summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/resctrl/resctrlfs.c
blob: 6f543e470ad4aacc999cf946bca301754b9c65c9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
// SPDX-License-Identifier: GPL-2.0
/*
 * Basic resctrl file system operations
 *
 * Copyright (C) 2018 Intel Corporation
 *
 * Authors:
 *    Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
 *    Fenghua Yu <fenghua.yu@intel.com>
 */
#include "resctrl.h"

static int find_resctrl_mount(char *buffer)
{
	FILE *mounts;
	char line[256], *fs, *mntpoint;

	mounts = fopen("/proc/mounts", "r");
	if (!mounts) {
		perror("/proc/mounts");
		return -ENXIO;
	}
	while (!feof(mounts)) {
		if (!fgets(line, 256, mounts))
			break;
		fs = strtok(line, " \t");
		if (!fs)
			continue;
		mntpoint = strtok(NULL, " \t");
		if (!mntpoint)
			continue;
		fs = strtok(NULL, " \t");
		if (!fs)
			continue;
		if (strcmp(fs, "resctrl"))
			continue;

		fclose(mounts);
		if (buffer)
			strncpy(buffer, mntpoint, 256);

		return 0;
	}

	fclose(mounts);

	return -ENOENT;
}

/*
 * remount_resctrlfs - Remount resctrl FS at /sys/fs/resctrl
 * @mum_resctrlfs:	Should the resctrl FS be remounted?
 *
 * If not mounted, mount it.
 * If mounted and mum_resctrlfs then remount resctrl FS.
 * If mounted and !mum_resctrlfs then noop
 *
 * Return: 0 on success, non-zero on failure
 */
int remount_resctrlfs(bool mum_resctrlfs)
{
	char mountpoint[256];
	int ret;

	ret = find_resctrl_mount(mountpoint);
	if (ret)
		strcpy(mountpoint, RESCTRL_PATH);

	if (!ret && mum_resctrlfs && umount(mountpoint))
		ksft_print_msg("Fail: unmounting \"%s\"\n", mountpoint);

	if (!ret && !mum_resctrlfs)
		return 0;

	ksft_print_msg("Mounting resctrl to \"%s\"\n", RESCTRL_PATH);
	ret = mount("resctrl", RESCTRL_PATH, "resctrl", 0, NULL);
	if (ret)
		perror("# mount");

	return ret;
}

int umount_resctrlfs(void)
{
	if (find_resctrl_mount(NULL))
		return 0;

	if (umount(RESCTRL_PATH)) {
		perror("# Unable to umount resctrl");

		return errno;
	}

	return 0;
}

/*
 * get_resource_id - Get socket number/l3 id for a specified CPU
 * @cpu_no:	CPU number
 * @resource_id: Socket number or l3_id
 *
 * Return: >= 0 on success, < 0 on failure.
 */
int get_resource_id(int cpu_no, int *resource_id)
{
	char phys_pkg_path[1024];
	FILE *fp;

	if (get_vendor() == ARCH_AMD)
		sprintf(phys_pkg_path, "%s%d/cache/index3/id",
			PHYS_ID_PATH, cpu_no);
	else
		sprintf(phys_pkg_path, "%s%d/topology/physical_package_id",
			PHYS_ID_PATH, cpu_no);

	fp = fopen(phys_pkg_path, "r");
	if (!fp) {
		perror("Failed to open physical_package_id");

		return -1;
	}
	if (fscanf(fp, "%d", resource_id) <= 0) {
		perror("Could not get socket number or l3 id");
		fclose(fp);

		return -1;
	}
	fclose(fp);

	return 0;
}

/*
 * get_cache_size - Get cache size for a specified CPU
 * @cpu_no:	CPU number
 * @cache_type:	Cache level L2/L3
 * @cache_size:	pointer to cache_size
 *
 * Return: = 0 on success, < 0 on failure.
 */
int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size)
{
	char cache_path[1024], cache_str[64];
	int length, i, cache_num;
	FILE *fp;

