// SPDX-License-Identifier: GPL-2.0-only

  /*

   * builtin-stat.c
   *
   * Builtin stat command: Give a precise performance counters summary
   * overview about any workload, CPU or specific PID.
   *
   * Sample output:

     $ perf stat ./hackbench 10

    Time: 0.118

    Performance counter stats for './hackbench 10':

         1708.761321 task-clock                #   11.037 CPUs utilized
              41,190 context-switches          #    0.024 M/sec
               6,735 CPU-migrations            #    0.004 M/sec
              17,318 page-faults               #    0.010 M/sec
       5,205,202,243 cycles                    #    3.046 GHz
       3,856,436,920 stalled-cycles-frontend   #   74.09% frontend cycles idle
       1,600,790,871 stalled-cycles-backend    #   30.75% backend  cycles idle
       2,603,501,247 instructions              #    0.50  insns per cycle
                                               #    1.48  stalled cycles per insn
         484,357,498 branches                  #  283.455 M/sec
           6,388,934 branch-misses             #    1.32% of all branches
  
          0.154822978  seconds time elapsed

   *

   * Copyright (C) 2008-2011, Red Hat Inc, Ingo Molnar <mingo@redhat.com>

   *
   * Improvements and fixes by:
   *
   *   Arjan van de Ven <arjan@linux.intel.com>
   *   Yanmin Zhang <yanmin.zhang@intel.com>
   *   Wu Fengguang <fengguang.wu@intel.com>
   *   Mike Galbraith <efault@gmx.de>
   *   Paul Mackerras <paulus@samba.org>

   *   Jaswinder Singh Rajput <jaswinder@kernel.org>

   */

  #include "builtin.h"

  #include "perf.h"

  #include "util/cgroup.h"

  #include <subcmd/parse-options.h>

  #include "util/parse-events.h"

  #include "util/pmu.h"

  #include "util/event.h"

  #include "util/evlist.h"

  #include "util/evsel.h"

  #include "util/debug.h"

  #include "util/color.h"

  #include "util/stat.h"

  #include "util/header.h"

  #include "util/cpumap.h"

  #include "util/thread_map.h"

  #include "util/counts.h"

  #include "util/topdown.h"

  #include "util/session.h"

  #include "util/tool.h"

  #include "util/string2.h"

  #include "util/metricgroup.h"

  #include "util/synthetic-events.h"

  #include "util/target.h"

  #include "util/time-utils.h"

  #include "util/top.h"

  #include "util/affinity.h"

  #include "util/pfm.h"

  #include "asm/bug.h"

  #include <linux/time64.h>

  #include <linux/zalloc.h>

  #include <api/fs/fs.h>

  #include <errno.h>

  #include <signal.h>

  #include <stdlib.h>

  #include <sys/prctl.h>

  #include <inttypes.h>

  #include <locale.h>

  #include <math.h>

  #include <sys/types.h>
  #include <sys/stat.h>

  #include <sys/wait.h>

  #include <unistd.h>

  #include <sys/time.h>
  #include <sys/resource.h>

  #include <linux/err.h>

  #include <linux/ctype.h>

  #include <perf/evlist.h>

  #define DEFAULT_SEPARATOR	" "

  #define FREEZE_ON_SMI_PATH	"devices/cpu/freeze_on_smi"

  static void print_counters(struct timespec *ts, int argc, const char **argv);

  /* Default events used for perf stat -T */

  static const char *transaction_attrs = {
  	"task-clock,"

  	"{"
  	"instructions,"
  	"cycles,"
  	"cpu/cycles-t/,"
  	"cpu/tx-start/,"
  	"cpu/el-start/,"
  	"cpu/cycles-ct/"
  	"}"
  };
  
  /* More limited version when the CPU does not have all events. */

  static const char * transaction_limited_attrs = {
  	"task-clock,"

  	"{"
  	"instructions,"
  	"cycles,"
  	"cpu/cycles-t/,"
  	"cpu/tx-start/"
  	"}"
  };

  static const char * topdown_attrs[] = {
  	"topdown-total-slots",
  	"topdown-slots-retired",
  	"topdown-recovery-bubbles",
  	"topdown-fetch-bubbles",
  	"topdown-slots-issued",
  	NULL,
  };

  static const char *topdown_metric_attrs[] = {
  	"slots",
  	"topdown-retiring",
  	"topdown-bad-spec",
  	"topdown-fe-bound",
  	"topdown-be-bound",
  	NULL,
  };

  static const char *smi_cost_attrs = {
  	"{"
  	"msr/aperf/,"
  	"msr/smi/,"
  	"cycles"
  	"}"
  };

  static struct evlist	*evsel_list;

  static struct target target = {

  	.uid	= UINT_MAX,
  };

  #define METRIC_ONLY_LEN 20

  static volatile pid_t		child_pid			= -1;

  static int			detailed_run			=  0;

  static bool			transaction_run;

  static bool			topdown_run			= false;

  static bool			smi_cost			= false;
  static bool			smi_reset			= false;

  static int			big_num_opt			=  -1;

  static bool			group				= false;

  static const char		*pre_cmd			= NULL;
  static const char		*post_cmd			= NULL;
  static bool			sync_run			= false;

  static bool			forever				= false;

  static bool			force_metric_only		= false;

  static struct timespec		ref_time;

  static bool			append_file;

  static bool			interval_count;

  static const char		*output_name;
  static int			output_fd;

  struct perf_stat {
  	bool			 record;

  	struct perf_data	 data;

  	struct perf_session	*session;
  	u64			 bytes_written;

  	struct perf_tool	 tool;

  	bool			 maps_allocated;

  	struct perf_cpu_map	*cpus;

  	struct perf_thread_map *threads;

  	enum aggr_mode		 aggr_mode;

  };
  
  static struct perf_stat		perf_stat;
  #define STAT_RECORD		perf_stat.record

  static volatile int done = 0;

  static struct perf_stat_config stat_config = {

  	.aggr_mode		= AGGR_GLOBAL,
  	.scale			= true,
  	.unit_width		= 4, /* strlen("unit") */
  	.run_count		= 1,
  	.metric_only_len	= METRIC_ONLY_LEN,
  	.walltime_nsecs_stats	= &walltime_nsecs_stats,

  	.big_num		= true,

  	.ctl_fd			= -1,
  	.ctl_fd_ack		= -1

  };

  static bool cpus_map_matched(struct evsel *a, struct evsel *b)
  {
  	if (!a->core.cpus && !b->core.cpus)
  		return true;
  
  	if (!a->core.cpus || !b->core.cpus)
  		return false;
  
  	if (a->core.cpus->nr != b->core.cpus->nr)
  		return false;
  
  	for (int i = 0; i < a->core.cpus->nr; i++) {
  		if (a->core.cpus->map[i] != b->core.cpus->map[i])
  			return false;
  	}
  
  	return true;
  }
  
  static void evlist__check_cpu_maps(struct evlist *evlist)
  {
  	struct evsel *evsel, *pos, *leader;
  	char buf[1024];
  
  	evlist__for_each_entry(evlist, evsel) {
  		leader = evsel->leader;
  
  		/* Check that leader matches cpus with each member. */
  		if (leader == evsel)
  			continue;
  		if (cpus_map_matched(leader, evsel))
  			continue;
  
  		/* If there's mismatch disable the group and warn user. */
  		WARN_ONCE(1, "WARNING: grouped events cpus do not match, disabling group:
  ");
  		evsel__group_desc(leader, buf, sizeof(buf));
  		pr_warning("  %s
  ", buf);
  
  		if (verbose) {
  			cpu_map__snprint(leader->core.cpus, buf, sizeof(buf));
  			pr_warning("     %s: %s
  ", leader->name, buf);
  			cpu_map__snprint(evsel->core.cpus, buf, sizeof(buf));
  			pr_warning("     %s: %s
  ", evsel->name, buf);
  		}
  
  		for_each_group_evsel(pos, leader) {
  			pos->leader = pos;
  			pos->core.nr_members = 0;
  		}
  		evsel->leader->core.nr_members = 0;
  	}
  }

  static inline void diff_timespec(struct timespec *r, struct timespec *a,
  				 struct timespec *b)
  {
  	r->tv_sec = a->tv_sec - b->tv_sec;
  	if (a->tv_nsec < b->tv_nsec) {

  		r->tv_nsec = a->tv_nsec + NSEC_PER_SEC - b->tv_nsec;

  		r->tv_sec--;
  	} else {
  		r->tv_nsec = a->tv_nsec - b->tv_nsec ;
  	}
  }

  static void perf_stat__reset_stats(void)
  {

  	int i;

  	perf_evlist__reset_stats(evsel_list);

  	perf_stat__reset_shadow_stats();

  
  	for (i = 0; i < stat_config.stats_num; i++)
  		perf_stat__reset_shadow_per_stat(&stat_config.stats[i]);

  }

  static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
  				     union perf_event *event,
  				     struct perf_sample *sample __maybe_unused,
  				     struct machine *machine __maybe_unused)

  {

  	if (perf_data__write(&perf_stat.data, event, event->header.size) < 0) {

  		pr_err("failed to write perf data, error: %m
  ");
  		return -1;
  	}

  	perf_stat.bytes_written += event->header.size;

  	return 0;
  }

  static int write_stat_round_event(u64 tm, u64 type)

  {

  	return perf_event__synthesize_stat_round(NULL, tm, type,

  						 process_synthesized_event,
  						 NULL);
  }
  
  #define WRITE_STAT_ROUND_EVENT(time, interval) \
  	write_stat_round_event(time, PERF_STAT_ROUND_TYPE__ ## interval)

  #define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y)

  static int evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread,
  				   struct perf_counts_values *count)

  {
  	struct perf_sample_id *sid = SID(counter, cpu, thread);
  
  	return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count,
  					   process_synthesized_event, NULL);
  }

  static int read_single_counter(struct evsel *counter, int cpu,

  			       int thread, struct timespec *rs)
  {
  	if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
  		u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
  		struct perf_counts_values *count =
  			perf_counts(counter->counts, cpu, thread);
  		count->ena = count->run = val;
  		count->val = val;
  		return 0;
  	}

  	return evsel__read_counter(counter, cpu, thread);

  }

  /*
   * Read out the results of a single counter:
   * do not aggregate counts across CPUs in system-wide mode
   */

  static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)

  {

  	int nthreads = perf_thread_map__nr(evsel_list->core.threads);

  	int thread;

  	if (!counter->supported)
  		return -ENOENT;

  	if (counter->core.system_wide)

  		nthreads = 1;
  
  	for (thread = 0; thread < nthreads; thread++) {

  		struct perf_counts_values *count;
  
  		count = perf_counts(counter->counts, cpu, thread);
  
  		/*
  		 * The leader's group read loads data into its group members

  		 * (via evsel__read_counter()) and sets their count->loaded.

  		 */
  		if (!perf_counts__is_loaded(counter->counts, cpu, thread) &&
  		    read_single_counter(counter, cpu, thread, rs)) {
  			counter->counts->scaled = -1;
  			perf_counts(counter->counts, cpu, thread)->ena = 0;
  			perf_counts(counter->counts, cpu, thread)->run = 0;
  			return -1;
  		}

  		perf_counts__set_loaded(counter->counts, cpu, thread, false);

  		if (STAT_RECORD) {

  			if (evsel__write_stat_event(counter, cpu, thread, count)) {

  				pr_err("failed to write stat event
  ");
  				return -1;

  			}

  		}

  		if (verbose > 1) {
  			fprintf(stat_config.output,
  				"%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "
  ",

  					evsel__name(counter),

  					cpu,
  					count->val, count->ena, count->run);

  		}

  	}

  
  	return 0;

  }

  static int read_affinity_counters(struct timespec *rs)

  {

  	struct evsel *counter;

  	struct affinity affinity;
  	int i, ncpus, cpu;
  
  	if (affinity__setup(&affinity) < 0)

  		return -1;

  
  	ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus);
  	if (!target__has_cpu(&target) || target__has_per_thread(&target))
  		ncpus = 1;
  	evlist__for_each_cpu(evsel_list, i, cpu) {
  		if (i >= ncpus)
  			break;
  		affinity__set(&affinity, cpu);
  
  		evlist__for_each_entry(evsel_list, counter) {
  			if (evsel__cpu_iter_skip(counter, cpu))
  				continue;
  			if (!counter->err) {
  				counter->err = read_counter_cpu(counter, rs,
  								counter->cpu_iter - 1);
  			}
  		}
  	}
  	affinity__cleanup(&affinity);

  	return 0;
  }
  
  static void read_counters(struct timespec *rs)
  {
  	struct evsel *counter;

  	if (!stat_config.stop_read_counter && (read_affinity_counters(rs) < 0))

  		return;

  	evlist__for_each_entry(evsel_list, counter) {

  		if (counter->err)

  			pr_debug("failed to read counter %s
  ", counter->name);

  		if (counter->err == 0 && perf_stat_process_counter(&stat_config, counter))

  			pr_warning("failed to process counter %s
  ", counter->name);

  		counter->err = 0;

  	}

  }

  static int runtime_stat_new(struct perf_stat_config *config, int nthreads)
  {
  	int i;
  
  	config->stats = calloc(nthreads, sizeof(struct runtime_stat));
  	if (!config->stats)
  		return -1;
  
  	config->stats_num = nthreads;
  
  	for (i = 0; i < nthreads; i++)
  		runtime_stat__init(&config->stats[i]);
  
  	return 0;
  }
  
  static void runtime_stat_delete(struct perf_stat_config *config)
  {
  	int i;
  
  	if (!config->stats)
  		return;
  
  	for (i = 0; i < config->stats_num; i++)
  		runtime_stat__exit(&config->stats[i]);
  
  	zfree(&config->stats);
  }
  
  static void runtime_stat_reset(struct perf_stat_config *config)
  {
  	int i;
  
  	if (!config->stats)
  		return;
  
  	for (i = 0; i < config->stats_num; i++)
  		perf_stat__reset_shadow_per_stat(&config->stats[i]);
  }

  static void process_interval(void)

