summaryrefslogtreecommitdiffstats
path: root/tools/perf/util/env.c
blob: ed2a42abe127066cca0ab008e08f1904c67451da (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
// SPDX-License-Identifier: GPL-2.0
#include "cpumap.h"
#include "debug.h"
#include "env.h"
#include "util/header.h"
#include <linux/ctype.h>
#include <linux/zalloc.h>
#include "bpf-event.h"
#include "cgroup.h"
#include <errno.h>
#include <sys/utsname.h>
#include <bpf/libbpf.h>
#include <stdlib.h>
#include <string.h>

struct perf_env perf_env;

void perf_env__insert_bpf_prog_info(struct perf_env *env,
				    struct bpf_prog_info_node *info_node)
{
	down_write(&env->bpf_progs.lock);
	__perf_env__insert_bpf_prog_info(env, info_node);
	up_write(&env->bpf_progs.lock);
}

void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node)
{
	__u32 prog_id = info_node->info_linear->info.id;
	struct bpf_prog_info_node *node;
	struct rb_node *parent = NULL;
	struct rb_node **p;

	p = &env->bpf_progs.infos.rb_node;

	while (*p != NULL) {
		parent = *p;
		node = rb_entry(parent, struct bpf_prog_info_node, rb_node);
		if (prog_id < node->info_linear->info.id) {
			p = &(*p)->rb_left;
		} else if (prog_id > node->info_linear->info.id) {
			p = &(*p)->rb_right;
		} else {
			pr_debug("duplicated bpf prog info %u\n", prog_id);
			return;
		}
	}

	rb_link_node(&info_node->rb_node, parent, p);
	rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos);
	env->bpf_progs.infos_cnt++;
}

struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
							__u32 prog_id)
{
	struct bpf_prog_info_node *node = NULL;
	struct rb_node *n;

	down_read(&env->bpf_progs.lock);
	n = env->bpf_progs.infos.rb_node;

	while (n) {
		node = rb_entry(n, struct bpf_prog_info_node, rb_node);
		if (prog_id < node->info_linear->info.id)
			n = n->rb_left;
		else if (prog_id > node->info_linear->info.id)
			n = n->rb_right;
		else
			goto out;
	}
	node = NULL;

out:
	up_read(&env->bpf_progs.lock);
	return node;
}

bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
{
	bool ret;

	down_write(&env->bpf_progs.lock);
	ret = __perf_env__insert_btf(env, btf_node);
	up_write(&env->bpf_progs.lock);
	return ret;
}

bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
{
	struct rb_node *parent = NULL;
	__u32 btf_id = btf_node->id;
	struct btf_node *node;
	struct rb_node **p;

	p = &env->bpf_progs.btfs.rb_node;

	while (*p != NULL) {
		parent = *p;
		node = rb_entry(parent, struct btf_node, rb_node);
		if (btf_id < node->id) {
			p = &(*p)->rb_left;
		} else if (btf_id > node->id) {
			p = &(*p)->rb_right;
		} else {
			pr_debug("duplicated btf %u\n", btf_id);
			return false;
		}
	}

	rb_link_node(&btf_node->rb_node, parent, p);
	rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs);
	env->bpf_progs.btfs_cnt++;
	return true;
}

struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
{
	struct btf_node *res;

	down_read(&env->bpf_progs.lock);
	res = __perf_env__find_btf(env, btf_id);
	up_read(&env->bpf_progs.lock);
	return res;
}

struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id)
{
	struct btf_node *node = NULL;
	struct rb_node *n;

	n = env->bpf_progs.btfs.rb_node;

	while (n) {
		node = rb_entry(n, struct btf_node, rb_node);
		if (btf_id < node->id)
			n = n->rb_left;
		else if (btf_id > node->id)
			n = n->rb_right;
		else
			return node;
	}
	return NULL;
}

/* purge data in bpf_progs.infos tree */
static void perf_env__purge_bpf(struct perf_env *env)
{
	struct rb_root *root;
	struct rb_node *next;

	down_write(&env->bpf_progs.lock);

	root = &env->bpf_progs.infos;
	next = rb_first(root);

	while (next) {
		struct bpf_prog_info_node *node;

		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
		next = rb_next(&node->rb_node);
		rb_erase(&node->rb_node, root);
		free(node->info_linear);
		free(node);
	}

	env->bpf_progs.infos_cnt = 0;

	root = &env->bpf_progs.btfs;
	next = rb_first(root);

	while (next) {
		struct btf_node *node;

		node = rb_entry(next, struct btf_node, rb_node);
		next = rb_next(&node->rb_node);
		rb_erase(&node->rb_node, root);
		free(node);
	}

	env->bpf_progs.btfs_cnt = 0;

	up_write(&env->bpf_progs.lock);
}

void perf_env__exit(struct perf_env *env)
{
	int i;

	perf_env__purge_bpf(env);
	perf_env__purge_cgroups(env);
	zfree(&env->hostname);
	zfree(&env->os_release);
	zfree(&env->version);
	zfree(&env->arch);
	zfree(&env->cpu_desc);
	zfree(&env->cpuid);
	zfree(&env->cmdline);
	zfree(&env->cmdline_argv);
	zfree(&env->sibling_dies);
	zfree(&env->sibling_cores);
	zfree(&env->sibling_threads);
	zfree(&env->pmu_mappings);
	zfree(&env->cpu);
	zfree(&env->cpu_pmu_caps);
	zfree(&env->numa_map);

	for (i = 0; i < env->nr_numa_nodes; i++)
		perf_cpu_map__put(env->numa_nodes[i].map);
	zfree(&env->numa_nodes);

	for (i = 0; i < env->caches_cnt; i++)
		cpu_cache_level__free(&env->caches[i]);
	zfree(&env->caches);

	for (i = 0; i < env->nr_memory_nodes; i++)
		zfree(&env->memory_nodes[i].set);
	zfree(&env->memory_nodes);
}

void perf_env__init(struct perf_env *env)
{
	env->bpf_progs.infos = RB_ROOT;
	env->bpf_progs.btfs = RB_ROOT;
	init_rwsem(&env->bpf_progs.lock);
}

int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
{
	int i;

	/* do not include NULL termination */
	env->cmdline_argv = calloc(argc, sizeof(char *));
	if (env->cmdline_argv == NULL)
		goto out_enomem;

	/*
	 * Must copy argv contents because it gets moved around during option
	 * parsing:
	 */
	for (i = 0; i < argc ; i++) {
		env->cmdline_argv[i] = argv[i];
		if (env->cmdline_argv[i] == NULL)
			goto out_free;
	}

	env->nr_cmdline = argc;

	return 0;
out_free:
	zfree(&env->cmdline_argv);
out_enomem:
	return -ENOMEM;
}

int perf_env__read_cpu_topology_map(struct perf_env *env)
{
	int cpu, nr_cpus;

	if (env->cpu != NULL)
		return 0;

	if (env->nr_cpus_avail == 0)
		env->nr_cpus_avail = cpu__max_present_cpu();

	nr_cpus = env->nr_cpus_avail;
	if (nr_cpus == -1)
		return -EINVAL;

	env->cpu = calloc(nr_cpus, sizeof(env->cpu[0]));
	if (env->cpu == NULL)
		return -ENOMEM;

	for (cpu = 0; cpu < nr_cpus; ++cpu) {
		env->cpu[cpu].core_id	= cpu_map__get_core_id(cpu);
		env->cpu[cpu].socket_id	= cpu_map__get_socket_id(cpu);
		env->cpu[cpu].die_id	= cpu_map__get_die_id(cpu);
	}

	env->nr_cpus_avail = nr_cpus;
	return 0;
}

int perf_env__read_cpuid(struct perf_env *env)
{
	char cpuid[128];
	int err = get_cpuid(cpuid, sizeof(cpuid));

	if (err)
		return err;

	free(env->cpuid);
	env->cpuid = strdup(cpuid);
	if (env->cpuid == NULL)
		return ENOMEM;
	return 0;
}

static int perf_env__read_arch(struct perf_env *env)
{
	struct utsname uts;

	if (env->arch)
		return 0;

	if (!uname(&uts))
		env->arch = strdup(uts.machine);

	return env->arch ? 0 : -ENOMEM;
}

static int perf_env__read_nr_cpus_avail(struct perf_env *env)
{
	if (env->nr_cpus_avail == 0)
		env->nr_cpus_avail = cpu__max_present_cpu();

	return env->nr_cpus_avail ? 0 : -ENOENT;
}

const char *perf_env__raw_arch(struct perf_env *env)
{
	return env && !perf_env__read_arch(env) ? env->arch : "unknown";
}

int perf_env__nr_cpus_avail(struct perf_env *env)
{
	return env && !perf_env__read_nr_cpus_avail(env) ? env->nr_cpus_avail : 0;
}

void cpu_cache_level__free(struct cpu_cache_level *cache)
{
	zfree(&cache->type);
	zfree(&cache->map);
	zfree(&cache->size);
}

/*
 * Return architecture name in a normalized form.
 * The conversion logic comes from the Makefile.
 */
static const char *normalize_arch(char *arch)
{
	if (!strcmp(arch, "x86_64"))
		return "x86";
	if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6')
		return "x86";
	if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
		return "sparc";
	if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64"))
		return "arm64";
	if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
		return "arm";
	if (!strncmp(arch, "s390", 4))
		return "s390";
	if (!strncmp(arch, "parisc", 6))
		return "parisc";
	if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3))
		return "powerpc";
	if (!strncmp(arch, "mips", 4))
		return "mips";
	if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
		return "sh";

	return arch;
}

const char *perf_env__arch(struct perf_env *env)
{
	char *arch_name;

	if (!env || !env->arch) { /* Assume local operation */
		static struct utsname uts = { .machine[0] = '\0', };
		if (uts.machine[0] == '\0' && uname(&uts) < 0)
			return NULL;
		arch_name = uts.machine;
	} else
		arch_name = env->arch;

	return normalize_arch(arch_name);
}


int perf_env__numa_node(struct perf_env *env, int cpu)
{
	if (!env->nr_numa_map) {
		struct numa_node *nn;
		int i, nr = 0;

		for (i = 0; i < env->nr_numa_nodes; i++) {
			nn = &env->numa_nodes[i];
			nr = max(nr, perf_cpu_map__max(nn->map));
		}

		nr++;

		/*
		 * We initialize the numa_map array to prepare
		 * it for missing cpus, which return node -1
		 */
		env->numa_map = malloc(nr * sizeof(int));
		if (!env->numa_map)
			return -1;

		for (i = 0; i < nr; i++)
			env->numa_map[i] = -1;

		env->nr_numa_map = nr;

		for (i = 0; i < env->nr_numa_nodes; i++) {
			int tmp, j;

			nn = &env->numa_nodes[i];
			perf_cpu_map__for_each_cpu(j, tmp, nn->map)
				env->numa_map[j] = i;
		}
	}

	return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1;
}