mirror of https://gitee.com/openkylin/linux.git
996 lines
27 KiB
C
996 lines
27 KiB
C
/*
|
|
* builtin-report.c
|
|
*
|
|
* Builtin report command: Analyze the perf.data input file,
|
|
* look up and read DSOs and symbol information and display
|
|
* a histogram of results, along various sorting keys.
|
|
*/
|
|
#include "builtin.h"
|
|
|
|
#include "util/util.h"
|
|
#include "util/cache.h"
|
|
|
|
#include "util/annotate.h"
|
|
#include "util/color.h"
|
|
#include <linux/list.h>
|
|
#include <linux/rbtree.h>
|
|
#include "util/symbol.h"
|
|
#include "util/callchain.h"
|
|
#include "util/strlist.h"
|
|
#include "util/values.h"
|
|
|
|
#include "perf.h"
|
|
#include "util/debug.h"
|
|
#include "util/evlist.h"
|
|
#include "util/evsel.h"
|
|
#include "util/header.h"
|
|
#include "util/session.h"
|
|
#include "util/tool.h"
|
|
|
|
#include "util/parse-options.h"
|
|
#include "util/parse-events.h"
|
|
|
|
#include "util/thread.h"
|
|
#include "util/sort.h"
|
|
#include "util/hist.h"
|
|
#include "util/data.h"
|
|
#include "arch/common.h"
|
|
|
|
#include <dlfcn.h>
|
|
#include <linux/bitmap.h>
|
|
|
|
struct perf_report {
|
|
struct perf_tool tool;
|
|
struct perf_session *session;
|
|
bool force, use_tui, use_gtk, use_stdio;
|
|
bool hide_unresolved;
|
|
bool dont_use_callchains;
|
|
bool show_full_info;
|
|
bool show_threads;
|
|
bool inverted_callchain;
|
|
bool mem_mode;
|
|
struct perf_read_values show_threads_values;
|
|
const char *pretty_printing_style;
|
|
const char *cpu_list;
|
|
const char *symbol_filter_str;
|
|
float min_percent;
|
|
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
|
|
};
|
|
|
|
static int perf_report_config(const char *var, const char *value, void *cb)
|
|
{
|
|
if (!strcmp(var, "report.group")) {
|
|
symbol_conf.event_group = perf_config_bool(var, value);
|
|
return 0;
|
|
}
|
|
if (!strcmp(var, "report.percent-limit")) {
|
|
struct perf_report *rep = cb;
|
|
rep->min_percent = strtof(value, NULL);
|
|
return 0;
|
|
}
|
|
|
|
return perf_default_config(var, value, cb);
|
|
}
|
|
|
|
static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
|
|
struct addr_location *al,
|
|
struct perf_sample *sample,
|
|
struct perf_evsel *evsel,
|
|
struct machine *machine,
|
|
union perf_event *event)
|
|
{
|
|
struct perf_report *rep = container_of(tool, struct perf_report, tool);
|
|
struct symbol *parent = NULL;
|
|
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
|
|
int err = 0;
|
|
struct hist_entry *he;
|
|
struct mem_info *mi, *mx;
|
|
uint64_t cost;
|
|
|
|
if ((sort__has_parent || symbol_conf.use_callchain) &&
|
|
sample->callchain) {
|
|
err = machine__resolve_callchain(machine, evsel, al->thread,
|
|
sample, &parent, al);
|
|
if (err)
|
|
return err;
|
|
}
|
|
|
|
mi = machine__resolve_mem(machine, al->thread, sample, cpumode);
|
|
if (!mi)
|
|
return -ENOMEM;
|
|
|
|
if (rep->hide_unresolved && !al->sym)
|
|
return 0;
|
|
|
|
cost = sample->weight;
|
|
if (!cost)
|
|
cost = 1;
|
|
|
|
/*
|
|
* must pass period=weight in order to get the correct
|
|
* sorting from hists__collapse_resort() which is solely
|
|
* based on periods. We want sorting be done on nr_events * weight
|
|
* and this is indirectly achieved by passing period=weight here
|
|
* and the he_stat__add_period() function.
|
|
*/
|
|
he = __hists__add_mem_entry(&evsel->hists, al, parent, mi, cost, cost);
|
|
if (!he)
|
|
return -ENOMEM;
|
|
|
|
/*
|
|
* In the TUI browser, we are doing integrated annotation,
|
|
* so we don't allocate the extra space needed because the stdio
|
|
* code will not use it.
|
|
*/
|
|
if (sort__has_sym && he->ms.sym && use_browser > 0) {
|
|
struct annotation *notes = symbol__annotation(he->ms.sym);
|
|
|
|
assert(evsel != NULL);
|
|
|
|
if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
|
|
goto out;
|
|
|
|
err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
|
|
if (err)
|
|
goto out;
|
|
}
|
|
|
|
if (sort__has_sym && he->mem_info->daddr.sym && use_browser > 0) {
|
|
struct annotation *notes;
|
|
|
|
mx = he->mem_info;
|
|
|
|
notes = symbol__annotation(mx->daddr.sym);
|
|
if (notes->src == NULL && symbol__alloc_hist(mx->daddr.sym) < 0)
|
|
goto out;
|
|
|
|
err = symbol__inc_addr_samples(mx->daddr.sym,
|
|
mx->daddr.map,
|
|
evsel->idx,
|
|
mx->daddr.al_addr);
|
|
if (err)
|
|
goto out;
|
|
}
|
|
|
|
evsel->hists.stats.total_period += cost;
|
|
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
|
|
err = 0;
|
|
|
|
if (symbol_conf.use_callchain) {
|
|
err = callchain_append(he->callchain,
|
|
&callchain_cursor,
|
|
sample->period);
|
|
}
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
|
|
struct addr_location *al,
|
|
struct perf_sample *sample,
|
|
struct perf_evsel *evsel,
|
|
struct machine *machine)
|
|
{
|
|
struct perf_report *rep = container_of(tool, struct perf_report, tool);
|
|
struct symbol *parent = NULL;
|
|
int err = 0;
|
|
unsigned i;
|
|
struct hist_entry *he;
|
|
struct branch_info *bi, *bx;
|
|
|
|
if ((sort__has_parent || symbol_conf.use_callchain)
|
|
&& sample->callchain) {
|
|
err = machine__resolve_callchain(machine, evsel, al->thread,
|
|
sample, &parent, al);
|
|
if (err)
|
|
return err;
|
|
}
|
|
|
|
bi = machine__resolve_bstack(machine, al->thread,
|
|
sample->branch_stack);
|
|
if (!bi)
|
|
return -ENOMEM;
|
|
|
|
for (i = 0; i < sample->branch_stack->nr; i++) {
|
|
if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
|
|
continue;
|
|
|
|
err = -ENOMEM;
|
|
|
|
/*
|
|
* The report shows the percentage of total branches captured
|
|
* and not events sampled. Thus we use a pseudo period of 1.
|
|
*/
|
|
he = __hists__add_branch_entry(&evsel->hists, al, parent,
|
|
&bi[i], 1, 1);
|
|
if (he) {
|
|
struct annotation *notes;
|
|
bx = he->branch_info;
|
|
if (bx->from.sym && use_browser == 1 && sort__has_sym) {
|
|
notes = symbol__annotation(bx->from.sym);
|
|
if (!notes->src
|
|
&& symbol__alloc_hist(bx->from.sym) < 0)
|
|
goto out;
|
|
|
|
err = symbol__inc_addr_samples(bx->from.sym,
|
|
bx->from.map,
|
|
evsel->idx,
|
|
bx->from.al_addr);
|
|
if (err)
|
|
goto out;
|
|
}
|
|
|
|
if (bx->to.sym && use_browser == 1 && sort__has_sym) {
|
|
notes = symbol__annotation(bx->to.sym);
|
|
if (!notes->src
|
|
&& symbol__alloc_hist(bx->to.sym) < 0)
|
|
goto out;
|
|
|
|
err = symbol__inc_addr_samples(bx->to.sym,
|
|
bx->to.map,
|
|
evsel->idx,
|
|
bx->to.al_addr);
|
|
if (err)
|
|
goto out;
|
|
}
|
|
evsel->hists.stats.total_period += 1;
|
|
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
|
|
} else
|
|
goto out;
|
|
}
|
|
err = 0;
|
|
out:
|
|
free(bi);
|
|
return err;
|
|
}
|
|
|
|
static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
|
|
struct addr_location *al,
|
|
struct perf_sample *sample,
|
|
struct machine *machine)
|
|
{
|
|
struct symbol *parent = NULL;
|
|
int err = 0;
|
|
struct hist_entry *he;
|
|
|
|
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
|
|
err = machine__resolve_callchain(machine, evsel, al->thread,
|
|
sample, &parent, al);
|
|
if (err)
|
|
return err;
|
|
}
|
|
|
|
he = __hists__add_entry(&evsel->hists, al, parent, sample->period,
|
|
sample->weight, sample->transaction);
|
|
if (he == NULL)
|
|
return -ENOMEM;
|
|
|
|
if (symbol_conf.use_callchain) {
|
|
err = callchain_append(he->callchain,
|
|
&callchain_cursor,
|
|
sample->period);
|
|
if (err)
|
|
return err;
|
|
}
|
|
/*
|
|
* Only in the TUI browser we are doing integrated annotation,
|
|
* so we don't allocated the extra space needed because the stdio
|
|
* code will not use it.
