aboutsummaryrefslogblamecommitdiffstats
path: root/main/linux-grsec/0015-xfrm-cache-bundles-instead-of-policies-for-outgoing-.patch
blob: 0d066c84d9d81884e93a4474a4388fb9a183d136 (plain) (tree)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068











































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































                                                                                                                     
From f89d21648e6dc06db2aeabc8926c270894c41446 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timo=20Ter=C3=A4s?= <timo.teras@iki.fi>
Date: Wed, 7 Apr 2010 00:30:05 +0000
Subject: [PATCH 15/18] xfrm: cache bundles instead of policies for outgoing flows

__xfrm_lookup() is called for each packet transmitted out of
system. The xfrm_find_bundle() does a linear search which can
kill system performance depending on how many bundles are
required per policy.

This modifies __xfrm_lookup() to store bundles directly in
the flow cache. If we did not get a hit, we just create a new
bundle instead of doing slow search. This means that we can now
get multiple xfrm_dst's for same flow (on per-cpu basis).

Signed-off-by: Timo Teras <timo.teras@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
(backported from commit 80c802f3073e84c956846e921e8a0b02dfa3755f)
---
 include/net/xfrm.h      |   10 +-
 net/ipv4/xfrm4_policy.c |   22 --
 net/ipv6/xfrm6_policy.c |   31 --
 net/xfrm/xfrm_policy.c  |  710 +++++++++++++++++++++++++----------------------
 4 files changed, 383 insertions(+), 390 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 6023a48..d51ef61 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -266,7 +266,6 @@ struct xfrm_policy_afinfo {
 					       xfrm_address_t *saddr,
 					       xfrm_address_t *daddr);
 	int			(*get_saddr)(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr);
-	struct dst_entry	*(*find_bundle)(struct flowi *fl, struct xfrm_policy *policy);
 	void			(*decode_session)(struct sk_buff *skb,
 						  struct flowi *fl,
 						  int reverse);
@@ -485,12 +484,12 @@ struct xfrm_policy
 	struct timer_list	timer;
 
 	struct flow_cache_object flo;
+	atomic_t		genid;
 	u32			priority;
 	u32			index;
 	struct xfrm_selector	selector;
 	struct xfrm_lifetime_cfg lft;
 	struct xfrm_lifetime_cur curlft;
-	struct dst_entry       *bundles;
 	struct xfrm_policy_walk_entry walk;
 	u8			type;
 	u8			action;
@@ -883,11 +882,15 @@ struct xfrm_dst
 		struct rt6_info		rt6;
 	} u;
 	struct dst_entry *route;
+	struct flow_cache_object flo;
+	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
+	int num_pols, num_xfrms;
 #ifdef CONFIG_XFRM_SUB_POLICY
 	struct flowi *origin;
 	struct xfrm_selector *partner;
 #endif
-	u32 genid;
+	u32 xfrm_genid;
+	u32 policy_genid;
 	u32 route_mtu_cached;
 	u32 child_mtu_cached;
 	u32 route_cookie;
@@ -897,6 +900,7 @@ struct xfrm_dst
 #ifdef CONFIG_XFRM
 static inline void xfrm_dst_destroy(struct xfrm_dst *xdst)
 {
+	xfrm_pols_put(xdst->pols, xdst->num_pols);
 	dst_release(xdst->route);
 	if (likely(xdst->u.dst.xfrm))
 		xfrm_state_put(xdst->u.dst.xfrm);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 7009886..651a3e7 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -60,27 +60,6 @@ static int xfrm4_get_saddr(struct net *net,
 	return 0;
 }
 
-static struct dst_entry *
-__xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
-{
-	struct dst_entry *dst;
-
-	read_lock_bh(&policy->lock);
-	for (dst = policy->bundles; dst; dst = dst->next) {
-		struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
-		if (xdst->u.rt.fl.oif == fl->oif &&	/*XXX*/
-		    xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
-		    xdst->u.rt.fl.fl4_src == fl->fl4_src &&
-		    xdst->u.rt.fl.fl4_tos == fl->fl4_tos &&
-		    xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) {
-			dst_clone(dst);
-			break;
-		}
-	}
-	read_unlock_bh(&policy->lock);
-	return dst;
-}
-
 static int xfrm4_get_tos(struct flowi *fl)
 {
 	return fl->fl4_tos;
@@ -258,7 +237,6 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.dst_ops =		&xfrm4_dst_ops,
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
-	.find_bundle = 		__xfrm4_find_bundle,
 	.decode_session =	_decode_session4,
 	.get_tos =		xfrm4_get_tos,
 	.init_path =		xfrm4_init_path,
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 3f89ab7..fb2a5b7 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -68,36 +68,6 @@ static int xfrm6_get_saddr(struct net *net,
 	return 0;
 }
 
