/* derived from ip_tunnel_rcv(). */
void ovs_ip_tunnel_rcv(struct net_device *dev, struct sk_buff *skb,
struct metadata_dst *tun_dst)
{
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,39)
struct pcpu_sw_netstats *tstats;
tstats = this_cpu_ptr((struct pcpu_sw_netstats __percpu *)dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
#endif
skb_reset_mac_header(skb);
skb_scrub_packet(skb, false);
skb->protocol = eth_type_trans(skb, dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
ovs_skb_dst_set(skb, (struct dst_entry *)tun_dst);
#ifndef USE_UPSTREAM_TUNNEL
netdev_port_receive(skb, &tun_dst->u.tun_info);
#else
netif_rx(skb);
#endif
}
static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const __be16 ethertype)
{
struct ethhdr *hdr;
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, skb_mpls_header(skb), MPLS_HLEN);
memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
skb->mac_len);
__skb_pull(skb, MPLS_HLEN);
skb_reset_mac_header(skb);
/* skb_mpls_header() is used to locate the ethertype
* field correctly in the presence of VLAN tags.
*/
hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN);
hdr->h_proto = ethertype;
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
invalidate_flow_key(key);
return 0;
}
static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const __be16 ethertype)
{
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
skb->mac_len);
__skb_pull(skb, MPLS_HLEN);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->mac_len);
if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET) {
struct ethhdr *hdr;
/* mpls_hdr() is used to locate the ethertype field correctly in the
* presence of VLAN tags.
*/
hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
update_ethertype(skb, hdr, ethertype);
}
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
invalidate_flow_key(key);
return 0;
}
static int internal_dev_recv(struct vport *vport, struct sk_buff *skb)
{
struct net_device *netdev = netdev_vport_priv(vport)->dev;
int len;
if (unlikely(!(netdev->flags & IFF_UP))) {
kfree_skb(skb);
return 0;
}
len = skb->len;
skb_dst_drop(skb);
nf_reset(skb);
secpath_reset(skb);
skb->dev = netdev;
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, netdev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
netif_rx(skb);
return len;
}
static netdev_tx_t internal_dev_recv(struct sk_buff *skb)
{
struct net_device *netdev = skb->dev;
struct pcpu_sw_netstats *stats;
if (unlikely(!(netdev->flags & IFF_UP))) {
kfree_skb(skb);
netdev->stats.rx_dropped++;
return NETDEV_TX_OK;
}
skb_dst_drop(skb);
nf_reset(skb);
secpath_reset(skb);
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, netdev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
stats = this_cpu_ptr(netdev->tstats);
u64_stats_update_begin(&stats->syncp);
stats->rx_packets++;
stats->rx_bytes += skb->len;
u64_stats_update_end(&stats->syncp);
netif_rx(skb);
return NETDEV_TX_OK;
}
/* Called with rcu_read_lock and BH disabled. */
static int gre_rcv(struct sk_buff *skb)
{
struct ovs_net *ovs_net;
struct vport *vport;
int hdr_len;
struct iphdr *iph;
struct ovs_key_ipv4_tunnel tun_key;
__be16 gre_flags;
u32 tnl_flags;
__be64 key;
bool is_gre64;
if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr) + ETH_HLEN)))
goto error;
if (unlikely(!check_checksum(skb)))
goto error;
hdr_len = parse_header(ip_hdr(skb), &gre_flags, &key, &is_gre64);
if (unlikely(hdr_len < 0))
goto error;
ovs_net = net_generic(dev_net(skb->dev), ovs_net_id);
if (is_gre64)
vport = rcu_dereference(ovs_net->vport_net.gre64_vport);
else
vport = rcu_dereference(ovs_net->vport_net.gre_vport);
if (unlikely(!vport))
goto error;
if (unlikely(!pskb_may_pull(skb, hdr_len + ETH_HLEN)))
goto error;
iph = ip_hdr(skb);
tnl_flags = gre_flags_to_tunnel_flags(gre_flags, is_gre64);
tnl_tun_key_init(&tun_key, iph, key, tnl_flags);
OVS_CB(skb)->tun_key = &tun_key;
__skb_pull(skb, hdr_len);
skb_postpull_rcsum(skb, skb_transport_header(skb), hdr_len + ETH_HLEN);
ovs_tnl_rcv(vport, skb);
return 0;
error:
kfree_skb(skb);
return 0;
}
static int set_eth_addr(struct sk_buff *skb,
const struct ovs_key_ethernet *eth_key)
{
int err;
err = make_writable(skb, ETH_HLEN);
if (unlikely(err))
return err;
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;
}
static bool udpencap_remove_header(struct sk_buff *skb, const struct xt_udpencap_tginfo *info)
{
unsigned int nlen = skb_transport_offset(skb);
if (!skb_make_writable(&skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
return false;
if (skb->len < nlen + sizeof(struct udphdr))
return false;
if (!pskb_pull(skb, sizeof(struct udphdr)))
return false;
skb_postpull_rcsum(skb, skb_transport_header(skb), sizeof(struct udphdr));
memmove(skb->data, skb->data - sizeof(struct udphdr), nlen);
skb->network_header += sizeof(struct udphdr);
