Linux-libre 4.5-gnu

4 files changed, 277 insertions, 293 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 5fa98f599..fcb92c0d0 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -124,37 +124,22 @@ struct ndis_tcp_ip_checksum_info;
 /*
  * Represent netvsc packet which contains 1 RNDIS and 1 ethernet frame
  * within the RNDIS
+ *
+ * The size of this structure is less than 48 bytes and we can now
+ * place this structure in the skb->cb field.
  */
 struct hv_netvsc_packet {
 	/* Bookkeeping stuff */
-	u32 status;
-
-	bool is_data_pkt;
-	bool xmit_more; /* from skb */
-	bool cp_partial; /* partial copy into send buffer */
+	u8 cp_partial; /* partial copy into send buffer */
 
-	u16 vlan_tci;
+	u8 rmsg_size; /* RNDIS header and PPI size */
+	u8 rmsg_pgcnt; /* page count of RNDIS header and PPI */
+	u8 page_buf_cnt;
 
 	u16 q_idx;
-	struct vmbus_channel *channel;
-
-	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;
-
-	u32 rmsg_size; /* RNDIS header and PPI size */
-	u32 rmsg_pgcnt; /* page count of RNDIS header and PPI */
-
 	u32 total_data_buflen;
-	/* Points to the send/receive buffer where the ethernet frame is */
-	void *data;
-	u32 page_buf_cnt;
-	struct hv_page_buffer *page_buf;
 };
 
 struct netvsc_device_info {
@@ -177,7 +162,6 @@ struct rndis_device {
 
 	enum rndis_device_state state;
 	bool link_state;
-	bool link_change;
 	atomic_t new_req_id;
 
 	spinlock_t request_lock;
@@ -188,16 +172,22 @@ struct rndis_device {
 
 
 /* Interface */
+struct rndis_message;
 int netvsc_device_add(struct hv_device *device, void *additional_info);
 int netvsc_device_remove(struct hv_device *device);
 int netvsc_send(struct hv_device *device,
-		struct hv_netvsc_packet *packet);
+		struct hv_netvsc_packet *packet,
+		struct rndis_message *rndis_msg,
+		struct hv_page_buffer **page_buffer,
+		struct sk_buff *skb);
 void netvsc_linkstatus_callback(struct hv_device *device_obj,
 				struct rndis_message *resp);
-void netvsc_xmit_completion(void *context);
 int netvsc_recv_callback(struct hv_device *device_obj,
 			struct hv_netvsc_packet *packet,
-			struct ndis_tcp_ip_checksum_info *csum_info);
+			void **data,
+			struct ndis_tcp_ip_checksum_info *csum_info,
+			struct vmbus_channel *channel,
+			u16 vlan_tci);
 void netvsc_channel_cb(void *context);
 int rndis_filter_open(struct hv_device *dev);
 int rndis_filter_close(struct hv_device *dev);
@@ -205,12 +195,13 @@ int rndis_filter_device_add(struct hv_device *dev,
 			void *additional_info);
 void rndis_filter_device_remove(struct hv_device *dev);
 int rndis_filter_receive(struct hv_device *dev,
-			struct hv_netvsc_packet *pkt);
+			struct hv_netvsc_packet *pkt,
+			void **data,
+			struct vmbus_channel *channel);
 
 int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter);
 int rndis_filter_set_device_mac(struct hv_device *hdev, char *mac);
 
-
 #define NVSP_INVALID_PROTOCOL_VERSION	((u32)0xFFFFFFFF)
 
 #define NVSP_PROTOCOL_VERSION_1		2
@@ -633,7 +624,7 @@ struct nvsp_message {
 #define RNDIS_PKT_ALIGN_DEFAULT 8
 
 struct multi_send_data {
-	spinlock_t lock; /* protect struct multi_send_data */
+	struct sk_buff *skb; /* skb containing the pkt */
 	struct hv_netvsc_packet *pkt; /* netvsc pkt pending */
 	u32 count; /* counter of batched packets */
 };
@@ -644,11 +635,24 @@ struct netvsc_stats {
 	struct u64_stats_sync syncp;
 };
 
+struct netvsc_reconfig {
+	struct list_head list;
+	u32 event;
+};
+
 /* The context of the netvsc device  */
 struct net_device_context {
 	/* point back to our device context */
 	struct hv_device *device_ctx;
+	/* reconfigure work */
 	struct delayed_work dwork;
+	/* last reconfig time */
+	unsigned long last_reconfig;
+	/* reconfig events */
+	struct list_head reconfig_events;
+	/* list protection */
+	spinlock_t lock;
+
 	struct work_struct work;
 	u32 msg_enable; /* debug level */
 
@@ -1260,5 +1264,4 @@ struct rndis_message {
 #define TRANSPORT_INFO_IPV6_TCP ((INFO_IPV6 << 16) | INFO_TCP)
 #define TRANSPORT_INFO_IPV6_UDP ((INFO_IPV6 << 16) | INFO_UDP)
 
