.ndo_set_mac_address =		netvsc_set_mac_addr,
@@ -1742,7 +1810,8 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto rx_handler_failed;
 	}
 
-	ret = netdev_upper_dev_link(vf_netdev, ndev);
+	ret = netdev_master_upper_dev_link(vf_netdev, ndev,
+					   NULL, NULL);
 	if (ret != 0) {
 		netdev_err(vf_netdev,
 			   "can not set master device %s (err = %d)\n",
@@ -1777,6 +1846,15 @@ static void __netvsc_vf_setup(struct net_device *ndev,
 		netdev_warn(vf_netdev,
 			    "unable to change mtu to %u\n", ndev->mtu);
 
+	/* set multicast etc flags on VF */
+	dev_change_flags(vf_netdev, ndev->flags | IFF_SLAVE);
+
+	/* sync address list from ndev to VF */
+	netif_addr_lock_bh(ndev);
+	dev_uc_sync(vf_netdev, ndev);
+	dev_mc_sync(vf_netdev, ndev);
+	netif_addr_unlock_bh(ndev);
+
 	if (netif_running(ndev)) {
 		ret = dev_open(vf_netdev);
 		if (ret)
@@ -1931,6 +2009,12 @@ static int netvsc_probe(struct hv_device *dev,
 	/* We always need headroom for rndis header */
 	net->needed_headroom = RNDIS_AND_PPI_SIZE;
 
+	/* Initialize the number of queues to be 1, we may change it if more
+	 * channels are offered later.
+	 */
+	netif_set_real_num_tx_queues(net, 1);
+	netif_set_real_num_rx_queues(net, 1);
+
 	/* Notify the netvsc driver of the new device */
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
@@ -1949,7 +2033,7 @@ static int netvsc_probe(struct hv_device *dev,
 
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
-	/* hw_features computed in rndis_filter_device_add */
+	/* hw_features computed in rndis_netdev_set_hwcaps() */
 	net->features = net->hw_features |
 		NETIF_F_HIGHDMA | NETIF_F_SG |
 		NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
@@ -1986,8 +2070,8 @@ no_net:
 static int netvsc_remove(struct hv_device *dev)
 {
 	struct net_device_context *ndev_ctx;
-	struct net_device *vf_netdev;
-	struct net_device *net;
+	struct net_device *vf_netdev, *net;
+	struct netvsc_device *nvdev;
 
 	net = hv_get_drvdata(dev);
 	if (net == NULL) {
@@ -1997,10 +2081,14 @@ static int netvsc_remove(struct hv_device *dev)
 
 	ndev_ctx = netdev_priv(net);
 
-	netif_device_detach(net);
-
 	cancel_delayed_work_sync(&ndev_ctx->dwork);
 
+	rcu_read_lock();
+	nvdev = rcu_dereference(ndev_ctx->nvdev);
+
+	if  (nvdev)
+		cancel_work_sync(&nvdev->subchan_work);
+
 	/*
 	 * Call to the vsc driver to let it know that the device is being
 	 * removed. Also blocks mtu and channel changes.
@@ -2010,11 +2098,13 @@ static int netvsc_remove(struct hv_device *dev)
 	if (vf_netdev)
 		netvsc_unregister_vf(vf_netdev);
 
+	if (nvdev)
+		rndis_filter_device_remove(dev, nvdev);
+
 	unregister_netdevice(net);
 
-	rndis_filter_device_remove(dev,
-				   rtnl_dereference(ndev_ctx->nvdev));
 	rtnl_unlock();
+	rcu_read_unlock();
 
 	hv_set_drvdata(dev, NULL);
 
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 065b204d8e17..d1ae184008b4 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -217,7 +217,6 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 	struct hv_netvsc_packet *packet;
 	struct hv_page_buffer page_buf[2];
 	struct hv_page_buffer *pb = page_buf;
-	struct net_device_context *net_device_ctx = netdev_priv(dev->ndev);
 	int ret;
 
 	/* Setup the packet to send it */
@@ -245,7 +244,7 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 	}
 
 	rcu_read_lock_bh();
-	ret = netvsc_send(net_device_ctx, packet, NULL, pb, NULL);
+	ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL);
 	rcu_read_unlock_bh();
 
 	return ret;
@@ -267,13 +266,23 @@ static void rndis_set_link_state(struct rndis_device *rdev,
 	}
 }
 
