int udp_gro_complete(struct sk_buff *skb, int nhoff,
udp_lookup_t lookup)
{
__be16 newlen = htons(skb->len - nhoff);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
int err = -ENOSYS;
struct sock *sk;
uh->len = newlen;
rcu_read_lock();
sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
udp4_lib_lookup_skb, skb, uh->source, uh->dest);
if (sk && udp_sk(sk)->gro_enabled) {
err = udp_gro_complete_segment(skb);
} else if (sk && udp_sk(sk)->gro_complete) {
skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM
: SKB_GSO_UDP_TUNNEL;
/* Set encapsulation before calling into inner gro_complete()
* functions to make them set up the inner offsets.
*/
skb->encapsulation = 1;
err = udp_sk(sk)->gro_complete(sk, skb,
nhoff + sizeof(struct udphdr));
}
rcu_read_unlock();
if (skb->remcsum_offload)
skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM;
return err;
}
struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
struct udphdr *uh, udp_lookup_t lookup)
{
struct sk_buff *pp = NULL;
struct sk_buff *p;
struct udphdr *uh2;
unsigned int off = skb_gro_offset(skb);
int flush = 1;
struct sock *sk;
rcu_read_lock();
sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
udp4_lib_lookup_skb, skb, uh->source, uh->dest);
if (!sk)
goto out_unlock;
if (udp_sk(sk)->gro_enabled) {
pp = call_gro_receive(udp_gro_receive_segment, head, skb);
rcu_read_unlock();
return pp;
}
if (NAPI_GRO_CB(skb)->encap_mark ||
(skb->ip_summed != CHECKSUM_PARTIAL &&
NAPI_GRO_CB(skb)->csum_cnt == 0 &&
!NAPI_GRO_CB(skb)->csum_valid) ||
!udp_sk(sk)->gro_receive)
goto out_unlock;
/* mark that this skb passed once through the tunnel gro layer */
NAPI_GRO_CB(skb)->encap_mark = 1;
flush = 0;
list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
uh2 = (struct udphdr *)(p->data + off);
/* Match ports and either checksums are either both zero
* or nonzero.
*/
if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) ||
(!uh->check ^ !uh2->check)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
out_unlock:
rcu_read_unlock();
skb_gro_flush_final(skb, pp, flush);
return pp;
}
static int sc_socket_create(int type, union capwap_addr* sockaddr, uint16_t protocol) {
int ret;
TRACEKMOD("### sc_socket_create\n");
/* Create socket */
ret = sock_create_kern(sockaddr->ss.ss_family, SOCK_DGRAM, protocol, &sc_sockets[type]);
if (ret) {
return ret;
}
/* Bind to interface */
ret = kernel_bind(sc_sockets[type], &sockaddr->sa, sizeof(union capwap_addr));
if (ret) {
goto failure;
}
/* Set callback */
udp_sk(sc_sockets[type]->sk)->encap_type = 1;
udp_sk(sc_sockets[type]->sk)->encap_rcv = sc_socket_recvpacket;
/* */
if (!((sockaddr->ss.ss_family == AF_INET) ? sockaddr->sin.sin_port : sockaddr->sin6.sin6_port)) {
union capwap_addr localaddr;
int localaddrsize = sizeof(union capwap_addr);
/* Retrieve port */
ret = kernel_getsockname(sc_sockets[type], &localaddr.sa, &localaddrsize);
if (ret) {
goto failure;
}
/* */
if ((sockaddr->ss.ss_family == AF_INET) && (localaddr.ss.ss_family == AF_INET)) {
sockaddr->sin.sin_port = localaddr.sin.sin_port;
} else if ((sockaddr->ss.ss_family == AF_INET6) && (localaddr.ss.ss_family == AF_INET6)) {
sockaddr->sin6.sin6_port = localaddr.sin6.sin6_port;
} else {
ret = -EFAULT;
goto failure;
}
}
return 0;
failure:
sock_release(sc_sockets[type]);
sc_sockets[type] = 0;
return ret;
}
void rpl_setup_udp_tunnel_sock(struct net *net, struct socket *sock,
struct udp_tunnel_sock_cfg *cfg)
{
struct sock *sk = sock->sk;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
rcu_assign_sk_user_data(sk, cfg->sk_user_data);
udp_sk(sk)->encap_type = cfg->encap_type;
udp_sk(sk)->encap_rcv = cfg->encap_rcv;
#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,9,0)
udp_sk(sk)->encap_destroy = cfg->encap_destroy;
#endif
udp_tunnel_encap_enable(sock);
}
void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
struct udp_tunnel_sock_cfg *cfg)
{
struct sock *sk = sock->sk;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
udp_set_convert_csum(sk, true);
rcu_assign_sk_user_data(sk, cfg->sk_user_data);
udp_sk(sk)->encap_type = cfg->encap_type;
udp_sk(sk)->encap_rcv = cfg->encap_rcv;
udp_sk(sk)->encap_destroy = cfg->encap_destroy;
udp_tunnel_encap_enable(sock);
}
/*
* Throw away all pending data and cancel the corking. Socket is locked.
