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, 462 insertions, 194 deletions

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2c35c02a931e..476e5dda59e1 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1,3 +1,4 @@
+#include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/export.h>
 #include <linux/ip.h>
@@ -12,19 +13,60 @@
 #include <linux/if_tunnel.h>
 #include <linux/if_pppox.h>
 #include <linux/ppp_defs.h>
-#include <net/flow_keys.h>
+#include <linux/stddef.h>
+#include <linux/if_ether.h>
+#include <linux/mpls.h>
+#include <net/flow_dissector.h>
 #include <scsi/fc/fc_fcoe.h>
 
-/* copy saddr & daddr, possibly using 64bit load/store
- * Equivalent to :	flow->src = iph->saddr;
- *			flow->dst = iph->daddr;
- */
-static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph)
+static bool skb_flow_dissector_uses_key(struct flow_dissector *flow_dissector,
+					enum flow_dissector_key_id key_id)
+{
+	return flow_dissector->used_keys & (1 << key_id);
+}
+
+static void skb_flow_dissector_set_key(struct flow_dissector *flow_dissector,
+				       enum flow_dissector_key_id key_id)
+{
+	flow_dissector->used_keys |= (1 << key_id);
+}
+
+static void *skb_flow_dissector_target(struct flow_dissector *flow_dissector,
+				       enum flow_dissector_key_id key_id,
+				       void *target_container)
+{
+	return ((char *) target_container) + flow_dissector->offset[key_id];
+}
+
+void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
+			     const struct flow_dissector_key *key,
+			     unsigned int key_count)
 {
-	BUILD_BUG_ON(offsetof(typeof(*flow), dst) !=
-		     offsetof(typeof(*flow), src) + sizeof(flow->src));
-	memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
+	unsigned int i;
+
+	memset(flow_dissector, 0, sizeof(*flow_dissector));
+
+	for (i = 0; i < key_count; i++, key++) {
+		/* User should make sure that every key target offset is withing
+		 * boundaries of unsigned short.
+		 */
+		BUG_ON(key->offset > USHRT_MAX);
+		BUG_ON(skb_flow_dissector_uses_key(flow_dissector,
+						   key->key_id));
+
+		skb_flow_dissector_set_key(flow_dissector, key->key_id);
+		flow_dissector->offset[key->key_id] = key->offset;
+	}
+
+	/* Ensure that the dissector always includes control and basic key.
+	 * That way we are able to avoid handling lack of these in fast path.
+	 */
+	BUG_ON(!skb_flow_dissector_uses_key(flow_dissector,
+					    FLOW_DISSECTOR_KEY_CONTROL));
+	BUG_ON(!skb_flow_dissector_uses_key(flow_dissector,
+					    FLOW_DISSECTOR_KEY_BASIC));
 }
+EXPORT_SYMBOL(skb_flow_dissector_init);
 
 /**
  * __skb_flow_get_ports - extract the upper layer ports and return them
@@ -63,17 +105,30 @@ EXPORT_SYMBOL(__skb_flow_get_ports);
 /**
  * __skb_flow_dissect - extract the flow_keys struct and return it
  * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
+ * @flow_dissector: list of keys to dissect
+ * @target_container: target structure to put dissected values into
  * @data: raw buffer pointer to the packet, if NULL use skb->data
  * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol
  * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb)
  * @hlen: packet header length, if @data is NULL use skb_headlen(skb)
  *
- * The function will try to retrieve the struct flow_keys from either the skbuff
- * or a raw buffer specified by the rest parameters
+ * The function will try to retrieve individual keys into target specified
+ * by flow_dissector from either the skbuff or a raw buffer specified by the
+ * rest parameters.
+ *
+ * Caller must take care of zeroing target container memory.
  */
-bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
+bool __skb_flow_dissect(const struct sk_buff *skb,
+			struct flow_dissector *flow_dissector,
+			void *target_container,
 			void *data, __be16 proto, int nhoff, int hlen)
 {
+	struct flow_dissector_key_control *key_control;
+	struct flow_dissector_key_basic *key_basic;
+	struct flow_dissector_key_addrs *key_addrs;
+	struct flow_dissector_key_ports *key_ports;
+	struct flow_dissector_key_tags *key_tags;
+	struct flow_dissector_key_keyid *key_keyid;
 	u8 ip_proto;
 
 	if (!data) {
@@ -83,7 +138,30 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
 		hlen = skb_headlen(skb);
 	}
 