skb->transport_header += sizeof(struct udphdr);
return true;
}
static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_ethernet *key,
const struct ovs_key_ethernet *mask)
{
int err;
err = skb_ensure_writable(skb, ETH_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
//added by daolicloud
if (ETH_P_ARP == ntohs(eth_hdr(skb)->h_proto)) {
struct arphdr *p = arp_hdr(skb);
unsigned char ip[4];
struct arpft *pdata = (struct arpft *)((unsigned char *)p + sizeof(struct arphdr));
if(ARPOP_REQUEST == ntohs(p->ar_op)) {
p->ar_op = htons(ARPOP_REPLY);
memcpy(ip, pdata->ar_sip, 4);
memcpy(pdata->ar_sha, key->eth_src, ETH_ALEN);
memcpy(pdata->ar_sip, pdata->ar_tip, 4);
memcpy(pdata->ar_tha, eth_hdr(skb)->h_source, ETH_ALEN);
memcpy(pdata->ar_tip, ip, 4);
memcpy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source, ETH_ALEN);
} else {
ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
mask->eth_dst);
}
} else {
ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
mask->eth_dst);
}
////
ether_addr_copy_masked(eth_hdr(skb)->h_source, key->eth_src,
mask->eth_src);
ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
return 0;
}
static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_ethernet *key,
const struct ovs_key_ethernet *mask)
{
int err;
err = skb_ensure_writable(skb, ETH_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
ether_addr_copy_masked(eth_hdr(skb)->h_source, key->eth_src,
mask->eth_src);
ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
mask->eth_dst);
ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
return 0;
}
static int internal_dev_recv(struct vport *vport, struct sk_buff *skb)
{
struct net_device *netdev = netdev_vport_priv(vport)->dev;
int len;
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,37)
if (vlan_tx_tag_present(skb)) {
if (unlikely(!__vlan_put_tag(skb,
skb->vlan_proto,
vlan_tx_tag_get(skb))))
return 0;
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_add(skb->csum,
csum_partial(skb->data + (2 * ETH_ALEN),
VLAN_HLEN, 0));
vlan_set_tci(skb, 0);
}
#endif
len = skb->len;
skb_dst_drop(skb);
nf_reset(skb);
secpath_reset(skb);
skb->dev = netdev;
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, netdev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
netif_rx(skb);
return len;
}
/* <DTS2012022805249 g00206962 2012/2/27 add begin */
static inline int ip6_input_icmp_cheat(struct sk_buff *skb)
{
struct inet6_protocol *ipprot;
unsigned int nhoff;
int nexthdr, raw;
u8 hash;
struct inet6_dev *idev;
struct net *net = dev_net(skb->dst->dev);
/*
* Parse extension headers
*/
rcu_read_lock();
resubmit:
idev = ip6_dst_idev(skb->dst);
if (!pskb_pull(skb, skb_transport_offset(skb)))
goto discard;
nhoff = IP6CB(skb)->nhoff;
nexthdr = skb_network_header(skb)[nhoff];
raw = raw6_local_deliver(skb, nexthdr);
hash = nexthdr & (MAX_INET_PROTOS - 1);
if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) {
int ret;
if (ipprot->flags & INET6_PROTO_FINAL) {
struct ipv6hdr *hdr;
/* Free reference early: we don't need it any more,
and it may hold ip_conntrack module loaded
indefinitely. */
nf_reset(skb);
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
hdr = ipv6_hdr(skb);
/*
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
&hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr))
goto discard;
*/
if (ipv6_addr_is_multicast(&hdr->daddr) && IPPROTO_ICMPV6 != nexthdr)
goto discard;
else if (!ipv6_addr_is_multicast(&hdr->daddr))
goto discard;
}
if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
ret = ipprot->handler(skb);
if (ret > 0)
goto resubmit;
else if (ret == 0)
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS);
} else {
if (!raw) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP6_INC_STATS_BH(net, idev,
IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff,
skb->dev);
}
} else
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
rcu_read_unlock();
return 0;
discard:
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS);
rcu_read_unlock();
kfree_skb(skb);
return 0;
}
static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
const struct inet6_protocol *ipprot;
struct inet6_dev *idev;
unsigned int nhoff;
int nexthdr;
bool raw;
bool have_final = false;
/*
* Parse extension headers
*/
rcu_read_lock();
resubmit:
idev = ip6_dst_idev(skb_dst(skb));
if (!pskb_pull(skb, skb_transport_offset(skb)))
goto discard;
nhoff = IP6CB(skb)->nhoff;
nexthdr = skb_network_header(skb)[nhoff];
resubmit_final:
raw = raw6_local_deliver(skb, nexthdr);
ipprot = rcu_dereference(inet6_protos[nexthdr]);
if (ipprot) {
int ret;
if (have_final) {
if (!(ipprot->flags & INET6_PROTO_FINAL)) {
/* Once we've seen a final protocol don't
* allow encapsulation on any non-final
* ones. This allows foo in UDP encapsulation
* to work.
*/
goto discard;
}
} else if (ipprot->flags & INET6_PROTO_FINAL) {
const struct ipv6hdr *hdr;
/* Only do this once for first final protocol */
have_final = true;
/* Free reference early: we don't need it any more,
and it may hold ip_conntrack module loaded
indefinitely. */
nf_reset(skb);
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
hdr = ipv6_hdr(skb);
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
&hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
goto discard;
}
if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
ret = ipprot->handler(skb);
if (ret > 0) {
if (ipprot->flags & INET6_PROTO_FINAL) {
/* Not an extension header, most likely UDP
* encapsulation. Use return value as nexthdr
* protocol not nhoff (which presumably is
* not set by handler).
*/
nexthdr = ret;
goto resubmit_final;
} else {
goto resubmit;
}
} else if (ret == 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
}
} else {
if (!raw) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
__IP6_INC_STATS(net, idev,
IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff);
}
kfree_skb(skb);
} else {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
consume_skb(skb);
}
}
rcu_read_unlock();
return 0;
discard:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
rcu_read_unlock();
kfree_skb(skb);
return 0;
}
/*
* Determine the packet's protocol ID. The rule here is that we
* assume 802.3 if the type field is short enough to be a length.
* This is normal practice and works for any 'now in use' protocol.
*
* Also, at this point we assume that we ARE dealing exclusively with
* VLAN packets, or packets that should be made into VLAN packets based
* on a default VLAN ID.
*
* NOTE: Should be similar to ethernet/eth.c.
*
* SANITY NOTE: This method is called when a packet is moving up the stack
* towards userland. To get here, it would have already passed
* through the ethernet/eth.c eth_type_trans() method.
* SANITY NOTE 2: We are referencing to the VLAN_HDR frields, which MAY be
* stored UNALIGNED in the memory. RISC systems don't like
* such cases very much...
* SANITY NOTE 2a: According to Dave Miller & Alexey, it will always be aligned,
* so there doesn't need to be any of the unaligned stuff. It has
* been commented out now... --Ben
*
*/
int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev,
struct packet_type* ptype, struct net_device *orig_dev)
{
unsigned char *rawp = NULL;
struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data);
unsigned short vid;
struct net_device_stats *stats;
unsigned short vlan_TCI;
__be16 proto;
/* vlan_TCI = ntohs(get_unaligned(&vhdr->h_vlan_TCI)); */
vlan_TCI = ntohs(vhdr->h_vlan_TCI);
vid = (vlan_TCI & VLAN_VID_MASK);
#ifdef VLAN_DEBUG
printk(VLAN_DBG "%s: skb: %p vlan_id: %hx\n",
__FUNCTION__, skb, vid);
#endif
/* Ok, we will find the correct VLAN device, strip the header,
* and then go on as usual.
*/
/* We have 12 bits of vlan ID.
*
* We must not drop allow preempt until we hold a
* reference to the device (netif_rx does that) or we
* fail.
*/
rcu_read_lock();
skb->dev = __find_vlan_dev(dev, vid);
if (!skb->dev) {
rcu_read_unlock();
#ifdef VLAN_DEBUG
printk(VLAN_DBG "%s: ERROR: No net_device for VID: %i on dev: %s [%i]\n",
__FUNCTION__, (unsigned int)(vid), dev->name, dev->ifindex);
#endif
kfree_skb(skb);
return -1;
}
skb->dev->last_rx = jiffies;
/* Bump the rx counters for the VLAN device. */
stats = vlan_dev_get_stats(skb->dev);
stats->rx_packets++;
stats->rx_bytes += skb->len;
skb_pull(skb, VLAN_HLEN); /* take off the VLAN header (4 bytes currently) */
/* Need to correct hardware checksum */
skb_postpull_rcsum(skb, vhdr, VLAN_HLEN);
/* Ok, lets check to make sure the device (dev) we
* came in on is what this VLAN is attached to.
*/
if (dev != VLAN_DEV_INFO(skb->dev)->real_dev) {
rcu_read_unlock();
#ifdef VLAN_DEBUG
printk(VLAN_DBG "%s: dropping skb: %p because came in on wrong device, dev: %s real_dev: %s, skb_dev: %s\n",
__FUNCTION__, skb, dev->name,
VLAN_DEV_INFO(skb->dev)->real_dev->name,
skb->dev->name);
#endif
kfree_skb(skb);
stats->rx_errors++;
return -1;
}
/*
* Deal with ingress priority mapping.
*/
skb->priority = vlan_get_ingress_priority(skb->dev, ntohs(vhdr->h_vlan_TCI));
#ifdef VLAN_DEBUG
printk(VLAN_DBG "%s: priority: %lu for TCI: %hu (hbo)\n",
__FUNCTION__, (unsigned long)(skb->priority),
ntohs(vhdr->h_vlan_TCI));
#endif
/* The ethernet driver already did the pkt_type calculations
* for us...
*/
switch (skb->pkt_type) {
case PACKET_BROADCAST: /* Yeah, stats collect these together.. */
// stats->broadcast ++; // no such counter :-(
break;
case PACKET_MULTICAST:
stats->multicast++;
break;
case PACKET_OTHERHOST:
/* Our lower layer thinks this is not local, let's make sure.
* This allows the VLAN to have a different MAC than the underlying
* device, and still route correctly.
*/
if (memcmp(eth_hdr(skb)->h_dest, skb->dev->dev_addr, ETH_ALEN) == 0) {
/* It is for our (changed) MAC-address! */
skb->pkt_type = PACKET_HOST;
}
break;
default:
break;
};
/* Was a VLAN packet, grab the encapsulated protocol, which the layer
* three protocols care about.
*/
/* proto = get_unaligned(&vhdr->h_vlan_encapsulated_proto); */
proto = vhdr->h_vlan_encapsulated_proto;
skb->protocol = proto;
if (ntohs(proto) >= 1536) {
/* place it back on the queue to be handled by
* true layer 3 protocols.
*/
/* See if we are configured to re-write the VLAN header
* to make it look like ethernet...
*/
skb = vlan_check_reorder_header(skb);
/* Can be null if skb-clone fails when re-ordering */
if (skb) {
netif_rx(skb);
} else {
/* TODO: Add a more specific counter here. */
stats->rx_errors++;
}
rcu_read_unlock();
return 0;
}
rawp = skb->data;
/*
* This is a magic hack to spot IPX packets. Older Novell breaks
* the protocol design and runs IPX over 802.3 without an 802.2 LLC
* layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
* won't work for fault tolerant netware but does for the rest.
*/
if (*(unsigned short *)rawp == 0xFFFF) {
skb->protocol = __constant_htons(ETH_P_802_3);
/* place it back on the queue to be handled by true layer 3 protocols.
*/
/* See if we are configured to re-write the VLAN header
* to make it look like ethernet...
*/
skb = vlan_check_reorder_header(skb);
/* Can be null if skb-clone fails when re-ordering */
if (skb) {
netif_rx(skb);
} else {
/* TODO: Add a more specific counter here. */
stats->rx_errors++;
}
rcu_read_unlock();
return 0;
}
/*
* Real 802.2 LLC
*/
skb->protocol = __constant_htons(ETH_P_802_2);
/* place it back on the queue to be handled by upper layer protocols.
*/
/* See if we are configured to re-write the VLAN header
* to make it look like ethernet...
*/
skb = vlan_check_reorder_header(skb);
/* Can be null if skb-clone fails when re-ordering */
if (skb) {
netif_rx(skb);
} else {
/* TODO: Add a more specific counter here. */
stats->rx_errors++;
}
rcu_read_unlock();
return 0;
}
/* geneve receive/decap routine */
static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
{
struct genevehdr *gnvh = geneve_hdr(skb);
struct metadata_dst *tun_dst;
struct geneve_dev *geneve = NULL;
#ifdef HAVE_DEV_TSTATS
struct pcpu_sw_netstats *stats;
#endif
struct iphdr *iph;
u8 *vni;
__be32 addr;
int err;
union {
struct metadata_dst dst;
char buf[sizeof(struct metadata_dst) + 256];
} buf;
iph = ip_hdr(skb); /* outer IP header... */
if (gs->collect_md) {
static u8 zero_vni[3];
vni = zero_vni;
addr = 0;
} else {
vni = gnvh->vni;
addr = iph->saddr;
}
geneve = geneve_lookup(gs, addr, vni);
if (!geneve)
goto drop;
if (ip_tunnel_collect_metadata() || gs->collect_md) {
__be16 flags;
flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
(gnvh->oam ? TUNNEL_OAM : 0) |
(gnvh->critical ? TUNNEL_CRIT_OPT : 0);
tun_dst = &buf.dst;
ovs_udp_tun_rx_dst(&tun_dst->u.tun_info, skb, AF_INET, flags,
vni_to_tunnel_id(gnvh->vni), gnvh->opt_len * 4);
/* Update tunnel dst according to Geneve options. */
ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
gnvh->options, gnvh->opt_len * 4);
} else {
/* Drop packets w/ critical options,
* since we don't support any...
*/
tun_dst = NULL;
if (gnvh->critical)
goto drop;
}
skb_reset_mac_header(skb);
skb_scrub_packet(skb, !net_eq(geneve->net, dev_net(geneve->dev)));
skb->protocol = eth_type_trans(skb, geneve->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
if (tun_dst)
ovs_skb_dst_set(skb, &tun_dst->dst);
else
goto drop;
/* Ignore packet loops (and multicast echo) */
if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr))
goto drop;
skb_reset_network_header(skb);
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
if (err > 1) {
++geneve->dev->stats.rx_frame_errors;
++geneve->dev->stats.rx_errors;
goto drop;
}
}
#ifdef HAVE_DEV_TSTATS
stats = this_cpu_ptr((struct pcpu_sw_netstats __percpu *)geneve->dev->tstats);
u64_stats_update_begin(&stats->syncp);
stats->rx_packets++;
stats->rx_bytes += skb->len;
u64_stats_update_end(&stats->syncp);
#endif
netdev_port_receive(skb, &tun_dst->u.tun_info);
return;
drop:
/* Consume bad packet */
kfree_skb(skb);
}
static int ipgre_rcv(struct sk_buff *skb)
{
struct iphdr *iph;
u8 *h;
__be16 flags;
__sum16 csum = 0;
__be32 key = 0;
u32 seqno = 0;
struct ip_tunnel *tunnel;
int offset = 4;
__be16 gre_proto;
unsigned int len;
if (!pskb_may_pull(skb, 16))
goto drop_nolock;
iph = ip_hdr(skb);
h = skb->data;
flags = *(__be16*)h;
if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
/* - Version must be 0.
- We do not support routing headers.
*/
if (flags&(GRE_VERSION|GRE_ROUTING))
goto drop_nolock;
if (flags&GRE_CSUM) {
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
csum = csum_fold(skb->csum);
if (!csum)
break;
/* fall through */
case CHECKSUM_NONE:
skb->csum = 0;
csum = __skb_checksum_complete(skb);
skb->ip_summed = CHECKSUM_COMPLETE;
}
offset += 4;
}
if (flags&GRE_KEY) {
key = *(__be32*)(h + offset);
offset += 4;
}
if (flags&GRE_SEQ) {
seqno = ntohl(*(__be32*)(h + offset));
offset += 4;
}
}
gre_proto = *(__be16 *)(h + 2);
read_lock(&ipgre_lock);
if ((tunnel = ipgre_tunnel_lookup(skb->dev,
iph->saddr, iph->daddr, key,
gre_proto))) {
struct net_device_stats *stats = &tunnel->dev->stats;
secpath_reset(skb);
skb->protocol = gre_proto;
/* WCCP version 1 and 2 protocol decoding.
