/
rdtgroup.c
3112 lines (2675 loc) · 76.8 KB
/
rdtgroup.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
/*
* User interface for Resource Alloction in Resource Director Technology(RDT)
*
* Copyright (C) 2016 Intel Corporation
*
* Author: Fenghua Yu <fenghua.yu@intel.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* More information about RDT be found in the Intel (R) x86 Architecture
* Software Developer Manual.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/debugfs.h>
#include <linux/fs.h>
#include <linux/fs_parser.h>
#include <linux/sysfs.h>
#include <linux/kernfs.h>
#include <linux/seq_buf.h>
#include <linux/seq_file.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/slab.h>
#include <linux/task_work.h>
#include <linux/user_namespace.h>
#include <uapi/linux/magic.h>
#include <asm/resctrl_sched.h>
#include "internal.h"
DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
static struct kernfs_root *rdt_root;
struct rdtgroup rdtgroup_default;
LIST_HEAD(rdt_all_groups);
/* Kernel fs node for "info" directory under root */
static struct kernfs_node *kn_info;
/* Kernel fs node for "mon_groups" directory under root */
static struct kernfs_node *kn_mongrp;
/* Kernel fs node for "mon_data" directory under root */
static struct kernfs_node *kn_mondata;
static struct seq_buf last_cmd_status;
static char last_cmd_status_buf[512];
struct dentry *debugfs_resctrl;
void rdt_last_cmd_clear(void)
{
lockdep_assert_held(&rdtgroup_mutex);
seq_buf_clear(&last_cmd_status);
}
void rdt_last_cmd_puts(const char *s)
{
lockdep_assert_held(&rdtgroup_mutex);
seq_buf_puts(&last_cmd_status, s);
}
void rdt_last_cmd_printf(const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
lockdep_assert_held(&rdtgroup_mutex);
seq_buf_vprintf(&last_cmd_status, fmt, ap);
va_end(ap);
}
/*
* Trivial allocator for CLOSIDs. Since h/w only supports a small number,
* we can keep a bitmap of free CLOSIDs in a single integer.
*
* Using a global CLOSID across all resources has some advantages and
* some drawbacks:
* + We can simply set "current->closid" to assign a task to a resource
* group.
* + Context switch code can avoid extra memory references deciding which
* CLOSID to load into the PQR_ASSOC MSR
* - We give up some options in configuring resource groups across multi-socket
* systems.
* - Our choices on how to configure each resource become progressively more
* limited as the number of resources grows.
*/
static int closid_free_map;
static int closid_free_map_len;
int closids_supported(void)
{
return closid_free_map_len;
}
static void closid_init(void)
{
struct rdt_resource *r;
int rdt_min_closid = 32;
/* Compute rdt_min_closid across all resources */
for_each_alloc_enabled_rdt_resource(r)
rdt_min_closid = min(rdt_min_closid, r->num_closid);
closid_free_map = BIT_MASK(rdt_min_closid) - 1;
/* CLOSID 0 is always reserved for the default group */
closid_free_map &= ~1;
closid_free_map_len = rdt_min_closid;
}
static int closid_alloc(void)
{
u32 closid = ffs(closid_free_map);
if (closid == 0)
return -ENOSPC;
closid--;
closid_free_map &= ~(1 << closid);
return closid;
}
void closid_free(int closid)
{
closid_free_map |= 1 << closid;
}
/**
* closid_allocated - test if provided closid is in use
* @closid: closid to be tested
*
* Return: true if @closid is currently associated with a resource group,
* false if @closid is free
*/
static bool closid_allocated(unsigned int closid)
{
return (closid_free_map & (1 << closid)) == 0;
}
/**
* rdtgroup_mode_by_closid - Return mode of resource group with closid
* @closid: closid if the resource group
*
* Each resource group is associated with a @closid. Here the mode
* of a resource group can be queried by searching for it using its closid.
