4 files changed, 128 insertions, 97 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index f4130af09244..8b3bd8ecd1c4 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -619,11 +619,13 @@ struct nvsp_message {
 #define NETVSC_PACKET_SIZE                      4096
 
 #define VRSS_SEND_TAB_SIZE 16
+#define VRSS_CHANNEL_MAX 64
 
 #define RNDIS_MAX_PKT_DEFAULT 8
 #define RNDIS_PKT_ALIGN_DEFAULT 8
 
 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 */
 };
@@ -657,6 +659,10 @@ struct net_device_context {
 
 	struct netvsc_stats __percpu *tx_stats;
 	struct netvsc_stats __percpu *rx_stats;
+
+	/* Ethtool settings */
+	u8 duplex;
+	u32 speed;
 };
 
 /* Per netvsc device */
@@ -695,13 +701,13 @@ struct netvsc_device {
 
 	struct net_device *ndev;
 
-	struct vmbus_channel *chn_table[NR_CPUS];
+	struct vmbus_channel *chn_table[VRSS_CHANNEL_MAX];
 	u32 send_table[VRSS_SEND_TAB_SIZE];
 	u32 max_chn;
 	u32 num_chn;
 	spinlock_t sc_lock; /* Protects num_sc_offered variable */
 	u32 num_sc_offered;
-	atomic_t queue_sends[NR_CPUS];
+	atomic_t queue_sends[VRSS_CHANNEL_MAX];
 
 	/* Holds rndis device info */
 	void *extension;
@@ -713,7 +719,7 @@ struct netvsc_device {
 	/* The sub channel callback buffer */
 	unsigned char *sub_cb_buf;
 
-	struct multi_send_data msd[NR_CPUS];
+	struct multi_send_data msd[VRSS_CHANNEL_MAX];
 	u32 max_pkt; /* max number of pkt in one send, e.g. 8 */
 	u32 pkt_align; /* alignment bytes, e.g. 8 */
 
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 059fc5231601..ec313fc08d82 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -841,6 +841,18 @@ 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 rndis_message *rndis_msg,
@@ -855,6 +867,7 @@ int netvsc_send(struct hv_device *device,
 	unsigned int section_index = NETVSC_INVALID_INDEX;
 	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;
 
@@ -897,10 +910,8 @@ int netvsc_send(struct hv_device *device,
 		   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;
 		}
 	}
 
@@ -919,31 +930,31 @@ int netvsc_send(struct hv_device *device,
 			packet->total_data_buflen += msd_len;
 		}
 
-		if (msdp->pkt)
-			dev_kfree_skb_any(skb);
+		if (msdp->skb)
+			dev_kfree_skb_any(msdp->skb);
 
 		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;
 	}
 
 	if (msd_send) {
-		m_ret = netvsc_send_pkt(msd_send, net_device, pb, skb);
+		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);
-			dev_kfree_skb_any(skb);
+			dev_kfree_skb_any(msd_skb);
 		}
 	}
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 1c8db9afdcda..b8121eba33ff 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -43,6 +43,11 @@
 
 #define RING_SIZE_MIN 64
 #define LINKCHANGE_INT (2 * HZ)
+#define NETVSC_HW_FEATURES	(NETIF_F_RXCSUM | \
+				 NETIF_F_SG | \
+				 NETIF_F_TSO | \
+				 NETIF_F_TSO6 | \
+				 NETIF_F_HW_CSUM)
 static int ring_size = 128;
 module_param(ring_size, int, S_IRUGO);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
@@ -196,65 +201,6 @@ 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)
 {
@@ -267,11 +213,9 @@ 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);
-	}
+	hash = skb_get_hash(skb);
+	q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
+		ndev->real_num_tx_queues;
 
 	if (!nvsc_dev->chn_table[q_idx])
 		q_idx = 0;
@@ -606,6 +550,8 @@ do_send:
 	packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size,
 					       skb, packet, &pb);
 
+	/* timestamp packet in software */
+	skb_tx_timestamp(skb);
 	ret = netvsc_send(net_device_ctx->device_ctx, packet,
 			  rndis_msg, &pb, skb);
 
@@ -853,6 +799,58 @@ static int netvsc_set_channels(struct net_device *net,
 	goto do_set;
 }
 
+static bool netvsc_validate_ethtool_ss_cmd(const struct ethtool_cmd *cmd)
+{
+	struct ethtool_cmd diff1 = *cmd;
+	struct ethtool_cmd diff2 = {};
+
+	ethtool_cmd_speed_set(&diff1, 0);
+	diff1.duplex = 0;
+	/* advertising and cmd are usually set */
+	diff1.advertising = 0;
+	diff1.cmd = 0;
+	/* We set port to PORT_OTHER */
+	diff2.port = PORT_OTHER;
+
+	return !memcmp(&diff1, &diff2, sizeof(diff1));
+}
+
+static void netvsc_init_settings(struct net_device *dev)
+{
+	struct net_device_context *ndc = netdev_priv(dev);
+
+	ndc->speed = SPEED_UNKNOWN;
+	ndc->duplex = DUPLEX_UNKNOWN;
+}
+
+static int netvsc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct net_device_context *ndc = netdev_priv(dev);
+
+	ethtool_cmd_speed_set(cmd, ndc->speed);
+	cmd->duplex = ndc->duplex;
+	cmd->port = PORT_OTHER;
+
+	return 0;
+}
+
+static int netvsc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct net_device_context *ndc = netdev_priv(dev);
+	u32 speed;
+
+	speed = ethtool_cmd_speed(cmd);
+	if (!ethtool_validate_speed(speed) ||
+	    !ethtool_validate_duplex(cmd->duplex) ||
+	    !netvsc_validate_ethtool_ss_cmd(cmd))
+		return -EINVAL;
+
+	ndc->speed = speed;
+	ndc->duplex = cmd->duplex;
+
+	return 0;
+}
+
 static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 {
 	struct net_device_context *ndevctx = netdev_priv(ndev);
@@ -860,6 +858,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	struct netvsc_device *nvdev = hv_get_drvdata(hdev);
 	struct netvsc_device_info device_info;
 	int limit = ETH_DATA_LEN;
+	u32 num_chn;
 	int ret = 0;
 
 	if (nvdev == NULL || nvdev->destroy)
@@ -875,6 +874,8 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	if (ret)
 		goto out;
 
+	num_chn = nvdev->num_chn;
+
 	nvdev->start_remove = true;
 	rndis_filter_device_remove(hdev);
 
@@ -885,7 +886,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
-	device_info.num_chn = nvdev->num_chn;
+	device_info.num_chn = num_chn;
 	device_info.max_num_vrss_chns = max_num_vrss_chns;
 	rndis_filter_device_add(hdev, &device_info);
 
@@ -976,6 +977,9 @@ static const struct ethtool_ops ethtool_ops = {
 	.get_link	= ethtool_op_get_link,
 	.get_channels   = netvsc_get_channels,
 	.set_channels   = netvsc_set_channels,
+	.get_ts_info	= ethtool_op_get_ts_info,
+	.get_settings	= netvsc_get_settings,
+	.set_settings	= netvsc_set_settings,
 };
 
 static const struct net_device_ops device_ops = {
@@ -1142,14 +1146,15 @@ static int netvsc_probe(struct hv_device *dev,
 
 	net->netdev_ops = &device_ops;
 
-	net->hw_features = NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_IP_CSUM |
-				NETIF_F_TSO;
-	net->features = NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_SG | NETIF_F_RXCSUM |
-			NETIF_F_IP_CSUM | NETIF_F_TSO;
+	net->hw_features = NETVSC_HW_FEATURES;
+	net->features = NETVSC_HW_FEATURES | NETIF_F_HW_VLAN_CTAG_TX;
 
 	net->ethtool_ops = &ethtool_ops;
 	SET_NETDEV_DEV(net, &dev->device);
 
+	/* 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));
 	device_info.ring_size = ring_size;
@@ -1167,6 +1172,8 @@ static int netvsc_probe(struct hv_device *dev,
 	netif_set_real_num_tx_queues(net, nvdev->num_chn);
 	netif_set_real_num_rx_queues(net, nvdev->num_chn);
 
+	netvsc_init_settings(net);
+
 	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 a37bbda37ffa..c4e1e0408433 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -986,12 +986,6 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 
 	nvscdev = hv_get_drvdata(new_sc->primary_channel->device_obj);
 
-	spin_lock_irqsave(&nvscdev->sc_lock, flags);
-	nvscdev->num_sc_offered--;
-	spin_unlock_irqrestore(&nvscdev->sc_lock, flags);
-	if (nvscdev->num_sc_offered == 0)
-		complete(&nvscdev->channel_init_wait);
-
 	if (chn_index >= nvscdev->num_chn)
 		return;
 
@@ -1004,6 +998,12 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 
 	if (ret == 0)
 		nvscdev->chn_table[chn_index] = new_sc;
+
+	spin_lock_irqsave(&nvscdev->sc_lock, flags);
+	nvscdev->num_sc_offered--;
+	spin_unlock_irqrestore(&nvscdev->sc_lock, flags);
+	if (nvscdev->num_sc_offered == 0)
+		complete(&nvscdev->channel_init_wait);
 }
 
 int rndis_filter_device_add(struct hv_device *dev,
@@ -1113,9 +1113,9 @@ int rndis_filter_device_add(struct hv_device *dev,
 	if (ret || rsscap.num_recv_que < 2)
 		goto out;
 
-	num_rss_qs = min(device_info->max_num_vrss_chns, rsscap.num_recv_que);
+	net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, rsscap.num_recv_que);
 
-	net_device->max_chn = rsscap.num_recv_que;
+	num_rss_qs = min(device_info->max_num_vrss_chns, net_device->max_chn);
 
 	/*
 	 * We will limit the VRSS channels to the number CPUs in the NUMA node
@@ -1175,22 +1175,18 @@ int rndis_filter_device_add(struct hv_device *dev,
 	ret = rndis_filter_set_rss_param(rndis_device, net_device->num_chn);
 
 	/*
-	 * Wait for the host to send us the sub-channel offers.
+	 * Set the number of sub-channels to be received.
 	 */
 	spin_lock_irqsave(&net_device->sc_lock, flags);
 	sc_delta = num_rss_qs - (net_device->num_chn - 1);
 	net_device->num_sc_offered -= sc_delta;
 	spin_unlock_irqrestore(&net_device->sc_lock, flags);
 
-	while (net_device->num_sc_offered != 0) {
-		t = wait_for_completion_timeout(&net_device->channel_init_wait, 10*HZ);
-		if (t == 0)
-			WARN(1, "Netvsc: Waiting for sub-channel processing");
-	}
 out:
 	if (ret) {
 		net_device->max_chn = 1;
 		net_device->num_chn = 1;
+		net_device->num_sc_offered = 0;
 	}
 
 	return 0; /* return 0 because primary channel can be used alone */
@@ -1204,6 +1200,17 @@ void rndis_filter_device_remove(struct hv_device *dev)
 {
 	struct netvsc_device *net_dev = hv_get_drvdata(dev);
 	struct rndis_device *rndis_dev = net_dev->extension;
+	unsigned long t;
+
+	/* If not all subchannel offers are complete, wait for them until
+	 * completion to avoid race.
+	 */
+	while (net_dev->num_sc_offered > 0) {
+		t = wait_for_completion_timeout(&net_dev->channel_init_wait,
+						10 * HZ);
+		if (t == 0)
+			WARN(1, "Netvsc: Waiting for sub-channel processing");
+	}
 
 	/* Halt and release the rndis device */
 	rndis_filter_halt_device(rndis_dev);