1 // SPDX-License-Identifier: GPL-2.0-only
2 /*
3 * xfrm_policy.c
4 *
5 * Changes:
6 * Mitsuru KANDA @USAGI
7 * Kazunori MIYAZAWA @USAGI
8 * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
9 * IPv6 support
10 * Kazunori MIYAZAWA @USAGI
11 * YOSHIFUJI Hideaki
12 * Split up af-specific portion
13 * Derek Atkins <derek@ihtfp.com> Add the post_input processor
14 *
15 */
16
17 #include <linux/err.h>
18 #include <linux/slab.h>
19 #include <linux/kmod.h>
20 #include <linux/list.h>
21 #include <linux/spinlock.h>
22 #include <linux/workqueue.h>
23 #include <linux/notifier.h>
24 #include <linux/netdevice.h>
25 #include <linux/netfilter.h>
26 #include <linux/module.h>
27 #include <linux/cache.h>
28 #include <linux/cpu.h>
29 #include <linux/audit.h>
30 #include <linux/rhashtable.h>
31 #include <linux/if_tunnel.h>
32 #include <net/dst.h>
33 #include <net/flow.h>
34 #include <net/inet_ecn.h>
35 #include <net/xfrm.h>
36 #include <net/ip.h>
37 #include <net/gre.h>
38 #if IS_ENABLED(CONFIG_IPV6_MIP6)
39 #include <net/mip6.h>
40 #endif
41 #ifdef CONFIG_XFRM_STATISTICS
42 #include <net/snmp.h>
43 #endif
44 #ifdef CONFIG_XFRM_ESPINTCP
45 #include <net/espintcp.h>
46 #endif
47
48 #include "xfrm_hash.h"
49
50 #define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10))
51 #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
52 #define XFRM_MAX_QUEUE_LEN 100
53
54 struct xfrm_flo {
55 struct dst_entry *dst_orig;
56 u8 flags;
57 };
58
59 /* prefixes smaller than this are stored in lists, not trees. */
60 #define INEXACT_PREFIXLEN_IPV4 16
61 #define INEXACT_PREFIXLEN_IPV6 48
62
63 struct xfrm_pol_inexact_node {
64 struct rb_node node;
65 union {
66 xfrm_address_t addr;
67 struct rcu_head rcu;
68 };
69 u8 prefixlen;
70
71 struct rb_root root;
72
73 /* the policies matching this node, can be empty list */
74 struct hlist_head hhead;
75 };
76
77 /* xfrm inexact policy search tree:
78 * xfrm_pol_inexact_bin = hash(dir,type,family,if_id);
79 * |
80 * +---- root_d: sorted by daddr:prefix
81 * | |
82 * | xfrm_pol_inexact_node
83 * | |
84 * | +- root: sorted by saddr/prefix
85 * | | |
86 * | | xfrm_pol_inexact_node
87 * | | |
88 * | | + root: unused
89 * | | |
90 * | | + hhead: saddr:daddr policies
91 * | |
92 * | +- coarse policies and all any:daddr policies
93 * |
94 * +---- root_s: sorted by saddr:prefix
95 * | |
96 * | xfrm_pol_inexact_node
97 * | |
98 * | + root: unused
99 * | |
100 * | + hhead: saddr:any policies
101 * |
102 * +---- coarse policies and all any:any policies
103 *
104 * Lookups return four candidate lists:
105 * 1. any:any list from top-level xfrm_pol_inexact_bin
106 * 2. any:daddr list from daddr tree
107 * 3. saddr:daddr list from 2nd level daddr tree
108 * 4. saddr:any list from saddr tree
109 *
110 * This result set then needs to be searched for the policy with
111 * the lowest priority. If two results have same prio, youngest one wins.
112 */
113
114 struct xfrm_pol_inexact_key {
115 possible_net_t net;
116 u32 if_id;
117 u16 family;
118 u8 dir, type;
119 };
120
121 struct xfrm_pol_inexact_bin {
122 struct xfrm_pol_inexact_key k;
123 struct rhash_head head;
124 /* list containing '*:*' policies */
125 struct hlist_head hhead;
126
127 seqcount_spinlock_t count;
128 /* tree sorted by daddr/prefix */
129 struct rb_root root_d;
130
131 /* tree sorted by saddr/prefix */
132 struct rb_root root_s;
133
134 /* slow path below */
135 struct list_head inexact_bins;
136 struct rcu_head rcu;
137 };
138
139 enum xfrm_pol_inexact_candidate_type {
140 XFRM_POL_CAND_BOTH,
141 XFRM_POL_CAND_SADDR,
142 XFRM_POL_CAND_DADDR,
143 XFRM_POL_CAND_ANY,
144
145 XFRM_POL_CAND_MAX,
146 };
147
148 struct xfrm_pol_inexact_candidates {
149 struct hlist_head *res[XFRM_POL_CAND_MAX];
150 };
151
152 static DEFINE_SPINLOCK(xfrm_if_cb_lock);
153 static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
154
155 static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
156 static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
157 __read_mostly;
158
159 static struct kmem_cache *xfrm_dst_cache __ro_after_init;
160
161 static struct rhashtable xfrm_policy_inexact_table;
162 static const struct rhashtable_params xfrm_pol_inexact_params;
163
164 static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr);
165 static int stale_bundle(struct dst_entry *dst);
166 static int xfrm_bundle_ok(struct xfrm_dst *xdst);
167 static void xfrm_policy_queue_process(struct timer_list *t);
168
169 static void __xfrm_policy_link(struct xfrm_policy *pol, int dir);
170 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
171 int dir);
172
173 static struct xfrm_pol_inexact_bin *
174 xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir,
175 u32 if_id);
176
177 static struct xfrm_pol_inexact_bin *
178 xfrm_policy_inexact_lookup_rcu(struct net *net,
179 u8 type, u16 family, u8 dir, u32 if_id);
180 static struct xfrm_policy *
181 xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
182 bool excl);
183 static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
184 struct xfrm_policy *policy);
185
186 static bool
187 xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
188 struct xfrm_pol_inexact_bin *b,
189 const xfrm_address_t *saddr,
190 const xfrm_address_t *daddr);
191
xfrm_pol_hold_rcu(struct xfrm_policy * policy)192 static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy)
193 {
194 return refcount_inc_not_zero(&policy->refcnt);
195 }
196
197 static inline bool
__xfrm4_selector_match(const struct xfrm_selector * sel,const struct flowi * fl)198 __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
199 {
200 const struct flowi4 *fl4 = &fl->u.ip4;
201
202 return addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) &&
203 addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) &&
204 !((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) &&
205 !((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) &&
206 (fl4->flowi4_proto == sel->proto || !sel->proto) &&
207 (fl4->flowi4_oif == sel->ifindex || !sel->ifindex);
208 }
209
210 static inline bool
__xfrm6_selector_match(const struct xfrm_selector * sel,const struct flowi * fl)211 __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
212 {
213 const struct flowi6 *fl6 = &fl->u.ip6;
214
215 return addr_match(&fl6->daddr, &sel->daddr, sel->prefixlen_d) &&
216 addr_match(&fl6->saddr, &sel->saddr, sel->prefixlen_s) &&
217 !((xfrm_flowi_dport(fl, &fl6->uli) ^ sel->dport) & sel->dport_mask) &&
218 !((xfrm_flowi_sport(fl, &fl6->uli) ^ sel->sport) & sel->sport_mask) &&
219 (fl6->flowi6_proto == sel->proto || !sel->proto) &&
220 (fl6->flowi6_oif == sel->ifindex || !sel->ifindex);
221 }
222
xfrm_selector_match(const struct xfrm_selector * sel,const struct flowi * fl,unsigned short family)223 bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl,
224 unsigned short family)
225 {
226 switch (family) {
227 case AF_INET:
228 return __xfrm4_selector_match(sel, fl);
229 case AF_INET6:
230 return __xfrm6_selector_match(sel, fl);
231 }
232 return false;
233 }
234
xfrm_policy_get_afinfo(unsigned short family)235 static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family)
236 {
237 const struct xfrm_policy_afinfo *afinfo;
238
239 if (unlikely(family >= ARRAY_SIZE(xfrm_policy_afinfo)))
240 return NULL;
241 rcu_read_lock();
242 afinfo = rcu_dereference(xfrm_policy_afinfo[family]);
243 if (unlikely(!afinfo))
244 rcu_read_unlock();
245 return afinfo;
246 }
247
248 /* Called with rcu_read_lock(). */
xfrm_if_get_cb(void)249 static const struct xfrm_if_cb *xfrm_if_get_cb(void)
250 {
251 return rcu_dereference(xfrm_if_cb);
252 }
253
__xfrm_dst_lookup(struct net * net,int tos,int oif,const xfrm_address_t * saddr,const xfrm_address_t * daddr,int family,u32 mark)254 struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
255 const xfrm_address_t *saddr,
256 const xfrm_address_t *daddr,
257 int family, u32 mark)
258 {
259 const struct xfrm_policy_afinfo *afinfo;
260 struct dst_entry *dst;
261
262 afinfo = xfrm_policy_get_afinfo(family);
263 if (unlikely(afinfo == NULL))
264 return ERR_PTR(-EAFNOSUPPORT);
265
266 dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr, mark);
267
268 rcu_read_unlock();
269
270 return dst;
271 }
272 EXPORT_SYMBOL(__xfrm_dst_lookup);
273
xfrm_dst_lookup(struct xfrm_state * x,int tos,int oif,xfrm_address_t * prev_saddr,xfrm_address_t * prev_daddr,int family,u32 mark)274 static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
275 int tos, int oif,
276 xfrm_address_t *prev_saddr,
277 xfrm_address_t *prev_daddr,
278 int family, u32 mark)
279 {
280 struct net *net = xs_net(x);
281 xfrm_address_t *saddr = &x->props.saddr;
282 xfrm_address_t *daddr = &x->id.daddr;
283 struct dst_entry *dst;
284
285 if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) {
286 saddr = x->coaddr;
287 daddr = prev_daddr;
288 }
289 if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) {
290 saddr = prev_saddr;
291 daddr = x->coaddr;
292 }
293
294 dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family, mark);
295
296 if (!IS_ERR(dst)) {
297 if (prev_saddr != saddr)
298 memcpy(prev_saddr, saddr, sizeof(*prev_saddr));
299 if (prev_daddr != daddr)
300 memcpy(prev_daddr, daddr, sizeof(*prev_daddr));
301 }
302
303 return dst;
304 }
305
make_jiffies(long secs)306 static inline unsigned long make_jiffies(long secs)
307 {
308 if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ)
309 return MAX_SCHEDULE_TIMEOUT-1;
310 else
311 return secs*HZ;
312 }
313
xfrm_policy_timer(struct timer_list * t)314 static void xfrm_policy_timer(struct timer_list *t)
315 {
316 struct xfrm_policy *xp = from_timer(xp, t, timer);
317 time64_t now = ktime_get_real_seconds();
318 time64_t next = TIME64_MAX;
319 int warn = 0;
320 int dir;
321
322 read_lock(&xp->lock);
323
324 if (unlikely(xp->walk.dead))
325 goto out;
326
327 dir = xfrm_policy_id2dir(xp->index);
328
329 if (xp->lft.hard_add_expires_seconds) {
330 time64_t tmo = xp->lft.hard_add_expires_seconds +
331 xp->curlft.add_time - now;
332 if (tmo <= 0)
333 goto expired;
334 if (tmo < next)
335 next = tmo;
336 }
337 if (xp->lft.hard_use_expires_seconds) {
338 time64_t tmo = xp->lft.hard_use_expires_seconds +
339 (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now;
340 if (tmo <= 0)
341 goto expired;
342 if (tmo < next)
343 next = tmo;
344 }
345 if (xp->lft.soft_add_expires_seconds) {
346 time64_t tmo = xp->lft.soft_add_expires_seconds +
347 xp->curlft.add_time - now;
348 if (tmo <= 0) {
349 warn = 1;
350 tmo = XFRM_KM_TIMEOUT;
351 }
352 if (tmo < next)
353 next = tmo;
354 }
355 if (xp->lft.soft_use_expires_seconds) {
356 time64_t tmo = xp->lft.soft_use_expires_seconds +
357 (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now;
358 if (tmo <= 0) {
359 warn = 1;
360 tmo = XFRM_KM_TIMEOUT;
361 }
362 if (tmo < next)
363 next = tmo;
364 }
365
366 if (warn)
367 km_policy_expired(xp, dir, 0, 0);
368 if (next != TIME64_MAX &&
369 !mod_timer(&xp->timer, jiffies + make_jiffies(next)))
370 xfrm_pol_hold(xp);
371
372 out:
373 read_unlock(&xp->lock);
374 xfrm_pol_put(xp);
375 return;
376
377 expired:
378 read_unlock(&xp->lock);
379 if (!xfrm_policy_delete(xp, dir))
380 km_policy_expired(xp, dir, 1, 0);
381 xfrm_pol_put(xp);
382 }
383
384 /* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2
385 * SPD calls.
386 */
387
xfrm_policy_alloc(struct net * net,gfp_t gfp)388 struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
389 {
390 struct xfrm_policy *policy;
391
392 policy = kzalloc(sizeof(struct xfrm_policy), gfp);
393
394 if (policy) {
395 write_pnet(&policy->xp_net, net);
396 INIT_LIST_HEAD(&policy->walk.all);
397 INIT_HLIST_NODE(&policy->bydst_inexact_list);
398 INIT_HLIST_NODE(&policy->bydst);
399 INIT_HLIST_NODE(&policy->byidx);
400 rwlock_init(&policy->lock);
401 refcount_set(&policy->refcnt, 1);
402 skb_queue_head_init(&policy->polq.hold_queue);
403 timer_setup(&policy->timer, xfrm_policy_timer, 0);
404 timer_setup(&policy->polq.hold_timer,
405 xfrm_policy_queue_process, 0);
406 }
407 return policy;
408 }
409 EXPORT_SYMBOL(xfrm_policy_alloc);
410
xfrm_policy_destroy_rcu(struct rcu_head * head)411 static void xfrm_policy_destroy_rcu(struct rcu_head *head)
412 {
413 struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu);
414
415 security_xfrm_policy_free(policy->security);
416 kfree(policy);
417 }
418
419 /* Destroy xfrm_policy: descendant resources must be released to this moment. */
420
xfrm_policy_destroy(struct xfrm_policy * policy)421 void xfrm_policy_destroy(struct xfrm_policy *policy)
422 {
423 BUG_ON(!policy->walk.dead);
424
425 if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer))
426 BUG();
427
428 xfrm_dev_policy_free(policy);
429 call_rcu(&policy->rcu, xfrm_policy_destroy_rcu);
430 }
431 EXPORT_SYMBOL(xfrm_policy_destroy);
432
433 /* Rule must be locked. Release descendant resources, announce
434 * entry dead. The rule must be unlinked from lists to the moment.
435 */
436
xfrm_policy_kill(struct xfrm_policy * policy)437 static void xfrm_policy_kill(struct xfrm_policy *policy)
438 {
439 write_lock_bh(&policy->lock);
440 policy->walk.dead = 1;
441 write_unlock_bh(&policy->lock);
442
443 atomic_inc(&policy->genid);
444
445 if (del_timer(&policy->polq.hold_timer))
446 xfrm_pol_put(policy);
447 skb_queue_purge(&policy->polq.hold_queue);
448
449 if (del_timer(&policy->timer))
450 xfrm_pol_put(policy);
451
452 xfrm_pol_put(policy);
453 }
454
455 static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024;
456
idx_hash(struct net * net,u32 index)457 static inline unsigned int idx_hash(struct net *net, u32 index)
458 {
459 return __idx_hash(index, net->xfrm.policy_idx_hmask);
460 }
461
462 /* calculate policy hash thresholds */
__get_hash_thresh(struct net * net,unsigned short family,int dir,u8 * dbits,u8 * sbits)463 static void __get_hash_thresh(struct net *net,
464 unsigned short family, int dir,
465 u8 *dbits, u8 *sbits)
466 {
467 switch (family) {
468 case AF_INET:
469 *dbits = net->xfrm.policy_bydst[dir].dbits4;
470 *sbits = net->xfrm.policy_bydst[dir].sbits4;
471 break;
472
473 case AF_INET6:
474 *dbits = net->xfrm.policy_bydst[dir].dbits6;
475 *sbits = net->xfrm.policy_bydst[dir].sbits6;
476 break;
477
478 default:
479 *dbits = 0;
480 *sbits = 0;
481 }
482 }
483
policy_hash_bysel(struct net * net,const struct xfrm_selector * sel,unsigned short family,int dir)484 static struct hlist_head *policy_hash_bysel(struct net *net,
485 const struct xfrm_selector *sel,
486 unsigned short family, int dir)
487 {
488 unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
489 unsigned int hash;
490 u8 dbits;
491 u8 sbits;
492
493 __get_hash_thresh(net, family, dir, &dbits, &sbits);
494 hash = __sel_hash(sel, family, hmask, dbits, sbits);
495
496 if (hash == hmask + 1)
497 return NULL;
498
499 return rcu_dereference_check(net->xfrm.policy_bydst[dir].table,
500 lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash;
501 }
502
policy_hash_direct(struct net * net,const xfrm_address_t * daddr,const xfrm_address_t * saddr,unsigned short family,int dir)503 static struct hlist_head *policy_hash_direct(struct net *net,
504 const xfrm_address_t *daddr,
505 const xfrm_address_t *saddr,
506 unsigned short family, int dir)
507 {
508 unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
509 unsigned int hash;
510 u8 dbits;
511 u8 sbits;
512
513 __get_hash_thresh(net, family, dir, &dbits, &sbits);
514 hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits);
515
516 return rcu_dereference_check(net->xfrm.policy_bydst[dir].table,
517 lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash;
518 }
519
xfrm_dst_hash_transfer(struct net * net,struct hlist_head * list,struct hlist_head * ndsttable,unsigned int nhashmask,int dir)520 static void xfrm_dst_hash_transfer(struct net *net,
521 struct hlist_head *list,
522 struct hlist_head *ndsttable,
523 unsigned int nhashmask,
524 int dir)
525 {
526 struct hlist_node *tmp, *entry0 = NULL;
527 struct xfrm_policy *pol;
528 unsigned int h0 = 0;
529 u8 dbits;
530 u8 sbits;
531
532 redo:
533 hlist_for_each_entry_safe(pol, tmp, list, bydst) {
534 unsigned int h;
535
536 __get_hash_thresh(net, pol->family, dir, &dbits, &sbits);
537 h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr,
538 pol->family, nhashmask, dbits, sbits);
539 if (!entry0 || pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
540 hlist_del_rcu(&pol->bydst);
541 hlist_add_head_rcu(&pol->bydst, ndsttable + h);
542 h0 = h;
543 } else {
544 if (h != h0)
545 continue;
546 hlist_del_rcu(&pol->bydst);
547 hlist_add_behind_rcu(&pol->bydst, entry0);
548 }
549 entry0 = &pol->bydst;
550 }
551 if (!hlist_empty(list)) {
552 entry0 = NULL;
553 goto redo;
554 }
555 }
556
xfrm_idx_hash_transfer(struct hlist_head * list,struct hlist_head * nidxtable,unsigned int nhashmask)557 static void xfrm_idx_hash_transfer(struct hlist_head *list,
558 struct hlist_head *nidxtable,
559 unsigned int nhashmask)
560 {
561 struct hlist_node *tmp;
562 struct xfrm_policy *pol;
563
564 hlist_for_each_entry_safe(pol, tmp, list, byidx) {
565 unsigned int h;
566
567 h = __idx_hash(pol->index, nhashmask);
568 hlist_add_head(&pol->byidx, nidxtable+h);
569 }
570 }
571
xfrm_new_hash_mask(unsigned int old_hmask)572 static unsigned long xfrm_new_hash_mask(unsigned int old_hmask)
573 {
574 return ((old_hmask + 1) << 1) - 1;
575 }
576
xfrm_bydst_resize(struct net * net,int dir)577 static void xfrm_bydst_resize(struct net *net, int dir)
578 {
579 unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
580 unsigned int nhashmask = xfrm_new_hash_mask(hmask);
581 unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head);
582 struct hlist_head *ndst = xfrm_hash_alloc(nsize);
583 struct hlist_head *odst;
584 int i;
585
586 if (!ndst)
587 return;
588
589 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
590 write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
591
592 odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
593 lockdep_is_held(&net->xfrm.xfrm_policy_lock));
594
595 for (i = hmask; i >= 0; i--)
596 xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir);
597
598 rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst);
599 net->xfrm.policy_bydst[dir].hmask = nhashmask;
600
601 write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
602 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
603
604 synchronize_rcu();
605
606 xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head));
607 }
608
xfrm_byidx_resize(struct net * net)609 static void xfrm_byidx_resize(struct net *net)
610 {
611 unsigned int hmask = net->xfrm.policy_idx_hmask;
612 unsigned int nhashmask = xfrm_new_hash_mask(hmask);
613 unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head);
614 struct hlist_head *oidx = net->xfrm.policy_byidx;
615 struct hlist_head *nidx = xfrm_hash_alloc(nsize);
616 int i;
617
618 if (!nidx)
619 return;
620
621 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
622
623 for (i = hmask; i >= 0; i--)
624 xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask);
625
626 net->xfrm.policy_byidx = nidx;
627 net->xfrm.policy_idx_hmask = nhashmask;
628
629 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
630
631 xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head));
632 }
633
xfrm_bydst_should_resize(struct net * net,int dir,int * total)634 static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total)
635 {
636 unsigned int cnt = net->xfrm.policy_count[dir];
637 unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
638
639 if (total)
640 *total += cnt;
641
642 if ((hmask + 1) < xfrm_policy_hashmax &&
643 cnt > hmask)
644 return 1;
645
646 return 0;
647 }
648
xfrm_byidx_should_resize(struct net * net,int total)649 static inline int xfrm_byidx_should_resize(struct net *net, int total)
650 {
651 unsigned int hmask = net->xfrm.policy_idx_hmask;
652
653 if ((hmask + 1) < xfrm_policy_hashmax &&
654 total > hmask)
655 return 1;
656
657 return 0;
658 }
659
xfrm_spd_getinfo(struct net * net,struct xfrmk_spdinfo * si)660 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
661 {
662 si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN];
663 si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT];
664 si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD];
665 si->inscnt = net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX];
666 si->outscnt = net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX];
667 si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX];
668 si->spdhcnt = net->xfrm.policy_idx_hmask;
669 si->spdhmcnt = xfrm_policy_hashmax;
670 }
671 EXPORT_SYMBOL(xfrm_spd_getinfo);
672
673 static DEFINE_MUTEX(hash_resize_mutex);
xfrm_hash_resize(struct work_struct * work)674 static void xfrm_hash_resize(struct work_struct *work)
675 {
676 struct net *net = container_of(work, struct net, xfrm.policy_hash_work);
677 int dir, total;
678
679 mutex_lock(&hash_resize_mutex);
680
681 total = 0;
682 for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
683 if (xfrm_bydst_should_resize(net, dir, &total))
684 xfrm_bydst_resize(net, dir);
685 }
686 if (xfrm_byidx_should_resize(net, total))
687 xfrm_byidx_resize(net);
688
689 mutex_unlock(&hash_resize_mutex);
690 }
691
692 /* Make sure *pol can be inserted into fastbin.
693 * Useful to check that later insert requests will be successful
694 * (provided xfrm_policy_lock is held throughout).
695 */
696 static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_alloc_bin(const struct xfrm_policy * pol,u8 dir)697 xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
698 {
699 struct xfrm_pol_inexact_bin *bin, *prev;
700 struct xfrm_pol_inexact_key k = {
701 .family = pol->family,
702 .type = pol->type,
703 .dir = dir,
704 .if_id = pol->if_id,
705 };
706 struct net *net = xp_net(pol);
707
708 lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
709
710 write_pnet(&k.net, net);
711 bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k,
712 xfrm_pol_inexact_params);
713 if (bin)
714 return bin;
715
716 bin = kzalloc(sizeof(*bin), GFP_ATOMIC);
717 if (!bin)
718 return NULL;
719
720 bin->k = k;
721 INIT_HLIST_HEAD(&bin->hhead);
722 bin->root_d = RB_ROOT;
723 bin->root_s = RB_ROOT;
724 seqcount_spinlock_init(&bin->count, &net->xfrm.xfrm_policy_lock);
725
726 prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
727 &bin->k, &bin->head,
728 xfrm_pol_inexact_params);
729 if (!prev) {
730 list_add(&bin->inexact_bins, &net->xfrm.inexact_bins);
731 return bin;
732 }
733
734 kfree(bin);
735
736 return IS_ERR(prev) ? NULL : prev;
737 }
738
xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t * addr,int family,u8 prefixlen)739 static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr,
740 int family, u8 prefixlen)
741 {
742 if (xfrm_addr_any(addr, family))
743 return true;
744
745 if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6)
746 return true;
747
748 if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4)
749 return true;
750
751 return false;
752 }
753
754 static bool
xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy * policy)755 xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy)
756 {
757 const xfrm_address_t *addr;
758 bool saddr_any, daddr_any;
759 u8 prefixlen;
760
761 addr = &policy->selector.saddr;
762 prefixlen = policy->selector.prefixlen_s;
763
764 saddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
765 policy->family,
766 prefixlen);
767 addr = &policy->selector.daddr;
768 prefixlen = policy->selector.prefixlen_d;
769 daddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
770 policy->family,
771 prefixlen);
772 return saddr_any && daddr_any;
773 }
774
xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node * node,const xfrm_address_t * addr,u8 prefixlen)775 static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node,
776 const xfrm_address_t *addr, u8 prefixlen)
777 {
778 node->addr = *addr;
779 node->prefixlen = prefixlen;
780 }
781
782 static struct xfrm_pol_inexact_node *
xfrm_pol_inexact_node_alloc(const xfrm_address_t * addr,u8 prefixlen)783 xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen)
784 {
785 struct xfrm_pol_inexact_node *node;
786
787 node = kzalloc(sizeof(*node), GFP_ATOMIC);
788 if (node)
789 xfrm_pol_inexact_node_init(node, addr, prefixlen);
790
791 return node;
792 }
793
xfrm_policy_addr_delta(const xfrm_address_t * a,const xfrm_address_t * b,u8 prefixlen,u16 family)794 static int xfrm_policy_addr_delta(const xfrm_address_t *a,
795 const xfrm_address_t *b,
796 u8 prefixlen, u16 family)
797 {
798 u32 ma, mb, mask;
799 unsigned int pdw, pbi;
800 int delta = 0;
801
802 switch (family) {
803 case AF_INET:
804 if (prefixlen == 0)
805 return 0;
806 mask = ~0U << (32 - prefixlen);
807 ma = ntohl(a->a4) & mask;
808 mb = ntohl(b->a4) & mask;
809 if (ma < mb)
810 delta = -1;
811 else if (ma > mb)
812 delta = 1;
813 break;
814 case AF_INET6:
815 pdw = prefixlen >> 5;
816 pbi = prefixlen & 0x1f;
817
818 if (pdw) {
819 delta = memcmp(a->a6, b->a6, pdw << 2);
820 if (delta)
821 return delta;
822 }
823 if (pbi) {
824 mask = ~0U << (32 - pbi);
825 ma = ntohl(a->a6[pdw]) & mask;
826 mb = ntohl(b->a6[pdw]) & mask;
827 if (ma < mb)
828 delta = -1;
829 else if (ma > mb)
830 delta = 1;
831 }
832 break;
833 default:
834 break;
835 }
836
837 return delta;
838 }
839
xfrm_policy_inexact_list_reinsert(struct net * net,struct xfrm_pol_inexact_node * n,u16 family)840 static void xfrm_policy_inexact_list_reinsert(struct net *net,
841 struct xfrm_pol_inexact_node *n,
842 u16 family)
843 {
844 unsigned int matched_s, matched_d;
845 struct xfrm_policy *policy, *p;
846
847 matched_s = 0;
848 matched_d = 0;
849
850 list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
851 struct hlist_node *newpos = NULL;
852 bool matches_s, matches_d;
853
854 if (!policy->bydst_reinsert)
855 continue;
856
857 WARN_ON_ONCE(policy->family != family);
858
859 policy->bydst_reinsert = false;
860 hlist_for_each_entry(p, &n->hhead, bydst) {
861 if (policy->priority > p->priority)
862 newpos = &p->bydst;
863 else if (policy->priority == p->priority &&
864 policy->pos > p->pos)
865 newpos = &p->bydst;
866 else
867 break;
868 }
869
870 if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
871 hlist_add_behind_rcu(&policy->bydst, newpos);
872 else
873 hlist_add_head_rcu(&policy->bydst, &n->hhead);
874
875 /* paranoia checks follow.
876 * Check that the reinserted policy matches at least
877 * saddr or daddr for current node prefix.
878 *
879 * Matching both is fine, matching saddr in one policy
880 * (but not daddr) and then matching only daddr in another
881 * is a bug.
882 */
883 matches_s = xfrm_policy_addr_delta(&policy->selector.saddr,
884 &n->addr,
885 n->prefixlen,
886 family) == 0;
887 matches_d = xfrm_policy_addr_delta(&policy->selector.daddr,
888 &n->addr,
889 n->prefixlen,
890 family) == 0;
891 if (matches_s && matches_d)
892 continue;
893
894 WARN_ON_ONCE(!matches_s && !matches_d);
895 if (matches_s)
896 matched_s++;
897 if (matches_d)
898 matched_d++;
899 WARN_ON_ONCE(matched_s && matched_d);
900 }
901 }
902
xfrm_policy_inexact_node_reinsert(struct net * net,struct xfrm_pol_inexact_node * n,struct rb_root * new,u16 family)903 static void xfrm_policy_inexact_node_reinsert(struct net *net,
904 struct xfrm_pol_inexact_node *n,
905 struct rb_root *new,
906 u16 family)
907 {
908 struct xfrm_pol_inexact_node *node;
909 struct rb_node **p, *parent;
910
911 /* we should not have another subtree here */
912 WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root));
913 restart:
914 parent = NULL;
915 p = &new->rb_node;
916 while (*p) {
917 u8 prefixlen;
918 int delta;
919
920 parent = *p;
921 node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
922
923 prefixlen = min(node->prefixlen, n->prefixlen);
924
925 delta = xfrm_policy_addr_delta(&n->addr, &node->addr,
926 prefixlen, family);
927 if (delta < 0) {
928 p = &parent->rb_left;
929 } else if (delta > 0) {
930 p = &parent->rb_right;
931 } else {
932 bool same_prefixlen = node->prefixlen == n->prefixlen;
933 struct xfrm_policy *tmp;
934
935 hlist_for_each_entry(tmp, &n->hhead, bydst) {
936 tmp->bydst_reinsert = true;
937 hlist_del_rcu(&tmp->bydst);
938 }
939
940 node->prefixlen = prefixlen;
941
942 xfrm_policy_inexact_list_reinsert(net, node, family);
943
944 if (same_prefixlen) {
945 kfree_rcu(n, rcu);
946 return;
947 }
948
949 rb_erase(*p, new);
950 kfree_rcu(n, rcu);
951 n = node;
952 goto restart;
953 }
954 }
955
956 rb_link_node_rcu(&n->node, parent, p);
957 rb_insert_color(&n->node, new);
958 }
959
960 /* merge nodes v and n */
xfrm_policy_inexact_node_merge(struct net * net,struct xfrm_pol_inexact_node * v,struct xfrm_pol_inexact_node * n,u16 family)961 static void xfrm_policy_inexact_node_merge(struct net *net,
962 struct xfrm_pol_inexact_node *v,
963 struct xfrm_pol_inexact_node *n,
964 u16 family)
965 {
966 struct xfrm_pol_inexact_node *node;
967 struct xfrm_policy *tmp;
968 struct rb_node *rnode;
969
970 /* To-be-merged node v has a subtree.
971 *
972 * Dismantle it and insert its nodes to n->root.
973 */
974 while ((rnode = rb_first(&v->root)) != NULL) {
975 node = rb_entry(rnode, struct xfrm_pol_inexact_node, node);
976 rb_erase(&node->node, &v->root);
977 xfrm_policy_inexact_node_reinsert(net, node, &n->root,
978 family);
979 }
980
981 hlist_for_each_entry(tmp, &v->hhead, bydst) {
982 tmp->bydst_reinsert = true;
983 hlist_del_rcu(&tmp->bydst);
984 }
985
986 xfrm_policy_inexact_list_reinsert(net, n, family);
987 }
988
989 static struct xfrm_pol_inexact_node *
xfrm_policy_inexact_insert_node(struct net * net,struct rb_root * root,xfrm_address_t * addr,u16 family,u8 prefixlen,u8 dir)990 xfrm_policy_inexact_insert_node(struct net *net,
991 struct rb_root *root,
992 xfrm_address_t *addr,
993 u16 family, u8 prefixlen, u8 dir)
994 {
995 struct xfrm_pol_inexact_node *cached = NULL;
996 struct rb_node **p, *parent = NULL;
997 struct xfrm_pol_inexact_node *node;
998
999 p = &root->rb_node;
1000 while (*p) {
1001 int delta;
1002
1003 parent = *p;
1004 node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
1005
1006 delta = xfrm_policy_addr_delta(addr, &node->addr,
1007 node->prefixlen,
1008 family);
1009 if (delta == 0 && prefixlen >= node->prefixlen) {
1010 WARN_ON_ONCE(cached); /* ipsec policies got lost */
1011 return node;
1012 }
1013
1014 if (delta < 0)
1015 p = &parent->rb_left;
1016 else
1017 p = &parent->rb_right;
1018
1019 if (prefixlen < node->prefixlen) {
1020 delta = xfrm_policy_addr_delta(addr, &node->addr,
1021 prefixlen,
1022 family);
1023 if (delta)
1024 continue;
1025
1026 /* This node is a subnet of the new prefix. It needs
1027 * to be removed and re-inserted with the smaller
1028 * prefix and all nodes that are now also covered
1029 * by the reduced prefixlen.
1030 */
1031 rb_erase(&node->node, root);
1032
1033 if (!cached) {
1034 xfrm_pol_inexact_node_init(node, addr,
1035 prefixlen);
1036 cached = node;
1037 } else {
1038 /* This node also falls within the new
1039 * prefixlen. Merge the to-be-reinserted
1040 * node and this one.
1041 */
1042 xfrm_policy_inexact_node_merge(net, node,
1043 cached, family);
1044 kfree_rcu(node, rcu);
1045 }
1046
1047 /* restart */
1048 p = &root->rb_node;
1049 parent = NULL;
1050 }
1051 }
1052
1053 node = cached;
1054 if (!node) {
1055 node = xfrm_pol_inexact_node_alloc(addr, prefixlen);
1056 if (!node)
1057 return NULL;
1058 }
1059
1060 rb_link_node_rcu(&node->node, parent, p);
1061 rb_insert_color(&node->node, root);
1062
1063 return node;
1064 }
1065
xfrm_policy_inexact_gc_tree(struct rb_root * r,bool rm)1066 static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm)
1067 {
1068 struct xfrm_pol_inexact_node *node;
1069 struct rb_node *rn = rb_first(r);
1070
1071 while (rn) {
1072 node = rb_entry(rn, struct xfrm_pol_inexact_node, node);
1073
1074 xfrm_policy_inexact_gc_tree(&node->root, rm);
1075 rn = rb_next(rn);
1076
1077 if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) {
1078 WARN_ON_ONCE(rm);
1079 continue;
1080 }
1081
1082 rb_erase(&node->node, r);
1083 kfree_rcu(node, rcu);
1084 }
1085 }
1086
__xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin * b,bool net_exit)1087 static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit)
1088 {
1089 write_seqcount_begin(&b->count);
1090 xfrm_policy_inexact_gc_tree(&b->root_d, net_exit);
1091 xfrm_policy_inexact_gc_tree(&b->root_s, net_exit);
1092 write_seqcount_end(&b->count);
1093
1094 if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) ||
1095 !hlist_empty(&b->hhead)) {
1096 WARN_ON_ONCE(net_exit);
1097 return;
1098 }
1099
1100 if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head,
1101 xfrm_pol_inexact_params) == 0) {
1102 list_del(&b->inexact_bins);
1103 kfree_rcu(b, rcu);
1104 }
1105 }
1106
xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin * b)1107 static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b)
1108 {
1109 struct net *net = read_pnet(&b->k.net);
1110
1111 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1112 __xfrm_policy_inexact_prune_bin(b, false);
1113 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1114 }
1115
__xfrm_policy_inexact_flush(struct net * net)1116 static void __xfrm_policy_inexact_flush(struct net *net)
1117 {
1118 struct xfrm_pol_inexact_bin *bin, *t;
1119
1120 lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
1121
1122 list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins)
1123 __xfrm_policy_inexact_prune_bin(bin, false);
1124 }
1125
1126 static struct hlist_head *
xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin * bin,struct xfrm_policy * policy,u8 dir)1127 xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
1128 struct xfrm_policy *policy, u8 dir)
1129 {
1130 struct xfrm_pol_inexact_node *n;
1131 struct net *net;
1132
1133 net = xp_net(policy);
1134 lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
1135
1136 if (xfrm_policy_inexact_insert_use_any_list(policy))
1137 return &bin->hhead;
1138
1139 if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
1140 policy->family,
1141 policy->selector.prefixlen_d)) {
1142 write_seqcount_begin(&bin->count);
1143 n = xfrm_policy_inexact_insert_node(net,
1144 &bin->root_s,
1145 &policy->selector.saddr,
1146 policy->family,
1147 policy->selector.prefixlen_s,
1148 dir);
1149 write_seqcount_end(&bin->count);
1150 if (!n)
1151 return NULL;
1152
1153 return &n->hhead;
1154 }
1155
1156 /* daddr is fixed */
1157 write_seqcount_begin(&bin->count);
1158 n = xfrm_policy_inexact_insert_node(net,
1159 &bin->root_d,
1160 &policy->selector.daddr,
1161 policy->family,
1162 policy->selector.prefixlen_d, dir);
1163 write_seqcount_end(&bin->count);
1164 if (!n)
1165 return NULL;
1166
1167 /* saddr is wildcard */
1168 if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
1169 policy->family,
1170 policy->selector.prefixlen_s))
1171 return &n->hhead;
1172
1173 write_seqcount_begin(&bin->count);
1174 n = xfrm_policy_inexact_insert_node(net,
1175 &n->root,
1176 &policy->selector.saddr,
1177 policy->family,
1178 policy->selector.prefixlen_s, dir);
1179 write_seqcount_end(&bin->count);
1180 if (!n)
1181 return NULL;
1182
1183 return &n->hhead;
1184 }
1185
1186 static struct xfrm_policy *
xfrm_policy_inexact_insert(struct xfrm_policy * policy,u8 dir,int excl)1187 xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
1188 {
1189 struct xfrm_pol_inexact_bin *bin;
1190 struct xfrm_policy *delpol;
1191 struct hlist_head *chain;
1192 struct net *net;
1193
1194 bin = xfrm_policy_inexact_alloc_bin(policy, dir);
1195 if (!bin)
1196 return ERR_PTR(-ENOMEM);
1197
1198 net = xp_net(policy);
1199 lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
1200
1201 chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir);
1202 if (!chain) {
1203 __xfrm_policy_inexact_prune_bin(bin, false);
1204 return ERR_PTR(-ENOMEM);
1205 }
1206
1207 delpol = xfrm_policy_insert_list(chain, policy, excl);
1208 if (delpol && excl) {
1209 __xfrm_policy_inexact_prune_bin(bin, false);
1210 return ERR_PTR(-EEXIST);
1211 }
1212
1213 chain = &net->xfrm.policy_inexact[dir];
1214 xfrm_policy_insert_inexact_list(chain, policy);
1215
1216 if (delpol)
1217 __xfrm_policy_inexact_prune_bin(bin, false);
1218
1219 return delpol;
1220 }
1221
xfrm_hash_rebuild(struct work_struct * work)1222 static void xfrm_hash_rebuild(struct work_struct *work)
1223 {
1224 struct net *net = container_of(work, struct net,
1225 xfrm.policy_hthresh.work);
1226 unsigned int hmask;
1227 struct xfrm_policy *pol;
1228 struct xfrm_policy *policy;
1229 struct hlist_head *chain;
1230 struct hlist_head *odst;
1231 struct hlist_node *newpos;
1232 int i;
1233 int dir;
1234 unsigned seq;
1235 u8 lbits4, rbits4, lbits6, rbits6;
1236
1237 mutex_lock(&hash_resize_mutex);
1238
1239 /* read selector prefixlen thresholds */
1240 do {
1241 seq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
1242
1243 lbits4 = net->xfrm.policy_hthresh.lbits4;
1244 rbits4 = net->xfrm.policy_hthresh.rbits4;
1245 lbits6 = net->xfrm.policy_hthresh.lbits6;
1246 rbits6 = net->xfrm.policy_hthresh.rbits6;
1247 } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
1248
1249 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1250 write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
1251
1252 /* make sure that we can insert the indirect policies again before
1253 * we start with destructive action.
1254 */
1255 list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) {
1256 struct xfrm_pol_inexact_bin *bin;
1257 u8 dbits, sbits;
1258
1259 dir = xfrm_policy_id2dir(policy->index);
1260 if (policy->walk.dead || dir >= XFRM_POLICY_MAX)
1261 continue;
1262
1263 if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
1264 if (policy->family == AF_INET) {
1265 dbits = rbits4;
1266 sbits = lbits4;
1267 } else {
1268 dbits = rbits6;
1269 sbits = lbits6;
1270 }
1271 } else {
1272 if (policy->family == AF_INET) {
1273 dbits = lbits4;
1274 sbits = rbits4;
1275 } else {
1276 dbits = lbits6;
1277 sbits = rbits6;
1278 }
1279 }
1280
1281 if (policy->selector.prefixlen_d < dbits ||
1282 policy->selector.prefixlen_s < sbits)
1283 continue;
1284
1285 bin = xfrm_policy_inexact_alloc_bin(policy, dir);
1286 if (!bin)
1287 goto out_unlock;
1288
1289 if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir))
1290 goto out_unlock;
1291 }
1292
1293 /* reset the bydst and inexact table in all directions */
1294 for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
1295 struct hlist_node *n;
1296
1297 hlist_for_each_entry_safe(policy, n,
1298 &net->xfrm.policy_inexact[dir],
1299 bydst_inexact_list) {
1300 hlist_del_rcu(&policy->bydst);
1301 hlist_del_init(&policy->bydst_inexact_list);
1302 }
1303
1304 hmask = net->xfrm.policy_bydst[dir].hmask;
1305 odst = net->xfrm.policy_bydst[dir].table;
1306 for (i = hmask; i >= 0; i--) {
1307 hlist_for_each_entry_safe(policy, n, odst + i, bydst)
1308 hlist_del_rcu(&policy->bydst);
1309 }
1310 if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
1311 /* dir out => dst = remote, src = local */
1312 net->xfrm.policy_bydst[dir].dbits4 = rbits4;
1313 net->xfrm.policy_bydst[dir].sbits4 = lbits4;
1314 net->xfrm.policy_bydst[dir].dbits6 = rbits6;
1315 net->xfrm.policy_bydst[dir].sbits6 = lbits6;
1316 } else {
1317 /* dir in/fwd => dst = local, src = remote */
1318 net->xfrm.policy_bydst[dir].dbits4 = lbits4;
1319 net->xfrm.policy_bydst[dir].sbits4 = rbits4;
1320 net->xfrm.policy_bydst[dir].dbits6 = lbits6;
1321 net->xfrm.policy_bydst[dir].sbits6 = rbits6;
1322 }
1323 }
1324
1325 /* re-insert all policies by order of creation */
1326 list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
1327 if (policy->walk.dead)
1328 continue;
1329 dir = xfrm_policy_id2dir(policy->index);
1330 if (dir >= XFRM_POLICY_MAX) {
1331 /* skip socket policies */
1332 continue;
1333 }
1334 newpos = NULL;
1335 chain = policy_hash_bysel(net, &policy->selector,
1336 policy->family, dir);
1337
1338 if (!chain) {
1339 void *p = xfrm_policy_inexact_insert(policy, dir, 0);
1340
1341 WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p));
1342 continue;
1343 }
1344
1345 hlist_for_each_entry(pol, chain, bydst) {
1346 if (policy->priority >= pol->priority)
1347 newpos = &pol->bydst;
1348 else
1349 break;
1350 }
1351 if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
1352 hlist_add_behind_rcu(&policy->bydst, newpos);
1353 else
1354 hlist_add_head_rcu(&policy->bydst, chain);
1355 }
1356
1357 out_unlock:
1358 __xfrm_policy_inexact_flush(net);
1359 write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
1360 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1361
1362 mutex_unlock(&hash_resize_mutex);
1363 }
1364
xfrm_policy_hash_rebuild(struct net * net)1365 void xfrm_policy_hash_rebuild(struct net *net)
1366 {
1367 schedule_work(&net->xfrm.policy_hthresh.work);
1368 }
1369 EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
1370
1371 /* Generate new index... KAME seems to generate them ordered by cost
1372 * of an absolute inpredictability of ordering of rules. This will not pass. */
xfrm_gen_index(struct net * net,int dir,u32 index)1373 static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
1374 {
1375 static u32 idx_generator;
1376
1377 for (;;) {
1378 struct hlist_head *list;
1379 struct xfrm_policy *p;
1380 u32 idx;
1381 int found;
1382
1383 if (!index) {
1384 idx = (idx_generator | dir);
1385 idx_generator += 8;
1386 } else {
1387 idx = index;
1388 index = 0;
1389 }
1390
1391 if (idx == 0)
1392 idx = 8;
1393 list = net->xfrm.policy_byidx + idx_hash(net, idx);
1394 found = 0;
1395 hlist_for_each_entry(p, list, byidx) {
1396 if (p->index == idx) {
1397 found = 1;
1398 break;
1399 }
1400 }
1401 if (!found)
1402 return idx;
1403 }
1404 }
1405
selector_cmp(struct xfrm_selector * s1,struct xfrm_selector * s2)1406 static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s2)
1407 {
1408 u32 *p1 = (u32 *) s1;
1409 u32 *p2 = (u32 *) s2;
1410 int len = sizeof(struct xfrm_selector) / sizeof(u32);
1411 int i;
1412
1413 for (i = 0; i < len; i++) {
1414 if (p1[i] != p2[i])
1415 return 1;
1416 }
1417
1418 return 0;
1419 }
1420
xfrm_policy_requeue(struct xfrm_policy * old,struct xfrm_policy * new)1421 static void xfrm_policy_requeue(struct xfrm_policy *old,
1422 struct xfrm_policy *new)
1423 {
1424 struct xfrm_policy_queue *pq = &old->polq;
1425 struct sk_buff_head list;
1426
1427 if (skb_queue_empty(&pq->hold_queue))
1428 return;
1429
1430 __skb_queue_head_init(&list);
1431
1432 spin_lock_bh(&pq->hold_queue.lock);
1433 skb_queue_splice_init(&pq->hold_queue, &list);
1434 if (del_timer(&pq->hold_timer))
1435 xfrm_pol_put(old);
1436 spin_unlock_bh(&pq->hold_queue.lock);
1437
1438 pq = &new->polq;
1439
1440 spin_lock_bh(&pq->hold_queue.lock);
1441 skb_queue_splice(&list, &pq->hold_queue);
1442 pq->timeout = XFRM_QUEUE_TMO_MIN;
1443 if (!mod_timer(&pq->hold_timer, jiffies))
1444 xfrm_pol_hold(new);
1445 spin_unlock_bh(&pq->hold_queue.lock);
1446 }
1447
xfrm_policy_mark_match(const struct xfrm_mark * mark,struct xfrm_policy * pol)1448 static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark,
1449 struct xfrm_policy *pol)
1450 {
1451 return mark->v == pol->mark.v && mark->m == pol->mark.m;
1452 }
1453
xfrm_pol_bin_key(const void * data,u32 len,u32 seed)1454 static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
1455 {
1456 const struct xfrm_pol_inexact_key *k = data;
1457 u32 a = k->type << 24 | k->dir << 16 | k->family;
1458
1459 return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)),
1460 seed);
1461 }
1462
xfrm_pol_bin_obj(const void * data,u32 len,u32 seed)1463 static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed)
1464 {
1465 const struct xfrm_pol_inexact_bin *b = data;
1466
1467 return xfrm_pol_bin_key(&b->k, 0, seed);
1468 }
1469
xfrm_pol_bin_cmp(struct rhashtable_compare_arg * arg,const void * ptr)1470 static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg,
1471 const void *ptr)
1472 {
1473 const struct xfrm_pol_inexact_key *key = arg->key;
1474 const struct xfrm_pol_inexact_bin *b = ptr;
1475 int ret;
1476
1477 if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net)))
1478 return -1;
1479
1480 ret = b->k.dir ^ key->dir;
1481 if (ret)
1482 return ret;
1483
1484 ret = b->k.type ^ key->type;
1485 if (ret)
1486 return ret;
1487
1488 ret = b->k.family ^ key->family;
1489 if (ret)
1490 return ret;
1491
1492 return b->k.if_id ^ key->if_id;
1493 }
1494
1495 static const struct rhashtable_params xfrm_pol_inexact_params = {
1496 .head_offset = offsetof(struct xfrm_pol_inexact_bin, head),
1497 .hashfn = xfrm_pol_bin_key,
1498 .obj_hashfn = xfrm_pol_bin_obj,
1499 .obj_cmpfn = xfrm_pol_bin_cmp,
1500 .automatic_shrinking = true,
1501 };
1502
xfrm_policy_insert_inexact_list(struct hlist_head * chain,struct xfrm_policy * policy)1503 static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
1504 struct xfrm_policy *policy)
1505 {
1506 struct xfrm_policy *pol, *delpol = NULL;
1507 struct hlist_node *newpos = NULL;
1508 int i = 0;
1509
1510 hlist_for_each_entry(pol, chain, bydst_inexact_list) {
1511 if (pol->type == policy->type &&
1512 pol->if_id == policy->if_id &&
1513 !selector_cmp(&pol->selector, &policy->selector) &&
1514 xfrm_policy_mark_match(&policy->mark, pol) &&
1515 xfrm_sec_ctx_match(pol->security, policy->security) &&
1516 !WARN_ON(delpol)) {
1517 delpol = pol;
1518 if (policy->priority > pol->priority)
1519 continue;
1520 } else if (policy->priority >= pol->priority) {
1521 newpos = &pol->bydst_inexact_list;
1522 continue;
1523 }
1524 if (delpol)
1525 break;
1526 }
1527
1528 if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
1529 hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
1530 else
1531 hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
1532
1533 hlist_for_each_entry(pol, chain, bydst_inexact_list) {
1534 pol->pos = i;
1535 i++;
1536 }
1537 }
1538
xfrm_policy_insert_list(struct hlist_head * chain,struct xfrm_policy * policy,bool excl)1539 static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
1540 struct xfrm_policy *policy,
1541 bool excl)
1542 {
1543 struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL;
1544
1545 hlist_for_each_entry(pol, chain, bydst) {
1546 if (pol->type == policy->type &&
1547 pol->if_id == policy->if_id &&
1548 !selector_cmp(&pol->selector, &policy->selector) &&
1549 xfrm_policy_mark_match(&policy->mark, pol) &&
1550 xfrm_sec_ctx_match(pol->security, policy->security) &&
1551 !WARN_ON(delpol)) {
1552 if (excl)
1553 return ERR_PTR(-EEXIST);
1554 delpol = pol;
1555 if (policy->priority > pol->priority)
1556 continue;
1557 } else if (policy->priority >= pol->priority) {
1558 newpos = pol;
1559 continue;
1560 }
1561 if (delpol)
1562 break;
1563 }
1564
1565 if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
1566 hlist_add_behind_rcu(&policy->bydst, &newpos->bydst);
1567 else
1568 /* Packet offload policies enter to the head
1569 * to speed-up lookups.
1570 */
1571 hlist_add_head_rcu(&policy->bydst, chain);
1572
1573 return delpol;
1574 }
1575
xfrm_policy_insert(int dir,struct xfrm_policy * policy,int excl)1576 int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
1577 {
1578 struct net *net = xp_net(policy);
1579 struct xfrm_policy *delpol;
1580 struct hlist_head *chain;
1581
1582 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1583 chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
1584 if (chain)
1585 delpol = xfrm_policy_insert_list(chain, policy, excl);
1586 else
1587 delpol = xfrm_policy_inexact_insert(policy, dir, excl);
1588
1589 if (IS_ERR(delpol)) {
1590 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1591 return PTR_ERR(delpol);
1592 }
1593
1594 __xfrm_policy_link(policy, dir);
1595
1596 /* After previous checking, family can either be AF_INET or AF_INET6 */
1597 if (policy->family == AF_INET)
1598 rt_genid_bump_ipv4(net);
1599 else
1600 rt_genid_bump_ipv6(net);
1601
1602 if (delpol) {
1603 xfrm_policy_requeue(delpol, policy);
1604 __xfrm_policy_unlink(delpol, dir);
1605 }
1606 policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index);
1607 hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
1608 policy->curlft.add_time = ktime_get_real_seconds();
1609 policy->curlft.use_time = 0;
1610 if (!mod_timer(&policy->timer, jiffies + HZ))
1611 xfrm_pol_hold(policy);
1612 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1613
1614 if (delpol)
1615 xfrm_policy_kill(delpol);
1616 else if (xfrm_bydst_should_resize(net, dir, NULL))
1617 schedule_work(&net->xfrm.policy_hash_work);
1618
1619 return 0;
1620 }
1621 EXPORT_SYMBOL(xfrm_policy_insert);
1622
1623 static struct xfrm_policy *
__xfrm_policy_bysel_ctx(struct hlist_head * chain,const struct xfrm_mark * mark,u32 if_id,u8 type,int dir,struct xfrm_selector * sel,struct xfrm_sec_ctx * ctx)1624 __xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark,
1625 u32 if_id, u8 type, int dir, struct xfrm_selector *sel,
1626 struct xfrm_sec_ctx *ctx)
1627 {
1628 struct xfrm_policy *pol;
1629
1630 if (!chain)
1631 return NULL;
1632
1633 hlist_for_each_entry(pol, chain, bydst) {
1634 if (pol->type == type &&
1635 pol->if_id == if_id &&
1636 xfrm_policy_mark_match(mark, pol) &&
1637 !selector_cmp(sel, &pol->selector) &&
1638 xfrm_sec_ctx_match(ctx, pol->security))
1639 return pol;
1640 }
1641
1642 return NULL;
1643 }
1644
1645 struct xfrm_policy *
xfrm_policy_bysel_ctx(struct net * net,const struct xfrm_mark * mark,u32 if_id,u8 type,int dir,struct xfrm_selector * sel,struct xfrm_sec_ctx * ctx,int delete,int * err)1646 xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id,
1647 u8 type, int dir, struct xfrm_selector *sel,
1648 struct xfrm_sec_ctx *ctx, int delete, int *err)
1649 {
1650 struct xfrm_pol_inexact_bin *bin = NULL;
1651 struct xfrm_policy *pol, *ret = NULL;
1652 struct hlist_head *chain;
1653
1654 *err = 0;
1655 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1656 chain = policy_hash_bysel(net, sel, sel->family, dir);
1657 if (!chain) {
1658 struct xfrm_pol_inexact_candidates cand;
1659 int i;
1660
1661 bin = xfrm_policy_inexact_lookup(net, type,
1662 sel->family, dir, if_id);
1663 if (!bin) {
1664 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1665 return NULL;
1666 }
1667
1668 if (!xfrm_policy_find_inexact_candidates(&cand, bin,
1669 &sel->saddr,
1670 &sel->daddr)) {
1671 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1672 return NULL;
1673 }
1674
1675 pol = NULL;
1676 for (i = 0; i < ARRAY_SIZE(cand.res); i++) {
1677 struct xfrm_policy *tmp;
1678
1679 tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark,
1680 if_id, type, dir,
1681 sel, ctx);
1682 if (!tmp)
1683 continue;
1684
1685 if (!pol || tmp->pos < pol->pos)
1686 pol = tmp;
1687 }
1688 } else {
1689 pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir,
1690 sel, ctx);
1691 }
1692
1693 if (pol) {
1694 xfrm_pol_hold(pol);
1695 if (delete) {
1696 *err = security_xfrm_policy_delete(pol->security);
1697 if (*err) {
1698 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1699 return pol;
1700 }
1701 __xfrm_policy_unlink(pol, dir);
1702 }
1703 ret = pol;
1704 }
1705 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1706
1707 if (ret && delete)
1708 xfrm_policy_kill(ret);
1709 if (bin && delete)
1710 xfrm_policy_inexact_prune_bin(bin);
1711 return ret;
1712 }
1713 EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
1714
1715 struct xfrm_policy *
xfrm_policy_byid(struct net * net,const struct xfrm_mark * mark,u32 if_id,u8 type,int dir,u32 id,int delete,int * err)1716 xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id,
1717 u8 type, int dir, u32 id, int delete, int *err)
1718 {
1719 struct xfrm_policy *pol, *ret;
1720 struct hlist_head *chain;
1721
1722 *err = -ENOENT;
1723 if (xfrm_policy_id2dir(id) != dir)
1724 return NULL;
1725
1726 *err = 0;
1727 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1728 chain = net->xfrm.policy_byidx + idx_hash(net, id);
1729 ret = NULL;
1730 hlist_for_each_entry(pol, chain, byidx) {
1731 if (pol->type == type && pol->index == id &&
1732 pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) {
1733 xfrm_pol_hold(pol);
1734 if (delete) {
1735 *err = security_xfrm_policy_delete(
1736 pol->security);
1737 if (*err) {
1738 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1739 return pol;
1740 }
1741 __xfrm_policy_unlink(pol, dir);
1742 }
1743 ret = pol;
1744 break;
1745 }
1746 }
1747 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1748
1749 if (ret && delete)
1750 xfrm_policy_kill(ret);
1751 return ret;
1752 }
1753 EXPORT_SYMBOL(xfrm_policy_byid);
1754
1755 #ifdef CONFIG_SECURITY_NETWORK_XFRM
1756 static inline int
xfrm_policy_flush_secctx_check(struct net * net,u8 type,bool task_valid)1757 xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
1758 {
1759 struct xfrm_policy *pol;
1760 int err = 0;
1761
1762 list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
1763 if (pol->walk.dead ||
1764 xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX ||
1765 pol->type != type)
1766 continue;
1767
1768 err = security_xfrm_policy_delete(pol->security);
1769 if (err) {
1770 xfrm_audit_policy_delete(pol, 0, task_valid);
1771 return err;
1772 }
1773 }
1774 return err;
1775 }
1776
xfrm_dev_policy_flush_secctx_check(struct net * net,struct net_device * dev,bool task_valid)1777 static inline int xfrm_dev_policy_flush_secctx_check(struct net *net,
1778 struct net_device *dev,
1779 bool task_valid)
1780 {
1781 struct xfrm_policy *pol;
1782 int err = 0;
1783
1784 list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
1785 if (pol->walk.dead ||
1786 xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX ||
1787 pol->xdo.dev != dev)
1788 continue;
1789
1790 err = security_xfrm_policy_delete(pol->security);
1791 if (err) {
1792 xfrm_audit_policy_delete(pol, 0, task_valid);
1793 return err;
1794 }
1795 }
1796 return err;
1797 }
1798 #else
1799 static inline int
xfrm_policy_flush_secctx_check(struct net * net,u8 type,bool task_valid)1800 xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
1801 {
1802 return 0;
1803 }
1804
xfrm_dev_policy_flush_secctx_check(struct net * net,struct net_device * dev,bool task_valid)1805 static inline int xfrm_dev_policy_flush_secctx_check(struct net *net,
1806 struct net_device *dev,
1807 bool task_valid)
1808 {
1809 return 0;
1810 }
1811 #endif
1812
xfrm_policy_flush(struct net * net,u8 type,bool task_valid)1813 int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
1814 {
1815 int dir, err = 0, cnt = 0;
1816 struct xfrm_policy *pol;
1817
1818 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1819
1820 err = xfrm_policy_flush_secctx_check(net, type, task_valid);
1821 if (err)
1822 goto out;
1823
1824 again:
1825 list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
1826 dir = xfrm_policy_id2dir(pol->index);
1827 if (pol->walk.dead ||
1828 dir >= XFRM_POLICY_MAX ||
1829 pol->type != type)
1830 continue;
1831
1832 __xfrm_policy_unlink(pol, dir);
1833 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1834 cnt++;
1835 xfrm_audit_policy_delete(pol, 1, task_valid);
1836 xfrm_policy_kill(pol);
1837 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1838 goto again;
1839 }
1840 if (cnt)
1841 __xfrm_policy_inexact_flush(net);
1842 else
1843 err = -ESRCH;
1844 out:
1845 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1846 return err;
1847 }
1848 EXPORT_SYMBOL(xfrm_policy_flush);
1849
xfrm_dev_policy_flush(struct net * net,struct net_device * dev,bool task_valid)1850 int xfrm_dev_policy_flush(struct net *net, struct net_device *dev,
1851 bool task_valid)
1852 {
1853 int dir, err = 0, cnt = 0;
1854 struct xfrm_policy *pol;
1855
1856 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1857
1858 err = xfrm_dev_policy_flush_secctx_check(net, dev, task_valid);
1859 if (err)
1860 goto out;
1861
1862 again:
1863 list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
1864 dir = xfrm_policy_id2dir(pol->index);
1865 if (pol->walk.dead ||
1866 dir >= XFRM_POLICY_MAX ||
1867 pol->xdo.dev != dev)
1868 continue;
1869
1870 __xfrm_policy_unlink(pol, dir);
1871 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1872 cnt++;
1873 xfrm_audit_policy_delete(pol, 1, task_valid);
1874 xfrm_policy_kill(pol);
1875 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1876 goto again;
1877 }
1878 if (cnt)
1879 __xfrm_policy_inexact_flush(net);
1880 else
1881 err = -ESRCH;
1882 out:
1883 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1884 return err;
1885 }
1886 EXPORT_SYMBOL(xfrm_dev_policy_flush);
1887
xfrm_policy_walk(struct net * net,struct xfrm_policy_walk * walk,int (* func)(struct xfrm_policy *,int,int,void *),void * data)1888 int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
1889 int (*func)(struct xfrm_policy *, int, int, void*),
1890 void *data)
1891 {
1892 struct xfrm_policy *pol;
1893 struct xfrm_policy_walk_entry *x;
1894 int error = 0;
1895
1896 if (walk->type >= XFRM_POLICY_TYPE_MAX &&
1897 walk->type != XFRM_POLICY_TYPE_ANY)
1898 return -EINVAL;
1899
1900 if (list_empty(&walk->walk.all) && walk->seq != 0)
1901 return 0;
1902
1903 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
1904 if (list_empty(&walk->walk.all))
1905 x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all);
1906 else
1907 x = list_first_entry(&walk->walk.all,
1908 struct xfrm_policy_walk_entry, all);
1909
1910 list_for_each_entry_from(x, &net->xfrm.policy_all, all) {
1911 if (x->dead)
1912 continue;
1913 pol = container_of(x, struct xfrm_policy, walk);
1914 if (walk->type != XFRM_POLICY_TYPE_ANY &&
1915 walk->type != pol->type)
1916 continue;
1917 error = func(pol, xfrm_policy_id2dir(pol->index),
1918 walk->seq, data);
1919 if (error) {
1920 list_move_tail(&walk->walk.all, &x->all);
1921 goto out;
1922 }
1923 walk->seq++;
1924 }
1925 if (walk->seq == 0) {
1926 error = -ENOENT;
1927 goto out;
1928 }
1929 list_del_init(&walk->walk.all);
1930 out:
1931 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1932 return error;
1933 }
1934 EXPORT_SYMBOL(xfrm_policy_walk);
1935
xfrm_policy_walk_init(struct xfrm_policy_walk * walk,u8 type)1936 void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type)
1937 {
1938 INIT_LIST_HEAD(&walk->walk.all);
1939 walk->walk.dead = 1;
1940 walk->type = type;
1941 walk->seq = 0;
1942 }
1943 EXPORT_SYMBOL(xfrm_policy_walk_init);
1944
xfrm_policy_walk_done(struct xfrm_policy_walk * walk,struct net * net)1945 void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net)
1946 {
1947 if (list_empty(&walk->walk.all))
1948 return;
1949
1950 spin_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */
1951 list_del(&walk->walk.all);
1952 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
1953 }
1954 EXPORT_SYMBOL(xfrm_policy_walk_done);
1955
1956 /*
1957 * Find policy to apply to this flow.
1958 *
1959 * Returns 0 if policy found, else an -errno.
1960 */
xfrm_policy_match(const struct xfrm_policy * pol,const struct flowi * fl,u8 type,u16 family,u32 if_id)1961 static int xfrm_policy_match(const struct xfrm_policy *pol,
1962 const struct flowi *fl,
1963 u8 type, u16 family, u32 if_id)
1964 {
1965 const struct xfrm_selector *sel = &pol->selector;
1966 int ret = -ESRCH;
1967 bool match;
1968
1969 if (pol->family != family ||
1970 pol->if_id != if_id ||
1971 (fl->flowi_mark & pol->mark.m) != pol->mark.v ||
1972 pol->type != type)
1973 return ret;
1974
1975 match = xfrm_selector_match(sel, fl, family);
1976 if (match)
1977 ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid);
1978 return ret;
1979 }
1980
1981 static struct xfrm_pol_inexact_node *
xfrm_policy_lookup_inexact_addr(const struct rb_root * r,seqcount_spinlock_t * count,const xfrm_address_t * addr,u16 family)1982 xfrm_policy_lookup_inexact_addr(const struct rb_root *r,
1983 seqcount_spinlock_t *count,
1984 const xfrm_address_t *addr, u16 family)
1985 {
1986 const struct rb_node *parent;
1987 int seq;
1988
1989 again:
1990 seq = read_seqcount_begin(count);
1991
1992 parent = rcu_dereference_raw(r->rb_node);
1993 while (parent) {
1994 struct xfrm_pol_inexact_node *node;
1995 int delta;
1996
1997 node = rb_entry(parent, struct xfrm_pol_inexact_node, node);
1998
1999 delta = xfrm_policy_addr_delta(addr, &node->addr,
2000 node->prefixlen, family);
2001 if (delta < 0) {
2002 parent = rcu_dereference_raw(parent->rb_left);
2003 continue;
2004 } else if (delta > 0) {
2005 parent = rcu_dereference_raw(parent->rb_right);
2006 continue;
2007 }
2008
2009 return node;
2010 }
2011
2012 if (read_seqcount_retry(count, seq))
2013 goto again;
2014
2015 return NULL;
2016 }
2017
2018 static bool
xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates * cand,struct xfrm_pol_inexact_bin * b,const xfrm_address_t * saddr,const xfrm_address_t * daddr)2019 xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
2020 struct xfrm_pol_inexact_bin *b,
2021 const xfrm_address_t *saddr,
2022 const xfrm_address_t *daddr)
2023 {
2024 struct xfrm_pol_inexact_node *n;
2025 u16 family;
2026
2027 if (!b)
2028 return false;
2029
2030 family = b->k.family;
2031 memset(cand, 0, sizeof(*cand));
2032 cand->res[XFRM_POL_CAND_ANY] = &b->hhead;
2033
2034 n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr,
2035 family);
2036 if (n) {
2037 cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
2038 n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr,
2039 family);
2040 if (n)
2041 cand->res[XFRM_POL_CAND_BOTH] = &n->hhead;
2042 }
2043
2044 n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr,
2045 family);
2046 if (n)
2047 cand->res[XFRM_POL_CAND_SADDR] = &n->hhead;
2048
2049 return true;
2050 }
2051
2052 static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_lookup_rcu(struct net * net,u8 type,u16 family,u8 dir,u32 if_id)2053 xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family,
2054 u8 dir, u32 if_id)
2055 {
2056 struct xfrm_pol_inexact_key k = {
2057 .family = family,
2058 .type = type,
2059 .dir = dir,
2060 .if_id = if_id,
2061 };
2062
2063 write_pnet(&k.net, net);
2064
2065 return rhashtable_lookup(&xfrm_policy_inexact_table, &k,
2066 xfrm_pol_inexact_params);
2067 }
2068
2069 static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_lookup(struct net * net,u8 type,u16 family,u8 dir,u32 if_id)2070 xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family,
2071 u8 dir, u32 if_id)
2072 {
2073 struct xfrm_pol_inexact_bin *bin;
2074
2075 lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
2076
2077 rcu_read_lock();
2078 bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
2079 rcu_read_unlock();
2080
2081 return bin;
2082 }
2083
2084 static struct xfrm_policy *
__xfrm_policy_eval_candidates(struct hlist_head * chain,struct xfrm_policy * prefer,const struct flowi * fl,u8 type,u16 family,u32 if_id)2085 __xfrm_policy_eval_candidates(struct hlist_head *chain,
2086 struct xfrm_policy *prefer,
2087 const struct flowi *fl,
2088 u8 type, u16 family, u32 if_id)
2089 {
2090 u32 priority = prefer ? prefer->priority : ~0u;
2091 struct xfrm_policy *pol;
2092
2093 if (!chain)
2094 return NULL;
2095
2096 hlist_for_each_entry_rcu(pol, chain, bydst) {
2097 int err;
2098
2099 if (pol->priority > priority)
2100 break;
2101
2102 err = xfrm_policy_match(pol, fl, type, family, if_id);
2103 if (err) {
2104 if (err != -ESRCH)
2105 return ERR_PTR(err);
2106
2107 continue;
2108 }
2109
2110 if (prefer) {
2111 /* matches. Is it older than *prefer? */
2112 if (pol->priority == priority &&
2113 prefer->pos < pol->pos)
2114 return prefer;
2115 }
2116
2117 return pol;
2118 }
2119
2120 return NULL;
2121 }
2122
2123 static struct xfrm_policy *
xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates * cand,struct xfrm_policy * prefer,const struct flowi * fl,u8 type,u16 family,u32 if_id)2124 xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand,
2125 struct xfrm_policy *prefer,
2126 const struct flowi *fl,
2127 u8 type, u16 family, u32 if_id)
2128 {
2129 struct xfrm_policy *tmp;
2130 int i;
2131
2132 for (i = 0; i < ARRAY_SIZE(cand->res); i++) {
2133 tmp = __xfrm_policy_eval_candidates(cand->res[i],
2134 prefer,
2135 fl, type, family, if_id);
2136 if (!tmp)
2137 continue;
2138
2139 if (IS_ERR(tmp))
2140 return tmp;
2141 prefer = tmp;
2142 }
2143
2144 return prefer;
2145 }
2146
xfrm_policy_lookup_bytype(struct net * net,u8 type,const struct flowi * fl,u16 family,u8 dir,u32 if_id)2147 static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
2148 const struct flowi *fl,
2149 u16 family, u8 dir,
2150 u32 if_id)
2151 {
2152 struct xfrm_pol_inexact_candidates cand;
2153 const xfrm_address_t *daddr, *saddr;
2154 struct xfrm_pol_inexact_bin *bin;
2155 struct xfrm_policy *pol, *ret;
2156 struct hlist_head *chain;
2157 unsigned int sequence;
2158 int err;
2159
2160 daddr = xfrm_flowi_daddr(fl, family);
2161 saddr = xfrm_flowi_saddr(fl, family);
2162 if (unlikely(!daddr || !saddr))
2163 return NULL;
2164
2165 rcu_read_lock();
2166 retry:
2167 do {
2168 sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
2169 chain = policy_hash_direct(net, daddr, saddr, family, dir);
2170 } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence));
2171
2172 ret = NULL;
2173 hlist_for_each_entry_rcu(pol, chain, bydst) {
2174 err = xfrm_policy_match(pol, fl, type, family, if_id);
2175 if (err) {
2176 if (err == -ESRCH)
2177 continue;
2178 else {
2179 ret = ERR_PTR(err);
2180 goto fail;
2181 }
2182 } else {
2183 ret = pol;
2184 break;
2185 }
2186 }
2187 if (ret && ret->xdo.type == XFRM_DEV_OFFLOAD_PACKET)
2188 goto skip_inexact;
2189
2190 bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
2191 if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr,
2192 daddr))
2193 goto skip_inexact;
2194
2195 pol = xfrm_policy_eval_candidates(&cand, ret, fl, type,
2196 family, if_id);
2197 if (pol) {
2198 ret = pol;
2199 if (IS_ERR(pol))
2200 goto fail;
2201 }
2202
2203 skip_inexact:
2204 if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence))
2205 goto retry;
2206
2207 if (ret && !xfrm_pol_hold_rcu(ret))
2208 goto retry;
2209 fail:
2210 rcu_read_unlock();
2211
2212 return ret;
2213 }
2214
xfrm_policy_lookup(struct net * net,const struct flowi * fl,u16 family,u8 dir,u32 if_id)2215 static struct xfrm_policy *xfrm_policy_lookup(struct net *net,
2216 const struct flowi *fl,
2217 u16 family, u8 dir, u32 if_id)
2218 {
2219 #ifdef CONFIG_XFRM_SUB_POLICY
2220 struct xfrm_policy *pol;
2221
2222 pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family,
2223 dir, if_id);
2224 if (pol != NULL)
2225 return pol;
2226 #endif
2227 return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family,
2228 dir, if_id);
2229 }
2230
xfrm_sk_policy_lookup(const struct sock * sk,int dir,const struct flowi * fl,u16 family,u32 if_id)2231 static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
2232 const struct flowi *fl,
2233 u16 family, u32 if_id)
2234 {
2235 struct xfrm_policy *pol;
2236
2237 rcu_read_lock();
2238 again:
2239 pol = rcu_dereference(sk->sk_policy[dir]);
2240 if (pol != NULL) {
2241 bool match;
2242 int err = 0;
2243
2244 if (pol->family != family) {
2245 pol = NULL;
2246 goto out;
2247 }
2248
2249 match = xfrm_selector_match(&pol->selector, fl, family);
2250 if (match) {
2251 if ((sk->sk_mark & pol->mark.m) != pol->mark.v ||
2252 pol->if_id != if_id) {
2253 pol = NULL;
2254 goto out;
2255 }
2256 err = security_xfrm_policy_lookup(pol->security,
2257 fl->flowi_secid);
2258 if (!err) {
2259 if (!xfrm_pol_hold_rcu(pol))
2260 goto again;
2261 } else if (err == -ESRCH) {
2262 pol = NULL;
2263 } else {
2264 pol = ERR_PTR(err);
2265 }
2266 } else
2267 pol = NULL;
2268 }
2269 out:
2270 rcu_read_unlock();
2271 return pol;
2272 }
2273
__xfrm_policy_link(struct xfrm_policy * pol,int dir)2274 static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
2275 {
2276 struct net *net = xp_net(pol);
2277
2278 list_add(&pol->walk.all, &net->xfrm.policy_all);
2279 net->xfrm.policy_count[dir]++;
2280 xfrm_pol_hold(pol);
2281 }
2282
__xfrm_policy_unlink(struct xfrm_policy * pol,int dir)2283 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
2284 int dir)
2285 {
2286 struct net *net = xp_net(pol);
2287
2288 if (list_empty(&pol->walk.all))
2289 return NULL;
2290
2291 /* Socket policies are not hashed. */
2292 if (!hlist_unhashed(&pol->bydst)) {
2293 hlist_del_rcu(&pol->bydst);
2294 hlist_del_init(&pol->bydst_inexact_list);
2295 hlist_del(&pol->byidx);
2296 }
2297
2298 list_del_init(&pol->walk.all);
2299 net->xfrm.policy_count[dir]--;
2300
2301 return pol;
2302 }
2303
xfrm_sk_policy_link(struct xfrm_policy * pol,int dir)2304 static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir)
2305 {
2306 __xfrm_policy_link(pol, XFRM_POLICY_MAX + dir);
2307 }
2308
xfrm_sk_policy_unlink(struct xfrm_policy * pol,int dir)2309 static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir)
2310 {
2311 __xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir);
2312 }
2313
xfrm_policy_delete(struct xfrm_policy * pol,int dir)2314 int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
2315 {
2316 struct net *net = xp_net(pol);
2317
2318 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
2319 pol = __xfrm_policy_unlink(pol, dir);
2320 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
2321 if (pol) {
2322 xfrm_dev_policy_delete(pol);
2323 xfrm_policy_kill(pol);
2324 return 0;
2325 }
2326 return -ENOENT;
2327 }
2328 EXPORT_SYMBOL(xfrm_policy_delete);
2329
xfrm_sk_policy_insert(struct sock * sk,int dir,struct xfrm_policy * pol)2330 int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
2331 {
2332 struct net *net = sock_net(sk);
2333 struct xfrm_policy *old_pol;
2334
2335 #ifdef CONFIG_XFRM_SUB_POLICY
2336 if (pol && pol->type != XFRM_POLICY_TYPE_MAIN)
2337 return -EINVAL;
2338 #endif
2339
2340 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
2341 old_pol = rcu_dereference_protected(sk->sk_policy[dir],
2342 lockdep_is_held(&net->xfrm.xfrm_policy_lock));
2343 if (pol) {
2344 pol->curlft.add_time = ktime_get_real_seconds();
2345 pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
2346 xfrm_sk_policy_link(pol, dir);
2347 }
2348 rcu_assign_pointer(sk->sk_policy[dir], pol);
2349 if (old_pol) {
2350 if (pol)
2351 xfrm_policy_requeue(old_pol, pol);
2352
2353 /* Unlinking succeeds always. This is the only function
2354 * allowed to delete or replace socket policy.
2355 */
2356 xfrm_sk_policy_unlink(old_pol, dir);
2357 }
2358 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
2359
2360 if (old_pol) {
2361 xfrm_policy_kill(old_pol);
2362 }
2363 return 0;
2364 }
2365
clone_policy(const struct xfrm_policy * old,int dir)2366 static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
2367 {
2368 struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC);
2369 struct net *net = xp_net(old);
2370
2371 if (newp) {
2372 newp->selector = old->selector;
2373 if (security_xfrm_policy_clone(old->security,
2374 &newp->security)) {
2375 kfree(newp);
2376 return NULL; /* ENOMEM */
2377 }
2378 newp->lft = old->lft;
2379 newp->curlft = old->curlft;
2380 newp->mark = old->mark;
2381 newp->if_id = old->if_id;
2382 newp->action = old->action;
2383 newp->flags = old->flags;
2384 newp->xfrm_nr = old->xfrm_nr;
2385 newp->index = old->index;
2386 newp->type = old->type;
2387 newp->family = old->family;
2388 memcpy(newp->xfrm_vec, old->xfrm_vec,
2389 newp->xfrm_nr*sizeof(struct xfrm_tmpl));
2390 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
2391 xfrm_sk_policy_link(newp, dir);
2392 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
2393 xfrm_pol_put(newp);
2394 }
2395 return newp;
2396 }
2397
__xfrm_sk_clone_policy(struct sock * sk,const struct sock * osk)2398 int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
2399 {
2400 const struct xfrm_policy *p;
2401 struct xfrm_policy *np;
2402 int i, ret = 0;
2403
2404 rcu_read_lock();
2405 for (i = 0; i < 2; i++) {
2406 p = rcu_dereference(osk->sk_policy[i]);
2407 if (p) {
2408 np = clone_policy(p, i);
2409 if (unlikely(!np)) {
2410 ret = -ENOMEM;
2411 break;
2412 }
2413 rcu_assign_pointer(sk->sk_policy[i], np);
2414 }
2415 }
2416 rcu_read_unlock();
2417 return ret;
2418 }
2419
2420 static int
xfrm_get_saddr(struct net * net,int oif,xfrm_address_t * local,xfrm_address_t * remote,unsigned short family,u32 mark)2421 xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local,
2422 xfrm_address_t *remote, unsigned short family, u32 mark)
2423 {
2424 int err;
2425 const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
2426
2427 if (unlikely(afinfo == NULL))
2428 return -EINVAL;
2429 err = afinfo->get_saddr(net, oif, local, remote, mark);
2430 rcu_read_unlock();
2431 return err;
2432 }
2433
2434 /* Resolve list of templates for the flow, given policy. */
2435
2436 static int
xfrm_tmpl_resolve_one(struct xfrm_policy * policy,const struct flowi * fl,struct xfrm_state ** xfrm,unsigned short family)2437 xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
2438 struct xfrm_state **xfrm, unsigned short family)
2439 {
2440 struct net *net = xp_net(policy);
2441 int nx;
2442 int i, error;
2443 xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family);
2444 xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family);
2445 xfrm_address_t tmp;
2446
2447 for (nx = 0, i = 0; i < policy->xfrm_nr; i++) {
2448 struct xfrm_state *x;
2449 xfrm_address_t *remote = daddr;
2450 xfrm_address_t *local = saddr;
2451 struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i];
2452
2453 if (tmpl->mode == XFRM_MODE_TUNNEL ||
2454 tmpl->mode == XFRM_MODE_BEET) {
2455 remote = &tmpl->id.daddr;
2456 local = &tmpl->saddr;
2457 if (xfrm_addr_any(local, tmpl->encap_family)) {
2458 error = xfrm_get_saddr(net, fl->flowi_oif,
2459 &tmp, remote,
2460 tmpl->encap_family, 0);
2461 if (error)
2462 goto fail;
2463 local = &tmp;
2464 }
2465 }
2466
2467 x = xfrm_state_find(remote, local, fl, tmpl, policy, &error,
2468 family, policy->if_id);
2469
2470 if (x && x->km.state == XFRM_STATE_VALID) {
2471 xfrm[nx++] = x;
2472 daddr = remote;
2473 saddr = local;
2474 continue;
2475 }
2476 if (x) {
2477 error = (x->km.state == XFRM_STATE_ERROR ?
2478 -EINVAL : -EAGAIN);
2479 xfrm_state_put(x);
2480 } else if (error == -ESRCH) {
2481 error = -EAGAIN;
2482 }
2483
2484 if (!tmpl->optional)
2485 goto fail;
2486 }
2487 return nx;
2488
2489 fail:
2490 for (nx--; nx >= 0; nx--)
2491 xfrm_state_put(xfrm[nx]);
2492 return error;
2493 }
2494
2495 static int
xfrm_tmpl_resolve(struct xfrm_policy ** pols,int npols,const struct flowi * fl,struct xfrm_state ** xfrm,unsigned short family)2496 xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl,
2497 struct xfrm_state **xfrm, unsigned short family)
2498 {
2499 struct xfrm_state *tp[XFRM_MAX_DEPTH];
2500 struct xfrm_state **tpp = (npols > 1) ? tp : xfrm;
2501 int cnx = 0;
2502 int error;
2503 int ret;
2504 int i;
2505
2506 for (i = 0; i < npols; i++) {
2507 if (cnx + pols[i]->xfrm_nr >= XFRM_MAX_DEPTH) {
2508 error = -ENOBUFS;
2509 goto fail;
2510 }
2511
2512 ret = xfrm_tmpl_resolve_one(pols[i], fl, &tpp[cnx], family);
2513 if (ret < 0) {
2514 error = ret;
2515 goto fail;
2516 } else
2517 cnx += ret;
2518 }
2519
2520 /* found states are sorted for outbound processing */
2521 if (npols > 1)
2522 xfrm_state_sort(xfrm, tpp, cnx, family);
2523
2524 return cnx;
2525
2526 fail:
2527 for (cnx--; cnx >= 0; cnx--)
2528 xfrm_state_put(tpp[cnx]);
2529 return error;
2530
2531 }
2532
xfrm_get_tos(const struct flowi * fl,int family)2533 static int xfrm_get_tos(const struct flowi *fl, int family)
2534 {
2535 if (family == AF_INET)
2536 return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos;
2537
2538 return 0;
2539 }
2540
xfrm_alloc_dst(struct net * net,int family)2541 static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
2542 {
2543 const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
2544 struct dst_ops *dst_ops;
2545 struct xfrm_dst *xdst;
2546
2547 if (!afinfo)
2548 return ERR_PTR(-EINVAL);
2549
2550 switch (family) {
2551 case AF_INET:
2552 dst_ops = &net->xfrm.xfrm4_dst_ops;
2553 break;
2554 #if IS_ENABLED(CONFIG_IPV6)
2555 case AF_INET6:
2556 dst_ops = &net->xfrm.xfrm6_dst_ops;
2557 break;
2558 #endif
2559 default:
2560 BUG();
2561 }
2562 xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, 0);
2563
2564 if (likely(xdst)) {
2565 memset_after(xdst, 0, u.dst);
2566 } else
2567 xdst = ERR_PTR(-ENOBUFS);
2568
2569 rcu_read_unlock();
2570
2571 return xdst;
2572 }
2573
xfrm_init_path(struct xfrm_dst * path,struct dst_entry * dst,int nfheader_len)2574 static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
2575 int nfheader_len)
2576 {
2577 if (dst->ops->family == AF_INET6) {
2578 struct rt6_info *rt = (struct rt6_info *)dst;
2579 path->path_cookie = rt6_get_cookie(rt);
2580 path->u.rt6.rt6i_nfheader_len = nfheader_len;
2581 }
2582 }
2583
xfrm_fill_dst(struct xfrm_dst * xdst,struct net_device * dev,const struct flowi * fl)2584 static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
2585 const struct flowi *fl)
2586 {
2587 const struct xfrm_policy_afinfo *afinfo =
2588 xfrm_policy_get_afinfo(xdst->u.dst.ops->family);
2589 int err;
2590
2591 if (!afinfo)
2592 return -EINVAL;
2593
2594 err = afinfo->fill_dst(xdst, dev, fl);
2595
2596 rcu_read_unlock();
2597
2598 return err;
2599 }
2600
2601
2602 /* Allocate chain of dst_entry's, attach known xfrm's, calculate
2603 * all the metrics... Shortly, bundle a bundle.
2604 */
2605
xfrm_bundle_create(struct xfrm_policy * policy,struct xfrm_state ** xfrm,struct xfrm_dst ** bundle,int nx,const struct flowi * fl,struct dst_entry * dst)2606 static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
2607 struct xfrm_state **xfrm,
2608 struct xfrm_dst **bundle,
2609 int nx,
2610 const struct flowi *fl,
2611 struct dst_entry *dst)
2612 {
2613 const struct xfrm_state_afinfo *afinfo;
2614 const struct xfrm_mode *inner_mode;
2615 struct net *net = xp_net(policy);
2616 unsigned long now = jiffies;
2617 struct net_device *dev;
2618 struct xfrm_dst *xdst_prev = NULL;
2619 struct xfrm_dst *xdst0 = NULL;
2620 int i = 0;
2621 int err;
2622 int header_len = 0;
2623 int nfheader_len = 0;
2624 int trailer_len = 0;
2625 int tos;
2626 int family = policy->selector.family;
2627 xfrm_address_t saddr, daddr;
2628
2629 xfrm_flowi_addr_get(fl, &saddr, &daddr, family);
2630
2631 tos = xfrm_get_tos(fl, family);
2632
2633 dst_hold(dst);
2634
2635 for (; i < nx; i++) {
2636 struct xfrm_dst *xdst = xfrm_alloc_dst(net, family);
2637 struct dst_entry *dst1 = &xdst->u.dst;
2638
2639 err = PTR_ERR(xdst);
2640 if (IS_ERR(xdst)) {
2641 dst_release(dst);
2642 goto put_states;
2643 }
2644
2645 bundle[i] = xdst;
2646 if (!xdst_prev)
2647 xdst0 = xdst;
2648 else
2649 /* Ref count is taken during xfrm_alloc_dst()
2650 * No need to do dst_clone() on dst1
2651 */
2652 xfrm_dst_set_child(xdst_prev, &xdst->u.dst);
2653
2654 if (xfrm[i]->sel.family == AF_UNSPEC) {
2655 inner_mode = xfrm_ip2inner_mode(xfrm[i],
2656 xfrm_af2proto(family));
2657 if (!inner_mode) {
2658 err = -EAFNOSUPPORT;
2659 dst_release(dst);
2660 goto put_states;
2661 }
2662 } else
2663 inner_mode = &xfrm[i]->inner_mode;
2664
2665 xdst->route = dst;
2666 dst_copy_metrics(dst1, dst);
2667
2668 if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
2669 __u32 mark = 0;
2670 int oif;
2671
2672 if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
2673 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
2674
2675 family = xfrm[i]->props.family;
2676 oif = fl->flowi_oif ? : fl->flowi_l3mdev;
2677 dst = xfrm_dst_lookup(xfrm[i], tos, oif,
2678 &saddr, &daddr, family, mark);
2679 err = PTR_ERR(dst);
2680 if (IS_ERR(dst))
2681 goto put_states;
2682 } else
2683 dst_hold(dst);
2684
2685 dst1->xfrm = xfrm[i];
2686 xdst->xfrm_genid = xfrm[i]->genid;
2687
2688 dst1->obsolete = DST_OBSOLETE_FORCE_CHK;
2689 dst1->lastuse = now;
2690
2691 dst1->input = dst_discard;
2692
2693 rcu_read_lock();
2694 afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
2695 if (likely(afinfo))
2696 dst1->output = afinfo->output;
2697 else
2698 dst1->output = dst_discard_out;
2699 rcu_read_unlock();
2700
2701 xdst_prev = xdst;
2702
2703 header_len += xfrm[i]->props.header_len;
2704 if (xfrm[i]->type->flags & XFRM_TYPE_NON_FRAGMENT)
2705 nfheader_len += xfrm[i]->props.header_len;
2706 trailer_len += xfrm[i]->props.trailer_len;
2707 }
2708
2709 xfrm_dst_set_child(xdst_prev, dst);
2710 xdst0->path = dst;
2711
2712 err = -ENODEV;
2713 dev = dst->dev;
2714 if (!dev)
2715 goto free_dst;
2716
2717 xfrm_init_path(xdst0, dst, nfheader_len);
2718 xfrm_init_pmtu(bundle, nx);
2719
2720 for (xdst_prev = xdst0; xdst_prev != (struct xfrm_dst *)dst;
2721 xdst_prev = (struct xfrm_dst *) xfrm_dst_child(&xdst_prev->u.dst)) {
2722 err = xfrm_fill_dst(xdst_prev, dev, fl);
2723 if (err)
2724 goto free_dst;
2725
2726 xdst_prev->u.dst.header_len = header_len;
2727 xdst_prev->u.dst.trailer_len = trailer_len;
2728 header_len -= xdst_prev->u.dst.xfrm->props.header_len;
2729 trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len;
2730 }
2731
2732 return &xdst0->u.dst;
2733
2734 put_states:
2735 for (; i < nx; i++)
2736 xfrm_state_put(xfrm[i]);
2737 free_dst:
2738 if (xdst0)
2739 dst_release_immediate(&xdst0->u.dst);
2740
2741 return ERR_PTR(err);
2742 }
2743
xfrm_expand_policies(const struct flowi * fl,u16 family,struct xfrm_policy ** pols,int * num_pols,int * num_xfrms)2744 static int xfrm_expand_policies(const struct flowi *fl, u16 family,
2745 struct xfrm_policy **pols,
2746 int *num_pols, int *num_xfrms)
2747 {
2748 int i;
2749
2750 if (*num_pols == 0 || !pols[0]) {
2751 *num_pols = 0;
2752 *num_xfrms = 0;
2753 return 0;
2754 }
2755 if (IS_ERR(pols[0])) {
2756 *num_pols = 0;
2757 return PTR_ERR(pols[0]);
2758 }
2759
2760 *num_xfrms = pols[0]->xfrm_nr;
2761
2762 #ifdef CONFIG_XFRM_SUB_POLICY
2763 if (pols[0]->action == XFRM_POLICY_ALLOW &&
2764 pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
2765 pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]),
2766 XFRM_POLICY_TYPE_MAIN,
2767 fl, family,
2768 XFRM_POLICY_OUT,
2769 pols[0]->if_id);
2770 if (pols[1]) {
2771 if (IS_ERR(pols[1])) {
2772 xfrm_pols_put(pols, *num_pols);
2773 *num_pols = 0;
2774 return PTR_ERR(pols[1]);
2775 }
2776 (*num_pols)++;
2777 (*num_xfrms) += pols[1]->xfrm_nr;
2778 }
2779 }
2780 #endif
2781 for (i = 0; i < *num_pols; i++) {
2782 if (pols[i]->action != XFRM_POLICY_ALLOW) {
2783 *num_xfrms = -1;
2784 break;
2785 }
2786 }
2787
2788 return 0;
2789
2790 }
2791
2792 static struct xfrm_dst *
xfrm_resolve_and_create_bundle(struct xfrm_policy ** pols,int num_pols,const struct flowi * fl,u16 family,struct dst_entry * dst_orig)2793 xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
2794 const struct flowi *fl, u16 family,
2795 struct dst_entry *dst_orig)
2796 {
2797 struct net *net = xp_net(pols[0]);
2798 struct xfrm_state *xfrm[XFRM_MAX_DEPTH];
2799 struct xfrm_dst *bundle[XFRM_MAX_DEPTH];
2800 struct xfrm_dst *xdst;
2801 struct dst_entry *dst;
2802 int err;
2803
2804 /* Try to instantiate a bundle */
2805 err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family);
2806 if (err <= 0) {
2807 if (err == 0)
2808 return NULL;
2809
2810 if (err != -EAGAIN)
2811 XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
2812 return ERR_PTR(err);
2813 }
2814
2815 dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig);
2816 if (IS_ERR(dst)) {
2817 XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR);
2818 return ERR_CAST(dst);
2819 }
2820
2821 xdst = (struct xfrm_dst *)dst;
2822 xdst->num_xfrms = err;
2823 xdst->num_pols = num_pols;
2824 memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
2825 xdst->policy_genid = atomic_read(&pols[0]->genid);
2826
2827 return xdst;
2828 }
2829
xfrm_policy_queue_process(struct timer_list * t)2830 static void xfrm_policy_queue_process(struct timer_list *t)
2831 {
2832 struct sk_buff *skb;
2833 struct sock *sk;
2834 struct dst_entry *dst;
2835 struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer);
2836 struct net *net = xp_net(pol);
2837 struct xfrm_policy_queue *pq = &pol->polq;
2838 struct flowi fl;
2839 struct sk_buff_head list;
2840 __u32 skb_mark;
2841
2842 spin_lock(&pq->hold_queue.lock);
2843 skb = skb_peek(&pq->hold_queue);
2844 if (!skb) {
2845 spin_unlock(&pq->hold_queue.lock);
2846 goto out;
2847 }
2848 dst = skb_dst(skb);
2849 sk = skb->sk;
2850
2851 /* Fixup the mark to support VTI. */
2852 skb_mark = skb->mark;
2853 skb->mark = pol->mark.v;
2854 xfrm_decode_session(skb, &fl, dst->ops->family);
2855 skb->mark = skb_mark;
2856 spin_unlock(&pq->hold_queue.lock);
2857
2858 dst_hold(xfrm_dst_path(dst));
2859 dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE);
2860 if (IS_ERR(dst))
2861 goto purge_queue;
2862
2863 if (dst->flags & DST_XFRM_QUEUE) {
2864 dst_release(dst);
2865
2866 if (pq->timeout >= XFRM_QUEUE_TMO_MAX)
2867 goto purge_queue;
2868
2869 pq->timeout = pq->timeout << 1;
2870 if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout))
2871 xfrm_pol_hold(pol);
2872 goto out;
2873 }
2874
2875 dst_release(dst);
2876
2877 __skb_queue_head_init(&list);
2878
2879 spin_lock(&pq->hold_queue.lock);
2880 pq->timeout = 0;
2881 skb_queue_splice_init(&pq->hold_queue, &list);
2882 spin_unlock(&pq->hold_queue.lock);
2883
2884 while (!skb_queue_empty(&list)) {
2885 skb = __skb_dequeue(&list);
2886
2887 /* Fixup the mark to support VTI. */
2888 skb_mark = skb->mark;
2889 skb->mark = pol->mark.v;
2890 xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family);
2891 skb->mark = skb_mark;
2892
2893 dst_hold(xfrm_dst_path(skb_dst(skb)));
2894 dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0);
2895 if (IS_ERR(dst)) {
2896 kfree_skb(skb);
2897 continue;
2898 }
2899
2900 nf_reset_ct(skb);
2901 skb_dst_drop(skb);
2902 skb_dst_set(skb, dst);
2903
2904 dst_output(net, skb->sk, skb);
2905 }
2906
2907 out:
2908 xfrm_pol_put(pol);
2909 return;
2910
2911 purge_queue:
2912 pq->timeout = 0;
2913 skb_queue_purge(&pq->hold_queue);
2914 xfrm_pol_put(pol);
2915 }
2916
xdst_queue_output(struct net * net,struct sock * sk,struct sk_buff * skb)2917 static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb)
2918 {
2919 unsigned long sched_next;
2920 struct dst_entry *dst = skb_dst(skb);
2921 struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
2922 struct xfrm_policy *pol = xdst->pols[0];
2923 struct xfrm_policy_queue *pq = &pol->polq;
2924
2925 if (unlikely(skb_fclone_busy(sk, skb))) {
2926 kfree_skb(skb);
2927 return 0;
2928 }
2929
2930 if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) {
2931 kfree_skb(skb);
2932 return -EAGAIN;
2933 }
2934
2935 skb_dst_force(skb);
2936
2937 spin_lock_bh(&pq->hold_queue.lock);
2938
2939 if (!pq->timeout)
2940 pq->timeout = XFRM_QUEUE_TMO_MIN;
2941
2942 sched_next = jiffies + pq->timeout;
2943
2944 if (del_timer(&pq->hold_timer)) {
2945 if (time_before(pq->hold_timer.expires, sched_next))
2946 sched_next = pq->hold_timer.expires;
2947 xfrm_pol_put(pol);
2948 }
2949
2950 __skb_queue_tail(&pq->hold_queue, skb);
2951 if (!mod_timer(&pq->hold_timer, sched_next))
2952 xfrm_pol_hold(pol);
2953
2954 spin_unlock_bh(&pq->hold_queue.lock);
2955
2956 return 0;
2957 }
2958
xfrm_create_dummy_bundle(struct net * net,struct xfrm_flo * xflo,const struct flowi * fl,int num_xfrms,u16 family)2959 static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
2960 struct xfrm_flo *xflo,
2961 const struct flowi *fl,
2962 int num_xfrms,
2963 u16 family)
2964 {
2965 int err;
2966 struct net_device *dev;
2967 struct dst_entry *dst;
2968 struct dst_entry *dst1;
2969 struct xfrm_dst *xdst;
2970
2971 xdst = xfrm_alloc_dst(net, family);
2972 if (IS_ERR(xdst))
2973 return xdst;
2974
2975 if (!(xflo->flags & XFRM_LOOKUP_QUEUE) ||
2976 net->xfrm.sysctl_larval_drop ||
2977 num_xfrms <= 0)
2978 return xdst;
2979
2980 dst = xflo->dst_orig;
2981 dst1 = &xdst->u.dst;
2982 dst_hold(dst);
2983 xdst->route = dst;
2984
2985 dst_copy_metrics(dst1, dst);
2986
2987 dst1->obsolete = DST_OBSOLETE_FORCE_CHK;
2988 dst1->flags |= DST_XFRM_QUEUE;
2989 dst1->lastuse = jiffies;
2990
2991 dst1->input = dst_discard;
2992 dst1->output = xdst_queue_output;
2993
2994 dst_hold(dst);
2995 xfrm_dst_set_child(xdst, dst);
2996 xdst->path = dst;
2997
2998 xfrm_init_path((struct xfrm_dst *)dst1, dst, 0);
2999
3000 err = -ENODEV;
3001 dev = dst->dev;
3002 if (!dev)
3003 goto free_dst;
3004
3005 err = xfrm_fill_dst(xdst, dev, fl);
3006 if (err)
3007 goto free_dst;
3008
3009 out:
3010 return xdst;
3011
3012 free_dst:
3013 dst_release(dst1);
3014 xdst = ERR_PTR(err);
3015 goto out;
3016 }
3017
xfrm_bundle_lookup(struct net * net,const struct flowi * fl,u16 family,u8 dir,struct xfrm_flo * xflo,u32 if_id)3018 static struct xfrm_dst *xfrm_bundle_lookup(struct net *net,
3019 const struct flowi *fl,
3020 u16 family, u8 dir,
3021 struct xfrm_flo *xflo, u32 if_id)
3022 {
3023 struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
3024 int num_pols = 0, num_xfrms = 0, err;
3025 struct xfrm_dst *xdst;
3026
3027 /* Resolve policies to use if we couldn't get them from
3028 * previous cache entry */
3029 num_pols = 1;
3030 pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id);
3031 err = xfrm_expand_policies(fl, family, pols,
3032 &num_pols, &num_xfrms);
3033 if (err < 0)
3034 goto inc_error;
3035 if (num_pols == 0)
3036 return NULL;
3037 if (num_xfrms <= 0)
3038 goto make_dummy_bundle;
3039
3040 xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
3041 xflo->dst_orig);
3042 if (IS_ERR(xdst)) {
3043 err = PTR_ERR(xdst);
3044 if (err == -EREMOTE) {
3045 xfrm_pols_put(pols, num_pols);
3046 return NULL;
3047 }
3048
3049 if (err != -EAGAIN)
3050 goto error;
3051 goto make_dummy_bundle;
3052 } else if (xdst == NULL) {
3053 num_xfrms = 0;
3054 goto make_dummy_bundle;
3055 }
3056
3057 return xdst;
3058
3059 make_dummy_bundle:
3060 /* We found policies, but there's no bundles to instantiate:
3061 * either because the policy blocks, has no transformations or
3062 * we could not build template (no xfrm_states).*/
3063 xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family);
3064 if (IS_ERR(xdst)) {
3065 xfrm_pols_put(pols, num_pols);
3066 return ERR_CAST(xdst);
3067 }
3068 xdst->num_pols = num_pols;
3069 xdst->num_xfrms = num_xfrms;
3070 memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
3071
3072 return xdst;
3073
3074 inc_error:
3075 XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
3076 error:
3077 xfrm_pols_put(pols, num_pols);
3078 return ERR_PTR(err);
3079 }
3080
make_blackhole(struct net * net,u16 family,struct dst_entry * dst_orig)3081 static struct dst_entry *make_blackhole(struct net *net, u16 family,
3082 struct dst_entry *dst_orig)
3083 {
3084 const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
3085 struct dst_entry *ret;
3086
3087 if (!afinfo) {
3088 dst_release(dst_orig);
3089 return ERR_PTR(-EINVAL);
3090 } else {
3091 ret = afinfo->blackhole_route(net, dst_orig);
3092 }
3093 rcu_read_unlock();
3094
3095 return ret;
3096 }
3097
3098 /* Finds/creates a bundle for given flow and if_id
3099 *
3100 * At the moment we eat a raw IP route. Mostly to speed up lookups
3101 * on interfaces with disabled IPsec.
3102 *
3103 * xfrm_lookup uses an if_id of 0 by default, and is provided for
3104 * compatibility
3105 */
xfrm_lookup_with_ifid(struct net * net,struct dst_entry * dst_orig,const struct flowi * fl,const struct sock * sk,int flags,u32 if_id)3106 struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
3107 struct dst_entry *dst_orig,
3108 const struct flowi *fl,
3109 const struct sock *sk,
3110 int flags, u32 if_id)
3111 {
3112 struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
3113 struct xfrm_dst *xdst;
3114 struct dst_entry *dst, *route;
3115 u16 family = dst_orig->ops->family;
3116 u8 dir = XFRM_POLICY_OUT;
3117 int i, err, num_pols, num_xfrms = 0, drop_pols = 0;
3118
3119 dst = NULL;
3120 xdst = NULL;
3121 route = NULL;
3122
3123 sk = sk_const_to_full_sk(sk);
3124 if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
3125 num_pols = 1;
3126 pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family,
3127 if_id);
3128 err = xfrm_expand_policies(fl, family, pols,
3129 &num_pols, &num_xfrms);
3130 if (err < 0)
3131 goto dropdst;
3132
3133 if (num_pols) {
3134 if (num_xfrms <= 0) {
3135 drop_pols = num_pols;
3136 goto no_transform;
3137 }
3138
3139 xdst = xfrm_resolve_and_create_bundle(
3140 pols, num_pols, fl,
3141 family, dst_orig);
3142
3143 if (IS_ERR(xdst)) {
3144 xfrm_pols_put(pols, num_pols);
3145 err = PTR_ERR(xdst);
3146 if (err == -EREMOTE)
3147 goto nopol;
3148
3149 goto dropdst;
3150 } else if (xdst == NULL) {
3151 num_xfrms = 0;
3152 drop_pols = num_pols;
3153 goto no_transform;
3154 }
3155
3156 route = xdst->route;
3157 }
3158 }
3159
3160 if (xdst == NULL) {
3161 struct xfrm_flo xflo;
3162
3163 xflo.dst_orig = dst_orig;
3164 xflo.flags = flags;
3165
3166 /* To accelerate a bit... */
3167 if (!if_id && ((dst_orig->flags & DST_NOXFRM) ||
3168 !net->xfrm.policy_count[XFRM_POLICY_OUT]))
3169 goto nopol;
3170
3171 xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id);
3172 if (xdst == NULL)
3173 goto nopol;
3174 if (IS_ERR(xdst)) {
3175 err = PTR_ERR(xdst);
3176 goto dropdst;
3177 }
3178
3179 num_pols = xdst->num_pols;
3180 num_xfrms = xdst->num_xfrms;
3181 memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols);
3182 route = xdst->route;
3183 }
3184
3185 dst = &xdst->u.dst;
3186 if (route == NULL && num_xfrms > 0) {
3187 /* The only case when xfrm_bundle_lookup() returns a
3188 * bundle with null route, is when the template could
3189 * not be resolved. It means policies are there, but
3190 * bundle could not be created, since we don't yet
3191 * have the xfrm_state's. We need to wait for KM to
3192 * negotiate new SA's or bail out with error.*/
3193 if (net->xfrm.sysctl_larval_drop) {
3194 XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
3195 err = -EREMOTE;
3196 goto error;
3197 }
3198
3199 err = -EAGAIN;
3200
3201 XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
3202 goto error;
3203 }
3204
3205 no_transform:
3206 if (num_pols == 0)
3207 goto nopol;
3208
3209 if ((flags & XFRM_LOOKUP_ICMP) &&
3210 !(pols[0]->flags & XFRM_POLICY_ICMP)) {
3211 err = -ENOENT;
3212 goto error;
3213 }
3214
3215 for (i = 0; i < num_pols; i++)
3216 pols[i]->curlft.use_time = ktime_get_real_seconds();
3217
3218 if (num_xfrms < 0) {
3219 /* Prohibit the flow */
3220 XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK);
3221 err = -EPERM;
3222 goto error;
3223 } else if (num_xfrms > 0) {
3224 /* Flow transformed */
3225 dst_release(dst_orig);
3226 } else {
3227 /* Flow passes untransformed */
3228 dst_release(dst);
3229 dst = dst_orig;
3230 }
3231 ok:
3232 xfrm_pols_put(pols, drop_pols);
3233 if (dst && dst->xfrm &&
3234 dst->xfrm->props.mode == XFRM_MODE_TUNNEL)
3235 dst->flags |= DST_XFRM_TUNNEL;
3236 return dst;
3237
3238 nopol:
3239 if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) &&
3240 net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
3241 err = -EPERM;
3242 goto error;
3243 }
3244 if (!(flags & XFRM_LOOKUP_ICMP)) {
3245 dst = dst_orig;
3246 goto ok;
3247 }
3248 err = -ENOENT;
3249 error:
3250 dst_release(dst);
3251 dropdst:
3252 if (!(flags & XFRM_LOOKUP_KEEP_DST_REF))
3253 dst_release(dst_orig);
3254 xfrm_pols_put(pols, drop_pols);
3255 return ERR_PTR(err);
3256 }
3257 EXPORT_SYMBOL(xfrm_lookup_with_ifid);
3258
3259 /* Main function: finds/creates a bundle for given flow.
3260 *
3261 * At the moment we eat a raw IP route. Mostly to speed up lookups
3262 * on interfaces with disabled IPsec.
3263 */
xfrm_lookup(struct net * net,struct dst_entry * dst_orig,const struct flowi * fl,const struct sock * sk,int flags)3264 struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
3265 const struct flowi *fl, const struct sock *sk,
3266 int flags)
3267 {
3268 return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0);
3269 }
3270 EXPORT_SYMBOL(xfrm_lookup);
3271
3272 /* Callers of xfrm_lookup_route() must ensure a call to dst_output().
3273 * Otherwise we may send out blackholed packets.
3274 */
xfrm_lookup_route(struct net * net,struct dst_entry * dst_orig,const struct flowi * fl,const struct sock * sk,int flags)3275 struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
3276 const struct flowi *fl,
3277 const struct sock *sk, int flags)
3278 {
3279 struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk,
3280 flags | XFRM_LOOKUP_QUEUE |
3281 XFRM_LOOKUP_KEEP_DST_REF);
3282
3283 if (PTR_ERR(dst) == -EREMOTE)
3284 return make_blackhole(net, dst_orig->ops->family, dst_orig);
3285
3286 if (IS_ERR(dst))
3287 dst_release(dst_orig);
3288
3289 return dst;
3290 }
3291 EXPORT_SYMBOL(xfrm_lookup_route);
3292
3293 static inline int
xfrm_secpath_reject(int idx,struct sk_buff * skb,const struct flowi * fl)3294 xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl)
3295 {
3296 struct sec_path *sp = skb_sec_path(skb);
3297 struct xfrm_state *x;
3298
3299 if (!sp || idx < 0 || idx >= sp->len)
3300 return 0;
3301 x = sp->xvec[idx];
3302 if (!x->type->reject)
3303 return 0;
3304 return x->type->reject(x, skb, fl);
3305 }
3306
3307 /* When skb is transformed back to its "native" form, we have to
3308 * check policy restrictions. At the moment we make this in maximally
3309 * stupid way. Shame on me. :-) Of course, connected sockets must
3310 * have policy cached at them.
3311 */
3312
3313 static inline int
xfrm_state_ok(const struct xfrm_tmpl * tmpl,const struct xfrm_state * x,unsigned short family)3314 xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x,
3315 unsigned short family)
3316 {
3317 if (xfrm_state_kern(x))
3318 return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family);
3319 return x->id.proto == tmpl->id.proto &&
3320 (x->id.spi == tmpl->id.spi || !tmpl->id.spi) &&
3321 (x->props.reqid == tmpl->reqid || !tmpl->reqid) &&
3322 x->props.mode == tmpl->mode &&
3323 (tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) ||
3324 !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) &&
3325 !(x->props.mode != XFRM_MODE_TRANSPORT &&
3326 xfrm_state_addr_cmp(tmpl, x, family));
3327 }
3328
3329 /*
3330 * 0 or more than 0 is returned when validation is succeeded (either bypass
3331 * because of optional transport mode, or next index of the matched secpath
3332 * state with the template.
3333 * -1 is returned when no matching template is found.
3334 * Otherwise "-2 - errored_index" is returned.
3335 */
3336 static inline int
xfrm_policy_ok(const struct xfrm_tmpl * tmpl,const struct sec_path * sp,int start,unsigned short family)3337 xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start,
3338 unsigned short family)
3339 {
3340 int idx = start;
3341
3342 if (tmpl->optional) {
3343 if (tmpl->mode == XFRM_MODE_TRANSPORT)
3344 return start;
3345 } else
3346 start = -1;
3347 for (; idx < sp->len; idx++) {
3348 if (xfrm_state_ok(tmpl, sp->xvec[idx], family))
3349 return ++idx;
3350 if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) {
3351 if (start == -1)
3352 start = -2-idx;
3353 break;
3354 }
3355 }
3356 return start;
3357 }
3358
3359 static void
decode_session4(struct sk_buff * skb,struct flowi * fl,bool reverse)3360 decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
3361 {
3362 const struct iphdr *iph = ip_hdr(skb);
3363 int ihl = iph->ihl;
3364 u8 *xprth = skb_network_header(skb) + ihl * 4;
3365 struct flowi4 *fl4 = &fl->u.ip4;
3366 int oif = 0;
3367
3368 if (skb_dst(skb) && skb_dst(skb)->dev)
3369 oif = skb_dst(skb)->dev->ifindex;
3370
3371 memset(fl4, 0, sizeof(struct flowi4));
3372 fl4->flowi4_mark = skb->mark;
3373 fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
3374
3375 fl4->flowi4_proto = iph->protocol;
3376 fl4->daddr = reverse ? iph->saddr : iph->daddr;
3377 fl4->saddr = reverse ? iph->daddr : iph->saddr;
3378 fl4->flowi4_tos = iph->tos & ~INET_ECN_MASK;
3379
3380 if (!ip_is_fragment(iph)) {
3381 switch (iph->protocol) {
3382 case IPPROTO_UDP:
3383 case IPPROTO_UDPLITE:
3384 case IPPROTO_TCP:
3385 case IPPROTO_SCTP:
3386 case IPPROTO_DCCP:
3387 if (xprth + 4 < skb->data ||
3388 pskb_may_pull(skb, xprth + 4 - skb->data)) {
3389 __be16 *ports;
3390
3391 xprth = skb_network_header(skb) + ihl * 4;
3392 ports = (__be16 *)xprth;
3393
3394 fl4->fl4_sport = ports[!!reverse];
3395 fl4->fl4_dport = ports[!reverse];
3396 }
3397 break;
3398 case IPPROTO_ICMP:
3399 if (xprth + 2 < skb->data ||
3400 pskb_may_pull(skb, xprth + 2 - skb->data)) {
3401 u8 *icmp;
3402
3403 xprth = skb_network_header(skb) + ihl * 4;
3404 icmp = xprth;
3405
3406 fl4->fl4_icmp_type = icmp[0];
3407 fl4->fl4_icmp_code = icmp[1];
3408 }
3409 break;
3410 case IPPROTO_GRE:
3411 if (xprth + 12 < skb->data ||
3412 pskb_may_pull(skb, xprth + 12 - skb->data)) {
3413 __be16 *greflags;
3414 __be32 *gre_hdr;
3415
3416 xprth = skb_network_header(skb) + ihl * 4;
3417 greflags = (__be16 *)xprth;
3418 gre_hdr = (__be32 *)xprth;
3419
3420 if (greflags[0] & GRE_KEY) {
3421 if (greflags[0] & GRE_CSUM)
3422 gre_hdr++;
3423 fl4->fl4_gre_key = gre_hdr[1];
3424 }
3425 }
3426 break;
3427 default:
3428 break;
3429 }
3430 }
3431 }
3432
3433 #if IS_ENABLED(CONFIG_IPV6)
3434 static void
decode_session6(struct sk_buff * skb,struct flowi * fl,bool reverse)3435 decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
3436 {
3437 struct flowi6 *fl6 = &fl->u.ip6;
3438 int onlyproto = 0;
3439 const struct ipv6hdr *hdr = ipv6_hdr(skb);
3440 u32 offset = sizeof(*hdr);
3441 struct ipv6_opt_hdr *exthdr;
3442 const unsigned char *nh = skb_network_header(skb);
3443 u16 nhoff = IP6CB(skb)->nhoff;
3444 int oif = 0;
3445 u8 nexthdr;
3446
3447 if (!nhoff)
3448 nhoff = offsetof(struct ipv6hdr, nexthdr);
3449
3450 nexthdr = nh[nhoff];
3451
3452 if (skb_dst(skb) && skb_dst(skb)->dev)
3453 oif = skb_dst(skb)->dev->ifindex;
3454
3455 memset(fl6, 0, sizeof(struct flowi6));
3456 fl6->flowi6_mark = skb->mark;
3457 fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
3458
3459 fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
3460 fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
3461
3462 while (nh + offset + sizeof(*exthdr) < skb->data ||
3463 pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) {
3464 nh = skb_network_header(skb);
3465 exthdr = (struct ipv6_opt_hdr *)(nh + offset);
3466
3467 switch (nexthdr) {
3468 case NEXTHDR_FRAGMENT:
3469 onlyproto = 1;
3470 fallthrough;
3471 case NEXTHDR_ROUTING:
3472 case NEXTHDR_HOP:
3473 case NEXTHDR_DEST:
3474 offset += ipv6_optlen(exthdr);
3475 nexthdr = exthdr->nexthdr;
3476 break;
3477 case IPPROTO_UDP:
3478 case IPPROTO_UDPLITE:
3479 case IPPROTO_TCP:
3480 case IPPROTO_SCTP:
3481 case IPPROTO_DCCP:
3482 if (!onlyproto && (nh + offset + 4 < skb->data ||
3483 pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
3484 __be16 *ports;
3485
3486 nh = skb_network_header(skb);
3487 ports = (__be16 *)(nh + offset);
3488 fl6->fl6_sport = ports[!!reverse];
3489 fl6->fl6_dport = ports[!reverse];
3490 }
3491 fl6->flowi6_proto = nexthdr;
3492 return;
3493 case IPPROTO_ICMPV6:
3494 if (!onlyproto && (nh + offset + 2 < skb->data ||
3495 pskb_may_pull(skb, nh + offset + 2 - skb->data))) {
3496 u8 *icmp;
3497
3498 nh = skb_network_header(skb);
3499 icmp = (u8 *)(nh + offset);
3500 fl6->fl6_icmp_type = icmp[0];
3501 fl6->fl6_icmp_code = icmp[1];
3502 }
3503 fl6->flowi6_proto = nexthdr;
3504 return;
3505 case IPPROTO_GRE:
3506 if (!onlyproto &&
3507 (nh + offset + 12 < skb->data ||
3508 pskb_may_pull(skb, nh + offset + 12 - skb->data))) {
3509 struct gre_base_hdr *gre_hdr;
3510 __be32 *gre_key;
3511
3512 nh = skb_network_header(skb);
3513 gre_hdr = (struct gre_base_hdr *)(nh + offset);
3514 gre_key = (__be32 *)(gre_hdr + 1);
3515
3516 if (gre_hdr->flags & GRE_KEY) {
3517 if (gre_hdr->flags & GRE_CSUM)
3518 gre_key++;
3519 fl6->fl6_gre_key = *gre_key;
3520 }
3521 }
3522 fl6->flowi6_proto = nexthdr;
3523 return;
3524
3525 #if IS_ENABLED(CONFIG_IPV6_MIP6)
3526 case IPPROTO_MH:
3527 offset += ipv6_optlen(exthdr);
3528 if (!onlyproto && (nh + offset + 3 < skb->data ||
3529 pskb_may_pull(skb, nh + offset + 3 - skb->data))) {
3530 struct ip6_mh *mh;
3531
3532 nh = skb_network_header(skb);
3533 mh = (struct ip6_mh *)(nh + offset);
3534 fl6->fl6_mh_type = mh->ip6mh_type;
3535 }
3536 fl6->flowi6_proto = nexthdr;
3537 return;
3538 #endif
3539 default:
3540 fl6->flowi6_proto = nexthdr;
3541 return;
3542 }
3543 }
3544 }
3545 #endif
3546
__xfrm_decode_session(struct sk_buff * skb,struct flowi * fl,unsigned int family,int reverse)3547 int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
3548 unsigned int family, int reverse)
3549 {
3550 switch (family) {
3551 case AF_INET:
3552 decode_session4(skb, fl, reverse);
3553 break;
3554 #if IS_ENABLED(CONFIG_IPV6)
3555 case AF_INET6:
3556 decode_session6(skb, fl, reverse);
3557 break;
3558 #endif
3559 default:
3560 return -EAFNOSUPPORT;
3561 }
3562
3563 return security_xfrm_decode_session(skb, &fl->flowi_secid);
3564 }
3565 EXPORT_SYMBOL(__xfrm_decode_session);
3566
secpath_has_nontransport(const struct sec_path * sp,int k,int * idxp)3567 static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int *idxp)
3568 {
3569 for (; k < sp->len; k++) {
3570 if (sp->xvec[k]->props.mode != XFRM_MODE_TRANSPORT) {
3571 *idxp = k;
3572 return 1;
3573 }
3574 }
3575
3576 return 0;
3577 }
3578
__xfrm_policy_check(struct sock * sk,int dir,struct sk_buff * skb,unsigned short family)3579 int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
3580 unsigned short family)
3581 {
3582 struct net *net = dev_net(skb->dev);
3583 struct xfrm_policy *pol;
3584 struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
3585 int npols = 0;
3586 int xfrm_nr;
3587 int pi;
3588 int reverse;
3589 struct flowi fl;
3590 int xerr_idx = -1;
3591 const struct xfrm_if_cb *ifcb;
3592 struct sec_path *sp;
3593 u32 if_id = 0;
3594
3595 rcu_read_lock();
3596 ifcb = xfrm_if_get_cb();
3597
3598 if (ifcb) {
3599 struct xfrm_if_decode_session_result r;
3600
3601 if (ifcb->decode_session(skb, family, &r)) {
3602 if_id = r.if_id;
3603 net = r.net;
3604 }
3605 }
3606 rcu_read_unlock();
3607
3608 reverse = dir & ~XFRM_POLICY_MASK;
3609 dir &= XFRM_POLICY_MASK;
3610
3611 if (__xfrm_decode_session(skb, &fl, family, reverse) < 0) {
3612 XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
3613 return 0;
3614 }
3615
3616 nf_nat_decode_session(skb, &fl, family);
3617
3618 /* First, check used SA against their selectors. */
3619 sp = skb_sec_path(skb);
3620 if (sp) {
3621 int i;
3622
3623 for (i = sp->len - 1; i >= 0; i--) {
3624 struct xfrm_state *x = sp->xvec[i];
3625 if (!xfrm_selector_match(&x->sel, &fl, family)) {
3626 XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
3627 return 0;
3628 }
3629 }
3630 }
3631
3632 pol = NULL;
3633 sk = sk_to_full_sk(sk);
3634 if (sk && sk->sk_policy[dir]) {
3635 pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id);
3636 if (IS_ERR(pol)) {
3637 XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
3638 return 0;
3639 }
3640 }
3641
3642 if (!pol)
3643 pol = xfrm_policy_lookup(net, &fl, family, dir, if_id);
3644
3645 if (IS_ERR(pol)) {
3646 XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
3647 return 0;
3648 }
3649
3650 if (!pol) {
3651 if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
3652 XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
3653 return 0;
3654 }
3655
3656 if (sp && secpath_has_nontransport(sp, 0, &xerr_idx)) {
3657 xfrm_secpath_reject(xerr_idx, skb, &fl);
3658 XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS);
3659 return 0;
3660 }
3661 return 1;
3662 }
3663
3664 /* This lockless write can happen from different cpus. */
3665 WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds());
3666
3667 pols[0] = pol;
3668 npols++;
3669 #ifdef CONFIG_XFRM_SUB_POLICY
3670 if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
3671 pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN,
3672 &fl, family,
3673 XFRM_POLICY_IN, if_id);
3674 if (pols[1]) {
3675 if (IS_ERR(pols[1])) {
3676 XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
3677 xfrm_pol_put(pols[0]);
3678 return 0;
3679 }
3680 /* This write can happen from different cpus. */
3681 WRITE_ONCE(pols[1]->curlft.use_time,
3682 ktime_get_real_seconds());
3683 npols++;
3684 }
3685 }
3686 #endif
3687
3688 if (pol->action == XFRM_POLICY_ALLOW) {
3689 static struct sec_path dummy;
3690 struct xfrm_tmpl *tp[XFRM_MAX_DEPTH];
3691 struct xfrm_tmpl *stp[XFRM_MAX_DEPTH];
3692 struct xfrm_tmpl **tpp = tp;
3693 int ti = 0;
3694 int i, k;
3695
3696 sp = skb_sec_path(skb);
3697 if (!sp)
3698 sp = &dummy;
3699
3700 for (pi = 0; pi < npols; pi++) {
3701 if (pols[pi] != pol &&
3702 pols[pi]->action != XFRM_POLICY_ALLOW) {
3703 XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK);
3704 goto reject;
3705 }
3706 if (ti + pols[pi]->xfrm_nr >= XFRM_MAX_DEPTH) {
3707 XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
3708 goto reject_error;
3709 }
3710 for (i = 0; i < pols[pi]->xfrm_nr; i++)
3711 tpp[ti++] = &pols[pi]->xfrm_vec[i];
3712 }
3713 xfrm_nr = ti;
3714
3715 if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK &&
3716 !xfrm_nr) {
3717 XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
3718 goto reject;
3719 }
3720
3721 if (npols > 1) {
3722 xfrm_tmpl_sort(stp, tpp, xfrm_nr, family);
3723 tpp = stp;
3724 }
3725
3726 /* For each tunnel xfrm, find the first matching tmpl.
3727 * For each tmpl before that, find corresponding xfrm.
3728 * Order is _important_. Later we will implement
3729 * some barriers, but at the moment barriers
3730 * are implied between each two transformations.
3731 */
3732 for (i = xfrm_nr-1, k = 0; i >= 0; i--) {
3733 k = xfrm_policy_ok(tpp[i], sp, k, family);
3734 if (k < 0) {
3735 if (k < -1)
3736 /* "-2 - errored_index" returned */
3737 xerr_idx = -(2+k);
3738 XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH);
3739 goto reject;
3740 }
3741 }
3742
3743 if (secpath_has_nontransport(sp, k, &xerr_idx)) {
3744 XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH);
3745 goto reject;
3746 }
3747
3748 if (if_id)
3749 secpath_reset(skb);
3750
3751 xfrm_pols_put(pols, npols);
3752 return 1;
3753 }
3754 XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK);
3755
3756 reject:
3757 xfrm_secpath_reject(xerr_idx, skb, &fl);
3758 reject_error:
3759 xfrm_pols_put(pols, npols);
3760 return 0;
3761 }
3762 EXPORT_SYMBOL(__xfrm_policy_check);
3763
__xfrm_route_forward(struct sk_buff * skb,unsigned short family)3764 int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
3765 {
3766 struct net *net = dev_net(skb->dev);
3767 struct flowi fl;
3768 struct dst_entry *dst;
3769 int res = 1;
3770
3771 if (xfrm_decode_session(skb, &fl, family) < 0) {
3772 XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR);
3773 return 0;
3774 }
3775
3776 skb_dst_force(skb);
3777 if (!skb_dst(skb)) {
3778 XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR);
3779 return 0;
3780 }
3781
3782 dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE);
3783 if (IS_ERR(dst)) {
3784 res = 0;
3785 dst = NULL;
3786 }
3787 skb_dst_set(skb, dst);
3788 return res;
3789 }
3790 EXPORT_SYMBOL(__xfrm_route_forward);
3791
3792 /* Optimize later using cookies and generation ids. */
3793
xfrm_dst_check(struct dst_entry * dst,u32 cookie)3794 static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie)
3795 {
3796 /* Code (such as __xfrm4_bundle_create()) sets dst->obsolete
3797 * to DST_OBSOLETE_FORCE_CHK to force all XFRM destinations to
3798 * get validated by dst_ops->check on every use. We do this
3799 * because when a normal route referenced by an XFRM dst is
3800 * obsoleted we do not go looking around for all parent
3801 * referencing XFRM dsts so that we can invalidate them. It
3802 * is just too much work. Instead we make the checks here on
3803 * every use. For example:
3804 *
3805 * XFRM dst A --> IPv4 dst X
3806 *
3807 * X is the "xdst->route" of A (X is also the "dst->path" of A
3808 * in this example). If X is marked obsolete, "A" will not
3809 * notice. That's what we are validating here via the
3810 * stale_bundle() check.
3811 *
3812 * When a dst is removed from the fib tree, DST_OBSOLETE_DEAD will
3813 * be marked on it.
3814 * This will force stale_bundle() to fail on any xdst bundle with
3815 * this dst linked in it.
3816 */
3817 if (dst->obsolete < 0 && !stale_bundle(dst))
3818 return dst;
3819
3820 return NULL;
3821 }
3822
stale_bundle(struct dst_entry * dst)3823 static int stale_bundle(struct dst_entry *dst)
3824 {
3825 return !xfrm_bundle_ok((struct xfrm_dst *)dst);
3826 }
3827
xfrm_dst_ifdown(struct dst_entry * dst,struct net_device * dev)3828 void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
3829 {
3830 while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) {
3831 dst->dev = blackhole_netdev;
3832 dev_hold(dst->dev);
3833 dev_put(dev);
3834 }
3835 }
3836 EXPORT_SYMBOL(xfrm_dst_ifdown);
3837
xfrm_link_failure(struct sk_buff * skb)3838 static void xfrm_link_failure(struct sk_buff *skb)
3839 {
3840 /* Impossible. Such dst must be popped before reaches point of failure. */
3841 }
3842
xfrm_negative_advice(struct dst_entry * dst)3843 static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst)
3844 {
3845 if (dst) {
3846 if (dst->obsolete) {
3847 dst_release(dst);
3848 dst = NULL;
3849 }
3850 }
3851 return dst;
3852 }
3853
xfrm_init_pmtu(struct xfrm_dst ** bundle,int nr)3854 static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr)
3855 {
3856 while (nr--) {
3857 struct xfrm_dst *xdst = bundle[nr];
3858 u32 pmtu, route_mtu_cached;
3859 struct dst_entry *dst;
3860
3861 dst = &xdst->u.dst;
3862 pmtu = dst_mtu(xfrm_dst_child(dst));
3863 xdst->child_mtu_cached = pmtu;
3864
3865 pmtu = xfrm_state_mtu(dst->xfrm, pmtu);
3866
3867 route_mtu_cached = dst_mtu(xdst->route);
3868 xdst->route_mtu_cached = route_mtu_cached;
3869
3870 if (pmtu > route_mtu_cached)
3871 pmtu = route_mtu_cached;
3872
3873 dst_metric_set(dst, RTAX_MTU, pmtu);
3874 }
3875 }
3876
3877 /* Check that the bundle accepts the flow and its components are
3878 * still valid.
3879 */
3880
xfrm_bundle_ok(struct xfrm_dst * first)3881 static int xfrm_bundle_ok(struct xfrm_dst *first)
3882 {
3883 struct xfrm_dst *bundle[XFRM_MAX_DEPTH];
3884 struct dst_entry *dst = &first->u.dst;
3885 struct xfrm_dst *xdst;
3886 int start_from, nr;
3887 u32 mtu;
3888
3889 if (!dst_check(xfrm_dst_path(dst), ((struct xfrm_dst *)dst)->path_cookie) ||
3890 (dst->dev && !netif_running(dst->dev)))
3891 return 0;
3892
3893 if (dst->flags & DST_XFRM_QUEUE)
3894 return 1;
3895
3896 start_from = nr = 0;
3897 do {
3898 struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
3899
3900 if (dst->xfrm->km.state != XFRM_STATE_VALID)
3901 return 0;
3902 if (xdst->xfrm_genid != dst->xfrm->genid)
3903 return 0;
3904 if (xdst->num_pols > 0 &&
3905 xdst->policy_genid != atomic_read(&xdst->pols[0]->genid))
3906 return 0;
3907
3908 bundle[nr++] = xdst;
3909
3910 mtu = dst_mtu(xfrm_dst_child(dst));
3911 if (xdst->child_mtu_cached != mtu) {
3912 start_from = nr;
3913 xdst->child_mtu_cached = mtu;
3914 }
3915
3916 if (!dst_check(xdst->route, xdst->route_cookie))
3917 return 0;
3918 mtu = dst_mtu(xdst->route);
3919 if (xdst->route_mtu_cached != mtu) {
3920 start_from = nr;
3921 xdst->route_mtu_cached = mtu;
3922 }
3923
3924 dst = xfrm_dst_child(dst);
3925 } while (dst->xfrm);
3926
3927 if (likely(!start_from))
3928 return 1;
3929
3930 xdst = bundle[start_from - 1];
3931 mtu = xdst->child_mtu_cached;
3932 while (start_from--) {
3933 dst = &xdst->u.dst;
3934
3935 mtu = xfrm_state_mtu(dst->xfrm, mtu);
3936 if (mtu > xdst->route_mtu_cached)
3937 mtu = xdst->route_mtu_cached;
3938 dst_metric_set(dst, RTAX_MTU, mtu);
3939 if (!start_from)
3940 break;
3941
3942 xdst = bundle[start_from - 1];
3943 xdst->child_mtu_cached = mtu;
3944 }
3945
3946 return 1;
3947 }
3948
xfrm_default_advmss(const struct dst_entry * dst)3949 static unsigned int xfrm_default_advmss(const struct dst_entry *dst)
3950 {
3951 return dst_metric_advmss(xfrm_dst_path(dst));
3952 }
3953
xfrm_mtu(const struct dst_entry * dst)3954 static unsigned int xfrm_mtu(const struct dst_entry *dst)
3955 {
3956 unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
3957
3958 return mtu ? : dst_mtu(xfrm_dst_path(dst));
3959 }
3960
xfrm_get_dst_nexthop(const struct dst_entry * dst,const void * daddr)3961 static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst,
3962 const void *daddr)
3963 {
3964 while (dst->xfrm) {
3965 const struct xfrm_state *xfrm = dst->xfrm;
3966
3967 dst = xfrm_dst_child(dst);
3968
3969 if (xfrm->props.mode == XFRM_MODE_TRANSPORT)
3970 continue;
3971 if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR)
3972 daddr = xfrm->coaddr;
3973 else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR))
3974 daddr = &xfrm->id.daddr;
3975 }
3976 return daddr;
3977 }
3978
xfrm_neigh_lookup(const struct dst_entry * dst,struct sk_buff * skb,const void * daddr)3979 static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
3980 struct sk_buff *skb,
3981 const void *daddr)
3982 {
3983 const struct dst_entry *path = xfrm_dst_path(dst);
3984
3985 if (!skb)
3986 daddr = xfrm_get_dst_nexthop(dst, daddr);
3987 return path->ops->neigh_lookup(path, skb, daddr);
3988 }
3989
xfrm_confirm_neigh(const struct dst_entry * dst,const void * daddr)3990 static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr)
3991 {
3992 const struct dst_entry *path = xfrm_dst_path(dst);
3993
3994 daddr = xfrm_get_dst_nexthop(dst, daddr);
3995 path->ops->confirm_neigh(path, daddr);
3996 }
3997
xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo * afinfo,int family)3998 int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family)
3999 {
4000 int err = 0;
4001
4002 if (WARN_ON(family >= ARRAY_SIZE(xfrm_policy_afinfo)))
4003 return -EAFNOSUPPORT;
4004
4005 spin_lock(&xfrm_policy_afinfo_lock);
4006 if (unlikely(xfrm_policy_afinfo[family] != NULL))
4007 err = -EEXIST;
4008 else {
4009 struct dst_ops *dst_ops = afinfo->dst_ops;
4010 if (likely(dst_ops->kmem_cachep == NULL))
4011 dst_ops->kmem_cachep = xfrm_dst_cache;
4012 if (likely(dst_ops->check == NULL))
4013 dst_ops->check = xfrm_dst_check;
4014 if (likely(dst_ops->default_advmss == NULL))
4015 dst_ops->default_advmss = xfrm_default_advmss;
4016 if (likely(dst_ops->mtu == NULL))
4017 dst_ops->mtu = xfrm_mtu;
4018 if (likely(dst_ops->negative_advice == NULL))
4019 dst_ops->negative_advice = xfrm_negative_advice;
4020 if (likely(dst_ops->link_failure == NULL))
4021 dst_ops->link_failure = xfrm_link_failure;
4022 if (likely(dst_ops->neigh_lookup == NULL))
4023 dst_ops->neigh_lookup = xfrm_neigh_lookup;
4024 if (likely(!dst_ops->confirm_neigh))
4025 dst_ops->confirm_neigh = xfrm_confirm_neigh;
4026 rcu_assign_pointer(xfrm_policy_afinfo[family], afinfo);
4027 }
4028 spin_unlock(&xfrm_policy_afinfo_lock);
4029
4030 return err;
4031 }
4032 EXPORT_SYMBOL(xfrm_policy_register_afinfo);
4033
xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo * afinfo)4034 void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo)
4035 {
4036 struct dst_ops *dst_ops = afinfo->dst_ops;
4037 int i;
4038
4039 for (i = 0; i < ARRAY_SIZE(xfrm_policy_afinfo); i++) {
4040 if (xfrm_policy_afinfo[i] != afinfo)
4041 continue;
4042 RCU_INIT_POINTER(xfrm_policy_afinfo[i], NULL);
4043 break;
4044 }
4045
4046 synchronize_rcu();
4047
4048 dst_ops->kmem_cachep = NULL;
4049 dst_ops->check = NULL;
4050 dst_ops->negative_advice = NULL;
4051 dst_ops->link_failure = NULL;
4052 }
4053 EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
4054
xfrm_if_register_cb(const struct xfrm_if_cb * ifcb)4055 void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb)
4056 {
4057 spin_lock(&xfrm_if_cb_lock);
4058 rcu_assign_pointer(xfrm_if_cb, ifcb);
4059 spin_unlock(&xfrm_if_cb_lock);
4060 }
4061 EXPORT_SYMBOL(xfrm_if_register_cb);
4062
xfrm_if_unregister_cb(void)4063 void xfrm_if_unregister_cb(void)
4064 {
4065 RCU_INIT_POINTER(xfrm_if_cb, NULL);
4066 synchronize_rcu();
4067 }
4068 EXPORT_SYMBOL(xfrm_if_unregister_cb);
4069
4070 #ifdef CONFIG_XFRM_STATISTICS
xfrm_statistics_init(struct net * net)4071 static int __net_init xfrm_statistics_init(struct net *net)
4072 {
4073 int rv;
4074 net->mib.xfrm_statistics = alloc_percpu(struct linux_xfrm_mib);
4075 if (!net->mib.xfrm_statistics)
4076 return -ENOMEM;
4077 rv = xfrm_proc_init(net);
4078 if (rv < 0)
4079 free_percpu(net->mib.xfrm_statistics);
4080 return rv;
4081 }
4082
xfrm_statistics_fini(struct net * net)4083 static void xfrm_statistics_fini(struct net *net)
4084 {
4085 xfrm_proc_fini(net);
4086 free_percpu(net->mib.xfrm_statistics);
4087 }
4088 #else
xfrm_statistics_init(struct net * net)4089 static int __net_init xfrm_statistics_init(struct net *net)
4090 {
4091 return 0;
4092 }
4093
xfrm_statistics_fini(struct net * net)4094 static void xfrm_statistics_fini(struct net *net)
4095 {
4096 }
4097 #endif
4098
xfrm_policy_init(struct net * net)4099 static int __net_init xfrm_policy_init(struct net *net)