|
|
*/
|
|
if (he->ms.sym != NULL && use_browser == 1 && sort__has_sym) {
|
|
struct annotation *notes = symbol__annotation(he->ms.sym);
|
|
|
|
assert(evsel != NULL);
|
|
|
|
err = -ENOMEM;
|
|
if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
|
|
goto out;
|
|
|
|
err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
|
|
}
|
|
|
|
evsel->hists.stats.total_period += sample->period;
|
|
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
|
|
static int process_sample_event(struct perf_tool *tool,
|
|
union perf_event *event,
|
|
struct perf_sample *sample,
|
|
struct perf_evsel *evsel,
|
|
struct machine *machine)
|
|
{
|
|
struct perf_report *rep = container_of(tool, struct perf_report, tool);
|
|
struct addr_location al;
|
|
int ret;
|
|
|
|
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
|
|
fprintf(stderr, "problem processing %d event, skipping it.\n",
|
|
event->header.type);
|
|
return -1;
|
|
}
|
|
|
|
if (al.filtered || (rep->hide_unresolved && al.sym == NULL))
|
|
return 0;
|
|
|
|
if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
|
|
return 0;
|
|
|
|
if (sort__mode == SORT_MODE__BRANCH) {
|
|
ret = perf_report__add_branch_hist_entry(tool, &al, sample,
|
|
evsel, machine);
|
|
if (ret < 0)
|
|
pr_debug("problem adding lbr entry, skipping event\n");
|
|
} else if (rep->mem_mode == 1) {
|
|
ret = perf_report__add_mem_hist_entry(tool, &al, sample,
|
|
evsel, machine, event);
|
|
if (ret < 0)
|
|
pr_debug("problem adding mem entry, skipping event\n");
|
|
} else {
|
|
if (al.map != NULL)
|
|
al.map->dso->hit = 1;
|
|
|
|
ret = perf_evsel__add_hist_entry(evsel, &al, sample, machine);
|
|
if (ret < 0)
|
|
pr_debug("problem incrementing symbol period, skipping event\n");
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
static int process_read_event(struct perf_tool *tool,
|
|
union perf_event *event,
|
|
struct perf_sample *sample __maybe_unused,
|
|
struct perf_evsel *evsel,
|
|
struct machine *machine __maybe_unused)
|
|
{
|
|
struct perf_report *rep = container_of(tool, struct perf_report, tool);
|
|
|
|
if (rep->show_threads) {
|
|
const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
|
|
perf_read_values_add_value(&rep->show_threads_values,
|
|
event->read.pid, event->read.tid,
|
|
event->read.id,
|
|
name,
|
|
event->read.value);
|
|
}
|
|
|
|
dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
|
|
evsel ? perf_evsel__name(evsel) : "FAIL",
|
|
event->read.value);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* For pipe mode, sample_type is not currently set */
|
|
static int perf_report__setup_sample_type(struct perf_report *rep)
|
|
{
|
|
struct perf_session *self = rep->session;
|
|
u64 sample_type = perf_evlist__combined_sample_type(self->evlist);
|
|
|
|
if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
|
|
if (sort__has_parent) {
|
|
ui__error("Selected --sort parent, but no "
|
|
"callchain data. Did you call "
|
|
"'perf record' without -g?\n");
|
|
return -EINVAL;
|
|
}
|
|
if (symbol_conf.use_callchain) {
|
|
ui__error("Selected -g but no callchain data. Did "
|
|
"you call 'perf record' without -g?\n");
|
|
return -1;
|
|
}
|
|
} else if (!rep->dont_use_callchains &&
|
|
callchain_param.mode != CHAIN_NONE &&
|
|
!symbol_conf.use_callchain) {
|
|
symbol_conf.use_callchain = true;
|
|
if (callchain_register_param(&callchain_param) < 0) {
|
|
ui__error("Can't register callchain params.\n");
|
|
return -EINVAL;
|
|
}
|
|
}
|
|
|
|
if (sort__mode == SORT_MODE__BRANCH) {
|
|
if (!self->fd_pipe &&
|
|
!(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
|
|
ui__error("Selected -b but no branch data. "
|
|
"Did you call perf record without -b?\n");
|
|
return -1;
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void sig_handler(int sig __maybe_unused)
|
|
{
|
|
session_done = 1;
|
|
}
|
|
|
|
static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
|
|
struct hists *self,
|
|
const char *evname, FILE *fp)
|
|
{
|
|
size_t ret;
|
|
char unit;
|
|
unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE];
|
|
u64 nr_events = self->stats.total_period;
|
|
struct perf_evsel *evsel = hists_to_evsel(self);
|
|
char buf[512];
|
|
size_t size = sizeof(buf);
|
|
|
|
if (perf_evsel__is_group_event(evsel)) {
|
|
struct perf_evsel *pos;
|
|
|
|
perf_evsel__group_desc(evsel, buf, size);
|
|
evname = buf;
|
|
|
|
for_each_group_member(pos, evsel) {
|
|
nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
|
|
nr_events += pos->hists.stats.total_period;
|
|
}
|
|
}
|
|
|
|
nr_samples = convert_unit(nr_samples, &unit);
|
|
ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit);
|
|
if (evname != NULL)
|
|
ret += fprintf(fp, " of event '%s'", evname);
|
|
|
|
if (rep->mem_mode) {
|
|
ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events);
|
|
ret += fprintf(fp, "\n# Sort order : %s", sort_order);
|
|
} else
|
|
ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
|
|
return ret + fprintf(fp, "\n#\n");
|
|
}
|
|
|
|
static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
|
|
struct perf_report *rep,
|
|
const char *help)
|
|
{
|
|
struct perf_evsel *pos;
|
|
|
|
list_for_each_entry(pos, &evlist->entries, node) {
|
|
struct hists *hists = &pos->hists;
|
|
const char *evname = perf_evsel__name(pos);
|
|
|
|
if (symbol_conf.event_group &&
|
|
!perf_evsel__is_group_leader(pos))
|
|
continue;
|
|
|
|
hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
|
|
hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
|
|
fprintf(stdout, "\n\n");
|
|
}
|
|
|
|
if (sort_order == default_sort_order &&
|
|
parent_pattern == default_parent_pattern) {
|
|
fprintf(stdout, "#\n# (%s)\n#\n", help);
|
|
|
|
if (rep->show_threads) {
|
|
bool style = !strcmp(rep->pretty_printing_style, "raw");
|
|
perf_read_values_display(stdout, &rep->show_threads_values,
|
|
style);
|
|
perf_read_values_destroy(&rep->show_threads_values);
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int __cmd_report(struct perf_report *rep)
|
|
{
|
|
int ret = -EINVAL;
|
|
u64 nr_samples;
|
|
struct perf_session *session = rep->session;
|
|
struct perf_evsel *pos;
|
|
struct map *kernel_map;
|
|
struct kmap *kernel_kmap;
|
|
const char *help = "For a higher level overview, try: perf report --sort comm,dso";
|
|
|
|
signal(SIGINT, sig_handler);
|
|
|
|
if (rep->cpu_list) {
|
|
ret = perf_session__cpu_bitmap(session, rep->cpu_list,
|
|
rep->cpu_bitmap);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
|
|
if (use_browser <= 0)
|
|
perf_session__fprintf_info(session, stdout, rep->show_full_info);
|
|
|
|
if (rep->show_threads)
|
|
perf_read_values_init(&rep->show_threads_values);
|
|
|
|
ret = perf_report__setup_sample_type(rep);
|
|
if (ret)
|
|
return ret;
|
|
|
|
ret = perf_session__process_events(session, &rep->tool);
|
|
if (ret)
|
|
return ret;
|
|
|
|
kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION];
|
|
kernel_kmap = map__kmap(kernel_map);
|
|
if (kernel_map == NULL ||
|
|
(kernel_map->dso->hit &&
|
|
(kernel_kmap->ref_reloc_sym == NULL ||
|
|
kernel_kmap->ref_reloc_sym->addr == 0))) {
|
|
const char *desc =
|
|
"As no suitable kallsyms nor vmlinux was found, kernel samples\n"
|
|
"can't be resolved.";
|
|
|
|
if (kernel_map) {
|
|
const struct dso *kdso = kernel_map->dso;
|
|
if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
|
|
desc = "If some relocation was applied (e.g. "
|
|
"kexec) symbols may be misresolved.";
|
|
}
|
|
}
|
|
|
|
ui__warning(
|
|
"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
|
|
"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
|
|
"Samples in kernel modules can't be resolved as well.\n\n",
|
|
desc);
|
|
}
|
|
|
|
if (verbose > 3)
|
|
perf_session__fprintf(session, stdout);
|
|
|
|
if (verbose > 2)
|
|
perf_session__fprintf_dsos(session, stdout);
|
|
|
|
if (dump_trace) {
|
|
perf_session__fprintf_nr_events(session, stdout);
|
|
return 0;
|
|
}
|
|
|
|
nr_samples = 0;
|
|
list_for_each_entry(pos, &session->evlist->entries, node) {
|
|
struct hists *hists = &pos->hists;
|
|
|
|
if (pos->idx == 0)
|
|
hists->symbol_filter_str = rep->symbol_filter_str;
|
|
|
|
hists__collapse_resort(hists);
|
|
nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
|
|
|
|
/* Non-group events are considered as leader */
|
|
if (symbol_conf.event_group &&
|
|
!perf_evsel__is_group_leader(pos)) {
|
|
struct hists *leader_hists = &pos->leader->hists;
|
|
|
|
hists__match(leader_hists, hists);
|
|
hists__link(leader_hists, hists);
|
|
}
|
|
}
|
|
|
|
if (session_done())
|
|
return 0;
|
|
|
|
if (nr_samples == 0) {
|
|
ui__error("The %s file has no samples!\n", session->filename);
|
|
return 0;
|
|
}
|
|
|
|
list_for_each_entry(pos, &session->evlist->entries, node)
|
|
hists__output_resort(&pos->hists);
|
|
|
|
if (use_browser > 0) {
|
|
if (use_browser == 1) {
|
|
ret = perf_evlist__tui_browse_hists(session->evlist,
|
|
help, NULL,
|
|
rep->min_percent,
|
|
&session->header.env);
|
|
/*
|
|
* Usually "ret" is the last pressed key, and we only
|
|
* care if the key notifies us to switch data file.
|
|
*/
|
|
if (ret != K_SWITCH_INPUT_DATA)
|
|
ret = 0;
|
|
|
|
} else if (use_browser == 2) {
|
|
int (*hist_browser)(struct perf_evlist *,
|
|
const char *,
|
|
struct hist_browser_timer *,
|
|
float min_pcnt);
|
|
|
|
hist_browser = dlsym(perf_gtk_handle,
|
|
"perf_evlist__gtk_browse_hists");
|
|
if (hist_browser == NULL) {
|
|
ui__error("GTK browser not found!\n");
|
|
return ret;
|
|
}
|
|
hist_browser(session->evlist, help, NULL,
|
|
rep->min_percent);
|
|
}
|
|
} else
|
|
perf_evlist__tty_browse_hists(session->evlist, rep, help);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int
|
|
parse_callchain_opt(const struct option *opt, const char *arg, int unset)
|
|
{
|
|
struct perf_report *rep = (struct perf_report *)opt->value;
|
|
char *tok, *tok2;
|
|
char *endptr;
|
|
|
|
/*
|
|
* --no-call-graph
|
|
*/
|
|
if (unset) {
|
|
rep->dont_use_callchains = true;
|
|
return 0;
|
|
}
|
|
|
|
symbol_conf.use_callchain = true;
|
|
|
|
if (!arg)
|
|
return 0;
|
|
|
|
tok = strtok((char *)arg, ",");
|
|
if (!tok)
|
|
return -1;
|
|
|
|
/* get the output mode */
|
|
if (!strncmp(tok, "graph", strlen(arg)))
|
|
callchain_param.mode = CHAIN_GRAPH_ABS;
|
|
|
|
else if (!strncmp(tok, "flat", strlen(arg)))
|
|
callchain_param.mode = CHAIN_FLAT;
|
|
|
|
else if (!strncmp(tok, "fractal", strlen(arg)))
|
|
callchain_param.mode = CHAIN_GRAPH_REL;
|
|
|
|
else if (!strncmp(tok, "none", strlen(arg))) {
|
|
callchain_param.mode = CHAIN_NONE;
|
|
symbol_conf.use_callchain = false;
|
|
|
|
return 0;
|
|
}
|
|
|
|
else
|
|
return -1;
|
|
|
|
/* get the min percentage */
|
|
tok = strtok(NULL, ",");
|
|
if (!tok)
|
|
goto setup;
|
|
|
|
callchain_param.min_percent = strtod(tok, &endptr);
|
|
if (tok == endptr)
|
|
return -1;
|
|
|
|
/* get the print limit */
|
|
tok2 = strtok(NULL, ",");
|
|
if (!tok2)
|
|
goto setup;
|
|
|
|
if (tok2[0] != 'c') {
|
|
callchain_param.print_limit = strtoul(tok2, &endptr, 0);
|
|
tok2 = strtok(NULL, ",");
|
|
if (!tok2)
|
|
goto setup;
|
|
}
|
|
|
|
/* get the call chain order */
|
|
if (!strncmp(tok2, "caller", strlen("caller")))
|
|
callchain_param.order = ORDER_CALLER;
|
|
else if (!strncmp(tok2, "callee", strlen("callee")))
|
|
callchain_param.order = ORDER_CALLEE;
|
|
else
|
|
return -1;
|
|
|
|
/* Get the sort key */
|
|
tok2 = strtok(NULL, ",");
|
|
if (!tok2)
|
|
goto setup;
|
|
if (!strncmp(tok2, "function", strlen("function")))
|
|
callchain_param.key = CCKEY_FUNCTION;
|
|
else if (!strncmp(tok2, "address", strlen("address")))
|
|
callchain_param.key = CCKEY_ADDRESS;
|
|
else
|
|
return -1;
|
|
setup:
|
|
if (callchain_register_param(&callchain_param) < 0) {
|
|
fprintf(stderr, "Can't register callchain params\n");
|
|
return -1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
int
|
|
report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
|
|
const char *arg, int unset __maybe_unused)
|
|
{
|
|
if (arg) {
|
|
int err = regcomp(&ignore_callees_regex, arg, REG_EXTENDED);
|
|
if (err) {
|
|
char buf[BUFSIZ];
|
|
regerror(err, &ignore_callees_regex, buf, sizeof(buf));
|
|
pr_err("Invalid --ignore-callees regex: %s\n%s", arg, buf);
|
|
return -1;
|
|
}
|
|
have_ignore_callees = 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
parse_branch_mode(const struct option *opt __maybe_unused,
|
|
const char *str __maybe_unused, int unset)
|
|
{
|
|
int *branch_mode = opt->value;
|
|
|
|
*branch_mode = !unset;
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
parse_percent_limit(const struct option *opt, const char *str,
|
|
int unset __maybe_unused)
|
|
{
|
|
struct perf_report *rep = opt->value;
|
|
|
|
rep->min_percent = strtof(str, NULL);
|
|
return 0;
|
|
}
|
|
|
|
int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
|
|
{
|
|
struct perf_session *session;
|
|
struct stat st;
|
|
bool has_br_stack = false;
|
|
int branch_mode = -1;
|
|
int ret = -1;
|
|
char callchain_default_opt[] = "fractal,0.5,callee";
|
|
const char * const report_usage[] = {
|
|
"perf report [<options>]",
|
|
NULL
|
|
};
|
|
struct perf_report report = {
|
|
.tool = {
|
|
.sample = process_sample_event,
|
|
.mmap = perf_event__process_mmap,
|
|
.mmap2 = perf_event__process_mmap2,
|
|
.comm = perf_event__process_comm,
|
|
.exit = perf_event__process_exit,
|
|
.fork = perf_event__process_fork,
|
|
.lost = perf_event__process_lost,
|
|
.read = process_read_event,
|
|
.attr = perf_event__process_attr,
|
|
.tracing_data = perf_event__process_tracing_data,
|
|
.build_id = perf_event__process_build_id,
|
|
.ordered_samples = true,
|
|
.ordering_requires_timestamps = true,
|
|
},
|
|
.pretty_printing_style = "normal",
|
|
};
|
|
const struct option options[] = {
|
|
OPT_STRING('i', "input", &input_name, "file",
|
|
"input file name"),
|
|
OPT_INCR('v', "verbose", &verbose,
|
|
"be more verbose (show symbol address, etc)"),
|
|
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
|
|
"dump raw trace in ASCII"),
|
|
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
|
|
"file", "vmlinux pathname"),
|
|
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
|
|
"file", "kallsyms pathname"),
|
|
OPT_BOOLEAN('f', "force", &report.force, "don't complain, do it"),
|
|
OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
|
|
"load module symbols - WARNING: use only with -k and LIVE kernel"),
|
|
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
|
|
"Show a column with the number of samples"),
|
|
OPT_BOOLEAN('T', "threads", &report.show_threads,
|
|
"Show per-thread event counters"),
|
|
OPT_STRING(0, "pretty", &report.pretty_printing_style, "key",
|
|
"pretty printing style key: normal raw"),
|
|
OPT_BOOLEAN(0, "tui", &report.use_tui, "Use the TUI interface"),
|
|
OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
|
|
OPT_BOOLEAN(0, "stdio", &report.use_stdio,
|
|
"Use the stdio interface"),
|
|
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
|
|
"sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
|
|
" dso_to, dso_from, symbol_to, symbol_from, mispredict,"
|
|
" weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, "
|
|
"snoop, locked, abort, in_tx, transaction"),
|
|
OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
|
|
"Show sample percentage for different cpu modes"),
|
|
OPT_STRING('p', "parent", &parent_pattern, "regex",
|
|
"regex filter to identify parent, see: '--sort parent'"),
|
|
OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
|
|
"Only display entries with parent-match"),
|
|
OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
|
|
"Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
|
|
"Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
|
|
OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
|
|
"alias for inverted call graph"),
|
|
OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
|
|
"ignore callees of these functions in call graphs",
|
|
report_parse_ignore_callees_opt),
|
|
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
|
|
"only consider symbols in these dsos"),
|
|
OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
|
|
"only consider symbols in these comms"),
|
|
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
|
|
"only consider these symbols"),
|
|
OPT_STRING(0, "symbol-filter", &report.symbol_filter_str, "filter",
|
|
"only show symbols that (partially) match with this filter"),
|
|
OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
|
|
"width[,width...]",
|
|
"don't try to adjust column width, use these fixed values"),
|
|
OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
|
|
"separator for columns, no spaces will be added between "
|
|
"columns '.' is reserved."),
|
|
OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved,
|
|
"Only display entries resolved to a symbol"),
|
|
OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
|
|
"Look for files with symbols relative to this directory"),
|
|
OPT_STRING('C', "cpu", &report.cpu_list, "cpu",
|
|
"list of cpus to profile"),
|
|
OPT_BOOLEAN('I', "show-info", &report.show_full_info,
|
|
"Display extended information about perf.data file"),
|
|
OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
|
|
"Interleave source code with assembly code (default)"),
|
|
OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
|
|
"Display raw encoding of assembly instructions (default)"),
|
|
OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
|
|
"Specify disassembler style (e.g. -M intel for intel syntax)"),
|
|
OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
|
|
"Show a column with the sum of periods"),
|
|
OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
|
|
"Show event group information together"),
|
|
OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
|
|
"use branch records for histogram filling", parse_branch_mode),
|
|
OPT_STRING(0, "objdump", &objdump_path, "path",
|
|
"objdump binary to use for disassembly and annotations"),
|
|
OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
|
|
"Disable symbol demangling"),
|
|
OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
|
|
OPT_CALLBACK(0, "percent-limit", &report, "percent",
|
|
"Don't show entries under that percent", parse_percent_limit),
|
|
OPT_END()
|
|
};
|
|
struct perf_data_file file = {
|
|
.mode = PERF_DATA_MODE_READ,
|
|
};
|
|
|
|
perf_config(perf_report_config, &report);
|
|
|
|
argc = parse_options(argc, argv, options, report_usage, 0);
|
|
|
|
if (report.use_stdio)
|
|
use_browser = 0;
|
|
else if (report.use_tui)
|
|
use_browser = 1;
|
|
else if (report.use_gtk)
|
|
use_browser = 2;
|
|
|
|
if (report.inverted_callchain)
|
|
callchain_param.order = ORDER_CALLER;
|
|
|
|
if (!input_name || !strlen(input_name)) {
|
|
if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
|
|
input_name = "-";
|
|
else
|
|
input_name = "perf.data";
|
|
}
|
|
|
|
if (strcmp(input_name, "-") != 0)
|
|
setup_browser(true);
|
|
else {
|
|
use_browser = 0;
|
|
perf_hpp__init();
|
|
}
|
|
|
|
file.path = input_name;
|
|
file.force = report.force;
|
|
|
|
repeat:
|
|
session = perf_session__new(&file, false, &report.tool);
|
|
if (session == NULL)
|
|
return -ENOMEM;
|
|
|
|
report.session = session;
|
|
|
|
has_br_stack = perf_header__has_feat(&session->header,
|
|
HEADER_BRANCH_STACK);
|
|
|
|
if (branch_mode == -1 && has_br_stack)
|
|
sort__mode = SORT_MODE__BRANCH;
|
|
|
|
/* sort__mode could be NORMAL if --no-branch-stack */
|
|
if (sort__mode == SORT_MODE__BRANCH) {
|
|
/*
|
|
* if no sort_order is provided, then specify
|
|
* branch-mode specific order
|
|
*/
|
|
if (sort_order == default_sort_order)
|
|
sort_order = "comm,dso_from,symbol_from,"
|
|
"dso_to,symbol_to";
|
|
|
|
}
|
|
if (report.mem_mode) {
|
|
if (sort__mode == SORT_MODE__BRANCH) {
|
|
fprintf(stderr, "branch and mem mode incompatible\n");
|
|
goto error;
|
|
}
|
|
sort__mode = SORT_MODE__MEMORY;
|
|
|
|
/*
|
|
* if no sort_order is provided, then specify
|
|
* branch-mode specific order
|
|
*/
|
|
if (sort_order == default_sort_order)
|
|
sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
|
|
}
|
|
|
|
if (setup_sorting() < 0)
|
|
usage_with_options(report_usage, options);
|
|
|
|
/*
|
|
* Only in the TUI browser we are doing integrated annotation,
|
|
* so don't allocate extra space that won't be used in the stdio
|
|
* implementation.
|
|
*/
|
|
if (use_browser == 1 && sort__has_sym) {
|
|
symbol_conf.priv_size = sizeof(struct annotation);
|
|
machines__set_symbol_filter(&session->machines,
|
|
symbol__annotate_init);
|
|
/*
|
|
* For searching by name on the "Browse map details".
|
|
* providing it only in verbose mode not to bloat too
|
|
* much struct symbol.
|
|
*/
|
|
if (verbose) {
|
|
/*
|
|
* XXX: Need to provide a less kludgy way to ask for
|
|
* more space per symbol, the u32 is for the index on
|
|
* the ui browser.
|
|
* See symbol__browser_index.
|
|
*/
|
|
symbol_conf.priv_size += sizeof(u32);
|
|
symbol_conf.sort_by_name = true;
|
|
}
|
|
}
|
|
|
|
if (symbol__init() < 0)
|
|
goto error;
|
|
|
|
if (parent_pattern != default_parent_pattern) {
|
|
if (sort_dimension__add("parent") < 0)
|
|
goto error;
|
|
}
|
|
|
|
if (argc) {
|
|
/*
|
|
* Special case: if there's an argument left then assume that
|
|
* it's a symbol filter:
|
|
*/
|
|
if (argc > 1)
|
|
usage_with_options(report_usage, options);
|
|
|
|
report.symbol_filter_str = argv[0];
|
|
}
|
|
|
|
sort__setup_elide(stdout);
|
|
|
|
ret = __cmd_report(&report);
|
|
if (ret == K_SWITCH_INPUT_DATA) {
|
|
perf_session__delete(session);
|
|
goto repeat;
|
|
} else
|
|
ret = 0;
|
|
|
|
error:
|
|
perf_session__delete(session);
|
|
return ret;
|
|
}
|