summaryrefslogtreecommitdiff
path: root/tools/lib/perf/cpumap.c
blob: 6cd0be7c1bb438e50011600ec5e1d898bba9059b (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
// SPDX-License-Identifier: GPL-2.0-only
#include <perf/cpumap.h>
#include <stdlib.h>
#include <linux/refcount.h>
#include <internal/cpumap.h>
#include <asm/bug.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <ctype.h>
#include <limits.h>

static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
{
	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);

	if (cpus != NULL) {
		cpus->nr = nr_cpus;
		refcount_set(&cpus->refcnt, 1);

	}
	return cpus;
}

struct perf_cpu_map *perf_cpu_map__dummy_new(void)
{
	struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);

	if (cpus)
		cpus->map[0].cpu = -1;

	return cpus;
}

static void cpu_map__delete(struct perf_cpu_map *map)
{
	if (map) {
		WARN_ONCE(refcount_read(&map->refcnt) != 0,
			  "cpu_map refcnt unbalanced\n");
		free(map);
	}
}

struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map)
{
	if (map)
		refcount_inc(&map->refcnt);
	return map;
}

void perf_cpu_map__put(struct perf_cpu_map *map)
{
	if (map && refcount_dec_and_test(&map->refcnt))
		cpu_map__delete(map);
}

static struct perf_cpu_map *cpu_map__default_new(void)
{
	struct perf_cpu_map *cpus;
	int nr_cpus;

	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
	if (nr_cpus < 0)
		return NULL;

	cpus = perf_cpu_map__alloc(nr_cpus);
	if (cpus != NULL) {
		int i;

		for (i = 0; i < nr_cpus; ++i)
			cpus->map[i].cpu = i;
	}

	return cpus;
}

struct perf_cpu_map *perf_cpu_map__default_new(void)
{
	return cpu_map__default_new();
}


static int cmp_cpu(const void *a, const void *b)
{
	const struct perf_cpu *cpu_a = a, *cpu_b = b;

	return cpu_a->cpu - cpu_b->cpu;
}

static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus)
{
	size_t payload_size = nr_cpus * sizeof(struct perf_cpu);
	struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr_cpus);
	int i, j;

	if (cpus != NULL) {
		memcpy(cpus->map, tmp_cpus, payload_size);
		qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
		/* Remove dups */
		j = 0;
		for (i = 0; i < nr_cpus; i++) {
			if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu)
				cpus->map[j++].cpu = cpus->map[i].cpu;
		}
		cpus->nr = j;
		assert(j <= nr_cpus);
	}
	return cpus;
}

struct perf_cpu_map *perf_cpu_map__read(FILE *file)
{
	struct perf_cpu_map *cpus = NULL;
	int nr_cpus = 0;
	struct perf_cpu *tmp_cpus = NULL, *tmp;
	int max_entries = 0;
	int n, cpu, prev;
	char sep;

	sep = 0;
	prev = -1;
	for (;;) {
		n = fscanf(file, "%u%c", &cpu, &sep);
		if (n <= 0)
			break;
		if (prev >= 0) {
			int new_max = nr_cpus + cpu - prev - 1;

			WARN_ONCE(new_max >= MAX_NR_CPUS, "Perf can support %d CPUs. "
							  "Consider raising MAX_NR_CPUS\n", MAX_NR_CPUS);

			if (new_max >= max_entries) {
				max_entries = new_max + MAX_NR_CPUS / 2;
				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
				if (tmp == NULL)
					goto out_free_tmp;
				tmp_cpus = tmp;
			}

			while (++prev < cpu)
				tmp_cpus[nr_cpus++].cpu = prev;
		}
		if (nr_cpus == max_entries) {
			max_entries += MAX_NR_CPUS;
			tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
			if (tmp == NULL)
				goto out_free_tmp;
			tmp_cpus = tmp;
		}

		tmp_cpus[nr_cpus++].cpu = cpu;
		if (n == 2 && sep == '-')
			prev = cpu;
		else
			prev = -1;
		if (n == 1 || sep == '\n')
			break;
	}

	if (nr_cpus > 0)
		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
	else
		cpus = cpu_map__default_new();
out_free_tmp:
	free(tmp_cpus);
	return cpus;
}

static struct perf_cpu_map *cpu_map__read_all_cpu_map(void)
{
	struct perf_cpu_map *cpus = NULL;
	FILE *onlnf;

	onlnf = fopen("/sys/devices/system/cpu/online", "r");
	if (!onlnf)
		return cpu_map__default_new();

	cpus = perf_cpu_map__read(onlnf);
	fclose(onlnf);
	return cpus;
}

struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
{
	struct perf_cpu_map *cpus = NULL;
	unsigned long start_cpu, end_cpu = 0;
	char *p = NULL;
	int i, nr_cpus = 0;
	struct perf_cpu *tmp_cpus = NULL, *tmp;
	int max_entries = 0;

	if (!cpu_list)
		return cpu_map__read_all_cpu_map();

	/*
	 * must handle the case of empty cpumap to cover
	 * TOPOLOGY header for NUMA nodes with no CPU
	 * ( e.g., because of CPU hotplug)
	 */
	if (!isdigit(*cpu_list) && *cpu_list != '\0')
		goto out;

	while (isdigit(*cpu_list)) {
		p = NULL;
		start_cpu = strtoul(cpu_list, &p, 0);
		if (start_cpu >= INT_MAX
		    || (*p != '\0' && *p != ',' && *p != '-'))
			goto invalid;

		if (*p == '-') {
			cpu_list = ++p;
			p = NULL;
			end_cpu = strtoul(cpu_list, &p, 0);

			if (end_cpu >= INT_MAX || (*p != '\0' && *p != ','))
				goto invalid;

			if (end_cpu < start_cpu)
				goto invalid;
		} else {
			end_cpu = start_cpu;
		}

		WARN_ONCE(end_cpu >= MAX_NR_CPUS, "Perf can support %d CPUs. "
						  "Consider raising MAX_NR_CPUS\n", MAX_NR_CPUS);

		for (; start_cpu <= end_cpu; start_cpu++) {
			/* check for duplicates */
			for (i = 0; i < nr_cpus; i++)
				if (tmp_cpus[i].cpu == (int)start_cpu)
					goto invalid;

			if (nr_cpus == max_entries) {
				max_entries += MAX_NR_CPUS;
				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
				if (tmp == NULL)
					goto invalid;
				tmp_cpus = tmp;
			}
			tmp_cpus[nr_cpus++].cpu = (int)start_cpu;
		}
		if (*p)
			++p;

		cpu_list = p;
	}

	if (nr_cpus > 0)
		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
	else if (*cpu_list != '\0')
		cpus = cpu_map__default_new();
	else
		cpus = perf_cpu_map__dummy_new();
invalid:
	free(tmp_cpus);
out:
	return cpus;
}

struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
{
	struct perf_cpu result = {
		.cpu = -1
	};

	if (cpus && idx < cpus->nr)
		return cpus->map[idx];

	return result;
}

int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
{
	return cpus ? cpus->nr : 1;
}

bool perf_cpu_map__empty(const struct perf_cpu_map *map)
{
	return map ? map->map[0].cpu == -1 : true;
}

int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
{
	int low, high;

	if (!cpus)
		return -1;

	low = 0;
	high = cpus->nr;
	while (low < high) {
		int idx = (low + high) / 2;
		struct perf_cpu cpu_at_idx = cpus->map[idx];

		if (cpu_at_idx.cpu == cpu.cpu)
			return idx;

		if (cpu_at_idx.cpu > cpu.cpu)
			high = idx;
		else
			low = idx + 1;
	}

	return -1;
}

bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
{
	return perf_cpu_map__idx(cpus, cpu) != -1;
}

struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
{
	struct perf_cpu result = {
		.cpu = -1
	};

	// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
	return map->nr > 0 ? map->map[map->nr - 1] : result;
}

/** Is 'b' a subset of 'a'. */
bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b)
{
	if (a == b || !b)
		return true;
	if (!a || b->nr > a->nr)
		return false;

	for (int i = 0, j = 0; i < a->nr; i++) {
		if (a->map[i].cpu > b->map[j].cpu)
			return false;
		if (a->map[i].cpu == b->map[j].cpu) {
			j++;
			if (j == b->nr)
				return true;
		}
	}
	return false;
}

/*
 * Merge two cpumaps
 *
 * orig either gets freed and replaced with a new map, or reused
 * with no reference count change (similar to "realloc")
 * other has its reference count increased.
 */

struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
					 struct perf_cpu_map *other)
{
	struct perf_cpu *tmp_cpus;
	int tmp_len;
	int i, j, k;
	struct perf_cpu_map *merged;

	if (perf_cpu_map__is_subset(orig, other))
		return orig;
	if (perf_cpu_map__is_subset(other, orig)) {
		perf_cpu_map__put(orig);
		return perf_cpu_map__get(other);
	}

	tmp_len = orig->nr + other->nr;
	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
	if (!tmp_cpus)
		return NULL;

	/* Standard merge algorithm from wikipedia */
	i = j = k = 0;
	while (i < orig->nr && j < other->nr) {
		if (orig->map[i].cpu <= other->map[j].cpu) {
			if (orig->map[i].cpu == other->map[j].cpu)
				j++;
			tmp_cpus[k++] = orig->map[i++];
		} else
			tmp_cpus[k++] = other->map[j++];
	}

	while (i < orig->nr)
		tmp_cpus[k++] = orig->map[i++];

	while (j < other->nr)
		tmp_cpus[k++] = other->map[j++];
	assert(k <= tmp_len);

	merged = cpu_map__trim_new(k, tmp_cpus);
	free(tmp_cpus);
	perf_cpu_map__put(orig);
	return merged;
}