aboutsummaryrefslogtreecommitdiffstats
path: root/lib/locking-selftest.c
blob: 507a22fab7380c120bcf45cb683051c2e4adb0da (plain) (blame)
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
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
/*
 * lib/locking-selftest.c
 *
 * Testsuite for various locking APIs: spinlocks, rwlocks,
 * mutexes and rw-semaphores.
 *
 * It is checking both false positives and false negatives.
 *
 * Started by Ingo Molnar:
 *
 *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 */
#include <linux/rwsem.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/lockdep.h>
#include <linux/spinlock.h>
#include <linux/kallsyms.h>
#include <linux/interrupt.h>
#include <linux/debug_locks.h>
#include <linux/irqflags.h>

/*
 * Change this to 1 if you want to see the failure printouts:
 */
static unsigned int debug_locks_verbose;

static int __init setup_debug_locks_verbose(char *str)
{
	get_option(&str, &debug_locks_verbose);

	return 1;
}

__setup("debug_locks_verbose=", setup_debug_locks_verbose);

#define FAILURE		0
#define SUCCESS		1

#define LOCKTYPE_SPIN	0x1
#define LOCKTYPE_RWLOCK	0x2
#define LOCKTYPE_MUTEX	0x4
#define LOCKTYPE_RWSEM	0x8

/*
 * Normal standalone locks, for the circular and irq-context
 * dependency tests:
 */
static DEFINE_SPINLOCK(lock_A);
static DEFINE_SPINLOCK(lock_B);
static DEFINE_SPINLOCK(lock_C);
static DEFINE_SPINLOCK(lock_D);

static DEFINE_RWLOCK(rwlock_A);
static DEFINE_RWLOCK(rwlock_B);
static DEFINE_RWLOCK(rwlock_C);
static DEFINE_RWLOCK(rwlock_D);

static DEFINE_MUTEX(mutex_A);
static DEFINE_MUTEX(mutex_B);
static DEFINE_MUTEX(mutex_C);
static DEFINE_MUTEX(mutex_D);

static DECLARE_RWSEM(rwsem_A);
static DECLARE_RWSEM(rwsem_B);
static DECLARE_RWSEM(rwsem_C);
static DECLARE_RWSEM(rwsem_D);

/*
 * Locks that we initialize dynamically as well so that
 * e.g. X1 and X2 becomes two instances of the same class,
 * but X* and Y* are different classes. We do this so that
 * we do not trigger a real lockup:
 */
static DEFINE_SPINLOCK(lock_X1);
static DEFINE_SPINLOCK(lock_X2);
static DEFINE_SPINLOCK(lock_Y1);
static DEFINE_SPINLOCK(lock_Y2);
static DEFINE_SPINLOCK(lock_Z1);
static DEFINE_SPINLOCK(lock_Z2);

static DEFINE_RWLOCK(rwlock_X1);
static DEFINE_RWLOCK(rwlock_X2);
static DEFINE_RWLOCK(rwlock_Y1);
static DEFINE_RWLOCK(rwlock_Y2);
static DEFINE_RWLOCK(rwlock_Z1);
static DEFINE_RWLOCK(rwlock_Z2);

static DEFINE_MUTEX(mutex_X1);
static DEFINE_MUTEX(mutex_X2);
static DEFINE_MUTEX(mutex_Y1);
static DEFINE_MUTEX(mutex_Y2);
static DEFINE_MUTEX(mutex_Z1);
static DEFINE_MUTEX(mutex_Z2);

static DECLARE_RWSEM(rwsem_X1);
static DECLARE_RWSEM(rwsem_X2);
static DECLARE_RWSEM(rwsem_Y1);
static DECLARE_RWSEM(rwsem_Y2);
static DECLARE_RWSEM(rwsem_Z1);
static DECLARE_RWSEM(rwsem_Z2);

/*
 * non-inlined runtime initializers, to let separate locks share
 * the same lock-class:
 */
#define INIT_CLASS_FUNC(class) 				\
static noinline void					\
init_class_##class(spinlock_t *lock, rwlock_t *rwlock, struct mutex *mutex, \
		 struct rw_semaphore *rwsem)		\
{							\
	spin_lock_init(lock);				\
	rwlock_init(rwlock);				\
	mutex_init(mutex);				\
	init_rwsem(rwsem);				\
}

INIT_CLASS_FUNC(X)
INIT_CLASS_FUNC(Y)
INIT_CLASS_FUNC(Z)

static void init_shared_classes(void)
{
	init_class_X(&lock_X1, &rwlock_X1, &mutex_X1, &rwsem_X1);
	init_class_X(&lock_X2, &rwlock_X2, &mutex_X2, &rwsem_X2);

	init_class_Y(&lock_Y1, &rwlock_Y1, &mutex_Y1, &rwsem_Y1);
	init_class_Y(&lock_Y2, &rwlock_Y2, &mutex_Y2, &rwsem_Y2);

	init_class_Z(&lock_Z1, &rwlock_Z1, &mutex_Z1, &rwsem_Z1);
	init_class_Z(&lock_Z2, &rwlock_Z2, &mutex_Z2, &rwsem_Z2);
}

/*
 * For spinlocks and rwlocks we also do hardirq-safe / softirq-safe tests.
 * The following functions use a lock from a simulated hardirq/softirq
 * context, causing the locks to be marked as hardirq-safe/softirq-safe:
 */

#define HARDIRQ_DISABLE		local_irq_disable
#define HARDIRQ_ENABLE		local_irq_enable

#define HARDIRQ_ENTER()				\
	local_irq_disable();			\
	__irq_enter();				\
	WARN_ON(!in_irq());

#define HARDIRQ_EXIT()				\
	__irq_exit();				\
	local_irq_enable();

#define SOFTIRQ_DISABLE		local_bh_disable
#define SOFTIRQ_ENABLE		local_bh_enable

#define SOFTIRQ_ENTER()				\
		local_bh_disable();		\
		local_irq_disable();		\
		lockdep_softirq_enter();	\
		WARN_ON(!in_softirq());

#define SOFTIRQ_EXIT()				\
		lockdep_softirq_exit();		\
		local_irq_enable();		\
		local_bh_enable();

/*
 * Shortcuts for lock/unlock API variants, to keep
 * the testcases compact:
 */
#define L(x)			spin_lock(&lock_##x)
#define U(x)			spin_unlock(&lock_##x)
#define LU(x)			L(x); U(x)
#define SI(x)			spin_lock_init(&lock_##x)

#define WL(x)			write_lock(&rwlock_##x)
#define WU(x)			write_unlock(&rwlock_##x)
#define WLU(x)			WL(x); WU(x)

#define RL(x)			read_lock(&rwlock_##x)
#define RU(x)			read_unlock(&rwlock_##x)
#define RLU(x)			RL(x); RU(x)
#define RWI(x)			rwlock_init(&rwlock_##x)

#define ML(x)			mutex_lock(&mutex_##x)
#define MU(x)			mutex_unlock(&mutex_##x)
#define MI(x)			mutex_init(&mutex_##x)

#define WSL(x)			down_write(&rwsem_##x)
#define WSU(x)			up_write(&rwsem_##x)

#define RSL(x)			down_read(&rwsem_##x)
#define RSU(x)			up_read(&rwsem_##x)
#define RWSI(x)			init_rwsem(&rwsem_##x)

#define LOCK_UNLOCK_2(x,y)	LOCK(x); LOCK(y); UNLOCK(y); UNLOCK(x)

/*
 * Generate different permutations of the same testcase, using
 * the same basic lock-dependency/state events:
 */

#define GENERATE_TESTCASE(name)			\
						\
static void name(void) { E(); }

#define GENERATE_PERMUTATIONS_2_EVENTS(name)	\
						\
static void name##_12(void) { E1(); E2(); }	\
static void name##_21(void) { E2(); E1(); }

#define GENERATE_PERMUTATIONS_3_EVENTS(name)		\
							\
static void name##_123(void) { E1(); E2(); E3(); }	\
static void name##_132(void) { E1(); E3(); E2(); }	\
static void name##_213(void) { E2(); E1(); E3(); }	\
static void name##_231(void) { E2(); E3(); E1(); }	\
static void name##_312(void) { E3(); E1(); E2(); }	\
static void name##_321(void) { E3(); E2(); E1(); }

/*
 * AA deadlock:
 */

#define E()					\
						\
	LOCK(X1);				\
	LOCK(X2); /* this one should fail */

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(AA_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(AA_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(AA_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(AA_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(AA_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(AA_rsem)

#undef E

/*
 * Special-case for read-locking, they are
 * allowed to recurse on the same lock class:
 */
static void rlock_AA1(void)
{
	RL(X1);
	RL(X1); // this one should NOT fail
}

static void rlock_AA1B(void)
{
	RL(X1);
	RL(X2); // this one should NOT fail
}

static void rsem_AA1(void)
{
	RSL(X1);
	RSL(X1); // this one should fail
}

static void rsem_AA1B(void)
{
	RSL(X1);
	RSL(X2); // this one should fail
}
/*
 * The mixing of read and write locks is not allowed:
 */
static void rlock_AA2(void)
{
	RL(X1);
	WL(X2); // this one should fail
}

static void rsem_AA2(void)
{
	RSL(X1);
	WSL(X2); // this one should fail
}

static void rlock_AA3(void)
{
	WL(X1);
	RL(X2); // this one should fail
}

static void rsem_AA3(void)
{
	WSL(X1);
	RSL(X2); // this one should fail
}

/*
 * ABBA deadlock:
 */

#define E()					\
						\
	LOCK_UNLOCK_2(A, B);			\
	LOCK_UNLOCK_2(B, A); /* fail */

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(ABBA_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(ABBA_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(ABBA_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(ABBA_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(ABBA_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(ABBA_rsem)

#undef E

/*
 * AB BC CA deadlock:
 */

#define E()					\
						\
	LOCK_UNLOCK_2(A, B);			\
	LOCK_UNLOCK_2(B, C);			\
	LOCK_UNLOCK_2(C, A); /* fail */

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(ABBCCA_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(ABBCCA_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(ABBCCA_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(ABBCCA_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(ABBCCA_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(ABBCCA_rsem)

#undef E

/*
 * AB CA BC deadlock:
 */

#define E()					\
						\
	LOCK_UNLOCK_2(A, B);			\
	LOCK_UNLOCK_2(C, A);			\
	LOCK_UNLOCK_2(B, C); /* fail */

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(ABCABC_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(ABCABC_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(ABCABC_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(ABCABC_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(ABCABC_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(ABCABC_rsem)

#undef E

/*
 * AB BC CD DA deadlock:
 */

#define E()					\
						\
	LOCK_UNLOCK_2(A, B);			\
	LOCK_UNLOCK_2(B, C);			\
	LOCK_UNLOCK_2(C, D);			\
	LOCK_UNLOCK_2(D, A); /* fail */

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(ABBCCDDA_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(ABBCCDDA_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(ABBCCDDA_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(ABBCCDDA_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(ABBCCDDA_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(ABBCCDDA_rsem)

#undef E

/*
 * AB CD BD DA deadlock:
 */
#define E()					\
						\
	LOCK_UNLOCK_2(A, B);			\
	LOCK_UNLOCK_2(C, D);			\
	LOCK_UNLOCK_2(B, D);			\
	LOCK_UNLOCK_2(D, A); /* fail */

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(ABCDBDDA_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(ABCDBDDA_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(ABCDBDDA_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(ABCDBDDA_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(ABCDBDDA_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(ABCDBDDA_rsem)

#undef E

/*
 * AB CD BC DA deadlock:
 */
#define E()					\
						\
	LOCK_UNLOCK_2(A, B);			\
	LOCK_UNLOCK_2(C, D);			\
	LOCK_UNLOCK_2(B, C);			\
	LOCK_UNLOCK_2(D, A); /* fail */

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(ABCDBCDA_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(ABCDBCDA_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(ABCDBCDA_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(ABCDBCDA_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(ABCDBCDA_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(ABCDBCDA_rsem)

#undef E

/*
 * Double unlock:
 */
#define E()					\
						\
	LOCK(A);				\
	UNLOCK(A);				\
	UNLOCK(A); /* fail */

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(double_unlock_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(double_unlock_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(double_unlock_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(double_unlock_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(double_unlock_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(double_unlock_rsem)

#undef E

/*
 * Bad unlock ordering:
 */
#define E()					\
						\
	LOCK(A);				\
	LOCK(B);				\
	UNLOCK(A); /* fail */			\
	UNLOCK(B);

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(bad_unlock_order_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(bad_unlock_order_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(bad_unlock_order_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(bad_unlock_order_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(bad_unlock_order_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(bad_unlock_order_rsem)

#undef E

/*
 * initializing a held lock:
 */
#define E()					\
						\
	LOCK(A);				\
	INIT(A); /* fail */

/*
 * 6 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_TESTCASE(init_held_spin)
#include "locking-selftest-wlock.h"
GENERATE_TESTCASE(init_held_wlock)
#include "locking-selftest-rlock.h"
GENERATE_TESTCASE(init_held_rlock)
#include "locking-selftest-mutex.h"
GENERATE_TESTCASE(init_held_mutex)
#include "locking-selftest-wsem.h"
GENERATE_TESTCASE(init_held_wsem)
#include "locking-selftest-rsem.h"
GENERATE_TESTCASE(init_held_rsem)

#undef E

/*
 * locking an irq-safe lock with irqs enabled:
 */
#define E1()				\
					\
	IRQ_ENTER();			\
	LOCK(A);			\
	UNLOCK(A);			\
	IRQ_EXIT();

#define E2()				\
					\
	LOCK(A);			\
	UNLOCK(A);

/*
 * Generate 24 testcases:
 */
#include "locking-selftest-spin-hardirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin)

#include "locking-selftest-rlock-hardirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock)

#include "locking-selftest-wlock-hardirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_wlock)

#include "locking-selftest-spin-softirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_spin)

#include "locking-selftest-rlock-softirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_rlock)

#include "locking-selftest-wlock-softirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock)

#undef E1
#undef E2

/*
 * Enabling hardirqs with a softirq-safe lock held:
 */
#define E1()				\
					\
	SOFTIRQ_ENTER();		\
	LOCK(A);			\
	UNLOCK(A);			\
	SOFTIRQ_EXIT();

#define E2()				\
					\
	HARDIRQ_DISABLE();		\
	LOCK(A);			\
	HARDIRQ_ENABLE();		\
	UNLOCK(A);

/*
 * Generate 12 testcases:
 */
#include "locking-selftest-spin.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_spin)

#include "locking-selftest-wlock.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_wlock)

#include "locking-selftest-rlock.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock)

#undef E1
#undef E2

/*
 * Enabling irqs with an irq-safe lock held:
 */
#define E1()				\
					\
	IRQ_ENTER();			\
	LOCK(A);			\
	UNLOCK(A);			\
	IRQ_EXIT();

#define E2()				\
					\
	IRQ_DISABLE();			\
	LOCK(A);			\
	IRQ_ENABLE();			\
	UNLOCK(A);

/*
 * Generate 24 testcases:
 */
#include "locking-selftest-spin-hardirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin)

#include "locking-selftest-rlock-hardirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock)

#include "locking-selftest-wlock-hardirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_wlock)

#include "locking-selftest-spin-softirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_spin)

#include "locking-selftest-rlock-softirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_rlock)

#include "locking-selftest-wlock-softirq.h"
GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)

#undef E1
#undef E2

/*
 * Acquiring a irq-unsafe lock while holding an irq-safe-lock:
 */
#define E1()				\
					\
	LOCK(A);			\
	LOCK(B);			\
	UNLOCK(B);			\
	UNLOCK(A);			\

#define E2()				\
					\
	LOCK(B);			\
	UNLOCK(B);

#define E3()				\
					\
	IRQ_ENTER();			\
	LOCK(A);			\
	UNLOCK(A);			\
	IRQ_EXIT();

/*
 * Generate 36 testcases:
 */
#include "locking-selftest-spin-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin)

#include "locking-selftest-rlock-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock)

#include "locking-selftest-wlock-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_wlock)

#include "locking-selftest-spin-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_spin)

#include "locking-selftest-rlock-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_rlock)

#include "locking-selftest-wlock-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)

#undef E1
#undef E2
#undef E3

/*
 * If a lock turns into softirq-safe, but earlier it took
 * a softirq-unsafe lock:
 */

#define E1()				\
	IRQ_DISABLE();			\
	LOCK(A);			\
	LOCK(B);			\
	UNLOCK(B);			\
	UNLOCK(A);			\
	IRQ_ENABLE();

#define E2()				\
	LOCK(B);			\
	UNLOCK(B);

#define E3()				\
	IRQ_ENTER();			\
	LOCK(A);			\
	UNLOCK(A);			\
	IRQ_EXIT();

/*
 * Generate 36 testcases:
 */
#include "locking-selftest-spin-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin)

#include "locking-selftest-rlock-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock)

#include "locking-selftest-wlock-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_wlock)

#include "locking-selftest-spin-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_spin)

