forked from Sricharanti/sricharan
-
Notifications
You must be signed in to change notification settings - Fork 0
/
blk-cgroup.c
1683 lines (1477 loc) · 42.9 KB
/
blk-cgroup.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
/*
* Common Block IO controller cgroup interface
*
* Based on ideas and code from CFQ, CFS and BFQ:
* Copyright (C) 2003 Jens Axboe <[email protected]>
*
* Copyright (C) 2008 Fabio Checconi <[email protected]>
* Paolo Valente <[email protected]>
*
* Copyright (C) 2009 Vivek Goyal <[email protected]>
* Nauman Rafique <[email protected]>
*/
#include <linux/ioprio.h>
#include <linux/seq_file.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include "blk-cgroup.h"
#include <linux/genhd.h>
#define MAX_KEY_LEN 100
static DEFINE_SPINLOCK(blkio_list_lock);
static LIST_HEAD(blkio_list);
struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
EXPORT_SYMBOL_GPL(blkio_root_cgroup);
static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,
struct cgroup *);
static int blkiocg_can_attach_task(struct cgroup *, struct task_struct *);
static void blkiocg_attach_task(struct cgroup *, struct task_struct *);
static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);
static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
/* for encoding cft->private value on file */
#define BLKIOFILE_PRIVATE(x, val) (((x) << 16) | (val))
/* What policy owns the file, proportional or throttle */
#define BLKIOFILE_POLICY(val) (((val) >> 16) & 0xffff)
#define BLKIOFILE_ATTR(val) ((val) & 0xffff)
struct cgroup_subsys blkio_subsys = {
.name = "blkio",
.create = blkiocg_create,
.can_attach_task = blkiocg_can_attach_task,
.attach_task = blkiocg_attach_task,
.destroy = blkiocg_destroy,
.populate = blkiocg_populate,
#ifdef CONFIG_BLK_CGROUP
/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
.subsys_id = blkio_subsys_id,
#endif
.use_id = 1,
.module = THIS_MODULE,
};
EXPORT_SYMBOL_GPL(blkio_subsys);
static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg,
struct blkio_policy_node *pn)
{
list_add(&pn->node, &blkcg->policy_list);
}
static inline bool cftype_blkg_same_policy(struct cftype *cft,
struct blkio_group *blkg)
{
enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
if (blkg->plid == plid)
return 1;
return 0;
}
/* Determines if policy node matches cgroup file being accessed */
static inline bool pn_matches_cftype(struct cftype *cft,
struct blkio_policy_node *pn)
{
enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
int fileid = BLKIOFILE_ATTR(cft->private);
return (plid == pn->plid && fileid == pn->fileid);
}
/* Must be called with blkcg->lock held */
static inline void blkio_policy_delete_node(struct blkio_policy_node *pn)
{
list_del(&pn->node);
}
/* Must be called with blkcg->lock held */
static struct blkio_policy_node *
blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev,
enum blkio_policy_id plid, int fileid)
{
struct blkio_policy_node *pn;
list_for_each_entry(pn, &blkcg->policy_list, node) {
if (pn->dev == dev && pn->plid == plid && pn->fileid == fileid)
return pn;
}
return NULL;
}
struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
{
return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
struct blkio_cgroup, css);
}
EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk)
{
return container_of(task_subsys_state(tsk, blkio_subsys_id),
struct blkio_cgroup, css);
}
EXPORT_SYMBOL_GPL(task_blkio_cgroup);
static inline void
blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
{
struct blkio_policy_type *blkiop;
list_for_each_entry(blkiop, &blkio_list, list) {
/* If this policy does not own the blkg, do not send updates */
if (blkiop->plid != blkg->plid)
continue;
if (blkiop->ops.blkio_update_group_weight_fn)
blkiop->ops.blkio_update_group_weight_fn(blkg->key,
blkg, weight);
}
}
static inline void blkio_update_group_bps(struct blkio_group *blkg, u64 bps,
int fileid)
{
struct blkio_policy_type *blkiop;
list_for_each_entry(blkiop, &blkio_list, list) {
/* If this policy does not own the blkg, do not send updates */
if (blkiop->plid != blkg->plid)
continue;
if (fileid == BLKIO_THROTL_read_bps_device
&& blkiop->ops.blkio_update_group_read_bps_fn)
blkiop->ops.blkio_update_group_read_bps_fn(blkg->key,
blkg, bps);
if (fileid == BLKIO_THROTL_write_bps_device
&& blkiop->ops.blkio_update_group_write_bps_fn)
blkiop->ops.blkio_update_group_write_bps_fn(blkg->key,
blkg, bps);
}
}
static inline void blkio_update_group_iops(struct blkio_group *blkg,
unsigned int iops, int fileid)
{
struct blkio_policy_type *blkiop;
list_for_each_entry(blkiop, &blkio_list, list) {
/* If this policy does not own the blkg, do not send updates */
if (blkiop->plid != blkg->plid)
continue;
if (fileid == BLKIO_THROTL_read_iops_device
&& blkiop->ops.blkio_update_group_read_iops_fn)
blkiop->ops.blkio_update_group_read_iops_fn(blkg->key,
blkg, iops);
if (fileid == BLKIO_THROTL_write_iops_device
&& blkiop->ops.blkio_update_group_write_iops_fn)
blkiop->ops.blkio_update_group_write_iops_fn(blkg->key,
blkg,iops);
}
}
/*
* Add to the appropriate stat variable depending on the request type.
* This should be called with the blkg->stats_lock held.
*/
static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction,
bool sync)
{
if (direction)
stat[BLKIO_STAT_WRITE] += add;
else
stat[BLKIO_STAT_READ] += add;
if (sync)
stat[BLKIO_STAT_SYNC] += add;
else
stat[BLKIO_STAT_ASYNC] += add;
}
/*
* Decrements the appropriate stat variable if non-zero depending on the
* request type. Panics on value being zero.
* This should be called with the blkg->stats_lock held.
*/
static void blkio_check_and_dec_stat(uint64_t *stat, bool direction, bool sync)
{
if (direction) {
BUG_ON(stat[BLKIO_STAT_WRITE] == 0);
stat[BLKIO_STAT_WRITE]--;
} else {
BUG_ON(stat[BLKIO_STAT_READ] == 0);
stat[BLKIO_STAT_READ]--;
}
if (sync) {
BUG_ON(stat[BLKIO_STAT_SYNC] == 0);
stat[BLKIO_STAT_SYNC]--;
} else {
BUG_ON(stat[BLKIO_STAT_ASYNC] == 0);
stat[BLKIO_STAT_ASYNC]--;
}
}
#ifdef CONFIG_DEBUG_BLK_CGROUP
/* This should be called with the blkg->stats_lock held. */
static void blkio_set_start_group_wait_time(struct blkio_group *blkg,
struct blkio_group *curr_blkg)
{
if (blkio_blkg_waiting(&blkg->stats))
return;
if (blkg == curr_blkg)
return;
blkg->stats.start_group_wait_time = sched_clock();
blkio_mark_blkg_waiting(&blkg->stats);
}
/* This should be called with the blkg->stats_lock held. */
static void blkio_update_group_wait_time(struct blkio_group_stats *stats)
{
unsigned long long now;
if (!blkio_blkg_waiting(stats))
return;
now = sched_clock();
if (time_after64(now, stats->start_group_wait_time))
stats->group_wait_time += now - stats->start_group_wait_time;
blkio_clear_blkg_waiting(stats);
}
/* This should be called with the blkg->stats_lock held. */
static void blkio_end_empty_time(struct blkio_group_stats *stats)
{
unsigned long long now;
if (!blkio_blkg_empty(stats))
return;
now = sched_clock();
if (time_after64(now, stats->start_empty_time))
stats->empty_time += now - stats->start_empty_time;
blkio_clear_blkg_empty(stats);
}
void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg)
{
unsigned long flags;
spin_lock_irqsave(&blkg->stats_lock, flags);
BUG_ON(blkio_blkg_idling(&blkg->stats));
blkg->stats.start_idle_time = sched_clock();
blkio_mark_blkg_idling(&blkg->stats);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_set_idle_time_stats);
void blkiocg_update_idle_time_stats(struct blkio_group *blkg)
{
unsigned long flags;
unsigned long long now;
struct blkio_group_stats *stats;
spin_lock_irqsave(&blkg->stats_lock, flags);
stats = &blkg->stats;
if (blkio_blkg_idling(stats)) {
now = sched_clock();
if (time_after64(now, stats->start_idle_time))
stats->idle_time += now - stats->start_idle_time;
blkio_clear_blkg_idling(stats);
}
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_idle_time_stats);
void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg)
{
unsigned long flags;
struct blkio_group_stats *stats;
spin_lock_irqsave(&blkg->stats_lock, flags);
stats = &blkg->stats;
stats->avg_queue_size_sum +=
stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] +
stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE];
stats->avg_queue_size_samples++;
blkio_update_group_wait_time(stats);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_avg_queue_size_stats);
void blkiocg_set_start_empty_time(struct blkio_group *blkg)
{
unsigned long flags;
struct blkio_group_stats *stats;
spin_lock_irqsave(&blkg->stats_lock, flags);
stats = &blkg->stats;
if (stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] ||
stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]) {
spin_unlock_irqrestore(&blkg->stats_lock, flags);
return;
}
/*
* group is already marked empty. This can happen if cfqq got new
* request in parent group and moved to this group while being added
* to service tree. Just ignore the event and move on.
*/
if(blkio_blkg_empty(stats)) {
spin_unlock_irqrestore(&blkg->stats_lock, flags);
return;
}
stats->start_empty_time = sched_clock();
blkio_mark_blkg_empty(stats);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_set_start_empty_time);
void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
unsigned long dequeue)
{
blkg->stats.dequeue += dequeue;
}
EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats);
#else
static inline void blkio_set_start_group_wait_time(struct blkio_group *blkg,
struct blkio_group *curr_blkg) {}
static inline void blkio_end_empty_time(struct blkio_group_stats *stats) {}
#endif
void blkiocg_update_io_add_stats(struct blkio_group *blkg,
struct blkio_group *curr_blkg, bool direction,
bool sync)
{
unsigned long flags;
spin_lock_irqsave(&blkg->stats_lock, flags);
blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], 1, direction,
sync);
blkio_end_empty_time(&blkg->stats);
blkio_set_start_group_wait_time(blkg, curr_blkg);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_add_stats);
void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
bool direction, bool sync)
{
unsigned long flags;
spin_lock_irqsave(&blkg->stats_lock, flags);
blkio_check_and_dec_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED],
direction, sync);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats);
void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time,
unsigned long unaccounted_time)
{
unsigned long flags;
spin_lock_irqsave(&blkg->stats_lock, flags);
blkg->stats.time += time;
#ifdef CONFIG_DEBUG_BLK_CGROUP
blkg->stats.unaccounted_time += unaccounted_time;
#endif
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
/*
* should be called under rcu read lock or queue lock to make sure blkg pointer
* is valid.
*/
void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
uint64_t bytes, bool direction, bool sync)
{
struct blkio_group_stats_cpu *stats_cpu;
unsigned long flags;
/*
* Disabling interrupts to provide mutual exclusion between two
* writes on same cpu. It probably is not needed for 64bit. Not
* optimizing that case yet.
*/
local_irq_save(flags);
stats_cpu = this_cpu_ptr(blkg->stats_cpu);
u64_stats_update_begin(&stats_cpu->syncp);
stats_cpu->sectors += bytes >> 9;
blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICED],
1, direction, sync);
blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICE_BYTES],
bytes, direction, sync);
u64_stats_update_end(&stats_cpu->syncp);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats);
void blkiocg_update_completion_stats(struct blkio_group *blkg,
uint64_t start_time, uint64_t io_start_time, bool direction, bool sync)
{
struct blkio_group_stats *stats;
unsigned long flags;
unsigned long long now = sched_clock();
spin_lock_irqsave(&blkg->stats_lock, flags);
stats = &blkg->stats;
if (time_after64(now, io_start_time))
blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_TIME],
now - io_start_time, direction, sync);
if (time_after64(io_start_time, start_time))
blkio_add_stat(stats->stat_arr[BLKIO_STAT_WAIT_TIME],
io_start_time - start_time, direction, sync);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats);
/* Merged stats are per cpu. */
void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
bool sync)
{
struct blkio_group_stats_cpu *stats_cpu;
unsigned long flags;
/*
* Disabling interrupts to provide mutual exclusion between two
* writes on same cpu. It probably is not needed for 64bit. Not
* optimizing that case yet.
*/
local_irq_save(flags);
stats_cpu = this_cpu_ptr(blkg->stats_cpu);
u64_stats_update_begin(&stats_cpu->syncp);
blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_MERGED], 1,
direction, sync);
u64_stats_update_end(&stats_cpu->syncp);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
/*
* This function allocates the per cpu stats for blkio_group. Should be called
* from sleepable context as alloc_per_cpu() requires that.
*/
int blkio_alloc_blkg_stats(struct blkio_group *blkg)
{
/* Allocate memory for per cpu stats */
blkg->stats_cpu = alloc_percpu(struct blkio_group_stats_cpu);
if (!blkg->stats_cpu)
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL_GPL(blkio_alloc_blkg_stats);
void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
struct blkio_group *blkg, void *key, dev_t dev,
enum blkio_policy_id plid)
{
unsigned long flags;
spin_lock_irqsave(&blkcg->lock, flags);
spin_lock_init(&blkg->stats_lock);
rcu_assign_pointer(blkg->key, key);
blkg->blkcg_id = css_id(&blkcg->css);
hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
blkg->plid = plid;
spin_unlock_irqrestore(&blkcg->lock, flags);
/* Need to take css reference ? */
cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
blkg->dev = dev;
}
EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group);
static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
{
hlist_del_init_rcu(&blkg->blkcg_node);
blkg->blkcg_id = 0;
}
/*
* returns 0 if blkio_group was still on cgroup list. Otherwise returns 1
* indicating that blk_group was unhashed by the time we got to it.
*/
int blkiocg_del_blkio_group(struct blkio_group *blkg)
{
struct blkio_cgroup *blkcg;
unsigned long flags;
struct cgroup_subsys_state *css;
int ret = 1;
rcu_read_lock();
css = css_lookup(&blkio_subsys, blkg->blkcg_id);
if (css) {
blkcg = container_of(css, struct blkio_cgroup, css);
spin_lock_irqsave(&blkcg->lock, flags);
if (!hlist_unhashed(&blkg->blkcg_node)) {
__blkiocg_del_blkio_group(blkg);
ret = 0;
}
spin_unlock_irqrestore(&blkcg->lock, flags);
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(blkiocg_del_blkio_group);
/* called under rcu_read_lock(). */
struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
{
struct blkio_group *blkg;
struct hlist_node *n;
void *__key;
hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
__key = blkg->key;
if (__key == key)
return blkg;
}
return NULL;
}
EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
static void blkio_reset_stats_cpu(struct blkio_group *blkg)
{
struct blkio_group_stats_cpu *stats_cpu;
int i, j, k;
/*
* Note: On 64 bit arch this should not be an issue. This has the
* possibility of returning some inconsistent value on 32bit arch
* as 64bit update on 32bit is non atomic. Taking care of this
* corner case makes code very complicated, like sending IPIs to
* cpus, taking care of stats of offline cpus etc.
*
* reset stats is anyway more of a debug feature and this sounds a
* corner case. So I am not complicating the code yet until and
* unless this becomes a real issue.
*/
for_each_possible_cpu(i) {
stats_cpu = per_cpu_ptr(blkg->stats_cpu, i);
stats_cpu->sectors = 0;
for(j = 0; j < BLKIO_STAT_CPU_NR; j++)
for (k = 0; k < BLKIO_STAT_TOTAL; k++)
stats_cpu->stat_arr_cpu[j][k] = 0;
}
}
static int
blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
{
struct blkio_cgroup *blkcg;
struct blkio_group *blkg;
struct blkio_group_stats *stats;
struct hlist_node *n;
uint64_t queued[BLKIO_STAT_TOTAL];
int i;
#ifdef CONFIG_DEBUG_BLK_CGROUP
bool idling, waiting, empty;
unsigned long long now = sched_clock();
#endif
blkcg = cgroup_to_blkio_cgroup(cgroup);
spin_lock_irq(&blkcg->lock);
hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
spin_lock(&blkg->stats_lock);
stats = &blkg->stats;
#ifdef CONFIG_DEBUG_BLK_CGROUP
idling = blkio_blkg_idling(stats);
waiting = blkio_blkg_waiting(stats);
empty = blkio_blkg_empty(stats);
#endif
for (i = 0; i < BLKIO_STAT_TOTAL; i++)
queued[i] = stats->stat_arr[BLKIO_STAT_QUEUED][i];
memset(stats, 0, sizeof(struct blkio_group_stats));
for (i = 0; i < BLKIO_STAT_TOTAL; i++)
stats->stat_arr[BLKIO_STAT_QUEUED][i] = queued[i];
#ifdef CONFIG_DEBUG_BLK_CGROUP
if (idling) {
blkio_mark_blkg_idling(stats);
stats->start_idle_time = now;
}
if (waiting) {
blkio_mark_blkg_waiting(stats);
stats->start_group_wait_time = now;
}
if (empty) {
blkio_mark_blkg_empty(stats);
stats->start_empty_time = now;
}
#endif
spin_unlock(&blkg->stats_lock);
/* Reset Per cpu stats which don't take blkg->stats_lock */
blkio_reset_stats_cpu(blkg);
}
spin_unlock_irq(&blkcg->lock);
return 0;
}
static void blkio_get_key_name(enum stat_sub_type type, dev_t dev, char *str,
int chars_left, bool diskname_only)
{
snprintf(str, chars_left, "%d:%d", MAJOR(dev), MINOR(dev));
chars_left -= strlen(str);
if (chars_left <= 0) {
printk(KERN_WARNING
"Possibly incorrect cgroup stat display format");
return;
}
if (diskname_only)
return;
switch (type) {
case BLKIO_STAT_READ:
strlcat(str, " Read", chars_left);
break;
case BLKIO_STAT_WRITE:
strlcat(str, " Write", chars_left);
break;
case BLKIO_STAT_SYNC:
strlcat(str, " Sync", chars_left);
break;
case BLKIO_STAT_ASYNC:
strlcat(str, " Async", chars_left);
break;
case BLKIO_STAT_TOTAL:
strlcat(str, " Total", chars_left);
break;
default:
strlcat(str, " Invalid", chars_left);
}
}
static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val,
struct cgroup_map_cb *cb, dev_t dev)
{
blkio_get_key_name(0, dev, str, chars_left, true);
cb->fill(cb, str, val);
return val;
}
static uint64_t blkio_read_stat_cpu(struct blkio_group *blkg,
enum stat_type_cpu type, enum stat_sub_type sub_type)
{
int cpu;
struct blkio_group_stats_cpu *stats_cpu;
u64 val = 0, tval;
for_each_possible_cpu(cpu) {
unsigned int start;
stats_cpu = per_cpu_ptr(blkg->stats_cpu, cpu);
do {
start = u64_stats_fetch_begin(&stats_cpu->syncp);
if (type == BLKIO_STAT_CPU_SECTORS)
tval = stats_cpu->sectors;
else
tval = stats_cpu->stat_arr_cpu[type][sub_type];
} while(u64_stats_fetch_retry(&stats_cpu->syncp, start));
val += tval;
}
return val;
}
static uint64_t blkio_get_stat_cpu(struct blkio_group *blkg,
struct cgroup_map_cb *cb, dev_t dev, enum stat_type_cpu type)
{
uint64_t disk_total, val;
char key_str[MAX_KEY_LEN];
enum stat_sub_type sub_type;
if (type == BLKIO_STAT_CPU_SECTORS) {
val = blkio_read_stat_cpu(blkg, type, 0);
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, val, cb, dev);
}
for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL;
sub_type++) {
blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false);
val = blkio_read_stat_cpu(blkg, type, sub_type);
cb->fill(cb, key_str, val);
}
disk_total = blkio_read_stat_cpu(blkg, type, BLKIO_STAT_READ) +
blkio_read_stat_cpu(blkg, type, BLKIO_STAT_WRITE);
blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false);
cb->fill(cb, key_str, disk_total);
return disk_total;
}
/* This should be called with blkg->stats_lock held */
static uint64_t blkio_get_stat(struct blkio_group *blkg,
struct cgroup_map_cb *cb, dev_t dev, enum stat_type type)
{
uint64_t disk_total;
char key_str[MAX_KEY_LEN];
enum stat_sub_type sub_type;
if (type == BLKIO_STAT_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.time, cb, dev);
#ifdef CONFIG_DEBUG_BLK_CGROUP
if (type == BLKIO_STAT_UNACCOUNTED_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.unaccounted_time, cb, dev);
if (type == BLKIO_STAT_AVG_QUEUE_SIZE) {
uint64_t sum = blkg->stats.avg_queue_size_sum;
uint64_t samples = blkg->stats.avg_queue_size_samples;
if (samples)
do_div(sum, samples);
else
sum = 0;
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, sum, cb, dev);
}
if (type == BLKIO_STAT_GROUP_WAIT_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.group_wait_time, cb, dev);
if (type == BLKIO_STAT_IDLE_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.idle_time, cb, dev);
if (type == BLKIO_STAT_EMPTY_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.empty_time, cb, dev);
if (type == BLKIO_STAT_DEQUEUE)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.dequeue, cb, dev);
#endif
for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL;
sub_type++) {
blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false);
cb->fill(cb, key_str, blkg->stats.stat_arr[type][sub_type]);
}
disk_total = blkg->stats.stat_arr[type][BLKIO_STAT_READ] +
blkg->stats.stat_arr[type][BLKIO_STAT_WRITE];
blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false);
cb->fill(cb, key_str, disk_total);
return disk_total;
}
static int blkio_policy_parse_and_set(char *buf,
struct blkio_policy_node *newpn, enum blkio_policy_id plid, int fileid)
{
struct gendisk *disk = NULL;
char *s[4], *p, *major_s = NULL, *minor_s = NULL;
unsigned long major, minor;
int i = 0, ret = -EINVAL;
int part;
dev_t dev;
u64 temp;
memset(s, 0, sizeof(s));
while ((p = strsep(&buf, " ")) != NULL) {
if (!*p)
continue;
s[i++] = p;
/* Prevent from inputing too many things */
if (i == 3)
break;
}
if (i != 2)
goto out;
p = strsep(&s[0], ":");
if (p != NULL)
major_s = p;
else
goto out;
minor_s = s[0];
if (!minor_s)
goto out;
if (strict_strtoul(major_s, 10, &major))
goto out;
if (strict_strtoul(minor_s, 10, &minor))
goto out;
dev = MKDEV(major, minor);
if (strict_strtoull(s[1], 10, &temp))
goto out;
/* For rule removal, do not check for device presence. */
if (temp) {
disk = get_gendisk(dev, &part);
if (!disk || part) {
ret = -ENODEV;
goto out;
}
}
newpn->dev = dev;
switch (plid) {
case BLKIO_POLICY_PROP:
if ((temp < BLKIO_WEIGHT_MIN && temp > 0) ||
temp > BLKIO_WEIGHT_MAX)
goto out;
newpn->plid = plid;
newpn->fileid = fileid;
newpn->val.weight = temp;
break;
case BLKIO_POLICY_THROTL:
switch(fileid) {
case BLKIO_THROTL_read_bps_device:
case BLKIO_THROTL_write_bps_device:
newpn->plid = plid;
newpn->fileid = fileid;
newpn->val.bps = temp;
break;
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
if (temp > THROTL_IOPS_MAX)
goto out;
newpn->plid = plid;
newpn->fileid = fileid;
newpn->val.iops = (unsigned int)temp;
break;
}
break;
default:
BUG();
}
ret = 0;
out:
put_disk(disk);
return ret;
}
unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
unsigned int weight;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_PROP,
BLKIO_PROP_weight_device);
if (pn)
weight = pn->val.weight;
else
weight = blkcg->weight;
spin_unlock_irqrestore(&blkcg->lock, flags);
return weight;
}
EXPORT_SYMBOL_GPL(blkcg_get_weight);
uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg, dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
uint64_t bps = -1;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
BLKIO_THROTL_read_bps_device);
if (pn)
bps = pn->val.bps;
spin_unlock_irqrestore(&blkcg->lock, flags);
return bps;
}
uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg, dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
uint64_t bps = -1;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
BLKIO_THROTL_write_bps_device);
if (pn)
bps = pn->val.bps;
spin_unlock_irqrestore(&blkcg->lock, flags);
return bps;
}
unsigned int blkcg_get_read_iops(struct blkio_cgroup *blkcg, dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
unsigned int iops = -1;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
BLKIO_THROTL_read_iops_device);
if (pn)
iops = pn->val.iops;
spin_unlock_irqrestore(&blkcg->lock, flags);
return iops;
}
unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg, dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
unsigned int iops = -1;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
BLKIO_THROTL_write_iops_device);
if (pn)
iops = pn->val.iops;
spin_unlock_irqrestore(&blkcg->lock, flags);
return iops;
}
/* Checks whether user asked for deleting a policy rule */
static bool blkio_delete_rule_command(struct blkio_policy_node *pn)
{
switch(pn->plid) {
case BLKIO_POLICY_PROP:
if (pn->val.weight == 0)
return 1;
break;
case BLKIO_POLICY_THROTL:
switch(pn->fileid) {
case BLKIO_THROTL_read_bps_device:
case BLKIO_THROTL_write_bps_device:
if (pn->val.bps == 0)
return 1;
break;
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
if (pn->val.iops == 0)
return 1;
}
break;
default:
BUG();
}
return 0;
}
static void blkio_update_policy_rule(struct blkio_policy_node *oldpn,
struct blkio_policy_node *newpn)
{
switch(oldpn->plid) {
case BLKIO_POLICY_PROP:
oldpn->val.weight = newpn->val.weight;
break;
case BLKIO_POLICY_THROTL:
switch(newpn->fileid) {
case BLKIO_THROTL_read_bps_device:
case BLKIO_THROTL_write_bps_device:
oldpn->val.bps = newpn->val.bps;
break;
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
oldpn->val.iops = newpn->val.iops;
}
break;
default: