/*
- * Copyright (c) 2007-2011 Nicira Networks.
+ * Copyright (c) 2007-2012 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
#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>
#include "vport.h"
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr, int len, bool keep_skb);
+ const struct nlattr *attr, int len,
+ struct ovs_key_ipv4_tunnel *tun_key, bool keep_skb);
static int make_writable(struct sk_buff *skb, int write_len)
{
return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
}
-/* remove VLAN header from packet and update csum accrodingly. */
+/* remove VLAN header from packet and update csum accordingly. */
static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
{
struct vlan_hdr *vhdr;
inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
*addr, new_addr, 1);
} else if (nh->protocol == IPPROTO_UDP) {
- if (likely(transport_len >= sizeof(struct udphdr)))
- inet_proto_csum_replace4(&udp_hdr(skb)->check, skb,
- *addr, new_addr, 1);
+ 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_replace4(&uh->check, skb,
+ *addr, new_addr, 1);
+ if (!uh->check)
+ uh->check = CSUM_MANGLED_0;
+ }
+ }
}
csum_replace4(&nh->check, *addr, new_addr);
*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));
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)
skb_clear_rxhash(skb);
}
-static int set_udp_port(struct sk_buff *skb,
- const struct ovs_key_udp *udp_port_key)
+static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
+{
+ struct udphdr *uh = udp_hdr(skb);
+
+ if (uh->check && get_ip_summed(skb) != OVS_CSUM_PARTIAL) {
+ set_tp_port(skb, port, new_port, &uh->check);
+
+ if (!uh->check)
+ uh->check = CSUM_MANGLED_0;
+ } else {
+ *port = new_port;
+ skb_clear_rxhash(skb);
+ }
+}
+
+static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key)
{
struct udphdr *uh;
int err;
uh = udp_hdr(skb);
if (udp_port_key->udp_src != uh->source)
- set_tp_port(skb, &uh->source, udp_port_key->udp_src, &uh->check);
+ set_udp_port(skb, &uh->source, udp_port_key->udp_src);
if (udp_port_key->udp_dst != uh->dest)
- set_tp_port(skb, &uh->dest, udp_port_key->udp_dst, &uh->check);
+ set_udp_port(skb, &uh->dest, udp_port_key->udp_dst);
return 0;
}
-static int set_tcp_port(struct sk_buff *skb,
- const struct ovs_key_tcp *tcp_port_key)
+static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key)
{
struct tcphdr *th;
int err;
if (unlikely(!skb))
return -ENOMEM;
- vport = rcu_dereference(dp->ports[out_port]);
+ vport = ovs_vport_rcu(dp, out_port);
if (unlikely(!vport)) {
kfree_skb(skb);
return -ENODEV;
}
- vport_send(vport, skb);
+ ovs_vport_send(vport, skb);
return 0;
}
}
}
- return dp_upcall(dp, skb, &upcall);
+ return ovs_dp_upcall(dp, skb, &upcall);
}
static int sample(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr)
+ const struct nlattr *attr,
+ struct ovs_key_ipv4_tunnel *tun_key)
{
const struct nlattr *acts_list = NULL;
const struct nlattr *a;
}
return do_execute_actions(dp, skb, nla_data(acts_list),
- nla_len(acts_list), true);
+ nla_len(acts_list), tun_key, true);
}
static int execute_set_action(struct sk_buff *skb,
- const struct nlattr *nested_attr)
+ const struct nlattr *nested_attr,
+ struct ovs_key_ipv4_tunnel *tun_key)
{
int err = 0;
break;
case OVS_KEY_ATTR_TUN_ID:
- OVS_CB(skb)->tun_id = nla_get_be64(nested_attr);
+ /* If we're only using the TUN_ID action, store the value in a
+ * temporary instance of struct ovs_key_ipv4_tunnel on the stack.
+ * If both IPV4_TUNNEL and TUN_ID are being used together we
+ * can't write into the IPV4_TUNNEL action, so make a copy and
+ * write into that version.
+ */
+ if (!OVS_CB(skb)->tun_key)
+ memset(tun_key, 0, sizeof(*tun_key));
+ else if (OVS_CB(skb)->tun_key != tun_key)
+ memcpy(tun_key, OVS_CB(skb)->tun_key, sizeof(*tun_key));
+ OVS_CB(skb)->tun_key = tun_key;
+
+ OVS_CB(skb)->tun_key->tun_id = nla_get_be64(nested_attr);
+ break;
+
+ case OVS_KEY_ATTR_IPV4_TUNNEL:
+ OVS_CB(skb)->tun_key = nla_data(nested_attr);
break;
case OVS_KEY_ATTR_ETHERNET:
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_port(skb, nla_data(nested_attr));
+ err = set_tcp(skb, nla_data(nested_attr));
break;
case OVS_KEY_ATTR_UDP:
- err = set_udp_port(skb, nla_data(nested_attr));
+ err = set_udp(skb, nla_data(nested_attr));
break;
}
/* Execute a list of actions against 'skb'. */
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr, int len, bool keep_skb)
+ const struct nlattr *attr, int len,
+ struct ovs_key_ipv4_tunnel *tun_key, bool keep_skb)
{
/* Every output action needs a separate clone of 'skb', but the common
* case is just a single output action, so that doing a clone and
break;
case OVS_ACTION_ATTR_SET:
- err = execute_set_action(skb, nla_data(a));
+ err = execute_set_action(skb, nla_data(a), tun_key);
break;
case OVS_ACTION_ATTR_SAMPLE:
- err = sample(dp, skb, a);
+ err = sample(dp, skb, a, tun_key);
break;
}
{
if (net_ratelimit())
pr_warn("%s: flow looped %d times, dropping\n",
- dp_name(dp), MAX_LOOPS);
+ ovs_dp_name(dp), MAX_LOOPS);
actions->actions_len = 0;
return -ELOOP;
}
/* Execute a list of actions against 'skb'. */
-int execute_actions(struct datapath *dp, struct sk_buff *skb)
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb)
{
struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
struct loop_counter *loop;
int error;
+ struct ovs_key_ipv4_tunnel tun_key;
/* Check whether we've looped too much. */
loop = &__get_cpu_var(loop_counters);
goto out_loop;
}
- OVS_CB(skb)->tun_id = 0;
+ OVS_CB(skb)->tun_key = NULL;
error = do_execute_actions(dp, skb, acts->actions,
- acts->actions_len, false);
+ acts->actions_len, &tun_key, false);
/* Check whether sub-actions looped too much. */
if (unlikely(loop->looping))