Merge branch 'cls_flower'

Jiri Pirko says:

====================
introduce programable flow dissector and cls_flower

Per Davem's request, I prepared this patchset which introduces programmable
flow dissector. For current users of flow_keys, there is a wrapper
skb_flow_dissect_flow_keys which maintains the previous behaviour.
For purposes of cls_flower, couple of new dissection keys were introduced.

Note that this dissector can be also eventually used by openvswitch code.

Also, as a next step, I plan to get rid of *skb_flow_get_ports(export)
and *__skb_get_poff as their functionality can be now implemented by
skb_flow_dissect as well.

v2->v3:
- remove TCA_FLOWER_POLICE attr suggested by Jamal

v1->v2:
- move __skb_tx_hash rather to dev.c as suggested by Alex
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/bonding/bond_main.c

@@ -76,7 +76,7 @@
 #include <net/netns/generic.h>
 #include <net/pkt_sched.h>
 #include <linux/rculist.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
 #include <net/switchdev.h>
 #include <net/bonding.h>
 #include <net/bond_3ad.h>
@@ -3051,16 +3051,16 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
 	int noff, proto = -1;
 
 	if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23)
-		return skb_flow_dissect(skb, fk);
+		return skb_flow_dissect_flow_keys(skb, fk);
 
-	fk->ports = 0;
+	fk->ports.ports = 0;
 	noff = skb_network_offset(skb);
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
 			return false;
 		iph = ip_hdr(skb);
-		fk->src = iph->saddr;
-		fk->dst = iph->daddr;
+		fk->addrs.src = iph->saddr;
+		fk->addrs.dst = iph->daddr;
 		noff += iph->ihl << 2;
 		if (!ip_is_fragment(iph))
 			proto = iph->protocol;
@@ -3068,15 +3068,15 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
 		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph6))))
 			return false;
 		iph6 = ipv6_hdr(skb);
-		fk->src = (__force __be32)ipv6_addr_hash(&iph6->saddr);
-		fk->dst = (__force __be32)ipv6_addr_hash(&iph6->daddr);
+		fk->addrs.src = (__force __be32)ipv6_addr_hash(&iph6->saddr);
+		fk->addrs.dst = (__force __be32)ipv6_addr_hash(&iph6->daddr);
 		noff += sizeof(*iph6);
 		proto = iph6->nexthdr;
 	} else {
 		return false;
 	}
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34 && proto >= 0)
-		fk->ports = skb_flow_get_ports(skb, noff, proto);
+		fk->ports.ports = skb_flow_get_ports(skb, noff, proto);
 
 	return true;
 }
@@ -3102,8 +3102,8 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23)
 		hash = bond_eth_hash(skb);
 	else
-		hash = (__force u32)flow.ports;
-	hash ^= (__force u32)flow.dst ^ (__force u32)flow.src;
+		hash = (__force u32)flow.ports.ports;
+	hash ^= (__force u32)flow.addrs.dst ^ (__force u32)flow.addrs.src;
 	hash ^= (hash >> 16);
 	hash ^= (hash >> 8);
 

drivers/net/ethernet/cisco/enic/enic_clsf.c

@@ -5,7 +5,7 @@
 #include <linux/in.h>
 #include <linux/types.h>
 #include <linux/skbuff.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
 #include "enic_res.h"
 #include "enic_clsf.h"
 
@@ -22,7 +22,7 @@ int enic_addfltr_5t(struct enic *enic, struct flow_keys *keys, u16 rq)
 	int res;
 	struct filter data;
 
-	switch (keys->ip_proto) {
+	switch (keys->basic.ip_proto) {
 	case IPPROTO_TCP:
 		data.u.ipv4.protocol = PROTO_TCP;
 		break;
@@ -33,10 +33,10 @@ int enic_addfltr_5t(struct enic *enic, struct flow_keys *keys, u16 rq)
 		return -EPROTONOSUPPORT;
 	};
 	data.type = FILTER_IPV4_5TUPLE;
-	data.u.ipv4.src_addr = ntohl(keys->src);
-	data.u.ipv4.dst_addr = ntohl(keys->dst);
-	data.u.ipv4.src_port = ntohs(keys->port16[0]);
-	data.u.ipv4.dst_port = ntohs(keys->port16[1]);
+	data.u.ipv4.src_addr = ntohl(keys->addrs.src);
+	data.u.ipv4.dst_addr = ntohl(keys->addrs.dst);
+	data.u.ipv4.src_port = ntohs(keys->ports.src);
+	data.u.ipv4.dst_port = ntohs(keys->ports.dst);
 	data.u.ipv4.flags = FILTER_FIELDS_IPV4_5TUPLE;
 
