-
Notifications
You must be signed in to change notification settings - Fork 54.6k
/
vector.c
1396 lines (1183 loc) · 37.1 KB
/
vector.c
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
// 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 (irq_get_nr_irqs() > NR_VECTORS * nr_cpu_ids)
irq_set_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 < irq_get_nr_irqs())
irq_set_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);