static void ip6ip6_dscp_ecn_decapsulate(struct ip6_tnl *t,
struct ipv6hdr *ipv6h,
struct sk_buff *skb)
{
if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb));
if (INET_ECN_is_ce(ipv6_get_dsfield(ipv6h)))
IP6_ECN_set_ce(ipv6_hdr(skb));
}
static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6)
goto out;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
if (skb_cloned(skb) &&
(err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
goto out;
if (x->props.flags & XFRM_STATE_DECAP_DSCP)
ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)),
ipipv6_hdr(skb));
if (!(x->props.flags & XFRM_STATE_NOECN))
ipip6_ecn_decapsulate(skb);
skb_reset_network_header(skb);
skb_mac_header_rebuild(skb);
err = 0;
out:
return err;
}
/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401. The following fields
* in it shall be filled in by x->type->output:
* payload_len
*
* On exit, skb->h will be set to the start of the encapsulation header to be
* filled in by x->type->output and skb->nh will be set to the nextheader field
* of the extension header directly preceding the encapsulation header, or in
* its absence, that of the top IP header. The value of skb->data will always
* point to the top IP header.
*/
static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb->dst;
struct ipv6hdr *iph, *top_iph;
int dsfield;
skb_push(skb, x->props.header_len);
iph = skb->nh.ipv6h;
skb->nh.raw = skb->data;
top_iph = skb->nh.ipv6h;
skb->nh.raw = &top_iph->nexthdr;
skb->h.ipv6h = top_iph + 1;
top_iph->version = 6;
top_iph->priority = iph->priority;
top_iph->flow_lbl[0] = iph->flow_lbl[0];
top_iph->flow_lbl[1] = iph->flow_lbl[1];
top_iph->flow_lbl[2] = iph->flow_lbl[2];
dsfield = ipv6_get_dsfield(top_iph);
dsfield = INET_ECN_encapsulate(dsfield, dsfield);
if (x->props.flags & XFRM_STATE_NOECN)
dsfield &= ~INET_ECN_MASK;
ipv6_change_dsfield(top_iph, 0, dsfield);
top_iph->nexthdr = IPPROTO_IPV6;
top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT);
ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
return 0;
}
static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
{
struct ipv6hdr *outer_iph = skb->nh.ipv6h;
struct ipv6hdr *inner_iph = skb->h.ipv6h;
if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
IP6_ECN_set_ce(inner_iph);
}
static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
{
const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
IP6_ECN_set_ce(inner_iph);
}
/* When forwarding a packet, we must ensure that we've got enough headroom
* for the encapsulation packet in the skb. This also gives us an
* opportunity to figure out what the payload_len, dsfield, ttl, and df
* values should be, so that we won't need to look at the old ip header
* again
*/
static struct sk_buff *
ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
unsigned int max_headroom, __u8 *next_protocol,
__u32 *payload_len, __u8 *dsfield, __u8 *ttl,
__be16 *df)
{
struct sk_buff *new_skb = NULL;
struct iphdr *old_iph = NULL;
#ifdef CONFIG_IP_VS_IPV6
struct ipv6hdr *old_ipv6h = NULL;
#endif
ip_vs_drop_early_demux_sk(skb);
if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb)
goto error;
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
consume_skb(skb);
skb = new_skb;
}
#ifdef CONFIG_IP_VS_IPV6
if (skb_af == AF_INET6) {
old_ipv6h = ipv6_hdr(skb);
*next_protocol = IPPROTO_IPV6;
if (payload_len)
*payload_len =
ntohs(old_ipv6h->payload_len) +
sizeof(*old_ipv6h);
*dsfield = ipv6_get_dsfield(old_ipv6h);
*ttl = old_ipv6h->hop_limit;
if (df)
*df = 0;
} else
#endif
{
old_iph = ip_hdr(skb);
/* Copy DF, reset fragment offset and MF */
if (df)
*df = (old_iph->frag_off & htons(IP_DF));
*next_protocol = IPPROTO_IPIP;
/* fix old IP header checksum */
ip_send_check(old_iph);
*dsfield = ipv4_get_dsfield(old_iph);
*ttl = old_iph->ttl;
if (payload_len)
*payload_len = ntohs(old_iph->tot_len);
}
return skb;
error:
kfree_skb(skb);
return ERR_PTR(-ENOMEM);
}
static inline u8
ipgre_ecn_encapsulate(u8 tos, struct iphdr *old_iph, struct sk_buff *skb)
{
u8 inner = 0;
if (skb->protocol == htons(ETH_P_IP))
inner = old_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
inner = ipv6_get_dsfield((struct ipv6hdr *)old_iph);
return INET_ECN_encapsulate(tos, inner);
}
static void ip4ip6_dscp_ecn_decapsulate(struct ip6_tnl *t,
struct ipv6hdr *ipv6h,
struct sk_buff *skb)
{
__u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK;
if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield);
if (INET_ECN_is_ce(dsfield))
IP_ECN_set_ce(ip_hdr(skb));
}
HYFI_MC_STATIC unsigned int mc_pre_routing_hook(unsigned int hooknum, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
int(*okfn)(struct sk_buff *))
{
struct hyfi_net_bridge *hyfi_br = hyfi_bridge_get_by_dev(in);
struct mc_struct *mc = MC_DEV(hyfi_br);
struct ethhdr *eh = eth_hdr(skb);
struct net_bridge_port *port;
u8 dscp;
if (!mc || skb->pkt_type != PACKET_HOST ||
(port = hyfi_br_port_get(in)) == NULL)
goto out;
dscp = MC_DSCP(mc->dscp) & (~INET_ECN_MASK);
switch (ntohs(skb->protocol)) {
case ETH_P_IP:
{
const struct iphdr *iph = ip_hdr(skb);
if (ipv4_is_multicast(iph->daddr) && (!mc->enable_retag ||
(mc->enable_retag && (ipv4_get_dsfield(iph) == dscp)))) {
ip_eth_mc_map(iph->daddr, eh->h_dest);
if (mc->debug && printk_ratelimit()) {
MC_PRINT("Decap the group "MC_IP4_STR" back to "MC_MAC_STR"\n",
MC_IP4_FMT((u8 *)(&iph->daddr)) ,MC_MAC_FMT(eh->h_dest));
