/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401.
*/
static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *top_iph;
int dsfield;
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct ipv6hdr, nexthdr);
skb->transport_header = skb->network_header + sizeof(*top_iph);
top_iph = ipv6_hdr(skb);
top_iph->version = 6;
memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
sizeof(top_iph->flow_lbl));
top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family);
dsfield = XFRM_MODE_SKB_CB(skb)->tos;
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->hop_limit = ip6_dst_hoplimit(dst->child);
ipv6_addr_copy(&top_iph->saddr, (const struct in6_addr *)&x->props.saddr);
ipv6_addr_copy(&top_iph->daddr, (const struct in6_addr *)&x->id.daddr);
return 0;
}
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
struct ipv6_txoptions *opt)
{
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *first_hop = &fl6->daddr;
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr;
u8 proto = fl6->flowi6_proto;
int seg_len = skb->len;
int hlimit = -1;
int tclass = 0;
u32 mtu;
if (opt) {
unsigned int head_room;
/* First: exthdrs may take lots of space (~8K for now)
MAX_HEADER is not enough.
*/
head_room = opt->opt_nflen + opt->opt_flen;
seg_len += head_room;
head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
if (skb_headroom(skb) < head_room) {
struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
if (skb2 == NULL) {
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return -ENOBUFS;
}
kfree_skb(skb);
skb = skb2;
skb_set_owner_w(skb, sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
/*
* Fill in the IPv6 header
*/
if (np) {
tclass = np->tclass;
hlimit = np->hop_limit;
}
if (hlimit < 0)
hlimit = ip6_dst_hoplimit(dst);
*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl6->flowlabel;
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
hdr->hop_limit = hlimit;
ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
ipv6_addr_copy(&hdr->daddr, first_hop);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
mtu = dst_mtu(dst);
if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUT, skb->len);
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
dst->dev, dst_output);
}
if (net_ratelimit())
printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen, unsigned int flags)
{
struct ipv6_pinfo *np = inet6_sk(sk);
int len;
int val;
if (ip6_mroute_opt(optname))
return ip6_mroute_getsockopt(sk, optname, optval, optlen);
if (get_user(len, optlen))
return -EFAULT;
switch (optname) {
case IPV6_ADDRFORM:
if (sk->sk_protocol != IPPROTO_UDP &&
sk->sk_protocol != IPPROTO_UDPLITE &&
sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
if (sk->sk_state != TCP_ESTABLISHED)
return -ENOTCONN;
val = sk->sk_family;
break;
case MCAST_MSFILTER:
{
struct group_filter gsf;
int err;
if (len < GROUP_FILTER_SIZE(0))
return -EINVAL;
if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0)))
return -EFAULT;
if (gsf.gf_group.ss_family != AF_INET6)
return -EADDRNOTAVAIL;
lock_sock(sk);
err = ip6_mc_msfget(sk, &gsf,
(struct group_filter __user *)optval, optlen);
release_sock(sk);
return err;
}
case IPV6_2292PKTOPTIONS:
{
struct msghdr msg;
struct sk_buff *skb;
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
msg.msg_control = (void __force_kernel *)optval;
msg.msg_controllen = len;
msg.msg_flags = flags;
lock_sock(sk);
skb = np->pktoptions;
if (skb)
atomic_inc(&skb->users);
release_sock(sk);
if (skb) {
int err = ip6_datagram_recv_ctl(sk, &msg, skb);
