4 files changed, 158 insertions, 74 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 5176be76ca7d..4958bb6b7376 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];
 };
 
 
@@ -686,6 +686,8 @@ struct netvsc_ethtool_stats {
 	unsigned long tx_busy;
 	unsigned long tx_send_full;
 	unsigned long rx_comp_busy;
+	unsigned long stop_queue;
+	unsigned long wake_queue;
 };
 
 struct netvsc_vf_pcpu_stats {
@@ -702,6 +704,14 @@ struct netvsc_reconfig {
 	u32 event;
 };
 
+/* L4 hash bits for different protocols */
+#define HV_TCP4_L4HASH 1
+#define HV_TCP6_L4HASH 2
+#define HV_UDP4_L4HASH 4
+#define HV_UDP6_L4HASH 8
+#define HV_DEFAULT_L4HASH (HV_TCP4_L4HASH | HV_TCP6_L4HASH | HV_UDP4_L4HASH | \
+			   HV_UDP6_L4HASH)
+
 /* The context of the netvsc device  */
 struct net_device_context {
 	/* point back to our device context */
@@ -721,13 +731,12 @@ 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;
-	bool udp6_l4_hash;
 	u8 duplex;
 	u32 speed;
+	u32 l4_hash; /* L4 hash settings */
 	struct netvsc_ethtool_stats eth_stats;
 
 	/* State to manage the associated VF interface. */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 8d5077fb0492..bfc79698b8f4 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -100,12 +100,11 @@ 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_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);
 	int ret;
 
 	/*
@@ -148,28 +147,6 @@ 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;
-	}
-
 	/* Deal with the send buffer we may have setup.
 	 * If we got a  send section size, it means we received a
 	 * NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE msg (ie sent
@@ -210,7 +187,35 @@ 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_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;
+	}
+
+	if (net_device->recv_buf) {
+		/* Free up the receive buffer */
+		vfree(net_device->recv_buf);
+		net_device->recv_buf = NULL;
+	}
+
 	if (net_device->send_buf_gpadl_handle) {
 		ret = vmbus_teardown_gpadl(device->channel,
 					   net_device->send_buf_gpadl_handle);
@@ -420,7 +425,8 @@ static int netvsc_init_buf(struct hv_device *device,
 	goto exit;
 
 cleanup:
-	netvsc_destroy_buf(device);
+	netvsc_revoke_buf(device, net_device);
+	netvsc_teardown_gpadl(device, net_device);
 
 exit:
 	return ret;
@@ -484,7 +490,7 @@ static int netvsc_connect_vsp(struct hv_device *device,
 			      struct netvsc_device *net_device,
 			      const struct netvsc_device_info *device_info)
 {
-	const u32 ver_list[] = {
+	static const u32 ver_list[] = {
 		NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2,
 		NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5
 	};
@@ -539,11 +545,6 @@ 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
  */
@@ -557,7 +558,7 @@ void netvsc_device_remove(struct hv_device *device)
 
 	cancel_work_sync(&net_device->subchan_work);
 
-	netvsc_disconnect_vsp(device);
+	netvsc_revoke_buf(device, net_device);
 
 	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
 
@@ -570,6 +571,8 @@ void netvsc_device_remove(struct hv_device *device)
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
+	netvsc_teardown_gpadl(device, net_device);
+
 	/* And dissassociate NAPI context from device */
 	for (i = 0; i < net_device->num_chn; i++)
 		netif_napi_del(&net_device->chan_table[i].napi);
@@ -609,6 +612,7 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 {
 	struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
 	struct net_device *ndev = hv_get_drvdata(device);
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	struct vmbus_channel *channel = device->channel;
 	u16 q_idx = 0;
 	int queue_sends;
@@ -643,8 +647,10 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device,
 
 	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))
+	     queue_sends < 1)) {
 		netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx));
+		ndev_ctx->eth_stats.wake_queue++;
+	}
 }
 
 static void netvsc_send_completion(struct netvsc_device *net_device,
@@ -749,6 +755,7 @@ static inline int netvsc_send_pkt(
 		&net_device->chan_table[packet->q_idx];
 	struct vmbus_channel *out_channel = nvchan->channel;
 	struct net_device *ndev = hv_get_drvdata(device);
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	struct netdev_queue *txq = netdev_get_tx_queue(ndev, packet->q_idx);
 	u64 req_id;
 	int ret;
@@ -789,12 +796,16 @@ static inline int netvsc_send_pkt(
 	if (ret == 0) {
 		atomic_inc_return(&nvchan->queue_sends);
 
