xref: /kernel/linux/linux-5.10/net/sctp/protocol.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-or-later
2/* SCTP kernel implementation
3 * (C) Copyright IBM Corp. 2001, 2004
4 * Copyright (c) 1999-2000 Cisco, Inc.
5 * Copyright (c) 1999-2001 Motorola, Inc.
6 * Copyright (c) 2001 Intel Corp.
7 * Copyright (c) 2001 Nokia, Inc.
8 * Copyright (c) 2001 La Monte H.P. Yarroll
9 *
10 * This file is part of the SCTP kernel implementation
11 *
12 * Initialization/cleanup for SCTP protocol support.
13 *
14 * Please send any bug reports or fixes you make to the
15 * email address(es):
16 *    lksctp developers <linux-sctp@vger.kernel.org>
17 *
18 * Written or modified by:
19 *    La Monte H.P. Yarroll <piggy@acm.org>
20 *    Karl Knutson <karl@athena.chicago.il.us>
21 *    Jon Grimm <jgrimm@us.ibm.com>
22 *    Sridhar Samudrala <sri@us.ibm.com>
23 *    Daisy Chang <daisyc@us.ibm.com>
24 *    Ardelle Fan <ardelle.fan@intel.com>
25 */
26
27#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
28
29#include <linux/module.h>
30#include <linux/init.h>
31#include <linux/netdevice.h>
32#include <linux/inetdevice.h>
33#include <linux/seq_file.h>
34#include <linux/memblock.h>
35#include <linux/highmem.h>
36#include <linux/swap.h>
37#include <linux/slab.h>
38#include <net/net_namespace.h>
39#include <net/protocol.h>
40#include <net/ip.h>
41#include <net/ipv6.h>
42#include <net/route.h>
43#include <net/sctp/sctp.h>
44#include <net/addrconf.h>
45#include <net/inet_common.h>
46#include <net/inet_ecn.h>
47
48#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
49
50/* Global data structures. */
51struct sctp_globals sctp_globals __read_mostly;
52
53struct idr sctp_assocs_id;
54DEFINE_SPINLOCK(sctp_assocs_id_lock);
55
56static struct sctp_pf *sctp_pf_inet6_specific;
57static struct sctp_pf *sctp_pf_inet_specific;
58static struct sctp_af *sctp_af_v4_specific;
59static struct sctp_af *sctp_af_v6_specific;
60
61struct kmem_cache *sctp_chunk_cachep __read_mostly;
62struct kmem_cache *sctp_bucket_cachep __read_mostly;
63
64long sysctl_sctp_mem[3];
65int sysctl_sctp_rmem[3];
66int sysctl_sctp_wmem[3];
67
68/* Private helper to extract ipv4 address and stash them in
69 * the protocol structure.
70 */
71static void sctp_v4_copy_addrlist(struct list_head *addrlist,
72				  struct net_device *dev)
73{
74	struct in_device *in_dev;
75	struct in_ifaddr *ifa;
76	struct sctp_sockaddr_entry *addr;
77
78	rcu_read_lock();
79	if ((in_dev = __in_dev_get_rcu(dev)) == NULL) {
80		rcu_read_unlock();
81		return;
82	}
83
84	in_dev_for_each_ifa_rcu(ifa, in_dev) {
85		/* Add the address to the local list.  */
86		addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
87		if (addr) {
88			addr->a.v4.sin_family = AF_INET;
89			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
90			addr->valid = 1;
91			INIT_LIST_HEAD(&addr->list);
92			list_add_tail(&addr->list, addrlist);
93		}
94	}
95
96	rcu_read_unlock();
97}
98
99/* Extract our IP addresses from the system and stash them in the
100 * protocol structure.
101 */
102static void sctp_get_local_addr_list(struct net *net)
103{
104	struct net_device *dev;
105	struct list_head *pos;
106	struct sctp_af *af;
107
108	rcu_read_lock();
109	for_each_netdev_rcu(net, dev) {
110		list_for_each(pos, &sctp_address_families) {
111			af = list_entry(pos, struct sctp_af, list);
112			af->copy_addrlist(&net->sctp.local_addr_list, dev);
113		}
114	}
115	rcu_read_unlock();
116}
117
118/* Free the existing local addresses.  */
119static void sctp_free_local_addr_list(struct net *net)
120{
121	struct sctp_sockaddr_entry *addr;
122	struct list_head *pos, *temp;
123
124	list_for_each_safe(pos, temp, &net->sctp.local_addr_list) {
125		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
126		list_del(pos);
127		kfree(addr);
128	}
129}
130
131/* Copy the local addresses which are valid for 'scope' into 'bp'.  */
132int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
133			      enum sctp_scope scope, gfp_t gfp, int copy_flags)
134{
135	struct sctp_sockaddr_entry *addr;
136	union sctp_addr laddr;
137	int error = 0;
138
139	rcu_read_lock();
140	list_for_each_entry_rcu(addr, &net->sctp.local_addr_list, list) {
141		if (!addr->valid)
142			continue;
143		if (!sctp_in_scope(net, &addr->a, scope))
144			continue;
145
146		/* Now that the address is in scope, check to see if
147		 * the address type is really supported by the local
148		 * sock as well as the remote peer.
149		 */
150		if (addr->a.sa.sa_family == AF_INET &&
151		    (!(copy_flags & SCTP_ADDR4_ALLOWED) ||
152		     !(copy_flags & SCTP_ADDR4_PEERSUPP)))
153			continue;
154		if (addr->a.sa.sa_family == AF_INET6 &&
155		    (!(copy_flags & SCTP_ADDR6_ALLOWED) ||
156		     !(copy_flags & SCTP_ADDR6_PEERSUPP)))
157			continue;
158
159		laddr = addr->a;
160		/* also works for setting ipv6 address port */
161		laddr.v4.sin_port = htons(bp->port);
162		if (sctp_bind_addr_state(bp, &laddr) != -1)
163			continue;
164
165		error = sctp_add_bind_addr(bp, &addr->a, sizeof(addr->a),
166					   SCTP_ADDR_SRC, GFP_ATOMIC);
167		if (error)
168			break;
169	}
170
171	rcu_read_unlock();
172	return error;
173}
174
175/* Copy over any ip options */
176static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk)
177{
178	struct inet_sock *newinet, *inet = inet_sk(sk);
179	struct ip_options_rcu *inet_opt, *newopt = NULL;
180
181	newinet = inet_sk(newsk);
182
183	rcu_read_lock();
184	inet_opt = rcu_dereference(inet->inet_opt);
185	if (inet_opt) {
186		newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
187				      inet_opt->opt.optlen, GFP_ATOMIC);
188		if (newopt)
189			memcpy(newopt, inet_opt, sizeof(*inet_opt) +
190			       inet_opt->opt.optlen);
191		else
192			pr_err("%s: Failed to copy ip options\n", __func__);
193	}
194	RCU_INIT_POINTER(newinet->inet_opt, newopt);
195	rcu_read_unlock();
196}
197
198/* Account for the IP options */
199static int sctp_v4_ip_options_len(struct sock *sk)
200{
201	struct inet_sock *inet = inet_sk(sk);
202	struct ip_options_rcu *inet_opt;
203	int len = 0;
204
205	rcu_read_lock();
206	inet_opt = rcu_dereference(inet->inet_opt);
207	if (inet_opt)
208		len = inet_opt->opt.optlen;
209
210	rcu_read_unlock();
211	return len;
212}
213
214/* Initialize a sctp_addr from in incoming skb.  */
215static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
216			     int is_saddr)
217{
218	/* Always called on head skb, so this is safe */
219	struct sctphdr *sh = sctp_hdr(skb);
220	struct sockaddr_in *sa = &addr->v4;
221
222	addr->v4.sin_family = AF_INET;
223
224	if (is_saddr) {
225		sa->sin_port = sh->source;
226		sa->sin_addr.s_addr = ip_hdr(skb)->saddr;
227	} else {
228		sa->sin_port = sh->dest;
229		sa->sin_addr.s_addr = ip_hdr(skb)->daddr;
230	}
231	memset(sa->sin_zero, 0, sizeof(sa->sin_zero));
232}
233
234/* Initialize an sctp_addr from a socket. */
235static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk)
236{
237	addr->v4.sin_family = AF_INET;
238	addr->v4.sin_port = 0;
239	addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr;
240	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
241}
242
243/* Initialize sk->sk_rcv_saddr from sctp_addr. */
244static void sctp_v4_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
245{
246	inet_sk(sk)->inet_rcv_saddr = addr->v4.sin_addr.s_addr;
247}
248
249/* Initialize sk->sk_daddr from sctp_addr. */
250static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
251{
252	inet_sk(sk)->inet_daddr = addr->v4.sin_addr.s_addr;
253}
254
255/* Initialize a sctp_addr from an address parameter. */
256static bool sctp_v4_from_addr_param(union sctp_addr *addr,
257				    union sctp_addr_param *param,
258				    __be16 port, int iif)
259{
260	if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param))
261		return false;
262
263	addr->v4.sin_family = AF_INET;
264	addr->v4.sin_port = port;
265	addr->v4.sin_addr.s_addr = param->v4.addr.s_addr;
266	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
267
268	return true;
269}
270
271/* Initialize an address parameter from a sctp_addr and return the length
272 * of the address parameter.
273 */
274static int sctp_v4_to_addr_param(const union sctp_addr *addr,
275				 union sctp_addr_param *param)
276{
277	int length = sizeof(struct sctp_ipv4addr_param);
278
279	param->v4.param_hdr.type = SCTP_PARAM_IPV4_ADDRESS;
280	param->v4.param_hdr.length = htons(length);
281	param->v4.addr.s_addr = addr->v4.sin_addr.s_addr;
282
283	return length;
284}
285
286/* Initialize a sctp_addr from a dst_entry. */
287static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4,
288			      __be16 port)
289{
290	saddr->v4.sin_family = AF_INET;
291	saddr->v4.sin_port = port;
292	saddr->v4.sin_addr.s_addr = fl4->saddr;
293	memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero));
294}
295
296/* Compare two addresses exactly. */
297static int sctp_v4_cmp_addr(const union sctp_addr *addr1,
298			    const union sctp_addr *addr2)
299{
300	if (addr1->sa.sa_family != addr2->sa.sa_family)
301		return 0;
302	if (addr1->v4.sin_port != addr2->v4.sin_port)
303		return 0;
304	if (addr1->v4.sin_addr.s_addr != addr2->v4.sin_addr.s_addr)
305		return 0;
306
307	return 1;
308}
309
310/* Initialize addr struct to INADDR_ANY. */
311static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port)
312{
313	addr->v4.sin_family = AF_INET;
314	addr->v4.sin_addr.s_addr = htonl(INADDR_ANY);
315	addr->v4.sin_port = port;
316	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
317}
318
319/* Is this a wildcard address? */
320static int sctp_v4_is_any(const union sctp_addr *addr)
321{
322	return htonl(INADDR_ANY) == addr->v4.sin_addr.s_addr;
323}
324
325/* This function checks if the address is a valid address to be used for
326 * SCTP binding.
327 *
328 * Output:
329 * Return 0 - If the address is a non-unicast or an illegal address.
330 * Return 1 - If the address is a unicast.
331 */
332static int sctp_v4_addr_valid(union sctp_addr *addr,
333			      struct sctp_sock *sp,
334			      const struct sk_buff *skb)
335{
336	/* IPv4 addresses not allowed */
337	if (sp && ipv6_only_sock(sctp_opt2sk(sp)))
338		return 0;
339
340	/* Is this a non-unicast address or a unusable SCTP address? */
341	if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr))
342		return 0;
343
344	/* Is this a broadcast address? */
345	if (skb && skb_rtable(skb)->rt_flags & RTCF_BROADCAST)
346		return 0;
347
348	return 1;
349}
350
351/* Should this be available for binding?   */
352static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
353{
354	struct net *net = sock_net(&sp->inet.sk);
355	int ret = inet_addr_type(net, addr->v4.sin_addr.s_addr);
356
357
358	if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
359	   ret != RTN_LOCAL &&
360	   !sp->inet.freebind &&
361	    !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind))
362		return 0;
363
364	if (ipv6_only_sock(sctp_opt2sk(sp)))
365		return 0;
366
367	return 1;
368}
369
370/* Checking the loopback, private and other address scopes as defined in
371 * RFC 1918.   The IPv4 scoping is based on the draft for SCTP IPv4
372 * scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>.
373 *
374 * Level 0 - unusable SCTP addresses
375 * Level 1 - loopback address
376 * Level 2 - link-local addresses
377 * Level 3 - private addresses.
378 * Level 4 - global addresses
379 * For INIT and INIT-ACK address list, let L be the level of
380 * requested destination address, sender and receiver
381 * SHOULD include all of its addresses with level greater
382 * than or equal to L.
383 *
384 * IPv4 scoping can be controlled through sysctl option
385 * net.sctp.addr_scope_policy
386 */
387static enum sctp_scope sctp_v4_scope(union sctp_addr *addr)
388{
389	enum sctp_scope retval;
390
391	/* Check for unusable SCTP addresses. */
392	if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) {
393		retval =  SCTP_SCOPE_UNUSABLE;
394	} else if (ipv4_is_loopback(addr->v4.sin_addr.s_addr)) {
395		retval = SCTP_SCOPE_LOOPBACK;
396	} else if (ipv4_is_linklocal_169(addr->v4.sin_addr.s_addr)) {
397		retval = SCTP_SCOPE_LINK;
398	} else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) ||
399		   ipv4_is_private_172(addr->v4.sin_addr.s_addr) ||
400		   ipv4_is_private_192(addr->v4.sin_addr.s_addr) ||
401		   ipv4_is_test_198(addr->v4.sin_addr.s_addr)) {
402		retval = SCTP_SCOPE_PRIVATE;
403	} else {
404		retval = SCTP_SCOPE_GLOBAL;
405	}
406
407	return retval;
408}
409
410/* Returns a valid dst cache entry for the given source and destination ip
411 * addresses. If an association is passed, trys to get a dst entry with a
412 * source address that matches an address in the bind address list.