-static struct dst_entry *
-__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
-{
-	struct dst_entry *dst;
-
-	/* Still not clear if we should set fl->fl6_{src,dst}... */
-	read_lock_bh(&policy->lock);
-	for (dst = policy->bundles; dst; dst = dst->next) {
-		struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
-		struct in6_addr fl_dst_prefix, fl_src_prefix;
-
-		ipv6_addr_prefix(&fl_dst_prefix,
-				 &fl->fl6_dst,
-				 xdst->u.rt6.rt6i_dst.plen);
-		ipv6_addr_prefix(&fl_src_prefix,
-				 &fl->fl6_src,
-				 xdst->u.rt6.rt6i_src.plen);
-		if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) &&
-		    ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) &&
-		    xfrm_bundle_ok(policy, xdst, fl, AF_INET6,
-				   (xdst->u.rt6.rt6i_dst.plen != 128 ||
-				    xdst->u.rt6.rt6i_src.plen != 128))) {
-			dst_clone(dst);
-			break;
-		}
-	}
-	read_unlock_bh(&policy->lock);
-	return dst;
-}
-
 static int xfrm6_get_tos(struct flowi *fl)
 {
 	return 0;
@@ -290,7 +260,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.dst_ops =		&xfrm6_dst_ops,
 	.dst_lookup =		xfrm6_dst_lookup,
 	.get_saddr = 		xfrm6_get_saddr,
-	.find_bundle =		__xfrm6_find_bundle,
 	.decode_session =	_decode_session6,
 	.get_tos =		xfrm6_get_tos,
 	.init_path =		xfrm6_init_path,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d1eb2b5..0379d82 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -37,6 +37,8 @@
 DEFINE_MUTEX(xfrm_cfg_mutex);
 EXPORT_SYMBOL(xfrm_cfg_mutex);
 
+static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock);
+static struct dst_entry *xfrm_policy_sk_bundles;
 static DEFINE_RWLOCK(xfrm_policy_lock);
 
 static DEFINE_RWLOCK(xfrm_policy_afinfo_lock);
@@ -50,6 +52,7 @@ static DEFINE_SPINLOCK(xfrm_policy_gc_lock);
 static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family);
 static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo);
 static void xfrm_init_pmtu(struct dst_entry *dst);
+static int stale_bundle(struct dst_entry *dst);
 
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
@@ -277,8 +280,6 @@ void xfrm_policy_destroy(struct xfrm_policy *policy)
 {
 	BUG_ON(!policy->walk.dead);
 
-	BUG_ON(policy->bundles);
-
 	if (del_timer(&policy->timer))
 		BUG();
 
@@ -289,12 +290,7 @@ EXPORT_SYMBOL(xfrm_policy_destroy);
 
 static void xfrm_policy_gc_kill(struct xfrm_policy *policy)
 {
-	struct dst_entry *dst;
-
-	while ((dst = policy->bundles) != NULL) {
-		policy->bundles = dst->next;
-		dst_free(dst);
-	}
+	atomic_inc(&policy->genid);
 
 	if (del_timer(&policy->timer))
 		atomic_dec(&policy->refcnt);
@@ -572,7 +568,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	struct xfrm_policy *delpol;
 	struct hlist_head *chain;
 	struct hlist_node *entry, *newpos;
-	struct dst_entry *gc_list;
 
 	write_lock_bh(&xfrm_policy_lock);
 	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
@@ -620,34 +615,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	else if (xfrm_bydst_should_resize(net, dir, NULL))
 		schedule_work(&net->xfrm.policy_hash_work);
 
