net: Add full IPv6 addresses to flow_keys

This patch adds full IPv6 addresses into flow_keys and uses them as input to the flow hash function. The implementation supports either IPv4 or IPv6 addresses in a union, and selector is used to determine how may words to input to jhash2. We also add flow_get_u32_dst and flow_get_u32_src functions which are used to get a u32 representation of the source and destination addresses. For IPv6, ipv6_addr_hash is called. These functions retain getting the legacy values of src and dst in flow_keys. With this patch, Ethertype and IP protocol are now included in the flow hash input. Signed-off-by: Tom Herbert <[email protected]> Signed-off-by: David S. Miller <[email protected]>
tdeneau · Jun 4, 2015 · c3f8324 · c3f8324
1 parent 42aecaa
commit c3f8324
Show file tree

Hide file tree

Showing 10 changed files with 193 additions and 63 deletions.
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
@@ -3059,17 +3059,15 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
 		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
 			return false;
 		iph = ip_hdr(skb);
-		fk->addrs.src = iph->saddr;
-		fk->addrs.dst = iph->daddr;
+		iph_to_flow_copy_v4addrs(fk, iph);
 		noff += iph->ihl << 2;
 		if (!ip_is_fragment(iph))
 			proto = iph->protocol;
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
 		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph6))))
 			return false;
 		iph6 = ipv6_hdr(skb);
-		fk->addrs.src = (__force __be32)ipv6_addr_hash(&iph6->saddr);
-		fk->addrs.dst = (__force __be32)ipv6_addr_hash(&iph6->daddr);
+		iph_to_flow_copy_v6addrs(fk, iph6);
 		noff += sizeof(*iph6);
 		proto = iph6->nexthdr;
 	} else {
@@ -3103,7 +3101,8 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 		hash = bond_eth_hash(skb);
 	else
 		hash = (__force u32)flow.ports.ports;
-	hash ^= (__force u32)flow.addrs.dst ^ (__force u32)flow.addrs.src;
+	hash ^= (__force u32)flow_get_u32_dst(&flow) ^
+		(__force u32)flow_get_u32_src(&flow);
 	hash ^= (hash >> 16);
 	hash ^= (hash >> 8);
 

diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.c b/drivers/net/ethernet/cisco/enic/enic_clsf.c
@@ -33,8 +33,8 @@ 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->addrs.src);
-	data.u.ipv4.dst_addr = ntohl(keys->addrs.dst);
+	data.u.ipv4.src_addr = ntohl(keys->addrs.v4addrs.src);
+	data.u.ipv4.dst_addr = ntohl(keys->addrs.v4addrs.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;
@@ -158,8 +158,8 @@ 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.addrs.src == k->addrs.src &&
-		    tpos->keys.addrs.dst == k->addrs.dst &&
+		if (tpos->keys.addrs.v4addrs.src == k->addrs.v4addrs.src &&
+		    tpos->keys.addrs.v4addrs.dst == k->addrs.v4addrs.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)

diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -346,10 +346,10 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd)
 		break;
 	}
 
-	fsp->h_u.tcp_ip4_spec.ip4src = n->keys.addrs.src;
+	fsp->h_u.tcp_ip4_spec.ip4src = flow_get_u32_src(&n->keys);
 	fsp->m_u.tcp_ip4_spec.ip4src = (__u32)~0;
 
-	fsp->h_u.tcp_ip4_spec.ip4dst = n->keys.addrs.dst;
+	fsp->h_u.tcp_ip4_spec.ip4dst = flow_get_u32_dst(&n->keys);
 	fsp->m_u.tcp_ip4_spec.ip4dst = (__u32)~0;
 
 	fsp->h_u.tcp_ip4_spec.psrc = n->keys.ports.src;

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
@@ -12,7 +12,7 @@
  */
 struct flow_dissector_key_control {
 	u16	thoff;
-	u16	padding;
+	u16	addr_type;
 };
 
 /**
@@ -28,18 +28,39 @@ struct flow_dissector_key_basic {
 };
 