413 */
414static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
415				struct flowi *fl, struct sock *sk)
416{
417	struct sctp_association *asoc = t->asoc;
418	struct rtable *rt;
419	struct flowi _fl;
420	struct flowi4 *fl4 = &_fl.u.ip4;
421	struct sctp_bind_addr *bp;
422	struct sctp_sockaddr_entry *laddr;
423	struct dst_entry *dst = NULL;
424	union sctp_addr *daddr = &t->ipaddr;
425	union sctp_addr dst_saddr;
426	__u8 tos = inet_sk(sk)->tos;
427
428	if (t->dscp & SCTP_DSCP_SET_MASK)
429		tos = t->dscp & SCTP_DSCP_VAL_MASK;
430	memset(&_fl, 0x0, sizeof(_fl));
431	fl4->daddr  = daddr->v4.sin_addr.s_addr;
432	fl4->fl4_dport = daddr->v4.sin_port;
433	fl4->flowi4_proto = IPPROTO_SCTP;
434	if (asoc) {
435		fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos);
436		fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
437		fl4->fl4_sport = htons(asoc->base.bind_addr.port);
438	}
439	if (saddr) {
440		fl4->saddr = saddr->v4.sin_addr.s_addr;
441		if (!fl4->fl4_sport)
442			fl4->fl4_sport = saddr->v4.sin_port;
443	}
444
445	pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr,
446		 &fl4->saddr);
447
448	rt = ip_route_output_key(sock_net(sk), fl4);
449	if (!IS_ERR(rt)) {
450		dst = &rt->dst;
451		t->dst = dst;
452		memcpy(fl, &_fl, sizeof(_fl));
453	}
454
455	/* If there is no association or if a source address is passed, no
456	 * more validation is required.
457	 */
458	if (!asoc || saddr)
459		goto out;
460
461	bp = &asoc->base.bind_addr;
462
463	if (dst) {
464		/* Walk through the bind address list and look for a bind
465		 * address that matches the source address of the returned dst.
466		 */
467		sctp_v4_dst_saddr(&dst_saddr, fl4, htons(bp->port));
468		rcu_read_lock();
469		list_for_each_entry_rcu(laddr, &bp->address_list, list) {
470			if (!laddr->valid || (laddr->state == SCTP_ADDR_DEL) ||
471			    (laddr->state != SCTP_ADDR_SRC &&
472			    !asoc->src_out_of_asoc_ok))
473				continue;
474			if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
475				goto out_unlock;
476		}
477		rcu_read_unlock();
478
479		/* None of the bound addresses match the source address of the
480		 * dst. So release it.
481		 */
482		dst_release(dst);
483		dst = NULL;
484	}
485
486	/* Walk through the bind address list and try to get a dst that
487	 * matches a bind address as the source address.
488	 */
489	rcu_read_lock();
490	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
491		struct net_device *odev;
492
493		if (!laddr->valid)
494			continue;
495		if (laddr->state != SCTP_ADDR_SRC ||
496		    AF_INET != laddr->a.sa.sa_family)
497			continue;
498
499		fl4->fl4_sport = laddr->a.v4.sin_port;
500		flowi4_update_output(fl4,
501				     asoc->base.sk->sk_bound_dev_if,
502				     RT_CONN_FLAGS_TOS(asoc->base.sk, tos),
503				     daddr->v4.sin_addr.s_addr,
504				     laddr->a.v4.sin_addr.s_addr);
505
506		rt = ip_route_output_key(sock_net(sk), fl4);
507		if (IS_ERR(rt))
508			continue;
509
510		/* Ensure the src address belongs to the output
511		 * interface.
512		 */
513		odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
514				     false);
515		if (!odev || odev->ifindex != fl4->flowi4_oif) {
516			if (!dst) {
517				dst = &rt->dst;
518				t->dst = dst;
519				memcpy(fl, &_fl, sizeof(_fl));
520			} else {
521				dst_release(&rt->dst);
522			}
523			continue;
524		}
525
526		dst_release(dst);
527		dst = &rt->dst;
528		t->dst = dst;
529		memcpy(fl, &_fl, sizeof(_fl));
530		break;
531	}
532
533out_unlock:
534	rcu_read_unlock();
535out:
536	if (dst) {
537		pr_debug("rt_dst:%pI4, rt_src:%pI4\n",
538			 &fl->u.ip4.daddr, &fl->u.ip4.saddr);
539	} else {
540		t->dst = NULL;
541		pr_debug("no route\n");
542	}
543}
544
545/* For v4, the source address is cached in the route entry(dst). So no need
546 * to cache it separately and hence this is an empty routine.
547 */
548static void sctp_v4_get_saddr(struct sctp_sock *sk,
549			      struct sctp_transport *t,
550			      struct flowi *fl)
551{
552	union sctp_addr *saddr = &t->saddr;
553	struct rtable *rt = (struct rtable *)t->dst;
554
555	if (rt) {
556		saddr->v4.sin_family = AF_INET;
557		saddr->v4.sin_addr.s_addr = fl->u.ip4.saddr;
558	}
559}
560
561/* What interface did this skb arrive on? */
562static int sctp_v4_skb_iif(const struct sk_buff *skb)
563{
564	return inet_iif(skb);
565}
566
567/* Was this packet marked by Explicit Congestion Notification? */
568static int sctp_v4_is_ce(const struct sk_buff *skb)
569{
570	return INET_ECN_is_ce(ip_hdr(skb)->tos);
571}
572
573/* Create and initialize a new sk for the socket returned by accept(). */
574static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
575					     struct sctp_association *asoc,
576					     bool kern)
577{
578	struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
579			sk->sk_prot, kern);
580	struct inet_sock *newinet;
581
582	if (!newsk)
583		goto out;
584
585	sock_init_data(NULL, newsk);
586
587	sctp_copy_sock(newsk, sk, asoc);
588	sock_reset_flag(newsk, SOCK_ZAPPED);
589
590	sctp_v4_copy_ip_options(sk, newsk);
591
592	newinet = inet_sk(newsk);
593
594	newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr;
595
596	sk_refcnt_debug_inc(newsk);
597
598	if (newsk->sk_prot->init(newsk)) {
599		sk_common_release(newsk);
600		newsk = NULL;
601	}
602
603out:
604	return newsk;
605}
606
607static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
608{
609	/* No address mapping for V4 sockets */
610	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
611	return sizeof(struct sockaddr_in);
612}
613
614/* Dump the v4 addr to the seq file. */
615static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
616{
617	seq_printf(seq, "%pI4 ", &addr->v4.sin_addr);
618}
619
620static void sctp_v4_ecn_capable(struct sock *sk)
621{
622	INET_ECN_xmit(sk);
623}
624
625static void sctp_addr_wq_timeout_handler(struct timer_list *t)
626{
627	struct net *net = from_timer(net, t, sctp.addr_wq_timer);
628	struct sctp_sockaddr_entry *addrw, *temp;
629	struct sctp_sock *sp;
630
631	spin_lock_bh(&net->sctp.addr_wq_lock);
632
633	list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
634		pr_debug("%s: the first ent in wq:%p is addr:%pISc for cmd:%d at "
635			 "entry:%p\n", __func__, &net->sctp.addr_waitq, &addrw->a.sa,
636			 addrw->state, addrw);
637
638#if IS_ENABLED(CONFIG_IPV6)
639		/* Now we send an ASCONF for each association */
640		/* Note. we currently don't handle link local IPv6 addressees */
641		if (addrw->a.sa.sa_family == AF_INET6) {
642			struct in6_addr *in6;
643
644			if (ipv6_addr_type(&addrw->a.v6.sin6_addr) &
645			    IPV6_ADDR_LINKLOCAL)
646				goto free_next;
647
648			in6 = (struct in6_addr *)&addrw->a.v6.sin6_addr;
649			if (ipv6_chk_addr(net, in6, NULL, 0) == 0 &&