-		if (ring_avail < RING_AVAIL_PERCENT_LOWATER)
+		if (ring_avail < RING_AVAIL_PERCENT_LOWATER) {
 			netif_tx_stop_queue(txq);
+			ndev_ctx->eth_stats.stop_queue++;
+		}
 	} else if (ret == -EAGAIN) {
 		netif_tx_stop_queue(txq);
+		ndev_ctx->eth_stats.stop_queue++;
 		if (atomic_read(&nvchan->queue_sends) < 1) {
 			netif_tx_wake_queue(txq);
+			ndev_ctx->eth_stats.wake_queue++;
 			ret = -ENOSPC;
 		}
 	} else {
@@ -1102,7 +1113,7 @@ 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,
@@ -1247,6 +1258,9 @@ 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
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index a32ae02e1b6c..da216ca4f2b2 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -203,7 +203,7 @@ static inline u32 netvsc_get_hash(
 	const struct net_device_context *ndc)
 {
 	struct flow_keys flow;
-	u32 hash;
+	u32 hash, pkt_proto = 0;
 	static u32 hashrnd __read_mostly;
 
 	net_get_random_once(&hashrnd, sizeof(hashrnd));
@@ -211,11 +211,25 @@ static inline u32 netvsc_get_hash(
 	if (!skb_flow_dissect_flow_keys(skb, &flow, 0))
 		return 0;
 
-	if (flow.basic.ip_proto == IPPROTO_TCP ||
-	    (flow.basic.ip_proto == IPPROTO_UDP &&
-	     ((flow.basic.n_proto == htons(ETH_P_IP) && ndc->udp4_l4_hash) ||
-	      (flow.basic.n_proto == htons(ETH_P_IPV6) &&
-	       ndc->udp6_l4_hash)))) {
+	switch (flow.basic.ip_proto) {
+	case IPPROTO_TCP:
+		if (flow.basic.n_proto == htons(ETH_P_IP))
+			pkt_proto = HV_TCP4_L4HASH;
+		else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+			pkt_proto = HV_TCP6_L4HASH;
+
+		break;
+
+	case IPPROTO_UDP:
+		if (flow.basic.n_proto == htons(ETH_P_IP))
+			pkt_proto = HV_UDP4_L4HASH;
+		else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+			pkt_proto = HV_UDP6_L4HASH;
+
+		break;
+	}
+
+	if (pkt_proto & ndc->l4_hash) {
 		return skb_get_hash(skb);
 	} else {
 		if (flow.basic.n_proto == htons(ETH_P_IP))
@@ -238,8 +252,8 @@ 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 &&
@@ -898,8 +912,7 @@ static void netvsc_init_settings(struct net_device *dev)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 
-	ndc->udp4_l4_hash = true;
-	ndc->udp6_l4_hash = true;
+	ndc->l4_hash = HV_DEFAULT_L4HASH;
 
 	ndc->speed = SPEED_UNKNOWN;
 	ndc->duplex = DUPLEX_FULL;
@@ -1126,6 +1139,8 @@ static const struct {
 	{ "tx_busy",	  offsetof(struct netvsc_ethtool_stats, tx_busy) },
 	{ "tx_send_full", offsetof(struct netvsc_ethtool_stats, tx_send_full) },
 	{ "rx_comp_busy", offsetof(struct netvsc_ethtool_stats, rx_comp_busy) },
+	{ "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
+	{ "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
 }, vf_stats[] = {
 	{ "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
 	{ "vf_rx_bytes",   offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
@@ -1243,23 +1258,32 @@ static int
 netvsc_get_rss_hash_opts(struct net_device_context *ndc,
 			 struct ethtool_rxnfc *info)
 {
+	const u32 l4_flag = RXH_L4_B_0_1 | RXH_L4_B_2_3;
+
 	info->data = RXH_IP_SRC | RXH_IP_DST;
 
