builtin-kvm.c

#include "builtin.h"
#include "perf.h"

#include "util/evsel.h"
#include "util/evlist.h"
#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/intlist.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
#include "util/debug.h"
#include <lk/debugfs.h>
#include "util/tool.h"
#include "util/stat.h"
#include "util/top.h"
#include "util/data.h"

#include <sys/prctl.h>
#ifdef HAVE_TIMERFD_SUPPORT
#include <sys/timerfd.h>
#endif

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

#if defined(__i386__) || defined(__x86_64__)
#include <asm/svm.h>
#include <asm/vmx.h>
#include <asm/kvm.h>

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

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;
};

typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);

struct kvm_event_key {
	const char *name;
	key_cmp_fun key;
};


struct perf_kvm_stat;

struct kvm_events_ops {
	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);
	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
			   char decode[20]);
	const char *name;
};

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

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

struct perf_kvm_stat {
	struct perf_tool    tool;
	struct perf_record_opts opts;
	struct perf_evlist  *evlist;
	struct perf_session *session;

	const char *file_name;
	const char *report_event;
	const char *sort_key;
	int trace_vcpu;

	struct exit_reasons_table *exit_reasons;
	int exit_reasons_size;
	const char *exit_reasons_isa;

	struct kvm_events_ops *events_ops;
	key_cmp_fun compare;
	struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];

	u64 total_time;
	u64 total_count;
	u64 lost_events;
	u64 duration;

	const char *pid_str;
	struct intlist *pid_list;

	struct rb_root result;

	int timerfd;
	unsigned int display_time;
	bool live;
};


static void exit_event_get_key(struct perf_evsel *evsel,
			       struct perf_sample *sample,
			       struct event_key *key)
{
	key->info = 0;
	key->key = perf_evsel__intval(evsel, sample, "exit_reason");
}

static bool kvm_exit_event(struct perf_evsel *evsel)
{
	return !strcmp(evsel->name, "kvm:kvm_exit");
}

static bool exit_event_begin(struct perf_evsel *evsel,
			     struct perf_sample *sample, struct event_key *key)
{
	if (kvm_exit_event(evsel)) {
		exit_event_get_key(evsel, sample, key);
		return true;
	}

	return false;
}

static bool kvm_entry_event(struct perf_evsel *evsel)
{
	return !strcmp(evsel->name, "kvm:kvm_entry");
}

static bool exit_event_end(struct perf_evsel *evsel,
			   struct perf_sample *sample __maybe_unused,
			   struct event_key *key __maybe_unused)
{
	return kvm_entry_event(evsel);
}

static struct exit_reasons_table vmx_exit_reasons[] = {
	VMX_EXIT_REASONS
};

static struct exit_reasons_table svm_exit_reasons[] = {
	SVM_EXIT_REASONS
};

static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
{
	int i = kvm->exit_reasons_size;
	struct exit_reasons_table *tbl = kvm->exit_reasons;

	while (i--) {
		if (tbl->exit_code == exit_code)
			return tbl->reason;
		tbl++;
	}

	pr_err("unknown kvm exit code:%lld on %s\n",
		(unsigned long long)exit_code, kvm->exit_reasons_isa);
	return "UNKNOWN";
}

static void exit_event_decode_key(struct perf_kvm_stat *kvm,
				  struct event_key *key,
				  char decode[20])
{
	const char *exit_reason = get_exit_reason(kvm, 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...).
 */
static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
			       struct event_key *key)
{
	key->key  = perf_evsel__intval(evsel, sample, "gpa");
	key->info = perf_evsel__intval(evsel, sample, "type");
}

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

static bool mmio_event_begin(struct perf_evsel *evsel,
			     struct perf_sample *sample, struct event_key *key)
{
	/* MMIO read begin event in kernel. */
	if (kvm_exit_event(evsel))
		return true;

	/* MMIO write begin event in kernel. */
	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
		mmio_event_get_key(evsel, sample, key);
		return true;
	}

	return false;
}

static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
			   struct event_key *key)
{
	/* MMIO write end event in kernel. */
	if (kvm_entry_event(evsel))
		return true;

	/* MMIO read end event in kernel.*/
	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
		mmio_event_get_key(evsel, sample, key);
		return true;
	}

	return false;
}

static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
				  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. */
static void ioport_event_get_key(struct perf_evsel *evsel,
				 struct perf_sample *sample,
				 struct event_key *key)
{
	key->key  = perf_evsel__intval(evsel, sample, "port");
	key->info = perf_evsel__intval(evsel, sample, "rw");
}

static bool ioport_event_begin(struct perf_evsel *evsel,
			       struct perf_sample *sample,
			       struct event_key *key)
{
	if (!strcmp(evsel->name, "kvm:kvm_pio")) {
		ioport_event_get_key(evsel, sample, key);
		return true;
	}

	return false;
}

static bool ioport_event_end(struct perf_evsel *evsel,
			     struct perf_sample *sample __maybe_unused,
			     struct event_key *key __maybe_unused)
{
	return kvm_entry_event(evsel);
}

static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
				    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 bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
{
	bool ret = true;

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

	return ret;
}

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


static void init_kvm_event_record(struct perf_kvm_stat *kvm)
{
	unsigned int i;

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

#ifdef HAVE_TIMERFD_SUPPORT
static void clear_events_cache_stats(struct list_head *kvm_events_cache)
{
	struct list_head *head;
	struct kvm_event *event;
	unsigned int i;
	int j;

	for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
		head = &kvm_events_cache[i];
		list_for_each_entry(event, head, hash_entry) {
			/* reset stats for event */
			event->total.time = 0;
			init_stats(&event->total.stats);

			for (j = 0; j < event->max_vcpu; ++j) {
				event->vcpu[j].time = 0;
				init_stats(&event->vcpu[j].stats);
			}
		}
	}
}
#endif

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;
	void *prev;

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

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

	prev = event->vcpu;
	event->vcpu = realloc(event->vcpu,
			      event->max_vcpu * sizeof(*event->vcpu));
	if (!event->vcpu) {
		free(prev);
		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 perf_kvm_stat *kvm,
					       struct event_key *key)
{
	struct kvm_event *event;
	struct list_head *head;

	BUG_ON(key->key == INVALID_KEY);

	head = &kvm->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 perf_kvm_stat *kvm,
			       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(kvm, 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)
{
	if (vcpu_id == -1) {
		kvm_update_event_stats(&event->total, time_diff);
		return true;
	}

	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 perf_kvm_stat *kvm,
			     struct vcpu_event_record *vcpu_record,
			     struct event_key *key,
			     struct perf_sample *sample)
{
	struct kvm_event *event;
	u64 time_begin, time_diff;
	int vcpu;

	if (kvm->trace_vcpu == -1)
		vcpu = -1;
	else
		vcpu = vcpu_record->vcpu_id;

	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(kvm, key);

	if (!event)
		return false;

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

	/* seems to happen once in a while during live mode */
	if (sample->time < time_begin) {
		pr_debug("End time before begin time; skipping event.\n");
		return true;
	}

	time_diff = sample->time - time_begin;

	if (kvm->duration && time_diff > kvm->duration) {
		char decode[32];

		kvm->events_ops->decode_key(kvm, &event->key, decode);
		if (strcmp(decode, "HLT")) {
			pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n",
				 sample->time, sample->pid, vcpu_record->vcpu_id,
				 decode, time_diff/1000);
		}
	}

	return update_kvm_event(event, vcpu, time_diff);
}

static
struct vcpu_event_record *per_vcpu_record(struct thread *thread,
					  struct perf_evsel *evsel,
					  struct perf_sample *sample)
{
	/* Only kvm_entry records vcpu id. */
	if (!thread->priv && kvm_entry_event(evsel)) {
		struct vcpu_event_record *vcpu_record;

		vcpu_record = zalloc(sizeof(*vcpu_record));
		if (!vcpu_record) {
			pr_err("%s: Not enough memory\n", __func__);
			return NULL;
		}

		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id");
		thread->priv = vcpu_record;
	}

	return thread->priv;
}

static bool handle_kvm_event(struct perf_kvm_stat *kvm,
			     struct thread *thread,
			     struct perf_evsel *evsel,
			     struct perf_sample *sample)
{
	struct vcpu_event_record *vcpu_record;
	struct event_key key = {.key = INVALID_KEY};

	vcpu_record = per_vcpu_record(thread, evsel, sample);
	if (!vcpu_record)
		return true;

