Gitiles
Code Review Sign In
LeafOS / LeafOS-Devices / android_kernel_samsung_exynos9820 / 9850488201f0b0bcbded1eca53750d2fd6accfbb / . / net / ipv6 / tcp_ipv6.c
blob: 7a47f9cd9f5b7234515e5c3a37a09943f12c2efa [file] [log] [blame]
/*
* TCP over IPv6
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
* Based on:
* linux/net/ipv4/tcp.c
* linux/net/ipv4/tcp_input.c
* linux/net/ipv4/tcp_output.c
*
* Fixes:
* Hideaki YOSHIFUJI : sin6_scope_id support
* YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which
* Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind
* a single port at the same time.
* YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/bottom_half.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/jiffies.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/init.h>
#include <linux/jhash.h>
#include <linux/ipsec.h>
#include <linux/times.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <net/tcp.h>
#include <net/ndisc.h>
#include <net/inet6_hashtables.h>
#include <net/inet6_connection_sock.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/ip6_checksum.h>
#include <net/inet_ecn.h>
#include <net/protocol.h>
#include <net/xfrm.h>
#include <net/snmp.h>
#include <net/dsfield.h>
#include <net/timewait_sock.h>
#include <net/inet_common.h>
#include <net/secure_seq.h>
#ifdef CONFIG_MPTCP
#include <net/mptcp.h>
#include <net/mptcp_v6.h>
#endif
#include <net/busy_poll.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <crypto/hash.h>
#include <linux/scatterlist.h>
#ifndef CONFIG_MPTCP
static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb);
static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
static const struct inet_connection_sock_af_ops ipv6_mapped;
static const struct inet_connection_sock_af_ops ipv6_specific;
#endif
#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_sock_af_ops tcp_sock_ipv6_specific;
static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
#else
static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk,
const struct in6_addr *addr)
{
return NULL;
}
#endif
#ifndef CONFIG_MPTCP
static
#endif
void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
if (dst && dst_hold_safe(dst)) {
const struct rt6_info *rt = (const struct rt6_info *)dst;
rcu_assign_pointer(sk->sk_rx_dst, dst);
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
}
}
static u32 tcp_v6_init_seq(const struct sk_buff *skb)
{
return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32,
ipv6_hdr(skb)->saddr.s6_addr32,
tcp_hdr(skb)->dest,
tcp_hdr(skb)->source);
}
static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb)
{
return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32,
ipv6_hdr(skb)->saddr.s6_addr32);
}
static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
/* This check is replicated from tcp_v6_connect() and intended to
* prevent BPF program called below from accessing bytes that are out
* of the bound specified by user in addr_len.
*/
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
sock_owned_by_me(sk);
return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr);
}
#ifndef CONFIG_MPTCP
static
#endif
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
int err;
struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl6, 0, sizeof(fl6));
if (np->sndflow) {
fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl6.flowlabel);
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (!flowlabel)
return -EINVAL;
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if (ipv6_addr_any(&usin->sin6_addr)) {
if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
&usin->sin6_addr);
else
usin->sin6_addr = in6addr_loopback;
}
addr_type = ipv6_addr_type(&usin->sin6_addr);
if (addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type&IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
if (tp->rx_opt.ts_recent_stamp &&
!ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
tp->write_seq = 0;
}
sk->sk_v6_daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
/*
* TCP over IPv4
*/
if (addr_type & IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
#ifdef CONFIG_MPTCP
if (sock_flag(sk, SOCK_MPTCP))
icsk->icsk_af_ops = &mptcp_v6_mapped;
else
#endif
icsk->icsk_af_ops = &ipv6_mapped;
sk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif
err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
#ifdef CONFIG_MPTCP
if (sock_flag(sk, SOCK_MPTCP))
icsk->icsk_af_ops = &mptcp_v6_specific;
else
#endif
icsk->icsk_af_ops = &ipv6_specific;
sk->sk_backlog_rcv = tcp_v6_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_specific;
#endif
goto failure;
}
np->saddr = sk->sk_v6_rcv_saddr;
return err;
}
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
saddr = &sk->sk_v6_rcv_saddr;
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = sk->sk_v6_daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
fl6.flowi6_uid = sk->sk_uid;
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
}
if (!saddr) {
saddr = &fl6.saddr;
sk->sk_v6_rcv_saddr = *saddr;
}
/* set the source address */
np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
sk->sk_gso_type = SKB_GSO_TCPV6;
ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (opt)
icsk->icsk_ext_hdr_len = opt->opt_flen +
opt->opt_nflen;
tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
inet->inet_dport = usin->sin6_port;
tcp_set_state(sk, TCP_SYN_SENT);
err = inet6_hash_connect(tcp_death_row, sk);
if (err)
goto late_failure;
sk_set_txhash(sk);
if (likely(!tp->repair)) {
if (!tp->write_seq)
tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32,
inet->inet_sport,
inet->inet_dport);
tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk),
np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32);
}
if (tcp_fastopen_defer_connect(sk, &err))
return err;
if (err)
goto late_failure;
err = tcp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
tcp_set_state(sk, TCP_CLOSE);
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
inet_reset_saddr(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
return err;
}
#ifndef CONFIG_MPTCP
static
#endif
void tcp_v6_mtu_reduced(struct sock *sk)
{
struct dst_entry *dst;
u32 mtu;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
return;
mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
/* Drop requests trying to increase our current mss.
* Check done in __ip6_rt_update_pmtu() is too late.
*/
if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache)
return;
dst = inet6_csk_update_pmtu(sk, mtu);
if (!dst)
return;
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
}
}
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
struct net *net = dev_net(skb->dev);
struct request_sock *fastopen;
struct ipv6_pinfo *np;
struct tcp_sock *tp;
__u32 seq, snd_una;
struct sock *sk;
#ifdef CONFIG_MPTCP
struct sock *meta_sk;
#endif
bool fatal;
int err;
sk = __inet6_lookup_established(net, &tcp_hashinfo,
&hdr->daddr, th->dest,
&hdr->saddr, ntohs(th->source),
skb->dev->ifindex, inet6_sdif(skb));
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
seq = ntohl(th->seq);
fatal = icmpv6_err_convert(type, code, &err);
if (sk->sk_state == TCP_NEW_SYN_RECV)
return tcp_req_err(sk, seq, fatal);
#ifdef CONFIG_MPTCP
tp = tcp_sk(sk);
if (mptcp(tp))
meta_sk = mptcp_meta_sk(sk);
else
meta_sk = sk;
bh_lock_sock(meta_sk);
if (sock_owned_by_user(meta_sk) && type != ICMPV6_PKT_TOOBIG)
#else
bh_lock_sock(sk);
if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
#endif
__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
goto out;
if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) {
__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
goto out;
}
#ifndef CONFIG_MPTCP
tp = tcp_sk(sk);
#endif
/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
fastopen = tp->fastopen_rsk;
snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
if (sk->sk_state != TCP_LISTEN &&
!between(seq, snd_una, tp->snd_nxt)) {
__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == NDISC_REDIRECT) {
if (!sock_owned_by_user(sk)) {
struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
if (dst)
dst->ops->redirect(dst, sk, skb);
}
goto out;
}
if (type == ICMPV6_PKT_TOOBIG) {
u32 mtu = ntohl(info);
/* We are not interested in TCP_LISTEN and open_requests
* (SYN-ACKs send out by Linux are always <576bytes so
* they should go through unfragmented).