 	spin_lock_bh(&enic->devcmd_lock);
@@ -158,11 +158,11 @@ static struct enic_rfs_fltr_node *htbl_key_search(struct hlist_head *h,
 	struct enic_rfs_fltr_node *tpos;
 
 	hlist_for_each_entry(tpos, h, node)
-		if (tpos->keys.src == k->src &&
-		    tpos->keys.dst == k->dst &&
-		    tpos->keys.ports == k->ports &&
-		    tpos->keys.ip_proto == k->ip_proto &&
-		    tpos->keys.n_proto == k->n_proto)
+		if (tpos->keys.addrs.src == k->addrs.src &&
+		    tpos->keys.addrs.dst == k->addrs.dst &&
+		    tpos->keys.ports.ports == k->ports.ports &&
+		    tpos->keys.basic.ip_proto == k->basic.ip_proto &&
+		    tpos->keys.basic.n_proto == k->basic.n_proto)
 			return tpos;
 	return NULL;
 }
@@ -177,9 +177,10 @@ int enic_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	int res, i;
 
 	enic = netdev_priv(dev);
-	res = skb_flow_dissect(skb, &keys);
-	if (!res || keys.n_proto != htons(ETH_P_IP) ||
-	    (keys.ip_proto != IPPROTO_TCP && keys.ip_proto != IPPROTO_UDP))
+	res = skb_flow_dissect_flow_keys(skb, &keys);
+	if (!res || keys.basic.n_proto != htons(ETH_P_IP) ||
+	    (keys.basic.ip_proto != IPPROTO_TCP &&
+	     keys.basic.ip_proto != IPPROTO_UDP))
 		return -EPROTONOSUPPORT;
 
 	tbl_idx = skb_get_hash_raw(skb) & ENIC_RFS_FLW_MASK;

drivers/net/ethernet/cisco/enic/enic_ethtool.c

@@ -334,7 +334,7 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd)
 	n = htbl_fltr_search(enic, (u16)fsp->location);
 	if (!n)
 		return -EINVAL;
-	switch (n->keys.ip_proto) {
+	switch (n->keys.basic.ip_proto) {
 	case IPPROTO_TCP:
 		fsp->flow_type = TCP_V4_FLOW;
 		break;
@@ -346,16 +346,16 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd)
 		break;
 	}
 
-	fsp->h_u.tcp_ip4_spec.ip4src = n->keys.src;
+	fsp->h_u.tcp_ip4_spec.ip4src = n->keys.addrs.src;
 	fsp->m_u.tcp_ip4_spec.ip4src = (__u32)~0;
 
-	fsp->h_u.tcp_ip4_spec.ip4dst = n->keys.dst;
+	fsp->h_u.tcp_ip4_spec.ip4dst = n->keys.addrs.dst;
 	fsp->m_u.tcp_ip4_spec.ip4dst = (__u32)~0;
 
-	fsp->h_u.tcp_ip4_spec.psrc = n->keys.port16[0];
+	fsp->h_u.tcp_ip4_spec.psrc = n->keys.ports.src;
 	fsp->m_u.tcp_ip4_spec.psrc = (__u16)~0;
 
-	fsp->h_u.tcp_ip4_spec.pdst = n->keys.port16[1];
+	fsp->h_u.tcp_ip4_spec.pdst = n->keys.ports.dst;
 	fsp->m_u.tcp_ip4_spec.pdst = (__u16)~0;
 
 	fsp->ring_cookie = n->rq_id;

drivers/net/hyperv/netvsc_drv.c

@@ -196,12 +196,12 @@ 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;

include/linux/netdevice.h

@@ -2832,6 +2832,9 @@ static inline int netif_set_xps_queue(struct net_device *dev,
 }
 #endif
 
+u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
+		  unsigned int num_tx_queues);
+
 /*
  * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used
  * as a distribution range limit for the returned value.

include/linux/skbuff.h

@@ -34,7 +34,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/netdev_features.h>
 #include <linux/sched.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
 
 /* A. Checksumming of received packets by device.
  *
@@ -918,7 +918,6 @@ skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type)
 	skb->hash = hash;
 }
 
-void __skb_get_hash(struct sk_buff *skb);
 static inline __u32 skb_get_hash(struct sk_buff *skb)
 {
 	if (!skb->l4_hash && !skb->sw_hash)
@@ -1936,8 +1935,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb,
 
 	if (skb_transport_header_was_set(skb))
 		return;
-	else if (skb_flow_dissect(skb, &keys))
-		skb_set_transport_header(skb, keys.thoff);
+	else if (skb_flow_dissect_flow_keys(skb, &keys))
+		skb_set_transport_header(skb, keys.basic.thoff);
 	else
 		skb_set_transport_header(skb, offset_hint);
 }
@@ -3300,9 +3299,6 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb)
 	return skb->queue_mapping != 0;
 }
 
-u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
-		  unsigned int num_tx_queues);
-
 static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
 {
 #ifdef CONFIG_XFRM
@@ -3424,10 +3420,6 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb,
 				     unsigned int transport_len,
 				     __sum16(*skb_chkf)(struct sk_buff *skb));
 
-u32 skb_get_poff(const struct sk_buff *skb);
-u32 __skb_get_poff(const struct sk_buff *skb, void *data,
-		   const struct flow_keys *keys, int hlen);
-
 /**
  * skb_head_is_locked - Determine if the skb->head is locked down
  * @skb: skb to check