*/
static void udp_flush_pending_frames(struct sock *sk)
{
struct udp_opt *up = udp_sk(sk);
if (up->pending) {
up->len = 0;
up->pending = 0;
ip_flush_pending_frames(sk);
}
}
static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
int val, valbool;
int retv = -ENOPROTOOPT;
if (optval == NULL)
val=0;
else {
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else
val = 0;
}
valbool = (val!=0);
if (ip6_mroute_opt(optname))
return ip6_mroute_setsockopt(sk, optname, optval, optlen);
lock_sock(sk);
switch (optname) {
case IPV6_ADDRFORM:
if (optlen < sizeof(int))
goto e_inval;
if (val == PF_INET) {
struct ipv6_txoptions *opt;
struct sk_buff *pktopt;
if (sk->sk_type == SOCK_RAW)
break;
if (sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_UDPLITE) {
struct udp_sock *up = udp_sk(sk);
if (up->pending == AF_INET6) {
retv = -EBUSY;
break;
}
} else if (sk->sk_protocol != IPPROTO_TCP)
break;
if (sk->sk_state != TCP_ESTABLISHED) {
retv = -ENOTCONN;
break;
}
if (ipv6_only_sock(sk) ||
!ipv6_addr_v4mapped(&np->daddr)) {
retv = -EADDRNOTAVAIL;
break;
}
fl6_free_socklist(sk);
ipv6_sock_mc_close(sk);
/*
* Sock is moving from IPv6 to IPv4 (sk_prot), so
* remove it from the refcnt debug socks count in the
* original family...
*/
sk_refcnt_debug_dec(sk);
if (sk->sk_protocol == IPPROTO_TCP) {
struct inet_connection_sock *icsk = inet_csk(sk);
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, &tcp_prot, 1);
local_bh_enable();
sk->sk_prot = &tcp_prot;
icsk->icsk_af_ops = &ipv4_specific;
sk->sk_socket->ops = &inet_stream_ops;
sk->sk_family = PF_INET;
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
} else {
struct proto *prot = &udp_prot;
if (sk->sk_protocol == IPPROTO_UDPLITE)
prot = &udplite_prot;
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, prot, 1);
local_bh_enable();
sk->sk_prot = prot;
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
opt = xchg(&np->opt, NULL);
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
pktopt = xchg(&np->pktoptions, NULL);
kfree_skb(pktopt);
sk->sk_destruct = inet_sock_destruct;
/*
* ... and add it to the refcnt debug socks count
* in the new family. -acme
*/
sk_refcnt_debug_inc(sk);
module_put(THIS_MODULE);
retv = 0;
break;
}
goto e_inval;
case IPV6_V6ONLY:
if (optlen < sizeof(int) ||
inet_sk(sk)->inet_num)
goto e_inval;
np->ipv6only = valbool;
retv = 0;
break;
case IPV6_RECVPKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxinfo = valbool;
retv = 0;
break;
case IPV6_2292PKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxoinfo = valbool;
retv = 0;
break;
case IPV6_RECVHOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxhlim = valbool;
retv = 0;
break;
case IPV6_2292HOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxohlim = valbool;
retv = 0;
break;
case IPV6_RECVRTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.srcrt = valbool;
retv = 0;
break;
case IPV6_2292RTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.osrcrt = valbool;
retv = 0;
break;
case IPV6_RECVHOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.hopopts = valbool;
retv = 0;
break;
case IPV6_2292HOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.ohopopts = valbool;
retv = 0;
break;
case IPV6_RECVDSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.dstopts = valbool;
retv = 0;
break;
case IPV6_2292DSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.odstopts = valbool;
retv = 0;
break;
case IPV6_TCLASS:
if (optlen < sizeof(int))
goto e_inval;
if (val < -1 || val > 0xff)
goto e_inval;
/* RFC 3542, 6.5: default traffic class of 0x0 */
if (val == -1)
val = 0;
np->tclass = val;
retv = 0;
break;
case IPV6_RECVTCLASS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxtclass = valbool;