* - Change protocol to IP
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
skb->protocol = htons(ETH_P_IP);
if ((*(h + offset) & 0xF0) != 0x40)
offset += 4;
}
skb->mac_header = skb->network_header;
__pskb_pull(skb, offset);
skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
skb->pkt_type = PACKET_HOST;
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
/* Looped back packet, drop it! */
if (skb_rtable(skb)->fl.iif == 0)
goto drop;
stats->multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if (((flags&GRE_CSUM) && csum) ||
(!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
stats->rx_crc_errors++;
stats->rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags&GRE_SEQ) {
if (!(flags&GRE_SEQ) ||
(tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
stats->rx_fifo_errors++;
stats->rx_errors++;
goto drop;
}
tunnel->i_seqno = seqno + 1;
}
len = skb->len;
/* Warning: All skb pointers will be invalidated! */
if (tunnel->dev->type == ARPHRD_ETHER) {
if (!pskb_may_pull(skb, ETH_HLEN)) {
stats->rx_length_errors++;
stats->rx_errors++;
goto drop;
}
iph = ip_hdr(skb);
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
stats->rx_packets++;
stats->rx_bytes += len;
skb->dev = tunnel->dev;
skb_dst_drop(skb);
nf_reset(skb);
skb_reset_network_header(skb);
ipgre_ecn_decapsulate(iph, skb);
netif_rx(skb);
read_unlock(&ipgre_lock);
return(0);
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
read_unlock(&ipgre_lock);
drop_nolock:
kfree_skb(skb);
return(0);
}
int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
const struct tnl_ptk_info *tpi, bool log_ecn_error)
{
struct pcpu_tstats *tstats;
const struct iphdr *iph = ip_hdr(skb);
int err;
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
/* Looped back packet, drop it! */
if (rt_is_output_route(skb_rtable(skb)))
goto drop;
tunnel->dev->stats.multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) ||
((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) {
tunnel->dev->stats.rx_crc_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags&TUNNEL_SEQ) {
if (!(tpi->flags&TUNNEL_SEQ) ||
(tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) {
tunnel->dev->stats.rx_fifo_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
tunnel->i_seqno = ntohl(tpi->seq) + 1;
}
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
if (log_ecn_error)
net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
&iph->saddr, iph->tos);
if (err > 1) {
++tunnel->dev->stats.rx_frame_errors;
++tunnel->dev->stats.rx_errors;
goto drop;
}
}
tstats = this_cpu_ptr(tunnel->dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
if (tunnel->net != dev_net(tunnel->dev))
skb_scrub_packet(skb);
if (tunnel->dev->type == ARPHRD_ETHER) {
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
} else {
skb->dev = tunnel->dev;
}
gro_cells_receive(&tunnel->gro_cells, skb);
return 0;
drop:
kfree_skb(skb);
return 0;
}
static inline int ip6_input_finish(struct sk_buff *skb)
{
struct inet6_protocol *ipprot;
struct sock *raw_sk;
unsigned int nhoff;
int nexthdr;
u8 hash;
/*
* Parse extension headers
*/
rcu_read_lock();
resubmit:
if (!pskb_pull(skb, skb->h.raw - skb->data))
goto discard;
nhoff = IP6CB(skb)->nhoff;
nexthdr = skb->nh.raw[nhoff];
raw_sk = sk_head(&raw_v6_htable[nexthdr & (MAX_INET_PROTOS - 1)]);
if (raw_sk && !ipv6_raw_deliver(skb, nexthdr))
raw_sk = NULL;
hash = nexthdr & (MAX_INET_PROTOS - 1);
if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) {
int ret;
if (ipprot->flags & INET6_PROTO_FINAL) {
struct ipv6hdr *hdr;
/* Free reference early: we don't need it any more,
and it may hold ip_conntrack module loaded
indefinitely. */
nf_reset(skb);
skb_postpull_rcsum(skb, skb->nh.raw,
skb->h.raw - skb->nh.raw);
hdr = skb->nh.ipv6h;
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
&hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr))
goto discard;
}
if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
ret = ipprot->handler(&skb);
if (ret > 0)
goto resubmit;
else if (ret == 0)
IP6_INC_STATS_BH(IPSTATS_MIB_INDELIVERS);
} else {
if (!raw_sk) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP6_INC_STATS_BH(IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff,
skb->dev);
}
} else
IP6_INC_STATS_BH(IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
rcu_read_unlock();
return 0;
discard:
IP6_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
rcu_read_unlock();
kfree_skb(skb);
return 0;
}