-static void rndis_filter_receive_response(struct rndis_device *dev,
-				       struct rndis_message *resp)
+static void rndis_filter_receive_response(struct net_device *ndev,
+					  struct netvsc_device *nvdev,
+					  const struct rndis_message *resp)
 {
+	struct rndis_device *dev = nvdev->extension;
 	struct rndis_request *request = NULL;
 	bool found = false;
 	unsigned long flags;
-	struct net_device *ndev = dev->ndev;
+
+	/* This should never happen, it means control message
+	 * response received after device removed.
+	 */
+	if (dev->state == RNDIS_DEV_UNINITIALIZED) {
+		netdev_err(ndev,
+			   "got rndis message uninitialized\n");
+		return;
+	}
 
 	spin_lock_irqsave(&dev->request_lock, flags);
 	list_for_each_entry(request, &dev->req_list, list_ent) {
@@ -354,7 +363,7 @@ static inline void *rndis_get_ppi(struct rndis_packet *rpkt, u32 type)
 }
 
 static int rndis_filter_receive_data(struct net_device *ndev,
-				     struct rndis_device *dev,
+				     struct netvsc_device *nvdev,
 				     struct rndis_message *msg,
 				     struct vmbus_channel *channel,
 				     void *data, u32 data_buflen)
@@ -374,7 +383,7 @@ static int rndis_filter_receive_data(struct net_device *ndev,
 	 * should be the data packet size plus the trailer padding size
 	 */
 	if (unlikely(data_buflen < rndis_pkt->data_len)) {
-		netdev_err(dev->ndev, "rndis message buffer "
+		netdev_err(ndev, "rndis message buffer "
 			   "overflow detected (got %u, min %u)"
 			   "...dropping this message!\n",
 			   data_buflen, rndis_pkt->data_len);
@@ -402,34 +411,20 @@ int rndis_filter_receive(struct net_device *ndev,
 			 void *data, u32 buflen)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct rndis_device *rndis_dev = net_dev->extension;
 	struct rndis_message *rndis_msg = data;
 
-	/* Make sure the rndis device state is initialized */
-	if (unlikely(!rndis_dev)) {
-		netif_err(net_device_ctx, rx_err, ndev,
-			  "got rndis message but no rndis device!\n");
-		return NVSP_STAT_FAIL;
-	}
-
-	if (unlikely(rndis_dev->state == RNDIS_DEV_UNINITIALIZED)) {
-		netif_err(net_device_ctx, rx_err, ndev,
-			  "got rndis message uninitialized\n");
-		return NVSP_STAT_FAIL;
-	}
-
 	if (netif_msg_rx_status(net_device_ctx))
 		dump_rndis_message(dev, rndis_msg);
 
 	switch (rndis_msg->ndis_msg_type) {
 	case RNDIS_MSG_PACKET:
-		return rndis_filter_receive_data(ndev, rndis_dev, rndis_msg,
+		return rndis_filter_receive_data(ndev, net_dev, rndis_msg,
 						 channel, data, buflen);
 	case RNDIS_MSG_INIT_C:
 	case RNDIS_MSG_QUERY_C:
 	case RNDIS_MSG_SET_C:
 		/* completion msgs */
-		rndis_filter_receive_response(rndis_dev, rndis_msg);
+		rndis_filter_receive_response(ndev, net_dev, rndis_msg);
 		break;
 
 	case RNDIS_MSG_INDICATE:
@@ -759,7 +754,7 @@ int rndis_filter_set_rss_param(struct rndis_device *rdev,
 	/* Set indirection table entries */
 	itab = (u32 *)(rssp + 1);
 	for (i = 0; i < ITAB_NUM; i++)
-		itab[i] = rdev->ind_table[i];
+		itab[i] = rdev->rx_table[i];
 
 	/* Set hask key values */
 	keyp = (u8 *)((unsigned long)rssp + rssp->kashkey_offset);
@@ -855,15 +850,19 @@ static void rndis_set_multicast(struct work_struct *w)
 {
 	struct rndis_device *rdev
 		= container_of(w, struct rndis_device, mcast_work);
+	u32 filter = NDIS_PACKET_TYPE_DIRECTED;
+	unsigned int flags = rdev->ndev->flags;
 
-	if (rdev->ndev->flags & IFF_PROMISC)
-		rndis_filter_set_packet_filter(rdev,
-					       NDIS_PACKET_TYPE_PROMISCUOUS);
-	else
-		rndis_filter_set_packet_filter(rdev,
-					       NDIS_PACKET_TYPE_BROADCAST |
-					       NDIS_PACKET_TYPE_ALL_MULTICAST |
-					       NDIS_PACKET_TYPE_DIRECTED);
+	if (flags & IFF_PROMISC) {
+		filter = NDIS_PACKET_TYPE_PROMISCUOUS;
+	} else {
+		if (!netdev_mc_empty(rdev->ndev) || (flags & IFF_ALLMULTI))
+			filter |= NDIS_PACKET_TYPE_ALL_MULTICAST;
+		if (flags & IFF_BROADCAST)
+			filter |= NDIS_PACKET_TYPE_BROADCAST;
+	}
+
+	rndis_filter_set_packet_filter(rdev, filter);
 }
 
 void rndis_filter_update(struct netvsc_device *nvdev)
@@ -1114,6 +1113,10 @@ void rndis_set_subchannel(struct work_struct *w)
 	netif_set_real_num_tx_queues(ndev, nvdev->num_chn);
 	netif_set_real_num_rx_queues(ndev, nvdev->num_chn);
 