*/
if (sk->sk_state == TCP_LISTEN)
goto out;
if (!ip6_sk_accept_pmtu(sk))
goto out;
if (mtu < IPV6_MIN_MTU)
goto out;
WRITE_ONCE(tp->mtu_info, ntohl(info));
#ifdef CONFIG_MPTCP
if (!sock_owned_by_user(meta_sk))
#else
if (!sock_owned_by_user(sk))
#endif
tcp_v6_mtu_reduced(sk);
#ifdef CONFIG_MPTCP
else {
if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
&sk->sk_tsq_flags))
sock_hold(sk);
if (mptcp(tp))
mptcp_tsq_flags(sk);
}
#else
else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
&sk->sk_tsq_flags))
sock_hold(sk);
#endif
goto out;
}
/* Might be for an request_sock */
switch (sk->sk_state) {
case TCP_SYN_SENT:
case TCP_SYN_RECV:
/* Only in fast or simultaneous open. If a fast open socket is
* is already accepted it is treated as a connected one below.
*/
if (fastopen && !fastopen->sk)
break;
#ifdef CONFIG_MPTCP
if (!sock_owned_by_user(meta_sk)) {
#else
if (!sock_owned_by_user(sk)) {
#endif
sk->sk_err = err;
sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */
tcp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
#ifdef CONFIG_MPTCP
if (!sock_owned_by_user(meta_sk) && np->recverr) {
#else
if (!sock_owned_by_user(sk) && np->recverr) {
#endif
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
#ifdef CONFIG_MPTCP
bh_unlock_sock(meta_sk);
#else
bh_unlock_sock(sk);
#endif
sock_put(sk);
}
static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
enum tcp_synack_type synack_type)
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_txoptions *opt;
struct flowi6 *fl6 = &fl->u.ip6;
struct sk_buff *skb;
int err = -ENOMEM;
/* First, grab a route. */
if (!dst && (dst = inet6_csk_route_req(sk, fl6, req,
IPPROTO_TCP)) == NULL)
goto done;
skb = tcp_make_synack(sk, dst, req, foc, synack_type);
if (skb) {
__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
&ireq->ir_v6_rmt_addr);
fl6->daddr = ireq->ir_v6_rmt_addr;
if (np->repflow && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
rcu_read_lock();
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt,
np->tclass);
rcu_read_unlock();
err = net_xmit_eval(err);
}
done:
return err;
}
#ifndef CONFIG_MPTCP
static
#endif
void tcp_v6_reqsk_destructor(struct request_sock *req)
{
kfree(inet_rsk(req)->ipv6_opt);
kfree_skb(inet_rsk(req)->pktopts);
}
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk,
const struct in6_addr *addr)
{
return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6);
}
static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk,
const struct sock *addr_sk)
{
return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr);
}
static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
char __user *optval, int optlen)
{
struct tcp_md5sig cmd;
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
u8 prefixlen;
if (optlen < sizeof(cmd))
return -EINVAL;
if (copy_from_user(&cmd, optval, sizeof(cmd)))
return -EFAULT;
if (sin6->sin6_family != AF_INET6)
return -EINVAL;
if (optname == TCP_MD5SIG_EXT &&
cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) {
prefixlen = cmd.tcpm_prefixlen;
if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) &&
prefixlen > 32))
return -EINVAL;
} else {
prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128;
}
if (!cmd.tcpm_keylen) {
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
AF_INET, prefixlen);
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
AF_INET6, prefixlen);
}
if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
return -EINVAL;
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
AF_INET, prefixlen, cmd.tcpm_key,
cmd.tcpm_keylen, GFP_KERNEL);
return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
AF_INET6, prefixlen, cmd.tcpm_key,
cmd.tcpm_keylen, GFP_KERNEL);
}
static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp,
const struct in6_addr *daddr,
const struct in6_addr *saddr,
const struct tcphdr *th, int nbytes)
{
struct tcp6_pseudohdr *bp;
struct scatterlist sg;
struct tcphdr *_th;
bp = hp->scratch;
/* 1. TCP pseudo-header (RFC2460) */
bp->saddr = *saddr;
bp->daddr = *daddr;
bp->protocol = cpu_to_be32(IPPROTO_TCP);
bp->len = cpu_to_be32(nbytes);
_th = (struct tcphdr *)(bp + 1);
memcpy(_th, th, sizeof(*th));
_th->check = 0;
sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
ahash_request_set_crypt(hp->md5_req, &sg, NULL,
sizeof(*bp) + sizeof(*th));
return crypto_ahash_update(hp->md5_req);
}
static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
const struct in6_addr *daddr, struct in6_addr *saddr,
const struct tcphdr *th)
{
struct tcp_md5sig_pool *hp;
struct ahash_request *req;
hp = tcp_get_md5sig_pool();
if (!hp)
goto clear_hash_noput;
req = hp->md5_req;
if (crypto_ahash_init(req))
goto clear_hash;
if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2))
goto clear_hash;
if (tcp_md5_hash_key(hp, key))
goto clear_hash;
ahash_request_set_crypt(req, NULL, md5_hash, 0);
if (crypto_ahash_final(req))
goto clear_hash;
tcp_put_md5sig_pool();
return 0;
clear_hash:
tcp_put_md5sig_pool();
clear_hash_noput:
memset(md5_hash, 0, 16);
return 1;
}
static int tcp_v6_md5_hash_skb(char *md5_hash,
const struct tcp_md5sig_key *key,
const struct sock *sk,
const struct sk_buff *skb)
{
const struct in6_addr *saddr, *daddr;
struct tcp_md5sig_pool *hp;
struct ahash_request *req;
const struct tcphdr *th = tcp_hdr(skb);
if (sk) { /* valid for establish/request sockets */
saddr = &sk->sk_v6_rcv_saddr;
daddr = &sk->sk_v6_daddr;
} else {
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
saddr = &ip6h->saddr;
daddr = &ip6h->daddr;
}
hp = tcp_get_md5sig_pool();
if (!hp)
goto clear_hash_noput;
req = hp->md5_req;
if (crypto_ahash_init(req))
goto clear_hash;
if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, skb->len))
goto clear_hash;
if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
goto clear_hash;
if (tcp_md5_hash_key(hp, key))
goto clear_hash;
ahash_request_set_crypt(req, NULL, md5_hash, 0);
if (crypto_ahash_final(req))
goto clear_hash;
tcp_put_md5sig_pool();
return 0;
clear_hash:
tcp_put_md5sig_pool();
clear_hash_noput:
memset(md5_hash, 0, 16);
return 1;
}
#endif
static bool tcp_v6_inbound_md5_hash(const struct sock *sk,
const struct sk_buff *skb)
{
#ifdef CONFIG_TCP_MD5SIG
const __u8 *hash_location = NULL;