-	read_lock_bh(&xfrm_policy_lock);
-	gc_list = NULL;
-	entry = &policy->bydst;
-	hlist_for_each_entry_continue(policy, entry, bydst) {
-		struct dst_entry *dst;
-
-		write_lock(&policy->lock);
-		dst = policy->bundles;
-		if (dst) {
-			struct dst_entry *tail = dst;
-			while (tail->next)
-				tail = tail->next;
-			tail->next = gc_list;
-			gc_list = dst;
-
-			policy->bundles = NULL;
-		}
-		write_unlock(&policy->lock);
-	}
-	read_unlock_bh(&xfrm_policy_lock);
-
-	while (gc_list) {
-		struct dst_entry *dst = gc_list;
-
-		gc_list = dst->next;
-		dst_free(dst);
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL(xfrm_policy_insert);
@@ -990,6 +957,19 @@ fail:
 	return ret;
 }
 
+static struct xfrm_policy *
+__xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir)
+{
+#ifdef CONFIG_XFRM_SUB_POLICY
+	struct xfrm_policy *pol;
+
+	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir);
+	if (pol != NULL)
+		return pol;
+#endif
+	return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir);
+}
+
 static struct flow_cache_object *
 xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family,
 		   u8 dir, struct flow_cache_object *old_obj, void *ctx)
@@ -999,21 +979,10 @@ xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family,
 	if (old_obj)
 		xfrm_pol_put(container_of(old_obj, struct xfrm_policy, flo));
 
-#ifdef CONFIG_XFRM_SUB_POLICY
-	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir);
-	if (IS_ERR(pol))
+	pol = __xfrm_policy_lookup(net, fl, family, dir);
+	if (pol == NULL || IS_ERR(pol))
 		return ERR_CAST(pol);
-	if (pol)
-		goto found;
-#endif
-	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir);
-	if (IS_ERR(pol))
-		return ERR_CAST(pol);
-	if (pol)
-		goto found;
-	return NULL;
 
-found:
 	/* Resolver returns two references:
 	 * one for cache and one for caller of flow_cache_lookup() */
 	xfrm_pol_hold(pol);
@@ -1299,18 +1268,6 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, struct flowi *fl,
  * still valid.
  */
 
-static struct dst_entry *
-xfrm_find_bundle(struct flowi *fl, struct xfrm_policy *policy, unsigned short family)
-{
-	struct dst_entry *x;
-	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
-	if (unlikely(afinfo == NULL))
-		return ERR_PTR(-EINVAL);
-	x = afinfo->find_bundle(fl, policy);
-	xfrm_policy_put_afinfo(afinfo);
-	return x;
-}
-
 static inline int xfrm_get_tos(struct flowi *fl, int family)
 {
 	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
@@ -1326,6 +1283,54 @@ static inline int xfrm_get_tos(struct flowi *fl, int family)
 	return tos;
 }
 
+static struct flow_cache_object *xfrm_bundle_flo_get(struct flow_cache_object *flo)
+{
+	struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
+	struct dst_entry *dst = &xdst->u.dst;
+
+	if (xdst->route == NULL) {
+		/* Dummy bundle - if it has xfrms we were not
+		 * able to build bundle as template resolution failed.
+		 * It means we need to try again resolving. */
+		if (xdst->num_xfrms > 0)
+			return NULL;
+	} else {
+		/* Real bundle */
+		if (stale_bundle(dst))
+			return NULL;
+	}
+
+	dst_hold(dst);
+	return flo;
+}
+
+static int xfrm_bundle_flo_check(struct flow_cache_object *flo)
+{
+	struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
+	struct dst_entry *dst = &xdst->u.dst;
+
+	if (!xdst->route)
+		return 0;
+	if (stale_bundle(dst))
+		return 0;
+
+	return 1;
+}
+
+static void xfrm_bundle_flo_delete(struct flow_cache_object *flo)
+{
+	struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
+	struct dst_entry *dst = &xdst->u.dst;
+
+	dst_free(dst);
+}
+
+static const struct flow_cache_ops xfrm_bundle_fc_ops = {
+	.get = xfrm_bundle_flo_get,
+	.check = xfrm_bundle_flo_check,
+	.delete = xfrm_bundle_flo_delete,
+};
+
 static inline struct xfrm_dst *xfrm_alloc_dst(int family)
 {
 	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
@@ -1338,6 +1343,8 @@ static inline struct xfrm_dst *xfrm_alloc_dst(int family)
 
 	xfrm_policy_put_afinfo(afinfo);
 
+	xdst->flo.ops = &xfrm_bundle_fc_ops;
+
 	return xdst;
 }
 
@@ -1375,6 +1382,7 @@ static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	return err;
 }
 
+
 /* Allocate chain of dst_entry's, attach known xfrm's, calculate
  * all the metrics... Shortly, bundle a bundle.
  */
@@ -1437,7 +1445,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 			dst_hold(dst);
 
 		dst1->xfrm = xfrm[i];
-		xdst->genid = xfrm[i]->genid;
+		xdst->xfrm_genid = xfrm[i]->genid;
 
 		dst1->obsolete = -1;
 		dst1->flags |= DST_HOST;
@@ -1530,7 +1538,186 @@ xfrm_dst_update_origin(struct dst_entry *dst, struct flowi *fl)
 #endif
 }
 
-static int stale_bundle(struct dst_entry *dst);
+static int xfrm_expand_policies(struct flowi *fl, u16 family,
+				struct xfrm_policy **pols,
+				int *num_pols, int *num_xfrms)
+{
+	int i;
+
+	if (*num_pols == 0 || !pols[0]) {
+		*num_pols = 0;
+		*num_xfrms = 0;
+		return 0;
+	}
+	if (IS_ERR(pols[0]))
+		return PTR_ERR(pols[0]);
+
+	*num_xfrms = pols[0]->xfrm_nr;
+
+#ifdef CONFIG_XFRM_SUB_POLICY
+	if (pols[0] && pols[0]->action == XFRM_POLICY_ALLOW &&
+	    pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
+		pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]),
+						    XFRM_POLICY_TYPE_MAIN,
+						    fl, family,
+						    XFRM_POLICY_OUT);
+		if (pols[1]) {
+			if (IS_ERR(pols[1])) {
+				xfrm_pols_put(pols, *num_pols);
+				return PTR_ERR(pols[1]);
+			}
+			(*num_pols) ++;
+			(*num_xfrms) += pols[1]->xfrm_nr;
+		}
+	}
+#endif
+	for (i = 0; i < *num_pols; i++) {
+		if (pols[i]->action != XFRM_POLICY_ALLOW) {
+			*num_xfrms = -1;
+			break;
+		}
+	}
+
+	return 0;
+
+}
+
+static struct xfrm_dst *
+xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
+			       struct flowi *fl, u16 family,
+			       struct dst_entry *dst_orig)
+{
+	struct net *net = xp_net(pols[0]);
+	struct xfrm_state *xfrm[XFRM_MAX_DEPTH];
+	struct dst_entry *dst;
+	struct xfrm_dst *xdst;
+	int err;
+
+	/* Try to instantiate a bundle */
+	err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family);
+	if (err < 0) {
+		if (err != -EAGAIN)
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+		return ERR_PTR(err);
+	}
+
+	dst = xfrm_bundle_create(pols[0], xfrm, err, fl, dst_orig);
+	if (IS_ERR(dst)) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR);
+		return ERR_CAST(dst);
+	}
+
+	xdst = (struct xfrm_dst *)dst;
+	xdst->num_xfrms = err;
+	if (num_pols > 1)
+		err = xfrm_dst_update_parent(dst, &pols[1]->selector);
+	else
+		err = xfrm_dst_update_origin(dst, fl);
+	if (unlikely(err)) {
+		dst_free(dst);
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
+		return ERR_PTR(err);
+	}
+
+	xdst->num_pols = num_pols;
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	xdst->policy_genid = atomic_read(&pols[0]->genid);
+
+	return xdst;
+}
+
+static struct flow_cache_object *
+xfrm_bundle_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir,
+		   struct flow_cache_object *oldflo, void *ctx)
+{
+	struct dst_entry *dst_orig = (struct dst_entry *)ctx;
+	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
+	struct xfrm_dst *xdst, *new_xdst;
+	int num_pols = 0, num_xfrms = 0, i, err, pol_dead;
+
+	/* Check if the policies from old bundle are usable */
+	xdst = NULL;
+	if (oldflo) {
+		xdst = container_of(oldflo, struct xfrm_dst, flo);
+		num_pols = xdst->num_pols;
+		num_xfrms = xdst->num_xfrms;
+		pol_dead = 0;
+		for (i = 0; i < num_pols; i++) {
+			pols[i] = xdst->pols[i];
+			pol_dead |= pols[i]->walk.dead;
+		}
+		if (pol_dead) {
+			dst_free(&xdst->u.dst);
+			xdst = NULL;
+			num_pols = 0;
+			num_xfrms = 0;
+			oldflo = NULL;
+		}
+	}
+
+	/* Resolve policies to use if we couldn't get them from
+	 * previous cache entry */
+	if (xdst == NULL) {
+		num_pols = 1;
+		pols[0] = __xfrm_policy_lookup(net, fl, family, dir);
+		err = xfrm_expand_policies(fl, family, pols,
+					   &num_pols, &num_xfrms);
+		if (err < 0)
+			goto inc_error;
+		if (num_pols == 0)
+			return NULL;
+		if (num_xfrms <= 0)
+			goto make_dummy_bundle;
+	}
+
+	new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig);
+	if (IS_ERR(new_xdst)) {
+		err = PTR_ERR(new_xdst);
+		if (err != -EAGAIN)
+			goto error;
+		if (oldflo == NULL)
+			goto make_dummy_bundle;
+		dst_hold(&xdst->u.dst);
+		return oldflo;
+	}
+
+	/* Kill the previous bundle */
+	if (xdst) {
+		/* The policies were stolen for newly generated bundle */
+		xdst->num_pols = 0;
+		dst_free(&xdst->u.dst);
+	}
+
+	/* Flow cache does not have reference, it dst_free()'s,
+	 * but we do need to return one reference for original caller */
+	dst_hold(&new_xdst->u.dst);
+	return &new_xdst->flo;
+
+make_dummy_bundle:
+	/* We found policies, but there's no bundles to instantiate:
+	 * either because the policy blocks, has no transformations or
+	 * we could not build template (no xfrm_states).*/
+	xdst = xfrm_alloc_dst(family);
+	if (IS_ERR(xdst)) {
+		xfrm_pols_put(pols, num_pols);
+		return ERR_CAST(xdst);
+	}
+	xdst->num_pols = num_pols;
+	xdst->num_xfrms = num_xfrms;
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+
+	dst_hold(&xdst->u.dst);
+	return &xdst->flo;
+
+inc_error:
+	XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+error:
+	if (xdst != NULL)
+		dst_free(&xdst->u.dst);
+	else
+		xfrm_pols_put(pols, num_pols);
+	return ERR_PTR(err);
+}
 
 /* Main function: finds/creates a bundle for given flow.
  *
@@ -1540,248 +1727,152 @@ static int stale_bundle(struct dst_entry *dst);
 int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl,
 		  struct sock *sk, int flags)
 {
-	struct xfrm_policy *policy;
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
-	int npols;
-	int pol_dead;
-	int xfrm_nr;
-	int pi;
-	struct xfrm_state *xfrm[XFRM_MAX_DEPTH];
-	struct dst_entry *dst, *dst_orig = *dst_p;
-	int nx = 0;
-	int err;
-	u32 genid;
-	u16 family;
+	struct flow_cache_object *flo;
+	struct xfrm_dst *xdst;
+	struct dst_entry *dst, *dst_orig = *dst_p, *route;
+	u16 family = dst_orig->ops->family;
 	u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
+	int i, err, num_pols, num_xfrms, drop_pols = 0;
 
 restart:
-	genid = atomic_read(&flow_cache_genid);
-	policy = NULL;
-	for (pi = 0; pi < ARRAY_SIZE(pols); pi++)
-		pols[pi] = NULL;
-	npols = 0;
-	pol_dead = 0;
-	xfrm_nr = 0;
+	dst = NULL;
+	xdst = NULL;
+	route = NULL;
 
 	if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
-		policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
-		err = PTR_ERR(policy);
-		if (IS_ERR(policy)) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+		num_pols = 1;
+		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
+		err = xfrm_expand_policies(fl, family, pols,
+					   &num_pols, &num_xfrms);
+		if (err < 0)
 			goto dropdst;
+
+		if (num_pols) {
+			if (num_xfrms <= 0) {
+				drop_pols = num_pols;
+				goto no_transform;
+			}
+
+			xdst = xfrm_resolve_and_create_bundle(
+					pols, num_pols, fl,
+					family, dst_orig);
+			if (IS_ERR(xdst)) {
+				xfrm_pols_put(pols, num_pols);
+				err = PTR_ERR(xdst);
+				goto dropdst;
+			}
+
+			spin_lock_bh(&xfrm_policy_sk_bundle_lock);
+			xdst->u.dst.next = xfrm_policy_sk_bundles;
+			xfrm_policy_sk_bundles = &xdst->u.dst;
+			spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
+
+			route = xdst->route;
 		}
 	}
 