650			    addrw->state == SCTP_ADDR_NEW) {
651				unsigned long timeo_val;
652
653				pr_debug("%s: this is on DAD, trying %d sec "
654					 "later\n", __func__,
655					 SCTP_ADDRESS_TICK_DELAY);
656
657				timeo_val = jiffies;
658				timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
659				mod_timer(&net->sctp.addr_wq_timer, timeo_val);
660				break;
661			}
662		}
663#endif
664		list_for_each_entry(sp, &net->sctp.auto_asconf_splist, auto_asconf_list) {
665			struct sock *sk;
666
667			sk = sctp_opt2sk(sp);
668			/* ignore bound-specific endpoints */
669			if (!sctp_is_ep_boundall(sk))
670				continue;
671			bh_lock_sock(sk);
672			if (sctp_asconf_mgmt(sp, addrw) < 0)
673				pr_debug("%s: sctp_asconf_mgmt failed\n", __func__);
674			bh_unlock_sock(sk);
675		}
676#if IS_ENABLED(CONFIG_IPV6)
677free_next:
678#endif
679		list_del(&addrw->list);
680		kfree(addrw);
681	}
682	spin_unlock_bh(&net->sctp.addr_wq_lock);
683}
684
685static void sctp_free_addr_wq(struct net *net)
686{
687	struct sctp_sockaddr_entry *addrw;
688	struct sctp_sockaddr_entry *temp;
689
690	spin_lock_bh(&net->sctp.addr_wq_lock);
691	del_timer(&net->sctp.addr_wq_timer);
692	list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
693		list_del(&addrw->list);
694		kfree(addrw);
695	}
696	spin_unlock_bh(&net->sctp.addr_wq_lock);
697}
698
699/* lookup the entry for the same address in the addr_waitq
700 * sctp_addr_wq MUST be locked
701 */
702static struct sctp_sockaddr_entry *sctp_addr_wq_lookup(struct net *net,
703					struct sctp_sockaddr_entry *addr)
704{
705	struct sctp_sockaddr_entry *addrw;
706
707	list_for_each_entry(addrw, &net->sctp.addr_waitq, list) {
708		if (addrw->a.sa.sa_family != addr->a.sa.sa_family)
709			continue;
710		if (addrw->a.sa.sa_family == AF_INET) {
711			if (addrw->a.v4.sin_addr.s_addr ==
712			    addr->a.v4.sin_addr.s_addr)
713				return addrw;
714		} else if (addrw->a.sa.sa_family == AF_INET6) {
715			if (ipv6_addr_equal(&addrw->a.v6.sin6_addr,
716			    &addr->a.v6.sin6_addr))
717				return addrw;
718		}
719	}
720	return NULL;
721}
722
723void sctp_addr_wq_mgmt(struct net *net, struct sctp_sockaddr_entry *addr, int cmd)
724{
725	struct sctp_sockaddr_entry *addrw;
726	unsigned long timeo_val;
727
728	/* first, we check if an opposite message already exist in the queue.
729	 * If we found such message, it is removed.
730	 * This operation is a bit stupid, but the DHCP client attaches the
731	 * new address after a couple of addition and deletion of that address
732	 */
733
734	spin_lock_bh(&net->sctp.addr_wq_lock);
735	/* Offsets existing events in addr_wq */
736	addrw = sctp_addr_wq_lookup(net, addr);
737	if (addrw) {
738		if (addrw->state != cmd) {
739			pr_debug("%s: offsets existing entry for %d, addr:%pISc "
740				 "in wq:%p\n", __func__, addrw->state, &addrw->a.sa,
741				 &net->sctp.addr_waitq);
742
743			list_del(&addrw->list);
744			kfree(addrw);
745		}
746		spin_unlock_bh(&net->sctp.addr_wq_lock);
747		return;
748	}
749
750	/* OK, we have to add the new address to the wait queue */
751	addrw = kmemdup(addr, sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
752	if (addrw == NULL) {
753		spin_unlock_bh(&net->sctp.addr_wq_lock);
754		return;
755	}
756	addrw->state = cmd;
757	list_add_tail(&addrw->list, &net->sctp.addr_waitq);
758
759	pr_debug("%s: add new entry for cmd:%d, addr:%pISc in wq:%p\n",
760		 __func__, addrw->state, &addrw->a.sa, &net->sctp.addr_waitq);
761
762	if (!timer_pending(&net->sctp.addr_wq_timer)) {
763		timeo_val = jiffies;
764		timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
765		mod_timer(&net->sctp.addr_wq_timer, timeo_val);
766	}
767	spin_unlock_bh(&net->sctp.addr_wq_lock);
768}
769
770/* Event handler for inet address addition/deletion events.
771 * The sctp_local_addr_list needs to be protocted by a spin lock since
772 * multiple notifiers (say IPv4 and IPv6) may be running at the same
773 * time and thus corrupt the list.
774 * The reader side is protected with RCU.
775 */
776static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
777			       void *ptr)
778{
779	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
780	struct sctp_sockaddr_entry *addr = NULL;
781	struct sctp_sockaddr_entry *temp;
782	struct net *net = dev_net(ifa->ifa_dev->dev);
783	int found = 0;
784
785	switch (ev) {
786	case NETDEV_UP:
787		addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
788		if (addr) {
789			addr->a.v4.sin_family = AF_INET;
790			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
791			addr->valid = 1;
792			spin_lock_bh(&net->sctp.local_addr_lock);
793			list_add_tail_rcu(&addr->list, &net->sctp.local_addr_list);
794			sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_NEW);
795			spin_unlock_bh(&net->sctp.local_addr_lock);
796		}
797		break;
798	case NETDEV_DOWN:
799		spin_lock_bh(&net->sctp.local_addr_lock);
800		list_for_each_entry_safe(addr, temp,
801					&net->sctp.local_addr_list, list) {
802			if (addr->a.sa.sa_family == AF_INET &&
803					addr->a.v4.sin_addr.s_addr ==
804					ifa->ifa_local) {
805				sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
806				found = 1;
807				addr->valid = 0;
808				list_del_rcu(&addr->list);
809				break;
810			}
811		}
812		spin_unlock_bh(&net->sctp.local_addr_lock);
813		if (found)
814			kfree_rcu(addr, rcu);
815		break;
816	}
817
818	return NOTIFY_DONE;
819}
820
821/*
822 * Initialize the control inode/socket with a control endpoint data
823 * structure.  This endpoint is reserved exclusively for the OOTB processing.
824 */
825static int sctp_ctl_sock_init(struct net *net)
826{
827	int err;
828	sa_family_t family = PF_INET;
829
830	if (sctp_get_pf_specific(PF_INET6))
831		family = PF_INET6;
832
833	err = inet_ctl_sock_create(&net->sctp.ctl_sock, family,
834				   SOCK_SEQPACKET, IPPROTO_SCTP, net);
835
836	/* If IPv6 socket could not be created, try the IPv4 socket */
837	if (err < 0 && family == PF_INET6)
838		err = inet_ctl_sock_create(&net->sctp.ctl_sock, AF_INET,
839					   SOCK_SEQPACKET, IPPROTO_SCTP,
840					   net);
841
842	if (err < 0) {
843		pr_err("Failed to create the SCTP control socket\n");
844		return err;
845	}
846	return 0;
847}
848
849/* Register address family specific functions. */
850int sctp_register_af(struct sctp_af *af)
851{
852	switch (af->sa_family) {
853	case AF_INET:
854		if (sctp_af_v4_specific)
855			return 0;
856		sctp_af_v4_specific = af;
857		break;
858	case AF_INET6:
859		if (sctp_af_v6_specific)
860			return 0;
861		sctp_af_v6_specific = af;
862		break;
863	default:
864		return 0;
865	}
866
867	INIT_LIST_HEAD(&af->list);
868	list_add_tail(&af->list, &sctp_address_families);
869	return 1;
870}
871
872/* Get the table of functions for manipulating a particular address
873 * family.
