/*
- * Copyright (c) 2007-2012 Nicira Networks.
+ * Copyright (c) 2007-2014 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/in.h>
#include <linux/ip.h>
#include <linux/openvswitch.h>
+#include <linux/sctp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/in6.h>
#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 <net/sctp/checksum.h>
-#include "checksum.h"
#include "datapath.h"
#include "vlan.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, 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;
if (unlikely(err))
return err;
- if (get_ip_summed(skb) == OVS_CSUM_COMPLETE)
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_sub(skb->csum, csum_partial(skb->data
- + ETH_HLEN, VLAN_HLEN, 0));
+ + (2 * ETH_ALEN), VLAN_HLEN, 0));
vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
*current_tci = vhdr->h_vlan_TCI;
if (unlikely(err))
return err;
- __vlan_hwaccel_put_tag(skb, ntohs(tci));
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(tci));
return 0;
}
/* push down current VLAN tag */
current_tag = vlan_tx_tag_get(skb);
- if (!__vlan_put_tag(skb, current_tag))
+ if (!__vlan_put_tag(skb, skb->vlan_proto, current_tag))
return -ENOMEM;
- if (get_ip_summed(skb) == OVS_CSUM_COMPLETE)
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_add(skb->csum, csum_partial(skb->data
- + ETH_HLEN, VLAN_HLEN, 0));
+ + (2 * ETH_ALEN), VLAN_HLEN, 0));
}
- __vlan_hwaccel_put_tag(skb, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
+ __vlan_hwaccel_put_tag(skb, vlan->vlan_tpid, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
return 0;
}
if (unlikely(err))
return err;
- memcpy(eth_hdr(skb)->h_source, eth_key->eth_src, ETH_ALEN);
- memcpy(eth_hdr(skb)->h_dest, eth_key->eth_dst, ETH_ALEN);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
+
+ ether_addr_copy(eth_hdr(skb)->h_source, eth_key->eth_src);
+ ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst);
+
+ ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
return 0;
}
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
- if (uh->check ||
- get_ip_summed(skb) == OVS_CSUM_PARTIAL) {
+ if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace4(&uh->check, skb,
*addr, new_addr, 1);
if (!uh->check)
*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_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)
{
struct udphdr *uh = udp_hdr(skb);
- if (uh->check && get_ip_summed(skb) != OVS_CSUM_PARTIAL) {
+ if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
set_tp_port(skb, port, new_port, &uh->check);
if (!uh->check)
return 0;
}
+static int set_sctp(struct sk_buff *skb,
+ const struct ovs_key_sctp *sctp_port_key)
+{
+ struct sctphdr *sh;
+ int err;
+ unsigned int sctphoff = skb_transport_offset(skb);
+
+ err = make_writable(skb, sctphoff + sizeof(struct sctphdr));
+ if (unlikely(err))
+ return err;
+
+ sh = sctp_hdr(skb);
+ if (sctp_port_key->sctp_src != sh->source ||
+ sctp_port_key->sctp_dst != sh->dest) {
+ __le32 old_correct_csum, new_csum, old_csum;
+
+ old_csum = sh->checksum;
+ old_correct_csum = sctp_compute_cksum(skb, sctphoff);
+
+ sh->source = sctp_port_key->sctp_src;
+ sh->dest = sctp_port_key->sctp_dst;
+
+ new_csum = sctp_compute_cksum(skb, sctphoff);
+
+ /* Carry any checksum errors through. */
+ sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
+
+ skb_clear_rxhash(skb);
+ }
+
+ return 0;
+}
+
static int do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
{
struct vport *vport;
const struct nlattr *a;
int rem;
+ BUG_ON(!OVS_CB(skb)->pkt_key);
+
upcall.cmd = OVS_PACKET_CMD_ACTION;
- upcall.key = &OVS_CB(skb)->flow->key;
+ upcall.key = OVS_CB(skb)->pkt_key;
upcall.userdata = NULL;
- upcall.pid = 0;
+ upcall.portid = 0;
for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
a = nla_next(a, &rem)) {
break;
case OVS_USERSPACE_ATTR_PID:
- upcall.pid = nla_get_u32(a);
+ upcall.portid = nla_get_u32(a);
break;
}
}
}
return do_execute_actions(dp, skb, nla_data(acts_list),
- nla_len(acts_list), true);
+ nla_len(acts_list), true);
+}
+
+static void execute_hash(struct sk_buff *skb, const struct nlattr *attr)
+{
+ struct sw_flow_key *key = OVS_CB(skb)->pkt_key;
+ struct ovs_action_hash *hash_act = nla_data(attr);
+ u32 hash = 0;
+
+ /* OVS_HASH_ALG_L4 is the only possible hash algorithm. */
+ hash = skb_get_rxhash(skb);
+ hash = jhash_1word(hash, hash_act->hash_basis);
+ if (!hash)
+ hash = 0x1;
+
+ key->ovs_flow_hash = hash;
}
static int execute_set_action(struct sk_buff *skb,
skb->priority = nla_get_u32(nested_attr);
break;
- case OVS_KEY_ATTR_TUN_ID:
- OVS_CB(skb)->tun_id = nla_get_be64(nested_attr);
+ case OVS_KEY_ATTR_SKB_MARK:
+ skb->mark = nla_get_u32(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(skb, nla_data(nested_attr));
break;
case OVS_KEY_ATTR_UDP:
err = set_udp(skb, nla_data(nested_attr));
break;
+
+ case OVS_KEY_ATTR_SCTP:
+ err = set_sctp(skb, nla_data(nested_attr));
+ break;
}
return err;
}
+static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
+ const struct nlattr *a)
+{
+ struct sw_flow_key recirc_key;
+ const struct vport *p = OVS_CB(skb)->input_vport;
+ uint32_t hash = OVS_CB(skb)->pkt_key->ovs_flow_hash;
+ int err;
+
+ err = ovs_flow_extract(skb, p->port_no, &recirc_key);
+ if (err)
+ return err;
+
+ recirc_key.ovs_flow_hash = hash;
+ recirc_key.recirc_id = nla_get_u32(a);
+
+ ovs_dp_process_packet_with_key(skb, &recirc_key);
+
+ return 0;
+}
+
/* 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)
output_userspace(dp, skb, a);
break;
+ case OVS_ACTION_ATTR_HASH:
+ execute_hash(skb, a);
+ break;
+
case OVS_ACTION_ATTR_PUSH_VLAN:
err = push_vlan(skb, nla_data(a));
if (unlikely(err)) /* skb already freed. */
err = pop_vlan(skb);
break;
+ case OVS_ACTION_ATTR_RECIRC: {
+ struct sk_buff *recirc_skb;
+ const bool last_action = (a->nla_len == rem);
+
+ if (!last_action || keep_skb)
+ recirc_skb = skb_clone(skb, GFP_ATOMIC);
+ else
+ recirc_skb = skb;
+
+ err = execute_recirc(dp, recirc_skb, a);
+
+ if (last_action || err)
+ return err;
+
+ break;
+ }
+
case OVS_ACTION_ATTR_SET:
err = execute_set_action(skb, nla_data(a));
break;
case OVS_ACTION_ATTR_SAMPLE:
err = sample(dp, skb, a);
+ if (unlikely(err)) /* skb already freed. */
+ return err;
break;
}
/* We limit the number of times that we pass into execute_actions()
* to avoid blowing out the stack in the event that we have a loop. */
-#define MAX_LOOPS 5
+#define MAX_LOOPS 4
struct loop_counter {
u8 count; /* Count. */
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);