1 // SPDX-License-Identifier: GPL-2.0-or-later
2 /*
3 * TCP over IPv6
4 * Linux INET6 implementation
5 *
6 * Authors:
7 * Pedro Roque <roque@di.fc.ul.pt>
8 *
9 * Based on:
10 * linux/net/ipv4/tcp.c
11 * linux/net/ipv4/tcp_input.c
12 * linux/net/ipv4/tcp_output.c
13 *
14 * Fixes:
15 * Hideaki YOSHIFUJI : sin6_scope_id support
16 * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which
17 * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind
18 * a single port at the same time.
19 * YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file.
20 */
21
22 #include <linux/bottom_half.h>
23 #include <linux/module.h>
24 #include <linux/errno.h>
25 #include <linux/types.h>
26 #include <linux/socket.h>
27 #include <linux/sockios.h>
28 #include <linux/net.h>
29 #include <linux/jiffies.h>
30 #include <linux/in.h>
31 #include <linux/in6.h>
32 #include <linux/netdevice.h>
33 #include <linux/init.h>
34 #include <linux/jhash.h>
35 #include <linux/ipsec.h>
36 #include <linux/times.h>
37 #include <linux/slab.h>
38 #include <linux/uaccess.h>
39 #include <linux/ipv6.h>
40 #include <linux/icmpv6.h>
41 #include <linux/random.h>
42 #include <linux/indirect_call_wrapper.h>
43
44 #include <net/tcp.h>
45 #include <net/ndisc.h>
46 #include <net/inet6_hashtables.h>
47 #include <net/inet6_connection_sock.h>
48 #include <net/ipv6.h>
49 #include <net/transp_v6.h>
50 #include <net/addrconf.h>
51 #include <net/ip6_route.h>
52 #include <net/ip6_checksum.h>
53 #include <net/inet_ecn.h>
54 #include <net/protocol.h>
55 #include <net/xfrm.h>
56 #include <net/snmp.h>
57 #include <net/dsfield.h>
58 #include <net/timewait_sock.h>
59 #include <net/inet_common.h>
60 #include <net/secure_seq.h>
61 #include <net/busy_poll.h>
62
63 #include <linux/proc_fs.h>
64 #include <linux/seq_file.h>
65
66 #include <crypto/hash.h>
67 #include <linux/scatterlist.h>
68
69 #include <trace/events/tcp.h>
70
71 static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb);
72 static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
73 struct request_sock *req);
74
75 INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
76
77 static const struct inet_connection_sock_af_ops ipv6_mapped;
78 const struct inet_connection_sock_af_ops ipv6_specific;
79 #ifdef CONFIG_TCP_MD5SIG
80 static const struct tcp_sock_af_ops tcp_sock_ipv6_specific;
81 static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
82 #else
tcp_v6_md5_do_lookup(const struct sock * sk,const struct in6_addr * addr,int l3index)83 static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk,
84 const struct in6_addr *addr,
85 int l3index)
86 {
87 return NULL;
88 }
89 #endif
90
91 /* Helper returning the inet6 address from a given tcp socket.
92 * It can be used in TCP stack instead of inet6_sk(sk).
93 * This avoids a dereference and allow compiler optimizations.
94 * It is a specialized version of inet6_sk_generic().
95 */
tcp_inet6_sk(const struct sock * sk)96 static struct ipv6_pinfo *tcp_inet6_sk(const struct sock *sk)
97 {
98 unsigned int offset = sizeof(struct tcp6_sock) - sizeof(struct ipv6_pinfo);
99
100 return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
101 }
102
inet6_sk_rx_dst_set(struct sock * sk,const struct sk_buff * skb)103 static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
104 {
105 struct dst_entry *dst = skb_dst(skb);
106
107 if (dst && dst_hold_safe(dst)) {
108 const struct rt6_info *rt = (const struct rt6_info *)dst;
109
110 rcu_assign_pointer(sk->sk_rx_dst, dst);
111 sk->sk_rx_dst_ifindex = skb->skb_iif;
112 sk->sk_rx_dst_cookie = rt6_get_cookie(rt);
113 }
114 }
115
tcp_v6_init_seq(const struct sk_buff * skb)116 static u32 tcp_v6_init_seq(const struct sk_buff *skb)
117 {
118 return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32,
119 ipv6_hdr(skb)->saddr.s6_addr32,
120 tcp_hdr(skb)->dest,
121 tcp_hdr(skb)->source);
122 }
123
tcp_v6_init_ts_off(const struct net * net,const struct sk_buff * skb)124 static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb)
125 {
126 return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32,
127 ipv6_hdr(skb)->saddr.s6_addr32);
128 }
129
tcp_v6_pre_connect(struct sock * sk,struct sockaddr * uaddr,int addr_len)130 static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
131 int addr_len)
132 {
133 /* This check is replicated from tcp_v6_connect() and intended to
134 * prevent BPF program called below from accessing bytes that are out
135 * of the bound specified by user in addr_len.
136 */
137 if (addr_len < SIN6_LEN_RFC2133)
138 return -EINVAL;
139
140 sock_owned_by_me(sk);
141
142 return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr);
143 }
144
tcp_v6_connect(struct sock * sk,struct sockaddr * uaddr,int addr_len)145 static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
146 int addr_len)
147 {
148 struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
149 struct inet_connection_sock *icsk = inet_csk(sk);
150 struct in6_addr *saddr = NULL, *final_p, final;
151 struct inet_timewait_death_row *tcp_death_row;
152 struct ipv6_pinfo *np = tcp_inet6_sk(sk);
153 struct inet_sock *inet = inet_sk(sk);
154 struct tcp_sock *tp = tcp_sk(sk);
155 struct net *net = sock_net(sk);
156 struct ipv6_txoptions *opt;
157 struct dst_entry *dst;
158 struct flowi6 fl6;
159 int addr_type;
160 int err;
161
162 if (addr_len < SIN6_LEN_RFC2133)
163 return -EINVAL;
164
165 if (usin->sin6_family != AF_INET6)
166 return -EAFNOSUPPORT;
167
168 memset(&fl6, 0, sizeof(fl6));
169
170 if (np->sndflow) {
171 fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
172 IP6_ECN_flow_init(fl6.flowlabel);
173 if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
174 struct ip6_flowlabel *flowlabel;
175 flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
176 if (IS_ERR(flowlabel))
177 return -EINVAL;
178 fl6_sock_release(flowlabel);
179 }
180 }
181
182 /*
183 * connect() to INADDR_ANY means loopback (BSD'ism).
184 */
185
186 if (ipv6_addr_any(&usin->sin6_addr)) {
187 if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
188 ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
189 &usin->sin6_addr);
190 else
191 usin->sin6_addr = in6addr_loopback;
192 }
193
194 addr_type = ipv6_addr_type(&usin->sin6_addr);
195
196 if (addr_type & IPV6_ADDR_MULTICAST)
197 return -ENETUNREACH;
198
199 if (addr_type&IPV6_ADDR_LINKLOCAL) {
200 if (addr_len >= sizeof(struct sockaddr_in6) &&
201 usin->sin6_scope_id) {
202 /* If interface is set while binding, indices
203 * must coincide.
204 */
205 if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id))
206 return -EINVAL;
207
208 sk->sk_bound_dev_if = usin->sin6_scope_id;
209 }
210
211 /* Connect to link-local address requires an interface */
212 if (!sk->sk_bound_dev_if)
213 return -EINVAL;
214 }
215
216 if (tp->rx_opt.ts_recent_stamp &&
217 !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
218 tp->rx_opt.ts_recent = 0;
219 tp->rx_opt.ts_recent_stamp = 0;
220 WRITE_ONCE(tp->write_seq, 0);
221 }
222
223 sk->sk_v6_daddr = usin->sin6_addr;
224 np->flow_label = fl6.flowlabel;
225
226 /*
227 * TCP over IPv4
228 */
229
230 if (addr_type & IPV6_ADDR_MAPPED) {
231 u32 exthdrlen = icsk->icsk_ext_hdr_len;
232 struct sockaddr_in sin;
233
234 if (ipv6_only_sock(sk))
235 return -ENETUNREACH;
236
237 sin.sin_family = AF_INET;
238 sin.sin_port = usin->sin6_port;
239 sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
240
241 /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
242 WRITE_ONCE(icsk->icsk_af_ops, &ipv6_mapped);
243 if (sk_is_mptcp(sk))
244 mptcpv6_handle_mapped(sk, true);
245 sk->sk_backlog_rcv = tcp_v4_do_rcv;
246 #ifdef CONFIG_TCP_MD5SIG
247 tp->af_specific = &tcp_sock_ipv6_mapped_specific;
248 #endif
249
250 err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
251
252 if (err) {
253 icsk->icsk_ext_hdr_len = exthdrlen;
254 /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */
255 WRITE_ONCE(icsk->icsk_af_ops, &ipv6_specific);
256 if (sk_is_mptcp(sk))
257 mptcpv6_handle_mapped(sk, false);
258 sk->sk_backlog_rcv = tcp_v6_do_rcv;
259 #ifdef CONFIG_TCP_MD5SIG
260 tp->af_specific = &tcp_sock_ipv6_specific;
261 #endif
262 goto failure;
263 }
264 np->saddr = sk->sk_v6_rcv_saddr;
265
266 return err;
267 }
268
269 if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
270 saddr = &sk->sk_v6_rcv_saddr;
271
272 fl6.flowi6_proto = IPPROTO_TCP;
273 fl6.daddr = sk->sk_v6_daddr;
274 fl6.saddr = saddr ? *saddr : np->saddr;
275 fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
276 fl6.flowi6_oif = sk->sk_bound_dev_if;
277 fl6.flowi6_mark = sk->sk_mark;
278 fl6.fl6_dport = usin->sin6_port;
279 fl6.fl6_sport = inet->inet_sport;
280 fl6.flowi6_uid = sk->sk_uid;
281
282 opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
283 final_p = fl6_update_dst(&fl6, opt, &final);
284
285 security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
286
287 dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p);
288 if (IS_ERR(dst)) {
289 err = PTR_ERR(dst);
290 goto failure;
291 }
292
293 tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
294
295 if (!saddr) {
296 saddr = &fl6.saddr;
297
298 err = inet_bhash2_update_saddr(sk, saddr, AF_INET6);
299 if (err)
300 goto failure;
301 }
302
303 /* set the source address */
304 np->saddr = *saddr;
305 inet->inet_rcv_saddr = LOOPBACK4_IPV6;
306
307 sk->sk_gso_type = SKB_GSO_TCPV6;
308 ip6_dst_store(sk, dst, NULL, NULL);
309
310 icsk->icsk_ext_hdr_len = 0;
311 if (opt)
312 icsk->icsk_ext_hdr_len = opt->opt_flen +
313 opt->opt_nflen;
314
315 tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
316
317 inet->inet_dport = usin->sin6_port;
318
319 tcp_set_state(sk, TCP_SYN_SENT);
320 err = inet6_hash_connect(tcp_death_row, sk);
321 if (err)
322 goto late_failure;
323
324 sk_set_txhash(sk);
325
326 if (likely(!tp->repair)) {
327 if (!tp->write_seq)
328 WRITE_ONCE(tp->write_seq,
329 secure_tcpv6_seq(np->saddr.s6_addr32,
330 sk->sk_v6_daddr.s6_addr32,
331 inet->inet_sport,
332 inet->inet_dport));
333 tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32,
334 sk->sk_v6_daddr.s6_addr32);
335 }
336
337 if (tcp_fastopen_defer_connect(sk, &err))
338 return err;
339 if (err)
340 goto late_failure;
341
342 err = tcp_connect(sk);
343 if (err)
344 goto late_failure;
345
346 return 0;
347
348 late_failure:
349 tcp_set_state(sk, TCP_CLOSE);
350 inet_bhash2_reset_saddr(sk);
351 failure:
352 inet->inet_dport = 0;
353 sk->sk_route_caps = 0;
354 return err;
355 }
356
tcp_v6_mtu_reduced(struct sock * sk)357 static void tcp_v6_mtu_reduced(struct sock *sk)
358 {
359 struct dst_entry *dst;
360 u32 mtu;
361
362 if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
363 return;
364
365 mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
366
367 /* Drop requests trying to increase our current mss.