-	memset(flow, 0, sizeof(*flow));
+	/* It is ensured by skb_flow_dissector_init() that control key will
+	 * be always present.
+	 */
+	key_control = skb_flow_dissector_target(flow_dissector,
+						FLOW_DISSECTOR_KEY_CONTROL,
+						target_container);
+
+	/* It is ensured by skb_flow_dissector_init() that basic key will
+	 * be always present.
+	 */
+	key_basic = skb_flow_dissector_target(flow_dissector,
+					      FLOW_DISSECTOR_KEY_BASIC,
+					      target_container);
+
+	if (skb_flow_dissector_uses_key(flow_dissector,
+					FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct ethhdr *eth = eth_hdr(skb);
+		struct flow_dissector_key_eth_addrs *key_eth_addrs;
+
+		key_eth_addrs = skb_flow_dissector_target(flow_dissector,
+							  FLOW_DISSECTOR_KEY_ETH_ADDRS,
+							  target_container);
+		memcpy(key_eth_addrs, &eth->h_dest, sizeof(*key_eth_addrs));
+	}
 
 again:
 	switch (proto) {
@@ -100,14 +178,15 @@ ip:
 		if (ip_is_fragment(iph))
 			ip_proto = 0;
 
-		/* skip the address processing if skb is NULL.  The assumption
-		 * here is that if there is no skb we are not looking for flow
-		 * info but lengths and protocols.
-		 */
-		if (!skb)
+		if (!skb_flow_dissector_uses_key(flow_dissector,
+						 FLOW_DISSECTOR_KEY_IPV4_ADDRS))
 			break;
 
-		iph_to_flow_copy_addrs(flow, iph);
+		key_addrs = skb_flow_dissector_target(flow_dissector,
+			      FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container);
+		memcpy(&key_addrs->v4addrs, &iph->saddr,
+		       sizeof(key_addrs->v4addrs));
+		key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 		break;
 	}
 	case htons(ETH_P_IPV6): {
@@ -123,25 +202,27 @@ ipv6:
 		ip_proto = iph->nexthdr;
 		nhoff += sizeof(struct ipv6hdr);
 
-		/* see comment above in IPv4 section */
-		if (!skb)
-			break;
+		if (skb_flow_dissector_uses_key(flow_dissector,
+						FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+			struct flow_dissector_key_ipv6_addrs *key_ipv6_addrs;
+
+			key_ipv6_addrs = skb_flow_dissector_target(flow_dissector,
+								   FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+								   target_container);
 
-		flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
-		flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
+			memcpy(key_ipv6_addrs, &iph->saddr, sizeof(*key_ipv6_addrs));
+			key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+		}
 
 		flow_label = ip6_flowlabel(iph);
 		if (flow_label) {
-			/* Awesome, IPv6 packet has a flow label so we can
-			 * use that to represent the ports without any
-			 * further dissection.
-			 */
-			flow->n_proto = proto;
-			flow->ip_proto = ip_proto;
-			flow->ports = flow_label;
-			flow->thoff = (u16)nhoff;
-
-			return true;
+			if (skb_flow_dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
+				key_tags = skb_flow_dissector_target(flow_dissector,
+								     FLOW_DISSECTOR_KEY_FLOW_LABEL,
+								     target_container);
+				key_tags->flow_label = ntohl(flow_label);
+			}
 		}
 
 		break;
@@ -155,6 +236,15 @@ ipv6:
 		if (!vlan)
 			return false;
 
