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
  ...

1 files changed, 173 insertions, 47 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index aa82f9ab6a36..6778a9999d52 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -135,6 +135,7 @@
 #include <linux/if_macvlan.h>
 #include <linux/errqueue.h>
 #include <linux/hrtimer.h>
+#include <linux/netfilter_ingress.h>
 
 #include "net-sysfs.h"
 
@@ -468,10 +469,14 @@ EXPORT_SYMBOL(dev_remove_pack);
  */
 void dev_add_offload(struct packet_offload *po)
 {
-	struct list_head *head = &offload_base;
+	struct packet_offload *elem;
 
 	spin_lock(&offload_lock);
-	list_add_rcu(&po->list, head);
+	list_for_each_entry(elem, &offload_base, list) {
+		if (po->priority < elem->priority)
+			break;
+	}
+	list_add_rcu(&po->list, elem->list.prev);
 	spin_unlock(&offload_lock);
 }
 EXPORT_SYMBOL(dev_add_offload);
@@ -1630,7 +1635,7 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_INGRESS
 static struct static_key ingress_needed __read_mostly;
 
 void net_inc_ingress_queue(void)
@@ -2343,6 +2348,34 @@ void netif_device_attach(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_device_attach);
 
+/*
+ * Returns a Tx hash based on the given packet descriptor a Tx queues' number
+ * to be used as a distribution range.
+ */
+u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
+		  unsigned int num_tx_queues)
+{
+	u32 hash;
+	u16 qoffset = 0;
+	u16 qcount = num_tx_queues;
+
+	if (skb_rx_queue_recorded(skb)) {
+		hash = skb_get_rx_queue(skb);
+		while (unlikely(hash >= num_tx_queues))
+			hash -= num_tx_queues;
+		return hash;
+	}
+
+	if (dev->num_tc) {
+		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+		qoffset = dev->tc_to_txq[tc].offset;
+		qcount = dev->tc_to_txq[tc].count;
+	}
+
+	return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
+}
+EXPORT_SYMBOL(__skb_tx_hash);
+
 static void skb_warn_bad_offload(const struct sk_buff *skb)
 {
 	static const netdev_features_t null_features = 0;
@@ -2901,6 +2934,84 @@ int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dev_loopback_xmit);
 
+static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+{
+#ifdef CONFIG_XPS
+	struct xps_dev_maps *dev_maps;
+	struct xps_map *map;
+	int queue_index = -1;
+
+	rcu_read_lock();
+	dev_maps = rcu_dereference(dev->xps_maps);
+	if (dev_maps) {
+		map = rcu_dereference(
+		    dev_maps->cpu_map[skb->sender_cpu - 1]);
+		if (map) {
+			if (map->len == 1)
+				queue_index = map->queues[0];
+			else
+				queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
+									   map->len)];
+			if (unlikely(queue_index >= dev->real_num_tx_queues))
+				queue_index = -1;
+		}
+	}
+	rcu_read_unlock();
+
+	return queue_index;
+#else
+	return -1;
+#endif
+}
+
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+{
+	struct sock *sk = skb->sk;
+	int queue_index = sk_tx_queue_get(sk);
+
+	if (queue_index < 0 || skb->ooo_okay ||
+	    queue_index >= dev->real_num_tx_queues) {
+		int new_index = get_xps_queue(dev, skb);
+		if (new_index < 0)
+			new_index = skb_tx_hash(dev, skb);
+
+		if (queue_index != new_index && sk &&
+		    rcu_access_pointer(sk->sk_dst_cache))
+			sk_tx_queue_set(sk, new_index);
+
+		queue_index = new_index;
+	}
+
+	return queue_index;
+}
+
+struct netdev_queue *netdev_pick_tx(struct net_device *dev,
+				    struct sk_buff *skb,
+				    void *accel_priv)
+{
+	int queue_index = 0;
+
+#ifdef CONFIG_XPS
+	if (skb->sender_cpu == 0)
+		skb->sender_cpu = raw_smp_processor_id() + 1;
+#endif
+
+	if (dev->real_num_tx_queues != 1) {
+		const struct net_device_ops *ops = dev->netdev_ops;
+		if (ops->ndo_select_queue)
+			queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+							    __netdev_pick_tx);
+		else
+			queue_index = __netdev_pick_tx(dev, skb);
+
+		if (!accel_priv)
+			queue_index = netdev_cap_txqueue(dev, queue_index);
+	}
+
+	skb_set_queue_mapping(skb, queue_index);
+	return netdev_get_tx_queue(dev, queue_index);
+}
+
 /**
  *	__dev_queue_xmit - transmit a buffer
  *	@skb: buffer to transmit
@@ -3513,66 +3624,47 @@ int (*br_fdb_test_addr_hook)(struct net_device *dev,
 EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
 #endif
 