	/* only process events for vcpus user cares about */
	if ((kvm->trace_vcpu != -1) &&
	    (kvm->trace_vcpu != vcpu_record->vcpu_id))
		return true;

	if (kvm->events_ops->is_begin_event(evsel, sample, &key))
		return handle_begin_event(kvm, vcpu_record, &key, sample->time);

	if (kvm->events_ops->is_end_event(evsel, sample, &key))
		return handle_end_event(kvm, vcpu_record, &key, sample);

	return true;
}

#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);
GET_EVENT_KEY(max, stats.max);
GET_EVENT_KEY(min, stats.min);

#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 bool select_key(struct perf_kvm_stat *kvm)
{
	int i;

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

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

static void insert_to_result(struct rb_root *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 perf_kvm_stat *kvm, struct kvm_event *event)
{
	int vcpu = kvm->trace_vcpu;

	kvm->total_count += get_event_count(event, vcpu);
	kvm->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(struct perf_kvm_stat *kvm)
{
	unsigned int i;
	int vcpu = kvm->trace_vcpu;
	struct kvm_event *event;

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

/* returns left most element of result, and erase it */
static struct kvm_event *pop_from_result(struct rb_root *result)
{
	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(struct perf_kvm_stat *kvm)
{
	int vcpu = kvm->trace_vcpu;

	pr_info("Analyze events for ");

	if (kvm->live) {
		if (kvm->opts.target.system_wide)
			pr_info("all VMs, ");
		else if (kvm->opts.target.pid)
			pr_info("pid(s) %s, ", kvm->opts.target.pid);
		else
			pr_info("dazed and confused on what is monitored, ");
	}

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

static void show_timeofday(void)
{
	char date[64];
	struct timeval tv;
	struct tm ltime;

	gettimeofday(&tv, NULL);
	if (localtime_r(&tv.tv_sec, &ltime)) {
		strftime(date, sizeof(date), "%H:%M:%S", &ltime);
		pr_info("%s.%06ld", date, tv.tv_usec);
	} else
		pr_info("00:00:00.000000");

	return;
}

static void print_result(struct perf_kvm_stat *kvm)
{
	char decode[20];
	struct kvm_event *event;
	int vcpu = kvm->trace_vcpu;

	if (kvm->live) {
		puts(CONSOLE_CLEAR);
		show_timeofday();
	}

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

	pr_info("%9s ", "Time%");
	pr_info("%10s ", "Min Time");
	pr_info("%10s ", "Max Time");
	pr_info("%16s ", "Avg time");
	pr_info("\n\n");

	while ((event = pop_from_result(&kvm->result))) {
		u64 ecount, etime, max, min;

		ecount = get_event_count(event, vcpu);
		etime = get_event_time(event, vcpu);
		max = get_event_max(event, vcpu);
		min = get_event_min(event, vcpu);

		kvm->events_ops->decode_key(kvm, &event->key, decode);
		pr_info("%20s ", decode);
		pr_info("%10llu ", (unsigned long long)ecount);
		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
		pr_info("%8" PRIu64 "us ", min / 1000);
		pr_info("%8" PRIu64 "us ", max / 1000);
		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
			kvm_event_rel_stddev(vcpu, event));
		pr_info("\n");
	}

	pr_info("\nTotal Samples:%" PRIu64 ", Total events handled time:%.2fus.\n\n",
		kvm->total_count, kvm->total_time / 1e3);

	if (kvm->lost_events)
		pr_info("\nLost events: %" PRIu64 "\n\n", kvm->lost_events);
}

#ifdef HAVE_TIMERFD_SUPPORT
static int process_lost_event(struct perf_tool *tool,
			      union perf_event *event __maybe_unused,
			      struct perf_sample *sample __maybe_unused,
			      struct machine *machine __maybe_unused)
{
	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat, tool);

	kvm->lost_events++;
	return 0;
}
#endif

static bool skip_sample(struct perf_kvm_stat *kvm,
			struct perf_sample *sample)
{
	if (kvm->pid_list && intlist__find(kvm->pid_list, sample->pid) == NULL)
		return true;

	return false;
}

static int process_sample_event(struct perf_tool *tool,
				union perf_event *event,
				struct perf_sample *sample,
				struct perf_evsel *evsel,
				struct machine *machine)
{
	struct thread *thread;
	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
						 tool);

	if (skip_sample(kvm, sample))
		return 0;