kfree_skb(skb);
if (err)
return err;
} else {
if (np->rxopt.bits.rxinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxhlim) {
int hlim = np->mcast_hops;
put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
}
if (np->rxopt.bits.rxtclass) {
int tclass = np->rcv_tclass;
put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
}
if (np->rxopt.bits.rxoinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxohlim) {
int hlim = np->mcast_hops;
put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim);
}
}
len -= msg.msg_controllen;
return put_user(len, optlen);
}
case IPV6_MTU:
{
struct dst_entry *dst;
val = 0;
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
val = dst_mtu(dst);
rcu_read_unlock();
if (!val)
return -ENOTCONN;
break;
}
case IPV6_V6ONLY:
val = np->ipv6only;
break;
case IPV6_RECVPKTINFO:
val = np->rxopt.bits.rxinfo;
break;
case IPV6_2292PKTINFO:
val = np->rxopt.bits.rxoinfo;
break;
case IPV6_RECVHOPLIMIT:
val = np->rxopt.bits.rxhlim;
break;
case IPV6_2292HOPLIMIT:
val = np->rxopt.bits.rxohlim;
break;
case IPV6_RECVRTHDR:
val = np->rxopt.bits.srcrt;
break;
case IPV6_2292RTHDR:
val = np->rxopt.bits.osrcrt;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
lock_sock(sk);
len = ipv6_getsockopt_sticky(sk, np->opt,
optname, optval, len);
release_sock(sk);
/* check if ipv6_getsockopt_sticky() returns err code */
if (len < 0)
return len;
return put_user(len, optlen);
}
case IPV6_RECVHOPOPTS:
val = np->rxopt.bits.hopopts;
break;
case IPV6_2292HOPOPTS:
val = np->rxopt.bits.ohopopts;
break;
case IPV6_RECVDSTOPTS:
val = np->rxopt.bits.dstopts;
break;
case IPV6_2292DSTOPTS:
val = np->rxopt.bits.odstopts;
break;
case IPV6_TCLASS:
val = np->tclass;
break;
case IPV6_RECVTCLASS:
val = np->rxopt.bits.rxtclass;
break;
case IPV6_FLOWINFO:
val = np->rxopt.bits.rxflow;
break;
case IPV6_RECVPATHMTU:
val = np->rxopt.bits.rxpmtu;
break;
case IPV6_PATHMTU:
{
struct dst_entry *dst;
struct ip6_mtuinfo mtuinfo;
if (len < sizeof(mtuinfo))
return -EINVAL;
len = sizeof(mtuinfo);
memset(&mtuinfo, 0, sizeof(mtuinfo));
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
mtuinfo.ip6m_mtu = dst_mtu(dst);
rcu_read_unlock();
if (!mtuinfo.ip6m_mtu)
return -ENOTCONN;
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &mtuinfo, len))
return -EFAULT;
return 0;
break;
}
case IPV6_TRANSPARENT:
val = inet_sk(sk)->transparent;
break;
case IPV6_RECVORIGDSTADDR:
val = np->rxopt.bits.rxorigdstaddr;
break;
case IPV6_UNICAST_HOPS:
case IPV6_MULTICAST_HOPS:
{
struct dst_entry *dst;
if (optname == IPV6_UNICAST_HOPS)
val = np->hop_limit;
else
val = np->mcast_hops;
if (val < 0) {
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
val = ip6_dst_hoplimit(dst);
rcu_read_unlock();
}
if (val < 0)
val = sock_net(sk)->ipv6.devconf_all->hop_limit;
break;
}
case IPV6_MULTICAST_LOOP:
val = np->mc_loop;
break;
case IPV6_MULTICAST_IF:
val = np->mcast_oif;
break;
case IPV6_UNICAST_IF:
val = (__force int)htonl((__u32) np->ucast_oif);
break;
case IPV6_MTU_DISCOVER:
val = np->pmtudisc;
break;
case IPV6_RECVERR:
val = np->recverr;
break;
case IPV6_FLOWINFO_SEND:
val = np->sndflow;
break;
case IPV6_ADDR_PREFERENCES:
val = 0;
if (np->srcprefs & IPV6_PREFER_SRC_TMP)
val |= IPV6_PREFER_SRC_TMP;
else if (np->srcprefs & IPV6_PREFER_SRC_PUBLIC)
val |= IPV6_PREFER_SRC_PUBLIC;
else {
/* XXX: should we return system default? */
val |= IPV6_PREFER_SRC_PUBTMP_DEFAULT;
}
if (np->srcprefs & IPV6_PREFER_SRC_COA)
val |= IPV6_PREFER_SRC_COA;
else
val |= IPV6_PREFER_SRC_HOME;
break;