368 * Check done in __ip6_rt_update_pmtu() is too late.
369 */
370 if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache)
371 return;
372
373 dst = inet6_csk_update_pmtu(sk, mtu);
374 if (!dst)
375 return;
376
377 if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
378 tcp_sync_mss(sk, dst_mtu(dst));
379 tcp_simple_retransmit(sk);
380 }
381 }
382
tcp_v6_err(struct sk_buff * skb,struct inet6_skb_parm * opt,u8 type,u8 code,int offset,__be32 info)383 static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
384 u8 type, u8 code, int offset, __be32 info)
385 {
386 const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
387 const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
388 struct net *net = dev_net(skb->dev);
389 struct request_sock *fastopen;
390 struct ipv6_pinfo *np;
391 struct tcp_sock *tp;
392 __u32 seq, snd_una;
393 struct sock *sk;
394 bool fatal;
395 int err;
396
397 sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
398 &hdr->daddr, th->dest,
399 &hdr->saddr, ntohs(th->source),
400 skb->dev->ifindex, inet6_sdif(skb));
401
402 if (!sk) {
403 __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
404 ICMP6_MIB_INERRORS);
405 return -ENOENT;
406 }
407
408 if (sk->sk_state == TCP_TIME_WAIT) {
409 inet_twsk_put(inet_twsk(sk));
410 return 0;
411 }
412 seq = ntohl(th->seq);
413 fatal = icmpv6_err_convert(type, code, &err);
414 if (sk->sk_state == TCP_NEW_SYN_RECV) {
415 tcp_req_err(sk, seq, fatal);
416 return 0;
417 }
418
419 bh_lock_sock(sk);
420 if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
421 __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
422
423 if (sk->sk_state == TCP_CLOSE)
424 goto out;
425
426 if (static_branch_unlikely(&ip6_min_hopcount)) {
427 /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */
428 if (ipv6_hdr(skb)->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) {
429 __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
430 goto out;
431 }
432 }
433
434 tp = tcp_sk(sk);
435 /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
436 fastopen = rcu_dereference(tp->fastopen_rsk);
437 snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
438 if (sk->sk_state != TCP_LISTEN &&
439 !between(seq, snd_una, tp->snd_nxt)) {
440 __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
441 goto out;
442 }
443
444 np = tcp_inet6_sk(sk);
445
446 if (type == NDISC_REDIRECT) {
447 if (!sock_owned_by_user(sk)) {
448 struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
449
450 if (dst)
451 dst->ops->redirect(dst, sk, skb);
452 }
453 goto out;
454 }
455
456 if (type == ICMPV6_PKT_TOOBIG) {
457 u32 mtu = ntohl(info);
458
459 /* We are not interested in TCP_LISTEN and open_requests
460 * (SYN-ACKs send out by Linux are always <576bytes so
461 * they should go through unfragmented).
462 */
463 if (sk->sk_state == TCP_LISTEN)
464 goto out;
465
466 if (!ip6_sk_accept_pmtu(sk))
467 goto out;
468
469 if (mtu < IPV6_MIN_MTU)
470 goto out;
471
472 WRITE_ONCE(tp->mtu_info, mtu);
473
474 if (!sock_owned_by_user(sk))
475 tcp_v6_mtu_reduced(sk);
476 else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
477 &sk->sk_tsq_flags))
478 sock_hold(sk);
479 goto out;
480 }
481
482
483 /* Might be for an request_sock */
484 switch (sk->sk_state) {
485 case TCP_SYN_SENT:
486 case TCP_SYN_RECV:
487 /* Only in fast or simultaneous open. If a fast open socket is
488 * already accepted it is treated as a connected one below.
489 */
490 if (fastopen && !fastopen->sk)
491 break;
492
493 ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th);
494
495 if (!sock_owned_by_user(sk)) {
496 sk->sk_err = err;
497 sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */
498
499 tcp_done(sk);
500 } else
501 sk->sk_err_soft = err;
502 goto out;
503 case TCP_LISTEN:
504 break;
505 default:
506 /* check if this ICMP message allows revert of backoff.
507 * (see RFC 6069)
508 */
509 if (!fastopen && type == ICMPV6_DEST_UNREACH &&
510 code == ICMPV6_NOROUTE)
511 tcp_ld_RTO_revert(sk, seq);
512 }
513
514 if (!sock_owned_by_user(sk) && np->recverr) {
515 sk->sk_err = err;
516 sk_error_report(sk);
517 } else
518 sk->sk_err_soft = err;
519
520 out:
521 bh_unlock_sock(sk);
522 sock_put(sk);
523 return 0;
524 }
525
526
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 sk_buff * syn_skb)527 static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
528 struct flowi *fl,
529 struct request_sock *req,
530 struct tcp_fastopen_cookie *foc,
531 enum tcp_synack_type synack_type,
532 struct sk_buff *syn_skb)
533 {
534 struct inet_request_sock *ireq = inet_rsk(req);
535 struct ipv6_pinfo *np = tcp_inet6_sk(sk);
536 struct ipv6_txoptions *opt;
537 struct flowi6 *fl6 = &fl->u.ip6;
538 struct sk_buff *skb;
539 int err = -ENOMEM;
540 u8 tclass;
541
542 /* First, grab a route. */
543 if (!dst && (dst = inet6_csk_route_req(sk, fl6, req,
544 IPPROTO_TCP)) == NULL)
545 goto done;
546
547 skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
548
549 if (skb) {
550 __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
551 &ireq->ir_v6_rmt_addr);
552
553 fl6->daddr = ireq->ir_v6_rmt_addr;
554 if (np->repflow && ireq->pktopts)
555 fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
556
557 tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
558 (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
559 (np->tclass & INET_ECN_MASK) :
560 np->tclass;
561
562 if (!INET_ECN_is_capable(tclass) &&
563 tcp_bpf_ca_needs_ecn((struct sock *)req))
564 tclass |= INET_ECN_ECT_0;
565
566 rcu_read_lock();
567 opt = ireq->ipv6_opt;
568 if (!opt)
569 opt = rcu_dereference(np->opt);
570 err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt,
571 tclass, sk->sk_priority);
572 rcu_read_unlock();
573 err = net_xmit_eval(err);
574 }
575
576 done:
577 return err;
578 }
579
580
tcp_v6_reqsk_destructor(struct request_sock * req)581 static void tcp_v6_reqsk_destructor(struct request_sock *req)
582 {
583 kfree(inet_rsk(req)->ipv6_opt);
584 consume_skb(inet_rsk(req)->pktopts);
585 }
586
587 #ifdef CONFIG_TCP_MD5SIG
tcp_v6_md5_do_lookup(const struct sock * sk,const struct in6_addr * addr,int l3index)588 static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk,
589 const struct in6_addr *addr,
590 int l3index)
591 {
592 return tcp_md5_do_lookup(sk, l3index,
593 (union tcp_md5_addr *)addr, AF_INET6);
594 }
595
tcp_v6_md5_lookup(const struct sock * sk,const struct sock * addr_sk)596 static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk,
597 const struct sock *addr_sk)
598 {
599 int l3index;
600
601 l3index = l3mdev_master_ifindex_by_index(sock_net(sk),
602 addr_sk->sk_bound_dev_if);
603 return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr,
604 l3index);
605 }
606
tcp_v6_parse_md5_keys(struct sock * sk,int optname,sockptr_t optval,int optlen)607 static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
608 sockptr_t optval, int optlen)
609 {
610 struct tcp_md5sig cmd;
611 struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
612 int l3index = 0;
613 u8 prefixlen;
614 u8 flags;
615
616 if (optlen < sizeof(cmd))
617 return -EINVAL;
618
619 if (copy_from_sockptr(&cmd, optval, sizeof(cmd)))
620 return -EFAULT;
621
622 if (sin6->sin6_family != AF_INET6)
623 return -EINVAL;
624
625 flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;
626
627 if (optname == TCP_MD5SIG_EXT &&
628 cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) {
629 prefixlen = cmd.tcpm_prefixlen;
630 if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) &&
631 prefixlen > 32))
632 return -EINVAL;
633 } else {
634 prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128;
635 }
636
637 if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex &&
638 cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) {
639 struct net_device *dev;
640
641 rcu_read_lock();
642 dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex);
643 if (dev && netif_is_l3_master(dev))
644 l3index = dev->ifindex;
645 rcu_read_unlock();
646
647 /* ok to reference set/not set outside of rcu;
648 * right now device MUST be an L3 master
649 */
650 if (!dev || !l3index)
651 return -EINVAL;
652 }
653
654 if (!cmd.tcpm_keylen) {
655 if (ipv6_addr_v4mapped(&sin6->sin6_addr))
656 return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
657 AF_INET, prefixlen,
658 l3index, flags);
659 return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
