cs-etm.c 23.1 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
2 3 4 5 6 7
/*
 * Copyright(C) 2015 Linaro Limited. All rights reserved.
 * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
 */

#include <api/fs/fs.h>
8
#include <linux/bits.h>
9
#include <linux/bitops.h>
10
#include <linux/compiler.h>
11 12 13
#include <linux/coresight-pmu.h>
#include <linux/kernel.h>
#include <linux/log2.h>
14
#include <linux/string.h>
15
#include <linux/types.h>
16
#include <linux/zalloc.h>
17 18

#include "cs-etm.h"
19
#include "../../util/debug.h"
20
#include "../../util/record.h"
21 22
#include "../../util/auxtrace.h"
#include "../../util/cpumap.h"
23
#include "../../util/event.h"
24
#include "../../util/evlist.h"
25
#include "../../util/evsel.h"
26
#include "../../util/evsel_config.h"
27 28
#include "../../util/pmu.h"
#include "../../util/cs-etm.h"
29
#include <internal/lib.h> // page_size
30
#include "../../util/session.h"
31

32
#include <errno.h>
33
#include <stdlib.h>
34
#include <sys/stat.h>
35 36 37 38

struct cs_etm_recording {
	struct auxtrace_record	itr;
	struct perf_pmu		*cs_etm_pmu;
39
	struct evlist		*evlist;
40 41
	int			wrapped_cnt;
	bool			*wrapped;
42 43 44 45
	bool			snapshot_mode;
	size_t			snapshot_size;
};

46 47 48 49 50 51 52 53 54 55 56 57 58
static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = {
	[CS_ETM_ETMCCER]	= "mgmt/etmccer",
	[CS_ETM_ETMIDR]		= "mgmt/etmidr",
};

static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = {
	[CS_ETMV4_TRCIDR0]		= "trcidr/trcidr0",
	[CS_ETMV4_TRCIDR1]		= "trcidr/trcidr1",
	[CS_ETMV4_TRCIDR2]		= "trcidr/trcidr2",
	[CS_ETMV4_TRCIDR8]		= "trcidr/trcidr8",
	[CS_ETMV4_TRCAUTHSTATUS]	= "mgmt/trcauthstatus",
};

59 60
static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu);

61
static int cs_etm_set_context_id(struct auxtrace_record *itr,
62
				 struct evsel *evsel, int cpu)
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
{
	struct cs_etm_recording *ptr;
	struct perf_pmu *cs_etm_pmu;
	char path[PATH_MAX];
	int err = -EINVAL;
	u32 val;

	ptr = container_of(itr, struct cs_etm_recording, itr);
	cs_etm_pmu = ptr->cs_etm_pmu;

	if (!cs_etm_is_etmv4(itr, cpu))
		goto out;

	/* Get a handle on TRCIRD2 */
	snprintf(path, PATH_MAX, "cpu%d/%s",
		 cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
	err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);

	/* There was a problem reading the file, bailing out */
	if (err != 1) {
		pr_err("%s: can't read file %s\n",
		       CORESIGHT_ETM_PMU_NAME, path);
		goto out;
	}

	/*
	 * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID tracing
	 * is supported:
	 *  0b00000 Context ID tracing is not supported.
	 *  0b00100 Maximum of 32-bit Context ID size.
	 *  All other values are reserved.
	 */
	val = BMVAL(val, 5, 9);
	if (!val || val != 0x4) {
		err = -EINVAL;
		goto out;
	}

	/* All good, let the kernel know */
102
	evsel->core.attr.config |= (1 << ETM_OPT_CTXTID);
103 104 105 106 107 108 109
	err = 0;

out:

	return err;
}

110
static int cs_etm_set_timestamp(struct auxtrace_record *itr,
111
				struct evsel *evsel, int cpu)
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
{
	struct cs_etm_recording *ptr;
	struct perf_pmu *cs_etm_pmu;
	char path[PATH_MAX];
	int err = -EINVAL;
	u32 val;

	ptr = container_of(itr, struct cs_etm_recording, itr);
	cs_etm_pmu = ptr->cs_etm_pmu;

	if (!cs_etm_is_etmv4(itr, cpu))
		goto out;

	/* Get a handle on TRCIRD0 */
	snprintf(path, PATH_MAX, "cpu%d/%s",
		 cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
	err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);

	/* There was a problem reading the file, bailing out */
	if (err != 1) {
		pr_err("%s: can't read file %s\n",
		       CORESIGHT_ETM_PMU_NAME, path);
		goto out;
	}

	/*
	 * TRCIDR0.TSSIZE, bit [28-24], indicates whether global timestamping
	 * is supported:
	 *  0b00000 Global timestamping is not implemented
	 *  0b00110 Implementation supports a maximum timestamp of 48bits.
	 *  0b01000 Implementation supports a maximum timestamp of 64bits.
	 */
	val &= GENMASK(28, 24);
	if (!val) {
		err = -EINVAL;
		goto out;
	}

	/* All good, let the kernel know */
151
	evsel->core.attr.config |= (1 << ETM_OPT_TS);
152 153 154 155 156 157
	err = 0;

out:
	return err;
}

158
static int cs_etm_set_option(struct auxtrace_record *itr,
159
			     struct evsel *evsel, u32 option)
160 161
{
	int i, err = -EINVAL;
162
	struct perf_cpu_map *event_cpus = evsel->evlist->core.cpus;
163
	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
164 165 166 167 168 169 170

	/* Set option of each CPU we have */
	for (i = 0; i < cpu__max_cpu(); i++) {
		if (!cpu_map__has(event_cpus, i) ||
		    !cpu_map__has(online_cpus, i))
			continue;

171
		if (option & ETM_OPT_CTXTID) {
172 173 174
			err = cs_etm_set_context_id(itr, evsel, i);
			if (err)
				goto out;
175 176
		}
		if (option & ETM_OPT_TS) {
177 178 179
			err = cs_etm_set_timestamp(itr, evsel, i);
			if (err)
				goto out;
180
		}
181 182 183
		if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS))
			/* Nothing else is currently supported */
			goto out;
184 185 186 187
	}

	err = 0;
out:
188
	perf_cpu_map__put(online_cpus);
189 190 191
	return err;
}

192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213
static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr,
					 struct record_opts *opts,
					 const char *str)
{
	struct cs_etm_recording *ptr =
				container_of(itr, struct cs_etm_recording, itr);
	unsigned long long snapshot_size = 0;
	char *endptr;

	if (str) {
		snapshot_size = strtoull(str, &endptr, 0);
		if (*endptr || snapshot_size > SIZE_MAX)
			return -1;
	}

	opts->auxtrace_snapshot_mode = true;
	opts->auxtrace_snapshot_size = snapshot_size;
	ptr->snapshot_size = snapshot_size;

	return 0;
}

214
static int cs_etm_set_sink_attr(struct perf_pmu *pmu,
215
				struct evsel *evsel)
216 217 218 219 220 221
{
	char msg[BUFSIZ], path[PATH_MAX], *sink;
	struct perf_evsel_config_term *term;
	int ret = -EINVAL;
	u32 hash;

222
	if (evsel->core.attr.config2 & GENMASK(31, 0))
223 224 225 226 227 228
		return 0;

	list_for_each_entry(term, &evsel->config_terms, list) {
		if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG)
			continue;

229
		sink = term->val.str;
230 231 232 233 234 235 236 237 238 239
		snprintf(path, PATH_MAX, "sinks/%s", sink);

		ret = perf_pmu__scan_file(pmu, path, "%x", &hash);
		if (ret != 1) {
			pr_err("failed to set sink \"%s\" on event %s with %d (%s)\n",
			       sink, perf_evsel__name(evsel), errno,
			       str_error_r(errno, msg, sizeof(msg)));
			return ret;
		}

240
		evsel->core.attr.config2 |= hash;
241 242 243 244 245 246 247 248 249 250
		return 0;
	}

	/*
	 * No sink was provided on the command line - for _now_ treat
	 * this as an error.
	 */
	return ret;
}

251
static int cs_etm_recording_options(struct auxtrace_record *itr,
252
				    struct evlist *evlist,
253 254
				    struct record_opts *opts)
{
255
	int ret;
256 257 258
	struct cs_etm_recording *ptr =
				container_of(itr, struct cs_etm_recording, itr);
	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
259
	struct evsel *evsel, *cs_etm_evsel = NULL;
260
	struct perf_cpu_map *cpus = evlist->core.cpus;
261
	bool privileged = perf_event_paranoid_check(-1);
262
	int err = 0;
263 264 265

	ptr->evlist = evlist;
	ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
266 267 268

	if (perf_can_record_switch_events())
		opts->record_switch_events = true;
269 270

	evlist__for_each_entry(evlist, evsel) {
271
		if (evsel->core.attr.type == cs_etm_pmu->type) {
272 273 274 275 276
			if (cs_etm_evsel) {
				pr_err("There may be only one %s event\n",
				       CORESIGHT_ETM_PMU_NAME);
				return -EINVAL;
			}
277 278
			evsel->core.attr.freq = 0;
			evsel->core.attr.sample_period = 1;
279 280 281 282 283 284 285 286 287
			cs_etm_evsel = evsel;
			opts->full_auxtrace = true;
		}
	}

	/* no need to continue if at least one event of interest was found */
	if (!cs_etm_evsel)
		return 0;

288 289 290 291
	ret = cs_etm_set_sink_attr(cs_etm_pmu, cs_etm_evsel);
	if (ret)
		return ret;

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
	if (opts->use_clockid) {
		pr_err("Cannot use clockid (-k option) with %s\n",
		       CORESIGHT_ETM_PMU_NAME);
		return -EINVAL;
	}

	/* we are in snapshot mode */
	if (opts->auxtrace_snapshot_mode) {
		/*
		 * No size were given to '-S' or '-m,', so go with
		 * the default
		 */
		if (!opts->auxtrace_snapshot_size &&
		    !opts->auxtrace_mmap_pages) {
			if (privileged) {
				opts->auxtrace_mmap_pages = MiB(4) / page_size;
			} else {
				opts->auxtrace_mmap_pages =
							KiB(128) / page_size;
				if (opts->mmap_pages == UINT_MAX)
					opts->mmap_pages = KiB(256) / page_size;
			}
		} else if (!opts->auxtrace_mmap_pages && !privileged &&
						opts->mmap_pages == UINT_MAX) {
			opts->mmap_pages = KiB(256) / page_size;
		}

		/*
		 * '-m,xyz' was specified but no snapshot size, so make the
		 * snapshot size as big as the auxtrace mmap area.
		 */
		if (!opts->auxtrace_snapshot_size) {
			opts->auxtrace_snapshot_size =
				opts->auxtrace_mmap_pages * (size_t)page_size;
		}

		/*
		 * -Sxyz was specified but no auxtrace mmap area, so make the
		 * auxtrace mmap area big enough to fit the requested snapshot
		 * size.
		 */
		if (!opts->auxtrace_mmap_pages) {
			size_t sz = opts->auxtrace_snapshot_size;

			sz = round_up(sz, page_size) / page_size;
			opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
		}

		/* Snapshost size can't be bigger than the auxtrace area */
		if (opts->auxtrace_snapshot_size >
				opts->auxtrace_mmap_pages * (size_t)page_size) {
			pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
			       opts->auxtrace_snapshot_size,
			       opts->auxtrace_mmap_pages * (size_t)page_size);
			return -EINVAL;
		}

		/* Something went wrong somewhere - this shouldn't happen */
		if (!opts->auxtrace_snapshot_size ||
		    !opts->auxtrace_mmap_pages) {
			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
			return -EINVAL;
		}
	}

	/* We are in full trace mode but '-m,xyz' wasn't specified */
	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
		if (privileged) {
			opts->auxtrace_mmap_pages = MiB(4) / page_size;
		} else {
			opts->auxtrace_mmap_pages = KiB(128) / page_size;
			if (opts->mmap_pages == UINT_MAX)
				opts->mmap_pages = KiB(256) / page_size;
		}

	}

	/* Validate auxtrace_mmap_pages provided by user */
	if (opts->auxtrace_mmap_pages) {
		unsigned int max_page = (KiB(128) / page_size);
		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;

		if (!privileged &&
		    opts->auxtrace_mmap_pages > max_page) {
			opts->auxtrace_mmap_pages = max_page;
			pr_err("auxtrace too big, truncating to %d\n",
			       max_page);
		}

		if (!is_power_of_2(sz)) {
			pr_err("Invalid mmap size for %s: must be a power of 2\n",
			       CORESIGHT_ETM_PMU_NAME);
			return -EINVAL;
		}
	}

	if (opts->auxtrace_snapshot_mode)
		pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME,
			  opts->auxtrace_snapshot_size);

392 393 394 395 396 397 398 399
	/*
	 * To obtain the auxtrace buffer file descriptor, the auxtrace
	 * event must come first.
	 */
	perf_evlist__to_front(evlist, cs_etm_evsel);

	/*
	 * In the case of per-cpu mmaps, we need the CPU on the
400 401
	 * AUX event.  We also need the contextID in order to be notified
	 * when a context switch happened.
402
	 */
403
	if (!perf_cpu_map__empty(cpus)) {
404
		perf_evsel__set_sample_bit(cs_etm_evsel, CPU);
405

406 407
		err = cs_etm_set_option(itr, cs_etm_evsel,
					ETM_OPT_CTXTID | ETM_OPT_TS);
408 409
		if (err)
			goto out;
410 411
	}

412 413
	/* Add dummy event to keep tracking */
	if (opts->full_auxtrace) {
414
		struct evsel *tracking_evsel;
415 416 417

		err = parse_events(evlist, "dummy:u", NULL);
		if (err)
418
			goto out;
419

420
		tracking_evsel = evlist__last(evlist);
421 422
		perf_evlist__set_tracking_event(evlist, tracking_evsel);

423 424
		tracking_evsel->core.attr.freq = 0;
		tracking_evsel->core.attr.sample_period = 1;
425 426

		/* In per-cpu case, always need the time of mmap events etc */
427
		if (!perf_cpu_map__empty(cpus))
428 429 430
			perf_evsel__set_sample_bit(tracking_evsel, TIME);
	}

431 432
out:
	return err;
433 434 435 436 437 438 439 440
}

static u64 cs_etm_get_config(struct auxtrace_record *itr)
{
	u64 config = 0;
	struct cs_etm_recording *ptr =
			container_of(itr, struct cs_etm_recording, itr);
	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
441
	struct evlist *evlist = ptr->evlist;
442
	struct evsel *evsel;
443 444

	evlist__for_each_entry(evlist, evsel) {
445
		if (evsel->core.attr.type == cs_etm_pmu->type) {
446 447 448 449 450 451 452 453
			/*
			 * Variable perf_event_attr::config is assigned to
			 * ETMv3/PTM.  The bit fields have been made to match
			 * the ETMv3.5 ETRMCR register specification.  See the
			 * PMU_FORMAT_ATTR() declarations in
			 * drivers/hwtracing/coresight/coresight-perf.c for
			 * details.
			 */
454
			config = evsel->core.attr.config;
455 456 457 458 459 460 461
			break;
		}
	}

	return config;
}

462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479
#ifndef BIT
#define BIT(N) (1UL << (N))
#endif

static u64 cs_etmv4_get_config(struct auxtrace_record *itr)
{
	u64 config = 0;
	u64 config_opts = 0;

	/*
	 * The perf event variable config bits represent both
	 * the command line options and register programming
	 * bits in ETMv3/PTM. For ETMv4 we must remap options
	 * to real bits
	 */
	config_opts = cs_etm_get_config(itr);
	if (config_opts & BIT(ETM_OPT_CYCACC))
		config |= BIT(ETM4_CFG_BIT_CYCACC);
480 481
	if (config_opts & BIT(ETM_OPT_CTXTID))
		config |= BIT(ETM4_CFG_BIT_CTXTID);
482 483 484 485 486 487 488 489
	if (config_opts & BIT(ETM_OPT_TS))
		config |= BIT(ETM4_CFG_BIT_TS);
	if (config_opts & BIT(ETM_OPT_RETSTK))
		config |= BIT(ETM4_CFG_BIT_RETSTK);

	return config;
}

490 491
static size_t
cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
492
		      struct evlist *evlist __maybe_unused)
493 494 495
{
	int i;
	int etmv3 = 0, etmv4 = 0;
496
	struct perf_cpu_map *event_cpus = evlist->core.cpus;
497
	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
498 499

	/* cpu map is not empty, we have specific CPUs to work with */
500
	if (!perf_cpu_map__empty(event_cpus)) {
501 502 503 504 505 506
		for (i = 0; i < cpu__max_cpu(); i++) {
			if (!cpu_map__has(event_cpus, i) ||
			    !cpu_map__has(online_cpus, i))
				continue;

			if (cs_etm_is_etmv4(itr, i))
507 508 509 510 511 512 513
				etmv4++;
			else
				etmv3++;
		}
	} else {
		/* get configuration for all CPUs in the system */
		for (i = 0; i < cpu__max_cpu(); i++) {
514 515 516
			if (!cpu_map__has(online_cpus, i))
				continue;

517 518 519 520 521 522 523
			if (cs_etm_is_etmv4(itr, i))
				etmv4++;
			else
				etmv3++;
		}
	}

524
	perf_cpu_map__put(online_cpus);
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
	return (CS_ETM_HEADER_SIZE +
	       (etmv4 * CS_ETMV4_PRIV_SIZE) +
	       (etmv3 * CS_ETMV3_PRIV_SIZE));
}

static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu)
{
	bool ret = false;
	char path[PATH_MAX];
	int scan;
	unsigned int val;
	struct cs_etm_recording *ptr =
			container_of(itr, struct cs_etm_recording, itr);
	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;

	/* Take any of the RO files for ETMv4 and see if it present */
	snprintf(path, PATH_MAX, "cpu%d/%s",
		 cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
	scan = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val);

	/* The file was read successfully, we have a winner */
	if (scan == 1)
		ret = true;

	return ret;
}

static int cs_etm_get_ro(struct perf_pmu *pmu, int cpu, const char *path)
{
	char pmu_path[PATH_MAX];
	int scan;
	unsigned int val = 0;

	/* Get RO metadata from sysfs */
	snprintf(pmu_path, PATH_MAX, "cpu%d/%s", cpu, path);

	scan = perf_pmu__scan_file(pmu, pmu_path, "%x", &val);
	if (scan != 1)
		pr_err("%s: error reading: %s\n", __func__, pmu_path);

	return val;
}

static void cs_etm_get_metadata(int cpu, u32 *offset,
				struct auxtrace_record *itr,
571
				struct perf_record_auxtrace_info *info)
572 573 574 575 576 577 578 579 580 581 582 583
{
	u32 increment;
	u64 magic;
	struct cs_etm_recording *ptr =
			container_of(itr, struct cs_etm_recording, itr);
	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;

	/* first see what kind of tracer this cpu is affined to */
	if (cs_etm_is_etmv4(itr, cpu)) {
		magic = __perf_cs_etmv4_magic;
		/* Get trace configuration register */
		info->priv[*offset + CS_ETMV4_TRCCONFIGR] =
584
						cs_etmv4_get_config(itr);
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
		/* Get traceID from the framework */
		info->priv[*offset + CS_ETMV4_TRCTRACEIDR] =
						coresight_get_trace_id(cpu);
		/* Get read-only information from sysFS */
		info->priv[*offset + CS_ETMV4_TRCIDR0] =
			cs_etm_get_ro(cs_etm_pmu, cpu,
				      metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
		info->priv[*offset + CS_ETMV4_TRCIDR1] =
			cs_etm_get_ro(cs_etm_pmu, cpu,
				      metadata_etmv4_ro[CS_ETMV4_TRCIDR1]);
		info->priv[*offset + CS_ETMV4_TRCIDR2] =
			cs_etm_get_ro(cs_etm_pmu, cpu,
				      metadata_etmv4_ro[CS_ETMV4_TRCIDR2]);
		info->priv[*offset + CS_ETMV4_TRCIDR8] =
			cs_etm_get_ro(cs_etm_pmu, cpu,
				      metadata_etmv4_ro[CS_ETMV4_TRCIDR8]);
		info->priv[*offset + CS_ETMV4_TRCAUTHSTATUS] =
			cs_etm_get_ro(cs_etm_pmu, cpu,
				      metadata_etmv4_ro
				      [CS_ETMV4_TRCAUTHSTATUS]);

		/* How much space was used */
		increment = CS_ETMV4_PRIV_MAX;
	} else {
		magic = __perf_cs_etmv3_magic;
		/* Get configuration register */
		info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr);
		/* Get traceID from the framework */
		info->priv[*offset + CS_ETM_ETMTRACEIDR] =
						coresight_get_trace_id(cpu);
		/* Get read-only information from sysFS */
		info->priv[*offset + CS_ETM_ETMCCER] =
			cs_etm_get_ro(cs_etm_pmu, cpu,
				      metadata_etmv3_ro[CS_ETM_ETMCCER]);
		info->priv[*offset + CS_ETM_ETMIDR] =
			cs_etm_get_ro(cs_etm_pmu, cpu,
				      metadata_etmv3_ro[CS_ETM_ETMIDR]);

		/* How much space was used */
		increment = CS_ETM_PRIV_MAX;
	}

	/* Build generic header portion */
	info->priv[*offset + CS_ETM_MAGIC] = magic;
	info->priv[*offset + CS_ETM_CPU] = cpu;
	/* Where the next CPU entry should start from */
	*offset += increment;
}

static int cs_etm_info_fill(struct auxtrace_record *itr,
			    struct perf_session *session,
636
			    struct perf_record_auxtrace_info *info,
637 638 639 640 641
			    size_t priv_size)
{
	int i;
	u32 offset;
	u64 nr_cpu, type;
642
	struct perf_cpu_map *cpu_map;
643
	struct perf_cpu_map *event_cpus = session->evlist->core.cpus;
644
	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
645 646 647 648 649 650 651
	struct cs_etm_recording *ptr =
			container_of(itr, struct cs_etm_recording, itr);
	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;

	if (priv_size != cs_etm_info_priv_size(itr, session->evlist))
		return -EINVAL;

652
	if (!session->evlist->core.nr_mmaps)
653 654
		return -EINVAL;

655
	/* If the cpu_map is empty all online CPUs are involved */
656
	if (perf_cpu_map__empty(event_cpus)) {
657 658 659
		cpu_map = online_cpus;
	} else {
		/* Make sure all specified CPUs are online */
660
		for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) {
661 662 663 664 665 666 667 668
			if (cpu_map__has(event_cpus, i) &&
			    !cpu_map__has(online_cpus, i))
				return -EINVAL;
		}

		cpu_map = event_cpus;
	}

669
	nr_cpu = perf_cpu_map__nr(cpu_map);
670 671 672 673 674 675 676 677 678 679 680 681
	/* Get PMU type as dynamically assigned by the core */
	type = cs_etm_pmu->type;

	/* First fill out the session header */
	info->type = PERF_AUXTRACE_CS_ETM;
	info->priv[CS_HEADER_VERSION_0] = 0;
	info->priv[CS_PMU_TYPE_CPUS] = type << 32;
	info->priv[CS_PMU_TYPE_CPUS] |= nr_cpu;
	info->priv[CS_ETM_SNAPSHOT] = ptr->snapshot_mode;

	offset = CS_ETM_SNAPSHOT + 1;

682 683
	for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++)
		if (cpu_map__has(cpu_map, i))
684
			cs_etm_get_metadata(i, &offset, itr, info);
685

686
	perf_cpu_map__put(online_cpus);
687 688 689 690

	return 0;
}

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
static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx)
{
	bool *wrapped;
	int cnt = ptr->wrapped_cnt;

	/* Make @ptr->wrapped as big as @idx */
	while (cnt <= idx)
		cnt++;

	/*
	 * Free'ed in cs_etm_recording_free().  Using realloc() to avoid
	 * cross compilation problems where the host's system supports
	 * reallocarray() but not the target.
	 */
	wrapped = realloc(ptr->wrapped, cnt * sizeof(bool));
	if (!wrapped)
		return -ENOMEM;

	wrapped[cnt - 1] = false;
	ptr->wrapped_cnt = cnt;
	ptr->wrapped = wrapped;

	return 0;
}

static bool cs_etm_buffer_has_wrapped(unsigned char *buffer,
				      size_t buffer_size, u64 head)
{
	u64 i, watermark;
	u64 *buf = (u64 *)buffer;
	size_t buf_size = buffer_size;

	/*
	 * We want to look the very last 512 byte (chosen arbitrarily) in
	 * the ring buffer.
	 */
	watermark = buf_size - 512;

	/*
	 * @head is continuously increasing - if its value is equal or greater
	 * than the size of the ring buffer, it has wrapped around.
	 */
	if (head >= buffer_size)
		return true;

	/*
	 * The value of @head is somewhere within the size of the ring buffer.
	 * This can be that there hasn't been enough data to fill the ring
	 * buffer yet or the trace time was so long that @head has numerically
	 * wrapped around.  To find we need to check if we have data at the very
	 * end of the ring buffer.  We can reliably do this because mmap'ed
	 * pages are zeroed out and there is a fresh mapping with every new
	 * session.
	 */

	/* @head is less than 512 byte from the end of the ring buffer */
	if (head > watermark)
		watermark = head;

	/*
	 * Speed things up by using 64 bit transactions (see "u64 *buf" above)
	 */
	watermark >>= 3;
	buf_size >>= 3;

	/*
	 * If we find trace data at the end of the ring buffer, @head has
	 * been there and has numerically wrapped around at least once.
	 */
	for (i = watermark; i < buf_size; i++)
		if (buf[i])
			return true;

	return false;
}

static int cs_etm_find_snapshot(struct auxtrace_record *itr,
768
				int idx, struct auxtrace_mmap *mm,
769
				unsigned char *data,
770 771
				u64 *head, u64 *old)
{
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
	int err;
	bool wrapped;
	struct cs_etm_recording *ptr =
			container_of(itr, struct cs_etm_recording, itr);

	/*
	 * Allocate memory to keep track of wrapping if this is the first
	 * time we deal with this *mm.
	 */
	if (idx >= ptr->wrapped_cnt) {
		err = cs_etm_alloc_wrapped_array(ptr, idx);
		if (err)
			return err;
	}

	/*
	 * Check to see if *head has wrapped around.  If it hasn't only the
	 * amount of data between *head and *old is snapshot'ed to avoid
	 * bloating the perf.data file with zeros.  But as soon as *head has
	 * wrapped around the entire size of the AUX ring buffer it taken.
	 */
	wrapped = ptr->wrapped[idx];
	if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) {
		wrapped = true;
		ptr->wrapped[idx] = true;
	}

799 800 801
	pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
		  __func__, idx, (size_t)*old, (size_t)*head, mm->len);

802 803 804 805 806 807 808 809 810 811 812 813 814 815
	/* No wrap has occurred, we can just use *head and *old. */
	if (!wrapped)
		return 0;

	/*
	 * *head has wrapped around - adjust *head and *old to pickup the
	 * entire content of the AUX buffer.
	 */
	if (*head >= mm->len) {
		*old = *head - mm->len;
	} else {
		*head += mm->len;
		*old = *head - mm->len;
	}
816 817 818 819 820 821 822 823

	return 0;
}

static int cs_etm_snapshot_start(struct auxtrace_record *itr)
{
	struct cs_etm_recording *ptr =
			container_of(itr, struct cs_etm_recording, itr);
824
	struct evsel *evsel;
825 826

	evlist__for_each_entry(ptr->evlist, evsel) {
827
		if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
828
			return evsel__disable(evsel);
829 830 831 832 833 834 835 836
	}
	return -EINVAL;
}

static int cs_etm_snapshot_finish(struct auxtrace_record *itr)
{
	struct cs_etm_recording *ptr =
			container_of(itr, struct cs_etm_recording, itr);
837
	struct evsel *evsel;
838 839

	evlist__for_each_entry(ptr->evlist, evsel) {
840
		if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
841
			return evsel__enable(evsel);
842 843 844 845 846 847 848 849 850 851 852 853 854 855
	}
	return -EINVAL;
}

static u64 cs_etm_reference(struct auxtrace_record *itr __maybe_unused)
{
	return (((u64) rand() <<  0) & 0x00000000FFFFFFFFull) |
		(((u64) rand() << 32) & 0xFFFFFFFF00000000ull);
}

static void cs_etm_recording_free(struct auxtrace_record *itr)
{
	struct cs_etm_recording *ptr =
			container_of(itr, struct cs_etm_recording, itr);
856 857

	zfree(&ptr->wrapped);
858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879
	free(ptr);
}

struct auxtrace_record *cs_etm_record_init(int *err)
{
	struct perf_pmu *cs_etm_pmu;
	struct cs_etm_recording *ptr;

	cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);

	if (!cs_etm_pmu) {
		*err = -EINVAL;
		goto out;
	}

	ptr = zalloc(sizeof(struct cs_etm_recording));
	if (!ptr) {
		*err = -ENOMEM;
		goto out;
	}

	ptr->cs_etm_pmu			= cs_etm_pmu;
880
	ptr->itr.pmu			= cs_etm_pmu;
881 882 883 884 885 886 887 888 889
	ptr->itr.parse_snapshot_options	= cs_etm_parse_snapshot_options;
	ptr->itr.recording_options	= cs_etm_recording_options;
	ptr->itr.info_priv_size		= cs_etm_info_priv_size;
	ptr->itr.info_fill		= cs_etm_info_fill;
	ptr->itr.find_snapshot		= cs_etm_find_snapshot;
	ptr->itr.snapshot_start		= cs_etm_snapshot_start;
	ptr->itr.snapshot_finish	= cs_etm_snapshot_finish;
	ptr->itr.reference		= cs_etm_reference;
	ptr->itr.free			= cs_etm_recording_free;
890
	ptr->itr.read_finish		= auxtrace_record__read_finish;
891 892 893 894 895 896

	*err = 0;
	return &ptr->itr;
out:
	return NULL;
}