Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.

 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
    Benniston.

 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
    Mork.

 4) BPF now has a "random" opcode, from Chema Gonzalez.

 5) Add more BPF documentation and improve test framework, from Daniel
    Borkmann.

 6) Support TCP fastopen over ipv6, from Daniel Lee.

 7) Add software TSO helper functions and use them to support software
    TSO in mvneta and mv643xx_eth drivers.  From Ezequiel Garcia.

 8) Support software TSO in fec driver too, from Nimrod Andy.

 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.

10) Handle broadcasts more gracefully over macvlan when there are large
    numbers of interfaces configured, from Herbert Xu.

11) Allow more control over fwmark used for non-socket based responses,
    from Lorenzo Colitti.

12) Do TCP congestion window limiting based upon measurements, from Neal
    Cardwell.

13) Support busy polling in SCTP, from Neal Horman.

14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.

15) Bridge promisc mode handling improvements from Vlad Yasevich.

16) Don't use inetpeer entries to implement ID generation any more, it
    performs poorly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
  tcp: fixing TLP's FIN recovery
  net: fec: Add software TSO support
  net: fec: Add Scatter/gather support
  net: fec: Increase buffer descriptor entry number
  net: fec: Factorize feature setting
  net: fec: Enable IP header hardware checksum
  net: fec: Factorize the .xmit transmit function
  bridge: fix compile error when compiling without IPv6 support
  bridge: fix smatch warning / potential null pointer dereference
  via-rhine: fix full-duplex with autoneg disable
  bnx2x: Enlarge the dorq threshold for VFs
  bnx2x: Check for UNDI in uncommon branch
  bnx2x: Fix 1G-baseT link
  bnx2x: Fix link for KR with swapped polarity lane
  sctp: Fix sk_ack_backlog wrap-around problem
  net/core: Add VF link state control policy
  net/fsl: xgmac_mdio is dependent on OF_MDIO
  net/fsl: Make xgmac_mdio read error message useful
  net_sched: drr: warn when qdisc is not work conserving
  ...

4 files changed, 765 insertions, 249 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index d18f711d0b0c..6cc37c15e0bf 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -28,50 +28,119 @@
 #include <linux/hyperv.h>
 #include <linux/rndis.h>
 
-/* Fwd declaration */
-struct hv_netvsc_packet;
-struct ndis_tcp_ip_checksum_info;
+/* RSS related */
+#define OID_GEN_RECEIVE_SCALE_CAPABILITIES 0x00010203  /* query only */
+#define OID_GEN_RECEIVE_SCALE_PARAMETERS 0x00010204  /* query and set */
 
-/* Represent the xfer page packet which contains 1 or more netvsc packet */
-struct xferpage_packet {
-	struct list_head list_ent;
-	u32 status;
+#define NDIS_OBJECT_TYPE_RSS_CAPABILITIES 0x88
+#define NDIS_OBJECT_TYPE_RSS_PARAMETERS 0x89
 
-	/* # of netvsc packets this xfer packet contains */
-	u32 count;
+#define NDIS_RECEIVE_SCALE_CAPABILITIES_REVISION_2 2
+#define NDIS_RECEIVE_SCALE_PARAMETERS_REVISION_2 2
+
+struct ndis_obj_header {
+	u8 type;
+	u8 rev;
+	u16 size;
+} __packed;
+
+/* ndis_recv_scale_cap/cap_flag */
+#define NDIS_RSS_CAPS_MESSAGE_SIGNALED_INTERRUPTS 0x01000000
+#define NDIS_RSS_CAPS_CLASSIFICATION_AT_ISR       0x02000000
+#define NDIS_RSS_CAPS_CLASSIFICATION_AT_DPC       0x04000000
+#define NDIS_RSS_CAPS_USING_MSI_X                 0x08000000
+#define NDIS_RSS_CAPS_RSS_AVAILABLE_ON_PORTS      0x10000000
+#define NDIS_RSS_CAPS_SUPPORTS_MSI_X              0x20000000
+#define NDIS_RSS_CAPS_HASH_TYPE_TCP_IPV4          0x00000100
+#define NDIS_RSS_CAPS_HASH_TYPE_TCP_IPV6          0x00000200
+#define NDIS_RSS_CAPS_HASH_TYPE_TCP_IPV6_EX       0x00000400
+
+struct ndis_recv_scale_cap { /* NDIS_RECEIVE_SCALE_CAPABILITIES */
+	struct ndis_obj_header hdr;
+	u32 cap_flag;
+	u32 num_int_msg;
+	u32 num_recv_que;
+	u16 num_indirect_tabent;
+} __packed;
+
+
+/* ndis_recv_scale_param flags */
+#define NDIS_RSS_PARAM_FLAG_BASE_CPU_UNCHANGED     0x0001
+#define NDIS_RSS_PARAM_FLAG_HASH_INFO_UNCHANGED    0x0002
+#define NDIS_RSS_PARAM_FLAG_ITABLE_UNCHANGED       0x0004
+#define NDIS_RSS_PARAM_FLAG_HASH_KEY_UNCHANGED     0x0008
+#define NDIS_RSS_PARAM_FLAG_DISABLE_RSS            0x0010
+
+/* Hash info bits */
+#define NDIS_HASH_FUNC_TOEPLITZ 0x00000001
+#define NDIS_HASH_IPV4          0x00000100
+#define NDIS_HASH_TCP_IPV4      0x00000200
+#define NDIS_HASH_IPV6          0x00000400
+#define NDIS_HASH_IPV6_EX       0x00000800
+#define NDIS_HASH_TCP_IPV6      0x00001000
+#define NDIS_HASH_TCP_IPV6_EX   0x00002000
+
+#define NDIS_RSS_INDIRECTION_TABLE_MAX_SIZE_REVISION_2 (128 * 4)
+#define NDIS_RSS_HASH_SECRET_KEY_MAX_SIZE_REVISION_2   40
+
+#define ITAB_NUM 128
+#define HASH_KEYLEN NDIS_RSS_HASH_SECRET_KEY_MAX_SIZE_REVISION_2
+extern u8 netvsc_hash_key[];
+
+struct ndis_recv_scale_param { /* NDIS_RECEIVE_SCALE_PARAMETERS */
+	struct ndis_obj_header hdr;
+
+	/* Qualifies the rest of the information */
+	u16 flag;
+
+	/* The base CPU number to do receive processing. not used */
+	u16 base_cpu_number;
+
+	/* This describes the hash function and type being enabled */
+	u32 hashinfo;
+
+	/* The size of indirection table array */
+	u16 indirect_tabsize;
+
+	/* The offset of the indirection table from the beginning of this
+	 * structure
+	 */
+	u32 indirect_taboffset;
+
+	/* The size of the hash secret key */
+	u16 hashkey_size;
+
+	/* The offset of the secret key from the beginning of this structure */
+	u32 kashkey_offset;
+
+	u32 processor_masks_offset;
+	u32 num_processor_masks;
+	u32 processor_masks_entry_size;
 };
 