#include "locking-selftest-rlock-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_rlock)

#include "locking-selftest-wlock-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock)

#undef E1
#undef E2
#undef E3

/*
 * read-lock / write-lock irq inversion.
 *
 * Deadlock scenario:
 *
 * CPU#1 is at #1, i.e. it has write-locked A, but has not
 * taken B yet.
 *
 * CPU#2 is at #2, i.e. it has locked B.
 *
 * Hardirq hits CPU#2 at point #2 and is trying to read-lock A.
 *
 * The deadlock occurs because CPU#1 will spin on B, and CPU#2
 * will spin on A.
 */

#define E1()				\
					\
	IRQ_DISABLE();			\
	WL(A);				\
	LOCK(B);			\
	UNLOCK(B);			\
	WU(A);				\
	IRQ_ENABLE();

#define E2()				\
					\
	LOCK(B);			\
	UNLOCK(B);

#define E3()				\
					\
	IRQ_ENTER();			\
	RL(A);				\
	RU(A);				\
	IRQ_EXIT();

/*
 * Generate 36 testcases:
 */
#include "locking-selftest-spin-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_hard_spin)

#include "locking-selftest-rlock-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_hard_rlock)

#include "locking-selftest-wlock-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_hard_wlock)

#include "locking-selftest-spin-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_soft_spin)

#include "locking-selftest-rlock-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_soft_rlock)

#include "locking-selftest-wlock-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_soft_wlock)

#undef E1
#undef E2
#undef E3

/*
 * read-lock / write-lock recursion that is actually safe.
 */

#define E1()				\
					\
	IRQ_DISABLE();			\
	WL(A);				\
	WU(A);				\
	IRQ_ENABLE();

#define E2()				\
					\
	RL(A);				\
	RU(A);				\

#define E3()				\
					\
	IRQ_ENTER();			\
	RL(A);				\
	L(B);				\
	U(B);				\
	RU(A);				\
	IRQ_EXIT();

/*
 * Generate 12 testcases:
 */
#include "locking-selftest-hardirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_hard)

#include "locking-selftest-softirq.h"
GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft)

#undef E1
#undef E2
#undef E3

/*
 * read-lock / write-lock recursion that is unsafe.
 */

#define E1()				\
					\
	IRQ_DISABLE();			\
	L(B);				\
	WL(A);				\
	WU(A);				\
	U(B);				\
	IRQ_ENABLE();

#define E2()				\
					\
	RL(A);				\
	RU(A);				\

#define E3()				\
					\
	IRQ_ENTER();			\
	L(B);				\
	U(B);				\
	IRQ_EXIT();

/*
 * Generate 12 testcases:
 */
#include "locking-selftest-hardirq.h"
// GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion2_hard)

#include "locking-selftest-softirq.h"
// GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion2_soft)

#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define I_SPINLOCK(x)	lockdep_reset_lock(&lock_##x.dep_map)
# define I_RWLOCK(x)	lockdep_reset_lock(&rwlock_##x.dep_map)
# define I_MUTEX(x)	lockdep_reset_lock(&mutex_##x.dep_map)
# define I_RWSEM(x)	lockdep_reset_lock(&rwsem_##x.dep_map)
#else
# define I_SPINLOCK(x)
# define I_RWLOCK(x)
# define I_MUTEX(x)
# define I_RWSEM(x)
#endif

#define I1(x)					\
	do {					\
		I_SPINLOCK(x);			\
		I_RWLOCK(x);			\
		I_MUTEX(x);			\
		I_RWSEM(x);			\
	} while (0)

#define I2(x)					\
	do {					\
		spin_lock_init(&lock_##x);	\
		rwlock_init(&rwlock_##x);	\
		mutex_init(&mutex_##x);		\
		init_rwsem(&rwsem_##x);		\
	} while (0)

static void reset_locks(void)
{
	local_irq_disable();
	I1(A); I1(B); I1(C); I1(D);
	I1(X1); I1(X2); I1(Y1); I1(Y2); I1(Z1); I1(Z2);
	lockdep_reset();
	I2(A); I2(B); I2(C); I2(D);
	init_shared_classes();
	local_irq_enable();
}

#undef I

static int testcase_total;
static int testcase_successes;
static int expected_testcase_failures;
static int unexpected_testcase_failures;

static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask)
{
	unsigned long saved_preempt_count = preempt_count();
	int expected_failure = 0;

	WARN_ON(irqs_disabled());

	testcase_fn();
	/*
	 * Filter out expected failures:
	 */
#ifndef CONFIG_PROVE_LOCKING
	if ((lockclass_mask & LOCKTYPE_SPIN) && debug_locks != expected)
		expected_failure = 1;
	if ((lockclass_mask & LOCKTYPE_RWLOCK) && debug_locks != expected)
		expected_failure = 1;
	if ((lockclass_mask & LOCKTYPE_MUTEX) && debug_locks != expected)
		expected_failure = 1;
	if ((lockclass_mask & LOCKTYPE_RWSEM) && debug_locks != expected)
		expected_failure = 1;
#endif
	if (debug_locks != expected) {
		if (expected_failure) {
			expected_testcase_failures++;
			printk("failed|");
		} else {
			unexpected_testcase_failures++;

			printk("FAILED|");
			dump_stack();
		}
	} else {
		testcase_successes++;
		printk("  ok  |");
	}
	testcase_total++;

	if (debug_locks_verbose)
		printk(" lockclass mask: %x, debug_locks: %d, expected: %d\n",
			lockclass_mask, debug_locks, expected);
	/*
	 * Some tests (e.g. double-unlock) might corrupt the preemption
	 * count, so restore it:
	 */
	preempt_count() = saved_preempt_count;
#ifdef CONFIG_TRACE_IRQFLAGS
	if (softirq_count())
		current->softirqs_enabled = 0;
	else
		current->softirqs_enabled = 1;
#endif

	reset_locks();
}

static inline void print_testname(const char *testname)
{
	printk("%33s:", testname);
}

#define DO_TESTCASE_1(desc, name, nr)				\
	print_testname(desc"/"#nr);				\
	dotest(name##_##nr, SUCCESS, LOCKTYPE_RWLOCK);		\
	printk("\n");

#define DO_TESTCASE_1B(desc, name, nr)				\
	print_testname(desc"/"#nr);				\
	dotest(name##_##nr, FAILURE, LOCKTYPE_RWLOCK);		\
	printk("\n");

#define DO_TESTCASE_3(desc, name, nr)				\
	print_testname(desc"/"#nr);				\
	dotest(name##_spin_##nr, FAILURE, LOCKTYPE_SPIN);	\
	dotest(name##_wlock_##nr, FAILURE, LOCKTYPE_RWLOCK);	\
	dotest(name##_rlock_##nr, SUCCESS, LOCKTYPE_RWLOCK);	\
	printk("\n");

#define DO_TESTCASE_3RW(desc, name, nr)				\
	print_testname(desc"/"#nr);				\
	dotest(name##_spin_##nr, FAILURE, LOCKTYPE_SPIN|LOCKTYPE_RWLOCK);\
	dotest(name##_wlock_##nr, FAILURE, LOCKTYPE_RWLOCK);	\
	dotest(name##_rlock_##nr, SUCCESS, LOCKTYPE_RWLOCK);	\
	printk("\n");

#define DO_TESTCASE_6(desc, name)				\
	print_testname(desc);					\
	dotest(name##_spin, FAILURE, LOCKTYPE_SPIN);		\
	dotest(name##_wlock, FAILURE, LOCKTYPE_RWLOCK);		\
	dotest(name##_rlock, FAILURE, LOCKTYPE_RWLOCK);		\
	dotest(name##_mutex, FAILURE, LOCKTYPE_MUTEX);		\
	dotest(name##_wsem, FAILURE, LOCKTYPE_RWSEM);		\
	dotest(name##_rsem, FAILURE, LOCKTYPE_RWSEM);		\
	printk("\n");

#define DO_TESTCASE_6_SUCCESS(desc, name)			\
	print_testname(desc);					\
	dotest(name##_spin, SUCCESS, LOCKTYPE_SPIN);		\
	dotest(name##_wlock, SUCCESS, LOCKTYPE_RWLOCK);		\
	dotest(name##_rlock, SUCCESS, LOCKTYPE_RWLOCK);		\
	dotest(name##_mutex, SUCCESS, LOCKTYPE_MUTEX);		\
	dotest(name##_wsem, SUCCESS, LOCKTYPE_RWSEM);		\
	dotest(name##_rsem, SUCCESS, LOCKTYPE_RWSEM);		\
	printk("\n");

/*
 * 'read' variant: rlocks must not trigger.
 */
#define DO_TESTCASE_6R(desc, name)				\
	print_testname(desc);					\
	dotest(name##_spin, FAILURE, LOCKTYPE_SPIN);		\
	dotest(name##_wlock, FAILURE, LOCKTYPE_RWLOCK);		\
	dotest(name##_rlock, SUCCESS, LOCKTYPE_RWLOCK);		\
	dotest(name##_mutex, FAILURE, LOCKTYPE_MUTEX);		\
	dotest(name##_wsem, FAILURE, LOCKTYPE_RWSEM);		\
	dotest(name##_rsem, FAILURE, LOCKTYPE_RWSEM);		\
	printk("\n");

#define DO_TESTCASE_2I(desc, name, nr)				\
	DO_TESTCASE_1("hard-"desc, name##_hard, nr);		\
	DO_TESTCASE_1("soft-"desc, name##_soft, nr);

#define DO_TESTCASE_2IB(desc, name, nr)				\
	DO_TESTCASE_1B("hard-"desc, name##_hard, nr);		\
	DO_TESTCASE_1B("soft-"desc, name##_soft, nr);

#define DO_TESTCASE_6I(desc, name, nr)				\
	DO_TESTCASE_3("hard-"desc, name##_hard, nr);		\
	DO_TESTCASE_3("soft-"desc, name##_soft, nr);

#define DO_TESTCASE_6IRW(desc, name, nr)			\
	DO_TESTCASE_3RW("hard-"desc, name##_hard, nr);		\
	DO_TESTCASE_3RW("soft-"desc, name##_soft, nr);

#define DO_TESTCASE_2x3(desc, name)				\
	DO_TESTCASE_3(desc, name, 12);				\
	DO_TESTCASE_3(desc, name, 21);

#define DO_TESTCASE_2x6(desc, name)				\
	DO_TESTCASE_6I(desc, name, 12);				\
	DO_TESTCASE_6I(desc, name, 21);

#define DO_TESTCASE_6x2(desc, name)				\
	DO_TESTCASE_2I(desc, name, 123);			\
	DO_TESTCASE_2I(desc, name, 132);			\
	DO_TESTCASE_2I(desc, name, 213);			\
	DO_TESTCASE_2I(desc, name, 231);			\
	DO_TESTCASE_2I(desc, name, 312);			\
	DO_TESTCASE_2I(desc, name, 321);

#define DO_TESTCASE_6x2B(desc, name)				\
	DO_TESTCASE_2IB(desc, name, 123);			\
	DO_TESTCASE_2IB(desc, name, 132);			\
	DO_TESTCASE_2IB(desc, name, 213);			\
	DO_TESTCASE_2IB(desc, name, 231);			\
	DO_TESTCASE_2IB(desc, name, 312);			\
	DO_TESTCASE_2IB(desc, name, 321);

#define DO_TESTCASE_6x6(desc, name)				\
	DO_TESTCASE_6I(desc, name, 123);			\
	DO_TESTCASE_6I(desc, name, 132);			\
	DO_TESTCASE_6I(desc, name, 213);			\
	DO_TESTCASE_6I(desc, name, 231);			\
	DO_TESTCASE_6I(desc, name, 312);			\
	DO_TESTCASE_6I(desc, name, 321);

#define DO_TESTCASE_6x6RW(desc, name)				\
	DO_TESTCASE_6IRW(desc, name, 123);			\
	DO_TESTCASE_6IRW(desc, name, 132);			\
	DO_TESTCASE_6IRW(desc, name, 213);			\
	DO_TESTCASE_6IRW(desc, name, 231);			\
	DO_TESTCASE_6IRW(desc, name, 312);			\
	DO_TESTCASE_6IRW(desc, name, 321);


void locking_selftest(void)
{
	/*
	 * Got a locking failure before the selftest ran?
	 */
	if (!debug_locks) {
		printk("----------------------------------\n");
		printk("| Locking API testsuite disabled |\n");
		printk("----------------------------------\n");
		return;
	}

	/*
	 * Run the testsuite:
	 */
	printk("------------------------\n");
	printk("| Locking API testsuite:\n");
	printk("----------------------------------------------------------------------------\n");
	printk("                                 | spin |wlock |rlock |mutex | wsem | rsem |\n");
	printk("  --------------------------------------------------------------------------\n");

	init_shared_classes();
	debug_locks_silent = !debug_locks_verbose;

	DO_TESTCASE_6R("A-A deadlock", AA);
	DO_TESTCASE_6R("A-B-B-A deadlock", ABBA);
	DO_TESTCASE_6R("A-B-B-C-C-A deadlock", ABBCCA);
	DO_TESTCASE_6R("A-B-C-A-B-C deadlock", ABCABC);
	DO_TESTCASE_6R("A-B-B-C-C-D-D-A deadlock", ABBCCDDA);
	DO_TESTCASE_6R("A-B-C-D-B-D-D-A deadlock", ABCDBDDA);
	DO_TESTCASE_6R("A-B-C-D-B-C-D-A deadlock", ABCDBCDA);
	DO_TESTCASE_6("double unlock", double_unlock);
	DO_TESTCASE_6("initialize held", init_held);
	DO_TESTCASE_6_SUCCESS("bad unlock order", bad_unlock_order);

	printk("  --------------------------------------------------------------------------\n");
	print_testname("recursive read-lock");
	printk("             |");
	dotest(rlock_AA1, SUCCESS, LOCKTYPE_RWLOCK);
	printk("             |");
	dotest(rsem_AA1, FAILURE, LOCKTYPE_RWSEM);
	printk("\n");

	print_testname("recursive read-lock #2");
	printk("             |");
	dotest(rlock_AA1B, SUCCESS, LOCKTYPE_RWLOCK);
	printk("             |");
	dotest(rsem_AA1B, FAILURE, LOCKTYPE_RWSEM);
	printk("\n");

	print_testname("mixed read-write-lock");
	printk("             |");
	dotest(rlock_AA2, FAILURE, LOCKTYPE_RWLOCK);
	printk("             |");
	dotest(rsem_AA2, FAILURE, LOCKTYPE_RWSEM);
	printk("\n");

	print_testname("mixed write-read-lock");
	printk("             |");
	dotest(rlock_AA3, FAILURE, LOCKTYPE_RWLOCK);
	printk("             |");
	dotest(rsem_AA3, FAILURE, LOCKTYPE_RWSEM);
	printk("\n");

	printk("  --------------------------------------------------------------------------\n");

	/*
	 * irq-context testcases:
	 */
	DO_TESTCASE_2x6("irqs-on + irq-safe-A", irqsafe1);
	DO_TESTCASE_2x3("sirq-safe-A => hirqs-on", irqsafe2A);
	DO_TESTCASE_2x6("safe-A + irqs-on", irqsafe2B);
	DO_TESTCASE_6x6("safe-A + unsafe-B #1", irqsafe3);
	DO_TESTCASE_6x6("safe-A + unsafe-B #2", irqsafe4);
	DO_TESTCASE_6x6RW("irq lock-inversion", irq_inversion);

	DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion);
//	DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2);

	if (unexpected_testcase_failures) {
		printk("-----------------------------------------------------------------\n");
		debug_locks = 0;
		printk("BUG: %3d unexpected failures (out of %3d) - debugging disabled! |\n",
			unexpected_testcase_failures, testcase_total);
		printk("-----------------------------------------------------------------\n");
	} else if (expected_testcase_failures && testcase_successes) {
		printk("--------------------------------------------------------\n");
		printk("%3d out of %3d testcases failed, as expected. |\n",
			expected_testcase_failures, testcase_total);
		printk("----------------------------------------------------\n");
		debug_locks = 1;
	} else if (expected_testcase_failures && !testcase_successes) {
		printk("--------------------------------------------------------\n");
		printk("All %3d testcases failed, as expected. |\n",
			expected_testcase_failures);
		printk("----------------------------------------\n");
		debug_locks = 1;
	} else {
		printk("-------------------------------------------------------\n");
		printk("Good, all %3d testcases passed! |\n",
			testcase_successes);
		printk("---------------------------------\n");
		debug_locks = 1;
	}
	debug_locks_silent = 0;
}
10' href='#n3710'>3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613
/*
 * originally based on the dummy device.
 *
 * Copyright 1999, Thomas Davis, tadavis@lbl.gov.
 * Licensed under the GPL. Based on dummy.c, and eql.c devices.
 *
 * bonding.c: an Ethernet Bonding driver
 *
 * This is useful to talk to a Cisco EtherChannel compatible equipment:
 *	Cisco 5500
 *	Sun Trunking (Solaris)
 *	Alteon AceDirector Trunks
 *	Linux Bonding
 *	and probably many L2 switches ...
 *
 * How it works:
 *    ifconfig bond0 ipaddress netmask up
 *      will setup a network device, with an ip address.  No mac address
 *	will be assigned at this time.  The hw mac address will come from
 *	the first slave bonded to the channel.  All slaves will then use
 *	this hw mac address.
 *
 *    ifconfig bond0 down
 *         will release all slaves, marking them as down.
 *
 *    ifenslave bond0 eth0
 *	will attach eth0 to bond0 as a slave.  eth0 hw mac address will either
 *	a: be used as initial mac address
 *	b: if a hw mac address already is there, eth0's hw mac address
 *	   will then be set from bond0.
 *
 */

//#define BONDING_DEBUG 1

#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/interrupt.h>
#include <linux/ptrace.h>
#include <linux/ioport.h>
#include <linux/in.h>
#include <net/ip.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/timer.h>
#include <linux/socket.h>
#include <linux/ctype.h>
#include <linux/inet.h>
#include <linux/bitops.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/dma.h>
#include <asm/uaccess.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/if_ether.h>
#include <net/arp.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <linux/if_bonding.h>
#include <net/route.h>
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"

/*---------------------------- Module parameters ----------------------------*/

/* monitor all links that often (in milliseconds). <=0 disables monitoring */
#define BOND_LINK_MON_INTERV	0
#define BOND_LINK_ARP_INTERV	0

static int max_bonds	= BOND_DEFAULT_MAX_BONDS;
static int miimon	= BOND_LINK_MON_INTERV;
static int updelay	= 0;
static int downdelay	= 0;
static int use_carrier	= 1;
static char *mode	= NULL;
static char *primary	= NULL;
static char *lacp_rate	= NULL;
static char *xmit_hash_policy = NULL;
static int arp_interval = BOND_LINK_ARP_INTERV;
static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, };
struct bond_params bonding_defaults;

module_param(max_bonds, int, 0);
MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
module_param(miimon, int, 0);
MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
module_param(updelay, int, 0);
MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds");
module_param(downdelay, int, 0);
MODULE_PARM_DESC(downdelay, "Delay before considering link down, "
			    "in milliseconds");
module_param(use_carrier, int, 0);
MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; "
			      "0 for off, 1 for on (default)");
module_param(mode, charp, 0);
MODULE_PARM_DESC(mode, "Mode of operation : 0 for balance-rr, "
		       "1 for active-backup, 2 for balance-xor, "
		       "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, "
		       "6 for balance-alb");
module_param(primary, charp, 0);
MODULE_PARM_DESC(primary, "Primary network device to use");
module_param(lacp_rate, charp, 0);
MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner "
			    "(slow/fast)");
module_param(xmit_hash_policy, charp, 0);
MODULE_PARM_DESC(xmit_hash_policy, "XOR hashing method: 0 for layer 2 (default)"
				   ", 1 for layer 3+4");
module_param(arp_interval, int, 0);
MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds");
module_param_array(arp_ip_target, charp, NULL, 0);
MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form");

/*----------------------------- Global variables ----------------------------*/

static const char *version =
	DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n";

LIST_HEAD(bond_dev_list);

#ifdef CONFIG_PROC_FS
static struct proc_dir_entry *bond_proc_dir = NULL;
#endif

extern struct rw_semaphore bonding_rwsem;
static u32 arp_target[BOND_MAX_ARP_TARGETS] = { 0, } ;
static int arp_ip_count	= 0;
static int bond_mode	= BOND_MODE_ROUNDROBIN;
static int xmit_hashtype= BOND_XMIT_POLICY_LAYER2;
static int lacp_fast	= 0;


struct bond_parm_tbl bond_lacp_tbl[] = {
{	"slow",		AD_LACP_SLOW},
{	"fast",		AD_LACP_FAST},
{	NULL,		-1},
};

struct bond_parm_tbl bond_mode_tbl[] = {
{	"balance-rr",		BOND_MODE_ROUNDROBIN},
{	"active-backup",	BOND_MODE_ACTIVEBACKUP},
{	"balance-xor",		BOND_MODE_XOR},
{	"broadcast",		BOND_MODE_BROADCAST},
{	"802.3ad",		BOND_MODE_8023AD},
{	"balance-tlb",		BOND_MODE_TLB},
{	"balance-alb",		BOND_MODE_ALB},
{	NULL,			-1},
};

struct bond_parm_tbl xmit_hashtype_tbl[] = {
{	"layer2",		BOND_XMIT_POLICY_LAYER2},
{	"layer3+4",		BOND_XMIT_POLICY_LAYER34},
{	NULL,			-1},
};

/*-------------------------- Forward declarations ---------------------------*/

static void bond_send_gratuitous_arp(struct bonding *bond);

/*---------------------------- General routines -----------------------------*/

const char *bond_mode_name(int mode)
{
	switch (mode) {
	case BOND_MODE_ROUNDROBIN :
		return "load balancing (round-robin)";
	case BOND_MODE_ACTIVEBACKUP :
		return "fault-tolerance (active-backup)";
	case BOND_MODE_XOR :
		return "load balancing (xor)";
	case BOND_MODE_BROADCAST :
		return "fault-tolerance (broadcast)";
	case BOND_MODE_8023AD:
		return "IEEE 802.3ad Dynamic link aggregation";
	case BOND_MODE_TLB:
		return "transmit load balancing";
	case BOND_MODE_ALB:
		return "adaptive load balancing";
	default:
		return "unknown";
	}
}

/*---------------------------------- VLAN -----------------------------------*/

/**
 * bond_add_vlan - add a new vlan id on bond
 * @bond: bond that got the notification
 * @vlan_id: the vlan id to add
 *
 * Returns -ENOMEM if allocation failed.
 */
static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id)
{
	struct vlan_entry *vlan;

	dprintk("bond: %s, vlan id %d\n",
		(bond ? bond->dev->name: "None"), vlan_id);

	vlan = kmalloc(sizeof(struct vlan_entry), GFP_KERNEL);
	if (!vlan) {
		return -ENOMEM;
	}

	INIT_LIST_HEAD(&vlan->vlan_list);
	vlan->vlan_id = vlan_id;
	vlan->vlan_ip = 0;

	write_lock_bh(&bond->lock);

	list_add_tail(&vlan->vlan_list, &bond->vlan_list);

	write_unlock_bh(&bond->lock);

	dprintk("added VLAN ID %d on bond %s\n", vlan_id, bond->dev->name);

	return 0;
}

/**
 * bond_del_vlan - delete a vlan id from bond
 * @bond: bond that got the notification
 * @vlan_id: the vlan id to delete
 *
 * returns -ENODEV if @vlan_id was not found in @bond.
 */
static int bond_del_vlan(struct bonding *bond, unsigned short vlan_id)
{
	struct vlan_entry *vlan, *next;
	int res = -ENODEV;

	dprintk("bond: %s, vlan id %d\n", bond->dev->name, vlan_id);

	write_lock_bh(&bond->lock);

	list_for_each_entry_safe(vlan, next, &bond->vlan_list, vlan_list) {
		if (vlan->vlan_id == vlan_id) {
			list_del(&vlan->vlan_list);

			if ((bond->params.mode == BOND_MODE_TLB) ||
			    (bond->params.mode == BOND_MODE_ALB)) {
				bond_alb_clear_vlan(bond, vlan_id);
			}

			dprintk("removed VLAN ID %d from bond %s\n", vlan_id,
				bond->dev->name);

			kfree(vlan);

			if (list_empty(&bond->vlan_list) &&
			    (bond->slave_cnt == 0)) {
				/* Last VLAN removed and no slaves, so
				 * restore block on adding VLANs. This will
				 * be removed once new slaves that are not
				 * VLAN challenged will be added.
				 */
				bond->dev->features |= NETIF_F_VLAN_CHALLENGED;
			}

			res = 0;
			goto out;
		}
	}

	dprintk("couldn't find VLAN ID %d in bond %s\n", vlan_id,
		bond->dev->name);

out:
	write_unlock_bh(&bond->lock);
	return res;
}

/**
 * bond_has_challenged_slaves
 * @bond: the bond we're working on
 *
 * Searches the slave list. Returns 1 if a vlan challenged slave
 * was found, 0 otherwise.
 *
 * Assumes bond->lock is held.
 */
static int bond_has_challenged_slaves(struct bonding *bond)
{
	struct slave *slave;
	int i;

	bond_for_each_slave(bond, slave, i) {
		if (slave->dev->features & NETIF_F_VLAN_CHALLENGED) {
			dprintk("found VLAN challenged slave - %s\n",
				slave->dev->name);
			return 1;
		}
	}

	dprintk("no VLAN challenged slaves found\n");
	return 0;
}

/**
 * bond_next_vlan - safely skip to the next item in the vlans list.
 * @bond: the bond we're working on
 * @curr: item we're advancing from
 *
 * Returns %NULL if list is empty, bond->next_vlan if @curr is %NULL,
 * or @curr->next otherwise (even if it is @curr itself again).
 * 
 * Caller must hold bond->lock
 */
struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr)
{
	struct vlan_entry *next, *last;

	if (list_empty(&bond->vlan_list)) {
		return NULL;
	}

	if (!curr) {
		next = list_entry(bond->vlan_list.next,
				  struct vlan_entry, vlan_list);
	} else {
		last = list_entry(bond->vlan_list.prev,
				  struct vlan_entry, vlan_list);
		if (last == curr) {
			next = list_entry(bond->vlan_list.next,
					  struct vlan_entry, vlan_list);
		} else {
			next = list_entry(curr->vlan_list.next,
					  struct vlan_entry, vlan_list);
		}
	}

	return next;
}

/**
 * bond_dev_queue_xmit - Prepare skb for xmit.
 * 
 * @bond: bond device that got this skb for tx.
 * @skb: hw accel VLAN tagged skb to transmit
 * @slave_dev: slave that is supposed to xmit this skbuff
 * 
 * When the bond gets an skb to transmit that is
 * already hardware accelerated VLAN tagged, and it
 * needs to relay this skb to a slave that is not
 * hw accel capable, the skb needs to be "unaccelerated",
 * i.e. strip the hwaccel tag and re-insert it as part
 * of the payload.
 */
int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev)
{
	unsigned short vlan_id;

	if (!list_empty(&bond->vlan_list) &&
	    !(slave_dev->features & NETIF_F_HW_VLAN_TX) &&
	    vlan_get_tag(skb, &vlan_id) == 0) {
		skb->dev = slave_dev;
		skb = vlan_put_tag(skb, vlan_id);
		if (!skb) {
			/* vlan_put_tag() frees the skb in case of error,
			 * so return success here so the calling functions
			 * won't attempt to free is again.
			 */
			return 0;
		}
	} else {
		skb->dev = slave_dev;
	}

	skb->priority = 1;
	dev_queue_xmit(skb);

	return 0;
}

/*
 * In the following 3 functions, bond_vlan_rx_register(), bond_vlan_rx_add_vid
 * and bond_vlan_rx_kill_vid, We don't protect the slave list iteration with a
 * lock because:
 * a. This operation is performed in IOCTL context,
 * b. The operation is protected by the RTNL semaphore in the 8021q code,
 * c. Holding a lock with BH disabled while directly calling a base driver
 *    entry point is generally a BAD idea.
 * 
 * The design of synchronization/protection for this operation in the 8021q
 * module is good for one or more VLAN devices over a single physical device
 * and cannot be extended for a teaming solution like bonding, so there is a
 * potential race condition here where a net device from the vlan group might
 * be referenced (either by a base driver or the 8021q code) while it is being
 * removed from the system. However, it turns out we're not making matters
 * worse, and if it works for regular VLAN usage it will work here too.
*/

/**
 * bond_vlan_rx_register - Propagates registration to slaves
 * @bond_dev: bonding net device that got called
 * @grp: vlan group being registered
 */
static void bond_vlan_rx_register(struct net_device *bond_dev, struct vlan_group *grp)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave;
	int i;

	bond->vlgrp = grp;

	bond_for_each_slave(bond, slave, i) {
		struct net_device *slave_dev = slave->dev;

		if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
		    slave_dev->vlan_rx_register) {
			slave_dev->vlan_rx_register(slave_dev, grp);
		}
	}
}

/**
 * bond_vlan_rx_add_vid - Propagates adding an id to slaves
 * @bond_dev: bonding net device that got called
 * @vid: vlan id being added
 */
static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave;
	int i, res;

	bond_for_each_slave(bond, slave, i) {
		struct net_device *slave_dev = slave->dev;

		if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
		    slave_dev->vlan_rx_add_vid) {
			slave_dev->vlan_rx_add_vid(slave_dev, vid);
		}
	}

	res = bond_add_vlan(bond, vid);
	if (res) {
		printk(KERN_ERR DRV_NAME
		       ": %s: Error: Failed to add vlan id %d\n",
		       bond_dev->name, vid);
	}
}

/**
 * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves
 * @bond_dev: bonding net device that got called
 * @vid: vlan id being removed
 */
static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave;
	struct net_device *vlan_dev;
	int i, res;

	bond_for_each_slave(bond, slave, i) {
		struct net_device *slave_dev = slave->dev;

		if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
		    slave_dev->vlan_rx_kill_vid) {
			/* Save and then restore vlan_dev in the grp array,
			 * since the slave's driver might clear it.
			 */
			vlan_dev = bond->vlgrp->vlan_devices[vid];
			slave_dev->vlan_rx_kill_vid(slave_dev, vid);
			bond->vlgrp->vlan_devices[vid] = vlan_dev;
		}
	}

	res = bond_del_vlan(bond, vid);
	if (res) {
		printk(KERN_ERR DRV_NAME
		       ": %s: Error: Failed to remove vlan id %d\n",
		       bond_dev->name, vid);
	}
}

static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev)
{
	struct vlan_entry *vlan;

	write_lock_bh(&bond->lock);

	if (list_empty(&bond->vlan_list)) {
		goto out;
	}

	if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
	    slave_dev->vlan_rx_register) {
		slave_dev->vlan_rx_register(slave_dev, bond->vlgrp);
	}

	if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
	    !(slave_dev->vlan_rx_add_vid)) {
		goto out;
	}

	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
		slave_dev->vlan_rx_add_vid(slave_dev, vlan->vlan_id);
	}

out:
	write_unlock_bh(&bond->lock);
}

static void bond_del_vlans_from_slave(struct bonding *bond, struct net_device *slave_dev)
{
	struct vlan_entry *vlan;
	struct net_device *vlan_dev;

	write_lock_bh(&bond->lock);

	if (list_empty(&bond->vlan_list)) {
		goto out;
	}

	if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
	    !(slave_dev->vlan_rx_kill_vid)) {
		goto unreg;
	}

	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
		/* Save and then restore vlan_dev in the grp array,
		 * since the slave's driver might clear it.
		 */
		vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id];
		slave_dev->vlan_rx_kill_vid(slave_dev, vlan->vlan_id);
		bond->vlgrp->vlan_devices[vlan->vlan_id] = vlan_dev;
	}

unreg:
	if ((slave_dev->features & NETIF_F_HW_VLAN_RX) &&
	    slave_dev->vlan_rx_register) {
		slave_dev->vlan_rx_register(slave_dev, NULL);
	}

out:
	write_unlock_bh(&bond->lock);
}

/*------------------------------- Link status -------------------------------*/

/*
 * Get link speed and duplex from the slave's base driver
 * using ethtool. If for some reason the call fails or the
 * values are invalid, fake speed and duplex to 100/Full
 * and return error.
 */
static int bond_update_speed_duplex(struct slave *slave)
{
	struct net_device *slave_dev = slave->dev;
	static int (* ioctl)(struct net_device *, struct ifreq *, int);
	struct ifreq ifr;
	struct ethtool_cmd etool;

	/* Fake speed and duplex */
	slave->speed = SPEED_100;
	slave->duplex = DUPLEX_FULL;

	if (slave_dev->ethtool_ops) {
		int res;

		if (!slave_dev->ethtool_ops->get_settings) {
			return -1;
		}

		res = slave_dev->ethtool_ops->get_settings(slave_dev, &etool);
		if (res < 0) {
			return -1;
		}

		goto verify;
	}

	ioctl = slave_dev->do_ioctl;
	strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
	etool.cmd = ETHTOOL_GSET;
	ifr.ifr_data = (char*)&etool;
	if (!ioctl || (IOCTL(slave_dev, &ifr, SIOCETHTOOL) < 0)) {
		return -1;
	}

verify:
	switch (etool.speed) {
	case SPEED_10:
	case SPEED_100:
	case SPEED_1000:
		break;
	default:
		return -1;
	}

	switch (etool.duplex) {
	case DUPLEX_FULL:
	case DUPLEX_HALF:
		break;
	default:
		return -1;
	}

	slave->speed = etool.speed;
	slave->duplex = etool.duplex;

	return 0;
}

/*
 * if <dev> supports MII link status reporting, check its link status.
 *
 * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(),
 * depening upon the setting of the use_carrier parameter.
 *
 * Return either BMSR_LSTATUS, meaning that the link is up (or we
 * can't tell and just pretend it is), or 0, meaning that the link is
 * down.
 *
 * If reporting is non-zero, instead of faking link up, return -1 if
 * both ETHTOOL and MII ioctls fail (meaning the device does not
 * support them).  If use_carrier is set, return whatever it says.
 * It'd be nice if there was a good way to tell if a driver supports
 * netif_carrier, but there really isn't.
 */
static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_dev, int reporting)
{
	static int (* ioctl)(struct net_device *, struct ifreq *, int);
	struct ifreq ifr;
	struct mii_ioctl_data *mii;
	struct ethtool_value etool;

	if (bond->params.use_carrier) {
		return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;
	}

	ioctl = slave_dev->do_ioctl;
	if (ioctl) {
		/* TODO: set pointer to correct ioctl on a per team member */
		/*       bases to make this more efficient. that is, once  */
		/*       we determine the correct ioctl, we will always    */
		/*       call it and not the others for that team          */
		/*       member.                                           */