-
 #endif /* _HYPERV_NET_H */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 51e4c0fd0..ec313fc08 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -38,7 +38,6 @@ static struct netvsc_device *alloc_net_device(struct hv_device *device)
 {
 	struct netvsc_device *net_device;
 	struct net_device *ndev = hv_get_drvdata(device);
-	int i;
 
 	net_device = kzalloc(sizeof(struct netvsc_device), GFP_KERNEL);
 	if (!net_device)
@@ -58,9 +57,6 @@ static struct netvsc_device *alloc_net_device(struct hv_device *device)
 	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
 	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
 
-	for (i = 0; i < num_online_cpus(); i++)
-		spin_lock_init(&net_device->msd[i].lock);
-
 	hv_set_drvdata(device, net_device);
 	return net_device;
 }
@@ -610,6 +606,7 @@ static inline void netvsc_free_send_slot(struct netvsc_device *net_device,
 }
 
 static void netvsc_send_completion(struct netvsc_device *net_device,
+				   struct vmbus_channel *incoming_channel,
 				   struct hv_device *device,
 				   struct vmpacket_descriptor *packet)
 {
@@ -617,6 +614,7 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 	struct hv_netvsc_packet *nvsc_packet;
 	struct net_device *ndev;
 	u32 send_index;
+	struct sk_buff *skb;
 
 	ndev = net_device->ndev;
 
@@ -642,18 +640,17 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 		int queue_sends;
 
 		/* Get the send context */
-		nvsc_packet = (struct hv_netvsc_packet *)(unsigned long)
-			packet->trans_id;
+		skb = (struct sk_buff *)(unsigned long)packet->trans_id;
 
 		/* Notify the layer above us */
-		if (nvsc_packet) {
+		if (skb) {
+			nvsc_packet = (struct hv_netvsc_packet *) skb->cb;
 			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);
+			channel = incoming_channel;
+			dev_kfree_skb_any(skb);
 		}
 
 		num_outstanding_sends =
@@ -705,12 +702,17 @@ static u32 netvsc_get_next_send_section(struct netvsc_device *net_device)
 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 hv_netvsc_packet *packet,
+				   struct rndis_message *rndis_msg,
+				   struct hv_page_buffer **pb,
+				   struct sk_buff *skb)
 {
 	char *start = net_device->send_buf;
 	char *dest = start + (section_index * net_device->send_section_size)
 		     + pend_size;
 	int i;
+	bool is_data_pkt = (skb != NULL) ? true : false;
+	bool xmit_more = (skb != NULL) ? skb->xmit_more : false;
 	u32 msg_size = 0;
 	u32 padding = 0;
 	u32 remain = packet->total_data_buflen % net_device->pkt_align;
@@ -718,17 +720,17 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		packet->page_buf_cnt;
 
 	/* Add padding */
-	if (packet->is_data_pkt && packet->xmit_more && remain &&
+	if (is_data_pkt && xmit_more && remain &&
 	    !packet->cp_partial) {
 		padding = net_device->pkt_align - remain;
-		packet->rndis_msg->msg_len += padding;
+		rndis_msg->msg_len += padding;
 		packet->total_data_buflen += padding;
 	}
 
 	for (i = 0; i < page_count; 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;
+		char *src = phys_to_virt((*pb)[i].pfn << PAGE_SHIFT);
+		u32 offset = (*pb)[i].offset;
+		u32 len = (*pb)[i].len;
 
 		memcpy(dest, (src + offset), len);
 		msg_size += len;
@@ -745,19 +747,22 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 
 static inline int netvsc_send_pkt(
 	struct hv_netvsc_packet *packet,
-	struct netvsc_device *net_device)
+	struct netvsc_device *net_device,
+	struct hv_page_buffer **pb,
+	struct sk_buff *skb)
 {
 	struct nvsp_message nvmsg;
-	struct vmbus_channel *out_channel = packet->channel;
 	u16 q_idx = packet->q_idx;
+	struct vmbus_channel *out_channel = net_device->chn_table[q_idx];
 	struct net_device *ndev = net_device->ndev;
 	u64 req_id;
 	int ret;
 	struct hv_page_buffer *pgbuf;
 	u32 ring_avail = hv_ringbuf_avail_percent(&out_channel->outbound);
+	bool xmit_more = (skb != NULL) ? skb->xmit_more : false;
 
 	nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
-	if (packet->is_data_pkt) {
+	if (skb != NULL) {
 		/* 0 is RMC_DATA; */
 		nvmsg.msg.v1_msg.send_rndis_pkt.channel_type = 0;
 	} else {
@@ -773,10 +778,7 @@ static inline int netvsc_send_pkt(
 		nvmsg.msg.v1_msg.send_rndis_pkt.send_buf_section_size =
 			packet->total_data_buflen;
 
-	if (packet->send_completion)
-		req_id = (ulong)packet;
-	else
-		req_id = 0;
+	req_id = (ulong)skb;
 
 	if (out_channel->rescind)
 		return -ENODEV;
@@ -789,11 +791,11 @@ static inline int netvsc_send_pkt(
 	 * unnecessarily.
 	 */
 	if (ring_avail < (RING_AVAIL_PERCENT_LOWATER + 1))
-		packet->xmit_more = false;
+		xmit_more = false;
 
 	if (packet->page_buf_cnt) {
-		pgbuf = packet->cp_partial ? packet->page_buf +
-			packet->rmsg_pgcnt : packet->page_buf;
+		pgbuf = packet->cp_partial ? (*pb) +
+			packet->rmsg_pgcnt : (*pb);
 		ret = vmbus_sendpacket_pagebuffer_ctl(out_channel,
 						      pgbuf,
 						      packet->page_buf_cnt,
@@ -801,14 +803,14 @@ static inline int netvsc_send_pkt(
 						      sizeof(struct nvsp_message),
 						      req_id,
 						      VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
-						      !packet->xmit_more);
+						      !xmit_more);
 	} else {
 		ret = vmbus_sendpacket_ctl(out_channel, &nvmsg,
 					   sizeof(struct nvsp_message),
 					   req_id,
 					   VM_PKT_DATA_INBAND,
 					   VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
-					   !packet->xmit_more);
+					   !xmit_more);
 	}
 
 	if (ret == 0) {
@@ -839,8 +841,23 @@ static inline int netvsc_send_pkt(
 	return ret;
 }
 
+/* Move packet out of multi send data (msd), and clear msd */
+static inline void move_pkt_msd(struct hv_netvsc_packet **msd_send,
+				struct sk_buff **msd_skb,
+				struct multi_send_data *msdp)
+{
+	*msd_skb = msdp->skb;
+	*msd_send = msdp->pkt;
+	msdp->skb = NULL;
+	msdp->pkt = NULL;
+	msdp->count = 0;
+}
+
 int netvsc_send(struct hv_device *device,
-		struct hv_netvsc_packet *packet)
+		struct hv_netvsc_packet *packet,
+		struct rndis_message *rndis_msg,
+		struct hv_page_buffer **pb,
+		struct sk_buff *skb)
 {
 	struct netvsc_device *net_device;
 	int ret = 0, m_ret = 0;
@@ -848,33 +865,36 @@ int netvsc_send(struct hv_device *device,
 	u16 q_idx = packet->q_idx;
 	u32 pktlen = packet->total_data_buflen, msd_len = 0;
 	unsigned int section_index = NETVSC_INVALID_INDEX;
-	unsigned long flag;
 	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;
 
 	net_device = get_outbound_net_device(device);
 	if (!net_device)
 		return -ENODEV;
 
 	out_channel = net_device->chn_table[q_idx];
-	if (!out_channel) {
-		out_channel = device->channel;
-		q_idx = 0;
-		packet->q_idx = 0;
-	}
-	packet->channel = out_channel;
+
 	packet->send_buf_index = NETVSC_INVALID_INDEX;
 	packet->cp_partial = false;
 
+	/* 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;
+	}
+
 	msdp = &net_device->msd[q_idx];
 
 	/* batch packets in send buffer if possible */
-	spin_lock_irqsave(&msdp->lock, flag);
 	if (msdp->pkt)
 		msd_len = msdp->pkt->total_data_buflen;
 
-	try_batch = packet->is_data_pkt && msd_len > 0 && msdp->count <
+	try_batch = (skb != NULL) && msd_len > 0 && msdp->count <
 		    net_device->max_pkt;
 
 	if (try_batch && msd_len + pktlen + net_device->pkt_align <
@@ -886,21 +906,19 @@ int netvsc_send(struct hv_device *device,
 		section_index = msdp->pkt->send_buf_index;
 		packet->cp_partial = true;
 
-	} else if (packet->is_data_pkt && pktlen + net_device->pkt_align <
+	} else if ((skb != NULL) && pktlen + net_device->pkt_align <
 		   net_device->send_section_size) {
 		section_index = netvsc_get_next_send_section(net_device);
 		if (section_index != NETVSC_INVALID_INDEX) {
-				msd_send = msdp->pkt;
-				msdp->pkt = NULL;
-				msdp->count = 0;
-				msd_len = 0;
+			move_pkt_msd(&msd_send, &msd_skb, msdp);
+			msd_len = 0;
 		}
 	}
 
 	if (section_index != NETVSC_INVALID_INDEX) {
 		netvsc_copy_to_send_buf(net_device,
 					section_index, msd_len,
-					packet);
+					packet, rndis_msg, pb, skb);
 
 		packet->send_buf_index = section_index;
 
@@ -912,38 +930,37 @@ int netvsc_send(struct hv_device *device,
 			packet->total_data_buflen += msd_len;
 		}
 
-		if (msdp->pkt)
-			netvsc_xmit_completion(msdp->pkt);
+		if (msdp->skb)
+			dev_kfree_skb_any(msdp->skb);
 
-		if (packet->xmit_more && !packet->cp_partial) {
+		if (xmit_more && !packet->cp_partial) {
+			msdp->skb = skb;
 			msdp->pkt = packet;
 			msdp->count++;
 		} else {
 			cur_send = packet;
+			msdp->skb = NULL;
 			msdp->pkt = NULL;
 			msdp->count = 0;
 		}
 	} else {
-		msd_send = msdp->pkt;
-		msdp->pkt = NULL;
-		msdp->count = 0;
+		move_pkt_msd(&msd_send, &msd_skb, msdp);
 		cur_send = packet;
 	}
 