660 AF_INET6, prefixlen, l3index, flags);
661 }
662
663 if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
664 return -EINVAL;
665
666 if (ipv6_addr_v4mapped(&sin6->sin6_addr))
667 return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
668 AF_INET, prefixlen, l3index, flags,
669 cmd.tcpm_key, cmd.tcpm_keylen);
670
671 return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
672 AF_INET6, prefixlen, l3index, flags,
673 cmd.tcpm_key, cmd.tcpm_keylen);
674 }
675
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)676 static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp,
677 const struct in6_addr *daddr,
678 const struct in6_addr *saddr,
679 const struct tcphdr *th, int nbytes)
680 {
681 struct tcp6_pseudohdr *bp;
682 struct scatterlist sg;
683 struct tcphdr *_th;
684
685 bp = hp->scratch;
686 /* 1. TCP pseudo-header (RFC2460) */
687 bp->saddr = *saddr;
688 bp->daddr = *daddr;
689 bp->protocol = cpu_to_be32(IPPROTO_TCP);
690 bp->len = cpu_to_be32(nbytes);
691
692 _th = (struct tcphdr *)(bp + 1);
693 memcpy(_th, th, sizeof(*th));
694 _th->check = 0;
695
696 sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
697 ahash_request_set_crypt(hp->md5_req, &sg, NULL,
698 sizeof(*bp) + sizeof(*th));
699 return crypto_ahash_update(hp->md5_req);
700 }
701
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)702 static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
703 const struct in6_addr *daddr, struct in6_addr *saddr,
704 const struct tcphdr *th)
705 {
706 struct tcp_md5sig_pool *hp;
707 struct ahash_request *req;
708
709 hp = tcp_get_md5sig_pool();
710 if (!hp)
711 goto clear_hash_noput;
712 req = hp->md5_req;
713
714 if (crypto_ahash_init(req))
715 goto clear_hash;
716 if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2))
717 goto clear_hash;
718 if (tcp_md5_hash_key(hp, key))
719 goto clear_hash;
720 ahash_request_set_crypt(req, NULL, md5_hash, 0);
721 if (crypto_ahash_final(req))
722 goto clear_hash;
723
724 tcp_put_md5sig_pool();
725 return 0;
726
727 clear_hash:
728 tcp_put_md5sig_pool();
729 clear_hash_noput:
730 memset(md5_hash, 0, 16);
731 return 1;
732 }
733
tcp_v6_md5_hash_skb(char * md5_hash,const struct tcp_md5sig_key * key,const struct sock * sk,const struct sk_buff * skb)734 static int tcp_v6_md5_hash_skb(char *md5_hash,
735 const struct tcp_md5sig_key *key,
736 const struct sock *sk,
737 const struct sk_buff *skb)
738 {
739 const struct in6_addr *saddr, *daddr;
740 struct tcp_md5sig_pool *hp;
741 struct ahash_request *req;
742 const struct tcphdr *th = tcp_hdr(skb);
743
744 if (sk) { /* valid for establish/request sockets */
745 saddr = &sk->sk_v6_rcv_saddr;
746 daddr = &sk->sk_v6_daddr;
747 } else {
748 const struct ipv6hdr *ip6h = ipv6_hdr(skb);
749 saddr = &ip6h->saddr;
750 daddr = &ip6h->daddr;
751 }
752
753 hp = tcp_get_md5sig_pool();
754 if (!hp)
755 goto clear_hash_noput;
756 req = hp->md5_req;
757
758 if (crypto_ahash_init(req))
759 goto clear_hash;
760
761 if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, skb->len))
762 goto clear_hash;
763 if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
764 goto clear_hash;
765 if (tcp_md5_hash_key(hp, key))
766 goto clear_hash;
767 ahash_request_set_crypt(req, NULL, md5_hash, 0);
768 if (crypto_ahash_final(req))
769 goto clear_hash;
770
771 tcp_put_md5sig_pool();
772 return 0;
773
774 clear_hash:
775 tcp_put_md5sig_pool();
776 clear_hash_noput:
777 memset(md5_hash, 0, 16);
778 return 1;
779 }
780
781 #endif
782
tcp_v6_init_req(struct request_sock * req,const struct sock * sk_listener,struct sk_buff * skb)783 static void tcp_v6_init_req(struct request_sock *req,
784 const struct sock *sk_listener,
785 struct sk_buff *skb)
786 {
787 bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
788 struct inet_request_sock *ireq = inet_rsk(req);
789 const struct ipv6_pinfo *np = tcp_inet6_sk(sk_listener);
790
791 ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
792 ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
793
794 /* So that link locals have meaning */
795 if ((!sk_listener->sk_bound_dev_if || l3_slave) &&
796 ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
797 ireq->ir_iif = tcp_v6_iif(skb);
798
799 if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
800 (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) ||
801 np->rxopt.bits.rxinfo ||
802 np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
803 np->rxopt.bits.rxohlim || np->repflow)) {
804 refcount_inc(&skb->users);
805 ireq->pktopts = skb;
806 }
807 }
808
tcp_v6_route_req(const struct sock * sk,struct sk_buff * skb,struct flowi * fl,struct request_sock * req)809 static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
810 struct sk_buff *skb,
811 struct flowi *fl,
812 struct request_sock *req)
813 {
814 tcp_v6_init_req(req, sk, skb);
815
816 if (security_inet_conn_request(sk, skb, req))
817 return NULL;
818
819 return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP);
820 }
821
822 struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
823 .family = AF_INET6,
824 .obj_size = sizeof(struct tcp6_request_sock),
825 .rtx_syn_ack = tcp_rtx_synack,
826 .send_ack = tcp_v6_reqsk_send_ack,
827 .destructor = tcp_v6_reqsk_destructor,
828 .send_reset = tcp_v6_send_reset,
829 .syn_ack_timeout = tcp_syn_ack_timeout,
830 };
831
832 const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
833 .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) -
834 sizeof(struct ipv6hdr),
835 #ifdef CONFIG_TCP_MD5SIG
836 .req_md5_lookup = tcp_v6_md5_lookup,
837 .calc_md5_hash = tcp_v6_md5_hash_skb,
838 #endif
839 #ifdef CONFIG_SYN_COOKIES
840 .cookie_init_seq = cookie_v6_init_sequence,
841 #endif
842 .route_req = tcp_v6_route_req,
843 .init_seq = tcp_v6_init_seq,
844 .init_ts_off = tcp_v6_init_ts_off,
845 .send_synack = tcp_v6_send_synack,
846 };
847
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,u32 priority,u32 txhash)848 static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq,
849 u32 ack, u32 win, u32 tsval, u32 tsecr,
850 int oif, struct tcp_md5sig_key *key, int rst,
851 u8 tclass, __be32 label, u32 priority, u32 txhash)
852 {
853 const struct tcphdr *th = tcp_hdr(skb);
854 struct tcphdr *t1;
855 struct sk_buff *buff;
856 struct flowi6 fl6;
857 struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
858 struct sock *ctl_sk = net->ipv6.tcp_sk;
859 unsigned int tot_len = sizeof(struct tcphdr);
860 __be32 mrst = 0, *topt;
861 struct dst_entry *dst;
862 __u32 mark = 0;
863
864 if (tsecr)
865 tot_len += TCPOLEN_TSTAMP_ALIGNED;
866 #ifdef CONFIG_TCP_MD5SIG
867 if (key)
868 tot_len += TCPOLEN_MD5SIG_ALIGNED;
869 #endif
870
871 #ifdef CONFIG_MPTCP
872 if (rst && !key) {
873 mrst = mptcp_reset_option(skb);
874
875 if (mrst)
876 tot_len += sizeof(__be32);
877 }
878 #endif
879
880 buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
881 if (!buff)
882 return;
883
884 skb_reserve(buff, MAX_TCP_HEADER);
885
886 t1 = skb_push(buff, tot_len);
887 skb_reset_transport_header(buff);
888
889 /* Swap the send and the receive. */
890 memset(t1, 0, sizeof(*t1));
891 t1->dest = th->source;
892 t1->source = th->dest;
893 t1->doff = tot_len / 4;
894 t1->seq = htonl(seq);
895 t1->ack_seq = htonl(ack);
896 t1->ack = !rst || !th->ack;
897 t1->rst = rst;
898 t1->window = htons(win);
899
900 topt = (__be32 *)(t1 + 1);
901
902 if (tsecr) {
903 *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
904 (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
905 *topt++ = htonl(tsval);
906 *topt++ = htonl(tsecr);
907 }
908
909 if (mrst)
910 *topt++ = mrst;
911
912 #ifdef CONFIG_TCP_MD5SIG
913 if (key) {
914 *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
915 (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
916 tcp_v6_md5_hash_hdr((__u8 *)topt, key,
917 &ipv6_hdr(skb)->saddr,
918 &ipv6_hdr(skb)->daddr, t1);
919 }
920 #endif
921
922 memset(&fl6, 0, sizeof(fl6));
923 fl6.daddr = ipv6_hdr(skb)->saddr;
924 fl6.saddr = ipv6_hdr(skb)->daddr;
925 fl6.flowlabel = label;
926
927 buff->ip_summed = CHECKSUM_PARTIAL;
928
929 __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
930
931 fl6.flowi6_proto = IPPROTO_TCP;
932 if (rt6_need_strict(&fl6.daddr) && !oif)
933 fl6.flowi6_oif = tcp_v6_iif(skb);
934 else {
935 if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
936 oif = skb->skb_iif;
937
938 fl6.flowi6_oif = oif;
939 }
