datapath: add ipv6 'set' action

This patch adds ipv6 set action functionality. It allows to change
traffic class, flow label, hop-limit, ipv6 source and destination
address fields.

Acked-by: Jesse Gross <[email protected]>
Signed-off-by: Ansis Atteka <[email protected]>

NEWS

@@ -7,6 +7,7 @@ v1.9.0 - xx xxx xxxx
     - The tunneling code no longer assumes input and output keys are symmetric.
       If they are not, PMTUD needs to be disabled for tunneling to work. Note
       this only applies to flow-based keys.
+    - Datapath: Support for ipv6 set action.
     - FreeBSD is now a supported platform, thanks to code contributions from
       Gaetano Catalli, Ed Maste, and Giuseppe Lettieri.
     - ovs-bugtool: New --ovs option to report only OVS related information.

datapath/actions.c

@@ -28,6 +28,7 @@
 #include <linux/if_arp.h>
 #include <linux/if_vlan.h>
 #include <net/ip.h>
+#include <net/ipv6.h>
 #include <net/checksum.h>
 #include <net/dsfield.h>
 
@@ -166,6 +167,54 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
 	*addr = new_addr;
 }
 
+static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,
+				 __be32 addr[4], const __be32 new_addr[4])
+{
+	int transport_len = skb->len - skb_transport_offset(skb);
+
+	if (l4_proto == IPPROTO_TCP) {
+		if (likely(transport_len >= sizeof(struct tcphdr)))
+			inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb,
+						  addr, new_addr, 1);
+	} else if (l4_proto == IPPROTO_UDP) {
+		if (likely(transport_len >= sizeof(struct udphdr))) {
+			struct udphdr *uh = udp_hdr(skb);
+
+			if (uh->check ||
+			    get_ip_summed(skb) == OVS_CSUM_PARTIAL) {
+				inet_proto_csum_replace16(&uh->check, skb,
+							  addr, new_addr, 1);
+				if (!uh->check)
+					uh->check = CSUM_MANGLED_0;
+			}
+		}
+	}
+}
+
+static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
+			  __be32 addr[4], const __be32 new_addr[4],
+			  bool recalculate_csum)
+{
+	if (recalculate_csum)
+		update_ipv6_checksum(skb, l4_proto, addr, new_addr);
+
+	skb_clear_rxhash(skb);
+	memcpy(addr, new_addr, sizeof(__be32[4]));
+}
+
+static void set_ipv6_tc(struct ipv6hdr *nh, u8 tc)
+{
+	nh->priority = tc >> 4;
+	nh->flow_lbl[0] = (nh->flow_lbl[0] & 0x0F) | ((tc & 0x0F) << 4);
+}
+
+static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl)
+{
+	nh->flow_lbl[0] = (nh->flow_lbl[0] & 0xF0) | (fl & 0x000F0000) >> 16;
+	nh->flow_lbl[1] = (fl & 0x0000FF00) >> 8;
+	nh->flow_lbl[2] = fl & 0x000000FF;
+}
+
 static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl)
 {
 	csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
@@ -199,6 +248,47 @@ static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key)
 	return 0;
 }
 
