From 6778948f9de86c3cfaf36725a7c87dcff9ba247f Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 08:20:59 +0000
Subject: [PATCH] kernel_5.10 no rt
---
kernel/tools/perf/util/stat.c | 257 +++++++++++++++++++++++++++++++++++++--------------
1 files changed, 186 insertions(+), 71 deletions(-)
diff --git a/kernel/tools/perf/util/stat.c b/kernel/tools/perf/util/stat.c
index b254bee..bd0decd 100644
--- a/kernel/tools/perf/util/stat.c
+++ b/kernel/tools/perf/util/stat.c
@@ -2,10 +2,18 @@
#include <errno.h>
#include <inttypes.h>
#include <math.h>
+#include <string.h>
+#include "counts.h"
+#include "cpumap.h"
+#include "debug.h"
+#include "header.h"
#include "stat.h"
+#include "session.h"
+#include "target.h"
#include "evlist.h"
#include "evsel.h"
#include "thread_map.h"
+#include <linux/zalloc.h>
void update_stats(struct stats *stats, u64 val)
{
@@ -67,7 +75,7 @@
return pct;
}
-bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+bool __perf_evsel_stat__is(struct evsel *evsel,
enum perf_stat_evsel_id id)
{
struct perf_stat_evsel *ps = evsel->stats;
@@ -87,12 +95,16 @@
ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
+ ID(TOPDOWN_RETIRING, topdown-retiring),
+ ID(TOPDOWN_BAD_SPEC, topdown-bad-spec),
+ ID(TOPDOWN_FE_BOUND, topdown-fe-bound),
+ ID(TOPDOWN_BE_BOUND, topdown-be-bound),
ID(SMI_NUM, msr/smi/),
ID(APERF, msr/aperf/),
};
#undef ID
-static void perf_stat_evsel_id_init(struct perf_evsel *evsel)
+static void perf_stat_evsel_id_init(struct evsel *evsel)
{
struct perf_stat_evsel *ps = evsel->stats;
int i;
@@ -100,14 +112,14 @@
/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
- if (!strcmp(perf_evsel__name(evsel), id_str[i])) {
+ if (!strcmp(evsel__name(evsel), id_str[i])) {
ps->id = i;
break;
}
}
}
-static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+static void evsel__reset_stat_priv(struct evsel *evsel)
{
int i;
struct perf_stat_evsel *ps = evsel->stats;
@@ -118,26 +130,25 @@
perf_stat_evsel_id_init(evsel);
}
-static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+static int evsel__alloc_stat_priv(struct evsel *evsel)
{
evsel->stats = zalloc(sizeof(struct perf_stat_evsel));
if (evsel->stats == NULL)
return -ENOMEM;
- perf_evsel__reset_stat_priv(evsel);
+ evsel__reset_stat_priv(evsel);
return 0;
}
-static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+static void evsel__free_stat_priv(struct evsel *evsel)
{
struct perf_stat_evsel *ps = evsel->stats;
if (ps)
- free(ps->group_data);
+ zfree(&ps->group_data);
zfree(&evsel->stats);
}
-static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
- int ncpus, int nthreads)
+static int evsel__alloc_prev_raw_counts(struct evsel *evsel, int ncpus, int nthreads)
{
struct perf_counts *counts;
@@ -148,40 +159,37 @@
return counts ? 0 : -ENOMEM;
}
-static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+static void evsel__free_prev_raw_counts(struct evsel *evsel)
{
perf_counts__delete(evsel->prev_raw_counts);
evsel->prev_raw_counts = NULL;
}
-static void perf_evsel__reset_prev_raw_counts(struct perf_evsel *evsel)
+static void evsel__reset_prev_raw_counts(struct evsel *evsel)
{
- if (evsel->prev_raw_counts) {
- evsel->prev_raw_counts->aggr.val = 0;
- evsel->prev_raw_counts->aggr.ena = 0;
- evsel->prev_raw_counts->aggr.run = 0;
- }
+ if (evsel->prev_raw_counts)
+ perf_counts__reset(evsel->prev_raw_counts);
}
-static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
{
- int ncpus = perf_evsel__nr_cpus(evsel);
- int nthreads = thread_map__nr(evsel->threads);
+ int ncpus = evsel__nr_cpus(evsel);
+ int nthreads = perf_thread_map__nr(evsel->core.threads);
- if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
- perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
- (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+ if (evsel__alloc_stat_priv(evsel) < 0 ||
+ evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
+ (alloc_raw && evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
return -ENOMEM;
return 0;
}
-int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
+int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
- if (perf_evsel__alloc_stats(evsel, alloc_raw))
+ if (evsel__alloc_stats(evsel, alloc_raw))
goto out_free;
}
@@ -192,46 +200,90 @@
return -1;
}
-void perf_evlist__free_stats(struct perf_evlist *evlist)
+void perf_evlist__free_stats(struct evlist *evlist)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
- perf_evsel__free_stat_priv(evsel);
- perf_evsel__free_counts(evsel);
- perf_evsel__free_prev_raw_counts(evsel);
+ evsel__free_stat_priv(evsel);
+ evsel__free_counts(evsel);
+ evsel__free_prev_raw_counts(evsel);
}
}
-void perf_evlist__reset_stats(struct perf_evlist *evlist)
+void perf_evlist__reset_stats(struct evlist *evlist)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
- perf_evsel__reset_stat_priv(evsel);
- perf_evsel__reset_counts(evsel);
+ evsel__reset_stat_priv(evsel);
+ evsel__reset_counts(evsel);
}
}
-void perf_evlist__reset_prev_raw_counts(struct perf_evlist *evlist)
+void perf_evlist__reset_prev_raw_counts(struct evlist *evlist)
{
- struct perf_evsel *evsel;
+ struct evsel *evsel;
evlist__for_each_entry(evlist, evsel)
- perf_evsel__reset_prev_raw_counts(evsel);
+ evsel__reset_prev_raw_counts(evsel);
}
-static void zero_per_pkg(struct perf_evsel *counter)
+static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel)
+{
+ int ncpus = evsel__nr_cpus(evsel);
+ int nthreads = perf_thread_map__nr(evsel->core.threads);
+
+ for (int thread = 0; thread < nthreads; thread++) {
+ for (int cpu = 0; cpu < ncpus; cpu++) {
+ *perf_counts(evsel->counts, cpu, thread) =
+ *perf_counts(evsel->prev_raw_counts, cpu,
+ thread);
+ }
+ }
+
+ evsel->counts->aggr = evsel->prev_raw_counts->aggr;
+}
+
+void perf_evlist__copy_prev_raw_counts(struct evlist *evlist)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(evlist, evsel)
+ perf_evsel__copy_prev_raw_counts(evsel);
+}
+
+void perf_evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
+{
+ struct evsel *evsel;
+
+ /*
+ * To collect the overall statistics for interval mode,
+ * we copy the counts from evsel->prev_raw_counts to
+ * evsel->counts. The perf_stat_process_counter creates
+ * aggr values from per cpu values, but the per cpu values
+ * are 0 for AGGR_GLOBAL. So we use a trick that saves the
+ * previous aggr value to the first member of perf_counts,
+ * then aggr calculation in process_counter_values can work
+ * correctly.
+ */
+ evlist__for_each_entry(evlist, evsel) {
+ *perf_counts(evsel->prev_raw_counts, 0, 0) =
+ evsel->prev_raw_counts->aggr;
+ }
+}
+
+static void zero_per_pkg(struct evsel *counter)
{
if (counter->per_pkg_mask)
- memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
+ memset(counter->per_pkg_mask, 0, cpu__max_cpu());
}
-static int check_per_pkg(struct perf_evsel *counter,
+static int check_per_pkg(struct evsel *counter,
struct perf_counts_values *vals, int cpu, bool *skip)
{
unsigned long *mask = counter->per_pkg_mask;
- struct cpu_map *cpus = perf_evsel__cpus(counter);
+ struct perf_cpu_map *cpus = evsel__cpus(counter);
int s;
*skip = false;
@@ -239,11 +291,11 @@
if (!counter->per_pkg)
return 0;
- if (cpu_map__empty(cpus))
+ if (perf_cpu_map__empty(cpus))
return 0;
if (!mask) {
- mask = zalloc(MAX_NR_CPUS);
+ mask = zalloc(cpu__max_cpu());
if (!mask)
return -ENOMEM;
@@ -270,7 +322,7 @@
}
static int
-process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel,
+process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
int cpu, int thread,
struct perf_counts_values *count)
{
@@ -289,14 +341,18 @@
switch (config->aggr_mode) {
case AGGR_THREAD:
case AGGR_CORE:
+ case AGGR_DIE:
case AGGR_SOCKET:
+ case AGGR_NODE:
case AGGR_NONE:
if (!evsel->snapshot)
- perf_evsel__compute_deltas(evsel, cpu, thread, count);
+ evsel__compute_deltas(evsel, cpu, thread, count);
perf_counts_values__scale(count, config->scale, NULL);
- if (config->aggr_mode == AGGR_NONE)
- perf_stat__update_shadow_stats(evsel, count->val, cpu,
- &rt_stat);
+ if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
+ perf_stat__update_shadow_stats(evsel, count->val,
+ cpu, &rt_stat);
+ }
+
if (config->aggr_mode == AGGR_THREAD) {
if (config->stats)
perf_stat__update_shadow_stats(evsel,
@@ -308,10 +364,8 @@
break;
case AGGR_GLOBAL:
aggr->val += count->val;
- if (config->scale) {
- aggr->ena += count->ena;
- aggr->run += count->run;
- }
+ aggr->ena += count->ena;
+ aggr->run += count->run;
case AGGR_UNSET:
default:
break;
@@ -321,13 +375,13 @@
}
static int process_counter_maps(struct perf_stat_config *config,
- struct perf_evsel *counter)
+ struct evsel *counter)
{
- int nthreads = thread_map__nr(counter->threads);
- int ncpus = perf_evsel__nr_cpus(counter);
+ int nthreads = perf_thread_map__nr(counter->core.threads);
+ int ncpus = evsel__nr_cpus(counter);
int cpu, thread;
- if (counter->system_wide)
+ if (counter->core.system_wide)
nthreads = 1;
for (thread = 0; thread < nthreads; thread++) {
@@ -342,7 +396,7 @@
}
int perf_stat_process_counter(struct perf_stat_config *config,
- struct perf_evsel *counter)
+ struct evsel *counter)
{
struct perf_counts_values *aggr = &counter->counts->aggr;
struct perf_stat_evsel *ps = counter->stats;
@@ -358,7 +412,7 @@
* interval mode, otherwise overall avg running
* averages will be shown for each interval.
*/
- if (config->interval) {
+ if (config->interval || config->summary) {
for (i = 0; i < 3; i++)
init_stats(&ps->res_stats[i]);
}
@@ -374,7 +428,7 @@
return 0;
if (!counter->snapshot)
- perf_evsel__compute_deltas(counter, -1, -1, aggr);
+ evsel__compute_deltas(counter, -1, -1, aggr);
perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);
for (i = 0; i < 3; i++)
@@ -382,7 +436,7 @@
if (verbose > 0) {
fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
- perf_evsel__name(counter), count[0], count[1], count[2]);
+ evsel__name(counter), count[0], count[1], count[2]);
}
/*
@@ -393,13 +447,12 @@
return 0;
}
-int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
- union perf_event *event,
- struct perf_session *session)
+int perf_event__process_stat_event(struct perf_session *session,
+ union perf_event *event)
{
struct perf_counts_values count;
- struct stat_event *st = &event->stat;
- struct perf_evsel *counter;
+ struct perf_record_stat *st = &event->stat;
+ struct evsel *counter;
count.val = st->val;
count.ena = st->ena;
@@ -418,12 +471,12 @@
size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp)
{
- struct stat_event *st = (struct stat_event *) event;
+ struct perf_record_stat *st = (struct perf_record_stat *)event;
size_t ret;
- ret = fprintf(fp, "\n... id %" PRIu64 ", cpu %d, thread %d\n",
+ ret = fprintf(fp, "\n... id %" PRI_lu64 ", cpu %d, thread %d\n",
st->id, st->cpu, st->thread);
- ret += fprintf(fp, "... value %" PRIu64 ", enabled %" PRIu64 ", running %" PRIu64 "\n",
+ ret += fprintf(fp, "... value %" PRI_lu64 ", enabled %" PRI_lu64 ", running %" PRI_lu64 "\n",
st->val, st->ena, st->run);
return ret;
@@ -431,10 +484,10 @@
size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
{
- struct stat_round_event *rd = (struct stat_round_event *)event;
+ struct perf_record_stat_round *rd = (struct perf_record_stat_round *)event;
size_t ret;
- ret = fprintf(fp, "\n... time %" PRIu64 ", type %s\n", rd->time,
+ ret = fprintf(fp, "\n... time %" PRI_lu64 ", type %s\n", rd->time,
rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL");
return ret;
@@ -454,3 +507,65 @@
return ret;
}
+
+int create_perf_stat_counter(struct evsel *evsel,
+ struct perf_stat_config *config,
+ struct target *target,
+ int cpu)
+{
+ struct perf_event_attr *attr = &evsel->core.attr;
+ struct evsel *leader = evsel->leader;
+
+ 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->core.nr_members > 1)
+ attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
+
+ attr->inherit = !config->no_inherit;
+
+ /*
+ * Some events get initialized with sample_(period/type) set,
+ * like tracepoints. Clear it up for counting.
+ */
+ attr->sample_period = 0;
+
+ if (config->identifier)
+ attr->sample_type = PERF_SAMPLE_IDENTIFIER;
+
+ if (config->all_user) {
+ attr->exclude_kernel = 1;
+ attr->exclude_user = 0;
+ }
+
+ if (config->all_kernel) {
+ attr->exclude_kernel = 0;
+ attr->exclude_user = 1;
+ }
+
+ /*
+ * Disabling all counters initially, they will be enabled
+ * either manually by us or by kernel via enable_on_exec
+ * set later.
+ */
+ if (evsel__is_group_leader(evsel)) {
+ attr->disabled = 1;
+
+ /*
+ * In case of initial_delay we enable tracee
+ * events manually.
+ */
+ if (target__none(target) && !config->initial_delay)
+ attr->enable_on_exec = 1;
+ }
+
+ if (target__has_cpu(target) && !target__has_per_thread(target))
+ return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
+
+ return evsel__open_per_thread(evsel, evsel->core.threads);
+}
--
Gitblit v1.6.2