case IPV6_MINHOPCOUNT:
val = np->min_hopcount;
break;
case IPV6_DONTFRAG:
val = np->dontfrag;
break;
default:
return -ENOPROTOOPT;
}
len = min_t(unsigned int, sizeof(int), len);
if(put_user(len, optlen))
return -EFAULT;
if(copy_to_user(optval,&val,len))
return -EFAULT;
return 0;
}
/* tipc_send_msg - enqueue a send request */
static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
struct tipc_bearer *b,
struct tipc_media_addr *dest)
{
int ttl, err = 0;
struct udp_bearer *ub;
struct udp_media_addr *dst = (struct udp_media_addr *)&dest->value;
struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value;
struct rtable *rt;
if (skb_headroom(skb) < UDP_MIN_HEADROOM) {
err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
if (err)
goto tx_error;
}
skb_set_inner_protocol(skb, htons(ETH_P_TIPC));
ub = rcu_dereference_rtnl(b->media_ptr);
if (!ub) {
err = -ENODEV;
goto tx_error;
}
if (dst->proto == htons(ETH_P_IP)) {
struct flowi4 fl = {
.daddr = dst->ipv4.s_addr,
.saddr = src->ipv4.s_addr,
.flowi4_mark = skb->mark,
.flowi4_proto = IPPROTO_UDP
};
rt = ip_route_output_key(net, &fl);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
goto tx_error;
}
skb->dev = rt->dst.dev;
ttl = ip4_dst_hoplimit(&rt->dst);
udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr,
dst->ipv4.s_addr, 0, ttl, 0, src->port,
dst->port, false, true);
#if IS_ENABLED(CONFIG_IPV6)
} else {
struct dst_entry *ndst;
struct flowi6 fl6 = {
.flowi6_oif = ub->ifindex,
.daddr = dst->ipv6,
.saddr = src->ipv6,
.flowi6_proto = IPPROTO_UDP
};
err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk, &ndst,
&fl6);
if (err)
goto tx_error;
ttl = ip6_dst_hoplimit(ndst);
err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb,
ndst->dev, &src->ipv6,
&dst->ipv6, 0, ttl, 0, src->port,
dst->port, false);
#endif
}
return err;
tx_error:
kfree_skb(skb);
return err;
}
/* tipc_udp_recv - read data from bearer socket */
static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
{
struct udp_bearer *ub;
struct tipc_bearer *b;
ub = rcu_dereference_sk_user_data(sk);
if (!ub) {
pr_err_ratelimited("Failed to get UDP bearer reference");
kfree_skb(skb);
return 0;
}
skb_pull(skb, sizeof(struct udphdr));
rcu_read_lock();
b = rcu_dereference_rtnl(ub->bearer);
if (b) {
tipc_rcv(sock_net(sk), skb, b);
rcu_read_unlock();
return 0;
}
rcu_read_unlock();
kfree_skb(skb);
return 0;
}
static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote)
{
int err = 0;
struct ip_mreqn mreqn;
struct sock *sk = ub->ubsock->sk;
if (ntohs(remote->proto) == ETH_P_IP) {
if (!ipv4_is_multicast(remote->ipv4.s_addr))
return 0;
mreqn.imr_multiaddr = remote->ipv4;
mreqn.imr_ifindex = ub->ifindex;
err = ip_mc_join_group(sk, &mreqn);
#if IS_ENABLED(CONFIG_IPV6)
} else {
if (!ipv6_addr_is_multicast(&remote->ipv6))
return 0;
err = ipv6_stub->ipv6_sock_mc_join(sk, ub->ifindex,
&remote->ipv6);
#endif
}
return err;
}
int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct icmp6hdr user_icmph;
int addr_type;
struct in6_addr *daddr;
int iif = 0;
struct flowi6 fl6;
int err;
int hlimit;
struct dst_entry *dst;
struct rt6_info *rt;
struct pingfakehdr pfh;
pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph,
sizeof(user_icmph));
if (err)
return err;
if (msg->msg_name) {
struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name;
if (msg->msg_namelen < sizeof(struct sockaddr_in6) ||
u->sin6_family != AF_INET6) {
return -EINVAL;
}
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != u->sin6_scope_id) {
return -EINVAL;
}
daddr = &(u->sin6_addr);
iif = u->sin6_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
daddr = &np->daddr;
}
if (!iif)
iif = sk->sk_bound_dev_if;
addr_type = ipv6_addr_type(daddr);
if (__ipv6_addr_needs_scope_id(addr_type) && !iif)
return -EINVAL;
if (addr_type & IPV6_ADDR_MAPPED)
return -EINVAL;
/* TODO: use ip6_datagram_send_ctl to get options from cmsg */
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.saddr = np->saddr;
fl6.daddr = *daddr;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
fl6.flowi6_uid = sock_i_uid(sk);
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
fl6.flowi6_oif = np->mcast_oif;
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, 1);
if (IS_ERR(dst))
return PTR_ERR(dst);
rt = (struct rt6_info *) dst;
np = inet6_sk(sk);
if (!np)
return -EBADF;
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
fl6.flowi6_oif = np->mcast_oif;
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
pfh.icmph.type = user_icmph.icmp6_type;
pfh.icmph.code = user_icmph.icmp6_code;
pfh.icmph.checksum = 0;
pfh.icmph.un.echo.id = inet->inet_sport;
pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
pfh.iov = msg->msg_iov;
pfh.wcheck = 0;
pfh.family = AF_INET6;
if (ipv6_addr_is_multicast(&fl6.daddr))
hlimit = np->mcast_hops;
else
hlimit = np->hop_limit;
if (hlimit < 0)
hlimit = ip6_dst_hoplimit(dst);
lock_sock(sk);
err = ip6_append_data(sk, ping_getfrag, &pfh, len,
0, hlimit,
np->tclass, NULL, &fl6, rt,
MSG_DONTWAIT, np->dontfrag);
if (err) {
ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
} else {
err = icmpv6_push_pending_frames(sk, &fl6,
(struct icmp6hdr *) &pfh.icmph,
len);
}
release_sock(sk);
if (err)
return err;
return len;
}
/*
* xmit an sk_buff (used by TCP, SCTP and DCCP)
* Note : socket lock is not held for SYNACK packets, but might be modified
* by calls to skb_set_owner_w() and ipv6_local_error(),
* which are using proper atomic operations or spinlocks.
*/
int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
struct ipv6_txoptions *opt, int tclass)
{
struct net *net = sock_net(sk);
const struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *first_hop = &fl6->daddr;
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr;
u8 proto = fl6->flowi6_proto;
int seg_len = skb->len;
int hlimit = -1;
u32 mtu;
if (opt) {
unsigned int head_room;
/* First: exthdrs may take lots of space (~8K for now)
MAX_HEADER is not enough.
*/
head_room = opt->opt_nflen + opt->opt_flen;
seg_len += head_room;
head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
if (skb_headroom(skb) < head_room) {
struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
if (!skb2) {
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return -ENOBUFS;
}
consume_skb(skb);
skb = skb2;
/* skb_set_owner_w() changes sk->sk_wmem_alloc atomically,
* it is safe to call in our context (socket lock not held)
*/
skb_set_owner_w(skb, (struct sock *)sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
/*
* Fill in the IPv6 header
*/
if (np)
hlimit = np->hop_limit;
if (hlimit < 0)
hlimit = ip6_dst_hoplimit(dst);
ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
np->autoflowlabel, fl6));
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
hdr->hop_limit = hlimit;
hdr->saddr = fl6->saddr;
hdr->daddr = *first_hop;
skb->protocol = htons(ETH_P_IPV6);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
mtu = dst_mtu(dst);
if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUT, skb->len);
/* hooks should never assume socket lock is held.
* we promote our socket to non const
*/
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
net, (struct sock *)sk, skb, NULL, dst->dev,
dst_output);
}
skb->dev = dst->dev;
/* ipv6_local_error() does not require socket lock,
* we promote our socket to non const
*/
ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
struct ipv6_txoptions *opt)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *first_hop = &fl->fl6_dst;
struct dst_entry *dst = skb->dst;
struct ipv6hdr *hdr;
u8 proto = fl->proto;
int seg_len = skb->len;
int hlimit, tclass;
u32 mtu;
if (opt) {
unsigned int head_room;
/* First: exthdrs may take lots of space (~8K for now)
MAX_HEADER is not enough.
*/
head_room = opt->opt_nflen + opt->opt_flen;
seg_len += head_room;
head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
if (skb_headroom(skb) < head_room) {
struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
if (skb2 == NULL) {
IP6_INC_STATS(ip6_dst_idev(skb->dst),
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return -ENOBUFS;
}
kfree_skb(skb);
skb = skb2;
skb_set_owner_w(skb, sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
}
hdr = skb->nh.ipv6h = (struct ipv6hdr*)skb_push(skb, sizeof(struct ipv6hdr));
/*
* Fill in the IPv6 header
*/
hlimit = -1;
if (np)
hlimit = np->hop_limit;
if (hlimit < 0)
hlimit = ip6_dst_hoplimit(dst);
tclass = -1;
if (np)
tclass = np->tclass;
if (tclass < 0)
tclass = 0;
*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel;
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
hdr->hop_limit = hlimit;
ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
ipv6_addr_copy(&hdr->daddr, first_hop);
skb->protocol = htons(ETH_P_IPV6);
skb->priority = sk->sk_priority;
mtu = ip6_skb_dst_mtu(skb);
if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
IP6_INC_STATS(ip6_dst_idev(skb->dst),
IPSTATS_MIB_OUTREQUESTS);
#if defined (CONFIG_RA_HW_NAT_IPV6)
#if defined(CONFIG_RA_HW_NAT) || defined(CONFIG_RA_HW_NAT_MODULE)
FOE_MAGIC_TAG(skb) = 0;
FOE_AI_UNHIT(skb);
#endif
#endif
return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev,
dst_output);
}
skb->dev = dst->dev;
ipv6_local_error(sk, EMSGSIZE, fl, mtu);
IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
/* Send RST reply */
static void send_reset(struct net *net, struct sk_buff *oldskb)
{
struct sk_buff *nskb;
struct tcphdr otcph, *tcph;
unsigned int otcplen, hh_len;
int tcphoff, needs_ack;
const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
struct ipv6hdr *ip6h;
#define DEFAULT_TOS_VALUE 0x0U
const __u8 tclass = DEFAULT_TOS_VALUE;
struct dst_entry *dst = NULL;
u8 proto;
__be16 frag_off;
struct flowi6 fl6;
if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
(!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
pr_debug("addr is not unicast.\n");
return;
}
proto = oip6h->nexthdr;
tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
pr_debug("Cannot get TCP header.\n");
return;
}
otcplen = oldskb->len - tcphoff;
/* IP header checks: fragment, too short. */
if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
pr_debug("proto(%d) != IPPROTO_TCP, "
"or too short. otcplen = %d\n",
proto, otcplen);
return;
}
if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
BUG();
/* No RST for RST. */
if (otcph.rst) {
pr_debug("RST is set\n");
return;
}
/* Check checksum. */
if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP,
skb_checksum(oldskb, tcphoff, otcplen, 0))) {
pr_debug("TCP checksum is invalid\n");
return;
}
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.saddr = oip6h->daddr;
fl6.daddr = oip6h->saddr;
fl6.fl6_sport = otcph.dest;
fl6.fl6_dport = otcph.source;
security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
dst = ip6_route_output(net, NULL, &fl6);
if (dst == NULL || dst->error) {
dst_release(dst);
return;
}
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst))
return;
hh_len = (dst->dev->hard_header_len + 15)&~15;
nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
+ sizeof(struct tcphdr) + dst->trailer_len,
GFP_ATOMIC);
if (!nskb) {
net_dbg_ratelimited("cannot alloc skb\n");
dst_release(dst);
return;
}
skb_dst_set(nskb, dst);
skb_reserve(nskb, hh_len + dst->header_len);
skb_put(nskb, sizeof(struct ipv6hdr));
skb_reset_network_header(nskb);
ip6h = ipv6_hdr(nskb);
ip6_flow_hdr(ip6h, tclass, 0);
ip6h->hop_limit = ip6_dst_hoplimit(dst);
ip6h->nexthdr = IPPROTO_TCP;
ip6h->saddr = oip6h->daddr;
ip6h->daddr = oip6h->saddr;
skb_reset_transport_header(nskb);
tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
/* Truncate to length (no data) */
tcph->doff = sizeof(struct tcphdr)/4;
tcph->source = otcph.dest;
tcph->dest = otcph.source;
if (otcph.ack) {
needs_ack = 0;
tcph->seq = otcph.ack_seq;
tcph->ack_seq = 0;
} else {
needs_ack = 1;
tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
+ otcplen - (otcph.doff<<2));
tcph->seq = 0;
}
/* Reset flags */
((u_int8_t *)tcph)[13] = 0;
tcph->rst = 1;
tcph->ack = needs_ack;
tcph->window = 0;
tcph->urg_ptr = 0;
tcph->check = 0;
/* Adjust TCP checksum */
tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
&ipv6_hdr(nskb)->daddr,
sizeof(struct tcphdr), IPPROTO_TCP,
csum_partial(tcph,
sizeof(struct tcphdr), 0));
nf_ct_attach(nskb, oldskb);
ip6_local_out(nskb);
}
static void tarpit_tcp6(struct net *net, struct sk_buff *oldskb,
unsigned int hook, unsigned int mode)
{
struct sk_buff *nskb;
struct tcphdr *tcph, oth;
unsigned int otcplen;
int tcphoff;
const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
struct ipv6hdr *ip6h;
const uint8_t tclass = 0;
uint8_t proto;
uint16_t payload;
__be16 frag_off;
proto = oip6h->nexthdr;
tcphoff = ipv6_skip_exthdr(oldskb,
(uint8_t *)(oip6h + 1) - oldskb->data, &proto, &frag_off);
if (tcphoff < 0 || tcphoff > oldskb->len) {
pr_debug("Cannot get TCP header.\n");
return;
}
otcplen = oldskb->len - tcphoff;
/* IP header checks: fragment, too short. */
if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
pr_debug("proto(%d) != IPPROTO_TCP, "
"or too short. otcplen = %d\n",
proto, otcplen);
return;
}
if (skb_copy_bits(oldskb, tcphoff, &oth, sizeof(struct tcphdr))) {
WARN_ON(1);
return;
}
/* Check checksum. */
if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP,
skb_checksum(oldskb, tcphoff, otcplen, 0))) {
pr_debug("TCP checksum is invalid\n");
return;
}
nskb = skb_copy_expand(oldskb, LL_MAX_HEADER,
skb_tailroom(oldskb), GFP_ATOMIC);
if (nskb == NULL) {
if (net_ratelimit())
pr_debug("cannot alloc skb\n");
return;
}