retv = 0;
break;
case IPV6_FLOWINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxflow = valbool;
retv = 0;
break;
case IPV6_RECVPATHMTU:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxpmtu = valbool;
retv = 0;
break;
case IPV6_TRANSPARENT:
if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) &&
!ns_capable(net->user_ns, CAP_NET_RAW)) {
retv = -EPERM;
break;
}
if (optlen < sizeof(int))
goto e_inval;
/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
inet_sk(sk)->transparent = valbool;
retv = 0;
break;
case IPV6_RECVORIGDSTADDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxorigdstaddr = valbool;
retv = 0;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
struct ipv6_txoptions *opt;
/* remove any sticky options header with a zero option
* length, per RFC3542.
*/
if (optlen == 0)
optval = NULL;
else if (optval == NULL)
goto e_inval;
else if (optlen < sizeof(struct ipv6_opt_hdr) ||
optlen & 0x7 || optlen > 8 * 255)
goto e_inval;
/* hop-by-hop / destination options are privileged option */
retv = -EPERM;
if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
break;
opt = ipv6_renew_options(sk, np->opt, optname,
(struct ipv6_opt_hdr __user *)optval,
optlen);
if (IS_ERR(opt)) {
retv = PTR_ERR(opt);
break;
}
/* routing header option needs extra check */
retv = -EINVAL;
if (optname == IPV6_RTHDR && opt && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = opt->srcrt;
switch (rthdr->type) {
#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1)
goto sticky_done;
break;
#endif
default:
goto sticky_done;
}
}
retv = 0;
opt = ipv6_update_options(sk, opt);
sticky_done:
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
break;
}
case IPV6_PKTINFO:
{
struct in6_pktinfo pkt;
if (optlen == 0)
goto e_inval;
else if (optlen < sizeof(struct in6_pktinfo) || optval == NULL)
goto e_inval;
if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) {
retv = -EFAULT;
break;
}
if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr;
retv = 0;
break;
}
case IPV6_2292PKTOPTIONS:
{
struct ipv6_txoptions *opt = NULL;
struct msghdr msg;
struct flowi6 fl6;
int junk;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
if (optlen == 0)
goto update;
/* 1K is probably excessive
* 1K is surely not enough, 2K per standard header is 16K.
*/
retv = -EINVAL;
if (optlen > 64*1024)
break;
opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
retv = -ENOBUFS;
if (opt == NULL)
break;
memset(opt, 0, sizeof(*opt));
opt->tot_len = sizeof(*opt) + optlen;
retv = -EFAULT;
if (copy_from_user(opt+1, optval, optlen))
goto done;
msg.msg_controllen = optlen;
msg.msg_control = (void*)(opt+1);
retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk,
&junk, &junk);
if (retv)
goto done;
update:
retv = 0;
opt = ipv6_update_options(sk, opt);
done:
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
break;
}
case IPV6_UNICAST_HOPS:
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->hop_limit = val;
retv = 0;
break;
case IPV6_MULTICAST_HOPS:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
retv = 0;
break;
case IPV6_MULTICAST_LOOP:
if (optlen < sizeof(int))
goto e_inval;
if (val != valbool)
goto e_inval;
np->mc_loop = valbool;
retv = 0;
break;
case IPV6_UNICAST_IF:
{
struct net_device *dev = NULL;
int ifindex;
if (optlen != sizeof(int))
goto e_inval;
ifindex = (__force int)ntohl((__force __be32)val);
if (ifindex == 0) {
np->ucast_oif = 0;
retv = 0;
break;
}
dev = dev_get_by_index(net, ifindex);
retv = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
retv = -EINVAL;
if (sk->sk_bound_dev_if)
break;
np->ucast_oif = ifindex;
retv = 0;
break;
}
case IPV6_MULTICAST_IF:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val) {
struct net_device *dev;
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
goto e_inval;
dev = dev_get_by_index(net, val);
if (!dev) {
retv = -ENODEV;
break;
}
dev_put(dev);
}
np->mcast_oif = val;
retv = 0;
break;
case IPV6_ADD_MEMBERSHIP:
case IPV6_DROP_MEMBERSHIP:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_ADD_MEMBERSHIP)
retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
else
retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
break;
}
case IPV6_JOIN_ANYCAST:
case IPV6_LEAVE_ANYCAST:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_JOIN_ANYCAST)
retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
else
retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in6 *psin6;
if (optlen < sizeof(struct group_req))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(struct group_req)))
break;
if (greq.gr_group.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
psin6 = (struct sockaddr_in6 *)&greq.gr_group;
if (optname == MCAST_JOIN_GROUP)
retv = ipv6_sock_mc_join(sk, greq.gr_interface,
&psin6->sin6_addr);
else
retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
&psin6->sin6_addr);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
int omode, add;
if (optlen < sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
retv = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET6 ||
greqs.gsr_source.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct sockaddr_in6 *psin6;
psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
&psin6->sin6_addr);
/* prior join w/ different source is ok */
if (retv && retv != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
retv = ip6_mc_source(add, omode, sk, &greqs);
break;
}
case MCAST_MSFILTER:
{
struct group_filter *gsf;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
retv = -ENOBUFS;
break;
}
gsf = kmalloc(optlen,GFP_KERNEL);
if (!gsf) {
retv = -ENOBUFS;
break;
}
retv = -EFAULT;
if (copy_from_user(gsf, optval, optlen)) {
kfree(gsf);
break;
}
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffffU ||
gsf->gf_numsrc > sysctl_mld_max_msf) {
kfree(gsf);
retv = -ENOBUFS;
break;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
kfree(gsf);
retv = -EINVAL;
break;
}
retv = ip6_mc_msfilter(sk, gsf);
kfree(gsf);
break;
}
case IPV6_ROUTER_ALERT:
if (optlen < sizeof(int))
goto e_inval;
retv = ip6_ra_control(sk, val);
break;
case IPV6_MTU_DISCOVER:
if (optlen < sizeof(int))
goto e_inval;
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
goto e_inval;
np->pmtudisc = val;
retv = 0;
break;
case IPV6_MTU:
if (optlen < sizeof(int))
goto e_inval;
if (val && val < IPV6_MIN_MTU)
goto e_inval;
np->frag_size = val;
retv = 0;
break;
case IPV6_RECVERR:
if (optlen < sizeof(int))
goto e_inval;
np->recverr = valbool;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
retv = 0;
break;
case IPV6_FLOWINFO_SEND:
if (optlen < sizeof(int))
goto e_inval;
np->sndflow = valbool;
retv = 0;
break;
case IPV6_FLOWLABEL_MGR:
retv = ipv6_flowlabel_opt(sk, optval, optlen);
break;
case IPV6_IPSEC_POLICY:
case IPV6_XFRM_POLICY:
retv = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
retv = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IPV6_ADDR_PREFERENCES:
{
unsigned int pref = 0;
unsigned int prefmask = ~0;
if (optlen < sizeof(int))
goto e_inval;
retv = -EINVAL;
/* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */
switch (val & (IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP|
IPV6_PREFER_SRC_PUBTMP_DEFAULT)) {
case IPV6_PREFER_SRC_PUBLIC:
pref |= IPV6_PREFER_SRC_PUBLIC;
break;
case IPV6_PREFER_SRC_TMP:
pref |= IPV6_PREFER_SRC_TMP;
break;
case IPV6_PREFER_SRC_PUBTMP_DEFAULT:
break;
case 0:
goto pref_skip_pubtmp;
default:
goto e_inval;
}
prefmask &= ~(IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP);
pref_skip_pubtmp:
/* check HOME/COA conflicts */
switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) {
case IPV6_PREFER_SRC_HOME:
break;
case IPV6_PREFER_SRC_COA:
pref |= IPV6_PREFER_SRC_COA;
case 0:
goto pref_skip_coa;
default:
goto e_inval;
}
prefmask &= ~IPV6_PREFER_SRC_COA;
pref_skip_coa:
/* check CGA/NONCGA conflicts */
switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) {
case IPV6_PREFER_SRC_CGA:
case IPV6_PREFER_SRC_NONCGA:
case 0:
break;
default:
goto e_inval;
}
np->srcprefs = (np->srcprefs & prefmask) | pref;
retv = 0;
break;
}
case IPV6_MINHOPCOUNT:
if (optlen < sizeof(int))
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
np->min_hopcount = val;
retv = 0;
break;
case IPV6_DONTFRAG:
np->dontfrag = valbool;
retv = 0;
break;
}
release_sock(sk);
return retv;
e_inval:
release_sock(sk);
return -EINVAL;
}
int rst_socket_in(struct cpt_sock_image *si, loff_t pos, struct sock *sk,
struct cpt_context *ctx)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = get_exec_env()->ve_ns->net_ns;
int err, ret_err = 0;
lock_sock(sk);
sk->sk_state = si->cpt_state;
inet->daddr = si->cpt_daddr;
inet->dport = si->cpt_dport;
inet->saddr = si->cpt_saddr;
inet->rcv_saddr = si->cpt_rcv_saddr;
inet->sport = si->cpt_sport;
inet->uc_ttl = si->cpt_uc_ttl;
inet->tos = si->cpt_tos;
inet->cmsg_flags = si->cpt_cmsg_flags;
inet->mc_index = si->cpt_mc_index;
inet->mc_addr = si->cpt_mc_addr;
inet->hdrincl = si->cpt_hdrincl;
inet->mc_ttl = si->cpt_mc_ttl;
inet->mc_loop = si->cpt_mc_loop;
inet->pmtudisc = si->cpt_pmtudisc;
inet->recverr = si->cpt_recverr;
inet->freebind = si->cpt_freebind;
inet->id = si->cpt_idcounter;
inet->cork.flags = si->cpt_cork_flags;
inet->cork.fragsize = si->cpt_cork_fragsize;
inet->cork.length = si->cpt_cork_length;
inet->cork.addr = si->cpt_cork_addr;
inet->cork.fl.fl4_src = si->cpt_cork_saddr;
inet->cork.fl.fl4_dst = si->cpt_cork_daddr;
inet->cork.fl.oif = si->cpt_cork_oif;
if (inet->cork.fragsize) {
if (ip_route_output_key(net, (struct rtable **)&inet->cork.dst, &inet->cork.fl)) {
eprintk_ctx("failed to restore cork route\n");
inet->cork.fragsize = 0;
}
}
if (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP) {
struct udp_sock *up = udp_sk(sk);
up->pending = si->cpt_udp_pending;
up->corkflag = si->cpt_udp_corkflag;
up->encap_type = si->cpt_udp_encap;
up->len = si->cpt_udp_len;
}
if (sk->sk_family == AF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
memcpy(&np->saddr, si->cpt_saddr6, 16);
memcpy(&np->rcv_saddr, si->cpt_rcv_saddr6, 16);
memcpy(&np->daddr, si->cpt_daddr6, 16);
np->flow_label = si->cpt_flow_label6;
np->frag_size = si->cpt_frag_size6;
np->hop_limit = si->cpt_hop_limit6;
np->mcast_hops = si->cpt_mcast_hops6;
np->mcast_oif = si->cpt_mcast_oif6;
np->rxopt.all = si->cpt_rxopt6;
np->mc_loop = si->cpt_mc_loop6;
np->recverr = si->cpt_recverr6;
np->sndflow = si->cpt_sndflow6;
np->pmtudisc = si->cpt_pmtudisc6;
np->ipv6only = si->cpt_ipv6only6;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
if (si->cpt_mapped) {
extern struct inet_connection_sock_af_ops ipv6_mapped;
if (sk->sk_type == SOCK_STREAM &&
sk->sk_protocol == IPPROTO_TCP) {
inet_csk(sk)->icsk_af_ops = &ipv6_mapped;
sk->sk_backlog_rcv = tcp_v4_do_rcv;
}
}
#endif
}
err = restore_queues(sk, si, pos, ctx);
if (sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP) {
ret_err = err;
rst_socket_tcp(si, pos, sk, ctx);
}
release_sock(sk);
return ret_err;
}
int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
struct udphdr *uh;
struct iphdr *iph;
int iphlen, len;
__u8 *udpdata;
__be32 *udpdata32;
__u16 encap_type = up->encap_type;
/* if this is not encapsulated socket, then just return now */
if (!encap_type)
return 1;
/* If this is a paged skb, make sure we pull up
* whatever data we need to look at. */
len = skb->len - sizeof(struct udphdr);
if (!pskb_may_pull(skb, sizeof(struct udphdr) + min(len, 8)))
return 1;
/* Now we can get the pointers */
uh = udp_hdr(skb);
udpdata = (__u8 *)uh + sizeof(struct udphdr);
udpdata32 = (__be32 *)udpdata;
switch (encap_type) {
default:
case UDP_ENCAP_ESPINUDP:
/* Check if this is a keepalive packet. If so, eat it. */
if (len == 1 && udpdata[0] == 0xff) {
goto drop;
} else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0) {
/* ESP Packet without Non-ESP header */
len = sizeof(struct udphdr);
} else
/* Must be an IKE packet.. pass it through */
return 1;
break;
case UDP_ENCAP_ESPINUDP_NON_IKE:
/* Check if this is a keepalive packet. If so, eat it. */
if (len == 1 && udpdata[0] == 0xff) {
goto drop;
} else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) &&
udpdata32[0] == 0 && udpdata32[1] == 0) {
/* ESP Packet with Non-IKE marker */
len = sizeof(struct udphdr) + 2 * sizeof(u32);
} else
/* Must be an IKE packet.. pass it through */
return 1;
break;
}
/* At this point we are sure that this is an ESPinUDP packet,
* so we need to remove 'len' bytes from the packet (the UDP
* header and optional ESP marker bytes) and then modify the
* protocol to ESP, and then call into the transform receiver.
*/
if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
goto drop;
/* Now we can update and verify the packet length... */
iph = ip_hdr(skb);
iphlen = iph->ihl << 2;
iph->tot_len = htons(ntohs(iph->tot_len) - len);
if (skb->len < iphlen + len) {
/* packet is too small!?! */
goto drop;
}
/* pull the data buffer up to the ESP header and set the
* transport header to point to ESP. Keep UDP on the stack
* for later.
*/
__skb_pull(skb, len);
skb_reset_transport_header(skb);
/* process ESP */
return xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, encap_type);
drop:
kfree_skb(skb);
return 0;
}
static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data)
{
struct vxlan_sock *vs;
struct sock *sk;
struct sockaddr_in vxlan_addr = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = port,
};
int rc;
vs = kmalloc(sizeof(*vs), GFP_KERNEL);
if (!vs) {
pr_debug("memory alocation failure\n");
return ERR_PTR(-ENOMEM);
}
INIT_WORK(&vs->del_work, vxlan_del_work);
/* Create UDP socket for encapsulation receive. */
rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &vs->sock);
if (rc < 0) {
pr_debug("UDP socket create failed\n");
kfree(vs);
return ERR_PTR(rc);
}
/* Put in proper namespace */
sk = vs->sock->sk;
sk_change_net(sk, net);
rc = kernel_bind(vs->sock, (struct sockaddr *) &vxlan_addr,
sizeof(vxlan_addr));
if (rc < 0) {
pr_debug("bind for UDP socket %pI4:%u (%d)\n",
&vxlan_addr.sin_addr, ntohs(vxlan_addr.sin_port), rc);
sk_release_kernel(sk);
kfree(vs);
return ERR_PTR(rc);
}
vs->rcv = rcv;
vs->data = data;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
rcu_assign_sk_user_data(vs->sock->sk, vs);
/* Mark socket as an encapsulation socket. */
udp_sk(sk)->encap_type = 1;
udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv;
udp_encap_enable();
return vs;
}
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data,
bool no_share, u32 flags)
{
return vxlan_socket_create(net, port, rcv, data);
}
void vxlan_sock_release(struct vxlan_sock *vs)
{
ASSERT_OVSL();
rcu_assign_sk_user_data(vs->sock->sk, NULL);
queue_work(system_wq, &vs->del_work);
}
int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
struct udphdr *uh;
struct iphdr *iph;
int iphlen, len;
__u8 *udpdata;
__be32 *udpdata32;
__u16 encap_type = up->encap_type;
if (!encap_type)
return 1;
len = skb->len - sizeof(struct udphdr);
if (!pskb_may_pull(skb, sizeof(struct udphdr) + min(len, 8)))
return 1;
uh = udp_hdr(skb);
udpdata = (__u8 *)uh + sizeof(struct udphdr);
udpdata32 = (__be32 *)udpdata;
switch (encap_type) {
default:
case UDP_ENCAP_ESPINUDP:
if (len == 1 && udpdata[0] == 0xff) {
goto drop;
} else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0) {
len = sizeof(struct udphdr);
} else
return 1;
break;
case UDP_ENCAP_ESPINUDP_NON_IKE:
if (len == 1 && udpdata[0] == 0xff) {
goto drop;
} else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) &&
udpdata32[0] == 0 && udpdata32[1] == 0) {
len = sizeof(struct udphdr) + 2 * sizeof(u32);
} else
return 1;
break;
}
if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
goto drop;
iph = ip_hdr(skb);
iphlen = iph->ihl << 2;
iph->tot_len = htons(ntohs(iph->tot_len) - len);
if (skb->len < iphlen + len) {
goto drop;
}
__skb_pull(skb, len);
skb_reset_transport_header(skb);
return xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, encap_type);
drop:
kfree_skb(skb);
return 0;
}
int ax8netfilter_udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
int rc;
int is_udplite = IS_UDPLITE(sk);
/*
* Charge it to the socket, dropping if the queue is full.
*/
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
goto drop;
nf_reset(skb);
if (up->encap_type) {
/*
* This is an encapsulation socket so pass the skb to
* the socket's udp_encap_rcv() hook. Otherwise, just
* fall through and pass this up the UDP socket.
* up->encap_rcv() returns the following value:
* =0 if skb was successfully passed to the encap
* handler or was discarded by it.
* >0 if skb should be passed on to UDP.
* <0 if skb should be resubmitted as proto -N
*/
/* if we're overly short, let UDP handle it */
if (skb->len > sizeof(struct udphdr) &&
up->encap_rcv != NULL) {
int ret;
ret = (*up->encap_rcv)(sk, skb);
if (ret <= 0) {
UDP_INC_STATS_BH(sock_net(sk),
UDP_MIB_INDATAGRAMS,
is_udplite);
return -ret;
}
}
/* FALLTHROUGH -- it's a UDP Packet */
}
/*
* UDP-Lite specific tests, ignored on UDP sockets
*/
if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
/*
* MIB statistics other than incrementing the error count are
* disabled for the following two types of errors: these depend
* on the application settings, not on the functioning of the
* protocol stack as such.
*
* RFC 3828 here recommends (sec 3.3): "There should also be a
* way ... to ... at least let the receiving application block
* delivery of packets with coverage values less than a value
* provided by the application."
*/
if (up->pcrlen == 0) { /* full coverage was set */
LIMIT_NETDEBUG(KERN_WARNING "UDPLITE: partial coverage "
"%d while full coverage %d requested\n",
UDP_SKB_CB(skb)->cscov, skb->len);
goto drop;
}
/* The next case involves violating the min. coverage requested
* by the receiver. This is subtle: if receiver wants x and x is
* greater than the buffersize/MTU then receiver will complain
* that it wants x while sender emits packets of smaller size y.
* Therefore the above ...()->partial_cov statement is essential.
*/
if (UDP_SKB_CB(skb)->cscov < up->pcrlen) {
LIMIT_NETDEBUG(KERN_WARNING
"UDPLITE: coverage %d too small, need min %d\n",
UDP_SKB_CB(skb)->cscov, up->pcrlen);
goto drop;
}
}
if (sk->sk_filter) {
if (udp_lib_checksum_complete(skb))
goto drop;
}
rc = 0;
bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
rc = ax8netfilter___udp_queue_rcv_skb(sk, skb);
else
sk_add_backlog(sk, skb);
bh_unlock_sock(sk);
return rc;
drop:
UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb(skb);
return -1;
}