-#ifdef CONFIG_NET_CLS_ACT
-/* TODO: Maybe we should just force sch_ingress to be compiled in
- * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
- * a compare and 2 stores extra right now if we dont have it on
- * but have CONFIG_NET_CLS_ACT
- * NOTE: This doesn't stop any functionality; if you dont have
- * the ingress scheduler, you just can't add policies on ingress.
- *
- */
-static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
-{
-	struct net_device *dev = skb->dev;
-	u32 ttl = G_TC_RTTL(skb->tc_verd);
-	int result = TC_ACT_OK;
-	struct Qdisc *q;
-
-	if (unlikely(MAX_RED_LOOP < ttl++)) {
-		net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n",
-				     skb->skb_iif, dev->ifindex);
-		return TC_ACT_SHOT;
-	}
-
-	skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
-	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
-
-	q = rcu_dereference(rxq->qdisc);
-	if (q != &noop_qdisc) {
-		spin_lock(qdisc_lock(q));
-		if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
-			result = qdisc_enqueue_root(skb, q);
-		spin_unlock(qdisc_lock(q));
-	}
-
-	return result;
-}
-
 static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 					 struct packet_type **pt_prev,
 					 int *ret, struct net_device *orig_dev)
 {
-	struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
+#ifdef CONFIG_NET_CLS_ACT
+	struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list);
+	struct tcf_result cl_res;
 
-	if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc)
+	/* If there's at least one ingress present somewhere (so
+	 * we get here via enabled static key), remaining devices
+	 * that are not configured with an ingress qdisc will bail
+	 * out here.
+	 */
+	if (!cl)
 		return skb;
-
 	if (*pt_prev) {
 		*ret = deliver_skb(skb, *pt_prev, orig_dev);
 		*pt_prev = NULL;
 	}
 
-	switch (ing_filter(skb, rxq)) {
+	qdisc_skb_cb(skb)->pkt_len = skb->len;
+	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
+	qdisc_bstats_update_cpu(cl->q, skb);
+
+	switch (tc_classify(skb, cl, &cl_res)) {
+	case TC_ACT_OK:
+	case TC_ACT_RECLASSIFY:
+		skb->tc_index = TC_H_MIN(cl_res.classid);
+		break;
 	case TC_ACT_SHOT:
+		qdisc_qstats_drop_cpu(cl->q);
 	case TC_ACT_STOLEN:
+	case TC_ACT_QUEUED:
 		kfree_skb(skb);
 		return NULL;
+	default:
+		break;
 	}
-
+#endif /* CONFIG_NET_CLS_ACT */
 	return skb;
 }
-#endif
 
 /**
  *	netdev_rx_handler_register - register receive handler
@@ -3645,6 +3737,22 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
 	}
 }
 
+static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
+			     int *ret, struct net_device *orig_dev)
+{
+#ifdef CONFIG_NETFILTER_INGRESS
+	if (nf_hook_ingress_active(skb)) {
+		if (*pt_prev) {
+			*ret = deliver_skb(skb, *pt_prev, orig_dev);
+			*pt_prev = NULL;
+		}
+
+		return nf_hook_ingress(skb);
+	}
+#endif /* CONFIG_NETFILTER_INGRESS */
+	return 0;
+}
+
 static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 {
 	struct packet_type *ptype, *pt_prev;
@@ -3704,13 +3812,17 @@ another_round:
 	}
 
 skip_taps:
-#ifdef CONFIG_NET_CLS_ACT
+#ifdef CONFIG_NET_INGRESS
 	if (static_key_false(&ingress_needed)) {
 		skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 		if (!skb)
 			goto unlock;
-	}
 
+		if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0)
+			goto unlock;
+	}
+#endif
+#ifdef CONFIG_NET_CLS_ACT
 	skb->tc_verd = 0;
 ncls:
 #endif
@@ -6313,6 +6425,17 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
 	return 0;
 }
 
+void netif_tx_stop_all_queues(struct net_device *dev)
+{
+	unsigned int i;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
+		netif_tx_stop_queue(txq);
+	}
+}
+EXPORT_SYMBOL(netif_tx_stop_all_queues);
+
 /**
  *	register_netdevice	- register a network device
  *	@dev: device to register
@@ -6862,6 +6985,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->group = INIT_NETDEV_GROUP;
 	if (!dev->ethtool_ops)
 		dev->ethtool_ops = &default_ethtool_ops;
+
+	nf_hook_ingress_init(dev);
+
 	return dev;
 
 free_all: