static struct sk_buff *tnl_skb_gso_segment(struct sk_buff *skb,
netdev_features_t features,
bool tx_path)
{
struct iphdr *iph = ip_hdr(skb);
int pkt_hlen = skb_inner_network_offset(skb); /* inner l2 + tunnel hdr. */
int mac_offset = skb_inner_mac_offset(skb);
struct sk_buff *skb1 = skb;
struct sk_buff *segs;
__be16 proto = skb->protocol;
char cb[sizeof(skb->cb)];
/* setup whole inner packet to get protocol. */
__skb_pull(skb, mac_offset);
skb->protocol = __skb_network_protocol(skb);
/* setup l3 packet to gso, to get around segmentation bug on older kernel.*/
__skb_pull(skb, (pkt_hlen - mac_offset));
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
/* From 3.9 kernel skb->cb is used by skb gso. Therefore
* make copy of it to restore it back. */
memcpy(cb, skb->cb, sizeof(cb));
segs = __skb_gso_segment(skb, 0, tx_path);
if (!segs || IS_ERR(segs))
goto free;
skb = segs;
while (skb) {
__skb_push(skb, pkt_hlen);
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
skb_set_transport_header(skb, sizeof(struct iphdr));
skb->mac_len = 0;
memcpy(ip_hdr(skb), iph, pkt_hlen);
memcpy(skb->cb, cb, sizeof(cb));
if (OVS_GSO_CB(skb)->fix_segment)
OVS_GSO_CB(skb)->fix_segment(skb);
skb->protocol = proto;
skb = skb->next;
}
free:
consume_skb(skb1);
return segs;
}
void rpl_iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto, __u8 tos, __u8 ttl,
__be16 df, bool xnet)
{
struct net_device *dev = skb->dev;
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct iphdr *iph;
int err;
skb_scrub_packet(skb, xnet);
skb_clear_hash(skb);
skb_dst_set(skb, &rt->dst);
#if 0
/* Do not clear ovs_skb_cb. It will be done in gso code. */
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
#endif
/* Push down and install the IP header. */
__skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
#ifdef HAVE_IP_SELECT_IDENT_USING_DST_ENTRY
__ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
#elif defined(HAVE_IP_SELECT_IDENT_USING_NET)
__ip_select_ident(dev_net(rt->dst.dev), iph,
skb_shinfo(skb)->gso_segs ?: 1);
#else
__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
#endif
err = ip_local_out(skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
iptunnel_xmit_stats(dev, pkt_len);
}
void rpl_ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
struct net_device *dev)
{
int pkt_len, err;
pkt_len = skb->len - skb_inner_network_offset(skb);
#ifdef HAVE_IP6_LOCAL_OUT_SK
err = ip6_local_out_sk(sk, skb);
#else
err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
#endif
if (net_xmit_eval(err))
pkt_len = -1;
iptunnel_xmit_stats(dev, pkt_len);
}
void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct net *net = dev_net(rt->dst.dev);
struct net_device *dev = skb->dev;
struct iphdr *iph;
int err;
skb_scrub_packet(skb, xnet);
skb_clear_hash(skb);
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
__ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);
err = ip_local_out(net, sk, skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
iptunnel_xmit_stats(dev, pkt_len);
}
static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
netdev_features_t enc_features;
int ghl = GRE_HEADER_SECTION;
struct gre_base_hdr *greh;
u16 mac_offset = skb->mac_header;
int mac_len = skb->mac_len;
__be16 protocol = skb->protocol;
int tnl_hlen;
bool csum;
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_TCPV4 |
SKB_GSO_TCPV6 |
SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
SKB_GSO_IPIP)))
goto out;
if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
goto out;
greh = (struct gre_base_hdr *)skb_transport_header(skb);
if (greh->flags & GRE_KEY)
ghl += GRE_HEADER_SECTION;
if (greh->flags & GRE_SEQ)
ghl += GRE_HEADER_SECTION;
if (greh->flags & GRE_CSUM) {
ghl += GRE_HEADER_SECTION;
csum = true;
} else
csum = false;
if (unlikely(!pskb_may_pull(skb, ghl)))
goto out;
/* setup inner skb. */
skb->protocol = greh->protocol;
skb->encapsulation = 0;
__skb_pull(skb, ghl);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
skb->mac_len = skb_inner_network_offset(skb);
/* segment inner packet. */
enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
segs = skb_mac_gso_segment(skb, enc_features);
if (!segs || IS_ERR(segs)) {
skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len);
goto out;
}
skb = segs;
tnl_hlen = skb_tnl_header_len(skb);
do {
__skb_push(skb, ghl);
if (csum) {
__be32 *pcsum;
if (skb_has_shared_frag(skb)) {
int err;
err = __skb_linearize(skb);
if (err) {
kfree_skb_list(segs);
segs = ERR_PTR(err);
goto out;
}
}
greh = (struct gre_base_hdr *)(skb->data);
pcsum = (__be32 *)(greh + 1);
*pcsum = 0;
*(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
}
__skb_push(skb, tnl_hlen - ghl);
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);
skb->mac_len = mac_len;
skb->protocol = protocol;
} while ((skb = skb->next));
out:
return segs;
}
static struct sk_buff *tnl_skb_gso_segment(struct sk_buff *skb,
netdev_features_t features,
bool tx_path,
sa_family_t sa_family)
{
void *iph = skb_network_header(skb);
int pkt_hlen = skb_inner_network_offset(skb); /* inner l2 + tunnel hdr. */
int mac_offset = skb_inner_mac_offset(skb);
int outer_l3_offset = skb_network_offset(skb);
int outer_l4_offset = skb_transport_offset(skb);
struct sk_buff *skb1 = skb;
struct dst_entry *dst = skb_dst(skb);
struct sk_buff *segs;
__be16 proto = skb->protocol;
char cb[sizeof(skb->cb)];
BUILD_BUG_ON(sizeof(struct ovs_gso_cb) > FIELD_SIZEOF(struct sk_buff, cb));
OVS_GSO_CB(skb)->ipv6 = (sa_family == AF_INET6);
/* setup whole inner packet to get protocol. */
__skb_pull(skb, mac_offset);
skb->protocol = __skb_network_protocol(skb);
/* setup l3 packet to gso, to get around segmentation bug on older kernel.*/
__skb_pull(skb, (pkt_hlen - mac_offset));
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
/* From 3.9 kernel skb->cb is used by skb gso. Therefore
* make copy of it to restore it back. */
memcpy(cb, skb->cb, sizeof(cb));
skb->encapsulation = 0;
/* We are handling offloads by segmenting l3 packet, so
* no need to call OVS compat segmentation function. */
#ifdef HAVE___SKB_GSO_SEGMENT
#undef __skb_gso_segment
segs = __skb_gso_segment(skb, 0, tx_path);
#else
#undef skb_gso_segment
segs = skb_gso_segment(skb, 0);
#endif
if (!segs || IS_ERR(segs))
goto free;
skb = segs;
while (skb) {
__skb_push(skb, pkt_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, outer_l3_offset);
skb_set_transport_header(skb, outer_l4_offset);
skb->mac_len = 0;
memcpy(skb_network_header(skb), iph, pkt_hlen);
memcpy(skb->cb, cb, sizeof(cb));
skb->protocol = proto;
if (skb->next)
dst = dst_clone(dst);
skb_dst_set(skb, dst);
OVS_GSO_CB(skb)->fix_segment(skb);
skb = skb->next;
}
free:
consume_skb(skb1);
return segs;
}
static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
netdev_features_t features,
struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
netdev_features_t features),
__be16 new_protocol, bool is_ipv6)
{
int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
bool remcsum, need_csum, offload_csum, gso_partial;
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct udphdr *uh = udp_hdr(skb);
u16 mac_offset = skb->mac_header;
__be16 protocol = skb->protocol;
u16 mac_len = skb->mac_len;
int udp_offset, outer_hlen;
__wsum partial;
bool need_ipsec;
if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
goto out;
/* Adjust partial header checksum to negate old length.
* We cannot rely on the value contained in uh->len as it is
* possible that the actual value exceeds the boundaries of the
* 16 bit length field due to the header being added outside of an
* IP or IPv6 frame that was already limited to 64K - 1.
*/
if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)
partial = (__force __wsum)uh->len;
else
partial = (__force __wsum)htonl(skb->len);
partial = csum_sub(csum_unfold(uh->check), partial);
/* setup inner skb. */
skb->encapsulation = 0;
SKB_GSO_CB(skb)->encap_level = 0;
__skb_pull(skb, tnl_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
skb->mac_len = skb_inner_network_offset(skb);
skb->protocol = new_protocol;
need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
skb->encap_hdr_csum = need_csum;
remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM);
skb->remcsum_offload = remcsum;
need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
/* Try to offload checksum if possible */
offload_csum = !!(need_csum &&
!need_ipsec &&
(skb->dev->features &
(is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) :
(NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
features &= skb->dev->hw_enc_features;
/* The only checksum offload we care about from here on out is the
* outer one so strip the existing checksum feature flags and
* instead set the flag based on our outer checksum offload value.
*/
if (remcsum) {
features &= ~NETIF_F_CSUM_MASK;
if (!need_csum || offload_csum)
features |= NETIF_F_HW_CSUM;
}
/* segment inner packet. */
segs = gso_inner_segment(skb, features);
if (IS_ERR_OR_NULL(segs)) {
skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
mac_len);
goto out;
}
gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
outer_hlen = skb_tnl_header_len(skb);
udp_offset = outer_hlen - tnl_hlen;
skb = segs;
do {
unsigned int len;
if (remcsum)
skb->ip_summed = CHECKSUM_NONE;
/* Set up inner headers if we are offloading inner checksum */
if (skb->ip_summed == CHECKSUM_PARTIAL) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
skb->mac_len = mac_len;
skb->protocol = protocol;
__skb_push(skb, outer_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);
skb_set_transport_header(skb, udp_offset);
len = skb->len - udp_offset;
uh = udp_hdr(skb);
/* If we are only performing partial GSO the inner header
* will be using a length value equal to only one MSS sized
* segment instead of the entire frame.
*/
if (gso_partial && skb_is_gso(skb)) {
uh->len = htons(skb_shinfo(skb)->gso_size +
SKB_GSO_CB(skb)->data_offset +
skb->head - (unsigned char *)uh);
} else {
uh->len = htons(len);
}
if (!need_csum)
continue;
uh->check = ~csum_fold(csum_add(partial,
(__force __wsum)htonl(len)));
if (skb->encapsulation || !offload_csum) {
uh->check = gso_make_checksum(skb, ~uh->check);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
} else {
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
}
} while ((skb = skb->next));
out:
return segs;
}
static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
struct sk_buff *segs = ERR_PTR(-EINVAL);
u16 mac_offset = skb->mac_header;
__be16 protocol = skb->protocol;
u16 mac_len = skb->mac_len;
int gre_offset, outer_hlen;
bool need_csum, ufo;
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_TCPV4 |
SKB_GSO_TCPV6 |
SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_TCP_FIXEDID |
SKB_GSO_GRE |
SKB_GSO_GRE_CSUM |
SKB_GSO_IPIP |
SKB_GSO_SIT |
SKB_GSO_PARTIAL)))
goto out;
if (!skb->encapsulation)
goto out;
if (unlikely(tnl_hlen < sizeof(struct gre_base_hdr)))
goto out;
if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
goto out;
/* setup inner skb. */
skb->encapsulation = 0;
SKB_GSO_CB(skb)->encap_level = 0;
__skb_pull(skb, tnl_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
skb->mac_len = skb_inner_network_offset(skb);
skb->protocol = skb->inner_protocol;
need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
skb->encap_hdr_csum = need_csum;
ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
features &= skb->dev->hw_enc_features;
/* The only checksum offload we care about from here on out is the
* outer one so strip the existing checksum feature flags based
* on the fact that we will be computing our checksum in software.
*/
if (ufo) {
features &= ~NETIF_F_CSUM_MASK;
if (!need_csum)
features |= NETIF_F_HW_CSUM;
}
/* segment inner packet. */
segs = skb_mac_gso_segment(skb, features);
if (IS_ERR_OR_NULL(segs)) {
skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
mac_len);
goto out;
}
outer_hlen = skb_tnl_header_len(skb);
gre_offset = outer_hlen - tnl_hlen;
skb = segs;
do {
struct gre_base_hdr *greh;
__sum16 *pcsum;
/* Set up inner headers if we are offloading inner checksum */
if (skb->ip_summed == CHECKSUM_PARTIAL) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
skb->mac_len = mac_len;
skb->protocol = protocol;
__skb_push(skb, outer_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, mac_len);
skb_set_transport_header(skb, gre_offset);
if (!need_csum)
continue;
greh = (struct gre_base_hdr *)skb_transport_header(skb);
pcsum = (__sum16 *)(greh + 1);
if (skb_is_gso(skb)) {
unsigned int partial_adj;
/* Adjust checksum to account for the fact that
* the partial checksum is based on actual size
* whereas headers should be based on MSS size.
*/
partial_adj = skb->len + skb_headroom(skb) -
SKB_GSO_CB(skb)->data_offset -
skb_shinfo(skb)->gso_size;
*pcsum = ~csum_fold((__force __wsum)htonl(partial_adj));
} else {
*pcsum = 0;
}
*(pcsum + 1) = 0;
*pcsum = gso_make_checksum(skb, 0);
} while ((skb = skb->next));
out:
return segs;
}