+/* Fwd declaration */
+struct ndis_tcp_ip_checksum_info;
+
 /*
  * Represent netvsc packet which contains 1 RNDIS and 1 ethernet frame
  * within the RNDIS
  */
 struct hv_netvsc_packet {
 	/* Bookkeeping stuff */
-	struct list_head list_ent;
 	u32 status;
 
 	struct hv_device *device;
 	bool is_data_pkt;
 	u16 vlan_tci;
 
-	/*
-	 * Valid only for receives when we break a xfer page packet
-	 * into multiple netvsc packets
-	 */
-	struct xferpage_packet *xfer_page_pkt;
+	u16 q_idx;
+	struct vmbus_channel *channel;
 
-	union {
-		struct {
-			u64 recv_completion_tid;
-			void *recv_completion_ctx;
-			void (*recv_completion)(void *context);
-		} recv;
-		struct {
-			u64 send_completion_tid;
-			void *send_completion_ctx;
-			void (*send_completion)(void *context);
-		} send;
-	} completion;
+	u64 send_completion_tid;
+	void *send_completion_ctx;
+	void (*send_completion)(void *context);
+
+	u32 send_buf_index;
 
 	/* This points to the memory after page_buf */
 	struct rndis_message *rndis_msg;
@@ -120,6 +189,7 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj,
 int netvsc_recv_callback(struct hv_device *device_obj,
 			struct hv_netvsc_packet *packet,
 			struct ndis_tcp_ip_checksum_info *csum_info);
+void netvsc_channel_cb(void *context);
 int rndis_filter_open(struct hv_device *dev);
 int rndis_filter_close(struct hv_device *dev);
 int rndis_filter_device_add(struct hv_device *dev,
@@ -514,14 +584,16 @@ struct nvsp_message {
 
 #define NETVSC_RECEIVE_BUFFER_SIZE		(1024*1024*16)	/* 16MB */
 #define NETVSC_RECEIVE_BUFFER_SIZE_LEGACY	(1024*1024*15)  /* 15MB */
+#define NETVSC_SEND_BUFFER_SIZE			(1024 * 1024)   /* 1MB */
+#define NETVSC_INVALID_INDEX			-1
 
-#define NETVSC_RECEIVE_BUFFER_ID		0xcafe
 
-/* Preallocated receive packets */
-#define NETVSC_RECEIVE_PACKETLIST_COUNT		256
+#define NETVSC_RECEIVE_BUFFER_ID		0xcafe
 
 #define NETVSC_PACKET_SIZE                      2048
 
+#define VRSS_SEND_TAB_SIZE 16
+
 /* Per netvsc channel-specific */
 struct netvsc_device {
 	struct hv_device *dev;
@@ -532,12 +604,6 @@ struct netvsc_device {
 	wait_queue_head_t wait_drain;
 	bool start_remove;
 	bool destroy;
-	/*
-	 * List of free preallocated hv_netvsc_packet to represent receive
-	 * packet
-	 */
-	struct list_head recv_pkt_list;
-	spinlock_t recv_pkt_list_lock;
 
 	/* Receive buffer allocated by us but manages by NetVSP */
 	void *recv_buf;
@@ -546,6 +612,15 @@ struct netvsc_device {
 	u32 recv_section_cnt;
 	struct nvsp_1_receive_buffer_section *recv_section;
 
+	/* Send buffer allocated by us */
+	void *send_buf;
+	u32 send_buf_size;
+	u32 send_buf_gpadl_handle;
+	u32 send_section_cnt;
+	u32 send_section_size;
+	unsigned long *send_section_map;
+	int map_words;
+
 	/* Used for NetVSP initialization protocol */
 	struct completion channel_init_wait;
 	struct nvsp_message channel_init_pkt;
@@ -555,10 +630,20 @@ struct netvsc_device {
 
 	struct net_device *ndev;
 
+	struct vmbus_channel *chn_table[NR_CPUS];
+	u32 send_table[VRSS_SEND_TAB_SIZE];
+	u32 num_chn;
+	atomic_t queue_sends[NR_CPUS];
+
 	/* Holds rndis device info */
 	void *extension;
-	/* The recive buffer for this device */
+
+	int ring_size;
+
+	/* The primary channel callback buffer */
 	unsigned char cb_buffer[NETVSC_PACKET_SIZE];
+	/* The sub channel callback buffer */
+	unsigned char *sub_cb_buf;
 };
 
 /* NdisInitialize message */
@@ -706,6 +791,7 @@ enum ndis_per_pkt_info_type {
 	IEEE_8021Q_INFO,
 	ORIGINAL_PKTINFO,
 	PACKET_CANCEL_ID,
+	NBL_HASH_VALUE = PACKET_CANCEL_ID,
 	ORIGINAL_NET_BUFLIST,
 	CACHED_NET_BUFLIST,
 	SHORT_PKT_PADINFO,
@@ -852,6 +938,9 @@ struct ndis_tcp_lso_info {
 #define NDIS_LSO_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \
 		sizeof(struct ndis_tcp_lso_info))
 
+#define NDIS_HASH_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \
+		sizeof(u32))
+
 /* Format of Information buffer passed in a SetRequest for the OID */
 /* OID_GEN_RNDIS_CONFIG_PARAMETER. */
 struct rndis_config_parameter_info {
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index f7629ecefa84..c041f63a6d30 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/netdevice.h>
 #include <linux/if_ether.h>
+#include <asm/sync_bitops.h>
 
 #include "hyperv_net.h"
 
@@ -80,7 +81,7 @@ get_in_err:
 }
 
 
-static int netvsc_destroy_recv_buf(struct netvsc_device *net_device)
+static int netvsc_destroy_buf(struct netvsc_device *net_device)
 {
 	struct nvsp_message *revoke_packet;
 	int ret = 0;
@@ -146,10 +147,62 @@ static int netvsc_destroy_recv_buf(struct netvsc_device *net_device)
 		net_device->recv_section = NULL;
 	}
 
+	/* Deal with the send buffer we may have setup.
+	 * If we got a  send section size, it means we received a
+	 * SendsendBufferComplete msg (ie sent
+	 * NvspMessage1TypeSendReceiveBuffer msg) therefore, we need
+	 * to send a revoke msg here
+	 */
+	if (net_device->send_section_size) {
+		/* Send the revoke receive buffer */
+		revoke_packet = &net_device->revoke_packet;
+		memset(revoke_packet, 0, sizeof(struct nvsp_message));
+
+		revoke_packet->hdr.msg_type =
+			NVSP_MSG1_TYPE_REVOKE_SEND_BUF;
+		revoke_packet->msg.v1_msg.revoke_recv_buf.id = 0;
+
+		ret = vmbus_sendpacket(net_device->dev->channel,
+				       revoke_packet,
+				       sizeof(struct nvsp_message),
+				       (unsigned long)revoke_packet,
+				       VM_PKT_DATA_INBAND, 0);
+		/* 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 send "
+				   "revoke send buffer to netvsp\n");
+			return ret;
+		}
+	}
+	/* Teardown the gpadl on the vsp end */
+	if (net_device->send_buf_gpadl_handle) {
+		ret = vmbus_teardown_gpadl(net_device->dev->channel,
+					   net_device->send_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 send buffer's gpadl\n");
+			return ret;
+		}
+		net_device->recv_buf_gpadl_handle = 0;
+	}
+	if (net_device->send_buf) {
+		/* Free up the receive buffer */
+		free_pages((unsigned long)net_device->send_buf,
+			   get_order(net_device->send_buf_size));
+		net_device->send_buf = NULL;
+	}
+	kfree(net_device->send_section_map);
+
 	return ret;
 }
 
-static int netvsc_init_recv_buf(struct hv_device *device)
+static int netvsc_init_buf(struct hv_device *device)
 {
 	int ret = 0;
 	int t;
@@ -248,10 +301,90 @@ static int netvsc_init_recv_buf(struct hv_device *device)
 		goto cleanup;
 	}
 
+	/* Now setup the send buffer.
+	 */
+	net_device->send_buf =
+		(void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
+					 get_order(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);
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	/* Establish the gpadl handle for this buffer on this
+	 * channel.  Note: This call uses the vmbus connection rather
+	 * than the channel to establish the gpadl handle.
+	 */
+	ret = vmbus_establish_gpadl(device->channel, net_device->send_buf,
+				    net_device->send_buf_size,
+				    &net_device->send_buf_gpadl_handle);
+	if (ret != 0) {
+		netdev_err(ndev,
+			   "unable to establish send buffer's gpadl\n");
+		goto cleanup;
+	}
+
+	/* Notify the NetVsp of the gpadl handle */
+	init_packet = &net_device->channel_init_pkt;
+	memset(init_packet, 0, sizeof(struct nvsp_message));
+	init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_SEND_BUF;
+	init_packet->msg.v1_msg.send_recv_buf.gpadl_handle =
+		net_device->send_buf_gpadl_handle;
+	init_packet->msg.v1_msg.send_recv_buf.id = 0;
+
+	/* Send the gpadl notification request */
+	ret = vmbus_sendpacket(device->channel, init_packet,
+			       sizeof(struct nvsp_message),
+			       (unsigned long)init_packet,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret != 0) {
+		netdev_err(ndev,
+			   "unable to send send buffer's gpadl to netvsp\n");
+		goto cleanup;
+	}
+
+	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
+	BUG_ON(t == 0);
+
+	/* Check the response */
+	if (init_packet->msg.v1_msg.
+	    send_send_buf_complete.status != NVSP_STAT_SUCCESS) {
+		netdev_err(ndev, "Unable to complete send buffer "
+			   "initialization with NetVsp - status %d\n",
+			   init_packet->msg.v1_msg.
+			   send_recv_buf_complete.status);
+		ret = -EINVAL;
+		goto cleanup;
+	}
+
+	/* Parse the response */
+	net_device->send_section_size = init_packet->msg.
+				v1_msg.send_send_buf_complete.section_size;
+
+	/* Section count is simply the size divided by the section size.
+	 */
+	net_device->send_section_cnt =
+		net_device->send_buf_size/net_device->send_section_size;
+
+	dev_info(&device->device, "Send section size: %d, Section count:%d\n",
+		 net_device->send_section_size, net_device->send_section_cnt);
+
+	/* Setup state for managing the send buffer. */
+	net_device->map_words = DIV_ROUND_UP(net_device->send_section_cnt,
+					     BITS_PER_LONG);
+
+	net_device->send_section_map =
+		kzalloc(net_device->map_words * sizeof(ulong), GFP_KERNEL);
+	if (net_device->send_section_map == NULL)
+		goto cleanup;
+
 	goto exit;
 
 cleanup:
-	netvsc_destroy_recv_buf(net_device);
+	netvsc_destroy_buf(net_device);
 
 exit:
 	return ret;
@@ -369,8 +502,9 @@ static int netvsc_connect_vsp(struct hv_device *device)
 		net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE_LEGACY;
 	else
 		net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE;
+	net_device->send_buf_size = NETVSC_SEND_BUFFER_SIZE;
 
-	ret = netvsc_init_recv_buf(device);
+	ret = netvsc_init_buf(device);
 
 cleanup:
 	return ret;
@@ -378,7 +512,7 @@ cleanup:
 
 static void netvsc_disconnect_vsp(struct netvsc_device *net_device)
 {
-	netvsc_destroy_recv_buf(net_device);
+	netvsc_destroy_buf(net_device);
 }
 
 /*
@@ -387,7 +521,6 @@ static void netvsc_disconnect_vsp(struct netvsc_device *net_device)
 int netvsc_device_remove(struct hv_device *device)
 {
 	struct netvsc_device *net_device;
-	struct hv_netvsc_packet *netvsc_packet, *pos;
 	unsigned long flags;
 
 	net_device = hv_get_drvdata(device);
@@ -416,11 +549,8 @@ int netvsc_device_remove(struct hv_device *device)
 	vmbus_close(device->channel);
 
 	/* Release all resources */
-	list_for_each_entry_safe(netvsc_packet, pos,
-				 &net_device->recv_pkt_list, list_ent) {
-		list_del(&netvsc_packet->list_ent);
-		kfree(netvsc_packet);
-	}
+	if (net_device->sub_cb_buf)
+		vfree(net_device->sub_cb_buf);
 
 	kfree(net_device);
 	return 0;
@@ -444,6 +574,12 @@ static inline u32 hv_ringbuf_avail_percent(
 	return avail_write * 100 / ring_info->ring_datasize;
 }
 
+static inline void netvsc_free_send_slot(struct netvsc_device *net_device,
+					 u32 index)
+{
+	sync_change_bit(index, net_device->send_section_map);
+}
+
 static void netvsc_send_completion(struct netvsc_device *net_device,
 				   struct hv_device *device,
 				   struct vmpacket_descriptor *packet)
@@ -451,6 +587,7 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 	struct nvsp_message *nvsp_packet;
 	struct hv_netvsc_packet *nvsc_packet;
 	struct net_device *ndev;
+	u32 send_index;
 
 	ndev = net_device->ndev;
 
@@ -461,7 +598,9 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 	    (nvsp_packet->hdr.msg_type ==
 	     NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE) ||
 	    (nvsp_packet->hdr.msg_type ==
-	     NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE)) {
+	     NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE) ||
+	    (nvsp_packet->hdr.msg_type ==
+	     NVSP_MSG5_TYPE_SUBCHANNEL)) {
 		/* Copy the response back */
 		memcpy(&net_device->channel_init_pkt, nvsp_packet,
 		       sizeof(struct nvsp_message));
@@ -469,28 +608,39 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 	} else if (nvsp_packet->hdr.msg_type ==
 		   NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE) {
 		int num_outstanding_sends;
+		u16 q_idx = 0;
+		struct vmbus_channel *channel = device->channel;
+		int queue_sends;
 
 		/* Get the send context */
 		nvsc_packet = (struct hv_netvsc_packet *)(unsigned long)
 			packet->trans_id;
 
 		/* Notify the layer above us */
-		if (nvsc_packet)
-			nvsc_packet->completion.send.send_completion(
-				nvsc_packet->completion.send.
-				send_completion_ctx);
+		if (nvsc_packet) {
+			send_index = nvsc_packet->send_buf_index;
+			if (send_index != NETVSC_INVALID_INDEX)
+				netvsc_free_send_slot(net_device, send_index);
+			q_idx = nvsc_packet->q_idx;
+			channel = nvsc_packet->channel;
+			nvsc_packet->send_completion(nvsc_packet->
+						     send_completion_ctx);
+		}
 
 		num_outstanding_sends =
 			atomic_dec_return(&net_device->num_outstanding_sends);
+		queue_sends = atomic_dec_return(&net_device->
+						queue_sends[q_idx]);
 
 		if (net_device->destroy && num_outstanding_sends == 0)
 			wake_up(&net_device->wait_drain);
 
-		if (netif_queue_stopped(ndev) && !net_device->start_remove &&
-			(hv_ringbuf_avail_percent(&device->channel->outbound)
-			> RING_AVAIL_PERCENT_HIWATER ||
-			num_outstanding_sends < 1))
-				netif_wake_queue(ndev);
+		if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) &&
+		    !net_device->start_remove &&
+		    (hv_ringbuf_avail_percent(&channel->outbound) >
+		     RING_AVAIL_PERCENT_HIWATER || queue_sends < 1))
+				netif_tx_wake_queue(netdev_get_tx_queue(
+						    ndev, q_idx));
 	} else {
 		netdev_err(ndev, "Unknown send completion packet type- "
 			   "%d received!!\n", nvsp_packet->hdr.msg_type);
@@ -498,6 +648,52 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 
 }
 
+static u32 netvsc_get_next_send_section(struct netvsc_device *net_device)
+{
+	unsigned long index;
+	u32 max_words = net_device->map_words;
+	unsigned long *map_addr = (unsigned long *)net_device->send_section_map;
+	u32 section_cnt = net_device->send_section_cnt;
+	int ret_val = NETVSC_INVALID_INDEX;
+	int i;
+	int prev_val;
+
+	for (i = 0; i < max_words; i++) {
+		if (!~(map_addr[i]))
+			continue;
+		index = ffz(map_addr[i]);
+		prev_val = sync_test_and_set_bit(index, &map_addr[i]);
+		if (prev_val)
+			continue;
+		if ((index + (i * BITS_PER_LONG)) >= section_cnt)
+			break;
+		ret_val = (index + (i * BITS_PER_LONG));
+		break;
+	}
+	return ret_val;
+}
+
+u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
+			    unsigned int section_index,
+			    struct hv_netvsc_packet *packet)
+{
+	char *start = net_device->send_buf;
+	char *dest = (start + (section_index * net_device->send_section_size));
+	int i;
+	u32 msg_size = 0;
+
+	for (i = 0; i < packet->page_buf_cnt; i++) {
+		char *src = phys_to_virt(packet->page_buf[i].pfn << PAGE_SHIFT);
+		u32 offset = packet->page_buf[i].offset;
+		u32 len = packet->page_buf[i].len;
+
+		memcpy(dest, (src + offset), len);
+		msg_size += len;
+		dest += len;
+	}
+	return msg_size;
+}
+
 int netvsc_send(struct hv_device *device,
 			struct hv_netvsc_packet *packet)
 {
@@ -505,7 +701,12 @@ int netvsc_send(struct hv_device *device,
 	int ret = 0;
 	struct nvsp_message sendMessage;
 	struct net_device *ndev;
+	struct vmbus_channel *out_channel = NULL;
 	u64 req_id;
+	unsigned int section_index = NETVSC_INVALID_INDEX;
+	u32 msg_size = 0;
+	struct sk_buff *skb;
+
 
 	net_device = get_outbound_net_device(device);
 	if (!net_device)
@@ -521,25 +722,46 @@ int netvsc_send(struct hv_device *device,
 		sendMessage.msg.v1_msg.send_rndis_pkt.channel_type = 1;
 	}
 
-	/* Not using send buffer section */
+	/* Attempt to send via sendbuf */
+	if (packet->total_data_buflen < net_device->send_section_size) {
+		section_index = netvsc_get_next_send_section(net_device);
+		if (section_index != NETVSC_INVALID_INDEX) {
+			msg_size = netvsc_copy_to_send_buf(net_device,
+							   section_index,
+							   packet);
+			skb = (struct sk_buff *)
+			      (unsigned long)packet->send_completion_tid;
+			if (skb)
+				dev_kfree_skb_any(skb);
+			packet->page_buf_cnt = 0;
+		}
+	}
+	packet->send_buf_index = section_index;
+
+
 	sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_index =
-		0xFFFFFFFF;
-	sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_size = 0;
+		section_index;
+	sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_size = msg_size;
 
-	if (packet->completion.send.send_completion)
+	if (packet->send_completion)
 		req_id = (ulong)packet;
 	else
 		req_id = 0;
 
+	out_channel = net_device->chn_table[packet->q_idx];
+	if (out_channel == NULL)
+		out_channel = device->channel;
+	packet->channel = out_channel;
+
 	if (packet->page_buf_cnt) {
-		ret = vmbus_sendpacket_pagebuffer(device->channel,
+		ret = vmbus_sendpacket_pagebuffer(out_channel,
 						  packet->page_buf,
 						  packet->page_buf_cnt,
 						  &sendMessage,
 						  sizeof(struct nvsp_message),
 						  req_id);
 	} else {
-		ret = vmbus_sendpacket(device->channel, &sendMessage,
+		ret = vmbus_sendpacket(out_channel, &sendMessage,
 				sizeof(struct nvsp_message),
 				req_id,
 				VM_PKT_DATA_INBAND,
@@ -548,17 +770,24 @@ int netvsc_send(struct hv_device *device,
 
 	if (ret == 0) {
 		atomic_inc(&net_device->num_outstanding_sends);
-		if (hv_ringbuf_avail_percent(&device->channel->outbound) <
+		atomic_inc(&net_device->queue_sends[packet->q_idx]);
+
+		if (hv_ringbuf_avail_percent(&out_channel->outbound) <
 			RING_AVAIL_PERCENT_LOWATER) {
-			netif_stop_queue(ndev);
+			netif_tx_stop_queue(netdev_get_tx_queue(
+					    ndev, packet->q_idx));
+
 			if (atomic_read(&net_device->
-				num_outstanding_sends) < 1)
-				netif_wake_queue(ndev);
+				queue_sends[packet->q_idx]) < 1)
+				netif_tx_wake_queue(netdev_get_tx_queue(
+						    ndev, packet->q_idx));
 		}
 	} else if (ret == -EAGAIN) {
-		netif_stop_queue(ndev);
-		if (atomic_read(&net_device->num_outstanding_sends) < 1) {
-			netif_wake_queue(ndev);
+		netif_tx_stop_queue(netdev_get_tx_queue(
+				    ndev, packet->q_idx));
+		if (atomic_read(&net_device->queue_sends[packet->q_idx]) < 1) {
+			netif_tx_wake_queue(netdev_get_tx_queue(
+					    ndev, packet->q_idx));
 			ret = -ENOSPC;
 		}
 	} else {
@@ -570,6 +799,7 @@ int netvsc_send(struct hv_device *device,
 }
 
 static void netvsc_send_recv_completion(struct hv_device *device,
+					struct vmbus_channel *channel,
 					struct netvsc_device *net_device,
 					u64 transaction_id, u32 status)
 {
@@ -587,7 +817,7 @@ static void netvsc_send_recv_completion(struct hv_device *device,
 
 retry_send_cmplt:
 	/* Send the completion */
-	ret = vmbus_sendpacket(device->channel, &recvcompMessage,
+	ret = vmbus_sendpacket(channel, &recvcompMessage,
 			       sizeof(struct nvsp_message), transaction_id,
 			       VM_PKT_COMP, 0);
 	if (ret == 0) {
@@ -613,76 +843,20 @@ retry_send_cmplt:
 	}
 }
 
-/* Send a receive completion packet to RNDIS device (ie NetVsp) */
-static void netvsc_receive_completion(void *context)
-{
-	struct hv_netvsc_packet *packet = context;
-	struct hv_device *device = packet->device;
-	struct netvsc_device *net_device;
-	u64 transaction_id = 0;
-	bool fsend_receive_comp = false;
-	unsigned long flags;
-	struct net_device *ndev;
-	u32 status = NVSP_STAT_NONE;
-
-	/*
-	 * Even though it seems logical to do a GetOutboundNetDevice() here to
-	 * send out receive completion, we are using GetInboundNetDevice()
-	 * since we may have disable outbound traffic already.
-	 */
-	net_device = get_inbound_net_device(device);
-	if (!net_device)
-		return;
-	ndev = net_device->ndev;
-
-	/* Overloading use of the lock. */
-	spin_lock_irqsave(&net_device->recv_pkt_list_lock, flags);
-
-	if (packet->status != NVSP_STAT_SUCCESS)
-		packet->xfer_page_pkt->status = NVSP_STAT_FAIL;
-
-	packet->xfer_page_pkt->count--;
-
-	/*
-	 * Last one in the line that represent 1 xfer page packet.
-	 * Return the xfer page packet itself to the freelist
-	 */
-	if (packet->xfer_page_pkt->count == 0) {
-		fsend_receive_comp = true;
-		transaction_id = packet->completion.recv.recv_completion_tid;
-		status = packet->xfer_page_pkt->status;
-		list_add_tail(&packet->xfer_page_pkt->list_ent,
-			      &net_device->recv_pkt_list);
-
-	}
-
-	/* Put the packet back */
-	list_add_tail(&packet->list_ent, &net_device->recv_pkt_list);
-	spin_unlock_irqrestore(&net_device->recv_pkt_list_lock, flags);
-
-	/* Send a receive completion for the xfer page packet */
-	if (fsend_receive_comp)
-		netvsc_send_recv_completion(device, net_device, transaction_id,
-					status);
-
-}
-
 static void netvsc_receive(struct netvsc_device *net_device,
+			struct vmbus_channel *channel,
 			struct hv_device *device,
 			struct vmpacket_descriptor *packet)
 {
 	struct vmtransfer_page_packet_header *vmxferpage_packet;
 	struct nvsp_message *nvsp_packet;
-	struct hv_netvsc_packet *netvsc_packet = NULL;
-	/* struct netvsc_driver *netvscDriver; */
-	struct xferpage_packet *xferpage_packet = NULL;
+	struct hv_netvsc_packet nv_pkt;
+	struct hv_netvsc_packet *netvsc_packet = &nv_pkt;
+	u32 status = NVSP_STAT_SUCCESS;
 	int i;
 	int count = 0;
-	unsigned long flags;
 	struct net_device *ndev;
 
-	LIST_HEAD(listHead);
-
 	ndev = net_device->ndev;
 
 	/*
@@ -715,77 +889,14 @@ static void netvsc_receive(struct netvsc_device *net_device,
 		return;
 	}
 
-	/*
-	 * Grab free packets (range count + 1) to represent this xfer
-	 * page packet. +1 to represent the xfer page packet itself.
-	 * We grab it here so that we know exactly how many we can
-	 * fulfil
-	 */
-	spin_lock_irqsave(&net_device->recv_pkt_list_lock, flags);
-	while (!list_empty(&net_device->recv_pkt_list)) {
-		list_move_tail(net_device->recv_pkt_list.next, &listHead);
-		if (++count == vmxferpage_packet->range_cnt + 1)
-			break;
-	}
-	spin_unlock_irqrestore(&net_device->recv_pkt_list_lock, flags);
-
-	/*
-	 * We need at least 2 netvsc pkts (1 to represent the xfer
-	 * page and at least 1 for the range) i.e. we can handled
-	 * some of the xfer page packet ranges...
-	 */
-	if (count < 2) {
-		netdev_err(ndev, "Got only %d netvsc pkt...needed "
-			"%d pkts. Dropping this xfer page packet completely!\n",
-			count, vmxferpage_packet->range_cnt + 1);
-
-		/* Return it to the freelist */
-		spin_lock_irqsave(&net_device->recv_pkt_list_lock, flags);
-		for (i = count; i != 0; i--) {
-			list_move_tail(listHead.next,
-				       &net_device->recv_pkt_list);
-		}
-		spin_unlock_irqrestore(&net_device->recv_pkt_list_lock,
-				       flags);
-
-		netvsc_send_recv_completion(device, net_device,
-					    vmxferpage_packet->d.trans_id,
-					    NVSP_STAT_FAIL);
-
-		return;
-	}
-
-	/* Remove the 1st packet to represent the xfer page packet itself */
-	xferpage_packet = (struct xferpage_packet *)listHead.next;
-	list_del(&xferpage_packet->list_ent);
-	xferpage_packet->status = NVSP_STAT_SUCCESS;
-
-	/* This is how much we can satisfy */
-	xferpage_packet->count = count - 1;
-
-	if (xferpage_packet->count != vmxferpage_packet->range_cnt) {
-		netdev_err(ndev, "Needed %d netvsc pkts to satisfy "
-			"this xfer page...got %d\n",
-			vmxferpage_packet->range_cnt, xferpage_packet->count);
-	}
+	count = vmxferpage_packet->range_cnt;
+	netvsc_packet->device = device;
+	netvsc_packet->channel = channel;
 
 	/* Each range represents 1 RNDIS pkt that contains 1 ethernet frame */
-	for (i = 0; i < (count - 1); i++) {
-		netvsc_packet = (struct hv_netvsc_packet *)listHead.next;
-		list_del(&netvsc_packet->list_ent);
-
+	for (i = 0; i < count; i++) {
 		/* Initialize the netvsc packet */
 		netvsc_packet->status = NVSP_STAT_SUCCESS;
-		netvsc_packet->xfer_page_pkt = xferpage_packet;
-		netvsc_packet->completion.recv.recv_completion =
-					netvsc_receive_completion;
-		netvsc_packet->completion.recv.recv_completion_ctx =
-					netvsc_packet;
-		netvsc_packet->device = device;
-		/* Save this so that we can send it back */
-		netvsc_packet->completion.recv.recv_completion_tid =
-					vmxferpage_packet->d.trans_id;
-
 		netvsc_packet->data = (void *)((unsigned long)net_device->
 			recv_buf + vmxferpage_packet->ranges[i].byte_offset);
 		netvsc_packet->total_data_buflen =
@@ -794,16 +905,53 @@ static void netvsc_receive(struct netvsc_device *net_device,
 		/* Pass it to the upper layer */
 		rndis_filter_receive(device, netvsc_packet);
 
-		netvsc_receive_completion(netvsc_packet->
-				completion.recv.recv_completion_ctx);
+		if (netvsc_packet->status != NVSP_STAT_SUCCESS)
+			status = NVSP_STAT_FAIL;
+	}
+
+	netvsc_send_recv_completion(device, channel, net_device,
+				    vmxferpage_packet->d.trans_id, status);
+}
+
+
+static void netvsc_send_table(struct hv_device *hdev,
+			      struct vmpacket_descriptor *vmpkt)
+{
+	struct netvsc_device *nvscdev;
+	struct net_device *ndev;
+	struct nvsp_message *nvmsg;
+	int i;
+	u32 count, *tab;
+
+	nvscdev = get_outbound_net_device(hdev);
+	if (!nvscdev)
+		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);
+		return;
 	}
 
+	tab = (u32 *)((unsigned long)&nvmsg->msg.v5_msg.send_table +
+		      nvmsg->msg.v5_msg.send_table.offset);
+
+	for (i = 0; i < count; i++)
+		nvscdev->send_table[i] = tab[i];
 }
 
-static void netvsc_channel_cb(void *context)
+void netvsc_channel_cb(void *context)
 {
 	int ret;
-	struct hv_device *device = context;
+	struct vmbus_channel *channel = (struct vmbus_channel *)context;
+	struct hv_device *device;
 	struct netvsc_device *net_device;
 	u32 bytes_recvd;
 	u64 request_id;
@@ -812,14 +960,19 @@ static void netvsc_channel_cb(void *context)
 	int bufferlen = NETVSC_PACKET_SIZE;
 	struct net_device *ndev;
 
+	if (channel->primary_channel != NULL)
+		device = channel->primary_channel->device_obj;
+	else
+		device = channel->device_obj;
+
 	net_device = get_inbound_net_device(device);
 	if (!net_device)
 		return;
 	ndev = net_device->ndev;
-	buffer = net_device->cb_buffer;
+	buffer = get_per_channel_state(channel);
 
 	do {
-		ret = vmbus_recvpacket_raw(device->channel, buffer, bufferlen,
+		ret = vmbus_recvpacket_raw(channel, buffer, bufferlen,
 					   &bytes_recvd, &request_id);
 		if (ret == 0) {
 			if (bytes_recvd > 0) {
@@ -831,8 +984,12 @@ static void netvsc_channel_cb(void *context)
 					break;
 
 				case VM_PKT_DATA_USING_XFER_PAGES:
-					netvsc_receive(net_device,
-							device, desc);
+					netvsc_receive(net_device, channel,
+						       device, desc);
+					break;
+
+				case VM_PKT_DATA_INBAND:
+					netvsc_send_table(device, desc);
 					break;
 
 				default:
@@ -880,11 +1037,9 @@ static void netvsc_channel_cb(void *context)
 int netvsc_device_add(struct hv_device *device, void *additional_info)
 {
 	int ret = 0;
-	int i;
 	int ring_size =
 	((struct netvsc_device_info *)additional_info)->ring_size;
 	struct netvsc_device *net_device;
-	struct hv_netvsc_packet *packet, *pos;
 	struct net_device *ndev;
 
 	net_device = alloc_net_device(device);
@@ -893,6 +1048,8 @@ int netvsc_device_add(struct hv_device *device, void *additional_info)
 		goto cleanup;
 	}
 
+	net_device->ring_size = ring_size;
+
 	/*
 	 * Coming into this function, struct net_device * is
 	 * registered as the driver private data.
@@ -903,24 +1060,14 @@ int netvsc_device_add(struct hv_device *device, void *additional_info)
 	ndev = net_device->ndev;
 
 	/* Initialize the NetVSC channel extension */
-	spin_lock_init(&net_device->recv_pkt_list_lock);
-
-	INIT_LIST_HEAD(&net_device->recv_pkt_list);
-
-	for (i = 0; i < NETVSC_RECEIVE_PACKETLIST_COUNT; i++) {
-		packet = kzalloc(sizeof(struct hv_netvsc_packet), GFP_KERNEL);
-		if (!packet)
-			break;
-
-		list_add_tail(&packet->list_ent,
-			      &net_device->recv_pkt_list);
-	}
 	init_completion(&net_device->channel_init_wait);
 
+	set_per_channel_state(device->channel, net_device->cb_buffer);
+
 	/* Open the channel */
 	ret = vmbus_open(device->channel, ring_size * PAGE_SIZE,
 			 ring_size * PAGE_SIZE, NULL, 0,
-			 netvsc_channel_cb, device);
+			 netvsc_channel_cb, device->channel);
 
 	if (ret != 0) {
 		netdev_err(ndev, "unable to open channel: %d\n", ret);
@@ -930,6 +1077,8 @@ int netvsc_device_add(struct hv_device *device, void *additional_info)
 	/* Channel is opened */
 	pr_info("hv_netvsc channel opened successfully\n");
 
+	net_device->chn_table[0] = device->channel;
+
 	/* Connect with the NetVsp */
 	ret = netvsc_connect_vsp(device);
 	if (ret != 0) {
@@ -946,16 +1095,8 @@ close:
 
 cleanup:
 
-	if (net_device) {
-		list_for_each_entry_safe(packet, pos,
-					 &net_device->recv_pkt_list,
-					 list_ent) {
-			list_del(&packet->list_ent);
-			kfree(packet);
-		}
-
+	if (net_device)
 		kfree(net_device);
-	}
 
 	return ret;
 }
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 7918d5132c1f..4fd71b75e666 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -101,7 +101,7 @@ static int netvsc_open(struct net_device *net)
 		return ret;
 	}
 
-	netif_start_queue(net);
+	netif_tx_start_all_queues(net);
 
 	nvdev = hv_get_drvdata(device_obj);
 	rdev = nvdev->extension;
@@ -149,15 +149,100 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
 	return ppi;
 }
 
+union sub_key {
+	u64 k;
+	struct {
+		u8 pad[3];
+		u8 kb;
+		u32 ka;
+	};
+};
+
+/* Toeplitz hash function
+ * data: network byte order
+ * return: host byte order
+ */
+static u32 comp_hash(u8 *key, int klen, u8 *data, int dlen)
+{
+	union sub_key subk;
+	int k_next = 4;
+	u8 dt;
+	int i, j;
+	u32 ret = 0;
+
+	subk.k = 0;
+	subk.ka = ntohl(*(u32 *)key);
+
+	for (i = 0; i < dlen; i++) {
+		subk.kb = key[k_next];
+		k_next = (k_next + 1) % klen;
+		dt = data[i];
+		for (j = 0; j < 8; j++) {
+			if (dt & 0x80)
+				ret ^= subk.ka;
+			dt <<= 1;
+			subk.k <<= 1;
+		}
+	}
+
+	return ret;
+}
+
+static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb)
+{
+	struct iphdr *iphdr;
+	int data_len;
+	bool ret = false;
+
+	if (eth_hdr(skb)->h_proto != htons(ETH_P_IP))
+		return false;
+
+	iphdr = ip_hdr(skb);
+
+	if (iphdr->version == 4) {
+		if (iphdr->protocol == IPPROTO_TCP)
+			data_len = 12;
+		else
+			data_len = 8;
+		*hash = comp_hash(netvsc_hash_key, HASH_KEYLEN,
+				  (u8 *)&iphdr->saddr, data_len);
+		ret = true;
+	}
+
+	return ret;
+}
+
+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;
+
+	if (netvsc_set_hash(&hash, skb)) {
+		q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
+			ndev->real_num_tx_queues;
+		skb_set_hash(skb, hash, PKT_HASH_TYPE_L3);
+	}
+
+	return q_idx;
+}
+
 static 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;
+		(unsigned long)packet->send_completion_tid;
+	u32 index = packet->send_buf_index;
 
 	kfree(packet);
 
-	if (skb)
+	if (skb && (index == NETVSC_INVALID_INDEX))
 		dev_kfree_skb_any(skb);
 }
 
@@ -301,6 +386,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	struct ndis_tcp_lso_info *lso_info;
 	int  hdr_offset;
 	u32 net_trans_info;
+	u32 hash;
 
 
 	/* We will atmost need two pages to describe the rndis
@@ -319,9 +405,8 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	packet = kzalloc(sizeof(struct hv_netvsc_packet) +
 			 (num_data_pgs * sizeof(struct hv_page_buffer)) +
 			 sizeof(struct rndis_message) +
-			 NDIS_VLAN_PPI_SIZE +
-			 NDIS_CSUM_PPI_SIZE +
-			 NDIS_LSO_PPI_SIZE, GFP_ATOMIC);
+			 NDIS_VLAN_PPI_SIZE + NDIS_CSUM_PPI_SIZE +
+			 NDIS_LSO_PPI_SIZE + NDIS_HASH_PPI_SIZE, GFP_ATOMIC);
 	if (!packet) {
 		/* out of memory, drop packet */
 		netdev_err(net, "unable to allocate hv_netvsc_packet\n");
@@ -333,6 +418,8 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 
 	packet->vlan_tci = skb->vlan_tci;
 
+	packet->q_idx = skb_get_queue_mapping(skb);
+
 	packet->is_data_pkt = true;
 	packet->total_data_buflen = skb->len;
 
@@ -341,9 +428,9 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 				(num_data_pgs * sizeof(struct hv_page_buffer)));
 
 	/* 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;
+	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;
 
@@ -358,6 +445,14 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 
 	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;
 
@@ -558,6 +653,9 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 				       packet->vlan_tci);
 
+	skb_record_rx_queue(skb, packet->channel->
+			    offermsg.offer.sub_channel_index);
+
 	net->stats.rx_packets++;
 	net->stats.rx_bytes += packet->total_data_buflen;
 
@@ -606,7 +704,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	hv_set_drvdata(hdev, ndev);
 	device_info.ring_size = ring_size;
 	rndis_filter_device_add(hdev, &device_info);
-	netif_wake_queue(ndev);
+	netif_tx_wake_all_queues(ndev);
 
 	return 0;
 }
@@ -652,6 +750,7 @@ static const struct net_device_ops device_ops = {
 	.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,
 };
 
 /*
@@ -698,9 +797,11 @@ static int netvsc_probe(struct hv_device *dev,
 	struct net_device *net = NULL;
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device_info device_info;
+	struct netvsc_device *nvdev;
 	int ret;
 
-	net = alloc_etherdev(sizeof(struct net_device_context));
+	net = alloc_etherdev_mq(sizeof(struct net_device_context),
+				num_online_cpus());
 	if (!net)
 		return -ENOMEM;
 
@@ -719,7 +820,7 @@ static int netvsc_probe(struct hv_device *dev,
 	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);
 
 	/* Notify the netvsc driver of the new device */
@@ -733,6 +834,10 @@ static int netvsc_probe(struct hv_device *dev,
 	}
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
+	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);
+
 	ret = register_netdev(net);
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 143a98caf618..99c527adae5b 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -31,7 +31,7 @@
 #include "hyperv_net.h"
 
 
-#define RNDIS_EXT_LEN 100
+#define RNDIS_EXT_LEN PAGE_SIZE
 struct rndis_request {
 	struct list_head list_ent;
 	struct completion  wait_event;
@@ -94,6 +94,8 @@ static struct rndis_request *get_rndis_request(struct rndis_device *dev,
 	rndis_msg->ndis_msg_type = msg_type;
 	rndis_msg->msg_len = msg_len;
 
+	request->pkt.q_idx = 0;
+
 	/*
 	 * Set the request id. This field is always after the rndis header for
 	 * request/response packet types so we just used the SetRequest as a
@@ -234,7 +236,7 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 			packet->page_buf[0].len;
 	}
 
-	packet->completion.send.send_completion = NULL;
+	packet->send_completion = NULL;
 
 	ret = netvsc_send(dev->net_dev->dev, packet);
 	return ret;
@@ -399,8 +401,6 @@ static void rndis_filter_receive_data(struct rndis_device *dev,
 	pkt->total_data_buflen = rndis_pkt->data_len;
 	pkt->data = (void *)((unsigned long)pkt->data + data_offset);
 
-	pkt->is_data_pkt = true;
-
 	vlan = rndis_get_ppi(rndis_pkt, IEEE_8021Q_INFO);
 	if (vlan) {
 		pkt->vlan_tci = VLAN_TAG_PRESENT | vlan->vlanid |
@@ -509,6 +509,19 @@ static int rndis_filter_query_device(struct rndis_device *dev, u32 oid,
 	query->info_buflen = 0;
 	query->dev_vc_handle = 0;
 
+	if (oid == OID_GEN_RECEIVE_SCALE_CAPABILITIES) {
+		struct ndis_recv_scale_cap *cap;
+
+		request->request_msg.msg_len +=
+			sizeof(struct ndis_recv_scale_cap);
+		query->info_buflen = sizeof(struct ndis_recv_scale_cap);
+		cap = (struct ndis_recv_scale_cap *)((unsigned long)query +
+						     query->info_buf_offset);
+		cap->hdr.type = NDIS_OBJECT_TYPE_RSS_CAPABILITIES;
+		cap->hdr.rev = NDIS_RECEIVE_SCALE_CAPABILITIES_REVISION_2;
+		cap->hdr.size = sizeof(struct ndis_recv_scale_cap);
+	}
+
 	ret = rndis_filter_send_request(dev, request);
 	if (ret != 0)
 		goto cleanup;
@@ -695,6 +708,89 @@ cleanup:
 	return ret;
 }
 