940
941 if (sk) {
942 if (sk->sk_state == TCP_TIME_WAIT)
943 mark = inet_twsk(sk)->tw_mark;
944 else
945 mark = sk->sk_mark;
946 skb_set_delivery_time(buff, tcp_transmit_time(sk), true);
947 }
948 if (txhash) {
949 /* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */
950 skb_set_hash(buff, txhash, PKT_HASH_TYPE_L4);
951 }
952 fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark;
953 fl6.fl6_dport = t1->dest;
954 fl6.fl6_sport = t1->source;
955 fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
956 security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
957
958 /* Pass a socket to ip6_dst_lookup either it is for RST
959 * Underlying function will use this to retrieve the network
960 * namespace
961 */
962 if (sk && sk->sk_state != TCP_TIME_WAIT)
963 dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/
964 else
965 dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL);
966 if (!IS_ERR(dst)) {
967 skb_dst_set(buff, dst);
968 ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL,
969 tclass & ~INET_ECN_MASK, priority);
970 TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
971 if (rst)
972 TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
973 return;
974 }
975
976 kfree_skb(buff);
977 }
978
tcp_v6_send_reset(const struct sock * sk,struct sk_buff * skb)979 static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
980 {
981 const struct tcphdr *th = tcp_hdr(skb);
982 struct ipv6hdr *ipv6h = ipv6_hdr(skb);
983 u32 seq = 0, ack_seq = 0;
984 struct tcp_md5sig_key *key = NULL;
985 #ifdef CONFIG_TCP_MD5SIG
986 const __u8 *hash_location = NULL;
987 unsigned char newhash[16];
988 int genhash;
989 struct sock *sk1 = NULL;
990 #endif
991 __be32 label = 0;
992 u32 priority = 0;
993 struct net *net;
994 u32 txhash = 0;
995 int oif = 0;
996
997 if (th->rst)
998 return;
999
1000 /* If sk not NULL, it means we did a successful lookup and incoming
1001 * route had to be correct. prequeue might have dropped our dst.
1002 */
1003 if (!sk && !ipv6_unicast_destination(skb))
1004 return;
1005
1006 net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
1007 #ifdef CONFIG_TCP_MD5SIG
1008 rcu_read_lock();
1009 hash_location = tcp_parse_md5sig_option(th);
1010 if (sk && sk_fullsock(sk)) {
1011 int l3index;
1012
1013 /* sdif set, means packet ingressed via a device
1014 * in an L3 domain and inet_iif is set to it.
1015 */
1016 l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0;
1017 key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr, l3index);
1018 } else if (hash_location) {
1019 int dif = tcp_v6_iif_l3_slave(skb);
1020 int sdif = tcp_v6_sdif(skb);
1021 int l3index;
1022
1023 /*
1024 * active side is lost. Try to find listening socket through
1025 * source port, and then find md5 key through listening socket.
1026 * we are not loose security here:
1027 * Incoming packet is checked with md5 hash with finding key,
1028 * no RST generated if md5 hash doesn't match.
1029 */
1030 sk1 = inet6_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo,
1031 NULL, 0, &ipv6h->saddr, th->source,
1032 &ipv6h->daddr, ntohs(th->source),
1033 dif, sdif);
1034 if (!sk1)
1035 goto out;
1036
1037 /* sdif set, means packet ingressed via a device
1038 * in an L3 domain and dif is set to it.
1039 */
1040 l3index = tcp_v6_sdif(skb) ? dif : 0;
1041
1042 key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr, l3index);
1043 if (!key)
1044 goto out;
1045
1046 genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb);
1047 if (genhash || memcmp(hash_location, newhash, 16) != 0)
1048 goto out;
1049 }
1050 #endif
1051
1052 if (th->ack)
1053 seq = ntohl(th->ack_seq);
1054 else
1055 ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len -
1056 (th->doff << 2);
1057
1058 if (sk) {
1059 oif = sk->sk_bound_dev_if;
1060 if (sk_fullsock(sk)) {
1061 const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
1062
1063 trace_tcp_send_reset(sk, skb);
1064 if (np->repflow)
1065 label = ip6_flowlabel(ipv6h);
1066 priority = sk->sk_priority;
1067 txhash = sk->sk_hash;
1068 }
1069 if (sk->sk_state == TCP_TIME_WAIT) {
1070 label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel);
1071 priority = inet_twsk(sk)->tw_priority;
1072 txhash = inet_twsk(sk)->tw_txhash;
1073 }
1074 } else {
1075 if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_TCP_RESET)
1076 label = ip6_flowlabel(ipv6h);
1077 }
1078
1079 tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1,
1080 ipv6_get_dsfield(ipv6h), label, priority, txhash);
1081
1082 #ifdef CONFIG_TCP_MD5SIG
1083 out:
1084 rcu_read_unlock();
1085 #endif
1086 }
1087
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,u32 priority,u32 txhash)1088 static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
1089 u32 ack, u32 win, u32 tsval, u32 tsecr, int oif,
1090 struct tcp_md5sig_key *key, u8 tclass,
1091 __be32 label, u32 priority, u32 txhash)
1092 {
1093 tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
1094 tclass, label, priority, txhash);
1095 }
1096
tcp_v6_timewait_ack(struct sock * sk,struct sk_buff * skb)1097 static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
1098 {
1099 struct inet_timewait_sock *tw = inet_twsk(sk);
1100 struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
1101
1102 tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
1103 tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
1104 tcp_time_stamp_raw() + tcptw->tw_ts_offset,
1105 tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
1106 tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority,
1107 tw->tw_txhash);
1108
1109 inet_twsk_put(tw);
1110 }
1111
tcp_v6_reqsk_send_ack(const struct sock * sk,struct sk_buff * skb,struct request_sock * req)1112 static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
1113 struct request_sock *req)
1114 {
1115 int l3index;
1116
1117 l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0;
1118
1119 /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
1120 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
1121 */
1122 /* RFC 7323 2.3
1123 * The window field (SEG.WND) of every outgoing segment, with the
1124 * exception of <SYN> segments, MUST be right-shifted by
1125 * Rcv.Wind.Shift bits:
1126 */
1127 tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
1128 tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
1129 tcp_rsk(req)->rcv_nxt,
1130 req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
1131 tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
1132 req->ts_recent, sk->sk_bound_dev_if,
1133 tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index),
1134 ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority,
1135 tcp_rsk(req)->txhash);
1136 }
1137
1138
tcp_v6_cookie_check(struct sock * sk,struct sk_buff * skb)1139 static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb)
1140 {
1141 #ifdef CONFIG_SYN_COOKIES
1142 const struct tcphdr *th = tcp_hdr(skb);
1143
1144 if (!th->syn)
1145 sk = cookie_v6_check(sk, skb);
1146 #endif
1147 return sk;
1148 }
1149
tcp_v6_get_syncookie(struct sock * sk,struct ipv6hdr * iph,struct tcphdr * th,u32 * cookie)1150 u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
1151 struct tcphdr *th, u32 *cookie)
1152 {
1153 u16 mss = 0;
1154 #ifdef CONFIG_SYN_COOKIES
1155 mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops,
1156 &tcp_request_sock_ipv6_ops, sk, th);
1157 if (mss) {
1158 *cookie = __cookie_v6_init_sequence(iph, th, &mss);
1159 tcp_synq_overflow(sk);
1160 }
1161 #endif
1162 return mss;
1163 }
1164
tcp_v6_conn_request(struct sock * sk,struct sk_buff * skb)1165 static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
1166 {
1167 if (skb->protocol == htons(ETH_P_IP))
1168 return tcp_v4_conn_request(sk, skb);
1169
1170 if (!ipv6_unicast_destination(skb))
1171 goto drop;
1172
1173 if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
1174 __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
1175 return 0;
1176 }
1177
1178 return tcp_conn_request(&tcp6_request_sock_ops,
1179 &tcp_request_sock_ipv6_ops, sk, skb);
1180
1181 drop:
1182 tcp_listendrop(sk);
1183 return 0; /* don't send reset */
1184 }
1185
tcp_v6_restore_cb(struct sk_buff * skb)1186 static void tcp_v6_restore_cb(struct sk_buff *skb)
1187 {
1188 /* We need to move header back to the beginning if xfrm6_policy_check()
1189 * and tcp_v6_fill_cb() are going to be called again.