874 */
875struct sctp_af *sctp_get_af_specific(sa_family_t family)
876{
877	switch (family) {
878	case AF_INET:
879		return sctp_af_v4_specific;
880	case AF_INET6:
881		return sctp_af_v6_specific;
882	default:
883		return NULL;
884	}
885}
886
887/* Common code to initialize a AF_INET msg_name. */
888static void sctp_inet_msgname(char *msgname, int *addr_len)
889{
890	struct sockaddr_in *sin;
891
892	sin = (struct sockaddr_in *)msgname;
893	*addr_len = sizeof(struct sockaddr_in);
894	sin->sin_family = AF_INET;
895	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
896}
897
898/* Copy the primary address of the peer primary address as the msg_name. */
899static void sctp_inet_event_msgname(struct sctp_ulpevent *event, char *msgname,
900				    int *addr_len)
901{
902	struct sockaddr_in *sin, *sinfrom;
903
904	if (msgname) {
905		struct sctp_association *asoc;
906
907		asoc = event->asoc;
908		sctp_inet_msgname(msgname, addr_len);
909		sin = (struct sockaddr_in *)msgname;
910		sinfrom = &asoc->peer.primary_addr.v4;
911		sin->sin_port = htons(asoc->peer.port);
912		sin->sin_addr.s_addr = sinfrom->sin_addr.s_addr;
913	}
914}
915
916/* Initialize and copy out a msgname from an inbound skb. */
917static void sctp_inet_skb_msgname(struct sk_buff *skb, char *msgname, int *len)
918{
919	if (msgname) {
920		struct sctphdr *sh = sctp_hdr(skb);
921		struct sockaddr_in *sin = (struct sockaddr_in *)msgname;
922
923		sctp_inet_msgname(msgname, len);
924		sin->sin_port = sh->source;
925		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
926	}
927}
928
929/* Do we support this AF? */
930static int sctp_inet_af_supported(sa_family_t family, struct sctp_sock *sp)
931{
932	/* PF_INET only supports AF_INET addresses. */
933	return AF_INET == family;
934}
935
936/* Address matching with wildcards allowed. */
937static int sctp_inet_cmp_addr(const union sctp_addr *addr1,
938			      const union sctp_addr *addr2,
939			      struct sctp_sock *opt)
940{
941	/* PF_INET only supports AF_INET addresses. */
942	if (addr1->sa.sa_family != addr2->sa.sa_family)
943		return 0;
944	if (htonl(INADDR_ANY) == addr1->v4.sin_addr.s_addr ||
945	    htonl(INADDR_ANY) == addr2->v4.sin_addr.s_addr)
946		return 1;
947	if (addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr)
948		return 1;
949
950	return 0;
951}
952
953/* Verify that provided sockaddr looks bindable.  Common verification has
954 * already been taken care of.
955 */
956static int sctp_inet_bind_verify(struct sctp_sock *opt, union sctp_addr *addr)
957{
958	return sctp_v4_available(addr, opt);
959}
960
961/* Verify that sockaddr looks sendable.  Common verification has already
962 * been taken care of.
963 */
964static int sctp_inet_send_verify(struct sctp_sock *opt, union sctp_addr *addr)
965{
966	return 1;
967}
968
969/* Fill in Supported Address Type information for INIT and INIT-ACK
970 * chunks.  Returns number of addresses supported.
971 */
972static int sctp_inet_supported_addrs(const struct sctp_sock *opt,
973				     __be16 *types)
974{
975	types[0] = SCTP_PARAM_IPV4_ADDRESS;
976	return 1;
977}
978
979/* Wrapper routine that calls the ip transmit routine. */
980static inline int sctp_v4_xmit(struct sk_buff *skb,
981			       struct sctp_transport *transport)
982{
983	struct inet_sock *inet = inet_sk(skb->sk);
984	__u8 dscp = inet->tos;
985
986	pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
987		 skb->len, &transport->fl.u.ip4.saddr,
988		 &transport->fl.u.ip4.daddr);
989
990	if (transport->dscp & SCTP_DSCP_SET_MASK)
991		dscp = transport->dscp & SCTP_DSCP_VAL_MASK;
992
993	inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
994			 IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
995
996	SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS);
997
998	return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp);
999}
1000
1001static struct sctp_af sctp_af_inet;
1002
1003static struct sctp_pf sctp_pf_inet = {
1004	.event_msgname = sctp_inet_event_msgname,
1005	.skb_msgname   = sctp_inet_skb_msgname,
1006	.af_supported  = sctp_inet_af_supported,
1007	.cmp_addr      = sctp_inet_cmp_addr,
1008	.bind_verify   = sctp_inet_bind_verify,
1009	.send_verify   = sctp_inet_send_verify,
1010	.supported_addrs = sctp_inet_supported_addrs,
1011	.create_accept_sk = sctp_v4_create_accept_sk,
1012	.addr_to_user  = sctp_v4_addr_to_user,
1013	.to_sk_saddr   = sctp_v4_to_sk_saddr,
1014	.to_sk_daddr   = sctp_v4_to_sk_daddr,
1015	.copy_ip_options = sctp_v4_copy_ip_options,
1016	.af            = &sctp_af_inet
1017};
1018
1019/* Notifier for inetaddr addition/deletion events.  */
1020static struct notifier_block sctp_inetaddr_notifier = {
1021	.notifier_call = sctp_inetaddr_event,
1022};
1023
1024/* Socket operations.  */
1025static const struct proto_ops inet_seqpacket_ops = {
1026	.family		   = PF_INET,
1027	.owner		   = THIS_MODULE,
1028	.release	   = inet_release,	/* Needs to be wrapped... */
1029	.bind		   = inet_bind,
1030	.connect	   = sctp_inet_connect,
1031	.socketpair	   = sock_no_socketpair,
1032	.accept		   = inet_accept,
1033	.getname	   = inet_getname,	/* Semantics are different.  */
1034	.poll		   = sctp_poll,
1035	.ioctl		   = inet_ioctl,
1036	.gettstamp	   = sock_gettstamp,
1037	.listen		   = sctp_inet_listen,
1038	.shutdown	   = inet_shutdown,	/* Looks harmless.  */
1039	.setsockopt	   = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */
1040	.getsockopt	   = sock_common_getsockopt,
1041	.sendmsg	   = inet_sendmsg,
1042	.recvmsg	   = inet_recvmsg,
1043	.mmap		   = sock_no_mmap,
1044	.sendpage	   = sock_no_sendpage,
1045};
1046
1047/* Registration with AF_INET family.  */
1048static struct inet_protosw sctp_seqpacket_protosw = {
1049	.type       = SOCK_SEQPACKET,
1050	.protocol   = IPPROTO_SCTP,
1051	.prot       = &sctp_prot,