*
* Return: mode as &enum rdtgrp_mode of resource group with closid @closid
*/
enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
{
struct rdtgroup *rdtgrp;
list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
if (rdtgrp->closid == closid)
return rdtgrp->mode;
}
return RDT_NUM_MODES;
}
static const char * const rdt_mode_str[] = {
[RDT_MODE_SHAREABLE] = "shareable",
[RDT_MODE_EXCLUSIVE] = "exclusive",
[RDT_MODE_PSEUDO_LOCKSETUP] = "pseudo-locksetup",
[RDT_MODE_PSEUDO_LOCKED] = "pseudo-locked",
};
/**
* rdtgroup_mode_str - Return the string representation of mode
* @mode: the resource group mode as &enum rdtgroup_mode
*
* Return: string representation of valid mode, "unknown" otherwise
*/
static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
{
if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
return "unknown";
return rdt_mode_str[mode];
}
/* set uid and gid of rdtgroup dirs and files to that of the creator */
static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
{
struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
.ia_uid = current_fsuid(),
.ia_gid = current_fsgid(), };
if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
return 0;
return kernfs_setattr(kn, &iattr);
}
static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
{
struct kernfs_node *kn;
int ret;
kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
0, rft->kf_ops, rft, NULL, NULL);
if (IS_ERR(kn))
return PTR_ERR(kn);
ret = rdtgroup_kn_set_ugid(kn);
if (ret) {
kernfs_remove(kn);
return ret;
}
return 0;
}
static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
{
struct kernfs_open_file *of = m->private;
struct rftype *rft = of->kn->priv;
if (rft->seq_show)
return rft->seq_show(of, m, arg);
return 0;
}
static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct rftype *rft = of->kn->priv;
if (rft->write)
return rft->write(of, buf, nbytes, off);
return -EINVAL;
}
static struct kernfs_ops rdtgroup_kf_single_ops = {
.atomic_write_len = PAGE_SIZE,
.write = rdtgroup_file_write,
.seq_show = rdtgroup_seqfile_show,
};
static struct kernfs_ops kf_mondata_ops = {
.atomic_write_len = PAGE_SIZE,
.seq_show = rdtgroup_mondata_show,
};
static bool is_cpu_list(struct kernfs_open_file *of)
{
struct rftype *rft = of->kn->priv;
return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
}
static int rdtgroup_cpus_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
{
struct rdtgroup *rdtgrp;
struct cpumask *mask;
int ret = 0;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (rdtgrp) {
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
if (!rdtgrp->plr->d) {
rdt_last_cmd_clear();
rdt_last_cmd_puts("Cache domain offline\n");
ret = -ENODEV;
} else {
mask = &rdtgrp->plr->d->cpu_mask;
seq_printf(s, is_cpu_list(of) ?
"%*pbl\n" : "%*pb\n",
cpumask_pr_args(mask));
}
} else {
seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
cpumask_pr_args(&rdtgrp->cpu_mask));
}
} else {
ret = -ENOENT;
}
rdtgroup_kn_unlock(of->kn);
return ret;
}
/*
* This is safe against resctrl_sched_in() called from __switch_to()
* because __switch_to() is executed with interrupts disabled. A local call
* from update_closid_rmid() is proteced against __switch_to() because
* preemption is disabled.
*/
static void update_cpu_closid_rmid(void *info)
{
struct rdtgroup *r = info;
if (r) {
this_cpu_write(pqr_state.default_closid, r->closid);
this_cpu_write(pqr_state.default_rmid, r->mon.rmid);
}
/*
* We cannot unconditionally write the MSR because the current
* executing task might have its own closid selected. Just reuse
* the context switch code.
*/
resctrl_sched_in();
}
/*
* Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
*
* Per task closids/rmids must have been set up before calling this function.
*/
static void
update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
{
int cpu = get_cpu();
if (cpumask_test_cpu(cpu, cpu_mask))
update_cpu_closid_rmid(r);
smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1);
put_cpu();
}
static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
cpumask_var_t tmpmask)
{
struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp;
struct list_head *head;
/* Check whether cpus belong to parent ctrl group */
cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
if (cpumask_weight(tmpmask)) {
rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n");
return -EINVAL;
}
/* Check whether cpus are dropped from this group */
cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
if (cpumask_weight(tmpmask)) {
/* Give any dropped cpus to parent rdtgroup */
cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask);
update_closid_rmid(tmpmask, prgrp);
}
/*
* If we added cpus, remove them from previous group that owned them
* and update per-cpu rmid
*/
cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
if (cpumask_weight(tmpmask)) {
head = &prgrp->mon.crdtgrp_list;
list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
if (crgrp == rdtgrp)
continue;
cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask,
tmpmask);
}
update_closid_rmid(tmpmask, rdtgrp);
}
/* Done pushing/pulling - update this group with new mask */
cpumask_copy(&rdtgrp->cpu_mask, newmask);
return 0;
}
static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m)
{
struct rdtgroup *crgrp;
cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m);
/* update the child mon group masks as well*/
list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list)
cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask);
}
static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
cpumask_var_t tmpmask, cpumask_var_t tmpmask1)
{
struct rdtgroup *r, *crgrp;
struct list_head *head;
/* Check whether cpus are dropped from this group */
cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
if (cpumask_weight(tmpmask)) {
/* Can't drop from default group */
if (rdtgrp == &rdtgroup_default) {
rdt_last_cmd_puts("Can't drop CPUs from default group\n");
return -EINVAL;
}
/* Give any dropped cpus to rdtgroup_default */
cpumask_or(&rdtgroup_default.cpu_mask,
&rdtgroup_default.cpu_mask, tmpmask);
update_closid_rmid(tmpmask, &rdtgroup_default);
}
/*
* If we added cpus, remove them from previous group and
* the prev group's child groups that owned them
* and update per-cpu closid/rmid.
*/
cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
if (cpumask_weight(tmpmask)) {
list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
if (r == rdtgrp)
continue;
cpumask_and(tmpmask1, &r->cpu_mask, tmpmask);
if (cpumask_weight(tmpmask1))
cpumask_rdtgrp_clear(r, tmpmask1);
}
update_closid_rmid(tmpmask, rdtgrp);
}
/* Done pushing/pulling - update this group with new mask */
cpumask_copy(&rdtgrp->cpu_mask, newmask);
/*
* Clear child mon group masks since there is a new parent mask
* now and update the rmid for the cpus the child lost.
*/
head = &rdtgrp->mon.crdtgrp_list;
list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask);
update_closid_rmid(tmpmask, rdtgrp);
cpumask_clear(&crgrp->cpu_mask);
}
return 0;
}
static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
cpumask_var_t tmpmask, newmask, tmpmask1;
struct rdtgroup *rdtgrp;
int ret;
if (!buf)
return -EINVAL;
if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
return -ENOMEM;
if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
free_cpumask_var(tmpmask);
return -ENOMEM;
}
if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) {
free_cpumask_var(tmpmask);
free_cpumask_var(newmask);
return -ENOMEM;
}
rdtgrp = rdtgroup_kn_lock_live(of->kn);
rdt_last_cmd_clear();
if (!rdtgrp) {
ret = -ENOENT;
rdt_last_cmd_puts("Directory was removed\n");
goto unlock;
}
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
ret = -EINVAL;
rdt_last_cmd_puts("Pseudo-locking in progress\n");
goto unlock;
}
if (is_cpu_list(of))
ret = cpulist_parse(buf, newmask);
else
ret = cpumask_parse(buf, newmask);
if (ret) {
rdt_last_cmd_puts("Bad CPU list/mask\n");
goto unlock;
}
/* check that user didn't specify any offline cpus */
cpumask_andnot(tmpmask, newmask, cpu_online_mask);
if (cpumask_weight(tmpmask)) {
ret = -EINVAL;
rdt_last_cmd_puts("Can only assign online CPUs\n");
goto unlock;
}
if (rdtgrp->type == RDTCTRL_GROUP)
ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1);
else if (rdtgrp->type == RDTMON_GROUP)
ret = cpus_mon_write(rdtgrp, newmask, tmpmask);
else
ret = -EINVAL;
unlock:
rdtgroup_kn_unlock(of->kn);
free_cpumask_var(tmpmask);
free_cpumask_var(newmask);
free_cpumask_var(tmpmask1);
return ret ?: nbytes;
}
struct task_move_callback {
struct callback_head work;
struct rdtgroup *rdtgrp;
};
static void move_myself(struct callback_head *head)
{
struct task_move_callback *callback;
struct rdtgroup *rdtgrp;
callback = container_of(head, struct task_move_callback, work);
rdtgrp = callback->rdtgrp;
/*
* If resource group was deleted before this task work callback
* was invoked, then assign the task to root group and free the
* resource group.
*/
if (atomic_dec_and_test(&rdtgrp->waitcount) &&
(rdtgrp->flags & RDT_DELETED)) {
current->closid = 0;
current->rmid = 0;
kfree(rdtgrp);
}
preempt_disable();
/* update PQR_ASSOC MSR to make resource group go into effect */
resctrl_sched_in();
preempt_enable();
kfree(callback);
}
static int __rdtgroup_move_task(struct task_struct *tsk,
struct rdtgroup *rdtgrp)
{
struct task_move_callback *callback;
int ret;
callback = kzalloc(sizeof(*callback), GFP_KERNEL);
if (!callback)
return -ENOMEM;
callback->work.func = move_myself;
callback->rdtgrp = rdtgrp;
/*
* Take a refcount, so rdtgrp cannot be freed before the
* callback has been invoked.
*/
atomic_inc(&rdtgrp->waitcount);
ret = task_work_add(tsk, &callback->work, true);
if (ret) {
/*
* Task is exiting. Drop the refcount and free the callback.
* No need to check the refcount as the group cannot be
* deleted before the write function unlocks rdtgroup_mutex.
*/
atomic_dec(&rdtgrp->waitcount);
kfree(callback);
rdt_last_cmd_puts("Task exited\n");
} else {
/*
* For ctrl_mon groups move both closid and rmid.
* For monitor groups, can move the tasks only from
* their parent CTRL group.
*/
if (rdtgrp->type == RDTCTRL_GROUP) {
tsk->closid = rdtgrp->closid;
tsk->rmid = rdtgrp->mon.rmid;
} else if (rdtgrp->type == RDTMON_GROUP) {
if (rdtgrp->mon.parent->closid == tsk->closid) {
tsk->rmid = rdtgrp->mon.rmid;
} else {
rdt_last_cmd_puts("Can't move task to different control group\n");
ret = -EINVAL;
}
}
}
return ret;
}
/**
* rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
* @r: Resource group
*
* Return: 1 if tasks have been assigned to @r, 0 otherwise
*/
int rdtgroup_tasks_assigned(struct rdtgroup *r)
{
struct task_struct *p, *t;
int ret = 0;
lockdep_assert_held(&rdtgroup_mutex);
rcu_read_lock();
for_each_process_thread(p, t) {
if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
(r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) {
ret = 1;
break;
}
}
rcu_read_unlock();
return ret;
}
static int rdtgroup_task_write_permission(struct task_struct *task,
struct kernfs_open_file *of)
{
const struct cred *tcred = get_task_cred(task);
const struct cred *cred = current_cred();
int ret = 0;
/*
* Even if we're attaching all tasks in the thread group, we only
* need to check permissions on one of them.
*/
if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
!uid_eq(cred->euid, tcred->uid) &&
!uid_eq(cred->euid, tcred->suid)) {
rdt_last_cmd_printf("No permission to move task %d\n", task->pid);
ret = -EPERM;
}
put_cred(tcred);
return ret;
}
static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
struct kernfs_open_file *of)
{
struct task_struct *tsk;
int ret;
rcu_read_lock();
if (pid) {
tsk = find_task_by_vpid(pid);
if (!tsk) {
rcu_read_unlock();
rdt_last_cmd_printf("No task %d\n", pid);
return -ESRCH;
}
} else {
tsk = current;
}
get_task_struct(tsk);
rcu_read_unlock();
ret = rdtgroup_task_write_permission(tsk, of);
if (!ret)
ret = __rdtgroup_move_task(tsk, rdtgrp);
put_task_struct(tsk);
return ret;
}
static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct rdtgroup *rdtgrp;
int ret = 0;
pid_t pid;
if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
return -EINVAL;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (!rdtgrp) {
rdtgroup_kn_unlock(of->kn);
return -ENOENT;
}
rdt_last_cmd_clear();
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
ret = -EINVAL;
rdt_last_cmd_puts("Pseudo-locking in progress\n");
goto unlock;
}
ret = rdtgroup_move_task(pid, rdtgrp, of);
unlock:
rdtgroup_kn_unlock(of->kn);
return ret ?: nbytes;
}
static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
{
struct task_struct *p, *t;
rcu_read_lock();
for_each_process_thread(p, t) {
if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
(r->type == RDTMON_GROUP && t->rmid == r->mon.rmid))
seq_printf(s, "%d\n", t->pid);
}
rcu_read_unlock();
}
static int rdtgroup_tasks_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
{
struct rdtgroup *rdtgrp;
int ret = 0;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (rdtgrp)
show_rdt_tasks(rdtgrp, s);
else
ret = -ENOENT;
rdtgroup_kn_unlock(of->kn);
return ret;
}
static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
int len;
mutex_lock(&rdtgroup_mutex);
len = seq_buf_used(&last_cmd_status);
if (len)
seq_printf(seq, "%.*s", len, last_cmd_status_buf);
else
seq_puts(seq, "ok\n");
mutex_unlock(&rdtgroup_mutex);
return 0;
}
static int rdt_num_closids_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
seq_printf(seq, "%d\n", r->num_closid);
return 0;
}
static int rdt_default_ctrl_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
seq_printf(seq, "%x\n", r->default_ctrl);
return 0;
}
static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
return 0;
}
static int rdt_shareable_bits_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
seq_printf(seq, "%x\n", r->cache.shareable_bits);
return 0;
}
/**
* rdt_bit_usage_show - Display current usage of resources
*
* A domain is a shared resource that can now be allocated differently. Here
* we display the current regions of the domain as an annotated bitmask.
* For each domain of this resource its allocation bitmask
* is annotated as below to indicate the current usage of the corresponding bit:
* 0 - currently unused
* X - currently available for sharing and used by software and hardware
* H - currently used by hardware only but available for software use
* S - currently used and shareable by software only
* E - currently used exclusively by one resource group
* P - currently pseudo-locked by one resource group
*/
static int rdt_bit_usage_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
u32 sw_shareable = 0, hw_shareable = 0;
u32 exclusive = 0, pseudo_locked = 0;
struct rdt_domain *dom;
int i, hwb, swb, excl, psl;
enum rdtgrp_mode mode;
bool sep = false;
u32 *ctrl;
mutex_lock(&rdtgroup_mutex);
hw_shareable = r->cache.shareable_bits;
list_for_each_entry(dom, &r->domains, list) {
if (sep)
seq_putc(seq, ';');
ctrl = dom->ctrl_val;
sw_shareable = 0;
exclusive = 0;
seq_printf(seq, "%d=", dom->id);
for (i = 0; i < closids_supported(); i++, ctrl++) {
if (!closid_allocated(i))
continue;
mode = rdtgroup_mode_by_closid(i);
switch (mode) {
case RDT_MODE_SHAREABLE:
sw_shareable |= *ctrl;
break;
case RDT_MODE_EXCLUSIVE:
exclusive |= *ctrl;
break;
case RDT_MODE_PSEUDO_LOCKSETUP:
/*
* RDT_MODE_PSEUDO_LOCKSETUP is possible
* here but not included since the CBM
* associated with this CLOSID in this mode
* is not initialized and no task or cpu can be
* assigned this CLOSID.
*/
break;
case RDT_MODE_PSEUDO_LOCKED:
case RDT_NUM_MODES:
WARN(1,
"invalid mode for closid %d\n", i);
break;
}
}
for (i = r->cache.cbm_len - 1; i >= 0; i--) {
pseudo_locked = dom->plr ? dom->plr->cbm : 0;
hwb = test_bit(i, (unsigned long *)&hw_shareable);
swb = test_bit(i, (unsigned long *)&sw_shareable);
excl = test_bit(i, (unsigned long *)&exclusive);
psl = test_bit(i, (unsigned long *)&pseudo_locked);
if (hwb && swb)
seq_putc(seq, 'X');
else if (hwb && !swb)
seq_putc(seq, 'H');
else if (!hwb && swb)
seq_putc(seq, 'S');
else if (excl)
seq_putc(seq, 'E');
else if (psl)
seq_putc(seq, 'P');
else /* Unused bits remain */
seq_putc(seq, '0');
}
sep = true;
}
seq_putc(seq, '\n');
mutex_unlock(&rdtgroup_mutex);
return 0;
}
static int rdt_min_bw_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
seq_printf(seq, "%u\n", r->membw.min_bw);
return 0;
}
static int rdt_num_rmids_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
seq_printf(seq, "%d\n", r->num_rmid);
return 0;
}
static int rdt_mon_features_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
struct mon_evt *mevt;
list_for_each_entry(mevt, &r->evt_list, list)
seq_printf(seq, "%s\n", mevt->name);
return 0;
}
static int rdt_bw_gran_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
seq_printf(seq, "%u\n", r->membw.bw_gran);
return 0;
}
static int rdt_delay_linear_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
seq_printf(seq, "%u\n", r->membw.delay_linear);
return 0;
}
static int max_threshold_occ_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
struct rdt_resource *r = of->kn->parent->priv;
seq_printf(seq, "%u\n", resctrl_cqm_threshold * r->mon_scale);
return 0;
}
static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct rdt_resource *r = of->kn->parent->priv;
unsigned int bytes;
int ret;
ret = kstrtouint(buf, 0, &bytes);
if (ret)
return ret;
if (bytes > (boot_cpu_data.x86_cache_size * 1024))
return -EINVAL;
resctrl_cqm_threshold = bytes / r->mon_scale;
return nbytes;
}
/*
* rdtgroup_mode_show - Display mode of this resource group
*/
static int rdtgroup_mode_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
{
struct rdtgroup *rdtgrp;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (!rdtgrp) {
rdtgroup_kn_unlock(of->kn);
return -ENOENT;
}
seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));
rdtgroup_kn_unlock(of->kn);
return 0;
}
/**
* rdt_cdp_peer_get - Retrieve CDP peer if it exists
* @r: RDT resource to which RDT domain @d belongs
* @d: Cache instance for which a CDP peer is requested
* @r_cdp: RDT resource that shares hardware with @r (RDT resource peer)
* Used to return the result.
* @d_cdp: RDT domain that shares hardware with @d (RDT domain peer)
* Used to return the result.
*
* RDT resources are managed independently and by extension the RDT domains
* (RDT resource instances) are managed independently also. The Code and
* Data Prioritization (CDP) RDT resources, while managed independently,
* could refer to the same underlying hardware. For example,
* RDT_RESOURCE_L2CODE and RDT_RESOURCE_L2DATA both refer to the L2 cache.
*
* When provided with an RDT resource @r and an instance of that RDT
* resource @d rdt_cdp_peer_get() will return if there is a peer RDT
* resource and the exact instance that shares the same hardware.
*
* Return: 0 if a CDP peer was found, <0 on error or if no CDP peer exists.
* If a CDP peer was found, @r_cdp will point to the peer RDT resource
* and @d_cdp will point to the peer RDT domain.
*/
static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
struct rdt_resource **r_cdp,
struct rdt_domain **d_cdp)