openvswitch: 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.

Signed-off-by: Ansis Atteka <aatteka@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>

2 files changed, 113 insertions, 0 deletions

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 08114478cb85..a58ed276f70d 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/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>
 
@@ -162,6 +163,53 @@ 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 || skb->ip_summed == CHECKSUM_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->rxhash = 0;
+        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));
@@ -195,6 +243,47 @@ 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 = IP6_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)
@@ -347,6 +436,10 @@ 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;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 4c4b62ccc7d7..fd4a6a4ce3cd 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -479,6 +479,7 @@ static int validate_set(const struct nlattr *a,
 
         switch (key_type) {
         const struct ovs_key_ipv4 *ipv4_key;
+        const struct ovs_key_ipv6 *ipv6_key;
 
         case OVS_KEY_ATTR_PRIORITY:
         case OVS_KEY_ATTR_ETHERNET:
@@ -500,6 +501,25 @@ 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;