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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

4 files changed, 145 insertions, 32 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 41071d32bc8e..dd4544085db3 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -161,6 +161,7 @@ struct netvsc_device_info {
 	unsigned char mac_adr[ETH_ALEN];
 	bool link_state;	/* 0 - link up, 1 - link down */
 	int  ring_size;
+	u32  max_num_vrss_chns;
 };
 
 enum rndis_device_state {
@@ -611,6 +612,12 @@ struct multi_send_data {
 	u32 count; /* counter of batched packets */
 };
 
+struct netvsc_stats {
+	u64 packets;
+	u64 bytes;
+	struct u64_stats_sync syncp;
+};
+
 /* The context of the netvsc device  */
 struct net_device_context {
 	/* point back to our device context */
@@ -618,6 +625,9 @@ struct net_device_context {
 	struct delayed_work dwork;
 	struct work_struct work;
 	u32 msg_enable; /* debug level */
+
+	struct netvsc_stats __percpu *tx_stats;
+	struct netvsc_stats __percpu *rx_stats;
 };
 
 /* Per netvsc device */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 1e09243d5449..23126a74f357 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -228,13 +228,18 @@ static int netvsc_init_buf(struct hv_device *device)
 	struct netvsc_device *net_device;
 	struct nvsp_message *init_packet;
 	struct net_device *ndev;
+	int node;
 
 	net_device = get_outbound_net_device(device);
 	if (!net_device)
 		return -ENODEV;
 	ndev = net_device->ndev;
 
-	net_device->recv_buf = vzalloc(net_device->recv_buf_size);
+	node = cpu_to_node(device->channel->target_cpu);
+	net_device->recv_buf = vzalloc_node(net_device->recv_buf_size, node);
+	if (!net_device->recv_buf)
+		net_device->recv_buf = vzalloc(net_device->recv_buf_size);
+
 	if (!net_device->recv_buf) {
 		netdev_err(ndev, "unable to allocate receive "
 			"buffer of size %d\n", net_device->recv_buf_size);
@@ -322,7 +327,9 @@ static int netvsc_init_buf(struct hv_device *device)
 
 	/* Now setup the send buffer.
 	 */
-	net_device->send_buf = vzalloc(net_device->send_buf_size);
+	net_device->send_buf = vzalloc_node(net_device->send_buf_size, node);
+	if (!net_device->send_buf)
+		net_device->send_buf = vzalloc(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);
@@ -744,6 +751,7 @@ static inline int netvsc_send_pkt(
 	u64 req_id;
 	int ret;
 	struct hv_page_buffer *pgbuf;
+	u32 ring_avail = hv_ringbuf_avail_percent(&out_channel->outbound);
 
 	nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
 	if (packet->is_data_pkt) {
@@ -770,32 +778,42 @@ static inline int netvsc_send_pkt(
 	if (out_channel->rescind)
 		return -ENODEV;
 
+	/*
+	 * It is possible that once we successfully place this packet
+	 * on the ringbuffer, we may stop the queue. In that case, we want
+	 * to notify the host independent of the xmit_more flag. We don't
+	 * need to be precise here; in the worst case we may signal the host
+	 * unnecessarily.
+	 */
+	if (ring_avail < (RING_AVAIL_PERCENT_LOWATER + 1))
+		packet->xmit_more = false;
+
 	if (packet->page_buf_cnt) {
 		pgbuf = packet->cp_partial ? packet->page_buf +
 			packet->rmsg_pgcnt : packet->page_buf;
-		ret = vmbus_sendpacket_pagebuffer(out_channel,
-						  pgbuf,
-						  packet->page_buf_cnt,
-						  &nvmsg,
-						  sizeof(struct nvsp_message),
-						  req_id);
+		ret = vmbus_sendpacket_pagebuffer_ctl(out_channel,
+						      pgbuf,
+						      packet->page_buf_cnt,
+						      &nvmsg,
+						      sizeof(struct nvsp_message),
+						      req_id,
+						      VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
+						      !packet->xmit_more);
 	} else {
-		ret = vmbus_sendpacket(
-				out_channel, &nvmsg,
-				sizeof(struct nvsp_message),
-				req_id,
-				VM_PKT_DATA_INBAND,
-				VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+		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);
 	}
 
 	if (ret == 0) {
 		atomic_inc(&net_device->num_outstanding_sends);
 		atomic_inc(&net_device->queue_sends[q_idx]);
 
-		if (hv_ringbuf_avail_percent(&out_channel->outbound) <
-			RING_AVAIL_PERCENT_LOWATER) {
-			netif_tx_stop_queue(netdev_get_tx_queue(
-					    ndev, q_idx));
+		if (ring_avail < RING_AVAIL_PERCENT_LOWATER) {
+			netif_tx_stop_queue(netdev_get_tx_queue(ndev, q_idx));
 
 			if (atomic_read(&net_device->
 				queue_sends[q_idx]) < 1)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 5993c7e2d723..358475ed9b59 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -46,6 +46,8 @@ static int ring_size = 128;
 module_param(ring_size, int, S_IRUGO);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
 
+static int max_num_vrss_chns = 8;
+
 static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
 				NETIF_MSG_LINK | NETIF_MSG_IFUP |
 				NETIF_MSG_IFDOWN | NETIF_MSG_RX_ERR |
@@ -196,12 +198,12 @@ static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb)
 	struct flow_keys flow;
 	int data_len;
 
-	if (!skb_flow_dissect(skb, &flow) ||
-	    !(flow.n_proto == htons(ETH_P_IP) ||
-	      flow.n_proto == htons(ETH_P_IPV6)))
+	if (!skb_flow_dissect_flow_keys(skb, &flow) ||
+	    !(flow.basic.n_proto == htons(ETH_P_IP) ||
+	      flow.basic.n_proto == htons(ETH_P_IPV6)))
 		return false;
 
-	if (flow.ip_proto == IPPROTO_TCP)
+	if (flow.basic.ip_proto == IPPROTO_TCP)
 		data_len = 12;
 	else
 		data_len = 8;
@@ -391,7 +393,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	u32 skb_length;
 	u32 pkt_sz;
 	struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT];
-
+	struct netvsc_stats *tx_stats = this_cpu_ptr(net_device_ctx->tx_stats);
 
 	/* We will atmost need two pages to describe the rndis
 	 * header. We can only transmit MAX_PAGE_BUFFER_COUNT number
@@ -580,8 +582,10 @@ do_send:
 
 drop:
 	if (ret == 0) {
-		net->stats.tx_bytes += skb_length;
-		net->stats.tx_packets++;
+		u64_stats_update_begin(&tx_stats->syncp);
+		tx_stats->packets++;
+		tx_stats->bytes += skb_length;
+		u64_stats_update_end(&tx_stats->syncp);
 	} else {
 		if (ret != -EAGAIN) {
 			dev_kfree_skb_any(skb);
@@ -644,13 +648,17 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 				struct ndis_tcp_ip_checksum_info *csum_info)
 {
 	struct net_device *net;
+	struct net_device_context *net_device_ctx;
 	struct sk_buff *skb;
+	struct netvsc_stats *rx_stats;
 
 	net = ((struct netvsc_device *)hv_get_drvdata(device_obj))->ndev;
 	if (!net || net->reg_state != NETREG_REGISTERED) {
 		packet->status = NVSP_STAT_FAIL;
 		return 0;
 	}
+	net_device_ctx = netdev_priv(net);
+	rx_stats = this_cpu_ptr(net_device_ctx->rx_stats);
 
 	/* Allocate a skb - TODO direct I/O to pages? */
 	skb = netdev_alloc_skb_ip_align(net, packet->total_data_buflen);
@@ -686,8 +694,10 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	skb_record_rx_queue(skb, packet->channel->
 			    offermsg.offer.sub_channel_index);
 
-	net->stats.rx_packets++;
-	net->stats.rx_bytes += packet->total_data_buflen;
+	u64_stats_update_begin(&rx_stats->syncp);
+	rx_stats->packets++;
+	rx_stats->bytes += packet->total_data_buflen;
+	u64_stats_update_end(&rx_stats->syncp);
 
 	/*
 	 * Pass the skb back up. Network stack will deallocate the skb when it
@@ -747,12 +757,53 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	ndevctx->device_ctx = hdev;
 	hv_set_drvdata(hdev, ndev);
 	device_info.ring_size = ring_size;
+	device_info.max_num_vrss_chns = max_num_vrss_chns;
 	rndis_filter_device_add(hdev, &device_info);
 	netif_tx_wake_all_queues(ndev);
 