-	spin_unlock_irqrestore(&msdp->lock, flag);
-
 	if (msd_send) {
-		m_ret = netvsc_send_pkt(msd_send, net_device);
+		m_ret = netvsc_send_pkt(msd_send, net_device, NULL, msd_skb);
 
 		if (m_ret != 0) {
 			netvsc_free_send_slot(net_device,
 					      msd_send->send_buf_index);
-			netvsc_xmit_completion(msd_send);
+			dev_kfree_skb_any(msd_skb);
 		}
 	}
 
+send_now:
 	if (cur_send)
-		ret = netvsc_send_pkt(cur_send, net_device);
+		ret = netvsc_send_pkt(cur_send, net_device, pb, skb);
 
 	if (ret != 0 && section_index != NETVSC_INVALID_INDEX)
 		netvsc_free_send_slot(net_device, section_index);
@@ -1009,6 +1026,7 @@ static void netvsc_receive(struct netvsc_device *net_device,
 	int i;
 	int count = 0;
 	struct net_device *ndev;
+	void *data;
 
 	ndev = net_device->ndev;
 
@@ -1043,22 +1061,19 @@ static void netvsc_receive(struct netvsc_device *net_device,
 	}
 
 	count = vmxferpage_packet->range_cnt;
-	netvsc_packet->channel = channel;
 
 	/* Each range represents 1 RNDIS pkt that contains 1 ethernet frame */
 	for (i = 0; i < count; i++) {
 		/* Initialize the netvsc packet */
-		netvsc_packet->status = NVSP_STAT_SUCCESS;
-		netvsc_packet->data = (void *)((unsigned long)net_device->
+		data = (void *)((unsigned long)net_device->
 			recv_buf + vmxferpage_packet->ranges[i].byte_offset);
 		netvsc_packet->total_data_buflen =
 					vmxferpage_packet->ranges[i].byte_count;
 
 		/* Pass it to the upper layer */
-		rndis_filter_receive(device, netvsc_packet);
+		status = rndis_filter_receive(device, netvsc_packet, &data,
+					      channel);
 
-		if (netvsc_packet->status != NVSP_STAT_SUCCESS)
-			status = NVSP_STAT_FAIL;
 	}
 
 	netvsc_send_recv_completion(device, channel, net_device,
@@ -1150,6 +1165,7 @@ void netvsc_channel_cb(void *context)
 				switch (desc->type) {
 				case VM_PKT_COMP:
 					netvsc_send_completion(net_device,
+								channel,
 								device, desc);
 					break;
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 409b48e1e..98e34fee4 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -42,6 +42,7 @@
 
 
 #define RING_SIZE_MIN 64
+#define LINKCHANGE_INT (2 * HZ)
 static int ring_size = 128;
 module_param(ring_size, int, S_IRUGO);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
@@ -195,65 +196,6 @@ 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, void *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 = ((u8 *)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 flow_keys flow;
-	int data_len;
-
-	if (!skb_flow_dissect_flow_keys(skb, &flow, 0) ||
-	    !(flow.basic.n_proto == htons(ETH_P_IP) ||
-	      flow.basic.n_proto == htons(ETH_P_IPV6)))
-		return false;
-
-	if (flow.basic.ip_proto == IPPROTO_TCP)
-		data_len = 12;
-	else
-		data_len = 8;
-
-	*hash = comp_hash(netvsc_hash_key, HASH_KEYLEN, &flow, data_len);
-
-	return true;
-}
-
 static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 			void *accel_priv, select_queue_fallback_t fallback)
 {
@@ -266,23 +208,14 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	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;
-}
+	hash = skb_get_hash(skb);
+	q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
+		ndev->real_num_tx_queues;
 
-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->send_completion_tid;
+	if (!nvsc_dev->chn_table[q_idx])
+		q_idx = 0;
 
-	if (skb)
-		dev_kfree_skb_any(skb);
+	return q_idx;
 }
 
 static u32 fill_pg_buf(struct page *page, u32 offset, u32 len,
@@ -320,9 +253,10 @@ static u32 fill_pg_buf(struct page *page, u32 offset, u32 len,
 }
 
 static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
-			   struct hv_netvsc_packet *packet)
+			   struct hv_netvsc_packet *packet,
+			   struct hv_page_buffer **page_buf)
 {
-	struct hv_page_buffer *pb = packet->page_buf;
+	struct hv_page_buffer *pb = *page_buf;
 	u32 slots_used = 0;
 	char *data = skb->data;
 	int frags = skb_shinfo(skb)->nr_frags;
@@ -432,8 +366,8 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	u32 net_trans_info;
 	u32 hash;
 	u32 skb_length;
-	u32 pkt_sz;
 	struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT];
+	struct hv_page_buffer *pb = page_buf;
 	struct netvsc_stats *tx_stats = this_cpu_ptr(net_device_ctx->tx_stats);
 
 	/* We will atmost need two pages to describe the rndis
@@ -460,42 +394,34 @@ check_size:
 		goto check_size;
 	}
 