+u8 netvsc_hash_key[HASH_KEYLEN] = {
+	0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2,
+	0x41, 0x67, 0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0,
+	0xd0, 0xca, 0x2b, 0xcb, 0xae, 0x7b, 0x30, 0xb4,
+	0x77, 0xcb, 0x2d, 0xa3, 0x80, 0x30, 0xf2, 0x0c,
+	0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa
+};
+
+int rndis_filter_set_rss_param(struct rndis_device *rdev, int num_queue)
+{
+	struct net_device *ndev = rdev->net_dev->ndev;
+	struct rndis_request *request;
+	struct rndis_set_request *set;
+	struct rndis_set_complete *set_complete;
+	u32 extlen = sizeof(struct ndis_recv_scale_param) +
+		     4*ITAB_NUM + HASH_KEYLEN;
+	struct ndis_recv_scale_param *rssp;
+	u32 *itab;
+	u8 *keyp;
+	int i, t, ret;
+
+	request = get_rndis_request(
+			rdev, RNDIS_MSG_SET,
+			RNDIS_MESSAGE_SIZE(struct rndis_set_request) + extlen);
+	if (!request)
+		return -ENOMEM;
+
+	set = &request->request_msg.msg.set_req;
+	set->oid = OID_GEN_RECEIVE_SCALE_PARAMETERS;
+	set->info_buflen = extlen;
+	set->info_buf_offset = sizeof(struct rndis_set_request);
+	set->dev_vc_handle = 0;
+
+	rssp = (struct ndis_recv_scale_param *)(set + 1);
+	rssp->hdr.type = NDIS_OBJECT_TYPE_RSS_PARAMETERS;
+	rssp->hdr.rev = NDIS_RECEIVE_SCALE_PARAMETERS_REVISION_2;
+	rssp->hdr.size = sizeof(struct ndis_recv_scale_param);
+	rssp->flag = 0;
+	rssp->hashinfo = NDIS_HASH_FUNC_TOEPLITZ | NDIS_HASH_IPV4 |
+			 NDIS_HASH_TCP_IPV4;
+	rssp->indirect_tabsize = 4*ITAB_NUM;
+	rssp->indirect_taboffset = sizeof(struct ndis_recv_scale_param);
+	rssp->hashkey_size = HASH_KEYLEN;
+	rssp->kashkey_offset = rssp->indirect_taboffset +
+			       rssp->indirect_tabsize;
+
+	/* Set indirection table entries */
+	itab = (u32 *)(rssp + 1);
+	for (i = 0; i < ITAB_NUM; i++)
+		itab[i] = i % num_queue;
+
+	/* Set hask key values */
+	keyp = (u8 *)((unsigned long)rssp + rssp->kashkey_offset);
+	for (i = 0; i < HASH_KEYLEN; i++)
+		keyp[i] = netvsc_hash_key[i];
+
+
+	ret = rndis_filter_send_request(rdev, request);
+	if (ret != 0)
+		goto cleanup;
+
+	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	if (t == 0) {
+		netdev_err(ndev, "timeout before we got a set response...\n");
+		/* can't put_rndis_request, since we may still receive a
+		 * send-completion.
+		 */
+		return -ETIMEDOUT;
+	} else {
+		set_complete = &request->response_msg.msg.set_complete;
+		if (set_complete->status != RNDIS_STATUS_SUCCESS) {
+			netdev_err(ndev, "Fail to set RSS parameters:0x%x\n",
+				   set_complete->status);
+			ret = -EINVAL;
+		}
+	}
+
+cleanup:
+	put_rndis_request(rdev, request);
+	return ret;
+}
+
+
 static int rndis_filter_query_device_link_status(struct rndis_device *dev)
 {
 	u32 size = sizeof(u32);
@@ -886,6 +982,28 @@ static int rndis_filter_close_device(struct rndis_device *dev)
 	return ret;
 }
 
+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;
+
+	nvscdev = hv_get_drvdata(new_sc->primary_channel->device_obj);
+
+	if (chn_index >= nvscdev->num_chn)
+		return;
+
+	set_per_channel_state(new_sc, nvscdev->sub_cb_buf + (chn_index - 1) *
+			      NETVSC_PACKET_SIZE);
+
+	ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE,
+			 nvscdev->ring_size * PAGE_SIZE, NULL, 0,
+			 netvsc_channel_cb, new_sc);
+
+	if (ret == 0)
+		nvscdev->chn_table[chn_index] = new_sc;
+}
+
 int rndis_filter_device_add(struct hv_device *dev,
 				  void *additional_info)
 {
@@ -894,6 +1012,10 @@ int rndis_filter_device_add(struct hv_device *dev,
 	struct rndis_device *rndis_device;
 	struct netvsc_device_info *device_info = additional_info;
 	struct ndis_offload_params offloads;
+	struct nvsp_message *init_packet;
+	int t;
+	struct ndis_recv_scale_cap rsscap;
+	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 
 	rndis_device = get_rndis_device();
 	if (!rndis_device)
@@ -913,6 +1035,7 @@ int rndis_filter_device_add(struct hv_device *dev,
 
 	/* Initialize the rndis device */
 	net_device = hv_get_drvdata(dev);
+	net_device->num_chn = 1;
 
 	net_device->extension = rndis_device;
 	rndis_device->net_dev = net_device;
@@ -952,7 +1075,6 @@ int rndis_filter_device_add(struct hv_device *dev,
 	if (ret)
 		goto err_dev_remv;
 
-
 	rndis_filter_query_device_link_status(rndis_device);
 
 	device_info->link_state = rndis_device->link_state;
@@ -961,7 +1083,66 @@ int rndis_filter_device_add(struct hv_device *dev,
 		 rndis_device->hw_mac_adr,
 		 device_info->link_state ? "down" : "up");
 
-	return ret;
+	if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_5)
+		return 0;
+
+	/* vRSS setup */
+	memset(&rsscap, 0, rsscap_size);
+	ret = rndis_filter_query_device(rndis_device,
+					OID_GEN_RECEIVE_SCALE_CAPABILITIES,
+					&rsscap, &rsscap_size);
+	if (ret || rsscap.num_recv_que < 2)
+		goto out;
+
+	net_device->num_chn = (num_online_cpus() < rsscap.num_recv_que) ?
+			       num_online_cpus() : rsscap.num_recv_que;
+	if (net_device->num_chn == 1)
+		goto out;
+
+	net_device->sub_cb_buf = vzalloc((net_device->num_chn - 1) *
+					 NETVSC_PACKET_SIZE);
+	if (!net_device->sub_cb_buf) {
+		net_device->num_chn = 1;
+		dev_info(&dev->device, "No memory for subchannels.\n");
+		goto out;
+	}
+
+	vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
+
+	init_packet = &net_device->channel_init_pkt;
+	memset(init_packet, 0, sizeof(struct nvsp_message));
+	init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
+	init_packet->msg.v5_msg.subchn_req.op = NVSP_SUBCHANNEL_ALLOCATE;
+	init_packet->msg.v5_msg.subchn_req.num_subchannels =
+						net_device->num_chn - 1;
+	ret = vmbus_sendpacket(dev->channel, init_packet,
+			       sizeof(struct nvsp_message),
+			       (unsigned long)init_packet,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret)
+		goto out;
+	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
+	if (t == 0) {
+		ret = -ETIMEDOUT;
+		goto out;
+	}
+	if (init_packet->msg.v5_msg.subchn_comp.status !=
+	    NVSP_STAT_SUCCESS) {
+		ret = -ENODEV;
+		goto out;
+	}
+	net_device->num_chn = 1 +
+		init_packet->msg.v5_msg.subchn_comp.num_subchannels;
+
+	vmbus_are_subchannels_present(dev->channel);
+
+	ret = rndis_filter_set_rss_param(rndis_device, net_device->num_chn);
+
+out:
+	if (ret)
+		net_device->num_chn = 1;
+	return 0; /* return 0 because primary channel can be used alone */
 
 err_dev_remv:
 	rndis_filter_device_remove(dev);