}
skb->pkt_type = PACKET_MULTICAST;
}
}
break;
#ifdef HYBRID_MC_MLD
case ETH_P_IPV6:
{
struct ipv6hdr *iph6 = ipv6_hdr(skb);
if (ipv6_addr_is_multicast(&iph6->daddr) && (!mc->enable_retag ||
(mc->enable_retag && (ipv6_get_dsfield(iph6) == dscp)))) {
ipv6_eth_mc_map(&iph6->daddr, eh->h_dest);
if (mc->debug && printk_ratelimit()) {
MC_PRINT("Decap the group "MC_IP6_STR" back to "MC_MAC_STR"\n",
MC_IP6_FMT((__be16 *)(&iph6->daddr)) ,MC_MAC_FMT(eh->h_dest));
}
skb->pkt_type = PACKET_MULTICAST;
}
}
break;
#endif
}
out:
return NF_ACCEPT;
}
static bool
ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct ebt_ip6_info *info = par->matchinfo;
const struct ipv6hdr *ih6;
struct ipv6hdr _ip6h;
const struct tcpudphdr *pptr;
struct tcpudphdr _ports;
ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
if (ih6 == NULL)
return false;
if (info->bitmask & EBT_IP6_TCLASS &&
FWINV(info->tclass != ipv6_get_dsfield(ih6), EBT_IP6_TCLASS))
return false;
if (FWINV(ipv6_masked_addr_cmp(&ih6->saddr, &info->smsk,
&info->saddr), EBT_IP6_SOURCE) ||
FWINV(ipv6_masked_addr_cmp(&ih6->daddr, &info->dmsk,
&info->daddr), EBT_IP6_DEST))
return false;
if (info->bitmask & EBT_IP6_PROTO) {
uint8_t nexthdr = ih6->nexthdr;
int offset_ph;
offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr);
if (offset_ph == -1)
return false;
if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
return false;
if (!(info->bitmask & EBT_IP6_DPORT) &&
!(info->bitmask & EBT_IP6_SPORT))
return true;
pptr = skb_header_pointer(skb, offset_ph, sizeof(_ports),
&_ports);
if (pptr == NULL)
return false;
if (info->bitmask & EBT_IP6_DPORT) {
u32 dst = ntohs(pptr->dst);
if (FWINV(dst < info->dport[0] ||
dst > info->dport[1], EBT_IP6_DPORT))
return false;
}
if (info->bitmask & EBT_IP6_SPORT) {
u32 src = ntohs(pptr->src);
if (FWINV(src < info->sport[0] ||
src > info->sport[1], EBT_IP6_SPORT))
return false;
}
return true;
}
return true;
}
/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401. The following fields
* in it shall be filled in by x->type->output:
* tot_len
* check
*
* On exit, skb->h will be set to the start of the payload to be processed
* by x->type->output and skb->nh will be set to the top IP header.
*/
static int xfrm4_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb->dst;
struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
struct iphdr *iph, *top_iph;
int flags;
iph = skb->nh.iph;
skb->h.ipiph = iph;
skb->nh.raw = skb_push(skb, x->props.header_len);
top_iph = skb->nh.iph;
top_iph->ihl = 5;
top_iph->version = 4;
flags = x->props.flags;
/* DS disclosed */
if (xdst->route->ops->family == AF_INET) {
top_iph->protocol = IPPROTO_IPIP;
top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos);
top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (iph->frag_off & htons(IP_DF));
}
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
else {
struct ipv6hdr *ipv6h = (struct ipv6hdr*)iph;
top_iph->protocol = IPPROTO_IPV6;
top_iph->tos = INET_ECN_encapsulate(iph->tos, ipv6_get_dsfield(ipv6h));
top_iph->frag_off = 0;
}
#endif
if (flags & XFRM_STATE_NOECN)
IP_ECN_clear(top_iph);
if (!top_iph->frag_off)
__ip_select_ident(top_iph, dst->child, 0);
top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT);
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
skb->protocol = htons(ETH_P_IP);
memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
return 0;
}
int xfrm6_extract_header(struct sk_buff *skb)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph);
XFRM_MODE_SKB_CB(skb)->id = 0;
XFRM_MODE_SKB_CB(skb)->frag_off = htons(IP_DF);
XFRM_MODE_SKB_CB(skb)->tos = ipv6_get_dsfield(iph);
XFRM_MODE_SKB_CB(skb)->ttl = iph->hop_limit;
XFRM_MODE_SKB_CB(skb)->optlen = 0;
memcpy(XFRM_MODE_SKB_CB(skb)->flow_lbl, iph->flow_lbl,
sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl));
return 0;
}
static void
__skb_flow_dissect_ipv6(const struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container, void *data, const struct ipv6hdr *iph)
{
struct flow_dissector_key_ip *key_ip;
if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP))
return;
key_ip = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IP,
target_container);
key_ip->tos = ipv6_get_dsfield(iph);
key_ip->ttl = iph->hop_limit;
}
static inline int
ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
int encap_limit = -1;
__u16 offset;
struct flowi fl;
__u8 dsfield;
__u32 mtu;
int err;
if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
!ip6_tnl_xmit_ctl(t) || ip6_tnl_addr_conflict(t, ipv6h))
return -1;
offset = parse_tlv_tnl_enc_lim(skb, skb_network_header(skb));
if (offset > 0) {
struct ipv6_tlv_tnl_enc_lim *tel;
tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
if (tel->encap_limit == 0) {
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_HDR_FIELD, offset + 2, skb->dev);
return -1;
}
encap_limit = tel->encap_limit - 1;
} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
encap_limit = t->parms.encap_limit;
memcpy(&fl, &t->fl, sizeof (fl));
fl.proto = IPPROTO_IPV6;
dsfield = ipv6_get_dsfield(ipv6h);
if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL))
fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);
err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
if (err != 0) {
if (err == -EMSGSIZE)
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
return -1;
}
return 0;
}
/* Add encapsulation header.
*
* In transport mode, the IP header and mutable extension headers will be moved
* forward to make space for the encapsulation header.
*
* In tunnel mode, the top IP header will be constructed per RFC 2401.
* The following fields in it shall be filled in by x->type->output:
* payload_len
*
* On exit, skb->h will be set to the start of the encapsulation header to be
* filled in by x->type->output and skb->nh will be set to the nextheader field
* of the extension header directly preceding the encapsulation header, or in
* its absence, that of the top IP header. The value of skb->data will always
* point to the top IP header.
*/
static void xfrm6_encap(struct sk_buff *skb)
{
struct dst_entry *dst = skb->dst;
struct xfrm_state *x = dst->xfrm;
struct ipv6hdr *iph, *top_iph;
int dsfield;
skb_push(skb, x->props.header_len);
iph = skb->nh.ipv6h;
if (!x->props.mode) {
u8 *prevhdr;
int hdr_len;
#ifdef CONFIG_XFRM_ENHANCEMENT
hdr_len = xfrm6_place_find(skb, &prevhdr, x->id.proto);
#else
hdr_len = ip6_find_1stfragopt(skb, &prevhdr);
#endif
skb->nh.raw = prevhdr - x->props.header_len;
skb->h.raw = skb->data + hdr_len;
memmove(skb->data, iph, hdr_len);
return;
}
skb->nh.raw = skb->data;
top_iph = skb->nh.ipv6h;
skb->nh.raw = &top_iph->nexthdr;
skb->h.ipv6h = top_iph + 1;
top_iph->version = 6;
top_iph->priority = iph->priority;
top_iph->flow_lbl[0] = iph->flow_lbl[0];
top_iph->flow_lbl[1] = iph->flow_lbl[1];
top_iph->flow_lbl[2] = iph->flow_lbl[2];
dsfield = ipv6_get_dsfield(top_iph);
dsfield = INET_ECN_encapsulate(dsfield, dsfield);
if (x->props.flags & XFRM_STATE_NOECN)
dsfield &= ~INET_ECN_MASK;
ipv6_change_dsfield(top_iph, 0, dsfield);
top_iph->nexthdr = IPPROTO_IPV6;
top_iph->hop_limit = dst_path_metric(dst, RTAX_HOPLIMIT);
ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
}
static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key,
int *key_lenp)
{
unsigned int nh_ofs = skb_network_offset(skb);
unsigned int nh_len;
int payload_ofs;
struct ipv6hdr *nh;
uint8_t nexthdr;
__be16 frag_off;
int err;
*key_lenp = SW_FLOW_KEY_OFFSET(ipv6.label);
err = check_header(skb, nh_ofs + sizeof(*nh));
if (unlikely(err))
return err;
nh = ipv6_hdr(skb);
nexthdr = nh->nexthdr;
payload_ofs = (u8 *)(nh + 1) - skb->data;
key->ip.proto = NEXTHDR_NONE;
key->ip.tos = ipv6_get_dsfield(nh);
key->ip.ttl = nh->hop_limit;
key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
key->ipv6.addr.src = nh->saddr;
key->ipv6.addr.dst = nh->daddr;
payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off);
if (unlikely(payload_ofs < 0))
return -EINVAL;
if (frag_off) {
if (frag_off & htons(~0x7))
key->ip.frag = OVS_FRAG_TYPE_LATER;
else
key->ip.frag = OVS_FRAG_TYPE_FIRST;
}
nh_len = payload_ofs - nh_ofs;
skb_set_transport_header(skb, nh_ofs + nh_len);
key->ip.proto = nexthdr;
return nh_len;
}
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params, const u8 protocol)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *inner_iph;
struct flowi4 fl4;
u8 tos, ttl;
__be16 df;
struct rtable *rt; /* Route to the other host */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
int err;
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
dst = tnl_params->daddr;
if (dst == 0) {
/* NBMA tunnel */
if (skb_dst(skb) == NULL) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
dst = rt_nexthop(rt, inner_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
const struct in6_addr *addr6;
struct neighbour *neigh;
bool do_tx_error_icmp;
int addr_type;
neigh = dst_neigh_lookup(skb_dst(skb),
&ipv6_hdr(skb)->daddr);
if (neigh == NULL)
goto tx_error;
addr6 = (const struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
do_tx_error_icmp = true;
else {
do_tx_error_icmp = false;
dst = addr6->s6_addr32[3];
}
neigh_release(neigh);
if (do_tx_error_icmp)
goto tx_error_icmp;
}
#endif
else
goto tx_error;
}
tos = tnl_params->tos;
if (tos & 0x1) {
tos &= ~0x1;
if (skb->protocol == htons(ETH_P_IP))
tos = inner_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
}
rt = ip_route_output_tunnel(tunnel->net, &fl4,
protocol,
dst, tnl_params->saddr,
tunnel->parms.o_key,
RT_TOS(tos),
tunnel->parms.link);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
if (rt->dst.dev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->net != dev_net(dev))
skb_scrub_packet(skb);
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
ttl = tnl_params->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
ttl = inner_iph->ttl;
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
#endif
else
ttl = ip4_dst_hoplimit(&rt->dst);
}
df = tnl_params->frag_off;
if (skb->protocol == htons(ETH_P_IP))
df |= (inner_iph->frag_off&htons(IP_DF));
max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
+ rt->dst.header_len;
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return;
}
err = iptunnel_xmit(dev_net(dev), rt, skb,
fl4.saddr, fl4.daddr, protocol,
tos, ttl, df);