-	pkt_sz = sizeof(struct hv_netvsc_packet) + RNDIS_AND_PPI_SIZE;
-
-	ret = skb_cow_head(skb, pkt_sz);
+	/*
+	 * Place the rndis header in the skb head room and
+	 * the skb->cb will be used for hv_netvsc_packet
+	 * structure.
+	 */
+	ret = skb_cow_head(skb, RNDIS_AND_PPI_SIZE);
 	if (ret) {
 		netdev_err(net, "unable to alloc hv_netvsc_packet\n");
 		ret = -ENOMEM;
 		goto drop;
 	}
-	/* Use the headroom for building up the packet */
-	packet = (struct hv_netvsc_packet *)skb->head;
-
-	packet->status = 0;
-	packet->xmit_more = skb->xmit_more;
+	/* Use the skb control buffer for building up the packet */
+	BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) >
+			FIELD_SIZEOF(struct sk_buff, cb));
+	packet = (struct hv_netvsc_packet *)skb->cb;
 
-	packet->vlan_tci = skb->vlan_tci;
-	packet->page_buf = page_buf;
 
 	packet->q_idx = skb_get_queue_mapping(skb);
 
-	packet->is_data_pkt = true;
 	packet->total_data_buflen = skb->len;
 
-	packet->rndis_msg = (struct rndis_message *)((unsigned long)packet +
-				sizeof(struct hv_netvsc_packet));
+	rndis_msg = (struct rndis_message *)skb->head;
 
-	memset(packet->rndis_msg, 0, RNDIS_AND_PPI_SIZE);
+	memset(rndis_msg, 0, RNDIS_AND_PPI_SIZE);
 
-	/* Set the completion routine */
-	packet->send_completion = netvsc_xmit_completion;
-	packet->send_completion_ctx = packet;
-	packet->send_completion_tid = (unsigned long)skb;
-
-	isvlan = packet->vlan_tci & VLAN_TAG_PRESENT;
+	isvlan = skb->vlan_tci & VLAN_TAG_PRESENT;
 
 	/* Add the rndis header */
-	rndis_msg = packet->rndis_msg;
 	rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
 	rndis_msg->msg_len = packet->total_data_buflen;
 	rndis_pkt = &rndis_msg->msg.pkt;
@@ -521,8 +447,8 @@ check_size:
 					IEEE_8021Q_INFO);
 		vlan = (struct ndis_pkt_8021q_info *)((void *)ppi +
 						ppi->ppi_offset);
-		vlan->vlanid = packet->vlan_tci & VLAN_VID_MASK;
-		vlan->pri = (packet->vlan_tci & VLAN_PRIO_MASK) >>
+		vlan->vlanid = skb->vlan_tci & VLAN_VID_MASK;
+		vlan->pri = (skb->vlan_tci & VLAN_PRIO_MASK) >>
 				VLAN_PRIO_SHIFT;
 	}
 
@@ -617,9 +543,10 @@ do_send:
 	rndis_msg->msg_len += rndis_msg_size;
 	packet->total_data_buflen = rndis_msg->msg_len;
 	packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size,
-					       skb, packet);
+					       skb, packet, &pb);
 
-	ret = netvsc_send(net_device_ctx->device_ctx, packet);
+	ret = netvsc_send(net_device_ctx->device_ctx, packet,
+			  rndis_msg, &pb, skb);
 
 drop:
 	if (ret == 0) {
@@ -647,37 +574,33 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj,
 	struct net_device *net;
 	struct net_device_context *ndev_ctx;
 	struct netvsc_device *net_device;
-	struct rndis_device *rdev;
+	struct netvsc_reconfig *event;
+	unsigned long flags;
 
-	net_device = hv_get_drvdata(device_obj);
-	rdev = net_device->extension;
-
-	switch (indicate->status) {
-	case RNDIS_STATUS_MEDIA_CONNECT:
-		rdev->link_state = false;
-		break;
-	case RNDIS_STATUS_MEDIA_DISCONNECT:
-		rdev->link_state = true;
-		break;
-	case RNDIS_STATUS_NETWORK_CHANGE:
-		rdev->link_change = true;
-		break;
-	default:
+	/* Handle link change statuses only */
+	if (indicate->status != RNDIS_STATUS_NETWORK_CHANGE &&
+	    indicate->status != RNDIS_STATUS_MEDIA_CONNECT &&
+	    indicate->status != RNDIS_STATUS_MEDIA_DISCONNECT)
 		return;
-	}
 
+	net_device = hv_get_drvdata(device_obj);
 	net = net_device->ndev;
 
 	if (!net || net->reg_state != NETREG_REGISTERED)
 		return;
 
 	ndev_ctx = netdev_priv(net);
-	if (!rdev->link_state) {
-		schedule_delayed_work(&ndev_ctx->dwork, 0);
-		schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20));
-	} else {
-		schedule_delayed_work(&ndev_ctx->dwork, 0);
-	}
+
+	event = kzalloc(sizeof(*event), GFP_ATOMIC);
+	if (!event)
+		return;
+	event->event = indicate->status;
+
+	spin_lock_irqsave(&ndev_ctx->lock, flags);
+	list_add_tail(&event->list, &ndev_ctx->reconfig_events);
+	spin_unlock_irqrestore(&ndev_ctx->lock, flags);
+
+	schedule_delayed_work(&ndev_ctx->dwork, 0);
 }
 