+static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key)
+{
+	struct ipv6hdr *nh;
+	int err;
+	__be32 *saddr;
+	__be32 *daddr;
+
+	err = make_writable(skb, skb_network_offset(skb) +
+			    sizeof(struct ipv6hdr));
+	if (unlikely(err))
+		return err;
+
+	nh = ipv6_hdr(skb);
+	saddr = (__be32 *)&nh->saddr;
+	daddr = (__be32 *)&nh->daddr;
+
+	if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src)))
+		set_ipv6_addr(skb, ipv6_key->ipv6_proto, saddr,
+			      ipv6_key->ipv6_src, true);
+
+	if (memcmp(ipv6_key->ipv6_dst, daddr, sizeof(ipv6_key->ipv6_dst))) {
+		unsigned int offset = 0;
+		int flags = OVS_IP6T_FH_F_SKIP_RH;
+		bool recalc_csum = true;
+
+		if (ipv6_ext_hdr(nh->nexthdr))
+			recalc_csum = ipv6_find_hdr(skb, &offset,
+						    NEXTHDR_ROUTING, NULL,
+						    &flags) != NEXTHDR_ROUTING;
+
+		set_ipv6_addr(skb, ipv6_key->ipv6_proto, daddr,
+			      ipv6_key->ipv6_dst, recalc_csum);
+	}
+
+	set_ipv6_tc(nh, ipv6_key->ipv6_tclass);
+	set_ipv6_fl(nh, ntohl(ipv6_key->ipv6_label));
+	nh->hop_limit = ipv6_key->ipv6_hlimit;
+
+	return 0;
+}
+
 /* Must follow make_writable() since that can move the skb data. */
 static void set_tp_port(struct sk_buff *skb, __be16 *port,
 			 __be16 new_port, __sum16 *check)
@@ -373,6 +463,10 @@ static int execute_set_action(struct sk_buff *skb,
 		err = set_ipv4(skb, nla_data(nested_attr));
 		break;
 
+	case OVS_KEY_ATTR_IPV6:
+		err = set_ipv6(skb, nla_data(nested_attr));
+		break;
+
 	case OVS_KEY_ATTR_TCP:
 		err = set_tcp(skb, nla_data(nested_attr));
 		break;

datapath/checksum.h

@@ -102,6 +102,30 @@ static inline void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
 }
 #endif
 
+#if defined(NEED_CSUM_NORMALIZE) || LINUX_VERSION_CODE < KERNEL_VERSION(3,7,0)
+#define inet_proto_csum_replace16 rpl_inet_proto_csum_replace16
+static inline void inet_proto_csum_replace16(__sum16 *sum,
+					     struct sk_buff *skb,
+					     const __be32 *from,
+					     const __be32 *to,
+					     int pseudohdr)
+{
+	__be32 diff[] = {
+		~from[0], ~from[1], ~from[2], ~from[3],
+		to[0], to[1], to[2], to[3],
+	};
+	if (get_ip_summed(skb) != OVS_CSUM_PARTIAL) {
+		*sum = csum_fold(csum_partial(diff, sizeof(diff),
+				 ~csum_unfold(*sum)));
+		if (get_ip_summed(skb) == OVS_CSUM_COMPLETE && pseudohdr)
+			skb->csum = ~csum_partial(diff, sizeof(diff),
+						  ~skb->csum);
+	} else if (pseudohdr)
+		*sum = ~csum_fold(csum_partial(diff, sizeof(diff),
+				  csum_unfold(*sum)));
+}
+#endif
+
 #ifdef NEED_CSUM_NORMALIZE
 static inline void update_csum_start(struct sk_buff *skb, int delta)
 {

datapath/datapath.c

@@ -588,6 +588,7 @@ static int validate_set(const struct nlattr *a,
 	switch (key_type) {
 	const struct ovs_key_ipv4 *ipv4_key;
 	const struct ovs_key_ipv4_tunnel *tun_key;
+	const struct ovs_key_ipv6 *ipv6_key;
 
 	case OVS_KEY_ATTR_PRIORITY:
 	case OVS_KEY_ATTR_TUN_ID:
@@ -616,6 +617,25 @@ static int validate_set(const struct nlattr *a,
 
 		break;
 
+	case OVS_KEY_ATTR_IPV6:
+		if (flow_key->eth.type != htons(ETH_P_IPV6))
+			return -EINVAL;
+
+		if (!flow_key->ip.proto)
+			return -EINVAL;
+
+		ipv6_key = nla_data(ovs_key);
+		if (ipv6_key->ipv6_proto != flow_key->ip.proto)
+			return -EINVAL;
+
+		if (ipv6_key->ipv6_frag != flow_key->ip.frag)
+			return -EINVAL;
+
+		if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000)
+			return -EINVAL;
+
+		break;
+
 	case OVS_KEY_ATTR_TCP:
 		if (flow_key->ip.proto != IPPROTO_TCP)
 			return -EINVAL;