+		if (skb_flow_dissector_uses_key(flow_dissector,
+						FLOW_DISSECTOR_KEY_VLANID)) {
+			key_tags = skb_flow_dissector_target(flow_dissector,
+							     FLOW_DISSECTOR_KEY_VLANID,
+							     target_container);
+
+			key_tags->vlan_id = skb_vlan_tag_get_id(skb);
+		}
+
 		proto = vlan->h_vlan_encapsulated_proto;
 		nhoff += sizeof(*vlan);
 		goto again;
@@ -186,19 +276,58 @@ ipv6:
 		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
 		if (!hdr)
 			return false;
-		flow->src = hdr->srcnode;
-		flow->dst = 0;
-		flow->n_proto = proto;
-		flow->thoff = (u16)nhoff;
+		key_basic->n_proto = proto;
+		key_control->thoff = (u16)nhoff;
+
+		if (skb_flow_dissector_uses_key(flow_dissector,
+						FLOW_DISSECTOR_KEY_TIPC_ADDRS)) {
+			key_addrs = skb_flow_dissector_target(flow_dissector,
+							      FLOW_DISSECTOR_KEY_TIPC_ADDRS,
+							      target_container);
+			key_addrs->tipcaddrs.srcnode = hdr->srcnode;
+			key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC_ADDRS;
+		}
+		return true;
+	}
+
+	case htons(ETH_P_MPLS_UC):
+	case htons(ETH_P_MPLS_MC): {
+		struct mpls_label *hdr, _hdr[2];
+mpls:
+		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
+					   hlen, &_hdr);
+		if (!hdr)
+			return false;
+
+		if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >>
+		     MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) {
+			if (skb_flow_dissector_uses_key(flow_dissector,
+							FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
+				key_keyid = skb_flow_dissector_target(flow_dissector,
+								      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
+								      target_container);
+				key_keyid->keyid = hdr[1].entry &
+					htonl(MPLS_LS_LABEL_MASK);
+			}
+
+			key_basic->n_proto = proto;
+			key_basic->ip_proto = ip_proto;
+			key_control->thoff = (u16)nhoff;
+
+			return true;
+		}
+
 		return true;
 	}
+
 	case htons(ETH_P_FCOE):
-		flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
+		key_control->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
 		/* fall through */
 	default:
 		return false;
 	}
 
+ip_proto_again:
 	switch (ip_proto) {
 	case IPPROTO_GRE: {
 		struct gre_hdr {
@@ -213,30 +342,65 @@ ipv6:
 		 * Only look inside GRE if version zero and no
 		 * routing
 		 */
-		if (!(hdr->flags & (GRE_VERSION|GRE_ROUTING))) {
-			proto = hdr->proto;
+		if (hdr->flags & (GRE_VERSION | GRE_ROUTING))
+			break;
+
+		proto = hdr->proto;
+		nhoff += 4;
+		if (hdr->flags & GRE_CSUM)
 			nhoff += 4;
-			if (hdr->flags & GRE_CSUM)
-				nhoff += 4;
-			if (hdr->flags & GRE_KEY)
-				nhoff += 4;
-			if (hdr->flags & GRE_SEQ)
-				nhoff += 4;
-			if (proto == htons(ETH_P_TEB)) {
-				const struct ethhdr *eth;
-				struct ethhdr _eth;
-
-				eth = __skb_header_pointer(skb, nhoff,
-							   sizeof(_eth),
-							   data, hlen, &_eth);
-				if (!eth)
-					return false;
-				proto = eth->h_proto;
-				nhoff += sizeof(*eth);
+		if (hdr->flags & GRE_KEY) {
+			const __be32 *keyid;
+			__be32 _keyid;
+
+			keyid = __skb_header_pointer(skb, nhoff, sizeof(_keyid),
+						     data, hlen, &_keyid);
+
+			if (!keyid)
+				return false;
+
+			if (skb_flow_dissector_uses_key(flow_dissector,
+							FLOW_DISSECTOR_KEY_GRE_KEYID)) {
+				key_keyid = skb_flow_dissector_target(flow_dissector,
+								      FLOW_DISSECTOR_KEY_GRE_KEYID,
+								      target_container);
+				key_keyid->keyid = *keyid;
 			}
-			goto again;
+			nhoff += 4;
 		}
-		break;
+		if (hdr->flags & GRE_SEQ)
+			nhoff += 4;
+		if (proto == htons(ETH_P_TEB)) {
+			const struct ethhdr *eth;
+			struct ethhdr _eth;
+
+			eth = __skb_header_pointer(skb, nhoff,
+						   sizeof(_eth),
+						   data, hlen, &_eth);
+			if (!eth)
+				return false;
+			proto = eth->h_proto;
+			nhoff += sizeof(*eth);
+		}
+		goto again;
+	}
+	case NEXTHDR_HOP:
+	case NEXTHDR_ROUTING:
+	case NEXTHDR_DEST: {
+		u8 _opthdr[2], *opthdr;
+
+		if (proto != htons(ETH_P_IPV6))
+			break;
+
+		opthdr = __skb_header_pointer(skb, nhoff, sizeof(_opthdr),
+					      data, hlen, &_opthdr);
+		if (!opthdr)
+			return false;
+
+		ip_proto = opthdr[0];
+		nhoff += (opthdr[1] + 1) << 3;
+
+		goto ip_proto_again;
 	}
 	case IPPROTO_IPIP:
 		proto = htons(ETH_P_IP);
@@ -244,18 +408,25 @@ ipv6:
 	case IPPROTO_IPV6:
 		proto = htons(ETH_P_IPV6);
 		goto ipv6;
+	case IPPROTO_MPLS:
+		proto = htons(ETH_P_MPLS_UC);
+		goto mpls;
 	default:
 		break;
 	}
 