 /*
@@ -686,7 +609,10 @@ 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 **data,
+				struct ndis_tcp_ip_checksum_info *csum_info,
+				struct vmbus_channel *channel,
+				u16 vlan_tci)
 {
 	struct net_device *net;
 	struct net_device_context *net_device_ctx;
@@ -695,8 +621,7 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 
 	net = ((struct netvsc_device *)hv_get_drvdata(device_obj))->ndev;
 	if (!net || net->reg_state != NETREG_REGISTERED) {
-		packet->status = NVSP_STAT_FAIL;
-		return 0;
+		return NVSP_STAT_FAIL;
 	}
 	net_device_ctx = netdev_priv(net);
 	rx_stats = this_cpu_ptr(net_device_ctx->rx_stats);
@@ -705,15 +630,14 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	skb = netdev_alloc_skb_ip_align(net, packet->total_data_buflen);
 	if (unlikely(!skb)) {
 		++net->stats.rx_dropped;
-		packet->status = NVSP_STAT_FAIL;
-		return 0;
+		return NVSP_STAT_FAIL;
 	}
 
 	/*
 	 * Copy to skb. This copy is needed here since the memory pointed by
 	 * hv_netvsc_packet cannot be deallocated
 	 */
-	memcpy(skb_put(skb, packet->total_data_buflen), packet->data,
+	memcpy(skb_put(skb, packet->total_data_buflen), *data,
 		packet->total_data_buflen);
 
 	skb->protocol = eth_type_trans(skb, net);
@@ -728,11 +652,11 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 			skb->ip_summed = CHECKSUM_NONE;
 	}
 
-	if (packet->vlan_tci & VLAN_TAG_PRESENT)
+	if (vlan_tci & VLAN_TAG_PRESENT)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
-				       packet->vlan_tci);
+				       vlan_tci);
 
-	skb_record_rx_queue(skb, packet->channel->
+	skb_record_rx_queue(skb, channel->
 			    offermsg.offer.sub_channel_index);
 
 	u64_stats_update_begin(&rx_stats->syncp);
@@ -1009,12 +933,9 @@ static const struct net_device_ops device_ops = {
 };
 
 /*
- * Send GARP packet to network peers after migrations.
- * After Quick Migration, the network is not immediately operational in the
- * current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, add
- * another netif_notify_peers() into a delayed work, otherwise GARP packet
- * will not be sent after quick migration, and cause network disconnection.
- * Also, we update the carrier status here.
+ * Handle link status changes. For RNDIS_STATUS_NETWORK_CHANGE emulate link
+ * down/up sequence. In case of RNDIS_STATUS_MEDIA_CONNECT when carrier is
+ * present send GARP packet to network peers with netif_notify_peers().
  */
 static void netvsc_link_change(struct work_struct *w)
 {
@@ -1022,36 +943,89 @@ static void netvsc_link_change(struct work_struct *w)
 	struct net_device *net;
 	struct netvsc_device *net_device;
 	struct rndis_device *rdev;
-	bool notify, refresh = false;
-	char *argv[] = { "/etc/init.d/network", "restart", NULL };
-	char *envp[] = { "HOME=/", "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL };
-
-	rtnl_lock();
+	struct netvsc_reconfig *event = NULL;
+	bool notify = false, reschedule = false;
+	unsigned long flags, next_reconfig, delay;
 
 	ndev_ctx = container_of(w, struct net_device_context, dwork.work);
 	net_device = hv_get_drvdata(ndev_ctx->device_ctx);
 	rdev = net_device->extension;
 	net = net_device->ndev;
 
-	if (rdev->link_state) {
-		netif_carrier_off(net);
-		notify = false;
-	} else {
-		netif_carrier_on(net);
-		notify = true;
-		if (rdev->link_change) {
-			rdev->link_change = false;
-			refresh = true;
+	next_reconfig = ndev_ctx->last_reconfig + LINKCHANGE_INT;
+	if (time_is_after_jiffies(next_reconfig)) {
+		/* link_watch only sends one notification with current state
+		 * per second, avoid doing reconfig more frequently. Handle
+		 * wrap around.
+		 */
+		delay = next_reconfig - jiffies;
+		delay = delay < LINKCHANGE_INT ? delay : LINKCHANGE_INT;
+		schedule_delayed_work(&ndev_ctx->dwork, delay);
+		return;
+	}
+	ndev_ctx->last_reconfig = jiffies;
+
+	spin_lock_irqsave(&ndev_ctx->lock, flags);
+	if (!list_empty(&ndev_ctx->reconfig_events)) {
+		event = list_first_entry(&ndev_ctx->reconfig_events,
+					 struct netvsc_reconfig, list);
+		list_del(&event->list);
+		reschedule = !list_empty(&ndev_ctx->reconfig_events);
+	}
+	spin_unlock_irqrestore(&ndev_ctx->lock, flags);
+
+	if (!event)
+		return;
+
+	rtnl_lock();
+
+	switch (event->event) {
+		/* Only the following events are possible due to the check in
+		 * netvsc_linkstatus_callback()
+		 */
+	case RNDIS_STATUS_MEDIA_CONNECT:
+		if (rdev->link_state) {
+			rdev->link_state = false;
+			netif_carrier_on(net);
+			netif_tx_wake_all_queues(net);
+		} else {
+			notify = true;
+		}
+		kfree(event);
+		break;
+	case RNDIS_STATUS_MEDIA_DISCONNECT:
+		if (!rdev->link_state) {
+			rdev->link_state = true;
+			netif_carrier_off(net);
+			netif_tx_stop_all_queues(net);
+		}
+		kfree(event);
+		break;
+	case RNDIS_STATUS_NETWORK_CHANGE:
+		/* Only makes sense if carrier is present */
+		if (!rdev->link_state) {
+			rdev->link_state = true;
+			netif_carrier_off(net);
+			netif_tx_stop_all_queues(net);
+			event->event = RNDIS_STATUS_MEDIA_CONNECT;
+			spin_lock_irqsave(&ndev_ctx->lock, flags);
+			list_add_tail(&event->list, &ndev_ctx->reconfig_events);
+			spin_unlock_irqrestore(&ndev_ctx->lock, flags);
+			reschedule = true;
 		}
+		break;
 	}
 
 	rtnl_unlock();
 
-	if (refresh)
-		call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
-
 	if (notify)
 		netdev_notify_peers(net);
+
+	/* link_watch only sends one notification with current state per
+	 * second, handle next reconfig event in 2 seconds.
+	 */
+	if (reschedule)
+		schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);
 }
 
 static void netvsc_free_netdev(struct net_device *netdev)
@@ -1071,16 +1045,12 @@ static int netvsc_probe(struct hv_device *dev,
 	struct netvsc_device_info device_info;
 	struct netvsc_device *nvdev;
 	int ret;
-	u32 max_needed_headroom;
 
 	net = alloc_etherdev_mq(sizeof(struct net_device_context),
 				num_online_cpus());
 	if (!net)
 		return -ENOMEM;
 
-	max_needed_headroom = sizeof(struct hv_netvsc_packet) +
-			      RNDIS_AND_PPI_SIZE;
-
 	netif_carrier_off(net);
 
 	net_device_ctx = netdev_priv(net);
@@ -1106,6 +1076,9 @@ static int netvsc_probe(struct hv_device *dev,
 	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
 	INIT_WORK(&net_device_ctx->work, do_set_multicast);
 
+	spin_lock_init(&net_device_ctx->lock);
+	INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
+
 	net->netdev_ops = &device_ops;
 
 	net->hw_features = NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_IP_CSUM |
@@ -1116,12 +1089,8 @@ static int netvsc_probe(struct hv_device *dev,
 	net->ethtool_ops = &ethtool_ops;
 	SET_NETDEV_DEV(net, &dev->device);
 
-	/*
-	 * Request additional head room in the skb.
-	 * We will use this space to build the rndis
-	 * heaser and other state we need to maintain.
-	 */
-	net->needed_headroom = max_needed_headroom;
+	/* We always need headroom for rndis header */
+	net->needed_headroom = RNDIS_AND_PPI_SIZE;
 
 	/* Notify the netvsc driver of the new device */
 	memset(&device_info, 0, sizeof(device_info));
@@ -1145,8 +1114,6 @@ static int netvsc_probe(struct hv_device *dev,
 		pr_err("Unable to register netdev.\n");
 		rndis_filter_device_remove(dev);
 		netvsc_free_netdev(net);
-	} else {
-		schedule_delayed_work(&net_device_ctx->dwork, 0);
 	}
 
 	return ret;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 5931a799a..a37bbda37 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -210,37 +210,33 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 	int ret;
 	struct hv_netvsc_packet *packet;
 	struct hv_page_buffer page_buf[2];
+	struct hv_page_buffer *pb = page_buf;
 
 	/* Setup the packet to send it */
 	packet = &req->pkt;
 
-	packet->is_data_pkt = false;
 	packet->total_data_buflen = req->request_msg.msg_len;
 	packet->page_buf_cnt = 1;
-	packet->page_buf = page_buf;
 
-	packet->page_buf[0].pfn = virt_to_phys(&req->request_msg) >>
+	pb[0].pfn = virt_to_phys(&req->request_msg) >>
 					PAGE_SHIFT;
-	packet->page_buf[0].len = req->request_msg.msg_len;
-	packet->page_buf[0].offset =
+	pb[0].len = req->request_msg.msg_len;
+	pb[0].offset =
 		(unsigned long)&req->request_msg & (PAGE_SIZE - 1);
 
 	/* Add one page_buf when request_msg crossing page boundary */
-	if (packet->page_buf[0].offset + packet->page_buf[0].len > PAGE_SIZE) {
+	if (pb[0].offset + pb[0].len > PAGE_SIZE) {
 		packet->page_buf_cnt++;
-		packet->page_buf[0].len = PAGE_SIZE -
-			packet->page_buf[0].offset;
-		packet->page_buf[1].pfn = virt_to_phys((void *)&req->request_msg
-			+ packet->page_buf[0].len) >> PAGE_SHIFT;
-		packet->page_buf[1].offset = 0;
-		packet->page_buf[1].len = req->request_msg.msg_len -
-			packet->page_buf[0].len;
+		pb[0].len = PAGE_SIZE -
+			pb[0].offset;
+		pb[1].pfn = virt_to_phys((void *)&req->request_msg
+			+ pb[0].len) >> PAGE_SHIFT;
+		pb[1].offset = 0;
+		pb[1].len = req->request_msg.msg_len -
+			pb[0].len;
 	}
 
-	packet->send_completion = NULL;
-	packet->xmit_more = false;
-
-	ret = netvsc_send(dev->net_dev->dev, packet);
+	ret = netvsc_send(dev->net_dev->dev, packet, NULL, &pb, NULL);
 	return ret;
 }
 
@@ -348,14 +344,17 @@ static inline void *rndis_get_ppi(struct rndis_packet *rpkt, u32 type)
 	return NULL;
 }
 
-static void rndis_filter_receive_data(struct rndis_device *dev,
+static int rndis_filter_receive_data(struct rndis_device *dev,
 				   struct rndis_message *msg,
-				   struct hv_netvsc_packet *pkt)
+				   struct hv_netvsc_packet *pkt,
+				   void **data,
+				   struct vmbus_channel *channel)
 {
 	struct rndis_packet *rndis_pkt;
 	u32 data_offset;
 	struct ndis_pkt_8021q_info *vlan;
 	struct ndis_tcp_ip_checksum_info *csum_info;
+	u16 vlan_tci = 0;
 
 	rndis_pkt = &msg->msg.pkt;
 
@@ -373,7 +372,7 @@ static void rndis_filter_receive_data(struct rndis_device *dev,
 			   "overflow detected (got %u, min %u)"
 			   "...dropping this message!\n",
 			   pkt->total_data_buflen, rndis_pkt->data_len);
-		return;
+		return NVSP_STAT_FAIL;
 	}
 
 	/*
@@ -382,22 +381,23 @@ static void rndis_filter_receive_data(struct rndis_device *dev,
 	 * the data packet to the stack, without the rndis trailer padding
 	 */
 	pkt->total_data_buflen = rndis_pkt->data_len;
-	pkt->data = (void *)((unsigned long)pkt->data + data_offset);
+	*data = (void *)((unsigned long)(*data) + data_offset);
 
 	vlan = rndis_get_ppi(rndis_pkt, IEEE_8021Q_INFO);
 	if (vlan) {
-		pkt->vlan_tci = VLAN_TAG_PRESENT | vlan->vlanid |
+		vlan_tci = VLAN_TAG_PRESENT | vlan->vlanid |
 			(vlan->pri << VLAN_PRIO_SHIFT);
-	} else {
-		pkt->vlan_tci = 0;
 	}
 
 	csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO);
-	netvsc_recv_callback(dev->net_dev->dev, pkt, csum_info);
+	return netvsc_recv_callback(dev->net_dev->dev, pkt, data,
+				    csum_info, channel, vlan_tci);
 }
 
 int rndis_filter_receive(struct hv_device *dev,
-				struct hv_netvsc_packet	*pkt)
+				struct hv_netvsc_packet	*pkt,
+				void **data,
+				struct vmbus_channel *channel)
 {
 	struct netvsc_device *net_dev = hv_get_drvdata(dev);
 	struct rndis_device *rndis_dev;
@@ -406,7 +406,7 @@ int rndis_filter_receive(struct hv_device *dev,
 	int ret = 0;
 
 	if (!net_dev) {
-		ret = -EINVAL;
+		ret = NVSP_STAT_FAIL;
 		goto exit;
 	}
 
@@ -416,7 +416,7 @@ int rndis_filter_receive(struct hv_device *dev,
 	if (!net_dev->extension) {
 		netdev_err(ndev, "got rndis message but no rndis device - "
 			  "dropping this message!\n");
-		ret = -ENODEV;
+		ret = NVSP_STAT_FAIL;
 		goto exit;
 	}
 
@@ -424,11 +424,11 @@ int rndis_filter_receive(struct hv_device *dev,
 	if (rndis_dev->state == RNDIS_DEV_UNINITIALIZED) {
 		netdev_err(ndev, "got rndis message but rndis device "
 			   "uninitialized...dropping this message!\n");
-		ret = -ENODEV;
+		ret = NVSP_STAT_FAIL;
 		goto exit;
 	}
 
-	rndis_msg = pkt->data;
+	rndis_msg = *data;
 
 	if (netif_msg_rx_err(net_dev->nd_ctx))
 		dump_rndis_message(dev, rndis_msg);
@@ -436,7 +436,8 @@ int rndis_filter_receive(struct hv_device *dev,
 	switch (rndis_msg->ndis_msg_type) {
 	case RNDIS_MSG_PACKET:
 		/* data msg */
-		rndis_filter_receive_data(rndis_dev, rndis_msg, pkt);
+		ret = rndis_filter_receive_data(rndis_dev, rndis_msg, pkt,
+						data, channel);
 		break;
 
 	case RNDIS_MSG_INIT_C:
@@ -459,9 +460,6 @@ int rndis_filter_receive(struct hv_device *dev,
 	}
 
 exit:
-	if (ret != 0)
-		pkt->status = NVSP_STAT_FAIL;
-
 	return ret;
 }