 	switch (info->flow_type) {
 	case TCP_V4_FLOW:
+		if (ndc->l4_hash & HV_TCP4_L4HASH)
+			info->data |= l4_flag;
+
+		break;
+
 	case TCP_V6_FLOW:
-		info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		if (ndc->l4_hash & HV_TCP6_L4HASH)
+			info->data |= l4_flag;
+
 		break;
 
 	case UDP_V4_FLOW:
-		if (ndc->udp4_l4_hash)
-			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		if (ndc->l4_hash & HV_UDP4_L4HASH)
+			info->data |= l4_flag;
 
 		break;
 
 	case UDP_V6_FLOW:
-		if (ndc->udp6_l4_hash)
-			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		if (ndc->l4_hash & HV_UDP6_L4HASH)
+			info->data |= l4_flag;
 
 		break;
 
@@ -1300,23 +1324,51 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc,
 {
 	if (info->data == (RXH_IP_SRC | RXH_IP_DST |
 			   RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		if (info->flow_type == UDP_V4_FLOW)
-			ndc->udp4_l4_hash = true;
-		else if (info->flow_type == UDP_V6_FLOW)
-			ndc->udp6_l4_hash = true;
-		else
+		switch (info->flow_type) {
+		case TCP_V4_FLOW:
+			ndc->l4_hash |= HV_TCP4_L4HASH;
+			break;
+
+		case TCP_V6_FLOW:
+			ndc->l4_hash |= HV_TCP6_L4HASH;
+			break;
+
+		case UDP_V4_FLOW:
+			ndc->l4_hash |= HV_UDP4_L4HASH;
+			break;
+
+		case UDP_V6_FLOW:
+			ndc->l4_hash |= HV_UDP6_L4HASH;
+			break;
+
+		default:
 			return -EOPNOTSUPP;
+		}
 
 		return 0;
 	}
 
 	if (info->data == (RXH_IP_SRC | RXH_IP_DST)) {
-		if (info->flow_type == UDP_V4_FLOW)
-			ndc->udp4_l4_hash = false;
-		else if (info->flow_type == UDP_V6_FLOW)
-			ndc->udp6_l4_hash = false;
-		else
+		switch (info->flow_type) {
+		case TCP_V4_FLOW:
+			ndc->l4_hash &= ~HV_TCP4_L4HASH;
+			break;
+
+		case TCP_V6_FLOW:
+			ndc->l4_hash &= ~HV_TCP6_L4HASH;
+			break;
+
+		case UDP_V4_FLOW:
+			ndc->l4_hash &= ~HV_UDP4_L4HASH;
+			break;
+
+		case UDP_V6_FLOW:
+			ndc->l4_hash &= ~HV_UDP6_L4HASH;
+			break;
+
+		default:
 			return -EOPNOTSUPP;
+		}
 
 		return 0;
 	}
@@ -1382,7 +1434,7 @@ 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)
@@ -1412,7 +1464,7 @@ 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) {
@@ -1746,7 +1798,7 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto rx_handler_failed;
 	}
 
-	ret = netdev_upper_dev_link(vf_netdev, ndev);
+	ret = netdev_upper_dev_link(vf_netdev, ndev, NULL);
 	if (ret != 0) {
 		netdev_err(vf_netdev,
 			   "can not set master device %s (err = %d)\n",
@@ -1935,6 +1987,12 @@ 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;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 065b204d8e17..8b1242b8d8ef 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -407,13 +407,13 @@ int rndis_filter_receive(struct net_device *ndev,
 
 	/* Make sure the rndis device state is initialized */
 	if (unlikely(!rndis_dev)) {
-		netif_err(net_device_ctx, rx_err, ndev,
+		netif_dbg(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,
+		netif_dbg(net_device_ctx, rx_err, ndev,
 			  "got rndis message uninitialized\n");
 		return NVSP_STAT_FAIL;
 	}
@@ -759,7 +759,7 @@ 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);
@@ -1114,6 +1114,9 @@ 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;
+
 	rtnl_unlock();
 	return;
 
@@ -1284,8 +1287,8 @@ 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);