struct tcp_md5sig_key *hash_expected;
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
const struct tcphdr *th = tcp_hdr(skb);
int genhash;
u8 newhash[16];
hash_expected = tcp_v6_md5_do_lookup(sk, &ip6h->saddr);
hash_location = tcp_parse_md5sig_option(th);
/* We've parsed the options - do we have a hash? */
if (!hash_expected && !hash_location)
return false;
if (hash_expected && !hash_location) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
return true;
}
if (!hash_expected && hash_location) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
return true;
}
/* check the signature */
genhash = tcp_v6_md5_hash_skb(newhash,
hash_expected,
NULL, skb);
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n",
genhash ? "failed" : "mismatch",
&ip6h->saddr, ntohs(th->source),
&ip6h->daddr, ntohs(th->dest));
return true;
}
#endif
return false;
}
#ifdef CONFIG_MPTCP
static int tcp_v6_init_req(struct request_sock *req, const struct sock *sk_listener,
struct sk_buff *skb, bool want_cookie)
#else
static void tcp_v6_init_req(struct request_sock *req,
const struct sock *sk_listener,
struct sk_buff *skb)
#endif
{
struct inet_request_sock *ireq = inet_rsk(req);
const struct ipv6_pinfo *np = inet6_sk(sk_listener);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
/* So that link locals have meaning */
if (!sk_listener->sk_bound_dev_if &&
ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq->ir_iif = tcp_v6_iif(skb);
if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
(ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) ||
np->rxopt.bits.rxinfo ||
np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
np->rxopt.bits.rxohlim || np->repflow)) {
refcount_inc(&skb->users);
ireq->pktopts = skb;
}
#ifdef CONFIG_MPTCP
return 0;
#endif
}
static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
struct flowi *fl,
const struct request_sock *req)
{
return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP);
}
struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
.family = AF_INET6,
.obj_size = sizeof(struct tcp6_request_sock),
.rtx_syn_ack = tcp_rtx_synack,
.send_ack = tcp_v6_reqsk_send_ack,
.destructor = tcp_v6_reqsk_destructor,
.send_reset = tcp_v6_send_reset,
.syn_ack_timeout = tcp_syn_ack_timeout,
};
#ifndef CONFIG_MPTCP
static
#endif
const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) -
sizeof(struct ipv6hdr),
#ifdef CONFIG_TCP_MD5SIG
.req_md5_lookup = tcp_v6_md5_lookup,
.calc_md5_hash = tcp_v6_md5_hash_skb,
#endif
.init_req = tcp_v6_init_req,
#ifdef CONFIG_SYN_COOKIES
.cookie_init_seq = cookie_v6_init_sequence,
#endif
.route_req = tcp_v6_route_req,
.init_seq = tcp_v6_init_seq,
.init_ts_off = tcp_v6_init_ts_off,
.send_synack = tcp_v6_send_synack,
};
#ifdef CONFIG_MPTCP
static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 data_ack, u32 win, u32 tsval, u32 tsecr,
int oif, struct tcp_md5sig_key *key, int rst,
u8 tclass, __be32 label, int mptcp)
#else
static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 win, u32 tsval, u32 tsecr,
int oif, struct tcp_md5sig_key *key, int rst,
u8 tclass, __be32 label)
#endif
{
const struct tcphdr *th = tcp_hdr(skb);
struct tcphdr *t1;
struct sk_buff *buff;
struct flowi6 fl6;
struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
struct sock *ctl_sk = net->ipv6.tcp_sk;
unsigned int tot_len = sizeof(struct tcphdr);
struct dst_entry *dst;
__be32 *topt;
if (tsecr)
tot_len += TCPOLEN_TSTAMP_ALIGNED;
#ifdef CONFIG_TCP_MD5SIG
if (key)
tot_len += TCPOLEN_MD5SIG_ALIGNED;
#endif
#ifdef CONFIG_MPTCP
if (mptcp)
tot_len += MPTCP_SUB_LEN_DSS + MPTCP_SUB_LEN_ACK;
#endif
buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
GFP_ATOMIC);
if (!buff)
return;
skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len);
t1 = skb_push(buff, tot_len);
skb_reset_transport_header(buff);
/* Swap the send and the receive. */
memset(t1, 0, sizeof(*t1));
t1->dest = th->source;
t1->source = th->dest;
t1->doff = tot_len / 4;
t1->seq = htonl(seq);
t1->ack_seq = htonl(ack);
t1->ack = !rst || !th->ack;
t1->rst = rst;
t1->window = htons(win);
topt = (__be32 *)(t1 + 1);
if (tsecr) {
*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
*topt++ = htonl(tsval);
*topt++ = htonl(tsecr);
}
#ifdef CONFIG_TCP_MD5SIG
if (key) {
*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
tcp_v6_md5_hash_hdr((__u8 *)topt, key,
&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr, t1);
#ifdef CONFIG_MPTCP
topt += 4;
#endif
}
#endif
#ifdef CONFIG_MPTCP
if (mptcp) {
/* Construction of 32-bit data_ack */
*topt++ = htonl((TCPOPT_MPTCP << 24) |
((MPTCP_SUB_LEN_DSS + MPTCP_SUB_LEN_ACK) << 16) |
(0x20 << 8) |
(0x01));
*topt++ = htonl(data_ack);
}
#endif
memset(&fl6, 0, sizeof(fl6));
fl6.daddr = ipv6_hdr(skb)->saddr;
fl6.saddr = ipv6_hdr(skb)->daddr;
fl6.flowlabel = label;
buff->ip_summed = CHECKSUM_PARTIAL;
buff->csum = 0;
__tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
fl6.flowi6_proto = IPPROTO_TCP;
if (rt6_need_strict(&fl6.daddr) && !oif)
fl6.flowi6_oif = tcp_v6_iif(skb);
else {
if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
oif = skb->skb_iif;
fl6.flowi6_oif = oif;
}
fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
/* Pass a socket to ip6_dst_lookup either it is for RST
* Underlying function will use this to retrieve the network
* namespace
*/
dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
if (!IS_ERR(dst)) {
skb_dst_set(buff, dst);
ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass);
TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
if (rst)
TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
return;
}
kfree_skb(buff);
}
#ifndef CONFIG_MPTCP
static
#endif
void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
{
const struct tcphdr *th = tcp_hdr(skb);
u32 seq = 0, ack_seq = 0;
struct tcp_md5sig_key *key = NULL;
#ifdef CONFIG_TCP_MD5SIG
const __u8 *hash_location = NULL;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
unsigned char newhash[16];
int genhash;
struct sock *sk1 = NULL;
#endif
int oif;
DROPDUMP_CLEAR_SKB(skb);
if (th->rst)
return;
/* If sk not NULL, it means we did a successful lookup and incoming
* route had to be correct. prequeue might have dropped our dst.
*/
if (!sk && !ipv6_unicast_destination(skb))
return;
#ifdef CONFIG_TCP_MD5SIG
rcu_read_lock();
hash_location = tcp_parse_md5sig_option(th);
if (sk && sk_fullsock(sk)) {
key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr);
} else if (hash_location) {
/*
* active side is lost. Try to find listening socket through
* source port, and then find md5 key through listening socket.
* we are not loose security here:
* Incoming packet is checked with md5 hash with finding key,
* no RST generated if md5 hash doesn't match.
*/
sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev),
&tcp_hashinfo, NULL, 0,
&ipv6h->saddr,
th->source, &ipv6h->daddr,
ntohs(th->source),
tcp_v6_iif_l3_slave(skb),
tcp_v6_sdif(skb));
if (!sk1)
goto out;
key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr);
if (!key)
goto out;
genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb);
if (genhash || memcmp(hash_location, newhash, 16) != 0)
goto out;
}
#endif
if (th->ack)
seq = ntohl(th->ack_seq);
else
ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len -
(th->doff << 2);
oif = sk ? sk->sk_bound_dev_if : 0;
#ifdef CONFIG_MPTCP
tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, 0, oif, key, 1, 0, 0, 0);
#else
tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
#endif
#ifdef CONFIG_TCP_MD5SIG
out:
rcu_read_unlock();
#endif
}
#ifdef CONFIG_MPTCP
static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 data_ack, u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key, u8 tclass,
__be32 label, int mptcp)
{
tcp_v6_send_response(sk, skb, seq, ack, data_ack, win, tsval, tsecr, oif,
key, 0, tclass, label, mptcp);
}
#else
static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key, u8 tclass,
__be32 label)
{
tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
tclass, label);
}
#endif
static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
#ifdef CONFIG_MPTCP
u32 data_ack = 0;
int mptcp = 0;
if (tcptw->mptcp_tw) {
data_ack = (u32)tcptw->mptcp_tw->rcv_nxt;
mptcp = 1;
}
tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
data_ack,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp_raw() + tcptw->tw_ts_offset,
tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), mptcp);
#else
tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp_raw() + tcptw->tw_ts_offset,
tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel));
#endif
inet_twsk_put(tw);
}
#ifndef CONFIG_MPTCP
static
#endif
void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
* sk->sk_state == TCP_SYN_RECV -> for Fast Open.
*/
/* RFC 7323 2.3
* The window field (SEG.WND) of every outgoing segment, with the
* exception of <SYN> segments, MUST be right-shifted by
* Rcv.Wind.Shift bits:
*/
#ifdef CONFIG_MPTCP
tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN || is_meta_sk(sk)) ?
tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
tcp_rsk(req)->rcv_nxt, 0,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
req->ts_recent, sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
0, 0, 0);
#else
tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
tcp_rsk(req)->rcv_nxt,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
req->ts_recent, sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
0, 0);
#endif
}
#ifndef CONFIG_MPTCP
static
#endif
struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb)
{
#ifdef CONFIG_SYN_COOKIES
const struct tcphdr *th = tcp_hdr(skb);
if (!th->syn)
sk = cookie_v6_check(sk, skb);
#endif
return sk;
}
#ifndef CONFIG_MPTCP
static
#endif
int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_conn_request(sk, skb);
if (!ipv6_unicast_destination(skb))
goto drop;
if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
return 0;
}
return tcp_conn_request(&tcp6_request_sock_ops,
&tcp_request_sock_ipv6_ops, sk, skb);
drop:
tcp_listendrop(sk);
return 0; /* don't send reset */
}
static void tcp_v6_restore_cb(struct sk_buff *skb)
{
/* We need to move header back to the beginning if xfrm6_policy_check()
* and tcp_v6_fill_cb() are going to be called again.
* ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
*/
memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
sizeof(struct inet6_skb_parm));
}
#ifndef CONFIG_MPTCP
static
#endif
struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
struct request_sock *req_unhash,
bool *own_req)
{
struct inet_request_sock *ireq;
struct ipv6_pinfo *newnp;
const struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_txoptions *opt;
struct tcp6_sock *newtcp6sk;
struct inet_sock *newinet;
bool found_dup_sk = false;
struct tcp_sock *newtp;
struct sock *newsk;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *key;
#endif
struct flowi6 fl6;
if (skb->protocol == htons(ETH_P_IP)) {
/*
* v6 mapped
*/
newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst,
req_unhash, own_req);
if (!newsk)
return NULL;
newtcp6sk = (struct tcp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
newinet = inet_sk(newsk);
newnp = inet6_sk(newsk);
newtp = tcp_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newnp->saddr = newsk->sk_v6_rcv_saddr;
#ifdef CONFIG_MPTCP
/* We must check on the request-socket because the listener
* socket's flag may have been changed halfway through.
*/
if (!inet_rsk(req)->saw_mpc)
inet_csk(newsk)->icsk_af_ops = &mptcp_v6_mapped;
else
#endif
inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
newsk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif
newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet_iif(skb);
newnp->mcast_hops = ip_hdr(skb)->ttl;
newnp->rcv_flowinfo = 0;
if (np->repflow)
newnp->flow_label = 0;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
* here, tcp_create_openreq_child now does this for us, see the comment in
* that function for the gory details. -acme
*/
/* It is tricky place. Until this moment IPv4 tcp
worked with IPv6 icsk.icsk_af_ops.
