summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/apic/vector.c
blob: 557318145038ece388de667760448c92128d14d4 (plain)
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
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Local APIC related interfaces to support IOAPIC, MSI, etc.
 *
 * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
 *	Moved from arch/x86/kernel/apic/io_apic.c.
 * Jiang Liu <jiang.liu@linux.intel.com>
 *	Enable support of hierarchical irqdomains
 */
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/slab.h>
#include <asm/irqdomain.h>
#include <asm/hw_irq.h>
#include <asm/traps.h>
#include <asm/apic.h>
#include <asm/i8259.h>
#include <asm/desc.h>
#include <asm/irq_remapping.h>

#include <asm/trace/irq_vectors.h>

struct apic_chip_data {
	struct irq_cfg		hw_irq_cfg;
	unsigned int		vector;
	unsigned int		prev_vector;
	unsigned int		cpu;
	unsigned int		prev_cpu;
	unsigned int		irq;
	struct hlist_node	clist;
	unsigned int		move_in_progress	: 1,
				is_managed		: 1,
				can_reserve		: 1,
				has_reserved		: 1;
};

struct irq_domain *x86_vector_domain;
EXPORT_SYMBOL_GPL(x86_vector_domain);
static DEFINE_RAW_SPINLOCK(vector_lock);
static cpumask_var_t vector_searchmask;
static struct irq_chip lapic_controller;
static struct irq_matrix *vector_matrix;
#ifdef CONFIG_SMP

static void vector_cleanup_callback(struct timer_list *tmr);

struct vector_cleanup {
	struct hlist_head	head;
	struct timer_list	timer;
};

static DEFINE_PER_CPU(struct vector_cleanup, vector_cleanup) = {
	.head	= HLIST_HEAD_INIT,
	.timer	= __TIMER_INITIALIZER(vector_cleanup_callback, TIMER_PINNED),
};
#endif

void lock_vector_lock(void)
{
	/* Used to the online set of cpus does not change
	 * during assign_irq_vector.
	 */
	raw_spin_lock(&vector_lock);
}

void unlock_vector_lock(void)
{
	raw_spin_unlock(&vector_lock);
}

void init_irq_alloc_info(struct irq_alloc_info *info,
			 const struct cpumask *mask)
{
	memset(info, 0, sizeof(*info));
	info->mask = mask;
}

void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
{
	if (src)
		*dst = *src;
	else
		memset(dst, 0, sizeof(*dst));
}

static struct apic_chip_data *apic_chip_data(struct irq_data *irqd)
{
	if (!irqd)
		return NULL;

	while (irqd->parent_data)
		irqd = irqd->parent_data;

	return irqd->chip_data;
}

struct irq_cfg *irqd_cfg(struct irq_data *irqd)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);

	return apicd ? &apicd->hw_irq_cfg : NULL;
}
EXPORT_SYMBOL_GPL(irqd_cfg);

struct irq_cfg *irq_cfg(unsigned int irq)
{
	return irqd_cfg(irq_get_irq_data(irq));
}

static struct apic_chip_data *alloc_apic_chip_data(int node)
{
	struct apic_chip_data *apicd;

	apicd = kzalloc_node(sizeof(*apicd), GFP_KERNEL, node);
	if (apicd)
		INIT_HLIST_NODE(&apicd->clist);
	return apicd;
}

static void free_apic_chip_data(struct apic_chip_data *apicd)
{
	kfree(apicd);
}

static void apic_update_irq_cfg(struct irq_data *irqd, unsigned int vector,
				unsigned int cpu)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);

	lockdep_assert_held(&vector_lock);

	apicd->hw_irq_cfg.vector = vector;
	apicd->hw_irq_cfg.dest_apicid = apic->calc_dest_apicid(cpu);
	irq_data_update_effective_affinity(irqd, cpumask_of(cpu));
	trace_vector_config(irqd->irq, vector, cpu,
			    apicd->hw_irq_cfg.dest_apicid);
}

static void apic_update_vector(struct irq_data *irqd, unsigned int newvec,
			       unsigned int newcpu)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);
	struct irq_desc *desc = irq_data_to_desc(irqd);
	bool managed = irqd_affinity_is_managed(irqd);

	lockdep_assert_held(&vector_lock);

	trace_vector_update(irqd->irq, newvec, newcpu, apicd->vector,
			    apicd->cpu);

	/*
	 * If there is no vector associated or if the associated vector is
	 * the shutdown vector, which is associated to make PCI/MSI
	 * shutdown mode work, then there is nothing to release. Clear out
	 * prev_vector for this and the offlined target case.
	 */
	apicd->prev_vector = 0;
	if (!apicd->vector || apicd->vector == MANAGED_IRQ_SHUTDOWN_VECTOR)
		goto setnew;
	/*
	 * If the target CPU of the previous vector is online, then mark
	 * the vector as move in progress and store it for cleanup when the
	 * first interrupt on the new vector arrives. If the target CPU is
	 * offline then the regular release mechanism via the cleanup
	 * vector is not possible and the vector can be immediately freed
	 * in the underlying matrix allocator.
	 */
	if (cpu_online(apicd->cpu)) {
		apicd->move_in_progress = true;
		apicd->prev_vector = apicd->vector;
		apicd->prev_cpu = apicd->cpu;
		WARN_ON_ONCE(apicd->cpu == newcpu);
	} else {
		irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector,
				managed);
	}

setnew:
	apicd->vector = newvec;
	apicd->cpu = newcpu;
	BUG_ON(!IS_ERR_OR_NULL(per_cpu(vector_irq, newcpu)[newvec]));
	per_cpu(vector_irq, newcpu)[newvec] = desc;
}