-	if (!policy) {
-		struct flow_cache_object *flo;
-
+	if (xdst == NULL) {
 		/* To accelerate a bit...  */
 		if ((dst_orig->flags & DST_NOXFRM) ||
 		    !net->xfrm.policy_count[XFRM_POLICY_OUT])
 			goto nopol;
 
-		flo = flow_cache_lookup(net, fl, dst_orig->ops->family,
-					dir, xfrm_policy_lookup, NULL);
-		err = PTR_ERR(flo);
+		flo = flow_cache_lookup(net, fl, family, dir,
+					xfrm_bundle_lookup, dst_orig);
+		if (flo == NULL)
+			goto nopol;
 		if (IS_ERR(flo)) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+			err = PTR_ERR(flo);
 			goto dropdst;
 		}
-		if (flo)
-			policy = container_of(flo, struct xfrm_policy, flo);
-		else
-			policy = NULL;
+		xdst = container_of(flo, struct xfrm_dst, flo);
+
+		num_pols = xdst->num_pols;
+		num_xfrms = xdst->num_xfrms;
+		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols);
+		route = xdst->route;
+	}
+
+	dst = &xdst->u.dst;
+	if (route == NULL && num_xfrms > 0) {
+		/* The only case when xfrm_bundle_lookup() returns a
+		 * bundle with null route, is when the template could
+		 * not be resolved. It means policies are there, but
+		 * bundle could not be created, since we don't yet
+		 * have the xfrm_state's. We need to wait for KM to
+		 * negotiate new SA's or bail out with error.*/
+		if (net->xfrm.sysctl_larval_drop) {
+			/* EREMOTE tells the caller to generate
+			 * a one-shot blackhole route. */
+			dst_release(dst);
+			xfrm_pols_put(pols, num_pols);
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
+			return -EREMOTE;
+		}
+		if (flags & XFRM_LOOKUP_WAIT) {
+			DECLARE_WAITQUEUE(wait, current);
+
+			add_wait_queue(&net->xfrm.km_waitq, &wait);
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule();
+			set_current_state(TASK_RUNNING);
+			remove_wait_queue(&net->xfrm.km_waitq, &wait);
+
+			if (!signal_pending(current)) {
+				dst_release(dst);
+				goto restart;
+			}
+
+			err = -ERESTART;
+		} else
+			err = -EAGAIN;
+
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
+		goto error;
 	}
 
-	if (!policy)
+no_transform:
+	if (num_pols == 0)
 		goto nopol;
 
-	family = dst_orig->ops->family;
-	pols[0] = policy;
-	npols ++;
-	xfrm_nr += pols[0]->xfrm_nr;
-
-	err = -ENOENT;
-	if ((flags & XFRM_LOOKUP_ICMP) && !(policy->flags & XFRM_POLICY_ICMP))
+	if ((flags & XFRM_LOOKUP_ICMP) &&
+	    !(pols[0]->flags & XFRM_POLICY_ICMP)) {
+		err = -ENOENT;
 		goto error;
+	}
 
-	policy->curlft.use_time = get_seconds();
+	for (i = 0; i < num_pols; i++)
+		pols[i]->curlft.use_time = get_seconds();
 
-	switch (policy->action) {
-	default:
-	case XFRM_POLICY_BLOCK:
+	if (num_xfrms < 0) {
 		/* Prohibit the flow */
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK);
 		err = -EPERM;
 		goto error;
-
-	case XFRM_POLICY_ALLOW:
-#ifndef CONFIG_XFRM_SUB_POLICY
-		if (policy->xfrm_nr == 0) {
-			/* Flow passes not transformed. */
-			xfrm_pol_put(policy);
-			return 0;
-		}
-#endif
-
-		/* Try to find matching bundle.
-		 *
-		 * LATER: help from flow cache. It is optional, this
-		 * is required only for output policy.
-		 */
-		dst = xfrm_find_bundle(fl, policy, family);
-		if (IS_ERR(dst)) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
-			err = PTR_ERR(dst);
-			goto error;
-		}
-
-		if (dst)
-			break;
-
-#ifdef CONFIG_XFRM_SUB_POLICY
-		if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
-			pols[1] = xfrm_policy_lookup_bytype(net,
-							    XFRM_POLICY_TYPE_MAIN,
-							    fl, family,
-							    XFRM_POLICY_OUT);
-			if (pols[1]) {
-				if (IS_ERR(pols[1])) {
-					XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
-					err = PTR_ERR(pols[1]);
-					goto error;
-				}
-				if (pols[1]->action == XFRM_POLICY_BLOCK) {
-					XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK);
-					err = -EPERM;
-					goto error;
-				}
-				npols ++;
-				xfrm_nr += pols[1]->xfrm_nr;
-			}
-		}
-
-		/*
-		 * Because neither flowi nor bundle information knows about
-		 * transformation template size. On more than one policy usage
-		 * we can realize whether all of them is bypass or not after
-		 * they are searched. See above not-transformed bypass
-		 * is surrounded by non-sub policy configuration, too.
-		 */
-		if (xfrm_nr == 0) {
-			/* Flow passes not transformed. */
-			xfrm_pols_put(pols, npols);
-			return 0;
-		}
-
-#endif
-		nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family);
-
-		if (unlikely(nx<0)) {
-			err = nx;
-			if (err == -EAGAIN && net->xfrm.sysctl_larval_drop) {
-				/* EREMOTE tells the caller to generate
-				 * a one-shot blackhole route.
-				 */
-				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
-				xfrm_pol_put(policy);
-				return -EREMOTE;
-			}
-			if (err == -EAGAIN && (flags & XFRM_LOOKUP_WAIT)) {
-				DECLARE_WAITQUEUE(wait, current);
-
-				add_wait_queue(&net->xfrm.km_waitq, &wait);
-				set_current_state(TASK_INTERRUPTIBLE);
-				schedule();
-				set_current_state(TASK_RUNNING);
-				remove_wait_queue(&net->xfrm.km_waitq, &wait);
-
-				nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family);
-
-				if (nx == -EAGAIN && signal_pending(current)) {
-					XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
-					err = -ERESTART;
-					goto error;
-				}
-				if (nx == -EAGAIN ||
-				    genid != atomic_read(&flow_cache_genid)) {
-					xfrm_pols_put(pols, npols);
-					goto restart;
-				}
-				err = nx;
-			}
-			if (err < 0) {
-				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
-				goto error;
-			}
-		}
-		if (nx == 0) {
-			/* Flow passes not transformed. */
-			xfrm_pols_put(pols, npols);
-			return 0;
-		}
-
-		dst = xfrm_bundle_create(policy, xfrm, nx, fl, dst_orig);
-		err = PTR_ERR(dst);
-		if (IS_ERR(dst)) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR);
-			goto error;
-		}
-
-		for (pi = 0; pi < npols; pi++)
-			pol_dead |= pols[pi]->walk.dead;
-
-		write_lock_bh(&policy->lock);
-		if (unlikely(pol_dead || stale_bundle(dst))) {
-			/* Wow! While we worked on resolving, this
-			 * policy has gone. Retry. It is not paranoia,
-			 * we just cannot enlist new bundle to dead object.
-			 * We can't enlist stable bundles either.
-			 */
-			write_unlock_bh(&policy->lock);
-			dst_free(dst);
-
-			if (pol_dead)
-				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLDEAD);
-			else
-				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
-			err = -EHOSTUNREACH;
-			goto error;
-		}
-
-		if (npols > 1)
-			err = xfrm_dst_update_parent(dst, &pols[1]->selector);
-		else
-			err = xfrm_dst_update_origin(dst, fl);
-		if (unlikely(err)) {
-			write_unlock_bh(&policy->lock);
-			dst_free(dst);
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
-			goto error;
-		}
-
-		dst->next = policy->bundles;
-		policy->bundles = dst;
-		dst_hold(dst);
-		write_unlock_bh(&policy->lock);
+	} else if (num_xfrms > 0) {
+		/* Flow transformed */
+		*dst_p = dst;
+		dst_release(dst_orig);
+	} else {
+		/* Flow passes untransformed */
+		dst_release(dst);
 	}
-	*dst_p = dst;
-	dst_release(dst_orig);
-	xfrm_pols_put(pols, npols);
+ok:
+	xfrm_pols_put(pols, drop_pols);
 	return 0;
 
+nopol:
+	if (!(flags & XFRM_LOOKUP_ICMP))
+		goto ok;
+	err = -ENOENT;
 error:
-	xfrm_pols_put(pols, npols);
+	dst_release(dst);
 dropdst:
 	dst_release(dst_orig);
 	*dst_p = NULL;
+	xfrm_pols_put(pols, drop_pols);
 	return err;
-
-nopol:
-	err = -ENOENT;
-	if (flags & XFRM_LOOKUP_ICMP)
-		goto dropdst;
-	return 0;
 }
 EXPORT_SYMBOL(__xfrm_lookup);
 
@@ -2134,71 +2225,24 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst)
 	return dst;
 }
 
-static void prune_one_bundle(struct xfrm_policy *pol, int (*func)(struct dst_entry *), struct dst_entry **gc_list_p)
-{
-	struct dst_entry *dst, **dstp;
-
-	write_lock(&pol->lock);
-	dstp = &pol->bundles;
-	while ((dst=*dstp) != NULL) {
-		if (func(dst)) {
-			*dstp = dst->next;
-			dst->next = *gc_list_p;
-			*gc_list_p = dst;
-		} else {
-			dstp = &dst->next;
-		}
-	}
-	write_unlock(&pol->lock);
-}
-
-static void xfrm_prune_bundles(struct net *net, int (*func)(struct dst_entry *))
+static void __xfrm_garbage_collect(struct net *net)
 {
-	struct dst_entry *gc_list = NULL;
-	int dir;
+	struct dst_entry *head, *next;
 
-	read_lock_bh(&xfrm_policy_lock);
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
-		struct xfrm_policy *pol;
-		struct hlist_node *entry;
-		struct hlist_head *table;
-		int i;
+	flow_cache_flush();
 
-		hlist_for_each_entry(pol, entry,
-				     &net->xfrm.policy_inexact[dir], bydst)
-			prune_one_bundle(pol, func, &gc_list);
+	spin_lock_bh(&xfrm_policy_sk_bundle_lock);
+	head = xfrm_policy_sk_bundles;
+	xfrm_policy_sk_bundles = NULL;
+	spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
 
-		table = net->xfrm.policy_bydst[dir].table;
-		for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) {
-			hlist_for_each_entry(pol, entry, table + i, bydst)
-				prune_one_bundle(pol, func, &gc_list);
-		}
-	}
-	read_unlock_bh(&xfrm_policy_lock);
-
-	while (gc_list) {
-		struct dst_entry *dst = gc_list;
-		gc_list = dst->next;
-		dst_free(dst);
+	while (head) {
+		next = head->next;
+		dst_free(head);
+		head = next;
 	}
 }
 
-static int unused_bundle(struct dst_entry *dst)
-{
-	return !atomic_read(&dst->__refcnt);
-}
-
-static void __xfrm_garbage_collect(struct net *net)
-{
-	xfrm_prune_bundles(net, unused_bundle);
-}
-
-static int xfrm_flush_bundles(struct net *net)
-{
-	xfrm_prune_bundles(net, stale_bundle);
-	return 0;
-}
-
 static void xfrm_init_pmtu(struct dst_entry *dst)
 {
 	do {
@@ -2256,7 +2300,9 @@ int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first,
 			return 0;
 		if (dst->xfrm->km.state != XFRM_STATE_VALID)
 			return 0;
-		if (xdst->genid != dst->xfrm->genid)
+		if (xdst->xfrm_genid != dst->xfrm->genid)
+			return 0;
+		if (xdst->policy_genid != atomic_read(&xdst->pols[0]->genid))
 			return 0;
 
 		if (strict && fl &&
@@ -2383,7 +2429,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void
 
 	switch (event) {
 	case NETDEV_DOWN:
-		xfrm_flush_bundles(dev_net(dev));
+		__xfrm_garbage_collect(dev_net(dev));
 	}
 	return NOTIFY_DONE;
 }
@@ -2714,7 +2760,6 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol,
 			       struct xfrm_migrate *m, int num_migrate)
 {
 	struct xfrm_migrate *mp;
-	struct dst_entry *dst;
 	int i, j, n = 0;
 
 	write_lock_bh(&pol->lock);
@@ -2739,10 +2784,7 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol,
 			       sizeof(pol->xfrm_vec[i].saddr));
 			pol->xfrm_vec[i].encap_family = mp->new_family;
 			/* flush bundles */
-			while ((dst = pol->bundles) != NULL) {
-				pol->bundles = dst->next;
-				dst_free(dst);
-			}
+			atomic_inc(&pol->genid);
 		}
 	}
 
-- 
1.7.0.2