include/net/flow_dissector.h

+#ifndef _NET_FLOW_DISSECTOR_H
+#define _NET_FLOW_DISSECTOR_H
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/in6.h>
+#include <uapi/linux/if_ether.h>
+
+/**
+ * struct flow_dissector_key_basic:
+ * @thoff: Transport header offset
+ * @n_proto: Network header protocol (eg. IPv4/IPv6)
+ * @ip_proto: Transport header protocol (eg. TCP/UDP)
+ */
+struct flow_dissector_key_basic {
+	u16	thoff;
+	__be16	n_proto;
+	u8	ip_proto;
+};
+
+/**
+ * struct flow_dissector_key_addrs:
+ * @src: source ip address in case of IPv4
+ *	 For IPv6 it contains 32bit hash of src address
+ * @dst: destination ip address in case of IPv4
+ *	 For IPv6 it contains 32bit hash of dst address
+ */
+struct flow_dissector_key_addrs {
+	/* (src,dst) must be grouped, in the same way than in IP header */
+	__be32 src;
+	__be32 dst;
+};
+
+/**
+ * flow_dissector_key_tp_ports:
+ *	@ports: port numbers of Transport header
+ *		src: source port number
+ *		dst: destination port number
+ */
+struct flow_dissector_key_ports {
+	union {
+		__be32 ports;
+		struct {
+			__be16 src;
+			__be16 dst;
+		};
+	};
+};
+
+/**
+ * struct flow_dissector_key_ipv6_addrs:
+ * @src: source ip address
+ * @dst: destination ip address
+ */
+struct flow_dissector_key_ipv6_addrs {
+	/* (src,dst) must be grouped, in the same way than in IP header */
+	struct in6_addr src;
+	struct in6_addr dst;
+};
+
+/**
+ * struct flow_dissector_key_eth_addrs:
+ * @src: source Ethernet address
+ * @dst: destination Ethernet address
+ */
+struct flow_dissector_key_eth_addrs {
+	/* (dst,src) must be grouped, in the same way than in ETH header */
+	unsigned char dst[ETH_ALEN];
+	unsigned char src[ETH_ALEN];
+};
+
+enum flow_dissector_key_id {
+	FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
+	FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_addrs */
+	FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS, /* struct flow_dissector_key_addrs */
+	FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */
+	FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */
+	FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */
+
+	FLOW_DISSECTOR_KEY_MAX,
+};
+
+struct flow_dissector_key {
+	enum flow_dissector_key_id key_id;
+	size_t offset; /* offset of struct flow_dissector_key_*
+			  in target the struct */
+};
+
+struct flow_dissector {
+	unsigned int used_keys; /* each bit repesents presence of one key id */
+	unsigned short int offset[FLOW_DISSECTOR_KEY_MAX];
+};
+
+void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
+			     const struct flow_dissector_key *key,
+			     unsigned int key_count);
+
+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);
+
+static inline bool skb_flow_dissect(const struct sk_buff *skb,
+				    struct flow_dissector *flow_dissector,
+				    void *target_container)
+{
+	return __skb_flow_dissect(skb, flow_dissector, target_container,
+				  NULL, 0, 0, 0);
+}
+
+struct flow_keys {
+	struct flow_dissector_key_addrs addrs;
+	struct flow_dissector_key_ports ports;
+	struct flow_dissector_key_basic basic;
+};
+
+extern struct flow_dissector flow_keys_dissector;
+extern struct flow_dissector flow_keys_buf_dissector;
+
+static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
+					      struct flow_keys *flow)
+{
+	memset(flow, 0, sizeof(*flow));
+	return __skb_flow_dissect(skb, &flow_keys_dissector, flow,
+				  NULL, 0, 0, 0);
+}
+
+static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow,
+						  void *data, __be16 proto,
+						  int nhoff, int hlen)
+{
+	memset(flow, 0, sizeof(*flow));
+	return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow,
+				  data, proto, nhoff, hlen);
+}
+
+__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
+			    void *data, int hlen_proto);
+
+static inline __be32 skb_flow_get_ports(const struct sk_buff *skb,
+					int thoff, u8 ip_proto)
+{
+	return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
+}
+
+u32 flow_hash_from_keys(struct flow_keys *keys);
+void __skb_get_hash(struct sk_buff *skb);
+u32 skb_get_poff(const struct sk_buff *skb);
+u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+		   const struct flow_keys *keys, int hlen);
+
+/* struct flow_keys_digest:
+ *
+ * This structure is used to hold a digest of the full flow keys. This is a
+ * larger "hash" of a flow to allow definitively matching specific flows where
+ * the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so
+ * that it can by used in CB of skb (see sch_choke for an example).
+ */
+#define FLOW_KEYS_DIGEST_LEN	16
+struct flow_keys_digest {
+	u8	data[FLOW_KEYS_DIGEST_LEN];
+};
+
+void make_flow_keys_digest(struct flow_keys_digest *digest,
+			   const struct flow_keys *flow);
+
+#endif

include/net/flow_keys.h

-#ifndef _NET_FLOW_KEYS_H
-#define _NET_FLOW_KEYS_H
-
-/* struct flow_keys:
- *	@src: source ip address in case of IPv4
- *	      For IPv6 it contains 32bit hash of src address
- *	@dst: destination ip address in case of IPv4
- *	      For IPv6 it contains 32bit hash of dst address
- *	@ports: port numbers of Transport header
- *		port16[0]: src port number
- *		port16[1]: dst port number
- *	@thoff: Transport header offset
- *	@n_proto: Network header protocol (eg. IPv4/IPv6)
- *	@ip_proto: Transport header protocol (eg. TCP/UDP)
- * All the members, except thoff, are in network byte order.
- */
-struct flow_keys {
-	/* (src,dst) must be grouped, in the same way than in IP header */
-	__be32 src;
-	__be32 dst;
-	union {
-		__be32 ports;
-		__be16 port16[2];
-	};
-	u16	thoff;
-	__be16	n_proto;
-	u8	ip_proto;
-};
-
-bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
-			void *data, __be16 proto, int nhoff, int hlen);
-static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
-{
-	return __skb_flow_dissect(skb, flow, NULL, 0, 0, 0);
-}
-__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
-			    void *data, int hlen_proto);
-static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto)
-{
-	return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
-}
-u32 flow_hash_from_keys(struct flow_keys *keys);
-unsigned int flow_get_hlen(const unsigned char *data, unsigned int max_len,
-			   __be16 protocol);
-
-/* struct flow_keys_digest:
- *
- * This structure is used to hold a digest of the full flow keys. This is a
- * larger "hash" of a flow to allow definitively matching specific flows where
- * the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so
- * that it can by used in CB of skb (see sch_choke for an example).
- */
-#define FLOW_KEYS_DIGEST_LEN	16
-struct flow_keys_digest {
-	u8	data[FLOW_KEYS_DIGEST_LEN];
-};
-
-void make_flow_keys_digest(struct flow_keys_digest *digest,
-			   const struct flow_keys *flow);
-
-#endif