-	flow->n_proto = proto;
-	flow->ip_proto = ip_proto;
-	flow->thoff = (u16) nhoff;
-
-	/* unless skb is set we don't need to record port info */
-	if (skb)
-		flow->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
-						   data, hlen);
+	key_basic->n_proto = proto;
+	key_basic->ip_proto = ip_proto;
+	key_control->thoff = (u16)nhoff;
+
+	if (skb_flow_dissector_uses_key(flow_dissector,
+					FLOW_DISSECTOR_KEY_PORTS)) {
+		key_ports = skb_flow_dissector_target(flow_dissector,
+						      FLOW_DISSECTOR_KEY_PORTS,
+						      target_container);
+		key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
+							data, hlen);
+	}
 
 	return true;
 }
@@ -267,27 +438,109 @@ static __always_inline void __flow_hash_secret_init(void)
 	net_get_random_once(&hashrnd, sizeof(hashrnd));
 }
 
-static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c)
+static __always_inline u32 __flow_hash_words(u32 *words, u32 length, u32 keyval)
 {
-	__flow_hash_secret_init();
-	return jhash_3words(a, b, c, hashrnd);
+	return jhash2(words, length, keyval);
 }
 
-static inline u32 __flow_hash_from_keys(struct flow_keys *keys)
+static inline void *flow_keys_hash_start(struct flow_keys *flow)
 {
-	u32 hash;
+	BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32));
+	return (void *)flow + FLOW_KEYS_HASH_OFFSET;
+}
+
+static inline size_t flow_keys_hash_length(struct flow_keys *flow)
+{
+	size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs);
+	BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
+	BUILD_BUG_ON(offsetof(typeof(*flow), addrs) !=
+		     sizeof(*flow) - sizeof(flow->addrs));
+
+	switch (flow->control.addr_type) {
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		diff -= sizeof(flow->addrs.v4addrs);
+		break;
+	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+		diff -= sizeof(flow->addrs.v6addrs);
+		break;
+	case FLOW_DISSECTOR_KEY_TIPC_ADDRS:
+		diff -= sizeof(flow->addrs.tipcaddrs);
+		break;
+	}
+	return (sizeof(*flow) - diff) / sizeof(u32);
+}
+
+__be32 flow_get_u32_src(const struct flow_keys *flow)
+{
+	switch (flow->control.addr_type) {
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		return flow->addrs.v4addrs.src;
+	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+		return (__force __be32)ipv6_addr_hash(
+			&flow->addrs.v6addrs.src);
+	case FLOW_DISSECTOR_KEY_TIPC_ADDRS:
+		return flow->addrs.tipcaddrs.srcnode;
+	default:
+		return 0;
+	}
+}
+EXPORT_SYMBOL(flow_get_u32_src);
 
-	/* get a consistent hash (same value on both flow directions) */
-	if (((__force u32)keys->dst < (__force u32)keys->src) ||
-	    (((__force u32)keys->dst == (__force u32)keys->src) &&
-	     ((__force u16)keys->port16[1] < (__force u16)keys->port16[0]))) {
-		swap(keys->dst, keys->src);
-		swap(keys->port16[0], keys->port16[1]);
+__be32 flow_get_u32_dst(const struct flow_keys *flow)
+{
+	switch (flow->control.addr_type) {
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		return flow->addrs.v4addrs.dst;
+	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+		return (__force __be32)ipv6_addr_hash(
+			&flow->addrs.v6addrs.dst);
+	default:
+		return 0;
 	}
+}
+EXPORT_SYMBOL(flow_get_u32_dst);
 
-	hash = __flow_hash_3words((__force u32)keys->dst,
-				  (__force u32)keys->src,
-				  (__force u32)keys->ports);
+static inline void __flow_hash_consistentify(struct flow_keys *keys)
+{
+	int addr_diff, i;
+
+	switch (keys->control.addr_type) {
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		addr_diff = (__force u32)keys->addrs.v4addrs.dst -
+			    (__force u32)keys->addrs.v4addrs.src;
+		if ((addr_diff < 0) ||
+		    (addr_diff == 0 &&
+		     ((__force u16)keys->ports.dst <
+		      (__force u16)keys->ports.src))) {
+			swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst);
+			swap(keys->ports.src, keys->ports.dst);
+		}
+		break;
+	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+		addr_diff = memcmp(&keys->addrs.v6addrs.dst,
+				   &keys->addrs.v6addrs.src,
+				   sizeof(keys->addrs.v6addrs.dst));
+		if ((addr_diff < 0) ||
+		    (addr_diff == 0 &&
+		     ((__force u16)keys->ports.dst <
+		      (__force u16)keys->ports.src))) {
+			for (i = 0; i < 4; i++)
+				swap(keys->addrs.v6addrs.src.s6_addr32[i],
+				     keys->addrs.v6addrs.dst.s6_addr32[i]);
+			swap(keys->ports.src, keys->ports.dst);
+		}
+		break;
+	}
+}
+
+static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
+{
+	u32 hash;
+
+	__flow_hash_consistentify(keys);
+
+	hash = __flow_hash_words((u32 *)flow_keys_hash_start(keys),
+				 flow_keys_hash_length(keys), keyval);
 	if (!hash)
 		hash = 1;
 
@@ -296,12 +549,52 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys)
 
 u32 flow_hash_from_keys(struct flow_keys *keys)
 {
-	return __flow_hash_from_keys(keys);
+	__flow_hash_secret_init();
+	return __flow_hash_from_keys(keys, hashrnd);
 }
 EXPORT_SYMBOL(flow_hash_from_keys);
 
-/*
- * __skb_get_hash: calculate a flow hash based on src/dst addresses
+static inline u32 ___skb_get_hash(const struct sk_buff *skb,
+				  struct flow_keys *keys, u32 keyval)
+{
+	if (!skb_flow_dissect_flow_keys(skb, keys))
+		return 0;
+
+	return __flow_hash_from_keys(keys, keyval);
+}
+
+struct _flow_keys_digest_data {
+	__be16	n_proto;
+	u8	ip_proto;
+	u8	padding;
+	__be32	ports;
+	__be32	src;
+	__be32	dst;
+};
+
+void make_flow_keys_digest(struct flow_keys_digest *digest,
+			   const struct flow_keys *flow)
+{
+	struct _flow_keys_digest_data *data =
+	    (struct _flow_keys_digest_data *)digest;
+
+	BUILD_BUG_ON(sizeof(*data) > sizeof(*digest));
+
+	memset(digest, 0, sizeof(*digest));
+
+	data->n_proto = flow->basic.n_proto;
+	data->ip_proto = flow->basic.ip_proto;
+	data->ports = flow->ports.ports;
+	data->src = flow->addrs.v4addrs.src;
+	data->dst = flow->addrs.v4addrs.dst;
+}
+EXPORT_SYMBOL(make_flow_keys_digest);
+
+/**
+ * __skb_get_hash: calculate a flow hash
+ * @skb: sk_buff to calculate flow hash from
+ *
+ * This function calculates a flow hash based on src/dst addresses
  * and src/dst port numbers.  Sets hash in skb to non-zero hash value
  * on success, zero indicates no valid hash.  Also, sets l4_hash in skb
  * if hash is a canonical 4-tuple hash over transport ports.
@@ -309,53 +602,34 @@ EXPORT_SYMBOL(flow_hash_from_keys);
 void __skb_get_hash(struct sk_buff *skb)
 {
 	struct flow_keys keys;
+	u32 hash;
 
-	if (!skb_flow_dissect(skb, &keys))
-		return;
+	__flow_hash_secret_init();
 
-	if (keys.ports)
+	hash = ___skb_get_hash(skb, &keys, hashrnd);
+	if (!hash)
+		return;
+	if (keys.ports.ports)
 		skb->l4_hash = 1;
-
 	skb->sw_hash = 1;
-
-	skb->hash = __flow_hash_from_keys(&keys);
+	skb->hash = hash;
 }
 EXPORT_SYMBOL(__skb_get_hash);
 
-/*
- * 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 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
 {
-	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;
-	}
+	struct flow_keys keys;
 
-	return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
+	return ___skb_get_hash(skb, &keys, perturb);
 }
-EXPORT_SYMBOL(__skb_tx_hash);
+EXPORT_SYMBOL(skb_get_hash_perturb);
 
 u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 		   const struct flow_keys *keys, int hlen)
 {
-	u32 poff = keys->thoff;
+	u32 poff = keys->control.thoff;
 
-	switch (keys->ip_proto) {
+	switch (keys->basic.ip_proto) {
 	case IPPROTO_TCP: {
 		/* access doff as u8 to avoid unaligned access */
 		const u8 *doff;
@@ -396,8 +670,12 @@ u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 	return poff;
 }
 
-/* skb_get_poff() returns the offset to the payload as far as it could
- * be dissected. The main user is currently BPF, so that we can dynamically
+/**
+ * skb_get_poff - get the offset to the payload
+ * @skb: sk_buff to get the payload offset from
+ *
+ * The function will get the offset to the payload as far as it could
+ * be dissected.  The main user is currently BPF, so that we can dynamically
  * truncate packets without needing to push actual payload to the user
  * space and can analyze headers only, instead.
  */
@@ -405,86 +683,76 @@ u32 skb_get_poff(const struct sk_buff *skb)
 {
 	struct flow_keys keys;
 
-	if (!skb_flow_dissect(skb, &keys))
+	if (!skb_flow_dissect_flow_keys(skb, &keys))
 		return 0;
 
 	return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
 }
 
-static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+static const struct flow_dissector_key flow_keys_dissector_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v4addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v6addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_TIPC_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.tipcaddrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct flow_keys, ports),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_VLANID,
+		.offset = offsetof(struct flow_keys, tags),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL,
+		.offset = offsetof(struct flow_keys, tags),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_GRE_KEYID,
+		.offset = offsetof(struct flow_keys, keyid),
+	},
+};
+
+static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+};
+
+struct flow_dissector flow_keys_dissector __read_mostly;
+EXPORT_SYMBOL(flow_keys_dissector);
+
+struct flow_dissector flow_keys_buf_dissector __read_mostly;
+
+static int __init init_default_flow_dissectors(void)
 {
-#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;
+	skb_flow_dissector_init(&flow_keys_dissector,
+				flow_keys_dissector_keys,
+				ARRAY_SIZE(flow_keys_dissector_keys));
+	skb_flow_dissector_init(&flow_keys_buf_dissector,
+				flow_keys_buf_dissector_keys,
+				ARRAY_SIZE(flow_keys_buf_dissector_keys));
+	return 0;
 }
 
-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);
-}
+late_initcall_sync(init_default_flow_dissectors);