 	return 0;
 }
 
+static struct rtnl_link_stats64 *netvsc_get_stats64(struct net_device *net,
+						    struct rtnl_link_stats64 *t)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(net);
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct netvsc_stats *tx_stats = per_cpu_ptr(ndev_ctx->tx_stats,
+							    cpu);
+		struct netvsc_stats *rx_stats = per_cpu_ptr(ndev_ctx->rx_stats,
+							    cpu);
+		u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&tx_stats->syncp);
+			tx_packets = tx_stats->packets;
+			tx_bytes = tx_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start));
+
+		do {
+			start = u64_stats_fetch_begin_irq(&rx_stats->syncp);
+			rx_packets = rx_stats->packets;
+			rx_bytes = rx_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start));
+
+		t->tx_bytes	+= tx_bytes;
+		t->tx_packets	+= tx_packets;
+		t->rx_bytes	+= rx_bytes;
+		t->rx_packets	+= rx_packets;
+	}
+
+	t->tx_dropped	= net->stats.tx_dropped;
+	t->tx_errors	= net->stats.tx_dropped;
+
+	t->rx_dropped	= net->stats.rx_dropped;
+	t->rx_errors	= net->stats.rx_errors;
+
+	return t;
+}
 
 static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
 {
@@ -804,6 +855,7 @@ static const struct net_device_ops device_ops = {
 	.ndo_validate_addr =		eth_validate_addr,
 	.ndo_set_mac_address =		netvsc_set_mac_addr,
 	.ndo_select_queue =		netvsc_select_queue,
+	.ndo_get_stats64 =		netvsc_get_stats64,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller =		netvsc_poll_controller,
 #endif
@@ -855,6 +907,14 @@ static void netvsc_link_change(struct work_struct *w)
 		netdev_notify_peers(net);
 }
 
+static void netvsc_free_netdev(struct net_device *netdev)
+{
+	struct net_device_context *net_device_ctx = netdev_priv(netdev);
+
+	free_percpu(net_device_ctx->tx_stats);
+	free_percpu(net_device_ctx->rx_stats);
+	free_netdev(netdev);
+}
 
 static int netvsc_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
@@ -883,6 +943,18 @@ static int netvsc_probe(struct hv_device *dev,
 		netdev_dbg(net, "netvsc msg_enable: %d\n",
 			   net_device_ctx->msg_enable);
 
+	net_device_ctx->tx_stats = netdev_alloc_pcpu_stats(struct netvsc_stats);
+	if (!net_device_ctx->tx_stats) {
+		free_netdev(net);
+		return -ENOMEM;
+	}
+	net_device_ctx->rx_stats = netdev_alloc_pcpu_stats(struct netvsc_stats);
+	if (!net_device_ctx->rx_stats) {
+		free_percpu(net_device_ctx->tx_stats);
+		free_netdev(net);
+		return -ENOMEM;
+	}
+
 	hv_set_drvdata(dev, net);
 	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
 	INIT_WORK(&net_device_ctx->work, do_set_multicast);
@@ -906,10 +978,11 @@ static int netvsc_probe(struct hv_device *dev,
 
 	/* Notify the netvsc driver of the new device */
 	device_info.ring_size = ring_size;
+	device_info.max_num_vrss_chns = max_num_vrss_chns;
 	ret = rndis_filter_device_add(dev, &device_info);
 	if (ret != 0) {
 		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
-		free_netdev(net);
+		netvsc_free_netdev(net);
 		hv_set_drvdata(dev, NULL);
 		return ret;
 	}
@@ -923,7 +996,7 @@ static int netvsc_probe(struct hv_device *dev,
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
 		rndis_filter_device_remove(dev);
-		free_netdev(net);
+		netvsc_free_netdev(net);
 	} else {
 		schedule_delayed_work(&net_device_ctx->dwork, 0);
 	}
@@ -962,7 +1035,7 @@ static int netvsc_remove(struct hv_device *dev)
 	 */
 	rndis_filter_device_remove(dev);
 
-	free_netdev(net);
+	netvsc_free_netdev(net);
 	return 0;
 }
 
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 35a482d526d9..236aeb76ef22 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1014,6 +1014,9 @@ int rndis_filter_device_add(struct hv_device *dev,
 	struct ndis_recv_scale_cap rsscap;
 	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	u32 mtu, size;
+	u32 num_rss_qs;
+	const struct cpumask *node_cpu_mask;
+	u32 num_possible_rss_qs;
 
 	rndis_device = get_rndis_device();
 	if (!rndis_device)
@@ -1101,9 +1104,18 @@ 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 = rsscap.num_recv_que;
-	net_device->num_chn = (num_online_cpus() < rsscap.num_recv_que) ?
-			       num_online_cpus() : rsscap.num_recv_que;
+
+	/*
+	 * We will limit the VRSS channels to the number CPUs in the NUMA node
+	 * the primary channel is currently bound to.
+	 */
+	node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu));
+	num_possible_rss_qs = cpumask_weight(node_cpu_mask);
+	net_device->num_chn = min(num_possible_rss_qs, num_rss_qs);
+
 	if (net_device->num_chn == 1)
 		goto out;