/* This packet will not be the same as the other: clear nf fields */
nf_reset(nskb);
skb_nfmark(nskb) = 0;
skb_init_secmark(nskb);
skb_shinfo(nskb)->gso_size = 0;
skb_shinfo(nskb)->gso_segs = 0;
skb_shinfo(nskb)->gso_type = 0;
skb_put(nskb, sizeof(struct ipv6hdr));
ip6h = ipv6_hdr(nskb);
*(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20));
ip6h->nexthdr = IPPROTO_TCP;
ip6h->saddr = oip6h->daddr;
ip6h->daddr = oip6h->saddr;
/* Adjust IP TTL */
if (mode == XTTARPIT_HONEYPOT) {
ip6h->hop_limit = 128;
} else {
ip6h->hop_limit = ip6_dst_hoplimit(skb_dst(nskb));
}
tcph = (struct tcphdr *)(skb_network_header(nskb) +
sizeof(struct ipv6hdr));
/* Truncate to length (no data) */
skb_trim(nskb, sizeof(struct ipv6hdr) + sizeof(struct tcphdr));
tcph->doff = sizeof(struct tcphdr)/4;
tcph->source = oth.dest;
tcph->dest = oth.source;
tcph->urg_ptr = 0;
/* Reset flags */
((uint8_t *)tcph)[13] = 0;
payload = nskb->len - sizeof(struct ipv6hdr) - sizeof(struct tcphdr);
if (!tarpit_generic(&oth, tcph, payload, mode))
goto free_nskb;
ip6h->payload_len = htons(sizeof(struct tcphdr));
tcph->check = 0;
/* Adjust TCP checksum */
tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
&ipv6_hdr(nskb)->daddr, sizeof(struct tcphdr),
IPPROTO_TCP,
csum_partial(tcph, sizeof(struct tcphdr), 0));
if (ip6_route_me_harder(net, nskb))
goto free_nskb;
nskb->ip_summed = CHECKSUM_NONE;
nf_ct_attach(nskb, oldskb);
NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, nskb->sk, nskb, NULL,
skb_dst(nskb)->dev, dst_output);
return;
free_nskb:
kfree_skb(nskb);
}
static unsigned int
echo_tg6(struct sk_buff *oldskb, const struct xt_action_param *par)
{
const struct udphdr *oldudp;
const struct ipv6hdr *oldip;
struct udphdr *newudp, oldudp_buf;
struct ipv6hdr *newip;
struct sk_buff *newskb;
unsigned int data_len;
void *payload;
struct flowi6 fl;
struct dst_entry *dst = NULL;
struct net *net = dev_net((par->in != NULL) ? par->in : par->out);
/* This allows us to do the copy operation in fewer lines of code. */
if (skb_linearize(oldskb) < 0)
return NF_DROP;
oldip = ipv6_hdr(oldskb);
oldudp = skb_header_pointer(oldskb, par->thoff,
sizeof(*oldudp), &oldudp_buf);
if (oldudp == NULL)
return NF_DROP;
if (ntohs(oldudp->len) <= sizeof(*oldudp))
return NF_DROP;
newskb = alloc_skb(LL_MAX_HEADER + sizeof(*newip) +
ntohs(oldudp->len), GFP_ATOMIC);
if (newskb == NULL)
return NF_DROP;
skb_reserve(newskb, LL_MAX_HEADER);
newskb->protocol = oldskb->protocol;
skb_reset_network_header(newskb);
newip = (void *)skb_put(newskb, sizeof(*newip));
newip->version = oldip->version;
newip->priority = oldip->priority;
memcpy(newip->flow_lbl, oldip->flow_lbl, sizeof(newip->flow_lbl));
newip->nexthdr = par->target->proto;
newip->saddr = oldip->daddr;
newip->daddr = oldip->saddr;
skb_reset_transport_header(newskb);
newudp = (void *)skb_put(newskb, sizeof(*newudp));
newudp->source = oldudp->dest;
newudp->dest = oldudp->source;
newudp->len = oldudp->len;
data_len = htons(oldudp->len) - sizeof(*oldudp);
payload = skb_header_pointer(oldskb, par->thoff +
sizeof(*oldudp), data_len, NULL);
memcpy(skb_put(newskb, data_len), payload, data_len);
#if 0
/*
* Since no fields are modified (we just swapped things around),
* this works too in our specific echo case.
*/
newudp->check = oldudp->check;
#else
newudp->check = 0;
newudp->check = csum_ipv6_magic(&newip->saddr, &newip->daddr,
ntohs(newudp->len), IPPROTO_UDP,
csum_partial(newudp, ntohs(newudp->len), 0));
#endif
memset(&fl, 0, sizeof(fl));
fl.flowi6_proto = newip->nexthdr;
memcpy(&fl.saddr, &newip->saddr, sizeof(fl.saddr));
memcpy(&fl.daddr, &newip->daddr, sizeof(fl.daddr));
fl.fl6_sport = newudp->source;
fl.fl6_dport = newudp->dest;
security_skb_classify_flow((struct sk_buff *)oldskb, flowi6_to_flowi(&fl));
dst = ip6_route_output(net, NULL, &fl);
if (dst == NULL || dst->error != 0) {
dst_release(dst);
goto free_nskb;
}
skb_dst_set(newskb, dst);
newip->hop_limit = ip6_dst_hoplimit(skb_dst(newskb));
newskb->ip_summed = CHECKSUM_NONE;
/* "Never happens" (?) */
if (newskb->len > dst_mtu(skb_dst(newskb)))
goto free_nskb;
nf_ct_attach(newskb, oldskb);
ip6_local_out(newskb);
return NF_DROP;
free_nskb:
kfree_skb(newskb);
return NF_DROP;
}
void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
struct tcphdr _otcph;
const struct tcphdr *otcph;
unsigned int otcplen, hh_len;
const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
struct ipv6hdr *ip6h;
struct dst_entry *dst = NULL;
struct flowi6 fl6;
if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
(!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
pr_debug("addr is not unicast.\n");
return;
}
otcph = nf_reject_ip6_tcphdr_get(oldskb, &_otcph, &otcplen, hook);
if (!otcph)
return;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.saddr = oip6h->daddr;
fl6.daddr = oip6h->saddr;
fl6.fl6_sport = otcph->dest;
fl6.fl6_dport = otcph->source;
security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
dst = ip6_route_output(net, NULL, &fl6);
if (dst == NULL || dst->error) {
dst_release(dst);
return;
}
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst))
return;
hh_len = (dst->dev->hard_header_len + 15)&~15;
nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
+ sizeof(struct tcphdr) + dst->trailer_len,
GFP_ATOMIC);
if (!nskb) {
net_dbg_ratelimited("cannot alloc skb\n");
dst_release(dst);
return;
}
skb_dst_set(nskb, dst);
skb_reserve(nskb, hh_len + dst->header_len);
ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
ip6_dst_hoplimit(dst));
nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen);
nf_ct_attach(nskb, oldskb);
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
/* If we use ip6_local_out for bridged traffic, the MAC source on
* the RST will be ours, instead of the destination's. This confuses
* some routers/firewalls, and they drop the packet. So we need to
* build the eth header using the original destination's MAC as the
* source, and send the RST packet directly.
*/
if (oldskb->nf_bridge) {
struct ethhdr *oeth = eth_hdr(oldskb);
nskb->dev = nf_bridge_get_physindev(oldskb);
nskb->protocol = htons(ETH_P_IPV6);
ip6h->payload_len = htons(sizeof(struct tcphdr));
if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
oeth->h_source, oeth->h_dest, nskb->len) < 0)
return;
dev_queue_xmit(nskb);
} else
#endif
ip6_local_out(net, nskb->sk, nskb);
}
