builtin-kvm.c 22.1 KB
Newer Older
1 2 3
#include "builtin.h"
#include "perf.h"

X
Xiao Guangrong 已提交
4
#include "util/evsel.h"
5 6 7 8 9 10 11 12 13 14
#include "util/util.h"
#include "util/cache.h"
#include "util/symbol.h"
#include "util/thread.h"
#include "util/header.h"
#include "util/session.h"

#include "util/parse-options.h"
#include "util/trace-event.h"
#include "util/debug.h"
X
Xiao Guangrong 已提交
15 16 17
#include "util/debugfs.h"
#include "util/tool.h"
#include "util/stat.h"
18 19 20 21 22 23 24

#include <sys/prctl.h>

#include <semaphore.h>
#include <pthread.h>
#include <math.h>

X
Xiao Guangrong 已提交
25 26 27 28 29 30 31 32 33 34 35
#include "../../arch/x86/include/asm/svm.h"
#include "../../arch/x86/include/asm/vmx.h"
#include "../../arch/x86/include/asm/kvm.h"

struct event_key {
	#define INVALID_KEY     (~0ULL)
	u64 key;
	int info;
};

struct kvm_events_ops {
36 37 38 39 40
	bool (*is_begin_event)(struct perf_evsel *evsel,
			       struct perf_sample *sample,
			       struct event_key *key);
	bool (*is_end_event)(struct perf_evsel *evsel,
			     struct perf_sample *sample, struct event_key *key);
X
Xiao Guangrong 已提交
41 42 43 44
	void (*decode_key)(struct event_key *key, char decode[20]);
	const char *name;
};

45 46 47
static void exit_event_get_key(struct perf_evsel *evsel,
			       struct perf_sample *sample,
			       struct event_key *key)
X
Xiao Guangrong 已提交
48 49
{
	key->info = 0;
50
	key->key = perf_evsel__intval(evsel, sample, "exit_reason");
X
Xiao Guangrong 已提交
51 52
}

53
static bool kvm_exit_event(struct perf_evsel *evsel)
X
Xiao Guangrong 已提交
54
{
55
	return !strcmp(evsel->name, "kvm:kvm_exit");
X
Xiao Guangrong 已提交
56 57
}

58 59
static bool exit_event_begin(struct perf_evsel *evsel,
			     struct perf_sample *sample, struct event_key *key)
X
Xiao Guangrong 已提交
60
{
61 62
	if (kvm_exit_event(evsel)) {
		exit_event_get_key(evsel, sample, key);
X
Xiao Guangrong 已提交
63 64 65 66 67 68
		return true;
	}

	return false;
}

69
static bool kvm_entry_event(struct perf_evsel *evsel)
X
Xiao Guangrong 已提交
70
{
71
	return !strcmp(evsel->name, "kvm:kvm_entry");
X
Xiao Guangrong 已提交
72 73
}

74 75 76
static bool exit_event_end(struct perf_evsel *evsel,
			   struct perf_sample *sample __maybe_unused,
			   struct event_key *key __maybe_unused)
X
Xiao Guangrong 已提交
77
{
78
	return kvm_entry_event(evsel);
X
Xiao Guangrong 已提交
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
}

struct exit_reasons_table {
	unsigned long exit_code;
	const char *reason;
};

struct exit_reasons_table vmx_exit_reasons[] = {
	VMX_EXIT_REASONS
};

struct exit_reasons_table svm_exit_reasons[] = {
	SVM_EXIT_REASONS
};

static int cpu_isa;

static const char *get_exit_reason(u64 exit_code)
{
	int table_size = ARRAY_SIZE(svm_exit_reasons);
	struct exit_reasons_table *table = svm_exit_reasons;

	if (cpu_isa == 1) {
		table = vmx_exit_reasons;
		table_size = ARRAY_SIZE(vmx_exit_reasons);
	}

	while (table_size--) {
		if (table->exit_code == exit_code)
			return table->reason;
		table++;
	}

	pr_err("unknown kvm exit code:%lld on %s\n",
		(unsigned long long)exit_code, cpu_isa ? "VMX" : "SVM");
	return "UNKNOWN";
}

static void exit_event_decode_key(struct event_key *key, char decode[20])
{
	const char *exit_reason = get_exit_reason(key->key);

	scnprintf(decode, 20, "%s", exit_reason);
}

static struct kvm_events_ops exit_events = {
	.is_begin_event = exit_event_begin,
	.is_end_event = exit_event_end,
	.decode_key = exit_event_decode_key,
	.name = "VM-EXIT"
};

    /*
     * For the mmio events, we treat:
     * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
     * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
     */
136 137
static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
			       struct event_key *key)
X
Xiao Guangrong 已提交
138
{
139 140
	key->key  = perf_evsel__intval(evsel, sample, "gpa");
	key->info = perf_evsel__intval(evsel, sample, "type");
X
Xiao Guangrong 已提交
141 142 143 144 145 146
}

#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
#define KVM_TRACE_MMIO_READ 1
#define KVM_TRACE_MMIO_WRITE 2

147 148
static bool mmio_event_begin(struct perf_evsel *evsel,
			     struct perf_sample *sample, struct event_key *key)
X
Xiao Guangrong 已提交
149 150
{
	/* MMIO read begin event in kernel. */
151
	if (kvm_exit_event(evsel))
X
Xiao Guangrong 已提交
152 153 154
		return true;

	/* MMIO write begin event in kernel. */
155 156 157
	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
		mmio_event_get_key(evsel, sample, key);
X
Xiao Guangrong 已提交
158 159 160 161 162 163
		return true;
	}

	return false;
}

164 165
static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
			   struct event_key *key)
X
Xiao Guangrong 已提交
166 167
{
	/* MMIO write end event in kernel. */
168
	if (kvm_entry_event(evsel))
X
Xiao Guangrong 已提交
169 170 171
		return true;

	/* MMIO read end event in kernel.*/
172 173 174
	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
		mmio_event_get_key(evsel, sample, key);
X
Xiao Guangrong 已提交
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194
		return true;
	}

	return false;
}

static void mmio_event_decode_key(struct event_key *key, char decode[20])
{
	scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key,
				key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
}

static struct kvm_events_ops mmio_events = {
	.is_begin_event = mmio_event_begin,
	.is_end_event = mmio_event_end,
	.decode_key = mmio_event_decode_key,
	.name = "MMIO Access"
};

 /* The time of emulation pio access is from kvm_pio to kvm_entry. */
195 196 197
static void ioport_event_get_key(struct perf_evsel *evsel,
				 struct perf_sample *sample,
				 struct event_key *key)
X
Xiao Guangrong 已提交
198
{
199 200
	key->key  = perf_evsel__intval(evsel, sample, "port");
	key->info = perf_evsel__intval(evsel, sample, "rw");
X
Xiao Guangrong 已提交
201 202
}

203 204 205
static bool ioport_event_begin(struct perf_evsel *evsel,
			       struct perf_sample *sample,
			       struct event_key *key)
X
Xiao Guangrong 已提交
206
{
207 208
	if (!strcmp(evsel->name, "kvm:kvm_pio")) {
		ioport_event_get_key(evsel, sample, key);
X
Xiao Guangrong 已提交
209 210 211 212 213 214
		return true;
	}

	return false;
}

215 216
static bool ioport_event_end(struct perf_evsel *evsel,
			     struct perf_sample *sample __maybe_unused,
X
Xiao Guangrong 已提交
217 218
			     struct event_key *key __maybe_unused)
{
219
	return kvm_entry_event(evsel);
X
Xiao Guangrong 已提交
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
}

static void ioport_event_decode_key(struct event_key *key, char decode[20])
{
	scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key,
				key->info ? "POUT" : "PIN");
}

static struct kvm_events_ops ioport_events = {
	.is_begin_event = ioport_event_begin,
	.is_end_event = ioport_event_end,
	.decode_key = ioport_event_decode_key,
	.name = "IO Port Access"
};

static const char *report_event = "vmexit";
struct kvm_events_ops *events_ops;

static bool register_kvm_events_ops(void)
{
	bool ret = true;

	if (!strcmp(report_event, "vmexit"))
		events_ops = &exit_events;
	else if (!strcmp(report_event, "mmio"))
		events_ops = &mmio_events;
	else if (!strcmp(report_event, "ioport"))
		events_ops = &ioport_events;
	else {
		pr_err("Unknown report event:%s\n", report_event);
		ret = false;
	}

	return ret;
}

struct kvm_event_stats {
	u64 time;
	struct stats stats;
};

struct kvm_event {
	struct list_head hash_entry;
	struct rb_node rb;

	struct event_key key;

	struct kvm_event_stats total;

	#define DEFAULT_VCPU_NUM 8
	int max_vcpu;
	struct kvm_event_stats *vcpu;
};

struct vcpu_event_record {
	int vcpu_id;
	u64 start_time;
	struct kvm_event *last_event;
};

#define EVENTS_BITS			12
#define EVENTS_CACHE_SIZE	(1UL << EVENTS_BITS)

static u64 total_time;
static u64 total_count;
static struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];

static void init_kvm_event_record(void)
{
	int i;

	for (i = 0; i < (int)EVENTS_CACHE_SIZE; i++)
		INIT_LIST_HEAD(&kvm_events_cache[i]);
}

static int kvm_events_hash_fn(u64 key)
{
	return key & (EVENTS_CACHE_SIZE - 1);
}

static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
{
	int old_max_vcpu = event->max_vcpu;

	if (vcpu_id < event->max_vcpu)
		return true;

	while (event->max_vcpu <= vcpu_id)
		event->max_vcpu += DEFAULT_VCPU_NUM;

	event->vcpu = realloc(event->vcpu,
			      event->max_vcpu * sizeof(*event->vcpu));
	if (!event->vcpu) {
		pr_err("Not enough memory\n");
		return false;
	}

	memset(event->vcpu + old_max_vcpu, 0,
	       (event->max_vcpu - old_max_vcpu) * sizeof(*event->vcpu));
	return true;
}

static struct kvm_event *kvm_alloc_init_event(struct event_key *key)
{
	struct kvm_event *event;

	event = zalloc(sizeof(*event));
	if (!event) {
		pr_err("Not enough memory\n");
		return NULL;
	}

	event->key = *key;
	return event;
}

static struct kvm_event *find_create_kvm_event(struct event_key *key)
{
	struct kvm_event *event;
	struct list_head *head;

	BUG_ON(key->key == INVALID_KEY);

	head = &kvm_events_cache[kvm_events_hash_fn(key->key)];
	list_for_each_entry(event, head, hash_entry)
		if (event->key.key == key->key && event->key.info == key->info)
			return event;

	event = kvm_alloc_init_event(key);
	if (!event)
		return NULL;

	list_add(&event->hash_entry, head);
	return event;
}

static bool handle_begin_event(struct vcpu_event_record *vcpu_record,
			       struct event_key *key, u64 timestamp)
{
	struct kvm_event *event = NULL;

	if (key->key != INVALID_KEY)
		event = find_create_kvm_event(key);

	vcpu_record->last_event = event;
	vcpu_record->start_time = timestamp;
	return true;
}

static void
kvm_update_event_stats(struct kvm_event_stats *kvm_stats, u64 time_diff)
{
	kvm_stats->time += time_diff;
	update_stats(&kvm_stats->stats, time_diff);
}

static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event)
{
	struct kvm_event_stats *kvm_stats = &event->total;

	if (vcpu_id != -1)
		kvm_stats = &event->vcpu[vcpu_id];

	return rel_stddev_stats(stddev_stats(&kvm_stats->stats),
				avg_stats(&kvm_stats->stats));
}

static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
			     u64 time_diff)
{
	kvm_update_event_stats(&event->total, time_diff);

	if (!kvm_event_expand(event, vcpu_id))
		return false;

	kvm_update_event_stats(&event->vcpu[vcpu_id], time_diff);
	return true;
}

static bool handle_end_event(struct vcpu_event_record *vcpu_record,
			     struct event_key *key, u64 timestamp)
{
	struct kvm_event *event;
	u64 time_begin, time_diff;

	event = vcpu_record->last_event;
	time_begin = vcpu_record->start_time;

	/* The begin event is not caught. */
	if (!time_begin)
		return true;

	/*
	 * In some case, the 'begin event' only records the start timestamp,
	 * the actual event is recognized in the 'end event' (e.g. mmio-event).
	 */

	/* Both begin and end events did not get the key. */
	if (!event && key->key == INVALID_KEY)
		return true;

	if (!event)
		event = find_create_kvm_event(key);

	if (!event)
		return false;

	vcpu_record->last_event = NULL;
	vcpu_record->start_time = 0;

	BUG_ON(timestamp < time_begin);

	time_diff = timestamp - time_begin;
	return update_kvm_event(event, vcpu_record->vcpu_id, time_diff);
}

436 437 438 439
static
struct vcpu_event_record *per_vcpu_record(struct thread *thread,
					  struct perf_evsel *evsel,
					  struct perf_sample *sample)
X
Xiao Guangrong 已提交
440 441
{
	/* Only kvm_entry records vcpu id. */
442
	if (!thread->priv && kvm_entry_event(evsel)) {
X
Xiao Guangrong 已提交
443 444
		struct vcpu_event_record *vcpu_record;

445
		vcpu_record = zalloc(sizeof(*vcpu_record));
X
Xiao Guangrong 已提交
446
		if (!vcpu_record) {
447
			pr_err("%s: Not enough memory\n", __func__);
X
Xiao Guangrong 已提交
448 449 450
			return NULL;
		}

451
		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id");
X
Xiao Guangrong 已提交
452 453 454
		thread->priv = vcpu_record;
	}

455
	return thread->priv;
X
Xiao Guangrong 已提交
456 457
}

458 459
static bool handle_kvm_event(struct thread *thread, struct perf_evsel *evsel,
			     struct perf_sample *sample)
X
Xiao Guangrong 已提交
460 461 462 463
{
	struct vcpu_event_record *vcpu_record;
	struct event_key key = {.key = INVALID_KEY};

464
	vcpu_record = per_vcpu_record(thread, evsel, sample);
X
Xiao Guangrong 已提交
465 466 467
	if (!vcpu_record)
		return true;

468 469
	if (events_ops->is_begin_event(evsel, sample, &key))
		return handle_begin_event(vcpu_record, &key, sample->time);
X
Xiao Guangrong 已提交
470

471 472
	if (events_ops->is_end_event(evsel, sample, &key))
		return handle_end_event(vcpu_record, &key, sample->time);
X
Xiao Guangrong 已提交
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

	return true;
}

typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
struct kvm_event_key {
	const char *name;
	key_cmp_fun key;
};

static int trace_vcpu = -1;
#define GET_EVENT_KEY(func, field)					\
static u64 get_event_ ##func(struct kvm_event *event, int vcpu)		\
{									\
	if (vcpu == -1)							\
		return event->total.field;				\
									\
	if (vcpu >= event->max_vcpu)					\
		return 0;						\
									\
	return event->vcpu[vcpu].field;					\
}

#define COMPARE_EVENT_KEY(func, field)					\
GET_EVENT_KEY(func, field)						\
static int compare_kvm_event_ ## func(struct kvm_event *one,		\
					struct kvm_event *two, int vcpu)\
{									\
	return get_event_ ##func(one, vcpu) >				\
				get_event_ ##func(two, vcpu);		\
}

GET_EVENT_KEY(time, time);
COMPARE_EVENT_KEY(count, stats.n);
COMPARE_EVENT_KEY(mean, stats.mean);

#define DEF_SORT_NAME_KEY(name, compare_key)				\
	{ #name, compare_kvm_event_ ## compare_key }

static struct kvm_event_key keys[] = {
	DEF_SORT_NAME_KEY(sample, count),
	DEF_SORT_NAME_KEY(time, mean),
	{ NULL, NULL }
};

static const char *sort_key = "sample";
static key_cmp_fun compare;

static bool select_key(void)
{
	int i;

	for (i = 0; keys[i].name; i++) {
		if (!strcmp(keys[i].name, sort_key)) {
			compare = keys[i].key;
			return true;
		}
	}

	pr_err("Unknown compare key:%s\n", sort_key);
	return false;
}

static struct rb_root result;
static void insert_to_result(struct kvm_event *event, key_cmp_fun bigger,
			     int vcpu)
{
	struct rb_node **rb = &result.rb_node;
	struct rb_node *parent = NULL;
	struct kvm_event *p;

	while (*rb) {
		p = container_of(*rb, struct kvm_event, rb);
		parent = *rb;

		if (bigger(event, p, vcpu))
			rb = &(*rb)->rb_left;
		else
			rb = &(*rb)->rb_right;
	}

	rb_link_node(&event->rb, parent, rb);
	rb_insert_color(&event->rb, &result);
}

static void update_total_count(struct kvm_event *event, int vcpu)
{
	total_count += get_event_count(event, vcpu);
	total_time += get_event_time(event, vcpu);
}

static bool event_is_valid(struct kvm_event *event, int vcpu)
{
	return !!get_event_count(event, vcpu);
}

static void sort_result(int vcpu)
{
	unsigned int i;
	struct kvm_event *event;

	for (i = 0; i < EVENTS_CACHE_SIZE; i++)
		list_for_each_entry(event, &kvm_events_cache[i], hash_entry)
			if (event_is_valid(event, vcpu)) {
				update_total_count(event, vcpu);
				insert_to_result(event, compare, vcpu);
			}
}

/* returns left most element of result, and erase it */
static struct kvm_event *pop_from_result(void)
{
	struct rb_node *node = rb_first(&result);

	if (!node)
		return NULL;

	rb_erase(node, &result);
	return container_of(node, struct kvm_event, rb);
}

static void print_vcpu_info(int vcpu)
{
	pr_info("Analyze events for ");

	if (vcpu == -1)
		pr_info("all VCPUs:\n\n");
	else
		pr_info("VCPU %d:\n\n", vcpu);
}

static void print_result(int vcpu)
{
	char decode[20];
	struct kvm_event *event;

	pr_info("\n\n");
	print_vcpu_info(vcpu);
	pr_info("%20s ", events_ops->name);
	pr_info("%10s ", "Samples");
	pr_info("%9s ", "Samples%");

	pr_info("%9s ", "Time%");
	pr_info("%16s ", "Avg time");
	pr_info("\n\n");

	while ((event = pop_from_result())) {
		u64 ecount, etime;

		ecount = get_event_count(event, vcpu);
		etime = get_event_time(event, vcpu);

		events_ops->decode_key(&event->key, decode);
		pr_info("%20s ", decode);
		pr_info("%10llu ", (unsigned long long)ecount);
		pr_info("%8.2f%% ", (double)ecount / total_count * 100);
		pr_info("%8.2f%% ", (double)etime / total_time * 100);
		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
			kvm_event_rel_stddev(vcpu, event));
		pr_info("\n");
	}

	pr_info("\nTotal Samples:%lld, Total events handled time:%.2fus.\n\n",
		(unsigned long long)total_count, total_time / 1e3);
}

static int process_sample_event(struct perf_tool *tool __maybe_unused,
				union perf_event *event,
				struct perf_sample *sample,
				struct perf_evsel *evsel,
				struct machine *machine)
{
	struct thread *thread = machine__findnew_thread(machine, sample->tid);

	if (thread == NULL) {
		pr_debug("problem processing %d event, skipping it.\n",
			event->header.type);
		return -1;
	}

653
	if (!handle_kvm_event(thread, evsel, sample))
X
Xiao Guangrong 已提交
654 655 656 657 658 659 660 661 662 663 664 665 666
		return -1;

	return 0;
}

static struct perf_tool eops = {
	.sample			= process_sample_event,
	.comm			= perf_event__process_comm,
	.ordered_samples	= true,
};

static int get_cpu_isa(struct perf_session *session)
{
667
	char *cpuid = session->header.env.cpuid;
X
Xiao Guangrong 已提交
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
	int isa;

	if (strstr(cpuid, "Intel"))
		isa = 1;
	else if (strstr(cpuid, "AMD"))
		isa = 0;
	else {
		pr_err("CPU %s is not supported.\n", cpuid);
		isa = -ENOTSUP;
	}

	return isa;
}

static const char *file_name;

static int read_events(void)
{
	struct perf_session *kvm_session;
	int ret;

	kvm_session = perf_session__new(file_name, O_RDONLY, 0, false, &eops);
	if (!kvm_session) {
		pr_err("Initializing perf session failed\n");
		return -EINVAL;
	}

	if (!perf_session__has_traces(kvm_session, "kvm record"))
		return -EINVAL;

	/*
	 * Do not use 'isa' recorded in kvm_exit tracepoint since it is not
	 * traced in the old kernel.
	 */
	ret = get_cpu_isa(kvm_session);

	if (ret < 0)
		return ret;

	cpu_isa = ret;

	return perf_session__process_events(kvm_session, &eops);
}

static bool verify_vcpu(int vcpu)
{
	if (vcpu != -1 && vcpu < 0) {
		pr_err("Invalid vcpu:%d.\n", vcpu);
		return false;
	}

	return true;
}

static int kvm_events_report_vcpu(int vcpu)
{
	int ret = -EINVAL;

	if (!verify_vcpu(vcpu))
		goto exit;

	if (!select_key())
		goto exit;

	if (!register_kvm_events_ops())
		goto exit;

	init_kvm_event_record();
	setup_pager();

	ret = read_events();
	if (ret)
		goto exit;

	sort_result(vcpu);
	print_result(vcpu);
exit:
	return ret;
}

static const char * const record_args[] = {
	"record",
	"-R",
	"-f",
	"-m", "1024",
	"-c", "1",
	"-e", "kvm:kvm_entry",
	"-e", "kvm:kvm_exit",
	"-e", "kvm:kvm_mmio",
	"-e", "kvm:kvm_pio",
};

#define STRDUP_FAIL_EXIT(s)		\
	({	char *_p;		\
	_p = strdup(s);		\
		if (!_p)		\
			return -ENOMEM;	\
		_p;			\
	})

static int kvm_events_record(int argc, const char **argv)
{
	unsigned int rec_argc, i, j;
	const char **rec_argv;

	rec_argc = ARRAY_SIZE(record_args) + argc + 2;
	rec_argv = calloc(rec_argc + 1, sizeof(char *));

	if (rec_argv == NULL)
		return -ENOMEM;

	for (i = 0; i < ARRAY_SIZE(record_args); i++)
		rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]);

	rec_argv[i++] = STRDUP_FAIL_EXIT("-o");
	rec_argv[i++] = STRDUP_FAIL_EXIT(file_name);

	for (j = 1; j < (unsigned int)argc; j++, i++)
		rec_argv[i] = argv[j];

	return cmd_record(i, rec_argv, NULL);
}

static const char * const kvm_events_report_usage[] = {
	"perf kvm stat report [<options>]",
	NULL
};

static const struct option kvm_events_report_options[] = {
	OPT_STRING(0, "event", &report_event, "report event",
		    "event for reporting: vmexit, mmio, ioport"),
	OPT_INTEGER(0, "vcpu", &trace_vcpu,
		    "vcpu id to report"),
	OPT_STRING('k', "key", &sort_key, "sort-key",
		    "key for sorting: sample(sort by samples number)"
		    " time (sort by avg time)"),
	OPT_END()
};

static int kvm_events_report(int argc, const char **argv)
{
	symbol__init();

	if (argc) {
		argc = parse_options(argc, argv,
				     kvm_events_report_options,
				     kvm_events_report_usage, 0);
		if (argc)
			usage_with_options(kvm_events_report_usage,
					   kvm_events_report_options);
	}

	return kvm_events_report_vcpu(trace_vcpu);
}

static void print_kvm_stat_usage(void)
{
	printf("Usage: perf kvm stat <command>\n\n");

	printf("# Available commands:\n");
	printf("\trecord: record kvm events\n");
	printf("\treport: report statistical data of kvm events\n");

	printf("\nOtherwise, it is the alias of 'perf stat':\n");
}

static int kvm_cmd_stat(int argc, const char **argv)
{
	if (argc == 1) {
		print_kvm_stat_usage();
		goto perf_stat;
	}

	if (!strncmp(argv[1], "rec", 3))
		return kvm_events_record(argc - 1, argv + 1);

	if (!strncmp(argv[1], "rep", 3))
		return kvm_events_report(argc - 1 , argv + 1);

perf_stat:
	return cmd_stat(argc, argv, NULL);
}

851 852 853
static char			name_buffer[256];

static const char * const kvm_usage[] = {
X
Xiao Guangrong 已提交
854
	"perf kvm [<options>] {top|record|report|diff|buildid-list|stat}",
855 856 857 858 859 860 861 862 863 864 865
	NULL
};

static const struct option kvm_options[] = {
	OPT_STRING('i', "input", &file_name, "file",
		   "Input file name"),
	OPT_STRING('o', "output", &file_name, "file",
		   "Output file name"),
	OPT_BOOLEAN(0, "guest", &perf_guest,
		    "Collect guest os data"),
	OPT_BOOLEAN(0, "host", &perf_host,
866
		    "Collect host os data"),
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
	OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
		   "guest mount directory under which every guest os"
		   " instance has a subdir"),
	OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name,
		   "file", "file saving guest os vmlinux"),
	OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms,
		   "file", "file saving guest os /proc/kallsyms"),
	OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
		   "file", "file saving guest os /proc/modules"),
	OPT_END()
};

static int __cmd_record(int argc, const char **argv)
{
	int rec_argc, i = 0, j;
	const char **rec_argv;

	rec_argc = argc + 2;
	rec_argv = calloc(rec_argc + 1, sizeof(char *));
	rec_argv[i++] = strdup("record");
	rec_argv[i++] = strdup("-o");
	rec_argv[i++] = strdup(file_name);
	for (j = 1; j < argc; j++, i++)
		rec_argv[i] = argv[j];

	BUG_ON(i != rec_argc);

	return cmd_record(i, rec_argv, NULL);
}

static int __cmd_report(int argc, const char **argv)
{
	int rec_argc, i = 0, j;
	const char **rec_argv;

	rec_argc = argc + 2;
	rec_argv = calloc(rec_argc + 1, sizeof(char *));
	rec_argv[i++] = strdup("report");
	rec_argv[i++] = strdup("-i");
	rec_argv[i++] = strdup(file_name);
	for (j = 1; j < argc; j++, i++)
		rec_argv[i] = argv[j];

	BUG_ON(i != rec_argc);

	return cmd_report(i, rec_argv, NULL);
}

static int __cmd_buildid_list(int argc, const char **argv)
{
	int rec_argc, i = 0, j;
	const char **rec_argv;

	rec_argc = argc + 2;
	rec_argv = calloc(rec_argc + 1, sizeof(char *));
	rec_argv[i++] = strdup("buildid-list");
	rec_argv[i++] = strdup("-i");
	rec_argv[i++] = strdup(file_name);
	for (j = 1; j < argc; j++, i++)
		rec_argv[i] = argv[j];

	BUG_ON(i != rec_argc);

	return cmd_buildid_list(i, rec_argv, NULL);
}

933
int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
934
{
935 936
	perf_host  = 0;
	perf_guest = 1;
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

	argc = parse_options(argc, argv, kvm_options, kvm_usage,
			PARSE_OPT_STOP_AT_NON_OPTION);
	if (!argc)
		usage_with_options(kvm_usage, kvm_options);

	if (!perf_host)
		perf_guest = 1;

	if (!file_name) {
		if (perf_host && !perf_guest)
			sprintf(name_buffer, "perf.data.host");
		else if (!perf_host && perf_guest)
			sprintf(name_buffer, "perf.data.guest");
		else
			sprintf(name_buffer, "perf.data.kvm");
		file_name = name_buffer;
	}

	if (!strncmp(argv[0], "rec", 3))
		return __cmd_record(argc, argv);
	else if (!strncmp(argv[0], "rep", 3))
		return __cmd_report(argc, argv);
	else if (!strncmp(argv[0], "diff", 4))
		return cmd_diff(argc, argv, NULL);
	else if (!strncmp(argv[0], "top", 3))
		return cmd_top(argc, argv, NULL);
	else if (!strncmp(argv[0], "buildid-list", 12))
		return __cmd_buildid_list(argc, argv);
X
Xiao Guangrong 已提交
966 967
	else if (!strncmp(argv[0], "stat", 4))
		return kvm_cmd_stat(argc, argv);
968 969 970 971 972
	else
		usage_with_options(kvm_usage, kvm_options);

	return 0;
}