+	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
+		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
+
+	netif_device_attach(ndev);
 	rtnl_unlock();
 	return;
 
@@ -1124,73 +1127,26 @@ failed:
 
 	nvdev->max_chn = 1;
 	nvdev->num_chn = 1;
+
+	netif_device_attach(ndev);
 unlock:
 	rtnl_unlock();
 }
 
-struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
-				      struct netvsc_device_info *device_info)
+static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
+				   struct netvsc_device *nvdev)
 {
-	struct net_device *net = hv_get_drvdata(dev);
+	struct net_device *net = rndis_device->ndev;
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct netvsc_device *net_device;
-	struct rndis_device *rndis_device;
 	struct ndis_offload hwcaps;
 	struct ndis_offload_params offloads;
-	struct ndis_recv_scale_cap rsscap;
-	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	unsigned int gso_max_size = GSO_MAX_SIZE;
-	u32 mtu, size;
-	const struct cpumask *node_cpu_mask;
-	u32 num_possible_rss_qs;
-	int i, ret;
-
-	rndis_device = get_rndis_device();
-	if (!rndis_device)
-		return ERR_PTR(-ENODEV);
-
-	/*
-	 * Let the inner driver handle this first to create the netvsc channel
-	 * NOTE! Once the channel is created, we may get a receive callback
-	 * (RndisFilterOnReceive()) before this call is completed
-	 */
-	net_device = netvsc_device_add(dev, device_info);
-	if (IS_ERR(net_device)) {
-		kfree(rndis_device);
-		return net_device;
-	}
-
-	/* Initialize the rndis device */
-	net_device->max_chn = 1;
-	net_device->num_chn = 1;
-
-	net_device->extension = rndis_device;
-	rndis_device->ndev = net;
-
-	/* Send the rndis initialization message */
-	ret = rndis_filter_init_device(rndis_device, net_device);
-	if (ret != 0)
-		goto err_dev_remv;
-
-	/* Get the MTU from the host */
-	size = sizeof(u32);
-	ret = rndis_filter_query_device(rndis_device, net_device,
-					RNDIS_OID_GEN_MAXIMUM_FRAME_SIZE,
-					&mtu, &size);
-	if (ret == 0 && size == sizeof(u32) && mtu < net->mtu)
-		net->mtu = mtu;
-
-	/* Get the mac address */
-	ret = rndis_filter_query_device_mac(rndis_device, net_device);
-	if (ret != 0)
-		goto err_dev_remv;
-
-	memcpy(device_info->mac_adr, rndis_device->hw_mac_adr, ETH_ALEN);
+	int ret;
 
 	/* Find HW offload capabilities */
-	ret = rndis_query_hwcaps(rndis_device, net_device, &hwcaps);
+	ret = rndis_query_hwcaps(rndis_device, nvdev, &hwcaps);
 	if (ret != 0)
-		goto err_dev_remv;
+		return ret;
 
 	/* A value of zero means "no change"; now turn on what we want. */
 	memset(&offloads, 0, sizeof(struct ndis_offload_params));
@@ -1198,8 +1154,12 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 	/* Linux does not care about IP checksum, always does in kernel */
 	offloads.ip_v4_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_DISABLED;
 
+	/* Reset previously set hw_features flags */
+	net->hw_features &= ~NETVSC_SUPPORTED_HW_FEATURES;
+	net_device_ctx->tx_checksum_mask = 0;
+
 	/* Compute tx offload settings based on hw capabilities */
-	net->hw_features = NETIF_F_RXCSUM;
+	net->hw_features |= NETIF_F_RXCSUM;
 
 	if ((hwcaps.csum.ip4_txcsum & NDIS_TXCSUM_ALL_TCP4) == NDIS_TXCSUM_ALL_TCP4) {
 		/* Can checksum TCP */
@@ -1243,10 +1203,74 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 		}
 	}
 
+	/* In case some hw_features disappeared we need to remove them from
+	 * net->features list as they're no longer supported.
+	 */
+	net->features &= ~NETVSC_SUPPORTED_HW_FEATURES | net->hw_features;
+
 	netif_set_gso_max_size(net, gso_max_size);
 
