forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtopology.c
2007 lines (1673 loc) · 49.2 KB
/
topology.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
/*
* Scheduler topology setup/handling methods
*/
#include "sched.h"
DEFINE_MUTEX(sched_domains_mutex);
/* Protected by sched_domains_mutex: */
static cpumask_var_t sched_domains_tmpmask;
static cpumask_var_t sched_domains_tmpmask2;
#ifdef CONFIG_SCHED_DEBUG
static int __init sched_debug_setup(char *str)
{
sched_debug_enabled = true;
return 0;
}
early_param("sched_debug", sched_debug_setup);
static inline bool sched_debug(void)
{
return sched_debug_enabled;
}
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
struct cpumask *groupmask)
{
struct sched_group *group = sd->groups;
cpumask_clear(groupmask);
printk(KERN_DEBUG "%*s domain-%d: ", level, "", level);
if (!(sd->flags & SD_LOAD_BALANCE)) {
printk("does not load-balance\n");
if (sd->parent)
printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain has parent");
return -1;
}
printk(KERN_CONT "span=%*pbl level=%s\n",
cpumask_pr_args(sched_domain_span(sd)), sd->name);
if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
}
if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) {
printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
}
printk(KERN_DEBUG "%*s groups:", level + 1, "");
do {
if (!group) {
printk("\n");
printk(KERN_ERR "ERROR: group is NULL\n");
break;
}
if (!cpumask_weight(sched_group_span(group))) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: empty group\n");
break;
}
if (!(sd->flags & SD_OVERLAP) &&
cpumask_intersects(groupmask, sched_group_span(group))) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: repeated CPUs\n");
break;
}
cpumask_or(groupmask, groupmask, sched_group_span(group));
printk(KERN_CONT " %d:{ span=%*pbl",
group->sgc->id,
cpumask_pr_args(sched_group_span(group)));
if ((sd->flags & SD_OVERLAP) &&
!cpumask_equal(group_balance_mask(group), sched_group_span(group))) {
printk(KERN_CONT " mask=%*pbl",
cpumask_pr_args(group_balance_mask(group)));
}
if (group->sgc->capacity != SCHED_CAPACITY_SCALE)
printk(KERN_CONT " cap=%lu", group->sgc->capacity);
if (group == sd->groups && sd->child &&
!cpumask_equal(sched_domain_span(sd->child),
sched_group_span(group))) {
printk(KERN_ERR "ERROR: domain->groups does not match domain->child\n");
}
printk(KERN_CONT " }");
group = group->next;
if (group != sd->groups)
printk(KERN_CONT ",");
} while (group != sd->groups);
printk(KERN_CONT "\n");
if (!cpumask_equal(sched_domain_span(sd), groupmask))
printk(KERN_ERR "ERROR: groups don't span domain->span\n");
if (sd->parent &&
!cpumask_subset(groupmask, sched_domain_span(sd->parent)))
printk(KERN_ERR "ERROR: parent span is not a superset of domain->span\n");
return 0;
}
static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
int level = 0;
if (!sched_debug_enabled)
return;
if (!sd) {
printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
return;
}
printk(KERN_DEBUG "CPU%d attaching sched-domain(s):\n", cpu);
for (;;) {
if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
break;
level++;
sd = sd->parent;
if (!sd)
break;
}
}
#else /* !CONFIG_SCHED_DEBUG */
# define sched_debug_enabled 0
# define sched_domain_debug(sd, cpu) do { } while (0)
static inline bool sched_debug(void)
{
return false;
}
#endif /* CONFIG_SCHED_DEBUG */
static int sd_degenerate(struct sched_domain *sd)
{
if (cpumask_weight(sched_domain_span(sd)) == 1)
return 1;
/* Following flags need at least 2 groups */
if (sd->flags & (SD_LOAD_BALANCE |
SD_BALANCE_NEWIDLE |
SD_BALANCE_FORK |
SD_BALANCE_EXEC |
SD_SHARE_CPUCAPACITY |
SD_ASYM_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
SD_SHARE_POWERDOMAIN)) {
if (sd->groups != sd->groups->next)
return 0;
}
/* Following flags don't use groups */
if (sd->flags & (SD_WAKE_AFFINE))
return 0;
return 1;
}
static int
sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
{
unsigned long cflags = sd->flags, pflags = parent->flags;
if (sd_degenerate(parent))
return 1;
if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
return 0;
/* Flags needing groups don't count if only 1 group in parent */
if (parent->groups == parent->groups->next) {
pflags &= ~(SD_LOAD_BALANCE |
SD_BALANCE_NEWIDLE |
SD_BALANCE_FORK |
SD_BALANCE_EXEC |
SD_ASYM_CPUCAPACITY |
SD_SHARE_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
SD_PREFER_SIBLING |
SD_SHARE_POWERDOMAIN);
if (nr_node_ids == 1)
pflags &= ~SD_SERIALIZE;
}
if (~cflags & pflags)
return 0;
return 1;
}
static void free_rootdomain(struct rcu_head *rcu)
{
struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
cpupri_cleanup(&rd->cpupri);
cpudl_cleanup(&rd->cpudl);
free_cpumask_var(rd->dlo_mask);
free_cpumask_var(rd->rto_mask);
free_cpumask_var(rd->online);
free_cpumask_var(rd->span);
kfree(rd);
}
void rq_attach_root(struct rq *rq, struct root_domain *rd)
{
struct root_domain *old_rd = NULL;
unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
old_rd = rq->rd;
if (cpumask_test_cpu(rq->cpu, old_rd->online))
set_rq_offline(rq);
cpumask_clear_cpu(rq->cpu, old_rd->span);
/*
* If we dont want to free the old_rd yet then
* set old_rd to NULL to skip the freeing later
* in this function:
*/
if (!atomic_dec_and_test(&old_rd->refcount))
old_rd = NULL;
}
atomic_inc(&rd->refcount);
rq->rd = rd;
cpumask_set_cpu(rq->cpu, rd->span);
if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
set_rq_online(rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
if (old_rd)
call_rcu_sched(&old_rd->rcu, free_rootdomain);
}
void sched_get_rd(struct root_domain *rd)
{
atomic_inc(&rd->refcount);
}
void sched_put_rd(struct root_domain *rd)
{
if (!atomic_dec_and_test(&rd->refcount))
return;
call_rcu_sched(&rd->rcu, free_rootdomain);
}
static int init_rootdomain(struct root_domain *rd)
{
if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
goto out;
if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
goto free_span;
if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
goto free_online;
if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
goto free_dlo_mask;
#ifdef HAVE_RT_PUSH_IPI
rd->rto_cpu = -1;
raw_spin_lock_init(&rd->rto_lock);
init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
#endif
init_dl_bw(&rd->dl_bw);
if (cpudl_init(&rd->cpudl) != 0)
goto free_rto_mask;
if (cpupri_init(&rd->cpupri) != 0)
goto free_cpudl;
return 0;
free_cpudl:
cpudl_cleanup(&rd->cpudl);
free_rto_mask:
free_cpumask_var(rd->rto_mask);
free_dlo_mask:
free_cpumask_var(rd->dlo_mask);
free_online:
free_cpumask_var(rd->online);
free_span:
free_cpumask_var(rd->span);
out:
return -ENOMEM;
}
/*
* By default the system creates a single root-domain with all CPUs as
* members (mimicking the global state we have today).
*/
struct root_domain def_root_domain;
void init_defrootdomain(void)
{
init_rootdomain(&def_root_domain);
atomic_set(&def_root_domain.refcount, 1);
}
static struct root_domain *alloc_rootdomain(void)
{
struct root_domain *rd;
rd = kzalloc(sizeof(*rd), GFP_KERNEL);
if (!rd)
return NULL;
if (init_rootdomain(rd) != 0) {
kfree(rd);
return NULL;
}
return rd;
}
static void free_sched_groups(struct sched_group *sg, int free_sgc)
{
struct sched_group *tmp, *first;
if (!sg)
return;
first = sg;
do {
tmp = sg->next;
if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
kfree(sg->sgc);
if (atomic_dec_and_test(&sg->ref))
kfree(sg);
sg = tmp;
} while (sg != first);
}
static void destroy_sched_domain(struct sched_domain *sd)
{
/*
* A normal sched domain may have multiple group references, an
* overlapping domain, having private groups, only one. Iterate,
* dropping group/capacity references, freeing where none remain.
*/
free_sched_groups(sd->groups, 1);
if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
kfree(sd->shared);
kfree(sd);
}
static void destroy_sched_domains_rcu(struct rcu_head *rcu)
{
struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
while (sd) {
struct sched_domain *parent = sd->parent;
destroy_sched_domain(sd);
sd = parent;
}
}
static void destroy_sched_domains(struct sched_domain *sd)
{
if (sd)
call_rcu(&sd->rcu, destroy_sched_domains_rcu);
}
/*
* Keep a special pointer to the highest sched_domain that has
* SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
* allows us to avoid some pointer chasing select_idle_sibling().
*
* Also keep a unique ID per domain (we use the first CPU number in
* the cpumask of the domain), this allows us to quickly tell if
* two CPUs are in the same cache domain, see cpus_share_cache().
*/
DEFINE_PER_CPU(struct sched_domain *, sd_llc);
DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
DEFINE_PER_CPU(struct sched_domain *, sd_asym);
DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
static void update_top_cache_domain(int cpu)
{
struct sched_domain_shared *sds = NULL;
struct sched_domain *sd;
int id = cpu;
int size = 1;
sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
if (sd) {
id = cpumask_first(sched_domain_span(sd));
size = cpumask_weight(sched_domain_span(sd));
sds = sd->shared;
}
rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
per_cpu(sd_llc_size, cpu) = size;
per_cpu(sd_llc_id, cpu) = id;
rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
sd = lowest_flag_domain(cpu, SD_NUMA);
rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
}
/*
* Attach the domain 'sd' to 'cpu' as its base domain. Callers must
* hold the hotplug lock.
*/
static void
cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct sched_domain *tmp;
/* Remove the sched domains which do not contribute to scheduling. */
for (tmp = sd; tmp; ) {
struct sched_domain *parent = tmp->parent;
if (!parent)
break;
if (sd_parent_degenerate(tmp, parent)) {
tmp->parent = parent->parent;
if (parent->parent)
parent->parent->child = tmp;
/*
* Transfer SD_PREFER_SIBLING down in case of a
* degenerate parent; the spans match for this
* so the property transfers.
*/
if (parent->flags & SD_PREFER_SIBLING)
tmp->flags |= SD_PREFER_SIBLING;
destroy_sched_domain(parent);
} else
tmp = tmp->parent;
}
if (sd && sd_degenerate(sd)) {
tmp = sd;
sd = sd->parent;
destroy_sched_domain(tmp);
if (sd)
sd->child = NULL;
}
sched_domain_debug(sd, cpu);
rq_attach_root(rq, rd);
tmp = rq->sd;
rcu_assign_pointer(rq->sd, sd);
dirty_sched_domain_sysctl(cpu);
destroy_sched_domains(tmp);
update_top_cache_domain(cpu);
}
struct s_data {
struct sched_domain ** __percpu sd;
struct root_domain *rd;
};
enum s_alloc {
sa_rootdomain,
sa_sd,
sa_sd_storage,
sa_none,
};
/*
* Return the canonical balance CPU for this group, this is the first CPU
* of this group that's also in the balance mask.
*
* The balance mask are all those CPUs that could actually end up at this
* group. See build_balance_mask().
*
* Also see should_we_balance().
*/
int group_balance_cpu(struct sched_group *sg)
{
return cpumask_first(group_balance_mask(sg));
}
/*
* NUMA topology (first read the regular topology blurb below)
*
* Given a node-distance table, for example:
*
* node 0 1 2 3
* 0: 10 20 30 20
* 1: 20 10 20 30
* 2: 30 20 10 20
* 3: 20 30 20 10
*
* which represents a 4 node ring topology like:
*
* 0 ----- 1
* | |
* | |
* | |
* 3 ----- 2
*
* We want to construct domains and groups to represent this. The way we go
* about doing this is to build the domains on 'hops'. For each NUMA level we
* construct the mask of all nodes reachable in @level hops.
*
* For the above NUMA topology that gives 3 levels:
*
* NUMA-2 0-3 0-3 0-3 0-3
* groups: {0-1,3},{1-3} {0-2},{0,2-3} {1-3},{0-1,3} {0,2-3},{0-2}
*
* NUMA-1 0-1,3 0-2 1-3 0,2-3
* groups: {0},{1},{3} {0},{1},{2} {1},{2},{3} {0},{2},{3}
*
* NUMA-0 0 1 2 3
*
*
* As can be seen; things don't nicely line up as with the regular topology.
* When we iterate a domain in child domain chunks some nodes can be
* represented multiple times -- hence the "overlap" naming for this part of
* the topology.
*
* In order to minimize this overlap, we only build enough groups to cover the
* domain. For instance Node-0 NUMA-2 would only get groups: 0-1,3 and 1-3.
*
* Because:
*
* - the first group of each domain is its child domain; this
* gets us the first 0-1,3
* - the only uncovered node is 2, who's child domain is 1-3.
*
* However, because of the overlap, computing a unique CPU for each group is
* more complicated. Consider for instance the groups of NODE-1 NUMA-2, both
* groups include the CPUs of Node-0, while those CPUs would not in fact ever
* end up at those groups (they would end up in group: 0-1,3).
*
* To correct this we have to introduce the group balance mask. This mask
* will contain those CPUs in the group that can reach this group given the
* (child) domain tree.
*
* With this we can once again compute balance_cpu and sched_group_capacity
* relations.
*
* XXX include words on how balance_cpu is unique and therefore can be
* used for sched_group_capacity links.
*
*
* Another 'interesting' topology is:
*
* node 0 1 2 3
* 0: 10 20 20 30
* 1: 20 10 20 20
* 2: 20 20 10 20
* 3: 30 20 20 10
*
* Which looks a little like:
*
* 0 ----- 1
* | / |
* | / |
* | / |
* 2 ----- 3
*
* This topology is asymmetric, nodes 1,2 are fully connected, but nodes 0,3
* are not.
*
* This leads to a few particularly weird cases where the sched_domain's are
* not of the same number for each CPU. Consider:
*
* NUMA-2 0-3 0-3
* groups: {0-2},{1-3} {1-3},{0-2}
*
* NUMA-1 0-2 0-3 0-3 1-3
*
* NUMA-0 0 1 2 3
*
*/
/*
* Build the balance mask; it contains only those CPUs that can arrive at this
* group and should be considered to continue balancing.
*
* We do this during the group creation pass, therefore the group information
* isn't complete yet, however since each group represents a (child) domain we
* can fully construct this using the sched_domain bits (which are already
* complete).
*/
static void
build_balance_mask(struct sched_domain *sd, struct sched_group *sg, struct cpumask *mask)
{
const struct cpumask *sg_span = sched_group_span(sg);
struct sd_data *sdd = sd->private;
struct sched_domain *sibling;
int i;
cpumask_clear(mask);
for_each_cpu(i, sg_span) {
sibling = *per_cpu_ptr(sdd->sd, i);
/*
* Can happen in the asymmetric case, where these siblings are
* unused. The mask will not be empty because those CPUs that
* do have the top domain _should_ span the domain.
*/
if (!sibling->child)
continue;
/* If we would not end up here, we can't continue from here */
if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
continue;
cpumask_set_cpu(i, mask);
}
/* We must not have empty masks here */
WARN_ON_ONCE(cpumask_empty(mask));
}
/*
* XXX: This creates per-node group entries; since the load-balancer will
* immediately access remote memory to construct this group's load-balance
* statistics having the groups node local is of dubious benefit.
*/
static struct sched_group *
build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
{
struct sched_group *sg;
struct cpumask *sg_span;
sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
GFP_KERNEL, cpu_to_node(cpu));
if (!sg)
return NULL;
sg_span = sched_group_span(sg);
if (sd->child)
cpumask_copy(sg_span, sched_domain_span(sd->child));
else
cpumask_copy(sg_span, sched_domain_span(sd));
atomic_inc(&sg->ref);
return sg;
}
static void init_overlap_sched_group(struct sched_domain *sd,
struct sched_group *sg)
{
struct cpumask *mask = sched_domains_tmpmask2;
struct sd_data *sdd = sd->private;
struct cpumask *sg_span;
int cpu;
build_balance_mask(sd, sg, mask);
cpu = cpumask_first_and(sched_group_span(sg), mask);
sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
if (atomic_inc_return(&sg->sgc->ref) == 1)
cpumask_copy(group_balance_mask(sg), mask);
else
WARN_ON_ONCE(!cpumask_equal(group_balance_mask(sg), mask));
/*
* Initialize sgc->capacity such that even if we mess up the
* domains and no possible iteration will get us here, we won't
* die on a /0 trap.
*/
sg_span = sched_group_span(sg);
sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
}
static int
build_overlap_sched_groups(struct sched_domain *sd, int cpu)
{
struct sched_group *first = NULL, *last = NULL, *sg;
const struct cpumask *span = sched_domain_span(sd);
struct cpumask *covered = sched_domains_tmpmask;
struct sd_data *sdd = sd->private;
struct sched_domain *sibling;
int i;
cpumask_clear(covered);
for_each_cpu_wrap(i, span, cpu) {
struct cpumask *sg_span;
if (cpumask_test_cpu(i, covered))
continue;
sibling = *per_cpu_ptr(sdd->sd, i);
/*
* Asymmetric node setups can result in situations where the
* domain tree is of unequal depth, make sure to skip domains
* that already cover the entire range.
*
* In that case build_sched_domains() will have terminated the
* iteration early and our sibling sd spans will be empty.
* Domains should always include the CPU they're built on, so
* check that.
*/
if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
continue;
sg = build_group_from_child_sched_domain(sibling, cpu);
if (!sg)
goto fail;
sg_span = sched_group_span(sg);
cpumask_or(covered, covered, sg_span);
init_overlap_sched_group(sd, sg);
if (!first)
first = sg;
if (last)
last->next = sg;
last = sg;
last->next = first;
}
sd->groups = first;
return 0;
fail:
free_sched_groups(first, 0);
return -ENOMEM;
}
/*
* Package topology (also see the load-balance blurb in fair.c)
*
* The scheduler builds a tree structure to represent a number of important
* topology features. By default (default_topology[]) these include:
*
* - Simultaneous multithreading (SMT)
* - Multi-Core Cache (MC)
* - Package (DIE)
*
* Where the last one more or less denotes everything up to a NUMA node.
*
* The tree consists of 3 primary data structures:
*
* sched_domain -> sched_group -> sched_group_capacity
* ^ ^ ^ ^
* `-' `-'
*
* The sched_domains are per-CPU and have a two way link (parent & child) and
* denote the ever growing mask of CPUs belonging to that level of topology.
*
* Each sched_domain has a circular (double) linked list of sched_group's, each
* denoting the domains of the level below (or individual CPUs in case of the
* first domain level). The sched_group linked by a sched_domain includes the
* CPU of that sched_domain [*].
*
* Take for instance a 2 threaded, 2 core, 2 cache cluster part:
*
* CPU 0 1 2 3 4 5 6 7
*
* DIE [ ]
* MC [ ] [ ]
* SMT [ ] [ ] [ ] [ ]
*
* - or -
*
* DIE 0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
* MC 0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
* SMT 0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
*
* CPU 0 1 2 3 4 5 6 7
*
* One way to think about it is: sched_domain moves you up and down among these
* topology levels, while sched_group moves you sideways through it, at child
* domain granularity.
*
* sched_group_capacity ensures each unique sched_group has shared storage.
*
* There are two related construction problems, both require a CPU that
* uniquely identify each group (for a given domain):
*
* - The first is the balance_cpu (see should_we_balance() and the
* load-balance blub in fair.c); for each group we only want 1 CPU to
* continue balancing at a higher domain.
*
* - The second is the sched_group_capacity; we want all identical groups
* to share a single sched_group_capacity.
*
* Since these topologies are exclusive by construction. That is, its
* impossible for an SMT thread to belong to multiple cores, and cores to
* be part of multiple caches. There is a very clear and unique location
* for each CPU in the hierarchy.
*
* Therefore computing a unique CPU for each group is trivial (the iteration
* mask is redundant and set all 1s; all CPUs in a group will end up at _that_
* group), we can simply pick the first CPU in each group.
*
*
* [*] in other words, the first group of each domain is its child domain.
*/
static struct sched_group *get_group(int cpu, struct sd_data *sdd)
{
struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
struct sched_domain *child = sd->child;
struct sched_group *sg;
if (child)
cpu = cpumask_first(sched_domain_span(child));
sg = *per_cpu_ptr(sdd->sg, cpu);
sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
/* For claim_allocations: */
atomic_inc(&sg->ref);
atomic_inc(&sg->sgc->ref);
if (child) {
cpumask_copy(sched_group_span(sg), sched_domain_span(child));
cpumask_copy(group_balance_mask(sg), sched_group_span(sg));
} else {
cpumask_set_cpu(cpu, sched_group_span(sg));
cpumask_set_cpu(cpu, group_balance_mask(sg));
}
sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg));
sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
return sg;
}
/*
* build_sched_groups will build a circular linked list of the groups
* covered by the given span, and will set each group's ->cpumask correctly,
* and ->cpu_capacity to 0.
*
* Assumes the sched_domain tree is fully constructed
*/
static int
build_sched_groups(struct sched_domain *sd, int cpu)
{
struct sched_group *first = NULL, *last = NULL;
struct sd_data *sdd = sd->private;
const struct cpumask *span = sched_domain_span(sd);
struct cpumask *covered;
int i;
lockdep_assert_held(&sched_domains_mutex);
covered = sched_domains_tmpmask;
cpumask_clear(covered);
for_each_cpu_wrap(i, span, cpu) {
struct sched_group *sg;
if (cpumask_test_cpu(i, covered))
continue;
sg = get_group(i, sdd);
cpumask_or(covered, covered, sched_group_span(sg));
if (!first)
first = sg;
if (last)
last->next = sg;
last = sg;
}
last->next = first;
sd->groups = first;
return 0;
}
/*
* Initialize sched groups cpu_capacity.
*
* cpu_capacity indicates the capacity of sched group, which is used while
* distributing the load between different sched groups in a sched domain.
* Typically cpu_capacity for all the groups in a sched domain will be same
* unless there are asymmetries in the topology. If there are asymmetries,
* group having more cpu_capacity will pickup more load compared to the
* group having less cpu_capacity.
*/
static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
{
struct sched_group *sg = sd->groups;
WARN_ON(!sg);
do {
int cpu, max_cpu = -1;
sg->group_weight = cpumask_weight(sched_group_span(sg));
if (!(sd->flags & SD_ASYM_PACKING))
goto next;
for_each_cpu(cpu, sched_group_span(sg)) {
if (max_cpu < 0)
max_cpu = cpu;
else if (sched_asym_prefer(cpu, max_cpu))
max_cpu = cpu;
}
sg->asym_prefer_cpu = max_cpu;
next:
sg = sg->next;
} while (sg != sd->groups);
if (cpu != group_balance_cpu(sg))
return;
update_group_capacity(sd, cpu);
}
/*
* Initializers for schedule domains
* Non-inlined to reduce accumulated stack pressure in build_sched_domains()
*/
static int default_relax_domain_level = -1;
int sched_domain_level_max;
static int __init setup_relax_domain_level(char *str)
{
if (kstrtoint(str, 0, &default_relax_domain_level))
pr_warn("Unable to set relax_domain_level\n");
return 1;
}
__setup("relax_domain_level=", setup_relax_domain_level);
static void set_domain_attribute(struct sched_domain *sd,
struct sched_domain_attr *attr)
{
int request;
if (!attr || attr->relax_domain_level < 0) {
if (default_relax_domain_level < 0)
return;
else
request = default_relax_domain_level;
} else
request = attr->relax_domain_level;
if (request < sd->level) {
/* Turn off idle balance on this domain: */
sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
} else {
/* Turn on idle balance on this domain: */
sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
}
}
static void __sdt_free(const struct cpumask *cpu_map);
static int __sdt_alloc(const struct cpumask *cpu_map);
static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
const struct cpumask *cpu_map)
{
switch (what) {
case sa_rootdomain:
if (!atomic_read(&d->rd->refcount))
free_rootdomain(&d->rd->rcu);
/* Fall through */
case sa_sd:
free_percpu(d->sd);
/* Fall through */
case sa_sd_storage:
__sdt_free(cpu_map);
/* Fall through */