  {

  	struct timespec ts, rs;

  	clock_gettime(CLOCK_MONOTONIC, &ts);
  	diff_timespec(&rs, &ts, &ref_time);

  	perf_stat__reset_shadow_per_stat(&rt_stat);

  	runtime_stat_reset(&stat_config);

  	read_counters(&rs);

  	if (STAT_RECORD) {

  		if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL))

  			pr_err("failed to write stat round event
  ");
  	}

  	init_stats(&walltime_nsecs_stats);

  	update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000ULL);

  	print_counters(&rs, 0, NULL);

  }

  static bool handle_interval(unsigned int interval, int *times)
  {
  	if (interval) {
  		process_interval();
  		if (interval_count && !(--(*times)))
  			return true;
  	}
  	return false;
  }

  static void enable_counters(void)

  {

  	if (stat_config.initial_delay < 0) {
  		pr_info(EVLIST_DISABLED_MSG);
  		return;
  	}
  
  	if (stat_config.initial_delay > 0) {
  		pr_info(EVLIST_DISABLED_MSG);

  		usleep(stat_config.initial_delay * USEC_PER_MSEC);

  	}

  
  	/*
  	 * We need to enable counters only if:
  	 * - we don't have tracee (attaching to task or cpu)
  	 * - we have initial delay configured
  	 */

  	if (!target__none(&target) || stat_config.initial_delay) {

  		evlist__enable(evsel_list);

  		if (stat_config.initial_delay > 0)
  			pr_info(EVLIST_ENABLED_MSG);
  	}

  }

  static void disable_counters(void)
  {
  	/*
  	 * If we don't have tracee (attaching to task or cpu), counters may
  	 * still be running. To get accurate group ratios, we must stop groups
  	 * from counting before reading their constituent counters.
  	 */
  	if (!target__none(&target))

  		evlist__disable(evsel_list);

  }

  static volatile int workload_exec_errno;

  
  /*
   * perf_evlist__prepare_workload will send a SIGUSR1
   * if the fork fails, since we asked by setting its
   * want_signal to true.
   */

  static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *info,
  					void *ucontext __maybe_unused)

  {

  	workload_exec_errno = info->si_value.sival_int;

  }

  static bool evsel__should_store_id(struct evsel *counter)

  {

  	return STAT_RECORD || counter->core.attr.read_format & PERF_FORMAT_ID;

  }

  static bool is_target_alive(struct target *_target,

  			    struct perf_thread_map *threads)

  {
  	struct stat st;
  	int i;
  
  	if (!target__has_task(_target))
  		return true;
  
  	for (i = 0; i < threads->nr; i++) {
  		char path[PATH_MAX];
  
  		scnprintf(path, PATH_MAX, "%s/%d", procfs__mountpoint(),
  			  threads->map[i].pid);
  
  		if (!stat(path, &st))
  			return true;
  	}
  
  	return false;
  }

  static void process_evlist(struct evlist *evlist, unsigned int interval)
  {
  	enum evlist_ctl_cmd cmd = EVLIST_CTL_CMD_UNSUPPORTED;
  
  	if (evlist__ctlfd_process(evlist, &cmd) > 0) {
  		switch (cmd) {
  		case EVLIST_CTL_CMD_ENABLE:
  			pr_info(EVLIST_ENABLED_MSG);
  			if (interval)
  				process_interval();
  			break;
  		case EVLIST_CTL_CMD_DISABLE:
  			if (interval)
  				process_interval();
  			pr_info(EVLIST_DISABLED_MSG);
  			break;

  		case EVLIST_CTL_CMD_SNAPSHOT:

  		case EVLIST_CTL_CMD_ACK:
  		case EVLIST_CTL_CMD_UNSUPPORTED:
  		default:
  			break;
  		}
  	}
  }
  
  static void compute_tts(struct timespec *time_start, struct timespec *time_stop,
  			int *time_to_sleep)
  {
  	int tts = *time_to_sleep;
  	struct timespec time_diff;
  
  	diff_timespec(&time_diff, time_stop, time_start);
  
  	tts -= time_diff.tv_sec * MSEC_PER_SEC +
  	       time_diff.tv_nsec / NSEC_PER_MSEC;
  
  	if (tts < 0)
  		tts = 0;
  
  	*time_to_sleep = tts;
  }
  
  static int dispatch_events(bool forks, int timeout, int interval, int *times)

  {
  	int child_exited = 0, status = 0;

  	int time_to_sleep, sleep_time;
  	struct timespec time_start, time_stop;
  
  	if (interval)
  		sleep_time = interval;
  	else if (timeout)
  		sleep_time = timeout;
  	else
  		sleep_time = 1000;
  
  	time_to_sleep = sleep_time;

  
  	while (!done) {
  		if (forks)
  			child_exited = waitpid(child_pid, &status, WNOHANG);
  		else
  			child_exited = !is_target_alive(&target, evsel_list->core.threads) ? 1 : 0;
  
  		if (child_exited)
  			break;

  		clock_gettime(CLOCK_MONOTONIC, &time_start);
  		if (!(evlist__poll(evsel_list, time_to_sleep) > 0)) { /* poll timeout or EINTR */
  			if (timeout || handle_interval(interval, times))
  				break;
  			time_to_sleep = sleep_time;
  		} else { /* fd revent */
  			process_evlist(evsel_list, interval);
  			clock_gettime(CLOCK_MONOTONIC, &time_stop);
  			compute_tts(&time_start, &time_stop, &time_to_sleep);
  		}

  	}
  
  	return status;
  }

  enum counter_recovery {
  	COUNTER_SKIP,
  	COUNTER_RETRY,
  	COUNTER_FATAL,
  };
  
  static enum counter_recovery stat_handle_error(struct evsel *counter)
  {
  	char msg[BUFSIZ];
  	/*
  	 * PPC returns ENXIO for HW counters until 2.6.37
  	 * (behavior changed with commit b0a873e).
  	 */
  	if (errno == EINVAL || errno == ENOSYS ||
  	    errno == ENOENT || errno == EOPNOTSUPP ||
  	    errno == ENXIO) {
  		if (verbose > 0)
  			ui__warning("%s event is not supported by the kernel.
  ",

  				    evsel__name(counter));

  		counter->supported = false;

  		/*
  		 * errored is a sticky flag that means one of the counter's
  		 * cpu event had a problem and needs to be reexamined.
  		 */
  		counter->errored = true;

  
  		if ((counter->leader != counter) ||
  		    !(counter->leader->core.nr_members > 1))
  			return COUNTER_SKIP;

  	} else if (evsel__fallback(counter, errno, msg, sizeof(msg))) {

  		if (verbose > 0)
  			ui__warning("%s
  ", msg);
  		return COUNTER_RETRY;
  	} else if (target__has_per_thread(&target) &&
  		   evsel_list->core.threads &&
  		   evsel_list->core.threads->err_thread != -1) {
  		/*
  		 * For global --per-thread case, skip current
  		 * error thread.
  		 */
  		if (!thread_map__remove(evsel_list->core.threads,
  					evsel_list->core.threads->err_thread)) {
  			evsel_list->core.threads->err_thread = -1;
  			return COUNTER_RETRY;
  		}
  	}

  	evsel__open_strerror(counter, &target, errno, msg, sizeof(msg));

  	ui__error("%s
  ", msg);
  
  	if (child_pid != -1)
  		kill(child_pid, SIGTERM);
  	return COUNTER_FATAL;
  }

  static int __run_perf_stat(int argc, const char **argv, int run_idx)

  {

  	int interval = stat_config.interval;

  	int times = stat_config.times;

  	int timeout = stat_config.timeout;

  	char msg[BUFSIZ];

  	unsigned long long t0, t1;

  	struct evsel *counter;

  	size_t l;

  	int status = 0;

  	const bool forks = (argc > 0);

  	bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;

  	struct affinity affinity;
  	int i, cpu;
  	bool second_pass = false;

  	if (forks) {

  		if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe,

  						  workload_exec_failed_signal) < 0) {

  			perror("failed to prepare workload");
  			return -1;

  		}

  		child_pid = evsel_list->workload.pid;

  	}

  	if (group)

  		perf_evlist__set_leader(evsel_list);

  	if (affinity__setup(&affinity) < 0)
  		return -1;
  
  	evlist__for_each_cpu (evsel_list, i, cpu) {
  		affinity__set(&affinity, cpu);
  
  		evlist__for_each_entry(evsel_list, counter) {
  			if (evsel__cpu_iter_skip(counter, cpu))
  				continue;
  			if (counter->reset_group || counter->errored)
  				continue;

  try_again:

  			if (create_perf_stat_counter(counter, &stat_config, &target,
  						     counter->cpu_iter - 1) < 0) {
  
  				/*
  				 * Weak group failed. We cannot just undo this here
  				 * because earlier CPUs might be in group mode, and the kernel
  				 * doesn't support mixing group and non group reads. Defer
  				 * it to later.
  				 * Don't close here because we're in the wrong affinity.
  				 */
  				if ((errno == EINVAL || errno == EBADF) &&
  				    counter->leader != counter &&
  				    counter->weak_group) {
  					perf_evlist__reset_weak_group(evsel_list, counter, false);
  					assert(counter->reset_group);
  					second_pass = true;
  					continue;
  				}
  
  				switch (stat_handle_error(counter)) {
  				case COUNTER_FATAL:
  					return -1;
  				case COUNTER_RETRY:
  					goto try_again;
  				case COUNTER_SKIP:
  					continue;
  				default:
  					break;
  				}

  			}

  			counter->supported = true;
  		}
  	}

  	if (second_pass) {
  		/*
  		 * Now redo all the weak group after closing them,
  		 * and also close errored counters.
  		 */
  
  		evlist__for_each_cpu(evsel_list, i, cpu) {
  			affinity__set(&affinity, cpu);
  			/* First close errored or weak retry */
  			evlist__for_each_entry(evsel_list, counter) {
  				if (!counter->reset_group && !counter->errored)
  					continue;
  				if (evsel__cpu_iter_skip_no_inc(counter, cpu))
  					continue;
  				perf_evsel__close_cpu(&counter->core, counter->cpu_iter);

  			}

  			/* Now reopen weak */
  			evlist__for_each_entry(evsel_list, counter) {
  				if (!counter->reset_group && !counter->errored)
  					continue;
  				if (evsel__cpu_iter_skip(counter, cpu))
  					continue;
  				if (!counter->reset_group)
  					continue;
  try_again_reset:

  				pr_debug2("reopening weak %s
  ", evsel__name(counter));

  				if (create_perf_stat_counter(counter, &stat_config, &target,
  							     counter->cpu_iter - 1) < 0) {
  
  					switch (stat_handle_error(counter)) {
  					case COUNTER_FATAL:
  						return -1;
  					case COUNTER_RETRY:
  						goto try_again_reset;
  					case COUNTER_SKIP:
  						continue;
  					default:
  						break;
  					}
  				}
  				counter->supported = true;
  			}
  		}
  	}
  	affinity__cleanup(&affinity);
  
  	evlist__for_each_entry(evsel_list, counter) {
  		if (!counter->supported) {
  			perf_evsel__free_fd(&counter->core);
  			continue;

  		}

  
  		l = strlen(counter->unit);

  		if (l > stat_config.unit_width)
  			stat_config.unit_width = l;

  		if (evsel__should_store_id(counter) &&

  		    evsel__store_ids(counter, evsel_list))

  			return -1;

  	}

  	if (perf_evlist__apply_filters(evsel_list, &counter)) {

  		pr_err("failed to set filter \"%s\" on event %s with %d (%s)
  ",

  			counter->filter, evsel__name(counter), errno,

  			str_error_r(errno, msg, sizeof(msg)));

  		return -1;
  	}

  	if (STAT_RECORD) {

  		int err, fd = perf_data__fd(&perf_stat.data);

  		if (is_pipe) {

  			err = perf_header__write_pipe(perf_data__fd(&perf_stat.data));

  		} else {
  			err = perf_session__write_header(perf_stat.session, evsel_list,
  							 fd, false);
  		}

  		if (err < 0)
  			return err;

  		err = perf_event__synthesize_stat_events(&stat_config, NULL, evsel_list,
  							 process_synthesized_event, is_pipe);

  		if (err < 0)
  			return err;

  	}

  	/*
  	 * Enable counters and exec the command:
  	 */
  	t0 = rdclock();

  	clock_gettime(CLOCK_MONOTONIC, &ref_time);

  	if (forks) {

  		perf_evlist__start_workload(evsel_list);

  		enable_counters();

  		if (interval || timeout || evlist__ctlfd_initialized(evsel_list))

  			status = dispatch_events(forks, timeout, interval, &times);

  		if (child_pid != -1) {
  			if (timeout)
  				kill(child_pid, SIGTERM);

  			wait4(child_pid, &status, 0, &stat_config.ru_data);

  		}

  		if (workload_exec_errno) {

  			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));

  			pr_err("Workload failed: %s
  ", emsg);

  			return -1;

  		}

  		if (WIFSIGNALED(status))
  			psignal(WTERMSIG(status), argv[0]);

  	} else {

  		enable_counters();

  		status = dispatch_events(forks, timeout, interval, &times);

  	}

  	disable_counters();

  	t1 = rdclock();

  	if (stat_config.walltime_run_table)
  		stat_config.walltime_run[run_idx] = t1 - t0;

  	if (interval && stat_config.summary) {

  		stat_config.interval = 0;

  		stat_config.stop_read_counter = true;

  		init_stats(&walltime_nsecs_stats);
  		update_stats(&walltime_nsecs_stats, t1 - t0);
  
  		if (stat_config.aggr_mode == AGGR_GLOBAL)
  			perf_evlist__save_aggr_prev_raw_counts(evsel_list);
  
  		perf_evlist__copy_prev_raw_counts(evsel_list);
  		perf_evlist__reset_prev_raw_counts(evsel_list);
  		runtime_stat_reset(&stat_config);
  		perf_stat__reset_shadow_per_stat(&rt_stat);
  	} else
  		update_stats(&walltime_nsecs_stats, t1 - t0);

  	/*
  	 * Closing a group leader splits the group, and as we only disable
  	 * group leaders, results in remaining events becoming enabled. To
  	 * avoid arbitrary skew, we must read all counters before closing any
  	 * group leaders.
  	 */

  	read_counters(&(struct timespec) { .tv_nsec = t1-t0 });

  
  	/*
  	 * We need to keep evsel_list alive, because it's processed
  	 * later the evsel_list will be closed after.
  	 */
  	if (!STAT_RECORD)

  		evlist__close(evsel_list);

  	return WEXITSTATUS(status);
  }

  static int run_perf_stat(int argc, const char **argv, int run_idx)

  {
  	int ret;
  
  	if (pre_cmd) {
  		ret = system(pre_cmd);
  		if (ret)
  			return ret;
  	}
  
  	if (sync_run)
  		sync();

  	ret = __run_perf_stat(argc, argv, run_idx);

  	if (ret)
  		return ret;
  
  	if (post_cmd) {
  		ret = system(post_cmd);
  		if (ret)
  			return ret;
  	}
  
  	return ret;
  }

  static void print_counters(struct timespec *ts, int argc, const char **argv)
  {

  	/* Do not print anything if we record to the pipe. */
  	if (STAT_RECORD && perf_stat.data.is_pipe)
  		return;

  	perf_evlist__print_counters(evsel_list, &stat_config, &target,

  				    ts, argc, argv);

  }

  static volatile int signr = -1;

  static void skip_signal(int signo)

  {

  	if ((child_pid == -1) || stat_config.interval)

  		done = 1;

  	signr = signo;

  	/*
  	 * render child_pid harmless
  	 * won't send SIGTERM to a random
  	 * process in case of race condition
  	 * and fast PID recycling
  	 */
  	child_pid = -1;

  }
  
  static void sig_atexit(void)
  {

  	sigset_t set, oset;
  
  	/*
  	 * avoid race condition with SIGCHLD handler
  	 * in skip_signal() which is modifying child_pid
  	 * goal is to avoid send SIGTERM to a random
  	 * process
  	 */
  	sigemptyset(&set);
  	sigaddset(&set, SIGCHLD);
  	sigprocmask(SIG_BLOCK, &set, &oset);

  	if (child_pid != -1)
  		kill(child_pid, SIGTERM);

  	sigprocmask(SIG_SETMASK, &oset, NULL);

  	if (signr == -1)
  		return;
  
  	signal(signr, SIG_DFL);
  	kill(getpid(), signr);

  }

  void perf_stat__set_big_num(int set)
  {
  	stat_config.big_num = (set != 0);
  }

  static int stat__set_big_num(const struct option *opt __maybe_unused,
  			     const char *s __maybe_unused, int unset)

  {
  	big_num_opt = unset ? 0 : 1;

  	perf_stat__set_big_num(!unset);

  	return 0;
  }

  static int enable_metric_only(const struct option *opt __maybe_unused,
  			      const char *s __maybe_unused, int unset)
  {
  	force_metric_only = true;

  	stat_config.metric_only = !unset;

  	return 0;
  }

  static int parse_metric_groups(const struct option *opt,
  			       const char *str,
  			       int unset __maybe_unused)
  {

  	return metricgroup__parse_groups(opt, str,
  					 stat_config.metric_no_group,
  					 stat_config.metric_no_merge,
  					 &stat_config.metric_events);

  }

  static int parse_control_option(const struct option *opt,
  				const char *str,
  				int unset __maybe_unused)
  {

  	struct perf_stat_config *config = opt->value;

  	return evlist__parse_control(str, &config->ctl_fd, &config->ctl_fd_ack, &config->ctl_fd_close);
  }

  static int parse_stat_cgroups(const struct option *opt,
  			      const char *str, int unset)
  {
  	if (stat_config.cgroup_list) {
  		pr_err("--cgroup and --for-each-cgroup cannot be used together
  ");
  		return -1;
  	}
  
  	return parse_cgroups(opt, str, unset);
  }

  static struct option stat_options[] = {

  	OPT_BOOLEAN('T', "transaction", &transaction_run,
  		    "hardware transaction statistics"),
  	OPT_CALLBACK('e', "event", &evsel_list, "event",
  		     "event selector. use 'perf list' to list available events",
  		     parse_events_option),
  	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
  		     "event filter", parse_filter),

  	OPT_BOOLEAN('i', "no-inherit", &stat_config.no_inherit,

  		    "child tasks do not inherit counters"),
  	OPT_STRING('p', "pid", &target.pid, "pid",
  		   "stat events on existing process id"),
  	OPT_STRING('t', "tid", &target.tid, "tid",
  		   "stat events on existing thread id"),
  	OPT_BOOLEAN('a', "all-cpus", &target.system_wide,
  		    "system-wide collection from all CPUs"),
  	OPT_BOOLEAN('g', "group", &group,
  		    "put the counters into a counter group"),

  	OPT_BOOLEAN(0, "scale", &stat_config.scale,
  		    "Use --no-scale to disable counter scaling for multiplexing"),

  	OPT_INCR('v', "verbose", &verbose,
  		    "be more verbose (show counter open errors, etc)"),

  	OPT_INTEGER('r', "repeat", &stat_config.run_count,

  		    "repeat command and print average + stddev (max: 100, forever: 0)"),

  	OPT_BOOLEAN(0, "table", &stat_config.walltime_run_table,

  		    "display details about each run (only with -r option)"),

  	OPT_BOOLEAN('n', "null", &stat_config.null_run,

  		    "null run - dont start any counters"),
  	OPT_INCR('d', "detailed", &detailed_run,
  		    "detailed run - start a lot of events"),
  	OPT_BOOLEAN('S', "sync", &sync_run,
  		    "call sync() before starting a run"),
  	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
  			   "print large numbers with thousands\' separators",
  			   stat__set_big_num),
  	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
  		    "list of cpus to monitor in system-wide"),
  	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
  		    "disable CPU count aggregation", AGGR_NONE),

  	OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge identical named events"),

  	OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator",

  		   "print counts with custom separator"),
  	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",

  		     "monitor event in cgroup name only", parse_stat_cgroups),
  	OPT_STRING(0, "for-each-cgroup", &stat_config.cgroup_list, "name",
  		    "expand events for each cgroup"),

  	OPT_STRING('o', "output", &output_name, "file", "output file name"),
  	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
  	OPT_INTEGER(0, "log-fd", &output_fd,
  		    "log output to fd, instead of stderr"),
  	OPT_STRING(0, "pre", &pre_cmd, "command",
  			"command to run prior to the measured command"),
  	OPT_STRING(0, "post", &post_cmd, "command",
  			"command to run after to the measured command"),
  	OPT_UINTEGER('I', "interval-print", &stat_config.interval,

  		    "print counts at regular interval in ms "
  		    "(overhead is possible for values <= 100ms)"),

  	OPT_INTEGER(0, "interval-count", &stat_config.times,
  		    "print counts for fixed number of times"),

  	OPT_BOOLEAN(0, "interval-clear", &stat_config.interval_clear,

  		    "clear screen in between new interval"),

  	OPT_UINTEGER(0, "timeout", &stat_config.timeout,
  		    "stop workload and print counts after a timeout period in ms (>= 10ms)"),

  	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
  		     "aggregate counts per processor socket", AGGR_SOCKET),

  	OPT_SET_UINT(0, "per-die", &stat_config.aggr_mode,
  		     "aggregate counts per processor die", AGGR_DIE),

  	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
  		     "aggregate counts per physical processor core", AGGR_CORE),
  	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
  		     "aggregate counts per thread", AGGR_THREAD),

  	OPT_SET_UINT(0, "per-node", &stat_config.aggr_mode,
  		     "aggregate counts per numa node", AGGR_NODE),

  	OPT_INTEGER('D', "delay", &stat_config.initial_delay,
  		    "ms to wait before starting measurement after program start (-1: start with events disabled)"),

  	OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL,

  			"Only print computed metrics. No raw values", enable_metric_only),

  	OPT_BOOLEAN(0, "metric-no-group", &stat_config.metric_no_group,
  		       "don't group metric events, impacts multiplexing"),
  	OPT_BOOLEAN(0, "metric-no-merge", &stat_config.metric_no_merge,
  		       "don't try to share events between metrics in a group"),

  	OPT_BOOLEAN(0, "topdown", &topdown_run,
  			"measure topdown level 1 statistics"),

  	OPT_BOOLEAN(0, "smi-cost", &smi_cost,
  			"measure SMI cost"),

  	OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
  		     "monitor specified metrics or metric groups (separated by ,)",
  		     parse_metric_groups),

  	OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel,
  			 "Configure all used events to run in kernel space.",
  			 PARSE_OPT_EXCLUSIVE),
  	OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user,
  			 "Configure all used events to run in user space.",
  			 PARSE_OPT_EXCLUSIVE),

  	OPT_BOOLEAN(0, "percore-show-thread", &stat_config.percore_show_thread,
  		    "Use with 'percore' event qualifier to show the event "
  		    "counts of one hardware thread by sum up total hardware "
  		    "threads of same physical core"),

  	OPT_BOOLEAN(0, "summary", &stat_config.summary,
  		       "print summary for interval mode"),

  #ifdef HAVE_LIBPFM
  	OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
  		"libpfm4 event selector. use 'perf list' to list available events",
  		parse_libpfm_events_option),
  #endif

  	OPT_CALLBACK(0, "control", &stat_config, "fd:ctl-fd[,ack-fd] or fifo:ctl-fifo[,ack-fifo]",

  		     "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events).
  "

  		     "\t\t\t  Optionally send control command completion ('ack\
  ') to ack-fd descriptor.
  "
  		     "\t\t\t  Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.",

  		      parse_control_option),

  	OPT_END()
  };

  static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,

  				 struct perf_cpu_map *map, int cpu)

  {
  	return cpu_map__get_socket(map, cpu, NULL);
  }

  static int perf_stat__get_die(struct perf_stat_config *config __maybe_unused,

  			      struct perf_cpu_map *map, int cpu)

  {
  	return cpu_map__get_die(map, cpu, NULL);
  }

  static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,

  			       struct perf_cpu_map *map, int cpu)

  {
  	return cpu_map__get_core(map, cpu, NULL);
  }

  static int perf_stat__get_node(struct perf_stat_config *config __maybe_unused,
  			       struct perf_cpu_map *map, int cpu)
  {
  	return cpu_map__get_node(map, cpu, NULL);
  }

  static int perf_stat__get_aggr(struct perf_stat_config *config,

  			       aggr_get_id_t get_id, struct perf_cpu_map *map, int idx)

  {
  	int cpu;
  
  	if (idx >= map->nr)
  		return -1;
  
  	cpu = map->map[idx];

  	if (config->cpus_aggr_map->map[cpu] == -1)
  		config->cpus_aggr_map->map[cpu] = get_id(config, map, idx);

  	return config->cpus_aggr_map->map[cpu];

  }

  static int perf_stat__get_socket_cached(struct perf_stat_config *config,

  					struct perf_cpu_map *map, int idx)

  {

  	return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);

  }

  static int perf_stat__get_die_cached(struct perf_stat_config *config,

  					struct perf_cpu_map *map, int idx)

  {
  	return perf_stat__get_aggr(config, perf_stat__get_die, map, idx);
  }

  static int perf_stat__get_core_cached(struct perf_stat_config *config,

  				      struct perf_cpu_map *map, int idx)

  {

  	return perf_stat__get_aggr(config, perf_stat__get_core, map, idx);

  }

  static int perf_stat__get_node_cached(struct perf_stat_config *config,
  				      struct perf_cpu_map *map, int idx)
  {
  	return perf_stat__get_aggr(config, perf_stat__get_node, map, idx);
  }

  static bool term_percore_set(void)
  {

  	struct evsel *counter;

  
  	evlist__for_each_entry(evsel_list, counter) {
  		if (counter->percore)
  			return true;
  	}
  
  	return false;
  }

  static int perf_stat_init_aggr_mode(void)
  {

  	int nr;

  	switch (stat_config.aggr_mode) {

  	case AGGR_SOCKET:

  		if (cpu_map__build_socket_map(evsel_list->core.cpus, &stat_config.aggr_map)) {

  			perror("cannot build socket map");
  			return -1;
  		}

  		stat_config.aggr_get_id = perf_stat__get_socket_cached;

  		break;

  	case AGGR_DIE:

  		if (cpu_map__build_die_map(evsel_list->core.cpus, &stat_config.aggr_map)) {

  			perror("cannot build die map");
  			return -1;
  		}
  		stat_config.aggr_get_id = perf_stat__get_die_cached;
  		break;

  	case AGGR_CORE:

  		if (cpu_map__build_core_map(evsel_list->core.cpus, &stat_config.aggr_map)) {

  			perror("cannot build core map");
  			return -1;
  		}

  		stat_config.aggr_get_id = perf_stat__get_core_cached;

  		break;

  	case AGGR_NODE:
  		if (cpu_map__build_node_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
  			perror("cannot build core map");
  			return -1;
  		}
  		stat_config.aggr_get_id = perf_stat__get_node_cached;
  		break;

  	case AGGR_NONE:

  		if (term_percore_set()) {

  			if (cpu_map__build_core_map(evsel_list->core.cpus,

  						    &stat_config.aggr_map)) {
  				perror("cannot build core map");
  				return -1;
  			}
  			stat_config.aggr_get_id = perf_stat__get_core_cached;
  		}
  		break;

  	case AGGR_GLOBAL:

  	case AGGR_THREAD:

  	case AGGR_UNSET:

  	default:
  		break;
  	}

  
  	/*
  	 * The evsel_list->cpus is the base we operate on,
  	 * taking the highest cpu number to be the size of
  	 * the aggregation translate cpumap.
  	 */

  	nr = perf_cpu_map__max(evsel_list->core.cpus);

  	stat_config.cpus_aggr_map = perf_cpu_map__empty_new(nr + 1);

  	return stat_config.cpus_aggr_map ? 0 : -ENOMEM;

  }

  static void perf_stat__exit_aggr_mode(void)
  {

  	perf_cpu_map__put(stat_config.aggr_map);
  	perf_cpu_map__put(stat_config.cpus_aggr_map);

  	stat_config.aggr_map = NULL;
  	stat_config.cpus_aggr_map = NULL;

  }

  static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *map, int idx)

  {
  	int cpu;
  
  	if (idx > map->nr)
  		return -1;
  
  	cpu = map->map[idx];

  	if (cpu >= env->nr_cpus_avail)

  		return -1;
  
  	return cpu;
  }

  static int perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data)

  {
  	struct perf_env *env = data;
  	int cpu = perf_env__get_cpu(env, map, idx);
  
  	return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
  }

  static int perf_env__get_die(struct perf_cpu_map *map, int idx, void *data)

  {
  	struct perf_env *env = data;
  	int die_id = -1, cpu = perf_env__get_cpu(env, map, idx);
  
  	if (cpu != -1) {
  		/*
  		 * Encode socket in bit range 15:8
  		 * die_id is relative to socket,
  		 * we need a global id. So we combine
  		 * socket + die id
  		 */
  		if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.
  "))
  			return -1;
  
  		if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.
  "))
  			return -1;
  
  		die_id = (env->cpu[cpu].socket_id << 8) | (env->cpu[cpu].die_id & 0xff);
  	}
  
  	return die_id;
  }

  static int perf_env__get_core(struct perf_cpu_map *map, int idx, void *data)

  {
  	struct perf_env *env = data;
  	int core = -1, cpu = perf_env__get_cpu(env, map, idx);
  
  	if (cpu != -1) {

  		/*

  		 * Encode socket in bit range 31:24
  		 * encode die id in bit range 23:16
  		 * core_id is relative to socket and die,

  		 * we need a global id. So we combine

  		 * socket + die id + core id

  		 */

  		if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.
  "))
  			return -1;
  
  		if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.
  "))
  			return -1;
  
  		if (WARN_ONCE(env->cpu[cpu].core_id >> 16, "The core id number is too big.
  "))
  			return -1;
  
  		core = (env->cpu[cpu].socket_id << 24) |
  		       (env->cpu[cpu].die_id << 16) |
  		       (env->cpu[cpu].core_id & 0xffff);

  	}
  
  	return core;
  }

  static int perf_env__get_node(struct perf_cpu_map *map, int idx, void *data)
  {
  	int cpu = perf_env__get_cpu(data, map, idx);
  
  	return perf_env__numa_node(data, cpu);
  }

  static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus,
  				      struct perf_cpu_map **sockp)

  {
  	return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
  }

  static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus,
  				   struct perf_cpu_map **diep)

  {
  	return cpu_map__build_map(cpus, diep, perf_env__get_die, env);
  }

  static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus,
  				    struct perf_cpu_map **corep)

  {
  	return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
  }

  static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus,
  				    struct perf_cpu_map **nodep)
  {
  	return cpu_map__build_map(cpus, nodep, perf_env__get_node, env);
  }

  static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,

  				      struct perf_cpu_map *map, int idx)

  {
  	return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
  }

  static int perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,

  				   struct perf_cpu_map *map, int idx)

  {
  	return perf_env__get_die(map, idx, &perf_stat.session->header.env);
  }

  static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,

  				    struct perf_cpu_map *map, int idx)

  {
  	return perf_env__get_core(map, idx, &perf_stat.session->header.env);
  }

  static int perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused,
  				    struct perf_cpu_map *map, int idx)
  {
  	return perf_env__get_node(map, idx, &perf_stat.session->header.env);
  }

  static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
  {
  	struct perf_env *env = &st->session->header.env;
  
  	switch (stat_config.aggr_mode) {
  	case AGGR_SOCKET:

  		if (perf_env__build_socket_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {

  			perror("cannot build socket map");
  			return -1;
  		}

  		stat_config.aggr_get_id = perf_stat__get_socket_file;

  		break;

  	case AGGR_DIE:

  		if (perf_env__build_die_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {

  			perror("cannot build die map");
  			return -1;
  		}
  		stat_config.aggr_get_id = perf_stat__get_die_file;
  		break;

  	case AGGR_CORE:

  		if (perf_env__build_core_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {

  			perror("cannot build core map");
  			return -1;
  		}

  		stat_config.aggr_get_id = perf_stat__get_core_file;

  		break;

  	case AGGR_NODE:
  		if (perf_env__build_node_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
  			perror("cannot build core map");
  			return -1;
  		}
  		stat_config.aggr_get_id = perf_stat__get_node_file;
  		break;

  	case AGGR_NONE:
  	case AGGR_GLOBAL:
  	case AGGR_THREAD:
  	case AGGR_UNSET:
  	default:
  		break;
  	}
  
  	return 0;
  }

  /*
   * Add default attributes, if there were no attributes specified or
   * if -d/--detailed, -d -d or -d -d -d is used:
   */
  static int add_default_attributes(void)
  {

  	int err;

  	struct perf_event_attr default_attrs0[] = {

  
    { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
    { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
    { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS		},
    { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
  
    { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},

  };
  	struct perf_event_attr frontend_attrs[] = {

    { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	},

  };
  	struct perf_event_attr backend_attrs[] = {

    { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},

  };
  	struct perf_event_attr default_attrs1[] = {

    { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
    { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
    { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},
  
  };
  
  /*
   * Detailed stats (-d), covering the L1 and last level data caches:
   */
  	struct perf_event_attr detailed_attrs[] = {
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_LL			<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_LL			<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
  };
  
  /*
   * Very detailed stats (-d -d), covering the instruction cache and the TLB caches:
   */
  	struct perf_event_attr very_detailed_attrs[] = {
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_L1I		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_DTLB		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_ITLB		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_READ		<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
  
  };
  
  /*
   * Very, very detailed stats (-d -d -d), adding prefetch events:
   */
  	struct perf_event_attr very_very_detailed_attrs[] = {
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_ACCESS	<< 16)				},
  
    { .type = PERF_TYPE_HW_CACHE,
      .config =
  	 PERF_COUNT_HW_CACHE_L1D		<<  0  |
  	(PERF_COUNT_HW_CACHE_OP_PREFETCH	<<  8) |
  	(PERF_COUNT_HW_CACHE_RESULT_MISS	<< 16)				},
  };

  	struct parse_events_error errinfo;

  	/* Set attrs if no event is selected and !null_run: */

  	if (stat_config.null_run)

  		return 0;

  	bzero(&errinfo, sizeof(errinfo));

  	if (transaction_run) {

  		/* Handle -T as -M transaction. Once platform specific metrics
  		 * support has been added to the json files, all archictures
  		 * will use this approach. To determine transaction support
  		 * on an architecture test for such a metric name.
  		 */
  		if (metricgroup__has_metric("transaction")) {
  			struct option opt = { .value = &evsel_list };
  
  			return metricgroup__parse_groups(&opt, "transaction",

  							 stat_config.metric_no_group,
  							stat_config.metric_no_merge,

  							 &stat_config.metric_events);

  		}

  		if (pmu_have_event("cpu", "cycles-ct") &&
  		    pmu_have_event("cpu", "el-start"))

  			err = parse_events(evsel_list, transaction_attrs,
  					   &errinfo);

  		else

  			err = parse_events(evsel_list,
  					   transaction_limited_attrs,
  					   &errinfo);

  		if (err) {

  			fprintf(stderr, "Cannot set up transaction events
  ");

  			parse_events_print_error(&errinfo, transaction_attrs);

  			return -1;
  		}
  		return 0;
  	}

  	if (smi_cost) {
  		int smi;
  
  		if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) {
  			fprintf(stderr, "freeze_on_smi is not supported.
  ");
  			return -1;
  		}
  
  		if (!smi) {
  			if (sysfs__write_int(FREEZE_ON_SMI_PATH, 1) < 0) {
  				fprintf(stderr, "Failed to set freeze_on_smi.
  ");
  				return -1;
  			}
  			smi_reset = true;
  		}
  
  		if (pmu_have_event("msr", "aperf") &&
  		    pmu_have_event("msr", "smi")) {
  			if (!force_metric_only)

  				stat_config.metric_only = true;

  			err = parse_events(evsel_list, smi_cost_attrs, &errinfo);

  		} else {
  			fprintf(stderr, "To measure SMI cost, it needs "
  				"msr/aperf/, msr/smi/ and cpu/cycles/ support
  ");

  			parse_events_print_error(&errinfo, smi_cost_attrs);

  			return -1;
  		}
  		if (err) {

  			parse_events_print_error(&errinfo, smi_cost_attrs);

  			fprintf(stderr, "Cannot set up SMI cost events
  ");
  			return -1;
  		}
  		return 0;
  	}

  	if (topdown_run) {
  		char *str = NULL;
  		bool warn = false;

  		if (!force_metric_only)
  			stat_config.metric_only = true;
  
  		if (topdown_filter_events(topdown_metric_attrs, &str, 1) < 0) {
  			pr_err("Out of memory
  ");
  			return -1;
  		}
  		if (topdown_metric_attrs[0] && str) {
  			if (!stat_config.interval && !stat_config.metric_only) {
  				fprintf(stat_config.output,
  					"Topdown accuracy may decrease when measuring long periods.
  "
  					"Please print the result regularly, e.g. -I1000
  ");
  			}
  			goto setup_metrics;
  		}
  
  		zfree(&str);

  		if (stat_config.aggr_mode != AGGR_GLOBAL &&
  		    stat_config.aggr_mode != AGGR_CORE) {
  			pr_err("top down event configuration requires --per-core mode
  ");
  			return -1;
  		}
  		stat_config.aggr_mode = AGGR_CORE;
  		if (nr_cgroups || !target__has_cpu(&target)) {
  			pr_err("top down event configuration requires system-wide mode (-a)
  ");
  			return -1;
  		}

  		if (topdown_filter_events(topdown_attrs, &str,
  				arch_topdown_check_group(&warn)) < 0) {
  			pr_err("Out of memory
  ");
  			return -1;
  		}
  		if (topdown_attrs[0] && str) {
  			if (warn)
  				arch_topdown_group_warn();

  setup_metrics:

  			err = parse_events(evsel_list, str, &errinfo);

  			if (err) {
  				fprintf(stderr,
  					"Cannot set up top down events %s: %d
  ",
  					str, err);

  				parse_events_print_error(&errinfo, str);

  				free(str);

  				return -1;
  			}
  		} else {
  			fprintf(stderr, "System does not support topdown
  ");
  			return -1;
  		}
  		free(str);
  	}

  	if (!evsel_list->core.nr_entries) {

  		if (target__has_cpu(&target))
  			default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;

  		if (evlist__add_default_attrs(evsel_list, default_attrs0) < 0)

  			return -1;
  		if (pmu_have_event("cpu", "stalled-cycles-frontend")) {

  			if (evlist__add_default_attrs(evsel_list, frontend_attrs) < 0)

  				return -1;
  		}
  		if (pmu_have_event("cpu", "stalled-cycles-backend")) {

  			if (evlist__add_default_attrs(evsel_list, backend_attrs) < 0)

  				return -1;
  		}

  		if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0)

  			return -1;

  	}
  
  	/* Detailed events get appended to the event list: */
  
  	if (detailed_run <  1)
  		return 0;
  
  	/* Append detailed run extra attributes: */

  	if (evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)

  		return -1;

  
  	if (detailed_run < 2)
  		return 0;
  
  	/* Append very detailed run extra attributes: */

  	if (evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)

  		return -1;

  
  	if (detailed_run < 3)
  		return 0;
  
  	/* Append very, very detailed run extra attributes: */

  	return evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);

  }

  static const char * const stat_record_usage[] = {

  	"perf stat record [<options>]",
  	NULL,
  };

  static void init_features(struct perf_session *session)
  {
  	int feat;
  
  	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
  		perf_header__set_feat(&session->header, feat);

  	perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);

  	perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
  	perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
  	perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
  	perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
  }

  static int __cmd_record(int argc, const char **argv)
  {
  	struct perf_session *session;

  	struct perf_data *data = &perf_stat.data;

  	argc = parse_options(argc, argv, stat_options, stat_record_usage,

  			     PARSE_OPT_STOP_AT_NON_OPTION);
  
  	if (output_name)

  		data->path = output_name;

  	if (stat_config.run_count != 1 || forever) {

  		pr_err("Cannot use -r option with perf stat record.
  ");
  		return -1;
  	}

  	session = perf_session__new(data, false, NULL);

  	if (IS_ERR(session)) {
  		pr_err("Perf session creation failed
  ");
  		return PTR_ERR(session);

  	}

  	init_features(session);

  	session->evlist   = evsel_list;
  	perf_stat.session = session;
  	perf_stat.record  = true;
  	return argc;
  }

  static int process_stat_round_event(struct perf_session *session,
  				    union perf_event *event)

  {

  	struct perf_record_stat_round *stat_round = &event->stat_round;

  	struct evsel *counter;

  	struct timespec tsh, *ts = NULL;
  	const char **argv = session->header.env.cmdline_argv;
  	int argc = session->header.env.nr_cmdline;

  	evlist__for_each_entry(evsel_list, counter)

  		perf_stat_process_counter(&stat_config, counter);

  	if (stat_round->type == PERF_STAT_ROUND_TYPE__FINAL)
  		update_stats(&walltime_nsecs_stats, stat_round->time);

  	if (stat_config.interval && stat_round->time) {

  		tsh.tv_sec  = stat_round->time / NSEC_PER_SEC;
  		tsh.tv_nsec = stat_round->time % NSEC_PER_SEC;

  		ts = &tsh;
  	}
  
  	print_counters(ts, argc, argv);
  	return 0;
  }

  static

  int process_stat_config_event(struct perf_session *session,
  			      union perf_event *event)

  {

  	struct perf_tool *tool = session->tool;

  	struct perf_stat *st = container_of(tool, struct perf_stat, tool);

  	perf_event__read_stat_config(&stat_config, &event->stat_config);

  	if (perf_cpu_map__empty(st->cpus)) {

  		if (st->aggr_mode != AGGR_UNSET)
  			pr_warning("warning: processing task data, aggregation mode not set
  ");
  		return 0;
  	}
  
  	if (st->aggr_mode != AGGR_UNSET)
  		stat_config.aggr_mode = st->aggr_mode;

  	if (perf_stat.data.is_pipe)

  		perf_stat_init_aggr_mode();
  	else
  		perf_stat_init_aggr_mode_file(st);

  	return 0;
  }

  static int set_maps(struct perf_stat *st)
  {
  	if (!st->cpus || !st->threads)
  		return 0;
  
  	if (WARN_ONCE(st->maps_allocated, "stats double allocation
  "))
  		return -EINVAL;

  	perf_evlist__set_maps(&evsel_list->core, st->cpus, st->threads);

  
  	if (perf_evlist__alloc_stats(evsel_list, true))
  		return -ENOMEM;
  
  	st->maps_allocated = true;
  	return 0;
  }
  
  static

  int process_thread_map_event(struct perf_session *session,
  			     union perf_event *event)

  {

  	struct perf_tool *tool = session->tool;