-	ret = rndis_filter_set_offload_params(net, net_device, &offloads);
-	if (ret)
+	ret = rndis_filter_set_offload_params(net, nvdev, &offloads);
+
+	return ret;
+}
+
+struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
+				      struct netvsc_device_info *device_info)
+{
+	struct net_device *net = hv_get_drvdata(dev);
+	struct netvsc_device *net_device;
+	struct rndis_device *rndis_device;
+	struct ndis_recv_scale_cap rsscap;
+	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
+	u32 mtu, size;
+	u32 num_possible_rss_qs;
+	int i, ret;
+
+	rndis_device = get_rndis_device();
+	if (!rndis_device)
+		return ERR_PTR(-ENODEV);
+
+	/* Let the inner driver handle this first to create the netvsc channel
+	 * NOTE! Once the channel is created, we may get a receive callback
+	 * (RndisFilterOnReceive()) before this call is completed
+	 */
+	net_device = netvsc_device_add(dev, device_info);
+	if (IS_ERR(net_device)) {
+		kfree(rndis_device);
+		return net_device;
+	}
+
+	/* Initialize the rndis device */
+	net_device->max_chn = 1;
+	net_device->num_chn = 1;
+
+	net_device->extension = rndis_device;
+	rndis_device->ndev = net;
+
+	/* Send the rndis initialization message */
+	ret = rndis_filter_init_device(rndis_device, net_device);
+	if (ret != 0)
+		goto err_dev_remv;
+
+	/* Get the MTU from the host */
+	size = sizeof(u32);
+	ret = rndis_filter_query_device(rndis_device, net_device,
+					RNDIS_OID_GEN_MAXIMUM_FRAME_SIZE,
+					&mtu, &size);
+	if (ret == 0 && size == sizeof(u32) && mtu < net->mtu)
+		net->mtu = mtu;
+
+	/* Get the mac address */
+	ret = rndis_filter_query_device_mac(rndis_device, net_device);
+	if (ret != 0)
+		goto err_dev_remv;
+
+	memcpy(device_info->mac_adr, rndis_device->hw_mac_adr, ETH_ALEN);
+
+	/* Query and set hardware capabilities */
+	ret = rndis_netdev_set_hwcaps(rndis_device, net_device);
+	if (ret != 0)
 		goto err_dev_remv;
 
 	rndis_filter_query_device_link_status(rndis_device, net_device);
@@ -1256,7 +1280,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 		   rndis_device->link_state ? "down" : "up");
 
 	if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_5)
-		return net_device;
+		goto out;
 
 	rndis_filter_query_link_speed(rndis_device, net_device);
 
@@ -1268,14 +1292,8 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 	if (ret || rsscap.num_recv_que < 2)
 		goto out;
 
-	/*
-	 * We will limit the VRSS channels to the number CPUs in the NUMA node
-	 * the primary channel is currently bound to.
-	 *
-	 * This also guarantees that num_possible_rss_qs <= num_online_cpus
-	 */
-	node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu));
-	num_possible_rss_qs = min_t(u32, cpumask_weight(node_cpu_mask),
+	/* This guarantees that num_possible_rss_qs <= num_online_cpus */
+	num_possible_rss_qs = min_t(u32, num_online_cpus(),
 				    rsscap.num_recv_que);
 
 	net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, num_possible_rss_qs);
@@ -1284,8 +1302,8 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 	net_device->num_chn = min(net_device->max_chn, device_info->num_chn);
 
 	for (i = 0; i < ITAB_NUM; i++)
-		rndis_device->ind_table[i] = ethtool_rxfh_indir_default(i,
-							net_device->num_chn);
+		rndis_device->rx_table[i] = ethtool_rxfh_indir_default(
+						i, net_device->num_chn);
 
 	atomic_set(&net_device->open_chn, 1);
 	vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
@@ -1313,6 +1331,10 @@ out:
 		net_device->num_chn = 1;
 	}
 
+	/* No sub channels, device is ready */
+	if (net_device->num_chn == 1)
+		netif_device_attach(net);
+
 	return net_device;
 
 err_dev_remv:
@@ -1331,7 +1353,6 @@ void rndis_filter_device_remove(struct hv_device *dev,
 	net_dev->extension = NULL;
 
 	netvsc_device_remove(dev);
-	kfree(rndis_dev);
 }
 
 int rndis_filter_open(struct netvsc_device *nvdev)
@@ -1355,8 +1376,3 @@ int rndis_filter_close(struct netvsc_device *nvdev)
 
 	return rndis_filter_close_device(nvdev->extension);
 }
-
-bool rndis_filter_opened(const struct netvsc_device *nvdev)
-{
-	return atomic_read(&nvdev->open_cnt) > 0;
-}