include/net/ip.h

@@ -31,7 +31,7 @@
 #include <net/route.h>
 #include <net/snmp.h>
 #include <net/flow.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
 
 struct sock;
 
@@ -360,10 +360,10 @@ static inline void inet_set_txhash(struct sock *sk)
 	struct inet_sock *inet = inet_sk(sk);
 	struct flow_keys keys;
 
-	keys.src = inet->inet_saddr;
-	keys.dst = inet->inet_daddr;
-	keys.port16[0] = inet->inet_sport;
-	keys.port16[1] = inet->inet_dport;
+	keys.addrs.src = inet->inet_saddr;
+	keys.addrs.dst = inet->inet_daddr;
+	keys.ports.src = inet->inet_sport;
+	keys.ports.dst = inet->inet_dport;
 
 	sk->sk_txhash = flow_hash_from_keys(&keys);
 }

include/net/ipv6.h

@@ -19,7 +19,7 @@
 #include <net/if_inet6.h>
 #include <net/ndisc.h>
 #include <net/flow.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
 #include <net/snmp.h>
 
 #define SIN6_LEN_RFC2133	24
@@ -698,10 +698,10 @@ static inline void ip6_set_txhash(struct sock *sk)
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct flow_keys keys;
 
-	keys.src = (__force __be32)ipv6_addr_hash(&np->saddr);
-	keys.dst = (__force __be32)ipv6_addr_hash(&sk->sk_v6_daddr);
-	keys.port16[0] = inet->inet_sport;
-	keys.port16[1] = inet->inet_dport;
+	keys.addrs.src = (__force __be32)ipv6_addr_hash(&np->saddr);
+	keys.addrs.dst = (__force __be32)ipv6_addr_hash(&sk->sk_v6_daddr);
+	keys.ports.src = inet->inet_sport;
+	keys.ports.dst = inet->inet_dport;
 
 	sk->sk_txhash = flow_hash_from_keys(&keys);
 }

include/uapi/linux/pkt_cls.h

@@ -409,6 +409,36 @@ enum {
 
 #define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
 
+/* Flower classifier */
+
+enum {
+	TCA_FLOWER_UNSPEC,
+	TCA_FLOWER_CLASSID,
+	TCA_FLOWER_INDEV,
+	TCA_FLOWER_ACT,
+	TCA_FLOWER_KEY_ETH_DST,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_DST_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_TYPE,	/* be16 */
+	TCA_FLOWER_KEY_IP_PROTO,	/* u8 */
+	TCA_FLOWER_KEY_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_SRC_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_SRC_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_TCP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_TCP_DST,		/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_UDP_DST,		/* be16 */
+	__TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
 /* Extended Matches */
 
 struct tcf_ematch_tree_hdr {

net/core/dev.c

@@ -2350,6 +2350,34 @@ 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;
@@ -2908,6 +2936,84 @@ 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

net/core/filter.c

@@ -36,6 +36,7 @@
 #include <net/netlink.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
+#include <net/flow_dissector.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
 #include <asm/uaccess.h>

net/ethernet/eth.c

@@ -58,6 +58,7 @@
 #include <net/ipv6.h>
 #include <net/ip.h>
 #include <net/dsa.h>
+#include <net/flow_dissector.h>
 #include <linux/uaccess.h>
 
 __setup("ether=", netdev_boot_setup);
@@ -130,9 +131,9 @@ u32 eth_get_headlen(void *data, unsigned int len)
 		return len;
 
 	/* parse any remaining L2/L3 headers, check for L4 */
-	if (!__skb_flow_dissect(NULL, &keys, data,
-				eth->h_proto, sizeof(*eth), len))
-		return max_t(u32, keys.thoff, sizeof(*eth));
+	if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto,
+					    sizeof(*eth), len))
+		return max_t(u32, keys.basic.thoff, sizeof(*eth));
 
 	/* parse for any L4 headers */
 	return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);

net/sched/Kconfig

@@ -477,6 +477,16 @@ config NET_CLS_BPF
 	  To compile this code as a module, choose M here: the module will
 	  be called cls_bpf.
 
