From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/tools/perf/builtin-stat.c | 2565 +++++++++++++++++++++--------------------------------------
1 files changed, 911 insertions(+), 1,654 deletions(-)
diff --git a/kernel/tools/perf/builtin-stat.c b/kernel/tools/perf/builtin-stat.c
index adabe9d..b01af17 100644
--- a/kernel/tools/perf/builtin-stat.c
+++ b/kernel/tools/perf/builtin-stat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* builtin-stat.c
*
@@ -37,14 +38,11 @@
* Mike Galbraith <efault@gmx.de>
* Paul Mackerras <paulus@samba.org>
* Jaswinder Singh Rajput <jaswinder@kernel.org>
- *
- * Released under the GPL v2. (and only v2, not any later version)
*/
-#include "perf.h"
#include "builtin.h"
+#include "perf.h"
#include "util/cgroup.h"
-#include "util/util.h"
#include <subcmd/parse-options.h>
#include "util/parse-events.h"
#include "util/pmu.h"
@@ -52,23 +50,27 @@
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
-#include "util/drv_configs.h"
#include "util/color.h"
#include "util/stat.h"
#include "util/header.h"
#include "util/cpumap.h"
-#include "util/thread.h"
#include "util/thread_map.h"
#include "util/counts.h"
-#include "util/group.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>
@@ -83,13 +85,12 @@
#include <unistd.h>
#include <sys/time.h>
#include <sys/resource.h>
-#include <sys/wait.h>
+#include <linux/err.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <perf/evlist.h>
#define DEFAULT_SEPARATOR " "
-#define CNTR_NOT_SUPPORTED "<not supported>"
-#define CNTR_NOT_COUNTED "<not counted>"
#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi"
static void print_counters(struct timespec *ts, int argc, const char **argv);
@@ -127,6 +128,15 @@
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/,"
@@ -135,56 +145,32 @@
"}"
};
-static struct perf_evlist *evsel_list;
-
-static struct rblist metric_events;
+static struct evlist *evsel_list;
static struct target target = {
.uid = UINT_MAX,
};
-typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
-
#define METRIC_ONLY_LEN 20
-static int run_count = 1;
-static bool no_inherit = false;
static volatile pid_t child_pid = -1;
-static bool null_run = false;
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 bool big_num = true;
static int big_num_opt = -1;
-static const char *csv_sep = NULL;
-static bool csv_output = false;
static bool group = false;
static const char *pre_cmd = NULL;
static const char *post_cmd = NULL;
static bool sync_run = false;
-static unsigned int initial_delay = 0;
-static unsigned int unit_width = 4; /* strlen("unit") */
static bool forever = false;
-static bool metric_only = false;
static bool force_metric_only = false;
-static bool no_merge = false;
-static bool walltime_run_table = false;
static struct timespec ref_time;
-static struct cpu_map *aggr_map;
-static aggr_get_id_t aggr_get_id;
static bool append_file;
static bool interval_count;
-static bool interval_clear;
static const char *output_name;
static int output_fd;
-static int print_free_counters_hint;
-static int print_mixed_hw_group_error;
-static u64 *walltime_run;
-static bool ru_display = false;
-static struct rusage ru_data;
-static unsigned int metric_only_len = METRIC_ONLY_LEN;
struct perf_stat {
bool record;
@@ -193,8 +179,8 @@
u64 bytes_written;
struct perf_tool tool;
bool maps_allocated;
- struct cpu_map *cpus;
- struct thread_map *threads;
+ struct perf_cpu_map *cpus;
+ struct perf_thread_map *threads;
enum aggr_mode aggr_mode;
};
@@ -204,13 +190,68 @@
static volatile int done = 0;
static struct perf_stat_config stat_config = {
- .aggr_mode = AGGR_GLOBAL,
- .scale = true,
+ .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 is_duration_time(struct perf_evsel *evsel)
+static bool cpus_map_matched(struct evsel *a, struct evsel *b)
{
- return !strcmp(evsel->name, "duration_time");
+ 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:\n");
+ evsel__group_desc(leader, buf, sizeof(buf));
+ pr_warning(" %s\n", buf);
+
+ if (verbose) {
+ cpu_map__snprint(leader->core.cpus, buf, sizeof(buf));
+ pr_warning(" %s: %s\n", leader->name, buf);
+ cpu_map__snprint(evsel->core.cpus, buf, sizeof(buf));
+ pr_warning(" %s: %s\n", 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,
@@ -234,66 +275,6 @@
for (i = 0; i < stat_config.stats_num; i++)
perf_stat__reset_shadow_per_stat(&stat_config.stats[i]);
-}
-
-static int create_perf_stat_counter(struct perf_evsel *evsel)
-{
- struct perf_event_attr *attr = &evsel->attr;
- struct perf_evsel *leader = evsel->leader;
-
- if (stat_config.scale) {
- attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
- PERF_FORMAT_TOTAL_TIME_RUNNING;
- }
-
- /*
- * The event is part of non trivial group, let's enable
- * the group read (for leader) and ID retrieval for all
- * members.
- */
- if (leader->nr_members > 1)
- attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
-
- attr->inherit = !no_inherit;
-
- /*
- * Some events get initialized with sample_(period/type) set,
- * like tracepoints. Clear it up for counting.
- */
- attr->sample_period = 0;
-
- /*
- * But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
- * while avoiding that older tools show confusing messages.
- *
- * However for pipe sessions we need to keep it zero,
- * because script's perf_evsel__check_attr is triggered
- * by attr->sample_type != 0, and we can't run it on
- * stat sessions.
- */
- if (!(STAT_RECORD && perf_stat.data.is_pipe))
- attr->sample_type = PERF_SAMPLE_IDENTIFIER;
-
- /*
- * Disabling all counters initially, they will be enabled
- * either manually by us or by kernel via enable_on_exec
- * set later.
- */
- if (perf_evsel__is_group_leader(evsel)) {
- attr->disabled = 1;
-
- /*
- * In case of initial_delay we enable tracee
- * events manually.
- */
- if (target__none(&target) && !initial_delay)
- attr->enable_on_exec = 1;
- }
-
- if (target__has_cpu(&target) && !target__has_per_thread(&target))
- return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
-
- return perf_evsel__open_per_thread(evsel, evsel_list->threads);
}
static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
@@ -320,11 +301,10 @@
#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->sample_id, x, y)
+#define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y)
-static int
-perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
- struct perf_counts_values *count)
+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);
@@ -332,89 +312,169 @@
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(struct perf_evsel *counter)
+static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
{
- int nthreads = thread_map__nr(evsel_list->threads);
- int ncpus, cpu, thread;
-
- if (target__has_cpu(&target) && !target__has_per_thread(&target))
- ncpus = perf_evsel__nr_cpus(counter);
- else
- ncpus = 1;
+ int nthreads = perf_thread_map__nr(evsel_list->core.threads);
+ int thread;
if (!counter->supported)
return -ENOENT;
- if (counter->system_wide)
+ if (counter->core.system_wide)
nthreads = 1;
for (thread = 0; thread < nthreads; thread++) {
- for (cpu = 0; cpu < ncpus; cpu++) {
- struct perf_counts_values *count;
+ struct perf_counts_values *count;
- count = perf_counts(counter->counts, cpu, thread);
+ count = perf_counts(counter->counts, cpu, thread);
- /*
- * The leader's group read loads data into its group members
- * (via perf_evsel__read_counter) and sets threir count->loaded.
- */
- if (!count->loaded &&
- perf_evsel__read_counter(counter, cpu, thread)) {
- counter->counts->scaled = -1;
- perf_counts(counter->counts, cpu, thread)->ena = 0;
- perf_counts(counter->counts, cpu, thread)->run = 0;
+ /*
+ * 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\n");
return -1;
}
+ }
- count->loaded = false;
-
- if (STAT_RECORD) {
- if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
- pr_err("failed to write stat event\n");
- return -1;
- }
- }
-
- if (verbose > 1) {
- fprintf(stat_config.output,
- "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
- perf_evsel__name(counter),
- cpu,
- count->val, count->ena, count->run);
- }
+ if (verbose > 1) {
+ fprintf(stat_config.output,
+ "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+ evsel__name(counter),
+ cpu,
+ count->val, count->ena, count->run);
}
}
return 0;
}
-static void read_counters(void)
+static int read_affinity_counters(struct timespec *rs)
{
- struct perf_evsel *counter;
- int ret;
+ 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) {
- ret = read_counter(counter);
- if (ret)
+ if (counter->err)
pr_debug("failed to read counter %s\n", counter->name);
-
- if (ret == 0 && perf_stat_process_counter(&stat_config, counter))
+ if (counter->err == 0 && perf_stat_process_counter(&stat_config, counter))
pr_warning("failed to process counter %s\n", 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;
- read_counters();
-
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))
@@ -426,18 +486,38 @@
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 (initial_delay)
- usleep(initial_delay * USEC_PER_MSEC);
+ 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) || initial_delay)
- perf_evlist__enable(evsel_list);
+ 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)
@@ -448,7 +528,7 @@
* from counting before reading their constituent counters.
*/
if (!target__none(&target))
- perf_evlist__disable(evsel_list);
+ evlist__disable(evsel_list);
}
static volatile int workload_exec_errno;
@@ -464,109 +544,167 @@
workload_exec_errno = info->si_value.sival_int;
}
-static int perf_stat_synthesize_config(bool is_pipe)
+static bool evsel__should_store_id(struct evsel *counter)
{
- int err;
+ return STAT_RECORD || counter->core.attr.read_format & PERF_FORMAT_ID;
+}
- if (is_pipe) {
- err = perf_event__synthesize_attrs(NULL, perf_stat.session,
- process_synthesized_event);
- if (err < 0) {
- pr_err("Couldn't synthesize attrs.\n");
- return err;
+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);
}
}
- err = perf_event__synthesize_extra_attr(NULL,
- evsel_list,
- process_synthesized_event,
- is_pipe);
-
- err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
- process_synthesized_event,
- NULL);
- if (err < 0) {
- pr_err("Couldn't synthesize thread map.\n");
- return err;
- }
-
- err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus,
- process_synthesized_event, NULL);
- if (err < 0) {
- pr_err("Couldn't synthesize thread map.\n");
- return err;
- }
-
- err = perf_event__synthesize_stat_config(NULL, &stat_config,
- process_synthesized_event, NULL);
- if (err < 0) {
- pr_err("Couldn't synthesize config.\n");
- return err;
- }
-
- return 0;
+ return status;
}
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+enum counter_recovery {
+ COUNTER_SKIP,
+ COUNTER_RETRY,
+ COUNTER_FATAL,
+};
-static int __store_counter_ids(struct perf_evsel *counter)
+static enum counter_recovery stat_handle_error(struct evsel *counter)
{
- int cpu, thread;
-
- for (cpu = 0; cpu < xyarray__max_x(counter->fd); cpu++) {
- for (thread = 0; thread < xyarray__max_y(counter->fd);
- thread++) {
- int fd = FD(counter, cpu, thread);
-
- if (perf_evlist__id_add_fd(evsel_list, counter,
- cpu, thread, fd) < 0)
- return -1;
- }
- }
-
- return 0;
-}
-
-static int store_counter_ids(struct perf_evsel *counter)
-{
- struct cpu_map *cpus = counter->cpus;
- struct thread_map *threads = counter->threads;
-
- if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr))
- return -ENOMEM;
-
- return __store_counter_ids(counter);
-}
-
-static bool perf_evsel__should_store_id(struct perf_evsel *counter)
-{
- return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
-}
-
-static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
-{
- struct perf_evsel *c2, *leader;
- bool is_open = true;
-
- leader = evsel->leader;
- pr_debug("Weak group for %s/%d failed\n",
- leader->name, leader->nr_members);
-
+ char msg[BUFSIZ];
/*
- * for_each_group_member doesn't work here because it doesn't
- * include the first entry.
+ * PPC returns ENXIO for HW counters until 2.6.37
+ * (behavior changed with commit b0a873e).
*/
- evlist__for_each_entry(evsel_list, c2) {
- if (c2 == evsel)
- is_open = false;
- if (c2->leader == leader) {
- if (is_open)
- perf_evsel__close(c2);
- c2->leader = c2;
- c2->nr_members = 0;
+ if (errno == EINVAL || errno == ENOSYS ||
+ errno == ENOENT || errno == EOPNOTSUPP ||
+ errno == ENXIO) {
+ if (verbose > 0)
+ ui__warning("%s event is not supported by the kernel.\n",
+ 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\n", 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;
}
}
- return leader;
+
+ evsel__open_strerror(counter, &target, errno, msg, sizeof(msg));
+ ui__error("%s\n", 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)
@@ -576,24 +714,14 @@
int timeout = stat_config.timeout;
char msg[BUFSIZ];
unsigned long long t0, t1;
- struct perf_evsel *counter;
- struct timespec ts;
+ 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 perf_evsel_config_term *err_term;
-
- if (interval) {
- ts.tv_sec = interval / USEC_PER_MSEC;
- ts.tv_nsec = (interval % USEC_PER_MSEC) * NSEC_PER_MSEC;
- } else if (timeout) {
- ts.tv_sec = timeout / USEC_PER_MSEC;
- ts.tv_nsec = (timeout % USEC_PER_MSEC) * NSEC_PER_MSEC;
- } else {
- ts.tv_sec = 1;
- ts.tv_nsec = 0;
- }
+ struct affinity affinity;
+ int i, cpu;
+ bool second_pass = false;
if (forks) {
if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe,
@@ -607,82 +735,118 @@
if (group)
perf_evlist__set_leader(evsel_list);
- evlist__for_each_entry(evsel_list, counter) {
+ 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) < 0) {
+ if (create_perf_stat_counter(counter, &stat_config, &target,
+ counter->cpu_iter - 1) < 0) {
- /* Weak group failed. Reset the group. */
- if ((errno == EINVAL || errno == EBADF) &&
- counter->leader != counter &&
- counter->weak_group) {
- counter = perf_evsel__reset_weak_group(counter);
- goto try_again;
- }
-
- /*
- * 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.\n",
- perf_evsel__name(counter));
- counter->supported = false;
-
- if ((counter->leader != counter) ||
- !(counter->leader->nr_members > 1))
- continue;
- } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
- if (verbose > 0)
- ui__warning("%s\n", msg);
- goto try_again;
- } else if (target__has_per_thread(&target) &&
- evsel_list->threads &&
- evsel_list->threads->err_thread != -1) {
/*
- * For global --per-thread case, skip current
- * error thread.
+ * 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 (!thread_map__remove(evsel_list->threads,
- evsel_list->threads->err_thread)) {
- evsel_list->threads->err_thread = -1;
- goto try_again;
+ 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;
+ }
+
}
-
- perf_evsel__open_strerror(counter, &target,
- errno, msg, sizeof(msg));
- ui__error("%s\n", msg);
-
- if (child_pid != -1)
- kill(child_pid, SIGTERM);
-
- return -1;
+ counter->supported = true;
}
- 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\n", 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 > unit_width)
- unit_width = l;
+ if (l > stat_config.unit_width)
+ stat_config.unit_width = l;
- if (perf_evsel__should_store_id(counter) &&
- store_counter_ids(counter))
+ 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)\n",
- counter->filter, perf_evsel__name(counter), errno,
+ counter->filter, evsel__name(counter), errno,
str_error_r(errno, msg, sizeof(msg)));
- return -1;
- }
-
- if (perf_evlist__apply_drv_configs(evsel_list, &counter, &err_term)) {
- pr_err("failed to set config \"%s\" on event %s with %d (%s)\n",
- err_term->val.drv_cfg, perf_evsel__name(counter), errno,
- str_error_r(errno, msg, sizeof(msg)));
return -1;
}
@@ -699,7 +863,8 @@
if (err < 0)
return err;
- err = perf_stat_synthesize_config(is_pipe);
+ err = perf_event__synthesize_stat_events(&stat_config, NULL, evsel_list,
+ process_synthesized_event, is_pipe);
if (err < 0)
return err;
}
@@ -714,17 +879,13 @@
perf_evlist__start_workload(evsel_list);
enable_counters();
- if (interval || timeout) {
- while (!waitpid(child_pid, &status, WNOHANG)) {
- nanosleep(&ts, NULL);
- if (timeout)
- break;
- process_interval();
- if (interval_count && !(--times))
- break;
- }
+ if (interval || timeout || evlist__ctlfd_initialized(evsel_list))
+ status = dispatch_events(forks, timeout, interval, ×);
+ if (child_pid != -1) {
+ if (timeout)
+ kill(child_pid, SIGTERM);
+ wait4(child_pid, &status, 0, &stat_config.ru_data);
}
- wait4(child_pid, &status, 0, &ru_data);
if (workload_exec_errno) {
const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
@@ -736,26 +897,31 @@
psignal(WTERMSIG(status), argv[0]);
} else {
enable_counters();
- while (!done) {
- nanosleep(&ts, NULL);
- if (timeout)
- break;
- if (interval) {
- process_interval();
- if (interval_count && !(--times))
- break;
- }
- }
+ status = dispatch_events(forks, timeout, interval, ×);
}
disable_counters();
t1 = rdclock();
- if (walltime_run_table)
- walltime_run[run_idx] = t1 - t0;
+ if (stat_config.walltime_run_table)
+ stat_config.walltime_run[run_idx] = t1 - t0;
- update_stats(&walltime_nsecs_stats, 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
@@ -763,8 +929,14 @@
* avoid arbitrary skew, we must read all counters before closing any
* group leaders.
*/
- read_counters();
- perf_evlist__close(evsel_list);
+ 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);
}
@@ -795,1105 +967,14 @@
return ret;
}
-static void print_running(u64 run, u64 ena)
-{
- if (csv_output) {
- fprintf(stat_config.output, "%s%" PRIu64 "%s%.2f",
- csv_sep,
- run,
- csv_sep,
- ena ? 100.0 * run / ena : 100.0);
- } else if (run != ena) {
- fprintf(stat_config.output, " (%.2f%%)", 100.0 * run / ena);
- }
-}
-
-static void print_noise_pct(double total, double avg)
-{
- double pct = rel_stddev_stats(total, avg);
-
- if (csv_output)
- fprintf(stat_config.output, "%s%.2f%%", csv_sep, pct);
- else if (pct)
- fprintf(stat_config.output, " ( +-%6.2f%% )", pct);
-}
-
-static void print_noise(struct perf_evsel *evsel, double avg)
-{
- struct perf_stat_evsel *ps;
-
- if (run_count == 1)
- return;
-
- ps = evsel->stats;
- print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
-}
-
-static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
-{
- switch (stat_config.aggr_mode) {
- case AGGR_CORE:
- fprintf(stat_config.output, "S%d-C%*d%s%*d%s",
- cpu_map__id_to_socket(id),
- csv_output ? 0 : -8,
- cpu_map__id_to_cpu(id),
- csv_sep,
- csv_output ? 0 : 4,
- nr,
- csv_sep);
- break;
- case AGGR_SOCKET:
- fprintf(stat_config.output, "S%*d%s%*d%s",
- csv_output ? 0 : -5,
- id,
- csv_sep,
- csv_output ? 0 : 4,
- nr,
- csv_sep);
- break;
- case AGGR_NONE:
- fprintf(stat_config.output, "CPU%*d%s",
- csv_output ? 0 : -4,
- perf_evsel__cpus(evsel)->map[id], csv_sep);
- break;
- case AGGR_THREAD:
- fprintf(stat_config.output, "%*s-%*d%s",
- csv_output ? 0 : 16,
- thread_map__comm(evsel->threads, id),
- csv_output ? 0 : -8,
- thread_map__pid(evsel->threads, id),
- csv_sep);
- break;
- case AGGR_GLOBAL:
- case AGGR_UNSET:
- default:
- break;
- }
-}
-
-struct outstate {
- FILE *fh;
- bool newline;
- const char *prefix;
- int nfields;
- int id, nr;
- struct perf_evsel *evsel;
-};
-
-#define METRIC_LEN 35
-
-static void new_line_std(void *ctx)
-{
- struct outstate *os = ctx;
-
- os->newline = true;
-}
-
-static void do_new_line_std(struct outstate *os)
-{
- fputc('\n', os->fh);
- fputs(os->prefix, os->fh);
- aggr_printout(os->evsel, os->id, os->nr);
- if (stat_config.aggr_mode == AGGR_NONE)
- fprintf(os->fh, " ");
- fprintf(os->fh, " ");
-}
-
-static void print_metric_std(void *ctx, const char *color, const char *fmt,
- const char *unit, double val)
-{
- struct outstate *os = ctx;
- FILE *out = os->fh;
- int n;
- bool newline = os->newline;
-
- os->newline = false;
-
- if (unit == NULL || fmt == NULL) {
- fprintf(out, "%-*s", METRIC_LEN, "");
- return;
- }
-
- if (newline)
- do_new_line_std(os);
-
- n = fprintf(out, " # ");
- if (color)
- n += color_fprintf(out, color, fmt, val);
- else
- n += fprintf(out, fmt, val);
- fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
-}
-
-static void new_line_csv(void *ctx)
-{
- struct outstate *os = ctx;
- int i;
-
- fputc('\n', os->fh);
- if (os->prefix)
- fprintf(os->fh, "%s%s", os->prefix, csv_sep);
- aggr_printout(os->evsel, os->id, os->nr);
- for (i = 0; i < os->nfields; i++)
- fputs(csv_sep, os->fh);
-}
-
-static void print_metric_csv(void *ctx,
- const char *color __maybe_unused,
- const char *fmt, const char *unit, double val)
-{
- struct outstate *os = ctx;
- FILE *out = os->fh;
- char buf[64], *vals, *ends;
-
- if (unit == NULL || fmt == NULL) {
- fprintf(out, "%s%s", csv_sep, csv_sep);
- return;
- }
- snprintf(buf, sizeof(buf), fmt, val);
- ends = vals = ltrim(buf);
- while (isdigit(*ends) || *ends == '.')
- ends++;
- *ends = 0;
- while (isspace(*unit))
- unit++;
- fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
-}
-
-/* Filter out some columns that don't work well in metrics only mode */
-
-static bool valid_only_metric(const char *unit)
-{
- if (!unit)
- return false;
- if (strstr(unit, "/sec") ||
- strstr(unit, "hz") ||
- strstr(unit, "Hz") ||
- strstr(unit, "CPUs utilized"))
- return false;
- return true;
-}
-
-static const char *fixunit(char *buf, struct perf_evsel *evsel,
- const char *unit)
-{
- if (!strncmp(unit, "of all", 6)) {
- snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
- unit);
- return buf;
- }
- return unit;
-}
-
-static void print_metric_only(void *ctx, const char *color, const char *fmt,
- const char *unit, double val)
-{
- struct outstate *os = ctx;
- FILE *out = os->fh;
- char buf[1024], str[1024];
- unsigned mlen = metric_only_len;
-
- if (!valid_only_metric(unit))
- return;
- unit = fixunit(buf, os->evsel, unit);
- if (mlen < strlen(unit))
- mlen = strlen(unit) + 1;
-
- if (color)
- mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
-
- color_snprintf(str, sizeof(str), color ?: "", fmt, val);
- fprintf(out, "%*s ", mlen, str);
-}
-
-static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
- const char *fmt,
- const char *unit, double val)
-{
- struct outstate *os = ctx;
- FILE *out = os->fh;
- char buf[64], *vals, *ends;
- char tbuf[1024];
-
- if (!valid_only_metric(unit))
- return;
- unit = fixunit(tbuf, os->evsel, unit);
- snprintf(buf, sizeof buf, fmt, val);
- ends = vals = ltrim(buf);
- while (isdigit(*ends) || *ends == '.')
- ends++;
- *ends = 0;
- fprintf(out, "%s%s", vals, csv_sep);
-}
-
-static void new_line_metric(void *ctx __maybe_unused)
-{
-}
-
-static void print_metric_header(void *ctx, const char *color __maybe_unused,
- const char *fmt __maybe_unused,
- const char *unit, double val __maybe_unused)
-{
- struct outstate *os = ctx;
- char tbuf[1024];
-
- if (!valid_only_metric(unit))
- return;
- unit = fixunit(tbuf, os->evsel, unit);
- if (csv_output)
- fprintf(os->fh, "%s%s", unit, csv_sep);
- else
- fprintf(os->fh, "%*s ", metric_only_len, unit);
-}
-
-static int first_shadow_cpu(struct perf_evsel *evsel, int id)
-{
- int i;
-
- if (!aggr_get_id)
- return 0;
-
- if (stat_config.aggr_mode == AGGR_NONE)
- return id;
-
- if (stat_config.aggr_mode == AGGR_GLOBAL)
- return 0;
-
- for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
- int cpu2 = perf_evsel__cpus(evsel)->map[i];
-
- if (aggr_get_id(evsel_list->cpus, cpu2) == id)
- return cpu2;
- }
- return 0;
-}
-
-static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
- FILE *output = stat_config.output;
- double sc = evsel->scale;
- const char *fmt;
-
- if (csv_output) {
- fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s";
- } else {
- if (big_num)
- fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
- else
- fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
- }
-
- aggr_printout(evsel, id, nr);
-
- fprintf(output, fmt, avg, csv_sep);
-
- if (evsel->unit)
- fprintf(output, "%-*s%s",
- csv_output ? 0 : unit_width,
- evsel->unit, csv_sep);
-
- fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
-
- if (evsel->cgrp)
- fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-}
-
-static bool is_mixed_hw_group(struct perf_evsel *counter)
-{
- struct perf_evlist *evlist = counter->evlist;
- u32 pmu_type = counter->attr.type;
- struct perf_evsel *pos;
-
- if (counter->nr_members < 2)
- return false;
-
- evlist__for_each_entry(evlist, pos) {
- /* software events can be part of any hardware group */
- if (pos->attr.type == PERF_TYPE_SOFTWARE)
- continue;
- if (pmu_type == PERF_TYPE_SOFTWARE) {
- pmu_type = pos->attr.type;
- continue;
- }
- if (pmu_type != pos->attr.type)
- return true;
- }
-
- return false;
-}
-
-static void printout(int id, int nr, struct perf_evsel *counter, double uval,
- char *prefix, u64 run, u64 ena, double noise,
- struct runtime_stat *st)
-{
- struct perf_stat_output_ctx out;
- struct outstate os = {
- .fh = stat_config.output,
- .prefix = prefix ? prefix : "",
- .id = id,
- .nr = nr,
- .evsel = counter,
- };
- print_metric_t pm = print_metric_std;
- void (*nl)(void *);
-
- if (metric_only) {
- nl = new_line_metric;
- if (csv_output)
- pm = print_metric_only_csv;
- else
- pm = print_metric_only;
- } else
- nl = new_line_std;
-
- if (csv_output && !metric_only) {
- static int aggr_fields[] = {
- [AGGR_GLOBAL] = 0,
- [AGGR_THREAD] = 1,
- [AGGR_NONE] = 1,
- [AGGR_SOCKET] = 2,
- [AGGR_CORE] = 2,
- };
-
- pm = print_metric_csv;
- nl = new_line_csv;
- os.nfields = 3;
- os.nfields += aggr_fields[stat_config.aggr_mode];
- if (counter->cgrp)
- os.nfields++;
- }
- if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
- if (metric_only) {
- pm(&os, NULL, "", "", 0);
- return;
- }
- aggr_printout(counter, id, nr);
-
- fprintf(stat_config.output, "%*s%s",
- csv_output ? 0 : 18,
- counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep);
-
- if (counter->supported) {
- print_free_counters_hint = 1;
- if (is_mixed_hw_group(counter))
- print_mixed_hw_group_error = 1;
- }
-
- fprintf(stat_config.output, "%-*s%s",
- csv_output ? 0 : unit_width,
- counter->unit, csv_sep);
-
- fprintf(stat_config.output, "%*s",
- csv_output ? 0 : -25,
- perf_evsel__name(counter));
-
- if (counter->cgrp)
- fprintf(stat_config.output, "%s%s",
- csv_sep, counter->cgrp->name);
-
- if (!csv_output)
- pm(&os, NULL, NULL, "", 0);
- print_noise(counter, noise);
- print_running(run, ena);
- if (csv_output)
- pm(&os, NULL, NULL, "", 0);
- return;
- }
-
- if (!metric_only)
- abs_printout(id, nr, counter, uval);
-
- out.print_metric = pm;
- out.new_line = nl;
- out.ctx = &os;
- out.force_header = false;
-
- if (csv_output && !metric_only) {
- print_noise(counter, noise);
- print_running(run, ena);
- }
-
- perf_stat__print_shadow_stats(counter, uval,
- first_shadow_cpu(counter, id),
- &out, &metric_events, st);
- if (!csv_output && !metric_only) {
- print_noise(counter, noise);
- print_running(run, ena);
- }
-}
-
-static void aggr_update_shadow(void)
-{
- int cpu, s2, id, s;
- u64 val;
- struct perf_evsel *counter;
-
- for (s = 0; s < aggr_map->nr; s++) {
- id = aggr_map->map[s];
- evlist__for_each_entry(evsel_list, counter) {
- val = 0;
- for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
- s2 = aggr_get_id(evsel_list->cpus, cpu);
- if (s2 != id)
- continue;
- val += perf_counts(counter->counts, cpu, 0)->val;
- }
- perf_stat__update_shadow_stats(counter, val,
- first_shadow_cpu(counter, id),
- &rt_stat);
- }
- }
-}
-
-static void uniquify_event_name(struct perf_evsel *counter)
-{
- char *new_name;
- char *config;
-
- if (counter->uniquified_name ||
- !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
- strlen(counter->pmu_name)))
- return;
-
- config = strchr(counter->name, '/');
- if (config) {
- if (asprintf(&new_name,
- "%s%s", counter->pmu_name, config) > 0) {
- free(counter->name);
- counter->name = new_name;
- }
- } else {
- if (asprintf(&new_name,
- "%s [%s]", counter->name, counter->pmu_name) > 0) {
- free(counter->name);
- counter->name = new_name;
- }
- }
-
- counter->uniquified_name = true;
-}
-
-static void collect_all_aliases(struct perf_evsel *counter,
- void (*cb)(struct perf_evsel *counter, void *data,
- bool first),
- void *data)
-{
- struct perf_evsel *alias;
-
- alias = list_prepare_entry(counter, &(evsel_list->entries), node);
- list_for_each_entry_continue (alias, &evsel_list->entries, node) {
- if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
- alias->scale != counter->scale ||
- alias->cgrp != counter->cgrp ||
- strcmp(alias->unit, counter->unit) ||
- perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
- break;
- alias->merged_stat = true;
- cb(alias, data, false);
- }
-}
-
-static bool collect_data(struct perf_evsel *counter,
- void (*cb)(struct perf_evsel *counter, void *data,
- bool first),
- void *data)
-{
- if (counter->merged_stat)
- return false;
- cb(counter, data, true);
- if (no_merge)
- uniquify_event_name(counter);
- else if (counter->auto_merge_stats)
- collect_all_aliases(counter, cb, data);
- return true;
-}
-
-struct aggr_data {
- u64 ena, run, val;
- int id;
- int nr;
- int cpu;
-};
-
-static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
-{
- struct aggr_data *ad = data;
- int cpu, s2;
-
- for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
- struct perf_counts_values *counts;
-
- s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
- if (s2 != ad->id)
- continue;
- if (first)
- ad->nr++;
- counts = perf_counts(counter->counts, cpu, 0);
- /*
- * When any result is bad, make them all to give
- * consistent output in interval mode.
- */
- if (counts->ena == 0 || counts->run == 0 ||
- counter->counts->scaled == -1) {
- ad->ena = 0;
- ad->run = 0;
- break;
- }
- ad->val += counts->val;
- ad->ena += counts->ena;
- ad->run += counts->run;
- }
-}
-
-static void print_aggr(char *prefix)
-{
- FILE *output = stat_config.output;
- struct perf_evsel *counter;
- int s, id, nr;
- double uval;
- u64 ena, run, val;
- bool first;
-
- if (!(aggr_map || aggr_get_id))
- return;
-
- aggr_update_shadow();
-
- /*
- * With metric_only everything is on a single line.
- * Without each counter has its own line.
- */
- for (s = 0; s < aggr_map->nr; s++) {
- struct aggr_data ad;
- if (prefix && metric_only)
- fprintf(output, "%s", prefix);
-
- ad.id = id = aggr_map->map[s];
- first = true;
- evlist__for_each_entry(evsel_list, counter) {
- if (is_duration_time(counter))
- continue;
-
- ad.val = ad.ena = ad.run = 0;
- ad.nr = 0;
- if (!collect_data(counter, aggr_cb, &ad))
- continue;
- nr = ad.nr;
- ena = ad.ena;
- run = ad.run;
- val = ad.val;
- if (first && metric_only) {
- first = false;
- aggr_printout(counter, id, nr);
- }
- if (prefix && !metric_only)
- fprintf(output, "%s", prefix);
-
- uval = val * counter->scale;
- printout(id, nr, counter, uval, prefix, run, ena, 1.0,
- &rt_stat);
- if (!metric_only)
- fputc('\n', output);
- }
- if (metric_only)
- fputc('\n', output);
- }
-}
-
-static int cmp_val(const void *a, const void *b)
-{
- return ((struct perf_aggr_thread_value *)b)->val -
- ((struct perf_aggr_thread_value *)a)->val;
-}
-
-static struct perf_aggr_thread_value *sort_aggr_thread(
- struct perf_evsel *counter,
- int nthreads, int ncpus,
- int *ret)
-{
- int cpu, thread, i = 0;
- double uval;
- struct perf_aggr_thread_value *buf;
-
- buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
- if (!buf)
- return NULL;
-
- for (thread = 0; thread < nthreads; thread++) {
- u64 ena = 0, run = 0, val = 0;
-
- for (cpu = 0; cpu < ncpus; cpu++) {
- val += perf_counts(counter->counts, cpu, thread)->val;
- ena += perf_counts(counter->counts, cpu, thread)->ena;
- run += perf_counts(counter->counts, cpu, thread)->run;
- }
-
- uval = val * counter->scale;
-
- /*
- * Skip value 0 when enabling --per-thread globally,
- * otherwise too many 0 output.
- */
- if (uval == 0.0 && target__has_per_thread(&target))
- continue;
-
- buf[i].counter = counter;
- buf[i].id = thread;
- buf[i].uval = uval;
- buf[i].val = val;
- buf[i].run = run;
- buf[i].ena = ena;
- i++;
- }
-
- qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
-
- if (ret)
- *ret = i;
-
- return buf;
-}
-
-static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
-{
- FILE *output = stat_config.output;
- int nthreads = thread_map__nr(counter->threads);
- int ncpus = cpu_map__nr(counter->cpus);
- int thread, sorted_threads, id;
- struct perf_aggr_thread_value *buf;
-
- buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads);
- if (!buf) {
- perror("cannot sort aggr thread");
- return;
- }
-
- for (thread = 0; thread < sorted_threads; thread++) {
- if (prefix)
- fprintf(output, "%s", prefix);
-
- id = buf[thread].id;
- if (stat_config.stats)
- printout(id, 0, buf[thread].counter, buf[thread].uval,
- prefix, buf[thread].run, buf[thread].ena, 1.0,
- &stat_config.stats[id]);
- else
- printout(id, 0, buf[thread].counter, buf[thread].uval,
- prefix, buf[thread].run, buf[thread].ena, 1.0,
- &rt_stat);
- fputc('\n', output);
- }
-
- free(buf);
-}
-
-struct caggr_data {
- double avg, avg_enabled, avg_running;
-};
-
-static void counter_aggr_cb(struct perf_evsel *counter, void *data,
- bool first __maybe_unused)
-{
- struct caggr_data *cd = data;
- struct perf_stat_evsel *ps = counter->stats;
-
- cd->avg += avg_stats(&ps->res_stats[0]);
- cd->avg_enabled += avg_stats(&ps->res_stats[1]);
- cd->avg_running += avg_stats(&ps->res_stats[2]);
-}
-
-/*
- * Print out the results of a single counter:
- * aggregated counts in system-wide mode
- */
-static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
-{
- FILE *output = stat_config.output;
- double uval;
- struct caggr_data cd = { .avg = 0.0 };
-
- if (!collect_data(counter, counter_aggr_cb, &cd))
- return;
-
- if (prefix && !metric_only)
- fprintf(output, "%s", prefix);
-
- uval = cd.avg * counter->scale;
- printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
- cd.avg, &rt_stat);
- if (!metric_only)
- fprintf(output, "\n");
-}
-
-static void counter_cb(struct perf_evsel *counter, void *data,
- bool first __maybe_unused)
-{
- struct aggr_data *ad = data;
-
- ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
- ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
- ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
-}
-
-/*
- * Print out the results of a single counter:
- * does not use aggregated count in system-wide
- */
-static void print_counter(struct perf_evsel *counter, char *prefix)
-{
- FILE *output = stat_config.output;
- u64 ena, run, val;
- double uval;
- int cpu;
-
- for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
- struct aggr_data ad = { .cpu = cpu };
-
- if (!collect_data(counter, counter_cb, &ad))
- return;
- val = ad.val;
- ena = ad.ena;
- run = ad.run;
-
- if (prefix)
- fprintf(output, "%s", prefix);
-
- uval = val * counter->scale;
- printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
- &rt_stat);
-
- fputc('\n', output);
- }
-}
-
-static void print_no_aggr_metric(char *prefix)
-{
- int cpu;
- int nrcpus = 0;
- struct perf_evsel *counter;
- u64 ena, run, val;
- double uval;
-
- nrcpus = evsel_list->cpus->nr;
- for (cpu = 0; cpu < nrcpus; cpu++) {
- bool first = true;
-
- if (prefix)
- fputs(prefix, stat_config.output);
- evlist__for_each_entry(evsel_list, counter) {
- if (is_duration_time(counter))
- continue;
- if (first) {
- aggr_printout(counter, cpu, 0);
- first = false;
- }
- val = perf_counts(counter->counts, cpu, 0)->val;
- ena = perf_counts(counter->counts, cpu, 0)->ena;
- run = perf_counts(counter->counts, cpu, 0)->run;
-
- uval = val * counter->scale;
- printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
- &rt_stat);
- }
- fputc('\n', stat_config.output);
- }
-}
-
-static int aggr_header_lens[] = {
- [AGGR_CORE] = 18,
- [AGGR_SOCKET] = 12,
- [AGGR_NONE] = 6,
- [AGGR_THREAD] = 24,
- [AGGR_GLOBAL] = 0,
-};
-
-static const char *aggr_header_csv[] = {
- [AGGR_CORE] = "core,cpus,",
- [AGGR_SOCKET] = "socket,cpus",
- [AGGR_NONE] = "cpu,",
- [AGGR_THREAD] = "comm-pid,",
- [AGGR_GLOBAL] = ""
-};
-
-static void print_metric_headers(const char *prefix, bool no_indent)
-{
- struct perf_stat_output_ctx out;
- struct perf_evsel *counter;
- struct outstate os = {
- .fh = stat_config.output
- };
-
- if (prefix)
- fprintf(stat_config.output, "%s", prefix);
-
- if (!csv_output && !no_indent)
- fprintf(stat_config.output, "%*s",
- aggr_header_lens[stat_config.aggr_mode], "");
- if (csv_output) {
- if (stat_config.interval)
- fputs("time,", stat_config.output);
- fputs(aggr_header_csv[stat_config.aggr_mode],
- stat_config.output);
- }
-
- /* Print metrics headers only */
- evlist__for_each_entry(evsel_list, counter) {
- if (is_duration_time(counter))
- continue;
- os.evsel = counter;
- out.ctx = &os;
- out.print_metric = print_metric_header;
- out.new_line = new_line_metric;
- out.force_header = true;
- os.evsel = counter;
- perf_stat__print_shadow_stats(counter, 0,
- 0,
- &out,
- &metric_events,
- &rt_stat);
- }
- fputc('\n', stat_config.output);
-}
-
-static void print_interval(char *prefix, struct timespec *ts)
-{
- FILE *output = stat_config.output;
- static int num_print_interval;
-
- if (interval_clear)
- puts(CONSOLE_CLEAR);
-
- sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
-
- if ((num_print_interval == 0 && !csv_output) || interval_clear) {
- switch (stat_config.aggr_mode) {
- case AGGR_SOCKET:
- fprintf(output, "# time socket cpus");
- if (!metric_only)
- fprintf(output, " counts %*s events\n", unit_width, "unit");
- break;
- case AGGR_CORE:
- fprintf(output, "# time core cpus");
- if (!metric_only)
- fprintf(output, " counts %*s events\n", unit_width, "unit");
- break;
- case AGGR_NONE:
- fprintf(output, "# time CPU ");
- if (!metric_only)
- fprintf(output, " counts %*s events\n", unit_width, "unit");
- break;
- case AGGR_THREAD:
- fprintf(output, "# time comm-pid");
- if (!metric_only)
- fprintf(output, " counts %*s events\n", unit_width, "unit");
- break;
- case AGGR_GLOBAL:
- default:
- fprintf(output, "# time");
- if (!metric_only)
- fprintf(output, " counts %*s events\n", unit_width, "unit");
- case AGGR_UNSET:
- break;
- }
- }
-
- if ((num_print_interval == 0 || interval_clear) && metric_only)
- print_metric_headers(" ", true);
- if (++num_print_interval == 25)
- num_print_interval = 0;
-}
-
-static void print_header(int argc, const char **argv)
-{
- FILE *output = stat_config.output;
- int i;
-
- fflush(stdout);
-
- if (!csv_output) {
- fprintf(output, "\n");
- fprintf(output, " Performance counter stats for ");
- if (target.system_wide)
- fprintf(output, "\'system wide");
- else if (target.cpu_list)
- fprintf(output, "\'CPU(s) %s", target.cpu_list);
- else if (!target__has_task(&target)) {
- fprintf(output, "\'%s", argv ? argv[0] : "pipe");
- for (i = 1; argv && (i < argc); i++)
- fprintf(output, " %s", argv[i]);
- } else if (target.pid)
- fprintf(output, "process id \'%s", target.pid);
- else
- fprintf(output, "thread id \'%s", target.tid);
-
- fprintf(output, "\'");
- if (run_count > 1)
- fprintf(output, " (%d runs)", run_count);
- fprintf(output, ":\n\n");
- }
-}
-
-static int get_precision(double num)
-{
- if (num > 1)
- return 0;
-
- return lround(ceil(-log10(num)));
-}
-
-static void print_table(FILE *output, int precision, double avg)
-{
- char tmp[64];
- int idx, indent = 0;
-
- scnprintf(tmp, 64, " %17.*f", precision, avg);
- while (tmp[indent] == ' ')
- indent++;
-
- fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
-
- for (idx = 0; idx < run_count; idx++) {
- double run = (double) walltime_run[idx] / NSEC_PER_SEC;
- int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
-
- fprintf(output, " %17.*f (%+.*f) ",
- precision, run, precision, run - avg);
-
- for (h = 0; h < n; h++)
- fprintf(output, "#");
-
- fprintf(output, "\n");
- }
-
- fprintf(output, "\n%*s# Final result:\n", indent, "");
-}
-
-static double timeval2double(struct timeval *t)
-{
- return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
-}
-
-static void print_footer(void)
-{
- double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
- FILE *output = stat_config.output;
- int n;
-
- if (!null_run)
- fprintf(output, "\n");
-
- if (run_count == 1) {
- fprintf(output, " %17.9f seconds time elapsed", avg);
-
- if (ru_display) {
- double ru_utime = timeval2double(&ru_data.ru_utime);
- double ru_stime = timeval2double(&ru_data.ru_stime);
-
- fprintf(output, "\n\n");
- fprintf(output, " %17.9f seconds user\n", ru_utime);
- fprintf(output, " %17.9f seconds sys\n", ru_stime);
- }
- } else {
- double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
- /*
- * Display at most 2 more significant
- * digits than the stddev inaccuracy.
- */
- int precision = get_precision(sd) + 2;
-
- if (walltime_run_table)
- print_table(output, precision, avg);
-
- fprintf(output, " %17.*f +- %.*f seconds time elapsed",
- precision, avg, precision, sd);
-
- print_noise_pct(sd, avg);
- }
- fprintf(output, "\n\n");
-
- if (print_free_counters_hint &&
- sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
- n > 0)
- fprintf(output,
-"Some events weren't counted. Try disabling the NMI watchdog:\n"
-" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
-" perf stat ...\n"
-" echo 1 > /proc/sys/kernel/nmi_watchdog\n");
-
- if (print_mixed_hw_group_error)
- fprintf(output,
- "The events in group usually have to be from "
- "the same PMU. Try reorganizing the group.\n");
-}
-
static void print_counters(struct timespec *ts, int argc, const char **argv)
{
- int interval = stat_config.interval;
- struct perf_evsel *counter;
- char buf[64], *prefix = NULL;
-
/* Do not print anything if we record to the pipe. */
if (STAT_RECORD && perf_stat.data.is_pipe)
return;
- if (interval)
- print_interval(prefix = buf, ts);
- else
- print_header(argc, argv);
-
- if (metric_only) {
- static int num_print_iv;
-
- if (num_print_iv == 0 && !interval)
- print_metric_headers(prefix, false);
- if (num_print_iv++ == 25)
- num_print_iv = 0;
- if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
- fprintf(stat_config.output, "%s", prefix);
- }
-
- switch (stat_config.aggr_mode) {
- case AGGR_CORE:
- case AGGR_SOCKET:
- print_aggr(prefix);
- break;
- case AGGR_THREAD:
- evlist__for_each_entry(evsel_list, counter) {
- if (is_duration_time(counter))
- continue;
- print_aggr_thread(counter, prefix);
- }
- break;
- case AGGR_GLOBAL:
- evlist__for_each_entry(evsel_list, counter) {
- if (is_duration_time(counter))
- continue;
- print_counter_aggr(counter, prefix);
- }
- if (metric_only)
- fputc('\n', stat_config.output);
- break;
- case AGGR_NONE:
- if (metric_only)
- print_no_aggr_metric(prefix);
- else {
- evlist__for_each_entry(evsel_list, counter) {
- if (is_duration_time(counter))
- continue;
- print_counter(counter, prefix);
- }
- }
- break;
- case AGGR_UNSET:
- default:
- break;
- }
-
- if (!interval && !csv_output)
- print_footer();
-
- fflush(stat_config.output);
+ perf_evlist__print_counters(evsel_list, &stat_config, &target,
+ ts, argc, argv);
}
static volatile int signr = -1;
@@ -1939,10 +1020,16 @@
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;
}
@@ -1950,7 +1037,7 @@
const char *s __maybe_unused, int unset)
{
force_metric_only = true;
- metric_only = !unset;
+ stat_config.metric_only = !unset;
return 0;
}
@@ -1958,7 +1045,30 @@
const char *str,
int unset __maybe_unused)
{
- return metricgroup__parse_groups(opt, str, &metric_events);
+ 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\n");
+ return -1;
+ }
+
+ return parse_cgroups(opt, str, unset);
}
static struct option stat_options[] = {
@@ -1969,7 +1079,7 @@
parse_events_option),
OPT_CALLBACK(0, "filter", &evsel_list, "filter",
"event filter", parse_filter),
- OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+ 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"),
@@ -1979,14 +1089,15 @@
"system-wide collection from all CPUs"),
OPT_BOOLEAN('g', "group", &group,
"put the counters into a counter group"),
- OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
+ 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", &run_count,
+ OPT_INTEGER('r', "repeat", &stat_config.run_count,
"repeat command and print average + stddev (max: 100, forever: 0)"),
- OPT_BOOLEAN(0, "table", &walltime_run_table,
+ OPT_BOOLEAN(0, "table", &stat_config.walltime_run_table,
"display details about each run (only with -r option)"),
- OPT_BOOLEAN('n', "null", &null_run,
+ 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"),
@@ -1999,11 +1110,13 @@
"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", &no_merge, "Do not merge identical named events"),
- OPT_STRING('x', "field-separator", &csv_sep, "separator",
+ 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_cgroups),
+ "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,
@@ -2017,20 +1130,28 @@
"(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", &interval_clear,
+ 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_UINTEGER('D', "delay", &initial_delay,
- "ms to wait before starting measurement after program start"),
- OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
+ 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,
@@ -2038,34 +1159,57 @@
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).\n"
+ "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n"
+ "\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 cpu_map *map, int cpu)
+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_core(struct cpu_map *map, int cpu)
+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 cpu_map__get_max(struct cpu_map *map)
+static int perf_stat__get_node(struct perf_stat_config *config __maybe_unused,
+ struct perf_cpu_map *map, int cpu)
{
- int i, max = -1;
-
- for (i = 0; i < map->nr; i++) {
- if (map->map[i] > max)
- max = map->map[i];
- }
-
- return max;
+ return cpu_map__get_node(map, cpu, NULL);
}
-static struct cpu_map *cpus_aggr_map;
-
-static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int idx)
+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;
@@ -2074,20 +1218,46 @@
cpu = map->map[idx];
- if (cpus_aggr_map->map[cpu] == -1)
- cpus_aggr_map->map[cpu] = get_id(map, idx);
+ if (config->cpus_aggr_map->map[cpu] == -1)
+ config->cpus_aggr_map->map[cpu] = get_id(config, map, idx);
- return cpus_aggr_map->map[cpu];
+ return config->cpus_aggr_map->map[cpu];
}
-static int perf_stat__get_socket_cached(struct cpu_map *map, int idx)
+static int perf_stat__get_socket_cached(struct perf_stat_config *config,
+ struct perf_cpu_map *map, int idx)
{
- return perf_stat__get_aggr(perf_stat__get_socket, map, idx);
+ return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
}
-static int perf_stat__get_core_cached(struct cpu_map *map, int 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(perf_stat__get_core, map, 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)
@@ -2096,20 +1266,43 @@
switch (stat_config.aggr_mode) {
case AGGR_SOCKET:
- if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) {
+ if (cpu_map__build_socket_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
perror("cannot build socket map");
return -1;
}
- aggr_get_id = perf_stat__get_socket_cached;
+ 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->cpus, &aggr_map)) {
+ if (cpu_map__build_core_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
perror("cannot build core map");
return -1;
}
- aggr_get_id = perf_stat__get_core_cached;
+ 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:
@@ -2122,20 +1315,20 @@
* taking the highest cpu number to be the size of
* the aggregation translate cpumap.
*/
- nr = cpu_map__get_max(evsel_list->cpus);
- cpus_aggr_map = cpu_map__empty_new(nr + 1);
- return cpus_aggr_map ? 0 : -ENOMEM;
+ 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)
{
- cpu_map__put(aggr_map);
- cpu_map__put(cpus_aggr_map);
- aggr_map = NULL;
- cpus_aggr_map = NULL;
+ 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 cpu_map *map, int idx)
+static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *map, int idx)
{
int cpu;
@@ -2150,7 +1343,7 @@
return cpu;
}
-static int perf_env__get_socket(struct cpu_map *map, int idx, void *data)
+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);
@@ -2158,46 +1351,112 @@
return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
}
-static int perf_env__get_core(struct cpu_map *map, int idx, void *data)
+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.\n"))
+ return -1;
+
+ if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
+ 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) {
- int socket_id = env->cpu[cpu].socket_id;
-
/*
- * Encode socket in upper 16 bits
- * core_id is relative to socket, and
+ * 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 + core id.
+ * socket + die id + core id
*/
- core = (socket_id << 16) | (env->cpu[cpu].core_id & 0xffff);
+ if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
+ return -1;
+
+ if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
+ return -1;
+
+ if (WARN_ONCE(env->cpu[cpu].core_id >> 16, "The core id number is too big.\n"))
+ 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__build_socket_map(struct perf_env *env, struct cpu_map *cpus,
- struct cpu_map **sockp)
+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_core_map(struct perf_env *env, struct cpu_map *cpus,
- struct cpu_map **corep)
+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_stat__get_socket_file(struct cpu_map *map, int idx)
+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 cpu_map *map, int idx)
+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)
@@ -2206,18 +1465,32 @@
switch (stat_config.aggr_mode) {
case AGGR_SOCKET:
- if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) {
+ if (perf_env__build_socket_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
perror("cannot build socket map");
return -1;
}
- aggr_get_id = perf_stat__get_socket_file;
+ 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->cpus, &aggr_map)) {
+ if (perf_env__build_core_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
perror("cannot build core map");
return -1;
}
- aggr_get_id = perf_stat__get_core_file;
+ 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:
@@ -2228,55 +1501,6 @@
}
return 0;
-}
-
-static int topdown_filter_events(const char **attr, char **str, bool use_group)
-{
- int off = 0;
- int i;
- int len = 0;
- char *s;
-
- for (i = 0; attr[i]; i++) {
- if (pmu_have_event("cpu", attr[i])) {
- len += strlen(attr[i]) + 1;
- attr[i - off] = attr[i];
- } else
- off++;
- }
- attr[i - off] = NULL;
-
- *str = malloc(len + 1 + 2);
- if (!*str)
- return -1;
- s = *str;
- if (i - off == 0) {
- *s = 0;
- return 0;
- }
- if (use_group)
- *s++ = '{';
- for (i = 0; attr[i]; i++) {
- strcpy(s, attr[i]);
- s += strlen(s);
- *s++ = ',';
- }
- if (use_group) {
- s[-1] = '}';
- *s = 0;
- } else
- s[-1] = 0;
- return 0;
-}
-
-__weak bool arch_topdown_check_group(bool *warn)
-{
- *warn = false;
- return false;
-}
-
-__weak void arch_topdown_group_warn(void)
-{
}
/*
@@ -2401,9 +1625,10 @@
struct parse_events_error errinfo;
/* Set attrs if no event is selected and !null_run: */
- if (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
@@ -2414,7 +1639,9 @@
struct option opt = { .value = &evsel_list };
return metricgroup__parse_groups(&opt, "transaction",
- &metric_events);
+ stat_config.metric_no_group,
+ stat_config.metric_no_merge,
+ &stat_config.metric_events);
}
if (pmu_have_event("cpu", "cycles-ct") &&
@@ -2452,7 +1679,7 @@
if (pmu_have_event("msr", "aperf") &&
pmu_have_event("msr", "smi")) {
if (!force_metric_only)
- metric_only = true;
+ stat_config.metric_only = true;
err = parse_events(evsel_list, smi_cost_attrs, &errinfo);
} else {
fprintf(stderr, "To measure SMI cost, it needs "
@@ -2461,6 +1688,7 @@
return -1;
}
if (err) {
+ parse_events_print_error(&errinfo, smi_cost_attrs);
fprintf(stderr, "Cannot set up SMI cost events\n");
return -1;
}
@@ -2470,6 +1698,24 @@
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\n");
+ 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.\n"
+ "Please print the result regularly, e.g. -I1000\n");
+ }
+ goto setup_metrics;
+ }
+
+ zfree(&str);
if (stat_config.aggr_mode != AGGR_GLOBAL &&
stat_config.aggr_mode != AGGR_CORE) {
@@ -2482,8 +1728,6 @@
return -1;
}
- if (!force_metric_only)
- metric_only = true;
if (topdown_filter_events(topdown_attrs, &str,
arch_topdown_check_group(&warn)) < 0) {
pr_err("Out of memory\n");
@@ -2492,6 +1736,7 @@
if (topdown_attrs[0] && str) {
if (warn)
arch_topdown_group_warn();
+setup_metrics:
err = parse_events(evsel_list, str, &errinfo);
if (err) {
fprintf(stderr,
@@ -2508,23 +1753,21 @@
free(str);
}
- if (!evsel_list->nr_entries) {
+ if (!evsel_list->core.nr_entries) {
if (target__has_cpu(&target))
default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
- if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
+ if (evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
return -1;
if (pmu_have_event("cpu", "stalled-cycles-frontend")) {
- if (perf_evlist__add_default_attrs(evsel_list,
- frontend_attrs) < 0)
+ if (evlist__add_default_attrs(evsel_list, frontend_attrs) < 0)
return -1;
}
if (pmu_have_event("cpu", "stalled-cycles-backend")) {
- if (perf_evlist__add_default_attrs(evsel_list,
- backend_attrs) < 0)
+ if (evlist__add_default_attrs(evsel_list, backend_attrs) < 0)
return -1;
}
- if (perf_evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
+ if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
return -1;
}
@@ -2534,21 +1777,21 @@
return 0;
/* Append detailed run extra attributes: */
- if (perf_evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)
+ 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 (perf_evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)
+ 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 perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
+ return evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
}
static const char * const stat_record_usage[] = {
@@ -2563,6 +1806,7 @@
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);
@@ -2578,17 +1822,17 @@
PARSE_OPT_STOP_AT_NON_OPTION);
if (output_name)
- data->file.path = output_name;
+ data->path = output_name;
- if (run_count != 1 || forever) {
+ if (stat_config.run_count != 1 || forever) {
pr_err("Cannot use -r option with perf stat record.\n");
return -1;
}
session = perf_session__new(data, false, NULL);
- if (session == NULL) {
- pr_err("Perf session creation failed.\n");
- return -1;
+ if (IS_ERR(session)) {
+ pr_err("Perf session creation failed\n");
+ return PTR_ERR(session);
}
init_features(session);
@@ -2599,12 +1843,11 @@
return argc;
}
-static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
- union perf_event *event,
- struct perf_session *session)
+static int process_stat_round_event(struct perf_session *session,
+ union perf_event *event)
{
- struct stat_round_event *stat_round = &event->stat_round;
- struct perf_evsel *counter;
+ 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;
@@ -2626,15 +1869,15 @@
}
static
-int process_stat_config_event(struct perf_tool *tool,
- union perf_event *event,
- struct perf_session *session __maybe_unused)
+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 (cpu_map__empty(st->cpus)) {
+ if (perf_cpu_map__empty(st->cpus)) {
if (st->aggr_mode != AGGR_UNSET)
pr_warning("warning: processing task data, aggregation mode not set\n");
return 0;
@@ -2659,7 +1902,7 @@
if (WARN_ONCE(st->maps_allocated, "stats double allocation\n"))
return -EINVAL;
- perf_evlist__set_maps(evsel_list, st->cpus, st->threads);
+ perf_evlist__set_maps(&evsel_list->core, st->cpus, st->threads);
if (perf_evlist__alloc_stats(evsel_list, true))
return -ENOMEM;
@@ -2669,10 +1912,10 @@
}
static
-int process_thread_map_event(struct perf_tool *tool,
- union perf_event *event,
- struct perf_session *session __maybe_unused)
+int process_thread_map_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);
if (st->threads) {
@@ -2688,12 +1931,12 @@
}
static
-int process_cpu_map_event(struct perf_tool *tool,
- union perf_event *event,
- struct perf_session *session __maybe_unused)
+int process_cpu_map_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);
- struct cpu_map *cpus;
+ struct perf_cpu_map *cpus;
if (st->cpus) {
pr_warning("Extra cpu map event, ignoring.\n");
@@ -2706,35 +1949,6 @@
st->cpus = cpus;
return set_maps(st);
-}
-
-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]);
-
- free(config->stats);
}
static const char * const stat_report_usage[] = {
@@ -2762,8 +1976,12 @@
OPT_STRING('i', "input", &input_name, "file", "input file name"),
OPT_SET_UINT(0, "per-socket", &perf_stat.aggr_mode,
"aggregate counts per processor socket", AGGR_SOCKET),
+ OPT_SET_UINT(0, "per-die", &perf_stat.aggr_mode,
+ "aggregate counts per processor die", AGGR_DIE),
OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode,
"aggregate counts per physical processor core", AGGR_CORE),
+ OPT_SET_UINT(0, "per-node", &perf_stat.aggr_mode,
+ "aggregate counts per numa node", AGGR_NODE),
OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode,
"disable CPU count aggregation", AGGR_NONE),
OPT_END()
@@ -2780,12 +1998,12 @@
input_name = "perf.data";
}
- perf_stat.data.file.path = input_name;
- perf_stat.data.mode = PERF_DATA_MODE_READ;
+ perf_stat.data.path = input_name;
+ perf_stat.data.mode = PERF_DATA_MODE_READ;
session = perf_session__new(&perf_stat.data, false, &perf_stat.tool);
- if (session == NULL)
- return -1;
+ if (IS_ERR(session))
+ return PTR_ERR(session);
perf_stat.session = session;
stat_config.output = stderr;
@@ -2816,14 +2034,16 @@
if (!forks)
target.system_wide = true;
else {
- struct perf_evsel *counter;
+ struct evsel *counter;
evlist__for_each_entry(evsel_list, counter) {
- if (!counter->system_wide)
+ if (!counter->core.system_wide &&
+ strcmp(counter->name, "duration_time")) {
return;
+ }
}
- if (evsel_list->nr_entries)
+ if (evsel_list->core.nr_entries)
target.system_wide = true;
}
}
@@ -2842,7 +2062,7 @@
setlocale(LC_ALL, "");
- evsel_list = perf_evlist__new();
+ evsel_list = evlist__new();
if (evsel_list == NULL)
return -ENOMEM;
@@ -2859,12 +2079,12 @@
perf_stat__collect_metric_expr(evsel_list);
perf_stat__init_shadow_stats();
- if (csv_sep) {
- csv_output = true;
- if (!strcmp(csv_sep, "\\t"))
- csv_sep = "\t";
+ if (stat_config.csv_sep) {
+ stat_config.csv_output = true;
+ if (!strcmp(stat_config.csv_sep, "\\t"))
+ stat_config.csv_sep = "\t";
} else
- csv_sep = DEFAULT_SEPARATOR;
+ stat_config.csv_sep = DEFAULT_SEPARATOR;
if (argc && !strncmp(argv[0], "rec", 3)) {
argc = __cmd_record(argc, argv);
@@ -2889,17 +2109,17 @@
goto out;
}
- if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+ if (stat_config.metric_only && stat_config.aggr_mode == AGGR_THREAD) {
fprintf(stderr, "--metric-only is not supported with --per-thread\n");
goto out;
}
- if (metric_only && run_count > 1) {
+ if (stat_config.metric_only && stat_config.run_count > 1) {
fprintf(stderr, "--metric-only is not supported with -r\n");
goto out;
}
- if (walltime_run_table && run_count <= 1) {
+ if (stat_config.walltime_run_table && stat_config.run_count <= 1) {
fprintf(stderr, "--table is only supported with -r\n");
parse_options_usage(stat_usage, stat_options, "r", 1);
parse_options_usage(NULL, stat_options, "table", 0);
@@ -2937,7 +2157,7 @@
/*
* let the spreadsheet do the pretty-printing
*/
- if (csv_output) {
+ if (stat_config.csv_output) {
/* User explicitly passed -B? */
if (big_num_opt == 1) {
fprintf(stderr, "-B option not supported with -x\n");
@@ -2945,9 +2165,9 @@
parse_options_usage(NULL, stat_options, "x", 1);
goto out;
} else /* Nope, so disable big number formatting */
- big_num = false;
+ stat_config.big_num = false;
} else if (big_num_opt == 0) /* User passed --no-big-num */
- big_num = false;
+ stat_config.big_num = false;
setup_system_wide(argc);
@@ -2955,21 +2175,21 @@
* Display user/system times only for single
* run and when there's specified tracee.
*/
- if ((run_count == 1) && target__none(&target))
- ru_display = true;
+ if ((stat_config.run_count == 1) && target__none(&target))
+ stat_config.ru_display = true;
- if (run_count < 0) {
+ if (stat_config.run_count < 0) {
pr_err("Run count must be a positive number\n");
parse_options_usage(stat_usage, stat_options, "r", 1);
goto out;
- } else if (run_count == 0) {
+ } else if (stat_config.run_count == 0) {
forever = true;
- run_count = 1;
+ stat_config.run_count = 1;
}
- if (walltime_run_table) {
- walltime_run = zalloc(run_count * sizeof(walltime_run[0]));
- if (!walltime_run) {
+ if (stat_config.walltime_run_table) {
+ stat_config.walltime_run = zalloc(stat_config.run_count * sizeof(stat_config.walltime_run[0]));
+ if (!stat_config.walltime_run) {
pr_err("failed to setup -r option");
goto out;
}
@@ -3006,6 +2226,19 @@
if (add_default_attributes())
goto out;
+ if (stat_config.cgroup_list) {
+ if (nr_cgroups > 0) {
+ pr_err("--cgroup and --for-each-cgroup cannot be used together\n");
+ parse_options_usage(stat_usage, stat_options, "G", 1);
+ parse_options_usage(NULL, stat_options, "for-each-cgroup", 0);
+ goto out;
+ }
+
+ if (evlist__expand_cgroup(evsel_list, stat_config.cgroup_list,
+ &stat_config.metric_events, true) < 0)
+ goto out;
+ }
+
target__validate(&target);
if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
@@ -3024,19 +2257,24 @@
goto out;
}
+ evlist__check_cpu_maps(evsel_list);
+
/*
* Initialize thread_map with comm names,
* so we could print it out on output.
*/
if (stat_config.aggr_mode == AGGR_THREAD) {
- thread_map__read_comms(evsel_list->threads);
+ thread_map__read_comms(evsel_list->core.threads);
if (target.system_wide) {
if (runtime_stat_new(&stat_config,
- thread_map__nr(evsel_list->threads))) {
+ perf_thread_map__nr(evsel_list->core.threads))) {
goto out;
}
}
}
+
+ if (stat_config.aggr_mode == AGGR_NODE)
+ cpu__setup_cpunode_map();
if (stat_config.times && interval)
interval_count = true;
@@ -3072,6 +2310,17 @@
goto out;
/*
+ * Set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
+ * while avoiding that older tools show confusing messages.
+ *
+ * However for pipe sessions we need to keep it zero,
+ * because script's perf_evsel__check_attr is triggered
+ * by attr->sample_type != 0, and we can't run it on
+ * stat sessions.
+ */
+ stat_config.identifier = !(STAT_RECORD && perf_stat.data.is_pipe);
+
+ /*
* We dont want to block the signals - that would cause
* child tasks to inherit that and Ctrl-C would not work.
* What we want is for Ctrl-C to work in the exec()-ed
@@ -3084,9 +2333,12 @@
signal(SIGALRM, skip_signal);
signal(SIGABRT, skip_signal);
+ if (evlist__initialize_ctlfd(evsel_list, stat_config.ctl_fd, stat_config.ctl_fd_ack))
+ goto out;
+
status = 0;
- for (run_idx = 0; forever || run_idx < run_count; run_idx++) {
- if (run_count != 1 && verbose > 0)
+ for (run_idx = 0; forever || run_idx < stat_config.run_count; run_idx++) {
+ if (stat_config.run_count != 1 && verbose > 0)
fprintf(output, "[ perf stat: executing run #%d ... ]\n",
run_idx + 1);
@@ -3100,8 +2352,10 @@
}
}
- if (!forever && status != -1 && !interval)
+ if (!forever && status != -1 && (!interval || stat_config.summary))
print_counters(NULL, argc, argv);
+
+ evlist__finalize_ctlfd(evsel_list);
if (STAT_RECORD) {
/*
@@ -3135,20 +2389,23 @@
perf_session__write_header(perf_stat.session, evsel_list, fd, true);
}
+ evlist__close(evsel_list);
perf_session__delete(perf_stat.session);
}
perf_stat__exit_aggr_mode();
perf_evlist__free_stats(evsel_list);
out:
- free(walltime_run);
+ zfree(&stat_config.walltime_run);
if (smi_cost && smi_reset)
sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
- perf_evlist__delete(evsel_list);
+ evlist__delete(evsel_list);
+ metricgroup__rblist_exit(&stat_config.metric_events);
runtime_stat_delete(&stat_config);
+ evlist__close_control(stat_config.ctl_fd, stat_config.ctl_fd_ack, &stat_config.ctl_fd_close);
return status;
}
--
Gitblit v1.6.2