static void vector_assign_managed_shutdown(struct irq_data *irqd)
{
	unsigned int cpu = cpumask_first(cpu_online_mask);

	apic_update_irq_cfg(irqd, MANAGED_IRQ_SHUTDOWN_VECTOR, cpu);
}

static int reserve_managed_vector(struct irq_data *irqd)
{
	const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd);
	struct apic_chip_data *apicd = apic_chip_data(irqd);
	unsigned long flags;
	int ret;

	raw_spin_lock_irqsave(&vector_lock, flags);
	apicd->is_managed = true;
	ret = irq_matrix_reserve_managed(vector_matrix, affmsk);
	raw_spin_unlock_irqrestore(&vector_lock, flags);
	trace_vector_reserve_managed(irqd->irq, ret);
	return ret;
}

static void reserve_irq_vector_locked(struct irq_data *irqd)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);

	irq_matrix_reserve(vector_matrix);
	apicd->can_reserve = true;
	apicd->has_reserved = true;
	irqd_set_can_reserve(irqd);
	trace_vector_reserve(irqd->irq, 0);
	vector_assign_managed_shutdown(irqd);
}

static int reserve_irq_vector(struct irq_data *irqd)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&vector_lock, flags);
	reserve_irq_vector_locked(irqd);
	raw_spin_unlock_irqrestore(&vector_lock, flags);
	return 0;
}

static int
assign_vector_locked(struct irq_data *irqd, const struct cpumask *dest)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);
	bool resvd = apicd->has_reserved;
	unsigned int cpu = apicd->cpu;
	int vector = apicd->vector;

	lockdep_assert_held(&vector_lock);

	/*
	 * If the current target CPU is online and in the new requested
	 * affinity mask, there is no point in moving the interrupt from
	 * one CPU to another.
	 */
	if (vector && cpu_online(cpu) && cpumask_test_cpu(cpu, dest))
		return 0;

	/*
	 * Careful here. @apicd might either have move_in_progress set or
	 * be enqueued for cleanup. Assigning a new vector would either
	 * leave a stale vector on some CPU around or in case of a pending
	 * cleanup corrupt the hlist.
	 */
	if (apicd->move_in_progress || !hlist_unhashed(&apicd->clist))
		return -EBUSY;

	vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu);
	trace_vector_alloc(irqd->irq, vector, resvd, vector);
	if (vector < 0)
		return vector;
	apic_update_vector(irqd, vector, cpu);
	apic_update_irq_cfg(irqd, vector, cpu);

	return 0;
}

static int assign_irq_vector(struct irq_data *irqd, const struct cpumask *dest)
{
	unsigned long flags;
	int ret;

	raw_spin_lock_irqsave(&vector_lock, flags);
	cpumask_and(vector_searchmask, dest, cpu_online_mask);
	ret = assign_vector_locked(irqd, vector_searchmask);
	raw_spin_unlock_irqrestore(&vector_lock, flags);
	return ret;
}

static int assign_irq_vector_any_locked(struct irq_data *irqd)
{
	/* Get the affinity mask - either irq_default_affinity or (user) set */
	const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd);
	int node = irq_data_get_node(irqd);

	if (node != NUMA_NO_NODE) {
		/* Try the intersection of @affmsk and node mask */
		cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk);
		if (!assign_vector_locked(irqd, vector_searchmask))
			return 0;
	}

	/* Try the full affinity mask */
	cpumask_and(vector_searchmask, affmsk, cpu_online_mask);
	if (!assign_vector_locked(irqd, vector_searchmask))
		return 0;

	if (node != NUMA_NO_NODE) {
		/* Try the node mask */
		if (!assign_vector_locked(irqd, cpumask_of_node(node)))
			return 0;
	}

	/* Try the full online mask */
	return assign_vector_locked(irqd, cpu_online_mask);
}

static int
assign_irq_vector_policy(struct irq_data *irqd, struct irq_alloc_info *info)
{
	if (irqd_affinity_is_managed(irqd))
		return reserve_managed_vector(irqd);
	if (info->mask)
		return assign_irq_vector(irqd, info->mask);
	/*
	 * Make only a global reservation with no guarantee. A real vector
	 * is associated at activation time.
	 */
	return reserve_irq_vector(irqd);
}

static int
assign_managed_vector(struct irq_data *irqd, const struct cpumask *dest)
{
	const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd);
	struct apic_chip_data *apicd = apic_chip_data(irqd);
	int vector, cpu;

	cpumask_and(vector_searchmask, dest, affmsk);

	/* set_affinity might call here for nothing */
	if (apicd->vector && cpumask_test_cpu(apicd->cpu, vector_searchmask))
		return 0;
	vector = irq_matrix_alloc_managed(vector_matrix, vector_searchmask,
					  &cpu);
	trace_vector_alloc_managed(irqd->irq, vector, vector);
	if (vector < 0)
		return vector;
	apic_update_vector(irqd, vector, cpu);
	apic_update_irq_cfg(irqd, vector, cpu);
	return 0;
}

static void clear_irq_vector(struct irq_data *irqd)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);
	bool managed = irqd_affinity_is_managed(irqd);
	unsigned int vector = apicd->vector;

	lockdep_assert_held(&vector_lock);

	if (!vector)
		return;

	trace_vector_clear(irqd->irq, vector, apicd->cpu, apicd->prev_vector,
			   apicd->prev_cpu);

	per_cpu(vector_irq, apicd->cpu)[vector] = VECTOR_SHUTDOWN;
	irq_matrix_free(vector_matrix, apicd->cpu, vector, managed);
	apicd->vector = 0;

	/* Clean up move in progress */
	vector = apicd->prev_vector;
	if (!vector)
		return;

	per_cpu(vector_irq, apicd->prev_cpu)[vector] = VECTOR_SHUTDOWN;
	irq_matrix_free(vector_matrix, apicd->prev_cpu, vector, managed);
	apicd->prev_vector = 0;
	apicd->move_in_progress = 0;
	hlist_del_init(&apicd->clist);
}

static void x86_vector_deactivate(struct irq_domain *dom, struct irq_data *irqd)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);
	unsigned long flags;

	trace_vector_deactivate(irqd->irq, apicd->is_managed,
				apicd->can_reserve, false);

	/* Regular fixed assigned interrupt */
	if (!apicd->is_managed && !apicd->can_reserve)
		return;
	/* If the interrupt has a global reservation, nothing to do */
	if (apicd->has_reserved)
		return;

	raw_spin_lock_irqsave(&vector_lock, flags);
	clear_irq_vector(irqd);
	if (apicd->can_reserve)
		reserve_irq_vector_locked(irqd);
	else
		vector_assign_managed_shutdown(irqd);
	raw_spin_unlock_irqrestore(&vector_lock, flags);
}

static int activate_reserved(struct irq_data *irqd)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);
	int ret;

	ret = assign_irq_vector_any_locked(irqd);
	if (!ret) {
		apicd->has_reserved = false;
		/*
		 * Core might have disabled reservation mode after
		 * allocating the irq descriptor. Ideally this should
		 * happen before allocation time, but that would require
		 * completely convoluted ways of transporting that
		 * information.
		 */
		if (!irqd_can_reserve(irqd))
			apicd->can_reserve = false;
	}

	/*
	 * Check to ensure that the effective affinity mask is a subset
	 * the user supplied affinity mask, and warn the user if it is not
	 */
	if (!cpumask_subset(irq_data_get_effective_affinity_mask(irqd),
			    irq_data_get_affinity_mask(irqd))) {
		pr_warn("irq %u: Affinity broken due to vector space exhaustion.\n",
			irqd->irq);
	}

	return ret;
}

static int activate_managed(struct irq_data *irqd)
{
	const struct cpumask *dest = irq_data_get_affinity_mask(irqd);
	int ret;

	cpumask_and(vector_searchmask, dest, cpu_online_mask);
	if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) {
		/* Something in the core code broke! Survive gracefully */
		pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq);
		return -EINVAL;
	}

	ret = assign_managed_vector(irqd, vector_searchmask);
	/*
	 * This should not happen. The vector reservation got buggered.  Handle
	 * it gracefully.
	 */
	if (WARN_ON_ONCE(ret < 0)) {
		pr_err("Managed startup irq %u, no vector available\n",
		       irqd->irq);
	}
	return ret;
}

static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
			       bool reserve)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);
	unsigned long flags;
	int ret = 0;

	trace_vector_activate(irqd->irq, apicd->is_managed,
			      apicd->can_reserve, reserve);

	raw_spin_lock_irqsave(&vector_lock, flags);
	if (!apicd->can_reserve && !apicd->is_managed)
		assign_irq_vector_any_locked(irqd);
	else if (reserve || irqd_is_managed_and_shutdown(irqd))
		vector_assign_managed_shutdown(irqd);
	else if (apicd->is_managed)
		ret = activate_managed(irqd);
	else if (apicd->has_reserved)
		ret = activate_reserved(irqd);
	raw_spin_unlock_irqrestore(&vector_lock, flags);
	return ret;
}

static void vector_free_reserved_and_managed(struct irq_data *irqd)
{
	const struct cpumask *dest = irq_data_get_affinity_mask(irqd);
	struct apic_chip_data *apicd = apic_chip_data(irqd);

	trace_vector_teardown(irqd->irq, apicd->is_managed,
			      apicd->has_reserved);

	if (apicd->has_reserved)
		irq_matrix_remove_reserved(vector_matrix);
	if (apicd->is_managed)
		irq_matrix_remove_managed(vector_matrix, dest);
}

static void x86_vector_free_irqs(struct irq_domain *domain,
				 unsigned int virq, unsigned int nr_irqs)
{
	struct apic_chip_data *apicd;
	struct irq_data *irqd;
	unsigned long flags;
	int i;

	for (i = 0; i < nr_irqs; i++) {
		irqd = irq_domain_get_irq_data(x86_vector_domain, virq + i);
		if (irqd && irqd->chip_data) {
			raw_spin_lock_irqsave(&vector_lock, flags);
			clear_irq_vector(irqd);
			vector_free_reserved_and_managed(irqd);
			apicd = irqd->chip_data;
			irq_domain_reset_irq_data(irqd);
			raw_spin_unlock_irqrestore(&vector_lock, flags);
			free_apic_chip_data(apicd);
		}
	}
}

static bool vector_configure_legacy(unsigned int virq, struct irq_data *irqd,
				    struct apic_chip_data *apicd)
{
	unsigned long flags;
	bool realloc = false;

	apicd->vector = ISA_IRQ_VECTOR(virq);
	apicd->cpu = 0;

	raw_spin_lock_irqsave(&vector_lock, flags);
	/*
	 * If the interrupt is activated, then it must stay at this vector
	 * position. That's usually the timer interrupt (0).
	 */
	if (irqd_is_activated(irqd)) {
		trace_vector_setup(virq, true, 0);
		apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu);
	} else {
		/* Release the vector */
		apicd->can_reserve = true;
		irqd_set_can_reserve(irqd);
		clear_irq_vector(irqd);
		realloc = true;
	}
	raw_spin_unlock_irqrestore(&vector_lock, flags);
	return realloc;
}

static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
				 unsigned int nr_irqs, void *arg)
{
	struct irq_alloc_info *info = arg;
	struct apic_chip_data *apicd;
	struct irq_data *irqd;
	int i, err, node;

	if (apic_is_disabled)
		return -ENXIO;

	/*
	 * Catch any attempt to touch the cascade interrupt on a PIC
	 * equipped system.
	 */
	if (WARN_ON_ONCE(info->flags & X86_IRQ_ALLOC_LEGACY &&
			 virq == PIC_CASCADE_IR))
		return -EINVAL;

	for (i = 0; i < nr_irqs; i++) {
		irqd = irq_domain_get_irq_data(domain, virq + i);
		BUG_ON(!irqd);
		node = irq_data_get_node(irqd);
		WARN_ON_ONCE(irqd->chip_data);
		apicd = alloc_apic_chip_data(node);
		if (!apicd) {
			err = -ENOMEM;
			goto error;
		}

		apicd->irq = virq + i;
		irqd->chip = &lapic_controller;
		irqd->chip_data = apicd;
		irqd->hwirq = virq + i;
		irqd_set_single_target(irqd);
		/*
		 * Prevent that any of these interrupts is invoked in
		 * non interrupt context via e.g. generic_handle_irq()
		 * as that can corrupt the affinity move state.
		 */
		irqd_set_handle_enforce_irqctx(irqd);

		/* Don't invoke affinity setter on deactivated interrupts */
		irqd_set_affinity_on_activate(irqd);

		/*
		 * Legacy vectors are already assigned when the IOAPIC
		 * takes them over. They stay on the same vector. This is
		 * required for check_timer() to work correctly as it might
		 * switch back to legacy mode. Only update the hardware
		 * config.
		 */
		if (info->flags & X86_IRQ_ALLOC_LEGACY) {
			if (!vector_configure_legacy(virq + i, irqd, apicd))
				continue;
		}

		err = assign_irq_vector_policy(irqd, info);
		trace_vector_setup(virq + i, false, err);
		if (err) {
			irqd->chip_data = NULL;
			free_apic_chip_data(apicd);
			goto error;
		}
	}

	return 0;

error:
	x86_vector_free_irqs(domain, virq, i);
	return err;
}

#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
static void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
				  struct irq_data *irqd, int ind)
{
	struct apic_chip_data apicd;
	unsigned long flags;
	int irq;

	if (!irqd) {
		irq_matrix_debug_show(m, vector_matrix, ind);
		return;
	}

	irq = irqd->irq;
	if (irq < nr_legacy_irqs() && !test_bit(irq, &io_apic_irqs)) {
		seq_printf(m, "%*sVector: %5d\n", ind, "", ISA_IRQ_VECTOR(irq));
		seq_printf(m, "%*sTarget: Legacy PIC all CPUs\n", ind, "");
		return;
	}

	if (!irqd->chip_data) {
		seq_printf(m, "%*sVector: Not assigned\n", ind, "");
		return;
	}

	raw_spin_lock_irqsave(&vector_lock, flags);
	memcpy(&apicd, irqd->chip_data, sizeof(apicd));
	raw_spin_unlock_irqrestore(&vector_lock, flags);

	seq_printf(m, "%*sVector: %5u\n", ind, "", apicd.vector);
	seq_printf(m, "%*sTarget: %5u\n", ind, "", apicd.cpu);
	if (apicd.prev_vector) {
		seq_printf(m, "%*sPrevious vector: %5u\n", ind, "", apicd.prev_vector);
		seq_printf(m, "%*sPrevious target: %5u\n", ind, "", apicd.prev_cpu);
	}
	seq_printf(m, "%*smove_in_progress: %u\n", ind, "", apicd.move_in_progress ? 1 : 0);
	seq_printf(m, "%*sis_managed:       %u\n", ind, "", apicd.is_managed ? 1 : 0);
	seq_printf(m, "%*scan_reserve:      %u\n", ind, "", apicd.can_reserve ? 1 : 0);
	seq_printf(m, "%*shas_reserved:     %u\n", ind, "", apicd.has_reserved ? 1 : 0);
	seq_printf(m, "%*scleanup_pending:  %u\n", ind, "", !hlist_unhashed(&apicd.clist));
}
#endif

int x86_fwspec_is_ioapic(struct irq_fwspec *fwspec)
{
	if (fwspec->param_count != 1)
		return 0;

	if (is_fwnode_irqchip(fwspec->fwnode)) {
		const char *fwname = fwnode_get_name(fwspec->fwnode);
		return fwname && !strncmp(fwname, "IO-APIC-", 8) &&
			simple_strtol(fwname+8, NULL, 10) == fwspec->param[0];
	}
	return to_of_node(fwspec->fwnode) &&
		of_device_is_compatible(to_of_node(fwspec->fwnode),
					"intel,ce4100-ioapic");
}

int x86_fwspec_is_hpet(struct irq_fwspec *fwspec)
{
	if (fwspec->param_count != 1)
		return 0;

	if (is_fwnode_irqchip(fwspec->fwnode)) {
		const char *fwname = fwnode_get_name(fwspec->fwnode);
		return fwname && !strncmp(fwname, "HPET-MSI-", 9) &&
			simple_strtol(fwname+9, NULL, 10) == fwspec->param[0];
	}
	return 0;
}

static int x86_vector_select(struct irq_domain *d, struct irq_fwspec *fwspec,
			     enum irq_domain_bus_token bus_token)
{
	/*
	 * HPET and I/OAPIC cannot be parented in the vector domain
	 * if IRQ remapping is enabled. APIC IDs above 15 bits are
	 * only permitted if IRQ remapping is enabled, so check that.
	 */
	if (apic_id_valid(32768))
		return 0;

	return x86_fwspec_is_ioapic(fwspec) || x86_fwspec_is_hpet(fwspec);
}

static const struct irq_domain_ops x86_vector_domain_ops = {
	.select		= x86_vector_select,
	.alloc		= x86_vector_alloc_irqs,
	.free		= x86_vector_free_irqs,
	.activate	= x86_vector_activate,
	.deactivate	= x86_vector_deactivate,
#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
	.debug_show	= x86_vector_debug_show,
#endif
};

int __init arch_probe_nr_irqs(void)
{
	int nr;

	if (nr_irqs > (NR_VECTORS * nr_cpu_ids))
		nr_irqs = NR_VECTORS * nr_cpu_ids;

	nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
#if defined(CONFIG_PCI_MSI)
	/*
	 * for MSI and HT dyn irq
	 */
	if (gsi_top <= NR_IRQS_LEGACY)
		nr +=  8 * nr_cpu_ids;
	else
		nr += gsi_top * 16;
#endif
	if (nr < nr_irqs)
		nr_irqs = nr;

	/*
	 * We don't know if PIC is present at this point so we need to do
	 * probe() to get the right number of legacy IRQs.
	 */
	return legacy_pic->probe();
}

void lapic_assign_legacy_vector(unsigned int irq, bool replace)
{
	/*
	 * Use assign system here so it won't get accounted as allocated
	 * and movable in the cpu hotplug check and it prevents managed
	 * irq reservation from touching it.
	 */
	irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace);
}

void __init lapic_update_legacy_vectors(void)
{
	unsigned int i;

	if (IS_ENABLED(CONFIG_X86_IO_APIC) && nr_ioapics > 0)
		return;

	/*
	 * If the IO/APIC is disabled via config, kernel command line or
	 * lack of enumeration then all legacy interrupts are routed
	 * through the PIC. Make sure that they are marked as legacy
	 * vectors. PIC_CASCADE_IRQ has already been marked in
	 * lapic_assign_system_vectors().
	 */
	for (i = 0; i < nr_legacy_irqs(); i++) {
		if (i != PIC_CASCADE_IR)
			lapic_assign_legacy_vector(i, true);
	}
}

void __init lapic_assign_system_vectors(void)
{
	unsigned int i, vector;

	for_each_set_bit(vector, system_vectors, NR_VECTORS)
		irq_matrix_assign_system(vector_matrix, vector, false);

	if (nr_legacy_irqs() > 1)
		lapic_assign_legacy_vector(PIC_CASCADE_IR, false);

	/* System vectors are reserved, online it */
	irq_matrix_online(vector_matrix);

	/* Mark the preallocated legacy interrupts */
	for (i = 0; i < nr_legacy_irqs(); i++) {
		/*
		 * Don't touch the cascade interrupt. It's unusable
		 * on PIC equipped machines. See the large comment
		 * in the IO/APIC code.
		 */
		if (i != PIC_CASCADE_IR)
			irq_matrix_assign(vector_matrix, ISA_IRQ_VECTOR(i));
	}
}

int __init arch_early_irq_init(void)
{
	struct fwnode_handle *fn;

	fn = irq_domain_alloc_named_fwnode("VECTOR");
	BUG_ON(!fn);
	x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops,
						   NULL);
	BUG_ON(x86_vector_domain == NULL);
	irq_set_default_host(x86_vector_domain);

	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));

	/*
	 * Allocate the vector matrix allocator data structure and limit the
	 * search area.
	 */
	vector_matrix = irq_alloc_matrix(NR_VECTORS, FIRST_EXTERNAL_VECTOR,
					 FIRST_SYSTEM_VECTOR);
	BUG_ON(!vector_matrix);

	return arch_early_ioapic_init();
}

#ifdef CONFIG_SMP

static struct irq_desc *__setup_vector_irq(int vector)
{
	int isairq = vector - ISA_IRQ_VECTOR(0);

	/* Check whether the irq is in the legacy space */
	if (isairq < 0 || isairq >= nr_legacy_irqs())
		return VECTOR_UNUSED;
	/* Check whether the irq is handled by the IOAPIC */
	if (test_bit(isairq, &io_apic_irqs))
		return VECTOR_UNUSED;
	return irq_to_desc(isairq);
}

/* Online the local APIC infrastructure and initialize the vectors */
void lapic_online(void)
{
	unsigned int vector;

	lockdep_assert_held(&vector_lock);

	/* Online the vector matrix array for this CPU */
	irq_matrix_online(vector_matrix);

	/*
	 * The interrupt affinity logic never targets interrupts to offline
	 * CPUs. The exception are the legacy PIC interrupts. In general
	 * they are only targeted to CPU0, but depending on the platform
	 * they can be distributed to any online CPU in hardware. The
	 * kernel has no influence on that. So all active legacy vectors
	 * must be installed on all CPUs. All non legacy interrupts can be
	 * cleared.
	 */
	for (vector = 0; vector < NR_VECTORS; vector++)
		this_cpu_write(vector_irq[vector], __setup_vector_irq(vector));
}

static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr);

void lapic_offline(void)
{
	struct vector_cleanup *cl = this_cpu_ptr(&vector_cleanup);

	lock_vector_lock();

	/* In case the vector cleanup timer has not expired */
	__vector_cleanup(cl, false);

	irq_matrix_offline(vector_matrix);
	WARN_ON_ONCE(try_to_del_timer_sync(&cl->timer) < 0);
	WARN_ON_ONCE(!hlist_empty(&cl->head));

	unlock_vector_lock();
}

static int apic_set_affinity(struct irq_data *irqd,
			     const struct cpumask *dest, bool force)
{
	int err;

	if (WARN_ON_ONCE(!irqd_is_activated(irqd)))
		return -EIO;

	raw_spin_lock(&vector_lock);
	cpumask_and(vector_searchmask, dest, cpu_online_mask);
	if (irqd_affinity_is_managed(irqd))
		err = assign_managed_vector(irqd, vector_searchmask);
	else
		err = assign_vector_locked(irqd, vector_searchmask);
	raw_spin_unlock(&vector_lock);
	return err ? err : IRQ_SET_MASK_OK;
}

#else
# define apic_set_affinity	NULL
#endif

static int apic_retrigger_irq(struct irq_data *irqd)
{
	struct apic_chip_data *apicd = apic_chip_data(irqd);
	unsigned long flags;

	raw_spin_lock_irqsave(&vector_lock, flags);
	__apic_send_IPI(apicd->cpu, apicd->vector);
	raw_spin_unlock_irqrestore(&vector_lock, flags);

	return 1;
}

void apic_ack_irq(struct irq_data *irqd)
{
	irq_move_irq(irqd);
	apic_eoi();
}

void apic_ack_edge(struct irq_data *irqd)
{
	irq_complete_move(irqd_cfg(irqd));
	apic_ack_irq(irqd);
}

static void x86_vector_msi_compose_msg(struct irq_data *data,
				       struct msi_msg *msg)
{
       __irq_msi_compose_msg(irqd_cfg(data), msg, false);
}

static struct irq_chip lapic_controller = {
	.name			= "APIC",
	.irq_ack		= apic_ack_edge,
	.irq_set_affinity	= apic_set_affinity,
	.irq_compose_msi_msg	= x86_vector_msi_compose_msg,
	.irq_retrigger		= apic_retrigger_irq,
};

#ifdef CONFIG_SMP

static void free_moved_vector(struct apic_chip_data *apicd)
{
	unsigned int vector = apicd->prev_vector;
	unsigned int cpu = apicd->prev_cpu;
	bool managed = apicd->is_managed;

	/*
	 * Managed interrupts are usually not migrated away
	 * from an online CPU, but CPU isolation 'managed_irq'
	 * can make that happen.
	 * 1) Activation does not take the isolation into account
	 *    to keep the code simple
	 * 2) Migration away from an isolated CPU can happen when
	 *    a non-isolated CPU which is in the calculated
	 *    affinity mask comes online.
	 */
	trace_vector_free_moved(apicd->irq, cpu, vector, managed);
	irq_matrix_free(vector_matrix, cpu, vector, managed);
	per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED;
	hlist_del_init(&apicd->clist);
	apicd->prev_vector = 0;
	apicd->move_in_progress = 0;
}

static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr)
{
	struct apic_chip_data *apicd;
	struct hlist_node *tmp;
	bool rearm = false;

	lockdep_assert_held(&vector_lock);

	hlist_for_each_entry_safe(apicd, tmp, &cl->head, clist) {
		unsigned int vector = apicd->prev_vector;

		/*
		 * Paranoia: Check if the vector that needs to be cleaned
		 * up is registered at the APICs IRR. That's clearly a
		 * hardware issue if the vector arrived on the old target
		 * _after_ interrupts were disabled above. Keep @apicd
		 * on the list and schedule the timer again to give the CPU
		 * a chance to handle the pending interrupt.
		 *
		 * Do not check IRR when called from lapic_offline(), because
		 * fixup_irqs() was just called to scan IRR for set bits and
		 * forward them to new destination CPUs via IPIs.
		 */
		if (check_irr && is_vector_pending(vector)) {
			pr_warn_once("Moved interrupt pending in old target APIC %u\n", apicd->irq);
			rearm = true;
			continue;
		}
		free_moved_vector(apicd);
	}

	/*
	 * Must happen under vector_lock to make the timer_pending() check
	 * in __vector_schedule_cleanup() race free against the rearm here.
	 */
	if (rearm)
		mod_timer(&cl->timer, jiffies + 1);
}

static void vector_cleanup_callback(struct timer_list *tmr)
{
	struct vector_cleanup *cl = container_of(tmr, typeof(*cl), timer);

	/* Prevent vectors vanishing under us */
	raw_spin_lock_irq(&vector_lock);
	__vector_cleanup(cl, true);
	raw_spin_unlock_irq(&vector_lock);
}

static void __vector_schedule_cleanup(struct apic_chip_data *apicd)
{
	unsigned int cpu = apicd->prev_cpu;

	raw_spin_lock(&vector_lock);
	apicd->move_in_progress = 0;
	if (cpu_online(cpu)) {
		struct vector_cleanup *cl = per_cpu_ptr(&vector_cleanup, cpu);

		hlist_add_head(&apicd->clist, &cl->head);

		/*
		 * The lockless timer_pending() check is safe here. If it
		 * returns true, then the callback will observe this new
		 * apic data in the hlist as everything is serialized by
		 * vector lock.
		 *
		 * If it returns false then the timer is either not armed
		 * or the other CPU executes the callback, which again
		 * would be blocked on vector lock. Rearming it in the
		 * latter case makes it fire for nothing.
		 *
		 * This is also safe against the callback rearming the timer
		 * because that's serialized via vector lock too.
		 */
		if (!timer_pending(&cl->timer)) {
			cl->timer.expires = jiffies + 1;
			add_timer_on(&cl->timer, cpu);
		}
	} else {
		pr_warn("IRQ %u schedule cleanup for offline CPU %u\n", apicd->irq, cpu);
		free_moved_vector(apicd);
	}
	raw_spin_unlock(&vector_lock);
}

void vector_schedule_cleanup(struct irq_cfg *cfg)
{
	struct apic_chip_data *apicd;

	apicd = container_of(cfg, struct apic_chip_data, hw_irq_cfg);
	if (apicd->move_in_progress)
		__vector_schedule_cleanup(apicd);
}

void irq_complete_move(struct irq_cfg *cfg)
{
	struct apic_chip_data *apicd;

	apicd = container_of(cfg, struct apic_chip_data, hw_irq_cfg);
	if (likely(!apicd->move_in_progress))
		return;

	/*
	 * If the interrupt arrived on the new target CPU, cleanup the
	 * vector on the old target CPU. A vector check is not required
	 * because an interrupt can never move from one vector to another
	 * on the same CPU.
	 */
	if (apicd->cpu == smp_processor_id())
		__vector_schedule_cleanup(apicd);
}

/*
 * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
 */
void irq_force_complete_move(struct irq_desc *desc)
{
	unsigned int cpu = smp_processor_id();
	struct apic_chip_data *apicd;
	struct irq_data *irqd;
	unsigned int vector;

	/*
	 * The function is called for all descriptors regardless of which
	 * irqdomain they belong to. For example if an IRQ is provided by
	 * an irq_chip as part of a GPIO driver, the chip data for that
	 * descriptor is specific to the irq_chip in question.
	 *
	 * Check first that the chip_data is what we expect
	 * (apic_chip_data) before touching it any further.
	 */
	irqd = irq_domain_get_irq_data(x86_vector_domain,
				       irq_desc_get_irq(desc));
	if (!irqd)
		return;

	raw_spin_lock(&vector_lock);
	apicd = apic_chip_data(irqd);
	if (!apicd)
		goto unlock;

	/*
	 * If prev_vector is empty or the descriptor is neither currently
	 * nor previously on the outgoing CPU no action required.
	 */
	vector = apicd->prev_vector;
	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
		goto unlock;

	/*
	 * This is tricky. If the cleanup of the old vector has not been
	 * done yet, then the following setaffinity call will fail with
	 * -EBUSY. This can leave the interrupt in a stale state.
	 *
	 * All CPUs are stuck in stop machine with interrupts disabled so
	 * calling __irq_complete_move() would be completely pointless.
	 *
	 * 1) The interrupt is in move_in_progress state. That means that we
	 *    have not seen an interrupt since the io_apic was reprogrammed to
	 *    the new vector.
	 *
	 * 2) The interrupt has fired on the new vector, but the cleanup IPIs
	 *    have not been processed yet.
	 */
	if (apicd->move_in_progress) {
		/*
		 * In theory there is a race:
		 *
		 * set_ioapic(new_vector) <-- Interrupt is raised before update
		 *			      is effective, i.e. it's raised on
		 *			      the old vector.
		 *
		 * So if the target cpu cannot handle that interrupt before
		 * the old vector is cleaned up, we get a spurious interrupt
		 * and in the worst case the ioapic irq line becomes stale.
		 *
		 * But in case of cpu hotplug this should be a non issue
		 * because if the affinity update happens right before all
		 * cpus rendezvous in stop machine, there is no way that the
		 * interrupt can be blocked on the target cpu because all cpus
		 * loops first with interrupts enabled in stop machine, so the
		 * old vector is not yet cleaned up when the interrupt fires.
		 *
		 * So the only way to run into this issue is if the delivery
		 * of the interrupt on the apic/system bus would be delayed
		 * beyond the point where the target cpu disables interrupts
		 * in stop machine. I doubt that it can happen, but at least
		 * there is a theoretical chance. Virtualization might be
		 * able to expose this, but AFAICT the IOAPIC emulation is not
		 * as stupid as the real hardware.
		 *
		 * Anyway, there is nothing we can do about that at this point
		 * w/o refactoring the whole fixup_irq() business completely.
		 * We print at least the irq number and the old vector number,
		 * so we have the necessary information when a problem in that
		 * area arises.
		 */
		pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n",
			irqd->irq, vector);
	}
	free_moved_vector(apicd);
unlock:
	raw_spin_unlock(&vector_lock);
}

#ifdef CONFIG_HOTPLUG_CPU
/*
 * Note, this is not accurate accounting, but at least good enough to
 * prevent that the actual interrupt move will run out of vectors.
 */
int lapic_can_unplug_cpu(void)
{
	unsigned int rsvd, avl, tomove, cpu = smp_processor_id();
	int ret = 0;

	raw_spin_lock(&vector_lock);
	tomove = irq_matrix_allocated(vector_matrix);
	avl = irq_matrix_available(vector_matrix, true);
	if (avl < tomove) {
		pr_warn("CPU %u has %u vectors, %u available. Cannot disable CPU\n",
			cpu, tomove, avl);
		ret = -ENOSPC;
		goto out;
	}
	rsvd = irq_matrix_reserved(vector_matrix);
	if (avl < rsvd) {
		pr_warn("Reserved vectors %u > available %u. IRQ request may fail\n",
			rsvd, avl);
	}
out:
	raw_spin_unlock(&vector_lock);
	return ret;
}
#endif /* HOTPLUG_CPU */
#endif /* SMP */

static void __init print_APIC_field(int base)
{
	int i;

	printk(KERN_DEBUG);

	for (i = 0; i < 8; i++)
		pr_cont("%08x", apic_read(base + i*0x10));

	pr_cont("\n");
}

static void __init print_local_APIC(void *dummy)
{
	unsigned int i, v, ver, maxlvt;
	u64 icr;

	pr_debug("printing local APIC contents on CPU#%d/%d:\n",
		 smp_processor_id(), read_apic_id());
	v = apic_read(APIC_ID);
	pr_info("... APIC ID:      %08x (%01x)\n", v, read_apic_id());
	v = apic_read(APIC_LVR);
	pr_info("... APIC VERSION: %08x\n", v);
	ver = GET_APIC_VERSION(v);
	maxlvt = lapic_get_maxlvt();

	v = apic_read(APIC_TASKPRI);
	pr_debug("... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK);

	/* !82489DX */
	if (APIC_INTEGRATED(ver)) {
		if (!APIC_XAPIC(ver)) {
			v = apic_read(APIC_ARBPRI);
			pr_debug("... APIC ARBPRI: %08x (%02x)\n",
				 v, v & APIC_ARBPRI_MASK);
		}
		v = apic_read(APIC_PROCPRI);
		pr_debug("... APIC PROCPRI: %08x\n", v);
	}

	/*
	 * Remote read supported only in the 82489DX and local APIC for
	 * Pentium processors.
	 */
	if (!APIC_INTEGRATED(ver) || maxlvt == 3) {
		v = apic_read(APIC_RRR);
		pr_debug("... APIC RRR: %08x\n", v);
	}

	v = apic_read(APIC_LDR);
	pr_debug("... APIC LDR: %08x\n", v);
	if (!x2apic_enabled()) {
		v = apic_read(APIC_DFR);
		pr_debug("... APIC DFR: %08x\n", v);
	}
	v = apic_read(APIC_SPIV);
	pr_debug("... APIC SPIV: %08x\n", v);

	pr_debug("... APIC ISR field:\n");
	print_APIC_field(APIC_ISR);
	pr_debug("... APIC TMR field:\n");
	print_APIC_field(APIC_TMR);
	pr_debug("... APIC IRR field:\n");
	print_APIC_field(APIC_IRR);

	/* !82489DX */
	if (APIC_INTEGRATED(ver)) {
		/* Due to the Pentium erratum 3AP. */
		if (maxlvt > 3)
			apic_write(APIC_ESR, 0);

		v = apic_read(APIC_ESR);
		pr_debug("... APIC ESR: %08x\n", v);
	}

	icr = apic_icr_read();
	pr_debug("... APIC ICR: %08x\n", (u32)icr);
	pr_debug("... APIC ICR2: %08x\n", (u32)(icr >> 32));

	v = apic_read(APIC_LVTT);
	pr_debug("... APIC LVTT: %08x\n", v);

	if (maxlvt > 3) {
		/* PC is LVT#4. */
		v = apic_read(APIC_LVTPC);
		pr_debug("... APIC LVTPC: %08x\n", v);
	}
	v = apic_read(APIC_LVT0);
	pr_debug("... APIC LVT0: %08x\n", v);
	v = apic_read(APIC_LVT1);
	pr_debug("... APIC LVT1: %08x\n", v);

	if (maxlvt > 2) {
		/* ERR is LVT#3. */
		v = apic_read(APIC_LVTERR);
		pr_debug("... APIC LVTERR: %08x\n", v);
	}

	v = apic_read(APIC_TMICT);
	pr_debug("... APIC TMICT: %08x\n", v);
	v = apic_read(APIC_TMCCT);
	pr_debug("... APIC TMCCT: %08x\n", v);
	v = apic_read(APIC_TDCR);
	pr_debug("... APIC TDCR: %08x\n", v);

	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
		v = apic_read(APIC_EFEAT);
		maxlvt = (v >> 16) & 0xff;
		pr_debug("... APIC EFEAT: %08x\n", v);
		v = apic_read(APIC_ECTRL);
		pr_debug("... APIC ECTRL: %08x\n", v);
		for (i = 0; i < maxlvt; i++) {
			v = apic_read(APIC_EILVTn(i));
			pr_debug("... APIC EILVT%d: %08x\n", i, v);
		}
	}
	pr_cont("\n");
}

static void __init print_local_APICs(int maxcpu)
{
	int cpu;

	if (!maxcpu)
		return;

	preempt_disable();
	for_each_online_cpu(cpu) {
		if (cpu >= maxcpu)
			break;
		smp_call_function_single(cpu, print_local_APIC, NULL, 1);
	}
	preempt_enable();
}

static void __init print_PIC(void)
{
	unsigned int v;
	unsigned long flags;

	if (!nr_legacy_irqs())
		return;

	pr_debug("\nprinting PIC contents\n");

	raw_spin_lock_irqsave(&i8259A_lock, flags);

	v = inb(0xa1) << 8 | inb(0x21);
	pr_debug("... PIC  IMR: %04x\n", v);

	v = inb(0xa0) << 8 | inb(0x20);
	pr_debug("... PIC  IRR: %04x\n", v);

	outb(0x0b, 0xa0);
	outb(0x0b, 0x20);
	v = inb(0xa0) << 8 | inb(0x20);
	outb(0x0a, 0xa0);
	outb(0x0a, 0x20);

	raw_spin_unlock_irqrestore(&i8259A_lock, flags);

	pr_debug("... PIC  ISR: %04x\n", v);

	v = inb(PIC_ELCR2) << 8 | inb(PIC_ELCR1);
	pr_debug("... PIC ELCR: %04x\n", v);
}

static int show_lapic __initdata = 1;
static __init int setup_show_lapic(char *arg)
{
	int num = -1;

	if (strcmp(arg, "all") == 0) {
		show_lapic = CONFIG_NR_CPUS;
	} else {
		get_option(&arg, &num);
		if (num >= 0)
			show_lapic = num;
	}

	return 1;
}
__setup("show_lapic=", setup_show_lapic);

static int __init print_ICs(void)
{
	if (apic_verbosity == APIC_QUIET)
		return 0;

	print_PIC();

	/* don't print out if apic is not there */
	if (!boot_cpu_has(X86_FEATURE_APIC) && !apic_from_smp_config())
		return 0;

	print_local_APICs(show_lapic);
	print_IO_APICs();

	return 0;
}

late_initcall(print_ICs);