	if (!strcmp(cache_type, "L3")) {
		cache_num = 3;
	} else if (!strcmp(cache_type, "L2")) {
		cache_num = 2;
	} else {
		perror("Invalid cache level");
		return -1;
	}

	sprintf(cache_path, "/sys/bus/cpu/devices/cpu%d/cache/index%d/size",
		cpu_no, cache_num);
	fp = fopen(cache_path, "r");
	if (!fp) {
		perror("Failed to open cache size");

		return -1;
	}
	if (fscanf(fp, "%s", cache_str) <= 0) {
		perror("Could not get cache_size");
		fclose(fp);

		return -1;
	}
	fclose(fp);

	length = (int)strlen(cache_str);

	*cache_size = 0;

	for (i = 0; i < length; i++) {
		if ((cache_str[i] >= '0') && (cache_str[i] <= '9'))

			*cache_size = *cache_size * 10 + (cache_str[i] - '0');

		else if (cache_str[i] == 'K')

			*cache_size = *cache_size * 1024;

		else if (cache_str[i] == 'M')

			*cache_size = *cache_size * 1024 * 1024;

		else
			break;
	}

	return 0;
}

#define CORE_SIBLINGS_PATH	"/sys/bus/cpu/devices/cpu"

/*
 * get_cbm_mask - Get cbm mask for given cache
 * @cache_type:	Cache level L2/L3
 * @cbm_mask:	cbm_mask returned as a string
 *
 * Return: = 0 on success, < 0 on failure.
 */
int get_cbm_mask(char *cache_type, char *cbm_mask)
{
	char cbm_mask_path[1024];
	FILE *fp;

	if (!cbm_mask)
		return -1;

	sprintf(cbm_mask_path, "%s/%s/cbm_mask", CBM_MASK_PATH, cache_type);

	fp = fopen(cbm_mask_path, "r");
	if (!fp) {
		perror("Failed to open cache level");

		return -1;
	}
	if (fscanf(fp, "%s", cbm_mask) <= 0) {
		perror("Could not get max cbm_mask");
		fclose(fp);

		return -1;
	}
	fclose(fp);

	return 0;
}

/*
 * get_core_sibling - Get sibling core id from the same socket for given CPU
 * @cpu_no:	CPU number
 *
 * Return:	> 0 on success, < 0 on failure.
 */
int get_core_sibling(int cpu_no)
{
	char core_siblings_path[1024], cpu_list_str[64];
	int sibling_cpu_no = -1;
	FILE *fp;

	sprintf(core_siblings_path, "%s%d/topology/core_siblings_list",
		CORE_SIBLINGS_PATH, cpu_no);

	fp = fopen(core_siblings_path, "r");
	if (!fp) {
		perror("Failed to open core siblings path");

		return -1;
	}
	if (fscanf(fp, "%s", cpu_list_str) <= 0) {
		perror("Could not get core_siblings list");
		fclose(fp);

		return -1;
	}
	fclose(fp);

	char *token = strtok(cpu_list_str, "-,");

	while (token) {
		sibling_cpu_no = atoi(token);
		/* Skipping core 0 as we don't want to run test on core 0 */
		if (sibling_cpu_no != 0 && sibling_cpu_no != cpu_no)
			break;
		token = strtok(NULL, "-,");
	}

	return sibling_cpu_no;
}

/*
 * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu
 * @bm_pid:	PID that should be binded
 * @cpu_no:	CPU number at which the PID would be binded
 *
 * Return: 0 on success, non-zero on failure
 */
int taskset_benchmark(pid_t bm_pid, int cpu_no)
{
	cpu_set_t my_set;