		/*
		 * We cannot assume that SIOCGMIIPHY will also read a
		 * register; not all network drivers (e.g., e100)
		 * support that.
		 */

		/* Yes, the mii is overlaid on the ifreq.ifr_ifru */
		strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
		mii = if_mii(&ifr);
		if (IOCTL(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
			mii->reg_num = MII_BMSR;
			if (IOCTL(slave_dev, &ifr, SIOCGMIIREG) == 0) {
				return (mii->val_out & BMSR_LSTATUS);
			}
		}
	}

	/* try SIOCETHTOOL ioctl, some drivers cache ETHTOOL_GLINK */
	/* for a period of time so we attempt to get link status   */
	/* from it last if the above MII ioctls fail...            */
	if (slave_dev->ethtool_ops) {
		if (slave_dev->ethtool_ops->get_link) {
			u32 link;

			link = slave_dev->ethtool_ops->get_link(slave_dev);

			return link ? BMSR_LSTATUS : 0;
		}
	}

	if (ioctl) {
		strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
		etool.cmd = ETHTOOL_GLINK;
		ifr.ifr_data = (char*)&etool;
		if (IOCTL(slave_dev, &ifr, SIOCETHTOOL) == 0) {
			if (etool.data == 1) {
				return BMSR_LSTATUS;
			} else {
				dprintk("SIOCETHTOOL shows link down\n");
				return 0;
			}
		}
	}

	/*
	 * If reporting, report that either there's no dev->do_ioctl,
	 * or both SIOCGMIIREG and SIOCETHTOOL failed (meaning that we
	 * cannot report link status).  If not reporting, pretend
	 * we're ok.
	 */
	return (reporting ? -1 : BMSR_LSTATUS);
}

/*----------------------------- Multicast list ------------------------------*/

/*
 * Returns 0 if dmi1 and dmi2 are the same, non-0 otherwise
 */
static inline int bond_is_dmi_same(struct dev_mc_list *dmi1, struct dev_mc_list *dmi2)
{
	return memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0 &&
			dmi1->dmi_addrlen == dmi2->dmi_addrlen;
}

/*
 * returns dmi entry if found, NULL otherwise
 */
static struct dev_mc_list *bond_mc_list_find_dmi(struct dev_mc_list *dmi, struct dev_mc_list *mc_list)
{
	struct dev_mc_list *idmi;

	for (idmi = mc_list; idmi; idmi = idmi->next) {
		if (bond_is_dmi_same(dmi, idmi)) {
			return idmi;
		}
	}

	return NULL;
}

/*
 * Push the promiscuity flag down to appropriate slaves
 */
static void bond_set_promiscuity(struct bonding *bond, int inc)
{
	if (USES_PRIMARY(bond->params.mode)) {
		/* write lock already acquired */
		if (bond->curr_active_slave) {
			dev_set_promiscuity(bond->curr_active_slave->dev, inc);
		}
	} else {
		struct slave *slave;
		int i;
		bond_for_each_slave(bond, slave, i) {
			dev_set_promiscuity(slave->dev, inc);
		}
	}
}

/*
 * Push the allmulti flag down to all slaves
 */
static void bond_set_allmulti(struct bonding *bond, int inc)
{
	if (USES_PRIMARY(bond->params.mode)) {
		/* write lock already acquired */
		if (bond->curr_active_slave) {
			dev_set_allmulti(bond->curr_active_slave->dev, inc);
		}
	} else {
		struct slave *slave;
		int i;
		bond_for_each_slave(bond, slave, i) {
			dev_set_allmulti(slave->dev, inc);
		}
	}
}

/*
 * Add a Multicast address to slaves
 * according to mode
 */
static void bond_mc_add(struct bonding *bond, void *addr, int alen)
{
	if (USES_PRIMARY(bond->params.mode)) {
		/* write lock already acquired */
		if (bond->curr_active_slave) {
			dev_mc_add(bond->curr_active_slave->dev, addr, alen, 0);
		}
	} else {
		struct slave *slave;
		int i;
		bond_for_each_slave(bond, slave, i) {
			dev_mc_add(slave->dev, addr, alen, 0);
		}
	}
}

/*
 * Remove a multicast address from slave
 * according to mode
 */
static void bond_mc_delete(struct bonding *bond, void *addr, int alen)
{
	if (USES_PRIMARY(bond->params.mode)) {
		/* write lock already acquired */
		if (bond->curr_active_slave) {
			dev_mc_delete(bond->curr_active_slave->dev, addr, alen, 0);
		}
	} else {
		struct slave *slave;
		int i;
		bond_for_each_slave(bond, slave, i) {
			dev_mc_delete(slave->dev, addr, alen, 0);
		}
	}
}

/*
 * Totally destroys the mc_list in bond
 */
static void bond_mc_list_destroy(struct bonding *bond)
{
	struct dev_mc_list *dmi;

	dmi = bond->mc_list;
	while (dmi) {
		bond->mc_list = dmi->next;
		kfree(dmi);
		dmi = bond->mc_list;
	}
}

/*
 * Copy all the Multicast addresses from src to the bonding device dst
 */
static int bond_mc_list_copy(struct dev_mc_list *mc_list, struct bonding *bond,
			     gfp_t gfp_flag)
{
	struct dev_mc_list *dmi, *new_dmi;

	for (dmi = mc_list; dmi; dmi = dmi->next) {
		new_dmi = kmalloc(sizeof(struct dev_mc_list), gfp_flag);

		if (!new_dmi) {
			/* FIXME: Potential memory leak !!! */
			return -ENOMEM;
		}

		new_dmi->next = bond->mc_list;
		bond->mc_list = new_dmi;
		new_dmi->dmi_addrlen = dmi->dmi_addrlen;
		memcpy(new_dmi->dmi_addr, dmi->dmi_addr, dmi->dmi_addrlen);
		new_dmi->dmi_users = dmi->dmi_users;
		new_dmi->dmi_gusers = dmi->dmi_gusers;
	}

	return 0;
}

/*
 * flush all members of flush->mc_list from device dev->mc_list
 */
static void bond_mc_list_flush(struct net_device *bond_dev, struct net_device *slave_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct dev_mc_list *dmi;

	for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) {
		dev_mc_delete(slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
	}

	if (bond->params.mode == BOND_MODE_8023AD) {
		/* del lacpdu mc addr from mc list */
		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;

		dev_mc_delete(slave_dev, lacpdu_multicast, ETH_ALEN, 0);
	}
}

/*--------------------------- Active slave change ---------------------------*/

/*
 * Update the mc list and multicast-related flags for the new and
 * old active slaves (if any) according to the multicast mode, and
 * promiscuous flags unconditionally.
 */
static void bond_mc_swap(struct bonding *bond, struct slave *new_active, struct slave *old_active)
{
	struct dev_mc_list *dmi;

	if (!USES_PRIMARY(bond->params.mode)) {
		/* nothing to do -  mc list is already up-to-date on
		 * all slaves
		 */
		return;
	}

	if (old_active) {
		if (bond->dev->flags & IFF_PROMISC) {
			dev_set_promiscuity(old_active->dev, -1);
		}

		if (bond->dev->flags & IFF_ALLMULTI) {
			dev_set_allmulti(old_active->dev, -1);
		}

		for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) {
			dev_mc_delete(old_active->dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
		}
	}

	if (new_active) {
		if (bond->dev->flags & IFF_PROMISC) {
			dev_set_promiscuity(new_active->dev, 1);
		}

		if (bond->dev->flags & IFF_ALLMULTI) {
			dev_set_allmulti(new_active->dev, 1);
		}

		for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) {
			dev_mc_add(new_active->dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
		}
	}
}

/**
 * find_best_interface - select the best available slave to be the active one
 * @bond: our bonding struct
 *
 * Warning: Caller must hold curr_slave_lock for writing.
 */
static struct slave *bond_find_best_slave(struct bonding *bond)
{
	struct slave *new_active, *old_active;
	struct slave *bestslave = NULL;
	int mintime = bond->params.updelay;
	int i;

	new_active = old_active = bond->curr_active_slave;

	if (!new_active) { /* there were no active slaves left */
		if (bond->slave_cnt > 0) {  /* found one slave */
			new_active = bond->first_slave;
		} else {
			return NULL; /* still no slave, return NULL */
		}
	}

	/* first try the primary link; if arping, a link must tx/rx traffic
	 * before it can be considered the curr_active_slave - also, we would skip
	 * slaves between the curr_active_slave and primary_slave that may be up
	 * and able to arp
	 */
	if ((bond->primary_slave) &&
	    (!bond->params.arp_interval) &&
	    (IS_UP(bond->primary_slave->dev))) {
		new_active = bond->primary_slave;
	}

	/* remember where to stop iterating over the slaves */
	old_active = new_active;

	bond_for_each_slave_from(bond, new_active, i, old_active) {
		if (IS_UP(new_active->dev)) {
			if (new_active->link == BOND_LINK_UP) {
				return new_active;
			} else if (new_active->link == BOND_LINK_BACK) {
				/* link up, but waiting for stabilization */
				if (new_active->delay < mintime) {
					mintime = new_active->delay;
					bestslave = new_active;
				}
			}
		}
	}

	return bestslave;
}

/**
 * change_active_interface - change the active slave into the specified one
 * @bond: our bonding struct
 * @new: the new slave to make the active one
 *
 * Set the new slave to the bond's settings and unset them on the old
 * curr_active_slave.
 * Setting include flags, mc-list, promiscuity, allmulti, etc.
 *
 * If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP,
 * because it is apparently the best available slave we have, even though its
 * updelay hasn't timed out yet.
 *
 * Warning: Caller must hold curr_slave_lock for writing.
 */
void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
{
	struct slave *old_active = bond->curr_active_slave;

	if (old_active == new_active) {
		return;
	}

	if (new_active) {
		if (new_active->link == BOND_LINK_BACK) {
			if (USES_PRIMARY(bond->params.mode)) {
				printk(KERN_INFO DRV_NAME
				       ": %s: making interface %s the new "
				       "active one %d ms earlier.\n",
				       bond->dev->name, new_active->dev->name,
				       (bond->params.updelay - new_active->delay) * bond->params.miimon);
			}

			new_active->delay = 0;
			new_active->link = BOND_LINK_UP;
			new_active->jiffies = jiffies;

			if (bond->params.mode == BOND_MODE_8023AD) {
				bond_3ad_handle_link_change(new_active, BOND_LINK_UP);
			}

			if ((bond->params.mode == BOND_MODE_TLB) ||
			    (bond->params.mode == BOND_MODE_ALB)) {
				bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP);
			}
		} else {
			if (USES_PRIMARY(bond->params.mode)) {
				printk(KERN_INFO DRV_NAME
				       ": %s: making interface %s the new "
				       "active one.\n",
				       bond->dev->name, new_active->dev->name);
			}
		}
	}

	if (USES_PRIMARY(bond->params.mode)) {
		bond_mc_swap(bond, new_active, old_active);
	}

	if ((bond->params.mode == BOND_MODE_TLB) ||
	    (bond->params.mode == BOND_MODE_ALB)) {
		bond_alb_handle_active_change(bond, new_active);
	} else {
		bond->curr_active_slave = new_active;
	}

	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
		if (old_active) {
			bond_set_slave_inactive_flags(old_active);
		}

		if (new_active) {
			bond_set_slave_active_flags(new_active);
		}
		bond_send_gratuitous_arp(bond);
	}
}

/**
 * bond_select_active_slave - select a new active slave, if needed
 * @bond: our bonding struct
 *
 * This functions shoud be called when one of the following occurs:
 * - The old curr_active_slave has been released or lost its link.
 * - The primary_slave has got its link back.
 * - A slave has got its link back and there's no old curr_active_slave.
 *
 * Warning: Caller must hold curr_slave_lock for writing.
 */
void bond_select_active_slave(struct bonding *bond)
{
	struct slave *best_slave;

	best_slave = bond_find_best_slave(bond);
	if (best_slave != bond->curr_active_slave) {
		bond_change_active_slave(bond, best_slave);
	}
}

/*--------------------------- slave list handling ---------------------------*/

/*
 * This function attaches the slave to the end of list.
 *
 * bond->lock held for writing by caller.
 */
static void bond_attach_slave(struct bonding *bond, struct slave *new_slave)
{
	if (bond->first_slave == NULL) { /* attaching the first slave */
		new_slave->next = new_slave;
		new_slave->prev = new_slave;
		bond->first_slave = new_slave;
	} else {
		new_slave->next = bond->first_slave;
		new_slave->prev = bond->first_slave->prev;
		new_slave->next->prev = new_slave;
		new_slave->prev->next = new_slave;
	}

	bond->slave_cnt++;
}

/*
 * This function detaches the slave from the list.
 * WARNING: no check is made to verify if the slave effectively
 * belongs to <bond>.
 * Nothing is freed on return, structures are just unchained.
 * If any slave pointer in bond was pointing to <slave>,
 * it should be changed by the calling function.
 *
 * bond->lock held for writing by caller.
 */
static void bond_detach_slave(struct bonding *bond, struct slave *slave)
{
	if (slave->next) {
		slave->next->prev = slave->prev;
	}

	if (slave->prev) {
		slave->prev->next = slave->next;
	}

	if (bond->first_slave == slave) { /* slave is the first slave */
		if (bond->slave_cnt > 1) { /* there are more slave */
			bond->first_slave = slave->next;
		} else {
			bond->first_slave = NULL; /* slave was the last one */
		}
	}

	slave->next = NULL;
	slave->prev = NULL;
	bond->slave_cnt--;
}

/*---------------------------------- IOCTL ----------------------------------*/

int bond_sethwaddr(struct net_device *bond_dev, struct net_device *slave_dev)
{
	dprintk("bond_dev=%p\n", bond_dev);
	dprintk("slave_dev=%p\n", slave_dev);
	dprintk("slave_dev->addr_len=%d\n", slave_dev->addr_len);
	memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
	return 0;
}

#define BOND_INTERSECT_FEATURES \
	(NETIF_F_SG|NETIF_F_IP_CSUM|NETIF_F_NO_CSUM|NETIF_F_HW_CSUM|\
	NETIF_F_TSO|NETIF_F_UFO)

/* 
 * Compute the common dev->feature set available to all slaves.  Some
 * feature bits are managed elsewhere, so preserve feature bits set on
 * master device that are not part of the examined set.
 */
static int bond_compute_features(struct bonding *bond)
{
	unsigned long features = BOND_INTERSECT_FEATURES;
	struct slave *slave;
	struct net_device *bond_dev = bond->dev;
	int i;

	bond_for_each_slave(bond, slave, i)
		features &= (slave->dev->features & BOND_INTERSECT_FEATURES);

	if ((features & NETIF_F_SG) && 
	    !(features & (NETIF_F_IP_CSUM |
			  NETIF_F_NO_CSUM |
			  NETIF_F_HW_CSUM)))
		features &= ~NETIF_F_SG;

	/* 
	 * features will include NETIF_F_TSO (NETIF_F_UFO) iff all 
	 * slave devices support NETIF_F_TSO (NETIF_F_UFO), which 
	 * implies that all slaves also support scatter-gather 
	 * (NETIF_F_SG), which implies that features also includes 
	 * NETIF_F_SG. So no need to check whether we have an  
	 * illegal combination of NETIF_F_{TSO,UFO} and 
	 * !NETIF_F_SG 
	 */

	features |= (bond_dev->features & ~BOND_INTERSECT_FEATURES);
	bond_dev->features = features;

	return 0;
}

/* enslave device <slave> to bond device <master> */
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *new_slave = NULL;
	struct dev_mc_list *dmi;
	struct sockaddr addr;
	int link_reporting;
	int old_features = bond_dev->features;
	int res = 0;

	if (!bond->params.use_carrier && slave_dev->ethtool_ops == NULL &&
		slave_dev->do_ioctl == NULL) {
		printk(KERN_WARNING DRV_NAME
		       ": %s: Warning: no link monitoring support for %s\n",
		       bond_dev->name, slave_dev->name);
	}

	/* bond must be initialized by bond_open() before enslaving */
	if (!(bond_dev->flags & IFF_UP)) {
		dprintk("Error, master_dev is not up\n");
		return -EPERM;
	}

	/* already enslaved */
	if (slave_dev->flags & IFF_SLAVE) {
		dprintk("Error, Device was already enslaved\n");
		return -EBUSY;
	}

	/* vlan challenged mutual exclusion */
	/* no need to lock since we're protected by rtnl_lock */
	if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
		dprintk("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
		if (!list_empty(&bond->vlan_list)) {
			printk(KERN_ERR DRV_NAME
			       ": %s: Error: cannot enslave VLAN "
			       "challenged slave %s on VLAN enabled "
			       "bond %s\n", bond_dev->name, slave_dev->name,
			       bond_dev->name);
			return -EPERM;
		} else {
			printk(KERN_WARNING DRV_NAME
			       ": %s: Warning: enslaved VLAN challenged "
			       "slave %s. Adding VLANs will be blocked as "
			       "long as %s is part of bond %s\n",
			       bond_dev->name, slave_dev->name, slave_dev->name,
			       bond_dev->name);
			bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
		}
	} else {
		dprintk("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
		if (bond->slave_cnt == 0) {
			/* First slave, and it is not VLAN challenged,
			 * so remove the block of adding VLANs over the bond.
			 */
			bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
		}
	}

	/*
	 * Old ifenslave binaries are no longer supported.  These can
	 * be identified with moderate accurary by the state of the slave:
	 * the current ifenslave will set the interface down prior to
	 * enslaving it; the old ifenslave will not.
	 */
	if ((slave_dev->flags & IFF_UP)) {
		printk(KERN_ERR DRV_NAME ": %s is up. "
		       "This may be due to an out of date ifenslave.\n",
		       slave_dev->name);
		res = -EPERM;
		goto err_undo_flags;
	}

	if (slave_dev->set_mac_address == NULL) {
		printk(KERN_ERR DRV_NAME
			": %s: Error: The slave device you specified does "
			"not support setting the MAC address. "
			"Your kernel likely does not support slave "
			"devices.\n", bond_dev->name);
  		res = -EOPNOTSUPP;
		goto err_undo_flags;
	}

	new_slave = kmalloc(sizeof(struct slave), GFP_KERNEL);
	if (!new_slave) {
		res = -ENOMEM;
		goto err_undo_flags;
	}

	memset(new_slave, 0, sizeof(struct slave));

	/* save slave's original flags before calling
	 * netdev_set_master and dev_open
	 */
	new_slave->original_flags = slave_dev->flags;

	/*
	 * Save slave's original ("permanent") mac address for modes
	 * that need it, and for restoring it upon release, and then
	 * set it to the master's address
	 */
	memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN);

	/*
	 * Set slave to master's mac address.  The application already
	 * set the master's mac address to that of the first slave
	 */
	memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
	addr.sa_family = slave_dev->type;
	res = dev_set_mac_address(slave_dev, &addr);
	if (res) {
		dprintk("Error %d calling set_mac_address\n", res);
		goto err_free;
	}

	/* open the slave since the application closed it */
	res = dev_open(slave_dev);
	if (res) {
		dprintk("Openning slave %s failed\n", slave_dev->name);
		goto err_restore_mac;
	}

	res = netdev_set_master(slave_dev, bond_dev);
	if (res) {
		dprintk("Error %d calling netdev_set_master\n", res);
		goto err_close;
	}

	new_slave->dev = slave_dev;

	if ((bond->params.mode == BOND_MODE_TLB) ||
	    (bond->params.mode == BOND_MODE_ALB)) {
		/* bond_alb_init_slave() must be called before all other stages since
		 * it might fail and we do not want to have to undo everything
		 */
		res = bond_alb_init_slave(bond, new_slave);
		if (res) {
			goto err_unset_master;
		}
	}

	/* If the mode USES_PRIMARY, then the new slave gets the
	 * master's promisc (and mc) settings only if it becomes the
	 * curr_active_slave, and that is taken care of later when calling
	 * bond_change_active()
	 */
	if (!USES_PRIMARY(bond->params.mode)) {
		/* set promiscuity level to new slave */
		if (bond_dev->flags & IFF_PROMISC) {
			dev_set_promiscuity(slave_dev, 1);
		}

		/* set allmulti level to new slave */
		if (bond_dev->flags & IFF_ALLMULTI) {
			dev_set_allmulti(slave_dev, 1);
		}

		/* upload master's mc_list to new slave */
		for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) {
			dev_mc_add (slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0);
		}
	}

	if (bond->params.mode == BOND_MODE_8023AD) {
		/* add lacpdu mc addr to mc list */
		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;

		dev_mc_add(slave_dev, lacpdu_multicast, ETH_ALEN, 0);
	}

	bond_add_vlans_on_slave(bond, slave_dev);

	write_lock_bh(&bond->lock);

	bond_attach_slave(bond, new_slave);

	new_slave->delay = 0;
	new_slave->link_failure_count = 0;

	bond_compute_features(bond);

	if (bond->params.miimon && !bond->params.use_carrier) {
		link_reporting = bond_check_dev_link(bond, slave_dev, 1);

		if ((link_reporting == -1) && !bond->params.arp_interval) {
			/*
			 * miimon is set but a bonded network driver
			 * does not support ETHTOOL/MII and
			 * arp_interval is not set.  Note: if
			 * use_carrier is enabled, we will never go
			 * here (because netif_carrier is always
			 * supported); thus, we don't need to change
			 * the messages for netif_carrier.
			 */
			printk(KERN_WARNING DRV_NAME
			       ": %s: Warning: MII and ETHTOOL support not "
			       "available for interface %s, and "
			       "arp_interval/arp_ip_target module parameters "
			       "not specified, thus bonding will not detect "
			       "link failures! see bonding.txt for details.\n",
			       bond_dev->name, slave_dev->name);
		} else if (link_reporting == -1) {
			/* unable get link status using mii/ethtool */
			printk(KERN_WARNING DRV_NAME
			       ": %s: Warning: can't get link status from "
			       "interface %s; the network driver associated "
			       "with this interface does not support MII or "
			       "ETHTOOL link status reporting, thus miimon "
			       "has no effect on this interface.\n",
			       bond_dev->name, slave_dev->name);
		}
	}

	/* check for initial state */
	if (!bond->params.miimon ||
	    (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS)) {
		if (bond->params.updelay) {
			dprintk("Initial state of slave_dev is "
				"BOND_LINK_BACK\n");
			new_slave->link  = BOND_LINK_BACK;
			new_slave->delay = bond->params.updelay;
		} else {
			dprintk("Initial state of slave_dev is "
				"BOND_LINK_UP\n");
			new_slave->link  = BOND_LINK_UP;
		}
		new_slave->jiffies = jiffies;
	} else {
		dprintk("Initial state of slave_dev is "
			"BOND_LINK_DOWN\n");
		new_slave->link  = BOND_LINK_DOWN;
	}

	if (bond_update_speed_duplex(new_slave) &&
	    (new_slave->link != BOND_LINK_DOWN)) {
		printk(KERN_WARNING DRV_NAME
		       ": %s: Warning: failed to get speed and duplex from %s, "
		       "assumed to be 100Mb/sec and Full.\n",
		       bond_dev->name, new_slave->dev->name);

		if (bond->params.mode == BOND_MODE_8023AD) {
			printk(KERN_WARNING DRV_NAME
			       ": %s: Warning: Operation of 802.3ad mode requires ETHTOOL "
			       "support in base driver for proper aggregator "
			       "selection.\n", bond_dev->name);
		}
	}

	if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
		/* if there is a primary slave, remember it */
		if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
			bond->primary_slave = new_slave;
		}
	}

	switch (bond->params.mode) {
	case BOND_MODE_ACTIVEBACKUP:
		/* if we're in active-backup mode, we need one and only one active
		 * interface. The backup interfaces will have their NOARP flag set
		 * because we need them to be completely deaf and not to respond to
		 * any ARP request on the network to avoid fooling a switch. Thus,
		 * since we guarantee that curr_active_slave always point to the last
		 * usable interface, we just have to verify this interface's flag.
		 */
		if (((!bond->curr_active_slave) ||
		     (bond->curr_active_slave->dev->flags & IFF_NOARP)) &&
		    (new_slave->link != BOND_LINK_DOWN)) {
			dprintk("This is the first active slave\n");
			/* first slave or no active slave yet, and this link
			   is OK, so make this interface the active one */
			bond_change_active_slave(bond, new_slave);
		} else {
			dprintk("This is just a backup slave\n");
			bond_set_slave_inactive_flags(new_slave);
		}
		break;
	case BOND_MODE_8023AD:
		/* in 802.3ad mode, the internal mechanism
		 * will activate the slaves in the selected
		 * aggregator
		 */
		bond_set_slave_inactive_flags(new_slave);
		/* if this is the first slave */
		if (bond->slave_cnt == 1) {
			SLAVE_AD_INFO(new_slave).id = 1;
			/* Initialize AD with the number of times that the AD timer is called in 1 second
			 * can be called only after the mac address of the bond is set
			 */
			bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL,
					    bond->params.lacp_fast);
		} else {
			SLAVE_AD_INFO(new_slave).id =
				SLAVE_AD_INFO(new_slave->prev).id + 1;
		}

		bond_3ad_bind_slave(new_slave);
		break;
	case BOND_MODE_TLB:
	case BOND_MODE_ALB:
		new_slave->state = BOND_STATE_ACTIVE;
		if ((!bond->curr_active_slave) &&
		    (new_slave->link != BOND_LINK_DOWN)) {
			/* first slave or no active slave yet, and this link
			 * is OK, so make this interface the active one
			 */
			bond_change_active_slave(bond, new_slave);
		}
		break;
	default:
		dprintk("This slave is always active in trunk mode\n");

		/* always active in trunk mode */
		new_slave->state = BOND_STATE_ACTIVE;

		/* In trunking mode there is little meaning to curr_active_slave
		 * anyway (it holds no special properties of the bond device),
		 * so we can change it without calling change_active_interface()
		 */
		if (!bond->curr_active_slave) {
			bond->curr_active_slave = new_slave;
		}
		break;
	} /* switch(bond_mode) */

	write_unlock_bh(&bond->lock);

	res = bond_create_slave_symlinks(bond_dev, slave_dev);
	if (res)
		goto err_unset_master;

	printk(KERN_INFO DRV_NAME
	       ": %s: enslaving %s as a%s interface with a%s link.\n",
	       bond_dev->name, slave_dev->name,
	       new_slave->state == BOND_STATE_ACTIVE ? "n active" : " backup",
	       new_slave->link != BOND_LINK_DOWN ? "n up" : " down");

	/* enslave is successful */
	return 0;

/* Undo stages on error */
err_unset_master:
	netdev_set_master(slave_dev, NULL);

err_close:
	dev_close(slave_dev);

err_restore_mac:
	memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
	addr.sa_family = slave_dev->type;
	dev_set_mac_address(slave_dev, &addr);

err_free:
	kfree(new_slave);

err_undo_flags:
	bond_dev->features = old_features;
 
	return res;
}

/*
 * Try to release the slave device <slave> from the bond device <master>
 * It is legal to access curr_active_slave without a lock because all the function
 * is write-locked.
 *
 * The rules for slave state should be:
 *   for Active/Backup:
 *     Active stays on all backups go down
 *   for Bonded connections:
 *     The first up interface should be left on and all others downed.
 */
int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave, *oldcurrent;
	struct sockaddr addr;
	int mac_addr_differ;

	/* slave is not a slave or master is not master of this slave */
	if (!(slave_dev->flags & IFF_SLAVE) ||
	    (slave_dev->master != bond_dev)) {
		printk(KERN_ERR DRV_NAME
		       ": %s: Error: cannot release %s.\n",
		       bond_dev->name, slave_dev->name);
		return -EINVAL;
	}

	write_lock_bh(&bond->lock);

	slave = bond_get_slave_by_dev(bond, slave_dev);
	if (!slave) {
		/* not a slave of this bond */
		printk(KERN_INFO DRV_NAME
		       ": %s: %s not enslaved\n",
		       bond_dev->name, slave_dev->name);
		write_unlock_bh(&bond->lock);
		return -EINVAL;
	}

	mac_addr_differ = memcmp(bond_dev->dev_addr,
				 slave->perm_hwaddr,
				 ETH_ALEN);
	if (!mac_addr_differ && (bond->slave_cnt > 1)) {
		printk(KERN_WARNING DRV_NAME
		       ": %s: Warning: the permanent HWaddr of %s "
		       "- %02X:%02X:%02X:%02X:%02X:%02X - is "
		       "still in use by %s. Set the HWaddr of "
		       "%s to a different address to avoid "
		       "conflicts.\n",
		       bond_dev->name,
		       slave_dev->name,
		       slave->perm_hwaddr[0],
		       slave->perm_hwaddr[1],
		       slave->perm_hwaddr[2],
		       slave->perm_hwaddr[3],
		       slave->perm_hwaddr[4],
		       slave->perm_hwaddr[5],
		       bond_dev->name,
		       slave_dev->name);
	}

	/* Inform AD package of unbinding of slave. */
	if (bond->params.mode == BOND_MODE_8023AD) {
		/* must be called before the slave is
		 * detached from the list
		 */
		bond_3ad_unbind_slave(slave);
	}

	printk(KERN_INFO DRV_NAME
	       ": %s: releasing %s interface %s\n",
	       bond_dev->name,
	       (slave->state == BOND_STATE_ACTIVE)
	       ? "active" : "backup",
	       slave_dev->name);

	oldcurrent = bond->curr_active_slave;

	bond->current_arp_slave = NULL;

	/* release the slave from its bond */
	bond_detach_slave(bond, slave);

	bond_compute_features(bond);

	if (bond->primary_slave == slave) {
		bond->primary_slave = NULL;
	}

	if (oldcurrent == slave) {
		bond_change_active_slave(bond, NULL);
	}

	if ((bond->params.mode == BOND_MODE_TLB) ||
	    (bond->params.mode == BOND_MODE_ALB)) {
		/* Must be called only after the slave has been
		 * detached from the list and the curr_active_slave
		 * has been cleared (if our_slave == old_current),
		 * but before a new active slave is selected.
		 */
		bond_alb_deinit_slave(bond, slave);
	}

	if (oldcurrent == slave) {
		bond_select_active_slave(bond);

		if (!bond->curr_active_slave) {
			printk(KERN_INFO DRV_NAME
			       ": %s: now running without any active "
			       "interface !\n",
			       bond_dev->name);
		}
	}

	if (bond->slave_cnt == 0) {
		/* if the last slave was removed, zero the mac address
		 * of the master so it will be set by the application
		 * to the mac address of the first slave
		 */
		memset(bond_dev->dev_addr, 0, bond_dev->addr_len);

		if (list_empty(&bond->vlan_list)) {
			bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
		} else {
			printk(KERN_WARNING DRV_NAME
			       ": %s: Warning: clearing HW address of %s while it "
			       "still has VLANs.\n",
			       bond_dev->name, bond_dev->name);
			printk(KERN_WARNING DRV_NAME
			       ": %s: When re-adding slaves, make sure the bond's "
			       "HW address matches its VLANs'.\n",
			       bond_dev->name);
		}
	} else if ((bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
		   !bond_has_challenged_slaves(bond)) {
		printk(KERN_INFO DRV_NAME
		       ": %s: last VLAN challenged slave %s "
		       "left bond %s. VLAN blocking is removed\n",
		       bond_dev->name, slave_dev->name, bond_dev->name);
		bond_dev->features &= ~NETIF_F_VLAN_CHALLENGED;
	}

	write_unlock_bh(&bond->lock);

	/* must do this from outside any spinlocks */
	bond_destroy_slave_symlinks(bond_dev, slave_dev);

	bond_del_vlans_from_slave(bond, slave_dev);

	/* If the mode USES_PRIMARY, then we should only remove its
	 * promisc and mc settings if it was the curr_active_slave, but that was
	 * already taken care of above when we detached the slave
	 */
	if (!USES_PRIMARY(bond->params.mode)) {
		/* unset promiscuity level from slave */
		if (bond_dev->flags & IFF_PROMISC) {
			dev_set_promiscuity(slave_dev, -1);
		}

		/* unset allmulti level from slave */
		if (bond_dev->flags & IFF_ALLMULTI) {
			dev_set_allmulti(slave_dev, -1);
		}

		/* flush master's mc_list from slave */
		bond_mc_list_flush(bond_dev, slave_dev);
	}

	netdev_set_master(slave_dev, NULL);

	/* close slave before restoring its mac address */
	dev_close(slave_dev);

	/* restore original ("permanent") mac address */
	memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
	addr.sa_family = slave_dev->type;
	dev_set_mac_address(slave_dev, &addr);

	/* restore the original state of the
	 * IFF_NOARP flag that might have been
	 * set by bond_set_slave_inactive_flags()
	 */
	if ((slave->original_flags & IFF_NOARP) == 0) {
		slave_dev->flags &= ~IFF_NOARP;
	}

	kfree(slave);

	return 0;  /* deletion OK */
}

/*
 * This function releases all slaves.
 */
static int bond_release_all(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave;
	struct net_device *slave_dev;
	struct sockaddr addr;

	write_lock_bh(&bond->lock);

	if (bond->slave_cnt == 0) {
		goto out;
	}

	bond->current_arp_slave = NULL;
	bond->primary_slave = NULL;
	bond_change_active_slave(bond, NULL);

	while ((slave = bond->first_slave) != NULL) {
		/* Inform AD package of unbinding of slave
		 * before slave is detached from the list.
		 */
		if (bond->params.mode == BOND_MODE_8023AD) {
			bond_3ad_unbind_slave(slave);
		}

		slave_dev = slave->dev;
		bond_detach_slave(bond, slave);

		if ((bond->params.mode == BOND_MODE_TLB) ||
		    (bond->params.mode == BOND_MODE_ALB)) {
			/* must be called only after the slave
			 * has been detached from the list
			 */
			bond_alb_deinit_slave(bond, slave);
		}

		bond_compute_features(bond);

		/* now that the slave is detached, unlock and perform
		 * all the undo steps that should not be called from
		 * within a lock.
		 */
		write_unlock_bh(&bond->lock);

		bond_destroy_slave_symlinks(bond_dev, slave_dev);
		bond_del_vlans_from_slave(bond, slave_dev);

		/* If the mode USES_PRIMARY, then we should only remove its
		 * promisc and mc settings if it was the curr_active_slave, but that was
		 * already taken care of above when we detached the slave
		 */
		if (!USES_PRIMARY(bond->params.mode)) {
			/* unset promiscuity level from slave */
			if (bond_dev->flags & IFF_PROMISC) {
				dev_set_promiscuity(slave_dev, -1);
			}

			/* unset allmulti level from slave */
			if (bond_dev->flags & IFF_ALLMULTI) {
				dev_set_allmulti(slave_dev, -1);
			}

			/* flush master's mc_list from slave */
			bond_mc_list_flush(bond_dev, slave_dev);
		}

		netdev_set_master(slave_dev, NULL);

		/* close slave before restoring its mac address */
		dev_close(slave_dev);

		/* restore original ("permanent") mac address*/
		memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
		addr.sa_family = slave_dev->type;
		dev_set_mac_address(slave_dev, &addr);

		/* restore the original state of the IFF_NOARP flag that might have
		 * been set by bond_set_slave_inactive_flags()
		 */
		if ((slave->original_flags & IFF_NOARP) == 0) {
			slave_dev->flags &= ~IFF_NOARP;
		}

		kfree(slave);

		/* re-acquire the lock before getting the next slave */
		write_lock_bh(&bond->lock);
	}

	/* zero the mac address of the master so it will be
	 * set by the application to the mac address of the
	 * first slave
	 */
	memset(bond_dev->dev_addr, 0, bond_dev->addr_len);

	if (list_empty(&bond->vlan_list)) {
		bond_dev->features |= NETIF_F_VLAN_CHALLENGED;
	} else {
		printk(KERN_WARNING DRV_NAME
		       ": %s: Warning: clearing HW address of %s while it "
		       "still has VLANs.\n",
		       bond_dev->name, bond_dev->name);
		printk(KERN_WARNING DRV_NAME
		       ": %s: When re-adding slaves, make sure the bond's "
		       "HW address matches its VLANs'.\n",
		       bond_dev->name);
	}

	printk(KERN_INFO DRV_NAME
	       ": %s: released all slaves\n",
	       bond_dev->name);

out:
	write_unlock_bh(&bond->lock);

	return 0;
}

/*
 * This function changes the active slave to slave <slave_dev>.
 * It returns -EINVAL in the following cases.
 *  - <slave_dev> is not found in the list.
 *  - There is not active slave now.
 *  - <slave_dev> is already active.
 *  - The link state of <slave_dev> is not BOND_LINK_UP.
 *  - <slave_dev> is not running.
 * In these cases, this fuction does nothing.
 * In the other cases, currnt_slave pointer is changed and 0 is returned.
 */
static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_device *slave_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *old_active = NULL;
	struct slave *new_active = NULL;
	int res = 0;

	if (!USES_PRIMARY(bond->params.mode)) {
		return -EINVAL;
	}

	/* Verify that master_dev is indeed the master of slave_dev */
	if (!(slave_dev->flags & IFF_SLAVE) ||
	    (slave_dev->master != bond_dev)) {
		return -EINVAL;
	}

	write_lock_bh(&bond->lock);

	old_active = bond->curr_active_slave;
	new_active = bond_get_slave_by_dev(bond, slave_dev);

	/*
	 * Changing to the current active: do nothing; return success.
	 */
	if (new_active && (new_active == old_active)) {
		write_unlock_bh(&bond->lock);
		return 0;
	}

	if ((new_active) &&
	    (old_active) &&
	    (new_active->link == BOND_LINK_UP) &&
	    IS_UP(new_active->dev)) {
		bond_change_active_slave(bond, new_active);
	} else {
		res = -EINVAL;
	}

	write_unlock_bh(&bond->lock);

	return res;
}

static int bond_info_query(struct net_device *bond_dev, struct ifbond *info)
{
	struct bonding *bond = bond_dev->priv;

	info->bond_mode = bond->params.mode;
	info->miimon = bond->params.miimon;

	read_lock_bh(&bond->lock);
	info->num_slaves = bond->slave_cnt;
	read_unlock_bh(&bond->lock);

	return 0;
}

static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave;
	int i, found = 0;

	if (info->slave_id < 0) {
		return -ENODEV;
	}

	read_lock_bh(&bond->lock);

	bond_for_each_slave(bond, slave, i) {
		if (i == (int)info->slave_id) {
			found = 1;
			break;
		}
	}

	read_unlock_bh(&bond->lock);

	if (found) {
		strcpy(info->slave_name, slave->dev->name);
		info->link = slave->link;
		info->state = slave->state;
		info->link_failure_count = slave->link_failure_count;
	} else {
		return -ENODEV;
	}

	return 0;
}

/*-------------------------------- Monitoring -------------------------------*/

/* this function is called regularly to monitor each slave's link. */
void bond_mii_monitor(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave, *oldcurrent;
	int do_failover = 0;
	int delta_in_ticks;
	int i;

	read_lock(&bond->lock);

	delta_in_ticks = (bond->params.miimon * HZ) / 1000;

	if (bond->kill_timers) {
		goto out;
	}

	if (bond->slave_cnt == 0) {
		goto re_arm;
	}

	/* we will try to read the link status of each of our slaves, and
	 * set their IFF_RUNNING flag appropriately. For each slave not
	 * supporting MII status, we won't do anything so that a user-space
	 * program could monitor the link itself if needed.
	 */

	read_lock(&bond->curr_slave_lock);
	oldcurrent = bond->curr_active_slave;
	read_unlock(&bond->curr_slave_lock);

	bond_for_each_slave(bond, slave, i) {
		struct net_device *slave_dev = slave->dev;
		int link_state;
		u16 old_speed = slave->speed;
		u8 old_duplex = slave->duplex;

		link_state = bond_check_dev_link(bond, slave_dev, 0);

		switch (slave->link) {
		case BOND_LINK_UP:	/* the link was up */
			if (link_state == BMSR_LSTATUS) {
				/* link stays up, nothing more to do */
				break;
			} else { /* link going down */
				slave->link  = BOND_LINK_FAIL;
				slave->delay = bond->params.downdelay;

				if (slave->link_failure_count < UINT_MAX) {
					slave->link_failure_count++;
				}

				if (bond->params.downdelay) {
					printk(KERN_INFO DRV_NAME
					       ": %s: link status down for %s "
					       "interface %s, disabling it in "
					       "%d ms.\n",
					       bond_dev->name,
					       IS_UP(slave_dev)
					       ? ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
						  ? ((slave == oldcurrent)
						     ? "active " : "backup ")
						  : "")
					       : "idle ",
					       slave_dev->name,
					       bond->params.downdelay * bond->params.miimon);
				}
			}
			/* no break ! fall through the BOND_LINK_FAIL test to
			   ensure proper action to be taken
			*/
		case BOND_LINK_FAIL:	/* the link has just gone down */
			if (link_state != BMSR_LSTATUS) {
				/* link stays down */
				if (slave->delay <= 0) {
					/* link down for too long time */
					slave->link = BOND_LINK_DOWN;

					/* in active/backup mode, we must
					 * completely disable this interface
					 */
					if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) ||
					    (bond->params.mode == BOND_MODE_8023AD)) {
						bond_set_slave_inactive_flags(slave);
					}

					printk(KERN_INFO DRV_NAME
					       ": %s: link status definitely "
					       "down for interface %s, "
					       "disabling it\n",
					       bond_dev->name,
					       slave_dev->name);

					/* notify ad that the link status has changed */
					if (bond->params.mode == BOND_MODE_8023AD) {
						bond_3ad_handle_link_change(slave, BOND_LINK_DOWN);
					}

					if ((bond->params.mode == BOND_MODE_TLB) ||
					    (bond->params.mode == BOND_MODE_ALB)) {
						bond_alb_handle_link_change(bond, slave, BOND_LINK_DOWN);
					}

					if (slave == oldcurrent) {
						do_failover = 1;
					}
				} else {
					slave->delay--;
				}
			} else {
				/* link up again */
				slave->link  = BOND_LINK_UP;
				slave->jiffies = jiffies;
				printk(KERN_INFO DRV_NAME
				       ": %s: link status up again after %d "
				       "ms for interface %s.\n",
				       bond_dev->name,
				       (bond->params.downdelay - slave->delay) * bond->params.miimon,
				       slave_dev->name);
			}
			break;
		case BOND_LINK_DOWN:	/* the link was down */
			if (link_state != BMSR_LSTATUS) {
				/* the link stays down, nothing more to do */
				break;
			} else {	/* link going up */
				slave->link  = BOND_LINK_BACK;
				slave->delay = bond->params.updelay;

				if (bond->params.updelay) {
					/* if updelay == 0, no need to
					   advertise about a 0 ms delay */
					printk(KERN_INFO DRV_NAME
					       ": %s: link status up for "
					       "interface %s, enabling it "
					       "in %d ms.\n",
					       bond_dev->name,
					       slave_dev->name,
					       bond->params.updelay * bond->params.miimon);
				}
			}
			/* no break ! fall through the BOND_LINK_BACK state in
			   case there's something to do.
			*/
		case BOND_LINK_BACK:	/* the link has just come back */
			if (link_state != BMSR_LSTATUS) {
				/* link down again */
				slave->link  = BOND_LINK_DOWN;

				printk(KERN_INFO DRV_NAME
				       ": %s: link status down again after %d "
				       "ms for interface %s.\n",
				       bond_dev->name,
				       (bond->params.updelay - slave->delay) * bond->params.miimon,
				       slave_dev->name);
			} else {
				/* link stays up */
				if (slave->delay == 0) {
					/* now the link has been up for long time enough */
					slave->link = BOND_LINK_UP;
					slave->jiffies = jiffies;

					if (bond->params.mode == BOND_MODE_8023AD) {
						/* prevent it from being the active one */
						slave->state = BOND_STATE_BACKUP;
					} else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
						/* make it immediately active */
						slave->state = BOND_STATE_ACTIVE;
					} else if (slave != bond->primary_slave) {
						/* prevent it from being the active one */
						slave->state = BOND_STATE_BACKUP;
					}

					printk(KERN_INFO DRV_NAME
					       ": %s: link status definitely "
					       "up for interface %s.\n",
					       bond_dev->name,
					       slave_dev->name);

					/* notify ad that the link status has changed */
					if (bond->params.mode == BOND_MODE_8023AD) {
						bond_3ad_handle_link_change(slave, BOND_LINK_UP);
					}

					if ((bond->params.mode == BOND_MODE_TLB) ||
					    (bond->params.mode == BOND_MODE_ALB)) {
						bond_alb_handle_link_change(bond, slave, BOND_LINK_UP);
					}

					if ((!oldcurrent) ||
					    (slave == bond->primary_slave)) {
						do_failover = 1;
					}
				} else {
					slave->delay--;
				}
			}
			break;
		default:
			/* Should not happen */
			printk(KERN_ERR DRV_NAME
			       ": %s: Error: %s Illegal value (link=%d)\n",
			       bond_dev->name,
			       slave->dev->name,
			       slave->link);
			goto out;
		} /* end of switch (slave->link) */

		bond_update_speed_duplex(slave);

		if (bond->params.mode == BOND_MODE_8023AD) {
			if (old_speed != slave->speed) {
				bond_3ad_adapter_speed_changed(slave);
			}

			if (old_duplex != slave->duplex) {
				bond_3ad_adapter_duplex_changed(slave);
			}
		}

	} /* end of for */

	if (do_failover) {
		write_lock(&bond->curr_slave_lock);

		bond_select_active_slave(bond);

		if (oldcurrent && !bond->curr_active_slave) {
			printk(KERN_INFO DRV_NAME
			       ": %s: now running without any active "
			       "interface !\n",
			       bond_dev->name);
		}

		write_unlock(&bond->curr_slave_lock);
	}

re_arm:
	if (bond->params.miimon) {
		mod_timer(&bond->mii_timer, jiffies + delta_in_ticks);
	}
out:
	read_unlock(&bond->lock);
}


static u32 bond_glean_dev_ip(struct net_device *dev)
{
	struct in_device *idev;
	struct in_ifaddr *ifa;
	u32 addr = 0;

	if (!dev)
		return 0;

	rcu_read_lock();
	idev = __in_dev_get_rcu(dev);
	if (!idev)
		goto out;

	ifa = idev->ifa_list;
	if (!ifa)
		goto out;

	addr = ifa->ifa_local;
out:
	rcu_read_unlock();
	return addr;
}

static int bond_has_ip(struct bonding *bond)
{
	struct vlan_entry *vlan, *vlan_next;

	if (bond->master_ip)
		return 1;

	if (list_empty(&bond->vlan_list))
		return 0;

	list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list,
				 vlan_list) {
		if (vlan->vlan_ip)
			return 1;
	}

	return 0;
}

/*
 * We go to the (large) trouble of VLAN tagging ARP frames because
 * switches in VLAN mode (especially if ports are configured as
 * "native" to a VLAN) might not pass non-tagged frames.
 */
static void bond_arp_send(struct net_device *slave_dev, int arp_op, u32 dest_ip, u32 src_ip, unsigned short vlan_id)
{
	struct sk_buff *skb;

	dprintk("arp %d on slave %s: dst %x src %x vid %d\n", arp_op,
	       slave_dev->name, dest_ip, src_ip, vlan_id);
	       
	skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
			 NULL, slave_dev->dev_addr, NULL);

	if (!skb) {
		printk(KERN_ERR DRV_NAME ": ARP packet allocation failed\n");
		return;
	}
	if (vlan_id) {
		skb = vlan_put_tag(skb, vlan_id);
		if (!skb) {
			printk(KERN_ERR DRV_NAME ": failed to insert VLAN tag\n");
			return;
		}
	}
	arp_xmit(skb);
}


static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
{
	int i, vlan_id, rv;
	u32 *targets = bond->params.arp_targets;
	struct vlan_entry *vlan, *vlan_next;
	struct net_device *vlan_dev;
	struct flowi fl;
	struct rtable *rt;

	for (i = 0; (i < BOND_MAX_ARP_TARGETS); i++) {
		if (!targets[i])
			continue;
		dprintk("basa: target %x\n", targets[i]);
		if (list_empty(&bond->vlan_list)) {
			dprintk("basa: empty vlan: arp_send\n");
			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
				      bond->master_ip, 0);
			continue;
		}

		/*
		 * If VLANs are configured, we do a route lookup to
		 * determine which VLAN interface would be used, so we
		 * can tag the ARP with the proper VLAN tag.
		 */
		memset(&fl, 0, sizeof(fl));
		fl.fl4_dst = targets[i];
		fl.fl4_tos = RTO_ONLINK;

		rv = ip_route_output_key(&rt, &fl);
		if (rv) {
			if (net_ratelimit()) {
				printk(KERN_WARNING DRV_NAME
			     ": %s: no route to arp_ip_target %u.%u.%u.%u\n",
				       bond->dev->name, NIPQUAD(fl.fl4_dst));
			}
			continue;
		}