debian/changelog

@@ -11,6 +11,7 @@ openvswitch (1.9.0-1) unstable; urgency=low
     - The tunneling code no longer assumes input and output keys are symmetric.
       If they are not, PMTUD needs to be disabled for tunneling to work. Note
       this only applies to flow-based keys.
+    - Datapath: Support for ipv6 set action.
     - FreeBSD is now a supported platform, thanks to code contributions from
       Gaetano Catalli, Ed Maste, and Giuseppe Lettieri.
     - ovs-bugtool: New --ovs option to report only OVS related information.

lib/csum.c

@@ -112,6 +112,21 @@ recalc_csum32(ovs_be16 old_csum, ovs_be32 old_u32, ovs_be32 new_u32)
                          old_u32 >> 16, new_u32 >> 16);
 }
 
+/* Returns the new checksum for a packet in which the checksum field previously
+ * contained 'old_csum' and in which a field that contained 'old_u32[4]' was
+ * changed to contain 'new_u32[4]'. */
+ovs_be16
+recalc_csum128(ovs_be16 old_csum, ovs_be32 old_u32[4],
+               const ovs_be32 new_u32[4])
+{
+    ovs_be16 new_csum = old_csum;
+    int i;
+
+    for (i = 0; i < 4; ++i) {
+        new_csum = recalc_csum32(new_csum, old_u32[i], new_u32[i]);
+    }
+    return new_csum;
+}
 #else  /* __CHECKER__ */
 /* Making sparse happy with these functions also makes them unreadable, so
  * don't bother to show it their implementations. */

lib/csum.h

@@ -28,5 +28,7 @@ uint32_t csum_continue(uint32_t partial, const void *, size_t);
 ovs_be16 csum_finish(uint32_t partial);
 ovs_be16 recalc_csum16(ovs_be16 old_csum, ovs_be16 old_u16, ovs_be16 new_u16);
 ovs_be16 recalc_csum32(ovs_be16 old_csum, ovs_be32 old_u32, ovs_be32 new_u32);
+ovs_be16 recalc_csum128(ovs_be16 old_csum, ovs_be32 old_u32[4],
+                        const ovs_be32 new_u32[4]);
 
 #endif /* csum.h */

lib/dpif-netdev.c

@@ -1181,13 +1181,13 @@ execute_set_action(struct ofpbuf *packet, const struct nlattr *a)
 {
     enum ovs_key_attr type = nl_attr_type(a);
     const struct ovs_key_ipv4 *ipv4_key;
+    const struct ovs_key_ipv6 *ipv6_key;
     const struct ovs_key_tcp *tcp_key;
     const struct ovs_key_udp *udp_key;
 
     switch (type) {
     case OVS_KEY_ATTR_TUN_ID:
     case OVS_KEY_ATTR_PRIORITY:
-    case OVS_KEY_ATTR_IPV6:
     case OVS_KEY_ATTR_IPV4_TUNNEL:
         /* not implemented */
         break;
@@ -1203,6 +1203,13 @@ execute_set_action(struct ofpbuf *packet, const struct nlattr *a)
                         ipv4_key->ipv4_tos, ipv4_key->ipv4_ttl);
         break;
 
+    case OVS_KEY_ATTR_IPV6:
+        ipv6_key = nl_attr_get_unspec(a, sizeof(struct ovs_key_ipv6));
+        packet_set_ipv6(packet, ipv6_key->ipv6_proto, ipv6_key->ipv6_src,
+                        ipv6_key->ipv6_dst, ipv6_key->ipv6_tclass,
+                        ipv6_key->ipv6_label, ipv6_key->ipv6_hlimit);
+        break;
+
     case OVS_KEY_ATTR_TCP:
         tcp_key = nl_attr_get_unspec(a, sizeof(struct ovs_key_tcp));
         packet_set_tcp_port(packet, tcp_key->tcp_src, tcp_key->tcp_dst);