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
return;
#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
dst_link_failure(skb);
#endif
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
}
static bool
ebt_ip6_mt(const struct sk_buff *skb, const struct xt_match_param *par)
{
const struct ebt_ip6_info *info = par->matchinfo;
const struct ipv6hdr *ih6;
struct ipv6hdr _ip6h;
const struct tcpudphdr *pptr;
struct tcpudphdr _ports;
struct in6_addr tmp_addr;
int i;
ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
if (ih6 == NULL)
return false;
if (info->bitmask & EBT_IP6_TCLASS &&
FWINV(info->tclass != ipv6_get_dsfield(ih6), EBT_IP6_TCLASS))
return false;
#if defined(CONFIG_MIPS_BRCM)
for (i = 0; i < 8; i++)
tmp_addr.in6_u.u6_addr16[i] = ih6->saddr.in6_u.u6_addr16[i] &
info->smsk.in6_u.u6_addr16[i];
#else
for (i = 0; i < 4; i++)
tmp_addr.in6_u.u6_addr32[i] = ih6->saddr.in6_u.u6_addr32[i] &
info->smsk.in6_u.u6_addr32[i];
#endif
if (info->bitmask & EBT_IP6_SOURCE &&
FWINV((ipv6_addr_cmp(&tmp_addr, &info->saddr) != 0),
EBT_IP6_SOURCE))
return false;
#if defined(CONFIG_MIPS_BRCM)
for (i = 0; i < 8; i++)
tmp_addr.in6_u.u6_addr16[i] = ih6->daddr.in6_u.u6_addr16[i] &
info->dmsk.in6_u.u6_addr16[i];
#else
for (i = 0; i < 4; i++)
tmp_addr.in6_u.u6_addr32[i] = ih6->daddr.in6_u.u6_addr32[i] &
info->dmsk.in6_u.u6_addr32[i];
#endif
if (info->bitmask & EBT_IP6_DEST &&
FWINV((ipv6_addr_cmp(&tmp_addr, &info->daddr) != 0), EBT_IP6_DEST))
return false;
if (info->bitmask & EBT_IP6_PROTO) {
uint8_t nexthdr = ih6->nexthdr;
int offset_ph;
offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr);
if (offset_ph == -1)
return false;
if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
return false;
if (!(info->bitmask & EBT_IP6_DPORT) &&
!(info->bitmask & EBT_IP6_SPORT))
return true;
pptr = skb_header_pointer(skb, offset_ph, sizeof(_ports),
&_ports);
if (pptr == NULL)
return false;
if (info->bitmask & EBT_IP6_DPORT) {
u32 dst = ntohs(pptr->dst);
if (FWINV(dst < info->dport[0] ||
dst > info->dport[1], EBT_IP6_DPORT))
return false;
}
if (info->bitmask & EBT_IP6_SPORT) {
u32 src = ntohs(pptr->src);
if (FWINV(src < info->sport[0] ||
src > info->sport[1], EBT_IP6_SPORT))
return false;
}
return true;
}
return true;
}
void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
u32 headroom = sizeof(struct iphdr);
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
const struct iphdr *inner_iph;
struct rtable *rt;
struct flowi4 fl4;
__be16 df = 0;
u8 tos, ttl;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
ip_tunnel_info_af(tun_info) != AF_INET))
goto tx_error;
key = &tun_info->key;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
tos = key->tos;
if (tos == 1) {
if (skb->protocol == htons(ETH_P_IP))
tos = inner_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
}
init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0,
RT_TOS(tos), tunnel->parms.link);
if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
goto tx_error;
rt = ip_route_output_key(tunnel->net, &fl4);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
if (rt->dst.dev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
ttl = key->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
ttl = inner_iph->ttl;
else if (skb->protocol == htons(ETH_P_IPV6))
ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
else
ttl = ip4_dst_hoplimit(&rt->dst);
}
if (key->tun_flags & TUNNEL_DONT_FRAGMENT)
df = htons(IP_DF);
else if (skb->protocol == htons(ETH_P_IP))
df = inner_iph->frag_off & htons(IP_DF);
headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
if (headroom > dev->needed_headroom)
dev->needed_headroom = headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
ip_rt_put(rt);
goto tx_dropped;
}
iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos,
key->ttl, df, !net_eq(tunnel->net, dev_net(dev)));
return;
tx_error:
dev->stats.tx_errors++;
goto kfree;
tx_dropped:
dev->stats.tx_dropped++;
kfree:
kfree_skb(skb);
}
int
ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
struct rt6_info *rt; /* Route to the other host */
struct in6_addr saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct ipv6hdr *old_iph = ipv6_hdr(skb);
struct ipv6hdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int ret, local;
EnterFunction(10);
rcu_read_lock();
local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6,
&saddr, ipvsh, 1,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_TUNNEL);
if (local < 0)
goto tx_error;
if (local) {
rcu_read_unlock();
return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1);
}
rt = (struct rt6_info *) skb_dst(skb);
tdev = rt->dst.dev;
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);
if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
if (!new_skb)
goto tx_error;
consume_skb(skb);
skb = new_skb;
old_iph = ipv6_hdr(skb);
}
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/*
* Push down and install the IPIP header.
*/
iph = ipv6_hdr(skb);
iph->version = 6;
iph->nexthdr = IPPROTO_IPV6;
iph->payload_len = old_iph->payload_len;
be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph));
iph->daddr = cp->daddr.in6;
iph->saddr = saddr;
iph->hop_limit = old_iph->hop_limit;
/* Another hack: avoid icmp_send in ip_fragment */
skb->ignore_df = 1;
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
ip6_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
tx_error:
kfree_skb(skb);
rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
}
static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct net_device_stats *stats = &tunnel->stat;
struct iphdr *tiph = &tunnel->parms.iph;
struct ipv6hdr *iph6 = ipv6_hdr(skb);
u8 tos = tunnel->parms.iph.tos;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
int mtu;
if (tunnel->recursion++) {
tunnel->stat.collisions++;
goto tx_error;
}
if (skb->protocol != htons(ETH_P_IPV6))
goto tx_error;
if (extract_ipv4_endpoint(&iph6->daddr, &dst) < 0)
goto tx_error_icmp;
{
struct flowi fl = { .nl_u = { .ip4_u =
{ .daddr = dst,
.saddr = tiph->saddr,
.tos = RT_TOS(tos) } },
.oif = tunnel->parms.link,
.proto = IPPROTO_IPV6 };
if (ip_route_output_key(&rt, &fl)) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
}
if (rt->rt_type != RTN_UNICAST) {
ip_rt_put(rt);
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
tunnel->stat.collisions++;
goto tx_error;
}
if (tiph->frag_off)
mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
else
mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
if (mtu < 68) {
tunnel->stat.collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (tunnel->parms.iph.daddr && skb->dst)
skb->dst->ops->update_pmtu(skb->dst, mtu);
if (skb->len > mtu) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->err_count > 0) {
if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
iph6 = ipv6_hdr(skb);
}
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags = 0;
dst_release(skb->dst);
skb->dst = &rt->u.dst;
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
if (mtu > IPV6_MIN_MTU)
iph->frag_off = htons(IP_DF);
else
iph->frag_off = 0;
iph->protocol = IPPROTO_IPV6;
iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = iph6->hop_limit;
nf_reset(skb);
IPTUNNEL_XMIT();
tunnel->recursion--;
return 0;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
static bool
ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct ebt_ip6_info *info = par->matchinfo;
const struct ipv6hdr *ih6;
struct ipv6hdr _ip6h;
const union pkthdr *pptr;
union pkthdr _pkthdr;
ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
if (ih6 == NULL)
return false;
if (info->bitmask & EBT_IP6_TCLASS &&
FWINV(info->tclass != ipv6_get_dsfield(ih6), EBT_IP6_TCLASS))
return false;
if (FWINV(ipv6_masked_addr_cmp(&ih6->saddr, &info->smsk,
&info->saddr), EBT_IP6_SOURCE) ||
FWINV(ipv6_masked_addr_cmp(&ih6->daddr, &info->dmsk,
&info->daddr), EBT_IP6_DEST))
return false;
if (info->bitmask & EBT_IP6_PROTO) {
uint8_t nexthdr = ih6->nexthdr;
__be16 frag_off;
int offset_ph;
offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr, &frag_off);
if (offset_ph == -1)
return false;
if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
return false;
if (!(info->bitmask & ( EBT_IP6_DPORT |
EBT_IP6_SPORT | EBT_IP6_ICMP6)))
return true;
/* min icmpv6 headersize is 4, so sizeof(_pkthdr) is ok. */
pptr = skb_header_pointer(skb, offset_ph, sizeof(_pkthdr),
&_pkthdr);
if (pptr == NULL)
return false;
if (info->bitmask & EBT_IP6_DPORT) {
u16 dst = ntohs(pptr->tcpudphdr.dst);
if (FWINV(dst < info->dport[0] ||
dst > info->dport[1], EBT_IP6_DPORT))
return false;
}
if (info->bitmask & EBT_IP6_SPORT) {
u16 src = ntohs(pptr->tcpudphdr.src);
if (FWINV(src < info->sport[0] ||
src > info->sport[1], EBT_IP6_SPORT))
return false;
}
if ((info->bitmask & EBT_IP6_ICMP6) &&
FWINV(pptr->icmphdr.type < info->icmpv6_type[0] ||
pptr->icmphdr.type > info->icmpv6_type[1] ||
pptr->icmphdr.code < info->icmpv6_code[0] ||
pptr->icmphdr.code > info->icmpv6_code[1],
EBT_IP6_ICMP6))
return false;
}
return true;
}
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
const struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
struct net *net = dev_net(skb->dev);
if (skb->pkt_type == PACKET_OTHERHOST) {
kfree_skb(skb);
return NET_RX_DROP;
}
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
__IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
!idev || unlikely(idev->cnf.disable_ipv6)) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
/*
* Store incoming device index. When the packet will
* be queued, we cannot refer to skb->dev anymore.
*
* BTW, when we send a packet for our own local address on a
* non-loopback interface (e.g. ethX), it is being delivered
* via the loopback interface (lo) here; skb->dev = loopback_dev.
* It, however, should be considered as if it is being
* arrived via the sending interface (ethX), because of the
* nature of scoping architecture. --yoshfuji
*/
IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
goto err;
hdr = ipv6_hdr(skb);
if (hdr->version != 6)
goto err;
__IP6_ADD_STATS(net, idev,
IPSTATS_MIB_NOECTPKTS +
(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
/*
* RFC4291 2.5.3
* A packet received on an interface with a destination address
* of loopback must be dropped.
*/
if (!(dev->flags & IFF_LOOPBACK) &&
ipv6_addr_loopback(&hdr->daddr))
goto err;
/* RFC4291 Errata ID: 3480
* Interface-Local scope spans only a single interface on a
* node and is useful only for loopback transmission of
* multicast. Packets with interface-local scope received
* from another node must be discarded.
*/
if (!(skb->pkt_type == PACKET_LOOPBACK ||
dev->flags & IFF_LOOPBACK) &&
ipv6_addr_is_multicast(&hdr->daddr) &&
IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
goto err;
/* If enabled, drop unicast packets that were encapsulated in link-layer
* multicast or broadcast to protected against the so-called "hole-196"
* attack in 802.11 wireless.
*/
if (!ipv6_addr_is_multicast(&hdr->daddr) &&
(skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) &&
idev->cnf.drop_unicast_in_l2_multicast)
goto err;
/* RFC4291 2.7
* Nodes must not originate a packet to a multicast address whose scope
* field contains the reserved value 0; if such a packet is received, it
* must be silently dropped.
*/
if (ipv6_addr_is_multicast(&hdr->daddr) &&
IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
goto err;
/*
* RFC4291 2.7
* Multicast addresses must not be used as source addresses in IPv6
* packets or appear in any Routing header.
*/
if (ipv6_addr_is_multicast(&hdr->saddr))
goto err;
skb->transport_header = skb->network_header + sizeof(*hdr);
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
pkt_len = ntohs(hdr->payload_len);
/* pkt_len may be zero if Jumbo payload option is present */
if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
__IP6_INC_STATS(net,
idev, IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
}
if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
goto drop;
}
hdr = ipv6_hdr(skb);
}
if (hdr->nexthdr == NEXTHDR_HOP) {
if (ipv6_parse_hopopts(skb) < 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
rcu_read_unlock();
return NET_RX_DROP;
}
}
rcu_read_unlock();
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
net, NULL, skb, dev, NULL,
ip6_rcv_finish);
err:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
drop:
rcu_read_unlock();
kfree_skb(skb);
return NET_RX_DROP;
}
static bool
ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct ebt_ip6_info *info = par->matchinfo;
const struct ipv6hdr *ih6;
struct ipv6hdr _ip6h;
const struct tcpudphdr *pptr;
struct tcpudphdr _ports;
struct in6_addr tmp_addr;
int i;
#if 1
if(skb->protocol == htons(ETH_P_IPV6))
ih6 = (struct ipv6hdr *)skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
else if((skb->protocol == htons(ETH_P_8021Q)) && (vlan_proto(skb) == htons(ETH_P_IPV6)))
ih6 = (struct ipv6hdr *)(skb_mac_header(skb) + VLAN_ETH_HLEN);
else if((skb->protocol == htons(ETH_P_PPP_SES)) && (pppoe_proto(skb) == htons(0x0021)))
ih6 = (struct ipv6hdr *)(skb_mac_header(skb) + ETH_HLEN +PPPOE_SES_HLEN);
else
ih6 = (struct ipv6hdr *)skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
#else
ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h);
#endif
if (ih6 == NULL)
return false;
#if 1
if (info->bitmask & EBT_IP6_TCLASS) {
__u8 tc = ipv6_get_dsfield((struct ipv6hdr *)ih6);
if (FWINV(tc < info->tclass[0] ||
tc > info->tclass[1], EBT_IP6_TCLASS))
return false;
}
#else
if (info->bitmask & EBT_IP6_TCLASS &&
FWINV(info->tclass != ipv6_get_dsfield((struct ipv6hdr *)ih6), EBT_IP6_TCLASS))
//return false;
return false;
#endif
#if 1
for (i = 0; i < 4; i++)
tmp_addr.in6_u.u6_addr32[i] = ih6->saddr.in6_u.u6_addr32[i] &
info->smsk.in6_u.u6_addr32[i];
if (info->bitmask & EBT_IP6_SOURCE &&
FWINV((ipv6_addr_cmp(&tmp_addr, &info->saddr) != 0),
EBT_IP6_SOURCE))
return false;
for (i = 0; i < 4; i++)
tmp_addr.in6_u.u6_addr32[i] = ih6->daddr.in6_u.u6_addr32[i] &
info->dmsk.in6_u.u6_addr32[i];
if (info->bitmask & EBT_IP6_DEST &&
FWINV((ipv6_addr_cmp(&tmp_addr, &info->daddr) != 0), EBT_IP6_DEST))
return false;
#else
if (FWINV(ipv6_masked_addr_cmp(&ih6->saddr, &info->smsk,
&info->saddr), EBT_IP6_SOURCE) ||
FWINV(ipv6_masked_addr_cmp(&ih6->daddr, &info->dmsk,
&info->daddr), EBT_IP6_DEST))
return false;
#endif
if (info->bitmask & EBT_IP6_PROTO) {
uint8_t nexthdr = ih6->nexthdr;
int offset_ph;
offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr);
if (offset_ph == -1)
return false;
#if 1
if ( FWINV((info->protocol[0] != nexthdr) && (info->protocol[1] != nexthdr), EBT_IP6_PROTO) )
return false;
#else
if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
return false;
#endif
if (!(info->bitmask & EBT_IP6_DPORT) &&
!(info->bitmask & EBT_IP6_SPORT)){
return true;
}
#if 1
if(skb->protocol == htons(ETH_P_IP))
pptr = (struct tcpudphdr *)skb_header_pointer(skb, offset_ph, sizeof(_ports), &_ports);
else if((skb->protocol == htons(ETH_P_8021Q)) && (vlan_proto(skb) == htons(ETH_P_IP)))
pptr = (struct tcpudphdr *)(skb_mac_header(skb) + VLAN_ETH_HLEN + offset_ph);
else if((skb->protocol == htons(ETH_P_PPP_SES)) && (pppoe_proto(skb) == htons(0x0021)))
pptr = (struct tcpudphdr *)(skb_mac_header(skb) + ETH_HLEN + PPPOE_SES_HLEN + offset_ph);
else
pptr = (struct tcpudphdr *)skb_header_pointer(skb, offset_ph, sizeof(_ports), &_ports);
#else
pptr = skb_header_pointer(skb, offset_ph, sizeof(_ports),
&_ports);
#endif
if (pptr == NULL)
return false;
if (info->bitmask & EBT_IP6_DPORT) {
u32 dst = ntohs(pptr->dst);
if (FWINV(dst < info->dport[0] ||
dst > info->dport[1], EBT_IP6_DPORT))
return false;
}
if (info->bitmask & EBT_IP6_SPORT) {
u32 src = ntohs(pptr->src);
if (FWINV(src < info->sport[0] ||
src > info->sport[1], EBT_IP6_SPORT))
return false;
}
return true;
}
return true;
}
static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct net_device_stats *stats = &tunnel->dev->stats;
struct iphdr *tiph = &tunnel->parms.iph;
struct ipv6hdr *iph6 = ipv6_hdr(skb);
u8 tos = tunnel->parms.iph.tos;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
int mtu;
struct in6_addr *addr6;
int addr_type;
if (skb->protocol != htons(ETH_P_IPV6))
goto tx_error;
/* ISATAP (RFC4214) - must come before 6to4 */
if (dev->priv_flags & IFF_ISATAP) {
struct neighbour *neigh = NULL;
if (skb_dst(skb))
neigh = skb_dst(skb)->neighbour;
if (neigh == NULL) {
if (net_ratelimit())
printk(KERN_DEBUG "sit: nexthop == NULL\n");
goto tx_error;
}
addr6 = (struct in6_addr*)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if ((addr_type & IPV6_ADDR_UNICAST) &&
ipv6_addr_is_isatap(addr6))
dst = addr6->s6_addr32[3];
else
goto tx_error;
}
if (!dst)
dst = try_6to4(&iph6->daddr);
if (!dst) {
struct neighbour *neigh = NULL;
if (skb_dst(skb))
neigh = skb_dst(skb)->neighbour;
if (neigh == NULL) {
if (net_ratelimit())
printk(KERN_DEBUG "sit: nexthop == NULL\n");
goto tx_error;
}
addr6 = (struct in6_addr*)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
goto tx_error_icmp;
dst = addr6->s6_addr32[3];
}
{
struct flowi fl = { .nl_u = { .ip4_u =
{ .daddr = dst,
.saddr = tiph->saddr,
.tos = RT_TOS(tos) } },
.oif = tunnel->parms.link,
.proto = IPPROTO_IPV6 };
if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
stats->tx_carrier_errors++;
goto tx_error_icmp;
}
}
if (rt->rt_type != RTN_UNICAST) {
ip_rt_put(rt);
stats->tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
stats->collisions++;
goto tx_error;
}
if (tiph->frag_off)
mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
else
mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
if (mtu < 68) {
stats->collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (tunnel->parms.iph.daddr && skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (skb->len > mtu) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
stats->tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
iph6 = ipv6_hdr(skb);
}
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags = 0;
skb_dst_drop(skb);
skb_dst_set(skb, &rt->u.dst);
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
if (mtu > IPV6_MIN_MTU)
iph->frag_off = tiph->frag_off;
else
iph->frag_off = 0;
iph->protocol = IPPROTO_IPV6;
iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = iph6->hop_limit;
nf_reset(skb);
IPTUNNEL_XMIT();
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
static inline void ip6ip_ecn_decapsulate(struct sk_buff *skb)
{
if (INET_ECN_is_ce(ipv6_get_dsfield(skb->nh.ipv6h)))
IP_ECN_set_ce(skb->h.ipiph);
}
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *inner_iph;
struct iphdr *iph;
struct flowi4 fl4;
u8 tos, ttl;
__be16 df;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
int mtu;
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
dst = tnl_params->daddr;
if (dst == 0) {
/* NBMA tunnel */
if (skb_dst(skb) == NULL) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
dst = rt_nexthop(rt, inner_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
const struct in6_addr *addr6;
struct neighbour *neigh;
bool do_tx_error_icmp;
int addr_type;
neigh = dst_neigh_lookup(skb_dst(skb),
&ipv6_hdr(skb)->daddr);
if (neigh == NULL)
goto tx_error;
addr6 = (const struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
do_tx_error_icmp = true;
else {
do_tx_error_icmp = false;
dst = addr6->s6_addr32[3];
}
neigh_release(neigh);
if (do_tx_error_icmp)
goto tx_error_icmp;
}
#endif
else
goto tx_error;
}
tos = tnl_params->tos;
if (tos & 0x1) {
tos &= ~0x1;
if (skb->protocol == htons(ETH_P_IP))
tos = inner_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
}
rt = ip_route_output_tunnel(dev_net(dev), &fl4,
tunnel->parms.iph.protocol,
dst, tnl_params->saddr,
tunnel->parms.o_key,
RT_TOS(tos),
tunnel->parms.link);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
tdev = rt->dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
df = tnl_params->frag_off;
if (df)
mtu = dst_mtu(&rt->dst) - dev->hard_header_len
- sizeof(struct iphdr);
else
mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
df |= (inner_iph->frag_off&htons(IP_DF));
if (!skb_is_gso(skb) &&
(inner_iph->frag_off&htons(IP_DF)) &&
mtu < ntohs(inner_iph->tot_len)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
ip_rt_put(rt);
goto tx_error;
}
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
mtu >= IPV6_MIN_MTU) {
if ((tunnel->parms.iph.daddr &&
!ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
rt6->rt6i_dst.plen == 128) {
rt6->rt6i_flags |= RTF_MODIFIED;
dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
}
}
if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
mtu < skb->len) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
}
}
#endif
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
ttl = tnl_params->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
ttl = inner_iph->ttl;
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
#endif
else
ttl = ip4_dst_hoplimit(&rt->dst);
}
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr)
+ rt->dst.header_len;
if (max_headroom > dev->needed_headroom) {
dev->needed_headroom = max_headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return;
}
}
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = tnl_params->protocol;
iph->tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
iph->daddr = fl4.daddr;
iph->saddr = fl4.saddr;
iph->ttl = ttl;
tunnel_ip_select_ident(skb, inner_iph, &rt->dst);
iptunnel_xmit(skb, dev);
return;
#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
dst_link_failure(skb);
#endif
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
}
static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
{
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
}
static int
ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->stat;
struct ipv6hdr *ipv6h = skb->nh.ipv6h;
int encap_limit = -1;
struct ipv6_tel_txoption opt;
__u16 offset;
struct flowi fl;
struct dst_entry *dst;
struct net_device *tdev;
int mtu;
int max_headroom = sizeof(struct ipv6hdr);
u8 proto;
int err;
int pkt_len;
int dsfield;
if (t->recursion++) {
stats->collisions++;
goto tx_err;
}
if (skb->protocol != htons(ETH_P_IPV6) ||
!ip6_tnl_xmit_ctl(t) || ip6ip6_tnl_addr_conflict(t, ipv6h))
goto tx_err;
if ((offset = parse_tlv_tnl_enc_lim(skb, skb->nh.raw)) > 0) {
struct ipv6_tlv_tnl_enc_lim *tel;
tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->nh.raw[offset];
if (tel->encap_limit == 0) {
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_HDR_FIELD, offset + 2, skb->dev);
goto tx_err;
}
encap_limit = tel->encap_limit - 1;
} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
encap_limit = t->parms.encap_limit;
memcpy(&fl, &t->fl, sizeof (fl));
proto = fl.proto;
dsfield = ipv6_get_dsfield(ipv6h);
if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL))
fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);
if ((dst = ip6_tnl_dst_check(t)) != NULL)
dst_hold(dst);
else {
dst = ip6_route_output(NULL, &fl);
if (dst->error || xfrm_lookup(&dst, &fl, NULL, 0) < 0)
goto tx_err_link_failure;
}
tdev = dst->dev;
if (tdev == dev) {
stats->collisions++;
if (net_ratelimit())
printk(KERN_WARNING
"%s: Local routing loop detected!\n",
t->parms.name);
goto tx_err_dst_release;
}
mtu = dst_mtu(dst) - sizeof (*ipv6h);
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (skb->dst)
skb->dst->ops->update_pmtu(skb->dst, mtu);
if (skb->len > mtu) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
goto tx_err_dst_release;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom += LL_RESERVED_SPACE(tdev);
if (skb_headroom(skb) < max_headroom ||
skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb;
if (!(new_skb = skb_realloc_headroom(skb, max_headroom)))
goto tx_err_dst_release;
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
kfree_skb(skb);
skb = new_skb;
}
dst_release(skb->dst);
skb->dst = dst_clone(dst);
skb->h.raw = skb->nh.raw;
if (encap_limit >= 0) {
init_tel_txopt(&opt, encap_limit);
ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
}
skb->nh.raw = skb_push(skb, sizeof(struct ipv6hdr));
ipv6h = skb->nh.ipv6h;
*(__be32*)ipv6h = fl.fl6_flowlabel | htonl(0x60000000);
dsfield = INET_ECN_encapsulate(0, dsfield);
ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = proto;
ipv6_addr_copy(&ipv6h->saddr, &fl.fl6_src);
ipv6_addr_copy(&ipv6h->daddr, &fl.fl6_dst);
nf_reset(skb);
pkt_len = skb->len;
err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL,
skb->dst->dev, dst_output);
if (net_xmit_eval(err) == 0) {
stats->tx_bytes += pkt_len;
stats->tx_packets++;
} else {
stats->tx_errors++;
stats->tx_aborted_errors++;
}
ip6_tnl_dst_store(t, dst);
t->recursion--;
return 0;
tx_err_link_failure:
stats->tx_carrier_errors++;
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
tx_err:
stats->tx_errors++;
stats->tx_dropped++;
kfree_skb(skb);
t->recursion--;
return 0;
}