		/*
		 * This target is not on a VLAN
		 */
		if (rt->u.dst.dev == bond->dev) {
			ip_rt_put(rt);
			dprintk("basa: rtdev == bond->dev: arp_send\n");
			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
				      bond->master_ip, 0);
			continue;
		}

		vlan_id = 0;
		list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list,
					 vlan_list) {
			vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id];
			if (vlan_dev == rt->u.dst.dev) {
				vlan_id = vlan->vlan_id;
				dprintk("basa: vlan match on %s %d\n",
				       vlan_dev->name, vlan_id);
				break;
			}
		}

		if (vlan_id) {
			ip_rt_put(rt);
			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
				      vlan->vlan_ip, vlan_id);
			continue;
		}

		if (net_ratelimit()) {
			printk(KERN_WARNING DRV_NAME
	       ": %s: no path to arp_ip_target %u.%u.%u.%u via rt.dev %s\n",
			       bond->dev->name, NIPQUAD(fl.fl4_dst),
			       rt->u.dst.dev ? rt->u.dst.dev->name : "NULL");
		}
		ip_rt_put(rt);
	}
}

/*
 * Kick out a gratuitous ARP for an IP on the bonding master plus one
 * for each VLAN above us.
 */
static void bond_send_gratuitous_arp(struct bonding *bond)
{
	struct slave *slave = bond->curr_active_slave;
	struct vlan_entry *vlan;
	struct net_device *vlan_dev;

	dprintk("bond_send_grat_arp: bond %s slave %s\n", bond->dev->name,
				slave ? slave->dev->name : "NULL");
	if (!slave)
		return;

	if (bond->master_ip) {
		bond_arp_send(slave->dev, ARPOP_REPLY, bond->master_ip,
				  bond->master_ip, 0);
	}

	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
		vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id];
		if (vlan->vlan_ip) {
			bond_arp_send(slave->dev, ARPOP_REPLY, vlan->vlan_ip,
				      vlan->vlan_ip, vlan->vlan_id);
		}
	}
}

/*
 * this function is called regularly to monitor each slave's link
 * ensuring that traffic is being sent and received when arp monitoring
 * is used in load-balancing mode. if the adapter has been dormant, then an
 * arp is transmitted to generate traffic. see activebackup_arp_monitor for
 * arp monitoring in active backup mode.
 */
void bond_loadbalance_arp_mon(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave, *oldcurrent;
	int do_failover = 0;
	int delta_in_ticks;
	int i;

	read_lock(&bond->lock);

	delta_in_ticks = (bond->params.arp_interval * HZ) / 1000;

	if (bond->kill_timers) {
		goto out;
	}

	if (bond->slave_cnt == 0) {
		goto re_arm;
	}

	read_lock(&bond->curr_slave_lock);
	oldcurrent = bond->curr_active_slave;
	read_unlock(&bond->curr_slave_lock);

	/* see if any of the previous devices are up now (i.e. they have
	 * xmt and rcv traffic). the curr_active_slave does not come into
	 * the picture unless it is null. also, slave->jiffies is not needed
	 * here because we send an arp on each slave and give a slave as
	 * long as it needs to get the tx/rx within the delta.
	 * TODO: what about up/down delay in arp mode? it wasn't here before
	 *       so it can wait
	 */
	bond_for_each_slave(bond, slave, i) {
		if (slave->link != BOND_LINK_UP) {
			if (((jiffies - slave->dev->trans_start) <= delta_in_ticks) &&
			    ((jiffies - slave->dev->last_rx) <= delta_in_ticks)) {

				slave->link  = BOND_LINK_UP;
				slave->state = BOND_STATE_ACTIVE;

				/* primary_slave has no meaning in round-robin
				 * mode. the window of a slave being up and
				 * curr_active_slave being null after enslaving
				 * is closed.
				 */
				if (!oldcurrent) {
					printk(KERN_INFO DRV_NAME
					       ": %s: link status definitely "
					       "up for interface %s, ",
					       bond_dev->name,
					       slave->dev->name);
					do_failover = 1;
				} else {
					printk(KERN_INFO DRV_NAME
					       ": %s: interface %s is now up\n",
					       bond_dev->name,
					       slave->dev->name);
				}
			}
		} else {
			/* slave->link == BOND_LINK_UP */

			/* not all switches will respond to an arp request
			 * when the source ip is 0, so don't take the link down
			 * if we don't know our ip yet
			 */
			if (((jiffies - slave->dev->trans_start) >= (2*delta_in_ticks)) ||
			    (((jiffies - slave->dev->last_rx) >= (2*delta_in_ticks)) &&
			     bond_has_ip(bond))) {

				slave->link  = BOND_LINK_DOWN;
				slave->state = BOND_STATE_BACKUP;

				if (slave->link_failure_count < UINT_MAX) {
					slave->link_failure_count++;
				}

				printk(KERN_INFO DRV_NAME
				       ": %s: interface %s is now down.\n",
				       bond_dev->name,
				       slave->dev->name);

				if (slave == oldcurrent) {
					do_failover = 1;
				}
			}
		}

		/* note: if switch is in round-robin mode, all links
		 * must tx arp to ensure all links rx an arp - otherwise
		 * links may oscillate or not come up at all; if switch is
		 * in something like xor mode, there is nothing we can
		 * do - all replies will be rx'ed on same link causing slaves
		 * to be unstable during low/no traffic periods
		 */
		if (IS_UP(slave->dev)) {
			bond_arp_send_all(bond, slave);
		}
	}

	if (do_failover) {
		write_lock(&bond->curr_slave_lock);

		bond_select_active_slave(bond);

		if (oldcurrent && !bond->curr_active_slave) {
			printk(KERN_INFO DRV_NAME
			       ": %s: now running without any active "
			       "interface !\n",
			       bond_dev->name);
		}

		write_unlock(&bond->curr_slave_lock);
	}

re_arm:
	if (bond->params.arp_interval) {
		mod_timer(&bond->arp_timer, jiffies + delta_in_ticks);
	}
out:
	read_unlock(&bond->lock);
}

/*
 * When using arp monitoring in active-backup mode, this function is
 * called to determine if any backup slaves have went down or a new
 * current slave needs to be found.
 * The backup slaves never generate traffic, they are considered up by merely
 * receiving traffic. If the current slave goes down, each backup slave will
 * be given the opportunity to tx/rx an arp before being taken down - this
 * prevents all slaves from being taken down due to the current slave not
 * sending any traffic for the backups to receive. The arps are not necessarily
 * necessary, any tx and rx traffic will keep the current slave up. While any
 * rx traffic will keep the backup slaves up, the current slave is responsible
 * for generating traffic to keep them up regardless of any other traffic they
 * may have received.
 * see loadbalance_arp_monitor for arp monitoring in load balancing mode
 */
void bond_activebackup_arp_mon(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct slave *slave;
	int delta_in_ticks;
	int i;

	read_lock(&bond->lock);

	delta_in_ticks = (bond->params.arp_interval * HZ) / 1000;

	if (bond->kill_timers) {
		goto out;
	}

	if (bond->slave_cnt == 0) {
		goto re_arm;
	}

	/* determine if any slave has come up or any backup slave has
	 * gone down
	 * TODO: what about up/down delay in arp mode? it wasn't here before
	 *       so it can wait
	 */
	bond_for_each_slave(bond, slave, i) {
		if (slave->link != BOND_LINK_UP) {
			if ((jiffies - slave->dev->last_rx) <= delta_in_ticks) {

				slave->link = BOND_LINK_UP;

				write_lock(&bond->curr_slave_lock);

				if ((!bond->curr_active_slave) &&
				    ((jiffies - slave->dev->trans_start) <= delta_in_ticks)) {
					bond_change_active_slave(bond, slave);
					bond->current_arp_slave = NULL;
				} else if (bond->curr_active_slave != slave) {
					/* this slave has just come up but we
					 * already have a current slave; this
					 * can also happen if bond_enslave adds
					 * a new slave that is up while we are
					 * searching for a new slave
					 */
					bond_set_slave_inactive_flags(slave);
					bond->current_arp_slave = NULL;
				}

				if (slave == bond->curr_active_slave) {
					printk(KERN_INFO DRV_NAME
					       ": %s: %s is up and now the "
					       "active interface\n",
					       bond_dev->name,
					       slave->dev->name);
				} else {
					printk(KERN_INFO DRV_NAME
					       ": %s: backup interface %s is "
					       "now up\n",
					       bond_dev->name,
					       slave->dev->name);
				}

				write_unlock(&bond->curr_slave_lock);
			}
		} else {
			read_lock(&bond->curr_slave_lock);

			if ((slave != bond->curr_active_slave) &&
			    (!bond->current_arp_slave) &&
			    (((jiffies - slave->dev->last_rx) >= 3*delta_in_ticks) &&
			     bond_has_ip(bond))) {
				/* a backup slave has gone down; three times
				 * the delta allows the current slave to be
				 * taken out before the backup slave.
				 * note: a non-null current_arp_slave indicates
				 * the curr_active_slave went down and we are
				 * searching for a new one; under this
				 * condition we only take the curr_active_slave
				 * down - this gives each slave a chance to
				 * tx/rx traffic before being taken out
				 */

				read_unlock(&bond->curr_slave_lock);

				slave->link  = BOND_LINK_DOWN;

				if (slave->link_failure_count < UINT_MAX) {
					slave->link_failure_count++;
				}

				bond_set_slave_inactive_flags(slave);

				printk(KERN_INFO DRV_NAME
				       ": %s: backup interface %s is now down\n",
				       bond_dev->name,
				       slave->dev->name);
			} else {
				read_unlock(&bond->curr_slave_lock);
			}
		}
	}

	read_lock(&bond->curr_slave_lock);
	slave = bond->curr_active_slave;
	read_unlock(&bond->curr_slave_lock);

	if (slave) {
		/* if we have sent traffic in the past 2*arp_intervals but
		 * haven't xmit and rx traffic in that time interval, select
		 * a different slave. slave->jiffies is only updated when
		 * a slave first becomes the curr_active_slave - not necessarily
		 * after every arp; this ensures the slave has a full 2*delta
		 * before being taken out. if a primary is being used, check
		 * if it is up and needs to take over as the curr_active_slave
		 */
		if ((((jiffies - slave->dev->trans_start) >= (2*delta_in_ticks)) ||
	    (((jiffies - slave->dev->last_rx) >= (2*delta_in_ticks)) &&
	     bond_has_ip(bond))) &&
		    ((jiffies - slave->jiffies) >= 2*delta_in_ticks)) {

			slave->link  = BOND_LINK_DOWN;

			if (slave->link_failure_count < UINT_MAX) {
				slave->link_failure_count++;
			}

			printk(KERN_INFO DRV_NAME
			       ": %s: link status down for active interface "
			       "%s, disabling it\n",
			       bond_dev->name,
			       slave->dev->name);

			write_lock(&bond->curr_slave_lock);

			bond_select_active_slave(bond);
			slave = bond->curr_active_slave;

			write_unlock(&bond->curr_slave_lock);

			bond->current_arp_slave = slave;

			if (slave) {
				slave->jiffies = jiffies;
			}
		} else if ((bond->primary_slave) &&
			   (bond->primary_slave != slave) &&
			   (bond->primary_slave->link == BOND_LINK_UP)) {
			/* at this point, slave is the curr_active_slave */
			printk(KERN_INFO DRV_NAME
			       ": %s: changing from interface %s to primary "
			       "interface %s\n",
			       bond_dev->name,
			       slave->dev->name,
			       bond->primary_slave->dev->name);

			/* primary is up so switch to it */
			write_lock(&bond->curr_slave_lock);
			bond_change_active_slave(bond, bond->primary_slave);
			write_unlock(&bond->curr_slave_lock);

			slave = bond->primary_slave;
			slave->jiffies = jiffies;
		} else {
			bond->current_arp_slave = NULL;
		}

		/* the current slave must tx an arp to ensure backup slaves
		 * rx traffic
		 */
		if (slave && bond_has_ip(bond)) {
			bond_arp_send_all(bond, slave);
		}
	}

	/* if we don't have a curr_active_slave, search for the next available
	 * backup slave from the current_arp_slave and make it the candidate
	 * for becoming the curr_active_slave
	 */
	if (!slave) {
		if (!bond->current_arp_slave) {
			bond->current_arp_slave = bond->first_slave;
		}

		if (bond->current_arp_slave) {
			bond_set_slave_inactive_flags(bond->current_arp_slave);

			/* search for next candidate */
			bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) {
				if (IS_UP(slave->dev)) {
					slave->link = BOND_LINK_BACK;
					bond_set_slave_active_flags(slave);
					bond_arp_send_all(bond, slave);
					slave->jiffies = jiffies;
					bond->current_arp_slave = slave;
					break;
				}

				/* if the link state is up at this point, we
				 * mark it down - this can happen if we have
				 * simultaneous link failures and
				 * reselect_active_interface doesn't make this
				 * one the current slave so it is still marked
				 * up when it is actually down
				 */
				if (slave->link == BOND_LINK_UP) {
					slave->link  = BOND_LINK_DOWN;
					if (slave->link_failure_count < UINT_MAX) {
						slave->link_failure_count++;
					}

					bond_set_slave_inactive_flags(slave);

					printk(KERN_INFO DRV_NAME
					       ": %s: backup interface %s is "
					       "now down.\n",
					       bond_dev->name,
					       slave->dev->name);
				}
			}
		}
	}

re_arm:
	if (bond->params.arp_interval) {
		mod_timer(&bond->arp_timer, jiffies + delta_in_ticks);
	}
out:
	read_unlock(&bond->lock);
}

/*------------------------------ proc/seq_file-------------------------------*/

#ifdef CONFIG_PROC_FS

#define SEQ_START_TOKEN ((void *)1)

static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct bonding *bond = seq->private;
	loff_t off = 0;
	struct slave *slave;
	int i;

	/* make sure the bond won't be taken away */
	read_lock(&dev_base_lock);
	read_lock_bh(&bond->lock);

	if (*pos == 0) {
		return SEQ_START_TOKEN;
	}

	bond_for_each_slave(bond, slave, i) {
		if (++off == *pos) {
			return slave;
		}
	}

	return NULL;
}

static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct bonding *bond = seq->private;
	struct slave *slave = v;

	++*pos;
	if (v == SEQ_START_TOKEN) {
		return bond->first_slave;
	}

	slave = slave->next;

	return (slave == bond->first_slave) ? NULL : slave;
}

static void bond_info_seq_stop(struct seq_file *seq, void *v)
{
	struct bonding *bond = seq->private;

	read_unlock_bh(&bond->lock);
	read_unlock(&dev_base_lock);
}

static void bond_info_show_master(struct seq_file *seq)
{
	struct bonding *bond = seq->private;
	struct slave *curr;
	int i;
	u32 target;

	read_lock(&bond->curr_slave_lock);
	curr = bond->curr_active_slave;
	read_unlock(&bond->curr_slave_lock);

	seq_printf(seq, "Bonding Mode: %s\n",
		   bond_mode_name(bond->params.mode));

	if (bond->params.mode == BOND_MODE_XOR ||
		bond->params.mode == BOND_MODE_8023AD) {
		seq_printf(seq, "Transmit Hash Policy: %s (%d)\n",
			xmit_hashtype_tbl[bond->params.xmit_policy].modename,
			bond->params.xmit_policy);
	}

	if (USES_PRIMARY(bond->params.mode)) {
		seq_printf(seq, "Primary Slave: %s\n",
			   (bond->primary_slave) ?
			   bond->primary_slave->dev->name : "None");

		seq_printf(seq, "Currently Active Slave: %s\n",
			   (curr) ? curr->dev->name : "None");
	}

	seq_printf(seq, "MII Status: %s\n", (curr) ? "up" : "down");
	seq_printf(seq, "MII Polling Interval (ms): %d\n", bond->params.miimon);
	seq_printf(seq, "Up Delay (ms): %d\n",
		   bond->params.updelay * bond->params.miimon);
	seq_printf(seq, "Down Delay (ms): %d\n",
		   bond->params.downdelay * bond->params.miimon);


	/* ARP information */
	if(bond->params.arp_interval > 0) {
		int printed=0;
		seq_printf(seq, "ARP Polling Interval (ms): %d\n",
				bond->params.arp_interval);

		seq_printf(seq, "ARP IP target/s (n.n.n.n form):");

		for(i = 0; (i < BOND_MAX_ARP_TARGETS) ;i++) {
			if (!bond->params.arp_targets[i])
				continue;
			if (printed)
				seq_printf(seq, ",");
			target = ntohl(bond->params.arp_targets[i]);
			seq_printf(seq, " %d.%d.%d.%d", HIPQUAD(target));
			printed = 1;
		}
		seq_printf(seq, "\n");
	}

	if (bond->params.mode == BOND_MODE_8023AD) {
		struct ad_info ad_info;

		seq_puts(seq, "\n802.3ad info\n");
		seq_printf(seq, "LACP rate: %s\n",
			   (bond->params.lacp_fast) ? "fast" : "slow");

		if (bond_3ad_get_active_agg_info(bond, &ad_info)) {
			seq_printf(seq, "bond %s has no active aggregator\n",
				   bond->dev->name);
		} else {
			seq_printf(seq, "Active Aggregator Info:\n");

			seq_printf(seq, "\tAggregator ID: %d\n",
				   ad_info.aggregator_id);
			seq_printf(seq, "\tNumber of ports: %d\n",
				   ad_info.ports);
			seq_printf(seq, "\tActor Key: %d\n",
				   ad_info.actor_key);
			seq_printf(seq, "\tPartner Key: %d\n",
				   ad_info.partner_key);
			seq_printf(seq, "\tPartner Mac Address: %02x:%02x:%02x:%02x:%02x:%02x\n",
				   ad_info.partner_system[0],
				   ad_info.partner_system[1],
				   ad_info.partner_system[2],
				   ad_info.partner_system[3],
				   ad_info.partner_system[4],
				   ad_info.partner_system[5]);
		}
	}
}

static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave)
{
	struct bonding *bond = seq->private;

	seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name);
	seq_printf(seq, "MII Status: %s\n",
		   (slave->link == BOND_LINK_UP) ?  "up" : "down");
	seq_printf(seq, "Link Failure Count: %d\n",
		   slave->link_failure_count);

	seq_printf(seq,
		   "Permanent HW addr: %02x:%02x:%02x:%02x:%02x:%02x\n",
		   slave->perm_hwaddr[0], slave->perm_hwaddr[1],
		   slave->perm_hwaddr[2], slave->perm_hwaddr[3],
		   slave->perm_hwaddr[4], slave->perm_hwaddr[5]);

	if (bond->params.mode == BOND_MODE_8023AD) {
		const struct aggregator *agg
			= SLAVE_AD_INFO(slave).port.aggregator;

		if (agg) {
			seq_printf(seq, "Aggregator ID: %d\n",
				   agg->aggregator_identifier);
		} else {
			seq_puts(seq, "Aggregator ID: N/A\n");
		}
	}
}

static int bond_info_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN) {
		seq_printf(seq, "%s\n", version);
		bond_info_show_master(seq);
	} else {
		bond_info_show_slave(seq, v);
	}

	return 0;
}

static struct seq_operations bond_info_seq_ops = {
	.start = bond_info_seq_start,
	.next  = bond_info_seq_next,
	.stop  = bond_info_seq_stop,
	.show  = bond_info_seq_show,
};

static int bond_info_open(struct inode *inode, struct file *file)
{
	struct seq_file *seq;
	struct proc_dir_entry *proc;
	int res;

	res = seq_open(file, &bond_info_seq_ops);
	if (!res) {
		/* recover the pointer buried in proc_dir_entry data */
		seq = file->private_data;
		proc = PDE(inode);
		seq->private = proc->data;
	}

	return res;
}

static struct file_operations bond_info_fops = {
	.owner   = THIS_MODULE,
	.open    = bond_info_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release,
};

static int bond_create_proc_entry(struct bonding *bond)
{
	struct net_device *bond_dev = bond->dev;

	if (bond_proc_dir) {
		bond->proc_entry = create_proc_entry(bond_dev->name,
						     S_IRUGO,
						     bond_proc_dir);
		if (bond->proc_entry == NULL) {
			printk(KERN_WARNING DRV_NAME
			       ": Warning: Cannot create /proc/net/%s/%s\n",
			       DRV_NAME, bond_dev->name);
		} else {
			bond->proc_entry->data = bond;
			bond->proc_entry->proc_fops = &bond_info_fops;
			bond->proc_entry->owner = THIS_MODULE;
			memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ);
		}
	}

	return 0;
}

static void bond_remove_proc_entry(struct bonding *bond)
{
	if (bond_proc_dir && bond->proc_entry) {
		remove_proc_entry(bond->proc_file_name, bond_proc_dir);
		memset(bond->proc_file_name, 0, IFNAMSIZ);
		bond->proc_entry = NULL;
	}
}

/* Create the bonding directory under /proc/net, if doesn't exist yet.
 * Caller must hold rtnl_lock.
 */
static void bond_create_proc_dir(void)
{
	int len = strlen(DRV_NAME);

	for (bond_proc_dir = proc_net->subdir; bond_proc_dir;
	     bond_proc_dir = bond_proc_dir->next) {
		if ((bond_proc_dir->namelen == len) &&
		    !memcmp(bond_proc_dir->name, DRV_NAME, len)) {
			break;
		}
	}

	if (!bond_proc_dir) {
		bond_proc_dir = proc_mkdir(DRV_NAME, proc_net);
		if (bond_proc_dir) {
			bond_proc_dir->owner = THIS_MODULE;
		} else {
			printk(KERN_WARNING DRV_NAME
				": Warning: cannot create /proc/net/%s\n",
				DRV_NAME);
		}
	}
}

/* Destroy the bonding directory under /proc/net, if empty.
 * Caller must hold rtnl_lock.
 */
static void bond_destroy_proc_dir(void)
{
	struct proc_dir_entry *de;

	if (!bond_proc_dir) {
		return;
	}

	/* verify that the /proc dir is empty */
	for (de = bond_proc_dir->subdir; de; de = de->next) {
		/* ignore . and .. */
		if (*(de->name) != '.') {
			break;
		}
	}

	if (de) {
		if (bond_proc_dir->owner == THIS_MODULE) {
			bond_proc_dir->owner = NULL;
		}
	} else {
		remove_proc_entry(DRV_NAME, proc_net);
		bond_proc_dir = NULL;
	}
}
#endif /* CONFIG_PROC_FS */

/*-------------------------- netdev event handling --------------------------*/

/*
 * Change device name
 */
static int bond_event_changename(struct bonding *bond)
{
#ifdef CONFIG_PROC_FS
	bond_remove_proc_entry(bond);
	bond_create_proc_entry(bond);
#endif
	down_write(&(bonding_rwsem));
        bond_destroy_sysfs_entry(bond);
        bond_create_sysfs_entry(bond);
	up_write(&(bonding_rwsem));
	return NOTIFY_DONE;
}

static int bond_master_netdev_event(unsigned long event, struct net_device *bond_dev)
{
	struct bonding *event_bond = bond_dev->priv;

	switch (event) {
	case NETDEV_CHANGENAME:
		return bond_event_changename(event_bond);
	case NETDEV_UNREGISTER:
		/*
		 * TODO: remove a bond from the list?
		 */
		break;
	default:
		break;
	}

	return NOTIFY_DONE;
}

static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev)
{
	struct net_device *bond_dev = slave_dev->master;
	struct bonding *bond = bond_dev->priv;

	switch (event) {
	case NETDEV_UNREGISTER:
		if (bond_dev) {
			bond_release(bond_dev, slave_dev);
		}
		break;
	case NETDEV_CHANGE:
		/*
		 * TODO: is this what we get if somebody
		 * sets up a hierarchical bond, then rmmod's
		 * one of the slave bonding devices?
		 */
		break;
	case NETDEV_DOWN:
		/*
		 * ... Or is it this?
		 */
		break;
	case NETDEV_CHANGEMTU:
		/*
		 * TODO: Should slaves be allowed to
		 * independently alter their MTU?  For
		 * an active-backup bond, slaves need
		 * not be the same type of device, so
		 * MTUs may vary.  For other modes,
		 * slaves arguably should have the
		 * same MTUs. To do this, we'd need to
		 * take over the slave's change_mtu
		 * function for the duration of their
		 * servitude.
		 */
		break;
	case NETDEV_CHANGENAME:
		/*
		 * TODO: handle changing the primary's name
		 */
		break;
	case NETDEV_FEAT_CHANGE:
		bond_compute_features(bond);
		break;
	default:
		break;
	}

	return NOTIFY_DONE;
}

/*
 * bond_netdev_event: handle netdev notifier chain events.
 *
 * This function receives events for the netdev chain.  The caller (an
 * ioctl handler calling notifier_call_chain) holds the necessary
 * locks for us to safely manipulate the slave devices (RTNL lock,
 * dev_probe_lock).
 */
static int bond_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct net_device *event_dev = (struct net_device *)ptr;

	dprintk("event_dev: %s, event: %lx\n",
		(event_dev ? event_dev->name : "None"),
		event);

	if (event_dev->flags & IFF_MASTER) {
		dprintk("IFF_MASTER\n");
		return bond_master_netdev_event(event, event_dev);
	}

	if (event_dev->flags & IFF_SLAVE) {
		dprintk("IFF_SLAVE\n");
		return bond_slave_netdev_event(event, event_dev);
	}

	return NOTIFY_DONE;
}

/*
 * bond_inetaddr_event: handle inetaddr notifier chain events.
 *
 * We keep track of device IPs primarily to use as source addresses in
 * ARP monitor probes (rather than spewing out broadcasts all the time).
 *
 * We track one IP for the main device (if it has one), plus one per VLAN.
 */
static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct in_ifaddr *ifa = ptr;
	struct net_device *vlan_dev, *event_dev = ifa->ifa_dev->dev;
	struct bonding *bond, *bond_next;
	struct vlan_entry *vlan, *vlan_next;

	list_for_each_entry_safe(bond, bond_next, &bond_dev_list, bond_list) {
		if (bond->dev == event_dev) {
			switch (event) {
			case NETDEV_UP:
				bond->master_ip = ifa->ifa_local;
				return NOTIFY_OK;
			case NETDEV_DOWN:
				bond->master_ip = bond_glean_dev_ip(bond->dev);
				return NOTIFY_OK;
			default:
				return NOTIFY_DONE;
			}
		}

		if (list_empty(&bond->vlan_list))
			continue;

		list_for_each_entry_safe(vlan, vlan_next, &bond->vlan_list,
					 vlan_list) {
			vlan_dev = bond->vlgrp->vlan_devices[vlan->vlan_id];
			if (vlan_dev == event_dev) {
				switch (event) {
				case NETDEV_UP:
					vlan->vlan_ip = ifa->ifa_local;
					return NOTIFY_OK;
				case NETDEV_DOWN:
					vlan->vlan_ip =
						bond_glean_dev_ip(vlan_dev);
					return NOTIFY_OK;
				default:
					return NOTIFY_DONE;
				}
			}
		}
	}
	return NOTIFY_DONE;
}

static struct notifier_block bond_netdev_notifier = {
	.notifier_call = bond_netdev_event,
};

static struct notifier_block bond_inetaddr_notifier = {
	.notifier_call = bond_inetaddr_event,
};

/*-------------------------- Packet type handling ---------------------------*/

/* register to receive lacpdus on a bond */
static void bond_register_lacpdu(struct bonding *bond)
{
	struct packet_type *pk_type = &(BOND_AD_INFO(bond).ad_pkt_type);

	/* initialize packet type */
	pk_type->type = PKT_TYPE_LACPDU;
	pk_type->dev = bond->dev;
	pk_type->func = bond_3ad_lacpdu_recv;

	dev_add_pack(pk_type);
}

/* unregister to receive lacpdus on a bond */
static void bond_unregister_lacpdu(struct bonding *bond)
{
	dev_remove_pack(&(BOND_AD_INFO(bond).ad_pkt_type));
}

/*---------------------------- Hashing Policies -----------------------------*/

/*
 * Hash for the the output device based upon layer 3 and layer 4 data. If
 * the packet is a frag or not TCP or UDP, just use layer 3 data.  If it is
 * altogether not IP, mimic bond_xmit_hash_policy_l2()
 */
static int bond_xmit_hash_policy_l34(struct sk_buff *skb,
				    struct net_device *bond_dev, int count)
{
	struct ethhdr *data = (struct ethhdr *)skb->data;
	struct iphdr *iph = skb->nh.iph;
	u16 *layer4hdr = (u16 *)((u32 *)iph + iph->ihl);
	int layer4_xor = 0;

	if (skb->protocol == __constant_htons(ETH_P_IP)) {
		if (!(iph->frag_off & __constant_htons(IP_MF|IP_OFFSET)) &&
		    (iph->protocol == IPPROTO_TCP ||
		     iph->protocol == IPPROTO_UDP)) {
			layer4_xor = htons((*layer4hdr ^ *(layer4hdr + 1)));
		}
		return (layer4_xor ^
			((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count;

	}

	return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % count;
}

/*
 * Hash for the output device based upon layer 2 data
 */
static int bond_xmit_hash_policy_l2(struct sk_buff *skb,
				   struct net_device *bond_dev, int count)
{
	struct ethhdr *data = (struct ethhdr *)skb->data;

	return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % count;
}

/*-------------------------- Device entry points ----------------------------*/

static int bond_open(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct timer_list *mii_timer = &bond->mii_timer;
	struct timer_list *arp_timer = &bond->arp_timer;

	bond->kill_timers = 0;

	if ((bond->params.mode == BOND_MODE_TLB) ||
	    (bond->params.mode == BOND_MODE_ALB)) {
		struct timer_list *alb_timer = &(BOND_ALB_INFO(bond).alb_timer);

		/* bond_alb_initialize must be called before the timer
		 * is started.
		 */
		if (bond_alb_initialize(bond, (bond->params.mode == BOND_MODE_ALB))) {
			/* something went wrong - fail the open operation */
			return -1;
		}

		init_timer(alb_timer);
		alb_timer->expires  = jiffies + 1;
		alb_timer->data     = (unsigned long)bond;
		alb_timer->function = (void *)&bond_alb_monitor;
		add_timer(alb_timer);
	}

	if (bond->params.miimon) {  /* link check interval, in milliseconds. */
		init_timer(mii_timer);
		mii_timer->expires  = jiffies + 1;
		mii_timer->data     = (unsigned long)bond_dev;
		mii_timer->function = (void *)&bond_mii_monitor;
		add_timer(mii_timer);
	}

	if (bond->params.arp_interval) {  /* arp interval, in milliseconds. */
		init_timer(arp_timer);
		arp_timer->expires  = jiffies + 1;
		arp_timer->data     = (unsigned long)bond_dev;
		if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
			arp_timer->function = (void *)&bond_activebackup_arp_mon;
		} else {
			arp_timer->function = (void *)&bond_loadbalance_arp_mon;
		}
		add_timer(arp_timer);
	}

	if (bond->params.mode == BOND_MODE_8023AD) {
		struct timer_list *ad_timer = &(BOND_AD_INFO(bond).ad_timer);
		init_timer(ad_timer);
		ad_timer->expires  = jiffies + 1;
		ad_timer->data     = (unsigned long)bond;
		ad_timer->function = (void *)&bond_3ad_state_machine_handler;
		add_timer(ad_timer);

		/* register to receive LACPDUs */
		bond_register_lacpdu(bond);
	}

	return 0;
}

static int bond_close(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;

	if (bond->params.mode == BOND_MODE_8023AD) {
		/* Unregister the receive of LACPDUs */
		bond_unregister_lacpdu(bond);
	}

	write_lock_bh(&bond->lock);

	bond_mc_list_destroy(bond);

	/* signal timers not to re-arm */
	bond->kill_timers = 1;

	write_unlock_bh(&bond->lock);

	/* del_timer_sync must run without holding the bond->lock
	 * because a running timer might be trying to hold it too
	 */

	if (bond->params.miimon) {  /* link check interval, in milliseconds. */
		del_timer_sync(&bond->mii_timer);
	}

	if (bond->params.arp_interval) {  /* arp interval, in milliseconds. */
		del_timer_sync(&bond->arp_timer);
	}

	switch (bond->params.mode) {
	case BOND_MODE_8023AD:
		del_timer_sync(&(BOND_AD_INFO(bond).ad_timer));
		break;
	case BOND_MODE_TLB:
	case BOND_MODE_ALB:
		del_timer_sync(&(BOND_ALB_INFO(bond).alb_timer));
		break;
	default:
		break;
	}

	/* Release the bonded slaves */
	bond_release_all(bond_dev);

	if ((bond->params.mode == BOND_MODE_TLB) ||
	    (bond->params.mode == BOND_MODE_ALB)) {
		/* Must be called only after all
		 * slaves have been released
		 */
		bond_alb_deinitialize(bond);
	}

	return 0;
}

static struct net_device_stats *bond_get_stats(struct net_device *bond_dev)
{
	struct bonding *bond = bond_dev->priv;
	struct net_device_stats *stats = &(bond->stats), *sstats;
	struct slave *slave;
	int i;

	memset(stats, 0, sizeof(struct net_device_stats));

	read_lock_bh(&bond->lock);

	bond_for_each_slave(bond, slave, i) {
		sstats = slave->dev->get_stats(slave->dev);

		stats->rx_packets += sstats->rx_packets;
		stats->rx_bytes += sstats->rx_bytes;
		stats->rx_errors += sstats->rx_errors;
		stats->rx_dropped += sstats->rx_dropped;

		stats->tx_packets += sstats->tx_packets;
		stats->tx_bytes += sstats->tx_bytes;
		stats->tx_errors += sstats->tx_errors;
		stats->tx_dropped += sstats->tx_dropped;

		stats->multicast += sstats->multicast;
		stats->collisions += sstats->collisions;

		stats->rx_length_errors += sstats->rx_length_errors;
		stats->rx_over_errors += sstats->rx_over_errors;
		stats->rx_crc_errors += sstats->rx_crc_errors;
		stats->rx_frame_errors += sstats->rx_frame_errors;
		stats->rx_fifo_errors += sstats->rx_fifo_errors;
		stats->rx_missed_errors += sstats->rx_missed_errors;