	CPU_ZERO(&my_set);
	CPU_SET(cpu_no, &my_set);

	if (sched_setaffinity(bm_pid, sizeof(cpu_set_t), &my_set)) {
		perror("Unable to taskset benchmark");

		return -1;
	}

	return 0;
}

/*
 * run_benchmark - Run a specified benchmark or fill_buf (default benchmark)
 *		   in specified signal. Direct benchmark stdio to /dev/null.
 * @signum:	signal number
 * @info:	signal info
 * @ucontext:	user context in signal handling
 *
 * Return: void
 */
void run_benchmark(int signum, siginfo_t *info, void *ucontext)
{
	int operation, ret, malloc_and_init_memory, memflush;
	unsigned long span, buffer_span;
	char **benchmark_cmd;
	char resctrl_val[64];
	FILE *fp;

	benchmark_cmd = info->si_ptr;

	/*
	 * Direct stdio of child to /dev/null, so that only parent writes to
	 * stdio (console)
	 */
	fp = freopen("/dev/null", "w", stdout);
	if (!fp)
		PARENT_EXIT("Unable to direct benchmark status to /dev/null");

	if (strcmp(benchmark_cmd[0], "fill_buf") == 0) {
		/* Execute default fill_buf benchmark */
		span = strtoul(benchmark_cmd[1], NULL, 10);
		malloc_and_init_memory = atoi(benchmark_cmd[2]);
		memflush =  atoi(benchmark_cmd[3]);
		operation = atoi(benchmark_cmd[4]);
		sprintf(resctrl_val, "%s", benchmark_cmd[5]);

		if (strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
			buffer_span = span * MB;
		else
			buffer_span = span;

		if (run_fill_buf(buffer_span, malloc_and_init_memory, memflush,
				 operation, resctrl_val))
			fprintf(stderr, "Error in running fill buffer\n");
	} else {
		/* Execute specified benchmark */
		ret = execvp(benchmark_cmd[0], benchmark_cmd);
		if (ret)
			perror("wrong\n");
	}

	fclose(stdout);
	PARENT_EXIT("Unable to run specified benchmark");
}

/*
 * create_grp - Create a group only if one doesn't exist
 * @grp_name:	Name of the group
 * @grp:	Full path and name of the group
 * @parent_grp:	Full path and name of the parent group
 *
 * Return: 0 on success, non-zero on failure
 */
static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
{
	int found_grp = 0;
	struct dirent *ep;
	DIR *dp;

	/*
	 * At this point, we are guaranteed to have resctrl FS mounted and if
	 * length of grp_name == 0, it means, user wants to use root con_mon
	 * grp, so do nothing
	 */
	if (strlen(grp_name) == 0)
		return 0;

	/* Check if requested grp exists or not */
	dp = opendir(parent_grp);
	if (dp) {
		while ((ep = readdir(dp)) != NULL) {
			if (strcmp(ep->d_name, grp_name) == 0)
				found_grp = 1;
		}
		closedir(dp);
	} else {
		perror("Unable to open resctrl for group");

		return -1;
	}

	/* Requested grp doesn't exist, hence create it */
	if (found_grp == 0) {
		if (mkdir(grp, 0) == -1) {
			perror("Unable to create group");

			return -1;
		}
	}

	return 0;
}

static int write_pid_to_tasks(char *tasks, pid_t pid)
{
	FILE *fp;

	fp = fopen(tasks, "w");
	if (!fp) {
		perror("Failed to open tasks file");

		return -1;
	}
	if (fprintf(fp, "%d\n", pid) < 0) {
		perror("Failed to wr pid to tasks file");
		fclose(fp);

		return -1;
	}
	fclose(fp);

	return 0;
}

/*
 * write_bm_pid_to_resctrl - Write a PID (i.e. benchmark) to resctrl FS
 * @bm_pid:		PID that should be written
 * @ctrlgrp:		Name of the control monitor group (con_mon grp)
 * @mongrp:		Name of the monitor group (mon grp)
 * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
 *
 * If a con_mon grp is requested, create it and write pid to it, otherwise
 * write pid to root con_mon grp.
 * If a mon grp is requested, create it and write pid to it, otherwise
 * pid is not written, this means that pid is in con_mon grp and hence
 * should consult con_mon grp's mon_data directory for results.
 *
 * Return: 0 on success, non-zero on failure
 */
int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
			    char *resctrl_val)
{
	char controlgroup[128], monitorgroup[512], monitorgroup_p[256];
	char tasks[1024];
	int ret = 0;

	if (strlen(ctrlgrp))
		sprintf(controlgroup, "%s/%s", RESCTRL_PATH, ctrlgrp);
	else
		sprintf(controlgroup, "%s", RESCTRL_PATH);

	/* Create control and monitoring group and write pid into it */
	ret = create_grp(ctrlgrp, controlgroup, RESCTRL_PATH);
	if (ret)
		goto out;
	sprintf(tasks, "%s/tasks", controlgroup);
	ret = write_pid_to_tasks(tasks, bm_pid);
	if (ret)
		goto out;

	/* Create mon grp and write pid into it for "mbm" and "cmt" test */
	if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)) ||
	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) {
		if (strlen(mongrp)) {
			sprintf(monitorgroup_p, "%s/mon_groups", controlgroup);
			sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp);
			ret = create_grp(mongrp, monitorgroup, monitorgroup_p);
			if (ret)
				goto out;

			sprintf(tasks, "%s/mon_groups/%s/tasks",
				controlgroup, mongrp);
			ret = write_pid_to_tasks(tasks, bm_pid);
			if (ret)
				goto out;
		}
	}

out:
	ksft_print_msg("Writing benchmark parameters to resctrl FS\n");
	if (ret)
		perror("# writing to resctrlfs");

	return ret;
}

/*
 * write_schemata - Update schemata of a con_mon grp
 * @ctrlgrp:		Name of the con_mon grp
 * @schemata:		Schemata that should be updated to
 * @cpu_no:		CPU number that the benchmark PID is binded to
 * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
 *
 * Update schemata of a con_mon grp *only* if requested resctrl feature is
 * allocation type
 *
 * Return: 0 on success, non-zero on failure
 */
int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
{
	char controlgroup[1024], schema[1024], reason[64];
	int resource_id, ret = 0;
	FILE *fp;

	if (strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) &&
	    strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) &&
	    strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
		return -ENOENT;

	if (!schemata) {
		ksft_print_msg("Skipping empty schemata update\n");

		return -1;
	}

	if (get_resource_id(cpu_no, &resource_id) < 0) {
		sprintf(reason, "Failed to get resource id");
		ret = -1;

		goto out;
	}

	if (strlen(ctrlgrp) != 0)
		sprintf(controlgroup, "%s/%s/schemata", RESCTRL_PATH, ctrlgrp);
	else
		sprintf(controlgroup, "%s/schemata", RESCTRL_PATH);

	if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) ||
	    !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
		sprintf(schema, "%s%d%c%s", "L3:", resource_id, '=', schemata);
	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)))
		sprintf(schema, "%s%d%c%s", "MB:", resource_id, '=', schemata);

	fp = fopen(controlgroup, "w");
	if (!fp) {
		sprintf(reason, "Failed to open control group");
		ret = -1;

		goto out;
	}

	if (fprintf(fp, "%s\n", schema) < 0) {
		sprintf(reason, "Failed to write schemata in control group");
		fclose(fp);
		ret = -1;

		goto out;
	}
	fclose(fp);

out:
	ksft_print_msg("Write schema \"%s\" to resctrl FS%s%s\n",
		       schema, ret ? " # " : "",
		       ret ? reason : "");

	return ret;
}

bool check_resctrlfs_support(void)
{
	FILE *inf = fopen("/proc/filesystems", "r");
	DIR *dp;
	char *res;
	bool ret = false;

	if (!inf)
		return false;

	res = fgrep(inf, "nodev\tresctrl\n");

	if (res) {
		ret = true;
		free(res);
	}

	fclose(inf);

	ksft_print_msg("%s Check kernel supports resctrl filesystem\n",
		       ret ? "Pass:" : "Fail:");

	if (!ret)
		return ret;

	dp = opendir(RESCTRL_PATH);
	ksft_print_msg("%s Check resctrl mountpoint \"%s\" exists\n",
		       dp ? "Pass:" : "Fail:", RESCTRL_PATH);
	if (dp)
		closedir(dp);

	ksft_print_msg("resctrl filesystem %s mounted\n",
		       find_resctrl_mount(NULL) ? "not" : "is");

	return ret;
}

char *fgrep(FILE *inf, const char *str)
{
	char line[256];
	int slen = strlen(str);

	while (!feof(inf)) {
		if (!fgets(line, 256, inf))
			break;
		if (strncmp(line, str, slen))
			continue;

		return strdup(line);
	}

	return NULL;
}

/*
 * validate_resctrl_feature_request - Check if requested feature is valid.
 * @resctrl_val:	Requested feature
 *
 * Return: True if the feature is supported, else false
 */
bool validate_resctrl_feature_request(const char *resctrl_val)
{
	struct stat statbuf;
	bool found = false;
	char *res;
	FILE *inf;

	if (!resctrl_val)
		return false;

	if (remount_resctrlfs(false))
		return false;

	if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) {
		if (!stat(L3_PATH, &statbuf))
			return true;
	} else if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
		if (!stat(MB_PATH, &statbuf))
			return true;
	} else if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
		   !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {
		if (!stat(L3_MON_PATH, &statbuf)) {
			inf = fopen(L3_MON_FEATURES_PATH, "r");
			if (!inf)
				return false;

			if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {
				res = fgrep(inf, "llc_occupancy");
				if (res) {
					found = true;
					free(res);
				}
			}

			if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) {
				res = fgrep(inf, "mbm_total_bytes");
				if (res) {
					free(res);
					res = fgrep(inf, "mbm_local_bytes");
					if (res) {
						found = true;
						free(res);
					}
				}
			}
			fclose(inf);
		}
	}

	return found;
}

int filter_dmesg(void)
{
	char line[1024];
	FILE *fp;
	int pipefds[2];
	pid_t pid;
	int ret;

	ret = pipe(pipefds);
	if (ret) {
		perror("pipe");
		return ret;
	}
	pid = fork();
	if (pid == 0) {
		close(pipefds[0]);
		dup2(pipefds[1], STDOUT_FILENO);
		execlp("dmesg", "dmesg", NULL);
		perror("executing dmesg");
		exit(1);
	}
	close(pipefds[1]);
	fp = fdopen(pipefds[0], "r");
	if (!fp) {
		perror("fdopen(pipe)");
		kill(pid, SIGTERM);

		return -1;
	}

	while (fgets(line, 1024, fp)) {
		if (strstr(line, "intel_rdt:"))
			ksft_print_msg("dmesg: %s", line);
		if (strstr(line, "resctrl:"))
			ksft_print_msg("dmesg: %s", line);
	}
	fclose(fp);
	waitpid(pid, NULL, 0);

	return 0;
}

int validate_bw_report_request(char *bw_report)
{
	if (strcmp(bw_report, "reads") == 0)
		return 0;
	if (strcmp(bw_report, "writes") == 0)
		return 0;
	if (strcmp(bw_report, "nt-writes") == 0) {
		strcpy(bw_report, "writes");
		return 0;
	}
	if (strcmp(bw_report, "total") == 0)
		return 0;

	fprintf(stderr, "Requested iMC B/W report type unavailable\n");

	return -1;
}

int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
		    int group_fd, unsigned long flags)
{
	int ret;

	ret = syscall(__NR_perf_event_open, hw_event, pid, cpu,
		      group_fd, flags);
	return ret;
}

unsigned int count_bits(unsigned long n)
{
	unsigned int count = 0;

	while (n) {
		count += n & 1;
		n >>= 1;
	}

	return count;
}