 /**
- * 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_ipv4_addrs:
+ * @src: source ip address
+ * @dst: destination ip address
  */
-struct flow_dissector_key_addrs {
+struct flow_dissector_key_ipv4_addrs {
 	/* (src,dst) must be grouped, in the same way than in IP header */
 	__be32 src;
 	__be32 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_addrs:
+ * @v4addrs: IPv4 addresses
+ * @v6addrs: IPv6 addresses
+ */
+struct flow_dissector_key_addrs {
+	union {
+		struct flow_dissector_key_ipv4_addrs v4addrs;
+		struct flow_dissector_key_ipv6_addrs v6addrs;
+	};
+};
+
 /**
  * flow_dissector_key_tp_ports:
  *	@ports: port numbers of Transport header
@@ -56,16 +77,6 @@ struct flow_dissector_key_ports {
 	};
 };
 
-/**
- * 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:
@@ -81,10 +92,10 @@ struct flow_dissector_key_eth_addrs {
 enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
 	FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
-	FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_addrs */
+	FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */
+	FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_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,
@@ -129,6 +140,9 @@ struct flow_keys {
 #define FLOW_KEYS_HASH_OFFSET		\
 	offsetof(struct flow_keys, FLOW_KEYS_HASH_START_FIELD)
 
+__be32 flow_get_u32_src(const struct flow_keys *flow);
+__be32 flow_get_u32_dst(const struct flow_keys *flow);
+
 extern struct flow_dissector flow_keys_dissector;
 extern struct flow_dissector flow_keys_buf_dissector;
 

diff --git a/include/net/ip.h b/include/net/ip.h
@@ -355,15 +355,30 @@ static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto)
 				  skb->len, proto, 0);
 }
 
+/* copy IPv4 saddr & daddr to flow_keys, possibly using 64bit load/store
+ * Equivalent to :	flow->v4addrs.src = iph->saddr;
+ *			flow->v4addrs.dst = iph->daddr;
+ */
+static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow,
+					    const struct iphdr *iph)
+{
+	BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) !=
+		     offsetof(typeof(flow->addrs), v4addrs.src) +
+			      sizeof(flow->addrs.v4addrs.src));
+	memcpy(&flow->addrs.v4addrs, &iph->saddr, sizeof(flow->addrs.v4addrs));
+	flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+}
+
 static inline void inet_set_txhash(struct sock *sk)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct flow_keys keys;
 
 	memset(&keys, 0, sizeof(keys));
 
-	keys.addrs.src = inet->inet_saddr;
-	keys.addrs.dst = inet->inet_daddr;
+	keys.addrs.v4addrs.src = inet->inet_saddr;
+	keys.addrs.v4addrs.dst = inet->inet_daddr;
+	keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 	keys.ports.src = inet->inet_sport;
 	keys.ports.dst = inet->inet_dport;
 

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
@@ -692,6 +692,20 @@ static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6,
 	return hlimit;
 }
 
+/* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store
+ * Equivalent to :	flow->v6addrs.src = iph->saddr;
+ *			flow->v6addrs.dst = iph->daddr;
+ */
+static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow,
+					    const struct ipv6hdr *iph)
+{
+	BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) !=
+		     offsetof(typeof(flow->addrs), v6addrs.src) +
+		     sizeof(flow->addrs.v6addrs.src));
+	memcpy(&flow->addrs.v6addrs, &iph->saddr, sizeof(flow->addrs.v6addrs));
+	flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 static inline void ip6_set_txhash(struct sock *sk)
 {
@@ -701,8 +715,11 @@ static inline void ip6_set_txhash(struct sock *sk)
 
 	memset(&keys, 0, sizeof(keys));
 
-	keys.addrs.src = (__force __be32)ipv6_addr_hash(&np->saddr);
-	keys.addrs.dst = (__force __be32)ipv6_addr_hash(&sk->sk_v6_daddr);
+	memcpy(&keys.addrs.v6addrs.src, &np->saddr,
+	       sizeof(keys.addrs.v6addrs.src));
+	memcpy(&keys.addrs.v6addrs.dst, &sk->sk_v6_daddr,
+	       sizeof(keys.addrs.v6addrs.dst));
+	keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 	keys.ports.src = inet->inet_sport;
 	keys.ports.dst = inet->inet_dport;