Sync it now.
*/
tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
return newsk;
}
ireq = inet_rsk(req);
if (sk_acceptq_is_full(sk))
goto out_overflow;
if (!dst) {
dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP);
if (!dst)
goto out;
}
newsk = tcp_create_openreq_child(sk, req, skb);
if (!newsk)
goto out_nonewsk;
#ifdef CONFIG_MPTCP
/* If the meta_sk is v6-mapped we can end up here with the wrong af_ops.
* Just make sure that this subflow is v6.
*/
if (is_meta_sk(sk))
inet_csk(newsk)->icsk_af_ops = &mptcp_v6_specific;
#endif
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks
* count here, tcp_create_openreq_child now does this for us, see the
* comment in that function for the gory details. -acme
*/
newsk->sk_gso_type = SKB_GSO_TCPV6;
ip6_dst_store(newsk, dst, NULL, NULL);
inet6_sk_rx_dst_set(newsk, skb);
newtcp6sk = (struct tcp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
newtp = tcp_sk(newsk);
newinet = inet_sk(newsk);
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
newnp->saddr = ireq->ir_v6_loc_addr;
newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
newsk->sk_bound_dev_if = ireq->ir_iif;
/* Now IPv6 options...
First: no IPv4 options.
*/
newinet->inet_opt = NULL;
newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = tcp_v6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
if (np->repflow)
newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
/* Clone native IPv6 options from listening socket (if any)
Yes, keeping reference count would be much more clever,
but we make one more one thing there: reattach optmem
to newsk.
*/
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
if (opt) {
opt = ipv6_dup_options(newsk, opt);
RCU_INIT_POINTER(newnp->opt, opt);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (opt)
inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
opt->opt_flen;
tcp_ca_openreq_child(newsk, dst);
tcp_sync_mss(newsk, dst_mtu(dst));
newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
tcp_initialize_rcv_mss(newsk);
newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
#ifdef CONFIG_TCP_MD5SIG
/* Copy over the MD5 key from the original socket */
key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr);
if (key) {
/* We're using one, so create a matching key
* on the newsk structure. If we fail to get
* memory, then we end up not copying the key
* across. Shucks.
*/
tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr,
AF_INET6, 128, key->key, key->keylen,
sk_gfp_mask(sk, GFP_ATOMIC));
}
#endif
if (__inet_inherit_port(sk, newsk) < 0) {
inet_csk_prepare_forced_close(newsk);
tcp_done(newsk);
goto out;
}
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
&found_dup_sk);
if (*own_req) {
tcp_move_syn(newtp, req);
/* Clone pktoptions received with SYN, if we own the req */
if (ireq->pktopts) {
newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk);
consume_skb(ireq->pktopts);
ireq->pktopts = NULL;
if (newnp->pktoptions)
tcp_v6_restore_cb(newnp->pktoptions);
}
} else {
if (!req_unhash && found_dup_sk) {
/* This code path should only be executed in the
* syncookie case only
*/
bh_unlock_sock(newsk);
sock_put(newsk);
newsk = NULL;
}
}
return newsk;
out_overflow:
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out_nonewsk:
dst_release(dst);
out:
tcp_listendrop(sk);
return NULL;
}
/* The socket must have it's spinlock held when we get
* here, unless it is a TCP_LISTEN socket.
*
* We have a potential double-lock case here, so even when
* doing backlog processing we use the BH locking scheme.
* This is because we cannot sleep with the original spinlock
* held.
*/
#ifndef CONFIG_MPTCP
static
#endif
int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp;
struct sk_buff *opt_skb = NULL;
/* Imagine: socket is IPv6. IPv4 packet arrives,
goes to IPv4 receive handler and backlogged.
From backlog it always goes here. Kerboom...
Fortunately, tcp_rcv_established and rcv_established
handle them correctly, but it is not case with
tcp_v6_hnd_req and tcp_v6_send_reset(). --ANK
*/
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_do_rcv(sk, skb);
#ifdef CONFIG_MPTCP
if (is_meta_sk(sk))
return mptcp_v6_do_rcv(sk, skb);
#endif
/*
* socket locking is here for SMP purposes as backlog rcv
* is currently called with bh processing disabled.
*/
/* Do Stevens' IPV6_PKTOPTIONS.
Yes, guys, it is the only place in our code, where we
may make it not affecting IPv4.
The rest of code is protocol independent,
and I do not like idea to uglify IPv4.
Actually, all the idea behind IPV6_PKTOPTIONS
looks not very well thought. For now we latch
options, received in the last packet, enqueued
by tcp. Feel free to propose better solution.
--ANK (980728)
*/
if (np->rxopt.all)
opt_skb = skb_clone_and_charge_r(skb, sk);
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
struct dst_entry *dst;
dst = rcu_dereference_protected(sk->sk_rx_dst,
lockdep_sock_is_held(sk));
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
if (dst) {
if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
dst_release(dst);
}
}
tcp_rcv_established(sk, skb, tcp_hdr(skb));
if (opt_skb)
goto ipv6_pktoptions;
return 0;
}
if (tcp_checksum_complete(skb))
goto csum_err;
if (sk->sk_state == TCP_LISTEN) {
struct sock *nsk = tcp_v6_cookie_check(sk, skb);
if (!nsk)
goto discard;
if (nsk != sk) {
if (tcp_child_process(sk, nsk, skb))
goto reset;
if (opt_skb)
__kfree_skb(opt_skb);
return 0;
}
} else
sock_rps_save_rxhash(sk, skb);
if (tcp_rcv_state_process(sk, skb))
goto reset;
if (opt_skb)
goto ipv6_pktoptions;
return 0;
reset:
tcp_v6_send_reset(sk, skb);
discard:
if (opt_skb)
__kfree_skb(opt_skb);
kfree_skb(skb);
return 0;
csum_err:
TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
DROPDUMP_QUEUE_SKB(skb, NET_DROPDUMP_TCP_MIB_INERRS5);
goto discard;
ipv6_pktoptions:
/* Do you ask, what is it?
1. skb was enqueued by tcp.
2. skb is added to tail of read queue, rather than out of order.
3. socket is not in passive state.
