/* 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;
int err;
err = make_writable(skb, VLAN_ETH_HLEN);
if (unlikely(err))
return err;
if (get_ip_summed(skb) == OVS_CSUM_COMPLETE)
skb->csum = csum_sub(skb->csum, csum_partial(skb->data
+ ETH_HLEN, VLAN_HLEN, 0));
vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
*current_tci = vhdr->h_vlan_TCI;
memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
__skb_pull(skb, VLAN_HLEN);
vlan_set_encap_proto(skb, vhdr);
skb->mac_header += VLAN_HLEN;
skb_reset_mac_len(skb);
return 0;
}
static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_eth *ethh)
{
struct ethhdr *hdr;
/* Add the new Ethernet header */
if (skb_cow_head(skb, ETH_HLEN) < 0)
return -ENOMEM;
skb_push(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
hdr = eth_hdr(skb);
ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
hdr->h_proto = skb->protocol;
skb_postpush_rcsum(skb, hdr, ETH_HLEN);
/* safe right before invalidate_flow_key */
key->mac_proto = MAC_PROTO_ETHERNET;
invalidate_flow_key(key);
return 0;
}
bool vlan_do_receive(struct sk_buff **skbp, bool last_handler)
{
struct sk_buff *skb = *skbp;
u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK;
struct net_device *vlan_dev;
struct vlan_pcpu_stats *rx_stats;
vlan_dev = vlan_find_dev(skb->dev, vlan_id);
if (!vlan_dev) {
/* Only the last call to vlan_do_receive() should change
* pkt_type to PACKET_OTHERHOST
*/
if (vlan_id && last_handler)
skb->pkt_type = PACKET_OTHERHOST;
return false;
}
skb = *skbp = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(!skb))
return false;
skb->dev = vlan_dev;
if (skb->pkt_type == 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 (ether_addr_equal(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
skb->pkt_type = PACKET_HOST;
}
if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) {
unsigned int offset = skb->data - skb_mac_header(skb);
/*
* vlan_insert_tag expect skb->data pointing to mac header.
* So change skb->data before calling it and change back to
* original position later
*/
skb_push(skb, offset);
skb = *skbp = vlan_insert_tag(skb, skb->vlan_tci);
if (!skb)
return false;
skb_pull(skb, offset + VLAN_HLEN);
skb_reset_mac_len(skb);
}
skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci);
skb->vlan_tci = 0;
rx_stats = this_cpu_ptr(vlan_dev_priv(vlan_dev)->vlan_pcpu_stats);
u64_stats_update_begin(&rx_stats->syncp);
rx_stats->rx_packets++;
rx_stats->rx_bytes += skb->len;
if (skb->pkt_type == PACKET_MULTICAST)
rx_stats->rx_multicast++;
u64_stats_update_end(&rx_stats->syncp);
return true;
}
static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
{
if (skb_cow(skb, skb_headroom(skb)) < 0)
return NULL;
memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
skb->mac_header += VLAN_HLEN;
skb_reset_mac_len(skb);
return skb;
}
/* pop_eth does not support VLAN packets as this action is never called
* for them.
*/
static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
{
skb_pull_rcsum(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
/* safe right before invalidate_flow_key */
key->mac_proto = MAC_PROTO_NONE;
invalidate_flow_key(key);
return 0;
}
void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
{
int mtu = vport->dev->mtu;
switch (vport->dev->type) {
case ARPHRD_NONE:
if (mac_proto == MAC_PROTO_ETHERNET) {
skb_reset_network_header(skb);
skb_reset_mac_len(skb);
skb->protocol = htons(ETH_P_TEB);
} else if (mac_proto != MAC_PROTO_NONE) {
WARN_ON_ONCE(1);
goto drop;
}
break;
case ARPHRD_ETHER:
if (mac_proto != MAC_PROTO_ETHERNET)
goto drop;
break;
default:
goto drop;
}
if (unlikely(packet_length(skb, vport->dev) > mtu &&
!skb_is_gso(skb))) {
net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n",
vport->dev->name,
packet_length(skb, vport->dev), mtu);
vport->dev->stats.tx_errors++;
goto drop;
}
skb->dev = vport->dev;
vport->ops->send(skb);
return;
drop:
kfree_skb(skb);
}
struct sk_buff *vlan_untag(struct sk_buff *skb)
{
struct vlan_hdr *vhdr;
u16 vlan_tci;
if (unlikely(vlan_tx_tag_present(skb))) {
/* vlan_tci is already set-up so leave this for another time */
return skb;
}
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(!skb))
goto err_free;
if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
goto err_free;
vhdr = (struct vlan_hdr *) skb->data;
vlan_tci = ntohs(vhdr->h_vlan_TCI);
__vlan_hwaccel_put_tag(skb, vlan_tci);
skb_pull_rcsum(skb, VLAN_HLEN);
vlan_set_encap_proto(skb, vhdr);
skb = vlan_reorder_header(skb);
if (unlikely(!skb))
goto err_free;
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
skb_reset_mac_len(skb);
return skb;
err_free:
kfree_skb(skb);
return NULL;
}
/**
* key_extract - extracts a flow key from an Ethernet frame.
* @skb: sk_buff that contains the frame, with skb->data pointing to the
* Ethernet header
* @key: output flow key
*
* The caller must ensure that skb->len >= ETH_HLEN.
*
* Returns 0 if successful, otherwise a negative errno value.
*
* Initializes @skb header pointers as follows:
*
* - skb->mac_header: the Ethernet header.
*
* - skb->network_header: just past the Ethernet header, or just past the
* VLAN header, to the first byte of the Ethernet payload.
*
* - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
* on output, then just past the IP header, if one is present and
* of a correct length, otherwise the same as skb->network_header.
* For other key->eth.type values it is left untouched.
*/
static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
{
int error;
struct ethhdr *eth;
/* Flags are always used as part of stats */
key->tp.flags = 0;
skb_reset_mac_header(skb);
/* Link layer. We are guaranteed to have at least the 14 byte Ethernet
* header in the linear data area.
*/
eth = eth_hdr(skb);
ether_addr_copy(key->eth.src, eth->h_source);
ether_addr_copy(key->eth.dst, eth->h_dest);
__skb_pull(skb, 2 * ETH_ALEN);
/* We are going to push all headers that we pull, so no need to
* update skb->csum here.
*/
key->eth.tci = 0;
if (vlan_tx_tag_present(skb))
key->eth.tci = htons(vlan_get_tci(skb));
else if (eth->h_proto == htons(ETH_P_8021Q))
if (unlikely(parse_vlan(skb, key)))
return -ENOMEM;
key->eth.type = parse_ethertype(skb);
if (unlikely(key->eth.type == htons(0)))
return -ENOMEM;
skb_reset_network_header(skb);
skb_reset_mac_len(skb);
__skb_push(skb, skb->data - skb_mac_header(skb));
/* Network layer. */
if (key->eth.type == htons(ETH_P_IP)) {
struct iphdr *nh;
__be16 offset;
error = check_iphdr(skb);
if (unlikely(error)) {
memset(&key->ip, 0, sizeof(key->ip));
memset(&key->ipv4, 0, sizeof(key->ipv4));
if (error == -EINVAL) {
skb->transport_header = skb->network_header;
error = 0;
}
return error;
}
nh = ip_hdr(skb);
key->ipv4.addr.src = nh->saddr;
key->ipv4.addr.dst = nh->daddr;
key->ip.proto = nh->protocol;
key->ip.tos = nh->tos;
key->ip.ttl = nh->ttl;
offset = nh->frag_off & htons(IP_OFFSET);
if (offset) {
key->ip.frag = OVS_FRAG_TYPE_LATER;
return 0;
}
if (nh->frag_off & htons(IP_MF) ||
skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
key->ip.frag = OVS_FRAG_TYPE_FIRST;
else
key->ip.frag = OVS_FRAG_TYPE_NONE;
/* Transport layer. */
if (key->ip.proto == IPPROTO_TCP) {
if (tcphdr_ok(skb)) {
struct tcphdr *tcp = tcp_hdr(skb);
key->tp.src = tcp->source;
key->tp.dst = tcp->dest;
key->tp.flags = TCP_FLAGS_BE16(tcp);
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_UDP) {
if (udphdr_ok(skb)) {
struct udphdr *udp = udp_hdr(skb);
key->tp.src = udp->source;
key->tp.dst = udp->dest;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_SCTP) {
if (sctphdr_ok(skb)) {
struct sctphdr *sctp = sctp_hdr(skb);
key->tp.src = sctp->source;
key->tp.dst = sctp->dest;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_ICMP) {
if (icmphdr_ok(skb)) {
struct icmphdr *icmp = icmp_hdr(skb);
/* The ICMP type and code fields use the 16-bit
* transport port fields, so we need to store
* them in 16-bit network byte order.
*/
key->tp.src = htons(icmp->type);
key->tp.dst = htons(icmp->code);
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
}
} else if (key->eth.type == htons(ETH_P_ARP) ||
key->eth.type == htons(ETH_P_RARP)) {
struct arp_eth_header *arp;
bool arp_available = arphdr_ok(skb);
arp = (struct arp_eth_header *)skb_network_header(skb);
if (arp_available &&
arp->ar_hrd == htons(ARPHRD_ETHER) &&
arp->ar_pro == htons(ETH_P_IP) &&
arp->ar_hln == ETH_ALEN &&
arp->ar_pln == 4) {
/* We only match on the lower 8 bits of the opcode. */
if (ntohs(arp->ar_op) <= 0xff)
key->ip.proto = ntohs(arp->ar_op);
else
key->ip.proto = 0;
memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha);
ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha);
} else {
memset(&key->ip, 0, sizeof(key->ip));
memset(&key->ipv4, 0, sizeof(key->ipv4));
}
} else if (eth_p_mpls(key->eth.type)) {
size_t stack_len = MPLS_HLEN;
/* In the presence of an MPLS label stack the end of the L2
* header and the beginning of the L3 header differ.
*
* Advance network_header to the beginning of the L3
* header. mac_len corresponds to the end of the L2 header.
*/
while (1) {
__be32 lse;
error = check_header(skb, skb->mac_len + stack_len);
if (unlikely(error))
return 0;
memcpy(&lse, skb_network_header(skb), MPLS_HLEN);
if (stack_len == MPLS_HLEN)
memcpy(&key->mpls.top_lse, &lse, MPLS_HLEN);
skb_set_network_header(skb, skb->mac_len + stack_len);
if (lse & htonl(MPLS_LS_S_MASK))
break;
stack_len += MPLS_HLEN;
}
} else if (key->eth.type == htons(ETH_P_IPV6)) {
int nh_len; /* IPv6 Header + Extensions */
nh_len = parse_ipv6hdr(skb, key);
if (unlikely(nh_len < 0)) {
memset(&key->ip, 0, sizeof(key->ip));
memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr));
if (nh_len == -EINVAL) {
skb->transport_header = skb->network_header;
error = 0;
} else {
error = nh_len;
}
return error;
}
if (key->ip.frag == OVS_FRAG_TYPE_LATER)
return 0;
if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
key->ip.frag = OVS_FRAG_TYPE_FIRST;
/* Transport layer. */
if (key->ip.proto == NEXTHDR_TCP) {
if (tcphdr_ok(skb)) {
struct tcphdr *tcp = tcp_hdr(skb);
key->tp.src = tcp->source;
key->tp.dst = tcp->dest;
key->tp.flags = TCP_FLAGS_BE16(tcp);
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_UDP) {
if (udphdr_ok(skb)) {
struct udphdr *udp = udp_hdr(skb);
key->tp.src = udp->source;
key->tp.dst = udp->dest;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_SCTP) {
if (sctphdr_ok(skb)) {
struct sctphdr *sctp = sctp_hdr(skb);
key->tp.src = sctp->source;
key->tp.dst = sctp->dest;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_ICMP) {
if (icmp6hdr_ok(skb)) {
error = parse_icmpv6(skb, key, nh_len);
if (error)
return error;
} else {
memset(&key->tp, 0, sizeof(key->tp));
}
}
}
return 0;
}
bool vlan_do_receive(struct sk_buff **skbp, bool last_handler)
{
struct sk_buff *skb = *skbp;
u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK;
struct net_device *vlan_dev;
struct vlan_pcpu_stats *rx_stats;
vlan_dev = vlan_find_dev(skb->dev, vlan_id);
if (!vlan_dev) {
/*
*/
if (vlan_id && last_handler)
skb->pkt_type = PACKET_OTHERHOST;
return false;
}
skb = *skbp = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(!skb))
return false;
skb->dev = vlan_dev;
if (skb->pkt_type == PACKET_OTHERHOST) {
/*
*/
if (!compare_ether_addr(eth_hdr(skb)->h_dest,
vlan_dev->dev_addr))
skb->pkt_type = PACKET_HOST;
}
if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) {
unsigned int offset = skb->data - skb_mac_header(skb);
/*
*/
skb_push(skb, offset);
skb = *skbp = vlan_insert_tag(skb, skb->vlan_tci);
if (!skb)
return false;
skb_pull(skb, offset + VLAN_HLEN);
skb_reset_mac_len(skb);
}
skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci);
skb->vlan_tci = 0;
rx_stats = this_cpu_ptr(vlan_dev_priv(vlan_dev)->vlan_pcpu_stats);
u64_stats_update_begin(&rx_stats->syncp);
rx_stats->rx_packets++;
rx_stats->rx_bytes += skb->len;
if (skb->pkt_type == PACKET_MULTICAST)
rx_stats->rx_multicast++;
u64_stats_update_end(&rx_stats->syncp);
return true;
}