+config NET_CLS_FLOWER
+	tristate "Flower classifier"
+	select NET_CLS
+	---help---
+	  If you say Y here, you will be able to classify packets based on
+	  a configurable combination of packet keys and masks.
+
+	  To compile this code as a module, choose M here: the module will
+	  be called cls_flower.
+
 config NET_EMATCH
 	bool "Extended Matches"
 	select NET_CLS

net/sched/Makefile

@@ -56,6 +56,7 @@ obj-$(CONFIG_NET_CLS_BASIC)	+= cls_basic.o
 obj-$(CONFIG_NET_CLS_FLOW)	+= cls_flow.o
 obj-$(CONFIG_NET_CLS_CGROUP)	+= cls_cgroup.o
 obj-$(CONFIG_NET_CLS_BPF)	+= cls_bpf.o
+obj-$(CONFIG_NET_CLS_FLOWER)	+= cls_flower.o
 obj-$(CONFIG_NET_EMATCH)	+= ematch.o
 obj-$(CONFIG_NET_EMATCH_CMP)	+= em_cmp.o
 obj-$(CONFIG_NET_EMATCH_NBYTE)	+= em_nbyte.o

net/sched/cls_flow.c

@@ -26,7 +26,7 @@
 #include <net/pkt_cls.h>
 #include <net/ip.h>
 #include <net/route.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netfilter/nf_conntrack.h>
@@ -68,35 +68,35 @@ static inline u32 addr_fold(void *addr)
 
 static u32 flow_get_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	if (flow->src)
-		return ntohl(flow->src);
+	if (flow->addrs.src)
+		return ntohl(flow->addrs.src);
 	return addr_fold(skb->sk);
 }
 
 static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	if (flow->dst)
-		return ntohl(flow->dst);
+	if (flow->addrs.dst)
+		return ntohl(flow->addrs.dst);
 	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
 }
 
 static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	return flow->ip_proto;
+	return flow->basic.ip_proto;
 }
 
 static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	if (flow->ports)
-		return ntohs(flow->port16[0]);
+	if (flow->ports.ports)
+		return ntohs(flow->ports.src);
 
 	return addr_fold(skb->sk);
 }
 
 static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	if (flow->ports)
-		return ntohs(flow->port16[1]);
+	if (flow->ports.ports)
+		return ntohs(flow->ports.dst);
 
 	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
 }
@@ -295,7 +295,7 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 		keymask = f->keymask;
 		if (keymask & FLOW_KEYS_NEEDED)
-			skb_flow_dissect(skb, &flow_keys);
+			skb_flow_dissect_flow_keys(skb, &flow_keys);
 
 		for (n = 0; n < f->nkeys; n++) {
 			key = ffs(keymask) - 1;

net/sched/sch_choke.c

@@ -18,7 +18,7 @@
 #include <net/pkt_sched.h>
 #include <net/inet_ecn.h>
 #include <net/red.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
 
 /*
    CHOKe stateless AQM for fair bandwidth allocation
@@ -170,13 +170,13 @@ static bool choke_match_flow(struct sk_buff *skb1,
 
 	if (!choke_skb_cb(skb1)->keys_valid) {
 		choke_skb_cb(skb1)->keys_valid = 1;
-		skb_flow_dissect(skb1, &temp);
+		skb_flow_dissect_flow_keys(skb1, &temp);
 		make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp);
 	}
 
 	if (!choke_skb_cb(skb2)->keys_valid) {
 		choke_skb_cb(skb2)->keys_valid = 1;
-		skb_flow_dissect(skb2, &temp);
+		skb_flow_dissect_flow_keys(skb2, &temp);
 		make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp);
 	}