4. Finally, it really contains options, which user wants to receive.
*/
tp = tcp_sk(sk);
if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt &&
!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
np->mcast_oif = tcp_v6_iif(opt_skb);
if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
if (np->repflow)
np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
tcp_v6_restore_cb(opt_skb);
opt_skb = xchg(&np->pktoptions, opt_skb);
} else {
__kfree_skb(opt_skb);
opt_skb = xchg(&np->pktoptions, NULL);
}
}
DROPDUMP_CLEAR_SKB(opt_skb);
kfree_skb(opt_skb);
return 0;
}
static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
const struct tcphdr *th)
{
/* This is tricky: we move IP6CB at its correct location into
* TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because
* _decode_session6() uses IP6CB().
* barrier() makes sure compiler won't play aliasing games.
*/
memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb),
sizeof(struct inet6_skb_parm));
barrier();
TCP_SKB_CB(skb)->seq = ntohl(th->seq);
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff*4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
#ifdef CONFIG_MPTCP
TCP_SKB_CB(skb)->mptcp_flags = 0;
TCP_SKB_CB(skb)->dss_off = 0;
#endif
TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
TCP_SKB_CB(skb)->tcp_tw_isn = 0;
TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
TCP_SKB_CB(skb)->sacked = 0;
TCP_SKB_CB(skb)->has_rxtstamp =
skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
}
static int tcp_v6_rcv(struct sk_buff *skb)
{
int sdif = inet6_sdif(skb);
const struct tcphdr *th;
const struct ipv6hdr *hdr;
bool refcounted;
struct sock *sk;
#ifdef CONFIG_MPTCP
struct sock *meta_sk = NULL;
#endif
int ret;
struct net *net = dev_net(skb->dev);
if (skb->pkt_type != PACKET_HOST)
goto discard_it;
/*
* Count it even if it's bad.
*/
__TCP_INC_STATS(net, TCP_MIB_INSEGS);
if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
goto discard_it;
th = (const struct tcphdr *)skb->data;
if (unlikely(th->doff < sizeof(struct tcphdr)/4))
goto bad_packet;
if (!pskb_may_pull(skb, th->doff*4))
goto discard_it;
if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo))
goto csum_error;
th = (const struct tcphdr *)skb->data;
hdr = ipv6_hdr(skb);
lookup:
sk = __inet6_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th),
th->source, th->dest, inet6_iif(skb), sdif,
&refcounted);
if (!sk)
goto no_tcp_socket;
process:
if (sk->sk_state == TCP_TIME_WAIT)
goto do_time_wait;
if (sk->sk_state == TCP_NEW_SYN_RECV) {
struct request_sock *req = inet_reqsk(sk);
struct sock *nsk;
sk = req->rsk_listener;
if (tcp_v6_inbound_md5_hash(sk, skb)) {
sk_drops_add(sk, skb);
reqsk_put(req);
goto discard_it;
}
if (tcp_checksum_complete(skb)) {
reqsk_put(req);
goto csum_error;
}
if (unlikely(sk->sk_state != TCP_LISTEN
#ifdef CONFIG_MPTCP
&& !is_meta_sk(sk)
#endif
)) {
inet_csk_reqsk_queue_drop_and_put(sk, req);
goto lookup;
}
sock_hold(sk);
refcounted = true;
#ifdef CONFIG_MPTCP
if (is_meta_sk(sk)) {
bh_lock_sock(sk);
if (!mptcp_can_new_subflow(sk)) {
inet_csk_reqsk_queue_drop_and_put(sk, req);
bh_unlock_sock(sk);
goto discard_and_relse;
}
if (sock_owned_by_user(sk)) {
mptcp_prepare_for_backlog(sk, skb);
if (unlikely(sk_add_backlog(sk, skb,
sk->sk_rcvbuf + sk->sk_sndbuf))) {
reqsk_put(req);
bh_unlock_sock(sk);
__NET_INC_STATS(net, LINUX_MIB_TCPBACKLOGDROP);
DROPDUMP_QPCAP_SKB(skb, NET_DROPDUMP_OPT_TCP_BACKLOGDROP2);
goto discard_and_relse;
}
reqsk_put(req);
bh_unlock_sock(sk);
sock_put(sk);
return 0;
}
}
#endif
nsk = NULL;
if (!tcp_filter(sk, skb)) {
th = (const struct tcphdr *)skb->data;
hdr = ipv6_hdr(skb);
tcp_v6_fill_cb(skb, hdr, th);
nsk = tcp_check_req(sk, skb, req, false);
}
if (!nsk) {
reqsk_put(req);
#ifdef CONFIG_MPTCP
if (is_meta_sk(sk))
bh_unlock_sock(sk);
#endif
goto discard_and_relse;
}
if (nsk == sk) {
reqsk_put(req);
#ifdef CONFIG_MPTCP
if (is_meta_sk(sk))
bh_unlock_sock(sk);
#endif
tcp_v6_restore_cb(skb);
} else if (tcp_child_process(sk, nsk, skb)) {
tcp_v6_send_reset(nsk, skb);
goto discard_and_relse;
} else {
sock_put(sk);
return 0;
}
}
if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) {
__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
DROPDUMP_QUEUE_SKB(skb, NET_DROPDUMP_TCP_MIB_MINTTLDROP1);
goto discard_and_relse;
}
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
if (tcp_v6_inbound_md5_hash(sk, skb))
goto discard_and_relse;
if (tcp_filter(sk, skb))
goto discard_and_relse;
th = (const struct tcphdr *)skb->data;
hdr = ipv6_hdr(skb);
tcp_v6_fill_cb(skb, hdr, th);
skb->dev = NULL;
if (sk->sk_state == TCP_LISTEN) {
ret = tcp_v6_do_rcv(sk, skb);
goto put_and_return;
}
sk_incoming_cpu_update(sk);
#ifdef CONFIG_MPTCP
if (mptcp(tcp_sk(sk))) {
meta_sk = mptcp_meta_sk(sk);
bh_lock_sock_nested(meta_sk);
if (sock_owned_by_user(meta_sk))
mptcp_prepare_for_backlog(sk, skb);
} else {
meta_sk = sk;
#endif
bh_lock_sock_nested(sk);
#ifdef CONFIG_MPTCP
}
#endif
tcp_segs_in(tcp_sk(sk), skb);
ret = 0;
#ifdef CONFIG_MPTCP
if (!sock_owned_by_user(meta_sk)) {
#else
if (!sock_owned_by_user(sk)) {
#endif
ret = tcp_v6_do_rcv(sk, skb);
#ifdef CONFIG_MPTCP
} else if (tcp_add_backlog(meta_sk, skb)) {
#else
} else if (tcp_add_backlog(sk, skb)) {
#endif
goto discard_and_relse;
}
#ifdef CONFIG_MPTCP
bh_unlock_sock(meta_sk);
#else
bh_unlock_sock(sk);
#endif
put_and_return:
if (refcounted)
sock_put(sk);
return ret ? -1 : 0;
no_tcp_socket:
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
tcp_v6_fill_cb(skb, hdr, th);
#ifdef CONFIG_MPTCP
if (!sk && th->syn && !th->ack) {
int ret = mptcp_lookup_join(skb, NULL);
if (ret < 0) {
tcp_v6_send_reset(NULL, skb);
goto discard_it;
} else if (ret > 0) {
return 0;
}
}
#endif
if (tcp_checksum_complete(skb)) {
csum_error:
__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
DROPDUMP_QUEUE_SKB(skb, NET_DROPDUMP_TCP_MIB_CSUMERRORS1);
bad_packet:
__TCP_INC_STATS(net, TCP_MIB_INERRS);
DROPDUMP_QUEUE_SKB(skb, NET_DROPDUMP_TCP_MIB_INERRS6);
} else {
tcp_v6_send_reset(NULL, skb);
}
discard_it:
DROPDUMP_CHECK_SKB(skb);
kfree_skb(skb);
return 0;
discard_and_relse:
sk_drops_add(sk, skb);
if (refcounted)
sock_put(sk);
goto discard_it;
do_time_wait:
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
tcp_v6_fill_cb(skb, hdr, th);
if (tcp_checksum_complete(skb)) {
inet_twsk_put(inet_twsk(sk));
goto csum_error;
}
switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
case TCP_TW_SYN:
{
struct sock *sk2;
sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo,
skb, __tcp_hdrlen(th),
&ipv6_hdr(skb)->saddr, th->source,
&ipv6_hdr(skb)->daddr,
ntohs(th->dest),
tcp_v6_iif_l3_slave(skb),
sdif);
if (sk2) {
struct inet_timewait_sock *tw = inet_twsk(sk);
inet_twsk_deschedule_put(tw);
sk = sk2;
tcp_v6_restore_cb(skb);
refcounted = false;
goto process;
}
#ifdef CONFIG_MPTCP
if (th->syn && !th->ack) {
int ret = mptcp_lookup_join(skb, inet_twsk(sk));
if (ret < 0) {
tcp_v6_send_reset(NULL, skb);
goto discard_it;
} else if (ret > 0) {
return 0;
}
}
#endif
/* Fall through to ACK */
}
case TCP_TW_ACK:
tcp_v6_timewait_ack(sk, skb);
break;
case TCP_TW_RST:
tcp_v6_send_reset(sk, skb);
inet_twsk_deschedule_put(inet_twsk(sk));
goto discard_it;
case TCP_TW_SUCCESS:
;
}
goto discard_it;
}
void tcp_v6_early_demux(struct sk_buff *skb)
{
const struct ipv6hdr *hdr;
const struct tcphdr *th;
struct sock *sk;
if (skb->pkt_type != PACKET_HOST)
return;
if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
return;
hdr = ipv6_hdr(skb);
th = tcp_hdr(skb);
if (th->doff < sizeof(struct tcphdr) / 4)
return;
/* Note : We use inet6_iif() here, not tcp_v6_iif() */
sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
&hdr->saddr, th->source,
&hdr->daddr, ntohs(th->dest),
inet6_iif(skb), inet6_sdif(skb));
if (sk) {
skb->sk = sk;
skb->destructor = sock_edemux;
if (sk_fullsock(sk)) {
struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
if (dst &&
inet_sk(sk)->rx_dst_ifindex == skb->skb_iif)
skb_dst_set_noref(skb, dst);
}
}
}
#ifndef CONFIG_MPTCP
static
#endif
struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct tcp6_timewait_sock),
.twsk_unique = tcp_twsk_unique,
.twsk_destructor = tcp_twsk_destructor,
};
#ifndef CONFIG_MPTCP
static
#endif
const struct inet_connection_sock_af_ops ipv6_specific = {
.queue_xmit = inet6_csk_xmit,
.send_check = tcp_v6_send_check,
.rebuild_header = inet6_sk_rebuild_header,
.sk_rx_dst_set = inet6_sk_rx_dst_set,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.net_header_len = sizeof(struct ipv6hdr),
.net_frag_header_len = sizeof(struct frag_hdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
.mtu_reduced = tcp_v6_mtu_reduced,
};
#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = {
.md5_lookup = tcp_v6_md5_lookup,
.calc_md5_hash = tcp_v6_md5_hash_skb,
.md5_parse = tcp_v6_parse_md5_keys,
};
#endif
/*
* TCP over IPv4 via INET6 API
*/
#ifndef CONFIG_MPTCP
static
#endif
const struct inet_connection_sock_af_ops ipv6_mapped = {
.queue_xmit = ip_queue_xmit,
.send_check = tcp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
.sk_rx_dst_set = inet_sk_rx_dst_set,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.net_header_len = sizeof(struct iphdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
.mtu_reduced = tcp_v4_mtu_reduced,
};
#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = {
.md5_lookup = tcp_v4_md5_lookup,
.calc_md5_hash = tcp_v4_md5_hash_skb,
.md5_parse = tcp_v6_parse_md5_keys,
};
#endif
/* NOTE: A lot of things set to zero explicitly by call to
* sk_alloc() so need not be done here.
*/
static int tcp_v6_init_sock(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_init_sock(sk);
#ifdef CONFIG_MPTCP
if (sock_flag(sk, SOCK_MPTCP))
icsk->icsk_af_ops = &mptcp_v6_specific;
else
#endif
icsk->icsk_af_ops = &ipv6_specific;
#ifdef CONFIG_TCP_MD5SIG
tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific;
#endif
return 0;
}
#ifdef CONFIG_PROC_FS
/* Proc filesystem TCPv6 sock list dumping. */
static void get_openreq6(struct seq_file *seq,
const struct request_sock *req, int i)
{
long ttd = req->rsk_timer.expires - jiffies;
const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr;
const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr;
if (ttd < 0)
ttd = 0;
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
"%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3],
inet_rsk(req)->ir_num,
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3],
ntohs(inet_rsk(req)->ir_rmt_port),
TCP_SYN_RECV,
0, 0, /* could print option size, but that is af dependent. */
1, /* timers active (only the expire timer) */
jiffies_to_clock_t(ttd),
req->num_timeout,
from_kuid_munged(seq_user_ns(seq),
sock_i_uid(req->rsk_listener)),
0, /* non standard timer */
0, /* open_requests have no inode */
0, req);
}
static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
{
const struct in6_addr *dest, *src;
__u16 destp, srcp;
int timer_active;
unsigned long timer_expires;
const struct inet_sock *inet = inet_sk(sp);
const struct tcp_sock *tp = tcp_sk(sp);
const struct inet_connection_sock *icsk = inet_csk(sp);
const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq;
int rx_queue;
int state;
dest = &sp->sk_v6_daddr;
src = &sp->sk_v6_rcv_saddr;
destp = ntohs(inet->inet_dport);
srcp = ntohs(inet->inet_sport);
if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
timer_active = 1;
timer_expires = icsk->icsk_timeout;
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
timer_active = 4;
timer_expires = icsk->icsk_timeout;
} else if (timer_pending(&sp->sk_timer)) {
timer_active = 2;
timer_expires = sp->sk_timer.expires;
} else {
timer_active = 0;
timer_expires = jiffies;
}
state = sk_state_load(sp);
if (state == TCP_LISTEN)
rx_queue = sp->sk_ack_backlog;
else
/* Because we don't lock the socket,
* we might find a transient negative value.
*/
rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
"%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3], srcp,
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3], destp,
state,
tp->write_seq - tp->snd_una,
rx_queue,
timer_active,
jiffies_delta_to_clock_t(timer_expires - jiffies),
icsk->icsk_retransmits,
from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
icsk->icsk_probes_out,
sock_i_ino(sp),
refcount_read(&sp->sk_refcnt), sp,
jiffies_to_clock_t(icsk->icsk_rto),
jiffies_to_clock_t(icsk->icsk_ack.ato),
(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
tp->snd_cwnd,
state == TCP_LISTEN ?
fastopenq->max_qlen :
(tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)
);
}
static void get_timewait6_sock(struct seq_file *seq,
struct inet_timewait_sock *tw, int i)
{
long delta = tw->tw_timer.expires - jiffies;
const struct in6_addr *dest, *src;
__u16 destp, srcp;
dest = &tw->tw_v6_daddr;
src = &tw->tw_v6_rcv_saddr;
destp = ntohs(tw->tw_dport);
srcp = ntohs(tw->tw_sport);
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
"%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3], srcp,
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3], destp,
tw->tw_substate, 0, 0,
3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
refcount_read(&tw->tw_refcnt), tw);
}
static int tcp6_seq_show(struct seq_file *seq, void *v)
{
struct tcp_iter_state *st;
struct sock *sk = v;
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
" sl "
"local_address "
"remote_address "
"st tx_queue rx_queue tr tm->when retrnsmt"
" uid timeout inode\n");
goto out;
}
st = seq->private;
if (sk->sk_state == TCP_TIME_WAIT)
get_timewait6_sock(seq, v, st->num);
else if (sk->sk_state == TCP_NEW_SYN_RECV)
get_openreq6(seq, v, st->num);
else
get_tcp6_sock(seq, v, st->num);
out:
return 0;
}
static const struct file_operations tcp6_afinfo_seq_fops = {
.owner = THIS_MODULE,
.open = tcp_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_net
};
static struct tcp_seq_afinfo tcp6_seq_afinfo = {
.name = "tcp6",
.family = AF_INET6,
.seq_fops = &tcp6_afinfo_seq_fops,
.seq_ops = {
.show = tcp6_seq_show,
},
};
int __net_init tcp6_proc_init(struct net *net)
{
return tcp_proc_register(net, &tcp6_seq_afinfo);
}
void tcp6_proc_exit(struct net *net)
{
tcp_proc_unregister(net, &tcp6_seq_afinfo);
}
#endif
struct proto tcpv6_prot = {
.name = "TCPv6",
.owner = THIS_MODULE,
.close = tcp_close,
.pre_connect = tcp_v6_pre_connect,
.connect = tcp_v6_connect,
.disconnect = tcp_disconnect,
.accept = inet_csk_accept,
.ioctl = tcp_ioctl,
.init = tcp_v6_init_sock,
.destroy = tcp_v4_destroy_sock,
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
.keepalive = tcp_set_keepalive,
.recvmsg = tcp_recvmsg,
.sendmsg = tcp_sendmsg,
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v6_do_rcv,
.release_cb = tcp_release_cb,
.hash = inet6_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
.leave_memory_pressure = tcp_leave_memory_pressure,
.stream_memory_free = tcp_stream_memory_free,
.sockets_allocated = &tcp_sockets_allocated,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
.orphan_count = &tcp_orphan_count,
.sysctl_mem = sysctl_tcp_mem,
.sysctl_wmem = sysctl_tcp_wmem,
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp6_sock),
.slab_flags = SLAB_TYPESAFE_BY_RCU,
.twsk_prot = &tcp6_timewait_sock_ops,
.rsk_prot = &tcp6_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,
.no_autobind = true,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
#endif
.diag_destroy = tcp_abort,
#ifdef CONFIG_MPTCP
.clear_sk = mptcp_clear_sk,
#endif
};
static const struct inet6_protocol tcpv6_protocol = {
.handler = tcp_v6_rcv,
.err_handler = tcp_v6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};
static struct inet_protosw tcpv6_protosw = {
.type = SOCK_STREAM,
.protocol = IPPROTO_TCP,
.prot = &tcpv6_prot,
.ops = &inet6_stream_ops,
.flags = INET_PROTOSW_PERMANENT |
INET_PROTOSW_ICSK,
};
static int __net_init tcpv6_net_init(struct net *net)
{
return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
SOCK_RAW, IPPROTO_TCP, net);
}
static void __net_exit tcpv6_net_exit(struct net *net)
{
inet_ctl_sock_destroy(net->ipv6.tcp_sk);
}
static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list)
{
inet_twsk_purge(&tcp_hashinfo, AF_INET6);
}
static struct pernet_operations tcpv6_net_ops = {
.init = tcpv6_net_init,
.exit = tcpv6_net_exit,
.exit_batch = tcpv6_net_exit_batch,
};
int __init tcpv6_init(void)
{
int ret;
ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP);
if (ret)
goto out;
/* register inet6 protocol */
ret = inet6_register_protosw(&tcpv6_protosw);
if (ret)
goto out_tcpv6_protocol;
ret = register_pernet_subsys(&tcpv6_net_ops);
if (ret)
goto out_tcpv6_protosw;
out:
return ret;
out_tcpv6_protosw:
inet6_unregister_protosw(&tcpv6_protosw);
out_tcpv6_protocol:
inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
goto out;
}
void tcpv6_exit(void)
{
unregister_pernet_subsys(&tcpv6_net_ops);
inet6_unregister_protosw(&tcpv6_protosw);
inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
}