#include <netinet/in.h>
#include "event-parse.h"
#include "event-utils.h"
+#include "trace-seq.h"
static const char *input_buf;
static unsigned long long input_buf_ptr;
#include <regex.h>
#include <string.h>
+#include "trace-seq.h"
+
#ifndef __maybe_unused
#define __maybe_unused __attribute__((unused))
#endif
-/* ----------------------- trace_seq ----------------------- */
-
-
-#ifndef TRACE_SEQ_BUF_SIZE
-#define TRACE_SEQ_BUF_SIZE 4096
-#endif
-
#ifndef DEBUG_RECORD
#define DEBUG_RECORD 0
#endif
#endif
};
-enum trace_seq_fail {
- TRACE_SEQ__GOOD,
- TRACE_SEQ__BUFFER_POISONED,
- TRACE_SEQ__MEM_ALLOC_FAILED,
-};
-
-/*
- * Trace sequences are used to allow a function to call several other functions
- * to create a string of data to use (up to a max of PAGE_SIZE).
- */
-
-struct trace_seq {
- char *buffer;
- unsigned int buffer_size;
- unsigned int len;
- unsigned int readpos;
- enum trace_seq_fail state;
-};
-
-void trace_seq_init(struct trace_seq *s);
-void trace_seq_reset(struct trace_seq *s);
-void trace_seq_destroy(struct trace_seq *s);
-
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
- __attribute__ ((format (printf, 2, 3)));
-extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
- __attribute__ ((format (printf, 2, 0)));
-
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-
-extern void trace_seq_terminate(struct trace_seq *s);
-
-extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
-extern int trace_seq_do_printf(struct trace_seq *s);
-
-
/* ----------------------- pevent ----------------------- */
struct tep_handle;
#include <dirent.h>
#include "event-parse.h"
#include "event-utils.h"
+#include "trace-seq.h"
#define LOCAL_PLUGIN_DIR ".traceevent/plugins"
#include "event-parse.h"
#include "event-utils.h"
+#include "trace-seq.h"
static struct func_stack {
int size;
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
static int timer_expire_handler(struct trace_seq *s,
struct tep_record *record,
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
#define MINORBITS 20
#define MINORMASK ((1U << MINORBITS) - 1)
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
static int call_site_handler(struct trace_seq *s, struct tep_record *record,
struct event_format *event, void *context)
#include <stdint.h>
#include "event-parse.h"
+#include "trace-seq.h"
#ifdef HAVE_UDIS86
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
#define INDENT 65
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
static void write_state(struct trace_seq *s, int val)
{
#include <string.h>
#include <inttypes.h>
#include "event-parse.h"
+#include "trace-seq.h"
typedef unsigned long sector_t;
typedef uint64_t u64;
#include <stdlib.h>
#include <string.h>
#include "event-parse.h"
+#include "trace-seq.h"
#define __HYPERVISOR_set_trap_table 0
#define __HYPERVISOR_mmu_update 1
* Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
*/
+#include "trace-seq.h"
+
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
--- /dev/null
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#ifndef _TRACE_SEQ_H
+#define _TRACE_SEQ_H
+
+#include <stdarg.h>
+#include <stdio.h>
+
+/* ----------------------- trace_seq ----------------------- */
+
+#ifndef TRACE_SEQ_BUF_SIZE
+#define TRACE_SEQ_BUF_SIZE 4096
+#endif
+
+enum trace_seq_fail {
+ TRACE_SEQ__GOOD,
+ TRACE_SEQ__BUFFER_POISONED,
+ TRACE_SEQ__MEM_ALLOC_FAILED,
+};
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE).
+ */
+
+struct trace_seq {
+ char *buffer;
+ unsigned int buffer_size;
+ unsigned int len;
+ unsigned int readpos;
+ enum trace_seq_fail state;
+};
+
+void trace_seq_init(struct trace_seq *s);
+void trace_seq_reset(struct trace_seq *s);
+void trace_seq_destroy(struct trace_seq *s);
+
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+ __attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+ __attribute__ ((format (printf, 2, 0)));
+
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+
+extern void trace_seq_terminate(struct trace_seq *s);
+
+extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
+extern int trace_seq_do_printf(struct trace_seq *s);
+
+#endif /* _TRACE_SEQ_H */
ifndef NO_LIBBPF
$(call QUIET_INSTALL, bpf-headers) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
- $(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \
+ $(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+ $(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
$(call QUIET_INSTALL, bpf-examples) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
jump_insn;
};
+static int arm64_mov__parse(struct arch *arch __maybe_unused,
+ struct ins_operands *ops,
+ struct map_symbol *ms __maybe_unused)
+{
+ char *s = strchr(ops->raw, ','), *target, *endptr;
+
+ if (s == NULL)
+ return -1;
+
+ *s = '\0';
+ ops->source.raw = strdup(ops->raw);
+ *s = ',';
+
+ if (ops->source.raw == NULL)
+ return -1;
+
+ target = ++s;
+ ops->target.raw = strdup(target);
+ if (ops->target.raw == NULL)
+ goto out_free_source;
+
+ ops->target.addr = strtoull(target, &endptr, 16);
+ if (endptr == target)
+ goto out_free_target;
+
+ s = strchr(endptr, '<');
+ if (s == NULL)
+ goto out_free_target;
+ endptr = strchr(s + 1, '>');
+ if (endptr == NULL)
+ goto out_free_target;
+
+ *endptr = '\0';
+ *s = ' ';
+ ops->target.name = strdup(s);
+ *s = '<';
+ *endptr = '>';
+ if (ops->target.name == NULL)
+ goto out_free_target;
+
+ return 0;
+
+out_free_target:
+ zfree(&ops->target.raw);
+out_free_source:
+ zfree(&ops->source.raw);
+ return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+ struct ins_operands *ops);
+
+static struct ins_ops arm64_mov_ops = {
+ .parse = arm64_mov__parse,
+ .scnprintf = mov__scnprintf,
+};
+
static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
{
struct arm64_annotate *arm = arch->priv;
else if (!strcmp(name, "ret"))
ops = &ret_ops;
else
- return NULL;
+ ops = &arm64_mov_ops;
arch__associate_ins_ops(arch, name, ops);
return ops;
return -1;
}
-static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
- struct ins_operands *ops);
static struct ins_ops s390_mov_ops = {
.parse = s390_mov__parse,
* We need to synthesize events first, because some
* features works on top of them (on report side).
*/
- err = perf_event__synthesize_attrs(tool, session,
+ err = perf_event__synthesize_attrs(tool, rec->evlist,
process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize attrs.\n");
FILE *fp;
};
-static void script_print_metric(void *ctx, const char *color,
+static void script_print_metric(struct perf_stat_config *config __maybe_unused,
+ void *ctx, const char *color,
const char *fmt,
const char *unit, double val)
{
fprintf(mctx->fp, " %s\n", unit);
}
-static void script_new_line(void *ctx)
+static void script_new_line(struct perf_stat_config *config __maybe_unused,
+ void *ctx)
{
struct metric_ctx *mctx = ctx;
evsel_script(evsel)->val = val;
if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
for_each_group_member (ev2, evsel->leader) {
- perf_stat__print_shadow_stats(ev2,
+ perf_stat__print_shadow_stats(&stat_config, ev2,
evsel_script(ev2)->val,
sample->cpu,
&ctx,
#include "sane_ctype.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);
static struct perf_evlist *evsel_list;
-static struct rblist metric_events;
-
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;
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,
};
-static bool is_duration_time(struct perf_evsel *evsel)
-{
- return !strcmp(evsel->name, "duration_time");
-}
-
static inline void diff_timespec(struct timespec *r, struct timespec *a,
struct timespec *b)
{
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,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
static void enable_counters(void)
{
- if (initial_delay)
- usleep(initial_delay * USEC_PER_MSEC);
+ if (stat_config.initial_delay)
+ 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)
+ if (!target__none(&target) || stat_config.initial_delay)
perf_evlist__enable(evsel_list);
}
workload_exec_errno = info->si_value.sival_int;
}
-static int perf_stat_synthesize_config(bool is_pipe)
-{
- int err;
-
- 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;
- }
- }
-
- 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;
-}
-
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-
-static int __store_counter_ids(struct perf_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;
evlist__for_each_entry(evsel_list, counter) {
try_again:
- if (create_perf_stat_counter(counter) < 0) {
+ if (create_perf_stat_counter(counter, &stat_config, &target) < 0) {
/* Weak group failed. Reset the group. */
if ((errno == EINVAL || errno == EBADF) &&
counter->supported = true;
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))
+ perf_evsel__store_ids(counter, evsel_list))
return -1;
}
if (err < 0)
return err;
- err = perf_stat_synthesize_config(is_pipe);
+ err = perf_stat_synthesize_config(&stat_config, NULL, evsel_list,
+ process_synthesized_event, is_pipe);
if (err < 0)
return err;
}
break;
}
}
- wait4(child_pid, &status, 0, &ru_data);
+ wait4(child_pid, &status, 0, &stat_config.ru_data);
if (workload_exec_errno) {
const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
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);
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;
const char *s __maybe_unused, int unset)
{
force_metric_only = true;
- metric_only = !unset;
+ stat_config.metric_only = !unset;
return 0;
}
const char *str,
int unset __maybe_unused)
{
- return metricgroup__parse_groups(opt, str, &metric_events);
+ return metricgroup__parse_groups(opt, str, &stat_config.metric_events);
}
static const struct option stat_options[] = {
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"),
OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
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"),
"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),
"(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)"),
"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,
+ OPT_UINTEGER('D', "delay", &stat_config.initial_delay,
"ms to wait before starting measurement after program start"),
- OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
+ OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL,
"Only print computed metrics. No raw values", enable_metric_only),
OPT_BOOLEAN(0, "topdown", &topdown_run,
"measure topdown level 1 statistics"),
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 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_core(struct perf_stat_config *config __maybe_unused,
+ struct cpu_map *map, int cpu)
{
return cpu_map__get_core(map, cpu, NULL);
}
return max;
}
-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 cpu_map *map, int idx)
{
int cpu;
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 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_core_cached(struct perf_stat_config *config,
+ struct 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_core, map, idx);
}
static int perf_stat_init_aggr_mode(void)
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->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_CORE:
- if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) {
+ if (cpu_map__build_core_map(evsel_list->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_NONE:
case AGGR_GLOBAL:
* 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;
+ stat_config.cpus_aggr_map = 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;
+ cpu_map__put(stat_config.aggr_map);
+ 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)
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_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
+ struct cpu_map *map, int idx)
{
return perf_env__get_socket(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 cpu_map *map, int idx)
{
return perf_env__get_core(map, idx, &perf_stat.session->header.env);
}
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->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_CORE:
- if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) {
+ if (perf_env__build_core_map(env, evsel_list->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_NONE:
case AGGR_GLOBAL:
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;
if (transaction_run) {
struct option opt = { .value = &evsel_list };
return metricgroup__parse_groups(&opt, "transaction",
- &metric_events);
+ &stat_config.metric_events);
}
if (pmu_have_event("cpu", "cycles-ct") &&
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 "
}
if (!force_metric_only)
- metric_only = true;
+ stat_config.metric_only = true;
if (topdown_filter_events(topdown_attrs, &str,
arch_topdown_check_group(&warn)) < 0) {
pr_err("Out of memory\n");
if (output_name)
data->file.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;
}
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);
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);
/*
* 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");
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);
* 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;
}
if (perf_stat_init_aggr_mode())
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.
signal(SIGABRT, skip_signal);
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);
perf_stat__exit_aggr_mode();
perf_evlist__free_stats(evsel_list);
out:
- free(walltime_run);
+ free(stat_config.walltime_run);
if (smi_cost && smi_reset)
sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
}
+static int perf_evsel__init_augmented_syscall_tp_ret(struct perf_evsel *evsel)
+{
+ struct syscall_tp *sc = evsel->priv;
+
+ return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap);
+}
+
static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler)
{
evsel->priv = malloc(sizeof(struct syscall_tp));
};
static DEFINE_STRARRAY(clockid);
-static const char *socket_families[] = {
- "UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
- "BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
- "SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
- "RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
- "BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
- "ALG", "NFC", "VSOCK",
-};
-static DEFINE_STRARRAY(socket_families);
-
static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
struct syscall_arg *arg)
{
} syscall_fmts[] = {
{ .name = "access",
.arg = { [1] = { .scnprintf = SCA_ACCMODE, /* mode */ }, }, },
+ { .name = "bind",
+ .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, }, },
{ .name = "bpf",
.arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
{ .name = "brk", .hexret = true,
[4] = { .name = "tls", .scnprintf = SCA_HEX, }, }, },
{ .name = "close",
.arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, },
+ { .name = "connect",
+ .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, }, },
{ .name = "epoll_ctl",
.arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
{ .name = "eventfd2",
{ .name = "sendmsg",
.arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
{ .name = "sendto",
- .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+ .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
+ [4] = { .scnprintf = SCA_SOCKADDR, /* addr */ }, }, },
{ .name = "set_tid_address", .errpid = true, },
{ .name = "setitimer",
.arg = { [0] = STRARRAY(which, itimers), }, },
.arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
{ .name = "tkill",
.arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+ { .name = "umount2", .alias = "umount", },
{ .name = "uname", .alias = "newuname", },
{ .name = "unlinkat",
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
/*
* is_exit: is this "exit" or "exit_group"?
* is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
+ * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
*/
struct syscall {
struct event_format *tp_format;
int nr_args;
+ int args_size;
bool is_exit;
bool is_open;
struct format_field *args;
ttrace->filename.entry_str_pos = bf - ttrace->entry_str;
}
+static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size)
+{
+ struct augmented_arg *augmented_arg = arg->augmented.args;
+
+ return scnprintf(bf, size, "%.*s", augmented_arg->size, augmented_arg->value);
+}
+
static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
struct syscall_arg *arg)
{
unsigned long ptr = arg->val;
+ if (arg->augmented.args)
+ return syscall_arg__scnprintf_augmented_string(arg, bf, size);
+
if (!arg->trace->vfs_getname)
return scnprintf(bf, size, "%#x", ptr);
interrupted = sig == SIGINT;
}
-static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
- u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
+static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp)
{
- size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
- printed += fprintf_duration(duration, duration_calculated, fp);
+ size_t printed = 0;
if (trace->multiple_threads) {
if (trace->show_comm)
return printed;
}
+static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
+ u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
+{
+ size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
+ printed += fprintf_duration(duration, duration_calculated, fp);
+ return printed + trace__fprintf_comm_tid(trace, thread, fp);
+}
+
static int trace__process_event(struct trace *trace, struct machine *machine,
union perf_event *event, struct perf_sample *sample)
{
static int syscall__set_arg_fmts(struct syscall *sc)
{
- struct format_field *field;
+ struct format_field *field, *last_field = NULL;
int idx = 0, len;
for (field = sc->args; field; field = field->next, ++idx) {
+ last_field = field;
+
if (sc->fmt && sc->fmt->arg[idx].scnprintf)
continue;
}
}
+ if (last_field)
+ sc->args_size = last_field->offset + last_field->size;
+
return 0;
}
}
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
- unsigned char *args, struct trace *trace,
- struct thread *thread)
+ unsigned char *args, void *augmented_args, int augmented_args_size,
+ struct trace *trace, struct thread *thread)
{
size_t printed = 0;
unsigned long val;
u8 bit = 1;
struct syscall_arg arg = {
.args = args,
+ .augmented = {
+ .size = augmented_args_size,
+ .args = augmented_args,
+ },
.idx = 0,
.mask = 0,
.trace = trace,
return printed;
}
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
+{
+ void *augmented_args = NULL;
+
+ *augmented_args_size = sample->raw_size - sc->args_size;
+ if (*augmented_args_size > 0)
+ augmented_args = sample->raw_data + sc->args_size;
+
+ return augmented_args;
+}
+
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
size_t printed = 0;
struct thread *thread;
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
+ int augmented_args_size = 0;
+ void *augmented_args = NULL;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
struct thread_trace *ttrace;
if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
trace__printf_interrupted_entry(trace);
-
+ /*
+ * If this is raw_syscalls.sys_enter, then it always comes with the 6 possible
+ * arguments, even if the syscall being handled, say "openat", uses only 4 arguments
+ * this breaks syscall__augmented_args() check for augmented args, as we calculate
+ * syscall->args_size using each syscalls:sys_enter_NAME tracefs format file,
+ * so when handling, say the openat syscall, we end up getting 6 args for the
+ * raw_syscalls:sys_enter event, when we expected just 4, we end up mistakenly
+ * thinking that the extra 2 u64 args are the augmented filename, so just check
+ * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
+ */
+ if (evsel != trace->syscalls.events.sys_enter)
+ augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
ttrace->entry_time = sample->time;
msg = ttrace->entry_str;
printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
- args, trace, thread);
+ args, augmented_args, augmented_args_size, trace, thread);
if (sc->is_exit) {
if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
char msg[1024];
- void *args;
+ void *args, *augmented_args = NULL;
+ int augmented_args_size;
if (sc == NULL)
return -1;
goto out_put;
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
- syscall__scnprintf_args(sc, msg, sizeof(msg), args, trace, thread);
+ augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+ syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
fprintf(trace->output, "%s", msg);
err = 0;
out_put:
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
+ struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
int callchain_ret = 0;
if (sample->callchain) {
if (trace->trace_syscalls)
fprintf(trace->output, "( ): ");
+ if (thread)
+ trace__fprintf_comm_tid(trace, thread, trace->output);
+
+ if (evsel == trace->syscalls.events.augmented) {
+ int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+ struct syscall *sc = trace__syscall_info(trace, evsel, id);
+
+ if (sc) {
+ fprintf(trace->output, "%s(", sc->name);
+ trace__fprintf_sys_enter(trace, evsel, sample);
+ fputc(')', trace->output);
+ goto newline;
+ }
+
+ /*
+ * XXX: Not having the associated syscall info or not finding/adding
+ * the thread should never happen, but if it does...
+ * fall thru and print it as a bpf_output event.
+ */
+ }
+
fprintf(trace->output, "%s:", evsel->name);
if (perf_evsel__is_bpf_output(evsel)) {
- if (evsel == trace->syscalls.events.augmented)
- trace__fprintf_sys_enter(trace, evsel, sample);
- else
- bpf_output__fprintf(trace, sample);
+ bpf_output__fprintf(trace, sample);
} else if (evsel->tp_format) {
if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
trace__fprintf_sys_enter(trace, evsel, sample)) {
}
}
+newline:
fprintf(trace->output, "\n");
if (callchain_ret > 0)
trace__fprintf_callchain(trace, sample);
else if (callchain_ret < 0)
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+ thread__put(thread);
out:
return 0;
}
goto out;
}
- if (evsel) {
- if (perf_evsel__init_augmented_syscall_tp(evsel) ||
- perf_evsel__init_augmented_syscall_tp_args(evsel))
- goto out;
+ if (evsel)
trace.syscalls.events.augmented = evsel;
- }
err = bpf__setup_stdout(trace.evlist);
if (err) {
}
}
+ /*
+ * If we are augmenting syscalls, then combine what we put in the
+ * __augmented_syscalls__ BPF map with what is in the
+ * syscalls:sys_exit_FOO tracepoints, i.e. just like we do without BPF,
+ * combining raw_syscalls:sys_enter with raw_syscalls:sys_exit.
+ *
+ * We'll switch to look at two BPF maps, one for sys_enter and the
+ * other for sys_exit when we start augmenting the sys_exit paths with
+ * buffers that are being copied from kernel to userspace, think 'read'
+ * syscall.
+ */
+ if (trace.syscalls.events.augmented) {
+ evsel = trace.syscalls.events.augmented;
+
+ if (perf_evsel__init_augmented_syscall_tp(evsel) ||
+ perf_evsel__init_augmented_syscall_tp_args(evsel))
+ goto out;
+ evsel->handler = trace__sys_enter;
+
+ evlist__for_each_entry(trace.evlist, evsel) {
+ if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+ perf_evsel__init_augmented_syscall_tp(evsel);
+ perf_evsel__init_augmented_syscall_tp_ret(evsel);
+ evsel->handler = trace__sys_exit;
+ }
+ }
+ }
+
if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
return trace__record(&trace, argc-1, &argv[1]);
// SPDX-License-Identifier: GPL-2.0
/*
- * Augment the openat syscall with the contents of the filename pointer argument.
+ * Augment syscalls with the contents of the pointer arguments.
*
* Test it with:
*
* the last one should be the one for '/etc/passwd'.
*
* This matches what is marshalled into the raw_syscall:sys_enter payload
- * expected by the 'perf trace' beautifiers, and can be used by them unmodified,
- * which will be done as that feature is implemented in the next csets, for now
- * it will appear in a dump done by the default tracepoint handler in 'perf trace',
- * that uses bpf_output__fprintf() to just dump those contents, as done with
- * the bpf-output event associated with the __bpf_output__ map declared in
- * tools/perf/include/bpf/stdio.h.
+ * expected by the 'perf trace' beautifiers, and can be used by them, that will
+ * check if perf_sample->raw_data is more than what is expected for each
+ * syscalls:sys_{enter,exit}_SYSCALL tracepoint, uing the extra data as the
+ * contents of pointer arguments.
*/
#include <stdio.h>
+#include <linux/socket.h>
struct bpf_map SEC("maps") __augmented_syscalls__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.max_entries = __NR_CPUS__,
};
+struct syscall_exit_args {
+ unsigned long long common_tp_fields;
+ long syscall_nr;
+ long ret;
+};
+
+struct augmented_filename {
+ unsigned int size;
+ int reserved;
+ char value[256];
+};
+
+#define augmented_filename_syscall(syscall) \
+struct augmented_enter_##syscall##_args { \
+ struct syscall_enter_##syscall##_args args; \
+ struct augmented_filename filename; \
+}; \
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \
+{ \
+ struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; \
+ unsigned int len = sizeof(augmented_args); \
+ probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \
+ augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, \
+ sizeof(augmented_args.filename.value), \
+ args->filename_ptr); \
+ if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { \
+ len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; \
+ len &= sizeof(augmented_args.filename.value) - 1; \
+ } \
+ perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \
+ &augmented_args, len); \
+ return 0; \
+} \
+int syscall_exit(syscall)(struct syscall_exit_args *args) \
+{ \
+ return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ \
+}
+
struct syscall_enter_openat_args {
unsigned long long common_tp_fields;
long syscall_nr;
long mode;
};
-struct augmented_enter_openat_args {
- struct syscall_enter_openat_args args;
- char filename[64];
+augmented_filename_syscall(openat);
+
+struct syscall_enter_open_args {
+ unsigned long long common_tp_fields;
+ long syscall_nr;
+ char *filename_ptr;
+ long flags;
+ long mode;
+};
+
+augmented_filename_syscall(open);
+
+struct syscall_enter_inotify_add_watch_args {
+ unsigned long long common_tp_fields;
+ long syscall_nr;
+ long fd;
+ char *filename_ptr;
+ long mask;
+};
+
+augmented_filename_syscall(inotify_add_watch);
+
+struct statbuf;
+
+struct syscall_enter_newstat_args {
+ unsigned long long common_tp_fields;
+ long syscall_nr;
+ char *filename_ptr;
+ struct stat *statbuf;
};
-int syscall_enter(openat)(struct syscall_enter_openat_args *args)
-{
- struct augmented_enter_openat_args augmented_args;
+augmented_filename_syscall(newstat);
+
+#ifndef _K_SS_MAXSIZE
+#define _K_SS_MAXSIZE 128
+#endif
- probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
- probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr);
- perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
- &augmented_args, sizeof(augmented_args));
- return 1;
+#define augmented_sockaddr_syscall(syscall) \
+struct augmented_enter_##syscall##_args { \
+ struct syscall_enter_##syscall##_args args; \
+ struct sockaddr_storage addr; \
+}; \
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \
+{ \
+ struct augmented_enter_##syscall##_args augmented_args; \
+ unsigned long addrlen = sizeof(augmented_args.addr); \
+ probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \
+/* FIXME_CLANG_OPTIMIZATION_THAT_ACCESSES_USER_CONTROLLED_ADDRLEN_DESPITE_THIS_CHECK */ \
+/* if (addrlen > augmented_args.args.addrlen) */ \
+/* addrlen = augmented_args.args.addrlen; */ \
+/* */ \
+ probe_read(&augmented_args.addr, addrlen, args->addr_ptr); \
+ perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \
+ &augmented_args, \
+ sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen); \
+ return 0; \
+} \
+int syscall_exit(syscall)(struct syscall_exit_args *args) \
+{ \
+ return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ \
}
+struct sockaddr;
+
+struct syscall_enter_bind_args {
+ unsigned long long common_tp_fields;
+ long syscall_nr;
+ long fd;
+ struct sockaddr *addr_ptr;
+ unsigned long addrlen;
+};
+
+augmented_sockaddr_syscall(bind);
+
+struct syscall_enter_connect_args {
+ unsigned long long common_tp_fields;
+ long syscall_nr;
+ long fd;
+ struct sockaddr *addr_ptr;
+ unsigned long addrlen;
+};
+
+augmented_sockaddr_syscall(connect);
+
+struct syscall_enter_sendto_args {
+ unsigned long long common_tp_fields;
+ long syscall_nr;
+ long fd;
+ void *buff;
+ long len;
+ unsigned long flags;
+ struct sockaddr *addr_ptr;
+ long addr_len;
+};
+
+augmented_sockaddr_syscall(sendto);
+
license(GPL);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the filename syscalls with the contents of the filename pointer argument
+ * filtering only those that do not start with /etc/.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * It'll catch some openat syscalls related to the dynamic linked and
+ * the last one should be the one for '/etc/passwd'.
+ *
+ * This matches what is marshalled into the raw_syscall:sys_enter payload
+ * expected by the 'perf trace' beautifiers, and can be used by them unmodified,
+ * which will be done as that feature is implemented in the next csets, for now
+ * it will appear in a dump done by the default tracepoint handler in 'perf trace',
+ * that uses bpf_output__fprintf() to just dump those contents, as done with
+ * the bpf-output event associated with the __bpf_output__ map declared in
+ * tools/perf/include/bpf/stdio.h.
+ */
+
+#include <stdio.h>
+
+struct bpf_map SEC("maps") __augmented_syscalls__ = {
+ .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(u32),
+ .max_entries = __NR_CPUS__,
+};
+
+struct augmented_filename {
+ int size;
+ int reserved;
+ char value[64];
+};
+
+#define augmented_filename_syscall_enter(syscall) \
+struct augmented_enter_##syscall##_args { \
+ struct syscall_enter_##syscall##_args args; \
+ struct augmented_filename filename; \
+}; \
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \
+{ \
+ char etc[6] = "/etc/"; \
+ struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; \
+ probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \
+ augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, \
+ sizeof(augmented_args.filename.value), \
+ args->filename_ptr); \
+ if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0) \
+ return 0; \
+ perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \
+ &augmented_args, \
+ (sizeof(augmented_args) - sizeof(augmented_args.filename.value) + \
+ augmented_args.filename.size)); \
+ return 0; \
+}
+
+struct syscall_enter_openat_args {
+ unsigned long long common_tp_fields;
+ long syscall_nr;
+ long dfd;
+ char *filename_ptr;
+ long flags;
+ long mode;
+};
+
+augmented_filename_syscall_enter(openat);
+
+struct syscall_enter_open_args {
+ unsigned long long common_tp_fields;
+ long syscall_nr;
+ char *filename_ptr;
+ long flags;
+ long mode;
+};
+
+augmented_filename_syscall_enter(open);
+
+license(GPL);
#define syscall_enter(name) \
SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name
+#define syscall_exit(name) \
+ SEC("syscalls:sys_exit_" #name) syscall_exit_ ## name
+
#define license(name) \
char _license[] SEC("license") = #name; \
int _version SEC("version") = LINUX_VERSION_CODE;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SOCKET_H
+#define _UAPI_LINUX_SOCKET_H
+
+/*
+ * Desired design of maximum size and alignment (see RFC2553)
+ */
+#define _K_SS_MAXSIZE 128 /* Implementation specific max size */
+#define _K_SS_ALIGNSIZE (__alignof__ (struct sockaddr *))
+ /* Implementation specific desired alignment */
+
+typedef unsigned short __kernel_sa_family_t;
+
+struct __kernel_sockaddr_storage {
+ __kernel_sa_family_t ss_family; /* address family */
+ /* Following field(s) are implementation specific */
+ char __data[_K_SS_MAXSIZE - sizeof(unsigned short)];
+ /* space to achieve desired size, */
+ /* _SS_MAXSIZE value minus size of ss_family */
+} __attribute__ ((aligned(_K_SS_ALIGNSIZE))); /* force desired alignment */
+
+#define sockaddr_storage __kernel_sockaddr_storage
+
+#endif /* _UAPI_LINUX_SOCKET_H */
*)
eventattr='max-stack=3'
echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
- echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+ echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
;;
esac
libperf-y += kcmp.o
libperf-y += pkey_alloc.o
libperf-y += prctl.o
+libperf-y += sockaddr.o
libperf-y += socket.o
libperf-y += statx.o
size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size);
+extern struct strarray strarray__socket_families;
+
+/**
+ * augmented_arg: extra payload for syscall pointer arguments
+
+ * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts,
+ * then its the arguments contents, so that we can show more than just a
+ * pointer. This will be done initially with eBPF, the start of that is at the
+ * tools/perf/examples/bpf/augmented_syscalls.c example for the openat, but
+ * will eventually be done automagically caching the running kernel tracefs
+ * events data into an eBPF C script, that then gets compiled and its .o file
+ * cached for subsequent use. For char pointers like the ones for 'open' like
+ * syscalls its easy, for the rest we should use DWARF or better, BTF, much
+ * more compact.
+ *
+ * @size: 8 if all we need is an integer, otherwise all of the augmented arg.
+ * @int_arg: will be used for integer like pointer contents, like 'accept's 'upeer_addrlen'
+ * @value: u64 aligned, for structs, pathnames
+ */
+struct augmented_arg {
+ int size;
+ int int_arg;
+ u64 value[];
+};
+
/**
* @val: value of syscall argument being formatted
* @args: All the args, use syscall_args__val(arg, nth) to access one
+ * @augmented_args: Extra data that can be collected, for instance, with eBPF for expanding the pathname for open, etc
+ * @augmented_args_size: augmented_args total payload size
* @thread: tid state (maps, pid, tid, etc)
* @trace: 'perf trace' internals: all threads, etc
* @parm: private area, may be an strarray, for instance
struct syscall_arg {
unsigned long val;
unsigned char *args;
+ struct {
+ struct augmented_arg *args;
+ int size;
+ } augmented;
struct thread *thread;
struct trace *trace;
void *parm;
size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
+size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SOCKADDR syscall_arg__scnprintf_sockaddr
+
size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+
+#include "trace/beauty/beauty.h"
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <arpa/inet.h>
+
+static const char *socket_families[] = {
+ "UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
+ "BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
+ "SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
+ "RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
+ "BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
+ "ALG", "NFC", "VSOCK",
+};
+DEFINE_STRARRAY(socket_families);
+
+static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+ struct sockaddr_in *sin = (struct sockaddr_in *)sa;
+ char tmp[16];
+ return scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin->sin_port),
+ inet_ntop(sin->sin_family, &sin->sin_addr, tmp, sizeof(tmp)));
+}
+
+static size_t af_inet6__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa;
+ u32 flowinfo = ntohl(sin6->sin6_flowinfo);
+ char tmp[512];
+ size_t printed = scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin6->sin6_port),
+ inet_ntop(sin6->sin6_family, &sin6->sin6_addr, tmp, sizeof(tmp)));
+ if (flowinfo != 0)
+ printed += scnprintf(bf + printed, size - printed, ", flowinfo: %lu", flowinfo);
+ if (sin6->sin6_scope_id != 0)
+ printed += scnprintf(bf + printed, size - printed, ", scope_id: %lu", sin6->sin6_scope_id);
+
+ return printed;
+}
+
+static size_t af_local__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+ struct sockaddr_un *sun = (struct sockaddr_un *)sa;
+ return scnprintf(bf, size, ", path: %s", sun->sun_path);
+}
+
+static size_t (*af_scnprintfs[])(struct sockaddr *sa, char *bf, size_t size) = {
+ [AF_LOCAL] = af_local__scnprintf,
+ [AF_INET] = af_inet__scnprintf,
+ [AF_INET6] = af_inet6__scnprintf,
+};
+
+static size_t syscall_arg__scnprintf_augmented_sockaddr(struct syscall_arg *arg, char *bf, size_t size)
+{
+ struct sockaddr *sa = (struct sockaddr *)arg->augmented.args;
+ char family[32];
+ size_t printed;
+
+ strarray__scnprintf(&strarray__socket_families, family, sizeof(family), "%d", sa->sa_family);
+ printed = scnprintf(bf, size, "{ .family: %s", family);
+
+ if (sa->sa_family < ARRAY_SIZE(af_scnprintfs) && af_scnprintfs[sa->sa_family])
+ printed += af_scnprintfs[sa->sa_family](sa, bf + printed, size - printed);
+
+ return printed + scnprintf(bf + printed, size - printed, " }");
+}
+
+size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg)
+{
+ if (arg->augmented.args)
+ return syscall_arg__scnprintf_augmented_sockaddr(arg, bf, size);
+
+ return scnprintf(bf, size, "%#x", arg->val);
+}
libperf-y += counts.o
libperf-y += stat.o
libperf-y += stat-shadow.o
+libperf-y += stat-display.o
libperf-y += record.o
libperf-y += srcline.o
libperf-y += data.o
return evsel->evlist->env;
return NULL;
}
+
+static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+ int cpu, thread;
+
+ for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+ for (thread = 0; thread < xyarray__max_y(evsel->fd);
+ thread++) {
+ int fd = FD(evsel, cpu, thread);
+
+ if (perf_evlist__id_add_fd(evlist, evsel,
+ cpu, thread, fd) < 0)
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+ struct cpu_map *cpus = evsel->cpus;
+ struct thread_map *threads = evsel->threads;
+
+ if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr))
+ return -ENOMEM;
+
+ return store_evsel_ids(evsel, evlist);
+}
struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist);
#endif /* __PERF_EVSEL_H */
}
int perf_event__synthesize_attrs(struct perf_tool *tool,
- struct perf_session *session,
- perf_event__handler_t process)
+ struct perf_evlist *evlist,
+ perf_event__handler_t process)
{
struct perf_evsel *evsel;
int err = 0;
- evlist__for_each_entry(session->evlist, evsel) {
+ evlist__for_each_entry(evlist, evsel) {
err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
evsel->id, process);
if (err) {
struct perf_event_attr *attr, u32 ids, u64 *id,
perf_event__handler_t process);
int perf_event__synthesize_attrs(struct perf_tool *tool,
- struct perf_session *session,
+ struct perf_evlist *evlist,
perf_event__handler_t process);
int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
struct perf_evsel *evsel,
#define CLANG_BPF_CMD_DEFAULT_TEMPLATE \
"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \
- "$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
+ "$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
"-Wno-unused-value -Wno-pointer-sign " \
"-working-directory $WORKING_DIR " \
"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
build_id__sprintf(map->dso->build_id,
sizeof(map->dso->build_id),
sbuild_id);
- pr_warning("%s with build id %s not found",
- name, sbuild_id);
+ pr_debug("%s with build id %s not found", name, sbuild_id);
} else
- pr_warning("Failed to open %s", name);
+ pr_debug("Failed to open %s", name);
- pr_warning(", continuing without symbols\n");
+ pr_debug(", continuing without symbols\n");
return -1;
} else if (nr == 0) {
#ifdef HAVE_LIBELF_SUPPORT
if (len > sizeof(DSO__DELETED) &&
strcmp(name + real_len + 1, DSO__DELETED) == 0) {
- pr_warning("%.*s was updated (is prelink enabled?). "
+ pr_debug("%.*s was updated (is prelink enabled?). "
"Restart the long running apps that use it!\n",
(int)real_len, name);
} else {
- pr_warning("no symbols found in %s, maybe install "
- "a debug package?\n", name);
+ pr_debug("no symbols found in %s, maybe install a debug package?\n", name);
}
#endif
return -1;
if (verbose >= 2) {
if (use_browser) {
- pr_warning("overlapping maps in %s "
- "(disable tui for more info)\n",
+ pr_debug("overlapping maps in %s (disable tui for more info)\n",
map->dso->name);
} else {
fputs("overlapping maps:\n", fp);
#include <linux/bitops.h>
#include <linux/log2.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+
#include "cpumap.h"
#include "color.h"
#include "evsel.h"
#include "auxtrace.h"
#include "s390-cpumsf.h"
#include "s390-cpumsf-kernel.h"
+#include "config.h"
struct s390_cpumsf {
struct auxtrace auxtrace;
u32 pmu_type;
u16 machine_type;
bool data_queued;
+ bool use_logfile;
+ char *logdir;
};
struct s390_cpumsf_queue {
unsigned int queue_nr;
struct auxtrace_buffer *buffer;
int cpu;
+ FILE *logfile;
};
/* Display s390 CPU measurement facility basic-sampling data entry */
buffer->use_size = buffer->size;
buffer->use_data = buffer->data;
}
+ if (sfq->logfile) { /* Write into log file */
+ size_t rc = fwrite(buffer->data, buffer->size, 1,
+ sfq->logfile);
+ if (rc != 1)
+ pr_err("Failed to write auxiliary data\n");
+ }
} else
buffer = sfq->buffer;
return -ENOMEM;
buffer->use_size = buffer->size;
buffer->use_data = buffer->data;
+
+ if (sfq->logfile) { /* Write into log file */
+ size_t rc = fwrite(buffer->data, buffer->size, 1,
+ sfq->logfile);
+ if (rc != 1)
+ pr_err("Failed to write auxiliary data\n");
+ }
}
pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n",
__func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset,
sfq->sf = sf;
sfq->queue_nr = queue_nr;
sfq->cpu = -1;
+ if (sf->use_logfile) {
+ char *name;
+ int rc;
+
+ rc = (sf->logdir)
+ ? asprintf(&name, "%s/aux.smp.%02x",
+ sf->logdir, queue_nr)
+ : asprintf(&name, "aux.smp.%02x", queue_nr);
+ if (rc > 0)
+ sfq->logfile = fopen(name, "w");
+ if (sfq->logfile == NULL) {
+ pr_err("Failed to open auxiliary log file %s,"
+ "continue...\n", name);
+ sf->use_logfile = false;
+ }
+ free(name);
+ }
return sfq;
}
struct auxtrace_queues *queues = &sf->queues;
unsigned int i;
- for (i = 0; i < queues->nr_queues; i++)
+ for (i = 0; i < queues->nr_queues; i++) {
+ struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *)
+ queues->queue_array[i].priv;
+
+ if (sfq != NULL && sfq->logfile) {
+ fclose(sfq->logfile);
+ sfq->logfile = NULL;
+ }
zfree(&queues->queue_array[i].priv);
+ }
auxtrace_queues__free(queues);
}
auxtrace_heap__free(&sf->heap);
s390_cpumsf_free_queues(session);
session->auxtrace = NULL;
+ free(sf->logdir);
free(sf);
}
/* Check itrace options set on perf report command.
* Return true, if none are set or all options specified can be
- * handled on s390.
+ * handled on s390 (currently only option 'd' for logging.
* Return false otherwise.
*/
static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
{
+ bool ison = false;
+
if (!itops || !itops->set)
return true;
- pr_err("No --itrace options supported\n");
+ ison = itops->inject || itops->instructions || itops->branches ||
+ itops->transactions || itops->ptwrites ||
+ itops->pwr_events || itops->errors ||
+ itops->dont_decode || itops->calls || itops->returns ||
+ itops->callchain || itops->thread_stack ||
+ itops->last_branch;
+ if (!ison)
+ return true;
+ pr_err("Unsupported --itrace options specified\n");
return false;
}
+/* Check for AUXTRACE dump directory if it is needed.
+ * On failure print an error message but continue.
+ * Return 0 on wrong keyword in config file and 1 otherwise.
+ */
+static int s390_cpumsf__config(const char *var, const char *value, void *cb)
+{
+ struct s390_cpumsf *sf = cb;
+ struct stat stbuf;
+ int rc;
+
+ if (strcmp(var, "auxtrace.dumpdir"))
+ return 0;
+ sf->logdir = strdup(value);
+ if (sf->logdir == NULL) {
+ pr_err("Failed to find auxtrace log directory %s,"
+ " continue with current directory...\n", value);
+ return 1;
+ }
+ rc = stat(sf->logdir, &stbuf);
+ if (rc == -1 || !S_ISDIR(stbuf.st_mode)) {
+ pr_err("Missing auxtrace log directory %s,"
+ " continue with current directory...\n", value);
+ free(sf->logdir);
+ sf->logdir = NULL;
+ }
+ return 1;
+}
+
int s390_cpumsf_process_auxtrace_info(union perf_event *event,
struct perf_session *session)
{
err = -EINVAL;
goto err_free;
}
+ sf->use_logfile = session->itrace_synth_opts->log;
+ if (sf->use_logfile)
+ perf_config(s390_cpumsf__config, sf);
err = auxtrace_queues__init(&sf->queues);
if (err)
auxtrace_queues__free(&sf->queues);
session->auxtrace = NULL;
err_free:
+ free(sf->logdir);
free(sf);
return err;
}
--- /dev/null
+#include <stdio.h>
+#include <inttypes.h>
+#include <linux/time64.h>
+#include <math.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "stat.h"
+#include "top.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "string2.h"
+#include "sane_ctype.h"
+#include "cgroup.h"
+#include <math.h>
+#include <api/fs/fs.h>
+
+#define CNTR_NOT_SUPPORTED "<not supported>"
+#define CNTR_NOT_COUNTED "<not counted>"
+
+static bool is_duration_time(struct perf_evsel *evsel)
+{
+ return !strcmp(evsel->name, "duration_time");
+}
+
+static void print_running(struct perf_stat_config *config,
+ u64 run, u64 ena)
+{
+ if (config->csv_output) {
+ fprintf(config->output, "%s%" PRIu64 "%s%.2f",
+ config->csv_sep,
+ run,
+ config->csv_sep,
+ ena ? 100.0 * run / ena : 100.0);
+ } else if (run != ena) {
+ fprintf(config->output, " (%.2f%%)", 100.0 * run / ena);
+ }
+}
+
+static void print_noise_pct(struct perf_stat_config *config,
+ double total, double avg)
+{
+ double pct = rel_stddev_stats(total, avg);
+
+ if (config->csv_output)
+ fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
+ else if (pct)
+ fprintf(config->output, " ( +-%6.2f%% )", pct);
+}
+
+static void print_noise(struct perf_stat_config *config,
+ struct perf_evsel *evsel, double avg)
+{
+ struct perf_stat_evsel *ps;
+
+ if (config->run_count == 1)
+ return;
+
+ ps = evsel->stats;
+ print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
+}
+
+static void aggr_printout(struct perf_stat_config *config,
+ struct perf_evsel *evsel, int id, int nr)
+{
+ switch (config->aggr_mode) {
+ case AGGR_CORE:
+ fprintf(config->output, "S%d-C%*d%s%*d%s",
+ cpu_map__id_to_socket(id),
+ config->csv_output ? 0 : -8,
+ cpu_map__id_to_cpu(id),
+ config->csv_sep,
+ config->csv_output ? 0 : 4,
+ nr,
+ config->csv_sep);
+ break;
+ case AGGR_SOCKET:
+ fprintf(config->output, "S%*d%s%*d%s",
+ config->csv_output ? 0 : -5,
+ id,
+ config->csv_sep,
+ config->csv_output ? 0 : 4,
+ nr,
+ config->csv_sep);
+ break;
+ case AGGR_NONE:
+ fprintf(config->output, "CPU%*d%s",
+ config->csv_output ? 0 : -4,
+ perf_evsel__cpus(evsel)->map[id], config->csv_sep);
+ break;
+ case AGGR_THREAD:
+ fprintf(config->output, "%*s-%*d%s",
+ config->csv_output ? 0 : 16,
+ thread_map__comm(evsel->threads, id),
+ config->csv_output ? 0 : -8,
+ thread_map__pid(evsel->threads, id),
+ config->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(struct perf_stat_config *config __maybe_unused,
+ void *ctx)
+{
+ struct outstate *os = ctx;
+
+ os->newline = true;
+}
+
+static void do_new_line_std(struct perf_stat_config *config,
+ struct outstate *os)
+{
+ fputc('\n', os->fh);
+ fputs(os->prefix, os->fh);
+ aggr_printout(config, os->evsel, os->id, os->nr);
+ if (config->aggr_mode == AGGR_NONE)
+ fprintf(os->fh, " ");
+ fprintf(os->fh, " ");
+}
+
+static void print_metric_std(struct perf_stat_config *config,
+ 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(config, 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(struct perf_stat_config *config, void *ctx)
+{
+ struct outstate *os = ctx;
+ int i;
+
+ fputc('\n', os->fh);
+ if (os->prefix)
+ fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
+ aggr_printout(config, os->evsel, os->id, os->nr);
+ for (i = 0; i < os->nfields; i++)
+ fputs(config->csv_sep, os->fh);
+}
+
+static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
+ 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", config->csv_sep, config->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", config->csv_sep, vals, config->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(struct perf_stat_config *config,
+ 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 = config->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(struct perf_stat_config *config __maybe_unused,
+ 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, config->csv_sep);
+}
+
+static void new_line_metric(struct perf_stat_config *config __maybe_unused,
+ void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(struct perf_stat_config *config,
+ 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 (config->csv_output)
+ fprintf(os->fh, "%s%s", unit, config->csv_sep);
+ else
+ fprintf(os->fh, "%*s ", config->metric_only_len, unit);
+}
+
+static int first_shadow_cpu(struct perf_stat_config *config,
+ struct perf_evsel *evsel, int id)
+{
+ struct perf_evlist *evlist = evsel->evlist;
+ int i;
+
+ if (!config->aggr_get_id)
+ return 0;
+
+ if (config->aggr_mode == AGGR_NONE)
+ return id;
+
+ if (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 (config->aggr_get_id(config, evlist->cpus, cpu2) == id)
+ return cpu2;
+ }
+ return 0;
+}
+
+static void abs_printout(struct perf_stat_config *config,
+ int id, int nr, struct perf_evsel *evsel, double avg)
+{
+ FILE *output = config->output;
+ double sc = evsel->scale;
+ const char *fmt;
+
+ if (config->csv_output) {
+ fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s";
+ } else {
+ if (config->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(config, evsel, id, nr);
+
+ fprintf(output, fmt, avg, config->csv_sep);
+
+ if (evsel->unit)
+ fprintf(output, "%-*s%s",
+ config->csv_output ? 0 : config->unit_width,
+ evsel->unit, config->csv_sep);
+
+ fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
+
+ if (evsel->cgrp)
+ fprintf(output, "%s%s", config->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(struct perf_stat_config *config, 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 = config->output,
+ .prefix = prefix ? prefix : "",
+ .id = id,
+ .nr = nr,
+ .evsel = counter,
+ };
+ print_metric_t pm = print_metric_std;
+ new_line_t nl;
+
+ if (config->metric_only) {
+ nl = new_line_metric;
+ if (config->csv_output)
+ pm = print_metric_only_csv;
+ else
+ pm = print_metric_only;
+ } else
+ nl = new_line_std;
+
+ if (config->csv_output && !config->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[config->aggr_mode];
+ if (counter->cgrp)
+ os.nfields++;
+ }
+ if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+ if (config->metric_only) {
+ pm(config, &os, NULL, "", "", 0);
+ return;
+ }
+ aggr_printout(config, counter, id, nr);
+
+ fprintf(config->output, "%*s%s",
+ config->csv_output ? 0 : 18,
+ counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+ config->csv_sep);
+
+ if (counter->supported) {
+ config->print_free_counters_hint = 1;
+ if (is_mixed_hw_group(counter))
+ config->print_mixed_hw_group_error = 1;
+ }
+
+ fprintf(config->output, "%-*s%s",
+ config->csv_output ? 0 : config->unit_width,
+ counter->unit, config->csv_sep);
+
+ fprintf(config->output, "%*s",
+ config->csv_output ? 0 : -25,
+ perf_evsel__name(counter));
+
+ if (counter->cgrp)
+ fprintf(config->output, "%s%s",
+ config->csv_sep, counter->cgrp->name);
+
+ if (!config->csv_output)
+ pm(config, &os, NULL, NULL, "", 0);
+ print_noise(config, counter, noise);
+ print_running(config, run, ena);
+ if (config->csv_output)
+ pm(config, &os, NULL, NULL, "", 0);
+ return;
+ }
+
+ if (!config->metric_only)
+ abs_printout(config, id, nr, counter, uval);
+
+ out.print_metric = pm;
+ out.new_line = nl;
+ out.ctx = &os;
+ out.force_header = false;
+
+ if (config->csv_output && !config->metric_only) {
+ print_noise(config, counter, noise);
+ print_running(config, run, ena);
+ }
+
+ perf_stat__print_shadow_stats(config, counter, uval,
+ first_shadow_cpu(config, counter, id),
+ &out, &config->metric_events, st);
+ if (!config->csv_output && !config->metric_only) {
+ print_noise(config, counter, noise);
+ print_running(config, run, ena);
+ }
+}
+
+static void aggr_update_shadow(struct perf_stat_config *config,
+ struct perf_evlist *evlist)
+{
+ int cpu, s2, id, s;
+ u64 val;
+ struct perf_evsel *counter;
+
+ for (s = 0; s < config->aggr_map->nr; s++) {
+ id = config->aggr_map->map[s];
+ evlist__for_each_entry(evlist, counter) {
+ val = 0;
+ for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+ s2 = config->aggr_get_id(config, evlist->cpus, cpu);
+ if (s2 != id)
+ continue;
+ val += perf_counts(counter->counts, cpu, 0)->val;
+ }
+ perf_stat__update_shadow_stats(counter, val,
+ first_shadow_cpu(config, 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_stat_config *config, struct perf_evsel *counter,
+ void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+ bool first),
+ void *data)
+{
+ struct perf_evlist *evlist = counter->evlist;
+ struct perf_evsel *alias;
+
+ alias = list_prepare_entry(counter, &(evlist->entries), node);
+ list_for_each_entry_continue (alias, &evlist->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(config, alias, data, false);
+ }
+}
+
+static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter,
+ void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+ bool first),
+ void *data)
+{
+ if (counter->merged_stat)
+ return false;
+ cb(config, counter, data, true);
+ if (config->no_merge)
+ uniquify_event_name(counter);
+ else if (counter->auto_merge_stats)
+ collect_all_aliases(config, counter, cb, data);
+ return true;
+}
+
+struct aggr_data {
+ u64 ena, run, val;
+ int id;
+ int nr;
+ int cpu;
+};
+
+static void aggr_cb(struct perf_stat_config *config,
+ 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 = config->aggr_get_id(config, 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(struct perf_stat_config *config,
+ struct perf_evlist *evlist,
+ char *prefix)
+{
+ bool metric_only = config->metric_only;
+ FILE *output = config->output;
+ struct perf_evsel *counter;
+ int s, id, nr;
+ double uval;
+ u64 ena, run, val;
+ bool first;
+
+ if (!(config->aggr_map || config->aggr_get_id))
+ return;
+
+ aggr_update_shadow(config, evlist);
+
+ /*
+ * With metric_only everything is on a single line.
+ * Without each counter has its own line.
+ */
+ for (s = 0; s < config->aggr_map->nr; s++) {
+ struct aggr_data ad;
+ if (prefix && metric_only)
+ fprintf(output, "%s", prefix);
+
+ ad.id = id = config->aggr_map->map[s];
+ first = true;
+ evlist__for_each_entry(evlist, counter) {
+ if (is_duration_time(counter))
+ continue;
+
+ ad.val = ad.ena = ad.run = 0;
+ ad.nr = 0;
+ if (!collect_data(config, 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(config, counter, id, nr);
+ }
+ if (prefix && !metric_only)
+ fprintf(output, "%s", prefix);
+
+ uval = val * counter->scale;
+ printout(config, 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,
+ struct target *_target)
+{
+ 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_stat_config *config,
+ struct target *_target,
+ struct perf_evsel *counter, char *prefix)
+{
+ FILE *output = 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, _target);
+ 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 (config->stats)
+ printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+ prefix, buf[thread].run, buf[thread].ena, 1.0,
+ &config->stats[id]);
+ else
+ printout(config, 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_stat_config *config __maybe_unused,
+ 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_stat_config *config,
+ struct perf_evsel *counter, char *prefix)
+{
+ bool metric_only = config->metric_only;
+ FILE *output = config->output;
+ double uval;
+ struct caggr_data cd = { .avg = 0.0 };
+
+ if (!collect_data(config, counter, counter_aggr_cb, &cd))
+ return;
+
+ if (prefix && !metric_only)
+ fprintf(output, "%s", prefix);
+
+ uval = cd.avg * counter->scale;
+ printout(config, -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_stat_config *config __maybe_unused,
+ 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_stat_config *config,
+ struct perf_evsel *counter, char *prefix)
+{
+ FILE *output = 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(config, 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(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+ &rt_stat);
+
+ fputc('\n', output);
+ }
+}
+
+static void print_no_aggr_metric(struct perf_stat_config *config,
+ struct perf_evlist *evlist,
+ char *prefix)
+{
+ int cpu;
+ int nrcpus = 0;
+ struct perf_evsel *counter;
+ u64 ena, run, val;
+ double uval;
+
+ nrcpus = evlist->cpus->nr;
+ for (cpu = 0; cpu < nrcpus; cpu++) {
+ bool first = true;
+
+ if (prefix)
+ fputs(prefix, config->output);
+ evlist__for_each_entry(evlist, counter) {
+ if (is_duration_time(counter))
+ continue;
+ if (first) {
+ aggr_printout(config, 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(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+ &rt_stat);
+ }
+ fputc('\n', 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(struct perf_stat_config *config,
+ struct perf_evlist *evlist,
+ const char *prefix, bool no_indent)
+{
+ struct perf_stat_output_ctx out;
+ struct perf_evsel *counter;
+ struct outstate os = {
+ .fh = config->output
+ };
+
+ if (prefix)
+ fprintf(config->output, "%s", prefix);
+
+ if (!config->csv_output && !no_indent)
+ fprintf(config->output, "%*s",
+ aggr_header_lens[config->aggr_mode], "");
+ if (config->csv_output) {
+ if (config->interval)
+ fputs("time,", config->output);
+ fputs(aggr_header_csv[config->aggr_mode], config->output);
+ }
+
+ /* Print metrics headers only */
+ evlist__for_each_entry(evlist, 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(config, counter, 0,
+ 0,
+ &out,
+ &config->metric_events,
+ &rt_stat);
+ }
+ fputc('\n', config->output);
+}
+
+static void print_interval(struct perf_stat_config *config,
+ struct perf_evlist *evlist,
+ char *prefix, struct timespec *ts)
+{
+ bool metric_only = config->metric_only;
+ unsigned int unit_width = config->unit_width;
+ FILE *output = config->output;
+ static int num_print_interval;
+
+ if (config->interval_clear)
+ puts(CONSOLE_CLEAR);
+
+ sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
+
+ if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
+ switch (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 || config->interval_clear) && metric_only)
+ print_metric_headers(config, evlist, " ", true);
+ if (++num_print_interval == 25)
+ num_print_interval = 0;
+}
+
+static void print_header(struct perf_stat_config *config,
+ struct target *_target,
+ int argc, const char **argv)
+{
+ FILE *output = config->output;
+ int i;
+
+ fflush(stdout);
+
+ if (!config->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 (config->run_count > 1)
+ fprintf(output, " (%d runs)", config->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(struct perf_stat_config *config,
+ 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 < config->run_count; idx++) {
+ double run = (double) config->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(struct perf_stat_config *config)
+{
+ double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+ FILE *output = config->output;
+ int n;
+
+ if (!config->null_run)
+ fprintf(output, "\n");
+
+ if (config->run_count == 1) {
+ fprintf(output, " %17.9f seconds time elapsed", avg);
+
+ if (config->ru_display) {
+ double ru_utime = timeval2double(&config->ru_data.ru_utime);
+ double ru_stime = timeval2double(&config->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(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+ /*
+ * Display at most 2 more significant
+ * digits than the stddev inaccuracy.
+ */
+ int precision = get_precision(sd) + 2;
+
+ if (config->walltime_run_table)
+ print_table(config, output, precision, avg);
+
+ fprintf(output, " %17.*f +- %.*f seconds time elapsed",
+ precision, avg, precision, sd);
+
+ print_noise_pct(config, sd, avg);
+ }
+ fprintf(output, "\n\n");
+
+ if (config->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 (config->print_mixed_hw_group_error)
+ fprintf(output,
+ "The events in group usually have to be from "
+ "the same PMU. Try reorganizing the group.\n");
+}
+
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+ struct perf_stat_config *config,
+ struct target *_target,
+ struct timespec *ts,
+ int argc, const char **argv)
+{
+ bool metric_only = config->metric_only;
+ int interval = config->interval;
+ struct perf_evsel *counter;
+ char buf[64], *prefix = NULL;
+
+ if (interval)
+ print_interval(config, evlist, prefix = buf, ts);
+ else
+ print_header(config, _target, argc, argv);
+
+ if (metric_only) {
+ static int num_print_iv;
+
+ if (num_print_iv == 0 && !interval)
+ print_metric_headers(config, evlist, prefix, false);
+ if (num_print_iv++ == 25)
+ num_print_iv = 0;
+ if (config->aggr_mode == AGGR_GLOBAL && prefix)
+ fprintf(config->output, "%s", prefix);
+ }
+
+ switch (config->aggr_mode) {
+ case AGGR_CORE:
+ case AGGR_SOCKET:
+ print_aggr(config, evlist, prefix);
+ break;
+ case AGGR_THREAD:
+ evlist__for_each_entry(evlist, counter) {
+ if (is_duration_time(counter))
+ continue;
+ print_aggr_thread(config, _target, counter, prefix);
+ }
+ break;
+ case AGGR_GLOBAL:
+ evlist__for_each_entry(evlist, counter) {
+ if (is_duration_time(counter))
+ continue;
+ print_counter_aggr(config, counter, prefix);
+ }
+ if (metric_only)
+ fputc('\n', config->output);
+ break;
+ case AGGR_NONE:
+ if (metric_only)
+ print_no_aggr_metric(config, evlist, prefix);
+ else {
+ evlist__for_each_entry(evlist, counter) {
+ if (is_duration_time(counter))
+ continue;
+ print_counter(config, counter, prefix);
+ }
+ }
+ break;
+ case AGGR_UNSET:
+ default:
+ break;
+ }
+
+ if (!interval && !config->csv_output)
+ print_footer(config);
+
+ fflush(config->output);
+}
return v->stats.n;
}
-static void print_stalled_cycles_frontend(int cpu,
+static void print_stalled_cycles_frontend(struct perf_stat_config *config,
+ int cpu,
struct perf_evsel *evsel, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st)
color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
if (ratio)
- out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle",
ratio);
else
- out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
+ out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0);
}
-static void print_stalled_cycles_backend(int cpu,
+static void print_stalled_cycles_backend(struct perf_stat_config *config,
+ int cpu,
struct perf_evsel *evsel, double avg,
struct perf_stat_output_ctx *out,
struct runtime_stat *st)
color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
- out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
}
-static void print_branch_misses(int cpu,
+static void print_branch_misses(struct perf_stat_config *config,
+ int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio);
}
-static void print_l1_dcache_misses(int cpu,
+static void print_l1_dcache_misses(struct perf_stat_config *config,
+ int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
}
-static void print_l1_icache_misses(int cpu,
+static void print_l1_icache_misses(struct perf_stat_config *config,
+ int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
}
-static void print_dtlb_cache_misses(int cpu,
+static void print_dtlb_cache_misses(struct perf_stat_config *config,
+ int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
}
-static void print_itlb_cache_misses(int cpu,
+static void print_itlb_cache_misses(struct perf_stat_config *config,
+ int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
}
-static void print_ll_cache_misses(int cpu,
+static void print_ll_cache_misses(struct perf_stat_config *config,
+ int cpu,
struct perf_evsel *evsel,
double avg,
struct perf_stat_output_ctx *out,
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
- out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+ out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
}
/*
return sanitize_val(1.0 - sum);
}
-static void print_smi_cost(int cpu, struct perf_evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config,
+ int cpu, struct perf_evsel *evsel,
struct perf_stat_output_ctx *out,
struct runtime_stat *st)
{
if (cost > 10)
color = PERF_COLOR_RED;
- out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
- out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
+ out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
+ out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num);
}
-static void generic_metric(const char *metric_expr,
+static void generic_metric(struct perf_stat_config *config,
+ const char *metric_expr,
struct perf_evsel **metric_events,
char *name,
const char *metric_name,
const char *p = metric_expr;
if (expr__parse(&ratio, &pctx, &p) == 0)
- print_metric(ctxp, NULL, "%8.1f",
+ print_metric(config, ctxp, NULL, "%8.1f",
metric_name ?
metric_name :
out->force_header ? name : "",
ratio);
else
- print_metric(ctxp, NULL, NULL,
+ print_metric(config, ctxp, NULL, NULL,
out->force_header ?
(metric_name ? metric_name : name) : "", 0);
} else
- print_metric(ctxp, NULL, NULL, "", 0);
+ print_metric(config, ctxp, NULL, NULL, "", 0);
}
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+ struct perf_evsel *evsel,
double avg, int cpu,
struct perf_stat_output_ctx *out,
struct rblist *metric_events,
if (total) {
ratio = avg / total;
- print_metric(ctxp, NULL, "%7.2f ",
+ print_metric(config, ctxp, NULL, "%7.2f ",
"insn per cycle", ratio);
} else {
- print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
+ print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
}
total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
ctx, cpu));
if (total && avg) {
- out->new_line(ctxp);
+ out->new_line(config, ctxp);
ratio = total / avg;
- print_metric(ctxp, NULL, "%7.2f ",
+ print_metric(config, ctxp, NULL, "%7.2f ",
"stalled cycles per insn",
ratio);
} else if (have_frontend_stalled) {
- print_metric(ctxp, NULL, NULL,
+ print_metric(config, ctxp, NULL, NULL,
"stalled cycles per insn", 0);
}
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
- print_branch_misses(cpu, evsel, avg, out, st);
+ print_branch_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(ctxp, NULL, NULL, "of all branches", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
- print_l1_dcache_misses(cpu, evsel, avg, out, st);
+ print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
- print_l1_icache_misses(cpu, evsel, avg, out, st);
+ print_l1_icache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
- print_dtlb_cache_misses(cpu, evsel, avg, out, st);
+ print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
- print_itlb_cache_misses(cpu, evsel, avg, out, st);
+ print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
- print_ll_cache_misses(cpu, evsel, avg, out, st);
+ print_ll_cache_misses(config, cpu, evsel, avg, out, st);
else
- print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
ratio = avg * 100 / total;
if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
- print_metric(ctxp, NULL, "%8.3f %%",
+ print_metric(config, ctxp, NULL, "%8.3f %%",
"of all cache refs", ratio);
else
- print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
+ print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(cpu, evsel, avg, out, st);
+ print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(cpu, evsel, avg, out, st);
+ print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
if (total) {
ratio = avg / total;
- print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
+ print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio);
} else {
- print_metric(ctxp, NULL, NULL, "Ghz", 0);
+ print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
}
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
if (total)
- print_metric(ctxp, NULL,
+ print_metric(config, ctxp, NULL,
"%7.2f%%", "transactional cycles",
100.0 * (avg / total));
else
- print_metric(ctxp, NULL, NULL, "transactional cycles",
+ print_metric(config, ctxp, NULL, NULL, "transactional cycles",
0);
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
if (total2 < avg)
total2 = avg;
if (total)
- print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
+ print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles",
100.0 * ((total2-avg) / total));
else
- print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+ print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
ctx, cpu);
ratio = total / avg;
if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
- print_metric(ctxp, NULL, "%8.0f",
+ print_metric(config, ctxp, NULL, "%8.0f",
"cycles / transaction", ratio);
else
- print_metric(ctxp, NULL, NULL, "cycles / transaction",
+ print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
0);
} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
if (avg)
ratio = total / avg;
- print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
+ print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
} else if (perf_evsel__is_clock(evsel)) {
if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
- print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+ print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
avg / (ratio * evsel->scale));
else
- print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
+ print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
double fe_bound = td_fe_bound(ctx, cpu, st);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
- print_metric(ctxp, color, "%8.1f%%", "frontend bound",
+ print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
double retiring = td_retiring(ctx, cpu, st);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
- print_metric(ctxp, color, "%8.1f%%", "retiring",
+ print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
double bad_spec = td_bad_spec(ctx, cpu, st);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
- print_metric(ctxp, color, "%8.1f%%", "bad speculation",
+ print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
double be_bound = td_be_bound(ctx, cpu, st);
if (be_bound > 0.2)
color = PERF_COLOR_RED;
if (td_total_slots(ctx, cpu, st) > 0)
- print_metric(ctxp, color, "%8.1f%%", name,
+ print_metric(config, ctxp, color, "%8.1f%%", name,
be_bound * 100.);
else
- print_metric(ctxp, NULL, NULL, name, 0);
+ print_metric(config, ctxp, NULL, NULL, name, 0);
} else if (evsel->metric_expr) {
- generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+ generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
evsel->metric_name, avg, cpu, out, st);
} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
char unit = 'M';
unit = 'K';
}
snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
- print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
+ print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
- print_smi_cost(cpu, evsel, out, st);
+ print_smi_cost(config, cpu, evsel, out, st);
} else {
num = 0;
}
list_for_each_entry (mexp, &me->head, nd) {
if (num++ > 0)
- out->new_line(ctxp);
- generic_metric(mexp->metric_expr, mexp->metric_events,
+ out->new_line(config, ctxp);
+ generic_metric(config, mexp->metric_expr, mexp->metric_events,
evsel->name, mexp->metric_name,
avg, cpu, out, st);
}
}
if (num == 0)
- print_metric(ctxp, NULL, NULL, NULL, 0);
+ print_metric(config, ctxp, NULL, NULL, NULL, 0);
}
return ret;
}
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+ struct perf_stat_config *config,
+ struct target *target)
+{
+ struct perf_event_attr *attr = &evsel->attr;
+ struct perf_evsel *leader = evsel->leader;
+
+ if (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 = !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;
+
+ /*
+ * 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) && !config->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->threads);
+}
+
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+ struct perf_tool *tool,
+ struct perf_evlist *evlist,
+ perf_event__handler_t process,
+ bool attrs)
+{
+ int err;
+
+ if (attrs) {
+ err = perf_event__synthesize_attrs(tool, evlist, process);
+ if (err < 0) {
+ pr_err("Couldn't synthesize attrs.\n");
+ return err;
+ }
+ }
+
+ err = perf_event__synthesize_extra_attr(tool, evlist, process,
+ attrs);
+
+ err = perf_event__synthesize_thread_map2(tool, evlist->threads,
+ process, NULL);
+ if (err < 0) {
+ pr_err("Couldn't synthesize thread map.\n");
+ return err;
+ }
+
+ err = perf_event__synthesize_cpu_map(tool, evlist->cpus,
+ process, NULL);
+ if (err < 0) {
+ pr_err("Couldn't synthesize thread map.\n");
+ return err;
+ }
+
+ err = perf_event__synthesize_stat_config(tool, config, process, NULL);
+ if (err < 0) {
+ pr_err("Couldn't synthesize config.\n");
+ return err;
+ }
+
+ return 0;
+}
#include <linux/types.h>
#include <stdio.h>
+#include <sys/types.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/wait.h>
#include "xyarray.h"
#include "rblist.h"
+#include "perf.h"
+#include "event.h"
struct stats {
double n, mean, M2;
struct rblist value_list;
};
+typedef int (*aggr_get_id_t)(struct perf_stat_config *config,
+ struct cpu_map *m, int cpu);
+
struct perf_stat_config {
- enum aggr_mode aggr_mode;
- bool scale;
- FILE *output;
- unsigned int interval;
- unsigned int timeout;
- int times;
- struct runtime_stat *stats;
- int stats_num;
+ enum aggr_mode aggr_mode;
+ bool scale;
+ bool no_inherit;
+ bool identifier;
+ bool csv_output;
+ bool interval_clear;
+ bool metric_only;
+ bool null_run;
+ bool ru_display;
+ bool big_num;
+ bool no_merge;
+ bool walltime_run_table;
+ FILE *output;
+ unsigned int interval;
+ unsigned int timeout;
+ unsigned int initial_delay;
+ unsigned int unit_width;
+ unsigned int metric_only_len;
+ int times;
+ int run_count;
+ int print_free_counters_hint;
+ int print_mixed_hw_group_error;
+ struct runtime_stat *stats;
+ int stats_num;
+ const char *csv_sep;
+ struct stats *walltime_nsecs_stats;
+ struct rusage ru_data;
+ struct cpu_map *aggr_map;
+ aggr_get_id_t aggr_get_id;
+ struct cpu_map *cpus_aggr_map;
+ u64 *walltime_run;
+ struct rblist metric_events;
};
void update_stats(struct stats *stats, u64 val);
extern struct runtime_stat rt_stat;
extern struct stats walltime_nsecs_stats;
-typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+typedef void (*print_metric_t)(struct perf_stat_config *config,
+ void *ctx, const char *color, const char *unit,
const char *fmt, double val);
-typedef void (*new_line_t )(void *ctx);
+typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
void runtime_stat__init(struct runtime_stat *st);
void runtime_stat__exit(struct runtime_stat *st);
bool force_header;
};
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+ struct perf_evsel *evsel,
double avg, int cpu,
struct perf_stat_output_ctx *out,
struct rblist *metric_events,
size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+ struct perf_stat_config *config,
+ struct target *target);
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+ struct perf_tool *tool,
+ struct perf_evlist *evlist,
+ perf_event__handler_t process,
+ bool attrs);
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+ struct perf_stat_config *config,
+ struct target *_target,
+ struct timespec *ts,
+ int argc, const char **argv);
#endif
#define _PERF_UTIL_TRACE_EVENT_H
#include <traceevent/event-parse.h>
+#include <traceevent/trace-seq.h>
#include "parse-events.h"
struct machine;
projects / linux.git / commitdiff