1190 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
1191 */
1192 memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
1193 sizeof(struct inet6_skb_parm));
1194 }
1195
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)1196 static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
1197 struct request_sock *req,
1198 struct dst_entry *dst,
1199 struct request_sock *req_unhash,
1200 bool *own_req)
1201 {
1202 struct inet_request_sock *ireq;
1203 struct ipv6_pinfo *newnp;
1204 const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
1205 struct ipv6_txoptions *opt;
1206 struct inet_sock *newinet;
1207 bool found_dup_sk = false;
1208 struct tcp_sock *newtp;
1209 struct sock *newsk;
1210 #ifdef CONFIG_TCP_MD5SIG
1211 struct tcp_md5sig_key *key;
1212 int l3index;
1213 #endif
1214 struct flowi6 fl6;
1215
1216 if (skb->protocol == htons(ETH_P_IP)) {
1217 /*
1218 * v6 mapped
1219 */
1220
1221 newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst,
1222 req_unhash, own_req);
1223
1224 if (!newsk)
1225 return NULL;
1226
1227 inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
1228
1229 newnp = tcp_inet6_sk(newsk);
1230 newtp = tcp_sk(newsk);
1231
1232 memcpy(newnp, np, sizeof(struct ipv6_pinfo));
1233
1234 newnp->saddr = newsk->sk_v6_rcv_saddr;
1235
1236 inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
1237 if (sk_is_mptcp(newsk))
1238 mptcpv6_handle_mapped(newsk, true);
1239 newsk->sk_backlog_rcv = tcp_v4_do_rcv;
1240 #ifdef CONFIG_TCP_MD5SIG
1241 newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
1242 #endif
1243
1244 newnp->ipv6_mc_list = NULL;
1245 newnp->ipv6_ac_list = NULL;
1246 newnp->ipv6_fl_list = NULL;
1247 newnp->pktoptions = NULL;
1248 newnp->opt = NULL;
1249 newnp->mcast_oif = inet_iif(skb);
1250 newnp->mcast_hops = ip_hdr(skb)->ttl;
1251 newnp->rcv_flowinfo = 0;
1252 if (np->repflow)
1253 newnp->flow_label = 0;
1254
1255 /*
1256 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
1257 * here, tcp_create_openreq_child now does this for us, see the comment in
1258 * that function for the gory details. -acme
1259 */
1260
1261 /* It is tricky place. Until this moment IPv4 tcp
1262 worked with IPv6 icsk.icsk_af_ops.
1263 Sync it now.
1264 */
1265 tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
1266
1267 return newsk;
1268 }
1269
1270 ireq = inet_rsk(req);
1271
1272 if (sk_acceptq_is_full(sk))
1273 goto out_overflow;
1274
1275 if (!dst) {
1276 dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP);
1277 if (!dst)
1278 goto out;
1279 }
1280
1281 newsk = tcp_create_openreq_child(sk, req, skb);
1282 if (!newsk)
1283 goto out_nonewsk;
1284
1285 /*
1286 * No need to charge this sock to the relevant IPv6 refcnt debug socks
1287 * count here, tcp_create_openreq_child now does this for us, see the
1288 * comment in that function for the gory details. -acme
1289 */
1290
1291 newsk->sk_gso_type = SKB_GSO_TCPV6;
1292 ip6_dst_store(newsk, dst, NULL, NULL);
1293 inet6_sk_rx_dst_set(newsk, skb);
1294
1295 inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
1296
1297 newtp = tcp_sk(newsk);
1298 newinet = inet_sk(newsk);
1299 newnp = tcp_inet6_sk(newsk);
1300
1301 memcpy(newnp, np, sizeof(struct ipv6_pinfo));
1302
1303 newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
1304 newnp->saddr = ireq->ir_v6_loc_addr;
1305 newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
1306 newsk->sk_bound_dev_if = ireq->ir_iif;
1307
1308 /* Now IPv6 options...
1309
1310 First: no IPv4 options.
1311 */
1312 newinet->inet_opt = NULL;
1313 newnp->ipv6_mc_list = NULL;
1314 newnp->ipv6_ac_list = NULL;
1315 newnp->ipv6_fl_list = NULL;
1316
1317 /* Clone RX bits */
1318 newnp->rxopt.all = np->rxopt.all;
1319
1320 newnp->pktoptions = NULL;
1321 newnp->opt = NULL;
1322 newnp->mcast_oif = tcp_v6_iif(skb);
1323 newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
1324 newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
1325 if (np->repflow)
1326 newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
1327
1328 /* Set ToS of the new socket based upon the value of incoming SYN.
1329 * ECT bits are set later in tcp_init_transfer().
1330 */
1331 if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
1332 newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
1333
1334 /* Clone native IPv6 options from listening socket (if any)
1335
1336 Yes, keeping reference count would be much more clever,
1337 but we make one more one thing there: reattach optmem
1338 to newsk.
1339 */
1340 opt = ireq->ipv6_opt;
1341 if (!opt)
1342 opt = rcu_dereference(np->opt);
1343 if (opt) {
1344 opt = ipv6_dup_options(newsk, opt);
1345 RCU_INIT_POINTER(newnp->opt, opt);
1346 }
1347 inet_csk(newsk)->icsk_ext_hdr_len = 0;
1348 if (opt)
1349 inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
1350 opt->opt_flen;
1351
1352 tcp_ca_openreq_child(newsk, dst);
1353
1354 tcp_sync_mss(newsk, dst_mtu(dst));
1355 newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
1356
1357 tcp_initialize_rcv_mss(newsk);
1358
1359 newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
1360 newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
1361
1362 #ifdef CONFIG_TCP_MD5SIG
1363 l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif);
1364
1365 /* Copy over the MD5 key from the original socket */
1366 key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr, l3index);
1367 if (key) {
1368 const union tcp_md5_addr *addr;
1369
1370 addr = (union tcp_md5_addr *)&newsk->sk_v6_daddr;
1371 if (tcp_md5_key_copy(newsk, addr, AF_INET6, 128, l3index, key)) {
1372 inet_csk_prepare_forced_close(newsk);
1373 tcp_done(newsk);
1374 goto out;
1375 }
1376 }
1377 #endif
1378
1379 if (__inet_inherit_port(sk, newsk) < 0) {
1380 inet_csk_prepare_forced_close(newsk);
1381 tcp_done(newsk);
1382 goto out;
1383 }
1384 *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
1385 &found_dup_sk);
1386 if (*own_req) {
1387 tcp_move_syn(newtp, req);
1388
1389 /* Clone pktoptions received with SYN, if we own the req */
1390 if (ireq->pktopts) {
1391 newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk);
1392 consume_skb(ireq->pktopts);
1393 ireq->pktopts = NULL;
1394 if (newnp->pktoptions)
1395 tcp_v6_restore_cb(newnp->pktoptions);
1396 }
1397 } else {
1398 if (!req_unhash && found_dup_sk) {
1399 /* This code path should only be executed in the
1400 * syncookie case only
1401 */
1402 bh_unlock_sock(newsk);
1403 sock_put(newsk);
1404 newsk = NULL;
1405 }
1406 }
1407
1408 return newsk;
1409
1410 out_overflow:
1411 __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
1412 out_nonewsk:
1413 dst_release(dst);
1414 out:
1415 tcp_listendrop(sk);
1416 return NULL;
1417 }
1418
1419 INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *,
1420 u32));
1421 /* The socket must have it's spinlock held when we get
1422 * here, unless it is a TCP_LISTEN socket.
1423 *
1424 * We have a potential double-lock case here, so even when
1425 * doing backlog processing we use the BH locking scheme.
1426 * This is because we cannot sleep with the original spinlock
1427 * held.
1428 */
1429 INDIRECT_CALLABLE_SCOPE
tcp_v6_do_rcv(struct sock * sk,struct sk_buff * skb)1430 int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
1431 {
1432 struct ipv6_pinfo *np = tcp_inet6_sk(sk);
1433 struct sk_buff *opt_skb = NULL;
1434 enum skb_drop_reason reason;
1435 struct tcp_sock *tp;
1436
1437 /* Imagine: socket is IPv6. IPv4 packet arrives,
1438 goes to IPv4 receive handler and backlogged.
1439 From backlog it always goes here. Kerboom...
1440 Fortunately, tcp_rcv_established and rcv_established
1441 handle them correctly, but it is not case with
1442 tcp_v6_hnd_req and tcp_v6_send_reset(). --ANK
1443 */
1444
1445 if (skb->protocol == htons(ETH_P_IP))
1446 return tcp_v4_do_rcv(sk, skb);
1447
1448 /*
1449 * socket locking is here for SMP purposes as backlog rcv
1450 * is currently called with bh processing disabled.
1451 */
1452
1453 /* Do Stevens' IPV6_PKTOPTIONS.
1454
1455 Yes, guys, it is the only place in our code, where we
1456 may make it not affecting IPv4.
1457 The rest of code is protocol independent,
1458 and I do not like idea to uglify IPv4.
1459
1460 Actually, all the idea behind IPV6_PKTOPTIONS
1461 looks not very well thought. For now we latch
1462 options, received in the last packet, enqueued
1463 by tcp. Feel free to propose better solution.
1464 --ANK (980728)
1465 */
1466 if (np->rxopt.all)
1467 opt_skb = skb_clone_and_charge_r(skb, sk);
1468
1469 reason = SKB_DROP_REASON_NOT_SPECIFIED;
1470 if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
1471 struct dst_entry *dst;
1472
1473 dst = rcu_dereference_protected(sk->sk_rx_dst,
1474 lockdep_sock_is_held(sk));
1475
1476 sock_rps_save_rxhash(sk, skb);
1477 sk_mark_napi_id(sk, skb);
1478 if (dst) {
1479 if (sk->sk_rx_dst_ifindex != skb->skb_iif ||
1480 INDIRECT_CALL_1(dst->ops->check, ip6_dst_check,
1481 dst, sk->sk_rx_dst_cookie) == NULL) {
1482 RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
1483 dst_release(dst);
1484 }
1485 }
1486
1487 tcp_rcv_established(sk, skb);
1488 if (opt_skb)
1489 goto ipv6_pktoptions;
1490 return 0;
1491 }
1492
1493 if (tcp_checksum_complete(skb))
1494 goto csum_err;
1495
1496 if (sk->sk_state == TCP_LISTEN) {
1497 struct sock *nsk = tcp_v6_cookie_check(sk, skb);
1498
1499 if (!nsk)
1500 goto discard;
1501
1502 if (nsk != sk) {
1503 if (tcp_child_process(sk, nsk, skb))
1504 goto reset;
1505 if (opt_skb)
1506 __kfree_skb(opt_skb);
1507 return 0;
1508 }
1509 } else
1510 sock_rps_save_rxhash(sk, skb);
1511
1512 if (tcp_rcv_state_process(sk, skb))
1513 goto reset;
1514 if (opt_skb)
1515 goto ipv6_pktoptions;
1516 return 0;
1517
1518 reset:
1519 tcp_v6_send_reset(sk, skb);
1520 discard:
1521 if (opt_skb)
1522 __kfree_skb(opt_skb);
1523 kfree_skb_reason(skb, reason);
1524 return 0;
1525 csum_err:
1526 reason = SKB_DROP_REASON_TCP_CSUM;
1527 trace_tcp_bad_csum(skb);
1528 TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
1529 TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
1530 goto discard;
1531
1532
1533 ipv6_pktoptions:
1534 /* Do you ask, what is it?
1535
1536 1. skb was enqueued by tcp.
1537 2. skb is added to tail of read queue, rather than out of order.
1538 3. socket is not in passive state.
1539 4. Finally, it really contains options, which user wants to receive.
1540 */
1541 tp = tcp_sk(sk);
1542 if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt &&
1543 !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
1544 if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
1545 np->mcast_oif = tcp_v6_iif(opt_skb);
1546 if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
1547 np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
1548 if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
1549 np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
1550 if (np->repflow)
1551 np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
1552 if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
1553 tcp_v6_restore_cb(opt_skb);
1554 opt_skb = xchg(&np->pktoptions, opt_skb);
1555 } else {
1556 __kfree_skb(opt_skb);
1557 opt_skb = xchg(&np->pktoptions, NULL);
1558 }
1559 }
1560
1561 consume_skb(opt_skb);
1562 return 0;
1563 }
1564
tcp_v6_fill_cb(struct sk_buff * skb,const struct ipv6hdr * hdr,const struct tcphdr * th)1565 static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
1566 const struct tcphdr *th)
1567 {
1568 /* This is tricky: we move IP6CB at its correct location into
1569 * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because
1570 * _decode_session6() uses IP6CB().
1571 * barrier() makes sure compiler won't play aliasing games.
1572 */
1573 memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb),
1574 sizeof(struct inet6_skb_parm));
1575 barrier();
1576
1577 TCP_SKB_CB(skb)->seq = ntohl(th->seq);
1578 TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
1579 skb->len - th->doff*4);
1580 TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
1581 TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
1582 TCP_SKB_CB(skb)->tcp_tw_isn = 0;
1583 TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
1584 TCP_SKB_CB(skb)->sacked = 0;
1585 TCP_SKB_CB(skb)->has_rxtstamp =
1586 skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
1587 }
1588
tcp_v6_rcv(struct sk_buff * skb)1589 INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
1590 {
1591 enum skb_drop_reason drop_reason;
1592 int sdif = inet6_sdif(skb);
1593 int dif = inet6_iif(skb);
1594 const struct tcphdr *th;
1595 const struct ipv6hdr *hdr;
1596 bool refcounted;
1597 struct sock *sk;
1598 int ret;
1599 struct net *net = dev_net(skb->dev);
1600
1601 drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
1602 if (skb->pkt_type != PACKET_HOST)
1603 goto discard_it;
1604
1605 /*
1606 * Count it even if it's bad.
1607 */
1608 __TCP_INC_STATS(net, TCP_MIB_INSEGS);
1609
1610 if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
1611 goto discard_it;
1612
1613 th = (const struct tcphdr *)skb->data;
1614
1615 if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) {
1616 drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL;
1617 goto bad_packet;
1618 }
1619 if (!pskb_may_pull(skb, th->doff*4))
1620 goto discard_it;
1621
1622 if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo))
1623 goto csum_error;
1624
1625 th = (const struct tcphdr *)skb->data;
1626 hdr = ipv6_hdr(skb);
1627
1628 lookup:
1629 sk = __inet6_lookup_skb(net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th),
1630 th->source, th->dest, inet6_iif(skb), sdif,
1631 &refcounted);
1632 if (!sk)
1633 goto no_tcp_socket;
1634
1635 process:
1636 if (sk->sk_state == TCP_TIME_WAIT)
1637 goto do_time_wait;
1638
1639 if (sk->sk_state == TCP_NEW_SYN_RECV) {
1640 struct request_sock *req = inet_reqsk(sk);
1641 bool req_stolen = false;
1642 struct sock *nsk;
1643
1644 sk = req->rsk_listener;
1645 drop_reason = tcp_inbound_md5_hash(sk, skb,
1646 &hdr->saddr, &hdr->daddr,
1647 AF_INET6, dif, sdif);
1648 if (drop_reason) {
1649 sk_drops_add(sk, skb);
1650 reqsk_put(req);
1651 goto discard_it;
1652 }
1653 if (tcp_checksum_complete(skb)) {
1654 reqsk_put(req);
1655 goto csum_error;
1656 }
1657 if (unlikely(sk->sk_state != TCP_LISTEN)) {
1658 nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb);
1659 if (!nsk) {
1660 inet_csk_reqsk_queue_drop_and_put(sk, req);
1661 goto lookup;
1662 }
1663 sk = nsk;
1664 /* reuseport_migrate_sock() has already held one sk_refcnt
1665 * before returning.
1666 */
1667 } else {
1668 sock_hold(sk);
1669 }
1670 refcounted = true;
1671 nsk = NULL;
1672 if (!tcp_filter(sk, skb)) {
1673 th = (const struct tcphdr *)skb->data;
1674 hdr = ipv6_hdr(skb);
1675 tcp_v6_fill_cb(skb, hdr, th);
1676 nsk = tcp_check_req(sk, skb, req, false, &req_stolen);
1677 } else {
1678 drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
1679 }
1680 if (!nsk) {
1681 reqsk_put(req);
1682 if (req_stolen) {
1683 /* Another cpu got exclusive access to req
1684 * and created a full blown socket.
1685 * Try to feed this packet to this socket
1686 * instead of discarding it.
1687 */
1688 tcp_v6_restore_cb(skb);
1689 sock_put(sk);
1690 goto lookup;
1691 }
1692 goto discard_and_relse;
1693 }
1694 if (nsk == sk) {
1695 reqsk_put(req);
1696 tcp_v6_restore_cb(skb);
1697 } else if (tcp_child_process(sk, nsk, skb)) {
1698 tcp_v6_send_reset(nsk, skb);
1699 goto discard_and_relse;
1700 } else {
1701 sock_put(sk);
1702 return 0;
1703 }
1704 }
1705
1706 if (static_branch_unlikely(&ip6_min_hopcount)) {
1707 /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */
1708 if (unlikely(hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount))) {
1709 __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
1710 drop_reason = SKB_DROP_REASON_TCP_MINTTL;
1711 goto discard_and_relse;
1712 }
1713 }
1714
1715 if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
1716 drop_reason = SKB_DROP_REASON_XFRM_POLICY;
1717 goto discard_and_relse;
1718 }
1719
1720 drop_reason = tcp_inbound_md5_hash(sk, skb, &hdr->saddr, &hdr->daddr,
1721 AF_INET6, dif, sdif);
1722 if (drop_reason)
1723 goto discard_and_relse;
1724
1725 if (tcp_filter(sk, skb)) {
1726 drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
1727 goto discard_and_relse;
1728 }
1729 th = (const struct tcphdr *)skb->data;
1730 hdr = ipv6_hdr(skb);
1731 tcp_v6_fill_cb(skb, hdr, th);
1732
1733 skb->dev = NULL;
1734
1735 if (sk->sk_state == TCP_LISTEN) {
1736 ret = tcp_v6_do_rcv(sk, skb);
1737 goto put_and_return;
1738 }
1739
1740 sk_incoming_cpu_update(sk);
1741
1742 bh_lock_sock_nested(sk);
1743 tcp_segs_in(tcp_sk(sk), skb);
1744 ret = 0;
1745 if (!sock_owned_by_user(sk)) {
1746 ret = tcp_v6_do_rcv(sk, skb);
1747 } else {
1748 if (tcp_add_backlog(sk, skb, &drop_reason))
1749 goto discard_and_relse;
1750 }
1751 bh_unlock_sock(sk);
1752 put_and_return:
1753 if (refcounted)
1754 sock_put(sk);
1755 return ret ? -1 : 0;
1756
1757 no_tcp_socket:
1758 drop_reason = SKB_DROP_REASON_NO_SOCKET;
1759 if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
1760 goto discard_it;
1761
1762 tcp_v6_fill_cb(skb, hdr, th);
1763
1764 if (tcp_checksum_complete(skb)) {
1765 csum_error:
1766 drop_reason = SKB_DROP_REASON_TCP_CSUM;
1767 trace_tcp_bad_csum(skb);
1768 __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
1769 bad_packet:
1770 __TCP_INC_STATS(net, TCP_MIB_INERRS);
1771 } else {
1772 tcp_v6_send_reset(NULL, skb);
1773 }
1774
1775 discard_it:
1776 SKB_DR_OR(drop_reason, NOT_SPECIFIED);
1777 kfree_skb_reason(skb, drop_reason);
1778 return 0;
1779
1780 discard_and_relse:
1781 sk_drops_add(sk, skb);
1782 if (refcounted)
1783 sock_put(sk);
1784 goto discard_it;
1785
1786 do_time_wait:
1787 if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
1788 drop_reason = SKB_DROP_REASON_XFRM_POLICY;
1789 inet_twsk_put(inet_twsk(sk));
1790 goto discard_it;
1791 }
1792
1793 tcp_v6_fill_cb(skb, hdr, th);
1794
1795 if (tcp_checksum_complete(skb)) {
1796 inet_twsk_put(inet_twsk(sk));
1797 goto csum_error;
1798 }
1799
1800 switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
1801 case TCP_TW_SYN:
1802 {
1803 struct sock *sk2;
1804
1805 sk2 = inet6_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo,
1806 skb, __tcp_hdrlen(th),
1807 &ipv6_hdr(skb)->saddr, th->source,
1808 &ipv6_hdr(skb)->daddr,
1809 ntohs(th->dest),
1810 tcp_v6_iif_l3_slave(skb),
1811 sdif);
1812 if (sk2) {
1813 struct inet_timewait_sock *tw = inet_twsk(sk);
1814 inet_twsk_deschedule_put(tw);
1815 sk = sk2;
1816 tcp_v6_restore_cb(skb);
1817 refcounted = false;
1818 goto process;
1819 }
1820 }
1821 /* to ACK */
1822 fallthrough;
1823 case TCP_TW_ACK:
1824 tcp_v6_timewait_ack(sk, skb);
1825 break;
1826 case TCP_TW_RST:
1827 tcp_v6_send_reset(sk, skb);
1828 inet_twsk_deschedule_put(inet_twsk(sk));
1829 goto discard_it;
1830 case TCP_TW_SUCCESS:
1831 ;
1832 }
1833 goto discard_it;
1834 }
1835
tcp_v6_early_demux(struct sk_buff * skb)1836 void tcp_v6_early_demux(struct sk_buff *skb)
1837 {
1838 struct net *net = dev_net(skb->dev);
1839 const struct ipv6hdr *hdr;
1840 const struct tcphdr *th;
1841 struct sock *sk;
1842
1843 if (skb->pkt_type != PACKET_HOST)
1844 return;
1845
1846 if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
1847 return;
1848
1849 hdr = ipv6_hdr(skb);
1850 th = tcp_hdr(skb);
1851
1852 if (th->doff < sizeof(struct tcphdr) / 4)
1853 return;
1854
1855 /* Note : We use inet6_iif() here, not tcp_v6_iif() */
1856 sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
1857 &hdr->saddr, th->source,
1858 &hdr->daddr, ntohs(th->dest),
1859 inet6_iif(skb), inet6_sdif(skb));
1860 if (sk) {
1861 skb->sk = sk;
1862 skb->destructor = sock_edemux;
1863 if (sk_fullsock(sk)) {
1864 struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
1865
1866 if (dst)
1867 dst = dst_check(dst, sk->sk_rx_dst_cookie);
1868 if (dst &&
1869 sk->sk_rx_dst_ifindex == skb->skb_iif)
1870 skb_dst_set_noref(skb, dst);
1871 }
1872 }
1873 }
1874
1875 static struct timewait_sock_ops tcp6_timewait_sock_ops = {
1876 .twsk_obj_size = sizeof(struct tcp6_timewait_sock),
1877 .twsk_unique = tcp_twsk_unique,
1878 .twsk_destructor = tcp_twsk_destructor,
1879 };
1880
tcp_v6_send_check(struct sock * sk,struct sk_buff * skb)1881 INDIRECT_CALLABLE_SCOPE void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
1882 {
1883 __tcp_v6_send_check(skb, &sk->sk_v6_rcv_saddr, &sk->sk_v6_daddr);
1884 }
1885
1886 const struct inet_connection_sock_af_ops ipv6_specific = {
1887 .queue_xmit = inet6_csk_xmit,
1888 .send_check = tcp_v6_send_check,
1889 .rebuild_header = inet6_sk_rebuild_header,
1890 .sk_rx_dst_set = inet6_sk_rx_dst_set,
1891 .conn_request = tcp_v6_conn_request,
1892 .syn_recv_sock = tcp_v6_syn_recv_sock,
1893 .net_header_len = sizeof(struct ipv6hdr),
1894 .net_frag_header_len = sizeof(struct frag_hdr),
1895 .setsockopt = ipv6_setsockopt,
1896 .getsockopt = ipv6_getsockopt,
1897 .addr2sockaddr = inet6_csk_addr2sockaddr,
1898 .sockaddr_len = sizeof(struct sockaddr_in6),
1899 .mtu_reduced = tcp_v6_mtu_reduced,
1900 };
1901
1902 #ifdef CONFIG_TCP_MD5SIG
1903 static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = {
1904 .md5_lookup = tcp_v6_md5_lookup,
1905 .calc_md5_hash = tcp_v6_md5_hash_skb,
1906 .md5_parse = tcp_v6_parse_md5_keys,
1907 };
1908 #endif
1909
1910 /*
1911 * TCP over IPv4 via INET6 API
1912 */
1913 static const struct inet_connection_sock_af_ops ipv6_mapped = {
1914 .queue_xmit = ip_queue_xmit,
1915 .send_check = tcp_v4_send_check,
1916 .rebuild_header = inet_sk_rebuild_header,
1917 .sk_rx_dst_set = inet_sk_rx_dst_set,
1918 .conn_request = tcp_v6_conn_request,
1919 .syn_recv_sock = tcp_v6_syn_recv_sock,
1920 .net_header_len = sizeof(struct iphdr),
1921 .setsockopt = ipv6_setsockopt,
1922 .getsockopt = ipv6_getsockopt,
1923 .addr2sockaddr = inet6_csk_addr2sockaddr,
1924 .sockaddr_len = sizeof(struct sockaddr_in6),
1925 .mtu_reduced = tcp_v4_mtu_reduced,
1926 };
1927
1928 #ifdef CONFIG_TCP_MD5SIG
1929 static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = {
1930 .md5_lookup = tcp_v4_md5_lookup,
1931 .calc_md5_hash = tcp_v4_md5_hash_skb,
1932 .md5_parse = tcp_v6_parse_md5_keys,
1933 };
1934 #endif
1935
1936 /* NOTE: A lot of things set to zero explicitly by call to
1937 * sk_alloc() so need not be done here.
1938 */
tcp_v6_init_sock(struct sock * sk)1939 static int tcp_v6_init_sock(struct sock *sk)
1940 {
1941 struct inet_connection_sock *icsk = inet_csk(sk);
1942
1943 tcp_init_sock(sk);
1944
1945 icsk->icsk_af_ops = &ipv6_specific;
1946
1947 #ifdef CONFIG_TCP_MD5SIG
1948 tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific;
1949 #endif
1950
1951 return 0;
1952 }
1953
1954 #ifdef CONFIG_PROC_FS
1955 /* Proc filesystem TCPv6 sock list dumping. */
get_openreq6(struct seq_file * seq,const struct request_sock * req,int i)1956 static void get_openreq6(struct seq_file *seq,
1957 const struct request_sock *req, int i)
1958 {
1959 long ttd = req->rsk_timer.expires - jiffies;
1960 const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr;
1961 const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr;
1962
1963 if (ttd < 0)
1964 ttd = 0;
1965
1966 seq_printf(seq,
1967 "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
1968 "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n",
1969 i,
1970 src->s6_addr32[0], src->s6_addr32[1],
1971 src->s6_addr32[2], src->s6_addr32[3],
1972 inet_rsk(req)->ir_num,
1973 dest->s6_addr32[0], dest->s6_addr32[1],
1974 dest->s6_addr32[2], dest->s6_addr32[3],
1975 ntohs(inet_rsk(req)->ir_rmt_port),
1976 TCP_SYN_RECV,
1977 0, 0, /* could print option size, but that is af dependent. */
1978 1, /* timers active (only the expire timer) */
1979 jiffies_to_clock_t(ttd),
1980 req->num_timeout,
1981 from_kuid_munged(seq_user_ns(seq),
1982 sock_i_uid(req->rsk_listener)),
1983 0, /* non standard timer */
1984 0, /* open_requests have no inode */
1985 0, req);
1986 }
1987
get_tcp6_sock(struct seq_file * seq,struct sock * sp,int i)1988 static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
1989 {
1990 const struct in6_addr *dest, *src;
1991 __u16 destp, srcp;
1992 int timer_active;
1993 unsigned long timer_expires;
1994 const struct inet_sock *inet = inet_sk(sp);
1995 const struct tcp_sock *tp = tcp_sk(sp);
1996 const struct inet_connection_sock *icsk = inet_csk(sp);
1997 const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq;
1998 int rx_queue;
1999 int state;
2000
2001 dest = &sp->sk_v6_daddr;
2002 src = &sp->sk_v6_rcv_saddr;
2003 destp = ntohs(inet->inet_dport);
2004 srcp = ntohs(inet->inet_sport);
2005
2006 if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
2007 icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
2008 icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
2009 timer_active = 1;
2010 timer_expires = icsk->icsk_timeout;
2011 } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
2012 timer_active = 4;
2013 timer_expires = icsk->icsk_timeout;
2014 } else if (timer_pending(&sp->sk_timer)) {
2015 timer_active = 2;
2016 timer_expires = sp->sk_timer.expires;
2017 } else {
2018 timer_active = 0;
2019 timer_expires = jiffies;
2020 }
2021
2022 state = inet_sk_state_load(sp);
2023 if (state == TCP_LISTEN)
2024 rx_queue = READ_ONCE(sp->sk_ack_backlog);
2025 else
2026 /* Because we don't lock the socket,
2027 * we might find a transient negative value.
2028 */
2029 rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
2030 READ_ONCE(tp->copied_seq), 0);
2031
2032 seq_printf(seq,
2033 "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
2034 "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n",
2035 i,
2036 src->s6_addr32[0], src->s6_addr32[1],
2037 src->s6_addr32[2], src->s6_addr32[3], srcp,
2038 dest->s6_addr32[0], dest->s6_addr32[1],
2039 dest->s6_addr32[2], dest->s6_addr32[3], destp,
2040 state,
2041 READ_ONCE(tp->write_seq) - tp->snd_una,
2042 rx_queue,
2043 timer_active,
2044 jiffies_delta_to_clock_t(timer_expires - jiffies),
2045 icsk->icsk_retransmits,
2046 from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
2047 icsk->icsk_probes_out,
2048 sock_i_ino(sp),
2049 refcount_read(&sp->sk_refcnt), sp,
2050 jiffies_to_clock_t(icsk->icsk_rto),
2051 jiffies_to_clock_t(icsk->icsk_ack.ato),
2052 (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp),
2053 tcp_snd_cwnd(tp),
2054 state == TCP_LISTEN ?
2055 fastopenq->max_qlen :
2056 (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)
2057 );
2058 }
2059
get_timewait6_sock(struct seq_file * seq,struct inet_timewait_sock * tw,int i)2060 static void get_timewait6_sock(struct seq_file *seq,
2061 struct inet_timewait_sock *tw, int i)
2062 {
2063 long delta = tw->tw_timer.expires - jiffies;
2064 const struct in6_addr *dest, *src;
2065 __u16 destp, srcp;
2066
2067 dest = &tw->tw_v6_daddr;
2068 src = &tw->tw_v6_rcv_saddr;
2069 destp = ntohs(tw->tw_dport);
2070 srcp = ntohs(tw->tw_sport);
2071
2072 seq_printf(seq,
2073 "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
2074 "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n",
2075 i,
2076 src->s6_addr32[0], src->s6_addr32[1],
2077 src->s6_addr32[2], src->s6_addr32[3], srcp,
2078 dest->s6_addr32[0], dest->s6_addr32[1],
2079 dest->s6_addr32[2], dest->s6_addr32[3], destp,
2080 tw->tw_substate, 0, 0,
2081 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
2082 refcount_read(&tw->tw_refcnt), tw);
2083 }
2084
tcp6_seq_show(struct seq_file * seq,void * v)2085 static int tcp6_seq_show(struct seq_file *seq, void *v)
2086 {
2087 struct tcp_iter_state *st;
2088 struct sock *sk = v;
2089
2090 if (v == SEQ_START_TOKEN) {
2091 seq_puts(seq,
2092 " sl "
2093 "local_address "
2094 "remote_address "
2095 "st tx_queue rx_queue tr tm->when retrnsmt"
2096 " uid timeout inode\n");
2097 goto out;
2098 }
2099 st = seq->private;
2100
2101 if (sk->sk_state == TCP_TIME_WAIT)
2102 get_timewait6_sock(seq, v, st->num);
2103 else if (sk->sk_state == TCP_NEW_SYN_RECV)
2104 get_openreq6(seq, v, st->num);
2105 else
2106 get_tcp6_sock(seq, v, st->num);
2107 out:
2108 return 0;
2109 }
2110
2111 static const struct seq_operations tcp6_seq_ops = {
2112 .show = tcp6_seq_show,
2113 .start = tcp_seq_start,
2114 .next = tcp_seq_next,
2115 .stop = tcp_seq_stop,
2116 };
2117
2118 static struct tcp_seq_afinfo tcp6_seq_afinfo = {
2119 .family = AF_INET6,
2120 };
2121
tcp6_proc_init(struct net * net)2122 int __net_init tcp6_proc_init(struct net *net)
2123 {
2124 if (!proc_create_net_data("tcp6", 0444, net->proc_net, &tcp6_seq_ops,
2125 sizeof(struct tcp_iter_state), &tcp6_seq_afinfo))
2126 return -ENOMEM;
2127 return 0;
2128 }
2129
tcp6_proc_exit(struct net * net)2130 void tcp6_proc_exit(struct net *net)
2131 {
2132 remove_proc_entry("tcp6", net->proc_net);
2133 }
2134 #endif
2135
2136 struct proto tcpv6_prot = {
2137 .name = "TCPv6",
2138 .owner = THIS_MODULE,
2139 .close = tcp_close,
2140 .pre_connect = tcp_v6_pre_connect,
2141 .connect = tcp_v6_connect,
2142 .disconnect = tcp_disconnect,
2143 .accept = inet_csk_accept,
2144 .ioctl = tcp_ioctl,
2145 .init = tcp_v6_init_sock,
2146 .destroy = tcp_v4_destroy_sock,
2147 .shutdown = tcp_shutdown,
2148 .setsockopt = tcp_setsockopt,
2149 .getsockopt = tcp_getsockopt,
2150 .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt,
2151 .keepalive = tcp_set_keepalive,
2152 .recvmsg = tcp_recvmsg,
2153 .sendmsg = tcp_sendmsg,
2154 .sendpage = tcp_sendpage,
2155 .backlog_rcv = tcp_v6_do_rcv,
2156 .release_cb = tcp_release_cb,
2157 .hash = inet6_hash,
2158 .unhash = inet_unhash,
2159 .get_port = inet_csk_get_port,
2160 .put_port = inet_put_port,
2161 #ifdef CONFIG_BPF_SYSCALL
2162 .psock_update_sk_prot = tcp_bpf_update_proto,
2163 #endif
2164 .enter_memory_pressure = tcp_enter_memory_pressure,
2165 .leave_memory_pressure = tcp_leave_memory_pressure,
2166 .stream_memory_free = tcp_stream_memory_free,
2167 .sockets_allocated = &tcp_sockets_allocated,
2168
2169 .memory_allocated = &tcp_memory_allocated,
2170 .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc,
2171
2172 .memory_pressure = &tcp_memory_pressure,
2173 .orphan_count = &tcp_orphan_count,
2174 .sysctl_mem = sysctl_tcp_mem,
2175 .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem),
2176 .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem),
2177 .max_header = MAX_TCP_HEADER,
2178 .obj_size = sizeof(struct tcp6_sock),
2179 .slab_flags = SLAB_TYPESAFE_BY_RCU,
2180 .twsk_prot = &tcp6_timewait_sock_ops,
2181 .rsk_prot = &tcp6_request_sock_ops,
2182 .h.hashinfo = NULL,
2183 .no_autobind = true,
2184 .diag_destroy = tcp_abort,
2185 };
2186 EXPORT_SYMBOL_GPL(tcpv6_prot);
2187
2188 static const struct inet6_protocol tcpv6_protocol = {
2189 .handler = tcp_v6_rcv,
2190 .err_handler = tcp_v6_err,
2191 .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
2192 };
2193
2194 static struct inet_protosw tcpv6_protosw = {
2195 .type = SOCK_STREAM,
2196 .protocol = IPPROTO_TCP,
2197 .prot = &tcpv6_prot,
2198 .ops = &inet6_stream_ops,
2199 .flags = INET_PROTOSW_PERMANENT |
2200 INET_PROTOSW_ICSK,
2201 };
2202
tcpv6_net_init(struct net * net)2203 static int __net_init tcpv6_net_init(struct net *net)
2204 {
2205 return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
2206 SOCK_RAW, IPPROTO_TCP, net);
2207 }
2208
tcpv6_net_exit(struct net * net)2209 static void __net_exit tcpv6_net_exit(struct net *net)
2210 {
2211 inet_ctl_sock_destroy(net->ipv6.tcp_sk);
2212 }
2213
tcpv6_net_exit_batch(struct list_head * net_exit_list)2214 static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list)
2215 {
2216 tcp_twsk_purge(net_exit_list, AF_INET6);
2217 }
2218
2219 static struct pernet_operations tcpv6_net_ops = {
2220 .init = tcpv6_net_init,
2221 .exit = tcpv6_net_exit,
2222 .exit_batch = tcpv6_net_exit_batch,
2223 };
2224
tcpv6_init(void)2225 int __init tcpv6_init(void)
2226 {
2227 int ret;
2228
2229 ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP);
2230 if (ret)
2231 goto out;
2232
2233 /* register inet6 protocol */
2234 ret = inet6_register_protosw(&tcpv6_protosw);
2235 if (ret)
2236 goto out_tcpv6_protocol;
2237
2238 ret = register_pernet_subsys(&tcpv6_net_ops);
2239 if (ret)
2240 goto out_tcpv6_protosw;
2241
2242 ret = mptcpv6_init();
2243 if (ret)
2244 goto out_tcpv6_pernet_subsys;
2245
2246 out:
2247 return ret;
2248
2249 out_tcpv6_pernet_subsys:
2250 unregister_pernet_subsys(&tcpv6_net_ops);
2251 out_tcpv6_protosw:
2252 inet6_unregister_protosw(&tcpv6_protosw);
2253 out_tcpv6_protocol:
2254 inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
2255 goto out;
2256 }
2257
tcpv6_exit(void)2258 void tcpv6_exit(void)
2259 {
2260 unregister_pernet_subsys(&tcpv6_net_ops);
2261 inet6_unregister_protosw(&tcpv6_protosw);
2262 inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
2263 }
2264