1052	.ops        = &inet_seqpacket_ops,
1053	.flags      = SCTP_PROTOSW_FLAG
1054};
1055static struct inet_protosw sctp_stream_protosw = {
1056	.type       = SOCK_STREAM,
1057	.protocol   = IPPROTO_SCTP,
1058	.prot       = &sctp_prot,
1059	.ops        = &inet_seqpacket_ops,
1060	.flags      = SCTP_PROTOSW_FLAG
1061};
1062
1063/* Register with IP layer.  */
1064static const struct net_protocol sctp_protocol = {
1065	.handler     = sctp_rcv,
1066	.err_handler = sctp_v4_err,
1067	.no_policy   = 1,
1068	.netns_ok    = 1,
1069	.icmp_strict_tag_validation = 1,
1070};
1071
1072/* IPv4 address related functions.  */
1073static struct sctp_af sctp_af_inet = {
1074	.sa_family	   = AF_INET,
1075	.sctp_xmit	   = sctp_v4_xmit,
1076	.setsockopt	   = ip_setsockopt,
1077	.getsockopt	   = ip_getsockopt,
1078	.get_dst	   = sctp_v4_get_dst,
1079	.get_saddr	   = sctp_v4_get_saddr,
1080	.copy_addrlist	   = sctp_v4_copy_addrlist,
1081	.from_skb	   = sctp_v4_from_skb,
1082	.from_sk	   = sctp_v4_from_sk,
1083	.from_addr_param   = sctp_v4_from_addr_param,
1084	.to_addr_param	   = sctp_v4_to_addr_param,
1085	.cmp_addr	   = sctp_v4_cmp_addr,
1086	.addr_valid	   = sctp_v4_addr_valid,
1087	.inaddr_any	   = sctp_v4_inaddr_any,
1088	.is_any		   = sctp_v4_is_any,
1089	.available	   = sctp_v4_available,
1090	.scope		   = sctp_v4_scope,
1091	.skb_iif	   = sctp_v4_skb_iif,
1092	.is_ce		   = sctp_v4_is_ce,
1093	.seq_dump_addr	   = sctp_v4_seq_dump_addr,
1094	.ecn_capable	   = sctp_v4_ecn_capable,
1095	.net_header_len	   = sizeof(struct iphdr),
1096	.sockaddr_len	   = sizeof(struct sockaddr_in),
1097	.ip_options_len	   = sctp_v4_ip_options_len,
1098};
1099
1100struct sctp_pf *sctp_get_pf_specific(sa_family_t family)
1101{
1102	switch (family) {
1103	case PF_INET:
1104		return sctp_pf_inet_specific;
1105	case PF_INET6:
1106		return sctp_pf_inet6_specific;
1107	default:
1108		return NULL;
1109	}
1110}
1111
1112/* Register the PF specific function table.  */
1113int sctp_register_pf(struct sctp_pf *pf, sa_family_t family)
1114{
1115	switch (family) {
1116	case PF_INET:
1117		if (sctp_pf_inet_specific)
1118			return 0;
1119		sctp_pf_inet_specific = pf;
1120		break;
1121	case PF_INET6:
1122		if (sctp_pf_inet6_specific)
1123			return 0;
1124		sctp_pf_inet6_specific = pf;
1125		break;
1126	default:
1127		return 0;
1128	}
1129	return 1;
1130}
1131
1132static inline int init_sctp_mibs(struct net *net)
1133{
1134	net->sctp.sctp_statistics = alloc_percpu(struct sctp_mib);
1135	if (!net->sctp.sctp_statistics)
1136		return -ENOMEM;
1137	return 0;
1138}
1139
1140static inline void cleanup_sctp_mibs(struct net *net)
1141{
1142	free_percpu(net->sctp.sctp_statistics);
1143}
1144
1145static void sctp_v4_pf_init(void)
1146{
1147	/* Initialize the SCTP specific PF functions. */
1148	sctp_register_pf(&sctp_pf_inet, PF_INET);
1149	sctp_register_af(&sctp_af_inet);
1150}
1151
1152static void sctp_v4_pf_exit(void)
1153{
1154	list_del(&sctp_af_inet.list);
1155}
1156
1157static int sctp_v4_protosw_init(void)
1158{
1159	int rc;
1160
1161	rc = proto_register(&sctp_prot, 1);
1162	if (rc)
1163		return rc;
1164
1165	/* Register SCTP(UDP and TCP style) with socket layer.  */
1166	inet_register_protosw(&sctp_seqpacket_protosw);
1167	inet_register_protosw(&sctp_stream_protosw);
1168
1169	return 0;
1170}
1171
1172static void sctp_v4_protosw_exit(void)
1173{
1174	inet_unregister_protosw(&sctp_stream_protosw);
1175	inet_unregister_protosw(&sctp_seqpacket_protosw);
1176	proto_unregister(&sctp_prot);
1177}
1178
1179static int sctp_v4_add_protocol(void)
1180{
1181	/* Register notifier for inet address additions/deletions. */
1182	register_inetaddr_notifier(&sctp_inetaddr_notifier);
1183
1184	/* Register SCTP with inet layer.  */
1185	if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0)
1186		return -EAGAIN;
1187
1188	return 0;
1189}
1190
1191static void sctp_v4_del_protocol(void)
1192{
1193	inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
1194	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
1195}
1196
1197static int __net_init sctp_defaults_init(struct net *net)
1198{
1199	int status;
1200
1201	/*
1202	 * 14. Suggested SCTP Protocol Parameter Values
1203	 */
1204	/* The following protocol parameters are RECOMMENDED:  */
1205	/* RTO.Initial              - 3  seconds */
1206	net->sctp.rto_initial			= SCTP_RTO_INITIAL;
1207	/* RTO.Min                  - 1  second */
1208	net->sctp.rto_min	 		= SCTP_RTO_MIN;
1209	/* RTO.Max                 -  60 seconds */
1210	net->sctp.rto_max 			= SCTP_RTO_MAX;
1211	/* RTO.Alpha                - 1/8 */
1212	net->sctp.rto_alpha			= SCTP_RTO_ALPHA;
1213	/* RTO.Beta                 - 1/4 */
1214	net->sctp.rto_beta			= SCTP_RTO_BETA;
1215
1216	/* Valid.Cookie.Life        - 60  seconds */
1217	net->sctp.valid_cookie_life		= SCTP_DEFAULT_COOKIE_LIFE;
1218
1219	/* Whether Cookie Preservative is enabled(1) or not(0) */
1220	net->sctp.cookie_preserve_enable 	= 1;
1221
1222	/* Default sctp sockets to use md5 as their hmac alg */
1223#if defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_MD5)
1224	net->sctp.sctp_hmac_alg			= "md5";
1225#elif defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA1)
1226	net->sctp.sctp_hmac_alg			= "sha1";
1227#else
1228	net->sctp.sctp_hmac_alg			= NULL;
1229#endif
1230
1231	/* Max.Burst		    - 4 */
1232	net->sctp.max_burst			= SCTP_DEFAULT_MAX_BURST;
1233
1234	/* Disable of Primary Path Switchover by default */
1235	net->sctp.ps_retrans = SCTP_PS_RETRANS_MAX;
1236
1237	/* Enable pf state by default */
1238	net->sctp.pf_enable = 1;
1239
1240	/* Ignore pf exposure feature by default */
1241	net->sctp.pf_expose = SCTP_PF_EXPOSE_UNSET;
1242
1243	/* Association.Max.Retrans  - 10 attempts
1244	 * Path.Max.Retrans         - 5  attempts (per destination address)
1245	 * Max.Init.Retransmits     - 8  attempts
1246	 */
1247	net->sctp.max_retrans_association	= 10;
1248	net->sctp.max_retrans_path		= 5;
1249	net->sctp.max_retrans_init		= 8;
1250
1251	/* Sendbuffer growth	    - do per-socket accounting */
1252	net->sctp.sndbuf_policy			= 0;
1253
1254	/* Rcvbuffer growth	    - do per-socket accounting */
1255	net->sctp.rcvbuf_policy			= 0;
1256
1257	/* HB.interval              - 30 seconds */
1258	net->sctp.hb_interval			= SCTP_DEFAULT_TIMEOUT_HEARTBEAT;
1259
1260	/* delayed SACK timeout */
1261	net->sctp.sack_timeout			= SCTP_DEFAULT_TIMEOUT_SACK;
1262
1263	/* Disable ADDIP by default. */
1264	net->sctp.addip_enable = 0;
1265	net->sctp.addip_noauth = 0;
1266	net->sctp.default_auto_asconf = 0;
1267
1268	/* Enable PR-SCTP by default. */
1269	net->sctp.prsctp_enable = 1;
1270
1271	/* Disable RECONF by default. */
1272	net->sctp.reconf_enable = 0;
1273
1274	/* Disable AUTH by default. */
1275	net->sctp.auth_enable = 0;
1276
1277	/* Enable ECN by default. */
1278	net->sctp.ecn_enable = 1;
1279
1280	/* Set SCOPE policy to enabled */
1281	net->sctp.scope_policy = SCTP_SCOPE_POLICY_ENABLE;
1282
1283	/* Set the default rwnd update threshold */
1284	net->sctp.rwnd_upd_shift = SCTP_DEFAULT_RWND_SHIFT;
1285
1286	/* Initialize maximum autoclose timeout. */
1287	net->sctp.max_autoclose		= INT_MAX / HZ;
1288
1289	status = sctp_sysctl_net_register(net);
1290	if (status)
1291		goto err_sysctl_register;
1292
1293	/* Allocate and initialise sctp mibs.  */
1294	status = init_sctp_mibs(net);
1295	if (status)
1296		goto err_init_mibs;
1297
1298#ifdef CONFIG_PROC_FS
1299	/* Initialize proc fs directory.  */
1300	status = sctp_proc_init(net);
1301	if (status)
1302		goto err_init_proc;
1303#endif
1304
1305	sctp_dbg_objcnt_init(net);
1306
1307	/* Initialize the local address list. */
1308	INIT_LIST_HEAD(&net->sctp.local_addr_list);
1309	spin_lock_init(&net->sctp.local_addr_lock);
1310	sctp_get_local_addr_list(net);
1311
1312	/* Initialize the address event list */
1313	INIT_LIST_HEAD(&net->sctp.addr_waitq);
1314	INIT_LIST_HEAD(&net->sctp.auto_asconf_splist);
1315	spin_lock_init(&net->sctp.addr_wq_lock);
1316	net->sctp.addr_wq_timer.expires = 0;
1317	timer_setup(&net->sctp.addr_wq_timer, sctp_addr_wq_timeout_handler, 0);
1318
1319	return 0;
1320
1321#ifdef CONFIG_PROC_FS
1322err_init_proc:
1323	cleanup_sctp_mibs(net);
1324#endif
1325err_init_mibs:
1326	sctp_sysctl_net_unregister(net);
1327err_sysctl_register:
1328	return status;
1329}
1330
1331static void __net_exit sctp_defaults_exit(struct net *net)
1332{
1333	/* Free the local address list */
1334	sctp_free_addr_wq(net);
1335	sctp_free_local_addr_list(net);
1336
1337#ifdef CONFIG_PROC_FS
1338	remove_proc_subtree("sctp", net->proc_net);
1339	net->sctp.proc_net_sctp = NULL;
1340#endif
1341	cleanup_sctp_mibs(net);
1342	sctp_sysctl_net_unregister(net);
1343}
1344
1345static struct pernet_operations sctp_defaults_ops = {
1346	.init = sctp_defaults_init,
1347	.exit = sctp_defaults_exit,
1348};
1349
1350static int __net_init sctp_ctrlsock_init(struct net *net)
1351{
1352	int status;
1353
1354	/* Initialize the control inode/socket for handling OOTB packets.  */
1355	status = sctp_ctl_sock_init(net);
1356	if (status)
1357		pr_err("Failed to initialize the SCTP control sock\n");
1358
1359	return status;
1360}
1361
1362static void __net_exit sctp_ctrlsock_exit(struct net *net)
1363{
1364	/* Free the control endpoint.  */
1365	inet_ctl_sock_destroy(net->sctp.ctl_sock);
1366}
1367
1368static struct pernet_operations sctp_ctrlsock_ops = {
1369	.init = sctp_ctrlsock_init,
1370	.exit = sctp_ctrlsock_exit,
1371};
1372
1373/* Initialize the universe into something sensible.  */
1374static __init int sctp_init(void)
1375{
1376	unsigned long nr_pages = totalram_pages();
1377	unsigned long limit;
1378	unsigned long goal;
1379	int max_entry_order;
1380	int num_entries;
1381	int max_share;
1382	int status;
1383	int order;
1384	int i;
1385
1386	sock_skb_cb_check_size(sizeof(struct sctp_ulpevent));
1387
1388	/* Allocate bind_bucket and chunk caches. */
1389	status = -ENOBUFS;
1390	sctp_bucket_cachep = kmem_cache_create("sctp_bind_bucket",
1391					       sizeof(struct sctp_bind_bucket),
1392					       0, SLAB_HWCACHE_ALIGN,
1393					       NULL);
1394	if (!sctp_bucket_cachep)
1395		goto out;
1396
1397	sctp_chunk_cachep = kmem_cache_create("sctp_chunk",
1398					       sizeof(struct sctp_chunk),
1399					       0, SLAB_HWCACHE_ALIGN,
1400					       NULL);
1401	if (!sctp_chunk_cachep)
1402		goto err_chunk_cachep;
1403
1404	status = percpu_counter_init(&sctp_sockets_allocated, 0, GFP_KERNEL);
1405	if (status)
1406		goto err_percpu_counter_init;
1407
1408	/* Implementation specific variables. */
1409
1410	/* Initialize default stream count setup information. */
1411	sctp_max_instreams    		= SCTP_DEFAULT_INSTREAMS;
1412	sctp_max_outstreams   		= SCTP_DEFAULT_OUTSTREAMS;
1413
1414	/* Initialize handle used for association ids. */
1415	idr_init(&sctp_assocs_id);
1416
1417	limit = nr_free_buffer_pages() / 8;
1418	limit = max(limit, 128UL);
1419	sysctl_sctp_mem[0] = limit / 4 * 3;
1420	sysctl_sctp_mem[1] = limit;
1421	sysctl_sctp_mem[2] = sysctl_sctp_mem[0] * 2;
1422
1423	/* Set per-socket limits to no more than 1/128 the pressure threshold*/
1424	limit = (sysctl_sctp_mem[1]) << (PAGE_SHIFT - 7);
1425	max_share = min(4UL*1024*1024, limit);
1426
1427	sysctl_sctp_rmem[0] = SK_MEM_QUANTUM; /* give each asoc 1 page min */
1428	sysctl_sctp_rmem[1] = 1500 * SKB_TRUESIZE(1);
1429	sysctl_sctp_rmem[2] = max(sysctl_sctp_rmem[1], max_share);
1430
1431	sysctl_sctp_wmem[0] = SK_MEM_QUANTUM;
1432	sysctl_sctp_wmem[1] = 16*1024;
1433	sysctl_sctp_wmem[2] = max(64*1024, max_share);
1434
1435	/* Size and allocate the association hash table.
1436	 * The methodology is similar to that of the tcp hash tables.
1437	 * Though not identical.  Start by getting a goal size
1438	 */
1439	if (nr_pages >= (128 * 1024))
1440		goal = nr_pages >> (22 - PAGE_SHIFT);
1441	else
1442		goal = nr_pages >> (24 - PAGE_SHIFT);
1443
1444	/* Then compute the page order for said goal */
1445	order = get_order(goal);
1446
1447	/* Now compute the required page order for the maximum sized table we
1448	 * want to create
1449	 */
1450	max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES *
1451				    sizeof(struct sctp_bind_hashbucket));
1452
1453	/* Limit the page order by that maximum hash table size */
1454	order = min(order, max_entry_order);
1455
1456	/* Allocate and initialize the endpoint hash table.  */
1457	sctp_ep_hashsize = 64;
1458	sctp_ep_hashtable =
1459		kmalloc_array(64, sizeof(struct sctp_hashbucket), GFP_KERNEL);
1460	if (!sctp_ep_hashtable) {
1461		pr_err("Failed endpoint_hash alloc\n");
1462		status = -ENOMEM;
1463		goto err_ehash_alloc;
1464	}
1465	for (i = 0; i < sctp_ep_hashsize; i++) {
1466		rwlock_init(&sctp_ep_hashtable[i].lock);
1467		INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain);
1468	}
1469
1470	/* Allocate and initialize the SCTP port hash table.
1471	 * Note that order is initalized to start at the max sized
1472	 * table we want to support.  If we can't get that many pages
1473	 * reduce the order and try again
1474	 */
1475	do {
1476		sctp_port_hashtable = (struct sctp_bind_hashbucket *)
1477			__get_free_pages(GFP_KERNEL | __GFP_NOWARN, order);
1478	} while (!sctp_port_hashtable && --order > 0);
1479
1480	if (!sctp_port_hashtable) {
1481		pr_err("Failed bind hash alloc\n");
1482		status = -ENOMEM;
1483		goto err_bhash_alloc;
1484	}
1485
1486	/* Now compute the number of entries that will fit in the
1487	 * port hash space we allocated
1488	 */
1489	num_entries = (1UL << order) * PAGE_SIZE /
1490		      sizeof(struct sctp_bind_hashbucket);
1491
1492	/* And finish by rounding it down to the nearest power of two.
1493	 * This wastes some memory of course, but it's needed because
1494	 * the hash function operates based on the assumption that
1495	 * the number of entries is a power of two.
1496	 */
1497	sctp_port_hashsize = rounddown_pow_of_two(num_entries);
1498
1499	for (i = 0; i < sctp_port_hashsize; i++) {
1500		spin_lock_init(&sctp_port_hashtable[i].lock);
1501		INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
1502	}
1503
1504	status = sctp_transport_hashtable_init();
1505	if (status)
1506		goto err_thash_alloc;
1507
1508	pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize,
1509		num_entries);
1510
1511	sctp_sysctl_register();
1512
1513	INIT_LIST_HEAD(&sctp_address_families);
1514	sctp_v4_pf_init();
1515	sctp_v6_pf_init();
1516	sctp_sched_ops_init();
1517
1518	status = register_pernet_subsys(&sctp_defaults_ops);
1519	if (status)
1520		goto err_register_defaults;
1521
1522	status = sctp_v4_protosw_init();
1523	if (status)
1524		goto err_protosw_init;
1525
1526	status = sctp_v6_protosw_init();
1527	if (status)
1528		goto err_v6_protosw_init;
1529
1530	status = register_pernet_subsys(&sctp_ctrlsock_ops);
1531	if (status)
1532		goto err_register_ctrlsock;
1533
1534	status = sctp_v4_add_protocol();
1535	if (status)
1536		goto err_add_protocol;
1537
1538	/* Register SCTP with inet6 layer.  */
1539	status = sctp_v6_add_protocol();
1540	if (status)
1541		goto err_v6_add_protocol;
1542
1543	if (sctp_offload_init() < 0)
1544		pr_crit("%s: Cannot add SCTP protocol offload\n", __func__);
1545
1546out:
1547	return status;
1548err_v6_add_protocol:
1549	sctp_v4_del_protocol();
1550err_add_protocol:
1551	unregister_pernet_subsys(&sctp_ctrlsock_ops);
1552err_register_ctrlsock:
1553	sctp_v6_protosw_exit();
1554err_v6_protosw_init:
1555	sctp_v4_protosw_exit();
1556err_protosw_init:
1557	unregister_pernet_subsys(&sctp_defaults_ops);
1558err_register_defaults:
1559	sctp_v4_pf_exit();
1560	sctp_v6_pf_exit();
1561	sctp_sysctl_unregister();
1562	free_pages((unsigned long)sctp_port_hashtable,
1563		   get_order(sctp_port_hashsize *
1564			     sizeof(struct sctp_bind_hashbucket)));
1565err_bhash_alloc:
1566	sctp_transport_hashtable_destroy();
1567err_thash_alloc:
1568	kfree(sctp_ep_hashtable);
1569err_ehash_alloc:
1570	percpu_counter_destroy(&sctp_sockets_allocated);
1571err_percpu_counter_init:
1572	kmem_cache_destroy(sctp_chunk_cachep);
1573err_chunk_cachep:
1574	kmem_cache_destroy(sctp_bucket_cachep);
1575	goto out;
1576}
1577
1578/* Exit handler for the SCTP protocol.  */
1579static __exit void sctp_exit(void)
1580{
1581	/* BUG.  This should probably do something useful like clean
1582	 * up all the remaining associations and all that memory.
1583	 */
1584
1585	/* Unregister with inet6/inet layers. */
1586	sctp_v6_del_protocol();
1587	sctp_v4_del_protocol();
1588
1589	unregister_pernet_subsys(&sctp_ctrlsock_ops);
1590
1591	/* Free protosw registrations */
1592	sctp_v6_protosw_exit();
1593	sctp_v4_protosw_exit();
1594
1595	unregister_pernet_subsys(&sctp_defaults_ops);
1596
1597	/* Unregister with socket layer. */
1598	sctp_v6_pf_exit();
1599	sctp_v4_pf_exit();
1600
1601	sctp_sysctl_unregister();
1602
1603	free_pages((unsigned long)sctp_port_hashtable,
1604		   get_order(sctp_port_hashsize *
1605			     sizeof(struct sctp_bind_hashbucket)));
1606	kfree(sctp_ep_hashtable);
1607	sctp_transport_hashtable_destroy();
1608
1609	percpu_counter_destroy(&sctp_sockets_allocated);
1610
1611	rcu_barrier(); /* Wait for completion of call_rcu()'s */
1612
1613	kmem_cache_destroy(sctp_chunk_cachep);
1614	kmem_cache_destroy(sctp_bucket_cachep);
1615}
1616
1617module_init(sctp_init);
1618module_exit(sctp_exit);
1619
1620/*
1621 * __stringify doesn't likes enums, so use IPPROTO_SCTP value (132) directly.
1622 */
1623MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-132");
1624MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-132");
1625MODULE_AUTHOR("Linux Kernel SCTP developers <linux-sctp@vger.kernel.org>");
1626MODULE_DESCRIPTION("Support for the SCTP protocol (RFC2960)");
1627module_param_named(no_checksums, sctp_checksum_disable, bool, 0644);
1628MODULE_PARM_DESC(no_checksums, "Disable checksums computing and verification");
1629MODULE_LICENSE("GPL");
1630