4100 {
4101 unsigned int hmask, sz;
4102 int dir, err;
4103
4104 if (net_eq(net, &init_net)) {
4105 xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache",
4106 sizeof(struct xfrm_dst),
4107 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
4108 NULL);
4109 err = rhashtable_init(&xfrm_policy_inexact_table,
4110 &xfrm_pol_inexact_params);
4111 BUG_ON(err);
4112 }
4113
4114 hmask = 8 - 1;
4115 sz = (hmask+1) * sizeof(struct hlist_head);
4116
4117 net->xfrm.policy_byidx = xfrm_hash_alloc(sz);
4118 if (!net->xfrm.policy_byidx)
4119 goto out_byidx;
4120 net->xfrm.policy_idx_hmask = hmask;
4121
4122 for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
4123 struct xfrm_policy_hash *htab;
4124
4125 net->xfrm.policy_count[dir] = 0;
4126 net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0;
4127 INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
4128
4129 htab = &net->xfrm.policy_bydst[dir];
4130 htab->table = xfrm_hash_alloc(sz);
4131 if (!htab->table)
4132 goto out_bydst;
4133 htab->hmask = hmask;
4134 htab->dbits4 = 32;
4135 htab->sbits4 = 32;
4136 htab->dbits6 = 128;
4137 htab->sbits6 = 128;
4138 }
4139 net->xfrm.policy_hthresh.lbits4 = 32;
4140 net->xfrm.policy_hthresh.rbits4 = 32;
4141 net->xfrm.policy_hthresh.lbits6 = 128;
4142 net->xfrm.policy_hthresh.rbits6 = 128;
4143
4144 seqlock_init(&net->xfrm.policy_hthresh.lock);
4145
4146 INIT_LIST_HEAD(&net->xfrm.policy_all);
4147 INIT_LIST_HEAD(&net->xfrm.inexact_bins);
4148 INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
4149 INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
4150 return 0;
4151
4152 out_bydst:
4153 for (dir--; dir >= 0; dir--) {
4154 struct xfrm_policy_hash *htab;
4155
4156 htab = &net->xfrm.policy_bydst[dir];
4157 xfrm_hash_free(htab->table, sz);
4158 }
4159 xfrm_hash_free(net->xfrm.policy_byidx, sz);
4160 out_byidx:
4161 return -ENOMEM;
4162 }
4163
xfrm_policy_fini(struct net * net)4164 static void xfrm_policy_fini(struct net *net)
4165 {
4166 struct xfrm_pol_inexact_bin *b, *t;
4167 unsigned int sz;
4168 int dir;
4169
4170 flush_work(&net->xfrm.policy_hash_work);
4171 #ifdef CONFIG_XFRM_SUB_POLICY
4172 xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false);
4173 #endif
4174 xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false);
4175
4176 WARN_ON(!list_empty(&net->xfrm.policy_all));
4177
4178 for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
4179 struct xfrm_policy_hash *htab;
4180
4181 WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir]));
4182
4183 htab = &net->xfrm.policy_bydst[dir];
4184 sz = (htab->hmask + 1) * sizeof(struct hlist_head);
4185 WARN_ON(!hlist_empty(htab->table));
4186 xfrm_hash_free(htab->table, sz);
4187 }
4188
4189 sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head);
4190 WARN_ON(!hlist_empty(net->xfrm.policy_byidx));
4191 xfrm_hash_free(net->xfrm.policy_byidx, sz);
4192
4193 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
4194 list_for_each_entry_safe(b, t, &net->xfrm.inexact_bins, inexact_bins)
4195 __xfrm_policy_inexact_prune_bin(b, true);
4196 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
4197 }
4198
xfrm_net_init(struct net * net)4199 static int __net_init xfrm_net_init(struct net *net)
4200 {
4201 int rv;
4202
4203 /* Initialize the per-net locks here */
4204 spin_lock_init(&net->xfrm.xfrm_state_lock);
4205 spin_lock_init(&net->xfrm.xfrm_policy_lock);
4206 seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock);
4207 mutex_init(&net->xfrm.xfrm_cfg_mutex);
4208 net->xfrm.policy_default[XFRM_POLICY_IN] = XFRM_USERPOLICY_ACCEPT;
4209 net->xfrm.policy_default[XFRM_POLICY_FWD] = XFRM_USERPOLICY_ACCEPT;
4210 net->xfrm.policy_default[XFRM_POLICY_OUT] = XFRM_USERPOLICY_ACCEPT;
4211
4212 rv = xfrm_statistics_init(net);
4213 if (rv < 0)
4214 goto out_statistics;
4215 rv = xfrm_state_init(net);
4216 if (rv < 0)
4217 goto out_state;
4218 rv = xfrm_policy_init(net);
4219 if (rv < 0)
4220 goto out_policy;
4221 rv = xfrm_sysctl_init(net);
4222 if (rv < 0)
4223 goto out_sysctl;
4224
4225 return 0;
4226
4227 out_sysctl:
4228 xfrm_policy_fini(net);
4229 out_policy:
4230 xfrm_state_fini(net);
4231 out_state:
4232 xfrm_statistics_fini(net);
4233 out_statistics:
4234 return rv;
4235 }
4236
xfrm_net_exit(struct net * net)4237 static void __net_exit xfrm_net_exit(struct net *net)
4238 {
4239 xfrm_sysctl_fini(net);
4240 xfrm_policy_fini(net);
4241 xfrm_state_fini(net);
4242 xfrm_statistics_fini(net);
4243 }
4244
4245 static struct pernet_operations __net_initdata xfrm_net_ops = {
4246 .init = xfrm_net_init,
4247 .exit = xfrm_net_exit,
4248 };
4249
xfrm_init(void)4250 void __init xfrm_init(void)
4251 {
4252 register_pernet_subsys(&xfrm_net_ops);
4253 xfrm_dev_init();
4254 xfrm_input_init();
4255
4256 #ifdef CONFIG_XFRM_ESPINTCP
4257 espintcp_init();
4258 #endif
4259 }
4260
4261 #ifdef CONFIG_AUDITSYSCALL
xfrm_audit_common_policyinfo(struct xfrm_policy * xp,struct audit_buffer * audit_buf)4262 static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp,
4263 struct audit_buffer *audit_buf)
4264 {
4265 struct xfrm_sec_ctx *ctx = xp->security;
4266 struct xfrm_selector *sel = &xp->selector;
4267
4268 if (ctx)
4269 audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
4270 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
4271
4272 switch (sel->family) {
4273 case AF_INET:
4274 audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4);
4275 if (sel->prefixlen_s != 32)
4276 audit_log_format(audit_buf, " src_prefixlen=%d",
4277 sel->prefixlen_s);
4278 audit_log_format(audit_buf, " dst=%pI4", &sel->daddr.a4);
4279 if (sel->prefixlen_d != 32)
4280 audit_log_format(audit_buf, " dst_prefixlen=%d",
4281 sel->prefixlen_d);
4282 break;
4283 case AF_INET6:
4284 audit_log_format(audit_buf, " src=%pI6", sel->saddr.a6);
4285 if (sel->prefixlen_s != 128)
4286 audit_log_format(audit_buf, " src_prefixlen=%d",
4287 sel->prefixlen_s);
4288 audit_log_format(audit_buf, " dst=%pI6", sel->daddr.a6);
4289 if (sel->prefixlen_d != 128)
4290 audit_log_format(audit_buf, " dst_prefixlen=%d",
4291 sel->prefixlen_d);
4292 break;
4293 }
4294 }
4295
xfrm_audit_policy_add(struct xfrm_policy * xp,int result,bool task_valid)4296 void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid)
4297 {
4298 struct audit_buffer *audit_buf;
4299
4300 audit_buf = xfrm_audit_start("SPD-add");
4301 if (audit_buf == NULL)
4302 return;
4303 xfrm_audit_helper_usrinfo(task_valid, audit_buf);
4304 audit_log_format(audit_buf, " res=%u", result);
4305 xfrm_audit_common_policyinfo(xp, audit_buf);
4306 audit_log_end(audit_buf);
4307 }
4308 EXPORT_SYMBOL_GPL(xfrm_audit_policy_add);
4309
xfrm_audit_policy_delete(struct xfrm_policy * xp,int result,bool task_valid)4310 void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
4311 bool task_valid)
4312 {
4313 struct audit_buffer *audit_buf;
4314
4315 audit_buf = xfrm_audit_start("SPD-delete");
4316 if (audit_buf == NULL)
4317 return;
4318 xfrm_audit_helper_usrinfo(task_valid, audit_buf);
4319 audit_log_format(audit_buf, " res=%u", result);
4320 xfrm_audit_common_policyinfo(xp, audit_buf);
4321 audit_log_end(audit_buf);
4322 }
4323 EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete);
4324 #endif
4325
4326 #ifdef CONFIG_XFRM_MIGRATE
xfrm_migrate_selector_match(const struct xfrm_selector * sel_cmp,const struct xfrm_selector * sel_tgt)4327 static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp,
4328 const struct xfrm_selector *sel_tgt)
4329 {
4330 if (sel_cmp->proto == IPSEC_ULPROTO_ANY) {
4331 if (sel_tgt->family == sel_cmp->family &&
4332 xfrm_addr_equal(&sel_tgt->daddr, &sel_cmp->daddr,
4333 sel_cmp->family) &&
4334 xfrm_addr_equal(&sel_tgt->saddr, &sel_cmp->saddr,
4335 sel_cmp->family) &&
4336 sel_tgt->prefixlen_d == sel_cmp->prefixlen_d &&
4337 sel_tgt->prefixlen_s == sel_cmp->prefixlen_s) {
4338 return true;
4339 }
4340 } else {
4341 if (memcmp(sel_tgt, sel_cmp, sizeof(*sel_tgt)) == 0) {
4342 return true;
4343 }
4344 }
4345 return false;
4346 }
4347
xfrm_migrate_policy_find(const struct xfrm_selector * sel,u8 dir,u8 type,struct net * net,u32 if_id)4348 static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
4349 u8 dir, u8 type, struct net *net, u32 if_id)
4350 {
4351 struct xfrm_policy *pol, *ret = NULL;
4352 struct hlist_head *chain;
4353 u32 priority = ~0U;
4354
4355 spin_lock_bh(&net->xfrm.xfrm_policy_lock);
4356 chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
4357 hlist_for_each_entry(pol, chain, bydst) {
4358 if ((if_id == 0 || pol->if_id == if_id) &&
4359 xfrm_migrate_selector_match(sel, &pol->selector) &&
4360 pol->type == type) {
4361 ret = pol;
4362 priority = ret->priority;
4363 break;
4364 }
4365 }
4366 chain = &net->xfrm.policy_inexact[dir];
4367 hlist_for_each_entry(pol, chain, bydst_inexact_list) {
4368 if ((pol->priority >= priority) && ret)
4369 break;
4370
4371 if ((if_id == 0 || pol->if_id == if_id) &&
4372 xfrm_migrate_selector_match(sel, &pol->selector) &&
4373 pol->type == type) {
4374 ret = pol;
4375 break;
4376 }
4377 }
4378
4379 xfrm_pol_hold(ret);
4380
4381 spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
4382
4383 return ret;
4384 }
4385
migrate_tmpl_match(const struct xfrm_migrate * m,const struct xfrm_tmpl * t)4386 static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tmpl *t)
4387 {
4388 int match = 0;
4389
4390 if (t->mode == m->mode && t->id.proto == m->proto &&
4391 (m->reqid == 0 || t->reqid == m->reqid)) {
4392 switch (t->mode) {
4393 case XFRM_MODE_TUNNEL:
4394 case XFRM_MODE_BEET:
4395 if (xfrm_addr_equal(&t->id.daddr, &m->old_daddr,
4396 m->old_family) &&
4397 xfrm_addr_equal(&t->saddr, &m->old_saddr,
4398 m->old_family)) {
4399 match = 1;
4400 }
4401 break;
4402 case XFRM_MODE_TRANSPORT:
4403 /* in case of transport mode, template does not store
4404 any IP addresses, hence we just compare mode and
4405 protocol */
4406 match = 1;
4407 break;
4408 default:
4409 break;
4410 }
4411 }
4412 return match;
4413 }
4414
4415 /* update endpoint address(es) of template(s) */
xfrm_policy_migrate(struct xfrm_policy * pol,struct xfrm_migrate * m,int num_migrate,struct netlink_ext_ack * extack)4416 static int xfrm_policy_migrate(struct xfrm_policy *pol,
4417 struct xfrm_migrate *m, int num_migrate,
4418 struct netlink_ext_ack *extack)
4419 {
4420 struct xfrm_migrate *mp;
4421 int i, j, n = 0;
4422
4423 write_lock_bh(&pol->lock);
4424 if (unlikely(pol->walk.dead)) {
4425 /* target policy has been deleted */
4426 NL_SET_ERR_MSG(extack, "Target policy not found");
4427 write_unlock_bh(&pol->lock);
4428 return -ENOENT;
4429 }
4430
4431 for (i = 0; i < pol->xfrm_nr; i++) {
4432 for (j = 0, mp = m; j < num_migrate; j++, mp++) {
4433 if (!migrate_tmpl_match(mp, &pol->xfrm_vec[i]))
4434 continue;
4435 n++;
4436 if (pol->xfrm_vec[i].mode != XFRM_MODE_TUNNEL &&
4437 pol->xfrm_vec[i].mode != XFRM_MODE_BEET)
4438 continue;
4439 /* update endpoints */
4440 memcpy(&pol->xfrm_vec[i].id.daddr, &mp->new_daddr,
4441 sizeof(pol->xfrm_vec[i].id.daddr));
4442 memcpy(&pol->xfrm_vec[i].saddr, &mp->new_saddr,
4443 sizeof(pol->xfrm_vec[i].saddr));
4444 pol->xfrm_vec[i].encap_family = mp->new_family;
4445 /* flush bundles */
4446 atomic_inc(&pol->genid);
4447 }
4448 }
4449
4450 write_unlock_bh(&pol->lock);
4451
4452 if (!n)
4453 return -ENODATA;
4454
4455 return 0;
4456 }
4457
xfrm_migrate_check(const struct xfrm_migrate * m,int num_migrate,struct netlink_ext_ack * extack)4458 static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate,
4459 struct netlink_ext_ack *extack)
4460 {
4461 int i, j;
4462
4463 if (num_migrate < 1 || num_migrate > XFRM_MAX_DEPTH) {
4464 NL_SET_ERR_MSG(extack, "Invalid number of SAs to migrate, must be 0 < num <= XFRM_MAX_DEPTH (6)");
4465 return -EINVAL;
4466 }
4467
4468 for (i = 0; i < num_migrate; i++) {
4469 if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) ||
4470 xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) {
4471 NL_SET_ERR_MSG(extack, "Addresses in the MIGRATE attribute's list cannot be null");
4472 return -EINVAL;
4473 }
4474
4475 /* check if there is any duplicated entry */
4476 for (j = i + 1; j < num_migrate; j++) {
4477 if (!memcmp(&m[i].old_daddr, &m[j].old_daddr,
4478 sizeof(m[i].old_daddr)) &&
4479 !memcmp(&m[i].old_saddr, &m[j].old_saddr,
4480 sizeof(m[i].old_saddr)) &&
4481 m[i].proto == m[j].proto &&
4482 m[i].mode == m[j].mode &&
4483 m[i].reqid == m[j].reqid &&
4484 m[i].old_family == m[j].old_family) {
4485 NL_SET_ERR_MSG(extack, "Entries in the MIGRATE attribute's list must be unique");
4486 return -EINVAL;
4487 }
4488 }
4489 }
4490
4491 return 0;
4492 }
4493
xfrm_migrate(const struct xfrm_selector * sel,u8 dir,u8 type,struct xfrm_migrate * m,int num_migrate,struct xfrm_kmaddress * k,struct net * net,struct xfrm_encap_tmpl * encap,u32 if_id,struct netlink_ext_ack * extack)4494 int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
4495 struct xfrm_migrate *m, int num_migrate,
4496 struct xfrm_kmaddress *k, struct net *net,
4497 struct xfrm_encap_tmpl *encap, u32 if_id,
4498 struct netlink_ext_ack *extack)
4499 {
4500 int i, err, nx_cur = 0, nx_new = 0;
4501 struct xfrm_policy *pol = NULL;
4502 struct xfrm_state *x, *xc;
4503 struct xfrm_state *x_cur[XFRM_MAX_DEPTH];
4504 struct xfrm_state *x_new[XFRM_MAX_DEPTH];
4505 struct xfrm_migrate *mp;
4506
4507 /* Stage 0 - sanity checks */
4508 err = xfrm_migrate_check(m, num_migrate, extack);
4509 if (err < 0)
4510 goto out;
4511
4512 if (dir >= XFRM_POLICY_MAX) {
4513 NL_SET_ERR_MSG(extack, "Invalid policy direction");
4514 err = -EINVAL;
4515 goto out;
4516 }
4517
4518 /* Stage 1 - find policy */
4519 pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id);
4520 if (!pol) {
4521 NL_SET_ERR_MSG(extack, "Target policy not found");
4522 err = -ENOENT;
4523 goto out;
4524 }
4525
4526 /* Stage 2 - find and update state(s) */
4527 for (i = 0, mp = m; i < num_migrate; i++, mp++) {
4528 if ((x = xfrm_migrate_state_find(mp, net, if_id))) {
4529 x_cur[nx_cur] = x;
4530 nx_cur++;
4531 xc = xfrm_state_migrate(x, mp, encap);
4532 if (xc) {
4533 x_new[nx_new] = xc;
4534 nx_new++;
4535 } else {
4536 err = -ENODATA;
4537 goto restore_state;
4538 }
4539 }
4540 }
4541
4542 /* Stage 3 - update policy */
4543 err = xfrm_policy_migrate(pol, m, num_migrate, extack);
4544 if (err < 0)
4545 goto restore_state;
4546
4547 /* Stage 4 - delete old state(s) */
4548 if (nx_cur) {
4549 xfrm_states_put(x_cur, nx_cur);
4550 xfrm_states_delete(x_cur, nx_cur);
4551 }
4552
4553 /* Stage 5 - announce */
4554 km_migrate(sel, dir, type, m, num_migrate, k, encap);
4555
4556 xfrm_pol_put(pol);
4557
4558 return 0;
4559 out:
4560 return err;
4561
4562 restore_state:
4563 if (pol)
4564 xfrm_pol_put(pol);
4565 if (nx_cur)
4566 xfrm_states_put(x_cur, nx_cur);
4567 if (nx_new)
4568 xfrm_states_delete(x_new, nx_new);
4569
4570 return err;
4571 }
4572 EXPORT_SYMBOL(xfrm_migrate);
4573 #endif
4574