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

	if (!handle_kvm_event(kvm, thread, evsel, sample))
		return -1;

	return 0;
}

static int cpu_isa_config(struct perf_kvm_stat *kvm)
{
	char buf[64], *cpuid;
	int err, isa;

	if (kvm->live) {
		err = get_cpuid(buf, sizeof(buf));
		if (err != 0) {
			pr_err("Failed to look up CPU type (Intel or AMD)\n");
			return err;
		}
		cpuid = buf;
	} else
		cpuid = kvm->session->header.env.cpuid;

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

	if (isa == 1) {
		kvm->exit_reasons = vmx_exit_reasons;
		kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons);
		kvm->exit_reasons_isa = "VMX";
	}

	return 0;
}

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

	return true;
}

#ifdef HAVE_TIMERFD_SUPPORT
/* keeping the max events to a modest level to keep
 * the processing of samples per mmap smooth.
 */
#define PERF_KVM__MAX_EVENTS_PER_MMAP  25

static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
				   u64 *mmap_time)
{
	union perf_event *event;
	struct perf_sample sample;
	s64 n = 0;
	int err;

	*mmap_time = ULLONG_MAX;
	while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
		err = perf_evlist__parse_sample(kvm->evlist, event, &sample);
		if (err) {
			perf_evlist__mmap_consume(kvm->evlist, idx);
			pr_err("Failed to parse sample\n");
			return -1;
		}

		err = perf_session_queue_event(kvm->session, event, &sample, 0);
		/*
		 * FIXME: Here we can't consume the event, as perf_session_queue_event will
		 *        point to it, and it'll get possibly overwritten by the kernel.
		 */
		perf_evlist__mmap_consume(kvm->evlist, idx);

		if (err) {
			pr_err("Failed to enqueue sample: %d\n", err);
			return -1;
		}

		/* save time stamp of our first sample for this mmap */
		if (n == 0)
			*mmap_time = sample.time;

		/* limit events per mmap handled all at once */
		n++;
		if (n == PERF_KVM__MAX_EVENTS_PER_MMAP)
			break;
	}

	return n;
}

static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
{
	int i, err, throttled = 0;
	s64 n, ntotal = 0;
	u64 flush_time = ULLONG_MAX, mmap_time;

	for (i = 0; i < kvm->evlist->nr_mmaps; i++) {
		n = perf_kvm__mmap_read_idx(kvm, i, &mmap_time);
		if (n < 0)
			return -1;

		/* flush time is going to be the minimum of all the individual
		 * mmap times. Essentially, we flush all the samples queued up
		 * from the last pass under our minimal start time -- that leaves
		 * a very small race for samples to come in with a lower timestamp.
		 * The ioctl to return the perf_clock timestamp should close the
		 * race entirely.
		 */
		if (mmap_time < flush_time)
			flush_time = mmap_time;

		ntotal += n;
		if (n == PERF_KVM__MAX_EVENTS_PER_MMAP)
			throttled = 1;
	}

	/* flush queue after each round in which we processed events */
	if (ntotal) {
		kvm->session->ordered_samples.next_flush = flush_time;
		err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
		if (err) {
			if (kvm->lost_events)
				pr_info("\nLost events: %" PRIu64 "\n\n",
					kvm->lost_events);
			return err;
		}
	}

	return throttled;
}

static volatile int done;

static void sig_handler(int sig __maybe_unused)
{
	done = 1;
}

static int perf_kvm__timerfd_create(struct perf_kvm_stat *kvm)
{
	struct itimerspec new_value;
	int rc = -1;

	kvm->timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK);
	if (kvm->timerfd < 0) {
		pr_err("timerfd_create failed\n");
		goto out;
	}

	new_value.it_value.tv_sec = kvm->display_time;
	new_value.it_value.tv_nsec = 0;
	new_value.it_interval.tv_sec = kvm->display_time;
	new_value.it_interval.tv_nsec = 0;

	if (timerfd_settime(kvm->timerfd, 0, &new_value, NULL) != 0) {
		pr_err("timerfd_settime failed: %d\n", errno);
		close(kvm->timerfd);
		goto out;
	}

	rc = 0;
out: